// SPDX-License-Identifier: GPL-2.0-only
#include <linux/interval_tree.h>
#include <linux/interval_tree_generic.h>
#include <linux/compiler.h>
#include <linux/export.h>
#define START(node) ((node)->start)
#define LAST(node) ((node)->last)
INTERVAL_TREE_DEFINE(struct interval_tree_node, rb,
unsigned long, __subtree_last,
START, LAST,, interval_tree)
EXPORT_SYMBOL_GPL(interval_tree_insert);
EXPORT_SYMBOL_GPL(interval_tree_remove);
EXPORT_SYMBOL_GPL(interval_tree_iter_first);
EXPORT_SYMBOL_GPL(interval_tree_iter_next);
#ifdef CONFIG_INTERVAL_TREE_SPAN_ITER
/*
* Roll nodes[1] into nodes[0] by advancing nodes[1] to the end of a contiguous
* span of nodes. This makes nodes[0]->last the end of that contiguous used span
* of indexes that started at the original nodes[1]->start.
*
* If there is an interior hole, nodes[1] is now the first node starting the
* next used span. A hole span is between nodes[0]->last and nodes[1]->start.
*
* If there is a tailing hole, nodes[1] is now NULL. A hole span is between
* nodes[0]->last and last_index.
*
* If the contiguous used range span to last_index, nodes[1] is set to NULL.
*/
static void
interval_tree_span_iter_next_gap(struct interval_tree_span_iter *state)
{
struct interval_tree_node *cur = state->nodes[1];
state->nodes[0] = cur;
do {
if (cur->last > state->nodes[0]->last)
state->nodes[0] = cur;
cur = interval_tree_iter_next(cur, state->first_index,
state->last_index);
} while (cur && (state->nodes[0]->last >= cur->start ||
state->nodes[0]->last + 1 == cur->start));
state->nodes[1] = cur;
}
void interval_tree_span_iter_first(struct interval_tree_span_iter *iter,
struct rb_root_cached *itree,
unsigned long first_index,
unsigned long last_index)
{
iter->first_index = first_index;
iter->last_index = last_index;
iter->nodes[0] = NULL;
iter->nodes[1] =
interval_tree_iter_first(itree, first_index, last_index);
if (!iter->nodes[1]) {
/* No nodes intersect the span, whole span is hole */
iter->start_hole = first_index;
iter->last_hole = last_index;
iter->is_hole = 1;
return;
}
if (iter->nodes[1]->start > first_index) {
/* Leading hole on first iteration */
iter->start_hole = first_index;
iter->last_hole = iter->nodes[1]->start - 1;
iter->is_hole = 1;
interval_tree_span_iter_next_gap(iter);
return;
}
/* Starting inside a used */
iter->start_used = first_index;
iter->is_hole = 0;
interval_tree_span_iter_next_gap(iter);
iter->last_used = iter->nodes[0]->last;
if (iter->last_used >= last_index) {
iter->last_used = last_index;
iter->nodes[0] = NULL;
iter->nodes[1] = NULL;
}
}
EXPORT_SYMBOL_GPL(interval_tree_span_iter_first);
void interval_tree_span_iter_next(struct interval_tree_span_iter *iter)
{
if (!iter->nodes[0] && !iter->nodes[1]) {
iter->is_hole = -1;
return;
}
if (iter->is_hole) {
iter->start_used = iter->last_hole + 1;
iter->last_used = iter->nodes[0]->last;
if (iter->last_used >= iter->last_index) {
iter->last_used = iter->last_index;
iter->nodes[0] = NULL;
iter->nodes[1] = NULL;
}
iter->is_hole = 0;
return;
}
if (!iter->nodes[1]) {
/* Trailing hole */
iter->start_hole = iter->nodes[0]->last + 1;
iter->last_hole = iter->last_index;
iter->nodes[0] = NULL;
iter->is_hole = 1;
return;
}
/* must have both nodes[0] and [1], interior hole */
iter->start_hole = iter->nodes[0]->last + 1;
iter->last_hole = iter->nodes[1]->start - 1;
iter->is_hole = 1;
interval_tree_span_iter_next_gap(iter);
}
EXPORT_SYMBOL_GPL(interval_tree_span_iter_next);
/*
* Advance the iterator index to a specific position. The returned used/hole is
* updated to start at new_index. This is faster than calling
* interval_tree_span_iter_first() as it can avoid full searches in several
* cases where the iterator is already set.
*/
void interval_tree_span_iter_advance(struct interval_tree_span_iter *iter,
struct rb_root_cached *itree,
unsigned long new_index)
{
if (iter->is_hole == -1)
return;
iter->first_index = new_index;
if (new_index > iter->last_index) {
iter->is_hole = -1;
return;
}
/* Rely on the union aliasing hole/used */
if (iter->start_hole <= new_index && new_index <= iter->last_hole) {
iter->start_hole = new_index;
return;
}
if (new_index == iter->last_hole + 1)
interval_tree_span_iter_next(iter);
else
interval_tree_span_iter_first(iter, itree, new_index,
iter->last_index);
}
EXPORT_SYMBOL_GPL(interval_tree_span_iter_advance);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM signal
#if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_SIGNAL_H
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/tracepoint.h>
#define TP_STORE_SIGINFO(__entry, info) \
do { \
if (info == SEND_SIG_NOINFO) { \
__entry->errno = 0; \
__entry->code = SI_USER; \
} else if (info == SEND_SIG_PRIV) { \
__entry->errno = 0; \
__entry->code = SI_KERNEL; \
} else { \
__entry->errno = info->si_errno; \
__entry->code = info->si_code; \
} \
} while (0)
#ifndef TRACE_HEADER_MULTI_READ
enum {
TRACE_SIGNAL_DELIVERED,
TRACE_SIGNAL_IGNORED,
TRACE_SIGNAL_ALREADY_PENDING,
TRACE_SIGNAL_OVERFLOW_FAIL,
TRACE_SIGNAL_LOSE_INFO,
};
#endif
/**
* signal_generate - called when a signal is generated
* @sig: signal number
* @info: pointer to struct siginfo
* @task: pointer to struct task_struct
* @group: shared or private
* @result: TRACE_SIGNAL_*
*
* Current process sends a 'sig' signal to 'task' process with
* 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV,
* 'info' is not a pointer and you can't access its field. Instead,
* SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV
* means that si_code is SI_KERNEL.
*/
TRACE_EVENT(signal_generate,
TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task,
int group, int result),
TP_ARGS(sig, info, task, group, result),
TP_STRUCT__entry(
__field( int, sig )
__field( int, errno )
__field( int, code )
__array( char, comm, TASK_COMM_LEN )
__field( pid_t, pid )
__field( int, group )
__field( int, result )
),
TP_fast_assign(
__entry->sig = sig;
TP_STORE_SIGINFO(__entry, info);
memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
__entry->pid = task->pid;
__entry->group = group;
__entry->result = result;
),
TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d",
__entry->sig, __entry->errno, __entry->code,
__entry->comm, __entry->pid, __entry->group,
__entry->result)
);
/**
* signal_deliver - called when a signal is delivered
* @sig: signal number
* @info: pointer to struct siginfo
* @ka: pointer to struct k_sigaction
*
* A 'sig' signal is delivered to current process with 'info' siginfo,
* and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or
* SIG_DFL.
* Note that some signals reported by signal_generate tracepoint can be
* lost, ignored or modified (by debugger) before hitting this tracepoint.
* This means, this can show which signals are actually delivered, but
* matching generated signals and delivered signals may not be correct.
*/
TRACE_EVENT(signal_deliver,
TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka),
TP_ARGS(sig, info, ka),
TP_STRUCT__entry(
__field( int, sig )
__field( int, errno )
__field( int, code )
__field( unsigned long, sa_handler )
__field( unsigned long, sa_flags )
),
TP_fast_assign(
__entry->sig = sig;
TP_STORE_SIGINFO(__entry, info);
__entry->sa_handler = (unsigned long)ka->sa.sa_handler;
__entry->sa_flags = ka->sa.sa_flags;
),
TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx",
__entry->sig, __entry->errno, __entry->code,
__entry->sa_handler, __entry->sa_flags)
);
#endif /* _TRACE_SIGNAL_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
// SPDX-License-Identifier: GPL-2.0
/* Watch queue and general notification mechanism, built on pipes
*
* Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* See Documentation/core-api/watch_queue.rst
*/
#define pr_fmt(fmt) "watchq: " fmt
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/printk.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/poll.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/file.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/sched/signal.h>
#include <linux/watch_queue.h>
#include <linux/pipe_fs_i.h>
MODULE_DESCRIPTION("Watch queue");
MODULE_AUTHOR("Red Hat, Inc.");
#define WATCH_QUEUE_NOTE_SIZE 128
#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)
/*
* This must be called under the RCU read-lock, which makes
* sure that the wqueue still exists. It can then take the lock,
* and check that the wqueue hasn't been destroyed, which in
* turn makes sure that the notification pipe still exists.
*/
static inline bool lock_wqueue(struct watch_queue *wqueue)
{
spin_lock_bh(&wqueue->lock);
if (unlikely(!wqueue->pipe)) {
spin_unlock_bh(&wqueue->lock);
return false;
}
return true;
}
static inline void unlock_wqueue(struct watch_queue *wqueue)
{
spin_unlock_bh(&wqueue->lock);
}
static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct watch_queue *wqueue = (struct watch_queue *)buf->private;
struct page *page;
unsigned int bit;
/* We need to work out which note within the page this refers to, but
* the note might have been maximum size, so merely ANDing the offset
* off doesn't work. OTOH, the note must've been more than zero size.
*/
bit = buf->offset + buf->len;
if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0)
bit -= WATCH_QUEUE_NOTE_SIZE;
bit /= WATCH_QUEUE_NOTE_SIZE;
page = buf->page;
bit += page->private;
set_bit(bit, wqueue->notes_bitmap);
generic_pipe_buf_release(pipe, buf);
}
// No try_steal function => no stealing
#define watch_queue_pipe_buf_try_steal NULL
/* New data written to a pipe may be appended to a buffer with this type. */
static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
.release = watch_queue_pipe_buf_release,
.try_steal = watch_queue_pipe_buf_try_steal,
.get = generic_pipe_buf_get,
};
/*
* Post a notification to a watch queue.
*
* Must be called with the RCU lock for reading, and the
* watch_queue lock held, which guarantees that the pipe
* hasn't been released.
*/
static bool post_one_notification(struct watch_queue *wqueue,
struct watch_notification *n)
{
void *p;
struct pipe_inode_info *pipe = wqueue->pipe;
struct pipe_buffer *buf;
struct page *page;
unsigned int head, tail, note, offset, len;
bool done = false;
spin_lock_irq(&pipe->rd_wait.lock);
head = pipe->head;
tail = pipe->tail;
if (pipe_full(head, tail, pipe->ring_size))
goto lost;
note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes);
if (note >= wqueue->nr_notes)
goto lost;
page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE];
offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE;
get_page(page);
len = n->info & WATCH_INFO_LENGTH;
p = kmap_atomic(page);
memcpy(p + offset, n, len);
kunmap_atomic(p);
buf = pipe_buf(pipe, head);
buf->page = page;
buf->private = (unsigned long)wqueue;
buf->ops = &watch_queue_pipe_buf_ops;
buf->offset = offset;
buf->len = len;
buf->flags = PIPE_BUF_FLAG_WHOLE;
smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */
if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
spin_unlock_irq(&pipe->rd_wait.lock);
BUG();
}
wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
done = true;
out:
spin_unlock_irq(&pipe->rd_wait.lock);
if (done)
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
return done;
lost:
buf = pipe_buf(pipe, head - 1);
buf->flags |= PIPE_BUF_FLAG_LOSS;
goto out;
}
/*
* Apply filter rules to a notification.
*/
static bool filter_watch_notification(const struct watch_filter *wf,
const struct watch_notification *n)
{
const struct watch_type_filter *wt;
unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8;
unsigned int st_index = n->subtype / st_bits;
unsigned int st_bit = 1U << (n->subtype % st_bits);
int i;
if (!test_bit(n->type, wf->type_filter))
return false;
for (i = 0; i < wf->nr_filters; i++) {
wt = &wf->filters[i];
if (n->type == wt->type &&
(wt->subtype_filter[st_index] & st_bit) &&
(n->info & wt->info_mask) == wt->info_filter)
return true;
}
return false; /* If there is a filter, the default is to reject. */
}
/**
* __post_watch_notification - Post an event notification
* @wlist: The watch list to post the event to.
* @n: The notification record to post.
* @cred: The creds of the process that triggered the notification.
* @id: The ID to match on the watch.
*
* Post a notification of an event into a set of watch queues and let the users
* know.
*
* The size of the notification should be set in n->info & WATCH_INFO_LENGTH and
* should be in units of sizeof(*n).
*/
void __post_watch_notification(struct watch_list *wlist,
struct watch_notification *n,
const struct cred *cred,
u64 id)
{
const struct watch_filter *wf;
struct watch_queue *wqueue;
struct watch *watch;
if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) {
WARN_ON(1);
return;
}
rcu_read_lock();
hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) {
if (watch->id != id)
continue;
n->info &= ~WATCH_INFO_ID;
n->info |= watch->info_id;
wqueue = rcu_dereference(watch->queue);
wf = rcu_dereference(wqueue->filter);
if (wf && !filter_watch_notification(wf, n))
continue;
if (security_post_notification(watch->cred, cred, n) < 0)
continue;
if (lock_wqueue(wqueue)) {
post_one_notification(wqueue, n);
unlock_wqueue(wqueue);
}
}
rcu_read_unlock();
}
EXPORT_SYMBOL(__post_watch_notification);
/*
* Allocate sufficient pages to preallocation for the requested number of
* notifications.
*/
long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
{
struct watch_queue *wqueue = pipe->watch_queue;
struct page **pages;
unsigned long *bitmap;
unsigned long user_bufs;
int ret, i, nr_pages;
if (!wqueue)
return -ENODEV;
if (wqueue->notes)
return -EBUSY;
if (nr_notes < 1 ||
nr_notes > 512) /* TODO: choose a better hard limit */
return -EINVAL;
nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1);
nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE;
user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages);
if (nr_pages > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) &&
pipe_is_unprivileged_user()) {
ret = -EPERM;
goto error;
}
nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes));
if (ret < 0)
goto error;
/*
* pipe_resize_ring() does not update nr_accounted for watch_queue
* pipes, because the above vastly overprovisions. Set nr_accounted on
* and max_usage this pipe to the number that was actually charged to
* the user above via account_pipe_buffers.
*/
pipe->max_usage = nr_pages;
pipe->nr_accounted = nr_pages;
ret = -ENOMEM;
pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto error;
for (i = 0; i < nr_pages; i++) {
pages[i] = alloc_page(GFP_KERNEL);
if (!pages[i])
goto error_p;
pages[i]->private = i * WATCH_QUEUE_NOTES_PER_PAGE;
}
bitmap = bitmap_alloc(nr_notes, GFP_KERNEL);
if (!bitmap)
goto error_p;
bitmap_fill(bitmap, nr_notes);
wqueue->notes = pages;
wqueue->notes_bitmap = bitmap;
wqueue->nr_pages = nr_pages;
wqueue->nr_notes = nr_notes;
return 0;
error_p:
while (--i >= 0)
__free_page(pages[i]);
kfree(pages);
error:
(void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted);
return ret;
}
/*
* Set the filter on a watch queue.
*/
long watch_queue_set_filter(struct pipe_inode_info *pipe,
struct watch_notification_filter __user *_filter)
{
struct watch_notification_type_filter *tf;
struct watch_notification_filter filter;
struct watch_type_filter *q;
struct watch_filter *wfilter;
struct watch_queue *wqueue = pipe->watch_queue;
int ret, nr_filter = 0, i;
if (!wqueue)
return -ENODEV;
if (!_filter) {
/* Remove the old filter */
wfilter = NULL;
goto set;
}
/* Grab the user's filter specification */
if (copy_from_user(&filter, _filter, sizeof(filter)) != 0)
return -EFAULT;
if (filter.nr_filters == 0 || filter.nr_filters > 16 ||
filter.__reserved != 0)
return -EINVAL;
tf = memdup_array_user(_filter->filters, filter.nr_filters, sizeof(*tf));
if (IS_ERR(tf))
return PTR_ERR(tf);
ret = -EINVAL;
for (i = 0; i < filter.nr_filters; i++) { if ((tf[i].info_filter & ~tf[i].info_mask) ||
tf[i].info_mask & WATCH_INFO_LENGTH)
goto err_filter;
/* Ignore any unknown types */
if (tf[i].type >= WATCH_TYPE__NR)
continue;
nr_filter++;
}
/* Now we need to build the internal filter from only the relevant
* user-specified filters.
*/
ret = -ENOMEM;
wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL); if (!wfilter)
goto err_filter;
wfilter->nr_filters = nr_filter;
q = wfilter->filters;
for (i = 0; i < filter.nr_filters; i++) { if (tf[i].type >= WATCH_TYPE__NR)
continue;
q->type = tf[i].type;
q->info_filter = tf[i].info_filter;
q->info_mask = tf[i].info_mask;
q->subtype_filter[0] = tf[i].subtype_filter[0];
__set_bit(q->type, wfilter->type_filter);
q++;
}
kfree(tf);
set:
pipe_lock(pipe);
wfilter = rcu_replace_pointer(wqueue->filter, wfilter,
lockdep_is_held(&pipe->mutex));
pipe_unlock(pipe);
if (wfilter) kfree_rcu(wfilter, rcu);
return 0;
err_filter:
kfree(tf);
return ret;
}
static void __put_watch_queue(struct kref *kref)
{
struct watch_queue *wqueue =
container_of(kref, struct watch_queue, usage);
struct watch_filter *wfilter;
int i;
for (i = 0; i < wqueue->nr_pages; i++)
__free_page(wqueue->notes[i]);
kfree(wqueue->notes);
bitmap_free(wqueue->notes_bitmap);
wfilter = rcu_access_pointer(wqueue->filter);
if (wfilter)
kfree_rcu(wfilter, rcu);
kfree_rcu(wqueue, rcu);
}
/**
* put_watch_queue - Dispose of a ref on a watchqueue.
* @wqueue: The watch queue to unref.
*/
void put_watch_queue(struct watch_queue *wqueue)
{
kref_put(&wqueue->usage, __put_watch_queue);
}
EXPORT_SYMBOL(put_watch_queue);
static void free_watch(struct rcu_head *rcu)
{
struct watch *watch = container_of(rcu, struct watch, rcu);
put_watch_queue(rcu_access_pointer(watch->queue));
atomic_dec(&watch->cred->user->nr_watches);
put_cred(watch->cred);
kfree(watch);
}
static void __put_watch(struct kref *kref)
{
struct watch *watch = container_of(kref, struct watch, usage);
call_rcu(&watch->rcu, free_watch);
}
/*
* Discard a watch.
*/
static void put_watch(struct watch *watch)
{
kref_put(&watch->usage, __put_watch);
}
/**
* init_watch - Initialise a watch
* @watch: The watch to initialise.
* @wqueue: The queue to assign.
*
* Initialise a watch and set the watch queue.
*/
void init_watch(struct watch *watch, struct watch_queue *wqueue)
{
kref_init(&watch->usage);
INIT_HLIST_NODE(&watch->list_node);
INIT_HLIST_NODE(&watch->queue_node);
rcu_assign_pointer(watch->queue, wqueue);
}
static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue)
{
const struct cred *cred;
struct watch *w;
hlist_for_each_entry(w, &wlist->watchers, list_node) {
struct watch_queue *wq = rcu_access_pointer(w->queue);
if (wqueue == wq && watch->id == w->id)
return -EBUSY;
}
cred = current_cred();
if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) {
atomic_dec(&cred->user->nr_watches);
return -EAGAIN;
}
watch->cred = get_cred(cred);
rcu_assign_pointer(watch->watch_list, wlist);
kref_get(&wqueue->usage);
kref_get(&watch->usage);
hlist_add_head(&watch->queue_node, &wqueue->watches);
hlist_add_head_rcu(&watch->list_node, &wlist->watchers);
return 0;
}
/**
* add_watch_to_object - Add a watch on an object to a watch list
* @watch: The watch to add
* @wlist: The watch list to add to
*
* @watch->queue must have been set to point to the queue to post notifications
* to and the watch list of the object to be watched. @watch->cred must also
* have been set to the appropriate credentials and a ref taken on them.
*
* The caller must pin the queue and the list both and must hold the list
* locked against racing watch additions/removals.
*/
int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
{
struct watch_queue *wqueue;
int ret = -ENOENT;
rcu_read_lock();
wqueue = rcu_access_pointer(watch->queue);
if (lock_wqueue(wqueue)) {
spin_lock(&wlist->lock);
ret = add_one_watch(watch, wlist, wqueue);
spin_unlock(&wlist->lock);
unlock_wqueue(wqueue);
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(add_watch_to_object);
/**
* remove_watch_from_object - Remove a watch or all watches from an object.
* @wlist: The watch list to remove from
* @wq: The watch queue of interest (ignored if @all is true)
* @id: The ID of the watch to remove (ignored if @all is true)
* @all: True to remove all objects
*
* Remove a specific watch or all watches from an object. A notification is
* sent to the watcher to tell them that this happened.
*/
int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq,
u64 id, bool all)
{
struct watch_notification_removal n;
struct watch_queue *wqueue;
struct watch *watch;
int ret = -EBADSLT;
rcu_read_lock();
again:
spin_lock(&wlist->lock);
hlist_for_each_entry(watch, &wlist->watchers, list_node) {
if (all ||
(watch->id == id && rcu_access_pointer(watch->queue) == wq))
goto found;
}
spin_unlock(&wlist->lock);
goto out;
found:
ret = 0;
hlist_del_init_rcu(&watch->list_node);
rcu_assign_pointer(watch->watch_list, NULL);
spin_unlock(&wlist->lock);
/* We now own the reference on watch that used to belong to wlist. */
n.watch.type = WATCH_TYPE_META;
n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION;
n.watch.info = watch->info_id | watch_sizeof(n.watch);
n.id = id;
if (id != 0)
n.watch.info = watch->info_id | watch_sizeof(n);
wqueue = rcu_dereference(watch->queue);
if (lock_wqueue(wqueue)) {
post_one_notification(wqueue, &n.watch);
if (!hlist_unhashed(&watch->queue_node)) {
hlist_del_init_rcu(&watch->queue_node);
put_watch(watch);
}
unlock_wqueue(wqueue);
}
if (wlist->release_watch) {
void (*release_watch)(struct watch *);
release_watch = wlist->release_watch;
rcu_read_unlock();
(*release_watch)(watch);
rcu_read_lock();
}
put_watch(watch);
if (all && !hlist_empty(&wlist->watchers))
goto again;
out:
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(remove_watch_from_object);
/*
* Remove all the watches that are contributory to a queue. This has the
* potential to race with removal of the watches by the destruction of the
* objects being watched or with the distribution of notifications.
*/
void watch_queue_clear(struct watch_queue *wqueue)
{
struct watch_list *wlist;
struct watch *watch;
bool release;
rcu_read_lock();
spin_lock_bh(&wqueue->lock);
/*
* This pipe can be freed by callers like free_pipe_info().
* Removing this reference also prevents new notifications.
*/
wqueue->pipe = NULL;
while (!hlist_empty(&wqueue->watches)) {
watch = hlist_entry(wqueue->watches.first, struct watch, queue_node);
hlist_del_init_rcu(&watch->queue_node);
/* We now own a ref on the watch. */
spin_unlock_bh(&wqueue->lock);
/* We can't do the next bit under the queue lock as we need to
* get the list lock - which would cause a deadlock if someone
* was removing from the opposite direction at the same time or
* posting a notification.
*/
wlist = rcu_dereference(watch->watch_list);
if (wlist) {
void (*release_watch)(struct watch *);
spin_lock(&wlist->lock);
release = !hlist_unhashed(&watch->list_node);
if (release) {
hlist_del_init_rcu(&watch->list_node);
rcu_assign_pointer(watch->watch_list, NULL);
/* We now own a second ref on the watch. */
}
release_watch = wlist->release_watch;
spin_unlock(&wlist->lock);
if (release) {
if (release_watch) {
rcu_read_unlock();
/* This might need to call dput(), so
* we have to drop all the locks.
*/
(*release_watch)(watch);
rcu_read_lock();
}
put_watch(watch);
}
}
put_watch(watch);
spin_lock_bh(&wqueue->lock);
}
spin_unlock_bh(&wqueue->lock);
rcu_read_unlock();
}
/**
* get_watch_queue - Get a watch queue from its file descriptor.
* @fd: The fd to query.
*/
struct watch_queue *get_watch_queue(int fd)
{
struct pipe_inode_info *pipe;
struct watch_queue *wqueue = ERR_PTR(-EINVAL);
CLASS(fd, f)(fd);
if (!fd_empty(f)) {
pipe = get_pipe_info(fd_file(f), false);
if (pipe && pipe->watch_queue) {
wqueue = pipe->watch_queue;
kref_get(&wqueue->usage);
}
}
return wqueue;
}
EXPORT_SYMBOL(get_watch_queue);
/*
* Initialise a watch queue
*/
int watch_queue_init(struct pipe_inode_info *pipe)
{
struct watch_queue *wqueue;
wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL);
if (!wqueue)
return -ENOMEM;
wqueue->pipe = pipe;
kref_init(&wqueue->usage);
spin_lock_init(&wqueue->lock);
INIT_HLIST_HEAD(&wqueue->watches);
pipe->watch_queue = wqueue;
return 0;
}
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* The Internet Protocol (IP) module.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Richard Underwood
* Stefan Becker, <stefanb@yello.ping.de>
* Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
*
* Fixes:
* Alan Cox : Commented a couple of minor bits of surplus code
* Alan Cox : Undefining IP_FORWARD doesn't include the code
* (just stops a compiler warning).
* Alan Cox : Frames with >=MAX_ROUTE record routes, strict routes or loose routes
* are junked rather than corrupting things.
* Alan Cox : Frames to bad broadcast subnets are dumped
* We used to process them non broadcast and
* boy could that cause havoc.
* Alan Cox : ip_forward sets the free flag on the
* new frame it queues. Still crap because
* it copies the frame but at least it
* doesn't eat memory too.
* Alan Cox : Generic queue code and memory fixes.
* Fred Van Kempen : IP fragment support (borrowed from NET2E)
* Gerhard Koerting: Forward fragmented frames correctly.
* Gerhard Koerting: Fixes to my fix of the above 8-).
* Gerhard Koerting: IP interface addressing fix.
* Linus Torvalds : More robustness checks
* Alan Cox : Even more checks: Still not as robust as it ought to be
* Alan Cox : Save IP header pointer for later
* Alan Cox : ip option setting
* Alan Cox : Use ip_tos/ip_ttl settings
* Alan Cox : Fragmentation bogosity removed
* (Thanks to Mark.Bush@prg.ox.ac.uk)
* Dmitry Gorodchanin : Send of a raw packet crash fix.
* Alan Cox : Silly ip bug when an overlength
* fragment turns up. Now frees the
* queue.
* Linus Torvalds/ : Memory leakage on fragmentation
* Alan Cox : handling.
* Gerhard Koerting: Forwarding uses IP priority hints
* Teemu Rantanen : Fragment problems.
* Alan Cox : General cleanup, comments and reformat
* Alan Cox : SNMP statistics
* Alan Cox : BSD address rule semantics. Also see
* UDP as there is a nasty checksum issue
* if you do things the wrong way.
* Alan Cox : Always defrag, moved IP_FORWARD to the config.in file
* Alan Cox : IP options adjust sk->priority.
* Pedro Roque : Fix mtu/length error in ip_forward.
* Alan Cox : Avoid ip_chk_addr when possible.
* Richard Underwood : IP multicasting.
* Alan Cox : Cleaned up multicast handlers.
* Alan Cox : RAW sockets demultiplex in the BSD style.
* Gunther Mayer : Fix the SNMP reporting typo
* Alan Cox : Always in group 224.0.0.1
* Pauline Middelink : Fast ip_checksum update when forwarding
* Masquerading support.
* Alan Cox : Multicast loopback error for 224.0.0.1
* Alan Cox : IP_MULTICAST_LOOP option.
* Alan Cox : Use notifiers.
* Bjorn Ekwall : Removed ip_csum (from slhc.c too)
* Bjorn Ekwall : Moved ip_fast_csum to ip.h (inline!)
* Stefan Becker : Send out ICMP HOST REDIRECT
* Arnt Gulbrandsen : ip_build_xmit
* Alan Cox : Per socket routing cache
* Alan Cox : Fixed routing cache, added header cache.
* Alan Cox : Loopback didn't work right in original ip_build_xmit - fixed it.
* Alan Cox : Only send ICMP_REDIRECT if src/dest are the same net.
* Alan Cox : Incoming IP option handling.
* Alan Cox : Set saddr on raw output frames as per BSD.
* Alan Cox : Stopped broadcast source route explosions.
* Alan Cox : Can disable source routing
* Takeshi Sone : Masquerading didn't work.
* Dave Bonn,Alan Cox : Faster IP forwarding whenever possible.
* Alan Cox : Memory leaks, tramples, misc debugging.
* Alan Cox : Fixed multicast (by popular demand 8))
* Alan Cox : Fixed forwarding (by even more popular demand 8))
* Alan Cox : Fixed SNMP statistics [I think]
* Gerhard Koerting : IP fragmentation forwarding fix
* Alan Cox : Device lock against page fault.
* Alan Cox : IP_HDRINCL facility.
* Werner Almesberger : Zero fragment bug
* Alan Cox : RAW IP frame length bug
* Alan Cox : Outgoing firewall on build_xmit
* A.N.Kuznetsov : IP_OPTIONS support throughout the kernel
* Alan Cox : Multicast routing hooks
* Jos Vos : Do accounting *before* call_in_firewall
* Willy Konynenberg : Transparent proxying support
*
* To Fix:
* IP fragmentation wants rewriting cleanly. The RFC815 algorithm is much more efficient
* and could be made very efficient with the addition of some virtual memory hacks to permit
* the allocation of a buffer that can then be 'grown' by twiddling page tables.
* Output fragmentation wants updating along with the buffer management to use a single
* interleaved copy algorithm so that fragmenting has a one copy overhead. Actual packet
* output should probably do its own fragmentation at the UDP/RAW layer. TCP shouldn't cause
* fragmentation anyway.
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/indirect_call_wrapper.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/icmp.h>
#include <net/raw.h>
#include <net/checksum.h>
#include <net/inet_ecn.h>
#include <linux/netfilter_ipv4.h>
#include <net/xfrm.h>
#include <linux/mroute.h>
#include <linux/netlink.h>
#include <net/dst_metadata.h>
/*
* Process Router Attention IP option (RFC 2113)
*/
bool ip_call_ra_chain(struct sk_buff *skb)
{
struct ip_ra_chain *ra;
u8 protocol = ip_hdr(skb)->protocol;
struct sock *last = NULL;
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
for (ra = rcu_dereference(net->ipv4.ra_chain); ra; ra = rcu_dereference(ra->next)) {
struct sock *sk = ra->sk;
/* If socket is bound to an interface, only report
* the packet if it came from that interface.
*/
if (sk && inet_sk(sk)->inet_num == protocol &&
(!sk->sk_bound_dev_if ||
sk->sk_bound_dev_if == dev->ifindex)) {
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
return true;
}
if (last) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
raw_rcv(last, skb2);
}
last = sk;
}
}
if (last) {
raw_rcv(last, skb);
return true;
}
return false;
}
INDIRECT_CALLABLE_DECLARE(int udp_rcv(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int tcp_v4_rcv(struct sk_buff *));
void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
const struct net_protocol *ipprot;
int raw, ret;
resubmit:
raw = raw_local_deliver(skb, protocol);
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot) {
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb_reason(skb,
SKB_DROP_REASON_XFRM_POLICY);
return;
}
nf_reset_ct(skb);
}
ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv,
skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
kfree_skb_reason(skb, SKB_DROP_REASON_IP_NOPROTO);
} else {
__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
}
static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_clear_delivery_time(skb);
__skb_pull(skb, skb_network_header_len(skb));
rcu_read_lock();
ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
rcu_read_unlock();
return 0;
}
/*
* Deliver IP Packets to the higher protocol layers.
*/
int ip_local_deliver(struct sk_buff *skb)
{
/*
* Reassemble IP fragments.
*/
struct net *net = dev_net(skb->dev);
if (ip_is_fragment(ip_hdr(skb))) {
if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
return 0;
}
return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
net, NULL, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
EXPORT_SYMBOL(ip_local_deliver);
static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
{
struct ip_options *opt;
const struct iphdr *iph;
/* It looks as overkill, because not all
IP options require packet mangling.
But it is the easiest for now, especially taking
into account that combination of IP options
and running sniffer is extremely rare condition.
--ANK (980813)
*/
if (skb_cow(skb, skb_headroom(skb))) {
__IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
iph = ip_hdr(skb);
opt = &(IPCB(skb)->opt);
opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
if (ip_options_compile(dev_net(dev), opt, skb)) {
__IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
goto drop;
}
if (unlikely(opt->srr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
if (IN_DEV_LOG_MARTIANS(in_dev))
net_info_ratelimited("source route option %pI4 -> %pI4\n",
&iph->saddr,
&iph->daddr);
goto drop;
}
}
if (ip_options_rcv_srr(skb, dev))
goto drop;
}
return false;
drop:
return true;
}
static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
const struct sk_buff *hint)
{
return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr &&
ip_hdr(hint)->tos == iph->tos;
}
int tcp_v4_early_demux(struct sk_buff *skb);
int udp_v4_early_demux(struct sk_buff *skb);
static int ip_rcv_finish_core(struct net *net,
struct sk_buff *skb, struct net_device *dev,
const struct sk_buff *hint)
{
const struct iphdr *iph = ip_hdr(skb);
int err, drop_reason;
struct rtable *rt;
if (ip_can_use_hint(skb, iph, hint)) {
drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr,
ip4h_dscp(iph), dev, hint);
if (unlikely(drop_reason))
goto drop_error;
}
drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
!skb_dst(skb) &&
!skb->sk &&
!ip_is_fragment(iph)) {
switch (iph->protocol) {
case IPPROTO_TCP:
if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) {
tcp_v4_early_demux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
break;
case IPPROTO_UDP:
if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) {
err = udp_v4_early_demux(skb);
if (unlikely(err))
goto drop_error;
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
break;
}
}
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (!skb_valid_dst(skb)) {
drop_reason = ip_route_input_noref(skb, iph->daddr, iph->saddr,
ip4h_dscp(iph), dev);
if (unlikely(drop_reason))
goto drop_error;
drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
} else {
struct in_device *in_dev = __in_dev_get_rcu(dev);
if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
IPCB(skb)->flags |= IPSKB_NOPOLICY;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
if (unlikely(skb_dst(skb)->tclassid)) {
struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
u32 idx = skb_dst(skb)->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes += skb->len;
st[(idx>>16)&0xFF].i_packets++;
st[(idx>>16)&0xFF].i_bytes += skb->len;
}
#endif
if (iph->ihl > 5 && ip_rcv_options(skb, dev))
goto drop;
rt = skb_rtable(skb);
if (rt->rt_type == RTN_MULTICAST) {
__IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len);
} else if (rt->rt_type == RTN_BROADCAST) {
__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
} else if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* RFC 1122 3.3.6:
*
* When a host sends a datagram to a link-layer broadcast
* address, the IP destination address MUST be a legal IP
* broadcast or IP multicast address.
*
* A host SHOULD silently discard a datagram that is received
* via a link-layer broadcast (see Section 2.4) but does not
* specify an IP multicast or broadcast destination address.
*
* This doesn't explicitly say L2 *broadcast*, but broadcast is
* in a way a form of multicast and the most common use case for
* this is 802.11 protecting against cross-station spoofing (the
* so-called "hole-196" attack) so do it for both.
*/
if (in_dev &&
IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) {
drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST;
goto drop;
}
}
return NET_RX_SUCCESS;
drop:
kfree_skb_reason(skb, drop_reason);
return NET_RX_DROP;
drop_error:
if (drop_reason == SKB_DROP_REASON_IP_RPFILTER)
__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
goto drop;
}
static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
int ret;
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip_rcv(skb);
if (!skb)
return NET_RX_SUCCESS;
ret = ip_rcv_finish_core(net, skb, dev, NULL);
if (ret != NET_RX_DROP)
ret = dst_input(skb);
return ret;
}
/*
* Main IP Receive routine.
*/
static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
{
const struct iphdr *iph;
int drop_reason;
u32 len;
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
if (skb->pkt_type == PACKET_OTHERHOST) {
dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
drop_reason = SKB_DROP_REASON_OTHERHOST;
goto drop;
}
__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) {
__IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
goto out;
}
drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
iph = ip_hdr(skb);
/*
* RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
* 1. Length at least the size of an ip header
* 2. Version of 4
* 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums]
* 4. Doesn't have a bogus length
*/
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
__IP_ADD_STATS(net,
IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
iph = ip_hdr(skb);
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto csum_error;
len = iph_totlen(skb, iph); if (skb->len < len) {
drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
} else if (len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* is IP we can trim to the true length of the frame.
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS);
goto drop;
}
iph = ip_hdr(skb);
skb->transport_header = skb->network_header + iph->ihl*4;
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
IPCB(skb)->iif = skb->skb_iif;
/* Must drop socket now because of tproxy. */
if (!skb_sk_is_prefetched(skb)) skb_orphan(skb);
return skb;
csum_error:
drop_reason = SKB_DROP_REASON_IP_CSUM;
__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
inhdr_error:
if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED)
drop_reason = SKB_DROP_REASON_IP_INHDR;
__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb_reason(skb, drop_reason);
out:
return NULL;
}
/*
* IP receive entry point
*/
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev)
{
struct net *net = dev_net(dev);
skb = ip_rcv_core(skb, net);
if (skb == NULL)
return NET_RX_DROP;
return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
net, NULL, skb, dev, NULL,
ip_rcv_finish);
}
static void ip_sublist_rcv_finish(struct list_head *head)
{
struct sk_buff *skb, *next;
list_for_each_entry_safe(skb, next, head, list) {
skb_list_del_init(skb);
dst_input(skb);
}
}
static struct sk_buff *ip_extract_route_hint(const struct net *net,
struct sk_buff *skb, int rt_type)
{
if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST ||
IPCB(skb)->flags & IPSKB_MULTIPATH)
return NULL;
return skb;
}
static void ip_list_rcv_finish(struct net *net, struct list_head *head)
{
struct sk_buff *skb, *next, *hint = NULL;
struct dst_entry *curr_dst = NULL;
LIST_HEAD(sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *dev = skb->dev;
struct dst_entry *dst;
skb_list_del_init(skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
skb = l3mdev_ip_rcv(skb);
if (!skb)
continue;
if (ip_rcv_finish_core(net, skb, dev, hint) == NET_RX_DROP)
continue;
dst = skb_dst(skb);
if (curr_dst != dst) {
hint = ip_extract_route_hint(net, skb,
dst_rtable(dst)->rt_type);
/* dispatch old sublist */
if (!list_empty(&sublist))
ip_sublist_rcv_finish(&sublist);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dst = dst;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
ip_sublist_rcv_finish(&sublist);
}
static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
struct net *net)
{
NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
head, dev, NULL, ip_rcv_finish);
ip_list_rcv_finish(net, head);
}
/* Receive a list of IP packets */
void ip_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *orig_dev)
{
struct net_device *curr_dev = NULL;
struct net *curr_net = NULL;
struct sk_buff *skb, *next;
LIST_HEAD(sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
skb_list_del_init(skb);
skb = ip_rcv_core(skb, net);
if (skb == NULL)
continue;
if (curr_dev != dev || curr_net != net) {
/* dispatch old sublist */
if (!list_empty(&sublist))
ip_sublist_rcv(&sublist, curr_dev, curr_net);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
curr_dev = dev;
curr_net = net;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
if (!list_empty(&sublist))
ip_sublist_rcv(&sublist, curr_dev, curr_net);
}
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/fcntl.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched/task.h>
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/file.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/memfd.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/rw_hint.h>
#include <linux/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>
#include "internal.h"
#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
static int setfl(int fd, struct file * filp, unsigned int arg)
{
struct inode * inode = file_inode(filp);
int error = 0;
/*
* O_APPEND cannot be cleared if the file is marked as append-only
* and the file is open for write.
*/
if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
return -EPERM;
/* O_NOATIME can only be set by the owner or superuser */
if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
if (!inode_owner_or_capable(file_mnt_idmap(filp), inode))
return -EPERM;
/* required for strict SunOS emulation */
if (O_NONBLOCK != O_NDELAY)
if (arg & O_NDELAY)
arg |= O_NONBLOCK;
/* Pipe packetized mode is controlled by O_DIRECT flag */
if (!S_ISFIFO(inode->i_mode) &&
(arg & O_DIRECT) &&
!(filp->f_mode & FMODE_CAN_ODIRECT))
return -EINVAL;
if (filp->f_op->check_flags)
error = filp->f_op->check_flags(arg);
if (error)
return error;
/*
* ->fasync() is responsible for setting the FASYNC bit.
*/
if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
if (error < 0)
goto out;
if (error > 0)
error = 0;
}
spin_lock(&filp->f_lock);
filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
filp->f_iocb_flags = iocb_flags(filp);
spin_unlock(&filp->f_lock);
out:
return error;
}
/*
* Allocate an file->f_owner struct if it doesn't exist, handling racing
* allocations correctly.
*/
int file_f_owner_allocate(struct file *file)
{
struct fown_struct *f_owner;
f_owner = file_f_owner(file);
if (f_owner)
return 0;
f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL);
if (!f_owner)
return -ENOMEM;
rwlock_init(&f_owner->lock);
f_owner->file = file;
/* If someone else raced us, drop our allocation. */
if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner)))
kfree(f_owner);
return 0;
}
EXPORT_SYMBOL(file_f_owner_allocate);
void file_f_owner_release(struct file *file)
{
struct fown_struct *f_owner;
f_owner = file_f_owner(file);
if (f_owner) { put_pid(f_owner->pid);
kfree(f_owner);
}
}
void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
int force)
{
struct fown_struct *f_owner;
f_owner = file_f_owner(filp);
if (WARN_ON_ONCE(!f_owner))
return;
write_lock_irq(&f_owner->lock);
if (force || !f_owner->pid) {
put_pid(f_owner->pid);
f_owner->pid = get_pid(pid);
f_owner->pid_type = type;
if (pid) {
const struct cred *cred = current_cred();
security_file_set_fowner(filp);
f_owner->uid = cred->uid;
f_owner->euid = cred->euid;
}
}
write_unlock_irq(&f_owner->lock);
}
EXPORT_SYMBOL(__f_setown);
int f_setown(struct file *filp, int who, int force)
{
enum pid_type type;
struct pid *pid = NULL;
int ret = 0;
might_sleep();
type = PIDTYPE_TGID;
if (who < 0) {
/* avoid overflow below */
if (who == INT_MIN)
return -EINVAL;
type = PIDTYPE_PGID;
who = -who;
}
ret = file_f_owner_allocate(filp);
if (ret)
return ret;
rcu_read_lock();
if (who) {
pid = find_vpid(who);
if (!pid)
ret = -ESRCH;
}
if (!ret)
__f_setown(filp, pid, type, force);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(f_setown);
void f_delown(struct file *filp)
{
__f_setown(filp, NULL, PIDTYPE_TGID, 1);
}
pid_t f_getown(struct file *filp)
{
pid_t pid = 0;
struct fown_struct *f_owner;
f_owner = file_f_owner(filp);
if (!f_owner)
return pid;
read_lock_irq(&f_owner->lock);
rcu_read_lock();
if (pid_task(f_owner->pid, f_owner->pid_type)) {
pid = pid_vnr(f_owner->pid);
if (f_owner->pid_type == PIDTYPE_PGID)
pid = -pid;
}
rcu_read_unlock();
read_unlock_irq(&f_owner->lock);
return pid;
}
static int f_setown_ex(struct file *filp, unsigned long arg)
{
struct f_owner_ex __user *owner_p = (void __user *)arg;
struct f_owner_ex owner;
struct pid *pid;
int type;
int ret;
ret = copy_from_user(&owner, owner_p, sizeof(owner));
if (ret)
return -EFAULT;
switch (owner.type) {
case F_OWNER_TID:
type = PIDTYPE_PID;
break;
case F_OWNER_PID:
type = PIDTYPE_TGID;
break;
case F_OWNER_PGRP:
type = PIDTYPE_PGID;
break;
default:
return -EINVAL;
}
ret = file_f_owner_allocate(filp);
if (ret)
return ret;
rcu_read_lock();
pid = find_vpid(owner.pid);
if (owner.pid && !pid)
ret = -ESRCH;
else
__f_setown(filp, pid, type, 1);
rcu_read_unlock();
return ret;
}
static int f_getown_ex(struct file *filp, unsigned long arg)
{
struct f_owner_ex __user *owner_p = (void __user *)arg;
struct f_owner_ex owner = {};
int ret = 0;
struct fown_struct *f_owner;
enum pid_type pid_type = PIDTYPE_PID;
f_owner = file_f_owner(filp);
if (f_owner) {
read_lock_irq(&f_owner->lock);
rcu_read_lock();
if (pid_task(f_owner->pid, f_owner->pid_type))
owner.pid = pid_vnr(f_owner->pid);
rcu_read_unlock();
pid_type = f_owner->pid_type;
}
switch (pid_type) {
case PIDTYPE_PID:
owner.type = F_OWNER_TID;
break;
case PIDTYPE_TGID:
owner.type = F_OWNER_PID;
break;
case PIDTYPE_PGID:
owner.type = F_OWNER_PGRP;
break;
default:
WARN_ON(1);
ret = -EINVAL;
break;
}
if (f_owner)
read_unlock_irq(&f_owner->lock);
if (!ret) {
ret = copy_to_user(owner_p, &owner, sizeof(owner));
if (ret)
ret = -EFAULT;
}
return ret;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
struct user_namespace *user_ns = current_user_ns();
struct fown_struct *f_owner;
uid_t __user *dst = (void __user *)arg;
uid_t src[2] = {0, 0};
int err;
f_owner = file_f_owner(filp);
if (f_owner) {
read_lock_irq(&f_owner->lock);
src[0] = from_kuid(user_ns, f_owner->uid);
src[1] = from_kuid(user_ns, f_owner->euid);
read_unlock_irq(&f_owner->lock);
}
err = put_user(src[0], &dst[0]);
err |= put_user(src[1], &dst[1]);
return err;
}
#else
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
return -EINVAL;
}
#endif
static bool rw_hint_valid(u64 hint)
{
BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
switch (hint) {
case RWH_WRITE_LIFE_NOT_SET:
case RWH_WRITE_LIFE_NONE:
case RWH_WRITE_LIFE_SHORT:
case RWH_WRITE_LIFE_MEDIUM:
case RWH_WRITE_LIFE_LONG:
case RWH_WRITE_LIFE_EXTREME:
return true;
default:
return false;
}
}
static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct inode *inode = file_inode(file);
u64 __user *argp = (u64 __user *)arg;
u64 hint = READ_ONCE(inode->i_write_hint);
if (copy_to_user(argp, &hint, sizeof(*argp)))
return -EFAULT;
return 0;
}
static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct inode *inode = file_inode(file);
u64 __user *argp = (u64 __user *)arg;
u64 hint;
if (!inode_owner_or_capable(file_mnt_idmap(file), inode))
return -EPERM;
if (copy_from_user(&hint, argp, sizeof(hint)))
return -EFAULT;
if (!rw_hint_valid(hint))
return -EINVAL;
WRITE_ONCE(inode->i_write_hint, hint);
/*
* file->f_mapping->host may differ from inode. As an example,
* blkdev_open() modifies file->f_mapping.
*/
if (file->f_mapping->host != inode)
WRITE_ONCE(file->f_mapping->host->i_write_hint, hint);
return 0;
}
/* Is the file descriptor a dup of the file? */
static long f_dupfd_query(int fd, struct file *filp)
{
CLASS(fd_raw, f)(fd);
if (fd_empty(f))
return -EBADF;
/*
* We can do the 'fdput()' immediately, as the only thing that
* matters is the pointer value which isn't changed by the fdput.
*
* Technically we didn't need a ref at all, and 'fdget()' was
* overkill, but given our lockless file pointer lookup, the
* alternatives are complicated.
*/
return fd_file(f) == filp;
}
/* Let the caller figure out whether a given file was just created. */
static long f_created_query(const struct file *filp)
{
return !!(filp->f_mode & FMODE_CREATED);
}
static int f_owner_sig(struct file *filp, int signum, bool setsig)
{
int ret = 0;
struct fown_struct *f_owner;
might_sleep();
if (setsig) {
if (!valid_signal(signum))
return -EINVAL;
ret = file_f_owner_allocate(filp);
if (ret)
return ret;
}
f_owner = file_f_owner(filp);
if (setsig)
f_owner->signum = signum;
else if (f_owner)
ret = f_owner->signum;
return ret;
}
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
struct file *filp)
{
void __user *argp = (void __user *)arg;
int argi = (int)arg;
struct flock flock;
long err = -EINVAL;
switch (cmd) {
case F_CREATED_QUERY:
err = f_created_query(filp);
break;
case F_DUPFD:
err = f_dupfd(argi, filp, 0);
break;
case F_DUPFD_CLOEXEC:
err = f_dupfd(argi, filp, O_CLOEXEC);
break;
case F_DUPFD_QUERY:
err = f_dupfd_query(argi, filp);
break;
case F_GETFD:
err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
break;
case F_SETFD:
err = 0;
set_close_on_exec(fd, argi & FD_CLOEXEC);
break;
case F_GETFL:
err = filp->f_flags;
break;
case F_SETFL:
err = setfl(fd, filp, argi);
break;
#if BITS_PER_LONG != 32
/* 32-bit arches must use fcntl64() */
case F_OFD_GETLK:
#endif
case F_GETLK:
if (copy_from_user(&flock, argp, sizeof(flock)))
return -EFAULT;
err = fcntl_getlk(filp, cmd, &flock);
if (!err && copy_to_user(argp, &flock, sizeof(flock)))
return -EFAULT;
break;
#if BITS_PER_LONG != 32
/* 32-bit arches must use fcntl64() */
case F_OFD_SETLK:
case F_OFD_SETLKW:
fallthrough;
#endif
case F_SETLK:
case F_SETLKW:
if (copy_from_user(&flock, argp, sizeof(flock)))
return -EFAULT;
err = fcntl_setlk(fd, filp, cmd, &flock);
break;
case F_GETOWN:
/*
* XXX If f_owner is a process group, the
* negative return value will get converted
* into an error. Oops. If we keep the
* current syscall conventions, the only way
* to fix this will be in libc.
*/
err = f_getown(filp);
force_successful_syscall_return();
break;
case F_SETOWN:
err = f_setown(filp, argi, 1);
break;
case F_GETOWN_EX:
err = f_getown_ex(filp, arg);
break;
case F_SETOWN_EX:
err = f_setown_ex(filp, arg);
break;
case F_GETOWNER_UIDS:
err = f_getowner_uids(filp, arg);
break;
case F_GETSIG:
err = f_owner_sig(filp, 0, false);
break;
case F_SETSIG:
err = f_owner_sig(filp, argi, true);
break;
case F_GETLEASE:
err = fcntl_getlease(filp);
break;
case F_SETLEASE:
err = fcntl_setlease(fd, filp, argi);
break;
case F_NOTIFY:
err = fcntl_dirnotify(fd, filp, argi);
break;
case F_SETPIPE_SZ:
case F_GETPIPE_SZ:
err = pipe_fcntl(filp, cmd, argi);
break;
case F_ADD_SEALS:
case F_GET_SEALS:
err = memfd_fcntl(filp, cmd, argi);
break;
case F_GET_RW_HINT:
err = fcntl_get_rw_hint(filp, cmd, arg);
break;
case F_SET_RW_HINT:
err = fcntl_set_rw_hint(filp, cmd, arg);
break;
default:
break;
}
return err;
}
static int check_fcntl_cmd(unsigned cmd)
{
switch (cmd) {
case F_CREATED_QUERY:
case F_DUPFD:
case F_DUPFD_CLOEXEC:
case F_DUPFD_QUERY:
case F_GETFD:
case F_SETFD:
case F_GETFL:
return 1;
}
return 0;
}
SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
CLASS(fd_raw, f)(fd);
long err;
if (fd_empty(f))
return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (!err)
err = do_fcntl(fd, cmd, arg, fd_file(f));
return err;
}
#if BITS_PER_LONG == 32
SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
unsigned long, arg)
{
void __user *argp = (void __user *)arg;
CLASS(fd_raw, f)(fd);
struct flock64 flock;
long err;
if (fd_empty(f))
return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (err)
return err;
switch (cmd) {
case F_GETLK64:
case F_OFD_GETLK:
err = -EFAULT;
if (copy_from_user(&flock, argp, sizeof(flock)))
break;
err = fcntl_getlk64(fd_file(f), cmd, &flock);
if (!err && copy_to_user(argp, &flock, sizeof(flock)))
err = -EFAULT;
break;
case F_SETLK64:
case F_SETLKW64:
case F_OFD_SETLK:
case F_OFD_SETLKW:
err = -EFAULT;
if (copy_from_user(&flock, argp, sizeof(flock)))
break;
err = fcntl_setlk64(fd, fd_file(f), cmd, &flock);
break;
default:
err = do_fcntl(fd, cmd, arg, fd_file(f));
break;
}
return err;
}
#endif
#ifdef CONFIG_COMPAT
/* careful - don't use anywhere else */
#define copy_flock_fields(dst, src) \
(dst)->l_type = (src)->l_type; \
(dst)->l_whence = (src)->l_whence; \
(dst)->l_start = (src)->l_start; \
(dst)->l_len = (src)->l_len; \
(dst)->l_pid = (src)->l_pid;
static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl)
{
struct compat_flock fl;
if (copy_from_user(&fl, ufl, sizeof(struct compat_flock)))
return -EFAULT;
copy_flock_fields(kfl, &fl);
return 0;
}
static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl)
{
struct compat_flock64 fl;
if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64)))
return -EFAULT;
copy_flock_fields(kfl, &fl);
return 0;
}
static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl)
{
struct compat_flock fl;
memset(&fl, 0, sizeof(struct compat_flock));
copy_flock_fields(&fl, kfl);
if (copy_to_user(ufl, &fl, sizeof(struct compat_flock)))
return -EFAULT;
return 0;
}
static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl)
{
struct compat_flock64 fl;
BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start));
BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len));
memset(&fl, 0, sizeof(struct compat_flock64));
copy_flock_fields(&fl, kfl);
if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64)))
return -EFAULT;
return 0;
}
#undef copy_flock_fields
static unsigned int
convert_fcntl_cmd(unsigned int cmd)
{
switch (cmd) {
case F_GETLK64:
return F_GETLK;
case F_SETLK64:
return F_SETLK;
case F_SETLKW64:
return F_SETLKW;
}
return cmd;
}
/*
* GETLK was successful and we need to return the data, but it needs to fit in
* the compat structure.
* l_start shouldn't be too big, unless the original start + end is greater than
* COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return
* -EOVERFLOW in that case. l_len could be too big, in which case we just
* truncate it, and only allow the app to see that part of the conflicting lock
* that might make sense to it anyway
*/
static int fixup_compat_flock(struct flock *flock)
{
if (flock->l_start > COMPAT_OFF_T_MAX)
return -EOVERFLOW;
if (flock->l_len > COMPAT_OFF_T_MAX)
flock->l_len = COMPAT_OFF_T_MAX;
return 0;
}
static long do_compat_fcntl64(unsigned int fd, unsigned int cmd,
compat_ulong_t arg)
{
CLASS(fd_raw, f)(fd);
struct flock flock;
long err;
if (fd_empty(f))
return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (err)
return err;
switch (cmd) {
case F_GETLK:
err = get_compat_flock(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock);
if (err)
break;
err = fixup_compat_flock(&flock);
if (!err)
err = put_compat_flock(&flock, compat_ptr(arg));
break;
case F_GETLK64:
case F_OFD_GETLK:
err = get_compat_flock64(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock);
if (!err)
err = put_compat_flock64(&flock, compat_ptr(arg));
break;
case F_SETLK:
case F_SETLKW:
err = get_compat_flock(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock);
break;
case F_SETLK64:
case F_SETLKW64:
case F_OFD_SETLK:
case F_OFD_SETLKW:
err = get_compat_flock64(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock);
break;
default:
err = do_fcntl(fd, cmd, arg, fd_file(f));
break;
}
return err;
}
COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
compat_ulong_t, arg)
{
return do_compat_fcntl64(fd, cmd, arg);
}
COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
compat_ulong_t, arg)
{
switch (cmd) {
case F_GETLK64:
case F_SETLK64:
case F_SETLKW64:
case F_OFD_GETLK:
case F_OFD_SETLK:
case F_OFD_SETLKW:
return -EINVAL;
}
return do_compat_fcntl64(fd, cmd, arg);
}
#endif
/* Table to convert sigio signal codes into poll band bitmaps */
static const __poll_t band_table[NSIGPOLL] = {
EPOLLIN | EPOLLRDNORM, /* POLL_IN */
EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */
EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */
EPOLLERR, /* POLL_ERR */
EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */
EPOLLHUP | EPOLLERR /* POLL_HUP */
};
static inline int sigio_perm(struct task_struct *p,
struct fown_struct *fown, int sig)
{
const struct cred *cred;
int ret;
rcu_read_lock();
cred = __task_cred(p);
ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) ||
uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) ||
uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) &&
!security_file_send_sigiotask(p, fown, sig));
rcu_read_unlock();
return ret;
}
static void send_sigio_to_task(struct task_struct *p,
struct fown_struct *fown,
int fd, int reason, enum pid_type type)
{
/*
* F_SETSIG can change ->signum lockless in parallel, make
* sure we read it once and use the same value throughout.
*/
int signum = READ_ONCE(fown->signum);
if (!sigio_perm(p, fown, signum))
return;
switch (signum) {
default: {
kernel_siginfo_t si;
/* Queue a rt signal with the appropriate fd as its
value. We use SI_SIGIO as the source, not
SI_KERNEL, since kernel signals always get
delivered even if we can't queue. Failure to
queue in this case _should_ be reported; we fall
back to SIGIO in that case. --sct */
clear_siginfo(&si);
si.si_signo = signum;
si.si_errno = 0;
si.si_code = reason;
/*
* Posix definies POLL_IN and friends to be signal
* specific si_codes for SIG_POLL. Linux extended
* these si_codes to other signals in a way that is
* ambiguous if other signals also have signal
* specific si_codes. In that case use SI_SIGIO instead
* to remove the ambiguity.
*/
if ((signum != SIGPOLL) && sig_specific_sicodes(signum))
si.si_code = SI_SIGIO;
/* Make sure we are called with one of the POLL_*
reasons, otherwise we could leak kernel stack into
userspace. */
BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL));
if (reason - POLL_IN >= NSIGPOLL)
si.si_band = ~0L;
else
si.si_band = mangle_poll(band_table[reason - POLL_IN]);
si.si_fd = fd;
if (!do_send_sig_info(signum, &si, p, type))
break;
}
fallthrough; /* fall back on the old plain SIGIO signal */
case 0:
do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type);
}
}
void send_sigio(struct fown_struct *fown, int fd, int band)
{
struct task_struct *p;
enum pid_type type;
unsigned long flags;
struct pid *pid;
read_lock_irqsave(&fown->lock, flags);
type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
if (type <= PIDTYPE_TGID) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
send_sigio_to_task(p, fown, fd, band, type);
rcu_read_unlock();
} else {
read_lock(&tasklist_lock);
do_each_pid_task(pid, type, p) {
send_sigio_to_task(p, fown, fd, band, type);
} while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
}
out_unlock_fown:
read_unlock_irqrestore(&fown->lock, flags);
}
static void send_sigurg_to_task(struct task_struct *p,
struct fown_struct *fown, enum pid_type type)
{
if (sigio_perm(p, fown, SIGURG))
do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type);
}
int send_sigurg(struct file *file)
{
struct fown_struct *fown;
struct task_struct *p;
enum pid_type type;
struct pid *pid;
unsigned long flags;
int ret = 0;
fown = file_f_owner(file);
if (!fown)
return 0;
read_lock_irqsave(&fown->lock, flags);
type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
ret = 1;
if (type <= PIDTYPE_TGID) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
send_sigurg_to_task(p, fown, type);
rcu_read_unlock();
} else {
read_lock(&tasklist_lock);
do_each_pid_task(pid, type, p) {
send_sigurg_to_task(p, fown, type);
} while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
}
out_unlock_fown:
read_unlock_irqrestore(&fown->lock, flags);
return ret;
}
static DEFINE_SPINLOCK(fasync_lock);
static struct kmem_cache *fasync_cache __ro_after_init;
/*
* Remove a fasync entry. If successfully removed, return
* positive and clear the FASYNC flag. If no entry exists,
* do nothing and return 0.
*
* NOTE! It is very important that the FASYNC flag always
* match the state "is the filp on a fasync list".
*
*/
int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
{
struct fasync_struct *fa, **fp;
int result = 0;
spin_lock(&filp->f_lock);
spin_lock(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
if (fa->fa_file != filp)
continue;
write_lock_irq(&fa->fa_lock);
fa->fa_file = NULL;
write_unlock_irq(&fa->fa_lock);
*fp = fa->fa_next;
kfree_rcu(fa, fa_rcu);
filp->f_flags &= ~FASYNC;
result = 1;
break;
}
spin_unlock(&fasync_lock);
spin_unlock(&filp->f_lock);
return result;
}
struct fasync_struct *fasync_alloc(void)
{
return kmem_cache_alloc(fasync_cache, GFP_KERNEL);
}
/*
* NOTE! This can be used only for unused fasync entries:
* entries that actually got inserted on the fasync list
* need to be released by rcu - see fasync_remove_entry.
*/
void fasync_free(struct fasync_struct *new)
{
kmem_cache_free(fasync_cache, new);
}
/*
* Insert a new entry into the fasync list. Return the pointer to the
* old one if we didn't use the new one.
*
* NOTE! It is very important that the FASYNC flag always
* match the state "is the filp on a fasync list".
*/
struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new)
{
struct fasync_struct *fa, **fp;
spin_lock(&filp->f_lock);
spin_lock(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
if (fa->fa_file != filp)
continue;
write_lock_irq(&fa->fa_lock);
fa->fa_fd = fd;
write_unlock_irq(&fa->fa_lock);
goto out;
}
rwlock_init(&new->fa_lock);
new->magic = FASYNC_MAGIC;
new->fa_file = filp;
new->fa_fd = fd;
new->fa_next = *fapp;
rcu_assign_pointer(*fapp, new);
filp->f_flags |= FASYNC;
out:
spin_unlock(&fasync_lock);
spin_unlock(&filp->f_lock);
return fa;
}
/*
* Add a fasync entry. Return negative on error, positive if
* added, and zero if did nothing but change an existing one.
*/
static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
{
struct fasync_struct *new;
new = fasync_alloc();
if (!new)
return -ENOMEM;
/*
* fasync_insert_entry() returns the old (update) entry if
* it existed.
*
* So free the (unused) new entry and return 0 to let the
* caller know that we didn't add any new fasync entries.
*/
if (fasync_insert_entry(fd, filp, fapp, new)) {
fasync_free(new);
return 0;
}
return 1;
}
/*
* fasync_helper() is used by almost all character device drivers
* to set up the fasync queue, and for regular files by the file
* lease code. It returns negative on error, 0 if it did no changes
* and positive if it added/deleted the entry.
*/
int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
{
if (!on)
return fasync_remove_entry(filp, fapp);
return fasync_add_entry(fd, filp, fapp);
}
EXPORT_SYMBOL(fasync_helper);
/*
* rcu_read_lock() is held
*/
static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
{
while (fa) {
struct fown_struct *fown;
unsigned long flags;
if (fa->magic != FASYNC_MAGIC) {
printk(KERN_ERR "kill_fasync: bad magic number in "
"fasync_struct!\n");
return;
}
read_lock_irqsave(&fa->fa_lock, flags);
if (fa->fa_file) {
fown = file_f_owner(fa->fa_file);
if (!fown)
goto next;
/* Don't send SIGURG to processes which have not set a
queued signum: SIGURG has its own default signalling
mechanism. */
if (!(sig == SIGURG && fown->signum == 0))
send_sigio(fown, fa->fa_fd, band);
}
next:
read_unlock_irqrestore(&fa->fa_lock, flags);
fa = rcu_dereference(fa->fa_next);
}
}
void kill_fasync(struct fasync_struct **fp, int sig, int band)
{
/* First a quick test without locking: usually
* the list is empty.
*/
if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock();
}
}
EXPORT_SYMBOL(kill_fasync);
static int __init fcntl_init(void)
{
/*
* Please add new bits here to ensure allocation uniqueness.
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ !=
HWEIGHT32(
(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
__FMODE_EXEC));
fasync_cache = kmem_cache_create("fasync_cache",
sizeof(struct fasync_struct), 0,
SLAB_PANIC | SLAB_ACCOUNT, NULL);
return 0;
}
module_init(fcntl_init)
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/attr.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* changes by Thomas Schoebel-Theuer
*/
#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/sched/signal.h>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/filelock.h>
#include <linux/security.h>
/**
* setattr_should_drop_sgid - determine whether the setgid bit needs to be
* removed
* @idmap: idmap of the mount @inode was found from
* @inode: inode to check
*
* This function determines whether the setgid bit needs to be removed.
* We retain backwards compatibility and require setgid bit to be removed
* unconditionally if S_IXGRP is set. Otherwise we have the exact same
* requirements as setattr_prepare() and setattr_copy().
*
* Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise.
*/
int setattr_should_drop_sgid(struct mnt_idmap *idmap,
const struct inode *inode)
{
umode_t mode = inode->i_mode;
if (!(mode & S_ISGID))
return 0;
if (mode & S_IXGRP)
return ATTR_KILL_SGID;
if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
return ATTR_KILL_SGID;
return 0;
}
EXPORT_SYMBOL(setattr_should_drop_sgid);
/**
* setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to
* be dropped
* @idmap: idmap of the mount @inode was found from
* @inode: inode to check
*
* This function determines whether the set{g,u}id bits need to be removed.
* If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the
* setgid bit needs to be removed ATTR_KILL_SGID is returned. If both
* set{g,u}id bits need to be removed the corresponding mask of both flags is
* returned.
*
* Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits
* to remove, 0 otherwise.
*/
int setattr_should_drop_suidgid(struct mnt_idmap *idmap,
struct inode *inode)
{
umode_t mode = inode->i_mode;
int kill = 0;
/* suid always must be killed */
if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(idmap, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
return kill;
return 0;
}
EXPORT_SYMBOL(setattr_should_drop_suidgid);
/**
* chown_ok - verify permissions to chown inode
* @idmap: idmap of the mount @inode was found from
* @inode: inode to check permissions on
* @ia_vfsuid: uid to chown @inode to
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*/
static bool chown_ok(struct mnt_idmap *idmap,
const struct inode *inode, vfsuid_t ia_vfsuid)
{
vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()) &&
vfsuid_eq(ia_vfsuid, vfsuid))
return true;
if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN))
return true;
if (!vfsuid_valid(vfsuid) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
}
/**
* chgrp_ok - verify permissions to chgrp inode
* @idmap: idmap of the mount @inode was found from
* @inode: inode to check permissions on
* @ia_vfsgid: gid to chown @inode to
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*/
static bool chgrp_ok(struct mnt_idmap *idmap,
const struct inode *inode, vfsgid_t ia_vfsgid)
{
vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid))
return true;
if (vfsgid_in_group_p(ia_vfsgid))
return true;
}
if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN))
return true;
if (!vfsgid_valid(vfsgid) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
}
/**
* setattr_prepare - check if attribute changes to a dentry are allowed
* @idmap: idmap of the mount the inode was found from
* @dentry: dentry to check
* @attr: attributes to change
*
* Check if we are allowed to change the attributes contained in @attr
* in the given dentry. This includes the normal unix access permission
* checks, as well as checks for rlimits and others. The function also clears
* SGID bit from mode if user is not allowed to set it. Also file capabilities
* and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* Should be called as the first thing in ->setattr implementations,
* possibly after taking additional locks.
*/
int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
unsigned int ia_valid = attr->ia_valid;
/*
* First check size constraints. These can't be overriden using
* ATTR_FORCE.
*/
if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size);
if (error)
return error;
}
/* If force is set do it anyway. */
if (ia_valid & ATTR_FORCE)
goto kill_priv;
/* Make sure a caller can chown. */
if ((ia_valid & ATTR_UID) && !chown_ok(idmap, inode, attr->ia_vfsuid))
return -EPERM;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) && !chgrp_ok(idmap, inode, attr->ia_vfsgid))
return -EPERM;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
vfsgid_t vfsgid;
if (!inode_owner_or_capable(idmap, inode))
return -EPERM;
if (ia_valid & ATTR_GID)
vfsgid = attr->ia_vfsgid;
else
vfsgid = i_gid_into_vfsgid(idmap, inode);
/* Also check the setgid bit! */
if (!in_group_or_capable(idmap, inode, vfsgid)) attr->ia_mode &= ~S_ISGID;
}
/* Check for setting the inode time. */
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(idmap, inode))
return -EPERM;
}
kill_priv:
/* User has permission for the change */
if (ia_valid & ATTR_KILL_PRIV) {
int error;
error = security_inode_killpriv(idmap, dentry);
if (error)
return error;
}
return 0;
}
EXPORT_SYMBOL(setattr_prepare);
/**
* inode_newsize_ok - may this inode be truncated to a given size
* @inode: the inode to be truncated
* @offset: the new size to assign to the inode
*
* inode_newsize_ok must be called with i_mutex held.
*
* inode_newsize_ok will check filesystem limits and ulimits to check that the
* new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
* when necessary. Caller must not proceed with inode size change if failure is
* returned. @inode must be a file (not directory), with appropriate
* permissions to allow truncate (inode_newsize_ok does NOT check these
* conditions).
*
* Return: 0 on success, -ve errno on failure
*/
int inode_newsize_ok(const struct inode *inode, loff_t offset)
{
if (offset < 0)
return -EINVAL;
if (inode->i_size < offset) {
unsigned long limit;
limit = rlimit(RLIMIT_FSIZE);
if (limit != RLIM_INFINITY && offset > limit)
goto out_sig;
if (offset > inode->i_sb->s_maxbytes)
goto out_big;
} else {
/*
* truncation of in-use swapfiles is disallowed - it would
* cause subsequent swapout to scribble on the now-freed
* blocks.
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
}
return 0;
out_sig:
send_sig(SIGXFSZ, current, 0);
out_big:
return -EFBIG;
}
EXPORT_SYMBOL(inode_newsize_ok);
/**
* setattr_copy_mgtime - update timestamps for mgtime inodes
* @inode: inode timestamps to be updated
* @attr: attrs for the update
*
* With multigrain timestamps, take more care to prevent races when
* updating the ctime. Always update the ctime to the very latest using
* the standard mechanism, and use that to populate the atime and mtime
* appropriately (unless those are being set to specific values).
*/
static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
struct timespec64 now;
if (ia_valid & ATTR_CTIME) {
/*
* In the case of an update for a write delegation, we must respect
* the value in ia_ctime and not use the current time.
*/
if (ia_valid & ATTR_DELEG)
now = inode_set_ctime_deleg(inode, attr->ia_ctime);
else
now = inode_set_ctime_current(inode);
} else {
/* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */
WARN_ON_ONCE(ia_valid & ATTR_MTIME);
now = current_time(inode);
}
if (ia_valid & ATTR_ATIME_SET)
inode_set_atime_to_ts(inode, attr->ia_atime); else if (ia_valid & ATTR_ATIME)
inode_set_atime_to_ts(inode, now);
if (ia_valid & ATTR_MTIME_SET)
inode_set_mtime_to_ts(inode, attr->ia_mtime); else if (ia_valid & ATTR_MTIME)
inode_set_mtime_to_ts(inode, now);
}
/**
* setattr_copy - copy simple metadata updates into the generic inode
* @idmap: idmap of the mount the inode was found from
* @inode: the inode to be updated
* @attr: the new attributes
*
* setattr_copy must be called with i_mutex held.
*
* setattr_copy updates the inode's metadata with that specified
* in attr on idmapped mounts. Necessary permission checks to determine
* whether or not the S_ISGID property needs to be removed are performed with
* the correct idmapped mount permission helpers.
* Noticeably missing is inode size update, which is more complex
* as it requires pagecache updates.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* The inode is not marked as dirty after this operation. The rationale is
* that for "simple" filesystems, the struct inode is the inode storage.
* The caller is free to mark the inode dirty afterwards if needed.
*/
void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode;
if (!in_group_or_capable(idmap, inode,
i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
inode->i_mode = mode;
}
if (is_mgtime(inode))
return setattr_copy_mgtime(inode, attr); if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) {
if (ia_valid & ATTR_DELEG)
inode_set_ctime_deleg(inode, attr->ia_ctime);
else
inode_set_ctime_to_ts(inode, attr->ia_ctime);
}
}
EXPORT_SYMBOL(setattr_copy);
int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
unsigned int ia_valid)
{
int error;
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
/*
* If utimes(2) and friends are called with times == NULL (or both
* times are UTIME_NOW), then we need to check for write permission
*/
if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode))
return -EPERM;
if (!inode_owner_or_capable(idmap, inode)) {
error = inode_permission(idmap, inode, MAY_WRITE);
if (error)
return error;
}
}
return 0;
}
EXPORT_SYMBOL(may_setattr);
/**
* notify_change - modify attributes of a filesystem object
* @idmap: idmap of the mount the inode was found from
* @dentry: object affected
* @attr: new attributes
* @delegated_inode: returns inode, if the inode is delegated
*
* The caller must hold the i_mutex on the affected object.
*
* If notify_change discovers a delegation in need of breaking,
* it will return -EWOULDBLOCK and return a reference to the inode in
* delegated_inode. The caller should then break the delegation and
* retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported. Also, passing NULL is fine for callers holding
* the file open for write, as there can be no conflicting delegation in
* that case.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*/
int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
int error;
struct timespec64 now;
unsigned int ia_valid = attr->ia_valid;
WARN_ON_ONCE(!inode_is_locked(inode)); error = may_setattr(idmap, inode, ia_valid);
if (error)
return error;
if ((ia_valid & ATTR_MODE)) {
/*
* Don't allow changing the mode of symlinks:
*
* (1) The vfs doesn't take the mode of symlinks into account
* during permission checking.
* (2) This has never worked correctly. Most major filesystems
* did return EOPNOTSUPP due to interactions with POSIX ACLs
* but did still updated the mode of the symlink.
* This inconsistency led system call wrapper providers such
* as libc to block changing the mode of symlinks with
* EOPNOTSUPP already.
* (3) To even do this in the first place one would have to use
* specific file descriptors and quite some effort.
*/
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
/* Flag setting protected by i_mutex */
if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC;
}
now = current_time(inode);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
else
attr->ia_atime = timestamp_truncate(attr->ia_atime, inode);
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
else
attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) {
error = security_inode_need_killpriv(dentry);
if (error < 0)
return error;
if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV;
}
/*
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
* that the function has the ability to reinterpret a mode change
* that's due to these bits. This adds an implicit restriction that
* no function will ever call notify_change with both ATTR_MODE and
* ATTR_KILL_S*ID set.
*/
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
(ia_valid & ATTR_MODE))
BUG(); if (ia_valid & ATTR_KILL_SUID) {
if (mode & S_ISUID) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = (inode->i_mode & ~S_ISUID);
}
}
if (ia_valid & ATTR_KILL_SGID) {
if (mode & S_ISGID) {
if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
return 0;
/*
* Verify that uid/gid changes are valid in the target
* namespace of the superblock.
*/
if (ia_valid & ATTR_UID &&
!vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns,
attr->ia_vfsuid))
return -EOVERFLOW;
if (ia_valid & ATTR_GID &&
!vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns,
attr->ia_vfsgid))
return -EOVERFLOW;
/* Don't allow modifications of files with invalid uids or
* gids unless those uids & gids are being made valid.
*/
if (!(ia_valid & ATTR_UID) &&
!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)))
return -EOVERFLOW;
if (!(ia_valid & ATTR_GID) &&
!vfsgid_valid(i_gid_into_vfsgid(idmap, inode)))
return -EOVERFLOW;
error = security_inode_setattr(idmap, dentry, attr);
if (error)
return error;
/*
* If ATTR_DELEG is set, then these attributes are being set on
* behalf of the holder of a write delegation. We want to avoid
* breaking the delegation in this case.
*/
if (!(ia_valid & ATTR_DELEG)) {
error = try_break_deleg(inode, delegated_inode);
if (error)
return error;
}
if (inode->i_op->setattr)
error = inode->i_op->setattr(idmap, dentry, attr);
else
error = simple_setattr(idmap, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid);
security_inode_post_setattr(idmap, dentry, ia_valid);
}
return error;
}
EXPORT_SYMBOL(notify_change);
// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/swap_state.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*
* Rewritten to use page cache, (C) 1998 Stephen Tweedie
*/
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/huge_mm.h>
#include <linux/shmem_fs.h>
#include "internal.h"
#include "swap.h"
/*
* swapper_space is a fiction, retained to simplify the path through
* vmscan's shrink_folio_list.
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.dirty_folio = noop_dirty_folio,
#ifdef CONFIG_MIGRATION
.migrate_folio = migrate_folio,
#endif
};
struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly;
static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly;
static bool enable_vma_readahead __read_mostly = true;
#define SWAP_RA_ORDER_CEILING 5
#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2)
#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1)
#define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK
#define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK)
#define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK)
#define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT)
#define SWAP_RA_ADDR(v) ((v) & PAGE_MASK)
#define SWAP_RA_VAL(addr, win, hits) \
(((addr) & PAGE_MASK) | \
(((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \
((hits) & SWAP_RA_HITS_MASK))
/* Initial readahead hits is 4 to start up with a small window */
#define GET_SWAP_RA_VAL(vma) \
(atomic_long_read(&(vma)->swap_readahead_info) ? : 4)
static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
void show_swap_cache_info(void)
{
printk("%lu pages in swap cache\n", total_swapcache_pages());
printk("Free swap = %ldkB\n", K(get_nr_swap_pages()));
printk("Total swap = %lukB\n", K(total_swap_pages));
}
void *get_shadow_from_swap_cache(swp_entry_t entry)
{
struct address_space *address_space = swap_address_space(entry);
pgoff_t idx = swap_cache_index(entry);
void *shadow;
shadow = xa_load(&address_space->i_pages, idx);
if (xa_is_value(shadow))
return shadow;
return NULL;
}
/*
* add_to_swap_cache resembles filemap_add_folio on swapper_space,
* but sets SwapCache flag and 'swap' instead of mapping and index.
*/
int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
gfp_t gfp, void **shadowp)
{
struct address_space *address_space = swap_address_space(entry);
pgoff_t idx = swap_cache_index(entry);
XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio));
unsigned long i, nr = folio_nr_pages(folio);
void *old;
xas_set_update(&xas, workingset_update_node);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);
folio_ref_add(folio, nr);
folio_set_swapcache(folio);
folio->swap = entry;
do {
xas_lock_irq(&xas);
xas_create_range(&xas);
if (xas_error(&xas))
goto unlock;
for (i = 0; i < nr; i++) {
VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio);
if (shadowp) {
old = xas_load(&xas);
if (xa_is_value(old))
*shadowp = old;
}
xas_store(&xas, folio);
xas_next(&xas);
}
address_space->nrpages += nr;
__node_stat_mod_folio(folio, NR_FILE_PAGES, nr);
__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
if (!xas_error(&xas))
return 0;
folio_clear_swapcache(folio);
folio_ref_sub(folio, nr);
return xas_error(&xas);
}
/*
* This must be called only on folios that have
* been verified to be in the swap cache.
*/
void __delete_from_swap_cache(struct folio *folio,
swp_entry_t entry, void *shadow)
{
struct address_space *address_space = swap_address_space(entry);
int i;
long nr = folio_nr_pages(folio);
pgoff_t idx = swap_cache_index(entry);
XA_STATE(xas, &address_space->i_pages, idx);
xas_set_update(&xas, workingset_update_node);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
for (i = 0; i < nr; i++) {
void *entry = xas_store(&xas, shadow);
VM_BUG_ON_PAGE(entry != folio, entry);
xas_next(&xas);
}
folio->swap.val = 0;
folio_clear_swapcache(folio);
address_space->nrpages -= nr;
__node_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr);
}
/*
* This must be called only on folios that have
* been verified to be in the swap cache and locked.
* It will never put the folio into the free list,
* the caller has a reference on the folio.
*/
void delete_from_swap_cache(struct folio *folio)
{
swp_entry_t entry = folio->swap;
struct address_space *address_space = swap_address_space(entry);
xa_lock_irq(&address_space->i_pages);
__delete_from_swap_cache(folio, entry, NULL);
xa_unlock_irq(&address_space->i_pages);
put_swap_folio(folio, entry);
folio_ref_sub(folio, folio_nr_pages(folio));
}
void clear_shadow_from_swap_cache(int type, unsigned long begin,
unsigned long end)
{
unsigned long curr = begin;
void *old;
for (;;) {
swp_entry_t entry = swp_entry(type, curr);
unsigned long index = curr & SWAP_ADDRESS_SPACE_MASK;
struct address_space *address_space = swap_address_space(entry);
XA_STATE(xas, &address_space->i_pages, index);
xas_set_update(&xas, workingset_update_node);
xa_lock_irq(&address_space->i_pages);
xas_for_each(&xas, old, min(index + (end - curr), SWAP_ADDRESS_SPACE_PAGES)) {
if (!xa_is_value(old))
continue;
xas_store(&xas, NULL);
}
xa_unlock_irq(&address_space->i_pages);
/* search the next swapcache until we meet end */
curr = ALIGN((curr + 1), SWAP_ADDRESS_SPACE_PAGES);
if (curr > end)
break;
}
}
/*
* If we are the only user, then try to free up the swap cache.
*
* Its ok to check the swapcache flag without the folio lock
* here because we are going to recheck again inside
* folio_free_swap() _with_ the lock.
* - Marcelo
*/
void free_swap_cache(struct folio *folio)
{ if (folio_test_swapcache(folio) && !folio_mapped(folio) && folio_trylock(folio)) { folio_free_swap(folio);
folio_unlock(folio);
}
}
/*
* Perform a free_page(), also freeing any swap cache associated with
* this page if it is the last user of the page.
*/
void free_page_and_swap_cache(struct page *page)
{
struct folio *folio = page_folio(page);
free_swap_cache(folio);
if (!is_huge_zero_folio(folio))
folio_put(folio);
}
/*
* Passed an array of pages, drop them all from swapcache and then release
* them. They are removed from the LRU and freed if this is their last use.
*/
void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
{
struct folio_batch folios;
unsigned int refs[PAGEVEC_SIZE];
folio_batch_init(&folios);
for (int i = 0; i < nr; i++) { struct folio *folio = page_folio(encoded_page_ptr(pages[i]));
free_swap_cache(folio);
refs[folios.nr] = 1;
if (unlikely(encoded_page_flags(pages[i]) &
ENCODED_PAGE_BIT_NR_PAGES_NEXT))
refs[folios.nr] = encoded_nr_pages(pages[++i]); if (folio_batch_add(&folios, folio) == 0) folios_put_refs(&folios, refs);
}
if (folios.nr) folios_put_refs(&folios, refs);
}
static inline bool swap_use_vma_readahead(void)
{
return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
}
/*
* Lookup a swap entry in the swap cache. A found folio will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the folio
* lock before returning.
*
* Caller must lock the swap device or hold a reference to keep it valid.
*/
struct folio *swap_cache_get_folio(swp_entry_t entry,
struct vm_area_struct *vma, unsigned long addr)
{
struct folio *folio;
folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
if (!IS_ERR(folio)) {
bool vma_ra = swap_use_vma_readahead();
bool readahead;
/*
* At the moment, we don't support PG_readahead for anon THP
* so let's bail out rather than confusing the readahead stat.
*/
if (unlikely(folio_test_large(folio)))
return folio;
readahead = folio_test_clear_readahead(folio);
if (vma && vma_ra) {
unsigned long ra_val;
int win, hits;
ra_val = GET_SWAP_RA_VAL(vma);
win = SWAP_RA_WIN(ra_val);
hits = SWAP_RA_HITS(ra_val);
if (readahead)
hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
atomic_long_set(&vma->swap_readahead_info,
SWAP_RA_VAL(addr, win, hits));
}
if (readahead) {
count_vm_event(SWAP_RA_HIT);
if (!vma || !vma_ra)
atomic_inc(&swapin_readahead_hits);
}
} else {
folio = NULL;
}
return folio;
}
/**
* filemap_get_incore_folio - Find and get a folio from the page or swap caches.
* @mapping: The address_space to search.
* @index: The page cache index.
*
* This differs from filemap_get_folio() in that it will also look for the
* folio in the swap cache.
*
* Return: The found folio or %NULL.
*/
struct folio *filemap_get_incore_folio(struct address_space *mapping,
pgoff_t index)
{
swp_entry_t swp;
struct swap_info_struct *si;
struct folio *folio = filemap_get_entry(mapping, index);
if (!folio)
return ERR_PTR(-ENOENT);
if (!xa_is_value(folio))
return folio;
if (!shmem_mapping(mapping))
return ERR_PTR(-ENOENT);
swp = radix_to_swp_entry(folio);
/* There might be swapin error entries in shmem mapping. */
if (non_swap_entry(swp))
return ERR_PTR(-ENOENT);
/* Prevent swapoff from happening to us */
si = get_swap_device(swp);
if (!si)
return ERR_PTR(-ENOENT);
index = swap_cache_index(swp);
folio = filemap_get_folio(swap_address_space(swp), index);
put_swap_device(si);
return folio;
}
struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
bool skip_if_exists)
{
struct swap_info_struct *si = swp_swap_info(entry);
struct folio *folio;
struct folio *new_folio = NULL;
struct folio *result = NULL;
void *shadow = NULL;
*new_page_allocated = false;
for (;;) {
int err;
/*
* First check the swap cache. Since this is normally
* called after swap_cache_get_folio() failed, re-calling
* that would confuse statistics.
*/
folio = filemap_get_folio(swap_address_space(entry),
swap_cache_index(entry));
if (!IS_ERR(folio))
goto got_folio;
/*
* Just skip read ahead for unused swap slot.
*/
if (!swap_entry_swapped(si, entry))
goto put_and_return;
/*
* Get a new folio to read into from swap. Allocate it now if
* new_folio not exist, before marking swap_map SWAP_HAS_CACHE,
* when -EEXIST will cause any racers to loop around until we
* add it to cache.
*/
if (!new_folio) {
new_folio = folio_alloc_mpol(gfp_mask, 0, mpol, ilx, numa_node_id());
if (!new_folio)
goto put_and_return;
}
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry, 1);
if (!err)
break;
else if (err != -EEXIST)
goto put_and_return;
/*
* Protect against a recursive call to __read_swap_cache_async()
* on the same entry waiting forever here because SWAP_HAS_CACHE
* is set but the folio is not the swap cache yet. This can
* happen today if mem_cgroup_swapin_charge_folio() below
* triggers reclaim through zswap, which may call
* __read_swap_cache_async() in the writeback path.
*/
if (skip_if_exists)
goto put_and_return;
/*
* We might race against __delete_from_swap_cache(), and
* stumble across a swap_map entry whose SWAP_HAS_CACHE
* has not yet been cleared. Or race against another
* __read_swap_cache_async(), which has set SWAP_HAS_CACHE
* in swap_map, but not yet added its folio to swap cache.
*/
schedule_timeout_uninterruptible(1);
}
/*
* The swap entry is ours to swap in. Prepare the new folio.
*/
__folio_set_locked(new_folio);
__folio_set_swapbacked(new_folio);
if (mem_cgroup_swapin_charge_folio(new_folio, NULL, gfp_mask, entry))
goto fail_unlock;
/* May fail (-ENOMEM) if XArray node allocation failed. */
if (add_to_swap_cache(new_folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
goto fail_unlock;
memcg1_swapin(entry, 1);
if (shadow)
workingset_refault(new_folio, shadow);
/* Caller will initiate read into locked new_folio */
folio_add_lru(new_folio);
*new_page_allocated = true;
folio = new_folio;
got_folio:
result = folio;
goto put_and_return;
fail_unlock:
put_swap_folio(new_folio, entry);
folio_unlock(new_folio);
put_and_return:
if (!(*new_page_allocated) && new_folio)
folio_put(new_folio);
return result;
}
/*
* Locate a page of swap in physical memory, reserving swap cache space
* and reading the disk if it is not already cached.
* A failure return means that either the page allocation failed or that
* the swap entry is no longer in use.
*
* get/put_swap_device() aren't needed to call this function, because
* __read_swap_cache_async() call them and swap_read_folio() holds the
* swap cache folio lock.
*/
struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
struct swap_iocb **plug)
{
struct swap_info_struct *si;
bool page_allocated;
struct mempolicy *mpol;
pgoff_t ilx;
struct folio *folio;
si = get_swap_device(entry);
if (!si)
return NULL;
mpol = get_vma_policy(vma, addr, 0, &ilx);
folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
&page_allocated, false);
mpol_cond_put(mpol);
if (page_allocated)
swap_read_folio(folio, plug);
put_swap_device(si);
return folio;
}
static unsigned int __swapin_nr_pages(unsigned long prev_offset,
unsigned long offset,
int hits,
int max_pages,
int prev_win)
{
unsigned int pages, last_ra;
/*
* This heuristic has been found to work well on both sequential and
* random loads, swapping to hard disk or to SSD: please don't ask
* what the "+ 2" means, it just happens to work well, that's all.
*/
pages = hits + 2;
if (pages == 2) {
/*
* We can have no readahead hits to judge by: but must not get
* stuck here forever, so check for an adjacent offset instead
* (and don't even bother to check whether swap type is same).
*/
if (offset != prev_offset + 1 && offset != prev_offset - 1)
pages = 1;
} else {
unsigned int roundup = 4;
while (roundup < pages)
roundup <<= 1;
pages = roundup;
}
if (pages > max_pages)
pages = max_pages;
/* Don't shrink readahead too fast */
last_ra = prev_win / 2;
if (pages < last_ra)
pages = last_ra;
return pages;
}
static unsigned long swapin_nr_pages(unsigned long offset)
{
static unsigned long prev_offset;
unsigned int hits, pages, max_pages;
static atomic_t last_readahead_pages;
max_pages = 1 << READ_ONCE(page_cluster);
if (max_pages <= 1)
return 1;
hits = atomic_xchg(&swapin_readahead_hits, 0);
pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
max_pages,
atomic_read(&last_readahead_pages));
if (!hits)
WRITE_ONCE(prev_offset, offset);
atomic_set(&last_readahead_pages, pages);
return pages;
}
/**
* swap_cluster_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
* @gfp_mask: memory allocation flags
* @mpol: NUMA memory allocation policy to be applied
* @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
*
* Returns the struct folio for entry and addr, after queueing swapin.
*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
* because it doesn't cost us any seek time. We also make sure to queue
* the 'original' request together with the readahead ones...
*
* Note: it is intentional that the same NUMA policy and interleave index
* are used for every page of the readahead: neighbouring pages on swap
* are fairly likely to have been swapped out from the same node.
*/
struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct mempolicy *mpol, pgoff_t ilx)
{
struct folio *folio;
unsigned long entry_offset = swp_offset(entry);
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
struct swap_info_struct *si = swp_swap_info(entry);
struct blk_plug plug;
struct swap_iocb *splug = NULL;
bool page_allocated;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
if (!start_offset) /* First page is swap header. */
start_offset++;
if (end_offset >= si->max)
end_offset = si->max - 1;
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
folio = __read_swap_cache_async(
swp_entry(swp_type(entry), offset),
gfp_mask, mpol, ilx, &page_allocated, false);
if (!folio)
continue;
if (page_allocated) {
swap_read_folio(folio, &splug);
if (offset != entry_offset) {
folio_set_readahead(folio);
count_vm_event(SWAP_RA);
}
}
folio_put(folio);
}
blk_finish_plug(&plug);
swap_read_unplug(splug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
/* The page was likely read above, so no need for plugging here */
folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
&page_allocated, false);
if (unlikely(page_allocated))
swap_read_folio(folio, NULL);
return folio;
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
struct address_space *spaces, *space;
unsigned int i, nr;
nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL);
if (!spaces)
return -ENOMEM;
for (i = 0; i < nr; i++) {
space = spaces + i;
xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ);
atomic_set(&space->i_mmap_writable, 0);
space->a_ops = &swap_aops;
/* swap cache doesn't use writeback related tags */
mapping_set_no_writeback_tags(space);
}
nr_swapper_spaces[type] = nr;
swapper_spaces[type] = spaces;
return 0;
}
void exit_swap_address_space(unsigned int type)
{
int i;
struct address_space *spaces = swapper_spaces[type];
for (i = 0; i < nr_swapper_spaces[type]; i++)
VM_WARN_ON_ONCE(!mapping_empty(&spaces[i]));
kvfree(spaces);
nr_swapper_spaces[type] = 0;
swapper_spaces[type] = NULL;
}
static int swap_vma_ra_win(struct vm_fault *vmf, unsigned long *start,
unsigned long *end)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long ra_val;
unsigned long faddr, prev_faddr, left, right;
unsigned int max_win, hits, prev_win, win;
max_win = 1 << min(READ_ONCE(page_cluster), SWAP_RA_ORDER_CEILING);
if (max_win == 1)
return 1;
faddr = vmf->address;
ra_val = GET_SWAP_RA_VAL(vma);
prev_faddr = SWAP_RA_ADDR(ra_val);
prev_win = SWAP_RA_WIN(ra_val);
hits = SWAP_RA_HITS(ra_val);
win = __swapin_nr_pages(PFN_DOWN(prev_faddr), PFN_DOWN(faddr), hits,
max_win, prev_win);
atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(faddr, win, 0));
if (win == 1)
return 1;
if (faddr == prev_faddr + PAGE_SIZE)
left = faddr;
else if (prev_faddr == faddr + PAGE_SIZE)
left = faddr - (win << PAGE_SHIFT) + PAGE_SIZE;
else
left = faddr - (((win - 1) / 2) << PAGE_SHIFT);
right = left + (win << PAGE_SHIFT);
if ((long)left < 0)
left = 0;
*start = max3(left, vma->vm_start, faddr & PMD_MASK);
*end = min3(right, vma->vm_end, (faddr & PMD_MASK) + PMD_SIZE);
return win;
}
/**
* swap_vma_readahead - swap in pages in hope we need them soon
* @targ_entry: swap entry of the targeted memory
* @gfp_mask: memory allocation flags
* @mpol: NUMA memory allocation policy to be applied
* @targ_ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
* @vmf: fault information
*
* Returns the struct folio for entry and addr, after queueing swapin.
*
* Primitive swap readahead code. We simply read in a few pages whose
* virtual addresses are around the fault address in the same vma.
*
* Caller must hold read mmap_lock if vmf->vma is not NULL.
*
*/
static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf)
{
struct blk_plug plug;
struct swap_iocb *splug = NULL;
struct folio *folio;
pte_t *pte = NULL, pentry;
int win;
unsigned long start, end, addr;
swp_entry_t entry;
pgoff_t ilx;
bool page_allocated;
win = swap_vma_ra_win(vmf, &start, &end);
if (win == 1)
goto skip;
ilx = targ_ilx - PFN_DOWN(vmf->address - start);
blk_start_plug(&plug);
for (addr = start; addr < end; ilx++, addr += PAGE_SIZE) {
if (!pte++) {
pte = pte_offset_map(vmf->pmd, addr);
if (!pte)
break;
}
pentry = ptep_get_lockless(pte);
if (!is_swap_pte(pentry))
continue;
entry = pte_to_swp_entry(pentry);
if (unlikely(non_swap_entry(entry)))
continue;
pte_unmap(pte);
pte = NULL;
folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
&page_allocated, false);
if (!folio)
continue;
if (page_allocated) {
swap_read_folio(folio, &splug);
if (addr != vmf->address) {
folio_set_readahead(folio);
count_vm_event(SWAP_RA);
}
}
folio_put(folio);
}
if (pte)
pte_unmap(pte);
blk_finish_plug(&plug);
swap_read_unplug(splug);
lru_add_drain();
skip:
/* The folio was likely read above, so no need for plugging here */
folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
&page_allocated, false);
if (unlikely(page_allocated))
swap_read_folio(folio, NULL);
return folio;
}
/**
* swapin_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
* @gfp_mask: memory allocation flags
* @vmf: fault information
*
* Returns the struct folio for entry and addr, after queueing swapin.
*
* It's a main entry function for swap readahead. By the configuration,
* it will read ahead blocks by cluster-based(ie, physical disk based)
* or vma-based(ie, virtual address based on faulty address) readahead.
*/
struct folio *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_fault *vmf)
{
struct mempolicy *mpol;
pgoff_t ilx;
struct folio *folio;
mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx);
folio = swap_use_vma_readahead() ?
swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf) :
swap_cluster_readahead(entry, gfp_mask, mpol, ilx);
mpol_cond_put(mpol);
return folio;
}
#ifdef CONFIG_SYSFS
static ssize_t vma_ra_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%s\n", str_true_false(enable_vma_readahead));
}
static ssize_t vma_ra_enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret;
ret = kstrtobool(buf, &enable_vma_readahead);
if (ret)
return ret;
return count;
}
static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled);
static struct attribute *swap_attrs[] = {
&vma_ra_enabled_attr.attr,
NULL,
};
static const struct attribute_group swap_attr_group = {
.attrs = swap_attrs,
};
static int __init swap_init_sysfs(void)
{
int err;
struct kobject *swap_kobj;
swap_kobj = kobject_create_and_add("swap", mm_kobj);
if (!swap_kobj) {
pr_err("failed to create swap kobject\n");
return -ENOMEM;
}
err = sysfs_create_group(swap_kobj, &swap_attr_group);
if (err) {
pr_err("failed to register swap group\n");
goto delete_obj;
}
return 0;
delete_obj:
kobject_put(swap_kobj);
return err;
}
subsys_initcall(swap_init_sysfs);
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/kernel/setup.c
*
* Copyright (C) 1995-2001 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/acpi.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/console.h>
#include <linux/cache.h>
#include <linux/screen_info.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/root_dev.h>
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/panic_notifier.h>
#include <linux/proc_fs.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/efi.h>
#include <linux/psci.h>
#include <linux/sched/task.h>
#include <linux/scs.h>
#include <linux/mm.h>
#include <asm/acpi.h>
#include <asm/fixmap.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/daifflags.h>
#include <asm/elf.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
#include <asm/numa.h>
#include <asm/rsi.h>
#include <asm/scs.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>
#include <asm/efi.h>
#include <asm/xen/hypervisor.h>
#include <asm/mmu_context.h>
static int num_standard_resources;
static struct resource *standard_resources;
phys_addr_t __fdt_pointer __initdata;
u64 mmu_enabled_at_boot __initdata;
/*
* Standard memory resources
*/
static struct resource mem_res[] = {
{
.name = "Kernel code",
.start = 0,
.end = 0,
.flags = IORESOURCE_SYSTEM_RAM
},
{
.name = "Kernel data",
.start = 0,
.end = 0,
.flags = IORESOURCE_SYSTEM_RAM
}
};
#define kernel_code mem_res[0]
#define kernel_data mem_res[1]
/*
* The recorded values of x0 .. x3 upon kernel entry.
*/
u64 __cacheline_aligned boot_args[4];
void __init smp_setup_processor_id(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
set_cpu_logical_map(0, mpidr);
pr_info("Booting Linux on physical CPU 0x%010lx [0x%08x]\n",
(unsigned long)mpidr, read_cpuid_id());
}
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
return phys_id == cpu_logical_map(cpu);
}
struct mpidr_hash mpidr_hash;
/**
* smp_build_mpidr_hash - Pre-compute shifts required at each affinity
* level in order to build a linear index from an
* MPIDR value. Resulting algorithm is a collision
* free hash carried out through shifting and ORing
*/
static void __init smp_build_mpidr_hash(void)
{
u32 i, affinity, fs[4], bits[4], ls;
u64 mask = 0;
/*
* Pre-scan the list of MPIDRS and filter out bits that do
* not contribute to affinity levels, ie they never toggle.
*/
for_each_possible_cpu(i)
mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
pr_debug("mask of set bits %#llx\n", mask);
/*
* Find and stash the last and first bit set at all affinity levels to
* check how many bits are required to represent them.
*/
for (i = 0; i < 4; i++) {
affinity = MPIDR_AFFINITY_LEVEL(mask, i);
/*
* Find the MSB bit and LSB bits position
* to determine how many bits are required
* to express the affinity level.
*/
ls = fls(affinity);
fs[i] = affinity ? ffs(affinity) - 1 : 0;
bits[i] = ls - fs[i];
}
/*
* An index can be created from the MPIDR_EL1 by isolating the
* significant bits at each affinity level and by shifting
* them in order to compress the 32 bits values space to a
* compressed set of values. This is equivalent to hashing
* the MPIDR_EL1 through shifting and ORing. It is a collision free
* hash though not minimal since some levels might contain a number
* of CPUs that is not an exact power of 2 and their bit
* representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
*/
mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
(bits[1] + bits[0]);
mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
fs[3] - (bits[2] + bits[1] + bits[0]);
mpidr_hash.mask = mask;
mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
mpidr_hash.shift_aff[0],
mpidr_hash.shift_aff[1],
mpidr_hash.shift_aff[2],
mpidr_hash.shift_aff[3],
mpidr_hash.mask,
mpidr_hash.bits);
/*
* 4x is an arbitrary value used to warn on a hash table much bigger
* than expected on most systems.
*/
if (mpidr_hash_size() > 4 * num_possible_cpus())
pr_warn("Large number of MPIDR hash buckets detected\n");
}
static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
int size;
void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
const char *name;
if (dt_virt)
memblock_reserve(dt_phys, size);
/*
* dt_virt is a fixmap address, hence __pa(dt_virt) can't be used.
* Pass dt_phys directly.
*/
if (!early_init_dt_scan(dt_virt, dt_phys)) {
pr_crit("\n"
"Error: invalid device tree blob at physical address %pa (virtual address 0x%px)\n"
"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
"\nPlease check your bootloader.",
&dt_phys, dt_virt);
/*
* Note that in this _really_ early stage we cannot even BUG()
* or oops, so the least terrible thing to do is cpu_relax(),
* or else we could end-up printing non-initialized data, etc.
*/
while (true)
cpu_relax();
}
/* Early fixups are done, map the FDT as read-only now */
fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
name = of_flat_dt_get_machine_name();
if (!name)
return;
pr_info("Machine model: %s\n", name);
dump_stack_set_arch_desc("%s (DT)", name);
}
static void __init request_standard_resources(void)
{
struct memblock_region *region;
struct resource *res;
unsigned long i = 0;
size_t res_size;
kernel_code.start = __pa_symbol(_stext);
kernel_code.end = __pa_symbol(__init_begin - 1);
kernel_data.start = __pa_symbol(_sdata);
kernel_data.end = __pa_symbol(_end - 1);
insert_resource(&iomem_resource, &kernel_code);
insert_resource(&iomem_resource, &kernel_data);
num_standard_resources = memblock.memory.cnt;
res_size = num_standard_resources * sizeof(*standard_resources);
standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES);
for_each_mem_region(region) {
res = &standard_resources[i++];
if (memblock_is_nomap(region)) {
res->name = "reserved";
res->flags = IORESOURCE_MEM;
res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
} else {
res->name = "System RAM";
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
}
insert_resource(&iomem_resource, res);
}
}
static int __init reserve_memblock_reserved_regions(void)
{
u64 i, j;
for (i = 0; i < num_standard_resources; ++i) {
struct resource *mem = &standard_resources[i];
phys_addr_t r_start, r_end, mem_size = resource_size(mem);
if (!memblock_is_region_reserved(mem->start, mem_size))
continue;
for_each_reserved_mem_range(j, &r_start, &r_end) {
resource_size_t start, end;
start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
if (start > mem->end || end < mem->start)
continue;
reserve_region_with_split(mem, start, end, "reserved");
}
}
return 0;
}
arch_initcall(reserve_memblock_reserved_regions);
u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
u64 cpu_logical_map(unsigned int cpu)
{
return __cpu_logical_map[cpu];
}
void __init __no_sanitize_address setup_arch(char **cmdline_p)
{
setup_initial_init_mm(_stext, _etext, _edata, _end);
*cmdline_p = boot_command_line;
kaslr_init();
early_fixmap_init();
early_ioremap_init();
setup_machine_fdt(__fdt_pointer);
/*
* Initialise the static keys early as they may be enabled by the
* cpufeature code and early parameters.
*/
jump_label_init();
parse_early_param();
dynamic_scs_init();
/*
* The primary CPU enters the kernel with all DAIF exceptions masked.
*
* We must unmask Debug and SError before preemption or scheduling is
* possible to ensure that these are consistently unmasked across
* threads, and we want to unmask SError as soon as possible after
* initializing earlycon so that we can report any SErrors immediately.
*
* IRQ and FIQ will be unmasked after the root irqchip has been
* detected and initialized.
*/
local_daif_restore(DAIF_PROCCTX_NOIRQ);
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
*/
cpu_uninstall_idmap();
xen_early_init();
efi_init();
if (!efi_enabled(EFI_BOOT)) {
if ((u64)_text % MIN_KIMG_ALIGN)
pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!");
WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND,
FW_BUG "Booted with MMU enabled!");
}
arm64_memblock_init();
paging_init();
acpi_table_upgrade();
/* Parse the ACPI tables for possible boot-time configuration */
acpi_boot_table_init();
if (acpi_disabled)
unflatten_device_tree();
bootmem_init();
kasan_init();
request_standard_resources();
early_ioremap_reset();
if (acpi_disabled)
psci_dt_init();
else
psci_acpi_init();
arm64_rsi_init();
init_bootcpu_ops();
smp_init_cpus();
smp_build_mpidr_hash();
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
/*
* Make sure init_thread_info.ttbr0 always generates translation
* faults in case uaccess_enable() is inadvertently called by the init
* thread.
*/
init_task.thread_info.ttbr0 = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
#endif
if (boot_args[1] || boot_args[2] || boot_args[3]) {
pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
"This indicates a broken bootloader or old kernel\n",
boot_args[1], boot_args[2], boot_args[3]);
}
}
static inline bool cpu_can_disable(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
const struct cpu_operations *ops = get_cpu_ops(cpu);
if (ops && ops->cpu_can_disable)
return ops->cpu_can_disable(cpu);
#endif
return false;
}
bool arch_cpu_is_hotpluggable(int num)
{
return cpu_can_disable(num);
}
static void dump_kernel_offset(void)
{
const unsigned long offset = kaslr_offset();
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
offset, KIMAGE_VADDR);
pr_emerg("PHYS_OFFSET: 0x%llx\n", PHYS_OFFSET);
} else {
pr_emerg("Kernel Offset: disabled\n");
}
}
static int arm64_panic_block_dump(struct notifier_block *self,
unsigned long v, void *p)
{
dump_kernel_offset();
dump_cpu_features();
dump_mem_limit();
return 0;
}
static struct notifier_block arm64_panic_block = {
.notifier_call = arm64_panic_block_dump
};
static int __init register_arm64_panic_block(void)
{
atomic_notifier_chain_register(&panic_notifier_list,
&arm64_panic_block);
return 0;
}
device_initcall(register_arm64_panic_block);
static int __init check_mmu_enabled_at_boot(void)
{
if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot)
panic("Non-EFI boot detected with MMU and caches enabled");
return 0;
}
device_initcall_sync(check_mmu_enabled_at_boot);
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/signal.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 1997-11-02 Modified for POSIX.1b signals by Richard Henderson
*
* 2003-06-02 Jim Houston - Concurrent Computer Corp.
* Changes to use preallocated sigqueue structures
* to allow signals to be sent reliably.
*/
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/user.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/coredump.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/signalfd.h>
#include <linux/ratelimit.h>
#include <linux/task_work.h>
#include <linux/capability.h>
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
#include <linux/uprobes.h>
#include <linux/compat.h>
#include <linux/cn_proc.h>
#include <linux/compiler.h>
#include <linux/posix-timers.h>
#include <linux/cgroup.h>
#include <linux/audit.h>
#include <linux/sysctl.h>
#include <uapi/linux/pidfd.h>
#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
#include <asm/param.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
#include <asm/siginfo.h>
#include <asm/cacheflush.h>
#include <asm/syscall.h> /* for syscall_get_* */
#include "time/posix-timers.h"
/*
* SLAB caches for signal bits.
*/
static struct kmem_cache *sigqueue_cachep;
int print_fatal_signals __read_mostly;
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
}
static inline bool sig_handler_ignored(void __user *handler, int sig)
{
/* Is it explicitly or implicitly ignored? */
return handler == SIG_IGN || (handler == SIG_DFL && sig_kernel_ignore(sig));
}
static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
{
void __user *handler;
handler = sig_handler(t, sig);
/* SIGKILL and SIGSTOP may not be sent to the global init */
if (unlikely(is_global_init(t) && sig_kernel_only(sig)))
return true;
if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && handler == SIG_DFL && !(force && sig_kernel_only(sig)))
return true;
/* Only allow kernel generated signals to this kthread */
if (unlikely((t->flags & PF_KTHREAD) &&
(handler == SIG_KTHREAD_KERNEL) && !force))
return true;
return sig_handler_ignored(handler, sig);
}
static bool sig_ignored(struct task_struct *t, int sig, bool force)
{
/*
* Blocked signals are never ignored, since the
* signal handler may change by the time it is
* unblocked.
*/
if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
return false;
/*
* Tracers may want to know about even ignored signal unless it
* is SIGKILL which can't be reported anyway but can be ignored
* by SIGNAL_UNKILLABLE task.
*/
if (t->ptrace && sig != SIGKILL)
return false;
return sig_task_ignored(t, sig, force);
}
/*
* Re-calculate pending state from the set of locally pending
* signals, globally pending signals, and blocked signals.
*/
static inline bool has_pending_signals(sigset_t *signal, sigset_t *blocked)
{
unsigned long ready;
long i;
switch (_NSIG_WORDS) {
default:
for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;)
ready |= signal->sig[i] &~ blocked->sig[i];
break;
case 4: ready = signal->sig[3] &~ blocked->sig[3];
ready |= signal->sig[2] &~ blocked->sig[2];
ready |= signal->sig[1] &~ blocked->sig[1];
ready |= signal->sig[0] &~ blocked->sig[0];
break;
case 2: ready = signal->sig[1] &~ blocked->sig[1];
ready |= signal->sig[0] &~ blocked->sig[0];
break;
case 1: ready = signal->sig[0] &~ blocked->sig[0];
}
return ready != 0;
}
#define PENDING(p,b) has_pending_signals(&(p)->signal, (b))
static bool recalc_sigpending_tsk(struct task_struct *t)
{
if ((t->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) || PENDING(&t->pending, &t->blocked) || PENDING(&t->signal->shared_pending, &t->blocked) ||
cgroup_task_frozen(t)) {
set_tsk_thread_flag(t, TIF_SIGPENDING);
return true;
}
/*
* We must never clear the flag in another thread, or in current
* when it's possible the current syscall is returning -ERESTART*.
* So we don't clear it here, and only callers who know they should do.
*/
return false;
}
void recalc_sigpending(void)
{ if (!recalc_sigpending_tsk(current) && !freezing(current)) { if (unlikely(test_thread_flag(TIF_SIGPENDING))) clear_thread_flag(TIF_SIGPENDING);
}
}
EXPORT_SYMBOL(recalc_sigpending);
void calculate_sigpending(void)
{
/* Have any signals or users of TIF_SIGPENDING been delayed
* until after fork?
*/
spin_lock_irq(¤t->sighand->siglock);
set_tsk_thread_flag(current, TIF_SIGPENDING);
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
}
/* Given the mask, find the first available signal that should be serviced. */
#define SYNCHRONOUS_MASK \
(sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS))
int next_signal(struct sigpending *pending, sigset_t *mask)
{
unsigned long i, *s, *m, x;
int sig = 0;
s = pending->signal.sig;
m = mask->sig;
/*
* Handle the first word specially: it contains the
* synchronous signals that need to be dequeued first.
*/
x = *s &~ *m;
if (x) {
if (x & SYNCHRONOUS_MASK)
x &= SYNCHRONOUS_MASK;
sig = ffz(~x) + 1;
return sig;
}
switch (_NSIG_WORDS) {
default:
for (i = 1; i < _NSIG_WORDS; ++i) {
x = *++s &~ *++m;
if (!x)
continue;
sig = ffz(~x) + i*_NSIG_BPW + 1;
break;
}
break;
case 2:
x = s[1] &~ m[1];
if (!x)
break;
sig = ffz(~x) + _NSIG_BPW + 1;
break;
case 1:
/* Nothing to do */
break;
}
return sig;
}
static inline void print_dropped_signal(int sig)
{
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
if (!print_fatal_signals)
return;
if (!__ratelimit(&ratelimit_state))
return;
pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
current->comm, current->pid, sig);
}
/**
* task_set_jobctl_pending - set jobctl pending bits
* @task: target task
* @mask: pending bits to set
*
* Clear @mask from @task->jobctl. @mask must be subset of
* %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK |
* %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is
* cleared. If @task is already being killed or exiting, this function
* becomes noop.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*
* RETURNS:
* %true if @mask is set, %false if made noop because @task was dying.
*/
bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
{
BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME |
JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
return false;
if (mask & JOBCTL_STOP_SIGMASK)
task->jobctl &= ~JOBCTL_STOP_SIGMASK;
task->jobctl |= mask;
return true;
}
/**
* task_clear_jobctl_trapping - clear jobctl trapping bit
* @task: target task
*
* If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED.
* Clear it and wake up the ptracer. Note that we don't need any further
* locking. @task->siglock guarantees that @task->parent points to the
* ptracer.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*/
void task_clear_jobctl_trapping(struct task_struct *task)
{
if (unlikely(task->jobctl & JOBCTL_TRAPPING)) {
task->jobctl &= ~JOBCTL_TRAPPING;
smp_mb(); /* advised by wake_up_bit() */
wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT);
}
}
/**
* task_clear_jobctl_pending - clear jobctl pending bits
* @task: target task
* @mask: pending bits to clear
*
* Clear @mask from @task->jobctl. @mask must be subset of
* %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other
* STOP bits are cleared together.
*
* If clearing of @mask leaves no stop or trap pending, this function calls
* task_clear_jobctl_trapping().
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*/
void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask)
{
BUG_ON(mask & ~JOBCTL_PENDING_MASK);
if (mask & JOBCTL_STOP_PENDING)
mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED;
task->jobctl &= ~mask;
if (!(task->jobctl & JOBCTL_PENDING_MASK)) task_clear_jobctl_trapping(task);
}
/**
* task_participate_group_stop - participate in a group stop
* @task: task participating in a group stop
*
* @task has %JOBCTL_STOP_PENDING set and is participating in a group stop.
* Group stop states are cleared and the group stop count is consumed if
* %JOBCTL_STOP_CONSUME was set. If the consumption completes the group
* stop, the appropriate `SIGNAL_*` flags are set.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*
* RETURNS:
* %true if group stop completion should be notified to the parent, %false
* otherwise.
*/
static bool task_participate_group_stop(struct task_struct *task)
{
struct signal_struct *sig = task->signal;
bool consume = task->jobctl & JOBCTL_STOP_CONSUME;
WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING));
task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING);
if (!consume)
return false;
if (!WARN_ON_ONCE(sig->group_stop_count == 0))
sig->group_stop_count--;
/*
* Tell the caller to notify completion iff we are entering into a
* fresh group stop. Read comment in do_signal_stop() for details.
*/
if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED);
return true;
}
return false;
}
void task_join_group_stop(struct task_struct *task)
{
unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
struct signal_struct *sig = current->signal;
if (sig->group_stop_count) {
sig->group_stop_count++;
mask |= JOBCTL_STOP_CONSUME;
} else if (!(sig->flags & SIGNAL_STOP_STOPPED))
return;
/* Have the new thread join an on-going signal group stop */
task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
}
static struct ucounts *sig_get_ucounts(struct task_struct *t, int sig,
int override_rlimit)
{
struct ucounts *ucounts;
long sigpending;
/*
* Protect access to @t credentials. This can go away when all
* callers hold rcu read lock.
*
* NOTE! A pending signal will hold on to the user refcount,
* and we get/put the refcount only when the sigpending count
* changes from/to zero.
*/
rcu_read_lock(); ucounts = task_ucounts(t);
sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING,
override_rlimit);
rcu_read_unlock(); if (!sigpending)
return NULL;
if (unlikely(!override_rlimit && sigpending > task_rlimit(t, RLIMIT_SIGPENDING))) { dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
print_dropped_signal(sig);
return NULL;
}
return ucounts;
}
static void __sigqueue_init(struct sigqueue *q, struct ucounts *ucounts,
const unsigned int sigqueue_flags)
{
INIT_LIST_HEAD(&q->list);
q->flags = sigqueue_flags;
q->ucounts = ucounts;
}
/*
* allocate a new signal queue record
* - this may be called without locks if and only if t == current, otherwise an
* appropriate lock must be held to stop the target task from exiting
*/
static struct sigqueue *sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
int override_rlimit)
{
struct ucounts *ucounts = sig_get_ucounts(t, sig, override_rlimit);
struct sigqueue *q;
if (!ucounts)
return NULL;
q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
if (!q) {
dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
return NULL;
}
__sigqueue_init(q, ucounts, 0);
return q;
}
static void __sigqueue_free(struct sigqueue *q)
{
if (q->flags & SIGQUEUE_PREALLOC) {
posixtimer_sigqueue_putref(q);
return;
}
if (q->ucounts) { dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING);
q->ucounts = NULL;
}
kmem_cache_free(sigqueue_cachep, q);
}
void flush_sigqueue(struct sigpending *queue)
{
struct sigqueue *q;
sigemptyset(&queue->signal);
while (!list_empty(&queue->list)) {
q = list_entry(queue->list.next, struct sigqueue , list);
list_del_init(&q->list);
__sigqueue_free(q);
}
}
/*
* Flush all pending signals for this kthread.
*/
void flush_signals(struct task_struct *t)
{
unsigned long flags;
spin_lock_irqsave(&t->sighand->siglock, flags);
clear_tsk_thread_flag(t, TIF_SIGPENDING);
flush_sigqueue(&t->pending);
flush_sigqueue(&t->signal->shared_pending);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
}
EXPORT_SYMBOL(flush_signals);
void ignore_signals(struct task_struct *t)
{
int i;
for (i = 0; i < _NSIG; ++i)
t->sighand->action[i].sa.sa_handler = SIG_IGN;
flush_signals(t);
}
/*
* Flush all handlers for a task.
*/
void
flush_signal_handlers(struct task_struct *t, int force_default)
{
int i;
struct k_sigaction *ka = &t->sighand->action[0];
for (i = _NSIG ; i != 0 ; i--) {
if (force_default || ka->sa.sa_handler != SIG_IGN)
ka->sa.sa_handler = SIG_DFL;
ka->sa.sa_flags = 0;
#ifdef __ARCH_HAS_SA_RESTORER
ka->sa.sa_restorer = NULL;
#endif
sigemptyset(&ka->sa.sa_mask);
ka++;
}
}
bool unhandled_signal(struct task_struct *tsk, int sig)
{
void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
if (is_global_init(tsk))
return true;
if (handler != SIG_IGN && handler != SIG_DFL)
return false;
/* If dying, we handle all new signals by ignoring them */
if (fatal_signal_pending(tsk))
return false;
/* if ptraced, let the tracer determine */
return !tsk->ptrace;
}
static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info,
struct sigqueue **timer_sigq)
{
struct sigqueue *q, *first = NULL;
/*
* Collect the siginfo appropriate to this signal. Check if
* there is another siginfo for the same signal.
*/
list_for_each_entry(q, &list->list, list) {
if (q->info.si_signo == sig) {
if (first)
goto still_pending;
first = q;
}
}
sigdelset(&list->signal, sig);
if (first) {
still_pending:
list_del_init(&first->list);
copy_siginfo(info, &first->info);
/*
* posix-timer signals are preallocated and freed when the last
* reference count is dropped in posixtimer_deliver_signal() or
* immediately on timer deletion when the signal is not pending.
* Spare the extra round through __sigqueue_free() which is
* ignoring preallocated signals.
*/
if (unlikely((first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER)))
*timer_sigq = first;
else
__sigqueue_free(first);
} else {
/*
* Ok, it wasn't in the queue. This must be
* a fast-pathed signal or we must have been
* out of queue space. So zero out the info.
*/
clear_siginfo(info);
info->si_signo = sig;
info->si_errno = 0;
info->si_code = SI_USER;
info->si_pid = 0;
info->si_uid = 0;
}
}
static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
kernel_siginfo_t *info, struct sigqueue **timer_sigq)
{
int sig = next_signal(pending, mask);
if (sig)
collect_signal(sig, pending, info, timer_sigq);
return sig;
}
/*
* Try to dequeue a signal. If a deliverable signal is found fill in the
* caller provided siginfo and return the signal number. Otherwise return
* 0.
*/
int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type)
{
struct task_struct *tsk = current;
struct sigqueue *timer_sigq;
int signr;
lockdep_assert_held(&tsk->sighand->siglock);
again:
*type = PIDTYPE_PID;
timer_sigq = NULL;
signr = __dequeue_signal(&tsk->pending, mask, info, &timer_sigq);
if (!signr) {
*type = PIDTYPE_TGID;
signr = __dequeue_signal(&tsk->signal->shared_pending,
mask, info, &timer_sigq);
if (unlikely(signr == SIGALRM))
posixtimer_rearm_itimer(tsk);
}
recalc_sigpending();
if (!signr)
return 0;
if (unlikely(sig_kernel_stop(signr))) {
/*
* Set a marker that we have dequeued a stop signal. Our
* caller might release the siglock and then the pending
* stop signal it is about to process is no longer in the
* pending bitmasks, but must still be cleared by a SIGCONT
* (and overruled by a SIGKILL). So those cases clear this
* shared flag after we've set it. Note that this flag may
* remain set after the signal we return is ignored or
* handled. That doesn't matter because its only purpose
* is to alert stop-signal processing code when another
* processor has come along and cleared the flag.
*/
current->jobctl |= JOBCTL_STOP_DEQUEUED;
}
if (IS_ENABLED(CONFIG_POSIX_TIMERS) && unlikely(timer_sigq)) {
if (!posixtimer_deliver_signal(info, timer_sigq))
goto again;
}
return signr;
}
EXPORT_SYMBOL_GPL(dequeue_signal);
static int dequeue_synchronous_signal(kernel_siginfo_t *info)
{
struct task_struct *tsk = current;
struct sigpending *pending = &tsk->pending;
struct sigqueue *q, *sync = NULL;
/*
* Might a synchronous signal be in the queue?
*/
if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK))
return 0;
/*
* Return the first synchronous signal in the queue.
*/
list_for_each_entry(q, &pending->list, list) {
/* Synchronous signals have a positive si_code */
if ((q->info.si_code > SI_USER) &&
(sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
sync = q;
goto next;
}
}
return 0;
next:
/*
* Check if there is another siginfo for the same signal.
*/
list_for_each_entry_continue(q, &pending->list, list) {
if (q->info.si_signo == sync->info.si_signo)
goto still_pending;
}
sigdelset(&pending->signal, sync->info.si_signo);
recalc_sigpending();
still_pending:
list_del_init(&sync->list);
copy_siginfo(info, &sync->info);
__sigqueue_free(sync);
return info->si_signo;
}
/*
* Tell a process that it has a new active signal..
*
* NOTE! we rely on the previous spin_lock to
* lock interrupts for us! We can only be called with
* "siglock" held, and the local interrupt must
* have been disabled when that got acquired!
*
* No need to set need_resched since signal event passing
* goes through ->blocked
*/
void signal_wake_up_state(struct task_struct *t, unsigned int state)
{
lockdep_assert_held(&t->sighand->siglock); set_tsk_thread_flag(t, TIF_SIGPENDING);
/*
* TASK_WAKEKILL also means wake it up in the stopped/traced/killable
* case. We don't check t->state here because there is a race with it
* executing another processor and just now entering stopped state.
* By using wake_up_state, we ensure the process will wake up and
* handle its death signal.
*/
if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t);
}
static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q);
static void sigqueue_free_ignored(struct task_struct *tsk, struct sigqueue *q)
{
if (likely(!(q->flags & SIGQUEUE_PREALLOC) || q->info.si_code != SI_TIMER))
__sigqueue_free(q);
else
posixtimer_sig_ignore(tsk, q);
}
/* Remove signals in mask from the pending set and queue. */
static void flush_sigqueue_mask(struct task_struct *p, sigset_t *mask, struct sigpending *s)
{
struct sigqueue *q, *n;
sigset_t m;
lockdep_assert_held(&p->sighand->siglock);
sigandsets(&m, mask, &s->signal);
if (sigisemptyset(&m))
return;
sigandnsets(&s->signal, &s->signal, mask);
list_for_each_entry_safe(q, n, &s->list, list) {
if (sigismember(mask, q->info.si_signo)) {
list_del_init(&q->list);
sigqueue_free_ignored(p, q);
}
}
}
static inline int is_si_special(const struct kernel_siginfo *info)
{
return info <= SEND_SIG_PRIV;
}
static inline bool si_fromuser(const struct kernel_siginfo *info)
{
return info == SEND_SIG_NOINFO ||
(!is_si_special(info) && SI_FROMUSER(info));
}
/*
* called with RCU read lock from check_kill_permission()
*/
static bool kill_ok_by_cred(struct task_struct *t)
{
const struct cred *cred = current_cred();
const struct cred *tcred = __task_cred(t);
return uid_eq(cred->euid, tcred->suid) ||
uid_eq(cred->euid, tcred->uid) ||
uid_eq(cred->uid, tcred->suid) ||
uid_eq(cred->uid, tcred->uid) ||
ns_capable(tcred->user_ns, CAP_KILL);
}
/*
* Bad permissions for sending the signal
* - the caller must hold the RCU read lock
*/
static int check_kill_permission(int sig, struct kernel_siginfo *info,
struct task_struct *t)
{
struct pid *sid;
int error;
if (!valid_signal(sig))
return -EINVAL;
if (!si_fromuser(info))
return 0;
error = audit_signal_info(sig, t); /* Let audit system see the signal */
if (error)
return error;
if (!same_thread_group(current, t) &&
!kill_ok_by_cred(t)) {
switch (sig) {
case SIGCONT:
sid = task_session(t);
/*
* We don't return the error if sid == NULL. The
* task was unhashed, the caller must notice this.
*/
if (!sid || sid == task_session(current))
break;
fallthrough;
default:
return -EPERM;
}
}
return security_task_kill(t, info, sig, NULL);
}
/**
* ptrace_trap_notify - schedule trap to notify ptracer
* @t: tracee wanting to notify tracer
*
* This function schedules sticky ptrace trap which is cleared on the next
* TRAP_STOP to notify ptracer of an event. @t must have been seized by
* ptracer.
*
* If @t is running, STOP trap will be taken. If trapped for STOP and
* ptracer is listening for events, tracee is woken up so that it can
* re-trap for the new event. If trapped otherwise, STOP trap will be
* eventually taken without returning to userland after the existing traps
* are finished by PTRACE_CONT.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*/
static void ptrace_trap_notify(struct task_struct *t)
{
WARN_ON_ONCE(!(t->ptrace & PT_SEIZED));
lockdep_assert_held(&t->sighand->siglock);
task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
}
/*
* Handle magic process-wide effects of stop/continue signals. Unlike
* the signal actions, these happen immediately at signal-generation
* time regardless of blocking, ignoring, or handling. This does the
* actual continuing for SIGCONT, but not the actual stopping for stop
* signals. The process stop is done as a signal action for SIG_DFL.
*
* Returns true if the signal should be actually delivered, otherwise
* it should be dropped.
*/
static bool prepare_signal(int sig, struct task_struct *p, bool force)
{
struct signal_struct *signal = p->signal;
struct task_struct *t;
sigset_t flush;
if (signal->flags & SIGNAL_GROUP_EXIT) {
if (signal->core_state)
return sig == SIGKILL;
/*
* The process is in the middle of dying, drop the signal.
*/
return false;
} else if (sig_kernel_stop(sig)) {
/*
* This is a stop signal. Remove SIGCONT from all queues.
*/
siginitset(&flush, sigmask(SIGCONT));
flush_sigqueue_mask(p, &flush, &signal->shared_pending);
for_each_thread(p, t)
flush_sigqueue_mask(p, &flush, &t->pending);
} else if (sig == SIGCONT) {
unsigned int why;
/*
* Remove all stop signals from all queues, wake all threads.
*/
siginitset(&flush, SIG_KERNEL_STOP_MASK);
flush_sigqueue_mask(p, &flush, &signal->shared_pending);
for_each_thread(p, t) {
flush_sigqueue_mask(p, &flush, &t->pending);
task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
if (likely(!(t->ptrace & PT_SEIZED))) {
t->jobctl &= ~JOBCTL_STOPPED;
wake_up_state(t, __TASK_STOPPED);
} else
ptrace_trap_notify(t);
}
/*
* Notify the parent with CLD_CONTINUED if we were stopped.
*
* If we were in the middle of a group stop, we pretend it
* was already finished, and then continued. Since SIGCHLD
* doesn't queue we report only CLD_STOPPED, as if the next
* CLD_CONTINUED was dropped.
*/
why = 0;
if (signal->flags & SIGNAL_STOP_STOPPED)
why |= SIGNAL_CLD_CONTINUED;
else if (signal->group_stop_count)
why |= SIGNAL_CLD_STOPPED;
if (why) {
/*
* The first thread which returns from do_signal_stop()
* will take ->siglock, notice SIGNAL_CLD_MASK, and
* notify its parent. See get_signal().
*/
signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
signal->group_stop_count = 0;
signal->group_exit_code = 0;
}
}
return !sig_ignored(p, sig, force);
}
/*
* Test if P wants to take SIG. After we've checked all threads with this,
* it's equivalent to finding no threads not blocking SIG. Any threads not
* blocking SIG were ruled out because they are not running and already
* have pending signals. Such threads will dequeue from the shared queue
* as soon as they're available, so putting the signal on the shared queue
* will be equivalent to sending it to one such thread.
*/
static inline bool wants_signal(int sig, struct task_struct *p)
{
if (sigismember(&p->blocked, sig))
return false;
if (p->flags & PF_EXITING)
return false;
if (sig == SIGKILL)
return true;
if (task_is_stopped_or_traced(p))
return false;
return task_curr(p) || !task_sigpending(p);
}
static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
{
struct signal_struct *signal = p->signal;
struct task_struct *t;
/*
* Now find a thread we can wake up to take the signal off the queue.
*
* Try the suggested task first (may or may not be the main thread).
*/
if (wants_signal(sig, p))
t = p;
else if ((type == PIDTYPE_PID) || thread_group_empty(p))
/*
* There is just one thread and it does not need to be woken.
* It will dequeue unblocked signals before it runs again.
*/
return;
else {
/*
* Otherwise try to find a suitable thread.
*/
t = signal->curr_target;
while (!wants_signal(sig, t)) { t = next_thread(t); if (t == signal->curr_target)
/*
* No thread needs to be woken.
* Any eligible threads will see
* the signal in the queue soon.
*/
return;
}
signal->curr_target = t;
}
/*
* Found a killable thread. If the signal will be fatal,
* then start taking the whole group down immediately.
*/
if (sig_fatal(p, sig) && (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || !p->ptrace)) {
/*
* This signal will be fatal to the whole group.
*/
if (!sig_kernel_coredump(sig)) {
/*
* Start a group exit and wake everybody up.
* This way we don't have other threads
* running and doing things after a slower
* thread has the fatal signal pending.
*/
signal->flags = SIGNAL_GROUP_EXIT;
signal->group_exit_code = sig;
signal->group_stop_count = 0;
__for_each_thread(signal, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
}
return;
}
}
/*
* The signal is already in the shared-pending queue.
* Tell the chosen thread to wake up and dequeue it.
*/
signal_wake_up(t, sig == SIGKILL);
return;
}
static inline bool legacy_queue(struct sigpending *signals, int sig)
{
return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
}
static int __send_signal_locked(int sig, struct kernel_siginfo *info,
struct task_struct *t, enum pid_type type, bool force)
{
struct sigpending *pending;
struct sigqueue *q;
int override_rlimit;
int ret = 0, result;
lockdep_assert_held(&t->sighand->siglock);
result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t, force))
goto ret;
pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
/*
* Short-circuit ignored signals and support queuing
* exactly one non-rt signal, so that we can get more
* detailed information about the cause of the signal.
*/
result = TRACE_SIGNAL_ALREADY_PENDING;
if (legacy_queue(pending, sig))
goto ret;
result = TRACE_SIGNAL_DELIVERED;
/*
* Skip useless siginfo allocation for SIGKILL and kernel threads.
*/
if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
goto out_set;
/*
* Real-time signals must be queued if sent by sigqueue, or
* some other real-time mechanism. It is implementation
* defined whether kill() does so. We attempt to do so, on
* the principle of least surprise, but since kill is not
* allowed to fail with EAGAIN when low on memory we just
* make sure at least one signal gets delivered and don't
* pass on the info struct.
*/
if (sig < SIGRTMIN)
override_rlimit = (is_si_special(info) || info->si_code >= 0);
else
override_rlimit = 0;
q = sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit);
if (q) {
list_add_tail(&q->list, &pending->list);
switch ((unsigned long) info) {
case (unsigned long) SEND_SIG_NOINFO:
clear_siginfo(&q->info);
q->info.si_signo = sig;
q->info.si_errno = 0;
q->info.si_code = SI_USER;
q->info.si_pid = task_tgid_nr_ns(current,
task_active_pid_ns(t));
rcu_read_lock();
q->info.si_uid =
from_kuid_munged(task_cred_xxx(t, user_ns),
current_uid());
rcu_read_unlock();
break;
case (unsigned long) SEND_SIG_PRIV:
clear_siginfo(&q->info);
q->info.si_signo = sig;
q->info.si_errno = 0;
q->info.si_code = SI_KERNEL;
q->info.si_pid = 0;
q->info.si_uid = 0;
break;
default:
copy_siginfo(&q->info, info);
break;
}
} else if (!is_si_special(info) && sig >= SIGRTMIN && info->si_code != SI_USER) {
/*
* Queue overflow, abort. We may abort if the
* signal was rt and sent by user using something
* other than kill().
*/
result = TRACE_SIGNAL_OVERFLOW_FAIL;
ret = -EAGAIN;
goto ret;
} else {
/*
* This is a silent loss of information. We still
* send the signal, but the *info bits are lost.
*/
result = TRACE_SIGNAL_LOSE_INFO;
}
out_set:
signalfd_notify(t, sig);
sigaddset(&pending->signal, sig);
/* Let multiprocess signals appear after on-going forks */
if (type > PIDTYPE_TGID) {
struct multiprocess_signals *delayed;
hlist_for_each_entry(delayed, &t->signal->multiprocess, node) {
sigset_t *signal = &delayed->signal;
/* Can't queue both a stop and a continue signal */
if (sig == SIGCONT)
sigdelsetmask(signal, SIG_KERNEL_STOP_MASK);
else if (sig_kernel_stop(sig))
sigdelset(signal, SIGCONT);
sigaddset(signal, sig);
}
}
complete_signal(sig, t, type);
ret:
trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result);
return ret;
}
static inline bool has_si_pid_and_uid(struct kernel_siginfo *info)
{
bool ret = false;
switch (siginfo_layout(info->si_signo, info->si_code)) {
case SIL_KILL:
case SIL_CHLD:
case SIL_RT:
ret = true;
break;
case SIL_TIMER:
case SIL_POLL:
case SIL_FAULT:
case SIL_FAULT_TRAPNO:
case SIL_FAULT_MCEERR:
case SIL_FAULT_BNDERR:
case SIL_FAULT_PKUERR:
case SIL_FAULT_PERF_EVENT:
case SIL_SYS:
ret = false;
break;
}
return ret;
}
int send_signal_locked(int sig, struct kernel_siginfo *info,
struct task_struct *t, enum pid_type type)
{
/* Should SIGKILL or SIGSTOP be received by a pid namespace init? */
bool force = false;
if (info == SEND_SIG_NOINFO) {
/* Force if sent from an ancestor pid namespace */
force = !task_pid_nr_ns(current, task_active_pid_ns(t));
} else if (info == SEND_SIG_PRIV) {
/* Don't ignore kernel generated signals */
force = true;
} else if (has_si_pid_and_uid(info)) {
/* SIGKILL and SIGSTOP is special or has ids */
struct user_namespace *t_user_ns;
rcu_read_lock(); t_user_ns = task_cred_xxx(t, user_ns); if (current_user_ns() != t_user_ns) { kuid_t uid = make_kuid(current_user_ns(), info->si_uid);
info->si_uid = from_kuid_munged(t_user_ns, uid);
}
rcu_read_unlock();
/* A kernel generated signal? */
force = (info->si_code == SI_KERNEL);
/* From an ancestor pid namespace? */
if (!task_pid_nr_ns(current, task_active_pid_ns(t))) { info->si_pid = 0;
force = true;
}
}
return __send_signal_locked(sig, info, t, type, force);
}
static void print_fatal_signal(int signr)
{
struct pt_regs *regs = task_pt_regs(current);
struct file *exe_file;
exe_file = get_task_exe_file(current);
if (exe_file) {
pr_info("%pD: %s: potentially unexpected fatal signal %d.\n",
exe_file, current->comm, signr);
fput(exe_file);
} else {
pr_info("%s: potentially unexpected fatal signal %d.\n",
current->comm, signr);
}
#if defined(__i386__) && !defined(__arch_um__)
pr_info("code at %08lx: ", regs->ip);
{
int i;
for (i = 0; i < 16; i++) {
unsigned char insn;
if (get_user(insn, (unsigned char *)(regs->ip + i)))
break;
pr_cont("%02x ", insn);
}
}
pr_cont("\n");
#endif
preempt_disable();
show_regs(regs);
preempt_enable();
}
static int __init setup_print_fatal_signals(char *str)
{
get_option (&str, &print_fatal_signals);
return 1;
}
__setup("print-fatal-signals=", setup_print_fatal_signals);
int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p,
enum pid_type type)
{
unsigned long flags;
int ret = -ESRCH;
if (lock_task_sighand(p, &flags)) {
ret = send_signal_locked(sig, info, p, type);
unlock_task_sighand(p, &flags);
}
return ret;
}
enum sig_handler {
HANDLER_CURRENT, /* If reachable use the current handler */
HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */
HANDLER_EXIT, /* Only visible as the process exit code */
};
/*
* Force a signal that the process can't ignore: if necessary
* we unblock the signal and change any SIG_IGN to SIG_DFL.
*
* Note: If we unblock the signal, we always reset it to SIG_DFL,
* since we do not want to have a signal handler that was blocked
* be invoked when user space had explicitly blocked it.
*
* We don't want to have recursive SIGSEGV's etc, for example,
* that is why we also clear SIGNAL_UNKILLABLE.
*/
static int
force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
enum sig_handler handler)
{
unsigned long int flags;
int ret, blocked, ignored;
struct k_sigaction *action;
int sig = info->si_signo;
spin_lock_irqsave(&t->sighand->siglock, flags);
action = &t->sighand->action[sig-1];
ignored = action->sa.sa_handler == SIG_IGN;
blocked = sigismember(&t->blocked, sig);
if (blocked || ignored || (handler != HANDLER_CURRENT)) {
action->sa.sa_handler = SIG_DFL;
if (handler == HANDLER_EXIT) action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) sigdelset(&t->blocked, sig);
}
/*
* Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
* debugging to leave init killable. But HANDLER_EXIT is always fatal.
*/
if (action->sa.sa_handler == SIG_DFL && (!t->ptrace || (handler == HANDLER_EXIT))) t->signal->flags &= ~SIGNAL_UNKILLABLE;
ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
/* This can happen if the signal was already pending and blocked */
if (!task_sigpending(t)) signal_wake_up(t, 0);
spin_unlock_irqrestore(&t->sighand->siglock, flags);
return ret;
}
int force_sig_info(struct kernel_siginfo *info)
{
return force_sig_info_to_task(info, current, HANDLER_CURRENT);
}
/*
* Nuke all other threads in the group.
*/
int zap_other_threads(struct task_struct *p)
{
struct task_struct *t;
int count = 0;
p->signal->group_stop_count = 0;
for_other_threads(p, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
count++;
/* Don't bother with already dead threads */
if (t->exit_state)
continue;
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
}
return count;
}
struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
{
struct sighand_struct *sighand;
rcu_read_lock();
for (;;) {
sighand = rcu_dereference(tsk->sighand);
if (unlikely(sighand == NULL))
break;
/*
* This sighand can be already freed and even reused, but
* we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which
* initializes ->siglock: this slab can't go away, it has
* the same object type, ->siglock can't be reinitialized.
*
* We need to ensure that tsk->sighand is still the same
* after we take the lock, we can race with de_thread() or
* __exit_signal(). In the latter case the next iteration
* must see ->sighand == NULL.
*/
spin_lock_irqsave(&sighand->siglock, *flags);
if (likely(sighand == rcu_access_pointer(tsk->sighand)))
break;
spin_unlock_irqrestore(&sighand->siglock, *flags);
}
rcu_read_unlock();
return sighand;
}
#ifdef CONFIG_LOCKDEP
void lockdep_assert_task_sighand_held(struct task_struct *task)
{
struct sighand_struct *sighand;
rcu_read_lock();
sighand = rcu_dereference(task->sighand);
if (sighand)
lockdep_assert_held(&sighand->siglock);
else
WARN_ON_ONCE(1);
rcu_read_unlock();
}
#endif
/*
* send signal info to all the members of a thread group or to the
* individual thread if type == PIDTYPE_PID.
*/
int group_send_sig_info(int sig, struct kernel_siginfo *info,
struct task_struct *p, enum pid_type type)
{
int ret;
rcu_read_lock();
ret = check_kill_permission(sig, info, p);
rcu_read_unlock();
if (!ret && sig)
ret = do_send_sig_info(sig, info, p, type);
return ret;
}
/*
* __kill_pgrp_info() sends a signal to a process group: this is what the tty
* control characters do (^C, ^Z etc)
* - the caller must hold at least a readlock on tasklist_lock
*/
int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
{
struct task_struct *p = NULL;
int ret = -ESRCH;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID);
/*
* If group_send_sig_info() succeeds at least once ret
* becomes 0 and after that the code below has no effect.
* Otherwise we return the last err or -ESRCH if this
* process group is empty.
*/
if (ret)
ret = err;
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return ret;
}
static int kill_pid_info_type(int sig, struct kernel_siginfo *info,
struct pid *pid, enum pid_type type)
{
int error = -ESRCH;
struct task_struct *p;
for (;;) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
error = group_send_sig_info(sig, info, p, type);
rcu_read_unlock();
if (likely(!p || error != -ESRCH))
return error;
/*
* The task was unhashed in between, try again. If it
* is dead, pid_task() will return NULL, if we race with
* de_thread() it will find the new leader.
*/
}
}
int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
{
return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID);
}
static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
{
int error;
rcu_read_lock();
error = kill_pid_info(sig, info, find_vpid(pid));
rcu_read_unlock();
return error;
}
static inline bool kill_as_cred_perm(const struct cred *cred,
struct task_struct *target)
{
const struct cred *pcred = __task_cred(target);
return uid_eq(cred->euid, pcred->suid) ||
uid_eq(cred->euid, pcred->uid) ||
uid_eq(cred->uid, pcred->suid) ||
uid_eq(cred->uid, pcred->uid);
}
/*
* The usb asyncio usage of siginfo is wrong. The glibc support
* for asyncio which uses SI_ASYNCIO assumes the layout is SIL_RT.
* AKA after the generic fields:
* kernel_pid_t si_pid;
* kernel_uid32_t si_uid;
* sigval_t si_value;
*
* Unfortunately when usb generates SI_ASYNCIO it assumes the layout
* after the generic fields is:
* void __user *si_addr;
*
* This is a practical problem when there is a 64bit big endian kernel
* and a 32bit userspace. As the 32bit address will encoded in the low
* 32bits of the pointer. Those low 32bits will be stored at higher
* address than appear in a 32 bit pointer. So userspace will not
* see the address it was expecting for it's completions.
*
* There is nothing in the encoding that can allow
* copy_siginfo_to_user32 to detect this confusion of formats, so
* handle this by requiring the caller of kill_pid_usb_asyncio to
* notice when this situration takes place and to store the 32bit
* pointer in sival_int, instead of sival_addr of the sigval_t addr
* parameter.
*/
int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
struct pid *pid, const struct cred *cred)
{
struct kernel_siginfo info;
struct task_struct *p;
unsigned long flags;
int ret = -EINVAL;
if (!valid_signal(sig))
return ret;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = errno;
info.si_code = SI_ASYNCIO;
*((sigval_t *)&info.si_pid) = addr;
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (!p) {
ret = -ESRCH;
goto out_unlock;
}
if (!kill_as_cred_perm(cred, p)) {
ret = -EPERM;
goto out_unlock;
}
ret = security_task_kill(p, &info, sig, cred);
if (ret)
goto out_unlock;
if (sig) {
if (lock_task_sighand(p, &flags)) {
ret = __send_signal_locked(sig, &info, p, PIDTYPE_TGID, false);
unlock_task_sighand(p, &flags);
} else
ret = -ESRCH;
}
out_unlock:
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(kill_pid_usb_asyncio);
/*
* kill_something_info() interprets pid in interesting ways just like kill(2).
*
* POSIX specifies that kill(-1,sig) is unspecified, but what we have
* is probably wrong. Should make it like BSD or SYSV.
*/
static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid)
{
int ret;
if (pid > 0)
return kill_proc_info(sig, info, pid);
/* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */
if (pid == INT_MIN)
return -ESRCH;
read_lock(&tasklist_lock);
if (pid != -1) {
ret = __kill_pgrp_info(sig, info,
pid ? find_vpid(-pid) : task_pgrp(current));
} else {
int retval = 0, count = 0;
struct task_struct * p;
for_each_process(p) {
if (task_pid_vnr(p) > 1 &&
!same_thread_group(p, current)) {
int err = group_send_sig_info(sig, info, p,
PIDTYPE_MAX);
++count;
if (err != -EPERM)
retval = err;
}
}
ret = count ? retval : -ESRCH;
}
read_unlock(&tasklist_lock);
return ret;
}
/*
* These are for backward compatibility with the rest of the kernel source.
*/
int send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p)
{
/*
* Make sure legacy kernel users don't send in bad values
* (normal paths check this in check_kill_permission).
*/
if (!valid_signal(sig))
return -EINVAL;
return do_send_sig_info(sig, info, p, PIDTYPE_PID);
}
EXPORT_SYMBOL(send_sig_info);
#define __si_special(priv) \
((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO)
int
send_sig(int sig, struct task_struct *p, int priv)
{
return send_sig_info(sig, __si_special(priv), p);
}
EXPORT_SYMBOL(send_sig);
void force_sig(int sig)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = SI_KERNEL;
info.si_pid = 0;
info.si_uid = 0;
force_sig_info(&info);
}
EXPORT_SYMBOL(force_sig);
void force_fatal_sig(int sig)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = SI_KERNEL;
info.si_pid = 0;
info.si_uid = 0;
force_sig_info_to_task(&info, current, HANDLER_SIG_DFL);
}
void force_exit_sig(int sig)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = SI_KERNEL;
info.si_pid = 0;
info.si_uid = 0;
force_sig_info_to_task(&info, current, HANDLER_EXIT);
}
/*
* When things go south during signal handling, we
* will force a SIGSEGV. And if the signal that caused
* the problem was already a SIGSEGV, we'll want to
* make sure we don't even try to deliver the signal..
*/
void force_sigsegv(int sig)
{
if (sig == SIGSEGV)
force_fatal_sig(SIGSEGV);
else
force_sig(SIGSEGV);
}
int force_sig_fault_to_task(int sig, int code, void __user *addr,
struct task_struct *t)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
return force_sig_info_to_task(&info, t, HANDLER_CURRENT);
}
int force_sig_fault(int sig, int code, void __user *addr)
{
return force_sig_fault_to_task(sig, code, addr, current);
}
int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
return send_sig_info(info.si_signo, &info, t);
}
int force_sig_mceerr(int code, void __user *addr, short lsb)
{
struct kernel_siginfo info;
WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR));
clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
info.si_addr_lsb = lsb;
return force_sig_info(&info);
}
int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t)
{
struct kernel_siginfo info;
WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR));
clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
info.si_addr_lsb = lsb;
return send_sig_info(info.si_signo, &info, t);
}
EXPORT_SYMBOL(send_sig_mceerr);
int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_BNDERR;
info.si_addr = addr;
info.si_lower = lower;
info.si_upper = upper;
return force_sig_info(&info);
}
#ifdef SEGV_PKUERR
int force_sig_pkuerr(void __user *addr, u32 pkey)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_PKUERR;
info.si_addr = addr;
info.si_pkey = pkey;
return force_sig_info(&info);
}
#endif
int send_sig_perf(void __user *addr, u32 type, u64 sig_data)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGTRAP;
info.si_errno = 0;
info.si_code = TRAP_PERF;
info.si_addr = addr;
info.si_perf_data = sig_data;
info.si_perf_type = type;
/*
* Signals generated by perf events should not terminate the whole
* process if SIGTRAP is blocked, however, delivering the signal
* asynchronously is better than not delivering at all. But tell user
* space if the signal was asynchronous, so it can clearly be
* distinguished from normal synchronous ones.
*/
info.si_perf_flags = sigismember(¤t->blocked, info.si_signo) ?
TRAP_PERF_FLAG_ASYNC :
0;
return send_sig_info(info.si_signo, &info, current);
}
/**
* force_sig_seccomp - signals the task to allow in-process syscall emulation
* @syscall: syscall number to send to userland
* @reason: filter-supplied reason code to send to userland (via si_errno)
* @force_coredump: true to trigger a coredump
*
* Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
*/
int force_sig_seccomp(int syscall, int reason, bool force_coredump)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGSYS;
info.si_code = SYS_SECCOMP;
info.si_call_addr = (void __user *)KSTK_EIP(current);
info.si_errno = reason;
info.si_arch = syscall_get_arch(current);
info.si_syscall = syscall;
return force_sig_info_to_task(&info, current,
force_coredump ? HANDLER_EXIT : HANDLER_CURRENT);
}
/* For the crazy architectures that include trap information in
* the errno field, instead of an actual errno value.
*/
int force_sig_ptrace_errno_trap(int errno, void __user *addr)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGTRAP;
info.si_errno = errno;
info.si_code = TRAP_HWBKPT;
info.si_addr = addr;
return force_sig_info(&info);
}
/* For the rare architectures that include trap information using
* si_trapno.
*/
int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
info.si_trapno = trapno;
return force_sig_info(&info);
}
/* For the rare architectures that include trap information using
* si_trapno.
*/
int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno,
struct task_struct *t)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
info.si_code = code;
info.si_addr = addr;
info.si_trapno = trapno;
return send_sig_info(info.si_signo, &info, t);
}
static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
{
int ret;
read_lock(&tasklist_lock);
ret = __kill_pgrp_info(sig, info, pgrp);
read_unlock(&tasklist_lock);
return ret;
}
int kill_pgrp(struct pid *pid, int sig, int priv)
{
return kill_pgrp_info(sig, __si_special(priv), pid);
}
EXPORT_SYMBOL(kill_pgrp);
int kill_pid(struct pid *pid, int sig, int priv)
{
return kill_pid_info(sig, __si_special(priv), pid);
}
EXPORT_SYMBOL(kill_pid);
#ifdef CONFIG_POSIX_TIMERS
/*
* These functions handle POSIX timer signals. POSIX timers use
* preallocated sigqueue structs for sending signals.
*/
static void __flush_itimer_signals(struct sigpending *pending)
{
sigset_t signal, retain;
struct sigqueue *q, *n;
signal = pending->signal;
sigemptyset(&retain);
list_for_each_entry_safe(q, n, &pending->list, list) {
int sig = q->info.si_signo;
if (likely(q->info.si_code != SI_TIMER)) {
sigaddset(&retain, sig);
} else {
sigdelset(&signal, sig);
list_del_init(&q->list);
__sigqueue_free(q);
}
}
sigorsets(&pending->signal, &signal, &retain);
}
void flush_itimer_signals(void)
{
struct task_struct *tsk = current;
guard(spinlock_irqsave)(&tsk->sighand->siglock);
__flush_itimer_signals(&tsk->pending);
__flush_itimer_signals(&tsk->signal->shared_pending);
}
bool posixtimer_init_sigqueue(struct sigqueue *q)
{
struct ucounts *ucounts = sig_get_ucounts(current, -1, 0);
if (!ucounts)
return false;
clear_siginfo(&q->info);
__sigqueue_init(q, ucounts, SIGQUEUE_PREALLOC);
return true;
}
static void posixtimer_queue_sigqueue(struct sigqueue *q, struct task_struct *t, enum pid_type type)
{
struct sigpending *pending;
int sig = q->info.si_signo;
signalfd_notify(t, sig);
pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
list_add_tail(&q->list, &pending->list);
sigaddset(&pending->signal, sig);
complete_signal(sig, t, type);
}
/*
* This function is used by POSIX timers to deliver a timer signal.
* Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID
* set), the signal must be delivered to the specific thread (queues
* into t->pending).
*
* Where type is not PIDTYPE_PID, signals must be delivered to the
* process. In this case, prefer to deliver to current if it is in
* the same thread group as the target process and its sighand is
* stable, which avoids unnecessarily waking up a potentially idle task.
*/
static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr)
{
struct task_struct *t = pid_task(tmr->it_pid, tmr->it_pid_type);
if (t && tmr->it_pid_type != PIDTYPE_PID &&
same_thread_group(t, current) && !current->exit_state)
t = current;
return t;
}
void posixtimer_send_sigqueue(struct k_itimer *tmr)
{
struct sigqueue *q = &tmr->sigq;
int sig = q->info.si_signo;
struct task_struct *t;
unsigned long flags;
int result;
guard(rcu)();
t = posixtimer_get_target(tmr);
if (!t)
return;
if (!likely(lock_task_sighand(t, &flags)))
return;
/*
* Update @tmr::sigqueue_seq for posix timer signals with sighand
* locked to prevent a race against dequeue_signal().
*/
tmr->it_sigqueue_seq = tmr->it_signal_seq;
/*
* Set the signal delivery status under sighand lock, so that the
* ignored signal handling can distinguish between a periodic and a
* non-periodic timer.
*/
tmr->it_sig_periodic = tmr->it_status == POSIX_TIMER_REQUEUE_PENDING;
if (!prepare_signal(sig, t, false)) {
result = TRACE_SIGNAL_IGNORED;
if (!list_empty(&q->list)) {
/*
* The signal was ignored and blocked. The timer
* expiry queued it because blocked signals are
* queued independent of the ignored state.
*
* The unblocking set SIGPENDING, but the signal
* was not yet dequeued from the pending list.
* So prepare_signal() sees unblocked and ignored,
* which ends up here. Leave it queued like a
* regular signal.
*
* The same happens when the task group is exiting
* and the signal is already queued.
* prepare_signal() treats SIGNAL_GROUP_EXIT as
* ignored independent of its queued state. This
* gets cleaned up in __exit_signal().
*/
goto out;
}
/* Periodic timers with SIG_IGN are queued on the ignored list */
if (tmr->it_sig_periodic) {
/*
* Already queued means the timer was rearmed after
* the previous expiry got it on the ignore list.
* Nothing to do for that case.
*/
if (hlist_unhashed(&tmr->ignored_list)) {
/*
* Take a signal reference and queue it on
* the ignored list.
*/
posixtimer_sigqueue_getref(q);
posixtimer_sig_ignore(t, q);
}
} else if (!hlist_unhashed(&tmr->ignored_list)) {
/*
* Covers the case where a timer was periodic and
* then the signal was ignored. Later it was rearmed
* as oneshot timer. The previous signal is invalid
* now, and this oneshot signal has to be dropped.
* Remove it from the ignored list and drop the
* reference count as the signal is not longer
* queued.
*/
hlist_del_init(&tmr->ignored_list);
posixtimer_putref(tmr);
}
goto out;
}
if (unlikely(!list_empty(&q->list))) {
/* This holds a reference count already */
result = TRACE_SIGNAL_ALREADY_PENDING;
goto out;
}
/*
* If the signal is on the ignore list, it got blocked after it was
* ignored earlier. But nothing lifted the ignore. Move it back to
* the pending list to be consistent with the regular signal
* handling. This already holds a reference count.
*
* If it's not on the ignore list acquire a reference count.
*/
if (likely(hlist_unhashed(&tmr->ignored_list)))
posixtimer_sigqueue_getref(q);
else
hlist_del_init(&tmr->ignored_list);
posixtimer_queue_sigqueue(q, t, tmr->it_pid_type);
result = TRACE_SIGNAL_DELIVERED;
out:
trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result);
unlock_task_sighand(t, &flags);
}
static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q)
{
struct k_itimer *tmr = container_of(q, struct k_itimer, sigq);
/*
* If the timer is marked deleted already or the signal originates
* from a non-periodic timer, then just drop the reference
* count. Otherwise queue it on the ignored list.
*/
if (posixtimer_valid(tmr) && tmr->it_sig_periodic)
hlist_add_head(&tmr->ignored_list, &tsk->signal->ignored_posix_timers);
else
posixtimer_putref(tmr);
}
static void posixtimer_sig_unignore(struct task_struct *tsk, int sig)
{
struct hlist_head *head = &tsk->signal->ignored_posix_timers;
struct hlist_node *tmp;
struct k_itimer *tmr;
if (likely(hlist_empty(head)))
return;
/*
* Rearming a timer with sighand lock held is not possible due to
* lock ordering vs. tmr::it_lock. Just stick the sigqueue back and
* let the signal delivery path deal with it whether it needs to be
* rearmed or not. This cannot be decided here w/o dropping sighand
* lock and creating a loop retry horror show.
*/
hlist_for_each_entry_safe(tmr, tmp , head, ignored_list) {
struct task_struct *target;
/*
* tmr::sigq.info.si_signo is immutable, so accessing it
* without holding tmr::it_lock is safe.
*/
if (tmr->sigq.info.si_signo != sig)
continue;
hlist_del_init(&tmr->ignored_list);
/* This should never happen and leaks a reference count */
if (WARN_ON_ONCE(!list_empty(&tmr->sigq.list)))
continue;
/*
* Get the target for the signal. If target is a thread and
* has exited by now, drop the reference count.
*/
guard(rcu)();
target = posixtimer_get_target(tmr);
if (target)
posixtimer_queue_sigqueue(&tmr->sigq, target, tmr->it_pid_type);
else
posixtimer_putref(tmr);
}
}
#else /* CONFIG_POSIX_TIMERS */
static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) { }
static inline void posixtimer_sig_unignore(struct task_struct *tsk, int sig) { }
#endif /* !CONFIG_POSIX_TIMERS */
void do_notify_pidfd(struct task_struct *task)
{
struct pid *pid = task_pid(task);
WARN_ON(task->exit_state == 0);
__wake_up(&pid->wait_pidfd, TASK_NORMAL, 0,
poll_to_key(EPOLLIN | EPOLLRDNORM));
}
/*
* Let a parent know about the death of a child.
* For a stopped/continued status change, use do_notify_parent_cldstop instead.
*
* Returns true if our parent ignored us and so we've switched to
* self-reaping.
*/
bool do_notify_parent(struct task_struct *tsk, int sig)
{
struct kernel_siginfo info;
unsigned long flags;
struct sighand_struct *psig;
bool autoreap = false;
u64 utime, stime;
WARN_ON_ONCE(sig == -1);
/* do_notify_parent_cldstop should have been called instead. */
WARN_ON_ONCE(task_is_stopped_or_traced(tsk));
WARN_ON_ONCE(!tsk->ptrace &&
(tsk->group_leader != tsk || !thread_group_empty(tsk)));
/* ptraced, or group-leader without sub-threads */
do_notify_pidfd(tsk);
if (sig != SIGCHLD) {
/*
* This is only possible if parent == real_parent.
* Check if it has changed security domain.
*/
if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id))
sig = SIGCHLD;
}
clear_siginfo(&info);
info.si_signo = sig;
info.si_errno = 0;
/*
* We are under tasklist_lock here so our parent is tied to
* us and cannot change.
*
* task_active_pid_ns will always return the same pid namespace
* until a task passes through release_task.
*
* write_lock() currently calls preempt_disable() which is the
* same as rcu_read_lock(), but according to Oleg, this is not
* correct to rely on this
*/
rcu_read_lock();
info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent));
info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns),
task_uid(tsk));
rcu_read_unlock();
task_cputime(tsk, &utime, &stime);
info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime);
info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime);
info.si_status = tsk->exit_code & 0x7f;
if (tsk->exit_code & 0x80)
info.si_code = CLD_DUMPED;
else if (tsk->exit_code & 0x7f)
info.si_code = CLD_KILLED;
else {
info.si_code = CLD_EXITED;
info.si_status = tsk->exit_code >> 8;
}
psig = tsk->parent->sighand;
spin_lock_irqsave(&psig->siglock, flags);
if (!tsk->ptrace && sig == SIGCHLD &&
(psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
(psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
/*
* We are exiting and our parent doesn't care. POSIX.1
* defines special semantics for setting SIGCHLD to SIG_IGN
* or setting the SA_NOCLDWAIT flag: we should be reaped
* automatically and not left for our parent's wait4 call.
* Rather than having the parent do it as a magic kind of
* signal handler, we just set this to tell do_exit that we
* can be cleaned up without becoming a zombie. Note that
* we still call __wake_up_parent in this case, because a
* blocked sys_wait4 might now return -ECHILD.
*
* Whether we send SIGCHLD or not for SA_NOCLDWAIT
* is implementation-defined: we do (if you don't want
* it, just use SIG_IGN instead).
*/
autoreap = true;
if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
sig = 0;
}
/*
* Send with __send_signal as si_pid and si_uid are in the
* parent's namespaces.
*/
if (valid_signal(sig) && sig)
__send_signal_locked(sig, &info, tsk->parent, PIDTYPE_TGID, false);
__wake_up_parent(tsk, tsk->parent);
spin_unlock_irqrestore(&psig->siglock, flags);
return autoreap;
}
/**
* do_notify_parent_cldstop - notify parent of stopped/continued state change
* @tsk: task reporting the state change
* @for_ptracer: the notification is for ptracer
* @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report
*
* Notify @tsk's parent that the stopped/continued state has changed. If
* @for_ptracer is %false, @tsk's group leader notifies to its real parent.
* If %true, @tsk reports to @tsk->parent which should be the ptracer.
*
* CONTEXT:
* Must be called with tasklist_lock at least read locked.
*/
static void do_notify_parent_cldstop(struct task_struct *tsk,
bool for_ptracer, int why)
{
struct kernel_siginfo info;
unsigned long flags;
struct task_struct *parent;
struct sighand_struct *sighand;
u64 utime, stime;
if (for_ptracer) {
parent = tsk->parent;
} else {
tsk = tsk->group_leader;
parent = tsk->real_parent;
}
clear_siginfo(&info);
info.si_signo = SIGCHLD;
info.si_errno = 0;
/*
* see comment in do_notify_parent() about the following 4 lines
*/
rcu_read_lock();
info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent));
info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk));
rcu_read_unlock();
task_cputime(tsk, &utime, &stime);
info.si_utime = nsec_to_clock_t(utime);
info.si_stime = nsec_to_clock_t(stime);
info.si_code = why;
switch (why) {
case CLD_CONTINUED:
info.si_status = SIGCONT;
break;
case CLD_STOPPED:
info.si_status = tsk->signal->group_exit_code & 0x7f;
break;
case CLD_TRAPPED:
info.si_status = tsk->exit_code & 0x7f;
break;
default:
BUG();
}
sighand = parent->sighand;
spin_lock_irqsave(&sighand->siglock, flags);
if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN &&
!(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
send_signal_locked(SIGCHLD, &info, parent, PIDTYPE_TGID);
/*
* Even if SIGCHLD is not generated, we must wake up wait4 calls.
*/
__wake_up_parent(tsk, parent);
spin_unlock_irqrestore(&sighand->siglock, flags);
}
/*
* This must be called with current->sighand->siglock held.
*
* This should be the path for all ptrace stops.
* We always set current->last_siginfo while stopped here.
* That makes it a way to test a stopped process for
* being ptrace-stopped vs being job-control-stopped.
*
* Returns the signal the ptracer requested the code resume
* with. If the code did not stop because the tracer is gone,
* the stop signal remains unchanged unless clear_code.
*/
static int ptrace_stop(int exit_code, int why, unsigned long message,
kernel_siginfo_t *info)
__releases(¤t->sighand->siglock)
__acquires(¤t->sighand->siglock)
{
bool gstop_done = false;
if (arch_ptrace_stop_needed()) {
/*
* The arch code has something special to do before a
* ptrace stop. This is allowed to block, e.g. for faults
* on user stack pages. We can't keep the siglock while
* calling arch_ptrace_stop, so we must release it now.
* To preserve proper semantics, we must do this before
* any signal bookkeeping like checking group_stop_count.
*/
spin_unlock_irq(¤t->sighand->siglock);
arch_ptrace_stop();
spin_lock_irq(¤t->sighand->siglock);
}
/*
* After this point ptrace_signal_wake_up or signal_wake_up
* will clear TASK_TRACED if ptrace_unlink happens or a fatal
* signal comes in. Handle previous ptrace_unlinks and fatal
* signals here to prevent ptrace_stop sleeping in schedule.
*/
if (!current->ptrace || __fatal_signal_pending(current))
return exit_code;
set_special_state(TASK_TRACED);
current->jobctl |= JOBCTL_TRACED;
/*
* We're committing to trapping. TRACED should be visible before
* TRAPPING is cleared; otherwise, the tracer might fail do_wait().
* Also, transition to TRACED and updates to ->jobctl should be
* atomic with respect to siglock and should be done after the arch
* hook as siglock is released and regrabbed across it.
*
* TRACER TRACEE
*
* ptrace_attach()
* [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED)
* do_wait()
* set_current_state() smp_wmb();
* ptrace_do_wait()
* wait_task_stopped()
* task_stopped_code()
* [L] task_is_traced() [S] task_clear_jobctl_trapping();
*/
smp_wmb();
current->ptrace_message = message;
current->last_siginfo = info;
current->exit_code = exit_code;
/*
* If @why is CLD_STOPPED, we're trapping to participate in a group
* stop. Do the bookkeeping. Note that if SIGCONT was delievered
* across siglock relocks since INTERRUPT was scheduled, PENDING
* could be clear now. We act as if SIGCONT is received after
* TASK_TRACED is entered - ignore it.
*/
if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING))
gstop_done = task_participate_group_stop(current);
/* any trap clears pending STOP trap, STOP trap clears NOTIFY */
task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP);
if (info && info->si_code >> 8 == PTRACE_EVENT_STOP)
task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY);
/* entering a trap, clear TRAPPING */
task_clear_jobctl_trapping(current);
spin_unlock_irq(¤t->sighand->siglock);
read_lock(&tasklist_lock);
/*
* Notify parents of the stop.
*
* While ptraced, there are two parents - the ptracer and
* the real_parent of the group_leader. The ptracer should
* know about every stop while the real parent is only
* interested in the completion of group stop. The states
* for the two don't interact with each other. Notify
* separately unless they're gonna be duplicates.
*/
if (current->ptrace)
do_notify_parent_cldstop(current, true, why);
if (gstop_done && (!current->ptrace || ptrace_reparented(current)))
do_notify_parent_cldstop(current, false, why);
/*
* The previous do_notify_parent_cldstop() invocation woke ptracer.
* One a PREEMPTION kernel this can result in preemption requirement
* which will be fulfilled after read_unlock() and the ptracer will be
* put on the CPU.
* The ptracer is in wait_task_inactive(, __TASK_TRACED) waiting for
* this task wait in schedule(). If this task gets preempted then it
* remains enqueued on the runqueue. The ptracer will observe this and
* then sleep for a delay of one HZ tick. In the meantime this task
* gets scheduled, enters schedule() and will wait for the ptracer.
*
* This preemption point is not bad from a correctness point of
* view but extends the runtime by one HZ tick time due to the
* ptracer's sleep. The preempt-disable section ensures that there
* will be no preemption between unlock and schedule() and so
* improving the performance since the ptracer will observe that
* the tracee is scheduled out once it gets on the CPU.
*
* On PREEMPT_RT locking tasklist_lock does not disable preemption.
* Therefore the task can be preempted after do_notify_parent_cldstop()
* before unlocking tasklist_lock so there is no benefit in doing this.
*
* In fact disabling preemption is harmful on PREEMPT_RT because
* the spinlock_t in cgroup_enter_frozen() must not be acquired
* with preemption disabled due to the 'sleeping' spinlock
* substitution of RT.
*/
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_disable();
read_unlock(&tasklist_lock);
cgroup_enter_frozen();
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable_no_resched();
schedule();
cgroup_leave_frozen(true);
/*
* We are back. Now reacquire the siglock before touching
* last_siginfo, so that we are sure to have synchronized with
* any signal-sending on another CPU that wants to examine it.
*/
spin_lock_irq(¤t->sighand->siglock);
exit_code = current->exit_code;
current->last_siginfo = NULL;
current->ptrace_message = 0;
current->exit_code = 0;
/* LISTENING can be set only during STOP traps, clear it */
current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN);
/*
* Queued signals ignored us while we were stopped for tracing.
* So check for any that we should take before resuming user mode.
* This sets TIF_SIGPENDING, but never clears it.
*/
recalc_sigpending_tsk(current);
return exit_code;
}
static int ptrace_do_notify(int signr, int exit_code, int why, unsigned long message)
{
kernel_siginfo_t info;
clear_siginfo(&info);
info.si_signo = signr;
info.si_code = exit_code;
info.si_pid = task_pid_vnr(current);
info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
/* Let the debugger run. */
return ptrace_stop(exit_code, why, message, &info);
}
int ptrace_notify(int exit_code, unsigned long message)
{
int signr;
BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
if (unlikely(task_work_pending(current)))
task_work_run();
spin_lock_irq(¤t->sighand->siglock);
signr = ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED, message);
spin_unlock_irq(¤t->sighand->siglock);
return signr;
}
/**
* do_signal_stop - handle group stop for SIGSTOP and other stop signals
* @signr: signr causing group stop if initiating
*
* If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr
* and participate in it. If already set, participate in the existing
* group stop. If participated in a group stop (and thus slept), %true is
* returned with siglock released.
*
* If ptraced, this function doesn't handle stop itself. Instead,
* %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock
* untouched. The caller must ensure that INTERRUPT trap handling takes
* places afterwards.
*
* CONTEXT:
* Must be called with @current->sighand->siglock held, which is released
* on %true return.
*
* RETURNS:
* %false if group stop is already cancelled or ptrace trap is scheduled.
* %true if participated in group stop.
*/
static bool do_signal_stop(int signr)
__releases(¤t->sighand->siglock)
{
struct signal_struct *sig = current->signal;
if (!(current->jobctl & JOBCTL_STOP_PENDING)) {
unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
struct task_struct *t;
/* signr will be recorded in task->jobctl for retries */
WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK);
if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) ||
unlikely(sig->flags & SIGNAL_GROUP_EXIT) ||
unlikely(sig->group_exec_task))
return false;
/*
* There is no group stop already in progress. We must
* initiate one now.
*
* While ptraced, a task may be resumed while group stop is
* still in effect and then receive a stop signal and
* initiate another group stop. This deviates from the
* usual behavior as two consecutive stop signals can't
* cause two group stops when !ptraced. That is why we
* also check !task_is_stopped(t) below.
*
* The condition can be distinguished by testing whether
* SIGNAL_STOP_STOPPED is already set. Don't generate
* group_exit_code in such case.
*
* This is not necessary for SIGNAL_STOP_CONTINUED because
* an intervening stop signal is required to cause two
* continued events regardless of ptrace.
*/
if (!(sig->flags & SIGNAL_STOP_STOPPED))
sig->group_exit_code = signr;
sig->group_stop_count = 0;
if (task_set_jobctl_pending(current, signr | gstop))
sig->group_stop_count++;
for_other_threads(current, t) {
/*
* Setting state to TASK_STOPPED for a group
* stop is always done with the siglock held,
* so this check has no races.
*/
if (!task_is_stopped(t) &&
task_set_jobctl_pending(t, signr | gstop)) {
sig->group_stop_count++;
if (likely(!(t->ptrace & PT_SEIZED)))
signal_wake_up(t, 0);
else
ptrace_trap_notify(t);
}
}
}
if (likely(!current->ptrace)) {
int notify = 0;
/*
* If there are no other threads in the group, or if there
* is a group stop in progress and we are the last to stop,
* report to the parent.
*/
if (task_participate_group_stop(current))
notify = CLD_STOPPED;
current->jobctl |= JOBCTL_STOPPED;
set_special_state(TASK_STOPPED);
spin_unlock_irq(¤t->sighand->siglock);
/*
* Notify the parent of the group stop completion. Because
* we're not holding either the siglock or tasklist_lock
* here, ptracer may attach inbetween; however, this is for
* group stop and should always be delivered to the real
* parent of the group leader. The new ptracer will get
* its notification when this task transitions into
* TASK_TRACED.
*/
if (notify) {
read_lock(&tasklist_lock);
do_notify_parent_cldstop(current, false, notify);
read_unlock(&tasklist_lock);
}
/* Now we don't run again until woken by SIGCONT or SIGKILL */
cgroup_enter_frozen();
schedule();
return true;
} else {
/*
* While ptraced, group stop is handled by STOP trap.
* Schedule it and let the caller deal with it.
*/
task_set_jobctl_pending(current, JOBCTL_TRAP_STOP);
return false;
}
}
/**
* do_jobctl_trap - take care of ptrace jobctl traps
*
* When PT_SEIZED, it's used for both group stop and explicit
* SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with
* accompanying siginfo. If stopped, lower eight bits of exit_code contain
* the stop signal; otherwise, %SIGTRAP.
*
* When !PT_SEIZED, it's used only for group stop trap with stop signal
* number as exit_code and no siginfo.
*
* CONTEXT:
* Must be called with @current->sighand->siglock held, which may be
* released and re-acquired before returning with intervening sleep.
*/
static void do_jobctl_trap(void)
{
struct signal_struct *signal = current->signal;
int signr = current->jobctl & JOBCTL_STOP_SIGMASK;
if (current->ptrace & PT_SEIZED) {
if (!signal->group_stop_count &&
!(signal->flags & SIGNAL_STOP_STOPPED))
signr = SIGTRAP;
WARN_ON_ONCE(!signr);
ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8),
CLD_STOPPED, 0);
} else {
WARN_ON_ONCE(!signr);
ptrace_stop(signr, CLD_STOPPED, 0, NULL);
}
}
/**
* do_freezer_trap - handle the freezer jobctl trap
*
* Puts the task into frozen state, if only the task is not about to quit.
* In this case it drops JOBCTL_TRAP_FREEZE.
*
* CONTEXT:
* Must be called with @current->sighand->siglock held,
* which is always released before returning.
*/
static void do_freezer_trap(void)
__releases(¤t->sighand->siglock)
{
/*
* If there are other trap bits pending except JOBCTL_TRAP_FREEZE,
* let's make another loop to give it a chance to be handled.
* In any case, we'll return back.
*/
if ((current->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) !=
JOBCTL_TRAP_FREEZE) {
spin_unlock_irq(¤t->sighand->siglock);
return;
}
/*
* Now we're sure that there is no pending fatal signal and no
* pending traps. Clear TIF_SIGPENDING to not get out of schedule()
* immediately (if there is a non-fatal signal pending), and
* put the task into sleep.
*/
__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
clear_thread_flag(TIF_SIGPENDING);
spin_unlock_irq(¤t->sighand->siglock);
cgroup_enter_frozen();
schedule();
/*
* We could've been woken by task_work, run it to clear
* TIF_NOTIFY_SIGNAL. The caller will retry if necessary.
*/
clear_notify_signal();
if (unlikely(task_work_pending(current)))
task_work_run();
}
static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
{
/*
* We do not check sig_kernel_stop(signr) but set this marker
* unconditionally because we do not know whether debugger will
* change signr. This flag has no meaning unless we are going
* to stop after return from ptrace_stop(). In this case it will
* be checked in do_signal_stop(), we should only stop if it was
* not cleared by SIGCONT while we were sleeping. See also the
* comment in dequeue_signal().
*/
current->jobctl |= JOBCTL_STOP_DEQUEUED;
signr = ptrace_stop(signr, CLD_TRAPPED, 0, info);
/* We're back. Did the debugger cancel the sig? */
if (signr == 0)
return signr;
/*
* Update the siginfo structure if the signal has
* changed. If the debugger wanted something
* specific in the siginfo structure then it should
* have updated *info via PTRACE_SETSIGINFO.
*/
if (signr != info->si_signo) {
clear_siginfo(info);
info->si_signo = signr;
info->si_errno = 0;
info->si_code = SI_USER;
rcu_read_lock();
info->si_pid = task_pid_vnr(current->parent);
info->si_uid = from_kuid_munged(current_user_ns(),
task_uid(current->parent));
rcu_read_unlock();
}
/* If the (new) signal is now blocked, requeue it. */
if (sigismember(¤t->blocked, signr) ||
fatal_signal_pending(current)) {
send_signal_locked(signr, info, current, type);
signr = 0;
}
return signr;
}
static void hide_si_addr_tag_bits(struct ksignal *ksig)
{
switch (siginfo_layout(ksig->sig, ksig->info.si_code)) {
case SIL_FAULT:
case SIL_FAULT_TRAPNO:
case SIL_FAULT_MCEERR:
case SIL_FAULT_BNDERR:
case SIL_FAULT_PKUERR:
case SIL_FAULT_PERF_EVENT:
ksig->info.si_addr = arch_untagged_si_addr(
ksig->info.si_addr, ksig->sig, ksig->info.si_code);
break;
case SIL_KILL:
case SIL_TIMER:
case SIL_POLL:
case SIL_CHLD:
case SIL_RT:
case SIL_SYS:
break;
}
}
bool get_signal(struct ksignal *ksig)
{
struct sighand_struct *sighand = current->sighand;
struct signal_struct *signal = current->signal;
int signr;
clear_notify_signal(); if (unlikely(task_work_pending(current))) task_work_run(); if (!task_sigpending(current))
return false;
if (unlikely(uprobe_deny_signal()))
return false;
/*
* Do this once, we can't return to user-mode if freezing() == T.
* do_signal_stop() and ptrace_stop() do freezable_schedule() and
* thus do not need another check after return.
*/
try_to_freeze();
relock:
spin_lock_irq(&sighand->siglock);
/*
* Every stopped thread goes here after wakeup. Check to see if
* we should notify the parent, prepare_signal(SIGCONT) encodes
* the CLD_ si_code into SIGNAL_CLD_MASK bits.
*/
if (unlikely(signal->flags & SIGNAL_CLD_MASK)) {
int why;
if (signal->flags & SIGNAL_CLD_CONTINUED)
why = CLD_CONTINUED;
else
why = CLD_STOPPED;
signal->flags &= ~SIGNAL_CLD_MASK;
spin_unlock_irq(&sighand->siglock);
/*
* Notify the parent that we're continuing. This event is
* always per-process and doesn't make whole lot of sense
* for ptracers, who shouldn't consume the state via
* wait(2) either, but, for backward compatibility, notify
* the ptracer of the group leader too unless it's gonna be
* a duplicate.
*/
read_lock(&tasklist_lock);
do_notify_parent_cldstop(current, false, why);
if (ptrace_reparented(current->group_leader)) do_notify_parent_cldstop(current->group_leader,
true, why);
read_unlock(&tasklist_lock);
goto relock;
}
for (;;) {
struct k_sigaction *ka;
enum pid_type type;
/* Has this task already been marked for death? */
if ((signal->flags & SIGNAL_GROUP_EXIT) ||
signal->group_exec_task) {
signr = SIGKILL;
sigdelset(¤t->pending.signal, SIGKILL);
trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO,
&sighand->action[SIGKILL-1]);
recalc_sigpending();
/*
* implies do_group_exit() or return to PF_USER_WORKER,
* no need to initialize ksig->info/etc.
*/
goto fatal;
}
if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) &&
do_signal_stop(0))
goto relock;
if (unlikely(current->jobctl &
(JOBCTL_TRAP_MASK | JOBCTL_TRAP_FREEZE))) {
if (current->jobctl & JOBCTL_TRAP_MASK) {
do_jobctl_trap();
spin_unlock_irq(&sighand->siglock);
} else if (current->jobctl & JOBCTL_TRAP_FREEZE) do_freezer_trap();
goto relock;
}
/*
* If the task is leaving the frozen state, let's update
* cgroup counters and reset the frozen bit.
*/
if (unlikely(cgroup_task_frozen(current))) {
spin_unlock_irq(&sighand->siglock);
cgroup_leave_frozen(false);
goto relock;
}
/*
* Signals generated by the execution of an instruction
* need to be delivered before any other pending signals
* so that the instruction pointer in the signal stack
* frame points to the faulting instruction.
*/
type = PIDTYPE_PID;
signr = dequeue_synchronous_signal(&ksig->info); if (!signr)
signr = dequeue_signal(¤t->blocked, &ksig->info, &type);
if (!signr)
break; /* will return 0 */
if (unlikely(current->ptrace) && (signr != SIGKILL) &&
!(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) {
signr = ptrace_signal(signr, &ksig->info, type);
if (!signr)
continue;
}
ka = &sighand->action[signr-1];
/* Trace actually delivered signals. */
trace_signal_deliver(signr, &ksig->info, ka);
if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */
continue;
if (ka->sa.sa_handler != SIG_DFL) {
/* Run the handler. */
ksig->ka = *ka;
if (ka->sa.sa_flags & SA_ONESHOT) ka->sa.sa_handler = SIG_DFL;
break; /* will return non-zero "signr" value */
}
/*
* Now we are doing the default action for this signal.
*/
if (sig_kernel_ignore(signr)) /* Default is nothing. */
continue;
/*
* Global init gets no signals it doesn't want.
* Container-init gets no signals it doesn't want from same
* container.
*
* Note that if global/container-init sees a sig_kernel_only()
* signal here, the signal must have been generated internally
* or must have come from an ancestor namespace. In either
* case, the signal cannot be dropped.
*/
if (unlikely(signal->flags & SIGNAL_UNKILLABLE) &&
!sig_kernel_only(signr))
continue;
if (sig_kernel_stop(signr)) {
/*
* The default action is to stop all threads in
* the thread group. The job control signals
* do nothing in an orphaned pgrp, but SIGSTOP
* always works. Note that siglock needs to be
* dropped during the call to is_orphaned_pgrp()
* because of lock ordering with tasklist_lock.
* This allows an intervening SIGCONT to be posted.
* We need to check for that and bail out if necessary.
*/
if (signr != SIGSTOP) {
spin_unlock_irq(&sighand->siglock);
/* signals can be posted during this window */
if (is_current_pgrp_orphaned())
goto relock;
spin_lock_irq(&sighand->siglock);
}
if (likely(do_signal_stop(signr))) {
/* It released the siglock. */
goto relock;
}
/*
* We didn't actually stop, due to a race
* with SIGCONT or something like that.
*/
continue;
}
fatal:
spin_unlock_irq(&sighand->siglock);
if (unlikely(cgroup_task_frozen(current))) cgroup_leave_frozen(true);
/*
* Anything else is fatal, maybe with a core dump.
*/
current->flags |= PF_SIGNALED;
if (sig_kernel_coredump(signr)) { if (print_fatal_signals) print_fatal_signal(signr);
proc_coredump_connector(current);
/*
* If it was able to dump core, this kills all
* other threads in the group and synchronizes with
* their demise. If we lost the race with another
* thread getting here, it set group_exit_code
* first and our do_group_exit call below will use
* that value and ignore the one we pass it.
*/
do_coredump(&ksig->info);
}
/*
* PF_USER_WORKER threads will catch and exit on fatal signals
* themselves. They have cleanup that must be performed, so we
* cannot call do_exit() on their behalf. Note that ksig won't
* be properly initialized, PF_USER_WORKER's shouldn't use it.
*/
if (current->flags & PF_USER_WORKER)
goto out;
/*
* Death signals, no core dump.
*/
do_group_exit(signr);
/* NOTREACHED */
}
spin_unlock_irq(&sighand->siglock);
ksig->sig = signr;
if (signr && !(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) hide_si_addr_tag_bits(ksig);
out:
return signr > 0;
}
/**
* signal_delivered - called after signal delivery to update blocked signals
* @ksig: kernel signal struct
* @stepping: nonzero if debugger single-step or block-step in use
*
* This function should be called when a signal has successfully been
* delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask
* is always blocked), and the signal itself is blocked unless %SA_NODEFER
* is set in @ksig->ka.sa.sa_flags. Tracing is notified.
*/
static void signal_delivered(struct ksignal *ksig, int stepping)
{
sigset_t blocked;
/* A signal was successfully delivered, and the
saved sigmask was stored on the signal frame,
and will be restored by sigreturn. So we can
simply clear the restore sigmask flag. */
clear_restore_sigmask();
sigorsets(&blocked, ¤t->blocked, &ksig->ka.sa.sa_mask);
if (!(ksig->ka.sa.sa_flags & SA_NODEFER)) sigaddset(&blocked, ksig->sig);
set_current_blocked(&blocked);
if (current->sas_ss_flags & SS_AUTODISARM) sas_ss_reset(current); if (stepping) ptrace_notify(SIGTRAP, 0);
}
void signal_setup_done(int failed, struct ksignal *ksig, int stepping)
{
if (failed)
force_sigsegv(ksig->sig);
else
signal_delivered(ksig, stepping);
}
/*
* It could be that complete_signal() picked us to notify about the
* group-wide signal. Other threads should be notified now to take
* the shared signals in @which since we will not.
*/
static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
{
sigset_t retarget;
struct task_struct *t;
sigandsets(&retarget, &tsk->signal->shared_pending.signal, which);
if (sigisemptyset(&retarget))
return;
for_other_threads(tsk, t) {
if (t->flags & PF_EXITING)
continue;
if (!has_pending_signals(&retarget, &t->blocked))
continue;
/* Remove the signals this thread can handle. */
sigandsets(&retarget, &retarget, &t->blocked);
if (!task_sigpending(t))
signal_wake_up(t, 0);
if (sigisemptyset(&retarget))
break;
}
}
void exit_signals(struct task_struct *tsk)
{
int group_stop = 0;
sigset_t unblocked;
/*
* @tsk is about to have PF_EXITING set - lock out users which
* expect stable threadgroup.
*/
cgroup_threadgroup_change_begin(tsk);
if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
sched_mm_cid_exit_signals(tsk);
tsk->flags |= PF_EXITING;
cgroup_threadgroup_change_end(tsk);
return;
}
spin_lock_irq(&tsk->sighand->siglock);
/*
* From now this task is not visible for group-wide signals,
* see wants_signal(), do_signal_stop().
*/
sched_mm_cid_exit_signals(tsk);
tsk->flags |= PF_EXITING;
cgroup_threadgroup_change_end(tsk);
if (!task_sigpending(tsk))
goto out;
unblocked = tsk->blocked;
signotset(&unblocked);
retarget_shared_pending(tsk, &unblocked);
if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) &&
task_participate_group_stop(tsk))
group_stop = CLD_STOPPED;
out:
spin_unlock_irq(&tsk->sighand->siglock);
/*
* If group stop has completed, deliver the notification. This
* should always go to the real parent of the group leader.
*/
if (unlikely(group_stop)) {
read_lock(&tasklist_lock);
do_notify_parent_cldstop(tsk, false, group_stop);
read_unlock(&tasklist_lock);
}
}
/*
* System call entry points.
*/
/**
* sys_restart_syscall - restart a system call
*/
SYSCALL_DEFINE0(restart_syscall)
{
struct restart_block *restart = ¤t->restart_block;
return restart->fn(restart);
}
long do_no_restart_syscall(struct restart_block *param)
{
return -EINTR;
}
static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset)
{
if (task_sigpending(tsk) && !thread_group_empty(tsk)) {
sigset_t newblocked;
/* A set of now blocked but previously unblocked signals. */
sigandnsets(&newblocked, newset, ¤t->blocked);
retarget_shared_pending(tsk, &newblocked);
}
tsk->blocked = *newset;
recalc_sigpending();
}
/**
* set_current_blocked - change current->blocked mask
* @newset: new mask
*
* It is wrong to change ->blocked directly, this helper should be used
* to ensure the process can't miss a shared signal we are going to block.
*/
void set_current_blocked(sigset_t *newset)
{
sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP));
__set_current_blocked(newset);
}
void __set_current_blocked(const sigset_t *newset)
{
struct task_struct *tsk = current;
/*
* In case the signal mask hasn't changed, there is nothing we need
* to do. The current->blocked shouldn't be modified by other task.
*/
if (sigequalsets(&tsk->blocked, newset))
return;
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, newset);
spin_unlock_irq(&tsk->sighand->siglock);
}
/*
* This is also useful for kernel threads that want to temporarily
* (or permanently) block certain signals.
*
* NOTE! Unlike the user-mode sys_sigprocmask(), the kernel
* interface happily blocks "unblockable" signals like SIGKILL
* and friends.
*/
int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
{
struct task_struct *tsk = current;
sigset_t newset;
/* Lockless, only current can change ->blocked, never from irq */
if (oldset) *oldset = tsk->blocked; switch (how) {
case SIG_BLOCK:
sigorsets(&newset, &tsk->blocked, set);
break;
case SIG_UNBLOCK:
sigandnsets(&newset, &tsk->blocked, set);
break;
case SIG_SETMASK:
newset = *set;
break;
default:
return -EINVAL;
}
__set_current_blocked(&newset);
return 0;
}
EXPORT_SYMBOL(sigprocmask);
/*
* The api helps set app-provided sigmasks.
*
* This is useful for syscalls such as ppoll, pselect, io_pgetevents and
* epoll_pwait where a new sigmask is passed from userland for the syscalls.
*
* Note that it does set_restore_sigmask() in advance, so it must be always
* paired with restore_saved_sigmask_unless() before return from syscall.
*/
int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize)
{
sigset_t kmask;
if (!umask)
return 0;
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&kmask, umask, sizeof(sigset_t)))
return -EFAULT;
set_restore_sigmask();
current->saved_sigmask = current->blocked;
set_current_blocked(&kmask);
return 0;
}
#ifdef CONFIG_COMPAT
int set_compat_user_sigmask(const compat_sigset_t __user *umask,
size_t sigsetsize)
{
sigset_t kmask;
if (!umask)
return 0;
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
if (get_compat_sigset(&kmask, umask))
return -EFAULT;
set_restore_sigmask();
current->saved_sigmask = current->blocked;
set_current_blocked(&kmask);
return 0;
}
#endif
/**
* sys_rt_sigprocmask - change the list of currently blocked signals
* @how: whether to add, remove, or set signals
* @nset: stores pending signals
* @oset: previous value of signal mask if non-null
* @sigsetsize: size of sigset_t type
*/
SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset,
sigset_t __user *, oset, size_t, sigsetsize)
{
sigset_t old_set, new_set;
int error;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
old_set = current->blocked;
if (nset) {
if (copy_from_user(&new_set, nset, sizeof(sigset_t)))
return -EFAULT;
sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));
error = sigprocmask(how, &new_set, NULL);
if (error)
return error;
}
if (oset) {
if (copy_to_user(oset, &old_set, sizeof(sigset_t)))
return -EFAULT;
}
return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset,
compat_sigset_t __user *, oset, compat_size_t, sigsetsize)
{
sigset_t old_set = current->blocked;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (nset) {
sigset_t new_set;
int error;
if (get_compat_sigset(&new_set, nset))
return -EFAULT;
sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));
error = sigprocmask(how, &new_set, NULL);
if (error)
return error;
}
return oset ? put_compat_sigset(oset, &old_set, sizeof(*oset)) : 0;
}
#endif
static void do_sigpending(sigset_t *set)
{
spin_lock_irq(¤t->sighand->siglock);
sigorsets(set, ¤t->pending.signal,
¤t->signal->shared_pending.signal);
spin_unlock_irq(¤t->sighand->siglock);
/* Outside the lock because only this thread touches it. */
sigandsets(set, ¤t->blocked, set);
}
/**
* sys_rt_sigpending - examine a pending signal that has been raised
* while blocked
* @uset: stores pending signals
* @sigsetsize: size of sigset_t type or larger
*/
SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize)
{
sigset_t set;
if (sigsetsize > sizeof(*uset))
return -EINVAL;
do_sigpending(&set);
if (copy_to_user(uset, &set, sigsetsize))
return -EFAULT;
return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
compat_size_t, sigsetsize)
{
sigset_t set;
if (sigsetsize > sizeof(*uset))
return -EINVAL;
do_sigpending(&set);
return put_compat_sigset(uset, &set, sigsetsize);
}
#endif
static const struct {
unsigned char limit, layout;
} sig_sicodes[] = {
[SIGILL] = { NSIGILL, SIL_FAULT },
[SIGFPE] = { NSIGFPE, SIL_FAULT },
[SIGSEGV] = { NSIGSEGV, SIL_FAULT },
[SIGBUS] = { NSIGBUS, SIL_FAULT },
[SIGTRAP] = { NSIGTRAP, SIL_FAULT },
#if defined(SIGEMT)
[SIGEMT] = { NSIGEMT, SIL_FAULT },
#endif
[SIGCHLD] = { NSIGCHLD, SIL_CHLD },
[SIGPOLL] = { NSIGPOLL, SIL_POLL },
[SIGSYS] = { NSIGSYS, SIL_SYS },
};
static bool known_siginfo_layout(unsigned sig, int si_code)
{
if (si_code == SI_KERNEL)
return true;
else if ((si_code > SI_USER)) {
if (sig_specific_sicodes(sig)) {
if (si_code <= sig_sicodes[sig].limit)
return true;
}
else if (si_code <= NSIGPOLL)
return true;
}
else if (si_code >= SI_DETHREAD)
return true;
else if (si_code == SI_ASYNCNL)
return true;
return false;
}
enum siginfo_layout siginfo_layout(unsigned sig, int si_code)
{
enum siginfo_layout layout = SIL_KILL;
if ((si_code > SI_USER) && (si_code < SI_KERNEL)) {
if ((sig < ARRAY_SIZE(sig_sicodes)) &&
(si_code <= sig_sicodes[sig].limit)) {
layout = sig_sicodes[sig].layout;
/* Handle the exceptions */
if ((sig == SIGBUS) &&
(si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO))
layout = SIL_FAULT_MCEERR;
else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR))
layout = SIL_FAULT_BNDERR;
#ifdef SEGV_PKUERR
else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR))
layout = SIL_FAULT_PKUERR;
#endif
else if ((sig == SIGTRAP) && (si_code == TRAP_PERF))
layout = SIL_FAULT_PERF_EVENT;
else if (IS_ENABLED(CONFIG_SPARC) &&
(sig == SIGILL) && (si_code == ILL_ILLTRP))
layout = SIL_FAULT_TRAPNO;
else if (IS_ENABLED(CONFIG_ALPHA) &&
((sig == SIGFPE) ||
((sig == SIGTRAP) && (si_code == TRAP_UNK))))
layout = SIL_FAULT_TRAPNO;
}
else if (si_code <= NSIGPOLL)
layout = SIL_POLL;
} else {
if (si_code == SI_TIMER)
layout = SIL_TIMER;
else if (si_code == SI_SIGIO)
layout = SIL_POLL;
else if (si_code < 0)
layout = SIL_RT;
}
return layout;
}
static inline char __user *si_expansion(const siginfo_t __user *info)
{
return ((char __user *)info) + sizeof(struct kernel_siginfo);
}
int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from)
{
char __user *expansion = si_expansion(to);
if (copy_to_user(to, from , sizeof(struct kernel_siginfo)))
return -EFAULT;
if (clear_user(expansion, SI_EXPANSION_SIZE))
return -EFAULT;
return 0;
}
static int post_copy_siginfo_from_user(kernel_siginfo_t *info,
const siginfo_t __user *from)
{
if (unlikely(!known_siginfo_layout(info->si_signo, info->si_code))) {
char __user *expansion = si_expansion(from);
char buf[SI_EXPANSION_SIZE];
int i;
/*
* An unknown si_code might need more than
* sizeof(struct kernel_siginfo) bytes. Verify all of the
* extra bytes are 0. This guarantees copy_siginfo_to_user
* will return this data to userspace exactly.
*/
if (copy_from_user(&buf, expansion, SI_EXPANSION_SIZE))
return -EFAULT;
for (i = 0; i < SI_EXPANSION_SIZE; i++) {
if (buf[i] != 0)
return -E2BIG;
}
}
return 0;
}
static int __copy_siginfo_from_user(int signo, kernel_siginfo_t *to,
const siginfo_t __user *from)
{
if (copy_from_user(to, from, sizeof(struct kernel_siginfo)))
return -EFAULT;
to->si_signo = signo;
return post_copy_siginfo_from_user(to, from);
}
int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from)
{
if (copy_from_user(to, from, sizeof(struct kernel_siginfo)))
return -EFAULT;
return post_copy_siginfo_from_user(to, from);
}
#ifdef CONFIG_COMPAT
/**
* copy_siginfo_to_external32 - copy a kernel siginfo into a compat user siginfo
* @to: compat siginfo destination
* @from: kernel siginfo source
*
* Note: This function does not work properly for the SIGCHLD on x32, but
* fortunately it doesn't have to. The only valid callers for this function are
* copy_siginfo_to_user32, which is overriden for x32 and the coredump code.
* The latter does not care because SIGCHLD will never cause a coredump.
*/
void copy_siginfo_to_external32(struct compat_siginfo *to,
const struct kernel_siginfo *from)
{
memset(to, 0, sizeof(*to));
to->si_signo = from->si_signo;
to->si_errno = from->si_errno;
to->si_code = from->si_code;
switch(siginfo_layout(from->si_signo, from->si_code)) {
case SIL_KILL:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
break;
case SIL_TIMER:
to->si_tid = from->si_tid;
to->si_overrun = from->si_overrun;
to->si_int = from->si_int;
break;
case SIL_POLL:
to->si_band = from->si_band;
to->si_fd = from->si_fd;
break;
case SIL_FAULT:
to->si_addr = ptr_to_compat(from->si_addr);
break;
case SIL_FAULT_TRAPNO:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_trapno = from->si_trapno;
break;
case SIL_FAULT_MCEERR:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_addr_lsb = from->si_addr_lsb;
break;
case SIL_FAULT_BNDERR:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_lower = ptr_to_compat(from->si_lower);
to->si_upper = ptr_to_compat(from->si_upper);
break;
case SIL_FAULT_PKUERR:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_pkey = from->si_pkey;
break;
case SIL_FAULT_PERF_EVENT:
to->si_addr = ptr_to_compat(from->si_addr);
to->si_perf_data = from->si_perf_data;
to->si_perf_type = from->si_perf_type;
to->si_perf_flags = from->si_perf_flags;
break;
case SIL_CHLD:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
to->si_status = from->si_status;
to->si_utime = from->si_utime;
to->si_stime = from->si_stime;
break;
case SIL_RT:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
to->si_int = from->si_int;
break;
case SIL_SYS:
to->si_call_addr = ptr_to_compat(from->si_call_addr);
to->si_syscall = from->si_syscall;
to->si_arch = from->si_arch;
break;
}
}
int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
const struct kernel_siginfo *from)
{
struct compat_siginfo new;
copy_siginfo_to_external32(&new, from);
if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
return -EFAULT;
return 0;
}
static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
const struct compat_siginfo *from)
{
clear_siginfo(to);
to->si_signo = from->si_signo;
to->si_errno = from->si_errno;
to->si_code = from->si_code;
switch(siginfo_layout(from->si_signo, from->si_code)) {
case SIL_KILL:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
break;
case SIL_TIMER:
to->si_tid = from->si_tid;
to->si_overrun = from->si_overrun;
to->si_int = from->si_int;
break;
case SIL_POLL:
to->si_band = from->si_band;
to->si_fd = from->si_fd;
break;
case SIL_FAULT:
to->si_addr = compat_ptr(from->si_addr);
break;
case SIL_FAULT_TRAPNO:
to->si_addr = compat_ptr(from->si_addr);
to->si_trapno = from->si_trapno;
break;
case SIL_FAULT_MCEERR:
to->si_addr = compat_ptr(from->si_addr);
to->si_addr_lsb = from->si_addr_lsb;
break;
case SIL_FAULT_BNDERR:
to->si_addr = compat_ptr(from->si_addr);
to->si_lower = compat_ptr(from->si_lower);
to->si_upper = compat_ptr(from->si_upper);
break;
case SIL_FAULT_PKUERR:
to->si_addr = compat_ptr(from->si_addr);
to->si_pkey = from->si_pkey;
break;
case SIL_FAULT_PERF_EVENT:
to->si_addr = compat_ptr(from->si_addr);
to->si_perf_data = from->si_perf_data;
to->si_perf_type = from->si_perf_type;
to->si_perf_flags = from->si_perf_flags;
break;
case SIL_CHLD:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
to->si_status = from->si_status;
#ifdef CONFIG_X86_X32_ABI
if (in_x32_syscall()) {
to->si_utime = from->_sifields._sigchld_x32._utime;
to->si_stime = from->_sifields._sigchld_x32._stime;
} else
#endif
{
to->si_utime = from->si_utime;
to->si_stime = from->si_stime;
}
break;
case SIL_RT:
to->si_pid = from->si_pid;
to->si_uid = from->si_uid;
to->si_int = from->si_int;
break;
case SIL_SYS:
to->si_call_addr = compat_ptr(from->si_call_addr);
to->si_syscall = from->si_syscall;
to->si_arch = from->si_arch;
break;
}
return 0;
}
static int __copy_siginfo_from_user32(int signo, struct kernel_siginfo *to,
const struct compat_siginfo __user *ufrom)
{
struct compat_siginfo from;
if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo)))
return -EFAULT;
from.si_signo = signo;
return post_copy_siginfo_from_user32(to, &from);
}
int copy_siginfo_from_user32(struct kernel_siginfo *to,
const struct compat_siginfo __user *ufrom)
{
struct compat_siginfo from;
if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo)))
return -EFAULT;
return post_copy_siginfo_from_user32(to, &from);
}
#endif /* CONFIG_COMPAT */
/**
* do_sigtimedwait - wait for queued signals specified in @which
* @which: queued signals to wait for
* @info: if non-null, the signal's siginfo is returned here
* @ts: upper bound on process time suspension
*/
static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
const struct timespec64 *ts)
{
ktime_t *to = NULL, timeout = KTIME_MAX;
struct task_struct *tsk = current;
sigset_t mask = *which;
enum pid_type type;
int sig, ret = 0;
if (ts) {
if (!timespec64_valid(ts))
return -EINVAL;
timeout = timespec64_to_ktime(*ts);
to = &timeout;
}
/*
* Invert the set of allowed signals to get those we want to block.
*/
sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP));
signotset(&mask);
spin_lock_irq(&tsk->sighand->siglock);
sig = dequeue_signal(&mask, info, &type);
if (!sig && timeout) {
/*
* None ready, temporarily unblock those we're interested
* while we are sleeping in so that we'll be awakened when
* they arrive. Unblocking is always fine, we can avoid
* set_current_blocked().
*/
tsk->real_blocked = tsk->blocked;
sigandsets(&tsk->blocked, &tsk->blocked, &mask);
recalc_sigpending();
spin_unlock_irq(&tsk->sighand->siglock);
__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
ret = schedule_hrtimeout_range(to, tsk->timer_slack_ns,
HRTIMER_MODE_REL);
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, &tsk->real_blocked);
sigemptyset(&tsk->real_blocked);
sig = dequeue_signal(&mask, info, &type);
}
spin_unlock_irq(&tsk->sighand->siglock);
if (sig)
return sig;
return ret ? -EINTR : -EAGAIN;
}
/**
* sys_rt_sigtimedwait - synchronously wait for queued signals specified
* in @uthese
* @uthese: queued signals to wait for
* @uinfo: if non-null, the signal's siginfo is returned here
* @uts: upper bound on process time suspension
* @sigsetsize: size of sigset_t type
*/
SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
siginfo_t __user *, uinfo,
const struct __kernel_timespec __user *, uts,
size_t, sigsetsize)
{
sigset_t these;
struct timespec64 ts;
kernel_siginfo_t info;
int ret;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&these, uthese, sizeof(these)))
return -EFAULT;
if (uts) {
if (get_timespec64(&ts, uts))
return -EFAULT;
}
ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL);
if (ret > 0 && uinfo) {
if (copy_siginfo_to_user(uinfo, &info))
ret = -EFAULT;
}
return ret;
}
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE4(rt_sigtimedwait_time32, const sigset_t __user *, uthese,
siginfo_t __user *, uinfo,
const struct old_timespec32 __user *, uts,
size_t, sigsetsize)
{
sigset_t these;
struct timespec64 ts;
kernel_siginfo_t info;
int ret;
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&these, uthese, sizeof(these)))
return -EFAULT;
if (uts) {
if (get_old_timespec32(&ts, uts))
return -EFAULT;
}
ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL);
if (ret > 0 && uinfo) {
if (copy_siginfo_to_user(uinfo, &info))
ret = -EFAULT;
}
return ret;
}
#endif
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese,
struct compat_siginfo __user *, uinfo,
struct __kernel_timespec __user *, uts, compat_size_t, sigsetsize)
{
sigset_t s;
struct timespec64 t;
kernel_siginfo_t info;
long ret;
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (get_compat_sigset(&s, uthese))
return -EFAULT;
if (uts) {
if (get_timespec64(&t, uts))
return -EFAULT;
}
ret = do_sigtimedwait(&s, &info, uts ? &t : NULL);
if (ret > 0 && uinfo) {
if (copy_siginfo_to_user32(uinfo, &info))
ret = -EFAULT;
}
return ret;
}
#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese,
struct compat_siginfo __user *, uinfo,
struct old_timespec32 __user *, uts, compat_size_t, sigsetsize)
{
sigset_t s;
struct timespec64 t;
kernel_siginfo_t info;
long ret;
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (get_compat_sigset(&s, uthese))
return -EFAULT;
if (uts) {
if (get_old_timespec32(&t, uts))
return -EFAULT;
}
ret = do_sigtimedwait(&s, &info, uts ? &t : NULL);
if (ret > 0 && uinfo) {
if (copy_siginfo_to_user32(uinfo, &info))
ret = -EFAULT;
}
return ret;
}
#endif
#endif
static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info,
enum pid_type type)
{
clear_siginfo(info);
info->si_signo = sig;
info->si_errno = 0;
info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER;
info->si_pid = task_tgid_vnr(current);
info->si_uid = from_kuid_munged(current_user_ns(), current_uid());
}
/**
* sys_kill - send a signal to a process
* @pid: the PID of the process
* @sig: signal to be sent
*/
SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
{
struct kernel_siginfo info;
prepare_kill_siginfo(sig, &info, PIDTYPE_TGID);
return kill_something_info(sig, &info, pid);
}
/*
* Verify that the signaler and signalee either are in the same pid namespace
* or that the signaler's pid namespace is an ancestor of the signalee's pid
* namespace.
*/
static bool access_pidfd_pidns(struct pid *pid)
{
struct pid_namespace *active = task_active_pid_ns(current);
struct pid_namespace *p = ns_of_pid(pid);
for (;;) {
if (!p)
return false;
if (p == active)
break;
p = p->parent;
}
return true;
}
static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo,
siginfo_t __user *info)
{
#ifdef CONFIG_COMPAT
/*
* Avoid hooking up compat syscalls and instead handle necessary
* conversions here. Note, this is a stop-gap measure and should not be
* considered a generic solution.
*/
if (in_compat_syscall())
return copy_siginfo_from_user32(
kinfo, (struct compat_siginfo __user *)info);
#endif
return copy_siginfo_from_user(kinfo, info);
}
static struct pid *pidfd_to_pid(const struct file *file)
{
struct pid *pid;
pid = pidfd_pid(file);
if (!IS_ERR(pid))
return pid;
return tgid_pidfd_to_pid(file);
}
#define PIDFD_SEND_SIGNAL_FLAGS \
(PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \
PIDFD_SIGNAL_PROCESS_GROUP)
static int do_pidfd_send_signal(struct pid *pid, int sig, enum pid_type type,
siginfo_t __user *info, unsigned int flags)
{
kernel_siginfo_t kinfo;
switch (flags) {
case PIDFD_SIGNAL_THREAD:
type = PIDTYPE_PID;
break;
case PIDFD_SIGNAL_THREAD_GROUP:
type = PIDTYPE_TGID;
break;
case PIDFD_SIGNAL_PROCESS_GROUP:
type = PIDTYPE_PGID;
break;
}
if (info) {
int ret;
ret = copy_siginfo_from_user_any(&kinfo, info);
if (unlikely(ret))
return ret;
if (unlikely(sig != kinfo.si_signo))
return -EINVAL;
/* Only allow sending arbitrary signals to yourself. */
if ((task_pid(current) != pid || type > PIDTYPE_TGID) &&
(kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
return -EPERM;
} else {
prepare_kill_siginfo(sig, &kinfo, type);
}
if (type == PIDTYPE_PGID)
return kill_pgrp_info(sig, &kinfo, pid);
return kill_pid_info_type(sig, &kinfo, pid, type);
}
/**
* sys_pidfd_send_signal - Signal a process through a pidfd
* @pidfd: file descriptor of the process
* @sig: signal to send
* @info: signal info
* @flags: future flags
*
* Send the signal to the thread group or to the individual thread depending
* on PIDFD_THREAD.
* In the future extension to @flags may be used to override the default scope
* of @pidfd.
*
* Return: 0 on success, negative errno on failure
*/
SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
siginfo_t __user *, info, unsigned int, flags)
{
struct pid *pid;
enum pid_type type;
/* Enforce flags be set to 0 until we add an extension. */
if (flags & ~PIDFD_SEND_SIGNAL_FLAGS)
return -EINVAL;
/* Ensure that only a single signal scope determining flag is set. */
if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1)
return -EINVAL;
switch (pidfd) {
case PIDFD_SELF_THREAD:
pid = get_task_pid(current, PIDTYPE_PID);
type = PIDTYPE_PID;
break;
case PIDFD_SELF_THREAD_GROUP:
pid = get_task_pid(current, PIDTYPE_TGID);
type = PIDTYPE_TGID;
break;
default: {
CLASS(fd, f)(pidfd);
if (fd_empty(f))
return -EBADF;
/* Is this a pidfd? */
pid = pidfd_to_pid(fd_file(f));
if (IS_ERR(pid))
return PTR_ERR(pid);
if (!access_pidfd_pidns(pid))
return -EINVAL;
/* Infer scope from the type of pidfd. */
if (fd_file(f)->f_flags & PIDFD_THREAD)
type = PIDTYPE_PID;
else
type = PIDTYPE_TGID;
return do_pidfd_send_signal(pid, sig, type, info, flags);
}
}
return do_pidfd_send_signal(pid, sig, type, info, flags);
}
static int
do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info)
{
struct task_struct *p;
int error = -ESRCH;
rcu_read_lock();
p = find_task_by_vpid(pid);
if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) {
error = check_kill_permission(sig, info, p);
/*
* The null signal is a permissions and process existence
* probe. No signal is actually delivered.
*/
if (!error && sig) {
error = do_send_sig_info(sig, info, p, PIDTYPE_PID);
/*
* If lock_task_sighand() failed we pretend the task
* dies after receiving the signal. The window is tiny,
* and the signal is private anyway.
*/
if (unlikely(error == -ESRCH))
error = 0;
}
}
rcu_read_unlock();
return error;
}
static int do_tkill(pid_t tgid, pid_t pid, int sig)
{
struct kernel_siginfo info;
prepare_kill_siginfo(sig, &info, PIDTYPE_PID);
return do_send_specific(tgid, pid, sig, &info);
}
/**
* sys_tgkill - send signal to one specific thread
* @tgid: the thread group ID of the thread
* @pid: the PID of the thread
* @sig: signal to be sent
*
* This syscall also checks the @tgid and returns -ESRCH even if the PID
* exists but it's not belonging to the target process anymore. This
* method solves the problem of threads exiting and PIDs getting reused.
*/
SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig)
{
/* This is only valid for single tasks */
if (pid <= 0 || tgid <= 0)
return -EINVAL;
return do_tkill(tgid, pid, sig);
}
/**
* sys_tkill - send signal to one specific task
* @pid: the PID of the task
* @sig: signal to be sent
*
* Send a signal to only one task, even if it's a CLONE_THREAD task.
*/
SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig)
{
/* This is only valid for single tasks */
if (pid <= 0)
return -EINVAL;
return do_tkill(0, pid, sig);
}
static int do_rt_sigqueueinfo(pid_t pid, int sig, kernel_siginfo_t *info)
{
/* Not even root can pretend to send signals from the kernel.
* Nor can they impersonate a kill()/tgkill(), which adds source info.
*/
if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
(task_pid_vnr(current) != pid))
return -EPERM;
/* POSIX.1b doesn't mention process groups. */
return kill_proc_info(sig, info, pid);
}
/**
* sys_rt_sigqueueinfo - send signal information to a signal
* @pid: the PID of the thread
* @sig: signal to be sent
* @uinfo: signal info to be sent
*/
SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig,
siginfo_t __user *, uinfo)
{
kernel_siginfo_t info;
int ret = __copy_siginfo_from_user(sig, &info, uinfo);
if (unlikely(ret))
return ret;
return do_rt_sigqueueinfo(pid, sig, &info);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo,
compat_pid_t, pid,
int, sig,
struct compat_siginfo __user *, uinfo)
{
kernel_siginfo_t info;
int ret = __copy_siginfo_from_user32(sig, &info, uinfo);
if (unlikely(ret))
return ret;
return do_rt_sigqueueinfo(pid, sig, &info);
}
#endif
static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, kernel_siginfo_t *info)
{
/* This is only valid for single tasks */
if (pid <= 0 || tgid <= 0)
return -EINVAL;
/* Not even root can pretend to send signals from the kernel.
* Nor can they impersonate a kill()/tgkill(), which adds source info.
*/
if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
(task_pid_vnr(current) != pid))
return -EPERM;
return do_send_specific(tgid, pid, sig, info);
}
SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig,
siginfo_t __user *, uinfo)
{
kernel_siginfo_t info;
int ret = __copy_siginfo_from_user(sig, &info, uinfo);
if (unlikely(ret))
return ret;
return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo,
compat_pid_t, tgid,
compat_pid_t, pid,
int, sig,
struct compat_siginfo __user *, uinfo)
{
kernel_siginfo_t info;
int ret = __copy_siginfo_from_user32(sig, &info, uinfo);
if (unlikely(ret))
return ret;
return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
}
#endif
/*
* For kthreads only, must not be used if cloned with CLONE_SIGHAND
*/
void kernel_sigaction(int sig, __sighandler_t action)
{
spin_lock_irq(¤t->sighand->siglock);
current->sighand->action[sig - 1].sa.sa_handler = action;
if (action == SIG_IGN) {
sigset_t mask;
sigemptyset(&mask);
sigaddset(&mask, sig);
flush_sigqueue_mask(current, &mask, ¤t->signal->shared_pending);
flush_sigqueue_mask(current, &mask, ¤t->pending);
recalc_sigpending();
}
spin_unlock_irq(¤t->sighand->siglock);
}
EXPORT_SYMBOL(kernel_sigaction);
void __weak sigaction_compat_abi(struct k_sigaction *act,
struct k_sigaction *oact)
{
}
int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
{
struct task_struct *p = current, *t;
struct k_sigaction *k;
sigset_t mask;
if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig)))
return -EINVAL;
k = &p->sighand->action[sig-1];
spin_lock_irq(&p->sighand->siglock);
if (k->sa.sa_flags & SA_IMMUTABLE) {
spin_unlock_irq(&p->sighand->siglock);
return -EINVAL;
}
if (oact)
*oact = *k;
/*
* Make sure that we never accidentally claim to support SA_UNSUPPORTED,
* e.g. by having an architecture use the bit in their uapi.
*/
BUILD_BUG_ON(UAPI_SA_FLAGS & SA_UNSUPPORTED);
/*
* Clear unknown flag bits in order to allow userspace to detect missing
* support for flag bits and to allow the kernel to use non-uapi bits
* internally.
*/
if (act)
act->sa.sa_flags &= UAPI_SA_FLAGS;
if (oact)
oact->sa.sa_flags &= UAPI_SA_FLAGS;
sigaction_compat_abi(act, oact);
if (act) {
bool was_ignored = k->sa.sa_handler == SIG_IGN;
sigdelsetmask(&act->sa.sa_mask,
sigmask(SIGKILL) | sigmask(SIGSTOP));
*k = *act;
/*
* POSIX 3.3.1.3:
* "Setting a signal action to SIG_IGN for a signal that is
* pending shall cause the pending signal to be discarded,
* whether or not it is blocked."
*
* "Setting a signal action to SIG_DFL for a signal that is
* pending and whose default action is to ignore the signal
* (for example, SIGCHLD), shall cause the pending signal to
* be discarded, whether or not it is blocked"
*/
if (sig_handler_ignored(sig_handler(p, sig), sig)) {
sigemptyset(&mask);
sigaddset(&mask, sig);
flush_sigqueue_mask(p, &mask, &p->signal->shared_pending);
for_each_thread(p, t)
flush_sigqueue_mask(p, &mask, &t->pending);
} else if (was_ignored) {
posixtimer_sig_unignore(p, sig);
}
}
spin_unlock_irq(&p->sighand->siglock);
return 0;
}
#ifdef CONFIG_DYNAMIC_SIGFRAME
static inline void sigaltstack_lock(void)
__acquires(¤t->sighand->siglock)
{
spin_lock_irq(¤t->sighand->siglock);
}
static inline void sigaltstack_unlock(void)
__releases(¤t->sighand->siglock)
{
spin_unlock_irq(¤t->sighand->siglock);
}
#else
static inline void sigaltstack_lock(void) { }
static inline void sigaltstack_unlock(void) { }
#endif
static int
do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
size_t min_ss_size)
{
struct task_struct *t = current;
int ret = 0;
if (oss) {
memset(oss, 0, sizeof(stack_t));
oss->ss_sp = (void __user *) t->sas_ss_sp;
oss->ss_size = t->sas_ss_size;
oss->ss_flags = sas_ss_flags(sp) |
(current->sas_ss_flags & SS_FLAG_BITS);
}
if (ss) {
void __user *ss_sp = ss->ss_sp;
size_t ss_size = ss->ss_size;
unsigned ss_flags = ss->ss_flags;
int ss_mode;
if (unlikely(on_sig_stack(sp)))
return -EPERM;
ss_mode = ss_flags & ~SS_FLAG_BITS;
if (unlikely(ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK &&
ss_mode != 0))
return -EINVAL;
/*
* Return before taking any locks if no actual
* sigaltstack changes were requested.
*/
if (t->sas_ss_sp == (unsigned long)ss_sp &&
t->sas_ss_size == ss_size &&
t->sas_ss_flags == ss_flags)
return 0;
sigaltstack_lock();
if (ss_mode == SS_DISABLE) {
ss_size = 0;
ss_sp = NULL;
} else {
if (unlikely(ss_size < min_ss_size))
ret = -ENOMEM;
if (!sigaltstack_size_valid(ss_size))
ret = -ENOMEM;
}
if (!ret) {
t->sas_ss_sp = (unsigned long) ss_sp;
t->sas_ss_size = ss_size;
t->sas_ss_flags = ss_flags;
}
sigaltstack_unlock();
}
return ret;
}
SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss)
{
stack_t new, old;
int err;
if (uss && copy_from_user(&new, uss, sizeof(stack_t)))
return -EFAULT;
err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL,
current_user_stack_pointer(),
MINSIGSTKSZ);
if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t)))
err = -EFAULT;
return err;
}
int restore_altstack(const stack_t __user *uss)
{
stack_t new;
if (copy_from_user(&new, uss, sizeof(stack_t)))
return -EFAULT;
(void)do_sigaltstack(&new, NULL, current_user_stack_pointer(),
MINSIGSTKSZ);
/* squash all but EFAULT for now */
return 0;
}
int __save_altstack(stack_t __user *uss, unsigned long sp)
{
struct task_struct *t = current;
int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size);
return err;
}
#ifdef CONFIG_COMPAT
static int do_compat_sigaltstack(const compat_stack_t __user *uss_ptr,
compat_stack_t __user *uoss_ptr)
{
stack_t uss, uoss;
int ret;
if (uss_ptr) {
compat_stack_t uss32;
if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t)))
return -EFAULT;
uss.ss_sp = compat_ptr(uss32.ss_sp);
uss.ss_flags = uss32.ss_flags;
uss.ss_size = uss32.ss_size;
}
ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss,
compat_user_stack_pointer(),
COMPAT_MINSIGSTKSZ);
if (ret >= 0 && uoss_ptr) {
compat_stack_t old;
memset(&old, 0, sizeof(old));
old.ss_sp = ptr_to_compat(uoss.ss_sp);
old.ss_flags = uoss.ss_flags;
old.ss_size = uoss.ss_size;
if (copy_to_user(uoss_ptr, &old, sizeof(compat_stack_t)))
ret = -EFAULT;
}
return ret;
}
COMPAT_SYSCALL_DEFINE2(sigaltstack,
const compat_stack_t __user *, uss_ptr,
compat_stack_t __user *, uoss_ptr)
{
return do_compat_sigaltstack(uss_ptr, uoss_ptr);
}
int compat_restore_altstack(const compat_stack_t __user *uss)
{
int err = do_compat_sigaltstack(uss, NULL);
/* squash all but -EFAULT for now */
return err == -EFAULT ? err : 0;
}
int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp)
{
int err;
struct task_struct *t = current;
err = __put_user(ptr_to_compat((void __user *)t->sas_ss_sp),
&uss->ss_sp) |
__put_user(t->sas_ss_flags, &uss->ss_flags) |
__put_user(t->sas_ss_size, &uss->ss_size);
return err;
}
#endif
#ifdef __ARCH_WANT_SYS_SIGPENDING
/**
* sys_sigpending - examine pending signals
* @uset: where mask of pending signal is returned
*/
SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, uset)
{
sigset_t set;
if (sizeof(old_sigset_t) > sizeof(*uset))
return -EINVAL;
do_sigpending(&set);
if (copy_to_user(uset, &set, sizeof(old_sigset_t)))
return -EFAULT;
return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
{
sigset_t set;
do_sigpending(&set);
return put_user(set.sig[0], set32);
}
#endif
#endif
#ifdef __ARCH_WANT_SYS_SIGPROCMASK
/**
* sys_sigprocmask - examine and change blocked signals
* @how: whether to add, remove, or set signals
* @nset: signals to add or remove (if non-null)
* @oset: previous value of signal mask if non-null
*
* Some platforms have their own version with special arguments;
* others support only sys_rt_sigprocmask.
*/
SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset,
old_sigset_t __user *, oset)
{
old_sigset_t old_set, new_set;
sigset_t new_blocked;
old_set = current->blocked.sig[0];
if (nset) {
if (copy_from_user(&new_set, nset, sizeof(*nset)))
return -EFAULT;
new_blocked = current->blocked;
switch (how) {
case SIG_BLOCK:
sigaddsetmask(&new_blocked, new_set);
break;
case SIG_UNBLOCK:
sigdelsetmask(&new_blocked, new_set);
break;
case SIG_SETMASK:
new_blocked.sig[0] = new_set;
break;
default:
return -EINVAL;
}
set_current_blocked(&new_blocked);
}
if (oset) {
if (copy_to_user(oset, &old_set, sizeof(*oset)))
return -EFAULT;
}
return 0;
}
#endif /* __ARCH_WANT_SYS_SIGPROCMASK */
#ifndef CONFIG_ODD_RT_SIGACTION
/**
* sys_rt_sigaction - alter an action taken by a process
* @sig: signal to be sent
* @act: new sigaction
* @oact: used to save the previous sigaction
* @sigsetsize: size of sigset_t type
*/
SYSCALL_DEFINE4(rt_sigaction, int, sig,
const struct sigaction __user *, act,
struct sigaction __user *, oact,
size_t, sigsetsize)
{
struct k_sigaction new_sa, old_sa;
int ret;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (act && copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa)))
return -EFAULT;
ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL);
if (ret)
return ret;
if (oact && copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa)))
return -EFAULT;
return 0;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig,
const struct compat_sigaction __user *, act,
struct compat_sigaction __user *, oact,
compat_size_t, sigsetsize)
{
struct k_sigaction new_ka, old_ka;
#ifdef __ARCH_HAS_SA_RESTORER
compat_uptr_t restorer;
#endif
int ret;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
if (act) {
compat_uptr_t handler;
ret = get_user(handler, &act->sa_handler);
new_ka.sa.sa_handler = compat_ptr(handler);
#ifdef __ARCH_HAS_SA_RESTORER
ret |= get_user(restorer, &act->sa_restorer);
new_ka.sa.sa_restorer = compat_ptr(restorer);
#endif
ret |= get_compat_sigset(&new_ka.sa.sa_mask, &act->sa_mask);
ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags);
if (ret)
return -EFAULT;
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
ret = put_user(ptr_to_compat(old_ka.sa.sa_handler),
&oact->sa_handler);
ret |= put_compat_sigset(&oact->sa_mask, &old_ka.sa.sa_mask,
sizeof(oact->sa_mask));
ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags);
#ifdef __ARCH_HAS_SA_RESTORER
ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer),
&oact->sa_restorer);
#endif
}
return ret;
}
#endif
#endif /* !CONFIG_ODD_RT_SIGACTION */
#ifdef CONFIG_OLD_SIGACTION
SYSCALL_DEFINE3(sigaction, int, sig,
const struct old_sigaction __user *, act,
struct old_sigaction __user *, oact)
{
struct k_sigaction new_ka, old_ka;
int ret;
if (act) {
old_sigset_t mask;
if (!access_ok(act, sizeof(*act)) ||
__get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
__get_user(new_ka.sa.sa_restorer, &act->sa_restorer) ||
__get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
__get_user(mask, &act->sa_mask))
return -EFAULT;
#ifdef __ARCH_HAS_KA_RESTORER
new_ka.ka_restorer = NULL;
#endif
siginitset(&new_ka.sa.sa_mask, mask);
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
if (!access_ok(oact, sizeof(*oact)) ||
__put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
__put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
return -EFAULT;
}
return ret;
}
#endif
#ifdef CONFIG_COMPAT_OLD_SIGACTION
COMPAT_SYSCALL_DEFINE3(sigaction, int, sig,
const struct compat_old_sigaction __user *, act,
struct compat_old_sigaction __user *, oact)
{
struct k_sigaction new_ka, old_ka;
int ret;
compat_old_sigset_t mask;
compat_uptr_t handler, restorer;
if (act) {
if (!access_ok(act, sizeof(*act)) ||
__get_user(handler, &act->sa_handler) ||
__get_user(restorer, &act->sa_restorer) ||
__get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
__get_user(mask, &act->sa_mask))
return -EFAULT;
#ifdef __ARCH_HAS_KA_RESTORER
new_ka.ka_restorer = NULL;
#endif
new_ka.sa.sa_handler = compat_ptr(handler);
new_ka.sa.sa_restorer = compat_ptr(restorer);
siginitset(&new_ka.sa.sa_mask, mask);
}
ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
if (!ret && oact) {
if (!access_ok(oact, sizeof(*oact)) ||
__put_user(ptr_to_compat(old_ka.sa.sa_handler),
&oact->sa_handler) ||
__put_user(ptr_to_compat(old_ka.sa.sa_restorer),
&oact->sa_restorer) ||
__put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
return -EFAULT;
}
return ret;
}
#endif
#ifdef CONFIG_SGETMASK_SYSCALL
/*
* For backwards compatibility. Functionality superseded by sigprocmask.
*/
SYSCALL_DEFINE0(sgetmask)
{
/* SMP safe */
return current->blocked.sig[0];
}
SYSCALL_DEFINE1(ssetmask, int, newmask)
{
int old = current->blocked.sig[0];
sigset_t newset;
siginitset(&newset, newmask);
set_current_blocked(&newset);
return old;
}
#endif /* CONFIG_SGETMASK_SYSCALL */
#ifdef __ARCH_WANT_SYS_SIGNAL
/*
* For backwards compatibility. Functionality superseded by sigaction.
*/
SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler)
{
struct k_sigaction new_sa, old_sa;
int ret;
new_sa.sa.sa_handler = handler;
new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK;
sigemptyset(&new_sa.sa.sa_mask);
ret = do_sigaction(sig, &new_sa, &old_sa);
return ret ? ret : (unsigned long)old_sa.sa.sa_handler;
}
#endif /* __ARCH_WANT_SYS_SIGNAL */
#ifdef __ARCH_WANT_SYS_PAUSE
SYSCALL_DEFINE0(pause)
{
while (!signal_pending(current)) {
__set_current_state(TASK_INTERRUPTIBLE);
schedule();
}
return -ERESTARTNOHAND;
}
#endif
static int sigsuspend(sigset_t *set)
{
current->saved_sigmask = current->blocked;
set_current_blocked(set);
while (!signal_pending(current)) {
__set_current_state(TASK_INTERRUPTIBLE);
schedule();
}
set_restore_sigmask();
return -ERESTARTNOHAND;
}
/**
* sys_rt_sigsuspend - replace the signal mask for a value with the
* @unewset value until a signal is received
* @unewset: new signal mask value
* @sigsetsize: size of sigset_t type
*/
SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
{
sigset_t newset;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&newset, unewset, sizeof(newset)))
return -EFAULT;
return sigsuspend(&newset);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize)
{
sigset_t newset;
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (get_compat_sigset(&newset, unewset))
return -EFAULT;
return sigsuspend(&newset);
}
#endif
#ifdef CONFIG_OLD_SIGSUSPEND
SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask)
{
sigset_t blocked;
siginitset(&blocked, mask);
return sigsuspend(&blocked);
}
#endif
#ifdef CONFIG_OLD_SIGSUSPEND3
SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask)
{
sigset_t blocked;
siginitset(&blocked, mask);
return sigsuspend(&blocked);
}
#endif
__weak const char *arch_vma_name(struct vm_area_struct *vma)
{
return NULL;
}
static inline void siginfo_buildtime_checks(void)
{
BUILD_BUG_ON(sizeof(struct siginfo) != SI_MAX_SIZE);
/* Verify the offsets in the two siginfos match */
#define CHECK_OFFSET(field) \
BUILD_BUG_ON(offsetof(siginfo_t, field) != offsetof(kernel_siginfo_t, field))
/* kill */
CHECK_OFFSET(si_pid);
CHECK_OFFSET(si_uid);
/* timer */
CHECK_OFFSET(si_tid);
CHECK_OFFSET(si_overrun);
CHECK_OFFSET(si_value);
/* rt */
CHECK_OFFSET(si_pid);
CHECK_OFFSET(si_uid);
CHECK_OFFSET(si_value);
/* sigchld */
CHECK_OFFSET(si_pid);
CHECK_OFFSET(si_uid);
CHECK_OFFSET(si_status);
CHECK_OFFSET(si_utime);
CHECK_OFFSET(si_stime);
/* sigfault */
CHECK_OFFSET(si_addr);
CHECK_OFFSET(si_trapno);
CHECK_OFFSET(si_addr_lsb);
CHECK_OFFSET(si_lower);
CHECK_OFFSET(si_upper);
CHECK_OFFSET(si_pkey);
CHECK_OFFSET(si_perf_data);
CHECK_OFFSET(si_perf_type);
CHECK_OFFSET(si_perf_flags);
/* sigpoll */
CHECK_OFFSET(si_band);
CHECK_OFFSET(si_fd);
/* sigsys */
CHECK_OFFSET(si_call_addr);
CHECK_OFFSET(si_syscall);
CHECK_OFFSET(si_arch);
#undef CHECK_OFFSET
/* usb asyncio */
BUILD_BUG_ON(offsetof(struct siginfo, si_pid) !=
offsetof(struct siginfo, si_addr));
if (sizeof(int) == sizeof(void __user *)) {
BUILD_BUG_ON(sizeof_field(struct siginfo, si_pid) !=
sizeof(void __user *));
} else {
BUILD_BUG_ON((sizeof_field(struct siginfo, si_pid) +
sizeof_field(struct siginfo, si_uid)) !=
sizeof(void __user *));
BUILD_BUG_ON(offsetofend(struct siginfo, si_pid) !=
offsetof(struct siginfo, si_uid));
}
#ifdef CONFIG_COMPAT
BUILD_BUG_ON(offsetof(struct compat_siginfo, si_pid) !=
offsetof(struct compat_siginfo, si_addr));
BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) !=
sizeof(compat_uptr_t));
BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) !=
sizeof_field(struct siginfo, si_pid));
#endif
}
#if defined(CONFIG_SYSCTL)
static const struct ctl_table signal_debug_table[] = {
#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
{
.procname = "exception-trace",
.data = &show_unhandled_signals,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#endif
};
static int __init init_signal_sysctls(void)
{
register_sysctl_init("debug", signal_debug_table);
return 0;
}
early_initcall(init_signal_sysctls);
#endif /* CONFIG_SYSCTL */
void __init signals_init(void)
{
siginfo_buildtime_checks();
sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC | SLAB_ACCOUNT);
}
#ifdef CONFIG_KGDB_KDB
#include <linux/kdb.h>
/*
* kdb_send_sig - Allows kdb to send signals without exposing
* signal internals. This function checks if the required locks are
* available before calling the main signal code, to avoid kdb
* deadlocks.
*/
void kdb_send_sig(struct task_struct *t, int sig)
{
static struct task_struct *kdb_prev_t;
int new_t, ret;
if (!spin_trylock(&t->sighand->siglock)) {
kdb_printf("Can't do kill command now.\n"
"The sigmask lock is held somewhere else in "
"kernel, try again later\n");
return;
}
new_t = kdb_prev_t != t;
kdb_prev_t = t;
if (!task_is_running(t) && new_t) {
spin_unlock(&t->sighand->siglock);
kdb_printf("Process is not RUNNING, sending a signal from "
"kdb risks deadlock\n"
"on the run queue locks. "
"The signal has _not_ been sent.\n"
"Reissue the kill command if you want to risk "
"the deadlock.\n");
return;
}
ret = send_signal_locked(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
spin_unlock(&t->sighand->siglock);
if (ret)
kdb_printf("Fail to deliver Signal %d to process %d.\n",
sig, t->pid);
else
kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid);
}
#endif /* CONFIG_KGDB_KDB */
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kdebug.h>
#include <linux/kprobes.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/rcupdate.h>
#include <linux/vmalloc.h>
#define CREATE_TRACE_POINTS
#include <trace/events/notifier.h>
/*
* Notifier chain core routines. The exported routines below
* are layered on top of these, with appropriate locking added.
*/
static int notifier_chain_register(struct notifier_block **nl,
struct notifier_block *n,
bool unique_priority)
{
while ((*nl) != NULL) {
if (unlikely((*nl) == n)) {
WARN(1, "notifier callback %ps already registered",
n->notifier_call);
return -EEXIST;
}
if (n->priority > (*nl)->priority)
break;
if (n->priority == (*nl)->priority && unique_priority)
return -EBUSY;
nl = &((*nl)->next);
}
n->next = *nl;
rcu_assign_pointer(*nl, n);
trace_notifier_register((void *)n->notifier_call);
return 0;
}
static int notifier_chain_unregister(struct notifier_block **nl,
struct notifier_block *n)
{
while ((*nl) != NULL) {
if ((*nl) == n) {
rcu_assign_pointer(*nl, n->next);
trace_notifier_unregister((void *)n->notifier_call);
return 0;
}
nl = &((*nl)->next);
}
return -ENOENT;
}
/**
* notifier_call_chain - Informs the registered notifiers about an event.
* @nl: Pointer to head of the blocking notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
* @nr_to_call: Number of notifier functions to be called. Don't care
* value of this parameter is -1.
* @nr_calls: Records the number of notifications sent. Don't care
* value of this field is NULL.
* Return: notifier_call_chain returns the value returned by the
* last notifier function called.
*/
static int notifier_call_chain(struct notifier_block **nl,
unsigned long val, void *v,
int nr_to_call, int *nr_calls)
{
int ret = NOTIFY_DONE;
struct notifier_block *nb, *next_nb;
nb = rcu_dereference_raw(*nl);
while (nb && nr_to_call) {
next_nb = rcu_dereference_raw(nb->next);
#ifdef CONFIG_DEBUG_NOTIFIERS
if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
WARN(1, "Invalid notifier called!");
nb = next_nb;
continue;
}
#endif
trace_notifier_run((void *)nb->notifier_call);
ret = nb->notifier_call(nb, val, v);
if (nr_calls) (*nr_calls)++; if (ret & NOTIFY_STOP_MASK)
break;
nb = next_nb;
nr_to_call--;
}
return ret;
}
NOKPROBE_SYMBOL(notifier_call_chain);
/**
* notifier_call_chain_robust - Inform the registered notifiers about an event
* and rollback on error.
* @nl: Pointer to head of the blocking notifier chain
* @val_up: Value passed unmodified to the notifier function
* @val_down: Value passed unmodified to the notifier function when recovering
* from an error on @val_up
* @v: Pointer passed unmodified to the notifier function
*
* NOTE: It is important the @nl chain doesn't change between the two
* invocations of notifier_call_chain() such that we visit the
* exact same notifier callbacks; this rules out any RCU usage.
*
* Return: the return value of the @val_up call.
*/
static int notifier_call_chain_robust(struct notifier_block **nl,
unsigned long val_up, unsigned long val_down,
void *v)
{
int ret, nr = 0;
ret = notifier_call_chain(nl, val_up, v, -1, &nr);
if (ret & NOTIFY_STOP_MASK)
notifier_call_chain(nl, val_down, v, nr-1, NULL);
return ret;
}
/*
* Atomic notifier chain routines. Registration and unregistration
* use a spinlock, and call_chain is synchronized by RCU (no locks).
*/
/**
* atomic_notifier_chain_register - Add notifier to an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an atomic notifier chain.
*
* Returns 0 on success, %-EEXIST on error.
*/
int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
struct notifier_block *n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_register(&nh->head, n, false);
spin_unlock_irqrestore(&nh->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
/**
* atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an atomic notifier chain if there is no other
* notifier registered using the same priority.
*
* Returns 0 on success, %-EEXIST or %-EBUSY on error.
*/
int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh,
struct notifier_block *n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_register(&nh->head, n, true);
spin_unlock_irqrestore(&nh->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio);
/**
* atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from an atomic notifier chain.
*
* Returns zero on success or %-ENOENT on failure.
*/
int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
struct notifier_block *n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_unregister(&nh->head, n);
spin_unlock_irqrestore(&nh->lock, flags);
synchronize_rcu();
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
/**
* atomic_notifier_call_chain - Call functions in an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in an atomic context, so they must not block.
* This routine uses RCU to synchronize with changes to the chain.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then atomic_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
unsigned long val, void *v)
{
int ret;
rcu_read_lock();
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
NOKPROBE_SYMBOL(atomic_notifier_call_chain);
/**
* atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty
* @nh: Pointer to head of the atomic notifier chain
*
* Checks whether notifier chain is empty.
*
* Returns true is notifier chain is empty, false otherwise.
*/
bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh)
{
return !rcu_access_pointer(nh->head);
}
/*
* Blocking notifier chain routines. All access to the chain is
* synchronized by an rwsem.
*/
static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh,
struct notifier_block *n,
bool unique_priority)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call down_write().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_register(&nh->head, n, unique_priority);
down_write(&nh->rwsem);
ret = notifier_chain_register(&nh->head, n, unique_priority);
up_write(&nh->rwsem);
return ret;
}
/**
* blocking_notifier_chain_register - Add notifier to a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to a blocking notifier chain.
* Must be called in process context.
*
* Returns 0 on success, %-EEXIST on error.
*/
int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
struct notifier_block *n)
{
return __blocking_notifier_chain_register(nh, n, false);
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
/**
* blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an blocking notifier chain if there is no other
* notifier registered using the same priority.
*
* Returns 0 on success, %-EEXIST or %-EBUSY on error.
*/
int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh,
struct notifier_block *n)
{
return __blocking_notifier_chain_register(nh, n, true);
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio);
/**
* blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from a blocking notifier chain.
* Must be called from process context.
*
* Returns zero on success or %-ENOENT on failure.
*/
int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call down_write().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_unregister(&nh->head, n);
down_write(&nh->rwsem);
ret = notifier_chain_unregister(&nh->head, n);
up_write(&nh->rwsem);
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v)
{
int ret = NOTIFY_DONE;
/*
* We check the head outside the lock, but if this access is
* racy then it does not matter what the result of the test
* is, we re-check the list after having taken the lock anyway:
*/
if (rcu_access_pointer(nh->head)) {
down_read(&nh->rwsem);
ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
up_read(&nh->rwsem);
}
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust);
/**
* blocking_notifier_call_chain - Call functions in a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in a process context, so they are allowed to block.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then blocking_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
unsigned long val, void *v)
{
int ret = NOTIFY_DONE;
/*
* We check the head outside the lock, but if this access is
* racy then it does not matter what the result of the test
* is, we re-check the list after having taken the lock anyway:
*/
if (rcu_access_pointer(nh->head)) {
down_read(&nh->rwsem);
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
up_read(&nh->rwsem);
}
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
/*
* Raw notifier chain routines. There is no protection;
* the caller must provide it. Use at your own risk!
*/
/**
* raw_notifier_chain_register - Add notifier to a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to a raw notifier chain.
* All locking must be provided by the caller.
*
* Returns 0 on success, %-EEXIST on error.
*/
int raw_notifier_chain_register(struct raw_notifier_head *nh,
struct notifier_block *n)
{
return notifier_chain_register(&nh->head, n, false);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_register);
/**
* raw_notifier_chain_unregister - Remove notifier from a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from a raw notifier chain.
* All locking must be provided by the caller.
*
* Returns zero on success or %-ENOENT on failure.
*/
int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
struct notifier_block *n)
{
return notifier_chain_unregister(&nh->head, n);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v)
{
return notifier_call_chain_robust(&nh->head, val_up, val_down, v);
}
EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust);
/**
* raw_notifier_call_chain - Call functions in a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in an undefined context.
* All locking must be provided by the caller.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then raw_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int raw_notifier_call_chain(struct raw_notifier_head *nh,
unsigned long val, void *v)
{
return notifier_call_chain(&nh->head, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
/*
* SRCU notifier chain routines. Registration and unregistration
* use a mutex, and call_chain is synchronized by SRCU (no locks).
*/
/**
* srcu_notifier_chain_register - Add notifier to an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an SRCU notifier chain.
* Must be called in process context.
*
* Returns 0 on success, %-EEXIST on error.
*/
int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call mutex_lock().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_register(&nh->head, n, false);
mutex_lock(&nh->mutex);
ret = notifier_chain_register(&nh->head, n, false);
mutex_unlock(&nh->mutex);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_register);
/**
* srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from an SRCU notifier chain.
* Must be called from process context.
*
* Returns zero on success or %-ENOENT on failure.
*/
int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call mutex_lock().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_unregister(&nh->head, n);
mutex_lock(&nh->mutex);
ret = notifier_chain_unregister(&nh->head, n);
mutex_unlock(&nh->mutex);
synchronize_srcu(&nh->srcu);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
/**
* srcu_notifier_call_chain - Call functions in an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in a process context, so they are allowed to block.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then srcu_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
unsigned long val, void *v)
{
int ret;
int idx;
idx = srcu_read_lock(&nh->srcu);
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
srcu_read_unlock(&nh->srcu, idx);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);
/**
* srcu_init_notifier_head - Initialize an SRCU notifier head
* @nh: Pointer to head of the srcu notifier chain
*
* Unlike other sorts of notifier heads, SRCU notifier heads require
* dynamic initialization. Be sure to call this routine before
* calling any of the other SRCU notifier routines for this head.
*
* If an SRCU notifier head is deallocated, it must first be cleaned
* up by calling srcu_cleanup_notifier_head(). Otherwise the head's
* per-cpu data (used by the SRCU mechanism) will leak.
*/
void srcu_init_notifier_head(struct srcu_notifier_head *nh)
{
mutex_init(&nh->mutex);
if (init_srcu_struct(&nh->srcu) < 0)
BUG();
nh->head = NULL;
}
EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
static ATOMIC_NOTIFIER_HEAD(die_chain);
int notrace notify_die(enum die_val val, const char *str,
struct pt_regs *regs, long err, int trap, int sig)
{
struct die_args args = {
.regs = regs,
.str = str,
.err = err,
.trapnr = trap,
.signr = sig,
};
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"notify_die called but RCU thinks we're quiescent");
return atomic_notifier_call_chain(&die_chain, val, &args);
}
NOKPROBE_SYMBOL(notify_die);
int register_die_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_register(&die_chain, nb);
}
EXPORT_SYMBOL_GPL(register_die_notifier);
int unregister_die_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_unregister(&die_chain, nb);
}
EXPORT_SYMBOL_GPL(unregister_die_notifier);
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/memory.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* demand-loading started 01.12.91 - seems it is high on the list of
* things wanted, and it should be easy to implement. - Linus
*/
/*
* Ok, demand-loading was easy, shared pages a little bit tricker. Shared
* pages started 02.12.91, seems to work. - Linus.
*
* Tested sharing by executing about 30 /bin/sh: under the old kernel it
* would have taken more than the 6M I have free, but it worked well as
* far as I could see.
*
* Also corrected some "invalidate()"s - I wasn't doing enough of them.
*/
/*
* Real VM (paging to/from disk) started 18.12.91. Much more work and
* thought has to go into this. Oh, well..
* 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
* Found it. Everything seems to work now.
* 20.12.91 - Ok, making the swap-device changeable like the root.
*/
/*
* 05.04.94 - Multi-page memory management added for v1.1.
* Idea by Alex Bligh (alex@cconcepts.co.uk)
*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
*
* Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/task.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/memremap.h>
#include <linux/kmsan.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/pfn_t.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
#include <linux/memory-tiers.h>
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
#include <linux/dax.h>
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/vmalloc.h>
#include <linux/sched/sysctl.h>
#include <trace/events/kmem.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include "pgalloc-track.h"
#include "internal.h"
#include "swap.h"
#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
static vm_fault_t do_fault(struct vm_fault *vmf);
static vm_fault_t do_anonymous_page(struct vm_fault *vmf);
static bool vmf_pte_changed(struct vm_fault *vmf);
/*
* Return true if the original pte was a uffd-wp pte marker (so the pte was
* wr-protected).
*/
static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf)
{
if (!userfaultfd_wp(vmf->vma))
return false;
if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID))
return false;
return pte_marker_uffd_wp(vmf->orig_pte);
}
/*
* Randomize the address space (stacks, mmaps, brk, etc.).
*
* ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
* as ancient (libc5 based) binaries can segfault. )
*/
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
1;
#else
2;
#endif
#ifndef arch_wants_old_prefaulted_pte
static inline bool arch_wants_old_prefaulted_pte(void)
{
/*
* Transitioning a PTE from 'old' to 'young' can be expensive on
* some architectures, even if it's performed in hardware. By
* default, "false" means prefaulted entries will be 'young'.
*/
return false;
}
#endif
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
return 1;
}
__setup("norandmaps", disable_randmaps);
unsigned long zero_pfn __read_mostly;
EXPORT_SYMBOL(zero_pfn);
unsigned long highest_memmap_pfn __read_mostly;
/*
* CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
*/
static int __init init_zero_pfn(void)
{
zero_pfn = page_to_pfn(ZERO_PAGE(0));
return 0;
}
early_initcall(init_zero_pfn);
void mm_trace_rss_stat(struct mm_struct *mm, int member)
{ trace_rss_stat(mm, member);
}
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long addr)
{
pgtable_t token = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free_tlb(tlb, token, addr);
mm_dec_nr_ptes(tlb->mm);
}
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
unsigned long start;
start = addr;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end);
start &= PUD_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PUD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pmd = pmd_offset(pud, start); pud_clear(pud);
pmd_free_tlb(tlb, pmd, start);
mm_dec_nr_pmds(tlb->mm);
}
static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
unsigned long start;
start = addr;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end);
start &= P4D_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= P4D_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pud = pud_offset(p4d, start); p4d_clear(p4d);
pud_free_tlb(tlb, pud, start);
mm_dec_nr_puds(tlb->mm);
}
static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
p4d_t *p4d;
unsigned long next;
unsigned long start;
start = addr;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d))
continue;
free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end);
start &= PGDIR_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PGDIR_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start);
}
/*
* This function frees user-level page tables of a process.
*/
void free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
/*
* The next few lines have given us lots of grief...
*
* Why are we testing PMD* at this top level? Because often
* there will be no work to do at all, and we'd prefer not to
* go all the way down to the bottom just to discover that.
*
* Why all these "- 1"s? Because 0 represents both the bottom
* of the address space and the top of it (using -1 for the
* top wouldn't help much: the masks would do the wrong thing).
* The rule is that addr 0 and floor 0 refer to the bottom of
* the address space, but end 0 and ceiling 0 refer to the top
* Comparisons need to use "end - 1" and "ceiling - 1" (though
* that end 0 case should be mythical).
*
* Wherever addr is brought up or ceiling brought down, we must
* be careful to reject "the opposite 0" before it confuses the
* subsequent tests. But what about where end is brought down
* by PMD_SIZE below? no, end can't go down to 0 there.
*
* Whereas we round start (addr) and ceiling down, by different
* masks at different levels, in order to test whether a table
* now has no other vmas using it, so can be freed, we don't
* bother to round floor or end up - the tests don't need that.
*/
addr &= PMD_MASK;
if (addr < floor) {
addr += PMD_SIZE;
if (!addr)
return;
}
if (ceiling) {
ceiling &= PMD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
end -= PMD_SIZE;
if (addr > end - 1)
return;
/*
* We add page table cache pages with PAGE_SIZE,
* (see pte_free_tlb()), flush the tlb if we need
*/
tlb_change_page_size(tlb, PAGE_SIZE);
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end);
}
void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
struct vm_area_struct *vma, unsigned long floor,
unsigned long ceiling, bool mm_wr_locked)
{
struct unlink_vma_file_batch vb;
do {
unsigned long addr = vma->vm_start;
struct vm_area_struct *next;
/*
* Note: USER_PGTABLES_CEILING may be passed as ceiling and may
* be 0. This will underflow and is okay.
*/
next = mas_find(mas, ceiling - 1);
if (unlikely(xa_is_zero(next))) next = NULL;
/*
* Hide vma from rmap and truncate_pagecache before freeing
* pgtables
*/
if (mm_wr_locked) vma_start_write(vma);
unlink_anon_vmas(vma);
if (is_vm_hugetlb_page(vma)) {
unlink_file_vma(vma);
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
floor, next ? next->vm_start : ceiling);
} else {
unlink_file_vma_batch_init(&vb);
unlink_file_vma_batch_add(&vb, vma);
/*
* Optimization: gather nearby vmas into one call down
*/
while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) {
vma = next;
next = mas_find(mas, ceiling - 1);
if (unlikely(xa_is_zero(next))) next = NULL; if (mm_wr_locked) vma_start_write(vma);
unlink_anon_vmas(vma);
unlink_file_vma_batch_add(&vb, vma);
}
unlink_file_vma_batch_final(&vb);
free_pgd_range(tlb, addr, vma->vm_end,
floor, next ? next->vm_start : ceiling);
}
vma = next;
} while (vma);}
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
{
spinlock_t *ptl = pmd_lock(mm, pmd);
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm);
/*
* Ensure all pte setup (eg. pte page lock and page clearing) are
* visible before the pte is made visible to other CPUs by being
* put into page tables.
*
* The other side of the story is the pointer chasing in the page
* table walking code (when walking the page table without locking;
* ie. most of the time). Fortunately, these data accesses consist
* of a chain of data-dependent loads, meaning most CPUs (alpha
* being the notable exception) will already guarantee loads are
* seen in-order. See the alpha page table accessors for the
* smp_rmb() barriers in page table walking code.
*/
smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
pmd_populate(mm, pmd, *pte);
*pte = NULL;
}
spin_unlock(ptl);
}
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
{ pgtable_t new = pte_alloc_one(mm);
if (!new)
return -ENOMEM;
pmd_install(mm, pmd, &new);
if (new) pte_free(mm, new);
return 0;
}
int __pte_alloc_kernel(pmd_t *pmd)
{
pte_t *new = pte_alloc_one_kernel(&init_mm);
if (!new)
return -ENOMEM;
spin_lock(&init_mm.page_table_lock);
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */
smp_wmb(); /* See comment in pmd_install() */
pmd_populate_kernel(&init_mm, pmd, new);
new = NULL;
}
spin_unlock(&init_mm.page_table_lock);
if (new)
pte_free_kernel(&init_mm, new);
return 0;
}
static inline void init_rss_vec(int *rss)
{
memset(rss, 0, sizeof(int) * NR_MM_COUNTERS);
}
static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
{
int i;
for (i = 0; i < NR_MM_COUNTERS; i++)
if (rss[i]) add_mm_counter(mm, i, rss[i]);
}
/*
* This function is called to print an error when a bad pte
* is found. For example, we might have a PFN-mapped pte in
* a region that doesn't allow it.
*
* The calling function must still handle the error.
*/
static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
{
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
p4d_t *p4d = p4d_offset(pgd, addr);
pud_t *pud = pud_offset(p4d, addr);
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
return;
}
if (nr_unshown) {
pr_alert("BUG: Bad page map: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
index = linear_page_index(vma, addr);
pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n",
current->comm,
(long long)pte_val(pte), (long long)pmd_val(*pmd));
if (page)
dump_page(page, "bad pte");
pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n",
(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n",
vma->vm_file,
vma->vm_ops ? vma->vm_ops->fault : NULL,
vma->vm_file ? vma->vm_file->f_op->mmap : NULL,
mapping ? mapping->a_ops->read_folio : NULL);
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
/*
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
* "Special" mappings do not wish to be associated with a "struct page" (either
* it doesn't exist, or it exists but they don't want to touch it). In this
* case, NULL is returned here. "Normal" mappings do have a struct page.
*
* There are 2 broad cases. Firstly, an architecture may define a pte_special()
* pte bit, in which case this function is trivial. Secondly, an architecture
* may not have a spare pte bit, which requires a more complicated scheme,
* described below.
*
* A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
* special mapping (even if there are underlying and valid "struct pages").
* COWed pages of a VM_PFNMAP are always normal.
*
* The way we recognize COWed pages within VM_PFNMAP mappings is through the
* rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
* set, and the vm_pgoff will point to the first PFN mapped: thus every special
* mapping will always honor the rule
*
* pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
*
* And for normal mappings this is false.
*
* This restricts such mappings to be a linear translation from virtual address
* to pfn. To get around this restriction, we allow arbitrary mappings so long
* as the vma is not a COW mapping; in that case, we know that all ptes are
* special (because none can have been COWed).
*
*
* In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
*
* VM_MIXEDMAP mappings can likewise contain memory with or without "struct
* page" backing, however the difference is that _all_ pages with a struct
* page (that is, those where pfn_valid is true) are refcounted and considered
* normal pages by the VM. The only exception are zeropages, which are
* *never* refcounted.
*
* The disadvantage is that pages are refcounted (which can be slower and
* simply not an option for some PFNMAP users). The advantage is that we
* don't have to follow the strict linearity rule of PFNMAP mappings in
* order to support COWable mappings.
*
*/
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) {
if (likely(!pte_special(pte)))
goto check_pfn;
if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
if (is_zero_pfn(pfn))
return NULL;
if (pte_devmap(pte))
/*
* NOTE: New users of ZONE_DEVICE will not set pte_devmap()
* and will have refcounts incremented on their struct pages
* when they are inserted into PTEs, thus they are safe to
* return here. Legacy ZONE_DEVICE pages that set pte_devmap()
* do not have refcounts. Example of legacy ZONE_DEVICE is
* MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers.
*/
return NULL;
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
if (is_zero_pfn(pfn))
return NULL;
goto out;
} else {
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
if (is_zero_pfn(pfn))
return NULL;
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
out:
VM_WARN_ON_ONCE(is_zero_pfn(pfn));
return pfn_to_page(pfn);
}
struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
struct page *page = vm_normal_page(vma, addr, pte);
if (page) return page_folio(page);
return NULL;
}
#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd)
{
unsigned long pfn = pmd_pfn(pmd);
/* Currently it's only used for huge pfnmaps */
if (unlikely(pmd_special(pmd)))
return NULL;
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
goto out;
} else {
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
if (pmd_devmap(pmd))
return NULL;
if (is_huge_zero_pmd(pmd))
return NULL;
if (unlikely(pfn > highest_memmap_pfn))
return NULL;
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
out:
return pfn_to_page(pfn);
}
struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd)
{
struct page *page = vm_normal_page_pmd(vma, addr, pmd);
if (page)
return page_folio(page);
return NULL;
}
#endif
/**
* restore_exclusive_pte - Restore a device-exclusive entry
* @vma: VMA covering @address
* @folio: the mapped folio
* @page: the mapped folio page
* @address: the virtual address
* @ptep: pte pointer into the locked page table mapping the folio page
* @orig_pte: pte value at @ptep
*
* Restore a device-exclusive non-swap entry to an ordinary present pte.
*
* The folio and the page table must be locked, and MMU notifiers must have
* been called to invalidate any (exclusive) device mappings.
*
* Locking the folio makes sure that anybody who just converted the pte to
* a device-exclusive entry can map it into the device to make forward
* progress without others converting it back until the folio was unlocked.
*
* If the folio lock ever becomes an issue, we can stop relying on the folio
* lock; it might make some scenarios with heavy thrashing less likely to
* make forward progress, but these scenarios might not be valid use cases.
*
* Note that the folio lock does not protect against all cases of concurrent
* page table modifications (e.g., MADV_DONTNEED, mprotect), so device drivers
* must use MMU notifiers to sync against any concurrent changes.
*/
static void restore_exclusive_pte(struct vm_area_struct *vma,
struct folio *folio, struct page *page, unsigned long address,
pte_t *ptep, pte_t orig_pte)
{
pte_t pte;
VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
if (pte_swp_soft_dirty(orig_pte))
pte = pte_mksoft_dirty(pte);
if (pte_swp_uffd_wp(orig_pte))
pte = pte_mkuffd_wp(pte);
if ((vma->vm_flags & VM_WRITE) &&
can_change_pte_writable(vma, address, pte)) {
if (folio_test_dirty(folio))
pte = pte_mkdirty(pte);
pte = pte_mkwrite(pte, vma);
}
set_pte_at(vma->vm_mm, address, ptep, pte);
/*
* No need to invalidate - it was non-present before. However
* secondary CPUs may have mappings that need invalidating.
*/
update_mmu_cache(vma, address, ptep);
}
/*
* Tries to restore an exclusive pte if the page lock can be acquired without
* sleeping.
*/
static int try_restore_exclusive_pte(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep, pte_t orig_pte)
{
struct page *page = pfn_swap_entry_to_page(pte_to_swp_entry(orig_pte));
struct folio *folio = page_folio(page);
if (folio_trylock(folio)) {
restore_exclusive_pte(vma, folio, page, addr, ptep, orig_pte);
folio_unlock(folio);
return 0;
}
return -EBUSY;
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*/
static unsigned long
copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, unsigned long addr, int *rss)
{
unsigned long vm_flags = dst_vma->vm_flags;
pte_t orig_pte = ptep_get(src_pte);
pte_t pte = orig_pte;
struct folio *folio;
struct page *page;
swp_entry_t entry = pte_to_swp_entry(orig_pte);
if (likely(!non_swap_entry(entry))) {
if (swap_duplicate(entry) < 0)
return -EIO;
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
if (list_empty(&dst_mm->mmlist))
list_add(&dst_mm->mmlist,
&src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
/* Mark the swap entry as shared. */
if (pte_swp_exclusive(orig_pte)) {
pte = pte_swp_clear_exclusive(orig_pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
rss[MM_SWAPENTS]++;
} else if (is_migration_entry(entry)) {
folio = pfn_swap_entry_folio(entry);
rss[mm_counter(folio)]++;
if (!is_readable_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
/*
* COW mappings require pages in both parent and child
* to be set to read. A previously exclusive entry is
* now shared.
*/
entry = make_readable_migration_entry(
swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(orig_pte))
pte = pte_swp_mksoft_dirty(pte);
if (pte_swp_uffd_wp(orig_pte))
pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
} else if (is_device_private_entry(entry)) {
page = pfn_swap_entry_to_page(entry);
folio = page_folio(page);
/*
* Update rss count even for unaddressable pages, as
* they should treated just like normal pages in this
* respect.
*
* We will likely want to have some new rss counters
* for unaddressable pages, at some point. But for now
* keep things as they are.
*/
folio_get(folio);
rss[mm_counter(folio)]++;
/* Cannot fail as these pages cannot get pinned. */
folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma);
/*
* We do not preserve soft-dirty information, because so
* far, checkpoint/restore is the only feature that
* requires that. And checkpoint/restore does not work
* when a device driver is involved (you cannot easily
* save and restore device driver state).
*/
if (is_writable_device_private_entry(entry) &&
is_cow_mapping(vm_flags)) {
entry = make_readable_device_private_entry(
swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_uffd_wp(orig_pte))
pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
} else if (is_device_exclusive_entry(entry)) {
/*
* Make device exclusive entries present by restoring the
* original entry then copying as for a present pte. Device
* exclusive entries currently only support private writable
* (ie. COW) mappings.
*/
VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags));
if (try_restore_exclusive_pte(src_vma, addr, src_pte, orig_pte))
return -EBUSY;
return -ENOENT;
} else if (is_pte_marker_entry(entry)) {
pte_marker marker = copy_pte_marker(entry, dst_vma);
if (marker)
set_pte_at(dst_mm, addr, dst_pte,
make_pte_marker(marker));
return 0;
}
if (!userfaultfd_wp(dst_vma))
pte = pte_swp_clear_uffd_wp(pte);
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
/*
* Copy a present and normal page.
*
* NOTE! The usual case is that this isn't required;
* instead, the caller can just increase the page refcount
* and re-use the pte the traditional way.
*
* And if we need a pre-allocated page but don't yet have
* one, return a negative error to let the preallocation
* code know so that it can do so outside the page table
* lock.
*/
static inline int
copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
struct folio **prealloc, struct page *page)
{
struct folio *new_folio;
pte_t pte;
new_folio = *prealloc;
if (!new_folio)
return -EAGAIN;
/*
* We have a prealloc page, all good! Take it
* over and copy the page & arm it.
*/
if (copy_mc_user_highpage(&new_folio->page, page, addr, src_vma))
return -EHWPOISON;
*prealloc = NULL;
__folio_mark_uptodate(new_folio);
folio_add_new_anon_rmap(new_folio, dst_vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(new_folio, dst_vma);
rss[MM_ANONPAGES]++;
/* All done, just insert the new page copy in the child */
pte = mk_pte(&new_folio->page, dst_vma->vm_page_prot);
pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
if (userfaultfd_pte_wp(dst_vma, ptep_get(src_pte)))
/* Uffd-wp needs to be delivered to dest pte as well */
pte = pte_mkuffd_wp(pte);
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
return 0;
}
static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte,
pte_t pte, unsigned long addr, int nr)
{
struct mm_struct *src_mm = src_vma->vm_mm;
/* If it's a COW mapping, write protect it both processes. */
if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) {
wrprotect_ptes(src_mm, addr, src_pte, nr);
pte = pte_wrprotect(pte);
}
/* If it's a shared mapping, mark it clean in the child. */
if (src_vma->vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
if (!userfaultfd_wp(dst_vma))
pte = pte_clear_uffd_wp(pte);
set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr);
}
/*
* Copy one present PTE, trying to batch-process subsequent PTEs that map
* consecutive pages of the same folio by copying them as well.
*
* Returns -EAGAIN if one preallocated page is required to copy the next PTE.
* Otherwise, returns the number of copied PTEs (at least 1).
*/
static inline int
copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr,
int max_nr, int *rss, struct folio **prealloc)
{
struct page *page;
struct folio *folio;
bool any_writable;
fpb_t flags = 0;
int err, nr;
page = vm_normal_page(src_vma, addr, pte);
if (unlikely(!page))
goto copy_pte;
folio = page_folio(page);
/*
* If we likely have to copy, just don't bother with batching. Make
* sure that the common "small folio" case is as fast as possible
* by keeping the batching logic separate.
*/
if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) {
if (src_vma->vm_flags & VM_SHARED)
flags |= FPB_IGNORE_DIRTY;
if (!vma_soft_dirty_enabled(src_vma))
flags |= FPB_IGNORE_SOFT_DIRTY;
nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags,
&any_writable, NULL, NULL);
folio_ref_add(folio, nr);
if (folio_test_anon(folio)) {
if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
nr, dst_vma, src_vma))) {
folio_ref_sub(folio, nr);
return -EAGAIN;
}
rss[MM_ANONPAGES] += nr;
VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
} else {
folio_dup_file_rmap_ptes(folio, page, nr, dst_vma);
rss[mm_counter_file(folio)] += nr;
}
if (any_writable)
pte = pte_mkwrite(pte, src_vma);
__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte,
addr, nr);
return nr;
}
folio_get(folio);
if (folio_test_anon(folio)) {
/*
* If this page may have been pinned by the parent process,
* copy the page immediately for the child so that we'll always
* guarantee the pinned page won't be randomly replaced in the
* future.
*/
if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma))) {
/* Page may be pinned, we have to copy. */
folio_put(folio);
err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
addr, rss, prealloc, page);
return err ? err : 1;
}
rss[MM_ANONPAGES]++;
VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
} else {
folio_dup_file_rmap_pte(folio, page, dst_vma);
rss[mm_counter_file(folio)]++;
}
copy_pte:
__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1);
return 1;
}
static inline struct folio *folio_prealloc(struct mm_struct *src_mm,
struct vm_area_struct *vma, unsigned long addr, bool need_zero)
{
struct folio *new_folio;
if (need_zero)
new_folio = vma_alloc_zeroed_movable_folio(vma, addr);
else
new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (!new_folio)
return NULL;
if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) { folio_put(new_folio);
return NULL;
}
folio_throttle_swaprate(new_folio, GFP_KERNEL);
return new_folio;
}
static int
copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
pmd_t dummy_pmdval;
pte_t ptent;
spinlock_t *src_ptl, *dst_ptl;
int progress, max_nr, ret = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
struct folio *prealloc = NULL;
int nr;
again:
progress = 0;
init_rss_vec(rss);
/*
* copy_pmd_range()'s prior pmd_none_or_clear_bad(src_pmd), and the
* error handling here, assume that exclusive mmap_lock on dst and src
* protects anon from unexpected THP transitions; with shmem and file
* protected by mmap_lock-less collapse skipping areas with anon_vma
* (whereas vma_needs_copy() skips areas without anon_vma). A rework
* can remove such assumptions later, but this is good enough for now.
*/
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte) {
ret = -ENOMEM;
goto out;
}
/*
* We already hold the exclusive mmap_lock, the copy_pte_range() and
* retract_page_tables() are using vma->anon_vma to be exclusive, so
* the PTE page is stable, and there is no need to get pmdval and do
* pmd_same() check.
*/
src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval,
&src_ptl);
if (!src_pte) {
pte_unmap_unlock(dst_pte, dst_ptl);
/* ret == 0 */
goto out;
}
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
orig_src_pte = src_pte;
orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();
do {
nr = 1;
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32) {
progress = 0;
if (need_resched() ||
spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
break;
}
ptent = ptep_get(src_pte);
if (pte_none(ptent)) {
progress++;
continue;
}
if (unlikely(!pte_present(ptent))) {
ret = copy_nonpresent_pte(dst_mm, src_mm,
dst_pte, src_pte,
dst_vma, src_vma,
addr, rss);
if (ret == -EIO) {
entry = pte_to_swp_entry(ptep_get(src_pte));
break;
} else if (ret == -EBUSY) {
break;
} else if (!ret) {
progress += 8;
continue;
}
ptent = ptep_get(src_pte);
VM_WARN_ON_ONCE(!pte_present(ptent));
/*
* Device exclusive entry restored, continue by copying
* the now present pte.
*/
WARN_ON_ONCE(ret != -ENOENT);
}
/* copy_present_ptes() will clear `*prealloc' if consumed */
max_nr = (end - addr) / PAGE_SIZE;
ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte,
ptent, addr, max_nr, rss, &prealloc);
/*
* If we need a pre-allocated page for this pte, drop the
* locks, allocate, and try again.
* If copy failed due to hwpoison in source page, break out.
*/
if (unlikely(ret == -EAGAIN || ret == -EHWPOISON))
break;
if (unlikely(prealloc)) {
/*
* pre-alloc page cannot be reused by next time so as
* to strictly follow mempolicy (e.g., alloc_page_vma()
* will allocate page according to address). This
* could only happen if one pinned pte changed.
*/
folio_put(prealloc);
prealloc = NULL;
}
nr = ret;
progress += 8 * nr;
} while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr,
addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(orig_src_pte, src_ptl);
add_mm_rss_vec(dst_mm, rss);
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
if (ret == -EIO) {
VM_WARN_ON_ONCE(!entry.val);
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
ret = -ENOMEM;
goto out;
}
entry.val = 0;
} else if (ret == -EBUSY || unlikely(ret == -EHWPOISON)) {
goto out;
} else if (ret == -EAGAIN) {
prealloc = folio_prealloc(src_mm, src_vma, addr, false);
if (!prealloc)
return -ENOMEM;
} else if (ret < 0) {
VM_WARN_ON_ONCE(1);
}
/* We've captured and resolved the error. Reset, try again. */
ret = 0;
if (addr != end)
goto again;
out:
if (unlikely(prealloc))
folio_put(prealloc);
return ret;
}
static inline int
copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
if (!dst_pmd)
return -ENOMEM;
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
|| pmd_devmap(*src_pmd)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
addr, dst_vma, src_vma);
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
continue;
/* fall through */
}
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd,
addr, next))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
}
static inline int
copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pud_t *src_pud, *dst_pud;
unsigned long next;
dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
if (!dst_pud)
return -ENOMEM;
src_pud = pud_offset(src_p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
err = copy_huge_pud(dst_mm, src_mm,
dst_pud, src_pud, addr, src_vma);
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
continue;
/* fall through */
}
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud,
addr, next))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
}
static inline int
copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
p4d_t *src_p4d, *dst_p4d;
unsigned long next;
dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
if (!dst_p4d)
return -ENOMEM;
src_p4d = p4d_offset(src_pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(src_p4d))
continue;
if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d,
addr, next))
return -ENOMEM;
} while (dst_p4d++, src_p4d++, addr = next, addr != end);
return 0;
}
/*
* Return true if the vma needs to copy the pgtable during this fork(). Return
* false when we can speed up fork() by allowing lazy page faults later until
* when the child accesses the memory range.
*/
static bool
vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
/*
* Always copy pgtables when dst_vma has uffd-wp enabled even if it's
* file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable
* contains uffd-wp protection information, that's something we can't
* retrieve from page cache, and skip copying will lose those info.
*/
if (userfaultfd_wp(dst_vma))
return true;
if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return true;
if (src_vma->anon_vma)
return true;
/*
* Don't copy ptes where a page fault will fill them correctly. Fork
* becomes much lighter when there are big shared or private readonly
* mappings. The tradeoff is that copy_page_range is more efficient
* than faulting.
*/
return false;
}
int
copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long addr = src_vma->vm_start;
unsigned long end = src_vma->vm_end;
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
struct mmu_notifier_range range;
unsigned long next, pfn = 0;
bool is_cow;
int ret;
if (!vma_needs_copy(dst_vma, src_vma))
return 0;
if (is_vm_hugetlb_page(src_vma))
return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
ret = track_pfn_copy(dst_vma, src_vma, &pfn);
if (ret)
return ret;
}
/*
* We need to invalidate the secondary MMU mappings only when
* there could be a permission downgrade on the ptes of the
* parent mm. And a permission downgrade will only happen if
* is_cow_mapping() returns true.
*/
is_cow = is_cow_mapping(src_vma->vm_flags);
if (is_cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
0, src_mm, addr, end);
mmu_notifier_invalidate_range_start(&range);
/*
* Disabling preemption is not needed for the write side, as
* the read side doesn't spin, but goes to the mmap_lock.
*
* Use the raw variant of the seqcount_t write API to avoid
* lockdep complaining about preemptibility.
*/
vma_assert_write_locked(src_vma);
raw_write_seqcount_begin(&src_mm->write_protect_seq);
}
ret = 0;
dst_pgd = pgd_offset(dst_mm, addr);
src_pgd = pgd_offset(src_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
addr, next))) {
ret = -ENOMEM;
break;
}
} while (dst_pgd++, src_pgd++, addr = next, addr != end);
if (is_cow) {
raw_write_seqcount_end(&src_mm->write_protect_seq);
mmu_notifier_invalidate_range_end(&range);
}
if (ret && unlikely(src_vma->vm_flags & VM_PFNMAP))
untrack_pfn_copy(dst_vma, pfn);
return ret;
}
/* Whether we should zap all COWed (private) pages too */
static inline bool should_zap_cows(struct zap_details *details)
{
/* By default, zap all pages */
if (!details || details->reclaim_pt)
return true;
/* Or, we zap COWed pages only if the caller wants to */
return details->even_cows;
}
/* Decides whether we should zap this folio with the folio pointer specified */
static inline bool should_zap_folio(struct zap_details *details,
struct folio *folio)
{
/* If we can make a decision without *folio.. */
if (should_zap_cows(details))
return true;
/* Otherwise we should only zap non-anon folios */
return !folio_test_anon(folio);
}
static inline bool zap_drop_markers(struct zap_details *details)
{
if (!details)
return false;
return details->zap_flags & ZAP_FLAG_DROP_MARKER;
}
/*
* This function makes sure that we'll replace the none pte with an uffd-wp
* swap special pte marker when necessary. Must be with the pgtable lock held.
*
* Returns true if uffd-wp ptes was installed, false otherwise.
*/
static inline bool
zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte, int nr,
struct zap_details *details, pte_t pteval)
{
bool was_installed = false;
#ifdef CONFIG_PTE_MARKER_UFFD_WP
/* Zap on anonymous always means dropping everything */
if (vma_is_anonymous(vma))
return false;
if (zap_drop_markers(details))
return false;
for (;;) {
/* the PFN in the PTE is irrelevant. */
if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval))
was_installed = true;
if (--nr == 0)
break;
pte++;
addr += PAGE_SIZE;
}
#endif
return was_installed;
}
static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
struct vm_area_struct *vma, struct folio *folio,
struct page *page, pte_t *pte, pte_t ptent, unsigned int nr,
unsigned long addr, struct zap_details *details, int *rss,
bool *force_flush, bool *force_break, bool *any_skipped)
{
struct mm_struct *mm = tlb->mm;
bool delay_rmap = false;
if (!folio_test_anon(folio)) {
ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); if (pte_dirty(ptent)) { folio_mark_dirty(folio);
if (tlb_delay_rmap(tlb)) {
delay_rmap = true;
*force_flush = true;
}
}
if (pte_young(ptent) && likely(vma_has_recency(vma)))
folio_mark_accessed(folio);
rss[mm_counter(folio)] -= nr;
} else {
/* We don't need up-to-date accessed/dirty bits. */
clear_full_ptes(mm, addr, pte, nr, tlb->fullmm);
rss[MM_ANONPAGES] -= nr;
}
/* Checking a single PTE in a batch is sufficient. */
arch_check_zapped_pte(vma, ptent);
tlb_remove_tlb_entries(tlb, pte, nr, addr);
if (unlikely(userfaultfd_pte_wp(vma, ptent)))
*any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte,
nr, details, ptent);
if (!delay_rmap) {
folio_remove_rmap_ptes(folio, page, nr, vma);
if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page);
}
if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) {
*force_flush = true;
*force_break = true;
}
}
/*
* Zap or skip at least one present PTE, trying to batch-process subsequent
* PTEs that map consecutive pages of the same folio.
*
* Returns the number of processed (skipped or zapped) PTEs (at least 1).
*/
static inline int zap_present_ptes(struct mmu_gather *tlb,
struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
unsigned int max_nr, unsigned long addr,
struct zap_details *details, int *rss, bool *force_flush,
bool *force_break, bool *any_skipped)
{
const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
struct mm_struct *mm = tlb->mm;
struct folio *folio;
struct page *page;
int nr;
page = vm_normal_page(vma, addr, ptent);
if (!page) {
/* We don't need up-to-date accessed/dirty bits. */
ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm);
arch_check_zapped_pte(vma, ptent);
tlb_remove_tlb_entry(tlb, pte, addr);
if (userfaultfd_pte_wp(vma, ptent))
*any_skipped = zap_install_uffd_wp_if_needed(vma, addr,
pte, 1, details, ptent);
ksm_might_unmap_zero_page(mm, ptent);
return 1;
}
folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) {
*any_skipped = true;
return 1;
}
/*
* Make sure that the common "small folio" case is as fast as possible
* by keeping the batching logic separate.
*/
if (unlikely(folio_test_large(folio) && max_nr != 1)) {
nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags,
NULL, NULL, NULL);
zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
addr, details, rss, force_flush,
force_break, any_skipped);
return nr;
}
zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr,
details, rss, force_flush, force_break, any_skipped);
return 1;
}
static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
unsigned int max_nr, unsigned long addr,
struct zap_details *details, int *rss, bool *any_skipped)
{
swp_entry_t entry;
int nr = 1;
*any_skipped = true;
entry = pte_to_swp_entry(ptent);
if (is_device_private_entry(entry) ||
is_device_exclusive_entry(entry)) {
struct page *page = pfn_swap_entry_to_page(entry); struct folio *folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio)))
return 1;
/*
* Both device private/exclusive mappings should only
* work with anonymous page so far, so we don't need to
* consider uffd-wp bit when zap. For more information,
* see zap_install_uffd_wp_if_needed().
*/
WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(folio)]--;
folio_remove_rmap_pte(folio, page, vma);
folio_put(folio);
} else if (!non_swap_entry(entry)) {
/* Genuine swap entries, hence a private anon pages */
if (!should_zap_cows(details))
return 1;
nr = swap_pte_batch(pte, max_nr, ptent);
rss[MM_SWAPENTS] -= nr;
free_swap_and_cache_nr(entry, nr);
} else if (is_migration_entry(entry)) {
struct folio *folio = pfn_swap_entry_folio(entry); if (!should_zap_folio(details, folio))
return 1;
rss[mm_counter(folio)]--;
} else if (pte_marker_entry_uffd_wp(entry)) {
/*
* For anon: always drop the marker; for file: only
* drop the marker if explicitly requested.
*/
if (!vma_is_anonymous(vma) && !zap_drop_markers(details))
return 1;
} else if (is_guard_swp_entry(entry)) {
/*
* Ordinary zapping should not remove guard PTE
* markers. Only do so if we should remove PTE markers
* in general.
*/
if (!zap_drop_markers(details))
return 1;
} else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { if (!should_zap_cows(details))
return 1;
} else {
/* We should have covered all the swap entry types */
pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
WARN_ON_ONCE(1);
}
clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm);
*any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
return nr;
}
static inline int do_zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, unsigned long end,
struct zap_details *details, int *rss,
bool *force_flush, bool *force_break,
bool *any_skipped)
{
pte_t ptent = ptep_get(pte);
int max_nr = (end - addr) / PAGE_SIZE;
int nr = 0;
/* Skip all consecutive none ptes */
if (pte_none(ptent)) { for (nr = 1; nr < max_nr; nr++) { ptent = ptep_get(pte + nr);
if (!pte_none(ptent))
break;
}
max_nr -= nr;
if (!max_nr)
return nr;
pte += nr;
addr += nr * PAGE_SIZE;
}
if (pte_present(ptent))
nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr,
details, rss, force_flush, force_break,
any_skipped);
else
nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
details, rss, any_skipped);
return nr;
}
static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
bool force_flush = false, force_break = false;
struct mm_struct *mm = tlb->mm;
int rss[NR_MM_COUNTERS];
spinlock_t *ptl;
pte_t *start_pte;
pte_t *pte;
pmd_t pmdval;
unsigned long start = addr;
bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details);
bool direct_reclaim = true;
int nr;
retry:
tlb_change_page_size(tlb, PAGE_SIZE);
init_rss_vec(rss);
start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return addr;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
do {
bool any_skipped = false;
if (need_resched()) {
direct_reclaim = false;
break;
}
nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss,
&force_flush, &force_break, &any_skipped);
if (any_skipped)
can_reclaim_pt = false;
if (unlikely(force_break)) {
addr += nr * PAGE_SIZE;
direct_reclaim = false;
break;
}
} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
/*
* Fast path: try to hold the pmd lock and unmap the PTE page.
*
* If the pte lock was released midway (retry case), or if the attempt
* to hold the pmd lock failed, then we need to recheck all pte entries
* to ensure they are still none, thereby preventing the pte entries
* from being repopulated by another thread.
*/
if (can_reclaim_pt && direct_reclaim && addr == end)
direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval);
add_mm_rss_vec(mm, rss);
arch_leave_lazy_mmu_mode();
/* Do the actual TLB flush before dropping ptl */
if (force_flush) {
tlb_flush_mmu_tlbonly(tlb);
tlb_flush_rmaps(tlb, vma);
}
pte_unmap_unlock(start_pte, ptl);
/*
* If we forced a TLB flush (either due to running out of
* batch buffers or because we needed to flush dirty TLB
* entries before releasing the ptl), free the batched
* memory too. Come back again if we didn't do everything.
*/
if (force_flush) tlb_flush_mmu(tlb); if (addr != end) {
cond_resched();
force_flush = false;
force_break = false;
goto retry;
}
if (can_reclaim_pt) {
if (direct_reclaim)
free_pte(mm, start, tlb, pmdval);
else
try_to_free_pte(mm, pmd, start, tlb);
}
return addr;
}
static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
__split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) {
addr = next;
continue;
}
/* fall through */
} else if (details && details->single_folio && folio_test_pmd_mappable(details->single_folio) &&
next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
/*
* Take and drop THP pmd lock so that we cannot return
* prematurely, while zap_huge_pmd() has cleared *pmd,
* but not yet decremented compound_mapcount().
*/
spin_unlock(ptl);
}
if (pmd_none(*pmd)) {
addr = next;
continue;
}
addr = zap_pte_range(tlb, vma, pmd, addr, next, details);
if (addr != next)
pmd--;
} while (pmd++, cond_resched(), addr != end);
return addr;
}
static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
if (next - addr != HPAGE_PUD_SIZE) {
mmap_assert_locked(tlb->mm);
split_huge_pud(vma, pud, addr);
} else if (zap_huge_pud(tlb, vma, pud, addr))
goto next;
/* fall through */
}
if (pud_none_or_clear_bad(pud))
continue;
next = zap_pmd_range(tlb, vma, pud, addr, next, details);
next:
cond_resched(); } while (pud++, addr = next, addr != end);
return addr;
}
static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d))
continue;
next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end);
return addr;
}
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pgd_t *pgd;
unsigned long next;
BUG_ON(addr >= end); tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma);
}
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr,
struct zap_details *details, bool mm_wr_locked)
{
unsigned long start = max(vma->vm_start, start_addr);
unsigned long end;
if (start >= vma->vm_end)
return;
end = min(vma->vm_end, end_addr);
if (end <= vma->vm_start)
return;
if (vma->vm_file)
uprobe_munmap(vma, start, end);
if (unlikely(vma->vm_flags & VM_PFNMAP))
untrack_pfn(vma, 0, 0, mm_wr_locked);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
/*
* It is undesirable to test vma->vm_file as it
* should be non-null for valid hugetlb area.
* However, vm_file will be NULL in the error
* cleanup path of mmap_region. When
* hugetlbfs ->mmap method fails,
* mmap_region() nullifies vma->vm_file
* before calling this function to clean up.
* Since no pte has actually been setup, it is
* safe to do nothing in this case.
*/
if (vma->vm_file) { zap_flags_t zap_flags = details ? details->zap_flags : 0;
__unmap_hugepage_range(tlb, vma, start, end,
NULL, zap_flags);
}
} else
unmap_page_range(tlb, vma, start, end, details);
}
}
/**
* unmap_vmas - unmap a range of memory covered by a list of vma's
* @tlb: address of the caller's struct mmu_gather
* @mas: the maple state
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
* @tree_end: The maximum index to check
* @mm_wr_locked: lock flag
*
* Unmap all pages in the vma list.
*
* Only addresses between `start' and `end' will be unmapped.
*
* The VMA list must be sorted in ascending virtual address order.
*
* unmap_vmas() assumes that the caller will flush the whole unmapped address
* range after unmap_vmas() returns. So the only responsibility here is to
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr, unsigned long tree_end,
bool mm_wr_locked)
{
struct mmu_notifier_range range;
struct zap_details details = {
.zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP,
/* Careful - we need to zap private pages too! */
.even_cows = true,
};
mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
do {
unsigned long start = start_addr;
unsigned long end = end_addr;
hugetlb_zap_begin(vma, &start, &end); unmap_single_vma(tlb, vma, start, end, &details,
mm_wr_locked);
hugetlb_zap_end(vma, &details);
vma = mas_find(mas, tree_end - 1);
} while (vma && likely(!xa_is_zero(vma))); mmu_notifier_invalidate_range_end(&range);
}
/**
* zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @address: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of shared cache invalidation
*
* The range must fit into one VMA.
*/
void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
const unsigned long end = address + size;
struct mmu_notifier_range range;
struct mmu_gather tlb;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, end);
hugetlb_zap_begin(vma, &range.start, &range.end);
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
/*
* unmap 'address-end' not 'range.start-range.end' as range
* could have been expanded for hugetlb pmd sharing.
*/
unmap_single_vma(&tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
hugetlb_zap_end(vma, details);
}
/**
* zap_vma_ptes - remove ptes mapping the vma
* @vma: vm_area_struct holding ptes to be zapped
* @address: starting address of pages to zap
* @size: number of bytes to zap
*
* This function only unmaps ptes assigned to VM_PFNMAP vmas.
*
* The entire address range must be fully contained within the vma.
*
*/
void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size)
{
if (!range_in_vma(vma, address, address + size) ||
!(vma->vm_flags & VM_PFNMAP))
return;
zap_page_range_single(vma, address, size, NULL);
}
EXPORT_SYMBOL_GPL(zap_vma_ptes);
static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return NULL;
pud = pud_alloc(mm, p4d, addr);
if (!pud)
return NULL;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return NULL;
VM_BUG_ON(pmd_trans_huge(*pmd));
return pmd;
}
pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
pmd_t *pmd = walk_to_pmd(mm, addr);
if (!pmd)
return NULL;
return pte_alloc_map_lock(mm, pmd, addr, ptl);
}
static bool vm_mixed_zeropage_allowed(struct vm_area_struct *vma)
{
VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP);
/*
* Whoever wants to forbid the zeropage after some zeropages
* might already have been mapped has to scan the page tables and
* bail out on any zeropages. Zeropages in COW mappings can
* be unshared using FAULT_FLAG_UNSHARE faults.
*/
if (mm_forbids_zeropage(vma->vm_mm))
return false;
/* zeropages in COW mappings are common and unproblematic. */
if (is_cow_mapping(vma->vm_flags))
return true;
/* Mappings that do not allow for writable PTEs are unproblematic. */
if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE)))
return true;
/*
* Why not allow any VMA that has vm_ops->pfn_mkwrite? GUP could
* find the shared zeropage and longterm-pin it, which would
* be problematic as soon as the zeropage gets replaced by a different
* page due to vma->vm_ops->pfn_mkwrite, because what's mapped would
* now differ to what GUP looked up. FSDAX is incompatible to
* FOLL_LONGTERM and VM_IO is incompatible to GUP completely (see
* check_vma_flags).
*/
return vma->vm_ops && vma->vm_ops->pfn_mkwrite &&
(vma_is_fsdax(vma) || vma->vm_flags & VM_IO);
}
static int validate_page_before_insert(struct vm_area_struct *vma,
struct page *page)
{
struct folio *folio = page_folio(page);
if (!folio_ref_count(folio))
return -EINVAL;
if (unlikely(is_zero_folio(folio))) {
if (!vm_mixed_zeropage_allowed(vma))
return -EINVAL;
return 0;
}
if (folio_test_anon(folio) || folio_test_slab(folio) ||
page_has_type(page))
return -EINVAL;
flush_dcache_folio(folio);
return 0;
}
static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, struct page *page,
pgprot_t prot, bool mkwrite)
{
struct folio *folio = page_folio(page);
pte_t pteval = ptep_get(pte);
if (!pte_none(pteval)) {
if (!mkwrite)
return -EBUSY;
/* see insert_pfn(). */
if (pte_pfn(pteval) != page_to_pfn(page)) {
WARN_ON_ONCE(!is_zero_pfn(pte_pfn(pteval)));
return -EFAULT;
}
pteval = maybe_mkwrite(pteval, vma);
pteval = pte_mkyoung(pteval);
if (ptep_set_access_flags(vma, addr, pte, pteval, 1))
update_mmu_cache(vma, addr, pte);
return 0;
}
/* Ok, finally just insert the thing.. */
pteval = mk_pte(page, prot);
if (unlikely(is_zero_folio(folio))) {
pteval = pte_mkspecial(pteval);
} else {
folio_get(folio);
pteval = mk_pte(page, prot);
if (mkwrite) {
pteval = pte_mkyoung(pteval);
pteval = maybe_mkwrite(pte_mkdirty(pteval), vma);
}
inc_mm_counter(vma->vm_mm, mm_counter_file(folio));
folio_add_file_rmap_pte(folio, page, vma);
}
set_pte_at(vma->vm_mm, addr, pte, pteval);
return 0;
}
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page, pgprot_t prot, bool mkwrite)
{
int retval;
pte_t *pte;
spinlock_t *ptl;
retval = validate_page_before_insert(vma, page);
if (retval)
goto out;
retval = -ENOMEM;
pte = get_locked_pte(vma->vm_mm, addr, &ptl);
if (!pte)
goto out;
retval = insert_page_into_pte_locked(vma, pte, addr, page, prot,
mkwrite);
pte_unmap_unlock(pte, ptl);
out:
return retval;
}
static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, struct page *page, pgprot_t prot)
{
int err;
err = validate_page_before_insert(vma, page);
if (err)
return err;
return insert_page_into_pte_locked(vma, pte, addr, page, prot, false);
}
/* insert_pages() amortizes the cost of spinlock operations
* when inserting pages in a loop.
*/
static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num, pgprot_t prot)
{
pmd_t *pmd = NULL;
pte_t *start_pte, *pte;
spinlock_t *pte_lock;
struct mm_struct *const mm = vma->vm_mm;
unsigned long curr_page_idx = 0;
unsigned long remaining_pages_total = *num;
unsigned long pages_to_write_in_pmd;
int ret;
more:
ret = -EFAULT;
pmd = walk_to_pmd(mm, addr);
if (!pmd)
goto out;
pages_to_write_in_pmd = min_t(unsigned long,
remaining_pages_total, PTRS_PER_PTE - pte_index(addr));
/* Allocate the PTE if necessary; takes PMD lock once only. */
ret = -ENOMEM;
if (pte_alloc(mm, pmd))
goto out;
while (pages_to_write_in_pmd) {
int pte_idx = 0;
const int batch_size = min_t(int, pages_to_write_in_pmd, 8);
start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock);
if (!start_pte) {
ret = -EFAULT;
goto out;
}
for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) {
int err = insert_page_in_batch_locked(vma, pte,
addr, pages[curr_page_idx], prot);
if (unlikely(err)) {
pte_unmap_unlock(start_pte, pte_lock);
ret = err;
remaining_pages_total -= pte_idx;
goto out;
}
addr += PAGE_SIZE;
++curr_page_idx;
}
pte_unmap_unlock(start_pte, pte_lock);
pages_to_write_in_pmd -= batch_size;
remaining_pages_total -= batch_size;
}
if (remaining_pages_total)
goto more;
ret = 0;
out:
*num = remaining_pages_total;
return ret;
}
/**
* vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
* @vma: user vma to map to
* @addr: target start user address of these pages
* @pages: source kernel pages
* @num: in: number of pages to map. out: number of pages that were *not*
* mapped. (0 means all pages were successfully mapped).
*
* Preferred over vm_insert_page() when inserting multiple pages.
*
* In case of error, we may have mapped a subset of the provided
* pages. It is the caller's responsibility to account for this case.
*
* The same restrictions apply as in vm_insert_page().
*/
int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num)
{
const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
if (addr < vma->vm_start || end_addr >= vma->vm_end)
return -EFAULT;
if (!(vma->vm_flags & VM_MIXEDMAP)) {
BUG_ON(mmap_read_trylock(vma->vm_mm));
BUG_ON(vma->vm_flags & VM_PFNMAP);
vm_flags_set(vma, VM_MIXEDMAP);
}
/* Defer page refcount checking till we're about to map that page. */
return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_pages);
/**
* vm_insert_page - insert single page into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @page: source kernel page
*
* This allows drivers to insert individual pages they've allocated
* into a user vma. The zeropage is supported in some VMAs,
* see vm_mixed_zeropage_allowed().
*
* The page has to be a nice clean _individual_ kernel allocation.
* If you allocate a compound page, you need to have marked it as
* such (__GFP_COMP), or manually just split the page up yourself
* (see split_page()).
*
* NOTE! Traditionally this was done with "remap_pfn_range()" which
* took an arbitrary page protection parameter. This doesn't allow
* that. Your vma protection will have to be set up correctly, which
* means that if you want a shared writable mapping, you'd better
* ask for a shared writable mapping!
*
* The page does not need to be reserved.
*
* Usually this function is called from f_op->mmap() handler
* under mm->mmap_lock write-lock, so it can change vma->vm_flags.
* Caller must set VM_MIXEDMAP on vma if it wants to call this
* function from other places, for example from page-fault handler.
*
* Return: %0 on success, negative error code otherwise.
*/
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
{
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
if (!(vma->vm_flags & VM_MIXEDMAP)) {
BUG_ON(mmap_read_trylock(vma->vm_mm));
BUG_ON(vma->vm_flags & VM_PFNMAP);
vm_flags_set(vma, VM_MIXEDMAP);
}
return insert_page(vma, addr, page, vma->vm_page_prot, false);
}
EXPORT_SYMBOL(vm_insert_page);
/*
* __vm_map_pages - maps range of kernel pages into user vma
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
* @offset: user's requested vm_pgoff
*
* This allows drivers to map range of kernel pages into a user vma.
* The zeropage is supported in some VMAs, see
* vm_mixed_zeropage_allowed().
*
* Return: 0 on success and error code otherwise.
*/
static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num, unsigned long offset)
{
unsigned long count = vma_pages(vma);
unsigned long uaddr = vma->vm_start;
int ret, i;
/* Fail if the user requested offset is beyond the end of the object */
if (offset >= num)
return -ENXIO;
/* Fail if the user requested size exceeds available object size */
if (count > num - offset)
return -ENXIO;
for (i = 0; i < count; i++) {
ret = vm_insert_page(vma, uaddr, pages[offset + i]);
if (ret < 0)
return ret;
uaddr += PAGE_SIZE;
}
return 0;
}
/**
* vm_map_pages - maps range of kernel pages starts with non zero offset
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
*
* Maps an object consisting of @num pages, catering for the user's
* requested vm_pgoff
*
* If we fail to insert any page into the vma, the function will return
* immediately leaving any previously inserted pages present. Callers
* from the mmap handler may immediately return the error as their caller
* will destroy the vma, removing any successfully inserted pages. Other
* callers should make their own arrangements for calling unmap_region().
*
* Context: Process context. Called by mmap handlers.
* Return: 0 on success and error code otherwise.
*/
int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num)
{
return __vm_map_pages(vma, pages, num, vma->vm_pgoff);
}
EXPORT_SYMBOL(vm_map_pages);
/**
* vm_map_pages_zero - map range of kernel pages starts with zero offset
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
*
* Similar to vm_map_pages(), except that it explicitly sets the offset
* to 0. This function is intended for the drivers that did not consider
* vm_pgoff.
*
* Context: Process context. Called by mmap handlers.
* Return: 0 on success and error code otherwise.
*/
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
unsigned long num)
{
return __vm_map_pages(vma, pages, num, 0);
}
EXPORT_SYMBOL(vm_map_pages_zero);
static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn, pgprot_t prot, bool mkwrite)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, entry;
spinlock_t *ptl;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
return VM_FAULT_OOM;
entry = ptep_get(pte);
if (!pte_none(entry)) {
if (mkwrite) {
/*
* For read faults on private mappings the PFN passed
* in may not match the PFN we have mapped if the
* mapped PFN is a writeable COW page. In the mkwrite
* case we are creating a writable PTE for a shared
* mapping and we expect the PFNs to match. If they
* don't match, we are likely racing with block
* allocation and mapping invalidation so just skip the
* update.
*/
if (pte_pfn(entry) != pfn_t_to_pfn(pfn)) {
WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry)));
goto out_unlock;
}
entry = pte_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (ptep_set_access_flags(vma, addr, pte, entry, 1))
update_mmu_cache(vma, addr, pte);
}
goto out_unlock;
}
/* Ok, finally just insert the thing.. */
if (pfn_t_devmap(pfn))
entry = pte_mkdevmap(pfn_t_pte(pfn, prot));
else
entry = pte_mkspecial(pfn_t_pte(pfn, prot));
if (mkwrite) {
entry = pte_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
}
set_pte_at(mm, addr, pte, entry);
update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
out_unlock:
pte_unmap_unlock(pte, ptl);
return VM_FAULT_NOPAGE;
}
/**
* vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
* @pgprot: pgprot flags for the inserted page
*
* This is exactly like vmf_insert_pfn(), except that it allows drivers
* to override pgprot on a per-page basis.
*
* This only makes sense for IO mappings, and it makes no sense for
* COW mappings. In general, using multiple vmas is preferable;
* vmf_insert_pfn_prot should only be used if using multiple VMAs is
* impractical.
*
* pgprot typically only differs from @vma->vm_page_prot when drivers set
* caching- and encryption bits different than those of @vma->vm_page_prot,
* because the caching- or encryption mode may not be known at mmap() time.
*
* This is ok as long as @vma->vm_page_prot is not used by the core vm
* to set caching and encryption bits for those vmas (except for COW pages).
* This is ensured by core vm only modifying these page table entries using
* functions that don't touch caching- or encryption bits, using pte_modify()
* if needed. (See for example mprotect()).
*
* Also when new page-table entries are created, this is only done using the
* fault() callback, and never using the value of vma->vm_page_prot,
* except for page-table entries that point to anonymous pages as the result
* of COW.
*
* Context: Process context. May allocate using %GFP_KERNEL.
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, pgprot_t pgprot)
{
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
* consistency in testing and feature parity among all, so we should
* try to keep these invariants in place for everybody.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (!pfn_modify_allowed(pfn, pgprot))
return VM_FAULT_SIGBUS;
track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
false);
}
EXPORT_SYMBOL(vmf_insert_pfn_prot);
/**
* vmf_insert_pfn - insert single pfn into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
*
* Similar to vm_insert_page, this allows drivers to insert individual pages
* they've allocated into a user vma. Same comments apply.
*
* This function should only be called from a vm_ops->fault handler, and
* in that case the handler should return the result of this function.
*
* vma cannot be a COW mapping.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
* Context: Process context. May allocate using %GFP_KERNEL.
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
}
EXPORT_SYMBOL(vmf_insert_pfn);
static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite)
{
if (unlikely(is_zero_pfn(pfn_t_to_pfn(pfn))) &&
(mkwrite || !vm_mixed_zeropage_allowed(vma)))
return false;
/* these checks mirror the abort conditions in vm_normal_page */
if (vma->vm_flags & VM_MIXEDMAP)
return true;
if (pfn_t_devmap(pfn))
return true;
if (pfn_t_special(pfn))
return true;
if (is_zero_pfn(pfn_t_to_pfn(pfn)))
return true;
return false;
}
static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn, bool mkwrite)
{
pgprot_t pgprot = vma->vm_page_prot;
int err;
if (!vm_mixed_ok(vma, pfn, mkwrite))
return VM_FAULT_SIGBUS;
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
track_pfn_insert(vma, &pgprot, pfn);
if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
return VM_FAULT_SIGBUS;
/*
* If we don't have pte special, then we have to use the pfn_valid()
* based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
* refcount the page if pfn_valid is true (hence insert_page rather
* than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
* without pte special, it would there be refcounted as a normal page.
*/
if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) &&
!pfn_t_devmap(pfn) && pfn_t_valid(pfn)) {
struct page *page;
/*
* At this point we are committed to insert_page()
* regardless of whether the caller specified flags that
* result in pfn_t_has_page() == false.
*/
page = pfn_to_page(pfn_t_to_pfn(pfn));
err = insert_page(vma, addr, page, pgprot, mkwrite);
} else {
return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
}
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err < 0 && err != -EBUSY)
return VM_FAULT_SIGBUS;
return VM_FAULT_NOPAGE;
}
vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
bool write)
{
pgprot_t pgprot = vmf->vma->vm_page_prot;
unsigned long addr = vmf->address;
int err;
if (addr < vmf->vma->vm_start || addr >= vmf->vma->vm_end)
return VM_FAULT_SIGBUS;
err = insert_page(vmf->vma, addr, page, pgprot, write);
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err < 0 && err != -EBUSY)
return VM_FAULT_SIGBUS;
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_page_mkwrite);
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn)
{
return __vm_insert_mixed(vma, addr, pfn, false);
}
EXPORT_SYMBOL(vmf_insert_mixed);
/*
* If the insertion of PTE failed because someone else already added a
* different entry in the mean time, we treat that as success as we assume
* the same entry was actually inserted.
*/
vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn)
{
return __vm_insert_mixed(vma, addr, pfn, true);
}
/*
* maps a range of physical memory into the requested pages. the old
* mappings are removed. any references to nonexistent pages results
* in null mappings (currently treated as "copy-on-access")
*/
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pte_t *pte, *mapped_pte;
spinlock_t *ptl;
int err = 0;
mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
arch_enter_lazy_mmu_mode();
do {
BUG_ON(!pte_none(ptep_get(pte)));
if (!pfn_modify_allowed(pfn, prot)) {
err = -EACCES;
break;
}
set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(mapped_pte, ptl);
return err;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
int err;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
VM_BUG_ON(pmd_trans_huge(*pmd));
do {
next = pmd_addr_end(addr, end);
err = remap_pte_range(mm, pmd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
int err;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
err = remap_pmd_range(mm, pud, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
p4d_t *p4d;
unsigned long next;
int err;
pfn -= addr >> PAGE_SHIFT;
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
err = remap_pud_range(mm, p4d, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (p4d++, addr = next, addr != end);
return 0;
}
static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
int err;
if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
return -EINVAL;
/*
* Physically remapped pages are special. Tell the
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
* VM_PFNMAP tells the core MM that the base pages are just
* raw PFN mappings, and do not have a "struct page" associated
* with them.
* VM_DONTEXPAND
* Disable vma merging and expanding with mremap().
* VM_DONTDUMP
* Omit vma from core dump, even when VM_IO turned off.
*
* There's a horrible special case to handle copy-on-write
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
* See vm_normal_page() for details.
*/
if (is_cow_mapping(vma->vm_flags)) {
if (addr != vma->vm_start || end != vma->vm_end)
return -EINVAL;
vma->vm_pgoff = pfn;
}
vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
do {
next = pgd_addr_end(addr, end);
err = remap_p4d_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
return 0;
}
/*
* Variant of remap_pfn_range that does not call track_pfn_remap. The caller
* must have pre-validated the caching bits of the pgprot_t.
*/
int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
int error = remap_pfn_range_internal(vma, addr, pfn, size, prot);
if (!error)
return 0;
/*
* A partial pfn range mapping is dangerous: it does not
* maintain page reference counts, and callers may free
* pages due to the error. So zap it early.
*/
zap_page_range_single(vma, addr, size, NULL);
return error;
}
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
* @addr: target page aligned user address to start at
* @pfn: page frame number of kernel physical memory address
* @size: size of mapping area
* @prot: page protection flags for this mapping
*
* Note: this is only safe if the mm semaphore is held when called.
*
* Return: %0 on success, negative error code otherwise.
*/
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
int err;
err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
if (err)
return -EINVAL;
err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
if (err)
untrack_pfn(vma, pfn, PAGE_ALIGN(size), true);
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
/**
* vm_iomap_memory - remap memory to userspace
* @vma: user vma to map to
* @start: start of the physical memory to be mapped
* @len: size of area
*
* This is a simplified io_remap_pfn_range() for common driver use. The
* driver just needs to give us the physical memory range to be mapped,
* we'll figure out the rest from the vma information.
*
* NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
* whatever write-combining details or similar.
*
* Return: %0 on success, negative error code otherwise.
*/
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
unsigned long vm_len, pfn, pages;
/* Check that the physical memory area passed in looks valid */
if (start + len < start)
return -EINVAL;
/*
* You *really* shouldn't map things that aren't page-aligned,
* but we've historically allowed it because IO memory might
* just have smaller alignment.
*/
len += start & ~PAGE_MASK;
pfn = start >> PAGE_SHIFT;
pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
if (pfn + pages < pfn)
return -EINVAL;
/* We start the mapping 'vm_pgoff' pages into the area */
if (vma->vm_pgoff > pages)
return -EINVAL;
pfn += vma->vm_pgoff;
pages -= vma->vm_pgoff;
/* Can we fit all of the mapping? */
vm_len = vma->vm_end - vma->vm_start;
if (vm_len >> PAGE_SHIFT > pages)
return -EINVAL;
/* Ok, let it rip */
return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_iomap_memory);
static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pte_t *pte, *mapped_pte;
int err = 0;
spinlock_t *ptl;
if (create) {
mapped_pte = pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte)
return -ENOMEM;
} else {
mapped_pte = pte = (mm == &init_mm) ?
pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte)
return -EINVAL;
}
arch_enter_lazy_mmu_mode();
if (fn) {
do {
if (create || !pte_none(ptep_get(pte))) {
err = fn(pte, addr, data);
if (err)
break;
}
} while (pte++, addr += PAGE_SIZE, addr != end);
}
*mask |= PGTBL_PTE_MODIFIED;
arch_leave_lazy_mmu_mode();
if (mm != &init_mm) pte_unmap_unlock(mapped_pte, ptl);
return err;
}
static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
int err = 0;
BUG_ON(pud_leaf(*pud));
if (create) {
pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd)
return -ENOMEM;
} else {
pmd = pmd_offset(pud, addr);
}
do {
next = pmd_addr_end(addr, end);
if (pmd_none(*pmd) && !create)
continue;
if (WARN_ON_ONCE(pmd_leaf(*pmd)))
return -EINVAL;
if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
if (!create)
continue;
pmd_clear_bad(pmd);
}
err = apply_to_pte_range(mm, pmd, addr, next,
fn, data, create, mask);
if (err)
break;
} while (pmd++, addr = next, addr != end);
return err;
}
static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
int err = 0;
if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud)
return -ENOMEM;
} else {
pud = pud_offset(p4d, addr);
}
do {
next = pud_addr_end(addr, end);
if (pud_none(*pud) && !create)
continue;
if (WARN_ON_ONCE(pud_leaf(*pud)))
return -EINVAL;
if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { if (!create)
continue;
pud_clear_bad(pud);
}
err = apply_to_pmd_range(mm, pud, addr, next,
fn, data, create, mask);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
int err = 0;
if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d)
return -ENOMEM;
} else {
p4d = p4d_offset(pgd, addr);
}
do {
next = p4d_addr_end(addr, end);
if (p4d_none(*p4d) && !create)
continue;
if (WARN_ON_ONCE(p4d_leaf(*p4d)))
return -EINVAL;
if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
if (!create)
continue;
p4d_clear_bad(p4d);
}
err = apply_to_pud_range(mm, p4d, addr, next,
fn, data, create, mask);
if (err)
break;
} while (p4d++, addr = next, addr != end);
return err;
}
static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn,
void *data, bool create)
{
pgd_t *pgd;
unsigned long start = addr, next;
unsigned long end = addr + size;
pgtbl_mod_mask mask = 0;
int err = 0;
if (WARN_ON(addr >= end))
return -EINVAL;
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none(*pgd) && !create)
continue;
if (WARN_ON_ONCE(pgd_leaf(*pgd))) {
err = -EINVAL;
break;
}
if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create)
continue;
pgd_clear_bad(pgd);
}
err = apply_to_p4d_range(mm, pgd, addr, next,
fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, start + size);
return err;
}
/*
* Scan a region of virtual memory, filling in page tables as necessary
* and calling a provided function on each leaf page table.
*/
int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn, void *data)
{
return __apply_to_page_range(mm, addr, size, fn, data, true);
}
EXPORT_SYMBOL_GPL(apply_to_page_range);
/*
* Scan a region of virtual memory, calling a provided function on
* each leaf page table where it exists.
*
* Unlike apply_to_page_range, this does _not_ fill in page tables
* where they are absent.
*/
int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn, void *data)
{
return __apply_to_page_range(mm, addr, size, fn, data, false);
}
/*
* handle_pte_fault chooses page fault handler according to an entry which was
* read non-atomically. Before making any commitment, on those architectures
* or configurations (e.g. i386 with PAE) which might give a mix of unmatched
* parts, do_swap_page must check under lock before unmapping the pte and
* proceeding (but do_wp_page is only called after already making such a check;
* and do_anonymous_page can safely check later on).
*/
static inline int pte_unmap_same(struct vm_fault *vmf)
{
int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION)
if (sizeof(pte_t) > sizeof(unsigned long)) {
spin_lock(vmf->ptl);
same = pte_same(ptep_get(vmf->pte), vmf->orig_pte);
spin_unlock(vmf->ptl);
}
#endif
pte_unmap(vmf->pte);
vmf->pte = NULL;
return same;
}
/*
* Return:
* 0: copied succeeded
* -EHWPOISON: copy failed due to hwpoison in source page
* -EAGAIN: copied failed (some other reason)
*/
static inline int __wp_page_copy_user(struct page *dst, struct page *src,
struct vm_fault *vmf)
{
int ret;
void *kaddr;
void __user *uaddr;
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = vmf->address;
if (likely(src)) {
if (copy_mc_user_highpage(dst, src, addr, vma))
return -EHWPOISON;
return 0;
}
/*
* If the source page was a PFN mapping, we don't have
* a "struct page" for it. We do a best-effort copy by
* just copying from the original user address. If that
* fails, we just zero-fill it. Live with it.
*/
kaddr = kmap_local_page(dst);
pagefault_disable();
uaddr = (void __user *)(addr & PAGE_MASK);
/*
* On architectures with software "accessed" bits, we would
* take a double page fault, so mark it accessed here.
*/
vmf->pte = NULL;
if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) {
pte_t entry;
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
/*
* Other thread has already handled the fault
* and update local tlb only
*/
if (vmf->pte)
update_mmu_tlb(vma, addr, vmf->pte);
ret = -EAGAIN;
goto pte_unlock;
}
entry = pte_mkyoung(vmf->orig_pte);
if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1);
}
/*
* This really shouldn't fail, because the page is there
* in the page tables. But it might just be unreadable,
* in which case we just give up and fill the result with
* zeroes.
*/
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (vmf->pte)
goto warn;
/* Re-validate under PTL if the page is still mapped */
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
/* The PTE changed under us, update local tlb */
if (vmf->pte)
update_mmu_tlb(vma, addr, vmf->pte);
ret = -EAGAIN;
goto pte_unlock;
}
/*
* The same page can be mapped back since last copy attempt.
* Try to copy again under PTL.
*/
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
/*
* Give a warn in case there can be some obscure
* use-case
*/
warn:
WARN_ON_ONCE(1);
clear_page(kaddr);
}
}
ret = 0;
pte_unlock:
if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl);
pagefault_enable();
kunmap_local(kaddr);
flush_dcache_page(dst);
return ret;
}
static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
{
struct file *vm_file = vma->vm_file;
if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO;
/*
* Special mappings (e.g. VDSO) do not have any file so fake
* a default GFP_KERNEL for them.
*/
return GFP_KERNEL;
}
/*
* Notify the address space that the page is about to become writable so that
* it can prohibit this or wait for the page to get into an appropriate state.
*
* We do this without the lock held, so that it can sleep if it needs to.
*/
static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio)
{
vm_fault_t ret;
unsigned int old_flags = vmf->flags;
vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
if (vmf->vma->vm_file &&
IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host))
return VM_FAULT_SIGBUS;
ret = vmf->vma->vm_ops->page_mkwrite(vmf);
/* Restore original flags so that caller is not surprised */
vmf->flags = old_flags;
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
return ret;
if (unlikely(!(ret & VM_FAULT_LOCKED))) {
folio_lock(folio);
if (!folio->mapping) {
folio_unlock(folio);
return 0; /* retry */
}
ret |= VM_FAULT_LOCKED;
} else
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
return ret;
}
/*
* Handle dirtying of a page in shared file mapping on a write fault.
*
* The function expects the page to be locked and unlocks it.
*/
static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping;
struct folio *folio = page_folio(vmf->page);
bool dirtied;
bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
dirtied = folio_mark_dirty(folio);
VM_BUG_ON_FOLIO(folio_test_anon(folio), folio);
/*
* Take a local copy of the address_space - folio.mapping may be zeroed
* by truncate after folio_unlock(). The address_space itself remains
* pinned by vma->vm_file's reference. We rely on folio_unlock()'s
* release semantics to prevent the compiler from undoing this copying.
*/
mapping = folio_raw_mapping(folio);
folio_unlock(folio);
if (!page_mkwrite) file_update_time(vma->vm_file);
/*
* Throttle page dirtying rate down to writeback speed.
*
* mapping may be NULL here because some device drivers do not
* set page.mapping but still dirty their pages
*
* Drop the mmap_lock before waiting on IO, if we can. The file
* is pinning the mapping, as per above.
*/
if ((dirtied || page_mkwrite) && mapping) {
struct file *fpin;
fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin);
return VM_FAULT_COMPLETED;
}
}
return 0;
}
/*
* Handle write page faults for pages that can be reused in the current vma
*
* This can happen either due to the mapping being with the VM_SHARED flag,
* or due to us being the last reference standing to the page. In either
* case, all we need to do here is to mark the page as writable and update
* any related book-keeping.
*/
static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio)
__releases(vmf->ptl)
{
struct vm_area_struct *vma = vmf->vma;
pte_t entry;
VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
VM_WARN_ON(is_zero_pfn(pte_pfn(vmf->orig_pte)));
if (folio) {
VM_BUG_ON(folio_test_anon(folio) &&
!PageAnonExclusive(vmf->page));
/*
* Clear the folio's cpupid information as the existing
* information potentially belongs to a now completely
* unrelated process.
*/
folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1);
}
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = pte_mkyoung(vmf->orig_pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
pte_unmap_unlock(vmf->pte, vmf->ptl);
count_vm_event(PGREUSE);
}
/*
* We could add a bitflag somewhere, but for now, we know that all
* vm_ops that have a ->map_pages have been audited and don't need
* the mmap_lock to be held.
*/
static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK))
return 0;
vma_end_read(vma);
return VM_FAULT_RETRY;
}
/**
* __vmf_anon_prepare - Prepare to handle an anonymous fault.
* @vmf: The vm_fault descriptor passed from the fault handler.
*
* When preparing to insert an anonymous page into a VMA from a
* fault handler, call this function rather than anon_vma_prepare().
* If this vma does not already have an associated anon_vma and we are
* only protected by the per-VMA lock, the caller must retry with the
* mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to
* determine if this VMA can share its anon_vma, and that's not safe to
* do with only the per-VMA lock held for this VMA.
*
* Return: 0 if fault handling can proceed. Any other value should be
* returned to the caller.
*/
vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret = 0;
if (likely(vma->anon_vma))
return 0;
if (vmf->flags & FAULT_FLAG_VMA_LOCK) { if (!mmap_read_trylock(vma->vm_mm))
return VM_FAULT_RETRY;
}
if (__anon_vma_prepare(vma))
ret = VM_FAULT_OOM;
if (vmf->flags & FAULT_FLAG_VMA_LOCK) mmap_read_unlock(vma->vm_mm);
return ret;
}
/*
* Handle the case of a page which we actually need to copy to a new page,
* either due to COW or unsharing.
*
* Called with mmap_lock locked and the old page referenced, but
* without the ptl held.
*
* High level logic flow:
*
* - Allocate a page, copy the content of the old page to the new one.
* - Handle book keeping and accounting - cgroups, mmu-notifiers, etc.
* - Take the PTL. If the pte changed, bail out and release the allocated page
* - If the pte is still the way we remember it, update the page table and all
* relevant references. This includes dropping the reference the page-table
* held to the old page, as well as updating the rmap.
* - In any case, unlock the PTL and drop the reference we took to the old page.
*/
static vm_fault_t wp_page_copy(struct vm_fault *vmf)
{
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
struct folio *old_folio = NULL;
struct folio *new_folio = NULL;
pte_t entry;
int page_copied = 0;
struct mmu_notifier_range range;
vm_fault_t ret;
bool pfn_is_zero;
delayacct_wpcopy_start();
if (vmf->page) old_folio = page_folio(vmf->page); ret = vmf_anon_prepare(vmf); if (unlikely(ret))
goto out;
pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte));
new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero);
if (!new_folio)
goto oom;
if (!pfn_is_zero) {
int err;
err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); if (err) {
/*
* COW failed, if the fault was solved by other,
* it's fine. If not, userspace would re-fault on
* the same address and we will handle the fault
* from the second attempt.
* The -EHWPOISON case will not be retried.
*/
folio_put(new_folio); if (old_folio) folio_put(old_folio);
delayacct_wpcopy_end();
return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
}
kmsan_copy_page_meta(&new_folio->page, vmf->page);
}
__folio_mark_uptodate(new_folio);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
/*
* Re-check the pte - we dropped the lock
*/
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
if (old_folio) {
if (!folio_test_anon(old_folio)) { dec_mm_counter(mm, mm_counter_file(old_folio));
inc_mm_counter(mm, MM_ANONPAGES);
}
} else {
ksm_might_unmap_zero_page(mm, vmf->orig_pte);
inc_mm_counter(mm, MM_ANONPAGES);
}
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = mk_pte(&new_folio->page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
if (unlikely(unshare)) {
if (pte_soft_dirty(vmf->orig_pte))
entry = pte_mksoft_dirty(entry);
if (pte_uffd_wp(vmf->orig_pte)) entry = pte_mkuffd_wp(entry);
} else {
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
}
/*
* Clear the pte entry and flush it first, before updating the
* pte with the new entry, to keep TLBs on different CPUs in
* sync. This code used to set the new PTE then flush TLBs, but
* that left a window where the new PTE could be loaded into
* some TLBs while the old PTE remains in others.
*/
ptep_clear_flush(vma, vmf->address, vmf->pte);
folio_add_new_anon_rmap(new_folio, vma, vmf->address, RMAP_EXCLUSIVE);
folio_add_lru_vma(new_folio, vma);
BUG_ON(unshare && pte_write(entry)); set_pte_at(mm, vmf->address, vmf->pte, entry);
update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
if (old_folio) {
/*
* Only after switching the pte to the new page may
* we remove the mapcount here. Otherwise another
* process may come and find the rmap count decremented
* before the pte is switched to the new page, and
* "reuse" the old page writing into it while our pte
* here still points into it and can be read by other
* threads.
*
* The critical issue is to order this
* folio_remove_rmap_pte() with the ptp_clear_flush
* above. Those stores are ordered by (if nothing else,)
* the barrier present in the atomic_add_negative
* in folio_remove_rmap_pte();
*
* Then the TLB flush in ptep_clear_flush ensures that
* no process can access the old page before the
* decremented mapcount is visible. And the old page
* cannot be reused until after the decremented
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
folio_remove_rmap_pte(old_folio, vmf->page, vma);
}
/* Free the old page.. */
new_folio = old_folio;
page_copied = 1;
pte_unmap_unlock(vmf->pte, vmf->ptl); } else if (vmf->pte) {
update_mmu_tlb(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
mmu_notifier_invalidate_range_end(&range); if (new_folio) folio_put(new_folio); if (old_folio) { if (page_copied) free_swap_cache(old_folio); folio_put(old_folio);
}
delayacct_wpcopy_end();
return 0;
oom:
ret = VM_FAULT_OOM;
out:
if (old_folio) folio_put(old_folio);
delayacct_wpcopy_end();
return ret;
}
/**
* finish_mkwrite_fault - finish page fault for a shared mapping, making PTE
* writeable once the page is prepared
*
* @vmf: structure describing the fault
* @folio: the folio of vmf->page
*
* This function handles all that is needed to finish a write page fault in a
* shared mapping due to PTE being read-only once the mapped page is prepared.
* It handles locking of PTE and modifying it.
*
* The function expects the page to be locked or other protection against
* concurrent faults / writeback (such as DAX radix tree locks).
*
* Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before
* we acquired PTE lock.
*/
static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio)
{
WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (!vmf->pte)
return VM_FAULT_NOPAGE;
/*
* We might have raced with another page fault while we released the
* pte_offset_map_lock.
*/
if (!pte_same(ptep_get(vmf->pte), vmf->orig_pte)) {
update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return VM_FAULT_NOPAGE;
}
wp_page_reuse(vmf, folio);
return 0;
}
/*
* Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
* mapping
*/
static vm_fault_t wp_pfn_shared(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
vm_fault_t ret;
pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf_can_call_fault(vmf);
if (ret)
return ret;
vmf->flags |= FAULT_FLAG_MKWRITE;
ret = vma->vm_ops->pfn_mkwrite(vmf);
if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
return ret;
return finish_mkwrite_fault(vmf, NULL);
}
wp_page_reuse(vmf, NULL);
return 0;
}
static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio)
__releases(vmf->ptl)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret = 0;
folio_get(folio); if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
vm_fault_t tmp;
pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = vmf_can_call_fault(vmf);
if (tmp) {
folio_put(folio);
return tmp;
}
tmp = do_page_mkwrite(vmf, folio);
if (unlikely(!tmp || (tmp &
(VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
folio_put(folio);
return tmp;
}
tmp = finish_mkwrite_fault(vmf, folio);
if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { folio_unlock(folio);
folio_put(folio);
return tmp;
}
} else {
wp_page_reuse(vmf, folio);
folio_lock(folio);
}
ret |= fault_dirty_shared_page(vmf);
folio_put(folio);
return ret;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
struct vm_area_struct *vma)
{
bool exclusive = false;
/* Let's just free up a large folio if only a single page is mapped. */
if (folio_large_mapcount(folio) <= 1)
return false;
/*
* The assumption for anonymous folios is that each page can only get
* mapped once into each MM. The only exception are KSM folios, which
* are always small.
*
* Each taken mapcount must be paired with exactly one taken reference,
* whereby the refcount must be incremented before the mapcount when
* mapping a page, and the refcount must be decremented after the
* mapcount when unmapping a page.
*
* If all folio references are from mappings, and all mappings are in
* the page tables of this MM, then this folio is exclusive to this MM.
*/
if (folio_test_large_maybe_mapped_shared(folio))
return false;
VM_WARN_ON_ONCE(folio_test_ksm(folio)); if (unlikely(folio_test_swapcache(folio))) {
/*
* Note: freeing up the swapcache will fail if some PTEs are
* still swap entries.
*/
if (!folio_trylock(folio))
return false;
folio_free_swap(folio);
folio_unlock(folio);
}
if (folio_large_mapcount(folio) != folio_ref_count(folio))
return false;
/* Stabilize the mapcount vs. refcount and recheck. */
folio_lock_large_mapcount(folio); VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio)); if (folio_test_large_maybe_mapped_shared(folio))
goto unlock;
if (folio_large_mapcount(folio) != folio_ref_count(folio))
goto unlock;
VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio); VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
/*
* Do we need the folio lock? Likely not. If there would have been
* references from page migration/swapout, we would have detected
* an additional folio reference and never ended up here.
*/
exclusive = true;
unlock:
folio_unlock_large_mapcount(folio);
return exclusive;
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
struct vm_area_struct *vma)
{
BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static bool wp_can_reuse_anon_folio(struct folio *folio,
struct vm_area_struct *vma)
{
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && folio_test_large(folio)) return __wp_can_reuse_large_anon_folio(folio, vma);
/*
* We have to verify under folio lock: these early checks are
* just an optimization to avoid locking the folio and freeing
* the swapcache if there is little hope that we can reuse.
*
* KSM doesn't necessarily raise the folio refcount.
*/
if (folio_test_ksm(folio) || folio_ref_count(folio) > 3)
return false;
if (!folio_test_lru(folio))
/*
* We cannot easily detect+handle references from
* remote LRU caches or references to LRU folios.
*/
lru_add_drain(); if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio))
return false;
if (!folio_trylock(folio))
return false;
if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) {
folio_unlock(folio);
return false;
}
/*
* Ok, we've got the only folio reference from our mapping
* and the folio is locked, it's dark out, and we're wearing
* sunglasses. Hit it.
*/
folio_move_anon_rmap(folio, vma);
folio_unlock(folio);
return true;
}
/*
* This routine handles present pages, when
* * users try to write to a shared page (FAULT_FLAG_WRITE)
* * GUP wants to take a R/O pin on a possibly shared anonymous page
* (FAULT_FLAG_UNSHARE)
*
* It is done by copying the page to a new address and decrementing the
* shared-page counter for the old page.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've
* done any necessary COW.
*
* In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even
* though the page will change only once the write actually happens. This
* avoids a few races, and potentially makes it more efficient.
*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), with pte both mapped and locked.
* We return with mmap_lock still held, but pte unmapped and unlocked.
*/
static vm_fault_t do_wp_page(struct vm_fault *vmf)
__releases(vmf->ptl)
{
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
struct vm_area_struct *vma = vmf->vma;
struct folio *folio = NULL;
pte_t pte;
if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) {
if (!userfaultfd_wp_async(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_WP);
}
/*
* Nothing needed (cache flush, TLB invalidations,
* etc.) because we're only removing the uffd-wp bit,
* which is completely invisible to the user.
*/
pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
/*
* Update this to be prepared for following up CoW
* handling
*/
vmf->orig_pte = pte;
}
/*
* Userfaultfd write-protect can defer flushes. Ensure the TLB
* is flushed in this case before copying.
*/
if (unlikely(userfaultfd_wp(vmf->vma) &&
mm_tlb_flush_pending(vmf->vma->vm_mm)))
flush_tlb_page(vmf->vma, vmf->address);
}
vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
if (vmf->page)
folio = page_folio(vmf->page);
/*
* Shared mapping: we are guaranteed to have VM_WRITE and
* FAULT_FLAG_WRITE set at this point.
*/
if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
/*
* VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
* VM_PFNMAP VMA. FS DAX also wants ops->pfn_mkwrite called.
*
* We should not cow pages in a shared writeable mapping.
* Just mark the pages writable and/or call ops->pfn_mkwrite.
*/
if (!vmf->page || is_fsdax_page(vmf->page)) {
vmf->page = NULL;
return wp_pfn_shared(vmf);
}
return wp_page_shared(vmf, folio);
}
/*
* Private mapping: create an exclusive anonymous page copy if reuse
* is impossible. We might miss VM_WRITE for FOLL_FORCE handling.
*
* If we encounter a page that is marked exclusive, we must reuse
* the page without further checks.
*/
if (folio && folio_test_anon(folio) && (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { if (!PageAnonExclusive(vmf->page)) SetPageAnonExclusive(vmf->page);
if (unlikely(unshare)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
}
wp_page_reuse(vmf, folio);
return 0;
}
/*
* Ok, we need to copy. Oh, well..
*/
if (folio)
folio_get(folio); pte_unmap_unlock(vmf->pte, vmf->ptl);
#ifdef CONFIG_KSM
if (folio && folio_test_ksm(folio)) count_vm_event(COW_KSM);
#endif
return wp_page_copy(vmf);
}
static void unmap_mapping_range_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr,
struct zap_details *details)
{
zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}
static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
pgoff_t first_index,
pgoff_t last_index,
struct zap_details *details)
{
struct vm_area_struct *vma;
pgoff_t vba, vea, zba, zea;
vma_interval_tree_foreach(vma, root, first_index, last_index) {
vba = vma->vm_pgoff;
vea = vba + vma_pages(vma) - 1;
zba = max(first_index, vba);
zea = min(last_index, vea);
unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
details);
}
}
/**
* unmap_mapping_folio() - Unmap single folio from processes.
* @folio: The locked folio to be unmapped.
*
* Unmap this folio from any userspace process which still has it mmaped.
* Typically, for efficiency, the range of nearby pages has already been
* unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
* truncation or invalidation holds the lock on a folio, it may find that
* the page has been remapped again: and then uses unmap_mapping_folio()
* to unmap it finally.
*/
void unmap_mapping_folio(struct folio *folio)
{
struct address_space *mapping = folio->mapping;
struct zap_details details = { };
pgoff_t first_index;
pgoff_t last_index;
VM_BUG_ON(!folio_test_locked(folio));
first_index = folio->index;
last_index = folio_next_index(folio) - 1;
details.even_cows = false;
details.single_folio = folio;
details.zap_flags = ZAP_FLAG_DROP_MARKER;
i_mmap_lock_read(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
unmap_mapping_range_tree(&mapping->i_mmap, first_index,
last_index, &details);
i_mmap_unlock_read(mapping);
}
/**
* unmap_mapping_pages() - Unmap pages from processes.
* @mapping: The address space containing pages to be unmapped.
* @start: Index of first page to be unmapped.
* @nr: Number of pages to be unmapped. 0 to unmap to end of file.
* @even_cows: Whether to unmap even private COWed pages.
*
* Unmap the pages in this address space from any userspace process which
* has them mmaped. Generally, you want to remove COWed pages as well when
* a file is being truncated, but not when invalidating pages from the page
* cache.
*/
void unmap_mapping_pages(struct address_space *mapping, pgoff_t start,
pgoff_t nr, bool even_cows)
{
struct zap_details details = { };
pgoff_t first_index = start;
pgoff_t last_index = start + nr - 1;
details.even_cows = even_cows;
if (last_index < first_index)
last_index = ULONG_MAX;
i_mmap_lock_read(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
unmap_mapping_range_tree(&mapping->i_mmap, first_index,
last_index, &details);
i_mmap_unlock_read(mapping);
}
EXPORT_SYMBOL_GPL(unmap_mapping_pages);
/**
* unmap_mapping_range - unmap the portion of all mmaps in the specified
* address_space corresponding to the specified byte range in the underlying
* file.
*
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
* boundary. Note that this is different from truncate_pagecache(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
* up to a PAGE_SIZE boundary. A holelen of zero truncates to the
* end of the file.
* @even_cows: 1 when truncating a file, unmap even private COWed pages;
* but 0 when invalidating pagecache, don't throw away private data.
*/
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT;
pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
long long holeend =
(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (holeend & ~(long long)ULONG_MAX)
hlen = ULONG_MAX - hba + 1;
}
unmap_mapping_pages(mapping, hba, hlen, even_cows);
}
EXPORT_SYMBOL(unmap_mapping_range);
/*
* Restore a potential device exclusive pte to a working pte entry
*/
static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
{
struct folio *folio = page_folio(vmf->page);
struct vm_area_struct *vma = vmf->vma;
struct mmu_notifier_range range;
vm_fault_t ret;
/*
* We need a reference to lock the folio because we don't hold
* the PTL so a racing thread can remove the device-exclusive
* entry and unmap it. If the folio is free the entry must
* have been removed already. If it happens to have already
* been re-allocated after being freed all we do is lock and
* unlock it.
*/
if (!folio_try_get(folio))
return 0;
ret = folio_lock_or_retry(folio, vmf);
if (ret) {
folio_put(folio);
return ret;
}
mmu_notifier_range_init_owner(&range, MMU_NOTIFY_CLEAR, 0,
vma->vm_mm, vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
mmu_notifier_invalidate_range_start(&range);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
restore_exclusive_pte(vma, folio, vmf->page, vmf->address,
vmf->pte, vmf->orig_pte);
if (vmf->pte)
pte_unmap_unlock(vmf->pte, vmf->ptl);
folio_unlock(folio);
folio_put(folio);
mmu_notifier_invalidate_range_end(&range);
return 0;
}
static inline bool should_try_to_free_swap(struct folio *folio,
struct vm_area_struct *vma,
unsigned int fault_flags)
{
if (!folio_test_swapcache(folio))
return false;
if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) ||
folio_test_mlocked(folio))
return true;
/*
* If we want to map a page that's in the swapcache writable, we
* have to detect via the refcount if we're really the exclusive
* user. Try freeing the swapcache to get rid of the swapcache
* reference only in case it's likely that we'll be the exlusive user.
*/
return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) &&
folio_ref_count(folio) == (1 + folio_nr_pages(folio));
}
static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
{
vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (!vmf->pte)
return 0;
/*
* Be careful so that we will only recover a special uffd-wp pte into a
* none pte. Otherwise it means the pte could have changed, so retry.
*
* This should also cover the case where e.g. the pte changed
* quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED.
* So is_pte_marker() check is not enough to safely drop the pte.
*/
if (pte_same(vmf->orig_pte, ptep_get(vmf->pte)))
pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
}
static vm_fault_t do_pte_missing(struct vm_fault *vmf)
{
if (vma_is_anonymous(vmf->vma))
return do_anonymous_page(vmf);
else
return do_fault(vmf);
}
/*
* This is actually a page-missing access, but with uffd-wp special pte
* installed. It means this pte was wr-protected before being unmapped.
*/
static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf)
{
/*
* Just in case there're leftover special ptes even after the region
* got unregistered - we can simply clear them.
*/
if (unlikely(!userfaultfd_wp(vmf->vma)))
return pte_marker_clear(vmf);
return do_pte_missing(vmf);
}
static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
{
swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte);
unsigned long marker = pte_marker_get(entry);
/*
* PTE markers should never be empty. If anything weird happened,
* the best thing to do is to kill the process along with its mm.
*/
if (WARN_ON_ONCE(!marker))
return VM_FAULT_SIGBUS;
/* Higher priority than uffd-wp when data corrupted */
if (marker & PTE_MARKER_POISONED)
return VM_FAULT_HWPOISON;
/* Hitting a guard page is always a fatal condition. */
if (marker & PTE_MARKER_GUARD)
return VM_FAULT_SIGSEGV;
if (pte_marker_entry_uffd_wp(entry))
return pte_marker_handle_uffd_wp(vmf);
/* This is an unknown pte marker */
return VM_FAULT_SIGBUS;
}
static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
swp_entry_t entry;
folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address);
if (!folio)
return NULL;
entry = pte_to_swp_entry(vmf->orig_pte);
if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
GFP_KERNEL, entry)) {
folio_put(folio);
return NULL;
}
return folio;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
{
struct swap_info_struct *si = swp_swap_info(entry);
pgoff_t offset = swp_offset(entry);
int i;
/*
* While allocating a large folio and doing swap_read_folio, which is
* the case the being faulted pte doesn't have swapcache. We need to
* ensure all PTEs have no cache as well, otherwise, we might go to
* swap devices while the content is in swapcache.
*/
for (i = 0; i < max_nr; i++) {
if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
return i;
}
return i;
}
/*
* Check if the PTEs within a range are contiguous swap entries
* and have consistent swapcache, zeromap.
*/
static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
{
unsigned long addr;
swp_entry_t entry;
int idx;
pte_t pte;
addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
idx = (vmf->address - addr) / PAGE_SIZE;
pte = ptep_get(ptep);
if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx)))
return false;
entry = pte_to_swp_entry(pte);
if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages)
return false;
/*
* swap_read_folio() can't handle the case a large folio is hybridly
* from different backends. And they are likely corner cases. Similar
* things might be added once zswap support large folios.
*/
if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages))
return false;
if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages))
return false;
return true;
}
static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset,
unsigned long addr,
unsigned long orders)
{
int order, nr;
order = highest_order(orders);
/*
* To swap in a THP with nr pages, we require that its first swap_offset
* is aligned with that number, as it was when the THP was swapped out.
* This helps filter out most invalid entries.
*/
while (orders) {
nr = 1 << order;
if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr)
break;
order = next_order(&orders, order);
}
return orders;
}
static struct folio *alloc_swap_folio(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long orders;
struct folio *folio;
unsigned long addr;
swp_entry_t entry;
spinlock_t *ptl;
pte_t *pte;
gfp_t gfp;
int order;
/*
* If uffd is active for the vma we need per-page fault fidelity to
* maintain the uffd semantics.
*/
if (unlikely(userfaultfd_armed(vma)))
goto fallback;
/*
* A large swapped out folio could be partially or fully in zswap. We
* lack handling for such cases, so fallback to swapping in order-0
* folio.
*/
if (!zswap_never_enabled())
goto fallback;
entry = pte_to_swp_entry(vmf->orig_pte);
/*
* Get a list of all the (large) orders below PMD_ORDER that are enabled
* and suitable for swapping THP.
*/
orders = thp_vma_allowable_orders(vma, vma->vm_flags,
TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1);
orders = thp_vma_suitable_orders(vma, vmf->address, orders);
orders = thp_swap_suitable_orders(swp_offset(entry),
vmf->address, orders);
if (!orders)
goto fallback;
pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
vmf->address & PMD_MASK, &ptl);
if (unlikely(!pte))
goto fallback;
/*
* For do_swap_page, find the highest order where the aligned range is
* completely swap entries with contiguous swap offsets.
*/
order = highest_order(orders);
while (orders) {
addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order))
break;
order = next_order(&orders, order);
}
pte_unmap_unlock(pte, ptl);
/* Try allocating the highest of the remaining orders. */
gfp = vma_thp_gfp_mask(vma);
while (orders) {
addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
folio = vma_alloc_folio(gfp, order, vma, addr);
if (folio) {
if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
gfp, entry))
return folio;
count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
folio_put(folio);
}
count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK);
order = next_order(&orders, order);
}
fallback:
return __alloc_swap_folio(vmf);
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
static struct folio *alloc_swap_folio(struct vm_fault *vmf)
{
return __alloc_swap_folio(vmf);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with pte unmapped and unlocked.
*
* We return with the mmap_lock locked or unlocked in the same cases
* as does filemap_fault().
*/
vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *swapcache, *folio = NULL;
DECLARE_WAITQUEUE(wait, current);
struct page *page;
struct swap_info_struct *si = NULL;
rmap_t rmap_flags = RMAP_NONE;
bool need_clear_cache = false;
bool exclusive = false;
swp_entry_t entry;
pte_t pte;
vm_fault_t ret = 0;
void *shadow = NULL;
int nr_pages;
unsigned long page_idx;
unsigned long address;
pte_t *ptep;
if (!pte_unmap_same(vmf))
goto out;
entry = pte_to_swp_entry(vmf->orig_pte);
if (unlikely(non_swap_entry(entry))) {
if (is_migration_entry(entry)) {
migration_entry_wait(vma->vm_mm, vmf->pmd,
vmf->address);
} else if (is_device_exclusive_entry(entry)) {
vmf->page = pfn_swap_entry_to_page(entry);
ret = remove_device_exclusive_entry(vmf);
} else if (is_device_private_entry(entry)) {
if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
/*
* migrate_to_ram is not yet ready to operate
* under VMA lock.
*/
vma_end_read(vma);
ret = VM_FAULT_RETRY;
goto out;
}
vmf->page = pfn_swap_entry_to_page(entry);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (unlikely(!vmf->pte ||
!pte_same(ptep_get(vmf->pte),
vmf->orig_pte)))
goto unlock;
/*
* Get a page reference while we know the page can't be
* freed.
*/
if (trylock_page(vmf->page)) {
struct dev_pagemap *pgmap;
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
pgmap = page_pgmap(vmf->page);
ret = pgmap->ops->migrate_to_ram(vmf);
unlock_page(vmf->page);
put_page(vmf->page);
} else {
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
} else if (is_pte_marker_entry(entry)) {
ret = handle_pte_marker(vmf);
} else {
print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
ret = VM_FAULT_SIGBUS;
}
goto out;
}
/* Prevent swapoff from happening to us. */
si = get_swap_device(entry);
if (unlikely(!si))
goto out;
folio = swap_cache_get_folio(entry, vma, vmf->address);
if (folio)
page = folio_file_page(folio, swp_offset(entry));
swapcache = folio;
if (!folio) {
if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
__swap_count(entry) == 1) {
/* skip swapcache */
folio = alloc_swap_folio(vmf);
if (folio) {
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
nr_pages = folio_nr_pages(folio);
if (folio_test_large(folio))
entry.val = ALIGN_DOWN(entry.val, nr_pages);
/*
* Prevent parallel swapin from proceeding with
* the cache flag. Otherwise, another thread
* may finish swapin first, free the entry, and
* swapout reusing the same entry. It's
* undetectable as pte_same() returns true due
* to entry reuse.
*/
if (swapcache_prepare(entry, nr_pages)) {
/*
* Relax a bit to prevent rapid
* repeated page faults.
*/
add_wait_queue(&swapcache_wq, &wait);
schedule_timeout_uninterruptible(1);
remove_wait_queue(&swapcache_wq, &wait);
goto out_page;
}
need_clear_cache = true;
memcg1_swapin(entry, nr_pages);
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
workingset_refault(folio, shadow);
folio_add_lru(folio);
/* To provide entry to swap_read_folio() */
folio->swap = entry;
swap_read_folio(folio, NULL);
folio->private = NULL;
}
} else {
folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
vmf);
swapcache = folio;
}
if (!folio) {
/*
* Back out if somebody else faulted in this pte
* while we released the pte lock.
*/
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (likely(vmf->pte &&
pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
ret = VM_FAULT_OOM;
goto unlock;
}
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
page = folio_file_page(folio, swp_offset(entry));
} else if (PageHWPoison(page)) {
/*
* hwpoisoned dirty swapcache pages are kept for killing
* owner processes (which may be unknown at hwpoison time)
*/
ret = VM_FAULT_HWPOISON;
goto out_release;
}
ret |= folio_lock_or_retry(folio, vmf);
if (ret & VM_FAULT_RETRY)
goto out_release;
if (swapcache) {
/*
* Make sure folio_free_swap() or swapoff did not release the
* swapcache from under us. The page pin, and pte_same test
* below, are not enough to exclude that. Even if it is still
* swapcache, we need to check that the page's swap has not
* changed.
*/
if (unlikely(!folio_test_swapcache(folio) ||
page_swap_entry(page).val != entry.val))
goto out_page;
/*
* KSM sometimes has to copy on read faults, for example, if
* page->index of !PageKSM() pages would be nonlinear inside the
* anon VMA -- PageKSM() is lost on actual swapout.
*/
folio = ksm_might_need_to_copy(folio, vma, vmf->address);
if (unlikely(!folio)) {
ret = VM_FAULT_OOM;
folio = swapcache;
goto out_page;
} else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
ret = VM_FAULT_HWPOISON;
folio = swapcache;
goto out_page;
}
if (folio != swapcache)
page = folio_page(folio, 0);
/*
* If we want to map a page that's in the swapcache writable, we
* have to detect via the refcount if we're really the exclusive
* owner. Try removing the extra reference from the local LRU
* caches if required.
*/
if ((vmf->flags & FAULT_FLAG_WRITE) && folio == swapcache &&
!folio_test_ksm(folio) && !folio_test_lru(folio))
lru_add_drain();
}
folio_throttle_swaprate(folio, GFP_KERNEL);
/*
* Back out if somebody else already faulted in this pte.
*/
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
goto out_nomap;
if (unlikely(!folio_test_uptodate(folio))) {
ret = VM_FAULT_SIGBUS;
goto out_nomap;
}
/* allocated large folios for SWP_SYNCHRONOUS_IO */
if (folio_test_large(folio) && !folio_test_swapcache(folio)) {
unsigned long nr = folio_nr_pages(folio);
unsigned long folio_start = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE);
unsigned long idx = (vmf->address - folio_start) / PAGE_SIZE;
pte_t *folio_ptep = vmf->pte - idx;
pte_t folio_pte = ptep_get(folio_ptep);
if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) ||
swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
goto out_nomap;
page_idx = idx;
address = folio_start;
ptep = folio_ptep;
goto check_folio;
}
nr_pages = 1;
page_idx = 0;
address = vmf->address;
ptep = vmf->pte;
if (folio_test_large(folio) && folio_test_swapcache(folio)) {
int nr = folio_nr_pages(folio);
unsigned long idx = folio_page_idx(folio, page);
unsigned long folio_start = address - idx * PAGE_SIZE;
unsigned long folio_end = folio_start + nr * PAGE_SIZE;
pte_t *folio_ptep;
pte_t folio_pte;
if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start)))
goto check_folio;
if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end)))
goto check_folio;
folio_ptep = vmf->pte - idx;
folio_pte = ptep_get(folio_ptep);
if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) ||
swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
goto check_folio;
page_idx = idx;
address = folio_start;
ptep = folio_ptep;
nr_pages = nr;
entry = folio->swap;
page = &folio->page;
}
check_folio:
/*
* PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte
* must never point at an anonymous page in the swapcache that is
* PG_anon_exclusive. Sanity check that this holds and especially, that
* no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity
* check after taking the PT lock and making sure that nobody
* concurrently faulted in this page and set PG_anon_exclusive.
*/
BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio));
BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page));
/*
* Check under PT lock (to protect against concurrent fork() sharing
* the swap entry concurrently) for certainly exclusive pages.
*/
if (!folio_test_ksm(folio)) {
exclusive = pte_swp_exclusive(vmf->orig_pte);
if (folio != swapcache) {
/*
* We have a fresh page that is not exposed to the
* swapcache -> certainly exclusive.
*/
exclusive = true;
} else if (exclusive && folio_test_writeback(folio) &&
data_race(si->flags & SWP_STABLE_WRITES)) {
/*
* This is tricky: not all swap backends support
* concurrent page modifications while under writeback.
*
* So if we stumble over such a page in the swapcache
* we must not set the page exclusive, otherwise we can
* map it writable without further checks and modify it
* while still under writeback.
*
* For these problematic swap backends, simply drop the
* exclusive marker: this is perfectly fine as we start
* writeback only if we fully unmapped the page and
* there are no unexpected references on the page after
* unmapping succeeded. After fully unmapped, no
* further GUP references (FOLL_GET and FOLL_PIN) can
* appear, so dropping the exclusive marker and mapping
* it only R/O is fine.
*/
exclusive = false;
}
}
/*
* Some architectures may have to restore extra metadata to the page
* when reading from swap. This metadata may be indexed by swap entry
* so this must be called before swap_free().
*/
arch_swap_restore(folio_swap(entry, folio), folio);
/*
* Remove the swap entry and conditionally try to free up the swapcache.
* We're already holding a reference on the page but haven't mapped it
* yet.
*/
swap_free_nr(entry, nr_pages);
if (should_try_to_free_swap(folio, vma, vmf->flags))
folio_free_swap(folio);
add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages);
pte = mk_pte(page, vma->vm_page_prot);
if (pte_swp_soft_dirty(vmf->orig_pte))
pte = pte_mksoft_dirty(pte);
if (pte_swp_uffd_wp(vmf->orig_pte))
pte = pte_mkuffd_wp(pte);
/*
* Same logic as in do_wp_page(); however, optimize for pages that are
* certainly not shared either because we just allocated them without
* exposing them to the swapcache or because the swap entry indicates
* exclusivity.
*/
if (!folio_test_ksm(folio) &&
(exclusive || folio_ref_count(folio) == 1)) {
if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) &&
!pte_needs_soft_dirty_wp(vma, pte)) {
pte = pte_mkwrite(pte, vma);
if (vmf->flags & FAULT_FLAG_WRITE) {
pte = pte_mkdirty(pte);
vmf->flags &= ~FAULT_FLAG_WRITE;
}
}
rmap_flags |= RMAP_EXCLUSIVE;
}
folio_ref_add(folio, nr_pages - 1);
flush_icache_pages(vma, page, nr_pages);
vmf->orig_pte = pte_advance_pfn(pte, page_idx);
/* ksm created a completely new copy */
if (unlikely(folio != swapcache && swapcache)) {
folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
} else if (!folio_test_anon(folio)) {
/*
* We currently only expect small !anon folios which are either
* fully exclusive or fully shared, or new allocated large
* folios which are fully exclusive. If we ever get large
* folios within swapcache here, we have to be careful.
*/
VM_WARN_ON_ONCE(folio_test_large(folio) && folio_test_swapcache(folio));
VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
folio_add_new_anon_rmap(folio, vma, address, rmap_flags);
} else {
folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address,
rmap_flags);
}
VM_BUG_ON(!folio_test_anon(folio) ||
(pte_write(pte) && !PageAnonExclusive(page)));
set_ptes(vma->vm_mm, address, ptep, pte, nr_pages);
arch_do_swap_page_nr(vma->vm_mm, vma, address,
pte, pte, nr_pages);
folio_unlock(folio);
if (folio != swapcache && swapcache) {
/*
* Hold the lock to avoid the swap entry to be reused
* until we take the PT lock for the pte_same() check
* (to avoid false positives from pte_same). For
* further safety release the lock after the swap_free
* so that the swap count won't change under a
* parallel locked swapcache.
*/
folio_unlock(swapcache);
folio_put(swapcache);
}
if (vmf->flags & FAULT_FLAG_WRITE) {
ret |= do_wp_page(vmf);
if (ret & VM_FAULT_ERROR)
ret &= VM_FAULT_ERROR;
goto out;
}
/* No need to invalidate - it was non-present before */
update_mmu_cache_range(vmf, vma, address, ptep, nr_pages);
unlock:
if (vmf->pte)
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
/* Clear the swap cache pin for direct swapin after PTL unlock */
if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
if (waitqueue_active(&swapcache_wq))
wake_up(&swapcache_wq);
}
if (si)
put_swap_device(si);
return ret;
out_nomap:
if (vmf->pte)
pte_unmap_unlock(vmf->pte, vmf->ptl);
out_page:
folio_unlock(folio);
out_release:
folio_put(folio);
if (folio != swapcache && swapcache) {
folio_unlock(swapcache);
folio_put(swapcache);
}
if (need_clear_cache) {
swapcache_clear(si, entry, nr_pages);
if (waitqueue_active(&swapcache_wq))
wake_up(&swapcache_wq);
}
if (si)
put_swap_device(si);
return ret;
}
static bool pte_range_none(pte_t *pte, int nr_pages)
{
int i;
for (i = 0; i < nr_pages; i++) { if (!pte_none(ptep_get_lockless(pte + i)))
return false;
}
return true;
}
static struct folio *alloc_anon_folio(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
unsigned long orders;
struct folio *folio;
unsigned long addr;
pte_t *pte;
gfp_t gfp;
int order;
/*
* If uffd is active for the vma we need per-page fault fidelity to
* maintain the uffd semantics.
*/
if (unlikely(userfaultfd_armed(vma)))
goto fallback;
/*
* Get a list of all the (large) orders below PMD_ORDER that are enabled
* for this vma. Then filter out the orders that can't be allocated over
* the faulting address and still be fully contained in the vma.
*/
orders = thp_vma_allowable_orders(vma, vma->vm_flags,
TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1);
orders = thp_vma_suitable_orders(vma, vmf->address, orders);
if (!orders)
goto fallback;
pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK);
if (!pte)
return ERR_PTR(-EAGAIN);
/*
* Find the highest order where the aligned range is completely
* pte_none(). Note that all remaining orders will be completely
* pte_none().
*/
order = highest_order(orders);
while (orders) {
addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
if (pte_range_none(pte + pte_index(addr), 1 << order))
break;
order = next_order(&orders, order);
}
pte_unmap(pte); if (!orders)
goto fallback;
/* Try allocating the highest of the remaining orders. */
gfp = vma_thp_gfp_mask(vma);
while (orders) {
addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
folio = vma_alloc_folio(gfp, order, vma, addr);
if (folio) {
if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); folio_put(folio);
goto next;
}
folio_throttle_swaprate(folio, gfp);
/*
* When a folio is not zeroed during allocation
* (__GFP_ZERO not used) or user folios require special
* handling, folio_zero_user() is used to make sure
* that the page corresponding to the faulting address
* will be hot in the cache after zeroing.
*/
if (user_alloc_needs_zeroing()) folio_zero_user(folio, vmf->address);
return folio;
}
next:
count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
order = next_order(&orders, order);
}
fallback:
#endif
return folio_prealloc(vma->vm_mm, vma, vmf->address, true);
}
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_lock still held, but pte unmapped and unlocked.
*/
static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address;
struct folio *folio;
vm_fault_t ret = 0;
int nr_pages = 1;
pte_t entry;
/* File mapping without ->vm_ops ? */
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
/*
* Use pte_alloc() instead of pte_alloc_map(), so that OOM can
* be distinguished from a transient failure of pte_offset_map().
*/
if (pte_alloc(vma->vm_mm, vmf->pmd))
return VM_FAULT_OOM;
/* Use the zero-page for reads */
if (!(vmf->flags & FAULT_FLAG_WRITE) &&
!mm_forbids_zeropage(vma->vm_mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
vma->vm_page_prot));
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (!vmf->pte)
goto unlock;
if (vmf_pte_changed(vmf)) {
update_mmu_tlb(vma, vmf->address, vmf->pte);
goto unlock;
}
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto unlock;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
goto setpte;
}
/* Allocate our own private page. */
ret = vmf_anon_prepare(vmf); if (ret)
return ret;
/* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */
folio = alloc_anon_folio(vmf); if (IS_ERR(folio))
return 0;
if (!folio)
goto oom;
nr_pages = folio_nr_pages(folio);
addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
/*
* The memory barrier inside __folio_mark_uptodate makes sure that
* preceding stores to the page contents become visible before
* the set_pte_at() write.
*/
__folio_mark_uptodate(folio);
entry = mk_pte(&folio->page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry), vma);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
if (!vmf->pte)
goto release;
if (nr_pages == 1 && vmf_pte_changed(vmf)) {
update_mmu_tlb(vma, addr, vmf->pte);
goto release;
} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
goto release;
}
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto release;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
folio_put(folio);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
folio_ref_add(folio, nr_pages - 1);
add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC);
folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
setpte:
if (vmf_orig_pte_uffd_wp(vmf))
entry = pte_mkuffd_wp(entry);
set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages);
/* No need to invalidate - it was non-present before */
update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages);
unlock:
if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
release:
folio_put(folio);
goto unlock;
oom:
return VM_FAULT_OOM;
}
/*
* The mmap_lock must have been held on entry, and may have been
* released depending on flags and vma->vm_ops->fault() return value.
* See filemap_fault() and __lock_page_retry().
*/
static vm_fault_t __do_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
vm_fault_t ret;
/*
* Preallocate pte before we take page_lock because this might lead to
* deadlocks for memcg reclaim which waits for pages under writeback:
* lock_page(A)
* SetPageWriteback(A)
* unlock_page(A)
* lock_page(B)
* lock_page(B)
* pte_alloc_one
* shrink_folio_list
* wait_on_page_writeback(A)
* SetPageWriteback(B)
* unlock_page(B)
* # flush A, B to clear the writeback
*/
if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
}
ret = vma->vm_ops->fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
VM_FAULT_DONE_COW)))
return ret;
folio = page_folio(vmf->page); if (unlikely(PageHWPoison(vmf->page))) {
vm_fault_t poisonret = VM_FAULT_HWPOISON;
if (ret & VM_FAULT_LOCKED) { if (page_mapped(vmf->page)) unmap_mapping_folio(folio);
/* Retry if a clean folio was removed from the cache. */
if (mapping_evict_folio(folio->mapping, folio))
poisonret = VM_FAULT_NOPAGE;
folio_unlock(folio);
}
folio_put(folio);
vmf->page = NULL;
return poisonret;
}
if (unlikely(!(ret & VM_FAULT_LOCKED)))
folio_lock(folio);
else
VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page);
return ret;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void deposit_prealloc_pte(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
/*
* We are going to consume the prealloc table,
* count that as nr_ptes.
*/
mm_inc_nr_ptes(vma->vm_mm);
vmf->prealloc_pte = NULL;
}
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
{
struct folio *folio = page_folio(page);
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
pmd_t entry;
vm_fault_t ret = VM_FAULT_FALLBACK;
/*
* It is too late to allocate a small folio, we already have a large
* folio in the pagecache: especially s390 KVM cannot tolerate any
* PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any
* PMD mappings if THPs are disabled.
*/
if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags))
return ret;
if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
return ret;
if (folio_order(folio) != HPAGE_PMD_ORDER)
return ret;
page = &folio->page;
/*
* Just backoff if any subpage of a THP is corrupted otherwise
* the corrupted page may mapped by PMD silently to escape the
* check. This kind of THP just can be PTE mapped. Access to
* the corrupted subpage should trigger SIGBUS as expected.
*/
if (unlikely(folio_test_has_hwpoisoned(folio)))
return ret;
/*
* Archs like ppc64 need additional space to store information
* related to pte entry. Use the preallocated table for that.
*/
if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_none(*vmf->pmd)))
goto out;
flush_icache_pages(vma, page, HPAGE_PMD_NR);
entry = mk_huge_pmd(page, vma->vm_page_prot);
if (write)
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR);
folio_add_file_rmap_pmd(folio, page, vma);
/*
* deposit and withdraw with pmd lock held
*/
if (arch_needs_pgtable_deposit())
deposit_prealloc_pte(vmf);
set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
update_mmu_cache_pmd(vma, haddr, vmf->pmd);
/* fault is handled */
ret = 0;
count_vm_event(THP_FILE_MAPPED);
out:
spin_unlock(vmf->ptl);
return ret;
}
#else
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
{
return VM_FAULT_FALLBACK;
}
#endif
/**
* set_pte_range - Set a range of PTEs to point to pages in a folio.
* @vmf: Fault decription.
* @folio: The folio that contains @page.
* @page: The first page to create a PTE for.
* @nr: The number of PTEs to create.
* @addr: The first address to create a PTE for.
*/
void set_pte_range(struct vm_fault *vmf, struct folio *folio,
struct page *page, unsigned int nr, unsigned long addr)
{
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE);
pte_t entry;
flush_icache_pages(vma, page, nr);
entry = mk_pte(page, vma->vm_page_prot);
if (prefault && arch_wants_old_prefaulted_pte())
entry = pte_mkold(entry);
else
entry = pte_sw_mkyoung(entry);
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (unlikely(vmf_orig_pte_uffd_wp(vmf)))
entry = pte_mkuffd_wp(entry);
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) { VM_BUG_ON_FOLIO(nr != 1, folio); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
} else {
folio_add_file_rmap_ptes(folio, page, nr, vma);
}
set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
/* no need to invalidate: a not-present page won't be cached */
update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr);
}
static bool vmf_pte_changed(struct vm_fault *vmf)
{
if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)
return !pte_same(ptep_get(vmf->pte), vmf->orig_pte); return !pte_none(ptep_get(vmf->pte));
}
/**
* finish_fault - finish page fault once we have prepared the page to fault
*
* @vmf: structure describing the fault
*
* This function handles all that is needed to finish a page fault once the
* page to fault in is prepared. It handles locking of PTEs, inserts PTE for
* given page, adds reverse page mapping, handles memcg charges and LRU
* addition.
*
* The function expects the page to be locked and on success it consumes a
* reference of a page being mapped (for the PTE which maps it).
*
* Return: %0 on success, %VM_FAULT_ code in case of error.
*/
vm_fault_t finish_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page;
struct folio *folio;
vm_fault_t ret;
bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED);
int type, nr_pages;
unsigned long addr;
bool needs_fallback = false;
fallback:
addr = vmf->address;
/* Did we COW the page? */
if (is_cow)
page = vmf->cow_page;
else
page = vmf->page;
/*
* check even for read faults because we might have lost our CoWed
* page
*/
if (!(vma->vm_flags & VM_SHARED)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret)
return ret;
}
if (pmd_none(*vmf->pmd)) { if (PageTransCompound(page)) {
ret = do_set_pmd(vmf, page);
if (ret != VM_FAULT_FALLBACK)
return ret;
}
if (vmf->prealloc_pte)
pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
return VM_FAULT_OOM;
}
folio = page_folio(page); nr_pages = folio_nr_pages(folio);
/*
* Using per-page fault to maintain the uffd semantics, and same
* approach also applies to non-anonymous-shmem faults to avoid
* inflating the RSS of the process.
*/
if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) ||
unlikely(needs_fallback)) {
nr_pages = 1;
} else if (nr_pages > 1) {
pgoff_t idx = folio_page_idx(folio, page);
/* The page offset of vmf->address within the VMA. */
pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff;
/* The index of the entry in the pagetable for fault page. */
pgoff_t pte_off = pte_index(vmf->address);
/*
* Fallback to per-page fault in case the folio size in page
* cache beyond the VMA limits and PMD pagetable limits.
*/
if (unlikely(vma_off < idx ||
vma_off + (nr_pages - idx) > vma_pages(vma) ||
pte_off < idx ||
pte_off + (nr_pages - idx) > PTRS_PER_PTE)) {
nr_pages = 1;
} else {
/* Now we can set mappings for the whole large folio. */
addr = vmf->address - idx * PAGE_SIZE;
page = &folio->page;
}
}
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
addr, &vmf->ptl);
if (!vmf->pte)
return VM_FAULT_NOPAGE;
/* Re-check under ptl */
if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) {
update_mmu_tlb(vma, addr, vmf->pte);
ret = VM_FAULT_NOPAGE;
goto unlock;
} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
needs_fallback = true;
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto fallback;
}
folio_ref_add(folio, nr_pages - 1);
set_pte_range(vmf, folio, page, nr_pages, addr);
type = is_cow ? MM_ANONPAGES : mm_counter_file(folio);
add_mm_counter(vma->vm_mm, type, nr_pages);
ret = 0;
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
}
static unsigned long fault_around_pages __read_mostly =
65536 >> PAGE_SHIFT;
#ifdef CONFIG_DEBUG_FS
static int fault_around_bytes_get(void *data, u64 *val)
{
*val = fault_around_pages << PAGE_SHIFT;
return 0;
}
/*
* fault_around_bytes must be rounded down to the nearest page order as it's
* what do_fault_around() expects to see.
*/
static int fault_around_bytes_set(void *data, u64 val)
{
if (val / PAGE_SIZE > PTRS_PER_PTE)
return -EINVAL;
/*
* The minimum value is 1 page, however this results in no fault-around
* at all. See should_fault_around().
*/
val = max(val, PAGE_SIZE);
fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT;
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops,
fault_around_bytes_get, fault_around_bytes_set, "%llu\n");
static int __init fault_around_debugfs(void)
{
debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
&fault_around_bytes_fops);
return 0;
}
late_initcall(fault_around_debugfs);
#endif
/*
* do_fault_around() tries to map few pages around the fault address. The hope
* is that the pages will be needed soon and this will lower the number of
* faults to handle.
*
* It uses vm_ops->map_pages() to map the pages, which skips the page if it's
* not ready to be mapped: not up-to-date, locked, etc.
*
* This function doesn't cross VMA or page table boundaries, in order to call
* map_pages() and acquire a PTE lock only once.
*
* fault_around_pages defines how many pages we'll try to map.
* do_fault_around() expects it to be set to a power of two less than or equal
* to PTRS_PER_PTE.
*
* The virtual address of the area that we map is naturally aligned to
* fault_around_pages * PAGE_SIZE rounded down to the machine page size
* (and therefore to page order). This way it's easier to guarantee
* that we don't cross page table boundaries.
*/
static vm_fault_t do_fault_around(struct vm_fault *vmf)
{
pgoff_t nr_pages = READ_ONCE(fault_around_pages);
pgoff_t pte_off = pte_index(vmf->address);
/* The page offset of vmf->address within the VMA. */
pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff;
pgoff_t from_pte, to_pte;
vm_fault_t ret;
/* The PTE offset of the start address, clamped to the VMA. */
from_pte = max(ALIGN_DOWN(pte_off, nr_pages),
pte_off - min(pte_off, vma_off));
/* The PTE offset of the end address, clamped to the VMA and PTE. */
to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE,
pte_off + vma_pages(vmf->vma) - vma_off) - 1;
if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
}
rcu_read_lock();
ret = vmf->vma->vm_ops->map_pages(vmf,
vmf->pgoff + from_pte - pte_off,
vmf->pgoff + to_pte - pte_off);
rcu_read_unlock();
return ret;
}
/* Return true if we should do read fault-around, false otherwise */
static inline bool should_fault_around(struct vm_fault *vmf)
{
/* No ->map_pages? No way to fault around... */
if (!vmf->vma->vm_ops->map_pages)
return false;
if (uffd_disable_fault_around(vmf->vma))
return false;
/* A single page implies no faulting 'around' at all. */
return fault_around_pages > 1;
}
static vm_fault_t do_read_fault(struct vm_fault *vmf)
{
vm_fault_t ret = 0;
struct folio *folio;
/*
* Let's call ->map_pages() first and use ->fault() as fallback
* if page by the offset is not ready to be mapped (cold cache or
* something).
*/
if (should_fault_around(vmf)) { ret = do_fault_around(vmf); if (ret)
return ret;
}
ret = vmf_can_call_fault(vmf);
if (ret)
return ret;
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
ret |= finish_fault(vmf);
folio = page_folio(vmf->page);
folio_unlock(folio);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) folio_put(folio);
return ret;
}
static vm_fault_t do_cow_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
vm_fault_t ret;
ret = vmf_can_call_fault(vmf);
if (!ret)
ret = vmf_anon_prepare(vmf); if (ret)
return ret;
folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false);
if (!folio)
return VM_FAULT_OOM;
vmf->cow_page = &folio->page;
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
if (ret & VM_FAULT_DONE_COW)
return ret;
if (copy_mc_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma)) {
ret = VM_FAULT_HWPOISON;
goto unlock;
}
__folio_mark_uptodate(folio);
ret |= finish_fault(vmf);
unlock:
unlock_page(vmf->page);
put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
return ret;
uncharge_out:
folio_put(folio);
return ret;
}
static vm_fault_t do_shared_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret, tmp;
struct folio *folio;
ret = vmf_can_call_fault(vmf);
if (ret)
return ret;
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
folio = page_folio(vmf->page);
/*
* Check if the backing address space wants to know that the page is
* about to become writable
*/
if (vma->vm_ops->page_mkwrite) {
folio_unlock(folio);
tmp = do_page_mkwrite(vmf, folio);
if (unlikely(!tmp ||
(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
folio_put(folio);
return tmp;
}
}
ret |= finish_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
VM_FAULT_RETRY))) {
folio_unlock(folio);
folio_put(folio);
return ret;
}
ret |= fault_dirty_shared_page(vmf);
return ret;
}
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults).
* The mmap_lock may have been released depending on flags and our
* return value. See filemap_fault() and __folio_lock_or_retry().
* If mmap_lock is released, vma may become invalid (for example
* by other thread calling munmap()).
*/
static vm_fault_t do_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *vm_mm = vma->vm_mm;
vm_fault_t ret;
/*
* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
*/
if (!vma->vm_ops->fault) {
vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (unlikely(!vmf->pte))
ret = VM_FAULT_SIGBUS;
else {
/*
* Make sure this is not a temporary clearing of pte
* by holding ptl and checking again. A R/M/W update
* of pte involves: take ptl, clearing the pte so that
* we don't have concurrent modification by hardware
* followed by an update.
*/
if (unlikely(pte_none(ptep_get(vmf->pte))))
ret = VM_FAULT_SIGBUS;
else
ret = VM_FAULT_NOPAGE;
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
} else if (!(vmf->flags & FAULT_FLAG_WRITE))
ret = do_read_fault(vmf);
else if (!(vma->vm_flags & VM_SHARED))
ret = do_cow_fault(vmf);
else
ret = do_shared_fault(vmf);
/* preallocated pagetable is unused: free it */
if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte);
vmf->prealloc_pte = NULL;
}
return ret;
}
int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
unsigned long addr, int *flags,
bool writable, int *last_cpupid)
{
struct vm_area_struct *vma = vmf->vma;
/*
* Avoid grouping on RO pages in general. RO pages shouldn't hurt as
* much anyway since they can be in shared cache state. This misses
* the case where a mapping is writable but the process never writes
* to it but pte_write gets cleared during protection updates and
* pte_dirty has unpredictable behaviour between PTE scan updates,
* background writeback, dirty balancing and application behaviour.
*/
if (!writable)
*flags |= TNF_NO_GROUP;
/*
* Flag if the folio is shared between multiple address spaces. This
* is later used when determining whether to group tasks together
*/
if (folio_maybe_mapped_shared(folio) && (vma->vm_flags & VM_SHARED))
*flags |= TNF_SHARED;
/*
* For memory tiering mode, cpupid of slow memory page is used
* to record page access time. So use default value.
*/
if (folio_use_access_time(folio))
*last_cpupid = (-1 & LAST_CPUPID_MASK);
else
*last_cpupid = folio_last_cpupid(folio);
/* Record the current PID acceesing VMA */
vma_set_access_pid_bit(vma);
count_vm_numa_event(NUMA_HINT_FAULTS);
#ifdef CONFIG_NUMA_BALANCING
count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1);
#endif
if (folio_nid(folio) == numa_node_id()) {
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
*flags |= TNF_FAULT_LOCAL;
}
return mpol_misplaced(folio, vmf, addr);
}
static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma,
unsigned long fault_addr, pte_t *fault_pte,
bool writable)
{
pte_t pte, old_pte;
old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte);
pte = pte_modify(old_pte, vma->vm_page_prot);
pte = pte_mkyoung(pte);
if (writable)
pte = pte_mkwrite(pte, vma);
ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte);
update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1);
}
static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma,
struct folio *folio, pte_t fault_pte,
bool ignore_writable, bool pte_write_upgrade)
{
int nr = pte_pfn(fault_pte) - folio_pfn(folio);
unsigned long start, end, addr = vmf->address;
unsigned long addr_start = addr - (nr << PAGE_SHIFT);
unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE);
pte_t *start_ptep;
/* Stay within the VMA and within the page table. */
start = max3(addr_start, pt_start, vma->vm_start);
end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE,
vma->vm_end);
start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT);
/* Restore all PTEs' mapping of the large folio */
for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { pte_t ptent = ptep_get(start_ptep);
bool writable = false;
if (!pte_present(ptent) || !pte_protnone(ptent))
continue;
if (pfn_folio(pte_pfn(ptent)) != folio)
continue;
if (!ignore_writable) {
ptent = pte_modify(ptent, vma->vm_page_prot);
writable = pte_write(ptent);
if (!writable && pte_write_upgrade && can_change_pte_writable(vma, addr, ptent))
writable = true;
}
numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable);
}
}
static vm_fault_t do_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio = NULL;
int nid = NUMA_NO_NODE;
bool writable = false, ignore_writable = false;
bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma);
int last_cpupid;
int target_nid;
pte_t pte, old_pte;
int flags = 0, nr_pages;
/*
* The pte cannot be used safely until we verify, while holding the page
* table lock, that its contents have not changed during fault handling.
*/
spin_lock(vmf->ptl);
/* Read the live PTE from the page tables: */
old_pte = ptep_get(vmf->pte);
if (unlikely(!pte_same(old_pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
}
pte = pte_modify(old_pte, vma->vm_page_prot);
/*
* Detect now whether the PTE could be writable; this information
* is only valid while holding the PT lock.
*/
writable = pte_write(pte);
if (!writable && pte_write_upgrade && can_change_pte_writable(vma, vmf->address, pte))
writable = true;
folio = vm_normal_folio(vma, vmf->address, pte); if (!folio || folio_is_zone_device(folio))
goto out_map;
nid = folio_nid(folio); nr_pages = folio_nr_pages(folio);
target_nid = numa_migrate_check(folio, vmf, vmf->address, &flags,
writable, &last_cpupid);
if (target_nid == NUMA_NO_NODE)
goto out_map;
if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
flags |= TNF_MIGRATE_FAIL;
goto out_map;
}
/* The folio is isolated and isolation code holds a folio reference. */
pte_unmap_unlock(vmf->pte, vmf->ptl);
writable = false;
ignore_writable = true;
/* Migrate to the requested node */
if (!migrate_misplaced_folio(folio, target_nid)) {
nid = target_nid;
flags |= TNF_MIGRATED;
task_numa_fault(last_cpupid, nid, nr_pages, flags);
return 0;
}
flags |= TNF_MIGRATE_FAIL;
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (unlikely(!vmf->pte))
return 0;
if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
}
out_map:
/*
* Make it present again, depending on how arch implements
* non-accessible ptes, some can allow access by kernel mode.
*/
if (folio && folio_test_large(folio)) numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable,
pte_write_upgrade);
else
numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte,
writable);
pte_unmap_unlock(vmf->pte, vmf->ptl); if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, nr_pages, flags);
return 0;
}
static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
if (vma_is_anonymous(vma))
return do_huge_pmd_anonymous_page(vmf); if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
return VM_FAULT_FALLBACK;
}
/* `inline' is required to avoid gcc 4.1.2 build error */
static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
vm_fault_t ret;
if (vma_is_anonymous(vma)) {
if (likely(!unshare) &&
userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) {
if (userfaultfd_wp_async(vmf->vma))
goto split;
return handle_userfault(vmf, VM_UFFD_WP);
}
return do_huge_pmd_wp_page(vmf);
}
if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) {
ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
}
}
split:
/* COW or write-notify handled on pte level: split pmd. */
__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
return VM_FAULT_FALLBACK;
}
static vm_fault_t create_huge_pud(struct vm_fault *vmf)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
struct vm_area_struct *vma = vmf->vma;
/* No support for anonymous transparent PUD pages yet */
if (vma_is_anonymous(vma))
return VM_FAULT_FALLBACK;
if (vma->vm_ops->huge_fault)
return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return VM_FAULT_FALLBACK;
}
static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret;
/* No support for anonymous transparent PUD pages yet */
if (vma_is_anonymous(vma))
goto split;
if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
if (vma->vm_ops->huge_fault) {
ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
}
}
split:
/* COW or write-notify not handled on PUD level: split pud.*/
__split_huge_pud(vma, vmf->pud, vmf->address);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
return VM_FAULT_FALLBACK;
}
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
* RISC architectures). The early dirtying is also good on the i386.
*
* There is also a hook called "update_mmu_cache()" that architectures
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
* We enter with non-exclusive mmap_lock (to exclude vma changes, but allow
* concurrent faults).
*
* The mmap_lock may have been released depending on flags and our return value.
* See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
{
pte_t entry;
if (unlikely(pmd_none(*vmf->pmd))) {
/*
* Leave __pte_alloc() until later: because vm_ops->fault may
* want to allocate huge page, and if we expose page table
* for an instant, it will be difficult to retract from
* concurrent faults and from rmap lookups.
*/
vmf->pte = NULL;
vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID;
} else {
pmd_t dummy_pmdval;
/*
* A regular pmd is established and it can't morph into a huge
* pmd by anon khugepaged, since that takes mmap_lock in write
* mode; but shmem or file collapse to THP could still morph
* it into a huge pmd: just retry later if so.
*
* Use the maywrite version to indicate that vmf->pte may be
* modified, but since we will use pte_same() to detect the
* change of the !pte_none() entry, there is no need to recheck
* the pmdval. Here we chooes to pass a dummy variable instead
* of NULL, which helps new user think about why this place is
* special.
*/
vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd,
vmf->address, &dummy_pmdval,
&vmf->ptl);
if (unlikely(!vmf->pte))
return 0;
vmf->orig_pte = ptep_get_lockless(vmf->pte);
vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID;
if (pte_none(vmf->orig_pte)) {
pte_unmap(vmf->pte);
vmf->pte = NULL;
}
} if (!vmf->pte) return do_pte_missing(vmf);
if (!pte_present(vmf->orig_pte))
return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf);
spin_lock(vmf->ptl);
entry = vmf->orig_pte;
if (unlikely(!pte_same(ptep_get(vmf->pte), entry))) {
update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
goto unlock;
}
if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
if (!pte_write(entry))
return do_wp_page(vmf); else if (likely(vmf->flags & FAULT_FLAG_WRITE))
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
vmf->flags & FAULT_FLAG_WRITE)) {
update_mmu_cache_range(vmf, vmf->vma, vmf->address,
vmf->pte, 1);
} else {
/* Skip spurious TLB flush for retried page fault */
if (vmf->flags & FAULT_FLAG_TRIED)
goto unlock;
/*
* This is needed only for protection faults but the arch code
* is not yet telling us if this is a protection fault or not.
* This still avoids useless tlb flushes for .text page faults
* with threads.
*/
if (vmf->flags & FAULT_FLAG_WRITE)
flush_tlb_fix_spurious_fault(vmf->vma, vmf->address,
vmf->pte);
}
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
}
/*
* On entry, we hold either the VMA lock or the mmap_lock
* (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in
* the result, the mmap_lock is not held on exit. See filemap_fault()
* and __folio_lock_or_retry().
*/
static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
struct vm_fault vmf = {
.vma = vma,
.address = address & PAGE_MASK,
.real_address = address,
.flags = flags,
.pgoff = linear_page_index(vma, address),
.gfp_mask = __get_fault_gfp_mask(vma),
};
struct mm_struct *mm = vma->vm_mm;
unsigned long vm_flags = vma->vm_flags;
pgd_t *pgd;
p4d_t *p4d;
vm_fault_t ret;
pgd = pgd_offset(mm, address);
p4d = p4d_alloc(mm, pgd, address); if (!p4d)
return VM_FAULT_OOM;
vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud)
return VM_FAULT_OOM;
retry_pud:
if (pud_none(*vmf.pud) && thp_vma_allowable_order(vma, vm_flags,
TVA_IN_PF | TVA_ENFORCE_SYSFS, PUD_ORDER)) {
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
pud_t orig_pud = *vmf.pud;
barrier();
if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
/*
* TODO once we support anonymous PUDs: NUMA case and
* FAULT_FLAG_UNSHARE handling.
*/
if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) {
ret = wp_huge_pud(&vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
huge_pud_set_accessed(&vmf, orig_pud);
return 0;
}
}
}
vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd)
return VM_FAULT_OOM;
/* Huge pud page fault raced with pmd_alloc? */
if (pud_trans_unstable(vmf.pud))
goto retry_pud;
if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags,
TVA_IN_PF | TVA_ENFORCE_SYSFS, PMD_ORDER)) {
ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(vmf.orig_pmd));
if (is_pmd_migration_entry(vmf.orig_pmd))
pmd_migration_entry_wait(mm, vmf.pmd);
return 0;
}
if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf);
if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
!pmd_write(vmf.orig_pmd)) {
ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
huge_pmd_set_accessed(&vmf);
return 0;
}
}
}
return handle_pte_fault(&vmf);
}
/**
* mm_account_fault - Do page fault accounting
* @mm: mm from which memcg should be extracted. It can be NULL.
* @regs: the pt_regs struct pointer. When set to NULL, will skip accounting
* of perf event counters, but we'll still do the per-task accounting to
* the task who triggered this page fault.
* @address: the faulted address.
* @flags: the fault flags.
* @ret: the fault retcode.
*
* This will take care of most of the page fault accounting. Meanwhile, it
* will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
* updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
* still be in per-arch page fault handlers at the entry of page fault.
*/
static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs,
unsigned long address, unsigned int flags,
vm_fault_t ret)
{
bool major;
/* Incomplete faults will be accounted upon completion. */
if (ret & VM_FAULT_RETRY)
return;
/*
* To preserve the behavior of older kernels, PGFAULT counters record
* both successful and failed faults, as opposed to perf counters,
* which ignore failed cases.
*/
count_vm_event(PGFAULT);
count_memcg_event_mm(mm, PGFAULT);
/*
* Do not account for unsuccessful faults (e.g. when the address wasn't
* valid). That includes arch_vma_access_permitted() failing before
* reaching here. So this is not a "this many hardware page faults"
* counter. We should use the hw profiling for that.
*/
if (ret & VM_FAULT_ERROR)
return;
/*
* We define the fault as a major fault when the final successful fault
* is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
* handle it immediately previously).
*/
major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
if (major)
current->maj_flt++;
else
current->min_flt++;
/*
* If the fault is done for GUP, regs will be NULL. We only do the
* accounting for the per thread fault counters who triggered the
* fault, and we skip the perf event updates.
*/
if (!regs)
return;
if (major)
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
else
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
}
#ifdef CONFIG_LRU_GEN
static void lru_gen_enter_fault(struct vm_area_struct *vma)
{
/* the LRU algorithm only applies to accesses with recency */
current->in_lru_fault = vma_has_recency(vma);
}
static void lru_gen_exit_fault(void)
{
current->in_lru_fault = false;
}
#else
static void lru_gen_enter_fault(struct vm_area_struct *vma)
{
}
static void lru_gen_exit_fault(void)
{
}
#endif /* CONFIG_LRU_GEN */
static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma,
unsigned int *flags)
{
if (unlikely(*flags & FAULT_FLAG_UNSHARE)) {
if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE))
return VM_FAULT_SIGSEGV;
/*
* FAULT_FLAG_UNSHARE only applies to COW mappings. Let's
* just treat it like an ordinary read-fault otherwise.
*/
if (!is_cow_mapping(vma->vm_flags))
*flags &= ~FAULT_FLAG_UNSHARE;
} else if (*flags & FAULT_FLAG_WRITE) {
/* Write faults on read-only mappings are impossible ... */
if (WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE)))
return VM_FAULT_SIGSEGV;
/* ... and FOLL_FORCE only applies to COW mappings. */
if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE) &&
!is_cow_mapping(vma->vm_flags)))
return VM_FAULT_SIGSEGV;
}
#ifdef CONFIG_PER_VMA_LOCK
/*
* Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of
* the assumption that lock is dropped on VM_FAULT_RETRY.
*/
if (WARN_ON_ONCE((*flags &
(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) ==
(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)))
return VM_FAULT_SIGSEGV;
#endif
return 0;
}
/*
* By the time we get here, we already hold either the VMA lock or the
* mmap_lock (FAULT_FLAG_VMA_LOCK tells you which).
*
* The mmap_lock may have been released depending on flags and our
* return value. See filemap_fault() and __folio_lock_or_retry().
*/
vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
unsigned int flags, struct pt_regs *regs)
{
/* If the fault handler drops the mmap_lock, vma may be freed */
struct mm_struct *mm = vma->vm_mm;
vm_fault_t ret;
bool is_droppable;
__set_current_state(TASK_RUNNING); ret = sanitize_fault_flags(vma, &flags);
if (ret)
goto out;
if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
flags & FAULT_FLAG_INSTRUCTION,
flags & FAULT_FLAG_REMOTE)) {
ret = VM_FAULT_SIGSEGV;
goto out;
}
is_droppable = !!(vma->vm_flags & VM_DROPPABLE);
/*
* Enable the memcg OOM handling for faults triggered in user
* space. Kernel faults are handled more gracefully.
*/
if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); lru_gen_enter_fault(vma);
if (unlikely(is_vm_hugetlb_page(vma)))
ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
else
ret = __handle_mm_fault(vma, address, flags);
/*
* Warning: It is no longer safe to dereference vma-> after this point,
* because mmap_lock might have been dropped by __handle_mm_fault(), so
* vma might be destroyed from underneath us.
*/
lru_gen_exit_fault();
/* If the mapping is droppable, then errors due to OOM aren't fatal. */
if (is_droppable)
ret &= ~VM_FAULT_OOM;
if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault();
/*
* The task may have entered a memcg OOM situation but
* if the allocation error was handled gracefully (no
* VM_FAULT_OOM), there is no need to kill anything.
* Just clean up the OOM state peacefully.
*/
if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false);
}
out:
mm_account_fault(mm, regs, address, flags, ret);
return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
#ifdef CONFIG_LOCK_MM_AND_FIND_VMA
#include <linux/extable.h>
static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs)
{
if (likely(mmap_read_trylock(mm)))
return true;
if (regs && !user_mode(regs)) {
unsigned long ip = exception_ip(regs);
if (!search_exception_tables(ip))
return false;
}
return !mmap_read_lock_killable(mm);
}
static inline bool mmap_upgrade_trylock(struct mm_struct *mm)
{
/*
* We don't have this operation yet.
*
* It should be easy enough to do: it's basically a
* atomic_long_try_cmpxchg_acquire()
* from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but
* it also needs the proper lockdep magic etc.
*/
return false;
}
static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs)
{ mmap_read_unlock(mm); if (regs && !user_mode(regs)) {
unsigned long ip = exception_ip(regs);
if (!search_exception_tables(ip))
return false;
}
return !mmap_write_lock_killable(mm);
}
/*
* Helper for page fault handling.
*
* This is kind of equivalent to "mmap_read_lock()" followed
* by "find_extend_vma()", except it's a lot more careful about
* the locking (and will drop the lock on failure).
*
* For example, if we have a kernel bug that causes a page
* fault, we don't want to just use mmap_read_lock() to get
* the mm lock, because that would deadlock if the bug were
* to happen while we're holding the mm lock for writing.
*
* So this checks the exception tables on kernel faults in
* order to only do this all for instructions that are actually
* expected to fault.
*
* We can also actually take the mm lock for writing if we
* need to extend the vma, which helps the VM layer a lot.
*/
struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
unsigned long addr, struct pt_regs *regs)
{
struct vm_area_struct *vma;
if (!get_mmap_lock_carefully(mm, regs))
return NULL;
vma = find_vma(mm, addr);
if (likely(vma && (vma->vm_start <= addr)))
return vma;
/*
* Well, dang. We might still be successful, but only
* if we can extend a vma to do so.
*/
if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) {
mmap_read_unlock(mm);
return NULL;
}
/*
* We can try to upgrade the mmap lock atomically,
* in which case we can continue to use the vma
* we already looked up.
*
* Otherwise we'll have to drop the mmap lock and
* re-take it, and also look up the vma again,
* re-checking it.
*/
if (!mmap_upgrade_trylock(mm)) {
if (!upgrade_mmap_lock_carefully(mm, regs))
return NULL;
vma = find_vma(mm, addr);
if (!vma)
goto fail;
if (vma->vm_start <= addr)
goto success;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto fail;
}
if (expand_stack_locked(vma, addr))
goto fail;
success:
mmap_write_downgrade(mm);
return vma;
fail:
mmap_write_unlock(mm);
return NULL;
}
#endif
#ifdef CONFIG_PER_VMA_LOCK
static inline bool __vma_enter_locked(struct vm_area_struct *vma, bool detaching)
{
unsigned int tgt_refcnt = VMA_LOCK_OFFSET;
/* Additional refcnt if the vma is attached. */
if (!detaching)
tgt_refcnt++;
/*
* If vma is detached then only vma_mark_attached() can raise the
* vm_refcnt. mmap_write_lock prevents racing with vma_mark_attached().
*/
if (!refcount_add_not_zero(VMA_LOCK_OFFSET, &vma->vm_refcnt))
return false;
rwsem_acquire(&vma->vmlock_dep_map, 0, 0, _RET_IP_);
rcuwait_wait_event(&vma->vm_mm->vma_writer_wait,
refcount_read(&vma->vm_refcnt) == tgt_refcnt,
TASK_UNINTERRUPTIBLE);
lock_acquired(&vma->vmlock_dep_map, _RET_IP_);
return true;
}
static inline void __vma_exit_locked(struct vm_area_struct *vma, bool *detached)
{
*detached = refcount_sub_and_test(VMA_LOCK_OFFSET, &vma->vm_refcnt);
rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
}
void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
{
bool locked;
/*
* __vma_enter_locked() returns false immediately if the vma is not
* attached, otherwise it waits until refcnt is indicating that vma
* is attached with no readers.
*/
locked = __vma_enter_locked(vma, false);
/*
* We should use WRITE_ONCE() here because we can have concurrent reads
* from the early lockless pessimistic check in vma_start_read().
* We don't really care about the correctness of that early check, but
* we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
*/
WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
if (locked) {
bool detached;
__vma_exit_locked(vma, &detached);
WARN_ON_ONCE(detached); /* vma should remain attached */
}
}
EXPORT_SYMBOL_GPL(__vma_start_write);
void vma_mark_detached(struct vm_area_struct *vma)
{ vma_assert_write_locked(vma); vma_assert_attached(vma);
/*
* We are the only writer, so no need to use vma_refcount_put().
* The condition below is unlikely because the vma has been already
* write-locked and readers can increment vm_refcnt only temporarily
* before they check vm_lock_seq, realize the vma is locked and drop
* back the vm_refcnt. That is a narrow window for observing a raised
* vm_refcnt.
*/
if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
/* Wait until vma is detached with no readers. */
if (__vma_enter_locked(vma, true)) {
bool detached;
__vma_exit_locked(vma, &detached);
WARN_ON_ONCE(!detached);
}
}
}
/*
* Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be
* stable and not isolated. If the VMA is not found or is being modified the
* function returns NULL.
*/
struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
unsigned long address)
{
MA_STATE(mas, &mm->mm_mt, address, address);
struct vm_area_struct *vma;
rcu_read_lock();
retry:
vma = mas_walk(&mas);
if (!vma)
goto inval;
vma = vma_start_read(mm, vma); if (IS_ERR_OR_NULL(vma)) {
/* Check if the VMA got isolated after we found it */
if (PTR_ERR(vma) == -EAGAIN) {
count_vm_vma_lock_event(VMA_LOCK_MISS);
/* The area was replaced with another one */
goto retry;
}
/* Failed to lock the VMA */
goto inval;
}
/*
* At this point, we have a stable reference to a VMA: The VMA is
* locked and we know it hasn't already been isolated.
* From here on, we can access the VMA without worrying about which
* fields are accessible for RCU readers.
*/
/* Check if the vma we locked is the right one. */
if (unlikely(vma->vm_mm != mm ||
address < vma->vm_start || address >= vma->vm_end))
goto inval_end_read;
rcu_read_unlock();
return vma;
inval_end_read:
vma_end_read(vma);
inval:
rcu_read_unlock();
count_vm_vma_lock_event(VMA_LOCK_ABORT);
return NULL;
}
#endif /* CONFIG_PER_VMA_LOCK */
#ifndef __PAGETABLE_P4D_FOLDED
/*
* Allocate p4d page table.
* We've already handled the fast-path in-line.
*/
int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
p4d_t *new = p4d_alloc_one(mm, address);
if (!new)
return -ENOMEM;
spin_lock(&mm->page_table_lock);
if (pgd_present(*pgd)) { /* Another has populated it */
p4d_free(mm, new);
} else {
smp_wmb(); /* See comment in pmd_install() */
pgd_populate(mm, pgd, new);
}
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_P4D_FOLDED */
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
* We've already handled the fast-path in-line.
*/
int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
{
pud_t *new = pud_alloc_one(mm, address);
if (!new)
return -ENOMEM;
spin_lock(&mm->page_table_lock);
if (!p4d_present(*p4d)) {
mm_inc_nr_puds(mm);
smp_wmb(); /* See comment in pmd_install() */
p4d_populate(mm, p4d, new);
} else /* Another has populated it */
pud_free(mm, new);
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Allocate page middle directory.
* We've already handled the fast-path in-line.
*/
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
spinlock_t *ptl;
pmd_t *new = pmd_alloc_one(mm, address);
if (!new)
return -ENOMEM;
ptl = pud_lock(mm, pud);
if (!pud_present(*pud)) {
mm_inc_nr_pmds(mm);
smp_wmb(); /* See comment in pmd_install() */
pud_populate(mm, pud, new);
} else { /* Another has populated it */
pmd_free(mm, new);
}
spin_unlock(ptl);
return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */
static inline void pfnmap_args_setup(struct follow_pfnmap_args *args,
spinlock_t *lock, pte_t *ptep,
pgprot_t pgprot, unsigned long pfn_base,
unsigned long addr_mask, bool writable,
bool special)
{
args->lock = lock;
args->ptep = ptep;
args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT);
args->addr_mask = addr_mask;
args->pgprot = pgprot;
args->writable = writable;
args->special = special;
}
static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma)
{
#ifdef CONFIG_LOCKDEP
struct file *file = vma->vm_file;
struct address_space *mapping = file ? file->f_mapping : NULL;
if (mapping)
lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) ||
lockdep_is_held(&vma->vm_mm->mmap_lock));
else
lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock));
#endif
}
/**
* follow_pfnmap_start() - Look up a pfn mapping at a user virtual address
* @args: Pointer to struct @follow_pfnmap_args
*
* The caller needs to setup args->vma and args->address to point to the
* virtual address as the target of such lookup. On a successful return,
* the results will be put into other output fields.
*
* After the caller finished using the fields, the caller must invoke
* another follow_pfnmap_end() to proper releases the locks and resources
* of such look up request.
*
* During the start() and end() calls, the results in @args will be valid
* as proper locks will be held. After the end() is called, all the fields
* in @follow_pfnmap_args will be invalid to be further accessed. Further
* use of such information after end() may require proper synchronizations
* by the caller with page table updates, otherwise it can create a
* security bug.
*
* If the PTE maps a refcounted page, callers are responsible to protect
* against invalidation with MMU notifiers; otherwise access to the PFN at
* a later point in time can trigger use-after-free.
*
* Only IO mappings and raw PFN mappings are allowed. The mmap semaphore
* should be taken for read, and the mmap semaphore cannot be released
* before the end() is invoked.
*
* This function must not be used to modify PTE content.
*
* Return: zero on success, negative otherwise.
*/
int follow_pfnmap_start(struct follow_pfnmap_args *args)
{
struct vm_area_struct *vma = args->vma;
unsigned long address = args->address;
struct mm_struct *mm = vma->vm_mm;
spinlock_t *lock;
pgd_t *pgdp;
p4d_t *p4dp, p4d;
pud_t *pudp, pud;
pmd_t *pmdp, pmd;
pte_t *ptep, pte;
pfnmap_lockdep_assert(vma);
if (unlikely(address < vma->vm_start || address >= vma->vm_end))
goto out;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
goto out;
retry:
pgdp = pgd_offset(mm, address);
if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
goto out;
p4dp = p4d_offset(pgdp, address);
p4d = READ_ONCE(*p4dp);
if (p4d_none(p4d) || unlikely(p4d_bad(p4d)))
goto out;
pudp = pud_offset(p4dp, address);
pud = READ_ONCE(*pudp);
if (pud_none(pud))
goto out;
if (pud_leaf(pud)) {
lock = pud_lock(mm, pudp);
if (!unlikely(pud_leaf(pud))) {
spin_unlock(lock);
goto retry;
}
pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud),
pud_pfn(pud), PUD_MASK, pud_write(pud),
pud_special(pud));
return 0;
}
pmdp = pmd_offset(pudp, address);
pmd = pmdp_get_lockless(pmdp);
if (pmd_leaf(pmd)) {
lock = pmd_lock(mm, pmdp);
if (!unlikely(pmd_leaf(pmd))) {
spin_unlock(lock);
goto retry;
}
pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd),
pmd_pfn(pmd), PMD_MASK, pmd_write(pmd),
pmd_special(pmd));
return 0;
}
ptep = pte_offset_map_lock(mm, pmdp, address, &lock);
if (!ptep)
goto out;
pte = ptep_get(ptep);
if (!pte_present(pte))
goto unlock;
pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte),
pte_pfn(pte), PAGE_MASK, pte_write(pte),
pte_special(pte));
return 0;
unlock:
pte_unmap_unlock(ptep, lock);
out:
return -EINVAL;
}
EXPORT_SYMBOL_GPL(follow_pfnmap_start);
/**
* follow_pfnmap_end(): End a follow_pfnmap_start() process
* @args: Pointer to struct @follow_pfnmap_args
*
* Must be used in pair of follow_pfnmap_start(). See the start() function
* above for more information.
*/
void follow_pfnmap_end(struct follow_pfnmap_args *args)
{
if (args->lock)
spin_unlock(args->lock);
if (args->ptep)
pte_unmap(args->ptep);
}
EXPORT_SYMBOL_GPL(follow_pfnmap_end);
#ifdef CONFIG_HAVE_IOREMAP_PROT
/**
* generic_access_phys - generic implementation for iomem mmap access
* @vma: the vma to access
* @addr: userspace address, not relative offset within @vma
* @buf: buffer to read/write
* @len: length of transfer
* @write: set to FOLL_WRITE when writing, otherwise reading
*
* This is a generic implementation for &vm_operations_struct.access for an
* iomem mapping. This callback is used by access_process_vm() when the @vma is
* not page based.
*/
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write)
{
resource_size_t phys_addr;
pgprot_t prot = __pgprot(0);
void __iomem *maddr;
int offset = offset_in_page(addr);
int ret = -EINVAL;
bool writable;
struct follow_pfnmap_args args = { .vma = vma, .address = addr };
retry:
if (follow_pfnmap_start(&args))
return -EINVAL;
prot = args.pgprot;
phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT;
writable = args.writable;
follow_pfnmap_end(&args);
if ((write & FOLL_WRITE) && !writable)
return -EINVAL;
maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
if (!maddr)
return -ENOMEM;
if (follow_pfnmap_start(&args))
goto out_unmap;
if ((pgprot_val(prot) != pgprot_val(args.pgprot)) ||
(phys_addr != (args.pfn << PAGE_SHIFT)) ||
(writable != args.writable)) {
follow_pfnmap_end(&args);
iounmap(maddr);
goto retry;
}
if (write)
memcpy_toio(maddr + offset, buf, len);
else
memcpy_fromio(buf, maddr + offset, len);
ret = len;
follow_pfnmap_end(&args);
out_unmap:
iounmap(maddr);
return ret;
}
EXPORT_SYMBOL_GPL(generic_access_phys);
#endif
/*
* Access another process' address space as given in mm.
*/
static int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
void *old_buf = buf;
int write = gup_flags & FOLL_WRITE;
if (mmap_read_lock_killable(mm))
return 0;
/* Untag the address before looking up the VMA */
addr = untagged_addr_remote(mm, addr);
/* Avoid triggering the temporary warning in __get_user_pages */
if (!vma_lookup(mm, addr) && !expand_stack(mm, addr))
return 0;
/* ignore errors, just check how much was successfully transferred */
while (len) {
int bytes, offset;
void *maddr;
struct vm_area_struct *vma = NULL;
struct page *page = get_user_page_vma_remote(mm, addr,
gup_flags, &vma);
if (IS_ERR(page)) {
/* We might need to expand the stack to access it */
vma = vma_lookup(mm, addr);
if (!vma) {
vma = expand_stack(mm, addr);
/* mmap_lock was dropped on failure */
if (!vma)
return buf - old_buf;
/* Try again if stack expansion worked */
continue;
}
/*
* Check if this is a VM_IO | VM_PFNMAP VMA, which
* we can access using slightly different code.
*/
bytes = 0;
#ifdef CONFIG_HAVE_IOREMAP_PROT
if (vma->vm_ops && vma->vm_ops->access)
bytes = vma->vm_ops->access(vma, addr, buf,
len, write);
#endif
if (bytes <= 0)
break;
} else {
bytes = len;
offset = addr & (PAGE_SIZE-1);
if (bytes > PAGE_SIZE-offset)
bytes = PAGE_SIZE-offset;
maddr = kmap_local_page(page);
if (write) {
copy_to_user_page(vma, page, addr,
maddr + offset, buf, bytes);
set_page_dirty_lock(page);
} else {
copy_from_user_page(vma, page, addr,
buf, maddr + offset, bytes);
}
unmap_and_put_page(page, maddr);
}
len -= bytes;
buf += bytes;
addr += bytes;
}
mmap_read_unlock(mm);
return buf - old_buf;
}
/**
* access_remote_vm - access another process' address space
* @mm: the mm_struct of the target address space
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
* @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*
* Return: number of bytes copied from source to destination.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
return __access_remote_vm(mm, addr, buf, len, gup_flags);
}
/*
* Access another process' address space.
* Source/target buffer must be kernel space,
* Do not walk the page table directly, use get_user_pages
*/
int access_process_vm(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
struct mm_struct *mm;
int ret;
mm = get_task_mm(tsk);
if (!mm)
return 0;
ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
mmput(mm);
return ret;
}
EXPORT_SYMBOL_GPL(access_process_vm);
#ifdef CONFIG_BPF_SYSCALL
/*
* Copy a string from another process's address space as given in mm.
* If there is any error return -EFAULT.
*/
static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
void *old_buf = buf;
int err = 0;
*(char *)buf = '\0';
if (mmap_read_lock_killable(mm))
return -EFAULT;
addr = untagged_addr_remote(mm, addr);
/* Avoid triggering the temporary warning in __get_user_pages */
if (!vma_lookup(mm, addr)) {
err = -EFAULT;
goto out;
}
while (len) {
int bytes, offset, retval;
void *maddr;
struct page *page;
struct vm_area_struct *vma = NULL;
page = get_user_page_vma_remote(mm, addr, gup_flags, &vma);
if (IS_ERR(page)) {
/*
* Treat as a total failure for now until we decide how
* to handle the CONFIG_HAVE_IOREMAP_PROT case and
* stack expansion.
*/
*(char *)buf = '\0';
err = -EFAULT;
goto out;
}
bytes = len;
offset = addr & (PAGE_SIZE - 1);
if (bytes > PAGE_SIZE - offset)
bytes = PAGE_SIZE - offset;
maddr = kmap_local_page(page);
retval = strscpy(buf, maddr + offset, bytes);
if (retval >= 0) {
/* Found the end of the string */
buf += retval;
unmap_and_put_page(page, maddr);
break;
}
buf += bytes - 1;
/*
* Because strscpy always NUL terminates we need to
* copy the last byte in the page if we are going to
* load more pages
*/
if (bytes != len) {
addr += bytes - 1;
copy_from_user_page(vma, page, addr, buf, maddr + (PAGE_SIZE - 1), 1);
buf += 1;
addr += 1;
}
len -= bytes;
unmap_and_put_page(page, maddr);
}
out:
mmap_read_unlock(mm);
if (err)
return err;
return buf - old_buf;
}
/**
* copy_remote_vm_str - copy a string from another process's address space.
* @tsk: the task of the target address space
* @addr: start address to read from
* @buf: destination buffer
* @len: number of bytes to copy
* @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*
* Return: number of bytes copied from @addr (source) to @buf (destination);
* not including the trailing NUL. Always guaranteed to leave NUL-terminated
* buffer. On any error, return -EFAULT.
*/
int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
struct mm_struct *mm;
int ret;
if (unlikely(len == 0))
return 0;
mm = get_task_mm(tsk);
if (!mm) {
*(char *)buf = '\0';
return -EFAULT;
}
ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags);
mmput(mm);
return ret;
}
EXPORT_SYMBOL_GPL(copy_remote_vm_str);
#endif /* CONFIG_BPF_SYSCALL */
/*
* Print the name of a VMA.
*/
void print_vma_addr(char *prefix, unsigned long ip)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
/*
* we might be running from an atomic context so we cannot sleep
*/
if (!mmap_read_trylock(mm))
return;
vma = vma_lookup(mm, ip);
if (vma && vma->vm_file) {
struct file *f = vma->vm_file;
ip -= vma->vm_start;
ip += vma->vm_pgoff << PAGE_SHIFT;
printk("%s%pD[%lx,%lx+%lx]", prefix, f, ip,
vma->vm_start,
vma->vm_end - vma->vm_start);
}
mmap_read_unlock(mm);
}
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
void __might_fault(const char *file, int line)
{ if (pagefault_disabled())
return;
__might_sleep(file, line);
if (current->mm) might_lock_read(¤t->mm->mmap_lock);
}
EXPORT_SYMBOL(__might_fault);
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
/*
* Process all subpages of the specified huge page with the specified
* operation. The target subpage will be processed last to keep its
* cache lines hot.
*/
static inline int process_huge_page(
unsigned long addr_hint, unsigned int nr_pages,
int (*process_subpage)(unsigned long addr, int idx, void *arg),
void *arg)
{
int i, n, base, l, ret;
unsigned long addr = addr_hint &
~(((unsigned long)nr_pages << PAGE_SHIFT) - 1);
/* Process target subpage last to keep its cache lines hot */
might_sleep();
n = (addr_hint - addr) / PAGE_SIZE;
if (2 * n <= nr_pages) {
/* If target subpage in first half of huge page */
base = 0;
l = n;
/* Process subpages at the end of huge page */
for (i = nr_pages - 1; i >= 2 * n; i--) {
cond_resched();
ret = process_subpage(addr + i * PAGE_SIZE, i, arg);
if (ret)
return ret;
}
} else {
/* If target subpage in second half of huge page */
base = nr_pages - 2 * (nr_pages - n);
l = nr_pages - n;
/* Process subpages at the begin of huge page */
for (i = 0; i < base; i++) {
cond_resched();
ret = process_subpage(addr + i * PAGE_SIZE, i, arg);
if (ret)
return ret;
}
}
/*
* Process remaining subpages in left-right-left-right pattern
* towards the target subpage
*/
for (i = 0; i < l; i++) {
int left_idx = base + i;
int right_idx = base + 2 * l - 1 - i;
cond_resched();
ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg);
if (ret)
return ret;
cond_resched();
ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg);
if (ret)
return ret;
}
return 0;
}
static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint,
unsigned int nr_pages)
{
unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio));
int i;
might_sleep();
for (i = 0; i < nr_pages; i++) {
cond_resched();
clear_user_highpage(folio_page(folio, i), addr + i * PAGE_SIZE);
}
}
static int clear_subpage(unsigned long addr, int idx, void *arg)
{
struct folio *folio = arg;
clear_user_highpage(folio_page(folio, idx), addr);
return 0;
}
/**
* folio_zero_user - Zero a folio which will be mapped to userspace.
* @folio: The folio to zero.
* @addr_hint: The address will be accessed or the base address if uncelar.
*/
void folio_zero_user(struct folio *folio, unsigned long addr_hint)
{
unsigned int nr_pages = folio_nr_pages(folio); if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) clear_gigantic_page(folio, addr_hint, nr_pages);
else
process_huge_page(addr_hint, nr_pages, clear_subpage, folio);
}
static int copy_user_gigantic_page(struct folio *dst, struct folio *src,
unsigned long addr_hint,
struct vm_area_struct *vma,
unsigned int nr_pages)
{
unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst));
struct page *dst_page;
struct page *src_page;
int i;
for (i = 0; i < nr_pages; i++) {
dst_page = folio_page(dst, i);
src_page = folio_page(src, i);
cond_resched();
if (copy_mc_user_highpage(dst_page, src_page,
addr + i*PAGE_SIZE, vma))
return -EHWPOISON;
}
return 0;
}
struct copy_subpage_arg {
struct folio *dst;
struct folio *src;
struct vm_area_struct *vma;
};
static int copy_subpage(unsigned long addr, int idx, void *arg)
{
struct copy_subpage_arg *copy_arg = arg;
struct page *dst = folio_page(copy_arg->dst, idx);
struct page *src = folio_page(copy_arg->src, idx);
if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma))
return -EHWPOISON;
return 0;
}
int copy_user_large_folio(struct folio *dst, struct folio *src,
unsigned long addr_hint, struct vm_area_struct *vma)
{
unsigned int nr_pages = folio_nr_pages(dst);
struct copy_subpage_arg arg = {
.dst = dst,
.src = src,
.vma = vma,
};
if (unlikely(nr_pages > MAX_ORDER_NR_PAGES))
return copy_user_gigantic_page(dst, src, addr_hint, vma, nr_pages);
return process_huge_page(addr_hint, nr_pages, copy_subpage, &arg);
}
long copy_folio_from_user(struct folio *dst_folio,
const void __user *usr_src,
bool allow_pagefault)
{
void *kaddr;
unsigned long i, rc = 0;
unsigned int nr_pages = folio_nr_pages(dst_folio);
unsigned long ret_val = nr_pages * PAGE_SIZE;
struct page *subpage;
for (i = 0; i < nr_pages; i++) {
subpage = folio_page(dst_folio, i);
kaddr = kmap_local_page(subpage);
if (!allow_pagefault)
pagefault_disable();
rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE);
if (!allow_pagefault)
pagefault_enable();
kunmap_local(kaddr);
ret_val -= (PAGE_SIZE - rc);
if (rc)
break;
flush_dcache_page(subpage);
cond_resched();
}
return ret_val;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS
static struct kmem_cache *page_ptl_cachep;
void __init ptlock_cache_init(void)
{
page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
SLAB_PANIC, NULL);
}
bool ptlock_alloc(struct ptdesc *ptdesc)
{
spinlock_t *ptl;
ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!ptl)
return false;
ptdesc->ptl = ptl;
return true;
}
void ptlock_free(struct ptdesc *ptdesc)
{
if (ptdesc->ptl) kmem_cache_free(page_ptl_cachep, ptdesc->ptl);
}
#endif
void vma_pgtable_walk_begin(struct vm_area_struct *vma)
{ if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma);
}
void vma_pgtable_walk_end(struct vm_area_struct *vma)
{ if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma);
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org>
* Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2008-2012 Novell Inc.
* Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
* Copyright (c) 2012-2019 Linux Foundation
*
* Core driver model functions and structures that should not be
* shared outside of the drivers/base/ directory.
*
*/
#include <linux/notifier.h>
/**
* struct subsys_private - structure to hold the private to the driver core portions of the bus_type/class structure.
*
* @subsys - the struct kset that defines this subsystem
* @devices_kset - the subsystem's 'devices' directory
* @interfaces - list of subsystem interfaces associated
* @mutex - protect the devices, and interfaces lists.
*
* @drivers_kset - the list of drivers associated
* @klist_devices - the klist to iterate over the @devices_kset
* @klist_drivers - the klist to iterate over the @drivers_kset
* @bus_notifier - the bus notifier list for anything that cares about things
* on this bus.
* @bus - pointer back to the struct bus_type that this structure is associated
* with.
* @dev_root: Default device to use as the parent.
*
* @glue_dirs - "glue" directory to put in-between the parent device to
* avoid namespace conflicts
* @class - pointer back to the struct class that this structure is associated
* with.
* @lock_key: Lock class key for use by the lock validator
*
* This structure is the one that is the actual kobject allowing struct
* bus_type/class to be statically allocated safely. Nothing outside of the
* driver core should ever touch these fields.
*/
struct subsys_private {
struct kset subsys;
struct kset *devices_kset;
struct list_head interfaces;
struct mutex mutex;
struct kset *drivers_kset;
struct klist klist_devices;
struct klist klist_drivers;
struct blocking_notifier_head bus_notifier;
unsigned int drivers_autoprobe:1;
const struct bus_type *bus;
struct device *dev_root;
struct kset glue_dirs;
const struct class *class;
struct lock_class_key lock_key;
};
#define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj)
static inline struct subsys_private *subsys_get(struct subsys_private *sp)
{
if (sp) kset_get(&sp->subsys);
return sp;
}
static inline void subsys_put(struct subsys_private *sp)
{
if (sp)
kset_put(&sp->subsys);
}
struct subsys_private *bus_to_subsys(const struct bus_type *bus);
struct subsys_private *class_to_subsys(const struct class *class);
struct driver_private {
struct kobject kobj;
struct klist klist_devices;
struct klist_node knode_bus;
struct module_kobject *mkobj;
struct device_driver *driver;
};
#define to_driver(obj) container_of(obj, struct driver_private, kobj)
/**
* struct device_private - structure to hold the private to the driver core portions of the device structure.
*
* @klist_children - klist containing all children of this device
* @knode_parent - node in sibling list
* @knode_driver - node in driver list
* @knode_bus - node in bus list
* @knode_class - node in class list
* @deferred_probe - entry in deferred_probe_list which is used to retry the
* binding of drivers which were unable to get all the resources needed by
* the device; typically because it depends on another driver getting
* probed first.
* @async_driver - pointer to device driver awaiting probe via async_probe
* @device - pointer back to the struct device that this structure is
* associated with.
* @dead - This device is currently either in the process of or has been
* removed from the system. Any asynchronous events scheduled for this
* device should exit without taking any action.
*
* Nothing outside of the driver core should ever touch these fields.
*/
struct device_private {
struct klist klist_children;
struct klist_node knode_parent;
struct klist_node knode_driver;
struct klist_node knode_bus;
struct klist_node knode_class;
struct list_head deferred_probe;
const struct device_driver *async_driver;
char *deferred_probe_reason;
struct device *device;
u8 dead:1;
};
#define to_device_private_parent(obj) \
container_of(obj, struct device_private, knode_parent)
#define to_device_private_driver(obj) \
container_of(obj, struct device_private, knode_driver)
#define to_device_private_bus(obj) \
container_of(obj, struct device_private, knode_bus)
#define to_device_private_class(obj) \
container_of(obj, struct device_private, knode_class)
/* initialisation functions */
int devices_init(void);
int buses_init(void);
int classes_init(void);
int firmware_init(void);
#ifdef CONFIG_SYS_HYPERVISOR
int hypervisor_init(void);
#else
static inline int hypervisor_init(void) { return 0; }
#endif
int platform_bus_init(void);
int faux_bus_init(void);
void cpu_dev_init(void);
void container_dev_init(void);
#ifdef CONFIG_AUXILIARY_BUS
void auxiliary_bus_init(void);
#else
static inline void auxiliary_bus_init(void) { }
#endif
struct kobject *virtual_device_parent(void);
int bus_add_device(struct device *dev);
void bus_probe_device(struct device *dev);
void bus_remove_device(struct device *dev);
void bus_notify(struct device *dev, enum bus_notifier_event value);
bool bus_is_registered(const struct bus_type *bus);
int bus_add_driver(struct device_driver *drv);
void bus_remove_driver(struct device_driver *drv);
void device_release_driver_internal(struct device *dev, const struct device_driver *drv,
struct device *parent);
void driver_detach(const struct device_driver *drv);
void driver_deferred_probe_del(struct device *dev);
void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf);
static inline int driver_match_device(const struct device_driver *drv,
struct device *dev)
{
return drv->bus->match ? drv->bus->match(dev, drv) : 1;
}
static inline void dev_sync_state(struct device *dev)
{
if (dev->bus->sync_state)
dev->bus->sync_state(dev);
else if (dev->driver && dev->driver->sync_state)
dev->driver->sync_state(dev);
}
int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups);
void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
void device_driver_detach(struct device *dev);
static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
{
/*
* Majority (all?) read accesses to dev->driver happens either
* while holding device lock or in bus/driver code that is only
* invoked when the device is bound to a driver and there is no
* concern of the pointer being changed while it is being read.
* However when reading device's uevent file we read driver pointer
* without taking device lock (so we do not block there for
* arbitrary amount of time). We use WRITE_ONCE() here to prevent
* tearing so that READ_ONCE() can safely be used in uevent code.
*/
// FIXME - this cast should not be needed "soon"
WRITE_ONCE(dev->driver, (struct device_driver *)drv);
}
int devres_release_all(struct device *dev);
void device_block_probing(void);
void device_unblock_probing(void);
void deferred_probe_extend_timeout(void);
void driver_deferred_probe_trigger(void);
const char *device_get_devnode(const struct device *dev, umode_t *mode,
kuid_t *uid, kgid_t *gid, const char **tmp);
/* /sys/devices directory */
extern struct kset *devices_kset;
void devices_kset_move_last(struct device *dev);
#if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
int module_add_driver(struct module *mod, const struct device_driver *drv);
void module_remove_driver(const struct device_driver *drv);
#else
static inline int module_add_driver(struct module *mod,
struct device_driver *drv)
{
return 0;
}
static inline void module_remove_driver(struct device_driver *drv) { }
#endif
#ifdef CONFIG_DEVTMPFS
int devtmpfs_init(void);
#else
static inline int devtmpfs_init(void) { return 0; }
#endif
#ifdef CONFIG_BLOCK
extern const struct class block_class;
static inline bool is_blockdev(struct device *dev)
{
return dev->class == &block_class;
}
#else
static inline bool is_blockdev(struct device *dev) { return false; }
#endif
/* Device links support */
int device_links_read_lock(void);
void device_links_read_unlock(int idx);
int device_links_read_lock_held(void);
int device_links_check_suppliers(struct device *dev);
void device_links_force_bind(struct device *dev);
void device_links_driver_bound(struct device *dev);
void device_links_driver_cleanup(struct device *dev);
void device_links_no_driver(struct device *dev);
bool device_links_busy(struct device *dev);
void device_links_unbind_consumers(struct device *dev);
void fw_devlink_drivers_done(void);
void fw_devlink_probing_done(void);
/* device pm support */
void device_pm_move_to_tail(struct device *dev);
#ifdef CONFIG_DEVTMPFS
int devtmpfs_create_node(struct device *dev);
int devtmpfs_delete_node(struct device *dev);
#else
static inline int devtmpfs_create_node(struct device *dev) { return 0; }
static inline int devtmpfs_delete_node(struct device *dev) { return 0; }
#endif
void software_node_notify(struct device *dev);
void software_node_notify_remove(struct device *dev);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/mmu.c
*
* Copyright (C) 1995-2005 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/cache.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/kexec.h>
#include <linux/libfdt.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
#include <linux/memremap.h>
#include <linux/memory.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
#include <linux/kfence.h>
#include <linux/pkeys.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <linux/sizes.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/ptdump.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/kfence.h>
#define NO_BLOCK_MAPPINGS BIT(0)
#define NO_CONT_MAPPINGS BIT(1)
#define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 };
static bool rodata_is_rw __ro_after_init = true;
/*
* The booting CPU updates the failed status @__early_cpu_boot_status,
* with MMU turned off.
*/
long __section(".mmuoff.data.write") __early_cpu_boot_status;
/*
* Empty_zero_page is a special page that is used for zero-initialized data
* and COW.
*/
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
static DEFINE_SPINLOCK(swapper_pgdir_lock);
static DEFINE_MUTEX(fixmap_lock);
void noinstr set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
{
pgd_t *fixmap_pgdp;
/*
* Don't bother with the fixmap if swapper_pg_dir is still mapped
* writable in the kernel mapping.
*/
if (rodata_is_rw) {
WRITE_ONCE(*pgdp, pgd);
dsb(ishst);
isb();
return;
}
spin_lock(&swapper_pgdir_lock);
fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp));
WRITE_ONCE(*fixmap_pgdp, pgd);
/*
* We need dsb(ishst) here to ensure the page-table-walker sees
* our new entry before set_p?d() returns. The fixmap's
* flush_tlb_kernel_range() via clear_fixmap() does this for us.
*/
pgd_clear_fixmap();
spin_unlock(&swapper_pgdir_lock);
}
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
if (!pfn_is_map_memory(pfn))
return pgprot_noncached(vma_prot);
else if (file->f_flags & O_SYNC)
return pgprot_writecombine(vma_prot);
return vma_prot;
}
EXPORT_SYMBOL(phys_mem_access_prot);
static phys_addr_t __init early_pgtable_alloc(int shift)
{
phys_addr_t phys;
phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
MEMBLOCK_ALLOC_NOLEAKTRACE);
if (!phys)
panic("Failed to allocate page table page\n");
return phys;
}
bool pgattr_change_is_safe(pteval_t old, pteval_t new)
{
/*
* The following mapping attributes may be updated in live
* kernel mappings without the need for break-before-make.
*/
pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG |
PTE_SWBITS_MASK;
/* creating or taking down mappings is always safe */
if (!pte_valid(__pte(old)) || !pte_valid(__pte(new)))
return true;
/* A live entry's pfn should not change */
if (pte_pfn(__pte(old)) != pte_pfn(__pte(new)))
return false;
/* live contiguous mappings may not be manipulated at all */
if ((old | new) & PTE_CONT)
return false;
/* Transitioning from Non-Global to Global is unsafe */
if (old & ~new & PTE_NG)
return false;
/*
* Changing the memory type between Normal and Normal-Tagged is safe
* since Tagged is considered a permission attribute from the
* mismatched attribute aliases perspective.
*/
if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
(old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
(new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
mask |= PTE_ATTRINDX_MASK;
return ((old ^ new) & ~mask) == 0;
}
static void init_clear_pgtable(void *table)
{
clear_page(table);
/* Ensure the zeroing is observed by page table walks. */
dsb(ishst);
}
static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot)
{
do {
pte_t old_pte = __ptep_get(ptep);
/*
* Required barriers to make this visible to the table walker
* are deferred to the end of alloc_init_cont_pte().
*/
__set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
/*
* After the PTE entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
pte_val(__ptep_get(ptep))));
phys += PAGE_SIZE;
} while (ptep++, addr += PAGE_SIZE, addr != end);
}
static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
pmd_t pmd = READ_ONCE(*pmdp);
pte_t *ptep;
BUG_ON(pmd_sect(pmd));
if (pmd_none(pmd)) {
pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
phys_addr_t pte_phys;
if (flags & NO_EXEC_MAPPINGS)
pmdval |= PMD_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pte_phys = pgtable_alloc(PAGE_SHIFT);
ptep = pte_set_fixmap(pte_phys);
init_clear_pgtable(ptep);
ptep += pte_index(addr);
__pmd_populate(pmdp, pte_phys, pmdval);
} else {
BUG_ON(pmd_bad(pmd));
ptep = pte_set_fixmap_offset(pmdp, addr);
}
do {
pgprot_t __prot = prot;
next = pte_cont_addr_end(addr, end);
/* use a contiguous mapping if the range is suitably aligned */
if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
(flags & NO_CONT_MAPPINGS) == 0)
__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
init_pte(ptep, addr, next, phys, __prot);
ptep += pte_index(next) - pte_index(addr);
phys += next - addr;
} while (addr = next, addr != end);
/*
* Note: barriers and maintenance necessary to clear the fixmap slot
* ensure that all previous pgtable writes are visible to the table
* walker.
*/
pte_clear_fixmap();
}
static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
do {
pmd_t old_pmd = READ_ONCE(*pmdp);
next = pmd_addr_end(addr, end);
/* try section mapping first */
if (((addr | next | phys) & ~PMD_MASK) == 0 &&
(flags & NO_BLOCK_MAPPINGS) == 0) {
pmd_set_huge(pmdp, phys, prot);
/*
* After the PMD entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
READ_ONCE(pmd_val(*pmdp))));
} else {
alloc_init_cont_pte(pmdp, addr, next, phys, prot,
pgtable_alloc, flags);
BUG_ON(pmd_val(old_pmd) != 0 &&
pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
}
phys += next - addr;
} while (pmdp++, addr = next, addr != end);
}
static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
pmd_t *pmdp;
/*
* Check for initial section mappings in the pgd/pud.
*/
BUG_ON(pud_sect(pud));
if (pud_none(pud)) {
pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
phys_addr_t pmd_phys;
if (flags & NO_EXEC_MAPPINGS)
pudval |= PUD_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pmd_phys = pgtable_alloc(PMD_SHIFT);
pmdp = pmd_set_fixmap(pmd_phys);
init_clear_pgtable(pmdp);
pmdp += pmd_index(addr);
__pud_populate(pudp, pmd_phys, pudval);
} else {
BUG_ON(pud_bad(pud));
pmdp = pmd_set_fixmap_offset(pudp, addr);
}
do {
pgprot_t __prot = prot;
next = pmd_cont_addr_end(addr, end);
/* use a contiguous mapping if the range is suitably aligned */
if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
(flags & NO_CONT_MAPPINGS) == 0)
__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
pmdp += pmd_index(next) - pmd_index(addr);
phys += next - addr;
} while (addr = next, addr != end);
pmd_clear_fixmap();
}
static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
p4d_t p4d = READ_ONCE(*p4dp);
pud_t *pudp;
if (p4d_none(p4d)) {
p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN | P4D_TABLE_AF;
phys_addr_t pud_phys;
if (flags & NO_EXEC_MAPPINGS)
p4dval |= P4D_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pud_phys = pgtable_alloc(PUD_SHIFT);
pudp = pud_set_fixmap(pud_phys);
init_clear_pgtable(pudp);
pudp += pud_index(addr);
__p4d_populate(p4dp, pud_phys, p4dval);
} else {
BUG_ON(p4d_bad(p4d));
pudp = pud_set_fixmap_offset(p4dp, addr);
}
do {
pud_t old_pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
/*
* For 4K granule only, attempt to put down a 1GB block
*/
if (pud_sect_supported() &&
((addr | next | phys) & ~PUD_MASK) == 0 &&
(flags & NO_BLOCK_MAPPINGS) == 0) {
pud_set_huge(pudp, phys, prot);
/*
* After the PUD entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
READ_ONCE(pud_val(*pudp))));
} else {
alloc_init_cont_pmd(pudp, addr, next, phys, prot,
pgtable_alloc, flags);
BUG_ON(pud_val(old_pud) != 0 &&
pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
}
phys += next - addr;
} while (pudp++, addr = next, addr != end);
pud_clear_fixmap();
}
static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
pgd_t pgd = READ_ONCE(*pgdp);
p4d_t *p4dp;
if (pgd_none(pgd)) {
pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN | PGD_TABLE_AF;
phys_addr_t p4d_phys;
if (flags & NO_EXEC_MAPPINGS)
pgdval |= PGD_TABLE_PXN;
BUG_ON(!pgtable_alloc);
p4d_phys = pgtable_alloc(P4D_SHIFT);
p4dp = p4d_set_fixmap(p4d_phys);
init_clear_pgtable(p4dp);
p4dp += p4d_index(addr);
__pgd_populate(pgdp, p4d_phys, pgdval);
} else {
BUG_ON(pgd_bad(pgd));
p4dp = p4d_set_fixmap_offset(pgdp, addr);
}
do {
p4d_t old_p4d = READ_ONCE(*p4dp);
next = p4d_addr_end(addr, end);
alloc_init_pud(p4dp, addr, next, phys, prot,
pgtable_alloc, flags);
BUG_ON(p4d_val(old_p4d) != 0 &&
p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp)));
phys += next - addr;
} while (p4dp++, addr = next, addr != end);
p4d_clear_fixmap();
}
static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long addr, end, next;
pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
/*
* If the virtual and physical address don't have the same offset
* within a page, we cannot map the region as the caller expects.
*/
if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
return;
phys &= PAGE_MASK;
addr = virt & PAGE_MASK;
end = PAGE_ALIGN(virt + size);
do {
next = pgd_addr_end(addr, end);
alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc,
flags);
phys += next - addr;
} while (pgdp++, addr = next, addr != end);
}
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int),
int flags)
{
mutex_lock(&fixmap_lock);
__create_pgd_mapping_locked(pgdir, phys, virt, size, prot,
pgtable_alloc, flags);
mutex_unlock(&fixmap_lock);
}
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
extern __alias(__create_pgd_mapping_locked)
void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(int), int flags);
#endif
static phys_addr_t __pgd_pgtable_alloc(int shift)
{
/* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO);
BUG_ON(!ptr);
return __pa(ptr);
}
static phys_addr_t pgd_pgtable_alloc(int shift)
{
phys_addr_t pa = __pgd_pgtable_alloc(shift);
struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa));
/*
* Call proper page table ctor in case later we need to
* call core mm functions like apply_to_page_range() on
* this pre-allocated page table.
*
* We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
* folded, and if so pagetable_pte_ctor() becomes nop.
*/
if (shift == PAGE_SHIFT)
BUG_ON(!pagetable_pte_ctor(ptdesc));
else if (shift == PMD_SHIFT)
BUG_ON(!pagetable_pmd_ctor(ptdesc));
return pa;
}
/*
* This function can only be used to modify existing table entries,
* without allocating new levels of table. Note that this permits the
* creation of new section or page entries.
*/
void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot)
{
if (virt < PAGE_OFFSET) {
pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
}
__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
NO_CONT_MAPPINGS);
}
void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot, bool page_mappings_only)
{
int flags = 0;
BUG_ON(mm == &init_mm);
if (page_mappings_only)
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
pgd_pgtable_alloc, flags);
}
static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot)
{
if (virt < PAGE_OFFSET) {
pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
}
__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
NO_CONT_MAPPINGS);
/* flush the TLBs after updating live kernel mappings */
flush_tlb_kernel_range(virt, virt + size);
}
static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start,
phys_addr_t end, pgprot_t prot, int flags)
{
__create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
prot, early_pgtable_alloc, flags);
}
void __init mark_linear_text_alias_ro(void)
{
/*
* Remove the write permissions from the linear alias of .text/.rodata
*/
update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext),
(unsigned long)__init_begin - (unsigned long)_stext,
PAGE_KERNEL_RO);
}
#ifdef CONFIG_KFENCE
bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL;
/* early_param() will be parsed before map_mem() below. */
static int __init parse_kfence_early_init(char *arg)
{
int val;
if (get_option(&arg, &val))
kfence_early_init = !!val;
return 0;
}
early_param("kfence.sample_interval", parse_kfence_early_init);
static phys_addr_t __init arm64_kfence_alloc_pool(void)
{
phys_addr_t kfence_pool;
if (!kfence_early_init)
return 0;
kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
if (!kfence_pool) {
pr_err("failed to allocate kfence pool\n");
kfence_early_init = false;
return 0;
}
/* Temporarily mark as NOMAP. */
memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
return kfence_pool;
}
static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp)
{
if (!kfence_pool)
return;
/* KFENCE pool needs page-level mapping. */
__map_memblock(pgdp, kfence_pool, kfence_pool + KFENCE_POOL_SIZE,
pgprot_tagged(PAGE_KERNEL),
NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
__kfence_pool = phys_to_virt(kfence_pool);
}
#else /* CONFIG_KFENCE */
static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; }
static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { }
#endif /* CONFIG_KFENCE */
static void __init map_mem(pgd_t *pgdp)
{
static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
phys_addr_t kernel_start = __pa_symbol(_stext);
phys_addr_t kernel_end = __pa_symbol(__init_begin);
phys_addr_t start, end;
phys_addr_t early_kfence_pool;
int flags = NO_EXEC_MAPPINGS;
u64 i;
/*
* Setting hierarchical PXNTable attributes on table entries covering
* the linear region is only possible if it is guaranteed that no table
* entries at any level are being shared between the linear region and
* the vmalloc region. Check whether this is true for the PGD level, in
* which case it is guaranteed to be true for all other levels as well.
* (Unless we are running with support for LPA2, in which case the
* entire reduced VA space is covered by a single pgd_t which will have
* been populated without the PXNTable attribute by the time we get here.)
*/
BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) &&
pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1);
early_kfence_pool = arm64_kfence_alloc_pool();
if (can_set_direct_map())
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
* Take care not to create a writable alias for the
* read-only text and rodata sections of the kernel image.
* So temporarily mark them as NOMAP to skip mappings in
* the following for-loop
*/
memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
/* map all the memory banks */
for_each_mem_range(i, &start, &end) {
if (start >= end)
break;
/*
* The linear map must allow allocation tags reading/writing
* if MTE is present. Otherwise, it has the same attributes as
* PAGE_KERNEL.
*/
__map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
flags);
}
/*
* Map the linear alias of the [_stext, __init_begin) interval
* as non-executable now, and remove the write permission in
* mark_linear_text_alias_ro() below (which will be called after
* alternative patching has completed). This makes the contents
* of the region accessible to subsystems such as hibernate,
* but protects it from inadvertent modification or execution.
* Note that contiguous mappings cannot be remapped in this way,
* so we should avoid them here.
*/
__map_memblock(pgdp, kernel_start, kernel_end,
PAGE_KERNEL, NO_CONT_MAPPINGS);
memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
arm64_kfence_map_pool(early_kfence_pool, pgdp);
}
void mark_rodata_ro(void)
{
unsigned long section_size;
/*
* mark .rodata as read only. Use __init_begin rather than __end_rodata
* to cover NOTES and EXCEPTION_TABLE.
*/
section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
WRITE_ONCE(rodata_is_rw, false);
update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
section_size, PAGE_KERNEL_RO);
}
static void __init declare_vma(struct vm_struct *vma,
void *va_start, void *va_end,
unsigned long vm_flags)
{
phys_addr_t pa_start = __pa_symbol(va_start);
unsigned long size = va_end - va_start;
BUG_ON(!PAGE_ALIGNED(pa_start));
BUG_ON(!PAGE_ALIGNED(size));
if (!(vm_flags & VM_NO_GUARD))
size += PAGE_SIZE;
vma->addr = va_start;
vma->phys_addr = pa_start;
vma->size = size;
vma->flags = VM_MAP | vm_flags;
vma->caller = __builtin_return_address(0);
vm_area_add_early(vma);
}
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
static pgprot_t kernel_exec_prot(void)
{
return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
}
static int __init map_entry_trampoline(void)
{
int i;
if (!arm64_kernel_unmapped_at_el0())
return 0;
pgprot_t prot = kernel_exec_prot();
phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
/* The trampoline is always mapped and can therefore be global */
pgprot_val(prot) &= ~PTE_NG;
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
entry_tramp_text_size(), prot,
__pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);
/* Map both the text and data into the kernel page table */
for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
pa_start + i * PAGE_SIZE, prot);
if (IS_ENABLED(CONFIG_RELOCATABLE))
__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
pa_start + i * PAGE_SIZE, PAGE_KERNEL_RO);
return 0;
}
core_initcall(map_entry_trampoline);
#endif
/*
* Declare the VMA areas for the kernel
*/
static void __init declare_kernel_vmas(void)
{
static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT];
declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD);
declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD);
declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD);
declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD);
declare_vma(&vmlinux_seg[4], _data, _end, 0);
}
void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot,
int level, pte_t *tbl, bool may_use_cont, u64 va_offset);
static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init,
kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init;
static void __init create_idmap(void)
{
u64 start = __pa_symbol(__idmap_text_start);
u64 end = __pa_symbol(__idmap_text_end);
u64 ptep = __pa_symbol(idmap_ptes);
__pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX,
IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false,
__phys_to_virt(ptep) - ptep);
if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) {
extern u32 __idmap_kpti_flag;
u64 pa = __pa_symbol(&__idmap_kpti_flag);
/*
* The KPTI G-to-nG conversion code needs a read-write mapping
* of its synchronization flag in the ID map.
*/
ptep = __pa_symbol(kpti_ptes);
__pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL,
IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false,
__phys_to_virt(ptep) - ptep);
}
}
void __init paging_init(void)
{
map_mem(swapper_pg_dir);
memblock_allow_resize();
create_idmap();
declare_kernel_vmas();
}
#ifdef CONFIG_MEMORY_HOTPLUG
static void free_hotplug_page_range(struct page *page, size_t size,
struct vmem_altmap *altmap)
{
if (altmap) {
vmem_altmap_free(altmap, size >> PAGE_SHIFT);
} else {
WARN_ON(PageReserved(page));
free_pages((unsigned long)page_address(page), get_order(size));
}
}
static void free_hotplug_pgtable_page(struct page *page)
{
free_hotplug_page_range(page, PAGE_SIZE, NULL);
}
static bool pgtable_range_aligned(unsigned long start, unsigned long end,
unsigned long floor, unsigned long ceiling,
unsigned long mask)
{
start &= mask;
if (start < floor)
return false;
if (ceiling) {
ceiling &= mask;
if (!ceiling)
return false;
}
if (end - 1 > ceiling - 1)
return false;
return true;
}
static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
unsigned long end, bool free_mapped,
struct vmem_altmap *altmap)
{
pte_t *ptep, pte;
do {
ptep = pte_offset_kernel(pmdp, addr);
pte = __ptep_get(ptep);
if (pte_none(pte))
continue;
WARN_ON(!pte_present(pte));
__pte_clear(&init_mm, addr, ptep);
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
free_hotplug_page_range(pte_page(pte),
PAGE_SIZE, altmap);
} while (addr += PAGE_SIZE, addr < end);
}
static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
unsigned long end, bool free_mapped,
struct vmem_altmap *altmap)
{
unsigned long next;
pmd_t *pmdp, pmd;
do {
next = pmd_addr_end(addr, end);
pmdp = pmd_offset(pudp, addr);
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
continue;
WARN_ON(!pmd_present(pmd));
if (pmd_sect(pmd)) {
pmd_clear(pmdp);
/*
* One TLBI should be sufficient here as the PMD_SIZE
* range is mapped with a single block entry.
*/
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
free_hotplug_page_range(pmd_page(pmd),
PMD_SIZE, altmap);
continue;
}
WARN_ON(!pmd_table(pmd));
unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
unsigned long end, bool free_mapped,
struct vmem_altmap *altmap)
{
unsigned long next;
pud_t *pudp, pud;
do {
next = pud_addr_end(addr, end);
pudp = pud_offset(p4dp, addr);
pud = READ_ONCE(*pudp);
if (pud_none(pud))
continue;
WARN_ON(!pud_present(pud));
if (pud_sect(pud)) {
pud_clear(pudp);
/*
* One TLBI should be sufficient here as the PUD_SIZE
* range is mapped with a single block entry.
*/
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
free_hotplug_page_range(pud_page(pud),
PUD_SIZE, altmap);
continue;
}
WARN_ON(!pud_table(pud));
unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
unsigned long end, bool free_mapped,
struct vmem_altmap *altmap)
{
unsigned long next;
p4d_t *p4dp, p4d;
do {
next = p4d_addr_end(addr, end);
p4dp = p4d_offset(pgdp, addr);
p4d = READ_ONCE(*p4dp);
if (p4d_none(p4d))
continue;
WARN_ON(!p4d_present(p4d));
unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void unmap_hotplug_range(unsigned long addr, unsigned long end,
bool free_mapped, struct vmem_altmap *altmap)
{
unsigned long next;
pgd_t *pgdp, pgd;
/*
* altmap can only be used as vmemmap mapping backing memory.
* In case the backing memory itself is not being freed, then
* altmap is irrelevant. Warn about this inconsistency when
* encountered.
*/
WARN_ON(!free_mapped && altmap);
do {
next = pgd_addr_end(addr, end);
pgdp = pgd_offset_k(addr);
pgd = READ_ONCE(*pgdp);
if (pgd_none(pgd))
continue;
WARN_ON(!pgd_present(pgd));
unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned long floor,
unsigned long ceiling)
{
pte_t *ptep, pte;
unsigned long i, start = addr;
do {
ptep = pte_offset_kernel(pmdp, addr);
pte = __ptep_get(ptep);
/*
* This is just a sanity check here which verifies that
* pte clearing has been done by earlier unmap loops.
*/
WARN_ON(!pte_none(pte));
} while (addr += PAGE_SIZE, addr < end);
if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK))
return;
/*
* Check whether we can free the pte page if the rest of the
* entries are empty. Overlap with other regions have been
* handled by the floor/ceiling check.
*/
ptep = pte_offset_kernel(pmdp, 0UL);
for (i = 0; i < PTRS_PER_PTE; i++) {
if (!pte_none(__ptep_get(&ptep[i])))
return;
}
pmd_clear(pmdp);
__flush_tlb_kernel_pgtable(start);
free_hotplug_pgtable_page(virt_to_page(ptep));
}
static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
unsigned long end, unsigned long floor,
unsigned long ceiling)
{
pmd_t *pmdp, pmd;
unsigned long i, next, start = addr;
do {
next = pmd_addr_end(addr, end);
pmdp = pmd_offset(pudp, addr);
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
continue;
WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
free_empty_pte_table(pmdp, addr, next, floor, ceiling);
} while (addr = next, addr < end);
if (CONFIG_PGTABLE_LEVELS <= 2)
return;
if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK))
return;
/*
* Check whether we can free the pmd page if the rest of the
* entries are empty. Overlap with other regions have been
* handled by the floor/ceiling check.
*/
pmdp = pmd_offset(pudp, 0UL);
for (i = 0; i < PTRS_PER_PMD; i++) {
if (!pmd_none(READ_ONCE(pmdp[i])))
return;
}
pud_clear(pudp);
__flush_tlb_kernel_pgtable(start);
free_hotplug_pgtable_page(virt_to_page(pmdp));
}
static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
unsigned long end, unsigned long floor,
unsigned long ceiling)
{
pud_t *pudp, pud;
unsigned long i, next, start = addr;
do {
next = pud_addr_end(addr, end);
pudp = pud_offset(p4dp, addr);
pud = READ_ONCE(*pudp);
if (pud_none(pud))
continue;
WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
free_empty_pmd_table(pudp, addr, next, floor, ceiling);
} while (addr = next, addr < end);
if (!pgtable_l4_enabled())
return;
if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK))
return;
/*
* Check whether we can free the pud page if the rest of the
* entries are empty. Overlap with other regions have been
* handled by the floor/ceiling check.
*/
pudp = pud_offset(p4dp, 0UL);
for (i = 0; i < PTRS_PER_PUD; i++) {
if (!pud_none(READ_ONCE(pudp[i])))
return;
}
p4d_clear(p4dp);
__flush_tlb_kernel_pgtable(start);
free_hotplug_pgtable_page(virt_to_page(pudp));
}
static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr,
unsigned long end, unsigned long floor,
unsigned long ceiling)
{
p4d_t *p4dp, p4d;
unsigned long i, next, start = addr;
do {
next = p4d_addr_end(addr, end);
p4dp = p4d_offset(pgdp, addr);
p4d = READ_ONCE(*p4dp);
if (p4d_none(p4d))
continue;
WARN_ON(!p4d_present(p4d));
free_empty_pud_table(p4dp, addr, next, floor, ceiling);
} while (addr = next, addr < end);
if (!pgtable_l5_enabled())
return;
if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK))
return;
/*
* Check whether we can free the p4d page if the rest of the
* entries are empty. Overlap with other regions have been
* handled by the floor/ceiling check.
*/
p4dp = p4d_offset(pgdp, 0UL);
for (i = 0; i < PTRS_PER_P4D; i++) {
if (!p4d_none(READ_ONCE(p4dp[i])))
return;
}
pgd_clear(pgdp);
__flush_tlb_kernel_pgtable(start);
free_hotplug_pgtable_page(virt_to_page(p4dp));
}
static void free_empty_tables(unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
unsigned long next;
pgd_t *pgdp, pgd;
do {
next = pgd_addr_end(addr, end);
pgdp = pgd_offset_k(addr);
pgd = READ_ONCE(*pgdp);
if (pgd_none(pgd))
continue;
WARN_ON(!pgd_present(pgd));
free_empty_p4d_table(pgdp, addr, next, floor, ceiling);
} while (addr = next, addr < end);
}
#endif
void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node,
unsigned long addr, unsigned long next)
{
pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
}
int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
unsigned long addr, unsigned long next)
{
vmemmap_verify((pte_t *)pmdp, node, addr, next);
return pmd_sect(READ_ONCE(*pmdp));
}
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
/* [start, end] should be within one section */
WARN_ON_ONCE(end - start > PAGES_PER_SECTION * sizeof(struct page));
if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) ||
(end - start < PAGES_PER_SECTION * sizeof(struct page)))
return vmemmap_populate_basepages(start, end, node, altmap);
else
return vmemmap_populate_hugepages(start, end, node, altmap);
}
#ifdef CONFIG_MEMORY_HOTPLUG
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
unmap_hotplug_range(start, end, true, altmap);
free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
/* Only allow permission changes for now */
if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
pud_val(new_pud)))
return 0;
VM_BUG_ON(phys & ~PUD_MASK);
set_pud(pudp, new_pud);
return 1;
}
int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot));
/* Only allow permission changes for now */
if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
pmd_val(new_pmd)))
return 0;
VM_BUG_ON(phys & ~PMD_MASK);
set_pmd(pmdp, new_pmd);
return 1;
}
#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_huge(p4d_t *p4dp)
{
}
#endif
int pud_clear_huge(pud_t *pudp)
{ if (!pud_sect(READ_ONCE(*pudp)))
return 0;
pud_clear(pudp);
return 1;
}
int pmd_clear_huge(pmd_t *pmdp)
{ if (!pmd_sect(READ_ONCE(*pmdp)))
return 0;
pmd_clear(pmdp);
return 1;
}
int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
{
pte_t *table;
pmd_t pmd;
pmd = READ_ONCE(*pmdp);
if (!pmd_table(pmd)) {
VM_WARN_ON(1);
return 1;
}
table = pte_offset_kernel(pmdp, addr);
pmd_clear(pmdp);
__flush_tlb_kernel_pgtable(addr);
pte_free_kernel(NULL, table);
return 1;
}
int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
{
pmd_t *table;
pmd_t *pmdp;
pud_t pud;
unsigned long next, end;
pud = READ_ONCE(*pudp);
if (!pud_table(pud)) {
VM_WARN_ON(1);
return 1;
}
table = pmd_offset(pudp, addr);
pmdp = table;
next = addr;
end = addr + PUD_SIZE;
do {
pmd_free_pte_page(pmdp, next);
} while (pmdp++, next += PMD_SIZE, next != end);
pud_clear(pudp);
__flush_tlb_kernel_pgtable(addr);
pmd_free(NULL, table);
return 1;
}
#ifdef CONFIG_MEMORY_HOTPLUG
static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
{
unsigned long end = start + size;
WARN_ON(pgdir != init_mm.pgd);
WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
unmap_hotplug_range(start, end, false, NULL);
free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
}
struct range arch_get_mappable_range(void)
{
struct range mhp_range;
u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
u64 end_linear_pa = __pa(PAGE_END - 1);
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
/*
* Check for a wrap, it is possible because of randomized linear
* mapping the start physical address is actually bigger than
* the end physical address. In this case set start to zero
* because [0, end_linear_pa] range must still be able to cover
* all addressable physical addresses.
*/
if (start_linear_pa > end_linear_pa)
start_linear_pa = 0;
}
WARN_ON(start_linear_pa > end_linear_pa);
/*
* Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
* accommodating both its ends but excluding PAGE_END. Max physical
* range which can be mapped inside this linear mapping range, must
* also be derived from its end points.
*/
mhp_range.start = start_linear_pa;
mhp_range.end = end_linear_pa;
return mhp_range;
}
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_params *params)
{
int ret, flags = NO_EXEC_MAPPINGS;
VM_BUG_ON(!mhp_range_allowed(start, size, true));
if (can_set_direct_map())
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
size, params->pgprot, __pgd_pgtable_alloc,
flags);
memblock_clear_nomap(start, size);
ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
params);
if (ret)
__remove_pgd_mapping(swapper_pg_dir,
__phys_to_virt(start), size);
else {
/* Address of hotplugged memory can be smaller */
max_pfn = max(max_pfn, PFN_UP(start + size));
max_low_pfn = max_pfn;
}
return ret;
}
void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
__remove_pages(start_pfn, nr_pages, altmap);
__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
}
/*
* This memory hotplug notifier helps prevent boot memory from being
* inadvertently removed as it blocks pfn range offlining process in
* __offline_pages(). Hence this prevents both offlining as well as
* removal process for boot memory which is initially always online.
* In future if and when boot memory could be removed, this notifier
* should be dropped and free_hotplug_page_range() should handle any
* reserved pages allocated during boot.
*/
static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
struct mem_section *ms;
struct memory_notify *arg = data;
unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
unsigned long pfn = arg->start_pfn;
if ((action != MEM_GOING_OFFLINE) && (action != MEM_OFFLINE))
return NOTIFY_OK;
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
unsigned long start = PFN_PHYS(pfn);
unsigned long end = start + (1UL << PA_SECTION_SHIFT);
ms = __pfn_to_section(pfn);
if (!early_section(ms))
continue;
if (action == MEM_GOING_OFFLINE) {
/*
* Boot memory removal is not supported. Prevent
* it via blocking any attempted offline request
* for the boot memory and just report it.
*/
pr_warn("Boot memory [%lx %lx] offlining attempted\n", start, end);
return NOTIFY_BAD;
} else if (action == MEM_OFFLINE) {
/*
* This should have never happened. Boot memory
* offlining should have been prevented by this
* very notifier. Probably some memory removal
* procedure might have changed which would then
* require further debug.
*/
pr_err("Boot memory [%lx %lx] offlined\n", start, end);
/*
* Core memory hotplug does not process a return
* code from the notifier for MEM_OFFLINE events.
* The error condition has been reported. Return
* from here as if ignored.
*/
return NOTIFY_DONE;
}
}
return NOTIFY_OK;
}
static struct notifier_block prevent_bootmem_remove_nb = {
.notifier_call = prevent_bootmem_remove_notifier,
};
/*
* This ensures that boot memory sections on the platform are online
* from early boot. Memory sections could not be prevented from being
* offlined, unless for some reason they are not online to begin with.
* This helps validate the basic assumption on which the above memory
* event notifier works to prevent boot memory section offlining and
* its possible removal.
*/
static void validate_bootmem_online(void)
{
phys_addr_t start, end, addr;
struct mem_section *ms;
u64 i;
/*
* Scanning across all memblock might be expensive
* on some big memory systems. Hence enable this
* validation only with DEBUG_VM.
*/
if (!IS_ENABLED(CONFIG_DEBUG_VM))
return;
for_each_mem_range(i, &start, &end) {
for (addr = start; addr < end; addr += (1UL << PA_SECTION_SHIFT)) {
ms = __pfn_to_section(PHYS_PFN(addr));
/*
* All memory ranges in the system at this point
* should have been marked as early sections.
*/
WARN_ON(!early_section(ms));
/*
* Memory notifier mechanism here to prevent boot
* memory offlining depends on the fact that each
* early section memory on the system is initially
* online. Otherwise a given memory section which
* is already offline will be overlooked and can
* be removed completely. Call out such sections.
*/
if (!online_section(ms))
pr_err("Boot memory [%llx %llx] is offline, can be removed\n",
addr, addr + (1UL << PA_SECTION_SHIFT));
}
}
}
static int __init prevent_bootmem_remove_init(void)
{
int ret = 0;
if (!IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
return ret;
validate_bootmem_online();
ret = register_memory_notifier(&prevent_bootmem_remove_nb);
if (ret)
pr_err("%s: Notifier registration failed %d\n", __func__, ret);
return ret;
}
early_initcall(prevent_bootmem_remove_init);
#endif
pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
{
if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
/*
* Break-before-make (BBM) is required for all user space mappings
* when the permission changes from executable to non-executable
* in cases where cpu is affected with errata #2645198.
*/
if (pte_user_exec(ptep_get(ptep)))
return ptep_clear_flush(vma, addr, ptep);
}
return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
/*
* Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
* avoiding the possibility of conflicting TLB entries being allocated.
*/
void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
{
typedef void (ttbr_replace_func)(phys_addr_t);
extern ttbr_replace_func idmap_cpu_replace_ttbr1;
ttbr_replace_func *replace_phys;
unsigned long daif;
/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
if (cnp)
ttbr1 |= TTBR_CNP_BIT;
replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
cpu_install_idmap();
/*
* We really don't want to take *any* exceptions while TTBR1 is
* in the process of being replaced so mask everything.
*/
daif = local_daif_save();
replace_phys(ttbr1);
local_daif_restore(daif);
cpu_uninstall_idmap();
}
#ifdef CONFIG_ARCH_HAS_PKEYS
int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
{
u64 new_por;
u64 old_por;
if (!system_supports_poe())
return -ENOSPC;
/*
* This code should only be called with valid 'pkey'
* values originating from in-kernel users. Complain
* if a bad value is observed.
*/
if (WARN_ON_ONCE(pkey >= arch_max_pkey()))
return -EINVAL;
/* Set the bits we need in POR: */
new_por = POE_RWX;
if (init_val & PKEY_DISABLE_WRITE)
new_por &= ~POE_W;
if (init_val & PKEY_DISABLE_ACCESS)
new_por &= ~POE_RW;
if (init_val & PKEY_DISABLE_READ)
new_por &= ~POE_R;
if (init_val & PKEY_DISABLE_EXECUTE)
new_por &= ~POE_X;
/* Shift the bits in to the correct place in POR for pkey: */
new_por = POR_ELx_PERM_PREP(pkey, new_por);
/* Get old POR and mask off any old bits in place: */
old_por = read_sysreg_s(SYS_POR_EL0);
old_por &= ~(POE_MASK << POR_ELx_PERM_SHIFT(pkey));
/* Write old part along with new part: */
write_sysreg_s(old_por | new_por, SYS_POR_EL0);
return 0;
}
#endif
/* SPDX-License-Identifier: GPL-2.0 */
/*
* This file provides wrappers with sanitizer instrumentation for atomic bit
* operations.
*
* To use this functionality, an arch's bitops.h file needs to define each of
* the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
* arch___set_bit(), etc.).
*/
#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
#define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
#include <linux/instrumented.h>
/**
* set_bit - Atomically set a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
*
* This is a relaxed atomic operation (no implied memory barriers).
*
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
static __always_inline void set_bit(long nr, volatile unsigned long *addr)
{
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
arch_set_bit(nr, addr);
}
/**
* clear_bit - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* This is a relaxed atomic operation (no implied memory barriers).
*/
static __always_inline void clear_bit(long nr, volatile unsigned long *addr)
{
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
arch_clear_bit(nr, addr);
}
/**
* change_bit - Toggle a bit in memory
* @nr: Bit to change
* @addr: Address to start counting from
*
* This is a relaxed atomic operation (no implied memory barriers).
*
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
static __always_inline void change_bit(long nr, volatile unsigned long *addr)
{
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
arch_change_bit(nr, addr);
}
/**
* test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
* This is an atomic fully-ordered operation (implied full memory barrier).
*/
static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
{
kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_set_bit(nr, addr);
}
/**
* test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*
* This is an atomic fully-ordered operation (implied full memory barrier).
*/
static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
{
kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_clear_bit(nr, addr);
}
/**
* test_and_change_bit - Change a bit and return its old value
* @nr: Bit to change
* @addr: Address to count from
*
* This is an atomic fully-ordered operation (implied full memory barrier).
*/
static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
{
kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_change_bit(nr, addr);
}
#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H
#include <linux/gfp_types.h>
#include <linux/mmzone.h>
#include <linux/topology.h>
#include <linux/alloc_tag.h>
#include <linux/sched.h>
struct vm_area_struct;
struct mempolicy;
/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3
static inline int gfp_migratetype(const gfp_t gfp_flags)
{
VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);
BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE);
BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >>
GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC);
if (unlikely(page_group_by_mobility_disabled))
return MIGRATE_UNMOVABLE;
/* Group based on mobility */
return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
}
#undef GFP_MOVABLE_MASK
#undef GFP_MOVABLE_SHIFT
static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
{
return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
}
static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags)
{
/*
* !__GFP_DIRECT_RECLAIM -> direct claim is not allowed.
* !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd.
* All GFP_* flags including GFP_NOWAIT use one or both flags.
* try_alloc_pages() is the only API that doesn't specify either flag.
*
* This is stronger than GFP_NOWAIT or GFP_ATOMIC because
* those are guaranteed to never block on a sleeping lock.
* Here we are enforcing that the allocation doesn't ever spin
* on any locks (i.e. only trylocks). There is no high level
* GFP_$FOO flag for this use in try_alloc_pages() as the
* regular page allocator doesn't fully support this
* allocation mode.
*/
return !!(gfp_flags & __GFP_RECLAIM);
}
#ifdef CONFIG_HIGHMEM
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
#else
#define OPT_ZONE_HIGHMEM ZONE_NORMAL
#endif
#ifdef CONFIG_ZONE_DMA
#define OPT_ZONE_DMA ZONE_DMA
#else
#define OPT_ZONE_DMA ZONE_NORMAL
#endif
#ifdef CONFIG_ZONE_DMA32
#define OPT_ZONE_DMA32 ZONE_DMA32
#else
#define OPT_ZONE_DMA32 ZONE_NORMAL
#endif
/*
* GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
* zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT
* bits long and there are 16 of them to cover all possible combinations of
* __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM.
*
* The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
* But GFP_MOVABLE is not only a zone specifier but also an allocation
* policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
* Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1".
*
* bit result
* =================
* 0x0 => NORMAL
* 0x1 => DMA or NORMAL
* 0x2 => HIGHMEM or NORMAL
* 0x3 => BAD (DMA+HIGHMEM)
* 0x4 => DMA32 or NORMAL
* 0x5 => BAD (DMA+DMA32)
* 0x6 => BAD (HIGHMEM+DMA32)
* 0x7 => BAD (HIGHMEM+DMA32+DMA)
* 0x8 => NORMAL (MOVABLE+0)
* 0x9 => DMA or NORMAL (MOVABLE+DMA)
* 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too)
* 0xb => BAD (MOVABLE+HIGHMEM+DMA)
* 0xc => DMA32 or NORMAL (MOVABLE+DMA32)
* 0xd => BAD (MOVABLE+DMA32+DMA)
* 0xe => BAD (MOVABLE+DMA32+HIGHMEM)
* 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
*
* GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.
*/
#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
/* ZONE_DEVICE is not a valid GFP zone specifier */
#define GFP_ZONES_SHIFT 2
#else
#define GFP_ZONES_SHIFT ZONES_SHIFT
#endif
#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
#endif
#define GFP_ZONE_TABLE ( \
(ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \
| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \
| (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \
| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \
| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\
| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\
)
/*
* GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32
* __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
* entry starting with bit 0. Bit is set if the combination is not
* allowed.
*/
#define GFP_ZONE_BAD ( \
1 << (___GFP_DMA | ___GFP_HIGHMEM) \
| 1 << (___GFP_DMA | ___GFP_DMA32) \
| 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \
)
static inline enum zone_type gfp_zone(gfp_t flags)
{
enum zone_type z;
int bit = (__force int) (flags & GFP_ZONEMASK);
z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
((1 << GFP_ZONES_SHIFT) - 1);
VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
return z;
}
/*
* There is only one page-allocator function, and two main namespaces to
* it. The alloc_page*() variants return 'struct page *' and as such
* can allocate highmem pages, the *get*page*() variants return
* virtual kernel addresses to the allocated page(s).
*/
static inline int gfp_zonelist(gfp_t flags)
{
#ifdef CONFIG_NUMA
if (unlikely(flags & __GFP_THISNODE))
return ZONELIST_NOFALLBACK;
#endif
return ZONELIST_FALLBACK;
}
/*
* gfp flag masking for nested internal allocations.
*
* For code that needs to do allocations inside the public allocation API (e.g.
* memory allocation tracking code) the allocations need to obey the caller
* allocation context constrains to prevent allocation context mismatches (e.g.
* GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock
* situations.
*
* It is also assumed that these nested allocations are for internal kernel
* object storage purposes only and are not going to be used for DMA, etc. Hence
* we strip out all the zone information and leave just the context information
* intact.
*
* Further, internal allocations must fail before the higher level allocation
* can fail, so we must make them fail faster and fail silently. We also don't
* want them to deplete emergency reserves. Hence nested allocations must be
* prepared for these allocations to fail.
*/
static inline gfp_t gfp_nested_mask(gfp_t flags)
{
return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) |
(__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN));
}
/*
* We get the zone list from the current node and the gfp_mask.
* This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones.
* There are two zonelists per node, one for all zones with memory and
* one containing just zones from the node the zonelist belongs to.
*
* For the case of non-NUMA systems the NODE_DATA() gets optimized to
* &contig_page_data at compile-time.
*/
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
{
return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
}
#ifndef HAVE_ARCH_FREE_PAGE
static inline void arch_free_page(struct page *page, int order) { }
#endif
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif
struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
nodemask_t *nodemask);
#define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__))
struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
nodemask_t *nodemask);
#define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__))
unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
nodemask_t *nodemask, int nr_pages,
struct page **page_array);
#define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__))
unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp,
unsigned long nr_pages,
struct page **page_array);
#define alloc_pages_bulk_mempolicy(...) \
alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__))
/* Bulk allocate order-0 pages */
#define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \
__alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array)
static inline unsigned long
alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages,
struct page **page_array)
{
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array);
}
#define alloc_pages_bulk_node(...) \
alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__))
static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
{
gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);
if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN))
return;
if (node_online(this_node))
return;
pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node);
dump_stack();
}
/*
* Allocate pages, preferring the node given as nid. The node must be valid and
* online. For more general interface, see alloc_pages_node().
*/
static inline struct page *
__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order)
{
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask);
return __alloc_pages_noprof(gfp_mask, order, nid, NULL);
}
#define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__))
static inline
struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid)
{
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp);
return __folio_alloc_noprof(gfp, order, nid, NULL);
}
#define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__))
/*
* Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
* prefer the current CPU's closest node. Otherwise node must be valid and
* online.
*/
static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask,
unsigned int order)
{
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
return __alloc_pages_node_noprof(nid, gfp_mask, order);
}
#define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__))
#ifdef CONFIG_NUMA
struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order);
struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order);
struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
struct mempolicy *mpol, pgoff_t ilx, int nid);
struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma,
unsigned long addr);
#else
static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order)
{
return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order);
}
static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
{
return __folio_alloc_node_noprof(gfp, order, numa_node_id());
}
static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
struct mempolicy *mpol, pgoff_t ilx, int nid)
{
return folio_alloc_noprof(gfp, order);
}
#define vma_alloc_folio_noprof(gfp, order, vma, addr) \
folio_alloc_noprof(gfp, order)
#endif
#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__))
#define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__))
#define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__))
#define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__))
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
static inline struct page *alloc_page_vma_noprof(gfp_t gfp,
struct vm_area_struct *vma, unsigned long addr)
{
struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr);
return &folio->page;
}
#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__))
struct page *try_alloc_pages_noprof(int nid, unsigned int order);
#define try_alloc_pages(...) alloc_hooks(try_alloc_pages_noprof(__VA_ARGS__))
extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order);
#define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__))
extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask);
#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__))
void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1);
#define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__))
void free_pages_exact(void *virt, size_t size);
__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
#define alloc_pages_exact_nid(...) \
alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__))
#define __get_free_page(gfp_mask) \
__get_free_pages((gfp_mask), 0)
#define __get_dma_pages(gfp_mask, order) \
__get_free_pages((gfp_mask) | GFP_DMA, (order))
extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages_nolock(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)
void page_alloc_init_cpuhp(void);
int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp);
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
void drain_all_pages(struct zone *zone);
void drain_local_pages(struct zone *zone);
void page_alloc_init_late(void);
void setup_pcp_cacheinfo(unsigned int cpu);
/*
* gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
* GFP flags are used before interrupts are enabled. Once interrupts are
* enabled, it is set to __GFP_BITS_MASK while the system is running. During
* hibernation, it is used by PM to avoid I/O during memory allocation while
* devices are suspended.
*/
extern gfp_t gfp_allowed_mask;
/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
static inline bool gfp_has_io_fs(gfp_t gfp)
{
return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
}
/*
* Check if the gfp flags allow compaction - GFP_NOIO is a really
* tricky context because the migration might require IO.
*/
static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
{
return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
}
extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
#ifdef CONFIG_CONTIG_ALLOC
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range_noprof(unsigned long start, unsigned long end,
unsigned migratetype, gfp_t gfp_mask);
#define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__))
extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask,
int nid, nodemask_t *nodemask);
#define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__))
#endif
void free_contig_range(unsigned long pfn, unsigned long nr_pages);
#ifdef CONFIG_CONTIG_ALLOC
static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp,
int nid, nodemask_t *node)
{
struct page *page;
if (WARN_ON(!order || !(gfp & __GFP_COMP)))
return NULL;
page = alloc_contig_pages_noprof(1 << order, gfp, nid, node);
return page ? page_folio(page) : NULL;
}
#else
static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp,
int nid, nodemask_t *node)
{
return NULL;
}
#endif
/* This should be paired with folio_put() rather than free_contig_range(). */
#define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__))
#endif /* __LINUX_GFP_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
* Copyright (C) 2005-2006 Thomas Gleixner
*
* This file contains driver APIs to the irq subsystem.
*/
#define pr_fmt(fmt) "genirq: " fmt
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
#include <linux/sched/isolation.h>
#include <uapi/linux/sched/types.h>
#include <linux/task_work.h>
#include "internals.h"
#if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT)
DEFINE_STATIC_KEY_FALSE(force_irqthreads_key);
static int __init setup_forced_irqthreads(char *arg)
{
static_branch_enable(&force_irqthreads_key);
return 0;
}
early_param("threadirqs", setup_forced_irqthreads);
#endif
static int __irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *state);
static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
{
struct irq_data *irqd = irq_desc_get_irq_data(desc);
bool inprogress;
do {
unsigned long flags;
/*
* Wait until we're out of the critical section. This might
* give the wrong answer due to the lack of memory barriers.
*/
while (irqd_irq_inprogress(&desc->irq_data))
cpu_relax();
/* Ok, that indicated we're done: double-check carefully. */
raw_spin_lock_irqsave(&desc->lock, flags);
inprogress = irqd_irq_inprogress(&desc->irq_data);
/*
* If requested and supported, check at the chip whether it
* is in flight at the hardware level, i.e. already pending
* in a CPU and waiting for service and acknowledge.
*/
if (!inprogress && sync_chip) {
/*
* Ignore the return code. inprogress is only updated
* when the chip supports it.
*/
__irq_get_irqchip_state(irqd, IRQCHIP_STATE_ACTIVE,
&inprogress);
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
/* Oops, that failed? */
} while (inprogress);
}
/**
* synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
*
* This function waits for any pending hard IRQ handlers for this
* interrupt to complete before returning. If you use this
* function while holding a resource the IRQ handler may need you
* will deadlock. It does not take associated threaded handlers
* into account.
*
* Do not use this for shutdown scenarios where you must be sure
* that all parts (hardirq and threaded handler) have completed.
*
* Returns: false if a threaded handler is active.
*
* This function may be called - with care - from IRQ context.
*
* It does not check whether there is an interrupt in flight at the
* hardware level, but not serviced yet, as this might deadlock when
* called with interrupts disabled and the target CPU of the interrupt
* is the current CPU.
*/
bool synchronize_hardirq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc) {
__synchronize_hardirq(desc, false);
return !atomic_read(&desc->threads_active);
}
return true;
}
EXPORT_SYMBOL(synchronize_hardirq);
static void __synchronize_irq(struct irq_desc *desc)
{
__synchronize_hardirq(desc, true);
/*
* We made sure that no hardirq handler is running. Now verify that no
* threaded handlers are active.
*/
wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
}
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
*
* This function waits for any pending IRQ handlers for this interrupt
* to complete before returning. If you use this function while
* holding a resource the IRQ handler may need you will deadlock.
*
* Can only be called from preemptible code as it might sleep when
* an interrupt thread is associated to @irq.
*
* It optionally makes sure (when the irq chip supports that method)
* that the interrupt is not pending in any CPU and waiting for
* service.
*/
void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc)
__synchronize_irq(desc);
}
EXPORT_SYMBOL(synchronize_irq);
#ifdef CONFIG_SMP
cpumask_var_t irq_default_affinity;
static bool __irq_can_set_affinity(struct irq_desc *desc)
{
if (!desc || !irqd_can_balance(&desc->irq_data) ||
!desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
return false;
return true;
}
/**
* irq_can_set_affinity - Check if the affinity of a given irq can be set
* @irq: Interrupt to check
*
*/
int irq_can_set_affinity(unsigned int irq)
{
return __irq_can_set_affinity(irq_to_desc(irq));
}
/**
* irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
* @irq: Interrupt to check
*
* Like irq_can_set_affinity() above, but additionally checks for the
* AFFINITY_MANAGED flag.
*/
bool irq_can_set_affinity_usr(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
return __irq_can_set_affinity(desc) &&
!irqd_affinity_is_managed(&desc->irq_data);
}
/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
* @desc: irq descriptor which has affinity changed
*
* We just set IRQTF_AFFINITY and delegate the affinity setting
* to the interrupt thread itself. We can not call
* set_cpus_allowed_ptr() here as we hold desc->lock and this
* code can be called from hard interrupt context.
*/
static void irq_set_thread_affinity(struct irq_desc *desc)
{
struct irqaction *action;
for_each_action_of_desc(desc, action) {
if (action->thread) {
set_bit(IRQTF_AFFINITY, &action->thread_flags);
wake_up_process(action->thread);
}
if (action->secondary && action->secondary->thread) {
set_bit(IRQTF_AFFINITY, &action->secondary->thread_flags);
wake_up_process(action->secondary->thread);
}
}
}
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
static void irq_validate_effective_affinity(struct irq_data *data)
{
const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
struct irq_chip *chip = irq_data_get_irq_chip(data);
if (!cpumask_empty(m))
return;
pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
chip->name, data->irq);
}
#else
static inline void irq_validate_effective_affinity(struct irq_data *data) { }
#endif
static DEFINE_PER_CPU(struct cpumask, __tmp_mask);
int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
bool force)
{
struct cpumask *tmp_mask = this_cpu_ptr(&__tmp_mask);
struct irq_desc *desc = irq_data_to_desc(data);
struct irq_chip *chip = irq_data_get_irq_chip(data);
const struct cpumask *prog_mask;
int ret;
if (!chip || !chip->irq_set_affinity)
return -EINVAL;
/*
* If this is a managed interrupt and housekeeping is enabled on
* it check whether the requested affinity mask intersects with
* a housekeeping CPU. If so, then remove the isolated CPUs from
* the mask and just keep the housekeeping CPU(s). This prevents
* the affinity setter from routing the interrupt to an isolated
* CPU to avoid that I/O submitted from a housekeeping CPU causes
* interrupts on an isolated one.
*
* If the masks do not intersect or include online CPU(s) then
* keep the requested mask. The isolated target CPUs are only
* receiving interrupts when the I/O operation was submitted
* directly from them.
*
* If all housekeeping CPUs in the affinity mask are offline, the
* interrupt will be migrated by the CPU hotplug code once a
* housekeeping CPU which belongs to the affinity mask comes
* online.
*/
if (irqd_affinity_is_managed(data) &&
housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) {
const struct cpumask *hk_mask;
hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
cpumask_and(tmp_mask, mask, hk_mask);
if (!cpumask_intersects(tmp_mask, cpu_online_mask))
prog_mask = mask;
else
prog_mask = tmp_mask;
} else {
prog_mask = mask;
}
/*
* Make sure we only provide online CPUs to the irqchip,
* unless we are being asked to force the affinity (in which
* case we do as we are told).
*/
cpumask_and(tmp_mask, prog_mask, cpu_online_mask);
if (!force && !cpumask_empty(tmp_mask))
ret = chip->irq_set_affinity(data, tmp_mask, force);
else if (force)
ret = chip->irq_set_affinity(data, mask, force);
else
ret = -EINVAL;
switch (ret) {
case IRQ_SET_MASK_OK:
case IRQ_SET_MASK_OK_DONE:
cpumask_copy(desc->irq_common_data.affinity, mask);
fallthrough;
case IRQ_SET_MASK_OK_NOCOPY:
irq_validate_effective_affinity(data);
irq_set_thread_affinity(desc);
ret = 0;
}
return ret;
}
#ifdef CONFIG_GENERIC_PENDING_IRQ
static inline int irq_set_affinity_pending(struct irq_data *data,
const struct cpumask *dest)
{
struct irq_desc *desc = irq_data_to_desc(data);
irqd_set_move_pending(data);
irq_copy_pending(desc, dest);
return 0;
}
#else
static inline int irq_set_affinity_pending(struct irq_data *data,
const struct cpumask *dest)
{
return -EBUSY;
}
#endif
static int irq_try_set_affinity(struct irq_data *data,
const struct cpumask *dest, bool force)
{
int ret = irq_do_set_affinity(data, dest, force);
/*
* In case that the underlying vector management is busy and the
* architecture supports the generic pending mechanism then utilize
* this to avoid returning an error to user space.
*/
if (ret == -EBUSY && !force)
ret = irq_set_affinity_pending(data, dest);
return ret;
}
static bool irq_set_affinity_deactivated(struct irq_data *data,
const struct cpumask *mask)
{
struct irq_desc *desc = irq_data_to_desc(data);
/*
* Handle irq chips which can handle affinity only in activated
* state correctly
*
* If the interrupt is not yet activated, just store the affinity
* mask and do not call the chip driver at all. On activation the
* driver has to make sure anyway that the interrupt is in a
* usable state so startup works.
*/
if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
irqd_is_activated(data) || !irqd_affinity_on_activate(data))
return false;
cpumask_copy(desc->irq_common_data.affinity, mask);
irq_data_update_effective_affinity(data, mask);
irqd_set(data, IRQD_AFFINITY_SET);
return true;
}
int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
bool force)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
struct irq_desc *desc = irq_data_to_desc(data);
int ret = 0;
if (!chip || !chip->irq_set_affinity)
return -EINVAL;
if (irq_set_affinity_deactivated(data, mask))
return 0;
if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) {
ret = irq_try_set_affinity(data, mask, force);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
}
if (desc->affinity_notify) {
kref_get(&desc->affinity_notify->kref);
if (!schedule_work(&desc->affinity_notify->work)) {
/* Work was already scheduled, drop our extra ref */
kref_put(&desc->affinity_notify->kref,
desc->affinity_notify->release);
}
}
irqd_set(data, IRQD_AFFINITY_SET);
return ret;
}
/**
* irq_update_affinity_desc - Update affinity management for an interrupt
* @irq: The interrupt number to update
* @affinity: Pointer to the affinity descriptor
*
* This interface can be used to configure the affinity management of
* interrupts which have been allocated already.
*
* There are certain limitations on when it may be used - attempts to use it
* for when the kernel is configured for generic IRQ reservation mode (in
* config GENERIC_IRQ_RESERVATION_MODE) will fail, as it may conflict with
* managed/non-managed interrupt accounting. In addition, attempts to use it on
* an interrupt which is already started or which has already been configured
* as managed will also fail, as these mean invalid init state or double init.
*/
int irq_update_affinity_desc(unsigned int irq,
struct irq_affinity_desc *affinity)
{
struct irq_desc *desc;
unsigned long flags;
bool activated;
int ret = 0;
/*
* Supporting this with the reservation scheme used by x86 needs
* some more thought. Fail it for now.
*/
if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
return -EOPNOTSUPP;
desc = irq_get_desc_buslock(irq, &flags, 0);
if (!desc)
return -EINVAL;
/* Requires the interrupt to be shut down */
if (irqd_is_started(&desc->irq_data)) {
ret = -EBUSY;
goto out_unlock;
}
/* Interrupts which are already managed cannot be modified */
if (irqd_affinity_is_managed(&desc->irq_data)) {
ret = -EBUSY;
goto out_unlock;
}
/*
* Deactivate the interrupt. That's required to undo
* anything an earlier activation has established.
*/
activated = irqd_is_activated(&desc->irq_data);
if (activated)
irq_domain_deactivate_irq(&desc->irq_data);
if (affinity->is_managed) {
irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED);
irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN);
}
cpumask_copy(desc->irq_common_data.affinity, &affinity->mask);
/* Restore the activation state */
if (activated)
irq_domain_activate_irq(&desc->irq_data, false);
out_unlock:
irq_put_desc_busunlock(desc, flags);
return ret;
}
static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask,
bool force)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
int ret;
if (!desc)
return -EINVAL;
raw_spin_lock_irqsave(&desc->lock, flags);
ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
/**
* irq_set_affinity - Set the irq affinity of a given irq
* @irq: Interrupt to set affinity
* @cpumask: cpumask
*
* Fails if cpumask does not contain an online CPU
*/
int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
{
return __irq_set_affinity(irq, cpumask, false);
}
EXPORT_SYMBOL_GPL(irq_set_affinity);
/**
* irq_force_affinity - Force the irq affinity of a given irq
* @irq: Interrupt to set affinity
* @cpumask: cpumask
*
* Same as irq_set_affinity, but without checking the mask against
* online cpus.
*
* Solely for low level cpu hotplug code, where we need to make per
* cpu interrupts affine before the cpu becomes online.
*/
int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
{
return __irq_set_affinity(irq, cpumask, true);
}
EXPORT_SYMBOL_GPL(irq_force_affinity);
int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m,
bool setaffinity)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
if (!desc)
return -EINVAL;
desc->affinity_hint = m;
irq_put_desc_unlock(desc, flags);
if (m && setaffinity)
__irq_set_affinity(irq, m, false);
return 0;
}
EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint);
static void irq_affinity_notify(struct work_struct *work)
{
struct irq_affinity_notify *notify =
container_of(work, struct irq_affinity_notify, work);
struct irq_desc *desc = irq_to_desc(notify->irq);
cpumask_var_t cpumask;
unsigned long flags;
if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
goto out;
raw_spin_lock_irqsave(&desc->lock, flags);
if (irq_move_pending(&desc->irq_data))
irq_get_pending(cpumask, desc);
else
cpumask_copy(cpumask, desc->irq_common_data.affinity);
raw_spin_unlock_irqrestore(&desc->lock, flags);
notify->notify(notify, cpumask);
free_cpumask_var(cpumask);
out:
kref_put(¬ify->kref, notify->release);
}
/**
* irq_set_affinity_notifier - control notification of IRQ affinity changes
* @irq: Interrupt for which to enable/disable notification
* @notify: Context for notification, or %NULL to disable
* notification. Function pointers must be initialised;
* the other fields will be initialised by this function.
*
* Must be called in process context. Notification may only be enabled
* after the IRQ is allocated and must be disabled before the IRQ is
* freed using free_irq().
*/
int
irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_affinity_notify *old_notify;
unsigned long flags;
/* The release function is promised process context */
might_sleep();
if (!desc || irq_is_nmi(desc))
return -EINVAL;
/* Complete initialisation of *notify */
if (notify) {
notify->irq = irq;
kref_init(¬ify->kref);
INIT_WORK(¬ify->work, irq_affinity_notify);
}
raw_spin_lock_irqsave(&desc->lock, flags);
old_notify = desc->affinity_notify;
desc->affinity_notify = notify;
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (old_notify) {
if (cancel_work_sync(&old_notify->work)) {
/* Pending work had a ref, put that one too */
kref_put(&old_notify->kref, old_notify->release);
}
kref_put(&old_notify->kref, old_notify->release);
}
return 0;
}
EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
#ifndef CONFIG_AUTO_IRQ_AFFINITY
/*
* Generic version of the affinity autoselector.
*/
int irq_setup_affinity(struct irq_desc *desc)
{
struct cpumask *set = irq_default_affinity;
int ret, node = irq_desc_get_node(desc);
static DEFINE_RAW_SPINLOCK(mask_lock);
static struct cpumask mask;
/* Excludes PER_CPU and NO_BALANCE interrupts */
if (!__irq_can_set_affinity(desc))
return 0;
raw_spin_lock(&mask_lock);
/*
* Preserve the managed affinity setting and a userspace affinity
* setup, but make sure that one of the targets is online.
*/
if (irqd_affinity_is_managed(&desc->irq_data) ||
irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
if (cpumask_intersects(desc->irq_common_data.affinity,
cpu_online_mask))
set = desc->irq_common_data.affinity;
else
irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
}
cpumask_and(&mask, cpu_online_mask, set);
if (cpumask_empty(&mask))
cpumask_copy(&mask, cpu_online_mask);
if (node != NUMA_NO_NODE) {
const struct cpumask *nodemask = cpumask_of_node(node);
/* make sure at least one of the cpus in nodemask is online */
if (cpumask_intersects(&mask, nodemask))
cpumask_and(&mask, &mask, nodemask);
}
ret = irq_do_set_affinity(&desc->irq_data, &mask, false);
raw_spin_unlock(&mask_lock);
return ret;
}
#else
/* Wrapper for ALPHA specific affinity selector magic */
int irq_setup_affinity(struct irq_desc *desc)
{
return irq_select_affinity(irq_desc_get_irq(desc));
}
#endif /* CONFIG_AUTO_IRQ_AFFINITY */
#endif /* CONFIG_SMP */
/**
* irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
* @irq: interrupt number to set affinity
* @vcpu_info: vCPU specific data or pointer to a percpu array of vCPU
* specific data for percpu_devid interrupts
*
* This function uses the vCPU specific data to set the vCPU
* affinity for an irq. The vCPU specific data is passed from
* outside, such as KVM. One example code path is as below:
* KVM -> IOMMU -> irq_set_vcpu_affinity().
*/
int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
struct irq_data *data;
struct irq_chip *chip;
int ret = -ENOSYS;
if (!desc)
return -EINVAL;
data = irq_desc_get_irq_data(desc);
do {
chip = irq_data_get_irq_chip(data);
if (chip && chip->irq_set_vcpu_affinity)
break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
data = data->parent_data;
#else
data = NULL;
#endif
} while (data);
if (data)
ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
irq_put_desc_unlock(desc, flags);
return ret;
}
EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
void __disable_irq(struct irq_desc *desc)
{
if (!desc->depth++)
irq_disable(desc);
}
static int __disable_irq_nosync(unsigned int irq)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
if (!desc)
return -EINVAL;
__disable_irq(desc);
irq_put_desc_busunlock(desc, flags);
return 0;
}
/**
* disable_irq_nosync - disable an irq without waiting
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Disables and Enables are
* nested.
* Unlike disable_irq(), this function does not ensure existing
* instances of the IRQ handler have completed before returning.
*
* This function may be called from IRQ context.
*/
void disable_irq_nosync(unsigned int irq)
{
__disable_irq_nosync(irq);
}
EXPORT_SYMBOL(disable_irq_nosync);
/**
* disable_irq - disable an irq and wait for completion
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Enables and Disables are
* nested.
* This function waits for any pending IRQ handlers for this interrupt
* to complete before returning. If you use this function while
* holding a resource the IRQ handler may need you will deadlock.
*
* Can only be called from preemptible code as it might sleep when
* an interrupt thread is associated to @irq.
*
*/
void disable_irq(unsigned int irq)
{
might_sleep();
if (!__disable_irq_nosync(irq))
synchronize_irq(irq);
}
EXPORT_SYMBOL(disable_irq);
/**
* disable_hardirq - disables an irq and waits for hardirq completion
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Enables and Disables are
* nested.
* This function waits for any pending hard IRQ handlers for this
* interrupt to complete before returning. If you use this function while
* holding a resource the hard IRQ handler may need you will deadlock.
*
* When used to optimistically disable an interrupt from atomic context
* the return value must be checked.
*
* Returns: false if a threaded handler is active.
*
* This function may be called - with care - from IRQ context.
*/
bool disable_hardirq(unsigned int irq)
{
if (!__disable_irq_nosync(irq))
return synchronize_hardirq(irq);
return false;
}
EXPORT_SYMBOL_GPL(disable_hardirq);
/**
* disable_nmi_nosync - disable an nmi without waiting
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Disables and enables are
* nested.
* The interrupt to disable must have been requested through request_nmi.
* Unlike disable_nmi(), this function does not ensure existing
* instances of the IRQ handler have completed before returning.
*/
void disable_nmi_nosync(unsigned int irq)
{
disable_irq_nosync(irq);
}
void __enable_irq(struct irq_desc *desc)
{
switch (desc->depth) {
case 0:
err_out:
WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n",
irq_desc_get_irq(desc));
break;
case 1: {
if (desc->istate & IRQS_SUSPENDED)
goto err_out;
/* Prevent probing on this irq: */
irq_settings_set_noprobe(desc);
/*
* Call irq_startup() not irq_enable() here because the
* interrupt might be marked NOAUTOEN so irq_startup()
* needs to be invoked when it gets enabled the first time.
* This is also required when __enable_irq() is invoked for
* a managed and shutdown interrupt from the S3 resume
* path.
*
* If it was already started up, then irq_startup() will
* invoke irq_enable() under the hood.
*/
irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
break;
}
default:
desc->depth--;
}
}
/**
* enable_irq - enable handling of an irq
* @irq: Interrupt to enable
*
* Undoes the effect of one call to disable_irq(). If this
* matches the last disable, processing of interrupts on this
* IRQ line is re-enabled.
*
* This function may be called from IRQ context only when
* desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
*/
void enable_irq(unsigned int irq)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
if (!desc)
return;
if (WARN(!desc->irq_data.chip,
KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
goto out;
__enable_irq(desc);
out:
irq_put_desc_busunlock(desc, flags);
}
EXPORT_SYMBOL(enable_irq);
/**
* enable_nmi - enable handling of an nmi
* @irq: Interrupt to enable
*
* The interrupt to enable must have been requested through request_nmi.
* Undoes the effect of one call to disable_nmi(). If this
* matches the last disable, processing of interrupts on this
* IRQ line is re-enabled.
*/
void enable_nmi(unsigned int irq)
{
enable_irq(irq);
}
static int set_irq_wake_real(unsigned int irq, unsigned int on)
{
struct irq_desc *desc = irq_to_desc(irq);
int ret = -ENXIO;
if (irq_desc_get_chip(desc)->flags & IRQCHIP_SKIP_SET_WAKE)
return 0;
if (desc->irq_data.chip->irq_set_wake)
ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
return ret;
}
/**
* irq_set_irq_wake - control irq power management wakeup
* @irq: interrupt to control
* @on: enable/disable power management wakeup
*
* Enable/disable power management wakeup mode, which is
* disabled by default. Enables and disables must match,
* just as they match for non-wakeup mode support.
*
* Wakeup mode lets this IRQ wake the system from sleep
* states like "suspend to RAM".
*
* Note: irq enable/disable state is completely orthogonal
* to the enable/disable state of irq wake. An irq can be
* disabled with disable_irq() and still wake the system as
* long as the irq has wake enabled. If this does not hold,
* then the underlying irq chip and the related driver need
* to be investigated.
*/
int irq_set_irq_wake(unsigned int irq, unsigned int on)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
int ret = 0;
if (!desc)
return -EINVAL;
/* Don't use NMIs as wake up interrupts please */
if (irq_is_nmi(desc)) {
ret = -EINVAL;
goto out_unlock;
}
/* wakeup-capable irqs can be shared between drivers that
* don't need to have the same sleep mode behaviors.
*/
if (on) {
if (desc->wake_depth++ == 0) {
ret = set_irq_wake_real(irq, on);
if (ret)
desc->wake_depth = 0;
else
irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
}
} else {
if (desc->wake_depth == 0) {
WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
} else if (--desc->wake_depth == 0) {
ret = set_irq_wake_real(irq, on);
if (ret)
desc->wake_depth = 1;
else
irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
}
}
out_unlock:
irq_put_desc_busunlock(desc, flags);
return ret;
}
EXPORT_SYMBOL(irq_set_irq_wake);
/*
* Internal function that tells the architecture code whether a
* particular irq has been exclusively allocated or is available
* for driver use.
*/
int can_request_irq(unsigned int irq, unsigned long irqflags)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
int canrequest = 0;
if (!desc)
return 0;
if (irq_settings_can_request(desc)) {
if (!desc->action ||
irqflags & desc->action->flags & IRQF_SHARED)
canrequest = 1;
}
irq_put_desc_unlock(desc, flags);
return canrequest;
}
int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
{
struct irq_chip *chip = desc->irq_data.chip;
int ret, unmask = 0;
if (!chip || !chip->irq_set_type) {
/*
* IRQF_TRIGGER_* but the PIC does not support multiple
* flow-types?
*/
pr_debug("No set_type function for IRQ %d (%s)\n",
irq_desc_get_irq(desc),
chip ? (chip->name ? : "unknown") : "unknown");
return 0;
}
if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
if (!irqd_irq_masked(&desc->irq_data))
mask_irq(desc);
if (!irqd_irq_disabled(&desc->irq_data))
unmask = 1;
}
/* Mask all flags except trigger mode */
flags &= IRQ_TYPE_SENSE_MASK;
ret = chip->irq_set_type(&desc->irq_data, flags);
switch (ret) {
case IRQ_SET_MASK_OK:
case IRQ_SET_MASK_OK_DONE:
irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
irqd_set(&desc->irq_data, flags);
fallthrough;
case IRQ_SET_MASK_OK_NOCOPY:
flags = irqd_get_trigger_type(&desc->irq_data);
irq_settings_set_trigger_mask(desc, flags);
irqd_clear(&desc->irq_data, IRQD_LEVEL);
irq_settings_clr_level(desc);
if (flags & IRQ_TYPE_LEVEL_MASK) {
irq_settings_set_level(desc);
irqd_set(&desc->irq_data, IRQD_LEVEL);
}
ret = 0;
break;
default:
pr_err("Setting trigger mode %lu for irq %u failed (%pS)\n",
flags, irq_desc_get_irq(desc), chip->irq_set_type);
}
if (unmask)
unmask_irq(desc);
return ret;
}
#ifdef CONFIG_HARDIRQS_SW_RESEND
int irq_set_parent(int irq, int parent_irq)
{
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
if (!desc)
return -EINVAL;
desc->parent_irq = parent_irq;
irq_put_desc_unlock(desc, flags);
return 0;
}
EXPORT_SYMBOL_GPL(irq_set_parent);
#endif
/*
* Default primary interrupt handler for threaded interrupts. Is
* assigned as primary handler when request_threaded_irq is called
* with handler == NULL. Useful for oneshot interrupts.
*/
static irqreturn_t irq_default_primary_handler(int irq, void *dev_id)
{
return IRQ_WAKE_THREAD;
}
/*
* Primary handler for nested threaded interrupts. Should never be
* called.
*/
static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
{
WARN(1, "Primary handler called for nested irq %d\n", irq);
return IRQ_NONE;
}
static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
{
WARN(1, "Secondary action handler called for irq %d\n", irq);
return IRQ_NONE;
}
#ifdef CONFIG_SMP
/*
* Check whether we need to change the affinity of the interrupt thread.
*/
static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
{
cpumask_var_t mask;
bool valid = false;
if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
return;
__set_current_state(TASK_RUNNING);
/*
* In case we are out of memory we set IRQTF_AFFINITY again and
* try again next time
*/
if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
set_bit(IRQTF_AFFINITY, &action->thread_flags);
return;
}
raw_spin_lock_irq(&desc->lock);
/*
* This code is triggered unconditionally. Check the affinity
* mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
*/
if (cpumask_available(desc->irq_common_data.affinity)) {
const struct cpumask *m;
m = irq_data_get_effective_affinity_mask(&desc->irq_data);
cpumask_copy(mask, m);
valid = true;
}
raw_spin_unlock_irq(&desc->lock);
if (valid)
set_cpus_allowed_ptr(current, mask);
free_cpumask_var(mask);
}
#else
static inline void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif
static int irq_wait_for_interrupt(struct irq_desc *desc,
struct irqaction *action)
{
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
irq_thread_check_affinity(desc, action);
if (kthread_should_stop()) {
/* may need to run one last time */
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
__set_current_state(TASK_RUNNING);
return 0;
}
__set_current_state(TASK_RUNNING);
return -1;
}
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
__set_current_state(TASK_RUNNING);
return 0;
}
schedule();
}
}
/*
* Oneshot interrupts keep the irq line masked until the threaded
* handler finished. unmask if the interrupt has not been disabled and
* is marked MASKED.
*/
static void irq_finalize_oneshot(struct irq_desc *desc,
struct irqaction *action)
{
if (!(desc->istate & IRQS_ONESHOT) ||
action->handler == irq_forced_secondary_handler)
return;
again:
chip_bus_lock(desc);
raw_spin_lock_irq(&desc->lock);
/*
* Implausible though it may be we need to protect us against
* the following scenario:
*
* The thread is faster done than the hard interrupt handler
* on the other CPU. If we unmask the irq line then the
* interrupt can come in again and masks the line, leaves due
* to IRQS_INPROGRESS and the irq line is masked forever.
*
* This also serializes the state of shared oneshot handlers
* versus "desc->threads_oneshot |= action->thread_mask;" in
* irq_wake_thread(). See the comment there which explains the
* serialization.
*/
if (unlikely(irqd_irq_inprogress(&desc->irq_data))) {
raw_spin_unlock_irq(&desc->lock);
chip_bus_sync_unlock(desc);
cpu_relax();
goto again;
}
/*
* Now check again, whether the thread should run. Otherwise
* we would clear the threads_oneshot bit of this thread which
* was just set.
*/
if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
goto out_unlock;
desc->threads_oneshot &= ~action->thread_mask;
if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
irqd_irq_masked(&desc->irq_data))
unmask_threaded_irq(desc);
out_unlock:
raw_spin_unlock_irq(&desc->lock);
chip_bus_sync_unlock(desc);
}
/*
* Interrupts explicitly requested as threaded interrupts want to be
* preemptible - many of them need to sleep and wait for slow busses to
* complete.
*/
static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
irqreturn_t ret = action->thread_fn(action->irq, action->dev_id);
if (ret == IRQ_HANDLED)
atomic_inc(&desc->threads_handled);
irq_finalize_oneshot(desc, action);
return ret;
}
/*
* Interrupts which are not explicitly requested as threaded
* interrupts rely on the implicit bh/preempt disable of the hard irq
* context. So we need to disable bh here to avoid deadlocks and other
* side effects.
*/
static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
irqreturn_t ret;
local_bh_disable();
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_disable();
ret = irq_thread_fn(desc, action);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_enable();
local_bh_enable();
return ret;
}
void wake_threads_waitq(struct irq_desc *desc)
{
if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
static void irq_thread_dtor(struct callback_head *unused)
{
struct task_struct *tsk = current;
struct irq_desc *desc;
struct irqaction *action;
if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
return;
action = kthread_data(tsk);
pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
tsk->comm, tsk->pid, action->irq);
desc = irq_to_desc(action->irq);
/*
* If IRQTF_RUNTHREAD is set, we need to decrement
* desc->threads_active and wake possible waiters.
*/
if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
wake_threads_waitq(desc);
/* Prevent a stale desc->threads_oneshot */
irq_finalize_oneshot(desc, action);
}
static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
{
struct irqaction *secondary = action->secondary;
if (WARN_ON_ONCE(!secondary))
return;
raw_spin_lock_irq(&desc->lock);
__irq_wake_thread(desc, secondary);
raw_spin_unlock_irq(&desc->lock);
}
/*
* Internal function to notify that a interrupt thread is ready.
*/
static void irq_thread_set_ready(struct irq_desc *desc,
struct irqaction *action)
{
set_bit(IRQTF_READY, &action->thread_flags);
wake_up(&desc->wait_for_threads);
}
/*
* Internal function to wake up a interrupt thread and wait until it is
* ready.
*/
static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc,
struct irqaction *action)
{
if (!action || !action->thread)
return;
wake_up_process(action->thread);
wait_event(desc->wait_for_threads,
test_bit(IRQTF_READY, &action->thread_flags));
}
/*
* Interrupt handler thread
*/
static int irq_thread(void *data)
{
struct callback_head on_exit_work;
struct irqaction *action = data;
struct irq_desc *desc = irq_to_desc(action->irq);
irqreturn_t (*handler_fn)(struct irq_desc *desc,
struct irqaction *action);
irq_thread_set_ready(desc, action);
sched_set_fifo(current);
if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD,
&action->thread_flags))
handler_fn = irq_forced_thread_fn;
else
handler_fn = irq_thread_fn;
init_task_work(&on_exit_work, irq_thread_dtor);
task_work_add(current, &on_exit_work, TWA_NONE);
while (!irq_wait_for_interrupt(desc, action)) {
irqreturn_t action_ret;
action_ret = handler_fn(desc, action);
if (action_ret == IRQ_WAKE_THREAD)
irq_wake_secondary(desc, action);
wake_threads_waitq(desc);
}
/*
* This is the regular exit path. __free_irq() is stopping the
* thread via kthread_stop() after calling
* synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
* oneshot mask bit can be set.
*/
task_work_cancel_func(current, irq_thread_dtor);
return 0;
}
/**
* irq_wake_thread - wake the irq thread for the action identified by dev_id
* @irq: Interrupt line
* @dev_id: Device identity for which the thread should be woken
*
*/
void irq_wake_thread(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned long flags;
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return;
raw_spin_lock_irqsave(&desc->lock, flags);
for_each_action_of_desc(desc, action) {
if (action->dev_id == dev_id) {
if (action->thread)
__irq_wake_thread(desc, action);
break;
}
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL_GPL(irq_wake_thread);
static int irq_setup_forced_threading(struct irqaction *new)
{
if (!force_irqthreads())
return 0;
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return 0;
/*
* No further action required for interrupts which are requested as
* threaded interrupts already
*/
if (new->handler == irq_default_primary_handler)
return 0;
new->flags |= IRQF_ONESHOT;
/*
* Handle the case where we have a real primary handler and a
* thread handler. We force thread them as well by creating a
* secondary action.
*/
if (new->handler && new->thread_fn) {
/* Allocate the secondary action */
new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!new->secondary)
return -ENOMEM;
new->secondary->handler = irq_forced_secondary_handler;
new->secondary->thread_fn = new->thread_fn;
new->secondary->dev_id = new->dev_id;
new->secondary->irq = new->irq;
new->secondary->name = new->name;
}
/* Deal with the primary handler */
set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
new->thread_fn = new->handler;
new->handler = irq_default_primary_handler;
return 0;
}
static int irq_request_resources(struct irq_desc *desc)
{
struct irq_data *d = &desc->irq_data;
struct irq_chip *c = d->chip;
return c->irq_request_resources ? c->irq_request_resources(d) : 0;
}
static void irq_release_resources(struct irq_desc *desc)
{
struct irq_data *d = &desc->irq_data;
struct irq_chip *c = d->chip;
if (c->irq_release_resources)
c->irq_release_resources(d);
}
static bool irq_supports_nmi(struct irq_desc *desc)
{
struct irq_data *d = irq_desc_get_irq_data(desc);
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
/* Only IRQs directly managed by the root irqchip can be set as NMI */
if (d->parent_data)
return false;
#endif
/* Don't support NMIs for chips behind a slow bus */
if (d->chip->irq_bus_lock || d->chip->irq_bus_sync_unlock)
return false;
return d->chip->flags & IRQCHIP_SUPPORTS_NMI;
}
static int irq_nmi_setup(struct irq_desc *desc)
{
struct irq_data *d = irq_desc_get_irq_data(desc);
struct irq_chip *c = d->chip;
return c->irq_nmi_setup ? c->irq_nmi_setup(d) : -EINVAL;
}
static void irq_nmi_teardown(struct irq_desc *desc)
{
struct irq_data *d = irq_desc_get_irq_data(desc);
struct irq_chip *c = d->chip;
if (c->irq_nmi_teardown)
c->irq_nmi_teardown(d);
}
static int
setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
{
struct task_struct *t;
if (!secondary) {
t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
new->name);
} else {
t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq,
new->name);
}
if (IS_ERR(t))
return PTR_ERR(t);
/*
* We keep the reference to the task struct even if
* the thread dies to avoid that the interrupt code
* references an already freed task_struct.
*/
new->thread = get_task_struct(t);
/*
* Tell the thread to set its affinity. This is
* important for shared interrupt handlers as we do
* not invoke setup_affinity() for the secondary
* handlers as everything is already set up. Even for
* interrupts marked with IRQF_NO_BALANCE this is
* correct as we want the thread to move to the cpu(s)
* on which the requesting code placed the interrupt.
*/
set_bit(IRQTF_AFFINITY, &new->thread_flags);
return 0;
}
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
*
* Locking rules:
*
* desc->request_mutex Provides serialization against a concurrent free_irq()
* chip_bus_lock Provides serialization for slow bus operations
* desc->lock Provides serialization against hard interrupts
*
* chip_bus_lock and desc->lock are sufficient for all other management and
* interrupt related functions. desc->request_mutex solely serializes
* request/free_irq().
*/
static int
__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
{
struct irqaction *old, **old_ptr;
unsigned long flags, thread_mask = 0;
int ret, nested, shared = 0;
if (!desc)
return -EINVAL;
if (desc->irq_data.chip == &no_irq_chip)
return -ENOSYS;
if (!try_module_get(desc->owner))
return -ENODEV;
new->irq = irq;
/*
* If the trigger type is not specified by the caller,
* then use the default for this interrupt.
*/
if (!(new->flags & IRQF_TRIGGER_MASK))
new->flags |= irqd_get_trigger_type(&desc->irq_data);
/*
* Check whether the interrupt nests into another interrupt
* thread.
*/
nested = irq_settings_is_nested_thread(desc);
if (nested) {
if (!new->thread_fn) {
ret = -EINVAL;
goto out_mput;
}
/*
* Replace the primary handler which was provided from
* the driver for non nested interrupt handling by the
* dummy function which warns when called.
*/
new->handler = irq_nested_primary_handler;
} else {
if (irq_settings_can_thread(desc)) {
ret = irq_setup_forced_threading(new);
if (ret)
goto out_mput;
}
}
/*
* Create a handler thread when a thread function is supplied
* and the interrupt does not nest into another interrupt
* thread.
*/
if (new->thread_fn && !nested) {
ret = setup_irq_thread(new, irq, false);
if (ret)
goto out_mput;
if (new->secondary) {
ret = setup_irq_thread(new->secondary, irq, true);
if (ret)
goto out_thread;
}
}
/*
* Drivers are often written to work w/o knowledge about the
* underlying irq chip implementation, so a request for a
* threaded irq without a primary hard irq context handler
* requires the ONESHOT flag to be set. Some irq chips like
* MSI based interrupts are per se one shot safe. Check the
* chip flags, so we can avoid the unmask dance at the end of
* the threaded handler for those.
*/
if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)
new->flags &= ~IRQF_ONESHOT;
/*
* Protects against a concurrent __free_irq() call which might wait
* for synchronize_hardirq() to complete without holding the optional
* chip bus lock and desc->lock. Also protects against handing out
* a recycled oneshot thread_mask bit while it's still in use by
* its previous owner.
*/
mutex_lock(&desc->request_mutex);
/*
* Acquire bus lock as the irq_request_resources() callback below
* might rely on the serialization or the magic power management
* functions which are abusing the irq_bus_lock() callback,
*/
chip_bus_lock(desc);
/* First installed action requests resources. */
if (!desc->action) {
ret = irq_request_resources(desc);
if (ret) {
pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
new->name, irq, desc->irq_data.chip->name);
goto out_bus_unlock;
}
}
/*
* The following block of code has to be executed atomically
* protected against a concurrent interrupt and any of the other
* management calls which are not serialized via
* desc->request_mutex or the optional bus lock.
*/
raw_spin_lock_irqsave(&desc->lock, flags);
old_ptr = &desc->action;
old = *old_ptr;
if (old) {
/*
* Can't share interrupts unless both agree to and are
* the same type (level, edge, polarity). So both flag
* fields must have IRQF_SHARED set and the bits which
* set the trigger type must match. Also all must
* agree on ONESHOT.
* Interrupt lines used for NMIs cannot be shared.
*/
unsigned int oldtype;
if (irq_is_nmi(desc)) {
pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n",
new->name, irq, desc->irq_data.chip->name);
ret = -EINVAL;
goto out_unlock;
}
/*
* If nobody did set the configuration before, inherit
* the one provided by the requester.
*/
if (irqd_trigger_type_was_set(&desc->irq_data)) {
oldtype = irqd_get_trigger_type(&desc->irq_data);
} else {
oldtype = new->flags & IRQF_TRIGGER_MASK;
irqd_set_trigger_type(&desc->irq_data, oldtype);
}
if (!((old->flags & new->flags) & IRQF_SHARED) ||
(oldtype != (new->flags & IRQF_TRIGGER_MASK)))
goto mismatch;
if ((old->flags & IRQF_ONESHOT) &&
(new->flags & IRQF_COND_ONESHOT))
new->flags |= IRQF_ONESHOT;
else if ((old->flags ^ new->flags) & IRQF_ONESHOT)
goto mismatch;
/* All handlers must agree on per-cpuness */
if ((old->flags & IRQF_PERCPU) !=
(new->flags & IRQF_PERCPU))
goto mismatch;
/* add new interrupt at end of irq queue */
do {
/*
* Or all existing action->thread_mask bits,
* so we can find the next zero bit for this
* new action.
*/
thread_mask |= old->thread_mask;
old_ptr = &old->next;
old = *old_ptr;
} while (old);
shared = 1;
}
/*
* Setup the thread mask for this irqaction for ONESHOT. For
* !ONESHOT irqs the thread mask is 0 so we can avoid a
* conditional in irq_wake_thread().
*/
if (new->flags & IRQF_ONESHOT) {
/*
* Unlikely to have 32 resp 64 irqs sharing one line,
* but who knows.
*/
if (thread_mask == ~0UL) {
ret = -EBUSY;
goto out_unlock;
}
/*
* The thread_mask for the action is or'ed to
* desc->thread_active to indicate that the
* IRQF_ONESHOT thread handler has been woken, but not
* yet finished. The bit is cleared when a thread
* completes. When all threads of a shared interrupt
* line have completed desc->threads_active becomes
* zero and the interrupt line is unmasked. See
* handle.c:irq_wake_thread() for further information.
*
* If no thread is woken by primary (hard irq context)
* interrupt handlers, then desc->threads_active is
* also checked for zero to unmask the irq line in the
* affected hard irq flow handlers
* (handle_[fasteoi|level]_irq).
*
* The new action gets the first zero bit of
* thread_mask assigned. See the loop above which or's
* all existing action->thread_mask bits.
*/
new->thread_mask = 1UL << ffz(thread_mask);
} else if (new->handler == irq_default_primary_handler &&
!(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
/*
* The interrupt was requested with handler = NULL, so
* we use the default primary handler for it. But it
* does not have the oneshot flag set. In combination
* with level interrupts this is deadly, because the
* default primary handler just wakes the thread, then
* the irq lines is reenabled, but the device still
* has the level irq asserted. Rinse and repeat....
*
* While this works for edge type interrupts, we play
* it safe and reject unconditionally because we can't
* say for sure which type this interrupt really
* has. The type flags are unreliable as the
* underlying chip implementation can override them.
*/
pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n",
new->name, irq);
ret = -EINVAL;
goto out_unlock;
}
if (!shared) {
/* Setup the type (level, edge polarity) if configured: */
if (new->flags & IRQF_TRIGGER_MASK) {
ret = __irq_set_trigger(desc,
new->flags & IRQF_TRIGGER_MASK);
if (ret)
goto out_unlock;
}
/*
* Activate the interrupt. That activation must happen
* independently of IRQ_NOAUTOEN. request_irq() can fail
* and the callers are supposed to handle
* that. enable_irq() of an interrupt requested with
* IRQ_NOAUTOEN is not supposed to fail. The activation
* keeps it in shutdown mode, it merily associates
* resources if necessary and if that's not possible it
* fails. Interrupts which are in managed shutdown mode
* will simply ignore that activation request.
*/
ret = irq_activate(desc);
if (ret)
goto out_unlock;
desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
IRQS_ONESHOT | IRQS_WAITING);
irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
if (new->flags & IRQF_PERCPU) {
irqd_set(&desc->irq_data, IRQD_PER_CPU);
irq_settings_set_per_cpu(desc);
if (new->flags & IRQF_NO_DEBUG)
irq_settings_set_no_debug(desc);
}
if (noirqdebug)
irq_settings_set_no_debug(desc);
if (new->flags & IRQF_ONESHOT)
desc->istate |= IRQS_ONESHOT;
/* Exclude IRQ from balancing if requested */
if (new->flags & IRQF_NOBALANCING) {
irq_settings_set_no_balancing(desc);
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
if (!(new->flags & IRQF_NO_AUTOEN) &&
irq_settings_can_autoenable(desc)) {
irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
} else {
/*
* Shared interrupts do not go well with disabling
* auto enable. The sharing interrupt might request
* it while it's still disabled and then wait for
* interrupts forever.
*/
WARN_ON_ONCE(new->flags & IRQF_SHARED);
/* Undo nested disables: */
desc->depth = 1;
}
} else if (new->flags & IRQF_TRIGGER_MASK) {
unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
unsigned int omsk = irqd_get_trigger_type(&desc->irq_data);
if (nmsk != omsk)
/* hope the handler works with current trigger mode */
pr_warn("irq %d uses trigger mode %u; requested %u\n",
irq, omsk, nmsk);
}
*old_ptr = new;
irq_pm_install_action(desc, new);
/* Reset broken irq detection when installing new handler */
desc->irq_count = 0;
desc->irqs_unhandled = 0;
/*
* Check whether we disabled the irq via the spurious handler
* before. Reenable it and give it another chance.
*/
if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
desc->istate &= ~IRQS_SPURIOUS_DISABLED;
__enable_irq(desc);
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
chip_bus_sync_unlock(desc);
mutex_unlock(&desc->request_mutex);
irq_setup_timings(desc, new);
wake_up_and_wait_for_irq_thread_ready(desc, new);
wake_up_and_wait_for_irq_thread_ready(desc, new->secondary);
register_irq_proc(irq, desc);
new->dir = NULL;
register_handler_proc(irq, new);
return 0;
mismatch:
if (!(new->flags & IRQF_PROBE_SHARED)) {
pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
irq, new->flags, new->name, old->flags, old->name);
#ifdef CONFIG_DEBUG_SHIRQ
dump_stack();
#endif
}
ret = -EBUSY;
out_unlock:
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (!desc->action)
irq_release_resources(desc);
out_bus_unlock:
chip_bus_sync_unlock(desc);
mutex_unlock(&desc->request_mutex);
out_thread:
if (new->thread) {
struct task_struct *t = new->thread;
new->thread = NULL;
kthread_stop_put(t);
}
if (new->secondary && new->secondary->thread) {
struct task_struct *t = new->secondary->thread;
new->secondary->thread = NULL;
kthread_stop_put(t);
}
out_mput:
module_put(desc->owner);
return ret;
}
/*
* Internal function to unregister an irqaction - used to free
* regular and special interrupts that are part of the architecture.
*/
static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
{
unsigned irq = desc->irq_data.irq;
struct irqaction *action, **action_ptr;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
mutex_lock(&desc->request_mutex);
chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, flags);
/*
* There can be multiple actions per IRQ descriptor, find the right
* one based on the dev_id:
*/
action_ptr = &desc->action;
for (;;) {
action = *action_ptr;
if (!action) {
WARN(1, "Trying to free already-free IRQ %d\n", irq);
raw_spin_unlock_irqrestore(&desc->lock, flags);
chip_bus_sync_unlock(desc);
mutex_unlock(&desc->request_mutex);
return NULL;
}
if (action->dev_id == dev_id)
break;
action_ptr = &action->next;
}
/* Found it - now remove it from the list of entries: */
*action_ptr = action->next;
irq_pm_remove_action(desc, action);
/* If this was the last handler, shut down the IRQ line: */
if (!desc->action) {
irq_settings_clr_disable_unlazy(desc);
/* Only shutdown. Deactivate after synchronize_hardirq() */
irq_shutdown(desc);
}
#ifdef CONFIG_SMP
/* make sure affinity_hint is cleaned up */
if (WARN_ON_ONCE(desc->affinity_hint))
desc->affinity_hint = NULL;
#endif
raw_spin_unlock_irqrestore(&desc->lock, flags);
/*
* Drop bus_lock here so the changes which were done in the chip
* callbacks above are synced out to the irq chips which hang
* behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
*
* Aside of that the bus_lock can also be taken from the threaded
* handler in irq_finalize_oneshot() which results in a deadlock
* because kthread_stop() would wait forever for the thread to
* complete, which is blocked on the bus lock.
*
* The still held desc->request_mutex() protects against a
* concurrent request_irq() of this irq so the release of resources
* and timing data is properly serialized.
*/
chip_bus_sync_unlock(desc);
unregister_handler_proc(irq, action);
/*
* Make sure it's not being used on another CPU and if the chip
* supports it also make sure that there is no (not yet serviced)
* interrupt in flight at the hardware level.
*/
__synchronize_irq(desc);
#ifdef CONFIG_DEBUG_SHIRQ
/*
* It's a shared IRQ -- the driver ought to be prepared for an IRQ
* event to happen even now it's being freed, so let's make sure that
* is so by doing an extra call to the handler ....
*
* ( We do this after actually deregistering it, to make sure that a
* 'real' IRQ doesn't run in parallel with our fake. )
*/
if (action->flags & IRQF_SHARED) {
local_irq_save(flags);
action->handler(irq, dev_id);
local_irq_restore(flags);
}
#endif
/*
* The action has already been removed above, but the thread writes
* its oneshot mask bit when it completes. Though request_mutex is
* held across this which prevents __setup_irq() from handing out
* the same bit to a newly requested action.
*/
if (action->thread) {
kthread_stop_put(action->thread);
if (action->secondary && action->secondary->thread)
kthread_stop_put(action->secondary->thread);
}
/* Last action releases resources */
if (!desc->action) {
/*
* Reacquire bus lock as irq_release_resources() might
* require it to deallocate resources over the slow bus.
*/
chip_bus_lock(desc);
/*
* There is no interrupt on the fly anymore. Deactivate it
* completely.
*/
raw_spin_lock_irqsave(&desc->lock, flags);
irq_domain_deactivate_irq(&desc->irq_data);
raw_spin_unlock_irqrestore(&desc->lock, flags);
irq_release_resources(desc);
chip_bus_sync_unlock(desc);
irq_remove_timings(desc);
}
mutex_unlock(&desc->request_mutex);
irq_chip_pm_put(&desc->irq_data);
module_put(desc->owner);
kfree(action->secondary);
return action;
}
/**
* free_irq - free an interrupt allocated with request_irq
* @irq: Interrupt line to free
* @dev_id: Device identity to free
*
* Remove an interrupt handler. The handler is removed and if the
* interrupt line is no longer in use by any driver it is disabled.
* On a shared IRQ the caller must ensure the interrupt is disabled
* on the card it drives before calling this function. The function
* does not return until any executing interrupts for this IRQ
* have completed.
*
* This function must not be called from interrupt context.
*
* Returns the devname argument passed to request_irq.
*/
const void *free_irq(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
const char *devname;
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return NULL;
#ifdef CONFIG_SMP
if (WARN_ON(desc->affinity_notify))
desc->affinity_notify = NULL;
#endif
action = __free_irq(desc, dev_id);
if (!action)
return NULL;
devname = action->name;
kfree(action);
return devname;
}
EXPORT_SYMBOL(free_irq);
/* This function must be called with desc->lock held */
static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc)
{
const char *devname = NULL;
desc->istate &= ~IRQS_NMI;
if (!WARN_ON(desc->action == NULL)) {
irq_pm_remove_action(desc, desc->action);
devname = desc->action->name;
unregister_handler_proc(irq, desc->action);
kfree(desc->action);
desc->action = NULL;
}
irq_settings_clr_disable_unlazy(desc);
irq_shutdown_and_deactivate(desc);
irq_release_resources(desc);
irq_chip_pm_put(&desc->irq_data);
module_put(desc->owner);
return devname;
}
const void *free_nmi(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
const void *devname;
if (!desc || WARN_ON(!irq_is_nmi(desc)))
return NULL;
if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return NULL;
/* NMI still enabled */
if (WARN_ON(desc->depth == 0))
disable_nmi_nosync(irq);
raw_spin_lock_irqsave(&desc->lock, flags);
irq_nmi_teardown(desc);
devname = __cleanup_nmi(irq, desc);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return devname;
}
/**
* request_threaded_irq - allocate an interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* Primary handler for threaded interrupts.
* If handler is NULL and thread_fn != NULL
* the default primary handler is installed.
* @thread_fn: Function called from the irq handler thread
* If NULL, no irq thread is created
* @irqflags: Interrupt type flags
* @devname: An ascii name for the claiming device
* @dev_id: A cookie passed back to the handler function
*
* This call allocates interrupt resources and enables the
* interrupt line and IRQ handling. From the point this
* call is made your handler function may be invoked. Since
* your handler function must clear any interrupt the board
* raises, you must take care both to initialise your hardware
* and to set up the interrupt handler in the right order.
*
* If you want to set up a threaded irq handler for your device
* then you need to supply @handler and @thread_fn. @handler is
* still called in hard interrupt context and has to check
* whether the interrupt originates from the device. If yes it
* needs to disable the interrupt on the device and return
* IRQ_WAKE_THREAD which will wake up the handler thread and run
* @thread_fn. This split handler design is necessary to support
* shared interrupts.
*
* Dev_id must be globally unique. Normally the address of the
* device data structure is used as the cookie. Since the handler
* receives this value it makes sense to use it.
*
* If your interrupt is shared you must pass a non NULL dev_id
* as this is required when freeing the interrupt.
*
* Flags:
*
* IRQF_SHARED Interrupt is shared
* IRQF_TRIGGER_* Specify active edge(s) or level
* IRQF_ONESHOT Run thread_fn with interrupt line masked
*/
int request_threaded_irq(unsigned int irq, irq_handler_t handler,
irq_handler_t thread_fn, unsigned long irqflags,
const char *devname, void *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
int retval;
if (irq == IRQ_NOTCONNECTED)
return -ENOTCONN;
/*
* Sanity-check: shared interrupts must pass in a real dev-ID,
* otherwise we'll have trouble later trying to figure out
* which interrupt is which (messes up the interrupt freeing
* logic etc).
*
* Also shared interrupts do not go well with disabling auto enable.
* The sharing interrupt might request it while it's still disabled
* and then wait for interrupts forever.
*
* Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
* it cannot be set along with IRQF_NO_SUSPEND.
*/
if (((irqflags & IRQF_SHARED) && !dev_id) ||
((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) ||
(!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc)
return -EINVAL;
if (!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return -EINVAL;
if (!handler) {
if (!thread_fn)
return -EINVAL;
handler = irq_default_primary_handler;
}
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->thread_fn = thread_fn;
action->flags = irqflags;
action->name = devname;
action->dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
if (retval < 0) {
kfree(action);
return retval;
}
retval = __setup_irq(irq, desc, action);
if (retval) {
irq_chip_pm_put(&desc->irq_data);
kfree(action->secondary);
kfree(action);
}
#ifdef CONFIG_DEBUG_SHIRQ_FIXME
if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
* to happen immediately, so let's make sure....
* We disable the irq to make sure that a 'real' IRQ doesn't
* run in parallel with our fake.
*/
unsigned long flags;
disable_irq(irq);
local_irq_save(flags);
handler(irq, dev_id);
local_irq_restore(flags);
enable_irq(irq);
}
#endif
return retval;
}
EXPORT_SYMBOL(request_threaded_irq);
/**
* request_any_context_irq - allocate an interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* Threaded handler for threaded interrupts.
* @flags: Interrupt type flags
* @name: An ascii name for the claiming device
* @dev_id: A cookie passed back to the handler function
*
* This call allocates interrupt resources and enables the
* interrupt line and IRQ handling. It selects either a
* hardirq or threaded handling method depending on the
* context.
*
* On failure, it returns a negative value. On success,
* it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
*/
int request_any_context_irq(unsigned int irq, irq_handler_t handler,
unsigned long flags, const char *name, void *dev_id)
{
struct irq_desc *desc;
int ret;
if (irq == IRQ_NOTCONNECTED)
return -ENOTCONN;
desc = irq_to_desc(irq);
if (!desc)
return -EINVAL;
if (irq_settings_is_nested_thread(desc)) {
ret = request_threaded_irq(irq, NULL, handler,
flags, name, dev_id);
return !ret ? IRQC_IS_NESTED : ret;
}
ret = request_irq(irq, handler, flags, name, dev_id);
return !ret ? IRQC_IS_HARDIRQ : ret;
}
EXPORT_SYMBOL_GPL(request_any_context_irq);
/**
* request_nmi - allocate an interrupt line for NMI delivery
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* Threaded handler for threaded interrupts.
* @irqflags: Interrupt type flags
* @name: An ascii name for the claiming device
* @dev_id: A cookie passed back to the handler function
*
* This call allocates interrupt resources and enables the
* interrupt line and IRQ handling. It sets up the IRQ line
* to be handled as an NMI.
*
* An interrupt line delivering NMIs cannot be shared and IRQ handling
* cannot be threaded.
*
* Interrupt lines requested for NMI delivering must produce per cpu
* interrupts and have auto enabling setting disabled.
*
* Dev_id must be globally unique. Normally the address of the
* device data structure is used as the cookie. Since the handler
* receives this value it makes sense to use it.
*
* If the interrupt line cannot be used to deliver NMIs, function
* will fail and return a negative value.
*/
int request_nmi(unsigned int irq, irq_handler_t handler,
unsigned long irqflags, const char *name, void *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
unsigned long flags;
int retval;
if (irq == IRQ_NOTCONNECTED)
return -ENOTCONN;
/* NMI cannot be shared, used for Polling */
if (irqflags & (IRQF_SHARED | IRQF_COND_SUSPEND | IRQF_IRQPOLL))
return -EINVAL;
if (!(irqflags & IRQF_PERCPU))
return -EINVAL;
if (!handler)
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc || (irq_settings_can_autoenable(desc) &&
!(irqflags & IRQF_NO_AUTOEN)) ||
!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
!irq_supports_nmi(desc))
return -EINVAL;
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->flags = irqflags | IRQF_NO_THREAD | IRQF_NOBALANCING;
action->name = name;
action->dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
if (retval < 0)
goto err_out;
retval = __setup_irq(irq, desc, action);
if (retval)
goto err_irq_setup;
raw_spin_lock_irqsave(&desc->lock, flags);
/* Setup NMI state */
desc->istate |= IRQS_NMI;
retval = irq_nmi_setup(desc);
if (retval) {
__cleanup_nmi(irq, desc);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return -EINVAL;
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
err_irq_setup:
irq_chip_pm_put(&desc->irq_data);
err_out:
kfree(action);
return retval;
}
void enable_percpu_irq(unsigned int irq, unsigned int type)
{
unsigned int cpu = smp_processor_id();
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return;
/*
* If the trigger type is not specified by the caller, then
* use the default for this interrupt.
*/
type &= IRQ_TYPE_SENSE_MASK;
if (type == IRQ_TYPE_NONE)
type = irqd_get_trigger_type(&desc->irq_data);
if (type != IRQ_TYPE_NONE) {
int ret;
ret = __irq_set_trigger(desc, type);
if (ret) {
WARN(1, "failed to set type for IRQ%d\n", irq);
goto out;
}
}
irq_percpu_enable(desc, cpu);
out:
irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(enable_percpu_irq);
void enable_percpu_nmi(unsigned int irq, unsigned int type)
{
enable_percpu_irq(irq, type);
}
/**
* irq_percpu_is_enabled - Check whether the per cpu irq is enabled
* @irq: Linux irq number to check for
*
* Must be called from a non migratable context. Returns the enable
* state of a per cpu interrupt on the current cpu.
*/
bool irq_percpu_is_enabled(unsigned int irq)
{
unsigned int cpu = smp_processor_id();
struct irq_desc *desc;
unsigned long flags;
bool is_enabled;
desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return false;
is_enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
irq_put_desc_unlock(desc, flags);
return is_enabled;
}
EXPORT_SYMBOL_GPL(irq_percpu_is_enabled);
void disable_percpu_irq(unsigned int irq)
{
unsigned int cpu = smp_processor_id();
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return;
irq_percpu_disable(desc, cpu);
irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(disable_percpu_irq);
void disable_percpu_nmi(unsigned int irq)
{
disable_percpu_irq(irq);
}
/*
* Internal function to unregister a percpu irqaction.
*/
static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
if (!desc)
return NULL;
raw_spin_lock_irqsave(&desc->lock, flags);
action = desc->action;
if (!action || action->percpu_dev_id != dev_id) {
WARN(1, "Trying to free already-free IRQ %d\n", irq);
goto bad;
}
if (!cpumask_empty(desc->percpu_enabled)) {
WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
irq, cpumask_first(desc->percpu_enabled));
goto bad;
}
/* Found it - now remove it from the list of entries: */
desc->action = NULL;
desc->istate &= ~IRQS_NMI;
raw_spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
irq_chip_pm_put(&desc->irq_data);
module_put(desc->owner);
return action;
bad:
raw_spin_unlock_irqrestore(&desc->lock, flags);
return NULL;
}
/**
* remove_percpu_irq - free a per-cpu interrupt
* @irq: Interrupt line to free
* @act: irqaction for the interrupt
*
* Used to remove interrupts statically setup by the early boot process.
*/
void remove_percpu_irq(unsigned int irq, struct irqaction *act)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc && irq_settings_is_per_cpu_devid(desc))
__free_percpu_irq(irq, act->percpu_dev_id);
}
/**
* free_percpu_irq - free an interrupt allocated with request_percpu_irq
* @irq: Interrupt line to free
* @dev_id: Device identity to free
*
* Remove a percpu interrupt handler. The handler is removed, but
* the interrupt line is not disabled. This must be done on each
* CPU before calling this function. The function does not return
* until any executing interrupts for this IRQ have completed.
*
* This function must not be called from interrupt context.
*/
void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !irq_settings_is_per_cpu_devid(desc))
return;
chip_bus_lock(desc);
kfree(__free_percpu_irq(irq, dev_id));
chip_bus_sync_unlock(desc);
}
EXPORT_SYMBOL_GPL(free_percpu_irq);
void free_percpu_nmi(unsigned int irq, void __percpu *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !irq_settings_is_per_cpu_devid(desc))
return;
if (WARN_ON(!irq_is_nmi(desc)))
return;
kfree(__free_percpu_irq(irq, dev_id));
}
/**
* setup_percpu_irq - setup a per-cpu interrupt
* @irq: Interrupt line to setup
* @act: irqaction for the interrupt
*
* Used to statically setup per-cpu interrupts in the early boot process.
*/
int setup_percpu_irq(unsigned int irq, struct irqaction *act)
{
struct irq_desc *desc = irq_to_desc(irq);
int retval;
if (!desc || !irq_settings_is_per_cpu_devid(desc))
return -EINVAL;
retval = irq_chip_pm_get(&desc->irq_data);
if (retval < 0)
return retval;
retval = __setup_irq(irq, desc, act);
if (retval)
irq_chip_pm_put(&desc->irq_data);
return retval;
}
/**
* __request_percpu_irq - allocate a percpu interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* @flags: Interrupt type flags (IRQF_TIMER only)
* @devname: An ascii name for the claiming device
* @dev_id: A percpu cookie passed back to the handler function
*
* This call allocates interrupt resources and enables the
* interrupt on the local CPU. If the interrupt is supposed to be
* enabled on other CPUs, it has to be done on each CPU using
* enable_percpu_irq().
*
* Dev_id must be globally unique. It is a per-cpu variable, and
* the handler gets called with the interrupted CPU's instance of
* that variable.
*/
int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
unsigned long flags, const char *devname,
void __percpu *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
int retval;
if (!dev_id)
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc || !irq_settings_can_request(desc) ||
!irq_settings_is_per_cpu_devid(desc))
return -EINVAL;
if (flags && flags != IRQF_TIMER)
return -EINVAL;
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
action->name = devname;
action->percpu_dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
if (retval < 0) {
kfree(action);
return retval;
}
retval = __setup_irq(irq, desc, action);
if (retval) {
irq_chip_pm_put(&desc->irq_data);
kfree(action);
}
return retval;
}
EXPORT_SYMBOL_GPL(__request_percpu_irq);
/**
* request_percpu_nmi - allocate a percpu interrupt line for NMI delivery
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* @name: An ascii name for the claiming device
* @dev_id: A percpu cookie passed back to the handler function
*
* This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs
* have to be setup on each CPU by calling prepare_percpu_nmi() before
* being enabled on the same CPU by using enable_percpu_nmi().
*
* Dev_id must be globally unique. It is a per-cpu variable, and
* the handler gets called with the interrupted CPU's instance of
* that variable.
*
* Interrupt lines requested for NMI delivering should have auto enabling
* setting disabled.
*
* If the interrupt line cannot be used to deliver NMIs, function
* will fail returning a negative value.
*/
int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
const char *name, void __percpu *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
unsigned long flags;
int retval;
if (!handler)
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc || !irq_settings_can_request(desc) ||
!irq_settings_is_per_cpu_devid(desc) ||
irq_settings_can_autoenable(desc) ||
!irq_supports_nmi(desc))
return -EINVAL;
/* The line cannot already be NMI */
if (irq_is_nmi(desc))
return -EINVAL;
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD
| IRQF_NOBALANCING;
action->name = name;
action->percpu_dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
if (retval < 0)
goto err_out;
retval = __setup_irq(irq, desc, action);
if (retval)
goto err_irq_setup;
raw_spin_lock_irqsave(&desc->lock, flags);
desc->istate |= IRQS_NMI;
raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
err_irq_setup:
irq_chip_pm_put(&desc->irq_data);
err_out:
kfree(action);
return retval;
}
/**
* prepare_percpu_nmi - performs CPU local setup for NMI delivery
* @irq: Interrupt line to prepare for NMI delivery
*
* This call prepares an interrupt line to deliver NMI on the current CPU,
* before that interrupt line gets enabled with enable_percpu_nmi().
*
* As a CPU local operation, this should be called from non-preemptible
* context.
*
* If the interrupt line cannot be used to deliver NMIs, function
* will fail returning a negative value.
*/
int prepare_percpu_nmi(unsigned int irq)
{
unsigned long flags;
struct irq_desc *desc;
int ret = 0;
WARN_ON(preemptible());
desc = irq_get_desc_lock(irq, &flags,
IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return -EINVAL;
if (WARN(!irq_is_nmi(desc),
KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n",
irq)) {
ret = -EINVAL;
goto out;
}
ret = irq_nmi_setup(desc);
if (ret) {
pr_err("Failed to setup NMI delivery: irq %u\n", irq);
goto out;
}
out:
irq_put_desc_unlock(desc, flags);
return ret;
}
/**
* teardown_percpu_nmi - undoes NMI setup of IRQ line
* @irq: Interrupt line from which CPU local NMI configuration should be
* removed
*
* This call undoes the setup done by prepare_percpu_nmi().
*
* IRQ line should not be enabled for the current CPU.
*
* As a CPU local operation, this should be called from non-preemptible
* context.
*/
void teardown_percpu_nmi(unsigned int irq)
{
unsigned long flags;
struct irq_desc *desc;
WARN_ON(preemptible());
desc = irq_get_desc_lock(irq, &flags,
IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return;
if (WARN_ON(!irq_is_nmi(desc)))
goto out;
irq_nmi_teardown(desc);
out:
irq_put_desc_unlock(desc, flags);
}
static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state)
{
struct irq_chip *chip;
int err = -EINVAL;
do {
chip = irq_data_get_irq_chip(data);
if (WARN_ON_ONCE(!chip))
return -ENODEV;
if (chip->irq_get_irqchip_state)
break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
data = data->parent_data;
#else
data = NULL;
#endif
} while (data);
if (data)
err = chip->irq_get_irqchip_state(data, which, state);
return err;
}
/**
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
* @state: a pointer to a boolean where the state is to be stored
*
* This call snapshots the internal irqchip state of an
* interrupt, returning into @state the bit corresponding to
* stage @which
*
* This function should be called with preemption disabled if the
* interrupt controller has per-cpu registers.
*/
int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
bool *state)
{
struct irq_desc *desc;
struct irq_data *data;
unsigned long flags;
int err = -EINVAL;
desc = irq_get_desc_buslock(irq, &flags, 0);
if (!desc)
return err;
data = irq_desc_get_irq_data(desc);
err = __irq_get_irqchip_state(data, which, state);
irq_put_desc_busunlock(desc, flags);
return err;
}
EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
/**
* irq_set_irqchip_state - set the state of a forwarded interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: State to be restored (one of IRQCHIP_STATE_*)
* @val: Value corresponding to @which
*
* This call sets the internal irqchip state of an interrupt,
* depending on the value of @which.
*
* This function should be called with migration disabled if the
* interrupt controller has per-cpu registers.
*/
int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
bool val)
{
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
unsigned long flags;
int err = -EINVAL;
desc = irq_get_desc_buslock(irq, &flags, 0);
if (!desc)
return err;
data = irq_desc_get_irq_data(desc);
do {
chip = irq_data_get_irq_chip(data);
if (WARN_ON_ONCE(!chip)) {
err = -ENODEV;
goto out_unlock;
}
if (chip->irq_set_irqchip_state)
break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
data = data->parent_data;
#else
data = NULL;
#endif
} while (data);
if (data)
err = chip->irq_set_irqchip_state(data, which, val);
out_unlock:
irq_put_desc_busunlock(desc, flags);
return err;
}
EXPORT_SYMBOL_GPL(irq_set_irqchip_state);
/**
* irq_has_action - Check whether an interrupt is requested
* @irq: The linux irq number
*
* Returns: A snapshot of the current state
*/
bool irq_has_action(unsigned int irq)
{
bool res;
rcu_read_lock();
res = irq_desc_has_action(irq_to_desc(irq));
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL_GPL(irq_has_action);
/**
* irq_check_status_bit - Check whether bits in the irq descriptor status are set
* @irq: The linux irq number
* @bitmask: The bitmask to evaluate
*
* Returns: True if one of the bits in @bitmask is set
*/
bool irq_check_status_bit(unsigned int irq, unsigned int bitmask)
{
struct irq_desc *desc;
bool res = false;
rcu_read_lock();
desc = irq_to_desc(irq);
if (desc)
res = !!(desc->status_use_accessors & bitmask);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL_GPL(irq_check_status_bit);
// SPDX-License-Identifier: GPL-2.0-only
/*
* ratelimit.c - Do something with rate limit.
*
* Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com>
*
* 2008-05-01 rewrite the function and use a ratelimit_state data struct as
* parameter. Now every user can use their own standalone ratelimit_state.
*/
#include <linux/ratelimit.h>
#include <linux/jiffies.h>
#include <linux/export.h>
/*
* __ratelimit - rate limiting
* @rs: ratelimit_state data
* @func: name of calling function
*
* This enforces a rate limit: not more than @rs->burst callbacks
* in every @rs->interval
*
* RETURNS:
* 0 means callbacks will be suppressed.
* 1 means go ahead and do it.
*/
int ___ratelimit(struct ratelimit_state *rs, const char *func)
{
/* Paired with WRITE_ONCE() in .proc_handler().
* Changing two values seperately could be inconsistent
* and some message could be lost. (See: net_ratelimit_state).
*/
int interval = READ_ONCE(rs->interval);
int burst = READ_ONCE(rs->burst);
unsigned long flags;
int ret;
if (!interval)
return 1;
/*
* If we contend on this state's lock then almost
* by definition we are too busy to print a message,
* in addition to the one that will be printed by
* the entity that is holding the lock already:
*/
if (!raw_spin_trylock_irqsave(&rs->lock, flags))
return 0;
if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING
"%s: %d callbacks suppressed\n",
func, rs->missed);
rs->missed = 0;
}
}
rs->begin = jiffies;
rs->printed = 0;
}
if (burst && burst > rs->printed) { rs->printed++;
ret = 1;
} else {
rs->missed++;
ret = 0;
}
raw_spin_unlock_irqrestore(&rs->lock, flags);
return ret;
}
EXPORT_SYMBOL(___ratelimit);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <hyp/switch.h>
#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <linux/percpu.h>
#include <uapi/linux/psci.h>
#include <kvm/arm_psci.h>
#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/kprobes.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
#include <asm/thread_info.h>
#include <asm/vectors.h>
/* VHE specific context */
DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
/*
* HCR_EL2 bits that the NV guest can freely change (no RES0/RES1
* semantics, irrespective of the configuration), but that cannot be
* applied to the actual HW as things would otherwise break badly.
*
* - TGE: we want the guest to use EL1, which is incompatible with
* this bit being set
*
* - API/APK: they are already accounted for by vcpu_load(), and can
* only take effect across a load/put cycle (such as ERET)
*/
#define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK)
static u64 __compute_hcr(struct kvm_vcpu *vcpu)
{
u64 guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
u64 hcr = vcpu->arch.hcr_el2;
if (!vcpu_has_nv(vcpu))
return hcr;
/*
* We rely on the invariant that a vcpu entered from HYP
* context must also exit in the same context, as only an ERET
* instruction can kick us out of it, and we obviously trap
* that sucker. PSTATE.M will get fixed-up on exit.
*/
if (is_hyp_ctxt(vcpu)) { host_data_set_flag(VCPU_IN_HYP_CONTEXT);
hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB;
if (!vcpu_el2_e2h_is_set(vcpu))
hcr |= HCR_NV1;
write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2);
} else {
host_data_clear_flag(VCPU_IN_HYP_CONTEXT); if (guest_hcr & HCR_NV) { u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id()));
/* Inherit the low bits from the actual register */
va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0);
write_sysreg_s(va, SYS_VNCR_EL2);
/* Force NV2 in case the guest is forgetful... */
guest_hcr |= HCR_NV2;
}
}
BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) &&
host_data_test_flag(L1_VNCR_MAPPED));
return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE);
}
static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
{
u64 cptr;
/*
* With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
* CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
* except for some missing controls, such as TAM.
* In this case, CPTR_EL2.TAM has the same position with or without
* VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
* shift value for trapping the AMU accesses.
*/
u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM;
if (guest_owns_fp_regs()) {
val |= CPACR_EL1_FPEN;
if (vcpu_has_sve(vcpu))
val |= CPACR_EL1_ZEN;
} else {
__activate_traps_fpsimd32(vcpu);
}
if (!vcpu_has_nv(vcpu))
goto write;
/*
* The architecture is a bit crap (what a surprise): an EL2 guest
* writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
* as they are RES0 in the guest's view. To work around it, trap the
* sucker using the very same bit it can't set...
*/
if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
val |= CPTR_EL2_TCPAC;
/*
* Layer the guest hypervisor's trap configuration on top of our own if
* we're in a nested context.
*/
if (is_hyp_ctxt(vcpu))
goto write;
cptr = vcpu_sanitised_cptr_el2(vcpu);
/*
* Pay attention, there's some interesting detail here.
*
* The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
* meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
*
* - CPTR_EL2.xEN = x0, traps are enabled
* - CPTR_EL2.xEN = x1, traps are disabled
*
* In other words, bit[0] determines if guest accesses trap or not. In
* the interest of simplicity, clear the entire field if the guest
* hypervisor has traps enabled to dispel any illusion of something more
* complicated taking place.
*/
if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
val &= ~CPACR_EL1_FPEN;
if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
val &= ~CPACR_EL1_ZEN;
if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
val |= cptr & CPACR_EL1_E0POE;
val |= cptr & CPTR_EL2_TCPAC;
write:
write_sysreg(val, cpacr_el1);
}
static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
{
u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
if (cpus_have_final_cap(ARM64_SME))
val |= CPACR_EL1_SMEN_EL1EN;
write_sysreg(val, cpacr_el1);
}
static void __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
___activate_traps(vcpu, __compute_hcr(vcpu)); if (has_cntpoff()) {
struct timer_map map;
get_timer_map(vcpu, &map);
/*
* We're entrering the guest. Reload the correct
* values from memory now that TGE is clear.
*/
if (map.direct_ptimer == vcpu_ptimer(vcpu)) val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); if (map.direct_ptimer == vcpu_hptimer(vcpu)) val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); if (map.direct_ptimer) { write_sysreg_el0(val, SYS_CNTP_CVAL);
isb();
}
}
__activate_cptr_traps(vcpu);
write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
}
NOKPROBE_SYMBOL(__activate_traps);
static void __deactivate_traps(struct kvm_vcpu *vcpu)
{
const char *host_vectors = vectors;
___deactivate_traps(vcpu); write_sysreg_hcr(HCR_HOST_VHE_FLAGS); if (has_cntpoff()) {
struct timer_map map;
u64 val, offset;
get_timer_map(vcpu, &map);
/*
* We're exiting the guest. Save the latest CVAL value
* to memory and apply the offset now that TGE is set.
*/
val = read_sysreg_el0(SYS_CNTP_CVAL);
if (map.direct_ptimer == vcpu_ptimer(vcpu)) __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val; if (map.direct_ptimer == vcpu_hptimer(vcpu)) __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
offset = read_sysreg_s(SYS_CNTPOFF_EL2);
if (map.direct_ptimer && offset) { write_sysreg_el0(val + offset, SYS_CNTP_CVAL);
isb();
}
}
/*
* ARM errata 1165522 and 1530923 require the actual execution of the
* above before we can switch to the EL2/EL0 translation regime used by
* the host.
*/
asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
__deactivate_cptr_traps(vcpu); if (!arm64_kernel_unmapped_at_el0()) host_vectors = __this_cpu_read(this_cpu_vector);
write_sysreg(host_vectors, vbar_el1);
}
NOKPROBE_SYMBOL(__deactivate_traps);
/*
* Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to
* prevent a race condition between context switching of PMUSERENR_EL0
* in __{activate,deactivate}_traps_common() and IPIs that attempts to
* update PMUSERENR_EL0. See also kvm_set_pmuserenr().
*/
static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu)
{
unsigned long flags;
local_irq_save(flags); __activate_traps_common(vcpu); local_irq_restore(flags);
}
static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
{
unsigned long flags;
local_irq_save(flags); __deactivate_traps_common(vcpu); local_irq_restore(flags);
}
void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
{
host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu;
__vcpu_load_switch_sysregs(vcpu);
__vcpu_load_activate_traps(vcpu); __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
}
void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
{ __vcpu_put_deactivate_traps(vcpu);
__vcpu_put_switch_sysregs(vcpu);
host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL;
}
static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu,
enum vcpu_sysreg reg)
{
unsigned long ctl;
u64 cval, cnt;
bool stat;
switch (reg) {
case CNTP_CTL_EL0:
cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
ctl = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
cnt = compute_counter_value(vcpu_ptimer(vcpu));
break;
case CNTV_CTL_EL0:
cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
ctl = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
cnt = compute_counter_value(vcpu_vtimer(vcpu));
break;
default:
BUG();
}
stat = cval <= cnt;
__assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat);
return ctl;
}
static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code)
{
u64 esr, val;
/*
* Having FEAT_ECV allows for a better quality of timer emulation.
* However, this comes at a huge cost in terms of traps. Try and
* satisfy the reads from guest's hypervisor context without
* returning to the kernel if we can.
*/
if (!is_hyp_ctxt(vcpu))
return false;
esr = kvm_vcpu_get_esr(vcpu);
if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ)
return false;
switch (esr_sys64_to_sysreg(esr)) {
case SYS_CNTP_CTL_EL02:
val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
break;
case SYS_CNTP_CTL_EL0:
if (vcpu_el2_e2h_is_set(vcpu))
val = read_sysreg_el0(SYS_CNTP_CTL);
else
val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
break;
case SYS_CNTP_CVAL_EL02:
val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
break;
case SYS_CNTP_CVAL_EL0:
if (vcpu_el2_e2h_is_set(vcpu)) {
val = read_sysreg_el0(SYS_CNTP_CVAL);
if (!has_cntpoff()) val -= timer_get_offset(vcpu_hptimer(vcpu));
} else {
val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
}
break;
case SYS_CNTPCT_EL0:
case SYS_CNTPCTSS_EL0:
val = compute_counter_value(vcpu_hptimer(vcpu));
break;
case SYS_CNTV_CTL_EL02:
val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
break;
case SYS_CNTV_CTL_EL0:
if (vcpu_el2_e2h_is_set(vcpu))
val = read_sysreg_el0(SYS_CNTV_CTL);
else
val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
break;
case SYS_CNTV_CVAL_EL02:
val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
break;
case SYS_CNTV_CVAL_EL0:
if (vcpu_el2_e2h_is_set(vcpu))
val = read_sysreg_el0(SYS_CNTV_CVAL);
else
val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
break;
case SYS_CNTVCT_EL0:
case SYS_CNTVCTSS_EL0:
val = compute_counter_value(vcpu_hvtimer(vcpu));
break;
default:
return false;
}
vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); __kvm_skip_instr(vcpu);
return true;
}
static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
u64 spsr, elr, mode;
/*
* Going through the whole put/load motions is a waste of time
* if this is a VHE guest hypervisor returning to its own
* userspace, or the hypervisor performing a local exception
* return. No need to save/restore registers, no need to
* switch S2 MMU. Just do the canonical ERET.
*
* Unless the trap has to be forwarded further down the line,
* of course...
*/
if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) ||
(__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET))
return false;
spsr = read_sysreg_el1(SYS_SPSR);
mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
switch (mode) {
case PSR_MODE_EL0t:
if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
return false;
break;
case PSR_MODE_EL2t:
mode = PSR_MODE_EL1t;
break;
case PSR_MODE_EL2h:
mode = PSR_MODE_EL1h;
break;
default:
return false;
}
/* If ERETAx fails, take the slow path */
if (esr_iss_is_eretax(esr)) {
if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr)))
return false;
} else {
elr = read_sysreg_el1(SYS_ELR);
}
spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
write_sysreg_el2(spsr, SYS_SPSR);
write_sysreg_el2(elr, SYS_ELR);
return true;
}
static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
{
int ret = -EINVAL;
u32 instr;
u64 val;
/*
* Ideally, we would never trap on EL2 S1 TLB invalidations using
* the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}.
* But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2,
* meaning that we can't track changes to the virtual TGE bit. So we
* have to leave HCR_EL2.TTLB set on the host. Oopsie...
*
* Try and handle these invalidation as quickly as possible, without
* fully exiting. Note that we don't need to consider any forwarding
* here, as having E2H+TGE set is the very definition of being
* InHost.
*
* For the lesser hypervisors out there that have failed to get on
* with the VHE program, we can also handle the nVHE style of EL2
* invalidation.
*/
if (!(is_hyp_ctxt(vcpu)))
return false;
instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) && vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) || kvm_supported_tlbi_s1e2_op (vcpu, instr))
ret = __kvm_tlbi_s1e2(NULL, val, instr);
if (ret)
return false;
/*
* If we have to check for any VNCR mapping being invalidated,
* go back to the slow path for further processing.
*/
if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) &&
atomic_read(&vcpu->kvm->arch.vncr_map_count))
return false;
__kvm_skip_instr(vcpu);
return true;
}
static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
int rt;
if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1)
return false;
rt = kvm_vcpu_sys_get_rt(vcpu);
if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) {
vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2));
} else {
vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2);
__activate_cptr_traps(vcpu);
}
__kvm_skip_instr(vcpu);
return true;
}
static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
{
u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
if (!vcpu_has_nv(vcpu))
return false;
if (sysreg != SYS_ZCR_EL2)
return false;
if (guest_owns_fp_regs())
return false;
/*
* ZCR_EL2 traps are handled in the slow path, with the expectation
* that the guest's FP context has already been loaded onto the CPU.
*
* Load the guest's FP context and unconditionally forward to the
* slow path for handling (i.e. return false).
*/
kvm_hyp_handle_fpsimd(vcpu, exit_code);
return false;
}
static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
{ if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code))
return true;
if (kvm_hyp_handle_timer(vcpu, exit_code))
return true;
if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
return true;
if (kvm_hyp_handle_zcr_el2(vcpu, exit_code))
return true;
return kvm_hyp_handle_sysreg(vcpu, exit_code);
}
static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code)
{
u64 iss;
if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
return false;
/*
* Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2
* is populated with a correct ISS for a sysreg trap. These fruity
* parts are 64bit only, so unconditionally set IL.
*/
iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2));
vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) |
FIELD_PREP(ESR_ELx_ISS_MASK, iss) |
ESR_ELx_IL;
return false;
}
static const exit_handler_fn hyp_exit_handlers[] = {
[0 ... ESR_ELx_EC_MAX] = NULL,
[ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
[ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg_vhe,
[ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd,
[ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd,
[ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
[ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
[ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low,
[ESR_ELx_EC_ERET] = kvm_hyp_handle_eret,
[ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops,
/* Apple shenanigans */
[0x3F] = kvm_hyp_handle_impdef,
};
static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
{
synchronize_vcpu_pstate(vcpu, exit_code);
/*
* If we were in HYP context on entry, adjust the PSTATE view
* so that the usual helpers work correctly. This enforces our
* invariant that the guest's HYP context status is preserved
* across a run.
*/
if (vcpu_has_nv(vcpu) &&
unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) {
u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
switch (mode) {
case PSR_MODE_EL1t:
mode = PSR_MODE_EL2t;
break;
case PSR_MODE_EL1h:
mode = PSR_MODE_EL2h;
break;
}
*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
*vcpu_cpsr(vcpu) |= mode;
}
/* Apply extreme paranoia! */
BUG_ON(vcpu_has_nv(vcpu) &&
!!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu));
return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers);
}
/* Switch to the guest for VHE systems running in EL2 */
static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
u64 exit_code;
host_ctxt = host_data_ptr(host_ctxt);
guest_ctxt = &vcpu->arch.ctxt;
sysreg_save_host_state_vhe(host_ctxt);
fpsimd_lazy_switch_to_guest(vcpu);
/*
* Note that ARM erratum 1165522 requires us to configure both stage 1
* and stage 2 translation for the guest context before we clear
* HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been
* loaded on the CPU in kvm_vcpu_load_vhe().
*/
__activate_traps(vcpu);
__kvm_adjust_pc(vcpu);
sysreg_restore_guest_state_vhe(guest_ctxt);
__debug_switch_to_guest(vcpu);
do {
/* Jump in the fire! */
exit_code = __guest_enter(vcpu);
/* And we're baaack! */
} while (fixup_guest_exit(vcpu, &exit_code));
sysreg_save_guest_state_vhe(guest_ctxt);
__deactivate_traps(vcpu);
fpsimd_lazy_switch_to_host(vcpu);
sysreg_restore_host_state_vhe(host_ctxt);
if (guest_owns_fp_regs()) __fpsimd_save_fpexc32(vcpu);
__debug_switch_to_host(vcpu);
return exit_code;
}
NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
{
int ret;
local_daif_mask();
/*
* Having IRQs masked via PMR when entering the guest means the GIC
* will not signal the CPU of interrupts of lower priority, and the
* only way to get out will be via guest exceptions.
* Naturally, we want to avoid this.
*
* local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
* dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
*/
pmr_sync();
ret = __kvm_vcpu_run_vhe(vcpu);
/*
* local_daif_restore() takes care to properly restore PSTATE.DAIF
* and the GIC PMR if the host is using IRQ priorities.
*/
local_daif_restore(DAIF_PROCCTX_NOIRQ);
/*
* When we exit from the guest we change a number of CPU configuration
* parameters, such as traps. We rely on the isb() in kvm_call_hyp*()
* to make sure these changes take effect before running the host or
* additional guests.
*/
return ret;
}
static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_vcpu *vcpu;
host_ctxt = host_data_ptr(host_ctxt);
vcpu = host_ctxt->__hyp_running_vcpu;
__deactivate_traps(vcpu);
sysreg_restore_host_state_vhe(host_ctxt);
panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n",
spsr, elr,
read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
read_sysreg(hpfar_el2), par, vcpu);
}
NOKPROBE_SYMBOL(__hyp_call_panic);
void __noreturn hyp_panic(void)
{
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
u64 par = read_sysreg_par();
__hyp_call_panic(spsr, elr, par);
}
asmlinkage void kvm_unexpected_el2_exception(void)
{
__kvm_unexpected_el2_exception();
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Implementations of the security context functions.
*
* Author: Ondrej Mosnacek <omosnacek@gmail.com>
* Copyright (C) 2020 Red Hat, Inc.
*/
#include <linux/jhash.h>
#include "context.h"
#include "mls.h"
u32 context_compute_hash(const struct context *c)
{
u32 hash = 0;
/*
* If a context is invalid, it will always be represented by a
* context struct with only the len & str set (and vice versa)
* under a given policy. Since context structs from different
* policies should never meet, it is safe to hash valid and
* invalid contexts differently. The context_equal() function
* already operates under the same assumption.
*/
if (c->len)
return full_name_hash(NULL, c->str, c->len); hash = jhash_3words(c->user, c->role, c->type, hash);
hash = mls_range_hash(&c->range, hash);
return hash;
}
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (C) 2001 Momchil Velikov
* Portions Copyright (C) 2001 Christoph Hellwig
* Copyright (C) 2006 Nick Piggin
* Copyright (C) 2012 Konstantin Khlebnikov
*/
#ifndef _LINUX_RADIX_TREE_H
#define _LINUX_RADIX_TREE_H
#include <linux/bitops.h>
#include <linux/gfp_types.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/math.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/xarray.h>
#include <linux/local_lock.h>
/* Keep unconverted code working */
#define radix_tree_root xarray
#define radix_tree_node xa_node
struct radix_tree_preload {
local_lock_t lock;
unsigned nr;
/* nodes->parent points to next preallocated node */
struct radix_tree_node *nodes;
};
DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads);
/*
* The bottom two bits of the slot determine how the remaining bits in the
* slot are interpreted:
*
* 00 - data pointer
* 10 - internal entry
* x1 - value entry
*
* The internal entry may be a pointer to the next level in the tree, a
* sibling entry, or an indicator that the entry in this slot has been moved
* to another location in the tree and the lookup should be restarted. While
* NULL fits the 'data pointer' pattern, it means that there is no entry in
* the tree for this index (no matter what level of the tree it is found at).
* This means that storing a NULL entry in the tree is the same as deleting
* the entry from the tree.
*/
#define RADIX_TREE_ENTRY_MASK 3UL
#define RADIX_TREE_INTERNAL_NODE 2UL
static inline bool radix_tree_is_internal_node(void *ptr)
{
return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) ==
RADIX_TREE_INTERNAL_NODE;
}
/*** radix-tree API starts here ***/
#define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT
#define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT)
#define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1)
#define RADIX_TREE_MAX_TAGS XA_MAX_MARKS
#define RADIX_TREE_TAG_LONGS XA_MARK_LONGS
#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long))
#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
RADIX_TREE_MAP_SHIFT))
/* The IDR tag is stored in the low bits of xa_flags */
#define ROOT_IS_IDR ((__force gfp_t)4)
/* The top bits of xa_flags are used to store the root tags */
#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT)
#define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask)
#define RADIX_TREE(name, mask) \
struct radix_tree_root name = RADIX_TREE_INIT(name, mask)
#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask)
static inline bool radix_tree_empty(const struct radix_tree_root *root)
{
return root->xa_head == NULL;
}
/**
* struct radix_tree_iter - radix tree iterator state
*
* @index: index of current slot
* @next_index: one beyond the last index for this chunk
* @tags: bit-mask for tag-iterating
* @node: node that contains current slot
*
* This radix tree iterator works in terms of "chunks" of slots. A chunk is a
* subinterval of slots contained within one radix tree leaf node. It is
* described by a pointer to its first slot and a struct radix_tree_iter
* which holds the chunk's position in the tree and its size. For tagged
* iteration radix_tree_iter also holds the slots' bit-mask for one chosen
* radix tree tag.
*/
struct radix_tree_iter {
unsigned long index;
unsigned long next_index;
unsigned long tags;
struct radix_tree_node *node;
};
/**
* Radix-tree synchronization
*
* The radix-tree API requires that users provide all synchronisation (with
* specific exceptions, noted below).
*
* Synchronization of access to the data items being stored in the tree, and
* management of their lifetimes must be completely managed by API users.
*
* For API usage, in general,
* - any function _modifying_ the tree or tags (inserting or deleting
* items, setting or clearing tags) must exclude other modifications, and
* exclude any functions reading the tree.
* - any function _reading_ the tree or tags (looking up items or tags,
* gang lookups) must exclude modifications to the tree, but may occur
* concurrently with other readers.
*
* The notable exceptions to this rule are the following functions:
* __radix_tree_lookup
* radix_tree_lookup
* radix_tree_lookup_slot
* radix_tree_tag_get
* radix_tree_gang_lookup
* radix_tree_gang_lookup_tag
* radix_tree_gang_lookup_tag_slot
* radix_tree_tagged
*
* The first 7 functions are able to be called locklessly, using RCU. The
* caller must ensure calls to these functions are made within rcu_read_lock()
* regions. Other readers (lock-free or otherwise) and modifications may be
* running concurrently.
*
* It is still required that the caller manage the synchronization and lifetimes
* of the items. So if RCU lock-free lookups are used, typically this would mean
* that the items have their own locks, or are amenable to lock-free access; and
* that the items are freed by RCU (or only freed after having been deleted from
* the radix tree *and* a synchronize_rcu() grace period).
*
* (Note, rcu_assign_pointer and rcu_dereference are not needed to control
* access to data items when inserting into or looking up from the radix tree)
*
* Note that the value returned by radix_tree_tag_get() may not be relied upon
* if only the RCU read lock is held. Functions to set/clear tags and to
* delete nodes running concurrently with it may affect its result such that
* two consecutive reads in the same locked section may return different
* values. If reliability is required, modification functions must also be
* excluded from concurrency.
*
* radix_tree_tagged is able to be called without locking or RCU.
*/
/**
* radix_tree_deref_slot - dereference a slot
* @slot: slot pointer, returned by radix_tree_lookup_slot
*
* For use with radix_tree_lookup_slot(). Caller must hold tree at least read
* locked across slot lookup and dereference. Not required if write lock is
* held (ie. items cannot be concurrently inserted).
*
* radix_tree_deref_retry must be used to confirm validity of the pointer if
* only the read lock is held.
*
* Return: entry stored in that slot.
*/
static inline void *radix_tree_deref_slot(void __rcu **slot)
{
return rcu_dereference(*slot);
}
/**
* radix_tree_deref_slot_protected - dereference a slot with tree lock held
* @slot: slot pointer, returned by radix_tree_lookup_slot
*
* Similar to radix_tree_deref_slot. The caller does not hold the RCU read
* lock but it must hold the tree lock to prevent parallel updates.
*
* Return: entry stored in that slot.
*/
static inline void *radix_tree_deref_slot_protected(void __rcu **slot,
spinlock_t *treelock)
{
return rcu_dereference_protected(*slot, lockdep_is_held(treelock));
}
/**
* radix_tree_deref_retry - check radix_tree_deref_slot
* @arg: pointer returned by radix_tree_deref_slot
* Returns: 0 if retry is not required, otherwise retry is required
*
* radix_tree_deref_retry must be used with radix_tree_deref_slot.
*/
static inline int radix_tree_deref_retry(void *arg)
{
return unlikely(radix_tree_is_internal_node(arg));
}
/**
* radix_tree_exception - radix_tree_deref_slot returned either exception?
* @arg: value returned by radix_tree_deref_slot
* Returns: 0 if well-aligned pointer, non-0 if either kind of exception.
*/
static inline int radix_tree_exception(void *arg)
{
return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK);
}
int radix_tree_insert(struct radix_tree_root *, unsigned long index,
void *);
void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
struct radix_tree_node **nodep, void __rcu ***slotp);
void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
unsigned long index);
void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
void __rcu **slot, void *entry);
void radix_tree_iter_replace(struct radix_tree_root *,
const struct radix_tree_iter *, void __rcu **slot, void *entry);
void radix_tree_replace_slot(struct radix_tree_root *,
void __rcu **slot, void *entry);
void radix_tree_iter_delete(struct radix_tree_root *,
struct radix_tree_iter *iter, void __rcu **slot);
void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
void *radix_tree_delete(struct radix_tree_root *, unsigned long);
unsigned int radix_tree_gang_lookup(const struct radix_tree_root *,
void **results, unsigned long first_index,
unsigned int max_items);
int radix_tree_preload(gfp_t gfp_mask);
int radix_tree_maybe_preload(gfp_t gfp_mask);
void radix_tree_init(void);
void *radix_tree_tag_set(struct radix_tree_root *,
unsigned long index, unsigned int tag);
void *radix_tree_tag_clear(struct radix_tree_root *,
unsigned long index, unsigned int tag);
int radix_tree_tag_get(const struct radix_tree_root *,
unsigned long index, unsigned int tag);
void radix_tree_iter_tag_clear(struct radix_tree_root *,
const struct radix_tree_iter *iter, unsigned int tag);
unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *,
void **results, unsigned long first_index,
unsigned int max_items, unsigned int tag);
unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *,
void __rcu ***results, unsigned long first_index,
unsigned int max_items, unsigned int tag);
int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag);
static inline void radix_tree_preload_end(void)
{
local_unlock(&radix_tree_preloads.lock);
}
void __rcu **idr_get_free(struct radix_tree_root *root,
struct radix_tree_iter *iter, gfp_t gfp,
unsigned long max);
enum {
RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */
RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */
RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */
};
/**
* radix_tree_iter_init - initialize radix tree iterator
*
* @iter: pointer to iterator state
* @start: iteration starting index
* Returns: NULL
*/
static __always_inline void __rcu **
radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start)
{
/*
* Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it
* in the case of a successful tagged chunk lookup. If the lookup was
* unsuccessful or non-tagged then nobody cares about ->tags.
*
* Set index to zero to bypass next_index overflow protection.
* See the comment in radix_tree_next_chunk() for details.
*/
iter->index = 0;
iter->next_index = start;
return NULL;
}
/**
* radix_tree_next_chunk - find next chunk of slots for iteration
*
* @root: radix tree root
* @iter: iterator state
* @flags: RADIX_TREE_ITER_* flags and tag index
* Returns: pointer to chunk first slot, or NULL if there no more left
*
* This function looks up the next chunk in the radix tree starting from
* @iter->next_index. It returns a pointer to the chunk's first slot.
* Also it fills @iter with data about chunk: position in the tree (index),
* its end (next_index), and constructs a bit mask for tagged iterating (tags).
*/
void __rcu **radix_tree_next_chunk(const struct radix_tree_root *,
struct radix_tree_iter *iter, unsigned flags);
/**
* radix_tree_iter_lookup - look up an index in the radix tree
* @root: radix tree root
* @iter: iterator state
* @index: key to look up
*
* If @index is present in the radix tree, this function returns the slot
* containing it and updates @iter to describe the entry. If @index is not
* present, it returns NULL.
*/
static inline void __rcu **
radix_tree_iter_lookup(const struct radix_tree_root *root,
struct radix_tree_iter *iter, unsigned long index)
{
radix_tree_iter_init(iter, index);
return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG);
}
/**
* radix_tree_iter_retry - retry this chunk of the iteration
* @iter: iterator state
*
* If we iterate over a tree protected only by the RCU lock, a race
* against deletion or creation may result in seeing a slot for which
* radix_tree_deref_retry() returns true. If so, call this function
* and continue the iteration.
*/
static inline __must_check
void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter)
{
iter->next_index = iter->index;
iter->tags = 0;
return NULL;
}
static inline unsigned long
__radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots)
{
return iter->index + slots;
}
/**
* radix_tree_iter_resume - resume iterating when the chunk may be invalid
* @slot: pointer to current slot
* @iter: iterator state
* Returns: New slot pointer
*
* If the iterator needs to release then reacquire a lock, the chunk may
* have been invalidated by an insertion or deletion. Call this function
* before releasing the lock to continue the iteration from the next index.
*/
void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot,
struct radix_tree_iter *iter);
/**
* radix_tree_chunk_size - get current chunk size
*
* @iter: pointer to radix tree iterator
* Returns: current chunk size
*/
static __always_inline long
radix_tree_chunk_size(struct radix_tree_iter *iter)
{
return iter->next_index - iter->index;
}
/**
* radix_tree_next_slot - find next slot in chunk
*
* @slot: pointer to current slot
* @iter: pointer to iterator state
* @flags: RADIX_TREE_ITER_*, should be constant
* Returns: pointer to next slot, or NULL if there no more left
*
* This function updates @iter->index in the case of a successful lookup.
* For tagged lookup it also eats @iter->tags.
*
* There are several cases where 'slot' can be passed in as NULL to this
* function. These cases result from the use of radix_tree_iter_resume() or
* radix_tree_iter_retry(). In these cases we don't end up dereferencing
* 'slot' because either:
* a) we are doing tagged iteration and iter->tags has been set to 0, or
* b) we are doing non-tagged iteration, and iter->index and iter->next_index
* have been set up so that radix_tree_chunk_size() returns 1 or 0.
*/
static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot,
struct radix_tree_iter *iter, unsigned flags)
{
if (flags & RADIX_TREE_ITER_TAGGED) {
iter->tags >>= 1;
if (unlikely(!iter->tags))
return NULL;
if (likely(iter->tags & 1ul)) {
iter->index = __radix_tree_iter_add(iter, 1);
slot++;
goto found;
}
if (!(flags & RADIX_TREE_ITER_CONTIG)) {
unsigned offset = __ffs(iter->tags);
iter->tags >>= offset++;
iter->index = __radix_tree_iter_add(iter, offset);
slot += offset;
goto found;
}
} else {
long count = radix_tree_chunk_size(iter);
while (--count > 0) {
slot++;
iter->index = __radix_tree_iter_add(iter, 1);
if (likely(*slot))
goto found;
if (flags & RADIX_TREE_ITER_CONTIG) {
/* forbid switching to the next chunk */
iter->next_index = 0;
break;
}
}
}
return NULL;
found:
return slot;
}
/**
* radix_tree_for_each_slot - iterate over non-empty slots
*
* @slot: the void** variable for pointer to slot
* @root: the struct radix_tree_root pointer
* @iter: the struct radix_tree_iter pointer
* @start: iteration starting index
*
* @slot points to radix tree slot, @iter->index contains its index.
*/
#define radix_tree_for_each_slot(slot, root, iter, start) \
for (slot = radix_tree_iter_init(iter, start) ; \
slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \
slot = radix_tree_next_slot(slot, iter, 0))
/**
* radix_tree_for_each_tagged - iterate over tagged slots
*
* @slot: the void** variable for pointer to slot
* @root: the struct radix_tree_root pointer
* @iter: the struct radix_tree_iter pointer
* @start: iteration starting index
* @tag: tag index
*
* @slot points to radix tree slot, @iter->index contains its index.
*/
#define radix_tree_for_each_tagged(slot, root, iter, start, tag) \
for (slot = radix_tree_iter_init(iter, start) ; \
slot || (slot = radix_tree_next_chunk(root, iter, \
RADIX_TREE_ITER_TAGGED | tag)) ; \
slot = radix_tree_next_slot(slot, iter, \
RADIX_TREE_ITER_TAGGED | tag))
#endif /* _LINUX_RADIX_TREE_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* (C) 1997 Linus Torvalds
* (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
*/
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/mm.h>
#include <linux/backing-dev.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/cdev.h>
#include <linux/memblock.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include <linux/iversion.h>
#include <linux/rw_hint.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <trace/events/writeback.h>
#define CREATE_TRACE_POINTS
#include <trace/events/timestamp.h>
#include "internal.h"
/*
* Inode locking rules:
*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget(), inode->i_io_list
* Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode->i_sb->s_inode_list_lock protects:
* inode->i_sb->s_inodes, inode->i_sb_list
* bdi->wb.list_lock protects:
* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
* inode_hash_lock protects:
* inode_hashtable, inode->i_hash
*
* Lock ordering:
*
* inode->i_sb->s_inode_list_lock
* inode->i_lock
* Inode LRU list locks
*
* bdi->wb.list_lock
* inode->i_lock
*
* inode_hash_lock
* inode->i_sb->s_inode_list_lock
* inode->i_lock
*
* iunique_lock
* inode_hash_lock
*/
static unsigned int i_hash_mask __ro_after_init;
static unsigned int i_hash_shift __ro_after_init;
static struct hlist_head *inode_hashtable __ro_after_init;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
/*
* Empty aops. Can be used for the cases where the user does not
* define any of the address_space operations.
*/
const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);
static DEFINE_PER_CPU(unsigned long, nr_inodes);
static DEFINE_PER_CPU(unsigned long, nr_unused);
static struct kmem_cache *inode_cachep __ro_after_init;
static long get_nr_inodes(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_inodes, i);
return sum < 0 ? 0 : sum;
}
static inline long get_nr_inodes_unused(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_unused, i);
return sum < 0 ? 0 : sum;
}
long get_nr_dirty_inodes(void)
{
/* not actually dirty inodes, but a wild approximation */
long nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
return nr_dirty > 0 ? nr_dirty : 0;
}
#ifdef CONFIG_DEBUG_FS
static DEFINE_PER_CPU(long, mg_ctime_updates);
static DEFINE_PER_CPU(long, mg_fine_stamps);
static DEFINE_PER_CPU(long, mg_ctime_swaps);
static unsigned long get_mg_ctime_updates(void)
{
unsigned long sum = 0;
int i;
for_each_possible_cpu(i)
sum += data_race(per_cpu(mg_ctime_updates, i));
return sum;
}
static unsigned long get_mg_fine_stamps(void)
{
unsigned long sum = 0;
int i;
for_each_possible_cpu(i)
sum += data_race(per_cpu(mg_fine_stamps, i));
return sum;
}
static unsigned long get_mg_ctime_swaps(void)
{
unsigned long sum = 0;
int i;
for_each_possible_cpu(i)
sum += data_race(per_cpu(mg_ctime_swaps, i));
return sum;
}
#define mgtime_counter_inc(__var) this_cpu_inc(__var)
static int mgts_show(struct seq_file *s, void *p)
{
unsigned long ctime_updates = get_mg_ctime_updates();
unsigned long ctime_swaps = get_mg_ctime_swaps();
unsigned long fine_stamps = get_mg_fine_stamps();
unsigned long floor_swaps = timekeeping_get_mg_floor_swaps();
seq_printf(s, "%lu %lu %lu %lu\n",
ctime_updates, ctime_swaps, fine_stamps, floor_swaps);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(mgts);
static int __init mg_debugfs_init(void)
{
debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
return 0;
}
late_initcall(mg_debugfs_init);
#else /* ! CONFIG_DEBUG_FS */
#define mgtime_counter_inc(__var) do { } while (0)
#endif /* CONFIG_DEBUG_FS */
/*
* Handle nr_inode sysctl
*/
#ifdef CONFIG_SYSCTL
/*
* Statistics gathering..
*/
static struct inodes_stat_t inodes_stat;
static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
inodes_stat.nr_inodes = get_nr_inodes();
inodes_stat.nr_unused = get_nr_inodes_unused();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static const struct ctl_table inodes_sysctls[] = {
{
.procname = "inode-nr",
.data = &inodes_stat,
.maxlen = 2*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
{
.procname = "inode-state",
.data = &inodes_stat,
.maxlen = 7*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
};
static int __init init_fs_inode_sysctls(void)
{
register_sysctl_init("fs", inodes_sysctls);
return 0;
}
early_initcall(init_fs_inode_sysctls);
#endif
static int no_open(struct inode *inode, struct file *file)
{
return -ENXIO;
}
/**
* inode_init_always_gfp - perform inode structure initialisation
* @sb: superblock inode belongs to
* @inode: inode to initialise
* @gfp: allocation flags
*
* These are initializations that need to be done on every inode
* allocation as the fields are not initialised by slab allocation.
* If there are additional allocations required @gfp is used.
*/
int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp)
{
static const struct inode_operations empty_iops;
static const struct file_operations no_open_fops = {.open = no_open};
struct address_space *const mapping = &inode->i_data;
inode->i_sb = sb;
inode->i_blkbits = sb->s_blocksize_bits;
inode->i_flags = 0;
inode->i_state = 0;
atomic64_set(&inode->i_sequence, 0);
atomic_set(&inode->i_count, 1);
inode->i_op = &empty_iops;
inode->i_fop = &no_open_fops;
inode->i_ino = 0;
inode->__i_nlink = 1;
inode->i_opflags = 0;
if (sb->s_xattr)
inode->i_opflags |= IOP_XATTR;
if (sb->s_type->fs_flags & FS_MGTIME) inode->i_opflags |= IOP_MGTIME;
i_uid_write(inode, 0);
i_gid_write(inode, 0);
atomic_set(&inode->i_writecount, 0);
inode->i_size = 0;
inode->i_write_hint = WRITE_LIFE_NOT_SET;
inode->i_blocks = 0;
inode->i_bytes = 0;
inode->i_generation = 0;
inode->i_pipe = NULL;
inode->i_cdev = NULL;
inode->i_link = NULL;
inode->i_dir_seq = 0;
inode->i_rdev = 0;
inode->dirtied_when = 0;
#ifdef CONFIG_CGROUP_WRITEBACK
inode->i_wb_frn_winner = 0;
inode->i_wb_frn_avg_time = 0;
inode->i_wb_frn_history = 0;
#endif
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
init_rwsem(&inode->i_rwsem);
lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key);
atomic_set(&inode->i_dio_count, 0);
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
mapping->wb_err = 0;
atomic_set(&mapping->i_mmap_writable, 0);
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
atomic_set(&mapping->nr_thps, 0);
#endif
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->i_private_data = NULL;
mapping->writeback_index = 0;
init_rwsem(&mapping->invalidate_lock);
lockdep_set_class_and_name(&mapping->invalidate_lock,
&sb->s_type->invalidate_lock_key,
"mapping.invalidate_lock");
if (sb->s_iflags & SB_I_STABLE_WRITES) mapping_set_stable_writes(mapping);
inode->i_private = NULL;
inode->i_mapping = mapping;
INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
#ifdef CONFIG_FS_POSIX_ACL
inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif
#ifdef CONFIG_FSNOTIFY
inode->i_fsnotify_mask = 0;
#endif
inode->i_flctx = NULL;
if (unlikely(security_inode_alloc(inode, gfp)))
return -ENOMEM;
this_cpu_inc(nr_inodes);
return 0;
}
EXPORT_SYMBOL(inode_init_always_gfp);
void free_inode_nonrcu(struct inode *inode)
{
kmem_cache_free(inode_cachep, inode);
}
EXPORT_SYMBOL(free_inode_nonrcu);
static void i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
if (inode->free_inode)
inode->free_inode(inode);
else
free_inode_nonrcu(inode);
}
/**
* alloc_inode - obtain an inode
* @sb: superblock
*
* Allocates a new inode for given superblock.
* Inode wont be chained in superblock s_inodes list
* This means :
* - fs can't be unmount
* - quotas, fsnotify, writeback can't work
*/
struct inode *alloc_inode(struct super_block *sb)
{
const struct super_operations *ops = sb->s_op;
struct inode *inode;
if (ops->alloc_inode)
inode = ops->alloc_inode(sb);
else
inode = alloc_inode_sb(sb, inode_cachep, GFP_KERNEL); if (!inode)
return NULL;
if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) {
ops->destroy_inode(inode);
if (!ops->free_inode)
return NULL;
}
inode->free_inode = ops->free_inode;
i_callback(&inode->i_rcu);
return NULL;
}
return inode;
}
void __destroy_inode(struct inode *inode)
{ BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode);
security_inode_free(inode);
fsnotify_inode_delete(inode);
locks_free_lock_context(inode);
if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count);
}
#ifdef CONFIG_FS_POSIX_ACL
if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl);
#endif
this_cpu_dec(nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);
static void destroy_inode(struct inode *inode)
{
const struct super_operations *ops = inode->i_sb->s_op;
BUG_ON(!list_empty(&inode->i_lru));
__destroy_inode(inode);
if (ops->destroy_inode) {
ops->destroy_inode(inode);
if (!ops->free_inode)
return;
}
inode->free_inode = ops->free_inode;
call_rcu(&inode->i_rcu, i_callback);
}
/**
* drop_nlink - directly drop an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. In cases
* where we are attempting to track writes to the
* filesystem, a decrement to zero means an imminent
* write when the file is truncated and actually unlinked
* on the filesystem.
*/
void drop_nlink(struct inode *inode)
{ WARN_ON(inode->i_nlink == 0);
inode->__i_nlink--;
if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count);
}
EXPORT_SYMBOL(drop_nlink);
/**
* clear_nlink - directly zero an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. See
* drop_nlink() for why we care about i_nlink hitting zero.
*/
void clear_nlink(struct inode *inode)
{ if (inode->i_nlink) {
inode->__i_nlink = 0;
atomic_long_inc(&inode->i_sb->s_remove_count);
}
}
EXPORT_SYMBOL(clear_nlink);
/**
* set_nlink - directly set an inode's link count
* @inode: inode
* @nlink: new nlink (should be non-zero)
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink.
*/
void set_nlink(struct inode *inode, unsigned int nlink)
{
if (!nlink) {
clear_nlink(inode);
} else {
/* Yes, some filesystems do change nlink from zero to one */
if (inode->i_nlink == 0)
atomic_long_dec(&inode->i_sb->s_remove_count);
inode->__i_nlink = nlink;
}
}
EXPORT_SYMBOL(set_nlink);
/**
* inc_nlink - directly increment an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. Currently,
* it is only here for parity with dec_nlink().
*/
void inc_nlink(struct inode *inode)
{ if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count);
}
inode->__i_nlink++;
}
EXPORT_SYMBOL(inc_nlink);
static void __address_space_init_once(struct address_space *mapping)
{
xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
init_rwsem(&mapping->i_mmap_rwsem);
INIT_LIST_HEAD(&mapping->i_private_list);
spin_lock_init(&mapping->i_private_lock);
mapping->i_mmap = RB_ROOT_CACHED;
}
void address_space_init_once(struct address_space *mapping)
{
memset(mapping, 0, sizeof(*mapping));
__address_space_init_once(mapping);
}
EXPORT_SYMBOL(address_space_init_once);
/*
* These are initializations that only need to be done
* once, because the fields are idempotent across use
* of the inode, so let the slab aware of that.
*/
void inode_init_once(struct inode *inode)
{
memset(inode, 0, sizeof(*inode));
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_devices);
INIT_LIST_HEAD(&inode->i_io_list);
INIT_LIST_HEAD(&inode->i_wb_list);
INIT_LIST_HEAD(&inode->i_lru);
INIT_LIST_HEAD(&inode->i_sb_list);
__address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
}
EXPORT_SYMBOL(inode_init_once);
static void init_once(void *foo)
{
struct inode *inode = (struct inode *) foo;
inode_init_once(inode);
}
/*
* get additional reference to inode; caller must already hold one.
*/
void ihold(struct inode *inode)
{ WARN_ON(atomic_inc_return(&inode->i_count) < 2);
}
EXPORT_SYMBOL(ihold);
static void __inode_add_lru(struct inode *inode, bool rotate)
{ if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE))
return;
if (atomic_read(&inode->i_count))
return;
if (!(inode->i_sb->s_flags & SB_ACTIVE))
return;
if (!mapping_shrinkable(&inode->i_data))
return;
if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused); else if (rotate) inode->i_state |= I_REFERENCED;
}
struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe,
struct inode *inode, u32 bit)
{
void *bit_address;
bit_address = inode_state_wait_address(inode, bit);
init_wait_var_entry(wqe, bit_address, 0);
return __var_waitqueue(bit_address);
}
EXPORT_SYMBOL(inode_bit_waitqueue);
/*
* Add inode to LRU if needed (inode is unused and clean).
*
* Needs inode->i_lock held.
*/
void inode_add_lru(struct inode *inode)
{
__inode_add_lru(inode, false);
}
static void inode_lru_list_del(struct inode *inode)
{
if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused);
}
static void inode_pin_lru_isolating(struct inode *inode)
{
lockdep_assert_held(&inode->i_lock);
WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE));
inode->i_state |= I_LRU_ISOLATING;
}
static void inode_unpin_lru_isolating(struct inode *inode)
{
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_LRU_ISOLATING));
inode->i_state &= ~I_LRU_ISOLATING;
/* Called with inode->i_lock which ensures memory ordering. */
inode_wake_up_bit(inode, __I_LRU_ISOLATING);
spin_unlock(&inode->i_lock);
}
static void inode_wait_for_lru_isolating(struct inode *inode)
{
struct wait_bit_queue_entry wqe;
struct wait_queue_head *wq_head;
lockdep_assert_held(&inode->i_lock); if (!(inode->i_state & I_LRU_ISOLATING))
return;
wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING);
for (;;) {
prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
/*
* Checking I_LRU_ISOLATING with inode->i_lock guarantees
* memory ordering.
*/
if (!(inode->i_state & I_LRU_ISOLATING))
break;
spin_unlock(&inode->i_lock);
schedule();
spin_lock(&inode->i_lock);
}
finish_wait(wq_head, &wqe.wq_entry);
WARN_ON(inode->i_state & I_LRU_ISOLATING);
}
/**
* inode_sb_list_add - add inode to the superblock list of inodes
* @inode: inode to add
*/
void inode_sb_list_add(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
spin_lock(&sb->s_inode_list_lock);
list_add(&inode->i_sb_list, &sb->s_inodes);
spin_unlock(&sb->s_inode_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);
static inline void inode_sb_list_del(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
if (!list_empty(&inode->i_sb_list)) {
spin_lock(&sb->s_inode_list_lock);
list_del_init(&inode->i_sb_list);
spin_unlock(&sb->s_inode_list_lock);
}
}
static unsigned long hash(struct super_block *sb, unsigned long hashval)
{
unsigned long tmp;
tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
L1_CACHE_BYTES;
tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
return tmp & i_hash_mask;
}
/**
* __insert_inode_hash - hash an inode
* @inode: unhashed inode
* @hashval: unsigned long value used to locate this object in the
* inode_hashtable.
*
* Add an inode to the inode hash for this superblock.
*/
void __insert_inode_hash(struct inode *inode, unsigned long hashval)
{
struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);
spin_lock(&inode_hash_lock);
spin_lock(&inode->i_lock);
hlist_add_head_rcu(&inode->i_hash, b);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__insert_inode_hash);
/**
* __remove_inode_hash - remove an inode from the hash
* @inode: inode to unhash
*
* Remove an inode from the superblock.
*/
void __remove_inode_hash(struct inode *inode)
{
spin_lock(&inode_hash_lock);
spin_lock(&inode->i_lock);
hlist_del_init_rcu(&inode->i_hash);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__remove_inode_hash);
void dump_mapping(const struct address_space *mapping)
{
struct inode *host;
const struct address_space_operations *a_ops;
struct hlist_node *dentry_first;
struct dentry *dentry_ptr;
struct dentry dentry;
char fname[64] = {};
unsigned long ino;
/*
* If mapping is an invalid pointer, we don't want to crash
* accessing it, so probe everything depending on it carefully.
*/
if (get_kernel_nofault(host, &mapping->host) ||
get_kernel_nofault(a_ops, &mapping->a_ops)) {
pr_warn("invalid mapping:%px\n", mapping);
return;
}
if (!host) {
pr_warn("aops:%ps\n", a_ops);
return;
}
if (get_kernel_nofault(dentry_first, &host->i_dentry.first) ||
get_kernel_nofault(ino, &host->i_ino)) {
pr_warn("aops:%ps invalid inode:%px\n", a_ops, host);
return;
}
if (!dentry_first) {
pr_warn("aops:%ps ino:%lx\n", a_ops, ino);
return;
}
dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
if (get_kernel_nofault(dentry, dentry_ptr) ||
!dentry.d_parent || !dentry.d_name.name) {
pr_warn("aops:%ps ino:%lx invalid dentry:%px\n",
a_ops, ino, dentry_ptr);
return;
}
if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0)
strscpy(fname, "<invalid>");
/*
* Even if strncpy_from_kernel_nofault() succeeded,
* the fname could be unreliable
*/
pr_warn("aops:%ps ino:%lx dentry name(?):\"%s\"\n",
a_ops, ino, fname);
}
void clear_inode(struct inode *inode)
{
/*
* We have to cycle the i_pages lock here because reclaim can be in the
* process of removing the last page (in __filemap_remove_folio())
* and we must not free the mapping under it.
*/
xa_lock_irq(&inode->i_data.i_pages);
BUG_ON(inode->i_data.nrpages);
/*
* Almost always, mapping_empty(&inode->i_data) here; but there are
* two known and long-standing ways in which nodes may get left behind
* (when deep radix-tree node allocation failed partway; or when THP
* collapse_file() failed). Until those two known cases are cleaned up,
* or a cleanup function is called here, do not BUG_ON(!mapping_empty),
* nor even WARN_ON(!mapping_empty).
*/
xa_unlock_irq(&inode->i_data.i_pages);
BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list));
/* don't need i_lock here, no concurrent mods to i_state */
inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(clear_inode);
/*
* Free the inode passed in, removing it from the lists it is still connected
* to. We remove any pages still attached to the inode and wait for any IO that
* is still in progress before finally destroying the inode.
*
* An inode must already be marked I_FREEING so that we avoid the inode being
* moved back onto lists if we race with other code that manipulates the lists
* (e.g. writeback_single_inode). The caller is responsible for setting this.
*
* An inode must already be removed from the LRU list before being evicted from
* the cache. This should occur atomically with setting the I_FREEING state
* flag, so no inodes here should ever be on the LRU when being evicted.
*/
static void evict(struct inode *inode)
{
const struct super_operations *op = inode->i_sb->s_op;
BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode);
spin_lock(&inode->i_lock);
inode_wait_for_lru_isolating(inode);
/*
* Wait for flusher thread to be done with the inode so that filesystem
* does not start destroying it while writeback is still running. Since
* the inode has I_FREEING set, flusher thread won't start new work on
* the inode. We just have to wait for running writeback to finish.
*/
inode_wait_for_writeback(inode);
spin_unlock(&inode->i_lock);
if (op->evict_inode) {
op->evict_inode(inode);
} else {
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
}
if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode);
/*
* Wake up waiters in __wait_on_freeing_inode().
*
* It is an invariant that any thread we need to wake up is already
* accounted for before remove_inode_hash() acquires ->i_lock -- both
* sides take the lock and sleep is aborted if the inode is found
* unhashed. Thus either the sleeper wins and goes off CPU, or removal
* wins and the sleeper aborts after testing with the lock.
*
* This also means we don't need any fences for the call below.
*/
inode_wake_up_bit(inode, __I_NEW);
BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); destroy_inode(inode);
}
/*
* dispose_list - dispose of the contents of a local list
* @head: the head of the list to free
*
* Dispose-list gets a local list with local inodes in it, so it doesn't
* need to worry about list corruption and SMP locks.
*/
static void dispose_list(struct list_head *head)
{
while (!list_empty(head)) {
struct inode *inode;
inode = list_first_entry(head, struct inode, i_lru);
list_del_init(&inode->i_lru);
evict(inode);
cond_resched();
}
}
/**
* evict_inodes - evict all evictable inodes for a superblock
* @sb: superblock to operate on
*
* Make sure that no inodes with zero refcount are retained. This is
* called by superblock shutdown after having SB_ACTIVE flag removed,
* so any inode reaching zero refcount during or after that call will
* be immediately evicted.
*/
void evict_inodes(struct super_block *sb)
{
struct inode *inode, *next;
LIST_HEAD(dispose);
again:
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;
spin_lock(&inode->i_lock);
if (atomic_read(&inode->i_count)) {
spin_unlock(&inode->i_lock);
continue;
}
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
spin_unlock(&inode->i_lock);
continue;
}
inode->i_state |= I_FREEING;
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
/*
* We can have a ton of inodes to evict at unmount time given
* enough memory, check to see if we need to go to sleep for a
* bit so we don't livelock.
*/
if (need_resched()) {
spin_unlock(&sb->s_inode_list_lock);
cond_resched();
dispose_list(&dispose);
goto again;
}
}
spin_unlock(&sb->s_inode_list_lock);
dispose_list(&dispose);
}
EXPORT_SYMBOL_GPL(evict_inodes);
/*
* Isolate the inode from the LRU in preparation for freeing it.
*
* If the inode has the I_REFERENCED flag set, then it means that it has been
* used recently - the flag is set in iput_final(). When we encounter such an
* inode, clear the flag and move it to the back of the LRU so it gets another
* pass through the LRU before it gets reclaimed. This is necessary because of
* the fact we are doing lazy LRU updates to minimise lock contention so the
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
static enum lru_status inode_lru_isolate(struct list_head *item,
struct list_lru_one *lru, void *arg)
{
struct list_head *freeable = arg;
struct inode *inode = container_of(item, struct inode, i_lru);
/*
* We are inverting the lru lock/inode->i_lock here, so use a
* trylock. If we fail to get the lock, just skip it.
*/
if (!spin_trylock(&inode->i_lock))
return LRU_SKIP;
/*
* Inodes can get referenced, redirtied, or repopulated while
* they're already on the LRU, and this can make them
* unreclaimable for a while. Remove them lazily here; iput,
* sync, or the last page cache deletion will requeue them.
*/
if (atomic_read(&inode->i_count) ||
(inode->i_state & ~I_REFERENCED) ||
!mapping_shrinkable(&inode->i_data)) {
list_lru_isolate(lru, &inode->i_lru);
spin_unlock(&inode->i_lock);
this_cpu_dec(nr_unused);
return LRU_REMOVED;
}
/* Recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
return LRU_ROTATE;
}
/*
* On highmem systems, mapping_shrinkable() permits dropping
* page cache in order to free up struct inodes: lowmem might
* be under pressure before the cache inside the highmem zone.
*/
if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
inode_pin_lru_isolating(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&lru->lock);
if (remove_inode_buffers(inode)) {
unsigned long reap;
reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
else
__count_vm_events(PGINODESTEAL, reap);
mm_account_reclaimed_pages(reap);
}
inode_unpin_lru_isolating(inode);
return LRU_RETRY;
}
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
list_lru_isolate_move(lru, &inode->i_lru, freeable);
spin_unlock(&inode->i_lock);
this_cpu_dec(nr_unused);
return LRU_REMOVED;
}
/*
* Walk the superblock inode LRU for freeable inodes and attempt to free them.
* This is called from the superblock shrinker function with a number of inodes
* to trim from the LRU. Inodes to be freed are moved to a temporary list and
* then are freed outside inode_lock by dispose_list().
*/
long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
{
LIST_HEAD(freeable);
long freed;
freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
inode_lru_isolate, &freeable);
dispose_list(&freeable);
return freed;
}
static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked);
/*
* Called with the inode lock held.
*/
static struct inode *find_inode(struct super_block *sb,
struct hlist_head *head,
int (*test)(struct inode *, void *),
void *data, bool is_inode_hash_locked)
{
struct inode *inode = NULL;
if (is_inode_hash_locked)
lockdep_assert_held(&inode_hash_lock);
else
lockdep_assert_not_held(&inode_hash_lock);
rcu_read_lock();
repeat:
hlist_for_each_entry_rcu(inode, head, i_hash) {
if (inode->i_sb != sb)
continue;
if (!test(inode, data))
continue;
spin_lock(&inode->i_lock);
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode, is_inode_hash_locked);
goto repeat;
}
if (unlikely(inode->i_state & I_CREATING)) {
spin_unlock(&inode->i_lock);
rcu_read_unlock();
return ERR_PTR(-ESTALE);
}
__iget(inode);
spin_unlock(&inode->i_lock);
rcu_read_unlock();
return inode;
}
rcu_read_unlock();
return NULL;
}
/*
* find_inode_fast is the fast path version of find_inode, see the comment at
* iget_locked for details.
*/
static struct inode *find_inode_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino,
bool is_inode_hash_locked)
{
struct inode *inode = NULL;
if (is_inode_hash_locked)
lockdep_assert_held(&inode_hash_lock);
else
lockdep_assert_not_held(&inode_hash_lock);
rcu_read_lock();
repeat:
hlist_for_each_entry_rcu(inode, head, i_hash) {
if (inode->i_ino != ino)
continue;
if (inode->i_sb != sb)
continue;
spin_lock(&inode->i_lock);
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode, is_inode_hash_locked);
goto repeat;
}
if (unlikely(inode->i_state & I_CREATING)) {
spin_unlock(&inode->i_lock);
rcu_read_unlock();
return ERR_PTR(-ESTALE);
}
__iget(inode);
spin_unlock(&inode->i_lock);
rcu_read_unlock();
return inode;
}
rcu_read_unlock();
return NULL;
}
/*
* Each cpu owns a range of LAST_INO_BATCH numbers.
* 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
* to renew the exhausted range.
*
* This does not significantly increase overflow rate because every CPU can
* consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
* NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
* 2^32 range, and is a worst-case. Even a 50% wastage would only increase
* overflow rate by 2x, which does not seem too significant.
*
* On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
* error if st_ino won't fit in target struct field. Use 32bit counter
* here to attempt to avoid that.
*/
#define LAST_INO_BATCH 1024
static DEFINE_PER_CPU(unsigned int, last_ino);
unsigned int get_next_ino(void)
{
unsigned int *p = &get_cpu_var(last_ino);
unsigned int res = *p;
#ifdef CONFIG_SMP
if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
static atomic_t shared_last_ino;
int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);
res = next - LAST_INO_BATCH;
}
#endif
res++;
/* get_next_ino should not provide a 0 inode number */
if (unlikely(!res)) res++;
*p = res;
put_cpu_var(last_ino);
return res;
}
EXPORT_SYMBOL(get_next_ino);
/**
* new_inode - obtain an inode
* @sb: superblock
*
* Allocates a new inode for given superblock. The default gfp_mask
* for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
* If HIGHMEM pages are unsuitable or it is known that pages allocated
* for the page cache are not reclaimable or migratable,
* mapping_set_gfp_mask() must be called with suitable flags on the
* newly created inode's mapping
*
*/
struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;
inode = alloc_inode(sb);
if (inode) inode_sb_list_add(inode);
return inode;
}
EXPORT_SYMBOL(new_inode);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void lockdep_annotate_inode_mutex_key(struct inode *inode)
{ if (S_ISDIR(inode->i_mode)) {
struct file_system_type *type = inode->i_sb->s_type;
/* Set new key only if filesystem hasn't already changed it */
if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
/*
* ensure nobody is actually holding i_mutex
*/
// mutex_destroy(&inode->i_mutex);
init_rwsem(&inode->i_rwsem);
lockdep_set_class(&inode->i_rwsem,
&type->i_mutex_dir_key);
}
}
}
EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
#endif
/**
* unlock_new_inode - clear the I_NEW state and wake up any waiters
* @inode: new inode to unlock
*
* Called when the inode is fully initialised to clear the new state of the
* inode and wake up anyone waiting for the inode to finish initialisation.
*/
void unlock_new_inode(struct inode *inode)
{
lockdep_annotate_inode_mutex_key(inode);
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW & ~I_CREATING;
/*
* Pairs with the barrier in prepare_to_wait_event() to make sure
* ___wait_var_event() either sees the bit cleared or
* waitqueue_active() check in wake_up_var() sees the waiter.
*/
smp_mb();
inode_wake_up_bit(inode, __I_NEW);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);
void discard_new_inode(struct inode *inode)
{
lockdep_annotate_inode_mutex_key(inode);
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW;
/*
* Pairs with the barrier in prepare_to_wait_event() to make sure
* ___wait_var_event() either sees the bit cleared or
* waitqueue_active() check in wake_up_var() sees the waiter.
*/
smp_mb();
inode_wake_up_bit(inode, __I_NEW);
spin_unlock(&inode->i_lock);
iput(inode);
}
EXPORT_SYMBOL(discard_new_inode);
/**
* lock_two_nondirectories - take two i_mutexes on non-directory objects
*
* Lock any non-NULL argument. Passed objects must not be directories.
* Zero, one or two objects may be locked by this function.
*
* @inode1: first inode to lock
* @inode2: second inode to lock
*/
void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
if (inode1)
WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
if (inode2)
WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
if (inode1 > inode2)
swap(inode1, inode2);
if (inode1)
inode_lock(inode1);
if (inode2 && inode2 != inode1)
inode_lock_nested(inode2, I_MUTEX_NONDIR2);
}
EXPORT_SYMBOL(lock_two_nondirectories);
/**
* unlock_two_nondirectories - release locks from lock_two_nondirectories()
* @inode1: first inode to unlock
* @inode2: second inode to unlock
*/
void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
if (inode1) {
WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
inode_unlock(inode1);
}
if (inode2 && inode2 != inode1) {
WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
inode_unlock(inode2);
}
}
EXPORT_SYMBOL(unlock_two_nondirectories);
/**
* inode_insert5 - obtain an inode from a mounted file system
* @inode: pre-allocated inode to use for insert to cache
* @hashval: hash value (usually inode number) to get
* @test: callback used for comparisons between inodes
* @set: callback used to initialize a new struct inode
* @data: opaque data pointer to pass to @test and @set
*
* Search for the inode specified by @hashval and @data in the inode cache,
* and if present return it with an increased reference count. This is a
* variant of iget5_locked() that doesn't allocate an inode.
*
* If the inode is not present in the cache, insert the pre-allocated inode and
* return it locked, hashed, and with the I_NEW flag set. The file system gets
* to fill it in before unlocking it via unlock_new_inode().
*
* Note that both @test and @set are called with the inode_hash_lock held, so
* they can't sleep.
*/
struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
struct inode *old;
again:
spin_lock(&inode_hash_lock);
old = find_inode(inode->i_sb, head, test, data, true);
if (unlikely(old)) {
/*
* Uhhuh, somebody else created the same inode under us.
* Use the old inode instead of the preallocated one.
*/
spin_unlock(&inode_hash_lock);
if (IS_ERR(old))
return NULL;
wait_on_inode(old);
if (unlikely(inode_unhashed(old))) {
iput(old);
goto again;
}
return old;
}
if (set && unlikely(set(inode, data))) {
spin_unlock(&inode_hash_lock);
return NULL;
}
/*
* Return the locked inode with I_NEW set, the
* caller is responsible for filling in the contents
*/
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head_rcu(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
/*
* Add inode to the sb list if it's not already. It has I_NEW at this
* point, so it should be safe to test i_sb_list locklessly.
*/
if (list_empty(&inode->i_sb_list))
inode_sb_list_add(inode);
return inode;
}
EXPORT_SYMBOL(inode_insert5);
/**
* iget5_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @hashval: hash value (usually inode number) to get
* @test: callback used for comparisons between inodes
* @set: callback used to initialize a new struct inode
* @data: opaque data pointer to pass to @test and @set
*
* Search for the inode specified by @hashval and @data in the inode cache,
* and if present return it with an increased reference count. This is a
* generalized version of iget_locked() for file systems where the inode
* number is not sufficient for unique identification of an inode.
*
* If the inode is not present in the cache, allocate and insert a new inode
* and return it locked, hashed, and with the I_NEW flag set. The file system
* gets to fill it in before unlocking it via unlock_new_inode().
*
* Note that both @test and @set are called with the inode_hash_lock held, so
* they can't sleep.
*/
struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *data)
{
struct inode *inode = ilookup5(sb, hashval, test, data);
if (!inode) {
struct inode *new = alloc_inode(sb);
if (new) {
inode = inode_insert5(new, hashval, test, set, data);
if (unlikely(inode != new))
destroy_inode(new);
}
}
return inode;
}
EXPORT_SYMBOL(iget5_locked);
/**
* iget5_locked_rcu - obtain an inode from a mounted file system
* @sb: super block of file system
* @hashval: hash value (usually inode number) to get
* @test: callback used for comparisons between inodes
* @set: callback used to initialize a new struct inode
* @data: opaque data pointer to pass to @test and @set
*
* This is equivalent to iget5_locked, except the @test callback must
* tolerate the inode not being stable, including being mid-teardown.
*/
struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode, *new;
again:
inode = find_inode(sb, head, test, data, false);
if (inode) {
if (IS_ERR(inode))
return NULL;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
goto again;
}
return inode;
}
new = alloc_inode(sb);
if (new) {
inode = inode_insert5(new, hashval, test, set, data);
if (unlikely(inode != new))
destroy_inode(new);
}
return inode;
}
EXPORT_SYMBOL_GPL(iget5_locked_rcu);
/**
* iget_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @ino: inode number to get
*
* Search for the inode specified by @ino in the inode cache and if present
* return it with an increased reference count. This is for file systems
* where the inode number is sufficient for unique identification of an inode.
*
* If the inode is not in cache, allocate a new inode and return it locked,
* hashed, and with the I_NEW flag set. The file system gets to fill it in
* before unlocking it via unlock_new_inode().
*/
struct inode *iget_locked(struct super_block *sb, unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
again:
inode = find_inode_fast(sb, head, ino, false);
if (inode) {
if (IS_ERR(inode))
return NULL;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
goto again;
}
return inode;
}
inode = alloc_inode(sb);
if (inode) {
struct inode *old;
spin_lock(&inode_hash_lock);
/* We released the lock, so.. */
old = find_inode_fast(sb, head, ino, true);
if (!old) {
inode->i_ino = ino;
spin_lock(&inode->i_lock);
inode->i_state = I_NEW;
hlist_add_head_rcu(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
inode_sb_list_add(inode);
/* Return the locked inode with I_NEW set, the
* caller is responsible for filling in the contents
*/
return inode;
}
/*
* Uhhuh, somebody else created the same inode under
* us. Use the old inode instead of the one we just
* allocated.
*/
spin_unlock(&inode_hash_lock);
destroy_inode(inode);
if (IS_ERR(old))
return NULL;
inode = old;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
goto again;
}
}
return inode;
}
EXPORT_SYMBOL(iget_locked);
/*
* search the inode cache for a matching inode number.
* If we find one, then the inode number we are trying to
* allocate is not unique and so we should not use it.
*
* Returns 1 if the inode number is unique, 0 if it is not.
*/
static int test_inode_iunique(struct super_block *sb, unsigned long ino)
{
struct hlist_head *b = inode_hashtable + hash(sb, ino);
struct inode *inode;
hlist_for_each_entry_rcu(inode, b, i_hash) {
if (inode->i_ino == ino && inode->i_sb == sb)
return 0;
}
return 1;
}
/**
* iunique - get a unique inode number
* @sb: superblock
* @max_reserved: highest reserved inode number
*
* Obtain an inode number that is unique on the system for a given
* superblock. This is used by file systems that have no natural
* permanent inode numbering system. An inode number is returned that
* is higher than the reserved limit but unique.
*
* BUGS:
* With a large number of inodes live on the file system this function
* currently becomes quite slow.
*/
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
/*
* On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
* error if st_ino won't fit in target struct field. Use 32bit counter
* here to attempt to avoid that.
*/
static DEFINE_SPINLOCK(iunique_lock);
static unsigned int counter;
ino_t res;
rcu_read_lock();
spin_lock(&iunique_lock);
do {
if (counter <= max_reserved)
counter = max_reserved + 1;
res = counter++;
} while (!test_inode_iunique(sb, res));
spin_unlock(&iunique_lock);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL(iunique);
struct inode *igrab(struct inode *inode)
{
spin_lock(&inode->i_lock);
if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
__iget(inode);
spin_unlock(&inode->i_lock);
} else {
spin_unlock(&inode->i_lock);
/*
* Handle the case where s_op->clear_inode is not been
* called yet, and somebody is calling igrab
* while the inode is getting freed.
*/
inode = NULL;
}
return inode;
}
EXPORT_SYMBOL(igrab);
/**
* ilookup5_nowait - search for an inode in the inode cache
* @sb: super block of file system to search
* @hashval: hash value (usually inode number) to search for
* @test: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @test
*
* Search for the inode specified by @hashval and @data in the inode cache.
* If the inode is in the cache, the inode is returned with an incremented
* reference count.
*
* Note: I_NEW is not waited upon so you have to be very careful what you do
* with the returned inode. You probably should be using ilookup5() instead.
*
* Note2: @test is called with the inode_hash_lock held, so can't sleep.
*/
struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode;
spin_lock(&inode_hash_lock);
inode = find_inode(sb, head, test, data, true);
spin_unlock(&inode_hash_lock);
return IS_ERR(inode) ? NULL : inode;
}
EXPORT_SYMBOL(ilookup5_nowait);
/**
* ilookup5 - search for an inode in the inode cache
* @sb: super block of file system to search
* @hashval: hash value (usually inode number) to search for
* @test: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @test
*
* Search for the inode specified by @hashval and @data in the inode cache,
* and if the inode is in the cache, return the inode with an incremented
* reference count. Waits on I_NEW before returning the inode.
* returned with an incremented reference count.
*
* This is a generalized version of ilookup() for file systems where the
* inode number is not sufficient for unique identification of an inode.
*
* Note: @test is called with the inode_hash_lock held, so can't sleep.
*/
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct inode *inode;
again:
inode = ilookup5_nowait(sb, hashval, test, data);
if (inode) {
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
goto again;
}
}
return inode;
}
EXPORT_SYMBOL(ilookup5);
/**
* ilookup - search for an inode in the inode cache
* @sb: super block of file system to search
* @ino: inode number to search for
*
* Search for the inode @ino in the inode cache, and if the inode is in the
* cache, the inode is returned with an incremented reference count.
*/
struct inode *ilookup(struct super_block *sb, unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
again:
inode = find_inode_fast(sb, head, ino, false);
if (inode) {
if (IS_ERR(inode))
return NULL;
wait_on_inode(inode);
if (unlikely(inode_unhashed(inode))) {
iput(inode);
goto again;
}
}
return inode;
}
EXPORT_SYMBOL(ilookup);
/**
* find_inode_nowait - find an inode in the inode cache
* @sb: super block of file system to search
* @hashval: hash value (usually inode number) to search for
* @match: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @match
*
* Search for the inode specified by @hashval and @data in the inode
* cache, where the helper function @match will return 0 if the inode
* does not match, 1 if the inode does match, and -1 if the search
* should be stopped. The @match function must be responsible for
* taking the i_lock spin_lock and checking i_state for an inode being
* freed or being initialized, and incrementing the reference count
* before returning 1. It also must not sleep, since it is called with
* the inode_hash_lock spinlock held.
*
* This is a even more generalized version of ilookup5() when the
* function must never block --- find_inode() can block in
* __wait_on_freeing_inode() --- or when the caller can not increment
* the reference count because the resulting iput() might cause an
* inode eviction. The tradeoff is that the @match funtion must be
* very carefully implemented.
*/
struct inode *find_inode_nowait(struct super_block *sb,
unsigned long hashval,
int (*match)(struct inode *, unsigned long,
void *),
void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode, *ret_inode = NULL;
int mval;
spin_lock(&inode_hash_lock);
hlist_for_each_entry(inode, head, i_hash) {
if (inode->i_sb != sb)
continue;
mval = match(inode, hashval, data);
if (mval == 0)
continue;
if (mval == 1)
ret_inode = inode;
goto out;
}
out:
spin_unlock(&inode_hash_lock);
return ret_inode;
}
EXPORT_SYMBOL(find_inode_nowait);
/**
* find_inode_rcu - find an inode in the inode cache
* @sb: Super block of file system to search
* @hashval: Key to hash
* @test: Function to test match on an inode
* @data: Data for test function
*
* Search for the inode specified by @hashval and @data in the inode cache,
* where the helper function @test will return 0 if the inode does not match
* and 1 if it does. The @test function must be responsible for taking the
* i_lock spin_lock and checking i_state for an inode being freed or being
* initialized.
*
* If successful, this will return the inode for which the @test function
* returned 1 and NULL otherwise.
*
* The @test function is not permitted to take a ref on any inode presented.
* It is also not permitted to sleep.
*
* The caller must hold the RCU read lock.
*/
struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode;
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"suspicious find_inode_rcu() usage");
hlist_for_each_entry_rcu(inode, head, i_hash) {
if (inode->i_sb == sb &&
!(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) &&
test(inode, data))
return inode;
}
return NULL;
}
EXPORT_SYMBOL(find_inode_rcu);
/**
* find_inode_by_ino_rcu - Find an inode in the inode cache
* @sb: Super block of file system to search
* @ino: The inode number to match
*
* Search for the inode specified by @hashval and @data in the inode cache,
* where the helper function @test will return 0 if the inode does not match
* and 1 if it does. The @test function must be responsible for taking the
* i_lock spin_lock and checking i_state for an inode being freed or being
* initialized.
*
* If successful, this will return the inode for which the @test function
* returned 1 and NULL otherwise.
*
* The @test function is not permitted to take a ref on any inode presented.
* It is also not permitted to sleep.
*
* The caller must hold the RCU read lock.
*/
struct inode *find_inode_by_ino_rcu(struct super_block *sb,
unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"suspicious find_inode_by_ino_rcu() usage");
hlist_for_each_entry_rcu(inode, head, i_hash) {
if (inode->i_ino == ino &&
inode->i_sb == sb &&
!(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)))
return inode;
}
return NULL;
}
EXPORT_SYMBOL(find_inode_by_ino_rcu);
int insert_inode_locked(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
ino_t ino = inode->i_ino;
struct hlist_head *head = inode_hashtable + hash(sb, ino);
while (1) {
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
hlist_for_each_entry(old, head, i_hash) {
if (old->i_ino != ino)
continue;
if (old->i_sb != sb)
continue;
spin_lock(&old->i_lock);
if (old->i_state & (I_FREEING|I_WILL_FREE)) {
spin_unlock(&old->i_lock);
continue;
}
break;
}
if (likely(!old)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW | I_CREATING;
hlist_add_head_rcu(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
return 0;
}
if (unlikely(old->i_state & I_CREATING)) {
spin_unlock(&old->i_lock);
spin_unlock(&inode_hash_lock);
return -EBUSY;
}
__iget(old);
spin_unlock(&old->i_lock);
spin_unlock(&inode_hash_lock);
wait_on_inode(old);
if (unlikely(!inode_unhashed(old))) {
iput(old);
return -EBUSY;
}
iput(old);
}
}
EXPORT_SYMBOL(insert_inode_locked);
int insert_inode_locked4(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct inode *old;
inode->i_state |= I_CREATING;
old = inode_insert5(inode, hashval, test, NULL, data);
if (old != inode) {
iput(old);
return -EBUSY;
}
return 0;
}
EXPORT_SYMBOL(insert_inode_locked4);
int generic_delete_inode(struct inode *inode)
{
return 1;
}
EXPORT_SYMBOL(generic_delete_inode);
/*
* Called when we're dropping the last reference
* to an inode.
*
* Call the FS "drop_inode()" function, defaulting to
* the legacy UNIX filesystem behaviour. If it tells
* us to evict inode, do so. Otherwise, retain inode
* in cache if fs is alive, sync and evict if fs is
* shutting down.
*/
static void iput_final(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
const struct super_operations *op = inode->i_sb->s_op;
unsigned long state;
int drop;
WARN_ON(inode->i_state & I_NEW);
if (op->drop_inode)
drop = op->drop_inode(inode);
else
drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) &&
(sb->s_flags & SB_ACTIVE)) {
__inode_add_lru(inode, true);
spin_unlock(&inode->i_lock);
return;
}
state = inode->i_state;
if (!drop) {
WRITE_ONCE(inode->i_state, state | I_WILL_FREE);
spin_unlock(&inode->i_lock);
write_inode_now(inode, 1);
spin_lock(&inode->i_lock);
state = inode->i_state;
WARN_ON(state & I_NEW);
state &= ~I_WILL_FREE;
}
WRITE_ONCE(inode->i_state, state | I_FREEING);
if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
evict(inode);
}
/**
* iput - put an inode
* @inode: inode to put
*
* Puts an inode, dropping its usage count. If the inode use count hits
* zero, the inode is then freed and may also be destroyed.
*
* Consequently, iput() can sleep.
*/
void iput(struct inode *inode)
{ if (!inode)
return;
BUG_ON(inode->i_state & I_CLEAR);
retry:
if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count);
spin_unlock(&inode->i_lock);
trace_writeback_lazytime_iput(inode);
mark_inode_dirty_sync(inode);
goto retry;
}
iput_final(inode);
}
}
EXPORT_SYMBOL(iput);
#ifdef CONFIG_BLOCK
/**
* bmap - find a block number in a file
* @inode: inode owning the block number being requested
* @block: pointer containing the block to find
*
* Replaces the value in ``*block`` with the block number on the device holding
* corresponding to the requested block number in the file.
* That is, asked for block 4 of inode 1 the function will replace the
* 4 in ``*block``, with disk block relative to the disk start that holds that
* block of the file.
*
* Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a
* hole, returns 0 and ``*block`` is also set to 0.
*/
int bmap(struct inode *inode, sector_t *block)
{
if (!inode->i_mapping->a_ops->bmap)
return -EINVAL;
*block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block);
return 0;
}
EXPORT_SYMBOL(bmap);
#endif
/*
* With relative atime, only update atime if the previous atime is
* earlier than or equal to either the ctime or mtime,
* or if at least a day has passed since the last atime update.
*/
static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode,
struct timespec64 now)
{
struct timespec64 atime, mtime, ctime;
if (!(mnt->mnt_flags & MNT_RELATIME))
return true;
/*
* Is mtime younger than or equal to atime? If yes, update atime:
*/
atime = inode_get_atime(inode);
mtime = inode_get_mtime(inode);
if (timespec64_compare(&mtime, &atime) >= 0)
return true;
/*
* Is ctime younger than or equal to atime? If yes, update atime:
*/
ctime = inode_get_ctime(inode);
if (timespec64_compare(&ctime, &atime) >= 0)
return true;
/*
* Is the previous atime value older than a day? If yes,
* update atime:
*/
if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60)
return true;
/*
* Good, we can skip the atime update:
*/
return false;
}
/**
* inode_update_timestamps - update the timestamps on the inode
* @inode: inode to be updated
* @flags: S_* flags that needed to be updated
*
* The update_time function is called when an inode's timestamps need to be
* updated for a read or write operation. This function handles updating the
* actual timestamps. It's up to the caller to ensure that the inode is marked
* dirty appropriately.
*
* In the case where any of S_MTIME, S_CTIME, or S_VERSION need to be updated,
* attempt to update all three of them. S_ATIME updates can be handled
* independently of the rest.
*
* Returns a set of S_* flags indicating which values changed.
*/
int inode_update_timestamps(struct inode *inode, int flags)
{
int updated = 0;
struct timespec64 now;
if (flags & (S_MTIME|S_CTIME|S_VERSION)) {
struct timespec64 ctime = inode_get_ctime(inode);
struct timespec64 mtime = inode_get_mtime(inode);
now = inode_set_ctime_current(inode);
if (!timespec64_equal(&now, &ctime))
updated |= S_CTIME;
if (!timespec64_equal(&now, &mtime)) { inode_set_mtime_to_ts(inode, now);
updated |= S_MTIME;
}
if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated))
updated |= S_VERSION;
} else {
now = current_time(inode);
}
if (flags & S_ATIME) {
struct timespec64 atime = inode_get_atime(inode);
if (!timespec64_equal(&now, &atime)) {
inode_set_atime_to_ts(inode, now);
updated |= S_ATIME;
}
}
return updated;
}
EXPORT_SYMBOL(inode_update_timestamps);
/**
* generic_update_time - update the timestamps on the inode
* @inode: inode to be updated
* @flags: S_* flags that needed to be updated
*
* The update_time function is called when an inode's timestamps need to be
* updated for a read or write operation. In the case where any of S_MTIME, S_CTIME,
* or S_VERSION need to be updated we attempt to update all three of them. S_ATIME
* updates can be handled done independently of the rest.
*
* Returns a S_* mask indicating which fields were updated.
*/
int generic_update_time(struct inode *inode, int flags)
{
int updated = inode_update_timestamps(inode, flags);
int dirty_flags = 0;
if (updated & (S_ATIME|S_MTIME|S_CTIME)) dirty_flags = inode->i_sb->s_flags & SB_LAZYTIME ? I_DIRTY_TIME : I_DIRTY_SYNC;
if (updated & S_VERSION)
dirty_flags |= I_DIRTY_SYNC;
__mark_inode_dirty(inode, dirty_flags);
return updated;
}
EXPORT_SYMBOL(generic_update_time);
/*
* This does the actual work of updating an inodes time or version. Must have
* had called mnt_want_write() before calling this.
*/
int inode_update_time(struct inode *inode, int flags)
{
if (inode->i_op->update_time)
return inode->i_op->update_time(inode, flags); generic_update_time(inode, flags);
return 0;
}
EXPORT_SYMBOL(inode_update_time);
/**
* atime_needs_update - update the access time
* @path: the &struct path to update
* @inode: inode to update
*
* Update the accessed time on an inode and mark it for writeback.
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
bool atime_needs_update(const struct path *path, struct inode *inode)
{
struct vfsmount *mnt = path->mnt;
struct timespec64 now, atime;
if (inode->i_flags & S_NOATIME)
return false;
/* Atime updates will likely cause i_uid and i_gid to be written
* back improprely if their true value is unknown to the vfs.
*/
if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode))
return false;
if (IS_NOATIME(inode))
return false;
if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode))
return false;
if (mnt->mnt_flags & MNT_NOATIME)
return false;
if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
return false;
now = current_time(inode);
if (!relatime_need_update(mnt, inode, now))
return false;
atime = inode_get_atime(inode);
if (timespec64_equal(&atime, &now))
return false;
return true;
}
void touch_atime(const struct path *path)
{
struct vfsmount *mnt = path->mnt;
struct inode *inode = d_inode(path->dentry);
if (!atime_needs_update(path, inode))
return;
if (!sb_start_write_trylock(inode->i_sb))
return;
if (mnt_get_write_access(mnt) != 0)
goto skip_update;
/*
* File systems can error out when updating inodes if they need to
* allocate new space to modify an inode (such is the case for
* Btrfs), but since we touch atime while walking down the path we
* really don't care if we failed to update the atime of the file,
* so just ignore the return value.
* We may also fail on filesystems that have the ability to make parts
* of the fs read only, e.g. subvolumes in Btrfs.
*/
inode_update_time(inode, S_ATIME);
mnt_put_write_access(mnt);
skip_update:
sb_end_write(inode->i_sb);
}
EXPORT_SYMBOL(touch_atime);
/*
* Return mask of changes for notify_change() that need to be done as a
* response to write or truncate. Return 0 if nothing has to be changed.
* Negative value on error (change should be denied).
*/
int dentry_needs_remove_privs(struct mnt_idmap *idmap,
struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
int mask = 0;
int ret;
if (IS_NOSEC(inode))
return 0;
mask = setattr_should_drop_suidgid(idmap, inode);
ret = security_inode_need_killpriv(dentry);
if (ret < 0)
return ret;
if (ret)
mask |= ATTR_KILL_PRIV;
return mask;
}
static int __remove_privs(struct mnt_idmap *idmap,
struct dentry *dentry, int kill)
{
struct iattr newattrs;
newattrs.ia_valid = ATTR_FORCE | kill;
/*
* Note we call this on write, so notify_change will not
* encounter any conflicting delegations:
*/
return notify_change(idmap, dentry, &newattrs, NULL);
}
int file_remove_privs_flags(struct file *file, unsigned int flags)
{ struct dentry *dentry = file_dentry(file);
struct inode *inode = file_inode(file);
int error = 0;
int kill;
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0)
return kill;
if (kill) { if (flags & IOCB_NOWAIT)
return -EAGAIN;
error = __remove_privs(file_mnt_idmap(file), dentry, kill);
}
if (!error) inode_has_no_xattr(inode);
return error;
}
EXPORT_SYMBOL_GPL(file_remove_privs_flags);
/**
* file_remove_privs - remove special file privileges (suid, capabilities)
* @file: file to remove privileges from
*
* When file is modified by a write or truncation ensure that special
* file privileges are removed.
*
* Return: 0 on success, negative errno on failure.
*/
int file_remove_privs(struct file *file)
{
return file_remove_privs_flags(file, 0);
}
EXPORT_SYMBOL(file_remove_privs);
/**
* current_time - Return FS time (possibly fine-grained)
* @inode: inode.
*
* Return the current time truncated to the time granularity supported by
* the fs, as suitable for a ctime/mtime change. If the ctime is flagged
* as having been QUERIED, get a fine-grained timestamp, but don't update
* the floor.
*
* For a multigrain inode, this is effectively an estimate of the timestamp
* that a file would receive. An actual update must go through
* inode_set_ctime_current().
*/
struct timespec64 current_time(struct inode *inode)
{
struct timespec64 now;
u32 cns;
ktime_get_coarse_real_ts64_mg(&now);
if (!is_mgtime(inode))
goto out;
/* If nothing has queried it, then coarse time is fine */
cns = smp_load_acquire(&inode->i_ctime_nsec);
if (cns & I_CTIME_QUERIED) {
/*
* If there is no apparent change, then get a fine-grained
* timestamp.
*/
if (now.tv_nsec == (cns & ~I_CTIME_QUERIED)) ktime_get_real_ts64(&now);
}
out:
return timestamp_truncate(now, inode);
}
EXPORT_SYMBOL(current_time);
static int inode_needs_update_time(struct inode *inode)
{
struct timespec64 now, ts;
int sync_it = 0;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return 0;
now = current_time(inode);
ts = inode_get_mtime(inode);
if (!timespec64_equal(&ts, &now))
sync_it |= S_MTIME;
ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
sync_it |= S_VERSION;
return sync_it;
}
static int __file_update_time(struct file *file, int sync_mode)
{
int ret = 0;
struct inode *inode = file_inode(file);
/* try to update time settings */
if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode);
mnt_put_write_access_file(file);
}
return ret;
}
/**
* file_update_time - update mtime and ctime time
* @file: file accessed
*
* Update the mtime and ctime members of an inode and mark the inode for
* writeback. Note that this function is meant exclusively for usage in
* the file write path of filesystems, and filesystems may choose to
* explicitly ignore updates via this function with the _NOCMTIME inode
* flag, e.g. for network filesystem where these imestamps are handled
* by the server. This can return an error for file systems who need to
* allocate space in order to update an inode.
*
* Return: 0 on success, negative errno on failure.
*/
int file_update_time(struct file *file)
{
int ret;
struct inode *inode = file_inode(file);
ret = inode_needs_update_time(inode); if (ret <= 0)
return ret;
return __file_update_time(file, ret);
}
EXPORT_SYMBOL(file_update_time);
/**
* file_modified_flags - handle mandated vfs changes when modifying a file
* @file: file that was modified
* @flags: kiocb flags
*
* When file has been modified ensure that special
* file privileges are removed and time settings are updated.
*
* If IOCB_NOWAIT is set, special file privileges will not be removed and
* time settings will not be updated. It will return -EAGAIN.
*
* Context: Caller must hold the file's inode lock.
*
* Return: 0 on success, negative errno on failure.
*/
static int file_modified_flags(struct file *file, int flags)
{
int ret;
struct inode *inode = file_inode(file);
/*
* Clear the security bits if the process is not being run by root.
* This keeps people from modifying setuid and setgid binaries.
*/
ret = file_remove_privs_flags(file, flags);
if (ret)
return ret;
if (unlikely(file->f_mode & FMODE_NOCMTIME))
return 0;
ret = inode_needs_update_time(inode);
if (ret <= 0)
return ret;
if (flags & IOCB_NOWAIT)
return -EAGAIN;
return __file_update_time(file, ret);
}
/**
* file_modified - handle mandated vfs changes when modifying a file
* @file: file that was modified
*
* When file has been modified ensure that special
* file privileges are removed and time settings are updated.
*
* Context: Caller must hold the file's inode lock.
*
* Return: 0 on success, negative errno on failure.
*/
int file_modified(struct file *file)
{
return file_modified_flags(file, 0);
}
EXPORT_SYMBOL(file_modified);
/**
* kiocb_modified - handle mandated vfs changes when modifying a file
* @iocb: iocb that was modified
*
* When file has been modified ensure that special
* file privileges are removed and time settings are updated.
*
* Context: Caller must hold the file's inode lock.
*
* Return: 0 on success, negative errno on failure.
*/
int kiocb_modified(struct kiocb *iocb)
{
return file_modified_flags(iocb->ki_filp, iocb->ki_flags);
}
EXPORT_SYMBOL_GPL(kiocb_modified);
int inode_needs_sync(struct inode *inode)
{
if (IS_SYNC(inode))
return 1;
if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
return 1;
return 0;
}
EXPORT_SYMBOL(inode_needs_sync);
/*
* If we try to find an inode in the inode hash while it is being
* deleted, we have to wait until the filesystem completes its
* deletion before reporting that it isn't found. This function waits
* until the deletion _might_ have completed. Callers are responsible
* to recheck inode state.
*
* It doesn't matter if I_NEW is not set initially, a call to
* wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
* will DTRT.
*/
static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked)
{
struct wait_bit_queue_entry wqe;
struct wait_queue_head *wq_head;
/*
* Handle racing against evict(), see that routine for more details.
*/
if (unlikely(inode_unhashed(inode))) {
WARN_ON(is_inode_hash_locked);
spin_unlock(&inode->i_lock);
return;
}
wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW);
prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
spin_unlock(&inode->i_lock);
rcu_read_unlock();
if (is_inode_hash_locked)
spin_unlock(&inode_hash_lock);
schedule();
finish_wait(wq_head, &wqe.wq_entry);
if (is_inode_hash_locked)
spin_lock(&inode_hash_lock);
rcu_read_lock();
}
static __initdata unsigned long ihash_entries;
static int __init set_ihash_entries(char *str)
{
if (!str)
return 0;
ihash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("ihash_entries=", set_ihash_entries);
/*
* Initialize the waitqueues and inode hash table.
*/
void __init inode_init_early(void)
{
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
inode_hashtable =
alloc_large_system_hash("Inode-cache",
sizeof(struct hlist_head),
ihash_entries,
14,
HASH_EARLY | HASH_ZERO,
&i_hash_shift,
&i_hash_mask,
0,
0);
}
void __init inode_init(void)
{
/* inode slab cache */
inode_cachep = kmem_cache_create("inode_cache",
sizeof(struct inode),
0,
(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
SLAB_ACCOUNT),
init_once);
/* Hash may have been set up in inode_init_early */
if (!hashdist)
return;
inode_hashtable =
alloc_large_system_hash("Inode-cache",
sizeof(struct hlist_head),
ihash_entries,
14,
HASH_ZERO,
&i_hash_shift,
&i_hash_mask,
0,
0);
}
void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
inode->i_mode = mode;
if (S_ISCHR(mode)) {
inode->i_fop = &def_chr_fops;
inode->i_rdev = rdev;
} else if (S_ISBLK(mode)) {
if (IS_ENABLED(CONFIG_BLOCK))
inode->i_fop = &def_blk_fops;
inode->i_rdev = rdev;
} else if (S_ISFIFO(mode))
inode->i_fop = &pipefifo_fops;
else if (S_ISSOCK(mode))
; /* leave it no_open_fops */
else
printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
" inode %s:%lu\n", mode, inode->i_sb->s_id,
inode->i_ino);
}
EXPORT_SYMBOL(init_special_inode);
/**
* inode_init_owner - Init uid,gid,mode for new inode according to posix standards
* @idmap: idmap of the mount the inode was created from
* @inode: New inode
* @dir: Directory inode
* @mode: mode of the new inode
*
* If the inode has been created through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions
* and initializing i_uid and i_gid. On non-idmapped mounts or if permission
* checking is to be performed on the raw inode simply pass @nop_mnt_idmap.
*/
void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
const struct inode *dir, umode_t mode)
{
inode_fsuid_set(inode, idmap);
if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid;
/* Directories are special, and always inherit S_ISGID */
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode_fsgid_set(inode, idmap);
inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_init_owner);
/**
* inode_owner_or_capable - check current task permissions to inode
* @idmap: idmap of the mount the inode was found from
* @inode: inode being checked
*
* Return true if current either has CAP_FOWNER in a namespace with the
* inode owner uid mapped, or owns the file.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
bool inode_owner_or_capable(struct mnt_idmap *idmap,
const struct inode *inode)
{
vfsuid_t vfsuid;
struct user_namespace *ns;
vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
return true;
ns = current_user_ns();
if (vfsuid_has_mapping(ns, vfsuid) && ns_capable(ns, CAP_FOWNER))
return true;
return false;
}
EXPORT_SYMBOL(inode_owner_or_capable);
/*
* Direct i/o helper functions
*/
bool inode_dio_finished(const struct inode *inode)
{
return atomic_read(&inode->i_dio_count) == 0;
}
EXPORT_SYMBOL(inode_dio_finished);
/**
* inode_dio_wait - wait for outstanding DIO requests to finish
* @inode: inode to wait for
*
* Waits for all pending direct I/O requests to finish so that we can
* proceed with a truncate or equivalent operation.
*
* Must be called under a lock that serializes taking new references
* to i_dio_count, usually by inode->i_mutex.
*/
void inode_dio_wait(struct inode *inode)
{
wait_var_event(&inode->i_dio_count, inode_dio_finished(inode));
}
EXPORT_SYMBOL(inode_dio_wait);
void inode_dio_wait_interruptible(struct inode *inode)
{
wait_var_event_interruptible(&inode->i_dio_count,
inode_dio_finished(inode));
}
EXPORT_SYMBOL(inode_dio_wait_interruptible);
/*
* inode_set_flags - atomically set some inode flags
*
* Note: the caller should be holding i_mutex, or else be sure that
* they have exclusive access to the inode structure (i.e., while the
* inode is being instantiated). The reason for the cmpxchg() loop
* --- which wouldn't be necessary if all code paths which modify
* i_flags actually followed this rule, is that there is at least one
* code path which doesn't today so we use cmpxchg() out of an abundance
* of caution.
*
* In the long run, i_mutex is overkill, and we should probably look
* at using the i_lock spinlock to protect i_flags, and then make sure
* it is so documented in include/linux/fs.h and that all code follows
* the locking convention!!
*/
void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask)
{ WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags);
}
EXPORT_SYMBOL(inode_set_flags);
void inode_nohighmem(struct inode *inode)
{
mapping_set_gfp_mask(inode->i_mapping, GFP_USER);
}
EXPORT_SYMBOL(inode_nohighmem);
struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
{ trace_inode_set_ctime_to_ts(inode, &ts);
set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec);
inode->i_ctime_sec = ts.tv_sec;
inode->i_ctime_nsec = ts.tv_nsec;
return ts;
}
EXPORT_SYMBOL(inode_set_ctime_to_ts);
/**
* timestamp_truncate - Truncate timespec to a granularity
* @t: Timespec
* @inode: inode being updated
*
* Truncate a timespec to the granularity supported by the fs
* containing the inode. Always rounds down. gran must
* not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns).
*/
struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
unsigned int gran = sb->s_time_gran;
t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max);
if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0;
/* Avoid division in the common cases 1 ns and 1 s. */
if (gran == 1)
; /* nothing */
else if (gran == NSEC_PER_SEC)
t.tv_nsec = 0;
else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran;
else
WARN(1, "invalid file time granularity: %u", gran);
return t;
}
EXPORT_SYMBOL(timestamp_truncate);
/**
* inode_set_ctime_current - set the ctime to current_time
* @inode: inode
*
* Set the inode's ctime to the current value for the inode. Returns the
* current value that was assigned. If this is not a multigrain inode, then we
* set it to the later of the coarse time and floor value.
*
* If it is multigrain, then we first see if the coarse-grained timestamp is
* distinct from what is already there. If so, then use that. Otherwise, get a
* fine-grained timestamp.
*
* After that, try to swap the new value into i_ctime_nsec. Accept the
* resulting ctime, regardless of the outcome of the swap. If it has
* already been replaced, then that timestamp is later than the earlier
* unacceptable one, and is thus acceptable.
*/
struct timespec64 inode_set_ctime_current(struct inode *inode)
{
struct timespec64 now;
u32 cns, cur;
ktime_get_coarse_real_ts64_mg(&now);
now = timestamp_truncate(now, inode);
/* Just return that if this is not a multigrain fs */
if (!is_mgtime(inode)) {
inode_set_ctime_to_ts(inode, now);
goto out;
}
/*
* A fine-grained time is only needed if someone has queried
* for timestamps, and the current coarse grained time isn't
* later than what's already there.
*/
cns = smp_load_acquire(&inode->i_ctime_nsec);
if (cns & I_CTIME_QUERIED) {
struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec,
.tv_nsec = cns & ~I_CTIME_QUERIED };
if (timespec64_compare(&now, &ctime) <= 0) {
ktime_get_real_ts64_mg(&now);
now = timestamp_truncate(now, inode); mgtime_counter_inc(mg_fine_stamps);
}
}
mgtime_counter_inc(mg_ctime_updates);
/* No need to cmpxchg if it's exactly the same */
if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { trace_ctime_xchg_skip(inode, &now);
goto out;
}
cur = cns;
retry:
/* Try to swap the nsec value into place. */
if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) {
/* If swap occurred, then we're (mostly) done */
inode->i_ctime_sec = now.tv_sec;
trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); mgtime_counter_inc(mg_ctime_swaps);
} else {
/*
* Was the change due to someone marking the old ctime QUERIED?
* If so then retry the swap. This can only happen once since
* the only way to clear I_CTIME_QUERIED is to stamp the inode
* with a new ctime.
*/
if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) {
cns = cur;
goto retry;
}
/* Otherwise, keep the existing ctime */
now.tv_sec = inode->i_ctime_sec;
now.tv_nsec = cur & ~I_CTIME_QUERIED;
}
out:
return now;
}
EXPORT_SYMBOL(inode_set_ctime_current);
/**
* inode_set_ctime_deleg - try to update the ctime on a delegated inode
* @inode: inode to update
* @update: timespec64 to set the ctime
*
* Attempt to atomically update the ctime on behalf of a delegation holder.
*
* The nfs server can call back the holder of a delegation to get updated
* inode attributes, including the mtime. When updating the mtime, update
* the ctime to a value at least equal to that.
*
* This can race with concurrent updates to the inode, in which
* case the update is skipped.
*
* Note that this works even when multigrain timestamps are not enabled,
* so it is used in either case.
*/
struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update)
{
struct timespec64 now, cur_ts;
u32 cur, old;
/* pairs with try_cmpxchg below */
cur = smp_load_acquire(&inode->i_ctime_nsec);
cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
cur_ts.tv_sec = inode->i_ctime_sec;
/* If the update is older than the existing value, skip it. */
if (timespec64_compare(&update, &cur_ts) <= 0)
return cur_ts;
ktime_get_coarse_real_ts64_mg(&now);
/* Clamp the update to "now" if it's in the future */
if (timespec64_compare(&update, &now) > 0)
update = now;
update = timestamp_truncate(update, inode);
/* No need to update if the values are already the same */
if (timespec64_equal(&update, &cur_ts))
return cur_ts;
/*
* Try to swap the nsec value into place. If it fails, that means
* it raced with an update due to a write or similar activity. That
* stamp takes precedence, so just skip the update.
*/
retry:
old = cur;
if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) {
inode->i_ctime_sec = update.tv_sec;
mgtime_counter_inc(mg_ctime_swaps);
return update;
}
/*
* Was the change due to another task marking the old ctime QUERIED?
*
* If so, then retry the swap. This can only happen once since
* the only way to clear I_CTIME_QUERIED is to stamp the inode
* with a new ctime.
*/
if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED)))
goto retry;
/* Otherwise, it was a new timestamp. */
cur_ts.tv_sec = inode->i_ctime_sec;
cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
return cur_ts;
}
EXPORT_SYMBOL(inode_set_ctime_deleg);
/**
* in_group_or_capable - check whether caller is CAP_FSETID privileged
* @idmap: idmap of the mount @inode was found from
* @inode: inode to check
* @vfsgid: the new/current vfsgid of @inode
*
* Check whether @vfsgid is in the caller's group list or if the caller is
* privileged with CAP_FSETID over @inode. This can be used to determine
* whether the setgid bit can be kept or must be dropped.
*
* Return: true if the caller is sufficiently privileged, false if not.
*/
bool in_group_or_capable(struct mnt_idmap *idmap,
const struct inode *inode, vfsgid_t vfsgid)
{ if (vfsgid_in_group_p(vfsgid))
return true;
if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
return true;
return false;
}
EXPORT_SYMBOL(in_group_or_capable);
/**
* mode_strip_sgid - handle the sgid bit for non-directories
* @idmap: idmap of the mount the inode was created from
* @dir: parent directory inode
* @mode: mode of the file to be created in @dir
*
* If the @mode of the new file has both the S_ISGID and S_IXGRP bit
* raised and @dir has the S_ISGID bit raised ensure that the caller is
* either in the group of the parent directory or they have CAP_FSETID
* in their user namespace and are privileged over the parent directory.
* In all other cases, strip the S_ISGID bit from @mode.
*
* Return: the new mode to use for the file
*/
umode_t mode_strip_sgid(struct mnt_idmap *idmap,
const struct inode *dir, umode_t mode)
{ if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP))
return mode;
if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID))
return mode;
if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir)))
return mode;
return mode & ~S_ISGID;
}
EXPORT_SYMBOL(mode_strip_sgid);
#ifdef CONFIG_DEBUG_VFS
/*
* Dump an inode.
*
* TODO: add a proper inode dumping routine, this is a stub to get debug off the
* ground.
*/
void dump_inode(struct inode *inode, const char *reason)
{
pr_warn("%s encountered for inode %px", reason, inode);
}
EXPORT_SYMBOL(dump_inode);
#endif
// SPDX-License-Identifier: GPL-2.0-only
/* Kernel thread helper functions.
* Copyright (C) 2004 IBM Corporation, Rusty Russell.
* Copyright (C) 2009 Red Hat, Inc.
*
* Creation is done via kthreadd, so that we get a clean environment
* even if we're invoked from userspace (think modprobe, hotplug cpu,
* etc.).
*/
#include <uapi/linux/sched/types.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <linux/numa.h>
#include <linux/sched/isolation.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
static LIST_HEAD(kthreads_hotplug);
static DEFINE_MUTEX(kthreads_hotplug_lock);
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
char *full_name;
int (*threadfn)(void *data);
void *data;
int node;
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
struct completion *done;
struct list_head list;
};
struct kthread {
unsigned long flags;
unsigned int cpu;
unsigned int node;
int started;
int result;
int (*threadfn)(void *);
void *data;
struct completion parked;
struct completion exited;
#ifdef CONFIG_BLK_CGROUP
struct cgroup_subsys_state *blkcg_css;
#endif
/* To store the full name if task comm is truncated. */
char *full_name;
struct task_struct *task;
struct list_head hotplug_node;
struct cpumask *preferred_affinity;
};
enum KTHREAD_BITS {
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
};
static inline struct kthread *to_kthread(struct task_struct *k)
{
WARN_ON(!(k->flags & PF_KTHREAD));
return k->worker_private;
}
/*
* Variant of to_kthread() that doesn't assume @p is a kthread.
*
* Per construction; when:
*
* (p->flags & PF_KTHREAD) && p->worker_private
*
* the task is both a kthread and struct kthread is persistent. However
* PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and
* begin_new_exec()).
*/
static inline struct kthread *__to_kthread(struct task_struct *p)
{
void *kthread = p->worker_private;
if (kthread && !(p->flags & PF_KTHREAD))
kthread = NULL;
return kthread;
}
void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
{
struct kthread *kthread = to_kthread(tsk);
if (!kthread || !kthread->full_name) {
strscpy(buf, tsk->comm, buf_size);
return;
}
strscpy_pad(buf, kthread->full_name, buf_size);
}
bool set_kthread_struct(struct task_struct *p)
{
struct kthread *kthread;
if (WARN_ON_ONCE(to_kthread(p)))
return false;
kthread = kzalloc(sizeof(*kthread), GFP_KERNEL);
if (!kthread)
return false;
init_completion(&kthread->exited);
init_completion(&kthread->parked);
INIT_LIST_HEAD(&kthread->hotplug_node);
p->vfork_done = &kthread->exited;
kthread->task = p;
kthread->node = tsk_fork_get_node(current);
p->worker_private = kthread;
return true;
}
void free_kthread_struct(struct task_struct *k)
{
struct kthread *kthread;
/*
* Can be NULL if kmalloc() in set_kthread_struct() failed.
*/
kthread = to_kthread(k);
if (!kthread)
return;
#ifdef CONFIG_BLK_CGROUP
WARN_ON_ONCE(kthread->blkcg_css);
#endif
k->worker_private = NULL;
kfree(kthread->full_name);
kfree(kthread);
}
/**
* kthread_should_stop - should this kthread return now?
*
* When someone calls kthread_stop() on your kthread, it will be woken
* and this will return true. You should then return, and your return
* value will be passed through to kthread_stop().
*/
bool kthread_should_stop(void)
{
return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
}
EXPORT_SYMBOL(kthread_should_stop);
static bool __kthread_should_park(struct task_struct *k)
{
return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags);
}
/**
* kthread_should_park - should this kthread park now?
*
* When someone calls kthread_park() on your kthread, it will be woken
* and this will return true. You should then do the necessary
* cleanup and call kthread_parkme()
*
* Similar to kthread_should_stop(), but this keeps the thread alive
* and in a park position. kthread_unpark() "restarts" the thread and
* calls the thread function again.
*/
bool kthread_should_park(void)
{
return __kthread_should_park(current);
}
EXPORT_SYMBOL_GPL(kthread_should_park);
bool kthread_should_stop_or_park(void)
{
struct kthread *kthread = __to_kthread(current);
if (!kthread)
return false;
return kthread->flags & (BIT(KTHREAD_SHOULD_STOP) | BIT(KTHREAD_SHOULD_PARK));
}
/**
* kthread_freezable_should_stop - should this freezable kthread return now?
* @was_frozen: optional out parameter, indicates whether %current was frozen
*
* kthread_should_stop() for freezable kthreads, which will enter
* refrigerator if necessary. This function is safe from kthread_stop() /
* freezer deadlock and freezable kthreads should use this function instead
* of calling try_to_freeze() directly.
*/
bool kthread_freezable_should_stop(bool *was_frozen)
{
bool frozen = false;
might_sleep();
if (unlikely(freezing(current)))
frozen = __refrigerator(true);
if (was_frozen)
*was_frozen = frozen;
return kthread_should_stop();
}
EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
/**
* kthread_func - return the function specified on kthread creation
* @task: kthread task in question
*
* Returns NULL if the task is not a kthread.
*/
void *kthread_func(struct task_struct *task)
{
struct kthread *kthread = __to_kthread(task);
if (kthread)
return kthread->threadfn;
return NULL;
}
EXPORT_SYMBOL_GPL(kthread_func);
/**
* kthread_data - return data value specified on kthread creation
* @task: kthread task in question
*
* Return the data value specified when kthread @task was created.
* The caller is responsible for ensuring the validity of @task when
* calling this function.
*/
void *kthread_data(struct task_struct *task)
{
return to_kthread(task)->data;
}
EXPORT_SYMBOL_GPL(kthread_data);
/**
* kthread_probe_data - speculative version of kthread_data()
* @task: possible kthread task in question
*
* @task could be a kthread task. Return the data value specified when it
* was created if accessible. If @task isn't a kthread task or its data is
* inaccessible for any reason, %NULL is returned. This function requires
* that @task itself is safe to dereference.
*/
void *kthread_probe_data(struct task_struct *task)
{
struct kthread *kthread = __to_kthread(task);
void *data = NULL;
if (kthread)
copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
return data;
}
static void __kthread_parkme(struct kthread *self)
{
for (;;) {
/*
* TASK_PARKED is a special state; we must serialize against
* possible pending wakeups to avoid store-store collisions on
* task->state.
*
* Such a collision might possibly result in the task state
* changin from TASK_PARKED and us failing the
* wait_task_inactive() in kthread_park().
*/
set_special_state(TASK_PARKED);
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
/*
* Thread is going to call schedule(), do not preempt it,
* or the caller of kthread_park() may spend more time in
* wait_task_inactive().
*/
preempt_disable();
complete(&self->parked);
schedule_preempt_disabled();
preempt_enable();
}
__set_current_state(TASK_RUNNING);
}
void kthread_parkme(void)
{
__kthread_parkme(to_kthread(current));
}
EXPORT_SYMBOL_GPL(kthread_parkme);
/**
* kthread_exit - Cause the current kthread return @result to kthread_stop().
* @result: The integer value to return to kthread_stop().
*
* While kthread_exit can be called directly, it exists so that
* functions which do some additional work in non-modular code such as
* module_put_and_kthread_exit can be implemented.
*
* Does not return.
*/
void __noreturn kthread_exit(long result)
{
struct kthread *kthread = to_kthread(current);
kthread->result = result;
if (!list_empty(&kthread->hotplug_node)) {
mutex_lock(&kthreads_hotplug_lock);
list_del(&kthread->hotplug_node);
mutex_unlock(&kthreads_hotplug_lock);
if (kthread->preferred_affinity) {
kfree(kthread->preferred_affinity);
kthread->preferred_affinity = NULL;
}
}
do_exit(0);
}
EXPORT_SYMBOL(kthread_exit);
/**
* kthread_complete_and_exit - Exit the current kthread.
* @comp: Completion to complete
* @code: The integer value to return to kthread_stop().
*
* If present, complete @comp and then return code to kthread_stop().
*
* A kernel thread whose module may be removed after the completion of
* @comp can use this function to exit safely.
*
* Does not return.
*/
void __noreturn kthread_complete_and_exit(struct completion *comp, long code)
{
if (comp)
complete(comp);
kthread_exit(code);
}
EXPORT_SYMBOL(kthread_complete_and_exit);
static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask)
{
const struct cpumask *pref;
if (kthread->preferred_affinity) {
pref = kthread->preferred_affinity;
} else {
if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE))
return;
pref = cpumask_of_node(kthread->node);
}
cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD));
if (cpumask_empty(cpumask))
cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_KTHREAD));
}
static void kthread_affine_node(void)
{
struct kthread *kthread = to_kthread(current);
cpumask_var_t affinity;
WARN_ON_ONCE(kthread_is_per_cpu(current));
if (kthread->node == NUMA_NO_NODE) {
housekeeping_affine(current, HK_TYPE_KTHREAD);
} else {
if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) {
WARN_ON_ONCE(1);
return;
}
mutex_lock(&kthreads_hotplug_lock);
WARN_ON_ONCE(!list_empty(&kthread->hotplug_node));
list_add_tail(&kthread->hotplug_node, &kthreads_hotplug);
/*
* The node cpumask is racy when read from kthread() but:
* - a racing CPU going down will either fail on the subsequent
* call to set_cpus_allowed_ptr() or be migrated to housekeepers
* afterwards by the scheduler.
* - a racing CPU going up will be handled by kthreads_online_cpu()
*/
kthread_fetch_affinity(kthread, affinity);
set_cpus_allowed_ptr(current, affinity);
mutex_unlock(&kthreads_hotplug_lock);
free_cpumask_var(affinity);
}
}
static int kthread(void *_create)
{
static const struct sched_param param = { .sched_priority = 0 };
/* Copy data: it's on kthread's stack */
struct kthread_create_info *create = _create;
int (*threadfn)(void *data) = create->threadfn;
void *data = create->data;
struct completion *done;
struct kthread *self;
int ret;
self = to_kthread(current);
/* Release the structure when caller killed by a fatal signal. */
done = xchg(&create->done, NULL);
if (!done) {
kfree(create->full_name);
kfree(create);
kthread_exit(-EINTR);
}
self->full_name = create->full_name;
self->threadfn = threadfn;
self->data = data;
/*
* The new thread inherited kthreadd's priority and CPU mask. Reset
* back to default in case they have been changed.
*/
sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m);
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
/*
* Thread is going to call schedule(), do not preempt it,
* or the creator may spend more time in wait_task_inactive().
*/
preempt_disable();
complete(done);
schedule_preempt_disabled();
preempt_enable();
self->started = 1;
if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity)
kthread_affine_node();
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
cgroup_kthread_ready();
__kthread_parkme(self);
ret = threadfn(data);
}
kthread_exit(ret);
}
/* called from kernel_clone() to get node information for about to be created task */
int tsk_fork_get_node(struct task_struct *tsk)
{
#ifdef CONFIG_NUMA
if (tsk == kthreadd_task)
return tsk->pref_node_fork;
#endif
return NUMA_NO_NODE;
}
static void create_kthread(struct kthread_create_info *create)
{
int pid;
#ifdef CONFIG_NUMA
current->pref_node_fork = create->node;
#endif
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, create->full_name,
CLONE_FS | CLONE_FILES | SIGCHLD);
if (pid < 0) {
/* Release the structure when caller killed by a fatal signal. */
struct completion *done = xchg(&create->done, NULL);
kfree(create->full_name);
if (!done) {
kfree(create);
return;
}
create->result = ERR_PTR(pid);
complete(done);
}
}
static __printf(4, 0)
struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
va_list args)
{
DECLARE_COMPLETION_ONSTACK(done);
struct task_struct *task;
struct kthread_create_info *create = kmalloc(sizeof(*create),
GFP_KERNEL);
if (!create)
return ERR_PTR(-ENOMEM);
create->threadfn = threadfn;
create->data = data;
create->node = node;
create->done = &done;
create->full_name = kvasprintf(GFP_KERNEL, namefmt, args);
if (!create->full_name) {
task = ERR_PTR(-ENOMEM);
goto free_create;
}
spin_lock(&kthread_create_lock);
list_add_tail(&create->list, &kthread_create_list);
spin_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
/*
* Wait for completion in killable state, for I might be chosen by
* the OOM killer while kthreadd is trying to allocate memory for
* new kernel thread.
*/
if (unlikely(wait_for_completion_killable(&done))) {
/*
* If I was killed by a fatal signal before kthreadd (or new
* kernel thread) calls complete(), leave the cleanup of this
* structure to that thread.
*/
if (xchg(&create->done, NULL))
return ERR_PTR(-EINTR);
/*
* kthreadd (or new kernel thread) will call complete()
* shortly.
*/
wait_for_completion(&done);
}
task = create->result;
free_create:
kfree(create);
return task;
}
/**
* kthread_create_on_node - create a kthread.
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @node: task and thread structures for the thread are allocated on this node
* @namefmt: printf-style name for the thread.
*
* Description: This helper function creates and names a kernel
* thread. The thread will be stopped: use wake_up_process() to start
* it. See also kthread_run(). The new thread has SCHED_NORMAL policy and
* is affine to all CPUs.
*
* If thread is going to be bound on a particular cpu, give its node
* in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE.
* When woken, the thread will run @threadfn() with @data as its
* argument. @threadfn() can either return directly if it is a
* standalone thread for which no one will call kthread_stop(), or
* return when 'kthread_should_stop()' is true (which means
* kthread_stop() has been called). The return value should be zero
* or a negative error number; it will be passed to kthread_stop().
*
* Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
...)
{
struct task_struct *task;
va_list args;
va_start(args, namefmt);
task = __kthread_create_on_node(threadfn, data, node, namefmt, args);
va_end(args);
return task;
}
EXPORT_SYMBOL(kthread_create_on_node);
static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, unsigned int state)
{
unsigned long flags;
if (!wait_task_inactive(p, state)) {
WARN_ON(1);
return;
}
/* It's safe because the task is inactive. */
raw_spin_lock_irqsave(&p->pi_lock, flags);
do_set_cpus_allowed(p, mask);
p->flags |= PF_NO_SETAFFINITY;
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int state)
{
__kthread_bind_mask(p, cpumask_of(cpu), state);
}
void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
{
struct kthread *kthread = to_kthread(p);
__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
WARN_ON_ONCE(kthread->started);
}
/**
* kthread_bind - bind a just-created kthread to a cpu.
* @p: thread created by kthread_create().
* @cpu: cpu (might not be online, must be possible) for @k to run on.
*
* Description: This function is equivalent to set_cpus_allowed(),
* except that @cpu doesn't need to be online, and the thread must be
* stopped (i.e., just returned from kthread_create()).
*/
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
struct kthread *kthread = to_kthread(p);
__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
WARN_ON_ONCE(kthread->started);
}
EXPORT_SYMBOL(kthread_bind);
/**
* kthread_create_on_cpu - Create a cpu bound kthread
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @cpu: The cpu on which the thread should be bound,
* @namefmt: printf-style name for the thread. Format is restricted
* to "name.*%u". Code fills in cpu number.
*
* Description: This helper function creates and names a kernel thread
*/
struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
void *data, unsigned int cpu,
const char *namefmt)
{
struct task_struct *p;
p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
cpu);
if (IS_ERR(p))
return p;
kthread_bind(p, cpu);
/* CPU hotplug need to bind once again when unparking the thread. */
to_kthread(p)->cpu = cpu;
return p;
}
EXPORT_SYMBOL(kthread_create_on_cpu);
void kthread_set_per_cpu(struct task_struct *k, int cpu)
{
struct kthread *kthread = to_kthread(k);
if (!kthread)
return;
WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY));
if (cpu < 0) {
clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
return;
}
kthread->cpu = cpu;
set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
}
bool kthread_is_per_cpu(struct task_struct *p)
{ struct kthread *kthread = __to_kthread(p);
if (!kthread)
return false;
return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
}
/**
* kthread_unpark - unpark a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return false, wakes it, and
* waits for it to return. If the thread is marked percpu then its
* bound to the cpu again.
*/
void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))
return;
/*
* Newly created kthread was parked when the CPU was offline.
* The binding was lost and we need to set it again.
*/
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
* __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
*/
wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
/**
* kthread_park - park a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return true, wakes it, and
* waits for it to return. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will park without
* calling threadfn().
*
* Returns 0 if the thread is parked, -ENOSYS if the thread exited.
* If called by the kthread itself just the park bit is set.
*/
int kthread_park(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
return -EBUSY;
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
/*
* Wait for __kthread_parkme() to complete(), this means we
* _will_ have TASK_PARKED and are about to call schedule().
*/
wait_for_completion(&kthread->parked);
/*
* Now wait for that schedule() to complete and the task to
* get scheduled out.
*/
WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
}
return 0;
}
EXPORT_SYMBOL_GPL(kthread_park);
/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
* waits for it to exit. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
* If threadfn() may call kthread_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.
*/
int kthread_stop(struct task_struct *k)
{
struct kthread *kthread;
int ret;
trace_sched_kthread_stop(k);
get_task_struct(k);
kthread = to_kthread(k);
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
kthread_unpark(k);
set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL);
wake_up_process(k);
wait_for_completion(&kthread->exited);
ret = kthread->result;
put_task_struct(k);
trace_sched_kthread_stop_ret(ret);
return ret;
}
EXPORT_SYMBOL(kthread_stop);
/**
* kthread_stop_put - stop a thread and put its task struct
* @k: thread created by kthread_create().
*
* Stops a thread created by kthread_create() and put its task_struct.
* Only use when holding an extra task struct reference obtained by
* calling get_task_struct().
*/
int kthread_stop_put(struct task_struct *k)
{
int ret;
ret = kthread_stop(k);
put_task_struct(k);
return ret;
}
EXPORT_SYMBOL(kthread_stop_put);
int kthreadd(void *unused)
{
static const char comm[TASK_COMM_LEN] = "kthreadd";
struct task_struct *tsk = current;
/* Setup a clean context for our children to inherit. */
set_task_comm(tsk, comm);
ignore_signals(tsk);
set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD));
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (list_empty(&kthread_create_list))
schedule();
__set_current_state(TASK_RUNNING);
spin_lock(&kthread_create_lock);
while (!list_empty(&kthread_create_list)) {
struct kthread_create_info *create;
create = list_entry(kthread_create_list.next,
struct kthread_create_info, list);
list_del_init(&create->list);
spin_unlock(&kthread_create_lock);
create_kthread(create);
spin_lock(&kthread_create_lock);
}
spin_unlock(&kthread_create_lock);
}
return 0;
}
int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
{
struct kthread *kthread = to_kthread(p);
cpumask_var_t affinity;
unsigned long flags;
int ret = 0;
if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) {
WARN_ON(1);
return -EINVAL;
}
WARN_ON_ONCE(kthread->preferred_affinity);
if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
return -ENOMEM;
kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL);
if (!kthread->preferred_affinity) {
ret = -ENOMEM;
goto out;
}
mutex_lock(&kthreads_hotplug_lock);
cpumask_copy(kthread->preferred_affinity, mask);
WARN_ON_ONCE(!list_empty(&kthread->hotplug_node));
list_add_tail(&kthread->hotplug_node, &kthreads_hotplug);
kthread_fetch_affinity(kthread, affinity);
/* It's safe because the task is inactive. */
raw_spin_lock_irqsave(&p->pi_lock, flags);
do_set_cpus_allowed(p, affinity);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
mutex_unlock(&kthreads_hotplug_lock);
out:
free_cpumask_var(affinity);
return ret;
}
/*
* Re-affine kthreads according to their preferences
* and the newly online CPU. The CPU down part is handled
* by select_fallback_rq() which default re-affines to
* housekeepers from other nodes in case the preferred
* affinity doesn't apply anymore.
*/
static int kthreads_online_cpu(unsigned int cpu)
{
cpumask_var_t affinity;
struct kthread *k;
int ret;
guard(mutex)(&kthreads_hotplug_lock);
if (list_empty(&kthreads_hotplug))
return 0;
if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
return -ENOMEM;
ret = 0;
list_for_each_entry(k, &kthreads_hotplug, hotplug_node) {
if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) ||
kthread_is_per_cpu(k->task))) {
ret = -EINVAL;
continue;
}
kthread_fetch_affinity(k, affinity);
set_cpus_allowed_ptr(k->task, affinity);
}
free_cpumask_var(affinity);
return ret;
}
static int kthreads_init(void)
{
return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online",
kthreads_online_cpu, NULL);
}
early_initcall(kthreads_init);
void __kthread_init_worker(struct kthread_worker *worker,
const char *name,
struct lock_class_key *key)
{
memset(worker, 0, sizeof(struct kthread_worker));
raw_spin_lock_init(&worker->lock);
lockdep_set_class_and_name(&worker->lock, key, name);
INIT_LIST_HEAD(&worker->work_list);
INIT_LIST_HEAD(&worker->delayed_work_list);
}
EXPORT_SYMBOL_GPL(__kthread_init_worker);
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
*
* This function implements the main cycle of kthread worker. It processes
* work_list until it is stopped with kthread_stop(). It sleeps when the queue
* is empty.
*
* The works are not allowed to keep any locks, disable preemption or interrupts
* when they finish. There is defined a safe point for freezing when one work
* finishes and before a new one is started.
*
* Also the works must not be handled by more than one worker at the same time,
* see also kthread_queue_work().
*/
int kthread_worker_fn(void *worker_ptr)
{
struct kthread_worker *worker = worker_ptr;
struct kthread_work *work;
/*
* FIXME: Update the check and remove the assignment when all kthread
* worker users are created using kthread_create_worker*() functions.
*/
WARN_ON(worker->task && worker->task != current);
worker->task = current;
if (worker->flags & KTW_FREEZABLE)
set_freezable();
repeat:
set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
raw_spin_lock_irq(&worker->lock);
worker->task = NULL;
raw_spin_unlock_irq(&worker->lock);
return 0;
}
work = NULL;
raw_spin_lock_irq(&worker->lock);
if (!list_empty(&worker->work_list)) {
work = list_first_entry(&worker->work_list,
struct kthread_work, node);
list_del_init(&work->node);
}
worker->current_work = work;
raw_spin_unlock_irq(&worker->lock);
if (work) {
kthread_work_func_t func = work->func;
__set_current_state(TASK_RUNNING);
trace_sched_kthread_work_execute_start(work);
work->func(work);
/*
* Avoid dereferencing work after this point. The trace
* event only cares about the address.
*/
trace_sched_kthread_work_execute_end(work, func);
} else if (!freezing(current)) {
schedule();
} else {
/*
* Handle the case where the current remains
* TASK_INTERRUPTIBLE. try_to_freeze() expects
* the current to be TASK_RUNNING.
*/
__set_current_state(TASK_RUNNING);
}
try_to_freeze();
cond_resched();
goto repeat;
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
static __printf(3, 0) struct kthread_worker *
__kthread_create_worker_on_node(unsigned int flags, int node,
const char namefmt[], va_list args)
{
struct kthread_worker *worker;
struct task_struct *task;
worker = kzalloc(sizeof(*worker), GFP_KERNEL);
if (!worker)
return ERR_PTR(-ENOMEM);
kthread_init_worker(worker);
task = __kthread_create_on_node(kthread_worker_fn, worker,
node, namefmt, args);
if (IS_ERR(task))
goto fail_task;
worker->flags = flags;
worker->task = task;
return worker;
fail_task:
kfree(worker);
return ERR_CAST(task);
}
/**
* kthread_create_worker_on_node - create a kthread worker
* @flags: flags modifying the default behavior of the worker
* @node: task structure for the thread is allocated on this node
* @namefmt: printf-style name for the kthread worker (task).
*
* Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
* when the needed structures could not get allocated, and ERR_PTR(-EINTR)
* when the caller was killed by a fatal signal.
*/
struct kthread_worker *
kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...)
{
struct kthread_worker *worker;
va_list args;
va_start(args, namefmt);
worker = __kthread_create_worker_on_node(flags, node, namefmt, args);
va_end(args);
return worker;
}
EXPORT_SYMBOL(kthread_create_worker_on_node);
/**
* kthread_create_worker_on_cpu - create a kthread worker and bind it
* to a given CPU and the associated NUMA node.
* @cpu: CPU number
* @flags: flags modifying the default behavior of the worker
* @namefmt: printf-style name for the thread. Format is restricted
* to "name.*%u". Code fills in cpu number.
*
* Use a valid CPU number if you want to bind the kthread worker
* to the given CPU and the associated NUMA node.
*
* A good practice is to add the cpu number also into the worker name.
* For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu).
*
* CPU hotplug:
* The kthread worker API is simple and generic. It just provides a way
* to create, use, and destroy workers.
*
* It is up to the API user how to handle CPU hotplug. They have to decide
* how to handle pending work items, prevent queuing new ones, and
* restore the functionality when the CPU goes off and on. There are a
* few catches:
*
* - CPU affinity gets lost when it is scheduled on an offline CPU.
*
* - The worker might not exist when the CPU was off when the user
* created the workers.
*
* Good practice is to implement two CPU hotplug callbacks and to
* destroy/create the worker when the CPU goes down/up.
*
* Return:
* The pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
* when the needed structures could not get allocated, and ERR_PTR(-EINTR)
* when the caller was killed by a fatal signal.
*/
struct kthread_worker *
kthread_create_worker_on_cpu(int cpu, unsigned int flags,
const char namefmt[])
{
struct kthread_worker *worker;
worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu);
if (!IS_ERR(worker))
kthread_bind(worker->task, cpu);
return worker;
}
EXPORT_SYMBOL(kthread_create_worker_on_cpu);
/*
* Returns true when the work could not be queued at the moment.
* It happens when it is already pending in a worker list
* or when it is being cancelled.
*/
static inline bool queuing_blocked(struct kthread_worker *worker,
struct kthread_work *work)
{
lockdep_assert_held(&worker->lock);
return !list_empty(&work->node) || work->canceling;
}
static void kthread_insert_work_sanity_check(struct kthread_worker *worker,
struct kthread_work *work)
{
lockdep_assert_held(&worker->lock);
WARN_ON_ONCE(!list_empty(&work->node));
/* Do not use a work with >1 worker, see kthread_queue_work() */
WARN_ON_ONCE(work->worker && work->worker != worker);
}
/* insert @work before @pos in @worker */
static void kthread_insert_work(struct kthread_worker *worker,
struct kthread_work *work,
struct list_head *pos)
{
kthread_insert_work_sanity_check(worker, work);
trace_sched_kthread_work_queue_work(worker, work);
list_add_tail(&work->node, pos);
work->worker = worker;
if (!worker->current_work && likely(worker->task))
wake_up_process(worker->task);
}
/**
* kthread_queue_work - queue a kthread_work
* @worker: target kthread_worker
* @work: kthread_work to queue
*
* Queue @work to work processor @task for async execution. @task
* must have been created with kthread_create_worker(). Returns %true
* if @work was successfully queued, %false if it was already pending.
*
* Reinitialize the work if it needs to be used by another worker.
* For example, when the worker was stopped and started again.
*/
bool kthread_queue_work(struct kthread_worker *worker,
struct kthread_work *work)
{
bool ret = false;
unsigned long flags;
raw_spin_lock_irqsave(&worker->lock, flags);
if (!queuing_blocked(worker, work)) {
kthread_insert_work(worker, work, &worker->work_list);
ret = true;
}
raw_spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_queue_work);
/**
* kthread_delayed_work_timer_fn - callback that queues the associated kthread
* delayed work when the timer expires.
* @t: pointer to the expired timer
*
* The format of the function is defined by struct timer_list.
* It should have been called from irqsafe timer with irq already off.
*/
void kthread_delayed_work_timer_fn(struct timer_list *t)
{
struct kthread_delayed_work *dwork = from_timer(dwork, t, timer);
struct kthread_work *work = &dwork->work;
struct kthread_worker *worker = work->worker;
unsigned long flags;
/*
* This might happen when a pending work is reinitialized.
* It means that it is used a wrong way.
*/
if (WARN_ON_ONCE(!worker))
return;
raw_spin_lock_irqsave(&worker->lock, flags);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
/* Move the work from worker->delayed_work_list. */
WARN_ON_ONCE(list_empty(&work->node));
list_del_init(&work->node);
if (!work->canceling)
kthread_insert_work(worker, work, &worker->work_list);
raw_spin_unlock_irqrestore(&worker->lock, flags);
}
EXPORT_SYMBOL(kthread_delayed_work_timer_fn);
static void __kthread_queue_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct timer_list *timer = &dwork->timer;
struct kthread_work *work = &dwork->work;
WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn);
/*
* If @delay is 0, queue @dwork->work immediately. This is for
* both optimization and correctness. The earliest @timer can
* expire is on the closest next tick and delayed_work users depend
* on that there's no such delay when @delay is 0.
*/
if (!delay) {
kthread_insert_work(worker, work, &worker->work_list);
return;
}
/* Be paranoid and try to detect possible races already now. */
kthread_insert_work_sanity_check(worker, work);
list_add(&work->node, &worker->delayed_work_list);
work->worker = worker;
timer->expires = jiffies + delay;
add_timer(timer);
}
/**
* kthread_queue_delayed_work - queue the associated kthread work
* after a delay.
* @worker: target kthread_worker
* @dwork: kthread_delayed_work to queue
* @delay: number of jiffies to wait before queuing
*
* If the work has not been pending it starts a timer that will queue
* the work after the given @delay. If @delay is zero, it queues the
* work immediately.
*
* Return: %false if the @work has already been pending. It means that
* either the timer was running or the work was queued. It returns %true
* otherwise.
*/
bool kthread_queue_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct kthread_work *work = &dwork->work;
unsigned long flags;
bool ret = false;
raw_spin_lock_irqsave(&worker->lock, flags);
if (!queuing_blocked(worker, work)) {
__kthread_queue_delayed_work(worker, dwork, delay);
ret = true;
}
raw_spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_queue_delayed_work);
struct kthread_flush_work {
struct kthread_work work;
struct completion done;
};
static void kthread_flush_work_fn(struct kthread_work *work)
{
struct kthread_flush_work *fwork =
container_of(work, struct kthread_flush_work, work);
complete(&fwork->done);
}
/**
* kthread_flush_work - flush a kthread_work
* @work: work to flush
*
* If @work is queued or executing, wait for it to finish execution.
*/
void kthread_flush_work(struct kthread_work *work)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
struct kthread_worker *worker;
bool noop = false;
worker = work->worker;
if (!worker)
return;
raw_spin_lock_irq(&worker->lock);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
if (!list_empty(&work->node))
kthread_insert_work(worker, &fwork.work, work->node.next);
else if (worker->current_work == work)
kthread_insert_work(worker, &fwork.work,
worker->work_list.next);
else
noop = true;
raw_spin_unlock_irq(&worker->lock);
if (!noop)
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(kthread_flush_work);
/*
* Make sure that the timer is neither set nor running and could
* not manipulate the work list_head any longer.
*
* The function is called under worker->lock. The lock is temporary
* released but the timer can't be set again in the meantime.
*/
static void kthread_cancel_delayed_work_timer(struct kthread_work *work,
unsigned long *flags)
{
struct kthread_delayed_work *dwork =
container_of(work, struct kthread_delayed_work, work);
struct kthread_worker *worker = work->worker;
/*
* timer_delete_sync() must be called to make sure that the timer
* callback is not running. The lock must be temporary released
* to avoid a deadlock with the callback. In the meantime,
* any queuing is blocked by setting the canceling counter.
*/
work->canceling++;
raw_spin_unlock_irqrestore(&worker->lock, *flags);
timer_delete_sync(&dwork->timer);
raw_spin_lock_irqsave(&worker->lock, *flags);
work->canceling--;
}
/*
* This function removes the work from the worker queue.
*
* It is called under worker->lock. The caller must make sure that
* the timer used by delayed work is not running, e.g. by calling
* kthread_cancel_delayed_work_timer().
*
* The work might still be in use when this function finishes. See the
* current_work proceed by the worker.
*
* Return: %true if @work was pending and successfully canceled,
* %false if @work was not pending
*/
static bool __kthread_cancel_work(struct kthread_work *work)
{
/*
* Try to remove the work from a worker list. It might either
* be from worker->work_list or from worker->delayed_work_list.
*/
if (!list_empty(&work->node)) {
list_del_init(&work->node);
return true;
}
return false;
}
/**
* kthread_mod_delayed_work - modify delay of or queue a kthread delayed work
* @worker: kthread worker to use
* @dwork: kthread delayed work to queue
* @delay: number of jiffies to wait before queuing
*
* If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise,
* modify @dwork's timer so that it expires after @delay. If @delay is zero,
* @work is guaranteed to be queued immediately.
*
* Return: %false if @dwork was idle and queued, %true otherwise.
*
* A special case is when the work is being canceled in parallel.
* It might be caused either by the real kthread_cancel_delayed_work_sync()
* or yet another kthread_mod_delayed_work() call. We let the other command
* win and return %true here. The return value can be used for reference
* counting and the number of queued works stays the same. Anyway, the caller
* is supposed to synchronize these operations a reasonable way.
*
* This function is safe to call from any context including IRQ handler.
* See __kthread_cancel_work() and kthread_delayed_work_timer_fn()
* for details.
*/
bool kthread_mod_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct kthread_work *work = &dwork->work;
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&worker->lock, flags);
/* Do not bother with canceling when never queued. */
if (!work->worker) {
ret = false;
goto fast_queue;
}
/* Work must not be used with >1 worker, see kthread_queue_work() */
WARN_ON_ONCE(work->worker != worker);
/*
* Temporary cancel the work but do not fight with another command
* that is canceling the work as well.
*
* It is a bit tricky because of possible races with another
* mod_delayed_work() and cancel_delayed_work() callers.
*
* The timer must be canceled first because worker->lock is released
* when doing so. But the work can be removed from the queue (list)
* only when it can be queued again so that the return value can
* be used for reference counting.
*/
kthread_cancel_delayed_work_timer(work, &flags);
if (work->canceling) {
/* The number of works in the queue does not change. */
ret = true;
goto out;
}
ret = __kthread_cancel_work(work);
fast_queue:
__kthread_queue_delayed_work(worker, dwork, delay);
out:
raw_spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_mod_delayed_work);
static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork)
{
struct kthread_worker *worker = work->worker;
unsigned long flags;
int ret = false;
if (!worker)
goto out;
raw_spin_lock_irqsave(&worker->lock, flags);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
if (is_dwork)
kthread_cancel_delayed_work_timer(work, &flags);
ret = __kthread_cancel_work(work);
if (worker->current_work != work)
goto out_fast;
/*
* The work is in progress and we need to wait with the lock released.
* In the meantime, block any queuing by setting the canceling counter.
*/
work->canceling++;
raw_spin_unlock_irqrestore(&worker->lock, flags);
kthread_flush_work(work);
raw_spin_lock_irqsave(&worker->lock, flags);
work->canceling--;
out_fast:
raw_spin_unlock_irqrestore(&worker->lock, flags);
out:
return ret;
}
/**
* kthread_cancel_work_sync - cancel a kthread work and wait for it to finish
* @work: the kthread work to cancel
*
* Cancel @work and wait for its execution to finish. This function
* can be used even if the work re-queues itself. On return from this
* function, @work is guaranteed to be not pending or executing on any CPU.
*
* kthread_cancel_work_sync(&delayed_work->work) must not be used for
* delayed_work's. Use kthread_cancel_delayed_work_sync() instead.
*
* The caller must ensure that the worker on which @work was last
* queued can't be destroyed before this function returns.
*
* Return: %true if @work was pending, %false otherwise.
*/
bool kthread_cancel_work_sync(struct kthread_work *work)
{
return __kthread_cancel_work_sync(work, false);
}
EXPORT_SYMBOL_GPL(kthread_cancel_work_sync);
/**
* kthread_cancel_delayed_work_sync - cancel a kthread delayed work and
* wait for it to finish.
* @dwork: the kthread delayed work to cancel
*
* This is kthread_cancel_work_sync() for delayed works.
*
* Return: %true if @dwork was pending, %false otherwise.
*/
bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork)
{
return __kthread_cancel_work_sync(&dwork->work, true);
}
EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync);
/**
* kthread_flush_worker - flush all current works on a kthread_worker
* @worker: worker to flush
*
* Wait until all currently executing or pending works on @worker are
* finished.
*/
void kthread_flush_worker(struct kthread_worker *worker)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
kthread_queue_work(worker, &fwork.work);
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(kthread_flush_worker);
/**
* kthread_destroy_worker - destroy a kthread worker
* @worker: worker to be destroyed
*
* Flush and destroy @worker. The simple flush is enough because the kthread
* worker API is used only in trivial scenarios. There are no multi-step state
* machines needed.
*
* Note that this function is not responsible for handling delayed work, so
* caller should be responsible for queuing or canceling all delayed work items
* before invoke this function.
*/
void kthread_destroy_worker(struct kthread_worker *worker)
{
struct task_struct *task;
task = worker->task;
if (WARN_ON(!task))
return;
kthread_flush_worker(worker);
kthread_stop(task);
WARN_ON(!list_empty(&worker->delayed_work_list));
WARN_ON(!list_empty(&worker->work_list));
kfree(worker);
}
EXPORT_SYMBOL(kthread_destroy_worker);
/**
* kthread_use_mm - make the calling kthread operate on an address space
* @mm: address space to operate on
*/
void kthread_use_mm(struct mm_struct *mm)
{
struct mm_struct *active_mm;
struct task_struct *tsk = current;
WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
WARN_ON_ONCE(tsk->mm);
/*
* It is possible for mm to be the same as tsk->active_mm, but
* we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm),
* because these references are not equivalent.
*/
mmgrab(mm);
task_lock(tsk);
/* Hold off tlb flush IPIs while switching mm's */
local_irq_disable();
active_mm = tsk->active_mm;
tsk->active_mm = mm;
tsk->mm = mm;
membarrier_update_current_mm(mm);
switch_mm_irqs_off(active_mm, mm, tsk);
local_irq_enable();
task_unlock(tsk);
#ifdef finish_arch_post_lock_switch
finish_arch_post_lock_switch();
#endif
/*
* When a kthread starts operating on an address space, the loop
* in membarrier_{private,global}_expedited() may not observe
* that tsk->mm, and not issue an IPI. Membarrier requires a
* memory barrier after storing to tsk->mm, before accessing
* user-space memory. A full memory barrier for membarrier
* {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by
* mmdrop_lazy_tlb().
*/
mmdrop_lazy_tlb(active_mm);
}
EXPORT_SYMBOL_GPL(kthread_use_mm);
/**
* kthread_unuse_mm - reverse the effect of kthread_use_mm()
* @mm: address space to operate on
*/
void kthread_unuse_mm(struct mm_struct *mm)
{
struct task_struct *tsk = current;
WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
WARN_ON_ONCE(!tsk->mm);
task_lock(tsk);
/*
* When a kthread stops operating on an address space, the loop
* in membarrier_{private,global}_expedited() may not observe
* that tsk->mm, and not issue an IPI. Membarrier requires a
* memory barrier after accessing user-space memory, before
* clearing tsk->mm.
*/
smp_mb__after_spinlock();
local_irq_disable();
tsk->mm = NULL;
membarrier_update_current_mm(NULL);
mmgrab_lazy_tlb(mm);
/* active_mm is still 'mm' */
enter_lazy_tlb(mm, tsk);
local_irq_enable();
task_unlock(tsk);
mmdrop(mm);
}
EXPORT_SYMBOL_GPL(kthread_unuse_mm);
#ifdef CONFIG_BLK_CGROUP
/**
* kthread_associate_blkcg - associate blkcg to current kthread
* @css: the cgroup info
*
* Current thread must be a kthread. The thread is running jobs on behalf of
* other threads. In some cases, we expect the jobs attach cgroup info of
* original threads instead of that of current thread. This function stores
* original thread's cgroup info in current kthread context for later
* retrieval.
*/
void kthread_associate_blkcg(struct cgroup_subsys_state *css)
{
struct kthread *kthread;
if (!(current->flags & PF_KTHREAD))
return;
kthread = to_kthread(current);
if (!kthread)
return;
if (kthread->blkcg_css) {
css_put(kthread->blkcg_css);
kthread->blkcg_css = NULL;
}
if (css) {
css_get(css);
kthread->blkcg_css = css;
}
}
EXPORT_SYMBOL(kthread_associate_blkcg);
/**
* kthread_blkcg - get associated blkcg css of current kthread
*
* Current thread must be a kthread.
*/
struct cgroup_subsys_state *kthread_blkcg(void)
{
struct kthread *kthread;
if (current->flags & PF_KTHREAD) {
kthread = to_kthread(current);
if (kthread) return kthread->blkcg_css;
}
return NULL;
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* A generic implementation of binary search for the Linux kernel
*
* Copyright (C) 2008-2009 Ksplice, Inc.
* Author: Tim Abbott <tabbott@ksplice.com>
*/
#include <linux/export.h>
#include <linux/bsearch.h>
#include <linux/kprobes.h>
/*
* bsearch - binary search an array of elements
* @key: pointer to item being searched for
* @base: pointer to first element to search
* @num: number of elements
* @size: size of each element
* @cmp: pointer to comparison function
*
* This function does a binary search on the given array. The
* contents of the array should already be in ascending sorted order
* under the provided comparison function.
*
* Note that the key need not have the same type as the elements in
* the array, e.g. key could be a string and the comparison function
* could compare the string with the struct's name field. However, if
* the key and elements in the array are of the same type, you can use
* the same comparison function for both sort() and bsearch().
*/
void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp)
{ return __inline_bsearch(key, base, num, size, cmp);
}
EXPORT_SYMBOL(bsearch);
NOKPROBE_SYMBOL(bsearch);
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/traps.h
*
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_TRAP_H
#define __ASM_TRAP_H
#include <linux/list.h>
#include <asm/esr.h>
#include <asm/ptrace.h>
#include <asm/sections.h>
#ifdef CONFIG_ARMV8_DEPRECATED
bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn);
#else
static inline bool
try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
{
return false;
}
#endif /* CONFIG_ARMV8_DEPRECATED */
void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
void arm64_notify_segfault(unsigned long addr);
void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);
void arm64_force_sig_fault_pkey(unsigned long far, const char *str, int pkey);
void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str);
void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str);
int early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs);
/*
* Move regs->pc to next instruction and do necessary setup before it
* is executed.
*/
void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size);
static inline int __in_irqentry_text(unsigned long ptr)
{
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
static inline int in_entry_text(unsigned long ptr)
{
return ptr >= (unsigned long)&__entry_text_start &&
ptr < (unsigned long)&__entry_text_end;
}
/*
* CPUs with the RAS extensions have an Implementation-Defined-Syndrome bit
* to indicate whether this ESR has a RAS encoding. CPUs without this feature
* have a ISS-Valid bit in the same position.
* If this bit is set, we know its not a RAS SError.
* If its clear, we need to know if the CPU supports RAS. Uncategorized RAS
* errors share the same encoding as an all-zeros encoding from a CPU that
* doesn't support RAS.
*/
static inline bool arm64_is_ras_serror(unsigned long esr)
{
WARN_ON(preemptible()); if (esr & ESR_ELx_IDS)
return false;
if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN))
return true;
else
return false;
}
/*
* Return the AET bits from a RAS SError's ESR.
*
* It is implementation defined whether Uncategorized errors are containable.
* We treat them as Uncontainable.
* Non-RAS SError's are reported as Uncontained/Uncategorized.
*/
static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr)
{
unsigned long aet = esr & ESR_ELx_AET;
if (!arm64_is_ras_serror(esr)) {
/* Not a RAS error, we can't interpret the ESR. */
return ESR_ELx_AET_UC;
}
/*
* AET is RES0 if 'the value returned in the DFSC field is not
* [ESR_ELx_FSC_SERROR]'
*/
if ((esr & ESR_ELx_FSC) != ESR_ELx_FSC_SERROR) {
/* No severity information : Uncategorized */
return ESR_ELx_AET_UC;
}
return aet;
}
bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr);
void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr);
static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned long esr)
{
bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION;
bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A;
int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr);
int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr);
int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr);
unsigned long dst, size;
dst = regs->regs[dstreg];
size = regs->regs[sizereg];
/*
* Put the registers back in the original format suitable for a
* prologue instruction, using the generic return routine from the
* Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH.
*/
if (esr & ESR_ELx_MOPS_ISS_MEM_INST) {
/* SET* instruction */
if (option_a ^ wrong_option) {
/* Format is from Option A; forward set */
regs->regs[dstreg] = dst + size;
regs->regs[sizereg] = -size;
}
} else {
/* CPY* instruction */
unsigned long src = regs->regs[srcreg];
if (!(option_a ^ wrong_option)) {
/* Format is from Option B */
if (regs->pstate & PSR_N_BIT) {
/* Backward copy */
regs->regs[dstreg] = dst - size;
regs->regs[srcreg] = src - size;
}
} else {
/* Format is from Option A */
if (size & BIT(63)) {
/* Forward copy */
regs->regs[dstreg] = dst + size;
regs->regs[srcreg] = src + size;
regs->regs[sizereg] = -size;
}
}
}
if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE)
regs->pc -= 8;
else
regs->pc -= 4;
}
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H
#ifndef __ASSEMBLY__
#ifndef __GENERATING_BOUNDS_H
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/list_nulls.h>
#include <linux/wait.h>
#include <linux/bitops.h>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/numa.h>
#include <linux/init.h>
#include <linux/seqlock.h>
#include <linux/nodemask.h>
#include <linux/pageblock-flags.h>
#include <linux/page-flags-layout.h>
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <linux/local_lock.h>
#include <linux/zswap.h>
#include <asm/page.h>
/* Free memory management - zoned buddy allocator. */
#ifndef CONFIG_ARCH_FORCE_MAX_ORDER
#define MAX_PAGE_ORDER 10
#else
#define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
#endif
#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES)
#define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
/*
* PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
* costly to service. That is between allocation orders which should
* coalesce naturally under reasonable reclaim pressure and those which
* will not.
*/
#define PAGE_ALLOC_COSTLY_ORDER 3
enum migratetype {
MIGRATE_UNMOVABLE,
MIGRATE_MOVABLE,
MIGRATE_RECLAIMABLE,
MIGRATE_PCPTYPES, /* the number of types on the pcp lists */
MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
/*
* MIGRATE_CMA migration type is designed to mimic the way
* ZONE_MOVABLE works. Only movable pages can be allocated
* from MIGRATE_CMA pageblocks and page allocator never
* implicitly change migration type of MIGRATE_CMA pageblock.
*
* The way to use it is to change migratetype of a range of
* pageblocks to MIGRATE_CMA which can be done by
* __free_pageblock_cma() function.
*/
MIGRATE_CMA,
#endif
#ifdef CONFIG_MEMORY_ISOLATION
MIGRATE_ISOLATE, /* can't allocate from here */
#endif
MIGRATE_TYPES
};
/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */
extern const char * const migratetype_names[MIGRATE_TYPES];
#ifdef CONFIG_CMA
# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
# define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \
get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK))
#else
# define is_migrate_cma(migratetype) false
# define is_migrate_cma_page(_page) false
# define is_migrate_cma_folio(folio, pfn) false
#endif
static inline bool is_migrate_movable(int mt)
{
return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE;
}
/*
* Check whether a migratetype can be merged with another migratetype.
*
* It is only mergeable when it can fall back to other migratetypes for
* allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c.
*/
static inline bool migratetype_is_mergeable(int mt)
{
return mt < MIGRATE_PCPTYPES;
}
#define for_each_migratetype_order(order, type) \
for (order = 0; order < NR_PAGE_ORDERS; order++) \
for (type = 0; type < MIGRATE_TYPES; type++)
extern int page_group_by_mobility_disabled;
#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
#define get_pageblock_migratetype(page) \
get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
#define folio_migratetype(folio) \
get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \
MIGRATETYPE_MASK)
struct free_area {
struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
struct pglist_data;
#ifdef CONFIG_NUMA
enum numa_stat_item {
NUMA_HIT, /* allocated in intended node */
NUMA_MISS, /* allocated in non intended node */
NUMA_FOREIGN, /* was intended here, hit elsewhere */
NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */
NUMA_LOCAL, /* allocation from local node */
NUMA_OTHER, /* allocation from other node */
NR_VM_NUMA_EVENT_ITEMS
};
#else
#define NR_VM_NUMA_EVENT_ITEMS 0
#endif
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
NR_FREE_PAGES_BLOCKS,
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_ACTIVE_ANON,
NR_ZONE_INACTIVE_FILE,
NR_ZONE_ACTIVE_FILE,
NR_ZONE_UNEVICTABLE,
NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
/* Second 128 byte cacheline */
NR_BOUNCE,
#if IS_ENABLED(CONFIG_ZSMALLOC)
NR_ZSPAGES, /* allocated in zsmalloc */
#endif
NR_FREE_CMA_PAGES,
#ifdef CONFIG_UNACCEPTED_MEMORY
NR_UNACCEPTED,
#endif
NR_VM_ZONE_STAT_ITEMS };
enum node_stat_item {
NR_LRU_BASE,
NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
NR_ACTIVE_ANON, /* " " " " " */
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
NR_SLAB_RECLAIMABLE_B,
NR_SLAB_UNRECLAIMABLE_B,
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
WORKINGSET_NODES,
WORKINGSET_REFAULT_BASE,
WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE,
WORKINGSET_REFAULT_FILE,
WORKINGSET_ACTIVATE_BASE,
WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE,
WORKINGSET_ACTIVATE_FILE,
WORKINGSET_RESTORE_BASE,
WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE,
WORKINGSET_RESTORE_FILE,
WORKINGSET_NODERECLAIM,
NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_SHMEM_THPS,
NR_SHMEM_PMDMAPPED,
NR_FILE_THPS,
NR_FILE_PMDMAPPED,
NR_ANON_THPS,
NR_VMSCAN_WRITE,
NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */
NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */
NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */
NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */
NR_KERNEL_STACK_KB, /* measured in KiB */
#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
NR_KERNEL_SCS_KB, /* measured in KiB */
#endif
NR_PAGETABLE, /* used for pagetables */
NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */
#ifdef CONFIG_IOMMU_SUPPORT
NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */
#endif
#ifdef CONFIG_SWAP
NR_SWAPCACHE,
#endif
#ifdef CONFIG_NUMA_BALANCING
PGPROMOTE_SUCCESS, /* promote successfully */
PGPROMOTE_CANDIDATE, /* candidate pages to promote */
#endif
/* PGDEMOTE_*: pages demoted */
PGDEMOTE_KSWAPD,
PGDEMOTE_DIRECT,
PGDEMOTE_KHUGEPAGED,
PGDEMOTE_PROACTIVE,
#ifdef CONFIG_HUGETLB_PAGE
NR_HUGETLB,
#endif
NR_BALLOON_PAGES,
NR_VM_NODE_STAT_ITEMS
};
/*
* Returns true if the item should be printed in THPs (/proc/vmstat
* currently prints number of anon, file and shmem THPs. But the item
* is charged in pages).
*/
static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item)
{
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return false;
return item == NR_ANON_THPS ||
item == NR_FILE_THPS ||
item == NR_SHMEM_THPS ||
item == NR_SHMEM_PMDMAPPED ||
item == NR_FILE_PMDMAPPED;
}
/*
* Returns true if the value is measured in bytes (most vmstat values are
* measured in pages). This defines the API part, the internal representation
* might be different.
*/
static __always_inline bool vmstat_item_in_bytes(int idx)
{
/*
* Global and per-node slab counters track slab pages.
* It's expected that changes are multiples of PAGE_SIZE.
* Internally values are stored in pages.
*
* Per-memcg and per-lruvec counters track memory, consumed
* by individual slab objects. These counters are actually
* byte-precise.
*/
return (idx == NR_SLAB_RECLAIMABLE_B ||
idx == NR_SLAB_UNRECLAIMABLE_B);
}
/*
* We do arithmetic on the LRU lists in various places in the code,
* so it is important to keep the active lists LRU_ACTIVE higher in
* the array than the corresponding inactive lists, and to keep
* the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
*
* This has to be kept in sync with the statistics in zone_stat_item
* above and the descriptions in vmstat_text in mm/vmstat.c
*/
#define LRU_BASE 0
#define LRU_ACTIVE 1
#define LRU_FILE 2
enum lru_list {
LRU_INACTIVE_ANON = LRU_BASE,
LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
LRU_UNEVICTABLE,
NR_LRU_LISTS
};
enum vmscan_throttle_state {
VMSCAN_THROTTLE_WRITEBACK,
VMSCAN_THROTTLE_ISOLATED,
VMSCAN_THROTTLE_NOPROGRESS,
VMSCAN_THROTTLE_CONGESTED,
NR_VMSCAN_THROTTLE,
};
#define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++)
#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
static inline bool is_file_lru(enum lru_list lru)
{
return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE);
}
static inline bool is_active_lru(enum lru_list lru)
{
return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}
#define WORKINGSET_ANON 0
#define WORKINGSET_FILE 1
#define ANON_AND_FILE 2
enum lruvec_flags {
/*
* An lruvec has many dirty pages backed by a congested BDI:
* 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim.
* It can be cleared by cgroup reclaim or kswapd.
* 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim.
* It can only be cleared by kswapd.
*
* Essentially, kswapd can unthrottle an lruvec throttled by cgroup
* reclaim, but not vice versa. This only applies to the root cgroup.
* The goal is to prevent cgroup reclaim on the root cgroup (e.g.
* memory.reclaim) to unthrottle an unbalanced node (that was throttled
* by kswapd).
*/
LRUVEC_CGROUP_CONGESTED,
LRUVEC_NODE_CONGESTED,
};
#endif /* !__GENERATING_BOUNDS_H */
/*
* Evictable folios are divided into multiple generations. The youngest and the
* oldest generation numbers, max_seq and min_seq, are monotonically increasing.
* They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
* offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
* corresponding generation. The gen counter in folio->flags stores gen+1 while
* a folio is on one of lrugen->folios[]. Otherwise it stores 0.
*
* After a folio is faulted in, the aging needs to check the accessed bit at
* least twice before handing this folio over to the eviction. The first check
* clears the accessed bit from the initial fault; the second check makes sure
* this folio hasn't been used since then. This process, AKA second chance,
* requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI
* compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two
* generations are considered active; the rest of generations, if they exist,
* are considered inactive. See lru_gen_is_active().
*
* PG_active is always cleared while a folio is on one of lrugen->folios[] so
* that the sliding window needs not to worry about it. And it's set again when
* a folio considered active is isolated for non-reclaiming purposes, e.g.,
* migration. See lru_gen_add_folio() and lru_gen_del_folio().
*
* MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the
* number of categories of the active/inactive LRU when keeping track of
* accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits
* in folio->flags, masked by LRU_GEN_MASK.
*/
#define MIN_NR_GENS 2U
#define MAX_NR_GENS 4U
/*
* Each generation is divided into multiple tiers. A folio accessed N times
* through file descriptors is in tier order_base_2(N). A folio in the first
* tier (N=0,1) is marked by PG_referenced unless it was faulted in through page
* tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by
* PG_workingset. A folio in any other tier (1<N<5) between the first and last
* is marked by additional bits of LRU_REFS_WIDTH in folio->flags.
*
* In contrast to moving across generations which requires the LRU lock, moving
* across tiers only involves atomic operations on folio->flags and therefore
* has a negligible cost in the buffered access path. In the eviction path,
* comparisons of refaulted/(evicted+protected) from the first tier and the rest
* infer whether folios accessed multiple times through file descriptors are
* statistically hot and thus worth protecting.
*
* MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
* number of categories of the active/inactive LRU when keeping track of
* accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
* folio->flags, masked by LRU_REFS_MASK.
*/
#define MAX_NR_TIERS 4U
#ifndef __GENERATING_BOUNDS_H
#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
/*
* For folios accessed multiple times through file descriptors,
* lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags
* after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its
* bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily
* promoted into the second oldest generation in the eviction path. And when
* folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that
* lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is
* only valid when PG_referenced is set.
*
* For folios accessed multiple times through page tables, folio_update_gen()
* from a page table walk or lru_gen_set_refs() from a rmap walk sets
* PG_referenced after the accessed bit is cleared for the first time.
* Thereafter, those two paths set PG_workingset and promote folios to the
* youngest generation. Like folio_inc_gen(), folio_update_gen() also clears
* PG_referenced. Note that for this case, LRU_REFS_MASK is not used.
*
* For both cases above, after PG_workingset is set on a folio, it remains until
* this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It
* can be set again if lru_gen_test_recent() returns true upon a refault.
*/
#define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced))
struct lruvec;
struct page_vma_mapped_walk;
#ifdef CONFIG_LRU_GEN
enum {
LRU_GEN_ANON,
LRU_GEN_FILE,
};
enum {
LRU_GEN_CORE,
LRU_GEN_MM_WALK,
LRU_GEN_NONLEAF_YOUNG,
NR_LRU_GEN_CAPS
};
#define MIN_LRU_BATCH BITS_PER_LONG
#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64)
/* whether to keep historical stats from evicted generations */
#ifdef CONFIG_LRU_GEN_STATS
#define NR_HIST_GENS MAX_NR_GENS
#else
#define NR_HIST_GENS 1U
#endif
/*
* The youngest generation number is stored in max_seq for both anon and file
* types as they are aged on an equal footing. The oldest generation numbers are
* stored in min_seq[] separately for anon and file types so that they can be
* incremented independently. Ideally min_seq[] are kept in sync when both anon
* and file types are evictable. However, to adapt to situations like extreme
* swappiness, they are allowed to be out of sync by at most
* MAX_NR_GENS-MIN_NR_GENS-1.
*
* The number of pages in each generation is eventually consistent and therefore
* can be transiently negative when reset_batch_size() is pending.
*/
struct lru_gen_folio {
/* the aging increments the youngest generation number */
unsigned long max_seq;
/* the eviction increments the oldest generation numbers */
unsigned long min_seq[ANON_AND_FILE];
/* the birth time of each generation in jiffies */
unsigned long timestamps[MAX_NR_GENS];
/* the multi-gen LRU lists, lazily sorted on eviction */
struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
/* the multi-gen LRU sizes, eventually consistent */
long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
/* the exponential moving average of refaulted */
unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
/* the exponential moving average of evicted+protected */
unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
/* can only be modified under the LRU lock */
unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
/* can be modified without holding the LRU lock */
atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
/* whether the multi-gen LRU is enabled */
bool enabled;
/* the memcg generation this lru_gen_folio belongs to */
u8 gen;
/* the list segment this lru_gen_folio belongs to */
u8 seg;
/* per-node lru_gen_folio list for global reclaim */
struct hlist_nulls_node list;
};
enum {
MM_LEAF_TOTAL, /* total leaf entries */
MM_LEAF_YOUNG, /* young leaf entries */
MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */
MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */
NR_MM_STATS
};
/* double-buffering Bloom filters */
#define NR_BLOOM_FILTERS 2
struct lru_gen_mm_state {
/* synced with max_seq after each iteration */
unsigned long seq;
/* where the current iteration continues after */
struct list_head *head;
/* where the last iteration ended before */
struct list_head *tail;
/* Bloom filters flip after each iteration */
unsigned long *filters[NR_BLOOM_FILTERS];
/* the mm stats for debugging */
unsigned long stats[NR_HIST_GENS][NR_MM_STATS];
};
struct lru_gen_mm_walk {
/* the lruvec under reclaim */
struct lruvec *lruvec;
/* max_seq from lru_gen_folio: can be out of date */
unsigned long seq;
/* the next address within an mm to scan */
unsigned long next_addr;
/* to batch promoted pages */
int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
/* to batch the mm stats */
int mm_stats[NR_MM_STATS];
/* total batched items */
int batched;
int swappiness;
bool force_scan;
};
/*
* For each node, memcgs are divided into two generations: the old and the
* young. For each generation, memcgs are randomly sharded into multiple bins
* to improve scalability. For each bin, the hlist_nulls is virtually divided
* into three segments: the head, the tail and the default.
*
* An onlining memcg is added to the tail of a random bin in the old generation.
* The eviction starts at the head of a random bin in the old generation. The
* per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes
* the old generation, is incremented when all its bins become empty.
*
* There are four operations:
* 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
* current generation (old or young) and updates its "seg" to "head";
* 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
* current generation (old or young) and updates its "seg" to "tail";
* 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
* generation, updates its "gen" to "old" and resets its "seg" to "default";
* 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
* young generation, updates its "gen" to "young" and resets its "seg" to
* "default".
*
* The events that trigger the above operations are:
* 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
* 2. The first attempt to reclaim a memcg below low, which triggers
* MEMCG_LRU_TAIL;
* 3. The first attempt to reclaim a memcg offlined or below reclaimable size
* threshold, which triggers MEMCG_LRU_TAIL;
* 4. The second attempt to reclaim a memcg offlined or below reclaimable size
* threshold, which triggers MEMCG_LRU_YOUNG;
* 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
* 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
* 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
*
* Notes:
* 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
* of their max_seq counters ensures the eventual fairness to all eligible
* memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
* 2. There are only two valid generations: old (seq) and young (seq+1).
* MEMCG_NR_GENS is set to three so that when reading the generation counter
* locklessly, a stale value (seq-1) does not wraparound to young.
*/
#define MEMCG_NR_GENS 3
#define MEMCG_NR_BINS 8
struct lru_gen_memcg {
/* the per-node memcg generation counter */
unsigned long seq;
/* each memcg has one lru_gen_folio per node */
unsigned long nr_memcgs[MEMCG_NR_GENS];
/* per-node lru_gen_folio list for global reclaim */
struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS];
/* protects the above */
spinlock_t lock;
};
void lru_gen_init_pgdat(struct pglist_data *pgdat);
void lru_gen_init_lruvec(struct lruvec *lruvec);
bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
void lru_gen_init_memcg(struct mem_cgroup *memcg);
void lru_gen_exit_memcg(struct mem_cgroup *memcg);
void lru_gen_online_memcg(struct mem_cgroup *memcg);
void lru_gen_offline_memcg(struct mem_cgroup *memcg);
void lru_gen_release_memcg(struct mem_cgroup *memcg);
void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid);
#else /* !CONFIG_LRU_GEN */
static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
{
}
static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
{
}
static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
{
return false;
}
static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
{
}
static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg)
{
}
static inline void lru_gen_online_memcg(struct mem_cgroup *memcg)
{
}
static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg)
{
}
static inline void lru_gen_release_memcg(struct mem_cgroup *memcg)
{
}
static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
{
}
#endif /* CONFIG_LRU_GEN */
struct lruvec {
struct list_head lists[NR_LRU_LISTS];
/* per lruvec lru_lock for memcg */
spinlock_t lru_lock;
/*
* These track the cost of reclaiming one LRU - file or anon -
* over the other. As the observed cost of reclaiming one LRU
* increases, the reclaim scan balance tips toward the other.
*/
unsigned long anon_cost;
unsigned long file_cost;
/* Non-resident age, driven by LRU movement */
atomic_long_t nonresident_age;
/* Refaults at the time of last reclaim cycle */
unsigned long refaults[ANON_AND_FILE];
/* Various lruvec state flags (enum lruvec_flags) */
unsigned long flags;
#ifdef CONFIG_LRU_GEN
/* evictable pages divided into generations */
struct lru_gen_folio lrugen;
#ifdef CONFIG_LRU_GEN_WALKS_MMU
/* to concurrently iterate lru_gen_mm_list */
struct lru_gen_mm_state mm_state;
#endif
#endif /* CONFIG_LRU_GEN */
#ifdef CONFIG_MEMCG
struct pglist_data *pgdat;
#endif
struct zswap_lruvec_state zswap_lruvec_state;
};
/* Isolate for asynchronous migration */
#define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4)
/* Isolate unevictable pages */
#define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8)
/* LRU Isolation modes. */
typedef unsigned __bitwise isolate_mode_t;
enum zone_watermarks {
WMARK_MIN,
WMARK_LOW,
WMARK_HIGH,
WMARK_PROMO,
NR_WMARK
};
/*
* One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists
* are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list
* is used by GFP_UNMOVABLE and GFP_RECLAIMABLE.
*/
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define NR_PCP_THP 2
#else
#define NR_PCP_THP 0
#endif
#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1))
#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP)
/*
* Flags used in pcp->flags field.
*
* PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the
* previous page freeing. To avoid to drain PCP for an accident
* high-order page freeing.
*
* PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before
* draining PCP for consecutive high-order pages freeing without
* allocation if data cache slice of CPU is large enough. To reduce
* zone lock contention and keep cache-hot pages reusing.
*/
#define PCPF_PREV_FREE_HIGH_ORDER BIT(0)
#define PCPF_FREE_HIGH_BATCH BIT(1)
struct per_cpu_pages {
spinlock_t lock; /* Protects lists field */
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
int high_min; /* min high watermark */
int high_max; /* max high watermark */
int batch; /* chunk size for buddy add/remove */
u8 flags; /* protected by pcp->lock */
u8 alloc_factor; /* batch scaling factor during allocate */
#ifdef CONFIG_NUMA
u8 expire; /* When 0, remote pagesets are drained */
#endif
short free_count; /* consecutive free count */
/* Lists of pages, one per migrate type stored on the pcp-lists */
struct list_head lists[NR_PCP_LISTS];
} ____cacheline_aligned_in_smp;
struct per_cpu_zonestat {
#ifdef CONFIG_SMP
s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
s8 stat_threshold;
#endif
#ifdef CONFIG_NUMA
/*
* Low priority inaccurate counters that are only folded
* on demand. Use a large type to avoid the overhead of
* folding during refresh_cpu_vm_stats.
*/
unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
#endif
};
struct per_cpu_nodestat {
s8 stat_threshold;
s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
};
#endif /* !__GENERATING_BOUNDS.H */
enum zone_type {
/*
* ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able
* to DMA to all of the addressable memory (ZONE_NORMAL).
* On architectures where this area covers the whole 32 bit address
* space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller
* DMA addressing constraints. This distinction is important as a 32bit
* DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
* platforms may need both zones as they support peripherals with
* different DMA addressing limitations.
*/
#ifdef CONFIG_ZONE_DMA
ZONE_DMA,
#endif
#ifdef CONFIG_ZONE_DMA32
ZONE_DMA32,
#endif
/*
* Normal addressable memory is in ZONE_NORMAL. DMA operations can be
* performed on pages in ZONE_NORMAL if the DMA devices support
* transfers to all addressable memory.
*/
ZONE_NORMAL,
#ifdef CONFIG_HIGHMEM
/*
* A memory area that is only addressable by the kernel through
* mapping portions into its own address space. This is for example
* used by i386 to allow the kernel to address the memory beyond
* 900MB. The kernel will set up special mappings (page
* table entries on i386) for each page that the kernel needs to
* access.
*/
ZONE_HIGHMEM,
#endif
/*
* ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains
* movable pages with few exceptional cases described below. Main use
* cases for ZONE_MOVABLE are to make memory offlining/unplug more
* likely to succeed, and to locally limit unmovable allocations - e.g.,
* to increase the number of THP/huge pages. Notable special cases are:
*
* 1. Pinned pages: (long-term) pinning of movable pages might
* essentially turn such pages unmovable. Therefore, we do not allow
* pinning long-term pages in ZONE_MOVABLE. When pages are pinned and
* faulted, they come from the right zone right away. However, it is
* still possible that address space already has pages in
* ZONE_MOVABLE at the time when pages are pinned (i.e. user has
* touches that memory before pinning). In such case we migrate them
* to a different zone. When migration fails - pinning fails.
* 2. memblock allocations: kernelcore/movablecore setups might create
* situations where ZONE_MOVABLE contains unmovable allocations
* after boot. Memory offlining and allocations fail early.
* 3. Memory holes: kernelcore/movablecore setups might create very rare
* situations where ZONE_MOVABLE contains memory holes after boot,
* for example, if we have sections that are only partially
* populated. Memory offlining and allocations fail early.
* 4. PG_hwpoison pages: while poisoned pages can be skipped during
* memory offlining, such pages cannot be allocated.
* 5. Unmovable PG_offline pages: in paravirtualized environments,
* hotplugged memory blocks might only partially be managed by the
* buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The
* parts not manged by the buddy are unmovable PG_offline pages. In
* some cases (virtio-mem), such pages can be skipped during
* memory offlining, however, cannot be moved/allocated. These
* techniques might use alloc_contig_range() to hide previously
* exposed pages from the buddy again (e.g., to implement some sort
* of memory unplug in virtio-mem).
* 6. ZERO_PAGE(0), kernelcore/movablecore setups might create
* situations where ZERO_PAGE(0) which is allocated differently
* on different platforms may end up in a movable zone. ZERO_PAGE(0)
* cannot be migrated.
* 7. Memory-hotplug: when using memmap_on_memory and onlining the
* memory to the MOVABLE zone, the vmemmap pages are also placed in
* such zone. Such pages cannot be really moved around as they are
* self-stored in the range, but they are treated as movable when
* the range they describe is about to be offlined.
*
* In general, no unmovable allocations that degrade memory offlining
* should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range())
* have to expect that migrating pages in ZONE_MOVABLE can fail (even
* if has_unmovable_pages() states that there are no unmovable pages,
* there can be false negatives).
*/
ZONE_MOVABLE,
#ifdef CONFIG_ZONE_DEVICE
ZONE_DEVICE,
#endif
__MAX_NR_ZONES
};
#ifndef __GENERATING_BOUNDS_H
#define ASYNC_AND_SYNC 2
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long _watermark[NR_WMARK];
unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
unsigned long nr_free_highatomic;
/*
* We don't know if the memory that we're going to allocate will be
* freeable or/and it will be released eventually, so to avoid totally
* wasting several GB of ram we must reserve some of the lower zone
* memory (otherwise we risk to run OOM on the lower zones despite
* there being tons of freeable ram on the higher zones). This array is
* recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
* changes.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
struct pglist_data *zone_pgdat;
struct per_cpu_pages __percpu *per_cpu_pageset;
struct per_cpu_zonestat __percpu *per_cpu_zonestats;
/*
* the high and batch values are copied to individual pagesets for
* faster access
*/
int pageset_high_min;
int pageset_high_max;
int pageset_batch;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
* present_early_pages is present pages existing within the zone
* located on memory available since early boot, excluding hotplugged
* memory.
*
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
* managed_pages = present_pages - reserved_pages;
*
* cma pages is present pages that are assigned for CMA use
* (MIGRATE_CMA).
*
* So present_pages may be used by memory hotplug or memory power
* management logic to figure out unmanaged pages by checking
* (present_pages - managed_pages). And managed_pages should be used
* by page allocator and vm scanner to calculate all kinds of watermarks
* and thresholds.
*
* Locking rules:
*
* zone_start_pfn and spanned_pages are protected by span_seqlock.
* It is a seqlock because it has to be read outside of zone->lock,
* and it is done in the main allocator path. But, it is written
* quite infrequently.
*
* The span_seq lock is declared along with zone->lock because it is
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/done(). Any reader who can't tolerant drift of
* present_pages should use get_online_mems() to get a stable value.
*/
atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
#if defined(CONFIG_MEMORY_HOTPLUG)
unsigned long present_early_pages;
#endif
#ifdef CONFIG_CMA
unsigned long cma_pages;
#endif
const char *name;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
int initialized;
/* Write-intensive fields used from the page allocator */
CACHELINE_PADDING(_pad1_);
/* free areas of different sizes */
struct free_area free_area[NR_PAGE_ORDERS];
#ifdef CONFIG_UNACCEPTED_MEMORY
/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
struct list_head unaccepted_pages;
/* To be called once the last page in the zone is accepted */
struct work_struct unaccepted_cleanup;
#endif
/* zone flags, see below */
unsigned long flags;
/* Primarily protects free_area */
spinlock_t lock;
/* Pages to be freed when next trylock succeeds */
struct llist_head trylock_free_pages;
/* Write-intensive fields used by compaction and vmstats. */
CACHELINE_PADDING(_pad2_);
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC];
unsigned long compact_init_migrate_pfn;
unsigned long compact_init_free_pfn;
#endif
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
* compact_order_failed is the minimum compaction failed order.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
bool contiguous;
CACHELINE_PADDING(_pad3_);
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
} ____cacheline_internodealigned_in_smp;
enum pgdat_flags {
PGDAT_DIRTY, /* reclaim scanning has recently found
* many dirty file pages at the tail
* of the LRU.
*/
PGDAT_WRITEBACK, /* reclaim scanning has recently found
* many pages under writeback
*/
PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */
};
enum zone_flags {
ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks.
* Cleared when kswapd is woken.
*/
ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */
ZONE_BELOW_HIGH, /* zone is below high watermark. */
};
static inline unsigned long wmark_pages(const struct zone *z,
enum zone_watermarks w)
{
return z->_watermark[w] + z->watermark_boost;
}
static inline unsigned long min_wmark_pages(const struct zone *z)
{
return wmark_pages(z, WMARK_MIN);
}
static inline unsigned long low_wmark_pages(const struct zone *z)
{
return wmark_pages(z, WMARK_LOW);
}
static inline unsigned long high_wmark_pages(const struct zone *z)
{
return wmark_pages(z, WMARK_HIGH);
}
static inline unsigned long promo_wmark_pages(const struct zone *z)
{
return wmark_pages(z, WMARK_PROMO);
}
static inline unsigned long zone_managed_pages(struct zone *zone)
{
return (unsigned long)atomic_long_read(&zone->managed_pages);
}
static inline unsigned long zone_cma_pages(struct zone *zone)
{
#ifdef CONFIG_CMA
return zone->cma_pages;
#else
return 0;
#endif
}
static inline unsigned long zone_end_pfn(const struct zone *zone)
{
return zone->zone_start_pfn + zone->spanned_pages;
}
static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
{
return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone);
}
static inline bool zone_is_initialized(struct zone *zone)
{
return zone->initialized;
}
static inline bool zone_is_empty(struct zone *zone)
{
return zone->spanned_pages == 0;
}
#ifndef BUILD_VDSO32_64
/*
* The zone field is never updated after free_area_init_core()
* sets it, so none of the operations on it need to be atomic.
*/
/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH)
#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH)
#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH)
/*
* Define the bit shifts to access each section. For non-existent
* sections we define the shift as 0; that plus a 0 mask ensures
* the compiler will optimise away reference to them.
*/
#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0))
#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))
#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0))
/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
#ifdef NODE_NOT_IN_PAGE_FLAGS
#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \
SECTIONS_PGOFF : ZONES_PGOFF)
#else
#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \
NODES_PGOFF : ZONES_PGOFF)
#endif
#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1)
#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1)
#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1)
static inline enum zone_type page_zonenum(const struct page *page)
{
ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
static inline enum zone_type folio_zonenum(const struct folio *folio)
{
return page_zonenum(&folio->page);
}
#ifdef CONFIG_ZONE_DEVICE
static inline bool is_zone_device_page(const struct page *page)
{
return page_zonenum(page) == ZONE_DEVICE;
}
static inline struct dev_pagemap *page_pgmap(const struct page *page)
{
VM_WARN_ON_ONCE_PAGE(!is_zone_device_page(page), page);
return page_folio(page)->pgmap;
}
/*
* Consecutive zone device pages should not be merged into the same sgl
* or bvec segment with other types of pages or if they belong to different
* pgmaps. Otherwise getting the pgmap of a given segment is not possible
* without scanning the entire segment. This helper returns true either if
* both pages are not zone device pages or both pages are zone device pages
* with the same pgmap.
*/
static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
const struct page *b)
{
if (is_zone_device_page(a) != is_zone_device_page(b))
return false;
if (!is_zone_device_page(a))
return true;
return page_pgmap(a) == page_pgmap(b);
}
extern void memmap_init_zone_device(struct zone *, unsigned long,
unsigned long, struct dev_pagemap *);
#else
static inline bool is_zone_device_page(const struct page *page)
{
return false;
}
static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
const struct page *b)
{
return true;
}
static inline struct dev_pagemap *page_pgmap(const struct page *page)
{
return NULL;
}
#endif
static inline bool folio_is_zone_device(const struct folio *folio)
{
return is_zone_device_page(&folio->page);
}
static inline bool is_zone_movable_page(const struct page *page)
{
return page_zonenum(page) == ZONE_MOVABLE;
}
static inline bool folio_is_zone_movable(const struct folio *folio)
{
return folio_zonenum(folio) == ZONE_MOVABLE;
}
#endif
/*
* Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
* intersection with the given zone
*/
static inline bool zone_intersects(struct zone *zone,
unsigned long start_pfn, unsigned long nr_pages)
{
if (zone_is_empty(zone))
return false;
if (start_pfn >= zone_end_pfn(zone) ||
start_pfn + nr_pages <= zone->zone_start_pfn)
return false;
return true;
}
/*
* The "priority" of VM scanning is how much of the queues we will scan in one
* go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
* queues ("queue_length >> 12") during an aging round.
*/
#define DEF_PRIORITY 12
/* Maximum number of zones on a zonelist */
#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES)
enum {
ZONELIST_FALLBACK, /* zonelist with fallback */
#ifdef CONFIG_NUMA
/*
* The NUMA zonelists are doubled because we need zonelists that
* restrict the allocations to a single node for __GFP_THISNODE.
*/
ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */
#endif
MAX_ZONELISTS
};
/*
* This struct contains information about a zone in a zonelist. It is stored
* here to avoid dereferences into large structures and lookups of tables
*/
struct zoneref {
struct zone *zone; /* Pointer to actual zone */
int zone_idx; /* zone_idx(zoneref->zone) */
};
/*
* One allocation request operates on a zonelist. A zonelist
* is a list of zones, the first one is the 'goal' of the
* allocation, the other zones are fallback zones, in decreasing
* priority.
*
* To speed the reading of the zonelist, the zonerefs contain the zone index
* of the entry being read. Helper functions to access information given
* a struct zoneref are
*
* zonelist_zone() - Return the struct zone * for an entry in _zonerefs
* zonelist_zone_idx() - Return the index of the zone for an entry
* zonelist_node_idx() - Return the index of the node for an entry
*/
struct zonelist {
struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
};
/*
* The array of struct pages for flatmem.
* It must be declared for SPARSEMEM as well because there are configurations
* that rely on that.
*/
extern struct page *mem_map;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split {
spinlock_t split_queue_lock;
struct list_head split_queue;
unsigned long split_queue_len;
};
#endif
#ifdef CONFIG_MEMORY_FAILURE
/*
* Per NUMA node memory failure handling statistics.
*/
struct memory_failure_stats {
/*
* Number of raw pages poisoned.
* Cases not accounted: memory outside kernel control, offline page,
* arch-specific memory_failure (SGX), hwpoison_filter() filtered
* error events, and unpoison actions from hwpoison_unpoison.
*/
unsigned long total;
/*
* Recovery results of poisoned raw pages handled by memory_failure,
* in sync with mf_result.
* total = ignored + failed + delayed + recovered.
* total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted.
*/
unsigned long ignored;
unsigned long failed;
unsigned long delayed;
unsigned long recovered;
};
#endif
/*
* On NUMA machines, each NUMA node would have a pg_data_t to describe
* it's memory layout. On UMA machines there is a single pglist_data which
* describes the whole memory.
*
* Memory statistics and page replacement data structures are maintained on a
* per-zone basis.
*/
typedef struct pglist_data {
/*
* node_zones contains just the zones for THIS node. Not all of the
* zones may be populated, but it is the full list. It is referenced by
* this node's node_zonelists as well as other node's node_zonelists.
*/
struct zone node_zones[MAX_NR_ZONES];
/*
* node_zonelists contains references to all zones in all nodes.
* Generally the first zones will be references to this node's
* node_zones.
*/
struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones; /* number of populated zones in this node */
#ifdef CONFIG_FLATMEM /* means !SPARSEMEM */
struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
struct page_ext *node_page_ext;
#endif
#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
* Must be held any time you expect node_start_pfn,
* node_present_pages, node_spanned_pages or nr_zones to stay constant.
* Also synchronizes pgdat->first_deferred_pfn during deferred page
* init.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
* or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
*
* Nests above zone->lock and zone->span_seqlock
*/
spinlock_t node_size_lock;
#endif
unsigned long node_start_pfn;
unsigned long node_present_pages; /* total number of physical pages */
unsigned long node_spanned_pages; /* total size of physical page
range, including holes */
int node_id;
wait_queue_head_t kswapd_wait;
wait_queue_head_t pfmemalloc_wait;
/* workqueues for throttling reclaim for different reasons. */
wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE];
atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */
unsigned long nr_reclaim_start; /* nr pages written while throttled
* when throttling started. */
#ifdef CONFIG_MEMORY_HOTPLUG
struct mutex kswapd_lock;
#endif
struct task_struct *kswapd; /* Protected by kswapd_lock */
int kswapd_order;
enum zone_type kswapd_highest_zoneidx;
int kswapd_failures; /* Number of 'reclaimed == 0' runs */
#ifdef CONFIG_COMPACTION
int kcompactd_max_order;
enum zone_type kcompactd_highest_zoneidx;
wait_queue_head_t kcompactd_wait;
struct task_struct *kcompactd;
bool proactive_compact_trigger;
#endif
/*
* This is a per-node reserve of pages that are not available
* to userspace allocations.
*/
unsigned long totalreserve_pages;
#ifdef CONFIG_NUMA
/*
* node reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
#endif /* CONFIG_NUMA */
/* Write-intensive fields used by page reclaim */
CACHELINE_PADDING(_pad1_);
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* If memory initialisation on large machines is deferred then this
* is the first PFN that needs to be initialised.
*/
unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split deferred_split_queue;
#endif
#ifdef CONFIG_NUMA_BALANCING
/* start time in ms of current promote rate limit period */
unsigned int nbp_rl_start;
/* number of promote candidate pages at start time of current rate limit period */
unsigned long nbp_rl_nr_cand;
/* promote threshold in ms */
unsigned int nbp_threshold;
/* start time in ms of current promote threshold adjustment period */
unsigned int nbp_th_start;
/*
* number of promote candidate pages at start time of current promote
* threshold adjustment period
*/
unsigned long nbp_th_nr_cand;
#endif
/* Fields commonly accessed by the page reclaim scanner */
/*
* NOTE: THIS IS UNUSED IF MEMCG IS ENABLED.
*
* Use mem_cgroup_lruvec() to look up lruvecs.
*/
struct lruvec __lruvec;
unsigned long flags;
#ifdef CONFIG_LRU_GEN
/* kswap mm walk data */
struct lru_gen_mm_walk mm_walk;
/* lru_gen_folio list */
struct lru_gen_memcg memcg_lru;
#endif
CACHELINE_PADDING(_pad2_);
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
#ifdef CONFIG_NUMA
struct memory_tier __rcu *memtier;
#endif
#ifdef CONFIG_MEMORY_FAILURE
struct memory_failure_stats mf_stats;
#endif
} pg_data_t;
#define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
#define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages)
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
{
return pgdat->node_start_pfn + pgdat->node_spanned_pages;
}
#include <linux/memory_hotplug.h>
void build_all_zonelists(pg_data_t *pgdat);
void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
enum zone_type highest_zoneidx);
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int highest_zoneidx, unsigned int alloc_flags,
long free_pages);
bool zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int highest_zoneidx,
unsigned int alloc_flags);
/*
* Memory initialization context, use to differentiate memory added by
* the platform statically or via memory hotplug interface.
*/
enum meminit_context {
MEMINIT_EARLY,
MEMINIT_HOTPLUG,
};
extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
unsigned long size);
extern void lruvec_init(struct lruvec *lruvec);
static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
{
#ifdef CONFIG_MEMCG
return lruvec->pgdat;
#else
return container_of(lruvec, struct pglist_data, __lruvec);
#endif
}
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
int local_memory_node(int node_id);
#else
static inline int local_memory_node(int node_id) { return node_id; };
#endif
/*
* zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.
*/
#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones)
#ifdef CONFIG_ZONE_DEVICE
static inline bool zone_is_zone_device(struct zone *zone)
{
return zone_idx(zone) == ZONE_DEVICE;
}
#else
static inline bool zone_is_zone_device(struct zone *zone)
{
return false;
}
#endif
/*
* Returns true if a zone has pages managed by the buddy allocator.
* All the reclaim decisions have to use this function rather than
* populated_zone(). If the whole zone is reserved then we can easily
* end up with populated_zone() && !managed_zone().
*/
static inline bool managed_zone(struct zone *zone)
{
return zone_managed_pages(zone);
}
/* Returns true if a zone has memory */
static inline bool populated_zone(struct zone *zone)
{
return zone->present_pages;
}
#ifdef CONFIG_NUMA
static inline int zone_to_nid(struct zone *zone)
{
return zone->node;
}
static inline void zone_set_nid(struct zone *zone, int nid)
{
zone->node = nid;
}
#else
static inline int zone_to_nid(struct zone *zone)
{
return 0;
}
static inline void zone_set_nid(struct zone *zone, int nid) {}
#endif
extern int movable_zone;
static inline int is_highmem_idx(enum zone_type idx)
{
#ifdef CONFIG_HIGHMEM
return (idx == ZONE_HIGHMEM ||
(idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM));
#else
return 0;
#endif
}
/**
* is_highmem - helper function to quickly check if a struct zone is a
* highmem zone or not. This is an attempt to keep references
* to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
* @zone: pointer to struct zone variable
* Return: 1 for a highmem zone, 0 otherwise
*/
static inline int is_highmem(struct zone *zone)
{
return is_highmem_idx(zone_idx(zone));
}
#ifdef CONFIG_ZONE_DMA
bool has_managed_dma(void);
#else
static inline bool has_managed_dma(void)
{
return false;
}
#endif
#ifndef CONFIG_NUMA
extern struct pglist_data contig_page_data;
static inline struct pglist_data *NODE_DATA(int nid)
{
return &contig_page_data;
}
#else /* CONFIG_NUMA */
#include <asm/mmzone.h>
#endif /* !CONFIG_NUMA */
extern struct pglist_data *first_online_pgdat(void);
extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat);
extern struct zone *next_zone(struct zone *zone);
/**
* for_each_online_pgdat - helper macro to iterate over all online nodes
* @pgdat: pointer to a pg_data_t variable
*/
#define for_each_online_pgdat(pgdat) \
for (pgdat = first_online_pgdat(); \
pgdat; \
pgdat = next_online_pgdat(pgdat))
/**
* for_each_zone - helper macro to iterate over all memory zones
* @zone: pointer to struct zone variable
*
* The user only needs to declare the zone variable, for_each_zone
* fills it in.
*/
#define for_each_zone(zone) \
for (zone = (first_online_pgdat())->node_zones; \
zone; \
zone = next_zone(zone))
#define for_each_populated_zone(zone) \
for (zone = (first_online_pgdat())->node_zones; \
zone; \
zone = next_zone(zone)) \
if (!populated_zone(zone)) \
; /* do nothing */ \
else
static inline struct zone *zonelist_zone(struct zoneref *zoneref)
{
return zoneref->zone;
}
static inline int zonelist_zone_idx(struct zoneref *zoneref)
{
return zoneref->zone_idx;
}
static inline int zonelist_node_idx(struct zoneref *zoneref)
{
return zone_to_nid(zoneref->zone);
}
struct zoneref *__next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
nodemask_t *nodes);
/**
* next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point
* @z: The cursor used as a starting point for the search
* @highest_zoneidx: The zone index of the highest zone to return
* @nodes: An optional nodemask to filter the zonelist with
*
* This function returns the next zone at or below a given zone index that is
* within the allowed nodemask using a cursor as the starting point for the
* search. The zoneref returned is a cursor that represents the current zone
* being examined. It should be advanced by one before calling
* next_zones_zonelist again.
*
* Return: the next zone at or below highest_zoneidx within the allowed
* nodemask using a cursor within a zonelist as a starting point
*/
static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
nodemask_t *nodes)
{
if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx))
return z;
return __next_zones_zonelist(z, highest_zoneidx, nodes);
}
/**
* first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
* @zonelist: The zonelist to search for a suitable zone
* @highest_zoneidx: The zone index of the highest zone to return
* @nodes: An optional nodemask to filter the zonelist with
*
* This function returns the first zone at or below a given zone index that is
* within the allowed nodemask. The zoneref returned is a cursor that can be
* used to iterate the zonelist with next_zones_zonelist by advancing it by
* one before calling.
*
* When no eligible zone is found, zoneref->zone is NULL (zoneref itself is
* never NULL). This may happen either genuinely, or due to concurrent nodemask
* update due to cpuset modification.
*
* Return: Zoneref pointer for the first suitable zone found
*/
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
enum zone_type highest_zoneidx,
nodemask_t *nodes)
{
return next_zones_zonelist(zonelist->_zonerefs,
highest_zoneidx, nodes);
}
/**
* for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
* @zone: The current zone in the iterator
* @z: The current pointer within zonelist->_zonerefs being iterated
* @zlist: The zonelist being iterated
* @highidx: The zone index of the highest zone to return
* @nodemask: Nodemask allowed by the allocator
*
* This iterator iterates though all zones at or below a given zone index and
* within a given nodemask
*/
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \
zone; \
z = next_zones_zonelist(++z, highidx, nodemask), \
zone = zonelist_zone(z))
#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \
for (zone = zonelist_zone(z); \
zone; \
z = next_zones_zonelist(++z, highidx, nodemask), \
zone = zonelist_zone(z))
/**
* for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
* @zone: The current zone in the iterator
* @z: The current pointer within zonelist->zones being iterated
* @zlist: The zonelist being iterated
* @highidx: The zone index of the highest zone to return
*
* This iterator iterates though all zones at or below a given zone index.
*/
#define for_each_zone_zonelist(zone, z, zlist, highidx) \
for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
/* Whether the 'nodes' are all movable nodes */
static inline bool movable_only_nodes(nodemask_t *nodes)
{
struct zonelist *zonelist;
struct zoneref *z;
int nid;
if (nodes_empty(*nodes))
return false;
/*
* We can chose arbitrary node from the nodemask to get a
* zonelist as they are interlinked. We just need to find
* at least one zone that can satisfy kernel allocations.
*/
nid = first_node(*nodes);
zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes);
return (!zonelist_zone(z)) ? true : false;
}
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif
#ifdef CONFIG_FLATMEM
#define pfn_to_nid(pfn) (0)
#endif
#ifdef CONFIG_SPARSEMEM
/*
* PA_SECTION_SHIFT physical address to/from section number
* PFN_SECTION_SHIFT pfn to/from section number
*/
#define PA_SECTION_SHIFT (SECTION_SIZE_BITS)
#define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT)
#define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT)
#define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT)
#define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1))
#define SECTION_BLOCKFLAGS_BITS \
((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE
#endif
static inline unsigned long pfn_to_section_nr(unsigned long pfn)
{
return pfn >> PFN_SECTION_SHIFT;
}
static inline unsigned long section_nr_to_pfn(unsigned long sec)
{
return sec << PFN_SECTION_SHIFT;
}
#define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
#define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK)
#define SUBSECTION_SHIFT 21
#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT)
#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)
#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1))
#if SUBSECTION_SHIFT > SECTION_SIZE_BITS
#error Subsection size exceeds section size
#else
#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT))
#endif
#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
struct mem_section_usage {
struct rcu_head rcu;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
#endif
/* See declaration of similar field in struct zone */
unsigned long pageblock_flags[0];
};
void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
struct page;
struct page_ext;
struct mem_section {
/*
* This is, logically, a pointer to an array of struct
* pages. However, it is stored with some other magic.
* (see sparse.c::sparse_init_one_section())
*
* Additionally during early boot we encode node id of
* the location of the section here to guide allocation.
* (see sparse.c::memory_present())
*
* Making it a UL at least makes someone do a cast
* before using it wrong.
*/
unsigned long section_mem_map;
struct mem_section_usage *usage;
#ifdef CONFIG_PAGE_EXTENSION
/*
* If SPARSEMEM, pgdat doesn't have page_ext pointer. We use
* section. (see page_ext.h about this.)
*/
struct page_ext *page_ext;
unsigned long pad;
#endif
/*
* WARNING: mem_section must be a power-of-2 in size for the
* calculation and use of SECTION_ROOT_MASK to make sense.
*/
};
#ifdef CONFIG_SPARSEMEM_EXTREME
#define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section))
#else
#define SECTIONS_PER_ROOT 1
#endif
#define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT)
#define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT)
#define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1)
#ifdef CONFIG_SPARSEMEM_EXTREME
extern struct mem_section **mem_section;
#else
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
static inline unsigned long *section_to_usemap(struct mem_section *ms)
{
return ms->usage->pageblock_flags;
}
static inline struct mem_section *__nr_to_section(unsigned long nr)
{
unsigned long root = SECTION_NR_TO_ROOT(nr);
if (unlikely(root >= NR_SECTION_ROOTS))
return NULL;
#ifdef CONFIG_SPARSEMEM_EXTREME
if (!mem_section || !mem_section[root])
return NULL;
#endif
return &mem_section[root][nr & SECTION_ROOT_MASK];
}
extern size_t mem_section_usage_size(void);
/*
* We use the lower bits of the mem_map pointer to store
* a little bit of information. The pointer is calculated
* as mem_map - section_nr_to_pfn(pnum). The result is
* aligned to the minimum alignment of the two values:
* 1. All mem_map arrays are page-aligned.
* 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT
* lowest bits. PFN_SECTION_SHIFT is arch-specific
* (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
* worst combination is powerpc with 256k pages,
* which results in PFN_SECTION_SHIFT equal 6.
* To sum it up, at least 6 bits are available on all architectures.
* However, we can exceed 6 bits on some other architectures except
* powerpc (e.g. 15 bits are available on x86_64, 13 bits are available
* with the worst case of 64K pages on arm64) if we make sure the
* exceeded bit is not applicable to powerpc.
*/
enum {
SECTION_MARKED_PRESENT_BIT,
SECTION_HAS_MEM_MAP_BIT,
SECTION_IS_ONLINE_BIT,
SECTION_IS_EARLY_BIT,
#ifdef CONFIG_ZONE_DEVICE
SECTION_TAINT_ZONE_DEVICE_BIT,
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
SECTION_IS_VMEMMAP_PREINIT_BIT,
#endif
SECTION_MAP_LAST_BIT,
};
#define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT)
#define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT)
#define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT)
#define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT)
#ifdef CONFIG_ZONE_DEVICE
#define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT)
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
#define SECTION_IS_VMEMMAP_PREINIT BIT(SECTION_IS_VMEMMAP_PREINIT_BIT)
#endif
#define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1))
#define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT
static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
unsigned long map = section->section_mem_map;
map &= SECTION_MAP_MASK;
return (struct page *)map;
}
static inline int present_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
}
static inline int present_section_nr(unsigned long nr)
{
return present_section(__nr_to_section(nr));
}
static inline int valid_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
}
static inline int early_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_IS_EARLY));
}
static inline int valid_section_nr(unsigned long nr)
{
return valid_section(__nr_to_section(nr));
}
static inline int online_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_IS_ONLINE));
}
#ifdef CONFIG_ZONE_DEVICE
static inline int online_device_section(struct mem_section *section)
{
unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE;
return section && ((section->section_mem_map & flags) == flags);
}
#else
static inline int online_device_section(struct mem_section *section)
{
return 0;
}
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
static inline int preinited_vmemmap_section(struct mem_section *section)
{
return (section &&
(section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT));
}
void sparse_vmemmap_init_nid_early(int nid);
void sparse_vmemmap_init_nid_late(int nid);
#else
static inline int preinited_vmemmap_section(struct mem_section *section)
{
return 0;
}
static inline void sparse_vmemmap_init_nid_early(int nid)
{
}
static inline void sparse_vmemmap_init_nid_late(int nid)
{
}
#endif
static inline int online_section_nr(unsigned long nr)
{
return online_section(__nr_to_section(nr));
}
#ifdef CONFIG_MEMORY_HOTPLUG
void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
#endif
static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
return __nr_to_section(pfn_to_section_nr(pfn));
}
extern unsigned long __highest_present_section_nr;
static inline int subsection_map_index(unsigned long pfn)
{
return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION;
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
{
int idx = subsection_map_index(pfn);
struct mem_section_usage *usage = READ_ONCE(ms->usage);
return usage ? test_bit(idx, usage->subsection_map) : 0;
}
#else
static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
{
return 1;
}
#endif
void sparse_init_early_section(int nid, struct page *map, unsigned long pnum,
unsigned long flags);
#ifndef CONFIG_HAVE_ARCH_PFN_VALID
/**
* pfn_valid - check if there is a valid memory map entry for a PFN
* @pfn: the page frame number to check
*
* Check if there is a valid memory map entry aka struct page for the @pfn.
* Note, that availability of the memory map entry does not imply that
* there is actual usable memory at that @pfn. The struct page may
* represent a hole or an unusable page frame.
*
* Return: 1 for PFNs that have memory map entries and 0 otherwise
*/
static inline int pfn_valid(unsigned long pfn)
{
struct mem_section *ms;
int ret;
/*
* Ensure the upper PAGE_SHIFT bits are clear in the
* pfn. Else it might lead to false positives when
* some of the upper bits are set, but the lower bits
* match a valid pfn.
*/
if (PHYS_PFN(PFN_PHYS(pfn)) != pfn)
return 0;
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched();
return 0;
}
/*
* Traditionally early sections always returned pfn_valid() for
* the entire section-sized span.
*/
ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched();
return ret;
}
#endif
static inline int pfn_in_present_section(unsigned long pfn)
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
return present_section(__pfn_to_section(pfn));
}
static inline unsigned long next_present_section_nr(unsigned long section_nr)
{
while (++section_nr <= __highest_present_section_nr) {
if (present_section_nr(section_nr))
return section_nr;
}
return -1;
}
#define for_each_present_section_nr(start, section_nr) \
for (section_nr = next_present_section_nr(start - 1); \
section_nr != -1; \
section_nr = next_present_section_nr(section_nr))
/*
* These are _only_ used during initialisation, therefore they
* can use __initdata ... They could have names to indicate
* this restriction.
*/
#ifdef CONFIG_NUMA
#define pfn_to_nid(pfn) \
({ \
unsigned long __pfn_to_nid_pfn = (pfn); \
page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \
})
#else
#define pfn_to_nid(pfn) (0)
#endif
void sparse_init(void);
#else
#define sparse_init() do {} while (0)
#define sparse_index_init(_sec, _nid) do {} while (0)
#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0)
#define sparse_vmemmap_init_nid_late(_nid) do {} while (0)
#define pfn_in_present_section pfn_valid
#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
#endif /* !__GENERATING_BOUNDS.H */
#endif /* !__ASSEMBLY__ */
#endif /* _LINUX_MMZONE_H */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2001 Momchil Velikov
* Portions Copyright (C) 2001 Christoph Hellwig
* Copyright (C) 2005 SGI, Christoph Lameter
* Copyright (C) 2006 Nick Piggin
* Copyright (C) 2012 Konstantin Khlebnikov
* Copyright (C) 2016 Intel, Matthew Wilcox
* Copyright (C) 2016 Intel, Ross Zwisler
*/
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/idr.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kmemleak.h>
#include <linux/percpu.h>
#include <linux/preempt.h> /* in_interrupt() */
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/xarray.h>
#include "radix-tree.h"
/*
* Radix tree node cache.
*/
struct kmem_cache *radix_tree_node_cachep;
/*
* The radix tree is variable-height, so an insert operation not only has
* to build the branch to its corresponding item, it also has to build the
* branch to existing items if the size has to be increased (by
* radix_tree_extend).
*
* The worst case is a zero height tree with just a single item at index 0,
* and then inserting an item at index ULONG_MAX. This requires 2 new branches
* of RADIX_TREE_MAX_PATH size to be created, with only the root node shared.
* Hence:
*/
#define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1)
/*
* The IDR does not have to be as high as the radix tree since it uses
* signed integers, not unsigned longs.
*/
#define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1)
#define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \
RADIX_TREE_MAP_SHIFT))
#define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1)
/*
* Per-cpu pool of preloaded nodes
*/
DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = {
.lock = INIT_LOCAL_LOCK(lock),
};
EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads);
static inline struct radix_tree_node *entry_to_node(void *ptr)
{
return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE);
}
static inline void *node_to_entry(void *ptr)
{
return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE);
}
#define RADIX_TREE_RETRY XA_RETRY_ENTRY
static inline unsigned long
get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot)
{
return parent ? slot - parent->slots : 0;
}
static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
struct radix_tree_node **nodep, unsigned long index)
{
unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK;
void __rcu **entry = rcu_dereference_raw(parent->slots[offset]);
*nodep = (void *)entry;
return offset;
}
static inline gfp_t root_gfp_mask(const struct radix_tree_root *root)
{
return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK);
}
static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
int offset)
{
__set_bit(offset, node->tags[tag]);
}
static inline void tag_clear(struct radix_tree_node *node, unsigned int tag,
int offset)
{
__clear_bit(offset, node->tags[tag]);
}
static inline int tag_get(const struct radix_tree_node *node, unsigned int tag,
int offset)
{
return test_bit(offset, node->tags[tag]);
}
static inline void root_tag_set(struct radix_tree_root *root, unsigned tag)
{
root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT));
}
static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag)
{
root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT));
}
static inline void root_tag_clear_all(struct radix_tree_root *root)
{
root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1);
}
static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag)
{
return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT));
}
static inline unsigned root_tags_get(const struct radix_tree_root *root)
{
return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT;
}
static inline bool is_idr(const struct radix_tree_root *root)
{
return !!(root->xa_flags & ROOT_IS_IDR);
}
/*
* Returns 1 if any slot in the node has this tag set.
* Otherwise returns 0.
*/
static inline int any_tag_set(const struct radix_tree_node *node,
unsigned int tag)
{
unsigned idx;
for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) {
if (node->tags[tag][idx])
return 1;
}
return 0;
}
static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag)
{
bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE);
}
/**
* radix_tree_find_next_bit - find the next set bit in a memory region
*
* @node: where to begin the search
* @tag: the tag index
* @offset: the bitnumber to start searching at
*
* Unrollable variant of find_next_bit() for constant size arrays.
* Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero.
* Returns next bit offset, or size if nothing found.
*/
static __always_inline unsigned long
radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag,
unsigned long offset)
{
const unsigned long *addr = node->tags[tag];
if (offset < RADIX_TREE_MAP_SIZE) {
unsigned long tmp;
addr += offset / BITS_PER_LONG;
tmp = *addr >> (offset % BITS_PER_LONG);
if (tmp) return __ffs(tmp) + offset;
offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1);
while (offset < RADIX_TREE_MAP_SIZE) {
tmp = *++addr;
if (tmp)
return __ffs(tmp) + offset;
offset += BITS_PER_LONG;
}
}
return RADIX_TREE_MAP_SIZE;
}
static unsigned int iter_offset(const struct radix_tree_iter *iter)
{
return iter->index & RADIX_TREE_MAP_MASK;
}
/*
* The maximum index which can be stored in a radix tree
*/
static inline unsigned long shift_maxindex(unsigned int shift)
{
return (RADIX_TREE_MAP_SIZE << shift) - 1;
}
static inline unsigned long node_maxindex(const struct radix_tree_node *node)
{
return shift_maxindex(node->shift);
}
static unsigned long next_index(unsigned long index,
const struct radix_tree_node *node,
unsigned long offset)
{
return (index & ~node_maxindex(node)) + (offset << node->shift);
}
/*
* This assumes that the caller has performed appropriate preallocation, and
* that the caller has pinned this thread of control to the current CPU.
*/
static struct radix_tree_node *
radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent,
struct radix_tree_root *root,
unsigned int shift, unsigned int offset,
unsigned int count, unsigned int nr_values)
{
struct radix_tree_node *ret = NULL;
/*
* Preload code isn't irq safe and it doesn't make sense to use
* preloading during an interrupt anyway as all the allocations have
* to be atomic. So just do normal allocation when in interrupt.
*/
if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) {
struct radix_tree_preload *rtp;
/*
* Even if the caller has preloaded, try to allocate from the
* cache first for the new node to get accounted to the memory
* cgroup.
*/
ret = kmem_cache_alloc(radix_tree_node_cachep,
gfp_mask | __GFP_NOWARN);
if (ret)
goto out;
/*
* Provided the caller has preloaded here, we will always
* succeed in getting a node here (and never reach
* kmem_cache_alloc)
*/
rtp = this_cpu_ptr(&radix_tree_preloads);
if (rtp->nr) {
ret = rtp->nodes;
rtp->nodes = ret->parent;
rtp->nr--;
}
/*
* Update the allocation stack trace as this is more useful
* for debugging.
*/
kmemleak_update_trace(ret);
goto out;
}
ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
out:
BUG_ON(radix_tree_is_internal_node(ret));
if (ret) {
ret->shift = shift;
ret->offset = offset;
ret->count = count;
ret->nr_values = nr_values;
ret->parent = parent;
ret->array = root;
}
return ret;
}
void radix_tree_node_rcu_free(struct rcu_head *head)
{
struct radix_tree_node *node =
container_of(head, struct radix_tree_node, rcu_head);
/*
* Must only free zeroed nodes into the slab. We can be left with
* non-NULL entries by radix_tree_free_nodes, so clear the entries
* and tags here.
*/
memset(node->slots, 0, sizeof(node->slots));
memset(node->tags, 0, sizeof(node->tags));
INIT_LIST_HEAD(&node->private_list);
kmem_cache_free(radix_tree_node_cachep, node);
}
static inline void
radix_tree_node_free(struct radix_tree_node *node)
{
call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
}
/*
* Load up this CPU's radix_tree_node buffer with sufficient objects to
* ensure that the addition of a single element in the tree cannot fail. On
* success, return zero, with preemption disabled. On error, return -ENOMEM
* with preemption not disabled.
*
* To make use of this facility, the radix tree must be initialised without
* __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE().
*/
static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
{
struct radix_tree_preload *rtp;
struct radix_tree_node *node;
int ret = -ENOMEM;
/*
* Nodes preloaded by one cgroup can be used by another cgroup, so
* they should never be accounted to any particular memory cgroup.
*/
gfp_mask &= ~__GFP_ACCOUNT;
local_lock(&radix_tree_preloads.lock);
rtp = this_cpu_ptr(&radix_tree_preloads);
while (rtp->nr < nr) {
local_unlock(&radix_tree_preloads.lock);
node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
if (node == NULL)
goto out;
local_lock(&radix_tree_preloads.lock);
rtp = this_cpu_ptr(&radix_tree_preloads);
if (rtp->nr < nr) {
node->parent = rtp->nodes;
rtp->nodes = node;
rtp->nr++;
} else {
kmem_cache_free(radix_tree_node_cachep, node);
}
}
ret = 0;
out:
return ret;
}
/*
* Load up this CPU's radix_tree_node buffer with sufficient objects to
* ensure that the addition of a single element in the tree cannot fail. On
* success, return zero, with preemption disabled. On error, return -ENOMEM
* with preemption not disabled.
*
* To make use of this facility, the radix tree must be initialised without
* __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE().
*/
int radix_tree_preload(gfp_t gfp_mask)
{
/* Warn on non-sensical use... */
WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask));
return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
}
EXPORT_SYMBOL(radix_tree_preload);
/*
* The same as above function, except we don't guarantee preloading happens.
* We do it, if we decide it helps. On success, return zero with preemption
* disabled. On error, return -ENOMEM with preemption not disabled.
*/
int radix_tree_maybe_preload(gfp_t gfp_mask)
{
if (gfpflags_allow_blocking(gfp_mask))
return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
/* Preloading doesn't help anything with this gfp mask, skip it */
local_lock(&radix_tree_preloads.lock);
return 0;
}
EXPORT_SYMBOL(radix_tree_maybe_preload);
static unsigned radix_tree_load_root(const struct radix_tree_root *root,
struct radix_tree_node **nodep, unsigned long *maxindex)
{
struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
*nodep = node;
if (likely(radix_tree_is_internal_node(node))) {
node = entry_to_node(node);
*maxindex = node_maxindex(node);
return node->shift + RADIX_TREE_MAP_SHIFT;
}
*maxindex = 0;
return 0;
}
/*
* Extend a radix tree so it can store key @index.
*/
static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
unsigned long index, unsigned int shift)
{
void *entry;
unsigned int maxshift;
int tag;
/* Figure out what the shift should be. */
maxshift = shift;
while (index > shift_maxindex(maxshift))
maxshift += RADIX_TREE_MAP_SHIFT;
entry = rcu_dereference_raw(root->xa_head);
if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE)))
goto out;
do {
struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL,
root, shift, 0, 1, 0);
if (!node)
return -ENOMEM;
if (is_idr(root)) {
all_tag_set(node, IDR_FREE);
if (!root_tag_get(root, IDR_FREE)) {
tag_clear(node, IDR_FREE, 0);
root_tag_set(root, IDR_FREE);
}
} else {
/* Propagate the aggregated tag info to the new child */
for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
if (root_tag_get(root, tag))
tag_set(node, tag, 0);
}
}
BUG_ON(shift > BITS_PER_LONG);
if (radix_tree_is_internal_node(entry)) {
entry_to_node(entry)->parent = node;
} else if (xa_is_value(entry)) {
/* Moving a value entry root->xa_head to a node */
node->nr_values = 1;
}
/*
* entry was already in the radix tree, so we do not need
* rcu_assign_pointer here
*/
node->slots[0] = (void __rcu *)entry;
entry = node_to_entry(node);
rcu_assign_pointer(root->xa_head, entry);
shift += RADIX_TREE_MAP_SHIFT;
} while (shift <= maxshift);
out:
return maxshift + RADIX_TREE_MAP_SHIFT;
}
/**
* radix_tree_shrink - shrink radix tree to minimum height
* @root: radix tree root
*/
static inline bool radix_tree_shrink(struct radix_tree_root *root)
{
bool shrunk = false;
for (;;) {
struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
struct radix_tree_node *child;
if (!radix_tree_is_internal_node(node))
break;
node = entry_to_node(node);
/*
* The candidate node has more than one child, or its child
* is not at the leftmost slot, we cannot shrink.
*/
if (node->count != 1)
break;
child = rcu_dereference_raw(node->slots[0]);
if (!child)
break;
/*
* For an IDR, we must not shrink entry 0 into the root in
* case somebody calls idr_replace() with a pointer that
* appears to be an internal entry
*/
if (!node->shift && is_idr(root))
break;
if (radix_tree_is_internal_node(child))
entry_to_node(child)->parent = NULL;
/*
* We don't need rcu_assign_pointer(), since we are simply
* moving the node from one part of the tree to another: if it
* was safe to dereference the old pointer to it
* (node->slots[0]), it will be safe to dereference the new
* one (root->xa_head) as far as dependent read barriers go.
*/
root->xa_head = (void __rcu *)child;
if (is_idr(root) && !tag_get(node, IDR_FREE, 0))
root_tag_clear(root, IDR_FREE);
/*
* We have a dilemma here. The node's slot[0] must not be
* NULLed in case there are concurrent lookups expecting to
* find the item. However if this was a bottom-level node,
* then it may be subject to the slot pointer being visible
* to callers dereferencing it. If item corresponding to
* slot[0] is subsequently deleted, these callers would expect
* their slot to become empty sooner or later.
*
* For example, lockless pagecache will look up a slot, deref
* the page pointer, and if the page has 0 refcount it means it
* was concurrently deleted from pagecache so try the deref
* again. Fortunately there is already a requirement for logic
* to retry the entire slot lookup -- the indirect pointer
* problem (replacing direct root node with an indirect pointer
* also results in a stale slot). So tag the slot as indirect
* to force callers to retry.
*/
node->count = 0;
if (!radix_tree_is_internal_node(child)) {
node->slots[0] = (void __rcu *)RADIX_TREE_RETRY;
}
WARN_ON_ONCE(!list_empty(&node->private_list));
radix_tree_node_free(node);
shrunk = true;
}
return shrunk;
}
static bool delete_node(struct radix_tree_root *root,
struct radix_tree_node *node)
{
bool deleted = false;
do {
struct radix_tree_node *parent;
if (node->count) {
if (node_to_entry(node) ==
rcu_dereference_raw(root->xa_head))
deleted |= radix_tree_shrink(root);
return deleted;
}
parent = node->parent;
if (parent) {
parent->slots[node->offset] = NULL;
parent->count--;
} else {
/*
* Shouldn't the tags already have all been cleared
* by the caller?
*/
if (!is_idr(root))
root_tag_clear_all(root);
root->xa_head = NULL;
}
WARN_ON_ONCE(!list_empty(&node->private_list));
radix_tree_node_free(node);
deleted = true;
node = parent;
} while (node);
return deleted;
}
/**
* __radix_tree_create - create a slot in a radix tree
* @root: radix tree root
* @index: index key
* @nodep: returns node
* @slotp: returns slot
*
* Create, if necessary, and return the node and slot for an item
* at position @index in the radix tree @root.
*
* Until there is more than one item in the tree, no nodes are
* allocated and @root->xa_head is used as a direct slot instead of
* pointing to a node, in which case *@nodep will be NULL.
*
* Returns -ENOMEM, or 0 for success.
*/
static int __radix_tree_create(struct radix_tree_root *root,
unsigned long index, struct radix_tree_node **nodep,
void __rcu ***slotp)
{
struct radix_tree_node *node = NULL, *child;
void __rcu **slot = (void __rcu **)&root->xa_head;
unsigned long maxindex;
unsigned int shift, offset = 0;
unsigned long max = index;
gfp_t gfp = root_gfp_mask(root);
shift = radix_tree_load_root(root, &child, &maxindex);
/* Make sure the tree is high enough. */
if (max > maxindex) {
int error = radix_tree_extend(root, gfp, max, shift);
if (error < 0)
return error;
shift = error;
child = rcu_dereference_raw(root->xa_head);
}
while (shift > 0) {
shift -= RADIX_TREE_MAP_SHIFT;
if (child == NULL) {
/* Have to add a child node. */
child = radix_tree_node_alloc(gfp, node, root, shift,
offset, 0, 0);
if (!child)
return -ENOMEM;
rcu_assign_pointer(*slot, node_to_entry(child));
if (node)
node->count++;
} else if (!radix_tree_is_internal_node(child))
break;
/* Go a level down */
node = entry_to_node(child);
offset = radix_tree_descend(node, &child, index);
slot = &node->slots[offset];
}
if (nodep)
*nodep = node;
if (slotp)
*slotp = slot;
return 0;
}
/*
* Free any nodes below this node. The tree is presumed to not need
* shrinking, and any user data in the tree is presumed to not need a
* destructor called on it. If we need to add a destructor, we can
* add that functionality later. Note that we may not clear tags or
* slots from the tree as an RCU walker may still have a pointer into
* this subtree. We could replace the entries with RADIX_TREE_RETRY,
* but we'll still have to clear those in rcu_free.
*/
static void radix_tree_free_nodes(struct radix_tree_node *node)
{
unsigned offset = 0;
struct radix_tree_node *child = entry_to_node(node);
for (;;) {
void *entry = rcu_dereference_raw(child->slots[offset]);
if (xa_is_node(entry) && child->shift) {
child = entry_to_node(entry);
offset = 0;
continue;
}
offset++;
while (offset == RADIX_TREE_MAP_SIZE) {
struct radix_tree_node *old = child;
offset = child->offset + 1;
child = child->parent;
WARN_ON_ONCE(!list_empty(&old->private_list));
radix_tree_node_free(old);
if (old == entry_to_node(node))
return;
}
}
}
static inline int insert_entries(struct radix_tree_node *node,
void __rcu **slot, void *item)
{
if (*slot)
return -EEXIST;
rcu_assign_pointer(*slot, item);
if (node) {
node->count++;
if (xa_is_value(item))
node->nr_values++;
}
return 1;
}
/**
* radix_tree_insert - insert into a radix tree
* @root: radix tree root
* @index: index key
* @item: item to insert
*
* Insert an item into the radix tree at position @index.
*/
int radix_tree_insert(struct radix_tree_root *root, unsigned long index,
void *item)
{
struct radix_tree_node *node;
void __rcu **slot;
int error;
BUG_ON(radix_tree_is_internal_node(item));
error = __radix_tree_create(root, index, &node, &slot);
if (error)
return error;
error = insert_entries(node, slot, item);
if (error < 0)
return error;
if (node) {
unsigned offset = get_slot_offset(node, slot);
BUG_ON(tag_get(node, 0, offset));
BUG_ON(tag_get(node, 1, offset));
BUG_ON(tag_get(node, 2, offset));
} else {
BUG_ON(root_tags_get(root));
}
return 0;
}
EXPORT_SYMBOL(radix_tree_insert);
/**
* __radix_tree_lookup - lookup an item in a radix tree
* @root: radix tree root
* @index: index key
* @nodep: returns node
* @slotp: returns slot
*
* Lookup and return the item at position @index in the radix
* tree @root.
*
* Until there is more than one item in the tree, no nodes are
* allocated and @root->xa_head is used as a direct slot instead of
* pointing to a node, in which case *@nodep will be NULL.
*/
void *__radix_tree_lookup(const struct radix_tree_root *root,
unsigned long index, struct radix_tree_node **nodep,
void __rcu ***slotp)
{
struct radix_tree_node *node, *parent;
unsigned long maxindex;
void __rcu **slot;
restart:
parent = NULL;
slot = (void __rcu **)&root->xa_head;
radix_tree_load_root(root, &node, &maxindex); if (index > maxindex)
return NULL;
while (radix_tree_is_internal_node(node)) {
unsigned offset;
parent = entry_to_node(node);
offset = radix_tree_descend(parent, &node, index);
slot = parent->slots + offset;
if (node == RADIX_TREE_RETRY)
goto restart;
if (parent->shift == 0)
break;
}
if (nodep)
*nodep = parent;
if (slotp)
*slotp = slot;
return node;
}
/**
* radix_tree_lookup_slot - lookup a slot in a radix tree
* @root: radix tree root
* @index: index key
*
* Returns: the slot corresponding to the position @index in the
* radix tree @root. This is useful for update-if-exists operations.
*
* This function can be called under rcu_read_lock iff the slot is not
* modified by radix_tree_replace_slot, otherwise it must be called
* exclusive from other writers. Any dereference of the slot must be done
* using radix_tree_deref_slot.
*/
void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root,
unsigned long index)
{
void __rcu **slot;
if (!__radix_tree_lookup(root, index, NULL, &slot))
return NULL;
return slot;
}
EXPORT_SYMBOL(radix_tree_lookup_slot);
/**
* radix_tree_lookup - perform lookup operation on a radix tree
* @root: radix tree root
* @index: index key
*
* Lookup the item at the position @index in the radix tree @root.
*
* This function can be called under rcu_read_lock, however the caller
* must manage lifetimes of leaf nodes (eg. RCU may also be used to free
* them safely). No RCU barriers are required to access or modify the
* returned item, however.
*/
void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index)
{ return __radix_tree_lookup(root, index, NULL, NULL);
}
EXPORT_SYMBOL(radix_tree_lookup);
static void replace_slot(void __rcu **slot, void *item,
struct radix_tree_node *node, int count, int values)
{
if (node && (count || values)) {
node->count += count;
node->nr_values += values;
}
rcu_assign_pointer(*slot, item);
}
static bool node_tag_get(const struct radix_tree_root *root,
const struct radix_tree_node *node,
unsigned int tag, unsigned int offset)
{
if (node)
return tag_get(node, tag, offset);
return root_tag_get(root, tag);
}
/*
* IDR users want to be able to store NULL in the tree, so if the slot isn't
* free, don't adjust the count, even if it's transitioning between NULL and
* non-NULL. For the IDA, we mark slots as being IDR_FREE while they still
* have empty bits, but it only stores NULL in slots when they're being
* deleted.
*/
static int calculate_count(struct radix_tree_root *root,
struct radix_tree_node *node, void __rcu **slot,
void *item, void *old)
{
if (is_idr(root)) {
unsigned offset = get_slot_offset(node, slot);
bool free = node_tag_get(root, node, IDR_FREE, offset);
if (!free)
return 0;
if (!old)
return 1;
}
return !!item - !!old;
}
/**
* __radix_tree_replace - replace item in a slot
* @root: radix tree root
* @node: pointer to tree node
* @slot: pointer to slot in @node
* @item: new item to store in the slot.
*
* For use with __radix_tree_lookup(). Caller must hold tree write locked
* across slot lookup and replacement.
*/
void __radix_tree_replace(struct radix_tree_root *root,
struct radix_tree_node *node,
void __rcu **slot, void *item)
{
void *old = rcu_dereference_raw(*slot);
int values = !!xa_is_value(item) - !!xa_is_value(old);
int count = calculate_count(root, node, slot, item, old);
/*
* This function supports replacing value entries and
* deleting entries, but that needs accounting against the
* node unless the slot is root->xa_head.
*/
WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) &&
(count || values));
replace_slot(slot, item, node, count, values);
if (!node)
return;
delete_node(root, node);
}
/**
* radix_tree_replace_slot - replace item in a slot
* @root: radix tree root
* @slot: pointer to slot
* @item: new item to store in the slot.
*
* For use with radix_tree_lookup_slot() and
* radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked
* across slot lookup and replacement.
*
* NOTE: This cannot be used to switch between non-entries (empty slots),
* regular entries, and value entries, as that requires accounting
* inside the radix tree node. When switching from one type of entry or
* deleting, use __radix_tree_lookup() and __radix_tree_replace() or
* radix_tree_iter_replace().
*/
void radix_tree_replace_slot(struct radix_tree_root *root,
void __rcu **slot, void *item)
{
__radix_tree_replace(root, NULL, slot, item);
}
EXPORT_SYMBOL(radix_tree_replace_slot);
/**
* radix_tree_iter_replace - replace item in a slot
* @root: radix tree root
* @iter: iterator state
* @slot: pointer to slot
* @item: new item to store in the slot.
*
* For use with radix_tree_for_each_slot().
* Caller must hold tree write locked.
*/
void radix_tree_iter_replace(struct radix_tree_root *root,
const struct radix_tree_iter *iter,
void __rcu **slot, void *item)
{
__radix_tree_replace(root, iter->node, slot, item);
}
static void node_tag_set(struct radix_tree_root *root,
struct radix_tree_node *node,
unsigned int tag, unsigned int offset)
{
while (node) {
if (tag_get(node, tag, offset))
return;
tag_set(node, tag, offset);
offset = node->offset;
node = node->parent;
}
if (!root_tag_get(root, tag))
root_tag_set(root, tag);
}
/**
* radix_tree_tag_set - set a tag on a radix tree node
* @root: radix tree root
* @index: index key
* @tag: tag index
*
* Set the search tag (which must be < RADIX_TREE_MAX_TAGS)
* corresponding to @index in the radix tree. From
* the root all the way down to the leaf node.
*
* Returns the address of the tagged item. Setting a tag on a not-present
* item is a bug.
*/
void *radix_tree_tag_set(struct radix_tree_root *root,
unsigned long index, unsigned int tag)
{
struct radix_tree_node *node, *parent;
unsigned long maxindex;
radix_tree_load_root(root, &node, &maxindex);
BUG_ON(index > maxindex);
while (radix_tree_is_internal_node(node)) {
unsigned offset;
parent = entry_to_node(node);
offset = radix_tree_descend(parent, &node, index);
BUG_ON(!node);
if (!tag_get(parent, tag, offset))
tag_set(parent, tag, offset);
}
/* set the root's tag bit */
if (!root_tag_get(root, tag))
root_tag_set(root, tag);
return node;
}
EXPORT_SYMBOL(radix_tree_tag_set);
static void node_tag_clear(struct radix_tree_root *root,
struct radix_tree_node *node,
unsigned int tag, unsigned int offset)
{
while (node) {
if (!tag_get(node, tag, offset))
return;
tag_clear(node, tag, offset);
if (any_tag_set(node, tag))
return;
offset = node->offset;
node = node->parent;
}
/* clear the root's tag bit */
if (root_tag_get(root, tag))
root_tag_clear(root, tag);
}
/**
* radix_tree_tag_clear - clear a tag on a radix tree node
* @root: radix tree root
* @index: index key
* @tag: tag index
*
* Clear the search tag (which must be < RADIX_TREE_MAX_TAGS)
* corresponding to @index in the radix tree. If this causes
* the leaf node to have no tags set then clear the tag in the
* next-to-leaf node, etc.
*
* Returns the address of the tagged item on success, else NULL. ie:
* has the same return value and semantics as radix_tree_lookup().
*/
void *radix_tree_tag_clear(struct radix_tree_root *root,
unsigned long index, unsigned int tag)
{
struct radix_tree_node *node, *parent;
unsigned long maxindex;
int offset = 0;
radix_tree_load_root(root, &node, &maxindex);
if (index > maxindex)
return NULL;
parent = NULL;
while (radix_tree_is_internal_node(node)) {
parent = entry_to_node(node);
offset = radix_tree_descend(parent, &node, index);
}
if (node)
node_tag_clear(root, parent, tag, offset);
return node;
}
EXPORT_SYMBOL(radix_tree_tag_clear);
/**
* radix_tree_iter_tag_clear - clear a tag on the current iterator entry
* @root: radix tree root
* @iter: iterator state
* @tag: tag to clear
*/
void radix_tree_iter_tag_clear(struct radix_tree_root *root,
const struct radix_tree_iter *iter, unsigned int tag)
{
node_tag_clear(root, iter->node, tag, iter_offset(iter));
}
/**
* radix_tree_tag_get - get a tag on a radix tree node
* @root: radix tree root
* @index: index key
* @tag: tag index (< RADIX_TREE_MAX_TAGS)
*
* Return values:
*
* 0: tag not present or not set
* 1: tag set
*
* Note that the return value of this function may not be relied on, even if
* the RCU lock is held, unless tag modification and node deletion are excluded
* from concurrency.
*/
int radix_tree_tag_get(const struct radix_tree_root *root,
unsigned long index, unsigned int tag)
{
struct radix_tree_node *node, *parent;
unsigned long maxindex;
if (!root_tag_get(root, tag))
return 0;
radix_tree_load_root(root, &node, &maxindex);
if (index > maxindex)
return 0;
while (radix_tree_is_internal_node(node)) {
unsigned offset;
parent = entry_to_node(node);
offset = radix_tree_descend(parent, &node, index);
if (!tag_get(parent, tag, offset))
return 0;
if (node == RADIX_TREE_RETRY)
break;
}
return 1;
}
EXPORT_SYMBOL(radix_tree_tag_get);
/* Construct iter->tags bit-mask from node->tags[tag] array */
static void set_iter_tags(struct radix_tree_iter *iter,
struct radix_tree_node *node, unsigned offset,
unsigned tag)
{
unsigned tag_long = offset / BITS_PER_LONG;
unsigned tag_bit = offset % BITS_PER_LONG; if (!node) {
iter->tags = 1;
return;
}
iter->tags = node->tags[tag][tag_long] >> tag_bit;
/* This never happens if RADIX_TREE_TAG_LONGS == 1 */
if (tag_long < RADIX_TREE_TAG_LONGS - 1) {
/* Pick tags from next element */
if (tag_bit)
iter->tags |= node->tags[tag][tag_long + 1] <<
(BITS_PER_LONG - tag_bit);
/* Clip chunk size, here only BITS_PER_LONG tags */
iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG);
}
}
void __rcu **radix_tree_iter_resume(void __rcu **slot,
struct radix_tree_iter *iter)
{
iter->index = __radix_tree_iter_add(iter, 1);
iter->next_index = iter->index;
iter->tags = 0;
return NULL;
}
EXPORT_SYMBOL(radix_tree_iter_resume);
/**
* radix_tree_next_chunk - find next chunk of slots for iteration
*
* @root: radix tree root
* @iter: iterator state
* @flags: RADIX_TREE_ITER_* flags and tag index
* Returns: pointer to chunk first slot, or NULL if iteration is over
*/
void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
struct radix_tree_iter *iter, unsigned flags)
{
unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
struct radix_tree_node *node, *child;
unsigned long index, offset, maxindex;
if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
return NULL;
/*
* Catch next_index overflow after ~0UL. iter->index never overflows
* during iterating; it can be zero only at the beginning.
* And we cannot overflow iter->next_index in a single step,
* because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
*
* This condition also used by radix_tree_next_slot() to stop
* contiguous iterating, and forbid switching to the next chunk.
*/
index = iter->next_index;
if (!index && iter->index)
return NULL;
restart:
radix_tree_load_root(root, &child, &maxindex); if (index > maxindex)
return NULL;
if (!child)
return NULL;
if (!radix_tree_is_internal_node(child)) {
/* Single-slot tree */
iter->index = index;
iter->next_index = maxindex + 1;
iter->tags = 1;
iter->node = NULL;
return (void __rcu **)&root->xa_head;
}
do {
node = entry_to_node(child);
offset = radix_tree_descend(node, &child, index);
if ((flags & RADIX_TREE_ITER_TAGGED) ?
!tag_get(node, tag, offset) : !child) {
/* Hole detected */
if (flags & RADIX_TREE_ITER_CONTIG)
return NULL;
if (flags & RADIX_TREE_ITER_TAGGED)
offset = radix_tree_find_next_bit(node, tag,
offset + 1);
else
while (++offset < RADIX_TREE_MAP_SIZE) {
void *slot = rcu_dereference_raw(
node->slots[offset]);
if (slot)
break;
}
index &= ~node_maxindex(node);
index += offset << node->shift;
/* Overflow after ~0UL */
if (!index)
return NULL;
if (offset == RADIX_TREE_MAP_SIZE)
goto restart;
child = rcu_dereference_raw(node->slots[offset]);
}
if (!child)
goto restart;
if (child == RADIX_TREE_RETRY)
break;
} while (node->shift && radix_tree_is_internal_node(child));
/* Update the iterator state */
iter->index = (index &~ node_maxindex(node)) | offset;
iter->next_index = (index | node_maxindex(node)) + 1;
iter->node = node;
if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag);
return node->slots + offset;
}
EXPORT_SYMBOL(radix_tree_next_chunk);
/**
* radix_tree_gang_lookup - perform multiple lookup on a radix tree
* @root: radix tree root
* @results: where the results of the lookup are placed
* @first_index: start the lookup from this key
* @max_items: place up to this many items at *results
*
* Performs an index-ascending scan of the tree for present items. Places
* them at *@results and returns the number of items which were placed at
* *@results.
*
* The implementation is naive.
*
* Like radix_tree_lookup, radix_tree_gang_lookup may be called under
* rcu_read_lock. In this case, rather than the returned results being
* an atomic snapshot of the tree at a single point in time, the
* semantics of an RCU protected gang lookup are as though multiple
* radix_tree_lookups have been issued in individual locks, and results
* stored in 'results'.
*/
unsigned int
radix_tree_gang_lookup(const struct radix_tree_root *root, void **results,
unsigned long first_index, unsigned int max_items)
{
struct radix_tree_iter iter;
void __rcu **slot;
unsigned int ret = 0;
if (unlikely(!max_items))
return 0;
radix_tree_for_each_slot(slot, root, &iter, first_index) {
results[ret] = rcu_dereference_raw(*slot);
if (!results[ret])
continue;
if (radix_tree_is_internal_node(results[ret])) {
slot = radix_tree_iter_retry(&iter);
continue;
}
if (++ret == max_items)
break;
}
return ret;
}
EXPORT_SYMBOL(radix_tree_gang_lookup);
/**
* radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree
* based on a tag
* @root: radix tree root
* @results: where the results of the lookup are placed
* @first_index: start the lookup from this key
* @max_items: place up to this many items at *results
* @tag: the tag index (< RADIX_TREE_MAX_TAGS)
*
* Performs an index-ascending scan of the tree for present items which
* have the tag indexed by @tag set. Places the items at *@results and
* returns the number of items which were placed at *@results.
*/
unsigned int
radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results,
unsigned long first_index, unsigned int max_items,
unsigned int tag)
{
struct radix_tree_iter iter;
void __rcu **slot;
unsigned int ret = 0;
if (unlikely(!max_items))
return 0;
radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
results[ret] = rcu_dereference_raw(*slot);
if (!results[ret])
continue;
if (radix_tree_is_internal_node(results[ret])) {
slot = radix_tree_iter_retry(&iter);
continue;
}
if (++ret == max_items)
break;
}
return ret;
}
EXPORT_SYMBOL(radix_tree_gang_lookup_tag);
/**
* radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a
* radix tree based on a tag
* @root: radix tree root
* @results: where the results of the lookup are placed
* @first_index: start the lookup from this key
* @max_items: place up to this many items at *results
* @tag: the tag index (< RADIX_TREE_MAX_TAGS)
*
* Performs an index-ascending scan of the tree for present items which
* have the tag indexed by @tag set. Places the slots at *@results and
* returns the number of slots which were placed at *@results.
*/
unsigned int
radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root,
void __rcu ***results, unsigned long first_index,
unsigned int max_items, unsigned int tag)
{
struct radix_tree_iter iter;
void __rcu **slot;
unsigned int ret = 0;
if (unlikely(!max_items))
return 0;
radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
results[ret] = slot;
if (++ret == max_items)
break;
}
return ret;
}
EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
static bool __radix_tree_delete(struct radix_tree_root *root,
struct radix_tree_node *node, void __rcu **slot)
{
void *old = rcu_dereference_raw(*slot);
int values = xa_is_value(old) ? -1 : 0;
unsigned offset = get_slot_offset(node, slot);
int tag;
if (is_idr(root))
node_tag_set(root, node, IDR_FREE, offset);
else
for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
node_tag_clear(root, node, tag, offset);
replace_slot(slot, NULL, node, -1, values);
return node && delete_node(root, node);
}
/**
* radix_tree_iter_delete - delete the entry at this iterator position
* @root: radix tree root
* @iter: iterator state
* @slot: pointer to slot
*
* Delete the entry at the position currently pointed to by the iterator.
* This may result in the current node being freed; if it is, the iterator
* is advanced so that it will not reference the freed memory. This
* function may be called without any locking if there are no other threads
* which can access this tree.
*/
void radix_tree_iter_delete(struct radix_tree_root *root,
struct radix_tree_iter *iter, void __rcu **slot)
{
if (__radix_tree_delete(root, iter->node, slot))
iter->index = iter->next_index;
}
EXPORT_SYMBOL(radix_tree_iter_delete);
/**
* radix_tree_delete_item - delete an item from a radix tree
* @root: radix tree root
* @index: index key
* @item: expected item
*
* Remove @item at @index from the radix tree rooted at @root.
*
* Return: the deleted entry, or %NULL if it was not present
* or the entry at the given @index was not @item.
*/
void *radix_tree_delete_item(struct radix_tree_root *root,
unsigned long index, void *item)
{
struct radix_tree_node *node = NULL;
void __rcu **slot = NULL;
void *entry;
entry = __radix_tree_lookup(root, index, &node, &slot);
if (!slot)
return NULL;
if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE,
get_slot_offset(node, slot))))
return NULL;
if (item && entry != item)
return NULL;
__radix_tree_delete(root, node, slot);
return entry;
}
EXPORT_SYMBOL(radix_tree_delete_item);
/**
* radix_tree_delete - delete an entry from a radix tree
* @root: radix tree root
* @index: index key
*
* Remove the entry at @index from the radix tree rooted at @root.
*
* Return: The deleted entry, or %NULL if it was not present.
*/
void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
{
return radix_tree_delete_item(root, index, NULL);
}
EXPORT_SYMBOL(radix_tree_delete);
/**
* radix_tree_tagged - test whether any items in the tree are tagged
* @root: radix tree root
* @tag: tag to test
*/
int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag)
{
return root_tag_get(root, tag);
}
EXPORT_SYMBOL(radix_tree_tagged);
/**
* idr_preload - preload for idr_alloc()
* @gfp_mask: allocation mask to use for preloading
*
* Preallocate memory to use for the next call to idr_alloc(). This function
* returns with preemption disabled. It will be enabled by idr_preload_end().
*/
void idr_preload(gfp_t gfp_mask)
{
if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
local_lock(&radix_tree_preloads.lock);
}
EXPORT_SYMBOL(idr_preload);
void __rcu **idr_get_free(struct radix_tree_root *root,
struct radix_tree_iter *iter, gfp_t gfp,
unsigned long max)
{
struct radix_tree_node *node = NULL, *child;
void __rcu **slot = (void __rcu **)&root->xa_head;
unsigned long maxindex, start = iter->next_index;
unsigned int shift, offset = 0;
grow:
shift = radix_tree_load_root(root, &child, &maxindex);
if (!radix_tree_tagged(root, IDR_FREE))
start = max(start, maxindex + 1);
if (start > max)
return ERR_PTR(-ENOSPC);
if (start > maxindex) {
int error = radix_tree_extend(root, gfp, start, shift);
if (error < 0)
return ERR_PTR(error);
shift = error;
child = rcu_dereference_raw(root->xa_head);
}
if (start == 0 && shift == 0)
shift = RADIX_TREE_MAP_SHIFT;
while (shift) {
shift -= RADIX_TREE_MAP_SHIFT;
if (child == NULL) {
/* Have to add a child node. */
child = radix_tree_node_alloc(gfp, node, root, shift,
offset, 0, 0);
if (!child)
return ERR_PTR(-ENOMEM);
all_tag_set(child, IDR_FREE);
rcu_assign_pointer(*slot, node_to_entry(child));
if (node)
node->count++;
} else if (!radix_tree_is_internal_node(child))
break;
node = entry_to_node(child);
offset = radix_tree_descend(node, &child, start);
if (!tag_get(node, IDR_FREE, offset)) {
offset = radix_tree_find_next_bit(node, IDR_FREE,
offset + 1);
start = next_index(start, node, offset);
if (start > max || start == 0)
return ERR_PTR(-ENOSPC);
while (offset == RADIX_TREE_MAP_SIZE) {
offset = node->offset + 1;
node = node->parent;
if (!node)
goto grow;
shift = node->shift;
}
child = rcu_dereference_raw(node->slots[offset]);
}
slot = &node->slots[offset];
}
iter->index = start;
if (node)
iter->next_index = 1 + min(max, (start | node_maxindex(node)));
else
iter->next_index = 1;
iter->node = node;
set_iter_tags(iter, node, offset, IDR_FREE);
return slot;
}
/**
* idr_destroy - release all internal memory from an IDR
* @idr: idr handle
*
* After this function is called, the IDR is empty, and may be reused or
* the data structure containing it may be freed.
*
* A typical clean-up sequence for objects stored in an idr tree will use
* idr_for_each() to free all objects, if necessary, then idr_destroy() to
* free the memory used to keep track of those objects.
*/
void idr_destroy(struct idr *idr)
{
struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head);
if (radix_tree_is_internal_node(node))
radix_tree_free_nodes(node);
idr->idr_rt.xa_head = NULL;
root_tag_set(&idr->idr_rt, IDR_FREE);
}
EXPORT_SYMBOL(idr_destroy);
static void
radix_tree_node_ctor(void *arg)
{
struct radix_tree_node *node = arg;
memset(node, 0, sizeof(*node));
INIT_LIST_HEAD(&node->private_list);
}
static int radix_tree_cpu_dead(unsigned int cpu)
{
struct radix_tree_preload *rtp;
struct radix_tree_node *node;
/* Free per-cpu pool of preloaded nodes */
rtp = &per_cpu(radix_tree_preloads, cpu);
while (rtp->nr) {
node = rtp->nodes;
rtp->nodes = node->parent;
kmem_cache_free(radix_tree_node_cachep, node);
rtp->nr--;
}
return 0;
}
void __init radix_tree_init(void)
{
int ret;
BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32);
BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK);
BUILD_BUG_ON(XA_CHUNK_SIZE > 255);
radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
sizeof(struct radix_tree_node), 0,
SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
radix_tree_node_ctor);
ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead",
NULL, radix_tree_cpu_dead);
WARN_ON(ret < 0);
}
// SPDX-License-Identifier: GPL-2.0+
/*
* Maple Tree implementation
* Copyright (c) 2018-2022 Oracle Corporation
* Authors: Liam R. Howlett <Liam.Howlett@oracle.com>
* Matthew Wilcox <willy@infradead.org>
* Copyright (c) 2023 ByteDance
* Author: Peng Zhang <zhangpeng.00@bytedance.com>
*/
/*
* DOC: Interesting implementation details of the Maple Tree
*
* Each node type has a number of slots for entries and a number of slots for
* pivots. In the case of dense nodes, the pivots are implied by the position
* and are simply the slot index + the minimum of the node.
*
* In regular B-Tree terms, pivots are called keys. The term pivot is used to
* indicate that the tree is specifying ranges. Pivots may appear in the
* subtree with an entry attached to the value whereas keys are unique to a
* specific position of a B-tree. Pivot values are inclusive of the slot with
* the same index.
*
*
* The following illustrates the layout of a range64 nodes slots and pivots.
*
*
* Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 |
* ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬
* │ │ │ │ │ │ │ │ └─ Implied maximum
* │ │ │ │ │ │ │ └─ Pivot 14
* │ │ │ │ │ │ └─ Pivot 13
* │ │ │ │ │ └─ Pivot 12
* │ │ │ │ └─ Pivot 11
* │ │ │ └─ Pivot 2
* │ │ └─ Pivot 1
* │ └─ Pivot 0
* └─ Implied minimum
*
* Slot contents:
* Internal (non-leaf) nodes contain pointers to other nodes.
* Leaf nodes contain entries.
*
* The location of interest is often referred to as an offset. All offsets have
* a slot, but the last offset has an implied pivot from the node above (or
* UINT_MAX for the root node.
*
* Ranges complicate certain write activities. When modifying any of
* the B-tree variants, it is known that one entry will either be added or
* deleted. When modifying the Maple Tree, one store operation may overwrite
* the entire data set, or one half of the tree, or the middle half of the tree.
*
*/
#include <linux/maple_tree.h>
#include <linux/xarray.h>
#include <linux/types.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/limits.h>
#include <asm/barrier.h>
#define CREATE_TRACE_POINTS
#include <trace/events/maple_tree.h>
/*
* Kernel pointer hashing renders much of the maple tree dump useless as tagged
* pointers get hashed to arbitrary values.
*
* If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is
* permissible to bypass this. Otherwise remain cautious and retain the hashing.
*
* Userland doesn't know about %px so also use %p there.
*/
#if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE)
#define PTR_FMT "%px"
#else
#define PTR_FMT "%p"
#endif
#define MA_ROOT_PARENT 1
/*
* Maple state flags
* * MA_STATE_BULK - Bulk insert mode
* * MA_STATE_REBALANCE - Indicate a rebalance during bulk insert
* * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation
*/
#define MA_STATE_BULK 1
#define MA_STATE_REBALANCE 2
#define MA_STATE_PREALLOC 4
#define ma_parent_ptr(x) ((struct maple_pnode *)(x))
#define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT)
#define ma_mnode_ptr(x) ((struct maple_node *)(x))
#define ma_enode_ptr(x) ((struct maple_enode *)(x))
static struct kmem_cache *maple_node_cache;
#ifdef CONFIG_DEBUG_MAPLE_TREE
static const unsigned long mt_max[] = {
[maple_dense] = MAPLE_NODE_SLOTS,
[maple_leaf_64] = ULONG_MAX,
[maple_range_64] = ULONG_MAX,
[maple_arange_64] = ULONG_MAX,
};
#define mt_node_max(x) mt_max[mte_node_type(x)]
#endif
static const unsigned char mt_slots[] = {
[maple_dense] = MAPLE_NODE_SLOTS,
[maple_leaf_64] = MAPLE_RANGE64_SLOTS,
[maple_range_64] = MAPLE_RANGE64_SLOTS,
[maple_arange_64] = MAPLE_ARANGE64_SLOTS,
};
#define mt_slot_count(x) mt_slots[mte_node_type(x)]
static const unsigned char mt_pivots[] = {
[maple_dense] = 0,
[maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1,
[maple_range_64] = MAPLE_RANGE64_SLOTS - 1,
[maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1,
};
#define mt_pivot_count(x) mt_pivots[mte_node_type(x)]
static const unsigned char mt_min_slots[] = {
[maple_dense] = MAPLE_NODE_SLOTS / 2,
[maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2,
[maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2,
[maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1,
};
#define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)]
#define MAPLE_BIG_NODE_SLOTS (MAPLE_RANGE64_SLOTS * 2 + 2)
#define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1)
struct maple_big_node {
unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1];
union {
struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS];
struct {
unsigned long padding[MAPLE_BIG_NODE_GAPS];
unsigned long gap[MAPLE_BIG_NODE_GAPS];
};
};
unsigned char b_end;
enum maple_type type;
};
/*
* The maple_subtree_state is used to build a tree to replace a segment of an
* existing tree in a more atomic way. Any walkers of the older tree will hit a
* dead node and restart on updates.
*/
struct maple_subtree_state {
struct ma_state *orig_l; /* Original left side of subtree */
struct ma_state *orig_r; /* Original right side of subtree */
struct ma_state *l; /* New left side of subtree */
struct ma_state *m; /* New middle of subtree (rare) */
struct ma_state *r; /* New right side of subtree */
struct ma_topiary *free; /* nodes to be freed */
struct ma_topiary *destroy; /* Nodes to be destroyed (walked and freed) */
struct maple_big_node *bn;
};
#ifdef CONFIG_KASAN_STACK
/* Prevent mas_wr_bnode() from exceeding the stack frame limit */
#define noinline_for_kasan noinline_for_stack
#else
#define noinline_for_kasan inline
#endif
/* Functions */
static inline struct maple_node *mt_alloc_one(gfp_t gfp)
{
return kmem_cache_alloc(maple_node_cache, gfp);
}
static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes)
{
return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes);
}
static inline void mt_free_one(struct maple_node *node)
{
kmem_cache_free(maple_node_cache, node);
}
static inline void mt_free_bulk(size_t size, void __rcu **nodes)
{
kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes);
}
static void mt_free_rcu(struct rcu_head *head)
{
struct maple_node *node = container_of(head, struct maple_node, rcu);
kmem_cache_free(maple_node_cache, node);
}
/*
* ma_free_rcu() - Use rcu callback to free a maple node
* @node: The node to free
*
* The maple tree uses the parent pointer to indicate this node is no longer in
* use and will be freed.
*/
static void ma_free_rcu(struct maple_node *node)
{
WARN_ON(node->parent != ma_parent_ptr(node));
call_rcu(&node->rcu, mt_free_rcu);
}
static void mas_set_height(struct ma_state *mas)
{
unsigned int new_flags = mas->tree->ma_flags;
new_flags &= ~MT_FLAGS_HEIGHT_MASK;
MAS_BUG_ON(mas, mas->depth > MAPLE_HEIGHT_MAX);
new_flags |= mas->depth << MT_FLAGS_HEIGHT_OFFSET;
mas->tree->ma_flags = new_flags;
}
static unsigned int mas_mt_height(struct ma_state *mas)
{
return mt_height(mas->tree);
}
static inline unsigned int mt_attr(struct maple_tree *mt)
{
return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK;
}
static __always_inline enum maple_type mte_node_type(
const struct maple_enode *entry)
{
return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) &
MAPLE_NODE_TYPE_MASK;
}
static __always_inline bool ma_is_dense(const enum maple_type type)
{
return type < maple_leaf_64;
}
static __always_inline bool ma_is_leaf(const enum maple_type type)
{
return type < maple_range_64;
}
static __always_inline bool mte_is_leaf(const struct maple_enode *entry)
{
return ma_is_leaf(mte_node_type(entry));
}
/*
* We also reserve values with the bottom two bits set to '10' which are
* below 4096
*/
static __always_inline bool mt_is_reserved(const void *entry)
{
return ((unsigned long)entry < MAPLE_RESERVED_RANGE) &&
xa_is_internal(entry);
}
static __always_inline void mas_set_err(struct ma_state *mas, long err)
{
mas->node = MA_ERROR(err);
mas->status = ma_error;
}
static __always_inline bool mas_is_ptr(const struct ma_state *mas)
{
return mas->status == ma_root;
}
static __always_inline bool mas_is_start(const struct ma_state *mas)
{
return mas->status == ma_start;
}
static __always_inline bool mas_is_none(const struct ma_state *mas)
{
return mas->status == ma_none;
}
static __always_inline bool mas_is_paused(const struct ma_state *mas)
{
return mas->status == ma_pause;
}
static __always_inline bool mas_is_overflow(struct ma_state *mas)
{
return mas->status == ma_overflow;
}
static inline bool mas_is_underflow(struct ma_state *mas)
{
return mas->status == ma_underflow;
}
static __always_inline struct maple_node *mte_to_node(
const struct maple_enode *entry)
{
return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK);
}
/*
* mte_to_mat() - Convert a maple encoded node to a maple topiary node.
* @entry: The maple encoded node
*
* Return: a maple topiary pointer
*/
static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry)
{
return (struct maple_topiary *)
((unsigned long)entry & ~MAPLE_NODE_MASK);
}
/*
* mas_mn() - Get the maple state node.
* @mas: The maple state
*
* Return: the maple node (not encoded - bare pointer).
*/
static inline struct maple_node *mas_mn(const struct ma_state *mas)
{
return mte_to_node(mas->node);
}
/*
* mte_set_node_dead() - Set a maple encoded node as dead.
* @mn: The maple encoded node.
*/
static inline void mte_set_node_dead(struct maple_enode *mn)
{
mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn));
smp_wmb(); /* Needed for RCU */
}
/* Bit 1 indicates the root is a node */
#define MAPLE_ROOT_NODE 0x02
/* maple_type stored bit 3-6 */
#define MAPLE_ENODE_TYPE_SHIFT 0x03
/* Bit 2 means a NULL somewhere below */
#define MAPLE_ENODE_NULL 0x04
static inline struct maple_enode *mt_mk_node(const struct maple_node *node,
enum maple_type type)
{
return (void *)((unsigned long)node |
(type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL);
}
static inline void *mte_mk_root(const struct maple_enode *node)
{
return (void *)((unsigned long)node | MAPLE_ROOT_NODE);
}
static inline void *mte_safe_root(const struct maple_enode *node)
{
return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE);
}
static inline void __maybe_unused *mte_set_full(const struct maple_enode *node)
{
return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL);
}
static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node)
{
return (void *)((unsigned long)node | MAPLE_ENODE_NULL);
}
static inline bool __maybe_unused mte_has_null(const struct maple_enode *node)
{
return (unsigned long)node & MAPLE_ENODE_NULL;
}
static __always_inline bool ma_is_root(struct maple_node *node)
{
return ((unsigned long)node->parent & MA_ROOT_PARENT);
}
static __always_inline bool mte_is_root(const struct maple_enode *node)
{
return ma_is_root(mte_to_node(node));
}
static inline bool mas_is_root_limits(const struct ma_state *mas)
{
return !mas->min && mas->max == ULONG_MAX;
}
static __always_inline bool mt_is_alloc(struct maple_tree *mt)
{
return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE);
}
/*
* The Parent Pointer
* Excluding root, the parent pointer is 256B aligned like all other tree nodes.
* When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16
* bit values need an extra bit to store the offset. This extra bit comes from
* a reuse of the last bit in the node type. This is possible by using bit 1 to
* indicate if bit 2 is part of the type or the slot.
*
* Note types:
* 0x??1 = Root
* 0x?00 = 16 bit nodes
* 0x010 = 32 bit nodes
* 0x110 = 64 bit nodes
*
* Slot size and alignment
* 0b??1 : Root
* 0b?00 : 16 bit values, type in 0-1, slot in 2-7
* 0b010 : 32 bit values, type in 0-2, slot in 3-7
* 0b110 : 64 bit values, type in 0-2, slot in 3-7
*/
#define MAPLE_PARENT_ROOT 0x01
#define MAPLE_PARENT_SLOT_SHIFT 0x03
#define MAPLE_PARENT_SLOT_MASK 0xF8
#define MAPLE_PARENT_16B_SLOT_SHIFT 0x02
#define MAPLE_PARENT_16B_SLOT_MASK 0xFC
#define MAPLE_PARENT_RANGE64 0x06
#define MAPLE_PARENT_RANGE32 0x04
#define MAPLE_PARENT_NOT_RANGE16 0x02
/*
* mte_parent_shift() - Get the parent shift for the slot storage.
* @parent: The parent pointer cast as an unsigned long
* Return: The shift into that pointer to the star to of the slot
*/
static inline unsigned long mte_parent_shift(unsigned long parent)
{
/* Note bit 1 == 0 means 16B */
if (likely(parent & MAPLE_PARENT_NOT_RANGE16))
return MAPLE_PARENT_SLOT_SHIFT;
return MAPLE_PARENT_16B_SLOT_SHIFT;
}
/*
* mte_parent_slot_mask() - Get the slot mask for the parent.
* @parent: The parent pointer cast as an unsigned long.
* Return: The slot mask for that parent.
*/
static inline unsigned long mte_parent_slot_mask(unsigned long parent)
{
/* Note bit 1 == 0 means 16B */
if (likely(parent & MAPLE_PARENT_NOT_RANGE16))
return MAPLE_PARENT_SLOT_MASK;
return MAPLE_PARENT_16B_SLOT_MASK;
}
/*
* mas_parent_type() - Return the maple_type of the parent from the stored
* parent type.
* @mas: The maple state
* @enode: The maple_enode to extract the parent's enum
* Return: The node->parent maple_type
*/
static inline
enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode)
{
unsigned long p_type;
p_type = (unsigned long)mte_to_node(enode)->parent;
if (WARN_ON(p_type & MAPLE_PARENT_ROOT))
return 0;
p_type &= MAPLE_NODE_MASK;
p_type &= ~mte_parent_slot_mask(p_type);
switch (p_type) {
case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */
if (mt_is_alloc(mas->tree))
return maple_arange_64;
return maple_range_64;
}
return 0;
}
/*
* mas_set_parent() - Set the parent node and encode the slot
* @mas: The maple state
* @enode: The encoded maple node.
* @parent: The encoded maple node that is the parent of @enode.
* @slot: The slot that @enode resides in @parent.
*
* Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the
* parent type.
*/
static inline
void mas_set_parent(struct ma_state *mas, struct maple_enode *enode,
const struct maple_enode *parent, unsigned char slot)
{
unsigned long val = (unsigned long)parent;
unsigned long shift;
unsigned long type;
enum maple_type p_type = mte_node_type(parent);
MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64);
switch (p_type) {
case maple_range_64:
case maple_arange_64:
shift = MAPLE_PARENT_SLOT_SHIFT;
type = MAPLE_PARENT_RANGE64;
break;
default:
case maple_dense:
case maple_leaf_64:
shift = type = 0;
break;
}
val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */
val |= (slot << shift) | type;
mte_to_node(enode)->parent = ma_parent_ptr(val);
}
/*
* mte_parent_slot() - get the parent slot of @enode.
* @enode: The encoded maple node.
*
* Return: The slot in the parent node where @enode resides.
*/
static __always_inline
unsigned int mte_parent_slot(const struct maple_enode *enode)
{
unsigned long val = (unsigned long)mte_to_node(enode)->parent;
if (unlikely(val & MA_ROOT_PARENT))
return 0;
/*
* Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost
* by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT
*/
return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val);
}
/*
* mte_parent() - Get the parent of @node.
* @enode: The encoded maple node.
*
* Return: The parent maple node.
*/
static __always_inline
struct maple_node *mte_parent(const struct maple_enode *enode)
{
return (void *)((unsigned long)
(mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK);
}
/*
* ma_dead_node() - check if the @enode is dead.
* @enode: The encoded maple node
*
* Return: true if dead, false otherwise.
*/
static __always_inline bool ma_dead_node(const struct maple_node *node)
{
struct maple_node *parent;
/* Do not reorder reads from the node prior to the parent check */
smp_rmb();
parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK);
return (parent == node);
}
/*
* mte_dead_node() - check if the @enode is dead.
* @enode: The encoded maple node
*
* Return: true if dead, false otherwise.
*/
static __always_inline bool mte_dead_node(const struct maple_enode *enode)
{
struct maple_node *node;
node = mte_to_node(enode);
return ma_dead_node(node);
}
/*
* mas_allocated() - Get the number of nodes allocated in a maple state.
* @mas: The maple state
*
* The ma_state alloc member is overloaded to hold a pointer to the first
* allocated node or to the number of requested nodes to allocate. If bit 0 is
* set, then the alloc contains the number of requested nodes. If there is an
* allocated node, then the total allocated nodes is in that node.
*
* Return: The total number of nodes allocated
*/
static inline unsigned long mas_allocated(const struct ma_state *mas)
{
if (!mas->alloc || ((unsigned long)mas->alloc & 0x1))
return 0;
return mas->alloc->total;
}
/*
* mas_set_alloc_req() - Set the requested number of allocations.
* @mas: the maple state
* @count: the number of allocations.
*
* The requested number of allocations is either in the first allocated node,
* located in @mas->alloc->request_count, or directly in @mas->alloc if there is
* no allocated node. Set the request either in the node or do the necessary
* encoding to store in @mas->alloc directly.
*/
static inline void mas_set_alloc_req(struct ma_state *mas, unsigned long count)
{
if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) {
if (!count)
mas->alloc = NULL;
else
mas->alloc = (struct maple_alloc *)(((count) << 1U) | 1U);
return;
}
mas->alloc->request_count = count;
}
/*
* mas_alloc_req() - get the requested number of allocations.
* @mas: The maple state
*
* The alloc count is either stored directly in @mas, or in
* @mas->alloc->request_count if there is at least one node allocated. Decode
* the request count if it's stored directly in @mas->alloc.
*
* Return: The allocation request count.
*/
static inline unsigned int mas_alloc_req(const struct ma_state *mas)
{
if ((unsigned long)mas->alloc & 0x1)
return (unsigned long)(mas->alloc) >> 1; else if (mas->alloc)
return mas->alloc->request_count;
return 0;
}
/*
* ma_pivots() - Get a pointer to the maple node pivots.
* @node: the maple node
* @type: the node type
*
* In the event of a dead node, this array may be %NULL
*
* Return: A pointer to the maple node pivots
*/
static inline unsigned long *ma_pivots(struct maple_node *node,
enum maple_type type)
{
switch (type) {
case maple_arange_64:
return node->ma64.pivot;
case maple_range_64:
case maple_leaf_64:
return node->mr64.pivot;
case maple_dense:
return NULL;
}
return NULL;
}
/*
* ma_gaps() - Get a pointer to the maple node gaps.
* @node: the maple node
* @type: the node type
*
* Return: A pointer to the maple node gaps
*/
static inline unsigned long *ma_gaps(struct maple_node *node,
enum maple_type type)
{
switch (type) {
case maple_arange_64:
return node->ma64.gap;
case maple_range_64:
case maple_leaf_64:
case maple_dense:
return NULL;
}
return NULL;
}
/*
* mas_safe_pivot() - get the pivot at @piv or mas->max.
* @mas: The maple state
* @pivots: The pointer to the maple node pivots
* @piv: The pivot to fetch
* @type: The maple node type
*
* Return: The pivot at @piv within the limit of the @pivots array, @mas->max
* otherwise.
*/
static __always_inline unsigned long
mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots,
unsigned char piv, enum maple_type type)
{
if (piv >= mt_pivots[type])
return mas->max;
return pivots[piv];
}
/*
* mas_safe_min() - Return the minimum for a given offset.
* @mas: The maple state
* @pivots: The pointer to the maple node pivots
* @offset: The offset into the pivot array
*
* Return: The minimum range value that is contained in @offset.
*/
static inline unsigned long
mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset)
{
if (likely(offset)) return pivots[offset - 1] + 1; return mas->min;
}
/*
* mte_set_pivot() - Set a pivot to a value in an encoded maple node.
* @mn: The encoded maple node
* @piv: The pivot offset
* @val: The value of the pivot
*/
static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv,
unsigned long val)
{
struct maple_node *node = mte_to_node(mn);
enum maple_type type = mte_node_type(mn);
BUG_ON(piv >= mt_pivots[type]); switch (type) {
case maple_range_64:
case maple_leaf_64:
node->mr64.pivot[piv] = val;
break;
case maple_arange_64:
node->ma64.pivot[piv] = val;
break;
case maple_dense:
break;
}
}
/*
* ma_slots() - Get a pointer to the maple node slots.
* @mn: The maple node
* @mt: The maple node type
*
* Return: A pointer to the maple node slots
*/
static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt)
{
switch (mt) {
case maple_arange_64:
return mn->ma64.slot;
case maple_range_64:
case maple_leaf_64:
return mn->mr64.slot;
case maple_dense:
return mn->slot;
}
return NULL;
}
static inline bool mt_write_locked(const struct maple_tree *mt)
{
return mt_external_lock(mt) ? mt_write_lock_is_held(mt) :
lockdep_is_held(&mt->ma_lock);
}
static __always_inline bool mt_locked(const struct maple_tree *mt)
{
return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock);
}
static __always_inline void *mt_slot(const struct maple_tree *mt,
void __rcu **slots, unsigned char offset)
{
return rcu_dereference_check(slots[offset], mt_locked(mt));
}
static __always_inline void *mt_slot_locked(struct maple_tree *mt,
void __rcu **slots, unsigned char offset)
{
return rcu_dereference_protected(slots[offset], mt_write_locked(mt));
}
/*
* mas_slot_locked() - Get the slot value when holding the maple tree lock.
* @mas: The maple state
* @slots: The pointer to the slots
* @offset: The offset into the slots array to fetch
*
* Return: The entry stored in @slots at the @offset.
*/
static __always_inline void *mas_slot_locked(struct ma_state *mas,
void __rcu **slots, unsigned char offset)
{
return mt_slot_locked(mas->tree, slots, offset);
}
/*
* mas_slot() - Get the slot value when not holding the maple tree lock.
* @mas: The maple state
* @slots: The pointer to the slots
* @offset: The offset into the slots array to fetch
*
* Return: The entry stored in @slots at the @offset
*/
static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots,
unsigned char offset)
{
return mt_slot(mas->tree, slots, offset);
}
/*
* mas_root() - Get the maple tree root.
* @mas: The maple state.
*
* Return: The pointer to the root of the tree
*/
static __always_inline void *mas_root(struct ma_state *mas)
{
return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree));
}
static inline void *mt_root_locked(struct maple_tree *mt)
{
return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt));
}
/*
* mas_root_locked() - Get the maple tree root when holding the maple tree lock.
* @mas: The maple state.
*
* Return: The pointer to the root of the tree
*/
static inline void *mas_root_locked(struct ma_state *mas)
{
return mt_root_locked(mas->tree);
}
static inline struct maple_metadata *ma_meta(struct maple_node *mn,
enum maple_type mt)
{
switch (mt) {
case maple_arange_64:
return &mn->ma64.meta;
default:
return &mn->mr64.meta;
}
}
/*
* ma_set_meta() - Set the metadata information of a node.
* @mn: The maple node
* @mt: The maple node type
* @offset: The offset of the highest sub-gap in this node.
* @end: The end of the data in this node.
*/
static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt,
unsigned char offset, unsigned char end)
{
struct maple_metadata *meta = ma_meta(mn, mt);
meta->gap = offset;
meta->end = end;
}
/*
* mt_clear_meta() - clear the metadata information of a node, if it exists
* @mt: The maple tree
* @mn: The maple node
* @type: The maple node type
*/
static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn,
enum maple_type type)
{
struct maple_metadata *meta;
unsigned long *pivots;
void __rcu **slots;
void *next;
switch (type) {
case maple_range_64:
pivots = mn->mr64.pivot;
if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) {
slots = mn->mr64.slot;
next = mt_slot_locked(mt, slots,
MAPLE_RANGE64_SLOTS - 1);
if (unlikely((mte_to_node(next) &&
mte_node_type(next))))
return; /* no metadata, could be node */
}
fallthrough;
case maple_arange_64:
meta = ma_meta(mn, type);
break;
default:
return;
}
meta->gap = 0;
meta->end = 0;
}
/*
* ma_meta_end() - Get the data end of a node from the metadata
* @mn: The maple node
* @mt: The maple node type
*/
static inline unsigned char ma_meta_end(struct maple_node *mn,
enum maple_type mt)
{
struct maple_metadata *meta = ma_meta(mn, mt);
return meta->end;
}
/*
* ma_meta_gap() - Get the largest gap location of a node from the metadata
* @mn: The maple node
*/
static inline unsigned char ma_meta_gap(struct maple_node *mn)
{
return mn->ma64.meta.gap;
}
/*
* ma_set_meta_gap() - Set the largest gap location in a nodes metadata
* @mn: The maple node
* @mt: The maple node type
* @offset: The location of the largest gap.
*/
static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt,
unsigned char offset)
{
struct maple_metadata *meta = ma_meta(mn, mt);
meta->gap = offset;
}
/*
* mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes.
* @mat: the ma_topiary, a linked list of dead nodes.
* @dead_enode: the node to be marked as dead and added to the tail of the list
*
* Add the @dead_enode to the linked list in @mat.
*/
static inline void mat_add(struct ma_topiary *mat,
struct maple_enode *dead_enode)
{
mte_set_node_dead(dead_enode);
mte_to_mat(dead_enode)->next = NULL;
if (!mat->tail) {
mat->tail = mat->head = dead_enode;
return;
}
mte_to_mat(mat->tail)->next = dead_enode;
mat->tail = dead_enode;
}
static void mt_free_walk(struct rcu_head *head);
static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt,
bool free);
/*
* mas_mat_destroy() - Free all nodes and subtrees in a dead list.
* @mas: the maple state
* @mat: the ma_topiary linked list of dead nodes to free.
*
* Destroy walk a dead list.
*/
static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat)
{
struct maple_enode *next;
struct maple_node *node;
bool in_rcu = mt_in_rcu(mas->tree);
while (mat->head) {
next = mte_to_mat(mat->head)->next;
node = mte_to_node(mat->head);
mt_destroy_walk(mat->head, mas->tree, !in_rcu);
if (in_rcu) call_rcu(&node->rcu, mt_free_walk);
mat->head = next;
}
}
/*
* mas_descend() - Descend into the slot stored in the ma_state.
* @mas: the maple state.
*
* Note: Not RCU safe, only use in write side or debug code.
*/
static inline void mas_descend(struct ma_state *mas)
{
enum maple_type type;
unsigned long *pivots;
struct maple_node *node;
void __rcu **slots;
node = mas_mn(mas);
type = mte_node_type(mas->node);
pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1;
mas->max = mas_safe_pivot(mas, pivots, mas->offset, type);
mas->node = mas_slot(mas, slots, mas->offset);
}
/*
* mte_set_gap() - Set a maple node gap.
* @mn: The encoded maple node
* @gap: The offset of the gap to set
* @val: The gap value
*/
static inline void mte_set_gap(const struct maple_enode *mn,
unsigned char gap, unsigned long val)
{
switch (mte_node_type(mn)) {
default:
break;
case maple_arange_64:
mte_to_node(mn)->ma64.gap[gap] = val;
break;
}
}
/*
* mas_ascend() - Walk up a level of the tree.
* @mas: The maple state
*
* Sets the @mas->max and @mas->min to the correct values when walking up. This
* may cause several levels of walking up to find the correct min and max.
* May find a dead node which will cause a premature return.
* Return: 1 on dead node, 0 otherwise
*/
static int mas_ascend(struct ma_state *mas)
{
struct maple_enode *p_enode; /* parent enode. */
struct maple_enode *a_enode; /* ancestor enode. */
struct maple_node *a_node; /* ancestor node. */
struct maple_node *p_node; /* parent node. */
unsigned char a_slot;
enum maple_type a_type;
unsigned long min, max;
unsigned long *pivots;
bool set_max = false, set_min = false;
a_node = mas_mn(mas);
if (ma_is_root(a_node)) {
mas->offset = 0;
return 0;
}
p_node = mte_parent(mas->node);
if (unlikely(a_node == p_node))
return 1;
a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node);
a_enode = mt_mk_node(p_node, a_type);
/* Check to make sure all parent information is still accurate */
if (p_node != mte_parent(mas->node))
return 1;
mas->node = a_enode;
if (mte_is_root(a_enode)) {
mas->max = ULONG_MAX;
mas->min = 0;
return 0;
}
min = 0;
max = ULONG_MAX;
if (!mas->offset) { min = mas->min;
set_min = true;
}
if (mas->max == ULONG_MAX)
set_max = true;
do {
p_enode = a_enode;
a_type = mas_parent_type(mas, p_enode);
a_node = mte_parent(p_enode);
a_slot = mte_parent_slot(p_enode);
a_enode = mt_mk_node(a_node, a_type);
pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node)))
return 1;
if (!set_min && a_slot) {
set_min = true;
min = pivots[a_slot - 1] + 1;
}
if (!set_max && a_slot < mt_pivots[a_type]) {
set_max = true;
max = pivots[a_slot];
}
if (unlikely(ma_dead_node(a_node)))
return 1;
if (unlikely(ma_is_root(a_node)))
break;
} while (!set_min || !set_max);
mas->max = max;
mas->min = min;
return 0;
}
/*
* mas_pop_node() - Get a previously allocated maple node from the maple state.
* @mas: The maple state
*
* Return: A pointer to a maple node.
*/
static inline struct maple_node *mas_pop_node(struct ma_state *mas)
{
struct maple_alloc *ret, *node = mas->alloc;
unsigned long total = mas_allocated(mas);
unsigned int req = mas_alloc_req(mas);
/* nothing or a request pending. */
if (WARN_ON(!total))
return NULL;
if (total == 1) {
/* single allocation in this ma_state */
mas->alloc = NULL;
ret = node;
goto single_node;
}
if (node->node_count == 1) {
/* Single allocation in this node. */
mas->alloc = node->slot[0];
mas->alloc->total = node->total - 1;
ret = node;
goto new_head;
}
node->total--;
ret = node->slot[--node->node_count];
node->slot[node->node_count] = NULL;
single_node:
new_head:
if (req) {
req++;
mas_set_alloc_req(mas, req);
}
memset(ret, 0, sizeof(*ret));
return (struct maple_node *)ret;
}
/*
* mas_push_node() - Push a node back on the maple state allocation.
* @mas: The maple state
* @used: The used maple node
*
* Stores the maple node back into @mas->alloc for reuse. Updates allocated and
* requested node count as necessary.
*/
static inline void mas_push_node(struct ma_state *mas, struct maple_node *used)
{
struct maple_alloc *reuse = (struct maple_alloc *)used;
struct maple_alloc *head = mas->alloc;
unsigned long count;
unsigned int requested = mas_alloc_req(mas);
count = mas_allocated(mas);
reuse->request_count = 0;
reuse->node_count = 0;
if (count) {
if (head->node_count < MAPLE_ALLOC_SLOTS) {
head->slot[head->node_count++] = reuse;
head->total++;
goto done;
}
reuse->slot[0] = head;
reuse->node_count = 1;
}
reuse->total = count + 1;
mas->alloc = reuse;
done:
if (requested > 1) mas_set_alloc_req(mas, requested - 1);
}
/*
* mas_alloc_nodes() - Allocate nodes into a maple state
* @mas: The maple state
* @gfp: The GFP Flags
*/
static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
{
struct maple_alloc *node;
unsigned long allocated = mas_allocated(mas);
unsigned int requested = mas_alloc_req(mas);
unsigned int count;
void **slots = NULL;
unsigned int max_req = 0;
if (!requested)
return;
mas_set_alloc_req(mas, 0);
if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated)
return;
WARN_ON(!allocated);
}
if (!allocated || mas->alloc->node_count == MAPLE_ALLOC_SLOTS) {
node = (struct maple_alloc *)mt_alloc_one(gfp);
if (!node)
goto nomem_one;
if (allocated) {
node->slot[0] = mas->alloc;
node->node_count = 1;
} else {
node->node_count = 0;
}
mas->alloc = node;
node->total = ++allocated;
node->request_count = 0;
requested--;
}
node = mas->alloc;
while (requested) {
max_req = MAPLE_ALLOC_SLOTS - node->node_count;
slots = (void **)&node->slot[node->node_count];
max_req = min(requested, max_req);
count = mt_alloc_bulk(gfp, max_req, slots);
if (!count)
goto nomem_bulk;
if (node->node_count == 0) { node->slot[0]->node_count = 0;
node->slot[0]->request_count = 0;
}
node->node_count += count;
allocated += count;
/* find a non-full node*/
do {
node = node->slot[0];
} while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS));
requested -= count;
}
mas->alloc->total = allocated;
return;
nomem_bulk:
/* Clean up potential freed allocations on bulk failure */
memset(slots, 0, max_req * sizeof(unsigned long));
mas->alloc->total = allocated;
nomem_one:
mas_set_alloc_req(mas, requested);
mas_set_err(mas, -ENOMEM);
}
/*
* mas_free() - Free an encoded maple node
* @mas: The maple state
* @used: The encoded maple node to free.
*
* Uses rcu free if necessary, pushes @used back on the maple state allocations
* otherwise.
*/
static inline void mas_free(struct ma_state *mas, struct maple_enode *used)
{
struct maple_node *tmp = mte_to_node(used);
if (mt_in_rcu(mas->tree))
ma_free_rcu(tmp);
else
mas_push_node(mas, tmp);
}
/*
* mas_node_count_gfp() - Check if enough nodes are allocated and request more
* if there is not enough nodes.
* @mas: The maple state
* @count: The number of nodes needed
* @gfp: the gfp flags
*/
static void mas_node_count_gfp(struct ma_state *mas, int count, gfp_t gfp)
{
unsigned long allocated = mas_allocated(mas);
if (allocated < count) { mas_set_alloc_req(mas, count - allocated);
mas_alloc_nodes(mas, gfp);
}
}
/*
* mas_node_count() - Check if enough nodes are allocated and request more if
* there is not enough nodes.
* @mas: The maple state
* @count: The number of nodes needed
*
* Note: Uses GFP_NOWAIT | __GFP_NOWARN for gfp flags.
*/
static void mas_node_count(struct ma_state *mas, int count)
{
return mas_node_count_gfp(mas, count, GFP_NOWAIT | __GFP_NOWARN);
}
/*
* mas_start() - Sets up maple state for operations.
* @mas: The maple state.
*
* If mas->status == ma_start, then set the min, max and depth to
* defaults.
*
* Return:
* - If mas->node is an error or not mas_start, return NULL.
* - If it's an empty tree: NULL & mas->status == ma_none
* - If it's a single entry: The entry & mas->status == ma_root
* - If it's a tree: NULL & mas->status == ma_active
*/
static inline struct maple_enode *mas_start(struct ma_state *mas)
{ if (likely(mas_is_start(mas))) {
struct maple_enode *root;
mas->min = 0;
mas->max = ULONG_MAX;
retry:
mas->depth = 0;
root = mas_root(mas);
/* Tree with nodes */
if (likely(xa_is_node(root))) {
mas->depth = 1;
mas->status = ma_active;
mas->node = mte_safe_root(root);
mas->offset = 0;
if (mte_dead_node(mas->node))
goto retry;
return NULL;
}
mas->node = NULL;
/* empty tree */
if (unlikely(!root)) {
mas->status = ma_none;
mas->offset = MAPLE_NODE_SLOTS;
return NULL;
}
/* Single entry tree */
mas->status = ma_root;
mas->offset = MAPLE_NODE_SLOTS;
/* Single entry tree. */
if (mas->index > 0)
return NULL;
return root;
}
return NULL;
}
/*
* ma_data_end() - Find the end of the data in a node.
* @node: The maple node
* @type: The maple node type
* @pivots: The array of pivots in the node
* @max: The maximum value in the node
*
* Uses metadata to find the end of the data when possible.
* Return: The zero indexed last slot with data (may be null).
*/
static __always_inline unsigned char ma_data_end(struct maple_node *node,
enum maple_type type, unsigned long *pivots, unsigned long max)
{
unsigned char offset;
if (!pivots)
return 0;
if (type == maple_arange_64)
return ma_meta_end(node, type);
offset = mt_pivots[type] - 1;
if (likely(!pivots[offset]))
return ma_meta_end(node, type); if (likely(pivots[offset] == max))
return offset;
return mt_pivots[type];
}
/*
* mas_data_end() - Find the end of the data (slot).
* @mas: the maple state
*
* This method is optimized to check the metadata of a node if the node type
* supports data end metadata.
*
* Return: The zero indexed last slot with data (may be null).
*/
static inline unsigned char mas_data_end(struct ma_state *mas)
{
enum maple_type type;
struct maple_node *node;
unsigned char offset;
unsigned long *pivots;
type = mte_node_type(mas->node);
node = mas_mn(mas);
if (type == maple_arange_64) return ma_meta_end(node, type);
pivots = ma_pivots(node, type);
if (unlikely(ma_dead_node(node)))
return 0;
offset = mt_pivots[type] - 1;
if (likely(!pivots[offset]))
return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max))
return offset;
return mt_pivots[type];
}
/*
* mas_leaf_max_gap() - Returns the largest gap in a leaf node
* @mas: the maple state
*
* Return: The maximum gap in the leaf.
*/
static unsigned long mas_leaf_max_gap(struct ma_state *mas)
{
enum maple_type mt;
unsigned long pstart, gap, max_gap;
struct maple_node *mn;
unsigned long *pivots;
void __rcu **slots;
unsigned char i;
unsigned char max_piv;
mt = mte_node_type(mas->node);
mn = mas_mn(mas);
slots = ma_slots(mn, mt);
max_gap = 0;
if (unlikely(ma_is_dense(mt))) {
gap = 0;
for (i = 0; i < mt_slots[mt]; i++) {
if (slots[i]) {
if (gap > max_gap)
max_gap = gap;
gap = 0;
} else {
gap++;
}
}
if (gap > max_gap)
max_gap = gap;
return max_gap;
}
/*
* Check the first implied pivot optimizes the loop below and slot 1 may
* be skipped if there is a gap in slot 0.
*/
pivots = ma_pivots(mn, mt);
if (likely(!slots[0])) { max_gap = pivots[0] - mas->min + 1;
i = 2;
} else {
i = 1;
}
/* reduce max_piv as the special case is checked before the loop */
max_piv = ma_data_end(mn, mt, pivots, mas->max) - 1;
/*
* Check end implied pivot which can only be a gap on the right most
* node.
*/
if (unlikely(mas->max == ULONG_MAX) && !slots[max_piv + 1]) {
gap = ULONG_MAX - pivots[max_piv];
if (gap > max_gap)
max_gap = gap;
if (max_gap > pivots[max_piv] - mas->min)
return max_gap;
}
for (; i <= max_piv; i++) {
/* data == no gap. */
if (likely(slots[i]))
continue;
pstart = pivots[i - 1];
gap = pivots[i] - pstart;
if (gap > max_gap)
max_gap = gap;
/* There cannot be two gaps in a row. */
i++;
}
return max_gap;
}
/*
* ma_max_gap() - Get the maximum gap in a maple node (non-leaf)
* @node: The maple node
* @gaps: The pointer to the gaps
* @mt: The maple node type
* @off: Pointer to store the offset location of the gap.
*
* Uses the metadata data end to scan backwards across set gaps.
*
* Return: The maximum gap value
*/
static inline unsigned long
ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt,
unsigned char *off)
{
unsigned char offset, i;
unsigned long max_gap = 0;
i = offset = ma_meta_end(node, mt);
do {
if (gaps[i] > max_gap) {
max_gap = gaps[i];
offset = i;
}
} while (i--);
*off = offset;
return max_gap;
}
/*
* mas_max_gap() - find the largest gap in a non-leaf node and set the slot.
* @mas: The maple state.
*
* Return: The gap value.
*/
static inline unsigned long mas_max_gap(struct ma_state *mas)
{
unsigned long *gaps;
unsigned char offset;
enum maple_type mt;
struct maple_node *node;
mt = mte_node_type(mas->node);
if (ma_is_leaf(mt))
return mas_leaf_max_gap(mas);
node = mas_mn(mas);
MAS_BUG_ON(mas, mt != maple_arange_64);
offset = ma_meta_gap(node);
gaps = ma_gaps(node, mt);
return gaps[offset];
}
/*
* mas_parent_gap() - Set the parent gap and any gaps above, as needed
* @mas: The maple state
* @offset: The gap offset in the parent to set
* @new: The new gap value.
*
* Set the parent gap then continue to set the gap upwards, using the metadata
* of the parent to see if it is necessary to check the node above.
*/
static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset,
unsigned long new)
{
unsigned long meta_gap = 0;
struct maple_node *pnode;
struct maple_enode *penode;
unsigned long *pgaps;
unsigned char meta_offset;
enum maple_type pmt;
pnode = mte_parent(mas->node);
pmt = mas_parent_type(mas, mas->node);
penode = mt_mk_node(pnode, pmt);
pgaps = ma_gaps(pnode, pmt);
ascend:
MAS_BUG_ON(mas, pmt != maple_arange_64);
meta_offset = ma_meta_gap(pnode);
meta_gap = pgaps[meta_offset];
pgaps[offset] = new;
if (meta_gap == new)
return;
if (offset != meta_offset) {
if (meta_gap > new)
return;
ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset);
ma_set_meta_gap(pnode, pmt, meta_offset);
}
if (ma_is_root(pnode))
return;
/* Go to the parent node. */
pnode = mte_parent(penode);
pmt = mas_parent_type(mas, penode);
pgaps = ma_gaps(pnode, pmt);
offset = mte_parent_slot(penode);
penode = mt_mk_node(pnode, pmt);
goto ascend;
}
/*
* mas_update_gap() - Update a nodes gaps and propagate up if necessary.
* @mas: the maple state.
*/
static inline void mas_update_gap(struct ma_state *mas)
{
unsigned char pslot;
unsigned long p_gap;
unsigned long max_gap;
if (!mt_is_alloc(mas->tree))
return;
if (mte_is_root(mas->node))
return;
max_gap = mas_max_gap(mas);
pslot = mte_parent_slot(mas->node);
p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap);
}
/*
* mas_adopt_children() - Set the parent pointer of all nodes in @parent to
* @parent with the slot encoded.
* @mas: the maple state (for the tree)
* @parent: the maple encoded node containing the children.
*/
static inline void mas_adopt_children(struct ma_state *mas,
struct maple_enode *parent)
{
enum maple_type type = mte_node_type(parent);
struct maple_node *node = mte_to_node(parent);
void __rcu **slots = ma_slots(node, type);
unsigned long *pivots = ma_pivots(node, type);
struct maple_enode *child;
unsigned char offset;
offset = ma_data_end(node, type, pivots, mas->max);
do {
child = mas_slot_locked(mas, slots, offset);
mas_set_parent(mas, child, parent, offset);
} while (offset--);}
/*
* mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old
* node as dead.
* @mas: the maple state with the new node
* @old_enode: The old maple encoded node to replace.
*/
static inline void mas_put_in_tree(struct ma_state *mas,
struct maple_enode *old_enode)
__must_hold(mas->tree->ma_lock)
{
unsigned char offset;
void __rcu **slots;
if (mte_is_root(mas->node)) {
mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas));
rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node));
mas_set_height(mas);
} else {
offset = mte_parent_slot(mas->node);
slots = ma_slots(mte_parent(mas->node),
mas_parent_type(mas, mas->node));
rcu_assign_pointer(slots[offset], mas->node);
}
mte_set_node_dead(old_enode);
}
/*
* mas_replace_node() - Replace a node by putting it in the tree, marking it
* dead, and freeing it.
* the parent encoding to locate the maple node in the tree.
* @mas: the ma_state with @mas->node pointing to the new node.
* @old_enode: The old maple encoded node.
*/
static inline void mas_replace_node(struct ma_state *mas,
struct maple_enode *old_enode)
__must_hold(mas->tree->ma_lock)
{ mas_put_in_tree(mas, old_enode); mas_free(mas, old_enode);
}
/*
* mas_find_child() - Find a child who has the parent @mas->node.
* @mas: the maple state with the parent.
* @child: the maple state to store the child.
*/
static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child)
__must_hold(mas->tree->ma_lock)
{
enum maple_type mt;
unsigned char offset;
unsigned char end;
unsigned long *pivots;
struct maple_enode *entry;
struct maple_node *node;
void __rcu **slots;
mt = mte_node_type(mas->node);
node = mas_mn(mas);
slots = ma_slots(node, mt);
pivots = ma_pivots(node, mt);
end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset);
if (mte_parent(entry) == node) {
*child = *mas;
mas->offset = offset + 1;
child->offset = offset;
mas_descend(child);
child->offset = 0;
return true;
}
}
return false;
}
/*
* mab_shift_right() - Shift the data in mab right. Note, does not clean out the
* old data or set b_node->b_end.
* @b_node: the maple_big_node
* @shift: the shift count
*/
static inline void mab_shift_right(struct maple_big_node *b_node,
unsigned char shift)
{
unsigned long size = b_node->b_end * sizeof(unsigned long);
memmove(b_node->pivot + shift, b_node->pivot, size);
memmove(b_node->slot + shift, b_node->slot, size);
if (b_node->type == maple_arange_64) memmove(b_node->gap + shift, b_node->gap, size);
}
/*
* mab_middle_node() - Check if a middle node is needed (unlikely)
* @b_node: the maple_big_node that contains the data.
* @split: the potential split location
* @slot_count: the size that can be stored in a single node being considered.
*
* Return: true if a middle node is required.
*/
static inline bool mab_middle_node(struct maple_big_node *b_node, int split,
unsigned char slot_count)
{
unsigned char size = b_node->b_end;
if (size >= 2 * slot_count)
return true;
if (!b_node->slot[split] && (size >= 2 * slot_count - 1))
return true;
return false;
}
/*
* mab_no_null_split() - ensure the split doesn't fall on a NULL
* @b_node: the maple_big_node with the data
* @split: the suggested split location
* @slot_count: the number of slots in the node being considered.
*
* Return: the split location.
*/
static inline int mab_no_null_split(struct maple_big_node *b_node,
unsigned char split, unsigned char slot_count)
{ if (!b_node->slot[split]) {
/*
* If the split is less than the max slot && the right side will
* still be sufficient, then increment the split on NULL.
*/
if ((split < slot_count - 1) &&
(b_node->b_end - split) > (mt_min_slots[b_node->type]))
split++;
else
split--;
}
return split;
}
/*
* mab_calc_split() - Calculate the split location and if there needs to be two
* splits.
* @mas: The maple state
* @bn: The maple_big_node with the data
* @mid_split: The second split, if required. 0 otherwise.
*
* Return: The first split location. The middle split is set in @mid_split.
*/
static inline int mab_calc_split(struct ma_state *mas,
struct maple_big_node *bn, unsigned char *mid_split)
{
unsigned char b_end = bn->b_end;
int split = b_end / 2; /* Assume equal split. */
unsigned char slot_count = mt_slots[bn->type];
/*
* To support gap tracking, all NULL entries are kept together and a node cannot
* end on a NULL entry, with the exception of the left-most leaf. The
* limitation means that the split of a node must be checked for this condition
* and be able to put more data in one direction or the other.
*/
if (unlikely((mas->mas_flags & MA_STATE_BULK))) {
*mid_split = 0;
split = b_end - mt_min_slots[bn->type];
if (!ma_is_leaf(bn->type))
return split;
mas->mas_flags |= MA_STATE_REBALANCE;
if (!bn->slot[split])
split--;
return split;
}
/*
* Although extremely rare, it is possible to enter what is known as the 3-way
* split scenario. The 3-way split comes about by means of a store of a range
* that overwrites the end and beginning of two full nodes. The result is a set
* of entries that cannot be stored in 2 nodes. Sometimes, these two nodes can
* also be located in different parent nodes which are also full. This can
* carry upwards all the way to the root in the worst case.
*/
if (unlikely(mab_middle_node(bn, split, slot_count))) {
split = b_end / 3;
*mid_split = split * 2;
} else {
*mid_split = 0;
}
/* Avoid ending a node on a NULL entry */
split = mab_no_null_split(bn, split, slot_count); if (unlikely(*mid_split)) *mid_split = mab_no_null_split(bn, *mid_split, slot_count);
return split;
}
/*
* mas_mab_cp() - Copy data from a maple state inclusively to a maple_big_node
* and set @b_node->b_end to the next free slot.
* @mas: The maple state
* @mas_start: The starting slot to copy
* @mas_end: The end slot to copy (inclusively)
* @b_node: The maple_big_node to place the data
* @mab_start: The starting location in maple_big_node to store the data.
*/
static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start,
unsigned char mas_end, struct maple_big_node *b_node,
unsigned char mab_start)
{
enum maple_type mt;
struct maple_node *node;
void __rcu **slots;
unsigned long *pivots, *gaps;
int i = mas_start, j = mab_start;
unsigned char piv_end;
node = mas_mn(mas);
mt = mte_node_type(mas->node);
pivots = ma_pivots(node, mt); if (!i) {
b_node->pivot[j] = pivots[i++];
if (unlikely(i > mas_end))
goto complete;
j++;
}
piv_end = min(mas_end, mt_pivots[mt]);
for (; i < piv_end; i++, j++) {
b_node->pivot[j] = pivots[i];
if (unlikely(!b_node->pivot[j]))
goto complete;
if (unlikely(mas->max == b_node->pivot[j]))
goto complete;
}
b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt);
complete:
b_node->b_end = ++j;
j -= mab_start;
slots = ma_slots(node, mt);
memcpy(b_node->slot + mab_start, slots + mas_start, sizeof(void *) * j);
if (!ma_is_leaf(mt) && mt_is_alloc(mas->tree)) { gaps = ma_gaps(node, mt);
memcpy(b_node->gap + mab_start, gaps + mas_start,
sizeof(unsigned long) * j);
}
}
/*
* mas_leaf_set_meta() - Set the metadata of a leaf if possible.
* @node: The maple node
* @mt: The maple type
* @end: The node end
*/
static inline void mas_leaf_set_meta(struct maple_node *node,
enum maple_type mt, unsigned char end)
{
if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end);
}
/*
* mab_mas_cp() - Copy data from maple_big_node to a maple encoded node.
* @b_node: the maple_big_node that has the data
* @mab_start: the start location in @b_node.
* @mab_end: The end location in @b_node (inclusively)
* @mas: The maple state with the maple encoded node.
*/
static inline void mab_mas_cp(struct maple_big_node *b_node,
unsigned char mab_start, unsigned char mab_end,
struct ma_state *mas, bool new_max)
{
int i, j = 0;
enum maple_type mt = mte_node_type(mas->node);
struct maple_node *node = mte_to_node(mas->node);
void __rcu **slots = ma_slots(node, mt);
unsigned long *pivots = ma_pivots(node, mt);
unsigned long *gaps = NULL;
unsigned char end;
if (mab_end - mab_start > mt_pivots[mt])
mab_end--;
if (!pivots[mt_pivots[mt] - 1]) slots[mt_pivots[mt]] = NULL;
i = mab_start;
do {
pivots[j++] = b_node->pivot[i++]; } while (i <= mab_end && likely(b_node->pivot[i]));
memcpy(slots, b_node->slot + mab_start,
sizeof(void *) * (i - mab_start));
if (new_max)
mas->max = b_node->pivot[i - 1];
end = j - 1;
if (likely(!ma_is_leaf(mt) && mt_is_alloc(mas->tree))) {
unsigned long max_gap = 0;
unsigned char offset = 0;
gaps = ma_gaps(node, mt);
do {
gaps[--j] = b_node->gap[--i];
if (gaps[j] > max_gap) {
offset = j;
max_gap = gaps[j];
}
} while (j);
ma_set_meta(node, mt, offset, end);
} else {
mas_leaf_set_meta(node, mt, end);
}
}
/*
* mas_bulk_rebalance() - Rebalance the end of a tree after a bulk insert.
* @mas: The maple state
* @end: The maple node end
* @mt: The maple node type
*/
static inline void mas_bulk_rebalance(struct ma_state *mas, unsigned char end,
enum maple_type mt)
{
if (!(mas->mas_flags & MA_STATE_BULK))
return;
if (mte_is_root(mas->node))
return;
if (end > mt_min_slots[mt]) { mas->mas_flags &= ~MA_STATE_REBALANCE;
return;
}
}
/*
* mas_store_b_node() - Store an @entry into the b_node while also copying the
* data from a maple encoded node.
* @wr_mas: the maple write state
* @b_node: the maple_big_node to fill with data
* @offset_end: the offset to end copying
*
* Return: The actual end of the data stored in @b_node
*/
static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas,
struct maple_big_node *b_node, unsigned char offset_end)
{
unsigned char slot;
unsigned char b_end;
/* Possible underflow of piv will wrap back to 0 before use. */
unsigned long piv;
struct ma_state *mas = wr_mas->mas;
b_node->type = wr_mas->type;
b_end = 0;
slot = mas->offset;
if (slot) {
/* Copy start data up to insert. */
mas_mab_cp(mas, 0, slot - 1, b_node, 0);
b_end = b_node->b_end;
piv = b_node->pivot[b_end - 1];
} else
piv = mas->min - 1; if (piv + 1 < mas->index) {
/* Handle range starting after old range */
b_node->slot[b_end] = wr_mas->content;
if (!wr_mas->content) b_node->gap[b_end] = mas->index - 1 - piv;
b_node->pivot[b_end++] = mas->index - 1;
}
/* Store the new entry. */
mas->offset = b_end;
b_node->slot[b_end] = wr_mas->entry;
b_node->pivot[b_end] = mas->last;
/* Appended. */
if (mas->last >= mas->max)
goto b_end;
/* Handle new range ending before old range ends */
piv = mas_safe_pivot(mas, wr_mas->pivots, offset_end, wr_mas->type);
if (piv > mas->last) { if (piv == ULONG_MAX) mas_bulk_rebalance(mas, b_node->b_end, wr_mas->type); if (offset_end != slot) wr_mas->content = mas_slot_locked(mas, wr_mas->slots,
offset_end);
b_node->slot[++b_end] = wr_mas->content;
if (!wr_mas->content) b_node->gap[b_end] = piv - mas->last + 1;
b_node->pivot[b_end] = piv;
}
slot = offset_end + 1;
if (slot > mas->end)
goto b_end;
/* Copy end data to the end of the node. */
mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end);
b_node->b_end--;
return;
b_end:
b_node->b_end = b_end;
}
/*
* mas_prev_sibling() - Find the previous node with the same parent.
* @mas: the maple state
*
* Return: True if there is a previous sibling, false otherwise.
*/
static inline bool mas_prev_sibling(struct ma_state *mas)
{
unsigned int p_slot = mte_parent_slot(mas->node);
/* For root node, p_slot is set to 0 by mte_parent_slot(). */
if (!p_slot)
return false;
mas_ascend(mas);
mas->offset = p_slot - 1;
mas_descend(mas);
return true;
}
/*
* mas_next_sibling() - Find the next node with the same parent.
* @mas: the maple state
*
* Return: true if there is a next sibling, false otherwise.
*/
static inline bool mas_next_sibling(struct ma_state *mas)
{
MA_STATE(parent, mas->tree, mas->index, mas->last);
if (mte_is_root(mas->node))
return false;
parent = *mas;
mas_ascend(&parent);
parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent))
return false;
*mas = parent;
mas_descend(mas);
return true;
}
/*
* mas_node_or_none() - Set the enode and state.
* @mas: the maple state
* @enode: The encoded maple node.
*
* Set the node to the enode and the status.
*/
static inline void mas_node_or_none(struct ma_state *mas,
struct maple_enode *enode)
{
if (enode) {
mas->node = enode;
mas->status = ma_active;
} else {
mas->node = NULL;
mas->status = ma_none;
}
}
/*
* mas_wr_node_walk() - Find the correct offset for the index in the @mas.
* If @mas->index cannot be found within the containing
* node, we traverse to the last entry in the node.
* @wr_mas: The maple write state
*
* Uses mas_slot_locked() and does not need to worry about dead nodes.
*/
static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
unsigned char count, offset;
if (unlikely(ma_is_dense(wr_mas->type))) {
wr_mas->r_max = wr_mas->r_min = mas->index;
mas->offset = mas->index = mas->min;
return;
}
wr_mas->node = mas_mn(wr_mas->mas);
wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max);
offset = mas->offset;
while (offset < count && mas->index > wr_mas->pivots[offset])
offset++;
wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max;
wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset);
wr_mas->offset_end = mas->offset = offset;
}
/*
* mast_rebalance_next() - Rebalance against the next node
* @mast: The maple subtree state
*/
static inline void mast_rebalance_next(struct maple_subtree_state *mast)
{
unsigned char b_end = mast->bn->b_end;
mas_mab_cp(mast->orig_r, 0, mt_slot_count(mast->orig_r->node),
mast->bn, b_end);
mast->orig_r->last = mast->orig_r->max;
}
/*
* mast_rebalance_prev() - Rebalance against the previous node
* @mast: The maple subtree state
*/
static inline void mast_rebalance_prev(struct maple_subtree_state *mast)
{
unsigned char end = mas_data_end(mast->orig_l) + 1;
unsigned char b_end = mast->bn->b_end;
mab_shift_right(mast->bn, end);
mas_mab_cp(mast->orig_l, 0, end - 1, mast->bn, 0);
mast->l->min = mast->orig_l->min;
mast->orig_l->index = mast->orig_l->min;
mast->bn->b_end = end + b_end;
mast->l->offset += end;
}
/*
* mast_spanning_rebalance() - Rebalance nodes with nearest neighbour favouring
* the node to the right. Checking the nodes to the right then the left at each
* level upwards until root is reached.
* Data is copied into the @mast->bn.
* @mast: The maple_subtree_state.
*/
static inline
bool mast_spanning_rebalance(struct maple_subtree_state *mast)
{
struct ma_state r_tmp = *mast->orig_r;
struct ma_state l_tmp = *mast->orig_l;
unsigned char depth = 0;
do {
mas_ascend(mast->orig_r);
mas_ascend(mast->orig_l);
depth++;
if (mast->orig_r->offset < mas_data_end(mast->orig_r)) {
mast->orig_r->offset++;
do {
mas_descend(mast->orig_r);
mast->orig_r->offset = 0;
} while (--depth); mast_rebalance_next(mast);
*mast->orig_l = l_tmp;
return true;
} else if (mast->orig_l->offset != 0) {
mast->orig_l->offset--;
do {
mas_descend(mast->orig_l);
mast->orig_l->offset =
mas_data_end(mast->orig_l); } while (--depth); mast_rebalance_prev(mast);
*mast->orig_r = r_tmp;
return true;
}
} while (!mte_is_root(mast->orig_r->node)); *mast->orig_r = r_tmp;
*mast->orig_l = l_tmp;
return false;
}
/*
* mast_ascend() - Ascend the original left and right maple states.
* @mast: the maple subtree state.
*
* Ascend the original left and right sides. Set the offsets to point to the
* data already in the new tree (@mast->l and @mast->r).
*/
static inline void mast_ascend(struct maple_subtree_state *mast)
{
MA_WR_STATE(wr_mas, mast->orig_r, NULL);
mas_ascend(mast->orig_l);
mas_ascend(mast->orig_r);
mast->orig_r->offset = 0;
mast->orig_r->index = mast->r->max;
/* last should be larger than or equal to index */
if (mast->orig_r->last < mast->orig_r->index) mast->orig_r->last = mast->orig_r->index;
wr_mas.type = mte_node_type(mast->orig_r->node);
mas_wr_node_walk(&wr_mas);
/* Set up the left side of things */
mast->orig_l->offset = 0;
mast->orig_l->index = mast->l->min;
wr_mas.mas = mast->orig_l;
wr_mas.type = mte_node_type(mast->orig_l->node);
mas_wr_node_walk(&wr_mas);
mast->bn->type = wr_mas.type;
}
/*
* mas_new_ma_node() - Create and return a new maple node. Helper function.
* @mas: the maple state with the allocations.
* @b_node: the maple_big_node with the type encoding.
*
* Use the node type from the maple_big_node to allocate a new node from the
* ma_state. This function exists mainly for code readability.
*
* Return: A new maple encoded node
*/
static inline struct maple_enode
*mas_new_ma_node(struct ma_state *mas, struct maple_big_node *b_node)
{
return mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), b_node->type);
}
/*
* mas_mab_to_node() - Set up right and middle nodes
*
* @mas: the maple state that contains the allocations.
* @b_node: the node which contains the data.
* @left: The pointer which will have the left node
* @right: The pointer which may have the right node
* @middle: the pointer which may have the middle node (rare)
* @mid_split: the split location for the middle node
*
* Return: the split of left.
*/
static inline unsigned char mas_mab_to_node(struct ma_state *mas,
struct maple_big_node *b_node, struct maple_enode **left,
struct maple_enode **right, struct maple_enode **middle,
unsigned char *mid_split)
{
unsigned char split = 0;
unsigned char slot_count = mt_slots[b_node->type];
*left = mas_new_ma_node(mas, b_node);
*right = NULL;
*middle = NULL;
*mid_split = 0;
if (b_node->b_end < slot_count) {
split = b_node->b_end;
} else {
split = mab_calc_split(mas, b_node, mid_split); *right = mas_new_ma_node(mas, b_node);
}
if (*mid_split) *middle = mas_new_ma_node(mas, b_node);
return split;
}
/*
* mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end
* pointer.
* @b_node: the big node to add the entry
* @mas: the maple state to get the pivot (mas->max)
* @entry: the entry to add, if NULL nothing happens.
*/
static inline void mab_set_b_end(struct maple_big_node *b_node,
struct ma_state *mas,
void *entry)
{
if (!entry)
return;
b_node->slot[b_node->b_end] = entry;
if (mt_is_alloc(mas->tree)) b_node->gap[b_node->b_end] = mas_max_gap(mas);
b_node->pivot[b_node->b_end++] = mas->max;
}
/*
* mas_set_split_parent() - combine_then_separate helper function. Sets the parent
* of @mas->node to either @left or @right, depending on @slot and @split
*
* @mas: the maple state with the node that needs a parent
* @left: possible parent 1
* @right: possible parent 2
* @slot: the slot the mas->node was placed
* @split: the split location between @left and @right
*/
static inline void mas_set_split_parent(struct ma_state *mas,
struct maple_enode *left,
struct maple_enode *right,
unsigned char *slot, unsigned char split)
{
if (mas_is_none(mas))
return;
if ((*slot) <= split)
mas_set_parent(mas, mas->node, left, *slot); else if (right) mas_set_parent(mas, mas->node, right, (*slot) - split - 1);
(*slot)++;
}
/*
* mte_mid_split_check() - Check if the next node passes the mid-split
* @l: Pointer to left encoded maple node.
* @m: Pointer to middle encoded maple node.
* @r: Pointer to right encoded maple node.
* @slot: The offset
* @split: The split location.
* @mid_split: The middle split.
*/
static inline void mte_mid_split_check(struct maple_enode **l,
struct maple_enode **r,
struct maple_enode *right,
unsigned char slot,
unsigned char *split,
unsigned char mid_split)
{
if (*r == right)
return;
if (slot < mid_split)
return;
*l = *r;
*r = right;
*split = mid_split;
}
/*
* mast_set_split_parents() - Helper function to set three nodes parents. Slot
* is taken from @mast->l.
* @mast: the maple subtree state
* @left: the left node
* @right: the right node
* @split: the split location.
*/
static inline void mast_set_split_parents(struct maple_subtree_state *mast,
struct maple_enode *left,
struct maple_enode *middle,
struct maple_enode *right,
unsigned char split,
unsigned char mid_split)
{
unsigned char slot;
struct maple_enode *l = left;
struct maple_enode *r = right;
if (mas_is_none(mast->l))
return;
if (middle)
r = middle;
slot = mast->l->offset;
mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->l, l, r, &slot, split);
mte_mid_split_check(&l, &r, right, slot, &split, mid_split);
mas_set_split_parent(mast->m, l, r, &slot, split);
mte_mid_split_check(&l, &r, right, slot, &split, mid_split);
mas_set_split_parent(mast->r, l, r, &slot, split);
}
/*
* mas_topiary_node() - Dispose of a single node
* @mas: The maple state for pushing nodes
* @in_rcu: If the tree is in rcu mode
*
* The node will either be RCU freed or pushed back on the maple state.
*/
static inline void mas_topiary_node(struct ma_state *mas,
struct ma_state *tmp_mas, bool in_rcu)
{
struct maple_node *tmp;
struct maple_enode *enode;
if (mas_is_none(tmp_mas))
return;
enode = tmp_mas->node;
tmp = mte_to_node(enode);
mte_set_node_dead(enode);
if (in_rcu)
ma_free_rcu(tmp);
else
mas_push_node(mas, tmp);
}
/*
* mas_topiary_replace() - Replace the data with new data, then repair the
* parent links within the new tree. Iterate over the dead sub-tree and collect
* the dead subtrees and topiary the nodes that are no longer of use.
*
* The new tree will have up to three children with the correct parent. Keep
* track of the new entries as they need to be followed to find the next level
* of new entries.
*
* The old tree will have up to three children with the old parent. Keep track
* of the old entries as they may have more nodes below replaced. Nodes within
* [index, last] are dead subtrees, others need to be freed and followed.
*
* @mas: The maple state pointing at the new data
* @old_enode: The maple encoded node being replaced
*
*/
static inline void mas_topiary_replace(struct ma_state *mas,
struct maple_enode *old_enode)
{
struct ma_state tmp[3], tmp_next[3];
MA_TOPIARY(subtrees, mas->tree);
bool in_rcu;
int i, n;
/* Place data in tree & then mark node as old */
mas_put_in_tree(mas, old_enode);
/* Update the parent pointers in the tree */
tmp[0] = *mas;
tmp[0].offset = 0;
tmp[1].status = ma_none;
tmp[2].status = ma_none;
while (!mte_is_leaf(tmp[0].node)) {
n = 0;
for (i = 0; i < 3; i++) {
if (mas_is_none(&tmp[i]))
continue;
while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n]))
break;
n++;
}
mas_adopt_children(&tmp[i], tmp[i].node);
}
if (MAS_WARN_ON(mas, n == 0))
break;
while (n < 3)
tmp_next[n++].status = ma_none;
for (i = 0; i < 3; i++)
tmp[i] = tmp_next[i];
}
/* Collect the old nodes that need to be discarded */
if (mte_is_leaf(old_enode))
return mas_free(mas, old_enode);
tmp[0] = *mas;
tmp[0].offset = 0;
tmp[0].node = old_enode;
tmp[1].status = ma_none;
tmp[2].status = ma_none;
in_rcu = mt_in_rcu(mas->tree);
do {
n = 0;
for (i = 0; i < 3; i++) {
if (mas_is_none(&tmp[i]))
continue;
while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n]))
break;
if ((tmp_next[n].min >= tmp_next->index) &&
(tmp_next[n].max <= tmp_next->last)) {
mat_add(&subtrees, tmp_next[n].node);
tmp_next[n].status = ma_none;
} else {
n++;
}
}
}
if (MAS_WARN_ON(mas, n == 0))
break;
while (n < 3)
tmp_next[n++].status = ma_none;
for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu);
tmp[i] = tmp_next[i];
}
} while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees);
}
/*
* mas_wmb_replace() - Write memory barrier and replace
* @mas: The maple state
* @old_enode: The old maple encoded node that is being replaced.
*
* Updates gap as necessary.
*/
static inline void mas_wmb_replace(struct ma_state *mas,
struct maple_enode *old_enode)
{
/* Insert the new data in the tree */
mas_topiary_replace(mas, old_enode); if (mte_is_leaf(mas->node))
return;
mas_update_gap(mas);
}
/*
* mast_cp_to_nodes() - Copy data out to nodes.
* @mast: The maple subtree state
* @left: The left encoded maple node
* @middle: The middle encoded maple node
* @right: The right encoded maple node
* @split: The location to split between left and (middle ? middle : right)
* @mid_split: The location to split between middle and right.
*/
static inline void mast_cp_to_nodes(struct maple_subtree_state *mast,
struct maple_enode *left, struct maple_enode *middle,
struct maple_enode *right, unsigned char split, unsigned char mid_split)
{
bool new_lmax = true;
mas_node_or_none(mast->l, left);
mas_node_or_none(mast->m, middle);
mas_node_or_none(mast->r, right);
mast->l->min = mast->orig_l->min;
if (split == mast->bn->b_end) { mast->l->max = mast->orig_r->max;
new_lmax = false;
}
mab_mas_cp(mast->bn, 0, split, mast->l, new_lmax);
if (middle) { mab_mas_cp(mast->bn, 1 + split, mid_split, mast->m, true);
mast->m->min = mast->bn->pivot[split] + 1;
split = mid_split;
}
mast->r->max = mast->orig_r->max;
if (right) { mab_mas_cp(mast->bn, 1 + split, mast->bn->b_end, mast->r, false);
mast->r->min = mast->bn->pivot[split] + 1;
}
}
/*
* mast_combine_cp_left - Copy in the original left side of the tree into the
* combined data set in the maple subtree state big node.
* @mast: The maple subtree state
*/
static inline void mast_combine_cp_left(struct maple_subtree_state *mast)
{
unsigned char l_slot = mast->orig_l->offset;
if (!l_slot)
return;
mas_mab_cp(mast->orig_l, 0, l_slot - 1, mast->bn, 0);
}
/*
* mast_combine_cp_right: Copy in the original right side of the tree into the
* combined data set in the maple subtree state big node.
* @mast: The maple subtree state
*/
static inline void mast_combine_cp_right(struct maple_subtree_state *mast)
{
if (mast->bn->pivot[mast->bn->b_end - 1] >= mast->orig_r->max)
return;
mas_mab_cp(mast->orig_r, mast->orig_r->offset + 1,
mt_slot_count(mast->orig_r->node), mast->bn,
mast->bn->b_end);
mast->orig_r->last = mast->orig_r->max;
}
/*
* mast_sufficient: Check if the maple subtree state has enough data in the big
* node to create at least one sufficient node
* @mast: the maple subtree state
*/
static inline bool mast_sufficient(struct maple_subtree_state *mast)
{
if (mast->bn->b_end > mt_min_slot_count(mast->orig_l->node))
return true;
return false;
}
/*
* mast_overflow: Check if there is too much data in the subtree state for a
* single node.
* @mast: The maple subtree state
*/
static inline bool mast_overflow(struct maple_subtree_state *mast)
{
if (mast->bn->b_end >= mt_slot_count(mast->orig_l->node))
return true;
return false;
}
static inline void *mtree_range_walk(struct ma_state *mas)
{
unsigned long *pivots;
unsigned char offset;
struct maple_node *node;
struct maple_enode *next, *last;
enum maple_type type;
void __rcu **slots;
unsigned char end;
unsigned long max, min;
unsigned long prev_max, prev_min;
next = mas->node;
min = mas->min;
max = mas->max;
do {
last = next;
node = mte_to_node(next);
type = mte_node_type(next);
pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max);
prev_min = min;
prev_max = max;
if (pivots[0] >= mas->index) {
offset = 0;
max = pivots[0];
goto next;
}
offset = 1;
while (offset < end) {
if (pivots[offset] >= mas->index) {
max = pivots[offset];
break;
}
offset++;
}
min = pivots[offset - 1] + 1;
next:
slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset);
if (unlikely(ma_dead_node(node)))
goto dead_node;
} while (!ma_is_leaf(type)); mas->end = end;
mas->offset = offset;
mas->index = min;
mas->last = max;
mas->min = prev_min;
mas->max = prev_max;
mas->node = last;
return (void *)next;
dead_node:
mas_reset(mas);
return NULL;
}
/*
* mas_spanning_rebalance() - Rebalance across two nodes which may not be peers.
* @mas: The starting maple state
* @mast: The maple_subtree_state, keeps track of 4 maple states.
* @count: The estimated count of iterations needed.
*
* Follow the tree upwards from @l_mas and @r_mas for @count, or until the root
* is hit. First @b_node is split into two entries which are inserted into the
* next iteration of the loop. @b_node is returned populated with the final
* iteration. @mas is used to obtain allocations. orig_l_mas keeps track of the
* nodes that will remain active by using orig_l_mas->index and orig_l_mas->last
* to account of what has been copied into the new sub-tree. The update of
* orig_l_mas->last is used in mas_consume to find the slots that will need to
* be either freed or destroyed. orig_l_mas->depth keeps track of the height of
* the new sub-tree in case the sub-tree becomes the full tree.
*/
static void mas_spanning_rebalance(struct ma_state *mas,
struct maple_subtree_state *mast, unsigned char count)
{
unsigned char split, mid_split;
unsigned char slot = 0;
struct maple_enode *left = NULL, *middle = NULL, *right = NULL;
struct maple_enode *old_enode;
MA_STATE(l_mas, mas->tree, mas->index, mas->index);
MA_STATE(r_mas, mas->tree, mas->index, mas->last);
MA_STATE(m_mas, mas->tree, mas->index, mas->index);
/*
* The tree needs to be rebalanced and leaves need to be kept at the same level.
* Rebalancing is done by use of the ``struct maple_topiary``.
*/
mast->l = &l_mas;
mast->m = &m_mas;
mast->r = &r_mas;
l_mas.status = r_mas.status = m_mas.status = ma_none;
/* Check if this is not root and has sufficient data. */
if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) &&
unlikely(mast->bn->b_end <= mt_min_slots[mast->bn->type]))
mast_spanning_rebalance(mast);
l_mas.depth = 0;
/*
* Each level of the tree is examined and balanced, pushing data to the left or
* right, or rebalancing against left or right nodes is employed to avoid
* rippling up the tree to limit the amount of churn. Once a new sub-section of
* the tree is created, there may be a mix of new and old nodes. The old nodes
* will have the incorrect parent pointers and currently be in two trees: the
* original tree and the partially new tree. To remedy the parent pointers in
* the old tree, the new data is swapped into the active tree and a walk down
* the tree is performed and the parent pointers are updated.
* See mas_topiary_replace() for more information.
*/
while (count--) {
mast->bn->b_end--;
mast->bn->type = mte_node_type(mast->orig_l->node);
split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle,
&mid_split);
mast_set_split_parents(mast, left, middle, right, split,
mid_split);
mast_cp_to_nodes(mast, left, middle, right, split, mid_split);
/*
* Copy data from next level in the tree to mast->bn from next
* iteration
*/
memset(mast->bn, 0, sizeof(struct maple_big_node));
mast->bn->type = mte_node_type(left);
l_mas.depth++;
/* Root already stored in l->node. */
if (mas_is_root_limits(mast->l))
goto new_root;
mast_ascend(mast);
mast_combine_cp_left(mast);
l_mas.offset = mast->bn->b_end;
mab_set_b_end(mast->bn, &l_mas, left); mab_set_b_end(mast->bn, &m_mas, middle); mab_set_b_end(mast->bn, &r_mas, right);
/* Copy anything necessary out of the right node. */
mast_combine_cp_right(mast);
mast->orig_l->last = mast->orig_l->max;
if (mast_sufficient(mast))
continue;
if (mast_overflow(mast))
continue;
/* May be a new root stored in mast->bn */
if (mas_is_root_limits(mast->orig_l))
break;
mast_spanning_rebalance(mast);
/* rebalancing from other nodes may require another loop. */
if (!count)
count++;
}
l_mas.node = mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)),
mte_node_type(mast->orig_l->node));
l_mas.depth++;
mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, &l_mas, true);
mas_set_parent(mas, left, l_mas.node, slot);
if (middle) mas_set_parent(mas, middle, l_mas.node, ++slot); if (right) mas_set_parent(mas, right, l_mas.node, ++slot); if (mas_is_root_limits(mast->l)) {
new_root:
mas_mn(mast->l)->parent = ma_parent_ptr(mas_tree_parent(mas));
while (!mte_is_root(mast->orig_l->node))
mast_ascend(mast);
} else {
mas_mn(&l_mas)->parent = mas_mn(mast->orig_l)->parent;
}
old_enode = mast->orig_l->node;
mas->depth = l_mas.depth;
mas->node = l_mas.node;
mas->min = l_mas.min;
mas->max = l_mas.max;
mas->offset = l_mas.offset;
mas_wmb_replace(mas, old_enode);
mtree_range_walk(mas);
return;
}
/*
* mas_rebalance() - Rebalance a given node.
* @mas: The maple state
* @b_node: The big maple node.
*
* Rebalance two nodes into a single node or two new nodes that are sufficient.
* Continue upwards until tree is sufficient.
*/
static inline void mas_rebalance(struct ma_state *mas,
struct maple_big_node *b_node)
{
char empty_count = mas_mt_height(mas);
struct maple_subtree_state mast;
unsigned char shift, b_end = ++b_node->b_end;
MA_STATE(l_mas, mas->tree, mas->index, mas->last);
MA_STATE(r_mas, mas->tree, mas->index, mas->last);
trace_ma_op(__func__, mas);
/*
* Rebalancing occurs if a node is insufficient. Data is rebalanced
* against the node to the right if it exists, otherwise the node to the
* left of this node is rebalanced against this node. If rebalancing
* causes just one node to be produced instead of two, then the parent
* is also examined and rebalanced if it is insufficient. Every level
* tries to combine the data in the same way. If one node contains the
* entire range of the tree, then that node is used as a new root node.
*/
mast.orig_l = &l_mas;
mast.orig_r = &r_mas;
mast.bn = b_node;
mast.bn->type = mte_node_type(mas->node);
l_mas = r_mas = *mas;
if (mas_next_sibling(&r_mas)) {
mas_mab_cp(&r_mas, 0, mt_slot_count(r_mas.node), b_node, b_end);
r_mas.last = r_mas.index = r_mas.max;
} else {
mas_prev_sibling(&l_mas); shift = mas_data_end(&l_mas) + 1;
mab_shift_right(b_node, shift);
mas->offset += shift;
mas_mab_cp(&l_mas, 0, shift - 1, b_node, 0);
b_node->b_end = shift + b_end;
l_mas.index = l_mas.last = l_mas.min;
}
return mas_spanning_rebalance(mas, &mast, empty_count);
}
/*
* mas_destroy_rebalance() - Rebalance left-most node while destroying the maple
* state.
* @mas: The maple state
* @end: The end of the left-most node.
*
* During a mass-insert event (such as forking), it may be necessary to
* rebalance the left-most node when it is not sufficient.
*/
static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end)
{
enum maple_type mt = mte_node_type(mas->node);
struct maple_node reuse, *newnode, *parent, *new_left, *left, *node;
struct maple_enode *eparent, *old_eparent;
unsigned char offset, tmp, split = mt_slots[mt] / 2;
void __rcu **l_slots, **slots;
unsigned long *l_pivs, *pivs, gap;
bool in_rcu = mt_in_rcu(mas->tree);
MA_STATE(l_mas, mas->tree, mas->index, mas->last);
l_mas = *mas;
mas_prev_sibling(&l_mas);
/* set up node. */
if (in_rcu) { newnode = mas_pop_node(mas);
} else {
newnode = &reuse;
}
node = mas_mn(mas);
newnode->parent = node->parent;
slots = ma_slots(newnode, mt);
pivs = ma_pivots(newnode, mt);
left = mas_mn(&l_mas);
l_slots = ma_slots(left, mt);
l_pivs = ma_pivots(left, mt);
if (!l_slots[split])
split++;
tmp = mas_data_end(&l_mas) - split;
memcpy(slots, l_slots + split + 1, sizeof(void *) * tmp);
memcpy(pivs, l_pivs + split + 1, sizeof(unsigned long) * tmp);
pivs[tmp] = l_mas.max;
memcpy(slots + tmp, ma_slots(node, mt), sizeof(void *) * end); memcpy(pivs + tmp, ma_pivots(node, mt), sizeof(unsigned long) * end);
l_mas.max = l_pivs[split];
mas->min = l_mas.max + 1;
old_eparent = mt_mk_node(mte_parent(l_mas.node),
mas_parent_type(&l_mas, l_mas.node));
tmp += end;
if (!in_rcu) {
unsigned char max_p = mt_pivots[mt];
unsigned char max_s = mt_slots[mt];
if (tmp < max_p) memset(pivs + tmp, 0,
sizeof(unsigned long) * (max_p - tmp));
if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp));
memcpy(node, newnode, sizeof(struct maple_node));
ma_set_meta(node, mt, 0, tmp - 1);
mte_set_pivot(old_eparent, mte_parent_slot(l_mas.node),
l_pivs[split]);
/* Remove data from l_pivs. */
tmp = split + 1;
memset(l_pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp));
memset(l_slots + tmp, 0, sizeof(void *) * (max_s - tmp));
ma_set_meta(left, mt, 0, split);
eparent = old_eparent;
goto done;
}
/* RCU requires replacing both l_mas, mas, and parent. */
mas->node = mt_mk_node(newnode, mt);
ma_set_meta(newnode, mt, 0, tmp);
new_left = mas_pop_node(mas);
new_left->parent = left->parent;
mt = mte_node_type(l_mas.node);
slots = ma_slots(new_left, mt);
pivs = ma_pivots(new_left, mt);
memcpy(slots, l_slots, sizeof(void *) * split);
memcpy(pivs, l_pivs, sizeof(unsigned long) * split);
ma_set_meta(new_left, mt, 0, split);
l_mas.node = mt_mk_node(new_left, mt);
/* replace parent. */
offset = mte_parent_slot(mas->node); mt = mas_parent_type(&l_mas, l_mas.node); parent = mas_pop_node(mas); slots = ma_slots(parent, mt);
pivs = ma_pivots(parent, mt);
memcpy(parent, mte_to_node(old_eparent), sizeof(struct maple_node));
rcu_assign_pointer(slots[offset], mas->node);
rcu_assign_pointer(slots[offset - 1], l_mas.node);
pivs[offset - 1] = l_mas.max;
eparent = mt_mk_node(parent, mt);
done:
gap = mas_leaf_max_gap(mas);
mte_set_gap(eparent, mte_parent_slot(mas->node), gap);
gap = mas_leaf_max_gap(&l_mas);
mte_set_gap(eparent, mte_parent_slot(l_mas.node), gap);
mas_ascend(mas);
if (in_rcu) { mas_replace_node(mas, old_eparent);
mas_adopt_children(mas, mas->node);
}
mas_update_gap(mas);
}
/*
* mas_split_final_node() - Split the final node in a subtree operation.
* @mast: the maple subtree state
* @mas: The maple state
* @height: The height of the tree in case it's a new root.
*/
static inline void mas_split_final_node(struct maple_subtree_state *mast,
struct ma_state *mas, int height)
{
struct maple_enode *ancestor;
if (mte_is_root(mas->node)) { if (mt_is_alloc(mas->tree))
mast->bn->type = maple_arange_64;
else
mast->bn->type = maple_range_64;
mas->depth = height;
}
/*
* Only a single node is used here, could be root.
* The Big_node data should just fit in a single node.
*/
ancestor = mas_new_ma_node(mas, mast->bn);
mas_set_parent(mas, mast->l->node, ancestor, mast->l->offset);
mas_set_parent(mas, mast->r->node, ancestor, mast->r->offset);
mte_to_node(ancestor)->parent = mas_mn(mas)->parent;
mast->l->node = ancestor;
mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true);
mas->offset = mast->bn->b_end - 1;
}
/*
* mast_fill_bnode() - Copy data into the big node in the subtree state
* @mast: The maple subtree state
* @mas: the maple state
* @skip: The number of entries to skip for new nodes insertion.
*/
static inline void mast_fill_bnode(struct maple_subtree_state *mast,
struct ma_state *mas,
unsigned char skip)
{
bool cp = true;
unsigned char split;
memset(mast->bn, 0, sizeof(struct maple_big_node));
if (mte_is_root(mas->node)) {
cp = false;
} else {
mas_ascend(mas);
mas->offset = mte_parent_slot(mas->node);
}
if (cp && mast->l->offset) mas_mab_cp(mas, 0, mast->l->offset - 1, mast->bn, 0);
split = mast->bn->b_end;
mab_set_b_end(mast->bn, mast->l, mast->l->node);
mast->r->offset = mast->bn->b_end;
mab_set_b_end(mast->bn, mast->r, mast->r->node);
if (mast->bn->pivot[mast->bn->b_end - 1] == mas->max)
cp = false;
if (cp) mas_mab_cp(mas, split + skip, mt_slot_count(mas->node) - 1,
mast->bn, mast->bn->b_end);
mast->bn->b_end--;
mast->bn->type = mte_node_type(mas->node);
}
/*
* mast_split_data() - Split the data in the subtree state big node into regular
* nodes.
* @mast: The maple subtree state
* @mas: The maple state
* @split: The location to split the big node
*/
static inline void mast_split_data(struct maple_subtree_state *mast,
struct ma_state *mas, unsigned char split)
{
unsigned char p_slot;
mab_mas_cp(mast->bn, 0, split, mast->l, true);
mte_set_pivot(mast->r->node, 0, mast->r->max);
mab_mas_cp(mast->bn, split + 1, mast->bn->b_end, mast->r, false);
mast->l->offset = mte_parent_slot(mas->node);
mast->l->max = mast->bn->pivot[split];
mast->r->min = mast->l->max + 1;
if (mte_is_leaf(mas->node))
return;
p_slot = mast->orig_l->offset;
mas_set_split_parent(mast->orig_l, mast->l->node, mast->r->node,
&p_slot, split);
mas_set_split_parent(mast->orig_r, mast->l->node, mast->r->node,
&p_slot, split);
}
/*
* mas_push_data() - Instead of splitting a node, it is beneficial to push the
* data to the right or left node if there is room.
* @mas: The maple state
* @height: The current height of the maple state
* @mast: The maple subtree state
* @left: Push left or not.
*
* Keeping the height of the tree low means faster lookups.
*
* Return: True if pushed, false otherwise.
*/
static inline bool mas_push_data(struct ma_state *mas, int height,
struct maple_subtree_state *mast, bool left)
{
unsigned char slot_total = mast->bn->b_end;
unsigned char end, space, split;
MA_STATE(tmp_mas, mas->tree, mas->index, mas->last);
tmp_mas = *mas;
tmp_mas.depth = mast->l->depth;
if (left && !mas_prev_sibling(&tmp_mas))
return false;
else if (!left && !mas_next_sibling(&tmp_mas))
return false;
end = mas_data_end(&tmp_mas);
slot_total += end;
space = 2 * mt_slot_count(mas->node) - 2;
/* -2 instead of -1 to ensure there isn't a triple split */
if (ma_is_leaf(mast->bn->type))
space--;
if (mas->max == ULONG_MAX)
space--;
if (slot_total >= space)
return false;
/* Get the data; Fill mast->bn */
mast->bn->b_end++;
if (left) {
mab_shift_right(mast->bn, end + 1);
mas_mab_cp(&tmp_mas, 0, end, mast->bn, 0);
mast->bn->b_end = slot_total + 1;
} else {
mas_mab_cp(&tmp_mas, 0, end, mast->bn, mast->bn->b_end);
}
/* Configure mast for splitting of mast->bn */
split = mt_slots[mast->bn->type] - 2;
if (left) {
/* Switch mas to prev node */
*mas = tmp_mas;
/* Start using mast->l for the left side. */
tmp_mas.node = mast->l->node;
*mast->l = tmp_mas;
} else {
tmp_mas.node = mast->r->node;
*mast->r = tmp_mas;
split = slot_total - split;
}
split = mab_no_null_split(mast->bn, split, mt_slots[mast->bn->type]);
/* Update parent slot for split calculation. */
if (left) mast->orig_l->offset += end + 1;
mast_split_data(mast, mas, split);
mast_fill_bnode(mast, mas, 2);
mas_split_final_node(mast, mas, height + 1);
return true;
}
/*
* mas_split() - Split data that is too big for one node into two.
* @mas: The maple state
* @b_node: The maple big node
*/
static void mas_split(struct ma_state *mas, struct maple_big_node *b_node)
{
struct maple_subtree_state mast;
int height = 0;
unsigned char mid_split, split = 0;
struct maple_enode *old;
/*
* Splitting is handled differently from any other B-tree; the Maple
* Tree splits upwards. Splitting up means that the split operation
* occurs when the walk of the tree hits the leaves and not on the way
* down. The reason for splitting up is that it is impossible to know
* how much space will be needed until the leaf is (or leaves are)
* reached. Since overwriting data is allowed and a range could
* overwrite more than one range or result in changing one entry into 3
* entries, it is impossible to know if a split is required until the
* data is examined.
*
* Splitting is a balancing act between keeping allocations to a minimum
* and avoiding a 'jitter' event where a tree is expanded to make room
* for an entry followed by a contraction when the entry is removed. To
* accomplish the balance, there are empty slots remaining in both left
* and right nodes after a split.
*/
MA_STATE(l_mas, mas->tree, mas->index, mas->last);
MA_STATE(r_mas, mas->tree, mas->index, mas->last);
MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last);
MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last);
trace_ma_op(__func__, mas);
mas->depth = mas_mt_height(mas);
mast.l = &l_mas;
mast.r = &r_mas;
mast.orig_l = &prev_l_mas;
mast.orig_r = &prev_r_mas;
mast.bn = b_node;
while (height++ <= mas->depth) {
if (mt_slots[b_node->type] > b_node->b_end) {
mas_split_final_node(&mast, mas, height);
break;
}
l_mas = r_mas = *mas;
l_mas.node = mas_new_ma_node(mas, b_node); r_mas.node = mas_new_ma_node(mas, b_node);
/*
* Another way that 'jitter' is avoided is to terminate a split up early if the
* left or right node has space to spare. This is referred to as "pushing left"
* or "pushing right" and is similar to the B* tree, except the nodes left or
* right can rarely be reused due to RCU, but the ripple upwards is halted which
* is a significant savings.
*/
/* Try to push left. */
if (mas_push_data(mas, height, &mast, true))
break;
/* Try to push right. */
if (mas_push_data(mas, height, &mast, false))
break;
split = mab_calc_split(mas, b_node, &mid_split);
mast_split_data(&mast, mas, split);
/*
* Usually correct, mab_mas_cp in the above call overwrites
* r->max.
*/
mast.r->max = mas->max;
mast_fill_bnode(&mast, mas, 1);
prev_l_mas = *mast.l;
prev_r_mas = *mast.r;
}
/* Set the original node as dead */
old = mas->node;
mas->node = l_mas.node;
mas_wmb_replace(mas, old);
mtree_range_walk(mas);
return;
}
/*
* mas_commit_b_node() - Commit the big node into the tree.
* @wr_mas: The maple write state
* @b_node: The maple big node
*/
static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas,
struct maple_big_node *b_node)
{
enum store_type type = wr_mas->mas->store_type;
WARN_ON_ONCE(type != wr_rebalance && type != wr_split_store); if (type == wr_rebalance) return mas_rebalance(wr_mas->mas, b_node); return mas_split(wr_mas->mas, b_node);
}
/*
* mas_root_expand() - Expand a root to a node
* @mas: The maple state
* @entry: The entry to store into the tree
*/
static inline void mas_root_expand(struct ma_state *mas, void *entry)
{ void *contents = mas_root_locked(mas);
enum maple_type type = maple_leaf_64;
struct maple_node *node;
void __rcu **slots;
unsigned long *pivots;
int slot = 0;
node = mas_pop_node(mas);
pivots = ma_pivots(node, type);
slots = ma_slots(node, type);
node->parent = ma_parent_ptr(mas_tree_parent(mas));
mas->node = mt_mk_node(node, type);
mas->status = ma_active;
if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents);
if (likely(mas->index > 1))
slot++;
}
pivots[slot++] = mas->index - 1;
}
rcu_assign_pointer(slots[slot], entry);
mas->offset = slot;
pivots[slot] = mas->last;
if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX;
mas->depth = 1;
mas_set_height(mas);
ma_set_meta(node, maple_leaf_64, 0, slot);
/* swap the new root into the tree */
rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node));
return;
}
/*
* mas_store_root() - Storing value into root.
* @mas: The maple state
* @entry: The entry to store.
*
* There is no root node now and we are storing a value into the root - this
* function either assigns the pointer or expands into a node.
*/
static inline void mas_store_root(struct ma_state *mas, void *entry)
{
if (!entry) {
if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL);
} else if (likely((mas->last != 0) || (mas->index != 0)))
mas_root_expand(mas, entry);
else if (((unsigned long) (entry) & 3) == 2)
mas_root_expand(mas, entry);
else {
rcu_assign_pointer(mas->tree->ma_root, entry);
mas->status = ma_start;
}
}
/*
* mas_is_span_wr() - Check if the write needs to be treated as a write that
* spans the node.
* @wr_mas: The maple write state
*
* Spanning writes are writes that start in one node and end in another OR if
* the write of a %NULL will cause the node to end with a %NULL.
*
* Return: True if this is a spanning write, false otherwise.
*/
static bool mas_is_span_wr(struct ma_wr_state *wr_mas)
{
unsigned long max = wr_mas->r_max;
unsigned long last = wr_mas->mas->last;
enum maple_type type = wr_mas->type;
void *entry = wr_mas->entry;
/* Contained in this pivot, fast path */
if (last < max)
return false;
if (ma_is_leaf(type)) {
max = wr_mas->mas->max;
if (last < max)
return false;
}
if (last == max) {
/*
* The last entry of leaf node cannot be NULL unless it is the
* rightmost node (writing ULONG_MAX), otherwise it spans slots.
*/
if (entry || last == ULONG_MAX)
return false;
}
trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry);
return true;
}
static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas)
{
wr_mas->type = mte_node_type(wr_mas->mas->node);
mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type);
}
static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas)
{
wr_mas->mas->max = wr_mas->r_max;
wr_mas->mas->min = wr_mas->r_min;
wr_mas->mas->node = wr_mas->content;
wr_mas->mas->offset = 0;
wr_mas->mas->depth++;
}
/*
* mas_wr_walk() - Walk the tree for a write.
* @wr_mas: The maple write state
*
* Uses mas_slot_locked() and does not need to worry about dead nodes.
*
* Return: True if it's contained in a node, false on spanning write.
*/
static bool mas_wr_walk(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
while (true) {
mas_wr_walk_descend(wr_mas);
if (unlikely(mas_is_span_wr(wr_mas)))
return false;
wr_mas->content = mas_slot_locked(mas, wr_mas->slots,
mas->offset);
if (ma_is_leaf(wr_mas->type))
return true;
mas_wr_walk_traverse(wr_mas);
}
return true;
}
static void mas_wr_walk_index(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
while (true) {
mas_wr_walk_descend(wr_mas);
wr_mas->content = mas_slot_locked(mas, wr_mas->slots,
mas->offset);
if (ma_is_leaf(wr_mas->type))
return;
mas_wr_walk_traverse(wr_mas);
}
}
/*
* mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs.
* @l_wr_mas: The left maple write state
* @r_wr_mas: The right maple write state
*/
static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas,
struct ma_wr_state *r_wr_mas)
{
struct ma_state *r_mas = r_wr_mas->mas;
struct ma_state *l_mas = l_wr_mas->mas;
unsigned char l_slot;
l_slot = l_mas->offset;
if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) {
if (l_slot > 1)
l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1;
else
l_mas->index = l_mas->min;
l_mas->offset = l_slot - 1;
}
if (!r_wr_mas->content) {
if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max;
r_mas->offset++;
} else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots,
r_wr_mas->type, r_mas->offset + 1);
r_mas->offset++;
}
}
static inline void *mas_state_walk(struct ma_state *mas)
{
void *entry;
entry = mas_start(mas);
if (mas_is_none(mas))
return NULL;
if (mas_is_ptr(mas))
return entry;
return mtree_range_walk(mas);
}
/*
* mtree_lookup_walk() - Internal quick lookup that does not keep maple state up
* to date.
*
* @mas: The maple state.
*
* Note: Leaves mas in undesirable state.
* Return: The entry for @mas->index or %NULL on dead node.
*/
static inline void *mtree_lookup_walk(struct ma_state *mas)
{
unsigned long *pivots;
unsigned char offset;
struct maple_node *node;
struct maple_enode *next;
enum maple_type type;
void __rcu **slots;
unsigned char end;
next = mas->node;
do {
node = mte_to_node(next);
type = mte_node_type(next);
pivots = ma_pivots(node, type);
end = mt_pivots[type];
offset = 0;
do {
if (pivots[offset] >= mas->index)
break;
} while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset);
if (unlikely(ma_dead_node(node)))
goto dead_node;
} while (!ma_is_leaf(type));
return (void *)next;
dead_node:
mas_reset(mas);
return NULL;
}
static void mte_destroy_walk(struct maple_enode *, struct maple_tree *);
/*
* mas_new_root() - Create a new root node that only contains the entry passed
* in.
* @mas: The maple state
* @entry: The entry to store.
*
* Only valid when the index == 0 and the last == ULONG_MAX
*/
static inline void mas_new_root(struct ma_state *mas, void *entry)
{
struct maple_enode *root = mas_root_locked(mas);
enum maple_type type = maple_leaf_64;
struct maple_node *node;
void __rcu **slots;
unsigned long *pivots;
WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX);
if (!entry) {
mas->depth = 0;
mas_set_height(mas);
rcu_assign_pointer(mas->tree->ma_root, entry);
mas->status = ma_start;
goto done;
}
node = mas_pop_node(mas);
pivots = ma_pivots(node, type);
slots = ma_slots(node, type);
node->parent = ma_parent_ptr(mas_tree_parent(mas));
mas->node = mt_mk_node(node, type);
mas->status = ma_active;
rcu_assign_pointer(slots[0], entry);
pivots[0] = mas->last;
mas->depth = 1;
mas_set_height(mas);
rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node));
done:
if (xa_is_node(root))
mte_destroy_walk(root, mas->tree);
return;
}
/*
* mas_wr_spanning_store() - Create a subtree with the store operation completed
* and new nodes where necessary, then place the sub-tree in the actual tree.
* Note that mas is expected to point to the node which caused the store to
* span.
* @wr_mas: The maple write state
*/
static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas)
{
struct maple_subtree_state mast;
struct maple_big_node b_node;
struct ma_state *mas;
unsigned char height;
/* Left and Right side of spanning store */
MA_STATE(l_mas, NULL, 0, 0);
MA_STATE(r_mas, NULL, 0, 0);
MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry);
MA_WR_STATE(l_wr_mas, &l_mas, wr_mas->entry);
/*
* A store operation that spans multiple nodes is called a spanning
* store and is handled early in the store call stack by the function
* mas_is_span_wr(). When a spanning store is identified, the maple
* state is duplicated. The first maple state walks the left tree path
* to ``index``, the duplicate walks the right tree path to ``last``.
* The data in the two nodes are combined into a single node, two nodes,
* or possibly three nodes (see the 3-way split above). A ``NULL``
* written to the last entry of a node is considered a spanning store as
* a rebalance is required for the operation to complete and an overflow
* of data may happen.
*/
mas = wr_mas->mas;
trace_ma_op(__func__, mas);
if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry);
/*
* Node rebalancing may occur due to this store, so there may be three new
* entries per level plus a new root.
*/
height = mas_mt_height(mas);
/*
* Set up right side. Need to get to the next offset after the spanning
* store to ensure it's not NULL and to combine both the next node and
* the node with the start together.
*/
r_mas = *mas;
/* Avoid overflow, walk to next slot in the tree. */
if (r_mas.last + 1) r_mas.last++;
r_mas.index = r_mas.last;
mas_wr_walk_index(&r_wr_mas);
r_mas.last = r_mas.index = mas->last;
/* Set up left side. */
l_mas = *mas;
mas_wr_walk_index(&l_wr_mas);
if (!wr_mas->entry) { mas_extend_spanning_null(&l_wr_mas, &r_wr_mas);
mas->offset = l_mas.offset;
mas->index = l_mas.index;
mas->last = l_mas.last = r_mas.last;
}
/* expanding NULLs may make this cover the entire range */
if (!l_mas.index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX);
return mas_new_root(mas, wr_mas->entry);
}
memset(&b_node, 0, sizeof(struct maple_big_node));
/* Copy l_mas and store the value in b_node. */
mas_store_b_node(&l_wr_mas, &b_node, l_mas.end);
/* Copy r_mas into b_node if there is anything to copy. */
if (r_mas.max > r_mas.last)
mas_mab_cp(&r_mas, r_mas.offset, r_mas.end,
&b_node, b_node.b_end + 1);
else
b_node.b_end++;
/* Stop spanning searches by searching for just index. */
l_mas.index = l_mas.last = mas->index;
mast.bn = &b_node;
mast.orig_l = &l_mas;
mast.orig_r = &r_mas;
/* Combine l_mas and r_mas and split them up evenly again. */
return mas_spanning_rebalance(mas, &mast, height + 1);
}
/*
* mas_wr_node_store() - Attempt to store the value in a node
* @wr_mas: The maple write state
*
* Attempts to reuse the node, but may allocate.
*/
static inline void mas_wr_node_store(struct ma_wr_state *wr_mas,
unsigned char new_end)
{
struct ma_state *mas = wr_mas->mas;
void __rcu **dst_slots;
unsigned long *dst_pivots;
unsigned char dst_offset, offset_end = wr_mas->offset_end;
struct maple_node reuse, *newnode;
unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type];
bool in_rcu = mt_in_rcu(mas->tree);
if (mas->last == wr_mas->end_piv)
offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) mas_bulk_rebalance(mas, mas->end, wr_mas->type);
/* set up node. */
if (in_rcu) {
newnode = mas_pop_node(mas);
} else {
memset(&reuse, 0, sizeof(struct maple_node));
newnode = &reuse;
}
newnode->parent = mas_mn(mas)->parent;
dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type);
/* Copy from start to insert point */
memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset);
memcpy(dst_slots, wr_mas->slots, sizeof(void *) * mas->offset);
/* Handle insert of new range starting after old range */
if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content);
dst_pivots[mas->offset++] = mas->index - 1;
}
/* Store the new entry and range end. */
if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last;
rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry);
/*
* this range wrote to the end of the node or it overwrote the rest of
* the data
*/
if (offset_end > mas->end)
goto done;
dst_offset = mas->offset + 1;
/* Copy to the end of node if necessary. */
copy_size = mas->end - offset_end + 1;
memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end,
sizeof(void *) * copy_size);
memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end,
sizeof(unsigned long) * (copy_size - 1));
if (new_end < node_pivots) dst_pivots[new_end] = mas->max;
done:
mas_leaf_set_meta(newnode, maple_leaf_64, new_end);
if (in_rcu) {
struct maple_enode *old_enode = mas->node;
mas->node = mt_mk_node(newnode, wr_mas->type);
mas_replace_node(mas, old_enode);
} else {
memcpy(wr_mas->node, newnode, sizeof(struct maple_node));
}
trace_ma_write(__func__, mas, 0, wr_mas->entry);
mas_update_gap(mas);
mas->end = new_end;
return;
}
/*
* mas_wr_slot_store: Attempt to store a value in a slot.
* @wr_mas: the maple write state
*/
static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
unsigned char offset = mas->offset;
void __rcu **slots = wr_mas->slots;
bool gap = false;
gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1);
if (wr_mas->offset_end - offset == 1) {
if (mas->index == wr_mas->r_min) {
/* Overwriting the range and a part of the next one */
rcu_assign_pointer(slots[offset], wr_mas->entry);
wr_mas->pivots[offset] = mas->last;
} else {
/* Overwriting a part of the range and the next one */
rcu_assign_pointer(slots[offset + 1], wr_mas->entry);
wr_mas->pivots[offset] = mas->index - 1;
mas->offset++; /* Keep mas accurate. */
}
} else {
WARN_ON_ONCE(mt_in_rcu(mas->tree));
/*
* Expand the range, only partially overwriting the previous and
* next ranges
*/
gap |= !mt_slot_locked(mas->tree, slots, offset + 2);
rcu_assign_pointer(slots[offset + 1], wr_mas->entry);
wr_mas->pivots[offset] = mas->index - 1;
wr_mas->pivots[offset + 1] = mas->last;
mas->offset++; /* Keep mas accurate. */
}
trace_ma_write(__func__, mas, 0, wr_mas->entry);
/*
* Only update gap when the new entry is empty or there is an empty
* entry in the original two ranges.
*/
if (!wr_mas->entry || gap) mas_update_gap(mas);
return;
}
static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
if (!wr_mas->slots[wr_mas->offset_end]) {
/* If this one is null, the next and prev are not */
mas->last = wr_mas->end_piv;
} else {
/* Check next slot(s) if we are overwriting the end */
if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) &&
!wr_mas->slots[wr_mas->offset_end + 1]) {
wr_mas->offset_end++;
if (wr_mas->offset_end == mas->end)
mas->last = mas->max;
else
mas->last = wr_mas->pivots[wr_mas->offset_end];
wr_mas->end_piv = mas->last;
}
}
if (!wr_mas->content) {
/* If this one is null, the next and prev are not */
mas->index = wr_mas->r_min;
} else {
/* Check prev slot if we are overwriting the start */
if (mas->index == wr_mas->r_min && mas->offset &&
!wr_mas->slots[mas->offset - 1]) {
mas->offset--;
wr_mas->r_min = mas->index =
mas_safe_min(mas, wr_mas->pivots, mas->offset);
wr_mas->r_max = wr_mas->pivots[mas->offset];
}
}
}
static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas)
{
while ((wr_mas->offset_end < wr_mas->mas->end) &&
(wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end]))
wr_mas->offset_end++;
if (wr_mas->offset_end < wr_mas->mas->end)
wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end];
else
wr_mas->end_piv = wr_mas->mas->max;
}
static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
unsigned char new_end = mas->end + 2;
new_end -= wr_mas->offset_end - mas->offset;
if (wr_mas->r_min == mas->index)
new_end--;
if (wr_mas->end_piv == mas->last)
new_end--;
return new_end;
}
/*
* mas_wr_append: Attempt to append
* @wr_mas: the maple write state
* @new_end: The end of the node after the modification
*
* This is currently unsafe in rcu mode since the end of the node may be cached
* by readers while the node contents may be updated which could result in
* inaccurate information.
*/
static inline void mas_wr_append(struct ma_wr_state *wr_mas,
unsigned char new_end)
{
struct ma_state *mas = wr_mas->mas;
void __rcu **slots;
unsigned char end = mas->end;
if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end];
ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end);
}
slots = wr_mas->slots;
if (new_end == end + 1) {
if (mas->last == wr_mas->r_max) {
/* Append to end of range */
rcu_assign_pointer(slots[new_end], wr_mas->entry);
wr_mas->pivots[end] = mas->index - 1;
mas->offset = new_end;
} else {
/* Append to start of range */
rcu_assign_pointer(slots[new_end], wr_mas->content);
wr_mas->pivots[end] = mas->last;
rcu_assign_pointer(slots[end], wr_mas->entry);
}
} else {
/* Append to the range without touching any boundaries. */
rcu_assign_pointer(slots[new_end], wr_mas->content);
wr_mas->pivots[end + 1] = mas->last;
rcu_assign_pointer(slots[end + 1], wr_mas->entry);
wr_mas->pivots[end] = mas->index - 1;
mas->offset = end + 1;
}
if (!wr_mas->content || !wr_mas->entry)
mas_update_gap(mas);
mas->end = new_end;
trace_ma_write(__func__, mas, new_end, wr_mas->entry);
return;
}
/*
* mas_wr_bnode() - Slow path for a modification.
* @wr_mas: The write maple state
*
* This is where split, rebalance end up.
*/
static void mas_wr_bnode(struct ma_wr_state *wr_mas)
{
struct maple_big_node b_node;
trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
memset(&b_node, 0, sizeof(struct maple_big_node));
mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
mas_commit_b_node(wr_mas, &b_node);
}
/*
* mas_wr_store_entry() - Internal call to store a value
* @wr_mas: The maple write state
*/
static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
unsigned char new_end = mas_wr_new_end(wr_mas);
switch (mas->store_type) {
case wr_invalid:
MT_BUG_ON(mas->tree, 1);
return;
case wr_new_root:
mas_new_root(mas, wr_mas->entry);
break;
case wr_store_root:
mas_store_root(mas, wr_mas->entry);
break;
case wr_exact_fit:
rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry);
if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas);
break;
case wr_append:
mas_wr_append(wr_mas, new_end);
break;
case wr_slot_store:
mas_wr_slot_store(wr_mas);
break;
case wr_node_store:
mas_wr_node_store(wr_mas, new_end);
break;
case wr_spanning_store:
mas_wr_spanning_store(wr_mas);
break;
case wr_split_store:
case wr_rebalance:
mas_wr_bnode(wr_mas);
break;
}
return;
}
static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
if (!mas_is_active(mas)) {
if (mas_is_start(mas))
goto set_content;
if (unlikely(mas_is_paused(mas)))
goto reset;
if (unlikely(mas_is_none(mas)))
goto reset;
if (unlikely(mas_is_overflow(mas)))
goto reset;
if (unlikely(mas_is_underflow(mas)))
goto reset;
}
/*
* A less strict version of mas_is_span_wr() where we allow spanning
* writes within this node. This is to stop partial walks in
* mas_prealloc() from being reset.
*/
if (mas->last > mas->max)
goto reset;
if (wr_mas->entry)
goto set_content;
if (mte_is_leaf(mas->node) && mas->last == mas->max)
goto reset;
goto set_content;
reset:
mas_reset(mas);
set_content:
wr_mas->content = mas_start(mas);
}
/**
* mas_prealloc_calc() - Calculate number of nodes needed for a
* given store oepration
* @mas: The maple state
* @entry: The entry to store into the tree
*
* Return: Number of nodes required for preallocation.
*/
static inline int mas_prealloc_calc(struct ma_state *mas, void *entry)
{
int ret = mas_mt_height(mas) * 3 + 1;
switch (mas->store_type) {
case wr_invalid:
WARN_ON_ONCE(1);
break;
case wr_new_root:
ret = 1;
break;
case wr_store_root:
if (likely((mas->last != 0) || (mas->index != 0)))
ret = 1;
else if (((unsigned long) (entry) & 3) == 2)
ret = 1;
else
ret = 0;
break;
case wr_spanning_store:
ret = mas_mt_height(mas) * 3 + 1;
break;
case wr_split_store:
ret = mas_mt_height(mas) * 2 + 1;
break;
case wr_rebalance:
ret = mas_mt_height(mas) * 2 - 1;
break;
case wr_node_store:
ret = mt_in_rcu(mas->tree) ? 1 : 0;
break;
case wr_append:
case wr_exact_fit:
case wr_slot_store:
ret = 0;
}
return ret;
}
/*
* mas_wr_store_type() - Determine the store type for a given
* store operation.
* @wr_mas: The maple write state
*
* Return: the type of store needed for the operation
*/
static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas)
{
struct ma_state *mas = wr_mas->mas;
unsigned char new_end;
if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
return wr_store_root;
if (unlikely(!mas_wr_walk(wr_mas)))
return wr_spanning_store;
/* At this point, we are at the leaf node that needs to be altered. */
mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last))
return wr_exact_fit;
if (unlikely(!mas->index && mas->last == ULONG_MAX))
return wr_new_root;
new_end = mas_wr_new_end(wr_mas);
/* Potential spanning rebalance collapsing a node */
if (new_end < mt_min_slots[wr_mas->type]) {
if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK))
return wr_rebalance;
return wr_node_store;
}
if (new_end >= mt_slots[wr_mas->type])
return wr_split_store;
if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end))
return wr_append;
if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) ||
(wr_mas->offset_end - mas->offset == 1)))
return wr_slot_store;
return wr_node_store;
}
/**
* mas_wr_preallocate() - Preallocate enough nodes for a store operation
* @wr_mas: The maple write state
* @entry: The entry that will be stored
*
*/
static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry)
{
struct ma_state *mas = wr_mas->mas;
int request;
mas_wr_prealloc_setup(wr_mas);
mas->store_type = mas_wr_store_type(wr_mas);
request = mas_prealloc_calc(mas, entry); if (!request)
return;
mas_node_count(mas, request);
}
/**
* mas_insert() - Internal call to insert a value
* @mas: The maple state
* @entry: The entry to store
*
* Return: %NULL or the contents that already exists at the requested index
* otherwise. The maple state needs to be checked for error conditions.
*/
static inline void *mas_insert(struct ma_state *mas, void *entry)
{
MA_WR_STATE(wr_mas, mas, entry);
/*
* Inserting a new range inserts either 0, 1, or 2 pivots within the
* tree. If the insert fits exactly into an existing gap with a value
* of NULL, then the slot only needs to be written with the new value.
* If the range being inserted is adjacent to another range, then only a
* single pivot needs to be inserted (as well as writing the entry). If
* the new range is within a gap but does not touch any other ranges,
* then two pivots need to be inserted: the start - 1, and the end. As
* usual, the entry must be written. Most operations require a new node
* to be allocated and replace an existing node to ensure RCU safety,
* when in RCU mode. The exception to requiring a newly allocated node
* is when inserting at the end of a node (appending). When done
* carefully, appending can reuse the node in place.
*/
wr_mas.content = mas_start(mas);
if (wr_mas.content)
goto exists;
mas_wr_preallocate(&wr_mas, entry);
if (mas_is_err(mas))
return NULL;
/* spanning writes always overwrite something */
if (mas->store_type == wr_spanning_store)
goto exists;
/* At this point, we are at the leaf node that needs to be altered. */
if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) {
wr_mas.offset_end = mas->offset;
wr_mas.end_piv = wr_mas.r_max;
if (wr_mas.content || (mas->last > wr_mas.r_max))
goto exists;
}
mas_wr_store_entry(&wr_mas);
return wr_mas.content;
exists:
mas_set_err(mas, -EEXIST);
return wr_mas.content;
}
/**
* mas_alloc_cyclic() - Internal call to find somewhere to store an entry
* @mas: The maple state.
* @startp: Pointer to ID.
* @range_lo: Lower bound of range to search.
* @range_hi: Upper bound of range to search.
* @entry: The entry to store.
* @next: Pointer to next ID to allocate.
* @gfp: The GFP_FLAGS to use for allocations.
*
* Return: 0 if the allocation succeeded without wrapping, 1 if the
* allocation succeeded after wrapping, or -EBUSY if there are no
* free entries.
*/
int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
void *entry, unsigned long range_lo, unsigned long range_hi,
unsigned long *next, gfp_t gfp)
{
unsigned long min = range_lo;
int ret = 0;
range_lo = max(min, *next);
ret = mas_empty_area(mas, range_lo, range_hi, 1);
if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) {
mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED;
ret = 1;
}
if (ret < 0 && range_lo > min) { mas_reset(mas);
ret = mas_empty_area(mas, min, range_hi, 1);
if (ret == 0)
ret = 1;
}
if (ret < 0)
return ret;
do {
mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas))
return xa_err(mas->node);
*startp = mas->index;
*next = *startp + 1;
if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED;
mas_destroy(mas);
return ret;
}
EXPORT_SYMBOL(mas_alloc_cyclic);
static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index)
{
retry:
mas_set(mas, index);
mas_state_walk(mas); if (mas_is_start(mas))
goto retry;
}
static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas,
struct maple_node *node, const unsigned long index)
{
if (unlikely(ma_dead_node(node))) {
mas_rewalk(mas, index);
return true;
}
return false;
}
/*
* mas_prev_node() - Find the prev non-null entry at the same level in the
* tree. The prev value will be mas->node[mas->offset] or the status will be
* ma_none.
* @mas: The maple state
* @min: The lower limit to search
*
* The prev node value will be mas->node[mas->offset] or the status will be
* ma_none.
* Return: 1 if the node is dead, 0 otherwise.
*/
static int mas_prev_node(struct ma_state *mas, unsigned long min)
{
enum maple_type mt;
int offset, level;
void __rcu **slots;
struct maple_node *node;
unsigned long *pivots;
unsigned long max;
node = mas_mn(mas);
if (!mas->min)
goto no_entry;
max = mas->min - 1;
if (max < min)
goto no_entry;
level = 0;
do {
if (ma_is_root(node))
goto no_entry;
/* Walk up. */
if (unlikely(mas_ascend(mas)))
return 1;
offset = mas->offset;
level++;
node = mas_mn(mas);
} while (!offset);
offset--;
mt = mte_node_type(mas->node);
while (level > 1) {
level--;
slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node)))
return 1;
mt = mte_node_type(mas->node);
node = mas_mn(mas);
pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node)))
return 1;
}
slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node)))
return 1;
if (likely(offset)) mas->min = pivots[offset - 1] + 1;
mas->max = max;
mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node)))
return 1;
mas->end = mas->offset;
return 0;
no_entry:
if (unlikely(ma_dead_node(node)))
return 1;
mas->status = ma_underflow;
return 0;
}
/*
* mas_prev_slot() - Get the entry in the previous slot
*
* @mas: The maple state
* @min: The minimum starting range
* @empty: Can be empty
*
* Return: The entry in the previous slot which is possibly NULL
*/
static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty)
{
void *entry;
void __rcu **slots;
unsigned long pivot;
enum maple_type type;
unsigned long *pivots;
struct maple_node *node;
unsigned long save_point = mas->index;
retry:
node = mas_mn(mas);
type = mte_node_type(mas->node);
pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (pivot <= min)
goto underflow;
}
again:
if (likely(mas->offset)) {
mas->offset--;
mas->last = mas->index - 1;
mas->index = mas_safe_min(mas, pivots, mas->offset);
} else {
if (mas->index <= min)
goto underflow;
if (mas_prev_node(mas, min)) {
mas_rewalk(mas, save_point);
goto retry;
}
if (WARN_ON_ONCE(mas_is_underflow(mas)))
return NULL;
mas->last = mas->max;
node = mas_mn(mas);
type = mte_node_type(mas->node);
pivots = ma_pivots(node, type);
mas->index = pivots[mas->offset - 1] + 1;
}
slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (likely(entry))
return entry;
if (!empty) { if (mas->index <= min) { mas->status = ma_underflow;
return NULL;
}
goto again;
}
return entry;
underflow:
mas->status = ma_underflow;
return NULL;
}
/*
* mas_next_node() - Get the next node at the same level in the tree.
* @mas: The maple state
* @node: The maple node
* @max: The maximum pivot value to check.
*
* The next value will be mas->node[mas->offset] or the status will have
* overflowed.
* Return: 1 on dead node, 0 otherwise.
*/
static int mas_next_node(struct ma_state *mas, struct maple_node *node,
unsigned long max)
{
unsigned long min;
unsigned long *pivots;
struct maple_enode *enode;
struct maple_node *tmp;
int level = 0;
unsigned char node_end;
enum maple_type mt;
void __rcu **slots;
if (mas->max >= max)
goto overflow;
min = mas->max + 1;
level = 0;
do {
if (ma_is_root(node))
goto overflow;
/* Walk up. */
if (unlikely(mas_ascend(mas)))
return 1;
level++;
node = mas_mn(mas);
mt = mte_node_type(mas->node);
pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node)))
return 1;
} while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt);
mas->offset++;
enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node)))
return 1;
if (level > 1)
mas->offset = 0;
while (unlikely(level > 1)) {
level--;
mas->node = enode;
node = mas_mn(mas);
mt = mte_node_type(mas->node);
slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node)))
return 1;
}
if (!mas->offset) pivots = ma_pivots(node, mt);
mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt);
tmp = mte_to_node(enode);
mt = mte_node_type(enode);
pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node)))
return 1;
mas->node = enode;
mas->min = min;
return 0;
overflow:
if (unlikely(ma_dead_node(node)))
return 1;
mas->status = ma_overflow;
return 0;
}
/*
* mas_next_slot() - Get the entry in the next slot
*
* @mas: The maple state
* @max: The maximum starting range
* @empty: Can be empty
*
* Return: The entry in the next slot which is possibly NULL
*/
static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty)
{
void __rcu **slots;
unsigned long *pivots;
unsigned long pivot;
enum maple_type type;
struct maple_node *node;
unsigned long save_point = mas->last;
void *entry;
retry:
node = mas_mn(mas);
type = mte_node_type(mas->node);
pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset];
else
pivot = mas->max;
if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow;
return NULL;
}
}
if (likely(mas->offset < mas->end)) {
mas->index = pivots[mas->offset] + 1;
again:
mas->offset++;
if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset];
else
mas->last = mas->max;
} else {
if (mas->last >= max) {
mas->status = ma_overflow;
return NULL;
}
if (mas_next_node(mas, node, max)) {
mas_rewalk(mas, save_point);
goto retry;
}
if (WARN_ON_ONCE(mas_is_overflow(mas)))
return NULL;
mas->offset = 0;
mas->index = mas->min;
node = mas_mn(mas);
type = mte_node_type(mas->node);
pivots = ma_pivots(node, type);
mas->last = pivots[0];
}
slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (entry)
return entry;
if (!empty) {
if (mas->last >= max) { mas->status = ma_overflow;
return NULL;
}
mas->index = mas->last + 1;
goto again;
}
return entry;
}
/*
* mas_rev_awalk() - Internal function. Reverse allocation walk. Find the
* highest gap address of a given size in a given node and descend.
* @mas: The maple state
* @size: The needed size.
*
* Return: True if found in a leaf, false otherwise.
*
*/
static bool mas_rev_awalk(struct ma_state *mas, unsigned long size,
unsigned long *gap_min, unsigned long *gap_max)
{
enum maple_type type = mte_node_type(mas->node);
struct maple_node *node = mas_mn(mas);
unsigned long *pivots, *gaps;
void __rcu **slots;
unsigned long gap = 0;
unsigned long max, min;
unsigned char offset;
if (unlikely(mas_is_err(mas)))
return true;
if (ma_is_dense(type)) {
/* dense nodes. */
mas->offset = (unsigned char)(mas->index - mas->min);
return true;
}
pivots = ma_pivots(node, type);
slots = ma_slots(node, type);
gaps = ma_gaps(node, type);
offset = mas->offset;
min = mas_safe_min(mas, pivots, offset);
/* Skip out of bounds. */
while (mas->last < min)
min = mas_safe_min(mas, pivots, --offset);
max = mas_safe_pivot(mas, pivots, offset, type);
while (mas->index <= max) {
gap = 0;
if (gaps)
gap = gaps[offset];
else if (!mas_slot(mas, slots, offset))
gap = max - min + 1;
if (gap) {
if ((size <= gap) && (size <= mas->last - min + 1))
break;
if (!gaps) {
/* Skip the next slot, it cannot be a gap. */
if (offset < 2)
goto ascend;
offset -= 2;
max = pivots[offset];
min = mas_safe_min(mas, pivots, offset);
continue;
}
}
if (!offset)
goto ascend;
offset--;
max = min - 1;
min = mas_safe_min(mas, pivots, offset);
}
if (unlikely((mas->index > max) || (size - 1 > max - mas->index)))
goto no_space;
if (unlikely(ma_is_leaf(type))) {
mas->offset = offset;
*gap_min = min;
*gap_max = min + gap - 1;
return true;
}
/* descend, only happens under lock. */
mas->node = mas_slot(mas, slots, offset);
mas->min = min;
mas->max = max;
mas->offset = mas_data_end(mas);
return false;
ascend:
if (!mte_is_root(mas->node))
return false;
no_space:
mas_set_err(mas, -EBUSY);
return false;
}
static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
{
enum maple_type type = mte_node_type(mas->node);
unsigned long pivot, min, gap = 0;
unsigned char offset, data_end;
unsigned long *gaps, *pivots;
void __rcu **slots;
struct maple_node *node;
bool found = false;
if (ma_is_dense(type)) {
mas->offset = (unsigned char)(mas->index - mas->min);
return true;
}
node = mas_mn(mas);
pivots = ma_pivots(node, type);
slots = ma_slots(node, type);
gaps = ma_gaps(node, type);
offset = mas->offset;
min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) {
pivot = mas_safe_pivot(mas, pivots, offset, type);
/* Not within lower bounds */
if (mas->index > pivot)
goto next_slot;
if (gaps)
gap = gaps[offset];
else if (!mas_slot(mas, slots, offset))
gap = min(pivot, mas->last) - max(mas->index, min) + 1;
else
goto next_slot;
if (gap >= size) { if (ma_is_leaf(type)) {
found = true;
break;
}
mas->node = mas_slot(mas, slots, offset);
mas->min = min;
mas->max = pivot;
offset = 0;
break;
}
next_slot:
min = pivot + 1;
if (mas->last <= pivot) {
mas_set_err(mas, -EBUSY);
return true;
}
}
mas->offset = offset;
return found;
}
/**
* mas_walk() - Search for @mas->index in the tree.
* @mas: The maple state.
*
* mas->index and mas->last will be set to the range if there is a value. If
* mas->status is ma_none, reset to ma_start
*
* Return: the entry at the location or %NULL.
*/
void *mas_walk(struct ma_state *mas)
{
void *entry;
if (!mas_is_active(mas) || !mas_is_start(mas))
mas->status = ma_start;
retry:
entry = mas_state_walk(mas); if (mas_is_start(mas)) {
goto retry;
} else if (mas_is_none(mas)) {
mas->index = 0;
mas->last = ULONG_MAX;
} else if (mas_is_ptr(mas)) {
if (!mas->index) { mas->last = 0;
return entry;
}
mas->index = 1;
mas->last = ULONG_MAX;
mas->status = ma_none;
return NULL;
}
return entry;
}
EXPORT_SYMBOL_GPL(mas_walk);
static inline bool mas_rewind_node(struct ma_state *mas)
{
unsigned char slot;
do {
if (mte_is_root(mas->node)) {
slot = mas->offset;
if (!slot)
return false;
} else {
mas_ascend(mas);
slot = mas->offset;
}
} while (!slot);
mas->offset = --slot;
return true;
}
/*
* mas_skip_node() - Internal function. Skip over a node.
* @mas: The maple state.
*
* Return: true if there is another node, false otherwise.
*/
static inline bool mas_skip_node(struct ma_state *mas)
{
if (mas_is_err(mas))
return false;
do {
if (mte_is_root(mas->node)) {
if (mas->offset >= mas_data_end(mas)) {
mas_set_err(mas, -EBUSY);
return false;
}
} else {
mas_ascend(mas);
}
} while (mas->offset >= mas_data_end(mas));
mas->offset++;
return true;
}
/*
* mas_awalk() - Allocation walk. Search from low address to high, for a gap of
* @size
* @mas: The maple state
* @size: The size of the gap required
*
* Search between @mas->index and @mas->last for a gap of @size.
*/
static inline void mas_awalk(struct ma_state *mas, unsigned long size)
{
struct maple_enode *last = NULL;
/*
* There are 4 options:
* go to child (descend)
* go back to parent (ascend)
* no gap found. (return, error == -EBUSY)
* found the gap. (return)
*/
while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas);
else
last = mas->node;
}
}
/*
* mas_sparse_area() - Internal function. Return upper or lower limit when
* searching for a gap in an empty tree.
* @mas: The maple state
* @min: the minimum range
* @max: The maximum range
* @size: The size of the gap
* @fwd: Searching forward or back
*/
static inline int mas_sparse_area(struct ma_state *mas, unsigned long min,
unsigned long max, unsigned long size, bool fwd)
{
if (!unlikely(mas_is_none(mas)) && min == 0) {
min++;
/*
* At this time, min is increased, we need to recheck whether
* the size is satisfied.
*/
if (min > max || max - min + 1 < size)
return -EBUSY;
}
/* mas_is_ptr */
if (fwd) {
mas->index = min;
mas->last = min + size - 1;
} else {
mas->last = max;
mas->index = max - size + 1;
}
return 0;
}
/*
* mas_empty_area() - Get the lowest address within the range that is
* sufficient for the size requested.
* @mas: The maple state
* @min: The lowest value of the range
* @max: The highest value of the range
* @size: The size needed
*/
int mas_empty_area(struct ma_state *mas, unsigned long min,
unsigned long max, unsigned long size)
{
unsigned char offset;
unsigned long *pivots;
enum maple_type mt;
struct maple_node *node;
if (min > max)
return -EINVAL;
if (size == 0 || max - min < size - 1)
return -EINVAL;
if (mas_is_start(mas))
mas_start(mas);
else if (mas->offset >= 2)
mas->offset -= 2; else if (!mas_skip_node(mas))
return -EBUSY;
/* Empty set */
if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true);
/* The start of the window can only be within these values */
mas->index = min;
mas->last = max;
mas_awalk(mas, size); if (unlikely(mas_is_err(mas)))
return xa_err(mas->node);
offset = mas->offset;
node = mas_mn(mas);
mt = mte_node_type(mas->node);
pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min;
mas->last = mas->index + size - 1;
mas->end = ma_data_end(node, mt, pivots, mas->max);
return 0;
}
EXPORT_SYMBOL_GPL(mas_empty_area);
/*
* mas_empty_area_rev() - Get the highest address within the range that is
* sufficient for the size requested.
* @mas: The maple state
* @min: The lowest value of the range
* @max: The highest value of the range
* @size: The size needed
*/
int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
unsigned long max, unsigned long size)
{
struct maple_enode *last = mas->node;
if (min > max)
return -EINVAL;
if (size == 0 || max - min < size - 1)
return -EINVAL;
if (mas_is_start(mas))
mas_start(mas);
else if ((mas->offset < 2) && (!mas_rewind_node(mas)))
return -EBUSY;
if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
return mas_sparse_area(mas, min, max, size, false);
else if (mas->offset >= 2)
mas->offset -= 2;
else
mas->offset = mas_data_end(mas);
/* The start of the window can only be within these values. */
mas->index = min;
mas->last = max;
while (!mas_rev_awalk(mas, size, &min, &max)) {
if (last == mas->node) {
if (!mas_rewind_node(mas))
return -EBUSY;
} else {
last = mas->node;
}
}
if (mas_is_err(mas))
return xa_err(mas->node);
if (unlikely(mas->offset == MAPLE_NODE_SLOTS))
return -EBUSY;
/* Trim the upper limit to the max. */
if (max < mas->last)
mas->last = max;
mas->index = mas->last - size + 1;
mas->end = mas_data_end(mas);
return 0;
}
EXPORT_SYMBOL_GPL(mas_empty_area_rev);
/*
* mte_dead_leaves() - Mark all leaves of a node as dead.
* @enode: the encoded node
* @mt: the maple tree
* @slots: Pointer to the slot array
*
* Must hold the write lock.
*
* Return: The number of leaves marked as dead.
*/
static inline
unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt,
void __rcu **slots)
{
struct maple_node *node;
enum maple_type type;
void *entry;
int offset;
for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset);
type = mte_node_type(entry);
node = mte_to_node(entry);
/* Use both node and type to catch LE & BE metadata */
if (!node || !type)
break;
mte_set_node_dead(entry);
node->type = type;
rcu_assign_pointer(slots[offset], node);
}
return offset;
}
/**
* mte_dead_walk() - Walk down a dead tree to just before the leaves
* @enode: The maple encoded node
* @offset: The starting offset
*
* Note: This can only be used from the RCU callback context.
*/
static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset)
{
struct maple_node *node, *next;
void __rcu **slots = NULL;
next = mte_to_node(*enode);
do {
*enode = ma_enode_ptr(next);
node = mte_to_node(*enode);
slots = ma_slots(node, node->type);
next = rcu_dereference_protected(slots[offset],
lock_is_held(&rcu_callback_map));
offset = 0;
} while (!ma_is_leaf(next->type));
return slots;
}
/**
* mt_free_walk() - Walk & free a tree in the RCU callback context
* @head: The RCU head that's within the node.
*
* Note: This can only be used from the RCU callback context.
*/
static void mt_free_walk(struct rcu_head *head)
{
void __rcu **slots;
struct maple_node *node, *start;
struct maple_enode *enode;
unsigned char offset;
enum maple_type type;
node = container_of(head, struct maple_node, rcu);
if (ma_is_leaf(node->type))
goto free_leaf;
start = node;
enode = mt_mk_node(node, node->type);
slots = mte_dead_walk(&enode, 0);
node = mte_to_node(enode);
do {
mt_free_bulk(node->slot_len, slots);
offset = node->parent_slot + 1;
enode = node->piv_parent;
if (mte_to_node(enode) == node)
goto free_leaf;
type = mte_node_type(enode);
slots = ma_slots(mte_to_node(enode), type);
if ((offset < mt_slots[type]) &&
rcu_dereference_protected(slots[offset],
lock_is_held(&rcu_callback_map)))
slots = mte_dead_walk(&enode, offset);
node = mte_to_node(enode);
} while ((node != start) || (node->slot_len < offset));
slots = ma_slots(node, node->type);
mt_free_bulk(node->slot_len, slots);
free_leaf:
mt_free_rcu(&node->rcu);
}
static inline void __rcu **mte_destroy_descend(struct maple_enode **enode,
struct maple_tree *mt, struct maple_enode *prev, unsigned char offset)
{
struct maple_node *node;
struct maple_enode *next = *enode;
void __rcu **slots = NULL;
enum maple_type type;
unsigned char next_offset = 0;
do {
*enode = next;
node = mte_to_node(*enode);
type = mte_node_type(*enode);
slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset);
mte_set_node_dead(*enode);
node->type = type;
node->piv_parent = prev;
node->parent_slot = offset;
offset = next_offset;
next_offset = 0;
prev = *enode;
} while (!mte_is_leaf(next)); return slots;
}
static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt,
bool free)
{
void __rcu **slots;
struct maple_node *node = mte_to_node(enode);
struct maple_enode *start;
if (mte_is_leaf(enode)) {
node->type = mte_node_type(enode);
goto free_leaf;
}
start = enode;
slots = mte_destroy_descend(&enode, mt, start, 0);
node = mte_to_node(enode); // Updated in the above call.
do {
enum maple_type type;
unsigned char offset;
struct maple_enode *parent, *tmp;
node->slot_len = mte_dead_leaves(enode, mt, slots);
if (free) mt_free_bulk(node->slot_len, slots);
offset = node->parent_slot + 1;
enode = node->piv_parent;
if (mte_to_node(enode) == node)
goto free_leaf;
type = mte_node_type(enode);
slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type])
goto next;
tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) {
parent = enode;
enode = tmp;
slots = mte_destroy_descend(&enode, mt, parent, offset);
}
next:
node = mte_to_node(enode);
} while (start != enode);
node = mte_to_node(enode);
node->slot_len = mte_dead_leaves(enode, mt, slots);
if (free) mt_free_bulk(node->slot_len, slots);
free_leaf:
if (free)
mt_free_rcu(&node->rcu);
else
mt_clear_meta(mt, node, node->type);
}
/*
* mte_destroy_walk() - Free a tree or sub-tree.
* @enode: the encoded maple node (maple_enode) to start
* @mt: the tree to free - needed for node types.
*
* Must hold the write lock.
*/
static inline void mte_destroy_walk(struct maple_enode *enode,
struct maple_tree *mt)
{
struct maple_node *node = mte_to_node(enode);
if (mt_in_rcu(mt)) {
mt_destroy_walk(enode, mt, false);
call_rcu(&node->rcu, mt_free_walk);
} else {
mt_destroy_walk(enode, mt, true);
}
}
/* Interface */
/**
* mas_store() - Store an @entry.
* @mas: The maple state.
* @entry: The entry to store.
*
* The @mas->index and @mas->last is used to set the range for the @entry.
*
* Return: the first entry between mas->index and mas->last or %NULL.
*/
void *mas_store(struct ma_state *mas, void *entry)
{
int request;
MA_WR_STATE(wr_mas, mas, entry);
trace_ma_write(__func__, mas, 0, entry);
#ifdef CONFIG_DEBUG_MAPLE_TREE
if (MAS_WARN_ON(mas, mas->index > mas->last))
pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last,
entry);
if (mas->index > mas->last) {
mas_set_err(mas, -EINVAL);
return NULL;
}
#endif
/*
* Storing is the same operation as insert with the added caveat that it
* can overwrite entries. Although this seems simple enough, one may
* want to examine what happens if a single store operation was to
* overwrite multiple entries within a self-balancing B-Tree.
*/
mas_wr_prealloc_setup(&wr_mas);
mas->store_type = mas_wr_store_type(&wr_mas);
if (mas->mas_flags & MA_STATE_PREALLOC) {
mas_wr_store_entry(&wr_mas);
MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas));
return wr_mas.content;
}
request = mas_prealloc_calc(mas, entry);
if (!request)
goto store;
mas_node_count(mas, request);
if (mas_is_err(mas))
return NULL;
store:
mas_wr_store_entry(&wr_mas);
mas_destroy(mas);
return wr_mas.content;
}
EXPORT_SYMBOL_GPL(mas_store);
/**
* mas_store_gfp() - Store a value into the tree.
* @mas: The maple state
* @entry: The entry to store
* @gfp: The GFP_FLAGS to use for allocations if necessary.
*
* Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not
* be allocated.
*/
int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp)
{
unsigned long index = mas->index;
unsigned long last = mas->last;
MA_WR_STATE(wr_mas, mas, entry);
int ret = 0;
retry:
mas_wr_preallocate(&wr_mas, entry);
if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last);
goto retry;
}
if (mas_is_err(mas)) {
ret = xa_err(mas->node);
goto out;
}
mas_wr_store_entry(&wr_mas);
out:
mas_destroy(mas);
return ret;
}
EXPORT_SYMBOL_GPL(mas_store_gfp);
/**
* mas_store_prealloc() - Store a value into the tree using memory
* preallocated in the maple state.
* @mas: The maple state
* @entry: The entry to store.
*/
void mas_store_prealloc(struct ma_state *mas, void *entry)
{
MA_WR_STATE(wr_mas, mas, entry);
if (mas->store_type == wr_store_root) {
mas_wr_prealloc_setup(&wr_mas);
goto store;
}
mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) {
/* set wr_mas->content to current slot */
wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas);
}
store:
trace_ma_write(__func__, mas, 0, entry);
mas_wr_store_entry(&wr_mas);
MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas));
mas_destroy(mas);
}
EXPORT_SYMBOL_GPL(mas_store_prealloc);
/**
* mas_preallocate() - Preallocate enough nodes for a store operation
* @mas: The maple state
* @entry: The entry that will be stored
* @gfp: The GFP_FLAGS to use for allocations.
*
* Return: 0 on success, -ENOMEM if memory could not be allocated.
*/
int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
{
MA_WR_STATE(wr_mas, mas, entry);
int ret = 0;
int request;
mas_wr_prealloc_setup(&wr_mas);
mas->store_type = mas_wr_store_type(&wr_mas);
request = mas_prealloc_calc(mas, entry); if (!request)
return ret;
mas_node_count_gfp(mas, request, gfp);
if (mas_is_err(mas)) {
mas_set_alloc_req(mas, 0);
ret = xa_err(mas->node);
mas_destroy(mas);
mas_reset(mas);
return ret;
}
mas->mas_flags |= MA_STATE_PREALLOC;
return ret;
}
EXPORT_SYMBOL_GPL(mas_preallocate);
/*
* mas_destroy() - destroy a maple state.
* @mas: The maple state
*
* Upon completion, check the left-most node and rebalance against the node to
* the right if necessary. Frees any allocated nodes associated with this maple
* state.
*/
void mas_destroy(struct ma_state *mas)
{
struct maple_alloc *node;
unsigned long total;
/*
* When using mas_for_each() to insert an expected number of elements,
* it is possible that the number inserted is less than the expected
* number. To fix an invalid final node, a check is performed here to
* rebalance the previous node with the final node.
*/
if (mas->mas_flags & MA_STATE_REBALANCE) {
unsigned char end;
if (mas_is_err(mas)) mas_reset(mas);
mas_start(mas);
mtree_range_walk(mas);
end = mas->end + 1;
if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end);
mas->mas_flags &= ~MA_STATE_REBALANCE;
}
mas->mas_flags &= ~(MA_STATE_BULK|MA_STATE_PREALLOC);
total = mas_allocated(mas); while (total) {
node = mas->alloc;
mas->alloc = node->slot[0];
if (node->node_count > 1) {
size_t count = node->node_count - 1;
mt_free_bulk(count, (void __rcu **)&node->slot[1]);
total -= count;
}
mt_free_one(ma_mnode_ptr(node));
total--;
}
mas->alloc = NULL;
}
EXPORT_SYMBOL_GPL(mas_destroy);
/*
* mas_expected_entries() - Set the expected number of entries that will be inserted.
* @mas: The maple state
* @nr_entries: The number of expected entries.
*
* This will attempt to pre-allocate enough nodes to store the expected number
* of entries. The allocations will occur using the bulk allocator interface
* for speed. Please call mas_destroy() on the @mas after inserting the entries
* to ensure any unused nodes are freed.
*
* Return: 0 on success, -ENOMEM if memory could not be allocated.
*/
int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries)
{
int nonleaf_cap = MAPLE_ARANGE64_SLOTS - 2;
struct maple_enode *enode = mas->node;
int nr_nodes;
int ret;
/*
* Sometimes it is necessary to duplicate a tree to a new tree, such as
* forking a process and duplicating the VMAs from one tree to a new
* tree. When such a situation arises, it is known that the new tree is
* not going to be used until the entire tree is populated. For
* performance reasons, it is best to use a bulk load with RCU disabled.
* This allows for optimistic splitting that favours the left and reuse
* of nodes during the operation.
*/
/* Optimize splitting for bulk insert in-order */
mas->mas_flags |= MA_STATE_BULK;
/*
* Avoid overflow, assume a gap between each entry and a trailing null.
* If this is wrong, it just means allocation can happen during
* insertion of entries.
*/
nr_nodes = max(nr_entries, nr_entries * 2 + 1);
if (!mt_is_alloc(mas->tree))
nonleaf_cap = MAPLE_RANGE64_SLOTS - 2;
/* Leaves; reduce slots to keep space for expansion */
nr_nodes = DIV_ROUND_UP(nr_nodes, MAPLE_RANGE64_SLOTS - 2);
/* Internal nodes */
nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap);
/* Add working room for split (2 nodes) + new parents */
mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL);
/* Detect if allocations run out */
mas->mas_flags |= MA_STATE_PREALLOC;
if (!mas_is_err(mas))
return 0;
ret = xa_err(mas->node);
mas->node = enode;
mas_destroy(mas);
return ret;
}
EXPORT_SYMBOL_GPL(mas_expected_entries);
static bool mas_next_setup(struct ma_state *mas, unsigned long max,
void **entry)
{
bool was_none = mas_is_none(mas);
if (unlikely(mas->last >= max)) {
mas->status = ma_overflow;
return true;
}
switch (mas->status) {
case ma_active:
return false;
case ma_none:
fallthrough;
case ma_pause:
mas->status = ma_start;
fallthrough;
case ma_start:
mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
break;
case ma_overflow:
/* Overflowed before, but the max changed */
mas->status = ma_active;
break;
case ma_underflow:
/* The user expects the mas to be one before where it is */
mas->status = ma_active;
*entry = mas_walk(mas); if (*entry)
return true;
break;
case ma_root:
break;
case ma_error:
return true;
}
if (likely(mas_is_active(mas))) /* Fast path */
return false;
if (mas_is_ptr(mas)) {
*entry = NULL;
if (was_none && mas->index == 0) { mas->index = mas->last = 0;
return true;
}
mas->index = 1;
mas->last = ULONG_MAX;
mas->status = ma_none;
return true;
}
if (mas_is_none(mas))
return true;
return false;
}
/**
* mas_next() - Get the next entry.
* @mas: The maple state
* @max: The maximum index to check.
*
* Returns the next entry after @mas->index.
* Must hold rcu_read_lock or the write lock.
* Can return the zero entry.
*
* Return: The next entry or %NULL
*/
void *mas_next(struct ma_state *mas, unsigned long max)
{
void *entry = NULL;
if (mas_next_setup(mas, max, &entry))
return entry;
/* Retries on dead nodes handled by mas_next_slot */
return mas_next_slot(mas, max, false);
}
EXPORT_SYMBOL_GPL(mas_next);
/**
* mas_next_range() - Advance the maple state to the next range
* @mas: The maple state
* @max: The maximum index to check.
*
* Sets @mas->index and @mas->last to the range.
* Must hold rcu_read_lock or the write lock.
* Can return the zero entry.
*
* Return: The next entry or %NULL
*/
void *mas_next_range(struct ma_state *mas, unsigned long max)
{
void *entry = NULL;
if (mas_next_setup(mas, max, &entry))
return entry;
/* Retries on dead nodes handled by mas_next_slot */
return mas_next_slot(mas, max, true);
}
EXPORT_SYMBOL_GPL(mas_next_range);
/**
* mt_next() - get the next value in the maple tree
* @mt: The maple tree
* @index: The start index
* @max: The maximum index to check
*
* Takes RCU read lock internally to protect the search, which does not
* protect the returned pointer after dropping RCU read lock.
* See also: Documentation/core-api/maple_tree.rst
*
* Return: The entry higher than @index or %NULL if nothing is found.
*/
void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max)
{
void *entry = NULL;
MA_STATE(mas, mt, index, index);
rcu_read_lock();
entry = mas_next(&mas, max);
rcu_read_unlock();
return entry;
}
EXPORT_SYMBOL_GPL(mt_next);
static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry)
{
if (unlikely(mas->index <= min)) {
mas->status = ma_underflow;
return true;
}
switch (mas->status) {
case ma_active:
return false;
case ma_start:
break;
case ma_none:
fallthrough;
case ma_pause:
mas->status = ma_start;
break;
case ma_underflow:
/* underflowed before but the min changed */
mas->status = ma_active;
break;
case ma_overflow:
/* User expects mas to be one after where it is */
mas->status = ma_active;
*entry = mas_walk(mas); if (*entry)
return true;
break;
case ma_root:
break;
case ma_error:
return true;
}
if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) {
if (!mas->index) {
mas->status = ma_none;
return true;
}
mas->index = mas->last = 0;
*entry = mas_root(mas);
return true;
}
if (mas_is_none(mas)) {
if (mas->index) {
/* Walked to out-of-range pointer? */
mas->index = mas->last = 0;
mas->status = ma_root;
*entry = mas_root(mas);
return true;
}
return true;
}
return false;
}
/**
* mas_prev() - Get the previous entry
* @mas: The maple state
* @min: The minimum value to check.
*
* Must hold rcu_read_lock or the write lock.
* Will reset mas to ma_start if the status is ma_none. Will stop on not
* searchable nodes.
*
* Return: the previous value or %NULL.
*/
void *mas_prev(struct ma_state *mas, unsigned long min)
{
void *entry = NULL;
if (mas_prev_setup(mas, min, &entry))
return entry; return mas_prev_slot(mas, min, false);
}
EXPORT_SYMBOL_GPL(mas_prev);
/**
* mas_prev_range() - Advance to the previous range
* @mas: The maple state
* @min: The minimum value to check.
*
* Sets @mas->index and @mas->last to the range.
* Must hold rcu_read_lock or the write lock.
* Will reset mas to ma_start if the node is ma_none. Will stop on not
* searchable nodes.
*
* Return: the previous value or %NULL.
*/
void *mas_prev_range(struct ma_state *mas, unsigned long min)
{
void *entry = NULL;
if (mas_prev_setup(mas, min, &entry))
return entry; return mas_prev_slot(mas, min, true);
}
EXPORT_SYMBOL_GPL(mas_prev_range);
/**
* mt_prev() - get the previous value in the maple tree
* @mt: The maple tree
* @index: The start index
* @min: The minimum index to check
*
* Takes RCU read lock internally to protect the search, which does not
* protect the returned pointer after dropping RCU read lock.
* See also: Documentation/core-api/maple_tree.rst
*
* Return: The entry before @index or %NULL if nothing is found.
*/
void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min)
{
void *entry = NULL;
MA_STATE(mas, mt, index, index);
rcu_read_lock();
entry = mas_prev(&mas, min);
rcu_read_unlock();
return entry;
}
EXPORT_SYMBOL_GPL(mt_prev);
/**
* mas_pause() - Pause a mas_find/mas_for_each to drop the lock.
* @mas: The maple state to pause
*
* Some users need to pause a walk and drop the lock they're holding in
* order to yield to a higher priority thread or carry out an operation
* on an entry. Those users should call this function before they drop
* the lock. It resets the @mas to be suitable for the next iteration
* of the loop after the user has reacquired the lock. If most entries
* found during a walk require you to call mas_pause(), the mt_for_each()
* iterator may be more appropriate.
*
*/
void mas_pause(struct ma_state *mas)
{
mas->status = ma_pause;
mas->node = NULL;
}
EXPORT_SYMBOL_GPL(mas_pause);
/**
* mas_find_setup() - Internal function to set up mas_find*().
* @mas: The maple state
* @max: The maximum index
* @entry: Pointer to the entry
*
* Returns: True if entry is the answer, false otherwise.
*/
static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry)
{
switch (mas->status) {
case ma_active:
if (mas->last < max)
return false;
return true;
case ma_start:
break;
case ma_pause:
if (unlikely(mas->last >= max))
return true;
mas->index = ++mas->last;
mas->status = ma_start;
break;
case ma_none:
if (unlikely(mas->last >= max))
return true;
mas->index = mas->last;
mas->status = ma_start;
break;
case ma_underflow:
/* mas is pointing at entry before unable to go lower */
if (unlikely(mas->index >= max)) {
mas->status = ma_overflow;
return true;
}
mas->status = ma_active;
*entry = mas_walk(mas); if (*entry)
return true;
break;
case ma_overflow:
if (unlikely(mas->last >= max))
return true;
mas->status = ma_active;
*entry = mas_walk(mas); if (*entry)
return true;
break;
case ma_root:
break;
case ma_error:
return true;
}
if (mas_is_start(mas)) {
/* First run or continue */
if (mas->index > max)
return true;
*entry = mas_walk(mas); if (*entry)
return true;
}
if (unlikely(mas_is_ptr(mas)))
goto ptr_out_of_range;
if (unlikely(mas_is_none(mas)))
return true;
if (mas->index == max)
return true;
return false;
ptr_out_of_range:
mas->status = ma_none;
mas->index = 1;
mas->last = ULONG_MAX;
return true;
}
/**
* mas_find() - On the first call, find the entry at or after mas->index up to
* %max. Otherwise, find the entry after mas->index.
* @mas: The maple state
* @max: The maximum value to check.
*
* Must hold rcu_read_lock or the write lock.
* If an entry exists, last and index are updated accordingly.
* May set @mas->status to ma_overflow.
*
* Return: The entry or %NULL.
*/
void *mas_find(struct ma_state *mas, unsigned long max)
{
void *entry = NULL;
if (mas_find_setup(mas, max, &entry))
return entry;
/* Retries on dead nodes handled by mas_next_slot */
entry = mas_next_slot(mas, max, false);
/* Ignore overflow */
mas->status = ma_active;
return entry;
}
EXPORT_SYMBOL_GPL(mas_find);
/**
* mas_find_range() - On the first call, find the entry at or after
* mas->index up to %max. Otherwise, advance to the next slot mas->index.
* @mas: The maple state
* @max: The maximum value to check.
*
* Must hold rcu_read_lock or the write lock.
* If an entry exists, last and index are updated accordingly.
* May set @mas->status to ma_overflow.
*
* Return: The entry or %NULL.
*/
void *mas_find_range(struct ma_state *mas, unsigned long max)
{
void *entry = NULL;
if (mas_find_setup(mas, max, &entry))
return entry;
/* Retries on dead nodes handled by mas_next_slot */
return mas_next_slot(mas, max, true);
}
EXPORT_SYMBOL_GPL(mas_find_range);
/**
* mas_find_rev_setup() - Internal function to set up mas_find_*_rev()
* @mas: The maple state
* @min: The minimum index
* @entry: Pointer to the entry
*
* Returns: True if entry is the answer, false otherwise.
*/
static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
void **entry)
{
switch (mas->status) {
case ma_active:
goto active;
case ma_start:
break;
case ma_pause:
if (unlikely(mas->index <= min)) {
mas->status = ma_underflow;
return true;
}
mas->last = --mas->index;
mas->status = ma_start;
break;
case ma_none:
if (mas->index <= min)
goto none;
mas->last = mas->index;
mas->status = ma_start;
break;
case ma_overflow: /* user expects the mas to be one after where it is */
if (unlikely(mas->index <= min)) {
mas->status = ma_underflow;
return true;
}
mas->status = ma_active;
break;
case ma_underflow: /* user expects the mas to be one before where it is */
if (unlikely(mas->index <= min))
return true;
mas->status = ma_active;
break;
case ma_root:
break;
case ma_error:
return true;
}
if (mas_is_start(mas)) {
/* First run or continue */
if (mas->index < min)
return true;
*entry = mas_walk(mas);
if (*entry)
return true;
}
if (unlikely(mas_is_ptr(mas)))
goto none;
if (unlikely(mas_is_none(mas))) {
/*
* Walked to the location, and there was nothing so the previous
* location is 0.
*/
mas->last = mas->index = 0;
mas->status = ma_root;
*entry = mas_root(mas);
return true;
}
active:
if (mas->index < min)
return true;
return false;
none:
mas->status = ma_none;
return true;
}
/**
* mas_find_rev: On the first call, find the first non-null entry at or below
* mas->index down to %min. Otherwise find the first non-null entry below
* mas->index down to %min.
* @mas: The maple state
* @min: The minimum value to check.
*
* Must hold rcu_read_lock or the write lock.
* If an entry exists, last and index are updated accordingly.
* May set @mas->status to ma_underflow.
*
* Return: The entry or %NULL.
*/
void *mas_find_rev(struct ma_state *mas, unsigned long min)
{
void *entry = NULL;
if (mas_find_rev_setup(mas, min, &entry))
return entry;
/* Retries on dead nodes handled by mas_prev_slot */
return mas_prev_slot(mas, min, false);
}
EXPORT_SYMBOL_GPL(mas_find_rev);
/**
* mas_find_range_rev: On the first call, find the first non-null entry at or
* below mas->index down to %min. Otherwise advance to the previous slot after
* mas->index down to %min.
* @mas: The maple state
* @min: The minimum value to check.
*
* Must hold rcu_read_lock or the write lock.
* If an entry exists, last and index are updated accordingly.
* May set @mas->status to ma_underflow.
*
* Return: The entry or %NULL.
*/
void *mas_find_range_rev(struct ma_state *mas, unsigned long min)
{
void *entry = NULL;
if (mas_find_rev_setup(mas, min, &entry))
return entry;
/* Retries on dead nodes handled by mas_prev_slot */
return mas_prev_slot(mas, min, true);
}
EXPORT_SYMBOL_GPL(mas_find_range_rev);
/**
* mas_erase() - Find the range in which index resides and erase the entire
* range.
* @mas: The maple state
*
* Must hold the write lock.
* Searches for @mas->index, sets @mas->index and @mas->last to the range and
* erases that range.
*
* Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated.
*/
void *mas_erase(struct ma_state *mas)
{
void *entry;
unsigned long index = mas->index;
MA_WR_STATE(wr_mas, mas, NULL);
if (!mas_is_active(mas) || !mas_is_start(mas))
mas->status = ma_start;
write_retry:
entry = mas_state_walk(mas);
if (!entry)
return NULL;
/* Must reset to ensure spanning writes of last slot are detected */
mas_reset(mas);
mas_wr_preallocate(&wr_mas, NULL);
if (mas_nomem(mas, GFP_KERNEL)) {
/* in case the range of entry changed when unlocked */
mas->index = mas->last = index;
goto write_retry;
}
if (mas_is_err(mas))
goto out;
mas_wr_store_entry(&wr_mas);
out:
mas_destroy(mas);
return entry;
}
EXPORT_SYMBOL_GPL(mas_erase);
/**
* mas_nomem() - Check if there was an error allocating and do the allocation
* if necessary If there are allocations, then free them.
* @mas: The maple state
* @gfp: The GFP_FLAGS to use for allocations
* Return: true on allocation, false otherwise.
*/
bool mas_nomem(struct ma_state *mas, gfp_t gfp)
__must_hold(mas->tree->ma_lock)
{
if (likely(mas->node != MA_ERROR(-ENOMEM)))
return false;
if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree);
mas_alloc_nodes(mas, gfp);
mtree_lock(mas->tree);
} else {
mas_alloc_nodes(mas, gfp);
}
if (!mas_allocated(mas))
return false;
mas->status = ma_start;
return true;
}
void __init maple_tree_init(void)
{
maple_node_cache = kmem_cache_create("maple_node",
sizeof(struct maple_node), sizeof(struct maple_node),
SLAB_PANIC, NULL);
}
/**
* mtree_load() - Load a value stored in a maple tree
* @mt: The maple tree
* @index: The index to load
*
* Return: the entry or %NULL
*/
void *mtree_load(struct maple_tree *mt, unsigned long index)
{
MA_STATE(mas, mt, index, index);
void *entry;
trace_ma_read(__func__, &mas);
rcu_read_lock();
retry:
entry = mas_start(&mas);
if (unlikely(mas_is_none(&mas)))
goto unlock;
if (unlikely(mas_is_ptr(&mas))) {
if (index)
entry = NULL;
goto unlock;
}
entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas)))
goto retry;
unlock:
rcu_read_unlock();
if (xa_is_zero(entry))
return NULL;
return entry;
}
EXPORT_SYMBOL(mtree_load);
/**
* mtree_store_range() - Store an entry at a given range.
* @mt: The maple tree
* @index: The start of the range
* @last: The end of the range
* @entry: The entry to store
* @gfp: The GFP_FLAGS to use for allocations
*
* Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not
* be allocated.
*/
int mtree_store_range(struct maple_tree *mt, unsigned long index,
unsigned long last, void *entry, gfp_t gfp)
{
MA_STATE(mas, mt, index, last);
int ret = 0;
trace_ma_write(__func__, &mas, 0, entry);
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return -EINVAL;
if (index > last)
return -EINVAL;
mtree_lock(mt);
ret = mas_store_gfp(&mas, entry, gfp);
mtree_unlock(mt);
return ret;
}
EXPORT_SYMBOL(mtree_store_range);
/**
* mtree_store() - Store an entry at a given index.
* @mt: The maple tree
* @index: The index to store the value
* @entry: The entry to store
* @gfp: The GFP_FLAGS to use for allocations
*
* Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not
* be allocated.
*/
int mtree_store(struct maple_tree *mt, unsigned long index, void *entry,
gfp_t gfp)
{
return mtree_store_range(mt, index, index, entry, gfp);
}
EXPORT_SYMBOL(mtree_store);
/**
* mtree_insert_range() - Insert an entry at a given range if there is no value.
* @mt: The maple tree
* @first: The start of the range
* @last: The end of the range
* @entry: The entry to store
* @gfp: The GFP_FLAGS to use for allocations.
*
* Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid
* request, -ENOMEM if memory could not be allocated.
*/
int mtree_insert_range(struct maple_tree *mt, unsigned long first,
unsigned long last, void *entry, gfp_t gfp)
{
MA_STATE(ms, mt, first, last);
int ret = 0;
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return -EINVAL;
if (first > last)
return -EINVAL;
mtree_lock(mt);
retry:
mas_insert(&ms, entry); if (mas_nomem(&ms, gfp))
goto retry;
mtree_unlock(mt);
if (mas_is_err(&ms)) ret = xa_err(ms.node);
mas_destroy(&ms);
return ret;
}
EXPORT_SYMBOL(mtree_insert_range);
/**
* mtree_insert() - Insert an entry at a given index if there is no value.
* @mt: The maple tree
* @index : The index to store the value
* @entry: The entry to store
* @gfp: The GFP_FLAGS to use for allocations.
*
* Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid
* request, -ENOMEM if memory could not be allocated.
*/
int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry,
gfp_t gfp)
{
return mtree_insert_range(mt, index, index, entry, gfp);
}
EXPORT_SYMBOL(mtree_insert);
int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp)
{
int ret = 0;
MA_STATE(mas, mt, 0, 0);
if (!mt_is_alloc(mt))
return -EINVAL;
if (WARN_ON_ONCE(mt_is_reserved(entry)))
return -EINVAL;
mtree_lock(mt);
retry:
ret = mas_empty_area(&mas, min, max, size);
if (ret)
goto unlock;
mas_insert(&mas, entry);
/*
* mas_nomem() may release the lock, causing the allocated area
* to be unavailable, so try to allocate a free area again.
*/
if (mas_nomem(&mas, gfp))
goto retry;
if (mas_is_err(&mas))
ret = xa_err(mas.node);
else
*startp = mas.index;
unlock:
mtree_unlock(mt);
mas_destroy(&mas);
return ret;
}
EXPORT_SYMBOL(mtree_alloc_range);
/**
* mtree_alloc_cyclic() - Find somewhere to store this entry in the tree.
* @mt: The maple tree.
* @startp: Pointer to ID.
* @range_lo: Lower bound of range to search.
* @range_hi: Upper bound of range to search.
* @entry: The entry to store.
* @next: Pointer to next ID to allocate.
* @gfp: The GFP_FLAGS to use for allocations.
*
* Finds an empty entry in @mt after @next, stores the new index into
* the @id pointer, stores the entry at that index, then updates @next.
*
* @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag.
*
* Context: Any context. Takes and releases the mt.lock. May sleep if
* the @gfp flags permit.
*
* Return: 0 if the allocation succeeded without wrapping, 1 if the
* allocation succeeded after wrapping, -ENOMEM if memory could not be
* allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no
* free entries.
*/
int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long range_lo, unsigned long range_hi,
unsigned long *next, gfp_t gfp)
{
int ret;
MA_STATE(mas, mt, 0, 0);
if (!mt_is_alloc(mt))
return -EINVAL;
if (WARN_ON_ONCE(mt_is_reserved(entry)))
return -EINVAL;
mtree_lock(mt);
ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi,
next, gfp);
mtree_unlock(mt);
return ret;
}
EXPORT_SYMBOL(mtree_alloc_cyclic);
int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp)
{
int ret = 0;
MA_STATE(mas, mt, 0, 0);
if (!mt_is_alloc(mt))
return -EINVAL;
if (WARN_ON_ONCE(mt_is_reserved(entry)))
return -EINVAL;
mtree_lock(mt);
retry:
ret = mas_empty_area_rev(&mas, min, max, size);
if (ret)
goto unlock;
mas_insert(&mas, entry);
/*
* mas_nomem() may release the lock, causing the allocated area
* to be unavailable, so try to allocate a free area again.
*/
if (mas_nomem(&mas, gfp))
goto retry;
if (mas_is_err(&mas))
ret = xa_err(mas.node);
else
*startp = mas.index;
unlock:
mtree_unlock(mt);
mas_destroy(&mas);
return ret;
}
EXPORT_SYMBOL(mtree_alloc_rrange);
/**
* mtree_erase() - Find an index and erase the entire range.
* @mt: The maple tree
* @index: The index to erase
*
* Erasing is the same as a walk to an entry then a store of a NULL to that
* ENTIRE range. In fact, it is implemented as such using the advanced API.
*
* Return: The entry stored at the @index or %NULL
*/
void *mtree_erase(struct maple_tree *mt, unsigned long index)
{
void *entry = NULL;
MA_STATE(mas, mt, index, index);
trace_ma_op(__func__, &mas);
mtree_lock(mt);
entry = mas_erase(&mas);
mtree_unlock(mt);
return entry;
}
EXPORT_SYMBOL(mtree_erase);
/*
* mas_dup_free() - Free an incomplete duplication of a tree.
* @mas: The maple state of a incomplete tree.
*
* The parameter @mas->node passed in indicates that the allocation failed on
* this node. This function frees all nodes starting from @mas->node in the
* reverse order of mas_dup_build(). There is no need to hold the source tree
* lock at this time.
*/
static void mas_dup_free(struct ma_state *mas)
{
struct maple_node *node;
enum maple_type type;
void __rcu **slots;
unsigned char count, i;
/* Maybe the first node allocation failed. */
if (mas_is_none(mas))
return;
while (!mte_is_root(mas->node)) {
mas_ascend(mas);
if (mas->offset) {
mas->offset--;
do {
mas_descend(mas);
mas->offset = mas_data_end(mas);
} while (!mte_is_leaf(mas->node));
mas_ascend(mas);
}
node = mte_to_node(mas->node);
type = mte_node_type(mas->node);
slots = ma_slots(node, type);
count = mas_data_end(mas) + 1;
for (i = 0; i < count; i++)
((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK;
mt_free_bulk(count, slots);
}
node = mte_to_node(mas->node);
mt_free_one(node);
}
/*
* mas_copy_node() - Copy a maple node and replace the parent.
* @mas: The maple state of source tree.
* @new_mas: The maple state of new tree.
* @parent: The parent of the new node.
*
* Copy @mas->node to @new_mas->node, set @parent to be the parent of
* @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM.
*/
static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas,
struct maple_pnode *parent)
{
struct maple_node *node = mte_to_node(mas->node);
struct maple_node *new_node = mte_to_node(new_mas->node);
unsigned long val;
/* Copy the node completely. */
memcpy(new_node, node, sizeof(struct maple_node));
/* Update the parent node pointer. */
val = (unsigned long)node->parent & MAPLE_NODE_MASK;
new_node->parent = ma_parent_ptr(val | (unsigned long)parent);
}
/*
* mas_dup_alloc() - Allocate child nodes for a maple node.
* @mas: The maple state of source tree.
* @new_mas: The maple state of new tree.
* @gfp: The GFP_FLAGS to use for allocations.
*
* This function allocates child nodes for @new_mas->node during the duplication
* process. If memory allocation fails, @mas is set to -ENOMEM.
*/
static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas,
gfp_t gfp)
{
struct maple_node *node = mte_to_node(mas->node);
struct maple_node *new_node = mte_to_node(new_mas->node);
enum maple_type type;
unsigned char request, count, i;
void __rcu **slots;
void __rcu **new_slots;
unsigned long val;
/* Allocate memory for child nodes. */
type = mte_node_type(mas->node);
new_slots = ma_slots(new_node, type);
request = mas_data_end(mas) + 1;
count = mt_alloc_bulk(gfp, request, (void **)new_slots);
if (unlikely(count < request)) {
memset(new_slots, 0, request * sizeof(void *));
mas_set_err(mas, -ENOMEM);
return;
}
/* Restore node type information in slots. */
slots = ma_slots(node, type);
for (i = 0; i < count; i++) {
val = (unsigned long)mt_slot_locked(mas->tree, slots, i);
val &= MAPLE_NODE_MASK;
((unsigned long *)new_slots)[i] |= val;
}
}
/*
* mas_dup_build() - Build a new maple tree from a source tree
* @mas: The maple state of source tree, need to be in MAS_START state.
* @new_mas: The maple state of new tree, need to be in MAS_START state.
* @gfp: The GFP_FLAGS to use for allocations.
*
* This function builds a new tree in DFS preorder. If the memory allocation
* fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the
* last node. mas_dup_free() will free the incomplete duplication of a tree.
*
* Note that the attributes of the two trees need to be exactly the same, and the
* new tree needs to be empty, otherwise -EINVAL will be set in @mas.
*/
static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas,
gfp_t gfp)
{
struct maple_node *node;
struct maple_pnode *parent = NULL;
struct maple_enode *root;
enum maple_type type;
if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) ||
unlikely(!mtree_empty(new_mas->tree))) {
mas_set_err(mas, -EINVAL);
return;
}
root = mas_start(mas);
if (mas_is_ptr(mas) || mas_is_none(mas))
goto set_new_tree;
node = mt_alloc_one(gfp);
if (!node) {
new_mas->status = ma_none;
mas_set_err(mas, -ENOMEM);
return;
}
type = mte_node_type(mas->node);
root = mt_mk_node(node, type);
new_mas->node = root;
new_mas->min = 0;
new_mas->max = ULONG_MAX;
root = mte_mk_root(root);
while (1) {
mas_copy_node(mas, new_mas, parent);
if (!mte_is_leaf(mas->node)) {
/* Only allocate child nodes for non-leaf nodes. */
mas_dup_alloc(mas, new_mas, gfp);
if (unlikely(mas_is_err(mas)))
return;
} else {
/*
* This is the last leaf node and duplication is
* completed.
*/
if (mas->max == ULONG_MAX)
goto done;
/* This is not the last leaf node and needs to go up. */
do {
mas_ascend(mas);
mas_ascend(new_mas);
} while (mas->offset == mas_data_end(mas));
/* Move to the next subtree. */
mas->offset++;
new_mas->offset++;
}
mas_descend(mas);
parent = ma_parent_ptr(mte_to_node(new_mas->node));
mas_descend(new_mas);
mas->offset = 0;
new_mas->offset = 0;
}
done:
/* Specially handle the parent of the root node. */
mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas));
set_new_tree:
/* Make them the same height */
new_mas->tree->ma_flags = mas->tree->ma_flags;
rcu_assign_pointer(new_mas->tree->ma_root, root);
}
/**
* __mt_dup(): Duplicate an entire maple tree
* @mt: The source maple tree
* @new: The new maple tree
* @gfp: The GFP_FLAGS to use for allocations
*
* This function duplicates a maple tree in Depth-First Search (DFS) pre-order
* traversal. It uses memcpy() to copy nodes in the source tree and allocate
* new child nodes in non-leaf nodes. The new node is exactly the same as the
* source node except for all the addresses stored in it. It will be faster than
* traversing all elements in the source tree and inserting them one by one into
* the new tree.
* The user needs to ensure that the attributes of the source tree and the new
* tree are the same, and the new tree needs to be an empty tree, otherwise
* -EINVAL will be returned.
* Note that the user needs to manually lock the source tree and the new tree.
*
* Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
* the attributes of the two trees are different or the new tree is not an empty
* tree.
*/
int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
{
int ret = 0;
MA_STATE(mas, mt, 0, 0);
MA_STATE(new_mas, new, 0, 0);
mas_dup_build(&mas, &new_mas, gfp);
if (unlikely(mas_is_err(&mas))) {
ret = xa_err(mas.node);
if (ret == -ENOMEM)
mas_dup_free(&new_mas);
}
return ret;
}
EXPORT_SYMBOL(__mt_dup);
/**
* mtree_dup(): Duplicate an entire maple tree
* @mt: The source maple tree
* @new: The new maple tree
* @gfp: The GFP_FLAGS to use for allocations
*
* This function duplicates a maple tree in Depth-First Search (DFS) pre-order
* traversal. It uses memcpy() to copy nodes in the source tree and allocate
* new child nodes in non-leaf nodes. The new node is exactly the same as the
* source node except for all the addresses stored in it. It will be faster than
* traversing all elements in the source tree and inserting them one by one into
* the new tree.
* The user needs to ensure that the attributes of the source tree and the new
* tree are the same, and the new tree needs to be an empty tree, otherwise
* -EINVAL will be returned.
*
* Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
* the attributes of the two trees are different or the new tree is not an empty
* tree.
*/
int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
{
int ret = 0;
MA_STATE(mas, mt, 0, 0);
MA_STATE(new_mas, new, 0, 0);
mas_lock(&new_mas);
mas_lock_nested(&mas, SINGLE_DEPTH_NESTING);
mas_dup_build(&mas, &new_mas, gfp);
mas_unlock(&mas);
if (unlikely(mas_is_err(&mas))) {
ret = xa_err(mas.node);
if (ret == -ENOMEM)
mas_dup_free(&new_mas);
}
mas_unlock(&new_mas);
return ret;
}
EXPORT_SYMBOL(mtree_dup);
/**
* __mt_destroy() - Walk and free all nodes of a locked maple tree.
* @mt: The maple tree
*
* Note: Does not handle locking.
*/
void __mt_destroy(struct maple_tree *mt)
{ void *root = mt_root_locked(mt);
rcu_assign_pointer(mt->ma_root, NULL);
if (xa_is_node(root)) mte_destroy_walk(root, mt);
mt->ma_flags = mt_attr(mt);
}
EXPORT_SYMBOL_GPL(__mt_destroy);
/**
* mtree_destroy() - Destroy a maple tree
* @mt: The maple tree
*
* Frees all resources used by the tree. Handles locking.
*/
void mtree_destroy(struct maple_tree *mt)
{
mtree_lock(mt);
__mt_destroy(mt);
mtree_unlock(mt);
}
EXPORT_SYMBOL(mtree_destroy);
/**
* mt_find() - Search from the start up until an entry is found.
* @mt: The maple tree
* @index: Pointer which contains the start location of the search
* @max: The maximum value of the search range
*
* Takes RCU read lock internally to protect the search, which does not
* protect the returned pointer after dropping RCU read lock.
* See also: Documentation/core-api/maple_tree.rst
*
* In case that an entry is found @index is updated to point to the next
* possible entry independent whether the found entry is occupying a
* single index or a range if indices.
*
* Return: The entry at or after the @index or %NULL
*/
void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max)
{
MA_STATE(mas, mt, *index, *index);
void *entry;
#ifdef CONFIG_DEBUG_MAPLE_TREE
unsigned long copy = *index;
#endif
trace_ma_read(__func__, &mas);
if ((*index) > max)
return NULL;
rcu_read_lock();
retry:
entry = mas_state_walk(&mas); if (mas_is_start(&mas))
goto retry;
if (unlikely(xa_is_zero(entry)))
entry = NULL;
if (entry)
goto unlock;
while (mas_is_active(&mas) && (mas.last < max)) {
entry = mas_next_slot(&mas, max, false);
if (likely(entry && !xa_is_zero(entry)))
break;
}
if (unlikely(xa_is_zero(entry)))
entry = NULL;
unlock:
rcu_read_unlock(); if (likely(entry)) {
*index = mas.last + 1;
#ifdef CONFIG_DEBUG_MAPLE_TREE
if (MT_WARN_ON(mt, (*index) && ((*index) <= copy)))
pr_err("index not increased! %lx <= %lx\n",
*index, copy);
#endif
}
return entry;
}
EXPORT_SYMBOL(mt_find);
/**
* mt_find_after() - Search from the start up until an entry is found.
* @mt: The maple tree
* @index: Pointer which contains the start location of the search
* @max: The maximum value to check
*
* Same as mt_find() except that it checks @index for 0 before
* searching. If @index == 0, the search is aborted. This covers a wrap
* around of @index to 0 in an iterator loop.
*
* Return: The entry at or after the @index or %NULL
*/
void *mt_find_after(struct maple_tree *mt, unsigned long *index,
unsigned long max)
{
if (!(*index))
return NULL;
return mt_find(mt, index, max);
}
EXPORT_SYMBOL(mt_find_after);
#ifdef CONFIG_DEBUG_MAPLE_TREE
atomic_t maple_tree_tests_run;
EXPORT_SYMBOL_GPL(maple_tree_tests_run);
atomic_t maple_tree_tests_passed;
EXPORT_SYMBOL_GPL(maple_tree_tests_passed);
#ifndef __KERNEL__
extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int);
void mt_set_non_kernel(unsigned int val)
{
kmem_cache_set_non_kernel(maple_node_cache, val);
}
extern void kmem_cache_set_callback(struct kmem_cache *cachep,
void (*callback)(void *));
void mt_set_callback(void (*callback)(void *))
{
kmem_cache_set_callback(maple_node_cache, callback);
}
extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private);
void mt_set_private(void *private)
{
kmem_cache_set_private(maple_node_cache, private);
}
extern unsigned long kmem_cache_get_alloc(struct kmem_cache *);
unsigned long mt_get_alloc_size(void)
{
return kmem_cache_get_alloc(maple_node_cache);
}
extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *);
void mt_zero_nr_tallocated(void)
{
kmem_cache_zero_nr_tallocated(maple_node_cache);
}
extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *);
unsigned int mt_nr_tallocated(void)
{
return kmem_cache_nr_tallocated(maple_node_cache);
}
extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *);
unsigned int mt_nr_allocated(void)
{
return kmem_cache_nr_allocated(maple_node_cache);
}
void mt_cache_shrink(void)
{
}
#else
/*
* mt_cache_shrink() - For testing, don't use this.
*
* Certain testcases can trigger an OOM when combined with other memory
* debugging configuration options. This function is used to reduce the
* possibility of an out of memory even due to kmem_cache objects remaining
* around for longer than usual.
*/
void mt_cache_shrink(void)
{
kmem_cache_shrink(maple_node_cache);
}
EXPORT_SYMBOL_GPL(mt_cache_shrink);
#endif /* not defined __KERNEL__ */
/*
* mas_get_slot() - Get the entry in the maple state node stored at @offset.
* @mas: The maple state
* @offset: The offset into the slot array to fetch.
*
* Return: The entry stored at @offset.
*/
static inline struct maple_enode *mas_get_slot(struct ma_state *mas,
unsigned char offset)
{
return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)),
offset);
}
/* Depth first search, post-order */
static void mas_dfs_postorder(struct ma_state *mas, unsigned long max)
{
struct maple_enode *p, *mn = mas->node;
unsigned long p_min, p_max;
mas_next_node(mas, mas_mn(mas), max);
if (!mas_is_overflow(mas))
return;
if (mte_is_root(mn))
return;
mas->node = mn;
mas_ascend(mas);
do {
p = mas->node;
p_min = mas->min;
p_max = mas->max;
mas_prev_node(mas, 0);
} while (!mas_is_underflow(mas)); mas->node = p;
mas->max = p_max;
mas->min = p_min;
}
/* Tree validations */
static void mt_dump_node(const struct maple_tree *mt, void *entry,
unsigned long min, unsigned long max, unsigned int depth,
enum mt_dump_format format);
static void mt_dump_range(unsigned long min, unsigned long max,
unsigned int depth, enum mt_dump_format format)
{
static const char spaces[] = " ";
switch(format) {
case mt_dump_hex:
if (min == max)
pr_info("%.*s%lx: ", depth * 2, spaces, min);
else
pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max);
break;
case mt_dump_dec:
if (min == max)
pr_info("%.*s%lu: ", depth * 2, spaces, min);
else
pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max);
}
}
static void mt_dump_entry(void *entry, unsigned long min, unsigned long max,
unsigned int depth, enum mt_dump_format format)
{
mt_dump_range(min, max, depth, format);
if (xa_is_value(entry))
pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry),
xa_to_value(entry), entry);
else if (xa_is_zero(entry))
pr_cont("zero (%ld)\n", xa_to_internal(entry));
else if (mt_is_reserved(entry))
pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry);
else
pr_cont(PTR_FMT "\n", entry);
}
static void mt_dump_range64(const struct maple_tree *mt, void *entry,
unsigned long min, unsigned long max, unsigned int depth,
enum mt_dump_format format)
{
struct maple_range_64 *node = &mte_to_node(entry)->mr64;
bool leaf = mte_is_leaf(entry);
unsigned long first = min;
int i;
pr_cont(" contents: ");
for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) {
switch(format) {
case mt_dump_hex:
pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]);
break;
case mt_dump_dec:
pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]);
}
}
pr_cont(PTR_FMT "\n", node->slot[i]);
for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) {
unsigned long last = max;
if (i < (MAPLE_RANGE64_SLOTS - 1))
last = node->pivot[i];
else if (!node->slot[i] && max != mt_node_max(entry))
break;
if (last == 0 && i > 0)
break;
if (leaf)
mt_dump_entry(mt_slot(mt, node->slot, i),
first, last, depth + 1, format);
else if (node->slot[i])
mt_dump_node(mt, mt_slot(mt, node->slot, i),
first, last, depth + 1, format);
if (last == max)
break;
if (last > max) {
switch(format) {
case mt_dump_hex:
pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n",
node, last, max, i);
break;
case mt_dump_dec:
pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n",
node, last, max, i);
}
}
first = last + 1;
}
}
static void mt_dump_arange64(const struct maple_tree *mt, void *entry,
unsigned long min, unsigned long max, unsigned int depth,
enum mt_dump_format format)
{
struct maple_arange_64 *node = &mte_to_node(entry)->ma64;
unsigned long first = min;
int i;
pr_cont(" contents: ");
for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) {
switch (format) {
case mt_dump_hex:
pr_cont("%lx ", node->gap[i]);
break;
case mt_dump_dec:
pr_cont("%lu ", node->gap[i]);
}
}
pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap);
for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) {
switch (format) {
case mt_dump_hex:
pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]);
break;
case mt_dump_dec:
pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]);
}
}
pr_cont(PTR_FMT "\n", node->slot[i]);
for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) {
unsigned long last = max;
if (i < (MAPLE_ARANGE64_SLOTS - 1))
last = node->pivot[i];
else if (!node->slot[i])
break;
if (last == 0 && i > 0)
break;
if (node->slot[i])
mt_dump_node(mt, mt_slot(mt, node->slot, i),
first, last, depth + 1, format);
if (last == max)
break;
if (last > max) {
switch(format) {
case mt_dump_hex:
pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n",
node, last, max, i);
break;
case mt_dump_dec:
pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n",
node, last, max, i);
}
}
first = last + 1;
}
}
static void mt_dump_node(const struct maple_tree *mt, void *entry,
unsigned long min, unsigned long max, unsigned int depth,
enum mt_dump_format format)
{
struct maple_node *node = mte_to_node(entry);
unsigned int type = mte_node_type(entry);
unsigned int i;
mt_dump_range(min, max, depth, format);
pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node,
depth, type, node ? node->parent : NULL);
switch (type) {
case maple_dense:
pr_cont("\n");
for (i = 0; i < MAPLE_NODE_SLOTS; i++) {
if (min + i > max)
pr_cont("OUT OF RANGE: ");
mt_dump_entry(mt_slot(mt, node->slot, i),
min + i, min + i, depth, format);
}
break;
case maple_leaf_64:
case maple_range_64:
mt_dump_range64(mt, entry, min, max, depth, format);
break;
case maple_arange_64:
mt_dump_arange64(mt, entry, min, max, depth, format);
break;
default:
pr_cont(" UNKNOWN TYPE\n");
}
}
void mt_dump(const struct maple_tree *mt, enum mt_dump_format format)
{
void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt));
pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n",
mt, mt->ma_flags, mt_height(mt), entry);
if (xa_is_node(entry))
mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format);
else if (entry)
mt_dump_entry(entry, 0, 0, 0, format);
else
pr_info("(empty)\n");
}
EXPORT_SYMBOL_GPL(mt_dump);
/*
* Calculate the maximum gap in a node and check if that's what is reported in
* the parent (unless root).
*/
static void mas_validate_gaps(struct ma_state *mas)
{
struct maple_enode *mte = mas->node;
struct maple_node *p_mn, *node = mte_to_node(mte);
enum maple_type mt = mte_node_type(mas->node);
unsigned long gap = 0, max_gap = 0;
unsigned long p_end, p_start = mas->min;
unsigned char p_slot, offset;
unsigned long *gaps = NULL;
unsigned long *pivots = ma_pivots(node, mt);
unsigned int i;
if (ma_is_dense(mt)) {
for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) {
if (gap > max_gap)
max_gap = gap;
gap = 0;
continue;
}
gap++;
}
goto counted;
}
gaps = ma_gaps(node, mt);
for (i = 0; i < mt_slot_count(mte); i++) {
p_end = mas_safe_pivot(mas, pivots, i, mt);
if (!gaps) {
if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1;
} else {
void *entry = mas_get_slot(mas, i);
gap = gaps[i];
MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) {
pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n",
mas_mn(mas), i, gap, p_end, p_start,
p_end - p_start + 1);
MT_BUG_ON(mas->tree, gap > p_end - p_start + 1);
}
}
if (gap > max_gap)
max_gap = gap;
p_start = p_end + 1;
if (p_end >= mas->max)
break;
}
counted:
if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps);
offset = ma_meta_gap(node);
if (offset > i) {
pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset);
MT_BUG_ON(mas->tree, 1);
}
if (gaps[offset] != max_gap) {
pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n",
node, offset, max_gap);
MT_BUG_ON(mas->tree, 1);
}
for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) {
pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n",
node, i);
MT_BUG_ON(mas->tree, 1);
}
}
}
if (mte_is_root(mte))
return;
p_slot = mte_parent_slot(mas->node);
p_mn = mte_parent(mte);
MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) {
pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap);
mt_dump(mas->tree, mt_dump_hex);
MT_BUG_ON(mas->tree, 1);
}
}
static void mas_validate_parent_slot(struct ma_state *mas)
{
struct maple_node *parent;
struct maple_enode *node;
enum maple_type p_type;
unsigned char p_slot;
void __rcu **slots;
int i;
if (mte_is_root(mas->node))
return;
p_slot = mte_parent_slot(mas->node);
p_type = mas_parent_type(mas, mas->node);
parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent);
/* Check prev/next parent slot for duplicate node entry */
for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i);
if (i == p_slot) {
if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n",
parent, i, mas_mn(mas));
MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) {
pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n",
mas_mn(mas), parent, i, p_slot);
MT_BUG_ON(mas->tree, node == mas->node);
}
}
}
static void mas_validate_child_slot(struct ma_state *mas)
{
enum maple_type type = mte_node_type(mas->node);
void __rcu **slots = ma_slots(mte_to_node(mas->node), type);
unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type);
struct maple_enode *child;
unsigned char i;
if (mte_is_leaf(mas->node))
return;
for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) {
pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n",
mas_mn(mas), i);
MT_BUG_ON(mas->tree, 1);
}
if (mte_parent_slot(child) != i) {
pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n",
mas_mn(mas), i, mte_to_node(child),
mte_parent_slot(child));
MT_BUG_ON(mas->tree, 1);
}
if (mte_parent(child) != mte_to_node(mas->node)) {
pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n",
mte_to_node(child), mte_parent(child),
mte_to_node(mas->node));
MT_BUG_ON(mas->tree, 1);
}
if (i < mt_pivots[type] && pivots[i] == mas->max)
break;
}
}
/*
* Validate all pivots are within mas->min and mas->max, check metadata ends
* where the maximum ends and ensure there is no slots or pivots set outside of
* the end of the data.
*/
static void mas_validate_limits(struct ma_state *mas)
{
int i;
unsigned long prev_piv = 0;
enum maple_type type = mte_node_type(mas->node);
void __rcu **slots = ma_slots(mte_to_node(mas->node), type);
unsigned long *pivots = ma_pivots(mas_mn(mas), type);
for (i = 0; i < mt_slots[type]; i++) {
unsigned long piv;
piv = mas_safe_pivot(mas, pivots, i, type);
if (!piv && (i != 0)) {
pr_err("Missing node limit pivot at " PTR_FMT "[%u]",
mas_mn(mas), i);
MAS_WARN_ON(mas, 1);
}
if (prev_piv > piv) {
pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n",
mas_mn(mas), i, piv, prev_piv);
MAS_WARN_ON(mas, piv < prev_piv);
}
if (piv < mas->min) {
pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i,
piv, mas->min);
MAS_WARN_ON(mas, piv < mas->min);
}
if (piv > mas->max) {
pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i,
piv, mas->max);
MAS_WARN_ON(mas, piv > mas->max);
}
prev_piv = piv;
if (piv == mas->max)
break;
}
if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n",
mas_mn(mas), mas_data_end(mas), i);
MT_BUG_ON(mas->tree, 1);
}
for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) {
pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n",
mas_mn(mas), i, entry);
MT_BUG_ON(mas->tree, entry != NULL);
}
if (i < mt_pivots[type]) {
unsigned long piv = pivots[i];
if (!piv)
continue;
pr_err(PTR_FMT "[%u] should not have piv %lu\n",
mas_mn(mas), i, piv);
MAS_WARN_ON(mas, i < mt_pivots[type] - 1);
}
}
}
static void mt_validate_nulls(struct maple_tree *mt)
{
void *entry, *last = (void *)1;
unsigned char offset = 0;
void __rcu **slots;
MA_STATE(mas, mt, 0, 0);
mas_start(&mas);
if (mas_is_none(&mas) || (mas_is_ptr(&mas)))
return;
while (!mte_is_leaf(mas.node))
mas_descend(&mas);
slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node));
do {
entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n",
mas_mn(&mas), offset);
}
MT_BUG_ON(mt, !last && !entry);
last = entry;
if (offset == mas_data_end(&mas)) {
mas_next_node(&mas, mas_mn(&mas), ULONG_MAX);
if (mas_is_overflow(&mas))
return;
offset = 0;
slots = ma_slots(mte_to_node(mas.node),
mte_node_type(mas.node));
} else {
offset++;
}
} while (!mas_is_overflow(&mas));
}
/*
* validate a maple tree by checking:
* 1. The limits (pivots are within mas->min to mas->max)
* 2. The gap is correctly set in the parents
*/
void mt_validate(struct maple_tree *mt)
__must_hold(mas->tree->ma_lock)
{
unsigned char end;
MA_STATE(mas, mt, 0, 0);
mas_start(&mas);
if (!mas_is_active(&mas))
return;
while (!mte_is_leaf(mas.node))
mas_descend(&mas);
while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) &&
(!mte_is_root(mas.node)))) {
pr_err("Invalid size %u of " PTR_FMT "\n",
end, mas_mn(&mas));
}
mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX);
}
mt_validate_nulls(mt);
}
EXPORT_SYMBOL_GPL(mt_validate);
void mas_dump(const struct ma_state *mas)
{
pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ",
mas->tree, mas->node);
switch (mas->status) {
case ma_active:
pr_err("(ma_active)");
break;
case ma_none:
pr_err("(ma_none)");
break;
case ma_root:
pr_err("(ma_root)");
break;
case ma_start:
pr_err("(ma_start) ");
break;
case ma_pause:
pr_err("(ma_pause) ");
break;
case ma_overflow:
pr_err("(ma_overflow) ");
break;
case ma_underflow:
pr_err("(ma_underflow) ");
break;
case ma_error:
pr_err("(ma_error) ");
break;
}
pr_err("Store Type: ");
switch (mas->store_type) {
case wr_invalid:
pr_err("invalid store type\n");
break;
case wr_new_root:
pr_err("new_root\n");
break;
case wr_store_root:
pr_err("store_root\n");
break;
case wr_exact_fit:
pr_err("exact_fit\n");
break;
case wr_split_store:
pr_err("split_store\n");
break;
case wr_slot_store:
pr_err("slot_store\n");
break;
case wr_append:
pr_err("append\n");
break;
case wr_node_store:
pr_err("node_store\n");
break;
case wr_spanning_store:
pr_err("spanning_store\n");
break;
case wr_rebalance:
pr_err("rebalance\n");
break;
}
pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end,
mas->index, mas->last);
pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n",
mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags);
if (mas->index > mas->last)
pr_err("Check index & last\n");
}
EXPORT_SYMBOL_GPL(mas_dump);
void mas_wr_dump(const struct ma_wr_state *wr_mas)
{
pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n",
wr_mas->node, wr_mas->r_min, wr_mas->r_max);
pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n",
wr_mas->type, wr_mas->offset_end, wr_mas->mas->end,
wr_mas->end_piv);
}
EXPORT_SYMBOL_GPL(mas_wr_dump);
#endif /* CONFIG_DEBUG_MAPLE_TREE */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_CPUMASK_H
#define __LINUX_CPUMASK_H
/*
* Cpumasks provide a bitmap suitable for representing the
* set of CPUs in a system, one bit position per CPU number. In general,
* only nr_cpu_ids (<= NR_CPUS) bits are valid.
*/
#include <linux/cleanup.h>
#include <linux/kernel.h>
#include <linux/bitmap.h>
#include <linux/cpumask_types.h>
#include <linux/atomic.h>
#include <linux/bug.h>
#include <linux/gfp_types.h>
#include <linux/numa.h>
/**
* cpumask_pr_args - printf args to output a cpumask
* @maskp: cpumask to be printed
*
* Can be used to provide arguments for '%*pb[l]' when printing a cpumask.
*/
#define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp)
#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
#define nr_cpu_ids ((unsigned int)NR_CPUS)
#else
extern unsigned int nr_cpu_ids;
#endif
static __always_inline void set_nr_cpu_ids(unsigned int nr)
{
#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
WARN_ON(nr != nr_cpu_ids);
#else
nr_cpu_ids = nr;
#endif
}
/*
* We have several different "preferred sizes" for the cpumask
* operations, depending on operation.
*
* For example, the bitmap scanning and operating operations have
* optimized routines that work for the single-word case, but only when
* the size is constant. So if NR_CPUS fits in one single word, we are
* better off using that small constant, in order to trigger the
* optimized bit finding. That is 'small_cpumask_size'.
*
* The clearing and copying operations will similarly perform better
* with a constant size, but we limit that size arbitrarily to four
* words. We call this 'large_cpumask_size'.
*
* Finally, some operations just want the exact limit, either because
* they set bits or just don't have any faster fixed-sized versions. We
* call this just 'nr_cpumask_bits'.
*
* Note that these optional constants are always guaranteed to be at
* least as big as 'nr_cpu_ids' itself is, and all our cpumask
* allocations are at least that size (see cpumask_size()). The
* optimization comes from being able to potentially use a compile-time
* constant instead of a run-time generated exact number of CPUs.
*/
#if NR_CPUS <= BITS_PER_LONG
#define small_cpumask_bits ((unsigned int)NR_CPUS)
#define large_cpumask_bits ((unsigned int)NR_CPUS)
#elif NR_CPUS <= 4*BITS_PER_LONG
#define small_cpumask_bits nr_cpu_ids
#define large_cpumask_bits ((unsigned int)NR_CPUS)
#else
#define small_cpumask_bits nr_cpu_ids
#define large_cpumask_bits nr_cpu_ids
#endif
#define nr_cpumask_bits nr_cpu_ids
/*
* The following particular system cpumasks and operations manage
* possible, present, active and online cpus.
*
* cpu_possible_mask- has bit 'cpu' set iff cpu is populatable
* cpu_present_mask - has bit 'cpu' set iff cpu is populated
* cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online
* cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler
* cpu_active_mask - has bit 'cpu' set iff cpu available to migration
*
* If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
*
* The cpu_possible_mask is fixed at boot time, as the set of CPU IDs
* that it is possible might ever be plugged in at anytime during the
* life of that system boot. The cpu_present_mask is dynamic(*),
* representing which CPUs are currently plugged in. And
* cpu_online_mask is the dynamic subset of cpu_present_mask,
* indicating those CPUs available for scheduling.
*
* If HOTPLUG is enabled, then cpu_present_mask varies dynamically,
* depending on what ACPI reports as currently plugged in, otherwise
* cpu_present_mask is just a copy of cpu_possible_mask.
*
* (*) Well, cpu_present_mask is dynamic in the hotplug case. If not
* hotplug, it's a copy of cpu_possible_mask, hence fixed at boot.
*
* Subtleties:
* 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
* assumption that their single CPU is online. The UP
* cpu_{online,possible,present}_masks are placebos. Changing them
* will have no useful affect on the following num_*_cpus()
* and cpu_*() macros in the UP case. This ugliness is a UP
* optimization - don't waste any instructions or memory references
* asking if you're online or how many CPUs there are if there is
* only one CPU.
*/
extern struct cpumask __cpu_possible_mask;
extern struct cpumask __cpu_online_mask;
extern struct cpumask __cpu_enabled_mask;
extern struct cpumask __cpu_present_mask;
extern struct cpumask __cpu_active_mask;
extern struct cpumask __cpu_dying_mask;
#define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
#define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask)
#define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask)
#define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask)
#define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask)
#define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask)
extern atomic_t __num_online_cpus;
extern cpumask_t cpus_booted_once_mask;
static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
{
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
WARN_ON_ONCE(cpu >= bits);
#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
}
/* verify cpu argument to cpumask_* operators */
static __always_inline unsigned int cpumask_check(unsigned int cpu)
{
cpu_max_bits_warn(cpu, small_cpumask_bits);
return cpu;
}
/**
* cpumask_first - get the first cpu in a cpumask
* @srcp: the cpumask pointer
*
* Return: >= nr_cpu_ids if no cpus set.
*/
static __always_inline unsigned int cpumask_first(const struct cpumask *srcp)
{
return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
}
/**
* cpumask_first_zero - get the first unset cpu in a cpumask
* @srcp: the cpumask pointer
*
* Return: >= nr_cpu_ids if all cpus are set.
*/
static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
{
return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
}
/**
* cpumask_first_and - return the first cpu from *srcp1 & *srcp2
* @srcp1: the first input
* @srcp2: the second input
*
* Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and().
*/
static __always_inline
unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
{
return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
}
/**
* cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3
* @srcp1: the first input
* @srcp2: the second input
* @srcp3: the third input
*
* Return: >= nr_cpu_ids if no cpus set in all.
*/
static __always_inline
unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
const struct cpumask *srcp2,
const struct cpumask *srcp3)
{
return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
cpumask_bits(srcp3), small_cpumask_bits);
}
/**
* cpumask_last - get the last CPU in a cpumask
* @srcp: - the cpumask pointer
*
* Return: >= nr_cpumask_bits if no CPUs set.
*/
static __always_inline unsigned int cpumask_last(const struct cpumask *srcp)
{
return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
}
/**
* cpumask_next - get the next cpu in a cpumask
* @n: the cpu prior to the place to search (i.e. return will be > @n)
* @srcp: the cpumask pointer
*
* Return: >= nr_cpu_ids if no further cpus set.
*/
static __always_inline
unsigned int cpumask_next(int n, const struct cpumask *srcp)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1);
}
/**
* cpumask_next_zero - get the next unset cpu in a cpumask
* @n: the cpu prior to the place to search (i.e. return will be > @n)
* @srcp: the cpumask pointer
*
* Return: >= nr_cpu_ids if no further cpus unset.
*/
static __always_inline
unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1);
}
#if NR_CPUS == 1
/* Uniprocessor: there is only one valid CPU */
static __always_inline
unsigned int cpumask_local_spread(unsigned int i, int node)
{
return 0;
}
static __always_inline
unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p)
{
return cpumask_first_and(src1p, src2p);
}
static __always_inline
unsigned int cpumask_any_distribute(const struct cpumask *srcp)
{
return cpumask_first(srcp);
}
#else
unsigned int cpumask_local_spread(unsigned int i, int node);
unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p);
unsigned int cpumask_any_distribute(const struct cpumask *srcp);
#endif /* NR_CPUS */
/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (i.e. return will be > @n)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Return: >= nr_cpu_ids if no further cpus set in both.
*/
static __always_inline
unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
/* -1 is a legal arg here. */
if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
small_cpumask_bits, n + 1);
}
/**
* cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from
* @n+1. If nothing found, wrap around and start from
* the beginning
* @n: the cpu prior to the place to search (i.e. search starts from @n+1)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty.
*/
static __always_inline
unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p),
small_cpumask_bits, n + 1);
}
/**
* cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing
* found, wrap around and start from the beginning
* @n: the cpu prior to the place to search (i.e. search starts from @n+1)
* @src: cpumask pointer
*
* Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty.
*/
static __always_inline
unsigned int cpumask_next_wrap(int n, const struct cpumask *src)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1);
}
/**
* for_each_cpu - iterate over every cpu in a mask
* @cpu: the (optionally unsigned) integer iterator
* @mask: the cpumask pointer
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu(cpu, mask) \
for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
/**
* for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
* @cpu: the (optionally unsigned) integer iterator
* @mask: the cpumask pointer
* @start: the start location
*
* The implementation does not assume any bit in @mask is set (including @start).
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu_wrap(cpu, mask, start) \
for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start)
/**
* for_each_cpu_and - iterate over every cpu in both masks
* @cpu: the (optionally unsigned) integer iterator
* @mask1: the first cpumask pointer
* @mask2: the second cpumask pointer
*
* This saves a temporary CPU mask in many places. It is equivalent to:
* struct cpumask tmp;
* cpumask_and(&tmp, &mask1, &mask2);
* for_each_cpu(cpu, &tmp)
* ...
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu_and(cpu, mask1, mask2) \
for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
/**
* for_each_cpu_andnot - iterate over every cpu present in one mask, excluding
* those present in another.
* @cpu: the (optionally unsigned) integer iterator
* @mask1: the first cpumask pointer
* @mask2: the second cpumask pointer
*
* This saves a temporary CPU mask in many places. It is equivalent to:
* struct cpumask tmp;
* cpumask_andnot(&tmp, &mask1, &mask2);
* for_each_cpu(cpu, &tmp)
* ...
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu_andnot(cpu, mask1, mask2) \
for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
/**
* for_each_cpu_or - iterate over every cpu present in either mask
* @cpu: the (optionally unsigned) integer iterator
* @mask1: the first cpumask pointer
* @mask2: the second cpumask pointer
*
* This saves a temporary CPU mask in many places. It is equivalent to:
* struct cpumask tmp;
* cpumask_or(&tmp, &mask1, &mask2);
* for_each_cpu(cpu, &tmp)
* ...
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu_or(cpu, mask1, mask2) \
for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
/**
* for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask.
* @cpu: the (optionally unsigned) integer iterator
* @mask: the cpumask pointer
*
* After the loop, cpu is >= nr_cpu_ids.
*/
#define for_each_cpu_from(cpu, mask) \
for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits)
/**
* cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one.
* @mask: the cpumask to search
* @cpu: the cpu to ignore.
*
* Often used to find any cpu but smp_processor_id() in a mask.
* Return: >= nr_cpu_ids if no cpus set.
*/
static __always_inline
unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
{
unsigned int i;
cpumask_check(cpu);
for_each_cpu(i, mask)
if (i != cpu)
break;
return i;
}
/**
* cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one.
* @mask1: the first input cpumask
* @mask2: the second input cpumask
* @cpu: the cpu to ignore
*
* Returns >= nr_cpu_ids if no cpus set.
*/
static __always_inline
unsigned int cpumask_any_and_but(const struct cpumask *mask1,
const struct cpumask *mask2,
unsigned int cpu)
{
unsigned int i;
cpumask_check(cpu);
i = cpumask_first_and(mask1, mask2);
if (i != cpu)
return i;
return cpumask_next_and(cpu, mask1, mask2);
}
/**
* cpumask_nth - get the Nth cpu in a cpumask
* @srcp: the cpumask pointer
* @cpu: the Nth cpu to find, starting from 0
*
* Return: >= nr_cpu_ids if such cpu doesn't exist.
*/
static __always_inline
unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
{
return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
}
/**
* cpumask_nth_and - get the Nth cpu in 2 cpumasks
* @srcp1: the cpumask pointer
* @srcp2: the cpumask pointer
* @cpu: the Nth cpu to find, starting from 0
*
* Return: >= nr_cpu_ids if such cpu doesn't exist.
*/
static __always_inline
unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
const struct cpumask *srcp2)
{
return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
small_cpumask_bits, cpumask_check(cpu));
}
/**
* cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd.
* @srcp1: the cpumask pointer
* @srcp2: the cpumask pointer
* @cpu: the Nth cpu to find, starting from 0
*
* Return: >= nr_cpu_ids if such cpu doesn't exist.
*/
static __always_inline
unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
const struct cpumask *srcp2)
{
return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
small_cpumask_bits, cpumask_check(cpu));
}
/**
* cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd.
* @srcp1: the cpumask pointer
* @srcp2: the cpumask pointer
* @srcp3: the cpumask pointer
* @cpu: the Nth cpu to find, starting from 0
*
* Return: >= nr_cpu_ids if such cpu doesn't exist.
*/
static __always_inline
unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1,
const struct cpumask *srcp2,
const struct cpumask *srcp3)
{
return find_nth_and_andnot_bit(cpumask_bits(srcp1),
cpumask_bits(srcp2),
cpumask_bits(srcp3),
small_cpumask_bits, cpumask_check(cpu));
}
#define CPU_BITS_NONE \
{ \
[0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \
}
#define CPU_BITS_CPU0 \
{ \
[0] = 1UL \
}
/**
* cpumask_set_cpu - set a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @dstp: the cpumask pointer
*/
static __always_inline
void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
{
set_bit(cpumask_check(cpu), cpumask_bits(dstp));
}
static __always_inline
void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
{
__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
}
/**
* cpumask_clear_cpu - clear a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @dstp: the cpumask pointer
*/
static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
{
clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
}
static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
{
__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
}
/**
* cpumask_assign_cpu - assign a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @dstp: the cpumask pointer
* @bool: the value to assign
*/
static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
{
assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
}
static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
{
__assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
}
/**
* cpumask_test_cpu - test for a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
* Return: true if @cpu is set in @cpumask, else returns false
*/
static __always_inline
bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
{
return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
}
/**
* cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
* test_and_set_bit wrapper for cpumasks.
*
* Return: true if @cpu is set in old bitmap of @cpumask, else returns false
*/
static __always_inline
bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
{
return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
}
/**
* cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
* test_and_clear_bit wrapper for cpumasks.
*
* Return: true if @cpu is set in old bitmap of @cpumask, else returns false
*/
static __always_inline
bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
{
return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
}
/**
* cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
* @dstp: the cpumask pointer
*/
static __always_inline void cpumask_setall(struct cpumask *dstp)
{
if (small_const_nbits(small_cpumask_bits)) {
cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
return;
}
bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits);
}
/**
* cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
* @dstp: the cpumask pointer
*/
static __always_inline void cpumask_clear(struct cpumask *dstp)
{
bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
}
/**
* cpumask_and - *dstp = *src1p & *src2p
* @dstp: the cpumask result
* @src1p: the first input
* @src2p: the second input
*
* Return: false if *@dstp is empty, else returns true
*/
static __always_inline
bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p,
const struct cpumask *src2p)
{
return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
cpumask_bits(src2p), small_cpumask_bits);
}
/**
* cpumask_or - *dstp = *src1p | *src2p
* @dstp: the cpumask result
* @src1p: the first input
* @src2p: the second input
*/
static __always_inline
void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
const struct cpumask *src2p)
{
bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
cpumask_bits(src2p), small_cpumask_bits);
}
/**
* cpumask_xor - *dstp = *src1p ^ *src2p
* @dstp: the cpumask result
* @src1p: the first input
* @src2p: the second input
*/
static __always_inline
void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p,
const struct cpumask *src2p)
{
bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
cpumask_bits(src2p), small_cpumask_bits);
}
/**
* cpumask_andnot - *dstp = *src1p & ~*src2p
* @dstp: the cpumask result
* @src1p: the first input
* @src2p: the second input
*
* Return: false if *@dstp is empty, else returns true
*/
static __always_inline
bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p,
const struct cpumask *src2p)
{
return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
cpumask_bits(src2p), small_cpumask_bits);
}
/**
* cpumask_equal - *src1p == *src2p
* @src1p: the first input
* @src2p: the second input
*
* Return: true if the cpumasks are equal, false if not
*/
static __always_inline
bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p)
{
return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
small_cpumask_bits);
}
/**
* cpumask_or_equal - *src1p | *src2p == *src3p
* @src1p: the first input
* @src2p: the second input
* @src3p: the third input
*
* Return: true if first cpumask ORed with second cpumask == third cpumask,
* otherwise false
*/
static __always_inline
bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p,
const struct cpumask *src3p)
{
return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
cpumask_bits(src3p), small_cpumask_bits);
}
/**
* cpumask_intersects - (*src1p & *src2p) != 0
* @src1p: the first input
* @src2p: the second input
*
* Return: true if first cpumask ANDed with second cpumask is non-empty,
* otherwise false
*/
static __always_inline
bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p)
{
return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
small_cpumask_bits);
}
/**
* cpumask_subset - (*src1p & ~*src2p) == 0
* @src1p: the first input
* @src2p: the second input
*
* Return: true if *@src1p is a subset of *@src2p, else returns false
*/
static __always_inline
bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p)
{
return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
small_cpumask_bits);
}
/**
* cpumask_empty - *srcp == 0
* @srcp: the cpumask to that all cpus < nr_cpu_ids are clear.
*
* Return: true if srcp is empty (has no bits set), else false
*/
static __always_inline bool cpumask_empty(const struct cpumask *srcp)
{
return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits);
}
/**
* cpumask_full - *srcp == 0xFFFFFFFF...
* @srcp: the cpumask to that all cpus < nr_cpu_ids are set.
*
* Return: true if srcp is full (has all bits set), else false
*/
static __always_inline bool cpumask_full(const struct cpumask *srcp)
{
return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
}
/**
* cpumask_weight - Count of bits in *srcp
* @srcp: the cpumask to count bits (< nr_cpu_ids) in.
*
* Return: count of bits set in *srcp
*/
static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp)
{
return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits);
}
/**
* cpumask_weight_and - Count of bits in (*srcp1 & *srcp2)
* @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
* @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
*
* Return: count of bits set in both *srcp1 and *srcp2
*/
static __always_inline
unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
{
return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
}
/**
* cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2)
* @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
* @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
*
* Return: count of bits set in both *srcp1 and *srcp2
*/
static __always_inline
unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
const struct cpumask *srcp2)
{
return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
}
/**
* cpumask_shift_right - *dstp = *srcp >> n
* @dstp: the cpumask result
* @srcp: the input to shift
* @n: the number of bits to shift by
*/
static __always_inline
void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n)
{
bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
small_cpumask_bits);
}
/**
* cpumask_shift_left - *dstp = *srcp << n
* @dstp: the cpumask result
* @srcp: the input to shift
* @n: the number of bits to shift by
*/
static __always_inline
void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n)
{
bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
nr_cpumask_bits);
}
/**
* cpumask_copy - *dstp = *srcp
* @dstp: the result
* @srcp: the input cpumask
*/
static __always_inline
void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
{
bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits);
}
/**
* cpumask_any - pick an arbitrary cpu from *srcp
* @srcp: the input cpumask
*
* Return: >= nr_cpu_ids if no cpus set.
*/
#define cpumask_any(srcp) cpumask_first(srcp)
/**
* cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2
* @mask1: the first input cpumask
* @mask2: the second input cpumask
*
* Return: >= nr_cpu_ids if no cpus set.
*/
#define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2))
/**
* cpumask_of - the cpumask containing just a given cpu
* @cpu: the cpu (<= nr_cpu_ids)
*/
#define cpumask_of(cpu) (get_cpu_mask(cpu))
/**
* cpumask_parse_user - extract a cpumask from a user string
* @buf: the buffer to extract from
* @len: the length of the buffer
* @dstp: the cpumask to set.
*
* Return: -errno, or 0 for success.
*/
static __always_inline
int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp)
{
return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
* cpumask_parselist_user - extract a cpumask from a user string
* @buf: the buffer to extract from
* @len: the length of the buffer
* @dstp: the cpumask to set.
*
* Return: -errno, or 0 for success.
*/
static __always_inline
int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp)
{
return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
nr_cpumask_bits);
}
/**
* cpumask_parse - extract a cpumask from a string
* @buf: the buffer to extract from
* @dstp: the cpumask to set.
*
* Return: -errno, or 0 for success.
*/
static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp)
{
return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
* cpulist_parse - extract a cpumask from a user string of ranges
* @buf: the buffer to extract from
* @dstp: the cpumask to set.
*
* Return: -errno, or 0 for success.
*/
static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp)
{
return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
}
/**
* cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes
*
* Return: size to allocate for a &struct cpumask in bytes
*/
static __always_inline unsigned int cpumask_size(void)
{
return bitmap_size(large_cpumask_bits);
}
#ifdef CONFIG_CPUMASK_OFFSTACK
#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
#define __cpumask_var_read_mostly __read_mostly
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
static __always_inline
bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{
return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
}
/**
* alloc_cpumask_var - allocate a struct cpumask
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>).
*
* See alloc_cpumask_var_node.
*
* Return: %true if allocation succeeded, %false if not
*/
static __always_inline
bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
}
static __always_inline
bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var(mask, flags | __GFP_ZERO);
}
void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
void free_cpumask_var(cpumask_var_t mask);
void free_bootmem_cpumask_var(cpumask_var_t mask);
static __always_inline bool cpumask_available(cpumask_var_t mask)
{
return mask != NULL;
}
#else
#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
#define __cpumask_var_read_mostly
static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return true;
}
static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
int node)
{
return true;
}
static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
cpumask_clear(*mask);
return true;
}
static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
int node)
{
cpumask_clear(*mask);
return true;
}
static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
{
}
static __always_inline void free_cpumask_var(cpumask_var_t mask)
{
}
static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask)
{
}
static __always_inline bool cpumask_available(cpumask_var_t mask)
{
return true;
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T));
/* It's common to want to use cpu_all_mask in struct member initializers,
* so it has to refer to an address rather than a pointer. */
extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
#define cpu_all_mask to_cpumask(cpu_all_bits)
/* First bits of cpu_bit_bitmap are in fact unset. */
#define cpu_none_mask to_cpumask(cpu_bit_bitmap[0])
#if NR_CPUS == 1
/* Uniprocessor: the possible/online/present masks are always "1" */
#define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++)
#define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++)
#define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++)
#define for_each_possible_cpu_wrap(cpu, start) \
for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
#define for_each_online_cpu_wrap(cpu, start) \
for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
#else
#define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask)
#define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask)
#define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask)
#define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask)
#define for_each_possible_cpu_wrap(cpu, start) \
for_each_cpu_wrap((cpu), cpu_possible_mask, (start))
#define for_each_online_cpu_wrap(cpu, start) \
for_each_cpu_wrap((cpu), cpu_online_mask, (start))
#endif
/* Wrappers for arch boot code to manipulate normally-constant masks */
void init_cpu_present(const struct cpumask *src);
void init_cpu_possible(const struct cpumask *src);
#define assign_cpu(cpu, mask, val) \
assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible))
#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present))
#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active))
#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying))
void set_cpu_online(unsigned int cpu, bool online);
/**
* to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
* @bitmap: the bitmap
*
* There are a few places where cpumask_var_t isn't appropriate and
* static cpumasks must be used (eg. very early boot), yet we don't
* expose the definition of 'struct cpumask'.
*
* This does the conversion, and can be used as a constant initializer.
*/
#define to_cpumask(bitmap) \
((struct cpumask *)(1 ? (bitmap) \
: (void *)sizeof(__check_is_bitmap(bitmap))))
static __always_inline int __check_is_bitmap(const unsigned long *bitmap)
{
return 1;
}
/*
* Special-case data structure for "single bit set only" constant CPU masks.
*
* We pre-generate all the 64 (or 32) possible bit positions, with enough
* padding to the left and the right, and return the constant pointer
* appropriately offset.
*/
extern const unsigned long
cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu)
{
const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
p -= cpu / BITS_PER_LONG;
return to_cpumask(p);
}
#if NR_CPUS > 1
/**
* num_online_cpus() - Read the number of online CPUs
*
* Despite the fact that __num_online_cpus is of type atomic_t, this
* interface gives only a momentary snapshot and is not protected against
* concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
* region.
*
* Return: momentary snapshot of the number of online CPUs
*/
static __always_inline unsigned int num_online_cpus(void)
{
return raw_atomic_read(&__num_online_cpus);
}
#define num_possible_cpus() cpumask_weight(cpu_possible_mask)
#define num_enabled_cpus() cpumask_weight(cpu_enabled_mask)
#define num_present_cpus() cpumask_weight(cpu_present_mask)
#define num_active_cpus() cpumask_weight(cpu_active_mask)
static __always_inline bool cpu_online(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_online_mask);
}
static __always_inline bool cpu_enabled(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_enabled_mask);
}
static __always_inline bool cpu_possible(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_possible_mask);
}
static __always_inline bool cpu_present(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_present_mask);
}
static __always_inline bool cpu_active(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_active_mask);
}
static __always_inline bool cpu_dying(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_dying_mask);
}
#else
#define num_online_cpus() 1U
#define num_possible_cpus() 1U
#define num_enabled_cpus() 1U
#define num_present_cpus() 1U
#define num_active_cpus() 1U
static __always_inline bool cpu_online(unsigned int cpu)
{
return cpu == 0;
}
static __always_inline bool cpu_possible(unsigned int cpu)
{
return cpu == 0;
}
static __always_inline bool cpu_enabled(unsigned int cpu)
{
return cpu == 0;
}
static __always_inline bool cpu_present(unsigned int cpu)
{
return cpu == 0;
}
static __always_inline bool cpu_active(unsigned int cpu)
{
return cpu == 0;
}
static __always_inline bool cpu_dying(unsigned int cpu)
{
return false;
}
#endif /* NR_CPUS > 1 */
#define cpu_is_offline(cpu) unlikely(!cpu_online(cpu))
#if NR_CPUS <= BITS_PER_LONG
#define CPU_BITS_ALL \
{ \
[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \
}
#else /* NR_CPUS > BITS_PER_LONG */
#define CPU_BITS_ALL \
{ \
[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \
[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \
}
#endif /* NR_CPUS > BITS_PER_LONG */
/**
* cpumap_print_to_pagebuf - copies the cpumask into the buffer either
* as comma-separated list of cpus or hex values of cpumask
* @list: indicates whether the cpumap must be list
* @mask: the cpumask to copy
* @buf: the buffer to copy into
*
* Return: the length of the (null-terminated) @buf string, zero if
* nothing is copied.
*/
static __always_inline ssize_t
cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
{
return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
nr_cpu_ids);
}
/**
* cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as
* hex values of cpumask
*
* @buf: the buffer to copy into
* @mask: the cpumask to copy
* @off: in the string from which we are copying, we copy to @buf
* @count: the maximum number of bytes to print
*
* The function prints the cpumask into the buffer as hex values of
* cpumask; Typically used by bin_attribute to export cpumask bitmask
* ABI.
*
* Return: the length of how many bytes have been copied, excluding
* terminating '\0'.
*/
static __always_inline
ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
loff_t off, size_t count)
{
return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask),
nr_cpu_ids, off, count) - 1;
}
/**
* cpumap_print_list_to_buf - copies the cpumask into the buffer as
* comma-separated list of cpus
* @buf: the buffer to copy into
* @mask: the cpumask to copy
* @off: in the string from which we are copying, we copy to @buf
* @count: the maximum number of bytes to print
*
* Everything is same with the above cpumap_print_bitmask_to_buf()
* except the print format.
*
* Return: the length of how many bytes have been copied, excluding
* terminating '\0'.
*/
static __always_inline
ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
loff_t off, size_t count)
{
return bitmap_print_list_to_buf(buf, cpumask_bits(mask),
nr_cpu_ids, off, count) - 1;
}
#if NR_CPUS <= BITS_PER_LONG
#define CPU_MASK_ALL \
(cpumask_t) { { \
[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \
} }
#else
#define CPU_MASK_ALL \
(cpumask_t) { { \
[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \
[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \
} }
#endif /* NR_CPUS > BITS_PER_LONG */
#define CPU_MASK_NONE \
(cpumask_t) { { \
[0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \
} }
#define CPU_MASK_CPU0 \
(cpumask_t) { { \
[0] = 1UL \
} }
/*
* Provide a valid theoretical max size for cpumap and cpulist sysfs files
* to avoid breaking userspace which may allocate a buffer based on the size
* reported by e.g. fstat.
*
* for cpumap NR_CPUS * 9/32 - 1 should be an exact length.
*
* For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up
* to 2 orders of magnitude larger than 8192. And then we divide by 2 to
* cover a worst-case of every other cpu being on one of two nodes for a
* very large NR_CPUS.
*
* Use PAGE_SIZE as a minimum for smaller configurations while avoiding
* unsigned comparison to -1.
*/
#define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \
? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE)
#define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE)
#endif /* __LINUX_CPUMASK_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Derived from arch/arm/kvm/reset.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/hw_breakpoint.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>
#include <kvm/arm_arch_timer.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/virt.h>
/* Maximum phys_shift supported for any VM on this host */
static u32 __ro_after_init kvm_ipa_limit;
unsigned int __ro_after_init kvm_host_sve_max_vl;
/*
* ARMv8 Reset Values
*/
#define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
PSR_F_BIT | PSR_D_BIT)
#define VCPU_RESET_PSTATE_EL2 (PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \
PSR_F_BIT | PSR_D_BIT)
#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
PSR_AA32_I_BIT | PSR_AA32_F_BIT)
unsigned int __ro_after_init kvm_sve_max_vl;
int __init kvm_arm_init_sve(void)
{
if (system_supports_sve()) {
kvm_sve_max_vl = sve_max_virtualisable_vl();
kvm_host_sve_max_vl = sve_max_vl();
kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;
/*
* The get_sve_reg()/set_sve_reg() ioctl interface will need
* to be extended with multiple register slice support in
* order to support vector lengths greater than
* VL_ARCH_MAX:
*/
if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX))
kvm_sve_max_vl = VL_ARCH_MAX;
/*
* Don't even try to make use of vector lengths that
* aren't available on all CPUs, for now:
*/
if (kvm_sve_max_vl < sve_max_vl())
pr_warn("KVM: SVE vector length for guests limited to %u bytes\n",
kvm_sve_max_vl);
}
return 0;
}
static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
{
vcpu->arch.sve_max_vl = kvm_sve_max_vl;
/*
* Userspace can still customize the vector lengths by writing
* KVM_REG_ARM64_SVE_VLS. Allocation is deferred until
* kvm_arm_vcpu_finalize(), which freezes the configuration.
*/
set_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &vcpu->kvm->arch.flags);
}
/*
* Finalize vcpu's maximum SVE vector length, allocating
* vcpu->arch.sve_state as necessary.
*/
static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
{
void *buf;
unsigned int vl;
size_t reg_sz;
int ret;
vl = vcpu->arch.sve_max_vl;
/*
* Responsibility for these properties is shared between
* kvm_arm_init_sve(), kvm_vcpu_enable_sve() and
* set_sve_vls(). Double-check here just to be sure:
*/
if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() ||
vl > VL_ARCH_MAX))
return -EIO;
reg_sz = vcpu_sve_state_size(vcpu);
buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT);
if (!buf)
return -ENOMEM;
ret = kvm_share_hyp(buf, buf + reg_sz);
if (ret) {
kfree(buf);
return ret;
}
vcpu->arch.sve_state = buf;
vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED);
return 0;
}
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)
{ switch (feature) {
case KVM_ARM_VCPU_SVE:
if (!vcpu_has_sve(vcpu))
return -EINVAL;
if (kvm_arm_vcpu_sve_finalized(vcpu))
return -EPERM;
return kvm_vcpu_finalize_sve(vcpu);
}
return -EINVAL;
}
bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
{ if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu))
return false;
return true;
}
void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
void *sve_state = vcpu->arch.sve_state;
kvm_unshare_hyp(vcpu, vcpu + 1);
if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
kfree(sve_state);
free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
kfree(vcpu->arch.vncr_tlb);
kfree(vcpu->arch.ccsidr);
}
static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
{
if (vcpu_has_sve(vcpu)) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
}
/**
* kvm_reset_vcpu - sets core registers and sys_regs to reset value
* @vcpu: The VCPU pointer
*
* This function sets the registers on the virtual CPU struct to their
* architecturally defined reset values, except for registers whose reset is
* deferred until kvm_arm_vcpu_finalize().
*
* Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
* ioctl or as part of handling a request issued by another VCPU in the PSCI
* handling code. In the first case, the VCPU will not be loaded, and in the
* second case the VCPU will be loaded. Because this function operates purely
* on the memory-backed values of system registers, we want to do a full put if
* we were loaded (handling a request) and load the values back at the end of
* the function. Otherwise we leave the state alone. In both cases, we
* disable preemption around the vcpu reset as we would otherwise race with
* preempt notifiers which also call put/load.
*/
void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_reset_state reset_state;
bool loaded;
u32 pstate;
spin_lock(&vcpu->arch.mp_state_lock);
reset_state = vcpu->arch.reset_state;
vcpu->arch.reset_state.reset = false;
spin_unlock(&vcpu->arch.mp_state_lock);
preempt_disable();
loaded = (vcpu->cpu != -1);
if (loaded) kvm_arch_vcpu_put(vcpu);
if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) kvm_vcpu_enable_sve(vcpu);
} else {
kvm_vcpu_reset_sve(vcpu);
}
if (vcpu_el1_is_32bit(vcpu))
pstate = VCPU_RESET_PSTATE_SVC;
else if (vcpu_has_nv(vcpu))
pstate = VCPU_RESET_PSTATE_EL2;
else
pstate = VCPU_RESET_PSTATE_EL1;
/* Reset core registers */
memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
vcpu->arch.ctxt.spsr_abt = 0;
vcpu->arch.ctxt.spsr_und = 0;
vcpu->arch.ctxt.spsr_irq = 0;
vcpu->arch.ctxt.spsr_fiq = 0;
vcpu_gp_regs(vcpu)->pstate = pstate;
/* Reset system registers */
kvm_reset_sys_regs(vcpu);
/*
* Additional reset state handling that PSCI may have imposed on us.
* Must be done after all the sys_reg reset.
*/
if (reset_state.reset) {
unsigned long target_pc = reset_state.pc;
/* Gracefully handle Thumb2 entry point */
if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { target_pc &= ~1UL;
vcpu_set_thumb(vcpu);
}
/* Propagate caller endianness */
if (reset_state.be) kvm_vcpu_set_be(vcpu);
*vcpu_pc(vcpu) = target_pc;
vcpu_set_reg(vcpu, 0, reset_state.r0);
}
/* Reset timer */
kvm_timer_vcpu_reset(vcpu);
if (loaded) kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable();
}
u32 kvm_get_pa_bits(struct kvm *kvm)
{
/* Fixed limit until we can configure ID_AA64MMFR0.PARange */
return kvm_ipa_limit;
}
u32 get_kvm_ipa_limit(void)
{
return kvm_ipa_limit;
}
int __init kvm_set_ipa_limit(void)
{
unsigned int parange;
u64 mmfr0;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_PARANGE_SHIFT);
/*
* IPA size beyond 48 bits for 4K and 16K page size is only supported
* when LPA2 is available. So if we have LPA2, enable it, else cap to 48
* bits, in case it's reported as larger on the system.
*/
if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K)
parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
/*
* Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
* Stage-2. If not, things will stop very quickly.
*/
switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT)) {
case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE:
kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
return -EINVAL;
case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT:
kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
break;
case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX:
kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
break;
default:
kvm_err("Unsupported value for TGRAN_2, giving up\n");
return -EINVAL;
}
kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
" (Reduced IPA size, limited VM/VMM compatibility)" : ""));
return 0;
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* fscrypt.h: declarations for per-file encryption
*
* Filesystems that implement per-file encryption must include this header
* file.
*
* Copyright (C) 2015, Google, Inc.
*
* Written by Michael Halcrow, 2015.
* Modified by Jaegeuk Kim, 2015.
*/
#ifndef _LINUX_FSCRYPT_H
#define _LINUX_FSCRYPT_H
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <uapi/linux/fscrypt.h>
/*
* The lengths of all file contents blocks must be divisible by this value.
* This is needed to ensure that all contents encryption modes will work, as
* some of the supported modes don't support arbitrarily byte-aligned messages.
*
* Since the needed alignment is 16 bytes, most filesystems will meet this
* requirement naturally, as typical block sizes are powers of 2. However, if a
* filesystem can generate arbitrarily byte-aligned block lengths (e.g., via
* compression), then it will need to pad to this alignment before encryption.
*/
#define FSCRYPT_CONTENTS_ALIGNMENT 16
union fscrypt_policy;
struct fscrypt_inode_info;
struct fs_parameter;
struct seq_file;
struct fscrypt_str {
unsigned char *name;
u32 len;
};
struct fscrypt_name {
const struct qstr *usr_fname;
struct fscrypt_str disk_name;
u32 hash;
u32 minor_hash;
struct fscrypt_str crypto_buf;
bool is_nokey_name;
};
#define FSTR_INIT(n, l) { .name = n, .len = l }
#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len)
#define fname_name(p) ((p)->disk_name.name)
#define fname_len(p) ((p)->disk_name.len)
/* Maximum value for the third parameter of fscrypt_operations.set_context(). */
#define FSCRYPT_SET_CONTEXT_MAX_SIZE 40
#ifdef CONFIG_FS_ENCRYPTION
/* Crypto operations for filesystems */
struct fscrypt_operations {
/*
* If set, then fs/crypto/ will allocate a global bounce page pool the
* first time an encryption key is set up for a file. The bounce page
* pool is required by the following functions:
*
* - fscrypt_encrypt_pagecache_blocks()
* - fscrypt_zeroout_range() for files not using inline crypto
*
* If the filesystem doesn't use those, it doesn't need to set this.
*/
unsigned int needs_bounce_pages : 1;
/*
* If set, then fs/crypto/ will allow the use of encryption settings
* that assume inode numbers fit in 32 bits (i.e.
* FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64}), provided that the other
* prerequisites for these settings are also met. This is only useful
* if the filesystem wants to support inline encryption hardware that is
* limited to 32-bit or 64-bit data unit numbers and where programming
* keyslots is very slow.
*/
unsigned int has_32bit_inodes : 1;
/*
* If set, then fs/crypto/ will allow users to select a crypto data unit
* size that is less than the filesystem block size. This is done via
* the log2_data_unit_size field of the fscrypt policy. This flag is
* not compatible with filesystems that encrypt variable-length blocks
* (i.e. blocks that aren't all equal to filesystem's block size), for
* example as a result of compression. It's also not compatible with
* the fscrypt_encrypt_block_inplace() and
* fscrypt_decrypt_block_inplace() functions.
*/
unsigned int supports_subblock_data_units : 1;
/*
* This field exists only for backwards compatibility reasons and should
* only be set by the filesystems that are setting it already. It
* contains the filesystem-specific key description prefix that is
* accepted for "logon" keys for v1 fscrypt policies. This
* functionality is deprecated in favor of the generic prefix
* "fscrypt:", which itself is deprecated in favor of the filesystem
* keyring ioctls such as FS_IOC_ADD_ENCRYPTION_KEY. Filesystems that
* are newly adding fscrypt support should not set this field.
*/
const char *legacy_key_prefix;
/*
* Get the fscrypt context of the given inode.
*
* @inode: the inode whose context to get
* @ctx: the buffer into which to get the context
* @len: length of the @ctx buffer in bytes
*
* Return: On success, returns the length of the context in bytes; this
* may be less than @len. On failure, returns -ENODATA if the
* inode doesn't have a context, -ERANGE if the context is
* longer than @len, or another -errno code.
*/
int (*get_context)(struct inode *inode, void *ctx, size_t len);
/*
* Set an fscrypt context on the given inode.
*
* @inode: the inode whose context to set. The inode won't already have
* an fscrypt context.
* @ctx: the context to set
* @len: length of @ctx in bytes (at most FSCRYPT_SET_CONTEXT_MAX_SIZE)
* @fs_data: If called from fscrypt_set_context(), this will be the
* value the filesystem passed to fscrypt_set_context().
* Otherwise (i.e. when called from
* FS_IOC_SET_ENCRYPTION_POLICY) this will be NULL.
*
* i_rwsem will be held for write.
*
* Return: 0 on success, -errno on failure.
*/
int (*set_context)(struct inode *inode, const void *ctx, size_t len,
void *fs_data);
/*
* Get the dummy fscrypt policy in use on the filesystem (if any).
*
* Filesystems only need to implement this function if they support the
* test_dummy_encryption mount option.
*
* Return: A pointer to the dummy fscrypt policy, if the filesystem is
* mounted with test_dummy_encryption; otherwise NULL.
*/
const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb);
/*
* Check whether a directory is empty. i_rwsem will be held for write.
*/
bool (*empty_dir)(struct inode *inode);
/*
* Check whether the filesystem's inode numbers and UUID are stable,
* meaning that they will never be changed even by offline operations
* such as filesystem shrinking and therefore can be used in the
* encryption without the possibility of files becoming unreadable.
*
* Filesystems only need to implement this function if they want to
* support the FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags. These
* flags are designed to work around the limitations of UFS and eMMC
* inline crypto hardware, and they shouldn't be used in scenarios where
* such hardware isn't being used.
*
* Leaving this NULL is equivalent to always returning false.
*/
bool (*has_stable_inodes)(struct super_block *sb);
/*
* Return an array of pointers to the block devices to which the
* filesystem may write encrypted file contents, NULL if the filesystem
* only has a single such block device, or an ERR_PTR() on error.
*
* On successful non-NULL return, *num_devs is set to the number of
* devices in the returned array. The caller must free the returned
* array using kfree().
*
* If the filesystem can use multiple block devices (other than block
* devices that aren't used for encrypted file contents, such as
* external journal devices), and wants to support inline encryption,
* then it must implement this function. Otherwise it's not needed.
*/
struct block_device **(*get_devices)(struct super_block *sb,
unsigned int *num_devs);
};
int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
struct dentry *dentry, unsigned int flags);
static inline struct fscrypt_inode_info *
fscrypt_get_inode_info(const struct inode *inode)
{
/*
* Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info().
* I.e., another task may publish ->i_crypt_info concurrently, executing
* a RELEASE barrier. We need to use smp_load_acquire() here to safely
* ACQUIRE the memory the other task published.
*/
return smp_load_acquire(&inode->i_crypt_info);
}
/**
* fscrypt_needs_contents_encryption() - check whether an inode needs
* contents encryption
* @inode: the inode to check
*
* Return: %true iff the inode is an encrypted regular file and the kernel was
* built with fscrypt support.
*
* If you need to know whether the encrypt bit is set even when the kernel was
* built without fscrypt support, you must use IS_ENCRYPTED() directly instead.
*/
static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
{
return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
}
/*
* When d_splice_alias() moves a directory's no-key alias to its
* plaintext alias as a result of the encryption key being added,
* DCACHE_NOKEY_NAME must be cleared and there might be an opportunity
* to disable d_revalidate. Note that we don't have to support the
* inverse operation because fscrypt doesn't allow no-key names to be
* the source or target of a rename().
*/
static inline void fscrypt_handle_d_move(struct dentry *dentry)
{
/*
* VFS calls fscrypt_handle_d_move even for non-fscrypt
* filesystems.
*/
if (dentry->d_flags & DCACHE_NOKEY_NAME) {
dentry->d_flags &= ~DCACHE_NOKEY_NAME;
/*
* Other filesystem features might be handling dentry
* revalidation, in which case it cannot be disabled.
*/
if (dentry->d_op->d_revalidate == fscrypt_d_revalidate)
dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
}
}
/**
* fscrypt_is_nokey_name() - test whether a dentry is a no-key name
* @dentry: the dentry to check
*
* This returns true if the dentry is a no-key dentry. A no-key dentry is a
* dentry that was created in an encrypted directory that hasn't had its
* encryption key added yet. Such dentries may be either positive or negative.
*
* When a filesystem is asked to create a new filename in an encrypted directory
* and the new filename's dentry is a no-key dentry, it must fail the operation
* with ENOKEY. This includes ->create(), ->mkdir(), ->mknod(), ->symlink(),
* ->rename(), and ->link(). (However, ->rename() and ->link() are already
* handled by fscrypt_prepare_rename() and fscrypt_prepare_link().)
*
* This is necessary because creating a filename requires the directory's
* encryption key, but just checking for the key on the directory inode during
* the final filesystem operation doesn't guarantee that the key was available
* during the preceding dentry lookup. And the key must have already been
* available during the dentry lookup in order for it to have been checked
* whether the filename already exists in the directory and for the new file's
* dentry not to be invalidated due to it incorrectly having the no-key flag.
*
* Return: %true if the dentry is a no-key name
*/
static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
{
return dentry->d_flags & DCACHE_NOKEY_NAME;
}
static inline void fscrypt_prepare_dentry(struct dentry *dentry,
bool is_nokey_name)
{
/*
* This code tries to only take ->d_lock when necessary to write
* to ->d_flags. We shouldn't be peeking on d_flags for
* DCACHE_OP_REVALIDATE unlocked, but in the unlikely case
* there is a race, the worst it can happen is that we fail to
* unset DCACHE_OP_REVALIDATE and pay the cost of an extra
* d_revalidate.
*/
if (is_nokey_name) {
spin_lock(&dentry->d_lock);
dentry->d_flags |= DCACHE_NOKEY_NAME;
spin_unlock(&dentry->d_lock);
} else if (dentry->d_flags & DCACHE_OP_REVALIDATE &&
dentry->d_op->d_revalidate == fscrypt_d_revalidate) {
/*
* Unencrypted dentries and encrypted dentries where the
* key is available are always valid from fscrypt
* perspective. Avoid the cost of calling
* fscrypt_d_revalidate unnecessarily.
*/
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
spin_unlock(&dentry->d_lock);
}
}
/* crypto.c */
void fscrypt_enqueue_decrypt_work(struct work_struct *);
struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
size_t len, size_t offs, gfp_t gfp_flags);
int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
unsigned int len, unsigned int offs,
u64 lblk_num, gfp_t gfp_flags);
int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len,
size_t offs);
int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page,
unsigned int len, unsigned int offs,
u64 lblk_num);
static inline bool fscrypt_is_bounce_page(struct page *page)
{
return page->mapping == NULL;
}
static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
{
return (struct page *)page_private(bounce_page);
}
static inline bool fscrypt_is_bounce_folio(struct folio *folio)
{
return folio->mapping == NULL;
}
static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
{
return bounce_folio->private;
}
void fscrypt_free_bounce_page(struct page *bounce_page);
/* policy.c */
int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg);
int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg);
int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg);
int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
int fscrypt_context_for_new_inode(void *ctx, struct inode *inode);
int fscrypt_set_context(struct inode *inode, void *fs_data);
struct fscrypt_dummy_policy {
const union fscrypt_policy *policy;
};
int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
struct fscrypt_dummy_policy *dummy_policy);
bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
const struct fscrypt_dummy_policy *p2);
void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
struct super_block *sb);
static inline bool
fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy)
{
return dummy_policy->policy != NULL;
}
static inline void
fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
{
kfree(dummy_policy->policy);
dummy_policy->policy = NULL;
}
/* keyring.c */
void fscrypt_destroy_keyring(struct super_block *sb);
int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg);
int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg);
int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
/* keysetup.c */
int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
bool *encrypt_ret);
void fscrypt_put_encryption_info(struct inode *inode);
void fscrypt_free_inode(struct inode *inode);
int fscrypt_drop_inode(struct inode *inode);
/* fname.c */
int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
u8 *out, unsigned int olen);
bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
u32 max_len, u32 *encrypted_len_ret);
int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname,
int lookup, struct fscrypt_name *fname);
static inline void fscrypt_free_filename(struct fscrypt_name *fname)
{
kfree(fname->crypto_buf.name);
}
int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
struct fscrypt_str *crypto_str);
void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str);
int fscrypt_fname_disk_to_usr(const struct inode *inode,
u32 hash, u32 minor_hash,
const struct fscrypt_str *iname,
struct fscrypt_str *oname);
bool fscrypt_match_name(const struct fscrypt_name *fname,
const u8 *de_name, u32 de_name_len);
u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
/* bio.c */
bool fscrypt_decrypt_bio(struct bio *bio);
int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
sector_t pblk, unsigned int len);
/* hooks.c */
int fscrypt_file_open(struct inode *inode, struct file *filp);
int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
struct dentry *dentry);
int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags);
int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
struct fscrypt_name *fname);
int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry);
int __fscrypt_prepare_readdir(struct inode *dir);
int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr);
int fscrypt_prepare_setflags(struct inode *inode,
unsigned int oldflags, unsigned int flags);
int fscrypt_prepare_symlink(struct inode *dir, const char *target,
unsigned int len, unsigned int max_len,
struct fscrypt_str *disk_link);
int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
unsigned int len, struct fscrypt_str *disk_link);
const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
unsigned int max_size,
struct delayed_call *done);
int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat);
static inline void fscrypt_set_ops(struct super_block *sb,
const struct fscrypt_operations *s_cop)
{
sb->s_cop = s_cop;
}
#else /* !CONFIG_FS_ENCRYPTION */
static inline struct fscrypt_inode_info *
fscrypt_get_inode_info(const struct inode *inode)
{
return NULL;
}
static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
{
return false;
}
static inline void fscrypt_handle_d_move(struct dentry *dentry)
{
}
static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
{
return false;
}
static inline void fscrypt_prepare_dentry(struct dentry *dentry,
bool is_nokey_name)
{
}
/* crypto.c */
static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
{
}
static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
size_t len, size_t offs, gfp_t gfp_flags)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int fscrypt_encrypt_block_inplace(const struct inode *inode,
struct page *page,
unsigned int len,
unsigned int offs, u64 lblk_num,
gfp_t gfp_flags)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_decrypt_pagecache_blocks(struct folio *folio,
size_t len, size_t offs)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_decrypt_block_inplace(const struct inode *inode,
struct page *page,
unsigned int len,
unsigned int offs, u64 lblk_num)
{
return -EOPNOTSUPP;
}
static inline bool fscrypt_is_bounce_page(struct page *page)
{
return false;
}
static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
{
WARN_ON_ONCE(1);
return ERR_PTR(-EINVAL);
}
static inline bool fscrypt_is_bounce_folio(struct folio *folio)
{
return false;
}
static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
{
WARN_ON_ONCE(1);
return ERR_PTR(-EINVAL);
}
static inline void fscrypt_free_bounce_page(struct page *bounce_page)
{
}
/* policy.c */
static inline int fscrypt_ioctl_set_policy(struct file *filp,
const void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_get_policy_ex(struct file *filp,
void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_has_permitted_context(struct inode *parent,
struct inode *child)
{
return 0;
}
static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
{
return -EOPNOTSUPP;
}
struct fscrypt_dummy_policy {
};
static inline int
fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
struct fscrypt_dummy_policy *dummy_policy)
{
return -EINVAL;
}
static inline bool
fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
const struct fscrypt_dummy_policy *p2)
{
return true;
}
static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
char sep,
struct super_block *sb)
{
}
static inline bool
fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy)
{
return false;
}
static inline void
fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
{
}
/* keyring.c */
static inline void fscrypt_destroy_keyring(struct super_block *sb)
{
}
static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_remove_key_all_users(struct file *filp,
void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_ioctl_get_key_status(struct file *filp,
void __user *arg)
{
return -EOPNOTSUPP;
}
/* keysetup.c */
static inline int fscrypt_prepare_new_inode(struct inode *dir,
struct inode *inode,
bool *encrypt_ret)
{
if (IS_ENCRYPTED(dir))
return -EOPNOTSUPP;
return 0;
}
static inline void fscrypt_put_encryption_info(struct inode *inode)
{
return;
}
static inline void fscrypt_free_inode(struct inode *inode)
{
}
static inline int fscrypt_drop_inode(struct inode *inode)
{
return 0;
}
/* fname.c */
static inline int fscrypt_setup_filename(struct inode *dir,
const struct qstr *iname,
int lookup, struct fscrypt_name *fname)
{
if (IS_ENCRYPTED(dir))
return -EOPNOTSUPP;
memset(fname, 0, sizeof(*fname));
fname->usr_fname = iname;
fname->disk_name.name = (unsigned char *)iname->name;
fname->disk_name.len = iname->len;
return 0;
}
static inline void fscrypt_free_filename(struct fscrypt_name *fname)
{
return;
}
static inline int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
struct fscrypt_str *crypto_str)
{
return -EOPNOTSUPP;
}
static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
{
return;
}
static inline int fscrypt_fname_disk_to_usr(const struct inode *inode,
u32 hash, u32 minor_hash,
const struct fscrypt_str *iname,
struct fscrypt_str *oname)
{
return -EOPNOTSUPP;
}
static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
const u8 *de_name, u32 de_name_len)
{
/* Encryption support disabled; use standard comparison */
if (de_name_len != fname->disk_name.len)
return false;
return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len);
}
static inline u64 fscrypt_fname_siphash(const struct inode *dir,
const struct qstr *name)
{
WARN_ON_ONCE(1);
return 0;
}
static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
struct dentry *dentry, unsigned int flags)
{
return 1;
}
/* bio.c */
static inline bool fscrypt_decrypt_bio(struct bio *bio)
{
return true;
}
static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
sector_t pblk, unsigned int len)
{
return -EOPNOTSUPP;
}
/* hooks.c */
static inline int fscrypt_file_open(struct inode *inode, struct file *filp)
{
if (IS_ENCRYPTED(inode))
return -EOPNOTSUPP;
return 0;
}
static inline int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
struct dentry *dentry)
{
return -EOPNOTSUPP;
}
static inline int __fscrypt_prepare_rename(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry,
unsigned int flags)
{
return -EOPNOTSUPP;
}
static inline int __fscrypt_prepare_lookup(struct inode *dir,
struct dentry *dentry,
struct fscrypt_name *fname)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_prepare_lookup_partial(struct inode *dir,
struct dentry *dentry)
{
return -EOPNOTSUPP;
}
static inline int __fscrypt_prepare_readdir(struct inode *dir)
{
return -EOPNOTSUPP;
}
static inline int __fscrypt_prepare_setattr(struct dentry *dentry,
struct iattr *attr)
{
return -EOPNOTSUPP;
}
static inline int fscrypt_prepare_setflags(struct inode *inode,
unsigned int oldflags,
unsigned int flags)
{
return 0;
}
static inline int fscrypt_prepare_symlink(struct inode *dir,
const char *target,
unsigned int len,
unsigned int max_len,
struct fscrypt_str *disk_link)
{
if (IS_ENCRYPTED(dir))
return -EOPNOTSUPP;
disk_link->name = (unsigned char *)target;
disk_link->len = len + 1;
if (disk_link->len > max_len)
return -ENAMETOOLONG;
return 0;
}
static inline int __fscrypt_encrypt_symlink(struct inode *inode,
const char *target,
unsigned int len,
struct fscrypt_str *disk_link)
{
return -EOPNOTSUPP;
}
static inline const char *fscrypt_get_symlink(struct inode *inode,
const void *caddr,
unsigned int max_size,
struct delayed_call *done)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int fscrypt_symlink_getattr(const struct path *path,
struct kstat *stat)
{
return -EOPNOTSUPP;
}
static inline void fscrypt_set_ops(struct super_block *sb,
const struct fscrypt_operations *s_cop)
{
}
#endif /* !CONFIG_FS_ENCRYPTION */
/* inline_crypt.c */
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode);
void fscrypt_set_bio_crypt_ctx(struct bio *bio,
const struct inode *inode, u64 first_lblk,
gfp_t gfp_mask);
void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio,
const struct buffer_head *first_bh,
gfp_t gfp_mask);
bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
u64 next_lblk);
bool fscrypt_mergeable_bio_bh(struct bio *bio,
const struct buffer_head *next_bh);
bool fscrypt_dio_supported(struct inode *inode);
u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks);
#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode)
{
return false;
}
static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio,
const struct inode *inode,
u64 first_lblk, gfp_t gfp_mask) { }
static inline void fscrypt_set_bio_crypt_ctx_bh(
struct bio *bio,
const struct buffer_head *first_bh,
gfp_t gfp_mask) { }
static inline bool fscrypt_mergeable_bio(struct bio *bio,
const struct inode *inode,
u64 next_lblk)
{
return true;
}
static inline bool fscrypt_mergeable_bio_bh(struct bio *bio,
const struct buffer_head *next_bh)
{
return true;
}
static inline bool fscrypt_dio_supported(struct inode *inode)
{
return !fscrypt_needs_contents_encryption(inode);
}
static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk,
u64 nr_blocks)
{
return nr_blocks;
}
#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
/**
* fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline
* encryption
* @inode: an inode. If encrypted, its key must be set up.
*
* Return: true if the inode requires file contents encryption and if the
* encryption should be done in the block layer via blk-crypto rather
* than in the filesystem layer.
*/
static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode)
{
return fscrypt_needs_contents_encryption(inode) &&
__fscrypt_inode_uses_inline_crypto(inode);
}
/**
* fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer
* encryption
* @inode: an inode. If encrypted, its key must be set up.
*
* Return: true if the inode requires file contents encryption and if the
* encryption should be done in the filesystem layer rather than in the
* block layer via blk-crypto.
*/
static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode)
{
return fscrypt_needs_contents_encryption(inode) &&
!__fscrypt_inode_uses_inline_crypto(inode);
}
/**
* fscrypt_has_encryption_key() - check whether an inode has had its key set up
* @inode: the inode to check
*
* Return: %true if the inode has had its encryption key set up, else %false.
*
* Usually this should be preceded by fscrypt_get_encryption_info() to try to
* set up the key first.
*/
static inline bool fscrypt_has_encryption_key(const struct inode *inode)
{
return fscrypt_get_inode_info(inode) != NULL;
}
/**
* fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted
* directory
* @old_dentry: an existing dentry for the inode being linked
* @dir: the target directory
* @dentry: negative dentry for the target filename
*
* A new link can only be added to an encrypted directory if the directory's
* encryption key is available --- since otherwise we'd have no way to encrypt
* the filename.
*
* We also verify that the link will not violate the constraint that all files
* in an encrypted directory tree use the same encryption policy.
*
* Return: 0 on success, -ENOKEY if the directory's encryption key is missing,
* -EXDEV if the link would result in an inconsistent encryption policy, or
* another -errno code.
*/
static inline int fscrypt_prepare_link(struct dentry *old_dentry,
struct inode *dir,
struct dentry *dentry)
{
if (IS_ENCRYPTED(dir))
return __fscrypt_prepare_link(d_inode(old_dentry), dir, dentry);
return 0;
}
/**
* fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted
* directories
* @old_dir: source directory
* @old_dentry: dentry for source file
* @new_dir: target directory
* @new_dentry: dentry for target location (may be negative unless exchanging)
* @flags: rename flags (we care at least about %RENAME_EXCHANGE)
*
* Prepare for ->rename() where the source and/or target directories may be
* encrypted. A new link can only be added to an encrypted directory if the
* directory's encryption key is available --- since otherwise we'd have no way
* to encrypt the filename. A rename to an existing name, on the other hand,
* *is* cryptographically possible without the key. However, we take the more
* conservative approach and just forbid all no-key renames.
*
* We also verify that the rename will not violate the constraint that all files
* in an encrypted directory tree use the same encryption policy.
*
* Return: 0 on success, -ENOKEY if an encryption key is missing, -EXDEV if the
* rename would cause inconsistent encryption policies, or another -errno code.
*/
static inline int fscrypt_prepare_rename(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry,
unsigned int flags)
{
if (IS_ENCRYPTED(old_dir) || IS_ENCRYPTED(new_dir))
return __fscrypt_prepare_rename(old_dir, old_dentry,
new_dir, new_dentry, flags);
return 0;
}
/**
* fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted
* directory
* @dir: directory being searched
* @dentry: filename being looked up
* @fname: (output) the name to use to search the on-disk directory
*
* Prepare for ->lookup() in a directory which may be encrypted by determining
* the name that will actually be used to search the directory on-disk. If the
* directory's encryption policy is supported by this kernel and its encryption
* key is available, then the lookup is assumed to be by plaintext name;
* otherwise, it is assumed to be by no-key name.
*
* This will set DCACHE_NOKEY_NAME on the dentry if the lookup is by no-key
* name. In this case the filesystem must assign the dentry a dentry_operations
* which contains fscrypt_d_revalidate (or contains a d_revalidate method that
* calls fscrypt_d_revalidate), so that the dentry will be invalidated if the
* directory's encryption key is later added.
*
* Return: 0 on success; -ENOENT if the directory's key is unavailable but the
* filename isn't a valid no-key name, so a negative dentry should be created;
* or another -errno code.
*/
static inline int fscrypt_prepare_lookup(struct inode *dir,
struct dentry *dentry,
struct fscrypt_name *fname)
{
if (IS_ENCRYPTED(dir))
return __fscrypt_prepare_lookup(dir, dentry, fname);
memset(fname, 0, sizeof(*fname));
fname->usr_fname = &dentry->d_name;
fname->disk_name.name = (unsigned char *)dentry->d_name.name;
fname->disk_name.len = dentry->d_name.len;
fscrypt_prepare_dentry(dentry, false);
return 0;
}
/**
* fscrypt_prepare_readdir() - prepare to read a possibly-encrypted directory
* @dir: the directory inode
*
* If the directory is encrypted and it doesn't already have its encryption key
* set up, try to set it up so that the filenames will be listed in plaintext
* form rather than in no-key form.
*
* Return: 0 on success; -errno on error. Note that the encryption key being
* unavailable is not considered an error. It is also not an error if
* the encryption policy is unsupported by this kernel; that is treated
* like the key being unavailable, so that files can still be deleted.
*/
static inline int fscrypt_prepare_readdir(struct inode *dir)
{
if (IS_ENCRYPTED(dir))
return __fscrypt_prepare_readdir(dir);
return 0;
}
/**
* fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's
* attributes
* @dentry: dentry through which the inode is being changed
* @attr: attributes to change
*
* Prepare for ->setattr() on a possibly-encrypted inode. On an encrypted file,
* most attribute changes are allowed even without the encryption key. However,
* without the encryption key we do have to forbid truncates. This is needed
* because the size being truncated to may not be a multiple of the filesystem
* block size, and in that case we'd have to decrypt the final block, zero the
* portion past i_size, and re-encrypt it. (We *could* allow truncating to a
* filesystem block boundary, but it's simpler to just forbid all truncates ---
* and we already forbid all other contents modifications without the key.)
*
* Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
* if a problem occurred while setting up the encryption key.
*/
static inline int fscrypt_prepare_setattr(struct dentry *dentry,
struct iattr *attr)
{
if (IS_ENCRYPTED(d_inode(dentry)))
return __fscrypt_prepare_setattr(dentry, attr);
return 0;
}
/**
* fscrypt_encrypt_symlink() - encrypt the symlink target if needed
* @inode: symlink inode
* @target: plaintext symlink target
* @len: length of @target excluding null terminator
* @disk_link: (in/out) the on-disk symlink target being prepared
*
* If the symlink target needs to be encrypted, then this function encrypts it
* into @disk_link->name. fscrypt_prepare_symlink() must have been called
* previously to compute @disk_link->len. If the filesystem did not allocate a
* buffer for @disk_link->name after calling fscrypt_prepare_link(), then one
* will be kmalloc()'ed and the filesystem will be responsible for freeing it.
*
* Return: 0 on success, -errno on failure
*/
static inline int fscrypt_encrypt_symlink(struct inode *inode,
const char *target,
unsigned int len,
struct fscrypt_str *disk_link)
{
if (IS_ENCRYPTED(inode))
return __fscrypt_encrypt_symlink(inode, target, len, disk_link);
return 0;
}
/* If *pagep is a bounce page, free it and set *pagep to the pagecache page */
static inline void fscrypt_finalize_bounce_page(struct page **pagep)
{
struct page *page = *pagep;
if (fscrypt_is_bounce_page(page)) {
*pagep = fscrypt_pagecache_page(page);
fscrypt_free_bounce_page(page);
}
}
#endif /* _LINUX_FSCRYPT_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/mmap.c
*
* Written by obz.
*
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/profile.h>
#include <linux/export.h>
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/mmdebug.h>
#include <linux/perf_event.h>
#include <linux/audit.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/userfaultfd_k.h>
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>
#include <linux/ksm.h>
#include <linux/memfd.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#define CREATE_TRACE_POINTS
#include <trace/events/mmap.h>
#include "internal.h"
#ifndef arch_mmap_check
#define arch_mmap_check(addr, len, flags) (0)
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX;
int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
#endif
static bool ignore_rlimit_data;
core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
/* Update vma->vm_page_prot to reflect vma->vm_flags. */
void vma_set_page_prot(struct vm_area_struct *vma)
{
unsigned long vm_flags = vma->vm_flags;
pgprot_t vm_page_prot;
vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED;
vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
}
/* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
}
/*
* check_brk_limits() - Use platform specific check of range & verify mlock
* limits.
* @addr: The address to check
* @len: The size of increase.
*
* Return: 0 on success.
*/
static int check_brk_limits(unsigned long addr, unsigned long len)
{
unsigned long mapped_addr;
mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
if (IS_ERR_VALUE(mapped_addr))
return mapped_addr;
return mlock_future_ok(current->mm, current->mm->def_flags, len)
? 0 : -EAGAIN;
}
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
unsigned long newbrk, oldbrk, origbrk;
struct mm_struct *mm = current->mm;
struct vm_area_struct *brkvma, *next = NULL;
unsigned long min_brk;
bool populate = false;
LIST_HEAD(uf);
struct vma_iterator vmi;
if (mmap_write_lock_killable(mm))
return -EINTR;
origbrk = mm->brk;
#ifdef CONFIG_COMPAT_BRK
/*
* CONFIG_COMPAT_BRK can still be overridden by setting
* randomize_va_space to 2, which will still cause mm->start_brk
* to be arbitrarily shifted
*/
if (current->brk_randomized)
min_brk = mm->start_brk;
else
min_brk = mm->end_data;
#else
min_brk = mm->start_brk;
#endif
if (brk < min_brk)
goto out;
/*
* Check against rlimit here. If this check is done later after the test
* of oldbrk with newbrk then it can escape the test and let the data
* segment grow beyond its set limit the in case where the limit is
* not page aligned -Ram Gupta
*/
if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
mm->end_data, mm->start_data))
goto out;
newbrk = PAGE_ALIGN(brk);
oldbrk = PAGE_ALIGN(mm->brk);
if (oldbrk == newbrk) {
mm->brk = brk;
goto success;
}
/* Always allow shrinking brk. */
if (brk <= mm->brk) {
/* Search one past newbrk */
vma_iter_init(&vmi, mm, newbrk);
brkvma = vma_find(&vmi, oldbrk);
if (!brkvma || brkvma->vm_start >= oldbrk)
goto out; /* mapping intersects with an existing non-brk vma. */
/*
* mm->brk must be protected by write mmap_lock.
* do_vmi_align_munmap() will drop the lock on success, so
* update it before calling do_vma_munmap().
*/
mm->brk = brk;
if (do_vmi_align_munmap(&vmi, brkvma, mm, newbrk, oldbrk, &uf,
/* unlock = */ true))
goto out;
goto success_unlocked;
}
if (check_brk_limits(oldbrk, newbrk - oldbrk))
goto out;
/*
* Only check if the next VMA is within the stack_guard_gap of the
* expansion area
*/
vma_iter_init(&vmi, mm, oldbrk);
next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap);
if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
goto out;
brkvma = vma_prev_limit(&vmi, mm->start_brk);
/* Ok, looks good - let it rip. */
if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0)
goto out;
mm->brk = brk;
if (mm->def_flags & VM_LOCKED)
populate = true;
success:
mmap_write_unlock(mm);
success_unlocked:
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(oldbrk, newbrk - oldbrk);
return brk;
out:
mm->brk = origbrk;
mmap_write_unlock(mm);
return origbrk;
}
/*
* If a hint addr is less than mmap_min_addr change hint to be as
* low as possible but still greater than mmap_min_addr
*/
static inline unsigned long round_hint_to_min(unsigned long hint)
{
hint &= PAGE_MASK;
if (((void *)hint != NULL) &&
(hint < mmap_min_addr))
return PAGE_ALIGN(mmap_min_addr);
return hint;
}
bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
unsigned long bytes)
{
unsigned long locked_pages, limit_pages;
if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
return true;
locked_pages = bytes >> PAGE_SHIFT;
locked_pages += mm->locked_vm;
limit_pages = rlimit(RLIMIT_MEMLOCK);
limit_pages >>= PAGE_SHIFT;
return locked_pages <= limit_pages;
}
static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
{
if (S_ISREG(inode->i_mode))
return MAX_LFS_FILESIZE;
if (S_ISBLK(inode->i_mode))
return MAX_LFS_FILESIZE;
if (S_ISSOCK(inode->i_mode))
return MAX_LFS_FILESIZE;
/* Special "we do even unsigned file positions" case */
if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET)
return 0;
/* Yes, random drivers might want more. But I'm tired of buggy drivers */
return ULONG_MAX;
}
static inline bool file_mmap_ok(struct file *file, struct inode *inode,
unsigned long pgoff, unsigned long len)
{ u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize)
return false;
maxsize -= len;
if (pgoff > maxsize >> PAGE_SHIFT)
return false;
return true;
}
/**
* do_mmap() - Perform a userland memory mapping into the current process
* address space of length @len with protection bits @prot, mmap flags @flags
* (from which VMA flags will be inferred), and any additional VMA flags to
* apply @vm_flags. If this is a file-backed mapping then the file is specified
* in @file and page offset into the file via @pgoff.
*
* This function does not perform security checks on the file and assumes, if
* @uf is non-NULL, the caller has provided a list head to track unmap events
* for userfaultfd @uf.
*
* It also simply indicates whether memory population is required by setting
* @populate, which must be non-NULL, expecting the caller to actually perform
* this task itself if appropriate.
*
* This function will invoke architecture-specific (and if provided and
* relevant, file system-specific) logic to determine the most appropriate
* unmapped area in which to place the mapping if not MAP_FIXED.
*
* Callers which require userland mmap() behaviour should invoke vm_mmap(),
* which is also exported for module use.
*
* Those which require this behaviour less security checks, userfaultfd and
* populate behaviour, and who handle the mmap write lock themselves, should
* call this function.
*
* Note that the returned address may reside within a merged VMA if an
* appropriate merge were to take place, so it doesn't necessarily specify the
* start of a VMA, rather only the start of a valid mapped range of length
* @len bytes, rounded down to the nearest page size.
*
* The caller must write-lock current->mm->mmap_lock.
*
* @file: An optional struct file pointer describing the file which is to be
* mapped, if a file-backed mapping.
* @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the
* address at which to perform this mapping. See mmap (2) for details. Must be
* page-aligned.
* @len: The length of the mapping. Will be page-aligned and must be at least 1
* page in size.
* @prot: Protection bits describing access required to the mapping. See mmap
* (2) for details.
* @flags: Flags specifying how the mapping should be performed, see mmap (2)
* for details.
* @vm_flags: VMA flags which should be set by default, or 0 otherwise.
* @pgoff: Page offset into the @file if file-backed, should be 0 otherwise.
* @populate: A pointer to a value which will be set to 0 if no population of
* the range is required, or the number of bytes to populate if it is. Must be
* non-NULL. See mmap (2) for details as to under what circumstances population
* of the range occurs.
* @uf: An optional pointer to a list head to track userfaultfd unmap events
* should unmapping events arise. If provided, it is up to the caller to manage
* this.
*
* Returns: Either an error, or the address at which the requested mapping has
* been performed.
*/
unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flags, vm_flags_t vm_flags,
unsigned long pgoff, unsigned long *populate,
struct list_head *uf)
{
struct mm_struct *mm = current->mm;
int pkey = 0;
*populate = 0;
mmap_assert_write_locked(mm); if (!len)
return -EINVAL;
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
*
* (the exception is when the underlying filesystem is noexec
* mounted, in which case we don't add PROT_EXEC.)
*/
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path)))
prot |= PROT_EXEC;
/* force arch specific MAP_FIXED handling in get_unmapped_area */
if (flags & MAP_FIXED_NOREPLACE)
flags |= MAP_FIXED;
if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr);
/* Careful about overflows.. */
len = PAGE_ALIGN(len);
if (!len)
return -ENOMEM;
/* offset overflow? */
if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
return -EOVERFLOW;
/* Too many mappings? */
if (mm->map_count > sysctl_max_map_count)
return -ENOMEM;
/*
* addr is returned from get_unmapped_area,
* There are two cases:
* 1> MAP_FIXED == false
* unallocated memory, no need to check sealing.
* 1> MAP_FIXED == true
* sealing is checked inside mmap_region when
* do_vmi_munmap is called.
*/
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(mm);
if (pkey < 0)
pkey = 0;
}
/* Do simple checking here so the lower-level routines won't have
* to. we assume access permissions have been handled by the open
* of the memory object, so we don't do any here.
*/
vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) |
mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
/* Obtain the address to map to. we verify (or select) it and ensure
* that it represents a valid section of the address space.
*/
addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags);
if (IS_ERR_VALUE(addr))
return addr;
if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len))
return -EEXIST;
}
if (flags & MAP_LOCKED) if (!can_do_mlock())
return -EPERM;
if (!mlock_future_ok(mm, vm_flags, len))
return -EAGAIN;
if (file) {
struct inode *inode = file_inode(file);
unsigned long flags_mask;
int err;
if (!file_mmap_ok(file, inode, pgoff, len))
return -EOVERFLOW;
flags_mask = LEGACY_MAP_MASK;
if (file->f_op->fop_flags & FOP_MMAP_SYNC)
flags_mask |= MAP_SYNC;
switch (flags & MAP_TYPE) {
case MAP_SHARED:
/*
* Force use of MAP_SHARED_VALIDATE with non-legacy
* flags. E.g. MAP_SYNC is dangerous to use with
* MAP_SHARED as you don't know which consistency model
* you will get. We silently ignore unsupported flags
* with MAP_SHARED to preserve backward compatibility.
*/
flags &= LEGACY_MAP_MASK;
fallthrough;
case MAP_SHARED_VALIDATE:
if (flags & ~flags_mask)
return -EOPNOTSUPP;
if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE))
return -EACCES;
if (IS_SWAPFILE(file->f_mapping->host))
return -ETXTBSY;
}
/*
* Make sure we don't allow writing to an append-only
* file..
*/
if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
return -EACCES;
vm_flags |= VM_SHARED | VM_MAYSHARE;
if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
fallthrough;
case MAP_PRIVATE:
if (!(file->f_mode & FMODE_READ))
return -EACCES;
if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC)
return -EPERM;
vm_flags &= ~VM_MAYEXEC;
}
if (!file->f_op->mmap)
return -ENODEV;
if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
return -EINVAL;
break;
default:
return -EINVAL;
}
/*
* Check to see if we are violating any seals and update VMA
* flags if necessary to avoid future seal violations.
*/
err = memfd_check_seals_mmap(file, &vm_flags);
if (err)
return (unsigned long)err;
} else {
switch (flags & MAP_TYPE) {
case MAP_SHARED:
if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
return -EINVAL;
/*
* Ignore pgoff.
*/
pgoff = 0;
vm_flags |= VM_SHARED | VM_MAYSHARE;
break;
case MAP_DROPPABLE:
if (VM_DROPPABLE == VM_NONE)
return -ENOTSUPP;
/*
* A locked or stack area makes no sense to be droppable.
*
* Also, since droppable pages can just go away at any time
* it makes no sense to copy them on fork or dump them.
*
* And don't attempt to combine with hugetlb for now.
*/
if (flags & (MAP_LOCKED | MAP_HUGETLB))
return -EINVAL;
if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP))
return -EINVAL;
vm_flags |= VM_DROPPABLE;
/*
* If the pages can be dropped, then it doesn't make
* sense to reserve them.
*/
vm_flags |= VM_NORESERVE;
/*
* Likewise, they're volatile enough that they
* shouldn't survive forks or coredumps.
*/
vm_flags |= VM_WIPEONFORK | VM_DONTDUMP;
fallthrough;
case MAP_PRIVATE:
/*
* Set pgoff according to addr for anon_vma.
*/
pgoff = addr >> PAGE_SHIFT;
break;
default:
return -EINVAL;
}
}
/*
* Set 'VM_NORESERVE' if we should not account for the
* memory use of this mapping.
*/
if (flags & MAP_NORESERVE) {
/* We honor MAP_NORESERVE if allowed to overcommit */
if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE;
/* hugetlb applies strict overcommit unless MAP_NORESERVE */
if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE;
}
addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) ||
(flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
*populate = len;
return addr;
}
unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long pgoff)
{
struct file *file = NULL;
unsigned long retval;
if (!(flags & MAP_ANONYMOUS)) {
audit_mmap_fd(fd, flags);
file = fget(fd);
if (!file)
return -EBADF;
if (is_file_hugepages(file)) {
len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) {
retval = -EINVAL;
goto out_fput;
}
} else if (flags & MAP_HUGETLB) {
struct hstate *hs;
hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs)
return -EINVAL;
len = ALIGN(len, huge_page_size(hs));
/*
* VM_NORESERVE is used because the reservations will be
* taken when vm_ops->mmap() is called
*/
file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
VM_NORESERVE,
HUGETLB_ANONHUGE_INODE,
(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
if (IS_ERR(file))
return PTR_ERR(file);
}
retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
out_fput:
if (file)
fput(file);
return retval;
}
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, pgoff)
{
return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
}
#ifdef __ARCH_WANT_SYS_OLD_MMAP
struct mmap_arg_struct {
unsigned long addr;
unsigned long len;
unsigned long prot;
unsigned long flags;
unsigned long fd;
unsigned long offset;
};
SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
{
struct mmap_arg_struct a;
if (copy_from_user(&a, arg, sizeof(a)))
return -EFAULT;
if (offset_in_page(a.offset))
return -EINVAL;
return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
a.offset >> PAGE_SHIFT);
}
#endif /* __ARCH_WANT_SYS_OLD_MMAP */
/*
* Determine if the allocation needs to ensure that there is no
* existing mapping within it's guard gaps, for use as start_gap.
*/
static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
{
if (vm_flags & VM_SHADOW_STACK)
return PAGE_SIZE;
return 0;
}
/*
* Search for an unmapped address range.
*
* We are looking for a range that:
* - does not intersect with any VMA;
* - is contained within the [low_limit, high_limit) interval;
* - is at least the desired size.
* - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
*/
unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
{
unsigned long addr;
if (info->flags & VM_UNMAPPED_AREA_TOPDOWN)
addr = unmapped_area_topdown(info);
else
addr = unmapped_area(info);
trace_vm_unmapped_area(addr, info);
return addr;
}
/* Get an address range which is currently unmapped.
* For shmat() with addr=0.
*
* Ugly calling convention alert:
* Return value with the low bits set means error value,
* ie
* if (ret & ~PAGE_MASK)
* error = ret;
*
* This function "knows" that -ENOMEM has the bits set.
*/
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
struct vm_unmapped_area_info info = {};
const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
if (len > mmap_end - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
return addr;
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma_prev(mm, addr, &prev);
if (mmap_end - len >= addr && addr >= mmap_min_addr &&
(!vma || addr + len <= vm_start_gap(vma)) &&
(!prev || addr >= vm_end_gap(prev)))
return addr;
}
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = mmap_end;
info.start_gap = stack_guard_placement(vm_flags);
if (filp && is_file_hugepages(filp))
info.align_mask = huge_page_mask_align(filp);
return vm_unmapped_area(&info);
}
#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags)
{
return generic_get_unmapped_area(filp, addr, len, pgoff, flags,
vm_flags);
}
#endif
/*
* This mmap-allocator allocates new areas top-down from below the
* stack's low limit (the base):
*/
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags)
{
struct vm_area_struct *vma, *prev;
struct mm_struct *mm = current->mm;
struct vm_unmapped_area_info info = {};
const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
/* requested length too big for entire address space */
if (len > mmap_end - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
return addr;
/* requesting a specific address */
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev)))
return addr;
}
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = arch_get_mmap_base(addr, mm->mmap_base);
info.start_gap = stack_guard_placement(vm_flags);
if (filp && is_file_hugepages(filp)) info.align_mask = huge_page_mask_align(filp);
addr = vm_unmapped_area(&info);
/*
* A failed mmap() very likely causes application failure,
* so fall back to the bottom-up function here. This scenario
* can happen with large stack limits and large mmap()
* allocations.
*/
if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = mmap_end;
addr = vm_unmapped_area(&info);
}
return addr;
}
#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags)
{
return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags,
vm_flags);
}
#endif
unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags,
vm_flags_t vm_flags)
{
if (test_bit(MMF_TOPDOWN, &mm->flags))
return arch_get_unmapped_area_topdown(filp, addr, len, pgoff,
flags, vm_flags);
return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
}
unsigned long
__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
{
unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long)
= NULL;
unsigned long error = arch_mmap_check(addr, len, flags);
if (error)
return error;
/* Careful about overflows.. */
if (len > TASK_SIZE)
return -ENOMEM;
if (file) {
if (file->f_op->get_unmapped_area)
get_area = file->f_op->get_unmapped_area;
} else if (flags & MAP_SHARED) {
/*
* mmap_region() will call shmem_zero_setup() to create a file,
* so use shmem's get_unmapped_area in case it can be huge.
*/
get_area = shmem_get_unmapped_area;
}
/* Always treat pgoff as zero for anonymous memory. */
if (!file)
pgoff = 0;
if (get_area) {
addr = get_area(file, addr, len, pgoff, flags);
} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file
&& !addr /* no hint */
&& IS_ALIGNED(len, PMD_SIZE)) {
/* Ensures that larger anonymous mappings are THP aligned. */
addr = thp_get_unmapped_area_vmflags(file, addr, len,
pgoff, flags, vm_flags);
} else {
addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len,
pgoff, flags, vm_flags);
}
if (IS_ERR_VALUE(addr))
return addr;
if (addr > TASK_SIZE - len)
return -ENOMEM;
if (offset_in_page(addr))
return -EINVAL;
error = security_mmap_addr(addr);
return error ? error : addr;
}
unsigned long
mm_get_unmapped_area(struct mm_struct *mm, struct file *file,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
if (test_bit(MMF_TOPDOWN, &mm->flags))
return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags, 0); return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0);
}
EXPORT_SYMBOL(mm_get_unmapped_area);
/**
* find_vma_intersection() - Look up the first VMA which intersects the interval
* @mm: The process address space.
* @start_addr: The inclusive start user address.
* @end_addr: The exclusive end user address.
*
* Returns: The first VMA within the provided range, %NULL otherwise. Assumes
* start_addr < end_addr.
*/
struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
unsigned long start_addr,
unsigned long end_addr)
{
unsigned long index = start_addr;
mmap_assert_locked(mm);
return mt_find(&mm->mm_mt, &index, end_addr - 1);
}
EXPORT_SYMBOL(find_vma_intersection);
/**
* find_vma() - Find the VMA for a given address, or the next VMA.
* @mm: The mm_struct to check
* @addr: The address
*
* Returns: The VMA associated with addr, or the next VMA.
* May return %NULL in the case of no VMA at addr or above.
*/
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
unsigned long index = addr;
mmap_assert_locked(mm);
return mt_find(&mm->mm_mt, &index, ULONG_MAX);
}
EXPORT_SYMBOL(find_vma);
/**
* find_vma_prev() - Find the VMA for a given address, or the next vma and
* set %pprev to the previous VMA, if any.
* @mm: The mm_struct to check
* @addr: The address
* @pprev: The pointer to set to the previous VMA
*
* Note that RCU lock is missing here since the external mmap_lock() is used
* instead.
*
* Returns: The VMA associated with @addr, or the next vma.
* May return %NULL in the case of no vma at addr or above.
*/
struct vm_area_struct *
find_vma_prev(struct mm_struct *mm, unsigned long addr,
struct vm_area_struct **pprev)
{
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, addr);
vma = vma_iter_load(&vmi);
*pprev = vma_prev(&vmi);
if (!vma) vma = vma_next(&vmi);
return vma;
}
/* enforced gap between the expanding stack and other mappings. */
unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
static int __init cmdline_parse_stack_guard_gap(char *p)
{
unsigned long val;
char *endptr;
val = simple_strtoul(p, &endptr, 10);
if (!*endptr)
stack_guard_gap = val << PAGE_SHIFT;
return 1;
}
__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
#ifdef CONFIG_STACK_GROWSUP
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
return expand_upwards(vma, address);
}
struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma, *prev;
addr &= PAGE_MASK;
vma = find_vma_prev(mm, addr, &prev);
if (vma && (vma->vm_start <= addr))
return vma;
if (!prev)
return NULL;
if (expand_stack_locked(prev, addr))
return NULL;
if (prev->vm_flags & VM_LOCKED)
populate_vma_page_range(prev, addr, prev->vm_end, NULL);
return prev;
}
#else
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
return expand_downwards(vma, address);
}
struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma;
unsigned long start;
addr &= PAGE_MASK;
vma = find_vma(mm, addr);
if (!vma)
return NULL;
if (vma->vm_start <= addr)
return vma;
start = vma->vm_start;
if (expand_stack_locked(vma, addr))
return NULL;
if (vma->vm_flags & VM_LOCKED)
populate_vma_page_range(vma, addr, start, NULL);
return vma;
}
#endif
#if defined(CONFIG_STACK_GROWSUP)
#define vma_expand_up(vma,addr) expand_upwards(vma, addr)
#define vma_expand_down(vma, addr) (-EFAULT)
#else
#define vma_expand_up(vma,addr) (-EFAULT)
#define vma_expand_down(vma, addr) expand_downwards(vma, addr)
#endif
/*
* expand_stack(): legacy interface for page faulting. Don't use unless
* you have to.
*
* This is called with the mm locked for reading, drops the lock, takes
* the lock for writing, tries to look up a vma again, expands it if
* necessary, and downgrades the lock to reading again.
*
* If no vma is found or it can't be expanded, it returns NULL and has
* dropped the lock.
*/
struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma, *prev;
mmap_read_unlock(mm);
if (mmap_write_lock_killable(mm))
return NULL;
vma = find_vma_prev(mm, addr, &prev);
if (vma && vma->vm_start <= addr)
goto success;
if (prev && !vma_expand_up(prev, addr)) {
vma = prev;
goto success;
}
if (vma && !vma_expand_down(vma, addr))
goto success;
mmap_write_unlock(mm);
return NULL;
success:
mmap_write_downgrade(mm);
return vma;
}
/* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls.
* @mm: The mm_struct
* @start: The start address to munmap
* @len: The length to be munmapped.
* @uf: The userfaultfd list_head
*
* Return: 0 on success, error otherwise.
*/
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
struct list_head *uf)
{
VMA_ITERATOR(vmi, mm, start);
return do_vmi_munmap(&vmi, mm, start, len, uf, false);
}
int vm_munmap(unsigned long start, size_t len)
{
return __vm_munmap(start, len, false);
}
EXPORT_SYMBOL(vm_munmap);
SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
{
addr = untagged_addr(addr);
return __vm_munmap(addr, len, true);
}
/*
* Emulation of deprecated remap_file_pages() syscall.
*/
SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long populate = 0;
unsigned long ret = -EINVAL;
struct file *file;
vm_flags_t vm_flags;
pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
current->comm, current->pid);
if (prot)
return ret;
start = start & PAGE_MASK;
size = size & PAGE_MASK;
if (start + size <= start)
return ret;
/* Does pgoff wrap? */
if (pgoff + (size >> PAGE_SHIFT) < pgoff)
return ret;
if (mmap_read_lock_killable(mm))
return -EINTR;
/*
* Look up VMA under read lock first so we can perform the security
* without holding locks (which can be problematic). We reacquire a
* write lock later and check nothing changed underneath us.
*/
vma = vma_lookup(mm, start);
if (!vma || !(vma->vm_flags & VM_SHARED)) {
mmap_read_unlock(mm);
return -EINVAL;
}
prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
flags &= MAP_NONBLOCK;
flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
if (vma->vm_flags & VM_LOCKED)
flags |= MAP_LOCKED;
/* Save vm_flags used to calculate prot and flags, and recheck later. */
vm_flags = vma->vm_flags;
file = get_file(vma->vm_file);
mmap_read_unlock(mm);
/* Call outside mmap_lock to be consistent with other callers. */
ret = security_mmap_file(file, prot, flags);
if (ret) {
fput(file);
return ret;
}
ret = -EINVAL;
/* OK security check passed, take write lock + let it rip. */
if (mmap_write_lock_killable(mm)) {
fput(file);
return -EINTR;
}
vma = vma_lookup(mm, start);
if (!vma)
goto out;
/* Make sure things didn't change under us. */
if (vma->vm_flags != vm_flags)
goto out;
if (vma->vm_file != file)
goto out;
if (start + size > vma->vm_end) {
VMA_ITERATOR(vmi, mm, vma->vm_end);
struct vm_area_struct *next, *prev = vma;
for_each_vma_range(vmi, next, start + size) {
/* hole between vmas ? */
if (next->vm_start != prev->vm_end)
goto out;
if (next->vm_file != vma->vm_file)
goto out;
if (next->vm_flags != vma->vm_flags)
goto out;
if (start + size <= next->vm_end)
break;
prev = next;
}
if (!next)
goto out;
}
ret = do_mmap(vma->vm_file, start, size,
prot, flags, 0, pgoff, &populate, NULL);
out:
mmap_write_unlock(mm);
fput(file);
if (populate)
mm_populate(ret, populate);
if (!IS_ERR_VALUE(ret))
ret = 0;
return ret;
}
int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = NULL;
unsigned long len;
int ret;
bool populate;
LIST_HEAD(uf);
VMA_ITERATOR(vmi, mm, addr);
len = PAGE_ALIGN(request);
if (len < request)
return -ENOMEM;
if (!len)
return 0;
/* Until we need other flags, refuse anything except VM_EXEC. */
if ((flags & (~VM_EXEC)) != 0)
return -EINVAL;
if (mmap_write_lock_killable(mm))
return -EINTR;
ret = check_brk_limits(addr, len);
if (ret)
goto limits_failed;
ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0);
if (ret)
goto munmap_failed;
vma = vma_prev(&vmi);
ret = do_brk_flags(&vmi, vma, addr, len, flags);
populate = ((mm->def_flags & VM_LOCKED) != 0);
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate && !ret)
mm_populate(addr, len);
return ret;
munmap_failed:
limits_failed:
mmap_write_unlock(mm);
return ret;
}
EXPORT_SYMBOL(vm_brk_flags);
/* Release all mmaps. */
void exit_mmap(struct mm_struct *mm)
{
struct mmu_gather tlb;
struct vm_area_struct *vma;
unsigned long nr_accounted = 0;
VMA_ITERATOR(vmi, mm, 0);
int count = 0;
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
mmap_read_lock(mm);
arch_exit_mmap(mm);
vma = vma_next(&vmi);
if (!vma || unlikely(xa_is_zero(vma))) {
/* Can happen if dup_mmap() received an OOM */
mmap_read_unlock(mm);
mmap_write_lock(mm);
goto destroy;
}
flush_cache_mm(mm);
tlb_gather_mmu_fullmm(&tlb, mm);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX, false);
mmap_read_unlock(mm);
/*
* Set MMF_OOM_SKIP to hide this task from the oom killer/reaper
* because the memory has been already freed.
*/
set_bit(MMF_OOM_SKIP, &mm->flags);
mmap_write_lock(mm);
mt_clear_in_rcu(&mm->mm_mt);
vma_iter_set(&vmi, vma->vm_end);
free_pgtables(&tlb, &vmi.mas, vma, FIRST_USER_ADDRESS,
USER_PGTABLES_CEILING, true);
tlb_finish_mmu(&tlb);
/*
* Walk the list again, actually closing and freeing it, with preemption
* enabled, without holding any MM locks besides the unreachable
* mmap_write_lock.
*/
vma_iter_set(&vmi, vma->vm_end);
do {
if (vma->vm_flags & VM_ACCOUNT)
nr_accounted += vma_pages(vma);
vma_mark_detached(vma);
remove_vma(vma);
count++;
cond_resched();
vma = vma_next(&vmi);
} while (vma && likely(!xa_is_zero(vma)));
BUG_ON(count != mm->map_count);
trace_exit_mmap(mm);
destroy:
__mt_destroy(&mm->mm_mt);
mmap_write_unlock(mm);
vm_unacct_memory(nr_accounted);
}
/* Insert vm structure into process list sorted by address
* and into the inode's i_mmap tree. If vm_file is non-NULL
* then i_mmap_rwsem is taken here.
*/
int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
unsigned long charged = vma_pages(vma);
if (find_vma_intersection(mm, vma->vm_start, vma->vm_end))
return -ENOMEM;
if ((vma->vm_flags & VM_ACCOUNT) &&
security_vm_enough_memory_mm(mm, charged))
return -ENOMEM;
/*
* The vm_pgoff of a purely anonymous vma should be irrelevant
* until its first write fault, when page's anon_vma and index
* are set. But now set the vm_pgoff it will almost certainly
* end up with (unless mremap moves it elsewhere before that
* first wfault), so /proc/pid/maps tells a consistent story.
*
* By setting it to reflect the virtual start address of the
* vma, merges and splits can happen in a seamless way, just
* using the existing file pgoff checks and manipulations.
* Similarly in do_mmap and in do_brk_flags.
*/
if (vma_is_anonymous(vma)) {
BUG_ON(vma->anon_vma);
vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
}
if (vma_link(mm, vma)) {
if (vma->vm_flags & VM_ACCOUNT)
vm_unacct_memory(charged);
return -ENOMEM;
}
return 0;
}
/*
* Return true if the calling process may expand its vm space by the passed
* number of pages
*/
bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
{ if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
return false;
if (is_data_mapping(flags) &&
mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
/* Workaround for Valgrind */
if (rlimit(RLIMIT_DATA) == 0 &&
mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT)
return true;
pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n",
current->comm, current->pid,
(mm->data_vm + npages) << PAGE_SHIFT,
rlimit(RLIMIT_DATA),
ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data");
if (!ignore_rlimit_data)
return false;
}
return true;
}
void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
{
WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages);
if (is_exec_mapping(flags))
mm->exec_vm += npages;
else if (is_stack_mapping(flags))
mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages;
}
static vm_fault_t special_mapping_fault(struct vm_fault *vmf);
/*
* Close hook, called for unmap() and on the old vma for mremap().
*
* Having a close hook prevents vma merging regardless of flags.
*/
static void special_mapping_close(struct vm_area_struct *vma)
{
const struct vm_special_mapping *sm = vma->vm_private_data;
if (sm->close)
sm->close(sm, vma);
}
static const char *special_mapping_name(struct vm_area_struct *vma)
{
return ((struct vm_special_mapping *)vma->vm_private_data)->name;
}
static int special_mapping_mremap(struct vm_area_struct *new_vma)
{
struct vm_special_mapping *sm = new_vma->vm_private_data;
if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
return -EFAULT;
if (sm->mremap)
return sm->mremap(sm, new_vma);
return 0;
}
static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr)
{
/*
* Forbid splitting special mappings - kernel has expectations over
* the number of pages in mapping. Together with VM_DONTEXPAND
* the size of vma should stay the same over the special mapping's
* lifetime.
*/
return -EINVAL;
}
static const struct vm_operations_struct special_mapping_vmops = {
.close = special_mapping_close,
.fault = special_mapping_fault,
.mremap = special_mapping_mremap,
.name = special_mapping_name,
/* vDSO code relies that VVAR can't be accessed remotely */
.access = NULL,
.may_split = special_mapping_split,
};
static vm_fault_t special_mapping_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
pgoff_t pgoff;
struct page **pages;
struct vm_special_mapping *sm = vma->vm_private_data;
if (sm->fault)
return sm->fault(sm, vmf->vma, vmf);
pages = sm->pages;
for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
pgoff--;
if (*pages) {
struct page *page = *pages;
get_page(page);
vmf->page = page;
return 0;
}
return VM_FAULT_SIGBUS;
}
static struct vm_area_struct *__install_special_mapping(
struct mm_struct *mm,
unsigned long addr, unsigned long len,
unsigned long vm_flags, void *priv,
const struct vm_operations_struct *ops)
{
int ret;
struct vm_area_struct *vma;
vma = vm_area_alloc(mm);
if (unlikely(vma == NULL))
return ERR_PTR(-ENOMEM);
vma_set_range(vma, addr, addr + len, 0);
vm_flags_init(vma, (vm_flags | mm->def_flags |
VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK);
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
vma->vm_ops = ops;
vma->vm_private_data = priv;
ret = insert_vm_struct(mm, vma);
if (ret)
goto out;
vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT);
perf_event_mmap(vma);
return vma;
out:
vm_area_free(vma);
return ERR_PTR(ret);
}
bool vma_is_special_mapping(const struct vm_area_struct *vma,
const struct vm_special_mapping *sm)
{
return vma->vm_private_data == sm &&
vma->vm_ops == &special_mapping_vmops;
}
/*
* Called with mm->mmap_lock held for writing.
* Insert a new vma covering the given region, with the given flags.
* Its pages are supplied by the given array of struct page *.
* The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
* The region past the last page supplied will always produce SIGBUS.
* The array pointer and the pages it points to are assumed to stay alive
* for as long as this mapping might exist.
*/
struct vm_area_struct *_install_special_mapping(
struct mm_struct *mm,
unsigned long addr, unsigned long len,
unsigned long vm_flags, const struct vm_special_mapping *spec)
{
return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec,
&special_mapping_vmops);
}
#ifdef CONFIG_SYSCTL
#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
int sysctl_legacy_va_layout;
#endif
static const struct ctl_table mmap_table[] = {
{
.procname = "max_map_count",
.data = &sysctl_max_map_count,
.maxlen = sizeof(sysctl_max_map_count),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
{
.procname = "legacy_va_layout",
.data = &sysctl_legacy_va_layout,
.maxlen = sizeof(sysctl_legacy_va_layout),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
{
.procname = "mmap_rnd_bits",
.data = &mmap_rnd_bits,
.maxlen = sizeof(mmap_rnd_bits),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&mmap_rnd_bits_min,
.extra2 = (void *)&mmap_rnd_bits_max,
},
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
{
.procname = "mmap_rnd_compat_bits",
.data = &mmap_rnd_compat_bits,
.maxlen = sizeof(mmap_rnd_compat_bits),
.mode = 0600,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&mmap_rnd_compat_bits_min,
.extra2 = (void *)&mmap_rnd_compat_bits_max,
},
#endif
};
#endif /* CONFIG_SYSCTL */
/*
* initialise the percpu counter for VM
*/
void __init mmap_init(void)
{
int ret;
ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
VM_BUG_ON(ret);
#ifdef CONFIG_SYSCTL
register_sysctl_init("vm", mmap_table);
#endif
}
/*
* Initialise sysctl_user_reserve_kbytes.
*
* This is intended to prevent a user from starting a single memory hogging
* process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER
* mode.
*
* The default value is min(3% of free memory, 128MB)
* 128MB is enough to recover with sshd/login, bash, and top/kill.
*/
static int init_user_reserve(void)
{
unsigned long free_kbytes;
free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K);
return 0;
}
subsys_initcall(init_user_reserve);
/*
* Initialise sysctl_admin_reserve_kbytes.
*
* The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin
* to log in and kill a memory hogging process.
*
* Systems with more than 256MB will reserve 8MB, enough to recover
* with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will
* only reserve 3% of free pages by default.
*/
static int init_admin_reserve(void)
{
unsigned long free_kbytes;
free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K);
return 0;
}
subsys_initcall(init_admin_reserve);
/*
* Reinititalise user and admin reserves if memory is added or removed.
*
* The default user reserve max is 128MB, and the default max for the
* admin reserve is 8MB. These are usually, but not always, enough to
* enable recovery from a memory hogging process using login/sshd, a shell,
* and tools like top. It may make sense to increase or even disable the
* reserve depending on the existence of swap or variations in the recovery
* tools. So, the admin may have changed them.
*
* If memory is added and the reserves have been eliminated or increased above
* the default max, then we'll trust the admin.
*
* If memory is removed and there isn't enough free memory, then we
* need to reset the reserves.
*
* Otherwise keep the reserve set by the admin.
*/
static int reserve_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
unsigned long tmp, free_kbytes;
switch (action) {
case MEM_ONLINE:
/* Default max is 128MB. Leave alone if modified by operator. */
tmp = sysctl_user_reserve_kbytes;
if (tmp > 0 && tmp < SZ_128K)
init_user_reserve();
/* Default max is 8MB. Leave alone if modified by operator. */
tmp = sysctl_admin_reserve_kbytes;
if (tmp > 0 && tmp < SZ_8K)
init_admin_reserve();
break;
case MEM_OFFLINE:
free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
if (sysctl_user_reserve_kbytes > free_kbytes) {
init_user_reserve();
pr_info("vm.user_reserve_kbytes reset to %lu\n",
sysctl_user_reserve_kbytes);
}
if (sysctl_admin_reserve_kbytes > free_kbytes) {
init_admin_reserve();
pr_info("vm.admin_reserve_kbytes reset to %lu\n",
sysctl_admin_reserve_kbytes);
}
break;
default:
break;
}
return NOTIFY_OK;
}
static int __meminit init_reserve_notifier(void)
{
if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI))
pr_err("Failed registering memory add/remove notifier for admin reserve\n");
return 0;
}
subsys_initcall(init_reserve_notifier);
/*
* Relocate a VMA downwards by shift bytes. There cannot be any VMAs between
* this VMA and its relocated range, which will now reside at [vma->vm_start -
* shift, vma->vm_end - shift).
*
* This function is almost certainly NOT what you want for anything other than
* early executable temporary stack relocation.
*/
int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
{
/*
* The process proceeds as follows:
*
* 1) Use shift to calculate the new vma endpoints.
* 2) Extend vma to cover both the old and new ranges. This ensures the
* arguments passed to subsequent functions are consistent.
* 3) Move vma's page tables to the new range.
* 4) Free up any cleared pgd range.
* 5) Shrink the vma to cover only the new range.
*/
struct mm_struct *mm = vma->vm_mm;
unsigned long old_start = vma->vm_start;
unsigned long old_end = vma->vm_end;
unsigned long length = old_end - old_start;
unsigned long new_start = old_start - shift;
unsigned long new_end = old_end - shift;
VMA_ITERATOR(vmi, mm, new_start);
VMG_STATE(vmg, mm, &vmi, new_start, old_end, 0, vma->vm_pgoff);
struct vm_area_struct *next;
struct mmu_gather tlb;
PAGETABLE_MOVE(pmc, vma, vma, old_start, new_start, length);
BUG_ON(new_start > new_end);
/*
* ensure there are no vmas between where we want to go
* and where we are
*/
if (vma != vma_next(&vmi))
return -EFAULT;
vma_iter_prev_range(&vmi);
/*
* cover the whole range: [new_start, old_end)
*/
vmg.middle = vma;
if (vma_expand(&vmg))
return -ENOMEM;
/*
* move the page tables downwards, on failure we rely on
* process cleanup to remove whatever mess we made.
*/
pmc.for_stack = true;
if (length != move_page_tables(&pmc))
return -ENOMEM;
tlb_gather_mmu(&tlb, mm);
next = vma_next(&vmi);
if (new_end > old_start) {
/*
* when the old and new regions overlap clear from new_end.
*/
free_pgd_range(&tlb, new_end, old_end, new_end,
next ? next->vm_start : USER_PGTABLES_CEILING);
} else {
/*
* otherwise, clean from old_start; this is done to not touch
* the address space in [new_end, old_start) some architectures
* have constraints on va-space that make this illegal (IA64) -
* for the others its just a little faster.
*/
free_pgd_range(&tlb, old_start, old_end, new_end,
next ? next->vm_start : USER_PGTABLES_CEILING);
}
tlb_finish_mmu(&tlb);
vma_prev(&vmi);
/* Shrink the vma to just the new range */
return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff);
}
#ifdef CONFIG_MMU
/*
* Obtain a read lock on mm->mmap_lock, if the specified address is below the
* start of the VMA, the intent is to perform a write, and it is a
* downward-growing stack, then attempt to expand the stack to contain it.
*
* This function is intended only for obtaining an argument page from an ELF
* image, and is almost certainly NOT what you want to use for any other
* purpose.
*
* IMPORTANT - VMA fields are accessed without an mmap lock being held, so the
* VMA referenced must not be linked in any user-visible tree, i.e. it must be a
* new VMA being mapped.
*
* The function assumes that addr is either contained within the VMA or below
* it, and makes no attempt to validate this value beyond that.
*
* Returns true if the read lock was obtained and a stack was perhaps expanded,
* false if the stack expansion failed.
*
* On stack expansion the function temporarily acquires an mmap write lock
* before downgrading it.
*/
bool mmap_read_lock_maybe_expand(struct mm_struct *mm,
struct vm_area_struct *new_vma,
unsigned long addr, bool write)
{
if (!write || addr >= new_vma->vm_start) {
mmap_read_lock(mm);
return true;
}
if (!(new_vma->vm_flags & VM_GROWSDOWN))
return false;
mmap_write_lock(mm);
if (expand_downwards(new_vma, addr)) {
mmap_write_unlock(mm);
return false;
}
mmap_write_downgrade(mm);
return true;
}
#else
bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, bool write)
{
return false;
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/exit.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/stat.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/cpu.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/file.h>
#include <linux/freezer.h>
#include <linux/binfmts.h>
#include <linux/nsproxy.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
#include <linux/kthread.h>
#include <linux/mempolicy.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/cgroup.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/posix-timers.h>
#include <linux/cn_proc.h>
#include <linux/mutex.h>
#include <linux/futex.h>
#include <linux/pipe_fs_i.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/task_work.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
#include <linux/perf_event.h>
#include <trace/events/sched.h>
#include <linux/hw_breakpoint.h>
#include <linux/oom.h>
#include <linux/writeback.h>
#include <linux/shm.h>
#include <linux/kcov.h>
#include <linux/kmsan.h>
#include <linux/random.h>
#include <linux/rcuwait.h>
#include <linux/compat.h>
#include <linux/io_uring.h>
#include <linux/kprobes.h>
#include <linux/rethook.h>
#include <linux/sysfs.h>
#include <linux/user_events.h>
#include <linux/uaccess.h>
#include <linux/pidfs.h>
#include <uapi/linux/wait.h>
#include <asm/unistd.h>
#include <asm/mmu_context.h>
#include "exit.h"
/*
* The default value should be high enough to not crash a system that randomly
* crashes its kernel from time to time, but low enough to at least not permit
* overflowing 32-bit refcounts or the ldsem writer count.
*/
static unsigned int oops_limit = 10000;
#ifdef CONFIG_SYSCTL
static const struct ctl_table kern_exit_table[] = {
{
.procname = "oops_limit",
.data = &oops_limit,
.maxlen = sizeof(oops_limit),
.mode = 0644,
.proc_handler = proc_douintvec,
},
};
static __init int kernel_exit_sysctls_init(void)
{
register_sysctl_init("kernel", kern_exit_table);
return 0;
}
late_initcall(kernel_exit_sysctls_init);
#endif
static atomic_t oops_count = ATOMIC_INIT(0);
#ifdef CONFIG_SYSFS
static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr,
char *page)
{
return sysfs_emit(page, "%d\n", atomic_read(&oops_count));
}
static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count);
static __init int kernel_exit_sysfs_init(void)
{
sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL);
return 0;
}
late_initcall(kernel_exit_sysfs_init);
#endif
/*
* For things release_task() would like to do *after* tasklist_lock is released.
*/
struct release_task_post {
struct pid *pids[PIDTYPE_MAX];
};
static void __unhash_process(struct release_task_post *post, struct task_struct *p,
bool group_dead)
{
nr_threads--;
detach_pid(post->pids, p, PIDTYPE_PID);
if (group_dead) {
detach_pid(post->pids, p, PIDTYPE_TGID);
detach_pid(post->pids, p, PIDTYPE_PGID);
detach_pid(post->pids, p, PIDTYPE_SID);
list_del_rcu(&p->tasks);
list_del_init(&p->sibling);
__this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_node);
}
/*
* This function expects the tasklist_lock write-locked.
*/
static void __exit_signal(struct release_task_post *post, struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
bool group_dead = thread_group_leader(tsk);
struct sighand_struct *sighand;
struct tty_struct *tty;
u64 utime, stime;
sighand = rcu_dereference_check(tsk->sighand,
lockdep_tasklist_lock_is_held());
spin_lock(&sighand->siglock);
#ifdef CONFIG_POSIX_TIMERS
posix_cpu_timers_exit(tsk);
if (group_dead)
posix_cpu_timers_exit_group(tsk);
#endif
if (group_dead) {
tty = sig->tty;
sig->tty = NULL;
} else {
/*
* If there is any task waiting for the group exit
* then notify it:
*/
if (sig->notify_count > 0 && !--sig->notify_count)
wake_up_process(sig->group_exec_task);
if (tsk == sig->curr_target)
sig->curr_target = next_thread(tsk);
}
/*
* Accumulate here the counters for all threads as they die. We could
* skip the group leader because it is the last user of signal_struct,
* but we want to avoid the race with thread_group_cputime() which can
* see the empty ->thread_head list.
*/
task_cputime(tsk, &utime, &stime);
write_seqlock(&sig->stats_lock);
sig->utime += utime;
sig->stime += stime;
sig->gtime += task_gtime(tsk);
sig->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
sig->nvcsw += tsk->nvcsw;
sig->nivcsw += tsk->nivcsw;
sig->inblock += task_io_get_inblock(tsk);
sig->oublock += task_io_get_oublock(tsk);
task_io_accounting_add(&sig->ioac, &tsk->ioac);
sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
sig->nr_threads--;
__unhash_process(post, tsk, group_dead);
write_sequnlock(&sig->stats_lock);
tsk->sighand = NULL;
spin_unlock(&sighand->siglock);
__cleanup_sighand(sighand);
if (group_dead)
tty_kref_put(tty);
}
static void delayed_put_task_struct(struct rcu_head *rhp)
{
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
kprobe_flush_task(tsk);
rethook_flush_task(tsk);
perf_event_delayed_put(tsk);
trace_sched_process_free(tsk);
put_task_struct(tsk);
}
void put_task_struct_rcu_user(struct task_struct *task)
{ if (refcount_dec_and_test(&task->rcu_users))
call_rcu(&task->rcu, delayed_put_task_struct);
}
void __weak release_thread(struct task_struct *dead_task)
{
}
void release_task(struct task_struct *p)
{
struct release_task_post post;
struct task_struct *leader;
struct pid *thread_pid;
int zap_leader;
repeat:
memset(&post, 0, sizeof(post));
/* don't need to get the RCU readlock here - the process is dead and
* can't be modifying its own credentials. But shut RCU-lockdep up */
rcu_read_lock();
dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
rcu_read_unlock();
pidfs_exit(p);
cgroup_release(p);
thread_pid = get_pid(p->thread_pid);
write_lock_irq(&tasklist_lock);
ptrace_release_task(p);
__exit_signal(&post, p);
/*
* If we are the last non-leader member of the thread
* group, and the leader is zombie, then notify the
* group leader's parent process. (if it wants notification.)
*/
zap_leader = 0;
leader = p->group_leader;
if (leader != p && thread_group_empty(leader)
&& leader->exit_state == EXIT_ZOMBIE) {
/* for pidfs_exit() and do_notify_parent() */
if (leader->signal->flags & SIGNAL_GROUP_EXIT)
leader->exit_code = leader->signal->group_exit_code;
/*
* If we were the last child thread and the leader has
* exited already, and the leader's parent ignores SIGCHLD,
* then we are the one who should release the leader.
*/
zap_leader = do_notify_parent(leader, leader->exit_signal);
if (zap_leader)
leader->exit_state = EXIT_DEAD;
}
write_unlock_irq(&tasklist_lock);
proc_flush_pid(thread_pid);
put_pid(thread_pid);
add_device_randomness(&p->se.sum_exec_runtime,
sizeof(p->se.sum_exec_runtime));
free_pids(post.pids);
release_thread(p);
/*
* This task was already removed from the process/thread/pid lists
* and lock_task_sighand(p) can't succeed. Nobody else can touch
* ->pending or, if group dead, signal->shared_pending. We can call
* flush_sigqueue() lockless.
*/
flush_sigqueue(&p->pending);
if (thread_group_leader(p))
flush_sigqueue(&p->signal->shared_pending);
put_task_struct_rcu_user(p);
p = leader;
if (unlikely(zap_leader))
goto repeat;
}
int rcuwait_wake_up(struct rcuwait *w)
{
int ret = 0;
struct task_struct *task;
rcu_read_lock();
/*
* Order condition vs @task, such that everything prior to the load
* of @task is visible. This is the condition as to why the user called
* rcuwait_wake() in the first place. Pairs with set_current_state()
* barrier (A) in rcuwait_wait_event().
*
* WAIT WAKE
* [S] tsk = current [S] cond = true
* MB (A) MB (B)
* [L] cond [L] tsk
*/
smp_mb(); /* (B) */
task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(rcuwait_wake_up);
/*
* Determine if a process group is "orphaned", according to the POSIX
* definition in 2.2.2.52. Orphaned process groups are not to be affected
* by terminal-generated stop signals. Newly orphaned process groups are
* to receive a SIGHUP and a SIGCONT.
*
* "I ask you, have you ever known what it is to be an orphan?"
*/
static int will_become_orphaned_pgrp(struct pid *pgrp,
struct task_struct *ignored_task)
{
struct task_struct *p;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
if ((p == ignored_task) ||
(p->exit_state && thread_group_empty(p)) ||
is_global_init(p->real_parent))
continue;
if (task_pgrp(p->real_parent) != pgrp &&
task_session(p->real_parent) == task_session(p))
return 0;
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return 1;
}
int is_current_pgrp_orphaned(void)
{
int retval;
read_lock(&tasklist_lock);
retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
read_unlock(&tasklist_lock);
return retval;
}
static bool has_stopped_jobs(struct pid *pgrp)
{
struct task_struct *p;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
if (p->signal->flags & SIGNAL_STOP_STOPPED)
return true;
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return false;
}
/*
* Check to see if any process groups have become orphaned as
* a result of our exiting, and if they have any stopped jobs,
* send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
*/
static void
kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
{
struct pid *pgrp = task_pgrp(tsk);
struct task_struct *ignored_task = tsk;
if (!parent)
/* exit: our father is in a different pgrp than
* we are and we were the only connection outside.
*/
parent = tsk->real_parent;
else
/* reparent: our child is in a different pgrp than
* we are, and it was the only connection outside.
*/
ignored_task = NULL;
if (task_pgrp(parent) != pgrp &&
task_session(parent) == task_session(tsk) &&
will_become_orphaned_pgrp(pgrp, ignored_task) &&
has_stopped_jobs(pgrp)) {
__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
}
}
static void coredump_task_exit(struct task_struct *tsk)
{
struct core_state *core_state;
/*
* Serialize with any possible pending coredump.
* We must hold siglock around checking core_state
* and setting PF_POSTCOREDUMP. The core-inducing thread
* will increment ->nr_threads for each thread in the
* group without PF_POSTCOREDUMP set.
*/
spin_lock_irq(&tsk->sighand->siglock);
tsk->flags |= PF_POSTCOREDUMP;
core_state = tsk->signal->core_state;
spin_unlock_irq(&tsk->sighand->siglock);
if (core_state) {
struct core_thread self;
self.task = current;
if (self.task->flags & PF_SIGNALED)
self.next = xchg(&core_state->dumper.next, &self);
else
self.task = NULL;
/*
* Implies mb(), the result of xchg() must be visible
* to core_state->dumper.
*/
if (atomic_dec_and_test(&core_state->nr_threads))
complete(&core_state->startup);
for (;;) {
set_current_state(TASK_IDLE|TASK_FREEZABLE);
if (!self.task) /* see coredump_finish() */
break;
schedule();
}
__set_current_state(TASK_RUNNING);
}
}
#ifdef CONFIG_MEMCG
/* drops tasklist_lock if succeeds */
static bool __try_to_set_owner(struct task_struct *tsk, struct mm_struct *mm)
{
bool ret = false;
task_lock(tsk);
if (likely(tsk->mm == mm)) {
/* tsk can't pass exit_mm/exec_mmap and exit */
read_unlock(&tasklist_lock);
WRITE_ONCE(mm->owner, tsk);
lru_gen_migrate_mm(mm);
ret = true;
}
task_unlock(tsk);
return ret;
}
static bool try_to_set_owner(struct task_struct *g, struct mm_struct *mm)
{
struct task_struct *t;
for_each_thread(g, t) {
struct mm_struct *t_mm = READ_ONCE(t->mm);
if (t_mm == mm) {
if (__try_to_set_owner(t, mm))
return true;
} else if (t_mm)
break;
}
return false;
}
/*
* A task is exiting. If it owned this mm, find a new owner for the mm.
*/
void mm_update_next_owner(struct mm_struct *mm)
{
struct task_struct *g, *p = current;
/*
* If the exiting or execing task is not the owner, it's
* someone else's problem.
*/
if (mm->owner != p)
return;
/*
* The current owner is exiting/execing and there are no other
* candidates. Do not leave the mm pointing to a possibly
* freed task structure.
*/
if (atomic_read(&mm->mm_users) <= 1) {
WRITE_ONCE(mm->owner, NULL);
return;
}
read_lock(&tasklist_lock);
/*
* Search in the children
*/
list_for_each_entry(g, &p->children, sibling) {
if (try_to_set_owner(g, mm))
goto ret;
}
/*
* Search in the siblings
*/
list_for_each_entry(g, &p->real_parent->children, sibling) {
if (try_to_set_owner(g, mm))
goto ret;
}
/*
* Search through everything else, we should not get here often.
*/
for_each_process(g) {
if (atomic_read(&mm->mm_users) <= 1)
break;
if (g->flags & PF_KTHREAD)
continue;
if (try_to_set_owner(g, mm))
goto ret;
}
read_unlock(&tasklist_lock);
/*
* We found no owner yet mm_users > 1: this implies that we are
* most likely racing with swapoff (try_to_unuse()) or /proc or
* ptrace or page migration (get_task_mm()). Mark owner as NULL.
*/
WRITE_ONCE(mm->owner, NULL);
ret:
return;
}
#endif /* CONFIG_MEMCG */
/*
* Turn us into a lazy TLB process if we
* aren't already..
*/
static void exit_mm(void)
{
struct mm_struct *mm = current->mm;
exit_mm_release(current, mm);
if (!mm)
return;
mmap_read_lock(mm);
mmgrab_lazy_tlb(mm);
BUG_ON(mm != current->active_mm);
/* more a memory barrier than a real lock */
task_lock(current);
/*
* When a thread stops operating on an address space, the loop
* in membarrier_private_expedited() may not observe that
* tsk->mm, and the loop in membarrier_global_expedited() may
* not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED
* rq->membarrier_state, so those would not issue an IPI.
* Membarrier requires a memory barrier after accessing
* user-space memory, before clearing tsk->mm or the
* rq->membarrier_state.
*/
smp_mb__after_spinlock();
local_irq_disable();
current->mm = NULL;
membarrier_update_current_mm(NULL);
enter_lazy_tlb(mm, current);
local_irq_enable();
task_unlock(current);
mmap_read_unlock(mm);
mm_update_next_owner(mm);
mmput(mm);
if (test_thread_flag(TIF_MEMDIE))
exit_oom_victim();
}
static struct task_struct *find_alive_thread(struct task_struct *p)
{
struct task_struct *t;
for_each_thread(p, t) {
if (!(t->flags & PF_EXITING))
return t;
}
return NULL;
}
static struct task_struct *find_child_reaper(struct task_struct *father,
struct list_head *dead)
__releases(&tasklist_lock)
__acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *reaper = pid_ns->child_reaper;
struct task_struct *p, *n;
if (likely(reaper != father))
return reaper;
reaper = find_alive_thread(father);
if (reaper) {
pid_ns->child_reaper = reaper;
return reaper;
}
write_unlock_irq(&tasklist_lock);
list_for_each_entry_safe(p, n, dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
release_task(p);
}
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
return father;
}
/*
* When we die, we re-parent all our children, and try to:
* 1. give them to another thread in our thread group, if such a member exists
* 2. give it to the first ancestor process which prctl'd itself as a
* child_subreaper for its children (like a service manager)
* 3. give it to the init process (PID 1) in our pid namespace
*/
static struct task_struct *find_new_reaper(struct task_struct *father,
struct task_struct *child_reaper)
{
struct task_struct *thread, *reaper;
thread = find_alive_thread(father);
if (thread)
return thread;
if (father->signal->has_child_subreaper) {
unsigned int ns_level = task_pid(father)->level;
/*
* Find the first ->is_child_subreaper ancestor in our pid_ns.
* We can't check reaper != child_reaper to ensure we do not
* cross the namespaces, the exiting parent could be injected
* by setns() + fork().
* We check pid->level, this is slightly more efficient than
* task_active_pid_ns(reaper) != task_active_pid_ns(father).
*/
for (reaper = father->real_parent;
task_pid(reaper)->level == ns_level;
reaper = reaper->real_parent) {
if (reaper == &init_task)
break;
if (!reaper->signal->is_child_subreaper)
continue;
thread = find_alive_thread(reaper);
if (thread)
return thread;
}
}
return child_reaper;
}
/*
* Any that need to be release_task'd are put on the @dead list.
*/
static void reparent_leader(struct task_struct *father, struct task_struct *p,
struct list_head *dead)
{
if (unlikely(p->exit_state == EXIT_DEAD))
return;
/* We don't want people slaying init. */
p->exit_signal = SIGCHLD;
/* If it has exited notify the new parent about this child's death. */
if (!p->ptrace &&
p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
if (do_notify_parent(p, p->exit_signal)) {
p->exit_state = EXIT_DEAD;
list_add(&p->ptrace_entry, dead);
}
}
kill_orphaned_pgrp(p, father);
}
/*
* This does two things:
*
* A. Make init inherit all the child processes
* B. Check to see if any process groups have become orphaned
* as a result of our exiting, and if they have any stopped
* jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
*/
static void forget_original_parent(struct task_struct *father,
struct list_head *dead)
{
struct task_struct *p, *t, *reaper;
if (unlikely(!list_empty(&father->ptraced)))
exit_ptrace(father, dead);
/* Can drop and reacquire tasklist_lock */
reaper = find_child_reaper(father, dead);
if (list_empty(&father->children))
return;
reaper = find_new_reaper(father, reaper);
list_for_each_entry(p, &father->children, sibling) {
for_each_thread(p, t) {
RCU_INIT_POINTER(t->real_parent, reaper);
BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father));
if (likely(!t->ptrace))
t->parent = t->real_parent;
if (t->pdeath_signal)
group_send_sig_info(t->pdeath_signal,
SEND_SIG_NOINFO, t,
PIDTYPE_TGID);
}
/*
* If this is a threaded reparent there is no need to
* notify anyone anything has happened.
*/
if (!same_thread_group(reaper, father))
reparent_leader(father, p, dead);
}
list_splice_tail_init(&father->children, &reaper->children);
}
/*
* Send signals to all our closest relatives so that they know
* to properly mourn us..
*/
static void exit_notify(struct task_struct *tsk, int group_dead)
{
bool autoreap;
struct task_struct *p, *n;
LIST_HEAD(dead);
write_lock_irq(&tasklist_lock);
forget_original_parent(tsk, &dead);
if (group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
tsk->exit_state = EXIT_ZOMBIE;
if (unlikely(tsk->ptrace)) {
int sig = thread_group_leader(tsk) &&
thread_group_empty(tsk) &&
!ptrace_reparented(tsk) ?
tsk->exit_signal : SIGCHLD;
autoreap = do_notify_parent(tsk, sig);
} else if (thread_group_leader(tsk)) {
autoreap = thread_group_empty(tsk) &&
do_notify_parent(tsk, tsk->exit_signal);
} else {
autoreap = true;
/* untraced sub-thread */
do_notify_pidfd(tsk);
}
if (autoreap) {
tsk->exit_state = EXIT_DEAD;
list_add(&tsk->ptrace_entry, &dead);
}
/* mt-exec, de_thread() is waiting for group leader */
if (unlikely(tsk->signal->notify_count < 0))
wake_up_process(tsk->signal->group_exec_task);
write_unlock_irq(&tasklist_lock);
list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
release_task(p);
}
}
#ifdef CONFIG_DEBUG_STACK_USAGE
unsigned long stack_not_used(struct task_struct *p)
{
unsigned long *n = end_of_stack(p);
do { /* Skip over canary */
# ifdef CONFIG_STACK_GROWSUP
n--;
# else
n++;
# endif
} while (!*n);
# ifdef CONFIG_STACK_GROWSUP
return (unsigned long)end_of_stack(p) - (unsigned long)n;
# else
return (unsigned long)n - (unsigned long)end_of_stack(p);
# endif
}
/* Count the maximum pages reached in kernel stacks */
static inline void kstack_histogram(unsigned long used_stack)
{
#ifdef CONFIG_VM_EVENT_COUNTERS
if (used_stack <= 1024)
count_vm_event(KSTACK_1K);
#if THREAD_SIZE > 1024
else if (used_stack <= 2048)
count_vm_event(KSTACK_2K);
#endif
#if THREAD_SIZE > 2048
else if (used_stack <= 4096)
count_vm_event(KSTACK_4K);
#endif
#if THREAD_SIZE > 4096
else if (used_stack <= 8192)
count_vm_event(KSTACK_8K);
#endif
#if THREAD_SIZE > 8192
else if (used_stack <= 16384)
count_vm_event(KSTACK_16K);
#endif
#if THREAD_SIZE > 16384
else if (used_stack <= 32768)
count_vm_event(KSTACK_32K);
#endif
#if THREAD_SIZE > 32768
else if (used_stack <= 65536)
count_vm_event(KSTACK_64K);
#endif
#if THREAD_SIZE > 65536
else
count_vm_event(KSTACK_REST);
#endif
#endif /* CONFIG_VM_EVENT_COUNTERS */
}
static void check_stack_usage(void)
{
static DEFINE_SPINLOCK(low_water_lock);
static int lowest_to_date = THREAD_SIZE;
unsigned long free;
free = stack_not_used(current);
kstack_histogram(THREAD_SIZE - free);
if (free >= lowest_to_date)
return;
spin_lock(&low_water_lock);
if (free < lowest_to_date) {
pr_info("%s (%d) used greatest stack depth: %lu bytes left\n",
current->comm, task_pid_nr(current), free);
lowest_to_date = free;
}
spin_unlock(&low_water_lock);
}
#else
static inline void check_stack_usage(void) {}
#endif
static void synchronize_group_exit(struct task_struct *tsk, long code)
{
struct sighand_struct *sighand = tsk->sighand;
struct signal_struct *signal = tsk->signal;
spin_lock_irq(&sighand->siglock);
signal->quick_threads--;
if ((signal->quick_threads == 0) &&
!(signal->flags & SIGNAL_GROUP_EXIT)) {
signal->flags = SIGNAL_GROUP_EXIT;
signal->group_exit_code = code;
signal->group_stop_count = 0;
}
spin_unlock_irq(&sighand->siglock);
}
void __noreturn do_exit(long code)
{
struct task_struct *tsk = current;
int group_dead;
WARN_ON(irqs_disabled());
synchronize_group_exit(tsk, code);
WARN_ON(tsk->plug);
kcov_task_exit(tsk);
kmsan_task_exit(tsk);
coredump_task_exit(tsk);
ptrace_event(PTRACE_EVENT_EXIT, code);
user_events_exit(tsk);
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
seccomp_filter_release(tsk);
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
/*
* If the last thread of global init has exited, panic
* immediately to get a useable coredump.
*/
if (unlikely(is_global_init(tsk)))
panic("Attempted to kill init! exitcode=0x%08x\n",
tsk->signal->group_exit_code ?: (int)code);
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
}
acct_collect(code, group_dead);
if (group_dead)
tty_audit_exit();
audit_free(tsk);
tsk->exit_code = code;
taskstats_exit(tsk, group_dead);
exit_mm();
if (group_dead)
acct_process();
trace_sched_process_exit(tsk);
exit_sem(tsk);
exit_shm(tsk);
exit_files(tsk);
exit_fs(tsk);
if (group_dead)
disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
exit_thread(tsk);
/*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*
* because of cgroup mode, must be called before cgroup_exit()
*/
perf_event_exit_task(tsk);
sched_autogroup_exit_task(tsk);
cgroup_exit(tsk);
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
flush_ptrace_hw_breakpoint(tsk);
exit_tasks_rcu_start();
exit_notify(tsk, group_dead);
proc_exit_connector(tsk);
mpol_put_task_policy(tsk);
#ifdef CONFIG_FUTEX
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
#endif
/*
* Make sure we are holding no locks:
*/
debug_check_no_locks_held();
if (tsk->io_context)
exit_io_context(tsk);
if (tsk->splice_pipe)
free_pipe_info(tsk->splice_pipe);
if (tsk->task_frag.page)
put_page(tsk->task_frag.page);
exit_task_stack_account(tsk);
check_stack_usage();
preempt_disable();
if (tsk->nr_dirtied)
__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
exit_rcu();
exit_tasks_rcu_finish();
lockdep_free_task(tsk);
do_task_dead();
}
void __noreturn make_task_dead(int signr)
{
/*
* Take the task off the cpu after something catastrophic has
* happened.
*
* We can get here from a kernel oops, sometimes with preemption off.
* Start by checking for critical errors.
* Then fix up important state like USER_DS and preemption.
* Then do everything else.
*/
struct task_struct *tsk = current;
unsigned int limit;
if (unlikely(in_interrupt()))
panic("Aiee, killing interrupt handler!");
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
if (unlikely(irqs_disabled())) {
pr_info("note: %s[%d] exited with irqs disabled\n",
current->comm, task_pid_nr(current));
local_irq_enable();
}
if (unlikely(in_atomic())) {
pr_info("note: %s[%d] exited with preempt_count %d\n",
current->comm, task_pid_nr(current),
preempt_count());
preempt_count_set(PREEMPT_ENABLED);
}
/*
* Every time the system oopses, if the oops happens while a reference
* to an object was held, the reference leaks.
* If the oops doesn't also leak memory, repeated oopsing can cause
* reference counters to wrap around (if they're not using refcount_t).
* This means that repeated oopsing can make unexploitable-looking bugs
* exploitable through repeated oopsing.
* To make sure this can't happen, place an upper bound on how often the
* kernel may oops without panic().
*/
limit = READ_ONCE(oops_limit);
if (atomic_inc_return(&oops_count) >= limit && limit)
panic("Oopsed too often (kernel.oops_limit is %d)", limit);
/*
* We're taking recursive faults here in make_task_dead. Safest is to just
* leave this task alone and wait for reboot.
*/
if (unlikely(tsk->flags & PF_EXITING)) {
pr_alert("Fixing recursive fault but reboot is needed!\n");
futex_exit_recursive(tsk);
tsk->exit_state = EXIT_DEAD;
refcount_inc(&tsk->rcu_users);
do_task_dead();
}
do_exit(signr);
}
SYSCALL_DEFINE1(exit, int, error_code)
{
do_exit((error_code&0xff)<<8);
}
/*
* Take down every thread in the group. This is called by fatal signals
* as well as by sys_exit_group (below).
*/
void __noreturn
do_group_exit(int exit_code)
{
struct signal_struct *sig = current->signal;
if (sig->flags & SIGNAL_GROUP_EXIT)
exit_code = sig->group_exit_code;
else if (sig->group_exec_task)
exit_code = 0;
else {
struct sighand_struct *const sighand = current->sighand;
spin_lock_irq(&sighand->siglock);
if (sig->flags & SIGNAL_GROUP_EXIT)
/* Another thread got here before we took the lock. */
exit_code = sig->group_exit_code;
else if (sig->group_exec_task)
exit_code = 0;
else {
sig->group_exit_code = exit_code;
sig->flags = SIGNAL_GROUP_EXIT;
zap_other_threads(current);
}
spin_unlock_irq(&sighand->siglock);
}
do_exit(exit_code);
/* NOTREACHED */
}
/*
* this kills every thread in the thread group. Note that any externally
* wait4()-ing process will get the correct exit code - even if this
* thread is not the thread group leader.
*/
SYSCALL_DEFINE1(exit_group, int, error_code)
{
do_group_exit((error_code & 0xff) << 8);
/* NOTREACHED */
return 0;
}
static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
return wo->wo_type == PIDTYPE_MAX ||
task_pid_type(p, wo->wo_type) == wo->wo_pid;
}
static int
eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p)
{
if (!eligible_pid(wo, p))
return 0;
/*
* Wait for all children (clone and not) if __WALL is set or
* if it is traced by us.
*/
if (ptrace || (wo->wo_flags & __WALL))
return 1;
/*
* Otherwise, wait for clone children *only* if __WCLONE is set;
* otherwise, wait for non-clone children *only*.
*
* Note: a "clone" child here is one that reports to its parent
* using a signal other than SIGCHLD, or a non-leader thread which
* we can only see if it is traced by us.
*/
if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
return 0;
return 1;
}
/*
* Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
{
int state, status;
pid_t pid = task_pid_vnr(p);
uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p));
struct waitid_info *infop;
if (!likely(wo->wo_flags & WEXITED))
return 0;
if (unlikely(wo->wo_flags & WNOWAIT)) {
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
? p->signal->group_exit_code : p->exit_code;
get_task_struct(p);
read_unlock(&tasklist_lock);
sched_annotate_sleep();
if (wo->wo_rusage)
getrusage(p, RUSAGE_BOTH, wo->wo_rusage);
put_task_struct(p);
goto out_info;
}
/*
* Move the task's state to DEAD/TRACE, only one thread can do this.
*/
state = (ptrace_reparented(p) && thread_group_leader(p)) ?
EXIT_TRACE : EXIT_DEAD;
if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
return 0;
/*
* We own this thread, nobody else can reap it.
*/
read_unlock(&tasklist_lock);
sched_annotate_sleep();
/*
* Check thread_group_leader() to exclude the traced sub-threads.
*/
if (state == EXIT_DEAD && thread_group_leader(p)) {
struct signal_struct *sig = p->signal;
struct signal_struct *psig = current->signal;
unsigned long maxrss;
u64 tgutime, tgstime;
/*
* The resource counters for the group leader are in its
* own task_struct. Those for dead threads in the group
* are in its signal_struct, as are those for the child
* processes it has previously reaped. All these
* accumulate in the parent's signal_struct c* fields.
*
* We don't bother to take a lock here to protect these
* p->signal fields because the whole thread group is dead
* and nobody can change them.
*
* psig->stats_lock also protects us from our sub-threads
* which can reap other children at the same time.
*
* We use thread_group_cputime_adjusted() to get times for
* the thread group, which consolidates times for all threads
* in the group including the group leader.
*/
thread_group_cputime_adjusted(p, &tgutime, &tgstime);
write_seqlock_irq(&psig->stats_lock);
psig->cutime += tgutime + sig->cutime;
psig->cstime += tgstime + sig->cstime;
psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
psig->cmin_flt +=
p->min_flt + sig->min_flt + sig->cmin_flt;
psig->cmaj_flt +=
p->maj_flt + sig->maj_flt + sig->cmaj_flt;
psig->cnvcsw +=
p->nvcsw + sig->nvcsw + sig->cnvcsw;
psig->cnivcsw +=
p->nivcsw + sig->nivcsw + sig->cnivcsw;
psig->cinblock +=
task_io_get_inblock(p) +
sig->inblock + sig->cinblock;
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
maxrss = max(sig->maxrss, sig->cmaxrss);
if (psig->cmaxrss < maxrss)
psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
write_sequnlock_irq(&psig->stats_lock);
}
if (wo->wo_rusage)
getrusage(p, RUSAGE_BOTH, wo->wo_rusage);
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
? p->signal->group_exit_code : p->exit_code;
wo->wo_stat = status;
if (state == EXIT_TRACE) {
write_lock_irq(&tasklist_lock);
/* We dropped tasklist, ptracer could die and untrace */
ptrace_unlink(p);
/* If parent wants a zombie, don't release it now */
state = EXIT_ZOMBIE;
if (do_notify_parent(p, p->exit_signal))
state = EXIT_DEAD;
p->exit_state = state;
write_unlock_irq(&tasklist_lock);
}
if (state == EXIT_DEAD)
release_task(p);
out_info:
infop = wo->wo_info;
if (infop) {
if ((status & 0x7f) == 0) {
infop->cause = CLD_EXITED;
infop->status = status >> 8;
} else {
infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
infop->status = status & 0x7f;
}
infop->pid = pid;
infop->uid = uid;
}
return pid;
}
static int *task_stopped_code(struct task_struct *p, bool ptrace)
{
if (ptrace) {
if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING))
return &p->exit_code;
} else {
if (p->signal->flags & SIGNAL_STOP_STOPPED)
return &p->signal->group_exit_code;
}
return NULL;
}
/**
* wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED
* @wo: wait options
* @ptrace: is the wait for ptrace
* @p: task to wait for
*
* Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED.
*
* CONTEXT:
* read_lock(&tasklist_lock), which is released if return value is
* non-zero. Also, grabs and releases @p->sighand->siglock.
*
* RETURNS:
* 0 if wait condition didn't exist and search for other wait conditions
* should continue. Non-zero return, -errno on failure and @p's pid on
* success, implies that tasklist_lock is released and wait condition
* search should terminate.
*/
static int wait_task_stopped(struct wait_opts *wo,
int ptrace, struct task_struct *p)
{
struct waitid_info *infop;
int exit_code, *p_code, why;
uid_t uid = 0; /* unneeded, required by compiler */
pid_t pid;
/*
* Traditionally we see ptrace'd stopped tasks regardless of options.
*/
if (!ptrace && !(wo->wo_flags & WUNTRACED))
return 0;
if (!task_stopped_code(p, ptrace))
return 0;
exit_code = 0;
spin_lock_irq(&p->sighand->siglock);
p_code = task_stopped_code(p, ptrace);
if (unlikely(!p_code))
goto unlock_sig;
exit_code = *p_code;
if (!exit_code)
goto unlock_sig;
if (!unlikely(wo->wo_flags & WNOWAIT))
*p_code = 0;
uid = from_kuid_munged(current_user_ns(), task_uid(p));
unlock_sig:
spin_unlock_irq(&p->sighand->siglock);
if (!exit_code)
return 0;
/*
* Now we are pretty sure this task is interesting.
* Make sure it doesn't get reaped out from under us while we
* give up the lock and then examine it below. We don't want to
* keep holding onto the tasklist_lock while we call getrusage and
* possibly take page faults for user memory.
*/
get_task_struct(p);
pid = task_pid_vnr(p);
why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
read_unlock(&tasklist_lock);
sched_annotate_sleep();
if (wo->wo_rusage)
getrusage(p, RUSAGE_BOTH, wo->wo_rusage);
put_task_struct(p);
if (likely(!(wo->wo_flags & WNOWAIT)))
wo->wo_stat = (exit_code << 8) | 0x7f;
infop = wo->wo_info;
if (infop) {
infop->cause = why;
infop->status = exit_code;
infop->pid = pid;
infop->uid = uid;
}
return pid;
}
/*
* Handle do_wait work for one task in a live, non-stopped state.
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
{
struct waitid_info *infop;
pid_t pid;
uid_t uid;
if (!unlikely(wo->wo_flags & WCONTINUED))
return 0;
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
return 0;
spin_lock_irq(&p->sighand->siglock);
/* Re-check with the lock held. */
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
spin_unlock_irq(&p->sighand->siglock);
return 0;
}
if (!unlikely(wo->wo_flags & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
uid = from_kuid_munged(current_user_ns(), task_uid(p));
spin_unlock_irq(&p->sighand->siglock);
pid = task_pid_vnr(p);
get_task_struct(p);
read_unlock(&tasklist_lock);
sched_annotate_sleep();
if (wo->wo_rusage)
getrusage(p, RUSAGE_BOTH, wo->wo_rusage);
put_task_struct(p);
infop = wo->wo_info;
if (!infop) {
wo->wo_stat = 0xffff;
} else {
infop->cause = CLD_CONTINUED;
infop->pid = pid;
infop->uid = uid;
infop->status = SIGCONT;
}
return pid;
}
/*
* Consider @p for a wait by @parent.
*
* -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue;
* then ->notask_error is 0 if @p is an eligible child,
* or still -ECHILD.
*/
static int wait_consider_task(struct wait_opts *wo, int ptrace,
struct task_struct *p)
{
/*
* We can race with wait_task_zombie() from another thread.
* Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
* can't confuse the checks below.
*/
int exit_state = READ_ONCE(p->exit_state);
int ret;
if (unlikely(exit_state == EXIT_DEAD))
return 0;
ret = eligible_child(wo, ptrace, p);
if (!ret)
return ret;
if (unlikely(exit_state == EXIT_TRACE)) {
/*
* ptrace == 0 means we are the natural parent. In this case
* we should clear notask_error, debugger will notify us.
*/
if (likely(!ptrace))
wo->notask_error = 0;
return 0;
}
if (likely(!ptrace) && unlikely(p->ptrace)) {
/*
* If it is traced by its real parent's group, just pretend
* the caller is ptrace_do_wait() and reap this child if it
* is zombie.
*
* This also hides group stop state from real parent; otherwise
* a single stop can be reported twice as group and ptrace stop.
* If a ptracer wants to distinguish these two events for its
* own children it should create a separate process which takes
* the role of real parent.
*/
if (!ptrace_reparented(p))
ptrace = 1;
}
/* slay zombie? */
if (exit_state == EXIT_ZOMBIE) {
/* we don't reap group leaders with subthreads */
if (!delay_group_leader(p)) {
/*
* A zombie ptracee is only visible to its ptracer.
* Notification and reaping will be cascaded to the
* real parent when the ptracer detaches.
*/
if (unlikely(ptrace) || likely(!p->ptrace))
return wait_task_zombie(wo, p);
}
/*
* Allow access to stopped/continued state via zombie by
* falling through. Clearing of notask_error is complex.
*
* When !@ptrace:
*
* If WEXITED is set, notask_error should naturally be
* cleared. If not, subset of WSTOPPED|WCONTINUED is set,
* so, if there are live subthreads, there are events to
* wait for. If all subthreads are dead, it's still safe
* to clear - this function will be called again in finite
* amount time once all the subthreads are released and
* will then return without clearing.
*
* When @ptrace:
*
* Stopped state is per-task and thus can't change once the
* target task dies. Only continued and exited can happen.
* Clear notask_error if WCONTINUED | WEXITED.
*/
if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED)))
wo->notask_error = 0;
} else {
/*
* @p is alive and it's gonna stop, continue or exit, so
* there always is something to wait for.
*/
wo->notask_error = 0;
}
/*
* Wait for stopped. Depending on @ptrace, different stopped state
* is used and the two don't interact with each other.
*/
ret = wait_task_stopped(wo, ptrace, p);
if (ret)
return ret;
/*
* Wait for continued. There's only one continued state and the
* ptracer can consume it which can confuse the real parent. Don't
* use WCONTINUED from ptracer. You don't need or want it.
*/
return wait_task_continued(wo, p);
}
/*
* Do the work of do_wait() for one thread in the group, @tsk.
*
* -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue; then
* ->notask_error is 0 if there were any eligible children,
* or still -ECHILD.
*/
static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
list_for_each_entry(p, &tsk->children, sibling) {
int ret = wait_consider_task(wo, 0, p);
if (ret)
return ret;
}
return 0;
}
static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
int ret = wait_consider_task(wo, 1, p);
if (ret)
return ret;
}
return 0;
}
bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
{
if (!eligible_pid(wo, p))
return false;
if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent)
return false;
return true;
}
static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
int sync, void *key)
{
struct wait_opts *wo = container_of(wait, struct wait_opts,
child_wait);
struct task_struct *p = key;
if (pid_child_should_wake(wo, p))
return default_wake_function(wait, mode, sync, key);
return 0;
}
void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
{
__wake_up_sync_key(&parent->signal->wait_chldexit,
TASK_INTERRUPTIBLE, p);
}
static bool is_effectively_child(struct wait_opts *wo, bool ptrace,
struct task_struct *target)
{
struct task_struct *parent =
!ptrace ? target->real_parent : target->parent;
return current == parent || (!(wo->wo_flags & __WNOTHREAD) &&
same_thread_group(current, parent));
}
/*
* Optimization for waiting on PIDTYPE_PID. No need to iterate through child
* and tracee lists to find the target task.
*/
static int do_wait_pid(struct wait_opts *wo)
{
bool ptrace;
struct task_struct *target;
int retval;
ptrace = false;
target = pid_task(wo->wo_pid, PIDTYPE_TGID);
if (target && is_effectively_child(wo, ptrace, target)) {
retval = wait_consider_task(wo, ptrace, target);
if (retval)
return retval;
}
ptrace = true;
target = pid_task(wo->wo_pid, PIDTYPE_PID);
if (target && target->ptrace &&
is_effectively_child(wo, ptrace, target)) {
retval = wait_consider_task(wo, ptrace, target);
if (retval)
return retval;
}
return 0;
}
long __do_wait(struct wait_opts *wo)
{
long retval;
/*
* If there is nothing that can match our criteria, just get out.
* We will clear ->notask_error to zero if we see any child that
* might later match our criteria, even if we are not able to reap
* it yet.
*/
wo->notask_error = -ECHILD;
if ((wo->wo_type < PIDTYPE_MAX) &&
(!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
goto notask;
read_lock(&tasklist_lock);
if (wo->wo_type == PIDTYPE_PID) {
retval = do_wait_pid(wo);
if (retval)
return retval;
} else {
struct task_struct *tsk = current;
do {
retval = do_wait_thread(wo, tsk);
if (retval)
return retval;
retval = ptrace_do_wait(wo, tsk);
if (retval)
return retval;
if (wo->wo_flags & __WNOTHREAD)
break;
} while_each_thread(current, tsk);
}
read_unlock(&tasklist_lock);
notask:
retval = wo->notask_error;
if (!retval && !(wo->wo_flags & WNOHANG))
return -ERESTARTSYS;
return retval;
}
static long do_wait(struct wait_opts *wo)
{
int retval;
trace_sched_process_wait(wo->wo_pid);
init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
wo->child_wait.private = current;
add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
do {
set_current_state(TASK_INTERRUPTIBLE);
retval = __do_wait(wo);
if (retval != -ERESTARTSYS)
break;
if (signal_pending(current))
break;
schedule();
} while (1);
__set_current_state(TASK_RUNNING);
remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
return retval;
}
int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
struct waitid_info *infop, int options,
struct rusage *ru)
{
unsigned int f_flags = 0;
struct pid *pid = NULL;
enum pid_type type;
if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
__WNOTHREAD|__WCLONE|__WALL))
return -EINVAL;
if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
return -EINVAL;
switch (which) {
case P_ALL:
type = PIDTYPE_MAX;
break;
case P_PID:
type = PIDTYPE_PID;
if (upid <= 0)
return -EINVAL;
pid = find_get_pid(upid);
break;
case P_PGID:
type = PIDTYPE_PGID;
if (upid < 0)
return -EINVAL;
if (upid)
pid = find_get_pid(upid);
else
pid = get_task_pid(current, PIDTYPE_PGID);
break;
case P_PIDFD:
type = PIDTYPE_PID;
if (upid < 0)
return -EINVAL;
pid = pidfd_get_pid(upid, &f_flags);
if (IS_ERR(pid))
return PTR_ERR(pid);
break;
default:
return -EINVAL;
}
wo->wo_type = type;
wo->wo_pid = pid;
wo->wo_flags = options;
wo->wo_info = infop;
wo->wo_rusage = ru;
if (f_flags & O_NONBLOCK)
wo->wo_flags |= WNOHANG;
return 0;
}
static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
int options, struct rusage *ru)
{
struct wait_opts wo;
long ret;
ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru);
if (ret)
return ret;
ret = do_wait(&wo);
if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG))
ret = -EAGAIN;
put_pid(wo.wo_pid);
return ret;
}
SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
infop, int, options, struct rusage __user *, ru)
{
struct rusage r;
struct waitid_info info = {.status = 0};
long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL);
int signo = 0;
if (err > 0) {
signo = SIGCHLD;
err = 0;
if (ru && copy_to_user(ru, &r, sizeof(struct rusage)))
return -EFAULT;
}
if (!infop)
return err;
if (!user_write_access_begin(infop, sizeof(*infop)))
return -EFAULT;
unsafe_put_user(signo, &infop->si_signo, Efault);
unsafe_put_user(0, &infop->si_errno, Efault);
unsafe_put_user(info.cause, &infop->si_code, Efault);
unsafe_put_user(info.pid, &infop->si_pid, Efault);
unsafe_put_user(info.uid, &infop->si_uid, Efault);
unsafe_put_user(info.status, &infop->si_status, Efault);
user_write_access_end();
return err;
Efault:
user_write_access_end();
return -EFAULT;
}
long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
struct rusage *ru)
{
struct wait_opts wo;
struct pid *pid = NULL;
enum pid_type type;
long ret;
if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
__WNOTHREAD|__WCLONE|__WALL))
return -EINVAL;
/* -INT_MIN is not defined */
if (upid == INT_MIN)
return -ESRCH;
if (upid == -1)
type = PIDTYPE_MAX;
else if (upid < 0) {
type = PIDTYPE_PGID;
pid = find_get_pid(-upid);
} else if (upid == 0) {
type = PIDTYPE_PGID;
pid = get_task_pid(current, PIDTYPE_PGID);
} else /* upid > 0 */ {
type = PIDTYPE_PID;
pid = find_get_pid(upid);
}
wo.wo_type = type;
wo.wo_pid = pid;
wo.wo_flags = options | WEXITED;
wo.wo_info = NULL;
wo.wo_stat = 0;
wo.wo_rusage = ru;
ret = do_wait(&wo);
put_pid(pid);
if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr))
ret = -EFAULT;
return ret;
}
int kernel_wait(pid_t pid, int *stat)
{
struct wait_opts wo = {
.wo_type = PIDTYPE_PID,
.wo_pid = find_get_pid(pid),
.wo_flags = WEXITED,
};
int ret;
ret = do_wait(&wo);
if (ret > 0 && wo.wo_stat)
*stat = wo.wo_stat;
put_pid(wo.wo_pid);
return ret;
}
SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
int, options, struct rusage __user *, ru)
{
struct rusage r;
long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL);
if (err > 0) {
if (ru && copy_to_user(ru, &r, sizeof(struct rusage)))
return -EFAULT;
}
return err;
}
#ifdef __ARCH_WANT_SYS_WAITPID
/*
* sys_waitpid() remains for compatibility. waitpid() should be
* implemented by calling sys_wait4() from libc.a.
*/
SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
{
return kernel_wait4(pid, stat_addr, options, NULL);
}
#endif
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(wait4,
compat_pid_t, pid,
compat_uint_t __user *, stat_addr,
int, options,
struct compat_rusage __user *, ru)
{
struct rusage r;
long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL);
if (err > 0) {
if (ru && put_compat_rusage(&r, ru))
return -EFAULT;
}
return err;
}
COMPAT_SYSCALL_DEFINE5(waitid,
int, which, compat_pid_t, pid,
struct compat_siginfo __user *, infop, int, options,
struct compat_rusage __user *, uru)
{
struct rusage ru;
struct waitid_info info = {.status = 0};
long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL);
int signo = 0;
if (err > 0) {
signo = SIGCHLD;
err = 0;
if (uru) {
/* kernel_waitid() overwrites everything in ru */
if (COMPAT_USE_64BIT_TIME)
err = copy_to_user(uru, &ru, sizeof(ru));
else
err = put_compat_rusage(&ru, uru);
if (err)
return -EFAULT;
}
}
if (!infop)
return err;
if (!user_write_access_begin(infop, sizeof(*infop)))
return -EFAULT;
unsafe_put_user(signo, &infop->si_signo, Efault);
unsafe_put_user(0, &infop->si_errno, Efault);
unsafe_put_user(info.cause, &infop->si_code, Efault);
unsafe_put_user(info.pid, &infop->si_pid, Efault);
unsafe_put_user(info.uid, &infop->si_uid, Efault);
unsafe_put_user(info.status, &infop->si_status, Efault);
user_write_access_end();
return err;
Efault:
user_write_access_end();
return -EFAULT;
}
#endif
/*
* This needs to be __function_aligned as GCC implicitly makes any
* implementation of abort() cold and drops alignment specified by
* -falign-functions=N.
*
* See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11
*/
__weak __function_aligned void abort(void)
{
BUG();
/* if that doesn't kill us, halt */
panic("Oops failed to kill thread");
}
EXPORT_SYMBOL(abort);
// SPDX-License-Identifier: GPL-2.0-only
/*
* jump label support
*
* Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
* Copyright (C) 2011 Peter Zijlstra
*
*/
#include <linux/memory.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/err.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
#include <linux/bug.h>
#include <linux/cpu.h>
#include <asm/sections.h>
/* mutex to protect coming/going of the jump_label table */
static DEFINE_MUTEX(jump_label_mutex);
void jump_label_lock(void)
{
mutex_lock(&jump_label_mutex);
}
void jump_label_unlock(void)
{
mutex_unlock(&jump_label_mutex);
}
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
const struct jump_entry *jeb = b;
/*
* Entrires are sorted by key.
*/
if (jump_entry_key(jea) < jump_entry_key(jeb))
return -1;
if (jump_entry_key(jea) > jump_entry_key(jeb))
return 1;
/*
* In the batching mode, entries should also be sorted by the code
* inside the already sorted list of entries, enabling a bsearch in
* the vector.
*/
if (jump_entry_code(jea) < jump_entry_code(jeb))
return -1;
if (jump_entry_code(jea) > jump_entry_code(jeb))
return 1;
return 0;
}
static void jump_label_swap(void *a, void *b, int size)
{
long delta = (unsigned long)a - (unsigned long)b;
struct jump_entry *jea = a;
struct jump_entry *jeb = b;
struct jump_entry tmp = *jea;
jea->code = jeb->code - delta;
jea->target = jeb->target - delta;
jea->key = jeb->key - delta;
jeb->code = tmp.code + delta;
jeb->target = tmp.target + delta;
jeb->key = tmp.key + delta;
}
static void
jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
{
unsigned long size;
void *swapfn = NULL;
if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE))
swapfn = jump_label_swap;
size = (((unsigned long)stop - (unsigned long)start)
/ sizeof(struct jump_entry));
sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn);
}
static void jump_label_update(struct static_key *key);
/*
* There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h.
* The use of 'atomic_read()' requires atomic.h and its problematic for some
* kernel headers such as kernel.h and others. Since static_key_count() is not
* used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok
* to have it be a function here. Similarly, for 'static_key_enable()' and
* 'static_key_disable()', which require bug.h. This should allow jump_label.h
* to be included from most/all places for CONFIG_JUMP_LABEL.
*/
int static_key_count(struct static_key *key)
{
/*
* -1 means the first static_key_slow_inc() is in progress.
* static_key_enabled() must return true, so return 1 here.
*/
int n = atomic_read(&key->enabled);
return n >= 0 ? n : 1;
}
EXPORT_SYMBOL_GPL(static_key_count);
/*
* static_key_fast_inc_not_disabled - adds a user for a static key
* @key: static key that must be already enabled
*
* The caller must make sure that the static key can't get disabled while
* in this function. It doesn't patch jump labels, only adds a user to
* an already enabled static key.
*
* Returns true if the increment was done. Unlike refcount_t the ref counter
* is not saturated, but will fail to increment on overflow.
*/
bool static_key_fast_inc_not_disabled(struct static_key *key)
{
int v;
STATIC_KEY_CHECK_USE(key);
/*
* Negative key->enabled has a special meaning: it sends
* static_key_slow_inc/dec() down the slow path, and it is non-zero
* so it counts as "enabled" in jump_label_update().
*
* The INT_MAX overflow condition is either used by the networking
* code to reset or detected in the slow path of
* static_key_slow_inc_cpuslocked().
*/
v = atomic_read(&key->enabled);
do {
if (v <= 0 || v == INT_MAX)
return false;
} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1)));
return true;
}
EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled);
bool static_key_slow_inc_cpuslocked(struct static_key *key)
{
lockdep_assert_cpus_held();
/*
* Careful if we get concurrent static_key_slow_inc/dec() calls;
* later calls must wait for the first one to _finish_ the
* jump_label_update() process. At the same time, however,
* the jump_label_update() call below wants to see
* static_key_enabled(&key) for jumps to be updated properly.
*/
if (static_key_fast_inc_not_disabled(key))
return true;
guard(mutex)(&jump_label_mutex);
/* Try to mark it as 'enabling in progress. */
if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key);
/*
* Ensure that when static_key_fast_inc_not_disabled() or
* static_key_dec_not_one() observe the positive value,
* they must also observe all the text changes.
*/
atomic_set_release(&key->enabled, 1);
} else {
/*
* While holding the mutex this should never observe
* anything else than a value >= 1 and succeed
*/
if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key)))
return false;
}
return true;
}
bool static_key_slow_inc(struct static_key *key)
{
bool ret;
cpus_read_lock();
ret = static_key_slow_inc_cpuslocked(key);
cpus_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(static_key_slow_inc);
void static_key_enable_cpuslocked(struct static_key *key)
{ STATIC_KEY_CHECK_USE(key);
lockdep_assert_cpus_held();
if (atomic_read(&key->enabled) > 0) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
return;
}
jump_label_lock();
if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1);
jump_label_update(key);
/*
* See static_key_slow_inc().
*/
atomic_set_release(&key->enabled, 1);
}
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked);
void static_key_enable(struct static_key *key)
{
cpus_read_lock();
static_key_enable_cpuslocked(key);
cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(static_key_enable);
void static_key_disable_cpuslocked(struct static_key *key)
{
STATIC_KEY_CHECK_USE(key);
lockdep_assert_cpus_held();
if (atomic_read(&key->enabled) != 1) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
return;
}
jump_label_lock();
if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
jump_label_update(key);
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked);
void static_key_disable(struct static_key *key)
{
cpus_read_lock();
static_key_disable_cpuslocked(key);
cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(static_key_disable);
static bool static_key_dec_not_one(struct static_key *key)
{
int v;
/*
* Go into the slow path if key::enabled is less than or equal than
* one. One is valid to shut down the key, anything less than one
* is an imbalance, which is handled at the call site.
*
* That includes the special case of '-1' which is set in
* static_key_slow_inc_cpuslocked(), but that's harmless as it is
* fully serialized in the slow path below. By the time this task
* acquires the jump label lock the value is back to one and the
* retry under the lock must succeed.
*/
v = atomic_read(&key->enabled);
do {
/*
* Warn about the '-1' case though; since that means a
* decrement is concurrent with a first (0->1) increment. IOW
* people are trying to disable something that wasn't yet fully
* enabled. This suggests an ordering problem on the user side.
*/
WARN_ON_ONCE(v < 0);
/*
* Warn about underflow, and lie about success in an attempt to
* not make things worse.
*/
if (WARN_ON_ONCE(v == 0))
return true;
if (v <= 1)
return false;
} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1)));
return true;
}
static void __static_key_slow_dec_cpuslocked(struct static_key *key)
{
lockdep_assert_cpus_held();
int val;
if (static_key_dec_not_one(key))
return;
guard(mutex)(&jump_label_mutex);
val = atomic_read(&key->enabled);
/*
* It should be impossible to observe -1 with jump_label_mutex held,
* see static_key_slow_inc_cpuslocked().
*/
if (WARN_ON_ONCE(val == -1))
return;
/*
* Cannot already be 0, something went sideways.
*/
if (WARN_ON_ONCE(val == 0))
return;
if (atomic_dec_and_test(&key->enabled)) jump_label_update(key);
}
static void __static_key_slow_dec(struct static_key *key)
{
cpus_read_lock();
__static_key_slow_dec_cpuslocked(key);
cpus_read_unlock();
}
void jump_label_update_timeout(struct work_struct *work)
{
struct static_key_deferred *key =
container_of(work, struct static_key_deferred, work.work);
__static_key_slow_dec(&key->key);
}
EXPORT_SYMBOL_GPL(jump_label_update_timeout);
void static_key_slow_dec(struct static_key *key)
{ STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec(key);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_cpuslocked(struct static_key *key)
{
STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec_cpuslocked(key);
}
void __static_key_slow_dec_deferred(struct static_key *key,
struct delayed_work *work,
unsigned long timeout)
{
STATIC_KEY_CHECK_USE(key);
if (static_key_dec_not_one(key))
return;
schedule_delayed_work(work, timeout);
}
EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
void __static_key_deferred_flush(void *key, struct delayed_work *work)
{
STATIC_KEY_CHECK_USE(key);
flush_delayed_work(work);
}
EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
STATIC_KEY_CHECK_USE(key);
key->timeout = rl;
INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
}
EXPORT_SYMBOL_GPL(jump_label_rate_limit);
static int addr_conflict(struct jump_entry *entry, void *start, void *end)
{
if (jump_entry_code(entry) <= (unsigned long)end &&
jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start)
return 1;
return 0;
}
static int __jump_label_text_reserved(struct jump_entry *iter_start,
struct jump_entry *iter_stop, void *start, void *end, bool init)
{
struct jump_entry *iter;
iter = iter_start;
while (iter < iter_stop) {
if (init || !jump_entry_is_init(iter)) {
if (addr_conflict(iter, start, end))
return 1;
}
iter++;
}
return 0;
}
#ifndef arch_jump_label_transform_static
static void arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
/* nothing to do on most architectures */
}
#endif
static inline struct jump_entry *static_key_entries(struct static_key *key)
{
WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK);
}
static inline bool static_key_type(struct static_key *key)
{
return key->type & JUMP_TYPE_TRUE;
}
static inline bool static_key_linked(struct static_key *key)
{
return key->type & JUMP_TYPE_LINKED;
}
static inline void static_key_clear_linked(struct static_key *key)
{
key->type &= ~JUMP_TYPE_LINKED;
}
static inline void static_key_set_linked(struct static_key *key)
{
key->type |= JUMP_TYPE_LINKED;
}
/***
* A 'struct static_key' uses a union such that it either points directly
* to a table of 'struct jump_entry' or to a linked list of modules which in
* turn point to 'struct jump_entry' tables.
*
* The two lower bits of the pointer are used to keep track of which pointer
* type is in use and to store the initial branch direction, we use an access
* function which preserves these bits.
*/
static void static_key_set_entries(struct static_key *key,
struct jump_entry *entries)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->entries = entries;
key->type |= type;
}
static enum jump_label_type jump_label_type(struct jump_entry *entry)
{
struct static_key *key = jump_entry_key(entry);
bool enabled = static_key_enabled(key);
bool branch = jump_entry_is_branch(entry);
/* See the comment in linux/jump_label.h */
return enabled ^ branch;
}
static bool jump_label_can_update(struct jump_entry *entry, bool init)
{
/*
* Cannot update code that was in an init text area.
*/
if (!init && jump_entry_is_init(entry))
return false;
if (!kernel_text_address(jump_entry_code(entry))) {
/*
* This skips patching built-in __exit, which
* is part of init_section_contains() but is
* not part of kernel_text_address().
*
* Skipping built-in __exit is fine since it
* will never be executed.
*/
WARN_ONCE(!jump_entry_is_init(entry),
"can't patch jump_label at %pS",
(void *)jump_entry_code(entry));
return false;
}
return true;
}
#ifndef HAVE_JUMP_LABEL_BATCH
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop,
bool init)
{
for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
if (jump_label_can_update(entry, init))
arch_jump_label_transform(entry, jump_label_type(entry));
}
}
#else
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop,
bool init)
{ for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init))
continue;
if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) {
/*
* Queue is full: Apply the current queue and try again.
*/
arch_jump_label_transform_apply();
BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry)));
}
}
arch_jump_label_transform_apply();
}
#endif
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
struct static_key *key = NULL;
struct jump_entry *iter;
/*
* Since we are initializing the static_key.enabled field with
* with the 'raw' int values (to avoid pulling in atomic.h) in
* jump_label.h, let's make sure that is safe. There are only two
* cases to check since we initialize to 0 or 1.
*/
BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0);
BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1);
if (static_key_initialized)
return;
cpus_read_lock();
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk;
bool in_init;
/* rewrite NOPs */
if (jump_label_type(iter) == JUMP_LABEL_NOP)
arch_jump_label_transform_static(iter, JUMP_LABEL_NOP);
in_init = init_section_contains((void *)jump_entry_code(iter), 1);
jump_entry_set_init(iter, in_init);
iterk = jump_entry_key(iter);
if (iterk == key)
continue;
key = iterk;
static_key_set_entries(key, iter);
}
static_key_initialized = true;
jump_label_unlock();
cpus_read_unlock();
}
static inline bool static_key_sealed(struct static_key *key)
{
return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK);
}
static inline void static_key_seal(struct static_key *key)
{
unsigned long type = key->type & JUMP_TYPE_TRUE;
key->type = JUMP_TYPE_LINKED | type;
}
void jump_label_init_ro(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
struct jump_entry *iter;
if (WARN_ON_ONCE(!static_key_initialized))
return;
cpus_read_lock();
jump_label_lock();
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk = jump_entry_key(iter);
if (!is_kernel_ro_after_init((unsigned long)iterk))
continue;
if (static_key_sealed(iterk))
continue;
static_key_seal(iterk);
}
jump_label_unlock();
cpus_read_unlock();
}
#ifdef CONFIG_MODULES
enum jump_label_type jump_label_init_type(struct jump_entry *entry)
{
struct static_key *key = jump_entry_key(entry);
bool type = static_key_type(key);
bool branch = jump_entry_is_branch(entry);
/* See the comment in linux/jump_label.h */
return type ^ branch;
}
struct static_key_mod {
struct static_key_mod *next;
struct jump_entry *entries;
struct module *mod;
};
static inline struct static_key_mod *static_key_mod(struct static_key *key)
{
WARN_ON_ONCE(!static_key_linked(key));
return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK);
}
/***
* key->type and key->next are the same via union.
* This sets key->next and preserves the type bits.
*
* See additional comments above static_key_set_entries().
*/
static void static_key_set_mod(struct static_key *key,
struct static_key_mod *mod)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->next = mod;
key->type |= type;
}
static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
int ret;
scoped_guard(rcu) {
mod = __module_text_address((unsigned long)start);
WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
if (!try_module_get(mod))
mod = NULL;
}
if (!mod)
return 0;
ret = __jump_label_text_reserved(mod->jump_entries,
mod->jump_entries + mod->num_jump_entries,
start, end, mod->state == MODULE_STATE_COMING);
module_put(mod);
return ret;
}
static void __jump_label_mod_update(struct static_key *key)
{
struct static_key_mod *mod;
for (mod = static_key_mod(key); mod; mod = mod->next) {
struct jump_entry *stop;
struct module *m;
/*
* NULL if the static_key is defined in a module
* that does not use it
*/
if (!mod->entries)
continue;
m = mod->mod;
if (!m)
stop = __stop___jump_table;
else
stop = m->jump_entries + m->num_jump_entries;
__jump_label_update(key, mod->entries, stop,
m && m->state == MODULE_STATE_COMING);
}
}
static int jump_label_add_module(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct static_key *key = NULL;
struct static_key_mod *jlm, *jlm2;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
return 0;
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk;
bool in_init;
in_init = within_module_init(jump_entry_code(iter), mod);
jump_entry_set_init(iter, in_init);
iterk = jump_entry_key(iter);
if (iterk == key)
continue;
key = iterk;
if (within_module((unsigned long)key, mod)) {
static_key_set_entries(key, iter);
continue;
}
/*
* If the key was sealed at init, then there's no need to keep a
* reference to its module entries - just patch them now and be
* done with it.
*/
if (static_key_sealed(key))
goto do_poke;
jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
if (!jlm)
return -ENOMEM;
if (!static_key_linked(key)) {
jlm2 = kzalloc(sizeof(struct static_key_mod),
GFP_KERNEL);
if (!jlm2) {
kfree(jlm);
return -ENOMEM;
}
scoped_guard(rcu)
jlm2->mod = __module_address((unsigned long)key);
jlm2->entries = static_key_entries(key);
jlm2->next = NULL;
static_key_set_mod(key, jlm2);
static_key_set_linked(key);
}
jlm->mod = mod;
jlm->entries = iter;
jlm->next = static_key_mod(key);
static_key_set_mod(key, jlm);
static_key_set_linked(key);
/* Only update if we've changed from our initial state */
do_poke:
if (jump_label_type(iter) != jump_label_init_type(iter))
__jump_label_update(key, iter, iter_stop, true);
}
return 0;
}
static void jump_label_del_module(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct static_key *key = NULL;
struct static_key_mod *jlm, **prev;
for (iter = iter_start; iter < iter_stop; iter++) {
if (jump_entry_key(iter) == key)
continue;
key = jump_entry_key(iter);
if (within_module((unsigned long)key, mod))
continue;
/* No @jlm allocated because key was sealed at init. */
if (static_key_sealed(key))
continue;
/* No memory during module load */
if (WARN_ON(!static_key_linked(key)))
continue;
prev = &key->next;
jlm = static_key_mod(key);
while (jlm && jlm->mod != mod) {
prev = &jlm->next;
jlm = jlm->next;
}
/* No memory during module load */
if (WARN_ON(!jlm))
continue;
if (prev == &key->next)
static_key_set_mod(key, jlm->next);
else
*prev = jlm->next;
kfree(jlm);
jlm = static_key_mod(key);
/* if only one etry is left, fold it back into the static_key */
if (jlm->next == NULL) {
static_key_set_entries(key, jlm->entries);
static_key_clear_linked(key);
kfree(jlm);
}
}
}
static int
jump_label_module_notify(struct notifier_block *self, unsigned long val,
void *data)
{
struct module *mod = data;
int ret = 0;
cpus_read_lock();
jump_label_lock();
switch (val) {
case MODULE_STATE_COMING:
ret = jump_label_add_module(mod);
if (ret) {
WARN(1, "Failed to allocate memory: jump_label may not work properly.\n");
jump_label_del_module(mod);
}
break;
case MODULE_STATE_GOING:
jump_label_del_module(mod);
break;
}
jump_label_unlock();
cpus_read_unlock();
return notifier_from_errno(ret);
}
static struct notifier_block jump_label_module_nb = {
.notifier_call = jump_label_module_notify,
.priority = 1, /* higher than tracepoints */
};
static __init int jump_label_init_module(void)
{
return register_module_notifier(&jump_label_module_nb);
}
early_initcall(jump_label_init_module);
#endif /* CONFIG_MODULES */
/***
* jump_label_text_reserved - check if addr range is reserved
* @start: start text addr
* @end: end text addr
*
* checks if the text addr located between @start and @end
* overlaps with any of the jump label patch addresses. Code
* that wants to modify kernel text should first verify that
* it does not overlap with any of the jump label addresses.
* Caller must hold jump_label_mutex.
*
* returns 1 if there is an overlap, 0 otherwise
*/
int jump_label_text_reserved(void *start, void *end)
{
bool init = system_state < SYSTEM_RUNNING;
int ret = __jump_label_text_reserved(__start___jump_table,
__stop___jump_table, start, end, init);
if (ret)
return ret;
#ifdef CONFIG_MODULES
ret = __jump_label_mod_text_reserved(start, end);
#endif
return ret;
}
static void jump_label_update(struct static_key *key)
{
struct jump_entry *stop = __stop___jump_table;
bool init = system_state < SYSTEM_RUNNING;
struct jump_entry *entry;
#ifdef CONFIG_MODULES
struct module *mod;
if (static_key_linked(key)) {
__jump_label_mod_update(key);
return;
}
scoped_guard(rcu) {
mod = __module_address((unsigned long)key);
if (mod) { stop = mod->jump_entries + mod->num_jump_entries;
init = mod->state == MODULE_STATE_COMING;
}
}
#endif
entry = static_key_entries(key);
/* if there are no users, entry can be NULL */
if (entry)
__jump_label_update(key, entry, stop, init);
}
#ifdef CONFIG_STATIC_KEYS_SELFTEST
static DEFINE_STATIC_KEY_TRUE(sk_true);
static DEFINE_STATIC_KEY_FALSE(sk_false);
static __init int jump_label_test(void)
{
int i;
for (i = 0; i < 2; i++) {
WARN_ON(static_key_enabled(&sk_true.key) != true);
WARN_ON(static_key_enabled(&sk_false.key) != false);
WARN_ON(!static_branch_likely(&sk_true));
WARN_ON(!static_branch_unlikely(&sk_true));
WARN_ON(static_branch_likely(&sk_false));
WARN_ON(static_branch_unlikely(&sk_false));
static_branch_disable(&sk_true);
static_branch_enable(&sk_false);
WARN_ON(static_key_enabled(&sk_true.key) == true);
WARN_ON(static_key_enabled(&sk_false.key) == false);
WARN_ON(static_branch_likely(&sk_true));
WARN_ON(static_branch_unlikely(&sk_true));
WARN_ON(!static_branch_likely(&sk_false));
WARN_ON(!static_branch_unlikely(&sk_false));
static_branch_enable(&sk_true);
static_branch_disable(&sk_false);
}
return 0;
}
early_initcall(jump_label_test);
#endif /* STATIC_KEYS_SELFTEST */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic helpers for smp ipi calls
*
* (C) Jens Axboe <jens.axboe@oracle.com> 2008
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/irq_work.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/gfp.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/sched.h>
#include <linux/sched/idle.h>
#include <linux/hypervisor.h>
#include <linux/sched/clock.h>
#include <linux/nmi.h>
#include <linux/sched/debug.h>
#include <linux/jump_label.h>
#include <linux/string_choices.h>
#include <trace/events/ipi.h>
#define CREATE_TRACE_POINTS
#include <trace/events/csd.h>
#undef CREATE_TRACE_POINTS
#include "smpboot.h"
#include "sched/smp.h"
#define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK)
struct call_function_data {
call_single_data_t __percpu *csd;
cpumask_var_t cpumask;
cpumask_var_t cpumask_ipi;
};
static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data);
static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1);
static void __flush_smp_call_function_queue(bool warn_cpu_offline);
int smpcfd_prepare_cpu(unsigned int cpu)
{
struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
cpu_to_node(cpu)))
return -ENOMEM;
if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
cpu_to_node(cpu))) {
free_cpumask_var(cfd->cpumask);
return -ENOMEM;
}
cfd->csd = alloc_percpu(call_single_data_t);
if (!cfd->csd) {
free_cpumask_var(cfd->cpumask);
free_cpumask_var(cfd->cpumask_ipi);
return -ENOMEM;
}
return 0;
}
int smpcfd_dead_cpu(unsigned int cpu)
{
struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
free_cpumask_var(cfd->cpumask);
free_cpumask_var(cfd->cpumask_ipi);
free_percpu(cfd->csd);
return 0;
}
int smpcfd_dying_cpu(unsigned int cpu)
{
/*
* The IPIs for the smp-call-function callbacks queued by other
* CPUs might arrive late, either due to hardware latencies or
* because this CPU disabled interrupts (inside stop-machine)
* before the IPIs were sent. So flush out any pending callbacks
* explicitly (without waiting for the IPIs to arrive), to
* ensure that the outgoing CPU doesn't go offline with work
* still pending.
*/
__flush_smp_call_function_queue(false);
irq_work_run();
return 0;
}
void __init call_function_init(void)
{
int i;
for_each_possible_cpu(i)
init_llist_head(&per_cpu(call_single_queue, i));
smpcfd_prepare_cpu(smp_processor_id());
}
static __always_inline void
send_call_function_single_ipi(int cpu)
{
if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_,
generic_smp_call_function_single_interrupt);
arch_send_call_function_single_ipi(cpu);
}
}
static __always_inline void
send_call_function_ipi_mask(struct cpumask *mask)
{
trace_ipi_send_cpumask(mask, _RET_IP_,
generic_smp_call_function_single_interrupt);
arch_send_call_function_ipi_mask(mask);
}
static __always_inline void
csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd)
{
trace_csd_function_entry(func, csd);
func(info);
trace_csd_function_exit(func, csd);
}
#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled);
/*
* Parse the csdlock_debug= kernel boot parameter.
*
* If you need to restore the old "ext" value that once provided
* additional debugging information, reapply the following commits:
*
* de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging")
* a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging")
*/
static int __init csdlock_debug(char *str)
{
int ret;
unsigned int val = 0;
ret = get_option(&str, &val);
if (ret) {
if (val)
static_branch_enable(&csdlock_debug_enabled);
else
static_branch_disable(&csdlock_debug_enabled);
}
return 1;
}
__setup("csdlock_debug=", csdlock_debug);
static DEFINE_PER_CPU(call_single_data_t *, cur_csd);
static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);
static DEFINE_PER_CPU(void *, cur_csd_info);
static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */
module_param(csd_lock_timeout, ulong, 0644);
static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */
module_param(panic_on_ipistall, int, 0644);
static atomic_t csd_bug_count = ATOMIC_INIT(0);
/* Record current CSD work for current CPU, NULL to erase. */
static void __csd_lock_record(call_single_data_t *csd)
{
if (!csd) {
smp_mb(); /* NULL cur_csd after unlock. */
__this_cpu_write(cur_csd, NULL);
return;
}
__this_cpu_write(cur_csd_func, csd->func);
__this_cpu_write(cur_csd_info, csd->info);
smp_wmb(); /* func and info before csd. */
__this_cpu_write(cur_csd, csd);
smp_mb(); /* Update cur_csd before function call. */
/* Or before unlock, as the case may be. */
}
static __always_inline void csd_lock_record(call_single_data_t *csd)
{
if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd);
}
static int csd_lock_wait_getcpu(call_single_data_t *csd)
{
unsigned int csd_type;
csd_type = CSD_TYPE(csd);
if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC)
return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */
return -1;
}
static atomic_t n_csd_lock_stuck;
/**
* csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long?
*
* Returns @true if a CSD-lock acquisition is stuck and has been stuck
* long enough for a "non-responsive CSD lock" message to be printed.
*/
bool csd_lock_is_stuck(void)
{
return !!atomic_read(&n_csd_lock_stuck);
}
/*
* Complain if too much time spent waiting. Note that only
* the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
* so waiting on other types gets much less information.
*/
static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages)
{
int cpu = -1;
int cpux;
bool firsttime;
u64 ts2, ts_delta;
call_single_data_t *cpu_cur_csd;
unsigned int flags = READ_ONCE(csd->node.u_flags);
unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC;
if (!(flags & CSD_FLAG_LOCK)) {
if (!unlikely(*bug_id))
return true;
cpu = csd_lock_wait_getcpu(csd);
pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n",
*bug_id, raw_smp_processor_id(), cpu);
atomic_dec(&n_csd_lock_stuck);
return true;
}
ts2 = ktime_get_mono_fast_ns();
/* How long since we last checked for a stuck CSD lock.*/
ts_delta = ts2 - *ts1;
if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) *
(!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) ||
csd_lock_timeout_ns == 0))
return false;
if (ts0 > ts2) {
/* Our own sched_clock went backward; don't blame another CPU. */
ts_delta = ts0 - ts2;
pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta);
*ts1 = ts2;
return false;
}
firsttime = !*bug_id;
if (firsttime)
*bug_id = atomic_inc_return(&csd_bug_count);
cpu = csd_lock_wait_getcpu(csd);
if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu))
cpux = 0;
else
cpux = cpu;
cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
/* How long since this CSD lock was stuck. */
ts_delta = ts2 - ts0;
pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n",
firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta,
cpu, csd->func, csd->info);
(*nmessages)++;
if (firsttime)
atomic_inc(&n_csd_lock_stuck);
/*
* If the CSD lock is still stuck after 5 minutes, it is unlikely
* to become unstuck. Use a signed comparison to avoid triggering
* on underflows when the TSC is out of sync between sockets.
*/
BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC));
if (cpu_cur_csd && csd != cpu_cur_csd) {
pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n",
*bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)),
READ_ONCE(per_cpu(cur_csd_info, cpux)));
} else {
pr_alert("\tcsd: CSD lock (#%d) %s.\n",
*bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request");
}
if (cpu >= 0) {
if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0))
dump_cpu_task(cpu);
if (!cpu_cur_csd) {
pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
arch_send_call_function_single_ipi(cpu);
}
}
if (firsttime)
dump_stack();
*ts1 = ts2;
return false;
}
/*
* csd_lock/csd_unlock used to serialize access to per-cpu csd resources
*
* For non-synchronous ipi calls the csd can still be in use by the
* previous function call. For multi-cpu calls its even more interesting
* as we'll have to ensure no other cpu is observing our csd.
*/
static void __csd_lock_wait(call_single_data_t *csd)
{
unsigned long nmessages = 0;
int bug_id = 0;
u64 ts0, ts1;
ts1 = ts0 = ktime_get_mono_fast_ns();
for (;;) {
if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages))
break;
cpu_relax();
}
smp_acquire__after_ctrl_dep();
}
static __always_inline void csd_lock_wait(call_single_data_t *csd)
{
if (static_branch_unlikely(&csdlock_debug_enabled)) {
__csd_lock_wait(csd);
return;
}
smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
}
#else
static void csd_lock_record(call_single_data_t *csd)
{
}
static __always_inline void csd_lock_wait(call_single_data_t *csd)
{
smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
}
#endif
static __always_inline void csd_lock(call_single_data_t *csd)
{
csd_lock_wait(csd);
csd->node.u_flags |= CSD_FLAG_LOCK;
/*
* prevent CPU from reordering the above assignment
* to ->flags with any subsequent assignments to other
* fields of the specified call_single_data_t structure:
*/
smp_wmb();
}
static __always_inline void csd_unlock(call_single_data_t *csd)
{
WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK));
/*
* ensure we're all done before releasing data:
*/
smp_store_release(&csd->node.u_flags, 0);
}
static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
void __smp_call_single_queue(int cpu, struct llist_node *node)
{
/*
* We have to check the type of the CSD before queueing it, because
* once queued it can have its flags cleared by
* flush_smp_call_function_queue()
* even if we haven't sent the smp_call IPI yet (e.g. the stopper
* executes migration_cpu_stop() on the remote CPU).
*/
if (trace_csd_queue_cpu_enabled()) {
call_single_data_t *csd;
smp_call_func_t func;
csd = container_of(node, call_single_data_t, node.llist);
func = CSD_TYPE(csd) == CSD_TYPE_TTWU ?
sched_ttwu_pending : csd->func;
trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
}
/*
* The list addition should be visible to the target CPU when it pops
* the head of the list to pull the entry off it in the IPI handler
* because of normal cache coherency rules implied by the underlying
* llist ops.
*
* If IPIs can go out of order to the cache coherency protocol
* in an architecture, sufficient synchronisation should be added
* to arch code to make it appear to obey cache coherency WRT
* locking and barrier primitives. Generic code isn't really
* equipped to do the right thing...
*/
if (llist_add(node, &per_cpu(call_single_queue, cpu)))
send_call_function_single_ipi(cpu);
}
/*
* Insert a previously allocated call_single_data_t element
* for execution on the given CPU. data must already have
* ->func, ->info, and ->flags set.
*/
static int generic_exec_single(int cpu, call_single_data_t *csd)
{
if (cpu == smp_processor_id()) {
smp_call_func_t func = csd->func;
void *info = csd->info;
unsigned long flags;
/*
* We can unlock early even for the synchronous on-stack case,
* since we're doing this from the same CPU..
*/
csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags);
csd_do_func(func, info, NULL);
csd_lock_record(NULL); local_irq_restore(flags);
return 0;
}
if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd);
return -ENXIO;
}
__smp_call_single_queue(cpu, &csd->node.llist);
return 0;
}
/**
* generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks
*
* Invoked by arch to handle an IPI for call function single.
* Must be called with interrupts disabled.
*/
void generic_smp_call_function_single_interrupt(void)
{
__flush_smp_call_function_queue(true);
}
/**
* __flush_smp_call_function_queue - Flush pending smp-call-function callbacks
*
* @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an
* offline CPU. Skip this check if set to 'false'.
*
* Flush any pending smp-call-function callbacks queued on this CPU. This is
* invoked by the generic IPI handler, as well as by a CPU about to go offline,
* to ensure that all pending IPI callbacks are run before it goes completely
* offline.
*
* Loop through the call_single_queue and run all the queued callbacks.
* Must be called with interrupts disabled.
*/
static void __flush_smp_call_function_queue(bool warn_cpu_offline)
{
call_single_data_t *csd, *csd_next;
struct llist_node *entry, *prev;
struct llist_head *head;
static bool warned;
atomic_t *tbt;
lockdep_assert_irqs_disabled();
/* Allow waiters to send backtrace NMI from here onwards */
tbt = this_cpu_ptr(&trigger_backtrace);
atomic_set_release(tbt, 1);
head = this_cpu_ptr(&call_single_queue);
entry = llist_del_all(head);
entry = llist_reverse_order(entry);
/* There shouldn't be any pending callbacks on an offline CPU. */
if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) &&
!warned && entry != NULL)) {
warned = true;
WARN(1, "IPI on offline CPU %d\n", smp_processor_id());
/*
* We don't have to use the _safe() variant here
* because we are not invoking the IPI handlers yet.
*/
llist_for_each_entry(csd, entry, node.llist) {
switch (CSD_TYPE(csd)) {
case CSD_TYPE_ASYNC:
case CSD_TYPE_SYNC:
case CSD_TYPE_IRQ_WORK:
pr_warn("IPI callback %pS sent to offline CPU\n",
csd->func);
break;
case CSD_TYPE_TTWU:
pr_warn("IPI task-wakeup sent to offline CPU\n");
break;
default:
pr_warn("IPI callback, unknown type %d, sent to offline CPU\n",
CSD_TYPE(csd));
break;
}
}
}
/*
* First; run all SYNC callbacks, people are waiting for us.
*/
prev = NULL;
llist_for_each_entry_safe(csd, csd_next, entry, node.llist) {
/* Do we wait until *after* callback? */
if (CSD_TYPE(csd) == CSD_TYPE_SYNC) {
smp_call_func_t func = csd->func;
void *info = csd->info;
if (prev) {
prev->next = &csd_next->node.llist;
} else {
entry = &csd_next->node.llist;
}
csd_lock_record(csd);
csd_do_func(func, info, csd);
csd_unlock(csd);
csd_lock_record(NULL);
} else {
prev = &csd->node.llist;
}
}
if (!entry)
return;
/*
* Second; run all !SYNC callbacks.
*/
prev = NULL;
llist_for_each_entry_safe(csd, csd_next, entry, node.llist) {
int type = CSD_TYPE(csd);
if (type != CSD_TYPE_TTWU) {
if (prev) {
prev->next = &csd_next->node.llist;
} else {
entry = &csd_next->node.llist;
}
if (type == CSD_TYPE_ASYNC) {
smp_call_func_t func = csd->func;
void *info = csd->info;
csd_lock_record(csd);
csd_unlock(csd);
csd_do_func(func, info, csd);
csd_lock_record(NULL);
} else if (type == CSD_TYPE_IRQ_WORK) {
irq_work_single(csd);
}
} else {
prev = &csd->node.llist;
}
}
/*
* Third; only CSD_TYPE_TTWU is left, issue those.
*/
if (entry) {
csd = llist_entry(entry, typeof(*csd), node.llist);
csd_do_func(sched_ttwu_pending, entry, csd);
}
}
/**
* flush_smp_call_function_queue - Flush pending smp-call-function callbacks
* from task context (idle, migration thread)
*
* When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it
* set, then remote CPUs can avoid sending IPIs and wake the idle CPU by
* setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to
* handle queued SMP function calls before scheduling.
*
* The migration thread has to ensure that an eventually pending wakeup has
* been handled before it migrates a task.
*/
void flush_smp_call_function_queue(void)
{
unsigned int was_pending;
unsigned long flags;
if (llist_empty(this_cpu_ptr(&call_single_queue)))
return;
local_irq_save(flags);
/* Get the already pending soft interrupts for RT enabled kernels */
was_pending = local_softirq_pending();
__flush_smp_call_function_queue(true);
if (local_softirq_pending())
do_softirq_post_smp_call_flush(was_pending);
local_irq_restore(flags);
}
/*
* smp_call_function_single - Run a function on a specific CPU
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code.
*/
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
call_single_data_t *csd;
call_single_data_t csd_stack = {
.node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, },
};
int this_cpu;
int err;
/*
* prevent preemption and reschedule on another processor,
* as well as CPU removal
*/
this_cpu = get_cpu();
/*
* Can deadlock when called with interrupts disabled.
* We allow cpu's that are not yet online though, as no one else can
* send smp call function interrupt to this cpu and as such deadlocks
* can't happen.
*/
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
&& !oops_in_progress);
/*
* When @wait we can deadlock when we interrupt between llist_add() and
* arch_send_call_function_ipi*(); when !@wait we can deadlock due to
* csd_lock() on because the interrupt context uses the same csd
* storage.
*/
WARN_ON_ONCE(!in_task());
csd = &csd_stack;
if (!wait) {
csd = this_cpu_ptr(&csd_data);
csd_lock(csd);
}
csd->func = func;
csd->info = info;
#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
csd->node.src = smp_processor_id();
csd->node.dst = cpu;
#endif
err = generic_exec_single(cpu, csd);
if (wait) csd_lock_wait(csd); put_cpu();
return err;
}
EXPORT_SYMBOL(smp_call_function_single);
/**
* smp_call_function_single_async() - Run an asynchronous function on a
* specific CPU.
* @cpu: The CPU to run on.
* @csd: Pre-allocated and setup data structure
*
* Like smp_call_function_single(), but the call is asynchonous and
* can thus be done from contexts with disabled interrupts.
*
* The caller passes his own pre-allocated data structure
* (ie: embedded in an object) and is responsible for synchronizing it
* such that the IPIs performed on the @csd are strictly serialized.
*
* If the function is called with one csd which has not yet been
* processed by previous call to smp_call_function_single_async(), the
* function will return immediately with -EBUSY showing that the csd
* object is still in progress.
*
* NOTE: Be careful, there is unfortunately no current debugging facility to
* validate the correctness of this serialization.
*
* Return: %0 on success or negative errno value on error
*/
int smp_call_function_single_async(int cpu, call_single_data_t *csd)
{
int err = 0;
preempt_disable();
if (csd->node.u_flags & CSD_FLAG_LOCK) {
err = -EBUSY;
goto out;
}
csd->node.u_flags = CSD_FLAG_LOCK;
smp_wmb();
err = generic_exec_single(cpu, csd);
out:
preempt_enable();
return err;
}
EXPORT_SYMBOL_GPL(smp_call_function_single_async);
/*
* smp_call_function_any - Run a function on any of the given cpus
* @mask: The mask of cpus it can run on.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed.
*
* Returns 0 on success, else a negative status code (if no cpus were online).
*
* Selection preference:
* 1) current cpu if in @mask
* 2) any cpu of current node if in @mask
* 3) any other online cpu in @mask
*/
int smp_call_function_any(const struct cpumask *mask,
smp_call_func_t func, void *info, int wait)
{
unsigned int cpu;
const struct cpumask *nodemask;
int ret;
/* Try for same CPU (cheapest) */
cpu = get_cpu();
if (cpumask_test_cpu(cpu, mask))
goto call;
/* Try for same node. */
nodemask = cpumask_of_node(cpu_to_node(cpu));
for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
cpu = cpumask_next_and(cpu, nodemask, mask)) {
if (cpu_online(cpu))
goto call;
}
/* Any online will do: smp_call_function_single handles nr_cpu_ids. */
cpu = cpumask_any_and(mask, cpu_online_mask);
call:
ret = smp_call_function_single(cpu, func, info, wait);
put_cpu();
return ret;
}
EXPORT_SYMBOL_GPL(smp_call_function_any);
/*
* Flags to be used as scf_flags argument of smp_call_function_many_cond().
*
* %SCF_WAIT: Wait until function execution is completed
* %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask
*/
#define SCF_WAIT (1U << 0)
#define SCF_RUN_LOCAL (1U << 1)
static void smp_call_function_many_cond(const struct cpumask *mask,
smp_call_func_t func, void *info,
unsigned int scf_flags,
smp_cond_func_t cond_func)
{
int cpu, last_cpu, this_cpu = smp_processor_id();
struct call_function_data *cfd;
bool wait = scf_flags & SCF_WAIT;
int nr_cpus = 0;
bool run_remote = false;
bool run_local = false;
lockdep_assert_preemption_disabled();
/*
* Can deadlock when called with interrupts disabled.
* We allow cpu's that are not yet online though, as no one else can
* send smp call function interrupt to this cpu and as such deadlocks
* can't happen.
*/
if (cpu_online(this_cpu) && !oops_in_progress &&
!early_boot_irqs_disabled)
lockdep_assert_irqs_enabled();
/*
* When @wait we can deadlock when we interrupt between llist_add() and
* arch_send_call_function_ipi*(); when !@wait we can deadlock due to
* csd_lock() on because the interrupt context uses the same csd
* storage.
*/
WARN_ON_ONCE(!in_task());
/* Check if we need local execution. */
if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask) && (!cond_func || cond_func(this_cpu, info)))
run_local = true;
/* Check if we need remote execution, i.e., any CPU excluding this one. */
cpu = cpumask_first_and(mask, cpu_online_mask);
if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
if (cpu < nr_cpu_ids)
run_remote = true;
if (run_remote) {
cfd = this_cpu_ptr(&cfd_data);
cpumask_and(cfd->cpumask, mask, cpu_online_mask);
__cpumask_clear_cpu(this_cpu, cfd->cpumask);
cpumask_clear(cfd->cpumask_ipi);
for_each_cpu(cpu, cfd->cpumask) {
call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu);
if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask);
continue;
}
csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC;
csd->func = func;
csd->info = info;
#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
csd->node.src = smp_processor_id();
csd->node.dst = cpu;
#endif
trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi);
nr_cpus++;
last_cpu = cpu;
}
}
/*
* Choose the most efficient way to send an IPI. Note that the
* number of CPUs might be zero due to concurrent changes to the
* provided mask.
*/
if (nr_cpus == 1)
send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi);
}
if (run_local) {
unsigned long flags;
local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags);
}
if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) {
call_single_data_t *csd;
csd = per_cpu_ptr(cfd->csd, cpu);
csd_lock_wait(csd);
}
}
}
/**
* smp_call_function_many(): Run a function on a set of CPUs.
* @mask: The set of cpus to run on (only runs on online subset).
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait
* (atomically) until function has completed on other CPUs. If
* %SCF_RUN_LOCAL is set, the function will also be run locally
* if the local CPU is set in the @cpumask.
*
* If @wait is true, then returns once @func has returned.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. Preemption
* must be disabled when calling this function.
*/
void smp_call_function_many(const struct cpumask *mask,
smp_call_func_t func, void *info, bool wait)
{
smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL);
}
EXPORT_SYMBOL(smp_call_function_many);
/**
* smp_call_function(): Run a function on all other CPUs.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait (atomically) until function has completed
* on other CPUs.
*
* Returns 0.
*
* If @wait is true, then returns once @func has returned; otherwise
* it returns just before the target cpu calls @func.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
void smp_call_function(smp_call_func_t func, void *info, int wait)
{
preempt_disable();
smp_call_function_many(cpu_online_mask, func, info, wait);
preempt_enable();
}
EXPORT_SYMBOL(smp_call_function);
/* Setup configured maximum number of CPUs to activate */
unsigned int setup_max_cpus = NR_CPUS;
EXPORT_SYMBOL(setup_max_cpus);
/*
* Setup routine for controlling SMP activation
*
* Command-line option of "nosmp" or "maxcpus=0" will disable SMP
* activation entirely (the MPS table probe still happens, though).
*
* Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
* greater than 0, limits the maximum number of CPUs activated in
* SMP mode to <NUM>.
*/
void __weak __init arch_disable_smp_support(void) { }
static int __init nosmp(char *str)
{
setup_max_cpus = 0;
arch_disable_smp_support();
return 0;
}
early_param("nosmp", nosmp);
/* this is hard limit */
static int __init nrcpus(char *str)
{
int nr_cpus;
if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids)
set_nr_cpu_ids(nr_cpus);
return 0;
}
early_param("nr_cpus", nrcpus);
static int __init maxcpus(char *str)
{
get_option(&str, &setup_max_cpus);
if (setup_max_cpus == 0)
arch_disable_smp_support();
return 0;
}
early_param("maxcpus", maxcpus);
#if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS)
/* Setup number of possible processor ids */
unsigned int nr_cpu_ids __read_mostly = NR_CPUS;
EXPORT_SYMBOL(nr_cpu_ids);
#endif
/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
void __init setup_nr_cpu_ids(void)
{
set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1);
}
/* Called by boot processor to activate the rest. */
void __init smp_init(void)
{
int num_nodes, num_cpus;
idle_threads_init();
cpuhp_threads_init();
pr_info("Bringing up secondary CPUs ...\n");
bringup_nonboot_cpus(setup_max_cpus);
num_nodes = num_online_nodes();
num_cpus = num_online_cpus();
pr_info("Brought up %d node%s, %d CPU%s\n",
num_nodes, str_plural(num_nodes), num_cpus, str_plural(num_cpus));
/* Any cleanup work */
smp_cpus_done(setup_max_cpus);
}
/*
* on_each_cpu_cond(): Call a function on each processor for which
* the supplied function cond_func returns true, optionally waiting
* for all the required CPUs to finish. This may include the local
* processor.
* @cond_func: A callback function that is passed a cpu id and
* the info parameter. The function is called
* with preemption disabled. The function should
* return a blooean value indicating whether to IPI
* the specified CPU.
* @func: The function to run on all applicable CPUs.
* This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to both functions.
* @wait: If true, wait (atomically) until function has
* completed on other CPUs.
*
* Preemption is disabled to protect against CPUs going offline but not online.
* CPUs going online during the call will not be seen or sent an IPI.
*
* You must not call this function with disabled interrupts or
* from a hardware interrupt handler or from a bottom half handler.
*/
void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
void *info, bool wait, const struct cpumask *mask)
{
unsigned int scf_flags = SCF_RUN_LOCAL;
if (wait)
scf_flags |= SCF_WAIT;
preempt_disable();
smp_call_function_many_cond(mask, func, info, scf_flags, cond_func);
preempt_enable();
}
EXPORT_SYMBOL(on_each_cpu_cond_mask);
static void do_nothing(void *unused)
{
}
/**
* kick_all_cpus_sync - Force all cpus out of idle
*
* Used to synchronize the update of pm_idle function pointer. It's
* called after the pointer is updated and returns after the dummy
* callback function has been executed on all cpus. The execution of
* the function can only happen on the remote cpus after they have
* left the idle function which had been called via pm_idle function
* pointer. So it's guaranteed that nothing uses the previous pointer
* anymore.
*/
void kick_all_cpus_sync(void)
{
/* Make sure the change is visible before we kick the cpus */
smp_mb();
smp_call_function(do_nothing, NULL, 1);
}
EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
/**
* wake_up_all_idle_cpus - break all cpus out of idle
* wake_up_all_idle_cpus try to break all cpus which is in idle state even
* including idle polling cpus, for non-idle cpus, we will do nothing
* for them.
*/
void wake_up_all_idle_cpus(void)
{
int cpu;
for_each_possible_cpu(cpu) {
preempt_disable();
if (cpu != smp_processor_id() && cpu_online(cpu))
wake_up_if_idle(cpu);
preempt_enable();
}
}
EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus);
/**
* struct smp_call_on_cpu_struct - Call a function on a specific CPU
* @work: &work_struct
* @done: &completion to signal
* @func: function to call
* @data: function's data argument
* @ret: return value from @func
* @cpu: target CPU (%-1 for any CPU)
*
* Used to call a function on a specific cpu and wait for it to return.
* Optionally make sure the call is done on a specified physical cpu via vcpu
* pinning in order to support virtualized environments.
*/
struct smp_call_on_cpu_struct {
struct work_struct work;
struct completion done;
int (*func)(void *);
void *data;
int ret;
int cpu;
};
static void smp_call_on_cpu_callback(struct work_struct *work)
{
struct smp_call_on_cpu_struct *sscs;
sscs = container_of(work, struct smp_call_on_cpu_struct, work);
if (sscs->cpu >= 0)
hypervisor_pin_vcpu(sscs->cpu);
sscs->ret = sscs->func(sscs->data);
if (sscs->cpu >= 0)
hypervisor_pin_vcpu(-1);
complete(&sscs->done);
}
int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
{
struct smp_call_on_cpu_struct sscs = {
.done = COMPLETION_INITIALIZER_ONSTACK(sscs.done),
.func = func,
.data = par,
.cpu = phys ? cpu : -1,
};
INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback);
if (cpu >= nr_cpu_ids || !cpu_online(cpu))
return -ENXIO;
queue_work_on(cpu, system_wq, &sscs.work);
wait_for_completion(&sscs.done);
destroy_work_on_stack(&sscs.work);
return sscs.ret;
}
EXPORT_SYMBOL_GPL(smp_call_on_cpu);
// SPDX-License-Identifier: GPL-2.0-or-later
/* Common capabilities, needed by capability.o.
*/
#include <linux/capability.h>
#include <linux/audit.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/lsm_hooks.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/ptrace.h>
#include <linux/xattr.h>
#include <linux/hugetlb.h>
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/prctl.h>
#include <linux/securebits.h>
#include <linux/user_namespace.h>
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/mnt_idmapping.h>
#include <uapi/linux/lsm.h>
#define CREATE_TRACE_POINTS
#include <trace/events/capability.h>
/*
* If a non-root user executes a setuid-root binary in
* !secure(SECURE_NOROOT) mode, then we raise capabilities.
* However if fE is also set, then the intent is for only
* the file capabilities to be applied, and the setuid-root
* bit is left on either to change the uid (plausible) or
* to get full privilege on a kernel without file capabilities
* support. So in that case we do not raise capabilities.
*
* Warn if that happens, once per boot.
*/
static void warn_setuid_and_fcaps_mixed(const char *fname)
{
static int warned;
if (!warned) {
printk(KERN_INFO "warning: `%s' has both setuid-root and"
" effective capabilities. Therefore not raising all"
" capabilities.\n", fname);
warned = 1;
}
}
/**
* cap_capable_helper - Determine whether a task has a particular effective
* capability.
* @cred: The credentials to use
* @target_ns: The user namespace of the resource being accessed
* @cred_ns: The user namespace of the credentials
* @cap: The capability to check for
*
* Determine whether the nominated task has the specified capability amongst
* its effective set, returning 0 if it does, -ve if it does not.
*
* See cap_capable for more details.
*/
static inline int cap_capable_helper(const struct cred *cred,
struct user_namespace *target_ns,
const struct user_namespace *cred_ns,
int cap)
{
struct user_namespace *ns = target_ns;
/* See if cred has the capability in the target user namespace
* by examining the target user namespace and all of the target
* user namespace's parents.
*/
for (;;) {
/* Do we have the necessary capabilities? */
if (likely(ns == cred_ns))
return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
/*
* If we're already at a lower level than we're looking for,
* we're done searching.
*/
if (ns->level <= cred_ns->level)
return -EPERM;
/*
* The owner of the user namespace in the parent of the
* user namespace has all caps.
*/
if ((ns->parent == cred_ns) && uid_eq(ns->owner, cred->euid))
return 0;
/*
* If you have a capability in a parent user ns, then you have
* it over all children user namespaces as well.
*/
ns = ns->parent;
}
/* We never get here */
}
/**
* cap_capable - Determine whether a task has a particular effective capability
* @cred: The credentials to use
* @target_ns: The user namespace of the resource being accessed
* @cap: The capability to check for
* @opts: Bitmask of options defined in include/linux/security.h (unused)
*
* Determine whether the nominated task has the specified capability amongst
* its effective set, returning 0 if it does, -ve if it does not.
*
* NOTE WELL: cap_capable() has reverse semantics to the capable() call
* and friends. That is cap_capable() returns an int 0 when a task has
* a capability, while the kernel's capable(), has_ns_capability(),
* has_ns_capability_noaudit(), and has_capability_noaudit() return a
* bool true (1) for this case.
*/
int cap_capable(const struct cred *cred, struct user_namespace *target_ns,
int cap, unsigned int opts)
{
const struct user_namespace *cred_ns = cred->user_ns;
int ret = cap_capable_helper(cred, target_ns, cred_ns, cap); trace_cap_capable(cred, target_ns, cred_ns, cap, ret);
return ret;
}
/**
* cap_settime - Determine whether the current process may set the system clock
* @ts: The time to set
* @tz: The timezone to set
*
* Determine whether the current process may set the system clock and timezone
* information, returning 0 if permission granted, -ve if denied.
*/
int cap_settime(const struct timespec64 *ts, const struct timezone *tz)
{
if (!capable(CAP_SYS_TIME))
return -EPERM;
return 0;
}
/**
* cap_ptrace_access_check - Determine whether the current process may access
* another
* @child: The process to be accessed
* @mode: The mode of attachment.
*
* If we are in the same or an ancestor user_ns and have all the target
* task's capabilities, then ptrace access is allowed.
* If we have the ptrace capability to the target user_ns, then ptrace
* access is allowed.
* Else denied.
*
* Determine whether a process may access another, returning 0 if permission
* granted, -ve if denied.
*/
int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
{
int ret = 0;
const struct cred *cred, *child_cred;
const kernel_cap_t *caller_caps;
rcu_read_lock();
cred = current_cred();
child_cred = __task_cred(child);
if (mode & PTRACE_MODE_FSCREDS)
caller_caps = &cred->cap_effective;
else
caller_caps = &cred->cap_permitted;
if (cred->user_ns == child_cred->user_ns &&
cap_issubset(child_cred->cap_permitted, *caller_caps))
goto out;
if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
goto out;
ret = -EPERM;
out:
rcu_read_unlock();
return ret;
}
/**
* cap_ptrace_traceme - Determine whether another process may trace the current
* @parent: The task proposed to be the tracer
*
* If parent is in the same or an ancestor user_ns and has all current's
* capabilities, then ptrace access is allowed.
* If parent has the ptrace capability to current's user_ns, then ptrace
* access is allowed.
* Else denied.
*
* Determine whether the nominated task is permitted to trace the current
* process, returning 0 if permission is granted, -ve if denied.
*/
int cap_ptrace_traceme(struct task_struct *parent)
{
int ret = 0;
const struct cred *cred, *child_cred;
rcu_read_lock();
cred = __task_cred(parent);
child_cred = current_cred();
if (cred->user_ns == child_cred->user_ns &&
cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
goto out;
if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE))
goto out;
ret = -EPERM;
out:
rcu_read_unlock();
return ret;
}
/**
* cap_capget - Retrieve a task's capability sets
* @target: The task from which to retrieve the capability sets
* @effective: The place to record the effective set
* @inheritable: The place to record the inheritable set
* @permitted: The place to record the permitted set
*
* This function retrieves the capabilities of the nominated task and returns
* them to the caller.
*/
int cap_capget(const struct task_struct *target, kernel_cap_t *effective,
kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
const struct cred *cred;
/* Derived from kernel/capability.c:sys_capget. */
rcu_read_lock();
cred = __task_cred(target);
*effective = cred->cap_effective;
*inheritable = cred->cap_inheritable;
*permitted = cred->cap_permitted;
rcu_read_unlock();
return 0;
}
/*
* Determine whether the inheritable capabilities are limited to the old
* permitted set. Returns 1 if they are limited, 0 if they are not.
*/
static inline int cap_inh_is_capped(void)
{
/* they are so limited unless the current task has the CAP_SETPCAP
* capability
*/
if (cap_capable(current_cred(), current_cred()->user_ns,
CAP_SETPCAP, CAP_OPT_NONE) == 0)
return 0;
return 1;
}
/**
* cap_capset - Validate and apply proposed changes to current's capabilities
* @new: The proposed new credentials; alterations should be made here
* @old: The current task's current credentials
* @effective: A pointer to the proposed new effective capabilities set
* @inheritable: A pointer to the proposed new inheritable capabilities set
* @permitted: A pointer to the proposed new permitted capabilities set
*
* This function validates and applies a proposed mass change to the current
* process's capability sets. The changes are made to the proposed new
* credentials, and assuming no error, will be committed by the caller of LSM.
*/
int cap_capset(struct cred *new,
const struct cred *old,
const kernel_cap_t *effective,
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted)
{
if (cap_inh_is_capped() &&
!cap_issubset(*inheritable,
cap_combine(old->cap_inheritable,
old->cap_permitted)))
/* incapable of using this inheritable set */
return -EPERM;
if (!cap_issubset(*inheritable,
cap_combine(old->cap_inheritable,
old->cap_bset)))
/* no new pI capabilities outside bounding set */
return -EPERM;
/* verify restrictions on target's new Permitted set */
if (!cap_issubset(*permitted, old->cap_permitted))
return -EPERM;
/* verify the _new_Effective_ is a subset of the _new_Permitted_ */
if (!cap_issubset(*effective, *permitted))
return -EPERM;
new->cap_effective = *effective;
new->cap_inheritable = *inheritable;
new->cap_permitted = *permitted;
/*
* Mask off ambient bits that are no longer both permitted and
* inheritable.
*/
new->cap_ambient = cap_intersect(new->cap_ambient,
cap_intersect(*permitted,
*inheritable));
if (WARN_ON(!cap_ambient_invariant_ok(new)))
return -EINVAL;
return 0;
}
/**
* cap_inode_need_killpriv - Determine if inode change affects privileges
* @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV
*
* Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
* affects the security markings on that inode, and if it is, should
* inode_killpriv() be invoked or the change rejected.
*
* Return: 1 if security.capability has a value, meaning inode_killpriv()
* is required, 0 otherwise, meaning inode_killpriv() is not required.
*/
int cap_inode_need_killpriv(struct dentry *dentry)
{
struct inode *inode = d_backing_inode(dentry);
int error;
error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0);
return error > 0;
}
/**
* cap_inode_killpriv - Erase the security markings on an inode
*
* @idmap: idmap of the mount the inode was found from
* @dentry: The inode/dentry to alter
*
* Erase the privilege-enhancing security markings on an inode.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* Return: 0 if successful, -ve on error.
*/
int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry)
{
int error;
error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS);
if (error == -EOPNOTSUPP)
error = 0;
return error;
}
static bool rootid_owns_currentns(vfsuid_t rootvfsuid)
{
struct user_namespace *ns;
kuid_t kroot;
if (!vfsuid_valid(rootvfsuid))
return false;
kroot = vfsuid_into_kuid(rootvfsuid);
for (ns = current_user_ns();; ns = ns->parent) {
if (from_kuid(ns, kroot) == 0)
return true;
if (ns == &init_user_ns)
break;
}
return false;
}
static __u32 sansflags(__u32 m)
{
return m & ~VFS_CAP_FLAGS_EFFECTIVE;
}
static bool is_v2header(int size, const struct vfs_cap_data *cap)
{
if (size != XATTR_CAPS_SZ_2)
return false;
return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2;
}
static bool is_v3header(int size, const struct vfs_cap_data *cap)
{
if (size != XATTR_CAPS_SZ_3)
return false;
return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3;
}
/*
* getsecurity: We are called for security.* before any attempt to read the
* xattr from the inode itself.
*
* This gives us a chance to read the on-disk value and convert it. If we
* return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler.
*
* Note we are not called by vfs_getxattr_alloc(), but that is only called
* by the integrity subsystem, which really wants the unconverted values -
* so that's good.
*/
int cap_inode_getsecurity(struct mnt_idmap *idmap,
struct inode *inode, const char *name, void **buffer,
bool alloc)
{
int size;
kuid_t kroot;
vfsuid_t vfsroot;
u32 nsmagic, magic;
uid_t root, mappedroot;
char *tmpbuf = NULL;
struct vfs_cap_data *cap;
struct vfs_ns_cap_data *nscap = NULL;
struct dentry *dentry;
struct user_namespace *fs_ns;
if (strcmp(name, "capability") != 0)
return -EOPNOTSUPP;
dentry = d_find_any_alias(inode);
if (!dentry)
return -EINVAL;
size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf,
sizeof(struct vfs_ns_cap_data), GFP_NOFS);
dput(dentry);
/* gcc11 complains if we don't check for !tmpbuf */
if (size < 0 || !tmpbuf)
goto out_free;
fs_ns = inode->i_sb->s_user_ns;
cap = (struct vfs_cap_data *) tmpbuf;
if (is_v2header(size, cap)) {
root = 0;
} else if (is_v3header(size, cap)) {
nscap = (struct vfs_ns_cap_data *) tmpbuf;
root = le32_to_cpu(nscap->rootid);
} else {
size = -EINVAL;
goto out_free;
}
kroot = make_kuid(fs_ns, root);
/* If this is an idmapped mount shift the kuid. */
vfsroot = make_vfsuid(idmap, fs_ns, kroot);
/* If the root kuid maps to a valid uid in current ns, then return
* this as a nscap. */
mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot));
if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
size = sizeof(struct vfs_ns_cap_data);
if (alloc) {
if (!nscap) {
/* v2 -> v3 conversion */
nscap = kzalloc(size, GFP_ATOMIC);
if (!nscap) {
size = -ENOMEM;
goto out_free;
}
nsmagic = VFS_CAP_REVISION_3;
magic = le32_to_cpu(cap->magic_etc);
if (magic & VFS_CAP_FLAGS_EFFECTIVE)
nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
nscap->magic_etc = cpu_to_le32(nsmagic);
} else {
/* use allocated v3 buffer */
tmpbuf = NULL;
}
nscap->rootid = cpu_to_le32(mappedroot);
*buffer = nscap;
}
goto out_free;
}
if (!rootid_owns_currentns(vfsroot)) {
size = -EOVERFLOW;
goto out_free;
}
/* This comes from a parent namespace. Return as a v2 capability */
size = sizeof(struct vfs_cap_data);
if (alloc) {
if (nscap) {
/* v3 -> v2 conversion */
cap = kzalloc(size, GFP_ATOMIC);
if (!cap) {
size = -ENOMEM;
goto out_free;
}
magic = VFS_CAP_REVISION_2;
nsmagic = le32_to_cpu(nscap->magic_etc);
if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
magic |= VFS_CAP_FLAGS_EFFECTIVE;
memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
cap->magic_etc = cpu_to_le32(magic);
} else {
/* use unconverted v2 */
tmpbuf = NULL;
}
*buffer = cap;
}
out_free:
kfree(tmpbuf);
return size;
}
/**
* rootid_from_xattr - translate root uid of vfs caps
*
* @value: vfs caps value which may be modified by this function
* @size: size of @ivalue
* @task_ns: user namespace of the caller
*/
static vfsuid_t rootid_from_xattr(const void *value, size_t size,
struct user_namespace *task_ns)
{
const struct vfs_ns_cap_data *nscap = value;
uid_t rootid = 0;
if (size == XATTR_CAPS_SZ_3)
rootid = le32_to_cpu(nscap->rootid);
return VFSUIDT_INIT(make_kuid(task_ns, rootid));
}
static bool validheader(size_t size, const struct vfs_cap_data *cap)
{
return is_v2header(size, cap) || is_v3header(size, cap);
}
/**
* cap_convert_nscap - check vfs caps
*
* @idmap: idmap of the mount the inode was found from
* @dentry: used to retrieve inode to check permissions on
* @ivalue: vfs caps value which may be modified by this function
* @size: size of @ivalue
*
* User requested a write of security.capability. If needed, update the
* xattr to change from v2 to v3, or to fixup the v3 rootid.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* Return: On success, return the new size; on error, return < 0.
*/
int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry,
const void **ivalue, size_t size)
{
struct vfs_ns_cap_data *nscap;
uid_t nsrootid;
const struct vfs_cap_data *cap = *ivalue;
__u32 magic, nsmagic;
struct inode *inode = d_backing_inode(dentry);
struct user_namespace *task_ns = current_user_ns(),
*fs_ns = inode->i_sb->s_user_ns;
kuid_t rootid;
vfsuid_t vfsrootid;
size_t newsize;
if (!*ivalue)
return -EINVAL;
if (!validheader(size, cap))
return -EINVAL;
if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
return -EPERM;
if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap))
if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
/* user is privileged, just write the v2 */
return size;
vfsrootid = rootid_from_xattr(*ivalue, size, task_ns);
if (!vfsuid_valid(vfsrootid))
return -EINVAL;
rootid = from_vfsuid(idmap, fs_ns, vfsrootid);
if (!uid_valid(rootid))
return -EINVAL;
nsrootid = from_kuid(fs_ns, rootid);
if (nsrootid == -1)
return -EINVAL;
newsize = sizeof(struct vfs_ns_cap_data);
nscap = kmalloc(newsize, GFP_ATOMIC);
if (!nscap)
return -ENOMEM;
nscap->rootid = cpu_to_le32(nsrootid);
nsmagic = VFS_CAP_REVISION_3;
magic = le32_to_cpu(cap->magic_etc);
if (magic & VFS_CAP_FLAGS_EFFECTIVE)
nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
nscap->magic_etc = cpu_to_le32(nsmagic);
memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
*ivalue = nscap;
return newsize;
}
/*
* Calculate the new process capability sets from the capability sets attached
* to a file.
*/
static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
struct linux_binprm *bprm,
bool *effective,
bool *has_fcap)
{
struct cred *new = bprm->cred;
int ret = 0;
if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
*effective = true;
if (caps->magic_etc & VFS_CAP_REVISION_MASK)
*has_fcap = true;
/*
* pP' = (X & fP) | (pI & fI)
* The addition of pA' is handled later.
*/
new->cap_permitted.val =
(new->cap_bset.val & caps->permitted.val) |
(new->cap_inheritable.val & caps->inheritable.val);
if (caps->permitted.val & ~new->cap_permitted.val)
/* insufficient to execute correctly */
ret = -EPERM;
/*
* For legacy apps, with no internal support for recognizing they
* do not have enough capabilities, we return an error if they are
* missing some "forced" (aka file-permitted) capabilities.
*/
return *effective ? ret : 0;
}
/**
* get_vfs_caps_from_disk - retrieve vfs caps from disk
*
* @idmap: idmap of the mount the inode was found from
* @dentry: dentry from which @inode is retrieved
* @cpu_caps: vfs capabilities
*
* Extract the on-exec-apply capability sets for an executable file.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*/
int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
const struct dentry *dentry,
struct cpu_vfs_cap_data *cpu_caps)
{
struct inode *inode = d_backing_inode(dentry);
__u32 magic_etc;
int size;
struct vfs_ns_cap_data data, *nscaps = &data;
struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
kuid_t rootkuid;
vfsuid_t rootvfsuid;
struct user_namespace *fs_ns;
memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
if (!inode)
return -ENODATA;
fs_ns = inode->i_sb->s_user_ns;
size = __vfs_getxattr((struct dentry *)dentry, inode,
XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ);
if (size == -ENODATA || size == -EOPNOTSUPP)
/* no data, that's ok */
return -ENODATA;
if (size < 0)
return size;
if (size < sizeof(magic_etc))
return -EINVAL;
cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc);
rootkuid = make_kuid(fs_ns, 0);
switch (magic_etc & VFS_CAP_REVISION_MASK) {
case VFS_CAP_REVISION_1:
if (size != XATTR_CAPS_SZ_1)
return -EINVAL;
break;
case VFS_CAP_REVISION_2:
if (size != XATTR_CAPS_SZ_2)
return -EINVAL;
break;
case VFS_CAP_REVISION_3:
if (size != XATTR_CAPS_SZ_3)
return -EINVAL;
rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
break;
default:
return -EINVAL;
}
rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid);
if (!vfsuid_valid(rootvfsuid))
return -ENODATA;
/* Limit the caps to the mounter of the filesystem
* or the more limited uid specified in the xattr.
*/
if (!rootid_owns_currentns(rootvfsuid))
return -ENODATA;
cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted);
cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable);
/*
* Rev1 had just a single 32-bit word, later expanded
* to a second one for the high bits
*/
if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) {
cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32;
cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32;
}
cpu_caps->permitted.val &= CAP_VALID_MASK;
cpu_caps->inheritable.val &= CAP_VALID_MASK;
cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid);
return 0;
}
/*
* Attempt to get the on-exec apply capability sets for an executable file from
* its xattrs and, if present, apply them to the proposed credentials being
* constructed by execve().
*/
static int get_file_caps(struct linux_binprm *bprm, const struct file *file,
bool *effective, bool *has_fcap)
{
int rc = 0;
struct cpu_vfs_cap_data vcaps;
cap_clear(bprm->cred->cap_permitted);
if (!file_caps_enabled)
return 0;
if (!mnt_may_suid(file->f_path.mnt))
return 0;
/*
* This check is redundant with mnt_may_suid() but is kept to make
* explicit that capability bits are limited to s_user_ns and its
* descendants.
*/
if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns))
return 0;
rc = get_vfs_caps_from_disk(file_mnt_idmap(file),
file->f_path.dentry, &vcaps);
if (rc < 0) {
if (rc == -EINVAL)
printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
bprm->filename);
else if (rc == -ENODATA)
rc = 0;
goto out;
}
rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap);
out:
if (rc)
cap_clear(bprm->cred->cap_permitted);
return rc;
}
static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); }
static inline bool __is_real(kuid_t uid, struct cred *cred)
{ return uid_eq(cred->uid, uid); }
static inline bool __is_eff(kuid_t uid, struct cred *cred)
{ return uid_eq(cred->euid, uid); }
static inline bool __is_suid(kuid_t uid, struct cred *cred)
{ return !__is_real(uid, cred) && __is_eff(uid, cred); }
/*
* handle_privileged_root - Handle case of privileged root
* @bprm: The execution parameters, including the proposed creds
* @has_fcap: Are any file capabilities set?
* @effective: Do we have effective root privilege?
* @root_uid: This namespace' root UID WRT initial USER namespace
*
* Handle the case where root is privileged and hasn't been neutered by
* SECURE_NOROOT. If file capabilities are set, they won't be combined with
* set UID root and nothing is changed. If we are root, cap_permitted is
* updated. If we have become set UID root, the effective bit is set.
*/
static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap,
bool *effective, kuid_t root_uid)
{
const struct cred *old = current_cred();
struct cred *new = bprm->cred;
if (!root_privileged())
return;
/*
* If the legacy file capability is set, then don't set privs
* for a setuid root binary run by a non-root user. Do set it
* for a root user just to cause least surprise to an admin.
*/
if (has_fcap && __is_suid(root_uid, new)) {
warn_setuid_and_fcaps_mixed(bprm->filename);
return;
}
/*
* To support inheritance of root-permissions and suid-root
* executables under compatibility mode, we override the
* capability sets for the file.
*/
if (__is_eff(root_uid, new) || __is_real(root_uid, new)) {
/* pP' = (cap_bset & ~0) | (pI & ~0) */
new->cap_permitted = cap_combine(old->cap_bset,
old->cap_inheritable);
}
/*
* If only the real uid is 0, we do not set the effective bit.
*/
if (__is_eff(root_uid, new))
*effective = true;
}
#define __cap_gained(field, target, source) \
!cap_issubset(target->cap_##field, source->cap_##field)
#define __cap_grew(target, source, cred) \
!cap_issubset(cred->cap_##target, cred->cap_##source)
#define __cap_full(field, cred) \
cap_issubset(CAP_FULL_SET, cred->cap_##field)
static inline bool __is_setuid(struct cred *new, const struct cred *old)
{ return !uid_eq(new->euid, old->uid); }
static inline bool __is_setgid(struct cred *new, const struct cred *old)
{ return !gid_eq(new->egid, old->gid); }
/*
* 1) Audit candidate if current->cap_effective is set
*
* We do not bother to audit if 3 things are true:
* 1) cap_effective has all caps
* 2) we became root *OR* are were already root
* 3) root is supposed to have all caps (SECURE_NOROOT)
* Since this is just a normal root execing a process.
*
* Number 1 above might fail if you don't have a full bset, but I think
* that is interesting information to audit.
*
* A number of other conditions require logging:
* 2) something prevented setuid root getting all caps
* 3) non-setuid root gets fcaps
* 4) non-setuid root gets ambient
*/
static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old,
kuid_t root, bool has_fcap)
{
bool ret = false;
if ((__cap_grew(effective, ambient, new) &&
!(__cap_full(effective, new) &&
(__is_eff(root, new) || __is_real(root, new)) &&
root_privileged())) ||
(root_privileged() &&
__is_suid(root, new) &&
!__cap_full(effective, new)) ||
(!__is_setuid(new, old) &&
((has_fcap &&
__cap_gained(permitted, new, old)) ||
__cap_gained(ambient, new, old))))
ret = true;
return ret;
}
/**
* cap_bprm_creds_from_file - Set up the proposed credentials for execve().
* @bprm: The execution parameters, including the proposed creds
* @file: The file to pull the credentials from
*
* Set up the proposed credentials for a new execution context being
* constructed by execve(). The proposed creds in @bprm->cred is altered,
* which won't take effect immediately.
*
* Return: 0 if successful, -ve on error.
*/
int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file)
{
/* Process setpcap binaries and capabilities for uid 0 */
const struct cred *old = current_cred();
struct cred *new = bprm->cred;
bool effective = false, has_fcap = false, is_setid;
int ret;
kuid_t root_uid;
if (WARN_ON(!cap_ambient_invariant_ok(old)))
return -EPERM;
ret = get_file_caps(bprm, file, &effective, &has_fcap);
if (ret < 0)
return ret;
root_uid = make_kuid(new->user_ns, 0);
handle_privileged_root(bprm, has_fcap, &effective, root_uid);
/* if we have fs caps, clear dangerous personality flags */
if (__cap_gained(permitted, new, old))
bprm->per_clear |= PER_CLEAR_ON_SETID;
/* Don't let someone trace a set[ug]id/setpcap binary with the revised
* credentials unless they have the appropriate permit.
*
* In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
*/
is_setid = __is_setuid(new, old) || __is_setgid(new, old);
if ((is_setid || __cap_gained(permitted, new, old)) &&
((bprm->unsafe & ~LSM_UNSAFE_PTRACE) ||
!ptracer_capable(current, new->user_ns))) {
/* downgrade; they get no more than they had, and maybe less */
if (!ns_capable(new->user_ns, CAP_SETUID) ||
(bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) {
new->euid = new->uid;
new->egid = new->gid;
}
new->cap_permitted = cap_intersect(new->cap_permitted,
old->cap_permitted);
}
new->suid = new->fsuid = new->euid;
new->sgid = new->fsgid = new->egid;
/* File caps or setid cancels ambient. */
if (has_fcap || is_setid)
cap_clear(new->cap_ambient);
/*
* Now that we've computed pA', update pP' to give:
* pP' = (X & fP) | (pI & fI) | pA'
*/
new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient);
/*
* Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set,
* this is the same as pE' = (fE ? pP' : 0) | pA'.
*/
if (effective)
new->cap_effective = new->cap_permitted;
else
new->cap_effective = new->cap_ambient;
if (WARN_ON(!cap_ambient_invariant_ok(new)))
return -EPERM;
if (nonroot_raised_pE(new, old, root_uid, has_fcap)) {
ret = audit_log_bprm_fcaps(bprm, new, old);
if (ret < 0)
return ret;
}
new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
if (WARN_ON(!cap_ambient_invariant_ok(new)))
return -EPERM;
/* Check for privilege-elevated exec. */
if (is_setid ||
(!__is_real(root_uid, new) &&
(effective ||
__cap_grew(permitted, ambient, new))))
bprm->secureexec = 1;
return 0;
}
/**
* cap_inode_setxattr - Determine whether an xattr may be altered
* @dentry: The inode/dentry being altered
* @name: The name of the xattr to be changed
* @value: The value that the xattr will be changed to
* @size: The size of value
* @flags: The replacement flag
*
* Determine whether an xattr may be altered or set on an inode, returning 0 if
* permission is granted, -ve if denied.
*
* This is used to make sure security xattrs don't get updated or set by those
* who aren't privileged to do so.
*/
int cap_inode_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
/* Ignore non-security xattrs */
if (strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) != 0)
return 0;
/*
* For XATTR_NAME_CAPS the check will be done in
* cap_convert_nscap(), called by setxattr()
*/
if (strcmp(name, XATTR_NAME_CAPS) == 0)
return 0;
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
/**
* cap_inode_removexattr - Determine whether an xattr may be removed
*
* @idmap: idmap of the mount the inode was found from
* @dentry: The inode/dentry being altered
* @name: The name of the xattr to be changed
*
* Determine whether an xattr may be removed from an inode, returning 0 if
* permission is granted, -ve if denied.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* This is used to make sure security xattrs don't get removed by those who
* aren't privileged to remove them.
*/
int cap_inode_removexattr(struct mnt_idmap *idmap,
struct dentry *dentry, const char *name)
{
struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
/* Ignore non-security xattrs */
if (strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) != 0)
return 0;
if (strcmp(name, XATTR_NAME_CAPS) == 0) {
/* security.capability gets namespaced */
struct inode *inode = d_backing_inode(dentry);
if (!inode)
return -EINVAL;
if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
return -EPERM;
return 0;
}
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
/*
* cap_emulate_setxuid() fixes the effective / permitted capabilities of
* a process after a call to setuid, setreuid, or setresuid.
*
* 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
* {r,e,s}uid != 0, the permitted and effective capabilities are
* cleared.
*
* 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
* capabilities of the process are cleared.
*
* 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
* capabilities are set to the permitted capabilities.
*
* fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should
* never happen.
*
* -astor
*
* cevans - New behaviour, Oct '99
* A process may, via prctl(), elect to keep its capabilities when it
* calls setuid() and switches away from uid==0. Both permitted and
* effective sets will be retained.
* Without this change, it was impossible for a daemon to drop only some
* of its privilege. The call to setuid(!=0) would drop all privileges!
* Keeping uid 0 is not an option because uid 0 owns too many vital
* files..
* Thanks to Olaf Kirch and Peter Benie for spotting this.
*/
static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old)
{
kuid_t root_uid = make_kuid(old->user_ns, 0);
if ((uid_eq(old->uid, root_uid) ||
uid_eq(old->euid, root_uid) ||
uid_eq(old->suid, root_uid)) &&
(!uid_eq(new->uid, root_uid) &&
!uid_eq(new->euid, root_uid) &&
!uid_eq(new->suid, root_uid))) {
if (!issecure(SECURE_KEEP_CAPS)) {
cap_clear(new->cap_permitted);
cap_clear(new->cap_effective);
}
/*
* Pre-ambient programs expect setresuid to nonroot followed
* by exec to drop capabilities. We should make sure that
* this remains the case.
*/
cap_clear(new->cap_ambient);
}
if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid))
cap_clear(new->cap_effective);
if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid))
new->cap_effective = new->cap_permitted;
}
/**
* cap_task_fix_setuid - Fix up the results of setuid() call
* @new: The proposed credentials
* @old: The current task's current credentials
* @flags: Indications of what has changed
*
* Fix up the results of setuid() call before the credential changes are
* actually applied.
*
* Return: 0 to grant the changes, -ve to deny them.
*/
int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
{
switch (flags) {
case LSM_SETID_RE:
case LSM_SETID_ID:
case LSM_SETID_RES:
/* juggle the capabilities to follow [RES]UID changes unless
* otherwise suppressed */
if (!issecure(SECURE_NO_SETUID_FIXUP))
cap_emulate_setxuid(new, old);
break;
case LSM_SETID_FS:
/* juggle the capabilities to follow FSUID changes, unless
* otherwise suppressed
*
* FIXME - is fsuser used for all CAP_FS_MASK capabilities?
* if not, we might be a bit too harsh here.
*/
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
kuid_t root_uid = make_kuid(old->user_ns, 0);
if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid))
new->cap_effective =
cap_drop_fs_set(new->cap_effective);
if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid))
new->cap_effective =
cap_raise_fs_set(new->cap_effective,
new->cap_permitted);
}
break;
default:
return -EINVAL;
}
return 0;
}
/*
* Rationale: code calling task_setscheduler, task_setioprio, and
* task_setnice, assumes that
* . if capable(cap_sys_nice), then those actions should be allowed
* . if not capable(cap_sys_nice), but acting on your own processes,
* then those actions should be allowed
* This is insufficient now since you can call code without suid, but
* yet with increased caps.
* So we check for increased caps on the target process.
*/
static int cap_safe_nice(struct task_struct *p)
{
int is_subset, ret = 0;
rcu_read_lock();
is_subset = cap_issubset(__task_cred(p)->cap_permitted,
current_cred()->cap_permitted);
if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
ret = -EPERM;
rcu_read_unlock();
return ret;
}
/**
* cap_task_setscheduler - Determine if scheduler policy change is permitted
* @p: The task to affect
*
* Determine if the requested scheduler policy change is permitted for the
* specified task.
*
* Return: 0 if permission is granted, -ve if denied.
*/
int cap_task_setscheduler(struct task_struct *p)
{
return cap_safe_nice(p);
}
/**
* cap_task_setioprio - Determine if I/O priority change is permitted
* @p: The task to affect
* @ioprio: The I/O priority to set
*
* Determine if the requested I/O priority change is permitted for the specified
* task.
*
* Return: 0 if permission is granted, -ve if denied.
*/
int cap_task_setioprio(struct task_struct *p, int ioprio)
{
return cap_safe_nice(p);
}
/**
* cap_task_setnice - Determine if task priority change is permitted
* @p: The task to affect
* @nice: The nice value to set
*
* Determine if the requested task priority change is permitted for the
* specified task.
*
* Return: 0 if permission is granted, -ve if denied.
*/
int cap_task_setnice(struct task_struct *p, int nice)
{
return cap_safe_nice(p);
}
/*
* Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from
* the current task's bounding set. Returns 0 on success, -ve on error.
*/
static int cap_prctl_drop(unsigned long cap)
{
struct cred *new;
if (!ns_capable(current_user_ns(), CAP_SETPCAP))
return -EPERM;
if (!cap_valid(cap))
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
cap_lower(new->cap_bset, cap);
return commit_creds(new);
}
/**
* cap_task_prctl - Implement process control functions for this security module
* @option: The process control function requested
* @arg2: The argument data for this function
* @arg3: The argument data for this function
* @arg4: The argument data for this function
* @arg5: The argument data for this function
*
* Allow process control functions (sys_prctl()) to alter capabilities; may
* also deny access to other functions not otherwise implemented here.
*
* Return: 0 or +ve on success, -ENOSYS if this function is not implemented
* here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM
* modules will consider performing the function.
*/
int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
const struct cred *old = current_cred();
struct cred *new;
switch (option) {
case PR_CAPBSET_READ:
if (!cap_valid(arg2))
return -EINVAL;
return !!cap_raised(old->cap_bset, arg2);
case PR_CAPBSET_DROP:
return cap_prctl_drop(arg2);
/*
* The next four prctl's remain to assist with transitioning a
* system from legacy UID=0 based privilege (when filesystem
* capabilities are not in use) to a system using filesystem
* capabilities only - as the POSIX.1e draft intended.
*
* Note:
*
* PR_SET_SECUREBITS =
* issecure_mask(SECURE_KEEP_CAPS_LOCKED)
* | issecure_mask(SECURE_NOROOT)
* | issecure_mask(SECURE_NOROOT_LOCKED)
* | issecure_mask(SECURE_NO_SETUID_FIXUP)
* | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
*
* will ensure that the current process and all of its
* children will be locked into a pure
* capability-based-privilege environment.
*/
case PR_SET_SECUREBITS:
if ((((old->securebits & SECURE_ALL_LOCKS) >> 1)
& (old->securebits ^ arg2)) /*[1]*/
|| ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/
|| (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/
/*
* [1] no changing of bits that are locked
* [2] no unlocking of locks
* [3] no setting of unsupported bits
*/
)
/* cannot change a locked bit */
return -EPERM;
/*
* Doing anything requires privilege (go read about the
* "sendmail capabilities bug"), except for unprivileged bits.
* Indeed, the SECURE_ALL_UNPRIVILEGED bits are not
* restrictions enforced by the kernel but by user space on
* itself.
*/
if (cap_capable(current_cred(), current_cred()->user_ns,
CAP_SETPCAP, CAP_OPT_NONE) != 0) {
const unsigned long unpriv_and_locks =
SECURE_ALL_UNPRIVILEGED |
SECURE_ALL_UNPRIVILEGED << 1;
const unsigned long changed = old->securebits ^ arg2;
/* For legacy reason, denies non-change. */
if (!changed)
return -EPERM;
/* Denies privileged changes. */
if (changed & ~unpriv_and_locks)
return -EPERM;
}
new = prepare_creds();
if (!new)
return -ENOMEM;
new->securebits = arg2;
return commit_creds(new);
case PR_GET_SECUREBITS:
return old->securebits;
case PR_GET_KEEPCAPS:
return !!issecure(SECURE_KEEP_CAPS);
case PR_SET_KEEPCAPS:
if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
return -EINVAL;
if (issecure(SECURE_KEEP_CAPS_LOCKED))
return -EPERM;
new = prepare_creds();
if (!new)
return -ENOMEM;
if (arg2)
new->securebits |= issecure_mask(SECURE_KEEP_CAPS);
else
new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
return commit_creds(new);
case PR_CAP_AMBIENT:
if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) {
if (arg3 | arg4 | arg5)
return -EINVAL;
new = prepare_creds();
if (!new)
return -ENOMEM;
cap_clear(new->cap_ambient);
return commit_creds(new);
}
if (((!cap_valid(arg3)) | arg4 | arg5))
return -EINVAL;
if (arg2 == PR_CAP_AMBIENT_IS_SET) {
return !!cap_raised(current_cred()->cap_ambient, arg3);
} else if (arg2 != PR_CAP_AMBIENT_RAISE &&
arg2 != PR_CAP_AMBIENT_LOWER) {
return -EINVAL;
} else {
if (arg2 == PR_CAP_AMBIENT_RAISE &&
(!cap_raised(current_cred()->cap_permitted, arg3) ||
!cap_raised(current_cred()->cap_inheritable,
arg3) ||
issecure(SECURE_NO_CAP_AMBIENT_RAISE)))
return -EPERM;
new = prepare_creds();
if (!new)
return -ENOMEM;
if (arg2 == PR_CAP_AMBIENT_RAISE)
cap_raise(new->cap_ambient, arg3);
else
cap_lower(new->cap_ambient, arg3);
return commit_creds(new);
}
default:
/* No functionality available - continue with default */
return -ENOSYS;
}
}
/**
* cap_vm_enough_memory - Determine whether a new virtual mapping is permitted
* @mm: The VM space in which the new mapping is to be made
* @pages: The size of the mapping
*
* Determine whether the allocation of a new virtual mapping by the current
* task is permitted.
*
* Return: 0 if permission granted, negative error code if not.
*/
int cap_vm_enough_memory(struct mm_struct *mm, long pages)
{
return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN,
CAP_OPT_NOAUDIT);
}
/**
* cap_mmap_addr - check if able to map given addr
* @addr: address attempting to be mapped
*
* If the process is attempting to map memory below dac_mmap_min_addr they need
* CAP_SYS_RAWIO. The other parameters to this function are unused by the
* capability security module.
*
* Return: 0 if this mapping should be allowed or -EPERM if not.
*/
int cap_mmap_addr(unsigned long addr)
{
int ret = 0;
if (addr < dac_mmap_min_addr) {
ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO,
CAP_OPT_NONE);
/* set PF_SUPERPRIV if it turns out we allow the low mmap */
if (ret == 0) current->flags |= PF_SUPERPRIV;
}
return ret;
}
#ifdef CONFIG_SECURITY
static const struct lsm_id capability_lsmid = {
.name = "capability",
.id = LSM_ID_CAPABILITY,
};
static struct security_hook_list capability_hooks[] __ro_after_init = {
LSM_HOOK_INIT(capable, cap_capable),
LSM_HOOK_INIT(settime, cap_settime),
LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check),
LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme),
LSM_HOOK_INIT(capget, cap_capget),
LSM_HOOK_INIT(capset, cap_capset),
LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file),
LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv),
LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv),
LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity),
LSM_HOOK_INIT(mmap_addr, cap_mmap_addr),
LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid),
LSM_HOOK_INIT(task_prctl, cap_task_prctl),
LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler),
LSM_HOOK_INIT(task_setioprio, cap_task_setioprio),
LSM_HOOK_INIT(task_setnice, cap_task_setnice),
LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory),
};
static int __init capability_init(void)
{
security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks),
&capability_lsmid);
return 0;
}
DEFINE_LSM(capability) = {
.name = "capability",
.order = LSM_ORDER_FIRST,
.init = capability_init,
};
#endif /* CONFIG_SECURITY */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs-verity: read-only file-based authenticity protection
*
* This header declares the interface between the fs/verity/ support layer and
* filesystems that support fs-verity.
*
* Copyright 2019 Google LLC
*/
#ifndef _LINUX_FSVERITY_H
#define _LINUX_FSVERITY_H
#include <linux/fs.h>
#include <linux/mm.h>
#include <crypto/hash_info.h>
#include <crypto/sha2.h>
#include <uapi/linux/fsverity.h>
/*
* Largest digest size among all hash algorithms supported by fs-verity.
* Currently assumed to be <= size of fsverity_descriptor::root_hash.
*/
#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE
/* Arbitrary limit to bound the kmalloc() size. Can be changed. */
#define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384
/* Verity operations for filesystems */
struct fsverity_operations {
/**
* Begin enabling verity on the given file.
*
* @filp: a readonly file descriptor for the file
*
* The filesystem must do any needed filesystem-specific preparations
* for enabling verity, e.g. evicting inline data. It also must return
* -EBUSY if verity is already being enabled on the given file.
*
* i_rwsem is held for write.
*
* Return: 0 on success, -errno on failure
*/
int (*begin_enable_verity)(struct file *filp);
/**
* End enabling verity on the given file.
*
* @filp: a readonly file descriptor for the file
* @desc: the verity descriptor to write, or NULL on failure
* @desc_size: size of verity descriptor, or 0 on failure
* @merkle_tree_size: total bytes the Merkle tree took up
*
* If desc == NULL, then enabling verity failed and the filesystem only
* must do any necessary cleanups. Else, it must also store the given
* verity descriptor to a fs-specific location associated with the inode
* and do any fs-specific actions needed to mark the inode as a verity
* inode, e.g. setting a bit in the on-disk inode. The filesystem is
* also responsible for setting the S_VERITY flag in the VFS inode.
*
* i_rwsem is held for write, but it may have been dropped between
* ->begin_enable_verity() and ->end_enable_verity().
*
* Return: 0 on success, -errno on failure
*/
int (*end_enable_verity)(struct file *filp, const void *desc,
size_t desc_size, u64 merkle_tree_size);
/**
* Get the verity descriptor of the given inode.
*
* @inode: an inode with the S_VERITY flag set
* @buf: buffer in which to place the verity descriptor
* @bufsize: size of @buf, or 0 to retrieve the size only
*
* If bufsize == 0, then the size of the verity descriptor is returned.
* Otherwise the verity descriptor is written to 'buf' and its actual
* size is returned; -ERANGE is returned if it's too large. This may be
* called by multiple processes concurrently on the same inode.
*
* Return: the size on success, -errno on failure
*/
int (*get_verity_descriptor)(struct inode *inode, void *buf,
size_t bufsize);
/**
* Read a Merkle tree page of the given inode.
*
* @inode: the inode
* @index: 0-based index of the page within the Merkle tree
* @num_ra_pages: The number of Merkle tree pages that should be
* prefetched starting at @index if the page at @index
* isn't already cached. Implementations may ignore this
* argument; it's only a performance optimization.
*
* This can be called at any time on an open verity file. It may be
* called by multiple processes concurrently, even with the same page.
*
* Note that this must retrieve a *page*, not necessarily a *block*.
*
* Return: the page on success, ERR_PTR() on failure
*/
struct page *(*read_merkle_tree_page)(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages);
/**
* Write a Merkle tree block to the given inode.
*
* @inode: the inode for which the Merkle tree is being built
* @buf: the Merkle tree block to write
* @pos: the position of the block in the Merkle tree (in bytes)
* @size: the Merkle tree block size (in bytes)
*
* This is only called between ->begin_enable_verity() and
* ->end_enable_verity().
*
* Return: 0 on success, -errno on failure
*/
int (*write_merkle_tree_block)(struct inode *inode, const void *buf,
u64 pos, unsigned int size);
};
#ifdef CONFIG_FS_VERITY
static inline struct fsverity_info *fsverity_get_info(const struct inode *inode)
{
/*
* Pairs with the cmpxchg_release() in fsverity_set_info().
* I.e., another task may publish ->i_verity_info concurrently,
* executing a RELEASE barrier. We need to use smp_load_acquire() here
* to safely ACQUIRE the memory the other task published.
*/
return smp_load_acquire(&inode->i_verity_info);
}
/* enable.c */
int fsverity_ioctl_enable(struct file *filp, const void __user *arg);
/* measure.c */
int fsverity_ioctl_measure(struct file *filp, void __user *arg);
int fsverity_get_digest(struct inode *inode,
u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE],
u8 *alg, enum hash_algo *halg);
/* open.c */
int __fsverity_file_open(struct inode *inode, struct file *filp);
int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr);
void __fsverity_cleanup_inode(struct inode *inode);
/**
* fsverity_cleanup_inode() - free the inode's verity info, if present
* @inode: an inode being evicted
*
* Filesystems must call this on inode eviction to free ->i_verity_info.
*/
static inline void fsverity_cleanup_inode(struct inode *inode)
{
if (inode->i_verity_info)
__fsverity_cleanup_inode(inode);
}
/* read_metadata.c */
int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg);
/* verify.c */
bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset);
void fsverity_verify_bio(struct bio *bio);
void fsverity_enqueue_verify_work(struct work_struct *work);
#else /* !CONFIG_FS_VERITY */
static inline struct fsverity_info *fsverity_get_info(const struct inode *inode)
{
return NULL;
}
/* enable.c */
static inline int fsverity_ioctl_enable(struct file *filp,
const void __user *arg)
{
return -EOPNOTSUPP;
}
/* measure.c */
static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg)
{
return -EOPNOTSUPP;
}
static inline int fsverity_get_digest(struct inode *inode,
u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE],
u8 *alg, enum hash_algo *halg)
{
/*
* fsverity is not enabled in the kernel configuration, so always report
* that the file doesn't have fsverity enabled (digest size 0).
*/
return 0;
}
/* open.c */
static inline int __fsverity_file_open(struct inode *inode, struct file *filp)
{
return -EOPNOTSUPP;
}
static inline int __fsverity_prepare_setattr(struct dentry *dentry,
struct iattr *attr)
{
return -EOPNOTSUPP;
}
static inline void fsverity_cleanup_inode(struct inode *inode)
{
}
/* read_metadata.c */
static inline int fsverity_ioctl_read_metadata(struct file *filp,
const void __user *uarg)
{
return -EOPNOTSUPP;
}
/* verify.c */
static inline bool fsverity_verify_blocks(struct folio *folio, size_t len,
size_t offset)
{
WARN_ON_ONCE(1);
return false;
}
static inline void fsverity_verify_bio(struct bio *bio)
{
WARN_ON_ONCE(1);
}
static inline void fsverity_enqueue_verify_work(struct work_struct *work)
{
WARN_ON_ONCE(1);
}
#endif /* !CONFIG_FS_VERITY */
static inline bool fsverity_verify_folio(struct folio *folio)
{
return fsverity_verify_blocks(folio, folio_size(folio), 0);
}
static inline bool fsverity_verify_page(struct page *page)
{
return fsverity_verify_blocks(page_folio(page), PAGE_SIZE, 0);
}
/**
* fsverity_active() - do reads from the inode need to go through fs-verity?
* @inode: inode to check
*
* This checks whether ->i_verity_info has been set.
*
* Filesystems call this from ->readahead() to check whether the pages need to
* be verified or not. Don't use IS_VERITY() for this purpose; it's subject to
* a race condition where the file is being read concurrently with
* FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.)
*
* Return: true if reads need to go through fs-verity, otherwise false
*/
static inline bool fsverity_active(const struct inode *inode)
{
return fsverity_get_info(inode) != NULL;
}
/**
* fsverity_file_open() - prepare to open a verity file
* @inode: the inode being opened
* @filp: the struct file being set up
*
* When opening a verity file, deny the open if it is for writing. Otherwise,
* set up the inode's ->i_verity_info if not already done.
*
* When combined with fscrypt, this must be called after fscrypt_file_open().
* Otherwise, we won't have the key set up to decrypt the verity metadata.
*
* Return: 0 on success, -errno on failure
*/
static inline int fsverity_file_open(struct inode *inode, struct file *filp)
{
if (IS_VERITY(inode))
return __fsverity_file_open(inode, filp);
return 0;
}
/**
* fsverity_prepare_setattr() - prepare to change a verity inode's attributes
* @dentry: dentry through which the inode is being changed
* @attr: attributes to change
*
* Verity files are immutable, so deny truncates. This isn't covered by the
* open-time check because sys_truncate() takes a path, not a file descriptor.
*
* Return: 0 on success, -errno on failure
*/
static inline int fsverity_prepare_setattr(struct dentry *dentry,
struct iattr *attr)
{
if (IS_VERITY(d_inode(dentry)))
return __fsverity_prepare_setattr(dentry, attr);
return 0;
}
#endif /* _LINUX_FSVERITY_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <trace/events/kvm.h>
#include "trace.h"
void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data)
{
void *datap = NULL;
union {
u8 byte;
u16 hword;
u32 word;
u64 dword;
} tmp;
switch (len) {
case 1:
tmp.byte = data;
datap = &tmp.byte;
break;
case 2:
tmp.hword = data;
datap = &tmp.hword;
break;
case 4:
tmp.word = data;
datap = &tmp.word;
break;
case 8:
tmp.dword = data;
datap = &tmp.dword;
break;
}
memcpy(buf, datap, len);
}
unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len)
{
unsigned long data = 0;
union {
u16 hword;
u32 word;
u64 dword;
} tmp;
switch (len) {
case 1:
data = *(u8 *)buf;
break;
case 2:
memcpy(&tmp.hword, buf, len);
data = tmp.hword;
break;
case 4:
memcpy(&tmp.word, buf, len);
data = tmp.word;
break;
case 8:
memcpy(&tmp.dword, buf, len);
data = tmp.dword;
break;
}
return data;
}
static bool kvm_pending_sync_exception(struct kvm_vcpu *vcpu)
{
if (!vcpu_get_flag(vcpu, PENDING_EXCEPTION))
return false;
if (vcpu_el1_is_32bit(vcpu)) {
switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) {
case unpack_vcpu_flag(EXCEPT_AA32_UND):
case unpack_vcpu_flag(EXCEPT_AA32_IABT):
case unpack_vcpu_flag(EXCEPT_AA32_DABT):
return true;
default:
return false;
}
} else {
switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) {
case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC):
case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC):
return true;
default:
return false;
}
}
}
/**
* kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
* or in-kernel IO emulation
*
* @vcpu: The VCPU pointer
*/
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
{
unsigned long data;
unsigned int len;
int mask;
/*
* Detect if the MMIO return was already handled or if userspace aborted
* the MMIO access.
*/
if (unlikely(!vcpu->mmio_needed || kvm_pending_sync_exception(vcpu)))
return 1;
vcpu->mmio_needed = 0;
if (!kvm_vcpu_dabt_iswrite(vcpu)) {
struct kvm_run *run = vcpu->run;
len = kvm_vcpu_dabt_get_as(vcpu);
data = kvm_mmio_read_buf(run->mmio.data, len);
if (kvm_vcpu_dabt_issext(vcpu) &&
len < sizeof(unsigned long)) {
mask = 1U << ((len * 8) - 1);
data = (data ^ mask) - mask;
}
if (!kvm_vcpu_dabt_issf(vcpu)) data = data & 0xffffffff;
trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
&data);
data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
}
/*
* The MMIO instruction is emulated and should not be re-executed
* in the guest.
*/
kvm_incr_pc(vcpu);
return 1;
}
int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
struct kvm_run *run = vcpu->run;
unsigned long data;
unsigned long rt;
int ret;
bool is_write;
int len;
u8 data_buf[8];
/*
* No valid syndrome? Ask userspace for help if it has
* volunteered to do so, and bail out otherwise.
*
* In the protected VM case, there isn't much userspace can do
* though, so directly deliver an exception to the guest.
*/
if (!kvm_vcpu_dabt_isvalid(vcpu)) {
trace_kvm_mmio_nisv(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
kvm_vcpu_get_hfar(vcpu), fault_ipa);
if (vcpu_is_protected(vcpu)) { kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
return 1;
}
if (test_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER,
&vcpu->kvm->arch.flags)) {
run->exit_reason = KVM_EXIT_ARM_NISV;
run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu);
run->arm_nisv.fault_ipa = fault_ipa;
return 0;
}
return -ENOSYS;
}
/*
* Prepare MMIO operation. First decode the syndrome data we get
* from the CPU. Then try if some in-kernel emulation feels
* responsible, otherwise let user space do its magic.
*/
is_write = kvm_vcpu_dabt_iswrite(vcpu);
len = kvm_vcpu_dabt_get_as(vcpu);
rt = kvm_vcpu_dabt_get_rd(vcpu);
if (is_write) {
data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
len);
trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data);
kvm_mmio_write_buf(data_buf, len, data);
ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len,
data_buf);
} else {
trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len,
fault_ipa, NULL);
ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len,
data_buf);
}
/* Now prepare kvm_run for the potential return to userland. */
run->mmio.is_write = is_write;
run->mmio.phys_addr = fault_ipa;
run->mmio.len = len;
vcpu->mmio_needed = 1;
if (!ret) {
/* We handled the access successfully in the kernel. */
if (!is_write)
memcpy(run->mmio.data, data_buf, len);
vcpu->stat.mmio_exit_kernel++;
kvm_handle_mmio_return(vcpu);
return 1;
}
if (is_write)
memcpy(run->mmio.data, data_buf, len);
vcpu->stat.mmio_exit_user++;
run->exit_reason = KVM_EXIT_MMIO;
return 0;
}
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#ifndef __ARM64_KVM_MMU_H__
#define __ARM64_KVM_MMU_H__
#include <asm/page.h>
#include <asm/memory.h>
#include <asm/mmu.h>
#include <asm/cpufeature.h>
/*
* As ARMv8.0 only has the TTBR0_EL2 register, we cannot express
* "negative" addresses. This makes it impossible to directly share
* mappings with the kernel.
*
* Instead, give the HYP mode its own VA region at a fixed offset from
* the kernel by just masking the top bits (which are all ones for a
* kernel address). We need to find out how many bits to mask.
*
* We want to build a set of page tables that cover both parts of the
* idmap (the trampoline page used to initialize EL2), and our normal
* runtime VA space, at the same time.
*
* Given that the kernel uses VA_BITS for its entire address space,
* and that half of that space (VA_BITS - 1) is used for the linear
* mapping, we can also limit the EL2 space to (VA_BITS - 1).
*
* The main question is "Within the VA_BITS space, does EL2 use the
* top or the bottom half of that space to shadow the kernel's linear
* mapping?". As we need to idmap the trampoline page, this is
* determined by the range in which this page lives.
*
* If the page is in the bottom half, we have to use the top half. If
* the page is in the top half, we have to use the bottom half:
*
* T = __pa_symbol(__hyp_idmap_text_start)
* if (T & BIT(VA_BITS - 1))
* HYP_VA_MIN = 0 //idmap in upper half
* else
* HYP_VA_MIN = 1 << (VA_BITS - 1)
* HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
*
* When using VHE, there are no separate hyp mappings and all KVM
* functionality is already mapped as part of the main kernel
* mappings, and none of this applies in that case.
*/
#ifdef __ASSEMBLY__
#include <asm/alternative.h>
/*
* Convert a hypervisor VA to a PA
* reg: hypervisor address to be converted in place
* tmp: temporary register
*/
.macro hyp_pa reg, tmp
ldr_l \tmp, hyp_physvirt_offset
add \reg, \reg, \tmp
.endm
/*
* Convert a hypervisor VA to a kernel image address
* reg: hypervisor address to be converted in place
* tmp: temporary register
*
* The actual code generation takes place in kvm_get_kimage_voffset, and
* the instructions below are only there to reserve the space and
* perform the register allocation (kvm_get_kimage_voffset uses the
* specific registers encoded in the instructions).
*/
.macro hyp_kimg_va reg, tmp
/* Convert hyp VA -> PA. */
hyp_pa \reg, \tmp
/* Load kimage_voffset. */
alternative_cb ARM64_ALWAYS_SYSTEM, kvm_get_kimage_voffset
movz \tmp, #0
movk \tmp, #0, lsl #16
movk \tmp, #0, lsl #32
movk \tmp, #0, lsl #48
alternative_cb_end
/* Convert PA -> kimg VA. */
add \reg, \reg, \tmp
.endm
#else
#include <linux/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
#include <asm/kvm_nested.h>
void kvm_update_va_mask(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst);
void kvm_compute_layout(void);
void kvm_apply_hyp_relocations(void);
#define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
/*
* Convert a kernel VA into a HYP VA.
*
* Can be called from hyp or non-hyp context.
*
* The actual code generation takes place in kvm_update_va_mask(), and
* the instructions below are only there to reserve the space and
* perform the register allocation (kvm_update_va_mask() uses the
* specific registers encoded in the instructions).
*/
static __always_inline unsigned long __kern_hyp_va(unsigned long v)
{
/*
* This #ifndef is an optimisation for when this is called from VHE hyp
* context. When called from a VHE non-hyp context, kvm_update_va_mask() will
* replace the instructions with `nop`s.
*/
#ifndef __KVM_VHE_HYPERVISOR__
asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" /* mask with va_mask */
"ror %0, %0, #1\n" /* rotate to the first tag bit */
"add %0, %0, #0\n" /* insert the low 12 bits of the tag */
"add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */
"ror %0, %0, #63\n", /* rotate back */
ARM64_ALWAYS_SYSTEM,
kvm_update_va_mask)
: "+r" (v));
#endif
return v;
}
#define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v))))
extern u32 __hyp_va_bits;
/*
* We currently support using a VM-specified IPA size. For backward
* compatibility, the default IPA size is fixed to 40bits.
*/
#define KVM_PHYS_SHIFT (40)
#define kvm_phys_shift(mmu) VTCR_EL2_IPA((mmu)->vtcr)
#define kvm_phys_size(mmu) (_AC(1, ULL) << kvm_phys_shift(mmu))
#define kvm_phys_mask(mmu) (kvm_phys_size(mmu) - _AC(1, ULL))
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
int kvm_share_hyp(void *from, void *to);
void kvm_unshare_hyp(void *from, void *to);
int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
int __create_hyp_mappings(unsigned long start, unsigned long size,
unsigned long phys, enum kvm_pgtable_prot prot);
int hyp_alloc_private_va_range(size_t size, unsigned long *haddr);
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
void __iomem **kaddr,
void __iomem **haddr);
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr);
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
void __init free_hyp_pgds(void);
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
u64 size, bool may_block);
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
void stage2_unmap_vm(struct kvm *kvm);
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
void kvm_uninit_stage2_mmu(struct kvm *kvm);
void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
phys_addr_t pa, unsigned long size, bool writable);
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
phys_addr_t kvm_mmu_get_httbr(void);
phys_addr_t kvm_get_idmap_vector(void);
int __init kvm_mmu_init(u32 *hyp_va_bits);
static inline void *__kvm_vector_slot2addr(void *base,
enum arm64_hyp_spectre_vector slot)
{
int idx = slot - (slot != HYP_VECTOR_DIRECT);
return base + (idx * SZ_2K);
}
struct kvm;
#define kvm_flush_dcache_to_poc(a,l) \
dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
{
u64 cache_bits = SCTLR_ELx_M | SCTLR_ELx_C;
int reg;
if (vcpu_is_el2(vcpu))
reg = SCTLR_EL2;
else
reg = SCTLR_EL1;
return (vcpu_read_sys_reg(vcpu, reg) & cache_bits) == cache_bits;
}
static inline void __clean_dcache_guest_page(void *va, size_t size)
{
/*
* With FWB, we ensure that the guest always accesses memory using
* cacheable attributes, and we don't have to clean to PoC when
* faulting in pages. Furthermore, FWB implies IDC, so cleaning to
* PoU is not required either in this case.
*/
if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
return;
kvm_flush_dcache_to_poc(va, size);
}
static inline size_t __invalidate_icache_max_range(void)
{
u8 iminline;
u64 ctr;
asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
"movk %0, #0, lsl #16\n"
"movk %0, #0, lsl #32\n"
"movk %0, #0, lsl #48\n",
ARM64_ALWAYS_SYSTEM,
kvm_compute_final_ctr_el0)
: "=r" (ctr));
iminline = SYS_FIELD_GET(CTR_EL0, IminLine, ctr) + 2;
return MAX_DVM_OPS << iminline;
}
static inline void __invalidate_icache_guest_page(void *va, size_t size)
{
/*
* Blow the whole I-cache if it is aliasing (i.e. VIPT) or the
* invalidation range exceeds our arbitrary limit on invadations by
* cache line.
*/
if (icache_is_aliasing() || size > __invalidate_icache_max_range()) icache_inval_all_pou();
else
icache_inval_pou((unsigned long)va, (unsigned long)va + size);
}
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
static inline unsigned int kvm_get_vmid_bits(void)
{
int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
return get_vmid_bits(reg);
}
/*
* We are not in the kvm->srcu critical section most of the time, so we take
* the SRCU read lock here. Since we copy the data from the user page, we
* can immediately drop the lock again.
*/
static inline int kvm_read_guest_lock(struct kvm *kvm,
gpa_t gpa, void *data, unsigned long len)
{
int srcu_idx = srcu_read_lock(&kvm->srcu);
int ret = kvm_read_guest(kvm, gpa, data, len);
srcu_read_unlock(&kvm->srcu, srcu_idx);
return ret;
}
static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
const void *data, unsigned long len)
{
int srcu_idx = srcu_read_lock(&kvm->srcu);
int ret = kvm_write_guest(kvm, gpa, data, len);
srcu_read_unlock(&kvm->srcu, srcu_idx);
return ret;
}
#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
/*
* When this is (directly or indirectly) used on the TLB invalidation
* path, we rely on a previously issued DSB so that page table updates
* and VMID reads are correctly ordered.
*/
static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
{
struct kvm_vmid *vmid = &mmu->vmid;
u64 vmid_field, baddr;
u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
baddr = mmu->pgd_phys;
vmid_field = atomic64_read(&vmid->id) << VTTBR_VMID_SHIFT;
vmid_field &= VTTBR_VMID_MASK(kvm_arm_vmid_bits);
return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
}
/*
* Must be called from hyp code running at EL2 with an updated VTTBR
* and interrupts disabled.
*/
static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
struct kvm_arch *arch)
{
write_sysreg(mmu->vtcr, vtcr_el2);
write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
/*
* ARM errata 1165522 and 1530923 require the actual execution of the
* above before we can switch to the EL1/EL0 translation regime used by
* the guest.
*/
asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
}
static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
{
return container_of(mmu->arch, struct kvm, arch);
}
static inline u64 get_vmid(u64 vttbr)
{
return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
VTTBR_VMID_SHIFT;
}
static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
{
return !(mmu->tlb_vttbr & VTTBR_CNP_BIT);
}
static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
{
/*
* Be careful, mmu may not be fully initialised so do look at
* *any* of its fields.
*/
return &kvm->arch.mmu != mmu;
}
static inline void kvm_fault_lock(struct kvm *kvm)
{
if (is_protected_kvm_enabled()) write_lock(&kvm->mmu_lock);
else
read_lock(&kvm->mmu_lock);
}
static inline void kvm_fault_unlock(struct kvm *kvm)
{
if (is_protected_kvm_enabled()) write_unlock(&kvm->mmu_lock);
else
read_unlock(&kvm->mmu_lock);
}
#ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
#else
static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {}
#endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* include/linux/eventpoll.h ( Efficient event polling implementation )
* Copyright (C) 2001,...,2006 Davide Libenzi
*
* Davide Libenzi <davidel@xmailserver.org>
*/
#ifndef _LINUX_EVENTPOLL_H
#define _LINUX_EVENTPOLL_H
#include <uapi/linux/eventpoll.h>
#include <uapi/linux/kcmp.h>
/* Forward declarations to avoid compiler errors */
struct file;
#ifdef CONFIG_EPOLL
#ifdef CONFIG_KCMP
struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
#endif
/* Used to release the epoll bits inside the "struct file" */
void eventpoll_release_file(struct file *file);
/* Copy ready events to userspace */
int epoll_sendevents(struct file *file, struct epoll_event __user *events,
int maxevents);
/*
* This is called from inside fs/file_table.c:__fput() to unlink files
* from the eventpoll interface. We need to have this facility to cleanup
* correctly files that are closed without being removed from the eventpoll
* interface.
*/
static inline void eventpoll_release(struct file *file)
{
/*
* Fast check to avoid the get/release of the semaphore. Since
* we're doing this outside the semaphore lock, it might return
* false negatives, but we don't care. It'll help in 99.99% of cases
* to avoid the semaphore lock. False positives simply cannot happen
* because the file in on the way to be removed and nobody ( but
* eventpoll ) has still a reference to this file.
*/
if (likely(!READ_ONCE(file->f_ep)))
return;
/*
* The file is being closed while it is still linked to an epoll
* descriptor. We need to handle this by correctly unlinking it
* from its containers.
*/
eventpoll_release_file(file);
}
int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
bool nonblock);
/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
static inline int ep_op_has_event(int op)
{
return op != EPOLL_CTL_DEL;
}
#else
static inline void eventpoll_release(struct file *file) {}
#endif
#if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT)
/* ARM OABI has an incompatible struct layout and needs a special handler */
extern struct epoll_event __user *
epoll_put_uevent(__poll_t revents, __u64 data,
struct epoll_event __user *uevent);
#else
static inline struct epoll_event __user *
epoll_put_uevent(__poll_t revents, __u64 data,
struct epoll_event __user *uevent)
{
if (__put_user(revents, &uevent->events) ||
__put_user(data, &uevent->data))
return NULL;
return uevent+1;
}
#endif
#endif /* #ifndef _LINUX_EVENTPOLL_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _NETFILTER_NETDEV_H_
#define _NETFILTER_NETDEV_H_
#include <linux/netfilter.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NETFILTER_INGRESS
static inline bool nf_hook_ingress_active(const struct sk_buff *skb)
{
#ifdef CONFIG_JUMP_LABEL
if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS]))
return false;
#endif
return rcu_access_pointer(skb->dev->nf_hooks_ingress);
}
/* caller must hold rcu_read_lock */
static inline int nf_hook_ingress(struct sk_buff *skb)
{
struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress);
struct nf_hook_state state;
int ret;
/* Must recheck the ingress hook head, in the event it became NULL
* after the check in nf_hook_ingress_active evaluated to true.
*/
if (unlikely(!e))
return 0;
nf_hook_state_init(&state, NF_NETDEV_INGRESS,
NFPROTO_NETDEV, skb->dev, NULL, NULL,
dev_net(skb->dev), NULL);
ret = nf_hook_slow(skb, &state, e, 0);
if (ret == 0)
return -1;
return ret;
}
#else /* CONFIG_NETFILTER_INGRESS */
static inline int nf_hook_ingress_active(struct sk_buff *skb)
{
return 0;
}
static inline int nf_hook_ingress(struct sk_buff *skb)
{
return 0;
}
#endif /* CONFIG_NETFILTER_INGRESS */
#ifdef CONFIG_NETFILTER_EGRESS
static inline bool nf_hook_egress_active(void)
{
#ifdef CONFIG_JUMP_LABEL
if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS]))
return false;
#endif
return true;
}
/**
* nf_hook_egress - classify packets before transmission
* @skb: packet to be classified
* @rc: result code which shall be returned by __dev_queue_xmit() on failure
* @dev: netdev whose egress hooks shall be applied to @skb
*
* Caller must hold rcu_read_lock.
*
* On ingress, packets are classified first by tc, then by netfilter.
* On egress, the order is reversed for symmetry. Conceptually, tc and
* netfilter can be thought of as layers, with netfilter layered above tc:
* When tc redirects a packet to another interface, netfilter is not applied
* because the packet is on the tc layer.
*
* The nf_skip_egress flag controls whether netfilter is applied on egress.
* It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the
* packet passes through tc and netfilter. Because __dev_queue_xmit() may be
* called recursively by tunnel drivers such as vxlan, the flag is reverted to
* false after sch_handle_egress(). This ensures that netfilter is applied
* both on the overlay and underlying network.
*
* Returns: @skb on success or %NULL if the packet was consumed or filtered.
*/
static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc,
struct net_device *dev)
{
struct nf_hook_entries *e;
struct nf_hook_state state;
int ret;
#ifdef CONFIG_NETFILTER_SKIP_EGRESS
if (skb->nf_skip_egress)
return skb;
#endif
e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held());
if (!e)
return skb;
nf_hook_state_init(&state, NF_NETDEV_EGRESS,
NFPROTO_NETDEV, NULL, dev, NULL,
dev_net(dev), NULL);
/* nf assumes rcu_read_lock, not just read_lock_bh */
rcu_read_lock();
ret = nf_hook_slow(skb, &state, e, 0);
rcu_read_unlock();
if (ret == 1) {
return skb;
} else if (ret < 0) {
*rc = NET_XMIT_DROP;
return NULL;
} else { /* ret == 0 */
*rc = NET_XMIT_SUCCESS;
return NULL;
}
}
#else /* CONFIG_NETFILTER_EGRESS */
static inline bool nf_hook_egress_active(void)
{
return false;
}
static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc,
struct net_device *dev)
{
return skb;
}
#endif /* CONFIG_NETFILTER_EGRESS */
static inline void nf_skip_egress(struct sk_buff *skb, bool skip)
{
#ifdef CONFIG_NETFILTER_SKIP_EGRESS
skb->nf_skip_egress = skip;
#endif
}
static inline void nf_hook_netdev_init(struct net_device *dev)
{
#ifdef CONFIG_NETFILTER_INGRESS
RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL);
#endif
#ifdef CONFIG_NETFILTER_EGRESS
RCU_INIT_POINTER(dev->nf_hooks_egress, NULL);
#endif
}
#endif /* _NETFILTER_NETDEV_H_ */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
#define _ASM_GENERIC_BITOPS_FLS64_H_
#include <asm/types.h>
/**
* fls64 - find last set bit in a 64-bit word
* @x: the word to search
*
* This is defined in a similar way as the libc and compiler builtin
* ffsll, but returns the position of the most significant set bit.
*
* fls64(value) returns 0 if value is 0 or the position of the last
* set bit if value is nonzero. The last (most significant) bit is
* at position 64.
*/
#if BITS_PER_LONG == 32
static __always_inline int fls64(__u64 x)
{
__u32 h = x >> 32;
if (h)
return fls(h) + 32;
return fls(x);
}
#elif BITS_PER_LONG == 64
static __always_inline int fls64(__u64 x)
{
if (x == 0)
return 0;
return __fls(x) + 1;
}
#else
#error BITS_PER_LONG not 32 or 64
#endif
#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef LINUX_RESUME_USER_MODE_H
#define LINUX_RESUME_USER_MODE_H
#include <linux/sched.h>
#include <linux/task_work.h>
#include <linux/memcontrol.h>
#include <linux/rseq.h>
#include <linux/blk-cgroup.h>
/**
* set_notify_resume - cause resume_user_mode_work() to be called
* @task: task that will call resume_user_mode_work()
*
* Calling this arranges that @task will call resume_user_mode_work()
* before returning to user mode. If it's already running in user mode,
* it will enter the kernel and call resume_user_mode_work() soon.
* If it's blocked, it will not be woken.
*/
static inline void set_notify_resume(struct task_struct *task)
{
if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task);
}
/**
* resume_user_mode_work - Perform work before returning to user mode
* @regs: user-mode registers of @current task
*
* This is called when %TIF_NOTIFY_RESUME has been set. Now we are
* about to return to user mode, and the user state in @regs can be
* inspected or adjusted. The caller in arch code has cleared
* %TIF_NOTIFY_RESUME before the call. If the flag gets set again
* asynchronously, this will be called again before we return to
* user mode.
*
* Called without locks.
*/
static inline void resume_user_mode_work(struct pt_regs *regs)
{
clear_thread_flag(TIF_NOTIFY_RESUME);
/*
* This barrier pairs with task_work_add()->set_notify_resume() after
* hlist_add_head(task->task_works);
*/
smp_mb__after_atomic();
if (unlikely(task_work_pending(current)))
task_work_run();
#ifdef CONFIG_KEYS_REQUEST_CACHE
if (unlikely(current->cached_requested_key)) {
key_put(current->cached_requested_key);
current->cached_requested_key = NULL;
}
#endif
mem_cgroup_handle_over_high(GFP_KERNEL);
blkcg_maybe_throttle_current();
rseq_handle_notify_resume(NULL, regs);
}
#endif /* LINUX_RESUME_USER_MODE_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/open.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
#include <linux/falloc.h>
#include <linux/fs_struct.h>
#include <linux/dnotify.h>
#include <linux/compat.h>
#include <linux/mnt_idmapping.h>
#include <linux/filelock.h>
#include "internal.h"
int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
loff_t length, unsigned int time_attrs, struct file *filp)
{
int ret;
struct iattr newattrs;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
if (length < 0)
return -EINVAL;
newattrs.ia_size = length;
newattrs.ia_valid = ATTR_SIZE | time_attrs;
if (filp) { newattrs.ia_file = filp;
newattrs.ia_valid |= ATTR_FILE;
}
/* Remove suid, sgid, and file capabilities on truncate too */
ret = dentry_needs_remove_privs(idmap, dentry);
if (ret < 0)
return ret;
if (ret) newattrs.ia_valid |= ret | ATTR_FORCE;
inode_lock(dentry->d_inode);
/* Note any delegations or leases have already been broken: */
ret = notify_change(idmap, dentry, &newattrs, NULL);
inode_unlock(dentry->d_inode);
return ret;
}
int vfs_truncate(const struct path *path, loff_t length)
{
struct mnt_idmap *idmap;
struct inode *inode;
int error;
inode = path->dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
idmap = mnt_idmap(path->mnt);
error = inode_permission(idmap, inode, MAY_WRITE);
if (error)
return error;
error = fsnotify_truncate_perm(path, length);
if (error)
return error;
error = mnt_want_write(path->mnt);
if (error)
return error;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = security_path_truncate(path);
if (!error)
error = do_truncate(idmap, path->dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
return error;
}
EXPORT_SYMBOL_GPL(vfs_truncate);
int do_sys_truncate(const char __user *pathname, loff_t length)
{
unsigned int lookup_flags = LOOKUP_FOLLOW;
struct path path;
int error;
if (length < 0) /* sorry, but loff_t says... */
return -EINVAL;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (!error) {
error = vfs_truncate(&path, length);
path_put(&path);
}
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
{
return do_sys_truncate(path, length);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
{
return do_sys_truncate(path, length);
}
#endif
int do_ftruncate(struct file *file, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
int error;
/* explicitly opened as large or we are on 64-bit box */
if (file->f_flags & O_LARGEFILE)
small = 0;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
return -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
return -EINVAL;
/* Check IS_APPEND on real upper inode */
if (IS_APPEND(file_inode(file)))
return -EPERM;
error = security_file_truncate(file);
if (error)
return error;
error = fsnotify_truncate_perm(&file->f_path, length);
if (error)
return error;
sb_start_write(inode->i_sb);
error = do_truncate(file_mnt_idmap(file), dentry, length,
ATTR_MTIME | ATTR_CTIME, file);
sb_end_write(inode->i_sb);
return error;
}
int do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
if (length < 0)
return -EINVAL;
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
return do_ftruncate(fd_file(f), length, small);
}
SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#endif
/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length)
{
return do_sys_truncate(path, length);
}
SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
{
return do_sys_ftruncate(fd, length, 0);
}
#endif /* BITS_PER_LONG == 32 */
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64)
COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname,
compat_arg_u64_dual(length))
{
return ksys_truncate(pathname, compat_arg_u64_glue(length));
}
#endif
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64)
COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd,
compat_arg_u64_dual(length))
{
return ksys_ftruncate(fd, compat_arg_u64_glue(length));
}
#endif
int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
int ret;
loff_t sum;
if (offset < 0 || len <= 0)
return -EINVAL;
if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
/*
* Modes are exclusive, even if that is not obvious from the encoding
* as bit masks and the mix with the flag in the same namespace.
*
* To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is
* encoded as no bit set.
*/
switch (mode & FALLOC_FL_MODE_MASK) {
case FALLOC_FL_ALLOCATE_RANGE:
case FALLOC_FL_UNSHARE_RANGE:
case FALLOC_FL_ZERO_RANGE:
break;
case FALLOC_FL_PUNCH_HOLE:
if (!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
break;
case FALLOC_FL_COLLAPSE_RANGE:
case FALLOC_FL_INSERT_RANGE:
if (mode & FALLOC_FL_KEEP_SIZE)
return -EOPNOTSUPP;
break;
default:
return -EOPNOTSUPP;
}
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/*
* On append-only files only space preallocation is supported.
*/
if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* We cannot allow any fallocate operation on an active swapfile
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
if (S_ISDIR(inode->i_mode))
return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
return -ENODEV;
/* Check for wraparound */
if (check_add_overflow(offset, len, &sum))
return -EFBIG;
if (sum > inode->i_sb->s_maxbytes)
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
file_start_write(file);
ret = file->f_op->fallocate(file, mode, offset, len);
/*
* Create inotify and fanotify events.
*
* To keep the logic simple always create events if fallocate succeeds.
* This implies that events are even created if the file size remains
* unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
*/
if (ret == 0) fsnotify_modify(file); file_end_write(file);
return ret;
}
EXPORT_SYMBOL_GPL(vfs_fallocate);
int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len)
{
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
return vfs_fallocate(fd_file(f), mode, offset, len);
}
SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
{
return ksys_fallocate(fd, mode, offset, len);
}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE)
COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset),
compat_arg_u64_dual(len))
{
return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset),
compat_arg_u64_glue(len));
}
#endif
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*
* Creating new credentials is expensive, so we try to skip doing it,
* which we can if the result would match what we already got.
*/
static bool access_need_override_creds(int flags)
{
const struct cred *cred;
if (flags & AT_EACCESS)
return false;
cred = current_cred();
if (!uid_eq(cred->fsuid, cred->uid) ||
!gid_eq(cred->fsgid, cred->gid))
return true;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
kuid_t root_uid = make_kuid(cred->user_ns, 0);
if (!uid_eq(cred->uid, root_uid)) {
if (!cap_isclear(cred->cap_effective))
return true;
} else {
if (!cap_isidentical(cred->cap_effective,
cred->cap_permitted))
return true;
}
}
return false;
}
static const struct cred *access_override_creds(void)
{
struct cred *override_cred;
override_cred = prepare_creds();
if (!override_cred)
return NULL;
/*
* XXX access_need_override_creds performs checks in hopes of skipping
* this work. Make sure it stays in sync if making any changes in this
* routine.
*/
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/* Clear the capabilities if we switch to a non-root user */
kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
if (!uid_eq(override_cred->uid, root_uid))
cap_clear(override_cred->cap_effective);
else
override_cred->cap_effective =
override_cred->cap_permitted;
}
/*
* The new set of credentials can *only* be used in
* task-synchronous circumstances, and does not need
* RCU freeing, unless somebody then takes a separate
* reference to it.
*
* NOTE! This is _only_ true because this credential
* is used purely for override_creds() that installs
* it as the subjective cred. Other threads will be
* accessing ->real_cred, not the subjective cred.
*
* If somebody _does_ make a copy of this (using the
* 'get_current_cred()' function), that will clear the
* non_rcu field, because now that other user may be
* expecting RCU freeing. But normal thread-synchronous
* cred accesses will keep things non-racy to avoid RCU
* freeing.
*/
override_cred->non_rcu = 1;
return override_creds(override_cred);
}
static int do_faccessat(int dfd, const char __user *filename, int mode, int flags)
{
struct path path;
struct inode *inode;
int res;
unsigned int lookup_flags = LOOKUP_FOLLOW;
const struct cred *old_cred = NULL;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
return -EINVAL;
if (flags & AT_SYMLINK_NOFOLLOW)
lookup_flags &= ~LOOKUP_FOLLOW;
if (flags & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
if (access_need_override_creds(flags)) {
old_cred = access_override_creds();
if (!old_cred)
return -ENOMEM;
}
retry:
res = user_path_at(dfd, filename, lookup_flags, &path);
if (res)
goto out;
inode = d_backing_inode(path.dentry);
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path_noexec(&path))
goto out_path_release;
}
res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
if (retry_estale(res, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
if (old_cred)
put_cred(revert_creds(old_cred));
return res;
}
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
return do_faccessat(dfd, filename, mode, 0);
}
SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode,
int, flags)
{
return do_faccessat(dfd, filename, mode, flags);
}
SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
{
return do_faccessat(AT_FDCWD, filename, mode, 0);
}
SYSCALL_DEFINE1(chdir, const char __user *, filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
set_fs_pwd(current->fs, &path);
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
CLASS(fd_raw, f)(fd);
int error;
if (fd_empty(f))
return -EBADF;
if (!d_can_lookup(fd_file(f)->f_path.dentry))
return -ENOTDIR;
error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &fd_file(f)->f_path);
return error;
}
SYSCALL_DEFINE1(chroot, const char __user *, filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
goto dput_and_out;
error = security_path_chroot(&path);
if (error)
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
int chmod_common(const struct path *path, umode_t mode)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
struct iattr newattrs;
int error;
error = mnt_want_write(path->mnt);
if (error)
return error;
retry_deleg:
inode_lock(inode);
error = security_path_chmod(path, mode);
if (error)
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(mnt_idmap(path->mnt), path->dentry,
&newattrs, &delegated_inode);
out_unlock:
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
mnt_drop_write(path->mnt);
return error;
}
int vfs_fchmod(struct file *file, umode_t mode)
{
audit_file(file);
return chmod_common(&file->f_path, mode);
}
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
return vfs_fchmod(fd_file(f), mode);
}
static int do_fchmodat(int dfd, const char __user *filename, umode_t mode,
unsigned int flags)
{
struct path path;
int error;
unsigned int lookup_flags;
if (unlikely(flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)))
return -EINVAL;
lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
if (flags & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (!error) {
error = chmod_common(&path, mode);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
}
return error;
}
SYSCALL_DEFINE4(fchmodat2, int, dfd, const char __user *, filename,
umode_t, mode, unsigned int, flags)
{
return do_fchmodat(dfd, filename, mode, flags);
}
SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename,
umode_t, mode)
{
return do_fchmodat(dfd, filename, mode, 0);
}
SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
{
return do_fchmodat(AT_FDCWD, filename, mode, 0);
}
/*
* Check whether @kuid is valid and if so generate and set vfsuid_t in
* ia_vfsuid.
*
* Return: true if @kuid is valid, false if not.
*/
static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid)
{
if (!uid_valid(kuid))
return false;
attr->ia_valid |= ATTR_UID;
attr->ia_vfsuid = VFSUIDT_INIT(kuid);
return true;
}
/*
* Check whether @kgid is valid and if so generate and set vfsgid_t in
* ia_vfsgid.
*
* Return: true if @kgid is valid, false if not.
*/
static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid)
{
if (!gid_valid(kgid))
return false;
attr->ia_valid |= ATTR_GID;
attr->ia_vfsgid = VFSGIDT_INIT(kgid);
return true;
}
int chown_common(const struct path *path, uid_t user, gid_t group)
{
struct mnt_idmap *idmap;
struct user_namespace *fs_userns;
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
struct iattr newattrs;
kuid_t uid;
kgid_t gid;
uid = make_kuid(current_user_ns(), user);
gid = make_kgid(current_user_ns(), group);
idmap = mnt_idmap(path->mnt);
fs_userns = i_user_ns(inode);
retry_deleg:
newattrs.ia_vfsuid = INVALID_VFSUID;
newattrs.ia_vfsgid = INVALID_VFSGID;
newattrs.ia_valid = ATTR_CTIME;
if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid))
return -EINVAL;
if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid))
return -EINVAL;
inode_lock(inode);
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV |
setattr_should_drop_sgid(idmap, inode);
/* Continue to send actual fs values, not the mount values. */
error = security_path_chown(
path,
from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid),
from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid));
if (!error)
error = notify_change(idmap, path->dentry, &newattrs,
&delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
int flag)
{
struct path path;
int error = -EINVAL;
int lookup_flags;
if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
goto out;
lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
gid_t, group, int, flag)
{
return do_fchownat(dfd, filename, user, group, flag);
}
SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
{
return do_fchownat(AT_FDCWD, filename, user, group, 0);
}
SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
{
return do_fchownat(AT_FDCWD, filename, user, group,
AT_SYMLINK_NOFOLLOW);
}
int vfs_fchown(struct file *file, uid_t user, gid_t group)
{
int error;
error = mnt_want_write_file(file);
if (error)
return error;
audit_file(file);
error = chown_common(&file->f_path, user, group);
mnt_drop_write_file(file);
return error;
}
int ksys_fchown(unsigned int fd, uid_t user, gid_t group)
{
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
return vfs_fchown(fd_file(f), user, group);
}
SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
{
return ksys_fchown(fd, user, group);
}
static inline int file_get_write_access(struct file *f)
{
int error;
error = get_write_access(f->f_inode);
if (unlikely(error))
return error;
error = mnt_get_write_access(f->f_path.mnt);
if (unlikely(error))
goto cleanup_inode;
if (unlikely(f->f_mode & FMODE_BACKING)) {
error = mnt_get_write_access(backing_file_user_path(f)->mnt);
if (unlikely(error))
goto cleanup_mnt;
}
return 0;
cleanup_mnt:
mnt_put_write_access(f->f_path.mnt);
cleanup_inode:
put_write_access(f->f_inode);
return error;
}
static int do_dentry_open(struct file *f,
int (*open)(struct inode *, struct file *))
{
static const struct file_operations empty_fops = {};
struct inode *inode = f->f_path.dentry->d_inode;
int error;
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
f->f_sb_err = file_sample_sb_err(f);
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
file_set_fsnotify_mode(f, FMODE_NONOTIFY);
f->f_op = &empty_fops;
return 0;
}
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) {
i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = file_get_write_access(f);
if (unlikely(error))
goto cleanup_file;
f->f_mode |= FMODE_WRITER;
}
/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop);
if (WARN_ON(!f->f_op)) {
error = -ENODEV;
goto cleanup_all;
}
error = security_file_open(f);
if (error)
goto cleanup_all;
/*
* Set FMODE_NONOTIFY_* bits according to existing permission watches.
* If FMODE_NONOTIFY mode was already set for an fanotify fd or for a
* pseudo file, this call will not change the mode.
*/
file_set_fsnotify_mode_from_watchers(f);
error = fsnotify_open_perm(f); if (error)
goto cleanup_all;
error = break_lease(file_inode(f), f->f_flags); if (error)
goto cleanup_all;
/* normally all 3 are set; ->open() can clear them if needed */
f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
if (!open)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
f->f_mode |= FMODE_OPENED;
if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter))
f->f_mode |= FMODE_CAN_READ;
if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
if ((f->f_mode & FMODE_LSEEK) && !f->f_op->llseek) f->f_mode &= ~FMODE_LSEEK; if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) f->f_mode |= FMODE_CAN_ODIRECT;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
f->f_iocb_flags = iocb_flags(f);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT))
return -EINVAL;
/*
* XXX: Huge page cache doesn't support writing yet. Drop all page
* cache for this file before processing writes.
*/
if (f->f_mode & FMODE_WRITE) {
/*
* Depends on full fence from get_write_access() to synchronize
* against collapse_file() regarding i_writecount and nr_thps
* updates. Ensures subsequent insertion of THPs into the page
* cache will fail.
*/
if (filemap_nr_thps(inode->i_mapping)) { struct address_space *mapping = inode->i_mapping;
filemap_invalidate_lock(inode->i_mapping);
/*
* unmap_mapping_range just need to be called once
* here, because the private pages is not need to be
* unmapped mapping (e.g. data segment of dynamic
* shared libraries here).
*/
unmap_mapping_range(mapping, 0, 0, 0);
truncate_inode_pages(mapping, 0);
filemap_invalidate_unlock(inode->i_mapping);
}
}
return 0;
cleanup_all:
if (WARN_ON_ONCE(error > 0))
error = -EINVAL;
fops_put(f->f_op); put_file_access(f);
cleanup_file:
path_put(&f->f_path);
f->f_path.mnt = NULL;
f->f_path.dentry = NULL;
f->f_inode = NULL;
return error;
}
/**
* finish_open - finish opening a file
* @file: file pointer
* @dentry: pointer to dentry
* @open: open callback
*
* This can be used to finish opening a file passed to i_op->atomic_open().
*
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
*
* NB: the dentry reference is _not_ consumed. If, for example, the dentry is
* the return value of d_splice_alias(), then the caller needs to perform dput()
* on it after finish_open().
*
* Returns zero on success or -errno if the open failed.
*/
int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *))
{ BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry;
return do_dentry_open(file, open);
}
EXPORT_SYMBOL(finish_open);
/**
* finish_no_open - finish ->atomic_open() without opening the file
*
* @file: file pointer
* @dentry: dentry or NULL (as returned from ->lookup())
*
* This can be used to set the result of a successful lookup in ->atomic_open().
*
* NB: unlike finish_open() this function does consume the dentry reference and
* the caller need not dput() it.
*
* Returns "0" which must be the return value of ->atomic_open() after having
* called this function.
*/
int finish_no_open(struct file *file, struct dentry *dentry)
{
file->f_path.dentry = dentry;
return 0;
}
EXPORT_SYMBOL(finish_no_open);
char *file_path(struct file *filp, char *buf, int buflen)
{
return d_path(&filp->f_path, buf, buflen);
}
EXPORT_SYMBOL(file_path);
/**
* vfs_open - open the file at the given path
* @path: path to open
* @file: newly allocated file with f_flag initialized
*/
int vfs_open(const struct path *path, struct file *file)
{
int ret;
file->f_path = *path;
ret = do_dentry_open(file, NULL);
if (!ret) {
/*
* Once we return a file with FMODE_OPENED, __fput() will call
* fsnotify_close(), so we need fsnotify_open() here for
* symmetry.
*/
fsnotify_open(file);
}
return ret;
}
struct file *dentry_open(const struct path *path, int flags,
const struct cred *cred)
{
int error;
struct file *f;
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
f = alloc_empty_file(flags, cred);
if (!IS_ERR(f)) {
error = vfs_open(path, f);
if (error) { fput(f);
f = ERR_PTR(error);
}
}
return f;
}
EXPORT_SYMBOL(dentry_open);
struct file *dentry_open_nonotify(const struct path *path, int flags,
const struct cred *cred)
{
struct file *f = alloc_empty_file(flags, cred);
if (!IS_ERR(f)) {
int error;
file_set_fsnotify_mode(f, FMODE_NONOTIFY);
error = vfs_open(path, f);
if (error) {
fput(f);
f = ERR_PTR(error);
}
}
return f;
}
/**
* dentry_create - Create and open a file
* @path: path to create
* @flags: O_ flags
* @mode: mode bits for new file
* @cred: credentials to use
*
* Caller must hold the parent directory's lock, and have prepared
* a negative dentry, placed in @path->dentry, for the new file.
*
* Caller sets @path->mnt to the vfsmount of the filesystem where
* the new file is to be created. The parent directory and the
* negative dentry must reside on the same filesystem instance.
*
* On success, returns a "struct file *". Otherwise a ERR_PTR
* is returned.
*/
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
const struct cred *cred)
{
struct file *f;
int error;
f = alloc_empty_file(flags, cred);
if (IS_ERR(f))
return f;
error = vfs_create(mnt_idmap(path->mnt),
d_inode(path->dentry->d_parent),
path->dentry, mode, true);
if (!error)
error = vfs_open(path, f);
if (unlikely(error)) {
fput(f);
return ERR_PTR(error);
}
return f;
}
EXPORT_SYMBOL(dentry_create);
/**
* kernel_file_open - open a file for kernel internal use
* @path: path of the file to open
* @flags: open flags
* @cred: credentials for open
*
* Open a file for use by in-kernel consumers. The file is not accounted
* against nr_files and must not be installed into the file descriptor
* table.
*
* Return: Opened file on success, an error pointer on failure.
*/
struct file *kernel_file_open(const struct path *path, int flags,
const struct cred *cred)
{
struct file *f;
int error;
f = alloc_empty_file_noaccount(flags, cred);
if (IS_ERR(f))
return f;
f->f_path = *path;
error = do_dentry_open(f, NULL);
if (error) {
fput(f);
return ERR_PTR(error);
}
fsnotify_open(f);
return f;
}
EXPORT_SYMBOL_GPL(kernel_file_open);
#define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE))
#define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
inline struct open_how build_open_how(int flags, umode_t mode)
{
struct open_how how = {
.flags = flags & VALID_OPEN_FLAGS,
.mode = mode & S_IALLUGO,
};
/* O_PATH beats everything else. */
if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS;
/* Modes should only be set for create-like flags. */
if (!WILL_CREATE(how.flags)) how.mode = 0;
return how;
}
inline int build_open_flags(const struct open_how *how, struct open_flags *op)
{
u64 flags = how->flags;
u64 strip = O_CLOEXEC;
int lookup_flags = 0;
int acc_mode = ACC_MODE(flags);
BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS),
"struct open_flags doesn't yet handle flags > 32 bits");
/*
* Strip flags that aren't relevant in determining struct open_flags.
*/
flags &= ~strip;
/*
* Older syscalls implicitly clear all of the invalid flags or argument
* values before calling build_open_flags(), but openat2(2) checks all
* of its arguments.
*/
if (flags & ~VALID_OPEN_FLAGS)
return -EINVAL;
if (how->resolve & ~VALID_RESOLVE_FLAGS)
return -EINVAL;
/* Scoping flags are mutually exclusive. */
if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT))
return -EINVAL;
/* Deal with the mode. */
if (WILL_CREATE(flags)) {
if (how->mode & ~S_IALLUGO)
return -EINVAL;
op->mode = how->mode | S_IFREG;
} else {
if (how->mode != 0)
return -EINVAL;
op->mode = 0;
}
/*
* Block bugs where O_DIRECTORY | O_CREAT created regular files.
* Note, that blocking O_DIRECTORY | O_CREAT here also protects
* O_TMPFILE below which requires O_DIRECTORY being raised.
*/
if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT))
return -EINVAL;
/* Now handle the creative implementation of O_TMPFILE. */
if (flags & __O_TMPFILE) {
/*
* In order to ensure programs get explicit errors when trying
* to use O_TMPFILE on old kernels we enforce that O_DIRECTORY
* is raised alongside __O_TMPFILE.
*/
if (!(flags & O_DIRECTORY))
return -EINVAL;
if (!(acc_mode & MAY_WRITE))
return -EINVAL;
}
if (flags & O_PATH) {
/* O_PATH only permits certain other flags to be set. */
if (flags & ~O_PATH_FLAGS)
return -EINVAL;
acc_mode = 0;
}
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
* always set instead of having to deal with possibly weird behaviour
* for malicious applications setting only __O_SYNC.
*/
if (flags & __O_SYNC)
flags |= O_DSYNC;
op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
if (flags & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if (flags & O_APPEND)
acc_mode |= MAY_APPEND;
op->acc_mode = acc_mode;
op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
if (flags & O_CREAT) {
op->intent |= LOOKUP_CREATE;
if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL;
flags |= O_NOFOLLOW;
}
}
if (flags & O_DIRECTORY)
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
if (how->resolve & RESOLVE_NO_XDEV)
lookup_flags |= LOOKUP_NO_XDEV;
if (how->resolve & RESOLVE_NO_MAGICLINKS)
lookup_flags |= LOOKUP_NO_MAGICLINKS;
if (how->resolve & RESOLVE_NO_SYMLINKS)
lookup_flags |= LOOKUP_NO_SYMLINKS;
if (how->resolve & RESOLVE_BENEATH)
lookup_flags |= LOOKUP_BENEATH;
if (how->resolve & RESOLVE_IN_ROOT)
lookup_flags |= LOOKUP_IN_ROOT;
if (how->resolve & RESOLVE_CACHED) {
/* Don't bother even trying for create/truncate/tmpfile open */
if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE))
return -EAGAIN;
lookup_flags |= LOOKUP_CACHED;
}
op->lookup_flags = lookup_flags;
return 0;
}
/**
* file_open_name - open file and return file pointer
*
* @name: struct filename containing path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *file_open_name(struct filename *name, int flags, umode_t mode)
{
struct open_flags op;
struct open_how how = build_open_how(flags, mode);
int err = build_open_flags(&how, &op);
if (err)
return ERR_PTR(err);
return do_filp_open(AT_FDCWD, name, &op);
}
/**
* filp_open - open file and return file pointer
*
* @filename: path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *filp_open(const char *filename, int flags, umode_t mode)
{
struct filename *name = getname_kernel(filename);
struct file *file = ERR_CAST(name);
if (!IS_ERR(name)) {
file = file_open_name(name, flags, mode);
putname(name);
}
return file;
}
EXPORT_SYMBOL(filp_open);
struct file *file_open_root(const struct path *root,
const char *filename, int flags, umode_t mode)
{
struct open_flags op;
struct open_how how = build_open_how(flags, mode);
int err = build_open_flags(&how, &op);
if (err)
return ERR_PTR(err);
return do_file_open_root(root, filename, &op);
}
EXPORT_SYMBOL(file_open_root);
static int do_sys_openat2(int dfd, const char __user *filename,
struct open_how *how)
{
struct open_flags op;
struct filename *tmp;
int err, fd;
err = build_open_flags(how, &op);
if (unlikely(err))
return err;
tmp = getname(filename);
if (IS_ERR(tmp))
return PTR_ERR(tmp);
fd = get_unused_fd_flags(how->flags);
if (likely(fd >= 0)) {
struct file *f = do_filp_open(dfd, tmp, &op);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
fd_install(fd, f);
}
}
putname(tmp);
return fd;
}
int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
struct open_how how = build_open_how(flags, mode);
return do_sys_openat2(dfd, filename, &how);
}
SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(dfd, filename, flags, mode);
}
SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename,
struct open_how __user *, how, size_t, usize)
{
int err;
struct open_how tmp;
BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0);
BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST);
if (unlikely(usize < OPEN_HOW_SIZE_VER0))
return -EINVAL;
if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize);
if (err)
return err;
audit_openat2_how(&tmp);
/* O_LARGEFILE is only allowed for non-O_PATH. */
if (!(tmp.flags & O_PATH) && force_o_largefile())
tmp.flags |= O_LARGEFILE;
return do_sys_openat2(dfd, filename, &tmp);
}
#ifdef CONFIG_COMPAT
/*
* Exactly like sys_open(), except that it doesn't set the
* O_LARGEFILE flag.
*/
COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
/*
* Exactly like sys_openat(), except that it doesn't set the
* O_LARGEFILE flag.
*/
COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(dfd, filename, flags, mode);
}
#endif
#ifndef __alpha__
/*
* For backward compatibility? Maybe this should be moved
* into arch/i386 instead?
*/
SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
{
int flags = O_CREAT | O_WRONLY | O_TRUNC;
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(AT_FDCWD, pathname, flags, mode);
}
#endif
/*
* "id" is the POSIX thread ID. We use the
* files pointer for this..
*/
static int filp_flush(struct file *filp, fl_owner_t id)
{
int retval = 0;
if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp,
"VFS: Close: file count is 0 (f_op=%ps)",
filp->f_op)) {
return 0;
}
if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id);
locks_remove_posix(filp, id);
}
return retval;
}
int filp_close(struct file *filp, fl_owner_t id)
{
int retval;
retval = filp_flush(filp, id);
fput_close(filp);
return retval;
}
EXPORT_SYMBOL(filp_close);
/*
* Careful here! We test whether the file pointer is NULL before
* releasing the fd. This ensures that one clone task can't release
* an fd while another clone is opening it.
*/
SYSCALL_DEFINE1(close, unsigned int, fd)
{
int retval;
struct file *file;
file = file_close_fd(fd);
if (!file)
return -EBADF;
retval = filp_flush(file, current->files);
/*
* We're returning to user space. Don't bother
* with any delayed fput() cases.
*/
fput_close_sync(file);
if (likely(retval == 0))
return 0;
/* can't restart close syscall because file table entry was cleared */
if (retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK)
retval = -EINTR;
return retval;
}
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
*/
SYSCALL_DEFINE0(vhangup)
{
if (capable(CAP_SYS_TTY_CONFIG)) {
tty_vhangup_self();
return 0;
}
return -EPERM;
}
/*
* Called when an inode is about to be open.
* We use this to disallow opening large files on 32bit systems if
* the caller didn't specify O_LARGEFILE. On 64bit systems we force
* on this flag in sys_open.
*/
int generic_file_open(struct inode * inode, struct file * filp)
{ if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
return 0;
}
EXPORT_SYMBOL(generic_file_open);
/*
* This is used by subsystems that don't want seekable
* file descriptors. The function is not supposed to ever fail, the only
* reason it returns an 'int' and not 'void' is so that it can be plugged
* directly into file_operations structure.
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
EXPORT_SYMBOL(nonseekable_open);
/*
* stream_open is used by subsystems that want stream-like file descriptors.
* Such file descriptors are not seekable and don't have notion of position
* (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL).
* Contrary to file descriptors of other regular files, .read() and .write()
* can run simultaneously.
*
* stream_open never fails and is marked to return int so that it could be
* directly used as file_operations.open .
*/
int stream_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
filp->f_mode |= FMODE_STREAM;
return 0;
}
EXPORT_SYMBOL(stream_open);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/kernel/signal.c
*
* Copyright (C) 1995-2009 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/cache.h>
#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/freezer.h>
#include <linux/stddef.h>
#include <linux/uaccess.h>
#include <linux/sizes.h>
#include <linux/string.h>
#include <linux/ratelimit.h>
#include <linux/rseq.h>
#include <linux/syscalls.h>
#include <linux/pkeys.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
#include <asm/exception.h>
#include <asm/cacheflush.h>
#include <asm/gcs.h>
#include <asm/ucontext.h>
#include <asm/unistd.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
#include <asm/syscall.h>
#include <asm/signal32.h>
#include <asm/traps.h>
#include <asm/vdso.h>
#define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK)
/*
* Do a signal return; undo the signal stack. These are aligned to 128-bit.
*/
struct rt_sigframe {
struct siginfo info;
struct ucontext uc;
};
struct rt_sigframe_user_layout {
struct rt_sigframe __user *sigframe;
struct frame_record __user *next_frame;
unsigned long size; /* size of allocated sigframe data */
unsigned long limit; /* largest allowed size */
unsigned long fpsimd_offset;
unsigned long esr_offset;
unsigned long gcs_offset;
unsigned long sve_offset;
unsigned long tpidr2_offset;
unsigned long za_offset;
unsigned long zt_offset;
unsigned long fpmr_offset;
unsigned long poe_offset;
unsigned long extra_offset;
unsigned long end_offset;
};
/*
* Holds any EL0-controlled state that influences unprivileged memory accesses.
* This includes both accesses done in userspace and uaccess done in the kernel.
*
* This state needs to be carefully managed to ensure that it doesn't cause
* uaccess to fail when setting up the signal frame, and the signal handler
* itself also expects a well-defined state when entered.
*/
struct user_access_state {
u64 por_el0;
};
#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
/*
* Save the user access state into ua_state and reset it to disable any
* restrictions.
*/
static void save_reset_user_access_state(struct user_access_state *ua_state)
{
if (system_supports_poe()) {
u64 por_enable_all = 0;
for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX);
ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
write_sysreg_s(por_enable_all, SYS_POR_EL0);
/* Ensure that any subsequent uaccess observes the updated value */
isb();
}
}
/*
* Set the user access state for invoking the signal handler.
*
* No uaccess should be done after that function is called.
*/
static void set_handler_user_access_state(void)
{
if (system_supports_poe()) write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
}
/*
* Restore the user access state to the values saved in ua_state.
*
* No uaccess should be done after that function is called.
*/
static void restore_user_access_state(const struct user_access_state *ua_state)
{
if (system_supports_poe()) write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
}
static void init_user_layout(struct rt_sigframe_user_layout *user)
{
const size_t reserved_size =
sizeof(user->sigframe->uc.uc_mcontext.__reserved);
memset(user, 0, sizeof(*user));
user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved);
user->limit = user->size + reserved_size;
user->limit -= TERMINATOR_SIZE;
user->limit -= EXTRA_CONTEXT_SIZE;
/* Reserve space for extension and terminator ^ */
}
static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
{
return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
}
/*
* Sanity limit on the approximate maximum size of signal frame we'll
* try to generate. Stack alignment padding and the frame record are
* not taken into account. This limit is not a guarantee and is
* NOT ABI.
*/
#define SIGFRAME_MAXSZ SZ_256K
static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
unsigned long *offset, size_t size, bool extend)
{
size_t padded_size = round_up(size, 16);
if (padded_size > user->limit - user->size && !user->extra_offset &&
extend) {
int ret;
user->limit += EXTRA_CONTEXT_SIZE;
ret = __sigframe_alloc(user, &user->extra_offset,
sizeof(struct extra_context), false);
if (ret) {
user->limit -= EXTRA_CONTEXT_SIZE;
return ret;
}
/* Reserve space for the __reserved[] terminator */
user->size += TERMINATOR_SIZE;
/*
* Allow expansion up to SIGFRAME_MAXSZ, ensuring space for
* the terminator:
*/
user->limit = SIGFRAME_MAXSZ - TERMINATOR_SIZE;
}
/* Still not enough space? Bad luck! */
if (padded_size > user->limit - user->size)
return -ENOMEM;
*offset = user->size;
user->size += padded_size;
return 0;
}
/*
* Allocate space for an optional record of <size> bytes in the user
* signal frame. The offset from the signal frame base address to the
* allocated block is assigned to *offset.
*/
static int sigframe_alloc(struct rt_sigframe_user_layout *user,
unsigned long *offset, size_t size)
{
return __sigframe_alloc(user, offset, size, true);
}
/* Allocate the null terminator record and prevent further allocations */
static int sigframe_alloc_end(struct rt_sigframe_user_layout *user)
{
int ret;
/* Un-reserve the space reserved for the terminator: */
user->limit += TERMINATOR_SIZE;
ret = sigframe_alloc(user, &user->end_offset,
sizeof(struct _aarch64_ctx));
if (ret)
return ret;
/* Prevent further allocation: */
user->limit = user->size;
return 0;
}
static void __user *apply_user_offset(
struct rt_sigframe_user_layout const *user, unsigned long offset)
{
char __user *base = (char __user *)user->sigframe;
return base + offset;
}
struct user_ctxs {
struct fpsimd_context __user *fpsimd;
u32 fpsimd_size;
struct sve_context __user *sve;
u32 sve_size;
struct tpidr2_context __user *tpidr2;
u32 tpidr2_size;
struct za_context __user *za;
u32 za_size;
struct zt_context __user *zt;
u32 zt_size;
struct fpmr_context __user *fpmr;
u32 fpmr_size;
struct poe_context __user *poe;
u32 poe_size;
struct gcs_context __user *gcs;
u32 gcs_size;
};
static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
{
struct user_fpsimd_state const *fpsimd =
¤t->thread.uw.fpsimd_state;
int err;
/* copy the FP and status/control registers */
err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); __put_user_error(fpsimd->fpsr, &ctx->fpsr, err); __put_user_error(fpsimd->fpcr, &ctx->fpcr, err);
/* copy the magic/size information */
__put_user_error(FPSIMD_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(struct fpsimd_context), &ctx->head.size, err);
return err ? -EFAULT : 0;
}
static int restore_fpsimd_context(struct user_ctxs *user)
{
struct user_fpsimd_state fpsimd;
int err = 0;
/* check the size information */
if (user->fpsimd_size != sizeof(struct fpsimd_context))
return -EINVAL;
/* copy the FP and status/control registers */
err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs),
sizeof(fpsimd.vregs));
__get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err);
__get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err);
clear_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_FPSIMD;
/* load the hardware registers from the fpsimd_state structure */
if (!err)
fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
static int preserve_fpmr_context(struct fpmr_context __user *ctx)
{
int err = 0;
current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR);
__put_user_error(FPMR_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err);
return err;
}
static int restore_fpmr_context(struct user_ctxs *user)
{
u64 fpmr;
int err = 0;
if (user->fpmr_size != sizeof(*user->fpmr))
return -EINVAL;
__get_user_error(fpmr, &user->fpmr->fpmr, err);
if (!err)
write_sysreg_s(fpmr, SYS_FPMR);
return err;
}
static int preserve_poe_context(struct poe_context __user *ctx,
const struct user_access_state *ua_state)
{
int err = 0;
__put_user_error(POE_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(ua_state->por_el0, &ctx->por_el0, err);
return err;
}
static int restore_poe_context(struct user_ctxs *user,
struct user_access_state *ua_state)
{
u64 por_el0;
int err = 0;
if (user->poe_size != sizeof(*user->poe))
return -EINVAL;
__get_user_error(por_el0, &(user->poe->por_el0), err);
if (!err)
ua_state->por_el0 = por_el0;
return err;
}
#ifdef CONFIG_ARM64_SVE
static int preserve_sve_context(struct sve_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
u16 flags = 0;
unsigned int vl = task_get_sve_vl(current);
unsigned int vq = 0;
if (thread_sm_enabled(¤t->thread)) {
vl = task_get_sme_vl(current);
vq = sve_vq_from_vl(vl);
flags |= SVE_SIG_FLAG_SM;
} else if (current->thread.fp_type == FP_STATE_SVE) {
vq = sve_vq_from_vl(vl);
}
memset(reserved, 0, sizeof(reserved));
__put_user_error(SVE_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
&ctx->head.size, err);
__put_user_error(vl, &ctx->vl, err); __put_user_error(flags, &ctx->flags, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) {
/*
* This assumes that the SVE state has already been saved to
* the task struct by calling the function
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
current->thread.sve_state,
SVE_SIG_REGS_SIZE(vq));
}
return err ? -EFAULT : 0;
}
static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
int err = 0;
unsigned int vl, vq;
struct user_fpsimd_state fpsimd;
u16 user_vl, flags;
if (user->sve_size < sizeof(*user->sve))
return -EINVAL;
__get_user_error(user_vl, &(user->sve->vl), err);
__get_user_error(flags, &(user->sve->flags), err);
if (err)
return err;
if (flags & SVE_SIG_FLAG_SM) {
if (!system_supports_sme())
return -EINVAL;
vl = task_get_sme_vl(current);
} else {
/*
* A SME only system use SVE for streaming mode so can
* have a SVE formatted context with a zero VL and no
* payload data.
*/
if (!system_supports_sve() && !system_supports_sme())
return -EINVAL;
vl = task_get_sve_vl(current);
}
if (user_vl != vl)
return -EINVAL;
if (user->sve_size == sizeof(*user->sve)) {
clear_thread_flag(TIF_SVE);
current->thread.svcr &= ~SVCR_SM_MASK;
current->thread.fp_type = FP_STATE_FPSIMD;
goto fpsimd_only;
}
vq = sve_vq_from_vl(vl);
if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.sve_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
fpsimd_flush_task_state(current);
/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
sve_alloc(current, true);
if (!current->thread.sve_state) {
clear_thread_flag(TIF_SVE);
return -ENOMEM;
}
err = __copy_from_user(current->thread.sve_state,
(char __user const *)user->sve +
SVE_SIG_REGS_OFFSET,
SVE_SIG_REGS_SIZE(vq));
if (err)
return -EFAULT;
if (flags & SVE_SIG_FLAG_SM)
current->thread.svcr |= SVCR_SM_MASK;
else
set_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_SVE;
fpsimd_only:
/* copy the FP and status/control registers */
/* restore_sigframe() already checked that user->fpsimd != NULL. */
err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
sizeof(fpsimd.vregs));
__get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
__get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
/* load the hardware registers from the fpsimd_state structure */
if (!err)
fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
#else /* ! CONFIG_ARM64_SVE */
static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
WARN_ON_ONCE(1);
return -EINVAL;
}
/* Turn any non-optimised out attempts to use this into a link error: */
extern int preserve_sve_context(void __user *ctx);
#endif /* ! CONFIG_ARM64_SVE */
#ifdef CONFIG_ARM64_SME
static int preserve_tpidr2_context(struct tpidr2_context __user *ctx)
{
int err = 0;
current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
__put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
__put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err);
return err;
}
static int restore_tpidr2_context(struct user_ctxs *user)
{
u64 tpidr2_el0;
int err = 0;
if (user->tpidr2_size != sizeof(*user->tpidr2))
return -EINVAL;
__get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err);
if (!err)
write_sysreg_s(tpidr2_el0, SYS_TPIDR2_EL0);
return err;
}
static int preserve_za_context(struct za_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
unsigned int vl = task_get_sme_vl(current);
unsigned int vq;
if (thread_za_enabled(¤t->thread))
vq = sve_vq_from_vl(vl);
else
vq = 0;
memset(reserved, 0, sizeof(reserved));
__put_user_error(ZA_MAGIC, &ctx->head.magic, err);
__put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16),
&ctx->head.size, err);
__put_user_error(vl, &ctx->vl, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
if (vq) {
/*
* This assumes that the ZA state has already been saved to
* the task struct by calling the function
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
current->thread.sme_state,
ZA_SIG_REGS_SIZE(vq));
}
return err ? -EFAULT : 0;
}
static int restore_za_context(struct user_ctxs *user)
{
int err = 0;
unsigned int vq;
u16 user_vl;
if (user->za_size < sizeof(*user->za))
return -EINVAL;
__get_user_error(user_vl, &(user->za->vl), err);
if (err)
return err;
if (user_vl != task_get_sme_vl(current))
return -EINVAL;
if (user->za_size == sizeof(*user->za)) {
current->thread.svcr &= ~SVCR_ZA_MASK;
return 0;
}
vq = sve_vq_from_vl(user_vl);
if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.sme_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
fpsimd_flush_task_state(current);
/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
sme_alloc(current, true);
if (!current->thread.sme_state) {
current->thread.svcr &= ~SVCR_ZA_MASK;
clear_thread_flag(TIF_SME);
return -ENOMEM;
}
err = __copy_from_user(current->thread.sme_state,
(char __user const *)user->za +
ZA_SIG_REGS_OFFSET,
ZA_SIG_REGS_SIZE(vq));
if (err)
return -EFAULT;
set_thread_flag(TIF_SME);
current->thread.svcr |= SVCR_ZA_MASK;
return 0;
}
static int preserve_zt_context(struct zt_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
if (WARN_ON(!thread_za_enabled(¤t->thread)))
return -EINVAL;
memset(reserved, 0, sizeof(reserved));
__put_user_error(ZT_MAGIC, &ctx->head.magic, err);
__put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
&ctx->head.size, err);
__put_user_error(1, &ctx->nregs, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
/*
* This assumes that the ZT state has already been saved to
* the task struct by calling the function
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
thread_zt_state(¤t->thread),
ZT_SIG_REGS_SIZE(1));
return err ? -EFAULT : 0;
}
static int restore_zt_context(struct user_ctxs *user)
{
int err;
u16 nregs;
/* ZA must be restored first for this check to be valid */
if (!thread_za_enabled(¤t->thread))
return -EINVAL;
if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1))
return -EINVAL;
if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs)))
return -EFAULT;
if (nregs != 1)
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.zt_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
fpsimd_flush_task_state(current);
/* From now, fpsimd_thread_switch() won't touch ZT in thread state */
err = __copy_from_user(thread_zt_state(¤t->thread),
(char __user const *)user->zt +
ZT_SIG_REGS_OFFSET,
ZT_SIG_REGS_SIZE(1));
if (err)
return -EFAULT;
return 0;
}
#else /* ! CONFIG_ARM64_SME */
/* Turn any non-optimised out attempts to use these into a link error: */
extern int preserve_tpidr2_context(void __user *ctx);
extern int restore_tpidr2_context(struct user_ctxs *user);
extern int preserve_za_context(void __user *ctx);
extern int restore_za_context(struct user_ctxs *user);
extern int preserve_zt_context(void __user *ctx);
extern int restore_zt_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SME */
#ifdef CONFIG_ARM64_GCS
static int preserve_gcs_context(struct gcs_context __user *ctx)
{
int err = 0;
u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0);
/*
* If GCS is enabled we will add a cap token to the frame,
* include it in the GCSPR_EL0 we report to support stack
* switching via sigreturn if GCS is enabled. We do not allow
* enabling via sigreturn so the token is only relevant for
* threads with GCS enabled.
*/
if (task_gcs_el0_enabled(current))
gcspr -= 8;
__put_user_error(GCS_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(gcspr, &ctx->gcspr, err); __put_user_error(0, &ctx->reserved, err); __put_user_error(current->thread.gcs_el0_mode,
&ctx->features_enabled, err);
return err;
}
static int restore_gcs_context(struct user_ctxs *user)
{
u64 gcspr, enabled;
int err = 0;
if (user->gcs_size != sizeof(*user->gcs))
return -EINVAL;
__get_user_error(gcspr, &user->gcs->gcspr, err);
__get_user_error(enabled, &user->gcs->features_enabled, err);
if (err)
return err;
/* Don't allow unknown modes */
if (enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
return -EINVAL;
err = gcs_check_locked(current, enabled);
if (err != 0)
return err;
/* Don't allow enabling */
if (!task_gcs_el0_enabled(current) &&
(enabled & PR_SHADOW_STACK_ENABLE))
return -EINVAL;
/* If we are disabling disable everything */
if (!(enabled & PR_SHADOW_STACK_ENABLE))
enabled = 0;
current->thread.gcs_el0_mode = enabled;
/*
* We let userspace set GCSPR_EL0 to anything here, we will
* validate later in gcs_restore_signal().
*/
write_sysreg_s(gcspr, SYS_GCSPR_EL0);
return 0;
}
#else /* ! CONFIG_ARM64_GCS */
/* Turn any non-optimised out attempts to use these into a link error: */
extern int preserve_gcs_context(void __user *ctx);
extern int restore_gcs_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_GCS */
static int parse_user_sigframe(struct user_ctxs *user,
struct rt_sigframe __user *sf)
{
struct sigcontext __user *const sc = &sf->uc.uc_mcontext;
struct _aarch64_ctx __user *head;
char __user *base = (char __user *)&sc->__reserved;
size_t offset = 0;
size_t limit = sizeof(sc->__reserved);
bool have_extra_context = false;
char const __user *const sfp = (char const __user *)sf;
user->fpsimd = NULL;
user->sve = NULL;
user->tpidr2 = NULL;
user->za = NULL;
user->zt = NULL;
user->fpmr = NULL;
user->poe = NULL;
user->gcs = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
while (1) {
int err = 0;
u32 magic, size;
char const __user *userp;
struct extra_context const __user *extra;
u64 extra_datap;
u32 extra_size;
struct _aarch64_ctx const __user *end;
u32 end_magic, end_size;
if (limit - offset < sizeof(*head))
goto invalid;
if (!IS_ALIGNED(offset, 16))
goto invalid;
head = (struct _aarch64_ctx __user *)(base + offset);
__get_user_error(magic, &head->magic, err);
__get_user_error(size, &head->size, err);
if (err)
return err;
if (limit - offset < size)
goto invalid;
switch (magic) {
case 0:
if (size)
goto invalid;
goto done;
case FPSIMD_MAGIC:
if (!system_supports_fpsimd())
goto invalid;
if (user->fpsimd)
goto invalid;
user->fpsimd = (struct fpsimd_context __user *)head;
user->fpsimd_size = size;
break;
case ESR_MAGIC:
/* ignore */
break;
case POE_MAGIC:
if (!system_supports_poe())
goto invalid;
if (user->poe)
goto invalid;
user->poe = (struct poe_context __user *)head;
user->poe_size = size;
break;
case SVE_MAGIC:
if (!system_supports_sve() && !system_supports_sme())
goto invalid;
if (user->sve)
goto invalid;
user->sve = (struct sve_context __user *)head;
user->sve_size = size;
break;
case TPIDR2_MAGIC:
if (!system_supports_tpidr2())
goto invalid;
if (user->tpidr2)
goto invalid;
user->tpidr2 = (struct tpidr2_context __user *)head;
user->tpidr2_size = size;
break;
case ZA_MAGIC:
if (!system_supports_sme())
goto invalid;
if (user->za)
goto invalid;
user->za = (struct za_context __user *)head;
user->za_size = size;
break;
case ZT_MAGIC:
if (!system_supports_sme2())
goto invalid;
if (user->zt)
goto invalid;
user->zt = (struct zt_context __user *)head;
user->zt_size = size;
break;
case FPMR_MAGIC:
if (!system_supports_fpmr())
goto invalid;
if (user->fpmr)
goto invalid;
user->fpmr = (struct fpmr_context __user *)head;
user->fpmr_size = size;
break;
case GCS_MAGIC:
if (!system_supports_gcs())
goto invalid;
if (user->gcs)
goto invalid;
user->gcs = (struct gcs_context __user *)head;
user->gcs_size = size;
break;
case EXTRA_MAGIC:
if (have_extra_context)
goto invalid;
if (size < sizeof(*extra))
goto invalid;
userp = (char const __user *)head;
extra = (struct extra_context const __user *)userp;
userp += size;
__get_user_error(extra_datap, &extra->datap, err);
__get_user_error(extra_size, &extra->size, err);
if (err)
return err;
/* Check for the dummy terminator in __reserved[]: */
if (limit - offset - size < TERMINATOR_SIZE)
goto invalid;
end = (struct _aarch64_ctx const __user *)userp;
userp += TERMINATOR_SIZE;
__get_user_error(end_magic, &end->magic, err);
__get_user_error(end_size, &end->size, err);
if (err)
return err;
if (end_magic || end_size)
goto invalid;
/* Prevent looping/repeated parsing of extra_context */
have_extra_context = true;
base = (__force void __user *)extra_datap;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
if (!IS_ALIGNED(extra_size, 16))
goto invalid;
if (base != userp)
goto invalid;
/* Reject "unreasonably large" frames: */
if (extra_size > sfp + SIGFRAME_MAXSZ - userp)
goto invalid;
/*
* Ignore trailing terminator in __reserved[]
* and start parsing extra data:
*/
offset = 0;
limit = extra_size;
if (!access_ok(base, limit))
goto invalid;
continue;
default:
goto invalid;
}
if (size < sizeof(*head))
goto invalid;
if (limit - offset < size)
goto invalid;
offset += size;
}
done:
return 0;
invalid:
return -EINVAL;
}
static int restore_sigframe(struct pt_regs *regs,
struct rt_sigframe __user *sf,
struct user_access_state *ua_state)
{
sigset_t set;
int i, err;
struct user_ctxs user;
err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
if (err == 0)
set_current_blocked(&set);
for (i = 0; i < 31; i++)
__get_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i],
err);
__get_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err);
__get_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err);
__get_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err);
/*
* Avoid sys_rt_sigreturn() restarting.
*/
forget_syscall(regs);
err |= !valid_user_regs(®s->user_regs, current);
if (err == 0)
err = parse_user_sigframe(&user, sf);
if (err == 0 && system_supports_fpsimd()) {
if (!user.fpsimd)
return -EINVAL;
if (user.sve)
err = restore_sve_fpsimd_context(&user);
else
err = restore_fpsimd_context(&user);
}
if (err == 0 && system_supports_gcs() && user.gcs)
err = restore_gcs_context(&user);
if (err == 0 && system_supports_tpidr2() && user.tpidr2)
err = restore_tpidr2_context(&user);
if (err == 0 && system_supports_fpmr() && user.fpmr)
err = restore_fpmr_context(&user);
if (err == 0 && system_supports_sme() && user.za)
err = restore_za_context(&user);
if (err == 0 && system_supports_sme2() && user.zt)
err = restore_zt_context(&user);
if (err == 0 && system_supports_poe() && user.poe)
err = restore_poe_context(&user, ua_state);
return err;
}
#ifdef CONFIG_ARM64_GCS
static int gcs_restore_signal(void)
{
u64 gcspr_el0, cap;
int ret;
if (!system_supports_gcs())
return 0;
if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE))
return 0;
gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
/*
* Ensure that any changes to the GCS done via GCS operations
* are visible to the normal reads we do to validate the
* token.
*/
gcsb_dsync();
/*
* GCSPR_EL0 should be pointing at a capped GCS, read the cap.
* We don't enforce that this is in a GCS page, if it is not
* then faults will be generated on GCS operations - the main
* concern is to protect GCS pages.
*/
ret = copy_from_user(&cap, (unsigned long __user *)gcspr_el0,
sizeof(cap));
if (ret)
return -EFAULT;
/*
* Check that the cap is the actual GCS before replacing it.
*/
if (cap != GCS_SIGNAL_CAP(gcspr_el0))
return -EINVAL;
/* Invalidate the token to prevent reuse */
put_user_gcs(0, (unsigned long __user *)gcspr_el0, &ret);
if (ret != 0)
return -EFAULT;
write_sysreg_s(gcspr_el0 + 8, SYS_GCSPR_EL0);
return 0;
}
#else
static int gcs_restore_signal(void) { return 0; }
#endif
SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
struct user_access_state ua_state;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
/*
* Since we stacked the signal on a 128-bit boundary, then 'sp' should
* be word aligned here.
*/
if (regs->sp & 15)
goto badframe;
frame = (struct rt_sigframe __user *)regs->sp;
if (!access_ok(frame, sizeof (*frame)))
goto badframe;
if (restore_sigframe(regs, frame, &ua_state))
goto badframe;
if (gcs_restore_signal())
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
restore_user_access_state(&ua_state);
return regs->regs[0];
badframe:
arm64_notify_segfault(regs->sp);
return 0;
}
/*
* Determine the layout of optional records in the signal frame
*
* add_all: if true, lays out the biggest possible signal frame for
* this task; otherwise, generates a layout for the current state
* of the task.
*/
static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
bool add_all)
{
int err;
if (system_supports_fpsimd()) { err = sigframe_alloc(user, &user->fpsimd_offset,
sizeof(struct fpsimd_context));
if (err)
return err;
}
/* fault information, if valid */
if (add_all || current->thread.fault_code) { err = sigframe_alloc(user, &user->esr_offset,
sizeof(struct esr_context));
if (err)
return err;
}
#ifdef CONFIG_ARM64_GCS
if (system_supports_gcs() && (add_all || current->thread.gcspr_el0)) { err = sigframe_alloc(user, &user->gcs_offset,
sizeof(struct gcs_context));
if (err)
return err;
}
#endif
if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
if (add_all || current->thread.fp_type == FP_STATE_SVE ||
thread_sm_enabled(¤t->thread)) {
int vl = max(sve_max_vl(), sme_max_vl());
if (!add_all)
vl = thread_get_cur_vl(¤t->thread);
vq = sve_vq_from_vl(vl);
}
err = sigframe_alloc(user, &user->sve_offset,
SVE_SIG_CONTEXT_SIZE(vq));
if (err)
return err;
}
if (system_supports_tpidr2()) {
err = sigframe_alloc(user, &user->tpidr2_offset,
sizeof(struct tpidr2_context));
if (err)
return err;
}
if (system_supports_sme()) {
unsigned int vl;
unsigned int vq = 0;
if (add_all)
vl = sme_max_vl();
else
vl = task_get_sme_vl(current);
if (thread_za_enabled(¤t->thread))
vq = sve_vq_from_vl(vl);
err = sigframe_alloc(user, &user->za_offset,
ZA_SIG_CONTEXT_SIZE(vq));
if (err)
return err;
}
if (system_supports_sme2()) {
if (add_all || thread_za_enabled(¤t->thread)) {
err = sigframe_alloc(user, &user->zt_offset,
ZT_SIG_CONTEXT_SIZE(1));
if (err)
return err;
}
}
if (system_supports_fpmr()) { err = sigframe_alloc(user, &user->fpmr_offset,
sizeof(struct fpmr_context));
if (err)
return err;
}
if (system_supports_poe()) {
err = sigframe_alloc(user, &user->poe_offset,
sizeof(struct poe_context));
if (err)
return err;
}
return sigframe_alloc_end(user);
}
static int setup_sigframe(struct rt_sigframe_user_layout *user,
struct pt_regs *regs, sigset_t *set,
const struct user_access_state *ua_state)
{
int i, err = 0;
struct rt_sigframe __user *sf = user->sigframe;
/* set up the stack frame for unwinding */
__put_user_error(regs->regs[29], &user->next_frame->fp, err); __put_user_error(regs->regs[30], &user->next_frame->lr, err); for (i = 0; i < 31; i++) __put_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i],
err);
__put_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err); __put_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __put_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); __put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); if (err == 0 && system_supports_fpsimd()) {
struct fpsimd_context __user *fpsimd_ctx =
apply_user_offset(user, user->fpsimd_offset);
err |= preserve_fpsimd_context(fpsimd_ctx);
}
/* fault information, if valid */
if (err == 0 && user->esr_offset) {
struct esr_context __user *esr_ctx =
apply_user_offset(user, user->esr_offset);
__put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err); __put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err); __put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
}
if (system_supports_gcs() && err == 0 && user->gcs_offset) {
struct gcs_context __user *gcs_ctx =
apply_user_offset(user, user->gcs_offset);
err |= preserve_gcs_context(gcs_ctx);
}
/* Scalable Vector Extension state (including streaming), if present */
if ((system_supports_sve() || system_supports_sme()) && err == 0 && user->sve_offset) {
struct sve_context __user *sve_ctx =
apply_user_offset(user, user->sve_offset);
err |= preserve_sve_context(sve_ctx);
}
/* TPIDR2 if supported */
if (system_supports_tpidr2() && err == 0) {
struct tpidr2_context __user *tpidr2_ctx =
apply_user_offset(user, user->tpidr2_offset);
err |= preserve_tpidr2_context(tpidr2_ctx);
}
/* FPMR if supported */
if (system_supports_fpmr() && err == 0) {
struct fpmr_context __user *fpmr_ctx =
apply_user_offset(user, user->fpmr_offset);
err |= preserve_fpmr_context(fpmr_ctx);
}
if (system_supports_poe() && err == 0) {
struct poe_context __user *poe_ctx =
apply_user_offset(user, user->poe_offset);
err |= preserve_poe_context(poe_ctx, ua_state);
}
/* ZA state if present */
if (system_supports_sme() && err == 0 && user->za_offset) {
struct za_context __user *za_ctx =
apply_user_offset(user, user->za_offset);
err |= preserve_za_context(za_ctx);
}
/* ZT state if present */
if (system_supports_sme2() && err == 0 && user->zt_offset) {
struct zt_context __user *zt_ctx =
apply_user_offset(user, user->zt_offset);
err |= preserve_zt_context(zt_ctx);
}
if (err == 0 && user->extra_offset) {
char __user *sfp = (char __user *)user->sigframe;
char __user *userp =
apply_user_offset(user, user->extra_offset);
struct extra_context __user *extra;
struct _aarch64_ctx __user *end;
u64 extra_datap;
u32 extra_size;
extra = (struct extra_context __user *)userp;
userp += EXTRA_CONTEXT_SIZE;
end = (struct _aarch64_ctx __user *)userp;
userp += TERMINATOR_SIZE;
/*
* extra_datap is just written to the signal frame.
* The value gets cast back to a void __user *
* during sigreturn.
*/
extra_datap = (__force u64)userp;
extra_size = sfp + round_up(user->size, 16) - userp;
__put_user_error(EXTRA_MAGIC, &extra->head.magic, err); __put_user_error(EXTRA_CONTEXT_SIZE, &extra->head.size, err); __put_user_error(extra_datap, &extra->datap, err); __put_user_error(extra_size, &extra->size, err);
/* Add the terminator */
__put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err);
}
/* set the "end" magic */
if (err == 0) {
struct _aarch64_ctx __user *end =
apply_user_offset(user, user->end_offset);
__put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err);
}
return err;
}
static int get_sigframe(struct rt_sigframe_user_layout *user,
struct ksignal *ksig, struct pt_regs *regs)
{
unsigned long sp, sp_top;
int err;
init_user_layout(user);
err = setup_sigframe_layout(user, false);
if (err)
return err;
sp = sp_top = sigsp(regs->sp, ksig);
sp = round_down(sp - sizeof(struct frame_record), 16);
user->next_frame = (struct frame_record __user *)sp;
sp = round_down(sp, 16) - sigframe_size(user);
user->sigframe = (struct rt_sigframe __user *)sp;
/*
* Check that we can actually write to the signal frame.
*/
if (!access_ok(user->sigframe, sp_top - sp))
return -EFAULT;
return 0;
}
#ifdef CONFIG_ARM64_GCS
static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
{
u64 gcspr_el0;
int ret = 0;
if (!system_supports_gcs())
return 0;
if (!task_gcs_el0_enabled(current))
return 0;
/*
* We are entering a signal handler, current register state is
* active.
*/
gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
/*
* Push a cap and the GCS entry for the trampoline onto the GCS.
*/
put_user_gcs((unsigned long)sigtramp,
(unsigned long __user *)(gcspr_el0 - 16), &ret);
put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 8),
(unsigned long __user *)(gcspr_el0 - 8), &ret);
if (ret != 0)
return ret;
gcspr_el0 -= 16;
write_sysreg_s(gcspr_el0, SYS_GCSPR_EL0);
return 0;
}
#else
static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
{
return 0;
}
#endif
static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
struct rt_sigframe_user_layout *user, int usig)
{
__sigrestore_t sigtramp;
int err;
if (ksig->ka.sa.sa_flags & SA_RESTORER)
sigtramp = ksig->ka.sa.sa_restorer;
else
sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); err = gcs_signal_entry(sigtramp, ksig);
if (err)
return err;
/*
* We must not fail from this point onwards. We are going to update
* registers, including SP, in order to invoke the signal handler. If
* we failed and attempted to deliver a nested SIGSEGV to a handler
* after that point, the subsequent sigreturn would end up restoring
* the (partial) state for the original signal handler.
*/
regs->regs[0] = usig;
if (ksig->ka.sa.sa_flags & SA_SIGINFO) { regs->regs[1] = (unsigned long)&user->sigframe->info;
regs->regs[2] = (unsigned long)&user->sigframe->uc;
}
regs->sp = (unsigned long)user->sigframe;
regs->regs[29] = (unsigned long)&user->next_frame->fp;
regs->regs[30] = (unsigned long)sigtramp;
regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
/*
* Signal delivery is a (wacky) indirect function call in
* userspace, so simulate the same setting of BTYPE as a BLR
* <register containing the signal handler entry point>.
* Signal delivery to a location in a PROT_BTI guarded page
* that is not a function entry point will now trigger a
* SIGILL in userspace.
*
* If the signal handler entry point is not in a PROT_BTI
* guarded page, this is harmless.
*/
if (system_supports_bti()) { regs->pstate &= ~PSR_BTYPE_MASK;
regs->pstate |= PSR_BTYPE_C;
}
/* TCO (Tag Check Override) always cleared for signal handlers */
regs->pstate &= ~PSR_TCO_BIT;
/* Signal handlers are invoked with ZA and streaming mode disabled */
if (system_supports_sme()) {
/*
* If we were in streaming mode the saved register
* state was SVE but we will exit SM and use the
* FPSIMD register state - flush the saved FPSIMD
* register state in case it gets loaded.
*/
if (current->thread.svcr & SVCR_SM_MASK) {
memset(¤t->thread.uw.fpsimd_state, 0,
sizeof(current->thread.uw.fpsimd_state));
current->thread.fp_type = FP_STATE_FPSIMD;
}
current->thread.svcr &= ~(SVCR_ZA_MASK |
SVCR_SM_MASK);
sme_smstop();
}
return 0;
}
static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
struct rt_sigframe_user_layout user;
struct rt_sigframe __user *frame;
struct user_access_state ua_state;
int err = 0;
fpsimd_signal_preserve_current_state();
if (get_sigframe(&user, ksig, regs))
return 1;
save_reset_user_access_state(&ua_state);
frame = user.sigframe;
__put_user_error(0, &frame->uc.uc_flags, err); __put_user_error(NULL, &frame->uc.uc_link, err);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
err |= setup_sigframe(&user, regs, set, &ua_state); if (ksig->ka.sa.sa_flags & SA_SIGINFO) err |= copy_siginfo_to_user(&frame->info, &ksig->info); if (err == 0) err = setup_return(regs, ksig, &user, usig);
/*
* We must not fail if setup_return() succeeded - see comment at the
* beginning of setup_return().
*/
if (err == 0)
set_handler_user_access_state();
else
restore_user_access_state(&ua_state);
return err;
}
static void setup_restart_syscall(struct pt_regs *regs)
{
if (is_compat_task())
compat_setup_restart_syscall(regs);
else
regs->regs[8] = __NR_restart_syscall;
}
/*
* OK, we're invoking a handler
*/
static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
sigset_t *oldset = sigmask_to_save();
int usig = ksig->sig;
int ret;
rseq_signal_deliver(ksig, regs);
/*
* Set up the stack frame
*/
if (is_compat_task()) {
if (ksig->ka.sa.sa_flags & SA_SIGINFO)
ret = compat_setup_rt_frame(usig, ksig, oldset, regs);
else
ret = compat_setup_frame(usig, ksig, oldset, regs);
} else {
ret = setup_rt_frame(usig, ksig, oldset, regs);
}
/*
* Check that the resulting registers are actually sane.
*/
ret |= !valid_user_regs(®s->user_regs, current);
/* Step into the signal handler if we are stepping */
signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
}
/*
* Note that 'init' is a special process: it doesn't get signals it doesn't
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*
* Note that we go through the signals twice: once to check the signals that
* the kernel can handle, and then we build all the user-level signal handling
* stack-frames in one go after that.
*/
void do_signal(struct pt_regs *regs)
{
unsigned long continue_addr = 0, restart_addr = 0;
int retval = 0;
struct ksignal ksig;
bool syscall = in_syscall(regs);
/*
* If we were from a system call, check for system call restarting...
*/
if (syscall) {
continue_addr = regs->pc;
restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4);
retval = regs->regs[0];
/*
* Avoid additional syscall restarting via ret_to_user.
*/
forget_syscall(regs);
/*
* Prepare for system call restart. We do this here so that a
* debugger will see the already changed PC.
*/
switch (retval) {
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
case -ERESTART_RESTARTBLOCK:
regs->regs[0] = regs->orig_x0;
regs->pc = restart_addr;
break;
}
}
/*
* Get the signal to deliver. When running under ptrace, at this point
* the debugger may change all of our registers.
*/
if (get_signal(&ksig)) {
/*
* Depending on the signal settings, we may need to revert the
* decision to restart the system call, but skip this if a
* debugger has chosen to restart at a different PC.
*/
if (regs->pc == restart_addr && (retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK ||
(retval == -ERESTARTSYS &&
!(ksig.ka.sa.sa_flags & SA_RESTART)))) {
syscall_set_return_value(current, regs, -EINTR, 0);
regs->pc = continue_addr;
}
handle_signal(&ksig, regs);
return;
}
/*
* Handle restarting a different system call. As above, if a debugger
* has chosen to restart at a different PC, ignore the restart.
*/
if (syscall && regs->pc == restart_addr) { if (retval == -ERESTART_RESTARTBLOCK) setup_restart_syscall(regs);
user_rewind_single_step(current);
}
restore_saved_sigmask();
}
unsigned long __ro_after_init signal_minsigstksz;
/*
* Determine the stack space required for guaranteed signal devliery.
* This function is used to populate AT_MINSIGSTKSZ at process startup.
* cpufeatures setup is assumed to be complete.
*/
void __init minsigstksz_setup(void)
{
struct rt_sigframe_user_layout user;
init_user_layout(&user);
/*
* If this fails, SIGFRAME_MAXSZ needs to be enlarged. It won't
* be big enough, but it's our best guess:
*/
if (WARN_ON(setup_sigframe_layout(&user, true)))
return;
signal_minsigstksz = sigframe_size(&user) +
round_up(sizeof(struct frame_record), 16) +
16; /* max alignment padding */
}
/*
* Compile-time assertions for siginfo_t offsets. Check NSIG* as well, as
* changes likely come with new fields that should be added below.
*/
static_assert(NSIGILL == 11);
static_assert(NSIGFPE == 15);
static_assert(NSIGSEGV == 10);
static_assert(NSIGBUS == 5);
static_assert(NSIGTRAP == 6);
static_assert(NSIGCHLD == 6);
static_assert(NSIGSYS == 2);
static_assert(sizeof(siginfo_t) == 128);
static_assert(__alignof__(siginfo_t) == 8);
static_assert(offsetof(siginfo_t, si_signo) == 0x00);
static_assert(offsetof(siginfo_t, si_errno) == 0x04);
static_assert(offsetof(siginfo_t, si_code) == 0x08);
static_assert(offsetof(siginfo_t, si_pid) == 0x10);
static_assert(offsetof(siginfo_t, si_uid) == 0x14);
static_assert(offsetof(siginfo_t, si_tid) == 0x10);
static_assert(offsetof(siginfo_t, si_overrun) == 0x14);
static_assert(offsetof(siginfo_t, si_status) == 0x18);
static_assert(offsetof(siginfo_t, si_utime) == 0x20);
static_assert(offsetof(siginfo_t, si_stime) == 0x28);
static_assert(offsetof(siginfo_t, si_value) == 0x18);
static_assert(offsetof(siginfo_t, si_int) == 0x18);
static_assert(offsetof(siginfo_t, si_ptr) == 0x18);
static_assert(offsetof(siginfo_t, si_addr) == 0x10);
static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x18);
static_assert(offsetof(siginfo_t, si_lower) == 0x20);
static_assert(offsetof(siginfo_t, si_upper) == 0x28);
static_assert(offsetof(siginfo_t, si_pkey) == 0x20);
static_assert(offsetof(siginfo_t, si_perf_data) == 0x18);
static_assert(offsetof(siginfo_t, si_perf_type) == 0x20);
static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
static_assert(offsetof(siginfo_t, si_band) == 0x10);
static_assert(offsetof(siginfo_t, si_fd) == 0x18);
static_assert(offsetof(siginfo_t, si_call_addr) == 0x10);
static_assert(offsetof(siginfo_t, si_syscall) == 0x18);
static_assert(offsetof(siginfo_t, si_arch) == 0x1c);
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* fs/eventpoll.c (Efficient event retrieval implementation)
* Copyright (C) 2001,...,2009 Davide Libenzi
*
* Davide Libenzi <davidel@xmailserver.org>
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <linux/device.h>
#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <linux/atomic.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/compat.h>
#include <linux/rculist.h>
#include <linux/capability.h>
#include <net/busy_poll.h>
/*
* LOCKING:
* There are three level of locking required by epoll :
*
* 1) epnested_mutex (mutex)
* 2) ep->mtx (mutex)
* 3) ep->lock (rwlock)
*
* The acquire order is the one listed above, from 1 to 3.
* We need a rwlock (ep->lock) because we manipulate objects
* from inside the poll callback, that might be triggered from
* a wake_up() that in turn might be called from IRQ context.
* So we can't sleep inside the poll callback and hence we need
* a spinlock. During the event transfer loop (from kernel to
* user space) we could end up sleeping due a copy_to_user(), so
* we need a lock that will allow us to sleep. This lock is a
* mutex (ep->mtx). It is acquired during the event transfer loop,
* during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
* The epnested_mutex is acquired when inserting an epoll fd onto another
* epoll fd. We do this so that we walk the epoll tree and ensure that this
* insertion does not create a cycle of epoll file descriptors, which
* could lead to deadlock. We need a global mutex to prevent two
* simultaneous inserts (A into B and B into A) from racing and
* constructing a cycle without either insert observing that it is
* going to.
* It is necessary to acquire multiple "ep->mtx"es at once in the
* case when one epoll fd is added to another. In this case, we
* always acquire the locks in the order of nesting (i.e. after
* epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
* before e2->mtx). Since we disallow cycles of epoll file
* descriptors, this ensures that the mutexes are well-ordered. In
* order to communicate this nesting to lockdep, when walking a tree
* of epoll file descriptors, we use the current recursion depth as
* the lockdep subkey.
* It is possible to drop the "ep->mtx" and to use the global
* mutex "epnested_mutex" (together with "ep->lock") to have it working,
* but having "ep->mtx" will make the interface more scalable.
* Events that require holding "epnested_mutex" are very rare, while for
* normal operations the epoll private "ep->mtx" will guarantee
* a better scalability.
*/
/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
#define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT)
#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \
EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
#define EP_UNACTIVE_PTR ((void *) -1L)
#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
struct epoll_filefd {
struct file *file;
int fd;
} __packed;
/* Wait structure used by the poll hooks */
struct eppoll_entry {
/* List header used to link this structure to the "struct epitem" */
struct eppoll_entry *next;
/* The "base" pointer is set to the container "struct epitem" */
struct epitem *base;
/*
* Wait queue item that will be linked to the target file wait
* queue head.
*/
wait_queue_entry_t wait;
/* The wait queue head that linked the "wait" wait queue item */
wait_queue_head_t *whead;
};
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
* Avoid increasing the size of this struct, there can be many thousands
* of these on a server and we do not want this to take another cache line.
*/
struct epitem {
union {
/* RB tree node links this structure to the eventpoll RB tree */
struct rb_node rbn;
/* Used to free the struct epitem */
struct rcu_head rcu;
};
/* List header used to link this structure to the eventpoll ready list */
struct list_head rdllink;
/*
* Works together "struct eventpoll"->ovflist in keeping the
* single linked chain of items.
*/
struct epitem *next;
/* The file descriptor information this item refers to */
struct epoll_filefd ffd;
/*
* Protected by file->f_lock, true for to-be-released epitem already
* removed from the "struct file" items list; together with
* eventpoll->refcount orchestrates "struct eventpoll" disposal
*/
bool dying;
/* List containing poll wait queues */
struct eppoll_entry *pwqlist;
/* The "container" of this item */
struct eventpoll *ep;
/* List header used to link this item to the "struct file" items list */
struct hlist_node fllink;
/* wakeup_source used when EPOLLWAKEUP is set */
struct wakeup_source __rcu *ws;
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
};
/*
* This structure is stored inside the "private_data" member of the file
* structure and represents the main data structure for the eventpoll
* interface.
*/
struct eventpoll {
/*
* This mutex is used to ensure that files are not removed
* while epoll is using them. This is held during the event
* collection loop, the file cleanup path, the epoll file exit
* code and the ctl operations.
*/
struct mutex mtx;
/* Wait queue used by sys_epoll_wait() */
wait_queue_head_t wq;
/* Wait queue used by file->poll() */
wait_queue_head_t poll_wait;
/* List of ready file descriptors */
struct list_head rdllist;
/* Lock which protects rdllist and ovflist */
rwlock_t lock;
/* RB tree root used to store monitored fd structs */
struct rb_root_cached rbr;
/*
* This is a single linked list that chains all the "struct epitem" that
* happened while transferring ready events to userspace w/out
* holding ->lock.
*/
struct epitem *ovflist;
/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
struct wakeup_source *ws;
/* The user that created the eventpoll descriptor */
struct user_struct *user;
struct file *file;
/* used to optimize loop detection check */
u64 gen;
struct hlist_head refs;
/*
* usage count, used together with epitem->dying to
* orchestrate the disposal of this struct
*/
refcount_t refcount;
#ifdef CONFIG_NET_RX_BUSY_POLL
/* used to track busy poll napi_id */
unsigned int napi_id;
/* busy poll timeout */
u32 busy_poll_usecs;
/* busy poll packet budget */
u16 busy_poll_budget;
bool prefer_busy_poll;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* tracks wakeup nests for lockdep validation */
u8 nests;
#endif
};
/* Wrapper struct used by poll queueing */
struct ep_pqueue {
poll_table pt;
struct epitem *epi;
};
/*
* Configuration options available inside /proc/sys/fs/epoll/
*/
/* Maximum number of epoll watched descriptors, per user */
static long max_user_watches __read_mostly;
/* Used for cycles detection */
static DEFINE_MUTEX(epnested_mutex);
static u64 loop_check_gen = 0;
/* Used to check for epoll file descriptor inclusion loops */
static struct eventpoll *inserting_into;
/* Slab cache used to allocate "struct epitem" */
static struct kmem_cache *epi_cache __ro_after_init;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __ro_after_init;
/*
* List of files with newly added links, where we may need to limit the number
* of emanating paths. Protected by the epnested_mutex.
*/
struct epitems_head {
struct hlist_head epitems;
struct epitems_head *next;
};
static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR;
static struct kmem_cache *ephead_cache __ro_after_init;
static inline void free_ephead(struct epitems_head *head)
{
if (head)
kmem_cache_free(ephead_cache, head);
}
static void list_file(struct file *file)
{
struct epitems_head *head;
head = container_of(file->f_ep, struct epitems_head, epitems);
if (!head->next) {
head->next = tfile_check_list;
tfile_check_list = head;
}
}
static void unlist_file(struct epitems_head *head)
{
struct epitems_head *to_free = head;
struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems));
if (p) {
struct epitem *epi= container_of(p, struct epitem, fllink);
spin_lock(&epi->ffd.file->f_lock);
if (!hlist_empty(&head->epitems))
to_free = NULL;
head->next = NULL;
spin_unlock(&epi->ffd.file->f_lock);
}
free_ephead(to_free);
}
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static long long_zero;
static long long_max = LONG_MAX;
static const struct ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
.maxlen = sizeof(max_user_watches),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra1 = &long_zero,
.extra2 = &long_max,
},
};
static void __init epoll_sysctls_init(void)
{
register_sysctl("fs/epoll", epoll_table);
}
#else
#define epoll_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */
static const struct file_operations eventpoll_fops;
static inline int is_file_epoll(struct file *f)
{
return f->f_op == &eventpoll_fops;
}
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
struct file *file, int fd)
{
ffd->file = file;
ffd->fd = fd;
}
/* Compare RB tree keys */
static inline int ep_cmp_ffd(struct epoll_filefd *p1,
struct epoll_filefd *p2)
{
return (p1->file > p2->file ? +1:
(p1->file < p2->file ? -1 : p1->fd - p2->fd));
}
/* Tells us if the item is currently linked */
static inline int ep_is_linked(struct epitem *epi)
{
return !list_empty(&epi->rdllink);
}
static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
{
return container_of(p, struct eppoll_entry, wait);
}
/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
{
return container_of(p, struct eppoll_entry, wait)->base;
}
/**
* ep_events_available - Checks if ready events might be available.
*
* @ep: Pointer to the eventpoll context.
*
* Return: a value different than %zero if ready events are available,
* or %zero otherwise.
*/
static inline int ep_events_available(struct eventpoll *ep)
{
return !list_empty_careful(&ep->rdllist) ||
READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
}
#ifdef CONFIG_NET_RX_BUSY_POLL
/**
* busy_loop_ep_timeout - check if busy poll has timed out. The timeout value
* from the epoll instance ep is preferred, but if it is not set fallback to
* the system-wide global via busy_loop_timeout.
*
* @start_time: The start time used to compute the remaining time until timeout.
* @ep: Pointer to the eventpoll context.
*
* Return: true if the timeout has expired, false otherwise.
*/
static bool busy_loop_ep_timeout(unsigned long start_time,
struct eventpoll *ep)
{
unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs);
if (bp_usec) {
unsigned long end_time = start_time + bp_usec;
unsigned long now = busy_loop_current_time();
return time_after(now, end_time);
} else {
return busy_loop_timeout(start_time);
}
}
static bool ep_busy_loop_on(struct eventpoll *ep)
{
return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) ||
net_busy_loop_on();
}
static bool ep_busy_loop_end(void *p, unsigned long start_time)
{
struct eventpoll *ep = p;
return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep);
}
/*
* Busy poll if globally on and supporting sockets found && no events,
* busy loop will return if need_resched or ep_events_available.
*
* we must do our busy polling with irqs enabled
*/
static bool ep_busy_loop(struct eventpoll *ep)
{
unsigned int napi_id = READ_ONCE(ep->napi_id);
u16 budget = READ_ONCE(ep->busy_poll_budget);
bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll);
if (!budget)
budget = BUSY_POLL_BUDGET;
if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) {
napi_busy_loop(napi_id, ep_busy_loop_end,
ep, prefer_busy_poll, budget);
if (ep_events_available(ep))
return true;
/*
* Busy poll timed out. Drop NAPI ID for now, we can add
* it back in when we have moved a socket with a valid NAPI
* ID onto the ready list.
*/
if (prefer_busy_poll)
napi_resume_irqs(napi_id);
ep->napi_id = 0;
return false;
}
return false;
}
/*
* Set epoll busy poll NAPI ID from sk.
*/
static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
{
struct eventpoll *ep = epi->ep;
unsigned int napi_id;
struct socket *sock;
struct sock *sk;
if (!ep_busy_loop_on(ep))
return;
sock = sock_from_file(epi->ffd.file);
if (!sock)
return;
sk = sock->sk;
if (!sk)
return;
napi_id = READ_ONCE(sk->sk_napi_id);
/* Non-NAPI IDs can be rejected
* or
* Nothing to do if we already have this ID
*/
if (!napi_id_valid(napi_id) || napi_id == ep->napi_id)
return;
/* record NAPI ID for use in next busy poll */
ep->napi_id = napi_id;
}
static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct eventpoll *ep = file->private_data;
void __user *uarg = (void __user *)arg;
struct epoll_params epoll_params;
switch (cmd) {
case EPIOCSPARAMS:
if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params)))
return -EFAULT;
/* pad byte must be zero */
if (epoll_params.__pad)
return -EINVAL;
if (epoll_params.busy_poll_usecs > S32_MAX)
return -EINVAL;
if (epoll_params.prefer_busy_poll > 1)
return -EINVAL;
if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT &&
!capable(CAP_NET_ADMIN))
return -EPERM;
WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs);
WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget);
WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll);
return 0;
case EPIOCGPARAMS:
memset(&epoll_params, 0, sizeof(epoll_params));
epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs);
epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget);
epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll);
if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params)))
return -EFAULT;
return 0;
default:
return -ENOIOCTLCMD;
}
}
static void ep_suspend_napi_irqs(struct eventpoll *ep)
{
unsigned int napi_id = READ_ONCE(ep->napi_id);
if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll))
napi_suspend_irqs(napi_id);
}
static void ep_resume_napi_irqs(struct eventpoll *ep)
{
unsigned int napi_id = READ_ONCE(ep->napi_id);
if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll))
napi_resume_irqs(napi_id);
}
#else
static inline bool ep_busy_loop(struct eventpoll *ep)
{
return false;
}
static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
{
}
static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
return -EOPNOTSUPP;
}
static void ep_suspend_napi_irqs(struct eventpoll *ep)
{
}
static void ep_resume_napi_irqs(struct eventpoll *ep)
{
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
/*
* As described in commit 0ccf831cb lockdep: annotate epoll
* the use of wait queues used by epoll is done in a very controlled
* manner. Wake ups can nest inside each other, but are never done
* with the same locking. For example:
*
* dfd = socket(...);
* efd1 = epoll_create();
* efd2 = epoll_create();
* epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...);
* epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
*
* When a packet arrives to the device underneath "dfd", the net code will
* issue a wake_up() on its poll wake list. Epoll (efd1) has installed a
* callback wakeup entry on that queue, and the wake_up() performed by the
* "dfd" net code will end up in ep_poll_callback(). At this point epoll
* (efd1) notices that it may have some event ready, so it needs to wake up
* the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
* that ends up in another wake_up(), after having checked about the
* recursion constraints. That are, no more than EP_MAX_NESTS, to avoid
* stack blasting.
*
* When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
* this special case of epoll.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi,
unsigned pollflags)
{
struct eventpoll *ep_src;
unsigned long flags;
u8 nests = 0;
/*
* To set the subclass or nesting level for spin_lock_irqsave_nested()
* it might be natural to create a per-cpu nest count. However, since
* we can recurse on ep->poll_wait.lock, and a non-raw spinlock can
* schedule() in the -rt kernel, the per-cpu variable are no longer
* protected. Thus, we are introducing a per eventpoll nest field.
* If we are not being call from ep_poll_callback(), epi is NULL and
* we are at the first level of nesting, 0. Otherwise, we are being
* called from ep_poll_callback() and if a previous wakeup source is
* not an epoll file itself, we are at depth 1 since the wakeup source
* is depth 0. If the wakeup source is a previous epoll file in the
* wakeup chain then we use its nests value and record ours as
* nests + 1. The previous epoll file nests value is stable since its
* already holding its own poll_wait.lock.
*/
if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data;
nests = ep_src->nests;
} else {
nests = 1;
}
}
spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests);
ep->nests = nests + 1;
wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags);
ep->nests = 0;
spin_unlock_irqrestore(&ep->poll_wait.lock, flags);
}
#else
static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi,
__poll_t pollflags)
{
wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags);
}
#endif
static void ep_remove_wait_queue(struct eppoll_entry *pwq)
{
wait_queue_head_t *whead;
rcu_read_lock();
/*
* If it is cleared by POLLFREE, it should be rcu-safe.
* If we read NULL we need a barrier paired with
* smp_store_release() in ep_poll_callback(), otherwise
* we rely on whead->lock.
*/
whead = smp_load_acquire(&pwq->whead);
if (whead)
remove_wait_queue(whead, &pwq->wait);
rcu_read_unlock();
}
/*
* This function unregisters poll callbacks from the associated file
* descriptor. Must be called with "mtx" held.
*/
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
struct eppoll_entry **p = &epi->pwqlist;
struct eppoll_entry *pwq;
while ((pwq = *p) != NULL) {
*p = pwq->next;
ep_remove_wait_queue(pwq);
kmem_cache_free(pwq_cache, pwq);
}
}
/* call only when ep->mtx is held */
static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi)
{
return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx));
}
/* call only when ep->mtx is held */
static inline void ep_pm_stay_awake(struct epitem *epi)
{
struct wakeup_source *ws = ep_wakeup_source(epi);
if (ws)
__pm_stay_awake(ws);
}
static inline bool ep_has_wakeup_source(struct epitem *epi)
{
return rcu_access_pointer(epi->ws) ? true : false;
}
/* call when ep->mtx cannot be held (ep_poll_callback) */
static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
{
struct wakeup_source *ws;
rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock();
}
/*
* ep->mutex needs to be held because we could be hit by
* eventpoll_release_file() and epoll_ctl().
*/
static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)
{
/*
* Steal the ready list, and re-init the original one to the
* empty list. Also, set ep->ovflist to NULL so that events
* happening while looping w/out locks, are not lost. We cannot
* have the poll callback to queue directly on ep->rdllist,
* because we want the "sproc" callback to be able to do it
* in a lockless way.
*/
lockdep_assert_irqs_enabled();
write_lock_irq(&ep->lock);
list_splice_init(&ep->rdllist, txlist);
WRITE_ONCE(ep->ovflist, NULL);
write_unlock_irq(&ep->lock);
}
static void ep_done_scan(struct eventpoll *ep,
struct list_head *txlist)
{
struct epitem *epi, *nepi;
write_lock_irq(&ep->lock);
/*
* During the time we spent inside the "sproc" callback, some
* other events might have been queued by the poll callback.
* We re-insert them inside the main ready-list here.
*/
for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL;
nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
/*
* We need to check if the item is already in the list.
* During the "sproc" callback execution time, items are
* queued into ->ovflist but the "txlist" might already
* contain them, and the list_splice() below takes care of them.
*/
if (!ep_is_linked(epi)) {
/*
* ->ovflist is LIFO, so we have to reverse it in order
* to keep in FIFO.
*/
list_add(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
}
}
/*
* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
* releasing the lock, events will be queued in the normal way inside
* ep->rdllist.
*/
WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);
/*
* Quickly re-inject items left on "txlist".
*/
list_splice(txlist, &ep->rdllist);
__pm_relax(ep->ws);
if (!list_empty(&ep->rdllist)) {
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
}
write_unlock_irq(&ep->lock);
}
static void ep_get(struct eventpoll *ep)
{
refcount_inc(&ep->refcount);
}
/*
* Returns true if the event poll can be disposed
*/
static bool ep_refcount_dec_and_test(struct eventpoll *ep)
{
if (!refcount_dec_and_test(&ep->refcount))
return false;
WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root));
return true;
}
static void ep_free(struct eventpoll *ep)
{
ep_resume_napi_irqs(ep);
mutex_destroy(&ep->mtx);
free_uid(ep->user);
wakeup_source_unregister(ep->ws);
kfree(ep);
}
/*
* Removes a "struct epitem" from the eventpoll RB tree and deallocates
* all the associated resources. Must be called with "mtx" held.
* If the dying flag is set, do the removal only if force is true.
* This prevents ep_clear_and_put() from dropping all the ep references
* while running concurrently with eventpoll_release_file().
* Returns true if the eventpoll can be disposed.
*/
static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
{
struct file *file = epi->ffd.file;
struct epitems_head *to_free;
struct hlist_head *head;
lockdep_assert_irqs_enabled();
/*
* Removes poll wait queue hooks.
*/
ep_unregister_pollwait(ep, epi);
/* Remove the current item from the list of epoll hooks */
spin_lock(&file->f_lock);
if (epi->dying && !force) {
spin_unlock(&file->f_lock);
return false;
}
to_free = NULL;
head = file->f_ep;
if (head->first == &epi->fllink && !epi->fllink.next) {
/* See eventpoll_release() for details. */
WRITE_ONCE(file->f_ep, NULL);
if (!is_file_epoll(file)) {
struct epitems_head *v;
v = container_of(head, struct epitems_head, epitems);
if (!smp_load_acquire(&v->next))
to_free = v;
}
}
hlist_del_rcu(&epi->fllink);
spin_unlock(&file->f_lock);
free_ephead(to_free);
rb_erase_cached(&epi->rbn, &ep->rbr);
write_lock_irq(&ep->lock);
if (ep_is_linked(epi))
list_del_init(&epi->rdllink);
write_unlock_irq(&ep->lock);
wakeup_source_unregister(ep_wakeup_source(epi));
/*
* At this point it is safe to free the eventpoll item. Use the union
* field epi->rcu, since we are trying to minimize the size of
* 'struct epitem'. The 'rbn' field is no longer in use. Protected by
* ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
* use of the rbn field.
*/
kfree_rcu(epi, rcu);
percpu_counter_dec(&ep->user->epoll_watches);
return ep_refcount_dec_and_test(ep);
}
/*
* ep_remove variant for callers owing an additional reference to the ep
*/
static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi)
{
WARN_ON_ONCE(__ep_remove(ep, epi, false));
}
static void ep_clear_and_put(struct eventpoll *ep)
{
struct rb_node *rbp, *next;
struct epitem *epi;
bool dispose;
/* We need to release all tasks waiting for these file */
if (waitqueue_active(&ep->poll_wait))
ep_poll_safewake(ep, NULL, 0);
mutex_lock(&ep->mtx);
/*
* Walks through the whole tree by unregistering poll callbacks.
*/
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_unregister_pollwait(ep, epi);
cond_resched();
}
/*
* Walks through the whole tree and try to free each "struct epitem".
* Note that ep_remove_safe() will not remove the epitem in case of a
* racing eventpoll_release_file(); the latter will do the removal.
* At this point we are sure no poll callbacks will be lingering around.
* Since we still own a reference to the eventpoll struct, the loop can't
* dispose it.
*/
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) {
next = rb_next(rbp);
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove_safe(ep, epi);
cond_resched();
}
dispose = ep_refcount_dec_and_test(ep);
mutex_unlock(&ep->mtx);
if (dispose)
ep_free(ep);
}
static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
int ret;
if (!is_file_epoll(file))
return -EINVAL;
switch (cmd) {
case EPIOCSPARAMS:
case EPIOCGPARAMS:
ret = ep_eventpoll_bp_ioctl(file, cmd, arg);
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
struct eventpoll *ep = file->private_data;
if (ep)
ep_clear_and_put(ep);
return 0;
}
static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth);
static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth)
{
struct eventpoll *ep = file->private_data;
LIST_HEAD(txlist);
struct epitem *epi, *tmp;
poll_table pt;
__poll_t res = 0;
init_poll_funcptr(&pt, NULL);
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
/*
* Proceed to find out if wanted events are really available inside
* the ready list.
*/
mutex_lock_nested(&ep->mtx, depth);
ep_start_scan(ep, &txlist);
list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
if (ep_item_poll(epi, &pt, depth + 1)) {
res = EPOLLIN | EPOLLRDNORM;
break;
} else {
/*
* Item has been dropped into the ready list by the poll
* callback, but it's not actually ready, as far as
* caller requested events goes. We can remove it here.
*/
__pm_relax(ep_wakeup_source(epi));
list_del_init(&epi->rdllink);
}
}
ep_done_scan(ep, &txlist);
mutex_unlock(&ep->mtx);
return res;
}
/*
* The ffd.file pointer may be in the process of being torn down due to
* being closed, but we may not have finished eventpoll_release() yet.
*
* Normally, even with the atomic_long_inc_not_zero, the file may have
* been free'd and then gotten re-allocated to something else (since
* files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
*
* But for epoll, users hold the ep->mtx mutex, and as such any file in
* the process of being free'd will block in eventpoll_release_file()
* and thus the underlying file allocation will not be free'd, and the
* file re-use cannot happen.
*
* For the same reason we can avoid a rcu_read_lock() around the
* operation - 'ffd.file' cannot go away even if the refcount has
* reached zero (but we must still not call out to ->poll() functions
* etc).
*/
static struct file *epi_fget(const struct epitem *epi)
{
struct file *file;
file = epi->ffd.file;
if (!file_ref_get(&file->f_ref))
file = NULL;
return file;
}
/*
* Differs from ep_eventpoll_poll() in that internal callers already have
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
* is correctly annotated.
*/
static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
int depth)
{
struct file *file = epi_fget(epi);
__poll_t res;
/*
* We could return EPOLLERR | EPOLLHUP or something, but let's
* treat this more as "file doesn't exist, poll didn't happen".
*/
if (!file)
return 0;
pt->_key = epi->event.events;
if (!is_file_epoll(file))
res = vfs_poll(file, pt);
else
res = __ep_eventpoll_poll(file, pt, depth);
fput(file);
return res & epi->event.events;
}
static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
{
return __ep_eventpoll_poll(file, wait, 0);
}
#ifdef CONFIG_PROC_FS
static void ep_show_fdinfo(struct seq_file *m, struct file *f)
{
struct eventpoll *ep = f->private_data;
struct rb_node *rbp;
mutex_lock(&ep->mtx);
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
struct inode *inode = file_inode(epi->ffd.file);
seq_printf(m, "tfd: %8d events: %8x data: %16llx "
" pos:%lli ino:%lx sdev:%x\n",
epi->ffd.fd, epi->event.events,
(long long)epi->event.data,
(long long)epi->ffd.file->f_pos,
inode->i_ino, inode->i_sb->s_dev);
if (seq_has_overflowed(m))
break;
}
mutex_unlock(&ep->mtx);
}
#endif
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = ep_show_fdinfo,
#endif
.release = ep_eventpoll_release,
.poll = ep_eventpoll_poll,
.llseek = noop_llseek,
.unlocked_ioctl = ep_eventpoll_ioctl,
.compat_ioctl = compat_ptr_ioctl,
};
/*
* This is called from eventpoll_release() to unlink files from the eventpoll
* interface. We need to have this facility to cleanup correctly files that are
* closed without being removed from the eventpoll interface.
*/
void eventpoll_release_file(struct file *file)
{
struct eventpoll *ep;
struct epitem *epi;
bool dispose;
/*
* Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from
* touching the epitems list before eventpoll_release_file() can access
* the ep->mtx.
*/
again:
spin_lock(&file->f_lock);
if (file->f_ep && file->f_ep->first) {
epi = hlist_entry(file->f_ep->first, struct epitem, fllink);
epi->dying = true;
spin_unlock(&file->f_lock);
/*
* ep access is safe as we still own a reference to the ep
* struct
*/
ep = epi->ep;
mutex_lock(&ep->mtx);
dispose = __ep_remove(ep, epi, true);
mutex_unlock(&ep->mtx);
if (dispose)
ep_free(ep);
goto again;
}
spin_unlock(&file->f_lock);
}
static int ep_alloc(struct eventpoll **pep)
{
struct eventpoll *ep;
ep = kzalloc(sizeof(*ep), GFP_KERNEL);
if (unlikely(!ep))
return -ENOMEM;
mutex_init(&ep->mtx);
rwlock_init(&ep->lock);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT_CACHED;
ep->ovflist = EP_UNACTIVE_PTR;
ep->user = get_current_user();
refcount_set(&ep->refcount, 1);
*pep = ep;
return 0;
}
/*
* Search the file inside the eventpoll tree. The RB tree operations
* are protected by the "mtx" mutex, and ep_find() must be called with
* "mtx" held.
*/
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
int kcmp;
struct rb_node *rbp;
struct epitem *epi, *epir = NULL;
struct epoll_filefd ffd;
ep_set_ffd(&ffd, file, fd);
for (rbp = ep->rbr.rb_root.rb_node; rbp; ) {
epi = rb_entry(rbp, struct epitem, rbn);
kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
if (kcmp > 0)
rbp = rbp->rb_right;
else if (kcmp < 0)
rbp = rbp->rb_left;
else {
epir = epi;
break;
}
}
return epir;
}
#ifdef CONFIG_KCMP
static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
{
struct rb_node *rbp;
struct epitem *epi;
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
if (epi->ffd.fd == tfd) {
if (toff == 0)
return epi;
else
toff--;
}
cond_resched();
}
return NULL;
}
struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
unsigned long toff)
{
struct file *file_raw;
struct eventpoll *ep;
struct epitem *epi;
if (!is_file_epoll(file))
return ERR_PTR(-EINVAL);
ep = file->private_data;
mutex_lock(&ep->mtx);
epi = ep_find_tfd(ep, tfd, toff);
if (epi)
file_raw = epi->ffd.file;
else
file_raw = ERR_PTR(-ENOENT);
mutex_unlock(&ep->mtx);
return file_raw;
}
#endif /* CONFIG_KCMP */
/*
* Adds a new entry to the tail of the list in a lockless way, i.e.
* multiple CPUs are allowed to call this function concurrently.
*
* Beware: it is necessary to prevent any other modifications of the
* existing list until all changes are completed, in other words
* concurrent list_add_tail_lockless() calls should be protected
* with a read lock, where write lock acts as a barrier which
* makes sure all list_add_tail_lockless() calls are fully
* completed.
*
* Also an element can be locklessly added to the list only in one
* direction i.e. either to the tail or to the head, otherwise
* concurrent access will corrupt the list.
*
* Return: %false if element has been already added to the list, %true
* otherwise.
*/
static inline bool list_add_tail_lockless(struct list_head *new,
struct list_head *head)
{
struct list_head *prev;
/*
* This is simple 'new->next = head' operation, but cmpxchg()
* is used in order to detect that same element has been just
* added to the list from another CPU: the winner observes
* new->next == new.
*/
if (!try_cmpxchg(&new->next, &new, head))
return false;
/*
* Initially ->next of a new element must be updated with the head
* (we are inserting to the tail) and only then pointers are atomically
* exchanged. XCHG guarantees memory ordering, thus ->next should be
* updated before pointers are actually swapped and pointers are
* swapped before prev->next is updated.
*/
prev = xchg(&head->prev, new);
/*
* It is safe to modify prev->next and new->prev, because a new element
* is added only to the tail and new->next is updated before XCHG.
*/
prev->next = new;
new->prev = prev;
return true;
}
/*
* Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
* i.e. multiple CPUs are allowed to call this function concurrently.
*
* Return: %false if epi element has been already chained, %true otherwise.
*/
static inline bool chain_epi_lockless(struct epitem *epi)
{
struct eventpoll *ep = epi->ep;
/* Fast preliminary check */
if (epi->next != EP_UNACTIVE_PTR)
return false;
/* Check that the same epi has not been just chained from another CPU */
if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
return false;
/* Atomically exchange tail */
epi->next = xchg(&ep->ovflist, epi);
return true;
}
/*
* This is the callback that is passed to the wait queue wakeup
* mechanism. It is called by the stored file descriptors when they
* have events to report.
*
* This callback takes a read lock in order not to contend with concurrent
* events from another file descriptor, thus all modifications to ->rdllist
* or ->ovflist are lockless. Read lock is paired with the write lock from
* ep_start/done_scan(), which stops all list modifications and guarantees
* that lists state is seen correctly.
*
* Another thing worth to mention is that ep_poll_callback() can be called
* concurrently for the same @epi from different CPUs if poll table was inited
* with several wait queues entries. Plural wakeup from different CPUs of a
* single wait queue is serialized by wq.lock, but the case when multiple wait
* queues are used should be detected accordingly. This is detected using
* cmpxchg() operation.
*/
static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
int pwake = 0;
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
__poll_t pollflags = key_to_poll(key);
unsigned long flags;
int ewake = 0;
read_lock_irqsave(&ep->lock, flags);
ep_set_busy_poll_napi_id(epi);
/*
* If the event mask does not contain any poll(2) event, we consider the
* descriptor to be disabled. This condition is likely the effect of the
* EPOLLONESHOT bit that disables the descriptor when an event is received,
* until the next EPOLL_CTL_MOD will be issued.
*/
if (!(epi->event.events & ~EP_PRIVATE_BITS))
goto out_unlock;
/*
* Check the events coming with the callback. At this stage, not
* every device reports the events in the "key" parameter of the
* callback. We need to be able to handle both cases here, hence the
* test for "key" != NULL before the event match test.
*/
if (pollflags && !(pollflags & epi->event.events))
goto out_unlock;
/*
* If we are transferring events to userspace, we can hold no locks
* (because we're accessing user memory, and because of linux f_op->poll()
* semantics). All the events that happen during that period of time are
* chained in ep->ovflist and requeued later on.
*/
if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
if (chain_epi_lockless(epi))
ep_pm_stay_awake_rcu(epi);
} else if (!ep_is_linked(epi)) {
/* In the usual case, add event to ready list. */
if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
ep_pm_stay_awake_rcu(epi);
}
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) &&
!(pollflags & POLLFREE)) {
switch (pollflags & EPOLLINOUT_BITS) {
case EPOLLIN:
if (epi->event.events & EPOLLIN)
ewake = 1;
break;
case EPOLLOUT:
if (epi->event.events & EPOLLOUT)
ewake = 1;
break;
case 0:
ewake = 1;
break;
}
}
if (sync)
wake_up_sync(&ep->wq);
else
wake_up(&ep->wq);
}
if (waitqueue_active(&ep->poll_wait))
pwake++;
out_unlock:
read_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE);
if (!(epi->event.events & EPOLLEXCLUSIVE))
ewake = 1;
if (pollflags & POLLFREE) {
/*
* If we race with ep_remove_wait_queue() it can miss
* ->whead = NULL and do another remove_wait_queue() after
* us, so we can't use __remove_wait_queue().
*/
list_del_init(&wait->entry);
/*
* ->whead != NULL protects us from the race with
* ep_clear_and_put() or ep_remove(), ep_remove_wait_queue()
* takes whead->lock held by the caller. Once we nullify it,
* nothing protects ep/epi or even wait.
*/
smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
}
return ewake;
}
/*
* This is the callback that is used to add our wait queue to the
* target file wakeup lists.
*/
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
poll_table *pt)
{
struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt);
struct epitem *epi = epq->epi;
struct eppoll_entry *pwq;
if (unlikely(!epi)) // an earlier allocation has failed
return;
pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL);
if (unlikely(!pwq)) {
epq->epi = NULL;
return;
}
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
if (epi->event.events & EPOLLEXCLUSIVE)
add_wait_queue_exclusive(whead, &pwq->wait);
else
add_wait_queue(whead, &pwq->wait);
pwq->next = epi->pwqlist;
epi->pwqlist = pwq;
}
static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
int kcmp;
struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL;
struct epitem *epic;
bool leftmost = true;
while (*p) {
parent = *p;
epic = rb_entry(parent, struct epitem, rbn);
kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
if (kcmp > 0) {
p = &parent->rb_right;
leftmost = false;
} else
p = &parent->rb_left;
}
rb_link_node(&epi->rbn, parent, p);
rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost);
}
#define PATH_ARR_SIZE 5
/*
* These are the number paths of length 1 to 5, that we are allowing to emanate
* from a single file of interest. For example, we allow 1000 paths of length
* 1, to emanate from each file of interest. This essentially represents the
* potential wakeup paths, which need to be limited in order to avoid massive
* uncontrolled wakeup storms. The common use case should be a single ep which
* is connected to n file sources. In this case each file source has 1 path
* of length 1. Thus, the numbers below should be more than sufficient. These
* path limits are enforced during an EPOLL_CTL_ADD operation, since a modify
* and delete can't add additional paths. Protected by the epnested_mutex.
*/
static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 };
static int path_count[PATH_ARR_SIZE];
static int path_count_inc(int nests)
{
/* Allow an arbitrary number of depth 1 paths */
if (nests == 0)
return 0;
if (++path_count[nests] > path_limits[nests])
return -1;
return 0;
}
static void path_count_init(void)
{
int i;
for (i = 0; i < PATH_ARR_SIZE; i++)
path_count[i] = 0;
}
static int reverse_path_check_proc(struct hlist_head *refs, int depth)
{
int error = 0;
struct epitem *epi;
if (depth > EP_MAX_NESTS) /* too deep nesting */
return -1;
/* CTL_DEL can remove links here, but that can't increase our count */
hlist_for_each_entry_rcu(epi, refs, fllink) {
struct hlist_head *refs = &epi->ep->refs;
if (hlist_empty(refs))
error = path_count_inc(depth);
else
error = reverse_path_check_proc(refs, depth + 1);
if (error != 0)
break;
}
return error;
}
/**
* reverse_path_check - The tfile_check_list is list of epitem_head, which have
* links that are proposed to be newly added. We need to
* make sure that those added links don't add too many
* paths such that we will spend all our time waking up
* eventpoll objects.
*
* Return: %zero if the proposed links don't create too many paths,
* %-1 otherwise.
*/
static int reverse_path_check(void)
{
struct epitems_head *p;
for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) {
int error;
path_count_init();
rcu_read_lock();
error = reverse_path_check_proc(&p->epitems, 0);
rcu_read_unlock();
if (error)
return error;
}
return 0;
}
static int ep_create_wakeup_source(struct epitem *epi)
{
struct name_snapshot n;
struct wakeup_source *ws;
if (!epi->ep->ws) {
epi->ep->ws = wakeup_source_register(NULL, "eventpoll");
if (!epi->ep->ws)
return -ENOMEM;
}
take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry);
ws = wakeup_source_register(NULL, n.name.name);
release_dentry_name_snapshot(&n);
if (!ws)
return -ENOMEM;
rcu_assign_pointer(epi->ws, ws);
return 0;
}
/* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */
static noinline void ep_destroy_wakeup_source(struct epitem *epi)
{
struct wakeup_source *ws = ep_wakeup_source(epi);
RCU_INIT_POINTER(epi->ws, NULL);
/*
* wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is
* used internally by wakeup_source_remove, too (called by
* wakeup_source_unregister), so we cannot use call_rcu
*/
synchronize_rcu();
wakeup_source_unregister(ws);
}
static int attach_epitem(struct file *file, struct epitem *epi)
{
struct epitems_head *to_free = NULL;
struct hlist_head *head = NULL;
struct eventpoll *ep = NULL;
if (is_file_epoll(file))
ep = file->private_data;
if (ep) {
head = &ep->refs;
} else if (!READ_ONCE(file->f_ep)) {
allocate:
to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL);
if (!to_free)
return -ENOMEM;
head = &to_free->epitems;
}
spin_lock(&file->f_lock);
if (!file->f_ep) {
if (unlikely(!head)) {
spin_unlock(&file->f_lock);
goto allocate;
}
/* See eventpoll_release() for details. */
WRITE_ONCE(file->f_ep, head);
to_free = NULL;
}
hlist_add_head_rcu(&epi->fllink, file->f_ep);
spin_unlock(&file->f_lock);
free_ephead(to_free);
return 0;
}
/*
* Must be called with "mtx" held.
*/
static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
struct file *tfile, int fd, int full_check)
{
int error, pwake = 0;
__poll_t revents;
struct epitem *epi;
struct ep_pqueue epq;
struct eventpoll *tep = NULL;
if (is_file_epoll(tfile))
tep = tfile->private_data;
lockdep_assert_irqs_enabled();
if (unlikely(percpu_counter_compare(&ep->user->epoll_watches,
max_user_watches) >= 0))
return -ENOSPC;
percpu_counter_inc(&ep->user->epoll_watches);
if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) {
percpu_counter_dec(&ep->user->epoll_watches);
return -ENOMEM;
}
/* Item initialization follow here ... */
INIT_LIST_HEAD(&epi->rdllink);
epi->ep = ep;
ep_set_ffd(&epi->ffd, tfile, fd);
epi->event = *event;
epi->next = EP_UNACTIVE_PTR;
if (tep)
mutex_lock_nested(&tep->mtx, 1);
/* Add the current item to the list of active epoll hook for this file */
if (unlikely(attach_epitem(tfile, epi) < 0)) {
if (tep)
mutex_unlock(&tep->mtx);
kmem_cache_free(epi_cache, epi);
percpu_counter_dec(&ep->user->epoll_watches);
return -ENOMEM;
}
if (full_check && !tep)
list_file(tfile);
/*
* Add the current item to the RB tree. All RB tree operations are
* protected by "mtx", and ep_insert() is called with "mtx" held.
*/
ep_rbtree_insert(ep, epi);
if (tep)
mutex_unlock(&tep->mtx);
/*
* ep_remove_safe() calls in the later error paths can't lead to
* ep_free() as the ep file itself still holds an ep reference.
*/
ep_get(ep);
/* now check if we've created too many backpaths */
if (unlikely(full_check && reverse_path_check())) {
ep_remove_safe(ep, epi);
return -EINVAL;
}
if (epi->event.events & EPOLLWAKEUP) {
error = ep_create_wakeup_source(epi);
if (error) {
ep_remove_safe(ep, epi);
return error;
}
}
/* Initialize the poll table using the queue callback */
epq.epi = epi;
init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
/*
* Attach the item to the poll hooks and get current event bits.
* We can safely use the file* here because its usage count has
* been increased by the caller of this function. Note that after
* this operation completes, the poll callback can start hitting
* the new item.
*/
revents = ep_item_poll(epi, &epq.pt, 1);
/*
* We have to check if something went wrong during the poll wait queue
* install process. Namely an allocation for a wait queue failed due
* high memory pressure.
*/
if (unlikely(!epq.epi)) {
ep_remove_safe(ep, epi);
return -ENOMEM;
}
/* We have to drop the new item inside our item list to keep track of it */
write_lock_irq(&ep->lock);
/* record NAPI ID of new item if present */
ep_set_busy_poll_napi_id(epi);
/* If the file is already "ready" we drop it inside the ready list */
if (revents && !ep_is_linked(epi)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
write_unlock_irq(&ep->lock);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(ep, NULL, 0);
return 0;
}
/*
* Modify the interest event mask by dropping an event if the new mask
* has a match in the current file status. Must be called with "mtx" held.
*/
static int ep_modify(struct eventpoll *ep, struct epitem *epi,
const struct epoll_event *event)
{
int pwake = 0;
poll_table pt;
lockdep_assert_irqs_enabled();
init_poll_funcptr(&pt, NULL);
/*
* Set the new event interest mask before calling f_op->poll();
* otherwise we might miss an event that happens between the
* f_op->poll() call and the new event set registering.
*/
epi->event.events = event->events; /* need barrier below */
epi->event.data = event->data; /* protected by mtx */
if (epi->event.events & EPOLLWAKEUP) {
if (!ep_has_wakeup_source(epi))
ep_create_wakeup_source(epi);
} else if (ep_has_wakeup_source(epi)) {
ep_destroy_wakeup_source(epi);
}
/*
* The following barrier has two effects:
*
* 1) Flush epi changes above to other CPUs. This ensures
* we do not miss events from ep_poll_callback if an
* event occurs immediately after we call f_op->poll().
* We need this because we did not take ep->lock while
* changing epi above (but ep_poll_callback does take
* ep->lock).
*
* 2) We also need to ensure we do not miss _past_ events
* when calling f_op->poll(). This barrier also
* pairs with the barrier in wq_has_sleeper (see
* comments for wq_has_sleeper).
*
* This barrier will now guarantee ep_poll_callback or f_op->poll
* (or both) will notice the readiness of an item.
*/
smp_mb();
/*
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
* If the item is "hot" and it is not registered inside the ready
* list, push it inside.
*/
if (ep_item_poll(epi, &pt, 1)) {
write_lock_irq(&ep->lock);
if (!ep_is_linked(epi)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
wake_up(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
write_unlock_irq(&ep->lock);
}
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(ep, NULL, 0);
return 0;
}
static int ep_send_events(struct eventpoll *ep,
struct epoll_event __user *events, int maxevents)
{
struct epitem *epi, *tmp;
LIST_HEAD(txlist);
poll_table pt;
int res = 0;
/*
* Always short-circuit for fatal signals to allow threads to make a
* timely exit without the chance of finding more events available and
* fetching repeatedly.
*/
if (fatal_signal_pending(current))
return -EINTR;
init_poll_funcptr(&pt, NULL);
mutex_lock(&ep->mtx);
ep_start_scan(ep, &txlist);
/*
* We can loop without lock because we are passed a task private list.
* Items cannot vanish during the loop we are holding ep->mtx.
*/
list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
struct wakeup_source *ws;
__poll_t revents;
if (res >= maxevents)
break;
/*
* Activate ep->ws before deactivating epi->ws to prevent
* triggering auto-suspend here (in case we reactive epi->ws
* below).
*
* This could be rearranged to delay the deactivation of epi->ws
* instead, but then epi->ws would temporarily be out of sync
* with ep_is_linked().
*/
ws = ep_wakeup_source(epi);
if (ws) {
if (ws->active)
__pm_stay_awake(ep->ws);
__pm_relax(ws);
}
list_del_init(&epi->rdllink);
/*
* If the event mask intersect the caller-requested one,
* deliver the event to userspace. Again, we are holding ep->mtx,
* so no operations coming from userspace can change the item.
*/
revents = ep_item_poll(epi, &pt, 1);
if (!revents)
continue;
events = epoll_put_uevent(revents, epi->event.data, events);
if (!events) {
list_add(&epi->rdllink, &txlist);
ep_pm_stay_awake(epi);
if (!res)
res = -EFAULT;
break;
}
res++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {
/*
* If this file has been added with Level
* Trigger mode, we need to insert back inside
* the ready list, so that the next call to
* epoll_wait() will check again the events
* availability. At this point, no one can insert
* into ep->rdllist besides us. The epoll_ctl()
* callers are locked out by
* ep_send_events() holding "mtx" and the
* poll callback will queue them in ep->ovflist.
*/
list_add_tail(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
}
}
ep_done_scan(ep, &txlist);
mutex_unlock(&ep->mtx);
return res;
}
static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
{
struct timespec64 now;
if (ms < 0)
return NULL;
if (!ms) {
to->tv_sec = 0;
to->tv_nsec = 0;
return to;
}
to->tv_sec = ms / MSEC_PER_SEC;
to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC);
ktime_get_ts64(&now);
*to = timespec64_add_safe(now, *to);
return to;
}
/*
* autoremove_wake_function, but remove even on failure to wake up, because we
* know that default_wake_function/ttwu will only fail if the thread is already
* woken, and in that case the ep_poll loop will remove the entry anyways, not
* try to reuse it.
*/
static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
unsigned int mode, int sync, void *key)
{
int ret = default_wake_function(wq_entry, mode, sync, key);
/*
* Pairs with list_empty_careful in ep_poll, and ensures future loop
* iterations see the cause of this wakeup.
*/
list_del_init_careful(&wq_entry->entry);
return ret;
}
static int ep_try_send_events(struct eventpoll *ep,
struct epoll_event __user *events, int maxevents)
{
int res;
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
res = ep_send_events(ep, events, maxevents);
if (res > 0)
ep_suspend_napi_irqs(ep);
return res;
}
static int ep_schedule_timeout(ktime_t *to)
{
if (to)
return ktime_after(*to, ktime_get());
else
return 1;
}
/**
* ep_poll - Retrieves ready events, and delivers them to the caller-supplied
* event buffer.
*
* @ep: Pointer to the eventpoll context.
* @events: Pointer to the userspace buffer where the ready events should be
* stored.
* @maxevents: Size (in terms of number of events) of the caller event buffer.
* @timeout: Maximum timeout for the ready events fetch operation, in
* timespec. If the timeout is zero, the function will not block,
* while if the @timeout ptr is NULL, the function will block
* until at least one event has been retrieved (or an error
* occurred).
*
* Return: the number of ready events which have been fetched, or an
* error code, in case of error.
*/
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, struct timespec64 *timeout)
{
int res, eavail, timed_out = 0;
u64 slack = 0;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
lockdep_assert_irqs_enabled();
if (timeout && (timeout->tv_sec | timeout->tv_nsec)) {
slack = select_estimate_accuracy(timeout);
to = &expires;
*to = timespec64_to_ktime(*timeout);
} else if (timeout) {
/*
* Avoid the unnecessary trip to the wait queue loop, if the
* caller specified a non blocking operation.
*/
timed_out = 1;
}
/*
* This call is racy: We may or may not see events that are being added
* to the ready list under the lock (e.g., in IRQ callbacks). For cases
* with a non-zero timeout, this thread will check the ready list under
* lock and will add to the wait queue. For cases with a zero
* timeout, the user by definition should not care and will have to
* recheck again.
*/
eavail = ep_events_available(ep);
while (1) {
if (eavail) {
res = ep_try_send_events(ep, events, maxevents);
if (res)
return res;
}
if (timed_out)
return 0;
eavail = ep_busy_loop(ep);
if (eavail)
continue;
if (signal_pending(current))
return -EINTR;
/*
* Internally init_wait() uses autoremove_wake_function(),
* thus wait entry is removed from the wait queue on each
* wakeup. Why it is important? In case of several waiters
* each new wakeup will hit the next waiter, giving it the
* chance to harvest new event. Otherwise wakeup can be
* lost. This is also good performance-wise, because on
* normal wakeup path no need to call __remove_wait_queue()
* explicitly, thus ep->lock is not taken, which halts the
* event delivery.
*
* In fact, we now use an even more aggressive function that
* unconditionally removes, because we don't reuse the wait
* entry between loop iterations. This lets us also avoid the
* performance issue if a process is killed, causing all of its
* threads to wake up without being removed normally.
*/
init_wait(&wait);
wait.func = ep_autoremove_wake_function;
write_lock_irq(&ep->lock);
/*
* Barrierless variant, waitqueue_active() is called under
* the same lock on wakeup ep_poll_callback() side, so it
* is safe to avoid an explicit barrier.
*/
__set_current_state(TASK_INTERRUPTIBLE);
/*
* Do the final check under the lock. ep_start/done_scan()
* plays with two lists (->rdllist and ->ovflist) and there
* is always a race when both lists are empty for short
* period of time although events are pending, so lock is
* important.
*/
eavail = ep_events_available(ep);
if (!eavail)
__add_wait_queue_exclusive(&ep->wq, &wait);
write_unlock_irq(&ep->lock);
if (!eavail && ep_schedule_timeout(to))
timed_out = !schedule_hrtimeout_range(to, slack,
HRTIMER_MODE_ABS);
__set_current_state(TASK_RUNNING);
/*
* We were woken up, thus go and try to harvest some events.
* If timed out and still on the wait queue, recheck eavail
* carefully under lock, below.
*/
eavail = 1;
if (!list_empty_careful(&wait.entry)) {
write_lock_irq(&ep->lock);
/*
* If the thread timed out and is not on the wait queue,
* it means that the thread was woken up after its
* timeout expired before it could reacquire the lock.
* Thus, when wait.entry is empty, it needs to harvest
* events.
*/
if (timed_out)
eavail = list_empty(&wait.entry);
__remove_wait_queue(&ep->wq, &wait);
write_unlock_irq(&ep->lock);
}
}
}
/**
* ep_loop_check_proc - verify that adding an epoll file inside another
* epoll structure does not violate the constraints, in
* terms of closed loops, or too deep chains (which can
* result in excessive stack usage).
*
* @ep: the &struct eventpoll to be currently checked.
* @depth: Current depth of the path being checked.
*
* Return: %zero if adding the epoll @file inside current epoll
* structure @ep does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check_proc(struct eventpoll *ep, int depth)
{
int error = 0;
struct rb_node *rbp;
struct epitem *epi;
mutex_lock_nested(&ep->mtx, depth + 1);
ep->gen = loop_check_gen;
for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
if (unlikely(is_file_epoll(epi->ffd.file))) {
struct eventpoll *ep_tovisit;
ep_tovisit = epi->ffd.file->private_data;
if (ep_tovisit->gen == loop_check_gen)
continue;
if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
error = -1;
else
error = ep_loop_check_proc(ep_tovisit, depth + 1);
if (error != 0)
break;
} else {
/*
* If we've reached a file that is not associated with
* an ep, then we need to check if the newly added
* links are going to add too many wakeup paths. We do
* this by adding it to the tfile_check_list, if it's
* not already there, and calling reverse_path_check()
* during ep_insert().
*/
list_file(epi->ffd.file);
}
}
mutex_unlock(&ep->mtx);
return error;
}
/**
* ep_loop_check - Performs a check to verify that adding an epoll file (@to)
* into another epoll file (represented by @ep) does not create
* closed loops or too deep chains.
*
* @ep: Pointer to the epoll we are inserting into.
* @to: Pointer to the epoll to be inserted.
*
* Return: %zero if adding the epoll @to inside the epoll @from
* does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
{
inserting_into = ep;
return ep_loop_check_proc(to, 0);
}
static void clear_tfile_check_list(void)
{
rcu_read_lock();
while (tfile_check_list != EP_UNACTIVE_PTR) {
struct epitems_head *head = tfile_check_list;
tfile_check_list = head->next;
unlist_file(head);
}
rcu_read_unlock();
}
/*
* Open an eventpoll file descriptor.
*/
static int do_epoll_create(int flags)
{
int error, fd;
struct eventpoll *ep = NULL;
struct file *file;
/* Check the EPOLL_* constant for consistency. */
BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
if (flags & ~EPOLL_CLOEXEC)
return -EINVAL;
/*
* Create the internal data structure ("struct eventpoll").
*/
error = ep_alloc(&ep);
if (error < 0)
return error;
/*
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
if (fd < 0) {
error = fd;
goto out_free_ep;
}
file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
O_RDWR | (flags & O_CLOEXEC));
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto out_free_fd;
}
ep->file = file;
fd_install(fd, file);
return fd;
out_free_fd:
put_unused_fd(fd);
out_free_ep:
ep_clear_and_put(ep);
return error;
}
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
return do_epoll_create(flags);
}
SYSCALL_DEFINE1(epoll_create, int, size)
{
if (size <= 0)
return -EINVAL;
return do_epoll_create(0);
}
#ifdef CONFIG_PM_SLEEP
static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev)
{
if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
epev->events &= ~EPOLLWAKEUP;
}
#else
static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev)
{
epev->events &= ~EPOLLWAKEUP;
}
#endif
static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
bool nonblock)
{
if (!nonblock) {
mutex_lock_nested(mutex, depth);
return 0;
}
if (mutex_trylock(mutex))
return 0;
return -EAGAIN;
}
int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
bool nonblock)
{
int error;
int full_check = 0;
struct eventpoll *ep;
struct epitem *epi;
struct eventpoll *tep = NULL;
CLASS(fd, f)(epfd);
if (fd_empty(f))
return -EBADF;
/* Get the "struct file *" for the target file */
CLASS(fd, tf)(fd);
if (fd_empty(tf))
return -EBADF;
/* The target file descriptor must support poll */
if (!file_can_poll(fd_file(tf)))
return -EPERM;
/* Check if EPOLLWAKEUP is allowed */
if (ep_op_has_event(op))
ep_take_care_of_epollwakeup(epds);
/*
* We have to check that the file structure underneath the file descriptor
* the user passed to us _is_ an eventpoll file. And also we do not permit
* adding an epoll file descriptor inside itself.
*/
error = -EINVAL;
if (fd_file(f) == fd_file(tf) || !is_file_epoll(fd_file(f)))
goto error_tgt_fput;
/*
* epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
* so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
* Also, we do not currently supported nested exclusive wakeups.
*/
if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
if (op == EPOLL_CTL_MOD)
goto error_tgt_fput;
if (op == EPOLL_CTL_ADD && (is_file_epoll(fd_file(tf)) ||
(epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
goto error_tgt_fput;
}
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = fd_file(f)->private_data;
/*
* When we insert an epoll file descriptor inside another epoll file
* descriptor, there is the chance of creating closed loops, which are
* better be handled here, than in more critical paths. While we are
* checking for loops we also determine the list of files reachable
* and hang them on the tfile_check_list, so we can check that we
* haven't created too many possible wakeup paths.
*
* We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when
* the epoll file descriptor is attaching directly to a wakeup source,
* unless the epoll file descriptor is nested. The purpose of taking the
* 'epnested_mutex' on add is to prevent complex toplogies such as loops and
* deep wakeup paths from forming in parallel through multiple
* EPOLL_CTL_ADD operations.
*/
error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
if (error)
goto error_tgt_fput;
if (op == EPOLL_CTL_ADD) {
if (READ_ONCE(fd_file(f)->f_ep) || ep->gen == loop_check_gen ||
is_file_epoll(fd_file(tf))) {
mutex_unlock(&ep->mtx);
error = epoll_mutex_lock(&epnested_mutex, 0, nonblock);
if (error)
goto error_tgt_fput;
loop_check_gen++;
full_check = 1;
if (is_file_epoll(fd_file(tf))) {
tep = fd_file(tf)->private_data;
error = -ELOOP;
if (ep_loop_check(ep, tep) != 0)
goto error_tgt_fput;
}
error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
if (error)
goto error_tgt_fput;
}
}
/*
* Try to lookup the file inside our RB tree. Since we grabbed "mtx"
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
epi = ep_find(ep, fd_file(tf), fd);
error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
epds->events |= EPOLLERR | EPOLLHUP;
error = ep_insert(ep, epds, fd_file(tf), fd, full_check);
} else
error = -EEXIST;
break;
case EPOLL_CTL_DEL:
if (epi) {
/*
* The eventpoll itself is still alive: the refcount
* can't go to zero here.
*/
ep_remove_safe(ep, epi);
error = 0;
} else {
error = -ENOENT;
}
break;
case EPOLL_CTL_MOD:
if (epi) {
if (!(epi->event.events & EPOLLEXCLUSIVE)) {
epds->events |= EPOLLERR | EPOLLHUP;
error = ep_modify(ep, epi, epds);
}
} else
error = -ENOENT;
break;
}
mutex_unlock(&ep->mtx);
error_tgt_fput:
if (full_check) {
clear_tfile_check_list();
loop_check_gen++;
mutex_unlock(&epnested_mutex);
}
return error;
}
/*
* The following function implements the controller interface for
* the eventpoll file that enables the insertion/removal/change of
* file descriptors inside the interest set.
*/
SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
struct epoll_event __user *, event)
{
struct epoll_event epds;
if (ep_op_has_event(op) &&
copy_from_user(&epds, event, sizeof(struct epoll_event)))
return -EFAULT;
return do_epoll_ctl(epfd, op, fd, &epds, false);
}
static int ep_check_params(struct file *file, struct epoll_event __user *evs,
int maxevents)
{
/* The maximum number of event must be greater than zero */
if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
return -EINVAL;
/* Verify that the area passed by the user is writeable */
if (!access_ok(evs, maxevents * sizeof(struct epoll_event)))
return -EFAULT;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
if (!is_file_epoll(file))
return -EINVAL;
return 0;
}
int epoll_sendevents(struct file *file, struct epoll_event __user *events,
int maxevents)
{
struct eventpoll *ep;
int ret;
ret = ep_check_params(file, events, maxevents);
if (unlikely(ret))
return ret;
ep = file->private_data;
/*
* Racy call, but that's ok - it should get retried based on
* poll readiness anyway.
*/
if (ep_events_available(ep))
return ep_try_send_events(ep, events, maxevents);
return 0;
}
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_wait(2).
*/
static int do_epoll_wait(int epfd, struct epoll_event __user *events,
int maxevents, struct timespec64 *to)
{
struct eventpoll *ep;
int ret;
/* Get the "struct file *" for the eventpoll file */
CLASS(fd, f)(epfd);
if (fd_empty(f))
return -EBADF;
ret = ep_check_params(fd_file(f), events, maxevents);
if (unlikely(ret))
return ret;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = fd_file(f)->private_data;
/* Time to fish for events ... */
return ep_poll(ep, events, maxevents, to);
}
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout)
{
struct timespec64 to;
return do_epoll_wait(epfd, events, maxevents,
ep_timeout_to_timespec(&to, timeout));
}
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_pwait(2).
*/
static int do_epoll_pwait(int epfd, struct epoll_event __user *events,
int maxevents, struct timespec64 *to,
const sigset_t __user *sigmask, size_t sigsetsize)
{
int error;
/*
* If the caller wants a certain signal mask to be set during the wait,
* we apply it here.
*/
error = set_user_sigmask(sigmask, sigsetsize);
if (error)
return error;
error = do_epoll_wait(epfd, events, maxevents, to);
restore_saved_sigmask_unless(error == -EINTR);
return error;
}
SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout, const sigset_t __user *, sigmask,
size_t, sigsetsize)
{
struct timespec64 to;
return do_epoll_pwait(epfd, events, maxevents,
ep_timeout_to_timespec(&to, timeout),
sigmask, sigsetsize);
}
SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events,
int, maxevents, const struct __kernel_timespec __user *, timeout,
const sigset_t __user *, sigmask, size_t, sigsetsize)
{
struct timespec64 ts, *to = NULL;
if (timeout) {
if (get_timespec64(&ts, timeout))
return -EFAULT;
to = &ts;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
return do_epoll_pwait(epfd, events, maxevents, to,
sigmask, sigsetsize);
}
#ifdef CONFIG_COMPAT
static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events,
int maxevents, struct timespec64 *timeout,
const compat_sigset_t __user *sigmask,
compat_size_t sigsetsize)
{
long err;
/*
* If the caller wants a certain signal mask to be set during the wait,
* we apply it here.
*/
err = set_compat_user_sigmask(sigmask, sigsetsize);
if (err)
return err;
err = do_epoll_wait(epfd, events, maxevents, timeout);
restore_saved_sigmask_unless(err == -EINTR);
return err;
}
COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
struct epoll_event __user *, events,
int, maxevents, int, timeout,
const compat_sigset_t __user *, sigmask,
compat_size_t, sigsetsize)
{
struct timespec64 to;
return do_compat_epoll_pwait(epfd, events, maxevents,
ep_timeout_to_timespec(&to, timeout),
sigmask, sigsetsize);
}
COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd,
struct epoll_event __user *, events,
int, maxevents,
const struct __kernel_timespec __user *, timeout,
const compat_sigset_t __user *, sigmask,
compat_size_t, sigsetsize)
{
struct timespec64 ts, *to = NULL;
if (timeout) {
if (get_timespec64(&ts, timeout))
return -EFAULT;
to = &ts;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
return do_compat_epoll_pwait(epfd, events, maxevents, to,
sigmask, sigsetsize);
}
#endif
static int __init eventpoll_init(void)
{
struct sysinfo si;
si_meminfo(&si);
/*
* Allows top 4% of lomem to be allocated for epoll watches (per user).
*/
max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
EP_ITEM_COST;
BUG_ON(max_user_watches < 0);
/*
* We can have many thousands of epitems, so prevent this from
* using an extra cache line on 64-bit (and smaller) CPUs
*/
BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
epoll_sysctls_init();
ephead_cache = kmem_cache_create("ep_head",
sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
return 0;
}
fs_initcall(eventpoll_init);
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
Red Black Trees
(C) 1999 Andrea Arcangeli <andrea@suse.de>
linux/include/linux/rbtree.h
To use rbtrees you'll have to implement your own insert and search cores.
This will avoid us to use callbacks and to drop drammatically performances.
I know it's not the cleaner way, but in C (not in C++) to get
performances and genericity...
See Documentation/core-api/rbtree.rst for documentation and samples.
*/
#ifndef _LINUX_RBTREE_H
#define _LINUX_RBTREE_H
#include <linux/container_of.h>
#include <linux/rbtree_types.h>
#include <linux/stddef.h>
#include <linux/rcupdate.h>
#define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3))
#define rb_entry(ptr, type, member) container_of(ptr, type, member)
#define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL)
/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
#define RB_EMPTY_NODE(node) \
((node)->__rb_parent_color == (unsigned long)(node))
#define RB_CLEAR_NODE(node) \
((node)->__rb_parent_color = (unsigned long)(node))
extern void rb_insert_color(struct rb_node *, struct rb_root *);
extern void rb_erase(struct rb_node *, struct rb_root *);
/* Find logical next and previous nodes in a tree */
extern struct rb_node *rb_next(const struct rb_node *);
extern struct rb_node *rb_prev(const struct rb_node *);
extern struct rb_node *rb_first(const struct rb_root *);
extern struct rb_node *rb_last(const struct rb_root *);
/* Postorder iteration - always visit the parent after its children */
extern struct rb_node *rb_first_postorder(const struct rb_root *);
extern struct rb_node *rb_next_postorder(const struct rb_node *);
/* Fast replacement of a single node without remove/rebalance/add/rebalance */
extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
struct rb_root *root);
extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new,
struct rb_root *root);
static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
struct rb_node **rb_link)
{
node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL;
*rb_link = node;
}
static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
struct rb_node **rb_link)
{
node->__rb_parent_color = (unsigned long)parent;
node->rb_left = node->rb_right = NULL;
rcu_assign_pointer(*rb_link, node);
}
#define rb_entry_safe(ptr, type, member) \
({ typeof(ptr) ____ptr = (ptr); \
____ptr ? rb_entry(____ptr, type, member) : NULL; \
})
/**
* rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of
* given type allowing the backing memory of @pos to be invalidated
*
* @pos: the 'type *' to use as a loop cursor.
* @n: another 'type *' to use as temporary storage
* @root: 'rb_root *' of the rbtree.
* @field: the name of the rb_node field within 'type'.
*
* rbtree_postorder_for_each_entry_safe() provides a similar guarantee as
* list_for_each_entry_safe() and allows the iteration to continue independent
* of changes to @pos by the body of the loop.
*
* Note, however, that it cannot handle other modifications that re-order the
* rbtree it is iterating over. This includes calling rb_erase() on @pos, as
* rb_erase() may rebalance the tree, causing us to miss some nodes.
*/
#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
typeof(*pos), field); 1; }); \
pos = n)
/* Same as rb_first(), but O(1) */
#define rb_first_cached(root) (root)->rb_leftmost
static inline void rb_insert_color_cached(struct rb_node *node,
struct rb_root_cached *root,
bool leftmost)
{
if (leftmost)
root->rb_leftmost = node;
rb_insert_color(node, &root->rb_root);
}
static inline struct rb_node *
rb_erase_cached(struct rb_node *node, struct rb_root_cached *root)
{
struct rb_node *leftmost = NULL;
if (root->rb_leftmost == node) leftmost = root->rb_leftmost = rb_next(node);
rb_erase(node, &root->rb_root);
return leftmost;
}
static inline void rb_replace_node_cached(struct rb_node *victim,
struct rb_node *new,
struct rb_root_cached *root)
{
if (root->rb_leftmost == victim)
root->rb_leftmost = new;
rb_replace_node(victim, new, &root->rb_root);
}
/*
* The below helper functions use 2 operators with 3 different
* calling conventions. The operators are related like:
*
* comp(a->key,b) < 0 := less(a,b)
* comp(a->key,b) > 0 := less(b,a)
* comp(a->key,b) == 0 := !less(a,b) && !less(b,a)
*
* If these operators define a partial order on the elements we make no
* guarantee on which of the elements matching the key is found. See
* rb_find().
*
* The reason for this is to allow the find() interface without requiring an
* on-stack dummy object, which might not be feasible due to object size.
*/
/**
* rb_add_cached() - insert @node into the leftmost cached tree @tree
* @node: node to insert
* @tree: leftmost cached tree to insert @node into
* @less: operator defining the (partial) node order
*
* Returns @node when it is the new leftmost, or NULL.
*/
static __always_inline struct rb_node *
rb_add_cached(struct rb_node *node, struct rb_root_cached *tree,
bool (*less)(struct rb_node *, const struct rb_node *))
{
struct rb_node **link = &tree->rb_root.rb_node;
struct rb_node *parent = NULL;
bool leftmost = true;
while (*link) {
parent = *link;
if (less(node, parent)) {
link = &parent->rb_left;
} else {
link = &parent->rb_right;
leftmost = false;
}
}
rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost);
return leftmost ? node : NULL;
}
/**
* rb_add() - insert @node into @tree
* @node: node to insert
* @tree: tree to insert @node into
* @less: operator defining the (partial) node order
*/
static __always_inline void
rb_add(struct rb_node *node, struct rb_root *tree,
bool (*less)(struct rb_node *, const struct rb_node *))
{
struct rb_node **link = &tree->rb_node;
struct rb_node *parent = NULL;
while (*link) {
parent = *link;
if (less(node, parent))
link = &parent->rb_left;
else
link = &parent->rb_right;
}
rb_link_node(node, parent, link);
rb_insert_color(node, tree);
}
/**
* rb_find_add_cached() - find equivalent @node in @tree, or add @node
* @node: node to look-for / insert
* @tree: tree to search / modify
* @cmp: operator defining the node order
*
* Returns the rb_node matching @node, or NULL when no match is found and @node
* is inserted.
*/
static __always_inline struct rb_node *
rb_find_add_cached(struct rb_node *node, struct rb_root_cached *tree,
int (*cmp)(const struct rb_node *new, const struct rb_node *exist))
{
bool leftmost = true;
struct rb_node **link = &tree->rb_root.rb_node;
struct rb_node *parent = NULL;
int c;
while (*link) {
parent = *link;
c = cmp(node, parent);
if (c < 0) {
link = &parent->rb_left;
} else if (c > 0) {
link = &parent->rb_right;
leftmost = false;
} else {
return parent;
}
}
rb_link_node(node, parent, link);
rb_insert_color_cached(node, tree, leftmost);
return NULL;
}
/**
* rb_find_add() - find equivalent @node in @tree, or add @node
* @node: node to look-for / insert
* @tree: tree to search / modify
* @cmp: operator defining the node order
*
* Returns the rb_node matching @node, or NULL when no match is found and @node
* is inserted.
*/
static __always_inline struct rb_node *
rb_find_add(struct rb_node *node, struct rb_root *tree,
int (*cmp)(struct rb_node *, const struct rb_node *))
{
struct rb_node **link = &tree->rb_node;
struct rb_node *parent = NULL;
int c;
while (*link) {
parent = *link;
c = cmp(node, parent);
if (c < 0)
link = &parent->rb_left;
else if (c > 0)
link = &parent->rb_right;
else
return parent;
}
rb_link_node(node, parent, link);
rb_insert_color(node, tree);
return NULL;
}
/**
* rb_find_add_rcu() - find equivalent @node in @tree, or add @node
* @node: node to look-for / insert
* @tree: tree to search / modify
* @cmp: operator defining the node order
*
* Adds a Store-Release for link_node.
*
* Returns the rb_node matching @node, or NULL when no match is found and @node
* is inserted.
*/
static __always_inline struct rb_node *
rb_find_add_rcu(struct rb_node *node, struct rb_root *tree,
int (*cmp)(struct rb_node *, const struct rb_node *))
{
struct rb_node **link = &tree->rb_node;
struct rb_node *parent = NULL;
int c;
while (*link) {
parent = *link;
c = cmp(node, parent);
if (c < 0)
link = &parent->rb_left;
else if (c > 0)
link = &parent->rb_right;
else
return parent;
}
rb_link_node_rcu(node, parent, link);
rb_insert_color(node, tree);
return NULL;
}
/**
* rb_find() - find @key in tree @tree
* @key: key to match
* @tree: tree to search
* @cmp: operator defining the node order
*
* Returns the rb_node matching @key or NULL.
*/
static __always_inline struct rb_node *
rb_find(const void *key, const struct rb_root *tree,
int (*cmp)(const void *key, const struct rb_node *))
{
struct rb_node *node = tree->rb_node;
while (node) {
int c = cmp(key, node);
if (c < 0)
node = node->rb_left;
else if (c > 0)
node = node->rb_right;
else
return node;
}
return NULL;
}
/**
* rb_find_rcu() - find @key in tree @tree
* @key: key to match
* @tree: tree to search
* @cmp: operator defining the node order
*
* Notably, tree descent vs concurrent tree rotations is unsound and can result
* in false-negatives.
*
* Returns the rb_node matching @key or NULL.
*/
static __always_inline struct rb_node *
rb_find_rcu(const void *key, const struct rb_root *tree,
int (*cmp)(const void *key, const struct rb_node *))
{
struct rb_node *node = tree->rb_node;
while (node) {
int c = cmp(key, node);
if (c < 0)
node = rcu_dereference_raw(node->rb_left);
else if (c > 0)
node = rcu_dereference_raw(node->rb_right);
else
return node;
}
return NULL;
}
/**
* rb_find_first() - find the first @key in @tree
* @key: key to match
* @tree: tree to search
* @cmp: operator defining node order
*
* Returns the leftmost node matching @key, or NULL.
*/
static __always_inline struct rb_node *
rb_find_first(const void *key, const struct rb_root *tree,
int (*cmp)(const void *key, const struct rb_node *))
{
struct rb_node *node = tree->rb_node;
struct rb_node *match = NULL;
while (node) { int c = cmp(key, node);
if (c <= 0) {
if (!c)
match = node;
node = node->rb_left;
} else if (c > 0) {
node = node->rb_right;
}
}
return match;
}
/**
* rb_next_match() - find the next @key in @tree
* @key: key to match
* @tree: tree to search
* @cmp: operator defining node order
*
* Returns the next node matching @key, or NULL.
*/
static __always_inline struct rb_node *
rb_next_match(const void *key, struct rb_node *node,
int (*cmp)(const void *key, const struct rb_node *))
{
node = rb_next(node);
if (node && cmp(key, node))
node = NULL;
return node;
}
/**
* rb_for_each() - iterates a subtree matching @key
* @node: iterator
* @key: key to match
* @tree: tree to search
* @cmp: operator defining node order
*/
#define rb_for_each(node, key, tree, cmp) \
for ((node) = rb_find_first((key), (tree), (cmp)); \
(node); (node) = rb_next_match((key), (node), (cmp)))
#endif /* _LINUX_RBTREE_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _MM_PERCPU_INTERNAL_H
#define _MM_PERCPU_INTERNAL_H
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/memcontrol.h>
/*
* pcpu_block_md is the metadata block struct.
* Each chunk's bitmap is split into a number of full blocks.
* All units are in terms of bits.
*
* The scan hint is the largest known contiguous area before the contig hint.
* It is not necessarily the actual largest contig hint though. There is an
* invariant that the scan_hint_start > contig_hint_start iff
* scan_hint == contig_hint. This is necessary because when scanning forward,
* we don't know if a new contig hint would be better than the current one.
*/
struct pcpu_block_md {
int scan_hint; /* scan hint for block */
int scan_hint_start; /* block relative starting
position of the scan hint */
int contig_hint; /* contig hint for block */
int contig_hint_start; /* block relative starting
position of the contig hint */
int left_free; /* size of free space along
the left side of the block */
int right_free; /* size of free space along
the right side of the block */
int first_free; /* block position of first free */
int nr_bits; /* total bits responsible for */
};
struct pcpuobj_ext {
#ifdef CONFIG_MEMCG
struct obj_cgroup *cgroup;
#endif
#ifdef CONFIG_MEM_ALLOC_PROFILING
union codetag_ref tag;
#endif
};
#if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING)
#define NEED_PCPUOBJ_EXT
#endif
struct pcpu_chunk {
#ifdef CONFIG_PERCPU_STATS
int nr_alloc; /* # of allocations */
size_t max_alloc_size; /* largest allocation size */
#endif
struct list_head list; /* linked to pcpu_slot lists */
int free_bytes; /* free bytes in the chunk */
struct pcpu_block_md chunk_md;
unsigned long *bound_map; /* boundary map */
/*
* base_addr is the base address of this chunk.
* To reduce false sharing, current layout is optimized to make sure
* base_addr locate in the different cacheline with free_bytes and
* chunk_md.
*/
void *base_addr ____cacheline_aligned_in_smp;
unsigned long *alloc_map; /* allocation map */
struct pcpu_block_md *md_blocks; /* metadata blocks */
void *data; /* chunk data */
bool immutable; /* no [de]population allowed */
bool isolated; /* isolated from active chunk
slots */
int start_offset; /* the overlap with the previous
region to have a page aligned
base_addr */
int end_offset; /* additional area required to
have the region end page
aligned */
#ifdef NEED_PCPUOBJ_EXT
struct pcpuobj_ext *obj_exts; /* vector of object cgroups */
#endif
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
int nr_empty_pop_pages; /* # of empty populated pages */
unsigned long populated[]; /* populated bitmap */
};
static inline bool need_pcpuobj_ext(void)
{
if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING))
return true;
if (!mem_cgroup_kmem_disabled())
return true;
return false;
}
extern spinlock_t pcpu_lock;
extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
extern int pcpu_sidelined_slot;
extern int pcpu_to_depopulate_slot;
extern int pcpu_nr_empty_pop_pages;
extern struct pcpu_chunk *pcpu_first_chunk;
extern struct pcpu_chunk *pcpu_reserved_chunk;
/**
* pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks
* @chunk: chunk of interest
*
* This conversion is from the number of physical pages that the chunk
* serves to the number of bitmap blocks used.
*/
static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk)
{
return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE;
}
/**
* pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap
* @pages: number of physical pages
*
* This conversion is from physical pages to the number of bits
* required in the bitmap.
*/
static inline int pcpu_nr_pages_to_map_bits(int pages)
{
return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
}
/**
* pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap
* @chunk: chunk of interest
*
* This conversion is from the number of physical pages that the chunk
* serves to the number of bits in the bitmap.
*/
static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
{
return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
}
/**
* pcpu_obj_full_size - helper to calculate size of each accounted object
* @size: size of area to allocate in bytes
*
* For each accounted object there is an extra space which is used to store
* obj_cgroup membership if kmemcg is not disabled. Charge it too.
*/
static inline size_t pcpu_obj_full_size(size_t size)
{
size_t extra_size = 0;
#ifdef CONFIG_MEMCG
if (!mem_cgroup_kmem_disabled())
extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *);
#endif
return size * num_possible_cpus() + extra_size;
}
#ifdef CONFIG_PERCPU_STATS
#include <linux/spinlock.h>
struct percpu_stats {
u64 nr_alloc; /* lifetime # of allocations */
u64 nr_dealloc; /* lifetime # of deallocations */
u64 nr_cur_alloc; /* current # of allocations */
u64 nr_max_alloc; /* max # of live allocations */
u32 nr_chunks; /* current # of live chunks */
u32 nr_max_chunks; /* max # of live chunks */
size_t min_alloc_size; /* min allocation size */
size_t max_alloc_size; /* max allocation size */
};
extern struct percpu_stats pcpu_stats;
extern struct pcpu_alloc_info pcpu_stats_ai;
/*
* For debug purposes. We don't care about the flexible array.
*/
static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai)
{
memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info));
/* initialize min_alloc_size to unit_size */
pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size;
}
/*
* pcpu_stats_area_alloc - increment area allocation stats
* @chunk: the location of the area being allocated
* @size: size of area to allocate in bytes
*
* CONTEXT:
* pcpu_lock.
*/
static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size)
{
lockdep_assert_held(&pcpu_lock);
pcpu_stats.nr_alloc++;
pcpu_stats.nr_cur_alloc++;
pcpu_stats.nr_max_alloc =
max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc);
pcpu_stats.min_alloc_size =
min(pcpu_stats.min_alloc_size, size);
pcpu_stats.max_alloc_size =
max(pcpu_stats.max_alloc_size, size);
chunk->nr_alloc++;
chunk->max_alloc_size = max(chunk->max_alloc_size, size);
}
/*
* pcpu_stats_area_dealloc - decrement allocation stats
* @chunk: the location of the area being deallocated
*
* CONTEXT:
* pcpu_lock.
*/
static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk)
{
lockdep_assert_held(&pcpu_lock);
pcpu_stats.nr_dealloc++;
pcpu_stats.nr_cur_alloc--;
chunk->nr_alloc--;
}
/*
* pcpu_stats_chunk_alloc - increment chunk stats
*/
static inline void pcpu_stats_chunk_alloc(void)
{
unsigned long flags;
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_stats.nr_chunks++;
pcpu_stats.nr_max_chunks =
max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks);
spin_unlock_irqrestore(&pcpu_lock, flags);
}
/*
* pcpu_stats_chunk_dealloc - decrement chunk stats
*/
static inline void pcpu_stats_chunk_dealloc(void)
{
unsigned long flags;
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_stats.nr_chunks--;
spin_unlock_irqrestore(&pcpu_lock, flags);
}
#else
static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai)
{
}
static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size)
{
}
static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk)
{
}
static inline void pcpu_stats_chunk_alloc(void)
{
}
static inline void pcpu_stats_chunk_dealloc(void)
{
}
#endif /* !CONFIG_PERCPU_STATS */
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Lock-less NULL terminated single linked list
*
* The basic atomic operation of this list is cmpxchg on long. On
* architectures that don't have NMI-safe cmpxchg implementation, the
* list can NOT be used in NMI handlers. So code that uses the list in
* an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
*
* Copyright 2010,2011 Intel Corp.
* Author: Huang Ying <ying.huang@intel.com>
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/llist.h>
/**
* llist_add_batch - add several linked entries in batch
* @new_first: first entry in batch to be added
* @new_last: last entry in batch to be added
* @head: the head for your lock-less list
*
* Return whether list is empty before adding.
*/
bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
struct llist_head *head)
{
struct llist_node *first = READ_ONCE(head->first);
do {
new_last->next = first;
} while (!try_cmpxchg(&head->first, &first, new_first)); return !first;
}
EXPORT_SYMBOL_GPL(llist_add_batch);
/**
* llist_del_first - delete the first entry of lock-less list
* @head: the head for your lock-less list
*
* If list is empty, return NULL, otherwise, return the first entry
* deleted, this is the newest added one.
*
* Only one llist_del_first user can be used simultaneously with
* multiple llist_add users without lock. Because otherwise
* llist_del_first, llist_add, llist_add (or llist_del_all, llist_add,
* llist_add) sequence in another user may change @head->first->next,
* but keep @head->first. If multiple consumers are needed, please
* use llist_del_all or use lock between consumers.
*/
struct llist_node *llist_del_first(struct llist_head *head)
{
struct llist_node *entry, *next;
entry = smp_load_acquire(&head->first);
do {
if (entry == NULL)
return NULL;
next = READ_ONCE(entry->next);
} while (!try_cmpxchg(&head->first, &entry, next)); return entry;
}
EXPORT_SYMBOL_GPL(llist_del_first);
/**
* llist_del_first_this - delete given entry of lock-less list if it is first
* @head: the head for your lock-less list
* @this: a list entry.
*
* If head of the list is given entry, delete and return %true else
* return %false.
*
* Multiple callers can safely call this concurrently with multiple
* llist_add() callers, providing all the callers offer a different @this.
*/
bool llist_del_first_this(struct llist_head *head,
struct llist_node *this)
{
struct llist_node *entry, *next;
/* acquire ensures orderig wrt try_cmpxchg() is llist_del_first() */
entry = smp_load_acquire(&head->first);
do {
if (entry != this)
return false;
next = READ_ONCE(entry->next);
} while (!try_cmpxchg(&head->first, &entry, next));
return true;
}
EXPORT_SYMBOL_GPL(llist_del_first_this);
/**
* llist_reverse_order - reverse order of a llist chain
* @head: first item of the list to be reversed
*
* Reverse the order of a chain of llist entries and return the
* new first entry.
*/
struct llist_node *llist_reverse_order(struct llist_node *head)
{
struct llist_node *new_head = NULL;
while (head) {
struct llist_node *tmp = head;
head = head->next;
tmp->next = new_head;
new_head = tmp;
}
return new_head;
}
EXPORT_SYMBOL_GPL(llist_reverse_order);
// SPDX-License-Identifier: GPL-2.0
/*
* Lockless hierarchical page accounting & limiting
*
* Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
*/
#include <linux/page_counter.h>
#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/bug.h>
#include <asm/page.h>
static bool track_protection(struct page_counter *c)
{
return c->protection_support;
}
static void propagate_protected_usage(struct page_counter *c,
unsigned long usage)
{
unsigned long protected, old_protected;
long delta;
if (!c->parent)
return;
protected = min(usage, READ_ONCE(c->min));
old_protected = atomic_long_read(&c->min_usage);
if (protected != old_protected) {
old_protected = atomic_long_xchg(&c->min_usage, protected);
delta = protected - old_protected;
if (delta) atomic_long_add(delta, &c->parent->children_min_usage);
}
protected = min(usage, READ_ONCE(c->low));
old_protected = atomic_long_read(&c->low_usage);
if (protected != old_protected) {
old_protected = atomic_long_xchg(&c->low_usage, protected);
delta = protected - old_protected;
if (delta) atomic_long_add(delta, &c->parent->children_low_usage);
}
}
/**
* page_counter_cancel - take pages out of the local counter
* @counter: counter
* @nr_pages: number of pages to cancel
*/
void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
{
long new;
new = atomic_long_sub_return(nr_pages, &counter->usage);
/* More uncharges than charges? */
if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n",
new, nr_pages)) {
new = 0;
atomic_long_set(&counter->usage, new);
}
if (track_protection(counter)) propagate_protected_usage(counter, new);
}
/**
* page_counter_charge - hierarchically charge pages
* @counter: counter
* @nr_pages: number of pages to charge
*
* NOTE: This does not consider any configured counter limits.
*/
void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
bool protection = track_protection(counter);
for (c = counter; c; c = c->parent) {
long new;
new = atomic_long_add_return(nr_pages, &c->usage); if (protection) propagate_protected_usage(c, new);
/*
* This is indeed racy, but we can live with some
* inaccuracy in the watermark.
*
* Notably, we have two watermarks to allow for both a globally
* visible peak and one that can be reset at a smaller scope.
*
* Since we reset both watermarks when the global reset occurs,
* we can guarantee that watermark >= local_watermark, so we
* don't need to do both comparisons every time.
*
* On systems with branch predictors, the inner condition should
* be almost free.
*/
if (new > READ_ONCE(c->local_watermark)) {
WRITE_ONCE(c->local_watermark, new);
if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new);
}
}
}
/**
* page_counter_try_charge - try to hierarchically charge pages
* @counter: counter
* @nr_pages: number of pages to charge
* @fail: points first counter to hit its limit, if any
*
* Returns %true on success, or %false and @fail if the counter or one
* of its ancestors has hit its configured limit.
*/
bool page_counter_try_charge(struct page_counter *counter,
unsigned long nr_pages,
struct page_counter **fail)
{
struct page_counter *c;
bool protection = track_protection(counter);
bool track_failcnt = counter->track_failcnt;
for (c = counter; c; c = c->parent) {
long new;
/*
* Charge speculatively to avoid an expensive CAS. If
* a bigger charge fails, it might falsely lock out a
* racing smaller charge and send it into reclaim
* early, but the error is limited to the difference
* between the two sizes, which is less than 2M/4M in
* case of a THP locking out a regular page charge.
*
* The atomic_long_add_return() implies a full memory
* barrier between incrementing the count and reading
* the limit. When racing with page_counter_set_max(),
* we either see the new limit or the setter sees the
* counter has changed and retries.
*/
new = atomic_long_add_return(nr_pages, &c->usage);
if (new > c->max) {
atomic_long_sub(nr_pages, &c->usage);
/*
* This is racy, but we can live with some
* inaccuracy in the failcnt which is only used
* to report stats.
*/
if (track_failcnt) data_race(c->failcnt++);
*fail = c;
goto failed;
}
if (protection) propagate_protected_usage(c, new);
/* see comment on page_counter_charge */
if (new > READ_ONCE(c->local_watermark)) {
WRITE_ONCE(c->local_watermark, new);
if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new);
}
}
return true;
failed:
for (c = counter; c != *fail; c = c->parent)
page_counter_cancel(c, nr_pages);
return false;
}
/**
* page_counter_uncharge - hierarchically uncharge pages
* @counter: counter
* @nr_pages: number of pages to uncharge
*/
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
for (c = counter; c; c = c->parent)
page_counter_cancel(c, nr_pages);
}
/**
* page_counter_set_max - set the maximum number of pages allowed
* @counter: counter
* @nr_pages: limit to set
*
* Returns 0 on success, -EBUSY if the current number of pages on the
* counter already exceeds the specified limit.
*
* The caller must serialize invocations on the same counter.
*/
int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages)
{
for (;;) {
unsigned long old;
long usage;
/*
* Update the limit while making sure that it's not
* below the concurrently-changing counter value.
*
* The xchg implies two full memory barriers before
* and after, so the read-swap-read is ordered and
* ensures coherency with page_counter_try_charge():
* that function modifies the count before checking
* the limit, so if it sees the old limit, we see the
* modified counter and retry.
*/
usage = page_counter_read(counter);
if (usage > nr_pages)
return -EBUSY;
old = xchg(&counter->max, nr_pages);
if (page_counter_read(counter) <= usage || nr_pages >= old)
return 0;
counter->max = old;
cond_resched();
}
}
/**
* page_counter_set_min - set the amount of protected memory
* @counter: counter
* @nr_pages: value to set
*
* The caller must serialize invocations on the same counter.
*/
void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
WRITE_ONCE(counter->min, nr_pages);
for (c = counter; c; c = c->parent)
propagate_protected_usage(c, atomic_long_read(&c->usage));
}
/**
* page_counter_set_low - set the amount of protected memory
* @counter: counter
* @nr_pages: value to set
*
* The caller must serialize invocations on the same counter.
*/
void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
WRITE_ONCE(counter->low, nr_pages);
for (c = counter; c; c = c->parent)
propagate_protected_usage(c, atomic_long_read(&c->usage));
}
/**
* page_counter_memparse - memparse() for page counter limits
* @buf: string to parse
* @max: string meaning maximum possible value
* @nr_pages: returns the result in number of pages
*
* Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be
* limited to %PAGE_COUNTER_MAX.
*/
int page_counter_memparse(const char *buf, const char *max,
unsigned long *nr_pages)
{
char *end;
u64 bytes;
if (!strcmp(buf, max)) {
*nr_pages = PAGE_COUNTER_MAX;
return 0;
}
bytes = memparse(buf, &end);
if (*end != '\0')
return -EINVAL;
*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);
return 0;
}
#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM)
/*
* This function calculates an individual page counter's effective
* protection which is derived from its own memory.min/low, its
* parent's and siblings' settings, as well as the actual memory
* distribution in the tree.
*
* The following rules apply to the effective protection values:
*
* 1. At the first level of reclaim, effective protection is equal to
* the declared protection in memory.min and memory.low.
*
* 2. To enable safe delegation of the protection configuration, at
* subsequent levels the effective protection is capped to the
* parent's effective protection.
*
* 3. To make complex and dynamic subtrees easier to configure, the
* user is allowed to overcommit the declared protection at a given
* level. If that is the case, the parent's effective protection is
* distributed to the children in proportion to how much protection
* they have declared and how much of it they are utilizing.
*
* This makes distribution proportional, but also work-conserving:
* if one counter claims much more protection than it uses memory,
* the unused remainder is available to its siblings.
*
* 4. Conversely, when the declared protection is undercommitted at a
* given level, the distribution of the larger parental protection
* budget is NOT proportional. A counter's protection from a sibling
* is capped to its own memory.min/low setting.
*
* 5. However, to allow protecting recursive subtrees from each other
* without having to declare each individual counter's fixed share
* of the ancestor's claim to protection, any unutilized -
* "floating" - protection from up the tree is distributed in
* proportion to each counter's *usage*. This makes the protection
* neutral wrt sibling cgroups and lets them compete freely over
* the shared parental protection budget, but it protects the
* subtree as a whole from neighboring subtrees.
*
* Note that 4. and 5. are not in conflict: 4. is about protecting
* against immediate siblings whereas 5. is about protecting against
* neighboring subtrees.
*/
static unsigned long effective_protection(unsigned long usage,
unsigned long parent_usage,
unsigned long setting,
unsigned long parent_effective,
unsigned long siblings_protected,
bool recursive_protection)
{
unsigned long protected;
unsigned long ep;
protected = min(usage, setting);
/*
* If all cgroups at this level combined claim and use more
* protection than what the parent affords them, distribute
* shares in proportion to utilization.
*
* We are using actual utilization rather than the statically
* claimed protection in order to be work-conserving: claimed
* but unused protection is available to siblings that would
* otherwise get a smaller chunk than what they claimed.
*/
if (siblings_protected > parent_effective)
return protected * parent_effective / siblings_protected;
/*
* Ok, utilized protection of all children is within what the
* parent affords them, so we know whatever this child claims
* and utilizes is effectively protected.
*
* If there is unprotected usage beyond this value, reclaim
* will apply pressure in proportion to that amount.
*
* If there is unutilized protection, the cgroup will be fully
* shielded from reclaim, but we do return a smaller value for
* protection than what the group could enjoy in theory. This
* is okay. With the overcommit distribution above, effective
* protection is always dependent on how memory is actually
* consumed among the siblings anyway.
*/
ep = protected;
/*
* If the children aren't claiming (all of) the protection
* afforded to them by the parent, distribute the remainder in
* proportion to the (unprotected) memory of each cgroup. That
* way, cgroups that aren't explicitly prioritized wrt each
* other compete freely over the allowance, but they are
* collectively protected from neighboring trees.
*
* We're using unprotected memory for the weight so that if
* some cgroups DO claim explicit protection, we don't protect
* the same bytes twice.
*
* Check both usage and parent_usage against the respective
* protected values. One should imply the other, but they
* aren't read atomically - make sure the division is sane.
*/
if (!recursive_protection)
return ep;
if (parent_effective > siblings_protected &&
parent_usage > siblings_protected &&
usage > protected) {
unsigned long unclaimed;
unclaimed = parent_effective - siblings_protected;
unclaimed *= usage - protected;
unclaimed /= parent_usage - siblings_protected;
ep += unclaimed;
}
return ep;
}
/**
* page_counter_calculate_protection - check if memory consumption is in the normal range
* @root: the top ancestor of the sub-tree being checked
* @counter: the page_counter the counter to update
* @recursive_protection: Whether to use memory_recursiveprot behavior.
*
* Calculates elow/emin thresholds for given page_counter.
*
* WARNING: This function is not stateless! It can only be used as part
* of a top-down tree iteration, not for isolated queries.
*/
void page_counter_calculate_protection(struct page_counter *root,
struct page_counter *counter,
bool recursive_protection)
{
unsigned long usage, parent_usage;
struct page_counter *parent = counter->parent;
/*
* Effective values of the reclaim targets are ignored so they
* can be stale. Have a look at mem_cgroup_protection for more
* details.
* TODO: calculation should be more robust so that we do not need
* that special casing.
*/
if (root == counter)
return;
usage = page_counter_read(counter);
if (!usage)
return;
if (parent == root) {
counter->emin = READ_ONCE(counter->min);
counter->elow = READ_ONCE(counter->low);
return;
}
parent_usage = page_counter_read(parent);
WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage,
READ_ONCE(counter->min),
READ_ONCE(parent->emin),
atomic_long_read(&parent->children_min_usage),
recursive_protection));
WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage,
READ_ONCE(counter->low),
READ_ONCE(parent->elow),
atomic_long_read(&parent->children_low_usage),
recursive_protection));
}
#endif /* CONFIG_MEMCG || CONFIG_CGROUP_DMEM */
// SPDX-License-Identifier: GPL-2.0
// Generated by scripts/atomic/gen-atomic-long.sh
// DO NOT MODIFY THIS FILE DIRECTLY
#ifndef _LINUX_ATOMIC_LONG_H
#define _LINUX_ATOMIC_LONG_H
#include <linux/compiler.h>
#include <asm/types.h>
#ifdef CONFIG_64BIT
typedef atomic64_t atomic_long_t;
#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i)
#define atomic_long_cond_read_acquire atomic64_cond_read_acquire
#define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed
#else
typedef atomic_t atomic_long_t;
#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i)
#define atomic_long_cond_read_acquire atomic_cond_read_acquire
#define atomic_long_cond_read_relaxed atomic_cond_read_relaxed
#endif
/**
* raw_atomic_long_read() - atomic load with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically loads the value of @v with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_read() elsewhere.
*
* Return: The value loaded from @v.
*/
static __always_inline long
raw_atomic_long_read(const atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_read(v);
#else
return raw_atomic_read(v);
#endif
}
/**
* raw_atomic_long_read_acquire() - atomic load with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically loads the value of @v with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_read_acquire() elsewhere.
*
* Return: The value loaded from @v.
*/
static __always_inline long
raw_atomic_long_read_acquire(const atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_read_acquire(v);
#else
return raw_atomic_read_acquire(v);
#endif
}
/**
* raw_atomic_long_set() - atomic set with relaxed ordering
* @v: pointer to atomic_long_t
* @i: long value to assign
*
* Atomically sets @v to @i with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_set() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_set(atomic_long_t *v, long i)
{
#ifdef CONFIG_64BIT
raw_atomic64_set(v, i);
#else
raw_atomic_set(v, i);
#endif
}
/**
* raw_atomic_long_set_release() - atomic set with release ordering
* @v: pointer to atomic_long_t
* @i: long value to assign
*
* Atomically sets @v to @i with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_set_release() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_set_release(atomic_long_t *v, long i)
{
#ifdef CONFIG_64BIT
raw_atomic64_set_release(v, i);
#else
raw_atomic_set_release(v, i);
#endif
}
/**
* raw_atomic_long_add() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_add(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_add(i, v);
#else
raw_atomic_add(i, v);
#endif
}
/**
* raw_atomic_long_add_return() - atomic add with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_return() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_add_return(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_return(i, v);
#else
return raw_atomic_add_return(i, v);
#endif
}
/**
* raw_atomic_long_add_return_acquire() - atomic add with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_return_acquire() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_add_return_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_return_acquire(i, v);
#else
return raw_atomic_add_return_acquire(i, v);
#endif
}
/**
* raw_atomic_long_add_return_release() - atomic add with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_return_release() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_add_return_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_return_release(i, v);
#else
return raw_atomic_add_return_release(i, v);
#endif
}
/**
* raw_atomic_long_add_return_relaxed() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_return_relaxed() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_return_relaxed(i, v);
#else
return raw_atomic_add_return_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_fetch_add() - atomic add with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_add() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_add(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_add(i, v);
#else
return raw_atomic_fetch_add(i, v);
#endif
}
/**
* raw_atomic_long_fetch_add_acquire() - atomic add with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_add_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_add_acquire(i, v);
#else
return raw_atomic_fetch_add_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_add_release() - atomic add with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_add_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_add_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_add_release(i, v);
#else
return raw_atomic_fetch_add_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_add_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_add_relaxed(i, v);
#else
return raw_atomic_fetch_add_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_sub() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_sub(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_sub(i, v);
#else
raw_atomic_sub(i, v);
#endif
}
/**
* raw_atomic_long_sub_return() - atomic subtract with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub_return() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_sub_return(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_sub_return(i, v);
#else
return raw_atomic_sub_return(i, v);
#endif
}
/**
* raw_atomic_long_sub_return_acquire() - atomic subtract with acquire ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub_return_acquire() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_sub_return_acquire(i, v);
#else
return raw_atomic_sub_return_acquire(i, v);
#endif
}
/**
* raw_atomic_long_sub_return_release() - atomic subtract with release ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub_return_release() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_sub_return_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_sub_return_release(i, v);
#else
return raw_atomic_sub_return_release(i, v);
#endif
}
/**
* raw_atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub_return_relaxed() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_sub_return_relaxed(i, v);
#else
return raw_atomic_sub_return_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_fetch_sub() - atomic subtract with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_sub() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_sub(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_sub(i, v);
#else
return raw_atomic_fetch_sub(i, v);
#endif
}
/**
* raw_atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_sub_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_sub_acquire(i, v);
#else
return raw_atomic_fetch_sub_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_sub_release() - atomic subtract with release ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_sub_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_sub_release(i, v);
#else
return raw_atomic_fetch_sub_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_sub_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_sub_relaxed(i, v);
#else
return raw_atomic_fetch_sub_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_inc() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_inc(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_inc(v);
#else
raw_atomic_inc(v);
#endif
}
/**
* raw_atomic_long_inc_return() - atomic increment with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc_return() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_inc_return(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_return(v);
#else
return raw_atomic_inc_return(v);
#endif
}
/**
* raw_atomic_long_inc_return_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc_return_acquire() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_inc_return_acquire(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_return_acquire(v);
#else
return raw_atomic_inc_return_acquire(v);
#endif
}
/**
* raw_atomic_long_inc_return_release() - atomic increment with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc_return_release() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_inc_return_release(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_return_release(v);
#else
return raw_atomic_inc_return_release(v);
#endif
}
/**
* raw_atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc_return_relaxed() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_inc_return_relaxed(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_return_relaxed(v);
#else
return raw_atomic_inc_return_relaxed(v);
#endif
}
/**
* raw_atomic_long_fetch_inc() - atomic increment with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_inc() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_inc(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_inc(v);
#else
return raw_atomic_fetch_inc(v);
#endif
}
/**
* raw_atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_inc_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_inc_acquire(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_inc_acquire(v);
#else
return raw_atomic_fetch_inc_acquire(v);
#endif
}
/**
* raw_atomic_long_fetch_inc_release() - atomic increment with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_inc_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_inc_release(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_inc_release(v);
#else
return raw_atomic_fetch_inc_release(v);
#endif
}
/**
* raw_atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_inc_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_inc_relaxed(v);
#else
return raw_atomic_fetch_inc_relaxed(v);
#endif
}
/**
* raw_atomic_long_dec() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_dec(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_dec(v);
#else
raw_atomic_dec(v);
#endif
}
/**
* raw_atomic_long_dec_return() - atomic decrement with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec_return() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_dec_return(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_return(v);
#else
return raw_atomic_dec_return(v);
#endif
}
/**
* raw_atomic_long_dec_return_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec_return_acquire() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_dec_return_acquire(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_return_acquire(v);
#else
return raw_atomic_dec_return_acquire(v);
#endif
}
/**
* raw_atomic_long_dec_return_release() - atomic decrement with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec_return_release() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_dec_return_release(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_return_release(v);
#else
return raw_atomic_dec_return_release(v);
#endif
}
/**
* raw_atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec_return_relaxed() elsewhere.
*
* Return: The updated value of @v.
*/
static __always_inline long
raw_atomic_long_dec_return_relaxed(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_return_relaxed(v);
#else
return raw_atomic_dec_return_relaxed(v);
#endif
}
/**
* raw_atomic_long_fetch_dec() - atomic decrement with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_dec() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_dec(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_dec(v);
#else
return raw_atomic_fetch_dec(v);
#endif
}
/**
* raw_atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_dec_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_dec_acquire(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_dec_acquire(v);
#else
return raw_atomic_fetch_dec_acquire(v);
#endif
}
/**
* raw_atomic_long_fetch_dec_release() - atomic decrement with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_dec_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_dec_release(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_dec_release(v);
#else
return raw_atomic_fetch_dec_release(v);
#endif
}
/**
* raw_atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_dec_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_dec_relaxed(v);
#else
return raw_atomic_fetch_dec_relaxed(v);
#endif
}
/**
* raw_atomic_long_and() - atomic bitwise AND with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_and() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_and(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_and(i, v);
#else
raw_atomic_and(i, v);
#endif
}
/**
* raw_atomic_long_fetch_and() - atomic bitwise AND with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_and() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_and(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_and(i, v);
#else
return raw_atomic_fetch_and(i, v);
#endif
}
/**
* raw_atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_and_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_and_acquire(i, v);
#else
return raw_atomic_fetch_and_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_and_release() - atomic bitwise AND with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_and_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_and_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_and_release(i, v);
#else
return raw_atomic_fetch_and_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_and_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_and_relaxed(i, v);
#else
return raw_atomic_fetch_and_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_andnot() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_andnot(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_andnot(i, v);
#else
raw_atomic_andnot(i, v);
#endif
}
/**
* raw_atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_andnot() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_andnot(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_andnot(i, v);
#else
return raw_atomic_fetch_andnot(i, v);
#endif
}
/**
* raw_atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_andnot_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_andnot_acquire(i, v);
#else
return raw_atomic_fetch_andnot_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_andnot_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_andnot_release(i, v);
#else
return raw_atomic_fetch_andnot_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_andnot_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_andnot_relaxed(i, v);
#else
return raw_atomic_fetch_andnot_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_or() - atomic bitwise OR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_or() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_or(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_or(i, v);
#else
raw_atomic_or(i, v);
#endif
}
/**
* raw_atomic_long_fetch_or() - atomic bitwise OR with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_or() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_or(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_or(i, v);
#else
return raw_atomic_fetch_or(i, v);
#endif
}
/**
* raw_atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_or_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_or_acquire(i, v);
#else
return raw_atomic_fetch_or_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_or_release() - atomic bitwise OR with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_or_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_or_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_or_release(i, v);
#else
return raw_atomic_fetch_or_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_or_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_or_relaxed(i, v);
#else
return raw_atomic_fetch_or_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_xor() - atomic bitwise XOR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_xor() elsewhere.
*
* Return: Nothing.
*/
static __always_inline void
raw_atomic_long_xor(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
raw_atomic64_xor(i, v);
#else
raw_atomic_xor(i, v);
#endif
}
/**
* raw_atomic_long_fetch_xor() - atomic bitwise XOR with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_xor() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_xor(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_xor(i, v);
#else
return raw_atomic_fetch_xor(i, v);
#endif
}
/**
* raw_atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_xor_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_xor_acquire(i, v);
#else
return raw_atomic_fetch_xor_acquire(i, v);
#endif
}
/**
* raw_atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_xor_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_xor_release(i, v);
#else
return raw_atomic_fetch_xor_release(i, v);
#endif
}
/**
* raw_atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_xor_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_xor_relaxed(i, v);
#else
return raw_atomic_fetch_xor_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_xchg() - atomic exchange with full ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_xchg() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_xchg(atomic_long_t *v, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_xchg(v, new);
#else
return raw_atomic_xchg(v, new);
#endif
}
/**
* raw_atomic_long_xchg_acquire() - atomic exchange with acquire ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_xchg_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_xchg_acquire(atomic_long_t *v, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_xchg_acquire(v, new);
#else
return raw_atomic_xchg_acquire(v, new);
#endif
}
/**
* raw_atomic_long_xchg_release() - atomic exchange with release ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_xchg_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_xchg_release(atomic_long_t *v, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_xchg_release(v, new);
#else
return raw_atomic_xchg_release(v, new);
#endif
}
/**
* raw_atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_xchg_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_xchg_relaxed(v, new);
#else
return raw_atomic_xchg_relaxed(v, new);
#endif
}
/**
* raw_atomic_long_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_cmpxchg(v, old, new);
#else
return raw_atomic_cmpxchg(v, old, new);
#endif
}
/**
* raw_atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_cmpxchg_acquire(v, old, new);
#else
return raw_atomic_cmpxchg_acquire(v, old, new);
#endif
}
/**
* raw_atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_cmpxchg_release(v, old, new);
#else
return raw_atomic_cmpxchg_release(v, old, new);
#endif
}
/**
* raw_atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_cmpxchg_relaxed(v, old, new);
#else
return raw_atomic_cmpxchg_relaxed(v, old, new);
#endif
}
/**
* raw_atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_try_cmpxchg(v, (s64 *)old, new);
#else
return raw_atomic_try_cmpxchg(v, (int *)old, new);
#endif
}
/**
* raw_atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
#else
return raw_atomic_try_cmpxchg_acquire(v, (int *)old, new);
#endif
}
/**
* raw_atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_try_cmpxchg_release(v, (s64 *)old, new);
#else
return raw_atomic_try_cmpxchg_release(v, (int *)old, new);
#endif
}
/**
* raw_atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
{
#ifdef CONFIG_64BIT
return raw_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
#else
return raw_atomic_try_cmpxchg_relaxed(v, (int *)old, new);
#endif
}
/**
* raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_sub_and_test() elsewhere.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_sub_and_test(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_sub_and_test(i, v);
#else
return raw_atomic_sub_and_test(i, v);
#endif
}
/**
* raw_atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_dec_and_test() elsewhere.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_dec_and_test(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_and_test(v);
#else
return raw_atomic_dec_and_test(v);
#endif
}
/**
* raw_atomic_long_inc_and_test() - atomic increment and test if zero with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_inc_and_test() elsewhere.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_inc_and_test(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_and_test(v);
#else
return raw_atomic_inc_and_test(v);
#endif
}
/**
* raw_atomic_long_add_negative() - atomic add and test if negative with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_negative() elsewhere.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_add_negative(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_negative(i, v);
#else
return raw_atomic_add_negative(i, v);
#endif
}
/**
* raw_atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_negative_acquire() elsewhere.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_negative_acquire(i, v);
#else
return raw_atomic_add_negative_acquire(i, v);
#endif
}
/**
* raw_atomic_long_add_negative_release() - atomic add and test if negative with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_negative_release() elsewhere.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_add_negative_release(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_negative_release(i, v);
#else
return raw_atomic_add_negative_release(i, v);
#endif
}
/**
* raw_atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Safe to use in noinstr code; prefer atomic_long_add_negative_relaxed() elsewhere.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_negative_relaxed(i, v);
#else
return raw_atomic_add_negative_relaxed(i, v);
#endif
}
/**
* raw_atomic_long_fetch_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_long_t
* @a: long value to add
* @u: long value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere.
*
* Return: The original value of @v.
*/
static __always_inline long
raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
{
#ifdef CONFIG_64BIT
return raw_atomic64_fetch_add_unless(v, a, u);
#else
return raw_atomic_fetch_add_unless(v, a, u);
#endif
}
/**
* raw_atomic_long_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_long_t
* @a: long value to add
* @u: long value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_add_unless(atomic_long_t *v, long a, long u)
{
#ifdef CONFIG_64BIT
return raw_atomic64_add_unless(v, a, u);
#else
return raw_atomic_add_unless(v, a, u);
#endif
}
/**
* raw_atomic_long_inc_not_zero() - atomic increment unless zero with full ordering
* @v: pointer to atomic_long_t
*
* If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_inc_not_zero(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_not_zero(v);
#else
return raw_atomic_inc_not_zero(v);
#endif
}
/**
* raw_atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering
* @v: pointer to atomic_long_t
*
* If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_inc_unless_negative(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_inc_unless_negative(v);
#else
return raw_atomic_inc_unless_negative(v);
#endif
}
/**
* raw_atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering
* @v: pointer to atomic_long_t
*
* If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
raw_atomic_long_dec_unless_positive(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_unless_positive(v);
#else
return raw_atomic_dec_unless_positive(v);
#endif
}
/**
* raw_atomic_long_dec_if_positive() - atomic decrement if positive with full ordering
* @v: pointer to atomic_long_t
*
* If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere.
*
* Return: The old value of (@v - 1), regardless of whether @v was updated.
*/
static __always_inline long
raw_atomic_long_dec_if_positive(atomic_long_t *v)
{
#ifdef CONFIG_64BIT
return raw_atomic64_dec_if_positive(v);
#else
return raw_atomic_dec_if_positive(v);
#endif
}
#endif /* _LINUX_ATOMIC_LONG_H */
// eadf183c3600b8b92b91839dd3be6bcc560c752d
// SPDX-License-Identifier: GPL-2.0
/*
* Generic sched_clock() support, to extend low level hardware time
* counters to full 64-bit ns values.
*/
#include <linux/clocksource.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/ktime.h>
#include <linux/kernel.h>
#include <linux/math.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/syscore_ops.h>
#include <linux/hrtimer.h>
#include <linux/sched_clock.h>
#include <linux/seqlock.h>
#include <linux/bitops.h>
#include "timekeeping.h"
/**
* struct clock_data - all data needed for sched_clock() (including
* registration of a new clock source)
*
* @seq: Sequence counter for protecting updates. The lowest
* bit is the index for @read_data.
* @read_data: Data required to read from sched_clock.
* @wrap_kt: Duration for which clock can run before wrapping.
* @rate: Tick rate of the registered clock.
* @actual_read_sched_clock: Registered hardware level clock read function.
*
* The ordering of this structure has been chosen to optimize cache
* performance. In particular 'seq' and 'read_data[0]' (combined) should fit
* into a single 64-byte cache line.
*/
struct clock_data {
seqcount_latch_t seq;
struct clock_read_data read_data[2];
ktime_t wrap_kt;
unsigned long rate;
u64 (*actual_read_sched_clock)(void);
};
static struct hrtimer sched_clock_timer;
static int irqtime = -1;
core_param(irqtime, irqtime, int, 0400);
static u64 notrace jiffy_sched_clock_read(void)
{
/*
* We don't need to use get_jiffies_64 on 32-bit arches here
* because we register with BITS_PER_LONG
*/
return (u64)(jiffies - INITIAL_JIFFIES);
}
static struct clock_data cd ____cacheline_aligned = {
.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
.read_sched_clock = jiffy_sched_clock_read, },
.actual_read_sched_clock = jiffy_sched_clock_read,
};
static __always_inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
{
return (cyc * mult) >> shift;
}
notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
{
*seq = read_seqcount_latch(&cd.seq);
return cd.read_data + (*seq & 1);
}
notrace int sched_clock_read_retry(unsigned int seq)
{
return read_seqcount_latch_retry(&cd.seq, seq);
}
static __always_inline unsigned long long __sched_clock(void)
{
struct clock_read_data *rd;
unsigned int seq;
u64 cyc, res;
do {
seq = raw_read_seqcount_latch(&cd.seq);
rd = cd.read_data + (seq & 1);
cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
rd->sched_clock_mask;
res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
} while (raw_read_seqcount_latch_retry(&cd.seq, seq));
return res;
}
unsigned long long noinstr sched_clock_noinstr(void)
{
return __sched_clock();
}
unsigned long long notrace sched_clock(void)
{
unsigned long long ns;
preempt_disable_notrace();
/*
* All of __sched_clock() is a seqcount_latch reader critical section,
* but relies on the raw helpers which are uninstrumented. For KCSAN,
* mark all accesses in __sched_clock() as atomic.
*/
kcsan_nestable_atomic_begin();
ns = __sched_clock();
kcsan_nestable_atomic_end();
preempt_enable_notrace();
return ns;
}
/*
* Updating the data required to read the clock.
*
* sched_clock() will never observe mis-matched data even if called from
* an NMI. We do this by maintaining an odd/even copy of the data and
* steering sched_clock() to one or the other using a sequence counter.
* In order to preserve the data cache profile of sched_clock() as much
* as possible the system reverts back to the even copy when the update
* completes; the odd copy is used *only* during an update.
*/
static void update_clock_read_data(struct clock_read_data *rd)
{
/* steer readers towards the odd copy */
write_seqcount_latch_begin(&cd.seq);
/* now its safe for us to update the normal (even) copy */
cd.read_data[0] = *rd;
/* switch readers back to the even copy */
write_seqcount_latch(&cd.seq);
/* update the backup (odd) copy with the new data */
cd.read_data[1] = *rd;
write_seqcount_latch_end(&cd.seq);
}
/*
* Atomically update the sched_clock() epoch.
*/
static void update_sched_clock(void)
{
u64 cyc;
u64 ns;
struct clock_read_data rd;
rd = cd.read_data[0];
cyc = cd.actual_read_sched_clock();
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
rd.epoch_ns = ns;
rd.epoch_cyc = cyc;
update_clock_read_data(&rd);
}
static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
{
update_sched_clock();
hrtimer_forward_now(hrt, cd.wrap_kt);
return HRTIMER_RESTART;
}
void __init
sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
{
u64 res, wrap, new_mask, new_epoch, cyc, ns;
u32 new_mult, new_shift;
unsigned long r, flags;
char r_unit;
struct clock_read_data rd;
if (cd.rate > rate)
return;
/* Cannot register a sched_clock with interrupts on */
local_irq_save(flags);
/* Calculate the mult/shift to convert counter ticks to ns. */
clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
new_mask = CLOCKSOURCE_MASK(bits);
cd.rate = rate;
/* Calculate how many nanosecs until we risk wrapping */
wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
cd.wrap_kt = ns_to_ktime(wrap);
rd = cd.read_data[0];
/* Update epoch for new counter and update 'epoch_ns' from old counter*/
new_epoch = read();
cyc = cd.actual_read_sched_clock();
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
cd.actual_read_sched_clock = read;
rd.read_sched_clock = read;
rd.sched_clock_mask = new_mask;
rd.mult = new_mult;
rd.shift = new_shift;
rd.epoch_cyc = new_epoch;
rd.epoch_ns = ns;
update_clock_read_data(&rd);
if (sched_clock_timer.function != NULL) {
/* update timeout for clock wrap */
hrtimer_start(&sched_clock_timer, cd.wrap_kt,
HRTIMER_MODE_REL_HARD);
}
r = rate;
if (r >= 4000000) {
r = DIV_ROUND_CLOSEST(r, 1000000);
r_unit = 'M';
} else if (r >= 4000) {
r = DIV_ROUND_CLOSEST(r, 1000);
r_unit = 'k';
} else {
r_unit = ' ';
}
/* Calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, new_mult, new_shift);
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
/* Enable IRQ time accounting if we have a fast enough sched_clock() */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
local_irq_restore(flags);
pr_debug("Registered %pS as sched_clock source\n", read);
}
void __init generic_sched_clock_init(void)
{
/*
* If no sched_clock() function has been provided at that point,
* make it the final one.
*/
if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
update_sched_clock();
/*
* Start the timer to keep sched_clock() properly updated and
* sets the initial epoch.
*/
hrtimer_setup(&sched_clock_timer, sched_clock_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
}
/*
* Clock read function for use when the clock is suspended.
*
* This function makes it appear to sched_clock() as if the clock
* stopped counting at its last update.
*
* This function must only be called from the critical
* section in sched_clock(). It relies on the read_seqcount_retry()
* at the end of the critical section to be sure we observe the
* correct copy of 'epoch_cyc'.
*/
static u64 notrace suspended_sched_clock_read(void)
{
unsigned int seq = read_seqcount_latch(&cd.seq);
return cd.read_data[seq & 1].epoch_cyc;
}
int sched_clock_suspend(void)
{
struct clock_read_data *rd = &cd.read_data[0];
update_sched_clock();
hrtimer_cancel(&sched_clock_timer);
rd->read_sched_clock = suspended_sched_clock_read;
return 0;
}
void sched_clock_resume(void)
{
struct clock_read_data *rd = &cd.read_data[0];
rd->epoch_cyc = cd.actual_read_sched_clock();
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
rd->read_sched_clock = cd.actual_read_sched_clock;
}
static struct syscore_ops sched_clock_ops = {
.suspend = sched_clock_suspend,
.resume = sched_clock_resume,
};
static int __init sched_clock_syscore_init(void)
{
register_syscore_ops(&sched_clock_ops);
return 0;
}
device_initcall(sched_clock_syscore_init);
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Generic Timer-queue
*
* Manages a simple queue of timers, ordered by expiration time.
* Uses rbtrees for quick list adds and expiration.
*
* NOTE: All of the following functions need to be serialized
* to avoid races. No locking is done by this library code.
*/
#include <linux/bug.h>
#include <linux/timerqueue.h>
#include <linux/rbtree.h>
#include <linux/export.h>
#define __node_2_tq(_n) \
rb_entry((_n), struct timerqueue_node, node)
static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b)
{
return __node_2_tq(a)->expires < __node_2_tq(b)->expires;
}
/**
* timerqueue_add - Adds timer to timerqueue.
*
* @head: head of timerqueue
* @node: timer node to be added
*
* Adds the timer node to the timerqueue, sorted by the node's expires
* value. Returns true if the newly added timer is the first expiring timer in
* the queue.
*/
bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
{
/* Make sure we don't add nodes that are already added */
WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less);
}
EXPORT_SYMBOL_GPL(timerqueue_add);
/**
* timerqueue_del - Removes a timer from the timerqueue.
*
* @head: head of timerqueue
* @node: timer node to be removed
*
* Removes the timer node from the timerqueue. Returns true if the queue is
* not empty after the remove.
*/
bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
{ WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); rb_erase_cached(&node->node, &head->rb_root);
RB_CLEAR_NODE(&node->node);
return !RB_EMPTY_ROOT(&head->rb_root.rb_root);
}
EXPORT_SYMBOL_GPL(timerqueue_del);
/**
* timerqueue_iterate_next - Returns the timer after the provided timer
*
* @node: Pointer to a timer.
*
* Provides the timer that is after the given node. This is used, when
* necessary, to iterate through the list of timers in a timer list
* without modifying the list.
*/
struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node)
{
struct rb_node *next;
if (!node)
return NULL;
next = rb_next(&node->node);
if (!next)
return NULL;
return container_of(next, struct timerqueue_node, node);
}
EXPORT_SYMBOL_GPL(timerqueue_iterate_next);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MM_H
#define _LINUX_MM_H
#include <linux/errno.h>
#include <linux/mmdebug.h>
#include <linux/gfp.h>
#include <linux/pgalloc_tag.h>
#include <linux/bug.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/atomic.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
#include <linux/mmap_lock.h>
#include <linux/range.h>
#include <linux/pfn.h>
#include <linux/percpu-refcount.h>
#include <linux/bit_spinlock.h>
#include <linux/shrinker.h>
#include <linux/resource.h>
#include <linux/page_ext.h>
#include <linux/err.h>
#include <linux/page-flags.h>
#include <linux/page_ref.h>
#include <linux/overflow.h>
#include <linux/sizes.h>
#include <linux/sched.h>
#include <linux/pgtable.h>
#include <linux/kasan.h>
#include <linux/memremap.h>
#include <linux/slab.h>
#include <linux/cacheinfo.h>
#include <linux/rcuwait.h>
struct mempolicy;
struct anon_vma;
struct anon_vma_chain;
struct user_struct;
struct pt_regs;
struct folio_batch;
void arch_mm_preinit(void);
void mm_core_init(void);
void init_mm_internals(void);
extern atomic_long_t _totalram_pages;
static inline unsigned long totalram_pages(void)
{
return (unsigned long)atomic_long_read(&_totalram_pages);
}
static inline void totalram_pages_inc(void)
{
atomic_long_inc(&_totalram_pages);
}
static inline void totalram_pages_dec(void)
{
atomic_long_dec(&_totalram_pages);
}
static inline void totalram_pages_add(long count)
{
atomic_long_add(count, &_totalram_pages);
}
extern void * high_memory;
#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
#else
#define sysctl_legacy_va_layout 0
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
extern const int mmap_rnd_bits_min;
extern int mmap_rnd_bits_max __ro_after_init;
extern int mmap_rnd_bits __read_mostly;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
extern const int mmap_rnd_compat_bits_min;
extern const int mmap_rnd_compat_bits_max;
extern int mmap_rnd_compat_bits __read_mostly;
#endif
#ifndef DIRECT_MAP_PHYSMEM_END
# ifdef MAX_PHYSMEM_BITS
# define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1)
# else
# define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63))
# endif
#endif
#include <asm/page.h>
#include <asm/processor.h>
#ifndef __pa_symbol
#define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0))
#endif
#ifndef page_to_virt
#define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x)))
#endif
#ifndef lm_alias
#define lm_alias(x) __va(__pa_symbol(x))
#endif
/*
* To prevent common memory management code establishing
* a zero page mapping on a read fault.
* This macro should be defined within <asm/pgtable.h>.
* s390 does this to prevent multiplexing of hardware bits
* related to the physical page in case of virtualization.
*/
#ifndef mm_forbids_zeropage
#define mm_forbids_zeropage(X) (0)
#endif
/*
* On some architectures it is expensive to call memset() for small sizes.
* If an architecture decides to implement their own version of
* mm_zero_struct_page they should wrap the defines below in a #ifndef and
* define their own version of this macro in <asm/pgtable.h>
*/
#if BITS_PER_LONG == 64
/* This function must be updated when the size of struct page grows above 96
* or reduces below 56. The idea that compiler optimizes out switch()
* statement, and only leaves move/store instructions. Also the compiler can
* combine write statements if they are both assignments and can be reordered,
* this can result in several of the writes here being dropped.
*/
#define mm_zero_struct_page(pp) __mm_zero_struct_page(pp)
static inline void __mm_zero_struct_page(struct page *page)
{
unsigned long *_pp = (void *)page;
/* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */
BUILD_BUG_ON(sizeof(struct page) & 7);
BUILD_BUG_ON(sizeof(struct page) < 56);
BUILD_BUG_ON(sizeof(struct page) > 96);
switch (sizeof(struct page)) {
case 96:
_pp[11] = 0;
fallthrough;
case 88:
_pp[10] = 0;
fallthrough;
case 80:
_pp[9] = 0;
fallthrough;
case 72:
_pp[8] = 0;
fallthrough;
case 64:
_pp[7] = 0;
fallthrough;
case 56:
_pp[6] = 0;
_pp[5] = 0;
_pp[4] = 0;
_pp[3] = 0;
_pp[2] = 0;
_pp[1] = 0;
_pp[0] = 0;
}
}
#else
#define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page)))
#endif
/*
* Default maximum number of active map areas, this limits the number of vmas
* per mm struct. Users can overwrite this number by sysctl but there is a
* problem.
*
* When a program's coredump is generated as ELF format, a section is created
* per a vma. In ELF, the number of sections is represented in unsigned short.
* This means the number of sections should be smaller than 65535 at coredump.
* Because the kernel adds some informative sections to a image of program at
* generating coredump, we need some margin. The number of extra sections is
* 1-3 now and depends on arch. We use "5" as safe margin, here.
*
* ELF extended numbering allows more than 65535 sections, so 16-bit bound is
* not a hard limit any more. Although some userspace tools can be surprised by
* that.
*/
#define MAPCOUNT_ELF_CORE_MARGIN (5)
#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
extern int sysctl_max_map_count;
extern unsigned long sysctl_user_reserve_kbytes;
extern unsigned long sysctl_admin_reserve_kbytes;
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
#define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio))
#else
#define nth_page(page,n) ((page) + (n))
#define folio_page_idx(folio, p) ((p) - &(folio)->page)
#endif
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
/* to align the pointer to the (prev) page boundary */
#define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE)
/* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */
#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)
static inline struct folio *lru_to_folio(struct list_head *head)
{
return list_entry((head)->prev, struct folio, lru);
}
void setup_initial_init_mm(void *start_code, void *end_code,
void *end_data, void *brk);
/*
* Linux kernel virtual memory manager primitives.
* The idea being to have a "virtual" mm in the same way
* we have a virtual fs - giving a cleaner interface to the
* mm details, and allowing different kinds of memory mappings
* (from shared memory to executable loading to arbitrary
* mmap() functions).
*/
struct vm_area_struct *vm_area_alloc(struct mm_struct *);
struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
void vm_area_free(struct vm_area_struct *);
#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
extern struct rw_semaphore nommu_region_sem;
extern unsigned int kobjsize(const void *objp);
#endif
/*
* vm_flags in vm_area_struct, see mm_types.h.
* When changing, update also include/trace/events/mmflags.h
*/
#define VM_NONE 0x00000000
#define VM_READ 0x00000001 /* currently active flags */
#define VM_WRITE 0x00000002
#define VM_EXEC 0x00000004
#define VM_SHARED 0x00000008
/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
#define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */
#define VM_MAYWRITE 0x00000020
#define VM_MAYEXEC 0x00000040
#define VM_MAYSHARE 0x00000080
#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
#ifdef CONFIG_MMU
#define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */
#else /* CONFIG_MMU */
#define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
#define VM_UFFD_MISSING 0
#endif /* CONFIG_MMU */
#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */
#define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */
#define VM_LOCKED 0x00002000
#define VM_IO 0x00004000 /* Memory mapped I/O or similar */
/* Used by sys_madvise() */
#define VM_SEQ_READ 0x00008000 /* App will access data sequentially */
#define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */
#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
#define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
#define VM_SYNC 0x00800000 /* Synchronous page faults */
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
#ifdef CONFIG_MEM_SOFT_DIRTY
# define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */
#else
# define VM_SOFTDIRTY 0
#endif
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
#define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */
#define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */
#define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */
#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
#define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0)
#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1)
#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2)
#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3)
#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4)
#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5)
#define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6)
#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
#ifdef CONFIG_ARCH_HAS_PKEYS
# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0
# define VM_PKEY_BIT0 VM_HIGH_ARCH_0
# define VM_PKEY_BIT1 VM_HIGH_ARCH_1
# define VM_PKEY_BIT2 VM_HIGH_ARCH_2
#if CONFIG_ARCH_PKEY_BITS > 3
# define VM_PKEY_BIT3 VM_HIGH_ARCH_3
#else
# define VM_PKEY_BIT3 0
#endif
#if CONFIG_ARCH_PKEY_BITS > 4
# define VM_PKEY_BIT4 VM_HIGH_ARCH_4
#else
# define VM_PKEY_BIT4 0
#endif
#endif /* CONFIG_ARCH_HAS_PKEYS */
#ifdef CONFIG_X86_USER_SHADOW_STACK
/*
* VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
* support core mm.
*
* These VMAs will get a single end guard page. This helps userspace protect
* itself from attacks. A single page is enough for current shadow stack archs
* (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c
* for more details on the guard size.
*/
# define VM_SHADOW_STACK VM_HIGH_ARCH_5
#endif
#if defined(CONFIG_ARM64_GCS)
/*
* arm64's Guarded Control Stack implements similar functionality and
* has similar constraints to shadow stacks.
*/
# define VM_SHADOW_STACK VM_HIGH_ARCH_6
#endif
#ifndef VM_SHADOW_STACK
# define VM_SHADOW_STACK VM_NONE
#endif
#if defined(CONFIG_X86)
# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */
#elif defined(CONFIG_PPC64)
# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */
#elif defined(CONFIG_PARISC)
# define VM_GROWSUP VM_ARCH_1
#elif defined(CONFIG_SPARC64)
# define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */
# define VM_ARCH_CLEAR VM_SPARC_ADI
#elif defined(CONFIG_ARM64)
# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */
# define VM_ARCH_CLEAR VM_ARM64_BTI
#elif !defined(CONFIG_MMU)
# define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */
#endif
#if defined(CONFIG_ARM64_MTE)
# define VM_MTE VM_HIGH_ARCH_4 /* Use Tagged memory for access control */
# define VM_MTE_ALLOWED VM_HIGH_ARCH_5 /* Tagged memory permitted */
#else
# define VM_MTE VM_NONE
# define VM_MTE_ALLOWED VM_NONE
#endif
#ifndef VM_GROWSUP
# define VM_GROWSUP VM_NONE
#endif
#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
# define VM_UFFD_MINOR_BIT 38
# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */
#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
# define VM_UFFD_MINOR VM_NONE
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
/*
* This flag is used to connect VFIO to arch specific KVM code. It
* indicates that the memory under this VMA is safe for use with any
* non-cachable memory type inside KVM. Some VFIO devices, on some
* platforms, are thought to be unsafe and can cause machine crashes
* if KVM does not lock down the memory type.
*/
#ifdef CONFIG_64BIT
#define VM_ALLOW_ANY_UNCACHED_BIT 39
#define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT)
#else
#define VM_ALLOW_ANY_UNCACHED VM_NONE
#endif
#ifdef CONFIG_64BIT
#define VM_DROPPABLE_BIT 40
#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT)
#elif defined(CONFIG_PPC32)
#define VM_DROPPABLE VM_ARCH_1
#else
#define VM_DROPPABLE VM_NONE
#endif
#ifdef CONFIG_64BIT
/* VM is sealed, in vm_flags */
#define VM_SEALED _BITUL(63)
#endif
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
/* Common data flag combinations */
#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \
VM_MAYWRITE | VM_MAYEXEC)
#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC
#endif
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif
#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK VM_GROWSUP
#define VM_STACK_EARLY VM_GROWSDOWN
#else
#define VM_STACK VM_GROWSDOWN
#define VM_STACK_EARLY 0
#endif
#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
/* VMA basic access permission flags */
#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
/*
* Special vmas that are non-mergable, non-mlock()able.
*/
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
/* This mask prevents VMA from being scanned with khugepaged */
#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
/* This mask defines which mm->def_flags a process can inherit its parent */
#define VM_INIT_DEF_MASK VM_NOHUGEPAGE
/* This mask represents all the VMA flag bits used by mlock */
#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT)
/* Arch-specific flags to clear when updating VM flags on protection change */
#ifndef VM_ARCH_CLEAR
# define VM_ARCH_CLEAR VM_NONE
#endif
#define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR)
/*
* mapping from the currently active vm_flags protection bits (the
* low four bits) to a page protection mask..
*/
/*
* The default fault flags that should be used by most of the
* arch-specific page fault handlers.
*/
#define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \
FAULT_FLAG_KILLABLE | \
FAULT_FLAG_INTERRUPTIBLE)
/**
* fault_flag_allow_retry_first - check ALLOW_RETRY the first time
* @flags: Fault flags.
*
* This is mostly used for places where we want to try to avoid taking
* the mmap_lock for too long a time when waiting for another condition
* to change, in which case we can try to be polite to release the
* mmap_lock in the first round to avoid potential starvation of other
* processes that would also want the mmap_lock.
*
* Return: true if the page fault allows retry and this is the first
* attempt of the fault handling; false otherwise.
*/
static inline bool fault_flag_allow_retry_first(enum fault_flag flags)
{
return (flags & FAULT_FLAG_ALLOW_RETRY) &&
(!(flags & FAULT_FLAG_TRIED));
}
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
{ FAULT_FLAG_MKWRITE, "MKWRITE" }, \
{ FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \
{ FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \
{ FAULT_FLAG_KILLABLE, "KILLABLE" }, \
{ FAULT_FLAG_TRIED, "TRIED" }, \
{ FAULT_FLAG_USER, "USER" }, \
{ FAULT_FLAG_REMOTE, "REMOTE" }, \
{ FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \
{ FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \
{ FAULT_FLAG_VMA_LOCK, "VMA_LOCK" }
/*
* vm_fault is filled by the pagefault handler and passed to the vma's
* ->fault function. The vma's ->fault is responsible for returning a bitmask
* of VM_FAULT_xxx flags that give details about how the fault was handled.
*
* MM layer fills up gfp_mask for page allocations but fault handler might
* alter it if its implementation requires a different allocation context.
*
* pgoff should be used in favour of virtual_address, if possible.
*/
struct vm_fault {
const struct {
struct vm_area_struct *vma; /* Target VMA */
gfp_t gfp_mask; /* gfp mask to be used for allocations */
pgoff_t pgoff; /* Logical page offset based on vma */
unsigned long address; /* Faulting virtual address - masked */
unsigned long real_address; /* Faulting virtual address - unmasked */
};
enum fault_flag flags; /* FAULT_FLAG_xxx flags
* XXX: should really be 'const' */
pmd_t *pmd; /* Pointer to pmd entry matching
* the 'address' */
pud_t *pud; /* Pointer to pud entry matching
* the 'address'
*/
union {
pte_t orig_pte; /* Value of PTE at the time of fault */
pmd_t orig_pmd; /* Value of PMD at the time of fault,
* used by PMD fault only.
*/
};
struct page *cow_page; /* Page handler may use for COW fault */
struct page *page; /* ->fault handlers should return a
* page here, unless VM_FAULT_NOPAGE
* is set (which is also implied by
* VM_FAULT_ERROR).
*/
/* These three entries are valid only while holding ptl lock */
pte_t *pte; /* Pointer to pte entry matching
* the 'address'. NULL if the page
* table hasn't been allocated.
*/
spinlock_t *ptl; /* Page table lock.
* Protects pte page table if 'pte'
* is not NULL, otherwise pmd.
*/
pgtable_t prealloc_pte; /* Pre-allocated pte page table.
* vm_ops->map_pages() sets up a page
* table from atomic context.
* do_fault_around() pre-allocates
* page table to avoid allocation from
* atomic context.
*/
};
/*
* These are the virtual MM functions - opening of an area, closing and
* unmapping it (needed to keep files on disk up-to-date etc), pointer
* to the functions called when a no-page or a wp-page exception occurs.
*/
struct vm_operations_struct {
void (*open)(struct vm_area_struct * area);
/**
* @close: Called when the VMA is being removed from the MM.
* Context: User context. May sleep. Caller holds mmap_lock.
*/
void (*close)(struct vm_area_struct * area);
/* Called any time before splitting to check if it's allowed */
int (*may_split)(struct vm_area_struct *area, unsigned long addr);
int (*mremap)(struct vm_area_struct *area);
/*
* Called by mprotect() to make driver-specific permission
* checks before mprotect() is finalised. The VMA must not
* be modified. Returns 0 if mprotect() can proceed.
*/
int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
unsigned long end, unsigned long newflags);
vm_fault_t (*fault)(struct vm_fault *vmf);
vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
vm_fault_t (*map_pages)(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
unsigned long (*pagesize)(struct vm_area_struct * area);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
/* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
/* called by access_process_vm when get_user_pages() fails, typically
* for use by special VMAs. See also generic_access_phys() for a generic
* implementation useful for any iomem mapping.
*/
int (*access)(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write);
/* Called by the /proc/PID/maps code to ask the vma whether it
* has a special name. Returning non-NULL will also cause this
* vma to be dumped unconditionally. */
const char *(*name)(struct vm_area_struct *vma);
#ifdef CONFIG_NUMA
/*
* set_policy() op must add a reference to any non-NULL @new mempolicy
* to hold the policy upon return. Caller should pass NULL @new to
* remove a policy and fall back to surrounding context--i.e. do not
* install a MPOL_DEFAULT policy, nor the task or system default
* mempolicy.
*/
int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
/*
* get_policy() op must add reference [mpol_get()] to any policy at
* (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure
* in mm/mempolicy.c will do this automatically.
* get_policy() must NOT add a ref if the policy at (vma,addr) is not
* marked as MPOL_SHARED. vma policies are protected by the mmap_lock.
* If no [shared/vma] mempolicy exists at the addr, get_policy() op
* must return NULL--i.e., do not "fallback" to task or system default
* policy.
*/
struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx);
#endif
/*
* Called by vm_normal_page() for special PTEs to find the
* page for @addr. This is useful if the default behavior
* (using pte_page()) would not find the correct page.
*/
struct page *(*find_special_page)(struct vm_area_struct *vma,
unsigned long addr);
};
#ifdef CONFIG_NUMA_BALANCING
static inline void vma_numab_state_init(struct vm_area_struct *vma)
{
vma->numab_state = NULL;
}
static inline void vma_numab_state_free(struct vm_area_struct *vma)
{
kfree(vma->numab_state);
}
#else
static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_PER_VMA_LOCK
static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key lockdep_key;
lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0);
#endif
if (reset_refcnt)
refcount_set(&vma->vm_refcnt, 0);
vma->vm_lock_seq = UINT_MAX;
}
static inline bool is_vma_writer_only(int refcnt)
{
/*
* With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma
* is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on
* a detached vma happens only in vma_mark_detached() and is a rare
* case, therefore most of the time there will be no unnecessary wakeup.
*/
return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1;
}
static inline void vma_refcount_put(struct vm_area_struct *vma)
{
/* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
struct mm_struct *mm = vma->vm_mm;
int oldcnt;
rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { if (is_vma_writer_only(oldcnt - 1)) rcuwait_wake_up(&mm->vma_writer_wait);
}
}
/*
* Try to read-lock a vma. The function is allowed to occasionally yield false
* locked result to avoid performance overhead, in which case we fall back to
* using mmap_lock. The function should never yield false unlocked result.
* False locked result is possible if mm_lock_seq overflows or if vma gets
* reused and attached to a different mm before we lock it.
* Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
* detached.
*/
static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
struct vm_area_struct *vma)
{
int oldcnt;
/*
* Check before locking. A race might cause false locked result.
* We can use READ_ONCE() for the mm_lock_seq here, and don't need
* ACQUIRE semantics, because this is just a lockless check whose result
* we don't rely on for anything - the mm_lock_seq read against which we
* need ordering is below.
*/
if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence))
return NULL;
/*
* If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire()
* will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET.
* Acquire fence is required here to avoid reordering against later
* vm_lock_seq check and checks inside lock_vma_under_rcu().
*/
if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
VMA_REF_LIMIT))) {
/* return EAGAIN if vma got detached from under us */
return oldcnt ? NULL : ERR_PTR(-EAGAIN);
}
rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
/*
* Overflow of vm_lock_seq/mm_lock_seq might produce false locked result.
* False unlocked result is impossible because we modify and check
* vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq
* modification invalidates all existing locks.
*
* We must use ACQUIRE semantics for the mm_lock_seq so that if we are
* racing with vma_end_write_all(), we only start reading from the VMA
* after it has been unlocked.
* This pairs with RELEASE semantics in vma_end_write_all().
*/
if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) {
vma_refcount_put(vma);
return NULL;
}
return vma;
}
/*
* Use only while holding mmap read lock which guarantees that locking will not
* fail (nobody can concurrently write-lock the vma). vma_start_read() should
* not be used in such cases because it might fail due to mm_lock_seq overflow.
* This functionality is used to obtain vma read lock and drop the mmap read lock.
*/
static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
{
int oldcnt;
mmap_assert_locked(vma->vm_mm);
if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
VMA_REF_LIMIT)))
return false;
rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
return true;
}
/*
* Use only while holding mmap read lock which guarantees that locking will not
* fail (nobody can concurrently write-lock the vma). vma_start_read() should
* not be used in such cases because it might fail due to mm_lock_seq overflow.
* This functionality is used to obtain vma read lock and drop the mmap read lock.
*/
static inline bool vma_start_read_locked(struct vm_area_struct *vma)
{
return vma_start_read_locked_nested(vma, 0);
}
static inline void vma_end_read(struct vm_area_struct *vma)
{ vma_refcount_put(vma);
}
/* WARNING! Can only be used if mmap_lock is expected to be write-locked */
static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq)
{
mmap_assert_write_locked(vma->vm_mm);
/*
* current task is holding mmap_write_lock, both vma->vm_lock_seq and
* mm->mm_lock_seq can't be concurrently modified.
*/
*mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence;
return (vma->vm_lock_seq == *mm_lock_seq);
}
void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq);
/*
* Begin writing to a VMA.
* Exclude concurrent readers under the per-VMA lock until the currently
* write-locked mmap_lock is dropped or downgraded.
*/
static inline void vma_start_write(struct vm_area_struct *vma)
{
unsigned int mm_lock_seq;
if (__is_vma_write_locked(vma, &mm_lock_seq))
return;
__vma_start_write(vma, mm_lock_seq);
}
static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{
unsigned int mm_lock_seq;
VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
}
static inline void vma_assert_locked(struct vm_area_struct *vma)
{
unsigned int mm_lock_seq;
VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 &&
!__is_vma_write_locked(vma, &mm_lock_seq), vma);
}
/*
* WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
* assertions should be made either under mmap_write_lock or when the object
* has been isolated under mmap_write_lock, ensuring no competing writers.
*/
static inline void vma_assert_attached(struct vm_area_struct *vma)
{
WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
}
static inline void vma_assert_detached(struct vm_area_struct *vma)
{
WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
}
static inline void vma_mark_attached(struct vm_area_struct *vma)
{
vma_assert_write_locked(vma); vma_assert_detached(vma);
refcount_set_release(&vma->vm_refcnt, 1);
}
void vma_mark_detached(struct vm_area_struct *vma);
static inline void release_fault_lock(struct vm_fault *vmf)
{
if (vmf->flags & FAULT_FLAG_VMA_LOCK)
vma_end_read(vmf->vma);
else
mmap_read_unlock(vmf->vma->vm_mm);
}
static inline void assert_fault_locked(struct vm_fault *vmf)
{
if (vmf->flags & FAULT_FLAG_VMA_LOCK)
vma_assert_locked(vmf->vma);
else
mmap_assert_locked(vmf->vma->vm_mm);
}
struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
unsigned long address);
#else /* CONFIG_PER_VMA_LOCK */
static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {}
static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
struct vm_area_struct *vma)
{ return NULL; }
static inline void vma_end_read(struct vm_area_struct *vma) {}
static inline void vma_start_write(struct vm_area_struct *vma) {}
static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{ mmap_assert_write_locked(vma->vm_mm); }
static inline void vma_assert_attached(struct vm_area_struct *vma) {}
static inline void vma_assert_detached(struct vm_area_struct *vma) {}
static inline void vma_mark_attached(struct vm_area_struct *vma) {}
static inline void vma_mark_detached(struct vm_area_struct *vma) {}
static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
unsigned long address)
{
return NULL;
}
static inline void vma_assert_locked(struct vm_area_struct *vma)
{
mmap_assert_locked(vma->vm_mm);
}
static inline void release_fault_lock(struct vm_fault *vmf)
{
mmap_read_unlock(vmf->vma->vm_mm);
}
static inline void assert_fault_locked(struct vm_fault *vmf)
{
mmap_assert_locked(vmf->vma->vm_mm);
}
#endif /* CONFIG_PER_VMA_LOCK */
extern const struct vm_operations_struct vma_dummy_vm_ops;
static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
{
memset(vma, 0, sizeof(*vma));
vma->vm_mm = mm;
vma->vm_ops = &vma_dummy_vm_ops;
INIT_LIST_HEAD(&vma->anon_vma_chain);
vma_lock_init(vma, false);
}
/* Use when VMA is not part of the VMA tree and needs no locking */
static inline void vm_flags_init(struct vm_area_struct *vma,
vm_flags_t flags)
{
ACCESS_PRIVATE(vma, __vm_flags) = flags;
}
/*
* Use when VMA is part of the VMA tree and modifications need coordination
* Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
* it should be locked explicitly beforehand.
*/
static inline void vm_flags_reset(struct vm_area_struct *vma,
vm_flags_t flags)
{
vma_assert_write_locked(vma);
vm_flags_init(vma, flags);
}
static inline void vm_flags_reset_once(struct vm_area_struct *vma,
vm_flags_t flags)
{
vma_assert_write_locked(vma);
WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
}
static inline void vm_flags_set(struct vm_area_struct *vma,
vm_flags_t flags)
{
vma_start_write(vma);
ACCESS_PRIVATE(vma, __vm_flags) |= flags;
}
static inline void vm_flags_clear(struct vm_area_struct *vma,
vm_flags_t flags)
{
vma_start_write(vma);
ACCESS_PRIVATE(vma, __vm_flags) &= ~flags;
}
/*
* Use only if VMA is not part of the VMA tree or has no other users and
* therefore needs no locking.
*/
static inline void __vm_flags_mod(struct vm_area_struct *vma,
vm_flags_t set, vm_flags_t clear)
{
vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
}
/*
* Use only when the order of set/clear operations is unimportant, otherwise
* use vm_flags_{set|clear} explicitly.
*/
static inline void vm_flags_mod(struct vm_area_struct *vma,
vm_flags_t set, vm_flags_t clear)
{
vma_start_write(vma);
__vm_flags_mod(vma, set, clear);
}
static inline void vma_set_anonymous(struct vm_area_struct *vma)
{
vma->vm_ops = NULL;
}
static inline bool vma_is_anonymous(struct vm_area_struct *vma)
{
return !vma->vm_ops;
}
/*
* Indicate if the VMA is a heap for the given task; for
* /proc/PID/maps that is the heap of the main task.
*/
static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
{
return vma->vm_start < vma->vm_mm->brk &&
vma->vm_end > vma->vm_mm->start_brk;
}
/*
* Indicate if the VMA is a stack for the given task; for
* /proc/PID/maps that is the stack of the main task.
*/
static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
{
/*
* We make no effort to guess what a given thread considers to be
* its "stack". It's not even well-defined for programs written
* languages like Go.
*/
return vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack;
}
static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
{
int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
if (!maybe_stack)
return false;
if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
VM_STACK_INCOMPLETE_SETUP)
return true;
return false;
}
static inline bool vma_is_foreign(struct vm_area_struct *vma)
{
if (!current->mm)
return true;
if (current->mm != vma->vm_mm)
return true;
return false;
}
static inline bool vma_is_accessible(struct vm_area_struct *vma)
{
return vma->vm_flags & VM_ACCESS_FLAGS;
}
static inline bool is_shared_maywrite(vm_flags_t vm_flags)
{
return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
(VM_SHARED | VM_MAYWRITE);
}
static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma)
{
return is_shared_maywrite(vma->vm_flags);
}
static inline
struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
{
return mas_find(&vmi->mas, max - 1);
}
static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
{
/*
* Uses mas_find() to get the first VMA when the iterator starts.
* Calling mas_next() could skip the first entry.
*/
return mas_find(&vmi->mas, ULONG_MAX);
}
static inline
struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
{
return mas_next_range(&vmi->mas, ULONG_MAX);
}
static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
{
return mas_prev(&vmi->mas, 0);
}
static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
unsigned long start, unsigned long end, gfp_t gfp)
{
__mas_set_range(&vmi->mas, start, end - 1);
mas_store_gfp(&vmi->mas, NULL, gfp);
if (unlikely(mas_is_err(&vmi->mas)))
return -ENOMEM;
return 0;
}
/* Free any unused preallocations */
static inline void vma_iter_free(struct vma_iterator *vmi)
{
mas_destroy(&vmi->mas);
}
static inline int vma_iter_bulk_store(struct vma_iterator *vmi,
struct vm_area_struct *vma)
{
vmi->mas.index = vma->vm_start;
vmi->mas.last = vma->vm_end - 1;
mas_store(&vmi->mas, vma);
if (unlikely(mas_is_err(&vmi->mas)))
return -ENOMEM;
vma_mark_attached(vma);
return 0;
}
static inline void vma_iter_invalidate(struct vma_iterator *vmi)
{
mas_pause(&vmi->mas);
}
static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
{
mas_set(&vmi->mas, addr);
}
#define for_each_vma(__vmi, __vma) \
while (((__vma) = vma_next(&(__vmi))) != NULL)
/* The MM code likes to work with exclusive end addresses */
#define for_each_vma_range(__vmi, __vma, __end) \
while (((__vma) = vma_find(&(__vmi), (__end))) != NULL)
#ifdef CONFIG_SHMEM
/*
* The vma_is_shmem is not inline because it is used only by slow
* paths in userfault.
*/
bool vma_is_shmem(struct vm_area_struct *vma);
bool vma_is_anon_shmem(struct vm_area_struct *vma);
#else
static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; }
static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; }
#endif
int vma_is_stack_for_current(struct vm_area_struct *vma);
/* flush_tlb_range() takes a vma, not a mm, and can care about flags */
#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) }
struct mmu_gather;
struct inode;
extern void prep_compound_page(struct page *page, unsigned int order);
static inline unsigned int folio_large_order(const struct folio *folio)
{
return folio->_flags_1 & 0xff;
}
#ifdef NR_PAGES_IN_LARGE_FOLIO
static inline long folio_large_nr_pages(const struct folio *folio)
{
return folio->_nr_pages;
}
#else
static inline long folio_large_nr_pages(const struct folio *folio)
{
return 1L << folio_large_order(folio);
}
#endif
/*
* compound_order() can be called without holding a reference, which means
* that niceties like page_folio() don't work. These callers should be
* prepared to handle wild return values. For example, PG_head may be
* set before the order is initialised, or this may be a tail page.
* See compaction.c for some good examples.
*/
static inline unsigned int compound_order(struct page *page)
{
struct folio *folio = (struct folio *)page;
if (!test_bit(PG_head, &folio->flags))
return 0;
return folio_large_order(folio);
}
/**
* folio_order - The allocation order of a folio.
* @folio: The folio.
*
* A folio is composed of 2^order pages. See get_order() for the definition
* of order.
*
* Return: The order of the folio.
*/
static inline unsigned int folio_order(const struct folio *folio)
{ if (!folio_test_large(folio))
return 0;
return folio_large_order(folio);
}
/**
* folio_reset_order - Reset the folio order and derived _nr_pages
* @folio: The folio.
*
* Reset the order and derived _nr_pages to 0. Must only be used in the
* process of splitting large folios.
*/
static inline void folio_reset_order(struct folio *folio)
{
if (WARN_ON_ONCE(!folio_test_large(folio)))
return;
folio->_flags_1 &= ~0xffUL;
#ifdef NR_PAGES_IN_LARGE_FOLIO
folio->_nr_pages = 0;
#endif
}
#include <linux/huge_mm.h>
/*
* Methods to modify the page usage count.
*
* What counts for a page usage:
* - cache mapping (page->mapping)
* - private data (page->private)
* - page mapped in a task's page tables, each mapping
* is counted separately
*
* Also, many kernel routines increase the page count before a critical
* routine so they can be sure the page doesn't go away from under them.
*/
/*
* Drop a ref, return true if the refcount fell to zero (the page has no users)
*/
static inline int put_page_testzero(struct page *page)
{
VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page);
}
static inline int folio_put_testzero(struct folio *folio)
{
return put_page_testzero(&folio->page);
}
/*
* Try to grab a ref unless the page has a refcount of zero, return false if
* that is the case.
* This can be called when MMU is off so it must not access
* any of the virtual mappings.
*/
static inline bool get_page_unless_zero(struct page *page)
{
return page_ref_add_unless(page, 1, 0);
}
static inline struct folio *folio_get_nontail_page(struct page *page)
{
if (unlikely(!get_page_unless_zero(page)))
return NULL;
return (struct folio *)page;
}
extern int page_is_ram(unsigned long pfn);
enum {
REGION_INTERSECTS,
REGION_DISJOINT,
REGION_MIXED,
};
int region_intersects(resource_size_t offset, size_t size, unsigned long flags,
unsigned long desc);
/* Support for virtually mapped pages */
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);
/*
* Determine if an address is within the vmalloc range
*
* On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
* is no special casing required.
*/
#ifdef CONFIG_MMU
extern bool is_vmalloc_addr(const void *x);
extern int is_vmalloc_or_module_addr(const void *x);
#else
static inline bool is_vmalloc_addr(const void *x)
{
return false;
}
static inline int is_vmalloc_or_module_addr(const void *x)
{
return 0;
}
#endif
/*
* How many times the entire folio is mapped as a single unit (eg by a
* PMD or PUD entry). This is probably not what you want, except for
* debugging purposes or implementation of other core folio_*() primitives.
*/
static inline int folio_entire_mapcount(const struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1))
return 0;
return atomic_read(&folio->_entire_mapcount) + 1;
}
static inline int folio_large_mapcount(const struct folio *folio)
{
VM_WARN_ON_FOLIO(!folio_test_large(folio), folio);
return atomic_read(&folio->_large_mapcount) + 1;
}
/**
* folio_mapcount() - Number of mappings of this folio.
* @folio: The folio.
*
* The folio mapcount corresponds to the number of present user page table
* entries that reference any part of a folio. Each such present user page
* table entry must be paired with exactly on folio reference.
*
* For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts
* exactly once.
*
* For hugetlb folios, each abstracted "hugetlb" user page table entry that
* references the entire folio counts exactly once, even when such special
* page table entries are comprised of multiple ordinary page table entries.
*
* Will report 0 for pages which cannot be mapped into userspace, such as
* slab, page tables and similar.
*
* Return: The number of times this folio is mapped.
*/
static inline int folio_mapcount(const struct folio *folio)
{
int mapcount;
if (likely(!folio_test_large(folio))) {
mapcount = atomic_read(&folio->_mapcount) + 1;
if (page_mapcount_is_type(mapcount))
mapcount = 0;
return mapcount;
}
return folio_large_mapcount(folio);
}
/**
* folio_mapped - Is this folio mapped into userspace?
* @folio: The folio.
*
* Return: True if any page in this folio is referenced by user page tables.
*/
static inline bool folio_mapped(const struct folio *folio)
{
return folio_mapcount(folio) >= 1;
}
/*
* Return true if this page is mapped into pagetables.
* For compound page it returns true if any sub-page of compound page is mapped,
* even if this particular sub-page is not itself mapped by any PTE or PMD.
*/
static inline bool page_mapped(const struct page *page)
{
return folio_mapped(page_folio(page));
}
static inline struct page *virt_to_head_page(const void *x)
{
struct page *page = virt_to_page(x);
return compound_head(page);
}
static inline struct folio *virt_to_folio(const void *x)
{
struct page *page = virt_to_page(x);
return page_folio(page);
}
void __folio_put(struct folio *folio);
void split_page(struct page *page, unsigned int order);
void folio_copy(struct folio *dst, struct folio *src);
int folio_mc_copy(struct folio *dst, struct folio *src);
unsigned long nr_free_buffer_pages(void);
/* Returns the number of bytes in this potentially compound page. */
static inline unsigned long page_size(struct page *page)
{
return PAGE_SIZE << compound_order(page);
}
/* Returns the number of bits needed for the number of bytes in a page */
static inline unsigned int page_shift(struct page *page)
{
return PAGE_SHIFT + compound_order(page);
}
/**
* thp_order - Order of a transparent huge page.
* @page: Head page of a transparent huge page.
*/
static inline unsigned int thp_order(struct page *page)
{
VM_BUG_ON_PGFLAGS(PageTail(page), page);
return compound_order(page);
}
/**
* thp_size - Size of a transparent huge page.
* @page: Head page of a transparent huge page.
*
* Return: Number of bytes in this page.
*/
static inline unsigned long thp_size(struct page *page)
{
return PAGE_SIZE << thp_order(page);
}
#ifdef CONFIG_MMU
/*
* Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when
* servicing faults for write access. In the normal case, do always want
* pte_mkwrite. But get_user_pages can cause write faults for mappings
* that do not have writing enabled, when used by access_process_vm.
*/
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pte = pte_mkwrite(pte, vma);
return pte;
}
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
void set_pte_range(struct vm_fault *vmf, struct folio *folio,
struct page *page, unsigned int nr, unsigned long addr);
vm_fault_t finish_fault(struct vm_fault *vmf);
#endif
/*
* Multiple processes may "see" the same page. E.g. for untouched
* mappings of /dev/null, all processes see the same page full of
* zeroes, and text pages of executables and shared libraries have
* only one copy in memory, at most, normally.
*
* For the non-reserved pages, page_count(page) denotes a reference count.
* page_count() == 0 means the page is free. page->lru is then used for
* freelist management in the buddy allocator.
* page_count() > 0 means the page has been allocated.
*
* Pages are allocated by the slab allocator in order to provide memory
* to kmalloc and kmem_cache_alloc. In this case, the management of the
* page, and the fields in 'struct page' are the responsibility of mm/slab.c
* unless a particular usage is carefully commented. (the responsibility of
* freeing the kmalloc memory is the caller's, of course).
*
* A page may be used by anyone else who does a __get_free_page().
* In this case, page_count still tracks the references, and should only
* be used through the normal accessor functions. The top bits of page->flags
* and page->virtual store page management information, but all other fields
* are unused and could be used privately, carefully. The management of this
* page is the responsibility of the one who allocated it, and those who have
* subsequently been given references to it.
*
* The other pages (we may call them "pagecache pages") are completely
* managed by the Linux memory manager: I/O, buffers, swapping etc.
* The following discussion applies only to them.
*
* A pagecache page contains an opaque `private' member, which belongs to the
* page's address_space. Usually, this is the address of a circular list of
* the page's disk buffers. PG_private must be set to tell the VM to call
* into the filesystem to release these pages.
*
* A page may belong to an inode's memory mapping. In this case, page->mapping
* is the pointer to the inode, and page->index is the file offset of the page,
* in units of PAGE_SIZE.
*
* If pagecache pages are not associated with an inode, they are said to be
* anonymous pages. These may become associated with the swapcache, and in that
* case PG_swapcache is set, and page->private is an offset into the swapcache.
*
* In either case (swapcache or inode backed), the pagecache itself holds one
* reference to the page. Setting PG_private should also increment the
* refcount. The each user mapping also has a reference to the page.
*
* The pagecache pages are stored in a per-mapping radix tree, which is
* rooted at mapping->i_pages, and indexed by offset.
* Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
* lists, we instead now tag pages as dirty/writeback in the radix tree.
*
* All pagecache pages may be subject to I/O:
* - inode pages may need to be read from disk,
* - inode pages which have been modified and are MAP_SHARED may need
* to be written back to the inode on disk,
* - anonymous pages (including MAP_PRIVATE file mappings) which have been
* modified may need to be swapped out to swap space and (later) to be read
* back into memory.
*/
/* 127: arbitrary random number, small enough to assemble well */
#define folio_ref_zero_or_close_to_overflow(folio) \
((unsigned int) folio_ref_count(folio) + 127u <= 127u)
/**
* folio_get - Increment the reference count on a folio.
* @folio: The folio.
*
* Context: May be called in any context, as long as you know that
* you have a refcount on the folio. If you do not already have one,
* folio_try_get() may be the right interface for you to use.
*/
static inline void folio_get(struct folio *folio)
{
VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); folio_ref_inc(folio);
}
static inline void get_page(struct page *page)
{
struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_test_slab(folio)))
return;
folio_get(folio);
}
static inline __must_check bool try_get_page(struct page *page)
{
page = compound_head(page);
if (WARN_ON_ONCE(page_ref_count(page) <= 0))
return false;
page_ref_inc(page);
return true;
}
/**
* folio_put - Decrement the reference count on a folio.
* @folio: The folio.
*
* If the folio's reference count reaches zero, the memory will be
* released back to the page allocator and may be used by another
* allocation immediately. Do not access the memory or the struct folio
* after calling folio_put() unless you can be sure that it wasn't the
* last reference.
*
* Context: May be called in process or interrupt context, but not in NMI
* context. May be called while holding a spinlock.
*/
static inline void folio_put(struct folio *folio)
{ if (folio_put_testzero(folio)) __folio_put(folio);
}
/**
* folio_put_refs - Reduce the reference count on a folio.
* @folio: The folio.
* @refs: The amount to subtract from the folio's reference count.
*
* If the folio's reference count reaches zero, the memory will be
* released back to the page allocator and may be used by another
* allocation immediately. Do not access the memory or the struct folio
* after calling folio_put_refs() unless you can be sure that these weren't
* the last references.
*
* Context: May be called in process or interrupt context, but not in NMI
* context. May be called while holding a spinlock.
*/
static inline void folio_put_refs(struct folio *folio, int refs)
{
if (folio_ref_sub_and_test(folio, refs)) __folio_put(folio);
}
void folios_put_refs(struct folio_batch *folios, unsigned int *refs);
/*
* union release_pages_arg - an array of pages or folios
*
* release_pages() releases a simple array of multiple pages, and
* accepts various different forms of said page array: either
* a regular old boring array of pages, an array of folios, or
* an array of encoded page pointers.
*
* The transparent union syntax for this kind of "any of these
* argument types" is all kinds of ugly, so look away.
*/
typedef union {
struct page **pages;
struct folio **folios;
struct encoded_page **encoded_pages;
} release_pages_arg __attribute__ ((__transparent_union__));
void release_pages(release_pages_arg, int nr);
/**
* folios_put - Decrement the reference count on an array of folios.
* @folios: The folios.
*
* Like folio_put(), but for a batch of folios. This is more efficient
* than writing the loop yourself as it will optimise the locks which need
* to be taken if the folios are freed. The folios batch is returned
* empty and ready to be reused for another batch; there is no need to
* reinitialise it.
*
* Context: May be called in process or interrupt context, but not in NMI
* context. May be called while holding a spinlock.
*/
static inline void folios_put(struct folio_batch *folios)
{
folios_put_refs(folios, NULL);
}
static inline void put_page(struct page *page)
{
struct folio *folio = page_folio(page); if (folio_test_slab(folio))
return;
folio_put(folio);
}
/*
* GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
* the page's refcount so that two separate items are tracked: the original page
* reference count, and also a new count of how many pin_user_pages() calls were
* made against the page. ("gup-pinned" is another term for the latter).
*
* With this scheme, pin_user_pages() becomes special: such pages are marked as
* distinct from normal pages. As such, the unpin_user_page() call (and its
* variants) must be used in order to release gup-pinned pages.
*
* Choice of value:
*
* By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
* counts with respect to pin_user_pages() and unpin_user_page() becomes
* simpler, due to the fact that adding an even power of two to the page
* refcount has the effect of using only the upper N bits, for the code that
* counts up using the bias value. This means that the lower bits are left for
* the exclusive use of the original code that increments and decrements by one
* (or at least, by much smaller values than the bias value).
*
* Of course, once the lower bits overflow into the upper bits (and this is
* OK, because subtraction recovers the original values), then visual inspection
* no longer suffices to directly view the separate counts. However, for normal
* applications that don't have huge page reference counts, this won't be an
* issue.
*
* Locking: the lockless algorithm described in folio_try_get_rcu()
* provides safe operation for get_user_pages(), folio_mkclean() and
* other calls that race to set up page table entries.
*/
#define GUP_PIN_COUNTING_BIAS (1U << 10)
void unpin_user_page(struct page *page);
void unpin_folio(struct folio *folio);
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
bool make_dirty);
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
bool make_dirty);
void unpin_user_pages(struct page **pages, unsigned long npages);
void unpin_user_folio(struct folio *folio, unsigned long npages);
void unpin_folios(struct folio **folios, unsigned long nfolios);
static inline bool is_cow_mapping(vm_flags_t flags)
{
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
#ifndef CONFIG_MMU
static inline bool is_nommu_shared_mapping(vm_flags_t flags)
{
/*
* NOMMU shared mappings are ordinary MAP_SHARED mappings and selected
* R/O MAP_PRIVATE file mappings that are an effective R/O overlay of
* a file mapping. R/O MAP_PRIVATE mappings might still modify
* underlying memory if ptrace is active, so this is only possible if
* ptrace does not apply. Note that there is no mprotect() to upgrade
* write permissions later.
*/
return flags & (VM_MAYSHARE | VM_MAYOVERLAY);
}
#endif
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
/*
* The identification function is mainly used by the buddy allocator for
* determining if two pages could be buddies. We are not really identifying
* the zone since we could be using the section number id if we do not have
* node id available in page flags.
* We only guarantee that it will return the same value for two combinable
* pages in a zone.
*/
static inline int page_zone_id(struct page *page)
{
return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
}
#ifdef NODE_NOT_IN_PAGE_FLAGS
int page_to_nid(const struct page *page);
#else
static inline int page_to_nid(const struct page *page)
{
return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK;
}
#endif
static inline int folio_nid(const struct folio *folio)
{
return page_to_nid(&folio->page);
}
#ifdef CONFIG_NUMA_BALANCING
/* page access time bits needs to hold at least 4 seconds */
#define PAGE_ACCESS_TIME_MIN_BITS 12
#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS
#define PAGE_ACCESS_TIME_BUCKETS \
(PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT)
#else
#define PAGE_ACCESS_TIME_BUCKETS 0
#endif
#define PAGE_ACCESS_TIME_MASK \
(LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS)
static inline int cpu_pid_to_cpupid(int cpu, int pid)
{
return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK);
}
static inline int cpupid_to_pid(int cpupid)
{
return cpupid & LAST__PID_MASK;
}
static inline int cpupid_to_cpu(int cpupid)
{
return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK;
}
static inline int cpupid_to_nid(int cpupid)
{
return cpu_to_node(cpupid_to_cpu(cpupid));
}
static inline bool cpupid_pid_unset(int cpupid)
{
return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK);
}
static inline bool cpupid_cpu_unset(int cpupid)
{
return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK);
}
static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
{
return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid);
}
#define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid)
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
{
return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK);
}
static inline int folio_last_cpupid(struct folio *folio)
{
return folio->_last_cpupid;
}
static inline void page_cpupid_reset_last(struct page *page)
{
page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int folio_last_cpupid(struct folio *folio)
{
return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
}
int folio_xchg_last_cpupid(struct folio *folio, int cpupid);
static inline void page_cpupid_reset_last(struct page *page)
{
page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
}
#endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */
static inline int folio_xchg_access_time(struct folio *folio, int time)
{
int last_time;
last_time = folio_xchg_last_cpupid(folio,
time >> PAGE_ACCESS_TIME_BUCKETS);
return last_time << PAGE_ACCESS_TIME_BUCKETS;
}
static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
{
unsigned int pid_bit;
pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG));
if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) {
__set_bit(pid_bit, &vma->numab_state->pids_active[1]);
}
}
bool folio_use_access_time(struct folio *folio);
#else /* !CONFIG_NUMA_BALANCING */
static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
{
return folio_nid(folio); /* XXX */
}
static inline int folio_xchg_access_time(struct folio *folio, int time)
{
return 0;
}
static inline int folio_last_cpupid(struct folio *folio)
{
return folio_nid(folio); /* XXX */
}
static inline int cpupid_to_nid(int cpupid)
{
return -1;
}
static inline int cpupid_to_pid(int cpupid)
{
return -1;
}
static inline int cpupid_to_cpu(int cpupid)
{
return -1;
}
static inline int cpu_pid_to_cpupid(int nid, int pid)
{
return -1;
}
static inline bool cpupid_pid_unset(int cpupid)
{
return true;
}
static inline void page_cpupid_reset_last(struct page *page)
{
}
static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
{
return false;
}
static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
{
}
static inline bool folio_use_access_time(struct folio *folio)
{
return false;
}
#endif /* CONFIG_NUMA_BALANCING */
#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
/*
* KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid
* setting tags for all pages to native kernel tag value 0xff, as the default
* value 0x00 maps to 0xff.
*/
static inline u8 page_kasan_tag(const struct page *page)
{
u8 tag = KASAN_TAG_KERNEL;
if (kasan_enabled()) {
tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
tag ^= 0xff;
}
return tag;
}
static inline void page_kasan_tag_set(struct page *page, u8 tag)
{
unsigned long old_flags, flags;
if (!kasan_enabled())
return;
tag ^= 0xff;
old_flags = READ_ONCE(page->flags);
do {
flags = old_flags;
flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
} while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
}
static inline void page_kasan_tag_reset(struct page *page)
{
if (kasan_enabled())
page_kasan_tag_set(page, KASAN_TAG_KERNEL);
}
#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
static inline u8 page_kasan_tag(const struct page *page)
{
return 0xff;
}
static inline void page_kasan_tag_set(struct page *page, u8 tag) { }
static inline void page_kasan_tag_reset(struct page *page) { }
#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
static inline struct zone *page_zone(const struct page *page)
{
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}
static inline pg_data_t *page_pgdat(const struct page *page)
{
return NODE_DATA(page_to_nid(page));
}
static inline struct zone *folio_zone(const struct folio *folio)
{
return page_zone(&folio->page);
}
static inline pg_data_t *folio_pgdat(const struct folio *folio)
{
return page_pgdat(&folio->page);
}
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}
static inline unsigned long page_to_section(const struct page *page)
{
return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
#endif
/**
* folio_pfn - Return the Page Frame Number of a folio.
* @folio: The folio.
*
* A folio may contain multiple pages. The pages have consecutive
* Page Frame Numbers.
*
* Return: The Page Frame Number of the first page in the folio.
*/
static inline unsigned long folio_pfn(const struct folio *folio)
{
return page_to_pfn(&folio->page);
}
static inline struct folio *pfn_folio(unsigned long pfn)
{
return page_folio(pfn_to_page(pfn));
}
static inline bool folio_has_pincount(const struct folio *folio)
{
if (IS_ENABLED(CONFIG_64BIT))
return folio_test_large(folio);
return folio_order(folio) > 1;
}
/**
* folio_maybe_dma_pinned - Report if a folio may be pinned for DMA.
* @folio: The folio.
*
* This function checks if a folio has been pinned via a call to
* a function in the pin_user_pages() family.
*
* For small folios, the return value is partially fuzzy: false is not fuzzy,
* because it means "definitely not pinned for DMA", but true means "probably
* pinned for DMA, but possibly a false positive due to having at least
* GUP_PIN_COUNTING_BIAS worth of normal folio references".
*
* False positives are OK, because: a) it's unlikely for a folio to
* get that many refcounts, and b) all the callers of this routine are
* expected to be able to deal gracefully with a false positive.
*
* For most large folios, the result will be exactly correct. That's because
* we have more tracking data available: the _pincount field is used
* instead of the GUP_PIN_COUNTING_BIAS scheme.
*
* For more information, please see Documentation/core-api/pin_user_pages.rst.
*
* Return: True, if it is likely that the folio has been "dma-pinned".
* False, if the folio is definitely not dma-pinned.
*/
static inline bool folio_maybe_dma_pinned(struct folio *folio)
{
if (folio_has_pincount(folio))
return atomic_read(&folio->_pincount) > 0;
/*
* folio_ref_count() is signed. If that refcount overflows, then
* folio_ref_count() returns a negative value, and callers will avoid
* further incrementing the refcount.
*
* Here, for that overflow case, use the sign bit to count a little
* bit higher via unsigned math, and thus still get an accurate result.
*/
return ((unsigned int)folio_ref_count(folio)) >=
GUP_PIN_COUNTING_BIAS;
}
/*
* This should most likely only be called during fork() to see whether we
* should break the cow immediately for an anon page on the src mm.
*
* The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
*/
static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
struct folio *folio)
{
VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
return false;
return folio_maybe_dma_pinned(folio);
}
/**
* is_zero_page - Query if a page is a zero page
* @page: The page to query
*
* This returns true if @page is one of the permanent zero pages.
*/
static inline bool is_zero_page(const struct page *page)
{
return is_zero_pfn(page_to_pfn(page));
}
/**
* is_zero_folio - Query if a folio is a zero page
* @folio: The folio to query
*
* This returns true if @folio is one of the permanent zero pages.
*/
static inline bool is_zero_folio(const struct folio *folio)
{
return is_zero_page(&folio->page);
}
/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */
#ifdef CONFIG_MIGRATION
static inline bool folio_is_longterm_pinnable(struct folio *folio)
{
#ifdef CONFIG_CMA
int mt = folio_migratetype(folio);
if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
return false;
#endif
/* The zero page can be "pinned" but gets special handling. */
if (is_zero_folio(folio))
return true;
/* Coherent device memory must always allow eviction. */
if (folio_is_device_coherent(folio))
return false;
/*
* Filesystems can only tolerate transient delays to truncate and
* hole-punch operations
*/
if (folio_is_fsdax(folio))
return false;
/* Otherwise, non-movable zone folios can be pinned. */
return !folio_is_zone_movable(folio);
}
#else
static inline bool folio_is_longterm_pinnable(struct folio *folio)
{
return true;
}
#endif
static inline void set_page_zone(struct page *page, enum zone_type zone)
{
page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}
static inline void set_page_node(struct page *page, unsigned long node)
{
page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
}
static inline void set_page_links(struct page *page, enum zone_type zone,
unsigned long node, unsigned long pfn)
{
set_page_zone(page, zone);
set_page_node(page, node);
#ifdef SECTION_IN_PAGE_FLAGS
set_page_section(page, pfn_to_section_nr(pfn));
#endif
}
/**
* folio_nr_pages - The number of pages in the folio.
* @folio: The folio.
*
* Return: A positive power of two.
*/
static inline long folio_nr_pages(const struct folio *folio)
{
if (!folio_test_large(folio))
return 1;
return folio_large_nr_pages(folio);
}
/* Only hugetlbfs can allocate folios larger than MAX_ORDER */
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
#define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER)
#else
#define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES
#endif
/*
* compound_nr() returns the number of pages in this potentially compound
* page. compound_nr() can be called on a tail page, and is defined to
* return 1 in that case.
*/
static inline long compound_nr(struct page *page)
{
struct folio *folio = (struct folio *)page;
if (!test_bit(PG_head, &folio->flags))
return 1;
return folio_large_nr_pages(folio);
}
/**
* thp_nr_pages - The number of regular pages in this huge page.
* @page: The head page of a huge page.
*/
static inline long thp_nr_pages(struct page *page)
{
return folio_nr_pages((struct folio *)page);
}
/**
* folio_next - Move to the next physical folio.
* @folio: The folio we're currently operating on.
*
* If you have physically contiguous memory which may span more than
* one folio (eg a &struct bio_vec), use this function to move from one
* folio to the next. Do not use it if the memory is only virtually
* contiguous as the folios are almost certainly not adjacent to each
* other. This is the folio equivalent to writing ``page++``.
*
* Context: We assume that the folios are refcounted and/or locked at a
* higher level and do not adjust the reference counts.
* Return: The next struct folio.
*/
static inline struct folio *folio_next(struct folio *folio)
{
return (struct folio *)folio_page(folio, folio_nr_pages(folio));
}
/**
* folio_shift - The size of the memory described by this folio.
* @folio: The folio.
*
* A folio represents a number of bytes which is a power-of-two in size.
* This function tells you which power-of-two the folio is. See also
* folio_size() and folio_order().
*
* Context: The caller should have a reference on the folio to prevent
* it from being split. It is not necessary for the folio to be locked.
* Return: The base-2 logarithm of the size of this folio.
*/
static inline unsigned int folio_shift(const struct folio *folio)
{
return PAGE_SHIFT + folio_order(folio);
}
/**
* folio_size - The number of bytes in a folio.
* @folio: The folio.
*
* Context: The caller should have a reference on the folio to prevent
* it from being split. It is not necessary for the folio to be locked.
* Return: The number of bytes in this folio.
*/
static inline size_t folio_size(const struct folio *folio)
{
return PAGE_SIZE << folio_order(folio);
}
/**
* folio_maybe_mapped_shared - Whether the folio is mapped into the page
* tables of more than one MM
* @folio: The folio.
*
* This function checks if the folio maybe currently mapped into more than one
* MM ("maybe mapped shared"), or if the folio is certainly mapped into a single
* MM ("mapped exclusively").
*
* For KSM folios, this function also returns "mapped shared" when a folio is
* mapped multiple times into the same MM, because the individual page mappings
* are independent.
*
* For small anonymous folios and anonymous hugetlb folios, the return
* value will be exactly correct: non-KSM folios can only be mapped at most once
* into an MM, and they cannot be partially mapped. KSM folios are
* considered shared even if mapped multiple times into the same MM.
*
* For other folios, the result can be fuzzy:
* #. For partially-mappable large folios (THP), the return value can wrongly
* indicate "mapped shared" (false positive) if a folio was mapped by
* more than two MMs at one point in time.
* #. For pagecache folios (including hugetlb), the return value can wrongly
* indicate "mapped shared" (false positive) when two VMAs in the same MM
* cover the same file range.
*
* Further, this function only considers current page table mappings that
* are tracked using the folio mapcount(s).
*
* This function does not consider:
* #. If the folio might get mapped in the (near) future (e.g., swapcache,
* pagecache, temporary unmapping for migration).
* #. If the folio is mapped differently (VM_PFNMAP).
* #. If hugetlb page table sharing applies. Callers might want to check
* hugetlb_pmd_shared().
*
* Return: Whether the folio is estimated to be mapped into more than one MM.
*/
static inline bool folio_maybe_mapped_shared(struct folio *folio)
{
int mapcount = folio_mapcount(folio);
/* Only partially-mappable folios require more care. */
if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio)))
return mapcount > 1;
/*
* vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ...
* simply assume "mapped shared", nobody should really care
* about this for arbitrary kernel allocations.
*/
if (!IS_ENABLED(CONFIG_MM_ID))
return true;
/*
* A single mapping implies "mapped exclusively", even if the
* folio flag says something different: it's easier to handle this
* case here instead of on the RMAP hot path.
*/
if (mapcount <= 1)
return false;
return folio_test_large_maybe_mapped_shared(folio);
}
#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
static inline int arch_make_folio_accessible(struct folio *folio)
{
return 0;
}
#endif
/*
* Some inline functions in vmstat.h depend on page_zone()
*/
#include <linux/vmstat.h>
#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#define HASHED_PAGE_VIRTUAL
#endif
#if defined(WANT_PAGE_VIRTUAL)
static inline void *page_address(const struct page *page)
{
return page->virtual;
}
static inline void set_page_address(struct page *page, void *address)
{
page->virtual = address;
}
#define page_address_init() do { } while(0)
#endif
#if defined(HASHED_PAGE_VIRTUAL)
void *page_address(const struct page *page);
void set_page_address(struct page *page, void *virtual);
void page_address_init(void);
#endif
static __always_inline void *lowmem_page_address(const struct page *page)
{
return page_to_virt(page);
}
#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
#define page_address(page) lowmem_page_address(page)
#define set_page_address(page, address) do { } while(0)
#define page_address_init() do { } while(0)
#endif
static inline void *folio_address(const struct folio *folio)
{ return page_address(&folio->page);
}
/*
* Return true only if the page has been allocated with
* ALLOC_NO_WATERMARKS and the low watermark was not
* met implying that the system is under some pressure.
*/
static inline bool page_is_pfmemalloc(const struct page *page)
{
/*
* lru.next has bit 1 set if the page is allocated from the
* pfmemalloc reserves. Callers may simply overwrite it if
* they do not need to preserve that information.
*/
return (uintptr_t)page->lru.next & BIT(1);
}
/*
* Return true only if the folio has been allocated with
* ALLOC_NO_WATERMARKS and the low watermark was not
* met implying that the system is under some pressure.
*/
static inline bool folio_is_pfmemalloc(const struct folio *folio)
{
/*
* lru.next has bit 1 set if the page is allocated from the
* pfmemalloc reserves. Callers may simply overwrite it if
* they do not need to preserve that information.
*/
return (uintptr_t)folio->lru.next & BIT(1);
}
/*
* Only to be called by the page allocator on a freshly allocated
* page.
*/
static inline void set_page_pfmemalloc(struct page *page)
{
page->lru.next = (void *)BIT(1);
}
static inline void clear_page_pfmemalloc(struct page *page)
{
page->lru.next = NULL;
}
/*
* Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
*/
extern void pagefault_out_of_memory(void);
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1))
#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1))
/*
* Parameter block passed down to zap_pte_range in exceptional cases.
*/
struct zap_details {
struct folio *single_folio; /* Locked folio to be unmapped */
bool even_cows; /* Zap COWed private pages too? */
bool reclaim_pt; /* Need reclaim page tables? */
zap_flags_t zap_flags; /* Extra flags for zapping */
};
/*
* Whether to drop the pte markers, for example, the uffd-wp information for
* file-backed memory. This should only be specified when we will completely
* drop the page in the mm, either by truncation or unmapping of the vma. By
* default, the flag is not set.
*/
#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0))
/* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */
#define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1))
#ifdef CONFIG_SCHED_MM_CID
void sched_mm_cid_before_execve(struct task_struct *t);
void sched_mm_cid_after_execve(struct task_struct *t);
void sched_mm_cid_fork(struct task_struct *t);
void sched_mm_cid_exit_signals(struct task_struct *t);
static inline int task_mm_cid(struct task_struct *t)
{
return t->mm_cid;
}
#else
static inline void sched_mm_cid_before_execve(struct task_struct *t) { }
static inline void sched_mm_cid_after_execve(struct task_struct *t) { }
static inline void sched_mm_cid_fork(struct task_struct *t) { }
static inline void sched_mm_cid_exit_signals(struct task_struct *t) { }
static inline int task_mm_cid(struct task_struct *t)
{
/*
* Use the processor id as a fall-back when the mm cid feature is
* disabled. This provides functional per-cpu data structure accesses
* in user-space, althrough it won't provide the memory usage benefits.
*/
return raw_smp_processor_id();
}
#endif
#ifdef CONFIG_MMU
extern bool can_do_mlock(void);
#else
static inline bool can_do_mlock(void) { return false; }
#endif
extern int user_shm_lock(size_t, struct ucounts *);
extern void user_shm_unlock(size_t, struct ucounts *);
struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
pte_t pte);
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte);
struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd);
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd);
void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details);
static inline void zap_vma_pages(struct vm_area_struct *vma)
{
zap_page_range_single(vma, vma->vm_start,
vma->vm_end - vma->vm_start, NULL);
}
void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
struct vm_area_struct *start_vma, unsigned long start,
unsigned long end, unsigned long tree_end, bool mm_wr_locked);
struct mmu_notifier_range;
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
int
copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write);
struct follow_pfnmap_args {
/**
* Inputs:
* @vma: Pointer to @vm_area_struct struct
* @address: the virtual address to walk
*/
struct vm_area_struct *vma;
unsigned long address;
/**
* Internals:
*
* The caller shouldn't touch any of these.
*/
spinlock_t *lock;
pte_t *ptep;
/**
* Outputs:
*
* @pfn: the PFN of the address
* @addr_mask: address mask covering pfn
* @pgprot: the pgprot_t of the mapping
* @writable: whether the mapping is writable
* @special: whether the mapping is a special mapping (real PFN maps)
*/
unsigned long pfn;
unsigned long addr_mask;
pgprot_t pgprot;
bool writable;
bool special;
};
int follow_pfnmap_start(struct follow_pfnmap_args *args);
void follow_pfnmap_end(struct follow_pfnmap_args *args);
extern void truncate_pagecache(struct inode *inode, loff_t new);
extern void truncate_setsize(struct inode *inode, loff_t newsize);
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
int generic_error_remove_folio(struct address_space *mapping,
struct folio *folio);
struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
unsigned long address, struct pt_regs *regs);
#ifdef CONFIG_MMU
extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
struct pt_regs *regs);
extern int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows);
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
#else
static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
struct pt_regs *regs)
{
/* should never happen if there's no MMU */
BUG();
return VM_FAULT_SIGBUS;
}
static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
unsigned int fault_flags, bool *unlocked)
{
/* should never happen if there's no MMU */
BUG();
return -EFAULT;
}
static inline void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows) { }
static inline void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows) { }
#endif
static inline void unmap_shared_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen)
{
unmap_mapping_range(mapping, holebegin, holelen, 0);
}
static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
unsigned long addr);
extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags);
extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags);
#ifdef CONFIG_BPF_SYSCALL
extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags);
#endif
long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked);
long pin_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked);
/*
* Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT.
*/
static inline struct page *get_user_page_vma_remote(struct mm_struct *mm,
unsigned long addr,
int gup_flags,
struct vm_area_struct **vmap)
{
struct page *page;
struct vm_area_struct *vma;
int got;
if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT)))
return ERR_PTR(-EINVAL);
got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL);
if (got < 0)
return ERR_PTR(got);
vma = vma_lookup(mm, addr);
if (WARN_ON_ONCE(!vma)) {
put_page(page);
return ERR_PTR(-EINVAL);
}
*vmap = vma;
return page;
}
long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages);
long pin_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
struct folio **folios, unsigned int max_folios,
pgoff_t *offset);
int folio_add_pins(struct folio *folio, unsigned int pins);
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
int pin_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
void folio_add_pin(struct folio *folio);
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
struct task_struct *task, bool bypass_rlim);
struct kvec;
struct page *get_dump_page(unsigned long addr, int *locked);
bool folio_mark_dirty(struct folio *folio);
bool folio_mark_dirty_lock(struct folio *folio);
bool set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
int get_cmdline(struct task_struct *task, char *buffer, int buflen);
/*
* Flags used by change_protection(). For now we make it a bitmap so
* that we can pass in multiple flags just like parameters. However
* for now all the callers are only use one of the flags at the same
* time.
*/
/*
* Whether we should manually check if we can map individual PTEs writable,
* because something (e.g., COW, uffd-wp) blocks that from happening for all
* PTEs automatically in a writable mapping.
*/
#define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0)
/* Whether this protection change is for NUMA hints */
#define MM_CP_PROT_NUMA (1UL << 1)
/* Whether this change is for write protecting */
#define MM_CP_UFFD_WP (1UL << 2) /* do wp */
#define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */
#define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \
MM_CP_UFFD_WP_RESOLVE)
bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
pte_t pte);
extern long change_protection(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, unsigned long cp_flags);
extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
struct vm_area_struct *vma, struct vm_area_struct **pprev,
unsigned long start, unsigned long end, unsigned long newflags);
/*
* doesn't attempt to fault and will return short.
*/
int get_user_pages_fast_only(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
static inline bool get_user_page_fast_only(unsigned long addr,
unsigned int gup_flags, struct page **pagep)
{
return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1;
}
/*
* per-process(per-mm_struct) statistics.
*/
static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
{
return percpu_counter_read_positive(&mm->rss_stat[member]);
}
void mm_trace_rss_stat(struct mm_struct *mm, int member);
static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
{
percpu_counter_add(&mm->rss_stat[member], value);
mm_trace_rss_stat(mm, member);
}
static inline void inc_mm_counter(struct mm_struct *mm, int member)
{
percpu_counter_inc(&mm->rss_stat[member]);
mm_trace_rss_stat(mm, member);
}
static inline void dec_mm_counter(struct mm_struct *mm, int member)
{
percpu_counter_dec(&mm->rss_stat[member]);
mm_trace_rss_stat(mm, member);
}
/* Optimized variant when folio is already known not to be anon */
static inline int mm_counter_file(struct folio *folio)
{
if (folio_test_swapbacked(folio))
return MM_SHMEMPAGES;
return MM_FILEPAGES;
}
static inline int mm_counter(struct folio *folio)
{
if (folio_test_anon(folio))
return MM_ANONPAGES;
return mm_counter_file(folio);
}
static inline unsigned long get_mm_rss(struct mm_struct *mm)
{
return get_mm_counter(mm, MM_FILEPAGES) +
get_mm_counter(mm, MM_ANONPAGES) +
get_mm_counter(mm, MM_SHMEMPAGES);
}
static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
{
return max(mm->hiwater_rss, get_mm_rss(mm));
}
static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
{
return max(mm->hiwater_vm, mm->total_vm);
}
static inline void update_hiwater_rss(struct mm_struct *mm)
{
unsigned long _rss = get_mm_rss(mm);
if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss;
}
static inline void update_hiwater_vm(struct mm_struct *mm)
{
if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm;
}
static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
{
mm->hiwater_rss = get_mm_rss(mm);
}
static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
struct mm_struct *mm)
{
unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
if (*maxrss < hiwater_rss)
*maxrss = hiwater_rss;
}
#ifndef CONFIG_ARCH_HAS_PTE_SPECIAL
static inline int pte_special(pte_t pte)
{
return 0;
}
static inline pte_t pte_mkspecial(pte_t pte)
{
return pte;
}
#endif
#ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
static inline bool pmd_special(pmd_t pmd)
{
return false;
}
static inline pmd_t pmd_mkspecial(pmd_t pmd)
{
return pmd;
}
#endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */
#ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
static inline bool pud_special(pud_t pud)
{
return false;
}
static inline pud_t pud_mkspecial(pud_t pud)
{
return pud;
}
#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP
static inline int pte_devmap(pte_t pte)
{
return 0;
}
#endif
extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl);
static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
pte_t *ptep;
__cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl));
return ptep;
}
#ifdef __PAGETABLE_P4D_FOLDED
static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
unsigned long address)
{
return 0;
}
#else
int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
#endif
#if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU)
static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
unsigned long address)
{
return 0;
}
static inline void mm_inc_nr_puds(struct mm_struct *mm) {}
static inline void mm_dec_nr_puds(struct mm_struct *mm) {}
#else
int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
static inline void mm_inc_nr_puds(struct mm_struct *mm)
{
if (mm_pud_folded(mm))
return;
atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
}
static inline void mm_dec_nr_puds(struct mm_struct *mm)
{
if (mm_pud_folded(mm))
return;
atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
}
#endif
#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
unsigned long address)
{
return 0;
}
static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}
static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
#else
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
static inline void mm_inc_nr_pmds(struct mm_struct *mm)
{
if (mm_pmd_folded(mm))
return;
atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
}
static inline void mm_dec_nr_pmds(struct mm_struct *mm)
{
if (mm_pmd_folded(mm))
return;
atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
}
#endif
#ifdef CONFIG_MMU
static inline void mm_pgtables_bytes_init(struct mm_struct *mm)
{
atomic_long_set(&mm->pgtables_bytes, 0);
}
static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
{
return atomic_long_read(&mm->pgtables_bytes);
}
static inline void mm_inc_nr_ptes(struct mm_struct *mm)
{
atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
}
static inline void mm_dec_nr_ptes(struct mm_struct *mm)
{
atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
}
#else
static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {}
static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
{
return 0;
}
static inline void mm_inc_nr_ptes(struct mm_struct *mm) {}
static inline void mm_dec_nr_ptes(struct mm_struct *mm) {}
#endif
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd);
int __pte_alloc_kernel(pmd_t *pmd);
#if defined(CONFIG_MMU)
static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
unsigned long address)
{
return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address);
}
static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
unsigned long address)
{
return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address);
}
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address);
}
#endif /* CONFIG_MMU */
static inline struct ptdesc *virt_to_ptdesc(const void *x)
{
return page_ptdesc(virt_to_page(x));
}
static inline void *ptdesc_to_virt(const struct ptdesc *pt)
{
return page_to_virt(ptdesc_page(pt));
}
static inline void *ptdesc_address(const struct ptdesc *pt)
{
return folio_address(ptdesc_folio(pt));
}
static inline bool pagetable_is_reserved(struct ptdesc *pt)
{
return folio_test_reserved(ptdesc_folio(pt));
}
/**
* pagetable_alloc - Allocate pagetables
* @gfp: GFP flags
* @order: desired pagetable order
*
* pagetable_alloc allocates memory for page tables as well as a page table
* descriptor to describe that memory.
*
* Return: The ptdesc describing the allocated page tables.
*/
static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order)
{
struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order);
return page_ptdesc(page);
}
#define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__))
/**
* pagetable_free - Free pagetables
* @pt: The page table descriptor
*
* pagetable_free frees the memory of all page tables described by a page
* table descriptor and the memory for the descriptor itself.
*/
static inline void pagetable_free(struct ptdesc *pt)
{
struct page *page = ptdesc_page(pt);
__free_pages(page, compound_order(page));
}
#if defined(CONFIG_SPLIT_PTE_PTLOCKS)
#if ALLOC_SPLIT_PTLOCKS
void __init ptlock_cache_init(void);
bool ptlock_alloc(struct ptdesc *ptdesc);
void ptlock_free(struct ptdesc *ptdesc);
static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc)
{
return ptdesc->ptl;
}
#else /* ALLOC_SPLIT_PTLOCKS */
static inline void ptlock_cache_init(void)
{
}
static inline bool ptlock_alloc(struct ptdesc *ptdesc)
{
return true;
}
static inline void ptlock_free(struct ptdesc *ptdesc)
{
}
static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc)
{
return &ptdesc->ptl;
}
#endif /* ALLOC_SPLIT_PTLOCKS */
static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return ptlock_ptr(page_ptdesc(pmd_page(*pmd)));
}
static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
{
BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE));
BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE);
return ptlock_ptr(virt_to_ptdesc(pte));
}
static inline bool ptlock_init(struct ptdesc *ptdesc)
{
/*
* prep_new_page() initialize page->private (and therefore page->ptl)
* with 0. Make sure nobody took it in use in between.
*
* It can happen if arch try to use slab for page table allocation:
* slab code uses page->slab_cache, which share storage with page->ptl.
*/
VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); if (!ptlock_alloc(ptdesc))
return false;
spin_lock_init(ptlock_ptr(ptdesc));
return true;
}
#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */
/*
* We use mm->page_table_lock to guard all pagetable pages of the mm.
*/
static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return &mm->page_table_lock;
}
static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
{
return &mm->page_table_lock;
}
static inline void ptlock_cache_init(void) {}
static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
static inline void ptlock_free(struct ptdesc *ptdesc) {}
#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
static inline void __pagetable_ctor(struct ptdesc *ptdesc)
{
struct folio *folio = ptdesc_folio(ptdesc);
__folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE);
}
static inline void pagetable_dtor(struct ptdesc *ptdesc)
{
struct folio *folio = ptdesc_folio(ptdesc);
ptlock_free(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE);
}
static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
{ pagetable_dtor(ptdesc); pagetable_free(ptdesc);
}
static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc)
{
if (!ptlock_init(ptdesc))
return false;
__pagetable_ctor(ptdesc);
return true;
}
pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr,
pmd_t *pmdvalp)
{
pte_t *pte;
__cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp));
return pte;
}
static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr)
{
return __pte_offset_map(pmd, addr, NULL);
}
pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp);
static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp)
{
pte_t *pte;
__cond_lock(RCU, __cond_lock(*ptlp,
pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)));
return pte;
}
pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp);
pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, pmd_t *pmdvalp,
spinlock_t **ptlp);
#define pte_unmap_unlock(pte, ptl) do { \
spin_unlock(ptl); \
pte_unmap(pte); \
} while (0)
#define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd))
#define pte_alloc_map(mm, pmd, address) \
(pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address))
#define pte_alloc_map_lock(mm, pmd, address, ptlp) \
(pte_alloc(mm, pmd) ? \
NULL : pte_offset_map_lock(mm, pmd, address, ptlp))
#define pte_alloc_kernel(pmd, address) \
((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
NULL: pte_offset_kernel(pmd, address))
#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
static inline struct page *pmd_pgtable_page(pmd_t *pmd)
{
unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
return virt_to_page((void *)((unsigned long) pmd & mask));
}
static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd)
{
return page_ptdesc(pmd_pgtable_page(pmd));
}
static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return ptlock_ptr(pmd_ptdesc(pmd));
}
static inline bool pmd_ptlock_init(struct ptdesc *ptdesc)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
ptdesc->pmd_huge_pte = NULL;
#endif
return ptlock_init(ptdesc);
}
#define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte)
#else
static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return &mm->page_table_lock;
}
static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; }
#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
#endif
static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
{
spinlock_t *ptl = pmd_lockptr(mm, pmd);
spin_lock(ptl);
return ptl;
}
static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc)
{
if (!pmd_ptlock_init(ptdesc))
return false;
ptdesc_pmd_pts_init(ptdesc);
__pagetable_ctor(ptdesc);
return true;
}
/*
* No scalability reason to split PUD locks yet, but follow the same pattern
* as the PMD locks to make it easier if we decide to. The VM should not be
* considered ready to switch to split PUD locks yet; there may be places
* which need to be converted from page_table_lock.
*/
static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud)
{
return &mm->page_table_lock;
}
static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
{
spinlock_t *ptl = pud_lockptr(mm, pud);
spin_lock(ptl);
return ptl;
}
static inline void pagetable_pud_ctor(struct ptdesc *ptdesc)
{
__pagetable_ctor(ptdesc);
}
static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc)
{
__pagetable_ctor(ptdesc);
}
static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc)
{
__pagetable_ctor(ptdesc);
}
extern void __init pagecache_init(void);
extern void free_initmem(void);
/*
* Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK)
* into the buddy system. The freed pages will be poisoned with pattern
* "poison" if it's within range [0, UCHAR_MAX].
* Return pages freed into the buddy system.
*/
extern unsigned long free_reserved_area(void *start, void *end,
int poison, const char *s);
extern void adjust_managed_page_count(struct page *page, long count);
extern void reserve_bootmem_region(phys_addr_t start,
phys_addr_t end, int nid);
/* Free the reserved page into the buddy system, so it gets managed. */
void free_reserved_page(struct page *page);
static inline void mark_page_reserved(struct page *page)
{
SetPageReserved(page);
adjust_managed_page_count(page, -1);
}
static inline void free_reserved_ptdesc(struct ptdesc *pt)
{
free_reserved_page(ptdesc_page(pt));
}
/*
* Default method to free all the __init memory into the buddy system.
* The freed pages will be poisoned with pattern "poison" if it's within
* range [0, UCHAR_MAX].
* Return pages freed into the buddy system.
*/
static inline unsigned long free_initmem_default(int poison)
{
extern char __init_begin[], __init_end[];
return free_reserved_area(&__init_begin, &__init_end,
poison, "unused kernel image (initmem)");
}
static inline unsigned long get_num_physpages(void)
{
int nid;
unsigned long phys_pages = 0;
for_each_online_node(nid)
phys_pages += node_present_pages(nid);
return phys_pages;
}
/*
* Using memblock node mappings, an architecture may initialise its
* zones, allocate the backing mem_map and account for memory holes in an
* architecture independent manner.
*
* An architecture is expected to register range of page frames backed by
* physical memory with memblock_add[_node]() before calling
* free_area_init() passing in the PFN each zone ends at. At a basic
* usage, an architecture is expected to do something like
*
* unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
* max_highmem_pfn};
* for_each_valid_physical_page_range()
* memblock_add_node(base, size, nid, MEMBLOCK_NONE)
* free_area_init(max_zone_pfns);
*/
void free_area_init(unsigned long *max_zone_pfn);
unsigned long node_map_pfn_alignment(void);
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn);
extern void get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn);
#ifndef CONFIG_NUMA
static inline int early_pfn_to_nid(unsigned long pfn)
{
return 0;
}
#else
/* please see mm/page_alloc.c */
extern int __meminit early_pfn_to_nid(unsigned long pfn);
#endif
extern void mem_init(void);
extern void __init mmap_init(void);
extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx);
static inline void show_mem(void)
{
__show_mem(0, NULL, MAX_NR_ZONES - 1);
}
extern long si_mem_available(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
extern __printf(3, 4)
void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
extern void setup_per_cpu_pageset(void);
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
/* interval_tree.c */
void vma_interval_tree_insert(struct vm_area_struct *node,
struct rb_root_cached *root);
void vma_interval_tree_insert_after(struct vm_area_struct *node,
struct vm_area_struct *prev,
struct rb_root_cached *root);
void vma_interval_tree_remove(struct vm_area_struct *node,
struct rb_root_cached *root);
struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start, unsigned long last);
struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
unsigned long start, unsigned long last);
#define vma_interval_tree_foreach(vma, root, start, last) \
for (vma = vma_interval_tree_iter_first(root, start, last); \
vma; vma = vma_interval_tree_iter_next(vma, start, last))
void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
struct rb_root_cached *root);
void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
struct rb_root_cached *root);
struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root_cached *root,
unsigned long start, unsigned long last);
struct anon_vma_chain *anon_vma_interval_tree_iter_next(
struct anon_vma_chain *node, unsigned long start, unsigned long last);
#ifdef CONFIG_DEBUG_VM_RB
void anon_vma_interval_tree_verify(struct anon_vma_chain *node);
#endif
#define anon_vma_interval_tree_foreach(avc, root, start, last) \
for (avc = anon_vma_interval_tree_iter_first(root, start, last); \
avc; avc = anon_vma_interval_tree_iter_next(avc, start, last))
/* mmap.c */
extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void exit_mmap(struct mm_struct *);
int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift);
bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, bool write);
static inline int check_data_rlimit(unsigned long rlim,
unsigned long new,
unsigned long start,
unsigned long end_data,
unsigned long start_data)
{
if (rlim < RLIM_INFINITY) {
if (((new - start) + (end_data - start_data)) > rlim)
return -ENOSPC;
}
return 0;
}
extern int mm_take_all_locks(struct mm_struct *mm);
extern void mm_drop_all_locks(struct mm_struct *mm);
extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern struct file *get_mm_exe_file(struct mm_struct *mm);
extern struct file *get_task_exe_file(struct task_struct *task);
extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);
extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
extern bool vma_is_special_mapping(const struct vm_area_struct *vma,
const struct vm_special_mapping *sm);
extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
unsigned long addr, unsigned long len,
unsigned long flags,
const struct vm_special_mapping *spec);
unsigned long randomize_stack_top(unsigned long stack_top);
unsigned long randomize_page(unsigned long start, unsigned long range);
unsigned long
__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags);
static inline unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
}
extern unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
struct list_head *uf);
extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
unsigned long start, size_t len, struct list_head *uf,
bool unlock);
int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct mm_struct *mm, unsigned long start,
unsigned long end, struct list_head *uf, bool unlock);
extern int do_munmap(struct mm_struct *, unsigned long, size_t,
struct list_head *uf);
extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
#ifdef CONFIG_MMU
extern int __mm_populate(unsigned long addr, unsigned long len,
int ignore_errors);
static inline void mm_populate(unsigned long addr, unsigned long len)
{
/* Ignore errors */
(void) __mm_populate(addr, len, 1);
}
#else
static inline void mm_populate(unsigned long addr, unsigned long len) {}
#endif
/* This takes the mm semaphore itself */
extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
struct vm_unmapped_area_info {
#define VM_UNMAPPED_AREA_TOPDOWN 1
unsigned long flags;
unsigned long length;
unsigned long low_limit;
unsigned long high_limit;
unsigned long align_mask;
unsigned long align_offset;
unsigned long start_gap;
};
extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info);
/* truncate.c */
extern void truncate_inode_pages(struct address_space *, loff_t);
extern void truncate_inode_pages_range(struct address_space *,
loff_t lstart, loff_t lend);
extern void truncate_inode_pages_final(struct address_space *);
/* generic vm_area_ops exported for stackable file systems */
extern vm_fault_t filemap_fault(struct vm_fault *vmf);
extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
extern unsigned long stack_guard_gap;
/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address);
struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr);
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
struct vm_area_struct **pprev);
/*
* Look up the first VMA which intersects the interval [start_addr, end_addr)
* NULL if none. Assume start_addr < end_addr.
*/
struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
unsigned long start_addr, unsigned long end_addr);
/**
* vma_lookup() - Find a VMA at a specific address
* @mm: The process address space.
* @addr: The user address.
*
* Return: The vm_area_struct at the given address, %NULL otherwise.
*/
static inline
struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
{
return mtree_load(&mm->mm_mt, addr);
}
static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma)
{
if (vma->vm_flags & VM_GROWSDOWN)
return stack_guard_gap;
/* See reasoning around the VM_SHADOW_STACK definition */
if (vma->vm_flags & VM_SHADOW_STACK)
return PAGE_SIZE;
return 0;
}
static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
{
unsigned long gap = stack_guard_start_gap(vma);
unsigned long vm_start = vma->vm_start;
vm_start -= gap;
if (vm_start > vma->vm_start)
vm_start = 0;
return vm_start;
}
static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
{
unsigned long vm_end = vma->vm_end;
if (vma->vm_flags & VM_GROWSUP) {
vm_end += stack_guard_gap;
if (vm_end < vma->vm_end)
vm_end = -PAGE_SIZE;
}
return vm_end;
}
static inline unsigned long vma_pages(struct vm_area_struct *vma)
{
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}
/* Look up the first VMA which exactly match the interval vm_start ... vm_end */
static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
unsigned long vm_start, unsigned long vm_end)
{
struct vm_area_struct *vma = vma_lookup(mm, vm_start);
if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end))
vma = NULL;
return vma;
}
static inline bool range_in_vma(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
return (vma && vma->vm_start <= start && end <= vma->vm_end);
}
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(unsigned long vm_flags);
void vma_set_page_prot(struct vm_area_struct *vma);
#else
static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
return __pgprot(0);
}
static inline void vma_set_page_prot(struct vm_area_struct *vma)
{
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
}
#endif
void vma_set_file(struct vm_area_struct *vma, struct file *file);
#ifdef CONFIG_NUMA_BALANCING
unsigned long change_prot_numa(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#endif
struct vm_area_struct *find_extend_vma_locked(struct mm_struct *,
unsigned long addr);
int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t);
int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot);
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num);
int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
bool write);
vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, pgprot_t pgprot);
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn);
vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn);
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
unsigned long addr, struct page *page)
{
int err = vm_insert_page(vma, addr, page);
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err < 0 && err != -EBUSY)
return VM_FAULT_SIGBUS;
return VM_FAULT_NOPAGE;
}
#ifndef io_remap_pfn_range
static inline int io_remap_pfn_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long pfn,
unsigned long size, pgprot_t prot)
{
return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
}
#endif
static inline vm_fault_t vmf_error(int err)
{
if (err == -ENOMEM)
return VM_FAULT_OOM;
else if (err == -EHWPOISON)
return VM_FAULT_HWPOISON;
return VM_FAULT_SIGBUS;
}
/*
* Convert errno to return value for ->page_mkwrite() calls.
*
* This should eventually be merged with vmf_error() above, but will need a
* careful audit of all vmf_error() callers.
*/
static inline vm_fault_t vmf_fs_error(int err)
{
if (err == 0)
return VM_FAULT_LOCKED;
if (err == -EFAULT || err == -EAGAIN)
return VM_FAULT_NOPAGE;
if (err == -ENOMEM)
return VM_FAULT_OOM;
/* -ENOSPC, -EDQUOT, -EIO ... */
return VM_FAULT_SIGBUS;
}
static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
{
if (vm_fault & VM_FAULT_OOM)
return -ENOMEM;
if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT;
if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
return -EFAULT;
return 0;
}
/*
* Indicates whether GUP can follow a PROT_NONE mapped page, or whether
* a (NUMA hinting) fault is required.
*/
static inline bool gup_can_follow_protnone(struct vm_area_struct *vma,
unsigned int flags)
{
/*
* If callers don't want to honor NUMA hinting faults, no need to
* determine if we would actually have to trigger a NUMA hinting fault.
*/
if (!(flags & FOLL_HONOR_NUMA_FAULT))
return true;
/*
* NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs.
*
* Requiring a fault here even for inaccessible VMAs would mean that
* FOLL_FORCE cannot make any progress, because handle_mm_fault()
* refuses to process NUMA hinting faults in inaccessible VMAs.
*/
return !vma_is_accessible(vma);
}
typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size, pte_fn_t fn, void *data);
extern int apply_to_existing_page_range(struct mm_struct *mm,
unsigned long address, unsigned long size,
pte_fn_t fn, void *data);
#ifdef CONFIG_PAGE_POISONING
extern void __kernel_poison_pages(struct page *page, int numpages);
extern void __kernel_unpoison_pages(struct page *page, int numpages);
extern bool _page_poisoning_enabled_early;
DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled);
static inline bool page_poisoning_enabled(void)
{
return _page_poisoning_enabled_early;
}
/*
* For use in fast paths after init_mem_debugging() has run, or when a
* false negative result is not harmful when called too early.
*/
static inline bool page_poisoning_enabled_static(void)
{
return static_branch_unlikely(&_page_poisoning_enabled);
}
static inline void kernel_poison_pages(struct page *page, int numpages)
{
if (page_poisoning_enabled_static())
__kernel_poison_pages(page, numpages);
}
static inline void kernel_unpoison_pages(struct page *page, int numpages)
{
if (page_poisoning_enabled_static())
__kernel_unpoison_pages(page, numpages);
}
#else
static inline bool page_poisoning_enabled(void) { return false; }
static inline bool page_poisoning_enabled_static(void) { return false; }
static inline void __kernel_poison_pages(struct page *page, int nunmpages) { }
static inline void kernel_poison_pages(struct page *page, int numpages) { }
static inline void kernel_unpoison_pages(struct page *page, int numpages) { }
#endif
DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
static inline bool want_init_on_alloc(gfp_t flags)
{
if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
&init_on_alloc))
return true;
return flags & __GFP_ZERO;
}
DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
static inline bool want_init_on_free(void)
{
return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
&init_on_free);
}
extern bool _debug_pagealloc_enabled_early;
DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
static inline bool debug_pagealloc_enabled(void)
{
return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
_debug_pagealloc_enabled_early;
}
/*
* For use in fast paths after mem_debugging_and_hardening_init() has run,
* or when a false negative result is not harmful when called too early.
*/
static inline bool debug_pagealloc_enabled_static(void)
{
if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC))
return false;
return static_branch_unlikely(&_debug_pagealloc_enabled);
}
/*
* To support DEBUG_PAGEALLOC architecture must ensure that
* __kernel_map_pages() never fails
*/
extern void __kernel_map_pages(struct page *page, int numpages, int enable);
#ifdef CONFIG_DEBUG_PAGEALLOC
static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
{
if (debug_pagealloc_enabled_static())
__kernel_map_pages(page, numpages, 1);
}
static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
{
if (debug_pagealloc_enabled_static())
__kernel_map_pages(page, numpages, 0);
}
extern unsigned int _debug_guardpage_minorder;
DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
static inline unsigned int debug_guardpage_minorder(void)
{
return _debug_guardpage_minorder;
}
static inline bool debug_guardpage_enabled(void)
{
return static_branch_unlikely(&_debug_guardpage_enabled);
}
static inline bool page_is_guard(struct page *page)
{
if (!debug_guardpage_enabled())
return false;
return PageGuard(page);
}
bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order);
static inline bool set_page_guard(struct zone *zone, struct page *page,
unsigned int order)
{
if (!debug_guardpage_enabled())
return false;
return __set_page_guard(zone, page, order);
}
void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order);
static inline void clear_page_guard(struct zone *zone, struct page *page,
unsigned int order)
{
if (!debug_guardpage_enabled())
return;
__clear_page_guard(zone, page, order);
}
#else /* CONFIG_DEBUG_PAGEALLOC */
static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
static inline unsigned int debug_guardpage_minorder(void) { return 0; }
static inline bool debug_guardpage_enabled(void) { return false; }
static inline bool page_is_guard(struct page *page) { return false; }
static inline bool set_page_guard(struct zone *zone, struct page *page,
unsigned int order) { return false; }
static inline void clear_page_guard(struct zone *zone, struct page *page,
unsigned int order) {}
#endif /* CONFIG_DEBUG_PAGEALLOC */
#ifdef __HAVE_ARCH_GATE_AREA
extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
extern int in_gate_area_no_mm(unsigned long addr);
extern int in_gate_area(struct mm_struct *mm, unsigned long addr);
#else
static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
return NULL;
}
static inline int in_gate_area_no_mm(unsigned long addr) { return 0; }
static inline int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
return 0;
}
#endif /* __HAVE_ARCH_GATE_AREA */
extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
void drop_slab(void);
#ifndef CONFIG_MMU
#define randomize_va_space 0
#else
extern int randomize_va_space;
#endif
const char * arch_vma_name(struct vm_area_struct *vma);
#ifdef CONFIG_MMU
void print_vma_addr(char *prefix, unsigned long rip);
#else
static inline void print_vma_addr(char *prefix, unsigned long rip)
{
}
#endif
void *sparse_buffer_alloc(unsigned long size);
unsigned long section_map_size(void);
struct page * __populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
struct dev_pagemap *pgmap);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
struct vmem_altmap *altmap, unsigned long ptpfn,
unsigned long flags);
void *vmemmap_alloc_block(unsigned long size, int node);
struct vmem_altmap;
void *vmemmap_alloc_block_buf(unsigned long size, int node,
struct vmem_altmap *altmap);
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
void vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
unsigned long addr, unsigned long next);
int vmemmap_check_pmd(pmd_t *pmd, int node,
unsigned long addr, unsigned long next);
int vmemmap_populate_basepages(unsigned long start, unsigned long end,
int node, struct vmem_altmap *altmap);
int vmemmap_populate_hugepages(unsigned long start, unsigned long end,
int node, struct vmem_altmap *altmap);
int vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap);
int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node,
unsigned long headsize);
int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node,
unsigned long headsize);
void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node,
unsigned long headsize);
void vmemmap_populate_print_last(void);
#ifdef CONFIG_MEMORY_HOTPLUG
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap);
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
/* number of pfns from base where pfn_to_page() is valid */
if (altmap)
return altmap->reserve + altmap->free;
return 0;
}
static inline void vmem_altmap_free(struct vmem_altmap *altmap,
unsigned long nr_pfns)
{
altmap->alloc -= nr_pfns;
}
#else
static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
return 0;
}
static inline void vmem_altmap_free(struct vmem_altmap *altmap,
unsigned long nr_pfns)
{
}
#endif
#define VMEMMAP_RESERVE_NR 2
#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
struct dev_pagemap *pgmap)
{
unsigned long nr_pages;
unsigned long nr_vmemmap_pages;
if (!pgmap || !is_power_of_2(sizeof(struct page)))
return false;
nr_pages = pgmap_vmemmap_nr(pgmap);
nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT);
/*
* For vmemmap optimization with DAX we need minimum 2 vmemmap
* pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
*/
return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
}
/*
* If we don't have an architecture override, use the generic rule
*/
#ifndef vmemmap_can_optimize
#define vmemmap_can_optimize __vmemmap_can_optimize
#endif
#else
static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
struct dev_pagemap *pgmap)
{
return false;
}
#endif
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
MF_ACTION_REQUIRED = 1 << 1,
MF_MUST_KILL = 1 << 2,
MF_SOFT_OFFLINE = 1 << 3,
MF_UNPOISON = 1 << 4,
MF_SW_SIMULATED = 1 << 5,
MF_NO_RETRY = 1 << 6,
MF_MEM_PRE_REMOVE = 1 << 7,
};
int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
unsigned long count, int mf_flags);
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
extern atomic_long_t num_poisoned_pages __read_mostly;
extern int soft_offline_page(unsigned long pfn, int flags);
#ifdef CONFIG_MEMORY_FAILURE
/*
* Sysfs entries for memory failure handling statistics.
*/
extern const struct attribute_group memory_failure_attr_group;
extern void memory_failure_queue(unsigned long pfn, int flags);
extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared);
void num_poisoned_pages_inc(unsigned long pfn);
void num_poisoned_pages_sub(unsigned long pfn, long i);
#else
static inline void memory_failure_queue(unsigned long pfn, int flags)
{
}
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared)
{
return 0;
}
static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
}
#endif
#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
extern void memblk_nr_poison_inc(unsigned long pfn);
extern void memblk_nr_poison_sub(unsigned long pfn, long i);
#else
static inline void memblk_nr_poison_inc(unsigned long pfn)
{
}
static inline void memblk_nr_poison_sub(unsigned long pfn, long i)
{
}
#endif
#ifndef arch_memory_failure
static inline int arch_memory_failure(unsigned long pfn, int flags)
{
return -ENXIO;
}
#endif
#ifndef arch_is_platform_page
static inline bool arch_is_platform_page(u64 paddr)
{
return false;
}
#endif
/*
* Error handlers for various types of pages.
*/
enum mf_result {
MF_IGNORED, /* Error: cannot be handled */
MF_FAILED, /* Error: handling failed */
MF_DELAYED, /* Will be handled later */
MF_RECOVERED, /* Successfully recovered */
};
enum mf_action_page_type {
MF_MSG_KERNEL,
MF_MSG_KERNEL_HIGH_ORDER,
MF_MSG_DIFFERENT_COMPOUND,
MF_MSG_HUGE,
MF_MSG_FREE_HUGE,
MF_MSG_GET_HWPOISON,
MF_MSG_UNMAP_FAILED,
MF_MSG_DIRTY_SWAPCACHE,
MF_MSG_CLEAN_SWAPCACHE,
MF_MSG_DIRTY_MLOCKED_LRU,
MF_MSG_CLEAN_MLOCKED_LRU,
MF_MSG_DIRTY_UNEVICTABLE_LRU,
MF_MSG_CLEAN_UNEVICTABLE_LRU,
MF_MSG_DIRTY_LRU,
MF_MSG_CLEAN_LRU,
MF_MSG_TRUNCATED_LRU,
MF_MSG_BUDDY,
MF_MSG_DAX,
MF_MSG_UNSPLIT_THP,
MF_MSG_ALREADY_POISONED,
MF_MSG_UNKNOWN,
};
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
void folio_zero_user(struct folio *folio, unsigned long addr_hint);
int copy_user_large_folio(struct folio *dst, struct folio *src,
unsigned long addr_hint,
struct vm_area_struct *vma);
long copy_folio_from_user(struct folio *dst_folio,
const void __user *usr_src,
bool allow_pagefault);
/**
* vma_is_special_huge - Are transhuge page-table entries considered special?
* @vma: Pointer to the struct vm_area_struct to consider
*
* Whether transhuge page-table entries are considered "special" following
* the definition in vm_normal_page().
*
* Return: true if transhuge page-table entries should be considered special,
* false otherwise.
*/
static inline bool vma_is_special_huge(const struct vm_area_struct *vma)
{
return vma_is_dax(vma) || (vma->vm_file &&
(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#if MAX_NUMNODES > 1
void __init setup_nr_node_ids(void);
#else
static inline void setup_nr_node_ids(void) {}
#endif
extern int memcmp_pages(struct page *page1, struct page *page2);
static inline int pages_identical(struct page *page1, struct page *page2)
{
return !memcmp_pages(page1, page2);
}
#ifdef CONFIG_MAPPING_DIRTY_HELPERS
unsigned long clean_record_shared_mapping_range(struct address_space *mapping,
pgoff_t first_index, pgoff_t nr,
pgoff_t bitmap_pgoff,
unsigned long *bitmap,
pgoff_t *start,
pgoff_t *end);
unsigned long wp_shared_mapping_range(struct address_space *mapping,
pgoff_t first_index, pgoff_t nr);
#endif
#ifdef CONFIG_ANON_VMA_NAME
int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
unsigned long len_in,
struct anon_vma_name *anon_name);
#else
static inline int
madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
unsigned long len_in, struct anon_vma_name *anon_name) {
return 0;
}
#endif
#ifdef CONFIG_UNACCEPTED_MEMORY
bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size);
void accept_memory(phys_addr_t start, unsigned long size);
#else
static inline bool range_contains_unaccepted_memory(phys_addr_t start,
unsigned long size)
{
return false;
}
static inline void accept_memory(phys_addr_t start, unsigned long size)
{
}
#endif
static inline bool pfn_is_unaccepted_memory(unsigned long pfn)
{
return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE);
}
void vma_pgtable_walk_begin(struct vm_area_struct *vma);
void vma_pgtable_walk_end(struct vm_area_struct *vma);
int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size);
int reserve_mem_release_by_name(const char *name);
#ifdef CONFIG_64BIT
int do_mseal(unsigned long start, size_t len_in, unsigned long flags);
#else
static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
{
/* noop on 32 bit */
return 0;
}
#endif
/*
* user_alloc_needs_zeroing checks if a user folio from page allocator needs to
* be zeroed or not.
*/
static inline bool user_alloc_needs_zeroing(void)
{
/*
* for user folios, arch with cache aliasing requires cache flush and
* arc changes folio->flags to make icache coherent with dcache, so
* always return false to make caller use
* clear_user_page()/clear_user_highpage().
*/
return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() ||
!static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
&init_on_alloc);
}
int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
/*
* mseal of userspace process's system mappings.
*/
#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS
#define VM_SEALED_SYSMAP VM_SEALED
#else
#define VM_SEALED_SYSMAP VM_NONE
#endif
#endif /* _LINUX_MM_H */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* This header provides generic wrappers for memory access instrumentation that
* the compiler cannot emit for: KASAN, KCSAN, KMSAN.
*/
#ifndef _LINUX_INSTRUMENTED_H
#define _LINUX_INSTRUMENTED_H
#include <linux/compiler.h>
#include <linux/kasan-checks.h>
#include <linux/kcsan-checks.h>
#include <linux/kmsan-checks.h>
#include <linux/types.h>
/**
* instrument_read - instrument regular read access
* @v: address of access
* @size: size of access
*
* Instrument a regular read access. The instrumentation should be inserted
* before the actual read happens.
*/
static __always_inline void instrument_read(const volatile void *v, size_t size)
{
kasan_check_read(v, size);
kcsan_check_read(v, size);
}
/**
* instrument_write - instrument regular write access
* @v: address of access
* @size: size of access
*
* Instrument a regular write access. The instrumentation should be inserted
* before the actual write happens.
*/
static __always_inline void instrument_write(const volatile void *v, size_t size)
{
kasan_check_write(v, size);
kcsan_check_write(v, size);
}
/**
* instrument_read_write - instrument regular read-write access
* @v: address of access
* @size: size of access
*
* Instrument a regular write access. The instrumentation should be inserted
* before the actual write happens.
*/
static __always_inline void instrument_read_write(const volatile void *v, size_t size)
{
kasan_check_write(v, size);
kcsan_check_read_write(v, size);
}
/**
* instrument_atomic_read - instrument atomic read access
* @v: address of access
* @size: size of access
*
* Instrument an atomic read access. The instrumentation should be inserted
* before the actual read happens.
*/
static __always_inline void instrument_atomic_read(const volatile void *v, size_t size)
{
kasan_check_read(v, size);
kcsan_check_atomic_read(v, size);
}
/**
* instrument_atomic_write - instrument atomic write access
* @v: address of access
* @size: size of access
*
* Instrument an atomic write access. The instrumentation should be inserted
* before the actual write happens.
*/
static __always_inline void instrument_atomic_write(const volatile void *v, size_t size)
{
kasan_check_write(v, size);
kcsan_check_atomic_write(v, size);
}
/**
* instrument_atomic_read_write - instrument atomic read-write access
* @v: address of access
* @size: size of access
*
* Instrument an atomic read-write access. The instrumentation should be
* inserted before the actual write happens.
*/
static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size)
{
kasan_check_write(v, size);
kcsan_check_atomic_read_write(v, size);
}
/**
* instrument_copy_to_user - instrument reads of copy_to_user
* @to: destination address
* @from: source address
* @n: number of bytes to copy
*
* Instrument reads from kernel memory, that are due to copy_to_user (and
* variants). The instrumentation must be inserted before the accesses.
*/
static __always_inline void
instrument_copy_to_user(void __user *to, const void *from, unsigned long n)
{
kasan_check_read(from, n);
kcsan_check_read(from, n);
kmsan_copy_to_user(to, from, n, 0);
}
/**
* instrument_copy_from_user_before - add instrumentation before copy_from_user
* @to: destination address
* @from: source address
* @n: number of bytes to copy
*
* Instrument writes to kernel memory, that are due to copy_from_user (and
* variants). The instrumentation should be inserted before the accesses.
*/
static __always_inline void
instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n)
{
kasan_check_write(to, n);
kcsan_check_write(to, n);
}
/**
* instrument_copy_from_user_after - add instrumentation after copy_from_user
* @to: destination address
* @from: source address
* @n: number of bytes to copy
* @left: number of bytes not copied (as returned by copy_from_user)
*
* Instrument writes to kernel memory, that are due to copy_from_user (and
* variants). The instrumentation should be inserted after the accesses.
*/
static __always_inline void
instrument_copy_from_user_after(const void *to, const void __user *from,
unsigned long n, unsigned long left)
{
kmsan_unpoison_memory(to, n - left);
}
/**
* instrument_memcpy_before - add instrumentation before non-instrumented memcpy
* @to: destination address
* @from: source address
* @n: number of bytes to copy
*
* Instrument memory accesses that happen in custom memcpy implementations. The
* instrumentation should be inserted before the memcpy call.
*/
static __always_inline void instrument_memcpy_before(void *to, const void *from,
unsigned long n)
{
kasan_check_write(to, n);
kasan_check_read(from, n);
kcsan_check_write(to, n);
kcsan_check_read(from, n);
}
/**
* instrument_memcpy_after - add instrumentation after non-instrumented memcpy
* @to: destination address
* @from: source address
* @n: number of bytes to copy
* @left: number of bytes not copied (if known)
*
* Instrument memory accesses that happen in custom memcpy implementations. The
* instrumentation should be inserted after the memcpy call.
*/
static __always_inline void instrument_memcpy_after(void *to, const void *from,
unsigned long n,
unsigned long left)
{
kmsan_memmove(to, from, n - left);
}
/**
* instrument_get_user() - add instrumentation to get_user()-like macros
* @to: destination variable, may not be address-taken
*
* get_user() and friends are fragile, so it may depend on the implementation
* whether the instrumentation happens before or after the data is copied from
* the userspace.
*/
#define instrument_get_user(to) \
({ \
u64 __tmp = (u64)(to); \
kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \
to = __tmp; \
})
/**
* instrument_put_user() - add instrumentation to put_user()-like macros
* @from: source address
* @ptr: userspace pointer to copy to
* @size: number of bytes to copy
*
* put_user() and friends are fragile, so it may depend on the implementation
* whether the instrumentation happens before or after the data is copied from
* the userspace.
*/
#define instrument_put_user(from, ptr, size) \
({ \
kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \
})
#endif /* _LINUX_INSTRUMENTED_H */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
*/
#include <linux/dcache.h>
#include <linux/fs.h>
#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/srcu.h>
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
/*
* Clear all of the marks on an inode when it is being evicted from core
*/
void __fsnotify_inode_delete(struct inode *inode)
{
fsnotify_clear_marks_by_inode(inode);
}
EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);
void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
{
fsnotify_clear_marks_by_mount(mnt);
}
void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
{
fsnotify_clear_marks_by_mntns(mntns);
}
/**
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
* @sb: superblock being unmounted.
*
* Called during unmount with no locks held, so needs to be safe against
* concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
*/
static void fsnotify_unmount_inodes(struct super_block *sb)
{
struct inode *inode, *iput_inode = NULL;
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
/*
* We cannot __iget() an inode in state I_FREEING,
* I_WILL_FREE, or I_NEW which is fine because by that point
* the inode cannot have any associated watches.
*/
spin_lock(&inode->i_lock);
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
spin_unlock(&inode->i_lock);
continue;
}
/*
* If i_count is zero, the inode cannot have any watches and
* doing an __iget/iput with SB_ACTIVE clear would actually
* evict all inodes with zero i_count from icache which is
* unnecessarily violent and may in fact be illegal to do.
* However, we should have been called /after/ evict_inodes
* removed all zero refcount inodes, in any case. Test to
* be sure.
*/
if (!atomic_read(&inode->i_count)) {
spin_unlock(&inode->i_lock);
continue;
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_list_lock);
iput(iput_inode);
/* for each watch, send FS_UNMOUNT and then remove it */
fsnotify_inode(inode, FS_UNMOUNT);
fsnotify_inode_delete(inode);
iput_inode = inode;
cond_resched();
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&sb->s_inode_list_lock);
iput(iput_inode);
}
void fsnotify_sb_delete(struct super_block *sb)
{
struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
/* Were any marks ever added to any object on this sb? */
if (!sbinfo)
return;
fsnotify_unmount_inodes(sb);
fsnotify_clear_marks_by_sb(sb);
/* Wait for outstanding object references from connectors */
wait_var_event(fsnotify_sb_watched_objects(sb),
!atomic_long_read(fsnotify_sb_watched_objects(sb)));
WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT));
WARN_ON(fsnotify_sb_has_priority_watchers(sb,
FSNOTIFY_PRIO_PRE_CONTENT));
}
void fsnotify_sb_free(struct super_block *sb)
{
kfree(sb->s_fsnotify_info);
}
/*
* Given an inode, first check if we care what happens to our children. Inotify
* and dnotify both tell their parents about events. If we care about any event
* on a child we run all of our children and set a dentry flag saying that the
* parent cares. Thus when an event happens on a child it can quickly tell
* if there is a need to find a parent and send the event to the parent.
*/
void fsnotify_set_children_dentry_flags(struct inode *inode)
{
struct dentry *alias;
if (!S_ISDIR(inode->i_mode))
return;
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
struct dentry *child;
/* run all of the children of the original inode and fix their
* d_flags to indicate parental interest (their parent is the
* original inode) */
spin_lock(&alias->d_lock);
hlist_for_each_entry(child, &alias->d_children, d_sib) {
if (!child->d_inode)
continue;
spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
spin_unlock(&child->d_lock);
}
spin_unlock(&alias->d_lock);
}
spin_unlock(&inode->i_lock);
}
/*
* Lazily clear false positive PARENT_WATCHED flag for child whose parent had
* stopped watching children.
*/
static void fsnotify_clear_child_dentry_flag(struct inode *pinode,
struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
/*
* d_lock is a sufficient barrier to prevent observing a non-watched
* parent state from before the fsnotify_set_children_dentry_flags()
* or fsnotify_update_flags() call that had set PARENT_WATCHED.
*/
if (!fsnotify_inode_watches_children(pinode))
dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
spin_unlock(&dentry->d_lock);
}
/* Are inode/sb/mount interested in parent and name info with this event? */
static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
__u32 mask)
{
__u32 marks_mask = 0;
/* We only send parent/name to inode/sb/mount for events on non-dir */
if (mask & FS_ISDIR)
return false;
/*
* All events that are possible on child can also may be reported with
* parent/name info to inode/sb/mount. Otherwise, a watching parent
* could result in events reported with unexpected name info to sb/mount.
*/
BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
/* Did either inode/sb/mount subscribe for events with parent/name? */
marks_mask |= fsnotify_parent_needed_mask(
READ_ONCE(inode->i_fsnotify_mask));
marks_mask |= fsnotify_parent_needed_mask(
READ_ONCE(inode->i_sb->s_fsnotify_mask));
marks_mask |= fsnotify_parent_needed_mask(mnt_mask);
/* Did they subscribe for this event with parent/name info? */
return mask & marks_mask;
}
/* Are there any inode/mount/sb objects that watch for these events? */
static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
__u32 mask)
{
__u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask |
READ_ONCE(inode->i_sb->s_fsnotify_mask);
return mask & marks_mask & ALL_FSNOTIFY_EVENTS;
}
/* Report pre-content event with optional range info */
int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
size_t count)
{
struct file_range range;
/* Report page aligned range only when pos is known */
if (!ppos)
return fsnotify_path(path, FS_PRE_ACCESS);
range.path = path;
range.pos = PAGE_ALIGN_DOWN(*ppos);
range.count = PAGE_ALIGN(*ppos + count) - range.pos;
return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range,
FSNOTIFY_EVENT_FILE_RANGE);
}
/*
* Notify this dentry's parent about a child's events with child name info
* if parent is watching or if inode/sb/mount are interested in events with
* parent and name info.
*
* Notify only the child without name info if parent is not watching and
* inode/sb/mount are not interested in events with parent and name info.
*/
int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
int data_type)
{ const struct path *path = fsnotify_data_path(data, data_type); __u32 mnt_mask = path ? READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0;
struct inode *inode = d_inode(dentry);
struct dentry *parent;
bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
bool parent_needed, parent_interested;
__u32 p_mask;
struct inode *p_inode = NULL;
struct name_snapshot name;
struct qstr *file_name = NULL;
int ret = 0;
/* Optimize the likely case of nobody watching this path */
if (likely(!parent_watched &&
!fsnotify_object_watched(inode, mnt_mask, mask)))
return 0;
parent = NULL;
parent_needed = fsnotify_event_needs_parent(inode, mnt_mask, mask); if (!parent_watched && !parent_needed)
goto notify;
/* Does parent inode care about events on children? */
parent = dget_parent(dentry);
p_inode = parent->d_inode;
p_mask = fsnotify_inode_watches_children(p_inode);
if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry);
/*
* Include parent/name in notification either if some notification
* groups require parent info or the parent is interested in this event.
*/
parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS;
if (parent_needed || parent_interested) {
/* When notifying parent, child should be passed as data */
WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
/* Notify both parent and child with child name info */
take_dentry_name_snapshot(&name, dentry);
file_name = &name.name;
if (parent_interested)
mask |= FS_EVENT_ON_CHILD;
}
notify:
ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0);
if (file_name)
release_dentry_name_snapshot(&name);
dput(parent);
return ret;
}
EXPORT_SYMBOL_GPL(__fsnotify_parent);
static int fsnotify_handle_inode_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
u32 mask, const void *data, int data_type,
struct inode *dir, const struct qstr *name,
u32 cookie)
{
const struct path *path = fsnotify_data_path(data, data_type);
struct inode *inode = fsnotify_data_inode(data, data_type);
const struct fsnotify_ops *ops = group->ops;
if (WARN_ON_ONCE(!ops->handle_inode_event))
return 0;
if (WARN_ON_ONCE(!inode && !dir))
return 0;
if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) &&
path && d_unlinked(path->dentry))
return 0;
/* Check interest of this mark in case event was sent with two marks */
if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS))
return 0;
return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie);
}
static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
const void *data, int data_type,
struct inode *dir, const struct qstr *name,
u32 cookie, struct fsnotify_iter_info *iter_info)
{
struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info);
int ret;
if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
return 0;
/*
* For FS_RENAME, 'dir' is old dir and 'data' is new dentry.
* The only ->handle_inode_event() backend that supports FS_RENAME is
* dnotify, where it means file was renamed within same parent.
*/
if (mask & FS_RENAME) {
struct dentry *moved = fsnotify_data_dentry(data, data_type);
if (dir != moved->d_parent->d_inode)
return 0;
}
if (parent_mark) {
ret = fsnotify_handle_inode_event(group, parent_mark, mask,
data, data_type, dir, name, 0);
if (ret)
return ret;
}
if (!inode_mark)
return 0;
/*
* Some events can be sent on both parent dir and child marks (e.g.
* FS_ATTRIB). If both parent dir and child are watching, report the
* event once to parent dir with name (if interested) and once to child
* without name (if interested).
*
* In any case regardless whether the parent is watching or not, the
* child watcher is expecting an event without the FS_EVENT_ON_CHILD
* flag. The file name is expected if and only if this is a directory
* event.
*/
mask &= ~FS_EVENT_ON_CHILD;
if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) {
dir = NULL;
name = NULL;
}
return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
dir, name, cookie);
}
static int send_to_group(__u32 mask, const void *data, int data_type,
struct inode *dir, const struct qstr *file_name,
u32 cookie, struct fsnotify_iter_info *iter_info)
{
struct fsnotify_group *group = NULL;
__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
__u32 marks_mask = 0;
__u32 marks_ignore_mask = 0;
bool is_dir = mask & FS_ISDIR;
struct fsnotify_mark *mark;
int type;
if (!iter_info->report_mask)
return 0;
/* clear ignored on inode modification */
if (mask & FS_MODIFY) {
fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
if (!(mark->flags &
FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
mark->ignore_mask = 0;
}
}
/* Are any of the group marks interested in this event? */
fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
group = mark->group;
marks_mask |= mark->mask;
marks_ignore_mask |=
fsnotify_effective_ignore_mask(mark, is_dir, type);
}
pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
__func__, group, mask, marks_mask, marks_ignore_mask,
data, data_type, dir, cookie);
if (!(test_mask & marks_mask & ~marks_ignore_mask))
return 0;
if (group->ops->handle_event) {
return group->ops->handle_event(group, mask, data, data_type, dir,
file_name, cookie, iter_info);
}
return fsnotify_handle_event(group, mask, data, data_type, dir,
file_name, cookie, iter_info);
}
static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp)
{
struct fsnotify_mark_connector *conn;
struct hlist_node *node = NULL;
conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
if (conn)
node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu);
return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}
static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
{
struct hlist_node *node = NULL;
if (mark)
node = srcu_dereference(mark->obj_list.next,
&fsnotify_mark_srcu);
return hlist_entry_safe(node, struct fsnotify_mark, obj_list);
}
/*
* iter_info is a multi head priority queue of marks.
* Pick a subset of marks from queue heads, all with the same group
* and set the report_mask to a subset of the selected marks.
* Returns false if there are no more groups to iterate.
*/
static bool fsnotify_iter_select_report_types(
struct fsnotify_iter_info *iter_info)
{
struct fsnotify_group *max_prio_group = NULL;
struct fsnotify_mark *mark;
int type;
/* Choose max prio group among groups of all queue heads */
fsnotify_foreach_iter_type(type) {
mark = iter_info->marks[type];
if (mark &&
fsnotify_compare_groups(max_prio_group, mark->group) > 0)
max_prio_group = mark->group;
}
if (!max_prio_group)
return false;
/* Set the report mask for marks from same group as max prio group */
iter_info->current_group = max_prio_group;
iter_info->report_mask = 0;
fsnotify_foreach_iter_type(type) {
mark = iter_info->marks[type];
if (mark && mark->group == iter_info->current_group) {
/*
* FSNOTIFY_ITER_TYPE_PARENT indicates that this inode
* is watching children and interested in this event,
* which is an event possible on child.
* But is *this mark* watching children?
*/
if (type == FSNOTIFY_ITER_TYPE_PARENT &&
!(mark->mask & FS_EVENT_ON_CHILD) &&
!(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD))
continue;
fsnotify_iter_set_report_type(iter_info, type);
}
}
return true;
}
/*
* Pop from iter_info multi head queue, the marks that belong to the group of
* current iteration step.
*/
static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
{
struct fsnotify_mark *mark;
int type;
/*
* We cannot use fsnotify_foreach_iter_mark_type() here because we
* may need to advance a mark of type X that belongs to current_group
* but was not selected for reporting.
*/
fsnotify_foreach_iter_type(type) {
mark = iter_info->marks[type];
if (mark && mark->group == iter_info->current_group)
iter_info->marks[type] =
fsnotify_next_mark(iter_info->marks[type]);
}
}
/*
* fsnotify - This is the main call to fsnotify.
*
* The VFS calls into hook specific functions in linux/fsnotify.h.
* Those functions then in turn call here. Here will call out to all of the
* registered fsnotify_group. Those groups can then use the notification event
* in whatever means they feel necessary.
*
* @mask: event type and flags
* @data: object that event happened on
* @data_type: type of object for fanotify_data_XXX() accessors
* @dir: optional directory associated with event -
* if @file_name is not NULL, this is the directory that
* @file_name is relative to
* @file_name: optional file name associated with event
* @inode: optional inode associated with event -
* If @dir and @inode are both non-NULL, event may be
* reported to both.
* @cookie: inotify rename cookie
*/
int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
const struct qstr *file_name, struct inode *inode, u32 cookie)
{
const struct path *path = fsnotify_data_path(data, data_type);
struct super_block *sb = fsnotify_data_sb(data, data_type);
const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL;
struct fsnotify_iter_info iter_info = {};
struct mount *mnt = NULL;
struct inode *inode2 = NULL;
struct dentry *moved;
int inode2_type;
int ret = 0;
__u32 test_mask, marks_mask = 0;
if (path)
mnt = real_mount(path->mnt);
if (!inode) {
/* Dirent event - report on TYPE_INODE to dir */
inode = dir;
/* For FS_RENAME, inode is old_dir and inode2 is new_dir */
if (mask & FS_RENAME) {
moved = fsnotify_data_dentry(data, data_type);
inode2 = moved->d_parent->d_inode;
inode2_type = FSNOTIFY_ITER_TYPE_INODE2;
}
} else if (mask & FS_EVENT_ON_CHILD) {
/*
* Event on child - report on TYPE_PARENT to dir if it is
* watching children and on TYPE_INODE to child.
*/
inode2 = dir;
inode2_type = FSNOTIFY_ITER_TYPE_PARENT;
}
/*
* Optimization: srcu_read_lock() has a memory barrier which can
* be expensive. It protects walking the *_fsnotify_marks lists.
* However, if we do not walk the lists, we do not have to do
* SRCU because we have no references to any objects and do not
* need SRCU to keep them "alive".
*/
if ((!sbinfo || !sbinfo->sb_marks) &&
(!mnt || !mnt->mnt_fsnotify_marks) &&
(!inode || !inode->i_fsnotify_marks) &&
(!inode2 || !inode2->i_fsnotify_marks) &&
(!mnt_data || !mnt_data->ns->n_fsnotify_marks))
return 0;
if (sb)
marks_mask |= READ_ONCE(sb->s_fsnotify_mask);
if (mnt)
marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
if (inode)
marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
if (inode2)
marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
if (mnt_data)
marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask);
/*
* If this is a modify event we may need to clear some ignore masks.
* In that case, the object with ignore masks will have the FS_MODIFY
* event in its mask.
* Otherwise, return if none of the marks care about this type of event.
*/
test_mask = (mask & ALL_FSNOTIFY_EVENTS);
if (!(test_mask & marks_mask))
return 0;
iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
if (sbinfo) {
iter_info.marks[FSNOTIFY_ITER_TYPE_SB] =
fsnotify_first_mark(&sbinfo->sb_marks);
}
if (mnt) {
iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] =
fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
}
if (inode) {
iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] =
fsnotify_first_mark(&inode->i_fsnotify_marks);
}
if (inode2) {
iter_info.marks[inode2_type] =
fsnotify_first_mark(&inode2->i_fsnotify_marks);
}
if (mnt_data) {
iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] =
fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks);
}
/*
* We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
* ignore masks are properly reflected for mount/sb mark notifications.
* That's why this traversal is so complicated...
*/
while (fsnotify_iter_select_report_types(&iter_info)) {
ret = send_to_group(mask, data, data_type, dir, file_name,
cookie, &iter_info);
if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
goto out;
fsnotify_iter_next(&iter_info);
}
ret = 0;
out:
srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);
return ret;
}
EXPORT_SYMBOL_GPL(fsnotify);
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
/*
* At open time we check fsnotify_sb_has_priority_watchers() and set the
* FMODE_NONOTIFY_ mode bits accordignly.
* Later, fsnotify permission hooks do not check if there are permission event
* watches, but that there were permission event watches at open time.
*/
void file_set_fsnotify_mode_from_watchers(struct file *file)
{
struct dentry *dentry = file->f_path.dentry, *parent;
struct super_block *sb = dentry->d_sb;
__u32 mnt_mask, p_mask;
/* Is it a file opened by fanotify? */
if (FMODE_FSNOTIFY_NONE(file->f_mode))
return;
/*
* Permission events is a super set of pre-content events, so if there
* are no permission event watchers, there are also no pre-content event
* watchers and this is implied from the single FMODE_NONOTIFY_PERM bit.
*/
if (likely(!fsnotify_sb_has_priority_watchers(sb,
FSNOTIFY_PRIO_CONTENT))) {
file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
return;
}
/*
* If there are permission event watchers but no pre-content event
* watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
*/
if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || likely(!fsnotify_sb_has_priority_watchers(sb,
FSNOTIFY_PRIO_PRE_CONTENT))) {
file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
return;
}
/*
* OK, there are some pre-content watchers. Check if anybody is
* watching for pre-content events on *this* file.
*/
mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
FSNOTIFY_PRE_CONTENT_EVENTS))) {
/* Enable pre-content events */
file_set_fsnotify_mode(file, 0);
return;
}
/* Is parent watching for pre-content events on this file? */
if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
parent = dget_parent(dentry);
p_mask = fsnotify_inode_watches_children(d_inode(parent));
dput(parent);
if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
/* Enable pre-content events */
file_set_fsnotify_mode(file, 0);
return;
}
}
/* Nobody watching for pre-content events from this file */
file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
}
#endif
void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
{
struct fsnotify_mnt data = {
.ns = ns,
.mnt_id = real_mount(mnt)->mnt_id_unique,
};
if (WARN_ON_ONCE(!ns))
return;
/*
* This is an optimization as well as making sure fsnotify_init() has
* been called.
*/
if (!ns->n_fsnotify_marks)
return;
fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0);
}
static __init int fsnotify_init(void)
{
int ret;
BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
ret = init_srcu_struct(&fsnotify_mark_srcu);
if (ret)
panic("initializing fsnotify_mark_srcu");
fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
SLAB_PANIC);
return 0;
}
core_initcall(fsnotify_init);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Integrity Measurement Architecture
*
* Copyright (C) 2005,2006,2007,2008 IBM Corporation
*
* Authors:
* Reiner Sailer <sailer@watson.ibm.com>
* Serge Hallyn <serue@us.ibm.com>
* Kylene Hall <kylene@us.ibm.com>
* Mimi Zohar <zohar@us.ibm.com>
*
* File: ima_main.c
* implements the IMA hooks: ima_bprm_check, ima_file_mmap,
* and ima_file_check.
*/
#include <linux/module.h>
#include <linux/file.h>
#include <linux/binfmts.h>
#include <linux/kernel_read_file.h>
#include <linux/mount.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/ima.h>
#include <linux/fs.h>
#include <linux/iversion.h>
#include <linux/evm.h>
#include "ima.h"
#ifdef CONFIG_IMA_APPRAISE
int ima_appraise = IMA_APPRAISE_ENFORCE;
#else
int ima_appraise;
#endif
int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1;
static int hash_setup_done;
static struct notifier_block ima_lsm_policy_notifier = {
.notifier_call = ima_lsm_policy_change,
};
static int __init hash_setup(char *str)
{
struct ima_template_desc *template_desc = ima_template_desc_current();
int i;
if (hash_setup_done)
return 1;
if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
if (strncmp(str, "sha1", 4) == 0) {
ima_hash_algo = HASH_ALGO_SHA1;
} else if (strncmp(str, "md5", 3) == 0) {
ima_hash_algo = HASH_ALGO_MD5;
} else {
pr_err("invalid hash algorithm \"%s\" for template \"%s\"",
str, IMA_TEMPLATE_IMA_NAME);
return 1;
}
goto out;
}
i = match_string(hash_algo_name, HASH_ALGO__LAST, str);
if (i < 0) {
pr_err("invalid hash algorithm \"%s\"", str);
return 1;
}
ima_hash_algo = i;
out:
hash_setup_done = 1;
return 1;
}
__setup("ima_hash=", hash_setup);
enum hash_algo ima_get_current_hash_algo(void)
{
return ima_hash_algo;
}
/* Prevent mmap'ing a file execute that is already mmap'ed write */
static int mmap_violation_check(enum ima_hooks func, struct file *file,
char **pathbuf, const char **pathname,
char *filename)
{
struct inode *inode;
int rc = 0;
if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) &&
mapping_writably_mapped(file->f_mapping)) {
rc = -ETXTBSY;
inode = file_inode(file);
if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */
*pathname = ima_d_path(&file->f_path, pathbuf,
filename);
integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname,
"mmap_file", "mmapped_writers", rc, 0);
}
return rc;
}
/*
* ima_rdwr_violation_check
*
* Only invalidate the PCR for measured files:
* - Opening a file for write when already open for read,
* results in a time of measure, time of use (ToMToU) error.
* - Opening a file for read when already open for write,
* could result in a file measurement error.
*
*/
static void ima_rdwr_violation_check(struct file *file,
struct ima_iint_cache *iint,
int must_measure,
char **pathbuf,
const char **pathname,
char *filename)
{
struct inode *inode = file_inode(file);
fmode_t mode = file->f_mode;
bool send_tomtou = false, send_writers = false;
if (mode & FMODE_WRITE) {
if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint)
iint = ima_iint_find(inode);
/* IMA_MEASURE is set from reader side */
if (iint && test_and_clear_bit(IMA_MAY_EMIT_TOMTOU,
&iint->atomic_flags))
send_tomtou = true;
}
} else {
if (must_measure) set_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags);
/* Limit number of open_writers violations */
if (inode_is_open_for_write(inode) && must_measure) { if (!test_and_set_bit(IMA_EMITTED_OPENWRITERS,
&iint->atomic_flags))
send_writers = true;
}
}
if (!send_tomtou && !send_writers)
return;
*pathname = ima_d_path(&file->f_path, pathbuf, filename);
if (send_tomtou) ima_add_violation(file, *pathname, iint,
"invalid_pcr", "ToMToU");
if (send_writers) ima_add_violation(file, *pathname, iint,
"invalid_pcr", "open_writers");
}
static void ima_check_last_writer(struct ima_iint_cache *iint,
struct inode *inode, struct file *file)
{
fmode_t mode = file->f_mode;
bool update;
if (!(mode & FMODE_WRITE))
return;
mutex_lock(&iint->mutex);
if (atomic_read(&inode->i_writecount) == 1) {
struct kstat stat;
clear_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags); update = test_and_clear_bit(IMA_UPDATE_XATTR,
&iint->atomic_flags);
if ((iint->flags & IMA_NEW_FILE) ||
vfs_getattr_nosec(&file->f_path, &stat,
STATX_CHANGE_COOKIE,
AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) ||
stat.change_cookie != iint->real_inode.version) {
iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
iint->measured_pcrs = 0;
if (update) ima_update_xattr(iint, file);
}
}
mutex_unlock(&iint->mutex);
}
/**
* ima_file_free - called on __fput()
* @file: pointer to file structure being freed
*
* Flag files that changed, based on i_version
*/
static void ima_file_free(struct file *file)
{
struct inode *inode = file_inode(file);
struct ima_iint_cache *iint;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return;
iint = ima_iint_find(inode);
if (!iint)
return;
ima_check_last_writer(iint, inode, file);
}
static int process_measurement(struct file *file, const struct cred *cred,
struct lsm_prop *prop, char *buf, loff_t size,
int mask, enum ima_hooks func)
{
struct inode *real_inode, *inode = file_inode(file);
struct ima_iint_cache *iint = NULL;
struct ima_template_desc *template_desc = NULL;
struct inode *metadata_inode;
char *pathbuf = NULL;
char filename[NAME_MAX];
const char *pathname = NULL;
int rc = 0, action, must_appraise = 0;
int pcr = CONFIG_IMA_MEASURE_PCR_IDX;
struct evm_ima_xattr_data *xattr_value = NULL;
struct modsig *modsig = NULL;
int xattr_len = 0;
bool violation_check;
enum hash_algo hash_algo;
unsigned int allowed_algos = 0;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return 0;
/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
* bitmask based on the appraise/audit/measurement policy.
* Included is the appraise submask.
*/
action = ima_get_action(file_mnt_idmap(file), inode, cred, prop,
mask, func, &pcr, &template_desc, NULL,
&allowed_algos);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
func == MMAP_CHECK_REQPROT) &&
(ima_policy_flag & IMA_MEASURE) && ((action & IMA_MEASURE) || (file->f_mode & FMODE_WRITE))); if (!action && !violation_check)
return 0;
must_appraise = action & IMA_APPRAISE;
/* Is the appraise rule hook specific? */
if (action & IMA_FILE_APPRAISE)
func = FILE_CHECK;
inode_lock(inode);
if (action) {
iint = ima_inode_get(inode);
if (!iint)
rc = -ENOMEM;
}
if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
&pathbuf, &pathname, filename);
inode_unlock(inode); if (rc)
goto out;
if (!action)
goto out;
mutex_lock(&iint->mutex);
if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags))
/*
* Reset appraisal flags (action and non-action rule-specific)
* if ima_inode_post_setattr was called.
*/
iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED |
IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK |
IMA_NONACTION_RULE_FLAGS);
/*
* Re-evaulate the file if either the xattr has changed or the
* kernel has no way of detecting file change on the filesystem.
* (Limited to privileged mounted filesystems.)
*/
if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) &&
!(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) &&
!(action & IMA_FAIL_UNVERIFIABLE_SIGS))) {
iint->flags &= ~IMA_DONE_MASK;
iint->measured_pcrs = 0;
}
/*
* On stacked filesystems, detect and re-evaluate file data and
* metadata changes.
*/
real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) ||
integrity_inode_attrs_changed(&iint->real_inode,
real_inode)) {
iint->flags &= ~IMA_DONE_MASK;
iint->measured_pcrs = 0;
}
/*
* Reset the EVM status when metadata changed.
*/
metadata_inode = d_inode(d_real(file_dentry(file),
D_REAL_METADATA));
if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED |
IMA_APPRAISED_SUBMASK);
}
/* Determine if already appraised/measured based on bitmask
* (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
* IMA_AUDIT, IMA_AUDITED)
*/
iint->flags |= action;
action &= IMA_DO_MASK;
action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1);
/* If target pcr is already measured, unset IMA_MEASURE action */
if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr)))
action ^= IMA_MEASURE;
/* HASH sets the digital signature and update flags, nothing else */
if ((action & IMA_HASH) &&
!(test_bit(IMA_DIGSIG, &iint->atomic_flags))) {
xattr_len = ima_read_xattr(file_dentry(file),
&xattr_value, xattr_len);
if ((xattr_value && xattr_len > 2) &&
(xattr_value->type == EVM_IMA_XATTR_DIGSIG))
set_bit(IMA_DIGSIG, &iint->atomic_flags);
iint->flags |= IMA_HASHED;
action ^= IMA_HASH;
set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
}
/* Nothing to do, just return existing appraised status */
if (!action) { if (must_appraise) {
rc = mmap_violation_check(func, file, &pathbuf,
&pathname, filename);
if (!rc) rc = ima_get_cache_status(iint, func);
}
goto out_locked;
}
if ((action & IMA_APPRAISE_SUBMASK) ||
strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) {
/* read 'security.ima' */
xattr_len = ima_read_xattr(file_dentry(file),
&xattr_value, xattr_len);
/*
* Read the appended modsig if allowed by the policy, and allow
* an additional measurement list entry, if needed, based on the
* template format and whether the file was already measured.
*/
if (iint->flags & IMA_MODSIG_ALLOWED) {
rc = ima_read_modsig(func, buf, size, &modsig);
if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED)
action |= IMA_MEASURE;
}
}
hash_algo = ima_get_hash_algo(xattr_value, xattr_len);
rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig);
if (rc != 0 && rc != -EBADF && rc != -EINVAL)
goto out_locked;
if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname,
xattr_value, xattr_len, modsig, pcr,
template_desc);
if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
rc = ima_check_blacklist(iint, modsig, pcr);
if (rc != -EPERM) {
inode_lock(inode);
rc = ima_appraise_measurement(func, iint, file,
pathname, xattr_value,
xattr_len, modsig);
inode_unlock(inode);
}
if (!rc) rc = mmap_violation_check(func, file, &pathbuf,
&pathname, filename);
}
if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO))
rc = 0;
/* Ensure the digest was generated using an allowed algorithm */
if (rc == 0 && must_appraise && allowed_algos != 0 &&
(allowed_algos & (1U << hash_algo)) == 0) {
rc = -EACCES;
integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file),
pathname, "collect_data",
"denied-hash-algorithm", rc, 0);
}
out_locked:
if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE))
rc = -EACCES;
mutex_unlock(&iint->mutex);
kfree(xattr_value);
ima_free_modsig(modsig);
out:
if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE))
return -EACCES;
if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
}
return 0;
}
/**
* ima_file_mmap - based on policy, collect/store measurement.
* @file: pointer to the file to be measured (May be NULL)
* @reqprot: protection requested by the application
* @prot: protection that will be applied by the kernel
* @flags: operational flags
*
* Measure files being mmapped executable based on the ima_must_measure()
* policy decision.
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_file_mmap(struct file *file, unsigned long reqprot,
unsigned long prot, unsigned long flags)
{
struct lsm_prop prop;
int ret;
if (!file)
return 0;
security_current_getlsmprop_subj(&prop);
if (reqprot & PROT_EXEC) {
ret = process_measurement(file, current_cred(), &prop, NULL,
0, MAY_EXEC, MMAP_CHECK_REQPROT);
if (ret)
return ret;
}
if (prot & PROT_EXEC) return process_measurement(file, current_cred(), &prop, NULL,
0, MAY_EXEC, MMAP_CHECK);
return 0;
}
/**
* ima_file_mprotect - based on policy, limit mprotect change
* @vma: vm_area_struct protection is set to
* @reqprot: protection requested by the application
* @prot: protection that will be applied by the kernel
*
* Files can be mmap'ed read/write and later changed to execute to circumvent
* IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore
* would be taken before i_mutex), files can not be measured or appraised at
* this point. Eliminate this integrity gap by denying the mprotect
* PROT_EXECUTE change, if an mmap appraise policy rule exists.
*
* On mprotect change success, return 0. On failure, return -EACESS.
*/
static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
unsigned long prot)
{
struct ima_template_desc *template = NULL;
struct file *file;
char filename[NAME_MAX];
char *pathbuf = NULL;
const char *pathname = NULL;
struct inode *inode;
struct lsm_prop prop;
int result = 0;
int action;
int pcr;
/* Is mprotect making an mmap'ed file executable? */
if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file ||
!(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC))
return 0;
security_current_getlsmprop_subj(&prop);
inode = file_inode(vma->vm_file);
action = ima_get_action(file_mnt_idmap(vma->vm_file), inode,
current_cred(), &prop, MAY_EXEC, MMAP_CHECK,
&pcr, &template, NULL, NULL);
action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode,
current_cred(), &prop, MAY_EXEC,
MMAP_CHECK_REQPROT, &pcr, &template, NULL,
NULL);
/* Is the mmap'ed file in policy? */
if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK)))
return 0;
if (action & IMA_APPRAISE_SUBMASK)
result = -EPERM;
file = vma->vm_file;
pathname = ima_d_path(&file->f_path, &pathbuf, filename);
integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname,
"collect_data", "failed-mprotect", result, 0);
if (pathbuf)
__putname(pathbuf);
return result;
}
/**
* ima_bprm_check - based on policy, collect/store measurement.
* @bprm: contains the linux_binprm structure
*
* The OS protects against an executable file, already open for write,
* from being executed in deny_write_access() and an executable file,
* already open for execute, from being modified in get_write_access().
* So we can be certain that what we verify and measure here is actually
* what is being executed.
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_bprm_check(struct linux_binprm *bprm)
{
int ret;
struct lsm_prop prop;
security_current_getlsmprop_subj(&prop);
ret = process_measurement(bprm->file, current_cred(),
&prop, NULL, 0, MAY_EXEC, BPRM_CHECK);
if (ret)
return ret;
security_cred_getlsmprop(bprm->cred, &prop);
return process_measurement(bprm->file, bprm->cred, &prop, NULL, 0,
MAY_EXEC, CREDS_CHECK);
}
/**
* ima_bprm_creds_for_exec - collect/store/appraise measurement.
* @bprm: contains the linux_binprm structure
*
* Based on the IMA policy and the execveat(2) AT_EXECVE_CHECK flag, measure
* and appraise the integrity of a file to be executed by script interpreters.
* Unlike any of the other LSM hooks where the kernel enforces file integrity,
* enforcing file integrity is left up to the discretion of the script
* interpreter (userspace).
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_bprm_creds_for_exec(struct linux_binprm *bprm)
{
/*
* As security_bprm_check() is called multiple times, both
* the script and the shebang interpreter are measured, appraised,
* and audited. Limit usage of this LSM hook to just measuring,
* appraising, and auditing the indirect script execution
* (e.g. ./sh example.sh).
*/
if (!bprm->is_check)
return 0;
return ima_bprm_check(bprm);
}
/**
* ima_file_check - based on policy, collect/store measurement.
* @file: pointer to the file to be measured
* @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND
*
* Measure files based on the ima_must_measure() policy decision.
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_file_check(struct file *file, int mask)
{
struct lsm_prop prop;
security_current_getlsmprop_subj(&prop);
return process_measurement(file, current_cred(), &prop, NULL, 0,
mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
MAY_APPEND), FILE_CHECK);
}
static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf,
size_t buf_size)
{
struct ima_iint_cache *iint = NULL, tmp_iint;
int rc, hash_algo;
if (ima_policy_flag) {
iint = ima_iint_find(inode);
if (iint)
mutex_lock(&iint->mutex);
}
if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) {
if (iint)
mutex_unlock(&iint->mutex);
memset(&tmp_iint, 0, sizeof(tmp_iint));
mutex_init(&tmp_iint.mutex);
rc = ima_collect_measurement(&tmp_iint, file, NULL, 0,
ima_hash_algo, NULL);
if (rc < 0) {
/* ima_hash could be allocated in case of failure. */
if (rc != -ENOMEM)
kfree(tmp_iint.ima_hash);
return -EOPNOTSUPP;
}
iint = &tmp_iint;
mutex_lock(&iint->mutex);
}
if (!iint)
return -EOPNOTSUPP;
/*
* ima_file_hash can be called when ima_collect_measurement has still
* not been called, we might not always have a hash.
*/
if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) {
mutex_unlock(&iint->mutex);
return -EOPNOTSUPP;
}
if (buf) {
size_t copied_size;
copied_size = min_t(size_t, iint->ima_hash->length, buf_size);
memcpy(buf, iint->ima_hash->digest, copied_size);
}
hash_algo = iint->ima_hash->algo;
mutex_unlock(&iint->mutex);
if (iint == &tmp_iint)
kfree(iint->ima_hash);
return hash_algo;
}
/**
* ima_file_hash - return a measurement of the file
* @file: pointer to the file
* @buf: buffer in which to store the hash
* @buf_size: length of the buffer
*
* On success, return the hash algorithm (as defined in the enum hash_algo).
* If buf is not NULL, this function also outputs the hash into buf.
* If the hash is larger than buf_size, then only buf_size bytes will be copied.
* It generally just makes sense to pass a buffer capable of holding the largest
* possible hash: IMA_MAX_DIGEST_SIZE.
* The file hash returned is based on the entire file, including the appended
* signature.
*
* If the measurement cannot be performed, return -EOPNOTSUPP.
* If the parameters are incorrect, return -EINVAL.
*/
int ima_file_hash(struct file *file, char *buf, size_t buf_size)
{
if (!file)
return -EINVAL;
return __ima_inode_hash(file_inode(file), file, buf, buf_size);
}
EXPORT_SYMBOL_GPL(ima_file_hash);
/**
* ima_inode_hash - return the stored measurement if the inode has been hashed
* and is in the iint cache.
* @inode: pointer to the inode
* @buf: buffer in which to store the hash
* @buf_size: length of the buffer
*
* On success, return the hash algorithm (as defined in the enum hash_algo).
* If buf is not NULL, this function also outputs the hash into buf.
* If the hash is larger than buf_size, then only buf_size bytes will be copied.
* It generally just makes sense to pass a buffer capable of holding the largest
* possible hash: IMA_MAX_DIGEST_SIZE.
* The hash returned is based on the entire contents, including the appended
* signature.
*
* If IMA is disabled or if no measurement is available, return -EOPNOTSUPP.
* If the parameters are incorrect, return -EINVAL.
*/
int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
{
if (!inode)
return -EINVAL;
return __ima_inode_hash(inode, NULL, buf, buf_size);
}
EXPORT_SYMBOL_GPL(ima_inode_hash);
/**
* ima_post_create_tmpfile - mark newly created tmpfile as new
* @idmap: idmap of the mount the inode was found from
* @inode: inode of the newly created tmpfile
*
* No measuring, appraising or auditing of newly created tmpfiles is needed.
* Skip calling process_measurement(), but indicate which newly, created
* tmpfiles are in policy.
*/
static void ima_post_create_tmpfile(struct mnt_idmap *idmap,
struct inode *inode)
{
struct ima_iint_cache *iint;
int must_appraise;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return;
must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS,
FILE_CHECK);
if (!must_appraise)
return;
/* Nothing to do if we can't allocate memory */
iint = ima_inode_get(inode);
if (!iint)
return;
/* needed for writing the security xattrs */
set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
iint->ima_file_status = INTEGRITY_PASS;
}
/**
* ima_post_path_mknod - mark as a new inode
* @idmap: idmap of the mount the inode was found from
* @dentry: newly created dentry
*
* Mark files created via the mknodat syscall as new, so that the
* file data can be written later.
*/
static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry)
{
struct ima_iint_cache *iint;
struct inode *inode = dentry->d_inode;
int must_appraise;
if (!ima_policy_flag || !S_ISREG(inode->i_mode))
return;
must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS,
FILE_CHECK);
if (!must_appraise)
return;
/* Nothing to do if we can't allocate memory */
iint = ima_inode_get(inode);
if (!iint)
return;
/* needed for re-opening empty files */
iint->flags |= IMA_NEW_FILE;
}
/**
* ima_read_file - pre-measure/appraise hook decision based on policy
* @file: pointer to the file to be measured/appraised/audit
* @read_id: caller identifier
* @contents: whether a subsequent call will be made to ima_post_read_file()
*
* Permit reading a file based on policy. The policy rules are written
* in terms of the policy identifier. Appraising the integrity of
* a file requires a file descriptor.
*
* For permission return 0, otherwise return -EACCES.
*/
static int ima_read_file(struct file *file, enum kernel_read_file_id read_id,
bool contents)
{
enum ima_hooks func;
struct lsm_prop prop;
/*
* Do devices using pre-allocated memory run the risk of the
* firmware being accessible to the device prior to the completion
* of IMA's signature verification any more than when using two
* buffers? It may be desirable to include the buffer address
* in this API and walk all the dma_map_single() mappings to check.
*/
/*
* There will be a call made to ima_post_read_file() with
* a filled buffer, so we don't need to perform an extra
* read early here.
*/
if (contents)
return 0;
/* Read entire file for all partial reads. */
func = read_idmap[read_id] ?: FILE_CHECK;
security_current_getlsmprop_subj(&prop);
return process_measurement(file, current_cred(), &prop, NULL, 0,
MAY_READ, func);
}
const int read_idmap[READING_MAX_ID] = {
[READING_FIRMWARE] = FIRMWARE_CHECK,
[READING_MODULE] = MODULE_CHECK,
[READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK,
[READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK,
[READING_POLICY] = POLICY_CHECK
};
/**
* ima_post_read_file - in memory collect/appraise/audit measurement
* @file: pointer to the file to be measured/appraised/audit
* @buf: pointer to in memory file contents
* @size: size of in memory file contents
* @read_id: caller identifier
*
* Measure/appraise/audit in memory file based on policy. Policy rules
* are written in terms of a policy identifier.
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_post_read_file(struct file *file, char *buf, loff_t size,
enum kernel_read_file_id read_id)
{
enum ima_hooks func;
struct lsm_prop prop;
/* permit signed certs */
if (!file && read_id == READING_X509_CERTIFICATE)
return 0;
if (!file || !buf || size == 0) { /* should never happen */
if (ima_appraise & IMA_APPRAISE_ENFORCE)
return -EACCES;
return 0;
}
func = read_idmap[read_id] ?: FILE_CHECK;
security_current_getlsmprop_subj(&prop);
return process_measurement(file, current_cred(), &prop, buf, size,
MAY_READ, func);
}
/**
* ima_load_data - appraise decision based on policy
* @id: kernel load data caller identifier
* @contents: whether the full contents will be available in a later
* call to ima_post_load_data().
*
* Callers of this LSM hook can not measure, appraise, or audit the
* data provided by userspace. Enforce policy rules requiring a file
* signature (eg. kexec'ed kernel image).
*
* For permission return 0, otherwise return -EACCES.
*/
static int ima_load_data(enum kernel_load_data_id id, bool contents)
{
bool ima_enforce, sig_enforce;
ima_enforce =
(ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE;
switch (id) {
case LOADING_KEXEC_IMAGE:
if (IS_ENABLED(CONFIG_KEXEC_SIG)
&& arch_ima_get_secureboot()) {
pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
return -EACCES;
}
if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) {
pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
return -EACCES; /* INTEGRITY_UNKNOWN */
}
break;
case LOADING_FIRMWARE:
if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) {
pr_err("Prevent firmware sysfs fallback loading.\n");
return -EACCES; /* INTEGRITY_UNKNOWN */
}
break;
case LOADING_MODULE:
sig_enforce = is_module_sig_enforced();
if (ima_enforce && (!sig_enforce
&& (ima_appraise & IMA_APPRAISE_MODULES))) {
pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n");
return -EACCES; /* INTEGRITY_UNKNOWN */
}
break;
default:
break;
}
return 0;
}
/**
* ima_post_load_data - appraise decision based on policy
* @buf: pointer to in memory file contents
* @size: size of in memory file contents
* @load_id: kernel load data caller identifier
* @description: @load_id-specific description of contents
*
* Measure/appraise/audit in memory buffer based on policy. Policy rules
* are written in terms of a policy identifier.
*
* On success return 0. On integrity appraisal error, assuming the file
* is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
*/
static int ima_post_load_data(char *buf, loff_t size,
enum kernel_load_data_id load_id,
char *description)
{
if (load_id == LOADING_FIRMWARE) {
if ((ima_appraise & IMA_APPRAISE_FIRMWARE) &&
(ima_appraise & IMA_APPRAISE_ENFORCE)) {
pr_err("Prevent firmware loading_store.\n");
return -EACCES; /* INTEGRITY_UNKNOWN */
}
return 0;
}
/*
* Measure the init_module syscall buffer containing the ELF image.
*/
if (load_id == LOADING_MODULE)
ima_measure_critical_data("modules", "init_module",
buf, size, true, NULL, 0);
return 0;
}
/**
* process_buffer_measurement - Measure the buffer or the buffer data hash
* @idmap: idmap of the mount the inode was found from
* @inode: inode associated with the object being measured (NULL for KEY_CHECK)
* @buf: pointer to the buffer that needs to be added to the log.
* @size: size of buffer(in bytes).
* @eventname: event name to be used for the buffer entry.
* @func: IMA hook
* @pcr: pcr to extend the measurement
* @func_data: func specific data, may be NULL
* @buf_hash: measure buffer data hash
* @digest: buffer digest will be written to
* @digest_len: buffer length
*
* Based on policy, either the buffer data or buffer data hash is measured
*
* Return: 0 if the buffer has been successfully measured, 1 if the digest
* has been written to the passed location but not added to a measurement entry,
* a negative value otherwise.
*/
int process_buffer_measurement(struct mnt_idmap *idmap,
struct inode *inode, const void *buf, int size,
const char *eventname, enum ima_hooks func,
int pcr, const char *func_data,
bool buf_hash, u8 *digest, size_t digest_len)
{
int ret = 0;
const char *audit_cause = "ENOMEM";
struct ima_template_entry *entry = NULL;
struct ima_iint_cache iint = {};
struct ima_event_data event_data = {.iint = &iint,
.filename = eventname,
.buf = buf,
.buf_len = size};
struct ima_template_desc *template;
struct ima_max_digest_data hash;
struct ima_digest_data *hash_hdr = container_of(&hash.hdr,
struct ima_digest_data, hdr);
char digest_hash[IMA_MAX_DIGEST_SIZE];
int digest_hash_len = hash_digest_size[ima_hash_algo];
int violation = 0;
int action = 0;
struct lsm_prop prop;
if (digest && digest_len < digest_hash_len)
return -EINVAL;
if (!ima_policy_flag && !digest)
return -ENOENT;
template = ima_template_desc_buf();
if (!template) {
ret = -EINVAL;
audit_cause = "ima_template_desc_buf";
goto out;
}
/*
* Both LSM hooks and auxiliary based buffer measurements are
* based on policy. To avoid code duplication, differentiate
* between the LSM hooks and auxiliary buffer measurements,
* retrieving the policy rule information only for the LSM hook
* buffer measurements.
*/
if (func) {
security_current_getlsmprop_subj(&prop);
action = ima_get_action(idmap, inode, current_cred(),
&prop, 0, func, &pcr, &template,
func_data, NULL);
if (!(action & IMA_MEASURE) && !digest)
return -ENOENT;
}
if (!pcr)
pcr = CONFIG_IMA_MEASURE_PCR_IDX;
iint.ima_hash = hash_hdr;
iint.ima_hash->algo = ima_hash_algo;
iint.ima_hash->length = hash_digest_size[ima_hash_algo];
ret = ima_calc_buffer_hash(buf, size, iint.ima_hash);
if (ret < 0) {
audit_cause = "hashing_error";
goto out;
}
if (buf_hash) {
memcpy(digest_hash, hash_hdr->digest, digest_hash_len);
ret = ima_calc_buffer_hash(digest_hash, digest_hash_len,
iint.ima_hash);
if (ret < 0) {
audit_cause = "hashing_error";
goto out;
}
event_data.buf = digest_hash;
event_data.buf_len = digest_hash_len;
}
if (digest)
memcpy(digest, iint.ima_hash->digest, digest_hash_len);
if (!ima_policy_flag || (func && !(action & IMA_MEASURE)))
return 1;
ret = ima_alloc_init_template(&event_data, &entry, template);
if (ret < 0) {
audit_cause = "alloc_entry";
goto out;
}
ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr);
if (ret < 0) {
audit_cause = "store_entry";
ima_free_template_entry(entry);
}
out:
if (ret < 0)
integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname,
func_measure_str(func),
audit_cause, ret, 0, ret);
return ret;
}
/**
* ima_kexec_cmdline - measure kexec cmdline boot args
* @kernel_fd: file descriptor of the kexec kernel being loaded
* @buf: pointer to buffer
* @size: size of buffer
*
* Buffers can only be measured, not appraised.
*/
void ima_kexec_cmdline(int kernel_fd, const void *buf, int size)
{
if (!buf || !size)
return;
CLASS(fd, f)(kernel_fd);
if (fd_empty(f))
return;
process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)),
buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0,
NULL, false, NULL, 0);
}
/**
* ima_measure_critical_data - measure kernel integrity critical data
* @event_label: unique event label for grouping and limiting critical data
* @event_name: event name for the record in the IMA measurement list
* @buf: pointer to buffer data
* @buf_len: length of buffer data (in bytes)
* @hash: measure buffer data hash
* @digest: buffer digest will be written to
* @digest_len: buffer length
*
* Measure data critical to the integrity of the kernel into the IMA log
* and extend the pcr. Examples of critical data could be various data
* structures, policies, and states stored in kernel memory that can
* impact the integrity of the system.
*
* Return: 0 if the buffer has been successfully measured, 1 if the digest
* has been written to the passed location but not added to a measurement entry,
* a negative value otherwise.
*/
int ima_measure_critical_data(const char *event_label,
const char *event_name,
const void *buf, size_t buf_len,
bool hash, u8 *digest, size_t digest_len)
{
if (!event_name || !event_label || !buf || !buf_len)
return -ENOPARAM;
return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len,
event_name, CRITICAL_DATA, 0,
event_label, hash, digest,
digest_len);
}
EXPORT_SYMBOL_GPL(ima_measure_critical_data);
#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
/**
* ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests
* @kmod_name: kernel module name
*
* Avoid a verification loop where verifying the signature of the modprobe
* binary requires executing modprobe itself. Since the modprobe iint->mutex
* is already held when the signature verification is performed, a deadlock
* occurs as soon as modprobe is executed within the critical region, since
* the same lock cannot be taken again.
*
* This happens when public_key_verify_signature(), in case of RSA algorithm,
* use alg_name to store internal information in order to construct an
* algorithm on the fly, but crypto_larval_lookup() will try to use alg_name
* in order to load a kernel module with same name.
*
* Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules,
* we are safe to fail such module request from crypto_larval_lookup(), and
* avoid the verification loop.
*
* Return: Zero if it is safe to load the kernel module, -EINVAL otherwise.
*/
static int ima_kernel_module_request(char *kmod_name)
{
if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0)
return -EINVAL;
return 0;
}
#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */
static int __init init_ima(void)
{
int error;
ima_appraise_parse_cmdline();
ima_init_template_list();
hash_setup(CONFIG_IMA_DEFAULT_HASH);
error = ima_init();
if (error && strcmp(hash_algo_name[ima_hash_algo],
CONFIG_IMA_DEFAULT_HASH) != 0) {
pr_info("Allocating %s failed, going to use default hash algorithm %s\n",
hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH);
hash_setup_done = 0;
hash_setup(CONFIG_IMA_DEFAULT_HASH);
error = ima_init();
}
if (error)
return error;
error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier);
if (error)
pr_warn("Couldn't register LSM notifier, error %d\n", error);
if (!error)
ima_update_policy_flags();
return error;
}
static struct security_hook_list ima_hooks[] __ro_after_init = {
LSM_HOOK_INIT(bprm_check_security, ima_bprm_check),
LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec),
LSM_HOOK_INIT(file_post_open, ima_file_check),
LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile),
LSM_HOOK_INIT(file_release, ima_file_free),
LSM_HOOK_INIT(mmap_file, ima_file_mmap),
LSM_HOOK_INIT(file_mprotect, ima_file_mprotect),
LSM_HOOK_INIT(kernel_load_data, ima_load_data),
LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data),
LSM_HOOK_INIT(kernel_read_file, ima_read_file),
LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file),
LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod),
#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update),
#endif
#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request),
#endif
LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu),
};
static const struct lsm_id ima_lsmid = {
.name = "ima",
.id = LSM_ID_IMA,
};
static int __init init_ima_lsm(void)
{
ima_iintcache_init();
security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid);
init_ima_appraise_lsm(&ima_lsmid);
return 0;
}
struct lsm_blob_sizes ima_blob_sizes __ro_after_init = {
.lbs_inode = sizeof(struct ima_iint_cache *),
};
DEFINE_LSM(ima) = {
.name = "ima",
.init = init_ima_lsm,
.order = LSM_ORDER_LAST,
.blobs = &ima_blob_sizes,
};
late_initcall(init_ima); /* Start IMA after the TPM is available */
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2019 Arm Ltd.
#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <kvm/arm_hypercalls.h>
#include <kvm/arm_psci.h>
#define KVM_ARM_SMCCC_STD_FEATURES \
GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0)
#define KVM_ARM_SMCCC_STD_HYP_FEATURES \
GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0)
#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \
GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0)
#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2 \
GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT - 1, 0)
static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val)
{
struct system_time_snapshot systime_snapshot;
u64 cycles = ~0UL;
u32 feature;
/*
* system time and counter value must captured at the same
* time to keep consistency and precision.
*/
ktime_get_snapshot(&systime_snapshot);
/*
* This is only valid if the current clocksource is the
* architected counter, as this is the only one the guest
* can see.
*/
if (systime_snapshot.cs_id != CSID_ARM_ARCH_COUNTER)
return;
/*
* The guest selects one of the two reference counters
* (virtual or physical) with the first argument of the SMCCC
* call. In case the identifier is not supported, error out.
*/
feature = smccc_get_arg1(vcpu);
switch (feature) {
case KVM_PTP_VIRT_COUNTER:
cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset;
break;
case KVM_PTP_PHYS_COUNTER:
cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.poffset;
break;
default:
return;
}
/*
* This relies on the top bit of val[0] never being set for
* valid values of system time, because that is *really* far
* in the future (about 292 years from 1970, and at that stage
* nobody will give a damn about it).
*/
val[0] = upper_32_bits(systime_snapshot.real);
val[1] = lower_32_bits(systime_snapshot.real);
val[2] = upper_32_bits(cycles);
val[3] = lower_32_bits(cycles);
}
static bool kvm_smccc_default_allowed(u32 func_id)
{
switch (func_id) {
/*
* List of function-ids that are not gated with the bitmapped
* feature firmware registers, and are to be allowed for
* servicing the call by default.
*/
case ARM_SMCCC_VERSION_FUNC_ID:
case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
return true;
default:
/* PSCI 0.2 and up is in the 0:0x1f range */
if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD &&
ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f)
return true;
/*
* KVM's PSCI 0.1 doesn't comply with SMCCC, and has
* its own function-id base and range
*/
if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3))
return true;
return false;
}
}
static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id)
{
struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat;
switch (func_id) {
case ARM_SMCCC_TRNG_VERSION:
case ARM_SMCCC_TRNG_FEATURES:
case ARM_SMCCC_TRNG_GET_UUID:
case ARM_SMCCC_TRNG_RND32:
case ARM_SMCCC_TRNG_RND64:
return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0,
&smccc_feat->std_bmap);
case ARM_SMCCC_HV_PV_TIME_FEATURES:
case ARM_SMCCC_HV_PV_TIME_ST:
return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME,
&smccc_feat->std_hyp_bmap);
case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT,
&smccc_feat->vendor_hyp_bmap);
case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID:
return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP,
&smccc_feat->vendor_hyp_bmap);
default:
return false;
}
}
#define SMC32_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID
#define SMC32_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
ARM_SMCCC_SMC_32, \
0, ARM_SMCCC_FUNC_MASK)
#define SMC64_ARCH_RANGE_BEGIN ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
ARM_SMCCC_SMC_64, \
0, 0)
#define SMC64_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
ARM_SMCCC_SMC_64, \
0, ARM_SMCCC_FUNC_MASK)
static int kvm_smccc_filter_insert_reserved(struct kvm *kvm)
{
int r;
/*
* Prevent userspace from handling any SMCCC calls in the architecture
* range, avoiding the risk of misrepresenting Spectre mitigation status
* to the guest.
*/
r = mtree_insert_range(&kvm->arch.smccc_filter,
SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END,
xa_mk_value(KVM_SMCCC_FILTER_HANDLE),
GFP_KERNEL_ACCOUNT);
if (r)
goto out_destroy;
r = mtree_insert_range(&kvm->arch.smccc_filter,
SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END,
xa_mk_value(KVM_SMCCC_FILTER_HANDLE),
GFP_KERNEL_ACCOUNT);
if (r)
goto out_destroy;
return 0;
out_destroy:
mtree_destroy(&kvm->arch.smccc_filter);
return r;
}
static bool kvm_smccc_filter_configured(struct kvm *kvm)
{
return !mtree_empty(&kvm->arch.smccc_filter);
}
static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr)
{
const void *zero_page = page_to_virt(ZERO_PAGE(0));
struct kvm_smccc_filter filter;
u32 start, end;
int r;
if (copy_from_user(&filter, uaddr, sizeof(filter)))
return -EFAULT;
if (memcmp(filter.pad, zero_page, sizeof(filter.pad)))
return -EINVAL;
start = filter.base;
end = start + filter.nr_functions - 1;
if (end < start || filter.action >= NR_SMCCC_FILTER_ACTIONS)
return -EINVAL;
mutex_lock(&kvm->arch.config_lock);
if (kvm_vm_has_ran_once(kvm)) {
r = -EBUSY;
goto out_unlock;
}
if (!kvm_smccc_filter_configured(kvm)) {
r = kvm_smccc_filter_insert_reserved(kvm);
if (WARN_ON_ONCE(r))
goto out_unlock;
}
r = mtree_insert_range(&kvm->arch.smccc_filter, start, end,
xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT);
out_unlock:
mutex_unlock(&kvm->arch.config_lock);
return r;
}
static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id)
{
unsigned long idx = func_id;
void *val;
if (!kvm_smccc_filter_configured(kvm))
return KVM_SMCCC_FILTER_HANDLE;
/*
* But where's the error handling, you say?
*
* mt_find() returns NULL if no entry was found, which just so happens
* to match KVM_SMCCC_FILTER_HANDLE.
*/
val = mt_find(&kvm->arch.smccc_filter, &idx, idx);
return xa_to_value(val);
}
static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id)
{
/*
* Intervening actions in the SMCCC filter take precedence over the
* pseudo-firmware register bitmaps.
*/
u8 action = kvm_smccc_filter_get_action(vcpu->kvm, func_id); if (action != KVM_SMCCC_FILTER_HANDLE)
return action;
if (kvm_smccc_test_fw_bmap(vcpu, func_id) || kvm_smccc_default_allowed(func_id))
return KVM_SMCCC_FILTER_HANDLE;
return KVM_SMCCC_FILTER_DENY;
}
static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id)
{
u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
struct kvm_run *run = vcpu->run;
u64 flags = 0;
if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64)
flags |= KVM_HYPERCALL_EXIT_SMC;
if (!kvm_vcpu_trap_il_is32bit(vcpu))
flags |= KVM_HYPERCALL_EXIT_16BIT;
run->exit_reason = KVM_EXIT_HYPERCALL;
run->hypercall = (typeof(run->hypercall)) {
.nr = func_id,
.flags = flags,
};
}
int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
{
struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat;
u32 func_id = smccc_get_function(vcpu);
u64 val[4] = {SMCCC_RET_NOT_SUPPORTED};
u32 feature;
u8 action;
gpa_t gpa;
action = kvm_smccc_get_action(vcpu, func_id); switch (action) {
case KVM_SMCCC_FILTER_HANDLE:
break;
case KVM_SMCCC_FILTER_DENY:
goto out;
case KVM_SMCCC_FILTER_FWD_TO_USER:
kvm_prepare_hypercall_exit(vcpu, func_id);
return 0;
default:
WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action);
goto out;
}
switch (func_id) {
case ARM_SMCCC_VERSION_FUNC_ID:
val[0] = ARM_SMCCC_VERSION_1_1;
break;
case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
feature = smccc_get_arg1(vcpu);
switch (feature) {
case ARM_SMCCC_ARCH_WORKAROUND_1:
switch (arm64_get_spectre_v2_state()) {
case SPECTRE_VULNERABLE:
break;
case SPECTRE_MITIGATED:
val[0] = SMCCC_RET_SUCCESS;
break;
case SPECTRE_UNAFFECTED:
val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
break;
}
break;
case ARM_SMCCC_ARCH_WORKAROUND_2:
switch (arm64_get_spectre_v4_state()) {
case SPECTRE_VULNERABLE:
break;
case SPECTRE_MITIGATED:
/*
* SSBS everywhere: Indicate no firmware
* support, as the SSBS support will be
* indicated to the guest and the default is
* safe.
*
* Otherwise, expose a permanent mitigation
* to the guest, and hide SSBS so that the
* guest stays protected.
*/
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
break;
fallthrough;
case SPECTRE_UNAFFECTED:
val[0] = SMCCC_RET_NOT_REQUIRED;
break;
}
break;
case ARM_SMCCC_ARCH_WORKAROUND_3:
switch (arm64_get_spectre_bhb_state()) {
case SPECTRE_VULNERABLE:
break;
case SPECTRE_MITIGATED:
val[0] = SMCCC_RET_SUCCESS;
break;
case SPECTRE_UNAFFECTED:
val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
break;
}
break;
case ARM_SMCCC_HV_PV_TIME_FEATURES:
if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME,
&smccc_feat->std_hyp_bmap))
val[0] = SMCCC_RET_SUCCESS;
break;
}
break;
case ARM_SMCCC_HV_PV_TIME_FEATURES:
val[0] = kvm_hypercall_pv_features(vcpu);
break;
case ARM_SMCCC_HV_PV_TIME_ST:
gpa = kvm_init_stolen_time(vcpu);
if (gpa != INVALID_GPA) val[0] = gpa;
break;
case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
val[0] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0;
val[1] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1;
val[2] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2;
val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3;
break;
case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
val[0] = smccc_feat->vendor_hyp_bmap;
/* Function numbers 2-63 are reserved for pKVM for now */
val[2] = smccc_feat->vendor_hyp_bmap_2;
break;
case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID:
kvm_ptp_get_time(vcpu, val);
break;
case ARM_SMCCC_TRNG_VERSION:
case ARM_SMCCC_TRNG_FEATURES:
case ARM_SMCCC_TRNG_GET_UUID:
case ARM_SMCCC_TRNG_RND32:
case ARM_SMCCC_TRNG_RND64:
return kvm_trng_call(vcpu);
default:
return kvm_psci_call(vcpu);
}
out:
smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]);
return 1;
}
static const u64 kvm_arm_fw_reg_ids[] = {
KVM_REG_ARM_PSCI_VERSION,
KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1,
KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2,
KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3,
KVM_REG_ARM_STD_BMAP,
KVM_REG_ARM_STD_HYP_BMAP,
KVM_REG_ARM_VENDOR_HYP_BMAP,
KVM_REG_ARM_VENDOR_HYP_BMAP_2,
};
void kvm_arm_init_hypercalls(struct kvm *kvm)
{
struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat;
smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES;
smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES;
smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES;
mt_init(&kvm->arch.smccc_filter);
}
void kvm_arm_teardown_hypercalls(struct kvm *kvm)
{
mtree_destroy(&kvm->arch.smccc_filter);
}
int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
{
return ARRAY_SIZE(kvm_arm_fw_reg_ids);
}
int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
{
int i;
for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { if (put_user(kvm_arm_fw_reg_ids[i], uindices++))
return -EFAULT;
}
return 0;
}
#define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0)
/*
* Convert the workaround level into an easy-to-compare number, where higher
* values mean better protection.
*/
static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
{ switch (regid) {
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
switch (arm64_get_spectre_v2_state()) {
case SPECTRE_VULNERABLE:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
case SPECTRE_MITIGATED:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
case SPECTRE_UNAFFECTED:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
}
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
switch (arm64_get_spectre_v4_state()) {
case SPECTRE_MITIGATED:
/*
* As for the hypercall discovery, we pretend we
* don't have any FW mitigation if SSBS is there at
* all times.
*/
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
fallthrough;
case SPECTRE_UNAFFECTED:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
case SPECTRE_VULNERABLE:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
}
break;
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
switch (arm64_get_spectre_bhb_state()) {
case SPECTRE_VULNERABLE:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
case SPECTRE_MITIGATED:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL;
case SPECTRE_UNAFFECTED:
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED;
}
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
}
return -EINVAL;
}
int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{ struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat;
void __user *uaddr = (void __user *)(long)reg->addr;
u64 val;
switch (reg->id) {
case KVM_REG_ARM_PSCI_VERSION:
val = kvm_psci_version(vcpu);
break;
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
break;
case KVM_REG_ARM_STD_BMAP:
val = READ_ONCE(smccc_feat->std_bmap);
break;
case KVM_REG_ARM_STD_HYP_BMAP:
val = READ_ONCE(smccc_feat->std_hyp_bmap);
break;
case KVM_REG_ARM_VENDOR_HYP_BMAP:
val = READ_ONCE(smccc_feat->vendor_hyp_bmap);
break;
case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
val = READ_ONCE(smccc_feat->vendor_hyp_bmap_2);
break;
default:
return -ENOENT;
}
if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
return -EFAULT;
return 0;
}
static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val)
{
int ret = 0;
struct kvm *kvm = vcpu->kvm;
struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat;
unsigned long *fw_reg_bmap, fw_reg_features;
switch (reg_id) {
case KVM_REG_ARM_STD_BMAP:
fw_reg_bmap = &smccc_feat->std_bmap;
fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES;
break;
case KVM_REG_ARM_STD_HYP_BMAP:
fw_reg_bmap = &smccc_feat->std_hyp_bmap;
fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES;
break;
case KVM_REG_ARM_VENDOR_HYP_BMAP:
fw_reg_bmap = &smccc_feat->vendor_hyp_bmap;
fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES;
break;
case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
fw_reg_bmap = &smccc_feat->vendor_hyp_bmap_2;
fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2;
break;
default:
return -ENOENT;
}
/* Check for unsupported bit */
if (val & ~fw_reg_features)
return -EINVAL;
mutex_lock(&kvm->arch.config_lock);
if (kvm_vm_has_ran_once(kvm) && val != *fw_reg_bmap) {
ret = -EBUSY;
goto out;
}
WRITE_ONCE(*fw_reg_bmap, val);
out:
mutex_unlock(&kvm->arch.config_lock);
return ret;
}
int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
void __user *uaddr = (void __user *)(long)reg->addr;
u64 val;
int wa_level;
if (KVM_REG_SIZE(reg->id) != sizeof(val))
return -ENOENT;
if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
return -EFAULT;
switch (reg->id) {
case KVM_REG_ARM_PSCI_VERSION:
{
bool wants_02;
wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2);
switch (val) {
case KVM_ARM_PSCI_0_1:
if (wants_02)
return -EINVAL;
vcpu->kvm->arch.psci_version = val;
return 0;
case KVM_ARM_PSCI_0_2:
case KVM_ARM_PSCI_1_0:
case KVM_ARM_PSCI_1_1:
case KVM_ARM_PSCI_1_2:
case KVM_ARM_PSCI_1_3:
if (!wants_02)
return -EINVAL;
vcpu->kvm->arch.psci_version = val;
return 0;
}
break;
}
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
return -EINVAL;
if (get_kernel_wa_level(vcpu, reg->id) < val)
return -EINVAL;
return 0;
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
return -EINVAL;
/* The enabled bit must not be set unless the level is AVAIL. */
if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) &&
(val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL)
return -EINVAL;
/*
* Map all the possible incoming states to the only two we
* really want to deal with.
*/
switch (val & KVM_REG_FEATURE_LEVEL_MASK) {
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
break;
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
break;
default:
return -EINVAL;
}
/*
* We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
* other way around.
*/
if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
return -EINVAL;
return 0;
case KVM_REG_ARM_STD_BMAP:
case KVM_REG_ARM_STD_HYP_BMAP:
case KVM_REG_ARM_VENDOR_HYP_BMAP:
case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val);
default:
return -ENOENT;
}
return -EINVAL;
}
int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
switch (attr->attr) {
case KVM_ARM_VM_SMCCC_FILTER:
return 0;
default:
return -ENXIO;
}
}
int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
void __user *uaddr = (void __user *)attr->addr;
switch (attr->attr) {
case KVM_ARM_VM_SMCCC_FILTER:
return kvm_smccc_set_filter(kvm, uaddr);
default:
return -ENXIO;
}
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MM_TYPES_H
#define _LINUX_MM_TYPES_H
#include <linux/mm_types_task.h>
#include <linux/auxvec.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/rbtree.h>
#include <linux/maple_tree.h>
#include <linux/rwsem.h>
#include <linux/completion.h>
#include <linux/cpumask.h>
#include <linux/uprobes.h>
#include <linux/rcupdate.h>
#include <linux/page-flags-layout.h>
#include <linux/workqueue.h>
#include <linux/seqlock.h>
#include <linux/percpu_counter.h>
#include <linux/types.h>
#include <asm/mmu.h>
#ifndef AT_VECTOR_SIZE_ARCH
#define AT_VECTOR_SIZE_ARCH 0
#endif
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
#define INIT_PASID 0
struct address_space;
struct mem_cgroup;
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
* moment. Note that we have no way to track which tasks are using
* a page, though if it is a pagecache page, rmap structures can tell us
* who is mapping it.
*
* If you allocate the page using alloc_pages(), you can use some of the
* space in struct page for your own purposes. The five words in the main
* union are available, except for bit 0 of the first word which must be
* kept clear. Many users use this word to store a pointer to an object
* which is guaranteed to be aligned. If you use the same storage as
* page->mapping, you must restore it to NULL before freeing the page.
*
* The mapcount field must not be used for own purposes.
*
* If you want to use the refcount field, it must be used in such a way
* that other CPUs temporarily incrementing and then decrementing the
* refcount does not cause problems. On receiving the page from
* alloc_pages(), the refcount will be positive.
*
* If you allocate pages of order > 0, you can use some of the fields
* in each subpage, but you may need to restore some of their values
* afterwards.
*
* SLUB uses cmpxchg_double() to atomically update its freelist and counters.
* That requires that freelist & counters in struct slab be adjacent and
* double-word aligned. Because struct slab currently just reinterprets the
* bits of struct page, we align all struct pages to double-word boundaries,
* and ensure that 'freelist' is aligned within struct slab.
*/
#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
#define _struct_page_alignment __aligned(2 * sizeof(unsigned long))
#else
#define _struct_page_alignment __aligned(sizeof(unsigned long))
#endif
struct page {
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
/*
* Five words (20/40 bytes) are available in this union.
* WARNING: bit 0 of the first word is used for PageTail(). That
* means the other users of this union MUST NOT use the bit to
* avoid collision and false-positive PageTail().
*/
union {
struct { /* Page cache and anonymous pages */
/**
* @lru: Pageout list, eg. active_list protected by
* lruvec->lru_lock. Sometimes used as a generic list
* by the page owner.
*/
union {
struct list_head lru;
/* Or, for the Unevictable "LRU list" slot */
struct {
/* Always even, to negate PageTail */
void *__filler;
/* Count page's or folio's mlocks */
unsigned int mlock_count;
};
/* Or, free page */
struct list_head buddy_list;
struct list_head pcp_list;
struct {
struct llist_node pcp_llist;
unsigned int order;
};
};
/* See page-flags.h for PAGE_MAPPING_FLAGS */
struct address_space *mapping;
union {
pgoff_t index; /* Our offset within mapping. */
unsigned long share; /* share count for fsdax */
};
/**
* @private: Mapping-private opaque data.
* Usually used for buffer_heads if PagePrivate.
* Used for swp_entry_t if swapcache flag set.
* Indicates order in the buddy system if PageBuddy.
*/
unsigned long private;
};
struct { /* page_pool used by netstack */
/**
* @pp_magic: magic value to avoid recycling non
* page_pool allocated pages.
*/
unsigned long pp_magic;
struct page_pool *pp;
unsigned long _pp_mapping_pad;
unsigned long dma_addr;
atomic_long_t pp_ref_count;
};
struct { /* Tail pages of compound page */
unsigned long compound_head; /* Bit zero is set */
};
struct { /* ZONE_DEVICE pages */
/*
* The first word is used for compound_head or folio
* pgmap
*/
void *_unused_pgmap_compound_head;
void *zone_device_data;
/*
* ZONE_DEVICE private pages are counted as being
* mapped so the next 3 words hold the mapping, index,
* and private fields from the source anonymous or
* page cache page while the page is migrated to device
* private memory.
* ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also
* use the mapping, index, and private fields when
* pmem backed DAX files are mapped.
*/
};
/** @rcu_head: You can use this to free a page by RCU. */
struct rcu_head rcu_head;
};
union { /* This union is 4 bytes in size. */
/*
* For head pages of typed folios, the value stored here
* allows for determining what this page is used for. The
* tail pages of typed folios will not store a type
* (page_type == _mapcount == -1).
*
* See page-flags.h for a list of page types which are currently
* stored here.
*
* Owners of typed folios may reuse the lower 16 bit of the
* head page page_type field after setting the page type,
* but must reset these 16 bit to -1 before clearing the
* page type.
*/
unsigned int page_type;
/*
* For pages that are part of non-typed folios for which mappings
* are tracked via the RMAP, encodes the number of times this page
* is directly referenced by a page table.
*
* Note that the mapcount is always initialized to -1, so that
* transitions both from it and to it can be tracked, using
* atomic_inc_and_test() and atomic_add_negative(-1).
*/
atomic_t _mapcount;
};
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
atomic_t _refcount;
#ifdef CONFIG_MEMCG
unsigned long memcg_data;
#elif defined(CONFIG_SLAB_OBJ_EXT)
unsigned long _unused_slab_obj_exts;
#endif
/*
* On machines where all RAM is mapped into kernel address space,
* we can simply calculate the virtual address. On machines with
* highmem some memory is mapped into kernel virtual memory
* dynamically, so we need a place to store that address.
* Note that this field could be 16 bits on x86 ... ;)
*
* Architectures with slow multiplication can define
* WANT_PAGE_VIRTUAL in asm/page.h
*/
#if defined(WANT_PAGE_VIRTUAL)
void *virtual; /* Kernel virtual address (NULL if
not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
#ifdef CONFIG_KMSAN
/*
* KMSAN metadata for this page:
* - shadow page: every bit indicates whether the corresponding
* bit of the original page is initialized (0) or not (1);
* - origin page: every 4 bytes contain an id of the stack trace
* where the uninitialized value was created.
*/
struct page *kmsan_shadow;
struct page *kmsan_origin;
#endif
} _struct_page_alignment;
/*
* struct encoded_page - a nonexistent type marking this pointer
*
* An 'encoded_page' pointer is a pointer to a regular 'struct page', but
* with the low bits of the pointer indicating extra context-dependent
* information. Only used in mmu_gather handling, and this acts as a type
* system check on that use.
*
* We only really have two guaranteed bits in general, although you could
* play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
* for more.
*
* Use the supplied helper functions to endcode/decode the pointer and bits.
*/
struct encoded_page;
#define ENCODED_PAGE_BITS 3ul
/* Perform rmap removal after we have flushed the TLB. */
#define ENCODED_PAGE_BIT_DELAY_RMAP 1ul
/*
* The next item in an encoded_page array is the "nr_pages" argument, specifying
* the number of consecutive pages starting from this page, that all belong to
* the same folio. For example, "nr_pages" corresponds to the number of folio
* references that must be dropped. If this bit is not set, "nr_pages" is
* implicitly 1.
*/
#define ENCODED_PAGE_BIT_NR_PAGES_NEXT 2ul
static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags)
{
BUILD_BUG_ON(flags > ENCODED_PAGE_BITS);
return (struct encoded_page *)(flags | (unsigned long)page);
}
static inline unsigned long encoded_page_flags(struct encoded_page *page)
{
return ENCODED_PAGE_BITS & (unsigned long)page;
}
static inline struct page *encoded_page_ptr(struct encoded_page *page)
{
return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page);
}
static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr)
{
VM_WARN_ON_ONCE((nr << 2) >> 2 != nr);
return (struct encoded_page *)(nr << 2);
}
static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page)
{
return ((unsigned long)page) >> 2;
}
/*
* A swap entry has to fit into a "unsigned long", as the entry is hidden
* in the "index" field of the swapper address space.
*/
typedef struct {
unsigned long val;
} swp_entry_t;
#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT)
/* We have some extra room after the refcount in tail pages. */
#define NR_PAGES_IN_LARGE_FOLIO
#endif
/*
* On 32bit, we can cut the required metadata in half, because:
* (a) PID_MAX_LIMIT implicitly limits the number of MMs we could ever have,
* so we can limit MM IDs to 15 bit (32767).
* (b) We don't expect folios where even a single complete PTE mapping by
* one MM would exceed 15 bits (order-15).
*/
#ifdef CONFIG_64BIT
typedef int mm_id_mapcount_t;
#define MM_ID_MAPCOUNT_MAX INT_MAX
typedef unsigned int mm_id_t;
#else /* !CONFIG_64BIT */
typedef short mm_id_mapcount_t;
#define MM_ID_MAPCOUNT_MAX SHRT_MAX
typedef unsigned short mm_id_t;
#endif /* CONFIG_64BIT */
/* We implicitly use the dummy ID for init-mm etc. where we never rmap pages. */
#define MM_ID_DUMMY 0
#define MM_ID_MIN (MM_ID_DUMMY + 1)
/*
* We leave the highest bit of each MM id unused, so we can store a flag
* in the highest bit of each folio->_mm_id[].
*/
#define MM_ID_BITS ((sizeof(mm_id_t) * BITS_PER_BYTE) - 1)
#define MM_ID_MASK ((1U << MM_ID_BITS) - 1)
#define MM_ID_MAX MM_ID_MASK
/*
* In order to use bit_spin_lock(), which requires an unsigned long, we
* operate on folio->_mm_ids when working on flags.
*/
#define FOLIO_MM_IDS_LOCK_BITNUM MM_ID_BITS
#define FOLIO_MM_IDS_LOCK_BIT BIT(FOLIO_MM_IDS_LOCK_BITNUM)
#define FOLIO_MM_IDS_SHARED_BITNUM (2 * MM_ID_BITS + 1)
#define FOLIO_MM_IDS_SHARED_BIT BIT(FOLIO_MM_IDS_SHARED_BITNUM)
/**
* struct folio - Represents a contiguous set of bytes.
* @flags: Identical to the page flags.
* @lru: Least Recently Used list; tracks how recently this folio was used.
* @mlock_count: Number of times this folio has been pinned by mlock().
* @mapping: The file this page belongs to, or refers to the anon_vma for
* anonymous memory.
* @index: Offset within the file, in units of pages. For anonymous memory,
* this is the index from the beginning of the mmap.
* @share: number of DAX mappings that reference this folio. See
* dax_associate_entry.
* @private: Filesystem per-folio data (see folio_attach_private()).
* @swap: Used for swp_entry_t if folio_test_swapcache().
* @_mapcount: Do not access this member directly. Use folio_mapcount() to
* find out how many times this folio is mapped by userspace.
* @_refcount: Do not access this member directly. Use folio_ref_count()
* to find how many references there are to this folio.
* @memcg_data: Memory Control Group data.
* @pgmap: Metadata for ZONE_DEVICE mappings
* @virtual: Virtual address in the kernel direct map.
* @_last_cpupid: IDs of last CPU and last process that accessed the folio.
* @_entire_mapcount: Do not use directly, call folio_entire_mapcount().
* @_large_mapcount: Do not use directly, call folio_mapcount().
* @_nr_pages_mapped: Do not use outside of rmap and debug code.
* @_pincount: Do not use directly, call folio_maybe_dma_pinned().
* @_nr_pages: Do not use directly, call folio_nr_pages().
* @_mm_id: Do not use outside of rmap code.
* @_mm_ids: Do not use outside of rmap code.
* @_mm_id_mapcount: Do not use outside of rmap code.
* @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h.
* @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h.
* @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h.
* @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head().
* @_deferred_list: Folios to be split under memory pressure.
* @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab.
*
* A folio is a physically, virtually and logically contiguous set
* of bytes. It is a power-of-two in size, and it is aligned to that
* same power-of-two. It is at least as large as %PAGE_SIZE. If it is
* in the page cache, it is at a file offset which is a multiple of that
* power-of-two. It may be mapped into userspace at an address which is
* at an arbitrary page offset, but its kernel virtual address is aligned
* to its size.
*/
struct folio {
/* private: don't document the anon union */
union {
struct {
/* public: */
unsigned long flags;
union {
struct list_head lru;
/* private: avoid cluttering the output */
struct {
void *__filler;
/* public: */
unsigned int mlock_count;
/* private: */
};
/* public: */
struct dev_pagemap *pgmap;
};
struct address_space *mapping;
union {
pgoff_t index;
unsigned long share;
};
union {
void *private;
swp_entry_t swap;
};
atomic_t _mapcount;
atomic_t _refcount;
#ifdef CONFIG_MEMCG
unsigned long memcg_data;
#elif defined(CONFIG_SLAB_OBJ_EXT)
unsigned long _unused_slab_obj_exts;
#endif
#if defined(WANT_PAGE_VIRTUAL)
void *virtual;
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
/* private: the union with struct page is transitional */
};
struct page page;
};
union {
struct {
unsigned long _flags_1;
unsigned long _head_1;
union {
struct {
/* public: */
atomic_t _large_mapcount;
atomic_t _nr_pages_mapped;
#ifdef CONFIG_64BIT
atomic_t _entire_mapcount;
atomic_t _pincount;
#endif /* CONFIG_64BIT */
mm_id_mapcount_t _mm_id_mapcount[2];
union {
mm_id_t _mm_id[2];
unsigned long _mm_ids;
};
/* private: the union with struct page is transitional */
};
unsigned long _usable_1[4];
};
atomic_t _mapcount_1;
atomic_t _refcount_1;
/* public: */
#ifdef NR_PAGES_IN_LARGE_FOLIO
unsigned int _nr_pages;
#endif /* NR_PAGES_IN_LARGE_FOLIO */
/* private: the union with struct page is transitional */
};
struct page __page_1;
};
union {
struct {
unsigned long _flags_2;
unsigned long _head_2;
/* public: */
struct list_head _deferred_list;
#ifndef CONFIG_64BIT
atomic_t _entire_mapcount;
atomic_t _pincount;
#endif /* !CONFIG_64BIT */
/* private: the union with struct page is transitional */
};
struct page __page_2;
};
union {
struct {
unsigned long _flags_3;
unsigned long _head_3;
/* public: */
void *_hugetlb_subpool;
void *_hugetlb_cgroup;
void *_hugetlb_cgroup_rsvd;
void *_hugetlb_hwpoison;
/* private: the union with struct page is transitional */
};
struct page __page_3;
};
};
#define FOLIO_MATCH(pg, fl) \
static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))
FOLIO_MATCH(flags, flags);
FOLIO_MATCH(lru, lru);
FOLIO_MATCH(mapping, mapping);
FOLIO_MATCH(compound_head, lru);
FOLIO_MATCH(index, index);
FOLIO_MATCH(private, private);
FOLIO_MATCH(_mapcount, _mapcount);
FOLIO_MATCH(_refcount, _refcount);
#ifdef CONFIG_MEMCG
FOLIO_MATCH(memcg_data, memcg_data);
#endif
#if defined(WANT_PAGE_VIRTUAL)
FOLIO_MATCH(virtual, virtual);
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
FOLIO_MATCH(_last_cpupid, _last_cpupid);
#endif
#undef FOLIO_MATCH
#define FOLIO_MATCH(pg, fl) \
static_assert(offsetof(struct folio, fl) == \
offsetof(struct page, pg) + sizeof(struct page))
FOLIO_MATCH(flags, _flags_1);
FOLIO_MATCH(compound_head, _head_1);
FOLIO_MATCH(_mapcount, _mapcount_1);
FOLIO_MATCH(_refcount, _refcount_1);
#undef FOLIO_MATCH
#define FOLIO_MATCH(pg, fl) \
static_assert(offsetof(struct folio, fl) == \
offsetof(struct page, pg) + 2 * sizeof(struct page))
FOLIO_MATCH(flags, _flags_2);
FOLIO_MATCH(compound_head, _head_2);
#undef FOLIO_MATCH
#define FOLIO_MATCH(pg, fl) \
static_assert(offsetof(struct folio, fl) == \
offsetof(struct page, pg) + 3 * sizeof(struct page))
FOLIO_MATCH(flags, _flags_3);
FOLIO_MATCH(compound_head, _head_3);
#undef FOLIO_MATCH
/**
* struct ptdesc - Memory descriptor for page tables.
* @__page_flags: Same as page flags. Powerpc only.
* @pt_rcu_head: For freeing page table pages.
* @pt_list: List of used page tables. Used for s390 gmap shadow pages
* (which are not linked into the user page tables) and x86
* pgds.
* @_pt_pad_1: Padding that aliases with page's compound head.
* @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs.
* @__page_mapping: Aliases with page->mapping. Unused for page tables.
* @pt_index: Used for s390 gmap.
* @pt_mm: Used for x86 pgds.
* @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
* @pt_share_count: Used for HugeTLB PMD page table share count.
* @_pt_pad_2: Padding to ensure proper alignment.
* @ptl: Lock for the page table.
* @__page_type: Same as page->page_type. Unused for page tables.
* @__page_refcount: Same as page refcount.
* @pt_memcg_data: Memcg data. Tracked for page tables here.
*
* This struct overlays struct page for now. Do not modify without a good
* understanding of the issues.
*/
struct ptdesc {
unsigned long __page_flags;
union {
struct rcu_head pt_rcu_head;
struct list_head pt_list;
struct {
unsigned long _pt_pad_1;
pgtable_t pmd_huge_pte;
};
};
unsigned long __page_mapping;
union {
pgoff_t pt_index;
struct mm_struct *pt_mm;
atomic_t pt_frag_refcount;
#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
atomic_t pt_share_count;
#endif
};
union {
unsigned long _pt_pad_2;
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
#endif
};
unsigned int __page_type;
atomic_t __page_refcount;
#ifdef CONFIG_MEMCG
unsigned long pt_memcg_data;
#endif
};
#define TABLE_MATCH(pg, pt) \
static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt))
TABLE_MATCH(flags, __page_flags);
TABLE_MATCH(compound_head, pt_list);
TABLE_MATCH(compound_head, _pt_pad_1);
TABLE_MATCH(mapping, __page_mapping);
TABLE_MATCH(index, pt_index);
TABLE_MATCH(rcu_head, pt_rcu_head);
TABLE_MATCH(page_type, __page_type);
TABLE_MATCH(_refcount, __page_refcount);
#ifdef CONFIG_MEMCG
TABLE_MATCH(memcg_data, pt_memcg_data);
#endif
#undef TABLE_MATCH
static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
#define ptdesc_page(pt) (_Generic((pt), \
const struct ptdesc *: (const struct page *)(pt), \
struct ptdesc *: (struct page *)(pt)))
#define ptdesc_folio(pt) (_Generic((pt), \
const struct ptdesc *: (const struct folio *)(pt), \
struct ptdesc *: (struct folio *)(pt)))
#define page_ptdesc(p) (_Generic((p), \
const struct page *: (const struct ptdesc *)(p), \
struct page *: (struct ptdesc *)(p)))
#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
{
atomic_set(&ptdesc->pt_share_count, 0);
}
static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
{
atomic_inc(&ptdesc->pt_share_count);
}
static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
{
atomic_dec(&ptdesc->pt_share_count);
}
static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
{
return atomic_read(&ptdesc->pt_share_count);
}
#else
static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
{
}
#endif
/*
* Used for sizing the vmemmap region on some architectures
*/
#define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page)))
/*
* page_private can be used on tail pages. However, PagePrivate is only
* checked by the VM on the head page. So page_private on the tail pages
* should be used for data that's ancillary to the head page (eg attaching
* buffer heads to tail pages after attaching buffer heads to the head page)
*/
#define page_private(page) ((page)->private)
static inline void set_page_private(struct page *page, unsigned long private)
{
page->private = private;
}
static inline void *folio_get_private(struct folio *folio)
{
return folio->private;
}
typedef unsigned long vm_flags_t;
/*
* freeptr_t represents a SLUB freelist pointer, which might be encoded
* and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
*/
typedef struct { unsigned long v; } freeptr_t;
/*
* A region containing a mapping of a non-memory backed file under NOMMU
* conditions. These are held in a global tree and are pinned by the VMAs that
* map parts of them.
*/
struct vm_region {
struct rb_node vm_rb; /* link in global region tree */
vm_flags_t vm_flags; /* VMA vm_flags */
unsigned long vm_start; /* start address of region */
unsigned long vm_end; /* region initialised to here */
unsigned long vm_top; /* region allocated to here */
unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
struct file *vm_file; /* the backing file or NULL */
int vm_usage; /* region usage count (access under nommu_region_sem) */
bool vm_icache_flushed : 1; /* true if the icache has been flushed for
* this region */
};
#ifdef CONFIG_USERFAULTFD
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, })
struct vm_userfaultfd_ctx {
struct userfaultfd_ctx *ctx;
};
#else /* CONFIG_USERFAULTFD */
#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {})
struct vm_userfaultfd_ctx {};
#endif /* CONFIG_USERFAULTFD */
struct anon_vma_name {
struct kref kref;
/* The name needs to be at the end because it is dynamically sized. */
char name[];
};
#ifdef CONFIG_ANON_VMA_NAME
/*
* mmap_lock should be read-locked when calling anon_vma_name(). Caller should
* either keep holding the lock while using the returned pointer or it should
* raise anon_vma_name refcount before releasing the lock.
*/
struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma);
struct anon_vma_name *anon_vma_name_alloc(const char *name);
void anon_vma_name_free(struct kref *kref);
#else /* CONFIG_ANON_VMA_NAME */
static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
{
return NULL;
}
static inline struct anon_vma_name *anon_vma_name_alloc(const char *name)
{
return NULL;
}
#endif
#define VMA_LOCK_OFFSET 0x40000000
#define VMA_REF_LIMIT (VMA_LOCK_OFFSET - 1)
struct vma_numab_state {
/*
* Initialised as time in 'jiffies' after which VMA
* should be scanned. Delays first scan of new VMA by at
* least sysctl_numa_balancing_scan_delay:
*/
unsigned long next_scan;
/*
* Time in jiffies when pids_active[] is reset to
* detect phase change behaviour:
*/
unsigned long pids_active_reset;
/*
* Approximate tracking of PIDs that trapped a NUMA hinting
* fault. May produce false positives due to hash collisions.
*
* [0] Previous PID tracking
* [1] Current PID tracking
*
* Window moves after next_pid_reset has expired approximately
* every VMA_PID_RESET_PERIOD jiffies:
*/
unsigned long pids_active[2];
/* MM scan sequence ID when scan first started after VMA creation */
int start_scan_seq;
/*
* MM scan sequence ID when the VMA was last completely scanned.
* A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
*/
int prev_scan_seq;
};
/*
* This struct describes a virtual memory area. There is one of these
* per VM-area/task. A VM area is any part of the process virtual memory
* space that has a special rule for the page-fault handlers (ie a shared
* library, the executable area etc).
*
* Only explicitly marked struct members may be accessed by RCU readers before
* getting a stable reference.
*
* WARNING: when adding new members, please update vm_area_init_from() to copy
* them during vm_area_struct content duplication.
*/
struct vm_area_struct {
/* The first cache line has the info for VMA tree walking. */
union {
struct {
/* VMA covers [vm_start; vm_end) addresses within mm */
unsigned long vm_start;
unsigned long vm_end;
};
freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
};
/*
* The address space we belong to.
* Unstable RCU readers are allowed to read this.
*/
struct mm_struct *vm_mm;
pgprot_t vm_page_prot; /* Access permissions of this VMA. */
/*
* Flags, see mm.h.
* To modify use vm_flags_{init|reset|set|clear|mod} functions.
*/
union {
const vm_flags_t vm_flags;
vm_flags_t __private __vm_flags;
};
#ifdef CONFIG_PER_VMA_LOCK
/*
* Can only be written (using WRITE_ONCE()) while holding both:
* - mmap_lock (in write mode)
* - vm_refcnt bit at VMA_LOCK_OFFSET is set
* Can be read reliably while holding one of:
* - mmap_lock (in read or write mode)
* - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
* Can be read unreliably (using READ_ONCE()) for pessimistic bailout
* while holding nothing (except RCU to keep the VMA struct allocated).
*
* This sequence counter is explicitly allowed to overflow; sequence
* counter reuse can only lead to occasional unnecessary use of the
* slowpath.
*/
unsigned int vm_lock_seq;
#endif
/*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
* list, after a COW of one of the file pages. A MAP_SHARED vma
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
* or brk vma (with NULL file) can only be in an anon_vma list.
*/
struct list_head anon_vma_chain; /* Serialized by mmap_lock &
* page_table_lock */
struct anon_vma *anon_vma; /* Serialized by page_table_lock */
/* Function pointers to deal with this struct. */
const struct vm_operations_struct *vm_ops;
/* Information about our backing store: */
unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
units */
struct file * vm_file; /* File we map to (can be NULL). */
void * vm_private_data; /* was vm_pte (shared mem) */
#ifdef CONFIG_SWAP
atomic_long_t swap_readahead_info;
#endif
#ifndef CONFIG_MMU
struct vm_region *vm_region; /* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
#ifdef CONFIG_NUMA_BALANCING
struct vma_numab_state *numab_state; /* NUMA Balancing state */
#endif
#ifdef CONFIG_PER_VMA_LOCK
/* Unstable RCU readers are allowed to read this. */
refcount_t vm_refcnt ____cacheline_aligned_in_smp;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map vmlock_dep_map;
#endif
#endif
/*
* For areas with an address space and backing store,
* linkage into the address_space->i_mmap interval tree.
*
*/
struct {
struct rb_node rb;
unsigned long rb_subtree_last;
} shared;
#ifdef CONFIG_ANON_VMA_NAME
/*
* For private and shared anonymous mappings, a pointer to a null
* terminated string containing the name given to the vma, or NULL if
* unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
*/
struct anon_vma_name *anon_name;
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;
#ifdef CONFIG_NUMA
#define vma_policy(vma) ((vma)->vm_policy)
#else
#define vma_policy(vma) NULL
#endif
#ifdef CONFIG_SCHED_MM_CID
struct mm_cid {
u64 time;
int cid;
int recent_cid;
};
#endif
struct kioctx_table;
struct iommu_mm_data;
struct mm_struct {
struct {
/*
* Fields which are often written to are placed in a separate
* cache line.
*/
struct {
/**
* @mm_count: The number of references to &struct
* mm_struct (@mm_users count as 1).
*
* Use mmgrab()/mmdrop() to modify. When this drops to
* 0, the &struct mm_struct is freed.
*/
atomic_t mm_count;
} ____cacheline_aligned_in_smp;
struct maple_tree mm_mt;
unsigned long mmap_base; /* base of mmap area */
unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
/* Base addresses for compatible mmap() */
unsigned long mmap_compat_base;
unsigned long mmap_compat_legacy_base;
#endif
unsigned long task_size; /* size of task vm space */
pgd_t * pgd;
#ifdef CONFIG_MEMBARRIER
/**
* @membarrier_state: Flags controlling membarrier behavior.
*
* This field is close to @pgd to hopefully fit in the same
* cache-line, which needs to be touched by switch_mm().
*/
atomic_t membarrier_state;
#endif
/**
* @mm_users: The number of users including userspace.
*
* Use mmget()/mmget_not_zero()/mmput() to modify. When this
* drops to 0 (i.e. when the task exits and there are no other
* temporary reference holders), we also release a reference on
* @mm_count (which may then free the &struct mm_struct if
* @mm_count also drops to 0).
*/
atomic_t mm_users;
#ifdef CONFIG_SCHED_MM_CID
/**
* @pcpu_cid: Per-cpu current cid.
*
* Keep track of the currently allocated mm_cid for each cpu.
* The per-cpu mm_cid values are serialized by their respective
* runqueue locks.
*/
struct mm_cid __percpu *pcpu_cid;
/*
* @mm_cid_next_scan: Next mm_cid scan (in jiffies).
*
* When the next mm_cid scan is due (in jiffies).
*/
unsigned long mm_cid_next_scan;
/**
* @nr_cpus_allowed: Number of CPUs allowed for mm.
*
* Number of CPUs allowed in the union of all mm's
* threads allowed CPUs.
*/
unsigned int nr_cpus_allowed;
/**
* @max_nr_cid: Maximum number of allowed concurrency
* IDs allocated.
*
* Track the highest number of allowed concurrency IDs
* allocated for the mm.
*/
atomic_t max_nr_cid;
/**
* @cpus_allowed_lock: Lock protecting mm cpus_allowed.
*
* Provide mutual exclusion for mm cpus_allowed and
* mm nr_cpus_allowed updates.
*/
raw_spinlock_t cpus_allowed_lock;
#endif
#ifdef CONFIG_MMU
atomic_long_t pgtables_bytes; /* size of all page tables */
#endif
int map_count; /* number of VMAs */
spinlock_t page_table_lock; /* Protects page tables and some
* counters
*/
/*
* With some kernel config, the current mmap_lock's offset
* inside 'mm_struct' is at 0x120, which is very optimal, as
* its two hot fields 'count' and 'owner' sit in 2 different
* cachelines, and when mmap_lock is highly contended, both
* of the 2 fields will be accessed frequently, current layout
* will help to reduce cache bouncing.
*
* So please be careful with adding new fields before
* mmap_lock, which can easily push the 2 fields into one
* cacheline.
*/
struct rw_semaphore mmap_lock;
struct list_head mmlist; /* List of maybe swapped mm's. These
* are globally strung together off
* init_mm.mmlist, and are protected
* by mmlist_lock
*/
#ifdef CONFIG_PER_VMA_LOCK
struct rcuwait vma_writer_wait;
/*
* This field has lock-like semantics, meaning it is sometimes
* accessed with ACQUIRE/RELEASE semantics.
* Roughly speaking, incrementing the sequence number is
* equivalent to releasing locks on VMAs; reading the sequence
* number can be part of taking a read lock on a VMA.
* Incremented every time mmap_lock is write-locked/unlocked.
* Initialized to 0, therefore odd values indicate mmap_lock
* is write-locked and even values that it's released.
*
* Can be modified under write mmap_lock using RELEASE
* semantics.
* Can be read with no other protection when holding write
* mmap_lock.
* Can be read with ACQUIRE semantics if not holding write
* mmap_lock.
*/
seqcount_t mm_lock_seq;
#endif
unsigned long hiwater_rss; /* High-watermark of RSS usage */
unsigned long hiwater_vm; /* High-water virtual memory usage */
unsigned long total_vm; /* Total pages mapped */
unsigned long locked_vm; /* Pages that have PG_mlocked set */
atomic64_t pinned_vm; /* Refcount permanently increased */
unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
unsigned long stack_vm; /* VM_STACK */
unsigned long def_flags;
/**
* @write_protect_seq: Locked when any thread is write
* protecting pages mapped by this mm to enforce a later COW,
* for instance during page table copying for fork().
*/
seqcount_t write_protect_seq;
spinlock_t arg_lock; /* protect the below fields */
unsigned long start_code, end_code, start_data, end_data;
unsigned long start_brk, brk, start_stack;
unsigned long arg_start, arg_end, env_start, env_end;
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
struct percpu_counter rss_stat[NR_MM_COUNTERS];
struct linux_binfmt *binfmt;
/* Architecture-specific MM context */
mm_context_t context;
unsigned long flags; /* Must use atomic bitops to access */
#ifdef CONFIG_AIO
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
#endif
#ifdef CONFIG_MEMCG
/*
* "owner" points to a task that is regarded as the canonical
* user/owner of this mm. All of the following must be true in
* order for it to be changed:
*
* current == mm->owner
* current->mm != mm
* new_owner->mm == mm
* new_owner->alloc_lock is held
*/
struct task_struct __rcu *owner;
#endif
struct user_namespace *user_ns;
/* store ref to file /proc/<pid>/exe symlink points to */
struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER
struct mmu_notifier_subscriptions *notifier_subscriptions;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_NUMA_BALANCING
/*
* numa_next_scan is the next time that PTEs will be remapped
* PROT_NONE to trigger NUMA hinting faults; such faults gather
* statistics and migrate pages to new nodes if necessary.
*/
unsigned long numa_next_scan;
/* Restart point for scanning and remapping PTEs. */
unsigned long numa_scan_offset;
/* numa_scan_seq prevents two threads remapping PTEs. */
int numa_scan_seq;
#endif
/*
* An operation with batched TLB flushing is going on. Anything
* that can move process memory needs to flush the TLB when
* moving a PROT_NONE mapped page.
*/
atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/* See flush_tlb_batched_pending() */
atomic_t tlb_flush_batched;
#endif
struct uprobes_state uprobes_state;
#ifdef CONFIG_PREEMPT_RT
struct rcu_head delayed_drop;
#endif
#ifdef CONFIG_HUGETLB_PAGE
atomic_long_t hugetlb_usage;
#endif
struct work_struct async_put_work;
#ifdef CONFIG_IOMMU_MM_DATA
struct iommu_mm_data *iommu_mm;
#endif
#ifdef CONFIG_KSM
/*
* Represent how many pages of this process are involved in KSM
* merging (not including ksm_zero_pages).
*/
unsigned long ksm_merging_pages;
/*
* Represent how many pages are checked for ksm merging
* including merged and not merged.
*/
unsigned long ksm_rmap_items;
/*
* Represent how many empty pages are merged with kernel zero
* pages when enabling KSM use_zero_pages.
*/
atomic_long_t ksm_zero_pages;
#endif /* CONFIG_KSM */
#ifdef CONFIG_LRU_GEN_WALKS_MMU
struct {
/* this mm_struct is on lru_gen_mm_list */
struct list_head list;
/*
* Set when switching to this mm_struct, as a hint of
* whether it has been used since the last time per-node
* page table walkers cleared the corresponding bits.
*/
unsigned long bitmap;
#ifdef CONFIG_MEMCG
/* points to the memcg of "owner" above */
struct mem_cgroup *memcg;
#endif
} lru_gen;
#endif /* CONFIG_LRU_GEN_WALKS_MMU */
#ifdef CONFIG_MM_ID
mm_id_t mm_id;
#endif /* CONFIG_MM_ID */
} __randomize_layout;
/*
* The mm_cpumask needs to be at the end of mm_struct, because it
* is dynamically sized based on nr_cpu_ids.
*/
unsigned long cpu_bitmap[];
};
#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \
MT_FLAGS_USE_RCU)
extern struct mm_struct init_mm;
/* Pointer magic because the dynamic array size confuses some compilers. */
static inline void mm_init_cpumask(struct mm_struct *mm)
{
unsigned long cpu_bitmap = (unsigned long)mm;
cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
cpumask_clear((struct cpumask *)cpu_bitmap);
}
/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
{
return (struct cpumask *)&mm->cpu_bitmap;
}
#ifdef CONFIG_LRU_GEN
struct lru_gen_mm_list {
/* mm_struct list for page table walkers */
struct list_head fifo;
/* protects the list above */
spinlock_t lock;
};
#endif /* CONFIG_LRU_GEN */
#ifdef CONFIG_LRU_GEN_WALKS_MMU
void lru_gen_add_mm(struct mm_struct *mm);
void lru_gen_del_mm(struct mm_struct *mm);
void lru_gen_migrate_mm(struct mm_struct *mm);
static inline void lru_gen_init_mm(struct mm_struct *mm)
{
INIT_LIST_HEAD(&mm->lru_gen.list);
mm->lru_gen.bitmap = 0;
#ifdef CONFIG_MEMCG
mm->lru_gen.memcg = NULL;
#endif
}
static inline void lru_gen_use_mm(struct mm_struct *mm)
{
/*
* When the bitmap is set, page reclaim knows this mm_struct has been
* used since the last time it cleared the bitmap. So it might be worth
* walking the page tables of this mm_struct to clear the accessed bit.
*/
WRITE_ONCE(mm->lru_gen.bitmap, -1);
}
#else /* !CONFIG_LRU_GEN_WALKS_MMU */
static inline void lru_gen_add_mm(struct mm_struct *mm)
{
}
static inline void lru_gen_del_mm(struct mm_struct *mm)
{
}
static inline void lru_gen_migrate_mm(struct mm_struct *mm)
{
}
static inline void lru_gen_init_mm(struct mm_struct *mm)
{
}
static inline void lru_gen_use_mm(struct mm_struct *mm)
{
}
#endif /* CONFIG_LRU_GEN_WALKS_MMU */
struct vma_iterator {
struct ma_state mas;
};
#define VMA_ITERATOR(name, __mm, __addr) \
struct vma_iterator name = { \
.mas = { \
.tree = &(__mm)->mm_mt, \
.index = __addr, \
.node = NULL, \
.status = ma_start, \
}, \
}
static inline void vma_iter_init(struct vma_iterator *vmi,
struct mm_struct *mm, unsigned long addr)
{
mas_init(&vmi->mas, &mm->mm_mt, addr);
}
#ifdef CONFIG_SCHED_MM_CID
enum mm_cid_state {
MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */
MM_CID_LAZY_PUT = (1U << 31),
};
static inline bool mm_cid_is_unset(int cid)
{
return cid == MM_CID_UNSET;
}
static inline bool mm_cid_is_lazy_put(int cid)
{
return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT);
}
static inline bool mm_cid_is_valid(int cid)
{
return !(cid & MM_CID_LAZY_PUT);
}
static inline int mm_cid_set_lazy_put(int cid)
{
return cid | MM_CID_LAZY_PUT;
}
static inline int mm_cid_clear_lazy_put(int cid)
{
return cid & ~MM_CID_LAZY_PUT;
}
/*
* mm_cpus_allowed: Union of all mm's threads allowed CPUs.
*/
static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm)
{
unsigned long bitmap = (unsigned long)mm;
bitmap += offsetof(struct mm_struct, cpu_bitmap);
/* Skip cpu_bitmap */
bitmap += cpumask_size();
return (struct cpumask *)bitmap;
}
/* Accessor for struct mm_struct's cidmask. */
static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
{
unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm);
/* Skip mm_cpus_allowed */
cid_bitmap += cpumask_size();
return (struct cpumask *)cid_bitmap;
}
static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
{
int i;
for_each_possible_cpu(i) {
struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i);
pcpu_cid->cid = MM_CID_UNSET;
pcpu_cid->recent_cid = MM_CID_UNSET;
pcpu_cid->time = 0;
}
mm->nr_cpus_allowed = p->nr_cpus_allowed;
atomic_set(&mm->max_nr_cid, 0);
raw_spin_lock_init(&mm->cpus_allowed_lock);
cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
cpumask_clear(mm_cidmask(mm));
}
static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p)
{
mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid);
if (!mm->pcpu_cid)
return -ENOMEM;
mm_init_cid(mm, p);
return 0;
}
#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
static inline void mm_destroy_cid(struct mm_struct *mm)
{
free_percpu(mm->pcpu_cid);
mm->pcpu_cid = NULL;
}
static inline unsigned int mm_cid_size(void)
{
return 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */
}
static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask)
{
struct cpumask *mm_allowed = mm_cpus_allowed(mm);
if (!mm)
return;
/* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */
raw_spin_lock(&mm->cpus_allowed_lock);
cpumask_or(mm_allowed, mm_allowed, cpumask);
WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed));
raw_spin_unlock(&mm->cpus_allowed_lock);
}
#else /* CONFIG_SCHED_MM_CID */
static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { }
static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; }
static inline void mm_destroy_cid(struct mm_struct *mm) { }
static inline unsigned int mm_cid_size(void)
{
return 0;
}
static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { }
#endif /* CONFIG_SCHED_MM_CID */
struct mmu_gather;
extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
extern void tlb_finish_mmu(struct mmu_gather *tlb);
struct vm_fault;
/**
* typedef vm_fault_t - Return type for page fault handlers.
*
* Page fault handlers return a bitmask of %VM_FAULT values.
*/
typedef __bitwise unsigned int vm_fault_t;
/**
* enum vm_fault_reason - Page fault handlers return a bitmask of
* these values to tell the core VM what happened when handling the
* fault. Used to decide whether a process gets delivered SIGBUS or
* just gets major/minor fault counters bumped up.
*
* @VM_FAULT_OOM: Out Of Memory
* @VM_FAULT_SIGBUS: Bad access
* @VM_FAULT_MAJOR: Page read from storage
* @VM_FAULT_HWPOISON: Hit poisoned small page
* @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded
* in upper bits
* @VM_FAULT_SIGSEGV: segmentation fault
* @VM_FAULT_NOPAGE: ->fault installed the pte, not return page
* @VM_FAULT_LOCKED: ->fault locked the returned page
* @VM_FAULT_RETRY: ->fault blocked, must retry
* @VM_FAULT_FALLBACK: huge page fault failed, fall back to small
* @VM_FAULT_DONE_COW: ->fault has fully handled COW
* @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs
* fsync() to complete (for synchronous page faults
* in DAX)
* @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released
* @VM_FAULT_HINDEX_MASK: mask HINDEX value
*
*/
enum vm_fault_reason {
VM_FAULT_OOM = (__force vm_fault_t)0x000001,
VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002,
VM_FAULT_MAJOR = (__force vm_fault_t)0x000004,
VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010,
VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020,
VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040,
VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100,
VM_FAULT_LOCKED = (__force vm_fault_t)0x000200,
VM_FAULT_RETRY = (__force vm_fault_t)0x000400,
VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800,
VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000,
VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000,
VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000,
VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000,
};
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16))
#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf)
#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \
VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \
VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK)
#define VM_FAULT_RESULT_TRACE \
{ VM_FAULT_OOM, "OOM" }, \
{ VM_FAULT_SIGBUS, "SIGBUS" }, \
{ VM_FAULT_MAJOR, "MAJOR" }, \
{ VM_FAULT_HWPOISON, "HWPOISON" }, \
{ VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \
{ VM_FAULT_SIGSEGV, "SIGSEGV" }, \
{ VM_FAULT_NOPAGE, "NOPAGE" }, \
{ VM_FAULT_LOCKED, "LOCKED" }, \
{ VM_FAULT_RETRY, "RETRY" }, \
{ VM_FAULT_FALLBACK, "FALLBACK" }, \
{ VM_FAULT_DONE_COW, "DONE_COW" }, \
{ VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \
{ VM_FAULT_COMPLETED, "COMPLETED" }
struct vm_special_mapping {
const char *name; /* The name, e.g. "[vdso]". */
/*
* If .fault is not provided, this points to a
* NULL-terminated array of pages that back the special mapping.
*
* This must not be NULL unless .fault is provided.
*/
struct page **pages;
/*
* If non-NULL, then this is called to resolve page faults
* on the special mapping. If used, .pages is not checked.
*/
vm_fault_t (*fault)(const struct vm_special_mapping *sm,
struct vm_area_struct *vma,
struct vm_fault *vmf);
int (*mremap)(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma);
void (*close)(const struct vm_special_mapping *sm,
struct vm_area_struct *vma);
};
enum tlb_flush_reason {
TLB_FLUSH_ON_TASK_SWITCH,
TLB_REMOTE_SHOOTDOWN,
TLB_LOCAL_SHOOTDOWN,
TLB_LOCAL_MM_SHOOTDOWN,
TLB_REMOTE_SEND_IPI,
TLB_REMOTE_WRONG_CPU,
NR_TLB_FLUSH_REASONS,
};
/**
* enum fault_flag - Fault flag definitions.
* @FAULT_FLAG_WRITE: Fault was a write fault.
* @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE.
* @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked.
* @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying.
* @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region.
* @FAULT_FLAG_TRIED: The fault has been tried once.
* @FAULT_FLAG_USER: The fault originated in userspace.
* @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
* @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
* @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
* @FAULT_FLAG_UNSHARE: The fault is an unsharing request to break COW in a
* COW mapping, making sure that an exclusive anon page is
* mapped after the fault.
* @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached.
* We should only access orig_pte if this flag set.
* @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock.
*
* About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
* whether we would allow page faults to retry by specifying these two
* fault flags correctly. Currently there can be three legal combinations:
*
* (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and
* this is the first try
*
* (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and
* we've already tried at least once
*
* (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry
*
* The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never
* be used. Note that page faults can be allowed to retry for multiple times,
* in which case we'll have an initial fault with flags (a) then later on
* continuous faults with flags (b). We should always try to detect pending
* signals before a retry to make sure the continuous page faults can still be
* interrupted if necessary.
*
* The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal.
* FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when
* applied to mappings that are not COW mappings.
*/
enum fault_flag {
FAULT_FLAG_WRITE = 1 << 0,
FAULT_FLAG_MKWRITE = 1 << 1,
FAULT_FLAG_ALLOW_RETRY = 1 << 2,
FAULT_FLAG_RETRY_NOWAIT = 1 << 3,
FAULT_FLAG_KILLABLE = 1 << 4,
FAULT_FLAG_TRIED = 1 << 5,
FAULT_FLAG_USER = 1 << 6,
FAULT_FLAG_REMOTE = 1 << 7,
FAULT_FLAG_INSTRUCTION = 1 << 8,
FAULT_FLAG_INTERRUPTIBLE = 1 << 9,
FAULT_FLAG_UNSHARE = 1 << 10,
FAULT_FLAG_ORIG_PTE_VALID = 1 << 11,
FAULT_FLAG_VMA_LOCK = 1 << 12,
};
typedef unsigned int __bitwise zap_flags_t;
/* Flags for clear_young_dirty_ptes(). */
typedef int __bitwise cydp_t;
/* Clear the access bit */
#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0))
/* Clear the dirty bit */
#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1))
/*
* FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
* other. Here is what they mean, and how to use them:
*
*
* FIXME: For pages which are part of a filesystem, mappings are subject to the
* lifetime enforced by the filesystem and we need guarantees that longterm
* users like RDMA and V4L2 only establish mappings which coordinate usage with
* the filesystem. Ideas for this coordination include revoking the longterm
* pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was
* added after the problem with filesystems was found FS DAX VMAs are
* specifically failed. Filesystem pages are still subject to bugs and use of
* FOLL_LONGTERM should be avoided on those pages.
*
* In the CMA case: long term pins in a CMA region would unnecessarily fragment
* that region. And so, CMA attempts to migrate the page before pinning, when
* FOLL_LONGTERM is specified.
*
* FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
* but an additional pin counting system) will be invoked. This is intended for
* anything that gets a page reference and then touches page data (for example,
* Direct IO). This lets the filesystem know that some non-file-system entity is
* potentially changing the pages' data. In contrast to FOLL_GET (whose pages
* are released via put_page()), FOLL_PIN pages must be released, ultimately, by
* a call to unpin_user_page().
*
* FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
* and separate refcounting mechanisms, however, and that means that each has
* its own acquire and release mechanisms:
*
* FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
*
* FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release.
*
* FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
* (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
* calls applied to them, and that's perfectly OK. This is a constraint on the
* callers, not on the pages.)
*
* FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
* directly by the caller. That's in order to help avoid mismatches when
* releasing pages: get_user_pages*() pages must be released via put_page(),
* while pin_user_pages*() pages must be released via unpin_user_page().
*
* Please see Documentation/core-api/pin_user_pages.rst for more information.
*/
enum {
/* check pte is writable */
FOLL_WRITE = 1 << 0,
/* do get_page on page */
FOLL_GET = 1 << 1,
/* give error on hole if it would be zero */
FOLL_DUMP = 1 << 2,
/* get_user_pages read/write w/o permission */
FOLL_FORCE = 1 << 3,
/*
* if a disk transfer is needed, start the IO and return without waiting
* upon it
*/
FOLL_NOWAIT = 1 << 4,
/* do not fault in pages */
FOLL_NOFAULT = 1 << 5,
/* check page is hwpoisoned */
FOLL_HWPOISON = 1 << 6,
/* don't do file mappings */
FOLL_ANON = 1 << 7,
/*
* FOLL_LONGTERM indicates that the page will be held for an indefinite
* time period _often_ under userspace control. This is in contrast to
* iov_iter_get_pages(), whose usages are transient.
*/
FOLL_LONGTERM = 1 << 8,
/* split huge pmd before returning */
FOLL_SPLIT_PMD = 1 << 9,
/* allow returning PCI P2PDMA pages */
FOLL_PCI_P2PDMA = 1 << 10,
/* allow interrupts from generic signals */
FOLL_INTERRUPTIBLE = 1 << 11,
/*
* Always honor (trigger) NUMA hinting faults.
*
* FOLL_WRITE implicitly honors NUMA hinting faults because a
* PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
* apply). get_user_pages_fast_only() always implicitly honors NUMA
* hinting faults.
*/
FOLL_HONOR_NUMA_FAULT = 1 << 12,
/* See also internal only FOLL flags in mm/internal.h */
};
/* mm flags */
/*
* The first two bits represent core dump modes for set-user-ID,
* the modes are SUID_DUMP_* defined in linux/sched/coredump.h
*/
#define MMF_DUMPABLE_BITS 2
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED 8
#define MMF_DUMP_DAX_PRIVATE 9
#define MMF_DUMP_DAX_SHARED 10
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 9
#define MMF_DUMP_FILTER_MASK \
(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\
(1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS)
#else
# define MMF_DUMP_MASK_DEFAULT_ELF 0
#endif
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */
/*
* This one-shot flag is dropped due to necessity of changing exe once again
* on NFS restore
*/
//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
#define MMF_HAS_UPROBES 19 /* has uprobes */
#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */
#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */
#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */
#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */
#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */
#define MMF_MULTIPROCESS 26 /* mm is shared between processes */
/*
* MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either
* replaced in the future by mm.pinned_vm when it becomes stable, or grow into
* a counter on its own. We're aggresive on this bit for now: even if the
* pinned pages were unpinned later on, we'll still keep this bit set for the
* lifecycle of this mm, just for simplicity.
*/
#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */
#define MMF_HAS_MDWE 28
#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE)
#define MMF_HAS_MDWE_NO_INHERIT 29
#define MMF_VM_MERGE_ANY 30
#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY)
#define MMF_TOPDOWN 31 /* mm searches top down by default */
#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK)
static inline unsigned long mmf_init_flags(unsigned long flags)
{
if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT))
flags &= ~((1UL << MMF_HAS_MDWE) |
(1UL << MMF_HAS_MDWE_NO_INHERIT));
return flags & MMF_INIT_MASK;
}
#endif /* _LINUX_MM_TYPES_H */
/*
* llc_core.c - Minimum needed routines for sap handling and module init/exit
*
* Copyright (c) 1997 by Procom Technology, Inc.
* 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* This program can be redistributed or modified under the terms of the
* GNU General Public License as published by the Free Software Foundation.
* This program is distributed without any warranty or implied warranty
* of merchantability or fitness for a particular purpose.
*
* See the GNU General Public License for more details.
*/
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <net/net_namespace.h>
#include <net/llc.h>
LIST_HEAD(llc_sap_list);
static DEFINE_SPINLOCK(llc_sap_list_lock);
/**
* llc_sap_alloc - allocates and initializes sap.
*
* Allocates and initializes sap.
*/
static struct llc_sap *llc_sap_alloc(void)
{
struct llc_sap *sap = kzalloc(sizeof(*sap), GFP_ATOMIC);
int i;
if (sap) {
/* sap->laddr.mac - leave as a null, it's filled by bind */
sap->state = LLC_SAP_STATE_ACTIVE;
spin_lock_init(&sap->sk_lock);
for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++)
INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i);
refcount_set(&sap->refcnt, 1);
}
return sap;
}
static struct llc_sap *__llc_sap_find(unsigned char sap_value)
{
struct llc_sap *sap;
list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value)
goto out;
sap = NULL;
out:
return sap;
}
/**
* llc_sap_find - searches a SAP in station
* @sap_value: sap to be found
*
* Searches for a sap in the sap list of the LLC's station upon the sap ID.
* If the sap is found it will be refcounted and the user will have to do
* a llc_sap_put after use.
* Returns the sap or %NULL if not found.
*/
struct llc_sap *llc_sap_find(unsigned char sap_value)
{
struct llc_sap *sap;
rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (!sap || !llc_sap_hold_safe(sap))
sap = NULL;
rcu_read_unlock_bh();
return sap;
}
/**
* llc_sap_open - open interface to the upper layers.
* @lsap: SAP number.
* @func: rcv func for datalink protos
*
* Interface function to upper layer. Each one who wants to get a SAP
* (for example NetBEUI) should call this function. Returns the opened
* SAP for success, NULL for failure.
*/
struct llc_sap *llc_sap_open(unsigned char lsap,
int (*func)(struct sk_buff *skb,
struct net_device *dev,
struct packet_type *pt,
struct net_device *orig_dev))
{
struct llc_sap *sap = NULL;
spin_lock_bh(&llc_sap_list_lock);
if (__llc_sap_find(lsap)) /* SAP already exists */
goto out;
sap = llc_sap_alloc();
if (!sap)
goto out;
sap->laddr.lsap = lsap;
sap->rcv_func = func;
list_add_tail_rcu(&sap->node, &llc_sap_list);
out:
spin_unlock_bh(&llc_sap_list_lock);
return sap;
}
/**
* llc_sap_close - close interface for upper layers.
* @sap: SAP to be closed.
*
* Close interface function to upper layer. Each one who wants to
* close an open SAP (for example NetBEUI) should call this function.
* Removes this sap from the list of saps in the station and then
* frees the memory for this sap.
*/
void llc_sap_close(struct llc_sap *sap)
{
WARN_ON(sap->sk_count);
spin_lock_bh(&llc_sap_list_lock);
list_del_rcu(&sap->node);
spin_unlock_bh(&llc_sap_list_lock);
kfree_rcu(sap, rcu);
}
static struct packet_type llc_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_802_2),
.func = llc_rcv,
};
static int __init llc_init(void)
{
dev_add_pack(&llc_packet_type);
return 0;
}
static void __exit llc_exit(void)
{
dev_remove_pack(&llc_packet_type);
}
module_init(llc_init);
module_exit(llc_exit);
EXPORT_SYMBOL(llc_sap_list);
EXPORT_SYMBOL(llc_sap_find);
EXPORT_SYMBOL(llc_sap_open);
EXPORT_SYMBOL(llc_sap_close);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003");
MODULE_DESCRIPTION("LLC IEEE 802.2 core support");
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_ENTRYKVM_H
#define __LINUX_ENTRYKVM_H
#include <linux/static_call_types.h>
#include <linux/resume_user_mode.h>
#include <linux/syscalls.h>
#include <linux/seccomp.h>
#include <linux/sched.h>
#include <linux/tick.h>
/* Transfer to guest mode work */
#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
#ifndef ARCH_XFER_TO_GUEST_MODE_WORK
# define ARCH_XFER_TO_GUEST_MODE_WORK (0)
#endif
#define XFER_TO_GUEST_MODE_WORK \
(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \
_TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \
ARCH_XFER_TO_GUEST_MODE_WORK)
struct kvm_vcpu;
/**
* arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest
* mode work handling function.
* @vcpu: Pointer to current's VCPU data
* @ti_work: Cached TIF flags gathered in xfer_to_guest_mode_handle_work()
*
* Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be
* replaced by architecture specific code.
*/
static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
unsigned long ti_work);
#ifndef arch_xfer_to_guest_mode_work
static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
unsigned long ti_work)
{
return 0;
}
#endif
/**
* xfer_to_guest_mode_handle_work - Check and handle pending work which needs
* to be handled before going to guest mode
* @vcpu: Pointer to current's VCPU data
*
* Returns: 0 or an error code
*/
int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
/**
* xfer_to_guest_mode_prepare - Perform last minute preparation work that
* need to be handled while IRQs are disabled
* upon entering to guest.
*
* Has to be invoked with interrupts disabled before the last call
* to xfer_to_guest_mode_work_pending().
*/
static inline void xfer_to_guest_mode_prepare(void)
{
lockdep_assert_irqs_disabled();
tick_nohz_user_enter_prepare();
}
/**
* __xfer_to_guest_mode_work_pending - Check if work is pending
*
* Returns: True if work pending, False otherwise.
*
* Bare variant of xfer_to_guest_mode_work_pending(). Can be called from
* interrupt enabled code for racy quick checks with care.
*/
static inline bool __xfer_to_guest_mode_work_pending(void)
{
unsigned long ti_work = read_thread_flags();
return !!(ti_work & XFER_TO_GUEST_MODE_WORK);
}
/**
* xfer_to_guest_mode_work_pending - Check if work is pending which needs to be
* handled before returning to guest mode
*
* Returns: True if work pending, False otherwise.
*
* Has to be invoked with interrupts disabled before the transition to
* guest mode.
*/
static inline bool xfer_to_guest_mode_work_pending(void)
{
lockdep_assert_irqs_disabled();
return __xfer_to_guest_mode_work_pending();
}
#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <linux/irqflags.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/tlbflush.h>
struct tlb_inv_context {
struct kvm_s2_mmu *mmu;
unsigned long flags;
u64 tcr;
u64 sctlr;
};
static void enter_vmid_context(struct kvm_s2_mmu *mmu,
struct tlb_inv_context *cxt)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
u64 val;
local_irq_save(cxt->flags); if (vcpu && mmu != vcpu->arch.hw_mmu)
cxt->mmu = vcpu->arch.hw_mmu;
else
cxt->mmu = NULL;
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
/*
* For CPUs that are affected by ARM errata 1165522 or 1530923,
* we cannot trust stage-1 to be in a correct state at that
* point. Since we do not want to force a full load of the
* vcpu state, we prevent the EL1 page-table walker to
* allocate new TLBs. This is done by setting the EPD bits
* in the TCR_EL1 register. We also need to prevent it to
* allocate IPA->PA walks, so we enable the S1 MMU...
*/
val = cxt->tcr = read_sysreg_el1(SYS_TCR);
val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
write_sysreg_el1(val, SYS_TCR);
val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
val |= SCTLR_ELx_M;
write_sysreg_el1(val, SYS_SCTLR);
}
/*
* With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
* most TLB operations target EL2/EL0. In order to affect the
* guest TLBs (EL1/EL0), we need to change one of these two
* bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
* let's flip TGE before executing the TLB operation.
*
* ARM erratum 1165522 requires some special handling (again),
* as we need to make sure both stages of translation are in
* place before clearing TGE. __load_stage2() already
* has an ISB in order to deal with this.
*/
__load_stage2(mmu, mmu->arch);
val = read_sysreg(hcr_el2);
val &= ~HCR_TGE;
write_sysreg_hcr(val);
isb();
}
static void exit_vmid_context(struct tlb_inv_context *cxt)
{
/*
* We're done with the TLB operation, let's restore the host's
* view of HCR_EL2.
*/
write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
isb();
/* ... and the stage-2 MMU context that we switched away from */
if (cxt->mmu) __load_stage2(cxt->mmu, cxt->mmu->arch); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
/* Restore the registers to what they were */
write_sysreg_el1(cxt->tcr, SYS_TCR);
write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
}
local_irq_restore(cxt->flags);
}
void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
phys_addr_t ipa, int level)
{
struct tlb_inv_context cxt;
dsb(ishst);
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
/*
* We could do so much better if we had the VA as well.
* Instead, we invalidate Stage-2 for this IPA, and the
* whole of Stage-1. Weep...
*/
ipa >>= 12;
__tlbi_level(ipas2e1is, ipa, level);
/*
* We have to ensure completion of the invalidation at Stage-2,
* since a table walk on another CPU could refill a TLB with a
* complete (S1 + S2) walk based on the old Stage-2 mapping if
* the Stage-1 invalidation happened first.
*/
dsb(ish);
__tlbi(vmalle1is);
dsb(ish);
isb();
exit_vmid_context(&cxt);
}
void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
phys_addr_t ipa, int level)
{
struct tlb_inv_context cxt;
dsb(nshst);
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
/*
* We could do so much better if we had the VA as well.
* Instead, we invalidate Stage-2 for this IPA, and the
* whole of Stage-1. Weep...
*/
ipa >>= 12;
__tlbi_level(ipas2e1, ipa, level);
/*
* We have to ensure completion of the invalidation at Stage-2,
* since a table walk on another CPU could refill a TLB with a
* complete (S1 + S2) walk based on the old Stage-2 mapping if
* the Stage-1 invalidation happened first.
*/
dsb(nsh);
__tlbi(vmalle1);
dsb(nsh);
isb();
exit_vmid_context(&cxt);
}
void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
phys_addr_t start, unsigned long pages)
{
struct tlb_inv_context cxt;
unsigned long stride;
/*
* Since the range of addresses may not be mapped at
* the same level, assume the worst case as PAGE_SIZE
*/
stride = PAGE_SIZE;
start = round_down(start, stride);
dsb(ishst);
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
dsb(ish);
isb();
exit_vmid_context(&cxt);
}
void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
dsb(ishst);
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
__tlbi(vmalls12e1is);
dsb(ish);
isb();
exit_vmid_context(&cxt);
}
void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
__tlbi(vmalle1);
asm volatile("ic iallu");
dsb(nsh);
isb();
exit_vmid_context(&cxt);
}
void __kvm_flush_vm_context(void)
{
dsb(ishst);
__tlbi(alle1is);
dsb(ish);
}
/*
* TLB invalidation emulation for NV. For any given instruction, we
* perform the following transformtions:
*
* - a TLBI targeting EL2 S1 is remapped to EL1 S1
* - a non-shareable TLBI is upgraded to being inner-shareable
* - an outer-shareable TLBI is also mapped to inner-shareable
* - an nXS TLBI is upgraded to XS
*/
int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
{
struct tlb_inv_context cxt;
int ret = 0;
/*
* The guest will have provided its own DSB ISHST before trapping.
* If it hasn't, that's its own problem, and we won't paper over it
* (plus, there is plenty of extra synchronisation before we even
* get here...).
*/
if (mmu)
enter_vmid_context(mmu, &cxt);
switch (sys_encoding) {
case OP_TLBI_ALLE2:
case OP_TLBI_ALLE2IS:
case OP_TLBI_ALLE2OS:
case OP_TLBI_VMALLE1:
case OP_TLBI_VMALLE1IS:
case OP_TLBI_VMALLE1OS:
case OP_TLBI_ALLE2NXS:
case OP_TLBI_ALLE2ISNXS:
case OP_TLBI_ALLE2OSNXS:
case OP_TLBI_VMALLE1NXS:
case OP_TLBI_VMALLE1ISNXS:
case OP_TLBI_VMALLE1OSNXS:
__tlbi(vmalle1is);
break;
case OP_TLBI_VAE2:
case OP_TLBI_VAE2IS:
case OP_TLBI_VAE2OS:
case OP_TLBI_VAE1:
case OP_TLBI_VAE1IS:
case OP_TLBI_VAE1OS:
case OP_TLBI_VAE2NXS:
case OP_TLBI_VAE2ISNXS:
case OP_TLBI_VAE2OSNXS:
case OP_TLBI_VAE1NXS:
case OP_TLBI_VAE1ISNXS:
case OP_TLBI_VAE1OSNXS:
__tlbi(vae1is, va);
break;
case OP_TLBI_VALE2:
case OP_TLBI_VALE2IS:
case OP_TLBI_VALE2OS:
case OP_TLBI_VALE1:
case OP_TLBI_VALE1IS:
case OP_TLBI_VALE1OS:
case OP_TLBI_VALE2NXS:
case OP_TLBI_VALE2ISNXS:
case OP_TLBI_VALE2OSNXS:
case OP_TLBI_VALE1NXS:
case OP_TLBI_VALE1ISNXS:
case OP_TLBI_VALE1OSNXS:
__tlbi(vale1is, va);
break;
case OP_TLBI_ASIDE1:
case OP_TLBI_ASIDE1IS:
case OP_TLBI_ASIDE1OS:
case OP_TLBI_ASIDE1NXS:
case OP_TLBI_ASIDE1ISNXS:
case OP_TLBI_ASIDE1OSNXS:
__tlbi(aside1is, va);
break;
case OP_TLBI_VAAE1:
case OP_TLBI_VAAE1IS:
case OP_TLBI_VAAE1OS:
case OP_TLBI_VAAE1NXS:
case OP_TLBI_VAAE1ISNXS:
case OP_TLBI_VAAE1OSNXS:
__tlbi(vaae1is, va);
break;
case OP_TLBI_VAALE1:
case OP_TLBI_VAALE1IS:
case OP_TLBI_VAALE1OS:
case OP_TLBI_VAALE1NXS:
case OP_TLBI_VAALE1ISNXS:
case OP_TLBI_VAALE1OSNXS:
__tlbi(vaale1is, va);
break;
case OP_TLBI_RVAE2:
case OP_TLBI_RVAE2IS:
case OP_TLBI_RVAE2OS:
case OP_TLBI_RVAE1:
case OP_TLBI_RVAE1IS:
case OP_TLBI_RVAE1OS:
case OP_TLBI_RVAE2NXS:
case OP_TLBI_RVAE2ISNXS:
case OP_TLBI_RVAE2OSNXS:
case OP_TLBI_RVAE1NXS:
case OP_TLBI_RVAE1ISNXS:
case OP_TLBI_RVAE1OSNXS:
__tlbi(rvae1is, va);
break;
case OP_TLBI_RVALE2:
case OP_TLBI_RVALE2IS:
case OP_TLBI_RVALE2OS:
case OP_TLBI_RVALE1:
case OP_TLBI_RVALE1IS:
case OP_TLBI_RVALE1OS:
case OP_TLBI_RVALE2NXS:
case OP_TLBI_RVALE2ISNXS:
case OP_TLBI_RVALE2OSNXS:
case OP_TLBI_RVALE1NXS:
case OP_TLBI_RVALE1ISNXS:
case OP_TLBI_RVALE1OSNXS:
__tlbi(rvale1is, va);
break;
case OP_TLBI_RVAAE1:
case OP_TLBI_RVAAE1IS:
case OP_TLBI_RVAAE1OS:
case OP_TLBI_RVAAE1NXS:
case OP_TLBI_RVAAE1ISNXS:
case OP_TLBI_RVAAE1OSNXS:
__tlbi(rvaae1is, va);
break;
case OP_TLBI_RVAALE1:
case OP_TLBI_RVAALE1IS:
case OP_TLBI_RVAALE1OS:
case OP_TLBI_RVAALE1NXS:
case OP_TLBI_RVAALE1ISNXS:
case OP_TLBI_RVAALE1OSNXS:
__tlbi(rvaale1is, va);
break;
default:
ret = -EINVAL;
}
dsb(ish);
isb();
if (mmu)
exit_vmid_context(&cxt);
return ret;
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Percpu refcounts:
* (C) 2012 Google, Inc.
* Author: Kent Overstreet <koverstreet@google.com>
*
* This implements a refcount with similar semantics to atomic_t - atomic_inc(),
* atomic_dec_and_test() - but percpu.
*
* There's one important difference between percpu refs and normal atomic_t
* refcounts; you have to keep track of your initial refcount, and then when you
* start shutting down you call percpu_ref_kill() _before_ dropping the initial
* refcount.
*
* The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less
* than an atomic_t - this is because of the way shutdown works, see
* percpu_ref_kill()/PERCPU_COUNT_BIAS.
*
* Before you call percpu_ref_kill(), percpu_ref_put() does not check for the
* refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill()
* puts the ref back in single atomic_t mode, collecting the per cpu refs and
* issuing the appropriate barriers, and then marks the ref as shutting down so
* that percpu_ref_put() will check for the ref hitting 0. After it returns,
* it's safe to drop the initial ref.
*
* USAGE:
*
* See fs/aio.c for some example usage; it's used there for struct kioctx, which
* is created when userspaces calls io_setup(), and destroyed when userspace
* calls io_destroy() or the process exits.
*
* In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it
* removes the kioctx from the proccess's table of kioctxs and kills percpu_ref.
* After that, there can't be any new users of the kioctx (from lookup_ioctx())
* and it's then safe to drop the initial ref with percpu_ref_put().
*
* Note that the free path, free_ioctx(), needs to go through explicit call_rcu()
* to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't
* imply RCU grace periods of any kind and if a user wants to combine percpu_ref
* with RCU protection, it must be done explicitly.
*
* Code that does a two stage shutdown like this often needs some kind of
* explicit synchronization to ensure the initial refcount can only be dropped
* once - percpu_ref_kill() does this for you, it returns true once and false if
* someone else already called it. The aio code uses it this way, but it's not
* necessary if the code has some other mechanism to synchronize teardown.
* around.
*/
#ifndef _LINUX_PERCPU_REFCOUNT_H
#define _LINUX_PERCPU_REFCOUNT_H
#include <linux/atomic.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/types.h>
#include <linux/gfp.h>
struct percpu_ref;
typedef void (percpu_ref_func_t)(struct percpu_ref *);
/* flags set in the lower bits of percpu_ref->percpu_count_ptr */
enum {
__PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */
__PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */
__PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD,
__PERCPU_REF_FLAG_BITS = 2,
};
/* @flags for percpu_ref_init() */
enum {
/*
* Start w/ ref == 1 in atomic mode. Can be switched to percpu
* operation using percpu_ref_switch_to_percpu(). If initialized
* with this flag, the ref will stay in atomic mode until
* percpu_ref_switch_to_percpu() is invoked on it.
* Implies ALLOW_REINIT.
*/
PERCPU_REF_INIT_ATOMIC = 1 << 0,
/*
* Start dead w/ ref == 0 in atomic mode. Must be revived with
* percpu_ref_reinit() before used. Implies INIT_ATOMIC and
* ALLOW_REINIT.
*/
PERCPU_REF_INIT_DEAD = 1 << 1,
/*
* Allow switching from atomic mode to percpu mode.
*/
PERCPU_REF_ALLOW_REINIT = 1 << 2,
};
struct percpu_ref_data {
atomic_long_t count;
percpu_ref_func_t *release;
percpu_ref_func_t *confirm_switch;
bool force_atomic:1;
bool allow_reinit:1;
struct rcu_head rcu;
struct percpu_ref *ref;
};
struct percpu_ref {
/*
* The low bit of the pointer indicates whether the ref is in percpu
* mode; if set, then get/put will manipulate the atomic_t.
*/
unsigned long percpu_count_ptr;
/*
* 'percpu_ref' is often embedded into user structure, and only
* 'percpu_count_ptr' is required in fast path, move other fields
* into 'percpu_ref_data', so we can reduce memory footprint in
* fast path.
*/
struct percpu_ref_data *data;
};
int __must_check percpu_ref_init(struct percpu_ref *ref,
percpu_ref_func_t *release, unsigned int flags,
gfp_t gfp);
void percpu_ref_exit(struct percpu_ref *ref);
void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
percpu_ref_func_t *confirm_switch);
void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref);
void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
percpu_ref_func_t *confirm_kill);
void percpu_ref_resurrect(struct percpu_ref *ref);
void percpu_ref_reinit(struct percpu_ref *ref);
bool percpu_ref_is_zero(struct percpu_ref *ref);
/**
* percpu_ref_kill - drop the initial ref
* @ref: percpu_ref to kill
*
* Must be used to drop the initial ref on a percpu refcount; must be called
* precisely once before shutdown.
*
* Switches @ref into atomic mode before gathering up the percpu counters
* and dropping the initial ref.
*
* There are no implied RCU grace periods between kill and release.
*/
static inline void percpu_ref_kill(struct percpu_ref *ref)
{
percpu_ref_kill_and_confirm(ref, NULL);
}
/*
* Internal helper. Don't use outside percpu-refcount proper. The
* function doesn't return the pointer and let the caller test it for NULL
* because doing so forces the compiler to generate two conditional
* branches as it can't assume that @ref->percpu_count is not NULL.
*/
static inline bool __ref_is_percpu(struct percpu_ref *ref,
unsigned long __percpu **percpu_countp)
{
unsigned long percpu_ptr;
/*
* The value of @ref->percpu_count_ptr is tested for
* !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then
* used as a pointer. If the compiler generates a separate fetch
* when using it as a pointer, __PERCPU_REF_ATOMIC may be set in
* between contaminating the pointer value, meaning that
* READ_ONCE() is required when fetching it.
*
* The dependency ordering from the READ_ONCE() pairs
* with smp_store_release() in __percpu_ref_switch_to_percpu().
*/
percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
/*
* Theoretically, the following could test just ATOMIC; however,
* then we'd have to mask off DEAD separately as DEAD may be
* visible without ATOMIC if we race with percpu_ref_kill(). DEAD
* implies ATOMIC anyway. Test them together.
*/
if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD))
return false;
*percpu_countp = (unsigned long __percpu *)percpu_ptr;
return true;
}
/**
* percpu_ref_get_many - increment a percpu refcount
* @ref: percpu_ref to get
* @nr: number of references to get
*
* Analogous to atomic_long_add().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
{
unsigned long __percpu *percpu_count;
rcu_read_lock();
if (__ref_is_percpu(ref, &percpu_count))
this_cpu_add(*percpu_count, nr);
else
atomic_long_add(nr, &ref->data->count); rcu_read_unlock();
}
/**
* percpu_ref_get - increment a percpu refcount
* @ref: percpu_ref to get
*
* Analogous to atomic_long_inc().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_get(struct percpu_ref *ref)
{
percpu_ref_get_many(ref, 1);
}
/**
* percpu_ref_tryget_many - try to increment a percpu refcount
* @ref: percpu_ref to try-get
* @nr: number of references to get
*
* Increment a percpu refcount by @nr unless its count already reached zero.
* Returns %true on success; %false on failure.
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget_many(struct percpu_ref *ref,
unsigned long nr)
{
unsigned long __percpu *percpu_count;
bool ret;
rcu_read_lock();
if (__ref_is_percpu(ref, &percpu_count)) {
this_cpu_add(*percpu_count, nr);
ret = true;
} else {
ret = atomic_long_add_unless(&ref->data->count, nr, 0);
}
rcu_read_unlock();
return ret;
}
/**
* percpu_ref_tryget - try to increment a percpu refcount
* @ref: percpu_ref to try-get
*
* Increment a percpu refcount unless its count already reached zero.
* Returns %true on success; %false on failure.
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget(struct percpu_ref *ref)
{
return percpu_ref_tryget_many(ref, 1);
}
/**
* percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the
* caller is responsible for taking RCU.
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref)
{
unsigned long __percpu *percpu_count;
bool ret = false;
WARN_ON_ONCE(!rcu_read_lock_held());
if (likely(__ref_is_percpu(ref, &percpu_count))) {
this_cpu_inc(*percpu_count);
ret = true;
} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
ret = atomic_long_inc_not_zero(&ref->data->count);
}
return ret;
}
/**
* percpu_ref_tryget_live - try to increment a live percpu refcount
* @ref: percpu_ref to try-get
*
* Increment a percpu refcount unless it has already been killed. Returns
* %true on success; %false on failure.
*
* Completion of percpu_ref_kill() in itself doesn't guarantee that this
* function will fail. For such guarantee, percpu_ref_kill_and_confirm()
* should be used. After the confirm_kill callback is invoked, it's
* guaranteed that no new reference will be given out by
* percpu_ref_tryget_live().
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
bool ret = false;
rcu_read_lock();
ret = percpu_ref_tryget_live_rcu(ref);
rcu_read_unlock();
return ret;
}
/**
* percpu_ref_put_many - decrement a percpu refcount
* @ref: percpu_ref to put
* @nr: number of references to put
*
* Decrement the refcount, and if 0, call the release function (which was passed
* to percpu_ref_init())
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
{
unsigned long __percpu *percpu_count;
rcu_read_lock();
if (__ref_is_percpu(ref, &percpu_count))
this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock();
}
/**
* percpu_ref_put - decrement a percpu refcount
* @ref: percpu_ref to put
*
* Decrement the refcount, and if 0, call the release function (which was passed
* to percpu_ref_init())
*
* This function is safe to call as long as @ref is between init and exit.
*/
static inline void percpu_ref_put(struct percpu_ref *ref)
{
percpu_ref_put_many(ref, 1);
}
/**
* percpu_ref_is_dying - test whether a percpu refcount is dying or dead
* @ref: percpu_ref to test
*
* Returns %true if @ref is dying or dead.
*
* This function is safe to call as long as @ref is between init and exit
* and the caller is responsible for synchronizing against state changes.
*/
static inline bool percpu_ref_is_dying(struct percpu_ref *ref)
{
return ref->percpu_count_ptr & __PERCPU_REF_DEAD;
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/uaccess.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_nested.h>
#include "vgic.h"
#define ICH_LRN(n) (ICH_LR0_EL2 + (n))
#define ICH_AP0RN(n) (ICH_AP0R0_EL2 + (n))
#define ICH_AP1RN(n) (ICH_AP1R0_EL2 + (n))
struct mi_state {
u16 eisr;
u16 elrsr;
bool pend;
};
/*
* The shadow registers loaded to the hardware when running a L2 guest
* with the virtual IMO/FMO bits set.
*/
struct shadow_if {
struct vgic_v3_cpu_if cpuif;
unsigned long lr_map;
};
static DEFINE_PER_CPU(struct shadow_if, shadow_if);
/*
* Nesting GICv3 support
*
* On a non-nesting VM (only running at EL0/EL1), the host hypervisor
* completely controls the interrupts injected via the list registers.
* Consequently, most of the state that is modified by the guest (by ACK-ing
* and EOI-ing interrupts) is synced by KVM on each entry/exit, so that we
* keep a semi-consistent view of the interrupts.
*
* This still applies for a NV guest, but only while "InHost" (either
* running at EL2, or at EL0 with HCR_EL2.{E2H.TGE}=={1,1}.
*
* When running a L2 guest ("not InHost"), things are radically different,
* as the L1 guest is in charge of provisioning the interrupts via its own
* view of the ICH_LR*_EL2 registers, which conveniently live in the VNCR
* page. This means that the flow described above does work (there is no
* state to rebuild in the L0 hypervisor), and that most things happed on L2
* load/put:
*
* - on L2 load: move the in-memory L1 vGIC configuration into a shadow,
* per-CPU data structure that is used to populate the actual LRs. This is
* an extra copy that we could avoid, but life is short. In the process,
* we remap any interrupt that has the HW bit set to the mapped interrupt
* on the host, should the host consider it a HW one. This allows the HW
* deactivation to take its course, such as for the timer.
*
* - on L2 put: perform the inverse transformation, so that the result of L2
* running becomes visible to L1 in the VNCR-accessible registers.
*
* - there is nothing to do on L2 entry, as everything will have happened
* on load. However, this is the point where we detect that an interrupt
* targeting L1 and prepare the grand switcheroo.
*
* - on L2 exit: emulate the HW bit, and deactivate corresponding the L1
* interrupt. The L0 active state will be cleared by the HW if the L1
* interrupt was itself backed by a HW interrupt.
*
* Maintenance Interrupt (MI) management:
*
* Since the L2 guest runs the vgic in its full glory, MIs get delivered and
* used as a handover point between L2 and L1.
*
* - on delivery of a MI to L0 while L2 is running: make the L1 MI pending,
* and let it rip. This will initiate a vcpu_put() on L2, and allow L1 to
* run and process the MI.
*
* - L1 MI is a fully virtual interrupt, not linked to the host's MI. Its
* state must be computed at each entry/exit of the guest, much like we do
* it for the PMU interrupt.
*
* - because most of the ICH_*_EL2 registers live in the VNCR page, the
* quality of emulation is poor: L1 can setup the vgic so that an MI would
* immediately fire, and not observe anything until the next exit. Trying
* to read ICH_MISR_EL2 would do the trick, for example.
*
* System register emulation:
*
* We get two classes of registers:
*
* - those backed by memory (LRs, APRs, HCR, VMCR): L1 can freely access
* them, and L0 doesn't see a thing.
*
* - those that always trap (ELRSR, EISR, MISR): these are status registers
* that are built on the fly based on the in-memory state.
*
* Only L1 can access the ICH_*_EL2 registers. A non-NV L2 obviously cannot,
* and a NV L2 would either access the VNCR page provided by L1 (memory
* based registers), or see the access redirected to L1 (registers that
* trap) thanks to NV being set by L1.
*/
bool vgic_state_is_nested(struct kvm_vcpu *vcpu)
{
u64 xmo;
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { xmo = __vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_IMO | HCR_FMO); WARN_ONCE(xmo && xmo != (HCR_IMO | HCR_FMO),
"Separate virtual IRQ/FIQ settings not supported\n");
return !!xmo;
}
return false;
}
static struct shadow_if *get_shadow_if(void)
{
return this_cpu_ptr(&shadow_if);
}
static bool lr_triggers_eoi(u64 lr)
{
return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI);
}
static void vgic_compute_mi_state(struct kvm_vcpu *vcpu, struct mi_state *mi_state)
{
u16 eisr = 0, elrsr = 0;
bool pend = false;
for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
if (lr_triggers_eoi(lr))
eisr |= BIT(i);
if (!(lr & ICH_LR_STATE))
elrsr |= BIT(i);
pend |= (lr & ICH_LR_PENDING_BIT);
}
mi_state->eisr = eisr;
mi_state->elrsr = elrsr;
mi_state->pend = pend;
}
u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
{
struct mi_state mi_state;
vgic_compute_mi_state(vcpu, &mi_state);
return mi_state.eisr;
}
u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
{
struct mi_state mi_state;
vgic_compute_mi_state(vcpu, &mi_state);
return mi_state.elrsr;
}
u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
{
struct mi_state mi_state;
u64 reg = 0, hcr, vmcr;
hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
vgic_compute_mi_state(vcpu, &mi_state);
if (mi_state.eisr)
reg |= ICH_MISR_EL2_EOI;
if (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_UIE) {
int used_lrs = kvm_vgic_global_state.nr_lr;
used_lrs -= hweight16(mi_state.elrsr);
reg |= (used_lrs <= 1) ? ICH_MISR_EL2_U : 0;
}
if ((hcr & ICH_HCR_EL2_LRENPIE) && FIELD_GET(ICH_HCR_EL2_EOIcount_MASK, hcr))
reg |= ICH_MISR_EL2_LRENP;
if ((hcr & ICH_HCR_EL2_NPIE) && !mi_state.pend)
reg |= ICH_MISR_EL2_NP;
if ((hcr & ICH_HCR_EL2_VGrp0EIE) && (vmcr & ICH_VMCR_ENG0_MASK))
reg |= ICH_MISR_EL2_VGrp0E;
if ((hcr & ICH_HCR_EL2_VGrp0DIE) && !(vmcr & ICH_VMCR_ENG0_MASK))
reg |= ICH_MISR_EL2_VGrp0D;
if ((hcr & ICH_HCR_EL2_VGrp1EIE) && (vmcr & ICH_VMCR_ENG1_MASK))
reg |= ICH_MISR_EL2_VGrp1E;
if ((hcr & ICH_HCR_EL2_VGrp1DIE) && !(vmcr & ICH_VMCR_ENG1_MASK))
reg |= ICH_MISR_EL2_VGrp1D;
return reg;
}
/*
* For LRs which have HW bit set such as timer interrupts, we modify them to
* have the host hardware interrupt number instead of the virtual one programmed
* by the guest hypervisor.
*/
static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
struct vgic_v3_cpu_if *s_cpu_if)
{
unsigned long lr_map = 0;
int index = 0;
for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
struct vgic_irq *irq;
if (!(lr & ICH_LR_STATE))
lr = 0;
if (!(lr & ICH_LR_HW))
goto next;
/* We have the HW bit set, check for validity of pINTID */
irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) {
/* There was no real mapping, so nuke the HW bit */
lr &= ~ICH_LR_HW;
if (irq)
vgic_put_irq(vcpu->kvm, irq);
goto next;
}
/* Translate the virtual mapping to the real one */
lr &= ~ICH_LR_PHYS_ID_MASK;
lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
vgic_put_irq(vcpu->kvm, irq);
next:
s_cpu_if->vgic_lr[index] = lr;
if (lr) {
lr_map |= BIT(i);
index++;
}
}
container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map;
s_cpu_if->used_lrs = index;
}
void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
{
struct shadow_if *shadow_if = get_shadow_if();
int i, index = 0;
for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
struct vgic_irq *irq;
if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
goto next;
/*
* If we had a HW lr programmed by the guest hypervisor, we
* need to emulate the HW effect between the guest hypervisor
* and the nested guest.
*/
irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */
goto next;
lr = __gic_v3_get_lr(index);
if (!(lr & ICH_LR_STATE))
irq->active = false;
vgic_put_irq(vcpu->kvm, irq);
next:
index++;
}
}
static void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu,
struct vgic_v3_cpu_if *s_cpu_if)
{
struct vgic_v3_cpu_if *host_if = &vcpu->arch.vgic_cpu.vgic_v3;
u64 val = 0;
int i;
/*
* If we're on a system with a broken vgic that requires
* trapping, propagate the trapping requirements.
*
* Ah, the smell of rotten fruits...
*/
if (static_branch_unlikely(&vgic_v3_cpuif_trap))
val = host_if->vgic_hcr & (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
ICH_HCR_EL2_TC | ICH_HCR_EL2_TDIR);
s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) | val;
s_cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
s_cpu_if->vgic_sre = host_if->vgic_sre;
for (i = 0; i < 4; i++) {
s_cpu_if->vgic_ap0r[i] = __vcpu_sys_reg(vcpu, ICH_AP0RN(i));
s_cpu_if->vgic_ap1r[i] = __vcpu_sys_reg(vcpu, ICH_AP1RN(i));
}
vgic_v3_create_shadow_lr(vcpu, s_cpu_if);
}
void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
{
struct shadow_if *shadow_if = get_shadow_if();
struct vgic_v3_cpu_if *cpu_if = &shadow_if->cpuif;
BUG_ON(!vgic_state_is_nested(vcpu));
vgic_v3_create_shadow_state(vcpu, cpu_if);
__vgic_v3_restore_vmcr_aprs(cpu_if);
__vgic_v3_activate_traps(cpu_if);
__vgic_v3_restore_state(cpu_if);
/*
* Propagate the number of used LRs for the benefit of the HYP
* GICv3 emulation code. Yes, this is a pretty sorry hack.
*/
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = cpu_if->used_lrs;
}
void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
{
struct shadow_if *shadow_if = get_shadow_if();
struct vgic_v3_cpu_if *s_cpu_if = &shadow_if->cpuif;
u64 val;
int i;
__vgic_v3_save_vmcr_aprs(s_cpu_if);
__vgic_v3_deactivate_traps(s_cpu_if);
__vgic_v3_save_state(s_cpu_if);
/*
* Translate the shadow state HW fields back to the virtual ones
* before copying the shadow struct back to the nested one.
*/
val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
val &= ~ICH_HCR_EL2_EOIcount_MASK;
val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
for (i = 0; i < 4; i++) {
__vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
__vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
}
for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
val &= ~ICH_LR_STATE;
val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
__vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
s_cpu_if->vgic_lr[i] = 0;
}
shadow_if->lr_map = 0;
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0;
}
/*
* If we exit a L2 VM with a pending maintenance interrupt from the GIC,
* then we need to forward this to L1 so that it can re-sync the appropriate
* LRs and sample level triggered interrupts again.
*/
void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
{
bool state = read_sysreg_s(SYS_ICH_MISR_EL2);
/* This will force a switch back to L1 if the level is high */
kvm_vgic_inject_irq(vcpu->kvm, vcpu,
vcpu->kvm->arch.vgic.mi_intid, state, vcpu);
sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0);
}
void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
{
bool level;
level = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
if (level)
level &= vgic_v3_get_misr(vcpu);
kvm_vgic_inject_irq(vcpu->kvm, vcpu,
vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
}
// SPDX-License-Identifier: GPL-2.0
/*
* device_cgroup.c - device cgroup subsystem
*
* Copyright 2007 IBM Corp
*/
#include <linux/bpf-cgroup.h>
#include <linux/device_cgroup.h>
#include <linux/cgroup.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
#ifdef CONFIG_CGROUP_DEVICE
static DEFINE_MUTEX(devcgroup_mutex);
enum devcg_behavior {
DEVCG_DEFAULT_NONE,
DEVCG_DEFAULT_ALLOW,
DEVCG_DEFAULT_DENY,
};
/*
* exception list locking rules:
* hold devcgroup_mutex for update/read.
* hold rcu_read_lock() for read.
*/
struct dev_exception_item {
u32 major, minor;
short type;
short access;
struct list_head list;
struct rcu_head rcu;
};
struct dev_cgroup {
struct cgroup_subsys_state css;
struct list_head exceptions;
enum devcg_behavior behavior;
};
static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
{
return s ? container_of(s, struct dev_cgroup, css) : NULL;
}
static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
{
return css_to_devcgroup(task_css(task, devices_cgrp_id));
}
/*
* called under devcgroup_mutex
*/
static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig)
{
struct dev_exception_item *ex, *tmp, *new;
lockdep_assert_held(&devcgroup_mutex);
list_for_each_entry(ex, orig, list) {
new = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
if (!new)
goto free_and_exit;
list_add_tail(&new->list, dest);
}
return 0;
free_and_exit:
list_for_each_entry_safe(ex, tmp, dest, list) {
list_del(&ex->list);
kfree(ex);
}
return -ENOMEM;
}
static void dev_exceptions_move(struct list_head *dest, struct list_head *orig)
{
struct dev_exception_item *ex, *tmp;
lockdep_assert_held(&devcgroup_mutex);
list_for_each_entry_safe(ex, tmp, orig, list) {
list_move_tail(&ex->list, dest);
}
}
/*
* called under devcgroup_mutex
*/
static int dev_exception_add(struct dev_cgroup *dev_cgroup,
struct dev_exception_item *ex)
{
struct dev_exception_item *excopy, *walk;
lockdep_assert_held(&devcgroup_mutex);
excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
if (!excopy)
return -ENOMEM;
list_for_each_entry(walk, &dev_cgroup->exceptions, list) {
if (walk->type != ex->type)
continue;
if (walk->major != ex->major)
continue;
if (walk->minor != ex->minor)
continue;
walk->access |= ex->access;
kfree(excopy);
excopy = NULL;
}
if (excopy != NULL)
list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions);
return 0;
}
/*
* called under devcgroup_mutex
*/
static void dev_exception_rm(struct dev_cgroup *dev_cgroup,
struct dev_exception_item *ex)
{
struct dev_exception_item *walk, *tmp;
lockdep_assert_held(&devcgroup_mutex);
list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) {
if (walk->type != ex->type)
continue;
if (walk->major != ex->major)
continue;
if (walk->minor != ex->minor)
continue;
walk->access &= ~ex->access;
if (!walk->access) {
list_del_rcu(&walk->list);
kfree_rcu(walk, rcu);
}
}
}
static void __dev_exception_clean(struct dev_cgroup *dev_cgroup)
{
struct dev_exception_item *ex, *tmp;
list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) {
list_del_rcu(&ex->list);
kfree_rcu(ex, rcu);
}
}
/**
* dev_exception_clean - frees all entries of the exception list
* @dev_cgroup: dev_cgroup with the exception list to be cleaned
*
* called under devcgroup_mutex
*/
static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
{
lockdep_assert_held(&devcgroup_mutex);
__dev_exception_clean(dev_cgroup);
}
static inline bool is_devcg_online(const struct dev_cgroup *devcg)
{
return (devcg->behavior != DEVCG_DEFAULT_NONE);
}
/**
* devcgroup_online - initializes devcgroup's behavior and exceptions based on
* parent's
* @css: css getting online
* returns 0 in case of success, error code otherwise
*/
static int devcgroup_online(struct cgroup_subsys_state *css)
{
struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
int ret = 0;
mutex_lock(&devcgroup_mutex);
if (parent_dev_cgroup == NULL)
dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW;
else {
ret = dev_exceptions_copy(&dev_cgroup->exceptions,
&parent_dev_cgroup->exceptions);
if (!ret)
dev_cgroup->behavior = parent_dev_cgroup->behavior;
}
mutex_unlock(&devcgroup_mutex);
return ret;
}
static void devcgroup_offline(struct cgroup_subsys_state *css)
{
struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
mutex_lock(&devcgroup_mutex);
dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
mutex_unlock(&devcgroup_mutex);
}
/*
* called from kernel/cgroup/cgroup.c with cgroup_lock() held.
*/
static struct cgroup_subsys_state *
devcgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct dev_cgroup *dev_cgroup;
dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL);
if (!dev_cgroup)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&dev_cgroup->exceptions);
dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
return &dev_cgroup->css;
}
static void devcgroup_css_free(struct cgroup_subsys_state *css)
{
struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
__dev_exception_clean(dev_cgroup);
kfree(dev_cgroup);
}
#define DEVCG_ALLOW 1
#define DEVCG_DENY 2
#define DEVCG_LIST 3
#define MAJMINLEN 13
#define ACCLEN 4
static void set_access(char *acc, short access)
{
int idx = 0;
memset(acc, 0, ACCLEN);
if (access & DEVCG_ACC_READ)
acc[idx++] = 'r';
if (access & DEVCG_ACC_WRITE)
acc[idx++] = 'w';
if (access & DEVCG_ACC_MKNOD)
acc[idx++] = 'm';
}
static char type_to_char(short type)
{
if (type == DEVCG_DEV_ALL)
return 'a';
if (type == DEVCG_DEV_CHAR)
return 'c';
if (type == DEVCG_DEV_BLOCK)
return 'b';
return 'X';
}
static void set_majmin(char *str, unsigned m)
{
if (m == ~0)
strcpy(str, "*");
else
sprintf(str, "%u", m);
}
static int devcgroup_seq_show(struct seq_file *m, void *v)
{
struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m));
struct dev_exception_item *ex;
char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
rcu_read_lock();
/*
* To preserve the compatibility:
* - Only show the "all devices" when the default policy is to allow
* - List the exceptions in case the default policy is to deny
* This way, the file remains as a "whitelist of devices"
*/
if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
set_access(acc, DEVCG_ACC_MASK);
set_majmin(maj, ~0);
set_majmin(min, ~0);
seq_printf(m, "%c %s:%s %s\n", type_to_char(DEVCG_DEV_ALL),
maj, min, acc);
} else {
list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
set_access(acc, ex->access);
set_majmin(maj, ex->major);
set_majmin(min, ex->minor);
seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type),
maj, min, acc);
}
}
rcu_read_unlock();
return 0;
}
/**
* match_exception - iterates the exception list trying to find a complete match
* @exceptions: list of exceptions
* @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
* @major: device file major number, ~0 to match all
* @minor: device file minor number, ~0 to match all
* @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
*
* It is considered a complete match if an exception is found that will
* contain the entire range of provided parameters.
*
* Return: true in case it matches an exception completely
*/
static bool match_exception(struct list_head *exceptions, short type,
u32 major, u32 minor, short access)
{
struct dev_exception_item *ex;
list_for_each_entry_rcu(ex, exceptions, list) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
continue;
if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
continue;
if (ex->major != ~0 && ex->major != major)
continue;
if (ex->minor != ~0 && ex->minor != minor)
continue;
/* provided access cannot have more than the exception rule */
if (access & (~ex->access))
continue;
return true;
}
return false;
}
/**
* match_exception_partial - iterates the exception list trying to find a partial match
* @exceptions: list of exceptions
* @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
* @major: device file major number, ~0 to match all
* @minor: device file minor number, ~0 to match all
* @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
*
* It is considered a partial match if an exception's range is found to
* contain *any* of the devices specified by provided parameters. This is
* used to make sure no extra access is being granted that is forbidden by
* any of the exception list.
*
* Return: true in case the provided range mat matches an exception completely
*/
static bool match_exception_partial(struct list_head *exceptions, short type,
u32 major, u32 minor, short access)
{
struct dev_exception_item *ex;
list_for_each_entry_rcu(ex, exceptions, list,
lockdep_is_held(&devcgroup_mutex)) {
if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
continue;
if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
continue;
/*
* We must be sure that both the exception and the provided
* range aren't masking all devices
*/
if (ex->major != ~0 && major != ~0 && ex->major != major)
continue;
if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
continue;
/*
* In order to make sure the provided range isn't matching
* an exception, all its access bits shouldn't match the
* exception's access bits
*/
if (!(access & ex->access))
continue;
return true;
}
return false;
}
/**
* verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions
* @dev_cgroup: dev cgroup to be tested against
* @refex: new exception
* @behavior: behavior of the exception's dev_cgroup
*
* This is used to make sure a child cgroup won't have more privileges
* than its parent
*/
static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
struct dev_exception_item *refex,
enum devcg_behavior behavior)
{
bool match = false;
RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
!lockdep_is_held(&devcgroup_mutex),
"device_cgroup:verify_new_ex called without proper synchronization");
if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
if (behavior == DEVCG_DEFAULT_ALLOW) {
/*
* new exception in the child doesn't matter, only
* adding extra restrictions
*/
return true;
} else {
/*
* new exception in the child will add more devices
* that can be accessed, so it can't match any of
* parent's exceptions, even slightly
*/
match = match_exception_partial(&dev_cgroup->exceptions,
refex->type,
refex->major,
refex->minor,
refex->access);
if (match)
return false;
return true;
}
} else {
/*
* Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
* the new exception will add access to more devices and must
* be contained completely in an parent's exception to be
* allowed
*/
match = match_exception(&dev_cgroup->exceptions, refex->type,
refex->major, refex->minor,
refex->access);
if (match)
/* parent has an exception that matches the proposed */
return true;
else
return false;
}
return false;
}
/*
* parent_has_perm:
* when adding a new allow rule to a device exception list, the rule
* must be allowed in the parent device
*/
static int parent_has_perm(struct dev_cgroup *childcg,
struct dev_exception_item *ex)
{
struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
if (!parent)
return 1;
return verify_new_ex(parent, ex, childcg->behavior);
}
/**
* parent_allows_removal - verify if it's ok to remove an exception
* @childcg: child cgroup from where the exception will be removed
* @ex: exception being removed
*
* When removing an exception in cgroups with default ALLOW policy, it must
* be checked if removing it will give the child cgroup more access than the
* parent.
*
* Return: true if it's ok to remove exception, false otherwise
*/
static bool parent_allows_removal(struct dev_cgroup *childcg,
struct dev_exception_item *ex)
{
struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
if (!parent)
return true;
/* It's always allowed to remove access to devices */
if (childcg->behavior == DEVCG_DEFAULT_DENY)
return true;
/*
* Make sure you're not removing part or a whole exception existing in
* the parent cgroup
*/
return !match_exception_partial(&parent->exceptions, ex->type,
ex->major, ex->minor, ex->access);
}
/**
* may_allow_all - checks if it's possible to change the behavior to
* allow based on parent's rules.
* @parent: device cgroup's parent
* returns: != 0 in case it's allowed, 0 otherwise
*/
static inline int may_allow_all(struct dev_cgroup *parent)
{
if (!parent)
return 1;
return parent->behavior == DEVCG_DEFAULT_ALLOW;
}
/**
* revalidate_active_exceptions - walks through the active exception list and
* revalidates the exceptions based on parent's
* behavior and exceptions. The exceptions that
* are no longer valid will be removed.
* Called with devcgroup_mutex held.
* @devcg: cgroup which exceptions will be checked
*
* This is one of the three key functions for hierarchy implementation.
* This function is responsible for re-evaluating all the cgroup's active
* exceptions due to a parent's exception change.
* Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details.
*/
static void revalidate_active_exceptions(struct dev_cgroup *devcg)
{
struct dev_exception_item *ex;
struct list_head *this, *tmp;
list_for_each_safe(this, tmp, &devcg->exceptions) {
ex = container_of(this, struct dev_exception_item, list);
if (!parent_has_perm(devcg, ex))
dev_exception_rm(devcg, ex);
}
}
/**
* propagate_exception - propagates a new exception to the children
* @devcg_root: device cgroup that added a new exception
* @ex: new exception to be propagated
*
* returns: 0 in case of success, != 0 in case of error
*/
static int propagate_exception(struct dev_cgroup *devcg_root,
struct dev_exception_item *ex)
{
struct cgroup_subsys_state *pos;
int rc = 0;
rcu_read_lock();
css_for_each_descendant_pre(pos, &devcg_root->css) {
struct dev_cgroup *devcg = css_to_devcgroup(pos);
/*
* Because devcgroup_mutex is held, no devcg will become
* online or offline during the tree walk (see on/offline
* methods), and online ones are safe to access outside RCU
* read lock without bumping refcnt.
*/
if (pos == &devcg_root->css || !is_devcg_online(devcg))
continue;
rcu_read_unlock();
/*
* in case both root's behavior and devcg is allow, a new
* restriction means adding to the exception list
*/
if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW &&
devcg->behavior == DEVCG_DEFAULT_ALLOW) {
rc = dev_exception_add(devcg, ex);
if (rc)
return rc;
} else {
/*
* in the other possible cases:
* root's behavior: allow, devcg's: deny
* root's behavior: deny, devcg's: deny
* the exception will be removed
*/
dev_exception_rm(devcg, ex);
}
revalidate_active_exceptions(devcg);
rcu_read_lock();
}
rcu_read_unlock();
return rc;
}
/*
* Modify the exception list using allow/deny rules.
* CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD
* so we can give a container CAP_MKNOD to let it create devices but not
* modify the exception list.
* It seems likely we'll want to add a CAP_CONTAINER capability to allow
* us to also grant CAP_SYS_ADMIN to containers without giving away the
* device exception list controls, but for now we'll stick with CAP_SYS_ADMIN
*
* Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting
* new access is only allowed if you're in the top-level cgroup, or your
* parent cgroup has the access you're asking for.
*/
static int devcgroup_update_access(struct dev_cgroup *devcgroup,
int filetype, char *buffer)
{
const char *b;
char temp[12]; /* 11 + 1 characters needed for a u32 */
int count, rc = 0;
struct dev_exception_item ex;
struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
struct dev_cgroup tmp_devcgrp;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
memset(&ex, 0, sizeof(ex));
memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp));
b = buffer;
switch (*b) {
case 'a':
switch (filetype) {
case DEVCG_ALLOW:
if (css_has_online_children(&devcgroup->css))
return -EINVAL;
if (!may_allow_all(parent))
return -EPERM;
if (!parent) {
devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
dev_exception_clean(devcgroup);
break;
}
INIT_LIST_HEAD(&tmp_devcgrp.exceptions);
rc = dev_exceptions_copy(&tmp_devcgrp.exceptions,
&devcgroup->exceptions);
if (rc)
return rc;
dev_exception_clean(devcgroup);
rc = dev_exceptions_copy(&devcgroup->exceptions,
&parent->exceptions);
if (rc) {
dev_exceptions_move(&devcgroup->exceptions,
&tmp_devcgrp.exceptions);
return rc;
}
devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
dev_exception_clean(&tmp_devcgrp);
break;
case DEVCG_DENY:
if (css_has_online_children(&devcgroup->css))
return -EINVAL;
dev_exception_clean(devcgroup);
devcgroup->behavior = DEVCG_DEFAULT_DENY;
break;
default:
return -EINVAL;
}
return 0;
case 'b':
ex.type = DEVCG_DEV_BLOCK;
break;
case 'c':
ex.type = DEVCG_DEV_CHAR;
break;
default:
return -EINVAL;
}
b++;
if (!isspace(*b))
return -EINVAL;
b++;
if (*b == '*') {
ex.major = ~0;
b++;
} else if (isdigit(*b)) {
memset(temp, 0, sizeof(temp));
for (count = 0; count < sizeof(temp) - 1; count++) {
temp[count] = *b;
b++;
if (!isdigit(*b))
break;
}
rc = kstrtou32(temp, 10, &ex.major);
if (rc)
return -EINVAL;
} else {
return -EINVAL;
}
if (*b != ':')
return -EINVAL;
b++;
/* read minor */
if (*b == '*') {
ex.minor = ~0;
b++;
} else if (isdigit(*b)) {
memset(temp, 0, sizeof(temp));
for (count = 0; count < sizeof(temp) - 1; count++) {
temp[count] = *b;
b++;
if (!isdigit(*b))
break;
}
rc = kstrtou32(temp, 10, &ex.minor);
if (rc)
return -EINVAL;
} else {
return -EINVAL;
}
if (!isspace(*b))
return -EINVAL;
for (b++, count = 0; count < 3; count++, b++) {
switch (*b) {
case 'r':
ex.access |= DEVCG_ACC_READ;
break;
case 'w':
ex.access |= DEVCG_ACC_WRITE;
break;
case 'm':
ex.access |= DEVCG_ACC_MKNOD;
break;
case '\n':
case '\0':
count = 3;
break;
default:
return -EINVAL;
}
}
switch (filetype) {
case DEVCG_ALLOW:
/*
* If the default policy is to allow by default, try to remove
* an matching exception instead. And be silent about it: we
* don't want to break compatibility
*/
if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
/* Check if the parent allows removing it first */
if (!parent_allows_removal(devcgroup, &ex))
return -EPERM;
dev_exception_rm(devcgroup, &ex);
break;
}
if (!parent_has_perm(devcgroup, &ex))
return -EPERM;
rc = dev_exception_add(devcgroup, &ex);
break;
case DEVCG_DENY:
/*
* If the default policy is to deny by default, try to remove
* an matching exception instead. And be silent about it: we
* don't want to break compatibility
*/
if (devcgroup->behavior == DEVCG_DEFAULT_DENY)
dev_exception_rm(devcgroup, &ex);
else
rc = dev_exception_add(devcgroup, &ex);
if (rc)
break;
/* we only propagate new restrictions */
rc = propagate_exception(devcgroup, &ex);
break;
default:
rc = -EINVAL;
}
return rc;
}
static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
int retval;
mutex_lock(&devcgroup_mutex);
retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
of_cft(of)->private, strstrip(buf));
mutex_unlock(&devcgroup_mutex);
return retval ?: nbytes;
}
static struct cftype dev_cgroup_files[] = {
{
.name = "allow",
.write = devcgroup_access_write,
.private = DEVCG_ALLOW,
},
{
.name = "deny",
.write = devcgroup_access_write,
.private = DEVCG_DENY,
},
{
.name = "list",
.seq_show = devcgroup_seq_show,
.private = DEVCG_LIST,
},
{ } /* terminate */
};
struct cgroup_subsys devices_cgrp_subsys = {
.css_alloc = devcgroup_css_alloc,
.css_free = devcgroup_css_free,
.css_online = devcgroup_online,
.css_offline = devcgroup_offline,
.legacy_cftypes = dev_cgroup_files,
};
/**
* devcgroup_legacy_check_permission - checks if an inode operation is permitted
* @type: device type
* @major: device major number
* @minor: device minor number
* @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD
*
* returns 0 on success, -EPERM case the operation is not permitted
*/
static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor,
short access)
{
struct dev_cgroup *dev_cgroup;
bool rc;
rcu_read_lock(); dev_cgroup = task_devcgroup(current);
if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
/* Can't match any of the exceptions, even partially */
rc = !match_exception_partial(&dev_cgroup->exceptions,
type, major, minor, access);
else
/* Need to match completely one exception to be allowed */
rc = match_exception(&dev_cgroup->exceptions, type, major,
minor, access);
rcu_read_unlock();
if (!rc)
return -EPERM;
return 0;
}
#endif /* CONFIG_CGROUP_DEVICE */
#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
{ int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc)
return rc;
#ifdef CONFIG_CGROUP_DEVICE
return devcgroup_legacy_check_permission(type, major, minor, access);
#else /* CONFIG_CGROUP_DEVICE */
return 0;
#endif /* CONFIG_CGROUP_DEVICE */
}
EXPORT_SYMBOL(devcgroup_check_permission);
#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#ifndef __ARM64_KVM_HYP_FAULT_H__
#define __ARM64_KVM_HYP_FAULT_H__
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
static inline bool __fault_safe_to_translate(u64 esr)
{
u64 fsc = esr & ESR_ELx_FSC; if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr))
return false;
return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV));
}
static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
int ret;
u64 par, tmp;
/*
* Resolve the IPA the hard way using the guest VA.
*
* Stage-1 translation already validated the memory access
* rights. As such, we can use the EL1 translation regime, and
* don't have to distinguish between EL0 and EL1 access.
*
* We do need to save/restore PAR_EL1 though, as we haven't
* saved the guest context yet, and we may return early...
*/
par = read_sysreg_par();
ret = system_supports_poe() ? __kvm_at(OP_AT_S1E1A, far) : __kvm_at(OP_AT_S1E1R, far);
if (!ret)
tmp = read_sysreg_par();
else
tmp = SYS_PAR_EL1_F; /* back to the guest */
write_sysreg(par, par_el1); if (unlikely(tmp & SYS_PAR_EL1_F))
return false; /* Translation failed, back to guest */
/* Convert PAR to HPFAR format */
*hpfar = PAR_TO_HPFAR(tmp);
return true;
}
/*
* Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR.
*/
static inline bool __hpfar_valid(u64 esr)
{
/*
* CPUs affected by ARM erratum #834220 may incorrectly report a
* stage-2 translation fault when a stage-1 permission fault occurs.
*
* Re-walk the page tables to determine if a stage-1 fault actually
* occurred.
*/
if (cpus_have_final_cap(ARM64_WORKAROUND_834220) && esr_fsc_is_translation_fault(esr))
return false;
if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr))
return true;
if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr))
return true;
return esr_fsc_is_addr_sz_fault(esr);
}
static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
{
u64 hpfar;
fault->far_el2 = read_sysreg_el2(SYS_FAR);
fault->hpfar_el2 = 0;
if (__hpfar_valid(esr))
hpfar = read_sysreg(hpfar_el2);
else if (unlikely(!__fault_safe_to_translate(esr)))
return true;
else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar))
return false;
/*
* Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid
* HPFAR value.
*/
fault->hpfar_el2 = hpfar | HPFAR_EL2_NS;
return true;
}
#endif
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/fault-inject-usercopy.h>
#include <linux/kasan-checks.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <asm/byteorder.h>
#include <asm/word-at-a-time.h>
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
#define IS_UNALIGNED(src, dst) 0
#else
#define IS_UNALIGNED(src, dst) \
(((long) dst | (long) src) & (sizeof(long) - 1))
#endif
/*
* Do a strncpy, return length of string without final '\0'.
* 'count' is the user-supplied count (return 'count' if we
* hit it), 'max' is the address space maximum (and we return
* -EFAULT if we hit it).
*/
static __always_inline long do_strncpy_from_user(char *dst, const char __user *src,
unsigned long count, unsigned long max)
{
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
unsigned long res = 0;
if (IS_UNALIGNED(src, dst))
goto byte_at_a_time;
while (max >= sizeof(unsigned long)) {
unsigned long c, data, mask;
/* Fall back to byte-at-a-time if we get a page fault */
unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
/*
* Note that we mask out the bytes following the NUL. This is
* important to do because string oblivious code may read past
* the NUL. For those routines, we don't want to give them
* potentially random bytes after the NUL in `src`.
*
* One example of such code is BPF map keys. BPF treats map keys
* as an opaque set of bytes. Without the post-NUL mask, any BPF
* maps keyed by strings returned from strncpy_from_user() may
* have multiple entries for semantically identical strings.
*/
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
data = create_zero_mask(data);
mask = zero_bytemask(data);
*(unsigned long *)(dst+res) = c & mask;
return res + find_zero(data);
}
*(unsigned long *)(dst+res) = c;
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
byte_at_a_time:
while (max) {
char c;
unsafe_get_user(c,src+res, efault);
dst[res] = c;
if (!c)
return res;
res++;
max--;
}
/*
* Uhhuh. We hit 'max'. But was that the user-specified maximum
* too? If so, that's ok - we got as much as the user asked for.
*/
if (res >= count)
return res;
/*
* Nope: we hit the address space limit, and we still had more
* characters the caller would have wanted. That's an EFAULT.
*/
efault:
return -EFAULT;
}
/**
* strncpy_from_user: - Copy a NUL terminated string from userspace.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @src: Source address, in user space.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from userspace to kernel space.
*
* On success, returns the length of the string (not including the trailing
* NUL).
*
* If access to userspace fails, returns -EFAULT (some data may have been
* copied).
*
* If @count is smaller than the length of the string, copies @count bytes
* and returns @count.
*/
long strncpy_from_user(char *dst, const char __user *src, long count)
{
unsigned long max_addr, src_addr;
might_fault();
if (should_fail_usercopy())
return -EFAULT;
if (unlikely(count <= 0))
return 0;
kasan_check_write(dst, count);
check_object_size(dst, count, false);
if (can_do_masked_user_access()) {
long retval;
src = masked_user_access_begin(src);
retval = do_strncpy_from_user(dst, src, count, count);
user_read_access_end();
return retval;
}
max_addr = TASK_SIZE_MAX;
src_addr = (unsigned long)untagged_addr(src);
if (likely(src_addr < max_addr)) {
unsigned long max = max_addr - src_addr;
long retval;
/*
* Truncate 'max' to the user-specified limit, so that
* we only have one limit we need to check in the loop
*/
if (max > count)
max = count;
if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max);
user_read_access_end();
return retval;
}
}
return -EFAULT;
}
EXPORT_SYMBOL(strncpy_from_user);
/* SPDX-License-Identifier: GPL-2.0+ */
#ifndef _LINUX_XARRAY_H
#define _LINUX_XARRAY_H
/*
* eXtensible Arrays
* Copyright (c) 2017 Microsoft Corporation
* Author: Matthew Wilcox <willy@infradead.org>
*
* See Documentation/core-api/xarray.rst for how to use the XArray.
*/
#include <linux/bitmap.h>
#include <linux/bug.h>
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/kconfig.h>
#include <linux/limits.h>
#include <linux/lockdep.h>
#include <linux/rcupdate.h>
#include <linux/sched/mm.h>
#include <linux/spinlock.h>
#include <linux/types.h>
struct list_lru;
/*
* The bottom two bits of the entry determine how the XArray interprets
* the contents:
*
* 00: Pointer entry
* 10: Internal entry
* x1: Value entry or tagged pointer
*
* Attempting to store internal entries in the XArray is a bug.
*
* Most internal entries are pointers to the next node in the tree.
* The following internal entries have a special meaning:
*
* 0-62: Sibling entries
* 256: Retry entry
* 257: Zero entry
*
* Errors are also represented as internal entries, but use the negative
* space (-4094 to -2). They're never stored in the slots array; only
* returned by the normal API.
*/
#define BITS_PER_XA_VALUE (BITS_PER_LONG - 1)
/**
* xa_mk_value() - Create an XArray entry from an integer.
* @v: Value to store in XArray.
*
* Context: Any context.
* Return: An entry suitable for storing in the XArray.
*/
static inline void *xa_mk_value(unsigned long v)
{
WARN_ON((long)v < 0);
return (void *)((v << 1) | 1);
}
/**
* xa_to_value() - Get value stored in an XArray entry.
* @entry: XArray entry.
*
* Context: Any context.
* Return: The value stored in the XArray entry.
*/
static inline unsigned long xa_to_value(const void *entry)
{
return (unsigned long)entry >> 1;
}
/**
* xa_is_value() - Determine if an entry is a value.
* @entry: XArray entry.
*
* Context: Any context.
* Return: True if the entry is a value, false if it is a pointer.
*/
static inline bool xa_is_value(const void *entry)
{
return (unsigned long)entry & 1;
}
/**
* xa_tag_pointer() - Create an XArray entry for a tagged pointer.
* @p: Plain pointer.
* @tag: Tag value (0, 1 or 3).
*
* If the user of the XArray prefers, they can tag their pointers instead
* of storing value entries. Three tags are available (0, 1 and 3).
* These are distinct from the xa_mark_t as they are not replicated up
* through the array and cannot be searched for.
*
* Context: Any context.
* Return: An XArray entry.
*/
static inline void *xa_tag_pointer(void *p, unsigned long tag)
{
return (void *)((unsigned long)p | tag);
}
/**
* xa_untag_pointer() - Turn an XArray entry into a plain pointer.
* @entry: XArray entry.
*
* If you have stored a tagged pointer in the XArray, call this function
* to get the untagged version of the pointer.
*
* Context: Any context.
* Return: A pointer.
*/
static inline void *xa_untag_pointer(void *entry)
{
return (void *)((unsigned long)entry & ~3UL);
}
/**
* xa_pointer_tag() - Get the tag stored in an XArray entry.
* @entry: XArray entry.
*
* If you have stored a tagged pointer in the XArray, call this function
* to get the tag of that pointer.
*
* Context: Any context.
* Return: A tag.
*/
static inline unsigned int xa_pointer_tag(void *entry)
{
return (unsigned long)entry & 3UL;
}
/*
* xa_mk_internal() - Create an internal entry.
* @v: Value to turn into an internal entry.
*
* Internal entries are used for a number of purposes. Entries 0-255 are
* used for sibling entries (only 0-62 are used by the current code). 256
* is used for the retry entry. 257 is used for the reserved / zero entry.
* Negative internal entries are used to represent errnos. Node pointers
* are also tagged as internal entries in some situations.
*
* Context: Any context.
* Return: An XArray internal entry corresponding to this value.
*/
static inline void *xa_mk_internal(unsigned long v)
{
return (void *)((v << 2) | 2);
}
/*
* xa_to_internal() - Extract the value from an internal entry.
* @entry: XArray entry.
*
* Context: Any context.
* Return: The value which was stored in the internal entry.
*/
static inline unsigned long xa_to_internal(const void *entry)
{
return (unsigned long)entry >> 2;
}
/*
* xa_is_internal() - Is the entry an internal entry?
* @entry: XArray entry.
*
* Context: Any context.
* Return: %true if the entry is an internal entry.
*/
static inline bool xa_is_internal(const void *entry)
{
return ((unsigned long)entry & 3) == 2;
}
#define XA_ZERO_ENTRY xa_mk_internal(257)
/**
* xa_is_zero() - Is the entry a zero entry?
* @entry: Entry retrieved from the XArray
*
* The normal API will return NULL as the contents of a slot containing
* a zero entry. You can only see zero entries by using the advanced API.
*
* Return: %true if the entry is a zero entry.
*/
static inline bool xa_is_zero(const void *entry)
{
return unlikely(entry == XA_ZERO_ENTRY);
}
/**
* xa_is_err() - Report whether an XArray operation returned an error
* @entry: Result from calling an XArray function
*
* If an XArray operation cannot complete an operation, it will return
* a special value indicating an error. This function tells you
* whether an error occurred; xa_err() tells you which error occurred.
*
* Context: Any context.
* Return: %true if the entry indicates an error.
*/
static inline bool xa_is_err(const void *entry)
{
return unlikely(xa_is_internal(entry) &&
entry >= xa_mk_internal(-MAX_ERRNO));
}
/**
* xa_err() - Turn an XArray result into an errno.
* @entry: Result from calling an XArray function.
*
* If an XArray operation cannot complete an operation, it will return
* a special pointer value which encodes an errno. This function extracts
* the errno from the pointer value, or returns 0 if the pointer does not
* represent an errno.
*
* Context: Any context.
* Return: A negative errno or 0.
*/
static inline int xa_err(void *entry)
{
/* xa_to_internal() would not do sign extension. */
if (xa_is_err(entry))
return (long)entry >> 2;
return 0;
}
/**
* struct xa_limit - Represents a range of IDs.
* @min: The lowest ID to allocate (inclusive).
* @max: The maximum ID to allocate (inclusive).
*
* This structure is used either directly or via the XA_LIMIT() macro
* to communicate the range of IDs that are valid for allocation.
* Three common ranges are predefined for you:
* * xa_limit_32b - [0 - UINT_MAX]
* * xa_limit_31b - [0 - INT_MAX]
* * xa_limit_16b - [0 - USHRT_MAX]
*/
struct xa_limit {
u32 max;
u32 min;
};
#define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max }
#define xa_limit_32b XA_LIMIT(0, UINT_MAX)
#define xa_limit_31b XA_LIMIT(0, INT_MAX)
#define xa_limit_16b XA_LIMIT(0, USHRT_MAX)
typedef unsigned __bitwise xa_mark_t;
#define XA_MARK_0 ((__force xa_mark_t)0U)
#define XA_MARK_1 ((__force xa_mark_t)1U)
#define XA_MARK_2 ((__force xa_mark_t)2U)
#define XA_PRESENT ((__force xa_mark_t)8U)
#define XA_MARK_MAX XA_MARK_2
#define XA_FREE_MARK XA_MARK_0
enum xa_lock_type {
XA_LOCK_IRQ = 1,
XA_LOCK_BH = 2,
};
/*
* Values for xa_flags. The radix tree stores its GFP flags in the xa_flags,
* and we remain compatible with that.
*/
#define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ)
#define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH)
#define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U)
#define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U)
#define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U)
#define XA_FLAGS_ACCOUNT ((__force gfp_t)32U)
#define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
(__force unsigned)(mark)))
/* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */
#define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK))
#define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY)
/**
* struct xarray - The anchor of the XArray.
* @xa_lock: Lock that protects the contents of the XArray.
*
* To use the xarray, define it statically or embed it in your data structure.
* It is a very small data structure, so it does not usually make sense to
* allocate it separately and keep a pointer to it in your data structure.
*
* You may use the xa_lock to protect your own data structures as well.
*/
/*
* If all of the entries in the array are NULL, @xa_head is a NULL pointer.
* If the only non-NULL entry in the array is at index 0, @xa_head is that
* entry. If any other entry in the array is non-NULL, @xa_head points
* to an @xa_node.
*/
struct xarray {
spinlock_t xa_lock;
/* private: The rest of the data structure is not to be used directly. */
gfp_t xa_flags;
void __rcu * xa_head;
};
#define XARRAY_INIT(name, flags) { \
.xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \
.xa_flags = flags, \
.xa_head = NULL, \
}
/**
* DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags.
* @name: A string that names your XArray.
* @flags: XA_FLAG values.
*
* This is intended for file scope definitions of XArrays. It declares
* and initialises an empty XArray with the chosen name and flags. It is
* equivalent to calling xa_init_flags() on the array, but it does the
* initialisation at compiletime instead of runtime.
*/
#define DEFINE_XARRAY_FLAGS(name, flags) \
struct xarray name = XARRAY_INIT(name, flags)
/**
* DEFINE_XARRAY() - Define an XArray.
* @name: A string that names your XArray.
*
* This is intended for file scope definitions of XArrays. It declares
* and initialises an empty XArray with the chosen name. It is equivalent
* to calling xa_init() on the array, but it does the initialisation at
* compiletime instead of runtime.
*/
#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0)
/**
* DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0.
* @name: A string that names your XArray.
*
* This is intended for file scope definitions of allocating XArrays.
* See also DEFINE_XARRAY().
*/
#define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC)
/**
* DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1.
* @name: A string that names your XArray.
*
* This is intended for file scope definitions of allocating XArrays.
* See also DEFINE_XARRAY().
*/
#define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1)
void *xa_load(struct xarray *, unsigned long index);
void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
void *xa_erase(struct xarray *, unsigned long index);
void *xa_store_range(struct xarray *, unsigned long first, unsigned long last,
void *entry, gfp_t);
bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
void *xa_find(struct xarray *xa, unsigned long *index,
unsigned long max, xa_mark_t) __attribute__((nonnull(2)));
void *xa_find_after(struct xarray *xa, unsigned long *index,
unsigned long max, xa_mark_t) __attribute__((nonnull(2)));
unsigned int xa_extract(struct xarray *, void **dst, unsigned long start,
unsigned long max, unsigned int n, xa_mark_t);
void xa_destroy(struct xarray *);
/**
* xa_init_flags() - Initialise an empty XArray with flags.
* @xa: XArray.
* @flags: XA_FLAG values.
*
* If you need to initialise an XArray with special flags (eg you need
* to take the lock from interrupt context), use this function instead
* of xa_init().
*
* Context: Any context.
*/
static inline void xa_init_flags(struct xarray *xa, gfp_t flags)
{
spin_lock_init(&xa->xa_lock);
xa->xa_flags = flags;
xa->xa_head = NULL;
}
/**
* xa_init() - Initialise an empty XArray.
* @xa: XArray.
*
* An empty XArray is full of NULL entries.
*
* Context: Any context.
*/
static inline void xa_init(struct xarray *xa)
{
xa_init_flags(xa, 0);
}
/**
* xa_empty() - Determine if an array has any present entries.
* @xa: XArray.
*
* Context: Any context.
* Return: %true if the array contains only NULL pointers.
*/
static inline bool xa_empty(const struct xarray *xa)
{
return xa->xa_head == NULL;
}
/**
* xa_marked() - Inquire whether any entry in this array has a mark set
* @xa: Array
* @mark: Mark value
*
* Context: Any context.
* Return: %true if any entry has this mark set.
*/
static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
{
return xa->xa_flags & XA_FLAGS_MARK(mark);
}
/**
* xa_for_each_range() - Iterate over a portion of an XArray.
* @xa: XArray.
* @index: Index of @entry.
* @entry: Entry retrieved from array.
* @start: First index to retrieve from array.
* @last: Last index to retrieve from array.
*
* During the iteration, @entry will have the value of the entry stored
* in @xa at @index. You may modify @index during the iteration if you
* want to skip or reprocess indices. It is safe to modify the array
* during the iteration. At the end of the iteration, @entry will be set
* to NULL and @index will have a value less than or equal to max.
*
* xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have
* to handle your own locking with xas_for_each(), and if you have to unlock
* after each iteration, it will also end up being O(n.log(n)).
* xa_for_each_range() will spin if it hits a retry entry; if you intend to
* see retry entries, you should use the xas_for_each() iterator instead.
* The xas_for_each() iterator will expand into more inline code than
* xa_for_each_range().
*
* Context: Any context. Takes and releases the RCU lock.
*/
#define xa_for_each_range(xa, index, entry, start, last) \
for (index = start, \
entry = xa_find(xa, &index, last, XA_PRESENT); \
entry; \
entry = xa_find_after(xa, &index, last, XA_PRESENT))
/**
* xa_for_each_start() - Iterate over a portion of an XArray.
* @xa: XArray.
* @index: Index of @entry.
* @entry: Entry retrieved from array.
* @start: First index to retrieve from array.
*
* During the iteration, @entry will have the value of the entry stored
* in @xa at @index. You may modify @index during the iteration if you
* want to skip or reprocess indices. It is safe to modify the array
* during the iteration. At the end of the iteration, @entry will be set
* to NULL and @index will have a value less than or equal to max.
*
* xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have
* to handle your own locking with xas_for_each(), and if you have to unlock
* after each iteration, it will also end up being O(n.log(n)).
* xa_for_each_start() will spin if it hits a retry entry; if you intend to
* see retry entries, you should use the xas_for_each() iterator instead.
* The xas_for_each() iterator will expand into more inline code than
* xa_for_each_start().
*
* Context: Any context. Takes and releases the RCU lock.
*/
#define xa_for_each_start(xa, index, entry, start) \
xa_for_each_range(xa, index, entry, start, ULONG_MAX)
/**
* xa_for_each() - Iterate over present entries in an XArray.
* @xa: XArray.
* @index: Index of @entry.
* @entry: Entry retrieved from array.
*
* During the iteration, @entry will have the value of the entry stored
* in @xa at @index. You may modify @index during the iteration if you want
* to skip or reprocess indices. It is safe to modify the array during the
* iteration. At the end of the iteration, @entry will be set to NULL and
* @index will have a value less than or equal to max.
*
* xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have
* to handle your own locking with xas_for_each(), and if you have to unlock
* after each iteration, it will also end up being O(n.log(n)). xa_for_each()
* will spin if it hits a retry entry; if you intend to see retry entries,
* you should use the xas_for_each() iterator instead. The xas_for_each()
* iterator will expand into more inline code than xa_for_each().
*
* Context: Any context. Takes and releases the RCU lock.
*/
#define xa_for_each(xa, index, entry) \
xa_for_each_start(xa, index, entry, 0)
/**
* xa_for_each_marked() - Iterate over marked entries in an XArray.
* @xa: XArray.
* @index: Index of @entry.
* @entry: Entry retrieved from array.
* @filter: Selection criterion.
*
* During the iteration, @entry will have the value of the entry stored
* in @xa at @index. The iteration will skip all entries in the array
* which do not match @filter. You may modify @index during the iteration
* if you want to skip or reprocess indices. It is safe to modify the array
* during the iteration. At the end of the iteration, @entry will be set to
* NULL and @index will have a value less than or equal to max.
*
* xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n).
* You have to handle your own locking with xas_for_each(), and if you have
* to unlock after each iteration, it will also end up being O(n.log(n)).
* xa_for_each_marked() will spin if it hits a retry entry; if you intend to
* see retry entries, you should use the xas_for_each_marked() iterator
* instead. The xas_for_each_marked() iterator will expand into more inline
* code than xa_for_each_marked().
*
* Context: Any context. Takes and releases the RCU lock.
*/
#define xa_for_each_marked(xa, index, entry, filter) \
for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \
entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter))
#define xa_trylock(xa) spin_trylock(&(xa)->xa_lock)
#define xa_lock(xa) spin_lock(&(xa)->xa_lock)
#define xa_unlock(xa) spin_unlock(&(xa)->xa_lock)
#define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock)
#define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock)
#define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock)
#define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock)
#define xa_lock_irqsave(xa, flags) \
spin_lock_irqsave(&(xa)->xa_lock, flags)
#define xa_unlock_irqrestore(xa, flags) \
spin_unlock_irqrestore(&(xa)->xa_lock, flags)
#define xa_lock_nested(xa, subclass) \
spin_lock_nested(&(xa)->xa_lock, subclass)
#define xa_lock_bh_nested(xa, subclass) \
spin_lock_bh_nested(&(xa)->xa_lock, subclass)
#define xa_lock_irq_nested(xa, subclass) \
spin_lock_irq_nested(&(xa)->xa_lock, subclass)
#define xa_lock_irqsave_nested(xa, flags, subclass) \
spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass)
/*
* Versions of the normal API which require the caller to hold the
* xa_lock. If the GFP flags allow it, they will drop the lock to
* allocate memory, then reacquire it afterwards. These functions
* may also re-enable interrupts if the XArray flags indicate the
* locking should be interrupt safe.
*/
void *__xa_erase(struct xarray *, unsigned long index);
void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old,
void *entry, gfp_t);
int __must_check __xa_insert(struct xarray *, unsigned long index,
void *entry, gfp_t);
int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry,
struct xa_limit, gfp_t);
int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry,
struct xa_limit, u32 *next, gfp_t);
void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
/**
* xa_store_bh() - Store this entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* This function is like calling xa_store() except it disables softirqs
* while holding the array lock.
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs.
* Return: The old entry at this index or xa_err() if an error happened.
*/
static inline void *xa_store_bh(struct xarray *xa, unsigned long index,
void *entry, gfp_t gfp)
{
void *curr;
might_alloc(gfp);
xa_lock_bh(xa);
curr = __xa_store(xa, index, entry, gfp);
xa_unlock_bh(xa);
return curr;
}
/**
* xa_store_irq() - Store this entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* This function is like calling xa_store() except it disables interrupts
* while holding the array lock.
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts.
* Return: The old entry at this index or xa_err() if an error happened.
*/
static inline void *xa_store_irq(struct xarray *xa, unsigned long index,
void *entry, gfp_t gfp)
{
void *curr;
might_alloc(gfp);
xa_lock_irq(xa);
curr = __xa_store(xa, index, entry, gfp);
xa_unlock_irq(xa);
return curr;
}
/**
* xa_erase_bh() - Erase this entry from the XArray.
* @xa: XArray.
* @index: Index of entry.
*
* After this function returns, loading from @index will return %NULL.
* If the index is part of a multi-index entry, all indices will be erased
* and none of the entries will be part of a multi-index entry.
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs.
* Return: The entry which used to be at this index.
*/
static inline void *xa_erase_bh(struct xarray *xa, unsigned long index)
{
void *entry;
xa_lock_bh(xa);
entry = __xa_erase(xa, index);
xa_unlock_bh(xa);
return entry;
}
/**
* xa_erase_irq() - Erase this entry from the XArray.
* @xa: XArray.
* @index: Index of entry.
*
* After this function returns, loading from @index will return %NULL.
* If the index is part of a multi-index entry, all indices will be erased
* and none of the entries will be part of a multi-index entry.
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts.
* Return: The entry which used to be at this index.
*/
static inline void *xa_erase_irq(struct xarray *xa, unsigned long index)
{
void *entry;
xa_lock_irq(xa);
entry = __xa_erase(xa, index);
xa_unlock_irq(xa);
return entry;
}
/**
* xa_cmpxchg() - Conditionally replace an entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @old: Old value to test against.
* @entry: New value to place in array.
* @gfp: Memory allocation flags.
*
* If the entry at @index is the same as @old, replace it with @entry.
* If the return value is equal to @old, then the exchange was successful.
*
* Context: Any context. Takes and releases the xa_lock. May sleep
* if the @gfp flags permit.
* Return: The old value at this index or xa_err() if an error happened.
*/
static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp)
{
void *curr;
might_alloc(gfp);
xa_lock(xa);
curr = __xa_cmpxchg(xa, index, old, entry, gfp);
xa_unlock(xa);
return curr;
}
/**
* xa_cmpxchg_bh() - Conditionally replace an entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @old: Old value to test against.
* @entry: New value to place in array.
* @gfp: Memory allocation flags.
*
* This function is like calling xa_cmpxchg() except it disables softirqs
* while holding the array lock.
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs. May sleep if the @gfp flags permit.
* Return: The old value at this index or xa_err() if an error happened.
*/
static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp)
{
void *curr;
might_alloc(gfp);
xa_lock_bh(xa);
curr = __xa_cmpxchg(xa, index, old, entry, gfp);
xa_unlock_bh(xa);
return curr;
}
/**
* xa_cmpxchg_irq() - Conditionally replace an entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @old: Old value to test against.
* @entry: New value to place in array.
* @gfp: Memory allocation flags.
*
* This function is like calling xa_cmpxchg() except it disables interrupts
* while holding the array lock.
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts. May sleep if the @gfp flags permit.
* Return: The old value at this index or xa_err() if an error happened.
*/
static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp)
{
void *curr;
might_alloc(gfp);
xa_lock_irq(xa);
curr = __xa_cmpxchg(xa, index, old, entry, gfp);
xa_unlock_irq(xa);
return curr;
}
/**
* xa_insert() - Store this entry in the XArray unless another entry is
* already present.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* Inserting a NULL entry will store a reserved entry (like xa_reserve())
* if no entry is present. Inserting will fail if a reserved entry is
* present, even though loading from this index will return NULL.
*
* Context: Any context. Takes and releases the xa_lock. May sleep if
* the @gfp flags permit.
* Return: 0 if the store succeeded. -EBUSY if another entry was present.
* -ENOMEM if memory could not be allocated.
*/
static inline int __must_check xa_insert(struct xarray *xa,
unsigned long index, void *entry, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock(xa);
err = __xa_insert(xa, index, entry, gfp);
xa_unlock(xa);
return err;
}
/**
* xa_insert_bh() - Store this entry in the XArray unless another entry is
* already present.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* Inserting a NULL entry will store a reserved entry (like xa_reserve())
* if no entry is present. Inserting will fail if a reserved entry is
* present, even though loading from this index will return NULL.
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs. May sleep if the @gfp flags permit.
* Return: 0 if the store succeeded. -EBUSY if another entry was present.
* -ENOMEM if memory could not be allocated.
*/
static inline int __must_check xa_insert_bh(struct xarray *xa,
unsigned long index, void *entry, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_bh(xa);
err = __xa_insert(xa, index, entry, gfp);
xa_unlock_bh(xa);
return err;
}
/**
* xa_insert_irq() - Store this entry in the XArray unless another entry is
* already present.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* Inserting a NULL entry will store a reserved entry (like xa_reserve())
* if no entry is present. Inserting will fail if a reserved entry is
* present, even though loading from this index will return NULL.
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts. May sleep if the @gfp flags permit.
* Return: 0 if the store succeeded. -EBUSY if another entry was present.
* -ENOMEM if memory could not be allocated.
*/
static inline int __must_check xa_insert_irq(struct xarray *xa,
unsigned long index, void *entry, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_irq(xa);
err = __xa_insert(xa, index, entry, gfp);
xa_unlock_irq(xa);
return err;
}
/**
* xa_alloc() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Takes and releases the xa_lock. May sleep if
* the @gfp flags permit.
* Return: 0 on success, -ENOMEM if memory could not be allocated or
* -EBUSY if there are no free entries in @limit.
*/
static inline __must_check int xa_alloc(struct xarray *xa, u32 *id,
void *entry, struct xa_limit limit, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock(xa);
err = __xa_alloc(xa, id, entry, limit, gfp);
xa_unlock(xa);
return err;
}
/**
* xa_alloc_bh() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs. May sleep if the @gfp flags permit.
* Return: 0 on success, -ENOMEM if memory could not be allocated or
* -EBUSY if there are no free entries in @limit.
*/
static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id,
void *entry, struct xa_limit limit, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_bh(xa);
err = __xa_alloc(xa, id, entry, limit, gfp);
xa_unlock_bh(xa);
return err;
}
/**
* xa_alloc_irq() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts. May sleep if the @gfp flags permit.
* Return: 0 on success, -ENOMEM if memory could not be allocated or
* -EBUSY if there are no free entries in @limit.
*/
static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id,
void *entry, struct xa_limit limit, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_irq(xa);
err = __xa_alloc(xa, id, entry, limit, gfp);
xa_unlock_irq(xa);
return err;
}
/**
* xa_alloc_cyclic() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of allocated ID.
* @next: Pointer to next ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
* The search for an empty entry will start at @next and will wrap
* around if necessary.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Takes and releases the xa_lock. May sleep if
* the @gfp flags permit.
* Return: 0 if the allocation succeeded without wrapping. 1 if the
* allocation succeeded after wrapping, -ENOMEM if memory could not be
* allocated or -EBUSY if there are no free entries in @limit.
*/
static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry,
struct xa_limit limit, u32 *next, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock(xa);
err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
xa_unlock(xa);
return err;
}
/**
* xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of allocated ID.
* @next: Pointer to next ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
* The search for an empty entry will start at @next and will wrap
* around if necessary.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs. May sleep if the @gfp flags permit.
* Return: 0 if the allocation succeeded without wrapping. 1 if the
* allocation succeeded after wrapping, -ENOMEM if memory could not be
* allocated or -EBUSY if there are no free entries in @limit.
*/
static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry,
struct xa_limit limit, u32 *next, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_bh(xa);
err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
xa_unlock_bh(xa);
return err;
}
/**
* xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of allocated ID.
* @next: Pointer to next ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
* The search for an empty entry will start at @next and will wrap
* around if necessary.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts. May sleep if the @gfp flags permit.
* Return: 0 if the allocation succeeded without wrapping. 1 if the
* allocation succeeded after wrapping, -ENOMEM if memory could not be
* allocated or -EBUSY if there are no free entries in @limit.
*/
static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry,
struct xa_limit limit, u32 *next, gfp_t gfp)
{
int err;
might_alloc(gfp);
xa_lock_irq(xa);
err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
xa_unlock_irq(xa);
return err;
}
/**
* xa_reserve() - Reserve this index in the XArray.
* @xa: XArray.
* @index: Index into array.
* @gfp: Memory allocation flags.
*
* Ensures there is somewhere to store an entry at @index in the array.
* If there is already something stored at @index, this function does
* nothing. If there was nothing there, the entry is marked as reserved.
* Loading from a reserved entry returns a %NULL pointer.
*
* If you do not use the entry that you have reserved, call xa_release()
* or xa_erase() to free any unnecessary memory.
*
* Context: Any context. Takes and releases the xa_lock.
* May sleep if the @gfp flags permit.
* Return: 0 if the reservation succeeded or -ENOMEM if it failed.
*/
static inline __must_check
int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp)
{
return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp));
}
/**
* xa_reserve_bh() - Reserve this index in the XArray.
* @xa: XArray.
* @index: Index into array.
* @gfp: Memory allocation flags.
*
* A softirq-disabling version of xa_reserve().
*
* Context: Any context. Takes and releases the xa_lock while
* disabling softirqs.
* Return: 0 if the reservation succeeded or -ENOMEM if it failed.
*/
static inline __must_check
int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp)
{
return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp));
}
/**
* xa_reserve_irq() - Reserve this index in the XArray.
* @xa: XArray.
* @index: Index into array.
* @gfp: Memory allocation flags.
*
* An interrupt-disabling version of xa_reserve().
*
* Context: Process context. Takes and releases the xa_lock while
* disabling interrupts.
* Return: 0 if the reservation succeeded or -ENOMEM if it failed.
*/
static inline __must_check
int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp)
{
return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp));
}
/**
* xa_release() - Release a reserved entry.
* @xa: XArray.
* @index: Index of entry.
*
* After calling xa_reserve(), you can call this function to release the
* reservation. If the entry at @index has been stored to, this function
* will do nothing.
*/
static inline void xa_release(struct xarray *xa, unsigned long index)
{
xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0);
}
/* Everything below here is the Advanced API. Proceed with caution. */
/*
* The xarray is constructed out of a set of 'chunks' of pointers. Choosing
* the best chunk size requires some tradeoffs. A power of two recommends
* itself so that we can walk the tree based purely on shifts and masks.
* Generally, the larger the better; as the number of slots per level of the
* tree increases, the less tall the tree needs to be. But that needs to be
* balanced against the memory consumption of each node. On a 64-bit system,
* xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we
* doubled the number of slots per node, we'd get only 3 nodes per 4kB page.
*/
#ifndef XA_CHUNK_SHIFT
#define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6)
#endif
#define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT)
#define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1)
#define XA_MAX_MARKS 3
#define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE)
/*
* @count is the count of every non-NULL element in the ->slots array
* whether that is a value entry, a retry entry, a user pointer,
* a sibling entry or a pointer to the next level of the tree.
* @nr_values is the count of every element in ->slots which is
* either a value entry or a sibling of a value entry.
*/
struct xa_node {
unsigned char shift; /* Bits remaining in each slot */
unsigned char offset; /* Slot offset in parent */
unsigned char count; /* Total entry count */
unsigned char nr_values; /* Value entry count */
struct xa_node __rcu *parent; /* NULL at top of tree */
struct xarray *array; /* The array we belong to */
union {
struct list_head private_list; /* For tree user */
struct rcu_head rcu_head; /* Used when freeing node */
};
void __rcu *slots[XA_CHUNK_SIZE];
union {
unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS];
unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS];
};
};
void xa_dump(const struct xarray *);
void xa_dump_node(const struct xa_node *);
#ifdef XA_DEBUG
#define XA_BUG_ON(xa, x) do { \
if (x) { \
xa_dump(xa); \
BUG(); \
} \
} while (0)
#define XA_NODE_BUG_ON(node, x) do { \
if (x) { \
if (node) xa_dump_node(node); \
BUG(); \
} \
} while (0)
#else
#define XA_BUG_ON(xa, x) do { } while (0)
#define XA_NODE_BUG_ON(node, x) do { } while (0)
#endif
/* Private */
static inline void *xa_head(const struct xarray *xa)
{
return rcu_dereference_check(xa->xa_head,
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline void *xa_head_locked(const struct xarray *xa)
{
return rcu_dereference_protected(xa->xa_head,
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline void *xa_entry(const struct xarray *xa,
const struct xa_node *node, unsigned int offset)
{
XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
return rcu_dereference_check(node->slots[offset],
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline void *xa_entry_locked(const struct xarray *xa,
const struct xa_node *node, unsigned int offset)
{
XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
return rcu_dereference_protected(node->slots[offset],
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline struct xa_node *xa_parent(const struct xarray *xa,
const struct xa_node *node)
{ return rcu_dereference_check(node->parent,
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
const struct xa_node *node)
{
return rcu_dereference_protected(node->parent,
lockdep_is_held(&xa->xa_lock));
}
/* Private */
static inline void *xa_mk_node(const struct xa_node *node)
{
return (void *)((unsigned long)node | 2);
}
/* Private */
static inline struct xa_node *xa_to_node(const void *entry)
{
return (struct xa_node *)((unsigned long)entry - 2);
}
/* Private */
static inline bool xa_is_node(const void *entry)
{
return xa_is_internal(entry) && (unsigned long)entry > 4096;
}
/* Private */
static inline void *xa_mk_sibling(unsigned int offset)
{
return xa_mk_internal(offset);
}
/* Private */
static inline unsigned long xa_to_sibling(const void *entry)
{
return xa_to_internal(entry);
}
/**
* xa_is_sibling() - Is the entry a sibling entry?
* @entry: Entry retrieved from the XArray
*
* Return: %true if the entry is a sibling entry.
*/
static inline bool xa_is_sibling(const void *entry)
{
return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) &&
(entry < xa_mk_sibling(XA_CHUNK_SIZE - 1));
}
#define XA_RETRY_ENTRY xa_mk_internal(256)
/**
* xa_is_retry() - Is the entry a retry entry?
* @entry: Entry retrieved from the XArray
*
* Return: %true if the entry is a retry entry.
*/
static inline bool xa_is_retry(const void *entry)
{
return unlikely(entry == XA_RETRY_ENTRY);
}
/**
* xa_is_advanced() - Is the entry only permitted for the advanced API?
* @entry: Entry to be stored in the XArray.
*
* Return: %true if the entry cannot be stored by the normal API.
*/
static inline bool xa_is_advanced(const void *entry)
{
return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY);
}
/**
* typedef xa_update_node_t - A callback function from the XArray.
* @node: The node which is being processed
*
* This function is called every time the XArray updates the count of
* present and value entries in a node. It allows advanced users to
* maintain the private_list in the node.
*
* Context: The xa_lock is held and interrupts may be disabled.
* Implementations should not drop the xa_lock, nor re-enable
* interrupts.
*/
typedef void (*xa_update_node_t)(struct xa_node *node);
void xa_delete_node(struct xa_node *, xa_update_node_t);
/*
* The xa_state is opaque to its users. It contains various different pieces
* of state involved in the current operation on the XArray. It should be
* declared on the stack and passed between the various internal routines.
* The various elements in it should not be accessed directly, but only
* through the provided accessor functions. The below documentation is for
* the benefit of those working on the code, not for users of the XArray.
*
* @xa_node usually points to the xa_node containing the slot we're operating
* on (and @xa_offset is the offset in the slots array). If there is a
* single entry in the array at index 0, there are no allocated xa_nodes to
* point to, and so we store %NULL in @xa_node. @xa_node is set to
* the value %XAS_RESTART if the xa_state is not walked to the correct
* position in the tree of nodes for this operation. If an error occurs
* during an operation, it is set to an %XAS_ERROR value. If we run off the
* end of the allocated nodes, it is set to %XAS_BOUNDS.
*/
struct xa_state {
struct xarray *xa;
unsigned long xa_index;
unsigned char xa_shift;
unsigned char xa_sibs;
unsigned char xa_offset;
unsigned char xa_pad; /* Helps gcc generate better code */
struct xa_node *xa_node;
struct xa_node *xa_alloc;
xa_update_node_t xa_update;
struct list_lru *xa_lru;
};
/*
* We encode errnos in the xas->xa_node. If an error has happened, we need to
* drop the lock to fix it, and once we've done so the xa_state is invalid.
*/
#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL))
#define XAS_BOUNDS ((struct xa_node *)1UL)
#define XAS_RESTART ((struct xa_node *)3UL)
#define __XA_STATE(array, index, shift, sibs) { \
.xa = array, \
.xa_index = index, \
.xa_shift = shift, \
.xa_sibs = sibs, \
.xa_offset = 0, \
.xa_pad = 0, \
.xa_node = XAS_RESTART, \
.xa_alloc = NULL, \
.xa_update = NULL, \
.xa_lru = NULL, \
}
/**
* XA_STATE() - Declare an XArray operation state.
* @name: Name of this operation state (usually xas).
* @array: Array to operate on.
* @index: Initial index of interest.
*
* Declare and initialise an xa_state on the stack.
*/
#define XA_STATE(name, array, index) \
struct xa_state name = __XA_STATE(array, index, 0, 0)
/**
* XA_STATE_ORDER() - Declare an XArray operation state.
* @name: Name of this operation state (usually xas).
* @array: Array to operate on.
* @index: Initial index of interest.
* @order: Order of entry.
*
* Declare and initialise an xa_state on the stack. This variant of
* XA_STATE() allows you to specify the 'order' of the element you
* want to operate on.`
*/
#define XA_STATE_ORDER(name, array, index, order) \
struct xa_state name = __XA_STATE(array, \
(index >> order) << order, \
order - (order % XA_CHUNK_SHIFT), \
(1U << (order % XA_CHUNK_SHIFT)) - 1)
#define xas_marked(xas, mark) xa_marked((xas)->xa, (mark))
#define xas_trylock(xas) xa_trylock((xas)->xa)
#define xas_lock(xas) xa_lock((xas)->xa)
#define xas_unlock(xas) xa_unlock((xas)->xa)
#define xas_lock_bh(xas) xa_lock_bh((xas)->xa)
#define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa)
#define xas_lock_irq(xas) xa_lock_irq((xas)->xa)
#define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa)
#define xas_lock_irqsave(xas, flags) \
xa_lock_irqsave((xas)->xa, flags)
#define xas_unlock_irqrestore(xas, flags) \
xa_unlock_irqrestore((xas)->xa, flags)
/**
* xas_error() - Return an errno stored in the xa_state.
* @xas: XArray operation state.
*
* Return: 0 if no error has been noted. A negative errno if one has.
*/
static inline int xas_error(const struct xa_state *xas)
{
return xa_err(xas->xa_node);
}
/**
* xas_set_err() - Note an error in the xa_state.
* @xas: XArray operation state.
* @err: Negative error number.
*
* Only call this function with a negative @err; zero or positive errors
* will probably not behave the way you think they should. If you want
* to clear the error from an xa_state, use xas_reset().
*/
static inline void xas_set_err(struct xa_state *xas, long err)
{
xas->xa_node = XA_ERROR(err);
}
/**
* xas_invalid() - Is the xas in a retry or error state?
* @xas: XArray operation state.
*
* Return: %true if the xas cannot be used for operations.
*/
static inline bool xas_invalid(const struct xa_state *xas)
{
return (unsigned long)xas->xa_node & 3;
}
/**
* xas_valid() - Is the xas a valid cursor into the array?
* @xas: XArray operation state.
*
* Return: %true if the xas can be used for operations.
*/
static inline bool xas_valid(const struct xa_state *xas)
{
return !xas_invalid(xas);
}
/**
* xas_is_node() - Does the xas point to a node?
* @xas: XArray operation state.
*
* Return: %true if the xas currently references a node.
*/
static inline bool xas_is_node(const struct xa_state *xas)
{
return xas_valid(xas) && xas->xa_node;
}
/* True if the pointer is something other than a node */
static inline bool xas_not_node(struct xa_node *node)
{
return ((unsigned long)node & 3) || !node;
}
/* True if the node represents RESTART or an error */
static inline bool xas_frozen(struct xa_node *node)
{
return (unsigned long)node & 2;
}
/* True if the node represents head-of-tree, RESTART or BOUNDS */
static inline bool xas_top(struct xa_node *node)
{
return node <= XAS_RESTART;
}
/**
* xas_reset() - Reset an XArray operation state.
* @xas: XArray operation state.
*
* Resets the error or walk state of the @xas so future walks of the
* array will start from the root. Use this if you have dropped the
* xarray lock and want to reuse the xa_state.
*
* Context: Any context.
*/
static inline void xas_reset(struct xa_state *xas)
{
xas->xa_node = XAS_RESTART;
}
/**
* xas_retry() - Retry the operation if appropriate.
* @xas: XArray operation state.
* @entry: Entry from xarray.
*
* The advanced functions may sometimes return an internal entry, such as
* a retry entry or a zero entry. This function sets up the @xas to restart
* the walk from the head of the array if needed.
*
* Context: Any context.
* Return: true if the operation needs to be retried.
*/
static inline bool xas_retry(struct xa_state *xas, const void *entry)
{
if (xa_is_zero(entry))
return true;
if (!xa_is_retry(entry))
return false;
xas_reset(xas);
return true;
}
void *xas_load(struct xa_state *);
void *xas_store(struct xa_state *, void *entry);
void *xas_find(struct xa_state *, unsigned long max);
void *xas_find_conflict(struct xa_state *);
bool xas_get_mark(const struct xa_state *, xa_mark_t);
void xas_set_mark(const struct xa_state *, xa_mark_t);
void xas_clear_mark(const struct xa_state *, xa_mark_t);
void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t);
void xas_init_marks(const struct xa_state *);
bool xas_nomem(struct xa_state *, gfp_t);
void xas_destroy(struct xa_state *);
void xas_pause(struct xa_state *);
void xas_create_range(struct xa_state *);
#ifdef CONFIG_XARRAY_MULTI
int xa_get_order(struct xarray *, unsigned long index);
int xas_get_order(struct xa_state *xas);
void xas_split(struct xa_state *, void *entry, unsigned int order);
void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t);
void xas_try_split(struct xa_state *xas, void *entry, unsigned int order);
unsigned int xas_try_split_min_order(unsigned int order);
#else
static inline int xa_get_order(struct xarray *xa, unsigned long index)
{
return 0;
}
static inline int xas_get_order(struct xa_state *xas)
{
return 0;
}
static inline void xas_split(struct xa_state *xas, void *entry,
unsigned int order)
{
xas_store(xas, entry);
}
static inline void xas_split_alloc(struct xa_state *xas, void *entry,
unsigned int order, gfp_t gfp)
{
}
static inline void xas_try_split(struct xa_state *xas, void *entry,
unsigned int order)
{
}
static inline unsigned int xas_try_split_min_order(unsigned int order)
{
return 0;
}
#endif
/**
* xas_reload() - Refetch an entry from the xarray.
* @xas: XArray operation state.
*
* Use this function to check that a previously loaded entry still has
* the same value. This is useful for the lockless pagecache lookup where
* we walk the array with only the RCU lock to protect us, lock the page,
* then check that the page hasn't moved since we looked it up.
*
* The caller guarantees that @xas is still valid. If it may be in an
* error or restart state, call xas_load() instead.
*
* Return: The entry at this location in the xarray.
*/
static inline void *xas_reload(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
void *entry;
char offset;
if (!node)
return xa_head(xas->xa);
if (IS_ENABLED(CONFIG_XARRAY_MULTI)) {
offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK;
entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry))
return entry;
offset = xa_to_sibling(entry);
} else {
offset = xas->xa_offset;
}
return xa_entry(xas->xa, node, offset);
}
/**
* xas_set() - Set up XArray operation state for a different index.
* @xas: XArray operation state.
* @index: New index into the XArray.
*
* Move the operation state to refer to a different index. This will
* have the effect of starting a walk from the top; see xas_next()
* to move to an adjacent index.
*/
static inline void xas_set(struct xa_state *xas, unsigned long index)
{
xas->xa_index = index;
xas->xa_node = XAS_RESTART;
}
/**
* xas_advance() - Skip over sibling entries.
* @xas: XArray operation state.
* @index: Index of last sibling entry.
*
* Move the operation state to refer to the last sibling entry.
* This is useful for loops that normally want to see sibling
* entries but sometimes want to skip them. Use xas_set() if you
* want to move to an index which is not part of this entry.
*/
static inline void xas_advance(struct xa_state *xas, unsigned long index)
{
unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0;
xas->xa_index = index;
xas->xa_offset = (index >> shift) & XA_CHUNK_MASK;
}
/**
* xas_set_order() - Set up XArray operation state for a multislot entry.
* @xas: XArray operation state.
* @index: Target of the operation.
* @order: Entry occupies 2^@order indices.
*/
static inline void xas_set_order(struct xa_state *xas, unsigned long index,
unsigned int order)
{
#ifdef CONFIG_XARRAY_MULTI
xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0;
xas->xa_shift = order - (order % XA_CHUNK_SHIFT);
xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
xas->xa_node = XAS_RESTART;
#else
BUG_ON(order > 0);
xas_set(xas, index);
#endif
}
/**
* xas_set_update() - Set up XArray operation state for a callback.
* @xas: XArray operation state.
* @update: Function to call when updating a node.
*
* The XArray can notify a caller after it has updated an xa_node.
* This is advanced functionality and is only needed by the page
* cache and swap cache.
*/
static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update)
{
xas->xa_update = update;
}
static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru)
{
xas->xa_lru = lru;
}
/**
* xas_next_entry() - Advance iterator to next present entry.
* @xas: XArray operation state.
* @max: Highest index to return.
*
* xas_next_entry() is an inline function to optimise xarray traversal for
* speed. It is equivalent to calling xas_find(), and will call xas_find()
* for all the hard cases.
*
* Return: The next present entry after the one currently referred to by @xas.
*/
static inline void *xas_next_entry(struct xa_state *xas, unsigned long max)
{
struct xa_node *node = xas->xa_node;
void *entry;
if (unlikely(xas_not_node(node) || node->shift ||
xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)))
return xas_find(xas, max);
do {
if (unlikely(xas->xa_index >= max))
return xas_find(xas, max);
if (unlikely(xas->xa_offset == XA_CHUNK_MASK))
return xas_find(xas, max);
entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry)))
return xas_find(xas, max);
xas->xa_offset++;
xas->xa_index++;
} while (!entry);
return entry;
}
/* Private */
static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance,
xa_mark_t mark)
{
unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark];
unsigned int offset = xas->xa_offset;
if (advance)
offset++;
if (XA_CHUNK_SIZE == BITS_PER_LONG) {
if (offset < XA_CHUNK_SIZE) {
unsigned long data = *addr & (~0UL << offset);
if (data) return __ffs(data);
}
return XA_CHUNK_SIZE;
}
return find_next_bit(addr, XA_CHUNK_SIZE, offset);
}
/**
* xas_next_marked() - Advance iterator to next marked entry.
* @xas: XArray operation state.
* @max: Highest index to return.
* @mark: Mark to search for.
*
* xas_next_marked() is an inline function to optimise xarray traversal for
* speed. It is equivalent to calling xas_find_marked(), and will call
* xas_find_marked() for all the hard cases.
*
* Return: The next marked entry after the one currently referred to by @xas.
*/
static inline void *xas_next_marked(struct xa_state *xas, unsigned long max,
xa_mark_t mark)
{
struct xa_node *node = xas->xa_node;
void *entry;
unsigned int offset;
if (unlikely(xas_not_node(node) || node->shift))
return xas_find_marked(xas, max, mark);
offset = xas_find_chunk(xas, true, mark);
xas->xa_offset = offset;
xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset;
if (xas->xa_index > max)
return NULL;
if (offset == XA_CHUNK_SIZE)
return xas_find_marked(xas, max, mark);
entry = xa_entry(xas->xa, node, offset);
if (!entry)
return xas_find_marked(xas, max, mark);
return entry;
}
/*
* If iterating while holding a lock, drop the lock and reschedule
* every %XA_CHECK_SCHED loops.
*/
enum {
XA_CHECK_SCHED = 4096,
};
/**
* xas_for_each() - Iterate over a range of an XArray.
* @xas: XArray operation state.
* @entry: Entry retrieved from the array.
* @max: Maximum index to retrieve from array.
*
* The loop body will be executed for each entry present in the xarray
* between the current xas position and @max. @entry will be set to
* the entry retrieved from the xarray. It is safe to delete entries
* from the array in the loop body. You should hold either the RCU lock
* or the xa_lock while iterating. If you need to drop the lock, call
* xas_pause() first.
*/
#define xas_for_each(xas, entry, max) \
for (entry = xas_find(xas, max); entry; \
entry = xas_next_entry(xas, max))
/**
* xas_for_each_marked() - Iterate over a range of an XArray.
* @xas: XArray operation state.
* @entry: Entry retrieved from the array.
* @max: Maximum index to retrieve from array.
* @mark: Mark to search for.
*
* The loop body will be executed for each marked entry in the xarray
* between the current xas position and @max. @entry will be set to
* the entry retrieved from the xarray. It is safe to delete entries
* from the array in the loop body. You should hold either the RCU lock
* or the xa_lock while iterating. If you need to drop the lock, call
* xas_pause() first.
*/
#define xas_for_each_marked(xas, entry, max, mark) \
for (entry = xas_find_marked(xas, max, mark); entry; \
entry = xas_next_marked(xas, max, mark))
/**
* xas_for_each_conflict() - Iterate over a range of an XArray.
* @xas: XArray operation state.
* @entry: Entry retrieved from the array.
*
* The loop body will be executed for each entry in the XArray that
* lies within the range specified by @xas. If the loop terminates
* normally, @entry will be %NULL. The user may break out of the loop,
* which will leave @entry set to the conflicting entry. The caller
* may also call xa_set_err() to exit the loop while setting an error
* to record the reason.
*/
#define xas_for_each_conflict(xas, entry) \
while ((entry = xas_find_conflict(xas)))
void *__xas_next(struct xa_state *);
void *__xas_prev(struct xa_state *);
/**
* xas_prev() - Move iterator to previous index.
* @xas: XArray operation state.
*
* If the @xas was in an error state, it will remain in an error state
* and this function will return %NULL. If the @xas has never been walked,
* it will have the effect of calling xas_load(). Otherwise one will be
* subtracted from the index and the state will be walked to the correct
* location in the array for the next operation.
*
* If the iterator was referencing index 0, this function wraps
* around to %ULONG_MAX.
*
* Return: The entry at the new index. This may be %NULL or an internal
* entry.
*/
static inline void *xas_prev(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
if (unlikely(xas_not_node(node) || node->shift ||
xas->xa_offset == 0))
return __xas_prev(xas);
xas->xa_index--;
xas->xa_offset--;
return xa_entry(xas->xa, node, xas->xa_offset);
}
/**
* xas_next() - Move state to next index.
* @xas: XArray operation state.
*
* If the @xas was in an error state, it will remain in an error state
* and this function will return %NULL. If the @xas has never been walked,
* it will have the effect of calling xas_load(). Otherwise one will be
* added to the index and the state will be walked to the correct
* location in the array for the next operation.
*
* If the iterator was referencing index %ULONG_MAX, this function wraps
* around to 0.
*
* Return: The entry at the new index. This may be %NULL or an internal
* entry.
*/
static inline void *xas_next(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
if (unlikely(xas_not_node(node) || node->shift ||
xas->xa_offset == XA_CHUNK_MASK))
return __xas_next(xas);
xas->xa_index++;
xas->xa_offset++;
return xa_entry(xas->xa, node, xas->xa_offset);
}
#endif /* _LINUX_XARRAY_H */
/*
* include/net/tipc.h: Include file for TIPC message header routines
*
* Copyright (c) 2017 Ericsson AB
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the names of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* Alternatively, this software may be distributed under the terms of the
* GNU General Public License ("GPL") version 2 as published by the Free
* Software Foundation.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _TIPC_HDR_H
#define _TIPC_HDR_H
#include <linux/random.h>
#define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */
struct tipc_basic_hdr {
__be32 w[4];
};
static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
{
u32 w0 = ntohl(hdr->w[0]);
bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK;
__be32 key;
/* Return source node identity as key */
if (likely(!keepalive_msg))
return hdr->w[3];
/* Spread PROBE/PROBE_REPLY messages across the cores */
get_random_bytes(&key, sizeof(key));
return key;
}
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_PREEMPT_H
#define __LINUX_PREEMPT_H
/*
* include/linux/preempt.h - macros for accessing and manipulating
* preempt_count (used for kernel preemption, interrupt count, etc.)
*/
#include <linux/linkage.h>
#include <linux/cleanup.h>
#include <linux/types.h>
/*
* We put the hardirq and softirq counter into the preemption
* counter. The bitmask has the following meaning:
*
* - bits 0-7 are the preemption count (max preemption depth: 256)
* - bits 8-15 are the softirq count (max # of softirqs: 256)
*
* The hardirq count could in theory be the same as the number of
* interrupts in the system, but we run all interrupt handlers with
* interrupts disabled, so we cannot have nesting interrupts. Though
* there are a few palaeontologic drivers which reenable interrupts in
* the handler, so we need more than one bit here.
*
* PREEMPT_MASK: 0x000000ff
* SOFTIRQ_MASK: 0x0000ff00
* HARDIRQ_MASK: 0x000f0000
* NMI_MASK: 0x00f00000
* PREEMPT_NEED_RESCHED: 0x80000000
*/
#define PREEMPT_BITS 8
#define SOFTIRQ_BITS 8
#define HARDIRQ_BITS 4
#define NMI_BITS 4
#define PREEMPT_SHIFT 0
#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
#define __IRQ_MASK(x) ((1UL << (x))-1)
#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
#define NMI_OFFSET (1UL << NMI_SHIFT)
#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
/*
* Disable preemption until the scheduler is running -- use an unconditional
* value so that it also works on !PREEMPT_COUNT kernels.
*
* Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
*/
#define INIT_PREEMPT_COUNT PREEMPT_OFFSET
/*
* Initial preempt_count value; reflects the preempt_count schedule invariant
* which states that during context switches:
*
* preempt_count() == 2*PREEMPT_DISABLE_OFFSET
*
* Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
* Note: See finish_task_switch().
*/
#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
#include <asm/preempt.h>
/**
* interrupt_context_level - return interrupt context level
*
* Returns the current interrupt context level.
* 0 - normal context
* 1 - softirq context
* 2 - hardirq context
* 3 - NMI context
*/
static __always_inline unsigned char interrupt_context_level(void)
{
unsigned long pc = preempt_count();
unsigned char level = 0;
level += !!(pc & (NMI_MASK));
level += !!(pc & (NMI_MASK | HARDIRQ_MASK));
level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
return level;
}
/*
* These macro definitions avoid redundant invocations of preempt_count()
* because such invocations would result in redundant loads given that
* preempt_count() is commonly implemented with READ_ONCE().
*/
#define nmi_count() (preempt_count() & NMI_MASK)
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
#ifdef CONFIG_PREEMPT_RT
# define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK)
# define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count())
#else
# define softirq_count() (preempt_count() & SOFTIRQ_MASK)
# define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK))
#endif
/*
* Macros to retrieve the current execution context:
*
* in_nmi() - We're in NMI context
* in_hardirq() - We're in hard IRQ context
* in_serving_softirq() - We're in softirq context
* in_task() - We're in task context
*/
#define in_nmi() (nmi_count())
#define in_hardirq() (hardirq_count())
#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
#ifdef CONFIG_PREEMPT_RT
# define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq()))
#else
# define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
#endif
/*
* The following macros are deprecated and should not be used in new code:
* in_irq() - Obsolete version of in_hardirq()
* in_softirq() - We have BH disabled, or are processing softirqs
* in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled
*/
#define in_irq() (hardirq_count())
#define in_softirq() (softirq_count())
#define in_interrupt() (irq_count())
/*
* The preempt_count offset after preempt_disable();
*/
#if defined(CONFIG_PREEMPT_COUNT)
# define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET
#else
# define PREEMPT_DISABLE_OFFSET 0
#endif
/*
* The preempt_count offset after spin_lock()
*/
#if !defined(CONFIG_PREEMPT_RT)
#define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET
#else
/* Locks on RT do not disable preemption */
#define PREEMPT_LOCK_OFFSET 0
#endif
/*
* The preempt_count offset needed for things like:
*
* spin_lock_bh()
*
* Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
* softirqs, such that unlock sequences of:
*
* spin_unlock();
* local_bh_enable();
*
* Work as expected.
*/
#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
/*
* Are we running in atomic context? WARNING: this macro cannot
* always detect atomic context; in particular, it cannot know about
* held spinlocks in non-preemptible kernels. Thus it should not be
* used in the general case to determine whether sleeping is possible.
* Do not use in_atomic() in driver code.
*/
#define in_atomic() (preempt_count() != 0)
/*
* Check whether we were atomic before we did preempt_disable():
* (used by the scheduler)
*/
#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE)
extern void preempt_count_add(int val);
extern void preempt_count_sub(int val);
#define preempt_count_dec_and_test() \
({ preempt_count_sub(1); should_resched(0); })
#else
#define preempt_count_add(val) __preempt_count_add(val)
#define preempt_count_sub(val) __preempt_count_sub(val)
#define preempt_count_dec_and_test() __preempt_count_dec_and_test()
#endif
#define __preempt_count_inc() __preempt_count_add(1)
#define __preempt_count_dec() __preempt_count_sub(1)
#define preempt_count_inc() preempt_count_add(1)
#define preempt_count_dec() preempt_count_sub(1)
#ifdef CONFIG_PREEMPT_COUNT
#define preempt_disable() \
do { \
preempt_count_inc(); \
barrier(); \
} while (0)
#define sched_preempt_enable_no_resched() \
do { \
barrier(); \
preempt_count_dec(); \
} while (0)
#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
#define preemptible() (preempt_count() == 0 && !irqs_disabled())
#ifdef CONFIG_PREEMPTION
#define preempt_enable() \
do { \
barrier(); \
if (unlikely(preempt_count_dec_and_test())) \
__preempt_schedule(); \
} while (0)
#define preempt_enable_notrace() \
do { \
barrier(); \
if (unlikely(__preempt_count_dec_and_test())) \
__preempt_schedule_notrace(); \
} while (0)
#define preempt_check_resched() \
do { \
if (should_resched(0)) \
__preempt_schedule(); \
} while (0)
#else /* !CONFIG_PREEMPTION */
#define preempt_enable() \
do { \
barrier(); \
preempt_count_dec(); \
} while (0)
#define preempt_enable_notrace() \
do { \
barrier(); \
__preempt_count_dec(); \
} while (0)
#define preempt_check_resched() do { } while (0)
#endif /* CONFIG_PREEMPTION */
#define preempt_disable_notrace() \
do { \
__preempt_count_inc(); \
barrier(); \
} while (0)
#define preempt_enable_no_resched_notrace() \
do { \
barrier(); \
__preempt_count_dec(); \
} while (0)
#else /* !CONFIG_PREEMPT_COUNT */
/*
* Even if we don't have any preemption, we need preempt disable/enable
* to be barriers, so that we don't have things like get_user/put_user
* that can cause faults and scheduling migrate into our preempt-protected
* region.
*/
#define preempt_disable() barrier()
#define sched_preempt_enable_no_resched() barrier()
#define preempt_enable_no_resched() barrier()
#define preempt_enable() barrier()
#define preempt_check_resched() do { } while (0)
#define preempt_disable_notrace() barrier()
#define preempt_enable_no_resched_notrace() barrier()
#define preempt_enable_notrace() barrier()
#define preemptible() 0
#endif /* CONFIG_PREEMPT_COUNT */
#ifdef MODULE
/*
* Modules have no business playing preemption tricks.
*/
#undef sched_preempt_enable_no_resched
#undef preempt_enable_no_resched
#undef preempt_enable_no_resched_notrace
#undef preempt_check_resched
#endif
#define preempt_set_need_resched() \
do { \
set_preempt_need_resched(); \
} while (0)
#define preempt_fold_need_resched() \
do { \
if (tif_need_resched()) \
set_preempt_need_resched(); \
} while (0)
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier;
struct task_struct;
/**
* preempt_ops - notifiers called when a task is preempted and rescheduled
* @sched_in: we're about to be rescheduled:
* notifier: struct preempt_notifier for the task being scheduled
* cpu: cpu we're scheduled on
* @sched_out: we've just been preempted
* notifier: struct preempt_notifier for the task being preempted
* next: the task that's kicking us out
*
* Please note that sched_in and out are called under different
* contexts. sched_out is called with rq lock held and irq disabled
* while sched_in is called without rq lock and irq enabled. This
* difference is intentional and depended upon by its users.
*/
struct preempt_ops {
void (*sched_in)(struct preempt_notifier *notifier, int cpu);
void (*sched_out)(struct preempt_notifier *notifier,
struct task_struct *next);
};
/**
* preempt_notifier - key for installing preemption notifiers
* @link: internal use
* @ops: defines the notifier functions to be called
*
* Usually used in conjunction with container_of().
*/
struct preempt_notifier {
struct hlist_node link;
struct preempt_ops *ops;
};
void preempt_notifier_inc(void);
void preempt_notifier_dec(void);
void preempt_notifier_register(struct preempt_notifier *notifier);
void preempt_notifier_unregister(struct preempt_notifier *notifier);
static inline void preempt_notifier_init(struct preempt_notifier *notifier,
struct preempt_ops *ops)
{
/* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */
notifier->link.next = NULL;
notifier->link.pprev = NULL;
notifier->ops = ops;
}
#endif
#ifdef CONFIG_SMP
/*
* Migrate-Disable and why it is undesired.
*
* When a preempted task becomes elegible to run under the ideal model (IOW it
* becomes one of the M highest priority tasks), it might still have to wait
* for the preemptee's migrate_disable() section to complete. Thereby suffering
* a reduction in bandwidth in the exact duration of the migrate_disable()
* section.
*
* Per this argument, the change from preempt_disable() to migrate_disable()
* gets us:
*
* - a higher priority tasks gains reduced wake-up latency; with preempt_disable()
* it would have had to wait for the lower priority task.
*
* - a lower priority tasks; which under preempt_disable() could've instantly
* migrated away when another CPU becomes available, is now constrained
* by the ability to push the higher priority task away, which might itself be
* in a migrate_disable() section, reducing it's available bandwidth.
*
* IOW it trades latency / moves the interference term, but it stays in the
* system, and as long as it remains unbounded, the system is not fully
* deterministic.
*
*
* The reason we have it anyway.
*
* PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a
* number of primitives into becoming preemptible, they would also allow
* migration. This turns out to break a bunch of per-cpu usage. To this end,
* all these primitives employ migirate_disable() to restore this implicit
* assumption.
*
* This is a 'temporary' work-around at best. The correct solution is getting
* rid of the above assumptions and reworking the code to employ explicit
* per-cpu locking or short preempt-disable regions.
*
* The end goal must be to get rid of migrate_disable(), alternatively we need
* a schedulability theory that does not depend on abritrary migration.
*
*
* Notes on the implementation.
*
* The implementation is particularly tricky since existing code patterns
* dictate neither migrate_disable() nor migrate_enable() is allowed to block.
* This means that it cannot use cpus_read_lock() to serialize against hotplug,
* nor can it easily migrate itself into a pending affinity mask change on
* migrate_enable().
*
*
* Note: even non-work-conserving schedulers like semi-partitioned depends on
* migration, so migrate_disable() is not only a problem for
* work-conserving schedulers.
*
*/
extern void migrate_disable(void);
extern void migrate_enable(void);
#else
static inline void migrate_disable(void) { }
static inline void migrate_enable(void) { }
#endif /* CONFIG_SMP */
/**
* preempt_disable_nested - Disable preemption inside a normally preempt disabled section
*
* Use for code which requires preemption protection inside a critical
* section which has preemption disabled implicitly on non-PREEMPT_RT
* enabled kernels, by e.g.:
* - holding a spinlock/rwlock
* - soft interrupt context
* - regular interrupt handlers
*
* On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft
* interrupt context and regular interrupt handlers are preemptible and
* only prevent migration. preempt_disable_nested() ensures that preemption
* is disabled for cases which require CPU local serialization even on
* PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP.
*
* The use cases are code sequences which are not serialized by a
* particular lock instance, e.g.:
* - seqcount write side critical sections where the seqcount is not
* associated to a particular lock and therefore the automatic
* protection mechanism does not work. This prevents a live lock
* against a preempting high priority reader.
* - RMW per CPU variable updates like vmstat.
*/
/* Macro to avoid header recursion hell vs. lockdep */
#define preempt_disable_nested() \
do { \
if (IS_ENABLED(CONFIG_PREEMPT_RT)) \
preempt_disable(); \
else \
lockdep_assert_preemption_disabled(); \
} while (0)
/**
* preempt_enable_nested - Undo the effect of preempt_disable_nested()
*/
static __always_inline void preempt_enable_nested(void)
{
if (IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
}
DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable())DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace())
DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
#ifdef CONFIG_PREEMPT_DYNAMIC
extern bool preempt_model_none(void);
extern bool preempt_model_voluntary(void);
extern bool preempt_model_full(void);
extern bool preempt_model_lazy(void);
#else
static inline bool preempt_model_none(void)
{
return IS_ENABLED(CONFIG_PREEMPT_NONE);
}
static inline bool preempt_model_voluntary(void)
{
return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
}
static inline bool preempt_model_full(void)
{
return IS_ENABLED(CONFIG_PREEMPT);
}
static inline bool preempt_model_lazy(void)
{
return IS_ENABLED(CONFIG_PREEMPT_LAZY);
}
#endif
static inline bool preempt_model_rt(void)
{
return IS_ENABLED(CONFIG_PREEMPT_RT);
}
extern const char *preempt_model_str(void);
/*
* Does the preemption model allow non-cooperative preemption?
*
* For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
* CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
* kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
* PREEMPT_NONE model.
*/
static inline bool preempt_model_preemptible(void)
{
return preempt_model_full() || preempt_model_lazy() || preempt_model_rt();
}
#endif /* __LINUX_PREEMPT_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RCULIST_H
#define _LINUX_RCULIST_H
#ifdef __KERNEL__
/*
* RCU-protected list version
*/
#include <linux/list.h>
#include <linux/rcupdate.h>
/*
* INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers
* @list: list to be initialized
*
* You should instead use INIT_LIST_HEAD() for normal initialization and
* cleanup tasks, when readers have no access to the list being initialized.
* However, if the list being initialized is visible to readers, you
* need to keep the compiler from being too mischievous.
*/
static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
{
WRITE_ONCE(list->next, list);
WRITE_ONCE(list->prev, list);
}
/*
* return the ->next pointer of a list_head in an rcu safe
* way, we must not access it directly
*/
#define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next)))
/*
* Return the ->prev pointer of a list_head in an rcu safe way. Don't
* access it directly.
*
* Any list traversed with list_bidir_prev_rcu() must never use
* list_del_rcu(). Doing so will poison the ->prev pointer that
* list_bidir_prev_rcu() relies on, which will result in segfaults.
* To prevent these segfaults, use list_bidir_del_rcu() instead
* of list_del_rcu().
*/
#define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev)))
/**
* list_tail_rcu - returns the prev pointer of the head of the list
* @head: the head of the list
*
* Note: This should only be used with the list header, and even then
* only if list_del() and similar primitives are not also used on the
* list header.
*/
#define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev)))
/*
* Check during list traversal that we are within an RCU reader
*/
#define check_arg_count_one(dummy)
#ifdef CONFIG_PROVE_RCU_LIST
#define __list_check_rcu(dummy, cond, extra...) \
({ \
check_arg_count_one(extra); \
RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \
"RCU-list traversed in non-reader section!"); \
})
#define __list_check_srcu(cond) \
({ \
RCU_LOCKDEP_WARN(!(cond), \
"RCU-list traversed without holding the required lock!");\
})
#else
#define __list_check_rcu(dummy, cond, extra...) \
({ check_arg_count_one(extra); })
#define __list_check_srcu(cond) ({ })
#endif
/*
* Insert a new entry between two known consecutive entries.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
static inline void __list_add_rcu(struct list_head *new,
struct list_head *prev, struct list_head *next)
{
if (!__list_add_valid(new, prev, next))
return;
new->next = next;
new->prev = prev;
rcu_assign_pointer(list_next_rcu(prev), new);
next->prev = new;
}
/**
* list_add_rcu - add a new entry to rcu-protected list
* @new: new entry to be added
* @head: list head to add it after
*
* Insert a new entry after the specified head.
* This is good for implementing stacks.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as list_add_rcu()
* or list_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* list_for_each_entry_rcu().
*/
static inline void list_add_rcu(struct list_head *new, struct list_head *head)
{ __list_add_rcu(new, head, head->next);
}
/**
* list_add_tail_rcu - add a new entry to rcu-protected list
* @new: new entry to be added
* @head: list head to add it before
*
* Insert a new entry before the specified head.
* This is useful for implementing queues.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as list_add_tail_rcu()
* or list_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* list_for_each_entry_rcu().
*/
static inline void list_add_tail_rcu(struct list_head *new,
struct list_head *head)
{
__list_add_rcu(new, head->prev, head);
}
/**
* list_del_rcu - deletes entry from list without re-initialization
* @entry: the element to delete from the list.
*
* Note: list_empty() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as list_del_rcu()
* or list_add_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* list_for_each_entry_rcu().
*
* Note that the caller is not permitted to immediately free
* the newly deleted entry. Instead, either synchronize_rcu()
* or call_rcu() must be used to defer freeing until an RCU
* grace period has elapsed.
*/
static inline void list_del_rcu(struct list_head *entry)
{
__list_del_entry(entry);
entry->prev = LIST_POISON2;
}
/**
* list_bidir_del_rcu - deletes entry from list without re-initialization
* @entry: the element to delete from the list.
*
* In contrast to list_del_rcu() doesn't poison the prev pointer thus
* allowing backwards traversal via list_bidir_prev_rcu().
*
* Note: list_empty() on entry does not return true after this because
* the entry is in a special undefined state that permits RCU-based
* lockfree reverse traversal. In particular this means that we can not
* poison the forward and backwards pointers that may still be used for
* walking the list.
*
* The caller must take whatever precautions are necessary (such as
* holding appropriate locks) to avoid racing with another list-mutation
* primitive, such as list_bidir_del_rcu() or list_add_rcu(), running on
* this same list. However, it is perfectly legal to run concurrently
* with the _rcu list-traversal primitives, such as
* list_for_each_entry_rcu().
*
* Note that list_del_rcu() and list_bidir_del_rcu() must not be used on
* the same list.
*
* Note that the caller is not permitted to immediately free
* the newly deleted entry. Instead, either synchronize_rcu()
* or call_rcu() must be used to defer freeing until an RCU
* grace period has elapsed.
*/
static inline void list_bidir_del_rcu(struct list_head *entry)
{
__list_del_entry(entry);
}
/**
* hlist_del_init_rcu - deletes entry from hash list with re-initialization
* @n: the element to delete from the hash list.
*
* Note: list_unhashed() on the node return true after this. It is
* useful for RCU based read lockfree traversal if the writer side
* must know if the list entry is still hashed or already unhashed.
*
* In particular, it means that we can not poison the forward pointers
* that may still be used for walking the hash list and we can only
* zero the pprev pointer so list_unhashed() will return true after
* this.
*
* The caller must take whatever precautions are necessary (such as
* holding appropriate locks) to avoid racing with another
* list-mutation primitive, such as hlist_add_head_rcu() or
* hlist_del_rcu(), running on this same list. However, it is
* perfectly legal to run concurrently with the _rcu list-traversal
* primitives, such as hlist_for_each_entry_rcu().
*/
static inline void hlist_del_init_rcu(struct hlist_node *n)
{
if (!hlist_unhashed(n)) { __hlist_del(n);
WRITE_ONCE(n->pprev, NULL);
}
}
/**
* list_replace_rcu - replace old entry by new one
* @old : the element to be replaced
* @new : the new element to insert
*
* The @old entry will be replaced with the @new entry atomically from
* the perspective of concurrent readers. It is the caller's responsibility
* to synchronize with concurrent updaters, if any.
*
* Note: @old should not be empty.
*/
static inline void list_replace_rcu(struct list_head *old,
struct list_head *new)
{
new->next = old->next;
new->prev = old->prev;
rcu_assign_pointer(list_next_rcu(new->prev), new);
new->next->prev = new;
old->prev = LIST_POISON2;
}
/**
* __list_splice_init_rcu - join an RCU-protected list into an existing list.
* @list: the RCU-protected list to splice
* @prev: points to the last element of the existing list
* @next: points to the first element of the existing list
* @sync: synchronize_rcu, synchronize_rcu_expedited, ...
*
* The list pointed to by @prev and @next can be RCU-read traversed
* concurrently with this function.
*
* Note that this function blocks.
*
* Important note: the caller must take whatever action is necessary to prevent
* any other updates to the existing list. In principle, it is possible to
* modify the list as soon as sync() begins execution. If this sort of thing
* becomes necessary, an alternative version based on call_rcu() could be
* created. But only if -really- needed -- there is no shortage of RCU API
* members.
*/
static inline void __list_splice_init_rcu(struct list_head *list,
struct list_head *prev,
struct list_head *next,
void (*sync)(void))
{
struct list_head *first = list->next;
struct list_head *last = list->prev;
/*
* "first" and "last" tracking list, so initialize it. RCU readers
* have access to this list, so we must use INIT_LIST_HEAD_RCU()
* instead of INIT_LIST_HEAD().
*/
INIT_LIST_HEAD_RCU(list);
/*
* At this point, the list body still points to the source list.
* Wait for any readers to finish using the list before splicing
* the list body into the new list. Any new readers will see
* an empty list.
*/
sync();
ASSERT_EXCLUSIVE_ACCESS(*first);
ASSERT_EXCLUSIVE_ACCESS(*last);
/*
* Readers are finished with the source list, so perform splice.
* The order is important if the new list is global and accessible
* to concurrent RCU readers. Note that RCU readers are not
* permitted to traverse the prev pointers without excluding
* this function.
*/
last->next = next;
rcu_assign_pointer(list_next_rcu(prev), first);
first->prev = prev;
next->prev = last;
}
/**
* list_splice_init_rcu - splice an RCU-protected list into an existing list,
* designed for stacks.
* @list: the RCU-protected list to splice
* @head: the place in the existing list to splice the first list into
* @sync: synchronize_rcu, synchronize_rcu_expedited, ...
*/
static inline void list_splice_init_rcu(struct list_head *list,
struct list_head *head,
void (*sync)(void))
{
if (!list_empty(list))
__list_splice_init_rcu(list, head, head->next, sync);
}
/**
* list_splice_tail_init_rcu - splice an RCU-protected list into an existing
* list, designed for queues.
* @list: the RCU-protected list to splice
* @head: the place in the existing list to splice the first list into
* @sync: synchronize_rcu, synchronize_rcu_expedited, ...
*/
static inline void list_splice_tail_init_rcu(struct list_head *list,
struct list_head *head,
void (*sync)(void))
{
if (!list_empty(list))
__list_splice_init_rcu(list, head->prev, head, sync);
}
/**
* list_entry_rcu - get the struct for this entry
* @ptr: the &struct list_head pointer.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* This primitive may safely run concurrently with the _rcu list-mutation
* primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
*/
#define list_entry_rcu(ptr, type, member) \
container_of(READ_ONCE(ptr), type, member)
/*
* Where are list_empty_rcu() and list_first_entry_rcu()?
*
* They do not exist because they would lead to subtle race conditions:
*
* if (!list_empty_rcu(mylist)) {
* struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member);
* do_something(bar);
* }
*
* The list might be non-empty when list_empty_rcu() checks it, but it
* might have become empty by the time that list_first_entry_rcu() rereads
* the ->next pointer, which would result in a SEGV.
*
* When not using RCU, it is OK for list_first_entry() to re-read that
* pointer because both functions should be protected by some lock that
* blocks writers.
*
* When using RCU, list_empty() uses READ_ONCE() to fetch the
* RCU-protected ->next pointer and then compares it to the address of the
* list head. However, it neither dereferences this pointer nor provides
* this pointer to its caller. Thus, READ_ONCE() suffices (that is,
* rcu_dereference() is not needed), which means that list_empty() can be
* used anywhere you would want to use list_empty_rcu(). Just don't
* expect anything useful to happen if you do a subsequent lockless
* call to list_first_entry_rcu()!!!
*
* See list_first_or_null_rcu for an alternative.
*/
/**
* list_first_or_null_rcu - get the first element from a list
* @ptr: the list head to take the element from.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* Note that if the list is empty, it returns NULL.
*
* This primitive may safely run concurrently with the _rcu list-mutation
* primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
*/
#define list_first_or_null_rcu(ptr, type, member) \
({ \
struct list_head *__ptr = (ptr); \
struct list_head *__next = READ_ONCE(__ptr->next); \
likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \
})
/**
* list_next_or_null_rcu - get the next element from a list
* @head: the head for the list.
* @ptr: the list head to take the next element from.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* Note that if the ptr is at the end of the list, NULL is returned.
*
* This primitive may safely run concurrently with the _rcu list-mutation
* primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
*/
#define list_next_or_null_rcu(head, ptr, type, member) \
({ \
struct list_head *__head = (head); \
struct list_head *__ptr = (ptr); \
struct list_head *__next = READ_ONCE(__ptr->next); \
likely(__next != __head) ? list_entry_rcu(__next, type, \
member) : NULL; \
})
/**
* list_for_each_entry_rcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
* @cond: optional lockdep expression if called from non-RCU protection.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as list_add_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
#define list_for_each_entry_rcu(pos, head, member, cond...) \
for (__list_check_rcu(dummy, ## cond, 0), \
pos = list_entry_rcu((head)->next, typeof(*pos), member); \
&pos->member != (head); \
pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
/**
* list_for_each_entry_srcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
* @cond: lockdep expression for the lock required to traverse the list.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as list_add_rcu()
* as long as the traversal is guarded by srcu_read_lock().
* The lockdep expression srcu_read_lock_held() can be passed as the
* cond argument from read side.
*/
#define list_for_each_entry_srcu(pos, head, member, cond) \
for (__list_check_srcu(cond), \
pos = list_entry_rcu((head)->next, typeof(*pos), member); \
&pos->member != (head); \
pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
/**
* list_entry_lockless - get the struct for this entry
* @ptr: the &struct list_head pointer.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* This primitive may safely run concurrently with the _rcu
* list-mutation primitives such as list_add_rcu(), but requires some
* implicit RCU read-side guarding. One example is running within a special
* exception-time environment where preemption is disabled and where lockdep
* cannot be invoked. Another example is when items are added to the list,
* but never deleted.
*/
#define list_entry_lockless(ptr, type, member) \
container_of((typeof(ptr))READ_ONCE(ptr), type, member)
/**
* list_for_each_entry_lockless - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_struct within the struct.
*
* This primitive may safely run concurrently with the _rcu
* list-mutation primitives such as list_add_rcu(), but requires some
* implicit RCU read-side guarding. One example is running within a special
* exception-time environment where preemption is disabled and where lockdep
* cannot be invoked. Another example is when items are added to the list,
* but never deleted.
*/
#define list_for_each_entry_lockless(pos, head, member) \
for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \
&pos->member != (head); \
pos = list_entry_lockless(pos->member.next, typeof(*pos), member))
/**
* list_for_each_entry_continue_rcu - continue iteration over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Continue to iterate over list of given type, continuing after
* the current position which must have been in the list when the RCU read
* lock was taken.
* This would typically require either that you obtained the node from a
* previous walk of the list in the same RCU read-side critical section, or
* that you held some sort of non-RCU reference (such as a reference count)
* to keep the node alive *and* in the list.
*
* This iterator is similar to list_for_each_entry_from_rcu() except
* this starts after the given position and that one starts at the given
* position.
*/
#define list_for_each_entry_continue_rcu(pos, head, member) \
for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
&pos->member != (head); \
pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
/**
* list_for_each_entry_from_rcu - iterate over a list from current point
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_node within the struct.
*
* Iterate over the tail of a list starting from a given position,
* which must have been in the list when the RCU read lock was taken.
* This would typically require either that you obtained the node from a
* previous walk of the list in the same RCU read-side critical section, or
* that you held some sort of non-RCU reference (such as a reference count)
* to keep the node alive *and* in the list.
*
* This iterator is similar to list_for_each_entry_continue_rcu() except
* this starts from the given position and that one starts from the position
* after the given position.
*/
#define list_for_each_entry_from_rcu(pos, head, member) \
for (; &(pos)->member != (head); \
pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member))
/**
* hlist_del_rcu - deletes entry from hash list without re-initialization
* @n: the element to delete from the hash list.
*
* Note: list_unhashed() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the hash list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_add_head_rcu()
* or hlist_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_for_each_entry().
*/
static inline void hlist_del_rcu(struct hlist_node *n)
{
__hlist_del(n);
WRITE_ONCE(n->pprev, LIST_POISON2);
}
/**
* hlist_replace_rcu - replace old entry by new one
* @old : the element to be replaced
* @new : the new element to insert
*
* The @old entry will be replaced with the @new entry atomically from
* the perspective of concurrent readers. It is the caller's responsibility
* to synchronize with concurrent updaters, if any.
*/
static inline void hlist_replace_rcu(struct hlist_node *old,
struct hlist_node *new)
{
struct hlist_node *next = old->next;
new->next = next;
WRITE_ONCE(new->pprev, old->pprev);
rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new);
if (next) WRITE_ONCE(new->next->pprev, &new->next);
WRITE_ONCE(old->pprev, LIST_POISON2);
}
/**
* hlists_swap_heads_rcu - swap the lists the hlist heads point to
* @left: The hlist head on the left
* @right: The hlist head on the right
*
* The lists start out as [@left ][node1 ... ] and
* [@right ][node2 ... ]
* The lists end up as [@left ][node2 ... ]
* [@right ][node1 ... ]
*/
static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right)
{
struct hlist_node *node1 = left->first;
struct hlist_node *node2 = right->first;
rcu_assign_pointer(left->first, node2);
rcu_assign_pointer(right->first, node1);
WRITE_ONCE(node2->pprev, &left->first);
WRITE_ONCE(node1->pprev, &right->first);
}
/*
* return the first or the next element in an RCU protected hlist
*/
#define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first)))
#define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next)))
#define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev)))
/**
* hlist_add_head_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_add_head_rcu()
* or hlist_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_add_head_rcu(struct hlist_node *n,
struct hlist_head *h)
{
struct hlist_node *first = h->first;
n->next = first;
WRITE_ONCE(n->pprev, &h->first);
rcu_assign_pointer(hlist_first_rcu(h), n);
if (first) WRITE_ONCE(first->pprev, &n->next);
}
/**
* hlist_add_tail_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_add_head_rcu()
* or hlist_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_add_tail_rcu(struct hlist_node *n,
struct hlist_head *h)
{
struct hlist_node *i, *last = NULL;
/* Note: write side code, so rcu accessors are not needed. */
for (i = h->first; i; i = i->next)
last = i;
if (last) {
n->next = last->next;
WRITE_ONCE(n->pprev, &last->next);
rcu_assign_pointer(hlist_next_rcu(last), n);
} else {
hlist_add_head_rcu(n, h);
}
}
/**
* hlist_add_before_rcu
* @n: the new element to add to the hash list.
* @next: the existing element to add the new element before.
*
* Description:
* Adds the specified element to the specified hlist
* before the specified node while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_add_head_rcu()
* or hlist_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs.
*/
static inline void hlist_add_before_rcu(struct hlist_node *n,
struct hlist_node *next)
{
WRITE_ONCE(n->pprev, next->pprev);
n->next = next;
rcu_assign_pointer(hlist_pprev_rcu(n), n);
WRITE_ONCE(next->pprev, &n->next);
}
/**
* hlist_add_behind_rcu
* @n: the new element to add to the hash list.
* @prev: the existing element to add the new element after.
*
* Description:
* Adds the specified element to the specified hlist
* after the specified node while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_add_head_rcu()
* or hlist_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs.
*/
static inline void hlist_add_behind_rcu(struct hlist_node *n,
struct hlist_node *prev)
{
n->next = prev->next;
WRITE_ONCE(n->pprev, &prev->next);
rcu_assign_pointer(hlist_next_rcu(prev), n);
if (n->next)
WRITE_ONCE(n->next->pprev, &n->next);
}
#define __hlist_for_each_rcu(pos, head) \
for (pos = rcu_dereference(hlist_first_rcu(head)); \
pos; \
pos = rcu_dereference(hlist_next_rcu(pos)))
/**
* hlist_for_each_entry_rcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
* @cond: optional lockdep expression if called from non-RCU protection.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
#define hlist_for_each_entry_rcu(pos, head, member, cond...) \
for (__list_check_rcu(dummy, ## cond, 0), \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_srcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
* @cond: lockdep expression for the lock required to traverse the list.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by srcu_read_lock().
* The lockdep expression srcu_read_lock_held() can be passed as the
* cond argument from read side.
*/
#define hlist_for_each_entry_srcu(pos, head, member, cond) \
for (__list_check_srcu(cond), \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing)
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*
* This is the same as hlist_for_each_entry_rcu() except that it does
* not do any RCU debugging or tracing.
*/
#define hlist_for_each_entry_rcu_notrace(pos, head, member) \
for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\
typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_rcu_bh - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
#define hlist_for_each_entry_rcu_bh(pos, head, member) \
for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\
typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point
* @pos: the type * to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_continue_rcu(pos, member) \
for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
&(pos)->member)), typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point
* @pos: the type * to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_continue_rcu_bh(pos, member) \
for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \
&(pos)->member)), typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \
&(pos)->member)), typeof(*(pos)), member))
/**
* hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point
* @pos: the type * to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_from_rcu(pos, member) \
for (; pos; \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
&(pos)->member)), typeof(*(pos)), member))
#endif /* __KERNEL__ */
#endif
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* include/net/dsa.h - Driver for Distributed Switch Architecture switch chips
* Copyright (c) 2008-2009 Marvell Semiconductor
*/
#ifndef __LINUX_NET_DSA_H
#define __LINUX_NET_DSA_H
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/of.h>
#include <linux/ethtool.h>
#include <linux/net_tstamp.h>
#include <linux/phy.h>
#include <linux/platform_data/dsa.h>
#include <linux/phylink.h>
#include <net/devlink.h>
#include <net/switchdev.h>
struct dsa_8021q_context;
struct tc_action;
#define DSA_TAG_PROTO_NONE_VALUE 0
#define DSA_TAG_PROTO_BRCM_VALUE 1
#define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2
#define DSA_TAG_PROTO_DSA_VALUE 3
#define DSA_TAG_PROTO_EDSA_VALUE 4
#define DSA_TAG_PROTO_GSWIP_VALUE 5
#define DSA_TAG_PROTO_KSZ9477_VALUE 6
#define DSA_TAG_PROTO_KSZ9893_VALUE 7
#define DSA_TAG_PROTO_LAN9303_VALUE 8
#define DSA_TAG_PROTO_MTK_VALUE 9
#define DSA_TAG_PROTO_QCA_VALUE 10
#define DSA_TAG_PROTO_TRAILER_VALUE 11
#define DSA_TAG_PROTO_8021Q_VALUE 12
#define DSA_TAG_PROTO_SJA1105_VALUE 13
#define DSA_TAG_PROTO_KSZ8795_VALUE 14
#define DSA_TAG_PROTO_OCELOT_VALUE 15
#define DSA_TAG_PROTO_AR9331_VALUE 16
#define DSA_TAG_PROTO_RTL4_A_VALUE 17
#define DSA_TAG_PROTO_HELLCREEK_VALUE 18
#define DSA_TAG_PROTO_XRS700X_VALUE 19
#define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20
#define DSA_TAG_PROTO_SEVILLE_VALUE 21
#define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22
#define DSA_TAG_PROTO_SJA1110_VALUE 23
#define DSA_TAG_PROTO_RTL8_4_VALUE 24
#define DSA_TAG_PROTO_RTL8_4T_VALUE 25
#define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26
#define DSA_TAG_PROTO_LAN937X_VALUE 27
#define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE,
DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE,
DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE,
DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE,
DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE,
DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE,
DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE,
DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE,
DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE,
DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE,
DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE,
DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE,
DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE,
DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE,
DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE,
DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE,
DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE,
DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE,
DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE,
DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE,
DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE,
DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE,
DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE,
DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE,
DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE,
DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE,
DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE,
DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE,
DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE,
};
struct dsa_switch;
struct dsa_device_ops {
struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev);
void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
int *offset);
int (*connect)(struct dsa_switch *ds);
void (*disconnect)(struct dsa_switch *ds);
unsigned int needed_headroom;
unsigned int needed_tailroom;
const char *name;
enum dsa_tag_protocol proto;
/* Some tagging protocols either mangle or shift the destination MAC
* address, in which case the DSA conduit would drop packets on ingress
* if what it understands out of the destination MAC address is not in
* its RX filter.
*/
bool promisc_on_conduit;
};
struct dsa_lag {
struct net_device *dev;
unsigned int id;
struct mutex fdb_lock;
struct list_head fdbs;
refcount_t refcount;
};
struct dsa_switch_tree {
struct list_head list;
/* List of switch ports */
struct list_head ports;
/* Notifier chain for switch-wide events */
struct raw_notifier_head nh;
/* Tree identifier */
unsigned int index;
/* Number of switches attached to this tree */
struct kref refcount;
/* Maps offloaded LAG netdevs to a zero-based linear ID for
* drivers that need it.
*/
struct dsa_lag **lags;
/* Tagging protocol operations */
const struct dsa_device_ops *tag_ops;
/* Default tagging protocol preferred by the switches in this
* tree.
*/
enum dsa_tag_protocol default_proto;
/* Has this tree been applied to the hardware? */
bool setup;
/*
* Configuration data for the platform device that owns
* this dsa switch tree instance.
*/
struct dsa_platform_data *pd;
/* List of DSA links composing the routing table */
struct list_head rtable;
/* Length of "lags" array */
unsigned int lags_len;
/* Track the largest switch index within a tree */
unsigned int last_switch;
};
/* LAG IDs are one-based, the dst->lags array is zero-based */
#define dsa_lags_foreach_id(_id, _dst) \
for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \
if ((_dst)->lags[(_id) - 1])
#define dsa_lag_foreach_port(_dp, _dst, _lag) \
list_for_each_entry((_dp), &(_dst)->ports, list) \
if (dsa_port_offloads_lag((_dp), (_lag)))
#define dsa_hsr_foreach_port(_dp, _ds, _hsr) \
list_for_each_entry((_dp), &(_ds)->dst->ports, list) \
if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr))
static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst,
unsigned int id)
{
/* DSA LAG IDs are one-based, dst->lags is zero-based */
return dst->lags[id - 1];
}
static inline int dsa_lag_id(struct dsa_switch_tree *dst,
struct net_device *lag_dev)
{
unsigned int id;
dsa_lags_foreach_id(id, dst) {
struct dsa_lag *lag = dsa_lag_by_id(dst, id);
if (lag->dev == lag_dev)
return lag->id;
}
return -ENODEV;
}
/* TC matchall action types */
enum dsa_port_mall_action_type {
DSA_PORT_MALL_MIRROR,
DSA_PORT_MALL_POLICER,
};
/* TC mirroring entry */
struct dsa_mall_mirror_tc_entry {
u8 to_local_port;
bool ingress;
};
/* TC port policer entry */
struct dsa_mall_policer_tc_entry {
u32 burst;
u64 rate_bytes_per_sec;
};
/* TC matchall entry */
struct dsa_mall_tc_entry {
struct list_head list;
unsigned long cookie;
enum dsa_port_mall_action_type type;
union {
struct dsa_mall_mirror_tc_entry mirror;
struct dsa_mall_policer_tc_entry policer;
};
};
struct dsa_bridge {
struct net_device *dev;
unsigned int num;
bool tx_fwd_offload;
refcount_t refcount;
};
struct dsa_port {
/* A CPU port is physically connected to a conduit device. A user port
* exposes a network device to user-space, called 'user' here.
*/
union {
struct net_device *conduit;
struct net_device *user;
};
/* Copy of the tagging protocol operations, for quicker access
* in the data path. Valid only for the CPU ports.
*/
const struct dsa_device_ops *tag_ops;
/* Copies for faster access in conduit receive hot path */
struct dsa_switch_tree *dst;
struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev);
struct dsa_switch *ds;
unsigned int index;
enum {
DSA_PORT_TYPE_UNUSED = 0,
DSA_PORT_TYPE_CPU,
DSA_PORT_TYPE_DSA,
DSA_PORT_TYPE_USER,
} type;
const char *name;
struct dsa_port *cpu_dp;
u8 mac[ETH_ALEN];
u8 stp_state;
/* Warning: the following bit fields are not atomic, and updating them
* can only be done from code paths where concurrency is not possible
* (probe time or under rtnl_lock).
*/
u8 vlan_filtering:1;
/* Managed by DSA on user ports and by drivers on CPU and DSA ports */
u8 learning:1;
u8 lag_tx_enabled:1;
/* conduit state bits, valid only on CPU ports */
u8 conduit_admin_up:1;
u8 conduit_oper_up:1;
/* Valid only on user ports */
u8 cpu_port_in_lag:1;
u8 setup:1;
struct device_node *dn;
unsigned int ageing_time;
struct dsa_bridge *bridge;
struct devlink_port devlink_port;
struct phylink *pl;
struct phylink_config pl_config;
struct dsa_lag *lag;
struct net_device *hsr_dev;
struct list_head list;
/*
* Original copy of the conduit netdev ethtool_ops
*/
const struct ethtool_ops *orig_ethtool_ops;
/* List of MAC addresses that must be forwarded on this port.
* These are only valid on CPU ports and DSA links.
*/
struct mutex addr_lists_lock;
struct list_head fdbs;
struct list_head mdbs;
struct mutex vlans_lock;
union {
/* List of VLANs that CPU and DSA ports are members of.
* Access to this is serialized by the sleepable @vlans_lock.
*/
struct list_head vlans;
/* List of VLANs that user ports are members of.
* Access to this is serialized by netif_addr_lock_bh().
*/
struct list_head user_vlans;
};
};
static inline struct dsa_port *
dsa_phylink_to_port(struct phylink_config *config)
{
return container_of(config, struct dsa_port, pl_config);
}
/* TODO: ideally DSA ports would have a single dp->link_dp member,
* and no dst->rtable nor this struct dsa_link would be needed,
* but this would require some more complex tree walking,
* so keep it stupid at the moment and list them all.
*/
struct dsa_link {
struct dsa_port *dp;
struct dsa_port *link_dp;
struct list_head list;
};
enum dsa_db_type {
DSA_DB_PORT,
DSA_DB_LAG,
DSA_DB_BRIDGE,
};
struct dsa_db {
enum dsa_db_type type;
union {
const struct dsa_port *dp;
struct dsa_lag lag;
struct dsa_bridge bridge;
};
};
struct dsa_mac_addr {
unsigned char addr[ETH_ALEN];
u16 vid;
refcount_t refcount;
struct list_head list;
struct dsa_db db;
};
struct dsa_vlan {
u16 vid;
refcount_t refcount;
struct list_head list;
};
struct dsa_switch {
struct device *dev;
/*
* Parent switch tree, and switch index.
*/
struct dsa_switch_tree *dst;
unsigned int index;
/* Warning: the following bit fields are not atomic, and updating them
* can only be done from code paths where concurrency is not possible
* (probe time or under rtnl_lock).
*/
u32 setup:1;
/* Disallow bridge core from requesting different VLAN awareness
* settings on ports if not hardware-supported
*/
u32 vlan_filtering_is_global:1;
/* Keep VLAN filtering enabled on ports not offloading any upper */
u32 needs_standalone_vlan_filtering:1;
/* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges
* that have vlan_filtering=0. All drivers should ideally set this (and
* then the option would get removed), but it is unknown whether this
* would break things or not.
*/
u32 configure_vlan_while_not_filtering:1;
/* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames.
* DEPRECATED: Do NOT set this field in new drivers. Instead look at
* the dsa_software_vlan_untag() comments.
*/
u32 untag_bridge_pvid:1;
/* Pop the default_pvid of VLAN-aware bridge ports from tagged frames.
* Useful if the switch cannot preserve the VLAN tag as seen on the
* wire for user port ingress, and chooses to send all frames as
* VLAN-tagged to the CPU, including those which were originally
* untagged.
*/
u32 untag_vlan_aware_bridge_pvid:1;
/* Let DSA manage the FDB entries towards the
* CPU, based on the software bridge database.
*/
u32 assisted_learning_on_cpu_port:1;
/* In case vlan_filtering_is_global is set, the VLAN awareness state
* should be retrieved from here and not from the per-port settings.
*/
u32 vlan_filtering:1;
/* For switches that only have the MRU configurable. To ensure the
* configured MTU is not exceeded, normalization of MRU on all bridged
* interfaces is needed.
*/
u32 mtu_enforcement_ingress:1;
/* Drivers that isolate the FDBs of multiple bridges must set this
* to true to receive the bridge as an argument in .port_fdb_{add,del}
* and .port_mdb_{add,del}. Otherwise, the bridge.num will always be
* passed as zero.
*/
u32 fdb_isolation:1;
/* Drivers that have global DSCP mapping settings must set this to
* true to automatically apply the settings to all ports.
*/
u32 dscp_prio_mapping_is_global:1;
/* Listener for switch fabric events */
struct notifier_block nb;
/*
* Give the switch driver somewhere to hang its private data
* structure.
*/
void *priv;
void *tagger_data;
/*
* Configuration data for this switch.
*/
struct dsa_chip_data *cd;
/*
* The switch operations.
*/
const struct dsa_switch_ops *ops;
/*
* Allow a DSA switch driver to override the phylink MAC ops
*/
const struct phylink_mac_ops *phylink_mac_ops;
/*
* User mii_bus and devices for the individual ports.
*/
u32 phys_mii_mask;
struct mii_bus *user_mii_bus;
/* Ageing Time limits in msecs */
unsigned int ageing_time_min;
unsigned int ageing_time_max;
/* Storage for drivers using tag_8021q */
struct dsa_8021q_context *tag_8021q_ctx;
/* devlink used to represent this switch device */
struct devlink *devlink;
/* Number of switch port queues */
unsigned int num_tx_queues;
/* Drivers that benefit from having an ID associated with each
* offloaded LAG should set this to the maximum number of
* supported IDs. DSA will then maintain a mapping of _at
* least_ these many IDs, accessible to drivers via
* dsa_lag_id().
*/
unsigned int num_lag_ids;
/* Drivers that support bridge forwarding offload or FDB isolation
* should set this to the maximum number of bridges spanning the same
* switch tree (or all trees, in the case of cross-tree bridging
* support) that can be offloaded.
*/
unsigned int max_num_bridges;
unsigned int num_ports;
};
static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
{
struct dsa_switch_tree *dst = ds->dst;
struct dsa_port *dp;
list_for_each_entry(dp, &dst->ports, list)
if (dp->ds == ds && dp->index == p)
return dp;
return NULL;
}
static inline bool dsa_port_is_dsa(struct dsa_port *port)
{
return port->type == DSA_PORT_TYPE_DSA;
}
static inline bool dsa_port_is_cpu(struct dsa_port *port)
{
return port->type == DSA_PORT_TYPE_CPU;
}
static inline bool dsa_port_is_user(struct dsa_port *dp)
{
return dp->type == DSA_PORT_TYPE_USER;
}
static inline bool dsa_port_is_unused(struct dsa_port *dp)
{
return dp->type == DSA_PORT_TYPE_UNUSED;
}
static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp)
{
return dsa_port_is_cpu(dp) && dp->conduit_admin_up &&
dp->conduit_oper_up;
}
static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
{
return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
}
static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
{
return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU;
}
static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
{
return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA;
}
static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
{
return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER;
}
#define dsa_tree_for_each_user_port(_dp, _dst) \
list_for_each_entry((_dp), &(_dst)->ports, list) \
if (dsa_port_is_user((_dp)))
#define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \
list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \
if (dsa_port_is_user((_dp)))
#define dsa_tree_for_each_cpu_port(_dp, _dst) \
list_for_each_entry((_dp), &(_dst)->ports, list) \
if (dsa_port_is_cpu((_dp)))
#define dsa_switch_for_each_port(_dp, _ds) \
list_for_each_entry((_dp), &(_ds)->dst->ports, list) \
if ((_dp)->ds == (_ds))
#define dsa_switch_for_each_port_safe(_dp, _next, _ds) \
list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \
if ((_dp)->ds == (_ds))
#define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \
list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \
if ((_dp)->ds == (_ds))
#define dsa_switch_for_each_available_port(_dp, _ds) \
dsa_switch_for_each_port((_dp), (_ds)) \
if (!dsa_port_is_unused((_dp)))
#define dsa_switch_for_each_user_port(_dp, _ds) \
dsa_switch_for_each_port((_dp), (_ds)) \
if (dsa_port_is_user((_dp)))
#define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \
dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \
if (dsa_port_is_user((_dp)))
#define dsa_switch_for_each_cpu_port(_dp, _ds) \
dsa_switch_for_each_port((_dp), (_ds)) \
if (dsa_port_is_cpu((_dp)))
#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \
dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \
if (dsa_port_is_cpu((_dp)))
static inline u32 dsa_user_ports(struct dsa_switch *ds)
{
struct dsa_port *dp;
u32 mask = 0;
dsa_switch_for_each_user_port(dp, ds)
mask |= BIT(dp->index);
return mask;
}
static inline u32 dsa_cpu_ports(struct dsa_switch *ds)
{
struct dsa_port *cpu_dp;
u32 mask = 0;
dsa_switch_for_each_cpu_port(cpu_dp, ds)
mask |= BIT(cpu_dp->index);
return mask;
}
/* Return the local port used to reach an arbitrary switch device */
static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device)
{
struct dsa_switch_tree *dst = ds->dst;
struct dsa_link *dl;
list_for_each_entry(dl, &dst->rtable, list)
if (dl->dp->ds == ds && dl->link_dp->ds->index == device)
return dl->dp->index;
return ds->num_ports;
}
/* Return the local port used to reach an arbitrary switch port */
static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device,
int port)
{
if (device == ds->index)
return port;
else
return dsa_routing_port(ds, device);
}
/* Return the local port used to reach the dedicated CPU port */
static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port)
{
const struct dsa_port *dp = dsa_to_port(ds, port);
const struct dsa_port *cpu_dp = dp->cpu_dp;
if (!cpu_dp)
return port;
return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index);
}
/* Return true if this is the local port used to reach the CPU port */
static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port)
{
if (dsa_is_unused_port(ds, port))
return false;
return port == dsa_upstream_port(ds, port);
}
/* Return true if this is a DSA port leading away from the CPU */
static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port)
{
return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port);
}
/* Return the local port used to reach the CPU port */
static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds)
{
struct dsa_port *dp;
dsa_switch_for_each_available_port(dp, ds) {
return dsa_upstream_port(ds, dp->index);
}
return ds->num_ports;
}
/* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning
* that the routing port from @downstream_ds to @upstream_ds is also the port
* which @downstream_ds uses to reach its dedicated CPU.
*/
static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds,
struct dsa_switch *downstream_ds)
{
int routing_port;
if (upstream_ds == downstream_ds)
return true;
routing_port = dsa_routing_port(downstream_ds, upstream_ds->index);
return dsa_is_upstream_port(downstream_ds, routing_port);
}
static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
{
const struct dsa_switch *ds = dp->ds;
if (ds->vlan_filtering_is_global)
return ds->vlan_filtering;
else
return dp->vlan_filtering;
}
static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp)
{
return dp->lag ? dp->lag->id : 0;
}
static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp)
{
return dp->lag ? dp->lag->dev : NULL;
}
static inline bool dsa_port_offloads_lag(struct dsa_port *dp,
const struct dsa_lag *lag)
{
return dsa_port_lag_dev_get(dp) == lag->dev;
}
static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp)
{
if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp);
return dp->cpu_dp->conduit;
}
static inline
struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp)
{
if (!dp->bridge)
return NULL;
if (dp->lag)
return dp->lag->dev;
else if (dp->hsr_dev)
return dp->hsr_dev;
return dp->user;
}
static inline struct net_device *
dsa_port_bridge_dev_get(const struct dsa_port *dp)
{
return dp->bridge ? dp->bridge->dev : NULL;
}
static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp)
{
return dp->bridge ? dp->bridge->num : 0;
}
static inline bool dsa_port_bridge_same(const struct dsa_port *a,
const struct dsa_port *b)
{
struct net_device *br_a = dsa_port_bridge_dev_get(a);
struct net_device *br_b = dsa_port_bridge_dev_get(b);
/* Standalone ports are not in the same bridge with one another */
return (!br_a || !br_b) ? false : (br_a == br_b);
}
static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp,
const struct net_device *dev)
{
return dsa_port_to_bridge_port(dp) == dev;
}
static inline bool
dsa_port_offloads_bridge_dev(struct dsa_port *dp,
const struct net_device *bridge_dev)
{
/* DSA ports connected to a bridge, and event was emitted
* for the bridge.
*/
return dsa_port_bridge_dev_get(dp) == bridge_dev;
}
static inline bool dsa_port_offloads_bridge(struct dsa_port *dp,
const struct dsa_bridge *bridge)
{
return dsa_port_bridge_dev_get(dp) == bridge->dev;
}
/* Returns true if any port of this tree offloads the given net_device */
static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst,
const struct net_device *dev)
{
struct dsa_port *dp;
list_for_each_entry(dp, &dst->ports, list)
if (dsa_port_offloads_bridge_port(dp, dev))
return true;
return false;
}
/* Returns true if any port of this tree offloads the given bridge */
static inline bool
dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst,
const struct net_device *bridge_dev)
{
struct dsa_port *dp;
list_for_each_entry(dp, &dst->ports, list)
if (dsa_port_offloads_bridge_dev(dp, bridge_dev))
return true;
return false;
}
static inline bool dsa_port_tree_same(const struct dsa_port *a,
const struct dsa_port *b)
{
return a->ds->dst == b->ds->dst;
}
typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
bool is_static, void *data);
struct dsa_switch_ops {
/*
* Tagging protocol helpers called for the CPU ports and DSA links.
* @get_tag_protocol retrieves the initial tagging protocol and is
* mandatory. Switches which can operate using multiple tagging
* protocols should implement @change_tag_protocol and report in
* @get_tag_protocol the tagger in current use.
*/
enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
int port,
enum dsa_tag_protocol mprot);
int (*change_tag_protocol)(struct dsa_switch *ds,
enum dsa_tag_protocol proto);
/*
* Method for switch drivers to connect to the tagging protocol driver
* in current use. The switch driver can provide handlers for certain
* types of packets for switch management.
*/
int (*connect_tag_protocol)(struct dsa_switch *ds,
enum dsa_tag_protocol proto);
int (*port_change_conduit)(struct dsa_switch *ds, int port,
struct net_device *conduit,
struct netlink_ext_ack *extack);
/* Optional switch-wide initialization and destruction methods */
int (*setup)(struct dsa_switch *ds);
void (*teardown)(struct dsa_switch *ds);
/* Per-port initialization and destruction methods. Mandatory if the
* driver registers devlink port regions, optional otherwise.
*/
int (*port_setup)(struct dsa_switch *ds, int port);
void (*port_teardown)(struct dsa_switch *ds, int port);
u32 (*get_phy_flags)(struct dsa_switch *ds, int port);
/*
* Access to the switch's PHY registers.
*/
int (*phy_read)(struct dsa_switch *ds, int port, int regnum);
int (*phy_write)(struct dsa_switch *ds, int port,
int regnum, u16 val);
/*
* PHYLINK integration
*/
void (*phylink_get_caps)(struct dsa_switch *ds, int port,
struct phylink_config *config);
void (*phylink_fixed_state)(struct dsa_switch *ds, int port,
struct phylink_link_state *state);
/*
* Port statistics counters.
*/
void (*get_strings)(struct dsa_switch *ds, int port,
u32 stringset, uint8_t *data);
void (*get_ethtool_stats)(struct dsa_switch *ds,
int port, uint64_t *data);
int (*get_sset_count)(struct dsa_switch *ds, int port, int sset);
void (*get_ethtool_phy_stats)(struct dsa_switch *ds,
int port, uint64_t *data);
void (*get_eth_phy_stats)(struct dsa_switch *ds, int port,
struct ethtool_eth_phy_stats *phy_stats);
void (*get_eth_mac_stats)(struct dsa_switch *ds, int port,
struct ethtool_eth_mac_stats *mac_stats);
void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port,
struct ethtool_eth_ctrl_stats *ctrl_stats);
void (*get_rmon_stats)(struct dsa_switch *ds, int port,
struct ethtool_rmon_stats *rmon_stats,
const struct ethtool_rmon_hist_range **ranges);
void (*get_ts_stats)(struct dsa_switch *ds, int port,
struct ethtool_ts_stats *ts_stats);
void (*get_stats64)(struct dsa_switch *ds, int port,
struct rtnl_link_stats64 *s);
void (*get_pause_stats)(struct dsa_switch *ds, int port,
struct ethtool_pause_stats *pause_stats);
void (*self_test)(struct dsa_switch *ds, int port,
struct ethtool_test *etest, u64 *data);
/*
* ethtool Wake-on-LAN
*/
void (*get_wol)(struct dsa_switch *ds, int port,
struct ethtool_wolinfo *w);
int (*set_wol)(struct dsa_switch *ds, int port,
struct ethtool_wolinfo *w);
/*
* ethtool timestamp info
*/
int (*get_ts_info)(struct dsa_switch *ds, int port,
struct kernel_ethtool_ts_info *ts);
/*
* ethtool MAC merge layer
*/
int (*get_mm)(struct dsa_switch *ds, int port,
struct ethtool_mm_state *state);
int (*set_mm)(struct dsa_switch *ds, int port,
struct ethtool_mm_cfg *cfg,
struct netlink_ext_ack *extack);
void (*get_mm_stats)(struct dsa_switch *ds, int port,
struct ethtool_mm_stats *stats);
/*
* DCB ops
*/
int (*port_get_default_prio)(struct dsa_switch *ds, int port);
int (*port_set_default_prio)(struct dsa_switch *ds, int port,
u8 prio);
int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp);
int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp,
u8 prio);
int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp,
u8 prio);
int (*port_set_apptrust)(struct dsa_switch *ds, int port,
const u8 *sel, int nsel);
int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel,
int *nsel);
/*
* Suspend and resume
*/
int (*suspend)(struct dsa_switch *ds);
int (*resume)(struct dsa_switch *ds);
/*
* Port enable/disable
*/
int (*port_enable)(struct dsa_switch *ds, int port,
struct phy_device *phy);
void (*port_disable)(struct dsa_switch *ds, int port);
/*
* Notification for MAC address changes on user ports. Drivers can
* currently only veto operations. They should not use the method to
* program the hardware, since the operation is not rolled back in case
* of other errors.
*/
int (*port_set_mac_address)(struct dsa_switch *ds, int port,
const unsigned char *addr);
/*
* Compatibility between device trees defining multiple CPU ports and
* drivers which are not OK to use by default the numerically smallest
* CPU port of a switch for its local ports. This can return NULL,
* meaning "don't know/don't care".
*/
struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds);
/*
* Port's MAC EEE settings
*/
bool (*support_eee)(struct dsa_switch *ds, int port);
int (*set_mac_eee)(struct dsa_switch *ds, int port,
struct ethtool_keee *e);
/* EEPROM access */
int (*get_eeprom_len)(struct dsa_switch *ds);
int (*get_eeprom)(struct dsa_switch *ds,
struct ethtool_eeprom *eeprom, u8 *data);
int (*set_eeprom)(struct dsa_switch *ds,
struct ethtool_eeprom *eeprom, u8 *data);
/*
* Register access.
*/
int (*get_regs_len)(struct dsa_switch *ds, int port);
void (*get_regs)(struct dsa_switch *ds, int port,
struct ethtool_regs *regs, void *p);
/*
* Upper device tracking.
*/
int (*port_prechangeupper)(struct dsa_switch *ds, int port,
struct netdev_notifier_changeupper_info *info);
/*
* Bridge integration
*/
int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs);
int (*port_bridge_join)(struct dsa_switch *ds, int port,
struct dsa_bridge bridge,
bool *tx_fwd_offload,
struct netlink_ext_ack *extack);
void (*port_bridge_leave)(struct dsa_switch *ds, int port,
struct dsa_bridge bridge);
void (*port_stp_state_set)(struct dsa_switch *ds, int port,
u8 state);
int (*port_mst_state_set)(struct dsa_switch *ds, int port,
const struct switchdev_mst_state *state);
void (*port_fast_age)(struct dsa_switch *ds, int port);
int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid);
int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack);
int (*port_bridge_flags)(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack);
void (*port_set_host_flood)(struct dsa_switch *ds, int port,
bool uc, bool mc);
/*
* VLAN support
*/
int (*port_vlan_filtering)(struct dsa_switch *ds, int port,
bool vlan_filtering,
struct netlink_ext_ack *extack);
int (*port_vlan_add)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan,
struct netlink_ext_ack *extack);
int (*port_vlan_del)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan);
int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge,
const struct switchdev_vlan_msti *msti);
/*
* Forwarding database
*/
int (*port_fdb_add)(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid,
struct dsa_db db);
int (*port_fdb_del)(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid,
struct dsa_db db);
int (*port_fdb_dump)(struct dsa_switch *ds, int port,
dsa_fdb_dump_cb_t *cb, void *data);
int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag,
const unsigned char *addr, u16 vid,
struct dsa_db db);
int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag,
const unsigned char *addr, u16 vid,
struct dsa_db db);
/*
* Multicast database
*/
int (*port_mdb_add)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_mdb *mdb,
struct dsa_db db);
int (*port_mdb_del)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_mdb *mdb,
struct dsa_db db);
/*
* RXNFC
*/
int (*get_rxnfc)(struct dsa_switch *ds, int port,
struct ethtool_rxnfc *nfc, u32 *rule_locs);
int (*set_rxnfc)(struct dsa_switch *ds, int port,
struct ethtool_rxnfc *nfc);
/*
* TC integration
*/
int (*cls_flower_add)(struct dsa_switch *ds, int port,
struct flow_cls_offload *cls, bool ingress);
int (*cls_flower_del)(struct dsa_switch *ds, int port,
struct flow_cls_offload *cls, bool ingress);
int (*cls_flower_stats)(struct dsa_switch *ds, int port,
struct flow_cls_offload *cls, bool ingress);
int (*port_mirror_add)(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror,
bool ingress, struct netlink_ext_ack *extack);
void (*port_mirror_del)(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
int (*port_policer_add)(struct dsa_switch *ds, int port,
struct dsa_mall_policer_tc_entry *policer);
void (*port_policer_del)(struct dsa_switch *ds, int port);
int (*port_setup_tc)(struct dsa_switch *ds, int port,
enum tc_setup_type type, void *type_data);
/*
* Cross-chip operations
*/
int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index,
int sw_index, int port,
struct dsa_bridge bridge,
struct netlink_ext_ack *extack);
void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index,
int sw_index, int port,
struct dsa_bridge bridge);
int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index,
int port);
int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index,
int port, struct dsa_lag lag,
struct netdev_lag_upper_info *info,
struct netlink_ext_ack *extack);
int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index,
int port, struct dsa_lag lag);
/*
* PTP functionality
*/
int (*port_hwtstamp_get)(struct dsa_switch *ds, int port,
struct ifreq *ifr);
int (*port_hwtstamp_set)(struct dsa_switch *ds, int port,
struct ifreq *ifr);
void (*port_txtstamp)(struct dsa_switch *ds, int port,
struct sk_buff *skb);
bool (*port_rxtstamp)(struct dsa_switch *ds, int port,
struct sk_buff *skb, unsigned int type);
/* Devlink parameters, etc */
int (*devlink_param_get)(struct dsa_switch *ds, u32 id,
struct devlink_param_gset_ctx *ctx);
int (*devlink_param_set)(struct dsa_switch *ds, u32 id,
struct devlink_param_gset_ctx *ctx);
int (*devlink_info_get)(struct dsa_switch *ds,
struct devlink_info_req *req,
struct netlink_ext_ack *extack);
int (*devlink_sb_pool_get)(struct dsa_switch *ds,
unsigned int sb_index, u16 pool_index,
struct devlink_sb_pool_info *pool_info);
int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index,
u16 pool_index, u32 size,
enum devlink_sb_threshold_type threshold_type,
struct netlink_ext_ack *extack);
int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 pool_index,
u32 *p_threshold);
int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 pool_index,
u32 threshold,
struct netlink_ext_ack *extack);
int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 tc_index,
enum devlink_sb_pool_type pool_type,
u16 *p_pool_index, u32 *p_threshold);
int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 tc_index,
enum devlink_sb_pool_type pool_type,
u16 pool_index, u32 threshold,
struct netlink_ext_ack *extack);
int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds,
unsigned int sb_index);
int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds,
unsigned int sb_index);
int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 pool_index,
u32 *p_cur, u32 *p_max);
int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port,
unsigned int sb_index, u16 tc_index,
enum devlink_sb_pool_type pool_type,
u32 *p_cur, u32 *p_max);
/*
* MTU change functionality. Switches can also adjust their MRU through
* this method. By MTU, one understands the SDU (L2 payload) length.
* If the switch needs to account for the DSA tag on the CPU port, this
* method needs to do so privately.
*/
int (*port_change_mtu)(struct dsa_switch *ds, int port,
int new_mtu);
int (*port_max_mtu)(struct dsa_switch *ds, int port);
/*
* LAG integration
*/
int (*port_lag_change)(struct dsa_switch *ds, int port);
int (*port_lag_join)(struct dsa_switch *ds, int port,
struct dsa_lag lag,
struct netdev_lag_upper_info *info,
struct netlink_ext_ack *extack);
int (*port_lag_leave)(struct dsa_switch *ds, int port,
struct dsa_lag lag);
/*
* HSR integration
*/
int (*port_hsr_join)(struct dsa_switch *ds, int port,
struct net_device *hsr,
struct netlink_ext_ack *extack);
int (*port_hsr_leave)(struct dsa_switch *ds, int port,
struct net_device *hsr);
/*
* MRP integration
*/
int (*port_mrp_add)(struct dsa_switch *ds, int port,
const struct switchdev_obj_mrp *mrp);
int (*port_mrp_del)(struct dsa_switch *ds, int port,
const struct switchdev_obj_mrp *mrp);
int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port,
const struct switchdev_obj_ring_role_mrp *mrp);
int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port,
const struct switchdev_obj_ring_role_mrp *mrp);
/*
* tag_8021q operations
*/
int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid,
u16 flags);
int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid);
/*
* DSA conduit tracking operations
*/
void (*conduit_state_change)(struct dsa_switch *ds,
const struct net_device *conduit,
bool operational);
};
#define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \
DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \
dsa_devlink_param_get, dsa_devlink_param_set, NULL)
int dsa_devlink_param_get(struct devlink *dl, u32 id,
struct devlink_param_gset_ctx *ctx);
int dsa_devlink_param_set(struct devlink *dl, u32 id,
struct devlink_param_gset_ctx *ctx,
struct netlink_ext_ack *extack);
int dsa_devlink_params_register(struct dsa_switch *ds,
const struct devlink_param *params,
size_t params_count);
void dsa_devlink_params_unregister(struct dsa_switch *ds,
const struct devlink_param *params,
size_t params_count);
int dsa_devlink_resource_register(struct dsa_switch *ds,
const char *resource_name,
u64 resource_size,
u64 resource_id,
u64 parent_resource_id,
const struct devlink_resource_size_params *size_params);
void dsa_devlink_resources_unregister(struct dsa_switch *ds);
void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds,
u64 resource_id,
devlink_resource_occ_get_t *occ_get,
void *occ_get_priv);
void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
u64 resource_id);
struct devlink_region *
dsa_devlink_region_create(struct dsa_switch *ds,
const struct devlink_region_ops *ops,
u32 region_max_snapshots, u64 region_size);
struct devlink_region *
dsa_devlink_port_region_create(struct dsa_switch *ds,
int port,
const struct devlink_port_region_ops *ops,
u32 region_max_snapshots, u64 region_size);
void dsa_devlink_region_destroy(struct devlink_region *region);
struct dsa_port *dsa_port_from_netdev(struct net_device *netdev);
struct dsa_devlink_priv {
struct dsa_switch *ds;
};
static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl)
{
struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
return dl_priv->ds;
}
static inline
struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port)
{
struct devlink *dl = port->devlink;
struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
return dl_priv->ds;
}
static inline int dsa_devlink_port_to_port(struct devlink_port *port)
{
return port->index;
}
struct dsa_switch_driver {
struct list_head list;
const struct dsa_switch_ops *ops;
};
bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid,
struct dsa_db db);
bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_mdb *mdb,
struct dsa_db db);
/* Keep inline for faster access in hot path */
static inline bool netdev_uses_dsa(const struct net_device *dev)
{
#if IS_ENABLED(CONFIG_NET_DSA)
return dev->dsa_ptr && dev->dsa_ptr->rcv;
#endif
return false;
}
/* All DSA tags that push the EtherType to the right (basically all except tail
* tags, which don't break dissection) can be treated the same from the
* perspective of the flow dissector.
*
* We need to return:
* - offset: the (B - A) difference between:
* A. the position of the real EtherType and
* B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes
* after the normal EtherType was supposed to be)
* The offset in bytes is exactly equal to the tagger overhead (and half of
* that, in __be16 shorts).
*
* - proto: the value of the real EtherType.
*/
static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
__be16 *proto, int *offset)
{
#if IS_ENABLED(CONFIG_NET_DSA)
const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
int tag_len = ops->needed_headroom;
*offset = tag_len;
*proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];
#endif
}
void dsa_unregister_switch(struct dsa_switch *ds);
int dsa_register_switch(struct dsa_switch *ds);
void dsa_switch_shutdown(struct dsa_switch *ds);
struct dsa_switch *dsa_switch_find(int tree_index, int sw_index);
void dsa_flush_workqueue(void);
#ifdef CONFIG_PM_SLEEP
int dsa_switch_suspend(struct dsa_switch *ds);
int dsa_switch_resume(struct dsa_switch *ds);
#else
static inline int dsa_switch_suspend(struct dsa_switch *ds)
{
return 0;
}
static inline int dsa_switch_resume(struct dsa_switch *ds)
{
return 0;
}
#endif /* CONFIG_PM_SLEEP */
#if IS_ENABLED(CONFIG_NET_DSA)
bool dsa_user_dev_check(const struct net_device *dev);
#else
static inline bool dsa_user_dev_check(const struct net_device *dev)
{
return false;
}
#endif
netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev);
void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up);
bool dsa_supports_eee(struct dsa_switch *ds, int port);
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012-2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <hyp/sysreg-sr.h>
#include <linux/compiler.h>
#include <linux/kvm_host.h>
#include <asm/kprobes.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_nested.h>
static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
{
/* These registers are common with EL1 */
__vcpu_sys_reg(vcpu, PAR_EL1) = read_sysreg(par_el1);
__vcpu_sys_reg(vcpu, TPIDR_EL1) = read_sysreg(tpidr_el1);
__vcpu_sys_reg(vcpu, ESR_EL2) = read_sysreg_el1(SYS_ESR);
__vcpu_sys_reg(vcpu, AFSR0_EL2) = read_sysreg_el1(SYS_AFSR0);
__vcpu_sys_reg(vcpu, AFSR1_EL2) = read_sysreg_el1(SYS_AFSR1);
__vcpu_sys_reg(vcpu, FAR_EL2) = read_sysreg_el1(SYS_FAR);
__vcpu_sys_reg(vcpu, MAIR_EL2) = read_sysreg_el1(SYS_MAIR);
__vcpu_sys_reg(vcpu, VBAR_EL2) = read_sysreg_el1(SYS_VBAR);
__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
__vcpu_sys_reg(vcpu, AMAIR_EL2) = read_sysreg_el1(SYS_AMAIR);
/*
* In VHE mode those registers are compatible between EL1 and EL2,
* and the guest uses the _EL1 versions on the CPU naturally.
* So we save them into their _EL2 versions here.
* For nVHE mode we trap accesses to those registers, so our
* _EL2 copy in sys_regs[] is always up-to-date and we don't need
* to save anything here.
*/
if (vcpu_el2_e2h_is_set(vcpu)) {
u64 val;
/*
* We don't save CPTR_EL2, as accesses to CPACR_EL1
* are always trapped, ensuring that the in-memory
* copy is always up-to-date. A small blessing...
*/
__vcpu_sys_reg(vcpu, SCTLR_EL2) = read_sysreg_el1(SYS_SCTLR);
__vcpu_sys_reg(vcpu, TTBR0_EL2) = read_sysreg_el1(SYS_TTBR0);
__vcpu_sys_reg(vcpu, TTBR1_EL2) = read_sysreg_el1(SYS_TTBR1);
__vcpu_sys_reg(vcpu, TCR_EL2) = read_sysreg_el1(SYS_TCR);
if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
__vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
__vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
__vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
}
if (ctxt_has_s1poe(&vcpu->arch.ctxt))
__vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
}
/*
* The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where
* the interesting CNTHCTL_EL2 bits live. So preserve these
* bits when reading back the guest-visible value.
*/
val = read_sysreg_el1(SYS_CNTKCTL);
val &= CNTKCTL_VALID_BITS;
__vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
}
__vcpu_sys_reg(vcpu, SP_EL2) = read_sysreg(sp_el1);
__vcpu_sys_reg(vcpu, ELR_EL2) = read_sysreg_el1(SYS_ELR);
__vcpu_sys_reg(vcpu, SPSR_EL2) = read_sysreg_el1(SYS_SPSR);
}
static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
{
u64 val;
/* These registers are common with EL1 */
write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1);
write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1);
write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt), vpidr_el2);
write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2);
write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR);
if (vcpu_el2_e2h_is_set(vcpu)) {
/*
* In VHE mode those registers are compatible between
* EL1 and EL2.
*/
write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0);
write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1);
write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL);
} else {
/*
* CNTHCTL_EL2 only affects EL1 when running nVHE, so
* no need to restore it.
*/
val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2));
write_sysreg_el1(val, SYS_SCTLR);
val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2));
write_sysreg_el1(val, SYS_CPACR);
val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2));
write_sysreg_el1(val, SYS_TTBR0);
val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2));
write_sysreg_el1(val, SYS_TCR);
}
if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2);
if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0);
}
if (ctxt_has_s1poe(&vcpu->arch.ctxt))
write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR);
}
write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0);
write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1);
write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR);
write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1);
write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR);
write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2), SYS_SPSR);
}
/*
* VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
* pstate, which are handled as part of the el2 return state) on every
* switch (sp_el0 is being dealt with in the assembly code).
* tpidr_el0 and tpidrro_el0 only need to be switched when going
* to host userspace or a different VCPU. EL1 registers only need to be
* switched when potentially going to run a different VCPU. The latter two
* classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
*/
void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
{ __sysreg_save_common_state(ctxt);
}
NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
{ __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt);
}
NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
{ __sysreg_restore_common_state(ctxt);
}
NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
{ __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt);
}
NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
/**
* __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU
*
* @vcpu: The VCPU pointer
*
* Load system registers that do not affect the host's execution, for
* example EL1 system registers on a VHE system where the host kernel
* runs at EL2. This function is called from KVM's vcpu_load() function
* and loading system register state early avoids having to load them on
* every entry to the VM.
*/
void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
struct kvm_cpu_context *host_ctxt;
u64 midr, mpidr;
host_ctxt = host_data_ptr(host_ctxt);
__sysreg_save_user_state(host_ctxt);
/*
* When running a normal EL1 guest, we only load a new vcpu
* after a context switch, which imvolves a DSB, so all
* speculative EL1&0 walks will have already completed.
* If running NV, the vcpu may transition between vEL1 and
* vEL2 without a context switch, so make sure we complete
* those walks before loading a new context.
*/
if (vcpu_has_nv(vcpu)) dsb(nsh);
/*
* Load guest EL1 and user state
*
* We must restore the 32-bit state before the sysregs, thanks
* to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
*/
__sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); if (unlikely(is_hyp_ctxt(vcpu))) {
__sysreg_restore_vel2_state(vcpu);
} else {
if (vcpu_has_nv(vcpu)) {
/*
* As we're restoring a nested guest, set the value
* provided by the guest hypervisor.
*/
midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2); mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
} else {
midr = ctxt_midr_el1(guest_ctxt); mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
}
__sysreg_restore_el1_state(guest_ctxt, midr, mpidr);
}
vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
}
/**
* __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU
*
* @vcpu: The VCPU pointer
*
* Save guest system registers that do not affect the host's execution, for
* example EL1 system registers on a VHE system where the host kernel
* runs at EL2. This function is called from KVM's vcpu_put() function
* and deferring saving system register state until we're no longer running the
* VCPU avoids having to save them on every exit from the VM.
*/
void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
struct kvm_cpu_context *host_ctxt;
host_ctxt = host_data_ptr(host_ctxt);
if (unlikely(is_hyp_ctxt(vcpu)))
__sysreg_save_vel2_state(vcpu);
else
__sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu);
/* Restore host user state */
__sysreg_restore_user_state(host_ctxt); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU);
}
// SPDX-License-Identifier: GPL-2.0-only
/* Page fragment allocator
*
* Page Fragment:
* An arbitrary-length arbitrary-offset area of memory which resides within a
* 0 or higher order page. Multiple fragments within that page are
* individually refcounted, in the page's reference counter.
*
* The page_frag functions provide a simple allocation framework for page
* fragments. This is used by the network stack and network device drivers to
* provide a backing region of memory for use as either an sk_buff->head, or to
* be used in the "frags" portion of skb_shared_info.
*/
#include <linux/build_bug.h>
#include <linux/export.h>
#include <linux/gfp_types.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/page_frag_cache.h>
#include "internal.h"
static unsigned long encoded_page_create(struct page *page, unsigned int order,
bool pfmemalloc)
{
BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK);
BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE);
return (unsigned long)page_address(page) |
(order & PAGE_FRAG_CACHE_ORDER_MASK) |
((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
}
static unsigned long encoded_page_decode_order(unsigned long encoded_page)
{
return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK;
}
static void *encoded_page_decode_virt(unsigned long encoded_page)
{
return (void *)(encoded_page & PAGE_MASK);
}
static struct page *encoded_page_decode_page(unsigned long encoded_page)
{
return virt_to_page((void *)encoded_page);
}
static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
gfp_t gfp_mask)
{
unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER;
struct page *page = NULL;
gfp_t gfp = gfp_mask;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP |
__GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER,
numa_mem_id(), NULL);
#endif
if (unlikely(!page)) {
page = __alloc_pages(gfp, 0, numa_mem_id(), NULL);
order = 0;
}
nc->encoded_page = page ?
encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0;
return page;
}
void page_frag_cache_drain(struct page_frag_cache *nc)
{
if (!nc->encoded_page)
return;
__page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page),
nc->pagecnt_bias);
nc->encoded_page = 0;
}
EXPORT_SYMBOL(page_frag_cache_drain);
void __page_frag_cache_drain(struct page *page, unsigned int count)
{
VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
if (page_ref_sub_and_test(page, count))
free_frozen_pages(page, compound_order(page));
}
EXPORT_SYMBOL(__page_frag_cache_drain);
void *__page_frag_alloc_align(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask,
unsigned int align_mask)
{
unsigned long encoded_page = nc->encoded_page;
unsigned int size, offset;
struct page *page;
if (unlikely(!encoded_page)) {
refill:
page = __page_frag_cache_refill(nc, gfp_mask);
if (!page)
return NULL;
encoded_page = nc->encoded_page;
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
nc->offset = 0;
}
size = PAGE_SIZE << encoded_page_decode_order(encoded_page);
offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
if (unlikely(offset + fragsz > size)) {
if (unlikely(fragsz > PAGE_SIZE)) {
/*
* The caller is trying to allocate a fragment
* with fragsz > PAGE_SIZE but the cache isn't big
* enough to satisfy the request, this may
* happen in low memory conditions.
* We don't release the cache page because
* it could make memory pressure worse
* so we simply return NULL here.
*/
return NULL;
}
page = encoded_page_decode_page(encoded_page);
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) {
free_frozen_pages(page,
encoded_page_decode_order(encoded_page));
goto refill;
}
/* OK, page count is 0, we can safely set it */
set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
offset = 0;
}
nc->pagecnt_bias--;
nc->offset = offset + fragsz;
return encoded_page_decode_virt(encoded_page) + offset;
}
EXPORT_SYMBOL(__page_frag_alloc_align);
/*
* Frees a page fragment allocated out of either a compound or order 0 page.
*/
void page_frag_free(void *addr)
{ struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) free_frozen_pages(page, compound_order(page));
}
EXPORT_SYMBOL(page_frag_free);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_SEQLOCK_H
#define __LINUX_SEQLOCK_H
/*
* seqcount_t / seqlock_t - a reader-writer consistency mechanism with
* lockless readers (read-only retry loops), and no writer starvation.
*
* See Documentation/locking/seqlock.rst
*
* Copyrights:
* - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli
* - Sequence counters with associated locks, (C) 2020 Linutronix GmbH
*/
#include <linux/compiler.h>
#include <linux/kcsan-checks.h>
#include <linux/lockdep.h>
#include <linux/mutex.h>
#include <linux/preempt.h>
#include <linux/seqlock_types.h>
#include <linux/spinlock.h>
#include <asm/processor.h>
/*
* The seqlock seqcount_t interface does not prescribe a precise sequence of
* read begin/retry/end. For readers, typically there is a call to
* read_seqcount_begin() and read_seqcount_retry(), however, there are more
* esoteric cases which do not follow this pattern.
*
* As a consequence, we take the following best-effort approach for raw usage
* via seqcount_t under KCSAN: upon beginning a seq-reader critical section,
* pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as
* atomics; if there is a matching read_seqcount_retry() call, no following
* memory operations are considered atomic. Usage of the seqlock_t interface
* is not affected.
*/
#define KCSAN_SEQLOCK_REGION_MAX 1000
static inline void __seqcount_init(seqcount_t *s, const char *name,
struct lock_class_key *key)
{
/*
* Make sure we are not reinitializing a held lock:
*/
lockdep_init_map(&s->dep_map, name, key, 0);
s->sequence = 0;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define SEQCOUNT_DEP_MAP_INIT(lockname) \
.dep_map = { .name = #lockname }
/**
* seqcount_init() - runtime initializer for seqcount_t
* @s: Pointer to the seqcount_t instance
*/
# define seqcount_init(s) \
do { \
static struct lock_class_key __key; \
__seqcount_init((s), #s, &__key); \
} while (0)
static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
{
seqcount_t *l = (seqcount_t *)s;
unsigned long flags;
local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_);
seqcount_release(&l->dep_map, _RET_IP_);
local_irq_restore(flags);
}
#else
# define SEQCOUNT_DEP_MAP_INIT(lockname)
# define seqcount_init(s) __seqcount_init(s, NULL, NULL)
# define seqcount_lockdep_reader_access(x)
#endif
/**
* SEQCNT_ZERO() - static initializer for seqcount_t
* @name: Name of the seqcount_t instance
*/
#define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
/*
* Sequence counters with associated locks (seqcount_LOCKNAME_t)
*
* A sequence counter which associates the lock used for writer
* serialization at initialization time. This enables lockdep to validate
* that the write side critical section is properly serialized.
*
* For associated locks which do not implicitly disable preemption,
* preemption protection is enforced in the write side function.
*
* Lockdep is never used in any for the raw write variants.
*
* See Documentation/locking/seqlock.rst
*/
/*
* typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
* @seqcount: The real sequence counter
* @lock: Pointer to the associated lock
*
* A plain sequence counter with external writer synchronization by
* LOCKNAME @lock. The lock is associated to the sequence counter in the
* static initializer or init function. This enables lockdep to validate
* that the write side critical section is properly serialized.
*
* LOCKNAME: raw_spinlock, spinlock, rwlock or mutex
*/
/*
* seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
* @s: Pointer to the seqcount_LOCKNAME_t instance
* @lock: Pointer to the associated lock
*/
#define seqcount_LOCKNAME_init(s, _lock, lockname) \
do { \
seqcount_##lockname##_t *____s = (s); \
seqcount_init(&____s->seqcount); \
__SEQ_LOCK(____s->lock = (_lock)); \
} while (0)
#define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock)
#define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock)
#define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock)
#define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex)
/*
* SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers
* seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t
*
* @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t
* @locktype: LOCKNAME canonical C data type
* @preemptible: preemptibility of above locktype
* @lockbase: prefix for associated lock/unlock
*/
#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \
static __always_inline seqcount_t * \
__seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \
{ \
return &s->seqcount; \
} \
\
static __always_inline const seqcount_t * \
__seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \
{ \
return &s->seqcount; \
} \
\
static __always_inline unsigned \
__seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \
{ \
unsigned seq = smp_load_acquire(&s->seqcount.sequence); \
\
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \
return seq; \
\
if (preemptible && unlikely(seq & 1)) { \
__SEQ_LOCK(lockbase##_lock(s->lock)); \
__SEQ_LOCK(lockbase##_unlock(s->lock)); \
\
/* \
* Re-read the sequence counter since the (possibly \
* preempted) writer made progress. \
*/ \
seq = smp_load_acquire(&s->seqcount.sequence); \
} \
\
return seq; \
} \
\
static __always_inline bool \
__seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \
{ \
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \
return preemptible; \
\
/* PREEMPT_RT relies on the above LOCK+UNLOCK */ \
return false; \
} \
\
static __always_inline void \
__seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \
{ \
__SEQ_LOCK(lockdep_assert_held(s->lock)); \
}
/*
* __seqprop() for seqcount_t
*/
static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
{
return s;
}
static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s)
{
return s;
}
static inline unsigned __seqprop_sequence(const seqcount_t *s)
{
return smp_load_acquire(&s->sequence);
}
static inline bool __seqprop_preemptible(const seqcount_t *s)
{
return false;
}
static inline void __seqprop_assert(const seqcount_t *s)
{
lockdep_assert_preemption_disabled();
}
#define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT)
SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin)
SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin)
SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read)
SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex)
#undef SEQCOUNT_LOCKNAME
/*
* SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
* @name: Name of the seqcount_LOCKNAME_t instance
* @lock: Pointer to the associated LOCKNAME
*/
#define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \
.seqcount = SEQCNT_ZERO(seq_name.seqcount), \
__SEQ_LOCK(.lock = (assoc_lock)) \
}
#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock)
#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock)
#define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock)
#define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock)
#define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock)
#define __seqprop_case(s, lockname, prop) \
seqcount_##lockname##_t: __seqprop_##lockname##_##prop
#define __seqprop(s, prop) _Generic(*(s), \
seqcount_t: __seqprop_##prop, \
__seqprop_case((s), raw_spinlock, prop), \
__seqprop_case((s), spinlock, prop), \
__seqprop_case((s), rwlock, prop), \
__seqprop_case((s), mutex, prop))
#define seqprop_ptr(s) __seqprop(s, ptr)(s)
#define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s)
#define seqprop_sequence(s) __seqprop(s, sequence)(s)
#define seqprop_preemptible(s) __seqprop(s, preemptible)(s)
#define seqprop_assert(s) __seqprop(s, assert)(s)
/**
* __read_seqcount_begin() - begin a seqcount_t read section
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Return: count to be passed to read_seqcount_retry()
*/
#define __read_seqcount_begin(s) \
({ \
unsigned __seq; \
\
while (unlikely((__seq = seqprop_sequence(s)) & 1)) \
cpu_relax(); \
\
kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \
__seq; \
})
/**
* raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Return: count to be passed to read_seqcount_retry()
*/
#define raw_read_seqcount_begin(s) __read_seqcount_begin(s)
/**
* read_seqcount_begin() - begin a seqcount_t read critical section
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Return: count to be passed to read_seqcount_retry()
*/
#define read_seqcount_begin(s) \
({ \
seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \
raw_read_seqcount_begin(s); \
})
/**
* raw_read_seqcount() - read the raw seqcount_t counter value
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* raw_read_seqcount opens a read critical section of the given
* seqcount_t, without any lockdep checking, and without checking or
* masking the sequence counter LSB. Calling code is responsible for
* handling that.
*
* Return: count to be passed to read_seqcount_retry()
*/
#define raw_read_seqcount(s) \
({ \
unsigned __seq = seqprop_sequence(s); \
\
kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \
__seq; \
})
/**
* raw_seqcount_try_begin() - begin a seqcount_t read critical section
* w/o lockdep and w/o counter stabilization
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
* @start: count to be passed to read_seqcount_retry()
*
* Similar to raw_seqcount_begin(), except it enables eliding the critical
* section entirely if odd, instead of doing the speculation knowing it will
* fail.
*
* Useful when counter stabilization is more or less equivalent to taking
* the lock and there is a slowpath that does that.
*
* If true, start will be set to the (even) sequence count read.
*
* Return: true when a read critical section is started.
*/
#define raw_seqcount_try_begin(s, start) \
({ \
start = raw_read_seqcount(s); \
!(start & 1); \
})
/**
* raw_seqcount_begin() - begin a seqcount_t read critical section w/o
* lockdep and w/o counter stabilization
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* raw_seqcount_begin opens a read critical section of the given
* seqcount_t. Unlike read_seqcount_begin(), this function will not wait
* for the count to stabilize. If a writer is active when it begins, it
* will fail the read_seqcount_retry() at the end of the read critical
* section instead of stabilizing at the beginning of it.
*
* Use this only in special kernel hot paths where the read section is
* small and has a high probability of success through other external
* means. It will save a single branching instruction.
*
* Return: count to be passed to read_seqcount_retry()
*/
#define raw_seqcount_begin(s) \
({ \
/* \
* If the counter is odd, let read_seqcount_retry() fail \
* by decrementing the counter. \
*/ \
raw_read_seqcount(s) & ~1; \
})
/**
* __read_seqcount_retry() - end a seqcount_t read section w/o barrier
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
* @start: count, from read_seqcount_begin()
*
* __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
* barrier. Callers should ensure that smp_rmb() or equivalent ordering is
* provided before actually loading any of the variables that are to be
* protected in this critical section.
*
* Use carefully, only in critical code, and comment how the barrier is
* provided.
*
* Return: true if a read section retry is required, else false
*/
#define __read_seqcount_retry(s, start) \
do___read_seqcount_retry(seqprop_const_ptr(s), start)
static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start)
{
kcsan_atomic_next(0);
return unlikely(READ_ONCE(s->sequence) != start);
}
/**
* read_seqcount_retry() - end a seqcount_t read critical section
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
* @start: count, from read_seqcount_begin()
*
* read_seqcount_retry closes the read critical section of given
* seqcount_t. If the critical section was invalid, it must be ignored
* (and typically retried).
*
* Return: true if a read section retry is required, else false
*/
#define read_seqcount_retry(s, start) \
do_read_seqcount_retry(seqprop_const_ptr(s), start)
static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start)
{
smp_rmb();
return do___read_seqcount_retry(s, start);
}
/**
* raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Context: check write_seqcount_begin()
*/
#define raw_write_seqcount_begin(s) \
do { \
if (seqprop_preemptible(s)) \
preempt_disable(); \
\
do_raw_write_seqcount_begin(seqprop_ptr(s)); \
} while (0)
static inline void do_raw_write_seqcount_begin(seqcount_t *s)
{
kcsan_nestable_atomic_begin();
s->sequence++;
smp_wmb();
}
/**
* raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Context: check write_seqcount_end()
*/
#define raw_write_seqcount_end(s) \
do { \
do_raw_write_seqcount_end(seqprop_ptr(s)); \
\
if (seqprop_preemptible(s)) \
preempt_enable(); \
} while (0)
static inline void do_raw_write_seqcount_end(seqcount_t *s)
{
smp_wmb();
s->sequence++;
kcsan_nestable_atomic_end();
}
/**
* write_seqcount_begin_nested() - start a seqcount_t write section with
* custom lockdep nesting level
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
* @subclass: lockdep nesting level
*
* See Documentation/locking/lockdep-design.rst
* Context: check write_seqcount_begin()
*/
#define write_seqcount_begin_nested(s, subclass) \
do { \
seqprop_assert(s); \
\
if (seqprop_preemptible(s)) \
preempt_disable(); \
\
do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \
} while (0)
static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass)
{
seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
do_raw_write_seqcount_begin(s);
}
/**
* write_seqcount_begin() - start a seqcount_t write side critical section
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Context: sequence counter write side sections must be serialized and
* non-preemptible. Preemption will be automatically disabled if and
* only if the seqcount write serialization lock is associated, and
* preemptible. If readers can be invoked from hardirq or softirq
* context, interrupts or bottom halves must be respectively disabled.
*/
#define write_seqcount_begin(s) \
do { \
seqprop_assert(s); \
\
if (seqprop_preemptible(s)) \
preempt_disable(); \
\
do_write_seqcount_begin(seqprop_ptr(s)); \
} while (0)
static inline void do_write_seqcount_begin(seqcount_t *s)
{
do_write_seqcount_begin_nested(s, 0);
}
/**
* write_seqcount_end() - end a seqcount_t write side critical section
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* Context: Preemption will be automatically re-enabled if and only if
* the seqcount write serialization lock is associated, and preemptible.
*/
#define write_seqcount_end(s) \
do { \
do_write_seqcount_end(seqprop_ptr(s)); \
\
if (seqprop_preemptible(s)) \
preempt_enable(); \
} while (0)
static inline void do_write_seqcount_end(seqcount_t *s)
{
seqcount_release(&s->dep_map, _RET_IP_);
do_raw_write_seqcount_end(s);
}
/**
* raw_write_seqcount_barrier() - do a seqcount_t write barrier
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* This can be used to provide an ordering guarantee instead of the usual
* consistency guarantee. It is one wmb cheaper, because it can collapse
* the two back-to-back wmb()s.
*
* Note that writes surrounding the barrier should be declared atomic (e.g.
* via WRITE_ONCE): a) to ensure the writes become visible to other threads
* atomically, avoiding compiler optimizations; b) to document which writes are
* meant to propagate to the reader critical section. This is necessary because
* neither writes before nor after the barrier are enclosed in a seq-writer
* critical section that would ensure readers are aware of ongoing writes::
*
* seqcount_t seq;
* bool X = true, Y = false;
*
* void read(void)
* {
* bool x, y;
*
* do {
* int s = read_seqcount_begin(&seq);
*
* x = X; y = Y;
*
* } while (read_seqcount_retry(&seq, s));
*
* BUG_ON(!x && !y);
* }
*
* void write(void)
* {
* WRITE_ONCE(Y, true);
*
* raw_write_seqcount_barrier(seq);
*
* WRITE_ONCE(X, false);
* }
*/
#define raw_write_seqcount_barrier(s) \
do_raw_write_seqcount_barrier(seqprop_ptr(s))
static inline void do_raw_write_seqcount_barrier(seqcount_t *s)
{
kcsan_nestable_atomic_begin();
s->sequence++;
smp_wmb();
s->sequence++;
kcsan_nestable_atomic_end();
}
/**
* write_seqcount_invalidate() - invalidate in-progress seqcount_t read
* side operations
* @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
*
* After write_seqcount_invalidate, no seqcount_t read side operations
* will complete successfully and see data older than this.
*/
#define write_seqcount_invalidate(s) \
do_write_seqcount_invalidate(seqprop_ptr(s))
static inline void do_write_seqcount_invalidate(seqcount_t *s)
{
smp_wmb();
kcsan_nestable_atomic_begin();
s->sequence+=2;
kcsan_nestable_atomic_end();
}
/*
* Latch sequence counters (seqcount_latch_t)
*
* A sequence counter variant where the counter even/odd value is used to
* switch between two copies of protected data. This allows the read path,
* typically NMIs, to safely interrupt the write side critical section.
*
* As the write sections are fully preemptible, no special handling for
* PREEMPT_RT is needed.
*/
typedef struct {
seqcount_t seqcount;
} seqcount_latch_t;
/**
* SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t
* @seq_name: Name of the seqcount_latch_t instance
*/
#define SEQCNT_LATCH_ZERO(seq_name) { \
.seqcount = SEQCNT_ZERO(seq_name.seqcount), \
}
/**
* seqcount_latch_init() - runtime initializer for seqcount_latch_t
* @s: Pointer to the seqcount_latch_t instance
*/
#define seqcount_latch_init(s) seqcount_init(&(s)->seqcount)
/**
* raw_read_seqcount_latch() - pick even/odd latch data copy
* @s: Pointer to seqcount_latch_t
*
* See raw_write_seqcount_latch() for details and a full reader/writer
* usage example.
*
* Return: sequence counter raw value. Use the lowest bit as an index for
* picking which data copy to read. The full counter must then be checked
* with raw_read_seqcount_latch_retry().
*/
static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
{
/*
* Pairs with the first smp_wmb() in raw_write_seqcount_latch().
* Due to the dependent load, a full smp_rmb() is not needed.
*/
return READ_ONCE(s->seqcount.sequence);
}
/**
* read_seqcount_latch() - pick even/odd latch data copy
* @s: Pointer to seqcount_latch_t
*
* See write_seqcount_latch() for details and a full reader/writer usage
* example.
*
* Return: sequence counter raw value. Use the lowest bit as an index for
* picking which data copy to read. The full counter must then be checked
* with read_seqcount_latch_retry().
*/
static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s)
{
kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
return raw_read_seqcount_latch(s);
}
/**
* raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section
* @s: Pointer to seqcount_latch_t
* @start: count, from raw_read_seqcount_latch()
*
* Return: true if a read section retry is required, else false
*/
static __always_inline int
raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
{
smp_rmb();
return unlikely(READ_ONCE(s->seqcount.sequence) != start);
}
/**
* read_seqcount_latch_retry() - end a seqcount_latch_t read section
* @s: Pointer to seqcount_latch_t
* @start: count, from read_seqcount_latch()
*
* Return: true if a read section retry is required, else false
*/
static __always_inline int
read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
{
kcsan_atomic_next(0);
return raw_read_seqcount_latch_retry(s, start);
}
/**
* raw_write_seqcount_latch() - redirect latch readers to even/odd copy
* @s: Pointer to seqcount_latch_t
*/
static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s)
{
smp_wmb(); /* prior stores before incrementing "sequence" */
s->seqcount.sequence++;
smp_wmb(); /* increment "sequence" before following stores */
}
/**
* write_seqcount_latch_begin() - redirect latch readers to odd copy
* @s: Pointer to seqcount_latch_t
*
* The latch technique is a multiversion concurrency control method that allows
* queries during non-atomic modifications. If you can guarantee queries never
* interrupt the modification -- e.g. the concurrency is strictly between CPUs
* -- you most likely do not need this.
*
* Where the traditional RCU/lockless data structures rely on atomic
* modifications to ensure queries observe either the old or the new state the
* latch allows the same for non-atomic updates. The trade-off is doubling the
* cost of storage; we have to maintain two copies of the entire data
* structure.
*
* Very simply put: we first modify one copy and then the other. This ensures
* there is always one copy in a stable state, ready to give us an answer.
*
* The basic form is a data structure like::
*
* struct latch_struct {
* seqcount_latch_t seq;
* struct data_struct data[2];
* };
*
* Where a modification, which is assumed to be externally serialized, does the
* following::
*
* void latch_modify(struct latch_struct *latch, ...)
* {
* write_seqcount_latch_begin(&latch->seq);
* modify(latch->data[0], ...);
* write_seqcount_latch(&latch->seq);
* modify(latch->data[1], ...);
* write_seqcount_latch_end(&latch->seq);
* }
*
* The query will have a form like::
*
* struct entry *latch_query(struct latch_struct *latch, ...)
* {
* struct entry *entry;
* unsigned seq, idx;
*
* do {
* seq = read_seqcount_latch(&latch->seq);
*
* idx = seq & 0x01;
* entry = data_query(latch->data[idx], ...);
*
* // This includes needed smp_rmb()
* } while (read_seqcount_latch_retry(&latch->seq, seq));
*
* return entry;
* }
*
* So during the modification, queries are first redirected to data[1]. Then we
* modify data[0]. When that is complete, we redirect queries back to data[0]
* and we can modify data[1].
*
* NOTE:
*
* The non-requirement for atomic modifications does _NOT_ include
* the publishing of new entries in the case where data is a dynamic
* data structure.
*
* An iteration might start in data[0] and get suspended long enough
* to miss an entire modification sequence, once it resumes it might
* observe the new entry.
*
* NOTE2:
*
* When data is a dynamic data structure; one should use regular RCU
* patterns to manage the lifetimes of the objects within.
*/
static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s)
{
kcsan_nestable_atomic_begin();
raw_write_seqcount_latch(s);
}
/**
* write_seqcount_latch() - redirect latch readers to even copy
* @s: Pointer to seqcount_latch_t
*/
static __always_inline void write_seqcount_latch(seqcount_latch_t *s)
{
raw_write_seqcount_latch(s);
}
/**
* write_seqcount_latch_end() - end a seqcount_latch_t write section
* @s: Pointer to seqcount_latch_t
*
* Marks the end of a seqcount_latch_t writer section, after all copies of the
* latch-protected data have been updated.
*/
static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s)
{
kcsan_nestable_atomic_end();
}
#define __SEQLOCK_UNLOCKED(lockname) \
{ \
.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
.lock = __SPIN_LOCK_UNLOCKED(lockname) \
}
/**
* seqlock_init() - dynamic initializer for seqlock_t
* @sl: Pointer to the seqlock_t instance
*/
#define seqlock_init(sl) \
do { \
spin_lock_init(&(sl)->lock); \
seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \
} while (0)
/**
* DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t
* @sl: Name of the seqlock_t instance
*/
#define DEFINE_SEQLOCK(sl) \
seqlock_t sl = __SEQLOCK_UNLOCKED(sl)
/**
* read_seqbegin() - start a seqlock_t read side critical section
* @sl: Pointer to seqlock_t
*
* Return: count, to be passed to read_seqretry()
*/
static inline unsigned read_seqbegin(const seqlock_t *sl)
{ return read_seqcount_begin(&sl->seqcount);
}
/**
* read_seqretry() - end a seqlock_t read side section
* @sl: Pointer to seqlock_t
* @start: count, from read_seqbegin()
*
* read_seqretry closes the read side critical section of given seqlock_t.
* If the critical section was invalid, it must be ignored (and typically
* retried).
*
* Return: true if a read section retry is required, else false
*/
static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
{
return read_seqcount_retry(&sl->seqcount, start);
}
/*
* For all seqlock_t write side functions, use the internal
* do_write_seqcount_begin() instead of generic write_seqcount_begin().
* This way, no redundant lockdep_assert_held() checks are added.
*/
/**
* write_seqlock() - start a seqlock_t write side critical section
* @sl: Pointer to seqlock_t
*
* write_seqlock opens a write side critical section for the given
* seqlock_t. It also implicitly acquires the spinlock_t embedded inside
* that sequential lock. All seqlock_t write side sections are thus
* automatically serialized and non-preemptible.
*
* Context: if the seqlock_t read section, or other write side critical
* sections, can be invoked from hardirq or softirq contexts, use the
* _irqsave or _bh variants of this function instead.
*/
static inline void write_seqlock(seqlock_t *sl)
{
spin_lock(&sl->lock);
do_write_seqcount_begin(&sl->seqcount.seqcount);
}
/**
* write_sequnlock() - end a seqlock_t write side critical section
* @sl: Pointer to seqlock_t
*
* write_sequnlock closes the (serialized and non-preemptible) write side
* critical section of given seqlock_t.
*/
static inline void write_sequnlock(seqlock_t *sl)
{
do_write_seqcount_end(&sl->seqcount.seqcount);
spin_unlock(&sl->lock);
}
/**
* write_seqlock_bh() - start a softirqs-disabled seqlock_t write section
* @sl: Pointer to seqlock_t
*
* _bh variant of write_seqlock(). Use only if the read side section, or
* other write side sections, can be invoked from softirq contexts.
*/
static inline void write_seqlock_bh(seqlock_t *sl)
{
spin_lock_bh(&sl->lock);
do_write_seqcount_begin(&sl->seqcount.seqcount);
}
/**
* write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section
* @sl: Pointer to seqlock_t
*
* write_sequnlock_bh closes the serialized, non-preemptible, and
* softirqs-disabled, seqlock_t write side critical section opened with
* write_seqlock_bh().
*/
static inline void write_sequnlock_bh(seqlock_t *sl)
{
do_write_seqcount_end(&sl->seqcount.seqcount);
spin_unlock_bh(&sl->lock);
}
/**
* write_seqlock_irq() - start a non-interruptible seqlock_t write section
* @sl: Pointer to seqlock_t
*
* _irq variant of write_seqlock(). Use only if the read side section, or
* other write sections, can be invoked from hardirq contexts.
*/
static inline void write_seqlock_irq(seqlock_t *sl)
{
spin_lock_irq(&sl->lock);
do_write_seqcount_begin(&sl->seqcount.seqcount);
}
/**
* write_sequnlock_irq() - end a non-interruptible seqlock_t write section
* @sl: Pointer to seqlock_t
*
* write_sequnlock_irq closes the serialized and non-interruptible
* seqlock_t write side section opened with write_seqlock_irq().
*/
static inline void write_sequnlock_irq(seqlock_t *sl)
{
do_write_seqcount_end(&sl->seqcount.seqcount);
spin_unlock_irq(&sl->lock);
}
static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
{
unsigned long flags;
spin_lock_irqsave(&sl->lock, flags);
do_write_seqcount_begin(&sl->seqcount.seqcount);
return flags;
}
/**
* write_seqlock_irqsave() - start a non-interruptible seqlock_t write
* section
* @lock: Pointer to seqlock_t
* @flags: Stack-allocated storage for saving caller's local interrupt
* state, to be passed to write_sequnlock_irqrestore().
*
* _irqsave variant of write_seqlock(). Use it only if the read side
* section, or other write sections, can be invoked from hardirq context.
*/
#define write_seqlock_irqsave(lock, flags) \
do { flags = __write_seqlock_irqsave(lock); } while (0)
/**
* write_sequnlock_irqrestore() - end non-interruptible seqlock_t write
* section
* @sl: Pointer to seqlock_t
* @flags: Caller's saved interrupt state, from write_seqlock_irqsave()
*
* write_sequnlock_irqrestore closes the serialized and non-interruptible
* seqlock_t write section previously opened with write_seqlock_irqsave().
*/
static inline void
write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
{
do_write_seqcount_end(&sl->seqcount.seqcount);
spin_unlock_irqrestore(&sl->lock, flags);
}
/**
* read_seqlock_excl() - begin a seqlock_t locking reader section
* @sl: Pointer to seqlock_t
*
* read_seqlock_excl opens a seqlock_t locking reader critical section. A
* locking reader exclusively locks out *both* other writers *and* other
* locking readers, but it does not update the embedded sequence number.
*
* Locking readers act like a normal spin_lock()/spin_unlock().
*
* Context: if the seqlock_t write section, *or other read sections*, can
* be invoked from hardirq or softirq contexts, use the _irqsave or _bh
* variant of this function instead.
*
* The opened read section must be closed with read_sequnlock_excl().
*/
static inline void read_seqlock_excl(seqlock_t *sl)
{
spin_lock(&sl->lock);
}
/**
* read_sequnlock_excl() - end a seqlock_t locking reader critical section
* @sl: Pointer to seqlock_t
*/
static inline void read_sequnlock_excl(seqlock_t *sl)
{
spin_unlock(&sl->lock);
}
/**
* read_seqlock_excl_bh() - start a seqlock_t locking reader section with
* softirqs disabled
* @sl: Pointer to seqlock_t
*
* _bh variant of read_seqlock_excl(). Use this variant only if the
* seqlock_t write side section, *or other read sections*, can be invoked
* from softirq contexts.
*/
static inline void read_seqlock_excl_bh(seqlock_t *sl)
{
spin_lock_bh(&sl->lock);
}
/**
* read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking
* reader section
* @sl: Pointer to seqlock_t
*/
static inline void read_sequnlock_excl_bh(seqlock_t *sl)
{
spin_unlock_bh(&sl->lock);
}
/**
* read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking
* reader section
* @sl: Pointer to seqlock_t
*
* _irq variant of read_seqlock_excl(). Use this only if the seqlock_t
* write side section, *or other read sections*, can be invoked from a
* hardirq context.
*/
static inline void read_seqlock_excl_irq(seqlock_t *sl)
{
spin_lock_irq(&sl->lock);
}
/**
* read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t
* locking reader section
* @sl: Pointer to seqlock_t
*/
static inline void read_sequnlock_excl_irq(seqlock_t *sl)
{
spin_unlock_irq(&sl->lock);
}
static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl)
{
unsigned long flags;
spin_lock_irqsave(&sl->lock, flags);
return flags;
}
/**
* read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t
* locking reader section
* @lock: Pointer to seqlock_t
* @flags: Stack-allocated storage for saving caller's local interrupt
* state, to be passed to read_sequnlock_excl_irqrestore().
*
* _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t
* write side section, *or other read sections*, can be invoked from a
* hardirq context.
*/
#define read_seqlock_excl_irqsave(lock, flags) \
do { flags = __read_seqlock_excl_irqsave(lock); } while (0)
/**
* read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t
* locking reader section
* @sl: Pointer to seqlock_t
* @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave()
*/
static inline void
read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
{
spin_unlock_irqrestore(&sl->lock, flags);
}
/**
* read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader
* @lock: Pointer to seqlock_t
* @seq : Marker and return parameter. If the passed value is even, the
* reader will become a *lockless* seqlock_t reader as in read_seqbegin().
* If the passed value is odd, the reader will become a *locking* reader
* as in read_seqlock_excl(). In the first call to this function, the
* caller *must* initialize and pass an even value to @seq; this way, a
* lockless read can be optimistically tried first.
*
* read_seqbegin_or_lock is an API designed to optimistically try a normal
* lockless seqlock_t read section first. If an odd counter is found, the
* lockless read trial has failed, and the next read iteration transforms
* itself into a full seqlock_t locking reader.
*
* This is typically used to avoid seqlock_t lockless readers starvation
* (too much retry loops) in the case of a sharp spike in write side
* activity.
*
* Context: if the seqlock_t write section, *or other read sections*, can
* be invoked from hardirq or softirq contexts, use the _irqsave or _bh
* variant of this function instead.
*
* Check Documentation/locking/seqlock.rst for template example code.
*
* Return: the encountered sequence counter value, through the @seq
* parameter, which is overloaded as a return parameter. This returned
* value must be checked with need_seqretry(). If the read section need to
* be retried, this returned value must also be passed as the @seq
* parameter of the next read_seqbegin_or_lock() iteration.
*/
static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
{
if (!(*seq & 1)) /* Even */
*seq = read_seqbegin(lock);
else /* Odd */
read_seqlock_excl(lock);
}
/**
* need_seqretry() - validate seqlock_t "locking or lockless" read section
* @lock: Pointer to seqlock_t
* @seq: sequence count, from read_seqbegin_or_lock()
*
* Return: true if a read section retry is required, false otherwise
*/
static inline int need_seqretry(seqlock_t *lock, int seq)
{
return !(seq & 1) && read_seqretry(lock, seq);
}
/**
* done_seqretry() - end seqlock_t "locking or lockless" reader section
* @lock: Pointer to seqlock_t
* @seq: count, from read_seqbegin_or_lock()
*
* done_seqretry finishes the seqlock_t read side critical section started
* with read_seqbegin_or_lock() and validated by need_seqretry().
*/
static inline void done_seqretry(seqlock_t *lock, int seq)
{
if (seq & 1) read_sequnlock_excl(lock);
}
/**
* read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or
* a non-interruptible locking reader
* @lock: Pointer to seqlock_t
* @seq: Marker and return parameter. Check read_seqbegin_or_lock().
*
* This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if
* the seqlock_t write section, *or other read sections*, can be invoked
* from hardirq context.
*
* Note: Interrupts will be disabled only for "locking reader" mode.
*
* Return:
*
* 1. The saved local interrupts state in case of a locking reader, to
* be passed to done_seqretry_irqrestore().
*
* 2. The encountered sequence counter value, returned through @seq
* overloaded as a return parameter. Check read_seqbegin_or_lock().
*/
static inline unsigned long
read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
{
unsigned long flags = 0;
if (!(*seq & 1)) /* Even */
*seq = read_seqbegin(lock);
else /* Odd */
read_seqlock_excl_irqsave(lock, flags);
return flags;
}
/**
* done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a
* non-interruptible locking reader section
* @lock: Pointer to seqlock_t
* @seq: Count, from read_seqbegin_or_lock_irqsave()
* @flags: Caller's saved local interrupt state in case of a locking
* reader, also from read_seqbegin_or_lock_irqsave()
*
* This is the _irqrestore variant of done_seqretry(). The read section
* must've been opened with read_seqbegin_or_lock_irqsave(), and validated
* by need_seqretry().
*/
static inline void
done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
{
if (seq & 1)
read_sequnlock_excl_irqrestore(lock, flags);
}
#endif /* __LINUX_SEQLOCK_H */
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/list_sort.h>
#include <linux/list.h>
/*
* Returns a list organized in an intermediate format suited
* to chaining of merge() calls: null-terminated, no reserved or
* sentinel head node, "prev" links not maintained.
*/
__attribute__((nonnull(2,3,4)))
static struct list_head *merge(void *priv, list_cmp_func_t cmp,
struct list_head *a, struct list_head *b)
{
struct list_head *head, **tail = &head;
for (;;) {
/* if equal, take 'a' -- important for sort stability */
if (cmp(priv, a, b) <= 0) {
*tail = a;
tail = &a->next;
a = a->next;
if (!a) { *tail = b;
break;
}
} else {
*tail = b;
tail = &b->next;
b = b->next;
if (!b) { *tail = a;
break;
}
}
}
return head;
}
/*
* Combine final list merge with restoration of standard doubly-linked
* list structure. This approach duplicates code from merge(), but
* runs faster than the tidier alternatives of either a separate final
* prev-link restoration pass, or maintaining the prev links
* throughout.
*/
__attribute__((nonnull(2,3,4,5)))
static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head,
struct list_head *a, struct list_head *b)
{
struct list_head *tail = head;
u8 count = 0;
for (;;) {
/* if equal, take 'a' -- important for sort stability */
if (cmp(priv, a, b) <= 0) {
tail->next = a;
a->prev = tail;
tail = a;
a = a->next;
if (!a)
break;
} else {
tail->next = b;
b->prev = tail;
tail = b;
b = b->next;
if (!b) {
b = a;
break;
}
}
}
/* Finish linking remainder of list b on to tail */
tail->next = b;
do {
/*
* If the merge is highly unbalanced (e.g. the input is
* already sorted), this loop may run many iterations.
* Continue callbacks to the client even though no
* element comparison is needed, so the client's cmp()
* routine can invoke cond_resched() periodically.
*/
if (unlikely(!++count)) cmp(priv, b, b);
b->prev = tail;
tail = b;
b = b->next;
} while (b);
/* And the final links to make a circular doubly-linked list */
tail->next = head;
head->prev = tail;
}
/**
* list_sort - sort a list
* @priv: private data, opaque to list_sort(), passed to @cmp
* @head: the list to sort
* @cmp: the elements comparison function
*
* The comparison function @cmp must return > 0 if @a should sort after
* @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should
* sort before @b *or* their original order should be preserved. It is
* always called with the element that came first in the input in @a,
* and list_sort is a stable sort, so it is not necessary to distinguish
* the @a < @b and @a == @b cases.
*
* The comparison function must adhere to specific mathematical properties
* to ensure correct and stable sorting:
* - Antisymmetry: cmp(@a, @b) must return the opposite sign of
* cmp(@b, @a).
* - Transitivity: if cmp(@a, @b) <= 0 and cmp(@b, @c) <= 0, then
* cmp(@a, @c) <= 0.
*
* This is compatible with two styles of @cmp function:
* - The traditional style which returns <0 / =0 / >0, or
* - Returning a boolean 0/1.
* The latter offers a chance to save a few cycles in the comparison
* (which is used by e.g. plug_ctx_cmp() in block/blk-mq.c).
*
* A good way to write a multi-word comparison is::
*
* if (a->high != b->high)
* return a->high > b->high;
* if (a->middle != b->middle)
* return a->middle > b->middle;
* return a->low > b->low;
*
*
* This mergesort is as eager as possible while always performing at least
* 2:1 balanced merges. Given two pending sublists of size 2^k, they are
* merged to a size-2^(k+1) list as soon as we have 2^k following elements.
*
* Thus, it will avoid cache thrashing as long as 3*2^k elements can
* fit into the cache. Not quite as good as a fully-eager bottom-up
* mergesort, but it does use 0.2*n fewer comparisons, so is faster in
* the common case that everything fits into L1.
*
*
* The merging is controlled by "count", the number of elements in the
* pending lists. This is beautifully simple code, but rather subtle.
*
* Each time we increment "count", we set one bit (bit k) and clear
* bits k-1 .. 0. Each time this happens (except the very first time
* for each bit, when count increments to 2^k), we merge two lists of
* size 2^k into one list of size 2^(k+1).
*
* This merge happens exactly when the count reaches an odd multiple of
* 2^k, which is when we have 2^k elements pending in smaller lists,
* so it's safe to merge away two lists of size 2^k.
*
* After this happens twice, we have created two lists of size 2^(k+1),
* which will be merged into a list of size 2^(k+2) before we create
* a third list of size 2^(k+1), so there are never more than two pending.
*
* The number of pending lists of size 2^k is determined by the
* state of bit k of "count" plus two extra pieces of information:
*
* - The state of bit k-1 (when k == 0, consider bit -1 always set), and
* - Whether the higher-order bits are zero or non-zero (i.e.
* is count >= 2^(k+1)).
*
* There are six states we distinguish. "x" represents some arbitrary
* bits, and "y" represents some arbitrary non-zero bits:
* 0: 00x: 0 pending of size 2^k; x pending of sizes < 2^k
* 1: 01x: 0 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
* 2: x10x: 0 pending of size 2^k; 2^k + x pending of sizes < 2^k
* 3: x11x: 1 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
* 4: y00x: 1 pending of size 2^k; 2^k + x pending of sizes < 2^k
* 5: y01x: 2 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
* (merge and loop back to state 2)
*
* We gain lists of size 2^k in the 2->3 and 4->5 transitions (because
* bit k-1 is set while the more significant bits are non-zero) and
* merge them away in the 5->2 transition. Note in particular that just
* before the 5->2 transition, all lower-order bits are 11 (state 3),
* so there is one list of each smaller size.
*
* When we reach the end of the input, we merge all the pending
* lists, from smallest to largest. If you work through cases 2 to
* 5 above, you can see that the number of elements we merge with a list
* of size 2^k varies from 2^(k-1) (cases 3 and 5 when x == 0) to
* 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1).
*/
__attribute__((nonnull(2,3)))
void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp)
{
struct list_head *list = head->next, *pending = NULL;
size_t count = 0; /* Count of pending */
if (list == head->prev) /* Zero or one elements */
return;
/* Convert to a null-terminated singly-linked list. */
head->prev->next = NULL;
/*
* Data structure invariants:
* - All lists are singly linked and null-terminated; prev
* pointers are not maintained.
* - pending is a prev-linked "list of lists" of sorted
* sublists awaiting further merging.
* - Each of the sorted sublists is power-of-two in size.
* - Sublists are sorted by size and age, smallest & newest at front.
* - There are zero to two sublists of each size.
* - A pair of pending sublists are merged as soon as the number
* of following pending elements equals their size (i.e.
* each time count reaches an odd multiple of that size).
* That ensures each later final merge will be at worst 2:1.
* - Each round consists of:
* - Merging the two sublists selected by the highest bit
* which flips when count is incremented, and
* - Adding an element from the input as a size-1 sublist.
*/
do {
size_t bits;
struct list_head **tail = &pending;
/* Find the least-significant clear bit in count */
for (bits = count; bits & 1; bits >>= 1)
tail = &(*tail)->prev;
/* Do the indicated merge */
if (likely(bits)) {
struct list_head *a = *tail, *b = a->prev;
a = merge(priv, cmp, b, a);
/* Install the merged result in place of the inputs */
a->prev = b->prev;
*tail = a;
}
/* Move one element from input list to pending */
list->prev = pending;
pending = list;
list = list->next;
pending->next = NULL;
count++;
} while (list);
/* End of input; merge together all the pending lists. */
list = pending;
pending = pending->prev;
for (;;) {
struct list_head *next = pending->prev;
if (!next)
break;
list = merge(priv, cmp, pending, list);
pending = next;
}
/* The final merge, rebuilding prev links */
merge_final(priv, cmp, head, pending, list);
}
EXPORT_SYMBOL(list_sort);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015 Linaro Ltd.
* Author: Shannon Zhao <shannon.zhao@linaro.org>
*/
#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/perf/arm_pmu.h>
#include <linux/uaccess.h>
#include <asm/kvm_emulate.h>
#include <kvm/arm_pmu.h>
#include <kvm/arm_vgic.h>
#define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0)
static LIST_HEAD(arm_pmus);
static DEFINE_MUTEX(arm_pmus_lock);
static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc);
static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc);
static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc);
bool kvm_supports_guest_pmuv3(void)
{
guard(mutex)(&arm_pmus_lock);
return !list_empty(&arm_pmus);
}
static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc)
{
return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]);
}
static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx)
{
return &vcpu->arch.pmu.pmc[cnt_idx];
}
static u32 __kvm_pmu_event_mask(unsigned int pmuver)
{
switch (pmuver) {
case ID_AA64DFR0_EL1_PMUVer_IMP:
return GENMASK(9, 0);
case ID_AA64DFR0_EL1_PMUVer_V3P1:
case ID_AA64DFR0_EL1_PMUVer_V3P4:
case ID_AA64DFR0_EL1_PMUVer_V3P5:
case ID_AA64DFR0_EL1_PMUVer_V3P7:
return GENMASK(15, 0);
default: /* Shouldn't be here, just for sanity */
WARN_ONCE(1, "Unknown PMU version %d\n", pmuver);
return 0;
}
}
static u32 kvm_pmu_event_mask(struct kvm *kvm)
{
u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0);
return __kvm_pmu_event_mask(pmuver);
}
u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
{
u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 |
kvm_pmu_event_mask(kvm);
if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL2, IMP))
mask |= ARMV8_PMU_INCLUDE_EL2;
if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP))
mask |= ARMV8_PMU_EXCLUDE_NS_EL0 |
ARMV8_PMU_EXCLUDE_NS_EL1 |
ARMV8_PMU_EXCLUDE_EL3;
return mask;
}
/**
* kvm_pmc_is_64bit - determine if counter is 64bit
* @pmc: counter context
*/
static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (pmc->idx == ARMV8_PMU_CYCLE_IDX ||
kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5));
}
static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 val = kvm_vcpu_read_pmcr(vcpu);
if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return __vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HLP; return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
}
static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc)
{
return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX &&
!kvm_pmc_has_64bit_overflow(pmc));
}
static u32 counter_index_to_reg(u64 idx)
{
return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx;
}
static u32 counter_index_to_evtreg(u64 idx)
{
return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx;
}
static u64 kvm_pmc_read_evtreg(const struct kvm_pmc *pmc)
{
return __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), counter_index_to_evtreg(pmc->idx));
}
static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 counter, reg, enabled, running;
reg = counter_index_to_reg(pmc->idx);
counter = __vcpu_sys_reg(vcpu, reg);
/*
* The real counter value is equal to the value of counter register plus
* the value perf event counts.
*/
if (pmc->perf_event) counter += perf_event_read_value(pmc->perf_event, &enabled,
&running);
if (!kvm_pmc_is_64bit(pmc))
counter = lower_32_bits(counter);
return counter;
}
/**
* kvm_pmu_get_counter_value - get PMU counter value
* @vcpu: The vcpu pointer
* @select_idx: The counter index
*/
u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
{
return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
}
static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 reg;
kvm_pmu_release_perf_event(pmc);
reg = counter_index_to_reg(pmc->idx);
if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX &&
!force) {
/*
* Even with PMUv3p5, AArch32 cannot write to the top
* 32bit of the counters. The only possible course of
* action is to use PMCR.P, which will reset them to
* 0 (the only use of the 'force' parameter).
*/
val = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32);
val |= lower_32_bits(val);
}
__vcpu_sys_reg(vcpu, reg) = val;
/* Recreate the perf event to reflect the updated sample_period */
kvm_pmu_create_perf_event(pmc);
}
/**
* kvm_pmu_set_counter_value - set PMU counter value
* @vcpu: The vcpu pointer
* @select_idx: The counter index
* @val: The counter value
*/
void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
{ kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false);
}
/**
* kvm_pmu_set_counter_value_user - set PMU counter value from user
* @vcpu: The vcpu pointer
* @select_idx: The counter index
* @val: The counter value
*/
void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
{ kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); __vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val; kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
}
/**
* kvm_pmu_release_perf_event - remove the perf event
* @pmc: The PMU counter pointer
*/
static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
{
if (pmc->perf_event) { perf_event_disable(pmc->perf_event);
perf_event_release_kernel(pmc->perf_event);
pmc->perf_event = NULL;
}
}
/**
* kvm_pmu_stop_counter - stop PMU counter
* @pmc: The PMU counter pointer
*
* If this counter has been configured to monitor some event, release it here.
*/
static void kvm_pmu_stop_counter(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 reg, val;
if (!pmc->perf_event)
return;
val = kvm_pmu_get_pmc_value(pmc);
reg = counter_index_to_reg(pmc->idx);
__vcpu_sys_reg(vcpu, reg) = val; kvm_pmu_release_perf_event(pmc);
}
/**
* kvm_pmu_vcpu_init - assign pmu counter idx for cpu
* @vcpu: The vcpu pointer
*
*/
void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
{
int i;
struct kvm_pmu *pmu = &vcpu->arch.pmu;
for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++)
pmu->pmc[i].idx = i;
}
/**
* kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
* @vcpu: The vcpu pointer
*
*/
void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
{
int i;
for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work);
}
static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu)
{
unsigned int hpmn, n;
if (!vcpu_has_nv(vcpu))
return 0;
hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
n = vcpu->kvm->arch.nr_pmu_counters;
/*
* Programming HPMN to a value greater than PMCR_EL0.N is
* CONSTRAINED UNPREDICTABLE. Make the implementation choice that an
* UNKNOWN number of counters (in our case, zero) are reserved for EL2.
*/
if (hpmn >= n)
return 0;
/*
* Programming HPMN=0 is CONSTRAINED UNPREDICTABLE if FEAT_HPMN0 isn't
* implemented. Since KVM's ability to emulate HPMN=0 does not directly
* depend on hardware (all PMU registers are trapped), make the
* implementation choice that all counters are included in the second
* range reserved for EL2/EL3.
*/
return GENMASK(n - 1, hpmn);
}
bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
{
return kvm_pmu_hyp_counter_mask(vcpu) & BIT(idx);
}
u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
{
u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu))
return mask;
return mask & ~kvm_pmu_hyp_counter_mask(vcpu);
}
u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu)
{
u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
if (val == 0)
return BIT(ARMV8_PMU_CYCLE_IDX);
else
return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX);
}
static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc)
{
if (!pmc->perf_event) {
kvm_pmu_create_perf_event(pmc);
return;
}
perf_event_enable(pmc->perf_event);
if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) kvm_debug("fail to enable perf event\n");
}
static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc)
{
if (pmc->perf_event) perf_event_disable(pmc->perf_event);
}
void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val)
{
int i;
if (!val)
return;
for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
if (!(val & BIT(i)))
continue;
if (kvm_pmu_counter_is_enabled(pmc))
kvm_pmc_enable_perf_event(pmc);
else
kvm_pmc_disable_perf_event(pmc);
}
kvm_vcpu_pmu_restore_guest(vcpu);
}
/*
* Returns the PMU overflow state, which is true if there exists an event
* counter where the values of the global enable control, PMOVSSET_EL0[n], and
* PMINTENSET_EL1[n] are all 1.
*/
static bool kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
{ u64 reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
/*
* PMCR_EL0.E is the global enable control for event counters available
* to EL0 and EL1.
*/
if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) reg &= kvm_pmu_hyp_counter_mask(vcpu);
/*
* Otherwise, MDCR_EL2.HPME is the global enable control for event
* counters reserved for EL2.
*/
if (!(vcpu_read_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HPME)) reg &= ~kvm_pmu_hyp_counter_mask(vcpu);
return reg;
}
static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = &vcpu->arch.pmu;
bool overflow;
overflow = kvm_pmu_overflow_status(vcpu);
if (pmu->irq_level == overflow)
return;
pmu->irq_level = overflow;
if (likely(irqchip_in_kernel(vcpu->kvm))) {
int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
pmu->irq_num, overflow, pmu);
WARN_ON(ret);
}
}
bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = &vcpu->arch.pmu;
struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU;
if (likely(irqchip_in_kernel(vcpu->kvm)))
return false;
return pmu->irq_level != run_level;
}
/*
* Reflect the PMU overflow interrupt output level into the kvm_run structure
*/
void kvm_pmu_update_run(struct kvm_vcpu *vcpu)
{
struct kvm_sync_regs *regs = &vcpu->run->s.regs;
/* Populate the timer bitmap for user space */
regs->device_irq_level &= ~KVM_ARM_DEV_PMU;
if (vcpu->arch.pmu.irq_level) regs->device_irq_level |= KVM_ARM_DEV_PMU;
}
/**
* kvm_pmu_flush_hwstate - flush pmu state to cpu
* @vcpu: The vcpu pointer
*
* Check if the PMU has overflowed while we were running in the host, and inject
* an interrupt if that was the case.
*/
void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu)
{ kvm_pmu_update_state(vcpu);
}
/**
* kvm_pmu_sync_hwstate - sync pmu state from cpu
* @vcpu: The vcpu pointer
*
* Check if the PMU has overflowed while we were running in the guest, and
* inject an interrupt if that was the case.
*/
void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
{ kvm_pmu_update_state(vcpu);
}
/*
* When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding
* to the event.
* This is why we need a callback to do it once outside of the NMI context.
*/
static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work)
{
struct kvm_vcpu *vcpu;
vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work);
kvm_vcpu_kick(vcpu);
}
/*
* Perform an increment on any of the counters described in @mask,
* generating the overflow if required, and propagate it as a chained
* event if possible.
*/
static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
unsigned long mask, u32 event)
{
int i;
if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
return;
/* Weed out disabled counters */
mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) {
struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
u64 type, reg;
/* Filter on event type */
type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i)); type &= kvm_pmu_event_mask(vcpu->kvm); if (type != event)
continue;
/* Increment this counter */
reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1; if (!kvm_pmc_is_64bit(pmc))
reg = lower_32_bits(reg);
__vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg;
/* No overflow? move on */
if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg))
continue;
/* Mark overflow */
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(i + 1),
ARMV8_PMUV3_PERFCTR_CHAIN);
}
}
/* Compute the sample period for a given counter value */
static u64 compute_period(struct kvm_pmc *pmc, u64 counter)
{
u64 val;
if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc)) val = (-counter) & GENMASK(63, 0);
else
val = (-counter) & GENMASK(31, 0);
return val;
}
/*
* When the perf event overflows, set the overflow status and inform the vcpu.
*/
static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
struct perf_sample_data *data,
struct pt_regs *regs)
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
int idx = pmc->idx;
u64 period;
cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE);
/*
* Reset the sample period to the architectural limit,
* i.e. the point where the counter overflows.
*/
period = compute_period(pmc, local64_read(&perf_event->count));
local64_set(&perf_event->hw.period_left, 0);
perf_event->attr.sample_period = period;
perf_event->hw.sample_period = period;
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
if (kvm_pmu_counter_can_chain(pmc))
kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
ARMV8_PMUV3_PERFCTR_CHAIN);
if (kvm_pmu_overflow_status(vcpu)) {
kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
if (!in_nmi())
kvm_vcpu_kick(vcpu);
else
irq_work_queue(&vcpu->arch.pmu.overflow_work);
}
cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
}
/**
* kvm_pmu_software_increment - do software increment
* @vcpu: The vcpu pointer
* @val: the value guest writes to PMSWINC register
*/
void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
{
kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR);
}
/**
* kvm_pmu_handle_pmcr - handle PMCR register
* @vcpu: The vcpu pointer
* @val: the value guest writes to PMCR register
*/
void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
{
int i;
/* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */
if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
val &= ~ARMV8_PMU_PMCR_LP;
/* Request a reload of the PMU to enable/disable affected counters */
if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
/* The reset bits don't indicate any state, and shouldn't be saved. */
__vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) {
unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) &
~BIT(ARMV8_PMU_CYCLE_IDX);
if (!vcpu_is_el2(vcpu)) mask &= ~kvm_pmu_hyp_counter_mask(vcpu); for_each_set_bit(i, &mask, 32)
kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true);
}
}
static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)))
return false;
if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx)) return mdcr & MDCR_EL2_HPME; return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E;
}
static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc)
{
u64 evtreg = kvm_pmc_read_evtreg(pmc);
bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0;
bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0;
return u == nsu;
}
static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc)
{
u64 evtreg = kvm_pmc_read_evtreg(pmc);
bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1;
bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1;
return p == nsk;
}
static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD))
return false;
return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2;
}
static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel)
{
struct arm_pmu *pmu = kvm->arch.arm_pmu;
/*
* The CPU PMU likely isn't PMUv3; let the driver provide a mapping
* for the guest's PMUv3 event ID.
*/
if (unlikely(pmu->map_pmuv3_event))
return pmu->map_pmuv3_event(eventsel);
return eventsel;
}
/**
* kvm_pmu_create_perf_event - create a perf event for a counter
* @pmc: Counter context
*/
static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
struct perf_event *event;
struct perf_event_attr attr;
int eventsel;
u64 evtreg;
evtreg = kvm_pmc_read_evtreg(pmc); kvm_pmu_stop_counter(pmc); if (pmc->idx == ARMV8_PMU_CYCLE_IDX)
eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES;
else
eventsel = evtreg & kvm_pmu_event_mask(vcpu->kvm);
/*
* Neither SW increment nor chained events need to be backed
* by a perf event.
*/
if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR ||
eventsel == ARMV8_PMUV3_PERFCTR_CHAIN)
return;
/*
* If we have a filter in place and that the event isn't allowed, do
* not install a perf event either.
*/
if (vcpu->kvm->arch.pmu_filter &&
!test_bit(eventsel, vcpu->kvm->arch.pmu_filter))
return;
/*
* Don't create an event if we're running on hardware that requires
* PMUv3 event translation and we couldn't find a valid mapping.
*/
eventsel = kvm_map_pmu_event(vcpu->kvm, eventsel); if (eventsel < 0)
return;
memset(&attr, 0, sizeof(struct perf_event_attr));
attr.type = arm_pmu->pmu.type;
attr.size = sizeof(attr);
attr.pinned = 1;
attr.disabled = !kvm_pmu_counter_is_enabled(pmc);
attr.exclude_user = !kvm_pmc_counts_at_el0(pmc);
attr.exclude_hv = 1; /* Don't count EL2 events */
attr.exclude_host = 1; /* Don't count host events */
attr.config = eventsel;
/*
* Filter events at EL1 (i.e. vEL2) when in a hyp context based on the
* guest's EL2 filter.
*/
if (unlikely(is_hyp_ctxt(vcpu)))
attr.exclude_kernel = !kvm_pmc_counts_at_el2(pmc);
else
attr.exclude_kernel = !kvm_pmc_counts_at_el1(pmc);
/*
* If counting with a 64bit counter, advertise it to the perf
* code, carefully dealing with the initial sample period
* which also depends on the overflow.
*/
if (kvm_pmc_is_64bit(pmc))
attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT;
attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc));
event = perf_event_create_kernel_counter(&attr, -1, current,
kvm_pmu_perf_overflow, pmc);
if (IS_ERR(event)) {
pr_err_once("kvm: pmu event creation failed %ld\n",
PTR_ERR(event));
return;
}
pmc->perf_event = event;
}
/**
* kvm_pmu_set_counter_event_type - set selected counter to monitor some event
* @vcpu: The vcpu pointer
* @data: The data guest writes to PMXEVTYPER_EL0
* @select_idx: The number of selected counter
*
* When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
* event with given hardware event number. Here we call perf_event API to
* emulate this action and create a kernel perf event for it.
*/
void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
u64 select_idx)
{
struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx);
u64 reg;
reg = counter_index_to_evtreg(pmc->idx);
__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
kvm_pmu_create_perf_event(pmc);
}
void kvm_host_pmu_init(struct arm_pmu *pmu)
{
struct arm_pmu_entry *entry;
/*
* Check the sanitised PMU version for the system, as KVM does not
* support implementations where PMUv3 exists on a subset of CPUs.
*/
if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit()))
return;
guard(mutex)(&arm_pmus_lock);
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return;
entry->arm_pmu = pmu;
list_add_tail(&entry->entry, &arm_pmus);
}
static struct arm_pmu *kvm_pmu_probe_armpmu(void)
{
struct arm_pmu_entry *entry;
struct arm_pmu *pmu;
int cpu;
guard(mutex)(&arm_pmus_lock);
/*
* It is safe to use a stale cpu to iterate the list of PMUs so long as
* the same value is used for the entirety of the loop. Given this, and
* the fact that no percpu data is used for the lookup there is no need
* to disable preemption.
*
* It is still necessary to get a valid cpu, though, to probe for the
* default PMU instance as userspace is not required to specify a PMU
* type. In order to uphold the preexisting behavior KVM selects the
* PMU instance for the core during vcpu init. A dependent use
* case would be a user with disdain of all things big.LITTLE that
* affines the VMM to a particular cluster of cores.
*
* In any case, userspace should just do the sane thing and use the UAPI
* to select a PMU type directly. But, be wary of the baggage being
* carried here.
*/
cpu = raw_smp_processor_id();
list_for_each_entry(entry, &arm_pmus, entry) {
pmu = entry->arm_pmu;
if (cpumask_test_cpu(cpu, &pmu->supported_cpus))
return pmu;
}
return NULL;
}
static u64 __compute_pmceid(struct arm_pmu *pmu, bool pmceid1)
{
u32 hi[2], lo[2];
bitmap_to_arr32(lo, pmu->pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
bitmap_to_arr32(hi, pmu->pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
return ((u64)hi[pmceid1] << 32) | lo[pmceid1];
}
static u64 compute_pmceid0(struct arm_pmu *pmu)
{
u64 val = __compute_pmceid(pmu, 0);
/* always support SW_INCR */
val |= BIT(ARMV8_PMUV3_PERFCTR_SW_INCR);
/* always support CHAIN */
val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
return val;
}
static u64 compute_pmceid1(struct arm_pmu *pmu)
{
u64 val = __compute_pmceid(pmu, 1);
/*
* Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
* as RAZ
*/
val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
return val;
}
u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
{
struct arm_pmu *cpu_pmu = vcpu->kvm->arch.arm_pmu;
unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
u64 val, mask = 0;
int base, i, nr_events;
if (!pmceid1) {
val = compute_pmceid0(cpu_pmu);
base = 0;
} else {
val = compute_pmceid1(cpu_pmu);
base = 32;
}
if (!bmap)
return val;
nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
for (i = 0; i < 32; i += 8) {
u64 byte;
byte = bitmap_get_value8(bmap, base + i);
mask |= byte << i;
if (nr_events >= (0x4000 + base + 32)) {
byte = bitmap_get_value8(bmap, 0x4000 + base + i);
mask |= byte << (32 + i);
}
}
return val & mask;
}
void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
{
u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
kvm_pmu_reprogram_counter_mask(vcpu, mask);
}
int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
{ if (!vcpu->arch.pmu.created)
return -EINVAL;
/*
* A valid interrupt configuration for the PMU is either to have a
* properly configured interrupt number and using an in-kernel
* irqchip, or to not have an in-kernel GIC and not set an IRQ.
*/
if (irqchip_in_kernel(vcpu->kvm)) {
int irq = vcpu->arch.pmu.irq_num;
/*
* If we are using an in-kernel vgic, at this point we know
* the vgic will be initialized, so we can check the PMU irq
* number against the dimensions of the vgic and make sure
* it's valid.
*/
if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq))
return -EINVAL;
} else if (kvm_arm_pmu_irq_initialized(vcpu)) {
return -EINVAL;
}
return 0;
}
static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
{
if (irqchip_in_kernel(vcpu->kvm)) {
int ret;
/*
* If using the PMU with an in-kernel virtual GIC
* implementation, we require the GIC to be already
* initialized when initializing the PMU.
*/
if (!vgic_initialized(vcpu->kvm))
return -ENODEV;
if (!kvm_arm_pmu_irq_initialized(vcpu))
return -ENXIO;
ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num,
&vcpu->arch.pmu);
if (ret)
return ret;
}
init_irq_work(&vcpu->arch.pmu.overflow_work,
kvm_pmu_perf_overflow_notify_vcpu);
vcpu->arch.pmu.created = true;
return 0;
}
/*
* For one VM the interrupt type must be same for each vcpu.
* As a PPI, the interrupt number is the same for all vcpus,
* while as an SPI it must be a separate number per vcpu.
*/
static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
{
unsigned long i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu))
continue;
if (irq_is_ppi(irq)) {
if (vcpu->arch.pmu.irq_num != irq)
return false;
} else {
if (vcpu->arch.pmu.irq_num == irq)
return false;
}
}
return true;
}
/**
* kvm_arm_pmu_get_max_counters - Return the max number of PMU counters.
* @kvm: The kvm pointer
*/
u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
{
struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
/*
* PMUv3 requires that all event counters are capable of counting any
* event, though the same may not be true of non-PMUv3 hardware.
*/
if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
return 1;
/*
* The arm_pmu->cntr_mask considers the fixed counter(s) as well.
* Ignore those and return only the general-purpose counters.
*/
return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS);
}
static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr)
{
kvm->arch.nr_pmu_counters = nr;
/* Reset MDCR_EL2.HPMN behind the vcpus' back... */
if (test_bit(KVM_ARM_VCPU_HAS_EL2, kvm->arch.vcpu_features)) {
struct kvm_vcpu *vcpu;
unsigned long i;
kvm_for_each_vcpu(i, vcpu, kvm) { u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
val &= ~MDCR_EL2_HPMN;
val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
}
}
}
static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
{
lockdep_assert_held(&kvm->arch.config_lock);
kvm->arch.arm_pmu = arm_pmu;
kvm_arm_set_nr_counters(kvm, kvm_arm_pmu_get_max_counters(kvm));
}
/**
* kvm_arm_set_default_pmu - No PMU set, get the default one.
* @kvm: The kvm pointer
*
* The observant among you will notice that the supported_cpus
* mask does not get updated for the default PMU even though it
* is quite possible the selected instance supports only a
* subset of cores in the system. This is intentional, and
* upholds the preexisting behavior on heterogeneous systems
* where vCPUs can be scheduled on any core but the guest
* counters could stop working.
*/
int kvm_arm_set_default_pmu(struct kvm *kvm)
{ struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu(); if (!arm_pmu)
return -ENODEV;
kvm_arm_set_pmu(kvm, arm_pmu);
return 0;
}
static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
{
struct kvm *kvm = vcpu->kvm;
struct arm_pmu_entry *entry;
struct arm_pmu *arm_pmu;
int ret = -ENXIO;
lockdep_assert_held(&kvm->arch.config_lock);
mutex_lock(&arm_pmus_lock);
list_for_each_entry(entry, &arm_pmus, entry) {
arm_pmu = entry->arm_pmu;
if (arm_pmu->pmu.type == pmu_id) { if (kvm_vm_has_ran_once(kvm) || (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) {
ret = -EBUSY;
break;
}
kvm_arm_set_pmu(kvm, arm_pmu);
cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus);
ret = 0;
break;
}
}
mutex_unlock(&arm_pmus_lock);
return ret;
}
static int kvm_arm_pmu_v3_set_nr_counters(struct kvm_vcpu *vcpu, unsigned int n)
{
struct kvm *kvm = vcpu->kvm;
if (!kvm->arch.arm_pmu)
return -EINVAL;
if (n > kvm_arm_pmu_get_max_counters(kvm))
return -EINVAL;
kvm_arm_set_nr_counters(kvm, n);
return 0;
}
int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
struct kvm *kvm = vcpu->kvm;
lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vcpu_has_pmu(vcpu))
return -ENODEV;
if (vcpu->arch.pmu.created)
return -EBUSY;
switch (attr->attr) {
case KVM_ARM_VCPU_PMU_V3_IRQ: {
int __user *uaddr = (int __user *)(long)attr->addr;
int irq;
if (!irqchip_in_kernel(kvm))
return -EINVAL;
if (get_user(irq, uaddr))
return -EFAULT;
/* The PMU overflow interrupt can be a PPI or a valid SPI. */
if (!(irq_is_ppi(irq) || irq_is_spi(irq)))
return -EINVAL;
if (!pmu_irq_is_valid(kvm, irq))
return -EINVAL;
if (kvm_arm_pmu_irq_initialized(vcpu))
return -EBUSY;
kvm_debug("Set kvm ARM PMU irq: %d\n", irq);
vcpu->arch.pmu.irq_num = irq;
return 0;
}
case KVM_ARM_VCPU_PMU_V3_FILTER: {
u8 pmuver = kvm_arm_pmu_get_pmuver_limit();
struct kvm_pmu_event_filter __user *uaddr;
struct kvm_pmu_event_filter filter;
int nr_events;
/*
* Allow userspace to specify an event filter for the entire
* event range supported by PMUVer of the hardware, rather
* than the guest's PMUVer for KVM backward compatibility.
*/
nr_events = __kvm_pmu_event_mask(pmuver) + 1;
uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;
if (copy_from_user(&filter, uaddr, sizeof(filter)))
return -EFAULT;
if (((u32)filter.base_event + filter.nevents) > nr_events || (filter.action != KVM_PMU_EVENT_ALLOW &&
filter.action != KVM_PMU_EVENT_DENY))
return -EINVAL;
if (kvm_vm_has_ran_once(kvm))
return -EBUSY;
if (!kvm->arch.pmu_filter) {
kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
if (!kvm->arch.pmu_filter)
return -ENOMEM;
/*
* The default depends on the first applied filter.
* If it allows events, the default is to deny.
* Conversely, if the first filter denies a set of
* events, the default is to allow.
*/
if (filter.action == KVM_PMU_EVENT_ALLOW)
bitmap_zero(kvm->arch.pmu_filter, nr_events);
else
bitmap_fill(kvm->arch.pmu_filter, nr_events);
}
if (filter.action == KVM_PMU_EVENT_ALLOW)
bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents);
else
bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents);
return 0;
}
case KVM_ARM_VCPU_PMU_V3_SET_PMU: {
int __user *uaddr = (int __user *)(long)attr->addr;
int pmu_id;
if (get_user(pmu_id, uaddr))
return -EFAULT;
return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id);
}
case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: {
unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr;
unsigned int n;
if (get_user(n, uaddr))
return -EFAULT;
return kvm_arm_pmu_v3_set_nr_counters(vcpu, n);
}
case KVM_ARM_VCPU_PMU_V3_INIT:
return kvm_arm_pmu_v3_init(vcpu);
}
return -ENXIO;
}
int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{ switch (attr->attr) {
case KVM_ARM_VCPU_PMU_V3_IRQ: {
int __user *uaddr = (int __user *)(long)attr->addr;
int irq;
if (!irqchip_in_kernel(vcpu->kvm))
return -EINVAL;
if (!kvm_vcpu_has_pmu(vcpu))
return -ENODEV;
if (!kvm_arm_pmu_irq_initialized(vcpu))
return -ENXIO;
irq = vcpu->arch.pmu.irq_num;
return put_user(irq, uaddr);
}
}
return -ENXIO;
}
int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{ switch (attr->attr) {
case KVM_ARM_VCPU_PMU_V3_IRQ:
case KVM_ARM_VCPU_PMU_V3_INIT:
case KVM_ARM_VCPU_PMU_V3_FILTER:
case KVM_ARM_VCPU_PMU_V3_SET_PMU:
case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS:
if (kvm_vcpu_has_pmu(vcpu))
return 0;
}
return -ENXIO;
}
u8 kvm_arm_pmu_get_pmuver_limit(void)
{
unsigned int pmuver;
pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer,
read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1));
/*
* Spoof a barebones PMUv3 implementation if the system supports IMPDEF
* traps of the PMUv3 sysregs
*/
if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
return ID_AA64DFR0_EL1_PMUVer_IMP;
/*
* Otherwise, treat IMPLEMENTATION DEFINED functionality as
* unimplemented
*/
if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
return 0;
return min(pmuver, ID_AA64DFR0_EL1_PMUVer_V3P5);
}
/**
* kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU
* @vcpu: The vcpu pointer
*/
u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
{ u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
u64 n = vcpu->kvm->arch.nr_pmu_counters;
if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu)) n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
}
void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu)
{
bool reprogrammed = false;
unsigned long mask;
int i;
mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
for_each_set_bit(i, &mask, 32) {
struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
/*
* We only need to reconfigure events where the filter is
* different at EL1 vs. EL2, as we're multiplexing the true EL1
* event filter bit for nested.
*/
if (kvm_pmc_counts_at_el1(pmc) == kvm_pmc_counts_at_el2(pmc))
continue;
kvm_pmu_create_perf_event(pmc);
reprogrammed = true;
}
if (reprogrammed)
kvm_vcpu_pmu_restore_guest(vcpu);
}
// SPDX-License-Identifier: GPL-2.0
/*
* Hyp portion of the (not much of an) Emulation layer for 32bit guests.
*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* based on arch/arm/kvm/emulate.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
/*
* stolen from arch/arm/kernel/opcodes.c
*
* condition code lookup table
* index into the table is test code: EQ, NE, ... LT, GT, AL, NV
*
* bit position in short is condition code: NZCV
*/
static const unsigned short cc_map[16] = {
0xF0F0, /* EQ == Z set */
0x0F0F, /* NE */
0xCCCC, /* CS == C set */
0x3333, /* CC */
0xFF00, /* MI == N set */
0x00FF, /* PL */
0xAAAA, /* VS == V set */
0x5555, /* VC */
0x0C0C, /* HI == C set && Z clear */
0xF3F3, /* LS == C clear || Z set */
0xAA55, /* GE == (N==V) */
0x55AA, /* LT == (N!=V) */
0x0A05, /* GT == (!Z && (N==V)) */
0xF5FA, /* LE == (Z || (N!=V)) */
0xFFFF, /* AL always */
0 /* NV */
};
/*
* Check if a trapped instruction should have been executed or not.
*/
bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
{
unsigned long cpsr;
u32 cpsr_cond;
int cond;
/*
* These are the exception classes that could fire with a
* conditional instruction.
*/
switch (kvm_vcpu_trap_get_class(vcpu)) {
case ESR_ELx_EC_CP15_32:
case ESR_ELx_EC_CP15_64:
case ESR_ELx_EC_CP14_MR:
case ESR_ELx_EC_CP14_LS:
case ESR_ELx_EC_FP_ASIMD:
case ESR_ELx_EC_CP10_ID:
case ESR_ELx_EC_CP14_64:
case ESR_ELx_EC_SVC32:
break;
default:
return true;
}
/* Is condition field valid? */
cond = kvm_vcpu_get_condition(vcpu);
if (cond == 0xE)
return true;
cpsr = *vcpu_cpsr(vcpu);
if (cond < 0) {
/* This can happen in Thumb mode: examine IT state. */
unsigned long it;
it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
/* it == 0 => unconditional. */
if (it == 0)
return true;
/* The cond for this insn works out as the top 4 bits. */
cond = (it >> 4);
}
cpsr_cond = cpsr >> 28;
if (!((cc_map[cond] >> cpsr_cond) & 1))
return false;
return true;
}
/**
* kvm_adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
* @vcpu: The VCPU pointer
*
* When exceptions occur while instructions are executed in Thumb IF-THEN
* blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
* to do this little bit of work manually. The fields map like this:
*
* IT[7:0] -> CPSR[26:25],CPSR[15:10]
*/
static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
{
unsigned long itbits, cond;
unsigned long cpsr = *vcpu_cpsr(vcpu);
bool is_arm = !(cpsr & PSR_AA32_T_BIT);
if (is_arm || !(cpsr & PSR_AA32_IT_MASK))
return;
cond = (cpsr & 0xe000) >> 13;
itbits = (cpsr & 0x1c00) >> (10 - 2);
itbits |= (cpsr & (0x3 << 25)) >> 25;
/* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */
if ((itbits & 0x7) == 0)
itbits = cond = 0;
else
itbits = (itbits << 1) & 0x1f;
cpsr &= ~PSR_AA32_IT_MASK;
cpsr |= cond << 13;
cpsr |= (itbits & 0x1c) << (10 - 2);
cpsr |= (itbits & 0x3) << 25;
*vcpu_cpsr(vcpu) = cpsr;
}
/**
* kvm_skip_instr32 - skip a trapped instruction and proceed to the next
* @vcpu: The vcpu pointer
*/
void kvm_skip_instr32(struct kvm_vcpu *vcpu)
{
u32 pc = *vcpu_pc(vcpu);
bool is_thumb;
is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
if (is_thumb && !kvm_vcpu_trap_il_is32bit(vcpu))
pc += 2;
else
pc += 4;
*vcpu_pc(vcpu) = pc;
kvm_adjust_itstate(vcpu);
}
// SPDX-License-Identifier: GPL-2.0
/*
* VMID allocator.
*
* Based on Arm64 ASID allocator algorithm.
* Please refer arch/arm64/mm/context.c for detailed
* comments on algorithm.
*
* Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
unsigned int __ro_after_init kvm_arm_vmid_bits;
static DEFINE_RAW_SPINLOCK(cpu_vmid_lock);
static atomic64_t vmid_generation;
static unsigned long *vmid_map;
static DEFINE_PER_CPU(atomic64_t, active_vmids);
static DEFINE_PER_CPU(u64, reserved_vmids);
#define VMID_MASK (~GENMASK(kvm_arm_vmid_bits - 1, 0))
#define VMID_FIRST_VERSION (1UL << kvm_arm_vmid_bits)
#define NUM_USER_VMIDS VMID_FIRST_VERSION
#define vmid2idx(vmid) ((vmid) & ~VMID_MASK)
#define idx2vmid(idx) vmid2idx(idx)
/*
* As vmid #0 is always reserved, we will never allocate one
* as below and can be treated as invalid. This is used to
* set the active_vmids on vCPU schedule out.
*/
#define VMID_ACTIVE_INVALID VMID_FIRST_VERSION
#define vmid_gen_match(vmid) \
(!(((vmid) ^ atomic64_read(&vmid_generation)) >> kvm_arm_vmid_bits))
static void flush_context(void)
{
int cpu;
u64 vmid;
bitmap_zero(vmid_map, NUM_USER_VMIDS);
for_each_possible_cpu(cpu) {
vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0);
/* Preserve reserved VMID */
if (vmid == 0) vmid = per_cpu(reserved_vmids, cpu);
__set_bit(vmid2idx(vmid), vmid_map);
per_cpu(reserved_vmids, cpu) = vmid;
}
/*
* Unlike ASID allocator, we expect less frequent rollover in
* case of VMIDs. Hence, instead of marking the CPU as
* flush_pending and issuing a local context invalidation on
* the next context-switch, we broadcast TLB flush + I-cache
* invalidation over the inner shareable domain on rollover.
*/
kvm_call_hyp(__kvm_flush_vm_context);
}
static bool check_update_reserved_vmid(u64 vmid, u64 newvmid)
{
int cpu;
bool hit = false;
/*
* Iterate over the set of reserved VMIDs looking for a match
* and update to use newvmid (i.e. the same VMID in the current
* generation).
*/
for_each_possible_cpu(cpu) { if (per_cpu(reserved_vmids, cpu) == vmid) {
hit = true;
per_cpu(reserved_vmids, cpu) = newvmid;
}
}
return hit;
}
static u64 new_vmid(struct kvm_vmid *kvm_vmid)
{
static u32 cur_idx = 1;
u64 vmid = atomic64_read(&kvm_vmid->id);
u64 generation = atomic64_read(&vmid_generation);
if (vmid != 0) {
u64 newvmid = generation | (vmid & ~VMID_MASK);
if (check_update_reserved_vmid(vmid, newvmid)) {
atomic64_set(&kvm_vmid->id, newvmid);
return newvmid;
}
if (!__test_and_set_bit(vmid2idx(vmid), vmid_map)) {
atomic64_set(&kvm_vmid->id, newvmid);
return newvmid;
}
}
vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, cur_idx);
if (vmid != NUM_USER_VMIDS)
goto set_vmid;
/* We're out of VMIDs, so increment the global generation count */
generation = atomic64_add_return_relaxed(VMID_FIRST_VERSION,
&vmid_generation);
flush_context();
/* We have more VMIDs than CPUs, so this will always succeed */
vmid = find_next_zero_bit(vmid_map, NUM_USER_VMIDS, 1);
set_vmid:
__set_bit(vmid, vmid_map);
cur_idx = vmid;
vmid = idx2vmid(vmid) | generation;
atomic64_set(&kvm_vmid->id, vmid);
return vmid;
}
/* Called from vCPU sched out with preemption disabled */
void kvm_arm_vmid_clear_active(void)
{
atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
}
void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
{
unsigned long flags;
u64 vmid, old_active_vmid;
vmid = atomic64_read(&kvm_vmid->id);
/*
* Please refer comments in check_and_switch_context() in
* arch/arm64/mm/context.c.
*
* Unlike ASID allocator, we set the active_vmids to
* VMID_ACTIVE_INVALID on vCPU schedule out to avoid
* reserving the VMID space needlessly on rollover.
* Hence explicitly check here for a "!= 0" to
* handle the sync with a concurrent rollover.
*/
old_active_vmid = atomic64_read(this_cpu_ptr(&active_vmids));
if (old_active_vmid != 0 && vmid_gen_match(vmid) && 0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
old_active_vmid, vmid))
return;
raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
/* Check that our VMID belongs to the current generation. */
vmid = atomic64_read(&kvm_vmid->id);
if (!vmid_gen_match(vmid)) vmid = new_vmid(kvm_vmid);
atomic64_set(this_cpu_ptr(&active_vmids), vmid);
raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
}
/*
* Initialize the VMID allocator
*/
int __init kvm_arm_vmid_alloc_init(void)
{
kvm_arm_vmid_bits = kvm_get_vmid_bits();
/*
* Expect allocation after rollover to fail if we don't have
* at least one more VMID than CPUs. VMID #0 is always reserved.
*/
WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus());
atomic64_set(&vmid_generation, VMID_FIRST_VERSION);
vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL);
if (!vmid_map)
return -ENOMEM;
return 0;
}
void __init kvm_arm_vmid_alloc_free(void)
{
bitmap_free(vmid_map);
}
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
*
* Copyright IBM Corporation, 2008
*
* Author: Dipankar Sarma <dipankar@in.ibm.com>
* Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical algorithm
*
* Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
void rcu_softirq_qs(void);
void rcu_note_context_switch(bool preempt);
int rcu_needs_cpu(void);
void rcu_cpu_stall_reset(void);
void rcu_request_urgent_qs_task(struct task_struct *t);
/*
* Note a virtualization-based context switch. This is simply a
* wrapper around rcu_note_context_switch(), which allows TINY_RCU
* to save a few bytes. The caller must have disabled interrupts.
*/
static inline void rcu_virt_note_context_switch(void)
{
rcu_note_context_switch(false);
}
void synchronize_rcu_expedited(void);
void rcu_barrier(void);
void rcu_momentary_eqs(void);
struct rcu_gp_oldstate {
unsigned long rgos_norm;
unsigned long rgos_exp;
};
// Maximum number of rcu_gp_oldstate values corresponding to
// not-yet-completed RCU grace periods.
#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 4
/**
* same_state_synchronize_rcu_full - Are two old-state values identical?
* @rgosp1: First old-state value.
* @rgosp2: Second old-state value.
*
* The two old-state values must have been obtained from either
* get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
* or get_completed_synchronize_rcu_full(). Returns @true if the two
* values are identical and @false otherwise. This allows structures
* whose lifetimes are tracked by old-state values to push these values
* to a list header, allowing those structures to be slightly smaller.
*
* Note that equality is judged on a bitwise basis, so that an
* @rcu_gp_oldstate structure with an already-completed state in one field
* will compare not-equal to a structure with an already-completed state
* in the other field. After all, the @rcu_gp_oldstate structure is opaque
* so how did such a situation come to pass in the first place?
*/
static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1,
struct rcu_gp_oldstate *rgosp2)
{
return rgosp1->rgos_norm == rgosp2->rgos_norm && rgosp1->rgos_exp == rgosp2->rgos_exp;
}
unsigned long start_poll_synchronize_rcu_expedited(void);
void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
void cond_synchronize_rcu_expedited(unsigned long oldstate);
void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
unsigned long get_state_synchronize_rcu(void);
void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
unsigned long start_poll_synchronize_rcu(void);
void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
bool poll_state_synchronize_rcu(unsigned long oldstate);
bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
void cond_synchronize_rcu(unsigned long oldstate);
void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
#ifdef CONFIG_PROVE_RCU
void rcu_irq_exit_check_preempt(void);
#else
static inline void rcu_irq_exit_check_preempt(void) { }
#endif
struct task_struct;
void rcu_preempt_deferred_qs(struct task_struct *t);
void exit_rcu(void);
void rcu_scheduler_starting(void);
extern int rcu_scheduler_active;
void rcu_end_inkernel_boot(void);
bool rcu_inkernel_boot_has_ended(void);
bool rcu_is_watching(void);
#ifndef CONFIG_PREEMPT_RCU
void rcu_all_qs(void);
#endif
/* RCUtree hotplug events */
int rcutree_prepare_cpu(unsigned int cpu);
int rcutree_online_cpu(unsigned int cpu);
void rcutree_report_cpu_starting(unsigned int cpu);
#ifdef CONFIG_HOTPLUG_CPU
int rcutree_dead_cpu(unsigned int cpu);
int rcutree_dying_cpu(unsigned int cpu);
int rcutree_offline_cpu(unsigned int cpu);
#else
#define rcutree_dead_cpu NULL
#define rcutree_dying_cpu NULL
#define rcutree_offline_cpu NULL
#endif
void rcutree_migrate_callbacks(int cpu);
/* Called from hotplug and also arm64 early secondary boot failure */
void rcutree_report_cpu_dead(void);
#endif /* __LINUX_RCUTREE_H */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Access vector cache interface for object managers.
*
* Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
*/
#ifndef _SELINUX_AVC_H_
#define _SELINUX_AVC_H_
#include <linux/stddef.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kdev_t.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/audit.h>
#include <linux/lsm_audit.h>
#include <linux/in6.h>
#include "flask.h"
#include "av_permissions.h"
#include "security.h"
/*
* An entry in the AVC.
*/
struct avc_entry;
struct task_struct;
struct inode;
struct sock;
struct sk_buff;
/*
* AVC statistics
*/
struct avc_cache_stats {
unsigned int lookups;
unsigned int misses;
unsigned int allocations;
unsigned int reclaims;
unsigned int frees;
};
/*
* We only need this data after we have decided to send an audit message.
*/
struct selinux_audit_data {
u32 ssid;
u32 tsid;
u16 tclass;
u32 requested;
u32 audited;
u32 denied;
int result;
} __randomize_layout;
/*
* AVC operations
*/
void __init avc_init(void);
static inline u32 avc_audit_required(u32 requested, struct av_decision *avd,
int result, u32 auditdeny, u32 *deniedp)
{
u32 denied, audited;
denied = requested & ~avd->allowed;
if (unlikely(denied)) {
audited = denied & avd->auditdeny;
/*
* auditdeny is TRICKY! Setting a bit in
* this field means that ANY denials should NOT be audited if
* the policy contains an explicit dontaudit rule for that
* permission. Take notice that this is unrelated to the
* actual permissions that were denied. As an example lets
* assume:
*
* denied == READ
* avd.auditdeny & ACCESS == 0 (not set means explicit rule)
* auditdeny & ACCESS == 1
*
* We will NOT audit the denial even though the denied
* permission was READ and the auditdeny checks were for
* ACCESS
*/
if (auditdeny && !(auditdeny & avd->auditdeny))
audited = 0;
} else if (result)
audited = denied = requested;
else
audited = requested & avd->auditallow;
*deniedp = denied;
return audited;
}
int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited,
u32 denied, int result, struct common_audit_data *a);
/**
* avc_audit - Audit the granting or denial of permissions.
* @ssid: source security identifier
* @tsid: target security identifier
* @tclass: target security class
* @requested: requested permissions
* @avd: access vector decisions
* @result: result from avc_has_perm_noaudit
* @a: auxiliary audit data
*
* Audit the granting or denial of permissions in accordance
* with the policy. This function is typically called by
* avc_has_perm() after a permission check, but can also be
* called directly by callers who use avc_has_perm_noaudit()
* in order to separate the permission check from the auditing.
* For example, this separation is useful when the permission check must
* be performed under a lock, to allow the lock to be released
* before calling the auditing code.
*/
static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
struct av_decision *avd, int result,
struct common_audit_data *a)
{
u32 audited, denied;
audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited))
return 0;
return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied,
result, a);
}
#define AVC_STRICT 1 /* Ignore permissive mode. */
#define AVC_EXTENDED_PERMS 2 /* update extended permissions */
int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
unsigned int flags, struct av_decision *avd);
int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested,
struct common_audit_data *auditdata);
#define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */
#define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */
int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
u8 driver, u8 base_perm, u8 perm,
struct common_audit_data *ad);
u32 avc_policy_seqno(void);
#define AVC_CALLBACK_GRANT 1
#define AVC_CALLBACK_TRY_REVOKE 2
#define AVC_CALLBACK_REVOKE 4
#define AVC_CALLBACK_RESET 8
#define AVC_CALLBACK_AUDITALLOW_ENABLE 16
#define AVC_CALLBACK_AUDITALLOW_DISABLE 32
#define AVC_CALLBACK_AUDITDENY_ENABLE 64
#define AVC_CALLBACK_AUDITDENY_DISABLE 128
#define AVC_CALLBACK_ADD_XPERMS 256
int avc_add_callback(int (*callback)(u32 event), u32 events);
/* Exported to selinuxfs */
int avc_get_hash_stats(char *page);
unsigned int avc_get_cache_threshold(void);
void avc_set_cache_threshold(unsigned int cache_threshold);
#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats);
#endif
#endif /* _SELINUX_AVC_H_ */
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/anon_inodes.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
*
* Thanks to Arnd Bergmann for code review and suggestions.
* More changes for Thomas Gleixner suggestions.
*
*/
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/magic.h>
#include <linux/anon_inodes.h>
#include <linux/pseudo_fs.h>
#include <linux/uaccess.h>
static struct vfsmount *anon_inode_mnt __ro_after_init;
static struct inode *anon_inode_inode __ro_after_init;
/*
* anon_inodefs_dname() is called from d_path().
*/
static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen)
{
return dynamic_dname(buffer, buflen, "anon_inode:%s",
dentry->d_name.name);
}
static const struct dentry_operations anon_inodefs_dentry_operations = {
.d_dname = anon_inodefs_dname,
};
static int anon_inodefs_init_fs_context(struct fs_context *fc)
{
struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC);
if (!ctx)
return -ENOMEM;
ctx->dops = &anon_inodefs_dentry_operations;
return 0;
}
static struct file_system_type anon_inode_fs_type = {
.name = "anon_inodefs",
.init_fs_context = anon_inodefs_init_fs_context,
.kill_sb = kill_anon_super,
};
static struct inode *anon_inode_make_secure_inode(
const char *name,
const struct inode *context_inode)
{
struct inode *inode;
int error;
inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
if (IS_ERR(inode))
return inode;
inode->i_flags &= ~S_PRIVATE;
error = security_inode_init_security_anon(inode, &QSTR(name),
context_inode);
if (error) {
iput(inode);
return ERR_PTR(error);
}
return inode;
}
static struct file *__anon_inode_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode,
bool make_inode)
{
struct inode *inode;
struct file *file;
if (fops->owner && !try_module_get(fops->owner))
return ERR_PTR(-ENOENT);
if (make_inode) {
inode = anon_inode_make_secure_inode(name, context_inode);
if (IS_ERR(inode)) {
file = ERR_CAST(inode);
goto err;
}
} else {
inode = anon_inode_inode;
if (IS_ERR(inode)) {
file = ERR_PTR(-ENODEV);
goto err;
}
/*
* We know the anon_inode inode count is always
* greater than zero, so ihold() is safe.
*/
ihold(inode);
}
file = alloc_file_pseudo(inode, anon_inode_mnt, name,
flags & (O_ACCMODE | O_NONBLOCK), fops);
if (IS_ERR(file))
goto err_iput;
file->f_mapping = inode->i_mapping;
file->private_data = priv;
return file;
err_iput:
iput(inode);
err:
module_put(fops->owner);
return file;
}
/**
* anon_inode_getfile - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
* of the file
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
* All the files created with anon_inode_getfile() will share a single inode,
* hence saving memory and avoiding code duplication for the file/inode/dentry
* setup. Returns the newly created file* or an error pointer.
*/
struct file *anon_inode_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags)
{ return __anon_inode_getfile(name, fops, priv, flags, NULL, false);
}
EXPORT_SYMBOL_GPL(anon_inode_getfile);
/**
* anon_inode_getfile_fmode - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
* of the file
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
* @f_mode: [in] fmode
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
* All the files created with anon_inode_getfile() will share a single inode,
* hence saving memory and avoiding code duplication for the file/inode/dentry
* setup. Allows setting the fmode. Returns the newly created file* or an error
* pointer.
*/
struct file *anon_inode_getfile_fmode(const char *name,
const struct file_operations *fops,
void *priv, int flags, fmode_t f_mode)
{
struct file *file;
file = __anon_inode_getfile(name, fops, priv, flags, NULL, false);
if (!IS_ERR(file))
file->f_mode |= f_mode;
return file;
}
EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode);
/**
* anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new
* !S_PRIVATE anon inode rather than reuse the
* singleton anon inode and calls the
* inode_init_security_anon() LSM hook.
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
* @context_inode:
* [in] the logical relationship with the new inode (optional)
*
* Create a new anonymous inode and file pair. This can be done for two
* reasons:
*
* - for the inode to have its own security context, so that LSMs can enforce
* policy on the inode's creation;
*
* - if the caller needs a unique inode, for example in order to customize
* the size returned by fstat()
*
* The LSM may use @context_inode in inode_init_security_anon(), but a
* reference to it is not held.
*
* Returns the newly created file* or an error pointer.
*/
struct file *anon_inode_create_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode)
{
return __anon_inode_getfile(name, fops, priv, flags,
context_inode, true);
}
EXPORT_SYMBOL_GPL(anon_inode_create_getfile);
static int __anon_inode_getfd(const char *name,
const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode,
bool make_inode)
{
int error, fd;
struct file *file;
error = get_unused_fd_flags(flags);
if (error < 0)
return error;
fd = error;
file = __anon_inode_getfile(name, fops, priv, flags, context_inode,
make_inode);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_put_unused_fd;
}
fd_install(fd, file);
return fd;
err_put_unused_fd:
put_unused_fd(fd);
return error;
}
/**
* anon_inode_getfd - creates a new file instance by hooking it up to
* an anonymous inode and a dentry that describe
* the "class" of the file
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
*
* Creates a new file by hooking it on a single inode. This is
* useful for files that do not need to have a full-fledged inode in
* order to operate correctly. All the files created with
* anon_inode_getfd() will use the same singleton inode, reducing
* memory use and avoiding code duplication for the file/inode/dentry
* setup. Returns a newly created file descriptor or an error code.
*/
int anon_inode_getfd(const char *name, const struct file_operations *fops,
void *priv, int flags)
{ return __anon_inode_getfd(name, fops, priv, flags, NULL, false);
}
EXPORT_SYMBOL_GPL(anon_inode_getfd);
/**
* anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new
* !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls
* the inode_init_security_anon() LSM hook.
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
* @context_inode:
* [in] the logical relationship with the new inode (optional)
*
* Create a new anonymous inode and file pair. This can be done for two
* reasons:
*
* - for the inode to have its own security context, so that LSMs can enforce
* policy on the inode's creation;
*
* - if the caller needs a unique inode, for example in order to customize
* the size returned by fstat()
*
* The LSM may use @context_inode in inode_init_security_anon(), but a
* reference to it is not held.
*
* Returns a newly created file descriptor or an error code.
*/
int anon_inode_create_getfd(const char *name, const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode)
{
return __anon_inode_getfd(name, fops, priv, flags, context_inode, true);
}
static int __init anon_inode_init(void)
{
anon_inode_mnt = kern_mount(&anon_inode_fs_type);
if (IS_ERR(anon_inode_mnt))
panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt));
anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
if (IS_ERR(anon_inode_inode))
panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode));
return 0;
}
fs_initcall(anon_inode_init);
// SPDX-License-Identifier: GPL-2.0
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/memblock.h>
#include <linux/page_ext.h>
#include <linux/memory.h>
#include <linux/vmalloc.h>
#include <linux/kmemleak.h>
#include <linux/page_owner.h>
#include <linux/page_idle.h>
#include <linux/page_table_check.h>
#include <linux/rcupdate.h>
#include <linux/pgalloc_tag.h>
/*
* struct page extension
*
* This is the feature to manage memory for extended data per page.
*
* Until now, we must modify struct page itself to store extra data per page.
* This requires rebuilding the kernel and it is really time consuming process.
* And, sometimes, rebuild is impossible due to third party module dependency.
* At last, enlarging struct page could cause un-wanted system behaviour change.
*
* This feature is intended to overcome above mentioned problems. This feature
* allocates memory for extended data per page in certain place rather than
* the struct page itself. This memory can be accessed by the accessor
* functions provided by this code. During the boot process, it checks whether
* allocation of huge chunk of memory is needed or not. If not, it avoids
* allocating memory at all. With this advantage, we can include this feature
* into the kernel in default and can avoid rebuild and solve related problems.
*
* To help these things to work well, there are two callbacks for clients. One
* is the need callback which is mandatory if user wants to avoid useless
* memory allocation at boot-time. The other is optional, init callback, which
* is used to do proper initialization after memory is allocated.
*
* The need callback is used to decide whether extended memory allocation is
* needed or not. Sometimes users want to deactivate some features in this
* boot and extra memory would be unnecessary. In this case, to avoid
* allocating huge chunk of memory, each clients represent their need of
* extra memory through the need callback. If one of the need callbacks
* returns true, it means that someone needs extra memory so that
* page extension core should allocates memory for page extension. If
* none of need callbacks return true, memory isn't needed at all in this boot
* and page extension core can skip to allocate memory. As result,
* none of memory is wasted.
*
* When need callback returns true, page_ext checks if there is a request for
* extra memory through size in struct page_ext_operations. If it is non-zero,
* extra space is allocated for each page_ext entry and offset is returned to
* user through offset in struct page_ext_operations.
*
* The init callback is used to do proper initialization after page extension
* is completely initialized. In sparse memory system, extra memory is
* allocated some time later than memmap is allocated. In other words, lifetime
* of memory for page extension isn't same with memmap for struct page.
* Therefore, clients can't store extra data until page extension is
* initialized, even if pages are allocated and used freely. This could
* cause inadequate state of extra data per page, so, to prevent it, client
* can utilize this callback to initialize the state of it correctly.
*/
#ifdef CONFIG_SPARSEMEM
#define PAGE_EXT_INVALID (0x1)
#endif
#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
static bool need_page_idle(void)
{
return true;
}
static struct page_ext_operations page_idle_ops __initdata = {
.need = need_page_idle,
.need_shared_flags = true,
};
#endif
static struct page_ext_operations *page_ext_ops[] __initdata = {
#ifdef CONFIG_PAGE_OWNER
&page_owner_ops,
#endif
#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
&page_idle_ops,
#endif
#ifdef CONFIG_MEM_ALLOC_PROFILING
&page_alloc_tagging_ops,
#endif
#ifdef CONFIG_PAGE_TABLE_CHECK
&page_table_check_ops,
#endif
};
unsigned long page_ext_size;
static unsigned long total_usage;
#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
/*
* To ensure correct allocation tagging for pages, page_ext should be available
* before the first page allocation. Otherwise early task stacks will be
* allocated before page_ext initialization and missing tags will be flagged.
*/
bool early_page_ext __meminitdata = true;
#else
bool early_page_ext __meminitdata;
#endif
static int __init setup_early_page_ext(char *str)
{
early_page_ext = true;
return 0;
}
early_param("early_page_ext", setup_early_page_ext);
static bool __init invoke_need_callbacks(void)
{
int i;
int entries = ARRAY_SIZE(page_ext_ops);
bool need = false;
for (i = 0; i < entries; i++) {
if (page_ext_ops[i]->need()) {
if (page_ext_ops[i]->need_shared_flags) {
page_ext_size = sizeof(struct page_ext);
break;
}
}
}
for (i = 0; i < entries; i++) {
if (page_ext_ops[i]->need()) {
page_ext_ops[i]->offset = page_ext_size;
page_ext_size += page_ext_ops[i]->size;
need = true;
}
}
return need;
}
static void __init invoke_init_callbacks(void)
{
int i;
int entries = ARRAY_SIZE(page_ext_ops);
for (i = 0; i < entries; i++) {
if (page_ext_ops[i]->init)
page_ext_ops[i]->init();
}
}
static inline struct page_ext *get_entry(void *base, unsigned long index)
{
return base + page_ext_size * index;
}
#ifndef CONFIG_SPARSEMEM
void __init page_ext_init_flatmem_late(void)
{
invoke_init_callbacks();
}
void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
{
pgdat->node_page_ext = NULL;
}
static struct page_ext *lookup_page_ext(const struct page *page)
{
unsigned long pfn = page_to_pfn(page);
unsigned long index;
struct page_ext *base;
WARN_ON_ONCE(!rcu_read_lock_held());
base = NODE_DATA(page_to_nid(page))->node_page_ext;
/*
* The sanity checks the page allocator does upon freeing a
* page can reach here before the page_ext arrays are
* allocated when feeding a range of pages to the allocator
* for the first time during bootup or memory hotplug.
*/
if (unlikely(!base))
return NULL;
index = pfn - round_down(node_start_pfn(page_to_nid(page)),
MAX_ORDER_NR_PAGES);
return get_entry(base, index);
}
static int __init alloc_node_page_ext(int nid)
{
struct page_ext *base;
unsigned long table_size;
unsigned long nr_pages;
nr_pages = NODE_DATA(nid)->node_spanned_pages;
if (!nr_pages)
return 0;
/*
* Need extra space if node range is not aligned with
* MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm
* checks buddy's status, range could be out of exact node range.
*/
if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) ||
!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
nr_pages += MAX_ORDER_NR_PAGES;
table_size = page_ext_size * nr_pages;
base = memblock_alloc_try_nid(
table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
MEMBLOCK_ALLOC_ACCESSIBLE, nid);
if (!base)
return -ENOMEM;
NODE_DATA(nid)->node_page_ext = base;
total_usage += table_size;
memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE));
return 0;
}
void __init page_ext_init_flatmem(void)
{
int nid, fail;
if (!invoke_need_callbacks())
return;
for_each_online_node(nid) {
fail = alloc_node_page_ext(nid);
if (fail)
goto fail;
}
pr_info("allocated %ld bytes of page_ext\n", total_usage);
return;
fail:
pr_crit("allocation of page_ext failed.\n");
panic("Out of memory");
}
#else /* CONFIG_SPARSEMEM */
static bool page_ext_invalid(struct page_ext *page_ext)
{
return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID);
}
static struct page_ext *lookup_page_ext(const struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
struct page_ext *page_ext = READ_ONCE(section->page_ext);
WARN_ON_ONCE(!rcu_read_lock_held());
/*
* The sanity checks the page allocator does upon freeing a
* page can reach here before the page_ext arrays are
* allocated when feeding a range of pages to the allocator
* for the first time during bootup or memory hotplug.
*/
if (page_ext_invalid(page_ext))
return NULL;
return get_entry(page_ext, pfn);
}
static void *__meminit alloc_page_ext(size_t size, int nid)
{
gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
void *addr = NULL;
addr = alloc_pages_exact_nid(nid, size, flags);
if (addr)
kmemleak_alloc(addr, size, 1, flags);
else
addr = vzalloc_node(size, nid);
if (addr)
memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
return addr;
}
static int __meminit init_section_page_ext(unsigned long pfn, int nid)
{
struct mem_section *section;
struct page_ext *base;
unsigned long table_size;
section = __pfn_to_section(pfn);
if (section->page_ext)
return 0;
table_size = page_ext_size * PAGES_PER_SECTION;
base = alloc_page_ext(table_size, nid);
/*
* The value stored in section->page_ext is (base - pfn)
* and it does not point to the memory block allocated above,
* causing kmemleak false positives.
*/
kmemleak_not_leak(base);
if (!base) {
pr_err("page ext allocation failure\n");
return -ENOMEM;
}
/*
* The passed "pfn" may not be aligned to SECTION. For the calculation
* we need to apply a mask.
*/
pfn &= PAGE_SECTION_MASK;
section->page_ext = (void *)base - page_ext_size * pfn;
total_usage += table_size;
return 0;
}
static void free_page_ext(void *addr)
{
size_t table_size;
struct page *page;
table_size = page_ext_size * PAGES_PER_SECTION;
memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE)));
if (is_vmalloc_addr(addr)) {
vfree(addr);
} else {
page = virt_to_page(addr);
BUG_ON(PageReserved(page));
kmemleak_free(addr);
free_pages_exact(addr, table_size);
}
}
static void __free_page_ext(unsigned long pfn)
{
struct mem_section *ms;
struct page_ext *base;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_ext)
return;
base = READ_ONCE(ms->page_ext);
/*
* page_ext here can be valid while doing the roll back
* operation in online_page_ext().
*/
if (page_ext_invalid(base))
base = (void *)base - PAGE_EXT_INVALID;
WRITE_ONCE(ms->page_ext, NULL);
base = get_entry(base, pfn);
free_page_ext(base);
}
static void __invalidate_page_ext(unsigned long pfn)
{
struct mem_section *ms;
void *val;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_ext)
return;
val = (void *)ms->page_ext + PAGE_EXT_INVALID;
WRITE_ONCE(ms->page_ext, val);
}
static int __meminit online_page_ext(unsigned long start_pfn,
unsigned long nr_pages,
int nid)
{
unsigned long start, end, pfn;
int fail = 0;
start = SECTION_ALIGN_DOWN(start_pfn);
end = SECTION_ALIGN_UP(start_pfn + nr_pages);
if (nid == NUMA_NO_NODE) {
/*
* In this case, "nid" already exists and contains valid memory.
* "start_pfn" passed to us is a pfn which is an arg for
* online__pages(), and start_pfn should exist.
*/
nid = pfn_to_nid(start_pfn);
VM_BUG_ON(!node_online(nid));
}
for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION)
fail = init_section_page_ext(pfn, nid);
if (!fail)
return 0;
/* rollback */
end = pfn - PAGES_PER_SECTION;
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
__free_page_ext(pfn);
return -ENOMEM;
}
static void __meminit offline_page_ext(unsigned long start_pfn,
unsigned long nr_pages)
{
unsigned long start, end, pfn;
start = SECTION_ALIGN_DOWN(start_pfn);
end = SECTION_ALIGN_UP(start_pfn + nr_pages);
/*
* Freeing of page_ext is done in 3 steps to avoid
* use-after-free of it:
* 1) Traverse all the sections and mark their page_ext
* as invalid.
* 2) Wait for all the existing users of page_ext who
* started before invalidation to finish.
* 3) Free the page_ext.
*/
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
__invalidate_page_ext(pfn);
synchronize_rcu();
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
__free_page_ext(pfn);
}
static int __meminit page_ext_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
struct memory_notify *mn = arg;
int ret = 0;
switch (action) {
case MEM_GOING_ONLINE:
ret = online_page_ext(mn->start_pfn,
mn->nr_pages, mn->status_change_nid);
break;
case MEM_OFFLINE:
offline_page_ext(mn->start_pfn,
mn->nr_pages);
break;
case MEM_CANCEL_ONLINE:
offline_page_ext(mn->start_pfn,
mn->nr_pages);
break;
case MEM_GOING_OFFLINE:
break;
case MEM_ONLINE:
case MEM_CANCEL_OFFLINE:
break;
}
return notifier_from_errno(ret);
}
void __init page_ext_init(void)
{
unsigned long pfn;
int nid;
if (!invoke_need_callbacks())
return;
for_each_node_state(nid, N_MEMORY) {
unsigned long start_pfn, end_pfn;
start_pfn = node_start_pfn(nid);
end_pfn = node_end_pfn(nid);
/*
* start_pfn and end_pfn may not be aligned to SECTION and the
* page->flags of out of node pages are not initialized. So we
* scan [start_pfn, the biggest section's pfn < end_pfn) here.
*/
for (pfn = start_pfn; pfn < end_pfn;
pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
if (!pfn_valid(pfn))
continue;
/*
* Nodes's pfns can be overlapping.
* We know some arch can have a nodes layout such as
* -------------pfn-------------->
* N0 | N1 | N2 | N0 | N1 | N2|....
*/
if (pfn_to_nid(pfn) != nid)
continue;
if (init_section_page_ext(pfn, nid))
goto oom;
cond_resched();
}
}
hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI);
pr_info("allocated %ld bytes of page_ext\n", total_usage);
invoke_init_callbacks();
return;
oom:
panic("Out of memory");
}
void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
{
}
#endif
/**
* page_ext_lookup() - Lookup a page extension for a PFN.
* @pfn: PFN of the page we're interested in.
*
* Must be called with RCU read lock taken and @pfn must be valid.
*
* Return: NULL if no page_ext exists for this page.
*/
struct page_ext *page_ext_lookup(unsigned long pfn)
{ return lookup_page_ext(pfn_to_page(pfn));
}
/**
* page_ext_get() - Get the extended information for a page.
* @page: The page we're interested in.
*
* Ensures that the page_ext will remain valid until page_ext_put()
* is called.
*
* Return: NULL if no page_ext exists for this page.
* Context: Any context. Caller may not sleep until they have called
* page_ext_put().
*/
struct page_ext *page_ext_get(const struct page *page)
{
struct page_ext *page_ext;
rcu_read_lock();
page_ext = lookup_page_ext(page);
if (!page_ext) {
rcu_read_unlock();
return NULL;
}
return page_ext;
}
/**
* page_ext_put() - Working with page extended information is done.
* @page_ext: Page extended information received from page_ext_get().
*
* The page extended information of the page may not be valid after this
* function is called.
*
* Return: None.
* Context: Any context with corresponding page_ext_get() is called.
*/
void page_ext_put(struct page_ext *page_ext)
{
if (unlikely(!page_ext))
return;
rcu_read_unlock();
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PAGEMAP_H
#define _LINUX_PAGEMAP_H
/*
* Copyright 1995 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/compiler.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>
struct folio_batch;
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end);
static inline void invalidate_remote_inode(struct inode *inode)
{
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode))
invalidate_mapping_pages(inode->i_mapping, 0, -1);
}
int invalidate_inode_pages2(struct address_space *mapping);
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count);
int filemap_invalidate_pages(struct address_space *mapping,
loff_t pos, loff_t end, bool nowait);
int write_inode_now(struct inode *, int sync);
int filemap_fdatawrite(struct address_space *);
int filemap_flush(struct address_space *);
int filemap_fdatawait_keep_errors(struct address_space *mapping);
int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend);
int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
loff_t start_byte, loff_t end_byte);
int filemap_invalidate_inode(struct inode *inode, bool flush,
loff_t start, loff_t end);
static inline int filemap_fdatawait(struct address_space *mapping)
{
return filemap_fdatawait_range(mapping, 0, LLONG_MAX);
}
bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend);
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
int filemap_check_errors(struct address_space *mapping);
void __filemap_set_wb_err(struct address_space *mapping, int err);
int filemap_fdatawrite_wbc(struct address_space *mapping,
struct writeback_control *wbc);
int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
static inline int filemap_write_and_wait(struct address_space *mapping)
{
return filemap_write_and_wait_range(mapping, 0, LLONG_MAX);
}
/**
* filemap_set_wb_err - set a writeback error on an address_space
* @mapping: mapping in which to set writeback error
* @err: error to be set in mapping
*
* When writeback fails in some way, we must record that error so that
* userspace can be informed when fsync and the like are called. We endeavor
* to report errors on any file that was open at the time of the error. Some
* internal callers also need to know when writeback errors have occurred.
*
* When a writeback error occurs, most filesystems will want to call
* filemap_set_wb_err to record the error in the mapping so that it will be
* automatically reported whenever fsync is called on the file.
*/
static inline void filemap_set_wb_err(struct address_space *mapping, int err)
{
/* Fastpath for common case of no error */
if (unlikely(err))
__filemap_set_wb_err(mapping, err);
}
/**
* filemap_check_wb_err - has an error occurred since the mark was sampled?
* @mapping: mapping to check for writeback errors
* @since: previously-sampled errseq_t
*
* Grab the errseq_t value from the mapping, and see if it has changed "since"
* the given value was sampled.
*
* If it has then report the latest error set, otherwise return 0.
*/
static inline int filemap_check_wb_err(struct address_space *mapping,
errseq_t since)
{
return errseq_check(&mapping->wb_err, since);
}
/**
* filemap_sample_wb_err - sample the current errseq_t to test for later errors
* @mapping: mapping to be sampled
*
* Writeback errors are always reported relative to a particular sample point
* in the past. This function provides those sample points.
*/
static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
{
return errseq_sample(&mapping->wb_err);
}
/**
* file_sample_sb_err - sample the current errseq_t to test for later errors
* @file: file pointer to be sampled
*
* Grab the most current superblock-level errseq_t value for the given
* struct file.
*/
static inline errseq_t file_sample_sb_err(struct file *file)
{
return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
}
/*
* Flush file data before changing attributes. Caller must hold any locks
* required to prevent further writes to this file until we're done setting
* flags.
*/
static inline int inode_drain_writes(struct inode *inode)
{
inode_dio_wait(inode);
return filemap_write_and_wait(inode->i_mapping);
}
static inline bool mapping_empty(struct address_space *mapping)
{
return xa_empty(&mapping->i_pages);
}
/*
* mapping_shrinkable - test if page cache state allows inode reclaim
* @mapping: the page cache mapping
*
* This checks the mapping's cache state for the pupose of inode
* reclaim and LRU management.
*
* The caller is expected to hold the i_lock, but is not required to
* hold the i_pages lock, which usually protects cache state. That's
* because the i_lock and the list_lru lock that protect the inode and
* its LRU state don't nest inside the irq-safe i_pages lock.
*
* Cache deletions are performed under the i_lock, which ensures that
* when an inode goes empty, it will reliably get queued on the LRU.
*
* Cache additions do not acquire the i_lock and may race with this
* check, in which case we'll report the inode as shrinkable when it
* has cache pages. This is okay: the shrinker also checks the
* refcount and the referenced bit, which will be elevated or set in
* the process of adding new cache pages to an inode.
*/
static inline bool mapping_shrinkable(struct address_space *mapping)
{
void *head;
/*
* On highmem systems, there could be lowmem pressure from the
* inodes before there is highmem pressure from the page
* cache. Make inodes shrinkable regardless of cache state.
*/
if (IS_ENABLED(CONFIG_HIGHMEM))
return true;
/* Cache completely empty? Shrink away. */
head = rcu_access_pointer(mapping->i_pages.xa_head);
if (!head)
return true;
/*
* The xarray stores single offset-0 entries directly in the
* head pointer, which allows non-resident page cache entries
* to escape the shadow shrinker's list of xarray nodes. The
* inode shrinker needs to pick them up under memory pressure.
*/
if (!xa_is_node(head) && xa_is_value(head))
return true;
return false;
}
/*
* Bits in mapping->flags.
*/
enum mapping_flags {
AS_EIO = 0, /* IO error on async write */
AS_ENOSPC = 1, /* ENOSPC on async write */
AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */
AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */
AS_EXITING = 4, /* final truncate in progress */
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */
AS_STABLE_WRITES = 7, /* must wait for writeback before modifying
folio contents */
AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */
/* Bits 16-25 are used for FOLIO_ORDER */
AS_FOLIO_ORDER_BITS = 5,
AS_FOLIO_ORDER_MIN = 16,
AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS,
};
#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1)
#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN)
#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX)
#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK)
/**
* mapping_set_error - record a writeback error in the address_space
* @mapping: the mapping in which an error should be set
* @error: the error to set in the mapping
*
* When writeback fails in some way, we must record that error so that
* userspace can be informed when fsync and the like are called. We endeavor
* to report errors on any file that was open at the time of the error. Some
* internal callers also need to know when writeback errors have occurred.
*
* When a writeback error occurs, most filesystems will want to call
* mapping_set_error to record the error in the mapping so that it can be
* reported when the application calls fsync(2).
*/
static inline void mapping_set_error(struct address_space *mapping, int error)
{
if (likely(!error))
return;
/* Record in wb_err for checkers using errseq_t based tracking */
__filemap_set_wb_err(mapping, error);
/* Record it in superblock */
if (mapping->host)
errseq_set(&mapping->host->i_sb->s_wb_err, error);
/* Record it in flags for now, for legacy callers */
if (error == -ENOSPC)
set_bit(AS_ENOSPC, &mapping->flags);
else
set_bit(AS_EIO, &mapping->flags);
}
static inline void mapping_set_unevictable(struct address_space *mapping)
{
set_bit(AS_UNEVICTABLE, &mapping->flags);
}
static inline void mapping_clear_unevictable(struct address_space *mapping)
{
clear_bit(AS_UNEVICTABLE, &mapping->flags);
}
static inline bool mapping_unevictable(struct address_space *mapping)
{
return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags);
}
static inline void mapping_set_exiting(struct address_space *mapping)
{
set_bit(AS_EXITING, &mapping->flags);
}
static inline int mapping_exiting(struct address_space *mapping)
{
return test_bit(AS_EXITING, &mapping->flags);
}
static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
{
set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}
static inline int mapping_use_writeback_tags(struct address_space *mapping)
{
return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}
static inline bool mapping_release_always(const struct address_space *mapping)
{
return test_bit(AS_RELEASE_ALWAYS, &mapping->flags);
}
static inline void mapping_set_release_always(struct address_space *mapping)
{
set_bit(AS_RELEASE_ALWAYS, &mapping->flags);
}
static inline void mapping_clear_release_always(struct address_space *mapping)
{
clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
}
static inline bool mapping_stable_writes(const struct address_space *mapping)
{
return test_bit(AS_STABLE_WRITES, &mapping->flags);
}
static inline void mapping_set_stable_writes(struct address_space *mapping)
{
set_bit(AS_STABLE_WRITES, &mapping->flags);
}
static inline void mapping_clear_stable_writes(struct address_space *mapping)
{
clear_bit(AS_STABLE_WRITES, &mapping->flags);
}
static inline void mapping_set_inaccessible(struct address_space *mapping)
{
/*
* It's expected inaccessible mappings are also unevictable. Compaction
* migrate scanner (isolate_migratepages_block()) relies on this to
* reduce page locking.
*/
set_bit(AS_UNEVICTABLE, &mapping->flags);
set_bit(AS_INACCESSIBLE, &mapping->flags);
}
static inline bool mapping_inaccessible(struct address_space *mapping)
{
return test_bit(AS_INACCESSIBLE, &mapping->flags);
}
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return mapping->gfp_mask;
}
/* Restricts the given gfp_mask to what the mapping allows. */
static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
gfp_t gfp_mask)
{
return mapping_gfp_mask(mapping) & gfp_mask;
}
/*
* This is non-atomic. Only to be used before the mapping is activated.
* Probably needs a barrier...
*/
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
{
m->gfp_mask = mask;
}
/*
* There are some parts of the kernel which assume that PMD entries
* are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then,
* limit the maximum allocation order to PMD size. I'm not aware of any
* assumptions about maximum order if THP are disabled, but 8 seems like
* a good order (that's 1MB if you're using 4kB pages)
*/
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER
#else
#define PREFERRED_MAX_PAGECACHE_ORDER 8
#endif
/*
* xas_split_alloc() does not support arbitrary orders. This implies no
* 512MB THP on ARM64 with 64KB base page size.
*/
#define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1)
#define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
/*
* mapping_max_folio_size_supported() - Check the max folio size supported
*
* The filesystem should call this function at mount time if there is a
* requirement on the folio mapping size in the page cache.
*/
static inline size_t mapping_max_folio_size_supported(void)
{
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
return PAGE_SIZE;
}
/*
* mapping_set_folio_order_range() - Set the orders supported by a file.
* @mapping: The address space of the file.
* @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
* @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
*
* The filesystem should call this function in its inode constructor to
* indicate which base size (min) and maximum size (max) of folio the VFS
* can use to cache the contents of the file. This should only be used
* if the filesystem needs special handling of folio sizes (ie there is
* something the core cannot know).
* Do not tune it based on, eg, i_size.
*
* Context: This should not be called while the inode is active as it
* is non-atomic.
*/
static inline void mapping_set_folio_order_range(struct address_space *mapping,
unsigned int min,
unsigned int max)
{
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return;
if (min > MAX_PAGECACHE_ORDER)
min = MAX_PAGECACHE_ORDER;
if (max > MAX_PAGECACHE_ORDER)
max = MAX_PAGECACHE_ORDER;
if (max < min)
max = min;
mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
(min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX);
}
static inline void mapping_set_folio_min_order(struct address_space *mapping,
unsigned int min)
{
mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
}
/**
* mapping_set_large_folios() - Indicate the file supports large folios.
* @mapping: The address space of the file.
*
* The filesystem should call this function in its inode constructor to
* indicate that the VFS can use large folios to cache the contents of
* the file.
*
* Context: This should not be called while the inode is active as it
* is non-atomic.
*/
static inline void mapping_set_large_folios(struct address_space *mapping)
{
mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER);
}
static inline unsigned int
mapping_max_folio_order(const struct address_space *mapping)
{
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return 0;
return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
}
static inline unsigned int
mapping_min_folio_order(const struct address_space *mapping)
{
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return 0;
return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
}
static inline unsigned long
mapping_min_folio_nrpages(struct address_space *mapping)
{
return 1UL << mapping_min_folio_order(mapping);
}
/**
* mapping_align_index() - Align index for this mapping.
* @mapping: The address_space.
* @index: The page index.
*
* The index of a folio must be naturally aligned. If you are adding a
* new folio to the page cache and need to know what index to give it,
* call this function.
*/
static inline pgoff_t mapping_align_index(struct address_space *mapping,
pgoff_t index)
{
return round_down(index, mapping_min_folio_nrpages(mapping));
}
/*
* Large folio support currently depends on THP. These dependencies are
* being worked on but are not yet fixed.
*/
static inline bool mapping_large_folio_support(struct address_space *mapping)
{
/* AS_FOLIO_ORDER is only reasonable for pagecache folios */
VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON,
"Anonymous mapping always supports large folio");
return mapping_max_folio_order(mapping) > 0;
}
/* Return the maximum folio size for this pagecache mapping, in bytes. */
static inline size_t mapping_max_folio_size(const struct address_space *mapping)
{
return PAGE_SIZE << mapping_max_folio_order(mapping);
}
static inline int filemap_nr_thps(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
return atomic_read(&mapping->nr_thps);
#else
return 0;
#endif
}
static inline void filemap_nr_thps_inc(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
if (!mapping_large_folio_support(mapping))
atomic_inc(&mapping->nr_thps);
#else
WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0);
#endif
}
static inline void filemap_nr_thps_dec(struct address_space *mapping)
{
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps);
#else
WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0);
#endif
}
struct address_space *folio_mapping(struct folio *);
struct address_space *swapcache_mapping(struct folio *);
/**
* folio_flush_mapping - Find the file mapping this folio belongs to.
* @folio: The folio.
*
* For folios which are in the page cache, return the mapping that this
* page belongs to. Anonymous folios return NULL, even if they're in
* the swap cache. Other kinds of folio also return NULL.
*
* This is ONLY used by architecture cache flushing code. If you aren't
* writing cache flushing code, you want either folio_mapping() or
* folio_file_mapping().
*/
static inline struct address_space *folio_flush_mapping(struct folio *folio)
{
if (unlikely(folio_test_swapcache(folio)))
return NULL;
return folio_mapping(folio);
}
/**
* folio_inode - Get the host inode for this folio.
* @folio: The folio.
*
* For folios which are in the page cache, return the inode that this folio
* belongs to.
*
* Do not call this for folios which aren't in the page cache.
*/
static inline struct inode *folio_inode(struct folio *folio)
{
return folio->mapping->host;
}
/**
* folio_attach_private - Attach private data to a folio.
* @folio: Folio to attach data to.
* @data: Data to attach to folio.
*
* Attaching private data to a folio increments the page's reference count.
* The data must be detached before the folio will be freed.
*/
static inline void folio_attach_private(struct folio *folio, void *data)
{
folio_get(folio);
folio->private = data;
folio_set_private(folio);
}
/**
* folio_change_private - Change private data on a folio.
* @folio: Folio to change the data on.
* @data: Data to set on the folio.
*
* Change the private data attached to a folio and return the old
* data. The page must previously have had data attached and the data
* must be detached before the folio will be freed.
*
* Return: Data that was previously attached to the folio.
*/
static inline void *folio_change_private(struct folio *folio, void *data)
{
void *old = folio_get_private(folio);
folio->private = data;
return old;
}
/**
* folio_detach_private - Detach private data from a folio.
* @folio: Folio to detach data from.
*
* Removes the data that was previously attached to the folio and decrements
* the refcount on the page.
*
* Return: Data that was attached to the folio.
*/
static inline void *folio_detach_private(struct folio *folio)
{
void *data = folio_get_private(folio);
if (!folio_test_private(folio))
return NULL;
folio_clear_private(folio);
folio->private = NULL;
folio_put(folio);
return data;
}
static inline void attach_page_private(struct page *page, void *data)
{
folio_attach_private(page_folio(page), data);
}
static inline void *detach_page_private(struct page *page)
{
return folio_detach_private(page_folio(page));
}
#ifdef CONFIG_NUMA
struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
#else
static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
{
return folio_alloc_noprof(gfp, order);
}
#endif
#define filemap_alloc_folio(...) \
alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__))
static inline struct page *__page_cache_alloc(gfp_t gfp)
{
return &filemap_alloc_folio(gfp, 0)->page;
}
static inline gfp_t readahead_gfp_mask(struct address_space *x)
{
return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;
}
typedef int filler_t(struct file *, struct folio *);
pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
/**
* typedef fgf_t - Flags for getting folios from the page cache.
*
* Most users of the page cache will not need to use these flags;
* there are convenience functions such as filemap_get_folio() and
* filemap_lock_folio(). For users which need more control over exactly
* what is done with the folios, these flags to __filemap_get_folio()
* are available.
*
* * %FGP_ACCESSED - The folio will be marked accessed.
* * %FGP_LOCK - The folio is returned locked.
* * %FGP_CREAT - If no folio is present then a new folio is allocated,
* added to the page cache and the VM's LRU list. The folio is
* returned locked.
* * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
* folio is already in cache. If the folio was allocated, unlock it
* before returning so the caller can do the same dance.
* * %FGP_WRITE - The folio will be written to by the caller.
* * %FGP_NOFS - __GFP_FS will get cleared in gfp.
* * %FGP_NOWAIT - Don't block on the folio lock.
* * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
* * %FGP_DONTCACHE - Uncached buffered IO
* * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
* implementation.
*/
typedef unsigned int __bitwise fgf_t;
#define FGP_ACCESSED ((__force fgf_t)0x00000001)
#define FGP_LOCK ((__force fgf_t)0x00000002)
#define FGP_CREAT ((__force fgf_t)0x00000004)
#define FGP_WRITE ((__force fgf_t)0x00000008)
#define FGP_NOFS ((__force fgf_t)0x00000010)
#define FGP_NOWAIT ((__force fgf_t)0x00000020)
#define FGP_FOR_MMAP ((__force fgf_t)0x00000040)
#define FGP_STABLE ((__force fgf_t)0x00000080)
#define FGP_DONTCACHE ((__force fgf_t)0x00000100)
#define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */
#define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
static inline unsigned int filemap_get_order(size_t size)
{
unsigned int shift = ilog2(size);
if (shift <= PAGE_SHIFT)
return 0;
return shift - PAGE_SHIFT;
}
/**
* fgf_set_order - Encode a length in the fgf_t flags.
* @size: The suggested size of the folio to create.
*
* The caller of __filemap_get_folio() can use this to suggest a preferred
* size for the folio that is created. If there is already a folio at
* the index, it will be returned, no matter what its size. If a folio
* is freshly created, it may be of a different size than requested
* due to alignment constraints, memory pressure, or the presence of
* other folios at nearby indices.
*/
static inline fgf_t fgf_set_order(size_t size)
{
unsigned int order = filemap_get_order(size);
if (!order)
return 0;
return (__force fgf_t)(order << 26);
}
void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
fgf_t fgp_flags, gfp_t gfp);
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
fgf_t fgp_flags, gfp_t gfp);
/**
* filemap_get_folio - Find and get a folio.
* @mapping: The address_space to search.
* @index: The page index.
*
* Looks up the page cache entry at @mapping & @index. If a folio is
* present, it is returned with an increased refcount.
*
* Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for
* this index. Will not return a shadow, swap or DAX entry.
*/
static inline struct folio *filemap_get_folio(struct address_space *mapping,
pgoff_t index)
{
return __filemap_get_folio(mapping, index, 0, 0);
}
/**
* filemap_lock_folio - Find and lock a folio.
* @mapping: The address_space to search.
* @index: The page index.
*
* Looks up the page cache entry at @mapping & @index. If a folio is
* present, it is returned locked with an increased refcount.
*
* Context: May sleep.
* Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for
* this index. Will not return a shadow, swap or DAX entry.
*/
static inline struct folio *filemap_lock_folio(struct address_space *mapping,
pgoff_t index)
{
return __filemap_get_folio(mapping, index, FGP_LOCK, 0);
}
/**
* filemap_grab_folio - grab a folio from the page cache
* @mapping: The address space to search
* @index: The page index
*
* Looks up the page cache entry at @mapping & @index. If no folio is found,
* a new folio is created. The folio is locked, marked as accessed, and
* returned.
*
* Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found
* and failed to create a folio.
*/
static inline struct folio *filemap_grab_folio(struct address_space *mapping,
pgoff_t index)
{
return __filemap_get_folio(mapping, index,
FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
mapping_gfp_mask(mapping));
}
/**
* find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
* Otherwise, %NULL is returned.
*/
static inline struct page *find_get_page(struct address_space *mapping,
pgoff_t offset)
{
return pagecache_get_page(mapping, offset, 0, 0);
}
static inline struct page *find_get_page_flags(struct address_space *mapping,
pgoff_t offset, fgf_t fgp_flags)
{
return pagecache_get_page(mapping, offset, fgp_flags, 0);
}
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
* @index: the page index
*
* Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
* Context: May sleep.
* Return: A struct page or %NULL if there is no page in the cache for this
* index.
*/
static inline struct page *find_lock_page(struct address_space *mapping,
pgoff_t index)
{
return pagecache_get_page(mapping, index, FGP_LOCK, 0);
}
/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
* If the page is not present, a new page is allocated using @gfp_mask
* and added to the page cache and the VM's LRU list. The page is
* returned locked and with an increased refcount.
*
* On memory exhaustion, %NULL is returned.
*
* find_or_create_page() may sleep, even if @gfp_flags specifies an
* atomic allocation!
*/
static inline struct page *find_or_create_page(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask)
{
return pagecache_get_page(mapping, index,
FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
gfp_mask);
}
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
* @mapping: target address_space
* @index: the page index
*
* Same as grab_cache_page(), but do not wait if the page is unavailable.
* This is intended for speculative data generators, where the data can
* be regenerated if the page couldn't be grabbed. This routine should
* be safe to call while holding the lock for another page.
*
* Clear __GFP_FS when allocating the page to avoid recursion into the fs
* and deadlock against the caller's locked page.
*/
static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
pgoff_t index)
{
return pagecache_get_page(mapping, index,
FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
mapping_gfp_mask(mapping));
}
extern pgoff_t __folio_swap_cache_index(struct folio *folio);
/**
* folio_index - File index of a folio.
* @folio: The folio.
*
* For a folio which is either in the page cache or the swap cache,
* return its index within the address_space it belongs to. If you know
* the page is definitely in the page cache, you can look at the folio's
* index directly.
*
* Return: The index (offset in units of pages) of a folio in its file.
*/
static inline pgoff_t folio_index(struct folio *folio)
{
if (unlikely(folio_test_swapcache(folio))) return __folio_swap_cache_index(folio);
return folio->index;
}
/**
* folio_next_index - Get the index of the next folio.
* @folio: The current folio.
*
* Return: The index of the folio which follows this folio in the file.
*/
static inline pgoff_t folio_next_index(struct folio *folio)
{
return folio->index + folio_nr_pages(folio);
}
/**
* folio_file_page - The page for a particular index.
* @folio: The folio which contains this index.
* @index: The index we want to look up.
*
* Sometimes after looking up a folio in the page cache, we need to
* obtain the specific page for an index (eg a page fault).
*
* Return: The page containing the file data for this index.
*/
static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
{
return folio_page(folio, index & (folio_nr_pages(folio) - 1));
}
/**
* folio_contains - Does this folio contain this index?
* @folio: The folio.
* @index: The page index within the file.
*
* Context: The caller should have the page locked in order to prevent
* (eg) shmem from moving the page between the page cache and swap cache
* and changing its index in the middle of the operation.
* Return: true or false.
*/
static inline bool folio_contains(struct folio *folio, pgoff_t index)
{
return index - folio_index(folio) < folio_nr_pages(folio);
}
/*
* Given the page we found in the page cache, return the page corresponding
* to this index in the file
*/
static inline struct page *find_subpage(struct page *head, pgoff_t index)
{
/* HugeTLBfs wants the head page regardless */
if (PageHuge(head))
return head;
return head + (index & (thp_nr_pages(head) - 1));
}
unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch);
unsigned filemap_get_folios_contig(struct address_space *mapping,
pgoff_t *start, pgoff_t end, struct folio_batch *fbatch);
unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch);
/*
* Returns locked page at given index in given cache, creating it if needed.
*/
static inline struct page *grab_cache_page(struct address_space *mapping,
pgoff_t index)
{
return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
}
struct folio *read_cache_folio(struct address_space *, pgoff_t index,
filler_t *filler, struct file *file);
struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index,
gfp_t flags);
struct page *read_cache_page(struct address_space *, pgoff_t index,
filler_t *filler, struct file *file);
extern struct page * read_cache_page_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
static inline struct page *read_mapping_page(struct address_space *mapping,
pgoff_t index, struct file *file)
{
return read_cache_page(mapping, index, NULL, file);
}
static inline struct folio *read_mapping_folio(struct address_space *mapping,
pgoff_t index, struct file *file)
{
return read_cache_folio(mapping, index, NULL, file);
}
/**
* page_pgoff - Calculate the logical page offset of this page.
* @folio: The folio containing this page.
* @page: The page which we need the offset of.
*
* For file pages, this is the offset from the beginning of the file
* in units of PAGE_SIZE. For anonymous pages, this is the offset from
* the beginning of the anon_vma in units of PAGE_SIZE. This will
* return nonsense for KSM pages.
*
* Context: Caller must have a reference on the folio or otherwise
* prevent it from being split or freed.
*
* Return: The offset in units of PAGE_SIZE.
*/
static inline pgoff_t page_pgoff(const struct folio *folio,
const struct page *page)
{
return folio->index + folio_page_idx(folio, page);
}
/**
* folio_pos - Returns the byte position of this folio in its file.
* @folio: The folio.
*/
static inline loff_t folio_pos(const struct folio *folio)
{
return ((loff_t)folio->index) * PAGE_SIZE;
}
/*
* Return byte-offset into filesystem object for page.
*/
static inline loff_t page_offset(struct page *page)
{
struct folio *folio = page_folio(page);
return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE;
}
/*
* Get the offset in PAGE_SIZE (even for hugetlb folios).
*/
static inline pgoff_t folio_pgoff(struct folio *folio)
{
return folio->index;
}
static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
unsigned long address)
{
pgoff_t pgoff;
pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
pgoff += vma->vm_pgoff;
return pgoff;
}
struct wait_page_key {
struct folio *folio;
int bit_nr;
int page_match;
};
struct wait_page_queue {
struct folio *folio;
int bit_nr;
wait_queue_entry_t wait;
};
static inline bool wake_page_match(struct wait_page_queue *wait_page,
struct wait_page_key *key)
{
if (wait_page->folio != key->folio)
return false;
key->page_match = 1;
if (wait_page->bit_nr != key->bit_nr)
return false;
return true;
}
void __folio_lock(struct folio *folio);
int __folio_lock_killable(struct folio *folio);
vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf);
void unlock_page(struct page *page);
void folio_unlock(struct folio *folio);
/**
* folio_trylock() - Attempt to lock a folio.
* @folio: The folio to attempt to lock.
*
* Sometimes it is undesirable to wait for a folio to be unlocked (eg
* when the locks are being taken in the wrong order, or if making
* progress through a batch of folios is more important than processing
* them in order). Usually folio_lock() is the correct function to call.
*
* Context: Any context.
* Return: Whether the lock was successfully acquired.
*/
static inline bool folio_trylock(struct folio *folio)
{
return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0)));
}
/*
* Return true if the page was successfully locked
*/
static inline bool trylock_page(struct page *page)
{
return folio_trylock(page_folio(page));
}
/**
* folio_lock() - Lock this folio.
* @folio: The folio to lock.
*
* The folio lock protects against many things, probably more than it
* should. It is primarily held while a folio is being brought uptodate,
* either from its backing file or from swap. It is also held while a
* folio is being truncated from its address_space, so holding the lock
* is sufficient to keep folio->mapping stable.
*
* The folio lock is also held while write() is modifying the page to
* provide POSIX atomicity guarantees (as long as the write does not
* cross a page boundary). Other modifications to the data in the folio
* do not hold the folio lock and can race with writes, eg DMA and stores
* to mapped pages.
*
* Context: May sleep. If you need to acquire the locks of two or
* more folios, they must be in order of ascending index, if they are
* in the same address_space. If they are in different address_spaces,
* acquire the lock of the folio which belongs to the address_space which
* has the lowest address in memory first.
*/
static inline void folio_lock(struct folio *folio)
{
might_sleep();
if (!folio_trylock(folio))
__folio_lock(folio);
}
/**
* lock_page() - Lock the folio containing this page.
* @page: The page to lock.
*
* See folio_lock() for a description of what the lock protects.
* This is a legacy function and new code should probably use folio_lock()
* instead.
*
* Context: May sleep. Pages in the same folio share a lock, so do not
* attempt to lock two pages which share a folio.
*/
static inline void lock_page(struct page *page)
{
struct folio *folio;
might_sleep();
folio = page_folio(page);
if (!folio_trylock(folio))
__folio_lock(folio);
}
/**
* folio_lock_killable() - Lock this folio, interruptible by a fatal signal.
* @folio: The folio to lock.
*
* Attempts to lock the folio, like folio_lock(), except that the sleep
* to acquire the lock is interruptible by a fatal signal.
*
* Context: May sleep; see folio_lock().
* Return: 0 if the lock was acquired; -EINTR if a fatal signal was received.
*/
static inline int folio_lock_killable(struct folio *folio)
{
might_sleep();
if (!folio_trylock(folio))
return __folio_lock_killable(folio);
return 0;
}
/*
* folio_lock_or_retry - Lock the folio, unless this would block and the
* caller indicated that it can handle a retry.
*
* Return value and mmap_lock implications depend on flags; see
* __folio_lock_or_retry().
*/
static inline vm_fault_t folio_lock_or_retry(struct folio *folio,
struct vm_fault *vmf)
{
might_sleep();
if (!folio_trylock(folio))
return __folio_lock_or_retry(folio, vmf);
return 0;
}
/*
* This is exported only for folio_wait_locked/folio_wait_writeback, etc.,
* and should not be used directly.
*/
void folio_wait_bit(struct folio *folio, int bit_nr);
int folio_wait_bit_killable(struct folio *folio, int bit_nr);
/*
* Wait for a folio to be unlocked.
*
* This must be called with the caller "holding" the folio,
* ie with increased folio reference count so that the folio won't
* go away during the wait.
*/
static inline void folio_wait_locked(struct folio *folio)
{
if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked);
}
static inline int folio_wait_locked_killable(struct folio *folio)
{
if (!folio_test_locked(folio))
return 0;
return folio_wait_bit_killable(folio, PG_locked);
}
void folio_end_read(struct folio *folio, bool success);
void wait_on_page_writeback(struct page *page);
void folio_wait_writeback(struct folio *folio);
int folio_wait_writeback_killable(struct folio *folio);
void end_page_writeback(struct page *page);
void folio_end_writeback(struct folio *folio);
void folio_wait_stable(struct folio *folio);
void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb);
void __folio_cancel_dirty(struct folio *folio);
static inline void folio_cancel_dirty(struct folio *folio)
{
/* Avoid atomic ops, locking, etc. when not actually needed. */
if (folio_test_dirty(folio)) __folio_cancel_dirty(folio);
}
bool folio_clear_dirty_for_io(struct folio *folio);
bool clear_page_dirty_for_io(struct page *page);
void folio_invalidate(struct folio *folio, size_t offset, size_t length);
bool noop_dirty_folio(struct address_space *mapping, struct folio *folio);
#ifdef CONFIG_MIGRATION
int filemap_migrate_folio(struct address_space *mapping, struct folio *dst,
struct folio *src, enum migrate_mode mode);
#else
#define filemap_migrate_folio NULL
#endif
void folio_end_private_2(struct folio *folio);
void folio_wait_private_2(struct folio *folio);
int folio_wait_private_2_killable(struct folio *folio);
/*
* Fault in userspace address range.
*/
size_t fault_in_writeable(char __user *uaddr, size_t size);
size_t fault_in_subpage_writeable(char __user *uaddr, size_t size);
size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
size_t fault_in_readable(const char __user *uaddr, size_t size);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp);
int filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp);
void filemap_remove_folio(struct folio *folio);
void __filemap_remove_folio(struct folio *folio, void *shadow);
void replace_page_cache_folio(struct folio *old, struct folio *new);
void delete_from_page_cache_batch(struct address_space *mapping,
struct folio_batch *fbatch);
bool filemap_release_folio(struct folio *folio, gfp_t gfp);
loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end,
int whence);
/* Must be non-static for BPF error injection */
int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp, void **shadowp);
bool filemap_range_has_writeback(struct address_space *mapping,
loff_t start_byte, loff_t end_byte);
/**
* filemap_range_needs_writeback - check if range potentially needs writeback
* @mapping: address space within which to check
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Find at least one page in the range supplied, usually used to check if
* direct writing in this range will trigger a writeback. Used by O_DIRECT
* read/write with IOCB_NOWAIT, to see if the caller needs to do
* filemap_write_and_wait_range() before proceeding.
*
* Return: %true if the caller should do filemap_write_and_wait_range() before
* doing O_DIRECT to a page in this range, %false otherwise.
*/
static inline bool filemap_range_needs_writeback(struct address_space *mapping,
loff_t start_byte,
loff_t end_byte)
{
if (!mapping->nrpages)
return false;
if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
return false;
return filemap_range_has_writeback(mapping, start_byte, end_byte);
}
/**
* struct readahead_control - Describes a readahead request.
*
* A readahead request is for consecutive pages. Filesystems which
* implement the ->readahead method should call readahead_page() or
* readahead_page_batch() in a loop and attempt to start I/O against
* each page in the request.
*
* Most of the fields in this struct are private and should be accessed
* by the functions below.
*
* @file: The file, used primarily by network filesystems for authentication.
* May be NULL if invoked internally by the filesystem.
* @mapping: Readahead this filesystem object.
* @ra: File readahead state. May be NULL.
*/
struct readahead_control {
struct file *file;
struct address_space *mapping;
struct file_ra_state *ra;
/* private: use the readahead_* accessors instead */
pgoff_t _index;
unsigned int _nr_pages;
unsigned int _batch_count;
bool dropbehind;
bool _workingset;
unsigned long _pflags;
};
#define DEFINE_READAHEAD(ractl, f, r, m, i) \
struct readahead_control ractl = { \
.file = f, \
.mapping = m, \
.ra = r, \
._index = i, \
}
#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
void page_cache_ra_unbounded(struct readahead_control *,
unsigned long nr_to_read, unsigned long lookahead_count);
void page_cache_sync_ra(struct readahead_control *, unsigned long req_count);
void page_cache_async_ra(struct readahead_control *, struct folio *,
unsigned long req_count);
void readahead_expand(struct readahead_control *ractl,
loff_t new_start, size_t new_len);
/**
* page_cache_sync_readahead - generic file readahead
* @mapping: address_space which holds the pagecache and I/O vectors
* @ra: file_ra_state which holds the readahead state
* @file: Used by the filesystem for authentication.
* @index: Index of first page to be read.
* @req_count: Total number of pages being read by the caller.
*
* page_cache_sync_readahead() should be called when a cache miss happened:
* it will submit the read. The readahead logic may decide to piggyback more
* pages onto the read request if access patterns suggest it will improve
* performance.
*/
static inline
void page_cache_sync_readahead(struct address_space *mapping,
struct file_ra_state *ra, struct file *file, pgoff_t index,
unsigned long req_count)
{
DEFINE_READAHEAD(ractl, file, ra, mapping, index);
page_cache_sync_ra(&ractl, req_count);
}
/**
* page_cache_async_readahead - file readahead for marked pages
* @mapping: address_space which holds the pagecache and I/O vectors
* @ra: file_ra_state which holds the readahead state
* @file: Used by the filesystem for authentication.
* @folio: The folio which triggered the readahead call.
* @req_count: Total number of pages being read by the caller.
*
* page_cache_async_readahead() should be called when a page is used which
* is marked as PageReadahead; this is a marker to suggest that the application
* has used up enough of the readahead window that we should start pulling in
* more pages.
*/
static inline
void page_cache_async_readahead(struct address_space *mapping,
struct file_ra_state *ra, struct file *file,
struct folio *folio, unsigned long req_count)
{
DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index);
page_cache_async_ra(&ractl, folio, req_count);
}
static inline struct folio *__readahead_folio(struct readahead_control *ractl)
{
struct folio *folio;
BUG_ON(ractl->_batch_count > ractl->_nr_pages);
ractl->_nr_pages -= ractl->_batch_count;
ractl->_index += ractl->_batch_count;
if (!ractl->_nr_pages) {
ractl->_batch_count = 0;
return NULL;
}
folio = xa_load(&ractl->mapping->i_pages, ractl->_index);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio);
return folio;
}
/**
* readahead_page - Get the next page to read.
* @ractl: The current readahead request.
*
* Context: The page is locked and has an elevated refcount. The caller
* should decreases the refcount once the page has been submitted for I/O
* and unlock the page once all I/O to that page has completed.
* Return: A pointer to the next page, or %NULL if we are done.
*/
static inline struct page *readahead_page(struct readahead_control *ractl)
{
struct folio *folio = __readahead_folio(ractl);
return &folio->page;
}
/**
* readahead_folio - Get the next folio to read.
* @ractl: The current readahead request.
*
* Context: The folio is locked. The caller should unlock the folio once
* all I/O to that folio has completed.
* Return: A pointer to the next folio, or %NULL if we are done.
*/
static inline struct folio *readahead_folio(struct readahead_control *ractl)
{ struct folio *folio = __readahead_folio(ractl); if (folio) folio_put(folio);
return folio;
}
static inline unsigned int __readahead_batch(struct readahead_control *rac,
struct page **array, unsigned int array_sz)
{
unsigned int i = 0;
XA_STATE(xas, &rac->mapping->i_pages, 0);
struct page *page;
BUG_ON(rac->_batch_count > rac->_nr_pages);
rac->_nr_pages -= rac->_batch_count;
rac->_index += rac->_batch_count;
rac->_batch_count = 0;
xas_set(&xas, rac->_index);
rcu_read_lock();
xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
if (xas_retry(&xas, page))
continue;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageTail(page), page);
array[i++] = page;
rac->_batch_count += thp_nr_pages(page);
if (i == array_sz)
break;
}
rcu_read_unlock();
return i;
}
/**
* readahead_page_batch - Get a batch of pages to read.
* @rac: The current readahead request.
* @array: An array of pointers to struct page.
*
* Context: The pages are locked and have an elevated refcount. The caller
* should decreases the refcount once the page has been submitted for I/O
* and unlock the page once all I/O to that page has completed.
* Return: The number of pages placed in the array. 0 indicates the request
* is complete.
*/
#define readahead_page_batch(rac, array) \
__readahead_batch(rac, array, ARRAY_SIZE(array))
/**
* readahead_pos - The byte offset into the file of this readahead request.
* @rac: The readahead request.
*/
static inline loff_t readahead_pos(struct readahead_control *rac)
{
return (loff_t)rac->_index * PAGE_SIZE;
}
/**
* readahead_length - The number of bytes in this readahead request.
* @rac: The readahead request.
*/
static inline size_t readahead_length(struct readahead_control *rac)
{
return rac->_nr_pages * PAGE_SIZE;
}
/**
* readahead_index - The index of the first page in this readahead request.
* @rac: The readahead request.
*/
static inline pgoff_t readahead_index(struct readahead_control *rac)
{
return rac->_index;
}
/**
* readahead_count - The number of pages in this readahead request.
* @rac: The readahead request.
*/
static inline unsigned int readahead_count(struct readahead_control *rac)
{
return rac->_nr_pages;
}
/**
* readahead_batch_length - The number of bytes in the current batch.
* @rac: The readahead request.
*/
static inline size_t readahead_batch_length(struct readahead_control *rac)
{
return rac->_batch_count * PAGE_SIZE;
}
static inline unsigned long dir_pages(struct inode *inode)
{
return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
PAGE_SHIFT;
}
/**
* folio_mkwrite_check_truncate - check if folio was truncated
* @folio: the folio to check
* @inode: the inode to check the folio against
*
* Return: the number of bytes in the folio up to EOF,
* or -EFAULT if the folio was truncated.
*/
static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
struct inode *inode)
{
loff_t size = i_size_read(inode);
pgoff_t index = size >> PAGE_SHIFT;
size_t offset = offset_in_folio(folio, size);
if (!folio->mapping)
return -EFAULT;
/* folio is wholly inside EOF */
if (folio_next_index(folio) - 1 < index)
return folio_size(folio);
/* folio is wholly past EOF */
if (folio->index > index || !offset)
return -EFAULT;
/* folio is partially inside EOF */
return offset;
}
/**
* i_blocks_per_folio - How many blocks fit in this folio.
* @inode: The inode which contains the blocks.
* @folio: The folio.
*
* If the block size is larger than the size of this folio, return zero.
*
* Context: The caller should hold a refcount on the folio to prevent it
* from being split.
* Return: The number of filesystem blocks covered by this folio.
*/
static inline
unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio)
{
return folio_size(folio) >> inode->i_blkbits;
}
#endif /* _LINUX_PAGEMAP_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* This file contains the interface functions for the various time related
* system calls: time, stime, gettimeofday, settimeofday, adjtime
*
* Modification history:
*
* 1993-09-02 Philip Gladstone
* Created file with time related functions from sched/core.c and adjtimex()
* 1993-10-08 Torsten Duwe
* adjtime interface update and CMOS clock write code
* 1995-08-13 Torsten Duwe
* kernel PLL updated to 1994-12-13 specs (rfc-1589)
* 1999-01-16 Ulrich Windl
* Introduced error checking for many cases in adjtimex().
* Updated NTP code according to technical memorandum Jan '96
* "A Kernel Model for Precision Timekeeping" by Dave Mills
* Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
* (Even though the technical memorandum forbids it)
* 2004-07-14 Christoph Lameter
* Added getnstimeofday to allow the posix timer functions to return
* with nanosecond accuracy
*/
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/fs.h>
#include <linux/math64.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <asm/unistd.h>
#include <generated/timeconst.h>
#include "timekeeping.h"
/*
* The timezone where the local system is located. Used as a default by some
* programs who obtain this value by using gettimeofday.
*/
struct timezone sys_tz;
EXPORT_SYMBOL(sys_tz);
#ifdef __ARCH_WANT_SYS_TIME
/*
* sys_time() can be implemented in user-level using
* sys_gettimeofday(). Is this for backwards compatibility? If so,
* why not move it into the appropriate arch directory (for those
* architectures that need it).
*/
SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc)
{
__kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
return -EFAULT;
}
force_successful_syscall_return();
return i;
}
/*
* sys_stime() can be implemented in user-level using
* sys_settimeofday(). Is this for backwards compatibility? If so,
* why not move it into the appropriate arch directory (for those
* architectures that need it).
*/
SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr)
{
struct timespec64 tv;
int err;
if (get_user(tv.tv_sec, tptr))
return -EFAULT;
tv.tv_nsec = 0;
err = security_settime64(&tv, NULL);
if (err)
return err;
do_settimeofday64(&tv);
return 0;
}
#endif /* __ARCH_WANT_SYS_TIME */
#ifdef CONFIG_COMPAT_32BIT_TIME
#ifdef __ARCH_WANT_SYS_TIME32
/* old_time32_t is a 32 bit "long" and needs to get converted. */
SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc)
{
old_time32_t i;
i = (old_time32_t)ktime_get_real_seconds();
if (tloc) {
if (put_user(i,tloc))
return -EFAULT;
}
force_successful_syscall_return();
return i;
}
SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr)
{
struct timespec64 tv;
int err;
if (get_user(tv.tv_sec, tptr))
return -EFAULT;
tv.tv_nsec = 0;
err = security_settime64(&tv, NULL);
if (err)
return err;
do_settimeofday64(&tv);
return 0;
}
#endif /* __ARCH_WANT_SYS_TIME32 */
#endif
SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv,
struct timezone __user *, tz)
{
if (likely(tv != NULL)) {
struct timespec64 ts;
ktime_get_real_ts64(&ts);
if (put_user(ts.tv_sec, &tv->tv_sec) ||
put_user(ts.tv_nsec / 1000, &tv->tv_usec))
return -EFAULT;
}
if (unlikely(tz != NULL)) {
if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
return -EFAULT;
}
return 0;
}
/*
* In case for some reason the CMOS clock has not already been running
* in UTC, but in some local time: The first time we set the timezone,
* we will warp the clock so that it is ticking UTC time instead of
* local time. Presumably, if someone is setting the timezone then we
* are running in an environment where the programs understand about
* timezones. This should be done at boot time in the /etc/rc script,
* as soon as possible, so that the clock can be set right. Otherwise,
* various programs will get confused when the clock gets warped.
*/
int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz)
{
static int firsttime = 1;
int error = 0;
if (tv && !timespec64_valid_settod(tv))
return -EINVAL;
error = security_settime64(tv, tz);
if (error)
return error;
if (tz) {
/* Verify we're within the +-15 hrs range */
if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
return -EINVAL;
sys_tz = *tz;
update_vsyscall_tz();
if (firsttime) {
firsttime = 0;
if (!tv)
timekeeping_warp_clock();
}
}
if (tv)
return do_settimeofday64(tv);
return 0;
}
SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv,
struct timezone __user *, tz)
{
struct timespec64 new_ts;
struct timezone new_tz;
if (tv) {
if (get_user(new_ts.tv_sec, &tv->tv_sec) ||
get_user(new_ts.tv_nsec, &tv->tv_usec))
return -EFAULT;
if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0)
return -EINVAL;
new_ts.tv_nsec *= NSEC_PER_USEC;
}
if (tz) {
if (copy_from_user(&new_tz, tz, sizeof(*tz)))
return -EFAULT;
}
return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv,
struct timezone __user *, tz)
{
if (tv) {
struct timespec64 ts;
ktime_get_real_ts64(&ts);
if (put_user(ts.tv_sec, &tv->tv_sec) ||
put_user(ts.tv_nsec / 1000, &tv->tv_usec))
return -EFAULT;
}
if (tz) {
if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
return -EFAULT;
}
return 0;
}
COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv,
struct timezone __user *, tz)
{
struct timespec64 new_ts;
struct timezone new_tz;
if (tv) {
if (get_user(new_ts.tv_sec, &tv->tv_sec) ||
get_user(new_ts.tv_nsec, &tv->tv_usec))
return -EFAULT;
if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0)
return -EINVAL;
new_ts.tv_nsec *= NSEC_PER_USEC;
}
if (tz) {
if (copy_from_user(&new_tz, tz, sizeof(*tz)))
return -EFAULT;
}
return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
#endif
#ifdef CONFIG_64BIT
SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p)
{
struct __kernel_timex txc; /* Local copy of parameter */
int ret;
/* Copy the user data space into the kernel copy
* structure. But bear in mind that the structures
* may change
*/
if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex)))
return -EFAULT;
ret = do_adjtimex(&txc);
return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret;
}
#endif
#ifdef CONFIG_COMPAT_32BIT_TIME
int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp)
{
struct old_timex32 tx32;
memset(txc, 0, sizeof(struct __kernel_timex));
if (copy_from_user(&tx32, utp, sizeof(struct old_timex32)))
return -EFAULT;
txc->modes = tx32.modes;
txc->offset = tx32.offset;
txc->freq = tx32.freq;
txc->maxerror = tx32.maxerror;
txc->esterror = tx32.esterror;
txc->status = tx32.status;
txc->constant = tx32.constant;
txc->precision = tx32.precision;
txc->tolerance = tx32.tolerance;
txc->time.tv_sec = tx32.time.tv_sec;
txc->time.tv_usec = tx32.time.tv_usec;
txc->tick = tx32.tick;
txc->ppsfreq = tx32.ppsfreq;
txc->jitter = tx32.jitter;
txc->shift = tx32.shift;
txc->stabil = tx32.stabil;
txc->jitcnt = tx32.jitcnt;
txc->calcnt = tx32.calcnt;
txc->errcnt = tx32.errcnt;
txc->stbcnt = tx32.stbcnt;
return 0;
}
int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc)
{
struct old_timex32 tx32;
memset(&tx32, 0, sizeof(struct old_timex32));
tx32.modes = txc->modes;
tx32.offset = txc->offset;
tx32.freq = txc->freq;
tx32.maxerror = txc->maxerror;
tx32.esterror = txc->esterror;
tx32.status = txc->status;
tx32.constant = txc->constant;
tx32.precision = txc->precision;
tx32.tolerance = txc->tolerance;
tx32.time.tv_sec = txc->time.tv_sec;
tx32.time.tv_usec = txc->time.tv_usec;
tx32.tick = txc->tick;
tx32.ppsfreq = txc->ppsfreq;
tx32.jitter = txc->jitter;
tx32.shift = txc->shift;
tx32.stabil = txc->stabil;
tx32.jitcnt = txc->jitcnt;
tx32.calcnt = txc->calcnt;
tx32.errcnt = txc->errcnt;
tx32.stbcnt = txc->stbcnt;
tx32.tai = txc->tai;
if (copy_to_user(utp, &tx32, sizeof(struct old_timex32)))
return -EFAULT;
return 0;
}
SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp)
{
struct __kernel_timex txc;
int err, ret;
err = get_old_timex32(&txc, utp);
if (err)
return err;
ret = do_adjtimex(&txc);
err = put_old_timex32(utp, &txc);
if (err)
return err;
return ret;
}
#endif
/**
* jiffies_to_msecs - Convert jiffies to milliseconds
* @j: jiffies value
*
* Avoid unnecessary multiplications/divisions in the
* two most common HZ cases.
*
* Return: milliseconds value
*/
unsigned int jiffies_to_msecs(const unsigned long j)
{
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
return (MSEC_PER_SEC / HZ) * j;
#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
HZ_TO_MSEC_SHR32;
# else
return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
EXPORT_SYMBOL(jiffies_to_msecs);
/**
* jiffies_to_usecs - Convert jiffies to microseconds
* @j: jiffies value
*
* Return: microseconds value
*/
unsigned int jiffies_to_usecs(const unsigned long j)
{
/*
* Hz usually doesn't go much further MSEC_PER_SEC.
* jiffies_to_usecs() and usecs_to_jiffies() depend on that.
*/
BUILD_BUG_ON(HZ > USEC_PER_SEC);
#if !(USEC_PER_SEC % HZ)
return (USEC_PER_SEC / HZ) * j;
#else
# if BITS_PER_LONG == 32
return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
# else
return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
# endif
#endif
}
EXPORT_SYMBOL(jiffies_to_usecs);
/**
* mktime64 - Converts date to seconds.
* @year0: year to convert
* @mon0: month to convert
* @day: day to convert
* @hour: hour to convert
* @min: minute to convert
* @sec: second to convert
*
* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
* Assumes input in normal date format, i.e. 1980-12-31 23:59:59
* => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
*
* [For the Julian calendar (which was used in Russia before 1917,
* Britain & colonies before 1752, anywhere else before 1582,
* and is still in use by some communities) leave out the
* -year/100+year/400 terms, and add 10.]
*
* This algorithm was first published by Gauss (I think).
*
* A leap second can be indicated by calling this function with sec as
* 60 (allowable under ISO 8601). The leap second is treated the same
* as the following second since they don't exist in UNIX time.
*
* An encoding of midnight at the end of the day as 24:00:00 - ie. midnight
* tomorrow - (allowable under ISO 8601) is supported.
*
* Return: seconds since the epoch time for the given input date
*/
time64_t mktime64(const unsigned int year0, const unsigned int mon0,
const unsigned int day, const unsigned int hour,
const unsigned int min, const unsigned int sec)
{
unsigned int mon = mon0, year = year0;
/* 1..12 -> 11,12,1..10 */
if (0 >= (int) (mon -= 2)) {
mon += 12; /* Puts Feb last since it has leap day */
year -= 1;
}
return ((((time64_t)
(year/4 - year/100 + year/400 + 367*mon/12 + day) +
year*365 - 719499
)*24 + hour /* now have hours - midnight tomorrow handled here */
)*60 + min /* now have minutes */
)*60 + sec; /* finally seconds */
}
EXPORT_SYMBOL(mktime64);
struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec)
{
struct timespec64 ts = ns_to_timespec64(nsec);
struct __kernel_old_timeval tv;
tv.tv_sec = ts.tv_sec;
tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000;
return tv;
}
EXPORT_SYMBOL(ns_to_kernel_old_timeval);
/**
* set_normalized_timespec64 - set timespec sec and nsec parts and normalize
*
* @ts: pointer to timespec variable to be set
* @sec: seconds to set
* @nsec: nanoseconds to set
*
* Set seconds and nanoseconds field of a timespec variable and
* normalize to the timespec storage format
*
* Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC.
* For negative values only the tv_sec field is negative !
*/
void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec)
{ while (nsec >= NSEC_PER_SEC) {
/*
* The following asm() prevents the compiler from
* optimising this loop into a modulo operation. See
* also __iter_div_u64_rem() in include/linux/time.h
*/
asm("" : "+rm"(nsec));
nsec -= NSEC_PER_SEC;
++sec;
}
while (nsec < 0) {
asm("" : "+rm"(nsec));
nsec += NSEC_PER_SEC;
--sec;
}
ts->tv_sec = sec;
ts->tv_nsec = nsec;
}
EXPORT_SYMBOL(set_normalized_timespec64);
/**
* ns_to_timespec64 - Convert nanoseconds to timespec64
* @nsec: the nanoseconds value to be converted
*
* Return: the timespec64 representation of the nsec parameter.
*/
struct timespec64 ns_to_timespec64(s64 nsec)
{
struct timespec64 ts = { 0, 0 };
s32 rem;
if (likely(nsec > 0)) {
ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
ts.tv_nsec = rem;
} else if (nsec < 0) {
/*
* With negative times, tv_sec points to the earlier
* second, and tv_nsec counts the nanoseconds since
* then, so tv_nsec is always a positive number.
*/
ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1;
ts.tv_nsec = NSEC_PER_SEC - rem - 1;
}
return ts;
}
EXPORT_SYMBOL(ns_to_timespec64);
/**
* __msecs_to_jiffies: - convert milliseconds to jiffies
* @m: time in milliseconds
*
* conversion is done as follows:
*
* - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
*
* - 'too large' values [that would result in larger than
* MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
*
* - all other values are converted to jiffies by either multiplying
* the input value by a factor or dividing it with a factor and
* handling any 32-bit overflows.
* for the details see _msecs_to_jiffies()
*
* msecs_to_jiffies() checks for the passed in value being a constant
* via __builtin_constant_p() allowing gcc to eliminate most of the
* code, __msecs_to_jiffies() is called if the value passed does not
* allow constant folding and the actual conversion must be done at
* runtime.
* The _msecs_to_jiffies helpers are the HZ dependent conversion
* routines found in include/linux/jiffies.h
*
* Return: jiffies value
*/
unsigned long __msecs_to_jiffies(const unsigned int m)
{
/*
* Negative value, means infinite timeout:
*/
if ((int)m < 0)
return MAX_JIFFY_OFFSET;
return _msecs_to_jiffies(m);
}
EXPORT_SYMBOL(__msecs_to_jiffies);
/**
* __usecs_to_jiffies: - convert microseconds to jiffies
* @u: time in milliseconds
*
* Return: jiffies value
*/
unsigned long __usecs_to_jiffies(const unsigned int u)
{
if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
return MAX_JIFFY_OFFSET;
return _usecs_to_jiffies(u);
}
EXPORT_SYMBOL(__usecs_to_jiffies);
/**
* timespec64_to_jiffies - convert a timespec64 value to jiffies
* @value: pointer to &struct timespec64
*
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
* that a remainder subtract here would not do the right thing as the
* resolution values don't fall on second boundaries. I.e. the line:
* nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
* Note that due to the small error in the multiplier here, this
* rounding is incorrect for sufficiently large values of tv_nsec, but
* well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
* OK.
*
* Rather, we just shift the bits off the right.
*
* The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
* value to a scaled second value.
*
* Return: jiffies value
*/
unsigned long
timespec64_to_jiffies(const struct timespec64 *value)
{
u64 sec = value->tv_sec;
long nsec = value->tv_nsec + TICK_NSEC - 1;
if (sec >= MAX_SEC_IN_JIFFIES){
sec = MAX_SEC_IN_JIFFIES;
nsec = 0;
}
return ((sec * SEC_CONVERSION) +
(((u64)nsec * NSEC_CONVERSION) >>
(NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
}
EXPORT_SYMBOL(timespec64_to_jiffies);
/**
* jiffies_to_timespec64 - convert jiffies value to &struct timespec64
* @jiffies: jiffies value
* @value: pointer to &struct timespec64
*/
void
jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value)
{
/*
* Convert jiffies to nanoseconds and separate with
* one divide.
*/
u32 rem;
value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
NSEC_PER_SEC, &rem);
value->tv_nsec = rem;
}
EXPORT_SYMBOL(jiffies_to_timespec64);
/*
* Convert jiffies/jiffies_64 to clock_t and back.
*/
/**
* jiffies_to_clock_t - Convert jiffies to clock_t
* @x: jiffies value
*
* Return: jiffies converted to clock_t (CLOCKS_PER_SEC)
*/
clock_t jiffies_to_clock_t(unsigned long x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
# if HZ < USER_HZ
return x * (USER_HZ / HZ);
# else
return x / (HZ / USER_HZ);
# endif
#else
return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ);
#endif
}
EXPORT_SYMBOL(jiffies_to_clock_t);
/**
* clock_t_to_jiffies - Convert clock_t to jiffies
* @x: clock_t value
*
* Return: clock_t value converted to jiffies
*/
unsigned long clock_t_to_jiffies(unsigned long x)
{
#if (HZ % USER_HZ)==0
if (x >= ~0UL / (HZ / USER_HZ))
return ~0UL;
return x * (HZ / USER_HZ);
#else
/* Don't worry about loss of precision here .. */
if (x >= ~0UL / HZ * USER_HZ)
return ~0UL;
/* .. but do try to contain it here */
return div_u64((u64)x * HZ, USER_HZ);
#endif
}
EXPORT_SYMBOL(clock_t_to_jiffies);
/**
* jiffies_64_to_clock_t - Convert jiffies_64 to clock_t
* @x: jiffies_64 value
*
* Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
*/
u64 jiffies_64_to_clock_t(u64 x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
# if HZ < USER_HZ
x = div_u64(x * USER_HZ, HZ);
# elif HZ > USER_HZ
x = div_u64(x, HZ / USER_HZ);
# else
/* Nothing to do */
# endif
#else
/*
* There are better ways that don't overflow early,
* but even this doesn't overflow in hundreds of years
* in 64 bits, so..
*/
x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ));
#endif
return x;
}
EXPORT_SYMBOL(jiffies_64_to_clock_t);
/**
* nsec_to_clock_t - Convert nsec value to clock_t
* @x: nsec value
*
* Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
*/
u64 nsec_to_clock_t(u64 x)
{
#if (NSEC_PER_SEC % USER_HZ) == 0
return div_u64(x, NSEC_PER_SEC / USER_HZ);
#elif (USER_HZ % 512) == 0
return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
#else
/*
* max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
* overflow after 64.99 years.
* exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
*/
return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
#endif
}
/**
* jiffies64_to_nsecs - Convert jiffies64 to nanoseconds
* @j: jiffies64 value
*
* Return: nanoseconds value
*/
u64 jiffies64_to_nsecs(u64 j)
{
#if !(NSEC_PER_SEC % HZ)
return (NSEC_PER_SEC / HZ) * j;
# else
return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN);
#endif
}
EXPORT_SYMBOL(jiffies64_to_nsecs);
/**
* jiffies64_to_msecs - Convert jiffies64 to milliseconds
* @j: jiffies64 value
*
* Return: milliseconds value
*/
u64 jiffies64_to_msecs(const u64 j)
{
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
return (MSEC_PER_SEC / HZ) * j;
#else
return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
#endif
}
EXPORT_SYMBOL(jiffies64_to_msecs);
/**
* nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
* @n: nsecs in u64
*
* Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
* And this doesn't return MAX_JIFFY_OFFSET since this function is designed
* for scheduler, not for use in device drivers to calculate timeout value.
*
* note:
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
*
* Return: nsecs converted to jiffies64 value
*/
u64 nsecs_to_jiffies64(u64 n)
{
#if (NSEC_PER_SEC % HZ) == 0
/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
return div_u64(n, NSEC_PER_SEC / HZ);
#elif (HZ % 512) == 0
/* overflow after 292 years if HZ = 1024 */
return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
#else
/*
* Generic case - optimized for cases where HZ is a multiple of 3.
* overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
*/
return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
#endif
}
EXPORT_SYMBOL(nsecs_to_jiffies64);
/**
* nsecs_to_jiffies - Convert nsecs in u64 to jiffies
*
* @n: nsecs in u64
*
* Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
* And this doesn't return MAX_JIFFY_OFFSET since this function is designed
* for scheduler, not for use in device drivers to calculate timeout value.
*
* note:
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
*
* Return: nsecs converted to jiffies value
*/
unsigned long nsecs_to_jiffies(u64 n)
{
return (unsigned long)nsecs_to_jiffies64(n);
}
EXPORT_SYMBOL_GPL(nsecs_to_jiffies);
/**
* timespec64_add_safe - Add two timespec64 values and do a safety check
* for overflow.
* @lhs: first (left) timespec64 to add
* @rhs: second (right) timespec64 to add
*
* It's assumed that both values are valid (>= 0).
* And, each timespec64 is in normalized form.
*
* Return: sum of @lhs + @rhs
*/
struct timespec64 timespec64_add_safe(const struct timespec64 lhs,
const struct timespec64 rhs)
{
struct timespec64 res;
set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec,
lhs.tv_nsec + rhs.tv_nsec);
if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) {
res.tv_sec = TIME64_MAX;
res.tv_nsec = 0;
}
return res;
}
/**
* get_timespec64 - get user's time value into kernel space
* @ts: destination &struct timespec64
* @uts: user's time value as &struct __kernel_timespec
*
* Handles compat or 32-bit modes.
*
* Return: 0 on success or negative errno on error
*/
int get_timespec64(struct timespec64 *ts,
const struct __kernel_timespec __user *uts)
{
struct __kernel_timespec kts;
int ret;
ret = copy_from_user(&kts, uts, sizeof(kts));
if (ret)
return -EFAULT;
ts->tv_sec = kts.tv_sec;
/* Zero out the padding in compat mode */
if (in_compat_syscall())
kts.tv_nsec &= 0xFFFFFFFFUL;
/* In 32-bit mode, this drops the padding */
ts->tv_nsec = kts.tv_nsec;
return 0;
}
EXPORT_SYMBOL_GPL(get_timespec64);
/**
* put_timespec64 - convert timespec64 value to __kernel_timespec format and
* copy the latter to userspace
* @ts: input &struct timespec64
* @uts: user's &struct __kernel_timespec
*
* Return: 0 on success or negative errno on error
*/
int put_timespec64(const struct timespec64 *ts,
struct __kernel_timespec __user *uts)
{
struct __kernel_timespec kts = {
.tv_sec = ts->tv_sec,
.tv_nsec = ts->tv_nsec
};
return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(put_timespec64);
static int __get_old_timespec32(struct timespec64 *ts64,
const struct old_timespec32 __user *cts)
{
struct old_timespec32 ts;
int ret;
ret = copy_from_user(&ts, cts, sizeof(ts));
if (ret)
return -EFAULT;
ts64->tv_sec = ts.tv_sec;
ts64->tv_nsec = ts.tv_nsec;
return 0;
}
static int __put_old_timespec32(const struct timespec64 *ts64,
struct old_timespec32 __user *cts)
{
struct old_timespec32 ts = {
.tv_sec = ts64->tv_sec,
.tv_nsec = ts64->tv_nsec
};
return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
}
/**
* get_old_timespec32 - get user's old-format time value into kernel space
* @ts: destination &struct timespec64
* @uts: user's old-format time value (&struct old_timespec32)
*
* Handles X86_X32_ABI compatibility conversion.
*
* Return: 0 on success or negative errno on error
*/
int get_old_timespec32(struct timespec64 *ts, const void __user *uts)
{
if (COMPAT_USE_64BIT_TIME)
return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
else
return __get_old_timespec32(ts, uts);
}
EXPORT_SYMBOL_GPL(get_old_timespec32);
/**
* put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and
* copy the latter to userspace
* @ts: input &struct timespec64
* @uts: user's &struct old_timespec32
*
* Handles X86_X32_ABI compatibility conversion.
*
* Return: 0 on success or negative errno on error
*/
int put_old_timespec32(const struct timespec64 *ts, void __user *uts)
{
if (COMPAT_USE_64BIT_TIME)
return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
else
return __put_old_timespec32(ts, uts);
}
EXPORT_SYMBOL_GPL(put_old_timespec32);
/**
* get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space
* @it: destination &struct itimerspec64
* @uit: user's &struct __kernel_itimerspec
*
* Return: 0 on success or negative errno on error
*/
int get_itimerspec64(struct itimerspec64 *it,
const struct __kernel_itimerspec __user *uit)
{
int ret;
ret = get_timespec64(&it->it_interval, &uit->it_interval);
if (ret)
return ret;
ret = get_timespec64(&it->it_value, &uit->it_value);
return ret;
}
EXPORT_SYMBOL_GPL(get_itimerspec64);
/**
* put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format
* and copy the latter to userspace
* @it: input &struct itimerspec64
* @uit: user's &struct __kernel_itimerspec
*
* Return: 0 on success or negative errno on error
*/
int put_itimerspec64(const struct itimerspec64 *it,
struct __kernel_itimerspec __user *uit)
{
int ret;
ret = put_timespec64(&it->it_interval, &uit->it_interval);
if (ret)
return ret;
ret = put_timespec64(&it->it_value, &uit->it_value);
return ret;
}
EXPORT_SYMBOL_GPL(put_itimerspec64);
/**
* get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space
* @its: destination &struct itimerspec64
* @uits: user's &struct old_itimerspec32
*
* Return: 0 on success or negative errno on error
*/
int get_old_itimerspec32(struct itimerspec64 *its,
const struct old_itimerspec32 __user *uits)
{
if (__get_old_timespec32(&its->it_interval, &uits->it_interval) ||
__get_old_timespec32(&its->it_value, &uits->it_value))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(get_old_itimerspec32);
/**
* put_old_itimerspec32 - convert &struct itimerspec64 to &struct
* old_itimerspec32 and copy the latter to userspace
* @its: input &struct itimerspec64
* @uits: user's &struct old_itimerspec32
*
* Return: 0 on success or negative errno on error
*/
int put_old_itimerspec32(const struct itimerspec64 *its,
struct old_itimerspec32 __user *uits)
{
if (__put_old_timespec32(&its->it_interval, &uits->it_interval) ||
__put_old_timespec32(&its->it_value, &uits->it_value))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(put_old_itimerspec32);
/*
* mm/rmap.c - physical to virtual reverse mappings
*
* Copyright 2001, Rik van Riel <riel@conectiva.com.br>
* Released under the General Public License (GPL).
*
* Simple, low overhead reverse mapping scheme.
* Please try to keep this thing as modular as possible.
*
* Provides methods for unmapping each kind of mapped page:
* the anon methods track anonymous pages, and
* the file methods track pages belonging to an inode.
*
* Original design by Rik van Riel <riel@conectiva.com.br> 2001
* File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
* Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
* Contributions by Hugh Dickins 2003, 2004
*/
/*
* Lock ordering in mm:
*
* inode->i_rwsem (while writing or truncating, not reading or faulting)
* mm->mmap_lock
* mapping->invalidate_lock (in filemap_fault)
* folio_lock
* hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below)
* vma_start_write
* mapping->i_mmap_rwsem
* anon_vma->rwsem
* mm->page_table_lock or pte_lock
* swap_lock (in swap_duplicate, swap_info_get)
* mmlist_lock (in mmput, drain_mmlist and others)
* mapping->private_lock (in block_dirty_folio)
* i_pages lock (widely used)
* lruvec->lru_lock (in folio_lruvec_lock_irq)
* inode->i_lock (in set_page_dirty's __mark_inode_dirty)
* bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
* i_pages lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
* within bdi.wb->list_lock in __sync_single_inode)
*
* anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon)
* ->tasklist_lock
* pte map lock
*
* hugetlbfs PageHuge() take locks in this order:
* hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
* vma_lock (hugetlb specific lock for pmd_sharing)
* mapping->i_mmap_rwsem (also used for hugetlb pmd sharing)
* folio_lock
*/
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/mm_inline.h>
#include <linux/oom.h>
#include <asm/tlbflush.h>
#define CREATE_TRACE_POINTS
#include <trace/events/tlb.h>
#include <trace/events/migrate.h>
#include "internal.h"
static struct kmem_cache *anon_vma_cachep;
static struct kmem_cache *anon_vma_chain_cachep;
static inline struct anon_vma *anon_vma_alloc(void)
{
struct anon_vma *anon_vma;
anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
if (anon_vma) { atomic_set(&anon_vma->refcount, 1);
anon_vma->num_children = 0;
anon_vma->num_active_vmas = 0;
anon_vma->parent = anon_vma;
/*
* Initialise the anon_vma root to point to itself. If called
* from fork, the root will be reset to the parents anon_vma.
*/
anon_vma->root = anon_vma;
}
return anon_vma;
}
static inline void anon_vma_free(struct anon_vma *anon_vma)
{
VM_BUG_ON(atomic_read(&anon_vma->refcount));
/*
* Synchronize against folio_lock_anon_vma_read() such that
* we can safely hold the lock without the anon_vma getting
* freed.
*
* Relies on the full mb implied by the atomic_dec_and_test() from
* put_anon_vma() against the acquire barrier implied by
* down_read_trylock() from folio_lock_anon_vma_read(). This orders:
*
* folio_lock_anon_vma_read() VS put_anon_vma()
* down_read_trylock() atomic_dec_and_test()
* LOCK MB
* atomic_read() rwsem_is_locked()
*
* LOCK should suffice since the actual taking of the lock must
* happen _before_ what follows.
*/
might_sleep();
if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma);
anon_vma_unlock_write(anon_vma);
}
kmem_cache_free(anon_vma_cachep, anon_vma);
}
static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
{
return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
}
static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
{
kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
}
static void anon_vma_chain_link(struct vm_area_struct *vma,
struct anon_vma_chain *avc,
struct anon_vma *anon_vma)
{
avc->vma = vma;
avc->anon_vma = anon_vma;
list_add(&avc->same_vma, &vma->anon_vma_chain);
anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
}
/**
* __anon_vma_prepare - attach an anon_vma to a memory region
* @vma: the memory region in question
*
* This makes sure the memory mapping described by 'vma' has
* an 'anon_vma' attached to it, so that we can associate the
* anonymous pages mapped into it with that anon_vma.
*
* The common case will be that we already have one, which
* is handled inline by anon_vma_prepare(). But if
* not we either need to find an adjacent mapping that we
* can re-use the anon_vma from (very common when the only
* reason for splitting a vma has been mprotect()), or we
* allocate a new one.
*
* Anon-vma allocations are very subtle, because we may have
* optimistically looked up an anon_vma in folio_lock_anon_vma_read()
* and that may actually touch the rwsem even in the newly
* allocated vma (it depends on RCU to make sure that the
* anon_vma isn't actually destroyed).
*
* As a result, we need to do proper anon_vma locking even
* for the new allocation. At the same time, we do not want
* to do any locking for the common case of already having
* an anon_vma.
*/
int __anon_vma_prepare(struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
struct anon_vma *anon_vma, *allocated;
struct anon_vma_chain *avc;
mmap_assert_locked(mm);
might_sleep();
avc = anon_vma_chain_alloc(GFP_KERNEL);
if (!avc)
goto out_enomem;
anon_vma = find_mergeable_anon_vma(vma);
allocated = NULL;
if (!anon_vma) { anon_vma = anon_vma_alloc();
if (unlikely(!anon_vma))
goto out_enomem_free_avc;
anon_vma->num_children++; /* self-parent link for new root */
allocated = anon_vma;
}
anon_vma_lock_write(anon_vma);
/* page_table_lock to protect against threads */
spin_lock(&mm->page_table_lock);
if (likely(!vma->anon_vma)) {
vma->anon_vma = anon_vma;
anon_vma_chain_link(vma, avc, anon_vma);
anon_vma->num_active_vmas++;
allocated = NULL;
avc = NULL;
}
spin_unlock(&mm->page_table_lock);
anon_vma_unlock_write(anon_vma);
if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc))
anon_vma_chain_free(avc);
return 0;
out_enomem_free_avc:
anon_vma_chain_free(avc);
out_enomem:
return -ENOMEM;
}
/*
* This is a useful helper function for locking the anon_vma root as
* we traverse the vma->anon_vma_chain, looping over anon_vma's that
* have the same vma.
*
* Such anon_vma's should have the same root, so you'd expect to see
* just a single mutex_lock for the whole traversal.
*/
static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
{
struct anon_vma *new_root = anon_vma->root;
if (new_root != root) { if (WARN_ON_ONCE(root))
up_write(&root->rwsem);
root = new_root;
down_write(&root->rwsem);
}
return root;
}
static inline void unlock_anon_vma_root(struct anon_vma *root)
{
if (root) up_write(&root->rwsem);
}
/*
* Attach the anon_vmas from src to dst.
* Returns 0 on success, -ENOMEM on failure.
*
* anon_vma_clone() is called by vma_expand(), vma_merge(), __split_vma(),
* copy_vma() and anon_vma_fork(). The first four want an exact copy of src,
* while the last one, anon_vma_fork(), may try to reuse an existing anon_vma to
* prevent endless growth of anon_vma. Since dst->anon_vma is set to NULL before
* call, we can identify this case by checking (!dst->anon_vma &&
* src->anon_vma).
*
* If (!dst->anon_vma && src->anon_vma) is true, this function tries to find
* and reuse existing anon_vma which has no vmas and only one child anon_vma.
* This prevents degradation of anon_vma hierarchy to endless linear chain in
* case of constantly forking task. On the other hand, an anon_vma with more
* than one child isn't reused even if there was no alive vma, thus rmap
* walker has a good chance of avoiding scanning the whole hierarchy when it
* searches where page is mapped.
*/
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
struct anon_vma_chain *avc, *pavc;
struct anon_vma *root = NULL;
list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma;
avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
if (unlikely(!avc)) {
unlock_anon_vma_root(root);
root = NULL;
avc = anon_vma_chain_alloc(GFP_KERNEL);
if (!avc)
goto enomem_failure;
}
anon_vma = pavc->anon_vma;
root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma);
/*
* Reuse existing anon_vma if it has no vma and only one
* anon_vma child.
*
* Root anon_vma is never reused:
* it has self-parent reference and at least one child.
*/
if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 &&
anon_vma->num_active_vmas == 0)
dst->anon_vma = anon_vma;
}
if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root);
return 0;
enomem_failure:
/*
* dst->anon_vma is dropped here otherwise its num_active_vmas can
* be incorrectly decremented in unlink_anon_vmas().
* We can safely do this because callers of anon_vma_clone() don't care
* about dst->anon_vma if anon_vma_clone() failed.
*/
dst->anon_vma = NULL;
unlink_anon_vmas(dst);
return -ENOMEM;
}
/*
* Attach vma to its own anon_vma, as well as to the anon_vmas that
* the corresponding VMA in the parent process is attached to.
* Returns 0 on success, non-zero on failure.
*/
int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
{
struct anon_vma_chain *avc;
struct anon_vma *anon_vma;
int error;
/* Don't bother if the parent process has no anon_vma here. */
if (!pvma->anon_vma)
return 0;
/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
vma->anon_vma = NULL;
/*
* First, attach the new VMA to the parent VMA's anon_vmas,
* so rmap can find non-COWed pages in child processes.
*/
error = anon_vma_clone(vma, pvma);
if (error)
return error;
/* An existing anon_vma has been reused, all done then. */
if (vma->anon_vma)
return 0;
/* Then add our own anon_vma. */
anon_vma = anon_vma_alloc();
if (!anon_vma)
goto out_error;
anon_vma->num_active_vmas++;
avc = anon_vma_chain_alloc(GFP_KERNEL);
if (!avc)
goto out_error_free_anon_vma;
/*
* The root anon_vma's rwsem is the lock actually used when we
* lock any of the anon_vmas in this anon_vma tree.
*/
anon_vma->root = pvma->anon_vma->root;
anon_vma->parent = pvma->anon_vma;
/*
* With refcounts, an anon_vma can stay around longer than the
* process it belongs to. The root anon_vma needs to be pinned until
* this anon_vma is freed, because the lock lives in the root.
*/
get_anon_vma(anon_vma->root);
/* Mark this anon_vma as the one where our new (COWed) pages go. */
vma->anon_vma = anon_vma;
anon_vma_lock_write(anon_vma);
anon_vma_chain_link(vma, avc, anon_vma);
anon_vma->parent->num_children++;
anon_vma_unlock_write(anon_vma);
return 0;
out_error_free_anon_vma:
put_anon_vma(anon_vma);
out_error:
unlink_anon_vmas(vma);
return -ENOMEM;
}
void unlink_anon_vmas(struct vm_area_struct *vma)
{
struct anon_vma_chain *avc, *next;
struct anon_vma *root = NULL;
/*
* Unlink each anon_vma chained to the VMA. This list is ordered
* from newest to oldest, ensuring the root anon_vma gets freed last.
*/
list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma = avc->anon_vma;
root = lock_anon_vma_root(root, anon_vma);
anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
/*
* Leave empty anon_vmas on the list - we'll need
* to free them outside the lock.
*/
if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) {
anon_vma->parent->num_children--;
continue;
}
list_del(&avc->same_vma);
anon_vma_chain_free(avc);
}
if (vma->anon_vma) { vma->anon_vma->num_active_vmas--;
/*
* vma would still be needed after unlink, and anon_vma will be prepared
* when handle fault.
*/
vma->anon_vma = NULL;
}
unlock_anon_vma_root(root);
/*
* Iterate the list once more, it now only contains empty and unlinked
* anon_vmas, destroy them. Could not do before due to __put_anon_vma()
* needing to write-acquire the anon_vma->root->rwsem.
*/
list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma = avc->anon_vma;
VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma);
anon_vma_chain_free(avc);
}
}
static void anon_vma_ctor(void *data)
{
struct anon_vma *anon_vma = data;
init_rwsem(&anon_vma->rwsem);
atomic_set(&anon_vma->refcount, 0);
anon_vma->rb_root = RB_ROOT_CACHED;
}
void __init anon_vma_init(void)
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
anon_vma_ctor);
anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
SLAB_PANIC|SLAB_ACCOUNT);
}
/*
* Getting a lock on a stable anon_vma from a page off the LRU is tricky!
*
* Since there is no serialization what so ever against folio_remove_rmap_*()
* the best this function can do is return a refcount increased anon_vma
* that might have been relevant to this page.
*
* The page might have been remapped to a different anon_vma or the anon_vma
* returned may already be freed (and even reused).
*
* In case it was remapped to a different anon_vma, the new anon_vma will be a
* child of the old anon_vma, and the anon_vma lifetime rules will therefore
* ensure that any anon_vma obtained from the page will still be valid for as
* long as we observe page_mapped() [ hence all those page_mapped() tests ].
*
* All users of this function must be very careful when walking the anon_vma
* chain and verify that the page in question is indeed mapped in it
* [ something equivalent to page_mapped_in_vma() ].
*
* Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
* folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid
* if there is a mapcount, we can dereference the anon_vma after observing
* those.
*
* NOTE: the caller should normally hold folio lock when calling this. If
* not, the caller needs to double check the anon_vma didn't change after
* taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it
* concurrently without folio lock protection). See folio_lock_anon_vma_read()
* which has already covered that, and comment above remap_pages().
*/
struct anon_vma *folio_get_anon_vma(const struct folio *folio)
{
struct anon_vma *anon_vma = NULL;
unsigned long anon_mapping;
rcu_read_lock();
anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
goto out;
if (!folio_mapped(folio))
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
if (!atomic_inc_not_zero(&anon_vma->refcount)) {
anon_vma = NULL;
goto out;
}
/*
* If this folio is still mapped, then its anon_vma cannot have been
* freed. But if it has been unmapped, we have no security against the
* anon_vma structure being freed and reused (for another anon_vma:
* SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
* above cannot corrupt).
*/
if (!folio_mapped(folio)) {
rcu_read_unlock();
put_anon_vma(anon_vma);
return NULL;
}
out:
rcu_read_unlock();
return anon_vma;
}
/*
* Similar to folio_get_anon_vma() except it locks the anon_vma.
*
* Its a little more complex as it tries to keep the fast path to a single
* atomic op -- the trylock. If we fail the trylock, we fall back to getting a
* reference like with folio_get_anon_vma() and then block on the mutex
* on !rwc->try_lock case.
*/
struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
struct rmap_walk_control *rwc)
{
struct anon_vma *anon_vma = NULL;
struct anon_vma *root_anon_vma;
unsigned long anon_mapping;
retry:
rcu_read_lock();
anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
goto out;
if (!folio_mapped(folio))
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
root_anon_vma = READ_ONCE(anon_vma->root);
if (down_read_trylock(&root_anon_vma->rwsem)) {
/*
* folio_move_anon_rmap() might have changed the anon_vma as we
* might not hold the folio lock here.
*/
if (unlikely((unsigned long)READ_ONCE(folio->mapping) !=
anon_mapping)) {
up_read(&root_anon_vma->rwsem);
rcu_read_unlock();
goto retry;
}
/*
* If the folio is still mapped, then this anon_vma is still
* its anon_vma, and holding the mutex ensures that it will
* not go away, see anon_vma_free().
*/
if (!folio_mapped(folio)) {
up_read(&root_anon_vma->rwsem);
anon_vma = NULL;
}
goto out;
}
if (rwc && rwc->try_lock) {
anon_vma = NULL;
rwc->contended = true;
goto out;
}
/* trylock failed, we got to sleep */
if (!atomic_inc_not_zero(&anon_vma->refcount)) {
anon_vma = NULL;
goto out;
}
if (!folio_mapped(folio)) {
rcu_read_unlock();
put_anon_vma(anon_vma);
return NULL;
}
/* we pinned the anon_vma, its safe to sleep */
rcu_read_unlock();
anon_vma_lock_read(anon_vma);
/*
* folio_move_anon_rmap() might have changed the anon_vma as we might
* not hold the folio lock here.
*/
if (unlikely((unsigned long)READ_ONCE(folio->mapping) !=
anon_mapping)) {
anon_vma_unlock_read(anon_vma);
put_anon_vma(anon_vma);
anon_vma = NULL;
goto retry;
}
if (atomic_dec_and_test(&anon_vma->refcount)) {
/*
* Oops, we held the last refcount, release the lock
* and bail -- can't simply use put_anon_vma() because
* we'll deadlock on the anon_vma_lock_write() recursion.
*/
anon_vma_unlock_read(anon_vma);
__put_anon_vma(anon_vma);
anon_vma = NULL;
}
return anon_vma;
out:
rcu_read_unlock();
return anon_vma;
}
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/*
* Flush TLB entries for recently unmapped pages from remote CPUs. It is
* important if a PTE was dirty when it was unmapped that it's flushed
* before any IO is initiated on the page to prevent lost writes. Similarly,
* it must be flushed before freeing to prevent data leakage.
*/
void try_to_unmap_flush(void)
{
struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc;
if (!tlb_ubc->flush_required)
return;
arch_tlbbatch_flush(&tlb_ubc->arch);
tlb_ubc->flush_required = false;
tlb_ubc->writable = false;
}
/* Flush iff there are potentially writable TLB entries that can race with IO */
void try_to_unmap_flush_dirty(void)
{
struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc;
if (tlb_ubc->writable)
try_to_unmap_flush();
}
/*
* Bits 0-14 of mm->tlb_flush_batched record pending generations.
* Bits 16-30 of mm->tlb_flush_batched bit record flushed generations.
*/
#define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16
#define TLB_FLUSH_BATCH_PENDING_MASK \
((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1)
#define TLB_FLUSH_BATCH_PENDING_LARGE \
(TLB_FLUSH_BATCH_PENDING_MASK / 2)
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
unsigned long start, unsigned long end)
{
struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc;
int batch;
bool writable = pte_dirty(pteval);
if (!pte_accessible(mm, pteval))
return;
arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end);
tlb_ubc->flush_required = true;
/*
* Ensure compiler does not re-order the setting of tlb_flush_batched
* before the PTE is cleared.
*/
barrier();
batch = atomic_read(&mm->tlb_flush_batched);
retry:
if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) {
/*
* Prevent `pending' from catching up with `flushed' because of
* overflow. Reset `pending' and `flushed' to be 1 and 0 if
* `pending' becomes large.
*/
if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1))
goto retry;
} else {
atomic_inc(&mm->tlb_flush_batched);
}
/*
* If the PTE was dirty then it's best to assume it's writable. The
* caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
* before the page is queued for IO.
*/
if (writable)
tlb_ubc->writable = true;
}
/*
* Returns true if the TLB flush should be deferred to the end of a batch of
* unmap operations to reduce IPIs.
*/
static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
if (!(flags & TTU_BATCH_FLUSH))
return false;
return arch_tlbbatch_should_defer(mm);
}
/*
* Reclaim unmaps pages under the PTL but do not flush the TLB prior to
* releasing the PTL if TLB flushes are batched. It's possible for a parallel
* operation such as mprotect or munmap to race between reclaim unmapping
* the page and flushing the page. If this race occurs, it potentially allows
* access to data via a stale TLB entry. Tracking all mm's that have TLB
* batching in flight would be expensive during reclaim so instead track
* whether TLB batching occurred in the past and if so then do a flush here
* if required. This will cost one additional flush per reclaim cycle paid
* by the first operation at risk such as mprotect and mumap.
*
* This must be called under the PTL so that an access to tlb_flush_batched
* that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
* via the PTL.
*/
void flush_tlb_batched_pending(struct mm_struct *mm)
{
int batch = atomic_read(&mm->tlb_flush_batched);
int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK;
int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT;
if (pending != flushed) {
arch_flush_tlb_batched_pending(mm);
/*
* If the new TLB flushing is pending during flushing, leave
* mm->tlb_flush_batched as is, to avoid losing flushing.
*/
atomic_cmpxchg(&mm->tlb_flush_batched, batch,
pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT));
}
}
#else
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
unsigned long start, unsigned long end)
{
}
static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
return false;
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
/**
* page_address_in_vma - The virtual address of a page in this VMA.
* @folio: The folio containing the page.
* @page: The page within the folio.
* @vma: The VMA we need to know the address in.
*
* Calculates the user virtual address of this page in the specified VMA.
* It is the caller's responsibililty to check the page is actually
* within the VMA. There may not currently be a PTE pointing at this
* page, but if a page fault occurs at this address, this is the page
* which will be accessed.
*
* Context: Caller should hold a reference to the folio. Caller should
* hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the
* VMA from being altered.
*
* Return: The virtual address corresponding to this page in the VMA.
*/
unsigned long page_address_in_vma(const struct folio *folio,
const struct page *page, const struct vm_area_struct *vma)
{
if (folio_test_anon(folio)) {
struct anon_vma *page__anon_vma = folio_anon_vma(folio);
/*
* Note: swapoff's unuse_vma() is more efficient with this
* check, and needs it to match anon_vma when KSM is active.
*/
if (!vma->anon_vma || !page__anon_vma ||
vma->anon_vma->root != page__anon_vma->root)
return -EFAULT;
} else if (!vma->vm_file) {
return -EFAULT;
} else if (vma->vm_file->f_mapping != folio->mapping) {
return -EFAULT;
}
/* KSM folios don't reach here because of the !page__anon_vma check */
return vma_address(vma, page_pgoff(folio, page), 1);
}
/*
* Returns the actual pmd_t* where we expect 'address' to be mapped from, or
* NULL if it doesn't exist. No guarantees / checks on what the pmd_t*
* represents.
*/
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd = NULL;
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out;
p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d))
goto out;
pud = pud_offset(p4d, address); if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
out:
return pmd;
}
struct folio_referenced_arg {
int mapcount;
int referenced;
unsigned long vm_flags;
struct mem_cgroup *memcg;
};
/*
* arg: folio_referenced_arg will be passed
*/
static bool folio_referenced_one(struct folio *folio,
struct vm_area_struct *vma, unsigned long address, void *arg)
{
struct folio_referenced_arg *pra = arg;
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
int referenced = 0;
unsigned long start = address, ptes = 0;
while (page_vma_mapped_walk(&pvmw)) {
address = pvmw.address;
if (vma->vm_flags & VM_LOCKED) {
if (!folio_test_large(folio) || !pvmw.pte) {
/* Restore the mlock which got missed */
mlock_vma_folio(folio, vma);
page_vma_mapped_walk_done(&pvmw);
pra->vm_flags |= VM_LOCKED;
return false; /* To break the loop */
}
/*
* For large folio fully mapped to VMA, will
* be handled after the pvmw loop.
*
* For large folio cross VMA boundaries, it's
* expected to be picked by page reclaim. But
* should skip reference of pages which are in
* the range of VM_LOCKED vma. As page reclaim
* should just count the reference of pages out
* the range of VM_LOCKED vma.
*/
ptes++;
pra->mapcount--;
continue;
}
/*
* Skip the non-shared swapbacked folio mapped solely by
* the exiting or OOM-reaped process. This avoids redundant
* swap-out followed by an immediate unmap.
*/
if ((!atomic_read(&vma->vm_mm->mm_users) ||
check_stable_address_space(vma->vm_mm)) &&
folio_test_anon(folio) && folio_test_swapbacked(folio) &&
!folio_maybe_mapped_shared(folio)) {
pra->referenced = -1;
page_vma_mapped_walk_done(&pvmw);
return false;
}
if (lru_gen_enabled() && pvmw.pte) {
if (lru_gen_look_around(&pvmw))
referenced++;
} else if (pvmw.pte) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte))
referenced++;
} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
if (pmdp_clear_flush_young_notify(vma, address,
pvmw.pmd))
referenced++;
} else {
/* unexpected pmd-mapped folio? */
WARN_ON_ONCE(1);
}
pra->mapcount--;
}
if ((vma->vm_flags & VM_LOCKED) &&
folio_test_large(folio) &&
folio_within_vma(folio, vma)) {
unsigned long s_align, e_align;
s_align = ALIGN_DOWN(start, PMD_SIZE);
e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE);
/* folio doesn't cross page table boundary and fully mapped */
if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) {
/* Restore the mlock which got missed */
mlock_vma_folio(folio, vma);
pra->vm_flags |= VM_LOCKED;
return false; /* To break the loop */
}
}
if (referenced)
folio_clear_idle(folio);
if (folio_test_clear_young(folio))
referenced++;
if (referenced) {
pra->referenced++;
pra->vm_flags |= vma->vm_flags & ~VM_LOCKED;
}
if (!pra->mapcount)
return false; /* To break the loop */
return true;
}
static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
{
struct folio_referenced_arg *pra = arg;
struct mem_cgroup *memcg = pra->memcg;
/*
* Ignore references from this mapping if it has no recency. If the
* folio has been used in another mapping, we will catch it; if this
* other mapping is already gone, the unmap path will have set the
* referenced flag or activated the folio in zap_pte_range().
*/
if (!vma_has_recency(vma))
return true;
/*
* If we are reclaiming on behalf of a cgroup, skip counting on behalf
* of references from different cgroups.
*/
if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
return true;
return false;
}
/**
* folio_referenced() - Test if the folio was referenced.
* @folio: The folio to test.
* @is_locked: Caller holds lock on the folio.
* @memcg: target memory cgroup
* @vm_flags: A combination of all the vma->vm_flags which referenced the folio.
*
* Quick test_and_clear_referenced for all mappings of a folio,
*
* Return: The number of mappings which referenced the folio. Return -1 if
* the function bailed out due to rmap lock contention.
*/
int folio_referenced(struct folio *folio, int is_locked,
struct mem_cgroup *memcg, unsigned long *vm_flags)
{
bool we_locked = false;
struct folio_referenced_arg pra = {
.mapcount = folio_mapcount(folio),
.memcg = memcg,
};
struct rmap_walk_control rwc = {
.rmap_one = folio_referenced_one,
.arg = (void *)&pra,
.anon_lock = folio_lock_anon_vma_read,
.try_lock = true,
.invalid_vma = invalid_folio_referenced_vma,
};
*vm_flags = 0;
if (!pra.mapcount)
return 0;
if (!folio_raw_mapping(folio))
return 0;
if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) {
we_locked = folio_trylock(folio);
if (!we_locked)
return 1;
}
rmap_walk(folio, &rwc);
*vm_flags = pra.vm_flags;
if (we_locked)
folio_unlock(folio);
return rwc.contended ? -1 : pra.referenced;
}
static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
{
int cleaned = 0;
struct vm_area_struct *vma = pvmw->vma;
struct mmu_notifier_range range;
unsigned long address = pvmw->address;
/*
* We have to assume the worse case ie pmd for invalidation. Note that
* the folio can not be freed from this function.
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0,
vma->vm_mm, address, vma_address_end(pvmw));
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(pvmw)) {
int ret = 0;
address = pvmw->address;
if (pvmw->pte) {
pte_t *pte = pvmw->pte;
pte_t entry = ptep_get(pte);
/*
* PFN swap PTEs, such as device-exclusive ones, that
* actually map pages are clean and not writable from a
* CPU perspective. The MMU notifier takes care of any
* device aspects.
*/
if (!pte_present(entry))
continue;
if (!pte_dirty(entry) && !pte_write(entry))
continue;
flush_cache_page(vma, address, pte_pfn(entry));
entry = ptep_clear_flush(vma, address, pte);
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(vma->vm_mm, address, pte, entry);
ret = 1;
} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
pmd_t *pmd = pvmw->pmd;
pmd_t entry;
if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
continue;
flush_cache_range(vma, address,
address + HPAGE_PMD_SIZE);
entry = pmdp_invalidate(vma, address, pmd);
entry = pmd_wrprotect(entry);
entry = pmd_mkclean(entry);
set_pmd_at(vma->vm_mm, address, pmd, entry);
ret = 1;
#else
/* unexpected pmd-mapped folio? */
WARN_ON_ONCE(1);
#endif
}
if (ret)
cleaned++;
}
mmu_notifier_invalidate_range_end(&range);
return cleaned;
}
static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
int *cleaned = arg;
*cleaned += page_vma_mkclean_one(&pvmw);
return true;
}
static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
{
if (vma->vm_flags & VM_SHARED)
return false;
return true;
}
int folio_mkclean(struct folio *folio)
{
int cleaned = 0;
struct address_space *mapping;
struct rmap_walk_control rwc = {
.arg = (void *)&cleaned,
.rmap_one = page_mkclean_one,
.invalid_vma = invalid_mkclean_vma,
};
BUG_ON(!folio_test_locked(folio));
if (!folio_mapped(folio))
return 0;
mapping = folio_mapping(folio);
if (!mapping)
return 0;
rmap_walk(folio, &rwc);
return cleaned;
}
EXPORT_SYMBOL_GPL(folio_mkclean);
struct wrprotect_file_state {
int cleaned;
pgoff_t pgoff;
unsigned long pfn;
unsigned long nr_pages;
};
static bool mapping_wrprotect_range_one(struct folio *folio,
struct vm_area_struct *vma, unsigned long address, void *arg)
{
struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg;
struct page_vma_mapped_walk pvmw = {
.pfn = state->pfn,
.nr_pages = state->nr_pages,
.pgoff = state->pgoff,
.vma = vma,
.address = address,
.flags = PVMW_SYNC,
};
state->cleaned += page_vma_mkclean_one(&pvmw);
return true;
}
static void __rmap_walk_file(struct folio *folio, struct address_space *mapping,
pgoff_t pgoff_start, unsigned long nr_pages,
struct rmap_walk_control *rwc, bool locked);
/**
* mapping_wrprotect_range() - Write-protect all mappings in a specified range.
*
* @mapping: The mapping whose reverse mapping should be traversed.
* @pgoff: The page offset at which @pfn is mapped within @mapping.
* @pfn: The PFN of the page mapped in @mapping at @pgoff.
* @nr_pages: The number of physically contiguous base pages spanned.
*
* Traverses the reverse mapping, finding all VMAs which contain a shared
* mapping of the pages in the specified range in @mapping, and write-protects
* them (that is, updates the page tables to mark the mappings read-only such
* that a write protection fault arises when the mappings are written to).
*
* The @pfn value need not refer to a folio, but rather can reference a kernel
* allocation which is mapped into userland. We therefore do not require that
* the page maps to a folio with a valid mapping or index field, rather the
* caller specifies these in @mapping and @pgoff.
*
* Return: the number of write-protected PTEs, or an error.
*/
int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff,
unsigned long pfn, unsigned long nr_pages)
{
struct wrprotect_file_state state = {
.cleaned = 0,
.pgoff = pgoff,
.pfn = pfn,
.nr_pages = nr_pages,
};
struct rmap_walk_control rwc = {
.arg = (void *)&state,
.rmap_one = mapping_wrprotect_range_one,
.invalid_vma = invalid_mkclean_vma,
};
if (!mapping)
return 0;
__rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc,
/* locked = */false);
return state.cleaned;
}
EXPORT_SYMBOL_GPL(mapping_wrprotect_range);
/**
* pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
* [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
* within the @vma of shared mappings. And since clean PTEs
* should also be readonly, write protects them too.
* @pfn: start pfn.
* @nr_pages: number of physically contiguous pages srarting with @pfn.
* @pgoff: page offset that the @pfn mapped with.
* @vma: vma that @pfn mapped within.
*
* Returns the number of cleaned PTEs (including PMDs).
*/
int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
struct vm_area_struct *vma)
{
struct page_vma_mapped_walk pvmw = {
.pfn = pfn,
.nr_pages = nr_pages,
.pgoff = pgoff,
.vma = vma,
.flags = PVMW_SYNC,
};
if (invalid_mkclean_vma(vma, NULL))
return 0;
pvmw.address = vma_address(vma, pgoff, nr_pages);
VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);
return page_vma_mkclean_one(&pvmw);
}
static __always_inline unsigned int __folio_add_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *vma,
enum rmap_level level, int *nr_pmdmapped)
{
atomic_t *mapped = &folio->_nr_pages_mapped;
const int orig_nr_pages = nr_pages;
int first = 0, nr = 0;
__folio_rmap_sanity_checks(folio, page, nr_pages, level);
switch (level) {
case RMAP_LEVEL_PTE:
if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount);
break;
}
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma);
if (nr == orig_nr_pages)
/* Was completely unmapped. */
nr = folio_large_nr_pages(folio);
else
nr = 0;
break;
}
do {
first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED)
nr = first;
folio_add_large_mapcount(folio, orig_nr_pages, vma);
break;
case RMAP_LEVEL_PMD:
case RMAP_LEVEL_PUD:
first = atomic_inc_and_test(&folio->_entire_mapcount);
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
if (level == RMAP_LEVEL_PMD && first)
*nr_pmdmapped = folio_large_nr_pages(folio);
nr = folio_inc_return_large_mapcount(folio, vma);
if (nr == 1)
/* Was completely unmapped. */
nr = folio_large_nr_pages(folio);
else
nr = 0;
break;
}
if (first) {
nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped);
if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) {
nr_pages = folio_large_nr_pages(folio);
/*
* We only track PMD mappings of PMD-sized
* folios separately.
*/
if (level == RMAP_LEVEL_PMD)
*nr_pmdmapped = nr_pages;
nr = nr_pages - (nr & FOLIO_PAGES_MAPPED);
/* Raced ahead of a remove and another add? */
if (unlikely(nr < 0))
nr = 0;
} else {
/* Raced ahead of a remove of ENTIRELY_MAPPED */
nr = 0;
}
}
folio_inc_large_mapcount(folio, vma);
break;
}
return nr;
}
/**
* folio_move_anon_rmap - move a folio to our anon_vma
* @folio: The folio to move to our anon_vma
* @vma: The vma the folio belongs to
*
* When a folio belongs exclusively to one process after a COW event,
* that folio can be moved into the anon_vma that belongs to just that
* process, so the rmap code will not search the parent or sibling processes.
*/
void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma)
{
void *anon_vma = vma->anon_vma;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_VMA(!anon_vma, vma);
anon_vma += PAGE_MAPPING_ANON;
/*
* Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written
* simultaneously, so a concurrent reader (eg folio_referenced()'s
* folio_test_anon()) will not see one without the other.
*/
WRITE_ONCE(folio->mapping, anon_vma);
}
/**
* __folio_set_anon - set up a new anonymous rmap for a folio
* @folio: The folio to set up the new anonymous rmap for.
* @vma: VM area to add the folio to.
* @address: User virtual address of the mapping
* @exclusive: Whether the folio is exclusive to the process.
*/
static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, bool exclusive)
{
struct anon_vma *anon_vma = vma->anon_vma;
BUG_ON(!anon_vma);
/*
* If the folio isn't exclusive to this vma, we must use the _oldest_
* possible anon_vma for the folio mapping!
*/
if (!exclusive) anon_vma = anon_vma->root;
/*
* page_idle does a lockless/optimistic rmap scan on folio->mapping.
* Make sure the compiler doesn't split the stores of anon_vma and
* the PAGE_MAPPING_ANON type identifier, otherwise the rmap code
* could mistake the mapping for a struct address_space and crash.
*/
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma);
folio->index = linear_page_index(vma, address);
}
/**
* __page_check_anon_rmap - sanity check anonymous rmap addition
* @folio: The folio containing @page.
* @page: the page to check the mapping of
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*/
static void __page_check_anon_rmap(const struct folio *folio,
const struct page *page, struct vm_area_struct *vma,
unsigned long address)
{
/*
* The page's anon-rmap details (mapping and index) are guaranteed to
* be set up correctly at this point.
*
* We have exclusion against folio_add_anon_rmap_*() because the caller
* always holds the page locked.
*
* We have exclusion against folio_add_new_anon_rmap because those pages
* are initially only visible via the pagetables, and the pte is locked
* over the call to folio_add_new_anon_rmap.
*/
VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root,
folio);
VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address),
page);
}
static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped)
{
int idx;
if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED;
__lruvec_stat_mod_folio(folio, idx, nr);
}
if (nr_pmdmapped) {
if (folio_test_anon(folio)) {
idx = NR_ANON_THPS;
__lruvec_stat_mod_folio(folio, idx, nr_pmdmapped);
} else {
/* NR_*_PMDMAPPED are not maintained per-memcg */
idx = folio_test_swapbacked(folio) ?
NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED;
__mod_node_page_state(folio_pgdat(folio), idx,
nr_pmdmapped);
}
}
}
static __always_inline void __folio_add_anon_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *vma,
unsigned long address, rmap_t flags, enum rmap_level level)
{
int i, nr, nr_pmdmapped = 0;
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
nr = __folio_add_rmap(folio, page, nr_pages, vma, level, &nr_pmdmapped);
if (likely(!folio_test_ksm(folio)))
__page_check_anon_rmap(folio, page, vma, address);
__folio_mod_stat(folio, nr, nr_pmdmapped);
if (flags & RMAP_EXCLUSIVE) {
switch (level) {
case RMAP_LEVEL_PTE:
for (i = 0; i < nr_pages; i++)
SetPageAnonExclusive(page + i);
break;
case RMAP_LEVEL_PMD:
SetPageAnonExclusive(page);
break;
case RMAP_LEVEL_PUD:
/*
* Keep the compiler happy, we don't support anonymous
* PUD mappings.
*/
WARN_ON_ONCE(1);
break;
}
}
VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) &&
atomic_read(&folio->_mapcount) > 0, folio);
for (i = 0; i < nr_pages; i++) {
struct page *cur_page = page + i;
VM_WARN_ON_FOLIO(folio_test_large(folio) &&
folio_entire_mapcount(folio) > 1 &&
PageAnonExclusive(cur_page), folio);
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT))
continue;
/*
* While PTE-mapping a THP we have a PMD and a PTE
* mapping.
*/
VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 &&
PageAnonExclusive(cur_page), folio);
}
/*
* For large folio, only mlock it if it's fully mapped to VMA. It's
* not easy to check whether the large folio is fully mapped to VMA
* here. Only mlock normal 4K folio and leave page reclaim to handle
* large folio.
*/
if (!folio_test_large(folio))
mlock_vma_folio(folio, vma);
}
/**
* folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio
* @folio: The folio to add the mappings to
* @page: The first page to add
* @nr_pages: The number of pages which will be mapped
* @vma: The vm area in which the mappings are added
* @address: The user virtual address of the first page to map
* @flags: The rmap flags
*
* The page range of folio is defined by [first_page, first_page + nr_pages)
*
* The caller needs to hold the page table lock, and the page must be locked in
* the anon_vma case: to serialize mapping,index checking after setting,
* and to ensure that an anon folio is not being upgraded racily to a KSM folio
* (but KSM folios are never downgraded).
*/
void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page,
int nr_pages, struct vm_area_struct *vma, unsigned long address,
rmap_t flags)
{
__folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags,
RMAP_LEVEL_PTE);
}
/**
* folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio
* @folio: The folio to add the mapping to
* @page: The first page to add
* @vma: The vm area in which the mapping is added
* @address: The user virtual address of the first page to map
* @flags: The rmap flags
*
* The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock, and the page must be locked in
* the anon_vma case: to serialize mapping,index checking after setting.
*/
void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page,
struct vm_area_struct *vma, unsigned long address, rmap_t flags)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
__folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags,
RMAP_LEVEL_PMD);
#else
WARN_ON_ONCE(true);
#endif
}
/**
* folio_add_new_anon_rmap - Add mapping to a new anonymous folio.
* @folio: The folio to add the mapping to.
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
* @flags: The rmap flags
*
* Like folio_add_anon_rmap_*() but must only be called on *new* folios.
* This means the inc-and-test can be bypassed.
* The folio doesn't necessarily need to be locked while it's exclusive
* unless two threads map it concurrently. However, the folio must be
* locked if it's shared.
*
* If the folio is pmd-mappable, it is accounted as a THP.
*/
void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, rmap_t flags)
{
const bool exclusive = flags & RMAP_EXCLUSIVE;
int nr = 1, nr_pmdmapped = 0;
VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio);
/*
* VM_DROPPABLE mappings don't swap; instead they're just dropped when
* under memory pressure.
*/
if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive);
if (likely(!folio_test_large(folio))) {
/* increment count (starts at -1) */
atomic_set(&folio->_mapcount, 0);
if (exclusive) SetPageAnonExclusive(&folio->page);
} else if (!folio_test_pmd_mappable(folio)) {
int i;
nr = folio_large_nr_pages(folio);
for (i = 0; i < nr; i++) {
struct page *page = folio_page(folio, i);
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
/* increment count (starts at -1) */
atomic_set(&page->_mapcount, 0);
if (exclusive) SetPageAnonExclusive(page);
}
folio_set_large_mapcount(folio, nr, vma);
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
atomic_set(&folio->_nr_pages_mapped, nr);
} else {
nr = folio_large_nr_pages(folio);
/* increment count (starts at -1) */
atomic_set(&folio->_entire_mapcount, 0);
folio_set_large_mapcount(folio, 1, vma);
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED);
if (exclusive) SetPageAnonExclusive(&folio->page);
nr_pmdmapped = nr;
}
VM_WARN_ON_ONCE(address < vma->vm_start ||
address + (nr << PAGE_SHIFT) > vma->vm_end);
__folio_mod_stat(folio, nr, nr_pmdmapped);
mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1);
}
static __always_inline void __folio_add_file_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *vma,
enum rmap_level level)
{
int nr, nr_pmdmapped = 0;
VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, vma, level, &nr_pmdmapped);
__folio_mod_stat(folio, nr, nr_pmdmapped);
/* See comments in folio_add_anon_rmap_*() */
if (!folio_test_large(folio)) mlock_vma_folio(folio, vma);
}
/**
* folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio
* @folio: The folio to add the mappings to
* @page: The first page to add
* @nr_pages: The number of pages that will be mapped using PTEs
* @vma: The vm area in which the mappings are added
*
* The page range of the folio is defined by [page, page + nr_pages)
*
* The caller needs to hold the page table lock.
*/
void folio_add_file_rmap_ptes(struct folio *folio, struct page *page,
int nr_pages, struct vm_area_struct *vma)
{ __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
}
/**
* folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio
* @folio: The folio to add the mapping to
* @page: The first page to add
* @vma: The vm area in which the mapping is added
*
* The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock.
*/
void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
struct vm_area_struct *vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
__folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
#else
WARN_ON_ONCE(true);
#endif
}
/**
* folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio
* @folio: The folio to add the mapping to
* @page: The first page to add
* @vma: The vm area in which the mapping is added
*
* The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
*
* The caller needs to hold the page table lock.
*/
void folio_add_file_rmap_pud(struct folio *folio, struct page *page,
struct vm_area_struct *vma)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
__folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, RMAP_LEVEL_PUD);
#else
WARN_ON_ONCE(true);
#endif
}
static __always_inline void __folio_remove_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *vma,
enum rmap_level level)
{
atomic_t *mapped = &folio->_nr_pages_mapped;
int last = 0, nr = 0, nr_pmdmapped = 0;
bool partially_mapped = false;
__folio_rmap_sanity_checks(folio, page, nr_pages, level);
switch (level) {
case RMAP_LEVEL_PTE:
if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount);
break;
}
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
nr = folio_sub_return_large_mapcount(folio, nr_pages, vma);
if (!nr) {
/* Now completely unmapped. */
nr = folio_nr_pages(folio);
} else {
partially_mapped = nr < folio_large_nr_pages(folio) &&
!folio_entire_mapcount(folio);
nr = 0;
}
break;
}
folio_sub_large_mapcount(folio, nr_pages, vma);
do {
last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED)
nr = last;
partially_mapped = nr && atomic_read(mapped);
break;
case RMAP_LEVEL_PMD:
case RMAP_LEVEL_PUD:
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
last = atomic_add_negative(-1, &folio->_entire_mapcount);
if (level == RMAP_LEVEL_PMD && last)
nr_pmdmapped = folio_large_nr_pages(folio);
nr = folio_dec_return_large_mapcount(folio, vma);
if (!nr) {
/* Now completely unmapped. */
nr = folio_large_nr_pages(folio);
} else {
partially_mapped = last &&
nr < folio_large_nr_pages(folio);
nr = 0;
}
break;
}
folio_dec_large_mapcount(folio, vma);
last = atomic_add_negative(-1, &folio->_entire_mapcount);
if (last) {
nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped);
if (likely(nr < ENTIRELY_MAPPED)) {
nr_pages = folio_large_nr_pages(folio);
if (level == RMAP_LEVEL_PMD)
nr_pmdmapped = nr_pages;
nr = nr_pages - (nr & FOLIO_PAGES_MAPPED);
/* Raced ahead of another remove and an add? */
if (unlikely(nr < 0))
nr = 0;
} else {
/* An add of ENTIRELY_MAPPED raced ahead */
nr = 0;
}
}
partially_mapped = nr && nr < nr_pmdmapped;
break;
}
/*
* Queue anon large folio for deferred split if at least one page of
* the folio is unmapped and at least one page is still mapped.
*
* Check partially_mapped first to ensure it is a large folio.
*/
if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped);
/*
* It would be tidy to reset folio_test_anon mapping when fully
* unmapped, but that might overwrite a racing folio_add_anon_rmap_*()
* which increments mapcount after us but sets mapping before us:
* so leave the reset to free_pages_prepare, and remember that
* it's only reliable while mapped.
*/
munlock_vma_folio(folio, vma);
}
/**
* folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio
* @folio: The folio to remove the mappings from
* @page: The first page to remove
* @nr_pages: The number of pages that will be removed from the mapping
* @vma: The vm area from which the mappings are removed
*
* The page range of the folio is defined by [page, page + nr_pages)
*
* The caller needs to hold the page table lock.
*/
void folio_remove_rmap_ptes(struct folio *folio, struct page *page,
int nr_pages, struct vm_area_struct *vma)
{ __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
}
/**
* folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio
* @folio: The folio to remove the mapping from
* @page: The first page to remove
* @vma: The vm area from which the mapping is removed
*
* The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock.
*/
void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
struct vm_area_struct *vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
__folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
#else
WARN_ON_ONCE(true);
#endif
}
/**
* folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio
* @folio: The folio to remove the mapping from
* @page: The first page to remove
* @vma: The vm area from which the mapping is removed
*
* The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
*
* The caller needs to hold the page table lock.
*/
void folio_remove_rmap_pud(struct folio *folio, struct page *page,
struct vm_area_struct *vma)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
__folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, RMAP_LEVEL_PUD);
#else
WARN_ON_ONCE(true);
#endif
}
/* We support batch unmapping of PTEs for lazyfree large folios */
static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
struct folio *folio, pte_t *ptep)
{
const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
int max_nr = folio_nr_pages(folio);
pte_t pte = ptep_get(ptep);
if (!folio_test_anon(folio) || folio_test_swapbacked(folio))
return false;
if (pte_unused(pte))
return false;
if (pte_pfn(pte) != folio_pfn(folio))
return false;
return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
NULL, NULL) == max_nr;
}
/*
* @arg: enum ttu_flags will be passed to this argument
*/
static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
struct mm_struct *mm = vma->vm_mm;
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
bool anon_exclusive, ret = true;
pte_t pteval;
struct page *subpage;
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
unsigned long nr_pages = 1, end_addr;
unsigned long pfn;
unsigned long hsz = 0;
/*
* When racing against e.g. zap_pte_range() on another cpu,
* in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
* try_to_unmap() may return before page_mapped() has become false,
* if page table locking is skipped: use TTU_SYNC to wait for that.
*/
if (flags & TTU_SYNC)
pvmw.flags = PVMW_SYNC;
/*
* For THP, we have to assume the worse case ie pmd for invalidation.
* For hugetlb, it could be much worse if we need to do pud
* invalidation in the case of pmd sharing.
*
* Note that the folio can not be freed in this function as call of
* try_to_unmap() must hold a reference on the folio.
*/
range.end = vma_address_end(&pvmw);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, range.end);
if (folio_test_hugetlb(folio)) {
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
/* We need the huge page size for set_huge_pte_at() */
hsz = huge_page_size(hstate_vma(vma));
}
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
/*
* If the folio is in an mlock()d vma, we must not swap it out.
*/
if (!(flags & TTU_IGNORE_MLOCK) &&
(vma->vm_flags & VM_LOCKED)) {
/* Restore the mlock which got missed */
if (!folio_test_large(folio))
mlock_vma_folio(folio, vma);
goto walk_abort;
}
if (!pvmw.pte) {
if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio))
goto walk_done;
/*
* unmap_huge_pmd_locked has either already marked
* the folio as swap-backed or decided to retain it
* due to GUP or speculative references.
*/
goto walk_abort;
}
if (flags & TTU_SPLIT_HUGE_PMD) {
/*
* We temporarily have to drop the PTL and
* restart so we can process the PTE-mapped THP.
*/
split_huge_pmd_locked(vma, pvmw.address,
pvmw.pmd, false, folio);
flags &= ~TTU_SPLIT_HUGE_PMD;
page_vma_mapped_walk_restart(&pvmw);
continue;
}
}
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_FOLIO(!pvmw.pte, folio);
/*
* Handle PFN swap PTEs, such as device-exclusive ones, that
* actually map pages.
*/
pteval = ptep_get(pvmw.pte);
if (likely(pte_present(pteval))) {
pfn = pte_pfn(pteval);
} else {
pfn = swp_offset_pfn(pte_to_swp_entry(pteval));
VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
}
subpage = folio_page(folio, pfn - folio_pfn(folio));
address = pvmw.address;
anon_exclusive = folio_test_anon(folio) &&
PageAnonExclusive(subpage);
if (folio_test_hugetlb(folio)) {
bool anon = folio_test_anon(folio);
/*
* The try_to_unmap() is only passed a hugetlb page
* in the case where the hugetlb page is poisoned.
*/
VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage);
/*
* huge_pmd_unshare may unmap an entire PMD page.
* There is no way of knowing exactly which PMDs may
* be cached for this mm, so we must flush them all.
* start/end were already adjusted above to cover this
* range.
*/
flush_cache_range(vma, range.start, range.end);
/*
* To call huge_pmd_unshare, i_mmap_rwsem must be
* held in write mode. Caller needs to explicitly
* do this outside rmap routines.
*
* We also must hold hugetlb vma_lock in write mode.
* Lock order dictates acquiring vma_lock BEFORE
* i_mmap_rwsem. We can only try lock here and fail
* if unsuccessful.
*/
if (!anon) {
VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
if (!hugetlb_vma_trylock_write(vma))
goto walk_abort;
if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
hugetlb_vma_unlock_write(vma);
flush_tlb_range(vma,
range.start, range.end);
/*
* The ref count of the PMD page was
* dropped which is part of the way map
* counting is done for shared PMDs.
* Return 'true' here. When there is
* no other sharing, huge_pmd_unshare
* returns false and we will unmap the
* actual page and drop map count
* to zero.
*/
goto walk_done;
}
hugetlb_vma_unlock_write(vma);
}
pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
if (pte_dirty(pteval))
folio_mark_dirty(folio);
} else if (likely(pte_present(pteval))) {
if (folio_test_large(folio) && !(flags & TTU_HWPOISON) &&
can_batch_unmap_folio_ptes(address, folio, pvmw.pte))
nr_pages = folio_nr_pages(folio);
end_addr = address + nr_pages * PAGE_SIZE;
flush_cache_range(vma, address, end_addr);
/* Nuke the page table entry. */
pteval = get_and_clear_full_ptes(mm, address, pvmw.pte, nr_pages, 0);
/*
* We clear the PTE but do not flush so potentially
* a remote CPU could still be writing to the folio.
* If the entry was previously clean then the
* architecture must guarantee that a clear->dirty
* transition on a cached TLB entry is written through
* and traps if the PTE is unmapped.
*/
if (should_defer_flush(mm, flags))
set_tlb_ubc_flush_pending(mm, pteval, address, end_addr);
else
flush_tlb_range(vma, address, end_addr);
if (pte_dirty(pteval))
folio_mark_dirty(folio);
} else {
pte_clear(mm, address, pvmw.pte);
}
/*
* Now the pte is cleared. If this pte was uffd-wp armed,
* we may want to replace a none pte with a marker pte if
* it's file-backed, so we don't lose the tracking info.
*/
pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) {
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
set_huge_pte_at(mm, address, pvmw.pte, pteval,
hsz);
} else {
dec_mm_counter(mm, mm_counter(folio));
set_pte_at(mm, address, pvmw.pte, pteval);
}
} else if (likely(pte_present(pteval)) && pte_unused(pteval) &&
!userfaultfd_armed(vma)) {
/*
* The guest indicated that the page content is of no
* interest anymore. Simply discard the pte, vmscan
* will take care of the rest.
* A future reference will then fault in a new zero
* page. When userfaultfd is active, we must not drop
* this page though, as its main user (postcopy
* migration) will not expect userfaults on already
* copied pages.
*/
dec_mm_counter(mm, mm_counter(folio));
} else if (folio_test_anon(folio)) {
swp_entry_t entry = page_swap_entry(subpage);
pte_t swp_pte;
/*
* Store the swap location in the pte.
* See handle_pte_fault() ...
*/
if (unlikely(folio_test_swapbacked(folio) !=
folio_test_swapcache(folio))) {
WARN_ON_ONCE(1);
goto walk_abort;
}
/* MADV_FREE page check */
if (!folio_test_swapbacked(folio)) {
int ref_count, map_count;
/*
* Synchronize with gup_pte_range():
* - clear PTE; barrier; read refcount
* - inc refcount; barrier; read PTE
*/
smp_mb();
ref_count = folio_ref_count(folio);
map_count = folio_mapcount(folio);
/*
* Order reads for page refcount and dirty flag
* (see comments in __remove_mapping()).
*/
smp_rmb();
if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) {
/*
* redirtied either using the page table or a previously
* obtained GUP reference.
*/
set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
folio_set_swapbacked(folio);
goto walk_abort;
} else if (ref_count != 1 + map_count) {
/*
* Additional reference. Could be a GUP reference or any
* speculative reference. GUP users must mark the folio
* dirty if there was a modification. This folio cannot be
* reclaimed right now either way, so act just like nothing
* happened.
* We'll come back here later and detect if the folio was
* dirtied when the additional reference is gone.
*/
set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
goto walk_abort;
}
add_mm_counter(mm, MM_ANONPAGES, -nr_pages);
goto discard;
}
if (swap_duplicate(entry) < 0) {
set_pte_at(mm, address, pvmw.pte, pteval);
goto walk_abort;
}
/*
* arch_unmap_one() is expected to be a NOP on
* architectures where we could have PFN swap PTEs,
* so we'll not check/care.
*/
if (arch_unmap_one(mm, vma, address, pteval) < 0) {
swap_free(entry);
set_pte_at(mm, address, pvmw.pte, pteval);
goto walk_abort;
}
/* See folio_try_share_anon_rmap(): clear PTE first. */
if (anon_exclusive &&
folio_try_share_anon_rmap_pte(folio, subpage)) {
swap_free(entry);
set_pte_at(mm, address, pvmw.pte, pteval);
goto walk_abort;
}
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
if (list_empty(&mm->mmlist))
list_add(&mm->mmlist, &init_mm.mmlist);
spin_unlock(&mmlist_lock);
}
dec_mm_counter(mm, MM_ANONPAGES);
inc_mm_counter(mm, MM_SWAPENTS);
swp_pte = swp_entry_to_pte(entry);
if (anon_exclusive)
swp_pte = pte_swp_mkexclusive(swp_pte);
if (likely(pte_present(pteval))) {
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
if (pte_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
} else {
if (pte_swp_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
if (pte_swp_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
}
set_pte_at(mm, address, pvmw.pte, swp_pte);
} else {
/*
* This is a locked file-backed folio,
* so it cannot be removed from the page
* cache and replaced by a new folio before
* mmu_notifier_invalidate_range_end, so no
* concurrent thread might update its page table
* to point at a new folio while a device is
* still using this folio.
*
* See Documentation/mm/mmu_notifier.rst
*/
dec_mm_counter(mm, mm_counter_file(folio));
}
discard:
if (unlikely(folio_test_hugetlb(folio))) {
hugetlb_remove_rmap(folio);
} else {
folio_remove_rmap_ptes(folio, subpage, nr_pages, vma);
folio_ref_sub(folio, nr_pages - 1);
}
if (vma->vm_flags & VM_LOCKED)
mlock_drain_local();
folio_put(folio);
/* We have already batched the entire folio */
if (nr_pages > 1)
goto walk_done;
continue;
walk_abort:
ret = false;
walk_done:
page_vma_mapped_walk_done(&pvmw);
break;
}
mmu_notifier_invalidate_range_end(&range);
return ret;
}
static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
{
return vma_is_temporary_stack(vma);
}
static int folio_not_mapped(struct folio *folio)
{
return !folio_mapped(folio);
}
/**
* try_to_unmap - Try to remove all page table mappings to a folio.
* @folio: The folio to unmap.
* @flags: action and flags
*
* Tries to remove all the page table entries which are mapping this
* folio. It is the caller's responsibility to check if the folio is
* still mapped if needed (use TTU_SYNC to prevent accounting races).
*
* Context: Caller must hold the folio lock.
*/
void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
struct rmap_walk_control rwc = {
.rmap_one = try_to_unmap_one,
.arg = (void *)flags,
.done = folio_not_mapped,
.anon_lock = folio_lock_anon_vma_read,
};
if (flags & TTU_RMAP_LOCKED)
rmap_walk_locked(folio, &rwc);
else
rmap_walk(folio, &rwc);
}
/*
* @arg: enum ttu_flags will be passed to this argument.
*
* If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs
* containing migration entries.
*/
static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
struct mm_struct *mm = vma->vm_mm;
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
bool anon_exclusive, writable, ret = true;
pte_t pteval;
struct page *subpage;
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
unsigned long pfn;
unsigned long hsz = 0;
/*
* When racing against e.g. zap_pte_range() on another cpu,
* in between its ptep_get_and_clear_full() and folio_remove_rmap_*(),
* try_to_migrate() may return before page_mapped() has become false,
* if page table locking is skipped: use TTU_SYNC to wait for that.
*/
if (flags & TTU_SYNC)
pvmw.flags = PVMW_SYNC;
/*
* unmap_page() in mm/huge_memory.c is the only user of migration with
* TTU_SPLIT_HUGE_PMD and it wants to freeze.
*/
if (flags & TTU_SPLIT_HUGE_PMD)
split_huge_pmd_address(vma, address, true, folio);
/*
* For THP, we have to assume the worse case ie pmd for invalidation.
* For hugetlb, it could be much worse if we need to do pud
* invalidation in the case of pmd sharing.
*
* Note that the page can not be free in this function as call of
* try_to_unmap() must hold a reference on the page.
*/
range.end = vma_address_end(&pvmw);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address, range.end);
if (folio_test_hugetlb(folio)) {
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
/* We need the huge page size for set_huge_pte_at() */
hsz = huge_page_size(hstate_vma(vma));
}
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
/* PMD-mapped THP migration entry */
if (!pvmw.pte) {
subpage = folio_page(folio,
pmd_pfn(*pvmw.pmd) - folio_pfn(folio));
VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
!folio_test_pmd_mappable(folio), folio);
if (set_pmd_migration_entry(&pvmw, subpage)) {
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
}
continue;
}
#endif
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_FOLIO(!pvmw.pte, folio);
/*
* Handle PFN swap PTEs, such as device-exclusive ones, that
* actually map pages.
*/
pteval = ptep_get(pvmw.pte);
if (likely(pte_present(pteval))) {
pfn = pte_pfn(pteval);
} else {
pfn = swp_offset_pfn(pte_to_swp_entry(pteval));
VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
}
subpage = folio_page(folio, pfn - folio_pfn(folio));
address = pvmw.address;
anon_exclusive = folio_test_anon(folio) &&
PageAnonExclusive(subpage);
if (folio_test_hugetlb(folio)) {
bool anon = folio_test_anon(folio);
/*
* huge_pmd_unshare may unmap an entire PMD page.
* There is no way of knowing exactly which PMDs may
* be cached for this mm, so we must flush them all.
* start/end were already adjusted above to cover this
* range.
*/
flush_cache_range(vma, range.start, range.end);
/*
* To call huge_pmd_unshare, i_mmap_rwsem must be
* held in write mode. Caller needs to explicitly
* do this outside rmap routines.
*
* We also must hold hugetlb vma_lock in write mode.
* Lock order dictates acquiring vma_lock BEFORE
* i_mmap_rwsem. We can only try lock here and
* fail if unsuccessful.
*/
if (!anon) {
VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
if (!hugetlb_vma_trylock_write(vma)) {
page_vma_mapped_walk_done(&pvmw);
ret = false;
break;
}
if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) {
hugetlb_vma_unlock_write(vma);
flush_tlb_range(vma,
range.start, range.end);
/*
* The ref count of the PMD page was
* dropped which is part of the way map
* counting is done for shared PMDs.
* Return 'true' here. When there is
* no other sharing, huge_pmd_unshare
* returns false and we will unmap the
* actual page and drop map count
* to zero.
*/
page_vma_mapped_walk_done(&pvmw);
break;
}
hugetlb_vma_unlock_write(vma);
}
/* Nuke the hugetlb page table entry */
pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
if (pte_dirty(pteval))
folio_mark_dirty(folio);
writable = pte_write(pteval);
} else if (likely(pte_present(pteval))) {
flush_cache_page(vma, address, pfn);
/* Nuke the page table entry. */
if (should_defer_flush(mm, flags)) {
/*
* We clear the PTE but do not flush so potentially
* a remote CPU could still be writing to the folio.
* If the entry was previously clean then the
* architecture must guarantee that a clear->dirty
* transition on a cached TLB entry is written through
* and traps if the PTE is unmapped.
*/
pteval = ptep_get_and_clear(mm, address, pvmw.pte);
set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE);
} else {
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
if (pte_dirty(pteval))
folio_mark_dirty(folio);
writable = pte_write(pteval);
} else {
pte_clear(mm, address, pvmw.pte);
writable = is_writable_device_private_entry(pte_to_swp_entry(pteval));
}
VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) &&
!anon_exclusive, folio);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
if (PageHWPoison(subpage)) {
VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio);
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
set_huge_pte_at(mm, address, pvmw.pte, pteval,
hsz);
} else {
dec_mm_counter(mm, mm_counter(folio));
set_pte_at(mm, address, pvmw.pte, pteval);
}
} else if (likely(pte_present(pteval)) && pte_unused(pteval) &&
!userfaultfd_armed(vma)) {
/*
* The guest indicated that the page content is of no
* interest anymore. Simply discard the pte, vmscan
* will take care of the rest.
* A future reference will then fault in a new zero
* page. When userfaultfd is active, we must not drop
* this page though, as its main user (postcopy
* migration) will not expect userfaults on already
* copied pages.
*/
dec_mm_counter(mm, mm_counter(folio));
} else {
swp_entry_t entry;
pte_t swp_pte;
/*
* arch_unmap_one() is expected to be a NOP on
* architectures where we could have PFN swap PTEs,
* so we'll not check/care.
*/
if (arch_unmap_one(mm, vma, address, pteval) < 0) {
if (folio_test_hugetlb(folio))
set_huge_pte_at(mm, address, pvmw.pte,
pteval, hsz);
else
set_pte_at(mm, address, pvmw.pte, pteval);
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
}
/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
if (folio_test_hugetlb(folio)) {
if (anon_exclusive &&
hugetlb_try_share_anon_rmap(folio)) {
set_huge_pte_at(mm, address, pvmw.pte,
pteval, hsz);
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
}
} else if (anon_exclusive &&
folio_try_share_anon_rmap_pte(folio, subpage)) {
set_pte_at(mm, address, pvmw.pte, pteval);
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
}
/*
* Store the pfn of the page in a special migration
* pte. do_swap_page() will wait until the migration
* pte is removed and then restart fault handling.
*/
if (writable)
entry = make_writable_migration_entry(
page_to_pfn(subpage));
else if (anon_exclusive)
entry = make_readable_exclusive_migration_entry(
page_to_pfn(subpage));
else
entry = make_readable_migration_entry(
page_to_pfn(subpage));
if (likely(pte_present(pteval))) {
if (pte_young(pteval))
entry = make_migration_entry_young(entry);
if (pte_dirty(pteval))
entry = make_migration_entry_dirty(entry);
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
if (pte_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
} else {
swp_pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
if (pte_swp_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
}
if (folio_test_hugetlb(folio))
set_huge_pte_at(mm, address, pvmw.pte, swp_pte,
hsz);
else
set_pte_at(mm, address, pvmw.pte, swp_pte);
trace_set_migration_pte(address, pte_val(swp_pte),
folio_order(folio));
/*
* No need to invalidate here it will synchronize on
* against the special swap migration pte.
*/
}
if (unlikely(folio_test_hugetlb(folio)))
hugetlb_remove_rmap(folio);
else
folio_remove_rmap_pte(folio, subpage, vma);
if (vma->vm_flags & VM_LOCKED)
mlock_drain_local();
folio_put(folio);
}
mmu_notifier_invalidate_range_end(&range);
return ret;
}
/**
* try_to_migrate - try to replace all page table mappings with swap entries
* @folio: the folio to replace page table entries for
* @flags: action and flags
*
* Tries to remove all the page table entries which are mapping this folio and
* replace them with special swap entries. Caller must hold the folio lock.
*/
void try_to_migrate(struct folio *folio, enum ttu_flags flags)
{
struct rmap_walk_control rwc = {
.rmap_one = try_to_migrate_one,
.arg = (void *)flags,
.done = folio_not_mapped,
.anon_lock = folio_lock_anon_vma_read,
};
/*
* Migration always ignores mlock and only supports TTU_RMAP_LOCKED and
* TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags.
*/
if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
TTU_SYNC | TTU_BATCH_FLUSH)))
return;
if (folio_is_zone_device(folio) &&
(!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
return;
/*
* During exec, a temporary VMA is setup and later moved.
* The VMA is moved under the anon_vma lock but not the
* page tables leading to a race where migration cannot
* find the migration ptes. Rather than increasing the
* locking requirements of exec(), migration skips
* temporary VMAs until after exec() completes.
*/
if (!folio_test_ksm(folio) && folio_test_anon(folio))
rwc.invalid_vma = invalid_migration_vma;
if (flags & TTU_RMAP_LOCKED)
rmap_walk_locked(folio, &rwc);
else
rmap_walk(folio, &rwc);
}
#ifdef CONFIG_DEVICE_PRIVATE
/**
* make_device_exclusive() - Mark a page for exclusive use by a device
* @mm: mm_struct of associated target process
* @addr: the virtual address to mark for exclusive device access
* @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering
* @foliop: folio pointer will be stored here on success.
*
* This function looks up the page mapped at the given address, grabs a
* folio reference, locks the folio and replaces the PTE with special
* device-exclusive PFN swap entry, preventing access through the process
* page tables. The function will return with the folio locked and referenced.
*
* On fault, the device-exclusive entries are replaced with the original PTE
* under folio lock, after calling MMU notifiers.
*
* Only anonymous non-hugetlb folios are supported and the VMA must have
* write permissions such that we can fault in the anonymous page writable
* in order to mark it exclusive. The caller must hold the mmap_lock in read
* mode.
*
* A driver using this to program access from a device must use a mmu notifier
* critical section to hold a device specific lock during programming. Once
* programming is complete it should drop the folio lock and reference after
* which point CPU access to the page will revoke the exclusive access.
*
* Notes:
* #. This function always operates on individual PTEs mapping individual
* pages. PMD-sized THPs are first remapped to be mapped by PTEs before
* the conversion happens on a single PTE corresponding to @addr.
* #. While concurrent access through the process page tables is prevented,
* concurrent access through other page references (e.g., earlier GUP
* invocation) is not handled and not supported.
* #. device-exclusive entries are considered "clean" and "old" by core-mm.
* Device drivers must update the folio state when informed by MMU
* notifiers.
*
* Returns: pointer to mapped page on success, otherwise a negative error.
*/
struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
void *owner, struct folio **foliop)
{
struct mmu_notifier_range range;
struct folio *folio, *fw_folio;
struct vm_area_struct *vma;
struct folio_walk fw;
struct page *page;
swp_entry_t entry;
pte_t swp_pte;
int ret;
mmap_assert_locked(mm);
addr = PAGE_ALIGN_DOWN(addr);
/*
* Fault in the page writable and try to lock it; note that if the
* address would already be marked for exclusive use by a device,
* the GUP call would undo that first by triggering a fault.
*
* If any other device would already map this page exclusively, the
* fault will trigger a conversion to an ordinary
* (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE.
*/
retry:
page = get_user_page_vma_remote(mm, addr,
FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD,
&vma);
if (IS_ERR(page))
return page;
folio = page_folio(page);
if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) {
folio_put(folio);
return ERR_PTR(-EOPNOTSUPP);
}
ret = folio_lock_killable(folio);
if (ret) {
folio_put(folio);
return ERR_PTR(ret);
}
/*
* Inform secondary MMUs that we are going to convert this PTE to
* device-exclusive, such that they unmap it now. Note that the
* caller must filter this event out to prevent livelocks.
*/
mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
mm, addr, addr + PAGE_SIZE, owner);
mmu_notifier_invalidate_range_start(&range);
/*
* Let's do a second walk and make sure we still find the same page
* mapped writable. Note that any page of an anonymous folio can
* only be mapped writable using exactly one PTE ("exclusive"), so
* there cannot be other mappings.
*/
fw_folio = folio_walk_start(&fw, vma, addr, 0);
if (fw_folio != folio || fw.page != page ||
fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) {
if (fw_folio)
folio_walk_end(&fw, vma);
mmu_notifier_invalidate_range_end(&range);
folio_unlock(folio);
folio_put(folio);
goto retry;
}
/* Nuke the page table entry so we get the uptodate dirty bit. */
flush_cache_page(vma, addr, page_to_pfn(page));
fw.pte = ptep_clear_flush(vma, addr, fw.ptep);
/* Set the dirty flag on the folio now the PTE is gone. */
if (pte_dirty(fw.pte))
folio_mark_dirty(folio);
/*
* Store the pfn of the page in a special device-exclusive PFN swap PTE.
* do_swap_page() will trigger the conversion back while holding the
* folio lock.
*/
entry = make_device_exclusive_entry(page_to_pfn(page));
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(fw.pte))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
/* The pte is writable, uffd-wp does not apply. */
set_pte_at(mm, addr, fw.ptep, swp_pte);
folio_walk_end(&fw, vma);
mmu_notifier_invalidate_range_end(&range);
*foliop = folio;
return page;
}
EXPORT_SYMBOL_GPL(make_device_exclusive);
#endif
void __put_anon_vma(struct anon_vma *anon_vma)
{
struct anon_vma *root = anon_vma->root;
anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root);
}
static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio,
struct rmap_walk_control *rwc)
{
struct anon_vma *anon_vma;
if (rwc->anon_lock)
return rwc->anon_lock(folio, rwc);
/*
* Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read()
* because that depends on page_mapped(); but not all its usages
* are holding mmap_lock. Users without mmap_lock are required to
* take a reference count to prevent the anon_vma disappearing
*/
anon_vma = folio_anon_vma(folio);
if (!anon_vma)
return NULL;
if (anon_vma_trylock_read(anon_vma))
goto out;
if (rwc->try_lock) {
anon_vma = NULL;
rwc->contended = true;
goto out;
}
anon_vma_lock_read(anon_vma);
out:
return anon_vma;
}
/*
* rmap_walk_anon - do something to anonymous page using the object-based
* rmap method
* @folio: the folio to be handled
* @rwc: control variable according to each walk type
* @locked: caller holds relevant rmap lock
*
* Find all the mappings of a folio using the mapping pointer and the vma
* chains contained in the anon_vma struct it points to.
*/
static void rmap_walk_anon(struct folio *folio,
struct rmap_walk_control *rwc, bool locked)
{
struct anon_vma *anon_vma;
pgoff_t pgoff_start, pgoff_end;
struct anon_vma_chain *avc;
if (locked) {
anon_vma = folio_anon_vma(folio);
/* anon_vma disappear under us? */
VM_BUG_ON_FOLIO(!anon_vma, folio);
} else {
anon_vma = rmap_walk_anon_lock(folio, rwc);
}
if (!anon_vma)
return;
pgoff_start = folio_pgoff(folio);
pgoff_end = pgoff_start + folio_nr_pages(folio) - 1;
anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
pgoff_start, pgoff_end) {
struct vm_area_struct *vma = avc->vma;
unsigned long address = vma_address(vma, pgoff_start,
folio_nr_pages(folio));
VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
continue;
if (!rwc->rmap_one(folio, vma, address, rwc->arg))
break;
if (rwc->done && rwc->done(folio))
break;
}
if (!locked)
anon_vma_unlock_read(anon_vma);
}
/**
* __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping
* of a page mapped within a specified page cache object at a specified offset.
*
* @folio: Either the folio whose mappings to traverse, or if NULL,
* the callbacks specified in @rwc will be configured such
* as to be able to look up mappings correctly.
* @mapping: The page cache object whose mapping VMAs we intend to
* traverse. If @folio is non-NULL, this should be equal to
* folio_mapping(folio).
* @pgoff_start: The offset within @mapping of the page which we are
* looking up. If @folio is non-NULL, this should be equal
* to folio_pgoff(folio).
* @nr_pages: The number of pages mapped by the mapping. If @folio is
* non-NULL, this should be equal to folio_nr_pages(folio).
* @rwc: The reverse mapping walk control object describing how
* the traversal should proceed.
* @locked: Is the @mapping already locked? If not, we acquire the
* lock.
*/
static void __rmap_walk_file(struct folio *folio, struct address_space *mapping,
pgoff_t pgoff_start, unsigned long nr_pages,
struct rmap_walk_control *rwc, bool locked)
{
pgoff_t pgoff_end = pgoff_start + nr_pages - 1;
struct vm_area_struct *vma;
VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio);
VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio);
VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio);
if (!locked) {
if (i_mmap_trylock_read(mapping))
goto lookup;
if (rwc->try_lock) {
rwc->contended = true;
return;
}
i_mmap_lock_read(mapping);
}
lookup:
vma_interval_tree_foreach(vma, &mapping->i_mmap,
pgoff_start, pgoff_end) {
unsigned long address = vma_address(vma, pgoff_start, nr_pages);
VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
continue;
if (!rwc->rmap_one(folio, vma, address, rwc->arg))
goto done;
if (rwc->done && rwc->done(folio))
goto done;
}
done:
if (!locked)
i_mmap_unlock_read(mapping);
}
/*
* rmap_walk_file - do something to file page using the object-based rmap method
* @folio: the folio to be handled
* @rwc: control variable according to each walk type
* @locked: caller holds relevant rmap lock
*
* Find all the mappings of a folio using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
*/
static void rmap_walk_file(struct folio *folio,
struct rmap_walk_control *rwc, bool locked)
{
/*
* The folio lock not only makes sure that folio->mapping cannot
* suddenly be NULLified by truncation, it makes sure that the structure
* at mapping cannot be freed and reused yet, so we can safely take
* mapping->i_mmap_rwsem.
*/
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (!folio->mapping)
return;
__rmap_walk_file(folio, folio->mapping, folio->index,
folio_nr_pages(folio), rwc, locked);
}
void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc)
{
if (unlikely(folio_test_ksm(folio)))
rmap_walk_ksm(folio, rwc);
else if (folio_test_anon(folio))
rmap_walk_anon(folio, rwc, false);
else
rmap_walk_file(folio, rwc, false);
}
/* Like rmap_walk, but caller holds relevant rmap lock */
void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
{
/* no ksm support for now */
VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio);
if (folio_test_anon(folio))
rmap_walk_anon(folio, rwc, true);
else
rmap_walk_file(folio, rwc, true);
}
#ifdef CONFIG_HUGETLB_PAGE
/*
* The following two functions are for anonymous (private mapped) hugepages.
* Unlike common anonymous pages, anonymous hugepages have no accounting code
* and no lru code, because we handle hugepages differently from common pages.
*/
void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
unsigned long address, rmap_t flags)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
atomic_inc(&folio->_entire_mapcount);
atomic_inc(&folio->_large_mapcount);
if (flags & RMAP_EXCLUSIVE)
SetPageAnonExclusive(&folio->page);
VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 &&
PageAnonExclusive(&folio->page), folio);
}
void hugetlb_add_new_anon_rmap(struct folio *folio,
struct vm_area_struct *vma, unsigned long address)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
/* increment count (starts at -1) */
atomic_set(&folio->_entire_mapcount, 0);
atomic_set(&folio->_large_mapcount, 0);
folio_clear_hugetlb_restore_reserve(folio);
__folio_set_anon(folio, vma, address, true);
SetPageAnonExclusive(&folio->page);
}
#endif /* CONFIG_HUGETLB_PAGE */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_FIND_H_
#define __LINUX_FIND_H_
#ifndef __LINUX_BITMAP_H
#error only <linux/bitmap.h> can be included directly
#endif
#include <linux/bitops.h>
unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits,
unsigned long start);
unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long nbits, unsigned long start);
unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long nbits, unsigned long start);
unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long nbits, unsigned long start);
unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
unsigned long start);
extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n);
unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long size, unsigned long n);
unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long size, unsigned long n);
unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
const unsigned long *addr3, unsigned long size,
unsigned long n);
extern unsigned long _find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size);
unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2,
const unsigned long *addr3, unsigned long size);
extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
#ifdef __BIG_ENDIAN
unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size);
unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned
long size, unsigned long offset);
unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
long size, unsigned long offset);
#endif
#ifndef find_next_bit
/**
* find_next_bit - find the next set bit in a memory region
* @addr: The address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_bit(addr, size, offset);
}
#endif
#ifndef find_next_and_bit
/**
* find_next_and_bit - find the next set bit in both memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr1 & *addr2 & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_and_bit(addr1, addr2, size, offset);
}
#endif
#ifndef find_next_andnot_bit
/**
* find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits
* in *addr2
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_andnot_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr1 & ~*addr2 & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_andnot_bit(addr1, addr2, size, offset);
}
#endif
#ifndef find_next_or_bit
/**
* find_next_or_bit - find the next set bit in either memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_or_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = (*addr1 | *addr2) & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_or_bit(addr1, addr2, size, offset);
}
#endif
#ifndef find_next_zero_bit
/**
* find_next_zero_bit - find the next cleared bit in a memory region
* @addr: The address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number of the next zero bit
* If no bits are zero, returns @size.
*/
static __always_inline
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val;
if (unlikely(offset >= size))
return size;
val = *addr | ~GENMASK(size - 1, offset);
return val == ~0UL ? size : ffz(val);
}
return _find_next_zero_bit(addr, size, offset);
}
#endif
#ifndef find_first_bit
/**
* find_first_bit - find the first set bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
*
* Returns the bit number of the first set bit.
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr & GENMASK(size - 1, 0);
return val ? __ffs(val) : size;
}
return _find_first_bit(addr, size);
}
#endif
/**
* find_nth_bit - find N'th set bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
* @n: The number of set bit, which position is needed, counting from 0
*
* The following is semantically equivalent:
* idx = find_nth_bit(addr, size, 0);
* idx = find_first_bit(addr, size);
*
* Returns the bit number of the N'th set bit.
* If no such, returns >= @size.
*/
static __always_inline
unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
{
if (n >= size)
return size;
if (small_const_nbits(size)) {
unsigned long val = *addr & GENMASK(size - 1, 0);
return val ? fns(val, n) : size;
}
return __find_nth_bit(addr, size, n);
}
/**
* find_nth_and_bit - find N'th set bit in 2 memory regions
* @addr1: The 1st address to start the search at
* @addr2: The 2nd address to start the search at
* @size: The maximum number of bits to search
* @n: The number of set bit, which position is needed, counting from 0
*
* Returns the bit number of the N'th set bit.
* If no such, returns @size.
*/
static __always_inline
unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long size, unsigned long n)
{
if (n >= size)
return size;
if (small_const_nbits(size)) {
unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
return val ? fns(val, n) : size;
}
return __find_nth_and_bit(addr1, addr2, size, n);
}
/**
* find_nth_andnot_bit - find N'th set bit in 2 memory regions,
* flipping bits in 2nd region
* @addr1: The 1st address to start the search at
* @addr2: The 2nd address to start the search at
* @size: The maximum number of bits to search
* @n: The number of set bit, which position is needed, counting from 0
*
* Returns the bit number of the N'th set bit.
* If no such, returns @size.
*/
static __always_inline
unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
unsigned long size, unsigned long n)
{
if (n >= size)
return size;
if (small_const_nbits(size)) {
unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0);
return val ? fns(val, n) : size;
}
return __find_nth_andnot_bit(addr1, addr2, size, n);
}
/**
* find_nth_and_andnot_bit - find N'th set bit in 2 memory regions,
* excluding those set in 3rd region
* @addr1: The 1st address to start the search at
* @addr2: The 2nd address to start the search at
* @addr3: The 3rd address to start the search at
* @size: The maximum number of bits to search
* @n: The number of set bit, which position is needed, counting from 0
*
* Returns the bit number of the N'th set bit.
* If no such, returns @size.
*/
static __always_inline
unsigned long find_nth_and_andnot_bit(const unsigned long *addr1,
const unsigned long *addr2,
const unsigned long *addr3,
unsigned long size, unsigned long n)
{
if (n >= size)
return size;
if (small_const_nbits(size)) {
unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0);
return val ? fns(val, n) : size;
}
return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n);
}
#ifndef find_first_and_bit
/**
* find_first_and_bit - find the first set bit in both memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
*
* Returns the bit number for the next set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_first_and_bit(const unsigned long *addr1,
const unsigned long *addr2,
unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
return val ? __ffs(val) : size;
}
return _find_first_and_bit(addr1, addr2, size);
}
#endif
/**
* find_first_and_and_bit - find the first set bit in 3 memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @addr3: The third address to base the search on
* @size: The bitmap size in bits
*
* Returns the bit number for the first set bit
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_first_and_and_bit(const unsigned long *addr1,
const unsigned long *addr2,
const unsigned long *addr3,
unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0);
return val ? __ffs(val) : size;
}
return _find_first_and_and_bit(addr1, addr2, addr3, size);
}
#ifndef find_first_zero_bit
/**
* find_first_zero_bit - find the first cleared bit in a memory region
* @addr: The address to start the search at
* @size: The maximum number of bits to search
*
* Returns the bit number of the first cleared bit.
* If no bits are zero, returns @size.
*/
static __always_inline
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr | ~GENMASK(size - 1, 0);
return val == ~0UL ? size : ffz(val);
}
return _find_first_zero_bit(addr, size);
}
#endif
#ifndef find_last_bit
/**
* find_last_bit - find the last set bit in a memory region
* @addr: The address to start the search at
* @size: The number of bits to search
*
* Returns the bit number of the last set bit, or size.
*/
static __always_inline
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = *addr & GENMASK(size - 1, 0);
return val ? __fls(val) : size;
}
return _find_last_bit(addr, size);
}
#endif
/**
* find_next_and_bit_wrap - find the next set bit in both memory regions
* @addr1: The first address to base the search on
* @addr2: The second address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit, or first set bit up to @offset
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
const unsigned long *addr2,
unsigned long size, unsigned long offset)
{
unsigned long bit = find_next_and_bit(addr1, addr2, size, offset);
if (bit < size || offset == 0)
return bit;
bit = find_first_and_bit(addr1, addr2, offset);
return bit < offset ? bit : size;
}
/**
* find_next_bit_wrap - find the next set bit in a memory region
* @addr: The address to base the search on
* @size: The bitmap size in bits
* @offset: The bitnumber to start searching at
*
* Returns the bit number for the next set bit, or first set bit up to @offset
* If no bits are set, returns @size.
*/
static __always_inline
unsigned long find_next_bit_wrap(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
unsigned long bit = find_next_bit(addr, size, offset);
if (bit < size || offset == 0)
return bit;
bit = find_first_bit(addr, offset);
return bit < offset ? bit : size;
}
/*
* Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
* before using it alone.
*/
static __always_inline
unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
unsigned long start, unsigned long n)
{
unsigned long bit;
/* If not wrapped around */
if (n > start) {
/* and have a bit, just return it. */
bit = find_next_bit(bitmap, size, n);
if (bit < size)
return bit;
/* Otherwise, wrap around and ... */
n = 0;
}
/* Search the other part. */
bit = find_next_bit(bitmap, start, n);
return bit < start ? bit : size;
}
/**
* find_next_clump8 - find next 8-bit clump with set bits in a memory region
* @clump: location to store copy of found clump
* @addr: address to base the search on
* @size: bitmap size in number of bits
* @offset: bit offset at which to start searching
*
* Returns the bit offset for the next set clump; the found clump value is
* copied to the location pointed by @clump. If no bits are set, returns @size.
*/
extern unsigned long find_next_clump8(unsigned long *clump,
const unsigned long *addr,
unsigned long size, unsigned long offset);
#define find_first_clump8(clump, bits, size) \
find_next_clump8((clump), (bits), (size), 0)
#if defined(__LITTLE_ENDIAN)
static __always_inline
unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset)
{
return find_next_zero_bit(addr, size, offset);
}
static __always_inline
unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset)
{
return find_next_bit(addr, size, offset);
}
static __always_inline
unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
{
return find_first_zero_bit(addr, size);
}
#elif defined(__BIG_ENDIAN)
#ifndef find_next_zero_bit_le
static __always_inline
unsigned long find_next_zero_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val = *(const unsigned long *)addr;
if (unlikely(offset >= size))
return size;
val = swab(val) | ~GENMASK(size - 1, offset);
return val == ~0UL ? size : ffz(val);
}
return _find_next_zero_bit_le(addr, size, offset);
}
#endif
#ifndef find_first_zero_bit_le
static __always_inline
unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
{
if (small_const_nbits(size)) {
unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0);
return val == ~0UL ? size : ffz(val);
}
return _find_first_zero_bit_le(addr, size);
}
#endif
#ifndef find_next_bit_le
static __always_inline
unsigned long find_next_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
if (small_const_nbits(size)) {
unsigned long val = *(const unsigned long *)addr;
if (unlikely(offset >= size))
return size;
val = swab(val) & GENMASK(size - 1, offset);
return val ? __ffs(val) : size;
}
return _find_next_bit_le(addr, size, offset);
}
#endif
#else
#error "Please fix <asm/byteorder.h>"
#endif
#define for_each_set_bit(bit, addr, size) \
for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
#define for_each_and_bit(bit, addr1, addr2, size) \
for ((bit) = 0; \
(bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
(bit)++)
#define for_each_andnot_bit(bit, addr1, addr2, size) \
for ((bit) = 0; \
(bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
(bit)++)
#define for_each_or_bit(bit, addr1, addr2, size) \
for ((bit) = 0; \
(bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
(bit)++)
/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
#define for_each_clear_bit(bit, addr, size) \
for ((bit) = 0; \
(bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \
(bit)++)
/* same as for_each_clear_bit() but use bit as value to start with */
#define for_each_clear_bit_from(bit, addr, size) \
for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++)
/**
* for_each_set_bitrange - iterate over all set bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit)
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_bitrange(b, e, addr, size) \
for ((b) = 0; \
(b) = find_next_bit((addr), (size), b), \
(e) = find_next_zero_bit((addr), (size), (b) + 1), \
(b) < (size); \
(b) = (e) + 1)
/**
* for_each_set_bitrange_from - iterate over all set bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit); must be initialized
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_bitrange_from(b, e, addr, size) \
for (; \
(b) = find_next_bit((addr), (size), (b)), \
(e) = find_next_zero_bit((addr), (size), (b) + 1), \
(b) < (size); \
(b) = (e) + 1)
/**
* for_each_clear_bitrange - iterate over all unset bit ranges [b; e)
* @b: bit offset of start of current bitrange (first unset bit)
* @e: bit offset of end of current bitrange (first set bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_clear_bitrange(b, e, addr, size) \
for ((b) = 0; \
(b) = find_next_zero_bit((addr), (size), (b)), \
(e) = find_next_bit((addr), (size), (b) + 1), \
(b) < (size); \
(b) = (e) + 1)
/**
* for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e)
* @b: bit offset of start of current bitrange (first set bit); must be initialized
* @e: bit offset of end of current bitrange (first unset bit)
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_clear_bitrange_from(b, e, addr, size) \
for (; \
(b) = find_next_zero_bit((addr), (size), (b)), \
(e) = find_next_bit((addr), (size), (b) + 1), \
(b) < (size); \
(b) = (e) + 1)
/**
* for_each_set_bit_wrap - iterate over all set bits starting from @start, and
* wrapping around the end of bitmap.
* @bit: offset for current iteration
* @addr: bitmap address to base the search on
* @size: bitmap size in number of bits
* @start: Starting bit for bitmap traversing, wrapping around the bitmap end
*/
#define for_each_set_bit_wrap(bit, addr, size, start) \
for ((bit) = find_next_bit_wrap((addr), (size), (start)); \
(bit) < (size); \
(bit) = __for_each_wrap((addr), (size), (start), (bit) + 1))
/**
* for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits
* @start: bit offset to start search and to store the current iteration offset
* @clump: location to store copy of current 8-bit clump
* @bits: bitmap address to base the search on
* @size: bitmap size in number of bits
*/
#define for_each_set_clump8(start, clump, bits, size) \
for ((start) = find_first_clump8(&(clump), (bits), (size)); \
(start) < (size); \
(start) = find_next_clump8(&(clump), (bits), (size), (start) + 8))
#endif /*__LINUX_FIND_H_ */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Macros for manipulating and testing page->flags
*/
#ifndef PAGE_FLAGS_H
#define PAGE_FLAGS_H
#include <linux/types.h>
#include <linux/bug.h>
#include <linux/mmdebug.h>
#ifndef __GENERATING_BOUNDS_H
#include <linux/mm_types.h>
#include <generated/bounds.h>
#endif /* !__GENERATING_BOUNDS_H */
/*
* Various page->flags bits:
*
* PG_reserved is set for special pages. The "struct page" of such a page
* should in general not be touched (e.g. set dirty) except by its owner.
* Pages marked as PG_reserved include:
* - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS,
* initrd, HW tables)
* - Pages reserved or allocated early during boot (before the page allocator
* was initialized). This includes (depending on the architecture) the
* initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much
* much more. Once (if ever) freed, PG_reserved is cleared and they will
* be given to the page allocator.
* - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying
* to read/write these pages might end badly. Don't touch!
* - The zero page(s)
* - Pages allocated in the context of kexec/kdump (loaded kernel image,
* control pages, vmcoreinfo)
* - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are
* not marked PG_reserved (as they might be in use by somebody else who does
* not respect the caching strategy).
* - MCA pages on ia64
* - Pages holding CPU notes for POWER Firmware Assisted Dump
* - Device memory (e.g. PMEM, DAX, HMM)
* Some PG_reserved pages will be excluded from the hibernation image.
* PG_reserved does in general not hinder anybody from dumping or swapping
* and is no longer required for remap_pfn_range(). ioremap might require it.
* Consequently, PG_reserved for a page mapped into user space can indicate
* the zero page, the vDSO, MMIO pages or device memory.
*
* The PG_private bitflag is set on pagecache pages if they contain filesystem
* specific data (which is normally at page->private). It can be used by
* private allocations for its own usage.
*
* During initiation of disk I/O, PG_locked is set. This bit is set before I/O
* and cleared when writeback _starts_ or when read _completes_. PG_writeback
* is set before writeback starts and cleared when it finishes.
*
* PG_locked also pins a page in pagecache, and blocks truncation of the file
* while it is held.
*
* page_waitqueue(page) is a wait queue of all tasks waiting for the page
* to become unlocked.
*
* PG_swapbacked is set when a page uses swap as a backing storage. This are
* usually PageAnon or shmem pages but please note that even anonymous pages
* might lose their PG_swapbacked flag when they simply can be dropped (e.g. as
* a result of MADV_FREE).
*
* PG_referenced, PG_reclaim are used for page reclaim for anonymous and
* file-backed pagecache (see mm/vmscan.c).
*
* PG_arch_1 is an architecture specific page state bit. The generic code
* guarantees that this bit is cleared for a page when it first is entered into
* the page cache.
*
* PG_hwpoison indicates that a page got corrupted in hardware and contains
* data with incorrect ECC bits that triggered a machine check. Accessing is
* not safe since it may cause another machine check. Don't touch!
*/
/*
* Don't use the pageflags directly. Use the PageFoo macros.
*
* The page flags field is split into two parts, the main flags area
* which extends from the low bits upwards, and the fields area which
* extends from the high bits downwards.
*
* | FIELD | ... | FLAGS |
* N-1 ^ 0
* (NR_PAGEFLAGS)
*
* The fields area is reserved for fields mapping zone, node (for NUMA) and
* SPARSEMEM section (for variants of SPARSEMEM that require section ids like
* SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP).
*/
enum pageflags {
PG_locked, /* Page is locked. Don't touch. */
PG_writeback, /* Page is under writeback */
PG_referenced,
PG_uptodate,
PG_dirty,
PG_lru,
PG_head, /* Must be in bit 6 */
PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
PG_active,
PG_workingset,
PG_owner_priv_1, /* Owner use. If pagecache, fs may use */
PG_owner_2, /* Owner use. If pagecache, fs may use */
PG_arch_1,
PG_reserved,
PG_private, /* If pagecache, has fs-private data */
PG_private_2, /* If pagecache, has fs aux data */
PG_reclaim, /* To be reclaimed asap */
PG_swapbacked, /* Page is backed by RAM/swap */
PG_unevictable, /* Page is "unevictable" */
PG_dropbehind, /* drop pages on IO completion */
#ifdef CONFIG_MMU
PG_mlocked, /* Page is vma mlocked */
#endif
#ifdef CONFIG_MEMORY_FAILURE
PG_hwpoison, /* hardware poisoned page. Don't touch */
#endif
#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
PG_young,
PG_idle,
#endif
#ifdef CONFIG_ARCH_USES_PG_ARCH_2
PG_arch_2,
#endif
#ifdef CONFIG_ARCH_USES_PG_ARCH_3
PG_arch_3,
#endif
__NR_PAGEFLAGS,
PG_readahead = PG_reclaim,
/* Anonymous memory (and shmem) */
PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */
/* Some filesystems */
PG_checked = PG_owner_priv_1,
/*
* Depending on the way an anonymous folio can be mapped into a page
* table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped
* THP), PG_anon_exclusive may be set only for the head page or for
* tail pages of an anonymous folio. For now, we only expect it to be
* set on tail pages for PTE-mapped THP.
*/
PG_anon_exclusive = PG_owner_2,
/*
* Set if all buffer heads in the folio are mapped.
* Filesystems which do not use BHs can use it for their own purpose.
*/
PG_mappedtodisk = PG_owner_2,
/* Two page bits are conscripted by FS-Cache to maintain local caching
* state. These bits are set on pages belonging to the netfs's inodes
* when those inodes are being locally cached.
*/
PG_fscache = PG_private_2, /* page backed by cache */
/* XEN */
/* Pinned in Xen as a read-only pagetable page. */
PG_pinned = PG_owner_priv_1,
/* Pinned as part of domain save (see xen_mm_pin_all()). */
PG_savepinned = PG_dirty,
/* Has a grant mapping of another (foreign) domain's page. */
PG_foreign = PG_owner_priv_1,
/* Remapped by swiotlb-xen. */
PG_xen_remapped = PG_owner_priv_1,
/* non-lru isolated movable page */
PG_isolated = PG_reclaim,
/* Only valid for buddy pages. Used to track pages that are reported */
PG_reported = PG_uptodate,
#ifdef CONFIG_MEMORY_HOTPLUG
/* For self-hosted memmap pages */
PG_vmemmap_self_hosted = PG_owner_priv_1,
#endif
/*
* Flags only valid for compound pages. Stored in first tail page's
* flags word. Cannot use the first 8 flags or any flag marked as
* PF_ANY.
*/
/* At least one page in this folio has the hwpoison flag set */
PG_has_hwpoisoned = PG_active,
PG_large_rmappable = PG_workingset, /* anon or file-backed */
PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */
};
#define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1)
#ifndef __GENERATING_BOUNDS_H
#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key);
/*
* Return the real head page struct iff the @page is a fake head page, otherwise
* return the @page itself. See Documentation/mm/vmemmap_dedup.rst.
*/
static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
{
if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
return page;
/*
* Only addresses aligned with PAGE_SIZE of struct page may be fake head
* struct page. The alignment check aims to avoid access the fields (
* e.g. compound_head) of the @page[1]. It can avoid touch a (possibly)
* cold cacheline in some cases.
*/
if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) &&
test_bit(PG_head, &page->flags)) {
/*
* We can safely access the field of the @page[1] with PG_head
* because the @page is a compound page composed with at least
* two contiguous pages.
*/
unsigned long head = READ_ONCE(page[1].compound_head);
if (likely(head & 1))
return (const struct page *)(head - 1);
}
return page;
}
static __always_inline bool page_count_writable(const struct page *page, int u)
{
if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
return true;
/*
* The refcount check is ordered before the fake-head check to prevent
* the following race:
* CPU 1 (HVO) CPU 2 (speculative PFN walker)
*
* page_ref_freeze()
* synchronize_rcu()
* rcu_read_lock()
* page_is_fake_head() is false
* vmemmap_remap_pte()
* XXX: struct page[] becomes r/o
*
* page_ref_unfreeze()
* page_ref_count() is not zero
*
* atomic_add_unless(&page->_refcount)
* XXX: try to modify r/o struct page[]
*
* The refcount check also prevents modification attempts to other (r/o)
* tail pages that are not fake heads.
*/
if (atomic_read_acquire(&page->_refcount) == u)
return false;
return page_fixed_fake_head(page) == page;
}
#else
static inline const struct page *page_fixed_fake_head(const struct page *page)
{
return page;
}
static inline bool page_count_writable(const struct page *page, int u)
{
return true;
}
#endif
static __always_inline int page_is_fake_head(const struct page *page)
{
return page_fixed_fake_head(page) != page;
}
static __always_inline unsigned long _compound_head(const struct page *page)
{
unsigned long head = READ_ONCE(page->compound_head);
if (unlikely(head & 1)) return head - 1; return (unsigned long)page_fixed_fake_head(page);
}
#define compound_head(page) ((typeof(page))_compound_head(page))
/**
* page_folio - Converts from page to folio.
* @p: The page.
*
* Every page is part of a folio. This function cannot be called on a
* NULL pointer.
*
* Context: No reference, nor lock is required on @page. If the caller
* does not hold a reference, this call may race with a folio split, so
* it should re-check the folio still contains this page after gaining
* a reference on the folio.
* Return: The folio which contains this page.
*/
#define page_folio(p) (_Generic((p), \
const struct page *: (const struct folio *)_compound_head(p), \
struct page *: (struct folio *)_compound_head(p)))
/**
* folio_page - Return a page from a folio.
* @folio: The folio.
* @n: The page number to return.
*
* @n is relative to the start of the folio. This function does not
* check that the page number lies within @folio; the caller is presumed
* to have a reference to the page.
*/
#define folio_page(folio, n) nth_page(&(folio)->page, n)
static __always_inline int PageTail(const struct page *page)
{
return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page);
}
static __always_inline int PageCompound(const struct page *page)
{
return test_bit(PG_head, &page->flags) ||
READ_ONCE(page->compound_head) & 1;
}
#define PAGE_POISON_PATTERN -1l
static inline int PagePoisoned(const struct page *page)
{
return READ_ONCE(page->flags) == PAGE_POISON_PATTERN;
}
#ifdef CONFIG_DEBUG_VM
void page_init_poison(struct page *page, size_t size);
#else
static inline void page_init_poison(struct page *page, size_t size)
{
}
#endif
static const unsigned long *const_folio_flags(const struct folio *folio,
unsigned n)
{
const struct page *page = &folio->page;
VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
return &page[n].flags;
}
static unsigned long *folio_flags(struct folio *folio, unsigned n)
{
struct page *page = &folio->page;
VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
return &page[n].flags;
}
/*
* Page flags policies wrt compound pages
*
* PF_POISONED_CHECK
* check if this struct page poisoned/uninitialized
*
* PF_ANY:
* the page flag is relevant for small, head and tail pages.
*
* PF_HEAD:
* for compound page all operations related to the page flag applied to
* head page.
*
* PF_NO_TAIL:
* modifications of the page flag must be done on small or head pages,
* checks can be done on tail pages too.
*
* PF_NO_COMPOUND:
* the page flag is not relevant for compound pages.
*
* PF_SECOND:
* the page flag is stored in the first tail page.
*/
#define PF_POISONED_CHECK(page) ({ \
VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \
page; })
#define PF_ANY(page, enforce) PF_POISONED_CHECK(page)
#define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page))
#define PF_NO_TAIL(page, enforce) ({ \
VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \
PF_POISONED_CHECK(compound_head(page)); })
#define PF_NO_COMPOUND(page, enforce) ({ \
VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \
PF_POISONED_CHECK(page); })
#define PF_SECOND(page, enforce) ({ \
VM_BUG_ON_PGFLAGS(!PageHead(page), page); \
PF_POISONED_CHECK(&page[1]); })
/* Which page is the flag stored in */
#define FOLIO_PF_ANY 0
#define FOLIO_PF_HEAD 0
#define FOLIO_PF_NO_TAIL 0
#define FOLIO_PF_NO_COMPOUND 0
#define FOLIO_PF_SECOND 1
#define FOLIO_HEAD_PAGE 0
#define FOLIO_SECOND_PAGE 1
/*
* Macros to create function definitions for page flags
*/
#define FOLIO_TEST_FLAG(name, page) \
static __always_inline bool folio_test_##name(const struct folio *folio) \
{ return test_bit(PG_##name, const_folio_flags(folio, page)); }
#define FOLIO_SET_FLAG(name, page) \
static __always_inline void folio_set_##name(struct folio *folio) \
{ set_bit(PG_##name, folio_flags(folio, page)); }
#define FOLIO_CLEAR_FLAG(name, page) \
static __always_inline void folio_clear_##name(struct folio *folio) \
{ clear_bit(PG_##name, folio_flags(folio, page)); }
#define __FOLIO_SET_FLAG(name, page) \
static __always_inline void __folio_set_##name(struct folio *folio) \
{ __set_bit(PG_##name, folio_flags(folio, page)); }
#define __FOLIO_CLEAR_FLAG(name, page) \
static __always_inline void __folio_clear_##name(struct folio *folio) \
{ __clear_bit(PG_##name, folio_flags(folio, page)); }
#define FOLIO_TEST_SET_FLAG(name, page) \
static __always_inline bool folio_test_set_##name(struct folio *folio) \
{ return test_and_set_bit(PG_##name, folio_flags(folio, page)); }
#define FOLIO_TEST_CLEAR_FLAG(name, page) \
static __always_inline bool folio_test_clear_##name(struct folio *folio) \
{ return test_and_clear_bit(PG_##name, folio_flags(folio, page)); }
#define FOLIO_FLAG(name, page) \
FOLIO_TEST_FLAG(name, page) \
FOLIO_SET_FLAG(name, page) \
FOLIO_CLEAR_FLAG(name, page)
#define TESTPAGEFLAG(uname, lname, policy) \
FOLIO_TEST_FLAG(lname, FOLIO_##policy) \
static __always_inline int Page##uname(const struct page *page) \
{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
#define SETPAGEFLAG(uname, lname, policy) \
FOLIO_SET_FLAG(lname, FOLIO_##policy) \
static __always_inline void SetPage##uname(struct page *page) \
{ set_bit(PG_##lname, &policy(page, 1)->flags); }
#define CLEARPAGEFLAG(uname, lname, policy) \
FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \
static __always_inline void ClearPage##uname(struct page *page) \
{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define __SETPAGEFLAG(uname, lname, policy) \
__FOLIO_SET_FLAG(lname, FOLIO_##policy) \
static __always_inline void __SetPage##uname(struct page *page) \
{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
#define __CLEARPAGEFLAG(uname, lname, policy) \
__FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \
static __always_inline void __ClearPage##uname(struct page *page) \
{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTSETFLAG(uname, lname, policy) \
FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \
static __always_inline int TestSetPage##uname(struct page *page) \
{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTCLEARFLAG(uname, lname, policy) \
FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \
static __always_inline int TestClearPage##uname(struct page *page) \
{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define PAGEFLAG(uname, lname, policy) \
TESTPAGEFLAG(uname, lname, policy) \
SETPAGEFLAG(uname, lname, policy) \
CLEARPAGEFLAG(uname, lname, policy)
#define __PAGEFLAG(uname, lname, policy) \
TESTPAGEFLAG(uname, lname, policy) \
__SETPAGEFLAG(uname, lname, policy) \
__CLEARPAGEFLAG(uname, lname, policy)
#define TESTSCFLAG(uname, lname, policy) \
TESTSETFLAG(uname, lname, policy) \
TESTCLEARFLAG(uname, lname, policy)
#define FOLIO_TEST_FLAG_FALSE(name) \
static inline bool folio_test_##name(const struct folio *folio) \
{ return false; }
#define FOLIO_SET_FLAG_NOOP(name) \
static inline void folio_set_##name(struct folio *folio) { }
#define FOLIO_CLEAR_FLAG_NOOP(name) \
static inline void folio_clear_##name(struct folio *folio) { }
#define __FOLIO_SET_FLAG_NOOP(name) \
static inline void __folio_set_##name(struct folio *folio) { }
#define __FOLIO_CLEAR_FLAG_NOOP(name) \
static inline void __folio_clear_##name(struct folio *folio) { }
#define FOLIO_TEST_SET_FLAG_FALSE(name) \
static inline bool folio_test_set_##name(struct folio *folio) \
{ return false; }
#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \
static inline bool folio_test_clear_##name(struct folio *folio) \
{ return false; }
#define FOLIO_FLAG_FALSE(name) \
FOLIO_TEST_FLAG_FALSE(name) \
FOLIO_SET_FLAG_NOOP(name) \
FOLIO_CLEAR_FLAG_NOOP(name)
#define TESTPAGEFLAG_FALSE(uname, lname) \
FOLIO_TEST_FLAG_FALSE(lname) \
static inline int Page##uname(const struct page *page) { return 0; }
#define SETPAGEFLAG_NOOP(uname, lname) \
FOLIO_SET_FLAG_NOOP(lname) \
static inline void SetPage##uname(struct page *page) { }
#define CLEARPAGEFLAG_NOOP(uname, lname) \
FOLIO_CLEAR_FLAG_NOOP(lname) \
static inline void ClearPage##uname(struct page *page) { }
#define __CLEARPAGEFLAG_NOOP(uname, lname) \
__FOLIO_CLEAR_FLAG_NOOP(lname) \
static inline void __ClearPage##uname(struct page *page) { }
#define TESTSETFLAG_FALSE(uname, lname) \
FOLIO_TEST_SET_FLAG_FALSE(lname) \
static inline int TestSetPage##uname(struct page *page) { return 0; }
#define TESTCLEARFLAG_FALSE(uname, lname) \
FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \
static inline int TestClearPage##uname(struct page *page) { return 0; }
#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \
SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname)
#define TESTSCFLAG_FALSE(uname, lname) \
TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname)
__PAGEFLAG(Locked, locked, PF_NO_TAIL)FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE)FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE)
__FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE)PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD)FOLIO_FLAG(active, FOLIO_HEAD_PAGE)
__FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE)
PAGEFLAG(Workingset, workingset, PF_HEAD)
TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
/* Xen */
PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND)
TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND);
PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND);
PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND)
TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND)
PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
__SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE)
__FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE)
__FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE)
/*
* Private page markings that may be used by the filesystem that owns the page
* for its own purposes.
* - PG_private and PG_private_2 cause release_folio() and co to be invoked
*/
PAGEFLAG(Private, private, PF_ANY)
FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE)
/* owner_2 can be set on tail pages for anon memory */
FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE)
/*
* Only test-and-set exist for PG_writeback. The unconditional operators are
* risky: they bypass page accounting.
*/
TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL)
TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE)
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE)
FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE)
__FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE)
#ifdef CONFIG_HIGHMEM
/*
* Must use a macro here due to header dependency issues. page_zone() is not
* available at this point.
*/
#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
#define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f))
#else
PAGEFLAG_FALSE(HighMem, highmem)
#endif
#ifdef CONFIG_SWAP
static __always_inline bool folio_test_swapcache(const struct folio *folio)
{
return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0));
}
FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE)
FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE)
#else
FOLIO_FLAG_FALSE(swapcache)
#endif
FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE)
__FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE)
#ifdef CONFIG_MMU
FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE)
__FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE)
#else
FOLIO_FLAG_FALSE(mlocked)
__FOLIO_CLEAR_FLAG_NOOP(mlocked)
FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked)
FOLIO_TEST_SET_FLAG_FALSE(mlocked)
#endif
#ifdef CONFIG_MEMORY_FAILURE
PAGEFLAG(HWPoison, hwpoison, PF_ANY)
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
#else
PAGEFLAG_FALSE(HWPoison, hwpoison)
#define __PG_HWPOISON 0
#endif
#ifdef CONFIG_PAGE_IDLE_FLAG
#ifdef CONFIG_64BIT
FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE)
FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE)
FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE)
FOLIO_FLAG(idle, FOLIO_HEAD_PAGE)
#endif
/* See page_idle.h for !64BIT workaround */
#else /* !CONFIG_PAGE_IDLE_FLAG */
FOLIO_FLAG_FALSE(young)
FOLIO_TEST_CLEAR_FLAG_FALSE(young)
FOLIO_FLAG_FALSE(idle)
#endif
/*
* PageReported() is used to track reported free pages within the Buddy
* allocator. We can use the non-atomic version of the test and set
* operations as both should be shielded with the zone lock to prevent
* any possible races on the setting or clearing of the bit.
*/
__PAGEFLAG(Reported, reported, PF_NO_COMPOUND)
#ifdef CONFIG_MEMORY_HOTPLUG
PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY)
#else
PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
#endif
/*
* On an anonymous folio mapped into a user virtual memory area,
* folio->mapping points to its anon_vma, not to a struct address_space;
* with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h.
*
* On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
* the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON
* bit; and then folio->mapping points, not to an anon_vma, but to a private
* structure which KSM associates with that merged page. See ksm.h.
*
* PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable
* page and then folio->mapping points to a struct movable_operations.
*
* Please note that, confusingly, "folio_mapping" refers to the inode
* address_space which maps the folio from disk; whereas "folio_mapped"
* refers to user virtual address space into which the folio is mapped.
*
* For slab pages, since slab reuses the bits in struct page to store its
* internal states, the folio->mapping does not exist as such, nor do
* these flags below. So in order to avoid testing non-existent bits,
* please make sure that folio_test_slab(folio) actually evaluates to
* false before calling the following functions (e.g., folio_test_anon).
* See mm/slab.h.
*/
#define PAGE_MAPPING_ANON 0x1
#define PAGE_MAPPING_MOVABLE 0x2
#define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
static __always_inline bool folio_mapping_flags(const struct folio *folio)
{
return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0;
}
static __always_inline bool PageMappingFlags(const struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
}
static __always_inline bool folio_test_anon(const struct folio *folio)
{
return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
}
static __always_inline bool PageAnonNotKsm(const struct page *page)
{
unsigned long flags = (unsigned long)page_folio(page)->mapping;
return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON;
}
static __always_inline bool PageAnon(const struct page *page)
{
return folio_test_anon(page_folio(page));
}
static __always_inline bool __folio_test_movable(const struct folio *folio)
{
return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
PAGE_MAPPING_MOVABLE;
}
static __always_inline bool __PageMovable(const struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
PAGE_MAPPING_MOVABLE;
}
#ifdef CONFIG_KSM
/*
* A KSM page is one of those write-protected "shared pages" or "merged pages"
* which KSM maps into multiple mms, wherever identical anonymous page content
* is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any
* anon_vma, but to that page's node of the stable tree.
*/
static __always_inline bool folio_test_ksm(const struct folio *folio)
{
return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
PAGE_MAPPING_KSM;
}
#else
FOLIO_TEST_FLAG_FALSE(ksm)
#endif
u64 stable_page_flags(const struct page *page);
/**
* folio_xor_flags_has_waiters - Change some folio flags.
* @folio: The folio.
* @mask: Bits set in this word will be changed.
*
* This must only be used for flags which are changed with the folio
* lock held. For example, it is unsafe to use for PG_dirty as that
* can be set without the folio lock held. It can also only be used
* on flags which are in the range 0-6 as some of the implementations
* only affect those bits.
*
* Return: Whether there are tasks waiting on the folio.
*/
static inline bool folio_xor_flags_has_waiters(struct folio *folio,
unsigned long mask)
{
return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0));
}
/**
* folio_test_uptodate - Is this folio up to date?
* @folio: The folio.
*
* The uptodate flag is set on a folio when every byte in the folio is
* at least as new as the corresponding bytes on storage. Anonymous
* and CoW folios are always uptodate. If the folio is not uptodate,
* some of the bytes in it may be; see the is_partially_uptodate()
* address_space operation.
*/
static inline bool folio_test_uptodate(const struct folio *folio)
{
bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0));
/*
* Must ensure that the data we read out of the folio is loaded
* _after_ we've loaded folio->flags to check the uptodate bit.
* We can skip the barrier if the folio is not uptodate, because
* we wouldn't be reading anything from it.
*
* See folio_mark_uptodate() for the other side of the story.
*/
if (ret) smp_rmb();
return ret;
}
static inline bool PageUptodate(const struct page *page)
{
return folio_test_uptodate(page_folio(page));
}
static __always_inline void __folio_mark_uptodate(struct folio *folio)
{
smp_wmb();
__set_bit(PG_uptodate, folio_flags(folio, 0));
}
static __always_inline void folio_mark_uptodate(struct folio *folio)
{
/*
* Memory barrier must be issued before setting the PG_uptodate bit,
* so that all previous stores issued in order to bring the folio
* uptodate are actually visible before folio_test_uptodate becomes true.
*/
smp_wmb();
set_bit(PG_uptodate, folio_flags(folio, 0));
}
static __always_inline void __SetPageUptodate(struct page *page)
{
__folio_mark_uptodate((struct folio *)page);
}
static __always_inline void SetPageUptodate(struct page *page)
{
folio_mark_uptodate((struct folio *)page);
}
CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
void __folio_start_writeback(struct folio *folio, bool keep_write);
void set_page_writeback(struct page *page);
#define folio_start_writeback(folio) \
__folio_start_writeback(folio, false)
#define folio_start_writeback_keepwrite(folio) \
__folio_start_writeback(folio, true)
static __always_inline bool folio_test_head(const struct folio *folio)
{
return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY));
}
static __always_inline int PageHead(const struct page *page)
{
PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page);
}
__SETPAGEFLAG(Head, head, PF_ANY)
__CLEARPAGEFLAG(Head, head, PF_ANY)
CLEARPAGEFLAG(Head, head, PF_ANY)
/**
* folio_test_large() - Does this folio contain more than one page?
* @folio: The folio to test.
*
* Return: True if the folio is larger than one page.
*/
static inline bool folio_test_large(const struct folio *folio)
{
return folio_test_head(folio);
}
static __always_inline void set_compound_head(struct page *page, struct page *head)
{
WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
}
static __always_inline void clear_compound_head(struct page *page)
{
WRITE_ONCE(page->compound_head, 0);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void ClearPageCompound(struct page *page)
{
BUG_ON(!PageHead(page));
ClearPageHead(page);
}
FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
#else
FOLIO_FLAG_FALSE(large_rmappable)
FOLIO_FLAG_FALSE(partially_mapped)
#endif
#define PG_head_mask ((1UL << PG_head))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* PageHuge() only returns true for hugetlbfs pages, but not for
* normal or transparent huge pages.
*
* PageTransHuge() returns true for both transparent huge and
* hugetlbfs pages, but not normal pages. PageTransHuge() can only be
* called only in the core VM paths where hugetlbfs pages can't exist.
*/
static inline int PageTransHuge(const struct page *page)
{
VM_BUG_ON_PAGE(PageTail(page), page);
return PageHead(page);
}
/*
* PageTransCompound returns true for both transparent huge pages
* and hugetlbfs pages, so it should only be called when it's known
* that hugetlbfs pages aren't involved.
*/
static inline int PageTransCompound(const struct page *page)
{
return PageCompound(page);
}
#else
TESTPAGEFLAG_FALSE(TransHuge, transhuge)
TESTPAGEFLAG_FALSE(TransCompound, transcompound)
#endif
#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
/*
* PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the
* compound page.
*
* This flag is set by hwpoison handler. Cleared by THP split or free page.
*/
FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE)
#else
FOLIO_FLAG_FALSE(has_hwpoisoned)
#endif
/*
* For pages that do not use mapcount, page_type may be used.
* The low 24 bits of pagetype may be used for your own purposes, as long
* as you are careful to not affect the top 8 bits. The low bits of
* pagetype will be overwritten when you clear the page_type from the page.
*/
enum pagetype {
/* 0x00-0x7f are positive numbers, ie mapcount */
/* Reserve 0x80-0xef for mapcount overflow. */
PGTY_buddy = 0xf0,
PGTY_offline = 0xf1,
PGTY_table = 0xf2,
PGTY_guard = 0xf3,
PGTY_hugetlb = 0xf4,
PGTY_slab = 0xf5,
PGTY_zsmalloc = 0xf6,
PGTY_unaccepted = 0xf7,
PGTY_large_kmalloc = 0xf8,
PGTY_mapcount_underflow = 0xff
};
static inline bool page_type_has_type(int page_type)
{
return page_type < (PGTY_mapcount_underflow << 24);
}
/* This takes a mapcount which is one more than page->_mapcount */
static inline bool page_mapcount_is_type(unsigned int mapcount)
{
return page_type_has_type(mapcount - 1);
}
static inline bool page_has_type(const struct page *page)
{
return page_mapcount_is_type(data_race(page->page_type));
}
#define FOLIO_TYPE_OPS(lname, fname) \
static __always_inline bool folio_test_##fname(const struct folio *folio) \
{ \
return data_race(folio->page.page_type >> 24) == PGTY_##lname; \
} \
static __always_inline void __folio_set_##fname(struct folio *folio) \
{ \
if (folio_test_##fname(folio)) \
return; \
VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \
folio); \
folio->page.page_type = (unsigned int)PGTY_##lname << 24; \
} \
static __always_inline void __folio_clear_##fname(struct folio *folio) \
{ \
if (folio->page.page_type == UINT_MAX) \
return; \
VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \
folio->page.page_type = UINT_MAX; \
}
#define PAGE_TYPE_OPS(uname, lname, fname) \
FOLIO_TYPE_OPS(lname, fname) \
static __always_inline int Page##uname(const struct page *page) \
{ \
return data_race(page->page_type >> 24) == PGTY_##lname; \
} \
static __always_inline void __SetPage##uname(struct page *page) \
{ \
if (Page##uname(page)) \
return; \
VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \
page->page_type = (unsigned int)PGTY_##lname << 24; \
} \
static __always_inline void __ClearPage##uname(struct page *page) \
{ \
if (page->page_type == UINT_MAX) \
return; \
VM_BUG_ON_PAGE(!Page##uname(page), page); \
page->page_type = UINT_MAX; \
}
/*
* PageBuddy() indicates that the page is free and in the buddy system
* (see mm/page_alloc.c).
*/
PAGE_TYPE_OPS(Buddy, buddy, buddy)
/*
* PageOffline() indicates that the page is logically offline although the
* containing section is online. (e.g. inflated in a balloon driver or
* not onlined when onlining the section).
* The content of these pages is effectively stale. Such pages should not
* be touched (read/write/dump/save) except by their owner.
*
* When a memory block gets onlined, all pages are initialized with a
* refcount of 1 and PageOffline(). generic_online_page() will
* take care of clearing PageOffline().
*
* If a driver wants to allow to offline unmovable PageOffline() pages without
* putting them back to the buddy, it can do so via the memory notifier by
* decrementing the reference count in MEM_GOING_OFFLINE and incrementing the
* reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline()
* pages (now with a reference count of zero) are treated like free (unmanaged)
* pages, allowing the containing memory block to get offlined. A driver that
* relies on this feature is aware that re-onlining the memory block will
* require not giving them to the buddy via generic_online_page().
*
* Memory offlining code will not adjust the managed page count for any
* PageOffline() pages, treating them like they were never exposed to the
* buddy using generic_online_page().
*
* There are drivers that mark a page PageOffline() and expect there won't be
* any further access to page content. PFN walkers that read content of random
* pages should check PageOffline() and synchronize with such drivers using
* page_offline_freeze()/page_offline_thaw().
*/
PAGE_TYPE_OPS(Offline, offline, offline)
extern void page_offline_freeze(void);
extern void page_offline_thaw(void);
extern void page_offline_begin(void);
extern void page_offline_end(void);
/*
* Marks pages in use as page tables.
*/
PAGE_TYPE_OPS(Table, table, pgtable)
/*
* Marks guardpages used with debug_pagealloc.
*/
PAGE_TYPE_OPS(Guard, guard, guard)
FOLIO_TYPE_OPS(slab, slab)
/**
* PageSlab - Determine if the page belongs to the slab allocator
* @page: The page to test.
*
* Context: Any context.
* Return: True for slab pages, false for any other kind of page.
*/
static inline bool PageSlab(const struct page *page)
{
return folio_test_slab(page_folio(page));
}
#ifdef CONFIG_HUGETLB_PAGE
FOLIO_TYPE_OPS(hugetlb, hugetlb)
#else
FOLIO_TEST_FLAG_FALSE(hugetlb)
#endif
PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
/*
* Mark pages that has to be accepted before touched for the first time.
*
* Serialized with zone lock.
*/
PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted)
FOLIO_TYPE_OPS(large_kmalloc, large_kmalloc)
/**
* PageHuge - Determine if the page belongs to hugetlbfs
* @page: The page to test.
*
* Context: Any context.
* Return: True for hugetlbfs pages, false for anon pages or pages
* belonging to other filesystems.
*/
static inline bool PageHuge(const struct page *page)
{
return folio_test_hugetlb(page_folio(page));
}
/*
* Check if a page is currently marked HWPoisoned. Note that this check is
* best effort only and inherently racy: there is no way to synchronize with
* failing hardware.
*/
static inline bool is_page_hwpoison(const struct page *page)
{
const struct folio *folio;
if (PageHWPoison(page))
return true;
folio = page_folio(page);
return folio_test_hugetlb(folio) && PageHWPoison(&folio->page);
}
static inline bool folio_contain_hwpoisoned_page(struct folio *folio)
{
return folio_test_hwpoison(folio) || (folio_test_large(folio) && folio_test_has_hwpoisoned(folio));
}
bool is_free_buddy_page(const struct page *page);
PAGEFLAG(Isolated, isolated, PF_ANY);
static __always_inline int PageAnonExclusive(const struct page *page)
{
VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
/*
* HugeTLB stores this information on the head page; THP keeps it per
* page
*/
if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
}
static __always_inline void SetPageAnonExclusive(struct page *page)
{
VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
}
static __always_inline void ClearPageAnonExclusive(struct page *page)
{
VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page);
VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
}
static __always_inline void __ClearPageAnonExclusive(struct page *page)
{
VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
__clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
}
#ifdef CONFIG_MMU
#define __PG_MLOCKED (1UL << PG_mlocked)
#else
#define __PG_MLOCKED 0
#endif
/*
* Flags checked when a page is freed. Pages being freed should not have
* these flags set. If they are, there is a problem.
*/
#define PAGE_FLAGS_CHECK_AT_FREE \
(1UL << PG_lru | 1UL << PG_locked | \
1UL << PG_private | 1UL << PG_private_2 | \
1UL << PG_writeback | 1UL << PG_reserved | \
1UL << PG_active | \
1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK)
/*
* Flags checked when a page is prepped for return by the page allocator.
* Pages being prepped should not have these flags set. If they are set,
* there has been a kernel bug or struct page corruption.
*
* __PG_HWPOISON is exceptional because it needs to be kept beyond page's
* alloc-free cycle to prevent from reusing the page.
*/
#define PAGE_FLAGS_CHECK_AT_PREP \
((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK)
/*
* Flags stored in the second page of a compound page. They may overlap
* the CHECK_AT_FREE flags above, so need to be cleared.
*/
#define PAGE_FLAGS_SECOND \
(0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \
1UL << PG_large_rmappable | 1UL << PG_partially_mapped)
#define PAGE_FLAGS_PRIVATE \
(1UL << PG_private | 1UL << PG_private_2)
/**
* folio_has_private - Determine if folio has private stuff
* @folio: The folio to be checked
*
* Determine if a folio has private stuff, indicating that release routines
* should be invoked upon it.
*/
static inline int folio_has_private(const struct folio *folio)
{
return !!(folio->flags & PAGE_FLAGS_PRIVATE);
}
static inline bool folio_test_large_maybe_mapped_shared(const struct folio *folio)
{
return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids);
}
#undef PF_ANY
#undef PF_HEAD
#undef PF_NO_TAIL
#undef PF_NO_COMPOUND
#undef PF_SECOND
#endif /* !__GENERATING_BOUNDS_H */
#endif /* PAGE_FLAGS_H */
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Definitions for the 'struct ptr_ring' datastructure.
*
* Author:
* Michael S. Tsirkin <mst@redhat.com>
*
* Copyright (C) 2016 Red Hat, Inc.
*
* This is a limited-size FIFO maintaining pointers in FIFO order, with
* one CPU producing entries and another consuming entries from a FIFO.
*
* This implementation tries to minimize cache-contention when there is a
* single producer and a single consumer CPU.
*/
#ifndef _LINUX_PTR_RING_H
#define _LINUX_PTR_RING_H 1
#ifdef __KERNEL__
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <asm/errno.h>
#endif
struct ptr_ring {
int producer ____cacheline_aligned_in_smp;
spinlock_t producer_lock;
int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */
int consumer_tail; /* next entry to invalidate */
spinlock_t consumer_lock;
/* Shared consumer/producer data */
/* Read-only by both the producer and the consumer */
int size ____cacheline_aligned_in_smp; /* max entries in queue */
int batch; /* number of entries to consume in a batch */
void **queue;
};
/* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax().
*
* NB: this is unlike __ptr_ring_empty in that callers must hold producer_lock:
* see e.g. ptr_ring_full.
*/
static inline bool __ptr_ring_full(struct ptr_ring *r)
{
return r->queue[r->producer];
}
static inline bool ptr_ring_full(struct ptr_ring *r)
{
bool ret;
spin_lock(&r->producer_lock);
ret = __ptr_ring_full(r);
spin_unlock(&r->producer_lock);
return ret;
}
static inline bool ptr_ring_full_irq(struct ptr_ring *r)
{
bool ret;
spin_lock_irq(&r->producer_lock);
ret = __ptr_ring_full(r);
spin_unlock_irq(&r->producer_lock);
return ret;
}
static inline bool ptr_ring_full_any(struct ptr_ring *r)
{
unsigned long flags;
bool ret;
spin_lock_irqsave(&r->producer_lock, flags);
ret = __ptr_ring_full(r);
spin_unlock_irqrestore(&r->producer_lock, flags);
return ret;
}
static inline bool ptr_ring_full_bh(struct ptr_ring *r)
{
bool ret;
spin_lock_bh(&r->producer_lock);
ret = __ptr_ring_full(r);
spin_unlock_bh(&r->producer_lock);
return ret;
}
/* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax(). Callers must hold producer_lock.
* Callers are responsible for making sure pointer that is being queued
* points to a valid data.
*/
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
if (unlikely(!r->size) || r->queue[r->producer])
return -ENOSPC;
/* Make sure the pointer we are storing points to a valid data. */
/* Pairs with the dependency ordering in __ptr_ring_consume. */
smp_wmb();
WRITE_ONCE(r->queue[r->producer++], ptr);
if (unlikely(r->producer >= r->size))
r->producer = 0;
return 0;
}
/*
* Note: resize (below) nests producer lock within consumer lock, so if you
* consume in interrupt or BH context, you must disable interrupts/BH when
* calling this.
*/
static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
int ret;
spin_lock(&r->producer_lock);
ret = __ptr_ring_produce(r, ptr);
spin_unlock(&r->producer_lock);
return ret;
}
static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr)
{
int ret;
spin_lock_irq(&r->producer_lock);
ret = __ptr_ring_produce(r, ptr);
spin_unlock_irq(&r->producer_lock);
return ret;
}
static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&r->producer_lock, flags);
ret = __ptr_ring_produce(r, ptr);
spin_unlock_irqrestore(&r->producer_lock, flags);
return ret;
}
static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
{
int ret;
spin_lock_bh(&r->producer_lock);
ret = __ptr_ring_produce(r, ptr);
spin_unlock_bh(&r->producer_lock);
return ret;
}
static inline void *__ptr_ring_peek(struct ptr_ring *r)
{
if (likely(r->size))
return READ_ONCE(r->queue[r->consumer_head]);
return NULL;
}
/*
* Test ring empty status without taking any locks.
*
* NB: This is only safe to call if ring is never resized.
*
* However, if some other CPU consumes ring entries at the same time, the value
* returned is not guaranteed to be correct.
*
* In this case - to avoid incorrectly detecting the ring
* as empty - the CPU consuming the ring entries is responsible
* for either consuming all ring entries until the ring is empty,
* or synchronizing with some other CPU and causing it to
* re-test __ptr_ring_empty and/or consume the ring enteries
* after the synchronization point.
*
* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax().
*/
static inline bool __ptr_ring_empty(struct ptr_ring *r)
{
if (likely(r->size))
return !r->queue[READ_ONCE(r->consumer_head)];
return true;
}
static inline bool ptr_ring_empty(struct ptr_ring *r)
{
bool ret;
spin_lock(&r->consumer_lock);
ret = __ptr_ring_empty(r);
spin_unlock(&r->consumer_lock);
return ret;
}
static inline bool ptr_ring_empty_irq(struct ptr_ring *r)
{
bool ret;
spin_lock_irq(&r->consumer_lock);
ret = __ptr_ring_empty(r);
spin_unlock_irq(&r->consumer_lock);
return ret;
}
static inline bool ptr_ring_empty_any(struct ptr_ring *r)
{
unsigned long flags;
bool ret;
spin_lock_irqsave(&r->consumer_lock, flags);
ret = __ptr_ring_empty(r);
spin_unlock_irqrestore(&r->consumer_lock, flags);
return ret;
}
static inline bool ptr_ring_empty_bh(struct ptr_ring *r)
{
bool ret;
spin_lock_bh(&r->consumer_lock);
ret = __ptr_ring_empty(r);
spin_unlock_bh(&r->consumer_lock);
return ret;
}
/* Must only be called after __ptr_ring_peek returned !NULL */
static inline void __ptr_ring_discard_one(struct ptr_ring *r)
{
/* Fundamentally, what we want to do is update consumer
* index and zero out the entry so producer can reuse it.
* Doing it naively at each consume would be as simple as:
* consumer = r->consumer;
* r->queue[consumer++] = NULL;
* if (unlikely(consumer >= r->size))
* consumer = 0;
* r->consumer = consumer;
* but that is suboptimal when the ring is full as producer is writing
* out new entries in the same cache line. Defer these updates until a
* batch of entries has been consumed.
*/
/* Note: we must keep consumer_head valid at all times for __ptr_ring_empty
* to work correctly.
*/
int consumer_head = r->consumer_head;
int head = consumer_head++;
/* Once we have processed enough entries invalidate them in
* the ring all at once so producer can reuse their space in the ring.
* We also do this when we reach end of the ring - not mandatory
* but helps keep the implementation simple.
*/
if (unlikely(consumer_head - r->consumer_tail >= r->batch ||
consumer_head >= r->size)) {
/* Zero out entries in the reverse order: this way we touch the
* cache line that producer might currently be reading the last;
* producer won't make progress and touch other cache lines
* besides the first one until we write out all entries.
*/
while (likely(head >= r->consumer_tail))
r->queue[head--] = NULL;
r->consumer_tail = consumer_head;
}
if (unlikely(consumer_head >= r->size)) {
consumer_head = 0;
r->consumer_tail = 0;
}
/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
WRITE_ONCE(r->consumer_head, consumer_head);
}
static inline void *__ptr_ring_consume(struct ptr_ring *r)
{
void *ptr;
/* The READ_ONCE in __ptr_ring_peek guarantees that anyone
* accessing data through the pointer is up to date. Pairs
* with smp_wmb in __ptr_ring_produce.
*/
ptr = __ptr_ring_peek(r); if (ptr) __ptr_ring_discard_one(r);
return ptr;
}
static inline int __ptr_ring_consume_batched(struct ptr_ring *r,
void **array, int n)
{
void *ptr;
int i;
for (i = 0; i < n; i++) {
ptr = __ptr_ring_consume(r);
if (!ptr)
break;
array[i] = ptr;
}
return i;
}
/*
* Note: resize (below) nests producer lock within consumer lock, so if you
* call this in interrupt or BH context, you must disable interrupts/BH when
* producing.
*/
static inline void *ptr_ring_consume(struct ptr_ring *r)
{
void *ptr;
spin_lock(&r->consumer_lock);
ptr = __ptr_ring_consume(r);
spin_unlock(&r->consumer_lock);
return ptr;
}
static inline void *ptr_ring_consume_irq(struct ptr_ring *r)
{
void *ptr;
spin_lock_irq(&r->consumer_lock);
ptr = __ptr_ring_consume(r);
spin_unlock_irq(&r->consumer_lock);
return ptr;
}
static inline void *ptr_ring_consume_any(struct ptr_ring *r)
{
unsigned long flags;
void *ptr;
spin_lock_irqsave(&r->consumer_lock, flags);
ptr = __ptr_ring_consume(r);
spin_unlock_irqrestore(&r->consumer_lock, flags);
return ptr;
}
static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
{
void *ptr;
spin_lock_bh(&r->consumer_lock);
ptr = __ptr_ring_consume(r);
spin_unlock_bh(&r->consumer_lock);
return ptr;
}
static inline int ptr_ring_consume_batched(struct ptr_ring *r,
void **array, int n)
{
int ret;
spin_lock(&r->consumer_lock);
ret = __ptr_ring_consume_batched(r, array, n);
spin_unlock(&r->consumer_lock);
return ret;
}
static inline int ptr_ring_consume_batched_irq(struct ptr_ring *r,
void **array, int n)
{
int ret;
spin_lock_irq(&r->consumer_lock);
ret = __ptr_ring_consume_batched(r, array, n);
spin_unlock_irq(&r->consumer_lock);
return ret;
}
static inline int ptr_ring_consume_batched_any(struct ptr_ring *r,
void **array, int n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&r->consumer_lock, flags);
ret = __ptr_ring_consume_batched(r, array, n);
spin_unlock_irqrestore(&r->consumer_lock, flags);
return ret;
}
static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r,
void **array, int n)
{
int ret;
spin_lock_bh(&r->consumer_lock);
ret = __ptr_ring_consume_batched(r, array, n);
spin_unlock_bh(&r->consumer_lock);
return ret;
}
/* Cast to structure type and call a function without discarding from FIFO.
* Function must return a value.
* Callers must take consumer_lock.
*/
#define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r)))
#define PTR_RING_PEEK_CALL(r, f) ({ \
typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
\
spin_lock(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
spin_unlock(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v; \
})
#define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \
typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
\
spin_lock_irq(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
spin_unlock_irq(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v; \
})
#define PTR_RING_PEEK_CALL_BH(r, f) ({ \
typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
\
spin_lock_bh(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
spin_unlock_bh(&(r)->consumer_lock); \
__PTR_RING_PEEK_CALL_v; \
})
#define PTR_RING_PEEK_CALL_ANY(r, f) ({ \
typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
unsigned long __PTR_RING_PEEK_CALL_f;\
\
spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
__PTR_RING_PEEK_CALL_v; \
})
/* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See
* documentation for vmalloc for which of them are legal.
*/
static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp)
{
if (size > KMALLOC_MAX_SIZE / sizeof(void *))
return NULL;
return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO);
}
static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
{
r->size = size;
r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue));
/* We need to set batch at least to 1 to make logic
* in __ptr_ring_discard_one work correctly.
* Batching too much (because ring is small) would cause a lot of
* burstiness. Needs tuning, for now disable batching.
*/
if (r->batch > r->size / 2 || !r->batch)
r->batch = 1;
}
static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp)
{
r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
if (!r->queue)
return -ENOMEM;
__ptr_ring_set_size(r, size);
r->producer = r->consumer_head = r->consumer_tail = 0;
spin_lock_init(&r->producer_lock);
spin_lock_init(&r->consumer_lock);
return 0;
}
#define ptr_ring_init(...) alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__))
/*
* Return entries into ring. Destroy entries that don't fit.
*
* Note: this is expected to be a rare slow path operation.
*
* Note: producer lock is nested within consumer lock, so if you
* resize you must make sure all uses nest correctly.
* In particular if you consume ring in interrupt or BH context, you must
* disable interrupts/BH when doing so.
*/
static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n,
void (*destroy)(void *))
{
unsigned long flags;
int head;
spin_lock_irqsave(&r->consumer_lock, flags);
spin_lock(&r->producer_lock);
if (!r->size)
goto done;
/*
* Clean out buffered entries (for simplicity). This way following code
* can test entries for NULL and if not assume they are valid.
*/
head = r->consumer_head - 1;
while (likely(head >= r->consumer_tail))
r->queue[head--] = NULL;
r->consumer_tail = r->consumer_head;
/*
* Go over entries in batch, start moving head back and copy entries.
* Stop when we run into previously unconsumed entries.
*/
while (n) {
head = r->consumer_head - 1;
if (head < 0)
head = r->size - 1;
if (r->queue[head]) {
/* This batch entry will have to be destroyed. */
goto done;
}
r->queue[head] = batch[--n];
r->consumer_tail = head;
/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
WRITE_ONCE(r->consumer_head, head);
}
done:
/* Destroy all entries left in the batch. */
while (n)
destroy(batch[--n]);
spin_unlock(&r->producer_lock);
spin_unlock_irqrestore(&r->consumer_lock, flags);
}
static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
int size, gfp_t gfp,
void (*destroy)(void *))
{
int producer = 0;
void **old;
void *ptr;
while ((ptr = __ptr_ring_consume(r)))
if (producer < size)
queue[producer++] = ptr;
else if (destroy)
destroy(ptr);
if (producer >= size)
producer = 0;
__ptr_ring_set_size(r, size);
r->producer = producer;
r->consumer_head = 0;
r->consumer_tail = 0;
old = r->queue;
r->queue = queue;
return old;
}
/*
* Note: producer lock is nested within consumer lock, so if you
* resize you must make sure all uses nest correctly.
* In particular if you consume ring in interrupt or BH context, you must
* disable interrupts/BH when doing so.
*/
static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp,
void (*destroy)(void *))
{
unsigned long flags;
void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
void **old;
if (!queue)
return -ENOMEM;
spin_lock_irqsave(&(r)->consumer_lock, flags);
spin_lock(&(r)->producer_lock);
old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy);
spin_unlock(&(r)->producer_lock);
spin_unlock_irqrestore(&(r)->consumer_lock, flags);
kvfree(old);
return 0;
}
#define ptr_ring_resize(...) alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__))
/*
* Note: producer lock is nested within consumer lock, so if you
* resize you must make sure all uses nest correctly.
* In particular if you consume ring in BH context, you must
* disable BH when doing so.
*/
static inline int ptr_ring_resize_multiple_bh_noprof(struct ptr_ring **rings,
unsigned int nrings,
int size, gfp_t gfp,
void (*destroy)(void *))
{
void ***queues;
int i;
queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp);
if (!queues)
goto noqueues;
for (i = 0; i < nrings; ++i) { queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp);
if (!queues[i])
goto nomem;
}
for (i = 0; i < nrings; ++i) {
spin_lock_bh(&(rings[i])->consumer_lock);
spin_lock(&(rings[i])->producer_lock);
queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
size, gfp, destroy);
spin_unlock(&(rings[i])->producer_lock);
spin_unlock_bh(&(rings[i])->consumer_lock);
}
for (i = 0; i < nrings; ++i)
kvfree(queues[i]);
kfree(queues);
return 0;
nomem:
while (--i >= 0)
kvfree(queues[i]);
kfree(queues);
noqueues:
return -ENOMEM;
}
#define ptr_ring_resize_multiple_bh(...) \
alloc_hooks(ptr_ring_resize_multiple_bh_noprof(__VA_ARGS__))
static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
{
void *ptr;
if (destroy)
while ((ptr = ptr_ring_consume(r)))
destroy(ptr);
kvfree(r->queue);
}
#endif /* _LINUX_PTR_RING_H */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/kernel/capability.c
*
* Copyright (C) 1997 Andrew Main <zefram@fysh.org>
*
* Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org>
* 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/uaccess.h>
int file_caps_enabled = 1;
static int __init file_caps_disable(char *str)
{
file_caps_enabled = 0;
return 1;
}
__setup("no_file_caps", file_caps_disable);
#ifdef CONFIG_MULTIUSER
/*
* More recent versions of libcap are available from:
*
* http://www.kernel.org/pub/linux/libs/security/linux-privs/
*/
static void warn_legacy_capability_use(void)
{
pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n",
current->comm);
}
/*
* Version 2 capabilities worked fine, but the linux/capability.h file
* that accompanied their introduction encouraged their use without
* the necessary user-space source code changes. As such, we have
* created a version 3 with equivalent functionality to version 2, but
* with a header change to protect legacy source code from using
* version 2 when it wanted to use version 1. If your system has code
* that trips the following warning, it is using version 2 specific
* capabilities and may be doing so insecurely.
*
* The remedy is to either upgrade your version of libcap (to 2.10+,
* if the application is linked against it), or recompile your
* application with modern kernel headers and this warning will go
* away.
*/
static void warn_deprecated_v2(void)
{
pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n",
current->comm);
}
/*
* Version check. Return the number of u32s in each capability flag
* array, or a negative value on error.
*/
static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
{
__u32 version;
if (get_user(version, &header->version))
return -EFAULT;
switch (version) {
case _LINUX_CAPABILITY_VERSION_1:
warn_legacy_capability_use();
*tocopy = _LINUX_CAPABILITY_U32S_1;
break;
case _LINUX_CAPABILITY_VERSION_2:
warn_deprecated_v2();
fallthrough; /* v3 is otherwise equivalent to v2 */
case _LINUX_CAPABILITY_VERSION_3:
*tocopy = _LINUX_CAPABILITY_U32S_3;
break;
default:
if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
return -EFAULT;
return -EINVAL;
}
return 0;
}
/*
* The only thing that can change the capabilities of the current
* process is the current process. As such, we can't be in this code
* at the same time as we are in the process of setting capabilities
* in this process. The net result is that we can limit our use of
* locks to when we are reading the caps of another process.
*/
static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
kernel_cap_t *pIp, kernel_cap_t *pPp)
{
int ret;
if (pid && (pid != task_pid_vnr(current))) {
const struct task_struct *target;
rcu_read_lock();
target = find_task_by_vpid(pid);
if (!target)
ret = -ESRCH;
else
ret = security_capget(target, pEp, pIp, pPp);
rcu_read_unlock();
} else
ret = security_capget(current, pEp, pIp, pPp);
return ret;
}
/**
* sys_capget - get the capabilities of a given process.
* @header: pointer to struct that contains capability version and
* target pid data
* @dataptr: pointer to struct that contains the effective, permitted,
* and inheritable capabilities that are returned
*
* Returns 0 on success and < 0 on error.
*/
SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
{
int ret = 0;
pid_t pid;
unsigned tocopy;
kernel_cap_t pE, pI, pP;
struct __user_cap_data_struct kdata[2];
ret = cap_validate_magic(header, &tocopy);
if ((dataptr == NULL) || (ret != 0))
return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;
if (get_user(pid, &header->pid))
return -EFAULT;
if (pid < 0)
return -EINVAL;
ret = cap_get_target_pid(pid, &pE, &pI, &pP);
if (ret)
return ret;
/*
* Annoying legacy format with 64-bit capabilities exposed
* as two sets of 32-bit fields, so we need to split the
* capability values up.
*/
kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32;
kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32;
kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32;
/*
* Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
* we silently drop the upper capabilities here. This
* has the effect of making older libcap
* implementations implicitly drop upper capability
* bits when they perform a: capget/modify/capset
* sequence.
*
* This behavior is considered fail-safe
* behavior. Upgrading the application to a newer
* version of libcap will enable access to the newer
* capabilities.
*
* An alternative would be to return an error here
* (-ERANGE), but that causes legacy applications to
* unexpectedly fail; the capget/modify/capset aborts
* before modification is attempted and the application
* fails.
*/
if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0])))
return -EFAULT;
return 0;
}
static kernel_cap_t mk_kernel_cap(u32 low, u32 high)
{
return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK };
}
/**
* sys_capset - set capabilities for a process or (*) a group of processes
* @header: pointer to struct that contains capability version and
* target pid data
* @data: pointer to struct that contains the effective, permitted,
* and inheritable capabilities
*
* Set capabilities for the current process only. The ability to any other
* process(es) has been deprecated and removed.
*
* The restrictions on setting capabilities are specified as:
*
* I: any raised capabilities must be a subset of the old permitted
* P: any raised capabilities must be a subset of the old permitted
* E: must be set to a subset of new permitted
*
* Returns 0 on success and < 0 on error.
*/
SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
{
struct __user_cap_data_struct kdata[2] = { { 0, }, };
unsigned tocopy, copybytes;
kernel_cap_t inheritable, permitted, effective;
struct cred *new;
int ret;
pid_t pid;
ret = cap_validate_magic(header, &tocopy);
if (ret != 0)
return ret;
if (get_user(pid, &header->pid))
return -EFAULT;
/* may only affect current now */
if (pid != 0 && pid != task_pid_vnr(current))
return -EPERM;
copybytes = tocopy * sizeof(struct __user_cap_data_struct);
if (copybytes > sizeof(kdata))
return -EFAULT;
if (copy_from_user(&kdata, data, copybytes))
return -EFAULT;
effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective);
permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted);
inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable);
new = prepare_creds();
if (!new)
return -ENOMEM;
ret = security_capset(new, current_cred(),
&effective, &inheritable, &permitted);
if (ret < 0)
goto error;
audit_log_capset(new, current_cred());
return commit_creds(new);
error:
abort_creds(new);
return ret;
}
/**
* has_ns_capability - Does a task have a capability in a specific user ns
* @t: The task in question
* @ns: target user namespace
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to the specified user namespace, false if not.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_ns_capability(struct task_struct *t,
struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE);
rcu_read_unlock();
return (ret == 0);
}
/**
* has_ns_capability_noaudit - Does a task have a capability (unaudited)
* in a specific user ns.
* @t: The task in question
* @ns: target user namespace
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to the specified user namespace, false if not.
* Do not write an audit message for the check.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_ns_capability_noaudit(struct task_struct *t,
struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT);
rcu_read_unlock();
return (ret == 0);
}
/**
* has_capability_noaudit - Does a task have a capability (unaudited) in the
* initial user ns
* @t: The task in question
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to init_user_ns, false if not. Don't write an
* audit message for the check.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_capability_noaudit(struct task_struct *t, int cap)
{
return has_ns_capability_noaudit(t, &init_user_ns, cap);
}
EXPORT_SYMBOL(has_capability_noaudit);
static bool ns_capable_common(struct user_namespace *ns,
int cap,
unsigned int opts)
{
int capable;
if (unlikely(!cap_valid(cap))) {
pr_crit("capable() called with invalid cap=%u\n", cap);
BUG();
}
capable = security_capable(current_cred(), ns, cap, opts);
if (capable == 0) { current->flags |= PF_SUPERPRIV;
return true;
}
return false;
}
/**
* ns_capable - Determine if the current task has a superior capability in effect
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable(struct user_namespace *ns, int cap)
{ return ns_capable_common(ns, cap, CAP_OPT_NONE);
}
EXPORT_SYMBOL(ns_capable);
/**
* ns_capable_noaudit - Determine if the current task has a superior capability
* (unaudited) in effect
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable_noaudit(struct user_namespace *ns, int cap)
{
return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT);
}
EXPORT_SYMBOL(ns_capable_noaudit);
/**
* ns_capable_setid - Determine if the current task has a superior capability
* in effect, while signalling that this check is being done from within a
* setid or setgroups syscall.
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable_setid(struct user_namespace *ns, int cap)
{
return ns_capable_common(ns, cap, CAP_OPT_INSETID);
}
EXPORT_SYMBOL(ns_capable_setid);
/**
* capable - Determine if the current task has a superior capability in effect
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool capable(int cap)
{ return ns_capable(&init_user_ns, cap);
}
EXPORT_SYMBOL(capable);
#endif /* CONFIG_MULTIUSER */
/**
* file_ns_capable - Determine if the file's opener had a capability in effect
* @file: The file we want to check
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if task that opened the file had a capability in effect
* when the file was opened.
*
* This does not set PF_SUPERPRIV because the caller may not
* actually be privileged.
*/
bool file_ns_capable(const struct file *file, struct user_namespace *ns,
int cap)
{
if (WARN_ON_ONCE(!cap_valid(cap)))
return false;
if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0)
return true;
return false;
}
EXPORT_SYMBOL(file_ns_capable);
/**
* privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode?
* @ns: The user namespace in question
* @idmap: idmap of the mount @inode was found from
* @inode: The inode in question
*
* Return true if the inode uid and gid are within the namespace.
*/
bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
struct mnt_idmap *idmap,
const struct inode *inode)
{
return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode));
}
/**
* capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
* @idmap: idmap of the mount @inode was found from
* @inode: The inode in question
* @cap: The capability in question
*
* Return true if the current task has the given capability targeted at
* its own user namespace and that the given inode's uid and gid are
* mapped into the current user namespace.
*/
bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap,
const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, idmap, inode);
}
EXPORT_SYMBOL(capable_wrt_inode_uidgid);
/**
* ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace
* @tsk: The task that may be ptraced
* @ns: The user namespace to search for CAP_SYS_PTRACE in
*
* Return true if the task that is ptracing the current task had CAP_SYS_PTRACE
* in the specified user namespace.
*/
bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
{
int ret = 0; /* An absent tracer adds no restrictions */
const struct cred *cred;
rcu_read_lock();
cred = rcu_dereference(tsk->ptracer_cred);
if (cred)
ret = security_capable(cred, ns, CAP_SYS_PTRACE,
CAP_OPT_NOAUDIT);
rcu_read_unlock();
return (ret == 0);
}
// SPDX-License-Identifier: GPL-2.0-only
#include "cgroup-internal.h"
#include <linux/sched/cputime.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <trace/events/cgroup.h>
static DEFINE_SPINLOCK(cgroup_rstat_lock);
static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
{
return per_cpu_ptr(cgrp->rstat_cpu, cpu);
}
/*
* Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock).
*
* This makes it easier to diagnose locking issues and contention in
* production environments. The parameter @fast_path determine the
* tracepoints being added, allowing us to diagnose "flush" related
* operations without handling high-frequency fast-path "update" events.
*/
static __always_inline
unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu,
struct cgroup *cgrp, const bool fast_path)
{
unsigned long flags;
bool contended;
/*
* The _irqsave() is needed because cgroup_rstat_lock is
* spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
* this lock with the _irq() suffix only disables interrupts on
* a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
* interrupts on both configurations. The _irqsave() ensures
* that interrupts are always disabled and later restored.
*/
contended = !raw_spin_trylock_irqsave(cpu_lock, flags);
if (contended) {
if (fast_path)
trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended);
else
trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended);
raw_spin_lock_irqsave(cpu_lock, flags);
}
if (fast_path)
trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended);
else
trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended);
return flags;
}
static __always_inline
void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu,
struct cgroup *cgrp, unsigned long flags,
const bool fast_path)
{
if (fast_path)
trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false);
else
trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false);
raw_spin_unlock_irqrestore(cpu_lock, flags);
}
/**
* cgroup_rstat_updated - keep track of updated rstat_cpu
* @cgrp: target cgroup
* @cpu: cpu on which rstat_cpu was updated
*
* @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching
* rstat_cpu->updated_children list. See the comment on top of
* cgroup_rstat_cpu definition for details.
*/
__bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
{
raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
unsigned long flags;
/*
* Speculative already-on-list test. This may race leading to
* temporary inaccuracies, which is fine.
*
* Because @parent's updated_children is terminated with @parent
* instead of NULL, we can tell whether @cgrp is on the list by
* testing the next pointer for NULL.
*/
if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next))
return;
flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true);
/* put @cgrp and all ancestors on the corresponding updated lists */
while (true) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup_rstat_cpu *prstatc;
/*
* Both additions and removals are bottom-up. If a cgroup
* is already in the tree, all ancestors are.
*/
if (rstatc->updated_next)
break;
/* Root has no parent to link it to, but mark it busy */
if (!parent) {
rstatc->updated_next = cgrp;
break;
}
prstatc = cgroup_rstat_cpu(parent, cpu);
rstatc->updated_next = prstatc->updated_children;
prstatc->updated_children = cgrp;
cgrp = parent;
}
_cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true);
}
/**
* cgroup_rstat_push_children - push children cgroups into the given list
* @head: current head of the list (= subtree root)
* @child: first child of the root
* @cpu: target cpu
* Return: A new singly linked list of cgroups to be flush
*
* Iteratively traverse down the cgroup_rstat_cpu updated tree level by
* level and push all the parents first before their next level children
* into a singly linked list built from the tail backward like "pushing"
* cgroups into a stack. The root is pushed by the caller.
*/
static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
struct cgroup *child, int cpu)
{
struct cgroup *chead = child; /* Head of child cgroup level */
struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */
struct cgroup *parent, *grandchild;
struct cgroup_rstat_cpu *crstatc;
child->rstat_flush_next = NULL;
next_level:
while (chead) {
child = chead;
chead = child->rstat_flush_next;
parent = cgroup_parent(child);
/* updated_next is parent cgroup terminated */
while (child != parent) {
child->rstat_flush_next = head;
head = child;
crstatc = cgroup_rstat_cpu(child, cpu);
grandchild = crstatc->updated_children;
if (grandchild != child) {
/* Push the grand child to the next level */
crstatc->updated_children = child;
grandchild->rstat_flush_next = ghead;
ghead = grandchild;
}
child = crstatc->updated_next;
crstatc->updated_next = NULL;
}
}
if (ghead) {
chead = ghead;
ghead = NULL;
goto next_level;
}
return head;
}
/**
* cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
* @root: root of the cgroup subtree to traverse
* @cpu: target cpu
* Return: A singly linked list of cgroups to be flushed
*
* Walks the updated rstat_cpu tree on @cpu from @root. During traversal,
* each returned cgroup is unlinked from the updated tree.
*
* The only ordering guarantee is that, for a parent and a child pair
* covered by a given traversal, the child is before its parent in
* the list.
*
* Note that updated_children is self terminated and points to a list of
* child cgroups if not empty. Whereas updated_next is like a sibling link
* within the children list and terminated by the parent cgroup. An exception
* here is the cgroup root whose updated_next can be self terminated.
*/
static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
{
raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
struct cgroup *head = NULL, *parent, *child;
unsigned long flags;
flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false);
/* Return NULL if this subtree is not on-list */
if (!rstatc->updated_next)
goto unlock_ret;
/*
* Unlink @root from its parent. As the updated_children list is
* singly linked, we have to walk it to find the removal point.
*/
parent = cgroup_parent(root);
if (parent) {
struct cgroup_rstat_cpu *prstatc;
struct cgroup **nextp;
prstatc = cgroup_rstat_cpu(parent, cpu);
nextp = &prstatc->updated_children;
while (*nextp != root) {
struct cgroup_rstat_cpu *nrstatc;
nrstatc = cgroup_rstat_cpu(*nextp, cpu);
WARN_ON_ONCE(*nextp == parent);
nextp = &nrstatc->updated_next;
}
*nextp = rstatc->updated_next;
}
rstatc->updated_next = NULL;
/* Push @root to the list first before pushing the children */
head = root;
root->rstat_flush_next = NULL;
child = rstatc->updated_children;
rstatc->updated_children = root;
if (child != root)
head = cgroup_rstat_push_children(head, child, cpu);
unlock_ret:
_cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false);
return head;
}
/*
* A hook for bpf stat collectors to attach to and flush their stats.
* Together with providing bpf kfuncs for cgroup_rstat_updated() and
* cgroup_rstat_flush(), this enables a complete workflow where bpf progs that
* collect cgroup stats can integrate with rstat for efficient flushing.
*
* A static noinline declaration here could cause the compiler to optimize away
* the function. A global noinline declaration will keep the definition, but may
* optimize away the callsite. Therefore, __weak is needed to ensure that the
* call is still emitted, by telling the compiler that we don't know what the
* function might eventually be.
*/
__bpf_hook_start();
__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
struct cgroup *parent, int cpu)
{
}
__bpf_hook_end();
/*
* Helper functions for locking cgroup_rstat_lock.
*
* This makes it easier to diagnose locking issues and contention in
* production environments. The parameter @cpu_in_loop indicate lock
* was released and re-taken when collection data from the CPUs. The
* value -1 is used when obtaining the main lock else this is the CPU
* number processed last.
*/
static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop)
__acquires(&cgroup_rstat_lock)
{
bool contended;
contended = !spin_trylock_irq(&cgroup_rstat_lock);
if (contended) {
trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended);
spin_lock_irq(&cgroup_rstat_lock);
}
trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended);
}
static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
__releases(&cgroup_rstat_lock)
{
trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false);
spin_unlock_irq(&cgroup_rstat_lock);
}
/**
* cgroup_rstat_flush - flush stats in @cgrp's subtree
* @cgrp: target cgroup
*
* Collect all per-cpu stats in @cgrp's subtree into the global counters
* and propagate them upwards. After this function returns, all cgroups in
* the subtree have up-to-date ->stat.
*
* This also gets all cgroups in the subtree including @cgrp off the
* ->updated_children lists.
*
* This function may block.
*/
__bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
{
int cpu;
might_sleep();
for_each_possible_cpu(cpu) {
struct cgroup *pos;
/* Reacquire for each CPU to avoid disabling IRQs too long */
__cgroup_rstat_lock(cgrp, cpu);
pos = cgroup_rstat_updated_list(cgrp, cpu);
for (; pos; pos = pos->rstat_flush_next) {
struct cgroup_subsys_state *css;
cgroup_base_stat_flush(pos, cpu);
bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
rcu_read_lock();
list_for_each_entry_rcu(css, &pos->rstat_css_list,
rstat_css_node)
css->ss->css_rstat_flush(css, cpu);
rcu_read_unlock();
}
__cgroup_rstat_unlock(cgrp, cpu);
if (!cond_resched())
cpu_relax();
}
}
int cgroup_rstat_init(struct cgroup *cgrp)
{
int cpu;
/* the root cgrp has rstat_cpu preallocated */
if (!cgrp->rstat_cpu) {
cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu);
if (!cgrp->rstat_cpu)
return -ENOMEM;
}
/* ->updated_children list is self terminated */
for_each_possible_cpu(cpu) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
rstatc->updated_children = cgrp;
u64_stats_init(&rstatc->bsync);
}
return 0;
}
void cgroup_rstat_exit(struct cgroup *cgrp)
{
int cpu;
cgroup_rstat_flush(cgrp);
/* sanity check */
for_each_possible_cpu(cpu) {
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
if (WARN_ON_ONCE(rstatc->updated_children != cgrp) ||
WARN_ON_ONCE(rstatc->updated_next))
return;
}
free_percpu(cgrp->rstat_cpu);
cgrp->rstat_cpu = NULL;
}
void __init cgroup_rstat_boot(void)
{
int cpu;
for_each_possible_cpu(cpu)
raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
}
/*
* Functions for cgroup basic resource statistics implemented on top of
* rstat.
*/
static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
struct cgroup_base_stat *src_bstat)
{
dst_bstat->cputime.utime += src_bstat->cputime.utime;
dst_bstat->cputime.stime += src_bstat->cputime.stime;
dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
#ifdef CONFIG_SCHED_CORE
dst_bstat->forceidle_sum += src_bstat->forceidle_sum;
#endif
dst_bstat->ntime += src_bstat->ntime;
}
static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
struct cgroup_base_stat *src_bstat)
{
dst_bstat->cputime.utime -= src_bstat->cputime.utime;
dst_bstat->cputime.stime -= src_bstat->cputime.stime;
dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime;
#ifdef CONFIG_SCHED_CORE
dst_bstat->forceidle_sum -= src_bstat->forceidle_sum;
#endif
dst_bstat->ntime -= src_bstat->ntime;
}
static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
{
struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
struct cgroup *parent = cgroup_parent(cgrp);
struct cgroup_rstat_cpu *prstatc;
struct cgroup_base_stat delta;
unsigned seq;
/* Root-level stats are sourced from system-wide CPU stats */
if (!parent)
return;
/* fetch the current per-cpu values */
do {
seq = __u64_stats_fetch_begin(&rstatc->bsync);
delta = rstatc->bstat;
} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
/* propagate per-cpu delta to cgroup and per-cpu global statistics */
cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
cgroup_base_stat_add(&cgrp->bstat, &delta);
cgroup_base_stat_add(&rstatc->last_bstat, &delta);
cgroup_base_stat_add(&rstatc->subtree_bstat, &delta);
/* propagate cgroup and per-cpu global delta to parent (unless that's root) */
if (cgroup_parent(parent)) {
delta = cgrp->bstat;
cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
cgroup_base_stat_add(&parent->bstat, &delta);
cgroup_base_stat_add(&cgrp->last_bstat, &delta);
delta = rstatc->subtree_bstat;
prstatc = cgroup_rstat_cpu(parent, cpu);
cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat);
cgroup_base_stat_add(&prstatc->subtree_bstat, &delta);
cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta);
}
}
static struct cgroup_rstat_cpu *
cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags)
{
struct cgroup_rstat_cpu *rstatc;
rstatc = get_cpu_ptr(cgrp->rstat_cpu);
*flags = u64_stats_update_begin_irqsave(&rstatc->bsync);
return rstatc;
}
static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
struct cgroup_rstat_cpu *rstatc,
unsigned long flags)
{
u64_stats_update_end_irqrestore(&rstatc->bsync, flags);
cgroup_rstat_updated(cgrp, smp_processor_id());
put_cpu_ptr(rstatc);
}
void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
{
struct cgroup_rstat_cpu *rstatc;
unsigned long flags;
rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}
void __cgroup_account_cputime_field(struct cgroup *cgrp,
enum cpu_usage_stat index, u64 delta_exec)
{
struct cgroup_rstat_cpu *rstatc;
unsigned long flags;
rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
switch (index) {
case CPUTIME_NICE:
rstatc->bstat.ntime += delta_exec;
fallthrough;
case CPUTIME_USER:
rstatc->bstat.cputime.utime += delta_exec;
break;
case CPUTIME_SYSTEM:
case CPUTIME_IRQ:
case CPUTIME_SOFTIRQ:
rstatc->bstat.cputime.stime += delta_exec;
break;
#ifdef CONFIG_SCHED_CORE
case CPUTIME_FORCEIDLE:
rstatc->bstat.forceidle_sum += delta_exec;
break;
#endif
default:
break;
}
cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}
/*
* compute the cputime for the root cgroup by getting the per cpu data
* at a global level, then categorizing the fields in a manner consistent
* with how it is done by __cgroup_account_cputime_field for each bit of
* cpu time attributed to a cgroup.
*/
static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
{
struct task_cputime *cputime = &bstat->cputime;
int i;
memset(bstat, 0, sizeof(*bstat));
for_each_possible_cpu(i) {
struct kernel_cpustat kcpustat;
u64 *cpustat = kcpustat.cpustat;
u64 user = 0;
u64 sys = 0;
kcpustat_cpu_fetch(&kcpustat, i);
user += cpustat[CPUTIME_USER];
user += cpustat[CPUTIME_NICE];
cputime->utime += user;
sys += cpustat[CPUTIME_SYSTEM];
sys += cpustat[CPUTIME_IRQ];
sys += cpustat[CPUTIME_SOFTIRQ];
cputime->stime += sys;
cputime->sum_exec_runtime += user;
cputime->sum_exec_runtime += sys;
#ifdef CONFIG_SCHED_CORE
bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
#endif
bstat->ntime += cpustat[CPUTIME_NICE];
}
}
static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat)
{
#ifdef CONFIG_SCHED_CORE
u64 forceidle_time = bstat->forceidle_sum;
do_div(forceidle_time, NSEC_PER_USEC);
seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
#endif
}
void cgroup_base_stat_cputime_show(struct seq_file *seq)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
struct cgroup_base_stat bstat;
if (cgroup_parent(cgrp)) {
cgroup_rstat_flush(cgrp);
__cgroup_rstat_lock(cgrp, -1);
bstat = cgrp->bstat;
cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
&bstat.cputime.utime, &bstat.cputime.stime);
__cgroup_rstat_unlock(cgrp, -1);
} else {
root_cgroup_cputime(&bstat);
}
do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
do_div(bstat.cputime.utime, NSEC_PER_USEC);
do_div(bstat.cputime.stime, NSEC_PER_USEC);
do_div(bstat.ntime, NSEC_PER_USEC);
seq_printf(seq, "usage_usec %llu\n"
"user_usec %llu\n"
"system_usec %llu\n"
"nice_usec %llu\n",
bstat.cputime.sum_exec_runtime,
bstat.cputime.utime,
bstat.cputime.stime,
bstat.ntime);
cgroup_force_idle_show(seq, &bstat);
}
/* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */
BTF_KFUNCS_START(bpf_rstat_kfunc_ids)
BTF_ID_FLAGS(func, cgroup_rstat_updated)
BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE)
BTF_KFUNCS_END(bpf_rstat_kfunc_ids)
static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = {
.owner = THIS_MODULE,
.set = &bpf_rstat_kfunc_ids,
};
static int __init bpf_rstat_kfunc_init(void)
{
return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
&bpf_rstat_kfunc_set);
}
late_initcall(bpf_rstat_kfunc_init);
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Security plug functions
*
* Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
* Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com>
* Copyright (C) 2016 Mellanox Technologies
* Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com>
*/
#define pr_fmt(fmt) "LSM: " fmt
#include <linux/bpf.h>
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kernel_read_file.h>
#include <linux/lsm_hooks.h>
#include <linux/mman.h>
#include <linux/mount.h>
#include <linux/personality.h>
#include <linux/backing-dev.h>
#include <linux/string.h>
#include <linux/xattr.h>
#include <linux/msg.h>
#include <linux/overflow.h>
#include <linux/perf_event.h>
#include <linux/fs.h>
#include <net/flow.h>
#include <net/sock.h>
#define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX
/*
* Identifier for the LSM static calls.
* HOOK is an LSM hook as defined in linux/lsm_hookdefs.h
* IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT
*/
#define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX
/*
* Call the macro M for each LSM hook MAX_LSM_COUNT times.
*/
#define LSM_LOOP_UNROLL(M, ...) \
do { \
UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \
} while (0)
#define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__)
/*
* These are descriptions of the reasons that can be passed to the
* security_locked_down() LSM hook. Placing this array here allows
* all security modules to use the same descriptions for auditing
* purposes.
*/
const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = {
[LOCKDOWN_NONE] = "none",
[LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading",
[LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port",
[LOCKDOWN_EFI_TEST] = "/dev/efi_test access",
[LOCKDOWN_KEXEC] = "kexec of unsigned images",
[LOCKDOWN_HIBERNATION] = "hibernation",
[LOCKDOWN_PCI_ACCESS] = "direct PCI access",
[LOCKDOWN_IOPORT] = "raw io port access",
[LOCKDOWN_MSR] = "raw MSR access",
[LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables",
[LOCKDOWN_DEVICE_TREE] = "modifying device tree contents",
[LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage",
[LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO",
[LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters",
[LOCKDOWN_MMIOTRACE] = "unsafe mmio",
[LOCKDOWN_DEBUGFS] = "debugfs access",
[LOCKDOWN_XMON_WR] = "xmon write access",
[LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM",
[LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM",
[LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection",
[LOCKDOWN_INTEGRITY_MAX] = "integrity",
[LOCKDOWN_KCORE] = "/proc/kcore access",
[LOCKDOWN_KPROBES] = "use of kprobes",
[LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM",
[LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM",
[LOCKDOWN_PERF] = "unsafe use of perf",
[LOCKDOWN_TRACEFS] = "use of tracefs",
[LOCKDOWN_XMON_RW] = "xmon read and write access",
[LOCKDOWN_XFRM_SECRET] = "xfrm SA secret",
[LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality",
};
static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain);
static struct kmem_cache *lsm_file_cache;
static struct kmem_cache *lsm_inode_cache;
char *lsm_names;
static struct lsm_blob_sizes blob_sizes __ro_after_init;
/* Boot-time LSM user choice */
static __initdata const char *chosen_lsm_order;
static __initdata const char *chosen_major_lsm;
static __initconst const char *const builtin_lsm_order = CONFIG_LSM;
/* Ordered list of LSMs to initialize. */
static __initdata struct lsm_info *ordered_lsms[MAX_LSM_COUNT + 1];
static __initdata struct lsm_info *exclusive;
#ifdef CONFIG_HAVE_STATIC_CALL
#define LSM_HOOK_TRAMP(NAME, NUM) \
&STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM))
#else
#define LSM_HOOK_TRAMP(NAME, NUM) NULL
#endif
/*
* Define static calls and static keys for each LSM hook.
*/
#define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \
DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \
*((RET(*)(__VA_ARGS__))NULL)); \
DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM));
#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__)
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
#undef DEFINE_LSM_STATIC_CALL
/*
* Initialise a table of static calls for each LSM hook.
* DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY)
* and a trampoline (STATIC_CALL_TRAMP) which are used to call
* __static_call_update when updating the static call.
*
* The static calls table is used by early LSMs, some architectures can fault on
* unaligned accesses and the fault handling code may not be ready by then.
* Thus, the static calls table should be aligned to avoid any unhandled faults
* in early init.
*/
struct lsm_static_calls_table
static_calls_table __ro_after_init __aligned(sizeof(u64)) = {
#define INIT_LSM_STATIC_CALL(NUM, NAME) \
(struct lsm_static_call) { \
.key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \
.trampoline = LSM_HOOK_TRAMP(NAME, NUM), \
.active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \
},
#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
.NAME = { \
LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \
},
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
#undef INIT_LSM_STATIC_CALL
};
static __initdata bool debug;
#define init_debug(...) \
do { \
if (debug) \
pr_info(__VA_ARGS__); \
} while (0)
static bool __init is_enabled(struct lsm_info *lsm)
{
if (!lsm->enabled)
return false;
return *lsm->enabled;
}
/* Mark an LSM's enabled flag. */
static int lsm_enabled_true __initdata = 1;
static int lsm_enabled_false __initdata = 0;
static void __init set_enabled(struct lsm_info *lsm, bool enabled)
{
/*
* When an LSM hasn't configured an enable variable, we can use
* a hard-coded location for storing the default enabled state.
*/
if (!lsm->enabled) {
if (enabled)
lsm->enabled = &lsm_enabled_true;
else
lsm->enabled = &lsm_enabled_false;
} else if (lsm->enabled == &lsm_enabled_true) {
if (!enabled)
lsm->enabled = &lsm_enabled_false;
} else if (lsm->enabled == &lsm_enabled_false) {
if (enabled)
lsm->enabled = &lsm_enabled_true;
} else {
*lsm->enabled = enabled;
}
}
/* Is an LSM already listed in the ordered LSMs list? */
static bool __init exists_ordered_lsm(struct lsm_info *lsm)
{
struct lsm_info **check;
for (check = ordered_lsms; *check; check++)
if (*check == lsm)
return true;
return false;
}
/* Append an LSM to the list of ordered LSMs to initialize. */
static int last_lsm __initdata;
static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from)
{
/* Ignore duplicate selections. */
if (exists_ordered_lsm(lsm))
return;
if (WARN(last_lsm == MAX_LSM_COUNT, "%s: out of LSM static calls!?\n", from))
return;
/* Enable this LSM, if it is not already set. */
if (!lsm->enabled)
lsm->enabled = &lsm_enabled_true;
ordered_lsms[last_lsm++] = lsm;
init_debug("%s ordered: %s (%s)\n", from, lsm->name,
is_enabled(lsm) ? "enabled" : "disabled");
}
/* Is an LSM allowed to be initialized? */
static bool __init lsm_allowed(struct lsm_info *lsm)
{
/* Skip if the LSM is disabled. */
if (!is_enabled(lsm))
return false;
/* Not allowed if another exclusive LSM already initialized. */
if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) {
init_debug("exclusive disabled: %s\n", lsm->name);
return false;
}
return true;
}
static void __init lsm_set_blob_size(int *need, int *lbs)
{
int offset;
if (*need <= 0)
return;
offset = ALIGN(*lbs, sizeof(void *));
*lbs = offset + *need;
*need = offset;
}
static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
{
if (!needed)
return;
lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred);
lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file);
lsm_set_blob_size(&needed->lbs_ib, &blob_sizes.lbs_ib);
/*
* The inode blob gets an rcu_head in addition to
* what the modules might need.
*/
if (needed->lbs_inode && blob_sizes.lbs_inode == 0)
blob_sizes.lbs_inode = sizeof(struct rcu_head);
lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode);
lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc);
lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key);
lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg);
lsm_set_blob_size(&needed->lbs_perf_event, &blob_sizes.lbs_perf_event);
lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock);
lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock);
lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task);
lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev);
lsm_set_blob_size(&needed->lbs_xattr_count,
&blob_sizes.lbs_xattr_count);
lsm_set_blob_size(&needed->lbs_bdev, &blob_sizes.lbs_bdev);
}
/* Prepare LSM for initialization. */
static void __init prepare_lsm(struct lsm_info *lsm)
{
int enabled = lsm_allowed(lsm);
/* Record enablement (to handle any following exclusive LSMs). */
set_enabled(lsm, enabled);
/* If enabled, do pre-initialization work. */
if (enabled) {
if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) {
exclusive = lsm;
init_debug("exclusive chosen: %s\n", lsm->name);
}
lsm_set_blob_sizes(lsm->blobs);
}
}
/* Initialize a given LSM, if it is enabled. */
static void __init initialize_lsm(struct lsm_info *lsm)
{
if (is_enabled(lsm)) {
int ret;
init_debug("initializing %s\n", lsm->name);
ret = lsm->init();
WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret);
}
}
/*
* Current index to use while initializing the lsm id list.
*/
u32 lsm_active_cnt __ro_after_init;
const struct lsm_id *lsm_idlist[MAX_LSM_COUNT];
/* Populate ordered LSMs list from comma-separated LSM name list. */
static void __init ordered_lsm_parse(const char *order, const char *origin)
{
struct lsm_info *lsm;
char *sep, *name, *next;
/* LSM_ORDER_FIRST is always first. */
for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) {
if (lsm->order == LSM_ORDER_FIRST)
append_ordered_lsm(lsm, " first");
}
/* Process "security=", if given. */
if (chosen_major_lsm) {
struct lsm_info *major;
/*
* To match the original "security=" behavior, this
* explicitly does NOT fallback to another Legacy Major
* if the selected one was separately disabled: disable
* all non-matching Legacy Major LSMs.
*/
for (major = __start_lsm_info; major < __end_lsm_info;
major++) {
if ((major->flags & LSM_FLAG_LEGACY_MAJOR) &&
strcmp(major->name, chosen_major_lsm) != 0) {
set_enabled(major, false);
init_debug("security=%s disabled: %s (only one legacy major LSM)\n",
chosen_major_lsm, major->name);
}
}
}
sep = kstrdup(order, GFP_KERNEL);
next = sep;
/* Walk the list, looking for matching LSMs. */
while ((name = strsep(&next, ",")) != NULL) {
bool found = false;
for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) {
if (strcmp(lsm->name, name) == 0) {
if (lsm->order == LSM_ORDER_MUTABLE)
append_ordered_lsm(lsm, origin);
found = true;
}
}
if (!found)
init_debug("%s ignored: %s (not built into kernel)\n",
origin, name);
}
/* Process "security=", if given. */
if (chosen_major_lsm) {
for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) {
if (exists_ordered_lsm(lsm))
continue;
if (strcmp(lsm->name, chosen_major_lsm) == 0)
append_ordered_lsm(lsm, "security=");
}
}
/* LSM_ORDER_LAST is always last. */
for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) {
if (lsm->order == LSM_ORDER_LAST)
append_ordered_lsm(lsm, " last");
}
/* Disable all LSMs not in the ordered list. */
for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) {
if (exists_ordered_lsm(lsm))
continue;
set_enabled(lsm, false);
init_debug("%s skipped: %s (not in requested order)\n",
origin, lsm->name);
}
kfree(sep);
}
static void __init lsm_static_call_init(struct security_hook_list *hl)
{
struct lsm_static_call *scall = hl->scalls;
int i;
for (i = 0; i < MAX_LSM_COUNT; i++) {
/* Update the first static call that is not used yet */
if (!scall->hl) {
__static_call_update(scall->key, scall->trampoline,
hl->hook.lsm_func_addr);
scall->hl = hl;
static_branch_enable(scall->active);
return;
}
scall++;
}
panic("%s - Ran out of static slots.\n", __func__);
}
static void __init lsm_early_cred(struct cred *cred);
static void __init lsm_early_task(struct task_struct *task);
static int lsm_append(const char *new, char **result);
static void __init report_lsm_order(void)
{
struct lsm_info **lsm, *early;
int first = 0;
pr_info("initializing lsm=");
/* Report each enabled LSM name, comma separated. */
for (early = __start_early_lsm_info;
early < __end_early_lsm_info; early++)
if (is_enabled(early))
pr_cont("%s%s", first++ == 0 ? "" : ",", early->name);
for (lsm = ordered_lsms; *lsm; lsm++)
if (is_enabled(*lsm))
pr_cont("%s%s", first++ == 0 ? "" : ",", (*lsm)->name);
pr_cont("\n");
}
static void __init ordered_lsm_init(void)
{
struct lsm_info **lsm;
if (chosen_lsm_order) {
if (chosen_major_lsm) {
pr_warn("security=%s is ignored because it is superseded by lsm=%s\n",
chosen_major_lsm, chosen_lsm_order);
chosen_major_lsm = NULL;
}
ordered_lsm_parse(chosen_lsm_order, "cmdline");
} else
ordered_lsm_parse(builtin_lsm_order, "builtin");
for (lsm = ordered_lsms; *lsm; lsm++)
prepare_lsm(*lsm);
report_lsm_order();
init_debug("cred blob size = %d\n", blob_sizes.lbs_cred);
init_debug("file blob size = %d\n", blob_sizes.lbs_file);
init_debug("ib blob size = %d\n", blob_sizes.lbs_ib);
init_debug("inode blob size = %d\n", blob_sizes.lbs_inode);
init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc);
#ifdef CONFIG_KEYS
init_debug("key blob size = %d\n", blob_sizes.lbs_key);
#endif /* CONFIG_KEYS */
init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg);
init_debug("sock blob size = %d\n", blob_sizes.lbs_sock);
init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock);
init_debug("perf event blob size = %d\n", blob_sizes.lbs_perf_event);
init_debug("task blob size = %d\n", blob_sizes.lbs_task);
init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev);
init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count);
init_debug("bdev blob size = %d\n", blob_sizes.lbs_bdev);
/*
* Create any kmem_caches needed for blobs
*/
if (blob_sizes.lbs_file)
lsm_file_cache = kmem_cache_create("lsm_file_cache",
blob_sizes.lbs_file, 0,
SLAB_PANIC, NULL);
if (blob_sizes.lbs_inode)
lsm_inode_cache = kmem_cache_create("lsm_inode_cache",
blob_sizes.lbs_inode, 0,
SLAB_PANIC, NULL);
lsm_early_cred((struct cred *) current->cred);
lsm_early_task(current);
for (lsm = ordered_lsms; *lsm; lsm++)
initialize_lsm(*lsm);
}
int __init early_security_init(void)
{
struct lsm_info *lsm;
for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) {
if (!lsm->enabled)
lsm->enabled = &lsm_enabled_true;
prepare_lsm(lsm);
initialize_lsm(lsm);
}
return 0;
}
/**
* security_init - initializes the security framework
*
* This should be called early in the kernel initialization sequence.
*/
int __init security_init(void)
{
struct lsm_info *lsm;
init_debug("legacy security=%s\n", chosen_major_lsm ? : " *unspecified*");
init_debug(" CONFIG_LSM=%s\n", builtin_lsm_order);
init_debug("boot arg lsm=%s\n", chosen_lsm_order ? : " *unspecified*");
/*
* Append the names of the early LSM modules now that kmalloc() is
* available
*/
for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) {
init_debug(" early started: %s (%s)\n", lsm->name,
is_enabled(lsm) ? "enabled" : "disabled");
if (lsm->enabled)
lsm_append(lsm->name, &lsm_names);
}
/* Load LSMs in specified order. */
ordered_lsm_init();
return 0;
}
/* Save user chosen LSM */
static int __init choose_major_lsm(char *str)
{
chosen_major_lsm = str;
return 1;
}
__setup("security=", choose_major_lsm);
/* Explicitly choose LSM initialization order. */
static int __init choose_lsm_order(char *str)
{
chosen_lsm_order = str;
return 1;
}
__setup("lsm=", choose_lsm_order);
/* Enable LSM order debugging. */
static int __init enable_debug(char *str)
{
debug = true;
return 1;
}
__setup("lsm.debug", enable_debug);
static bool match_last_lsm(const char *list, const char *lsm)
{
const char *last;
if (WARN_ON(!list || !lsm))
return false;
last = strrchr(list, ',');
if (last)
/* Pass the comma, strcmp() will check for '\0' */
last++;
else
last = list;
return !strcmp(last, lsm);
}
static int lsm_append(const char *new, char **result)
{
char *cp;
if (*result == NULL) {
*result = kstrdup(new, GFP_KERNEL);
if (*result == NULL)
return -ENOMEM;
} else {
/* Check if it is the last registered name */
if (match_last_lsm(*result, new))
return 0;
cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new);
if (cp == NULL)
return -ENOMEM;
kfree(*result);
*result = cp;
}
return 0;
}
/**
* security_add_hooks - Add a modules hooks to the hook lists.
* @hooks: the hooks to add
* @count: the number of hooks to add
* @lsmid: the identification information for the security module
*
* Each LSM has to register its hooks with the infrastructure.
*/
void __init security_add_hooks(struct security_hook_list *hooks, int count,
const struct lsm_id *lsmid)
{
int i;
/*
* A security module may call security_add_hooks() more
* than once during initialization, and LSM initialization
* is serialized. Landlock is one such case.
* Look at the previous entry, if there is one, for duplication.
*/
if (lsm_active_cnt == 0 || lsm_idlist[lsm_active_cnt - 1] != lsmid) {
if (lsm_active_cnt >= MAX_LSM_COUNT)
panic("%s Too many LSMs registered.\n", __func__);
lsm_idlist[lsm_active_cnt++] = lsmid;
}
for (i = 0; i < count; i++) {
hooks[i].lsmid = lsmid;
lsm_static_call_init(&hooks[i]);
}
/*
* Don't try to append during early_security_init(), we'll come back
* and fix this up afterwards.
*/
if (slab_is_available()) {
if (lsm_append(lsmid->name, &lsm_names) < 0)
panic("%s - Cannot get early memory.\n", __func__);
}
}
int call_blocking_lsm_notifier(enum lsm_event event, void *data)
{
return blocking_notifier_call_chain(&blocking_lsm_notifier_chain,
event, data);
}
EXPORT_SYMBOL(call_blocking_lsm_notifier);
int register_blocking_lsm_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&blocking_lsm_notifier_chain,
nb);
}
EXPORT_SYMBOL(register_blocking_lsm_notifier);
int unregister_blocking_lsm_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain,
nb);
}
EXPORT_SYMBOL(unregister_blocking_lsm_notifier);
/**
* lsm_blob_alloc - allocate a composite blob
* @dest: the destination for the blob
* @size: the size of the blob
* @gfp: allocation type
*
* Allocate a blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp)
{
if (size == 0) {
*dest = NULL;
return 0;
}
*dest = kzalloc(size, gfp);
if (*dest == NULL)
return -ENOMEM;
return 0;
}
/**
* lsm_cred_alloc - allocate a composite cred blob
* @cred: the cred that needs a blob
* @gfp: allocation type
*
* Allocate the cred blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_cred_alloc(struct cred *cred, gfp_t gfp)
{
return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp);
}
/**
* lsm_early_cred - during initialization allocate a composite cred blob
* @cred: the cred that needs a blob
*
* Allocate the cred blob for all the modules
*/
static void __init lsm_early_cred(struct cred *cred)
{
int rc = lsm_cred_alloc(cred, GFP_KERNEL);
if (rc)
panic("%s: Early cred alloc failed.\n", __func__);
}
/**
* lsm_file_alloc - allocate a composite file blob
* @file: the file that needs a blob
*
* Allocate the file blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_file_alloc(struct file *file)
{
if (!lsm_file_cache) {
file->f_security = NULL;
return 0;
}
file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL);
if (file->f_security == NULL)
return -ENOMEM;
return 0;
}
/**
* lsm_inode_alloc - allocate a composite inode blob
* @inode: the inode that needs a blob
* @gfp: allocation flags
*
* Allocate the inode blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_inode_alloc(struct inode *inode, gfp_t gfp)
{
if (!lsm_inode_cache) {
inode->i_security = NULL;
return 0;
}
inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp);
if (inode->i_security == NULL)
return -ENOMEM;
return 0;
}
/**
* lsm_task_alloc - allocate a composite task blob
* @task: the task that needs a blob
*
* Allocate the task blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_task_alloc(struct task_struct *task)
{
return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL);
}
/**
* lsm_ipc_alloc - allocate a composite ipc blob
* @kip: the ipc that needs a blob
*
* Allocate the ipc blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_ipc_alloc(struct kern_ipc_perm *kip)
{
return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL);
}
#ifdef CONFIG_KEYS
/**
* lsm_key_alloc - allocate a composite key blob
* @key: the key that needs a blob
*
* Allocate the key blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_key_alloc(struct key *key)
{
return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL);
}
#endif /* CONFIG_KEYS */
/**
* lsm_msg_msg_alloc - allocate a composite msg_msg blob
* @mp: the msg_msg that needs a blob
*
* Allocate the ipc blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_msg_msg_alloc(struct msg_msg *mp)
{
return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg,
GFP_KERNEL);
}
/**
* lsm_bdev_alloc - allocate a composite block_device blob
* @bdev: the block_device that needs a blob
*
* Allocate the block_device blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_bdev_alloc(struct block_device *bdev)
{
if (blob_sizes.lbs_bdev == 0) {
bdev->bd_security = NULL;
return 0;
}
bdev->bd_security = kzalloc(blob_sizes.lbs_bdev, GFP_KERNEL);
if (!bdev->bd_security)
return -ENOMEM;
return 0;
}
/**
* lsm_early_task - during initialization allocate a composite task blob
* @task: the task that needs a blob
*
* Allocate the task blob for all the modules
*/
static void __init lsm_early_task(struct task_struct *task)
{
int rc = lsm_task_alloc(task);
if (rc)
panic("%s: Early task alloc failed.\n", __func__);
}
/**
* lsm_superblock_alloc - allocate a composite superblock blob
* @sb: the superblock that needs a blob
*
* Allocate the superblock blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_superblock_alloc(struct super_block *sb)
{
return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock,
GFP_KERNEL);
}
/**
* lsm_fill_user_ctx - Fill a user space lsm_ctx structure
* @uctx: a userspace LSM context to be filled
* @uctx_len: available uctx size (input), used uctx size (output)
* @val: the new LSM context value
* @val_len: the size of the new LSM context value
* @id: LSM id
* @flags: LSM defined flags
*
* Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL
* simply calculate the required size to output via @utc_len and return
* success.
*
* Returns 0 on success, -E2BIG if userspace buffer is not large enough,
* -EFAULT on a copyout error, -ENOMEM if memory can't be allocated.
*/
int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len,
void *val, size_t val_len,
u64 id, u64 flags)
{
struct lsm_ctx *nctx = NULL;
size_t nctx_len;
int rc = 0;
nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *));
if (nctx_len > *uctx_len) {
rc = -E2BIG;
goto out;
}
/* no buffer - return success/0 and set @uctx_len to the req size */
if (!uctx)
goto out;
nctx = kzalloc(nctx_len, GFP_KERNEL);
if (nctx == NULL) {
rc = -ENOMEM;
goto out;
}
nctx->id = id;
nctx->flags = flags;
nctx->len = nctx_len;
nctx->ctx_len = val_len;
memcpy(nctx->ctx, val, val_len);
if (copy_to_user(uctx, nctx, nctx_len))
rc = -EFAULT;
out:
kfree(nctx);
*uctx_len = nctx_len;
return rc;
}
/*
* The default value of the LSM hook is defined in linux/lsm_hook_defs.h and
* can be accessed with:
*
* LSM_RET_DEFAULT(<hook_name>)
*
* The macros below define static constants for the default value of each
* LSM hook.
*/
#define LSM_RET_DEFAULT(NAME) (NAME##_default)
#define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME)
#define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \
static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT);
#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME)
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
/*
* Hook list operation macros.
*
* call_void_hook:
* This is a hook that does not return a value.
*
* call_int_hook:
* This is a hook that returns a value.
*/
#define __CALL_STATIC_VOID(NUM, HOOK, ...) \
do { \
if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \
static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \
} \
} while (0);
#define call_void_hook(HOOK, ...) \
do { \
LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \
} while (0)
#define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \
do { \
if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \
R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \
if (R != LSM_RET_DEFAULT(HOOK)) \
goto LABEL; \
} \
} while (0);
#define call_int_hook(HOOK, ...) \
({ \
__label__ OUT; \
int RC = LSM_RET_DEFAULT(HOOK); \
\
LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \
OUT: \
RC; \
})
#define lsm_for_each_hook(scall, NAME) \
for (scall = static_calls_table.NAME; \
scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \
if (static_key_enabled(&scall->active->key))
/* Security operations */
/**
* security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok
* @mgr: task credentials of current binder process
*
* Check whether @mgr is allowed to be the binder context manager.
*
* Return: Return 0 if permission is granted.
*/
int security_binder_set_context_mgr(const struct cred *mgr)
{
return call_int_hook(binder_set_context_mgr, mgr);
}
/**
* security_binder_transaction() - Check if a binder transaction is allowed
* @from: sending process
* @to: receiving process
*
* Check whether @from is allowed to invoke a binder transaction call to @to.
*
* Return: Returns 0 if permission is granted.
*/
int security_binder_transaction(const struct cred *from,
const struct cred *to)
{
return call_int_hook(binder_transaction, from, to);
}
/**
* security_binder_transfer_binder() - Check if a binder transfer is allowed
* @from: sending process
* @to: receiving process
*
* Check whether @from is allowed to transfer a binder reference to @to.
*
* Return: Returns 0 if permission is granted.
*/
int security_binder_transfer_binder(const struct cred *from,
const struct cred *to)
{
return call_int_hook(binder_transfer_binder, from, to);
}
/**
* security_binder_transfer_file() - Check if a binder file xfer is allowed
* @from: sending process
* @to: receiving process
* @file: file being transferred
*
* Check whether @from is allowed to transfer @file to @to.
*
* Return: Returns 0 if permission is granted.
*/
int security_binder_transfer_file(const struct cred *from,
const struct cred *to, const struct file *file)
{
return call_int_hook(binder_transfer_file, from, to, file);
}
/**
* security_ptrace_access_check() - Check if tracing is allowed
* @child: target process
* @mode: PTRACE_MODE flags
*
* Check permission before allowing the current process to trace the @child
* process. Security modules may also want to perform a process tracing check
* during an execve in the set_security or apply_creds hooks of tracing check
* during an execve in the bprm_set_creds hook of binprm_security_ops if the
* process is being traced and its security attributes would be changed by the
* execve.
*
* Return: Returns 0 if permission is granted.
*/
int security_ptrace_access_check(struct task_struct *child, unsigned int mode)
{
return call_int_hook(ptrace_access_check, child, mode);
}
/**
* security_ptrace_traceme() - Check if tracing is allowed
* @parent: tracing process
*
* Check that the @parent process has sufficient permission to trace the
* current process before allowing the current process to present itself to the
* @parent process for tracing.
*
* Return: Returns 0 if permission is granted.
*/
int security_ptrace_traceme(struct task_struct *parent)
{
return call_int_hook(ptrace_traceme, parent);
}
/**
* security_capget() - Get the capability sets for a process
* @target: target process
* @effective: effective capability set
* @inheritable: inheritable capability set
* @permitted: permitted capability set
*
* Get the @effective, @inheritable, and @permitted capability sets for the
* @target process. The hook may also perform permission checking to determine
* if the current process is allowed to see the capability sets of the @target
* process.
*
* Return: Returns 0 if the capability sets were successfully obtained.
*/
int security_capget(const struct task_struct *target,
kernel_cap_t *effective,
kernel_cap_t *inheritable,
kernel_cap_t *permitted)
{
return call_int_hook(capget, target, effective, inheritable, permitted);
}
/**
* security_capset() - Set the capability sets for a process
* @new: new credentials for the target process
* @old: current credentials of the target process
* @effective: effective capability set
* @inheritable: inheritable capability set
* @permitted: permitted capability set
*
* Set the @effective, @inheritable, and @permitted capability sets for the
* current process.
*
* Return: Returns 0 and update @new if permission is granted.
*/
int security_capset(struct cred *new, const struct cred *old,
const kernel_cap_t *effective,
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted)
{
return call_int_hook(capset, new, old, effective, inheritable,
permitted);
}
/**
* security_capable() - Check if a process has the necessary capability
* @cred: credentials to examine
* @ns: user namespace
* @cap: capability requested
* @opts: capability check options
*
* Check whether the @tsk process has the @cap capability in the indicated
* credentials. @cap contains the capability <include/linux/capability.h>.
* @opts contains options for the capable check <include/linux/security.h>.
*
* Return: Returns 0 if the capability is granted.
*/
int security_capable(const struct cred *cred,
struct user_namespace *ns,
int cap,
unsigned int opts)
{ return call_int_hook(capable, cred, ns, cap, opts);
}
/**
* security_quotactl() - Check if a quotactl() syscall is allowed for this fs
* @cmds: commands
* @type: type
* @id: id
* @sb: filesystem
*
* Check whether the quotactl syscall is allowed for this @sb.
*
* Return: Returns 0 if permission is granted.
*/
int security_quotactl(int cmds, int type, int id, const struct super_block *sb)
{
return call_int_hook(quotactl, cmds, type, id, sb);
}
/**
* security_quota_on() - Check if QUOTAON is allowed for a dentry
* @dentry: dentry
*
* Check whether QUOTAON is allowed for @dentry.
*
* Return: Returns 0 if permission is granted.
*/
int security_quota_on(struct dentry *dentry)
{
return call_int_hook(quota_on, dentry);
}
/**
* security_syslog() - Check if accessing the kernel message ring is allowed
* @type: SYSLOG_ACTION_* type
*
* Check permission before accessing the kernel message ring or changing
* logging to the console. See the syslog(2) manual page for an explanation of
* the @type values.
*
* Return: Return 0 if permission is granted.
*/
int security_syslog(int type)
{
return call_int_hook(syslog, type);
}
/**
* security_settime64() - Check if changing the system time is allowed
* @ts: new time
* @tz: timezone
*
* Check permission to change the system time, struct timespec64 is defined in
* <include/linux/time64.h> and timezone is defined in <include/linux/time.h>.
*
* Return: Returns 0 if permission is granted.
*/
int security_settime64(const struct timespec64 *ts, const struct timezone *tz)
{
return call_int_hook(settime, ts, tz);
}
/**
* security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed
* @mm: mm struct
* @pages: number of pages
*
* Check permissions for allocating a new virtual mapping. If all LSMs return
* a positive value, __vm_enough_memory() will be called with cap_sys_admin
* set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be
* called with cap_sys_admin cleared.
*
* Return: Returns 0 if permission is granted by the LSM infrastructure to the
* caller.
*/
int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
{
struct lsm_static_call *scall;
int cap_sys_admin = 1;
int rc;
/*
* The module will respond with 0 if it thinks the __vm_enough_memory()
* call should be made with the cap_sys_admin set. If all of the modules
* agree that it should be set it will. If any module thinks it should
* not be set it won't.
*/
lsm_for_each_hook(scall, vm_enough_memory) {
rc = scall->hl->hook.vm_enough_memory(mm, pages);
if (rc < 0) {
cap_sys_admin = 0;
break;
}
}
return __vm_enough_memory(mm, pages, cap_sys_admin);
}
/**
* security_bprm_creds_for_exec() - Prepare the credentials for exec()
* @bprm: binary program information
*
* If the setup in prepare_exec_creds did not setup @bprm->cred->security
* properly for executing @bprm->file, update the LSM's portion of
* @bprm->cred->security to be what commit_creds needs to install for the new
* program. This hook may also optionally check permissions (e.g. for
* transitions between security domains). The hook must set @bprm->secureexec
* to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm
* contains the linux_binprm structure.
*
* If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is
* set. The result must be the same as without this flag even if the execution
* will never really happen and @bprm will always be dropped.
*
* This hook must not change current->cred, only @bprm->cred.
*
* Return: Returns 0 if the hook is successful and permission is granted.
*/
int security_bprm_creds_for_exec(struct linux_binprm *bprm)
{
return call_int_hook(bprm_creds_for_exec, bprm);
}
/**
* security_bprm_creds_from_file() - Update linux_binprm creds based on file
* @bprm: binary program information
* @file: associated file
*
* If @file is setpcap, suid, sgid or otherwise marked to change privilege upon
* exec, update @bprm->cred to reflect that change. This is called after
* finding the binary that will be executed without an interpreter. This
* ensures that the credentials will not be derived from a script that the
* binary will need to reopen, which when reopend may end up being a completely
* different file. This hook may also optionally check permissions (e.g. for
* transitions between security domains). The hook must set @bprm->secureexec
* to 1 if AT_SECURE should be set to request libc enable secure mode. The
* hook must add to @bprm->per_clear any personality flags that should be
* cleared from current->personality. @bprm contains the linux_binprm
* structure.
*
* Return: Returns 0 if the hook is successful and permission is granted.
*/
int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file)
{
return call_int_hook(bprm_creds_from_file, bprm, file);
}
/**
* security_bprm_check() - Mediate binary handler search
* @bprm: binary program information
*
* This hook mediates the point when a search for a binary handler will begin.
* It allows a check against the @bprm->cred->security value which was set in
* the preceding creds_for_exec call. The argv list and envp list are reliably
* available in @bprm. This hook may be called multiple times during a single
* execve. @bprm contains the linux_binprm structure.
*
* Return: Returns 0 if the hook is successful and permission is granted.
*/
int security_bprm_check(struct linux_binprm *bprm)
{
return call_int_hook(bprm_check_security, bprm);
}
/**
* security_bprm_committing_creds() - Install creds for a process during exec()
* @bprm: binary program information
*
* Prepare to install the new security attributes of a process being
* transformed by an execve operation, based on the old credentials pointed to
* by @current->cred and the information set in @bprm->cred by the
* bprm_creds_for_exec hook. @bprm points to the linux_binprm structure. This
* hook is a good place to perform state changes on the process such as closing
* open file descriptors to which access will no longer be granted when the
* attributes are changed. This is called immediately before commit_creds().
*/
void security_bprm_committing_creds(const struct linux_binprm *bprm)
{
call_void_hook(bprm_committing_creds, bprm);
}
/**
* security_bprm_committed_creds() - Tidy up after cred install during exec()
* @bprm: binary program information
*
* Tidy up after the installation of the new security attributes of a process
* being transformed by an execve operation. The new credentials have, by this
* point, been set to @current->cred. @bprm points to the linux_binprm
* structure. This hook is a good place to perform state changes on the
* process such as clearing out non-inheritable signal state. This is called
* immediately after commit_creds().
*/
void security_bprm_committed_creds(const struct linux_binprm *bprm)
{
call_void_hook(bprm_committed_creds, bprm);
}
/**
* security_fs_context_submount() - Initialise fc->security
* @fc: new filesystem context
* @reference: dentry reference for submount/remount
*
* Fill out the ->security field for a new fs_context.
*
* Return: Returns 0 on success or negative error code on failure.
*/
int security_fs_context_submount(struct fs_context *fc, struct super_block *reference)
{
return call_int_hook(fs_context_submount, fc, reference);
}
/**
* security_fs_context_dup() - Duplicate a fs_context LSM blob
* @fc: destination filesystem context
* @src_fc: source filesystem context
*
* Allocate and attach a security structure to sc->security. This pointer is
* initialised to NULL by the caller. @fc indicates the new filesystem context.
* @src_fc indicates the original filesystem context.
*
* Return: Returns 0 on success or a negative error code on failure.
*/
int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc)
{
return call_int_hook(fs_context_dup, fc, src_fc);
}
/**
* security_fs_context_parse_param() - Configure a filesystem context
* @fc: filesystem context
* @param: filesystem parameter
*
* Userspace provided a parameter to configure a superblock. The LSM can
* consume the parameter or return it to the caller for use elsewhere.
*
* Return: If the parameter is used by the LSM it should return 0, if it is
* returned to the caller -ENOPARAM is returned, otherwise a negative
* error code is returned.
*/
int security_fs_context_parse_param(struct fs_context *fc,
struct fs_parameter *param)
{
struct lsm_static_call *scall;
int trc;
int rc = -ENOPARAM;
lsm_for_each_hook(scall, fs_context_parse_param) {
trc = scall->hl->hook.fs_context_parse_param(fc, param);
if (trc == 0)
rc = 0;
else if (trc != -ENOPARAM)
return trc;
}
return rc;
}
/**
* security_sb_alloc() - Allocate a super_block LSM blob
* @sb: filesystem superblock
*
* Allocate and attach a security structure to the sb->s_security field. The
* s_security field is initialized to NULL when the structure is allocated.
* @sb contains the super_block structure to be modified.
*
* Return: Returns 0 if operation was successful.
*/
int security_sb_alloc(struct super_block *sb)
{
int rc = lsm_superblock_alloc(sb);
if (unlikely(rc))
return rc;
rc = call_int_hook(sb_alloc_security, sb);
if (unlikely(rc))
security_sb_free(sb);
return rc;
}
/**
* security_sb_delete() - Release super_block LSM associated objects
* @sb: filesystem superblock
*
* Release objects tied to a superblock (e.g. inodes). @sb contains the
* super_block structure being released.
*/
void security_sb_delete(struct super_block *sb)
{
call_void_hook(sb_delete, sb);
}
/**
* security_sb_free() - Free a super_block LSM blob
* @sb: filesystem superblock
*
* Deallocate and clear the sb->s_security field. @sb contains the super_block
* structure to be modified.
*/
void security_sb_free(struct super_block *sb)
{
call_void_hook(sb_free_security, sb);
kfree(sb->s_security);
sb->s_security = NULL;
}
/**
* security_free_mnt_opts() - Free memory associated with mount options
* @mnt_opts: LSM processed mount options
*
* Free memory associated with @mnt_ops.
*/
void security_free_mnt_opts(void **mnt_opts)
{
if (!*mnt_opts)
return;
call_void_hook(sb_free_mnt_opts, *mnt_opts);
*mnt_opts = NULL;
}
EXPORT_SYMBOL(security_free_mnt_opts);
/**
* security_sb_eat_lsm_opts() - Consume LSM mount options
* @options: mount options
* @mnt_opts: LSM processed mount options
*
* Eat (scan @options) and save them in @mnt_opts.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_sb_eat_lsm_opts(char *options, void **mnt_opts)
{
return call_int_hook(sb_eat_lsm_opts, options, mnt_opts);
}
EXPORT_SYMBOL(security_sb_eat_lsm_opts);
/**
* security_sb_mnt_opts_compat() - Check if new mount options are allowed
* @sb: filesystem superblock
* @mnt_opts: new mount options
*
* Determine if the new mount options in @mnt_opts are allowed given the
* existing mounted filesystem at @sb. @sb superblock being compared.
*
* Return: Returns 0 if options are compatible.
*/
int security_sb_mnt_opts_compat(struct super_block *sb,
void *mnt_opts)
{
return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts);
}
EXPORT_SYMBOL(security_sb_mnt_opts_compat);
/**
* security_sb_remount() - Verify no incompatible mount changes during remount
* @sb: filesystem superblock
* @mnt_opts: (re)mount options
*
* Extracts security system specific mount options and verifies no changes are
* being made to those options.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_remount(struct super_block *sb,
void *mnt_opts)
{
return call_int_hook(sb_remount, sb, mnt_opts);
}
EXPORT_SYMBOL(security_sb_remount);
/**
* security_sb_kern_mount() - Check if a kernel mount is allowed
* @sb: filesystem superblock
*
* Mount this @sb if allowed by permissions.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_kern_mount(const struct super_block *sb)
{
return call_int_hook(sb_kern_mount, sb);
}
/**
* security_sb_show_options() - Output the mount options for a superblock
* @m: output file
* @sb: filesystem superblock
*
* Show (print on @m) mount options for this @sb.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_sb_show_options(struct seq_file *m, struct super_block *sb)
{
return call_int_hook(sb_show_options, m, sb);
}
/**
* security_sb_statfs() - Check if accessing fs stats is allowed
* @dentry: superblock handle
*
* Check permission before obtaining filesystem statistics for the @mnt
* mountpoint. @dentry is a handle on the superblock for the filesystem.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_statfs(struct dentry *dentry)
{
return call_int_hook(sb_statfs, dentry);
}
/**
* security_sb_mount() - Check permission for mounting a filesystem
* @dev_name: filesystem backing device
* @path: mount point
* @type: filesystem type
* @flags: mount flags
* @data: filesystem specific data
*
* Check permission before an object specified by @dev_name is mounted on the
* mount point named by @nd. For an ordinary mount, @dev_name identifies a
* device if the file system type requires a device. For a remount
* (@flags & MS_REMOUNT), @dev_name is irrelevant. For a loopback/bind mount
* (@flags & MS_BIND), @dev_name identifies the pathname of the object being
* mounted.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_mount(const char *dev_name, const struct path *path,
const char *type, unsigned long flags, void *data)
{
return call_int_hook(sb_mount, dev_name, path, type, flags, data);
}
/**
* security_sb_umount() - Check permission for unmounting a filesystem
* @mnt: mounted filesystem
* @flags: unmount flags
*
* Check permission before the @mnt file system is unmounted.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_umount(struct vfsmount *mnt, int flags)
{
return call_int_hook(sb_umount, mnt, flags);
}
/**
* security_sb_pivotroot() - Check permissions for pivoting the rootfs
* @old_path: new location for current rootfs
* @new_path: location of the new rootfs
*
* Check permission before pivoting the root filesystem.
*
* Return: Returns 0 if permission is granted.
*/
int security_sb_pivotroot(const struct path *old_path,
const struct path *new_path)
{
return call_int_hook(sb_pivotroot, old_path, new_path);
}
/**
* security_sb_set_mnt_opts() - Set the mount options for a filesystem
* @sb: filesystem superblock
* @mnt_opts: binary mount options
* @kern_flags: kernel flags (in)
* @set_kern_flags: kernel flags (out)
*
* Set the security relevant mount options used for a superblock.
*
* Return: Returns 0 on success, error on failure.
*/
int security_sb_set_mnt_opts(struct super_block *sb,
void *mnt_opts,
unsigned long kern_flags,
unsigned long *set_kern_flags)
{
struct lsm_static_call *scall;
int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts);
lsm_for_each_hook(scall, sb_set_mnt_opts) {
rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags,
set_kern_flags);
if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts))
break;
}
return rc;
}
EXPORT_SYMBOL(security_sb_set_mnt_opts);
/**
* security_sb_clone_mnt_opts() - Duplicate superblock mount options
* @oldsb: source superblock
* @newsb: destination superblock
* @kern_flags: kernel flags (in)
* @set_kern_flags: kernel flags (out)
*
* Copy all security options from a given superblock to another.
*
* Return: Returns 0 on success, error on failure.
*/
int security_sb_clone_mnt_opts(const struct super_block *oldsb,
struct super_block *newsb,
unsigned long kern_flags,
unsigned long *set_kern_flags)
{
return call_int_hook(sb_clone_mnt_opts, oldsb, newsb,
kern_flags, set_kern_flags);
}
EXPORT_SYMBOL(security_sb_clone_mnt_opts);
/**
* security_move_mount() - Check permissions for moving a mount
* @from_path: source mount point
* @to_path: destination mount point
*
* Check permission before a mount is moved.
*
* Return: Returns 0 if permission is granted.
*/
int security_move_mount(const struct path *from_path,
const struct path *to_path)
{
return call_int_hook(move_mount, from_path, to_path);
}
/**
* security_path_notify() - Check if setting a watch is allowed
* @path: file path
* @mask: event mask
* @obj_type: file path type
*
* Check permissions before setting a watch on events as defined by @mask, on
* an object at @path, whose type is defined by @obj_type.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_notify(const struct path *path, u64 mask,
unsigned int obj_type)
{
return call_int_hook(path_notify, path, mask, obj_type);
}
/**
* security_inode_alloc() - Allocate an inode LSM blob
* @inode: the inode
* @gfp: allocation flags
*
* Allocate and attach a security structure to @inode->i_security. The
* i_security field is initialized to NULL when the inode structure is
* allocated.
*
* Return: Return 0 if operation was successful.
*/
int security_inode_alloc(struct inode *inode, gfp_t gfp)
{ int rc = lsm_inode_alloc(inode, gfp);
if (unlikely(rc))
return rc;
rc = call_int_hook(inode_alloc_security, inode); if (unlikely(rc))
security_inode_free(inode);
return rc;
}
static void inode_free_by_rcu(struct rcu_head *head)
{
/* The rcu head is at the start of the inode blob */
call_void_hook(inode_free_security_rcu, head);
kmem_cache_free(lsm_inode_cache, head);
}
/**
* security_inode_free() - Free an inode's LSM blob
* @inode: the inode
*
* Release any LSM resources associated with @inode, although due to the
* inode's RCU protections it is possible that the resources will not be
* fully released until after the current RCU grace period has elapsed.
*
* It is important for LSMs to note that despite being present in a call to
* security_inode_free(), @inode may still be referenced in a VFS path walk
* and calls to security_inode_permission() may be made during, or after,
* a call to security_inode_free(). For this reason the inode->i_security
* field is released via a call_rcu() callback and any LSMs which need to
* retain inode state for use in security_inode_permission() should only
* release that state in the inode_free_security_rcu() LSM hook callback.
*/
void security_inode_free(struct inode *inode)
{ call_void_hook(inode_free_security, inode); if (!inode->i_security)
return;
call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu);
}
/**
* security_dentry_init_security() - Perform dentry initialization
* @dentry: the dentry to initialize
* @mode: mode used to determine resource type
* @name: name of the last path component
* @xattr_name: name of the security/LSM xattr
* @lsmctx: pointer to the resulting LSM context
*
* Compute a context for a dentry as the inode is not yet available since NFSv4
* has no label backed by an EA anyway. It is important to note that
* @xattr_name does not need to be free'd by the caller, it is a static string.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_dentry_init_security(struct dentry *dentry, int mode,
const struct qstr *name,
const char **xattr_name,
struct lsm_context *lsmctx)
{
return call_int_hook(dentry_init_security, dentry, mode, name,
xattr_name, lsmctx);
}
EXPORT_SYMBOL(security_dentry_init_security);
/**
* security_dentry_create_files_as() - Perform dentry initialization
* @dentry: the dentry to initialize
* @mode: mode used to determine resource type
* @name: name of the last path component
* @old: creds to use for LSM context calculations
* @new: creds to modify
*
* Compute a context for a dentry as the inode is not yet available and set
* that context in passed in creds so that new files are created using that
* context. Context is calculated using the passed in creds and not the creds
* of the caller.
*
* Return: Returns 0 on success, error on failure.
*/
int security_dentry_create_files_as(struct dentry *dentry, int mode,
struct qstr *name,
const struct cred *old, struct cred *new)
{
return call_int_hook(dentry_create_files_as, dentry, mode,
name, old, new);
}
EXPORT_SYMBOL(security_dentry_create_files_as);
/**
* security_inode_init_security() - Initialize an inode's LSM context
* @inode: the inode
* @dir: parent directory
* @qstr: last component of the pathname
* @initxattrs: callback function to write xattrs
* @fs_data: filesystem specific data
*
* Obtain the security attribute name suffix and value to set on a newly
* created inode and set up the incore security field for the new inode. This
* hook is called by the fs code as part of the inode creation transaction and
* provides for atomic labeling of the inode, unlike the post_create/mkdir/...
* hooks called by the VFS.
*
* The hook function is expected to populate the xattrs array, by calling
* lsm_get_xattr_slot() to retrieve the slots reserved by the security module
* with the lbs_xattr_count field of the lsm_blob_sizes structure. For each
* slot, the hook function should set ->name to the attribute name suffix
* (e.g. selinux), to allocate ->value (will be freed by the caller) and set it
* to the attribute value, to set ->value_len to the length of the value. If
* the security module does not use security attributes or does not wish to put
* a security attribute on this particular inode, then it should return
* -EOPNOTSUPP to skip this processing.
*
* Return: Returns 0 if the LSM successfully initialized all of the inode
* security attributes that are required, negative values otherwise.
*/
int security_inode_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr,
const initxattrs initxattrs, void *fs_data)
{
struct lsm_static_call *scall;
struct xattr *new_xattrs = NULL;
int ret = -EOPNOTSUPP, xattr_count = 0;
if (unlikely(IS_PRIVATE(inode)))
return 0;
if (!blob_sizes.lbs_xattr_count)
return 0;
if (initxattrs) {
/* Allocate +1 as terminator. */
new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1,
sizeof(*new_xattrs), GFP_NOFS);
if (!new_xattrs)
return -ENOMEM;
}
lsm_for_each_hook(scall, inode_init_security) {
ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs,
&xattr_count);
if (ret && ret != -EOPNOTSUPP)
goto out;
/*
* As documented in lsm_hooks.h, -EOPNOTSUPP in this context
* means that the LSM is not willing to provide an xattr, not
* that it wants to signal an error. Thus, continue to invoke
* the remaining LSMs.
*/
}
/* If initxattrs() is NULL, xattr_count is zero, skip the call. */
if (!xattr_count)
goto out;
ret = initxattrs(inode, new_xattrs, fs_data);
out:
for (; xattr_count > 0; xattr_count--)
kfree(new_xattrs[xattr_count - 1].value);
kfree(new_xattrs);
return (ret == -EOPNOTSUPP) ? 0 : ret;
}
EXPORT_SYMBOL(security_inode_init_security);
/**
* security_inode_init_security_anon() - Initialize an anonymous inode
* @inode: the inode
* @name: the anonymous inode class
* @context_inode: an optional related inode
*
* Set up the incore security field for the new anonymous inode and return
* whether the inode creation is permitted by the security module or not.
*
* Return: Returns 0 on success, -EACCES if the security module denies the
* creation of this inode, or another -errno upon other errors.
*/
int security_inode_init_security_anon(struct inode *inode,
const struct qstr *name,
const struct inode *context_inode)
{
return call_int_hook(inode_init_security_anon, inode, name,
context_inode);
}
#ifdef CONFIG_SECURITY_PATH
/**
* security_path_mknod() - Check if creating a special file is allowed
* @dir: parent directory
* @dentry: new file
* @mode: new file mode
* @dev: device number
*
* Check permissions when creating a file. Note that this hook is called even
* if mknod operation is being done for a regular file.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_mknod(const struct path *dir, struct dentry *dentry,
umode_t mode, unsigned int dev)
{ if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
return 0;
return call_int_hook(path_mknod, dir, dentry, mode, dev);
}
EXPORT_SYMBOL(security_path_mknod);
/**
* security_path_post_mknod() - Update inode security after reg file creation
* @idmap: idmap of the mount
* @dentry: new file
*
* Update inode security field after a regular file has been created.
*/
void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(path_post_mknod, idmap, dentry);
}
/**
* security_path_mkdir() - Check if creating a new directory is allowed
* @dir: parent directory
* @dentry: new directory
* @mode: new directory mode
*
* Check permissions to create a new directory in the existing directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_mkdir(const struct path *dir, struct dentry *dentry,
umode_t mode)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
return 0;
return call_int_hook(path_mkdir, dir, dentry, mode);
}
EXPORT_SYMBOL(security_path_mkdir);
/**
* security_path_rmdir() - Check if removing a directory is allowed
* @dir: parent directory
* @dentry: directory to remove
*
* Check the permission to remove a directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_rmdir(const struct path *dir, struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
return 0;
return call_int_hook(path_rmdir, dir, dentry);
}
/**
* security_path_unlink() - Check if removing a hard link is allowed
* @dir: parent directory
* @dentry: file
*
* Check the permission to remove a hard link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_unlink(const struct path *dir, struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
return 0;
return call_int_hook(path_unlink, dir, dentry);
}
EXPORT_SYMBOL(security_path_unlink);
/**
* security_path_symlink() - Check if creating a symbolic link is allowed
* @dir: parent directory
* @dentry: symbolic link
* @old_name: file pathname
*
* Check the permission to create a symbolic link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_symlink(const struct path *dir, struct dentry *dentry,
const char *old_name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
return 0;
return call_int_hook(path_symlink, dir, dentry, old_name);
}
/**
* security_path_link - Check if creating a hard link is allowed
* @old_dentry: existing file
* @new_dir: new parent directory
* @new_dentry: new link
*
* Check permission before creating a new hard link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
struct dentry *new_dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry))))
return 0;
return call_int_hook(path_link, old_dentry, new_dir, new_dentry);
}
/**
* security_path_rename() - Check if renaming a file is allowed
* @old_dir: parent directory of the old file
* @old_dentry: the old file
* @new_dir: parent directory of the new file
* @new_dentry: the new file
* @flags: flags
*
* Check for permission to rename a file or directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_rename(const struct path *old_dir, struct dentry *old_dentry,
const struct path *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) ||
(d_is_positive(new_dentry) &&
IS_PRIVATE(d_backing_inode(new_dentry)))))
return 0;
return call_int_hook(path_rename, old_dir, old_dentry, new_dir,
new_dentry, flags);
}
EXPORT_SYMBOL(security_path_rename);
/**
* security_path_truncate() - Check if truncating a file is allowed
* @path: file
*
* Check permission before truncating the file indicated by path. Note that
* truncation permissions may also be checked based on already opened files,
* using the security_file_truncate() hook.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_truncate(const struct path *path)
{
if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
return 0;
return call_int_hook(path_truncate, path);
}
/**
* security_path_chmod() - Check if changing the file's mode is allowed
* @path: file
* @mode: new mode
*
* Check for permission to change a mode of the file @path. The new mode is
* specified in @mode which is a bitmask of constants from
* <include/uapi/linux/stat.h>.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_chmod(const struct path *path, umode_t mode)
{
if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
return 0;
return call_int_hook(path_chmod, path, mode);
}
/**
* security_path_chown() - Check if changing the file's owner/group is allowed
* @path: file
* @uid: file owner
* @gid: file group
*
* Check for permission to change owner/group of a file or directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
{
if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
return 0;
return call_int_hook(path_chown, path, uid, gid);
}
/**
* security_path_chroot() - Check if changing the root directory is allowed
* @path: directory
*
* Check for permission to change root directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_path_chroot(const struct path *path)
{
return call_int_hook(path_chroot, path);
}
#endif /* CONFIG_SECURITY_PATH */
/**
* security_inode_create() - Check if creating a file is allowed
* @dir: the parent directory
* @dentry: the file being created
* @mode: requested file mode
*
* Check permission to create a regular file.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_create(struct inode *dir, struct dentry *dentry,
umode_t mode)
{ if (unlikely(IS_PRIVATE(dir)))
return 0;
return call_int_hook(inode_create, dir, dentry, mode);
}
EXPORT_SYMBOL_GPL(security_inode_create);
/**
* security_inode_post_create_tmpfile() - Update inode security of new tmpfile
* @idmap: idmap of the mount
* @inode: inode of the new tmpfile
*
* Update inode security data after a tmpfile has been created.
*/
void security_inode_post_create_tmpfile(struct mnt_idmap *idmap,
struct inode *inode)
{ if (unlikely(IS_PRIVATE(inode)))
return;
call_void_hook(inode_post_create_tmpfile, idmap, inode);
}
/**
* security_inode_link() - Check if creating a hard link is allowed
* @old_dentry: existing file
* @dir: new parent directory
* @new_dentry: new link
*
* Check permission before creating a new hard link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry))))
return 0;
return call_int_hook(inode_link, old_dentry, dir, new_dentry);
}
/**
* security_inode_unlink() - Check if removing a hard link is allowed
* @dir: parent directory
* @dentry: file
*
* Check the permission to remove a hard link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_unlink(struct inode *dir, struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_unlink, dir, dentry);
}
/**
* security_inode_symlink() - Check if creating a symbolic link is allowed
* @dir: parent directory
* @dentry: symbolic link
* @old_name: existing filename
*
* Check the permission to create a symbolic link to a file.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_symlink(struct inode *dir, struct dentry *dentry,
const char *old_name)
{
if (unlikely(IS_PRIVATE(dir)))
return 0;
return call_int_hook(inode_symlink, dir, dentry, old_name);
}
/**
* security_inode_mkdir() - Check if creation a new director is allowed
* @dir: parent directory
* @dentry: new directory
* @mode: new directory mode
*
* Check permissions to create a new directory in the existing directory
* associated with inode structure @dir.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
if (unlikely(IS_PRIVATE(dir)))
return 0;
return call_int_hook(inode_mkdir, dir, dentry, mode);
}
EXPORT_SYMBOL_GPL(security_inode_mkdir);
/**
* security_inode_rmdir() - Check if removing a directory is allowed
* @dir: parent directory
* @dentry: directory to be removed
*
* Check the permission to remove a directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_rmdir(struct inode *dir, struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_rmdir, dir, dentry);
}
/**
* security_inode_mknod() - Check if creating a special file is allowed
* @dir: parent directory
* @dentry: new file
* @mode: new file mode
* @dev: device number
*
* Check permissions when creating a special file (or a socket or a fifo file
* created via the mknod system call). Note that if mknod operation is being
* done for a regular file, then the create hook will be called and not this
* hook.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t dev)
{
if (unlikely(IS_PRIVATE(dir)))
return 0;
return call_int_hook(inode_mknod, dir, dentry, mode, dev);
}
/**
* security_inode_rename() - Check if renaming a file is allowed
* @old_dir: parent directory of the old file
* @old_dentry: the old file
* @new_dir: parent directory of the new file
* @new_dentry: the new file
* @flags: flags
*
* Check for permission to rename a file or directory.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) ||
(d_is_positive(new_dentry) &&
IS_PRIVATE(d_backing_inode(new_dentry)))))
return 0;
if (flags & RENAME_EXCHANGE) {
int err = call_int_hook(inode_rename, new_dir, new_dentry,
old_dir, old_dentry);
if (err)
return err;
}
return call_int_hook(inode_rename, old_dir, old_dentry,
new_dir, new_dentry);
}
/**
* security_inode_readlink() - Check if reading a symbolic link is allowed
* @dentry: link
*
* Check the permission to read the symbolic link.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_readlink(struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_readlink, dentry);
}
/**
* security_inode_follow_link() - Check if following a symbolic link is allowed
* @dentry: link dentry
* @inode: link inode
* @rcu: true if in RCU-walk mode
*
* Check permission to follow a symbolic link when looking up a pathname. If
* @rcu is true, @inode is not stable.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
bool rcu)
{
if (unlikely(IS_PRIVATE(inode)))
return 0;
return call_int_hook(inode_follow_link, dentry, inode, rcu);
}
/**
* security_inode_permission() - Check if accessing an inode is allowed
* @inode: inode
* @mask: access mask
*
* Check permission before accessing an inode. This hook is called by the
* existing Linux permission function, so a security module can use it to
* provide additional checking for existing Linux permission checks. Notice
* that this hook is called when a file is opened (as well as many other
* operations), whereas the file_security_ops permission hook is called when
* the actual read/write operations are performed.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_permission(struct inode *inode, int mask)
{ if (unlikely(IS_PRIVATE(inode)))
return 0;
return call_int_hook(inode_permission, inode, mask);
}
/**
* security_inode_setattr() - Check if setting file attributes is allowed
* @idmap: idmap of the mount
* @dentry: file
* @attr: new attributes
*
* Check permission before setting file attributes. Note that the kernel call
* to notify_change is performed from several locations, whenever file
* attributes change (such as when a file is truncated, chown/chmod operations,
* transferring disk quotas, etc).
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *attr)
{ if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_setattr, idmap, dentry, attr);
}
EXPORT_SYMBOL_GPL(security_inode_setattr);
/**
* security_inode_post_setattr() - Update the inode after a setattr operation
* @idmap: idmap of the mount
* @dentry: file
* @ia_valid: file attributes set
*
* Update inode security field after successful setting file attributes.
*/
void security_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
int ia_valid)
{ if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(inode_post_setattr, idmap, dentry, ia_valid);
}
/**
* security_inode_getattr() - Check if getting file attributes is allowed
* @path: file
*
* Check permission before obtaining file attributes.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_getattr(const struct path *path)
{
if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
return 0;
return call_int_hook(inode_getattr, path);
}
/**
* security_inode_setxattr() - Check if setting file xattrs is allowed
* @idmap: idmap of the mount
* @dentry: file
* @name: xattr name
* @value: xattr value
* @size: size of xattr value
* @flags: flags
*
* This hook performs the desired permission checks before setting the extended
* attributes (xattrs) on @dentry. It is important to note that we have some
* additional logic before the main LSM implementation calls to detect if we
* need to perform an additional capability check at the LSM layer.
*
* Normally we enforce a capability check prior to executing the various LSM
* hook implementations, but if a LSM wants to avoid this capability check,
* it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
* xattrs that it wants to avoid the capability check, leaving the LSM fully
* responsible for enforcing the access control for the specific xattr. If all
* of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
* or return a 0 (the default return value), the capability check is still
* performed. If no 'inode_xattr_skipcap' hooks are registered the capability
* check is performed.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_setxattr(struct mnt_idmap *idmap,
struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
int rc;
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
/* enforce the capability checks at the lsm layer, if needed */
if (!call_int_hook(inode_xattr_skipcap, name)) {
rc = cap_inode_setxattr(dentry, name, value, size, flags);
if (rc)
return rc;
}
return call_int_hook(inode_setxattr, idmap, dentry, name, value, size,
flags);
}
/**
* security_inode_set_acl() - Check if setting posix acls is allowed
* @idmap: idmap of the mount
* @dentry: file
* @acl_name: acl name
* @kacl: acl struct
*
* Check permission before setting posix acls, the posix acls in @kacl are
* identified by @acl_name.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_set_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name,
struct posix_acl *kacl)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_set_acl, idmap, dentry, acl_name, kacl);
}
/**
* security_inode_post_set_acl() - Update inode security from posix acls set
* @dentry: file
* @acl_name: acl name
* @kacl: acl struct
*
* Update inode security data after successfully setting posix acls on @dentry.
* The posix acls in @kacl are identified by @acl_name.
*/
void security_inode_post_set_acl(struct dentry *dentry, const char *acl_name,
struct posix_acl *kacl)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(inode_post_set_acl, dentry, acl_name, kacl);
}
/**
* security_inode_get_acl() - Check if reading posix acls is allowed
* @idmap: idmap of the mount
* @dentry: file
* @acl_name: acl name
*
* Check permission before getting osix acls, the posix acls are identified by
* @acl_name.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_get_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_get_acl, idmap, dentry, acl_name);
}
/**
* security_inode_remove_acl() - Check if removing a posix acl is allowed
* @idmap: idmap of the mount
* @dentry: file
* @acl_name: acl name
*
* Check permission before removing posix acls, the posix acls are identified
* by @acl_name.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_remove_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_remove_acl, idmap, dentry, acl_name);
}
/**
* security_inode_post_remove_acl() - Update inode security after rm posix acls
* @idmap: idmap of the mount
* @dentry: file
* @acl_name: acl name
*
* Update inode security data after successfully removing posix acls on
* @dentry in @idmap. The posix acls are identified by @acl_name.
*/
void security_inode_post_remove_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(inode_post_remove_acl, idmap, dentry, acl_name);
}
/**
* security_inode_post_setxattr() - Update the inode after a setxattr operation
* @dentry: file
* @name: xattr name
* @value: xattr value
* @size: xattr value size
* @flags: flags
*
* Update inode security field after successful setxattr operation.
*/
void security_inode_post_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(inode_post_setxattr, dentry, name, value, size, flags);
}
/**
* security_inode_getxattr() - Check if xattr access is allowed
* @dentry: file
* @name: xattr name
*
* Check permission before obtaining the extended attributes identified by
* @name for @dentry.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_getxattr(struct dentry *dentry, const char *name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_getxattr, dentry, name);
}
/**
* security_inode_listxattr() - Check if listing xattrs is allowed
* @dentry: file
*
* Check permission before obtaining the list of extended attribute names for
* @dentry.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_listxattr(struct dentry *dentry)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
return call_int_hook(inode_listxattr, dentry);
}
/**
* security_inode_removexattr() - Check if removing an xattr is allowed
* @idmap: idmap of the mount
* @dentry: file
* @name: xattr name
*
* This hook performs the desired permission checks before setting the extended
* attributes (xattrs) on @dentry. It is important to note that we have some
* additional logic before the main LSM implementation calls to detect if we
* need to perform an additional capability check at the LSM layer.
*
* Normally we enforce a capability check prior to executing the various LSM
* hook implementations, but if a LSM wants to avoid this capability check,
* it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
* xattrs that it wants to avoid the capability check, leaving the LSM fully
* responsible for enforcing the access control for the specific xattr. If all
* of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
* or return a 0 (the default return value), the capability check is still
* performed. If no 'inode_xattr_skipcap' hooks are registered the capability
* check is performed.
*
* Return: Returns 0 if permission is granted.
*/
int security_inode_removexattr(struct mnt_idmap *idmap,
struct dentry *dentry, const char *name)
{
int rc;
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return 0;
/* enforce the capability checks at the lsm layer, if needed */
if (!call_int_hook(inode_xattr_skipcap, name)) {
rc = cap_inode_removexattr(idmap, dentry, name);
if (rc)
return rc;
}
return call_int_hook(inode_removexattr, idmap, dentry, name);
}
/**
* security_inode_post_removexattr() - Update the inode after a removexattr op
* @dentry: file
* @name: xattr name
*
* Update the inode after a successful removexattr operation.
*/
void security_inode_post_removexattr(struct dentry *dentry, const char *name)
{
if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
return;
call_void_hook(inode_post_removexattr, dentry, name);
}
/**
* security_inode_need_killpriv() - Check if security_inode_killpriv() required
* @dentry: associated dentry
*
* Called when an inode has been changed to determine if
* security_inode_killpriv() should be called.
*
* Return: Return <0 on error to abort the inode change operation, return 0 if
* security_inode_killpriv() does not need to be called, return >0 if
* security_inode_killpriv() does need to be called.
*/
int security_inode_need_killpriv(struct dentry *dentry)
{ return call_int_hook(inode_need_killpriv, dentry);
}
/**
* security_inode_killpriv() - The setuid bit is removed, update LSM state
* @idmap: idmap of the mount
* @dentry: associated dentry
*
* The @dentry's setuid bit is being removed. Remove similar security labels.
* Called with the dentry->d_inode->i_mutex held.
*
* Return: Return 0 on success. If error is returned, then the operation
* causing setuid bit removal is failed.
*/
int security_inode_killpriv(struct mnt_idmap *idmap,
struct dentry *dentry)
{
return call_int_hook(inode_killpriv, idmap, dentry);
}
/**
* security_inode_getsecurity() - Get the xattr security label of an inode
* @idmap: idmap of the mount
* @inode: inode
* @name: xattr name
* @buffer: security label buffer
* @alloc: allocation flag
*
* Retrieve a copy of the extended attribute representation of the security
* label associated with @name for @inode via @buffer. Note that @name is the
* remainder of the attribute name after the security prefix has been removed.
* @alloc is used to specify if the call should return a value via the buffer
* or just the value length.
*
* Return: Returns size of buffer on success.
*/
int security_inode_getsecurity(struct mnt_idmap *idmap,
struct inode *inode, const char *name,
void **buffer, bool alloc)
{
if (unlikely(IS_PRIVATE(inode)))
return LSM_RET_DEFAULT(inode_getsecurity);
return call_int_hook(inode_getsecurity, idmap, inode, name, buffer,
alloc);
}
/**
* security_inode_setsecurity() - Set the xattr security label of an inode
* @inode: inode
* @name: xattr name
* @value: security label
* @size: length of security label
* @flags: flags
*
* Set the security label associated with @name for @inode from the extended
* attribute value @value. @size indicates the size of the @value in bytes.
* @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. Note that @name is the
* remainder of the attribute name after the security. prefix has been removed.
*
* Return: Returns 0 on success.
*/
int security_inode_setsecurity(struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
if (unlikely(IS_PRIVATE(inode)))
return LSM_RET_DEFAULT(inode_setsecurity);
return call_int_hook(inode_setsecurity, inode, name, value, size,
flags);
}
/**
* security_inode_listsecurity() - List the xattr security label names
* @inode: inode
* @buffer: buffer
* @buffer_size: size of buffer
*
* Copy the extended attribute names for the security labels associated with
* @inode into @buffer. The maximum size of @buffer is specified by
* @buffer_size. @buffer may be NULL to request the size of the buffer
* required.
*
* Return: Returns number of bytes used/required on success.
*/
int security_inode_listsecurity(struct inode *inode,
char *buffer, size_t buffer_size)
{
if (unlikely(IS_PRIVATE(inode)))
return 0;
return call_int_hook(inode_listsecurity, inode, buffer, buffer_size);
}
EXPORT_SYMBOL(security_inode_listsecurity);
/**
* security_inode_getlsmprop() - Get an inode's LSM data
* @inode: inode
* @prop: lsm specific information to return
*
* Get the lsm specific information associated with the node.
*/
void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop)
{
call_void_hook(inode_getlsmprop, inode, prop);
}
/**
* security_inode_copy_up() - Create new creds for an overlayfs copy-up op
* @src: union dentry of copy-up file
* @new: newly created creds
*
* A file is about to be copied up from lower layer to upper layer of overlay
* filesystem. Security module can prepare a set of new creds and modify as
* need be and return new creds. Caller will switch to new creds temporarily to
* create new file and release newly allocated creds.
*
* Return: Returns 0 on success or a negative error code on error.
*/
int security_inode_copy_up(struct dentry *src, struct cred **new)
{
return call_int_hook(inode_copy_up, src, new);
}
EXPORT_SYMBOL(security_inode_copy_up);
/**
* security_inode_copy_up_xattr() - Filter xattrs in an overlayfs copy-up op
* @src: union dentry of copy-up file
* @name: xattr name
*
* Filter the xattrs being copied up when a unioned file is copied up from a
* lower layer to the union/overlay layer. The caller is responsible for
* reading and writing the xattrs, this hook is merely a filter.
*
* Return: Returns 0 to accept the xattr, -ECANCELED to discard the xattr,
* -EOPNOTSUPP if the security module does not know about attribute,
* or a negative error code to abort the copy up.
*/
int security_inode_copy_up_xattr(struct dentry *src, const char *name)
{
int rc;
rc = call_int_hook(inode_copy_up_xattr, src, name);
if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr))
return rc;
return LSM_RET_DEFAULT(inode_copy_up_xattr);
}
EXPORT_SYMBOL(security_inode_copy_up_xattr);
/**
* security_inode_setintegrity() - Set the inode's integrity data
* @inode: inode
* @type: type of integrity, e.g. hash digest, signature, etc
* @value: the integrity value
* @size: size of the integrity value
*
* Register a verified integrity measurement of a inode with LSMs.
* LSMs should free the previously saved data if @value is NULL.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_inode_setintegrity(const struct inode *inode,
enum lsm_integrity_type type, const void *value,
size_t size)
{
return call_int_hook(inode_setintegrity, inode, type, value, size);
}
EXPORT_SYMBOL(security_inode_setintegrity);
/**
* security_kernfs_init_security() - Init LSM context for a kernfs node
* @kn_dir: parent kernfs node
* @kn: the kernfs node to initialize
*
* Initialize the security context of a newly created kernfs node based on its
* own and its parent's attributes.
*
* Return: Returns 0 if permission is granted.
*/
int security_kernfs_init_security(struct kernfs_node *kn_dir,
struct kernfs_node *kn)
{
return call_int_hook(kernfs_init_security, kn_dir, kn);
}
/**
* security_file_permission() - Check file permissions
* @file: file
* @mask: requested permissions
*
* Check file permissions before accessing an open file. This hook is called
* by various operations that read or write files. A security module can use
* this hook to perform additional checking on these operations, e.g. to
* revalidate permissions on use to support privilege bracketing or policy
* changes. Notice that this hook is used when the actual read/write
* operations are performed, whereas the inode_security_ops hook is called when
* a file is opened (as well as many other operations). Although this hook can
* be used to revalidate permissions for various system call operations that
* read or write files, it does not address the revalidation of permissions for
* memory-mapped files. Security modules must handle this separately if they
* need such revalidation.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_permission(struct file *file, int mask)
{ return call_int_hook(file_permission, file, mask);
}
/**
* security_file_alloc() - Allocate and init a file's LSM blob
* @file: the file
*
* Allocate and attach a security structure to the file->f_security field. The
* security field is initialized to NULL when the structure is first created.
*
* Return: Return 0 if the hook is successful and permission is granted.
*/
int security_file_alloc(struct file *file)
{ int rc = lsm_file_alloc(file);
if (rc)
return rc;
rc = call_int_hook(file_alloc_security, file); if (unlikely(rc))
security_file_free(file);
return rc;
}
/**
* security_file_release() - Perform actions before releasing the file ref
* @file: the file
*
* Perform actions before releasing the last reference to a file.
*/
void security_file_release(struct file *file)
{ call_void_hook(file_release, file);
}
/**
* security_file_free() - Free a file's LSM blob
* @file: the file
*
* Deallocate and free any security structures stored in file->f_security.
*/
void security_file_free(struct file *file)
{
void *blob;
call_void_hook(file_free_security, file);
blob = file->f_security;
if (blob) { file->f_security = NULL;
kmem_cache_free(lsm_file_cache, blob);
}
}
/**
* security_file_ioctl() - Check if an ioctl is allowed
* @file: associated file
* @cmd: ioctl cmd
* @arg: ioctl arguments
*
* Check permission for an ioctl operation on @file. Note that @arg sometimes
* represents a user space pointer; in other cases, it may be a simple integer
* value. When @arg represents a user space pointer, it should never be used
* by the security module.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{ return call_int_hook(file_ioctl, file, cmd, arg);
}
EXPORT_SYMBOL_GPL(security_file_ioctl);
/**
* security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode
* @file: associated file
* @cmd: ioctl cmd
* @arg: ioctl arguments
*
* Compat version of security_file_ioctl() that correctly handles 32-bit
* processes running on 64-bit kernels.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_ioctl_compat(struct file *file, unsigned int cmd,
unsigned long arg)
{
return call_int_hook(file_ioctl_compat, file, cmd, arg);
}
EXPORT_SYMBOL_GPL(security_file_ioctl_compat);
static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
{
/*
* Does we have PROT_READ and does the application expect
* it to imply PROT_EXEC? If not, nothing to talk about...
*/
if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ)
return prot;
if (!(current->personality & READ_IMPLIES_EXEC))
return prot;
/*
* if that's an anonymous mapping, let it.
*/
if (!file)
return prot | PROT_EXEC;
/*
* ditto if it's not on noexec mount, except that on !MMU we need
* NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case
*/
if (!path_noexec(&file->f_path)) {
#ifndef CONFIG_MMU
if (file->f_op->mmap_capabilities) {
unsigned caps = file->f_op->mmap_capabilities(file);
if (!(caps & NOMMU_MAP_EXEC))
return prot;
}
#endif
return prot | PROT_EXEC;
}
/* anything on noexec mount won't get PROT_EXEC */
return prot;
}
/**
* security_mmap_file() - Check if mmap'ing a file is allowed
* @file: file
* @prot: protection applied by the kernel
* @flags: flags
*
* Check permissions for a mmap operation. The @file may be NULL, e.g. if
* mapping anonymous memory.
*
* Return: Returns 0 if permission is granted.
*/
int security_mmap_file(struct file *file, unsigned long prot,
unsigned long flags)
{ return call_int_hook(mmap_file, file, prot, mmap_prot(file, prot),
flags);
}
/**
* security_mmap_addr() - Check if mmap'ing an address is allowed
* @addr: address
*
* Check permissions for a mmap operation at @addr.
*
* Return: Returns 0 if permission is granted.
*/
int security_mmap_addr(unsigned long addr)
{ return call_int_hook(mmap_addr, addr);
}
/**
* security_file_mprotect() - Check if changing memory protections is allowed
* @vma: memory region
* @reqprot: application requested protection
* @prot: protection applied by the kernel
*
* Check permissions before changing memory access permissions.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
unsigned long prot)
{
return call_int_hook(file_mprotect, vma, reqprot, prot);
}
/**
* security_file_lock() - Check if a file lock is allowed
* @file: file
* @cmd: lock operation (e.g. F_RDLCK, F_WRLCK)
*
* Check permission before performing file locking operations. Note the hook
* mediates both flock and fcntl style locks.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_lock(struct file *file, unsigned int cmd)
{
return call_int_hook(file_lock, file, cmd);
}
/**
* security_file_fcntl() - Check if fcntl() op is allowed
* @file: file
* @cmd: fcntl command
* @arg: command argument
*
* Check permission before allowing the file operation specified by @cmd from
* being performed on the file @file. Note that @arg sometimes represents a
* user space pointer; in other cases, it may be a simple integer value. When
* @arg represents a user space pointer, it should never be used by the
* security module.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
{
return call_int_hook(file_fcntl, file, cmd, arg);
}
/**
* security_file_set_fowner() - Set the file owner info in the LSM blob
* @file: the file
*
* Save owner security information (typically from current->security) in
* file->f_security for later use by the send_sigiotask hook.
*
* This hook is called with file->f_owner.lock held.
*
* Return: Returns 0 on success.
*/
void security_file_set_fowner(struct file *file)
{
call_void_hook(file_set_fowner, file);
}
/**
* security_file_send_sigiotask() - Check if sending SIGIO/SIGURG is allowed
* @tsk: target task
* @fown: signal sender
* @sig: signal to be sent, SIGIO is sent if 0
*
* Check permission for the file owner @fown to send SIGIO or SIGURG to the
* process @tsk. Note that this hook is sometimes called from interrupt. Note
* that the fown_struct, @fown, is never outside the context of a struct file,
* so the file structure (and associated security information) can always be
* obtained: container_of(fown, struct file, f_owner).
*
* Return: Returns 0 if permission is granted.
*/
int security_file_send_sigiotask(struct task_struct *tsk,
struct fown_struct *fown, int sig)
{
return call_int_hook(file_send_sigiotask, tsk, fown, sig);
}
/**
* security_file_receive() - Check if receiving a file via IPC is allowed
* @file: file being received
*
* This hook allows security modules to control the ability of a process to
* receive an open file descriptor via socket IPC.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_receive(struct file *file)
{
return call_int_hook(file_receive, file);
}
/**
* security_file_open() - Save open() time state for late use by the LSM
* @file:
*
* Save open-time permission checking state for later use upon file_permission,
* and recheck access if anything has changed since inode_permission.
*
* We can check if a file is opened for execution (e.g. execve(2) call), either
* directly or indirectly (e.g. ELF's ld.so) by checking file->f_flags &
* __FMODE_EXEC .
*
* Return: Returns 0 if permission is granted.
*/
int security_file_open(struct file *file)
{ return call_int_hook(file_open, file);
}
/**
* security_file_post_open() - Evaluate a file after it has been opened
* @file: the file
* @mask: access mask
*
* Evaluate an opened file and the access mask requested with open(). The hook
* is useful for LSMs that require the file content to be available in order to
* make decisions.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_post_open(struct file *file, int mask)
{ return call_int_hook(file_post_open, file, mask);
}
EXPORT_SYMBOL_GPL(security_file_post_open);
/**
* security_file_truncate() - Check if truncating a file is allowed
* @file: file
*
* Check permission before truncating a file, i.e. using ftruncate. Note that
* truncation permission may also be checked based on the path, using the
* @path_truncate hook.
*
* Return: Returns 0 if permission is granted.
*/
int security_file_truncate(struct file *file)
{ return call_int_hook(file_truncate, file);
}
/**
* security_task_alloc() - Allocate a task's LSM blob
* @task: the task
* @clone_flags: flags indicating what is being shared
*
* Handle allocation of task-related resources.
*
* Return: Returns a zero on success, negative values on failure.
*/
int security_task_alloc(struct task_struct *task, unsigned long clone_flags)
{
int rc = lsm_task_alloc(task);
if (rc)
return rc;
rc = call_int_hook(task_alloc, task, clone_flags);
if (unlikely(rc))
security_task_free(task);
return rc;
}
/**
* security_task_free() - Free a task's LSM blob and related resources
* @task: task
*
* Handle release of task-related resources. Note that this can be called from
* interrupt context.
*/
void security_task_free(struct task_struct *task)
{
call_void_hook(task_free, task);
kfree(task->security);
task->security = NULL;
}
/**
* security_cred_alloc_blank() - Allocate the min memory to allow cred_transfer
* @cred: credentials
* @gfp: gfp flags
*
* Only allocate sufficient memory and attach to @cred such that
* cred_transfer() will not get ENOMEM.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_cred_alloc_blank(struct cred *cred, gfp_t gfp)
{
int rc = lsm_cred_alloc(cred, gfp);
if (rc)
return rc;
rc = call_int_hook(cred_alloc_blank, cred, gfp);
if (unlikely(rc))
security_cred_free(cred);
return rc;
}
/**
* security_cred_free() - Free the cred's LSM blob and associated resources
* @cred: credentials
*
* Deallocate and clear the cred->security field in a set of credentials.
*/
void security_cred_free(struct cred *cred)
{
/*
* There is a failure case in prepare_creds() that
* may result in a call here with ->security being NULL.
*/
if (unlikely(cred->security == NULL))
return;
call_void_hook(cred_free, cred);
kfree(cred->security);
cred->security = NULL;
}
/**
* security_prepare_creds() - Prepare a new set of credentials
* @new: new credentials
* @old: original credentials
* @gfp: gfp flags
*
* Prepare a new set of credentials by copying the data from the old set.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp)
{
int rc = lsm_cred_alloc(new, gfp);
if (rc)
return rc;
rc = call_int_hook(cred_prepare, new, old, gfp);
if (unlikely(rc))
security_cred_free(new);
return rc;
}
/**
* security_transfer_creds() - Transfer creds
* @new: target credentials
* @old: original credentials
*
* Transfer data from original creds to new creds.
*/
void security_transfer_creds(struct cred *new, const struct cred *old)
{
call_void_hook(cred_transfer, new, old);
}
/**
* security_cred_getsecid() - Get the secid from a set of credentials
* @c: credentials
* @secid: secid value
*
* Retrieve the security identifier of the cred structure @c. In case of
* failure, @secid will be set to zero.
*/
void security_cred_getsecid(const struct cred *c, u32 *secid)
{
*secid = 0;
call_void_hook(cred_getsecid, c, secid);
}
EXPORT_SYMBOL(security_cred_getsecid);
/**
* security_cred_getlsmprop() - Get the LSM data from a set of credentials
* @c: credentials
* @prop: destination for the LSM data
*
* Retrieve the security data of the cred structure @c. In case of
* failure, @prop will be cleared.
*/
void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop)
{
lsmprop_init(prop);
call_void_hook(cred_getlsmprop, c, prop);
}
EXPORT_SYMBOL(security_cred_getlsmprop);
/**
* security_kernel_act_as() - Set the kernel credentials to act as secid
* @new: credentials
* @secid: secid
*
* Set the credentials for a kernel service to act as (subjective context).
* The current task must be the one that nominated @secid.
*
* Return: Returns 0 if successful.
*/
int security_kernel_act_as(struct cred *new, u32 secid)
{
return call_int_hook(kernel_act_as, new, secid);
}
/**
* security_kernel_create_files_as() - Set file creation context using an inode
* @new: target credentials
* @inode: reference inode
*
* Set the file creation context in a set of credentials to be the same as the
* objective context of the specified inode. The current task must be the one
* that nominated @inode.
*
* Return: Returns 0 if successful.
*/
int security_kernel_create_files_as(struct cred *new, struct inode *inode)
{
return call_int_hook(kernel_create_files_as, new, inode);
}
/**
* security_kernel_module_request() - Check if loading a module is allowed
* @kmod_name: module name
*
* Ability to trigger the kernel to automatically upcall to userspace for
* userspace to load a kernel module with the given name.
*
* Return: Returns 0 if successful.
*/
int security_kernel_module_request(char *kmod_name)
{
return call_int_hook(kernel_module_request, kmod_name);
}
/**
* security_kernel_read_file() - Read a file specified by userspace
* @file: file
* @id: file identifier
* @contents: trust if security_kernel_post_read_file() will be called
*
* Read a file specified by userspace.
*
* Return: Returns 0 if permission is granted.
*/
int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
bool contents)
{
return call_int_hook(kernel_read_file, file, id, contents);
}
EXPORT_SYMBOL_GPL(security_kernel_read_file);
/**
* security_kernel_post_read_file() - Read a file specified by userspace
* @file: file
* @buf: file contents
* @size: size of file contents
* @id: file identifier
*
* Read a file specified by userspace. This must be paired with a prior call
* to security_kernel_read_file() call that indicated this hook would also be
* called, see security_kernel_read_file() for more information.
*
* Return: Returns 0 if permission is granted.
*/
int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
enum kernel_read_file_id id)
{
return call_int_hook(kernel_post_read_file, file, buf, size, id);
}
EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
/**
* security_kernel_load_data() - Load data provided by userspace
* @id: data identifier
* @contents: true if security_kernel_post_load_data() will be called
*
* Load data provided by userspace.
*
* Return: Returns 0 if permission is granted.
*/
int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
{
return call_int_hook(kernel_load_data, id, contents);
}
EXPORT_SYMBOL_GPL(security_kernel_load_data);
/**
* security_kernel_post_load_data() - Load userspace data from a non-file source
* @buf: data
* @size: size of data
* @id: data identifier
* @description: text description of data, specific to the id value
*
* Load data provided by a non-file source (usually userspace buffer). This
* must be paired with a prior security_kernel_load_data() call that indicated
* this hook would also be called, see security_kernel_load_data() for more
* information.
*
* Return: Returns 0 if permission is granted.
*/
int security_kernel_post_load_data(char *buf, loff_t size,
enum kernel_load_data_id id,
char *description)
{
return call_int_hook(kernel_post_load_data, buf, size, id, description);
}
EXPORT_SYMBOL_GPL(security_kernel_post_load_data);
/**
* security_task_fix_setuid() - Update LSM with new user id attributes
* @new: updated credentials
* @old: credentials being replaced
* @flags: LSM_SETID_* flag values
*
* Update the module's state after setting one or more of the user identity
* attributes of the current process. The @flags parameter indicates which of
* the set*uid system calls invoked this hook. If @new is the set of
* credentials that will be installed. Modifications should be made to this
* rather than to @current->cred.
*
* Return: Returns 0 on success.
*/
int security_task_fix_setuid(struct cred *new, const struct cred *old,
int flags)
{
return call_int_hook(task_fix_setuid, new, old, flags);
}
/**
* security_task_fix_setgid() - Update LSM with new group id attributes
* @new: updated credentials
* @old: credentials being replaced
* @flags: LSM_SETID_* flag value
*
* Update the module's state after setting one or more of the group identity
* attributes of the current process. The @flags parameter indicates which of
* the set*gid system calls invoked this hook. @new is the set of credentials
* that will be installed. Modifications should be made to this rather than to
* @current->cred.
*
* Return: Returns 0 on success.
*/
int security_task_fix_setgid(struct cred *new, const struct cred *old,
int flags)
{
return call_int_hook(task_fix_setgid, new, old, flags);
}
/**
* security_task_fix_setgroups() - Update LSM with new supplementary groups
* @new: updated credentials
* @old: credentials being replaced
*
* Update the module's state after setting the supplementary group identity
* attributes of the current process. @new is the set of credentials that will
* be installed. Modifications should be made to this rather than to
* @current->cred.
*
* Return: Returns 0 on success.
*/
int security_task_fix_setgroups(struct cred *new, const struct cred *old)
{
return call_int_hook(task_fix_setgroups, new, old);
}
/**
* security_task_setpgid() - Check if setting the pgid is allowed
* @p: task being modified
* @pgid: new pgid
*
* Check permission before setting the process group identifier of the process
* @p to @pgid.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_setpgid(struct task_struct *p, pid_t pgid)
{
return call_int_hook(task_setpgid, p, pgid);
}
/**
* security_task_getpgid() - Check if getting the pgid is allowed
* @p: task
*
* Check permission before getting the process group identifier of the process
* @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_getpgid(struct task_struct *p)
{
return call_int_hook(task_getpgid, p);
}
/**
* security_task_getsid() - Check if getting the session id is allowed
* @p: task
*
* Check permission before getting the session identifier of the process @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_getsid(struct task_struct *p)
{
return call_int_hook(task_getsid, p);
}
/**
* security_current_getlsmprop_subj() - Current task's subjective LSM data
* @prop: lsm specific information
*
* Retrieve the subjective security identifier of the current task and return
* it in @prop.
*/
void security_current_getlsmprop_subj(struct lsm_prop *prop)
{
lsmprop_init(prop);
call_void_hook(current_getlsmprop_subj, prop);
}
EXPORT_SYMBOL(security_current_getlsmprop_subj);
/**
* security_task_getlsmprop_obj() - Get a task's objective LSM data
* @p: target task
* @prop: lsm specific information
*
* Retrieve the objective security identifier of the task_struct in @p and
* return it in @prop.
*/
void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop)
{
lsmprop_init(prop);
call_void_hook(task_getlsmprop_obj, p, prop);
}
EXPORT_SYMBOL(security_task_getlsmprop_obj);
/**
* security_task_setnice() - Check if setting a task's nice value is allowed
* @p: target task
* @nice: nice value
*
* Check permission before setting the nice value of @p to @nice.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_setnice(struct task_struct *p, int nice)
{
return call_int_hook(task_setnice, p, nice);
}
/**
* security_task_setioprio() - Check if setting a task's ioprio is allowed
* @p: target task
* @ioprio: ioprio value
*
* Check permission before setting the ioprio value of @p to @ioprio.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_setioprio(struct task_struct *p, int ioprio)
{
return call_int_hook(task_setioprio, p, ioprio);
}
/**
* security_task_getioprio() - Check if getting a task's ioprio is allowed
* @p: task
*
* Check permission before getting the ioprio value of @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_getioprio(struct task_struct *p)
{
return call_int_hook(task_getioprio, p);
}
/**
* security_task_prlimit() - Check if get/setting resources limits is allowed
* @cred: current task credentials
* @tcred: target task credentials
* @flags: LSM_PRLIMIT_* flag bits indicating a get/set/both
*
* Check permission before getting and/or setting the resource limits of
* another task.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_prlimit(const struct cred *cred, const struct cred *tcred,
unsigned int flags)
{
return call_int_hook(task_prlimit, cred, tcred, flags);
}
/**
* security_task_setrlimit() - Check if setting a new rlimit value is allowed
* @p: target task's group leader
* @resource: resource whose limit is being set
* @new_rlim: new resource limit
*
* Check permission before setting the resource limits of process @p for
* @resource to @new_rlim. The old resource limit values can be examined by
* dereferencing (p->signal->rlim + resource).
*
* Return: Returns 0 if permission is granted.
*/
int security_task_setrlimit(struct task_struct *p, unsigned int resource,
struct rlimit *new_rlim)
{
return call_int_hook(task_setrlimit, p, resource, new_rlim);
}
/**
* security_task_setscheduler() - Check if setting sched policy/param is allowed
* @p: target task
*
* Check permission before setting scheduling policy and/or parameters of
* process @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_setscheduler(struct task_struct *p)
{
return call_int_hook(task_setscheduler, p);
}
/**
* security_task_getscheduler() - Check if getting scheduling info is allowed
* @p: target task
*
* Check permission before obtaining scheduling information for process @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_getscheduler(struct task_struct *p)
{
return call_int_hook(task_getscheduler, p);
}
/**
* security_task_movememory() - Check if moving memory is allowed
* @p: task
*
* Check permission before moving memory owned by process @p.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_movememory(struct task_struct *p)
{
return call_int_hook(task_movememory, p);
}
/**
* security_task_kill() - Check if sending a signal is allowed
* @p: target process
* @info: signal information
* @sig: signal value
* @cred: credentials of the signal sender, NULL if @current
*
* Check permission before sending signal @sig to @p. @info can be NULL, the
* constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or
* SI_FROMKERNEL(info) is true, then the signal should be viewed as coming from
* the kernel and should typically be permitted. SIGIO signals are handled
* separately by the send_sigiotask hook in file_security_ops.
*
* Return: Returns 0 if permission is granted.
*/
int security_task_kill(struct task_struct *p, struct kernel_siginfo *info,
int sig, const struct cred *cred)
{
return call_int_hook(task_kill, p, info, sig, cred);
}
/**
* security_task_prctl() - Check if a prctl op is allowed
* @option: operation
* @arg2: argument
* @arg3: argument
* @arg4: argument
* @arg5: argument
*
* Check permission before performing a process control operation on the
* current process.
*
* Return: Return -ENOSYS if no-one wanted to handle this op, any other value
* to cause prctl() to return immediately with that value.
*/
int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
int thisrc;
int rc = LSM_RET_DEFAULT(task_prctl);
struct lsm_static_call *scall;
lsm_for_each_hook(scall, task_prctl) {
thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5);
if (thisrc != LSM_RET_DEFAULT(task_prctl)) {
rc = thisrc;
if (thisrc != 0)
break;
}
}
return rc;
}
/**
* security_task_to_inode() - Set the security attributes of a task's inode
* @p: task
* @inode: inode
*
* Set the security attributes for an inode based on an associated task's
* security attributes, e.g. for /proc/pid inodes.
*/
void security_task_to_inode(struct task_struct *p, struct inode *inode)
{
call_void_hook(task_to_inode, p, inode);
}
/**
* security_create_user_ns() - Check if creating a new userns is allowed
* @cred: prepared creds
*
* Check permission prior to creating a new user namespace.
*
* Return: Returns 0 if successful, otherwise < 0 error code.
*/
int security_create_user_ns(const struct cred *cred)
{
return call_int_hook(userns_create, cred);
}
/**
* security_ipc_permission() - Check if sysv ipc access is allowed
* @ipcp: ipc permission structure
* @flag: requested permissions
*
* Check permissions for access to IPC.
*
* Return: Returns 0 if permission is granted.
*/
int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag)
{
return call_int_hook(ipc_permission, ipcp, flag);
}
/**
* security_ipc_getlsmprop() - Get the sysv ipc object LSM data
* @ipcp: ipc permission structure
* @prop: pointer to lsm information
*
* Get the lsm information associated with the ipc object.
*/
void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop)
{
lsmprop_init(prop);
call_void_hook(ipc_getlsmprop, ipcp, prop);
}
/**
* security_msg_msg_alloc() - Allocate a sysv ipc message LSM blob
* @msg: message structure
*
* Allocate and attach a security structure to the msg->security field. The
* security field is initialized to NULL when the structure is first created.
*
* Return: Return 0 if operation was successful and permission is granted.
*/
int security_msg_msg_alloc(struct msg_msg *msg)
{
int rc = lsm_msg_msg_alloc(msg);
if (unlikely(rc))
return rc;
rc = call_int_hook(msg_msg_alloc_security, msg);
if (unlikely(rc))
security_msg_msg_free(msg);
return rc;
}
/**
* security_msg_msg_free() - Free a sysv ipc message LSM blob
* @msg: message structure
*
* Deallocate the security structure for this message.
*/
void security_msg_msg_free(struct msg_msg *msg)
{
call_void_hook(msg_msg_free_security, msg);
kfree(msg->security);
msg->security = NULL;
}
/**
* security_msg_queue_alloc() - Allocate a sysv ipc msg queue LSM blob
* @msq: sysv ipc permission structure
*
* Allocate and attach a security structure to @msg. The security field is
* initialized to NULL when the structure is first created.
*
* Return: Returns 0 if operation was successful and permission is granted.
*/
int security_msg_queue_alloc(struct kern_ipc_perm *msq)
{
int rc = lsm_ipc_alloc(msq);
if (unlikely(rc))
return rc;
rc = call_int_hook(msg_queue_alloc_security, msq);
if (unlikely(rc))
security_msg_queue_free(msq);
return rc;
}
/**
* security_msg_queue_free() - Free a sysv ipc msg queue LSM blob
* @msq: sysv ipc permission structure
*
* Deallocate security field @perm->security for the message queue.
*/
void security_msg_queue_free(struct kern_ipc_perm *msq)
{
call_void_hook(msg_queue_free_security, msq);
kfree(msq->security);
msq->security = NULL;
}
/**
* security_msg_queue_associate() - Check if a msg queue operation is allowed
* @msq: sysv ipc permission structure
* @msqflg: operation flags
*
* Check permission when a message queue is requested through the msgget system
* call. This hook is only called when returning the message queue identifier
* for an existing message queue, not when a new message queue is created.
*
* Return: Return 0 if permission is granted.
*/
int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg)
{
return call_int_hook(msg_queue_associate, msq, msqflg);
}
/**
* security_msg_queue_msgctl() - Check if a msg queue operation is allowed
* @msq: sysv ipc permission structure
* @cmd: operation
*
* Check permission when a message control operation specified by @cmd is to be
* performed on the message queue with permissions.
*
* Return: Returns 0 if permission is granted.
*/
int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd)
{
return call_int_hook(msg_queue_msgctl, msq, cmd);
}
/**
* security_msg_queue_msgsnd() - Check if sending a sysv ipc message is allowed
* @msq: sysv ipc permission structure
* @msg: message
* @msqflg: operation flags
*
* Check permission before a message, @msg, is enqueued on the message queue
* with permissions specified in @msq.
*
* Return: Returns 0 if permission is granted.
*/
int security_msg_queue_msgsnd(struct kern_ipc_perm *msq,
struct msg_msg *msg, int msqflg)
{
return call_int_hook(msg_queue_msgsnd, msq, msg, msqflg);
}
/**
* security_msg_queue_msgrcv() - Check if receiving a sysv ipc msg is allowed
* @msq: sysv ipc permission structure
* @msg: message
* @target: target task
* @type: type of message requested
* @mode: operation flags
*
* Check permission before a message, @msg, is removed from the message queue.
* The @target task structure contains a pointer to the process that will be
* receiving the message (not equal to the current process when inline receives
* are being performed).
*
* Return: Returns 0 if permission is granted.
*/
int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg,
struct task_struct *target, long type, int mode)
{
return call_int_hook(msg_queue_msgrcv, msq, msg, target, type, mode);
}
/**
* security_shm_alloc() - Allocate a sysv shm LSM blob
* @shp: sysv ipc permission structure
*
* Allocate and attach a security structure to the @shp security field. The
* security field is initialized to NULL when the structure is first created.
*
* Return: Returns 0 if operation was successful and permission is granted.
*/
int security_shm_alloc(struct kern_ipc_perm *shp)
{
int rc = lsm_ipc_alloc(shp);
if (unlikely(rc))
return rc;
rc = call_int_hook(shm_alloc_security, shp);
if (unlikely(rc))
security_shm_free(shp);
return rc;
}
/**
* security_shm_free() - Free a sysv shm LSM blob
* @shp: sysv ipc permission structure
*
* Deallocate the security structure @perm->security for the memory segment.
*/
void security_shm_free(struct kern_ipc_perm *shp)
{
call_void_hook(shm_free_security, shp);
kfree(shp->security);
shp->security = NULL;
}
/**
* security_shm_associate() - Check if a sysv shm operation is allowed
* @shp: sysv ipc permission structure
* @shmflg: operation flags
*
* Check permission when a shared memory region is requested through the shmget
* system call. This hook is only called when returning the shared memory
* region identifier for an existing region, not when a new shared memory
* region is created.
*
* Return: Returns 0 if permission is granted.
*/
int security_shm_associate(struct kern_ipc_perm *shp, int shmflg)
{
return call_int_hook(shm_associate, shp, shmflg);
}
/**
* security_shm_shmctl() - Check if a sysv shm operation is allowed
* @shp: sysv ipc permission structure
* @cmd: operation
*
* Check permission when a shared memory control operation specified by @cmd is
* to be performed on the shared memory region with permissions in @shp.
*
* Return: Return 0 if permission is granted.
*/
int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd)
{
return call_int_hook(shm_shmctl, shp, cmd);
}
/**
* security_shm_shmat() - Check if a sysv shm attach operation is allowed
* @shp: sysv ipc permission structure
* @shmaddr: address of memory region to attach
* @shmflg: operation flags
*
* Check permissions prior to allowing the shmat system call to attach the
* shared memory segment with permissions @shp to the data segment of the
* calling process. The attaching address is specified by @shmaddr.
*
* Return: Returns 0 if permission is granted.
*/
int security_shm_shmat(struct kern_ipc_perm *shp,
char __user *shmaddr, int shmflg)
{
return call_int_hook(shm_shmat, shp, shmaddr, shmflg);
}
/**
* security_sem_alloc() - Allocate a sysv semaphore LSM blob
* @sma: sysv ipc permission structure
*
* Allocate and attach a security structure to the @sma security field. The
* security field is initialized to NULL when the structure is first created.
*
* Return: Returns 0 if operation was successful and permission is granted.
*/
int security_sem_alloc(struct kern_ipc_perm *sma)
{
int rc = lsm_ipc_alloc(sma);
if (unlikely(rc))
return rc;
rc = call_int_hook(sem_alloc_security, sma);
if (unlikely(rc))
security_sem_free(sma);
return rc;
}
/**
* security_sem_free() - Free a sysv semaphore LSM blob
* @sma: sysv ipc permission structure
*
* Deallocate security structure @sma->security for the semaphore.
*/
void security_sem_free(struct kern_ipc_perm *sma)
{
call_void_hook(sem_free_security, sma);
kfree(sma->security);
sma->security = NULL;
}
/**
* security_sem_associate() - Check if a sysv semaphore operation is allowed
* @sma: sysv ipc permission structure
* @semflg: operation flags
*
* Check permission when a semaphore is requested through the semget system
* call. This hook is only called when returning the semaphore identifier for
* an existing semaphore, not when a new one must be created.
*
* Return: Returns 0 if permission is granted.
*/
int security_sem_associate(struct kern_ipc_perm *sma, int semflg)
{
return call_int_hook(sem_associate, sma, semflg);
}
/**
* security_sem_semctl() - Check if a sysv semaphore operation is allowed
* @sma: sysv ipc permission structure
* @cmd: operation
*
* Check permission when a semaphore operation specified by @cmd is to be
* performed on the semaphore.
*
* Return: Returns 0 if permission is granted.
*/
int security_sem_semctl(struct kern_ipc_perm *sma, int cmd)
{
return call_int_hook(sem_semctl, sma, cmd);
}
/**
* security_sem_semop() - Check if a sysv semaphore operation is allowed
* @sma: sysv ipc permission structure
* @sops: operations to perform
* @nsops: number of operations
* @alter: flag indicating changes will be made
*
* Check permissions before performing operations on members of the semaphore
* set. If the @alter flag is nonzero, the semaphore set may be modified.
*
* Return: Returns 0 if permission is granted.
*/
int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops,
unsigned nsops, int alter)
{
return call_int_hook(sem_semop, sma, sops, nsops, alter);
}
/**
* security_d_instantiate() - Populate an inode's LSM state based on a dentry
* @dentry: dentry
* @inode: inode
*
* Fill in @inode security information for a @dentry if allowed.
*/
void security_d_instantiate(struct dentry *dentry, struct inode *inode)
{ if (unlikely(inode && IS_PRIVATE(inode)))
return;
call_void_hook(d_instantiate, dentry, inode);
}
EXPORT_SYMBOL(security_d_instantiate);
/*
* Please keep this in sync with it's counterpart in security/lsm_syscalls.c
*/
/**
* security_getselfattr - Read an LSM attribute of the current process.
* @attr: which attribute to return
* @uctx: the user-space destination for the information, or NULL
* @size: pointer to the size of space available to receive the data
* @flags: special handling options. LSM_FLAG_SINGLE indicates that only
* attributes associated with the LSM identified in the passed @ctx be
* reported.
*
* A NULL value for @uctx can be used to get both the number of attributes
* and the size of the data.
*
* Returns the number of attributes found on success, negative value
* on error. @size is reset to the total size of the data.
* If @size is insufficient to contain the data -E2BIG is returned.
*/
int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
u32 __user *size, u32 flags)
{
struct lsm_static_call *scall;
struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, };
u8 __user *base = (u8 __user *)uctx;
u32 entrysize;
u32 total = 0;
u32 left;
bool toobig = false;
bool single = false;
int count = 0;
int rc;
if (attr == LSM_ATTR_UNDEF)
return -EINVAL;
if (size == NULL)
return -EINVAL;
if (get_user(left, size))
return -EFAULT;
if (flags) {
/*
* Only flag supported is LSM_FLAG_SINGLE
*/
if (flags != LSM_FLAG_SINGLE || !uctx)
return -EINVAL;
if (copy_from_user(&lctx, uctx, sizeof(lctx)))
return -EFAULT;
/*
* If the LSM ID isn't specified it is an error.
*/
if (lctx.id == LSM_ID_UNDEF)
return -EINVAL;
single = true;
}
/*
* In the usual case gather all the data from the LSMs.
* In the single case only get the data from the LSM specified.
*/
lsm_for_each_hook(scall, getselfattr) {
if (single && lctx.id != scall->hl->lsmid->id)
continue;
entrysize = left;
if (base)
uctx = (struct lsm_ctx __user *)(base + total);
rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags);
if (rc == -EOPNOTSUPP)
continue;
if (rc == -E2BIG) {
rc = 0;
left = 0;
toobig = true;
} else if (rc < 0)
return rc;
else
left -= entrysize;
total += entrysize;
count += rc;
if (single)
break;
}
if (put_user(total, size))
return -EFAULT;
if (toobig)
return -E2BIG;
if (count == 0)
return LSM_RET_DEFAULT(getselfattr);
return count;
}
/*
* Please keep this in sync with it's counterpart in security/lsm_syscalls.c
*/
/**
* security_setselfattr - Set an LSM attribute on the current process.
* @attr: which attribute to set
* @uctx: the user-space source for the information
* @size: the size of the data
* @flags: reserved for future use, must be 0
*
* Set an LSM attribute for the current process. The LSM, attribute
* and new value are included in @uctx.
*
* Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT
* if the user buffer is inaccessible, E2BIG if size is too big, or an
* LSM specific failure.
*/
int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
u32 size, u32 flags)
{
struct lsm_static_call *scall;
struct lsm_ctx *lctx;
int rc = LSM_RET_DEFAULT(setselfattr);
u64 required_len;
if (flags)
return -EINVAL;
if (size < sizeof(*lctx))
return -EINVAL;
if (size > PAGE_SIZE)
return -E2BIG;
lctx = memdup_user(uctx, size);
if (IS_ERR(lctx))
return PTR_ERR(lctx);
if (size < lctx->len ||
check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) ||
lctx->len < required_len) {
rc = -EINVAL;
goto free_out;
}
lsm_for_each_hook(scall, setselfattr)
if ((scall->hl->lsmid->id) == lctx->id) {
rc = scall->hl->hook.setselfattr(attr, lctx, size, flags);
break;
}
free_out:
kfree(lctx);
return rc;
}
/**
* security_getprocattr() - Read an attribute for a task
* @p: the task
* @lsmid: LSM identification
* @name: attribute name
* @value: attribute value
*
* Read attribute @name for task @p and store it into @value if allowed.
*
* Return: Returns the length of @value on success, a negative value otherwise.
*/
int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
char **value)
{
struct lsm_static_call *scall;
lsm_for_each_hook(scall, getprocattr) {
if (lsmid != 0 && lsmid != scall->hl->lsmid->id)
continue;
return scall->hl->hook.getprocattr(p, name, value);
}
return LSM_RET_DEFAULT(getprocattr);
}
/**
* security_setprocattr() - Set an attribute for a task
* @lsmid: LSM identification
* @name: attribute name
* @value: attribute value
* @size: attribute value size
*
* Write (set) the current task's attribute @name to @value, size @size if
* allowed.
*
* Return: Returns bytes written on success, a negative value otherwise.
*/
int security_setprocattr(int lsmid, const char *name, void *value, size_t size)
{
struct lsm_static_call *scall;
lsm_for_each_hook(scall, setprocattr) {
if (lsmid != 0 && lsmid != scall->hl->lsmid->id)
continue;
return scall->hl->hook.setprocattr(name, value, size);
}
return LSM_RET_DEFAULT(setprocattr);
}
/**
* security_netlink_send() - Save info and check if netlink sending is allowed
* @sk: sending socket
* @skb: netlink message
*
* Save security information for a netlink message so that permission checking
* can be performed when the message is processed. The security information
* can be saved using the eff_cap field of the netlink_skb_parms structure.
* Also may be used to provide fine grained control over message transmission.
*
* Return: Returns 0 if the information was successfully saved and message is
* allowed to be transmitted.
*/
int security_netlink_send(struct sock *sk, struct sk_buff *skb)
{
return call_int_hook(netlink_send, sk, skb);
}
/**
* security_ismaclabel() - Check if the named attribute is a MAC label
* @name: full extended attribute name
*
* Check if the extended attribute specified by @name represents a MAC label.
*
* Return: Returns 1 if name is a MAC attribute otherwise returns 0.
*/
int security_ismaclabel(const char *name)
{
return call_int_hook(ismaclabel, name);
}
EXPORT_SYMBOL(security_ismaclabel);
/**
* security_secid_to_secctx() - Convert a secid to a secctx
* @secid: secid
* @cp: the LSM context
*
* Convert secid to security context. If @cp is NULL the length of the
* result will be returned, but no data will be returned. This
* does mean that the length could change between calls to check the length and
* the next call which actually allocates and returns the data.
*
* Return: Return length of data on success, error on failure.
*/
int security_secid_to_secctx(u32 secid, struct lsm_context *cp)
{
return call_int_hook(secid_to_secctx, secid, cp);
}
EXPORT_SYMBOL(security_secid_to_secctx);
/**
* security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx
* @prop: lsm specific information
* @cp: the LSM context
*
* Convert a @prop entry to security context. If @cp is NULL the
* length of the result will be returned. This does mean that the
* length could change between calls to check the length and the
* next call which actually allocates and returns the @cp.
*
* Return: Return length of data on success, error on failure.
*/
int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp)
{
return call_int_hook(lsmprop_to_secctx, prop, cp);
}
EXPORT_SYMBOL(security_lsmprop_to_secctx);
/**
* security_secctx_to_secid() - Convert a secctx to a secid
* @secdata: secctx
* @seclen: length of secctx
* @secid: secid
*
* Convert security context to secid.
*
* Return: Returns 0 on success, error on failure.
*/
int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
{
*secid = 0;
return call_int_hook(secctx_to_secid, secdata, seclen, secid);
}
EXPORT_SYMBOL(security_secctx_to_secid);
/**
* security_release_secctx() - Free a secctx buffer
* @cp: the security context
*
* Release the security context.
*/
void security_release_secctx(struct lsm_context *cp)
{
call_void_hook(release_secctx, cp);
memset(cp, 0, sizeof(*cp));
}
EXPORT_SYMBOL(security_release_secctx);
/**
* security_inode_invalidate_secctx() - Invalidate an inode's security label
* @inode: inode
*
* Notify the security module that it must revalidate the security context of
* an inode.
*/
void security_inode_invalidate_secctx(struct inode *inode)
{
call_void_hook(inode_invalidate_secctx, inode);
}
EXPORT_SYMBOL(security_inode_invalidate_secctx);
/**
* security_inode_notifysecctx() - Notify the LSM of an inode's security label
* @inode: inode
* @ctx: secctx
* @ctxlen: length of secctx
*
* Notify the security module of what the security context of an inode should
* be. Initializes the incore security context managed by the security module
* for this inode. Example usage: NFS client invokes this hook to initialize
* the security context in its incore inode to the value provided by the server
* for the file when the server returned the file's attributes to the client.
* Must be called with inode->i_mutex locked.
*
* Return: Returns 0 on success, error on failure.
*/
int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
{
return call_int_hook(inode_notifysecctx, inode, ctx, ctxlen);
}
EXPORT_SYMBOL(security_inode_notifysecctx);
/**
* security_inode_setsecctx() - Change the security label of an inode
* @dentry: inode
* @ctx: secctx
* @ctxlen: length of secctx
*
* Change the security context of an inode. Updates the incore security
* context managed by the security module and invokes the fs code as needed
* (via __vfs_setxattr_noperm) to update any backing xattrs that represent the
* context. Example usage: NFS server invokes this hook to change the security
* context in its incore inode and on the backing filesystem to a value
* provided by the client on a SETATTR operation. Must be called with
* inode->i_mutex locked.
*
* Return: Returns 0 on success, error on failure.
*/
int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
{
return call_int_hook(inode_setsecctx, dentry, ctx, ctxlen);
}
EXPORT_SYMBOL(security_inode_setsecctx);
/**
* security_inode_getsecctx() - Get the security label of an inode
* @inode: inode
* @cp: security context
*
* On success, returns 0 and fills out @cp with the security context
* for the given @inode.
*
* Return: Returns 0 on success, error on failure.
*/
int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp)
{
memset(cp, 0, sizeof(*cp));
return call_int_hook(inode_getsecctx, inode, cp);
}
EXPORT_SYMBOL(security_inode_getsecctx);
#ifdef CONFIG_WATCH_QUEUE
/**
* security_post_notification() - Check if a watch notification can be posted
* @w_cred: credentials of the task that set the watch
* @cred: credentials of the task which triggered the watch
* @n: the notification
*
* Check to see if a watch notification can be posted to a particular queue.
*
* Return: Returns 0 if permission is granted.
*/
int security_post_notification(const struct cred *w_cred,
const struct cred *cred,
struct watch_notification *n)
{
return call_int_hook(post_notification, w_cred, cred, n);
}
#endif /* CONFIG_WATCH_QUEUE */
#ifdef CONFIG_KEY_NOTIFICATIONS
/**
* security_watch_key() - Check if a task is allowed to watch for key events
* @key: the key to watch
*
* Check to see if a process is allowed to watch for event notifications from
* a key or keyring.
*
* Return: Returns 0 if permission is granted.
*/
int security_watch_key(struct key *key)
{
return call_int_hook(watch_key, key);
}
#endif /* CONFIG_KEY_NOTIFICATIONS */
#ifdef CONFIG_SECURITY_NETWORK
/**
* security_unix_stream_connect() - Check if a AF_UNIX stream is allowed
* @sock: originating sock
* @other: peer sock
* @newsk: new sock
*
* Check permissions before establishing a Unix domain stream connection
* between @sock and @other.
*
* The @unix_stream_connect and @unix_may_send hooks were necessary because
* Linux provides an alternative to the conventional file name space for Unix
* domain sockets. Whereas binding and connecting to sockets in the file name
* space is mediated by the typical file permissions (and caught by the mknod
* and permission hooks in inode_security_ops), binding and connecting to
* sockets in the abstract name space is completely unmediated. Sufficient
* control of Unix domain sockets in the abstract name space isn't possible
* using only the socket layer hooks, since we need to know the actual target
* socket, which is not looked up until we are inside the af_unix code.
*
* Return: Returns 0 if permission is granted.
*/
int security_unix_stream_connect(struct sock *sock, struct sock *other,
struct sock *newsk)
{
return call_int_hook(unix_stream_connect, sock, other, newsk);
}
EXPORT_SYMBOL(security_unix_stream_connect);
/**
* security_unix_may_send() - Check if AF_UNIX socket can send datagrams
* @sock: originating sock
* @other: peer sock
*
* Check permissions before connecting or sending datagrams from @sock to
* @other.
*
* The @unix_stream_connect and @unix_may_send hooks were necessary because
* Linux provides an alternative to the conventional file name space for Unix
* domain sockets. Whereas binding and connecting to sockets in the file name
* space is mediated by the typical file permissions (and caught by the mknod
* and permission hooks in inode_security_ops), binding and connecting to
* sockets in the abstract name space is completely unmediated. Sufficient
* control of Unix domain sockets in the abstract name space isn't possible
* using only the socket layer hooks, since we need to know the actual target
* socket, which is not looked up until we are inside the af_unix code.
*
* Return: Returns 0 if permission is granted.
*/
int security_unix_may_send(struct socket *sock, struct socket *other)
{
return call_int_hook(unix_may_send, sock, other);
}
EXPORT_SYMBOL(security_unix_may_send);
/**
* security_socket_create() - Check if creating a new socket is allowed
* @family: protocol family
* @type: communications type
* @protocol: requested protocol
* @kern: set to 1 if a kernel socket is requested
*
* Check permissions prior to creating a new socket.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_create(int family, int type, int protocol, int kern)
{
return call_int_hook(socket_create, family, type, protocol, kern);
}
/**
* security_socket_post_create() - Initialize a newly created socket
* @sock: socket
* @family: protocol family
* @type: communications type
* @protocol: requested protocol
* @kern: set to 1 if a kernel socket is requested
*
* This hook allows a module to update or allocate a per-socket security
* structure. Note that the security field was not added directly to the socket
* structure, but rather, the socket security information is stored in the
* associated inode. Typically, the inode alloc_security hook will allocate
* and attach security information to SOCK_INODE(sock)->i_security. This hook
* may be used to update the SOCK_INODE(sock)->i_security field with additional
* information that wasn't available when the inode was allocated.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_post_create(struct socket *sock, int family,
int type, int protocol, int kern)
{
return call_int_hook(socket_post_create, sock, family, type,
protocol, kern);
}
/**
* security_socket_socketpair() - Check if creating a socketpair is allowed
* @socka: first socket
* @sockb: second socket
*
* Check permissions before creating a fresh pair of sockets.
*
* Return: Returns 0 if permission is granted and the connection was
* established.
*/
int security_socket_socketpair(struct socket *socka, struct socket *sockb)
{
return call_int_hook(socket_socketpair, socka, sockb);
}
EXPORT_SYMBOL(security_socket_socketpair);
/**
* security_socket_bind() - Check if a socket bind operation is allowed
* @sock: socket
* @address: requested bind address
* @addrlen: length of address
*
* Check permission before socket protocol layer bind operation is performed
* and the socket @sock is bound to the address specified in the @address
* parameter.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_bind(struct socket *sock,
struct sockaddr *address, int addrlen)
{
return call_int_hook(socket_bind, sock, address, addrlen);
}
/**
* security_socket_connect() - Check if a socket connect operation is allowed
* @sock: socket
* @address: address of remote connection point
* @addrlen: length of address
*
* Check permission before socket protocol layer connect operation attempts to
* connect socket @sock to a remote address, @address.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_connect(struct socket *sock,
struct sockaddr *address, int addrlen)
{
return call_int_hook(socket_connect, sock, address, addrlen);
}
/**
* security_socket_listen() - Check if a socket is allowed to listen
* @sock: socket
* @backlog: connection queue size
*
* Check permission before socket protocol layer listen operation.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_listen(struct socket *sock, int backlog)
{
return call_int_hook(socket_listen, sock, backlog);
}
/**
* security_socket_accept() - Check if a socket is allowed to accept connections
* @sock: listening socket
* @newsock: newly creation connection socket
*
* Check permission before accepting a new connection. Note that the new
* socket, @newsock, has been created and some information copied to it, but
* the accept operation has not actually been performed.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_accept(struct socket *sock, struct socket *newsock)
{
return call_int_hook(socket_accept, sock, newsock);
}
/**
* security_socket_sendmsg() - Check if sending a message is allowed
* @sock: sending socket
* @msg: message to send
* @size: size of message
*
* Check permission before transmitting a message to another socket.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size)
{
return call_int_hook(socket_sendmsg, sock, msg, size);
}
/**
* security_socket_recvmsg() - Check if receiving a message is allowed
* @sock: receiving socket
* @msg: message to receive
* @size: size of message
* @flags: operational flags
*
* Check permission before receiving a message from a socket.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_recvmsg(struct socket *sock, struct msghdr *msg,
int size, int flags)
{
return call_int_hook(socket_recvmsg, sock, msg, size, flags);
}
/**
* security_socket_getsockname() - Check if reading the socket addr is allowed
* @sock: socket
*
* Check permission before reading the local address (name) of the socket
* object.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_getsockname(struct socket *sock)
{
return call_int_hook(socket_getsockname, sock);
}
/**
* security_socket_getpeername() - Check if reading the peer's addr is allowed
* @sock: socket
*
* Check permission before the remote address (name) of a socket object.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_getpeername(struct socket *sock)
{
return call_int_hook(socket_getpeername, sock);
}
/**
* security_socket_getsockopt() - Check if reading a socket option is allowed
* @sock: socket
* @level: option's protocol level
* @optname: option name
*
* Check permissions before retrieving the options associated with socket
* @sock.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_getsockopt(struct socket *sock, int level, int optname)
{
return call_int_hook(socket_getsockopt, sock, level, optname);
}
/**
* security_socket_setsockopt() - Check if setting a socket option is allowed
* @sock: socket
* @level: option's protocol level
* @optname: option name
*
* Check permissions before setting the options associated with socket @sock.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_setsockopt(struct socket *sock, int level, int optname)
{
return call_int_hook(socket_setsockopt, sock, level, optname);
}
/**
* security_socket_shutdown() - Checks if shutting down the socket is allowed
* @sock: socket
* @how: flag indicating how sends and receives are handled
*
* Checks permission before all or part of a connection on the socket @sock is
* shut down.
*
* Return: Returns 0 if permission is granted.
*/
int security_socket_shutdown(struct socket *sock, int how)
{
return call_int_hook(socket_shutdown, sock, how);
}
/**
* security_sock_rcv_skb() - Check if an incoming network packet is allowed
* @sk: destination sock
* @skb: incoming packet
*
* Check permissions on incoming network packets. This hook is distinct from
* Netfilter's IP input hooks since it is the first time that the incoming
* sk_buff @skb has been associated with a particular socket, @sk. Must not
* sleep inside this hook because some callers hold spinlocks.
*
* Return: Returns 0 if permission is granted.
*/
int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
{ return call_int_hook(socket_sock_rcv_skb, sk, skb);
}
EXPORT_SYMBOL(security_sock_rcv_skb);
/**
* security_socket_getpeersec_stream() - Get the remote peer label
* @sock: socket
* @optval: destination buffer
* @optlen: size of peer label copied into the buffer
* @len: maximum size of the destination buffer
*
* This hook allows the security module to provide peer socket security state
* for unix or connected tcp sockets to userspace via getsockopt SO_GETPEERSEC.
* For tcp sockets this can be meaningful if the socket is associated with an
* ipsec SA.
*
* Return: Returns 0 if all is well, otherwise, typical getsockopt return
* values.
*/
int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
sockptr_t optlen, unsigned int len)
{
return call_int_hook(socket_getpeersec_stream, sock, optval, optlen,
len);
}
/**
* security_socket_getpeersec_dgram() - Get the remote peer label
* @sock: socket
* @skb: datagram packet
* @secid: remote peer label secid
*
* This hook allows the security module to provide peer socket security state
* for udp sockets on a per-packet basis to userspace via getsockopt
* SO_GETPEERSEC. The application must first have indicated the IP_PASSSEC
* option via getsockopt. It can then retrieve the security state returned by
* this hook for a packet via the SCM_SECURITY ancillary message type.
*
* Return: Returns 0 on success, error on failure.
*/
int security_socket_getpeersec_dgram(struct socket *sock,
struct sk_buff *skb, u32 *secid)
{
return call_int_hook(socket_getpeersec_dgram, sock, skb, secid);
}
EXPORT_SYMBOL(security_socket_getpeersec_dgram);
/**
* lsm_sock_alloc - allocate a composite sock blob
* @sock: the sock that needs a blob
* @gfp: allocation mode
*
* Allocate the sock blob for all the modules
*
* Returns 0, or -ENOMEM if memory can't be allocated.
*/
static int lsm_sock_alloc(struct sock *sock, gfp_t gfp)
{
return lsm_blob_alloc(&sock->sk_security, blob_sizes.lbs_sock, gfp);
}
/**
* security_sk_alloc() - Allocate and initialize a sock's LSM blob
* @sk: sock
* @family: protocol family
* @priority: gfp flags
*
* Allocate and attach a security structure to the sk->sk_security field, which
* is used to copy security attributes between local stream sockets.
*
* Return: Returns 0 on success, error on failure.
*/
int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
{
int rc = lsm_sock_alloc(sk, priority);
if (unlikely(rc))
return rc;
rc = call_int_hook(sk_alloc_security, sk, family, priority);
if (unlikely(rc))
security_sk_free(sk);
return rc;
}
/**
* security_sk_free() - Free the sock's LSM blob
* @sk: sock
*
* Deallocate security structure.
*/
void security_sk_free(struct sock *sk)
{
call_void_hook(sk_free_security, sk);
kfree(sk->sk_security);
sk->sk_security = NULL;
}
/**
* security_sk_clone() - Clone a sock's LSM state
* @sk: original sock
* @newsk: target sock
*
* Clone/copy security structure.
*/
void security_sk_clone(const struct sock *sk, struct sock *newsk)
{
call_void_hook(sk_clone_security, sk, newsk);
}
EXPORT_SYMBOL(security_sk_clone);
/**
* security_sk_classify_flow() - Set a flow's secid based on socket
* @sk: original socket
* @flic: target flow
*
* Set the target flow's secid to socket's secid.
*/
void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic)
{
call_void_hook(sk_getsecid, sk, &flic->flowic_secid);
}
EXPORT_SYMBOL(security_sk_classify_flow);
/**
* security_req_classify_flow() - Set a flow's secid based on request_sock
* @req: request_sock
* @flic: target flow
*
* Sets @flic's secid to @req's secid.
*/
void security_req_classify_flow(const struct request_sock *req,
struct flowi_common *flic)
{
call_void_hook(req_classify_flow, req, flic);
}
EXPORT_SYMBOL(security_req_classify_flow);
/**
* security_sock_graft() - Reconcile LSM state when grafting a sock on a socket
* @sk: sock being grafted
* @parent: target parent socket
*
* Sets @parent's inode secid to @sk's secid and update @sk with any necessary
* LSM state from @parent.
*/
void security_sock_graft(struct sock *sk, struct socket *parent)
{
call_void_hook(sock_graft, sk, parent);
}
EXPORT_SYMBOL(security_sock_graft);
/**
* security_inet_conn_request() - Set request_sock state using incoming connect
* @sk: parent listening sock
* @skb: incoming connection
* @req: new request_sock
*
* Initialize the @req LSM state based on @sk and the incoming connect in @skb.
*
* Return: Returns 0 if permission is granted.
*/
int security_inet_conn_request(const struct sock *sk,
struct sk_buff *skb, struct request_sock *req)
{
return call_int_hook(inet_conn_request, sk, skb, req);
}
EXPORT_SYMBOL(security_inet_conn_request);
/**
* security_inet_csk_clone() - Set new sock LSM state based on request_sock
* @newsk: new sock
* @req: connection request_sock
*
* Set that LSM state of @sock using the LSM state from @req.
*/
void security_inet_csk_clone(struct sock *newsk,
const struct request_sock *req)
{
call_void_hook(inet_csk_clone, newsk, req);
}
/**
* security_inet_conn_established() - Update sock's LSM state with connection
* @sk: sock
* @skb: connection packet
*
* Update @sock's LSM state to represent a new connection from @skb.
*/
void security_inet_conn_established(struct sock *sk,
struct sk_buff *skb)
{
call_void_hook(inet_conn_established, sk, skb);
}
EXPORT_SYMBOL(security_inet_conn_established);
/**
* security_secmark_relabel_packet() - Check if setting a secmark is allowed
* @secid: new secmark value
*
* Check if the process should be allowed to relabel packets to @secid.
*
* Return: Returns 0 if permission is granted.
*/
int security_secmark_relabel_packet(u32 secid)
{
return call_int_hook(secmark_relabel_packet, secid);
}
EXPORT_SYMBOL(security_secmark_relabel_packet);
/**
* security_secmark_refcount_inc() - Increment the secmark labeling rule count
*
* Tells the LSM to increment the number of secmark labeling rules loaded.
*/
void security_secmark_refcount_inc(void)
{
call_void_hook(secmark_refcount_inc);
}
EXPORT_SYMBOL(security_secmark_refcount_inc);
/**
* security_secmark_refcount_dec() - Decrement the secmark labeling rule count
*
* Tells the LSM to decrement the number of secmark labeling rules loaded.
*/
void security_secmark_refcount_dec(void)
{
call_void_hook(secmark_refcount_dec);
}
EXPORT_SYMBOL(security_secmark_refcount_dec);
/**
* security_tun_dev_alloc_security() - Allocate a LSM blob for a TUN device
* @security: pointer to the LSM blob
*
* This hook allows a module to allocate a security structure for a TUN device,
* returning the pointer in @security.
*
* Return: Returns a zero on success, negative values on failure.
*/
int security_tun_dev_alloc_security(void **security)
{
int rc;
rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL);
if (rc)
return rc;
rc = call_int_hook(tun_dev_alloc_security, *security);
if (rc) {
kfree(*security);
*security = NULL;
}
return rc;
}
EXPORT_SYMBOL(security_tun_dev_alloc_security);
/**
* security_tun_dev_free_security() - Free a TUN device LSM blob
* @security: LSM blob
*
* This hook allows a module to free the security structure for a TUN device.
*/
void security_tun_dev_free_security(void *security)
{
kfree(security);
}
EXPORT_SYMBOL(security_tun_dev_free_security);
/**
* security_tun_dev_create() - Check if creating a TUN device is allowed
*
* Check permissions prior to creating a new TUN device.
*
* Return: Returns 0 if permission is granted.
*/
int security_tun_dev_create(void)
{
return call_int_hook(tun_dev_create);
}
EXPORT_SYMBOL(security_tun_dev_create);
/**
* security_tun_dev_attach_queue() - Check if attaching a TUN queue is allowed
* @security: TUN device LSM blob
*
* Check permissions prior to attaching to a TUN device queue.
*
* Return: Returns 0 if permission is granted.
*/
int security_tun_dev_attach_queue(void *security)
{
return call_int_hook(tun_dev_attach_queue, security);
}
EXPORT_SYMBOL(security_tun_dev_attach_queue);
/**
* security_tun_dev_attach() - Update TUN device LSM state on attach
* @sk: associated sock
* @security: TUN device LSM blob
*
* This hook can be used by the module to update any security state associated
* with the TUN device's sock structure.
*
* Return: Returns 0 if permission is granted.
*/
int security_tun_dev_attach(struct sock *sk, void *security)
{
return call_int_hook(tun_dev_attach, sk, security);
}
EXPORT_SYMBOL(security_tun_dev_attach);
/**
* security_tun_dev_open() - Update TUN device LSM state on open
* @security: TUN device LSM blob
*
* This hook can be used by the module to update any security state associated
* with the TUN device's security structure.
*
* Return: Returns 0 if permission is granted.
*/
int security_tun_dev_open(void *security)
{
return call_int_hook(tun_dev_open, security);
}
EXPORT_SYMBOL(security_tun_dev_open);
/**
* security_sctp_assoc_request() - Update the LSM on a SCTP association req
* @asoc: SCTP association
* @skb: packet requesting the association
*
* Passes the @asoc and @chunk->skb of the association INIT packet to the LSM.
*
* Return: Returns 0 on success, error on failure.
*/
int security_sctp_assoc_request(struct sctp_association *asoc,
struct sk_buff *skb)
{
return call_int_hook(sctp_assoc_request, asoc, skb);
}
EXPORT_SYMBOL(security_sctp_assoc_request);
/**
* security_sctp_bind_connect() - Validate a list of addrs for a SCTP option
* @sk: socket
* @optname: SCTP option to validate
* @address: list of IP addresses to validate
* @addrlen: length of the address list
*
* Validiate permissions required for each address associated with sock @sk.
* Depending on @optname, the addresses will be treated as either a connect or
* bind service. The @addrlen is calculated on each IPv4 and IPv6 address using
* sizeof(struct sockaddr_in) or sizeof(struct sockaddr_in6).
*
* Return: Returns 0 on success, error on failure.
*/
int security_sctp_bind_connect(struct sock *sk, int optname,
struct sockaddr *address, int addrlen)
{
return call_int_hook(sctp_bind_connect, sk, optname, address, addrlen);
}
EXPORT_SYMBOL(security_sctp_bind_connect);
/**
* security_sctp_sk_clone() - Clone a SCTP sock's LSM state
* @asoc: SCTP association
* @sk: original sock
* @newsk: target sock
*
* Called whenever a new socket is created by accept(2) (i.e. a TCP style
* socket) or when a socket is 'peeled off' e.g userspace calls
* sctp_peeloff(3).
*/
void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
struct sock *newsk)
{
call_void_hook(sctp_sk_clone, asoc, sk, newsk);
}
EXPORT_SYMBOL(security_sctp_sk_clone);
/**
* security_sctp_assoc_established() - Update LSM state when assoc established
* @asoc: SCTP association
* @skb: packet establishing the association
*
* Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet to the
* security module.
*
* Return: Returns 0 if permission is granted.
*/
int security_sctp_assoc_established(struct sctp_association *asoc,
struct sk_buff *skb)
{
return call_int_hook(sctp_assoc_established, asoc, skb);
}
EXPORT_SYMBOL(security_sctp_assoc_established);
/**
* security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket
* @sk: the owning MPTCP socket
* @ssk: the new subflow
*
* Update the labeling for the given MPTCP subflow, to match the one of the
* owning MPTCP socket. This hook has to be called after the socket creation and
* initialization via the security_socket_create() and
* security_socket_post_create() LSM hooks.
*
* Return: Returns 0 on success or a negative error code on failure.
*/
int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
{
return call_int_hook(mptcp_add_subflow, sk, ssk);
}
#endif /* CONFIG_SECURITY_NETWORK */
#ifdef CONFIG_SECURITY_INFINIBAND
/**
* security_ib_pkey_access() - Check if access to an IB pkey is allowed
* @sec: LSM blob
* @subnet_prefix: subnet prefix of the port
* @pkey: IB pkey
*
* Check permission to access a pkey when modifying a QP.
*
* Return: Returns 0 if permission is granted.
*/
int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey)
{
return call_int_hook(ib_pkey_access, sec, subnet_prefix, pkey);
}
EXPORT_SYMBOL(security_ib_pkey_access);
/**
* security_ib_endport_manage_subnet() - Check if SMPs traffic is allowed
* @sec: LSM blob
* @dev_name: IB device name
* @port_num: port number
*
* Check permissions to send and receive SMPs on a end port.
*
* Return: Returns 0 if permission is granted.
*/
int security_ib_endport_manage_subnet(void *sec,
const char *dev_name, u8 port_num)
{
return call_int_hook(ib_endport_manage_subnet, sec, dev_name, port_num);
}
EXPORT_SYMBOL(security_ib_endport_manage_subnet);
/**
* security_ib_alloc_security() - Allocate an Infiniband LSM blob
* @sec: LSM blob
*
* Allocate a security structure for Infiniband objects.
*
* Return: Returns 0 on success, non-zero on failure.
*/
int security_ib_alloc_security(void **sec)
{
int rc;
rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL);
if (rc)
return rc;
rc = call_int_hook(ib_alloc_security, *sec);
if (rc) {
kfree(*sec);
*sec = NULL;
}
return rc;
}
EXPORT_SYMBOL(security_ib_alloc_security);
/**
* security_ib_free_security() - Free an Infiniband LSM blob
* @sec: LSM blob
*
* Deallocate an Infiniband security structure.
*/
void security_ib_free_security(void *sec)
{
kfree(sec);
}
EXPORT_SYMBOL(security_ib_free_security);
#endif /* CONFIG_SECURITY_INFINIBAND */
#ifdef CONFIG_SECURITY_NETWORK_XFRM
/**
* security_xfrm_policy_alloc() - Allocate a xfrm policy LSM blob
* @ctxp: xfrm security context being added to the SPD
* @sec_ctx: security label provided by userspace
* @gfp: gfp flags
*
* Allocate a security structure to the xp->security field; the security field
* is initialized to NULL when the xfrm_policy is allocated.
*
* Return: Return 0 if operation was successful.
*/
int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
struct xfrm_user_sec_ctx *sec_ctx,
gfp_t gfp)
{
return call_int_hook(xfrm_policy_alloc_security, ctxp, sec_ctx, gfp);
}
EXPORT_SYMBOL(security_xfrm_policy_alloc);
/**
* security_xfrm_policy_clone() - Clone xfrm policy LSM state
* @old_ctx: xfrm security context
* @new_ctxp: target xfrm security context
*
* Allocate a security structure in new_ctxp that contains the information from
* the old_ctx structure.
*
* Return: Return 0 if operation was successful.
*/
int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
struct xfrm_sec_ctx **new_ctxp)
{
return call_int_hook(xfrm_policy_clone_security, old_ctx, new_ctxp);
}
/**
* security_xfrm_policy_free() - Free a xfrm security context
* @ctx: xfrm security context
*
* Free LSM resources associated with @ctx.
*/
void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
{
call_void_hook(xfrm_policy_free_security, ctx);
}
EXPORT_SYMBOL(security_xfrm_policy_free);
/**
* security_xfrm_policy_delete() - Check if deleting a xfrm policy is allowed
* @ctx: xfrm security context
*
* Authorize deletion of a SPD entry.
*
* Return: Returns 0 if permission is granted.
*/
int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
{
return call_int_hook(xfrm_policy_delete_security, ctx);
}
/**
* security_xfrm_state_alloc() - Allocate a xfrm state LSM blob
* @x: xfrm state being added to the SAD
* @sec_ctx: security label provided by userspace
*
* Allocate a security structure to the @x->security field; the security field
* is initialized to NULL when the xfrm_state is allocated. Set the context to
* correspond to @sec_ctx.
*
* Return: Return 0 if operation was successful.
*/
int security_xfrm_state_alloc(struct xfrm_state *x,
struct xfrm_user_sec_ctx *sec_ctx)
{
return call_int_hook(xfrm_state_alloc, x, sec_ctx);
}
EXPORT_SYMBOL(security_xfrm_state_alloc);
/**
* security_xfrm_state_alloc_acquire() - Allocate a xfrm state LSM blob
* @x: xfrm state being added to the SAD
* @polsec: associated policy's security context
* @secid: secid from the flow
*
* Allocate a security structure to the x->security field; the security field
* is initialized to NULL when the xfrm_state is allocated. Set the context to
* correspond to secid.
*
* Return: Returns 0 if operation was successful.
*/
int security_xfrm_state_alloc_acquire(struct xfrm_state *x,
struct xfrm_sec_ctx *polsec, u32 secid)
{
return call_int_hook(xfrm_state_alloc_acquire, x, polsec, secid);
}
/**
* security_xfrm_state_delete() - Check if deleting a xfrm state is allowed
* @x: xfrm state
*
* Authorize deletion of x->security.
*
* Return: Returns 0 if permission is granted.
*/
int security_xfrm_state_delete(struct xfrm_state *x)
{
return call_int_hook(xfrm_state_delete_security, x);
}
EXPORT_SYMBOL(security_xfrm_state_delete);
/**
* security_xfrm_state_free() - Free a xfrm state
* @x: xfrm state
*
* Deallocate x->security.
*/
void security_xfrm_state_free(struct xfrm_state *x)
{
call_void_hook(xfrm_state_free_security, x);
}
/**
* security_xfrm_policy_lookup() - Check if using a xfrm policy is allowed
* @ctx: target xfrm security context
* @fl_secid: flow secid used to authorize access
*
* Check permission when a flow selects a xfrm_policy for processing XFRMs on a
* packet. The hook is called when selecting either a per-socket policy or a
* generic xfrm policy.
*
* Return: Return 0 if permission is granted, -ESRCH otherwise, or -errno on
* other errors.
*/
int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid)
{
return call_int_hook(xfrm_policy_lookup, ctx, fl_secid);
}
/**
* security_xfrm_state_pol_flow_match() - Check for a xfrm match
* @x: xfrm state to match
* @xp: xfrm policy to check for a match
* @flic: flow to check for a match.
*
* Check @xp and @flic for a match with @x.
*
* Return: Returns 1 if there is a match.
*/
int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
struct xfrm_policy *xp,
const struct flowi_common *flic)
{
struct lsm_static_call *scall;
int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match);
/*
* Since this function is expected to return 0 or 1, the judgment
* becomes difficult if multiple LSMs supply this call. Fortunately,
* we can use the first LSM's judgment because currently only SELinux
* supplies this call.
*
* For speed optimization, we explicitly break the loop rather than
* using the macro
*/
lsm_for_each_hook(scall, xfrm_state_pol_flow_match) {
rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic);
break;
}
return rc;
}
/**
* security_xfrm_decode_session() - Determine the xfrm secid for a packet
* @skb: xfrm packet
* @secid: secid
*
* Decode the packet in @skb and return the security label in @secid.
*
* Return: Return 0 if all xfrms used have the same secid.
*/
int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
{
return call_int_hook(xfrm_decode_session, skb, secid, 1);
}
void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic)
{
int rc = call_int_hook(xfrm_decode_session, skb, &flic->flowic_secid,
0);
BUG_ON(rc);
}
EXPORT_SYMBOL(security_skb_classify_flow);
#endif /* CONFIG_SECURITY_NETWORK_XFRM */
#ifdef CONFIG_KEYS
/**
* security_key_alloc() - Allocate and initialize a kernel key LSM blob
* @key: key
* @cred: credentials
* @flags: allocation flags
*
* Permit allocation of a key and assign security data. Note that key does not
* have a serial number assigned at this point.
*
* Return: Return 0 if permission is granted, -ve error otherwise.
*/
int security_key_alloc(struct key *key, const struct cred *cred,
unsigned long flags)
{
int rc = lsm_key_alloc(key);
if (unlikely(rc))
return rc;
rc = call_int_hook(key_alloc, key, cred, flags);
if (unlikely(rc))
security_key_free(key);
return rc;
}
/**
* security_key_free() - Free a kernel key LSM blob
* @key: key
*
* Notification of destruction; free security data.
*/
void security_key_free(struct key *key)
{
kfree(key->security);
key->security = NULL;
}
/**
* security_key_permission() - Check if a kernel key operation is allowed
* @key_ref: key reference
* @cred: credentials of actor requesting access
* @need_perm: requested permissions
*
* See whether a specific operational right is granted to a process on a key.
*
* Return: Return 0 if permission is granted, -ve error otherwise.
*/
int security_key_permission(key_ref_t key_ref, const struct cred *cred,
enum key_need_perm need_perm)
{
return call_int_hook(key_permission, key_ref, cred, need_perm);
}
/**
* security_key_getsecurity() - Get the key's security label
* @key: key
* @buffer: security label buffer
*
* Get a textual representation of the security context attached to a key for
* the purposes of honouring KEYCTL_GETSECURITY. This function allocates the
* storage for the NUL-terminated string and the caller should free it.
*
* Return: Returns the length of @buffer (including terminating NUL) or -ve if
* an error occurs. May also return 0 (and a NULL buffer pointer) if
* there is no security label assigned to the key.
*/
int security_key_getsecurity(struct key *key, char **buffer)
{
*buffer = NULL;
return call_int_hook(key_getsecurity, key, buffer);
}
/**
* security_key_post_create_or_update() - Notification of key create or update
* @keyring: keyring to which the key is linked to
* @key: created or updated key
* @payload: data used to instantiate or update the key
* @payload_len: length of payload
* @flags: key flags
* @create: flag indicating whether the key was created or updated
*
* Notify the caller of a key creation or update.
*/
void security_key_post_create_or_update(struct key *keyring, struct key *key,
const void *payload, size_t payload_len,
unsigned long flags, bool create)
{
call_void_hook(key_post_create_or_update, keyring, key, payload,
payload_len, flags, create);
}
#endif /* CONFIG_KEYS */
#ifdef CONFIG_AUDIT
/**
* security_audit_rule_init() - Allocate and init an LSM audit rule struct
* @field: audit action
* @op: rule operator
* @rulestr: rule context
* @lsmrule: receive buffer for audit rule struct
* @gfp: GFP flag used for kmalloc
*
* Allocate and initialize an LSM audit rule structure.
*
* Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of
* an invalid rule.
*/
int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule,
gfp_t gfp)
{
return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp);
}
/**
* security_audit_rule_known() - Check if an audit rule contains LSM fields
* @krule: audit rule
*
* Specifies whether given @krule contains any fields related to the current
* LSM.
*
* Return: Returns 1 in case of relation found, 0 otherwise.
*/
int security_audit_rule_known(struct audit_krule *krule)
{
return call_int_hook(audit_rule_known, krule);
}
/**
* security_audit_rule_free() - Free an LSM audit rule struct
* @lsmrule: audit rule struct
*
* Deallocate the LSM audit rule structure previously allocated by
* audit_rule_init().
*/
void security_audit_rule_free(void *lsmrule)
{
call_void_hook(audit_rule_free, lsmrule);
}
/**
* security_audit_rule_match() - Check if a label matches an audit rule
* @prop: security label
* @field: LSM audit field
* @op: matching operator
* @lsmrule: audit rule
*
* Determine if given @secid matches a rule previously approved by
* security_audit_rule_known().
*
* Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on
* failure.
*/
int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op,
void *lsmrule)
{
return call_int_hook(audit_rule_match, prop, field, op, lsmrule);
}
#endif /* CONFIG_AUDIT */
#ifdef CONFIG_BPF_SYSCALL
/**
* security_bpf() - Check if the bpf syscall operation is allowed
* @cmd: command
* @attr: bpf attribute
* @size: size
* @kernel: whether or not call originated from kernel
*
* Do a initial check for all bpf syscalls after the attribute is copied into
* the kernel. The actual security module can implement their own rules to
* check the specific cmd they need.
*
* Return: Returns 0 if permission is granted.
*/
int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
return call_int_hook(bpf, cmd, attr, size, kernel);
}
/**
* security_bpf_map() - Check if access to a bpf map is allowed
* @map: bpf map
* @fmode: mode
*
* Do a check when the kernel generates and returns a file descriptor for eBPF
* maps.
*
* Return: Returns 0 if permission is granted.
*/
int security_bpf_map(struct bpf_map *map, fmode_t fmode)
{
return call_int_hook(bpf_map, map, fmode);
}
/**
* security_bpf_prog() - Check if access to a bpf program is allowed
* @prog: bpf program
*
* Do a check when the kernel generates and returns a file descriptor for eBPF
* programs.
*
* Return: Returns 0 if permission is granted.
*/
int security_bpf_prog(struct bpf_prog *prog)
{
return call_int_hook(bpf_prog, prog);
}
/**
* security_bpf_map_create() - Check if BPF map creation is allowed
* @map: BPF map object
* @attr: BPF syscall attributes used to create BPF map
* @token: BPF token used to grant user access
* @kernel: whether or not call originated from kernel
*
* Do a check when the kernel creates a new BPF map. This is also the
* point where LSM blob is allocated for LSMs that need them.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token, bool kernel)
{
return call_int_hook(bpf_map_create, map, attr, token, kernel);
}
/**
* security_bpf_prog_load() - Check if loading of BPF program is allowed
* @prog: BPF program object
* @attr: BPF syscall attributes used to create BPF program
* @token: BPF token used to grant user access to BPF subsystem
* @kernel: whether or not call originated from kernel
*
* Perform an access control check when the kernel loads a BPF program and
* allocates associated BPF program object. This hook is also responsible for
* allocating any required LSM state for the BPF program.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token, bool kernel)
{
return call_int_hook(bpf_prog_load, prog, attr, token, kernel);
}
/**
* security_bpf_token_create() - Check if creating of BPF token is allowed
* @token: BPF token object
* @attr: BPF syscall attributes used to create BPF token
* @path: path pointing to BPF FS mount point from which BPF token is created
*
* Do a check when the kernel instantiates a new BPF token object from BPF FS
* instance. This is also the point where LSM blob can be allocated for LSMs.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
const struct path *path)
{
return call_int_hook(bpf_token_create, token, attr, path);
}
/**
* security_bpf_token_cmd() - Check if BPF token is allowed to delegate
* requested BPF syscall command
* @token: BPF token object
* @cmd: BPF syscall command requested to be delegated by BPF token
*
* Do a check when the kernel decides whether provided BPF token should allow
* delegation of requested BPF syscall command.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
{
return call_int_hook(bpf_token_cmd, token, cmd);
}
/**
* security_bpf_token_capable() - Check if BPF token is allowed to delegate
* requested BPF-related capability
* @token: BPF token object
* @cap: capabilities requested to be delegated by BPF token
*
* Do a check when the kernel decides whether provided BPF token should allow
* delegation of requested BPF-related capabilities.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_capable(const struct bpf_token *token, int cap)
{
return call_int_hook(bpf_token_capable, token, cap);
}
/**
* security_bpf_map_free() - Free a bpf map's LSM blob
* @map: bpf map
*
* Clean up the security information stored inside bpf map.
*/
void security_bpf_map_free(struct bpf_map *map)
{
call_void_hook(bpf_map_free, map);
}
/**
* security_bpf_prog_free() - Free a BPF program's LSM blob
* @prog: BPF program struct
*
* Clean up the security information stored inside BPF program.
*/
void security_bpf_prog_free(struct bpf_prog *prog)
{
call_void_hook(bpf_prog_free, prog);
}
/**
* security_bpf_token_free() - Free a BPF token's LSM blob
* @token: BPF token struct
*
* Clean up the security information stored inside BPF token.
*/
void security_bpf_token_free(struct bpf_token *token)
{
call_void_hook(bpf_token_free, token);
}
#endif /* CONFIG_BPF_SYSCALL */
/**
* security_locked_down() - Check if a kernel feature is allowed
* @what: requested kernel feature
*
* Determine whether a kernel feature that potentially enables arbitrary code
* execution in kernel space should be permitted.
*
* Return: Returns 0 if permission is granted.
*/
int security_locked_down(enum lockdown_reason what)
{
return call_int_hook(locked_down, what);
}
EXPORT_SYMBOL(security_locked_down);
/**
* security_bdev_alloc() - Allocate a block device LSM blob
* @bdev: block device
*
* Allocate and attach a security structure to @bdev->bd_security. The
* security field is initialized to NULL when the bdev structure is
* allocated.
*
* Return: Return 0 if operation was successful.
*/
int security_bdev_alloc(struct block_device *bdev)
{
int rc = 0;
rc = lsm_bdev_alloc(bdev);
if (unlikely(rc))
return rc;
rc = call_int_hook(bdev_alloc_security, bdev);
if (unlikely(rc))
security_bdev_free(bdev);
return rc;
}
EXPORT_SYMBOL(security_bdev_alloc);
/**
* security_bdev_free() - Free a block device's LSM blob
* @bdev: block device
*
* Deallocate the bdev security structure and set @bdev->bd_security to NULL.
*/
void security_bdev_free(struct block_device *bdev)
{
if (!bdev->bd_security)
return;
call_void_hook(bdev_free_security, bdev);
kfree(bdev->bd_security);
bdev->bd_security = NULL;
}
EXPORT_SYMBOL(security_bdev_free);
/**
* security_bdev_setintegrity() - Set the device's integrity data
* @bdev: block device
* @type: type of integrity, e.g. hash digest, signature, etc
* @value: the integrity value
* @size: size of the integrity value
*
* Register a verified integrity measurement of a bdev with LSMs.
* LSMs should free the previously saved data if @value is NULL.
* Please note that the new hook should be invoked every time the security
* information is updated to keep these data current. For example, in dm-verity,
* if the mapping table is reloaded and configured to use a different dm-verity
* target with a new roothash and signing information, the previously stored
* data in the LSM blob will become obsolete. It is crucial to re-invoke the
* hook to refresh these data and ensure they are up to date. This necessity
* arises from the design of device-mapper, where a device-mapper device is
* first created, and then targets are subsequently loaded into it. These
* targets can be modified multiple times during the device's lifetime.
* Therefore, while the LSM blob is allocated during the creation of the block
* device, its actual contents are not initialized at this stage and can change
* substantially over time. This includes alterations from data that the LSMs
* 'trusts' to those they do not, making it essential to handle these changes
* correctly. Failure to address this dynamic aspect could potentially allow
* for bypassing LSM checks.
*
* Return: Returns 0 on success, negative values on failure.
*/
int security_bdev_setintegrity(struct block_device *bdev,
enum lsm_integrity_type type, const void *value,
size_t size)
{
return call_int_hook(bdev_setintegrity, bdev, type, value, size);
}
EXPORT_SYMBOL(security_bdev_setintegrity);
#ifdef CONFIG_PERF_EVENTS
/**
* security_perf_event_open() - Check if a perf event open is allowed
* @type: type of event
*
* Check whether the @type of perf_event_open syscall is allowed.
*
* Return: Returns 0 if permission is granted.
*/
int security_perf_event_open(int type)
{
return call_int_hook(perf_event_open, type);
}
/**
* security_perf_event_alloc() - Allocate a perf event LSM blob
* @event: perf event
*
* Allocate and save perf_event security info.
*
* Return: Returns 0 on success, error on failure.
*/
int security_perf_event_alloc(struct perf_event *event)
{
int rc;
rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event,
GFP_KERNEL);
if (rc)
return rc;
rc = call_int_hook(perf_event_alloc, event); if (rc) {
kfree(event->security);
event->security = NULL;
}
return rc;
}
/**
* security_perf_event_free() - Free a perf event LSM blob
* @event: perf event
*
* Release (free) perf_event security info.
*/
void security_perf_event_free(struct perf_event *event)
{
kfree(event->security);
event->security = NULL;
}
/**
* security_perf_event_read() - Check if reading a perf event label is allowed
* @event: perf event
*
* Read perf_event security info if allowed.
*
* Return: Returns 0 if permission is granted.
*/
int security_perf_event_read(struct perf_event *event)
{
return call_int_hook(perf_event_read, event);
}
/**
* security_perf_event_write() - Check if writing a perf event label is allowed
* @event: perf event
*
* Write perf_event security info if allowed.
*
* Return: Returns 0 if permission is granted.
*/
int security_perf_event_write(struct perf_event *event)
{
return call_int_hook(perf_event_write, event);
}
#endif /* CONFIG_PERF_EVENTS */
#ifdef CONFIG_IO_URING
/**
* security_uring_override_creds() - Check if overriding creds is allowed
* @new: new credentials
*
* Check if the current task, executing an io_uring operation, is allowed to
* override it's credentials with @new.
*
* Return: Returns 0 if permission is granted.
*/
int security_uring_override_creds(const struct cred *new)
{
return call_int_hook(uring_override_creds, new);
}
/**
* security_uring_sqpoll() - Check if IORING_SETUP_SQPOLL is allowed
*
* Check whether the current task is allowed to spawn a io_uring polling thread
* (IORING_SETUP_SQPOLL).
*
* Return: Returns 0 if permission is granted.
*/
int security_uring_sqpoll(void)
{
return call_int_hook(uring_sqpoll);
}
/**
* security_uring_cmd() - Check if a io_uring passthrough command is allowed
* @ioucmd: command
*
* Check whether the file_operations uring_cmd is allowed to run.
*
* Return: Returns 0 if permission is granted.
*/
int security_uring_cmd(struct io_uring_cmd *ioucmd)
{
return call_int_hook(uring_cmd, ioucmd);
}
/**
* security_uring_allowed() - Check if io_uring_setup() is allowed
*
* Check whether the current task is allowed to call io_uring_setup().
*
* Return: Returns 0 if permission is granted.
*/
int security_uring_allowed(void)
{
return call_int_hook(uring_allowed);
}
#endif /* CONFIG_IO_URING */
/**
* security_initramfs_populated() - Notify LSMs that initramfs has been loaded
*
* Tells the LSMs the initramfs has been unpacked into the rootfs.
*/
void security_initramfs_populated(void)
{
call_void_hook(initramfs_populated);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_BITMAP_H
#define __LINUX_BITMAP_H
#ifndef __ASSEMBLY__
#include <linux/align.h>
#include <linux/bitops.h>
#include <linux/cleanup.h>
#include <linux/errno.h>
#include <linux/find.h>
#include <linux/limits.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/bitmap-str.h>
struct device;
/*
* bitmaps provide bit arrays that consume one or more unsigned
* longs. The bitmap interface and available operations are listed
* here, in bitmap.h
*
* Function implementations generic to all architectures are in
* lib/bitmap.c. Functions implementations that are architecture
* specific are in various arch/<arch>/include/asm/bitops.h headers
* and other arch/<arch> specific files.
*
* See lib/bitmap.c for more details.
*/
/**
* DOC: bitmap overview
*
* The available bitmap operations and their rough meaning in the
* case that the bitmap is a single unsigned long are thus:
*
* The generated code is more efficient when nbits is known at
* compile-time and at most BITS_PER_LONG.
*
* ::
*
* bitmap_zero(dst, nbits) *dst = 0UL
* bitmap_fill(dst, nbits) *dst = ~0UL
* bitmap_copy(dst, src, nbits) *dst = *src
* bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2
* bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2
* bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2
* bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2)
* bitmap_complement(dst, src, nbits) *dst = ~(*src)
* bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal?
* bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap?
* bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2?
* bitmap_empty(src, nbits) Are all bits zero in *src?
* bitmap_full(src, nbits) Are all bits set in *src?
* bitmap_weight(src, nbits) Hamming Weight: number set bits
* bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap
* bitmap_weight_andnot(src1, src2, nbits) Hamming Weight of andnot'ed bitmap
* bitmap_set(dst, pos, nbits) Set specified bit area
* bitmap_clear(dst, pos, nbits) Clear specified bit area
* bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area
* bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above
* bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n
* bitmap_shift_left(dst, src, n, nbits) *dst = *src << n
* bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest
* bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask)
* bitmap_scatter(dst, src, mask, nbits) *dst = map(dense, sparse)(src)
* bitmap_gather(dst, src, mask, nbits) *dst = map(sparse, dense)(src)
* bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src)
* bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit)
* bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap
* bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz
* bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf
* bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf
* bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf
* bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf
* bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
* bitmap_release_region(bitmap, pos, order) Free specified bit region
* bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region
* bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst
* bitmap_from_arr64(dst, buf, nbits) Copy nbits from u64[] buf to dst
* bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst
* bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst
* bitmap_get_value8(map, start) Get 8bit value from map at start
* bitmap_set_value8(map, value, start) Set 8bit value to map at start
* bitmap_read(map, start, nbits) Read an nbits-sized value from
* map at start
* bitmap_write(map, value, start, nbits) Write an nbits-sized value to
* map at start
*
* Note, bitmap_zero() and bitmap_fill() operate over the region of
* unsigned longs, that is, bits behind bitmap till the unsigned long
* boundary will be zeroed or filled as well. Consider to use
* bitmap_clear() or bitmap_set() to make explicit zeroing or filling
* respectively.
*/
/**
* DOC: bitmap bitops
*
* Also the following operations in asm/bitops.h apply to bitmaps.::
*
* set_bit(bit, addr) *addr |= bit
* clear_bit(bit, addr) *addr &= ~bit
* change_bit(bit, addr) *addr ^= bit
* test_bit(bit, addr) Is bit set in *addr?
* test_and_set_bit(bit, addr) Set bit and return old value
* test_and_clear_bit(bit, addr) Clear bit and return old value
* test_and_change_bit(bit, addr) Change bit and return old value
* find_first_zero_bit(addr, nbits) Position first zero bit in *addr
* find_first_bit(addr, nbits) Position first set bit in *addr
* find_next_zero_bit(addr, nbits, bit)
* Position next zero bit in *addr >= bit
* find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit
* find_next_and_bit(addr1, addr2, nbits, bit)
* Same as find_next_bit, but in
* (*addr1 & *addr2)
*
*/
/**
* DOC: declare bitmap
* The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used
* to declare an array named 'name' of just enough unsigned longs to
* contain all bit positions from 0 to 'bits' - 1.
*/
/*
* Allocation and deallocation of bitmap.
* Provided in lib/bitmap.c to avoid circular dependency.
*/
unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags);
unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags);
unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node);
unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node);
void bitmap_free(const unsigned long *bitmap);
DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T))
/* Managed variants of the above. */
unsigned long *devm_bitmap_alloc(struct device *dev,
unsigned int nbits, gfp_t flags);
unsigned long *devm_bitmap_zalloc(struct device *dev,
unsigned int nbits, gfp_t flags);
/*
* lib/bitmap.c provides these functions:
*/
bool __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
bool __pure __bitmap_or_equal(const unsigned long *src1,
const unsigned long *src2,
const unsigned long *src3,
unsigned int nbits);
void __bitmap_complement(unsigned long *dst, const unsigned long *src,
unsigned int nbits);
void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits);
void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits);
void bitmap_cut(unsigned long *dst, const unsigned long *src,
unsigned int first, unsigned int cut, unsigned int nbits);
bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_replace(unsigned long *dst,
const unsigned long *old, const unsigned long *new,
const unsigned long *mask, unsigned int nbits);
bool __bitmap_intersects(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
bool __bitmap_subset(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_set(unsigned long *map, unsigned int start, int len);
void __bitmap_clear(unsigned long *map, unsigned int start, int len);
unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask,
unsigned long align_offset);
/**
* bitmap_find_next_zero_area - find a contiguous aligned zero area
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @align_mask: Alignment mask for zero area
*
* The @align_mask should be one less than a power of 2; the effect is that
* the bit offset of all zero areas this function finds is multiples of that
* power of 2. A @align_mask of 0 means no alignment is required.
*/
static __always_inline
unsigned long bitmap_find_next_zero_area(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask)
{
return bitmap_find_next_zero_area_off(map, size, start, nr,
align_mask, 0);
}
void bitmap_remap(unsigned long *dst, const unsigned long *src,
const unsigned long *old, const unsigned long *new, unsigned int nbits);
int bitmap_bitremap(int oldbit,
const unsigned long *old, const unsigned long *new, int bits);
void bitmap_onto(unsigned long *dst, const unsigned long *orig,
const unsigned long *relmap, unsigned int bits);
void bitmap_fold(unsigned long *dst, const unsigned long *orig,
unsigned int sz, unsigned int nbits);
#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
{
unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = 0;
else
memset(dst, 0, len);
}
static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
{
unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = ~0UL;
else
memset(dst, 0xff, len);
}
static __always_inline
void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits)
{
unsigned int len = bitmap_size(nbits);
if (small_const_nbits(nbits))
*dst = *src;
else
memcpy(dst, src, len);
}
/*
* Copy bitmap and clear tail bits in last word.
*/
static __always_inline
void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits)
{
bitmap_copy(dst, src, nbits);
if (nbits % BITS_PER_LONG)
dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
}
static inline void bitmap_copy_and_extend(unsigned long *to,
const unsigned long *from,
unsigned int count, unsigned int size)
{
unsigned int copy = BITS_TO_LONGS(count);
memcpy(to, from, copy * sizeof(long));
if (count % BITS_PER_LONG)
to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
}
/*
* On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
* machines the order of hi and lo parts of numbers match the bitmap structure.
* In both cases conversion is not needed when copying data from/to arrays of
* u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead
* to out-of-bound access. To avoid that, both LE and BE variants of 64-bit
* architectures are not using bitmap_copy_clear_tail().
*/
#if BITS_PER_LONG == 64
void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf,
unsigned int nbits);
void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
unsigned int nbits);
#else
#define bitmap_from_arr32(bitmap, buf, nbits) \
bitmap_copy_clear_tail((unsigned long *) (bitmap), \
(const unsigned long *) (buf), (nbits))
#define bitmap_to_arr32(buf, bitmap, nbits) \
bitmap_copy_clear_tail((unsigned long *) (buf), \
(const unsigned long *) (bitmap), (nbits))
#endif
/*
* On 64-bit systems bitmaps are represented as u64 arrays internally. So,
* the conversion is not needed when copying data from/to arrays of u64.
*/
#if BITS_PER_LONG == 32
void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
#else
#define bitmap_from_arr64(bitmap, buf, nbits) \
bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits))
#define bitmap_to_arr64(buf, bitmap, nbits) \
bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
#endif
static __always_inline
bool bitmap_and(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
return __bitmap_and(dst, src1, src2, nbits);
}
static __always_inline
void bitmap_or(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = *src1 | *src2;
else
__bitmap_or(dst, src1, src2, nbits);
}
static __always_inline
void bitmap_xor(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = *src1 ^ *src2;
else
__bitmap_xor(dst, src1, src2, nbits);
}
static __always_inline
bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
return __bitmap_andnot(dst, src1, src2, nbits);
}
static __always_inline
void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = ~(*src);
else
__bitmap_complement(dst, src, nbits);
}
#ifdef __LITTLE_ENDIAN
#define BITMAP_MEM_ALIGNMENT 8
#else
#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long))
#endif
#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
static __always_inline
bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
return !memcmp(src1, src2, nbits / 8);
return __bitmap_equal(src1, src2, nbits);
}
/**
* bitmap_or_equal - Check whether the or of two bitmaps is equal to a third
* @src1: Pointer to bitmap 1
* @src2: Pointer to bitmap 2 will be or'ed with bitmap 1
* @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2
* @nbits: number of bits in each of these bitmaps
*
* Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
*/
static __always_inline
bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2,
const unsigned long *src3, unsigned int nbits)
{
if (!small_const_nbits(nbits))
return __bitmap_or_equal(src1, src2, src3, nbits);
return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
}
static __always_inline
bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
else
return __bitmap_intersects(src1, src2, nbits);
}
static __always_inline
bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
else
return __bitmap_subset(src1, src2, nbits);
}
static __always_inline
bool bitmap_empty(const unsigned long *src, unsigned nbits)
{
if (small_const_nbits(nbits))
return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
return find_first_bit(src, nbits) == nbits;
}
static __always_inline
bool bitmap_full(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
return find_first_zero_bit(src, nbits) == nbits;
}
static __always_inline
unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
return __bitmap_weight(src, nbits);
}
static __always_inline
unsigned long bitmap_weight_and(const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits));
return __bitmap_weight_and(src1, src2, nbits);
}
static __always_inline
unsigned long bitmap_weight_andnot(const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits));
return __bitmap_weight_andnot(src1, src2, nbits);
}
static __always_inline
void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits)
{
if (__builtin_constant_p(nbits) && nbits == 1)
__set_bit(start, map);
else if (small_const_nbits(start + nbits))
*map |= GENMASK(start + nbits - 1, start);
else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
memset((char *)map + start / 8, 0xff, nbits / 8);
else
__bitmap_set(map, start, nbits);
}
static __always_inline
void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits)
{
if (__builtin_constant_p(nbits) && nbits == 1)
__clear_bit(start, map);
else if (small_const_nbits(start + nbits))
*map &= ~GENMASK(start + nbits - 1, start);
else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
memset((char *)map + start / 8, 0, nbits / 8);
else
__bitmap_clear(map, start, nbits);
}
static __always_inline
void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
else
__bitmap_shift_right(dst, src, shift, nbits);
}
static __always_inline
void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
else
__bitmap_shift_left(dst, src, shift, nbits);
}
static __always_inline
void bitmap_replace(unsigned long *dst,
const unsigned long *old,
const unsigned long *new,
const unsigned long *mask,
unsigned int nbits)
{
if (small_const_nbits(nbits))
*dst = (*old & ~(*mask)) | (*new & *mask);
else
__bitmap_replace(dst, old, new, mask, nbits);
}
/**
* bitmap_scatter - Scatter a bitmap according to the given mask
* @dst: scattered bitmap
* @src: gathered bitmap
* @mask: mask representing bits to assign to in the scattered bitmap
* @nbits: number of bits in each of these bitmaps
*
* Scatters bitmap with sequential bits according to the given @mask.
*
* Example:
* If @src bitmap = 0x005a, with @mask = 0x1313, @dst will be 0x0302.
*
* Or in binary form
* @src @mask @dst
* 0000000001011010 0001001100010011 0000001100000010
*
* (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12)
*
* A more 'visual' description of the operation::
*
* src: 0000000001011010
* ||||||
* +------+|||||
* | +----+||||
* | |+----+|||
* | || +-+||
* | || | ||
* mask: ...v..vv...v..vv
* ...0..11...0..10
* dst: 0000001100000010
*
* A relationship exists between bitmap_scatter() and bitmap_gather(). See
* bitmap_gather() for the bitmap gather detailed operations. TL;DR:
* bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
*/
static __always_inline
void bitmap_scatter(unsigned long *dst, const unsigned long *src,
const unsigned long *mask, unsigned int nbits)
{
unsigned int n = 0;
unsigned int bit;
bitmap_zero(dst, nbits);
for_each_set_bit(bit, mask, nbits)
__assign_bit(bit, dst, test_bit(n++, src));
}
/**
* bitmap_gather - Gather a bitmap according to given mask
* @dst: gathered bitmap
* @src: scattered bitmap
* @mask: mask representing bits to extract from in the scattered bitmap
* @nbits: number of bits in each of these bitmaps
*
* Gathers bitmap with sparse bits according to the given @mask.
*
* Example:
* If @src bitmap = 0x0302, with @mask = 0x1313, @dst will be 0x001a.
*
* Or in binary form
* @src @mask @dst
* 0000001100000010 0001001100010011 0000000000011010
*
* (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5)
*
* A more 'visual' description of the operation::
*
* mask: ...v..vv...v..vv
* src: 0000001100000010
* ^ ^^ ^ 0
* | || | 10
* | || > 010
* | |+--> 1010
* | +--> 11010
* +----> 011010
* dst: 0000000000011010
*
* A relationship exists between bitmap_gather() and bitmap_scatter(). See
* bitmap_scatter() for the bitmap scatter detailed operations. TL;DR:
* bitmap_scatter() can be seen as the 'reverse' bitmap_gather() operation.
*
* Suppose scattered computed using bitmap_scatter(scattered, src, mask, n).
* The operation bitmap_gather(result, scattered, mask, n) leads to a result
* equal or equivalent to src.
*
* The result can be 'equivalent' because bitmap_scatter() and bitmap_gather()
* are not bijective.
* The result and src values are equivalent in that sense that a call to
* bitmap_scatter(res, src, mask, n) and a call to
* bitmap_scatter(res, result, mask, n) will lead to the same res value.
*/
static __always_inline
void bitmap_gather(unsigned long *dst, const unsigned long *src,
const unsigned long *mask, unsigned int nbits)
{
unsigned int n = 0;
unsigned int bit;
bitmap_zero(dst, nbits);
for_each_set_bit(bit, mask, nbits)
__assign_bit(n++, dst, test_bit(bit, src));
}
static __always_inline
void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs,
unsigned int *re, unsigned int end)
{
*rs = find_next_bit(bitmap, end, *rs);
*re = find_next_zero_bit(bitmap, end, *rs + 1);
}
/**
* bitmap_release_region - release allocated bitmap region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @pos: beginning of bit region to release
* @order: region size (log base 2 of number of bits) to release
*
* This is the complement to __bitmap_find_free_region() and releases
* the found region (by clearing it in the bitmap).
*/
static __always_inline
void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
{
bitmap_clear(bitmap, pos, BIT(order));
}
/**
* bitmap_allocate_region - allocate bitmap region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @pos: beginning of bit region to allocate
* @order: region size (log base 2 of number of bits) to allocate
*
* Allocate (set bits in) a specified region of a bitmap.
*
* Returns: 0 on success, or %-EBUSY if specified region wasn't
* free (not all bits were zero).
*/
static __always_inline
int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
{
unsigned int len = BIT(order);
if (find_next_bit(bitmap, pos + len, pos) < pos + len)
return -EBUSY;
bitmap_set(bitmap, pos, len);
return 0;
}
/**
* bitmap_find_free_region - find a contiguous aligned mem region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @bits: number of bits in the bitmap
* @order: region size (log base 2 of number of bits) to find
*
* Find a region of free (zero) bits in a @bitmap of @bits bits and
* allocate them (set them to one). Only consider regions of length
* a power (@order) of two, aligned to that power of two, which
* makes the search algorithm much faster.
*
* Returns: the bit offset in bitmap of the allocated region,
* or -errno on failure.
*/
static __always_inline
int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
{
unsigned int pos, end; /* scans bitmap by regions of size order */
for (pos = 0; (end = pos + BIT(order)) <= bits; pos = end) {
if (!bitmap_allocate_region(bitmap, pos, order))
return pos;
}
return -ENOMEM;
}
/**
* BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap.
* @n: u64 value
*
* Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit
* integers in 32-bit environment, and 64-bit integers in 64-bit one.
*
* There are four combinations of endianness and length of the word in linux
* ABIs: LE64, BE64, LE32 and BE32.
*
* On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in
* bitmaps and therefore don't require any special handling.
*
* On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory
* prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the
* other hand is represented as an array of 32-bit words and the position of
* bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that
* word. For example, bit #42 is located at 10th position of 2nd word.
* It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit
* values in memory as it usually does. But for BE we need to swap hi and lo
* words manually.
*
* With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and
* lo parts of u64. For LE32 it does nothing, and for BE environment it swaps
* hi and lo words, as is expected by bitmap.
*/
#if __BITS_PER_LONG == 64
#define BITMAP_FROM_U64(n) (n)
#else
#define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \
((unsigned long) ((u64)(n) >> 32))
#endif
/**
* bitmap_from_u64 - Check and swap words within u64.
* @mask: source bitmap
* @dst: destination bitmap
*
* In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]``
* to read u64 mask, we will get the wrong word.
* That is ``(u32 *)(&val)[0]`` gets the upper 32 bits,
* but we expect the lower 32-bits of u64.
*/
static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask)
{
bitmap_from_arr64(dst, &mask, 64);
}
/**
* bitmap_read - read a value of n-bits from the memory region
* @map: address to the bitmap memory region
* @start: bit offset of the n-bit value
* @nbits: size of value in bits, nonzero, up to BITS_PER_LONG
*
* Returns: value of @nbits bits located at the @start bit offset within the
* @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
* value is undefined.
*/
static __always_inline
unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits)
{
size_t index = BIT_WORD(start);
unsigned long offset = start % BITS_PER_LONG;
unsigned long space = BITS_PER_LONG - offset;
unsigned long value_low, value_high;
if (unlikely(!nbits || nbits > BITS_PER_LONG))
return 0;
if (space >= nbits)
return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits);
value_low = map[index] & BITMAP_FIRST_WORD_MASK(start);
value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits);
return (value_low >> offset) | (value_high << space);
}
/**
* bitmap_write - write n-bit value within a memory region
* @map: address to the bitmap memory region
* @value: value to write, clamped to nbits
* @start: bit offset of the n-bit value
* @nbits: size of value in bits, nonzero, up to BITS_PER_LONG.
*
* bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(),
* i.e. bits beyond @nbits are ignored:
*
* for (bit = 0; bit < nbits; bit++)
* __assign_bit(start + bit, bitmap, val & BIT(bit));
*
* For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
*/
static __always_inline
void bitmap_write(unsigned long *map, unsigned long value,
unsigned long start, unsigned long nbits)
{
size_t index;
unsigned long offset;
unsigned long space;
unsigned long mask;
bool fit;
if (unlikely(!nbits || nbits > BITS_PER_LONG))
return;
mask = BITMAP_LAST_WORD_MASK(nbits);
value &= mask;
offset = start % BITS_PER_LONG;
space = BITS_PER_LONG - offset;
fit = space >= nbits;
index = BIT_WORD(start);
map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start));
map[index] |= value << offset;
if (fit)
return;
map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits);
map[index + 1] |= (value >> space);
}
#define bitmap_get_value8(map, start) \
bitmap_read(map, start, BITS_PER_BYTE)
#define bitmap_set_value8(map, value, start) \
bitmap_write(map, value, start, BITS_PER_BYTE)
#endif /* __ASSEMBLY__ */
#endif /* __LINUX_BITMAP_H */
// SPDX-License-Identifier: GPL-2.0
/*
* security/tomoyo/common.c
*
* Copyright (C) 2005-2011 NTT DATA CORPORATION
*/
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/string_helpers.h>
#include "common.h"
/* String table for operation mode. */
const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = {
[TOMOYO_CONFIG_DISABLED] = "disabled",
[TOMOYO_CONFIG_LEARNING] = "learning",
[TOMOYO_CONFIG_PERMISSIVE] = "permissive",
[TOMOYO_CONFIG_ENFORCING] = "enforcing"
};
/* String table for /sys/kernel/security/tomoyo/profile */
const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX
+ TOMOYO_MAX_MAC_CATEGORY_INDEX] = {
/* CONFIG::file group */
[TOMOYO_MAC_FILE_EXECUTE] = "execute",
[TOMOYO_MAC_FILE_OPEN] = "open",
[TOMOYO_MAC_FILE_CREATE] = "create",
[TOMOYO_MAC_FILE_UNLINK] = "unlink",
[TOMOYO_MAC_FILE_GETATTR] = "getattr",
[TOMOYO_MAC_FILE_MKDIR] = "mkdir",
[TOMOYO_MAC_FILE_RMDIR] = "rmdir",
[TOMOYO_MAC_FILE_MKFIFO] = "mkfifo",
[TOMOYO_MAC_FILE_MKSOCK] = "mksock",
[TOMOYO_MAC_FILE_TRUNCATE] = "truncate",
[TOMOYO_MAC_FILE_SYMLINK] = "symlink",
[TOMOYO_MAC_FILE_MKBLOCK] = "mkblock",
[TOMOYO_MAC_FILE_MKCHAR] = "mkchar",
[TOMOYO_MAC_FILE_LINK] = "link",
[TOMOYO_MAC_FILE_RENAME] = "rename",
[TOMOYO_MAC_FILE_CHMOD] = "chmod",
[TOMOYO_MAC_FILE_CHOWN] = "chown",
[TOMOYO_MAC_FILE_CHGRP] = "chgrp",
[TOMOYO_MAC_FILE_IOCTL] = "ioctl",
[TOMOYO_MAC_FILE_CHROOT] = "chroot",
[TOMOYO_MAC_FILE_MOUNT] = "mount",
[TOMOYO_MAC_FILE_UMOUNT] = "unmount",
[TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root",
/* CONFIG::network group */
[TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind",
[TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen",
[TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect",
[TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind",
[TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send",
[TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind",
[TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send",
[TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind",
[TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen",
[TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect",
[TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind",
[TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send",
[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind",
[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen",
[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect",
/* CONFIG::misc group */
[TOMOYO_MAC_ENVIRON] = "env",
/* CONFIG group */
[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file",
[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network",
[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc",
};
/* String table for conditions. */
const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = {
[TOMOYO_TASK_UID] = "task.uid",
[TOMOYO_TASK_EUID] = "task.euid",
[TOMOYO_TASK_SUID] = "task.suid",
[TOMOYO_TASK_FSUID] = "task.fsuid",
[TOMOYO_TASK_GID] = "task.gid",
[TOMOYO_TASK_EGID] = "task.egid",
[TOMOYO_TASK_SGID] = "task.sgid",
[TOMOYO_TASK_FSGID] = "task.fsgid",
[TOMOYO_TASK_PID] = "task.pid",
[TOMOYO_TASK_PPID] = "task.ppid",
[TOMOYO_EXEC_ARGC] = "exec.argc",
[TOMOYO_EXEC_ENVC] = "exec.envc",
[TOMOYO_TYPE_IS_SOCKET] = "socket",
[TOMOYO_TYPE_IS_SYMLINK] = "symlink",
[TOMOYO_TYPE_IS_FILE] = "file",
[TOMOYO_TYPE_IS_BLOCK_DEV] = "block",
[TOMOYO_TYPE_IS_DIRECTORY] = "directory",
[TOMOYO_TYPE_IS_CHAR_DEV] = "char",
[TOMOYO_TYPE_IS_FIFO] = "fifo",
[TOMOYO_MODE_SETUID] = "setuid",
[TOMOYO_MODE_SETGID] = "setgid",
[TOMOYO_MODE_STICKY] = "sticky",
[TOMOYO_MODE_OWNER_READ] = "owner_read",
[TOMOYO_MODE_OWNER_WRITE] = "owner_write",
[TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute",
[TOMOYO_MODE_GROUP_READ] = "group_read",
[TOMOYO_MODE_GROUP_WRITE] = "group_write",
[TOMOYO_MODE_GROUP_EXECUTE] = "group_execute",
[TOMOYO_MODE_OTHERS_READ] = "others_read",
[TOMOYO_MODE_OTHERS_WRITE] = "others_write",
[TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute",
[TOMOYO_EXEC_REALPATH] = "exec.realpath",
[TOMOYO_SYMLINK_TARGET] = "symlink.target",
[TOMOYO_PATH1_UID] = "path1.uid",
[TOMOYO_PATH1_GID] = "path1.gid",
[TOMOYO_PATH1_INO] = "path1.ino",
[TOMOYO_PATH1_MAJOR] = "path1.major",
[TOMOYO_PATH1_MINOR] = "path1.minor",
[TOMOYO_PATH1_PERM] = "path1.perm",
[TOMOYO_PATH1_TYPE] = "path1.type",
[TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major",
[TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor",
[TOMOYO_PATH2_UID] = "path2.uid",
[TOMOYO_PATH2_GID] = "path2.gid",
[TOMOYO_PATH2_INO] = "path2.ino",
[TOMOYO_PATH2_MAJOR] = "path2.major",
[TOMOYO_PATH2_MINOR] = "path2.minor",
[TOMOYO_PATH2_PERM] = "path2.perm",
[TOMOYO_PATH2_TYPE] = "path2.type",
[TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major",
[TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor",
[TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid",
[TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid",
[TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino",
[TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm",
[TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid",
[TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid",
[TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino",
[TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm",
};
/* String table for PREFERENCE keyword. */
static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = {
[TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log",
[TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry",
};
/* String table for path operation. */
const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = {
[TOMOYO_TYPE_EXECUTE] = "execute",
[TOMOYO_TYPE_READ] = "read",
[TOMOYO_TYPE_WRITE] = "write",
[TOMOYO_TYPE_APPEND] = "append",
[TOMOYO_TYPE_UNLINK] = "unlink",
[TOMOYO_TYPE_GETATTR] = "getattr",
[TOMOYO_TYPE_RMDIR] = "rmdir",
[TOMOYO_TYPE_TRUNCATE] = "truncate",
[TOMOYO_TYPE_SYMLINK] = "symlink",
[TOMOYO_TYPE_CHROOT] = "chroot",
[TOMOYO_TYPE_UMOUNT] = "unmount",
};
/* String table for socket's operation. */
const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = {
[TOMOYO_NETWORK_BIND] = "bind",
[TOMOYO_NETWORK_LISTEN] = "listen",
[TOMOYO_NETWORK_CONNECT] = "connect",
[TOMOYO_NETWORK_SEND] = "send",
};
/* String table for categories. */
static const char * const tomoyo_category_keywords
[TOMOYO_MAX_MAC_CATEGORY_INDEX] = {
[TOMOYO_MAC_CATEGORY_FILE] = "file",
[TOMOYO_MAC_CATEGORY_NETWORK] = "network",
[TOMOYO_MAC_CATEGORY_MISC] = "misc",
};
/* Permit policy management by non-root user? */
static bool tomoyo_manage_by_non_root;
/* Utility functions. */
/**
* tomoyo_addprintf - strncat()-like-snprintf().
*
* @buffer: Buffer to write to. Must be '\0'-terminated.
* @len: Size of @buffer.
* @fmt: The printf()'s format string, followed by parameters.
*
* Returns nothing.
*/
__printf(3, 4)
static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...)
{
va_list args;
const int pos = strlen(buffer);
va_start(args, fmt);
vsnprintf(buffer + pos, len - pos - 1, fmt, args);
va_end(args);
}
/**
* tomoyo_flush - Flush queued string to userspace's buffer.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns true if all data was flushed, false otherwise.
*/
static bool tomoyo_flush(struct tomoyo_io_buffer *head)
{
while (head->r.w_pos) {
const char *w = head->r.w[0];
size_t len = strlen(w);
if (len) {
if (len > head->read_user_buf_avail)
len = head->read_user_buf_avail;
if (!len)
return false;
if (copy_to_user(head->read_user_buf, w, len))
return false;
head->read_user_buf_avail -= len;
head->read_user_buf += len;
w += len;
}
head->r.w[0] = w;
if (*w)
return false;
/* Add '\0' for audit logs and query. */
if (head->poll) {
if (!head->read_user_buf_avail ||
copy_to_user(head->read_user_buf, "", 1))
return false;
head->read_user_buf_avail--;
head->read_user_buf++;
}
head->r.w_pos--;
for (len = 0; len < head->r.w_pos; len++)
head->r.w[len] = head->r.w[len + 1];
}
head->r.avail = 0;
return true;
}
/**
* tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @string: String to print.
*
* Note that @string has to be kept valid until @head is kfree()d.
* This means that char[] allocated on stack memory cannot be passed to
* this function. Use tomoyo_io_printf() for char[] allocated on stack memory.
*/
static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string)
{
if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) {
head->r.w[head->r.w_pos++] = string;
tomoyo_flush(head);
} else
WARN_ON(1);
}
static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt,
...) __printf(2, 3);
/**
* tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @fmt: The printf()'s format string, followed by parameters.
*/
static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt,
...)
{
va_list args;
size_t len;
size_t pos = head->r.avail;
int size = head->readbuf_size - pos;
if (size <= 0)
return;
va_start(args, fmt);
len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1;
va_end(args);
if (pos + len >= head->readbuf_size) {
WARN_ON(1);
return;
}
head->r.avail += len;
tomoyo_set_string(head, head->read_buf + pos);
}
/**
* tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static void tomoyo_set_space(struct tomoyo_io_buffer *head)
{
tomoyo_set_string(head, " ");
}
/**
* tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static bool tomoyo_set_lf(struct tomoyo_io_buffer *head)
{
tomoyo_set_string(head, "\n");
return !head->r.w_pos;
}
/**
* tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static void tomoyo_set_slash(struct tomoyo_io_buffer *head)
{
tomoyo_set_string(head, "/");
}
/* List of namespaces. */
LIST_HEAD(tomoyo_namespace_list);
/* True if namespace other than tomoyo_kernel_namespace is defined. */
static bool tomoyo_namespace_enabled;
/**
* tomoyo_init_policy_namespace - Initialize namespace.
*
* @ns: Pointer to "struct tomoyo_policy_namespace".
*
* Returns nothing.
*/
void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns)
{
unsigned int idx;
for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++)
INIT_LIST_HEAD(&ns->acl_group[idx]);
for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++)
INIT_LIST_HEAD(&ns->group_list[idx]);
for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++)
INIT_LIST_HEAD(&ns->policy_list[idx]);
ns->profile_version = 20150505;
tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list);
list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list);
}
/**
* tomoyo_print_namespace - Print namespace header.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static void tomoyo_print_namespace(struct tomoyo_io_buffer *head)
{
if (!tomoyo_namespace_enabled)
return;
tomoyo_set_string(head,
container_of(head->r.ns,
struct tomoyo_policy_namespace,
namespace_list)->name);
tomoyo_set_space(head);
}
/**
* tomoyo_print_name_union - Print a tomoyo_name_union.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @ptr: Pointer to "struct tomoyo_name_union".
*/
static void tomoyo_print_name_union(struct tomoyo_io_buffer *head,
const struct tomoyo_name_union *ptr)
{
tomoyo_set_space(head);
if (ptr->group) {
tomoyo_set_string(head, "@");
tomoyo_set_string(head, ptr->group->group_name->name);
} else {
tomoyo_set_string(head, ptr->filename->name);
}
}
/**
* tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @ptr: Pointer to "struct tomoyo_name_union".
*
* Returns nothing.
*/
static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head,
const struct tomoyo_name_union *ptr)
{
if (ptr->group) {
tomoyo_set_string(head, "@");
tomoyo_set_string(head, ptr->group->group_name->name);
} else {
tomoyo_set_string(head, "\"");
tomoyo_set_string(head, ptr->filename->name);
tomoyo_set_string(head, "\"");
}
}
/**
* tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @ptr: Pointer to "struct tomoyo_number_union".
*
* Returns nothing.
*/
static void tomoyo_print_number_union_nospace
(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr)
{
if (ptr->group) {
tomoyo_set_string(head, "@");
tomoyo_set_string(head, ptr->group->group_name->name);
} else {
int i;
unsigned long min = ptr->values[0];
const unsigned long max = ptr->values[1];
u8 min_type = ptr->value_type[0];
const u8 max_type = ptr->value_type[1];
char buffer[128];
buffer[0] = '\0';
for (i = 0; i < 2; i++) {
switch (min_type) {
case TOMOYO_VALUE_TYPE_HEXADECIMAL:
tomoyo_addprintf(buffer, sizeof(buffer),
"0x%lX", min);
break;
case TOMOYO_VALUE_TYPE_OCTAL:
tomoyo_addprintf(buffer, sizeof(buffer),
"0%lo", min);
break;
default:
tomoyo_addprintf(buffer, sizeof(buffer), "%lu",
min);
break;
}
if (min == max && min_type == max_type)
break;
tomoyo_addprintf(buffer, sizeof(buffer), "-");
min_type = max_type;
min = max;
}
tomoyo_io_printf(head, "%s", buffer);
}
}
/**
* tomoyo_print_number_union - Print a tomoyo_number_union.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @ptr: Pointer to "struct tomoyo_number_union".
*
* Returns nothing.
*/
static void tomoyo_print_number_union(struct tomoyo_io_buffer *head,
const struct tomoyo_number_union *ptr)
{
tomoyo_set_space(head);
tomoyo_print_number_union_nospace(head, ptr);
}
/**
* tomoyo_assign_profile - Create a new profile.
*
* @ns: Pointer to "struct tomoyo_policy_namespace".
* @profile: Profile number to create.
*
* Returns pointer to "struct tomoyo_profile" on success, NULL otherwise.
*/
static struct tomoyo_profile *tomoyo_assign_profile
(struct tomoyo_policy_namespace *ns, const unsigned int profile)
{
struct tomoyo_profile *ptr;
struct tomoyo_profile *entry;
if (profile >= TOMOYO_MAX_PROFILES)
return NULL;
ptr = ns->profile_ptr[profile];
if (ptr)
return ptr;
entry = kzalloc(sizeof(*entry), GFP_NOFS | __GFP_NOWARN);
if (mutex_lock_interruptible(&tomoyo_policy_lock))
goto out;
ptr = ns->profile_ptr[profile];
if (!ptr && tomoyo_memory_ok(entry)) {
ptr = entry;
ptr->default_config = TOMOYO_CONFIG_DISABLED |
TOMOYO_CONFIG_WANT_GRANT_LOG |
TOMOYO_CONFIG_WANT_REJECT_LOG;
memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT,
sizeof(ptr->config));
ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] =
CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG;
ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] =
CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY;
mb(); /* Avoid out-of-order execution. */
ns->profile_ptr[profile] = ptr;
entry = NULL;
}
mutex_unlock(&tomoyo_policy_lock);
out:
kfree(entry);
return ptr;
}
/**
* tomoyo_profile - Find a profile.
*
* @ns: Pointer to "struct tomoyo_policy_namespace".
* @profile: Profile number to find.
*
* Returns pointer to "struct tomoyo_profile".
*/
struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns,
const u8 profile)
{
static struct tomoyo_profile tomoyo_null_profile;
struct tomoyo_profile *ptr = ns->profile_ptr[profile];
if (!ptr)
ptr = &tomoyo_null_profile;
return ptr;
}
/**
* tomoyo_find_yesno - Find values for specified keyword.
*
* @string: String to check.
* @find: Name of keyword.
*
* Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise.
*/
static s8 tomoyo_find_yesno(const char *string, const char *find)
{
const char *cp = strstr(string, find);
if (cp) {
cp += strlen(find);
if (!strncmp(cp, "=yes", 4))
return 1;
else if (!strncmp(cp, "=no", 3))
return 0;
}
return -1;
}
/**
* tomoyo_set_uint - Set value for specified preference.
*
* @i: Pointer to "unsigned int".
* @string: String to check.
* @find: Name of keyword.
*
* Returns nothing.
*/
static void tomoyo_set_uint(unsigned int *i, const char *string,
const char *find)
{
const char *cp = strstr(string, find);
if (cp)
sscanf(cp + strlen(find), "=%u", i);
}
/**
* tomoyo_set_mode - Set mode for specified profile.
*
* @name: Name of functionality.
* @value: Mode for @name.
* @profile: Pointer to "struct tomoyo_profile".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_set_mode(char *name, const char *value,
struct tomoyo_profile *profile)
{
u8 i;
u8 config;
if (!strcmp(name, "CONFIG")) {
i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX;
config = profile->default_config;
} else if (tomoyo_str_starts(&name, "CONFIG::")) {
config = 0;
for (i = 0; i < TOMOYO_MAX_MAC_INDEX
+ TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) {
int len = 0;
if (i < TOMOYO_MAX_MAC_INDEX) {
const u8 c = tomoyo_index2category[i];
const char *category =
tomoyo_category_keywords[c];
len = strlen(category);
if (strncmp(name, category, len) ||
name[len++] != ':' || name[len++] != ':')
continue;
}
if (strcmp(name + len, tomoyo_mac_keywords[i]))
continue;
config = profile->config[i];
break;
}
if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX)
return -EINVAL;
} else {
return -EINVAL;
}
if (strstr(value, "use_default")) {
config = TOMOYO_CONFIG_USE_DEFAULT;
} else {
u8 mode;
for (mode = 0; mode < 4; mode++)
if (strstr(value, tomoyo_mode[mode]))
/*
* Update lower 3 bits in order to distinguish
* 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'.
*/
config = (config & ~7) | mode;
if (config != TOMOYO_CONFIG_USE_DEFAULT) {
switch (tomoyo_find_yesno(value, "grant_log")) {
case 1:
config |= TOMOYO_CONFIG_WANT_GRANT_LOG;
break;
case 0:
config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG;
break;
}
switch (tomoyo_find_yesno(value, "reject_log")) {
case 1:
config |= TOMOYO_CONFIG_WANT_REJECT_LOG;
break;
case 0:
config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG;
break;
}
}
}
if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX)
profile->config[i] = config;
else if (config != TOMOYO_CONFIG_USE_DEFAULT)
profile->default_config = config;
return 0;
}
/**
* tomoyo_write_profile - Write profile table.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_write_profile(struct tomoyo_io_buffer *head)
{
char *data = head->write_buf;
unsigned int i;
char *cp;
struct tomoyo_profile *profile;
if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version)
== 1)
return 0;
i = simple_strtoul(data, &cp, 10);
if (*cp != '-')
return -EINVAL;
data = cp + 1;
profile = tomoyo_assign_profile(head->w.ns, i);
if (!profile)
return -EINVAL;
cp = strchr(data, '=');
if (!cp)
return -EINVAL;
*cp++ = '\0';
if (!strcmp(data, "COMMENT")) {
static DEFINE_SPINLOCK(lock);
const struct tomoyo_path_info *new_comment
= tomoyo_get_name(cp);
const struct tomoyo_path_info *old_comment;
if (!new_comment)
return -ENOMEM;
spin_lock(&lock);
old_comment = profile->comment;
profile->comment = new_comment;
spin_unlock(&lock);
tomoyo_put_name(old_comment);
return 0;
}
if (!strcmp(data, "PREFERENCE")) {
for (i = 0; i < TOMOYO_MAX_PREF; i++)
tomoyo_set_uint(&profile->pref[i], cp,
tomoyo_pref_keywords[i]);
return 0;
}
return tomoyo_set_mode(data, cp, profile);
}
/**
* tomoyo_print_config - Print mode for specified functionality.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @config: Mode for that functionality.
*
* Returns nothing.
*
* Caller prints functionality's name.
*/
static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config)
{
tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n",
tomoyo_mode[config & 3],
str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG),
str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG));
}
/**
* tomoyo_read_profile - Read profile table.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static void tomoyo_read_profile(struct tomoyo_io_buffer *head)
{
u8 index;
struct tomoyo_policy_namespace *ns =
container_of(head->r.ns, typeof(*ns), namespace_list);
const struct tomoyo_profile *profile;
if (head->r.eof)
return;
next:
index = head->r.index;
profile = ns->profile_ptr[index];
switch (head->r.step) {
case 0:
tomoyo_print_namespace(head);
tomoyo_io_printf(head, "PROFILE_VERSION=%u\n",
ns->profile_version);
head->r.step++;
break;
case 1:
for ( ; head->r.index < TOMOYO_MAX_PROFILES;
head->r.index++)
if (ns->profile_ptr[head->r.index])
break;
if (head->r.index == TOMOYO_MAX_PROFILES) {
head->r.eof = true;
return;
}
head->r.step++;
break;
case 2:
{
u8 i;
const struct tomoyo_path_info *comment =
profile->comment;
tomoyo_print_namespace(head);
tomoyo_io_printf(head, "%u-COMMENT=", index);
tomoyo_set_string(head, comment ? comment->name : "");
tomoyo_set_lf(head);
tomoyo_print_namespace(head);
tomoyo_io_printf(head, "%u-PREFERENCE={ ", index);
for (i = 0; i < TOMOYO_MAX_PREF; i++)
tomoyo_io_printf(head, "%s=%u ",
tomoyo_pref_keywords[i],
profile->pref[i]);
tomoyo_set_string(head, "}\n");
head->r.step++;
}
break;
case 3:
{
tomoyo_print_namespace(head);
tomoyo_io_printf(head, "%u-%s", index, "CONFIG");
tomoyo_print_config(head, profile->default_config);
head->r.bit = 0;
head->r.step++;
}
break;
case 4:
for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX
+ TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) {
const u8 i = head->r.bit;
const u8 config = profile->config[i];
if (config == TOMOYO_CONFIG_USE_DEFAULT)
continue;
tomoyo_print_namespace(head);
if (i < TOMOYO_MAX_MAC_INDEX)
tomoyo_io_printf(head, "%u-CONFIG::%s::%s",
index,
tomoyo_category_keywords
[tomoyo_index2category[i]],
tomoyo_mac_keywords[i]);
else
tomoyo_io_printf(head, "%u-CONFIG::%s", index,
tomoyo_mac_keywords[i]);
tomoyo_print_config(head, config);
head->r.bit++;
break;
}
if (head->r.bit == TOMOYO_MAX_MAC_INDEX
+ TOMOYO_MAX_MAC_CATEGORY_INDEX) {
head->r.index++;
head->r.step = 1;
}
break;
}
if (tomoyo_flush(head))
goto next;
}
/**
* tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry.
*
* @a: Pointer to "struct tomoyo_acl_head".
* @b: Pointer to "struct tomoyo_acl_head".
*
* Returns true if @a == @b, false otherwise.
*/
static bool tomoyo_same_manager(const struct tomoyo_acl_head *a,
const struct tomoyo_acl_head *b)
{
return container_of(a, struct tomoyo_manager, head)->manager ==
container_of(b, struct tomoyo_manager, head)->manager;
}
/**
* tomoyo_update_manager_entry - Add a manager entry.
*
* @manager: The path to manager or the domainnamme.
* @is_delete: True if it is a delete request.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_update_manager_entry(const char *manager,
const bool is_delete)
{
struct tomoyo_manager e = { };
struct tomoyo_acl_param param = {
/* .ns = &tomoyo_kernel_namespace, */
.is_delete = is_delete,
.list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER],
};
int error = is_delete ? -ENOENT : -ENOMEM;
if (!tomoyo_correct_domain(manager) &&
!tomoyo_correct_word(manager))
return -EINVAL;
e.manager = tomoyo_get_name(manager);
if (e.manager) {
error = tomoyo_update_policy(&e.head, sizeof(e), ¶m,
tomoyo_same_manager);
tomoyo_put_name(e.manager);
}
return error;
}
/**
* tomoyo_write_manager - Write manager policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_write_manager(struct tomoyo_io_buffer *head)
{
char *data = head->write_buf;
if (!strcmp(data, "manage_by_non_root")) {
tomoyo_manage_by_non_root = !head->w.is_delete;
return 0;
}
return tomoyo_update_manager_entry(data, head->w.is_delete);
}
/**
* tomoyo_read_manager - Read manager policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Caller holds tomoyo_read_lock().
*/
static void tomoyo_read_manager(struct tomoyo_io_buffer *head)
{
if (head->r.eof)
return;
list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) {
struct tomoyo_manager *ptr =
list_entry(head->r.acl, typeof(*ptr), head.list);
if (ptr->head.is_deleted)
continue;
if (!tomoyo_flush(head))
return;
tomoyo_set_string(head, ptr->manager->name);
tomoyo_set_lf(head);
}
head->r.eof = true;
}
/**
* tomoyo_manager - Check whether the current process is a policy manager.
*
* Returns true if the current process is permitted to modify policy
* via /sys/kernel/security/tomoyo/ interface.
*
* Caller holds tomoyo_read_lock().
*/
static bool tomoyo_manager(void)
{
struct tomoyo_manager *ptr;
const char *exe;
const struct task_struct *task = current;
const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname;
bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING);
if (!tomoyo_policy_loaded)
return true;
if (!tomoyo_manage_by_non_root &&
(!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) ||
!uid_eq(task->cred->euid, GLOBAL_ROOT_UID)))
return false;
exe = tomoyo_get_exe();
if (!exe)
return false;
list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list,
srcu_read_lock_held(&tomoyo_ss)) {
if (!ptr->head.is_deleted &&
(!tomoyo_pathcmp(domainname, ptr->manager) ||
!strcmp(exe, ptr->manager->name))) {
found = true;
break;
}
}
if (!found) { /* Reduce error messages. */
static pid_t last_pid;
const pid_t pid = current->pid;
if (last_pid != pid) {
pr_warn("%s ( %s ) is not permitted to update policies.\n",
domainname->name, exe);
last_pid = pid;
}
}
kfree(exe);
return found;
}
static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
(unsigned int serial);
/**
* tomoyo_select_domain - Parse select command.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @data: String to parse.
*
* Returns true on success, false otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static bool tomoyo_select_domain(struct tomoyo_io_buffer *head,
const char *data)
{
unsigned int pid;
struct tomoyo_domain_info *domain = NULL;
bool global_pid = false;
if (strncmp(data, "select ", 7))
return false;
data += 7;
if (sscanf(data, "pid=%u", &pid) == 1 ||
(global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) {
struct task_struct *p;
rcu_read_lock();
if (global_pid)
p = find_task_by_pid_ns(pid, &init_pid_ns);
else
p = find_task_by_vpid(pid);
if (p)
domain = tomoyo_task(p)->domain_info;
rcu_read_unlock();
} else if (!strncmp(data, "domain=", 7)) {
if (tomoyo_domain_def(data + 7))
domain = tomoyo_find_domain(data + 7);
} else if (sscanf(data, "Q=%u", &pid) == 1) {
domain = tomoyo_find_domain_by_qid(pid);
} else
return false;
head->w.domain = domain;
/* Accessing read_buf is safe because head->io_sem is held. */
if (!head->read_buf)
return true; /* Do nothing if open(O_WRONLY). */
memset(&head->r, 0, sizeof(head->r));
head->r.print_this_domain_only = true;
if (domain)
head->r.domain = &domain->list;
else
head->r.eof = true;
tomoyo_io_printf(head, "# select %s\n", data);
if (domain && domain->is_deleted)
tomoyo_io_printf(head, "# This is a deleted domain.\n");
return true;
}
/**
* tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b, false otherwise.
*/
static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head);
const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head);
return p1->domainname == p2->domainname;
}
/**
* tomoyo_write_task - Update task related list.
*
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_write_task(struct tomoyo_acl_param *param)
{
int error = -EINVAL;
if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) {
struct tomoyo_task_acl e = {
.head.type = TOMOYO_TYPE_MANUAL_TASK_ACL,
.domainname = tomoyo_get_domainname(param),
};
if (e.domainname)
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_task_acl,
NULL);
tomoyo_put_name(e.domainname);
}
return error;
}
/**
* tomoyo_delete_domain - Delete a domain.
*
* @domainname: The name of domain.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_delete_domain(char *domainname)
{
struct tomoyo_domain_info *domain;
struct tomoyo_path_info name;
name.name = domainname;
tomoyo_fill_path_info(&name);
if (mutex_lock_interruptible(&tomoyo_policy_lock))
return -EINTR;
/* Is there an active domain? */
list_for_each_entry_rcu(domain, &tomoyo_domain_list, list,
srcu_read_lock_held(&tomoyo_ss)) {
/* Never delete tomoyo_kernel_domain */
if (domain == &tomoyo_kernel_domain)
continue;
if (domain->is_deleted ||
tomoyo_pathcmp(domain->domainname, &name))
continue;
domain->is_deleted = true;
break;
}
mutex_unlock(&tomoyo_policy_lock);
return 0;
}
/**
* tomoyo_write_domain2 - Write domain policy.
*
* @ns: Pointer to "struct tomoyo_policy_namespace".
* @list: Pointer to "struct list_head".
* @data: Policy to be interpreted.
* @is_delete: True if it is a delete request.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns,
struct list_head *list, char *data,
const bool is_delete)
{
struct tomoyo_acl_param param = {
.ns = ns,
.list = list,
.data = data,
.is_delete = is_delete,
};
static const struct {
const char *keyword;
int (*write)(struct tomoyo_acl_param *param);
} tomoyo_callback[5] = {
{ "file ", tomoyo_write_file },
{ "network inet ", tomoyo_write_inet_network },
{ "network unix ", tomoyo_write_unix_network },
{ "misc ", tomoyo_write_misc },
{ "task ", tomoyo_write_task },
};
u8 i;
for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) {
if (!tomoyo_str_starts(¶m.data,
tomoyo_callback[i].keyword))
continue;
return tomoyo_callback[i].write(¶m);
}
return -EINVAL;
}
/* String table for domain flags. */
const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = {
[TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n",
[TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n",
};
/**
* tomoyo_write_domain - Write domain policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_write_domain(struct tomoyo_io_buffer *head)
{
char *data = head->write_buf;
struct tomoyo_policy_namespace *ns;
struct tomoyo_domain_info *domain = head->w.domain;
const bool is_delete = head->w.is_delete;
bool is_select = !is_delete && tomoyo_str_starts(&data, "select ");
unsigned int idx;
if (*data == '<') {
int ret = 0;
domain = NULL;
if (is_delete)
ret = tomoyo_delete_domain(data);
else if (is_select)
domain = tomoyo_find_domain(data);
else
domain = tomoyo_assign_domain(data, false);
head->w.domain = domain;
return ret;
}
if (!domain)
return -EINVAL;
ns = domain->ns;
if (sscanf(data, "use_profile %u", &idx) == 1
&& idx < TOMOYO_MAX_PROFILES) {
if (!tomoyo_policy_loaded || ns->profile_ptr[idx])
if (!is_delete)
domain->profile = (u8) idx;
return 0;
}
if (sscanf(data, "use_group %u\n", &idx) == 1
&& idx < TOMOYO_MAX_ACL_GROUPS) {
if (!is_delete)
set_bit(idx, domain->group);
else
clear_bit(idx, domain->group);
return 0;
}
for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) {
const char *cp = tomoyo_dif[idx];
if (strncmp(data, cp, strlen(cp) - 1))
continue;
domain->flags[idx] = !is_delete;
return 0;
}
return tomoyo_write_domain2(ns, &domain->acl_info_list, data,
is_delete);
}
/**
* tomoyo_print_condition - Print condition part.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @cond: Pointer to "struct tomoyo_condition".
*
* Returns true on success, false otherwise.
*/
static bool tomoyo_print_condition(struct tomoyo_io_buffer *head,
const struct tomoyo_condition *cond)
{
switch (head->r.cond_step) {
case 0:
head->r.cond_index = 0;
head->r.cond_step++;
if (cond->transit) {
tomoyo_set_space(head);
tomoyo_set_string(head, cond->transit->name);
}
fallthrough;
case 1:
{
const u16 condc = cond->condc;
const struct tomoyo_condition_element *condp =
(typeof(condp)) (cond + 1);
const struct tomoyo_number_union *numbers_p =
(typeof(numbers_p)) (condp + condc);
const struct tomoyo_name_union *names_p =
(typeof(names_p))
(numbers_p + cond->numbers_count);
const struct tomoyo_argv *argv =
(typeof(argv)) (names_p + cond->names_count);
const struct tomoyo_envp *envp =
(typeof(envp)) (argv + cond->argc);
u16 skip;
for (skip = 0; skip < head->r.cond_index; skip++) {
const u8 left = condp->left;
const u8 right = condp->right;
condp++;
switch (left) {
case TOMOYO_ARGV_ENTRY:
argv++;
continue;
case TOMOYO_ENVP_ENTRY:
envp++;
continue;
case TOMOYO_NUMBER_UNION:
numbers_p++;
break;
}
switch (right) {
case TOMOYO_NAME_UNION:
names_p++;
break;
case TOMOYO_NUMBER_UNION:
numbers_p++;
break;
}
}
while (head->r.cond_index < condc) {
const u8 match = condp->equals;
const u8 left = condp->left;
const u8 right = condp->right;
if (!tomoyo_flush(head))
return false;
condp++;
head->r.cond_index++;
tomoyo_set_space(head);
switch (left) {
case TOMOYO_ARGV_ENTRY:
tomoyo_io_printf(head,
"exec.argv[%lu]%s=\"",
argv->index, argv->is_not ? "!" : "");
tomoyo_set_string(head,
argv->value->name);
tomoyo_set_string(head, "\"");
argv++;
continue;
case TOMOYO_ENVP_ENTRY:
tomoyo_set_string(head,
"exec.envp[\"");
tomoyo_set_string(head,
envp->name->name);
tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : "");
if (envp->value) {
tomoyo_set_string(head, "\"");
tomoyo_set_string(head, envp->value->name);
tomoyo_set_string(head, "\"");
} else {
tomoyo_set_string(head,
"NULL");
}
envp++;
continue;
case TOMOYO_NUMBER_UNION:
tomoyo_print_number_union_nospace
(head, numbers_p++);
break;
default:
tomoyo_set_string(head,
tomoyo_condition_keyword[left]);
break;
}
tomoyo_set_string(head, match ? "=" : "!=");
switch (right) {
case TOMOYO_NAME_UNION:
tomoyo_print_name_union_quoted
(head, names_p++);
break;
case TOMOYO_NUMBER_UNION:
tomoyo_print_number_union_nospace
(head, numbers_p++);
break;
default:
tomoyo_set_string(head,
tomoyo_condition_keyword[right]);
break;
}
}
}
head->r.cond_step++;
fallthrough;
case 2:
if (!tomoyo_flush(head))
break;
head->r.cond_step++;
fallthrough;
case 3:
if (cond->grant_log != TOMOYO_GRANTLOG_AUTO)
tomoyo_io_printf(head, " grant_log=%s",
str_yes_no(cond->grant_log ==
TOMOYO_GRANTLOG_YES));
tomoyo_set_lf(head);
return true;
}
return false;
}
/**
* tomoyo_set_group - Print "acl_group " header keyword and category name.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @category: Category name.
*
* Returns nothing.
*/
static void tomoyo_set_group(struct tomoyo_io_buffer *head,
const char *category)
{
if (head->type == TOMOYO_EXCEPTIONPOLICY) {
tomoyo_print_namespace(head);
tomoyo_io_printf(head, "acl_group %u ",
head->r.acl_group_index);
}
tomoyo_set_string(head, category);
}
/**
* tomoyo_print_entry - Print an ACL entry.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @acl: Pointer to an ACL entry.
*
* Returns true on success, false otherwise.
*/
static bool tomoyo_print_entry(struct tomoyo_io_buffer *head,
struct tomoyo_acl_info *acl)
{
const u8 acl_type = acl->type;
bool first = true;
u8 bit;
if (head->r.print_cond_part)
goto print_cond_part;
if (acl->is_deleted)
return true;
if (!tomoyo_flush(head))
return false;
else if (acl_type == TOMOYO_TYPE_PATH_ACL) {
struct tomoyo_path_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u16 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (head->r.print_transition_related_only &&
bit != TOMOYO_TYPE_EXECUTE)
continue;
if (first) {
tomoyo_set_group(head, "file ");
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_path_keyword[bit]);
}
if (first)
return true;
tomoyo_print_name_union(head, &ptr->name);
} else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) {
struct tomoyo_task_acl *ptr =
container_of(acl, typeof(*ptr), head);
tomoyo_set_group(head, "task ");
tomoyo_set_string(head, "manual_domain_transition ");
tomoyo_set_string(head, ptr->domainname->name);
} else if (head->r.print_transition_related_only) {
return true;
} else if (acl_type == TOMOYO_TYPE_PATH2_ACL) {
struct tomoyo_path2_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u8 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (first) {
tomoyo_set_group(head, "file ");
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_mac_keywords
[tomoyo_pp2mac[bit]]);
}
if (first)
return true;
tomoyo_print_name_union(head, &ptr->name1);
tomoyo_print_name_union(head, &ptr->name2);
} else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) {
struct tomoyo_path_number_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u8 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (first) {
tomoyo_set_group(head, "file ");
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_mac_keywords
[tomoyo_pn2mac[bit]]);
}
if (first)
return true;
tomoyo_print_name_union(head, &ptr->name);
tomoyo_print_number_union(head, &ptr->number);
} else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) {
struct tomoyo_mkdev_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u8 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (first) {
tomoyo_set_group(head, "file ");
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_mac_keywords
[tomoyo_pnnn2mac[bit]]);
}
if (first)
return true;
tomoyo_print_name_union(head, &ptr->name);
tomoyo_print_number_union(head, &ptr->mode);
tomoyo_print_number_union(head, &ptr->major);
tomoyo_print_number_union(head, &ptr->minor);
} else if (acl_type == TOMOYO_TYPE_INET_ACL) {
struct tomoyo_inet_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u8 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (first) {
tomoyo_set_group(head, "network inet ");
tomoyo_set_string(head, tomoyo_proto_keyword
[ptr->protocol]);
tomoyo_set_space(head);
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_socket_keyword[bit]);
}
if (first)
return true;
tomoyo_set_space(head);
if (ptr->address.group) {
tomoyo_set_string(head, "@");
tomoyo_set_string(head, ptr->address.group->group_name
->name);
} else {
char buf[128];
tomoyo_print_ip(buf, sizeof(buf), &ptr->address);
tomoyo_io_printf(head, "%s", buf);
}
tomoyo_print_number_union(head, &ptr->port);
} else if (acl_type == TOMOYO_TYPE_UNIX_ACL) {
struct tomoyo_unix_acl *ptr =
container_of(acl, typeof(*ptr), head);
const u8 perm = ptr->perm;
for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) {
if (!(perm & (1 << bit)))
continue;
if (first) {
tomoyo_set_group(head, "network unix ");
tomoyo_set_string(head, tomoyo_proto_keyword
[ptr->protocol]);
tomoyo_set_space(head);
first = false;
} else {
tomoyo_set_slash(head);
}
tomoyo_set_string(head, tomoyo_socket_keyword[bit]);
}
if (first)
return true;
tomoyo_print_name_union(head, &ptr->name);
} else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) {
struct tomoyo_mount_acl *ptr =
container_of(acl, typeof(*ptr), head);
tomoyo_set_group(head, "file mount");
tomoyo_print_name_union(head, &ptr->dev_name);
tomoyo_print_name_union(head, &ptr->dir_name);
tomoyo_print_name_union(head, &ptr->fs_type);
tomoyo_print_number_union(head, &ptr->flags);
} else if (acl_type == TOMOYO_TYPE_ENV_ACL) {
struct tomoyo_env_acl *ptr =
container_of(acl, typeof(*ptr), head);
tomoyo_set_group(head, "misc env ");
tomoyo_set_string(head, ptr->env->name);
}
if (acl->cond) {
head->r.print_cond_part = true;
head->r.cond_step = 0;
if (!tomoyo_flush(head))
return false;
print_cond_part:
if (!tomoyo_print_condition(head, acl->cond))
return false;
head->r.print_cond_part = false;
} else {
tomoyo_set_lf(head);
}
return true;
}
/**
* tomoyo_read_domain2 - Read domain policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @list: Pointer to "struct list_head".
*
* Caller holds tomoyo_read_lock().
*
* Returns true on success, false otherwise.
*/
static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head,
struct list_head *list)
{
list_for_each_cookie(head->r.acl, list) {
struct tomoyo_acl_info *ptr =
list_entry(head->r.acl, typeof(*ptr), list);
if (!tomoyo_print_entry(head, ptr))
return false;
}
head->r.acl = NULL;
return true;
}
/**
* tomoyo_read_domain - Read domain policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Caller holds tomoyo_read_lock().
*/
static void tomoyo_read_domain(struct tomoyo_io_buffer *head)
{
if (head->r.eof)
return;
list_for_each_cookie(head->r.domain, &tomoyo_domain_list) {
struct tomoyo_domain_info *domain =
list_entry(head->r.domain, typeof(*domain), list);
u8 i;
switch (head->r.step) {
case 0:
if (domain->is_deleted &&
!head->r.print_this_domain_only)
continue;
/* Print domainname and flags. */
tomoyo_set_string(head, domain->domainname->name);
tomoyo_set_lf(head);
tomoyo_io_printf(head, "use_profile %u\n",
domain->profile);
for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++)
if (domain->flags[i])
tomoyo_set_string(head, tomoyo_dif[i]);
head->r.index = 0;
head->r.step++;
fallthrough;
case 1:
while (head->r.index < TOMOYO_MAX_ACL_GROUPS) {
i = head->r.index++;
if (!test_bit(i, domain->group))
continue;
tomoyo_io_printf(head, "use_group %u\n", i);
if (!tomoyo_flush(head))
return;
}
head->r.index = 0;
head->r.step++;
tomoyo_set_lf(head);
fallthrough;
case 2:
if (!tomoyo_read_domain2(head, &domain->acl_info_list))
return;
head->r.step++;
if (!tomoyo_set_lf(head))
return;
fallthrough;
case 3:
head->r.step = 0;
if (head->r.print_this_domain_only)
goto done;
}
}
done:
head->r.eof = true;
}
/**
* tomoyo_write_pid: Specify PID to obtain domainname.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0.
*/
static int tomoyo_write_pid(struct tomoyo_io_buffer *head)
{
head->r.eof = false;
return 0;
}
/**
* tomoyo_read_pid - Get domainname of the specified PID.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns the domainname which the specified PID is in on success,
* empty string otherwise.
* The PID is specified by tomoyo_write_pid() so that the user can obtain
* using read()/write() interface rather than sysctl() interface.
*/
static void tomoyo_read_pid(struct tomoyo_io_buffer *head)
{
char *buf = head->write_buf;
bool global_pid = false;
unsigned int pid;
struct task_struct *p;
struct tomoyo_domain_info *domain = NULL;
/* Accessing write_buf is safe because head->io_sem is held. */
if (!buf) {
head->r.eof = true;
return; /* Do nothing if open(O_RDONLY). */
}
if (head->r.w_pos || head->r.eof)
return;
head->r.eof = true;
if (tomoyo_str_starts(&buf, "global-pid "))
global_pid = true;
if (kstrtouint(buf, 10, &pid))
return;
rcu_read_lock();
if (global_pid)
p = find_task_by_pid_ns(pid, &init_pid_ns);
else
p = find_task_by_vpid(pid);
if (p)
domain = tomoyo_task(p)->domain_info;
rcu_read_unlock();
if (!domain)
return;
tomoyo_io_printf(head, "%u %u ", pid, domain->profile);
tomoyo_set_string(head, domain->domainname->name);
}
/* String table for domain transition control keywords. */
static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = {
[TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ",
[TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ",
[TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ",
[TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ",
[TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ",
[TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ",
};
/* String table for grouping keywords. */
static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = {
[TOMOYO_PATH_GROUP] = "path_group ",
[TOMOYO_NUMBER_GROUP] = "number_group ",
[TOMOYO_ADDRESS_GROUP] = "address_group ",
};
/**
* tomoyo_write_exception - Write exception policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_write_exception(struct tomoyo_io_buffer *head)
{
const bool is_delete = head->w.is_delete;
struct tomoyo_acl_param param = {
.ns = head->w.ns,
.is_delete = is_delete,
.data = head->write_buf,
};
u8 i;
if (tomoyo_str_starts(¶m.data, "aggregator "))
return tomoyo_write_aggregator(¶m);
for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++)
if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i]))
return tomoyo_write_transition_control(¶m, i);
for (i = 0; i < TOMOYO_MAX_GROUP; i++)
if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i]))
return tomoyo_write_group(¶m, i);
if (tomoyo_str_starts(¶m.data, "acl_group ")) {
unsigned int group;
char *data;
group = simple_strtoul(param.data, &data, 10);
if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ')
return tomoyo_write_domain2
(head->w.ns, &head->w.ns->acl_group[group],
data, is_delete);
}
return -EINVAL;
}
/**
* tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @idx: Index number.
*
* Returns true on success, false otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx)
{
struct tomoyo_policy_namespace *ns =
container_of(head->r.ns, typeof(*ns), namespace_list);
struct list_head *list = &ns->group_list[idx];
list_for_each_cookie(head->r.group, list) {
struct tomoyo_group *group =
list_entry(head->r.group, typeof(*group), head.list);
list_for_each_cookie(head->r.acl, &group->member_list) {
struct tomoyo_acl_head *ptr =
list_entry(head->r.acl, typeof(*ptr), list);
if (ptr->is_deleted)
continue;
if (!tomoyo_flush(head))
return false;
tomoyo_print_namespace(head);
tomoyo_set_string(head, tomoyo_group_name[idx]);
tomoyo_set_string(head, group->group_name->name);
if (idx == TOMOYO_PATH_GROUP) {
tomoyo_set_space(head);
tomoyo_set_string(head, container_of
(ptr, struct tomoyo_path_group,
head)->member_name->name);
} else if (idx == TOMOYO_NUMBER_GROUP) {
tomoyo_print_number_union(head, &container_of
(ptr,
struct tomoyo_number_group,
head)->number);
} else if (idx == TOMOYO_ADDRESS_GROUP) {
char buffer[128];
struct tomoyo_address_group *member =
container_of(ptr, typeof(*member),
head);
tomoyo_print_ip(buffer, sizeof(buffer),
&member->address);
tomoyo_io_printf(head, " %s", buffer);
}
tomoyo_set_lf(head);
}
head->r.acl = NULL;
}
head->r.group = NULL;
return true;
}
/**
* tomoyo_read_policy - Read "struct tomoyo_..._entry" list.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @idx: Index number.
*
* Returns true on success, false otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx)
{
struct tomoyo_policy_namespace *ns =
container_of(head->r.ns, typeof(*ns), namespace_list);
struct list_head *list = &ns->policy_list[idx];
list_for_each_cookie(head->r.acl, list) {
struct tomoyo_acl_head *acl =
container_of(head->r.acl, typeof(*acl), list);
if (acl->is_deleted)
continue;
if (!tomoyo_flush(head))
return false;
switch (idx) {
case TOMOYO_ID_TRANSITION_CONTROL:
{
struct tomoyo_transition_control *ptr =
container_of(acl, typeof(*ptr), head);
tomoyo_print_namespace(head);
tomoyo_set_string(head, tomoyo_transition_type
[ptr->type]);
tomoyo_set_string(head, ptr->program ?
ptr->program->name : "any");
tomoyo_set_string(head, " from ");
tomoyo_set_string(head, ptr->domainname ?
ptr->domainname->name :
"any");
}
break;
case TOMOYO_ID_AGGREGATOR:
{
struct tomoyo_aggregator *ptr =
container_of(acl, typeof(*ptr), head);
tomoyo_print_namespace(head);
tomoyo_set_string(head, "aggregator ");
tomoyo_set_string(head,
ptr->original_name->name);
tomoyo_set_space(head);
tomoyo_set_string(head,
ptr->aggregated_name->name);
}
break;
default:
continue;
}
tomoyo_set_lf(head);
}
head->r.acl = NULL;
return true;
}
/**
* tomoyo_read_exception - Read exception policy.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Caller holds tomoyo_read_lock().
*/
static void tomoyo_read_exception(struct tomoyo_io_buffer *head)
{
struct tomoyo_policy_namespace *ns =
container_of(head->r.ns, typeof(*ns), namespace_list);
if (head->r.eof)
return;
while (head->r.step < TOMOYO_MAX_POLICY &&
tomoyo_read_policy(head, head->r.step))
head->r.step++;
if (head->r.step < TOMOYO_MAX_POLICY)
return;
while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP &&
tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY))
head->r.step++;
if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP)
return;
while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP
+ TOMOYO_MAX_ACL_GROUPS) {
head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY
- TOMOYO_MAX_GROUP;
if (!tomoyo_read_domain2(head, &ns->acl_group
[head->r.acl_group_index]))
return;
head->r.step++;
}
head->r.eof = true;
}
/* Wait queue for kernel -> userspace notification. */
static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait);
/* Wait queue for userspace -> kernel notification. */
static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait);
/* Structure for query. */
struct tomoyo_query {
struct list_head list;
struct tomoyo_domain_info *domain;
char *query;
size_t query_len;
unsigned int serial;
u8 timer;
u8 answer;
u8 retry;
};
/* The list for "struct tomoyo_query". */
static LIST_HEAD(tomoyo_query_list);
/* Lock for manipulating tomoyo_query_list. */
static DEFINE_SPINLOCK(tomoyo_query_list_lock);
/*
* Number of "struct file" referring /sys/kernel/security/tomoyo/query
* interface.
*/
static atomic_t tomoyo_query_observers = ATOMIC_INIT(0);
/**
* tomoyo_truncate - Truncate a line.
*
* @str: String to truncate.
*
* Returns length of truncated @str.
*/
static int tomoyo_truncate(char *str)
{
char *start = str;
while (*(unsigned char *) str > (unsigned char) ' ')
str++;
*str = '\0';
return strlen(start) + 1;
}
/**
* tomoyo_numscan - sscanf() which stores the length of a decimal integer value.
*
* @str: String to scan.
* @head: Leading string that must start with.
* @width: Pointer to "int" for storing length of a decimal integer value after @head.
* @tail: Optional character that must match after a decimal integer value.
*
* Returns whether @str starts with @head and a decimal value follows @head.
*/
static bool tomoyo_numscan(const char *str, const char *head, int *width, const char tail)
{
const char *cp;
const int n = strlen(head);
if (!strncmp(str, head, n)) {
cp = str + n;
while (*cp && *cp >= '0' && *cp <= '9')
cp++;
if (*cp == tail || !tail) {
*width = cp - (str + n);
return *width != 0;
}
}
*width = 0;
return 0;
}
/**
* tomoyo_patternize_path - Make patterns for file path. Used by learning mode.
*
* @buffer: Destination buffer.
* @len: Size of @buffer.
* @entry: Original line.
*
* Returns nothing.
*/
static void tomoyo_patternize_path(char *buffer, const int len, char *entry)
{
int width;
char *cp = entry;
/* Nothing to do if this line is not for "file" related entry. */
if (strncmp(entry, "file ", 5))
goto flush;
/*
* Nothing to do if there is no colon in this line, for this rewriting
* applies to only filesystems where numeric values in the path are volatile.
*/
cp = strchr(entry + 5, ':');
if (!cp) {
cp = entry;
goto flush;
}
/* Flush e.g. "file ioctl" part. */
while (*cp != ' ')
cp--;
*cp++ = '\0';
tomoyo_addprintf(buffer, len, "%s ", entry);
/* e.g. file ioctl pipe:[$INO] $CMD */
if (tomoyo_numscan(cp, "pipe:[", &width, ']')) {
cp += width + 7;
tomoyo_addprintf(buffer, len, "pipe:[\\$]");
goto flush;
}
/* e.g. file ioctl socket:[$INO] $CMD */
if (tomoyo_numscan(cp, "socket:[", &width, ']')) {
cp += width + 9;
tomoyo_addprintf(buffer, len, "socket:[\\$]");
goto flush;
}
if (!strncmp(cp, "proc:/self", 10)) {
/* e.g. file read proc:/self/task/$TID/fdinfo/$FD */
cp += 10;
tomoyo_addprintf(buffer, len, "proc:/self");
} else if (tomoyo_numscan(cp, "proc:/", &width, 0)) {
/* e.g. file read proc:/$PID/task/$TID/fdinfo/$FD */
/*
* Don't patternize $PID part if $PID == 1, for several
* programs access only files in /proc/1/ directory.
*/
cp += width + 6;
if (width == 1 && *(cp - 1) == '1')
tomoyo_addprintf(buffer, len, "proc:/1");
else
tomoyo_addprintf(buffer, len, "proc:/\\$");
} else {
goto flush;
}
/* Patternize $TID part if "/task/" follows. */
if (tomoyo_numscan(cp, "/task/", &width, 0)) { cp += width + 6;
tomoyo_addprintf(buffer, len, "/task/\\$");
}
/* Patternize $FD part if "/fd/" or "/fdinfo/" follows. */
if (tomoyo_numscan(cp, "/fd/", &width, 0)) {
cp += width + 4;
tomoyo_addprintf(buffer, len, "/fd/\\$");
} else if (tomoyo_numscan(cp, "/fdinfo/", &width, 0)) {
cp += width + 8;
tomoyo_addprintf(buffer, len, "/fdinfo/\\$");
}
flush:
/* Flush remaining part if any. */
if (*cp) tomoyo_addprintf(buffer, len, "%s", cp);
}
/**
* tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode.
*
* @domain: Pointer to "struct tomoyo_domain_info".
* @header: Lines containing ACL.
*
* Returns nothing.
*/
static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header)
{
char *buffer;
char *realpath = NULL;
char *argv0 = NULL;
char *symlink = NULL;
char *cp = strchr(header, '\n');
int len;
if (!cp)
return;
cp = strchr(cp + 1, '\n');
if (!cp)
return;
*cp++ = '\0';
/* Reserve some space for potentially using patterns. */
len = strlen(cp) + 16;
/* strstr() will return NULL if ordering is wrong. */
if (*cp == 'f') {
argv0 = strstr(header, " argv[]={ \"");
if (argv0) {
argv0 += 10;
len += tomoyo_truncate(argv0) + 14;
}
realpath = strstr(header, " exec={ realpath=\"");
if (realpath) {
realpath += 8;
len += tomoyo_truncate(realpath) + 6;
}
symlink = strstr(header, " symlink.target=\"");
if (symlink) len += tomoyo_truncate(symlink + 1) + 1;
}
buffer = kmalloc(len, GFP_NOFS | __GFP_ZERO);
if (!buffer)
return;
tomoyo_patternize_path(buffer, len, cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink);
tomoyo_normalize_line(buffer);
if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer,
false))
tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES);
kfree(buffer);
}
/**
* tomoyo_supervisor - Ask for the supervisor's decision.
*
* @r: Pointer to "struct tomoyo_request_info".
* @fmt: The printf()'s format string, followed by parameters.
*
* Returns 0 if the supervisor decided to permit the access request which
* violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the
* supervisor decided to retry the access request which violated the policy in
* enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise.
*/
int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...)
{
va_list args;
int error;
int len;
static unsigned int tomoyo_serial;
struct tomoyo_query entry = { };
bool quota_exceeded = false;
va_start(args, fmt);
len = vsnprintf(NULL, 0, fmt, args) + 1;
va_end(args);
/* Write /sys/kernel/security/tomoyo/audit. */
va_start(args, fmt);
tomoyo_write_log2(r, len, fmt, args);
va_end(args);
/* Nothing more to do if granted. */
if (r->granted)
return 0;
if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) {
case TOMOYO_CONFIG_ENFORCING:
error = -EPERM;
if (atomic_read(&tomoyo_query_observers))
break;
goto out;
case TOMOYO_CONFIG_LEARNING:
error = 0;
/* Check max_learning_entry parameter. */
if (tomoyo_domain_quota_is_ok(r))
break;
fallthrough;
default:
return 0;
}
/* Get message. */
va_start(args, fmt);
entry.query = tomoyo_init_log(r, len, fmt, args);
va_end(args);
if (!entry.query)
goto out;
entry.query_len = strlen(entry.query) + 1;
if (!error) {
tomoyo_add_entry(r->domain, entry.query);
goto out;
}
len = kmalloc_size_roundup(entry.query_len);
entry.domain = r->domain;
spin_lock(&tomoyo_query_list_lock);
if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] &&
tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len
>= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) {
quota_exceeded = true;
} else {
entry.serial = tomoyo_serial++;
entry.retry = r->retry;
tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len;
list_add_tail(&entry.list, &tomoyo_query_list);
}
spin_unlock(&tomoyo_query_list_lock);
if (quota_exceeded)
goto out;
/* Give 10 seconds for supervisor's opinion. */
while (entry.timer < 10) {
wake_up_all(&tomoyo_query_wait);
if (wait_event_interruptible_timeout
(tomoyo_answer_wait, entry.answer ||
!atomic_read(&tomoyo_query_observers), HZ))
break;
entry.timer++;
}
spin_lock(&tomoyo_query_list_lock);
list_del(&entry.list);
tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len;
spin_unlock(&tomoyo_query_list_lock);
switch (entry.answer) {
case 3: /* Asked to retry by administrator. */
error = TOMOYO_RETRY_REQUEST;
r->retry++;
break;
case 1:
/* Granted by administrator. */
error = 0;
break;
default:
/* Timed out or rejected by administrator. */
break;
}
out:
kfree(entry.query);
return error;
}
/**
* tomoyo_find_domain_by_qid - Get domain by query id.
*
* @serial: Query ID assigned by tomoyo_supervisor().
*
* Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise.
*/
static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
(unsigned int serial)
{
struct tomoyo_query *ptr;
struct tomoyo_domain_info *domain = NULL;
spin_lock(&tomoyo_query_list_lock);
list_for_each_entry(ptr, &tomoyo_query_list, list) {
if (ptr->serial != serial)
continue;
domain = ptr->domain;
break;
}
spin_unlock(&tomoyo_query_list_lock);
return domain;
}
/**
* tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query.
*
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table".
*
* Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise.
*
* Waits for access requests which violated policy in enforcing mode.
*/
static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait)
{
if (!list_empty(&tomoyo_query_list))
return EPOLLIN | EPOLLRDNORM;
poll_wait(file, &tomoyo_query_wait, wait);
if (!list_empty(&tomoyo_query_list))
return EPOLLIN | EPOLLRDNORM;
return 0;
}
/**
* tomoyo_read_query - Read access requests which violated policy in enforcing mode.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*/
static void tomoyo_read_query(struct tomoyo_io_buffer *head)
{
struct list_head *tmp;
unsigned int pos = 0;
size_t len = 0;
char *buf;
if (head->r.w_pos)
return;
kfree(head->read_buf);
head->read_buf = NULL;
spin_lock(&tomoyo_query_list_lock);
list_for_each(tmp, &tomoyo_query_list) {
struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
if (pos++ != head->r.query_index)
continue;
len = ptr->query_len;
break;
}
spin_unlock(&tomoyo_query_list_lock);
if (!len) {
head->r.query_index = 0;
return;
}
buf = kzalloc(len + 32, GFP_NOFS);
if (!buf)
return;
pos = 0;
spin_lock(&tomoyo_query_list_lock);
list_for_each(tmp, &tomoyo_query_list) {
struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
if (pos++ != head->r.query_index)
continue;
/*
* Some query can be skipped because tomoyo_query_list
* can change, but I don't care.
*/
if (len == ptr->query_len)
snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial,
ptr->retry, ptr->query);
break;
}
spin_unlock(&tomoyo_query_list_lock);
if (buf[0]) {
head->read_buf = buf;
head->r.w[head->r.w_pos++] = buf;
head->r.query_index++;
} else {
kfree(buf);
}
}
/**
* tomoyo_write_answer - Write the supervisor's decision.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0 on success, -EINVAL otherwise.
*/
static int tomoyo_write_answer(struct tomoyo_io_buffer *head)
{
char *data = head->write_buf;
struct list_head *tmp;
unsigned int serial;
unsigned int answer;
spin_lock(&tomoyo_query_list_lock);
list_for_each(tmp, &tomoyo_query_list) {
struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
ptr->timer = 0;
}
spin_unlock(&tomoyo_query_list_lock);
if (sscanf(data, "A%u=%u", &serial, &answer) != 2)
return -EINVAL;
spin_lock(&tomoyo_query_list_lock);
list_for_each(tmp, &tomoyo_query_list) {
struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
if (ptr->serial != serial)
continue;
ptr->answer = answer;
/* Remove from tomoyo_query_list. */
if (ptr->answer)
list_del_init(&ptr->list);
break;
}
spin_unlock(&tomoyo_query_list_lock);
return 0;
}
/**
* tomoyo_read_version: Get version.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns version information.
*/
static void tomoyo_read_version(struct tomoyo_io_buffer *head)
{
if (!head->r.eof) {
tomoyo_io_printf(head, "2.6.0");
head->r.eof = true;
}
}
/* String table for /sys/kernel/security/tomoyo/stat interface. */
static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = {
[TOMOYO_STAT_POLICY_UPDATES] = "update:",
[TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:",
[TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:",
[TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:",
};
/* String table for /sys/kernel/security/tomoyo/stat interface. */
static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = {
[TOMOYO_MEMORY_POLICY] = "policy:",
[TOMOYO_MEMORY_AUDIT] = "audit log:",
[TOMOYO_MEMORY_QUERY] = "query message:",
};
/* Counter for number of updates. */
static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT];
/* Timestamp counter for last updated. */
static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT];
/**
* tomoyo_update_stat - Update statistic counters.
*
* @index: Index for policy type.
*
* Returns nothing.
*/
void tomoyo_update_stat(const u8 index)
{
atomic_inc(&tomoyo_stat_updated[index]);
tomoyo_stat_modified[index] = ktime_get_real_seconds();
}
/**
* tomoyo_read_stat - Read statistic data.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static void tomoyo_read_stat(struct tomoyo_io_buffer *head)
{
u8 i;
unsigned int total = 0;
if (head->r.eof)
return;
for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) {
tomoyo_io_printf(head, "Policy %-30s %10u",
tomoyo_policy_headers[i],
atomic_read(&tomoyo_stat_updated[i]));
if (tomoyo_stat_modified[i]) {
struct tomoyo_time stamp;
tomoyo_convert_time(tomoyo_stat_modified[i], &stamp);
tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)",
stamp.year, stamp.month, stamp.day,
stamp.hour, stamp.min, stamp.sec);
}
tomoyo_set_lf(head);
}
for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) {
unsigned int used = tomoyo_memory_used[i];
total += used;
tomoyo_io_printf(head, "Memory used by %-22s %10u",
tomoyo_memory_headers[i], used);
used = tomoyo_memory_quota[i];
if (used)
tomoyo_io_printf(head, " (Quota: %10u)", used);
tomoyo_set_lf(head);
}
tomoyo_io_printf(head, "Total memory used: %10u\n",
total);
head->r.eof = true;
}
/**
* tomoyo_write_stat - Set memory quota.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns 0.
*/
static int tomoyo_write_stat(struct tomoyo_io_buffer *head)
{
char *data = head->write_buf;
u8 i;
if (tomoyo_str_starts(&data, "Memory used by "))
for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++)
if (tomoyo_str_starts(&data, tomoyo_memory_headers[i]))
sscanf(data, "%u", &tomoyo_memory_quota[i]);
return 0;
}
/**
* tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface.
*
* @type: Type of interface.
* @file: Pointer to "struct file".
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_open_control(const u8 type, struct file *file)
{
struct tomoyo_io_buffer *head = kzalloc(sizeof(*head), GFP_NOFS);
if (!head)
return -ENOMEM;
mutex_init(&head->io_sem);
head->type = type;
switch (type) {
case TOMOYO_DOMAINPOLICY:
/* /sys/kernel/security/tomoyo/domain_policy */
head->write = tomoyo_write_domain;
head->read = tomoyo_read_domain;
break;
case TOMOYO_EXCEPTIONPOLICY:
/* /sys/kernel/security/tomoyo/exception_policy */
head->write = tomoyo_write_exception;
head->read = tomoyo_read_exception;
break;
case TOMOYO_AUDIT:
/* /sys/kernel/security/tomoyo/audit */
head->poll = tomoyo_poll_log;
head->read = tomoyo_read_log;
break;
case TOMOYO_PROCESS_STATUS:
/* /sys/kernel/security/tomoyo/.process_status */
head->write = tomoyo_write_pid;
head->read = tomoyo_read_pid;
break;
case TOMOYO_VERSION:
/* /sys/kernel/security/tomoyo/version */
head->read = tomoyo_read_version;
head->readbuf_size = 128;
break;
case TOMOYO_STAT:
/* /sys/kernel/security/tomoyo/stat */
head->write = tomoyo_write_stat;
head->read = tomoyo_read_stat;
head->readbuf_size = 1024;
break;
case TOMOYO_PROFILE:
/* /sys/kernel/security/tomoyo/profile */
head->write = tomoyo_write_profile;
head->read = tomoyo_read_profile;
break;
case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */
head->poll = tomoyo_poll_query;
head->write = tomoyo_write_answer;
head->read = tomoyo_read_query;
break;
case TOMOYO_MANAGER:
/* /sys/kernel/security/tomoyo/manager */
head->write = tomoyo_write_manager;
head->read = tomoyo_read_manager;
break;
}
if (!(file->f_mode & FMODE_READ)) {
/*
* No need to allocate read_buf since it is not opened
* for reading.
*/
head->read = NULL;
head->poll = NULL;
} else if (!head->poll) {
/* Don't allocate read_buf for poll() access. */
if (!head->readbuf_size)
head->readbuf_size = 4096 * 2;
head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS);
if (!head->read_buf) {
kfree(head);
return -ENOMEM;
}
}
if (!(file->f_mode & FMODE_WRITE)) {
/*
* No need to allocate write_buf since it is not opened
* for writing.
*/
head->write = NULL;
} else if (head->write) {
head->writebuf_size = 4096 * 2;
head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS);
if (!head->write_buf) {
kfree(head->read_buf);
kfree(head);
return -ENOMEM;
}
}
/*
* If the file is /sys/kernel/security/tomoyo/query , increment the
* observer counter.
* The obserber counter is used by tomoyo_supervisor() to see if
* there is some process monitoring /sys/kernel/security/tomoyo/query.
*/
if (type == TOMOYO_QUERY)
atomic_inc(&tomoyo_query_observers);
file->private_data = head;
tomoyo_notify_gc(head, true);
return 0;
}
/**
* tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface.
*
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table". Maybe NULL.
*
* Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write,
* EPOLLOUT | EPOLLWRNORM otherwise.
*/
__poll_t tomoyo_poll_control(struct file *file, poll_table *wait)
{
struct tomoyo_io_buffer *head = file->private_data;
if (head->poll)
return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM;
return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM;
}
/**
* tomoyo_set_namespace_cursor - Set namespace to read.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns nothing.
*/
static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head)
{
struct list_head *ns;
if (head->type != TOMOYO_EXCEPTIONPOLICY &&
head->type != TOMOYO_PROFILE)
return;
/*
* If this is the first read, or reading previous namespace finished
* and has more namespaces to read, update the namespace cursor.
*/
ns = head->r.ns;
if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) {
/* Clearing is OK because tomoyo_flush() returned true. */
memset(&head->r, 0, sizeof(head->r));
head->r.ns = ns ? ns->next : tomoyo_namespace_list.next;
}
}
/**
* tomoyo_has_more_namespace - Check for unread namespaces.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*
* Returns true if we have more entries to print, false otherwise.
*/
static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head)
{
return (head->type == TOMOYO_EXCEPTIONPOLICY ||
head->type == TOMOYO_PROFILE) && head->r.eof &&
head->r.ns->next != &tomoyo_namespace_list;
}
/**
* tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @buffer: Pointer to buffer to write to.
* @buffer_len: Size of @buffer.
*
* Returns bytes read on success, negative value otherwise.
*/
ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer,
const int buffer_len)
{
int len;
int idx;
if (!head->read)
return -EINVAL;
if (mutex_lock_interruptible(&head->io_sem))
return -EINTR;
head->read_user_buf = buffer;
head->read_user_buf_avail = buffer_len;
idx = tomoyo_read_lock();
if (tomoyo_flush(head))
/* Call the policy handler. */
do {
tomoyo_set_namespace_cursor(head);
head->read(head);
} while (tomoyo_flush(head) &&
tomoyo_has_more_namespace(head));
tomoyo_read_unlock(idx);
len = head->read_user_buf - buffer;
mutex_unlock(&head->io_sem);
return len;
}
/**
* tomoyo_parse_policy - Parse a policy line.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @line: Line to parse.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line)
{
/* Delete request? */
head->w.is_delete = !strncmp(line, "delete ", 7);
if (head->w.is_delete)
memmove(line, line + 7, strlen(line + 7) + 1);
/* Selecting namespace to update. */
if (head->type == TOMOYO_EXCEPTIONPOLICY ||
head->type == TOMOYO_PROFILE) {
if (*line == '<') {
char *cp = strchr(line, ' ');
if (cp) {
*cp++ = '\0';
head->w.ns = tomoyo_assign_namespace(line);
memmove(line, cp, strlen(cp) + 1);
} else
head->w.ns = NULL;
} else
head->w.ns = &tomoyo_kernel_namespace;
/* Don't allow updating if namespace is invalid. */
if (!head->w.ns)
return -ENOENT;
}
/* Do the update. */
return head->write(head);
}
/**
* tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface.
*
* @head: Pointer to "struct tomoyo_io_buffer".
* @buffer: Pointer to buffer to read from.
* @buffer_len: Size of @buffer.
*
* Returns @buffer_len on success, negative value otherwise.
*/
ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
const char __user *buffer, const int buffer_len)
{
int error = buffer_len;
size_t avail_len = buffer_len;
char *cp0;
int idx;
if (!head->write)
return -EINVAL;
if (mutex_lock_interruptible(&head->io_sem))
return -EINTR;
cp0 = head->write_buf;
head->read_user_buf_avail = 0;
idx = tomoyo_read_lock();
/* Read a line and dispatch it to the policy handler. */
while (avail_len > 0) {
char c;
if (head->w.avail >= head->writebuf_size - 1) {
const int len = head->writebuf_size * 2;
char *cp = kzalloc(len, GFP_NOFS | __GFP_NOWARN);
if (!cp) {
error = -ENOMEM;
break;
}
memmove(cp, cp0, head->w.avail);
kfree(cp0);
head->write_buf = cp;
cp0 = cp;
head->writebuf_size = len;
}
if (get_user(c, buffer)) {
error = -EFAULT;
break;
}
buffer++;
avail_len--;
cp0[head->w.avail++] = c;
if (c != '\n')
continue;
cp0[head->w.avail - 1] = '\0';
head->w.avail = 0;
tomoyo_normalize_line(cp0);
if (!strcmp(cp0, "reset")) {
head->w.ns = &tomoyo_kernel_namespace;
head->w.domain = NULL;
memset(&head->r, 0, sizeof(head->r));
continue;
}
/* Don't allow updating policies by non manager programs. */
switch (head->type) {
case TOMOYO_PROCESS_STATUS:
/* This does not write anything. */
break;
case TOMOYO_DOMAINPOLICY:
if (tomoyo_select_domain(head, cp0))
continue;
fallthrough;
case TOMOYO_EXCEPTIONPOLICY:
if (!strcmp(cp0, "select transition_only")) {
head->r.print_transition_related_only = true;
continue;
}
fallthrough;
default:
if (!tomoyo_manager()) {
error = -EPERM;
goto out;
}
}
switch (tomoyo_parse_policy(head, cp0)) {
case -EPERM:
error = -EPERM;
goto out;
case 0:
switch (head->type) {
case TOMOYO_DOMAINPOLICY:
case TOMOYO_EXCEPTIONPOLICY:
case TOMOYO_STAT:
case TOMOYO_PROFILE:
case TOMOYO_MANAGER:
tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES);
break;
default:
break;
}
break;
}
}
out:
tomoyo_read_unlock(idx);
mutex_unlock(&head->io_sem);
return error;
}
/**
* tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface.
*
* @head: Pointer to "struct tomoyo_io_buffer".
*/
void tomoyo_close_control(struct tomoyo_io_buffer *head)
{
/*
* If the file is /sys/kernel/security/tomoyo/query , decrement the
* observer counter.
*/
if (head->type == TOMOYO_QUERY &&
atomic_dec_and_test(&tomoyo_query_observers))
wake_up_all(&tomoyo_answer_wait);
tomoyo_notify_gc(head, false);
}
/**
* tomoyo_check_profile - Check all profiles currently assigned to domains are defined.
*/
void tomoyo_check_profile(void)
{
struct tomoyo_domain_info *domain;
const int idx = tomoyo_read_lock();
tomoyo_policy_loaded = true;
pr_info("TOMOYO: 2.6.0\n");
list_for_each_entry_rcu(domain, &tomoyo_domain_list, list,
srcu_read_lock_held(&tomoyo_ss)) {
const u8 profile = domain->profile;
struct tomoyo_policy_namespace *ns = domain->ns;
if (ns->profile_version == 20110903) {
pr_info_once("Converting profile version from %u to %u.\n",
20110903, 20150505);
ns->profile_version = 20150505;
}
if (ns->profile_version != 20150505)
pr_err("Profile version %u is not supported.\n",
ns->profile_version);
else if (!ns->profile_ptr[profile])
pr_err("Profile %u (used by '%s') is not defined.\n",
profile, domain->domainname->name);
else
continue;
pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n");
pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n");
panic("STOP!");
}
tomoyo_read_unlock(idx);
pr_info("Mandatory Access Control activated.\n");
}
/**
* tomoyo_load_builtin_policy - Load built-in policy.
*
* Returns nothing.
*/
void __init tomoyo_load_builtin_policy(void)
{
#ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
static char tomoyo_builtin_profile[] __initdata =
"PROFILE_VERSION=20150505\n"
"0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n";
static char tomoyo_builtin_exception_policy[] __initdata =
"aggregator proc:/self/exe /proc/self/exe\n";
static char tomoyo_builtin_domain_policy[] __initdata = "";
static char tomoyo_builtin_manager[] __initdata = "";
static char tomoyo_builtin_stat[] __initdata = "";
#else
/*
* This include file is manually created and contains built-in policy
* named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy",
* "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager",
* "tomoyo_builtin_stat" in the form of "static char [] __initdata".
*/
#include "builtin-policy.h"
#endif
u8 i;
const int idx = tomoyo_read_lock();
for (i = 0; i < 5; i++) {
struct tomoyo_io_buffer head = { };
char *start = "";
switch (i) {
case 0:
start = tomoyo_builtin_profile;
head.type = TOMOYO_PROFILE;
head.write = tomoyo_write_profile;
break;
case 1:
start = tomoyo_builtin_exception_policy;
head.type = TOMOYO_EXCEPTIONPOLICY;
head.write = tomoyo_write_exception;
break;
case 2:
start = tomoyo_builtin_domain_policy;
head.type = TOMOYO_DOMAINPOLICY;
head.write = tomoyo_write_domain;
break;
case 3:
start = tomoyo_builtin_manager;
head.type = TOMOYO_MANAGER;
head.write = tomoyo_write_manager;
break;
case 4:
start = tomoyo_builtin_stat;
head.type = TOMOYO_STAT;
head.write = tomoyo_write_stat;
break;
}
while (1) {
char *end = strchr(start, '\n');
if (!end)
break;
*end = '\0';
tomoyo_normalize_line(start);
head.write_buf = start;
tomoyo_parse_policy(&head, start);
start = end + 1;
}
}
tomoyo_read_unlock(idx);
#ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
tomoyo_check_profile();
#endif
}
267
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
#define _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
/**
* fls - find last (most-significant) bit set
* @x: the word to search
*
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
static __always_inline int fls(unsigned int x)
{
return x ? sizeof(x) * 8 - __builtin_clz(x) : 0;
}
#endif
// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/* raw.c - Raw sockets for protocol family CAN
*
* Copyright (c) 2002-2007 Volkswagen Group Electronic Research
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of Volkswagen nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* Alternatively, provided that this notice is retained in full, this
* software may be distributed under the terms of the GNU General
* Public License ("GPL") version 2, in which case the provisions of the
* GPL apply INSTEAD OF those given above.
*
* The provided data structures and external interfaces from this code
* are not restricted to be used by modules with a GPL compatible license.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
* DAMAGE.
*
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/uio.h>
#include <linux/net.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/socket.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/can.h>
#include <linux/can/core.h>
#include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */
#include <linux/can/skb.h>
#include <linux/can/raw.h>
#include <net/sock.h>
#include <net/net_namespace.h>
MODULE_DESCRIPTION("PF_CAN raw protocol");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
MODULE_ALIAS("can-proto-1");
#define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
#define MASK_ALL 0
/* A raw socket has a list of can_filters attached to it, each receiving
* the CAN frames matching that filter. If the filter list is empty,
* no CAN frames will be received by the socket. The default after
* opening the socket, is to have one filter which receives all frames.
* The filter list is allocated dynamically with the exception of the
* list containing only one item. This common case is optimized by
* storing the single filter in dfilter, to avoid using dynamic memory.
*/
struct uniqframe {
int skbcnt;
const struct sk_buff *skb;
unsigned int join_rx_count;
};
struct raw_sock {
struct sock sk;
int bound;
int ifindex;
struct net_device *dev;
netdevice_tracker dev_tracker;
struct list_head notifier;
int loopback;
int recv_own_msgs;
int fd_frames;
int xl_frames;
struct can_raw_vcid_options raw_vcid_opts;
canid_t tx_vcid_shifted;
canid_t rx_vcid_shifted;
canid_t rx_vcid_mask_shifted;
int join_filters;
int count; /* number of active filters */
struct can_filter dfilter; /* default/single filter */
struct can_filter *filter; /* pointer to filter(s) */
can_err_mask_t err_mask;
struct uniqframe __percpu *uniq;
};
static LIST_HEAD(raw_notifier_list);
static DEFINE_SPINLOCK(raw_notifier_lock);
static struct raw_sock *raw_busy_notifier;
/* Return pointer to store the extra msg flags for raw_recvmsg().
* We use the space of one unsigned int beyond the 'struct sockaddr_can'
* in skb->cb.
*/
static inline unsigned int *raw_flags(struct sk_buff *skb)
{
sock_skb_cb_check_size(sizeof(struct sockaddr_can) +
sizeof(unsigned int));
/* return pointer after struct sockaddr_can */
return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]);
}
static inline struct raw_sock *raw_sk(const struct sock *sk)
{
return (struct raw_sock *)sk;
}
static void raw_rcv(struct sk_buff *oskb, void *data)
{
struct sock *sk = (struct sock *)data;
struct raw_sock *ro = raw_sk(sk);
struct sockaddr_can *addr;
struct sk_buff *skb;
unsigned int *pflags;
/* check the received tx sock reference */
if (!ro->recv_own_msgs && oskb->sk == sk)
return;
/* make sure to not pass oversized frames to the socket */
if (!ro->fd_frames && can_is_canfd_skb(oskb))
return;
if (can_is_canxl_skb(oskb)) {
struct canxl_frame *cxl = (struct canxl_frame *)oskb->data;
/* make sure to not pass oversized frames to the socket */
if (!ro->xl_frames)
return;
/* filter CAN XL VCID content */
if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) {
/* apply VCID filter if user enabled the filter */
if ((cxl->prio & ro->rx_vcid_mask_shifted) !=
(ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted))
return;
} else {
/* no filter => do not forward VCID tagged frames */
if (cxl->prio & CANXL_VCID_MASK)
return;
}
}
/* eliminate multiple filter matches for the same skb */
if (this_cpu_ptr(ro->uniq)->skb == oskb &&
this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) {
if (!ro->join_filters)
return;
this_cpu_inc(ro->uniq->join_rx_count);
/* drop frame until all enabled filters matched */
if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count)
return;
} else {
this_cpu_ptr(ro->uniq)->skb = oskb;
this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt;
this_cpu_ptr(ro->uniq)->join_rx_count = 1;
/* drop first frame to check all enabled filters? */
if (ro->join_filters && ro->count > 1)
return;
}
/* clone the given skb to be able to enqueue it into the rcv queue */
skb = skb_clone(oskb, GFP_ATOMIC);
if (!skb)
return;
/* Put the datagram to the queue so that raw_recvmsg() can get
* it from there. We need to pass the interface index to
* raw_recvmsg(). We pass a whole struct sockaddr_can in
* skb->cb containing the interface index.
*/
sock_skb_cb_check_size(sizeof(struct sockaddr_can));
addr = (struct sockaddr_can *)skb->cb;
memset(addr, 0, sizeof(*addr));
addr->can_family = AF_CAN;
addr->can_ifindex = skb->dev->ifindex;
/* add CAN specific message flags for raw_recvmsg() */
pflags = raw_flags(skb);
*pflags = 0;
if (oskb->sk)
*pflags |= MSG_DONTROUTE;
if (oskb->sk == sk)
*pflags |= MSG_CONFIRM;
if (sock_queue_rcv_skb(sk, skb) < 0)
kfree_skb(skb);
}
static int raw_enable_filters(struct net *net, struct net_device *dev,
struct sock *sk, struct can_filter *filter,
int count)
{
int err = 0;
int i;
for (i = 0; i < count; i++) {
err = can_rx_register(net, dev, filter[i].can_id,
filter[i].can_mask,
raw_rcv, sk, "raw", sk);
if (err) {
/* clean up successfully registered filters */
while (--i >= 0)
can_rx_unregister(net, dev, filter[i].can_id,
filter[i].can_mask,
raw_rcv, sk);
break;
}
}
return err;
}
static int raw_enable_errfilter(struct net *net, struct net_device *dev,
struct sock *sk, can_err_mask_t err_mask)
{
int err = 0;
if (err_mask)
err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG,
raw_rcv, sk, "raw", sk);
return err;
}
static void raw_disable_filters(struct net *net, struct net_device *dev,
struct sock *sk, struct can_filter *filter,
int count)
{
int i;
for (i = 0; i < count; i++)
can_rx_unregister(net, dev, filter[i].can_id,
filter[i].can_mask, raw_rcv, sk);
}
static inline void raw_disable_errfilter(struct net *net,
struct net_device *dev,
struct sock *sk,
can_err_mask_t err_mask)
{
if (err_mask) can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG,
raw_rcv, sk);
}
static inline void raw_disable_allfilters(struct net *net,
struct net_device *dev,
struct sock *sk)
{
struct raw_sock *ro = raw_sk(sk);
raw_disable_filters(net, dev, sk, ro->filter, ro->count); raw_disable_errfilter(net, dev, sk, ro->err_mask);
}
static int raw_enable_allfilters(struct net *net, struct net_device *dev,
struct sock *sk)
{
struct raw_sock *ro = raw_sk(sk);
int err;
err = raw_enable_filters(net, dev, sk, ro->filter, ro->count);
if (!err) {
err = raw_enable_errfilter(net, dev, sk, ro->err_mask);
if (err)
raw_disable_filters(net, dev, sk, ro->filter,
ro->count);
}
return err;
}
static void raw_notify(struct raw_sock *ro, unsigned long msg,
struct net_device *dev)
{
struct sock *sk = &ro->sk;
if (!net_eq(dev_net(dev), sock_net(sk)))
return;
if (ro->dev != dev)
return;
switch (msg) {
case NETDEV_UNREGISTER:
lock_sock(sk);
/* remove current filters & unregister */
if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); netdev_put(dev, &ro->dev_tracker);
}
if (ro->count > 1) kfree(ro->filter);
ro->ifindex = 0;
ro->bound = 0;
ro->dev = NULL;
ro->count = 0;
release_sock(sk);
sk->sk_err = ENODEV;
if (!sock_flag(sk, SOCK_DEAD))
sk_error_report(sk);
break;
case NETDEV_DOWN:
sk->sk_err = ENETDOWN;
if (!sock_flag(sk, SOCK_DEAD))
sk_error_report(sk);
break;
}
}
static int raw_notifier(struct notifier_block *nb, unsigned long msg,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (dev->type != ARPHRD_CAN)
return NOTIFY_DONE;
if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
return NOTIFY_DONE;
if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */
return NOTIFY_DONE;
spin_lock(&raw_notifier_lock);
list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) {
spin_unlock(&raw_notifier_lock);
raw_notify(raw_busy_notifier, msg, dev);
spin_lock(&raw_notifier_lock);
}
raw_busy_notifier = NULL;
spin_unlock(&raw_notifier_lock);
return NOTIFY_DONE;
}
static int raw_init(struct sock *sk)
{
struct raw_sock *ro = raw_sk(sk);
ro->bound = 0;
ro->ifindex = 0;
ro->dev = NULL;
/* set default filter to single entry dfilter */
ro->dfilter.can_id = 0;
ro->dfilter.can_mask = MASK_ALL;
ro->filter = &ro->dfilter;
ro->count = 1;
/* set default loopback behaviour */
ro->loopback = 1;
ro->recv_own_msgs = 0;
ro->fd_frames = 0;
ro->xl_frames = 0;
ro->join_filters = 0;
/* alloc_percpu provides zero'ed memory */
ro->uniq = alloc_percpu(struct uniqframe);
if (unlikely(!ro->uniq))
return -ENOMEM;
/* set notifier */
spin_lock(&raw_notifier_lock);
list_add_tail(&ro->notifier, &raw_notifier_list);
spin_unlock(&raw_notifier_lock);
return 0;
}
static int raw_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct raw_sock *ro;
struct net *net;
if (!sk)
return 0;
ro = raw_sk(sk);
net = sock_net(sk);
spin_lock(&raw_notifier_lock);
while (raw_busy_notifier == ro) {
spin_unlock(&raw_notifier_lock);
schedule_timeout_uninterruptible(1);
spin_lock(&raw_notifier_lock);
}
list_del(&ro->notifier);
spin_unlock(&raw_notifier_lock);
rtnl_lock();
lock_sock(sk);
/* remove current filters & unregister */
if (ro->bound) {
if (ro->dev) {
raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
netdev_put(ro->dev, &ro->dev_tracker);
} else {
raw_disable_allfilters(net, NULL, sk);
}
}
if (ro->count > 1)
kfree(ro->filter);
ro->ifindex = 0;
ro->bound = 0;
ro->dev = NULL;
ro->count = 0;
free_percpu(ro->uniq);
sock_orphan(sk);
sock->sk = NULL;
release_sock(sk);
rtnl_unlock();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_put(sk);
return 0;
}
static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
{
struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
struct sock *sk = sock->sk;
struct raw_sock *ro = raw_sk(sk);
struct net_device *dev = NULL;
int ifindex;
int err = 0;
int notify_enetdown = 0;
if (len < RAW_MIN_NAMELEN)
return -EINVAL;
if (addr->can_family != AF_CAN)
return -EINVAL;
rtnl_lock();
lock_sock(sk);
if (ro->bound && addr->can_ifindex == ro->ifindex)
goto out;
if (addr->can_ifindex) {
dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
if (!dev) {
err = -ENODEV;
goto out;
}
if (dev->type != ARPHRD_CAN) {
err = -ENODEV;
goto out_put_dev;
}
if (!(dev->flags & IFF_UP))
notify_enetdown = 1;
ifindex = dev->ifindex;
/* filters set by default/setsockopt */
err = raw_enable_allfilters(sock_net(sk), dev, sk);
if (err)
goto out_put_dev;
} else {
ifindex = 0;
/* filters set by default/setsockopt */
err = raw_enable_allfilters(sock_net(sk), NULL, sk);
}
if (!err) {
if (ro->bound) {
/* unregister old filters */
if (ro->dev) {
raw_disable_allfilters(dev_net(ro->dev),
ro->dev, sk);
/* drop reference to old ro->dev */
netdev_put(ro->dev, &ro->dev_tracker);
} else {
raw_disable_allfilters(sock_net(sk), NULL, sk);
}
}
ro->ifindex = ifindex;
ro->bound = 1;
/* bind() ok -> hold a reference for new ro->dev */
ro->dev = dev;
if (ro->dev)
netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL);
}
out_put_dev:
/* remove potential reference from dev_get_by_index() */
dev_put(dev);
out:
release_sock(sk);
rtnl_unlock();
if (notify_enetdown) {
sk->sk_err = ENETDOWN;
if (!sock_flag(sk, SOCK_DEAD))
sk_error_report(sk);
}
return err;
}
static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
int peer)
{
struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
struct sock *sk = sock->sk;
struct raw_sock *ro = raw_sk(sk);
if (peer)
return -EOPNOTSUPP;
memset(addr, 0, RAW_MIN_NAMELEN);
addr->can_family = AF_CAN;
addr->can_ifindex = ro->ifindex;
return RAW_MIN_NAMELEN;
}
static int raw_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
struct raw_sock *ro = raw_sk(sk);
struct can_filter *filter = NULL; /* dyn. alloc'ed filters */
struct can_filter sfilter; /* single filter */
struct net_device *dev = NULL;
can_err_mask_t err_mask = 0;
int fd_frames;
int count = 0;
int err = 0;
if (level != SOL_CAN_RAW)
return -EINVAL;
switch (optname) {
case CAN_RAW_FILTER:
if (optlen % sizeof(struct can_filter) != 0)
return -EINVAL;
if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter))
return -EINVAL;
count = optlen / sizeof(struct can_filter);
if (count > 1) {
/* filter does not fit into dfilter => alloc space */
filter = memdup_sockptr(optval, optlen);
if (IS_ERR(filter))
return PTR_ERR(filter);
} else if (count == 1) {
if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
return -EFAULT;
}
rtnl_lock();
lock_sock(sk);
dev = ro->dev;
if (ro->bound && dev) {
if (dev->reg_state != NETREG_REGISTERED) {
if (count > 1)
kfree(filter);
err = -ENODEV;
goto out_fil;
}
}
if (ro->bound) {
/* (try to) register the new filters */
if (count == 1)
err = raw_enable_filters(sock_net(sk), dev, sk,
&sfilter, 1);
else
err = raw_enable_filters(sock_net(sk), dev, sk,
filter, count);
if (err) {
if (count > 1)
kfree(filter);
goto out_fil;
}
/* remove old filter registrations */
raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
ro->count);
}
/* remove old filter space */
if (ro->count > 1)
kfree(ro->filter);
/* link new filters to the socket */
if (count == 1) {
/* copy filter data for single filter */
ro->dfilter = sfilter;
filter = &ro->dfilter;
}
ro->filter = filter;
ro->count = count;
out_fil:
release_sock(sk);
rtnl_unlock();
break;
case CAN_RAW_ERR_FILTER:
if (optlen != sizeof(err_mask))
return -EINVAL;
if (copy_from_sockptr(&err_mask, optval, optlen))
return -EFAULT;
err_mask &= CAN_ERR_MASK;
rtnl_lock();
lock_sock(sk);
dev = ro->dev;
if (ro->bound && dev) {
if (dev->reg_state != NETREG_REGISTERED) {
err = -ENODEV;
goto out_err;
}
}
/* remove current error mask */
if (ro->bound) {
/* (try to) register the new err_mask */
err = raw_enable_errfilter(sock_net(sk), dev, sk,
err_mask);
if (err)
goto out_err;
/* remove old err_mask registration */
raw_disable_errfilter(sock_net(sk), dev, sk,
ro->err_mask);
}
/* link new err_mask to the socket */
ro->err_mask = err_mask;
out_err:
release_sock(sk);
rtnl_unlock();
break;
case CAN_RAW_LOOPBACK:
if (optlen != sizeof(ro->loopback))
return -EINVAL;
if (copy_from_sockptr(&ro->loopback, optval, optlen))
return -EFAULT;
break;
case CAN_RAW_RECV_OWN_MSGS:
if (optlen != sizeof(ro->recv_own_msgs))
return -EINVAL;
if (copy_from_sockptr(&ro->recv_own_msgs, optval, optlen))
return -EFAULT;
break;
case CAN_RAW_FD_FRAMES:
if (optlen != sizeof(fd_frames))
return -EINVAL;
if (copy_from_sockptr(&fd_frames, optval, optlen))
return -EFAULT;
/* Enabling CAN XL includes CAN FD */
if (ro->xl_frames && !fd_frames)
return -EINVAL;
ro->fd_frames = fd_frames;
break;
case CAN_RAW_XL_FRAMES:
if (optlen != sizeof(ro->xl_frames))
return -EINVAL;
if (copy_from_sockptr(&ro->xl_frames, optval, optlen))
return -EFAULT;
/* Enabling CAN XL includes CAN FD */
if (ro->xl_frames)
ro->fd_frames = ro->xl_frames;
break;
case CAN_RAW_XL_VCID_OPTS:
if (optlen != sizeof(ro->raw_vcid_opts))
return -EINVAL;
if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen))
return -EFAULT;
/* prepare 32 bit values for handling in hot path */
ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET;
ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET;
ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET;
break;
case CAN_RAW_JOIN_FILTERS:
if (optlen != sizeof(ro->join_filters))
return -EINVAL;
if (copy_from_sockptr(&ro->join_filters, optval, optlen))
return -EFAULT;
break;
default:
return -ENOPROTOOPT;
}
return err;
}
static int raw_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
struct raw_sock *ro = raw_sk(sk);
int len;
void *val;
if (level != SOL_CAN_RAW)
return -EINVAL;
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
switch (optname) {
case CAN_RAW_FILTER: {
int err = 0;
lock_sock(sk);
if (ro->count > 0) {
int fsize = ro->count * sizeof(struct can_filter);
/* user space buffer to small for filter list? */
if (len < fsize) {
/* return -ERANGE and needed space in optlen */
err = -ERANGE;
if (put_user(fsize, optlen))
err = -EFAULT;
} else {
if (len > fsize)
len = fsize;
if (copy_to_user(optval, ro->filter, len))
err = -EFAULT;
}
} else {
len = 0;
}
release_sock(sk);
if (!err)
err = put_user(len, optlen);
return err;
}
case CAN_RAW_ERR_FILTER:
if (len > sizeof(can_err_mask_t))
len = sizeof(can_err_mask_t);
val = &ro->err_mask;
break;
case CAN_RAW_LOOPBACK:
if (len > sizeof(int))
len = sizeof(int);
val = &ro->loopback;
break;
case CAN_RAW_RECV_OWN_MSGS:
if (len > sizeof(int))
len = sizeof(int);
val = &ro->recv_own_msgs;
break;
case CAN_RAW_FD_FRAMES:
if (len > sizeof(int))
len = sizeof(int);
val = &ro->fd_frames;
break;
case CAN_RAW_XL_FRAMES:
if (len > sizeof(int))
len = sizeof(int);
val = &ro->xl_frames;
break;
case CAN_RAW_XL_VCID_OPTS: {
int err = 0;
/* user space buffer to small for VCID opts? */
if (len < sizeof(ro->raw_vcid_opts)) {
/* return -ERANGE and needed space in optlen */
err = -ERANGE;
if (put_user(sizeof(ro->raw_vcid_opts), optlen))
err = -EFAULT;
} else {
if (len > sizeof(ro->raw_vcid_opts))
len = sizeof(ro->raw_vcid_opts);
if (copy_to_user(optval, &ro->raw_vcid_opts, len))
err = -EFAULT;
}
if (!err)
err = put_user(len, optlen);
return err;
}
case CAN_RAW_JOIN_FILTERS:
if (len > sizeof(int))
len = sizeof(int);
val = &ro->join_filters;
break;
default:
return -ENOPROTOOPT;
}
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, val, len))
return -EFAULT;
return 0;
}
static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb)
{
struct canxl_frame *cxl = (struct canxl_frame *)skb->data;
/* sanitize non CAN XL bits */
cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK);
/* clear VCID in CAN XL frame if pass through is disabled */
if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS))
cxl->prio &= CANXL_PRIO_MASK;
/* set VCID in CAN XL frame if enabled */
if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) {
cxl->prio &= CANXL_PRIO_MASK;
cxl->prio |= ro->tx_vcid_shifted;
}
}
static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu)
{
/* Classical CAN -> no checks for flags and device capabilities */
if (can_is_can_skb(skb))
return CAN_MTU;
/* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */
if (ro->fd_frames && can_is_canfd_skb(skb) &&
(mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu)))
return CANFD_MTU;
/* CAN XL -> needs to be enabled and a CAN XL device */
if (ro->xl_frames && can_is_canxl_skb(skb) &&
can_is_canxl_dev_mtu(mtu))
return CANXL_MTU;
return 0;
}
static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
struct raw_sock *ro = raw_sk(sk);
struct sockcm_cookie sockc;
struct sk_buff *skb;
struct net_device *dev;
unsigned int txmtu;
int ifindex;
int err = -EINVAL;
/* check for valid CAN frame sizes */
if (size < CANXL_HDR_SIZE + CANXL_MIN_DLEN || size > CANXL_MTU)
return -EINVAL;
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
if (msg->msg_namelen < RAW_MIN_NAMELEN)
return -EINVAL;
if (addr->can_family != AF_CAN)
return -EINVAL;
ifindex = addr->can_ifindex;
} else {
ifindex = ro->ifindex;
}
dev = dev_get_by_index(sock_net(sk), ifindex);
if (!dev)
return -ENXIO;
skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv),
msg->msg_flags & MSG_DONTWAIT, &err);
if (!skb)
goto put_dev;
can_skb_reserve(skb);
can_skb_prv(skb)->ifindex = dev->ifindex;
can_skb_prv(skb)->skbcnt = 0;
/* fill the skb before testing for valid CAN frames */
err = memcpy_from_msg(skb_put(skb, size), msg, size);
if (err < 0)
goto free_skb;
err = -EINVAL;
/* check for valid CAN (CC/FD/XL) frame content */
txmtu = raw_check_txframe(ro, skb, dev->mtu);
if (!txmtu)
goto free_skb;
/* only CANXL: clear/forward/set VCID value */
if (txmtu == CANXL_MTU)
raw_put_canxl_vcid(ro, skb);
sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err))
goto free_skb;
}
skb->dev = dev;
skb->priority = sockc.priority;
skb->mark = sockc.mark;
skb->tstamp = sockc.transmit_time;
skb_setup_tx_timestamp(skb, &sockc);
err = can_send(skb, ro->loopback);
dev_put(dev);
if (err)
goto send_failed;
return size;
free_skb:
kfree_skb(skb);
put_dev:
dev_put(dev);
send_failed:
return err;
}
static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
struct sk_buff *skb;
int err = 0;
if (flags & MSG_ERRQUEUE)
return sock_recv_errqueue(sk, msg, size,
SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE);
skb = skb_recv_datagram(sk, flags, &err);
if (!skb)
return err;
if (size < skb->len)
msg->msg_flags |= MSG_TRUNC;
else
size = skb->len;
err = memcpy_to_msg(msg, skb->data, size);
if (err < 0) {
skb_free_datagram(sk, skb);
return err;
}
sock_recv_cmsgs(msg, sk, skb);
if (msg->msg_name) {
__sockaddr_check_size(RAW_MIN_NAMELEN);
msg->msg_namelen = RAW_MIN_NAMELEN;
memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
}
/* assign the flags that have been recorded in raw_rcv() */
msg->msg_flags |= *(raw_flags(skb));
skb_free_datagram(sk, skb);
return size;
}
static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
/* no ioctls for socket layer -> hand it down to NIC layer */
return -ENOIOCTLCMD;
}
static const struct proto_ops raw_ops = {
.family = PF_CAN,
.release = raw_release,
.bind = raw_bind,
.connect = sock_no_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = raw_getname,
.poll = datagram_poll,
.ioctl = raw_sock_no_ioctlcmd,
.gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = raw_setsockopt,
.getsockopt = raw_getsockopt,
.sendmsg = raw_sendmsg,
.recvmsg = raw_recvmsg,
.mmap = sock_no_mmap,
};
static struct proto raw_proto __read_mostly = {
.name = "CAN_RAW",
.owner = THIS_MODULE,
.obj_size = sizeof(struct raw_sock),
.init = raw_init,
};
static const struct can_proto raw_can_proto = {
.type = SOCK_RAW,
.protocol = CAN_RAW,
.ops = &raw_ops,
.prot = &raw_proto,
};
static struct notifier_block canraw_notifier = {
.notifier_call = raw_notifier
};
static __init int raw_module_init(void)
{
int err;
pr_info("can: raw protocol\n");
err = register_netdevice_notifier(&canraw_notifier);
if (err)
return err;
err = can_proto_register(&raw_can_proto);
if (err < 0) {
pr_err("can: registration of raw protocol failed\n");
goto register_proto_failed;
}
return 0;
register_proto_failed:
unregister_netdevice_notifier(&canraw_notifier);
return err;
}
static __exit void raw_module_exit(void)
{
can_proto_unregister(&raw_can_proto);
unregister_netdevice_notifier(&canraw_notifier);
}
module_init(raw_module_init);
module_exit(raw_module_exit);
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/file.c
*
* Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes
*
* Manage the dynamic fd arrays in the process files_struct.
*/
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/close_range.h>
#include <linux/file_ref.h>
#include <net/sock.h>
#include <linux/init_task.h>
#include "internal.h"
static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
{
/*
* If the reference count was already in the dead zone, then this
* put() operation is imbalanced. Warn, put the reference count back to
* DEAD and tell the caller to not deconstruct the object.
*/
if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) {
atomic_long_set(&ref->refcnt, FILE_REF_DEAD);
return false;
}
/*
* This is a put() operation on a saturated refcount. Restore the
* mean saturation value and tell the caller to not deconstruct the
* object.
*/
if (cnt > FILE_REF_MAXREF)
atomic_long_set(&ref->refcnt, FILE_REF_SATURATED);
return false;
}
/**
* __file_ref_put - Slowpath of file_ref_put()
* @ref: Pointer to the reference count
* @cnt: Current reference count
*
* Invoked when the reference count is outside of the valid zone.
*
* Return:
* True if this was the last reference with no future references
* possible. This signals the caller that it can safely schedule the
* object, which is protected by the reference counter, for
* deconstruction.
*
* False if there are still active references or the put() raced
* with a concurrent get()/put() pair. Caller is not allowed to
* deconstruct the protected object.
*/
bool __file_ref_put(file_ref_t *ref, unsigned long cnt)
{
/* Did this drop the last reference? */
if (likely(cnt == FILE_REF_NOREF)) {
/*
* Carefully try to set the reference count to FILE_REF_DEAD.
*
* This can fail if a concurrent get() operation has
* elevated it again or the corresponding put() even marked
* it dead already. Both are valid situations and do not
* require a retry. If this fails the caller is not
* allowed to deconstruct the object.
*/
if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD))
return false;
/*
* The caller can safely schedule the object for
* deconstruction. Provide acquire ordering.
*/
smp_acquire__after_ctrl_dep();
return true;
}
return __file_ref_put_badval(ref, cnt);
}
EXPORT_SYMBOL_GPL(__file_ref_put);
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
/* our min() is unusable in constant expressions ;-/ */
#define __const_min(x, y) ((x) < (y) ? (x) : (y))
unsigned int sysctl_nr_open_max =
__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;
static void __free_fdtable(struct fdtable *fdt)
{
kvfree(fdt->fd);
kvfree(fdt->open_fds);
kfree(fdt);
}
static void free_fdtable_rcu(struct rcu_head *rcu)
{
__free_fdtable(container_of(rcu, struct fdtable, rcu));
}
#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))
#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
/*
* Copy 'count' fd bits from the old table to the new table and clear the extra
* space if any. This does not copy the file pointers. Called with the files
* spinlock held for write.
*/
static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
unsigned int copy_words)
{
unsigned int nwords = fdt_words(nfdt);
bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
copy_words, nwords);
}
/*
* Copy all file descriptors from the old table to the new, expanded table and
* clear the extra space. Called with the files spinlock held for write.
*/
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{
size_t cpy, set;
BUG_ON(nfdt->max_fds < ofdt->max_fds);
cpy = ofdt->max_fds * sizeof(struct file *);
set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)nfdt->fd + cpy, 0, set);
copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
}
/*
* Note how the fdtable bitmap allocations very much have to be a multiple of
* BITS_PER_LONG. This is not only because we walk those things in chunks of
* 'unsigned long' in some places, but simply because that is how the Linux
* kernel bitmaps are defined to work: they are not "bits in an array of bytes",
* they are very much "bits in an array of unsigned long".
*/
static struct fdtable *alloc_fdtable(unsigned int slots_wanted)
{
struct fdtable *fdt;
unsigned int nr;
void *data;
/*
* Figure out how many fds we actually want to support in this fdtable.
* Allocation steps are keyed to the size of the fdarray, since it
* grows far faster than any of the other dynamic data. We try to fit
* the fdarray into comfortable page-tuned chunks: starting at 1024B
* and growing in powers of two from there on. Since we called only
* with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab
* already gives BITS_PER_LONG slots), the above boils down to
* 1. use the smallest power of two large enough to give us that many
* slots.
* 2. on 32bit skip 64 and 128 - the minimal capacity we want there is
* 256 slots (i.e. 1Kb fd array).
* 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there
* and we are never going to be asked for 64 or less.
*/
if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256)
nr = 256;
else
nr = roundup_pow_of_two(slots_wanted);
/*
* Note that this can drive nr *below* what we had passed if sysctl_nr_open
* had been set lower between the check in expand_files() and here.
*
* We make sure that nr remains a multiple of BITS_PER_LONG - otherwise
* bitmaps handling below becomes unpleasant, to put it mildly...
*/
if (unlikely(nr > sysctl_nr_open)) {
nr = round_down(sysctl_nr_open, BITS_PER_LONG);
if (nr < slots_wanted)
return ERR_PTR(-EMFILE);
}
fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
if (!fdt)
goto out;
fdt->max_fds = nr;
data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT);
if (!data)
goto out_fdt;
fdt->fd = data;
data = kvmalloc(max_t(size_t,
2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES),
GFP_KERNEL_ACCOUNT);
if (!data)
goto out_arr;
fdt->open_fds = data;
data += nr / BITS_PER_BYTE;
fdt->close_on_exec = data;
data += nr / BITS_PER_BYTE;
fdt->full_fds_bits = data;
return fdt;
out_arr:
kvfree(fdt->fd);
out_fdt:
kfree(fdt);
out:
return ERR_PTR(-ENOMEM);
}
/*
* Expand the file descriptor table.
* This function will allocate a new fdtable and both fd array and fdset, of
* the given size.
* Return <0 error code on error; 0 on successful completion.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_fdtable(struct files_struct *files, unsigned int nr)
__releases(files->file_lock)
__acquires(files->file_lock)
{
struct fdtable *new_fdt, *cur_fdt;
spin_unlock(&files->file_lock);
new_fdt = alloc_fdtable(nr + 1);
/* make sure all fd_install() have seen resize_in_progress
* or have finished their rcu_read_lock_sched() section.
*/
if (atomic_read(&files->count) > 1)
synchronize_rcu();
spin_lock(&files->file_lock);
if (IS_ERR(new_fdt))
return PTR_ERR(new_fdt);
cur_fdt = files_fdtable(files);
BUG_ON(nr < cur_fdt->max_fds);
copy_fdtable(new_fdt, cur_fdt);
rcu_assign_pointer(files->fdt, new_fdt);
if (cur_fdt != &files->fdtab)
call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
/* coupled with smp_rmb() in fd_install() */
smp_wmb();
return 0;
}
/*
* Expand files.
* This function will expand the file structures, if the requested size exceeds
* the current capacity and there is room for expansion.
* Return <0 error code on error; 0 on success.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_files(struct files_struct *files, unsigned int nr)
__releases(files->file_lock)
__acquires(files->file_lock)
{
struct fdtable *fdt;
int error;
repeat:
fdt = files_fdtable(files);
/* Do we need to expand? */
if (nr < fdt->max_fds)
return 0;
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
wait_event(files->resize_wait, !files->resize_in_progress);
spin_lock(&files->file_lock);
goto repeat;
}
/* Can we expand? */
if (unlikely(nr >= sysctl_nr_open))
return -EMFILE;
/* All good, so we try */
files->resize_in_progress = true;
error = expand_fdtable(files, nr);
files->resize_in_progress = false;
wake_up_all(&files->resize_wait);
return error;
}
static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt,
bool set)
{
if (set) {
__set_bit(fd, fdt->close_on_exec);
} else {
if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec);
}
}
static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set)
{
__set_bit(fd, fdt->open_fds);
__set_close_on_exec(fd, fdt, set);
fd /= BITS_PER_LONG;
if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits);
}
static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
{
__clear_bit(fd, fdt->open_fds);
fd /= BITS_PER_LONG;
if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits);
}
static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
{
return test_bit(fd, fdt->open_fds);
}
/*
* Note that a sane fdtable size always has to be a multiple of
* BITS_PER_LONG, since we have bitmaps that are sized by this.
*
* punch_hole is optional - when close_range() is asked to unshare
* and close, we don't need to copy descriptors in that range, so
* a smaller cloned descriptor table might suffice if the last
* currently opened descriptor falls into that range.
*/
static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole)
{
unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds);
if (last == fdt->max_fds)
return NR_OPEN_DEFAULT;
if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) {
last = find_last_bit(fdt->open_fds, punch_hole->from);
if (last == punch_hole->from)
return NR_OPEN_DEFAULT;
}
return ALIGN(last + 1, BITS_PER_LONG);
}
/*
* Allocate a new descriptor table and copy contents from the passed in
* instance. Returns a pointer to cloned table on success, ERR_PTR()
* on failure. For 'punch_hole' see sane_fdtable_size().
*/
struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
unsigned int open_files, i;
struct fdtable *old_fdt, *new_fdt;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
return ERR_PTR(-ENOMEM);
atomic_set(&newf->count, 1);
spin_lock_init(&newf->file_lock);
newf->resize_in_progress = false;
init_waitqueue_head(&newf->resize_wait);
newf->next_fd = 0;
new_fdt = &newf->fdtab;
new_fdt->max_fds = NR_OPEN_DEFAULT;
new_fdt->close_on_exec = newf->close_on_exec_init;
new_fdt->open_fds = newf->open_fds_init;
new_fdt->full_fds_bits = newf->full_fds_bits_init;
new_fdt->fd = &newf->fd_array[0];
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = sane_fdtable_size(old_fdt, punch_hole);
/*
* Check whether we need to allocate a larger fd array and fd set.
*/
while (unlikely(open_files > new_fdt->max_fds)) {
spin_unlock(&oldf->file_lock);
if (new_fdt != &newf->fdtab)
__free_fdtable(new_fdt);
new_fdt = alloc_fdtable(open_files);
if (IS_ERR(new_fdt)) {
kmem_cache_free(files_cachep, newf);
return ERR_CAST(new_fdt);
}
/*
* Reacquire the oldf lock and a pointer to its fd table
* who knows it may have a new bigger fd table. We need
* the latest pointer.
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = sane_fdtable_size(old_fdt, punch_hole);
}
copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
/*
* We may be racing against fd allocation from other threads using this
* files_struct, despite holding ->file_lock.
*
* alloc_fd() might have already claimed a slot, while fd_install()
* did not populate it yet. Note the latter operates locklessly, so
* the file can show up as we are walking the array below.
*
* At the same time we know no files will disappear as all other
* operations take the lock.
*
* Instead of trying to placate userspace racing with itself, we
* ref the file if we see it and mark the fd slot as unused otherwise.
*/
for (i = open_files; i != 0; i--) {
struct file *f = rcu_dereference_raw(*old_fds++);
if (f) {
get_file(f);
} else {
__clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
}
spin_unlock(&oldf->file_lock);
/* clear the remainder */
memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *));
rcu_assign_pointer(newf->fdt, new_fdt);
return newf;
}
static struct fdtable *close_files(struct files_struct * files)
{
/*
* It is safe to dereference the fd table without RCU or
* ->file_lock because this is the last reference to the
* files structure.
*/
struct fdtable *fdt = rcu_dereference_raw(files->fdt);
unsigned int i, j = 0;
for (;;) {
unsigned long set;
i = j * BITS_PER_LONG;
if (i >= fdt->max_fds)
break;
set = fdt->open_fds[j++];
while (set) {
if (set & 1) {
struct file *file = fdt->fd[i];
if (file) {
filp_close(file, files);
cond_resched();
}
}
i++;
set >>= 1;
}
}
return fdt;
}
void put_files_struct(struct files_struct *files)
{
if (atomic_dec_and_test(&files->count)) {
struct fdtable *fdt = close_files(files);
/* free the arrays if they are not embedded */
if (fdt != &files->fdtab)
__free_fdtable(fdt);
kmem_cache_free(files_cachep, files);
}
}
void exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
if (files) {
task_lock(tsk);
tsk->files = NULL;
task_unlock(tsk);
put_files_struct(files);
}
}
struct files_struct init_files = {
.count = ATOMIC_INIT(1),
.fdt = &init_files.fdtab,
.fdtab = {
.max_fds = NR_OPEN_DEFAULT,
.fd = &init_files.fd_array[0],
.close_on_exec = init_files.close_on_exec_init,
.open_fds = init_files.open_fds_init,
.full_fds_bits = init_files.full_fds_bits_init,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
.resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait),
};
static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
{
unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */
unsigned int maxbit = maxfd / BITS_PER_LONG;
unsigned int bitbit = start / BITS_PER_LONG;
unsigned int bit;
/*
* Try to avoid looking at the second level bitmap
*/
bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG,
start & (BITS_PER_LONG - 1));
if (bit < BITS_PER_LONG)
return bit + bitbit * BITS_PER_LONG;
bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
if (bitbit >= maxfd)
return maxfd;
if (bitbit > start)
start = bitbit;
return find_next_zero_bit(fdt->open_fds, maxfd, start);
}
/*
* allocate a file descriptor, mark it busy.
*/
static int alloc_fd(unsigned start, unsigned end, unsigned flags)
{
struct files_struct *files = current->files;
unsigned int fd;
int error;
struct fdtable *fdt;
spin_lock(&files->file_lock);
repeat:
fdt = files_fdtable(files);
fd = start;
if (fd < files->next_fd)
fd = files->next_fd;
if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd);
/*
* N.B. For clone tasks sharing a files structure, this test
* will limit the total number of files that can be opened.
*/
error = -EMFILE;
if (unlikely(fd >= end))
goto out;
if (unlikely(fd >= fdt->max_fds)) {
error = expand_files(files, fd);
if (error < 0)
goto out;
goto repeat;
}
if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC);
error = fd;
VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
out:
spin_unlock(&files->file_lock);
return error;
}
int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
{
return alloc_fd(0, nofile, flags);
}
int get_unused_fd_flags(unsigned flags)
{
return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE));
}
EXPORT_SYMBOL(get_unused_fd_flags);
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{ struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd;
}
void put_unused_fd(unsigned int fd)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(put_unused_fd);
/**
* fd_install - install a file pointer in the fd array
* @fd: file descriptor to install the file in
* @file: the file to install
*
* This consumes the "file" refcount, so callers should treat it
* as if they had called fput(file).
*/
void fd_install(unsigned int fd, struct file *file)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING)))
return;
rcu_read_lock_sched();
if (unlikely(files->resize_in_progress)) {
rcu_read_unlock_sched();
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
return;
}
/* coupled with smp_wmb() in expand_fdtable() */
smp_rmb();
fdt = rcu_dereference_sched(files->fdt);
VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
rcu_read_unlock_sched();
}
EXPORT_SYMBOL(fd_install);
/**
* file_close_fd_locked - return file associated with fd
* @files: file struct to retrieve file from
* @fd: file descriptor to retrieve file for
*
* Doesn't take a separate reference count.
*
* Context: files_lock must be held.
*
* Returns: The file associated with @fd (NULL if @fd is not open)
*/
struct file *file_close_fd_locked(struct files_struct *files, unsigned fd)
{ struct fdtable *fdt = files_fdtable(files);
struct file *file;
lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds)
return NULL;
fd = array_index_nospec(fd, fdt->max_fds);
file = rcu_dereference_raw(fdt->fd[fd]);
if (file) { rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
}
return file;
}
int close_fd(unsigned fd)
{
struct files_struct *files = current->files;
struct file *file;
spin_lock(&files->file_lock);
file = file_close_fd_locked(files, fd);
spin_unlock(&files->file_lock);
if (!file)
return -EBADF;
return filp_close(file, files);
}
EXPORT_SYMBOL(close_fd);
/**
* last_fd - return last valid index into fd table
* @fdt: File descriptor table.
*
* Context: Either rcu read lock or files_lock must be held.
*
* Returns: Last valid index into fdtable.
*/
static inline unsigned last_fd(struct fdtable *fdt)
{
return fdt->max_fds - 1;
}
static inline void __range_cloexec(struct files_struct *cur_fds,
unsigned int fd, unsigned int max_fd)
{
struct fdtable *fdt;
/* make sure we're using the correct maximum value */
spin_lock(&cur_fds->file_lock);
fdt = files_fdtable(cur_fds);
max_fd = min(last_fd(fdt), max_fd);
if (fd <= max_fd)
bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
spin_unlock(&cur_fds->file_lock);
}
static inline void __range_close(struct files_struct *files, unsigned int fd,
unsigned int max_fd)
{
struct file *file;
unsigned n;
spin_lock(&files->file_lock);
n = last_fd(files_fdtable(files));
max_fd = min(max_fd, n);
for (; fd <= max_fd; fd++) {
file = file_close_fd_locked(files, fd);
if (file) {
spin_unlock(&files->file_lock);
filp_close(file, files);
cond_resched();
spin_lock(&files->file_lock);
} else if (need_resched()) {
spin_unlock(&files->file_lock);
cond_resched();
spin_lock(&files->file_lock);
}
}
spin_unlock(&files->file_lock);
}
/**
* sys_close_range() - Close all file descriptors in a given range.
*
* @fd: starting file descriptor to close
* @max_fd: last file descriptor to close
* @flags: CLOSE_RANGE flags.
*
* This closes a range of file descriptors. All file descriptors
* from @fd up to and including @max_fd are closed.
* Currently, errors to close a given file descriptor are ignored.
*/
SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
unsigned int, flags)
{
struct task_struct *me = current;
struct files_struct *cur_fds = me->files, *fds = NULL;
if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC))
return -EINVAL;
if (fd > max_fd)
return -EINVAL;
if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) {
struct fd_range range = {fd, max_fd}, *punch_hole = ⦥
/*
* If the caller requested all fds to be made cloexec we always
* copy all of the file descriptors since they still want to
* use them.
*/
if (flags & CLOSE_RANGE_CLOEXEC)
punch_hole = NULL;
fds = dup_fd(cur_fds, punch_hole);
if (IS_ERR(fds))
return PTR_ERR(fds);
/*
* We used to share our file descriptor table, and have now
* created a private one, make sure we're using it below.
*/
swap(cur_fds, fds);
}
if (flags & CLOSE_RANGE_CLOEXEC)
__range_cloexec(cur_fds, fd, max_fd);
else
__range_close(cur_fds, fd, max_fd);
if (fds) {
/*
* We're done closing the files we were supposed to. Time to install
* the new file descriptor table and drop the old one.
*/
task_lock(me);
me->files = cur_fds;
task_unlock(me);
put_files_struct(fds);
}
return 0;
}
/**
* file_close_fd - return file associated with fd
* @fd: file descriptor to retrieve file for
*
* Doesn't take a separate reference count.
*
* Returns: The file associated with @fd (NULL if @fd is not open)
*/
struct file *file_close_fd(unsigned int fd)
{
struct files_struct *files = current->files;
struct file *file;
spin_lock(&files->file_lock);
file = file_close_fd_locked(files, fd);
spin_unlock(&files->file_lock);
return file;
}
void do_close_on_exec(struct files_struct *files)
{
unsigned i;
struct fdtable *fdt;
/* exec unshares first */
spin_lock(&files->file_lock);
for (i = 0; ; i++) {
unsigned long set;
unsigned fd = i * BITS_PER_LONG;
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
break;
set = fdt->close_on_exec[i];
if (!set)
continue;
fdt->close_on_exec[i] = 0;
for ( ; set ; fd++, set >>= 1) {
struct file *file;
if (!(set & 1))
continue;
file = fdt->fd[fd];
if (!file)
continue;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
filp_close(file, files);
cond_resched();
spin_lock(&files->file_lock);
}
}
spin_unlock(&files->file_lock);
}
static struct file *__get_file_rcu(struct file __rcu **f)
{
struct file __rcu *file;
struct file __rcu *file_reloaded;
struct file __rcu *file_reloaded_cmp;
file = rcu_dereference_raw(*f);
if (!file)
return NULL;
if (unlikely(!file_ref_get(&file->f_ref)))
return ERR_PTR(-EAGAIN);
file_reloaded = rcu_dereference_raw(*f);
/*
* Ensure that all accesses have a dependency on the load from
* rcu_dereference_raw() above so we get correct ordering
* between reuse/allocation and the pointer check below.
*/
file_reloaded_cmp = file_reloaded;
OPTIMIZER_HIDE_VAR(file_reloaded_cmp);
/*
* file_ref_get() above provided a full memory barrier when we
* acquired a reference.
*
* This is paired with the write barrier from assigning to the
* __rcu protected file pointer so that if that pointer still
* matches the current file, we know we have successfully
* acquired a reference to the right file.
*
* If the pointers don't match the file has been reallocated by
* SLAB_TYPESAFE_BY_RCU.
*/
if (file == file_reloaded_cmp)
return file_reloaded;
fput(file);
return ERR_PTR(-EAGAIN);
}
/**
* get_file_rcu - try go get a reference to a file under rcu
* @f: the file to get a reference on
*
* This function tries to get a reference on @f carefully verifying that
* @f hasn't been reused.
*
* This function should rarely have to be used and only by users who
* understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it.
*
* Return: Returns @f with the reference count increased or NULL.
*/
struct file *get_file_rcu(struct file __rcu **f)
{
for (;;) {
struct file __rcu *file;
file = __get_file_rcu(f);
if (!IS_ERR(file))
return file;
}
}
EXPORT_SYMBOL_GPL(get_file_rcu);
/**
* get_file_active - try go get a reference to a file
* @f: the file to get a reference on
*
* In contast to get_file_rcu() the pointer itself isn't part of the
* reference counting.
*
* This function should rarely have to be used and only by users who
* understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it.
*
* Return: Returns @f with the reference count increased or NULL.
*/
struct file *get_file_active(struct file **f)
{
struct file __rcu *file;
rcu_read_lock();
file = __get_file_rcu(f);
rcu_read_unlock();
if (IS_ERR(file))
file = NULL;
return file;
}
EXPORT_SYMBOL_GPL(get_file_active);
static inline struct file *__fget_files_rcu(struct files_struct *files,
unsigned int fd, fmode_t mask)
{
for (;;) {
struct file *file;
struct fdtable *fdt = rcu_dereference_raw(files->fdt);
struct file __rcu **fdentry;
unsigned long nospec_mask;
/* Mask is a 0 for invalid fd's, ~0 for valid ones */
nospec_mask = array_index_mask_nospec(fd, fdt->max_fds);
/*
* fdentry points to the 'fd' offset, or fdt->fd[0].
* Loading from fdt->fd[0] is always safe, because the
* array always exists.
*/
fdentry = fdt->fd + (fd & nospec_mask);
/* Do the load, then mask any invalid result */
file = rcu_dereference_raw(*fdentry);
file = (void *)(nospec_mask & (unsigned long)file);
if (unlikely(!file))
return NULL;
/*
* Ok, we have a file pointer that was valid at
* some point, but it might have become stale since.
*
* We need to confirm it by incrementing the refcount
* and then check the lookup again.
*
* file_ref_get() gives us a full memory barrier. We
* only really need an 'acquire' one to protect the
* loads below, but we don't have that.
*/
if (unlikely(!file_ref_get(&file->f_ref)))
continue;
/*
* Such a race can take two forms:
*
* (a) the file ref already went down to zero and the
* file hasn't been reused yet or the file count
* isn't zero but the file has already been reused.
*
* (b) the file table entry has changed under us.
* Note that we don't need to re-check the 'fdt->fd'
* pointer having changed, because it always goes
* hand-in-hand with 'fdt'.
*
* If so, we need to put our ref and try again.
*/
if (unlikely(file != rcu_dereference_raw(*fdentry)) ||
unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
fput(file);
continue;
}
/*
* This isn't the file we're looking for or we're not
* allowed to get a reference to it.
*/
if (unlikely(file->f_mode & mask)) { fput(file);
return NULL;
}
/*
* Ok, we have a ref to the file, and checked that it
* still exists.
*/
return file;
}
}
static struct file *__fget_files(struct files_struct *files, unsigned int fd,
fmode_t mask)
{
struct file *file;
rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock();
return file;
}
static inline struct file *__fget(unsigned int fd, fmode_t mask)
{
return __fget_files(current->files, fd, mask);
}
struct file *fget(unsigned int fd)
{
return __fget(fd, FMODE_PATH);
}
EXPORT_SYMBOL(fget);
struct file *fget_raw(unsigned int fd)
{
return __fget(fd, 0);
}
EXPORT_SYMBOL(fget_raw);
struct file *fget_task(struct task_struct *task, unsigned int fd)
{
struct file *file = NULL;
task_lock(task);
if (task->files)
file = __fget_files(task->files, fd, 0);
task_unlock(task);
return file;
}
struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd)
{
/* Must be called with rcu_read_lock held */
struct files_struct *files;
unsigned int fd = *ret_fd;
struct file *file = NULL;
task_lock(task);
files = task->files;
if (files) {
rcu_read_lock();
for (; fd < files_fdtable(files)->max_fds; fd++) {
file = __fget_files_rcu(files, fd, 0);
if (file)
break;
}
rcu_read_unlock();
}
task_unlock(task);
*ret_fd = fd;
return file;
}
EXPORT_SYMBOL(fget_task_next);
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
*
* You can use this instead of fget if you satisfy all of the following
* conditions:
* 1) You must call fput_light before exiting the syscall and returning control
* to userspace (i.e. you cannot remember the returned struct file * after
* returning to userspace).
* 2) You must not call filp_close on the returned struct file * in between
* calls to fget_light and fput_light.
* 3) You must not clone the current task in between the calls to fget_light
* and fput_light.
*
* The fput_needed flag returned by fget_light should be passed to the
* corresponding fput_light.
*
* (As an exception to rule 2, you can call filp_close between fget_light and
* fput_light provided that you capture a real refcount with get_file before
* the call to filp_close, and ensure that this real refcount is fput *after*
* the fput_light call.)
*
* See also the documentation in rust/kernel/file.rs.
*/
static inline struct fd __fget_light(unsigned int fd, fmode_t mask)
{
struct files_struct *files = current->files;
struct file *file;
/*
* If another thread is concurrently calling close_fd() followed
* by put_files_struct(), we must not observe the old table
* entry combined with the new refcount - otherwise we could
* return a file that is concurrently being freed.
*
* atomic_read_acquire() pairs with atomic_dec_and_test() in
* put_files_struct().
*/
if (likely(atomic_read_acquire(&files->count) == 1)) {
file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask))
return EMPTY_FD;
return BORROWED_FD(file);
} else {
file = __fget_files(files, fd, mask);
if (!file)
return EMPTY_FD;
return CLONED_FD(file);
}
}
struct fd fdget(unsigned int fd)
{ return __fget_light(fd, FMODE_PATH);
}
EXPORT_SYMBOL(fdget);
struct fd fdget_raw(unsigned int fd)
{ return __fget_light(fd, 0);
}
/*
* Try to avoid f_pos locking. We only need it if the
* file is marked for FMODE_ATOMIC_POS, and it can be
* accessed multiple ways.
*
* Always do it for directories, because pidfd_getfd()
* can make a file accessible even if it otherwise would
* not be, and for directories this is a correctness
* issue, not a "POSIX requirement".
*/
static inline bool file_needs_f_pos_lock(struct file *file)
{
if (!(file->f_mode & FMODE_ATOMIC_POS))
return false;
if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF)
return true;
if (file->f_op->iterate_shared)
return true;
return false;
}
bool file_seek_cur_needs_f_lock(struct file *file)
{
if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared)
return false;
VFS_WARN_ON_ONCE((file_count(file) > 1) &&
!mutex_is_locked(&file->f_pos_lock));
return true;
}
struct fd fdget_pos(unsigned int fd)
{ struct fd f = fdget(fd);
struct file *file = fd_file(f);
if (likely(file) && file_needs_f_pos_lock(file)) {
f.word |= FDPUT_POS_UNLOCK;
mutex_lock(&file->f_pos_lock);
}
return f;
}
void __f_unlock_pos(struct file *f)
{
mutex_unlock(&f->f_pos_lock);
}
/*
* We only lock f_pos if we have threads or if the file might be
* shared with another process. In both cases we'll have an elevated
* file count (done either by fdget() or by fork()).
*/
void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
__set_close_on_exec(fd, files_fdtable(files), flag);
spin_unlock(&files->file_lock);
}
bool get_close_on_exec(unsigned int fd)
{
bool res;
rcu_read_lock();
res = close_on_exec(fd, current->files);
rcu_read_unlock();
return res;
}
static int do_dup2(struct files_struct *files,
struct file *file, unsigned fd, unsigned flags)
__releases(&files->file_lock)
{
struct file *tofree;
struct fdtable *fdt;
/*
* dup2() is expected to close the file installed in the target fd slot
* (if any). However, userspace hand-picking a fd may be racing against
* its own threads which happened to allocate it in open() et al but did
* not populate it yet.
*
* Broadly speaking we may be racing against the following:
* fd = get_unused_fd_flags(); // fd slot reserved, ->fd[fd] == NULL
* file = hard_work_goes_here();
* fd_install(fd, file); // only now ->fd[fd] == file
*
* It is an invariant that a successfully allocated fd has a NULL entry
* in the array until the matching fd_install().
*
* If we fit the window, we have the fd to populate, yet no target file
* to close. Trying to ignore it and install our new file would violate
* the invariant and make fd_install() overwrite our file.
*
* Things can be done(tm) to handle this. However, the issue does not
* concern legitimate programs and we only need to make sure the kernel
* does not trip over it.
*
* The simplest way out is to return an error if we find ourselves here.
*
* POSIX is silent on the issue, we return -EBUSY.
*/
fdt = files_fdtable(files);
fd = array_index_nospec(fd, fdt->max_fds);
tofree = rcu_dereference_raw(fdt->fd[fd]);
if (!tofree && fd_is_open(fd, fdt))
goto Ebusy;
get_file(file);
rcu_assign_pointer(fdt->fd[fd], file);
__set_open_fd(fd, fdt, flags & O_CLOEXEC);
spin_unlock(&files->file_lock);
if (tofree)
filp_close(tofree, files);
return fd;
Ebusy:
spin_unlock(&files->file_lock);
return -EBUSY;
}
int replace_fd(unsigned fd, struct file *file, unsigned flags)
{
int err;
struct files_struct *files = current->files;
if (!file)
return close_fd(fd);
if (fd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, fd);
if (unlikely(err < 0))
goto out_unlock;
return do_dup2(files, file, fd, flags);
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
/**
* receive_fd() - Install received file into file descriptor table
* @file: struct file that was received from another process
* @ufd: __user pointer to write new fd number to
* @o_flags: the O_* flags to apply to the new fd entry
*
* Installs a received file into the file descriptor table, with appropriate
* checks and count updates. Optionally writes the fd number to userspace, if
* @ufd is non-NULL.
*
* This helper handles its own reference counting of the incoming
* struct file.
*
* Returns newly install fd or -ve on error.
*/
int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
{
int new_fd;
int error;
error = security_file_receive(file);
if (error)
return error;
new_fd = get_unused_fd_flags(o_flags);
if (new_fd < 0)
return new_fd;
if (ufd) {
error = put_user(new_fd, ufd);
if (error) {
put_unused_fd(new_fd);
return error;
}
}
fd_install(new_fd, get_file(file));
__receive_sock(file);
return new_fd;
}
EXPORT_SYMBOL_GPL(receive_fd);
int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
{
int error;
error = security_file_receive(file);
if (error)
return error;
error = replace_fd(new_fd, file, o_flags);
if (error)
return error;
__receive_sock(file);
return new_fd;
}
static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{
int err = -EBADF;
struct file *file;
struct files_struct *files = current->files;
if ((flags & ~O_CLOEXEC) != 0)
return -EINVAL;
if (unlikely(oldfd == newfd))
return -EINVAL;
if (newfd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, newfd);
file = files_lookup_fd_locked(files, oldfd);
if (unlikely(!file))
goto Ebadf;
if (unlikely(err < 0)) {
if (err == -EMFILE)
goto Ebadf;
goto out_unlock;
}
return do_dup2(files, file, newfd, flags);
Ebadf:
err = -EBADF;
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{
return ksys_dup3(oldfd, newfd, flags);
}
SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
{
if (unlikely(newfd == oldfd)) { /* corner case */
struct files_struct *files = current->files;
struct file *f;
int retval = oldfd;
rcu_read_lock();
f = __fget_files_rcu(files, oldfd, 0);
if (!f)
retval = -EBADF;
rcu_read_unlock();
if (f)
fput(f);
return retval;
}
return ksys_dup3(oldfd, newfd, 0);
}
SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
int ret = -EBADF;
struct file *file = fget_raw(fildes);
if (file) {
ret = get_unused_fd_flags(0);
if (ret >= 0)
fd_install(ret, file);
else
fput(file);
}
return ret;
}
int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{
unsigned long nofile = rlimit(RLIMIT_NOFILE);
int err;
if (from >= nofile)
return -EINVAL;
err = alloc_fd(from, nofile, flags);
if (err >= 0) {
get_file(file);
fd_install(err, file);
}
return err;
}
int iterate_fd(struct files_struct *files, unsigned n,
int (*f)(const void *, struct file *, unsigned),
const void *p)
{
struct fdtable *fdt;
int res = 0;
if (!files)
return 0;
spin_lock(&files->file_lock);
for (fdt = files_fdtable(files); n < fdt->max_fds; n++) {
struct file *file;
file = rcu_dereference_check_fdtable(files, fdt->fd[n]);
if (!file)
continue;
res = f(p, file, n);
if (res)
break;
}
spin_unlock(&files->file_lock);
return res;
}
EXPORT_SYMBOL(iterate_fd);
/*
* Performance events:
*
* Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
* Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
*
* Data type definitions, declarations, prototypes.
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* For licencing details see kernel-base/COPYING
*/
#ifndef _LINUX_PERF_EVENT_H
#define _LINUX_PERF_EVENT_H
#include <uapi/linux/perf_event.h>
#include <uapi/linux/bpf_perf_event.h>
/*
* Kernel-internal data types and definitions:
*/
#ifdef CONFIG_PERF_EVENTS
# include <asm/perf_event.h>
# include <asm/local64.h>
#endif
#define PERF_GUEST_ACTIVE 0x01
#define PERF_GUEST_USER 0x02
struct perf_guest_info_callbacks {
unsigned int (*state)(void);
unsigned long (*get_ip)(void);
unsigned int (*handle_intel_pt_intr)(void);
};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
#include <linux/rhashtable-types.h>
#include <asm/hw_breakpoint.h>
#endif
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/hrtimer.h>
#include <linux/fs.h>
#include <linux/pid_namespace.h>
#include <linux/workqueue.h>
#include <linux/ftrace.h>
#include <linux/cpu.h>
#include <linux/irq_work.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
#include <linux/perf_regs.h>
#include <linux/cgroup.h>
#include <linux/refcount.h>
#include <linux/security.h>
#include <linux/static_call.h>
#include <linux/lockdep.h>
#include <asm/local.h>
struct perf_callchain_entry {
__u64 nr;
__u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */
};
struct perf_callchain_entry_ctx {
struct perf_callchain_entry *entry;
u32 max_stack;
u32 nr;
short contexts;
bool contexts_maxed;
};
typedef unsigned long (*perf_copy_f)(void *dst, const void *src,
unsigned long off, unsigned long len);
struct perf_raw_frag {
union {
struct perf_raw_frag *next;
unsigned long pad;
};
perf_copy_f copy;
void *data;
u32 size;
} __packed;
struct perf_raw_record {
struct perf_raw_frag frag;
u32 size;
};
static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag)
{
return frag->pad < sizeof(u64);
}
/*
* branch stack layout:
* nr: number of taken branches stored in entries[]
* hw_idx: The low level index of raw branch records
* for the most recent branch.
* -1ULL means invalid/unknown.
*
* Note that nr can vary from sample to sample
* branches (to, from) are stored from most recent
* to least recent, i.e., entries[0] contains the most
* recent branch.
* The entries[] is an abstraction of raw branch records,
* which may not be stored in age order in HW, e.g. Intel LBR.
* The hw_idx is to expose the low level index of raw
* branch record for the most recent branch aka entries[0].
* The hw_idx index is between -1 (unknown) and max depth,
* which can be retrieved in /sys/devices/cpu/caps/branches.
* For the architectures whose raw branch records are
* already stored in age order, the hw_idx should be 0.
*/
struct perf_branch_stack {
__u64 nr;
__u64 hw_idx;
struct perf_branch_entry entries[];
};
struct task_struct;
/*
* extra PMU register associated with an event
*/
struct hw_perf_event_extra {
u64 config; /* register value */
unsigned int reg; /* register address or index */
int alloc; /* extra register already allocated */
int idx; /* index in shared_regs->regs[] */
};
/**
* hw_perf_event::flag values
*
* PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific
* usage.
*/
#define PERF_EVENT_FLAG_ARCH 0x000fffff
#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000
static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0);
/**
* struct hw_perf_event - performance event hardware details:
*/
struct hw_perf_event {
#ifdef CONFIG_PERF_EVENTS
union {
struct { /* hardware */
u64 config;
u64 last_tag;
unsigned long config_base;
unsigned long event_base;
int event_base_rdpmc;
int idx;
int last_cpu;
int flags;
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
};
struct { /* aux / Intel-PT */
u64 aux_config;
/*
* For AUX area events, aux_paused cannot be a state
* flag because it can be updated asynchronously to
* state.
*/
unsigned int aux_paused;
};
struct { /* software */
struct hrtimer hrtimer;
};
struct { /* tracepoint */
/* for tp_event->class */
struct list_head tp_list;
};
struct { /* amd_power */
u64 pwr_acc;
u64 ptsc;
};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct { /* breakpoint */
/*
* Crufty hack to avoid the chicken and egg
* problem hw_breakpoint has with context
* creation and event initalization.
*/
struct arch_hw_breakpoint info;
struct rhlist_head bp_list;
};
#endif
struct { /* amd_iommu */
u8 iommu_bank;
u8 iommu_cntr;
u16 padding;
u64 conf;
u64 conf1;
};
};
/*
* If the event is a per task event, this will point to the task in
* question. See the comment in perf_event_alloc().
*/
struct task_struct *target;
/*
* PMU would store hardware filter configuration
* here.
*/
void *addr_filters;
/* Last sync'ed generation of filters */
unsigned long addr_filters_gen;
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
*/
#define PERF_HES_STOPPED 0x01 /* the counter is stopped */
#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */
#define PERF_HES_ARCH 0x04
int state;
/*
* The last observed hardware counter value, updated with a
* local64_cmpxchg() such that pmu::read() can be called nested.
*/
local64_t prev_count;
/*
* The period to start the next sample with.
*/
u64 sample_period;
union {
struct { /* Sampling */
/*
* The period we started this sample with.
*/
u64 last_period;
/*
* However much is left of the current period;
* note that this is a full 64bit value and
* allows for generation of periods longer
* than hardware might allow.
*/
local64_t period_left;
};
struct { /* Topdown events counting for context switch */
u64 saved_metric;
u64 saved_slots;
};
};
/*
* State for throttling the event, see __perf_event_overflow() and
* perf_adjust_freq_unthr_context().
*/
u64 interrupts_seq;
u64 interrupts;
/*
* State for freq target events, see __perf_event_overflow() and
* perf_adjust_freq_unthr_context().
*/
u64 freq_time_stamp;
u64 freq_count_stamp;
#endif
};
struct perf_event;
struct perf_event_pmu_context;
/*
* Common implementation detail of pmu::{start,commit,cancel}_txn
*/
#define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */
#define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */
/**
* pmu::capabilities flags
*/
#define PERF_PMU_CAP_NO_INTERRUPT 0x0001
#define PERF_PMU_CAP_NO_NMI 0x0002
#define PERF_PMU_CAP_AUX_NO_SG 0x0004
#define PERF_PMU_CAP_EXTENDED_REGS 0x0008
#define PERF_PMU_CAP_EXCLUSIVE 0x0010
#define PERF_PMU_CAP_ITRACE 0x0020
#define PERF_PMU_CAP_NO_EXCLUDE 0x0040
#define PERF_PMU_CAP_AUX_OUTPUT 0x0080
#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
#define PERF_PMU_CAP_AUX_PAUSE 0x0200
/**
* pmu::scope
*/
enum perf_pmu_scope {
PERF_PMU_SCOPE_NONE = 0,
PERF_PMU_SCOPE_CORE,
PERF_PMU_SCOPE_DIE,
PERF_PMU_SCOPE_CLUSTER,
PERF_PMU_SCOPE_PKG,
PERF_PMU_SCOPE_SYS_WIDE,
PERF_PMU_MAX_SCOPE,
};
struct perf_output_handle;
#define PMU_NULL_DEV ((void *)(~0UL))
/**
* struct pmu - generic performance monitoring unit
*/
struct pmu {
struct list_head entry;
struct module *module;
struct device *dev;
struct device *parent;
const struct attribute_group **attr_groups;
const struct attribute_group **attr_update;
const char *name;
int type;
/*
* various common per-pmu feature flags
*/
int capabilities;
/*
* PMU scope
*/
unsigned int scope;
struct perf_cpu_pmu_context * __percpu *cpu_pmu_context;
atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */
int task_ctx_nr;
int hrtimer_interval_ms;
/* number of address filters this PMU can do */
unsigned int nr_addr_filters;
/*
* Fully disable/enable this PMU, can be used to protect from the PMI
* as well as for lazy/batch writing of the MSRs.
*/
void (*pmu_enable) (struct pmu *pmu); /* optional */
void (*pmu_disable) (struct pmu *pmu); /* optional */
/*
* Try and initialize the event for this PMU.
*
* Returns:
* -ENOENT -- @event is not for this PMU
*
* -ENODEV -- @event is for this PMU but PMU not present
* -EBUSY -- @event is for this PMU but PMU temporarily unavailable
* -EINVAL -- @event is for this PMU but @event is not valid
* -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported
* -EACCES -- @event is for this PMU, @event is valid, but no privileges
*
* 0 -- @event is for this PMU and valid
*
* Other error return values are allowed.
*/
int (*event_init) (struct perf_event *event);
/*
* Notification that the event was mapped or unmapped. Called
* in the context of the mapping task.
*/
void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */
void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */
/*
* Flags for ->add()/->del()/ ->start()/->stop(). There are
* matching hw_perf_event::state flags.
*/
#define PERF_EF_START 0x01 /* start the counter when adding */
#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
/*
* Adds/Removes a counter to/from the PMU, can be done inside a
* transaction, see the ->*_txn() methods.
*
* The add/del callbacks will reserve all hardware resources required
* to service the event, this includes any counter constraint
* scheduling etc.
*
* Called with IRQs disabled and the PMU disabled on the CPU the event
* is on.
*
* ->add() called without PERF_EF_START should result in the same state
* as ->add() followed by ->stop().
*
* ->del() must always PERF_EF_UPDATE stop an event. If it calls
* ->stop() that must deal with already being stopped without
* PERF_EF_UPDATE.
*/
int (*add) (struct perf_event *event, int flags);
void (*del) (struct perf_event *event, int flags);
/*
* Starts/Stops a counter present on the PMU.
*
* The PMI handler should stop the counter when perf_event_overflow()
* returns !0. ->start() will be used to continue.
*
* Also used to change the sample period.
*
* Called with IRQs disabled and the PMU disabled on the CPU the event
* is on -- will be called from NMI context with the PMU generates
* NMIs.
*
* ->stop() with PERF_EF_UPDATE will read the counter and update
* period/count values like ->read() would.
*
* ->start() with PERF_EF_RELOAD will reprogram the counter
* value, must be preceded by a ->stop() with PERF_EF_UPDATE.
*
* ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
* overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
* PERF_EF_RESUME.
*
* ->start() with PERF_EF_RESUME will start as simply as possible but
* only if the counter is not otherwise stopped. Will not overlap
* another ->start() with PERF_EF_RESUME nor ->stop() with
* PERF_EF_PAUSE.
*
* Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
* ->stop()/->start() invocations, just not itself.
*/
void (*start) (struct perf_event *event, int flags);
void (*stop) (struct perf_event *event, int flags);
/*
* Updates the counter value of the event.
*
* For sampling capable PMUs this will also update the software period
* hw_perf_event::period_left field.
*/
void (*read) (struct perf_event *event);
/*
* Group events scheduling is treated as a transaction, add
* group events as a whole and perform one schedulability test.
* If the test fails, roll back the whole group
*
* Start the transaction, after this ->add() doesn't need to
* do schedulability tests.
*
* Optional.
*/
void (*start_txn) (struct pmu *pmu, unsigned int txn_flags);
/*
* If ->start_txn() disabled the ->add() schedulability test
* then ->commit_txn() is required to perform one. On success
* the transaction is closed. On error the transaction is kept
* open until ->cancel_txn() is called.
*
* Optional.
*/
int (*commit_txn) (struct pmu *pmu);
/*
* Will cancel the transaction, assumes ->del() is called
* for each successful ->add() during the transaction.
*
* Optional.
*/
void (*cancel_txn) (struct pmu *pmu);
/*
* Will return the value for perf_event_mmap_page::index for this event,
* if no implementation is provided it will default to 0 (see
* perf_event_idx_default).
*/
int (*event_idx) (struct perf_event *event); /*optional */
/*
* context-switches callback
*/
void (*sched_task) (struct perf_event_pmu_context *pmu_ctx,
struct task_struct *task, bool sched_in);
/*
* Kmem cache of PMU specific data
*/
struct kmem_cache *task_ctx_cache;
/*
* Set up pmu-private data structures for an AUX area
*/
void *(*setup_aux) (struct perf_event *event, void **pages,
int nr_pages, bool overwrite);
/* optional */
/*
* Free pmu-private AUX data structures
*/
void (*free_aux) (void *aux); /* optional */
/*
* Take a snapshot of the AUX buffer without touching the event
* state, so that preempting ->start()/->stop() callbacks does
* not interfere with their logic. Called in PMI context.
*
* Returns the size of AUX data copied to the output handle.
*
* Optional.
*/
long (*snapshot_aux) (struct perf_event *event,
struct perf_output_handle *handle,
unsigned long size);
/*
* Validate address range filters: make sure the HW supports the
* requested configuration and number of filters; return 0 if the
* supplied filters are valid, -errno otherwise.
*
* Runs in the context of the ioctl()ing process and is not serialized
* with the rest of the PMU callbacks.
*/
int (*addr_filters_validate) (struct list_head *filters);
/* optional */
/*
* Synchronize address range filter configuration:
* translate hw-agnostic filters into hardware configuration in
* event::hw::addr_filters.
*
* Runs as a part of filter sync sequence that is done in ->start()
* callback by calling perf_event_addr_filters_sync().
*
* May (and should) traverse event::addr_filters::list, for which its
* caller provides necessary serialization.
*/
void (*addr_filters_sync) (struct perf_event *event);
/* optional */
/*
* Check if event can be used for aux_output purposes for
* events of this PMU.
*
* Runs from perf_event_open(). Should return 0 for "no match"
* or non-zero for "match".
*/
int (*aux_output_match) (struct perf_event *event);
/* optional */
/*
* Skip programming this PMU on the given CPU. Typically needed for
* big.LITTLE things.
*/
bool (*filter) (struct pmu *pmu, int cpu); /* optional */
/*
* Check period value for PERF_EVENT_IOC_PERIOD ioctl.
*/
int (*check_period) (struct perf_event *event, u64 value); /* optional */
};
enum perf_addr_filter_action_t {
PERF_ADDR_FILTER_ACTION_STOP = 0,
PERF_ADDR_FILTER_ACTION_START,
PERF_ADDR_FILTER_ACTION_FILTER,
};
/**
* struct perf_addr_filter - address range filter definition
* @entry: event's filter list linkage
* @path: object file's path for file-based filters
* @offset: filter range offset
* @size: filter range size (size==0 means single address trigger)
* @action: filter/start/stop
*
* This is a hardware-agnostic filter configuration as specified by the user.
*/
struct perf_addr_filter {
struct list_head entry;
struct path path;
unsigned long offset;
unsigned long size;
enum perf_addr_filter_action_t action;
};
/**
* struct perf_addr_filters_head - container for address range filters
* @list: list of filters for this event
* @lock: spinlock that serializes accesses to the @list and event's
* (and its children's) filter generations.
* @nr_file_filters: number of file-based filters
*
* A child event will use parent's @list (and therefore @lock), so they are
* bundled together; see perf_event_addr_filters().
*/
struct perf_addr_filters_head {
struct list_head list;
raw_spinlock_t lock;
unsigned int nr_file_filters;
};
struct perf_addr_filter_range {
unsigned long start;
unsigned long size;
};
/**
* enum perf_event_state - the states of an event:
*/
enum perf_event_state {
PERF_EVENT_STATE_DEAD = -4,
PERF_EVENT_STATE_EXIT = -3,
PERF_EVENT_STATE_ERROR = -2,
PERF_EVENT_STATE_OFF = -1,
PERF_EVENT_STATE_INACTIVE = 0,
PERF_EVENT_STATE_ACTIVE = 1,
};
struct file;
struct perf_sample_data;
typedef void (*perf_overflow_handler_t)(struct perf_event *,
struct perf_sample_data *,
struct pt_regs *regs);
/*
* Event capabilities. For event_caps and groups caps.
*
* PERF_EV_CAP_SOFTWARE: Is a software event.
* PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
* from any CPU in the package where it is active.
* PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
* cannot be a group leader. If an event with this flag is detached from the
* group it is scheduled out and moved into an unrecoverable ERROR state.
* PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the
* PMU scope where it is active.
*/
#define PERF_EV_CAP_SOFTWARE BIT(0)
#define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1)
#define PERF_EV_CAP_SIBLING BIT(2)
#define PERF_EV_CAP_READ_SCOPE BIT(3)
#define SWEVENT_HLIST_BITS 8
#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS)
struct swevent_hlist {
struct hlist_head heads[SWEVENT_HLIST_SIZE];
struct rcu_head rcu_head;
};
#define PERF_ATTACH_CONTEXT 0x0001
#define PERF_ATTACH_GROUP 0x0002
#define PERF_ATTACH_TASK 0x0004
#define PERF_ATTACH_TASK_DATA 0x0008
#define PERF_ATTACH_GLOBAL_DATA 0x0010
#define PERF_ATTACH_SCHED_CB 0x0020
#define PERF_ATTACH_CHILD 0x0040
#define PERF_ATTACH_EXCLUSIVE 0x0080
#define PERF_ATTACH_CALLCHAIN 0x0100
#define PERF_ATTACH_ITRACE 0x0200
struct bpf_prog;
struct perf_cgroup;
struct perf_buffer;
struct pmu_event_list {
raw_spinlock_t lock;
struct list_head list;
};
/*
* event->sibling_list is modified whole holding both ctx->lock and ctx->mutex
* as such iteration must hold either lock. However, since ctx->lock is an IRQ
* safe lock, and is only held by the CPU doing the modification, having IRQs
* disabled is sufficient since it will hold-off the IPIs.
*/
#ifdef CONFIG_PROVE_LOCKING
#define lockdep_assert_event_ctx(event) \
WARN_ON_ONCE(__lockdep_enabled && \
(this_cpu_read(hardirqs_enabled) && \
lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD))
#else
#define lockdep_assert_event_ctx(event)
#endif
#define for_each_sibling_event(sibling, event) \
lockdep_assert_event_ctx(event); \
if ((event)->group_leader == (event)) \
list_for_each_entry((sibling), &(event)->sibling_list, sibling_list)
/**
* struct perf_event - performance event kernel representation:
*/
struct perf_event {
#ifdef CONFIG_PERF_EVENTS
/*
* entry onto perf_event_context::event_list;
* modifications require ctx->lock
* RCU safe iterations.
*/
struct list_head event_entry;
/*
* Locked for modification by both ctx->mutex and ctx->lock; holding
* either sufficies for read.
*/
struct list_head sibling_list;
struct list_head active_list;
/*
* Node on the pinned or flexible tree located at the event context;
*/
struct rb_node group_node;
u64 group_index;
/*
* We need storage to track the entries in perf_pmu_migrate_context; we
* cannot use the event_entry because of RCU and we want to keep the
* group in tact which avoids us using the other two entries.
*/
struct list_head migrate_entry;
struct hlist_node hlist_entry;
struct list_head active_entry;
int nr_siblings;
/* Not serialized. Only written during event initialization. */
int event_caps;
/* The cumulative AND of all event_caps for events in this group. */
int group_caps;
unsigned int group_generation;
struct perf_event *group_leader;
/*
* event->pmu will always point to pmu in which this event belongs.
* Whereas event->pmu_ctx->pmu may point to other pmu when group of
* different pmu events is created.
*/
struct pmu *pmu;
void *pmu_private;
enum perf_event_state state;
unsigned int attach_state;
local64_t count;
atomic64_t child_count;
/*
* These are the total time in nanoseconds that the event
* has been enabled (i.e. eligible to run, and the task has
* been scheduled in, if this is a per-task event)
* and running (scheduled onto the CPU), respectively.
*/
u64 total_time_enabled;
u64 total_time_running;
u64 tstamp;
struct perf_event_attr attr;
u16 header_size;
u16 id_header_size;
u16 read_size;
struct hw_perf_event hw;
struct perf_event_context *ctx;
/*
* event->pmu_ctx points to perf_event_pmu_context in which the event
* is added. This pmu_ctx can be of other pmu for sw event when that
* sw event is part of a group which also contains non-sw events.
*/
struct perf_event_pmu_context *pmu_ctx;
atomic_long_t refcount;
/*
* These accumulate total time (in nanoseconds) that children
* events have been enabled and running, respectively.
*/
atomic64_t child_total_time_enabled;
atomic64_t child_total_time_running;
/*
* Protect attach/detach and child_list:
*/
struct mutex child_mutex;
struct list_head child_list;
struct perf_event *parent;
int oncpu;
int cpu;
struct list_head owner_entry;
struct task_struct *owner;
/* mmap bits */
struct mutex mmap_mutex;
atomic_t mmap_count;
struct perf_buffer *rb;
struct list_head rb_entry;
unsigned long rcu_batches;
int rcu_pending;
/* poll related */
wait_queue_head_t waitq;
struct fasync_struct *fasync;
/* delayed work for NMIs and such */
unsigned int pending_wakeup;
unsigned int pending_kill;
unsigned int pending_disable;
unsigned long pending_addr; /* SIGTRAP */
struct irq_work pending_irq;
struct irq_work pending_disable_irq;
struct callback_head pending_task;
unsigned int pending_work;
atomic_t event_limit;
/* address range filters */
struct perf_addr_filters_head addr_filters;
/* vma address array for file-based filders */
struct perf_addr_filter_range *addr_filter_ranges;
unsigned long addr_filters_gen;
/* for aux_output events */
struct perf_event *aux_event;
void (*destroy)(struct perf_event *);
struct rcu_head rcu_head;
struct pid_namespace *ns;
u64 id;
atomic64_t lost_samples;
u64 (*clock)(void);
perf_overflow_handler_t overflow_handler;
void *overflow_handler_context;
struct bpf_prog *prog;
u64 bpf_cookie;
#ifdef CONFIG_EVENT_TRACING
struct trace_event_call *tp_event;
struct event_filter *filter;
#ifdef CONFIG_FUNCTION_TRACER
struct ftrace_ops ftrace_ops;
#endif
#endif
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp; /* cgroup event is attach to */
#endif
#ifdef CONFIG_SECURITY
void *security;
#endif
struct list_head sb_list;
/*
* Certain events gets forwarded to another pmu internally by over-
* writing kernel copy of event->attr.type without user being aware
* of it. event->orig_type contains original 'type' requested by
* user.
*/
__u32 orig_type;
#endif /* CONFIG_PERF_EVENTS */
};
/*
* ,-----------------------[1:n]------------------------.
* V V
* perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event
* | |
* `--[n:1]-> pmu <-[1:n]--'
*
*
* struct perf_event_pmu_context lifetime is refcount based and RCU freed
* (similar to perf_event_context). Locking is as if it were a member of
* perf_event_context; specifically:
*
* modification, both: ctx->mutex && ctx->lock
* reading, either: ctx->mutex || ctx->lock
*
* There is one exception to this; namely put_pmu_ctx() isn't always called
* with ctx->mutex held; this means that as long as we can guarantee the epc
* has events the above rules hold.
*
* Specificially, sys_perf_event_open()'s group_leader case depends on
* ctx->mutex pinning the configuration. Since we hold a reference on
* group_leader (through the filedesc) it can't go away, therefore it's
* associated pmu_ctx must exist and cannot change due to ctx->mutex.
*
* perf_event holds a refcount on perf_event_context
* perf_event holds a refcount on perf_event_pmu_context
*/
struct perf_event_pmu_context {
struct pmu *pmu;
struct perf_event_context *ctx;
struct list_head pmu_ctx_entry;
struct list_head pinned_active;
struct list_head flexible_active;
/* Used to identify the per-cpu perf_event_pmu_context */
unsigned int embedded : 1;
unsigned int nr_events;
unsigned int nr_cgroups;
unsigned int nr_freq;
atomic_t refcount; /* event <-> epc */
struct rcu_head rcu_head;
/*
* Set when one or more (plausibly active) event can't be scheduled
* due to pmu overcommit or pmu constraints, except tolerant to
* events not necessary to be active due to scheduling constraints,
* such as cgroups.
*/
int rotate_necessary;
};
static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc)
{
return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active);
}
struct perf_event_groups {
struct rb_root tree;
u64 index;
};
/**
* struct perf_event_context - event context structure
*
* Used as a container for task events and CPU events as well:
*/
struct perf_event_context {
/*
* Protect the states of the events in the list,
* nr_active, and the list:
*/
raw_spinlock_t lock;
/*
* Protect the list of events. Locking either mutex or lock
* is sufficient to ensure the list doesn't change; to change
* the list you need to lock both the mutex and the spinlock.
*/
struct mutex mutex;
struct list_head pmu_ctx_list;
struct perf_event_groups pinned_groups;
struct perf_event_groups flexible_groups;
struct list_head event_list;
int nr_events;
int nr_user;
int is_active;
int nr_stat;
int nr_freq;
int rotate_disable;
refcount_t refcount; /* event <-> ctx */
struct task_struct *task;
/*
* Context clock, runs when context enabled.
*/
u64 time;
u64 timestamp;
u64 timeoffset;
/*
* These fields let us detect when two contexts have both
* been cloned (inherited) from a common ancestor.
*/
struct perf_event_context *parent_ctx;
u64 parent_gen;
u64 generation;
int pin_count;
#ifdef CONFIG_CGROUP_PERF
int nr_cgroups; /* cgroup evts */
#endif
struct rcu_head rcu_head;
/*
* The count of events for which using the switch-out fast path
* should be avoided.
*
* Sum (event->pending_work + events with
* (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)))
*
* The SIGTRAP is targeted at ctx->task, as such it won't do changing
* that until the signal is delivered.
*/
local_t nr_no_switch_fast;
};
/**
* struct perf_ctx_data - PMU specific data for a task
* @rcu_head: To avoid the race on free PMU specific data
* @refcount: To track users
* @global: To track system-wide users
* @ctx_cache: Kmem cache of PMU specific data
* @data: PMU specific data
*
* Currently, the struct is only used in Intel LBR call stack mode to
* save/restore the call stack of a task on context switches.
*
* The rcu_head is used to prevent the race on free the data.
* The data only be allocated when Intel LBR call stack mode is enabled.
* The data will be freed when the mode is disabled.
* The content of the data will only be accessed in context switch, which
* should be protected by rcu_read_lock().
*
* Because of the alignment requirement of Intel Arch LBR, the Kmem cache
* is used to allocate the PMU specific data. The ctx_cache is to track
* the Kmem cache.
*
* Careful: Struct perf_ctx_data is added as a pointer in struct task_struct.
* When system-wide Intel LBR call stack mode is enabled, a buffer with
* constant size will be allocated for each task.
* Also, system memory consumption can further grow when the size of
* struct perf_ctx_data enlarges.
*/
struct perf_ctx_data {
struct rcu_head rcu_head;
refcount_t refcount;
int global;
struct kmem_cache *ctx_cache;
void *data;
};
struct perf_cpu_pmu_context {
struct perf_event_pmu_context epc;
struct perf_event_pmu_context *task_epc;
struct list_head sched_cb_entry;
int sched_cb_usage;
int active_oncpu;
int exclusive;
int pmu_disable_count;
raw_spinlock_t hrtimer_lock;
struct hrtimer hrtimer;
ktime_t hrtimer_interval;
unsigned int hrtimer_active;
};
/**
* struct perf_event_cpu_context - per cpu event context structure
*/
struct perf_cpu_context {
struct perf_event_context ctx;
struct perf_event_context *task_ctx;
int online;
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
#endif
/*
* Per-CPU storage for iterators used in visit_groups_merge. The default
* storage is of size 2 to hold the CPU and any CPU event iterators.
*/
int heap_size;
struct perf_event **heap;
struct perf_event *heap_default[2];
};
struct perf_output_handle {
struct perf_event *event;
struct perf_buffer *rb;
unsigned long wakeup;
unsigned long size;
union {
u64 flags; /* perf_output*() */
u64 aux_flags; /* perf_aux_output*() */
struct {
u64 skip_read : 1;
};
};
union {
void *addr;
unsigned long head;
};
int page;
};
struct bpf_perf_event_data_kern {
bpf_user_pt_regs_t *regs;
struct perf_sample_data *data;
struct perf_event *event;
};
#ifdef CONFIG_CGROUP_PERF
/*
* perf_cgroup_info keeps track of time_enabled for a cgroup.
* This is a per-cpu dynamically allocated data structure.
*/
struct perf_cgroup_info {
u64 time;
u64 timestamp;
u64 timeoffset;
int active;
};
struct perf_cgroup {
struct cgroup_subsys_state css;
struct perf_cgroup_info __percpu *info;
};
/*
* Must ensure cgroup is pinned (css_get) before calling
* this function. In other words, we cannot call this function
* if there is no cgroup event for the current CPU context.
*/
static inline struct perf_cgroup *
perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
{
return container_of(task_css_check(task, perf_event_cgrp_id,
ctx ? lockdep_is_held(&ctx->lock)
: true),
struct perf_cgroup, css);
}
#endif /* CONFIG_CGROUP_PERF */
#ifdef CONFIG_PERF_EVENTS
extern struct perf_event_context *perf_cpu_task_ctx(void);
extern void *perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event);
extern void perf_aux_output_end(struct perf_output_handle *handle,
unsigned long size);
extern int perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size);
extern void *perf_get_aux(struct perf_output_handle *handle);
extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
extern void perf_event_itrace_started(struct perf_event *event);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
extern void __perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task);
extern void __perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next);
extern int perf_event_init_task(struct task_struct *child, u64 clone_flags);
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
extern struct file *perf_event_get(unsigned int fd);
extern const struct perf_event *perf_get_event(struct file *file);
extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
extern void perf_sched_cb_dec(struct pmu *pmu);
extern void perf_sched_cb_inc(struct pmu *pmu);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
extern void perf_pmu_resched(struct pmu *pmu);
extern int perf_event_refresh(struct perf_event *event, int refresh);
extern void perf_event_update_userpage(struct perf_event *event);
extern int perf_event_release_kernel(struct perf_event *event);
extern struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr,
int cpu,
struct task_struct *task,
perf_overflow_handler_t callback,
void *context);
extern void perf_pmu_migrate_context(struct pmu *pmu,
int src_cpu, int dst_cpu);
int perf_event_read_local(struct perf_event *event, u64 *value,
u64 *enabled, u64 *running);
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
static inline bool branch_sample_no_flags(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
}
static inline bool branch_sample_no_cycles(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
}
static inline bool branch_sample_type(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
}
static inline bool branch_sample_hw_index(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
}
static inline bool branch_sample_priv(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
}
static inline bool branch_sample_counters(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
}
static inline bool branch_sample_call_stack(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
struct perf_sample_data {
/*
* Fields set by perf_sample_data_init() unconditionally,
* group so as to minimize the cachelines touched.
*/
u64 sample_flags;
u64 period;
u64 dyn_size;
/*
* Fields commonly set by __perf_event_header__init_id(),
* group so as to minimize the cachelines touched.
*/
u64 type;
struct {
u32 pid;
u32 tid;
} tid_entry;
u64 time;
u64 id;
struct {
u32 cpu;
u32 reserved;
} cpu_entry;
/*
* The other fields, optionally {set,used} by
* perf_{prepare,output}_sample().
*/
u64 ip;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
u64 *br_stack_cntr;
union perf_sample_weight weight;
union perf_mem_data_src data_src;
u64 txn;
struct perf_regs regs_user;
struct perf_regs regs_intr;
u64 stack_user_size;
u64 stream_id;
u64 cgroup;
u64 addr;
u64 phys_addr;
u64 data_page_size;
u64 code_page_size;
u64 aux_size;
} ____cacheline_aligned;
/* default value for data source */
#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
PERF_MEM_S(LVL, NA) |\
PERF_MEM_S(SNOOP, NA) |\
PERF_MEM_S(LOCK, NA) |\
PERF_MEM_S(TLB, NA) |\
PERF_MEM_S(LVLNUM, NA))
static inline void perf_sample_data_init(struct perf_sample_data *data,
u64 addr, u64 period)
{
/* remaining struct members initialized in perf_prepare_sample() */
data->sample_flags = PERF_SAMPLE_PERIOD;
data->period = period;
data->dyn_size = 0;
if (addr) {
data->addr = addr;
data->sample_flags |= PERF_SAMPLE_ADDR;
}
}
static inline void perf_sample_save_callchain(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs)
{
int size = 1;
if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
return;
if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN))
return;
data->callchain = perf_callchain(event, regs);
size += data->callchain->nr;
data->dyn_size += size * sizeof(u64);
data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
}
static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
struct perf_event *event,
struct perf_raw_record *raw)
{
struct perf_raw_frag *frag = &raw->frag;
u32 sum = 0;
int size;
if (!(event->attr.sample_type & PERF_SAMPLE_RAW))
return;
if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW))
return;
do {
sum += frag->size;
if (perf_raw_frag_last(frag))
break;
frag = frag->next;
} while (1);
size = round_up(sum + sizeof(u32), sizeof(u64));
raw->size = size - sizeof(u32);
frag->pad = raw->size - sum;
data->raw = raw;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_RAW;
}
static inline bool has_branch_stack(struct perf_event *event)
{
return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
}
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
struct perf_branch_stack *brs,
u64 *brs_cntr)
{
int size = sizeof(u64); /* nr */
if (!has_branch_stack(event))
return;
if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK))
return;
if (branch_sample_hw_index(event))
size += sizeof(u64);
brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr);
size += brs->nr * sizeof(struct perf_branch_entry);
/*
* The extension space for counters is appended after the
* struct perf_branch_stack. It is used to store the occurrences
* of events of each branch.
*/
if (brs_cntr)
size += brs->nr * sizeof(u64);
data->br_stack = brs;
data->br_stack_cntr = brs_cntr;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
}
static inline u32 perf_sample_data_size(struct perf_sample_data *data,
struct perf_event *event)
{
u32 size = sizeof(struct perf_event_header);
size += event->header_size + event->id_header_size;
size += data->dyn_size;
return size;
}
/*
* Clear all bitfields in the perf_branch_entry.
* The to and from fields are not cleared because they are
* systematically modified by caller.
*/
static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
{
br->mispred = 0;
br->predicted = 0;
br->in_tx = 0;
br->abort = 0;
br->cycles = 0;
br->type = 0;
br->spec = PERF_BR_SPEC_NA;
br->reserved = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event);
extern void perf_prepare_sample(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);
extern void perf_prepare_header(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);
extern int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern void perf_event_output_forward(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern void perf_event_output_backward(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern int perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
static inline bool
is_default_overflow_handler(struct perf_event *event)
{
perf_overflow_handler_t overflow_handler = event->overflow_handler;
if (likely(overflow_handler == perf_event_output_forward))
return true;
if (unlikely(overflow_handler == perf_event_output_backward))
return true;
return false;
}
extern void
perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event);
extern void
perf_event__output_id_sample(struct perf_event *event,
struct perf_output_handle *handle,
struct perf_sample_data *sample);
extern void
perf_log_lost_samples(struct perf_event *event, u64 lost);
static inline bool event_has_any_exclude_flag(struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
return attr->exclude_idle || attr->exclude_user ||
attr->exclude_kernel || attr->exclude_hv ||
attr->exclude_guest || attr->exclude_host;
}
static inline bool is_sampling_event(struct perf_event *event)
{
return event->attr.sample_period != 0;
}
/*
* Return 1 for a software event, 0 for a hardware event
*/
static inline int is_software_event(struct perf_event *event)
{
return event->event_caps & PERF_EV_CAP_SOFTWARE;
}
/*
* Return 1 for event in sw context, 0 for event in hw context
*/
static inline int in_software_context(struct perf_event *event)
{
return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context;
}
static inline int is_exclusive_pmu(struct pmu *pmu)
{
return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE;
}
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
#ifndef perf_arch_fetch_caller_regs
static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
#endif
/*
* When generating a perf sample in-line, instead of from an interrupt /
* exception, we lack a pt_regs. This is typically used from software events
* like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
*
* We typically don't need a full set, but (for x86) do require:
* - ip for PERF_SAMPLE_IP
* - cs for user_mode() tests
* - sp for PERF_SAMPLE_CALLCHAIN
* - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
*
* NOTE: assumes @regs is otherwise already 0 filled; this is important for
* things like PERF_SAMPLE_REGS_INTR.
*/
static inline void perf_fetch_caller_regs(struct pt_regs *regs)
{
perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
}
static __always_inline void
perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr);
}
DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
/*
* 'Special' version for the scheduler, it hard assumes no recursion,
* which is guaranteed by us not actually scheduling inside other swevents
* because those disable preemption.
*/
static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
{
struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
perf_fetch_caller_regs(regs);
___perf_sw_event(event_id, nr, regs, addr);
}
extern struct static_key_false perf_sched_events;
static __always_inline bool __perf_sw_enabled(int swevt)
{
return static_key_false(&perf_swevent_enabled[swevt]);
}
static inline void perf_event_task_migrate(struct task_struct *task)
{
if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS))
task->sched_migrated = 1;
}
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_branch_unlikely(&perf_sched_events))
__perf_event_task_sched_in(prev, task);
if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) &&
task->sched_migrated) {
__perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
task->sched_migrated = 0;
}
}
static inline void perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next)
{
if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES))
__perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
#ifdef CONFIG_CGROUP_PERF
if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) &&
perf_cgroup_from_task(prev, NULL) !=
perf_cgroup_from_task(next, NULL))
__perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0);
#endif
if (static_branch_unlikely(&perf_sched_events))
__perf_event_task_sched_out(prev, next);
}
extern void perf_event_mmap(struct vm_area_struct *vma);
extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
bool unregister, const char *sym);
extern void perf_event_bpf_event(struct bpf_prog *prog,
enum perf_bpf_event_type type,
u16 flags);
#ifdef CONFIG_GUEST_PERF_EVENTS
extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state);
DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip);
DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);
static inline unsigned int perf_guest_state(void)
{
return static_call(__perf_guest_state)();
}
static inline unsigned long perf_guest_get_ip(void)
{
return static_call(__perf_guest_get_ip)();
}
static inline unsigned int perf_guest_handle_intel_pt_intr(void)
{
return static_call(__perf_guest_handle_intel_pt_intr)();
}
extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
#else
static inline unsigned int perf_guest_state(void) { return 0; }
static inline unsigned long perf_guest_get_ip(void) { return 0; }
static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; }
#endif /* CONFIG_GUEST_PERF_EVENTS */
extern void perf_event_exec(void);
extern void perf_event_comm(struct task_struct *tsk, bool exec);
extern void perf_event_namespaces(struct task_struct *tsk);
extern void perf_event_fork(struct task_struct *tsk);
extern void perf_event_text_poke(const void *addr,
const void *old_bytes, size_t old_len,
const void *new_bytes, size_t new_len);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(int max_stack);
extern void put_callchain_buffers(void);
extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
extern void put_callchain_entry(int rctx);
extern int sysctl_perf_event_max_stack;
extern int sysctl_perf_event_max_contexts_per_stack;
static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
++ctx->contexts;
return 0;
} else {
ctx->contexts_maxed = true;
return -1; /* no more room, stop walking the stack */
}
}
static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
++ctx->nr;
return 0;
} else {
return -1; /* no more room, stop walking the stack */
}
}
extern int sysctl_perf_event_paranoid;
extern int sysctl_perf_event_sample_rate;
extern void perf_sample_event_took(u64 sample_len_ns);
/* Access to perf_event_open(2) syscall. */
#define PERF_SECURITY_OPEN 0
/* Finer grained perf_event_open(2) access control. */
#define PERF_SECURITY_CPU 1
#define PERF_SECURITY_KERNEL 2
#define PERF_SECURITY_TRACEPOINT 3
static inline int perf_is_paranoid(void)
{
return sysctl_perf_event_paranoid > -1;
}
int perf_allow_kernel(void);
static inline int perf_allow_cpu(void)
{
if (sysctl_perf_event_paranoid > 0 && !perfmon_capable())
return -EACCES;
return security_perf_event_open(PERF_SECURITY_CPU);
}
static inline int perf_allow_tracepoint(void)
{
if (sysctl_perf_event_paranoid > -1 && !perfmon_capable())
return -EPERM;
return security_perf_event_open(PERF_SECURITY_TRACEPOINT);
}
extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs);
extern void perf_event_init(void);
extern void perf_tp_event(u16 event_type, u64 count, void *record,
int entry_size, struct pt_regs *regs,
struct hlist_head *head, int rctx,
struct task_struct *task);
extern void perf_bp_event(struct perf_event *event, void *data);
extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs);
extern unsigned long perf_instruction_pointer(struct perf_event *event,
struct pt_regs *regs);
#ifndef perf_arch_misc_flags
# define perf_arch_misc_flags(regs) \
(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
# define perf_arch_instruction_pointer(regs) instruction_pointer(regs)
#endif
#ifndef perf_arch_bpf_user_pt_regs
# define perf_arch_bpf_user_pt_regs(regs) regs
#endif
#ifndef perf_arch_guest_misc_flags
static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
{
unsigned long guest_state = perf_guest_state();
if (!(guest_state & PERF_GUEST_ACTIVE))
return 0;
if (guest_state & PERF_GUEST_USER)
return PERF_RECORD_MISC_GUEST_USER;
else
return PERF_RECORD_MISC_GUEST_KERNEL;
}
# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs)
#endif
static inline bool needs_branch_stack(struct perf_event *event)
{
return event->attr.branch_sample_type != 0;
}
static inline bool has_aux(struct perf_event *event)
{
return event->pmu->setup_aux;
}
static inline bool has_aux_action(struct perf_event *event)
{
return event->attr.aux_sample_size ||
event->attr.aux_pause ||
event->attr.aux_resume;
}
static inline bool is_write_backward(struct perf_event *event)
{
return !!event->attr.write_backward;
}
static inline bool has_addr_filter(struct perf_event *event)
{
return event->pmu->nr_addr_filters;
}
/*
* An inherited event uses parent's filters
*/
static inline struct perf_addr_filters_head *
perf_event_addr_filters(struct perf_event *event)
{
struct perf_addr_filters_head *ifh = &event->addr_filters;
if (event->parent)
ifh = &event->parent->addr_filters;
return ifh;
}
static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
{
/* Only the parent has fasync state */
if (event->parent)
event = event->parent;
return &event->fasync;
}
extern void perf_event_addr_filters_sync(struct perf_event *event);
extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event, unsigned int size);
extern int perf_output_begin_forward(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
extern int perf_output_begin_backward(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
extern unsigned int perf_output_skip(struct perf_output_handle *handle,
unsigned int len);
extern long perf_output_copy_aux(struct perf_output_handle *aux_handle,
struct perf_output_handle *handle,
unsigned long from, unsigned long to);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
extern u64 perf_swevent_set_period(struct perf_event *event);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
extern void perf_event_disable_local(struct perf_event *event);
extern void perf_event_disable_inatomic(struct perf_event *event);
extern void perf_event_task_tick(void);
extern int perf_event_account_interrupt(struct perf_event *event);
extern int perf_event_period(struct perf_event *event, u64 value);
extern u64 perf_event_pause(struct perf_event *event, bool reset);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event) { return NULL; }
static inline void
perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{ }
static inline int
perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size) { return -EINVAL; }
static inline void *
perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
perf_event_task_migrate(struct task_struct *task) { }
static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
static inline void
perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next) { }
static inline int perf_event_init_task(struct task_struct *child,
u64 clone_flags) { return 0; }
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
static inline const struct perf_event *perf_get_event(struct file *file)
{
return ERR_PTR(-EINVAL);
}
static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
return ERR_PTR(-EINVAL);
}
static inline int perf_event_read_local(struct perf_event *event, u64 *value,
u64 *enabled, u64 *running)
{
return -EINVAL;
}
static inline void perf_event_print_debug(void) { }
static inline int perf_event_task_disable(void) { return -EINVAL; }
static inline int perf_event_task_enable(void) { return -EINVAL; }
static inline int perf_event_refresh(struct perf_event *event, int refresh)
{
return -EINVAL;
}
static inline void
perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { }
static inline void
perf_bp_event(struct perf_event *event, void *data) { }
static inline void perf_event_mmap(struct vm_area_struct *vma) { }
typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
bool unregister, const char *sym) { }
static inline void perf_event_bpf_event(struct bpf_prog *prog,
enum perf_bpf_event_type type,
u16 flags) { }
static inline void perf_event_exec(void) { }
static inline void perf_event_comm(struct task_struct *tsk, bool exec) { }
static inline void perf_event_namespaces(struct task_struct *tsk) { }
static inline void perf_event_fork(struct task_struct *tsk) { }
static inline void perf_event_text_poke(const void *addr,
const void *old_bytes,
size_t old_len,
const void *new_bytes,
size_t new_len) { }
static inline void perf_event_init(void) { }
static inline int perf_swevent_get_recursion_context(void) { return -1; }
static inline void perf_swevent_put_recursion_context(int rctx) { }
static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; }
static inline void perf_event_enable(struct perf_event *event) { }
static inline void perf_event_disable(struct perf_event *event) { }
static inline int __perf_event_disable(void *info) { return -1; }
static inline void perf_event_task_tick(void) { }
static inline int perf_event_release_kernel(struct perf_event *event) { return 0; }
static inline int perf_event_period(struct perf_event *event, u64 value)
{
return -EINVAL;
}
static inline u64 perf_event_pause(struct perf_event *event, bool reset)
{
return 0;
}
static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs)
{
return 0;
}
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
extern void perf_restore_debug_store(void);
#else
static inline void perf_restore_debug_store(void) { }
#endif
#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
struct perf_pmu_events_attr {
struct device_attribute attr;
u64 id;
const char *event_str;
};
struct perf_pmu_events_ht_attr {
struct device_attribute attr;
u64 id;
const char *event_str_ht;
const char *event_str_noht;
};
struct perf_pmu_events_hybrid_attr {
struct device_attribute attr;
u64 id;
const char *event_str;
u64 pmu_type;
};
struct perf_pmu_format_hybrid_attr {
struct device_attribute attr;
u64 pmu_type;
};
ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, _show, NULL), \
.id = _id, \
};
#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
.id = 0, \
.event_str = _str, \
};
#define PMU_EVENT_ATTR_ID(_name, _show, _id) \
(&((struct perf_pmu_events_attr[]) { \
{ .attr = __ATTR(_name, 0444, _show, NULL), \
.id = _id, } \
})[0].attr.attr)
#define PMU_FORMAT_ATTR_SHOW(_name, _format) \
static ssize_t \
_name##_show(struct device *dev, \
struct device_attribute *attr, \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
return sprintf(page, _format "\n"); \
} \
#define PMU_FORMAT_ATTR(_name, _format) \
PMU_FORMAT_ATTR_SHOW(_name, _format) \
\
static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
/* Performance counter hotplug functions */
#ifdef CONFIG_PERF_EVENTS
int perf_event_init_cpu(unsigned int cpu);
int perf_event_exit_cpu(unsigned int cpu);
#else
#define perf_event_init_cpu NULL
#define perf_event_exit_cpu NULL
#endif
extern void arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg,
u64 now);
/*
* Snapshot branch stack on software events.
*
* Branch stack can be very useful in understanding software events. For
* example, when a long function, e.g. sys_perf_event_open, returns an
* errno, it is not obvious why the function failed. Branch stack could
* provide very helpful information in this type of scenarios.
*
* On software event, it is necessary to stop the hardware branch recorder
* fast. Otherwise, the hardware register/buffer will be flushed with
* entries of the triggering event. Therefore, static call is used to
* stop the hardware recorder.
*/
/*
* cnt is the number of entries allocated for entries.
* Return number of entries copied to .
*/
typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
unsigned int cnt);
DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
#ifndef PERF_NEEDS_LOPWR_CB
static inline void perf_lopwr_cb(bool mode)
{
}
#endif
#endif /* _LINUX_PERF_EVENT_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_LIST_NULLS_H
#define _LINUX_LIST_NULLS_H
#include <linux/poison.h>
#include <linux/const.h>
/*
* Special version of lists, where end of list is not a NULL pointer,
* but a 'nulls' marker, which can have many different values.
* (up to 2^31 different values guaranteed on all platforms)
*
* In the standard hlist, termination of a list is the NULL pointer.
* In this special 'nulls' variant, we use the fact that objects stored in
* a list are aligned on a word (4 or 8 bytes alignment).
* We therefore use the last significant bit of 'ptr' :
* Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1)
* Set to 0 : This is a pointer to some object (ptr)
*/
struct hlist_nulls_head {
struct hlist_nulls_node *first;
};
struct hlist_nulls_node {
struct hlist_nulls_node *next, **pprev;
};
#define NULLS_MARKER(value) (1UL | (((long)value) << 1))
#define INIT_HLIST_NULLS_HEAD(ptr, nulls) \
((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
#define HLIST_NULLS_HEAD_INIT(nulls) {.first = (struct hlist_nulls_node *)NULLS_MARKER(nulls)}
#define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
#define hlist_nulls_entry_safe(ptr, type, member) \
({ typeof(ptr) ____ptr = (ptr); \
!is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \
})
/**
* ptr_is_a_nulls - Test if a ptr is a nulls
* @ptr: ptr to be tested
*
*/
static inline int is_a_nulls(const struct hlist_nulls_node *ptr)
{
return ((unsigned long)ptr & 1);
}
/**
* get_nulls_value - Get the 'nulls' value of the end of chain
* @ptr: end of chain
*
* Should be called only if is_a_nulls(ptr);
*/
static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr)
{
return ((unsigned long)ptr) >> 1;
}
/**
* hlist_nulls_unhashed - Has node been removed and reinitialized?
* @h: Node to be checked
*
* Not that not all removal functions will leave a node in unhashed state.
* For example, hlist_del_init_rcu() leaves the node in unhashed state,
* but hlist_nulls_del() does not.
*/
static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h)
{
return !h->pprev;
}
/**
* hlist_nulls_unhashed_lockless - Has node been removed and reinitialized?
* @h: Node to be checked
*
* Not that not all removal functions will leave a node in unhashed state.
* For example, hlist_del_init_rcu() leaves the node in unhashed state,
* but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this
* function may be used locklessly.
*/
static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h)
{
return !READ_ONCE(h->pprev);
}
static inline int hlist_nulls_empty(const struct hlist_nulls_head *h)
{
return is_a_nulls(READ_ONCE(h->first));
}
static inline void hlist_nulls_add_head(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *first = h->first;
n->next = first;
WRITE_ONCE(n->pprev, &h->first);
h->first = n;
if (!is_a_nulls(first))
WRITE_ONCE(first->pprev, &n->next);
}
static inline void __hlist_nulls_del(struct hlist_nulls_node *n)
{
struct hlist_nulls_node *next = n->next;
struct hlist_nulls_node **pprev = n->pprev;
WRITE_ONCE(*pprev, next);
if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev);
}
static inline void hlist_nulls_del(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
WRITE_ONCE(n->pprev, LIST_POISON2);
}
/**
* hlist_nulls_for_each_entry - iterate over list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*
*/
#define hlist_nulls_for_each_entry(tpos, pos, head, member) \
for (pos = (head)->first; \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
/**
* hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_node to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*
*/
#define hlist_nulls_for_each_entry_from(tpos, pos, member) \
for (; (!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_BITOPS_H
#define _LINUX_BITOPS_H
#include <asm/types.h>
#include <linux/bits.h>
#include <linux/typecheck.h>
#include <uapi/linux/kernel.h>
#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
#define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
#define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
#define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
#define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE)
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
extern unsigned int __sw_hweight32(unsigned int w);
extern unsigned long __sw_hweight64(__u64 w);
/*
* Defined here because those may be needed by architecture-specific static
* inlines.
*/
#include <asm-generic/bitops/generic-non-atomic.h>
/*
* Many architecture-specific non-atomic bitops contain inline asm code and due
* to that the compiler can't optimize them to compile-time expressions or
* constants. In contrary, generic_*() helpers are defined in pure C and
* compilers optimize them just well.
* Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively
* equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when
* the arguments can be resolved at compile time. That expression itself is a
* constant and doesn't bring any functional changes to the rest of cases.
* The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when
* passing a bitmap from .bss or .data (-> `!!addr` is always true).
*/
#define bitop(op, nr, addr) \
((__builtin_constant_p(nr) && \
__builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) && \
(uintptr_t)(addr) != (uintptr_t)NULL && \
__builtin_constant_p(*(const unsigned long *)(addr))) ? \
const##op(nr, addr) : op(nr, addr))
/*
* The following macros are non-atomic versions of their non-underscored
* counterparts.
*/
#define __set_bit(nr, addr) bitop(___set_bit, nr, addr)
#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr)
#define __change_bit(nr, addr) bitop(___change_bit, nr, addr)
#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr)
#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr)
#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr)
#define test_bit(nr, addr) bitop(_test_bit, nr, addr)
#define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr)
/*
* Include this here because some architectures need generic_ffs/fls in
* scope
*/
#include <asm/bitops.h>
/* Check that the bitops prototypes are sane */
#define __check_bitop_pr(name) \
static_assert(__same_type(arch_##name, generic_##name) && \
__same_type(const_##name, generic_##name) && \
__same_type(_##name, generic_##name))
__check_bitop_pr(__set_bit);
__check_bitop_pr(__clear_bit);
__check_bitop_pr(__change_bit);
__check_bitop_pr(__test_and_set_bit);
__check_bitop_pr(__test_and_clear_bit);
__check_bitop_pr(__test_and_change_bit);
__check_bitop_pr(test_bit);
__check_bitop_pr(test_bit_acquire);
#undef __check_bitop_pr
static inline int get_bitmask_order(unsigned int count)
{
int order;
order = fls(count);
return order; /* We could be slightly more clever with -1 here... */
}
static __always_inline unsigned long hweight_long(unsigned long w)
{
return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w);
}
/**
* rol64 - rotate a 64-bit value left
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u64 rol64(__u64 word, unsigned int shift)
{
return (word << (shift & 63)) | (word >> ((-shift) & 63));
}
/**
* ror64 - rotate a 64-bit value right
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u64 ror64(__u64 word, unsigned int shift)
{
return (word >> (shift & 63)) | (word << ((-shift) & 63));
}
/**
* rol32 - rotate a 32-bit value left
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u32 rol32(__u32 word, unsigned int shift)
{
return (word << (shift & 31)) | (word >> ((-shift) & 31));
}
/**
* ror32 - rotate a 32-bit value right
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u32 ror32(__u32 word, unsigned int shift)
{
return (word >> (shift & 31)) | (word << ((-shift) & 31));
}
/**
* rol16 - rotate a 16-bit value left
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u16 rol16(__u16 word, unsigned int shift)
{
return (word << (shift & 15)) | (word >> ((-shift) & 15));
}
/**
* ror16 - rotate a 16-bit value right
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u16 ror16(__u16 word, unsigned int shift)
{
return (word >> (shift & 15)) | (word << ((-shift) & 15));
}
/**
* rol8 - rotate an 8-bit value left
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u8 rol8(__u8 word, unsigned int shift)
{
return (word << (shift & 7)) | (word >> ((-shift) & 7));
}
/**
* ror8 - rotate an 8-bit value right
* @word: value to rotate
* @shift: bits to roll
*/
static inline __u8 ror8(__u8 word, unsigned int shift)
{
return (word >> (shift & 7)) | (word << ((-shift) & 7));
}
/**
* sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
* @value: value to sign extend
* @index: 0 based bit index (0<=index<32) to sign bit
*
* This is safe to use for 16- and 8-bit types as well.
*/
static __always_inline __s32 sign_extend32(__u32 value, int index)
{
__u8 shift = 31 - index;
return (__s32)(value << shift) >> shift;
}
/**
* sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
* @value: value to sign extend
* @index: 0 based bit index (0<=index<64) to sign bit
*/
static __always_inline __s64 sign_extend64(__u64 value, int index)
{
__u8 shift = 63 - index;
return (__s64)(value << shift) >> shift;
}
static inline unsigned int fls_long(unsigned long l)
{
if (sizeof(l) == 4)
return fls(l);
return fls64(l);
}
static inline int get_count_order(unsigned int count)
{
if (count == 0)
return -1;
return fls(--count);
}
/**
* get_count_order_long - get order after rounding @l up to power of 2
* @l: parameter
*
* it is same as get_count_order() but with long type parameter
*/
static inline int get_count_order_long(unsigned long l)
{
if (l == 0UL)
return -1;
return (int)fls_long(--l);
}
/**
* parity8 - get the parity of an u8 value
* @value: the value to be examined
*
* Determine the parity of the u8 argument.
*
* Returns:
* 0 for even parity, 1 for odd parity
*
* Note: This function informs you about the current parity. Example to bail
* out when parity is odd:
*
* if (parity8(val) == 1)
* return -EBADMSG;
*
* If you need to calculate a parity bit, you need to draw the conclusion from
* this result yourself. Example to enforce odd parity, parity bit is bit 7:
*
* if (parity8(val) == 0)
* val ^= BIT(7);
*/
static inline int parity8(u8 val)
{
/*
* One explanation of this algorithm:
* https://funloop.org/codex/problem/parity/README.html
*/
val ^= val >> 4;
return (0x6996 >> (val & 0xf)) & 1;
}
/**
* __ffs64 - find first set bit in a 64 bit word
* @word: The 64 bit word
*
* On 64 bit arches this is a synonym for __ffs
* The result is not defined if no bits are set, so check that @word
* is non-zero before calling this.
*/
static inline unsigned int __ffs64(u64 word)
{
#if BITS_PER_LONG == 32
if (((u32)word) == 0UL)
return __ffs((u32)(word >> 32)) + 32;
#elif BITS_PER_LONG != 64
#error BITS_PER_LONG not 32 or 64
#endif
return __ffs((unsigned long)word);
}
/**
* fns - find N'th set bit in a word
* @word: The word to search
* @n: Bit to find
*/
static inline unsigned int fns(unsigned long word, unsigned int n)
{
while (word && n--)
word &= word - 1;
return word ? __ffs(word) : BITS_PER_LONG;
}
/**
* assign_bit - Assign value to a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
* @value: the value to assign
*/
#define assign_bit(nr, addr, value) \
((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr)))
#define __assign_bit(nr, addr, value) \
((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr)))
/**
* __ptr_set_bit - Set bit in a pointer's value
* @nr: the bit to set
* @addr: the address of the pointer variable
*
* Example:
* void *p = foo();
* __ptr_set_bit(bit, &p);
*/
#define __ptr_set_bit(nr, addr) \
({ \
typecheck_pointer(*(addr)); \
__set_bit(nr, (unsigned long *)(addr)); \
})
/**
* __ptr_clear_bit - Clear bit in a pointer's value
* @nr: the bit to clear
* @addr: the address of the pointer variable
*
* Example:
* void *p = foo();
* __ptr_clear_bit(bit, &p);
*/
#define __ptr_clear_bit(nr, addr) \
({ \
typecheck_pointer(*(addr)); \
__clear_bit(nr, (unsigned long *)(addr)); \
})
/**
* __ptr_test_bit - Test bit in a pointer's value
* @nr: the bit to test
* @addr: the address of the pointer variable
*
* Example:
* void *p = foo();
* if (__ptr_test_bit(bit, &p)) {
* ...
* } else {
* ...
* }
*/
#define __ptr_test_bit(nr, addr) \
({ \
typecheck_pointer(*(addr)); \
test_bit(nr, (unsigned long *)(addr)); \
})
#ifdef __KERNEL__
#ifndef set_mask_bits
#define set_mask_bits(ptr, mask, bits) \
({ \
const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \
typeof(*(ptr)) old__, new__; \
\
old__ = READ_ONCE(*(ptr)); \
do { \
new__ = (old__ & ~mask__) | bits__; \
} while (!try_cmpxchg(ptr, &old__, new__)); \
\
old__; \
})
#endif
#ifndef bit_clear_unless
#define bit_clear_unless(ptr, clear, test) \
({ \
const typeof(*(ptr)) clear__ = (clear), test__ = (test);\
typeof(*(ptr)) old__, new__; \
\
old__ = READ_ONCE(*(ptr)); \
do { \
if (old__ & test__) \
break; \
new__ = old__ & ~clear__; \
} while (!try_cmpxchg(ptr, &old__, new__)); \
\
!(old__ & test__); \
})
#endif
#endif /* __KERNEL__ */
#endif
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Prevent the compiler from merging or refetching reads or writes. The
* compiler is also forbidden from reordering successive instances of
* READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
* particular ordering. One way to make the compiler aware of ordering is to
* put the two invocations of READ_ONCE or WRITE_ONCE in different C
* statements.
*
* These two macros will also work on aggregate data types like structs or
* unions.
*
* Their two major use cases are: (1) Mediating communication between
* process-level code and irq/NMI handlers, all running on the same CPU,
* and (2) Ensuring that the compiler does not fold, spindle, or otherwise
* mutilate accesses that either do not require ordering or that interact
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*/
#ifndef __ASM_GENERIC_RWONCE_H
#define __ASM_GENERIC_RWONCE_H
#ifndef __ASSEMBLY__
#include <linux/compiler_types.h>
#include <linux/kasan-checks.h>
#include <linux/kcsan-checks.h>
/*
* Yes, this permits 64-bit accesses on 32-bit architectures. These will
* actually be atomic in some cases (namely Armv7 + LPAE), but for others we
* rely on the access being split into 2x32-bit accesses for a 32-bit quantity
* (e.g. a virtual address) and a strong prevailing wind.
*/
#define compiletime_assert_rwonce_type(t) \
compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \
"Unsupported access size for {READ,WRITE}_ONCE().")
/*
* Use __READ_ONCE() instead of READ_ONCE() if you do not require any
* atomicity. Note that this may result in tears!
*/
#ifndef __READ_ONCE
#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x))
#endif
#define READ_ONCE(x) \
({ \
compiletime_assert_rwonce_type(x); \
__READ_ONCE(x); \
})
#define __WRITE_ONCE(x, val) \
do { \
*(volatile typeof(x) *)&(x) = (val); \
} while (0)
#define WRITE_ONCE(x, val) \
do { \
compiletime_assert_rwonce_type(x); \
__WRITE_ONCE(x, val); \
} while (0)
static __no_sanitize_or_inline
unsigned long __read_once_word_nocheck(const void *addr)
{
return __READ_ONCE(*(unsigned long *)addr);
}
/*
* Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
* word from memory atomically but without telling KASAN/KCSAN. This is
* usually used by unwinding code when walking the stack of a running process.
*/
#define READ_ONCE_NOCHECK(x) \
({ \
compiletime_assert(sizeof(x) == sizeof(unsigned long), \
"Unsupported access size for READ_ONCE_NOCHECK()."); \
(typeof(x))__read_once_word_nocheck(&(x)); \
})
static __no_sanitize_or_inline
unsigned long read_word_at_a_time(const void *addr)
{
/* open-coded instrument_read(addr, 1) */
kasan_check_read(addr, 1);
kcsan_check_read(addr, 1);
/*
* This load can race with concurrent stores to out-of-bounds memory,
* but READ_ONCE() can't be used because it requires higher alignment
* than plain loads in arm64 builds with LTO.
*/
return *(unsigned long *)addr;
}
#endif /* __ASSEMBLY__ */
#endif /* __ASM_GENERIC_RWONCE_H */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
*/
/*
* fsnotify inode mark locking/lifetime/and refcnting
*
* REFCNT:
* The group->recnt and mark->refcnt tell how many "things" in the kernel
* currently are referencing the objects. Both kind of objects typically will
* live inside the kernel with a refcnt of 2, one for its creation and one for
* the reference a group and a mark hold to each other.
* If you are holding the appropriate locks, you can take a reference and the
* object itself is guaranteed to survive until the reference is dropped.
*
* LOCKING:
* There are 3 locks involved with fsnotify inode marks and they MUST be taken
* in order as follows:
*
* group->mark_mutex
* mark->lock
* mark->connector->lock
*
* group->mark_mutex protects the marks_list anchored inside a given group and
* each mark is hooked via the g_list. It also protects the groups private
* data (i.e group limits).
* mark->lock protects the marks attributes like its masks and flags.
* Furthermore it protects the access to a reference of the group that the mark
* is assigned to as well as the access to a reference of the inode/vfsmount
* that is being watched by the mark.
*
* mark->connector->lock protects the list of marks anchored inside an
* inode / vfsmount and each mark is hooked via the i_list.
*
* A list of notification marks relating to inode / mnt is contained in
* fsnotify_mark_connector. That structure is alive as long as there are any
* marks in the list and is also protected by fsnotify_mark_srcu. A mark gets
* detached from fsnotify_mark_connector when last reference to the mark is
* dropped. Thus having mark reference is enough to protect mark->connector
* pointer and to make sure fsnotify_mark_connector cannot disappear. Also
* because we remove mark from g_list before dropping mark reference associated
* with that, any mark found through g_list is guaranteed to have
* mark->connector set until we drop group->mark_mutex.
*
* LIFETIME:
* Inode marks survive between when they are added to an inode and when their
* refcnt==0. Marks are also protected by fsnotify_mark_srcu.
*
* The inode mark can be cleared for a number of different reasons including:
* - The inode is unlinked for the last time. (fsnotify_inode_remove)
* - The inode is being evicted from cache. (fsnotify_inode_delete)
* - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes)
* - Something explicitly requests that it be removed. (fsnotify_destroy_mark)
* - The fsnotify_group associated with the mark is going away and all such marks
* need to be cleaned up. (fsnotify_clear_marks_by_group)
*
* This has the very interesting property of being able to run concurrently with
* any (or all) other directions.
*/
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/srcu.h>
#include <linux/ratelimit.h>
#include <linux/atomic.h>
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */
struct srcu_struct fsnotify_mark_srcu;
struct kmem_cache *fsnotify_mark_connector_cachep;
static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
static struct fsnotify_mark_connector *connector_destroy_list;
static void fsnotify_mark_destroy_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
static void fsnotify_connector_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);
void fsnotify_get_mark(struct fsnotify_mark *mark)
{
WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt);
}
static fsnotify_connp_t *fsnotify_object_connp(void *obj,
enum fsnotify_obj_type obj_type)
{
switch (obj_type) {
case FSNOTIFY_OBJ_TYPE_INODE:
return &((struct inode *)obj)->i_fsnotify_marks;
case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
return &real_mount(obj)->mnt_fsnotify_marks;
case FSNOTIFY_OBJ_TYPE_SB:
return fsnotify_sb_marks(obj);
case FSNOTIFY_OBJ_TYPE_MNTNS:
return &((struct mnt_namespace *)obj)->n_fsnotify_marks;
default:
return NULL;
}
}
static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn)
{
if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
return &fsnotify_conn_inode(conn)->i_fsnotify_mask;
else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT)
return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask;
else if (conn->type == FSNOTIFY_OBJ_TYPE_SB)
return &fsnotify_conn_sb(conn)->s_fsnotify_mask;
else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS)
return &fsnotify_conn_mntns(conn)->n_fsnotify_mask;
return NULL;
}
__u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn)
{
if (WARN_ON(!fsnotify_valid_obj_type(conn->type)))
return 0;
return READ_ONCE(*fsnotify_conn_mask_p(conn));
}
static void fsnotify_get_sb_watched_objects(struct super_block *sb)
{
atomic_long_inc(fsnotify_sb_watched_objects(sb));
}
static void fsnotify_put_sb_watched_objects(struct super_block *sb)
{
atomic_long_t *watched_objects = fsnotify_sb_watched_objects(sb);
/* the superblock can go away after this decrement */
if (atomic_long_dec_and_test(watched_objects)) wake_up_var(watched_objects);
}
static void fsnotify_get_inode_ref(struct inode *inode)
{
ihold(inode);
fsnotify_get_sb_watched_objects(inode->i_sb);
}
static void fsnotify_put_inode_ref(struct inode *inode)
{
/* read ->i_sb before the inode can go away */
struct super_block *sb = inode->i_sb;
iput(inode);
fsnotify_put_sb_watched_objects(sb);
}
/*
* Grab or drop watched objects reference depending on whether the connector
* is attached and has any marks attached.
*/
static void fsnotify_update_sb_watchers(struct super_block *sb,
struct fsnotify_mark_connector *conn)
{
struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
bool is_watched = conn->flags & FSNOTIFY_CONN_FLAG_IS_WATCHED;
struct fsnotify_mark *first_mark = NULL;
unsigned int highest_prio = 0;
if (conn->obj)
first_mark = hlist_entry_safe(conn->list.first,
struct fsnotify_mark, obj_list);
if (first_mark)
highest_prio = first_mark->group->priority;
if (WARN_ON(highest_prio >= __FSNOTIFY_PRIO_NUM))
highest_prio = 0;
/*
* If the highest priority of group watching this object is prio,
* then watched object has a reference on counters [0..prio].
* Update priority >= 1 watched objects counters.
*/
for (unsigned int p = conn->prio + 1; p <= highest_prio; p++)
atomic_long_inc(&sbinfo->watched_objects[p]);
for (unsigned int p = conn->prio; p > highest_prio; p--)
atomic_long_dec(&sbinfo->watched_objects[p]);
conn->prio = highest_prio;
/* Update priority >= 0 (a.k.a total) watched objects counter */
BUILD_BUG_ON(FSNOTIFY_PRIO_NORMAL != 0);
if (first_mark && !is_watched) {
conn->flags |= FSNOTIFY_CONN_FLAG_IS_WATCHED;
fsnotify_get_sb_watched_objects(sb);
} else if (!first_mark && is_watched) {
conn->flags &= ~FSNOTIFY_CONN_FLAG_IS_WATCHED;
fsnotify_put_sb_watched_objects(sb);
}
}
/*
* Grab or drop inode reference for the connector if needed.
*
* When it's time to drop the reference, we only clear the HAS_IREF flag and
* return the inode object. fsnotify_drop_object() will be resonsible for doing
* iput() outside of spinlocks. This happens when last mark that wanted iref is
* detached.
*/
static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn,
bool want_iref)
{
bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF;
struct inode *inode = NULL;
if (conn->type != FSNOTIFY_OBJ_TYPE_INODE ||
want_iref == has_iref)
return NULL;
if (want_iref) {
/* Pin inode if any mark wants inode refcount held */
fsnotify_get_inode_ref(fsnotify_conn_inode(conn));
conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF;
} else {
/* Unpin inode after detach of last mark that wanted iref */
inode = fsnotify_conn_inode(conn);
conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF;
}
return inode;
}
static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
u32 new_mask = 0;
bool want_iref = false;
struct fsnotify_mark *mark;
assert_spin_locked(&conn->lock);
/* We can get detached connector here when inode is getting unlinked. */
if (!fsnotify_valid_obj_type(conn->type))
return NULL;
hlist_for_each_entry(mark, &conn->list, obj_list) {
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED))
continue;
new_mask |= fsnotify_calc_mask(mark);
if (conn->type == FSNOTIFY_OBJ_TYPE_INODE &&
!(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
want_iref = true;
}
/*
* We use WRITE_ONCE() to prevent silly compiler optimizations from
* confusing readers not holding conn->lock with partial updates.
*/
WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask);
return fsnotify_update_iref(conn, want_iref);
}
static bool fsnotify_conn_watches_children(
struct fsnotify_mark_connector *conn)
{
if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
return false;
return fsnotify_inode_watches_children(fsnotify_conn_inode(conn));
}
static void fsnotify_conn_set_children_dentry_flags(
struct fsnotify_mark_connector *conn)
{
if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
return;
fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn));
}
/*
* Calculate mask of events for a list of marks. The caller must make sure
* connector and connector->obj cannot disappear under us. Callers achieve
* this by holding a mark->lock or mark->group->mark_mutex for a mark on this
* list.
*/
void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
bool update_children;
if (!conn)
return;
spin_lock(&conn->lock);
update_children = !fsnotify_conn_watches_children(conn);
__fsnotify_recalc_mask(conn);
update_children &= fsnotify_conn_watches_children(conn);
spin_unlock(&conn->lock);
/*
* Set children's PARENT_WATCHED flags only if parent started watching.
* When parent stops watching, we clear false positive PARENT_WATCHED
* flags lazily in __fsnotify_parent().
*/
if (update_children)
fsnotify_conn_set_children_dentry_flags(conn);
}
/* Free all connectors queued for freeing once SRCU period ends */
static void fsnotify_connector_destroy_workfn(struct work_struct *work)
{
struct fsnotify_mark_connector *conn, *free;
spin_lock(&destroy_lock);
conn = connector_destroy_list;
connector_destroy_list = NULL;
spin_unlock(&destroy_lock);
synchronize_srcu(&fsnotify_mark_srcu);
while (conn) {
free = conn;
conn = conn->destroy_next;
kmem_cache_free(fsnotify_mark_connector_cachep, free);
}
}
static void *fsnotify_detach_connector_from_object(
struct fsnotify_mark_connector *conn,
unsigned int *type)
{
fsnotify_connp_t *connp = fsnotify_object_connp(conn->obj, conn->type);
struct super_block *sb = fsnotify_connector_sb(conn);
struct inode *inode = NULL;
*type = conn->type;
if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED)
return NULL;
if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
inode = fsnotify_conn_inode(conn);
inode->i_fsnotify_mask = 0;
/* Unpin inode when detaching from connector */
if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF))
inode = NULL;
} else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
} else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
fsnotify_conn_sb(conn)->s_fsnotify_mask = 0;
} else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
fsnotify_conn_mntns(conn)->n_fsnotify_mask = 0;
}
rcu_assign_pointer(*connp, NULL);
conn->obj = NULL;
conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
if (sb)
fsnotify_update_sb_watchers(sb, conn);
return inode;
}
static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
{
struct fsnotify_group *group = mark->group;
if (WARN_ON_ONCE(!group))
return;
group->ops->free_mark(mark);
fsnotify_put_group(group);
}
/* Drop object reference originally held by a connector */
static void fsnotify_drop_object(unsigned int type, void *objp)
{
if (!objp)
return;
/* Currently only inode references are passed to be dropped */
if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE))
return;
fsnotify_put_inode_ref(objp);
}
void fsnotify_put_mark(struct fsnotify_mark *mark)
{
struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
void *objp = NULL;
unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
bool free_conn = false;
/* Catch marks that were actually never attached to object */
if (!conn) {
if (refcount_dec_and_test(&mark->refcnt))
fsnotify_final_mark_destroy(mark);
return;
}
/*
* We have to be careful so that traversals of obj_list under lock can
* safely grab mark reference.
*/
if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock))
return;
hlist_del_init_rcu(&mark->obj_list);
if (hlist_empty(&conn->list)) {
objp = fsnotify_detach_connector_from_object(conn, &type);
free_conn = true;
} else {
struct super_block *sb = fsnotify_connector_sb(conn);
/* Update watched objects after detaching mark */
if (sb)
fsnotify_update_sb_watchers(sb, conn);
objp = __fsnotify_recalc_mask(conn);
type = conn->type;
}
WRITE_ONCE(mark->connector, NULL);
spin_unlock(&conn->lock);
fsnotify_drop_object(type, objp);
if (free_conn) {
spin_lock(&destroy_lock);
conn->destroy_next = connector_destroy_list;
connector_destroy_list = conn;
spin_unlock(&destroy_lock);
queue_work(system_unbound_wq, &connector_reaper_work);
}
/*
* Note that we didn't update flags telling whether inode cares about
* what's happening with children. We update these flags from
* __fsnotify_parent() lazily when next event happens on one of our
* children.
*/
spin_lock(&destroy_lock);
list_add(&mark->g_list, &destroy_list);
spin_unlock(&destroy_lock);
queue_delayed_work(system_unbound_wq, &reaper_work,
FSNOTIFY_REAPER_DELAY);
}
EXPORT_SYMBOL_GPL(fsnotify_put_mark);
/*
* Get mark reference when we found the mark via lockless traversal of object
* list. Mark can be already removed from the list by now and on its way to be
* destroyed once SRCU period ends.
*
* Also pin the group so it doesn't disappear under us.
*/
static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark)
{
if (!mark)
return true;
if (refcount_inc_not_zero(&mark->refcnt)) {
spin_lock(&mark->lock);
if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) {
/* mark is attached, group is still alive then */
atomic_inc(&mark->group->user_waits);
spin_unlock(&mark->lock);
return true;
}
spin_unlock(&mark->lock);
fsnotify_put_mark(mark);
}
return false;
}
/*
* Puts marks and wakes up group destruction if necessary.
*
* Pairs with fsnotify_get_mark_safe()
*/
static void fsnotify_put_mark_wake(struct fsnotify_mark *mark)
{
if (mark) {
struct fsnotify_group *group = mark->group;
fsnotify_put_mark(mark);
/*
* We abuse notification_waitq on group shutdown for waiting for
* all marks pinned when waiting for userspace.
*/
if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
wake_up(&group->notification_waitq);
}
}
bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info)
__releases(&fsnotify_mark_srcu)
{
int type;
fsnotify_foreach_iter_type(type) {
/* This can fail if mark is being removed */
if (!fsnotify_get_mark_safe(iter_info->marks[type])) {
__release(&fsnotify_mark_srcu);
goto fail;
}
}
/*
* Now that both marks are pinned by refcount in the inode / vfsmount
* lists, we can drop SRCU lock, and safely resume the list iteration
* once userspace returns.
*/
srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx);
return true;
fail:
for (type--; type >= 0; type--)
fsnotify_put_mark_wake(iter_info->marks[type]);
return false;
}
void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
__acquires(&fsnotify_mark_srcu)
{
int type;
iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
fsnotify_foreach_iter_type(type)
fsnotify_put_mark_wake(iter_info->marks[type]);
}
/*
* Mark mark as detached, remove it from group list. Mark still stays in object
* list until its last reference is dropped. Note that we rely on mark being
* removed from group list before corresponding reference to it is dropped. In
* particular we rely on mark->connector being valid while we hold
* group->mark_mutex if we found the mark through g_list.
*
* Must be called with group->mark_mutex held. The caller must either hold
* reference to the mark or be protected by fsnotify_mark_srcu.
*/
void fsnotify_detach_mark(struct fsnotify_mark *mark)
{
fsnotify_group_assert_locked(mark->group);
WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
refcount_read(&mark->refcnt) < 1 +
!!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
spin_lock(&mark->lock);
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
spin_unlock(&mark->lock);
return;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
list_del_init(&mark->g_list);
spin_unlock(&mark->lock);
/* Drop mark reference acquired in fsnotify_add_mark_locked() */
fsnotify_put_mark(mark);
}
/*
* Free fsnotify mark. The mark is actually only marked as being freed. The
* freeing is actually happening only once last reference to the mark is
* dropped from a workqueue which first waits for srcu period end.
*
* Caller must have a reference to the mark or be protected by
* fsnotify_mark_srcu.
*/
void fsnotify_free_mark(struct fsnotify_mark *mark)
{
struct fsnotify_group *group = mark->group;
spin_lock(&mark->lock);
/* something else already called this function on this mark */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
spin_unlock(&mark->lock);
return;
}
mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
spin_unlock(&mark->lock);
/*
* Some groups like to know that marks are being freed. This is a
* callback to the group function to let it know that this mark
* is being freed.
*/
if (group->ops->freeing_mark)
group->ops->freeing_mark(mark, group);
}
void fsnotify_destroy_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group)
{
fsnotify_group_lock(group);
fsnotify_detach_mark(mark);
fsnotify_group_unlock(group);
fsnotify_free_mark(mark);
}
EXPORT_SYMBOL_GPL(fsnotify_destroy_mark);
/*
* Sorting function for lists of fsnotify marks.
*
* Fanotify supports different notification classes (reflected as priority of
* notification group). Events shall be passed to notification groups in
* decreasing priority order. To achieve this marks in notification lists for
* inodes and vfsmounts are sorted so that priorities of corresponding groups
* are descending.
*
* Furthermore correct handling of the ignore mask requires processing inode
* and vfsmount marks of each group together. Using the group address as
* further sort criterion provides a unique sorting order and thus we can
* merge inode and vfsmount lists of marks in linear time and find groups
* present in both lists.
*
* A return value of 1 signifies that b has priority over a.
* A return value of 0 signifies that the two marks have to be handled together.
* A return value of -1 signifies that a has priority over b.
*/
int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
{
if (a == b)
return 0;
if (!a)
return 1;
if (!b)
return -1;
if (a->priority < b->priority)
return 1;
if (a->priority > b->priority)
return -1;
if (a < b)
return 1;
return -1;
}
static int fsnotify_attach_info_to_sb(struct super_block *sb)
{
struct fsnotify_sb_info *sbinfo;
/* sb info is freed on fsnotify_sb_delete() */
sbinfo = kzalloc(sizeof(*sbinfo), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
/*
* cmpxchg() provides the barrier so that callers of fsnotify_sb_info()
* will observe an initialized structure
*/
if (cmpxchg(&sb->s_fsnotify_info, NULL, sbinfo)) {
/* Someone else created sbinfo for us */
kfree(sbinfo);
}
return 0;
}
static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
void *obj, unsigned int obj_type)
{
struct fsnotify_mark_connector *conn;
conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL);
if (!conn)
return -ENOMEM;
spin_lock_init(&conn->lock);
INIT_HLIST_HEAD(&conn->list);
conn->flags = 0;
conn->prio = 0;
conn->type = obj_type;
conn->obj = obj;
/*
* cmpxchg() provides the barrier so that readers of *connp can see
* only initialized structure
*/
if (cmpxchg(connp, NULL, conn)) {
/* Someone else created list structure for us */
kmem_cache_free(fsnotify_mark_connector_cachep, conn);
}
return 0;
}
/*
* Get mark connector, make sure it is alive and return with its lock held.
* This is for users that get connector pointer from inode or mount. Users that
* hold reference to a mark on the list may directly lock connector->lock as
* they are sure list cannot go away under them.
*/
static struct fsnotify_mark_connector *fsnotify_grab_connector(
fsnotify_connp_t *connp)
{
struct fsnotify_mark_connector *conn;
int idx;
idx = srcu_read_lock(&fsnotify_mark_srcu);
conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn)
goto out;
spin_lock(&conn->lock);
if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) {
spin_unlock(&conn->lock);
srcu_read_unlock(&fsnotify_mark_srcu, idx);
return NULL;
}
out:
srcu_read_unlock(&fsnotify_mark_srcu, idx);
return conn;
}
/*
* Add mark into proper place in given list of marks. These marks may be used
* for the fsnotify backend to determine which event types should be delivered
* to which group and for which inodes. These marks are ordered according to
* priority, highest number first, and then by the group's location in memory.
*/
static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags)
{
struct super_block *sb = fsnotify_object_sb(obj, obj_type);
struct fsnotify_mark *lmark, *last = NULL;
struct fsnotify_mark_connector *conn;
fsnotify_connp_t *connp;
int cmp;
int err = 0;
if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
return -EINVAL;
/*
* Attach the sb info before attaching a connector to any object on sb.
* The sb info will remain attached as long as sb lives.
*/
if (sb && !fsnotify_sb_info(sb)) {
err = fsnotify_attach_info_to_sb(sb);
if (err)
return err;
}
connp = fsnotify_object_connp(obj, obj_type);
restart:
spin_lock(&mark->lock);
conn = fsnotify_grab_connector(connp);
if (!conn) {
spin_unlock(&mark->lock);
err = fsnotify_attach_connector_to_object(connp, obj, obj_type);
if (err)
return err;
goto restart;
}
/* is mark the first mark? */
if (hlist_empty(&conn->list)) {
hlist_add_head_rcu(&mark->obj_list, &conn->list);
goto added;
}
/* should mark be in the middle of the current list? */
hlist_for_each_entry(lmark, &conn->list, obj_list) {
last = lmark;
if ((lmark->group == mark->group) &&
(lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
!(mark->group->flags & FSNOTIFY_GROUP_DUPS)) {
err = -EEXIST;
goto out_err;
}
cmp = fsnotify_compare_groups(lmark->group, mark->group);
if (cmp >= 0) {
hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
goto added;
}
}
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
added:
if (sb)
fsnotify_update_sb_watchers(sb, conn);
/*
* Since connector is attached to object using cmpxchg() we are
* guaranteed that connector initialization is fully visible by anyone
* seeing mark->connector set.
*/
WRITE_ONCE(mark->connector, conn);
out_err:
spin_unlock(&conn->lock);
spin_unlock(&mark->lock);
return err;
}
/*
* Attach an initialized mark to a given group and fs object.
* These marks may be used for the fsnotify backend to determine which
* event types should be delivered to which group.
*/
int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
void *obj, unsigned int obj_type,
int add_flags)
{
struct fsnotify_group *group = mark->group;
int ret = 0;
fsnotify_group_assert_locked(group);
/*
* LOCKING ORDER!!!!
* group->mark_mutex
* mark->lock
* mark->connector->lock
*/
spin_lock(&mark->lock);
mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
list_add(&mark->g_list, &group->marks_list);
fsnotify_get_mark(mark); /* for g_list */
spin_unlock(&mark->lock);
ret = fsnotify_add_mark_list(mark, obj, obj_type, add_flags);
if (ret)
goto err;
fsnotify_recalc_mask(mark->connector);
return ret;
err:
spin_lock(&mark->lock);
mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE |
FSNOTIFY_MARK_FLAG_ATTACHED);
list_del_init(&mark->g_list);
spin_unlock(&mark->lock);
fsnotify_put_mark(mark);
return ret;
}
int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags)
{
int ret;
struct fsnotify_group *group = mark->group;
fsnotify_group_lock(group);
ret = fsnotify_add_mark_locked(mark, obj, obj_type, add_flags);
fsnotify_group_unlock(group);
return ret;
}
EXPORT_SYMBOL_GPL(fsnotify_add_mark);
/*
* Given a list of marks, find the mark associated with given group. If found
* take a reference to that mark and return it, else return NULL.
*/
struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type,
struct fsnotify_group *group)
{ fsnotify_connp_t *connp = fsnotify_object_connp(obj, obj_type);
struct fsnotify_mark_connector *conn;
struct fsnotify_mark *mark;
if (!connp)
return NULL;
conn = fsnotify_grab_connector(connp);
if (!conn)
return NULL;
hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group &&
(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
fsnotify_get_mark(mark);
spin_unlock(&conn->lock);
return mark;
}
}
spin_unlock(&conn->lock);
return NULL;
}
EXPORT_SYMBOL_GPL(fsnotify_find_mark);
/* Clear any marks in a group with given type mask */
void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
unsigned int obj_type)
{
struct fsnotify_mark *lmark, *mark;
LIST_HEAD(to_free);
struct list_head *head = &to_free;
/* Skip selection step if we want to clear all marks. */
if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) {
head = &group->marks_list;
goto clear;
}
/*
* We have to be really careful here. Anytime we drop mark_mutex, e.g.
* fsnotify_clear_marks_by_inode() can come and free marks. Even in our
* to_free list so we have to use mark_mutex even when accessing that
* list. And freeing mark requires us to drop mark_mutex. So we can
* reliably free only the first mark in the list. That's why we first
* move marks to free to to_free list in one go and then free marks in
* to_free list one by one.
*/
fsnotify_group_lock(group);
list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
if (mark->connector->type == obj_type)
list_move(&mark->g_list, &to_free);
}
fsnotify_group_unlock(group);
clear:
while (1) {
fsnotify_group_lock(group);
if (list_empty(head)) {
fsnotify_group_unlock(group);
break;
}
mark = list_first_entry(head, struct fsnotify_mark, g_list);
fsnotify_get_mark(mark);
fsnotify_detach_mark(mark);
fsnotify_group_unlock(group);
fsnotify_free_mark(mark);
fsnotify_put_mark(mark);
}
}
/* Destroy all marks attached to an object via connector */
void fsnotify_destroy_marks(fsnotify_connp_t *connp)
{
struct fsnotify_mark_connector *conn;
struct fsnotify_mark *mark, *old_mark = NULL;
void *objp;
unsigned int type;
conn = fsnotify_grab_connector(connp);
if (!conn)
return;
/*
* We have to be careful since we can race with e.g.
* fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
* list can get modified. However we are holding mark reference and
* thus our mark cannot be removed from obj_list so we can continue
* iteration after regaining conn->lock.
*/
hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark);
spin_unlock(&conn->lock);
if (old_mark) fsnotify_put_mark(old_mark);
old_mark = mark;
fsnotify_destroy_mark(mark, mark->group);
spin_lock(&conn->lock);
}
/*
* Detach list from object now so that we don't pin inode until all
* mark references get dropped. It would lead to strange results such
* as delaying inode deletion or blocking unmount.
*/
objp = fsnotify_detach_connector_from_object(conn, &type);
spin_unlock(&conn->lock);
if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp);
}
/*
* Nothing fancy, just initialize lists and locks and counters.
*/
void fsnotify_init_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group)
{
memset(mark, 0, sizeof(*mark));
spin_lock_init(&mark->lock);
refcount_set(&mark->refcnt, 1);
fsnotify_get_group(group);
mark->group = group;
WRITE_ONCE(mark->connector, NULL);
}
EXPORT_SYMBOL_GPL(fsnotify_init_mark);
/*
* Destroy all marks in destroy_list, waits for SRCU period to finish before
* actually freeing marks.
*/
static void fsnotify_mark_destroy_workfn(struct work_struct *work)
{
struct fsnotify_mark *mark, *next;
struct list_head private_destroy_list;
spin_lock(&destroy_lock);
/* exchange the list head */
list_replace_init(&destroy_list, &private_destroy_list);
spin_unlock(&destroy_lock);
synchronize_srcu(&fsnotify_mark_srcu);
list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
list_del_init(&mark->g_list);
fsnotify_final_mark_destroy(mark);
}
}
/* Wait for all marks queued for destruction to be actually destroyed */
void fsnotify_wait_marks_destroyed(void)
{
flush_delayed_work(&reaper_work);
}
EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org>
*
* Fixes from William Schumacher incorporated on 15 March 2001.
* (Reported by Charles Bertsch, <CBertsch@microtest.com>).
*/
/*
* This file contains generic functions for manipulating
* POSIX 1003.1e draft standard 17 ACLs.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/atomic.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
#include <linux/namei.h>
#include <linux/mnt_idmapping.h>
#include <linux/iversion.h>
#include <linux/security.h>
#include <linux/fsnotify.h>
#include <linux/filelock.h>
#include "internal.h"
static struct posix_acl **acl_by_type(struct inode *inode, int type)
{
switch (type) {
case ACL_TYPE_ACCESS:
return &inode->i_acl;
case ACL_TYPE_DEFAULT:
return &inode->i_default_acl;
default:
BUG();
}
}
struct posix_acl *get_cached_acl(struct inode *inode, int type)
{ struct posix_acl **p = acl_by_type(inode, type);
struct posix_acl *acl;
for (;;) {
rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount))
break;
rcu_read_unlock();
cpu_relax();
}
rcu_read_unlock();
return acl;
}
EXPORT_SYMBOL(get_cached_acl);
struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
{
struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));
if (acl == ACL_DONT_CACHE) {
struct posix_acl *ret;
ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU);
if (!IS_ERR(ret))
acl = ret;
}
return acl;
}
EXPORT_SYMBOL(get_cached_acl_rcu);
void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl)
{ struct posix_acl **p = acl_by_type(inode, type);
struct posix_acl *old;
old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old);
}
EXPORT_SYMBOL(set_cached_acl);
static void __forget_cached_acl(struct posix_acl **p)
{
struct posix_acl *old;
old = xchg(p, ACL_NOT_CACHED);
if (!is_uncached_acl(old))
posix_acl_release(old);
}
void forget_cached_acl(struct inode *inode, int type)
{
__forget_cached_acl(acl_by_type(inode, type));
}
EXPORT_SYMBOL(forget_cached_acl);
void forget_all_cached_acls(struct inode *inode)
{
__forget_cached_acl(&inode->i_acl);
__forget_cached_acl(&inode->i_default_acl);
}
EXPORT_SYMBOL(forget_all_cached_acls);
static struct posix_acl *__get_acl(struct mnt_idmap *idmap,
struct dentry *dentry, struct inode *inode,
int type)
{
struct posix_acl *sentinel;
struct posix_acl **p;
struct posix_acl *acl;
/*
* The sentinel is used to detect when another operation like
* set_cached_acl() or forget_cached_acl() races with get_inode_acl().
* It is guaranteed that is_uncached_acl(sentinel) is true.
*/
acl = get_cached_acl(inode, type);
if (!is_uncached_acl(acl))
return acl;
if (!IS_POSIXACL(inode))
return NULL;
sentinel = uncached_acl_sentinel(current);
p = acl_by_type(inode, type);
/*
* If the ACL isn't being read yet, set our sentinel. Otherwise, the
* current value of the ACL will not be ACL_NOT_CACHED and so our own
* sentinel will not be set; another task will update the cache. We
* could wait for that other task to complete its job, but it's easier
* to just call ->get_inode_acl to fetch the ACL ourself. (This is
* going to be an unlikely race.)
*/
cmpxchg(p, ACL_NOT_CACHED, sentinel);
/*
* Normally, the ACL returned by ->get{_inode}_acl will be cached.
* A filesystem can prevent that by calling
* forget_cached_acl(inode, type) in ->get{_inode}_acl.
*
* If the filesystem doesn't have a get{_inode}_ acl() function at all,
* we'll just create the negative cache entry.
*/
if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type);
} else if (inode->i_op->get_inode_acl) {
acl = inode->i_op->get_inode_acl(inode, type, false);
} else {
set_cached_acl(inode, type, NULL);
return NULL;
}
if (IS_ERR(acl)) {
/*
* Remove our sentinel so that we don't block future attempts
* to cache the ACL.
*/
cmpxchg(p, sentinel, ACL_NOT_CACHED);
return acl;
}
/*
* Cache the result, but only if our sentinel is still in place.
*/
posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl)))
posix_acl_release(acl);
return acl;
}
struct posix_acl *get_inode_acl(struct inode *inode, int type)
{
return __get_acl(&nop_mnt_idmap, NULL, inode, type);
}
EXPORT_SYMBOL(get_inode_acl);
/*
* Init a fresh posix_acl
*/
void
posix_acl_init(struct posix_acl *acl, int count)
{
refcount_set(&acl->a_refcount, 1);
acl->a_count = count;
}
EXPORT_SYMBOL(posix_acl_init);
/*
* Allocate a new ACL with the specified number of entries.
*/
struct posix_acl *
posix_acl_alloc(unsigned int count, gfp_t flags)
{
struct posix_acl *acl;
acl = kmalloc(struct_size(acl, a_entries, count), flags);
if (acl)
posix_acl_init(acl, count);
return acl;
}
EXPORT_SYMBOL(posix_acl_alloc);
/*
* Clone an ACL.
*/
struct posix_acl *
posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
{
struct posix_acl *clone = NULL;
if (acl) {
clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count),
flags);
if (clone)
refcount_set(&clone->a_refcount, 1);
}
return clone;
}
EXPORT_SYMBOL_GPL(posix_acl_clone);
/*
* Check if an acl is valid. Returns 0 if it is, or -E... otherwise.
*/
int
posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl)
{
const struct posix_acl_entry *pa, *pe;
int state = ACL_USER_OBJ;
int needs_mask = 0;
FOREACH_ACL_ENTRY(pa, acl, pe) {
if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE))
return -EINVAL;
switch (pa->e_tag) {
case ACL_USER_OBJ:
if (state == ACL_USER_OBJ) {
state = ACL_USER;
break;
}
return -EINVAL;
case ACL_USER:
if (state != ACL_USER)
return -EINVAL;
if (!kuid_has_mapping(user_ns, pa->e_uid))
return -EINVAL;
needs_mask = 1;
break;
case ACL_GROUP_OBJ:
if (state == ACL_USER) {
state = ACL_GROUP;
break;
}
return -EINVAL;
case ACL_GROUP:
if (state != ACL_GROUP)
return -EINVAL;
if (!kgid_has_mapping(user_ns, pa->e_gid))
return -EINVAL;
needs_mask = 1;
break;
case ACL_MASK:
if (state != ACL_GROUP)
return -EINVAL;
state = ACL_OTHER;
break;
case ACL_OTHER:
if (state == ACL_OTHER ||
(state == ACL_GROUP && !needs_mask)) {
state = 0;
break;
}
return -EINVAL;
default:
return -EINVAL;
}
}
if (state == 0)
return 0;
return -EINVAL;
}
EXPORT_SYMBOL(posix_acl_valid);
/*
* Returns 0 if the acl can be exactly represented in the traditional
* file mode permission bits, or else 1. Returns -E... on error.
*/
int
posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p)
{
const struct posix_acl_entry *pa, *pe;
umode_t mode = 0;
int not_equiv = 0;
/*
* A null ACL can always be presented as mode bits.
*/
if (!acl)
return 0;
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch (pa->e_tag) {
case ACL_USER_OBJ:
mode |= (pa->e_perm & S_IRWXO) << 6;
break;
case ACL_GROUP_OBJ:
mode |= (pa->e_perm & S_IRWXO) << 3;
break;
case ACL_OTHER:
mode |= pa->e_perm & S_IRWXO;
break;
case ACL_MASK:
mode = (mode & ~S_IRWXG) |
((pa->e_perm & S_IRWXO) << 3);
not_equiv = 1;
break;
case ACL_USER:
case ACL_GROUP:
not_equiv = 1;
break;
default:
return -EINVAL;
}
}
if (mode_p)
*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
return not_equiv;
}
EXPORT_SYMBOL(posix_acl_equiv_mode);
/*
* Create an ACL representing the file mode permission bits of an inode.
*/
struct posix_acl *
posix_acl_from_mode(umode_t mode, gfp_t flags)
{
struct posix_acl *acl = posix_acl_alloc(3, flags);
if (!acl)
return ERR_PTR(-ENOMEM);
acl->a_entries[0].e_tag = ACL_USER_OBJ;
acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6;
acl->a_entries[1].e_tag = ACL_GROUP_OBJ;
acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3;
acl->a_entries[2].e_tag = ACL_OTHER;
acl->a_entries[2].e_perm = (mode & S_IRWXO);
return acl;
}
EXPORT_SYMBOL(posix_acl_from_mode);
/*
* Return 0 if current is granted want access to the inode
* by the acl. Returns -E... otherwise.
*/
int
posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode,
const struct posix_acl *acl, int want)
{
const struct posix_acl_entry *pa, *pe, *mask_obj;
struct user_namespace *fs_userns = i_user_ns(inode);
int found = 0;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
want &= MAY_READ | MAY_WRITE | MAY_EXEC;
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch(pa->e_tag) {
case ACL_USER_OBJ:
/* (May have been checked already) */
vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto check_perm;
break;
case ACL_USER:
vfsuid = make_vfsuid(idmap, fs_userns,
pa->e_uid);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto mask;
break;
case ACL_GROUP_OBJ:
vfsgid = i_gid_into_vfsgid(idmap, inode);
if (vfsgid_in_group_p(vfsgid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
break;
case ACL_GROUP:
vfsgid = make_vfsgid(idmap, fs_userns,
pa->e_gid);
if (vfsgid_in_group_p(vfsgid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
break;
case ACL_MASK:
break;
case ACL_OTHER:
if (found)
return -EACCES;
else
goto check_perm;
default:
return -EIO;
}
}
return -EIO;
mask:
for (mask_obj = pa+1; mask_obj != pe; mask_obj++) {
if (mask_obj->e_tag == ACL_MASK) {
if ((pa->e_perm & mask_obj->e_perm & want) == want)
return 0;
return -EACCES;
}
}
check_perm:
if ((pa->e_perm & want) == want)
return 0;
return -EACCES;
}
/*
* Modify acl when creating a new inode. The caller must ensure the acl is
* only referenced once.
*
* mode_p initially must contain the mode parameter to the open() / creat()
* system calls. All permissions that are not granted by the acl are removed.
* The permissions in the acl are changed to reflect the mode_p parameter.
*/
static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
{
struct posix_acl_entry *pa, *pe;
struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
umode_t mode = *mode_p;
int not_equiv = 0;
/* assert(atomic_read(acl->a_refcount) == 1); */
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch(pa->e_tag) {
case ACL_USER_OBJ:
pa->e_perm &= (mode >> 6) | ~S_IRWXO;
mode &= (pa->e_perm << 6) | ~S_IRWXU;
break;
case ACL_USER:
case ACL_GROUP:
not_equiv = 1;
break;
case ACL_GROUP_OBJ:
group_obj = pa;
break;
case ACL_OTHER:
pa->e_perm &= mode | ~S_IRWXO;
mode &= pa->e_perm | ~S_IRWXO;
break;
case ACL_MASK:
mask_obj = pa;
not_equiv = 1;
break;
default:
return -EIO;
}
}
if (mask_obj) {
mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
} else {
if (!group_obj)
return -EIO;
group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
}
*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
return not_equiv;
}
/*
* Modify the ACL for the chmod syscall.
*/
static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode)
{
struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
struct posix_acl_entry *pa, *pe;
/* assert(atomic_read(acl->a_refcount) == 1); */
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch(pa->e_tag) {
case ACL_USER_OBJ:
pa->e_perm = (mode & S_IRWXU) >> 6;
break;
case ACL_USER:
case ACL_GROUP:
break;
case ACL_GROUP_OBJ:
group_obj = pa;
break;
case ACL_MASK:
mask_obj = pa;
break;
case ACL_OTHER:
pa->e_perm = (mode & S_IRWXO);
break;
default:
return -EIO;
}
}
if (mask_obj) {
mask_obj->e_perm = (mode & S_IRWXG) >> 3;
} else {
if (!group_obj)
return -EIO;
group_obj->e_perm = (mode & S_IRWXG) >> 3;
}
return 0;
}
int
__posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p)
{
struct posix_acl *clone = posix_acl_clone(*acl, gfp);
int err = -ENOMEM;
if (clone) {
err = posix_acl_create_masq(clone, mode_p);
if (err < 0) {
posix_acl_release(clone);
clone = NULL;
}
}
posix_acl_release(*acl);
*acl = clone;
return err;
}
EXPORT_SYMBOL(__posix_acl_create);
int
__posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode)
{
struct posix_acl *clone = posix_acl_clone(*acl, gfp);
int err = -ENOMEM;
if (clone) {
err = __posix_acl_chmod_masq(clone, mode);
if (err) {
posix_acl_release(clone);
clone = NULL;
}
}
posix_acl_release(*acl);
*acl = clone;
return err;
}
EXPORT_SYMBOL(__posix_acl_chmod);
/**
* posix_acl_chmod - chmod a posix acl
*
* @idmap: idmap of the mount @inode was found from
* @dentry: dentry to check permissions on
* @mode: the new mode of @inode
*
* If the dentry has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*/
int
posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry,
umode_t mode)
{
struct inode *inode = d_inode(dentry);
struct posix_acl *acl;
int ret = 0;
if (!IS_POSIXACL(inode))
return 0;
if (!inode->i_op->set_acl)
return -EOPNOTSUPP;
acl = get_inode_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR_OR_NULL(acl)) {
if (acl == ERR_PTR(-EOPNOTSUPP))
return 0;
return PTR_ERR(acl);
}
ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
if (ret)
return ret;
ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
return ret;
}
EXPORT_SYMBOL(posix_acl_chmod);
int
posix_acl_create(struct inode *dir, umode_t *mode,
struct posix_acl **default_acl, struct posix_acl **acl)
{
struct posix_acl *p;
struct posix_acl *clone;
int ret;
*acl = NULL;
*default_acl = NULL;
if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
return 0;
p = get_inode_acl(dir, ACL_TYPE_DEFAULT);
if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
*mode &= ~current_umask();
return 0;
}
if (IS_ERR(p))
return PTR_ERR(p);
ret = -ENOMEM;
clone = posix_acl_clone(p, GFP_NOFS);
if (!clone)
goto err_release;
ret = posix_acl_create_masq(clone, mode);
if (ret < 0)
goto err_release_clone;
if (ret == 0)
posix_acl_release(clone);
else
*acl = clone;
if (!S_ISDIR(*mode))
posix_acl_release(p);
else
*default_acl = p;
return 0;
err_release_clone:
posix_acl_release(clone);
err_release:
posix_acl_release(p);
return ret;
}
EXPORT_SYMBOL_GPL(posix_acl_create);
/**
* posix_acl_update_mode - update mode in set_acl
* @idmap: idmap of the mount @inode was found from
* @inode: target inode
* @mode_p: mode (pointer) for update
* @acl: acl pointer
*
* Update the file mode when setting an ACL: compute the new file permission
* bits based on the ACL. In addition, if the ACL is equivalent to the new
* file mode, set *@acl to NULL to indicate that no ACL should be set.
*
* As with chmod, clear the setgid bit if the caller is not in the owning group
* or capable of CAP_FSETID (see inode_change_ok).
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then
* take care to map the inode according to @idmap before checking
* permissions. On non-idmapped mounts or if permission checking is to be
* performed on the raw inode simply pass @nop_mnt_idmap.
*
* Called from set_acl inode operations.
*/
int posix_acl_update_mode(struct mnt_idmap *idmap,
struct inode *inode, umode_t *mode_p,
struct posix_acl **acl)
{
umode_t mode = inode->i_mode;
int error;
error = posix_acl_equiv_mode(*acl, &mode);
if (error < 0)
return error;
if (error == 0)
*acl = NULL;
if (!in_group_or_capable(idmap, inode,
i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
*mode_p = mode;
return 0;
}
EXPORT_SYMBOL(posix_acl_update_mode);
/*
* Fix up the uids and gids in posix acl extended attributes in place.
*/
static int posix_acl_fix_xattr_common(const void *value, size_t size)
{
const struct posix_acl_xattr_header *header = value;
int count;
if (!header)
return -EINVAL;
if (size < sizeof(struct posix_acl_xattr_header))
return -EINVAL;
if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
return -EOPNOTSUPP;
count = posix_acl_xattr_count(size);
if (count < 0)
return -EINVAL;
if (count == 0)
return 0;
return count;
}
/**
* posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format
* @userns: the filesystem's idmapping
* @value: the uapi representation of POSIX ACLs
* @size: the size of @void
*
* Filesystems that store POSIX ACLs in the unaltered uapi format should use
* posix_acl_from_xattr() when reading them from the backing store and
* converting them into the struct posix_acl VFS format. The helper is
* specifically intended to be called from the acl inode operation.
*
* The posix_acl_from_xattr() function will map the raw {g,u}id values stored
* in ACL_{GROUP,USER} entries into idmapping in @userns.
*
* Note that posix_acl_from_xattr() does not take idmapped mounts into account.
* If it did it calling it from the get acl inode operation would return POSIX
* ACLs mapped according to an idmapped mount which would mean that the value
* couldn't be cached for the filesystem. Idmapped mounts are taken into
* account on the fly during permission checking or right at the VFS -
* userspace boundary before reporting them to the user.
*
* Return: Allocated struct posix_acl on success, NULL for a valid header but
* without actual POSIX ACL entries, or ERR_PTR() encoded error code.
*/
struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns,
const void *value, size_t size)
{
const struct posix_acl_xattr_header *header = value;
const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end;
int count;
struct posix_acl *acl;
struct posix_acl_entry *acl_e;
count = posix_acl_fix_xattr_common(value, size);
if (count < 0)
return ERR_PTR(count);
if (count == 0)
return NULL;
acl = posix_acl_alloc(count, GFP_NOFS);
if (!acl)
return ERR_PTR(-ENOMEM);
acl_e = acl->a_entries;
for (end = entry + count; entry != end; acl_e++, entry++) {
acl_e->e_tag = le16_to_cpu(entry->e_tag);
acl_e->e_perm = le16_to_cpu(entry->e_perm);
switch(acl_e->e_tag) {
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
break;
case ACL_USER:
acl_e->e_uid = make_kuid(userns,
le32_to_cpu(entry->e_id));
if (!uid_valid(acl_e->e_uid))
goto fail;
break;
case ACL_GROUP:
acl_e->e_gid = make_kgid(userns,
le32_to_cpu(entry->e_id));
if (!gid_valid(acl_e->e_gid))
goto fail;
break;
default:
goto fail;
}
}
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL (posix_acl_from_xattr);
/*
* Convert from in-memory to extended attribute representation.
*/
int
posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
void *buffer, size_t size)
{
struct posix_acl_xattr_header *ext_acl = buffer;
struct posix_acl_xattr_entry *ext_entry;
int real_size, n;
real_size = posix_acl_xattr_size(acl->a_count);
if (!buffer)
return real_size;
if (real_size > size)
return -ERANGE;
ext_entry = (void *)(ext_acl + 1);
ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
for (n=0; n < acl->a_count; n++, ext_entry++) {
const struct posix_acl_entry *acl_e = &acl->a_entries[n];
ext_entry->e_tag = cpu_to_le16(acl_e->e_tag);
ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
switch(acl_e->e_tag) {
case ACL_USER:
ext_entry->e_id =
cpu_to_le32(from_kuid(user_ns, acl_e->e_uid));
break;
case ACL_GROUP:
ext_entry->e_id =
cpu_to_le32(from_kgid(user_ns, acl_e->e_gid));
break;
default:
ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
break;
}
}
return real_size;
}
EXPORT_SYMBOL (posix_acl_to_xattr);
/**
* vfs_posix_acl_to_xattr - convert from kernel to userspace representation
* @idmap: idmap of the mount
* @inode: inode the posix acls are set on
* @acl: the posix acls as represented by the vfs
* @buffer: the buffer into which to convert @acl
* @size: size of @buffer
*
* This converts @acl from the VFS representation in the filesystem idmapping
* to the uapi form reportable to userspace. And mount and caller idmappings
* are handled appropriately.
*
* Return: On success, the size of the stored uapi posix acls, on error a
* negative errno.
*/
static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
struct inode *inode,
const struct posix_acl *acl, void *buffer,
size_t size)
{
struct posix_acl_xattr_header *ext_acl = buffer;
struct posix_acl_xattr_entry *ext_entry;
struct user_namespace *fs_userns, *caller_userns;
ssize_t real_size, n;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
real_size = posix_acl_xattr_size(acl->a_count);
if (!buffer)
return real_size;
if (real_size > size)
return -ERANGE;
ext_entry = (void *)(ext_acl + 1);
ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
fs_userns = i_user_ns(inode);
caller_userns = current_user_ns();
for (n=0; n < acl->a_count; n++, ext_entry++) {
const struct posix_acl_entry *acl_e = &acl->a_entries[n];
ext_entry->e_tag = cpu_to_le16(acl_e->e_tag);
ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
switch(acl_e->e_tag) {
case ACL_USER:
vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid);
ext_entry->e_id = cpu_to_le32(from_kuid(
caller_userns, vfsuid_into_kuid(vfsuid)));
break;
case ACL_GROUP:
vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid);
ext_entry->e_id = cpu_to_le32(from_kgid(
caller_userns, vfsgid_into_kgid(vfsgid)));
break;
default:
ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
break;
}
}
return real_size;
}
int
set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry,
int type, struct posix_acl *acl)
{
struct inode *inode = d_inode(dentry);
if (!IS_POSIXACL(inode))
return -EOPNOTSUPP;
if (!inode->i_op->set_acl)
return -EOPNOTSUPP;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
if (!inode_owner_or_capable(idmap, inode))
return -EPERM;
if (acl) {
int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl);
if (ret)
return ret;
}
return inode->i_op->set_acl(idmap, dentry, acl, type);
}
EXPORT_SYMBOL(set_posix_acl);
int posix_acl_listxattr(struct inode *inode, char **buffer,
ssize_t *remaining_size)
{
int err;
if (!IS_POSIXACL(inode))
return 0;
if (inode->i_acl) {
err = xattr_list_one(buffer, remaining_size,
XATTR_NAME_POSIX_ACL_ACCESS);
if (err)
return err;
}
if (inode->i_default_acl) {
err = xattr_list_one(buffer, remaining_size,
XATTR_NAME_POSIX_ACL_DEFAULT);
if (err)
return err;
}
return 0;
}
static bool
posix_acl_xattr_list(struct dentry *dentry)
{
return IS_POSIXACL(d_backing_inode(dentry));
}
/*
* nop_posix_acl_access - legacy xattr handler for access POSIX ACLs
*
* This is the legacy POSIX ACL access xattr handler. It is used by some
* filesystems to implement their ->listxattr() inode operation. New code
* should never use them.
*/
const struct xattr_handler nop_posix_acl_access = {
.name = XATTR_NAME_POSIX_ACL_ACCESS,
.list = posix_acl_xattr_list,
};
EXPORT_SYMBOL_GPL(nop_posix_acl_access);
/*
* nop_posix_acl_default - legacy xattr handler for default POSIX ACLs
*
* This is the legacy POSIX ACL default xattr handler. It is used by some
* filesystems to implement their ->listxattr() inode operation. New code
* should never use them.
*/
const struct xattr_handler nop_posix_acl_default = {
.name = XATTR_NAME_POSIX_ACL_DEFAULT,
.list = posix_acl_xattr_list,
};
EXPORT_SYMBOL_GPL(nop_posix_acl_default);
int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
struct posix_acl *acl, int type)
{
int error;
struct inode *inode = d_inode(dentry);
if (type == ACL_TYPE_ACCESS) {
error = posix_acl_update_mode(idmap, inode,
&inode->i_mode, &acl);
if (error)
return error;
}
inode_set_ctime_current(inode);
if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
set_cached_acl(inode, type, acl);
return 0;
}
int simple_acl_create(struct inode *dir, struct inode *inode)
{
struct posix_acl *default_acl, *acl;
int error;
error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
if (error)
return error;
set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl);
set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl);
return 0;
}
static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap,
struct user_namespace *fs_userns,
struct posix_acl *acl)
{
for (int n = 0; n < acl->a_count; n++) {
struct posix_acl_entry *acl_e = &acl->a_entries[n];
switch (acl_e->e_tag) {
case ACL_USER:
acl_e->e_uid = from_vfsuid(idmap, fs_userns,
VFSUIDT_INIT(acl_e->e_uid));
break;
case ACL_GROUP:
acl_e->e_gid = from_vfsgid(idmap, fs_userns,
VFSGIDT_INIT(acl_e->e_gid));
break;
}
}
return 0;
}
/**
* vfs_set_acl - set posix acls
* @idmap: idmap of the mount
* @dentry: the dentry based on which to set the posix acls
* @acl_name: the name of the posix acl
* @kacl: the posix acls in the appropriate VFS format
*
* This function sets @kacl. The caller must all posix_acl_release() on @kacl
* afterwards.
*
* Return: On success 0, on error negative errno.
*/
int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name, struct posix_acl *kacl)
{
int acl_type;
int error;
struct inode *inode = d_inode(dentry);
struct inode *delegated_inode = NULL;
acl_type = posix_acl_type(acl_name);
if (acl_type < 0)
return -EINVAL;
if (kacl) {
/*
* If we're on an idmapped mount translate from mount specific
* vfs{g,u}id_t into global filesystem k{g,u}id_t.
* Afterwards we can cache the POSIX ACLs filesystem wide and -
* if this is a filesystem with a backing store - ultimately
* translate them to backing store values.
*/
error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl);
if (error)
return error;
}
retry_deleg:
inode_lock(inode);
/*
* We only care about restrictions the inode struct itself places upon
* us otherwise POSIX ACLs aren't subject to any VFS restrictions.
*/
error = may_write_xattr(idmap, inode);
if (error)
goto out_inode_unlock;
error = security_inode_set_acl(idmap, dentry, acl_name, kacl);
if (error)
goto out_inode_unlock;
error = try_break_deleg(inode, &delegated_inode);
if (error)
goto out_inode_unlock;
if (likely(!is_bad_inode(inode)))
error = set_posix_acl(idmap, dentry, acl_type, kacl);
else
error = -EIO;
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_set_acl(dentry, acl_name, kacl);
}
out_inode_unlock:
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_set_acl);
/**
* vfs_get_acl - get posix acls
* @idmap: idmap of the mount
* @dentry: the dentry based on which to retrieve the posix acls
* @acl_name: the name of the posix acl
*
* This function retrieves @kacl from the filesystem. The caller must all
* posix_acl_release() on @kacl.
*
* Return: On success POSIX ACLs in VFS format, on error negative errno.
*/
struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap,
struct dentry *dentry, const char *acl_name)
{
struct inode *inode = d_inode(dentry);
struct posix_acl *acl;
int acl_type, error;
acl_type = posix_acl_type(acl_name);
if (acl_type < 0)
return ERR_PTR(-EINVAL);
/*
* The VFS has no restrictions on reading POSIX ACLs so calling
* something like xattr_permission() isn't needed. Only LSMs get a say.
*/
error = security_inode_get_acl(idmap, dentry, acl_name);
if (error)
return ERR_PTR(error);
if (!IS_POSIXACL(inode))
return ERR_PTR(-EOPNOTSUPP);
if (S_ISLNK(inode->i_mode))
return ERR_PTR(-EOPNOTSUPP);
acl = __get_acl(idmap, dentry, inode, acl_type);
if (IS_ERR(acl))
return acl;
if (!acl)
return ERR_PTR(-ENODATA);
return acl;
}
EXPORT_SYMBOL_GPL(vfs_get_acl);
/**
* vfs_remove_acl - remove posix acls
* @idmap: idmap of the mount
* @dentry: the dentry based on which to retrieve the posix acls
* @acl_name: the name of the posix acl
*
* This function removes posix acls.
*
* Return: On success 0, on error negative errno.
*/
int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name)
{
int acl_type;
int error;
struct inode *inode = d_inode(dentry);
struct inode *delegated_inode = NULL;
acl_type = posix_acl_type(acl_name);
if (acl_type < 0)
return -EINVAL;
retry_deleg:
inode_lock(inode);
/*
* We only care about restrictions the inode struct itself places upon
* us otherwise POSIX ACLs aren't subject to any VFS restrictions.
*/
error = may_write_xattr(idmap, inode);
if (error)
goto out_inode_unlock;
error = security_inode_remove_acl(idmap, dentry, acl_name);
if (error)
goto out_inode_unlock;
error = try_break_deleg(inode, &delegated_inode);
if (error)
goto out_inode_unlock;
if (likely(!is_bad_inode(inode)))
error = set_posix_acl(idmap, dentry, acl_type, NULL);
else
error = -EIO;
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_remove_acl(idmap, dentry, acl_name);
}
out_inode_unlock:
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_remove_acl);
int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name, const void *kvalue, size_t size)
{
int error;
struct posix_acl *acl = NULL;
if (size) {
/*
* Note that posix_acl_from_xattr() uses GFP_NOFS when it
* probably doesn't need to here.
*/
acl = posix_acl_from_xattr(current_user_ns(), kvalue, size);
if (IS_ERR(acl))
return PTR_ERR(acl);
}
error = vfs_set_acl(idmap, dentry, acl_name, acl);
posix_acl_release(acl);
return error;
}
ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry,
const char *acl_name, void *kvalue, size_t size)
{
ssize_t error;
struct posix_acl *acl;
acl = vfs_get_acl(idmap, dentry, acl_name);
if (IS_ERR(acl))
return PTR_ERR(acl);
error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry),
acl, kvalue, size);
posix_acl_release(acl);
return error;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/readahead.c - address_space-level file readahead.
*
* Copyright (C) 2002, Linus Torvalds
*
* 09Apr2002 Andrew Morton
* Initial version.
*/
/**
* DOC: Readahead Overview
*
* Readahead is used to read content into the page cache before it is
* explicitly requested by the application. Readahead only ever
* attempts to read folios that are not yet in the page cache. If a
* folio is present but not up-to-date, readahead will not try to read
* it. In that case a simple ->read_folio() will be requested.
*
* Readahead is triggered when an application read request (whether a
* system call or a page fault) finds that the requested folio is not in
* the page cache, or that it is in the page cache and has the
* readahead flag set. This flag indicates that the folio was read
* as part of a previous readahead request and now that it has been
* accessed, it is time for the next readahead.
*
* Each readahead request is partly synchronous read, and partly async
* readahead. This is reflected in the struct file_ra_state which
* contains ->size being the total number of pages, and ->async_size
* which is the number of pages in the async section. The readahead
* flag will be set on the first folio in this async section to trigger
* a subsequent readahead. Once a series of sequential reads has been
* established, there should be no need for a synchronous component and
* all readahead request will be fully asynchronous.
*
* When either of the triggers causes a readahead, three numbers need
* to be determined: the start of the region to read, the size of the
* region, and the size of the async tail.
*
* The start of the region is simply the first page address at or after
* the accessed address, which is not currently populated in the page
* cache. This is found with a simple search in the page cache.
*
* The size of the async tail is determined by subtracting the size that
* was explicitly requested from the determined request size, unless
* this would be less than zero - then zero is used. NOTE THIS
* CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED
* PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY.
*
* The size of the region is normally determined from the size of the
* previous readahead which loaded the preceding pages. This may be
* discovered from the struct file_ra_state for simple sequential reads,
* or from examining the state of the page cache when multiple
* sequential reads are interleaved. Specifically: where the readahead
* was triggered by the readahead flag, the size of the previous
* readahead is assumed to be the number of pages from the triggering
* page to the start of the new readahead. In these cases, the size of
* the previous readahead is scaled, often doubled, for the new
* readahead, though see get_next_ra_size() for details.
*
* If the size of the previous read cannot be determined, the number of
* preceding pages in the page cache is used to estimate the size of
* a previous read. This estimate could easily be misled by random
* reads being coincidentally adjacent, so it is ignored unless it is
* larger than the current request, and it is not scaled up, unless it
* is at the start of file.
*
* In general readahead is accelerated at the start of the file, as
* reads from there are often sequential. There are other minor
* adjustments to the readahead size in various special cases and these
* are best discovered by reading the code.
*
* The above calculation, based on the previous readahead size,
* determines the size of the readahead, to which any requested read
* size may be added.
*
* Readahead requests are sent to the filesystem using the ->readahead()
* address space operation, for which mpage_readahead() is a canonical
* implementation. ->readahead() should normally initiate reads on all
* folios, but may fail to read any or all folios without causing an I/O
* error. The page cache reading code will issue a ->read_folio() request
* for any folio which ->readahead() did not read, and only an error
* from this will be final.
*
* ->readahead() will generally call readahead_folio() repeatedly to get
* each folio from those prepared for readahead. It may fail to read a
* folio by:
*
* * not calling readahead_folio() sufficiently many times, effectively
* ignoring some folios, as might be appropriate if the path to
* storage is congested.
*
* * failing to actually submit a read request for a given folio,
* possibly due to insufficient resources, or
*
* * getting an error during subsequent processing of a request.
*
* In the last two cases, the folio should be unlocked by the filesystem
* to indicate that the read attempt has failed. In the first case the
* folio will be unlocked by the VFS.
*
* Those folios not in the final ``async_size`` of the request should be
* considered to be important and ->readahead() should not fail them due
* to congestion or temporary resource unavailability, but should wait
* for necessary resources (e.g. memory or indexing information) to
* become available. Folios in the final ``async_size`` may be
* considered less urgent and failure to read them is more acceptable.
* In this case it is best to use filemap_remove_folio() to remove the
* folios from the page cache as is automatically done for folios that
* were not fetched with readahead_folio(). This will allow a
* subsequent synchronous readahead request to try them again. If they
* are left in the page cache, then they will be read individually using
* ->read_folio() which may be less efficient.
*/
#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/pagemap.h>
#include <linux/psi.h>
#include <linux/syscalls.h>
#include <linux/file.h>
#include <linux/mm_inline.h>
#include <linux/blk-cgroup.h>
#include <linux/fadvise.h>
#include <linux/sched/mm.h>
#include "internal.h"
/*
* Initialise a struct file's readahead state. Assumes that the caller has
* memset *ra to zero.
*/
void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
ra->prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);
static void read_pages(struct readahead_control *rac)
{
const struct address_space_operations *aops = rac->mapping->a_ops;
struct folio *folio;
struct blk_plug plug;
if (!readahead_count(rac))
return;
if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags);
blk_start_plug(&plug);
if (aops->readahead) {
aops->readahead(rac);
/* Clean up the remaining folios. */
while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio);
filemap_remove_folio(folio);
folio_unlock(folio);
folio_put(folio);
}
} else {
while ((folio = readahead_folio(rac)) != NULL)
aops->read_folio(rac->file, folio);
}
blk_finish_plug(&plug);
if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags);
rac->_workingset = false;
BUG_ON(readahead_count(rac));
}
static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
gfp_t gfp_mask, unsigned int order)
{
struct folio *folio;
folio = filemap_alloc_folio(gfp_mask, order);
if (folio && ractl->dropbehind) __folio_set_dropbehind(folio);
return folio;
}
/**
* page_cache_ra_unbounded - Start unchecked readahead.
* @ractl: Readahead control.
* @nr_to_read: The number of pages to read.
* @lookahead_size: Where to start the next readahead.
*
* This function is for filesystems to call when they want to start
* readahead beyond a file's stated i_size. This is almost certainly
* not the function you want to call. Use page_cache_async_readahead()
* or page_cache_sync_readahead() instead.
*
* Context: File is referenced by caller. Mutexes may be held by caller.
* May sleep, but will not reenter filesystem to reclaim memory.
*/
void page_cache_ra_unbounded(struct readahead_control *ractl,
unsigned long nr_to_read, unsigned long lookahead_size)
{
struct address_space *mapping = ractl->mapping;
unsigned long index = readahead_index(ractl);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
unsigned long mark = ULONG_MAX, i = 0;
unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
/*
* Partway through the readahead operation, we will have added
* locked pages to the page cache, but will not yet have submitted
* them for I/O. Adding another page may need to allocate memory,
* which can trigger memory reclaim. Telling the VM we're in
* the middle of a filesystem operation will cause it to not
* touch file-backed pages, preventing a deadlock. Most (all?)
* filesystems already specify __GFP_NOFS in their mapping's
* gfp_mask, but let's be explicit here.
*/
unsigned int nofs = memalloc_nofs_save();
filemap_invalidate_lock_shared(mapping);
index = mapping_align_index(mapping, index);
/*
* As iterator `i` is aligned to min_nrpages, round_up the
* difference between nr_to_read and lookahead_size to mark the
* index that only has lookahead or "async_region" to set the
* readahead flag.
*/
if (lookahead_size <= nr_to_read) {
unsigned long ra_folio_index;
ra_folio_index = round_up(readahead_index(ractl) +
nr_to_read - lookahead_size,
min_nrpages);
mark = ra_folio_index - index;
}
nr_to_read += readahead_index(ractl) - index;
ractl->_index = index;
/*
* Preallocate as many pages as we will need.
*/
while (i < nr_to_read) {
struct folio *folio = xa_load(&mapping->i_pages, index + i);
int ret;
if (folio && !xa_is_value(folio)) {
/*
* Page already present? Kick off the current batch
* of contiguous pages before continuing with the
* next batch. This page may be the one we would
* have intended to mark as Readahead, but we don't
* have a stable reference to this page, and it's
* not worth getting one just for that.
*/
read_pages(ractl);
ractl->_index += min_nrpages;
i = ractl->_index + ractl->_nr_pages - index;
continue;
}
folio = ractl_alloc_folio(ractl, gfp_mask,
mapping_min_folio_order(mapping));
if (!folio)
break;
ret = filemap_add_folio(mapping, folio, index + i, gfp_mask);
if (ret < 0) {
folio_put(folio); if (ret == -ENOMEM)
break;
read_pages(ractl);
ractl->_index += min_nrpages;
i = ractl->_index + ractl->_nr_pages - index;
continue;
}
if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio);
ractl->_nr_pages += min_nrpages;
i += min_nrpages;
}
/*
* Now start the IO. We ignore I/O errors - if the folio is not
* uptodate then the caller will launch read_folio again, and
* will then handle the error.
*/
read_pages(ractl);
filemap_invalidate_unlock_shared(mapping);
memalloc_nofs_restore(nofs);
}
EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
/*
* do_page_cache_ra() actually reads a chunk of disk. It allocates
* the pages first, then submits them for I/O. This avoids the very bad
* behaviour which would occur if page allocations are causing VM writeback.
* We really don't want to intermingle reads and writes like that.
*/
static void do_page_cache_ra(struct readahead_control *ractl,
unsigned long nr_to_read, unsigned long lookahead_size)
{
struct inode *inode = ractl->mapping->host;
unsigned long index = readahead_index(ractl);
loff_t isize = i_size_read(inode);
pgoff_t end_index; /* The last page we want to read */
if (isize == 0)
return;
end_index = (isize - 1) >> PAGE_SHIFT;
if (index > end_index)
return;
/* Don't read past the page containing the last byte of the file */
if (nr_to_read > end_index - index)
nr_to_read = end_index - index + 1;
page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size);
}
/*
* Chunk the readahead into 2 megabyte units, so that we don't pin too much
* memory at once.
*/
void force_page_cache_ra(struct readahead_control *ractl,
unsigned long nr_to_read)
{
struct address_space *mapping = ractl->mapping;
struct file_ra_state *ra = ractl->ra;
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long max_pages;
if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead))
return;
/*
* If the request exceeds the readahead window, allow the read to
* be up to the optimal hardware IO size
*/
max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
nr_to_read = min_t(unsigned long, nr_to_read, max_pages);
while (nr_to_read) {
unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;
if (this_chunk > nr_to_read)
this_chunk = nr_to_read;
do_page_cache_ra(ractl, this_chunk, 0);
nr_to_read -= this_chunk;
}
}
/*
* Set the initial window size, round to next power of 2 and square
* for small size, x 4 for medium, and x 2 for large
* for 128k (32 page) max ra
* 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial
*/
static unsigned long get_init_ra_size(unsigned long size, unsigned long max)
{
unsigned long newsize = roundup_pow_of_two(size);
if (newsize <= max / 32)
newsize = newsize * 4;
else if (newsize <= max / 4)
newsize = newsize * 2;
else
newsize = max;
return newsize;
}
/*
* Get the previous window size, ramp it up, and
* return it as the new window size.
*/
static unsigned long get_next_ra_size(struct file_ra_state *ra,
unsigned long max)
{
unsigned long cur = ra->size;
if (cur < max / 16)
return 4 * cur;
if (cur <= max / 2)
return 2 * cur;
return max;
}
/*
* On-demand readahead design.
*
* The fields in struct file_ra_state represent the most-recently-executed
* readahead attempt:
*
* |<----- async_size ---------|
* |------------------- size -------------------->|
* |==================#===========================|
* ^start ^page marked with PG_readahead
*
* To overlap application thinking time and disk I/O time, we do
* `readahead pipelining': Do not wait until the application consumed all
* readahead pages and stalled on the missing page at readahead_index;
* Instead, submit an asynchronous readahead I/O as soon as there are
* only async_size pages left in the readahead window. Normally async_size
* will be equal to size, for maximum pipelining.
*
* In interleaved sequential reads, concurrent streams on the same fd can
* be invalidating each other's readahead state. So we flag the new readahead
* page at (start+size-async_size) with PG_readahead, and use it as readahead
* indicator. The flag won't be set on already cached pages, to avoid the
* readahead-for-nothing fuss, saving pointless page cache lookups.
*
* prev_pos tracks the last visited byte in the _previous_ read request.
* It should be maintained by the caller, and will be used for detecting
* small random reads. Note that the readahead algorithm checks loosely
* for sequential patterns. Hence interleaved reads might be served as
* sequential ones.
*
* There is a special-case: if the first page which the application tries to
* read happens to be the first page of the file, it is assumed that a linear
* read is about to happen and the window is immediately set to the initial size
* based on I/O request size and the max_readahead.
*
* The code ramps up the readahead size aggressively at first, but slow down as
* it approaches max_readhead.
*/
static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
pgoff_t mark, unsigned int order, gfp_t gfp)
{
int err;
struct folio *folio = ractl_alloc_folio(ractl, gfp, order);
if (!folio)
return -ENOMEM;
mark = round_down(mark, 1UL << order);
if (index == mark) folio_set_readahead(folio);
err = filemap_add_folio(ractl->mapping, folio, index, gfp);
if (err) {
folio_put(folio);
return err;
}
ractl->_nr_pages += 1UL << order;
ractl->_workingset |= folio_test_workingset(folio);
return 0;
}
void page_cache_ra_order(struct readahead_control *ractl,
struct file_ra_state *ra, unsigned int new_order)
{
struct address_space *mapping = ractl->mapping;
pgoff_t start = readahead_index(ractl);
pgoff_t index = start;
unsigned int min_order = mapping_min_folio_order(mapping);
pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
pgoff_t mark = index + ra->size - ra->async_size;
unsigned int nofs;
int err = 0;
gfp_t gfp = readahead_gfp_mask(mapping);
unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping));
/*
* Fallback when size < min_nrpages as each folio should be
* at least min_nrpages anyway.
*/
if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size)
goto fallback;
limit = min(limit, index + ra->size - 1);
if (new_order < mapping_max_folio_order(mapping))
new_order += 2;
new_order = min(mapping_max_folio_order(mapping), new_order);
new_order = min_t(unsigned int, new_order, ilog2(ra->size));
new_order = max(new_order, min_order);
/* See comment in page_cache_ra_unbounded() */
nofs = memalloc_nofs_save();
filemap_invalidate_lock_shared(mapping);
/*
* If the new_order is greater than min_order and index is
* already aligned to new_order, then this will be noop as index
* aligned to new_order should also be aligned to min_order.
*/
ractl->_index = mapping_align_index(mapping, index);
index = readahead_index(ractl);
while (index <= limit) {
unsigned int order = new_order;
/* Align with smaller pages if needed */
if (index & ((1UL << order) - 1))
order = __ffs(index);
/* Don't allocate pages past EOF */
while (order > min_order && index + (1UL << order) - 1 > limit)
order--;
err = ra_alloc_folio(ractl, index, mark, order, gfp);
if (err)
break;
index += 1UL << order;
}
read_pages(ractl);
filemap_invalidate_unlock_shared(mapping);
memalloc_nofs_restore(nofs);
/*
* If there were already pages in the page cache, then we may have
* left some gaps. Let the regular readahead code take care of this
* situation below.
*/
if (!err)
return;
fallback:
/*
* ->readahead() may have updated readahead window size so we have to
* check there's still something to read.
*/
if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start),
ra->async_size);
}
static unsigned long ractl_max_pages(struct readahead_control *ractl,
unsigned long req_size)
{
struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host);
unsigned long max_pages = ractl->ra->ra_pages;
/*
* If the request exceeds the readahead window, allow the read to
* be up to the optimal hardware IO size
*/
if (req_size > max_pages && bdi->io_pages > max_pages)
max_pages = min(req_size, bdi->io_pages);
return max_pages;
}
void page_cache_sync_ra(struct readahead_control *ractl,
unsigned long req_count)
{
pgoff_t index = readahead_index(ractl);
bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM);
struct file_ra_state *ra = ractl->ra;
unsigned long max_pages, contig_count;
pgoff_t prev_index, miss;
/*
* Even if readahead is disabled, issue this request as readahead
* as we'll need it to satisfy the requested range. The forced
* readahead will do the right thing and limit the read to just the
* requested range, which we'll set to 1 page for this case.
*/
if (!ra->ra_pages || blk_cgroup_congested()) {
if (!ractl->file)
return;
req_count = 1;
do_forced_ra = true;
}
/* be dumb */
if (do_forced_ra) {
force_page_cache_ra(ractl, req_count);
return;
}
max_pages = ractl_max_pages(ractl, req_count);
prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT;
/*
* A start of file, oversized read, or sequential cache miss:
* trivial case: (index - prev_index) == 1
* unaligned reads: (index - prev_index) == 0
*/
if (!index || req_count > max_pages || index - prev_index <= 1UL) {
ra->start = index;
ra->size = get_init_ra_size(req_count, max_pages);
ra->async_size = ra->size > req_count ? ra->size - req_count :
ra->size >> 1;
goto readit;
}
/*
* Query the page cache and look for the traces(cached history pages)
* that a sequential stream would leave behind.
*/
rcu_read_lock();
miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages);
rcu_read_unlock();
contig_count = index - miss - 1;
/*
* Standalone, small random read. Read as is, and do not pollute the
* readahead state.
*/
if (contig_count <= req_count) {
do_page_cache_ra(ractl, req_count, 0);
return;
}
/*
* File cached from the beginning:
* it is a strong indication of long-run stream (or whole-file-read)
*/
if (miss == ULONG_MAX)
contig_count *= 2;
ra->start = index;
ra->size = min(contig_count + req_count, max_pages);
ra->async_size = 1;
readit:
ractl->_index = ra->start;
page_cache_ra_order(ractl, ra, 0);
}
EXPORT_SYMBOL_GPL(page_cache_sync_ra);
void page_cache_async_ra(struct readahead_control *ractl,
struct folio *folio, unsigned long req_count)
{
unsigned long max_pages;
struct file_ra_state *ra = ractl->ra;
pgoff_t index = readahead_index(ractl);
pgoff_t expected, start;
unsigned int order = folio_order(folio);
/* no readahead */
if (!ra->ra_pages)
return;
/*
* Same bit is used for PG_readahead and PG_reclaim.
*/
if (folio_test_writeback(folio))
return;
folio_clear_readahead(folio);
if (blk_cgroup_congested())
return;
max_pages = ractl_max_pages(ractl, req_count);
/*
* It's the expected callback index, assume sequential access.
* Ramp up sizes, and push forward the readahead window.
*/
expected = round_down(ra->start + ra->size - ra->async_size,
1UL << order);
if (index == expected) {
ra->start += ra->size;
/*
* In the case of MADV_HUGEPAGE, the actual size might exceed
* the readahead window.
*/
ra->size = max(ra->size, get_next_ra_size(ra, max_pages));
ra->async_size = ra->size;
goto readit;
}
/*
* Hit a marked folio without valid readahead state.
* E.g. interleaved reads.
* Query the pagecache for async_size, which normally equals to
* readahead size. Ramp it up and use it as the new readahead size.
*/
rcu_read_lock();
start = page_cache_next_miss(ractl->mapping, index + 1, max_pages);
rcu_read_unlock();
if (!start || start - index > max_pages)
return;
ra->start = start;
ra->size = start - index; /* old async_size */
ra->size += req_count;
ra->size = get_next_ra_size(ra, max_pages);
ra->async_size = ra->size;
readit:
ractl->_index = ra->start;
page_cache_ra_order(ractl, ra, order);
}
EXPORT_SYMBOL_GPL(page_cache_async_ra);
ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
{
CLASS(fd, f)(fd);
if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ))
return -EBADF;
/*
* The readahead() syscall is intended to run only on files
* that can execute readahead. If readahead is not possible
* on this file, then we must return -EINVAL.
*/
if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops ||
(!S_ISREG(file_inode(fd_file(f))->i_mode) &&
!S_ISBLK(file_inode(fd_file(f))->i_mode)))
return -EINVAL;
return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED);
}
SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
{
return ksys_readahead(fd, offset, count);
}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD)
COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count)
{
return ksys_readahead(fd, compat_arg_u64_glue(offset), count);
}
#endif
/**
* readahead_expand - Expand a readahead request
* @ractl: The request to be expanded
* @new_start: The revised start
* @new_len: The revised size of the request
*
* Attempt to expand a readahead request outwards from the current size to the
* specified size by inserting locked pages before and after the current window
* to increase the size to the new window. This may involve the insertion of
* THPs, in which case the window may get expanded even beyond what was
* requested.
*
* The algorithm will stop if it encounters a conflicting page already in the
* pagecache and leave a smaller expansion than requested.
*
* The caller must check for this by examining the revised @ractl object for a
* different expansion than was requested.
*/
void readahead_expand(struct readahead_control *ractl,
loff_t new_start, size_t new_len)
{
struct address_space *mapping = ractl->mapping;
struct file_ra_state *ra = ractl->ra;
pgoff_t new_index, new_nr_pages;
gfp_t gfp_mask = readahead_gfp_mask(mapping);
unsigned long min_nrpages = mapping_min_folio_nrpages(mapping);
unsigned int min_order = mapping_min_folio_order(mapping);
new_index = new_start / PAGE_SIZE;
/*
* Readahead code should have aligned the ractl->_index to
* min_nrpages before calling readahead aops.
*/
VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages));
/* Expand the leading edge downwards */
while (ractl->_index > new_index) {
unsigned long index = ractl->_index - 1;
struct folio *folio = xa_load(&mapping->i_pages, index);
if (folio && !xa_is_value(folio))
return; /* Folio apparently present */
folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
if (!folio)
return;
index = mapping_align_index(mapping, index);
if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
folio_put(folio);
return;
}
if (unlikely(folio_test_workingset(folio)) &&
!ractl->_workingset) {
ractl->_workingset = true;
psi_memstall_enter(&ractl->_pflags);
}
ractl->_nr_pages += min_nrpages;
ractl->_index = folio->index;
}
new_len += new_start - readahead_pos(ractl);
new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE);
/* Expand the trailing edge upwards */
while (ractl->_nr_pages < new_nr_pages) {
unsigned long index = ractl->_index + ractl->_nr_pages;
struct folio *folio = xa_load(&mapping->i_pages, index);
if (folio && !xa_is_value(folio))
return; /* Folio apparently present */
folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
if (!folio)
return;
index = mapping_align_index(mapping, index);
if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
folio_put(folio);
return;
}
if (unlikely(folio_test_workingset(folio)) &&
!ractl->_workingset) {
ractl->_workingset = true;
psi_memstall_enter(&ractl->_pflags);
}
ractl->_nr_pages += min_nrpages;
if (ra) {
ra->size += min_nrpages;
ra->async_size += min_nrpages;
}
}
}
EXPORT_SYMBOL(readahead_expand);
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/bitmap.h>
#include <linux/bug.h>
#include <linux/export.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/xarray.h>
/**
* idr_alloc_u32() - Allocate an ID.
* @idr: IDR handle.
* @ptr: Pointer to be associated with the new ID.
* @nextid: Pointer to an ID.
* @max: The maximum ID to allocate (inclusive).
* @gfp: Memory allocation flags.
*
* Allocates an unused ID in the range specified by @nextid and @max.
* Note that @max is inclusive whereas the @end parameter to idr_alloc()
* is exclusive. The new ID is assigned to @nextid before the pointer
* is inserted into the IDR, so if @nextid points into the object pointed
* to by @ptr, a concurrent lookup will not find an uninitialised ID.
*
* The caller should provide their own locking to ensure that two
* concurrent modifications to the IDR are not possible. Read-only
* accesses to the IDR may be done under the RCU read lock or may
* exclude simultaneous writers.
*
* Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed,
* or -ENOSPC if no free IDs could be found. If an error occurred,
* @nextid is unchanged.
*/
int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
unsigned long max, gfp_t gfp)
{
struct radix_tree_iter iter;
void __rcu **slot;
unsigned int base = idr->idr_base;
unsigned int id = *nextid;
if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR)))
idr->idr_rt.xa_flags |= IDR_RT_MARKER;
id = (id < base) ? 0 : id - base;
radix_tree_iter_init(&iter, id);
slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base);
if (IS_ERR(slot))
return PTR_ERR(slot);
*nextid = iter.index + base;
/* there is a memory barrier inside radix_tree_iter_replace() */
radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
return 0;
}
EXPORT_SYMBOL_GPL(idr_alloc_u32);
/**
* idr_alloc() - Allocate an ID.
* @idr: IDR handle.
* @ptr: Pointer to be associated with the new ID.
* @start: The minimum ID (inclusive).
* @end: The maximum ID (exclusive).
* @gfp: Memory allocation flags.
*
* Allocates an unused ID in the range specified by @start and @end. If
* @end is <= 0, it is treated as one larger than %INT_MAX. This allows
* callers to use @start + N as @end as long as N is within integer range.
*
* The caller should provide their own locking to ensure that two
* concurrent modifications to the IDR are not possible. Read-only
* accesses to the IDR may be done under the RCU read lock or may
* exclude simultaneous writers.
*
* Return: The newly allocated ID, -ENOMEM if memory allocation failed,
* or -ENOSPC if no free IDs could be found.
*/
int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
{
u32 id = start;
int ret;
if (WARN_ON_ONCE(start < 0))
return -EINVAL;
ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp);
if (ret)
return ret;
return id;
}
EXPORT_SYMBOL_GPL(idr_alloc);
/**
* idr_alloc_cyclic() - Allocate an ID cyclically.
* @idr: IDR handle.
* @ptr: Pointer to be associated with the new ID.
* @start: The minimum ID (inclusive).
* @end: The maximum ID (exclusive).
* @gfp: Memory allocation flags.
*
* Allocates an unused ID in the range specified by @start and @end. If
* @end is <= 0, it is treated as one larger than %INT_MAX. This allows
* callers to use @start + N as @end as long as N is within integer range.
* The search for an unused ID will start at the last ID allocated and will
* wrap around to @start if no free IDs are found before reaching @end.
*
* The caller should provide their own locking to ensure that two
* concurrent modifications to the IDR are not possible. Read-only
* accesses to the IDR may be done under the RCU read lock or may
* exclude simultaneous writers.
*
* Return: The newly allocated ID, -ENOMEM if memory allocation failed,
* or -ENOSPC if no free IDs could be found.
*/
int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
{
u32 id = idr->idr_next;
int err, max = end > 0 ? end - 1 : INT_MAX;
if ((int)id < start)
id = start;
err = idr_alloc_u32(idr, ptr, &id, max, gfp);
if ((err == -ENOSPC) && (id > start)) {
id = start;
err = idr_alloc_u32(idr, ptr, &id, max, gfp);
}
if (err)
return err;
idr->idr_next = id + 1;
return id;
}
EXPORT_SYMBOL(idr_alloc_cyclic);
/**
* idr_remove() - Remove an ID from the IDR.
* @idr: IDR handle.
* @id: Pointer ID.
*
* Removes this ID from the IDR. If the ID was not previously in the IDR,
* this function returns %NULL.
*
* Since this function modifies the IDR, the caller should provide their
* own locking to ensure that concurrent modification of the same IDR is
* not possible.
*
* Return: The pointer formerly associated with this ID.
*/
void *idr_remove(struct idr *idr, unsigned long id)
{
return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL);
}
EXPORT_SYMBOL_GPL(idr_remove);
/**
* idr_find() - Return pointer for given ID.
* @idr: IDR handle.
* @id: Pointer ID.
*
* Looks up the pointer associated with this ID. A %NULL pointer may
* indicate that @id is not allocated or that the %NULL pointer was
* associated with this ID.
*
* This function can be called under rcu_read_lock(), given that the leaf
* pointers lifetimes are correctly managed.
*
* Return: The pointer associated with this ID.
*/
void *idr_find(const struct idr *idr, unsigned long id)
{
return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base);
}
EXPORT_SYMBOL_GPL(idr_find);
/**
* idr_for_each() - Iterate through all stored pointers.
* @idr: IDR handle.
* @fn: Function to be called for each pointer.
* @data: Data passed to callback function.
*
* The callback function will be called for each entry in @idr, passing
* the ID, the entry and @data.
*
* If @fn returns anything other than %0, the iteration stops and that
* value is returned from this function.
*
* idr_for_each() can be called concurrently with idr_alloc() and
* idr_remove() if protected by RCU. Newly added entries may not be
* seen and deleted entries may be seen, but adding and removing entries
* will not cause other entries to be skipped, nor spurious ones to be seen.
*/
int idr_for_each(const struct idr *idr,
int (*fn)(int id, void *p, void *data), void *data)
{
struct radix_tree_iter iter;
void __rcu **slot;
int base = idr->idr_base;
radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) {
int ret;
unsigned long id = iter.index + base;
if (WARN_ON_ONCE(id > INT_MAX))
break;
ret = fn(id, rcu_dereference_raw(*slot), data);
if (ret)
return ret;
}
return 0;
}
EXPORT_SYMBOL(idr_for_each);
/**
* idr_get_next_ul() - Find next populated entry.
* @idr: IDR handle.
* @nextid: Pointer to an ID.
*
* Returns the next populated entry in the tree with an ID greater than
* or equal to the value pointed to by @nextid. On exit, @nextid is updated
* to the ID of the found value. To use in a loop, the value pointed to by
* nextid must be incremented by the user.
*/
void *idr_get_next_ul(struct idr *idr, unsigned long *nextid)
{
struct radix_tree_iter iter;
void __rcu **slot;
void *entry = NULL;
unsigned long base = idr->idr_base;
unsigned long id = *nextid;
id = (id < base) ? 0 : id - base;
radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) {
entry = rcu_dereference_raw(*slot);
if (!entry)
continue;
if (!xa_is_internal(entry))
break;
if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry))
break;
slot = radix_tree_iter_retry(&iter);
}
if (!slot)
return NULL;
*nextid = iter.index + base;
return entry;
}
EXPORT_SYMBOL(idr_get_next_ul);
/**
* idr_get_next() - Find next populated entry.
* @idr: IDR handle.
* @nextid: Pointer to an ID.
*
* Returns the next populated entry in the tree with an ID greater than
* or equal to the value pointed to by @nextid. On exit, @nextid is updated
* to the ID of the found value. To use in a loop, the value pointed to by
* nextid must be incremented by the user.
*/
void *idr_get_next(struct idr *idr, int *nextid)
{
unsigned long id = *nextid;
void *entry = idr_get_next_ul(idr, &id);
if (WARN_ON_ONCE(id > INT_MAX))
return NULL;
*nextid = id;
return entry;
}
EXPORT_SYMBOL(idr_get_next);
/**
* idr_replace() - replace pointer for given ID.
* @idr: IDR handle.
* @ptr: New pointer to associate with the ID.
* @id: ID to change.
*
* Replace the pointer registered with an ID and return the old value.
* This function can be called under the RCU read lock concurrently with
* idr_alloc() and idr_remove() (as long as the ID being removed is not
* the one being replaced!).
*
* Returns: the old value on success. %-ENOENT indicates that @id was not
* found. %-EINVAL indicates that @ptr was not valid.
*/
void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
{
struct radix_tree_node *node;
void __rcu **slot = NULL;
void *entry;
id -= idr->idr_base;
entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot);
if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
return ERR_PTR(-ENOENT);
__radix_tree_replace(&idr->idr_rt, node, slot, ptr);
return entry;
}
EXPORT_SYMBOL(idr_replace);
/**
* DOC: IDA description
*
* The IDA is an ID allocator which does not provide the ability to
* associate an ID with a pointer. As such, it only needs to store one
* bit per ID, and so is more space efficient than an IDR. To use an IDA,
* define it using DEFINE_IDA() (or embed a &struct ida in a data structure,
* then initialise it using ida_init()). To allocate a new ID, call
* ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range().
* To free an ID, call ida_free().
*
* ida_destroy() can be used to dispose of an IDA without needing to
* free the individual IDs in it. You can use ida_is_empty() to find
* out whether the IDA has any IDs currently allocated.
*
* The IDA handles its own locking. It is safe to call any of the IDA
* functions without synchronisation in your code.
*
* IDs are currently limited to the range [0-INT_MAX]. If this is an awkward
* limitation, it should be quite straightforward to raise the maximum.
*/
/*
* Developer's notes:
*
* The IDA uses the functionality provided by the XArray to store bitmaps in
* each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap
* have been set.
*
* I considered telling the XArray that each slot is an order-10 node
* and indexing by bit number, but the XArray can't allow a single multi-index
* entry in the head, which would significantly increase memory consumption
* for the IDA. So instead we divide the index by the number of bits in the
* leaf bitmap before doing a radix tree lookup.
*
* As an optimisation, if there are only a few low bits set in any given
* leaf, instead of allocating a 128-byte bitmap, we store the bits
* as a value entry. Value entries never have the XA_FREE_MARK cleared
* because we can always convert them into a bitmap entry.
*
* It would be possible to optimise further; once we've run out of a
* single 128-byte bitmap, we currently switch to a 576-byte node, put
* the 128-byte bitmap in the first entry and then start allocating extra
* 128-byte entries. We could instead use the 512 bytes of the node's
* data as a bitmap before moving to that scheme. I do not believe this
* is a worthwhile optimisation; Rasmus Villemoes surveyed the current
* users of the IDA and almost none of them use more than 1024 entries.
* Those that do use more than the 8192 IDs that the 512 bytes would
* provide.
*
* The IDA always uses a lock to alloc/free. If we add a 'test_bit'
* equivalent, it will still need locking. Going to RCU lookup would require
* using RCU to free bitmaps, and that's not trivial without embedding an
* RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte
* bitmap, which is excessive.
*/
/**
* ida_alloc_range() - Allocate an unused ID.
* @ida: IDA handle.
* @min: Lowest ID to allocate.
* @max: Highest ID to allocate.
* @gfp: Memory allocation flags.
*
* Allocate an ID between @min and @max, inclusive. The allocated ID will
* not exceed %INT_MAX, even if @max is larger.
*
* Context: Any context. It is safe to call this function without
* locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max,
gfp_t gfp)
{
XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS);
unsigned bit = min % IDA_BITMAP_BITS;
unsigned long flags;
struct ida_bitmap *bitmap, *alloc = NULL;
if ((int)min < 0)
return -ENOSPC;
if ((int)max < 0)
max = INT_MAX;
retry:
xas_lock_irqsave(&xas, flags);
next:
bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK);
if (xas.xa_index > min / IDA_BITMAP_BITS)
bit = 0;
if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
goto nospc;
if (xa_is_value(bitmap)) {
unsigned long tmp = xa_to_value(bitmap);
if (bit < BITS_PER_XA_VALUE) {
bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit);
if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
goto nospc;
if (bit < BITS_PER_XA_VALUE) {
tmp |= 1UL << bit;
xas_store(&xas, xa_mk_value(tmp));
goto out;
}
}
bitmap = alloc;
if (!bitmap)
bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
if (!bitmap)
goto alloc;
bitmap->bitmap[0] = tmp;
xas_store(&xas, bitmap);
if (xas_error(&xas)) {
bitmap->bitmap[0] = 0;
goto out;
}
}
if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
goto nospc;
if (bit == IDA_BITMAP_BITS)
goto next;
__set_bit(bit, bitmap->bitmap);
if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK);
} else {
if (bit < BITS_PER_XA_VALUE) {
bitmap = xa_mk_value(1UL << bit);
} else {
bitmap = alloc;
if (!bitmap)
bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
if (!bitmap)
goto alloc;
__set_bit(bit, bitmap->bitmap);
}
xas_store(&xas, bitmap);
}
out:
xas_unlock_irqrestore(&xas, flags);
if (xas_nomem(&xas, gfp)) {
xas.xa_index = min / IDA_BITMAP_BITS;
bit = min % IDA_BITMAP_BITS;
goto retry;
}
if (bitmap != alloc) kfree(alloc); if (xas_error(&xas))
return xas_error(&xas);
return xas.xa_index * IDA_BITMAP_BITS + bit;
alloc:
xas_unlock_irqrestore(&xas, flags);
alloc = kzalloc(sizeof(*bitmap), gfp); if (!alloc)
return -ENOMEM;
xas_set(&xas, min / IDA_BITMAP_BITS);
bit = min % IDA_BITMAP_BITS;
goto retry;
nospc:
xas_unlock_irqrestore(&xas, flags);
kfree(alloc);
return -ENOSPC;
}
EXPORT_SYMBOL(ida_alloc_range);
/**
* ida_find_first_range - Get the lowest used ID.
* @ida: IDA handle.
* @min: Lowest ID to get.
* @max: Highest ID to get.
*
* Get the lowest used ID between @min and @max, inclusive. The returned
* ID will not exceed %INT_MAX, even if @max is larger.
*
* Context: Any context. Takes and releases the xa_lock.
* Return: The lowest used ID, or errno if no used ID is found.
*/
int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max)
{
unsigned long index = min / IDA_BITMAP_BITS;
unsigned int offset = min % IDA_BITMAP_BITS;
unsigned long *addr, size, bit;
unsigned long tmp = 0;
unsigned long flags;
void *entry;
int ret;
if ((int)min < 0)
return -EINVAL;
if ((int)max < 0)
max = INT_MAX;
xa_lock_irqsave(&ida->xa, flags);
entry = xa_find(&ida->xa, &index, max / IDA_BITMAP_BITS, XA_PRESENT);
if (!entry) {
ret = -ENOENT;
goto err_unlock;
}
if (index > min / IDA_BITMAP_BITS)
offset = 0;
if (index * IDA_BITMAP_BITS + offset > max) {
ret = -ENOENT;
goto err_unlock;
}
if (xa_is_value(entry)) {
tmp = xa_to_value(entry);
addr = &tmp;
size = BITS_PER_XA_VALUE;
} else {
addr = ((struct ida_bitmap *)entry)->bitmap;
size = IDA_BITMAP_BITS;
}
bit = find_next_bit(addr, size, offset);
xa_unlock_irqrestore(&ida->xa, flags);
if (bit == size ||
index * IDA_BITMAP_BITS + bit > max)
return -ENOENT;
return index * IDA_BITMAP_BITS + bit;
err_unlock:
xa_unlock_irqrestore(&ida->xa, flags);
return ret;
}
EXPORT_SYMBOL(ida_find_first_range);
/**
* ida_free() - Release an allocated ID.
* @ida: IDA handle.
* @id: Previously allocated ID.
*
* Context: Any context. It is safe to call this function without
* locking in your code.
*/
void ida_free(struct ida *ida, unsigned int id)
{
XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS);
unsigned bit = id % IDA_BITMAP_BITS;
struct ida_bitmap *bitmap;
unsigned long flags;
if ((int)id < 0)
return;
xas_lock_irqsave(&xas, flags);
bitmap = xas_load(&xas);
if (xa_is_value(bitmap)) {
unsigned long v = xa_to_value(bitmap);
if (bit >= BITS_PER_XA_VALUE)
goto err;
if (!(v & (1UL << bit)))
goto err;
v &= ~(1UL << bit);
if (!v)
goto delete;
xas_store(&xas, xa_mk_value(v));
} else {
if (!bitmap || !test_bit(bit, bitmap->bitmap))
goto err;
__clear_bit(bit, bitmap->bitmap);
xas_set_mark(&xas, XA_FREE_MARK);
if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap);
delete:
xas_store(&xas, NULL);
}
}
xas_unlock_irqrestore(&xas, flags);
return;
err:
xas_unlock_irqrestore(&xas, flags);
WARN(1, "ida_free called for id=%d which is not allocated.\n", id);
}
EXPORT_SYMBOL(ida_free);
/**
* ida_destroy() - Free all IDs.
* @ida: IDA handle.
*
* Calling this function frees all IDs and releases all resources used
* by an IDA. When this call returns, the IDA is empty and can be reused
* or freed. If the IDA is already empty, there is no need to call this
* function.
*
* Context: Any context. It is safe to call this function without
* locking in your code.
*/
void ida_destroy(struct ida *ida)
{
XA_STATE(xas, &ida->xa, 0);
struct ida_bitmap *bitmap;
unsigned long flags;
xas_lock_irqsave(&xas, flags);
xas_for_each(&xas, bitmap, ULONG_MAX) {
if (!xa_is_value(bitmap))
kfree(bitmap);
xas_store(&xas, NULL);
}
xas_unlock_irqrestore(&xas, flags);
}
EXPORT_SYMBOL(ida_destroy);
#ifndef __KERNEL__
extern void xa_dump_index(unsigned long index, unsigned int shift);
#define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS)
static void ida_dump_entry(void *entry, unsigned long index)
{
unsigned long i;
if (!entry)
return;
if (xa_is_node(entry)) {
struct xa_node *node = xa_to_node(entry);
unsigned int shift = node->shift + IDA_CHUNK_SHIFT +
XA_CHUNK_SHIFT;
xa_dump_index(index * IDA_BITMAP_BITS, shift);
xa_dump_node(node);
for (i = 0; i < XA_CHUNK_SIZE; i++)
ida_dump_entry(node->slots[i],
index | (i << node->shift));
} else if (xa_is_value(entry)) {
xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG));
pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry);
} else {
struct ida_bitmap *bitmap = entry;
xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT);
pr_cont("bitmap: %p data", bitmap);
for (i = 0; i < IDA_BITMAP_LONGS; i++)
pr_cont(" %lx", bitmap->bitmap[i]);
pr_cont("\n");
}
}
static void ida_dump(struct ida *ida)
{
struct xarray *xa = &ida->xa;
pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head,
xa->xa_flags >> ROOT_TAG_SHIFT);
ida_dump_entry(xa->xa_head, 0);
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* SMP initialisation and IPI support
* Based on arch/arm/kernel/smp.c
*
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/acpi.h>
#include <linux/arm_sdei.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/sched/mm.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
#include <linux/interrupt.h>
#include <linux/cache.h>
#include <linux/profile.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/seq_file.h>
#include <linux/irq.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/completion.h>
#include <linux/of.h>
#include <linux/irq_work.h>
#include <linux/kernel_stat.h>
#include <linux/kexec.h>
#include <linux/kgdb.h>
#include <linux/kvm_host.h>
#include <linux/nmi.h>
#include <asm/alternative.h>
#include <asm/atomic.h>
#include <asm/cacheflush.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/cpu_ops.h>
#include <asm/daifflags.h>
#include <asm/kvm_mmu.h>
#include <asm/mmu_context.h>
#include <asm/numa.h>
#include <asm/processor.h>
#include <asm/smp_plat.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/ptrace.h>
#include <asm/virt.h>
#include <trace/events/ipi.h>
/*
* as from 2.5, kernels no longer have an init_tasks structure
* so we need some other way of telling a new secondary core
* where to place its SVC stack
*/
struct secondary_data secondary_data;
/* Number of CPUs which aren't online, but looping in kernel text. */
static int cpus_stuck_in_kernel;
enum ipi_msg_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
IPI_CPU_STOP_NMI,
IPI_TIMER,
IPI_IRQ_WORK,
NR_IPI,
/*
* Any enum >= NR_IPI and < MAX_IPI is special and not tracable
* with trace_ipi_*
*/
IPI_CPU_BACKTRACE = NR_IPI,
IPI_KGDB_ROUNDUP,
MAX_IPI
};
static int ipi_irq_base __ro_after_init;
static int nr_ipi __ro_after_init = NR_IPI;
static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init;
static bool crash_stop;
static void ipi_setup(int cpu);
#ifdef CONFIG_HOTPLUG_CPU
static void ipi_teardown(int cpu);
static int op_cpu_kill(unsigned int cpu);
#else
static inline int op_cpu_kill(unsigned int cpu)
{
return -ENOSYS;
}
#endif
/*
* Boot a secondary CPU, and assign it the specified idle task.
* This also gives us the initial stack to use for this CPU.
*/
static int boot_secondary(unsigned int cpu, struct task_struct *idle)
{
const struct cpu_operations *ops = get_cpu_ops(cpu);
if (ops->cpu_boot)
return ops->cpu_boot(cpu);
return -EOPNOTSUPP;
}
static DECLARE_COMPLETION(cpu_running);
int __cpu_up(unsigned int cpu, struct task_struct *idle)
{
int ret;
long status;
/*
* We need to tell the secondary core where to find its stack and the
* page tables.
*/
secondary_data.task = idle;
update_cpu_boot_status(CPU_MMU_OFF);
/* Now bring the CPU into our world */
ret = boot_secondary(cpu, idle);
if (ret) {
if (ret != -EPERM)
pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
return ret;
}
/*
* CPU was successfully started, wait for it to come online or
* time out.
*/
wait_for_completion_timeout(&cpu_running,
msecs_to_jiffies(5000));
if (cpu_online(cpu))
return 0;
pr_crit("CPU%u: failed to come online\n", cpu);
secondary_data.task = NULL;
status = READ_ONCE(secondary_data.status);
if (status == CPU_MMU_OFF)
status = READ_ONCE(__early_cpu_boot_status);
switch (status & CPU_BOOT_STATUS_MASK) {
default:
pr_err("CPU%u: failed in unknown state : 0x%lx\n",
cpu, status);
cpus_stuck_in_kernel++;
break;
case CPU_KILL_ME:
if (!op_cpu_kill(cpu)) {
pr_crit("CPU%u: died during early boot\n", cpu);
break;
}
pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
fallthrough;
case CPU_STUCK_IN_KERNEL:
pr_crit("CPU%u: is stuck in kernel\n", cpu);
if (status & CPU_STUCK_REASON_52_BIT_VA)
pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
if (status & CPU_STUCK_REASON_NO_GRAN) {
pr_crit("CPU%u: does not support %luK granule\n",
cpu, PAGE_SIZE / SZ_1K);
}
cpus_stuck_in_kernel++;
break;
case CPU_PANIC_KERNEL:
panic("CPU%u detected unsupported configuration\n", cpu);
}
return -EIO;
}
static void init_gic_priority_masking(void)
{
u32 cpuflags;
if (WARN_ON(!gic_enable_sre()))
return;
cpuflags = read_sysreg(daif);
WARN_ON(!(cpuflags & PSR_I_BIT));
WARN_ON(!(cpuflags & PSR_F_BIT));
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
}
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
*/
asmlinkage notrace void secondary_start_kernel(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
const struct cpu_operations *ops;
unsigned int cpu = smp_processor_id();
/*
* All kernel threads share the same mm context; grab a
* reference and switch to it.
*/
mmgrab(mm);
current->active_mm = mm;
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
*/
cpu_uninstall_idmap();
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
rcutree_report_cpu_starting(cpu);
trace_hardirqs_off();
/*
* If the system has established the capabilities, make sure
* this CPU ticks all of those. If it doesn't, the CPU will
* fail to come online.
*/
check_local_cpu_capabilities();
ops = get_cpu_ops(cpu);
if (ops->cpu_postboot)
ops->cpu_postboot();
/*
* Log the CPU info before it is marked online and might get read.
*/
cpuinfo_store_cpu();
store_cpu_topology(cpu);
/*
* Enable GIC and timers.
*/
notify_cpu_starting(cpu);
ipi_setup(cpu);
numa_add_cpu(cpu);
/*
* OK, now it's safe to let the boot CPU continue. Wait for
* the CPU migration code to notice that the CPU is online
* before we continue.
*/
pr_info("CPU%u: Booted secondary processor 0x%010lx [0x%08x]\n",
cpu, (unsigned long)mpidr,
read_cpuid_id());
update_cpu_boot_status(CPU_BOOT_SUCCESS);
set_cpu_online(cpu, true);
complete(&cpu_running);
/*
* Secondary CPUs enter the kernel with all DAIF exceptions masked.
*
* As with setup_arch() we must unmask Debug and SError exceptions, and
* as the root irqchip has already been detected and initialized we can
* unmask IRQ and FIQ at the same time.
*/
local_daif_restore(DAIF_PROCCTX);
/*
* OK, it's off to the idle thread for us
*/
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
#ifdef CONFIG_HOTPLUG_CPU
static int op_cpu_disable(unsigned int cpu)
{
const struct cpu_operations *ops = get_cpu_ops(cpu);
/*
* If we don't have a cpu_die method, abort before we reach the point
* of no return. CPU0 may not have an cpu_ops, so test for it.
*/
if (!ops || !ops->cpu_die)
return -EOPNOTSUPP;
/*
* We may need to abort a hot unplug for some other mechanism-specific
* reason.
*/
if (ops->cpu_disable)
return ops->cpu_disable(cpu);
return 0;
}
/*
* __cpu_disable runs on the processor to be shutdown.
*/
int __cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
int ret;
ret = op_cpu_disable(cpu);
if (ret)
return ret;
remove_cpu_topology(cpu);
numa_remove_cpu(cpu);
/*
* Take this CPU offline. Once we clear this, we can't return,
* and we must not schedule until we're ready to give up the cpu.
*/
set_cpu_online(cpu, false);
ipi_teardown(cpu);
/*
* OK - migrate IRQs away from this CPU
*/
irq_migrate_all_off_this_cpu();
return 0;
}
static int op_cpu_kill(unsigned int cpu)
{
const struct cpu_operations *ops = get_cpu_ops(cpu);
/*
* If we have no means of synchronising with the dying CPU, then assume
* that it is really dead. We can only wait for an arbitrary length of
* time and hope that it's dead, so let's skip the wait and just hope.
*/
if (!ops->cpu_kill)
return 0;
return ops->cpu_kill(cpu);
}
/*
* Called on the thread which is asking for a CPU to be shutdown after the
* shutdown completed.
*/
void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
{
int err;
pr_debug("CPU%u: shutdown\n", cpu);
/*
* Now that the dying CPU is beyond the point of no return w.r.t.
* in-kernel synchronisation, try to get the firwmare to help us to
* verify that it has really left the kernel before we consider
* clobbering anything it might still be using.
*/
err = op_cpu_kill(cpu);
if (err)
pr_warn("CPU%d may not have shut down cleanly: %d\n", cpu, err);
}
/*
* Called from the idle thread for the CPU which has been shutdown.
*
*/
void __noreturn cpu_die(void)
{
unsigned int cpu = smp_processor_id();
const struct cpu_operations *ops = get_cpu_ops(cpu);
idle_task_exit();
local_daif_mask();
/* Tell cpuhp_bp_sync_dead() that this CPU is now safe to dispose of */
cpuhp_ap_report_dead();
/*
* Actually shutdown the CPU. This must never fail. The specific hotplug
* mechanism must perform all required cache maintenance to ensure that
* no dirty lines are lost in the process of shutting down the CPU.
*/
ops->cpu_die(cpu);
BUG();
}
#endif
static void __cpu_try_die(int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
const struct cpu_operations *ops = get_cpu_ops(cpu);
if (ops && ops->cpu_die)
ops->cpu_die(cpu);
#endif
}
/*
* Kill the calling secondary CPU, early in bringup before it is turned
* online.
*/
void __noreturn cpu_die_early(void)
{
int cpu = smp_processor_id();
pr_crit("CPU%d: will not boot\n", cpu);
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
rcutree_report_cpu_dead();
if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
update_cpu_boot_status(CPU_KILL_ME);
__cpu_try_die(cpu);
}
update_cpu_boot_status(CPU_STUCK_IN_KERNEL);
cpu_park_loop();
}
static void __init hyp_mode_check(void)
{
if (is_hyp_mode_available())
pr_info("CPU: All CPU(s) started at EL2\n");
else if (is_hyp_mode_mismatched())
WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC,
"CPU: CPUs started in inconsistent modes");
else
pr_info("CPU: All CPU(s) started at EL1\n");
if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) {
kvm_compute_layout();
kvm_apply_hyp_relocations();
}
}
void __init smp_cpus_done(unsigned int max_cpus)
{
pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
hyp_mode_check();
setup_system_features();
setup_user_features();
mark_linear_text_alias_ro();
}
void __init smp_prepare_boot_cpu(void)
{
/*
* The runtime per-cpu areas have been allocated by
* setup_per_cpu_areas(), and CPU0's boot time per-cpu area will be
* freed shortly, so we must move over to the runtime per-cpu area.
*/
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
cpuinfo_store_boot_cpu();
setup_boot_cpu_features();
/* Conditionally switch to GIC PMR for interrupt masking */
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
kasan_init_hw_tags();
/* Init percpu seeds for random tags after cpus are set up. */
kasan_init_sw_tags();
}
/*
* Duplicate MPIDRs are a recipe for disaster. Scan all initialized
* entries and check for duplicates. If any is found just ignore the
* cpu. cpu_logical_map was initialized to INVALID_HWID to avoid
* matching valid MPIDR values.
*/
static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
{
unsigned int i;
for (i = 1; (i < cpu) && (i < NR_CPUS); i++)
if (cpu_logical_map(i) == hwid)
return true;
return false;
}
/*
* Initialize cpu operations for a logical cpu and
* set it in the possible mask on success
*/
static int __init smp_cpu_setup(int cpu)
{
const struct cpu_operations *ops;
if (init_cpu_ops(cpu))
return -ENODEV;
ops = get_cpu_ops(cpu);
if (ops->cpu_init(cpu))
return -ENODEV;
set_cpu_possible(cpu, true);
return 0;
}
static bool bootcpu_valid __initdata;
static unsigned int cpu_count = 1;
int arch_register_cpu(int cpu)
{
acpi_handle acpi_handle = acpi_get_processor_handle(cpu);
struct cpu *c = &per_cpu(cpu_devices, cpu);
if (!acpi_disabled && !acpi_handle &&
IS_ENABLED(CONFIG_ACPI_HOTPLUG_CPU))
return -EPROBE_DEFER;
#ifdef CONFIG_ACPI_HOTPLUG_CPU
/* For now block anything that looks like physical CPU Hotplug */
if (invalid_logical_cpuid(cpu) || !cpu_present(cpu)) {
pr_err_once("Changing CPU present bit is not supported\n");
return -ENODEV;
}
#endif
/*
* Availability of the acpi handle is sufficient to establish
* that _STA has aleady been checked. No need to recheck here.
*/
c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
return register_cpu(c, cpu);
}
#ifdef CONFIG_ACPI_HOTPLUG_CPU
void arch_unregister_cpu(int cpu)
{
acpi_handle acpi_handle = acpi_get_processor_handle(cpu);
struct cpu *c = &per_cpu(cpu_devices, cpu);
acpi_status status;
unsigned long long sta;
if (!acpi_handle) {
pr_err_once("Removing a CPU without associated ACPI handle\n");
return;
}
status = acpi_evaluate_integer(acpi_handle, "_STA", NULL, &sta);
if (ACPI_FAILURE(status))
return;
/* For now do not allow anything that looks like physical CPU HP */
if (cpu_present(cpu) && !(sta & ACPI_STA_DEVICE_PRESENT)) {
pr_err_once("Changing CPU present bit is not supported\n");
return;
}
unregister_cpu(c);
}
#endif /* CONFIG_ACPI_HOTPLUG_CPU */
#ifdef CONFIG_ACPI
static struct acpi_madt_generic_interrupt cpu_madt_gicc[NR_CPUS];
struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
{
return &cpu_madt_gicc[cpu];
}
EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc);
/*
* acpi_map_gic_cpu_interface - parse processor MADT entry
*
* Carry out sanity checks on MADT processor entry and initialize
* cpu_logical_map on success
*/
static void __init
acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
{
u64 hwid = processor->arm_mpidr;
if (!(processor->flags &
(ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) {
pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
return;
}
if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
return;
}
if (is_mpidr_duplicate(cpu_count, hwid)) {
pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid);
return;
}
/* Check if GICC structure of boot CPU is available in the MADT */
if (cpu_logical_map(0) == hwid) {
if (bootcpu_valid) {
pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n",
hwid);
return;
}
bootcpu_valid = true;
cpu_madt_gicc[0] = *processor;
return;
}
if (cpu_count >= NR_CPUS)
return;
/* map the logical cpu id to cpu MPIDR */
set_cpu_logical_map(cpu_count, hwid);
cpu_madt_gicc[cpu_count] = *processor;
/*
* Set-up the ACPI parking protocol cpu entries
* while initializing the cpu_logical_map to
* avoid parsing MADT entries multiple times for
* nothing (ie a valid cpu_logical_map entry should
* contain a valid parking protocol data set to
* initialize the cpu if the parking protocol is
* the only available enable method).
*/
acpi_set_mailbox_entry(cpu_count, processor);
cpu_count++;
}
static int __init
acpi_parse_gic_cpu_interface(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *processor;
processor = (struct acpi_madt_generic_interrupt *)header;
if (BAD_MADT_GICC_ENTRY(processor, end))
return -EINVAL;
acpi_table_print_madt_entry(&header->common);
acpi_map_gic_cpu_interface(processor);
return 0;
}
static void __init acpi_parse_and_init_cpus(void)
{
int i;
/*
* do a walk of MADT to determine how many CPUs
* we have including disabled CPUs, and get information
* we need for SMP init.
*/
acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
acpi_parse_gic_cpu_interface, 0);
/*
* In ACPI, SMP and CPU NUMA information is provided in separate
* static tables, namely the MADT and the SRAT.
*
* Thus, it is simpler to first create the cpu logical map through
* an MADT walk and then map the logical cpus to their node ids
* as separate steps.
*/
acpi_map_cpus_to_nodes();
for (i = 0; i < nr_cpu_ids; i++)
early_map_cpu_to_node(i, acpi_numa_get_nid(i));
}
#else
#define acpi_parse_and_init_cpus(...) do { } while (0)
#endif
/*
* Enumerate the possible CPU set from the device tree and build the
* cpu logical map array containing MPIDR values related to logical
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
*/
static void __init of_parse_and_init_cpus(void)
{
struct device_node *dn;
for_each_of_cpu_node(dn) {
u64 hwid = of_get_cpu_hwid(dn, 0);
if (hwid & ~MPIDR_HWID_BITMASK)
goto next;
if (is_mpidr_duplicate(cpu_count, hwid)) {
pr_err("%pOF: duplicate cpu reg properties in the DT\n",
dn);
goto next;
}
/*
* The numbering scheme requires that the boot CPU
* must be assigned logical id 0. Record it so that
* the logical map built from DT is validated and can
* be used.
*/
if (hwid == cpu_logical_map(0)) {
if (bootcpu_valid) {
pr_err("%pOF: duplicate boot cpu reg property in DT\n",
dn);
goto next;
}
bootcpu_valid = true;
early_map_cpu_to_node(0, of_node_to_nid(dn));
/*
* cpu_logical_map has already been
* initialized and the boot cpu doesn't need
* the enable-method so continue without
* incrementing cpu.
*/
continue;
}
if (cpu_count >= NR_CPUS)
goto next;
pr_debug("cpu logical map 0x%llx\n", hwid);
set_cpu_logical_map(cpu_count, hwid);
early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
next:
cpu_count++;
}
}
/*
* Enumerate the possible CPU set from the device tree or ACPI and build the
* cpu logical map array containing MPIDR values related to logical
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
*/
void __init smp_init_cpus(void)
{
int i;
if (acpi_disabled)
of_parse_and_init_cpus();
else
acpi_parse_and_init_cpus();
if (cpu_count > nr_cpu_ids)
pr_warn("Number of cores (%d) exceeds configured maximum of %u - clipping\n",
cpu_count, nr_cpu_ids);
if (!bootcpu_valid) {
pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
return;
}
/*
* We need to set the cpu_logical_map entries before enabling
* the cpus so that cpu processor description entries (DT cpu nodes
* and ACPI MADT entries) can be retrieved by matching the cpu hwid
* with entries in cpu_logical_map while initializing the cpus.
* If the cpu set-up fails, invalidate the cpu_logical_map entry.
*/
for (i = 1; i < nr_cpu_ids; i++) {
if (cpu_logical_map(i) != INVALID_HWID) {
if (smp_cpu_setup(i))
set_cpu_logical_map(i, INVALID_HWID);
}
}
}
void __init smp_prepare_cpus(unsigned int max_cpus)
{
const struct cpu_operations *ops;
int err;
unsigned int cpu;
unsigned int this_cpu;
init_cpu_topology();
this_cpu = smp_processor_id();
store_cpu_topology(this_cpu);
numa_store_cpu_info(this_cpu);
numa_add_cpu(this_cpu);
/*
* If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
* secondary CPUs present.
*/
if (max_cpus == 0)
return;
/*
* Initialise the present map (which describes the set of CPUs
* actually populated at the present time) and release the
* secondaries from the bootloader.
*/
for_each_possible_cpu(cpu) {
if (cpu == smp_processor_id())
continue;
ops = get_cpu_ops(cpu);
if (!ops)
continue;
err = ops->cpu_prepare(cpu);
if (err)
continue;
set_cpu_present(cpu, true);
numa_store_cpu_info(cpu);
}
}
static const char *ipi_types[MAX_IPI] __tracepoint_string = {
[IPI_RESCHEDULE] = "Rescheduling interrupts",
[IPI_CALL_FUNC] = "Function call interrupts",
[IPI_CPU_STOP] = "CPU stop interrupts",
[IPI_CPU_STOP_NMI] = "CPU stop NMIs",
[IPI_TIMER] = "Timer broadcast interrupts",
[IPI_IRQ_WORK] = "IRQ work interrupts",
[IPI_CPU_BACKTRACE] = "CPU backtrace interrupts",
[IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts",
};
static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
unsigned long irq_err_count;
int arch_show_interrupts(struct seq_file *p, int prec)
{
unsigned int cpu, i;
for (i = 0; i < MAX_IPI; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
seq_printf(p, " %s\n", ipi_types[i]);
}
seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
return 0;
}
void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_CALL_FUNC);
}
void arch_send_call_function_single_ipi(int cpu)
{
smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
}
#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
}
#endif
static void __noreturn local_cpu_stop(unsigned int cpu)
{
set_cpu_online(cpu, false);
local_daif_mask();
sdei_mask_local_cpu();
cpu_park_loop();
}
/*
* We need to implement panic_smp_self_stop() for parallel panic() calls, so
* that cpu_online_mask gets correctly updated and smp_send_stop() can skip
* CPUs that have already stopped themselves.
*/
void __noreturn panic_smp_self_stop(void)
{
local_cpu_stop(smp_processor_id());
}
static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
#ifdef CONFIG_KEXEC_CORE
/*
* Use local_daif_mask() instead of local_irq_disable() to make sure
* that pseudo-NMIs are disabled. The "crash stop" code starts with
* an IRQ and falls back to NMI (which might be pseudo). If the IRQ
* finally goes through right as we're timing out then the NMI could
* interrupt us. It's better to prevent the NMI and let the IRQ
* finish since the pt_regs will be better.
*/
local_daif_mask();
crash_save_cpu(regs, cpu);
set_cpu_online(cpu, false);
sdei_mask_local_cpu();
if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
__cpu_try_die(cpu);
/* just in case */
cpu_park_loop();
#else
BUG();
#endif
}
static void arm64_backtrace_ipi(cpumask_t *mask)
{
__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
}
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
{
/*
* NOTE: though nmi_trigger_cpumask_backtrace() has "nmi_" in the name,
* nothing about it truly needs to be implemented using an NMI, it's
* just that it's _allowed_ to work with NMIs. If ipi_should_be_nmi()
* returned false our backtrace attempt will just use a regular IPI.
*/
nmi_trigger_cpumask_backtrace(mask, exclude_cpu, arm64_backtrace_ipi);
}
#ifdef CONFIG_KGDB
void kgdb_roundup_cpus(void)
{
int this_cpu = raw_smp_processor_id();
int cpu;
for_each_online_cpu(cpu) {
/* No need to roundup ourselves */
if (cpu == this_cpu)
continue;
__ipi_send_single(ipi_desc[IPI_KGDB_ROUNDUP], cpu);
}
}
#endif
/*
* Main handler for inter-processor interrupts
*/
static void do_handle_IPI(int ipinr)
{
unsigned int cpu = smp_processor_id();
if ((unsigned)ipinr < NR_IPI)
trace_ipi_entry(ipi_types[ipinr]);
switch (ipinr) {
case IPI_RESCHEDULE:
scheduler_ipi();
break;
case IPI_CALL_FUNC:
generic_smp_call_function_interrupt();
break;
case IPI_CPU_STOP:
case IPI_CPU_STOP_NMI:
if (IS_ENABLED(CONFIG_KEXEC_CORE) && crash_stop) {
ipi_cpu_crash_stop(cpu, get_irq_regs());
unreachable();
} else {
local_cpu_stop(cpu);
}
break;
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
case IPI_TIMER:
tick_receive_broadcast();
break;
#endif
#ifdef CONFIG_IRQ_WORK
case IPI_IRQ_WORK:
irq_work_run();
break;
#endif
case IPI_CPU_BACKTRACE:
/*
* NOTE: in some cases this _won't_ be NMI context. See the
* comment in arch_trigger_cpumask_backtrace().
*/
nmi_cpu_backtrace(get_irq_regs());
break;
case IPI_KGDB_ROUNDUP:
kgdb_nmicallback(cpu, get_irq_regs());
break;
default:
pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
break;
}
if ((unsigned)ipinr < NR_IPI)
trace_ipi_exit(ipi_types[ipinr]);
}
static irqreturn_t ipi_handler(int irq, void *data)
{
do_handle_IPI(irq - ipi_irq_base);
return IRQ_HANDLED;
}
static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
{ trace_ipi_raise(target, ipi_types[ipinr]);
__ipi_send_mask(ipi_desc[ipinr], target);
}
static bool ipi_should_be_nmi(enum ipi_msg_type ipi)
{
if (!system_uses_irq_prio_masking())
return false;
switch (ipi) {
case IPI_CPU_STOP_NMI:
case IPI_CPU_BACKTRACE:
case IPI_KGDB_ROUNDUP:
return true;
default:
return false;
}
}
static void ipi_setup(int cpu)
{
int i;
if (WARN_ON_ONCE(!ipi_irq_base))
return;
for (i = 0; i < nr_ipi; i++) {
if (ipi_should_be_nmi(i)) {
prepare_percpu_nmi(ipi_irq_base + i);
enable_percpu_nmi(ipi_irq_base + i, 0);
} else {
enable_percpu_irq(ipi_irq_base + i, 0);
}
}
}
#ifdef CONFIG_HOTPLUG_CPU
static void ipi_teardown(int cpu)
{
int i;
if (WARN_ON_ONCE(!ipi_irq_base))
return;
for (i = 0; i < nr_ipi; i++) {
if (ipi_should_be_nmi(i)) {
disable_percpu_nmi(ipi_irq_base + i);
teardown_percpu_nmi(ipi_irq_base + i);
} else {
disable_percpu_irq(ipi_irq_base + i);
}
}
}
#endif
void __init set_smp_ipi_range(int ipi_base, int n)
{
int i;
WARN_ON(n < MAX_IPI);
nr_ipi = min(n, MAX_IPI);
for (i = 0; i < nr_ipi; i++) {
int err;
if (ipi_should_be_nmi(i)) {
err = request_percpu_nmi(ipi_base + i, ipi_handler,
"IPI", &irq_stat);
WARN(err, "Could not request IPI %d as NMI, err=%d\n",
i, err);
} else {
err = request_percpu_irq(ipi_base + i, ipi_handler,
"IPI", &irq_stat);
WARN(err, "Could not request IPI %d as IRQ, err=%d\n",
i, err);
}
ipi_desc[i] = irq_to_desc(ipi_base + i);
irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
}
ipi_irq_base = ipi_base;
/* Setup the boot CPU immediately */
ipi_setup(smp_processor_id());
}
void arch_smp_send_reschedule(int cpu)
{
smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
}
#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
void arch_send_wakeup_ipi(unsigned int cpu)
{
/*
* We use a scheduler IPI to wake the CPU as this avoids the need for a
* dedicated IPI and we can safely handle spurious scheduler IPIs.
*/
smp_send_reschedule(cpu);
}
#endif
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
smp_cross_call(mask, IPI_TIMER);
}
#endif
/*
* The number of CPUs online, not counting this CPU (which may not be
* fully online and so not counted in num_online_cpus()).
*/
static inline unsigned int num_other_online_cpus(void)
{
unsigned int this_cpu_online = cpu_online(smp_processor_id());
return num_online_cpus() - this_cpu_online;
}
void smp_send_stop(void)
{
static unsigned long stop_in_progress;
cpumask_t mask;
unsigned long timeout;
/*
* If this cpu is the only one alive at this point in time, online or
* not, there are no stop messages to be sent around, so just back out.
*/
if (num_other_online_cpus() == 0)
goto skip_ipi;
/* Only proceed if this is the first CPU to reach this code */
if (test_and_set_bit(0, &stop_in_progress))
return;
/*
* Send an IPI to all currently online CPUs except the CPU running
* this code.
*
* NOTE: we don't do anything here to prevent other CPUs from coming
* online after we snapshot `cpu_online_mask`. Ideally, the calling code
* should do something to prevent other CPUs from coming up. This code
* can be called in the panic path and thus it doesn't seem wise to
* grab the CPU hotplug mutex ourselves. Worst case:
* - If a CPU comes online as we're running, we'll likely notice it
* during the 1 second wait below and then we'll catch it when we try
* with an NMI (assuming NMIs are enabled) since we re-snapshot the
* mask before sending an NMI.
* - If we leave the function and see that CPUs are still online we'll
* at least print a warning. Especially without NMIs this function
* isn't foolproof anyway so calling code will just have to accept
* the fact that there could be cases where a CPU can't be stopped.
*/
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
if (system_state <= SYSTEM_RUNNING)
pr_crit("SMP: stopping secondary CPUs\n");
/*
* Start with a normal IPI and wait up to one second for other CPUs to
* stop. We do this first because it gives other processors a chance
* to exit critical sections / drop locks and makes the rest of the
* stop process (especially console flush) more robust.
*/
smp_cross_call(&mask, IPI_CPU_STOP);
timeout = USEC_PER_SEC;
while (num_other_online_cpus() && timeout--)
udelay(1);
/*
* If CPUs are still online, try an NMI. There's no excuse for this to
* be slow, so we only give them an extra 10 ms to respond.
*/
if (num_other_online_cpus() && ipi_should_be_nmi(IPI_CPU_STOP_NMI)) {
smp_rmb();
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
pr_info("SMP: retry stop with NMI for CPUs %*pbl\n",
cpumask_pr_args(&mask));
smp_cross_call(&mask, IPI_CPU_STOP_NMI);
timeout = USEC_PER_MSEC * 10;
while (num_other_online_cpus() && timeout--)
udelay(1);
}
if (num_other_online_cpus()) {
smp_rmb();
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(&mask));
}
skip_ipi:
sdei_mask_local_cpu();
}
#ifdef CONFIG_KEXEC_CORE
void crash_smp_send_stop(void)
{
/*
* This function can be called twice in panic path, but obviously
* we execute this only once.
*
* We use this same boolean to tell whether the IPI we send was a
* stop or a "crash stop".
*/
if (crash_stop)
return;
crash_stop = 1;
smp_send_stop();
sdei_handler_abort();
}
bool smp_crash_stop_failed(void)
{
return num_other_online_cpus() != 0;
}
#endif
static bool have_cpu_die(void)
{
#ifdef CONFIG_HOTPLUG_CPU
int any_cpu = raw_smp_processor_id();
const struct cpu_operations *ops = get_cpu_ops(any_cpu);
if (ops && ops->cpu_die)
return true;
#endif
return false;
}
bool cpus_are_stuck_in_kernel(void)
{
bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
return !!cpus_stuck_in_kernel || smp_spin_tables ||
is_protected_kvm_enabled();
}
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef __KVM_HOST_H
#define __KVM_HOST_H
#include <linux/types.h>
#include <linux/hardirq.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#include <linux/bug.h>
#include <linux/minmax.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/preempt.h>
#include <linux/msi.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/rcupdate.h>
#include <linux/ratelimit.h>
#include <linux/err.h>
#include <linux/irqflags.h>
#include <linux/context_tracking.h>
#include <linux/irqbypass.h>
#include <linux/rcuwait.h>
#include <linux/refcount.h>
#include <linux/nospec.h>
#include <linux/notifier.h>
#include <linux/ftrace.h>
#include <linux/hashtable.h>
#include <linux/instrumentation.h>
#include <linux/interval_tree.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
#include <asm/signal.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
#include <linux/kvm_types.h>
#include <asm/kvm_host.h>
#include <linux/kvm_dirty_ring.h>
#ifndef KVM_MAX_VCPU_IDS
#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS
#endif
/*
* The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally
* used in kvm, other bits are visible for userspace which are defined in
* include/linux/kvm_h.
*/
#define KVM_MEMSLOT_INVALID (1UL << 16)
/*
* Bit 63 of the memslot generation number is an "update in-progress flag",
* e.g. is temporarily set for the duration of kvm_swap_active_memslots().
* This flag effectively creates a unique generation number that is used to
* mark cached memslot data, e.g. MMIO accesses, as potentially being stale,
* i.e. may (or may not) have come from the previous memslots generation.
*
* This is necessary because the actual memslots update is not atomic with
* respect to the generation number update. Updating the generation number
* first would allow a vCPU to cache a spte from the old memslots using the
* new generation number, and updating the generation number after switching
* to the new memslots would allow cache hits using the old generation number
* to reference the defunct memslots.
*
* This mechanism is used to prevent getting hits in KVM's caches while a
* memslot update is in-progress, and to prevent cache hits *after* updating
* the actual generation number against accesses that were inserted into the
* cache *before* the memslots were updated.
*/
#define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63)
/* Two fragments for cross MMIO pages. */
#define KVM_MAX_MMIO_FRAGMENTS 2
#ifndef KVM_MAX_NR_ADDRESS_SPACES
#define KVM_MAX_NR_ADDRESS_SPACES 1
#endif
/*
* For the normal pfn, the highest 12 bits should be zero,
* so we can mask bit 62 ~ bit 52 to indicate the error pfn,
* mask bit 63 to indicate the noslot pfn.
*/
#define KVM_PFN_ERR_MASK (0x7ffULL << 52)
#define KVM_PFN_ERR_NOSLOT_MASK (0xfffULL << 52)
#define KVM_PFN_NOSLOT (0x1ULL << 63)
#define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK)
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3)
#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4)
/*
* error pfns indicate that the gfn is in slot but faild to
* translate it to pfn on host.
*/
static inline bool is_error_pfn(kvm_pfn_t pfn)
{
return !!(pfn & KVM_PFN_ERR_MASK);
}
/*
* KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted
* by a pending signal. Note, the signal may or may not be fatal.
*/
static inline bool is_sigpending_pfn(kvm_pfn_t pfn)
{
return pfn == KVM_PFN_ERR_SIGPENDING;
}
/*
* error_noslot pfns indicate that the gfn can not be
* translated to pfn - it is not in slot or failed to
* translate it to pfn.
*/
static inline bool is_error_noslot_pfn(kvm_pfn_t pfn)
{
return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
}
/* noslot pfn indicates that the gfn is not in slot. */
static inline bool is_noslot_pfn(kvm_pfn_t pfn)
{
return pfn == KVM_PFN_NOSLOT;
}
/*
* architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390)
* provide own defines and kvm_is_error_hva
*/
#ifndef KVM_HVA_ERR_BAD
#define KVM_HVA_ERR_BAD (PAGE_OFFSET)
#define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE)
static inline bool kvm_is_error_hva(unsigned long addr)
{
return addr >= PAGE_OFFSET;
}
#endif
static inline bool kvm_is_error_gpa(gpa_t gpa)
{
return gpa == INVALID_GPA;
}
#define KVM_REQUEST_MASK GENMASK(7,0)
#define KVM_REQUEST_NO_WAKEUP BIT(8)
#define KVM_REQUEST_WAIT BIT(9)
#define KVM_REQUEST_NO_ACTION BIT(10)
/*
* Architecture-independent vcpu->requests bit members
* Bits 3-7 are reserved for more arch-independent bits.
*/
#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_UNBLOCK 2
#define KVM_REQ_DIRTY_RING_SOFT_FULL 3
#define KVM_REQUEST_ARCH_BASE 8
/*
* KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to
* OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick"
* in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing
* on. A kick only guarantees that the vCPU is on its way out, e.g. a previous
* kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no
* guarantee the vCPU received an IPI and has actually exited guest mode.
*/
#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \
(unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \
})
#define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0)
bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
unsigned long *vcpu_bitmap);
bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
#define KVM_USERSPACE_IRQ_SOURCE_ID 0
#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1
extern struct mutex kvm_lock;
extern struct list_head vm_list;
struct kvm_io_range {
gpa_t addr;
int len;
struct kvm_io_device *dev;
};
#define NR_IOBUS_DEVS 1000
struct kvm_io_bus {
int dev_count;
int ioeventfd_count;
struct kvm_io_range range[];
};
enum kvm_bus {
KVM_MMIO_BUS,
KVM_PIO_BUS,
KVM_VIRTIO_CCW_NOTIFY_BUS,
KVM_FAST_MMIO_BUS,
KVM_IOCSR_BUS,
KVM_NR_BUSES
};
int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, const void *val);
int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
gpa_t addr, int len, const void *val, long cookie);
int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val);
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, struct kvm_io_device *dev);
int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
struct kvm_io_device *dev);
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr);
#ifdef CONFIG_KVM_ASYNC_PF
struct kvm_async_pf {
struct work_struct work;
struct list_head link;
struct list_head queue;
struct kvm_vcpu *vcpu;
gpa_t cr2_or_gpa;
unsigned long addr;
struct kvm_arch_async_pf arch;
bool wakeup_all;
bool notpresent_injected;
};
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
unsigned long hva, struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
union kvm_mmu_notifier_arg {
unsigned long attributes;
};
enum kvm_gfn_range_filter {
KVM_FILTER_SHARED = BIT(0),
KVM_FILTER_PRIVATE = BIT(1),
};
struct kvm_gfn_range {
struct kvm_memory_slot *slot;
gfn_t start;
gfn_t end;
union kvm_mmu_notifier_arg arg;
enum kvm_gfn_range_filter attr_filter;
bool may_block;
bool lockless;
};
bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
#endif
enum {
OUTSIDE_GUEST_MODE,
IN_GUEST_MODE,
EXITING_GUEST_MODE,
READING_SHADOW_PAGE_TABLES,
};
struct kvm_host_map {
/*
* Only valid if the 'pfn' is managed by the host kernel (i.e. There is
* a 'struct page' for it. When using mem= kernel parameter some memory
* can be used as guest memory but they are not managed by host
* kernel).
*/
struct page *pinned_page;
struct page *page;
void *hva;
kvm_pfn_t pfn;
kvm_pfn_t gfn;
bool writable;
};
/*
* Used to check if the mapping is valid or not. Never use 'kvm_host_map'
* directly to check for that.
*/
static inline bool kvm_vcpu_mapped(struct kvm_host_map *map)
{
return !!map->hva;
}
static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop)
{
return single_task_running() && !need_resched() && ktime_before(cur, stop);
}
/*
* Sometimes a large or cross-page mmio needs to be broken up into separate
* exits for userspace servicing.
*/
struct kvm_mmio_fragment {
gpa_t gpa;
void *data;
unsigned len;
};
struct kvm_vcpu {
struct kvm *kvm;
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier preempt_notifier;
#endif
int cpu;
int vcpu_id; /* id given by userspace at creation */
int vcpu_idx; /* index into kvm->vcpu_array */
int ____srcu_idx; /* Don't use this directly. You've been warned. */
#ifdef CONFIG_PROVE_RCU
int srcu_depth;
#endif
int mode;
u64 requests;
unsigned long guest_debug;
struct mutex mutex;
struct kvm_run *run;
#ifndef __KVM_HAVE_ARCH_WQP
struct rcuwait wait;
#endif
struct pid *pid;
rwlock_t pid_lock;
int sigset_active;
sigset_t sigset;
unsigned int halt_poll_ns;
bool valid_wakeup;
#ifdef CONFIG_HAS_IOMEM
int mmio_needed;
int mmio_read_completed;
int mmio_is_write;
int mmio_cur_fragment;
int mmio_nr_fragments;
struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
#endif
#ifdef CONFIG_KVM_ASYNC_PF
struct {
u32 queued;
struct list_head queue;
struct list_head done;
spinlock_t lock;
} async_pf;
#endif
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
/*
* Cpu relax intercept or pause loop exit optimization
* in_spin_loop: set when a vcpu does a pause loop exit
* or cpu relax intercepted.
* dy_eligible: indicates whether vcpu is eligible for directed yield.
*/
struct {
bool in_spin_loop;
bool dy_eligible;
} spin_loop;
#endif
bool wants_to_run;
bool preempted;
bool ready;
bool scheduled_out;
struct kvm_vcpu_arch arch;
struct kvm_vcpu_stat stat;
char stats_id[KVM_STATS_NAME_SIZE];
struct kvm_dirty_ring dirty_ring;
/*
* The most recently used memslot by this vCPU and the slots generation
* for which it is valid.
* No wraparound protection is needed since generations won't overflow in
* thousands of years, even assuming 1M memslot operations per second.
*/
struct kvm_memory_slot *last_used_slot;
u64 last_used_slot_gen;
};
/*
* Start accounting time towards a guest.
* Must be called before entering guest context.
*/
static __always_inline void guest_timing_enter_irqoff(void)
{
/*
* This is running in ioctl context so its safe to assume that it's the
* stime pending cputime to flush.
*/
instrumentation_begin();
vtime_account_guest_enter();
instrumentation_end();
}
/*
* Enter guest context and enter an RCU extended quiescent state.
*
* Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
* unsafe to use any code which may directly or indirectly use RCU, tracing
* (including IRQ flag tracing), or lockdep. All code in this period must be
* non-instrumentable.
*/
static __always_inline void guest_context_enter_irqoff(void)
{
/*
* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
* is very similar to exiting to userspace from rcu point of view. In
* addition CPU may stay in a guest mode for quite a long time (up to
* one time slice). Lets treat guest mode as quiescent state, just like
* we do with user-mode execution.
*/
if (!context_tracking_guest_enter()) {
instrumentation_begin();
rcu_virt_note_context_switch();
instrumentation_end();
}
}
/*
* Deprecated. Architectures should move to guest_timing_enter_irqoff() and
* guest_state_enter_irqoff().
*/
static __always_inline void guest_enter_irqoff(void)
{
guest_timing_enter_irqoff();
guest_context_enter_irqoff();
}
/**
* guest_state_enter_irqoff - Fixup state when entering a guest
*
* Entry to a guest will enable interrupts, but the kernel state is interrupts
* disabled when this is invoked. Also tell RCU about it.
*
* 1) Trace interrupts on state
* 2) Invoke context tracking if enabled to adjust RCU state
* 3) Tell lockdep that interrupts are enabled
*
* Invoked from architecture specific code before entering a guest.
* Must be called with interrupts disabled and the caller must be
* non-instrumentable.
* The caller has to invoke guest_timing_enter_irqoff() before this.
*
* Note: this is analogous to exit_to_user_mode().
*/
static __always_inline void guest_state_enter_irqoff(void)
{
instrumentation_begin();
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
instrumentation_end();
guest_context_enter_irqoff();
lockdep_hardirqs_on(CALLER_ADDR0);
}
/*
* Exit guest context and exit an RCU extended quiescent state.
*
* Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
* unsafe to use any code which may directly or indirectly use RCU, tracing
* (including IRQ flag tracing), or lockdep. All code in this period must be
* non-instrumentable.
*/
static __always_inline void guest_context_exit_irqoff(void)
{
/*
* Guest mode is treated as a quiescent state, see
* guest_context_enter_irqoff() for more details.
*/
if (!context_tracking_guest_exit()) {
instrumentation_begin();
rcu_virt_note_context_switch();
instrumentation_end();
}
}
/*
* Stop accounting time towards a guest.
* Must be called after exiting guest context.
*/
static __always_inline void guest_timing_exit_irqoff(void)
{
instrumentation_begin();
/* Flush the guest cputime we spent on the guest */
vtime_account_guest_exit();
instrumentation_end();
}
/*
* Deprecated. Architectures should move to guest_state_exit_irqoff() and
* guest_timing_exit_irqoff().
*/
static __always_inline void guest_exit_irqoff(void)
{
guest_context_exit_irqoff();
guest_timing_exit_irqoff();
}
static inline void guest_exit(void)
{
unsigned long flags;
local_irq_save(flags);
guest_exit_irqoff();
local_irq_restore(flags);
}
/**
* guest_state_exit_irqoff - Establish state when returning from guest mode
*
* Entry from a guest disables interrupts, but guest mode is traced as
* interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
*
* 1) Tell lockdep that interrupts are disabled
* 2) Invoke context tracking if enabled to reactivate RCU
* 3) Trace interrupts off state
*
* Invoked from architecture specific code after exiting a guest.
* Must be invoked with interrupts disabled and the caller must be
* non-instrumentable.
* The caller has to invoke guest_timing_exit_irqoff() after this.
*
* Note: this is analogous to enter_from_user_mode().
*/
static __always_inline void guest_state_exit_irqoff(void)
{
lockdep_hardirqs_off(CALLER_ADDR0);
guest_context_exit_irqoff();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
}
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
/*
* The memory barrier ensures a previous write to vcpu->requests cannot
* be reordered with the read of vcpu->mode. It pairs with the general
* memory barrier following the write of vcpu->mode in VCPU RUN.
*/
smp_mb__before_atomic();
return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
}
/*
* Some of the bitops functions do not support too long bitmaps.
* This number must be determined not to exceed such limits.
*/
#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
/*
* Since at idle each memslot belongs to two memslot sets it has to contain
* two embedded nodes for each data structure that it forms a part of.
*
* Two memslot sets (one active and one inactive) are necessary so the VM
* continues to run on one memslot set while the other is being modified.
*
* These two memslot sets normally point to the same set of memslots.
* They can, however, be desynchronized when performing a memslot management
* operation by replacing the memslot to be modified by its copy.
* After the operation is complete, both memslot sets once again point to
* the same, common set of memslot data.
*
* The memslots themselves are independent of each other so they can be
* individually added or deleted.
*/
struct kvm_memory_slot {
struct hlist_node id_node[2];
struct interval_tree_node hva_node[2];
struct rb_node gfn_node[2];
gfn_t base_gfn;
unsigned long npages;
unsigned long *dirty_bitmap;
struct kvm_arch_memory_slot arch;
unsigned long userspace_addr;
u32 flags;
short id;
u16 as_id;
#ifdef CONFIG_KVM_PRIVATE_MEM
struct {
/*
* Writes protected by kvm->slots_lock. Acquiring a
* reference via kvm_gmem_get_file() is protected by
* either kvm->slots_lock or kvm->srcu.
*/
struct file *file;
pgoff_t pgoff;
} gmem;
#endif
};
static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
{
return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
}
static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
{
return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
}
static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
{
return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
}
static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot)
{
unsigned long len = kvm_dirty_bitmap_bytes(memslot);
return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap);
}
#ifndef KVM_DIRTY_LOG_MANUAL_CAPS
#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE
#endif
struct kvm_s390_adapter_int {
u64 ind_addr;
u64 summary_addr;
u64 ind_offset;
u32 summary_offset;
u32 adapter_id;
};
struct kvm_hv_sint {
u32 vcpu;
u32 sint;
};
struct kvm_xen_evtchn {
u32 port;
u32 vcpu_id;
int vcpu_idx;
u32 priority;
};
struct kvm_kernel_irq_routing_entry {
u32 gsi;
u32 type;
int (*set)(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status);
union {
struct {
unsigned irqchip;
unsigned pin;
} irqchip;
struct {
u32 address_lo;
u32 address_hi;
u32 data;
u32 flags;
u32 devid;
} msi;
struct kvm_s390_adapter_int adapter;
struct kvm_hv_sint hv_sint;
struct kvm_xen_evtchn xen_evtchn;
};
struct hlist_node link;
};
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
struct kvm_irq_routing_table {
int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
u32 nr_rt_entries;
/*
* Array indexed by gsi. Each entry contains list of irq chips
* the gsi is connected to.
*/
struct hlist_head map[] __counted_by(nr_rt_entries);
};
#endif
bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
#ifndef KVM_INTERNAL_MEM_SLOTS
#define KVM_INTERNAL_MEM_SLOTS 0
#endif
#define KVM_MEM_SLOTS_NUM SHRT_MAX
#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
#if KVM_MAX_NR_ADDRESS_SPACES == 1
static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
{
return KVM_MAX_NR_ADDRESS_SPACES;
}
static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
{
return 0;
}
#endif
/*
* Arch code must define kvm_arch_has_private_mem if support for private memory
* is enabled.
*/
#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
{
return false;
}
#endif
#ifndef kvm_arch_has_readonly_mem
static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
{
return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM);
}
#endif
struct kvm_memslots {
u64 generation;
atomic_long_t last_used_slot;
struct rb_root_cached hva_tree;
struct rb_root gfn_tree;
/*
* The mapping table from slot id to memslot.
*
* 7-bit bucket count matches the size of the old id to index array for
* 512 slots, while giving good performance with this slot count.
* Higher bucket counts bring only small performance improvements but
* always result in higher memory usage (even for lower memslot counts).
*/
DECLARE_HASHTABLE(id_hash, 7);
int node_idx;
};
struct kvm {
#ifdef KVM_HAVE_MMU_RWLOCK
rwlock_t mmu_lock;
#else
spinlock_t mmu_lock;
#endif /* KVM_HAVE_MMU_RWLOCK */
struct mutex slots_lock;
/*
* Protects the arch-specific fields of struct kvm_memory_slots in
* use by the VM. To be used under the slots_lock (above) or in a
* kvm->srcu critical section where acquiring the slots_lock would
* lead to deadlock with the synchronize_srcu in
* kvm_swap_active_memslots().
*/
struct mutex slots_arch_lock;
struct mm_struct *mm; /* userspace tied to this vm */
unsigned long nr_memslot_pages;
/* The two memslot sets - active and inactive (per address space) */
struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
/* The current active memslot set for each address space */
struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
struct xarray vcpu_array;
/*
* Protected by slots_lock, but can be read outside if an
* incorrect answer is acceptable.
*/
atomic_t nr_memslots_dirty_logging;
/* Used to wait for completion of MMU notifiers. */
spinlock_t mn_invalidate_lock;
unsigned long mn_active_invalidate_count;
struct rcuwait mn_memslots_update_rcuwait;
/* For management / invalidation of gfn_to_pfn_caches */
spinlock_t gpc_lock;
struct list_head gpc_list;
/*
* created_vcpus is protected by kvm->lock, and is incremented
* at the beginning of KVM_CREATE_VCPU. online_vcpus is only
* incremented after storing the kvm_vcpu pointer in vcpus,
* and is accessed atomically.
*/
atomic_t online_vcpus;
int max_vcpus;
int created_vcpus;
int last_boosted_vcpu;
struct list_head vm_list;
struct mutex lock;
struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
#ifdef CONFIG_HAVE_KVM_IRQCHIP
struct {
spinlock_t lock;
struct list_head items;
/* resampler_list update side is protected by resampler_lock. */
struct list_head resampler_list;
struct mutex resampler_lock;
} irqfds;
#endif
struct list_head ioeventfds;
struct kvm_vm_stat stat;
struct kvm_arch arch;
refcount_t users_count;
#ifdef CONFIG_KVM_MMIO
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
spinlock_t ring_lock;
struct list_head coalesced_zones;
#endif
struct mutex irq_lock;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
/*
* Update side is protected by irq_lock.
*/
struct kvm_irq_routing_table __rcu *irq_routing;
struct hlist_head irq_ack_notifier_list;
#endif
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
struct mmu_notifier mmu_notifier;
unsigned long mmu_invalidate_seq;
long mmu_invalidate_in_progress;
gfn_t mmu_invalidate_range_start;
gfn_t mmu_invalidate_range_end;
#endif
struct list_head devices;
u64 manual_dirty_log_protect;
struct dentry *debugfs_dentry;
struct kvm_stat_data **debugfs_stat_data;
struct srcu_struct srcu;
struct srcu_struct irq_srcu;
pid_t userspace_pid;
bool override_halt_poll_ns;
unsigned int max_halt_poll_ns;
u32 dirty_ring_size;
bool dirty_ring_with_bitmap;
bool vm_bugged;
bool vm_dead;
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#endif
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
/* Protected by slots_locks (for writes) and RCU (for reads) */
struct xarray mem_attr_array;
#endif
char stats_id[KVM_STATS_NAME_SIZE];
};
#define kvm_err(fmt, ...) \
pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_info(fmt, ...) \
pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug(fmt, ...) \
pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__)
#define kvm_debug_ratelimited(fmt, ...) \
pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \
## __VA_ARGS__)
#define kvm_pr_unimpl(fmt, ...) \
pr_err_ratelimited("kvm [%i]: " fmt, \
task_tgid_nr(current), ## __VA_ARGS__)
/* The guest did something we don't support. */
#define vcpu_unimpl(vcpu, fmt, ...) \
kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \
(vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__)
#define vcpu_debug(vcpu, fmt, ...) \
kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
#define vcpu_debug_ratelimited(vcpu, fmt, ...) \
kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \
## __VA_ARGS__)
#define vcpu_err(vcpu, fmt, ...) \
kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
static inline void kvm_vm_dead(struct kvm *kvm)
{
kvm->vm_dead = true;
kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD);
}
static inline void kvm_vm_bugged(struct kvm *kvm)
{
kvm->vm_bugged = true;
kvm_vm_dead(kvm);
}
#define KVM_BUG(cond, kvm, fmt...) \
({ \
bool __ret = !!(cond); \
\
if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \
kvm_vm_bugged(kvm); \
unlikely(__ret); \
})
#define KVM_BUG_ON(cond, kvm) \
({ \
bool __ret = !!(cond); \
\
if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \
kvm_vm_bugged(kvm); \
unlikely(__ret); \
})
/*
* Note, "data corruption" refers to corruption of host kernel data structures,
* not guest data. Guest data corruption, suspected or confirmed, that is tied
* and contained to a single VM should *never* BUG() and potentially panic the
* host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure
* is corrupted and that corruption can have a cascading effect to other parts
* of the hosts and/or to other VMs.
*/
#define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) \
({ \
bool __ret = !!(cond); \
\
if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) \
BUG_ON(__ret); \
else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \
kvm_vm_bugged(kvm); \
unlikely(__ret); \
})
static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_PROVE_RCU
WARN_ONCE(vcpu->srcu_depth++,
"KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1);
#endif
vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
}
static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu)
{
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx);
#ifdef CONFIG_PROVE_RCU
WARN_ONCE(--vcpu->srcu_depth,
"KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth);
#endif
}
static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
{
return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
}
static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
{
return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
}
static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
{
int num_vcpus = atomic_read(&kvm->online_vcpus);
/*
* Explicitly verify the target vCPU is online, as the anti-speculation
* logic only limits the CPU's ability to speculate, e.g. given a "bad"
* index, clamping the index to 0 would return vCPU0, not NULL.
*/
if (i >= num_vcpus)
return NULL;
i = array_index_nospec(i, num_vcpus);
/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */
smp_rmb();
return xa_load(&kvm->vcpu_array, i);
}
#define kvm_for_each_vcpu(idx, vcpup, kvm) \
if (atomic_read(&kvm->online_vcpus)) \
xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \
(atomic_read(&kvm->online_vcpus) - 1))
static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
{
struct kvm_vcpu *vcpu = NULL;
unsigned long i;
if (id < 0)
return NULL;
if (id < KVM_MAX_VCPUS) vcpu = kvm_get_vcpu(kvm, id); if (vcpu && vcpu->vcpu_id == id)
return vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) if (vcpu->vcpu_id == id)
return vcpu;
return NULL;
}
void kvm_destroy_vcpus(struct kvm *kvm);
void vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);
#ifdef __KVM_HAVE_IOAPIC
void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
void kvm_arch_post_irq_routing_update(struct kvm *kvm);
#else
static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
{
}
static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
{
}
#endif
#ifdef CONFIG_HAVE_KVM_IRQCHIP
int kvm_irqfd_init(void);
void kvm_irqfd_exit(void);
#else
static inline int kvm_irqfd_init(void)
{
return 0;
}
static inline void kvm_irqfd_exit(void)
{
}
#endif
int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module);
void kvm_exit(void);
void kvm_get_kvm(struct kvm *kvm);
bool kvm_get_kvm_safe(struct kvm *kvm);
void kvm_put_kvm(struct kvm *kvm);
bool file_is_kvm(struct file *file);
void kvm_put_kvm_no_destroy(struct kvm *kvm);
static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
}
static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
{ return __kvm_memslots(kvm, 0);
}
static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu)
{
int as_id = kvm_arch_vcpu_memslots_id(vcpu);
return __kvm_memslots(vcpu->kvm, as_id);
}
static inline bool kvm_memslots_empty(struct kvm_memslots *slots)
{
return RB_EMPTY_ROOT(&slots->gfn_tree);
}
bool kvm_are_all_memslots_empty(struct kvm *kvm);
#define kvm_for_each_memslot(memslot, bkt, slots) \
hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \
if (WARN_ON_ONCE(!memslot->npages)) { \
} else
static inline
struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id)
{
struct kvm_memory_slot *slot;
int idx = slots->node_idx;
hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { if (slot->id == id)
return slot;
}
return NULL;
}
/* Iterator used for walking memslots that overlap a gfn range. */
struct kvm_memslot_iter {
struct kvm_memslots *slots;
struct rb_node *node;
struct kvm_memory_slot *slot;
};
static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter)
{
iter->node = rb_next(iter->node);
if (!iter->node)
return;
iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]);
}
static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter,
struct kvm_memslots *slots,
gfn_t start)
{
int idx = slots->node_idx;
struct rb_node *tmp;
struct kvm_memory_slot *slot;
iter->slots = slots;
/*
* Find the so called "upper bound" of a key - the first node that has
* its key strictly greater than the searched one (the start gfn in our case).
*/
iter->node = NULL;
for (tmp = slots->gfn_tree.rb_node; tmp; ) {
slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]);
if (start < slot->base_gfn) {
iter->node = tmp;
tmp = tmp->rb_left;
} else {
tmp = tmp->rb_right;
}
}
/*
* Find the slot with the lowest gfn that can possibly intersect with
* the range, so we'll ideally have slot start <= range start
*/
if (iter->node) {
/*
* A NULL previous node means that the very first slot
* already has a higher start gfn.
* In this case slot start > range start.
*/
tmp = rb_prev(iter->node);
if (tmp)
iter->node = tmp;
} else {
/* a NULL node below means no slots */
iter->node = rb_last(&slots->gfn_tree);
}
if (iter->node) { iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]);
/*
* It is possible in the slot start < range start case that the
* found slot ends before or at range start (slot end <= range start)
* and so it does not overlap the requested range.
*
* In such non-overlapping case the next slot (if it exists) will
* already have slot start > range start, otherwise the logic above
* would have found it instead of the current slot.
*/
if (iter->slot->base_gfn + iter->slot->npages <= start) kvm_memslot_iter_next(iter);
}
}
static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end)
{
if (!iter->node)
return false;
/*
* If this slot starts beyond or at the end of the range so does
* every next one
*/
return iter->slot->base_gfn < end;
}
/* Iterate over each memslot at least partially intersecting [start, end) range */
#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \
for (kvm_memslot_iter_start(iter, slots, start); \
kvm_memslot_iter_is_valid(iter, end); \
kvm_memslot_iter_next(iter))
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
/*
* KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
* - create a new memory slot
* - delete an existing memory slot
* - modify an existing memory slot
* -- move it in the guest physical memory space
* -- just change its flags
*
* Since flags can be changed by some of these operations, the following
* differentiation is the best we can do for kvm_set_memory_region():
*/
enum kvm_mr_change {
KVM_MR_CREATE,
KVM_MR_DELETE,
KVM_MR_MOVE,
KVM_MR_FLAGS_ONLY,
};
int kvm_set_internal_memslot(struct kvm *kvm,
const struct kvm_userspace_memory_region2 *mem);
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change);
void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change);
/* flush all memory translations */
void kvm_arch_flush_shadow_all(struct kvm *kvm);
/* flush memory translations pointing to 'slot' */
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot);
int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn,
struct page **pages, int nr_pages);
struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write);
static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
return __gfn_to_page(kvm, gfn, true);
}
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
bool *writable);
static inline void kvm_release_page_unused(struct page *page)
{
if (!page)
return;
put_page(page);
}
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page,
bool unused, bool dirty)
{
lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); if (!page)
return;
/*
* If the page that KVM got from the *primary MMU* is writable, and KVM
* installed or reused a SPTE, mark the page/folio dirty. Note, this
* may mark a folio dirty even if KVM created a read-only SPTE, e.g. if
* the GFN is write-protected. Folios can't be safely marked dirty
* outside of mmu_lock as doing so could race with writeback on the
* folio. As a result, KVM can't mark folios dirty in the fast page
* fault handler, and so KVM must (somewhat) speculatively mark the
* folio dirty if KVM could locklessly make the SPTE writable.
*/
if (unused)
kvm_release_page_unused(page);
else if (dirty)
kvm_release_page_dirty(page);
else
kvm_release_page_clean(page);
}
kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn,
unsigned int foll, bool *writable,
struct page **refcounted_page);
static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
bool write, bool *writable,
struct page **refcounted_page)
{
return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn,
write ? FOLL_WRITE : 0, writable, refcounted_page);
}
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len);
int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len);
int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
int offset, int len);
int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
unsigned long len);
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len);
int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len);
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
gpa_t gpa, unsigned long len);
#define __kvm_get_guest(kvm, gfn, offset, v) \
({ \
unsigned long __addr = gfn_to_hva(kvm, gfn); \
typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \
int __ret = -EFAULT; \
\
if (!kvm_is_error_hva(__addr)) \
__ret = get_user(v, __uaddr); \
__ret; \
})
#define kvm_get_guest(kvm, gpa, v) \
({ \
gpa_t __gpa = gpa; \
struct kvm *__kvm = kvm; \
\
__kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \
offset_in_page(__gpa), v); \
})
#define __kvm_put_guest(kvm, gfn, offset, v) \
({ \
unsigned long __addr = gfn_to_hva(kvm, gfn); \
typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \
int __ret = -EFAULT; \
\
if (!kvm_is_error_hva(__addr)) \
__ret = put_user(v, __uaddr); \
if (!__ret) \
mark_page_dirty(kvm, gfn); \
__ret; \
})
#define kvm_put_guest(kvm, gpa, v) \
({ \
gpa_t __gpa = gpa; \
struct kvm *__kvm = kvm; \
\
__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \
offset_in_page(__gpa), v); \
})
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map,
bool writable);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map);
static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa,
struct kvm_host_map *map)
{
return __kvm_vcpu_map(vcpu, gpa, map, true);
}
static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa,
struct kvm_host_map *map)
{
return __kvm_vcpu_map(vcpu, gpa, map, false);
}
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
int len);
int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
unsigned long len);
int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data,
unsigned long len);
int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data,
int offset, int len);
int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
unsigned long len);
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
/**
* kvm_gpc_init - initialize gfn_to_pfn_cache.
*
* @gpc: struct gfn_to_pfn_cache object.
* @kvm: pointer to kvm instance.
*
* This sets up a gfn_to_pfn_cache by initializing locks and assigning the
* immutable attributes. Note, the cache must be zero-allocated (or zeroed by
* the caller before init).
*/
void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm);
/**
* kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
* physical address.
*
* @gpc: struct gfn_to_pfn_cache object.
* @gpa: guest physical address to map.
* @len: sanity check; the range being access must fit a single page.
*
* @return: 0 for success.
* -EINVAL for a mapping which would cross a page boundary.
* -EFAULT for an untranslatable guest physical address.
*
* This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for
* invalidations to be processed. Callers are required to use kvm_gpc_check()
* to ensure that the cache is valid before accessing the target page.
*/
int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len);
/**
* kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA.
*
* @gpc: struct gfn_to_pfn_cache object.
* @hva: userspace virtual address to map.
* @len: sanity check; the range being access must fit a single page.
*
* @return: 0 for success.
* -EINVAL for a mapping which would cross a page boundary.
* -EFAULT for an untranslatable guest physical address.
*
* The semantics of this function are the same as those of kvm_gpc_activate(). It
* merely bypasses a layer of address translation.
*/
int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len);
/**
* kvm_gpc_check - check validity of a gfn_to_pfn_cache.
*
* @gpc: struct gfn_to_pfn_cache object.
* @len: sanity check; the range being access must fit a single page.
*
* @return: %true if the cache is still valid and the address matches.
* %false if the cache is not valid.
*
* Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock
* while calling this function, and then continue to hold the lock until the
* access is complete.
*
* Callers in IN_GUEST_MODE may do so without locking, although they should
* still hold a read lock on kvm->scru for the memslot checks.
*/
bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len);
/**
* kvm_gpc_refresh - update a previously initialized cache.
*
* @gpc: struct gfn_to_pfn_cache object.
* @len: sanity check; the range being access must fit a single page.
*
* @return: 0 for success.
* -EINVAL for a mapping which would cross a page boundary.
* -EFAULT for an untranslatable guest physical address.
*
* This will attempt to refresh a gfn_to_pfn_cache. Note that a successful
* return from this function does not mean the page can be immediately
* accessed because it may have raced with an invalidation. Callers must
* still lock and check the cache status, as this function does not return
* with the lock still held to permit access.
*/
int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len);
/**
* kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache.
*
* @gpc: struct gfn_to_pfn_cache object.
*
* This removes a cache from the VM's list to be processed on MMU notifier
* invocation.
*/
void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc);
static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc)
{
return gpc->active && !kvm_is_error_gpa(gpc->gpa);
}
static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc)
{
return gpc->active && kvm_is_error_gpa(gpc->gpa);
}
void kvm_sigset_activate(struct kvm_vcpu *vcpu);
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
void kvm_vcpu_halt(struct kvm_vcpu *vcpu);
bool kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
int kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
void kvm_flush_remote_tlbs(struct kvm *kvm);
void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min);
int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc);
void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
#endif
void kvm_mmu_invalidate_begin(struct kvm *kvm);
void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
void kvm_mmu_invalidate_end(struct kvm *kvm);
bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset,
unsigned long mask);
void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
int *is_dirty, struct kvm_memory_slot **memslot);
#endif
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
bool line_status);
int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap);
int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg);
long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg);
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
struct kvm_translation *tr);
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
struct kvm_guest_debug *dbg);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id);
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state);
#endif
#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry);
#else
static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {}
#endif
#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
/*
* kvm_arch_{enable,disable}_virtualization() are called on one CPU, under
* kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of
* kvm_usage_count, i.e. at the beginning of the generic hardware enabling
* sequence, and at the end of the generic hardware disabling sequence.
*/
void kvm_arch_enable_virtualization(void);
void kvm_arch_disable_virtualization(void);
/*
* kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to
* do the actual twiddling of hardware bits. The hooks are called on all
* online CPUs when KVM enables/disabled virtualization, and on a single CPU
* when that CPU is onlined/offlined (including for Resume/Suspend).
*/
int kvm_arch_enable_virtualization_cpu(void);
void kvm_arch_disable_virtualization_cpu(void);
#endif
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
void kvm_arch_pre_destroy_vm(struct kvm *kvm);
void kvm_arch_create_vm_debugfs(struct kvm *kvm);
#ifndef __KVM_HAVE_ARCH_VM_ALLOC
/*
* All architectures that want to use vzalloc currently also
* need their own kvm_arch_alloc_vm implementation.
*/
static inline struct kvm *kvm_arch_alloc_vm(void)
{
return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT);
}
#endif
static inline void __kvm_arch_free_vm(struct kvm *kvm)
{
kvfree(kvm);
}
#ifndef __KVM_HAVE_ARCH_VM_FREE
static inline void kvm_arch_free_vm(struct kvm *kvm)
{
__kvm_arch_free_vm(kvm);
}
#endif
#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
return -ENOTSUPP;
}
#else
int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
#endif
#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
gfn_t gfn, u64 nr_pages)
{
return -EOPNOTSUPP;
}
#else
int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
#endif
#ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
bool kvm_arch_has_noncoherent_dma(struct kvm *kvm);
#else
static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
{
}
static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
{
}
static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
{
return false;
}
#endif
#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
void kvm_arch_start_assignment(struct kvm *kvm);
void kvm_arch_end_assignment(struct kvm *kvm);
bool kvm_arch_has_assigned_device(struct kvm *kvm);
#else
static inline void kvm_arch_start_assignment(struct kvm *kvm)
{
}
static inline void kvm_arch_end_assignment(struct kvm *kvm)
{
}
static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
{
return false;
}
#endif
static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_WQP
return vcpu->arch.waitp;
#else
return &vcpu->wait;
#endif
}
/*
* Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns
* true if the vCPU was blocking and was awakened, false otherwise.
*/
static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
}
static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu)
{
return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu));
}
#ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED
/*
* returns true if the virtual interrupt controller is initialized and
* ready to accept virtual IRQ. On some architectures the virtual interrupt
* controller is dynamically instantiated and this is not always true.
*/
bool kvm_arch_intc_initialized(struct kvm *kvm);
#else
static inline bool kvm_arch_intc_initialized(struct kvm *kvm)
{
return true;
}
#endif
#ifdef CONFIG_GUEST_PERF_EVENTS
unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu);
void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void));
void kvm_unregister_perf_callbacks(void);
#else
static inline void kvm_register_perf_callbacks(void *ign) {}
static inline void kvm_unregister_perf_callbacks(void) {}
#endif /* CONFIG_GUEST_PERF_EVENTS */
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
struct kvm_irq_ack_notifier {
struct hlist_node link;
unsigned gsi;
void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
};
int kvm_irq_map_gsi(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *entries, int gsi);
int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
bool line_status);
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
int irq_source_id, int level, bool line_status);
int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id,
int level, bool line_status);
bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_notify_acked_gsi(struct kvm *kvm, int gsi);
void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
void kvm_register_irq_ack_notifier(struct kvm *kvm,
struct kvm_irq_ack_notifier *kian);
void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
struct kvm_irq_ack_notifier *kian);
int kvm_request_irq_source_id(struct kvm *kvm);
void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
/*
* Returns a pointer to the memslot if it contains gfn.
* Otherwise returns NULL.
*/
static inline struct kvm_memory_slot *
try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
{
if (!slot)
return NULL;
if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages)
return slot;
else
return NULL;
}
/*
* Returns a pointer to the memslot that contains gfn. Otherwise returns NULL.
*
* With "approx" set returns the memslot also when the address falls
* in a hole. In that case one of the memslots bordering the hole is
* returned.
*/
static inline struct kvm_memory_slot *
search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx)
{
struct kvm_memory_slot *slot;
struct rb_node *node;
int idx = slots->node_idx;
slot = NULL;
for (node = slots->gfn_tree.rb_node; node; ) {
slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]);
if (gfn >= slot->base_gfn) { if (gfn < slot->base_gfn + slot->npages)
return slot;
node = node->rb_right;
} else
node = node->rb_left;
}
return approx ? slot : NULL;
}
static inline struct kvm_memory_slot *
____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx)
{
struct kvm_memory_slot *slot;
slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot);
slot = try_get_memslot(slot, gfn);
if (slot)
return slot;
slot = search_memslots(slots, gfn, approx); if (slot) { atomic_long_set(&slots->last_used_slot, (unsigned long)slot);
return slot;
}
return NULL;
}
/*
* __gfn_to_memslot() and its descendants are here to allow arch code to inline
* the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline
* because that would bloat other code too much.
*/
static inline struct kvm_memory_slot *
__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
{
return ____gfn_to_memslot(slots, gfn, false);
}
static inline unsigned long
__gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
/*
* The index was checked originally in search_memslots. To avoid
* that a malicious guest builds a Spectre gadget out of e.g. page
* table walks, do not let the processor speculate loads outside
* the guest's registered memslots.
*/
unsigned long offset = gfn - slot->base_gfn;
offset = array_index_nospec(offset, slot->npages);
return slot->userspace_addr + offset * PAGE_SIZE;
}
static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_memslot(kvm, gfn)->id;
}
static inline gfn_t
hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
{
gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
return slot->base_gfn + gfn_offset;
}
static inline gpa_t gfn_to_gpa(gfn_t gfn)
{
return (gpa_t)gfn << PAGE_SHIFT;
}
static inline gfn_t gpa_to_gfn(gpa_t gpa)
{
return (gfn_t)(gpa >> PAGE_SHIFT);
}
static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn)
{
return (hpa_t)pfn << PAGE_SHIFT;
}
static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa)
{
unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
return !kvm_is_error_hva(hva);
}
static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc)
{
lockdep_assert_held(&gpc->lock);
if (!gpc->memslot)
return;
mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa));
}
enum kvm_stat_kind {
KVM_STAT_VM,
KVM_STAT_VCPU,
};
struct kvm_stat_data {
struct kvm *kvm;
const struct _kvm_stats_desc *desc;
enum kvm_stat_kind kind;
};
struct _kvm_stats_desc {
struct kvm_stats_desc desc;
char name[KVM_STATS_NAME_SIZE];
};
#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \
.flags = type | unit | base | \
BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \
BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \
BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \
.exponent = exp, \
.size = sz, \
.bucket_size = bsz
#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vm_stat, generic.stat) \
}, \
.name = #stat, \
}
#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
}, \
.name = #stat, \
}
#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vm_stat, stat) \
}, \
.name = #stat, \
}
#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \
{ \
{ \
STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \
.offset = offsetof(struct kvm_vcpu_stat, stat) \
}, \
.name = #stat, \
}
/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
#define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \
SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \
unit, base, exponent, 1, 0)
#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \
unit, base, exponent, 1, 0)
#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \
unit, base, exponent, 1, 0)
#define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \
unit, base, exponent, sz, bsz)
#define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \
STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \
unit, base, exponent, sz, 0)
/* Cumulative counter, read/write */
#define STATS_DESC_COUNTER(SCOPE, name) \
STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Instantaneous counter, read only */
#define STATS_DESC_ICOUNTER(SCOPE, name) \
STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Peak counter, read/write */
#define STATS_DESC_PCOUNTER(SCOPE, name) \
STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \
KVM_STATS_BASE_POW10, 0)
/* Instantaneous boolean value, read only */
#define STATS_DESC_IBOOLEAN(SCOPE, name) \
STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \
KVM_STATS_BASE_POW10, 0)
/* Peak (sticky) boolean value, read/write */
#define STATS_DESC_PBOOLEAN(SCOPE, name) \
STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \
KVM_STATS_BASE_POW10, 0)
/* Cumulative time in nanosecond */
#define STATS_DESC_TIME_NSEC(SCOPE, name) \
STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9)
/* Linear histogram for time in nanosecond */
#define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \
STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9, sz, bsz)
/* Logarithmic histogram for time in nanosecond */
#define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \
STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \
KVM_STATS_BASE_POW10, -9, sz)
#define KVM_GENERIC_VM_STATS() \
STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \
STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests)
#define KVM_GENERIC_VCPU_STATS() \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \
STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \
STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \
HALT_POLL_HIST_COUNT), \
STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
const struct _kvm_stats_desc *desc,
void *stats, size_t size_stats,
char __user *user_buffer, size_t size, loff_t *offset);
/**
* kvm_stats_linear_hist_update() - Update bucket value for linear histogram
* statistics data.
*
* @data: start address of the stats data
* @size: the number of bucket of the stats data
* @value: the new value used to update the linear histogram's bucket
* @bucket_size: the size (width) of a bucket
*/
static inline void kvm_stats_linear_hist_update(u64 *data, size_t size,
u64 value, size_t bucket_size)
{
size_t index = div64_u64(value, bucket_size);
index = min(index, size - 1);
++data[index];
}
/**
* kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram
* statistics data.
*
* @data: start address of the stats data
* @size: the number of bucket of the stats data
* @value: the new value used to update the logarithmic histogram's bucket
*/
static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
{
size_t index = fls64(value);
index = min(index, size - 1);
++data[index];
}
#define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \
kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize)
#define KVM_STATS_LOG_HIST_UPDATE(array, value) \
kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value)
extern const struct kvm_stats_header kvm_vm_stats_header;
extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
extern const struct kvm_stats_header kvm_vcpu_stats_header;
extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
{
if (unlikely(kvm->mmu_invalidate_in_progress))
return 1;
/*
* Ensure the read of mmu_invalidate_in_progress happens before
* the read of mmu_invalidate_seq. This interacts with the
* smp_wmb() in mmu_notifier_invalidate_range_end to make sure
* that the caller either sees the old (non-zero) value of
* mmu_invalidate_in_progress or the new (incremented) value of
* mmu_invalidate_seq.
*
* PowerPC Book3s HV KVM calls this under a per-page lock rather
* than under kvm->mmu_lock, for scalability, so can't rely on
* kvm->mmu_lock to keep things ordered.
*/
smp_rmb();
if (kvm->mmu_invalidate_seq != mmu_seq)
return 1;
return 0;
}
static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
unsigned long mmu_seq,
gfn_t gfn)
{
lockdep_assert_held(&kvm->mmu_lock);
/*
* If mmu_invalidate_in_progress is non-zero, then the range maintained
* by kvm_mmu_notifier_invalidate_range_start contains all addresses
* that might be being invalidated. Note that it may include some false
* positives, due to shortcuts when handing concurrent invalidations.
*/
if (unlikely(kvm->mmu_invalidate_in_progress)) {
/*
* Dropping mmu_lock after bumping mmu_invalidate_in_progress
* but before updating the range is a KVM bug.
*/
if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
kvm->mmu_invalidate_range_end == INVALID_GPA))
return 1;
if (gfn >= kvm->mmu_invalidate_range_start &&
gfn < kvm->mmu_invalidate_range_end)
return 1;
}
if (kvm->mmu_invalidate_seq != mmu_seq)
return 1;
return 0;
}
/*
* This lockless version of the range-based retry check *must* be paired with a
* call to the locked version after acquiring mmu_lock, i.e. this is safe to
* use only as a pre-check to avoid contending mmu_lock. This version *will*
* get false negatives and false positives.
*/
static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
unsigned long mmu_seq,
gfn_t gfn)
{
/*
* Use READ_ONCE() to ensure the in-progress flag and sequence counter
* are always read from memory, e.g. so that checking for retry in a
* loop won't result in an infinite retry loop. Don't force loads for
* start+end, as the key to avoiding infinite retry loops is observing
* the 1=>0 transition of in-progress, i.e. getting false negatives
* due to stale start+end values is acceptable.
*/
if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
gfn >= kvm->mmu_invalidate_range_start &&
gfn < kvm->mmu_invalidate_range_end)
return true;
return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
}
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
const struct kvm_irq_routing_entry *entries,
unsigned nr,
unsigned flags);
int kvm_init_irq_routing(struct kvm *kvm);
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue);
void kvm_free_irq_routing(struct kvm *kvm);
#else
static inline void kvm_free_irq_routing(struct kvm *kvm) {}
static inline int kvm_init_irq_routing(struct kvm *kvm)
{
return 0;
}
#endif
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
void kvm_eventfd_init(struct kvm *kvm);
int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
#ifdef CONFIG_HAVE_KVM_IRQCHIP
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
bool kvm_notify_irqfd_resampler(struct kvm *kvm,
unsigned int irqchip,
unsigned int pin);
void kvm_irq_routing_update(struct kvm *);
#else
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
return -EINVAL;
}
static inline void kvm_irqfd_release(struct kvm *kvm) {}
static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
unsigned int irqchip,
unsigned int pin)
{
return false;
}
#endif /* CONFIG_HAVE_KVM_IRQCHIP */
void kvm_arch_irq_routing_update(struct kvm *kvm);
static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
/*
* Ensure the rest of the request is published to kvm_check_request's
* caller. Paired with the smp_mb__after_atomic in kvm_check_request.
*/
smp_wmb();
set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
/*
* Request that don't require vCPU action should never be logged in
* vcpu->requests. The vCPU won't clear the request, so it will stay
* logged indefinitely and prevent the vCPU from entering the guest.
*/
BUILD_BUG_ON(!__builtin_constant_p(req) ||
(req & KVM_REQUEST_NO_ACTION));
__kvm_make_request(req, vcpu);
}
static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
{
return READ_ONCE(vcpu->requests);
}
static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
{
return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
{
clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
}
static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
{
if (kvm_test_request(req, vcpu)) { kvm_clear_request(req, vcpu);
/*
* Ensure the rest of the request is visible to kvm_check_request's
* caller. Paired with the smp_wmb in kvm_make_request.
*/
smp_mb__after_atomic();
return true;
} else {
return false;
}
}
#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
extern bool kvm_rebooting;
#endif
extern unsigned int halt_poll_ns;
extern unsigned int halt_poll_ns_grow;
extern unsigned int halt_poll_ns_grow_start;
extern unsigned int halt_poll_ns_shrink;
struct kvm_device {
const struct kvm_device_ops *ops;
struct kvm *kvm;
void *private;
struct list_head vm_node;
};
/* create, destroy, and name are mandatory */
struct kvm_device_ops {
const char *name;
/*
* create is called holding kvm->lock and any operations not suitable
* to do while holding the lock should be deferred to init (see
* below).
*/
int (*create)(struct kvm_device *dev, u32 type);
/*
* init is called after create if create is successful and is called
* outside of holding kvm->lock.
*/
void (*init)(struct kvm_device *dev);
/*
* Destroy is responsible for freeing dev.
*
* Destroy may be called before or after destructors are called
* on emulated I/O regions, depending on whether a reference is
* held by a vcpu or other kvm component that gets destroyed
* after the emulated I/O.
*/
void (*destroy)(struct kvm_device *dev);
/*
* Release is an alternative method to free the device. It is
* called when the device file descriptor is closed. Once
* release is called, the destroy method will not be called
* anymore as the device is removed from the device list of
* the VM. kvm->lock is held.
*/
void (*release)(struct kvm_device *dev);
int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
long (*ioctl)(struct kvm_device *dev, unsigned int ioctl,
unsigned long arg);
int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
};
struct kvm_device *kvm_device_from_filp(struct file *filp);
int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
void kvm_unregister_device_ops(u32 type);
extern struct kvm_device_ops kvm_mpic_ops;
extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
vcpu->spin_loop.in_spin_loop = val;
}
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
vcpu->spin_loop.dy_eligible = val;
}
#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
{
}
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
}
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot)
{
return (memslot && memslot->id < KVM_USER_MEM_SLOTS && !(memslot->flags & KVM_MEMSLOT_INVALID));
}
struct kvm_vcpu *kvm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
bool kvm_arch_has_irq_bypass(void);
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
struct irq_bypass_producer *);
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
struct irq_bypass_producer *);
void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
struct kvm_kernel_irq_routing_entry *);
#endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
#ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS
/* If we wakeup during the poll time, was it a sucessful poll? */
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
return vcpu->valid_wakeup;
}
#else
static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
{
return true;
}
#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */
#ifdef CONFIG_HAVE_KVM_NO_POLL
/* Callback that tells if we must not poll */
bool kvm_arch_no_poll(struct kvm_vcpu *vcpu);
#else
static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
{
return false;
}
#endif /* CONFIG_HAVE_KVM_NO_POLL */
#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
long kvm_arch_vcpu_async_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
#else
static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
unsigned int ioctl,
unsigned long arg)
{
return -ENOIOCTLCMD;
}
#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
#else
static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
{
return 0;
}
#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */
#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
{
vcpu->run->exit_reason = KVM_EXIT_INTR;
vcpu->stat.signal_exits++;
}
#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
/*
* If more than one page is being (un)accounted, @virt must be the address of
* the first page of a block of pages what were allocated together (i.e
* accounted together).
*
* kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state()
* is thread-safe.
*/
static inline void kvm_account_pgtable_pages(void *virt, int nr)
{
mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr);
}
/*
* This defines how many reserved entries we want to keep before we
* kick the vcpu to the userspace to avoid dirty ring full. This
* value can be tuned to higher if e.g. PML is enabled on the host.
*/
#define KVM_DIRTY_RING_RSVD_ENTRIES 64
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
gpa_t gpa, gpa_t size,
bool is_write, bool is_exec,
bool is_private)
{
vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
vcpu->run->memory_fault.gpa = gpa;
vcpu->run->memory_fault.size = size;
/* RWX flags are not (yet) defined or communicated to userspace. */
vcpu->run->memory_fault.flags = 0;
if (is_private)
vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
}
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
{
return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
}
bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
unsigned long mask, unsigned long attrs);
bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range);
bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range);
static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
{
return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
}
#else
static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
{
return false;
}
#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
#ifdef CONFIG_KVM_PRIVATE_MEM
int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
int *max_order);
#else
static inline int kvm_gmem_get_pfn(struct kvm *kvm,
struct kvm_memory_slot *slot, gfn_t gfn,
kvm_pfn_t *pfn, struct page **page,
int *max_order)
{
KVM_BUG_ON(1, kvm);
return -EIO;
}
#endif /* CONFIG_KVM_PRIVATE_MEM */
#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
#endif
#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
/**
* kvm_gmem_populate() - Populate/prepare a GPA range with guest data
*
* @kvm: KVM instance
* @gfn: starting GFN to be populated
* @src: userspace-provided buffer containing data to copy into GFN range
* (passed to @post_populate, and incremented on each iteration
* if not NULL)
* @npages: number of pages to copy from userspace-buffer
* @post_populate: callback to issue for each gmem page that backs the GPA
* range
* @opaque: opaque data to pass to @post_populate callback
*
* This is primarily intended for cases where a gmem-backed GPA range needs
* to be initialized with userspace-provided data prior to being mapped into
* the guest as a private page. This should be called with the slots->lock
* held so that caller-enforced invariants regarding the expected memory
* attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES.
*
* Returns the number of pages that were populated.
*/
typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
void __user *src, int order, void *opaque);
long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
kvm_gmem_populate_cb post_populate, void *opaque);
#endif
#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
#endif
#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
struct kvm_pre_fault_memory *range);
#endif
#endif
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Procedures for maintaining information about logical memory blocks.
*
* Peter Bergner, IBM Corp. June 2001.
* Copyright (C) 2001 Peter Bergner.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/poison.h>
#include <linux/pfn.h>
#include <linux/debugfs.h>
#include <linux/kmemleak.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
#include <asm/sections.h>
#include <linux/io.h>
#include "internal.h"
#define INIT_MEMBLOCK_REGIONS 128
#define INIT_PHYSMEM_REGIONS 4
#ifndef INIT_MEMBLOCK_RESERVED_REGIONS
# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS
#endif
#ifndef INIT_MEMBLOCK_MEMORY_REGIONS
#define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS
#endif
/**
* DOC: memblock overview
*
* Memblock is a method of managing memory regions during the early
* boot period when the usual kernel memory allocators are not up and
* running.
*
* Memblock views the system memory as collections of contiguous
* regions. There are several types of these collections:
*
* * ``memory`` - describes the physical memory available to the
* kernel; this may differ from the actual physical memory installed
* in the system, for instance when the memory is restricted with
* ``mem=`` command line parameter
* * ``reserved`` - describes the regions that were allocated
* * ``physmem`` - describes the actual physical memory available during
* boot regardless of the possible restrictions and memory hot(un)plug;
* the ``physmem`` type is only available on some architectures.
*
* Each region is represented by struct memblock_region that
* defines the region extents, its attributes and NUMA node id on NUMA
* systems. Every memory type is described by the struct memblock_type
* which contains an array of memory regions along with
* the allocator metadata. The "memory" and "reserved" types are nicely
* wrapped with struct memblock. This structure is statically
* initialized at build time. The region arrays are initially sized to
* %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and
* %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array
* for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS.
* The memblock_allow_resize() enables automatic resizing of the region
* arrays during addition of new regions. This feature should be used
* with care so that memory allocated for the region array will not
* overlap with areas that should be reserved, for example initrd.
*
* The early architecture setup should tell memblock what the physical
* memory layout is by using memblock_add() or memblock_add_node()
* functions. The first function does not assign the region to a NUMA
* node and it is appropriate for UMA systems. Yet, it is possible to
* use it on NUMA systems as well and assign the region to a NUMA node
* later in the setup process using memblock_set_node(). The
* memblock_add_node() performs such an assignment directly.
*
* Once memblock is setup the memory can be allocated using one of the
* API variants:
*
* * memblock_phys_alloc*() - these functions return the **physical**
* address of the allocated memory
* * memblock_alloc*() - these functions return the **virtual** address
* of the allocated memory.
*
* Note, that both API variants use implicit assumptions about allowed
* memory ranges and the fallback methods. Consult the documentation
* of memblock_alloc_internal() and memblock_alloc_range_nid()
* functions for more elaborate description.
*
* As the system boot progresses, the architecture specific mem_init()
* function frees all the memory to the buddy page allocator.
*
* Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the
* memblock data structures (except "physmem") will be discarded after the
* system initialization completes.
*/
#ifndef CONFIG_NUMA
struct pglist_data __refdata contig_page_data;
EXPORT_SYMBOL(contig_page_data);
#endif
unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;
unsigned long long max_possible_pfn;
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock;
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS];
#endif
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
.memory.max = INIT_MEMBLOCK_MEMORY_REGIONS,
.memory.name = "memory",
.reserved.regions = memblock_reserved_init_regions,
.reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS,
.reserved.name = "reserved",
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
struct memblock_type physmem = {
.regions = memblock_physmem_init_regions,
.max = INIT_PHYSMEM_REGIONS,
.name = "physmem",
};
#endif
/*
* keep a pointer to &memblock.memory in the text section to use it in
* __next_mem_range() and its helpers.
* For architectures that do not keep memblock data after init, this
* pointer will be reset to NULL at memblock_discard()
*/
static __refdata struct memblock_type *memblock_memory = &memblock.memory;
#define for_each_memblock_type(i, memblock_type, rgn) \
for (i = 0, rgn = &memblock_type->regions[0]; \
i < memblock_type->cnt; \
i++, rgn = &memblock_type->regions[i])
#define memblock_dbg(fmt, ...) \
do { \
if (memblock_debug) \
pr_info(fmt, ##__VA_ARGS__); \
} while (0)
static int memblock_debug __initdata_memblock;
static bool system_has_some_mirror __initdata_memblock;
static int memblock_can_resize __initdata_memblock;
static int memblock_memory_in_slab __initdata_memblock;
static int memblock_reserved_in_slab __initdata_memblock;
bool __init_memblock memblock_has_mirror(void)
{
return system_has_some_mirror;
}
static enum memblock_flags __init_memblock choose_memblock_flags(void)
{
return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
}
/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
{
return *size = min(*size, PHYS_ADDR_MAX - base);
}
/*
* Address comparison utilities
*/
unsigned long __init_memblock
memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2,
phys_addr_t size2)
{
return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}
bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
unsigned long i;
memblock_cap_size(base, &size);
for (i = 0; i < type->cnt; i++)
if (memblock_addrs_overlap(base, size, type->regions[i].base,
type->regions[i].size))
return true;
return false;
}
/**
* __memblock_find_range_bottom_up - find free area utility in bottom-up
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Utility called from memblock_find_in_range_node(), find free area bottom-up.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
cand = round_up(this_start, align);
if (cand < this_end && this_end - cand >= size)
return cand;
}
return 0;
}
/**
* __memblock_find_range_top_down - find free area utility, in top-down
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Utility called from memblock_find_in_range_node(), find free area top-down.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end,
NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
if (this_end < size)
continue;
cand = round_down(this_end - size, align);
if (cand >= this_start)
return cand;
}
return 0;
}
/**
* memblock_find_in_range_node - find free area in given range and node
* @size: size of free area to find
* @align: alignment of free area to find
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
* Find @size free area aligned to @align in the specified range and node.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid,
enum memblock_flags flags)
{
/* pump up @end */
if (end == MEMBLOCK_ALLOC_ACCESSIBLE ||
end == MEMBLOCK_ALLOC_NOLEAKTRACE)
end = memblock.current_limit;
/* avoid allocating the first page */
start = max_t(phys_addr_t, start, PAGE_SIZE);
end = max(start, end);
if (memblock_bottom_up())
return __memblock_find_range_bottom_up(start, end, size, align,
nid, flags);
else
return __memblock_find_range_top_down(start, end, size, align,
nid, flags);
}
/**
* memblock_find_in_range - find free area in given range
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
* %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
*
* Find @size free area aligned to @align in the specified range.
*
* Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
phys_addr_t end, phys_addr_t size,
phys_addr_t align)
{
phys_addr_t ret;
enum memblock_flags flags = choose_memblock_flags();
again:
ret = memblock_find_in_range_node(size, align, start, end,
NUMA_NO_NODE, flags);
if (!ret && (flags & MEMBLOCK_MIRROR)) {
pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n",
&size);
flags &= ~MEMBLOCK_MIRROR;
goto again;
}
return ret;
}
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
{
type->total_size -= type->regions[r].size;
memmove(&type->regions[r], &type->regions[r + 1],
(type->cnt - (r + 1)) * sizeof(type->regions[r]));
type->cnt--;
/* Special case for empty arrays */
if (type->cnt == 0) {
WARN_ON(type->total_size != 0);
type->regions[0].base = 0;
type->regions[0].size = 0;
type->regions[0].flags = 0;
memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
}
}
#ifndef CONFIG_ARCH_KEEP_MEMBLOCK
/**
* memblock_discard - discard memory and reserved arrays if they were allocated
*/
void __init memblock_discard(void)
{
phys_addr_t addr, size;
if (memblock.reserved.regions != memblock_reserved_init_regions) {
addr = __pa(memblock.reserved.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.reserved.max);
if (memblock_reserved_in_slab)
kfree(memblock.reserved.regions);
else
memblock_free_late(addr, size);
}
if (memblock.memory.regions != memblock_memory_init_regions) {
addr = __pa(memblock.memory.regions);
size = PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.memory.max);
if (memblock_memory_in_slab)
kfree(memblock.memory.regions);
else
memblock_free_late(addr, size);
}
memblock_memory = NULL;
}
#endif
/**
* memblock_double_array - double the size of the memblock regions array
* @type: memblock type of the regions array being doubled
* @new_area_start: starting address of memory range to avoid overlap with
* @new_area_size: size of memory range to avoid overlap with
*
* Double the size of the @type regions array. If memblock is being used to
* allocate memory for a new reserved regions array and there is a previously
* allocated memory range [@new_area_start, @new_area_start + @new_area_size]
* waiting to be reserved, ensure the memory used by the new array does
* not overlap.
*
* Return:
* 0 on success, -1 on failure.
*/
static int __init_memblock memblock_double_array(struct memblock_type *type,
phys_addr_t new_area_start,
phys_addr_t new_area_size)
{
struct memblock_region *new_array, *old_array;
phys_addr_t old_alloc_size, new_alloc_size;
phys_addr_t old_size, new_size, addr, new_end;
int use_slab = slab_is_available();
int *in_slab;
/* We don't allow resizing until we know about the reserved regions
* of memory that aren't suitable for allocation
*/
if (!memblock_can_resize)
panic("memblock: cannot resize %s array\n", type->name);
/* Calculate new doubled size */
old_size = type->max * sizeof(struct memblock_region);
new_size = old_size << 1;
/*
* We need to allocated new one align to PAGE_SIZE,
* so we can free them completely later.
*/
old_alloc_size = PAGE_ALIGN(old_size);
new_alloc_size = PAGE_ALIGN(new_size);
/* Retrieve the slab flag */
if (type == &memblock.memory)
in_slab = &memblock_memory_in_slab;
else
in_slab = &memblock_reserved_in_slab;
/* Try to find some space for it */
if (use_slab) {
new_array = kmalloc(new_size, GFP_KERNEL);
addr = new_array ? __pa(new_array) : 0;
} else {
/* only exclude range when trying to double reserved.regions */
if (type != &memblock.reserved)
new_area_start = new_area_size = 0;
addr = memblock_find_in_range(new_area_start + new_area_size,
memblock.current_limit,
new_alloc_size, PAGE_SIZE);
if (!addr && new_area_size)
addr = memblock_find_in_range(0,
min(new_area_start, memblock.current_limit),
new_alloc_size, PAGE_SIZE);
new_array = addr ? __va(addr) : NULL;
}
if (!addr) {
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
type->name, type->max, type->max * 2);
return -1;
}
new_end = addr + new_size - 1;
memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]",
type->name, type->max * 2, &addr, &new_end);
/*
* Found space, we now need to move the array over before we add the
* reserved region since it may be our reserved array itself that is
* full.
*/
memcpy(new_array, type->regions, old_size);
memset(new_array + type->max, 0, old_size);
old_array = type->regions;
type->regions = new_array;
type->max <<= 1;
/* Free old array. We needn't free it if the array is the static one */
if (*in_slab)
kfree(old_array);
else if (old_array != memblock_memory_init_regions &&
old_array != memblock_reserved_init_regions)
memblock_free(old_array, old_alloc_size);
/*
* Reserve the new array if that comes from the memblock. Otherwise, we
* needn't do it
*/
if (!use_slab)
BUG_ON(memblock_reserve(addr, new_alloc_size));
/* Update slab flag */
*in_slab = use_slab;
return 0;
}
/**
* memblock_merge_regions - merge neighboring compatible regions
* @type: memblock type to scan
* @start_rgn: start scanning from (@start_rgn - 1)
* @end_rgn: end scanning at (@end_rgn - 1)
* Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn)
*/
static void __init_memblock memblock_merge_regions(struct memblock_type *type,
unsigned long start_rgn,
unsigned long end_rgn)
{
int i = 0;
if (start_rgn)
i = start_rgn - 1;
end_rgn = min(end_rgn, type->cnt - 1);
while (i < end_rgn) {
struct memblock_region *this = &type->regions[i];
struct memblock_region *next = &type->regions[i + 1];
if (this->base + this->size != next->base ||
memblock_get_region_node(this) !=
memblock_get_region_node(next) ||
this->flags != next->flags) {
BUG_ON(this->base + this->size > next->base);
i++;
continue;
}
this->size += next->size;
/* move forward from next + 1, index of which is i + 2 */
memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
type->cnt--;
end_rgn--;
}
}
/**
* memblock_insert_region - insert new memblock region
* @type: memblock type to insert into
* @idx: index for the insertion point
* @base: base address of the new region
* @size: size of the new region
* @nid: node id of the new region
* @flags: flags of the new region
*
* Insert new memblock region [@base, @base + @size) into @type at @idx.
* @type must already have extra room to accommodate the new region.
*/
static void __init_memblock memblock_insert_region(struct memblock_type *type,
int idx, phys_addr_t base,
phys_addr_t size,
int nid,
enum memblock_flags flags)
{
struct memblock_region *rgn = &type->regions[idx];
BUG_ON(type->cnt >= type->max);
memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
rgn->base = base;
rgn->size = size;
rgn->flags = flags;
memblock_set_region_node(rgn, nid);
type->cnt++;
type->total_size += size;
}
/**
* memblock_add_range - add new memblock region
* @type: memblock type to add new region into
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
* @flags: flags of the new region
*
* Add new memblock region [@base, @base + @size) into @type. The new region
* is allowed to overlap with existing ones - overlaps don't affect already
* existing regions. @type is guaranteed to be minimal (all neighbouring
* compatible regions are merged) after the addition.
*
* Return:
* 0 on success, -errno on failure.
*/
static int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, enum memblock_flags flags)
{
bool insert = false;
phys_addr_t obase = base;
phys_addr_t end = base + memblock_cap_size(base, &size);
int idx, nr_new, start_rgn = -1, end_rgn;
struct memblock_region *rgn;
if (!size)
return 0;
/* special case for empty array */
if (type->regions[0].size == 0) {
WARN_ON(type->cnt != 0 || type->total_size);
type->regions[0].base = base;
type->regions[0].size = size;
type->regions[0].flags = flags;
memblock_set_region_node(&type->regions[0], nid);
type->total_size = size;
type->cnt = 1;
return 0;
}
/*
* The worst case is when new range overlaps all existing regions,
* then we'll need type->cnt + 1 empty regions in @type. So if
* type->cnt * 2 + 1 is less than or equal to type->max, we know
* that there is enough empty regions in @type, and we can insert
* regions directly.
*/
if (type->cnt * 2 + 1 <= type->max)
insert = true;
repeat:
/*
* The following is executed twice. Once with %false @insert and
* then with %true. The first counts the number of regions needed
* to accommodate the new area. The second actually inserts them.
*/
base = obase;
nr_new = 0;
for_each_memblock_type(idx, type, rgn) {
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
/*
* @rgn overlaps. If it separates the lower part of new
* area, insert that portion.
*/
if (rbase > base) {
#ifdef CONFIG_NUMA
WARN_ON(nid != memblock_get_region_node(rgn));
#endif
WARN_ON(flags != rgn->flags);
nr_new++;
if (insert) {
if (start_rgn == -1)
start_rgn = idx;
end_rgn = idx + 1;
memblock_insert_region(type, idx++, base,
rbase - base, nid,
flags);
}
}
/* area below @rend is dealt with, forget about it */
base = min(rend, end);
}
/* insert the remaining portion */
if (base < end) {
nr_new++;
if (insert) {
if (start_rgn == -1)
start_rgn = idx;
end_rgn = idx + 1;
memblock_insert_region(type, idx, base, end - base,
nid, flags);
}
}
if (!nr_new)
return 0;
/*
* If this was the first round, resize array and repeat for actual
* insertions; otherwise, merge and return.
*/
if (!insert) {
while (type->cnt + nr_new > type->max)
if (memblock_double_array(type, obase, size) < 0)
return -ENOMEM;
insert = true;
goto repeat;
} else {
memblock_merge_regions(type, start_rgn, end_rgn);
return 0;
}
}
/**
* memblock_add_node - add new memblock region within a NUMA node
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
* @flags: flags of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid, enum memblock_flags flags)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__,
&base, &end, nid, flags, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, nid, flags);
}
/**
* memblock_add - add new memblock region
* @base: base address of the new region
* @size: size of the new region
*
* Add new memblock region [@base, @base + @size) to the "memory"
* type. See memblock_add_range() description for mode details
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
}
/**
* memblock_validate_numa_coverage - check if amount of memory with
* no node ID assigned is less than a threshold
* @threshold_bytes: maximal memory size that can have unassigned node
* ID (in bytes).
*
* A buggy firmware may report memory that does not belong to any node.
* Check if amount of such memory is below @threshold_bytes.
*
* Return: true on success, false on failure.
*/
bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes)
{
unsigned long nr_pages = 0;
unsigned long start_pfn, end_pfn, mem_size_mb;
int nid, i;
/* calculate lose page */
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
if (!numa_valid_node(nid))
nr_pages += end_pfn - start_pfn;
}
if ((nr_pages << PAGE_SHIFT) > threshold_bytes) {
mem_size_mb = memblock_phys_mem_size() >> 20;
pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
(nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
return false;
}
return true;
}
/**
* memblock_isolate_range - isolate given range into disjoint memblocks
* @type: memblock type to isolate range for
* @base: base of range to isolate
* @size: size of range to isolate
* @start_rgn: out parameter for the start of isolated region
* @end_rgn: out parameter for the end of isolated region
*
* Walk @type and ensure that regions don't cross the boundaries defined by
* [@base, @base + @size). Crossing regions are split at the boundaries,
* which may create at most two more regions. The index of the first
* region inside the range is returned in *@start_rgn and the index of the
* first region after the range is returned in *@end_rgn.
*
* Return:
* 0 on success, -errno on failure.
*/
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int *start_rgn, int *end_rgn)
{
phys_addr_t end = base + memblock_cap_size(base, &size);
int idx;
struct memblock_region *rgn;
*start_rgn = *end_rgn = 0;
if (!size)
return 0;
/* we'll create at most two more regions */
while (type->cnt + 2 > type->max)
if (memblock_double_array(type, base, size) < 0)
return -ENOMEM;
for_each_memblock_type(idx, type, rgn) {
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
if (rbase < base) {
/*
* @rgn intersects from below. Split and continue
* to process the next region - the new top half.
*/
rgn->base = base;
rgn->size -= base - rbase;
type->total_size -= base - rbase;
memblock_insert_region(type, idx, rbase, base - rbase,
memblock_get_region_node(rgn),
rgn->flags);
} else if (rend > end) {
/*
* @rgn intersects from above. Split and redo the
* current region - the new bottom half.
*/
rgn->base = end;
rgn->size -= end - rbase;
type->total_size -= end - rbase;
memblock_insert_region(type, idx--, rbase, end - rbase,
memblock_get_region_node(rgn),
rgn->flags);
} else {
/* @rgn is fully contained, record it */
if (!*end_rgn)
*start_rgn = idx;
*end_rgn = idx + 1;
}
}
return 0;
}
static int __init_memblock memblock_remove_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = end_rgn - 1; i >= start_rgn; i--)
memblock_remove_region(type, i);
return 0;
}
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_remove_range(&memblock.memory, base, size);
}
/**
* memblock_free - free boot memory allocation
* @ptr: starting address of the boot memory allocation
* @size: size of the boot memory block in bytes
*
* Free boot memory block previously allocated by memblock_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
void __init_memblock memblock_free(void *ptr, size_t size)
{
if (ptr)
memblock_phys_free(__pa(ptr), size);
}
/**
* memblock_phys_free - free boot memory block
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
kmemleak_free_part_phys(base, size);
return memblock_remove_range(&memblock.reserved, base, size);
}
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
}
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0);
}
#endif
/**
* memblock_setclr_flag - set or clear flag for a memory region
* @type: memblock type to set/clear flag for
* @base: base address of the region
* @size: size of the region
* @set: set or clear the flag
* @flag: the flag to update
*
* This function isolates region [@base, @base + @size), and sets/clears flag
*
* Return: 0 on success, -errno on failure.
*/
static int __init_memblock memblock_setclr_flag(struct memblock_type *type,
phys_addr_t base, phys_addr_t size, int set, int flag)
{
int i, ret, start_rgn, end_rgn;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++) {
struct memblock_region *r = &type->regions[i];
if (set)
r->flags |= flag;
else
r->flags &= ~flag;
}
memblock_merge_regions(type, start_rgn, end_rgn);
return 0;
}
/**
* memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG);
}
/**
* memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG);
}
/**
* memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
{
if (!mirrored_kernelcore)
return 0;
system_has_some_mirror = true;
return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR);
}
/**
* memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP.
* @base: the base phys addr of the region
* @size: the size of the region
*
* The memory regions marked with %MEMBLOCK_NOMAP will not be added to the
* direct mapping of the physical memory. These regions will still be
* covered by the memory map. The struct page representing NOMAP memory
* frames in the memory map will be PageReserved()
*
* Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from
* memblock, the caller must inform kmemleak to ignore that memory
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP);
}
/**
* memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP);
}
/**
* memblock_reserved_mark_noinit - Mark a reserved memory region with flag
* MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized
* for this region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* struct pages will not be initialized for reserved memory regions marked with
* %MEMBLOCK_RSRV_NOINIT.
*
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size)
{
return memblock_setclr_flag(&memblock.reserved, base, size, 1,
MEMBLOCK_RSRV_NOINIT);
}
static bool should_skip_region(struct memblock_type *type,
struct memblock_region *m,
int nid, int flags)
{
int m_nid = memblock_get_region_node(m);
/* we never skip regions when iterating memblock.reserved or physmem */
if (type != memblock_memory)
return false;
/* only memory regions are associated with nodes, check it */
if (numa_valid_node(nid) && nid != m_nid)
return true;
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m) &&
!(flags & MEMBLOCK_HOTPLUG))
return true;
/* if we want mirror memory skip non-mirror memory regions */
if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
return true;
/* skip nomap memory unless we were asked for it explicitly */
if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
return true;
/* skip driver-managed memory unless we were asked for it explicitly */
if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m))
return true;
return false;
}
/**
* __next_mem_range - next function for for_each_free_mem_range() etc.
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Find the first area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
* *@idx contains index into type_a and the upper 32bit indexes the
* areas before each region in type_b. For example, if type_b regions
* look like the following,
*
* 0:[0-16), 1:[32-48), 2:[128-130)
*
* The upper 32bit indexes the following regions.
*
* 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX)
*
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
for (; idx_a < type_a->cnt; idx_a++) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
if (should_skip_region(type_a, m, nid, flags))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b < type_b->cnt + 1; idx_b++) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : PHYS_ADDR_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_start >= m_end)
break;
/* if the two regions intersect, we're done */
if (m_start < r_end) {
if (out_start)
*out_start =
max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
/*
* The region which ends first is
* advanced for the next iteration.
*/
if (m_end <= r_end)
idx_a++;
else
idx_b++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/**
* __next_mem_range_rev - generic next function for for_each_*_range_rev()
*
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Finds the next range from type_a which is not marked as unsuitable
* in type_b.
*
* Reverse of __next_mem_range().
*/
void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
if (*idx == (u64)ULLONG_MAX) {
idx_a = type_a->cnt - 1;
if (type_b != NULL)
idx_b = type_b->cnt;
else
idx_b = 0;
}
for (; idx_a >= 0; idx_a--) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
if (should_skip_region(type_a, m, nid, flags))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a--;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b >= 0; idx_b--) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : PHYS_ADDR_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_end <= m_start)
break;
/* if the two regions intersect, we're done */
if (m_end > r_start) {
if (out_start)
*out_start = max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
if (m_start >= r_start)
idx_a--;
else
idx_b--;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/*
* Common iterator interface used to define for_each_mem_pfn_range().
*/
void __init_memblock __next_mem_pfn_range(int *idx, int nid,
unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid)
{
struct memblock_type *type = &memblock.memory;
struct memblock_region *r;
int r_nid;
while (++*idx < type->cnt) {
r = &type->regions[*idx];
r_nid = memblock_get_region_node(r);
if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size))
continue;
if (!numa_valid_node(nid) || nid == r_nid)
break;
}
if (*idx >= type->cnt) {
*idx = -1;
return;
}
if (out_start_pfn)
*out_start_pfn = PFN_UP(r->base);
if (out_end_pfn)
*out_end_pfn = PFN_DOWN(r->base + r->size);
if (out_nid)
*out_nid = r_nid;
}
/**
* memblock_set_node - set node ID on memblock regions
* @base: base of area to set node ID for
* @size: size of area to set node ID for
* @type: memblock type to set node ID for
* @nid: node ID to set
*
* Set the nid of memblock @type regions in [@base, @base + @size) to @nid.
* Regions which cross the area boundaries are split as necessary.
*
* Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
struct memblock_type *type, int nid)
{
#ifdef CONFIG_NUMA
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
memblock_set_region_node(&type->regions[i], nid);
memblock_merge_regions(type, start_rgn, end_rgn);
#endif
return 0;
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/**
* __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone()
*
* @idx: pointer to u64 loop variable
* @zone: zone in which all of the memory blocks reside
* @out_spfn: ptr to ulong for start pfn of the range, can be %NULL
* @out_epfn: ptr to ulong for end pfn of the range, can be %NULL
*
* This function is meant to be a zone/pfn specific wrapper for the
* for_each_mem_range type iterators. Specifically they are used in the
* deferred memory init routines and as such we were duplicating much of
* this logic throughout the code. So instead of having it in multiple
* locations it seemed like it would make more sense to centralize this to
* one new iterator that does everything they need.
*/
void __init_memblock
__next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
unsigned long *out_spfn, unsigned long *out_epfn)
{
int zone_nid = zone_to_nid(zone);
phys_addr_t spa, epa;
__next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
&memblock.memory, &memblock.reserved,
&spa, &epa, NULL);
while (*idx != U64_MAX) {
unsigned long epfn = PFN_DOWN(epa);
unsigned long spfn = PFN_UP(spa);
/*
* Verify the end is at least past the start of the zone and
* that we have at least one PFN to initialize.
*/
if (zone->zone_start_pfn < epfn && spfn < epfn) {
/* if we went too far just stop searching */
if (zone_end_pfn(zone) <= spfn) {
*idx = U64_MAX;
break;
}
if (out_spfn)
*out_spfn = max(zone->zone_start_pfn, spfn);
if (out_epfn)
*out_epfn = min(zone_end_pfn(zone), epfn);
return;
}
__next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
&memblock.memory, &memblock.reserved,
&spa, &epa, NULL);
}
/* signal end of iteration */
if (out_spfn)
*out_spfn = ULONG_MAX;
if (out_epfn)
*out_epfn = 0;
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
/**
* memblock_alloc_range_nid - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @start: the lower bound of the memory region to allocate (phys address)
* @end: the upper bound of the memory region to allocate (phys address)
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @exact_nid: control the allocation fall back to other nodes
*
* The allocation is performed from memory region limited by
* memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE.
*
* If the specified node can not hold the requested memory and @exact_nid
* is false, the allocation falls back to any node in the system.
*
* For systems with memory mirroring, the allocation is attempted first
* from the regions with mirroring enabled and then retried from any
* memory region.
*
* In addition, function using kmemleak_alloc_phys for allocated boot
* memory block, it is never reported as leaks.
*
* Return:
* Physical address of allocated memory block on success, %0 on failure.
*/
phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid,
bool exact_nid)
{
enum memblock_flags flags = choose_memblock_flags();
phys_addr_t found;
/*
* Detect any accidental use of these APIs after slab is ready, as at
* this moment memblock may be deinitialized already and its
* internal data may be destroyed (after execution of memblock_free_all)
*/
if (WARN_ON_ONCE(slab_is_available())) {
void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid);
return vaddr ? virt_to_phys(vaddr) : 0;
}
if (!align) {
/* Can't use WARNs this early in boot on powerpc */
dump_stack();
align = SMP_CACHE_BYTES;
}
again:
found = memblock_find_in_range_node(size, align, start, end, nid,
flags);
if (found && !memblock_reserve(found, size))
goto done;
if (numa_valid_node(nid) && !exact_nid) {
found = memblock_find_in_range_node(size, align, start,
end, NUMA_NO_NODE,
flags);
if (found && !memblock_reserve(found, size))
goto done;
}
if (flags & MEMBLOCK_MIRROR) {
flags &= ~MEMBLOCK_MIRROR;
pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n",
&size);
goto again;
}
return 0;
done:
/*
* Skip kmemleak for those places like kasan_init() and
* early_pgtable_alloc() due to high volume.
*/
if (end != MEMBLOCK_ALLOC_NOLEAKTRACE)
/*
* Memblock allocated blocks are never reported as
* leaks. This is because many of these blocks are
* only referred via the physical address which is
* not looked up by kmemleak.
*/
kmemleak_alloc_phys(found, size, 0);
/*
* Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP,
* require memory to be accepted before it can be used by the
* guest.
*
* Accept the memory of the allocated buffer.
*/
accept_memory(found, size);
return found;
}
/**
* memblock_phys_alloc_range - allocate a memory block inside specified range
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @start: the lower bound of the memory region to allocate (physical address)
* @end: the upper bound of the memory region to allocate (physical address)
*
* Allocate @size bytes in the between @start and @end.
*
* Return: physical address of the allocated memory block on success,
* %0 on failure.
*/
phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size,
phys_addr_t align,
phys_addr_t start,
phys_addr_t end)
{
memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, &start, &end,
(void *)_RET_IP_);
return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE,
false);
}
/**
* memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Allocates memory block from the specified NUMA node. If the node
* has no available memory, attempts to allocated from any node in the
* system.
*
* Return: physical address of the allocated memory block on success,
* %0 on failure.
*/
phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
{
return memblock_alloc_range_nid(size, align, 0,
MEMBLOCK_ALLOC_ACCESSIBLE, nid, false);
}
/**
* memblock_alloc_internal - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region to allocate (phys address)
* @max_addr: the upper bound of the memory region to allocate (phys address)
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @exact_nid: control the allocation fall back to other nodes
*
* Allocates memory block using memblock_alloc_range_nid() and
* converts the returned physical address to virtual.
*
* The @min_addr limit is dropped if it can not be satisfied and the allocation
* will fall back to memory below @min_addr. Other constraints, such
* as node and mirrored memory will be handled again in
* memblock_alloc_range_nid().
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
static void * __init memblock_alloc_internal(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid, bool exact_nid)
{
phys_addr_t alloc;
if (max_addr > memblock.current_limit)
max_addr = memblock.current_limit;
alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid,
exact_nid);
/* retry allocation without lower limit */
if (!alloc && min_addr)
alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid,
exact_nid);
if (!alloc)
return NULL;
return phys_to_virt(alloc);
}
/**
* memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node
* without zeroing memory
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public function, provides additional debug information (including caller
* info), if enabled. Does not zero allocated memory.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_alloc_exact_nid_raw(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
true);
}
/**
* memblock_alloc_try_nid_raw - allocate boot memory block without zeroing
* memory and without panicking
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public function, provides additional debug information (including caller
* info), if enabled. Does not zero allocated memory, does not panic if request
* cannot be satisfied.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_alloc_try_nid_raw(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
return memblock_alloc_internal(size, align, min_addr, max_addr, nid,
false);
}
/**
* memblock_alloc_try_nid - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public function, provides additional debug information (including caller
* info), if enabled. This function zeroes the allocated memory.
*
* Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_alloc_try_nid(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
void *ptr;
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n",
__func__, (u64)size, (u64)align, nid, &min_addr,
&max_addr, (void *)_RET_IP_);
ptr = memblock_alloc_internal(size, align,
min_addr, max_addr, nid, false);
if (ptr)
memset(ptr, 0, size);
return ptr;
}
/**
* __memblock_alloc_or_panic - Try to allocate memory and panic on failure
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @func: caller func name
*
* This function attempts to allocate memory using memblock_alloc,
* and in case of failure, it calls panic with the formatted message.
* This function should not be used directly, please use the macro memblock_alloc_or_panic.
*/
void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
const char *func)
{
void *addr = memblock_alloc(size, align);
if (unlikely(!addr))
panic("%s: Failed to allocate %pap bytes\n", func, &size);
return addr;
}
/**
* memblock_free_late - free pages directly to buddy allocator
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* This is only useful when the memblock allocator has already been torn
* down, but we are still initializing the system. Pages are released directly
* to the buddy allocator.
*/
void __init memblock_free_late(phys_addr_t base, phys_addr_t size)
{
phys_addr_t cursor, end;
end = base + size - 1;
memblock_dbg("%s: [%pa-%pa] %pS\n",
__func__, &base, &end, (void *)_RET_IP_);
kmemleak_free_part_phys(base, size);
cursor = PFN_UP(base);
end = PFN_DOWN(base + size);
for (; cursor < end; cursor++) {
memblock_free_pages(pfn_to_page(cursor), cursor, 0);
totalram_pages_inc();
}
}
/*
* Remaining API functions
*/
phys_addr_t __init_memblock memblock_phys_mem_size(void)
{
return memblock.memory.total_size;
}
phys_addr_t __init_memblock memblock_reserved_size(void)
{
return memblock.reserved.total_size;
}
/**
* memblock_estimated_nr_free_pages - return estimated number of free pages
* from memblock point of view
*
* During bootup, subsystems might need a rough estimate of the number of free
* pages in the whole system, before precise numbers are available from the
* buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers
* obtained from the buddy might be very imprecise during bootup.
*
* Return:
* An estimated number of free pages from memblock point of view.
*/
unsigned long __init memblock_estimated_nr_free_pages(void)
{
return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size());
}
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
return memblock.memory.regions[0].base;
}
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
{
int idx = memblock.memory.cnt - 1;
return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
}
static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
{
phys_addr_t max_addr = PHYS_ADDR_MAX;
struct memblock_region *r;
/*
* translate the memory @limit size into the max address within one of
* the memory memblock regions, if the @limit exceeds the total size
* of those regions, max_addr will keep original value PHYS_ADDR_MAX
*/
for_each_mem_region(r) {
if (limit <= r->size) {
max_addr = r->base + limit;
break;
}
limit -= r->size;
}
return max_addr;
}
void __init memblock_enforce_memory_limit(phys_addr_t limit)
{
phys_addr_t max_addr;
if (!limit)
return;
max_addr = __find_max_addr(limit);
/* @limit exceeds the total size of the memory, do nothing */
if (max_addr == PHYS_ADDR_MAX)
return;
/* truncate both memory and reserved regions */
memblock_remove_range(&memblock.memory, max_addr,
PHYS_ADDR_MAX);
memblock_remove_range(&memblock.reserved, max_addr,
PHYS_ADDR_MAX);
}
void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
if (!size)
return;
if (!memblock_memory->total_size) {
pr_warn("%s: No memory registered yet\n", __func__);
return;
}
ret = memblock_isolate_range(&memblock.memory, base, size,
&start_rgn, &end_rgn);
if (ret)
return;
/* remove all the MAP regions */
for (i = memblock.memory.cnt - 1; i >= end_rgn; i--)
if (!memblock_is_nomap(&memblock.memory.regions[i]))
memblock_remove_region(&memblock.memory, i);
for (i = start_rgn - 1; i >= 0; i--)
if (!memblock_is_nomap(&memblock.memory.regions[i]))
memblock_remove_region(&memblock.memory, i);
/* truncate the reserved regions */
memblock_remove_range(&memblock.reserved, 0, base);
memblock_remove_range(&memblock.reserved,
base + size, PHYS_ADDR_MAX);
}
void __init memblock_mem_limit_remove_map(phys_addr_t limit)
{
phys_addr_t max_addr;
if (!limit)
return;
max_addr = __find_max_addr(limit);
/* @limit exceeds the total size of the memory, do nothing */
if (max_addr == PHYS_ADDR_MAX)
return;
memblock_cap_memory_range(0, max_addr);
}
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
{
unsigned int left = 0, right = type->cnt;
do {
unsigned int mid = (right + left) / 2;
if (addr < type->regions[mid].base)
right = mid;
else if (addr >= (type->regions[mid].base +
type->regions[mid].size))
left = mid + 1;
else
return mid;
} while (left < right);
return -1;
}
bool __init_memblock memblock_is_reserved(phys_addr_t addr)
{
return memblock_search(&memblock.reserved, addr) != -1;
}
bool __init_memblock memblock_is_memory(phys_addr_t addr)
{
return memblock_search(&memblock.memory, addr) != -1;
}
bool __init_memblock memblock_is_map_memory(phys_addr_t addr)
{ int i = memblock_search(&memblock.memory, addr);
if (i == -1)
return false;
return !memblock_is_nomap(&memblock.memory.regions[i]);
}
int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
unsigned long *start_pfn, unsigned long *end_pfn)
{
struct memblock_type *type = &memblock.memory;
int mid = memblock_search(type, PFN_PHYS(pfn));
if (mid == -1)
return NUMA_NO_NODE;
*start_pfn = PFN_DOWN(type->regions[mid].base);
*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
return memblock_get_region_node(&type->regions[mid]);
}
/**
* memblock_is_region_memory - check if a region is a subset of memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base + @size) is a subset of a memory block.
*
* Return:
* 0 if false, non-zero if true
*/
bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
{
int idx = memblock_search(&memblock.memory, base);
phys_addr_t end = base + memblock_cap_size(base, &size);
if (idx == -1)
return false;
return (memblock.memory.regions[idx].base +
memblock.memory.regions[idx].size) >= end;
}
/**
* memblock_is_region_reserved - check if a region intersects reserved memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base + @size) intersects a reserved
* memory block.
*
* Return:
* True if they intersect, false if not.
*/
bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
return memblock_overlaps_region(&memblock.reserved, base, size);
}
void __init_memblock memblock_trim_memory(phys_addr_t align)
{
phys_addr_t start, end, orig_start, orig_end;
struct memblock_region *r;
for_each_mem_region(r) {
orig_start = r->base;
orig_end = r->base + r->size;
start = round_up(orig_start, align);
end = round_down(orig_end, align);
if (start == orig_start && end == orig_end)
continue;
if (start < end) {
r->base = start;
r->size = end - start;
} else {
memblock_remove_region(&memblock.memory,
r - memblock.memory.regions);
r--;
}
}
}
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
{
memblock.current_limit = limit;
}
phys_addr_t __init_memblock memblock_get_current_limit(void)
{
return memblock.current_limit;
}
static void __init_memblock memblock_dump(struct memblock_type *type)
{
phys_addr_t base, end, size;
enum memblock_flags flags;
int idx;
struct memblock_region *rgn;
pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt);
for_each_memblock_type(idx, type, rgn) {
char nid_buf[32] = "";
base = rgn->base;
size = rgn->size;
end = base + size - 1;
flags = rgn->flags;
#ifdef CONFIG_NUMA
if (numa_valid_node(memblock_get_region_node(rgn)))
snprintf(nid_buf, sizeof(nid_buf), " on node %d",
memblock_get_region_node(rgn));
#endif
pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n",
type->name, idx, &base, &end, &size, nid_buf, flags);
}
}
static void __init_memblock __memblock_dump_all(void)
{
pr_info("MEMBLOCK configuration:\n");
pr_info(" memory size = %pa reserved size = %pa\n",
&memblock.memory.total_size,
&memblock.reserved.total_size);
memblock_dump(&memblock.memory);
memblock_dump(&memblock.reserved);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
memblock_dump(&physmem);
#endif
}
void __init_memblock memblock_dump_all(void)
{
if (memblock_debug)
__memblock_dump_all();
}
void __init memblock_allow_resize(void)
{
memblock_can_resize = 1;
}
static int __init early_memblock(char *p)
{
if (p && strstr(p, "debug"))
memblock_debug = 1;
return 0;
}
early_param("memblock", early_memblock);
static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn)
{
struct page *start_pg, *end_pg;
phys_addr_t pg, pgend;
/*
* Convert start_pfn/end_pfn to a struct page pointer.
*/
start_pg = pfn_to_page(start_pfn - 1) + 1;
end_pg = pfn_to_page(end_pfn - 1) + 1;
/*
* Convert to physical addresses, and round start upwards and end
* downwards.
*/
pg = PAGE_ALIGN(__pa(start_pg));
pgend = PAGE_ALIGN_DOWN(__pa(end_pg));
/*
* If there are free pages between these, free the section of the
* memmap array.
*/
if (pg < pgend)
memblock_phys_free(pg, pgend - pg);
}
/*
* The mem_map array can get very big. Free the unused area of the memory map.
*/
static void __init free_unused_memmap(void)
{
unsigned long start, end, prev_end = 0;
int i;
if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) ||
IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
return;
/*
* This relies on each bank being in address order.
* The banks are sorted previously in bootmem_init().
*/
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
#ifdef CONFIG_SPARSEMEM
/*
* Take care not to free memmap entries that don't exist
* due to SPARSEMEM sections which aren't present.
*/
start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));
#endif
/*
* Align down here since many operations in VM subsystem
* presume that there are no holes in the memory map inside
* a pageblock
*/
start = pageblock_start_pfn(start);
/*
* If we had a previous bank, and there is a space
* between the current bank and the previous, free it.
*/
if (prev_end && prev_end < start)
free_memmap(prev_end, start);
/*
* Align up here since many operations in VM subsystem
* presume that there are no holes in the memory map inside
* a pageblock
*/
prev_end = pageblock_align(end);
}
#ifdef CONFIG_SPARSEMEM
if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) {
prev_end = pageblock_align(end);
free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));
}
#endif
}
static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
int order;
while (start < end) {
/*
* Free the pages in the largest chunks alignment allows.
*
* __ffs() behaviour is undefined for 0. start == 0 is
* MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for
* the case.
*/
if (start)
order = min_t(int, MAX_PAGE_ORDER, __ffs(start));
else
order = MAX_PAGE_ORDER;
while (start + (1UL << order) > end)
order--;
memblock_free_pages(pfn_to_page(start), start, order);
start += (1UL << order);
}
}
static unsigned long __init __free_memory_core(phys_addr_t start,
phys_addr_t end)
{
unsigned long start_pfn = PFN_UP(start);
unsigned long end_pfn = PFN_DOWN(end);
if (!IS_ENABLED(CONFIG_HIGHMEM) && end_pfn > max_low_pfn)
end_pfn = max_low_pfn;
if (start_pfn >= end_pfn)
return 0;
__free_pages_memory(start_pfn, end_pfn);
return end_pfn - start_pfn;
}
static void __init memmap_init_reserved_pages(void)
{
struct memblock_region *region;
phys_addr_t start, end;
int nid;
/*
* set nid on all reserved pages and also treat struct
* pages for the NOMAP regions as PageReserved
*/
for_each_mem_region(region) {
nid = memblock_get_region_node(region);
start = region->base;
end = start + region->size;
if (memblock_is_nomap(region))
reserve_bootmem_region(start, end, nid);
memblock_set_node(start, end, &memblock.reserved, nid);
}
/*
* initialize struct pages for reserved regions that don't have
* the MEMBLOCK_RSRV_NOINIT flag set
*/
for_each_reserved_mem_region(region) {
if (!memblock_is_reserved_noinit(region)) {
nid = memblock_get_region_node(region);
start = region->base;
end = start + region->size;
if (!numa_valid_node(nid))
nid = early_pfn_to_nid(PFN_DOWN(start));
reserve_bootmem_region(start, end, nid);
}
}
}
static unsigned long __init free_low_memory_core_early(void)
{
unsigned long count = 0;
phys_addr_t start, end;
u64 i;
memblock_clear_hotplug(0, -1);
memmap_init_reserved_pages();
/*
* We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
* because in some case like Node0 doesn't have RAM installed
* low ram will be on Node1
*/
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
NULL)
count += __free_memory_core(start, end);
return count;
}
static int reset_managed_pages_done __initdata;
static void __init reset_node_managed_pages(pg_data_t *pgdat)
{
struct zone *z;
for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
atomic_long_set(&z->managed_pages, 0);
}
void __init reset_all_zones_managed_pages(void)
{
struct pglist_data *pgdat;
if (reset_managed_pages_done)
return;
for_each_online_pgdat(pgdat)
reset_node_managed_pages(pgdat);
reset_managed_pages_done = 1;
}
/**
* memblock_free_all - release free pages to the buddy allocator
*/
void __init memblock_free_all(void)
{
unsigned long pages;
free_unused_memmap();
reset_all_zones_managed_pages();
pages = free_low_memory_core_early();
totalram_pages_add(pages);
}
/* Keep a table to reserve named memory */
#define RESERVE_MEM_MAX_ENTRIES 8
#define RESERVE_MEM_NAME_SIZE 16
struct reserve_mem_table {
char name[RESERVE_MEM_NAME_SIZE];
phys_addr_t start;
phys_addr_t size;
};
static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES];
static int reserved_mem_count;
static DEFINE_MUTEX(reserve_mem_lock);
/* Add wildcard region with a lookup name */
static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size,
const char *name)
{
struct reserve_mem_table *map;
map = &reserved_mem_table[reserved_mem_count++];
map->start = start;
map->size = size;
strscpy(map->name, name);
}
static struct reserve_mem_table *reserve_mem_find_by_name_nolock(const char *name)
{
struct reserve_mem_table *map;
int i;
for (i = 0; i < reserved_mem_count; i++) {
map = &reserved_mem_table[i];
if (!map->size)
continue;
if (strcmp(name, map->name) == 0)
return map;
}
return NULL;
}
/**
* reserve_mem_find_by_name - Find reserved memory region with a given name
* @name: The name that is attached to a reserved memory region
* @start: If found, holds the start address
* @size: If found, holds the size of the address.
*
* @start and @size are only updated if @name is found.
*
* Returns: 1 if found or 0 if not found.
*/
int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size)
{
struct reserve_mem_table *map;
guard(mutex)(&reserve_mem_lock);
map = reserve_mem_find_by_name_nolock(name);
if (!map)
return 0;
*start = map->start;
*size = map->size;
return 1;
}
EXPORT_SYMBOL_GPL(reserve_mem_find_by_name);
/**
* reserve_mem_release_by_name - Release reserved memory region with a given name
* @name: The name that is attatched to a reserved memory region
*
* Forcibly release the pages in the reserved memory region so that those memory
* can be used as free memory. After released the reserved region size becomes 0.
*
* Returns: 1 if released or 0 if not found.
*/
int reserve_mem_release_by_name(const char *name)
{
char buf[RESERVE_MEM_NAME_SIZE + 12];
struct reserve_mem_table *map;
void *start, *end;
guard(mutex)(&reserve_mem_lock);
map = reserve_mem_find_by_name_nolock(name);
if (!map)
return 0;
start = phys_to_virt(map->start);
end = start + map->size - 1;
snprintf(buf, sizeof(buf), "reserve_mem:%s", name);
free_reserved_area(start, end, 0, buf);
map->size = 0;
return 1;
}
/*
* Parse reserve_mem=nn:align:name
*/
static int __init reserve_mem(char *p)
{
phys_addr_t start, size, align, tmp;
char *name;
char *oldp;
int len;
if (!p)
return -EINVAL;
/* Check if there's room for more reserved memory */
if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES)
return -EBUSY;
oldp = p;
size = memparse(p, &p);
if (!size || p == oldp)
return -EINVAL;
if (*p != ':')
return -EINVAL;
align = memparse(p+1, &p);
if (*p != ':')
return -EINVAL;
/*
* memblock_phys_alloc() doesn't like a zero size align,
* but it is OK for this command to have it.
*/
if (align < SMP_CACHE_BYTES)
align = SMP_CACHE_BYTES;
name = p + 1;
len = strlen(name);
/* name needs to have length but not too big */
if (!len || len >= RESERVE_MEM_NAME_SIZE)
return -EINVAL;
/* Make sure that name has text */
for (p = name; *p; p++) {
if (!isspace(*p))
break;
}
if (!*p)
return -EINVAL;
/* Make sure the name is not already used */
if (reserve_mem_find_by_name(name, &start, &tmp))
return -EBUSY;
start = memblock_phys_alloc(size, align);
if (!start)
return -ENOMEM;
reserved_mem_add(start, size, name);
return 1;
}
__setup("reserve_mem=", reserve_mem);
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK)
static const char * const flagname[] = {
[ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG",
[ilog2(MEMBLOCK_MIRROR)] = "MIRROR",
[ilog2(MEMBLOCK_NOMAP)] = "NOMAP",
[ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG",
[ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT",
};
static int memblock_debug_show(struct seq_file *m, void *private)
{
struct memblock_type *type = m->private;
struct memblock_region *reg;
int i, j, nid;
unsigned int count = ARRAY_SIZE(flagname);
phys_addr_t end;
for (i = 0; i < type->cnt; i++) {
reg = &type->regions[i];
end = reg->base + reg->size - 1;
nid = memblock_get_region_node(reg);
seq_printf(m, "%4d: ", i);
seq_printf(m, "%pa..%pa ", ®->base, &end);
if (numa_valid_node(nid))
seq_printf(m, "%4d ", nid);
else
seq_printf(m, "%4c ", 'x');
if (reg->flags) {
for (j = 0; j < count; j++) {
if (reg->flags & (1U << j)) {
seq_printf(m, "%s\n", flagname[j]);
break;
}
}
if (j == count)
seq_printf(m, "%s\n", "UNKNOWN");
} else {
seq_printf(m, "%s\n", "NONE");
}
}
return 0;
}
DEFINE_SHOW_ATTRIBUTE(memblock_debug);
static int __init memblock_init_debugfs(void)
{
struct dentry *root = debugfs_create_dir("memblock", NULL);
debugfs_create_file("memory", 0444, root,
&memblock.memory, &memblock_debug_fops);
debugfs_create_file("reserved", 0444, root,
&memblock.reserved, &memblock_debug_fops);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
debugfs_create_file("physmem", 0444, root, &physmem,
&memblock_debug_fops);
#endif
return 0;
}
__initcall(memblock_init_debugfs);
#endif /* CONFIG_DEBUG_FS */
// SPDX-License-Identifier: GPL-2.0-only
/*
* lib/bitmap.c
* Helper functions for bitmap.h.
*/
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/ctype.h>
#include <linux/device.h>
#include <linux/export.h>
#include <linux/slab.h>
/**
* DOC: bitmap introduction
*
* bitmaps provide an array of bits, implemented using an
* array of unsigned longs. The number of valid bits in a
* given bitmap does _not_ need to be an exact multiple of
* BITS_PER_LONG.
*
* The possible unused bits in the last, partially used word
* of a bitmap are 'don't care'. The implementation makes
* no particular effort to keep them zero. It ensures that
* their value will not affect the results of any operation.
* The bitmap operations that return Boolean (bitmap_empty,
* for example) or scalar (bitmap_weight, for example) results
* carefully filter out these unused bits from impacting their
* results.
*
* The byte ordering of bitmaps is more natural on little
* endian architectures. See the big-endian headers
* include/asm-ppc64/bitops.h and include/asm-s390/bitops.h
* for the best explanations of this ordering.
*/
bool __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] != bitmap2[k])
return false;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return false;
return true;
}
EXPORT_SYMBOL(__bitmap_equal);
bool __bitmap_or_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2,
const unsigned long *bitmap3,
unsigned int bits)
{
unsigned int k, lim = bits / BITS_PER_LONG;
unsigned long tmp;
for (k = 0; k < lim; ++k) {
if ((bitmap1[k] | bitmap2[k]) != bitmap3[k])
return false;
}
if (!(bits % BITS_PER_LONG))
return true;
tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k];
return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0;
}
void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits)
{
unsigned int k, lim = BITS_TO_LONGS(bits);
for (k = 0; k < lim; ++k)
dst[k] = ~src[k];
}
EXPORT_SYMBOL(__bitmap_complement);
/**
* __bitmap_shift_right - logical right shift of the bits in a bitmap
* @dst : destination bitmap
* @src : source bitmap
* @shift : shift by this many bits
* @nbits : bitmap size, in bits
*
* Shifting right (dividing) means moving bits in the MS -> LS bit
* direction. Zeros are fed into the vacated MS positions and the
* LS bits shifted off the bottom are lost.
*/
void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
unsigned shift, unsigned nbits)
{
unsigned k, lim = BITS_TO_LONGS(nbits);
unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
unsigned long mask = BITMAP_LAST_WORD_MASK(nbits);
for (k = 0; off + k < lim; ++k) {
unsigned long upper, lower;
/*
* If shift is not word aligned, take lower rem bits of
* word above and make them the top rem bits of result.
*/
if (!rem || off + k + 1 >= lim)
upper = 0;
else {
upper = src[off + k + 1];
if (off + k + 1 == lim - 1)
upper &= mask;
upper <<= (BITS_PER_LONG - rem);
}
lower = src[off + k];
if (off + k == lim - 1)
lower &= mask;
lower >>= rem;
dst[k] = lower | upper;
}
if (off)
memset(&dst[lim - off], 0, off*sizeof(unsigned long));
}
EXPORT_SYMBOL(__bitmap_shift_right);
/**
* __bitmap_shift_left - logical left shift of the bits in a bitmap
* @dst : destination bitmap
* @src : source bitmap
* @shift : shift by this many bits
* @nbits : bitmap size, in bits
*
* Shifting left (multiplying) means moving bits in the LS -> MS
* direction. Zeros are fed into the vacated LS bit positions
* and those MS bits shifted off the top are lost.
*/
void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits)
{
int k;
unsigned int lim = BITS_TO_LONGS(nbits);
unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
for (k = lim - off - 1; k >= 0; --k) {
unsigned long upper, lower;
/*
* If shift is not word aligned, take upper rem bits of
* word below and make them the bottom rem bits of result.
*/
if (rem && k > 0)
lower = src[k - 1] >> (BITS_PER_LONG - rem);
else
lower = 0;
upper = src[k] << rem;
dst[k + off] = lower | upper;
}
if (off)
memset(dst, 0, off*sizeof(unsigned long));
}
EXPORT_SYMBOL(__bitmap_shift_left);
/**
* bitmap_cut() - remove bit region from bitmap and right shift remaining bits
* @dst: destination bitmap, might overlap with src
* @src: source bitmap
* @first: start bit of region to be removed
* @cut: number of bits to remove
* @nbits: bitmap size, in bits
*
* Set the n-th bit of @dst iff the n-th bit of @src is set and
* n is less than @first, or the m-th bit of @src is set for any
* m such that @first <= n < nbits, and m = n + @cut.
*
* In pictures, example for a big-endian 32-bit architecture:
*
* The @src bitmap is::
*
* 31 63
* | |
* 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101
* | | | |
* 16 14 0 32
*
* if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is::
*
* 31 63
* | |
* 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010
* | | |
* 14 (bit 17 0 32
* from @src)
*
* Note that @dst and @src might overlap partially or entirely.
*
* This is implemented in the obvious way, with a shift and carry
* step for each moved bit. Optimisation is left as an exercise
* for the compiler.
*/
void bitmap_cut(unsigned long *dst, const unsigned long *src,
unsigned int first, unsigned int cut, unsigned int nbits)
{
unsigned int len = BITS_TO_LONGS(nbits);
unsigned long keep = 0, carry;
int i;
if (first % BITS_PER_LONG) {
keep = src[first / BITS_PER_LONG] &
(~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG));
}
memmove(dst, src, len * sizeof(*dst));
while (cut--) {
for (i = first / BITS_PER_LONG; i < len; i++) {
if (i < len - 1)
carry = dst[i + 1] & 1UL;
else
carry = 0;
dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1));
}
}
dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG);
dst[first / BITS_PER_LONG] |= keep;
}
EXPORT_SYMBOL(bitmap_cut);
bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int lim = bits/BITS_PER_LONG;
unsigned long result = 0;
for (k = 0; k < lim; k++)
result |= (dst[k] = bitmap1[k] & bitmap2[k]);
if (bits % BITS_PER_LONG)
result |= (dst[k] = bitmap1[k] & bitmap2[k] &
BITMAP_LAST_WORD_MASK(bits));
return result != 0;
}
EXPORT_SYMBOL(__bitmap_and);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(bits);
for (k = 0; k < nr; k++)
dst[k] = bitmap1[k] | bitmap2[k];
}
EXPORT_SYMBOL(__bitmap_or);
void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(bits);
for (k = 0; k < nr; k++)
dst[k] = bitmap1[k] ^ bitmap2[k];
}
EXPORT_SYMBOL(__bitmap_xor);
bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int lim = bits/BITS_PER_LONG;
unsigned long result = 0;
for (k = 0; k < lim; k++)
result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
if (bits % BITS_PER_LONG)
result |= (dst[k] = bitmap1[k] & ~bitmap2[k] &
BITMAP_LAST_WORD_MASK(bits));
return result != 0;
}
EXPORT_SYMBOL(__bitmap_andnot);
void __bitmap_replace(unsigned long *dst,
const unsigned long *old, const unsigned long *new,
const unsigned long *mask, unsigned int nbits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(nbits);
for (k = 0; k < nr; k++)
dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]);
}
EXPORT_SYMBOL(__bitmap_replace);
bool __bitmap_intersects(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] & bitmap2[k])
return true;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return true;
return false;
}
EXPORT_SYMBOL(__bitmap_intersects);
bool __bitmap_subset(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] & ~bitmap2[k])
return false;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return false;
return true;
}
EXPORT_SYMBOL(__bitmap_subset);
#define BITMAP_WEIGHT(FETCH, bits) \
({ \
unsigned int __bits = (bits), idx, w = 0; \
\
for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \
w += hweight_long(FETCH); \
\
if (__bits % BITS_PER_LONG) \
w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \
\
w; \
})
unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
{
return BITMAP_WEIGHT(bitmap[idx], bits);
}
EXPORT_SYMBOL(__bitmap_weight);
unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits);
}
EXPORT_SYMBOL(__bitmap_weight_and);
unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits);
}
EXPORT_SYMBOL(__bitmap_weight_andnot);
void __bitmap_set(unsigned long *map, unsigned int start, int len)
{
unsigned long *p = map + BIT_WORD(start);
const unsigned int size = start + len;
int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
while (len - bits_to_set >= 0) {
*p |= mask_to_set;
len -= bits_to_set;
bits_to_set = BITS_PER_LONG;
mask_to_set = ~0UL;
p++;
}
if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size);
*p |= mask_to_set;
}
}
EXPORT_SYMBOL(__bitmap_set);
void __bitmap_clear(unsigned long *map, unsigned int start, int len)
{
unsigned long *p = map + BIT_WORD(start);
const unsigned int size = start + len;
int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
while (len - bits_to_clear >= 0) {
*p &= ~mask_to_clear;
len -= bits_to_clear;
bits_to_clear = BITS_PER_LONG;
mask_to_clear = ~0UL;
p++;
}
if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
*p &= ~mask_to_clear;
}
}
EXPORT_SYMBOL(__bitmap_clear);
/**
* bitmap_find_next_zero_area_off - find a contiguous aligned zero area
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @align_mask: Alignment mask for zero area
* @align_offset: Alignment offset for zero area.
*
* The @align_mask should be one less than a power of 2; the effect is that
* the bit offset of all zero areas this function finds plus @align_offset
* is multiple of that power of 2.
*/
unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask,
unsigned long align_offset)
{
unsigned long index, end, i;
again:
index = find_next_zero_bit(map, size, start);
/* Align allocation */
index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
end = index + nr;
if (end > size)
return end;
i = find_next_bit(map, end, index);
if (i < end) {
start = i + 1;
goto again;
}
return index;
}
EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
/**
* bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
* @buf: pointer to a bitmap
* @pos: a bit position in @buf (0 <= @pos < @nbits)
* @nbits: number of valid bit positions in @buf
*
* Map the bit at position @pos in @buf (of length @nbits) to the
* ordinal of which set bit it is. If it is not set or if @pos
* is not a valid bit position, map to -1.
*
* If for example, just bits 4 through 7 are set in @buf, then @pos
* values 4 through 7 will get mapped to 0 through 3, respectively,
* and other @pos values will get mapped to -1. When @pos value 7
* gets mapped to (returns) @ord value 3 in this example, that means
* that bit 7 is the 3rd (starting with 0th) set bit in @buf.
*
* The bit positions 0 through @bits are valid positions in @buf.
*/
static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits)
{
if (pos >= nbits || !test_bit(pos, buf))
return -1;
return bitmap_weight(buf, pos);
}
/**
* bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap
* @dst: remapped result
* @src: subset to be remapped
* @old: defines domain of map
* @new: defines range of map
* @nbits: number of bits in each of these bitmaps
*
* Let @old and @new define a mapping of bit positions, such that
* whatever position is held by the n-th set bit in @old is mapped
* to the n-th set bit in @new. In the more general case, allowing
* for the possibility that the weight 'w' of @new is less than the
* weight of @old, map the position of the n-th set bit in @old to
* the position of the m-th set bit in @new, where m == n % w.
*
* If either of the @old and @new bitmaps are empty, or if @src and
* @dst point to the same location, then this routine copies @src
* to @dst.
*
* The positions of unset bits in @old are mapped to themselves
* (the identity map).
*
* Apply the above specified mapping to @src, placing the result in
* @dst, clearing any bits previously set in @dst.
*
* For example, lets say that @old has bits 4 through 7 set, and
* @new has bits 12 through 15 set. This defines the mapping of bit
* position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
* bit positions unchanged. So if say @src comes into this routine
* with bits 1, 5 and 7 set, then @dst should leave with bits 1,
* 13 and 15 set.
*/
void bitmap_remap(unsigned long *dst, const unsigned long *src,
const unsigned long *old, const unsigned long *new,
unsigned int nbits)
{
unsigned int oldbit, w;
if (dst == src) /* following doesn't handle inplace remaps */
return;
bitmap_zero(dst, nbits);
w = bitmap_weight(new, nbits);
for_each_set_bit(oldbit, src, nbits) {
int n = bitmap_pos_to_ord(old, oldbit, nbits);
if (n < 0 || w == 0)
set_bit(oldbit, dst); /* identity map */
else
set_bit(find_nth_bit(new, nbits, n % w), dst);
}
}
EXPORT_SYMBOL(bitmap_remap);
/**
* bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit
* @oldbit: bit position to be mapped
* @old: defines domain of map
* @new: defines range of map
* @bits: number of bits in each of these bitmaps
*
* Let @old and @new define a mapping of bit positions, such that
* whatever position is held by the n-th set bit in @old is mapped
* to the n-th set bit in @new. In the more general case, allowing
* for the possibility that the weight 'w' of @new is less than the
* weight of @old, map the position of the n-th set bit in @old to
* the position of the m-th set bit in @new, where m == n % w.
*
* The positions of unset bits in @old are mapped to themselves
* (the identity map).
*
* Apply the above specified mapping to bit position @oldbit, returning
* the new bit position.
*
* For example, lets say that @old has bits 4 through 7 set, and
* @new has bits 12 through 15 set. This defines the mapping of bit
* position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
* bit positions unchanged. So if say @oldbit is 5, then this routine
* returns 13.
*/
int bitmap_bitremap(int oldbit, const unsigned long *old,
const unsigned long *new, int bits)
{
int w = bitmap_weight(new, bits);
int n = bitmap_pos_to_ord(old, oldbit, bits);
if (n < 0 || w == 0)
return oldbit;
else
return find_nth_bit(new, bits, n % w);
}
EXPORT_SYMBOL(bitmap_bitremap);
#ifdef CONFIG_NUMA
/**
* bitmap_onto - translate one bitmap relative to another
* @dst: resulting translated bitmap
* @orig: original untranslated bitmap
* @relmap: bitmap relative to which translated
* @bits: number of bits in each of these bitmaps
*
* Set the n-th bit of @dst iff there exists some m such that the
* n-th bit of @relmap is set, the m-th bit of @orig is set, and
* the n-th bit of @relmap is also the m-th _set_ bit of @relmap.
* (If you understood the previous sentence the first time your
* read it, you're overqualified for your current job.)
*
* In other words, @orig is mapped onto (surjectively) @dst,
* using the map { <n, m> | the n-th bit of @relmap is the
* m-th set bit of @relmap }.
*
* Any set bits in @orig above bit number W, where W is the
* weight of (number of set bits in) @relmap are mapped nowhere.
* In particular, if for all bits m set in @orig, m >= W, then
* @dst will end up empty. In situations where the possibility
* of such an empty result is not desired, one way to avoid it is
* to use the bitmap_fold() operator, below, to first fold the
* @orig bitmap over itself so that all its set bits x are in the
* range 0 <= x < W. The bitmap_fold() operator does this by
* setting the bit (m % W) in @dst, for each bit (m) set in @orig.
*
* Example [1] for bitmap_onto():
* Let's say @relmap has bits 30-39 set, and @orig has bits
* 1, 3, 5, 7, 9 and 11 set. Then on return from this routine,
* @dst will have bits 31, 33, 35, 37 and 39 set.
*
* When bit 0 is set in @orig, it means turn on the bit in
* @dst corresponding to whatever is the first bit (if any)
* that is turned on in @relmap. Since bit 0 was off in the
* above example, we leave off that bit (bit 30) in @dst.
*
* When bit 1 is set in @orig (as in the above example), it
* means turn on the bit in @dst corresponding to whatever
* is the second bit that is turned on in @relmap. The second
* bit in @relmap that was turned on in the above example was
* bit 31, so we turned on bit 31 in @dst.
*
* Similarly, we turned on bits 33, 35, 37 and 39 in @dst,
* because they were the 4th, 6th, 8th and 10th set bits
* set in @relmap, and the 4th, 6th, 8th and 10th bits of
* @orig (i.e. bits 3, 5, 7 and 9) were also set.
*
* When bit 11 is set in @orig, it means turn on the bit in
* @dst corresponding to whatever is the twelfth bit that is
* turned on in @relmap. In the above example, there were
* only ten bits turned on in @relmap (30..39), so that bit
* 11 was set in @orig had no affect on @dst.
*
* Example [2] for bitmap_fold() + bitmap_onto():
* Let's say @relmap has these ten bits set::
*
* 40 41 42 43 45 48 53 61 74 95
*
* (for the curious, that's 40 plus the first ten terms of the
* Fibonacci sequence.)
*
* Further lets say we use the following code, invoking
* bitmap_fold() then bitmap_onto, as suggested above to
* avoid the possibility of an empty @dst result::
*
* unsigned long *tmp; // a temporary bitmap's bits
*
* bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits);
* bitmap_onto(dst, tmp, relmap, bits);
*
* Then this table shows what various values of @dst would be, for
* various @orig's. I list the zero-based positions of each set bit.
* The tmp column shows the intermediate result, as computed by
* using bitmap_fold() to fold the @orig bitmap modulo ten
* (the weight of @relmap):
*
* =============== ============== =================
* @orig tmp @dst
* 0 0 40
* 1 1 41
* 9 9 95
* 10 0 40 [#f1]_
* 1 3 5 7 1 3 5 7 41 43 48 61
* 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45
* 0 9 18 27 0 9 8 7 40 61 74 95
* 0 10 20 30 0 40
* 0 11 22 33 0 1 2 3 40 41 42 43
* 0 12 24 36 0 2 4 6 40 42 45 53
* 78 102 211 1 2 8 41 42 74 [#f1]_
* =============== ============== =================
*
* .. [#f1]
*
* For these marked lines, if we hadn't first done bitmap_fold()
* into tmp, then the @dst result would have been empty.
*
* If either of @orig or @relmap is empty (no set bits), then @dst
* will be returned empty.
*
* If (as explained above) the only set bits in @orig are in positions
* m where m >= W, (where W is the weight of @relmap) then @dst will
* once again be returned empty.
*
* All bits in @dst not set by the above rule are cleared.
*/
void bitmap_onto(unsigned long *dst, const unsigned long *orig,
const unsigned long *relmap, unsigned int bits)
{
unsigned int n, m; /* same meaning as in above comment */
if (dst == orig) /* following doesn't handle inplace mappings */
return;
bitmap_zero(dst, bits);
/*
* The following code is a more efficient, but less
* obvious, equivalent to the loop:
* for (m = 0; m < bitmap_weight(relmap, bits); m++) {
* n = find_nth_bit(orig, bits, m);
* if (test_bit(m, orig))
* set_bit(n, dst);
* }
*/
m = 0;
for_each_set_bit(n, relmap, bits) {
/* m == bitmap_pos_to_ord(relmap, n, bits) */
if (test_bit(m, orig))
set_bit(n, dst);
m++;
}
}
/**
* bitmap_fold - fold larger bitmap into smaller, modulo specified size
* @dst: resulting smaller bitmap
* @orig: original larger bitmap
* @sz: specified size
* @nbits: number of bits in each of these bitmaps
*
* For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
* Clear all other bits in @dst. See further the comment and
* Example [2] for bitmap_onto() for why and how to use this.
*/
void bitmap_fold(unsigned long *dst, const unsigned long *orig,
unsigned int sz, unsigned int nbits)
{
unsigned int oldbit;
if (dst == orig) /* following doesn't handle inplace mappings */
return;
bitmap_zero(dst, nbits);
for_each_set_bit(oldbit, orig, nbits)
set_bit(oldbit % sz, dst);
}
#endif /* CONFIG_NUMA */
unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags)
{
return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long),
flags);
}
EXPORT_SYMBOL(bitmap_alloc);
unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags)
{
return bitmap_alloc(nbits, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(bitmap_zalloc);
unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node)
{
return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long),
flags, node);
}
EXPORT_SYMBOL(bitmap_alloc_node);
unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node)
{
return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node);
}
EXPORT_SYMBOL(bitmap_zalloc_node);
void bitmap_free(const unsigned long *bitmap)
{
kfree(bitmap);
}
EXPORT_SYMBOL(bitmap_free);
static void devm_bitmap_free(void *data)
{
unsigned long *bitmap = data;
bitmap_free(bitmap);
}
unsigned long *devm_bitmap_alloc(struct device *dev,
unsigned int nbits, gfp_t flags)
{
unsigned long *bitmap;
int ret;
bitmap = bitmap_alloc(nbits, flags);
if (!bitmap)
return NULL;
ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap);
if (ret)
return NULL;
return bitmap;
}
EXPORT_SYMBOL_GPL(devm_bitmap_alloc);
unsigned long *devm_bitmap_zalloc(struct device *dev,
unsigned int nbits, gfp_t flags)
{
return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO);
}
EXPORT_SYMBOL_GPL(devm_bitmap_zalloc);
#if BITS_PER_LONG == 64
/**
* bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap
* @bitmap: array of unsigned longs, the destination bitmap
* @buf: array of u32 (in host byte order), the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits)
{
unsigned int i, halfwords;
halfwords = DIV_ROUND_UP(nbits, 32);
for (i = 0; i < halfwords; i++) {
bitmap[i/2] = (unsigned long) buf[i];
if (++i < halfwords)
bitmap[i/2] |= ((unsigned long) buf[i]) << 32;
}
/* Clear tail bits in last word beyond nbits. */
if (nbits % BITS_PER_LONG)
bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits);
}
EXPORT_SYMBOL(bitmap_from_arr32);
/**
* bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits
* @buf: array of u32 (in host byte order), the dest bitmap
* @bitmap: array of unsigned longs, the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
{
unsigned int i, halfwords;
halfwords = DIV_ROUND_UP(nbits, 32);
for (i = 0; i < halfwords; i++) {
buf[i] = (u32) (bitmap[i/2] & UINT_MAX);
if (++i < halfwords)
buf[i] = (u32) (bitmap[i/2] >> 32);
}
/* Clear tail bits in last element of array beyond nbits. */
if (nbits % BITS_PER_LONG)
buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
}
EXPORT_SYMBOL(bitmap_to_arr32);
#endif
#if BITS_PER_LONG == 32
/**
* bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
* @bitmap: array of unsigned longs, the destination bitmap
* @buf: array of u64 (in host byte order), the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
{
int n;
for (n = nbits; n > 0; n -= 64) {
u64 val = *buf++;
*bitmap++ = val;
if (n > 32)
*bitmap++ = val >> 32;
}
/*
* Clear tail bits in the last word beyond nbits.
*
* Negative index is OK because here we point to the word next
* to the last word of the bitmap, except for nbits == 0, which
* is tested implicitly.
*/
if (nbits % BITS_PER_LONG)
bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
}
EXPORT_SYMBOL(bitmap_from_arr64);
/**
* bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
* @buf: array of u64 (in host byte order), the dest bitmap
* @bitmap: array of unsigned longs, the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
{
const unsigned long *end = bitmap + BITS_TO_LONGS(nbits);
while (bitmap < end) {
*buf = *bitmap++;
if (bitmap < end)
*buf |= (u64)(*bitmap++) << 32;
buf++;
}
/* Clear tail bits in the last element of array beyond nbits. */
if (nbits % 64)
buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0);
}
EXPORT_SYMBOL(bitmap_to_arr64);
#endif
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Ethernet-type device handling.
*
* Version: @(#)eth.c 1.0.7 05/25/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Florian La Roche, <rzsfl@rz.uni-sb.de>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
*
* Fixes:
* Mr Linux : Arp problems
* Alan Cox : Generic queue tidyup (very tiny here)
* Alan Cox : eth_header ntohs should be htons
* Alan Cox : eth_rebuild_header missing an htons and
* minor other things.
* Tegge : Arp bug fixes.
* Florian : Removed many unnecessary functions, code cleanup
* and changes for new arp and skbuff.
* Alan Cox : Redid header building to reflect new format.
* Alan Cox : ARP only when compiled with CONFIG_INET
* Greg Page : 802.2 and SNAP stuff.
* Alan Cox : MAC layer pointers/new format.
* Paul Gortmaker : eth_copy_and_sum shouldn't csum padding.
* Alan Cox : Protect against forwarding explosions with
* older network drivers and IFF_ALLMULTI.
* Christer Weinigel : Better rebuild header message.
* Andrew Morton : 26Feb01: kill ether_setup() - use netdev_boot_setup().
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/nvmem-consumer.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <linux/of_net.h>
#include <linux/pci.h>
#include <linux/property.h>
#include <net/dst.h>
#include <net/arp.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
#include <net/flow_dissector.h>
#include <net/gro.h>
#include <linux/uaccess.h>
#include <net/pkt_sched.h>
/**
* eth_header - create the Ethernet header
* @skb: buffer to alter
* @dev: source device
* @type: Ethernet type field
* @daddr: destination address (NULL leave destination address)
* @saddr: source address (NULL use device source address)
* @len: packet length (<= skb->len)
*
*
* Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length
* in here instead.
*/
int eth_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr, unsigned int len)
{
struct ethhdr *eth = skb_push(skb, ETH_HLEN);
if (type != ETH_P_802_3 && type != ETH_P_802_2)
eth->h_proto = htons(type);
else
eth->h_proto = htons(len);
/*
* Set the source hardware address.
*/
if (!saddr)
saddr = dev->dev_addr;
memcpy(eth->h_source, saddr, ETH_ALEN);
if (daddr) {
memcpy(eth->h_dest, daddr, ETH_ALEN);
return ETH_HLEN;
}
/*
* Anyway, the loopback-device should never use this function...
*/
if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) {
eth_zero_addr(eth->h_dest);
return ETH_HLEN;
}
return -ETH_HLEN;
}
EXPORT_SYMBOL(eth_header);
/**
* eth_get_headlen - determine the length of header for an ethernet frame
* @dev: pointer to network device
* @data: pointer to start of frame
* @len: total length of frame
*
* Make a best effort attempt to pull the length for all of the headers for
* a given frame in a linear buffer.
*/
u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len)
{
const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
const struct ethhdr *eth = (const struct ethhdr *)data;
struct flow_keys_basic keys;
/* this should never happen, but better safe than sorry */
if (unlikely(len < sizeof(*eth)))
return len;
/* parse any remaining L2/L3 headers, check for L4 */
if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data,
eth->h_proto, sizeof(*eth),
len, flags))
return max_t(u32, keys.control.thoff, sizeof(*eth));
/* parse for any L4 headers */
return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
}
EXPORT_SYMBOL(eth_get_headlen);
/**
* eth_type_trans - determine the packet's protocol ID.
* @skb: received socket data
* @dev: receiving network device
*
* The rule here is that we
* assume 802.3 if the type field is short enough to be a length.
* This is normal practice and works for any 'now in use' protocol.
*/
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
{
unsigned short _service_access_point;
const unsigned short *sap;
const struct ethhdr *eth;
skb->dev = dev;
skb_reset_mac_header(skb); eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev);
/*
* Some variants of DSA tagging don't have an ethertype field
* at all, so we check here whether one of those tagging
* variants has been configured on the receiving interface,
* and if so, set skb->protocol without looking at the packet.
*/
if (unlikely(netdev_uses_dsa(dev)))
return htons(ETH_P_XDSA);
if (likely(eth_proto_is_802_3(eth->h_proto)))
return eth->h_proto;
/*
* This is a magic hack to spot IPX packets. Older Novell breaks
* the protocol design and runs IPX over 802.3 without an 802.2 LLC
* layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
* won't work for fault tolerant netware but does for the rest.
*/
sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point);
if (sap && *sap == 0xFFFF)
return htons(ETH_P_802_3);
/*
* Real 802.2 LLC
*/
return htons(ETH_P_802_2);
}
EXPORT_SYMBOL(eth_type_trans);
/**
* eth_header_parse - extract hardware address from packet
* @skb: packet to extract header from
* @haddr: destination buffer
*/
int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
const struct ethhdr *eth = eth_hdr(skb);
memcpy(haddr, eth->h_source, ETH_ALEN);
return ETH_ALEN;
}
EXPORT_SYMBOL(eth_header_parse);
/**
* eth_header_cache - fill cache entry from neighbour
* @neigh: source neighbour
* @hh: destination cache entry
* @type: Ethernet type field
*
* Create an Ethernet header template from the neighbour.
*/
int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type)
{
struct ethhdr *eth;
const struct net_device *dev = neigh->dev;
eth = (struct ethhdr *)
(((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth))));
if (type == htons(ETH_P_802_3))
return -1;
eth->h_proto = type;
memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
memcpy(eth->h_dest, neigh->ha, ETH_ALEN);
/* Pairs with READ_ONCE() in neigh_resolve_output(),
* neigh_hh_output() and neigh_update_hhs().
*/
smp_store_release(&hh->hh_len, ETH_HLEN);
return 0;
}
EXPORT_SYMBOL(eth_header_cache);
/**
* eth_header_cache_update - update cache entry
* @hh: destination cache entry
* @dev: network device
* @haddr: new hardware address
*
* Called by Address Resolution module to notify changes in address.
*/
void eth_header_cache_update(struct hh_cache *hh,
const struct net_device *dev,
const unsigned char *haddr)
{
memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)),
haddr, ETH_ALEN);
}
EXPORT_SYMBOL(eth_header_cache_update);
/**
* eth_header_parse_protocol - extract protocol from L2 header
* @skb: packet to extract protocol from
*/
__be16 eth_header_parse_protocol(const struct sk_buff *skb)
{
const struct ethhdr *eth = eth_hdr(skb);
return eth->h_proto;
}
EXPORT_SYMBOL(eth_header_parse_protocol);
/**
* eth_prepare_mac_addr_change - prepare for mac change
* @dev: network device
* @p: socket address
*/
int eth_prepare_mac_addr_change(struct net_device *dev, void *p)
{
struct sockaddr *addr = p;
if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
return -EBUSY;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
return 0;
}
EXPORT_SYMBOL(eth_prepare_mac_addr_change);
/**
* eth_commit_mac_addr_change - commit mac change
* @dev: network device
* @p: socket address
*/
void eth_commit_mac_addr_change(struct net_device *dev, void *p)
{
struct sockaddr *addr = p;
eth_hw_addr_set(dev, addr->sa_data);
}
EXPORT_SYMBOL(eth_commit_mac_addr_change);
/**
* eth_mac_addr - set new Ethernet hardware address
* @dev: network device
* @p: socket address
*
* Change hardware address of device.
*
* This doesn't change hardware matching, so needs to be overridden
* for most real devices.
*/
int eth_mac_addr(struct net_device *dev, void *p)
{
int ret;
ret = eth_prepare_mac_addr_change(dev, p);
if (ret < 0)
return ret;
eth_commit_mac_addr_change(dev, p);
return 0;
}
EXPORT_SYMBOL(eth_mac_addr);
int eth_validate_addr(struct net_device *dev)
{
if (!is_valid_ether_addr(dev->dev_addr))
return -EADDRNOTAVAIL;
return 0;
}
EXPORT_SYMBOL(eth_validate_addr);
const struct header_ops eth_header_ops ____cacheline_aligned = {
.create = eth_header,
.parse = eth_header_parse,
.cache = eth_header_cache,
.cache_update = eth_header_cache_update,
.parse_protocol = eth_header_parse_protocol,
};
/**
* ether_setup - setup Ethernet network device
* @dev: network device
*
* Fill in the fields of the device structure with Ethernet-generic values.
*/
void ether_setup(struct net_device *dev)
{
dev->header_ops = ð_header_ops;
dev->type = ARPHRD_ETHER;
dev->hard_header_len = ETH_HLEN;
dev->min_header_len = ETH_HLEN;
dev->mtu = ETH_DATA_LEN;
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = ETH_DATA_LEN;
dev->addr_len = ETH_ALEN;
dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
dev->flags = IFF_BROADCAST|IFF_MULTICAST;
dev->priv_flags |= IFF_TX_SKB_SHARING;
eth_broadcast_addr(dev->broadcast);
}
EXPORT_SYMBOL(ether_setup);
/**
* alloc_etherdev_mqs - Allocates and sets up an Ethernet device
* @sizeof_priv: Size of additional driver-private structure to be allocated
* for this Ethernet device
* @txqs: The number of TX queues this device has.
* @rxqs: The number of RX queues this device has.
*
* Fill in the fields of the device structure with Ethernet-generic
* values. Basically does everything except registering the device.
*
* Constructs a new net device, complete with a private data area of
* size (sizeof_priv). A 32-byte (not bit) alignment is enforced for
* this private data area.
*/
struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
unsigned int rxqs)
{
return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_ENUM,
ether_setup, txqs, rxqs);
}
EXPORT_SYMBOL(alloc_etherdev_mqs);
ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
{
return sysfs_emit(buf, "%*phC\n", len, addr);
}
EXPORT_SYMBOL(sysfs_format_mac);
struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
{
const struct packet_offload *ptype;
unsigned int hlen, off_eth;
struct sk_buff *pp = NULL;
struct ethhdr *eh, *eh2;
struct sk_buff *p;
__be16 type;
int flush = 1;
off_eth = skb_gro_offset(skb);
hlen = off_eth + sizeof(*eh);
eh = skb_gro_header(skb, hlen, off_eth);
if (unlikely(!eh))
goto out;
flush = 0;
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
eh2 = (struct ethhdr *)(p->data + off_eth);
if (compare_ether_header(eh, eh2)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
type = eh->h_proto;
ptype = gro_find_receive_by_type(type);
if (ptype == NULL) {
flush = 1;
goto out;
}
skb_gro_pull(skb, sizeof(*eh));
skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
ipv6_gro_receive, inet_gro_receive,
head, skb);
out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(eth_gro_receive);
int eth_gro_complete(struct sk_buff *skb, int nhoff)
{
struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff);
__be16 type = eh->h_proto;
struct packet_offload *ptype;
int err = -ENOSYS;
if (skb->encapsulation)
skb_set_inner_mac_header(skb, nhoff);
ptype = gro_find_complete_by_type(type);
if (ptype != NULL)
err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
ipv6_gro_complete, inet_gro_complete,
skb, nhoff + sizeof(*eh));
return err;
}
EXPORT_SYMBOL(eth_gro_complete);
static struct packet_offload eth_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_TEB),
.priority = 10,
.callbacks = {
.gro_receive = eth_gro_receive,
.gro_complete = eth_gro_complete,
},
};
static int __init eth_offload_init(void)
{
dev_add_offload(ð_packet_offload);
return 0;
}
fs_initcall(eth_offload_init);
unsigned char * __weak arch_get_platform_mac_address(void)
{
return NULL;
}
int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
{
unsigned char *addr;
int ret;
ret = of_get_mac_address(dev->of_node, mac_addr);
if (!ret)
return 0;
addr = arch_get_platform_mac_address();
if (!addr)
return -ENODEV;
ether_addr_copy(mac_addr, addr);
return 0;
}
EXPORT_SYMBOL(eth_platform_get_mac_address);
/**
* platform_get_ethdev_address - Set netdev's MAC address from a given device
* @dev: Pointer to the device
* @netdev: Pointer to netdev to write the address to
*
* Wrapper around eth_platform_get_mac_address() which writes the address
* directly to netdev->dev_addr.
*/
int platform_get_ethdev_address(struct device *dev, struct net_device *netdev)
{
u8 addr[ETH_ALEN] __aligned(2);
int ret;
ret = eth_platform_get_mac_address(dev, addr);
if (!ret)
eth_hw_addr_set(netdev, addr);
return ret;
}
EXPORT_SYMBOL(platform_get_ethdev_address);
/**
* nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named
* 'mac-address' associated with given device.
*
* @dev: Device with which the mac-address cell is associated.
* @addrbuf: Buffer to which the MAC address will be copied on success.
*
* Returns 0 on success or a negative error number on failure.
*/
int nvmem_get_mac_address(struct device *dev, void *addrbuf)
{
struct nvmem_cell *cell;
const void *mac;
size_t len;
cell = nvmem_cell_get(dev, "mac-address");
if (IS_ERR(cell))
return PTR_ERR(cell);
mac = nvmem_cell_read(cell, &len);
nvmem_cell_put(cell);
if (IS_ERR(mac))
return PTR_ERR(mac);
if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
kfree(mac);
return -EINVAL;
}
ether_addr_copy(addrbuf, mac);
kfree(mac);
return 0;
}
static int fwnode_get_mac_addr(struct fwnode_handle *fwnode,
const char *name, char *addr)
{
int ret;
ret = fwnode_property_read_u8_array(fwnode, name, addr, ETH_ALEN);
if (ret)
return ret;
if (!is_valid_ether_addr(addr))
return -EINVAL;
return 0;
}
/**
* fwnode_get_mac_address - Get the MAC from the firmware node
* @fwnode: Pointer to the firmware node
* @addr: Address of buffer to store the MAC in
*
* Search the firmware node for the best MAC address to use. 'mac-address' is
* checked first, because that is supposed to contain to "most recent" MAC
* address. If that isn't set, then 'local-mac-address' is checked next,
* because that is the default address. If that isn't set, then the obsolete
* 'address' is checked, just in case we're using an old device tree.
*
* Note that the 'address' property is supposed to contain a virtual address of
* the register set, but some DTS files have redefined that property to be the
* MAC address.
*
* All-zero MAC addresses are rejected, because those could be properties that
* exist in the firmware tables, but were not updated by the firmware. For
* example, the DTS could define 'mac-address' and 'local-mac-address', with
* zero MAC addresses. Some older U-Boots only initialized 'local-mac-address'.
* In this case, the real MAC is in 'local-mac-address', and 'mac-address'
* exists but is all zeros.
*/
int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr)
{
if (!fwnode_get_mac_addr(fwnode, "mac-address", addr) ||
!fwnode_get_mac_addr(fwnode, "local-mac-address", addr) ||
!fwnode_get_mac_addr(fwnode, "address", addr))
return 0;
return -ENOENT;
}
EXPORT_SYMBOL(fwnode_get_mac_address);
/**
* device_get_mac_address - Get the MAC for a given device
* @dev: Pointer to the device
* @addr: Address of buffer to store the MAC in
*/
int device_get_mac_address(struct device *dev, char *addr)
{
return fwnode_get_mac_address(dev_fwnode(dev), addr);
}
EXPORT_SYMBOL(device_get_mac_address);
/**
* device_get_ethdev_address - Set netdev's MAC address from a given device
* @dev: Pointer to the device
* @netdev: Pointer to netdev to write the address to
*
* Wrapper around device_get_mac_address() which writes the address
* directly to netdev->dev_addr.
*/
int device_get_ethdev_address(struct device *dev, struct net_device *netdev)
{
u8 addr[ETH_ALEN];
int ret;
ret = device_get_mac_address(dev, addr);
if (!ret)
eth_hw_addr_set(netdev, addr);
return ret;
}
EXPORT_SYMBOL(device_get_ethdev_address);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2013-2017 ARM Limited, All Rights Reserved.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#define pr_fmt(fmt) "GICv3: " fmt
#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include <linux/kernel.h>
#include <linux/kstrtox.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/percpu.h>
#include <linux/refcount.h>
#include <linux/slab.h>
#include <linux/iopoll.h>
#include <linux/irqchip.h>
#include <linux/irqchip/arm-gic-common.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/irqchip/arm-gic-v3-prio.h>
#include <linux/irqchip/irq-partition-percpu.h>
#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/arm-smccc.h>
#include <asm/cputype.h>
#include <asm/exception.h>
#include <asm/smp_plat.h>
#include <asm/virt.h>
#include "irq-gic-common.h"
static u8 dist_prio_irq __ro_after_init = GICV3_PRIO_IRQ;
static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI;
#define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0)
#define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1)
#define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 2)
#define FLAGS_WORKAROUND_INSECURE (1ULL << 3)
#define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1)
static struct cpumask broken_rdists __read_mostly __maybe_unused;
struct redist_region {
void __iomem *redist_base;
phys_addr_t phys_base;
bool single_redist;
};
struct gic_chip_data {
struct fwnode_handle *fwnode;
phys_addr_t dist_phys_base;
void __iomem *dist_base;
struct redist_region *redist_regions;
struct rdists rdists;
struct irq_domain *domain;
u64 redist_stride;
u32 nr_redist_regions;
u64 flags;
bool has_rss;
unsigned int ppi_nr;
struct partition_desc **ppi_descs;
};
#define T241_CHIPS_MAX 4
static void __iomem *t241_dist_base_alias[T241_CHIPS_MAX] __read_mostly;
static DEFINE_STATIC_KEY_FALSE(gic_nvidia_t241_erratum);
static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum);
static struct gic_chip_data gic_data __read_mostly;
static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
#define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
#define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
static bool nmi_support_forbidden;
/*
* There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs
* are potentially stolen by the secure side. Some code, especially code dealing
* with hwirq IDs, is simplified by accounting for all 16.
*/
#define SGI_NR 16
/*
* The behaviours of RPR and PMR registers differ depending on the value of
* SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the
* distributor and redistributors depends on whether security is enabled in the
* GIC.
*
* When security is enabled, non-secure priority values from the (re)distributor
* are presented to the GIC CPUIF as follow:
* (GIC_(R)DIST_PRI[irq] >> 1) | 0x80;
*
* If SCR_EL3.FIQ == 1, the values written to/read from PMR and RPR at non-secure
* EL1 are subject to a similar operation thus matching the priorities presented
* from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0,
* these values are unchanged by the GIC.
*
* see GICv3/GICv4 Architecture Specification (IHI0069D):
* - section 4.8.1 Non-secure accesses to register fields for Secure interrupt
* priorities.
* - Figure 4-7 Secure read of the priority field for a Non-secure Group 1
* interrupt.
*/
static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
static u32 gic_get_pribits(void)
{
u32 pribits;
pribits = gic_read_ctlr();
pribits &= ICC_CTLR_EL1_PRI_BITS_MASK;
pribits >>= ICC_CTLR_EL1_PRI_BITS_SHIFT;
pribits++;
return pribits;
}
static bool gic_has_group0(void)
{
u32 val;
u32 old_pmr;
old_pmr = gic_read_pmr();
/*
* Let's find out if Group0 is under control of EL3 or not by
* setting the highest possible, non-zero priority in PMR.
*
* If SCR_EL3.FIQ is set, the priority gets shifted down in
* order for the CPU interface to set bit 7, and keep the
* actual priority in the non-secure range. In the process, it
* looses the least significant bit and the actual priority
* becomes 0x80. Reading it back returns 0, indicating that
* we're don't have access to Group0.
*/
gic_write_pmr(BIT(8 - gic_get_pribits()));
val = gic_read_pmr();
gic_write_pmr(old_pmr);
return val != 0;
}
static inline bool gic_dist_security_disabled(void)
{
return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS;
}
static bool cpus_have_security_disabled __ro_after_init;
static bool cpus_have_group0 __ro_after_init;
static void __init gic_prio_init(void)
{
bool ds;
cpus_have_group0 = gic_has_group0();
ds = gic_dist_security_disabled();
if ((gic_data.flags & FLAGS_WORKAROUND_INSECURE) && !ds) {
if (cpus_have_group0) {
u32 val;
val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
val |= GICD_CTLR_DS;
writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
ds = gic_dist_security_disabled();
if (ds)
pr_warn("Broken GIC integration, security disabled\n");
} else {
pr_warn("Broken GIC integration, pNMI forbidden\n");
nmi_support_forbidden = true;
}
}
cpus_have_security_disabled = ds;
/*
* How priority values are used by the GIC depends on two things:
* the security state of the GIC (controlled by the GICD_CTRL.DS bit)
* and if Group 0 interrupts can be delivered to Linux in the non-secure
* world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the
* way priorities are presented in ICC_PMR_EL1 and in the distributor:
*
* GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Distributor
* -------------------------------------------------------
* 1 | - | unchanged | unchanged
* -------------------------------------------------------
* 0 | 1 | non-secure | non-secure
* -------------------------------------------------------
* 0 | 0 | unchanged | non-secure
*
* In the non-secure view reads and writes are modified:
*
* - A value written is right-shifted by one and the MSB is set,
* forcing the priority into the non-secure range.
*
* - A value read is left-shifted by one.
*
* In the first two cases, where ICC_PMR_EL1 and the interrupt priority
* are both either modified or unchanged, we can use the same set of
* priorities.
*
* In the last case, where only the interrupt priorities are modified to
* be in the non-secure range, we program the non-secure values into
* the distributor to match the PMR values we want.
*/
if (cpus_have_group0 && !cpus_have_security_disabled) {
dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq);
dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi);
}
pr_info("GICD_CTRL.DS=%d, SCR_EL3.FIQ=%d\n",
cpus_have_security_disabled,
!cpus_have_group0);
}
/* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */
static refcount_t *rdist_nmi_refs;
static struct gic_kvm_info gic_v3_kvm_info __initdata;
static DEFINE_PER_CPU(bool, has_rss);
#define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4)
#define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist))
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
#define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K)
/* Our default, arbitrary priority value. Linux only uses one anyway. */
#define DEFAULT_PMR_VALUE 0xf0
enum gic_intid_range {
SGI_RANGE,
PPI_RANGE,
SPI_RANGE,
EPPI_RANGE,
ESPI_RANGE,
LPI_RANGE,
__INVALID_RANGE__
};
static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq)
{ switch (hwirq) {
case 0 ... 15:
return SGI_RANGE;
case 16 ... 31:
return PPI_RANGE;
case 32 ... 1019:
return SPI_RANGE;
case EPPI_BASE_INTID ... (EPPI_BASE_INTID + 63):
return EPPI_RANGE;
case ESPI_BASE_INTID ... (ESPI_BASE_INTID + 1023):
return ESPI_RANGE;
case 8192 ... GENMASK(23, 0):
return LPI_RANGE;
default:
return __INVALID_RANGE__;
}
}
static enum gic_intid_range get_intid_range(struct irq_data *d)
{
return __get_intid_range(d->hwirq);
}
static inline bool gic_irq_in_rdist(struct irq_data *d)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
return true;
default:
return false;
}
}
static inline void __iomem *gic_dist_base_alias(struct irq_data *d)
{
if (static_branch_unlikely(&gic_nvidia_t241_erratum)) {
irq_hw_number_t hwirq = irqd_to_hwirq(d);
u32 chip;
/*
* For the erratum T241-FABRIC-4, read accesses to GICD_In{E}
* registers are directed to the chip that owns the SPI. The
* the alias region can also be used for writes to the
* GICD_In{E} except GICD_ICENABLERn. Each chip has support
* for 320 {E}SPIs. Mappings for all 4 chips:
* Chip0 = 32-351
* Chip1 = 352-671
* Chip2 = 672-991
* Chip3 = 4096-4415
*/
switch (__get_intid_range(hwirq)) {
case SPI_RANGE:
chip = (hwirq - 32) / 320;
break;
case ESPI_RANGE:
chip = 3;
break;
default:
unreachable();
}
return t241_dist_base_alias[chip];
}
return gic_data.dist_base;
}
static inline void __iomem *gic_dist_base(struct irq_data *d)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
/* SGI+PPI -> SGI_base for this CPU */
return gic_data_rdist_sgi_base();
case SPI_RANGE:
case ESPI_RANGE:
/* SPI -> dist_base */
return gic_data.dist_base;
default:
return NULL;
}
}
static void gic_do_wait_for_rwp(void __iomem *base, u32 bit)
{
u32 val;
int ret;
ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit),
1, USEC_PER_SEC);
if (ret == -ETIMEDOUT)
pr_err_ratelimited("RWP timeout, gone fishing\n");
}
/* Wait for completion of a distributor change */
static void gic_dist_wait_for_rwp(void)
{
gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP);
}
/* Wait for completion of a redistributor change */
static void gic_redist_wait_for_rwp(void)
{
gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP);
}
static void gic_enable_redist(bool enable)
{
void __iomem *rbase;
u32 val;
int ret;
if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996)
return;
rbase = gic_data_rdist_rd_base();
val = readl_relaxed(rbase + GICR_WAKER);
if (enable)
/* Wake up this CPU redistributor */
val &= ~GICR_WAKER_ProcessorSleep;
else
val |= GICR_WAKER_ProcessorSleep;
writel_relaxed(val, rbase + GICR_WAKER);
if (!enable) { /* Check that GICR_WAKER is writeable */
val = readl_relaxed(rbase + GICR_WAKER);
if (!(val & GICR_WAKER_ProcessorSleep))
return; /* No PM support in this redistributor */
}
ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val,
enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep),
1, USEC_PER_SEC);
if (ret == -ETIMEDOUT) {
pr_err_ratelimited("redistributor failed to %s...\n",
enable ? "wakeup" : "sleep");
}
}
/*
* Routines to disable, enable, EOI and route interrupts
*/
static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index)
{
switch (get_intid_range(d)) {
case SGI_RANGE:
case PPI_RANGE:
case SPI_RANGE:
*index = d->hwirq;
return offset;
case EPPI_RANGE:
/*
* Contrary to the ESPI range, the EPPI range is contiguous
* to the PPI range in the registers, so let's adjust the
* displacement accordingly. Consistency is overrated.
*/
*index = d->hwirq - EPPI_BASE_INTID + 32;
return offset;
case ESPI_RANGE:
*index = d->hwirq - ESPI_BASE_INTID;
switch (offset) {
case GICD_ISENABLER:
return GICD_ISENABLERnE;
case GICD_ICENABLER:
return GICD_ICENABLERnE;
case GICD_ISPENDR:
return GICD_ISPENDRnE;
case GICD_ICPENDR:
return GICD_ICPENDRnE;
case GICD_ISACTIVER:
return GICD_ISACTIVERnE;
case GICD_ICACTIVER:
return GICD_ICACTIVERnE;
case GICD_IPRIORITYR:
return GICD_IPRIORITYRnE;
case GICD_ICFGR:
return GICD_ICFGRnE;
case GICD_IROUTER:
return GICD_IROUTERnE;
default:
break;
}
break;
default:
break;
}
WARN_ON(1);
*index = d->hwirq;
return offset;
}
static int gic_peek_irq(struct irq_data *d, u32 offset)
{
void __iomem *base;
u32 index, mask;
offset = convert_offset_index(d, offset, &index);
mask = 1 << (index % 32);
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_dist_base_alias(d);
return !!(readl_relaxed(base + offset + (index / 32) * 4) & mask);
}
static void gic_poke_irq(struct irq_data *d, u32 offset)
{
void __iomem *base;
u32 index, mask;
offset = convert_offset_index(d, offset, &index);
mask = 1 << (index % 32);
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_data.dist_base;
writel_relaxed(mask, base + offset + (index / 32) * 4);
}
static void gic_mask_irq(struct irq_data *d)
{
gic_poke_irq(d, GICD_ICENABLER);
if (gic_irq_in_rdist(d))
gic_redist_wait_for_rwp();
else
gic_dist_wait_for_rwp();
}
static void gic_eoimode1_mask_irq(struct irq_data *d)
{
gic_mask_irq(d);
/*
* When masking a forwarded interrupt, make sure it is
* deactivated as well.
*
* This ensures that an interrupt that is getting
* disabled/masked will not get "stuck", because there is
* noone to deactivate it (guest is being terminated).
*/
if (irqd_is_forwarded_to_vcpu(d))
gic_poke_irq(d, GICD_ICACTIVER);
}
static void gic_unmask_irq(struct irq_data *d)
{
gic_poke_irq(d, GICD_ISENABLER);
}
static inline bool gic_supports_nmi(void)
{
return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
static_branch_likely(&supports_pseudo_nmis);
}
static int gic_irq_set_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool val)
{
u32 reg;
if (d->hwirq >= 8192) /* SGI/PPI/SPI only */
return -EINVAL;
switch (which) {
case IRQCHIP_STATE_PENDING:
reg = val ? GICD_ISPENDR : GICD_ICPENDR;
break;
case IRQCHIP_STATE_ACTIVE:
reg = val ? GICD_ISACTIVER : GICD_ICACTIVER;
break;
case IRQCHIP_STATE_MASKED:
if (val) { gic_mask_irq(d);
return 0;
}
reg = GICD_ISENABLER;
break;
default:
return -EINVAL;
}
gic_poke_irq(d, reg);
/*
* Force read-back to guarantee that the active state has taken
* effect, and won't race with a guest-driven deactivation.
*/
if (reg == GICD_ISACTIVER)
gic_peek_irq(d, reg);
return 0;
}
static int gic_irq_get_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool *val)
{
if (d->hwirq >= 8192) /* PPI/SPI only */
return -EINVAL;
switch (which) {
case IRQCHIP_STATE_PENDING:
*val = gic_peek_irq(d, GICD_ISPENDR);
break;
case IRQCHIP_STATE_ACTIVE:
*val = gic_peek_irq(d, GICD_ISACTIVER);
break;
case IRQCHIP_STATE_MASKED:
*val = !gic_peek_irq(d, GICD_ISENABLER);
break;
default:
return -EINVAL;
}
return 0;
}
static void gic_irq_set_prio(struct irq_data *d, u8 prio)
{
void __iomem *base = gic_dist_base(d);
u32 offset, index;
offset = convert_offset_index(d, GICD_IPRIORITYR, &index);
writeb_relaxed(prio, base + offset + index);
}
static u32 __gic_get_ppi_index(irq_hw_number_t hwirq)
{
switch (__get_intid_range(hwirq)) {
case PPI_RANGE:
return hwirq - 16;
case EPPI_RANGE:
return hwirq - EPPI_BASE_INTID + 16;
default:
unreachable();
}
}
static u32 __gic_get_rdist_index(irq_hw_number_t hwirq)
{
switch (__get_intid_range(hwirq)) {
case SGI_RANGE:
case PPI_RANGE:
return hwirq;
case EPPI_RANGE:
return hwirq - EPPI_BASE_INTID + 32;
default:
unreachable();
}
}
static u32 gic_get_rdist_index(struct irq_data *d)
{
return __gic_get_rdist_index(d->hwirq);
}
static int gic_irq_nmi_setup(struct irq_data *d)
{
struct irq_desc *desc = irq_to_desc(d->irq);
if (!gic_supports_nmi())
return -EINVAL;
if (gic_peek_irq(d, GICD_ISENABLER)) {
pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq);
return -EINVAL;
}
/*
* A secondary irq_chip should be in charge of LPI request,
* it should not be possible to get there
*/
if (WARN_ON(irqd_to_hwirq(d) >= 8192))
return -EINVAL;
/* desc lock should already be held */
if (gic_irq_in_rdist(d)) {
u32 idx = gic_get_rdist_index(d);
/*
* Setting up a percpu interrupt as NMI, only switch handler
* for first NMI
*/
if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) {
refcount_set(&rdist_nmi_refs[idx], 1);
desc->handle_irq = handle_percpu_devid_fasteoi_nmi;
}
} else {
desc->handle_irq = handle_fasteoi_nmi;
}
gic_irq_set_prio(d, dist_prio_nmi);
return 0;
}
static void gic_irq_nmi_teardown(struct irq_data *d)
{
struct irq_desc *desc = irq_to_desc(d->irq);
if (WARN_ON(!gic_supports_nmi()))
return;
if (gic_peek_irq(d, GICD_ISENABLER)) {
pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq);
return;
}
/*
* A secondary irq_chip should be in charge of LPI request,
* it should not be possible to get there
*/
if (WARN_ON(irqd_to_hwirq(d) >= 8192))
return;
/* desc lock should already be held */
if (gic_irq_in_rdist(d)) {
u32 idx = gic_get_rdist_index(d);
/* Tearing down NMI, only switch handler for last NMI */
if (refcount_dec_and_test(&rdist_nmi_refs[idx]))
desc->handle_irq = handle_percpu_devid_irq;
} else {
desc->handle_irq = handle_fasteoi_irq;
}
gic_irq_set_prio(d, dist_prio_irq);
}
static bool gic_arm64_erratum_2941627_needed(struct irq_data *d)
{
enum gic_intid_range range;
if (!static_branch_unlikely(&gic_arm64_2941627_erratum))
return false;
range = get_intid_range(d);
/*
* The workaround is needed if the IRQ is an SPI and
* the target cpu is different from the one we are
* executing on.
*/
return (range == SPI_RANGE || range == ESPI_RANGE) &&
!cpumask_test_cpu(raw_smp_processor_id(),
irq_data_get_effective_affinity_mask(d));
}
static void gic_eoi_irq(struct irq_data *d)
{
write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1);
isb();
if (gic_arm64_erratum_2941627_needed(d)) {
/*
* Make sure the GIC stream deactivate packet
* issued by ICC_EOIR1_EL1 has completed before
* deactivating through GICD_IACTIVER.
*/
dsb(sy);
gic_poke_irq(d, GICD_ICACTIVER);
}
}
static void gic_eoimode1_eoi_irq(struct irq_data *d)
{
/*
* No need to deactivate an LPI, or an interrupt that
* is is getting forwarded to a vcpu.
*/
if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
return;
if (!gic_arm64_erratum_2941627_needed(d))
gic_write_dir(irqd_to_hwirq(d));
else
gic_poke_irq(d, GICD_ICACTIVER);
}
static int gic_set_type(struct irq_data *d, unsigned int type)
{
irq_hw_number_t irq = irqd_to_hwirq(d);
enum gic_intid_range range;
void __iomem *base;
u32 offset, index;
int ret;
range = get_intid_range(d);
/* Interrupt configuration for SGIs can't be changed */
if (range == SGI_RANGE)
return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0;
/* SPIs have restrictions on the supported types */
if ((range == SPI_RANGE || range == ESPI_RANGE) &&
type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
return -EINVAL;
if (gic_irq_in_rdist(d))
base = gic_data_rdist_sgi_base();
else
base = gic_dist_base_alias(d);
offset = convert_offset_index(d, GICD_ICFGR, &index);
ret = gic_configure_irq(index, type, base + offset);
if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) {
/* Misconfigured PPIs are usually not fatal */
pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq);
ret = 0;
}
return ret;
}
static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
{
if (get_intid_range(d) == SGI_RANGE)
return -EINVAL;
if (vcpu)
irqd_set_forwarded_to_vcpu(d);
else
irqd_clr_forwarded_to_vcpu(d);
return 0;
}
static u64 gic_cpu_to_affinity(int cpu)
{
u64 mpidr = cpu_logical_map(cpu);
u64 aff;
/* ASR8601 needs to have its affinities shifted down... */
if (unlikely(gic_data.flags & FLAGS_WORKAROUND_ASR_ERRATUM_8601001)) mpidr = (MPIDR_AFFINITY_LEVEL(mpidr, 1) |
(MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8));
aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
MPIDR_AFFINITY_LEVEL(mpidr, 0));
return aff;
}
static void gic_deactivate_unhandled(u32 irqnr)
{
if (static_branch_likely(&supports_deactivate_key)) {
if (irqnr < 8192)
gic_write_dir(irqnr);
} else {
write_gicreg(irqnr, ICC_EOIR1_EL1);
isb();
}
}
/*
* Follow a read of the IAR with any HW maintenance that needs to happen prior
* to invoking the relevant IRQ handler. We must do two things:
*
* (1) Ensure instruction ordering between a read of IAR and subsequent
* instructions in the IRQ handler using an ISB.
*
* It is possible for the IAR to report an IRQ which was signalled *after*
* the CPU took an IRQ exception as multiple interrupts can race to be
* recognized by the GIC, earlier interrupts could be withdrawn, and/or
* later interrupts could be prioritized by the GIC.
*
* For devices which are tightly coupled to the CPU, such as PMUs, a
* context synchronization event is necessary to ensure that system
* register state is not stale, as these may have been indirectly written
* *after* exception entry.
*
* (2) Execute an interrupt priority drop when EOI mode 1 is in use.
*/
static inline void gic_complete_ack(u32 irqnr)
{
if (static_branch_likely(&supports_deactivate_key))
write_gicreg(irqnr, ICC_EOIR1_EL1);
isb();
}
static bool gic_rpr_is_nmi_prio(void)
{
if (!gic_supports_nmi())
return false;
return unlikely(gic_read_rpr() == GICV3_PRIO_NMI);
}
static bool gic_irqnr_is_special(u32 irqnr)
{
return irqnr >= 1020 && irqnr <= 1023;
}
static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs)
{
if (gic_irqnr_is_special(irqnr))
return;
gic_complete_ack(irqnr);
if (generic_handle_domain_irq(gic_data.domain, irqnr)) {
WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr);
gic_deactivate_unhandled(irqnr);
}
}
static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs)
{
if (gic_irqnr_is_special(irqnr))
return;
gic_complete_ack(irqnr);
if (generic_handle_domain_nmi(gic_data.domain, irqnr)) {
WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr);
gic_deactivate_unhandled(irqnr);
}
}
/*
* An exception has been taken from a context with IRQs enabled, and this could
* be an IRQ or an NMI.
*
* The entry code called us with DAIF.IF set to keep NMIs masked. We must clear
* DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning,
* after handling any NMI but before handling any IRQ.
*
* The entry code has performed IRQ entry, and if an NMI is detected we must
* perform NMI entry/exit around invoking the handler.
*/
static void __gic_handle_irq_from_irqson(struct pt_regs *regs)
{
bool is_nmi;
u32 irqnr;
irqnr = gic_read_iar();
is_nmi = gic_rpr_is_nmi_prio();
if (is_nmi) {
nmi_enter();
__gic_handle_nmi(irqnr, regs);
nmi_exit();
}
if (gic_prio_masking_enabled()) {
gic_pmr_mask_irqs();
gic_arch_enable_irqs();
}
if (!is_nmi)
__gic_handle_irq(irqnr, regs);
}
/*
* An exception has been taken from a context with IRQs disabled, which can only
* be an NMI.
*
* The entry code called us with DAIF.IF set to keep NMIs masked. We must leave
* DAIF.IF (and ICC_PMR_EL1) unchanged.
*
* The entry code has performed NMI entry.
*/
static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs)
{
u64 pmr;
u32 irqnr;
/*
* We were in a context with IRQs disabled. However, the
* entry code has set PMR to a value that allows any
* interrupt to be acknowledged, and not just NMIs. This can
* lead to surprising effects if the NMI has been retired in
* the meantime, and that there is an IRQ pending. The IRQ
* would then be taken in NMI context, something that nobody
* wants to debug twice.
*
* Until we sort this, drop PMR again to a level that will
* actually only allow NMIs before reading IAR, and then
* restore it to what it was.
*/
pmr = gic_read_pmr();
gic_pmr_mask_irqs();
isb();
irqnr = gic_read_iar();
gic_write_pmr(pmr);
__gic_handle_nmi(irqnr, regs);
}
static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs)))
__gic_handle_irq_from_irqsoff(regs);
else
__gic_handle_irq_from_irqson(regs);
}
static void __init gic_dist_init(void)
{
unsigned int i;
u64 affinity;
void __iomem *base = gic_data.dist_base;
u32 val;
/* Disable the distributor */
writel_relaxed(0, base + GICD_CTLR);
gic_dist_wait_for_rwp();
/*
* Configure SPIs as non-secure Group-1. This will only matter
* if the GIC only has a single security state. This will not
* do the right thing if the kernel is running in secure mode,
* but that's not the intended use case anyway.
*/
for (i = 32; i < GIC_LINE_NR; i += 32)
writel_relaxed(~0, base + GICD_IGROUPR + i / 8);
/* Extended SPI range, not handled by the GICv2/GICv3 common code */
for (i = 0; i < GIC_ESPI_NR; i += 32) {
writel_relaxed(~0U, base + GICD_ICENABLERnE + i / 8);
writel_relaxed(~0U, base + GICD_ICACTIVERnE + i / 8);
}
for (i = 0; i < GIC_ESPI_NR; i += 32)
writel_relaxed(~0U, base + GICD_IGROUPRnE + i / 8);
for (i = 0; i < GIC_ESPI_NR; i += 16)
writel_relaxed(0, base + GICD_ICFGRnE + i / 4);
for (i = 0; i < GIC_ESPI_NR; i += 4)
writel_relaxed(REPEAT_BYTE_U32(dist_prio_irq),
base + GICD_IPRIORITYRnE + i);
/* Now do the common stuff */
gic_dist_config(base, GIC_LINE_NR, dist_prio_irq);
val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1;
if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) {
pr_info("Enabling SGIs without active state\n");
val |= GICD_CTLR_nASSGIreq;
}
/* Enable distributor with ARE, Group1, and wait for it to drain */
writel_relaxed(val, base + GICD_CTLR);
gic_dist_wait_for_rwp();
/*
* Set all global interrupts to the boot CPU only. ARE must be
* enabled.
*/
affinity = gic_cpu_to_affinity(smp_processor_id());
for (i = 32; i < GIC_LINE_NR; i++)
gic_write_irouter(affinity, base + GICD_IROUTER + i * 8);
for (i = 0; i < GIC_ESPI_NR; i++)
gic_write_irouter(affinity, base + GICD_IROUTERnE + i * 8);
}
static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *))
{
int ret = -ENODEV;
int i;
for (i = 0; i < gic_data.nr_redist_regions; i++) {
void __iomem *ptr = gic_data.redist_regions[i].redist_base;
u64 typer;
u32 reg;
reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
if (reg != GIC_PIDR2_ARCH_GICv3 &&
reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
pr_warn("No redistributor present @%p\n", ptr);
break;
}
do {
typer = gic_read_typer(ptr + GICR_TYPER);
ret = fn(gic_data.redist_regions + i, ptr);
if (!ret)
return 0;
if (gic_data.redist_regions[i].single_redist)
break;
if (gic_data.redist_stride) {
ptr += gic_data.redist_stride;
} else {
ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
if (typer & GICR_TYPER_VLPIS)
ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
}
} while (!(typer & GICR_TYPER_LAST));
}
return ret ? -ENODEV : 0;
}
static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr)
{
unsigned long mpidr;
u64 typer;
u32 aff;
/*
* Convert affinity to a 32bit value that can be matched to
* GICR_TYPER bits [63:32].
*/
mpidr = gic_cpu_to_affinity(smp_processor_id());
aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
MPIDR_AFFINITY_LEVEL(mpidr, 0));
typer = gic_read_typer(ptr + GICR_TYPER);
if ((typer >> 32) == aff) {
u64 offset = ptr - region->redist_base;
raw_spin_lock_init(&gic_data_rdist()->rd_lock);
gic_data_rdist_rd_base() = ptr;
gic_data_rdist()->phys_base = region->phys_base + offset;
pr_info("CPU%d: found redistributor %lx region %d:%pa\n",
smp_processor_id(), mpidr,
(int)(region - gic_data.redist_regions),
&gic_data_rdist()->phys_base);
return 0;
}
/* Try next one */
return 1;
}
static int gic_populate_rdist(void)
{
if (gic_iterate_rdists(__gic_populate_rdist) == 0)
return 0;
/* We couldn't even deal with ourselves... */
WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n",
smp_processor_id(),
(unsigned long)cpu_logical_map(smp_processor_id()));
return -ENODEV;
}
static int __gic_update_rdist_properties(struct redist_region *region,
void __iomem *ptr)
{
u64 typer = gic_read_typer(ptr + GICR_TYPER);
u32 ctlr = readl_relaxed(ptr + GICR_CTLR);
/* Boot-time cleanup */
if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) {
u64 val;
/* Deactivate any present vPE */
val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER);
if (val & GICR_VPENDBASER_Valid)
gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast,
ptr + SZ_128K + GICR_VPENDBASER);
/* Mark the VPE table as invalid */
val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER);
val &= ~GICR_VPROPBASER_4_1_VALID;
gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER);
}
gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS);
/*
* TYPER.RVPEID implies some form of DirectLPI, no matter what the
* doc says... :-/ And CTLR.IR implies another subset of DirectLPI
* that the ITS driver can make use of for LPIs (and not VLPIs).
*
* These are 3 different ways to express the same thing, depending
* on the revision of the architecture and its relaxations over
* time. Just group them under the 'direct_lpi' banner.
*/
gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
!!(ctlr & GICR_CTLR_IR) |
gic_data.rdists.has_rvpeid);
gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY);
/* Detect non-sensical configurations */
if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
gic_data.rdists.has_direct_lpi = false;
gic_data.rdists.has_vlpis = false;
gic_data.rdists.has_rvpeid = false;
}
gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr);
return 1;
}
static void gic_update_rdist_properties(void)
{
gic_data.ppi_nr = UINT_MAX;
gic_iterate_rdists(__gic_update_rdist_properties);
if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
gic_data.ppi_nr = 0;
pr_info("GICv3 features: %d PPIs%s%s\n",
gic_data.ppi_nr,
gic_data.has_rss ? ", RSS" : "",
gic_data.rdists.has_direct_lpi ? ", DirectLPI" : "");
if (gic_data.rdists.has_vlpis)
pr_info("GICv4 features: %s%s%s\n",
gic_data.rdists.has_direct_lpi ? "DirectLPI " : "",
gic_data.rdists.has_rvpeid ? "RVPEID " : "",
gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
}
static void gic_cpu_sys_reg_enable(void)
{
/*
* Need to check that the SRE bit has actually been set. If
* not, it means that SRE is disabled at EL2. We're going to
* die painfully, and there is nothing we can do about it.
*
* Kindly inform the luser.
*/
if (!gic_enable_sre())
pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
}
static void gic_cpu_sys_reg_init(void)
{
int i, cpu = smp_processor_id();
u64 mpidr = gic_cpu_to_affinity(cpu);
u64 need_rss = MPIDR_RS(mpidr);
bool group0;
u32 pribits;
pribits = gic_get_pribits();
group0 = gic_has_group0();
/* Set priority mask register */
if (!gic_prio_masking_enabled()) {
write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1);
} else if (gic_supports_nmi()) {
/*
* Check that all CPUs use the same priority space.
*
* If there's a mismatch with the boot CPU, the system is
* likely to die as interrupt masking will not work properly on
* all CPUs.
*/
WARN_ON(group0 != cpus_have_group0);
WARN_ON(gic_dist_security_disabled() != cpus_have_security_disabled);
}
/*
* Some firmwares hand over to the kernel with the BPR changed from
* its reset value (and with a value large enough to prevent
* any pre-emptive interrupts from working at all). Writing a zero
* to BPR restores is reset value.
*/
gic_write_bpr1(0);
if (static_branch_likely(&supports_deactivate_key)) {
/* EOI drops priority only (mode 1) */
gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop);
} else {
/* EOI deactivates interrupt too (mode 0) */
gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
}
/* Always whack Group0 before Group1 */
if (group0) {
switch(pribits) {
case 8:
case 7:
write_gicreg(0, ICC_AP0R3_EL1);
write_gicreg(0, ICC_AP0R2_EL1);
fallthrough;
case 6:
write_gicreg(0, ICC_AP0R1_EL1);
fallthrough;
case 5:
case 4:
write_gicreg(0, ICC_AP0R0_EL1);
}
isb();
}
switch(pribits) {
case 8:
case 7:
write_gicreg(0, ICC_AP1R3_EL1);
write_gicreg(0, ICC_AP1R2_EL1);
fallthrough;
case 6:
write_gicreg(0, ICC_AP1R1_EL1);
fallthrough;
case 5:
case 4:
write_gicreg(0, ICC_AP1R0_EL1);
}
isb();
/* ... and let's hit the road... */
gic_write_grpen1(1);
/* Keep the RSS capability status in per_cpu variable */
per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS);
/* Check all the CPUs have capable of sending SGIs to other CPUs */
for_each_online_cpu(i) {
bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu);
need_rss |= MPIDR_RS(gic_cpu_to_affinity(i));
if (need_rss && (!have_rss))
pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n",
cpu, (unsigned long)mpidr,
i, (unsigned long)gic_cpu_to_affinity(i));
}
/**
* GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0,
* writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED
* UNPREDICTABLE choice of :
* - The write is ignored.
* - The RS field is treated as 0.
*/
if (need_rss && (!gic_data.has_rss))
pr_crit_once("RSS is required but GICD doesn't support it\n");
}
static bool gicv3_nolpi;
static int __init gicv3_nolpi_cfg(char *buf)
{
return kstrtobool(buf, &gicv3_nolpi);
}
early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg);
static int gic_dist_supports_lpis(void)
{
return (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) &&
!!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS) &&
!gicv3_nolpi);
}
static void gic_cpu_init(void)
{
void __iomem *rbase;
int i;
/* Register ourselves with the rest of the world */
if (gic_populate_rdist())
return;
gic_enable_redist(true);
WARN((gic_data.ppi_nr > 16 || GIC_ESPI_NR != 0) &&
!(gic_read_ctlr() & ICC_CTLR_EL1_ExtRange),
"Distributor has extended ranges, but CPU%d doesn't\n",
smp_processor_id());
rbase = gic_data_rdist_sgi_base();
/* Configure SGIs/PPIs as non-secure Group-1 */
for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32)
writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8);
gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, dist_prio_irq);
gic_redist_wait_for_rwp();
/* initialise system registers */
gic_cpu_sys_reg_init();
}
#ifdef CONFIG_SMP
#define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT)
#define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL)
/*
* gic_starting_cpu() is called after the last point where cpuhp is allowed
* to fail. So pre check for problems earlier.
*/
static int gic_check_rdist(unsigned int cpu)
{
if (cpumask_test_cpu(cpu, &broken_rdists))
return -EINVAL;
return 0;
}
static int gic_starting_cpu(unsigned int cpu)
{
gic_cpu_sys_reg_enable();
gic_cpu_init();
if (gic_dist_supports_lpis())
its_cpu_init();
return 0;
}
static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
unsigned long cluster_id)
{
int next_cpu, cpu = *base_cpu;
unsigned long mpidr;
u16 tlist = 0;
mpidr = gic_cpu_to_affinity(cpu); while (cpu < nr_cpu_ids) {
tlist |= 1 << (mpidr & 0xf);
next_cpu = cpumask_next(cpu, mask); if (next_cpu >= nr_cpu_ids)
goto out;
cpu = next_cpu;
mpidr = gic_cpu_to_affinity(cpu); if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) {
cpu--;
goto out;
}
}
out:
*base_cpu = cpu;
return tlist;
}
#define MPIDR_TO_SGI_AFFINITY(cluster_id, level) \
(MPIDR_AFFINITY_LEVEL(cluster_id, level) \
<< ICC_SGI1R_AFFINITY_## level ##_SHIFT)
static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
{
u64 val;
val = (MPIDR_TO_SGI_AFFINITY(cluster_id, 3) |
MPIDR_TO_SGI_AFFINITY(cluster_id, 2) |
irq << ICC_SGI1R_SGI_ID_SHIFT |
MPIDR_TO_SGI_AFFINITY(cluster_id, 1) |
MPIDR_TO_SGI_RS(cluster_id) |
tlist << ICC_SGI1R_TARGET_LIST_SHIFT);
pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
gic_write_sgi1r(val);
}
static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
{
int cpu;
if (WARN_ON(d->hwirq >= 16))
return;
/*
* Ensure that stores to Normal memory are visible to the
* other CPUs before issuing the IPI.
*/
dsb(ishst);
for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(gic_cpu_to_affinity(cpu));
u16 tlist;
tlist = gic_compute_target_list(&cpu, mask, cluster_id);
gic_send_sgi(cluster_id, tlist, d->hwirq);
}
/* Force the above writes to ICC_SGI1R_EL1 to be executed */
isb();
}
static void __init gic_smp_init(void)
{
struct irq_fwspec sgi_fwspec = {
.fwnode = gic_data.fwnode,
.param_count = 1,
};
int base_sgi;
cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN,
"irqchip/arm/gicv3:checkrdist",
gic_check_rdist, NULL);
cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
"irqchip/arm/gicv3:starting",
gic_starting_cpu, NULL);
/* Register all 8 non-secure SGIs */
base_sgi = irq_domain_alloc_irqs(gic_data.domain, 8, NUMA_NO_NODE, &sgi_fwspec);
if (WARN_ON(base_sgi <= 0))
return;
set_smp_ipi_range(base_sgi, 8);
}
static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
bool force)
{
unsigned int cpu;
u32 offset, index;
void __iomem *reg;
int enabled;
u64 val;
if (force)
cpu = cpumask_first(mask_val);
else
cpu = cpumask_any_and(mask_val, cpu_online_mask);
if (cpu >= nr_cpu_ids)
return -EINVAL;
if (gic_irq_in_rdist(d))
return -EINVAL;
/* If interrupt was enabled, disable it first */
enabled = gic_peek_irq(d, GICD_ISENABLER);
if (enabled)
gic_mask_irq(d);
offset = convert_offset_index(d, GICD_IROUTER, &index);
reg = gic_dist_base(d) + offset + (index * 8);
val = gic_cpu_to_affinity(cpu);
gic_write_irouter(val, reg);
/*
* If the interrupt was enabled, enabled it again. Otherwise,
* just wait for the distributor to have digested our changes.
*/
if (enabled)
gic_unmask_irq(d);
irq_data_update_effective_affinity(d, cpumask_of(cpu));
return IRQ_SET_MASK_OK_DONE;
}
#else
#define gic_set_affinity NULL
#define gic_ipi_send_mask NULL
#define gic_smp_init() do { } while(0)
#endif
static int gic_retrigger(struct irq_data *data)
{
return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true);
}
#ifdef CONFIG_CPU_PM
static int gic_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd, void *v)
{
if (cmd == CPU_PM_EXIT || cmd == CPU_PM_ENTER_FAILED) {
if (gic_dist_security_disabled())
gic_enable_redist(true);
gic_cpu_sys_reg_enable();
gic_cpu_sys_reg_init();
} else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) {
gic_write_grpen1(0);
gic_enable_redist(false);
}
return NOTIFY_OK;
}
static struct notifier_block gic_cpu_pm_notifier_block = {
.notifier_call = gic_cpu_pm_notifier,
};
static void gic_cpu_pm_init(void)
{
cpu_pm_register_notifier(&gic_cpu_pm_notifier_block);
}
#else
static inline void gic_cpu_pm_init(void) { }
#endif /* CONFIG_CPU_PM */
static struct irq_chip gic_chip = {
.name = "GICv3",
.irq_mask = gic_mask_irq,
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoi_irq,
.irq_set_type = gic_set_type,
.irq_set_affinity = gic_set_affinity,
.irq_retrigger = gic_retrigger,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
.irq_nmi_setup = gic_irq_nmi_setup,
.irq_nmi_teardown = gic_irq_nmi_teardown,
.ipi_send_mask = gic_ipi_send_mask,
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
static struct irq_chip gic_eoimode1_chip = {
.name = "GICv3",
.irq_mask = gic_eoimode1_mask_irq,
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoimode1_eoi_irq,
.irq_set_type = gic_set_type,
.irq_set_affinity = gic_set_affinity,
.irq_retrigger = gic_retrigger,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity,
.irq_nmi_setup = gic_irq_nmi_setup,
.irq_nmi_teardown = gic_irq_nmi_teardown,
.ipi_send_mask = gic_ipi_send_mask,
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
struct irq_chip *chip = &gic_chip;
struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq));
if (static_branch_likely(&supports_deactivate_key))
chip = &gic_eoimode1_chip;
switch (__get_intid_range(hw)) {
case SGI_RANGE:
case PPI_RANGE:
case EPPI_RANGE:
irq_set_percpu_devid(irq);
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_percpu_devid_irq, NULL, NULL);
break;
case SPI_RANGE:
case ESPI_RANGE:
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_fasteoi_irq, NULL, NULL);
irq_set_probe(irq);
irqd_set_single_target(irqd);
break;
case LPI_RANGE:
if (!gic_dist_supports_lpis())
return -EPERM;
irq_domain_set_info(d, irq, hw, chip, d->host_data,
handle_fasteoi_irq, NULL, NULL);
break;
default:
return -EPERM;
}
/* Prevents SW retriggers which mess up the ACK/EOI ordering */
irqd_set_handle_enforce_irqctx(irqd);
return 0;
}
static int gic_irq_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
unsigned int *type)
{
if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
*hwirq = fwspec->param[0];
*type = IRQ_TYPE_EDGE_RISING;
return 0;
}
if (is_of_node(fwspec->fwnode)) {
if (fwspec->param_count < 3)
return -EINVAL;
switch (fwspec->param[0]) {
case 0: /* SPI */
*hwirq = fwspec->param[1] + 32;
break;
case 1: /* PPI */
*hwirq = fwspec->param[1] + 16;
break;
case 2: /* ESPI */
*hwirq = fwspec->param[1] + ESPI_BASE_INTID;
break;
case 3: /* EPPI */
*hwirq = fwspec->param[1] + EPPI_BASE_INTID;
break;
case GIC_IRQ_TYPE_LPI: /* LPI */
*hwirq = fwspec->param[1];
break;
case GIC_IRQ_TYPE_PARTITION:
*hwirq = fwspec->param[1];
if (fwspec->param[1] >= 16)
*hwirq += EPPI_BASE_INTID - 16;
else
*hwirq += 16;
break;
default:
return -EINVAL;
}
*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
/*
* Make it clear that broken DTs are... broken.
* Partitioned PPIs are an unfortunate exception.
*/
WARN_ON(*type == IRQ_TYPE_NONE &&
fwspec->param[0] != GIC_IRQ_TYPE_PARTITION);
return 0;
}
if (is_fwnode_irqchip(fwspec->fwnode)) {
if(fwspec->param_count != 2)
return -EINVAL;
if (fwspec->param[0] < 16) {
pr_err(FW_BUG "Illegal GSI%d translation request\n",
fwspec->param[0]);
return -EINVAL;
}
*hwirq = fwspec->param[0];
*type = fwspec->param[1];
WARN_ON(*type == IRQ_TYPE_NONE);
return 0;
}
return -EINVAL;
}
static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
int i, ret;
irq_hw_number_t hwirq;
unsigned int type = IRQ_TYPE_NONE;
struct irq_fwspec *fwspec = arg;
ret = gic_irq_domain_translate(domain, fwspec, &hwirq, &type);
if (ret)
return ret;
for (i = 0; i < nr_irqs; i++) {
ret = gic_irq_domain_map(domain, virq + i, hwirq + i);
if (ret)
return ret;
}
return 0;
}
static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
int i;
for (i = 0; i < nr_irqs; i++) {
struct irq_data *d = irq_domain_get_irq_data(domain, virq + i);
irq_set_handler(virq + i, NULL);
irq_domain_reset_irq_data(d);
}
}
static bool fwspec_is_partitioned_ppi(struct irq_fwspec *fwspec,
irq_hw_number_t hwirq)
{
enum gic_intid_range range;
if (!gic_data.ppi_descs)
return false;
if (!is_of_node(fwspec->fwnode))
return false;
if (fwspec->param_count < 4 || !fwspec->param[3])
return false;
range = __get_intid_range(hwirq);
if (range != PPI_RANGE && range != EPPI_RANGE)
return false;
return true;
}
static int gic_irq_domain_select(struct irq_domain *d,
struct irq_fwspec *fwspec,
enum irq_domain_bus_token bus_token)
{
unsigned int type, ret, ppi_idx;
irq_hw_number_t hwirq;
/* Not for us */
if (fwspec->fwnode != d->fwnode)
return 0;
/* Handle pure domain searches */
if (!fwspec->param_count)
return d->bus_token == bus_token;
/* If this is not DT, then we have a single domain */
if (!is_of_node(fwspec->fwnode))
return 1;
ret = gic_irq_domain_translate(d, fwspec, &hwirq, &type);
if (WARN_ON_ONCE(ret))
return 0;
if (!fwspec_is_partitioned_ppi(fwspec, hwirq))
return d == gic_data.domain;
/*
* If this is a PPI and we have a 4th (non-null) parameter,
* then we need to match the partition domain.
*/
ppi_idx = __gic_get_ppi_index(hwirq);
return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]);
}
static const struct irq_domain_ops gic_irq_domain_ops = {
.translate = gic_irq_domain_translate,
.alloc = gic_irq_domain_alloc,
.free = gic_irq_domain_free,
.select = gic_irq_domain_select,
};
static int partition_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
unsigned int *type)
{
unsigned long ppi_intid;
struct device_node *np;
unsigned int ppi_idx;
int ret;
if (!gic_data.ppi_descs)
return -ENOMEM;
np = of_find_node_by_phandle(fwspec->param[3]);
if (WARN_ON(!np))
return -EINVAL;
ret = gic_irq_domain_translate(d, fwspec, &ppi_intid, type);
if (WARN_ON_ONCE(ret))
return 0;
ppi_idx = __gic_get_ppi_index(ppi_intid);
ret = partition_translate_id(gic_data.ppi_descs[ppi_idx],
of_node_to_fwnode(np));
if (ret < 0)
return ret;
*hwirq = ret;
*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
return 0;
}
static const struct irq_domain_ops partition_domain_ops = {
.translate = partition_domain_translate,
.select = gic_irq_domain_select,
};
static bool gic_enable_quirk_msm8996(void *data)
{
struct gic_chip_data *d = data;
d->flags |= FLAGS_WORKAROUND_GICR_WAKER_MSM8996;
return true;
}
static bool gic_enable_quirk_cavium_38539(void *data)
{
struct gic_chip_data *d = data;
d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539;
return true;
}
static bool gic_enable_quirk_hip06_07(void *data)
{
struct gic_chip_data *d = data;
/*
* HIP06 GICD_IIDR clashes with GIC-600 product number (despite
* not being an actual ARM implementation). The saving grace is
* that GIC-600 doesn't have ESPI, so nothing to do in that case.
* HIP07 doesn't even have a proper IIDR, and still pretends to
* have ESPI. In both cases, put them right.
*/
if (d->rdists.gicd_typer & GICD_TYPER_ESPI) {
/* Zero both ESPI and the RES0 field next to it... */
d->rdists.gicd_typer &= ~GENMASK(9, 8);
return true;
}
return false;
}
#define T241_CHIPN_MASK GENMASK_ULL(45, 44)
#define T241_CHIP_GICDA_OFFSET 0x1580000
#define SMCCC_SOC_ID_T241 0x036b0241
static bool gic_enable_quirk_nvidia_t241(void *data)
{
s32 soc_id = arm_smccc_get_soc_id_version();
unsigned long chip_bmask = 0;
phys_addr_t phys;
u32 i;
/* Check JEP106 code for NVIDIA T241 chip (036b:0241) */
if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241))
return false;
/* Find the chips based on GICR regions PHYS addr */
for (i = 0; i < gic_data.nr_redist_regions; i++) {
chip_bmask |= BIT(FIELD_GET(T241_CHIPN_MASK,
(u64)gic_data.redist_regions[i].phys_base));
}
if (hweight32(chip_bmask) < 3)
return false;
/* Setup GICD alias regions */
for (i = 0; i < ARRAY_SIZE(t241_dist_base_alias); i++) {
if (chip_bmask & BIT(i)) {
phys = gic_data.dist_phys_base + T241_CHIP_GICDA_OFFSET;
phys |= FIELD_PREP(T241_CHIPN_MASK, i);
t241_dist_base_alias[i] = ioremap(phys, SZ_64K);
WARN_ON_ONCE(!t241_dist_base_alias[i]);
}
}
static_branch_enable(&gic_nvidia_t241_erratum);
return true;
}
static bool gic_enable_quirk_asr8601(void *data)
{
struct gic_chip_data *d = data;
d->flags |= FLAGS_WORKAROUND_ASR_ERRATUM_8601001;
return true;
}
static bool gic_enable_quirk_arm64_2941627(void *data)
{
static_branch_enable(&gic_arm64_2941627_erratum);
return true;
}
static bool gic_enable_quirk_rk3399(void *data)
{
struct gic_chip_data *d = data;
if (of_machine_is_compatible("rockchip,rk3399")) {
d->flags |= FLAGS_WORKAROUND_INSECURE;
return true;
}
return false;
}
static bool rd_set_non_coherent(void *data)
{
struct gic_chip_data *d = data;
d->rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE;
return true;
}
static const struct gic_quirk gic_quirks[] = {
{
.desc = "GICv3: Qualcomm MSM8996 broken firmware",
.compatible = "qcom,msm8996-gic-v3",
.init = gic_enable_quirk_msm8996,
},
{
.desc = "GICv3: ASR erratum 8601001",
.compatible = "asr,asr8601-gic-v3",
.init = gic_enable_quirk_asr8601,
},
{
.desc = "GICv3: HIP06 erratum 161010803",
.iidr = 0x0204043b,
.mask = 0xffffffff,
.init = gic_enable_quirk_hip06_07,
},
{
.desc = "GICv3: HIP07 erratum 161010803",
.iidr = 0x00000000,
.mask = 0xffffffff,
.init = gic_enable_quirk_hip06_07,
},
{
/*
* Reserved register accesses generate a Synchronous
* External Abort. This erratum applies to:
* - ThunderX: CN88xx
* - OCTEON TX: CN83xx, CN81xx
* - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx*
*/
.desc = "GICv3: Cavium erratum 38539",
.iidr = 0xa000034c,
.mask = 0xe8f00fff,
.init = gic_enable_quirk_cavium_38539,
},
{
.desc = "GICv3: NVIDIA erratum T241-FABRIC-4",
.iidr = 0x0402043b,
.mask = 0xffffffff,
.init = gic_enable_quirk_nvidia_t241,
},
{
/*
* GIC-700: 2941627 workaround - IP variant [0,1]
*
*/
.desc = "GICv3: ARM64 erratum 2941627",
.iidr = 0x0400043b,
.mask = 0xff0e0fff,
.init = gic_enable_quirk_arm64_2941627,
},
{
/*
* GIC-700: 2941627 workaround - IP variant [2]
*/
.desc = "GICv3: ARM64 erratum 2941627",
.iidr = 0x0402043b,
.mask = 0xff0f0fff,
.init = gic_enable_quirk_arm64_2941627,
},
{
.desc = "GICv3: non-coherent attribute",
.property = "dma-noncoherent",
.init = rd_set_non_coherent,
},
{
.desc = "GICv3: Insecure RK3399 integration",
.iidr = 0x0000043b,
.mask = 0xff000fff,
.init = gic_enable_quirk_rk3399,
},
{
}
};
static void gic_enable_nmi_support(void)
{
int i;
if (!gic_prio_masking_enabled() || nmi_support_forbidden)
return;
rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,
sizeof(*rdist_nmi_refs), GFP_KERNEL);
if (!rdist_nmi_refs)
return;
for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++)
refcount_set(&rdist_nmi_refs[i], 0);
pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
gic_has_relaxed_pmr_sync() ? "relaxed" : "forced");
static_branch_enable(&supports_pseudo_nmis);
if (static_branch_likely(&supports_deactivate_key))
gic_eoimode1_chip.flags |= IRQCHIP_SUPPORTS_NMI;
else
gic_chip.flags |= IRQCHIP_SUPPORTS_NMI;
}
static int __init gic_init_bases(phys_addr_t dist_phys_base,
void __iomem *dist_base,
struct redist_region *rdist_regs,
u32 nr_redist_regions,
u64 redist_stride,
struct fwnode_handle *handle)
{
u32 typer;
int err;
if (!is_hyp_mode_available())
static_branch_disable(&supports_deactivate_key);
if (static_branch_likely(&supports_deactivate_key))
pr_info("GIC: Using split EOI/Deactivate mode\n");
gic_data.fwnode = handle;
gic_data.dist_phys_base = dist_phys_base;
gic_data.dist_base = dist_base;
gic_data.redist_regions = rdist_regs;
gic_data.nr_redist_regions = nr_redist_regions;
gic_data.redist_stride = redist_stride;
/*
* Find out how many interrupts are supported.
*/
typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
gic_data.rdists.gicd_typer = typer;
gic_enable_quirks(readl_relaxed(gic_data.dist_base + GICD_IIDR),
gic_quirks, &gic_data);
pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
/*
* ThunderX1 explodes on reading GICD_TYPER2, in violation of the
* architecture spec (which says that reserved registers are RES0).
*/
if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539))
gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
&gic_data);
gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
if (!static_branch_unlikely(&gic_nvidia_t241_erratum)) {
/* Disable GICv4.x features for the erratum T241-FABRIC-4 */
gic_data.rdists.has_rvpeid = true;
gic_data.rdists.has_vlpis = true;
gic_data.rdists.has_direct_lpi = true;
gic_data.rdists.has_vpend_valid_dirty = true;
}
if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
err = -ENOMEM;
goto out_free;
}
irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
gic_data.has_rss = !!(typer & GICD_TYPER_RSS);
if (typer & GICD_TYPER_MBIS) {
err = mbi_init(handle, gic_data.domain);
if (err)
pr_err("Failed to initialize MBIs\n");
}
set_handle_irq(gic_handle_irq);
gic_update_rdist_properties();
gic_cpu_sys_reg_enable();
gic_prio_init();
gic_dist_init();
gic_cpu_init();
gic_enable_nmi_support();
gic_smp_init();
gic_cpu_pm_init();
if (gic_dist_supports_lpis()) {
its_init(handle, &gic_data.rdists, gic_data.domain, dist_prio_irq);
its_cpu_init();
its_lpi_memreserve_init();
} else {
if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
gicv2m_init(handle, gic_data.domain);
}
return 0;
out_free:
if (gic_data.domain)
irq_domain_remove(gic_data.domain);
free_percpu(gic_data.rdists.rdist);
return err;
}
static int __init gic_validate_dist_version(void __iomem *dist_base)
{
u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4)
return -ENODEV;
return 0;
}
/* Create all possible partitions at boot time */
static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
{
struct device_node *parts_node, *child_part;
int part_idx = 0, i;
int nr_parts;
struct partition_affinity *parts;
parts_node = of_get_child_by_name(gic_node, "ppi-partitions");
if (!parts_node)
return;
gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL);
if (!gic_data.ppi_descs)
goto out_put_node;
nr_parts = of_get_child_count(parts_node);
if (!nr_parts)
goto out_put_node;
parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL);
if (WARN_ON(!parts))
goto out_put_node;
for_each_child_of_node(parts_node, child_part) {
struct partition_affinity *part;
int n;
part = &parts[part_idx];
part->partition_id = of_node_to_fwnode(child_part);
pr_info("GIC: PPI partition %pOFn[%d] { ",
child_part, part_idx);
n = of_property_count_elems_of_size(child_part, "affinity",
sizeof(u32));
WARN_ON(n <= 0);
for (i = 0; i < n; i++) {
int err, cpu;
u32 cpu_phandle;
struct device_node *cpu_node;
err = of_property_read_u32_index(child_part, "affinity",
i, &cpu_phandle);
if (WARN_ON(err))
continue;
cpu_node = of_find_node_by_phandle(cpu_phandle);
if (WARN_ON(!cpu_node))
continue;
cpu = of_cpu_node_to_id(cpu_node);
if (WARN_ON(cpu < 0)) {
of_node_put(cpu_node);
continue;
}
pr_cont("%pOF[%d] ", cpu_node, cpu);
cpumask_set_cpu(cpu, &part->mask);
of_node_put(cpu_node);
}
pr_cont("}\n");
part_idx++;
}
for (i = 0; i < gic_data.ppi_nr; i++) {
unsigned int irq;
struct partition_desc *desc;
struct irq_fwspec ppi_fwspec = {
.fwnode = gic_data.fwnode,
.param_count = 3,
.param = {
[0] = GIC_IRQ_TYPE_PARTITION,
[1] = i,
[2] = IRQ_TYPE_NONE,
},
};
irq = irq_create_fwspec_mapping(&ppi_fwspec);
if (WARN_ON(!irq))
continue;
desc = partition_create_desc(gic_data.fwnode, parts, nr_parts,
irq, &partition_domain_ops);
if (WARN_ON(!desc))
continue;
gic_data.ppi_descs[i] = desc;
}
out_put_node:
of_node_put(parts_node);
}
static void __init gic_of_setup_kvm_info(struct device_node *node, u32 nr_redist_regions)
{
int ret;
struct resource r;
gic_v3_kvm_info.type = GIC_V3;
gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
if (!gic_v3_kvm_info.maint_irq)
return;
/* Also skip GICD, GICC, GICH */
ret = of_address_to_resource(node, nr_redist_regions + 3, &r);
if (!ret)
gic_v3_kvm_info.vcpu = r;
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
vgic_set_kvm_info(&gic_v3_kvm_info);
}
static void gic_request_region(resource_size_t base, resource_size_t size,
const char *name)
{
if (!request_mem_region(base, size, name))
pr_warn_once(FW_BUG "%s region %pa has overlapping address\n",
name, &base);
}
static void __iomem *gic_of_iomap(struct device_node *node, int idx,
const char *name, struct resource *res)
{
void __iomem *base;
int ret;
ret = of_address_to_resource(node, idx, res);
if (ret)
return IOMEM_ERR_PTR(ret);
gic_request_region(res->start, resource_size(res), name);
base = of_iomap(node, idx);
return base ?: IOMEM_ERR_PTR(-ENOMEM);
}
static int __init gic_of_init(struct device_node *node, struct device_node *parent)
{
phys_addr_t dist_phys_base;
void __iomem *dist_base;
struct redist_region *rdist_regs;
struct resource res;
u64 redist_stride;
u32 nr_redist_regions;
int err, i;
dist_base = gic_of_iomap(node, 0, "GICD", &res);
if (IS_ERR(dist_base)) {
pr_err("%pOF: unable to map gic dist registers\n", node);
return PTR_ERR(dist_base);
}
dist_phys_base = res.start;
err = gic_validate_dist_version(dist_base);
if (err) {
pr_err("%pOF: no distributor detected, giving up\n", node);
goto out_unmap_dist;
}
if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions))
nr_redist_regions = 1;
rdist_regs = kcalloc(nr_redist_regions, sizeof(*rdist_regs),
GFP_KERNEL);
if (!rdist_regs) {
err = -ENOMEM;
goto out_unmap_dist;
}
for (i = 0; i < nr_redist_regions; i++) {
rdist_regs[i].redist_base = gic_of_iomap(node, 1 + i, "GICR", &res);
if (IS_ERR(rdist_regs[i].redist_base)) {
pr_err("%pOF: couldn't map region %d\n", node, i);
err = -ENODEV;
goto out_unmap_rdist;
}
rdist_regs[i].phys_base = res.start;
}
if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
redist_stride = 0;
gic_enable_of_quirks(node, gic_quirks, &gic_data);
err = gic_init_bases(dist_phys_base, dist_base, rdist_regs,
nr_redist_regions, redist_stride, &node->fwnode);
if (err)
goto out_unmap_rdist;
gic_populate_ppi_partitions(node);
if (static_branch_likely(&supports_deactivate_key))
gic_of_setup_kvm_info(node, nr_redist_regions);
return 0;
out_unmap_rdist:
for (i = 0; i < nr_redist_regions; i++)
if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base))
iounmap(rdist_regs[i].redist_base);
kfree(rdist_regs);
out_unmap_dist:
iounmap(dist_base);
return err;
}
IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
#ifdef CONFIG_ACPI
static struct
{
void __iomem *dist_base;
struct redist_region *redist_regs;
u32 nr_redist_regions;
bool single_redist;
int enabled_rdists;
u32 maint_irq;
int maint_irq_mode;
phys_addr_t vcpu_base;
} acpi_data __initdata;
static void __init
gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base)
{
static int count = 0;
acpi_data.redist_regs[count].phys_base = phys_base;
acpi_data.redist_regs[count].redist_base = redist_base;
acpi_data.redist_regs[count].single_redist = acpi_data.single_redist;
count++;
}
static int __init
gic_acpi_parse_madt_redist(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_redistributor *redist =
(struct acpi_madt_generic_redistributor *)header;
void __iomem *redist_base;
redist_base = ioremap(redist->base_address, redist->length);
if (!redist_base) {
pr_err("Couldn't map GICR region @%llx\n", redist->base_address);
return -ENOMEM;
}
if (acpi_get_madt_revision() >= 7 &&
(redist->flags & ACPI_MADT_GICR_NON_COHERENT))
gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE;
gic_request_region(redist->base_address, redist->length, "GICR");
gic_acpi_register_redist(redist->base_address, redist_base);
return 0;
}
static int __init
gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
void __iomem *redist_base;
/* Neither enabled or online capable means it doesn't exist, skip it */
if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE)))
return 0;
/*
* Capable but disabled CPUs can be brought online later. What about
* the redistributor? ACPI doesn't want to say!
* Virtual hotplug systems can use the MADT's "always-on" GICR entries.
* Otherwise, prevent such CPUs from being brought online.
*/
if (!(gicc->flags & ACPI_MADT_ENABLED)) {
int cpu = get_cpu_for_acpi_id(gicc->uid);
pr_warn("CPU %u's redistributor is inaccessible: this CPU can't be brought online\n", cpu);
if (cpu >= 0)
cpumask_set_cpu(cpu, &broken_rdists);
return 0;
}
redist_base = ioremap(gicc->gicr_base_address, size);
if (!redist_base)
return -ENOMEM;
gic_request_region(gicc->gicr_base_address, size, "GICR");
if (acpi_get_madt_revision() >= 7 &&
(gicc->flags & ACPI_MADT_GICC_NON_COHERENT))
gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE;
gic_acpi_register_redist(gicc->gicr_base_address, redist_base);
return 0;
}
static int __init gic_acpi_collect_gicr_base(void)
{
acpi_tbl_entry_handler redist_parser;
enum acpi_madt_type type;
if (acpi_data.single_redist) {
type = ACPI_MADT_TYPE_GENERIC_INTERRUPT;
redist_parser = gic_acpi_parse_madt_gicc;
} else {
type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR;
redist_parser = gic_acpi_parse_madt_redist;
}
/* Collect redistributor base addresses in GICR entries */
if (acpi_table_parse_madt(type, redist_parser, 0) > 0)
return 0;
pr_info("No valid GICR entries exist\n");
return -ENODEV;
}
static int __init gic_acpi_match_gicr(union acpi_subtable_headers *header,
const unsigned long end)
{
/* Subtable presence means that redist exists, that's it */
return 0;
}
static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
/*
* If GICC is enabled and has valid gicr base address, then it means
* GICR base is presented via GICC. The redistributor is only known to
* be accessible if the GICC is marked as enabled. If this bit is not
* set, we'd need to add the redistributor at runtime, which isn't
* supported.
*/
if (gicc->flags & ACPI_MADT_ENABLED && gicc->gicr_base_address)
acpi_data.enabled_rdists++;
return 0;
}
static int __init gic_acpi_count_gicr_regions(void)
{
int count;
/*
* Count how many redistributor regions we have. It is not allowed
* to mix redistributor description, GICR and GICC subtables have to be
* mutually exclusive.
*/
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR,
gic_acpi_match_gicr, 0);
if (count > 0) {
acpi_data.single_redist = false;
return count;
}
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_match_gicc, 0);
if (count > 0) {
acpi_data.single_redist = true;
count = acpi_data.enabled_rdists;
}
return count;
}
static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header,
struct acpi_probe_entry *ape)
{
struct acpi_madt_generic_distributor *dist;
int count;
dist = (struct acpi_madt_generic_distributor *)header;
if (dist->version != ape->driver_data)
return false;
/* We need to do that exercise anyway, the sooner the better */
count = gic_acpi_count_gicr_regions();
if (count <= 0)
return false;
acpi_data.nr_redist_regions = count;
return true;
}
static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_madt_generic_interrupt *gicc =
(struct acpi_madt_generic_interrupt *)header;
int maint_irq_mode;
static int first_madt = true;
if (!(gicc->flags &
(ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE)))
return 0;
maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE;
if (first_madt) {
first_madt = false;
acpi_data.maint_irq = gicc->vgic_interrupt;
acpi_data.maint_irq_mode = maint_irq_mode;
acpi_data.vcpu_base = gicc->gicv_base_address;
return 0;
}
/*
* The maintenance interrupt and GICV should be the same for every CPU
*/
if ((acpi_data.maint_irq != gicc->vgic_interrupt) ||
(acpi_data.maint_irq_mode != maint_irq_mode) ||
(acpi_data.vcpu_base != gicc->gicv_base_address))
return -EINVAL;
return 0;
}
static bool __init gic_acpi_collect_virt_info(void)
{
int count;
count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
gic_acpi_parse_virt_madt_gicc, 0);
return (count > 0);
}
#define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K)
#define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K)
#define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K)
static void __init gic_acpi_setup_kvm_info(void)
{
int irq;
if (!gic_acpi_collect_virt_info()) {
pr_warn("Unable to get hardware information used for virtualization\n");
return;
}
gic_v3_kvm_info.type = GIC_V3;
irq = acpi_register_gsi(NULL, acpi_data.maint_irq,
acpi_data.maint_irq_mode,
ACPI_ACTIVE_HIGH);
if (irq <= 0)
return;
gic_v3_kvm_info.maint_irq = irq;
if (acpi_data.vcpu_base) {
struct resource *vcpu = &gic_v3_kvm_info.vcpu;
vcpu->flags = IORESOURCE_MEM;
vcpu->start = acpi_data.vcpu_base;
vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1;
}
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
vgic_set_kvm_info(&gic_v3_kvm_info);
}
static struct fwnode_handle *gsi_domain_handle;
static struct fwnode_handle *gic_v3_get_gsi_domain_id(u32 gsi)
{
return gsi_domain_handle;
}
static int __init
gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end)
{
struct acpi_madt_generic_distributor *dist;
size_t size;
int i, err;
/* Get distributor base address */
dist = (struct acpi_madt_generic_distributor *)header;
acpi_data.dist_base = ioremap(dist->base_address,
ACPI_GICV3_DIST_MEM_SIZE);
if (!acpi_data.dist_base) {
pr_err("Unable to map GICD registers\n");
return -ENOMEM;
}
gic_request_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD");
err = gic_validate_dist_version(acpi_data.dist_base);
if (err) {
pr_err("No distributor detected at @%p, giving up\n",
acpi_data.dist_base);
goto out_dist_unmap;
}
size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions;
acpi_data.redist_regs = kzalloc(size, GFP_KERNEL);
if (!acpi_data.redist_regs) {
err = -ENOMEM;
goto out_dist_unmap;
}
err = gic_acpi_collect_gicr_base();
if (err)
goto out_redist_unmap;
gsi_domain_handle = irq_domain_alloc_fwnode(&dist->base_address);
if (!gsi_domain_handle) {
err = -ENOMEM;
goto out_redist_unmap;
}
err = gic_init_bases(dist->base_address, acpi_data.dist_base,
acpi_data.redist_regs, acpi_data.nr_redist_regions,
0, gsi_domain_handle);
if (err)
goto out_fwhandle_free;
acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, gic_v3_get_gsi_domain_id);
if (static_branch_likely(&supports_deactivate_key))
gic_acpi_setup_kvm_info();
return 0;
out_fwhandle_free:
irq_domain_free_fwnode(gsi_domain_handle);
out_redist_unmap:
for (i = 0; i < acpi_data.nr_redist_regions; i++)
if (acpi_data.redist_regs[i].redist_base)
iounmap(acpi_data.redist_regs[i].redist_base);
kfree(acpi_data.redist_regs);
out_dist_unmap:
iounmap(acpi_data.dist_base);
return err;
}
IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3,
gic_acpi_init);
IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4,
gic_acpi_init);
IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE,
gic_acpi_init);
#endif
// SPDX-License-Identifier: GPL-2.0
/*
* kobject.h - generic kernel object infrastructure.
*
* Copyright (c) 2002-2003 Patrick Mochel
* Copyright (c) 2002-2003 Open Source Development Labs
* Copyright (c) 2006-2008 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (c) 2006-2008 Novell Inc.
*
* Please read Documentation/core-api/kobject.rst before using the kobject
* interface, ESPECIALLY the parts about reference counts and object
* destructors.
*/
#ifndef _KOBJECT_H_
#define _KOBJECT_H_
#include <linux/types.h>
#include <linux/list.h>
#include <linux/sysfs.h>
#include <linux/compiler.h>
#include <linux/container_of.h>
#include <linux/spinlock.h>
#include <linux/kref.h>
#include <linux/kobject_ns.h>
#include <linux/wait.h>
#include <linux/atomic.h>
#include <linux/workqueue.h>
#include <linux/uidgid.h>
#define UEVENT_HELPER_PATH_LEN 256
#define UEVENT_NUM_ENVP 64 /* number of env pointers */
#define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */
#ifdef CONFIG_UEVENT_HELPER
/* path to the userspace helper executed on an event */
extern char uevent_helper[];
#endif
/* counter to tag the uevent, read only except for the kobject core */
extern atomic64_t uevent_seqnum;
/*
* The actions here must match the index to the string array
* in lib/kobject_uevent.c
*
* Do not add new actions here without checking with the driver-core
* maintainers. Action strings are not meant to express subsystem
* or device specific properties. In most cases you want to send a
* kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event
* specific variables added to the event environment.
*/
enum kobject_action {
KOBJ_ADD,
KOBJ_REMOVE,
KOBJ_CHANGE,
KOBJ_MOVE,
KOBJ_ONLINE,
KOBJ_OFFLINE,
KOBJ_BIND,
KOBJ_UNBIND,
};
struct kobject {
const char *name;
struct list_head entry;
struct kobject *parent;
struct kset *kset;
const struct kobj_type *ktype;
struct kernfs_node *sd; /* sysfs directory entry */
struct kref kref;
unsigned int state_initialized:1;
unsigned int state_in_sysfs:1;
unsigned int state_add_uevent_sent:1;
unsigned int state_remove_uevent_sent:1;
unsigned int uevent_suppress:1;
#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
struct delayed_work release;
#endif
};
__printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...);
__printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs);
static inline const char *kobject_name(const struct kobject *kobj)
{
return kobj->name;
}
void kobject_init(struct kobject *kobj, const struct kobj_type *ktype);
__printf(3, 4) __must_check int kobject_add(struct kobject *kobj,
struct kobject *parent,
const char *fmt, ...);
__printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj,
const struct kobj_type *ktype,
struct kobject *parent,
const char *fmt, ...);
void kobject_del(struct kobject *kobj);
struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent);
int __must_check kobject_rename(struct kobject *, const char *new_name);
int __must_check kobject_move(struct kobject *, struct kobject *);
struct kobject *kobject_get(struct kobject *kobj);
struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj);
void kobject_put(struct kobject *kobj);
const void *kobject_namespace(const struct kobject *kobj);
void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid);
char *kobject_get_path(const struct kobject *kobj, gfp_t flag);
struct kobj_type {
void (*release)(struct kobject *kobj);
const struct sysfs_ops *sysfs_ops;
const struct attribute_group **default_groups;
const struct kobj_ns_type_operations *(*child_ns_type)(const struct kobject *kobj);
const void *(*namespace)(const struct kobject *kobj);
void (*get_ownership)(const struct kobject *kobj, kuid_t *uid, kgid_t *gid);
};
struct kobj_uevent_env {
char *argv[3];
char *envp[UEVENT_NUM_ENVP];
int envp_idx;
char buf[UEVENT_BUFFER_SIZE];
int buflen;
};
struct kset_uevent_ops {
int (* const filter)(const struct kobject *kobj);
const char *(* const name)(const struct kobject *kobj);
int (* const uevent)(const struct kobject *kobj, struct kobj_uevent_env *env);
};
struct kobj_attribute {
struct attribute attr;
ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr,
char *buf);
ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t count);
};
extern const struct sysfs_ops kobj_sysfs_ops;
struct sock;
/**
* struct kset - a set of kobjects of a specific type, belonging to a specific subsystem.
*
* A kset defines a group of kobjects. They can be individually
* different "types" but overall these kobjects all want to be grouped
* together and operated on in the same manner. ksets are used to
* define the attribute callbacks and other common events that happen to
* a kobject.
*
* @list: the list of all kobjects for this kset
* @list_lock: a lock for iterating over the kobjects
* @kobj: the embedded kobject for this kset (recursion, isn't it fun...)
* @uevent_ops: the set of uevent operations for this kset. These are
* called whenever a kobject has something happen to it so that the kset
* can add new environment variables, or filter out the uevents if so
* desired.
*/
struct kset {
struct list_head list;
spinlock_t list_lock;
struct kobject kobj;
const struct kset_uevent_ops *uevent_ops;
} __randomize_layout;
void kset_init(struct kset *kset);
int __must_check kset_register(struct kset *kset);
void kset_unregister(struct kset *kset);
struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u,
struct kobject *parent_kobj);
static inline struct kset *to_kset(struct kobject *kobj)
{
return kobj ? container_of(kobj, struct kset, kobj) : NULL;
}
static inline struct kset *kset_get(struct kset *k)
{
return k ? to_kset(kobject_get(&k->kobj)) : NULL;
}
static inline void kset_put(struct kset *k)
{
kobject_put(&k->kobj);
}
static inline const struct kobj_type *get_ktype(const struct kobject *kobj)
{
return kobj->ktype;
}
struct kobject *kset_find_obj(struct kset *, const char *);
/* The global /sys/kernel/ kobject for people to chain off of */
extern struct kobject *kernel_kobj;
/* The global /sys/kernel/mm/ kobject for people to chain off of */
extern struct kobject *mm_kobj;
/* The global /sys/hypervisor/ kobject for people to chain off of */
extern struct kobject *hypervisor_kobj;
/* The global /sys/power/ kobject for people to chain off of */
extern struct kobject *power_kobj;
/* The global /sys/firmware/ kobject for people to chain off of */
extern struct kobject *firmware_kobj;
int kobject_uevent(struct kobject *kobj, enum kobject_action action);
int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
char *envp[]);
int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count);
__printf(2, 3)
int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...);
#endif /* _KOBJECT_H_ */
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/mmdebug.h>
#include <linux/mm_types.h>
#include <linux/mm_inline.h>
#include <linux/pagemap.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/swap.h>
#include <linux/rmap.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#ifndef CONFIG_MMU_GATHER_NO_GATHER
static bool tlb_next_batch(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
/* Limit batching if we have delayed rmaps pending */
if (tlb->delayed_rmap && tlb->active != &tlb->local)
return false;
batch = tlb->active;
if (batch->next) {
tlb->active = batch->next;
return true;
}
if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
return false;
batch = (void *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (!batch)
return false;
tlb->batch_count++;
batch->next = NULL;
batch->nr = 0;
batch->max = MAX_GATHER_BATCH;
tlb->active->next = batch;
tlb->active = batch;
return true;
}
#ifdef CONFIG_SMP
static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_struct *vma)
{
struct encoded_page **pages = batch->encoded_pages;
for (int i = 0; i < batch->nr; i++) {
struct encoded_page *enc = pages[i];
if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) {
struct page *page = encoded_page_ptr(enc);
unsigned int nr_pages = 1;
if (unlikely(encoded_page_flags(enc) &
ENCODED_PAGE_BIT_NR_PAGES_NEXT))
nr_pages = encoded_nr_pages(pages[++i]); folio_remove_rmap_ptes(page_folio(page), page, nr_pages,
vma);
}
}
}
/**
* tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB
* @tlb: the current mmu_gather
* @vma: The memory area from which the pages are being removed.
*
* Note that because of how tlb_next_batch() above works, we will
* never start multiple new batches with pending delayed rmaps, so
* we only need to walk through the current active batch and the
* original local one.
*/
void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
{ if (!tlb->delayed_rmap)
return;
tlb_flush_rmap_batch(&tlb->local, vma); if (tlb->active != &tlb->local) tlb_flush_rmap_batch(tlb->active, vma);
tlb->delayed_rmap = 0;
}
#endif
/*
* We might end up freeing a lot of pages. Reschedule on a regular
* basis to avoid soft lockups in configurations without full
* preemption enabled. The magic number of 512 folios seems to work.
*/
#define MAX_NR_FOLIOS_PER_FREE 512
static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch)
{
struct encoded_page **pages = batch->encoded_pages;
unsigned int nr, nr_pages;
while (batch->nr) { if (!page_poisoning_enabled_static() && !want_init_on_free()) {
nr = min(MAX_NR_FOLIOS_PER_FREE, batch->nr);
/*
* Make sure we cover page + nr_pages, and don't leave
* nr_pages behind when capping the number of entries.
*/
if (unlikely(encoded_page_flags(pages[nr - 1]) &
ENCODED_PAGE_BIT_NR_PAGES_NEXT))
nr++;
} else {
/*
* With page poisoning and init_on_free, the time it
* takes to free memory grows proportionally with the
* actual memory size. Therefore, limit based on the
* actual memory size and not the number of involved
* folios.
*/
for (nr = 0, nr_pages = 0;
nr < batch->nr && nr_pages < MAX_NR_FOLIOS_PER_FREE;
nr++) {
if (unlikely(encoded_page_flags(pages[nr]) &
ENCODED_PAGE_BIT_NR_PAGES_NEXT))
nr_pages += encoded_nr_pages(pages[++nr]);
else
nr_pages++;
}
}
free_pages_and_swap_cache(pages, nr);
pages += nr;
batch->nr -= nr;
cond_resched();
}
}
static void tlb_batch_pages_flush(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
for (batch = &tlb->local; batch && batch->nr; batch = batch->next) __tlb_batch_free_encoded_pages(batch);
tlb->active = &tlb->local;
}
static void tlb_batch_list_free(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch, *next;
for (batch = tlb->local.next; batch; batch = next) {
next = batch->next;
free_pages((unsigned long)batch, 0);
}
tlb->local.next = NULL;
}
static bool __tlb_remove_folio_pages_size(struct mmu_gather *tlb,
struct page *page, unsigned int nr_pages, bool delay_rmap,
int page_size)
{
int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0;
struct mmu_gather_batch *batch;
VM_BUG_ON(!tlb->end);
#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
VM_WARN_ON(tlb->page_size != page_size);
VM_WARN_ON_ONCE(nr_pages != 1 && page_size != PAGE_SIZE);
VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1));
#endif
batch = tlb->active;
/*
* Add the page and check if we are full. If so
* force a flush.
*/
if (likely(nr_pages == 1)) {
batch->encoded_pages[batch->nr++] = encode_page(page, flags);
} else {
flags |= ENCODED_PAGE_BIT_NR_PAGES_NEXT;
batch->encoded_pages[batch->nr++] = encode_page(page, flags);
batch->encoded_pages[batch->nr++] = encode_nr_pages(nr_pages);
}
/*
* Make sure that we can always add another "page" + "nr_pages",
* requiring two entries instead of only a single one.
*/
if (batch->nr >= batch->max - 1) { if (!tlb_next_batch(tlb))
return true;
batch = tlb->active;
}
VM_BUG_ON_PAGE(batch->nr > batch->max - 1, page);
return false;
}
bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
unsigned int nr_pages, bool delay_rmap)
{
return __tlb_remove_folio_pages_size(tlb, page, nr_pages, delay_rmap,
PAGE_SIZE);
}
bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
bool delay_rmap, int page_size)
{
return __tlb_remove_folio_pages_size(tlb, page, 1, delay_rmap, page_size);
}
#endif /* MMU_GATHER_NO_GATHER */
#ifdef CONFIG_MMU_GATHER_TABLE_FREE
static void __tlb_remove_table_free(struct mmu_table_batch *batch)
{
int i;
for (i = 0; i < batch->nr; i++)
__tlb_remove_table(batch->tables[i]);
free_page((unsigned long)batch);
}
#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
*
* This is needed by some architectures to implement software pagetable walkers.
*
* gup_fast() and other software pagetable walkers do a lockless page-table
* walk and therefore needs some synchronization with the freeing of the page
* directories. The chosen means to accomplish that is by disabling IRQs over
* the walk.
*
* Architectures that use IPIs to flush TLBs will then automagically DTRT,
* since we unlink the page, flush TLBs, free the page. Since the disabling of
* IRQs delays the completion of the TLB flush we can never observe an already
* freed page.
*
* Not all systems IPI every CPU for this purpose:
*
* - Some architectures have HW support for cross-CPU synchronisation of TLB
* flushes, so there's no IPI at all.
*
* - Paravirt guests can do this TLB flushing in the hypervisor, or coordinate
* with the hypervisor to defer flushing on preempted vCPUs.
*
* Such systems need to delay the freeing by some other means, this is that
* means.
*
* What we do is batch the freed directory pages (tables) and RCU free them.
* We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
* holds off grace periods.
*
* However, in order to batch these pages we need to allocate storage, this
* allocation is deep inside the MM code and can thus easily fail on memory
* pressure. To guarantee progress we fall back to single table freeing, see
* the implementation of tlb_remove_table_one().
*
*/
static void tlb_remove_table_smp_sync(void *arg)
{
/* Simply deliver the interrupt */
}
void tlb_remove_table_sync_one(void)
{
/*
* This isn't an RCU grace period and hence the page-tables cannot be
* assumed to be actually RCU-freed.
*
* It is however sufficient for software page-table walkers that rely on
* IRQ disabling.
*/
smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
}
static void tlb_remove_table_rcu(struct rcu_head *head)
{
__tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu));
}
static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
call_rcu(&batch->rcu, tlb_remove_table_rcu);
}
#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
__tlb_remove_table_free(batch);
}
#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
/*
* If we want tlb_remove_table() to imply TLB invalidates.
*/
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
if (tlb_needs_table_invalidate()) {
/*
* Invalidate page-table caches used by hardware walkers. Then
* we still need to RCU-sched wait while freeing the pages
* because software walkers can still be in-flight.
*/
tlb_flush_mmu_tlbonly(tlb);
}
}
#ifdef CONFIG_PT_RECLAIM
static inline void __tlb_remove_table_one_rcu(struct rcu_head *head)
{
struct ptdesc *ptdesc;
ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
__tlb_remove_table(ptdesc);
}
static inline void __tlb_remove_table_one(void *table)
{
struct ptdesc *ptdesc;
ptdesc = table;
call_rcu(&ptdesc->pt_rcu_head, __tlb_remove_table_one_rcu);
}
#else
static inline void __tlb_remove_table_one(void *table)
{
tlb_remove_table_sync_one();
__tlb_remove_table(table);
}
#endif /* CONFIG_PT_RECLAIM */
static void tlb_remove_table_one(void *table)
{
__tlb_remove_table_one(table);
}
static void tlb_table_flush(struct mmu_gather *tlb)
{
struct mmu_table_batch **batch = &tlb->batch;
if (*batch) { tlb_table_invalidate(tlb);
tlb_remove_table_free(*batch);
*batch = NULL;
}
}
void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
struct mmu_table_batch **batch = &tlb->batch;
if (*batch == NULL) {
*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
if (*batch == NULL) {
tlb_table_invalidate(tlb);
tlb_remove_table_one(table);
return;
}
(*batch)->nr = 0;
}
(*batch)->tables[(*batch)->nr++] = table;
if ((*batch)->nr == MAX_TABLE_BATCH) tlb_table_flush(tlb);
}
static inline void tlb_table_init(struct mmu_gather *tlb)
{
tlb->batch = NULL;
}
#else /* !CONFIG_MMU_GATHER_TABLE_FREE */
static inline void tlb_table_flush(struct mmu_gather *tlb) { }
static inline void tlb_table_init(struct mmu_gather *tlb) { }
#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
static void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
tlb_table_flush(tlb);
#ifndef CONFIG_MMU_GATHER_NO_GATHER
tlb_batch_pages_flush(tlb);
#endif
}
void tlb_flush_mmu(struct mmu_gather *tlb)
{
tlb_flush_mmu_tlbonly(tlb);
tlb_flush_mmu_free(tlb);
}
static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
bool fullmm)
{
tlb->mm = mm;
tlb->fullmm = fullmm;
#ifndef CONFIG_MMU_GATHER_NO_GATHER
tlb->need_flush_all = 0;
tlb->local.next = NULL;
tlb->local.nr = 0;
tlb->local.max = ARRAY_SIZE(tlb->__pages);
tlb->active = &tlb->local;
tlb->batch_count = 0;
#endif
tlb->delayed_rmap = 0;
tlb_table_init(tlb);
#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
tlb->page_size = 0;
#endif
__tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm);
}
/**
* tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
* @tlb: the mmu_gather structure to initialize
* @mm: the mm_struct of the target address space
*
* Called to initialize an (on-stack) mmu_gather structure for page-table
* tear-down from @mm.
*/
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
{ __tlb_gather_mmu(tlb, mm, false);
}
/**
* tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down
* @tlb: the mmu_gather structure to initialize
* @mm: the mm_struct of the target address space
*
* In this case, @mm is without users and we're going to destroy the
* full address space (exit/execve).
*
* Called to initialize an (on-stack) mmu_gather structure for page-table
* tear-down from @mm.
*/
void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
{
__tlb_gather_mmu(tlb, mm, true);
}
/**
* tlb_finish_mmu - finish an mmu_gather structure
* @tlb: the mmu_gather structure to finish
*
* Called at the end of the shootdown operation to free up any resources that
* were required.
*/
void tlb_finish_mmu(struct mmu_gather *tlb)
{
/*
* If there are parallel threads are doing PTE changes on same range
* under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB
* flush by batching, one thread may end up seeing inconsistent PTEs
* and result in having stale TLB entries. So flush TLB forcefully
* if we detect parallel PTE batching threads.
*
* However, some syscalls, e.g. munmap(), may free page tables, this
* needs force flush everything in the given range. Otherwise this
* may result in having stale TLB entries for some architectures,
* e.g. aarch64, that could specify flush what level TLB.
*/
if (mm_tlb_flush_nested(tlb->mm)) {
/*
* The aarch64 yields better performance with fullmm by
* avoiding multiple CPUs spamming TLBI messages at the
* same time.
*
* On x86 non-fullmm doesn't yield significant difference
* against fullmm.
*/
tlb->fullmm = 1;
__tlb_reset_range(tlb);
tlb->freed_tables = 1;
}
tlb_flush_mmu(tlb);
#ifndef CONFIG_MMU_GATHER_NO_GATHER
tlb_batch_list_free(tlb);
#endif
dec_tlb_flush_pending(tlb->mm);
}
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/uaccess.h>
#include <linux/fs_struct.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/prefetch.h>
#include "mount.h"
#include "internal.h"
struct prepend_buffer {
char *buf;
int len;
};
#define DECLARE_BUFFER(__name, __buf, __len) \
struct prepend_buffer __name = {.buf = __buf + __len, .len = __len}
static char *extract_string(struct prepend_buffer *p)
{
if (likely(p->len >= 0)) return p->buf;
return ERR_PTR(-ENAMETOOLONG);
}
static bool prepend_char(struct prepend_buffer *p, unsigned char c)
{
if (likely(p->len > 0)) { p->len--; *--p->buf = c;
return true;
}
p->len = -1;
return false;
}
/*
* The source of the prepend data can be an optimistic load
* of a dentry name and length. And because we don't hold any
* locks, the length and the pointer to the name may not be
* in sync if a concurrent rename happens, and the kernel
* copy might fault as a result.
*
* The end result will correct itself when we check the
* rename sequence count, but we need to be able to handle
* the fault gracefully.
*/
static bool prepend_copy(void *dst, const void *src, int len)
{
if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len);
return false;
}
return true;
}
static bool prepend(struct prepend_buffer *p, const char *str, int namelen)
{
// Already overflowed?
if (p->len < 0)
return false;
// Will overflow?
if (p->len < namelen) {
// Fill as much as possible from the end of the name
str += namelen - p->len;
p->buf -= p->len;
prepend_copy(p->buf, str, p->len);
p->len = -1;
return false;
}
// Fits fully
p->len -= namelen;
p->buf -= namelen;
return prepend_copy(p->buf, str, namelen);
}
/**
* prepend_name - prepend a pathname in front of current buffer pointer
* @p: prepend buffer which contains buffer pointer and allocated length
* @name: name string and length qstr structure
*
* With RCU path tracing, it may race with d_move(). Use READ_ONCE() to
* make sure that either the old or the new name pointer and length are
* fetched. However, there may be mismatch between length and pointer.
* But since the length cannot be trusted, we need to copy the name very
* carefully when doing the prepend_copy(). It also prepends "/" at
* the beginning of the name. The sequence number check at the caller will
* retry it again when a d_move() does happen. So any garbage in the buffer
* due to mismatched pointer and length will be discarded.
*
* Load acquire is needed to make sure that we see the new name data even
* if we might get the length wrong.
*/
static bool prepend_name(struct prepend_buffer *p, const struct qstr *name)
{
const char *dname = smp_load_acquire(&name->name); /* ^^^ */
u32 dlen = READ_ONCE(name->len);
return prepend(p, dname, dlen) && prepend_char(p, '/');
}
static int __prepend_path(const struct dentry *dentry, const struct mount *mnt,
const struct path *root, struct prepend_buffer *p)
{
while (dentry != root->dentry || &mnt->mnt != root->mnt) {
const struct dentry *parent = READ_ONCE(dentry->d_parent);
if (dentry == mnt->mnt.mnt_root) {
struct mount *m = READ_ONCE(mnt->mnt_parent);
struct mnt_namespace *mnt_ns;
if (likely(mnt != m)) {
dentry = READ_ONCE(mnt->mnt_mountpoint);
mnt = m;
continue;
}
/* Global root */
mnt_ns = READ_ONCE(mnt->mnt_ns);
/* open-coded is_mounted() to use local mnt_ns */
if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns))
return 1; // absolute root
else
return 2; // detached or not attached yet
}
if (unlikely(dentry == parent))
/* Escaped? */
return 3;
prefetch(parent);
if (!prepend_name(p, &dentry->d_name))
break;
dentry = parent;
}
return 0;
}
/**
* prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
* @root: root vfsmnt/dentry
* @p: prepend buffer which contains buffer pointer and allocated length
*
* The function will first try to write out the pathname without taking any
* lock other than the RCU read lock to make sure that dentries won't go away.
* It only checks the sequence number of the global rename_lock as any change
* in the dentry's d_seq will be preceded by changes in the rename_lock
* sequence number. If the sequence number had been changed, it will restart
* the whole pathname back-tracing sequence again by taking the rename_lock.
* In this case, there is no need to take the RCU read lock as the recursive
* parent pointer references will keep the dentry chain alive as long as no
* rename operation is performed.
*/
static int prepend_path(const struct path *path,
const struct path *root,
struct prepend_buffer *p)
{
unsigned seq, m_seq = 0;
struct prepend_buffer b;
int error;
rcu_read_lock();
restart_mnt:
read_seqbegin_or_lock(&mount_lock, &m_seq);
seq = 0;
rcu_read_lock();
restart:
b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b);
if (!(seq & 1))
rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) {
seq = 1;
goto restart;
}
done_seqretry(&rename_lock, seq);
if (!(m_seq & 1))
rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) {
m_seq = 1;
goto restart_mnt;
}
done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/');
*p = b;
return error;
}
/**
* __d_path - return the path of a dentry
* @path: the dentry/vfsmount to report
* @root: root vfsmnt/dentry
* @buf: buffer to return value in
* @buflen: buffer length
*
* Convert a dentry into an ASCII path name.
*
* Returns a pointer into the buffer or an error code if the
* path was too long.
*
* "buflen" should be positive.
*
* If the path is not reachable from the supplied root, return %NULL.
*/
char *__d_path(const struct path *path,
const struct path *root,
char *buf, int buflen)
{
DECLARE_BUFFER(b, buf, buflen);
prepend_char(&b, 0);
if (unlikely(prepend_path(path, root, &b) > 0))
return NULL;
return extract_string(&b);
}
char *d_absolute_path(const struct path *path,
char *buf, int buflen)
{
struct path root = {};
DECLARE_BUFFER(b, buf, buflen);
prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1))
return ERR_PTR(-EINVAL);
return extract_string(&b);
}
static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
{
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
*root = fs->root;
} while (read_seqcount_retry(&fs->seq, seq));
}
/**
* d_path - return the path of a dentry
* @path: path to report
* @buf: buffer to return value in
* @buflen: buffer length
*
* Convert a dentry into an ASCII path name. If the entry has been deleted
* the string " (deleted)" is appended. Note that this is ambiguous.
*
* Returns a pointer into the buffer or an error code if the path was
* too long. Note: Callers should use the returned pointer, not the passed
* in buffer, to use the name! The implementation often starts at an offset
* into the buffer, and may leave 0 bytes at the start.
*
* "buflen" should be positive.
*/
char *d_path(const struct path *path, char *buf, int buflen)
{
DECLARE_BUFFER(b, buf, buflen);
struct path root;
/*
* We have various synthetic filesystems that never get mounted. On
* these filesystems dentries are never used for lookup purposes, and
* thus don't need to be hashed. They also don't need a name until a
* user wants to identify the object in /proc/pid/fd/. The little hack
* below allows us to generate a name for these objects on demand:
*
* Some pseudo inodes are mountable. When they are mounted
* path->dentry == path->mnt->mnt_root. In that case don't call d_dname
* and instead have d_path return the mounted path.
*/
if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11);
else
prepend_char(&b, 0);
prepend_path(path, &root, &b);
rcu_read_unlock(); return extract_string(&b);
}
EXPORT_SYMBOL(d_path);
/*
* Helper function for dentry_operations.d_dname() members
*/
char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...)
{
va_list args;
char temp[64];
int sz;
va_start(args, fmt);
sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1;
va_end(args);
if (sz > sizeof(temp) || sz > buflen)
return ERR_PTR(-ENAMETOOLONG);
buffer += buflen - sz;
return memcpy(buffer, temp, sz);
}
char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
{
DECLARE_BUFFER(b, buffer, buflen);
/* these dentries are never renamed, so d_lock is not needed */
prepend(&b, " (deleted)", 11);
prepend(&b, dentry->d_name.name, dentry->d_name.len);
prepend_char(&b, '/');
return extract_string(&b);
}
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p)
{
const struct dentry *dentry;
struct prepend_buffer b;
int seq = 0;
rcu_read_lock();
restart:
dentry = d;
b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) {
const struct dentry *parent = dentry->d_parent;
prefetch(parent);
if (!prepend_name(&b, &dentry->d_name))
break;
dentry = parent;
}
if (!(seq & 1))
rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) {
seq = 1;
goto restart;
}
done_seqretry(&rename_lock, seq);
if (b.len == p->len)
prepend_char(&b, '/'); return extract_string(&b);
}
char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen)
{
DECLARE_BUFFER(b, buf, buflen);
prepend_char(&b, 0);
return __dentry_path(dentry, &b);
}
EXPORT_SYMBOL(dentry_path_raw);
char *dentry_path(const struct dentry *dentry, char *buf, int buflen)
{
DECLARE_BUFFER(b, buf, buflen);
if (unlikely(d_unlinked(dentry)))
prepend(&b, "//deleted", 10);
else
prepend_char(&b, 0);
return __dentry_path(dentry, &b);
}
static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root,
struct path *pwd)
{
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
*root = fs->root;
*pwd = fs->pwd;
} while (read_seqcount_retry(&fs->seq, seq));
}
/*
* NOTE! The user-level library version returns a
* character pointer. The kernel system call just
* returns the length of the buffer filled (which
* includes the ending '\0' character), or a negative
* error value. So libc would do something like
*
* char *getcwd(char * buf, size_t size)
* {
* int retval;
*
* retval = sys_getcwd(buf, size);
* if (retval >= 0)
* return buf;
* errno = -retval;
* return NULL;
* }
*/
SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
{
int error;
struct path pwd, root;
char *page = __getname();
if (!page)
return -ENOMEM;
rcu_read_lock();
get_fs_root_and_pwd_rcu(current->fs, &root, &pwd);
if (unlikely(d_unlinked(pwd.dentry))) {
rcu_read_unlock();
error = -ENOENT;
} else {
unsigned len;
DECLARE_BUFFER(b, page, PATH_MAX);
prepend_char(&b, 0);
if (unlikely(prepend_path(&pwd, &root, &b) > 0))
prepend(&b, "(unreachable)", 13);
rcu_read_unlock();
len = PATH_MAX - b.len;
if (unlikely(len > PATH_MAX))
error = -ENAMETOOLONG;
else if (unlikely(len > size))
error = -ERANGE;
else if (copy_to_user(buf, b.buf, len))
error = -EFAULT;
else
error = len;
}
__putname(page);
return error;
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_HUGETLB_H
#define _LINUX_HUGETLB_H
#include <linux/mm.h>
#include <linux/mm_types.h>
#include <linux/mmdebug.h>
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
#include <linux/page_ref.h>
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/pgtable.h>
#include <linux/gfp.h>
#include <linux/userfaultfd_k.h>
struct ctl_table;
struct user_struct;
struct mmu_gather;
struct node;
void free_huge_folio(struct folio *folio);
#ifdef CONFIG_HUGETLB_PAGE
#include <linux/pagemap.h>
#include <linux/shm.h>
#include <asm/tlbflush.h>
/*
* For HugeTLB page, there are more metadata to save in the struct page. But
* the head struct page cannot meet our needs, so we have to abuse other tail
* struct page to store the metadata.
*/
#define __NR_USED_SUBPAGE 3
struct hugepage_subpool {
spinlock_t lock;
long count;
long max_hpages; /* Maximum huge pages or -1 if no maximum. */
long used_hpages; /* Used count against maximum, includes */
/* both allocated and reserved pages. */
struct hstate *hstate;
long min_hpages; /* Minimum huge pages or -1 if no minimum. */
long rsv_hpages; /* Pages reserved against global pool to */
/* satisfy minimum size. */
};
struct resv_map {
struct kref refs;
spinlock_t lock;
struct list_head regions;
long adds_in_progress;
struct list_head region_cache;
long region_cache_count;
struct rw_semaphore rw_sema;
#ifdef CONFIG_CGROUP_HUGETLB
/*
* On private mappings, the counter to uncharge reservations is stored
* here. If these fields are 0, then either the mapping is shared, or
* cgroup accounting is disabled for this resv_map.
*/
struct page_counter *reservation_counter;
unsigned long pages_per_hpage;
struct cgroup_subsys_state *css;
#endif
};
/*
* Region tracking -- allows tracking of reservations and instantiated pages
* across the pages in a mapping.
*
* The region data structures are embedded into a resv_map and protected
* by a resv_map's lock. The set of regions within the resv_map represent
* reservations for huge pages, or huge pages that have already been
* instantiated within the map. The from and to elements are huge page
* indices into the associated mapping. from indicates the starting index
* of the region. to represents the first index past the end of the region.
*
* For example, a file region structure with from == 0 and to == 4 represents
* four huge pages in a mapping. It is important to note that the to element
* represents the first element past the end of the region. This is used in
* arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
*
* Interval notation of the form [from, to) will be used to indicate that
* the endpoint from is inclusive and to is exclusive.
*/
struct file_region {
struct list_head link;
long from;
long to;
#ifdef CONFIG_CGROUP_HUGETLB
/*
* On shared mappings, each reserved region appears as a struct
* file_region in resv_map. These fields hold the info needed to
* uncharge each reservation.
*/
struct page_counter *reservation_counter;
struct cgroup_subsys_state *css;
#endif
};
struct hugetlb_vma_lock {
struct kref refs;
struct rw_semaphore rw_sema;
struct vm_area_struct *vma;
};
extern struct resv_map *resv_map_alloc(void);
void resv_map_release(struct kref *ref);
extern spinlock_t hugetlb_lock;
extern int hugetlb_max_hstate __read_mostly;
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
long min_hpages);
void hugepage_put_subpool(struct hugepage_subpool *spool);
void hugetlb_dup_vma_private(struct vm_area_struct *vma);
void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
int move_hugetlb_page_tables(struct vm_area_struct *vma,
struct vm_area_struct *new_vma,
unsigned long old_addr, unsigned long new_addr,
unsigned long len);
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
struct vm_area_struct *, struct vm_area_struct *);
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *,
zap_flags_t);
void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page, zap_flags_t zap_flags);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(char *buf, int len, int nid);
void hugetlb_show_meminfo_node(int nid);
unsigned long hugetlb_total_pages(void);
vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags);
#ifdef CONFIG_USERFAULTFD
int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
uffd_flags_t flags,
struct folio **foliop);
#endif /* CONFIG_USERFAULTFD */
bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
struct vm_area_struct *vma,
vm_flags_t vm_flags);
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed);
bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list);
int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison);
int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared);
void folio_putback_hugetlb(struct folio *folio);
void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
void hugetlb_fix_reserve_counts(struct inode *inode);
extern struct mutex *hugetlb_fault_mutex_table;
u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pud_t *pud);
bool hugetlbfs_pagecache_present(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address);
struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio);
extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages[MAX_NUMNODES];
void hugetlb_bootmem_alloc(void);
bool hugetlb_bootmem_allocated(void);
/* arch callbacks */
#ifndef CONFIG_HIGHPTE
/*
* pte_offset_huge() and pte_alloc_huge() are helpers for those architectures
* which may go down to the lowest PTE level in their huge_pte_offset() and
* huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap().
*/
static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address)
{ return pte_offset_kernel(pmd, address);
}
static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd,
unsigned long address)
{
return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address);
}
#endif
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz);
/*
* huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE.
* Returns the pte_t* if found, or NULL if the address is not mapped.
*
* IMPORTANT: we should normally not directly call this function, instead
* this is only a common interface to implement arch-specific
* walker. Please use hugetlb_walk() instead, because that will attempt to
* verify the locking for you.
*
* Since this function will walk all the pgtable pages (including not only
* high-level pgtable page, but also PUD entry that can be unshared
* concurrently for VM_SHARED), the caller of this function should be
* responsible of its thread safety. One can follow this rule:
*
* (1) For private mappings: pmd unsharing is not possible, so holding the
* mmap_lock for either read or write is sufficient. Most callers
* already hold the mmap_lock, so normally, no special action is
* required.
*
* (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged
* pgtable page can go away from under us! It can be done by a pmd
* unshare with a follow up munmap() on the other process), then we
* need either:
*
* (2.1) hugetlb vma lock read or write held, to make sure pmd unshare
* won't happen upon the range (it also makes sure the pte_t we
* read is the right and stable one), or,
*
* (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make
* sure even if unshare happened the racy unmap() will wait until
* i_mmap_rwsem is released.
*
* Option (2.1) is the safest, which guarantees pte stability from pmd
* sharing pov, until the vma lock released. Option (2.2) doesn't protect
* a concurrent pmd unshare, but it makes sure the pgtable page is safe to
* access.
*/
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
unsigned long hugetlb_mask_last_page(struct hstate *h);
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end);
extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
unsigned long *begin, unsigned long *end);
extern void __hugetlb_zap_end(struct vm_area_struct *vma,
struct zap_details *details);
static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end);
}
static inline void hugetlb_zap_end(struct vm_area_struct *vma,
struct zap_details *details)
{
if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details);
}
void hugetlb_vma_lock_read(struct vm_area_struct *vma);
void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
void hugetlb_vma_lock_write(struct vm_area_struct *vma);
void hugetlb_vma_unlock_write(struct vm_area_struct *vma);
int hugetlb_vma_trylock_write(struct vm_area_struct *vma);
void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
void hugetlb_vma_lock_release(struct kref *kref);
long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot,
unsigned long cp_flags);
bool is_hugetlb_entry_migration(pte_t pte);
bool is_hugetlb_entry_hwpoisoned(pte_t pte);
void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
#else /* !CONFIG_HUGETLB_PAGE */
static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma)
{
}
static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
static inline unsigned long hugetlb_total_pages(void)
{
return 0;
}
static inline struct address_space *hugetlb_folio_mapping_lock_write(
struct folio *folio)
{
return NULL;
}
static inline int huge_pmd_unshare(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
return 0;
}
static inline void adjust_range_if_pmd_sharing_possible(
struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
}
static inline void hugetlb_zap_begin(
struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
}
static inline void hugetlb_zap_end(
struct vm_area_struct *vma,
struct zap_details *details)
{
}
static inline int copy_hugetlb_page_range(struct mm_struct *dst,
struct mm_struct *src,
struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma)
{
BUG();
return 0;
}
static inline int move_hugetlb_page_tables(struct vm_area_struct *vma,
struct vm_area_struct *new_vma,
unsigned long old_addr,
unsigned long new_addr,
unsigned long len)
{
BUG();
return 0;
}
static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}
static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid)
{
return 0;
}
static inline void hugetlb_show_meminfo_node(int nid)
{
}
static inline int prepare_hugepage_range(struct file *file,
unsigned long addr, unsigned long len)
{
return -EINVAL;
}
static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
{
}
static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
{
}
static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma)
{
}
static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
{
}
static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
{
return 1;
}
static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
{
}
static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr, unsigned long len)
{
return 0;
}
static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
BUG();
}
#ifdef CONFIG_USERFAULTFD
static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
uffd_flags_t flags,
struct folio **foliop)
{
BUG();
return 0;
}
#endif /* CONFIG_USERFAULTFD */
static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
unsigned long sz)
{
return NULL;
}
static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list)
{
return false;
}
static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison)
{
return 0;
}
static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared)
{
return 0;
}
static inline void folio_putback_hugetlb(struct folio *folio)
{
}
static inline void move_hugetlb_state(struct folio *old_folio,
struct folio *new_folio, int reason)
{
}
static inline long hugetlb_change_protection(
struct vm_area_struct *vma, unsigned long address,
unsigned long end, pgprot_t newprot,
unsigned long cp_flags)
{
return 0;
}
static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page,
zap_flags_t zap_flags)
{
BUG();
}
static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
unsigned int flags)
{
BUG();
return 0;
}
static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { }
#endif /* !CONFIG_HUGETLB_PAGE */
#ifndef pgd_write
static inline int pgd_write(pgd_t pgd)
{
BUG();
return 0;
}
#endif
#define HUGETLB_ANON_FILE "anon_hugepage"
enum {
/*
* The file will be used as an shm file so shmfs accounting rules
* apply
*/
HUGETLB_SHMFS_INODE = 1,
/*
* The file is being created on the internal vfs mount and shmfs
* accounting rules do not apply
*/
HUGETLB_ANONHUGE_INODE = 2,
};
#ifdef CONFIG_HUGETLBFS
struct hugetlbfs_sb_info {
long max_inodes; /* inodes allowed */
long free_inodes; /* inodes free */
spinlock_t stat_lock;
struct hstate *hstate;
struct hugepage_subpool *spool;
kuid_t uid;
kgid_t gid;
umode_t mode;
};
static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
struct hugetlbfs_inode_info {
struct inode vfs_inode;
unsigned int seals;
};
static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
{
return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
}
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
int creat_flags, int page_size_log);
static inline bool is_file_hugepages(const struct file *file)
{
return file->f_op->fop_flags & FOP_HUGE_PAGES;
}
static inline struct hstate *hstate_inode(struct inode *i)
{
return HUGETLBFS_SB(i->i_sb)->hstate;
}
#else /* !CONFIG_HUGETLBFS */
#define is_file_hugepages(file) false
static inline struct file *
hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
int creat_flags, int page_size_log)
{
return ERR_PTR(-ENOSYS);
}
static inline struct hstate *hstate_inode(struct inode *i)
{
return NULL;
}
#endif /* !CONFIG_HUGETLBFS */
unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
/*
* huegtlb page specific state flags. These flags are located in page.private
* of the hugetlb head page. Functions created via the below macros should be
* used to manipulate these flags.
*
* HPG_restore_reserve - Set when a hugetlb page consumes a reservation at
* allocation time. Cleared when page is fully instantiated. Free
* routine checks flag to restore a reservation on error paths.
* Synchronization: Examined or modified by code that knows it has
* the only reference to page. i.e. After allocation but before use
* or when the page is being freed.
* HPG_migratable - Set after a newly allocated page is added to the page
* cache and/or page tables. Indicates the page is a candidate for
* migration.
* Synchronization: Initially set after new page allocation with no
* locking. When examined and modified during migration processing
* (isolate, migrate, putback) the hugetlb_lock is held.
* HPG_temporary - Set on a page that is temporarily allocated from the buddy
* allocator. Typically used for migration target pages when no pages
* are available in the pool. The hugetlb free page path will
* immediately free pages with this flag set to the buddy allocator.
* Synchronization: Can be set after huge page allocation from buddy when
* code knows it has only reference. All other examinations and
* modifications require hugetlb_lock.
* HPG_freed - Set when page is on the free lists.
* Synchronization: hugetlb_lock held for examination and modification.
* HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed.
* HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page
* that is not tracked by raw_hwp_page list.
*/
enum hugetlb_page_flags {
HPG_restore_reserve = 0,
HPG_migratable,
HPG_temporary,
HPG_freed,
HPG_vmemmap_optimized,
HPG_raw_hwp_unreliable,
HPG_cma,
__NR_HPAGEFLAGS,
};
/*
* Macros to create test, set and clear function definitions for
* hugetlb specific page flags.
*/
#ifdef CONFIG_HUGETLB_PAGE
#define TESTHPAGEFLAG(uname, flname) \
static __always_inline \
bool folio_test_hugetlb_##flname(struct folio *folio) \
{ void *private = &folio->private; \
return test_bit(HPG_##flname, private); \
}
#define SETHPAGEFLAG(uname, flname) \
static __always_inline \
void folio_set_hugetlb_##flname(struct folio *folio) \
{ void *private = &folio->private; \
set_bit(HPG_##flname, private); \
}
#define CLEARHPAGEFLAG(uname, flname) \
static __always_inline \
void folio_clear_hugetlb_##flname(struct folio *folio) \
{ void *private = &folio->private; \
clear_bit(HPG_##flname, private); \
}
#else
#define TESTHPAGEFLAG(uname, flname) \
static inline bool \
folio_test_hugetlb_##flname(struct folio *folio) \
{ return 0; }
#define SETHPAGEFLAG(uname, flname) \
static inline void \
folio_set_hugetlb_##flname(struct folio *folio) \
{ }
#define CLEARHPAGEFLAG(uname, flname) \
static inline void \
folio_clear_hugetlb_##flname(struct folio *folio) \
{ }
#endif
#define HPAGEFLAG(uname, flname) \
TESTHPAGEFLAG(uname, flname) \
SETHPAGEFLAG(uname, flname) \
CLEARHPAGEFLAG(uname, flname) \
/*
* Create functions associated with hugetlb page flags
*/
HPAGEFLAG(RestoreReserve, restore_reserve)HPAGEFLAG(Migratable, migratable)HPAGEFLAG(Temporary, temporary)
HPAGEFLAG(Freed, freed)
HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
HPAGEFLAG(Cma, cma)
#ifdef CONFIG_HUGETLB_PAGE
#define HSTATE_NAME_LEN 32
/* Defines one hugetlb page size */
struct hstate {
struct mutex resize_lock;
struct lock_class_key resize_key;
int next_nid_to_alloc;
int next_nid_to_free;
unsigned int order;
unsigned int demote_order;
unsigned long mask;
unsigned long max_huge_pages;
unsigned long nr_huge_pages;
unsigned long free_huge_pages;
unsigned long resv_huge_pages;
unsigned long surplus_huge_pages;
unsigned long nr_overcommit_huge_pages;
struct list_head hugepage_activelist;
struct list_head hugepage_freelists[MAX_NUMNODES];
unsigned int max_huge_pages_node[MAX_NUMNODES];
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
char name[HSTATE_NAME_LEN];
};
struct cma;
struct huge_bootmem_page {
struct list_head list;
struct hstate *hstate;
unsigned long flags;
struct cma *cma;
};
#define HUGE_BOOTMEM_HVO 0x0001
#define HUGE_BOOTMEM_ZONES_VALID 0x0002
#define HUGE_BOOTMEM_CMA 0x0004
bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m);
int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
void wait_for_freed_hugetlb_folios(void);
struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, bool cow_from_owner);
struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask,
bool allow_alloc_fallback);
struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask);
int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
pgoff_t idx);
void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
unsigned long address, struct folio *folio);
/* arch callback */
int __init __alloc_bootmem_huge_page(struct hstate *h, int nid);
int __init alloc_bootmem_huge_page(struct hstate *h, int nid);
bool __init hugetlb_node_alloc_supported(void);
void __init hugetlb_add_hstate(unsigned order);
bool __init arch_hugetlb_valid_size(unsigned long size);
struct hstate *size_to_hstate(unsigned long size);
#ifndef HUGE_MAX_HSTATE
#define HUGE_MAX_HSTATE 1
#endif
extern struct hstate hstates[HUGE_MAX_HSTATE];
extern unsigned int default_hstate_idx;
#define default_hstate (hstates[default_hstate_idx])
static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
{
return folio->_hugetlb_subpool;
}
static inline void hugetlb_set_folio_subpool(struct folio *folio,
struct hugepage_subpool *subpool)
{
folio->_hugetlb_subpool = subpool;
}
static inline struct hstate *hstate_file(struct file *f)
{
return hstate_inode(file_inode(f));
}
static inline struct hstate *hstate_sizelog(int page_size_log)
{
if (!page_size_log)
return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log);
return NULL;
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return hstate_file(vma->vm_file);
}
static inline unsigned long huge_page_size(const struct hstate *h)
{
return (unsigned long)PAGE_SIZE << h->order;
}
extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma);
extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma);
static inline unsigned long huge_page_mask(struct hstate *h)
{
return h->mask;
}
static inline unsigned int huge_page_order(struct hstate *h)
{
return h->order;
}
static inline unsigned huge_page_shift(struct hstate *h)
{
return h->order + PAGE_SHIFT;
}
static inline bool hstate_is_gigantic(struct hstate *h)
{
return huge_page_order(h) > MAX_PAGE_ORDER;
}
static inline unsigned int pages_per_huge_page(const struct hstate *h)
{
return 1 << h->order;
}
static inline unsigned int blocks_per_huge_page(struct hstate *h)
{
return huge_page_size(h) / 512;
}
static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
struct address_space *mapping, pgoff_t idx)
{
return filemap_lock_folio(mapping, idx << huge_page_order(h));
}
#include <asm/hugetlb.h>
#ifndef is_hugepage_only_range
static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr, unsigned long len)
{
return 0;
}
#define is_hugepage_only_range is_hugepage_only_range
#endif
#ifndef arch_clear_hugetlb_flags
static inline void arch_clear_hugetlb_flags(struct folio *folio) { }
#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
#endif
#ifndef arch_make_huge_pte
static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
vm_flags_t flags)
{
return pte_mkhuge(entry);
}
#endif
#ifndef arch_has_huge_bootmem_alloc
/*
* Some architectures do their own bootmem allocation, so they can't use
* early CMA allocation.
*/
static inline bool arch_has_huge_bootmem_alloc(void)
{
return false;
}
#endif
static inline struct hstate *folio_hstate(struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
return size_to_hstate(folio_size(folio));
}
static inline unsigned hstate_index_to_shift(unsigned index)
{
return hstates[index].order + PAGE_SHIFT;
}
static inline int hstate_index(struct hstate *h)
{
return h - hstates;
}
int dissolve_free_hugetlb_folio(struct folio *folio);
int dissolve_free_hugetlb_folios(unsigned long start_pfn,
unsigned long end_pfn);
#ifdef CONFIG_MEMORY_FAILURE
extern void folio_clear_hugetlb_hwpoison(struct folio *folio);
#else
static inline void folio_clear_hugetlb_hwpoison(struct folio *folio)
{
}
#endif
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
#ifndef arch_hugetlb_migration_supported
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
if ((huge_page_shift(h) == PMD_SHIFT) ||
(huge_page_shift(h) == PUD_SHIFT) ||
(huge_page_shift(h) == PGDIR_SHIFT))
return true;
else
return false;
}
#endif
#else
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
return false;
}
#endif
static inline bool hugepage_migration_supported(struct hstate *h)
{
return arch_hugetlb_migration_supported(h);
}
/*
* Movability check is different as compared to migration check.
* It determines whether or not a huge page should be placed on
* movable zone or not. Movability of any huge page should be
* required only if huge page size is supported for migration.
* There won't be any reason for the huge page to be movable if
* it is not migratable to start with. Also the size of the huge
* page should be large enough to be placed under a movable zone
* and still feasible enough to be migratable. Just the presence
* in movable zone does not make the migration feasible.
*
* So even though large huge page sizes like the gigantic ones
* are migratable they should not be movable because its not
* feasible to migrate them from movable zone.
*/
static inline bool hugepage_movable_supported(struct hstate *h)
{
if (!hugepage_migration_supported(h))
return false;
if (hstate_is_gigantic(h))
return false;
return true;
}
/* Movability of hugepages depends on migration support. */
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
gfp_t gfp = __GFP_COMP | __GFP_NOWARN;
gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER;
return gfp;
}
static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
{
gfp_t modified_mask = htlb_alloc_mask(h);
/* Some callers might want to enforce node */
modified_mask |= (gfp_mask & __GFP_THISNODE);
modified_mask |= (gfp_mask & __GFP_NOWARN);
return modified_mask;
}
static inline bool htlb_allow_alloc_fallback(int reason)
{
bool allowed_fallback = false;
/*
* Note: the memory offline, memory failure and migration syscalls will
* be allowed to fallback to other nodes due to lack of a better chioce,
* that might break the per-node hugetlb pool. While other cases will
* set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool.
*/
switch (reason) {
case MR_MEMORY_HOTPLUG:
case MR_MEMORY_FAILURE:
case MR_SYSCALL:
case MR_MEMPOLICY_MBIND:
allowed_fallback = true;
break;
default:
break;
}
return allowed_fallback;
}
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
const unsigned long size = huge_page_size(h);
VM_WARN_ON(size == PAGE_SIZE);
/*
* hugetlb must use the exact same PT locks as core-mm page table
* walkers would. When modifying a PTE table, hugetlb must take the
* PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
* PT lock etc.
*
* The expectation is that any hugetlb folio smaller than a PMD is
* always mapped into a single PTE table and that any hugetlb folio
* smaller than a PUD (but at least as big as a PMD) is always mapped
* into a single PMD table.
*
* If that does not hold for an architecture, then that architecture
* must disable split PT locks such that all *_lockptr() functions
* will give us the same result: the per-MM PT lock.
*
* Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
* PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
* and core-mm would use pmd_lockptr(). However, in such configurations
* split PMD locks are disabled -- they don't make sense on a single
* PGDIR page table -- and the end result is the same.
*/
if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte);
/* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
return ptep_lockptr(mm, pte);
}
#ifndef hugepages_supported
/*
* Some platform decide whether they support huge pages at boot
* time. Some of them, such as powerpc, set HPAGE_SHIFT to 0
* when there is no such support
*/
#define hugepages_supported() (HPAGE_SHIFT != 0)
#endif
void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
static inline void hugetlb_count_init(struct mm_struct *mm)
{
atomic_long_set(&mm->hugetlb_usage, 0);
}
static inline void hugetlb_count_add(long l, struct mm_struct *mm)
{
atomic_long_add(l, &mm->hugetlb_usage);
}
static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
{
atomic_long_sub(l, &mm->hugetlb_usage);
}
#ifndef huge_ptep_modify_prot_start
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
unsigned long psize = huge_page_size(hstate_vma(vma));
return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
}
#endif
#ifndef huge_ptep_modify_prot_commit
#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
unsigned long psize = huge_page_size(hstate_vma(vma));
set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
#endif
#ifdef CONFIG_NUMA
void hugetlb_register_node(struct node *node);
void hugetlb_unregister_node(struct node *node);
#endif
/*
* Check if a given raw @page in a hugepage is HWPOISON.
*/
bool is_raw_hwpoison_page_in_hugepage(struct page *page);
static inline unsigned long huge_page_mask_align(struct file *file)
{
return PAGE_MASK & ~huge_page_mask(hstate_file(file));
}
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
static inline unsigned long huge_page_mask_align(struct file *file)
{
return 0;
}
static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
{
return NULL;
}
static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
struct address_space *mapping, pgoff_t idx)
{
return NULL;
}
static inline int isolate_or_dissolve_huge_page(struct page *page,
struct list_head *list)
{
return -ENOMEM;
}
static inline int replace_free_hugepage_folios(unsigned long start_pfn,
unsigned long end_pfn)
{
return 0;
}
static inline void wait_for_freed_hugetlb_folios(void)
{
}
static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr,
bool cow_from_owner)
{
return NULL;
}
static inline struct folio *
alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask)
{
return NULL;
}
static inline struct folio *
alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask,
bool allow_alloc_fallback)
{
return NULL;
}
static inline int __alloc_bootmem_huge_page(struct hstate *h)
{
return 0;
}
static inline struct hstate *hstate_file(struct file *f)
{
return NULL;
}
static inline struct hstate *hstate_sizelog(int page_size_log)
{
return NULL;
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return NULL;
}
static inline struct hstate *folio_hstate(struct folio *folio)
{
return NULL;
}
static inline struct hstate *size_to_hstate(unsigned long size)
{
return NULL;
}
static inline unsigned long huge_page_size(struct hstate *h)
{
return PAGE_SIZE;
}
static inline unsigned long huge_page_mask(struct hstate *h)
{
return PAGE_MASK;
}
static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
return PAGE_SIZE;
}
static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
return PAGE_SIZE;
}
static inline unsigned int huge_page_order(struct hstate *h)
{
return 0;
}
static inline unsigned int huge_page_shift(struct hstate *h)
{
return PAGE_SHIFT;
}
static inline bool hstate_is_gigantic(struct hstate *h)
{
return false;
}
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1;
}
static inline unsigned hstate_index_to_shift(unsigned index)
{
return 0;
}
static inline int hstate_index(struct hstate *h)
{
return 0;
}
static inline int dissolve_free_hugetlb_folio(struct folio *folio)
{
return 0;
}
static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn,
unsigned long end_pfn)
{
return 0;
}
static inline bool hugepage_migration_supported(struct hstate *h)
{
return false;
}
static inline bool hugepage_movable_supported(struct hstate *h)
{
return false;
}
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
return 0;
}
static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
{
return 0;
}
static inline bool htlb_allow_alloc_fallback(int reason)
{
return false;
}
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
return &mm->page_table_lock;
}
static inline void hugetlb_count_init(struct mm_struct *mm)
{
}
static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
{
}
static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
{
}
static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
#ifdef CONFIG_MMU
return ptep_get(ptep);
#else
return *ptep;
#endif
}
static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, unsigned long sz)
{
}
static inline void hugetlb_register_node(struct node *node)
{
}
static inline void hugetlb_unregister_node(struct node *node)
{
}
static inline bool hugetlbfs_pagecache_present(
struct hstate *h, struct vm_area_struct *vma, unsigned long address)
{
return false;
}
static inline void hugetlb_bootmem_alloc(void)
{
}
static inline bool hugetlb_bootmem_allocated(void)
{
return false;
}
#endif /* CONFIG_HUGETLB_PAGE */
static inline spinlock_t *huge_pte_lock(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
spinlock_t *ptl;
ptl = huge_pte_lockptr(h, mm, pte);
spin_lock(ptl);
return ptl;
}
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
extern void __init hugetlb_cma_reserve(int order);
#else
static inline __init void hugetlb_cma_reserve(int order)
{
}
#endif
#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
static inline bool hugetlb_pmd_shared(pte_t *pte)
{
return page_count(virt_to_page(pte)) > 1;
}
#else
static inline bool hugetlb_pmd_shared(pte_t *pte)
{
return false;
}
#endif
bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
/*
* ARCHes with special requirements for evicting HUGETLB backing TLB entries can
* implement this.
*/
#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#endif
static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
{
return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
}
bool __vma_private_lock(struct vm_area_struct *vma);
/*
* Safe version of huge_pte_offset() to check the locks. See comments
* above huge_pte_offset().
*/
static inline pte_t *
hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
{
#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP)
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
/*
* If pmd sharing possible, locking needed to safely walk the
* hugetlb pgtables. More information can be found at the comment
* above huge_pte_offset() in the same file.
*
* NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP.
*/
if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
!lockdep_is_held(
&vma->vm_file->f_mapping->i_mmap_rwsem));
#endif
return huge_pte_offset(vma->vm_mm, addr, sz);
}
#endif /* _LINUX_HUGETLB_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_TIMEKEEPING_H
#define _LINUX_TIMEKEEPING_H
#include <linux/errno.h>
#include <linux/clocksource_ids.h>
#include <linux/ktime.h>
/* Included from linux/ktime.h */
void timekeeping_init(void);
extern int timekeeping_suspended;
/* Architecture timer tick functions: */
extern void legacy_timer_tick(unsigned long ticks);
/*
* Get and set timeofday
*/
extern int do_settimeofday64(const struct timespec64 *ts);
extern int do_sys_settimeofday64(const struct timespec64 *tv,
const struct timezone *tz);
/*
* ktime_get() family - read the current time in a multitude of ways.
*
* The default time reference is CLOCK_MONOTONIC, starting at
* boot time but not counting the time spent in suspend.
* For other references, use the functions with "real", "clocktai",
* "boottime" and "raw" suffixes.
*
* To get the time in a different format, use the ones with
* "ns", "ts64" and "seconds" suffix.
*
* See Documentation/core-api/timekeeping.rst for more details.
*/
/*
* timespec64 based interfaces
*/
extern void ktime_get_raw_ts64(struct timespec64 *ts);
extern void ktime_get_ts64(struct timespec64 *ts);
extern void ktime_get_real_ts64(struct timespec64 *tv);
extern void ktime_get_coarse_ts64(struct timespec64 *ts);
extern void ktime_get_coarse_real_ts64(struct timespec64 *ts);
/* Multigrain timestamp interfaces */
extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts);
extern void ktime_get_real_ts64_mg(struct timespec64 *ts);
extern unsigned long timekeeping_get_mg_floor_swaps(void);
void getboottime64(struct timespec64 *ts);
/*
* time64_t base interfaces
*/
extern time64_t ktime_get_seconds(void);
extern time64_t __ktime_get_real_seconds(void);
extern time64_t ktime_get_real_seconds(void);
/*
* ktime_t based interfaces
*/
enum tk_offsets {
TK_OFFS_REAL,
TK_OFFS_BOOT,
TK_OFFS_TAI,
TK_OFFS_MAX,
};
extern ktime_t ktime_get(void);
extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs);
extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
extern ktime_t ktime_get_raw(void);
extern u32 ktime_get_resolution_ns(void);
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
*
* Returns: real (wall) time in ktime_t format
*/
static inline ktime_t ktime_get_real(void)
{
return ktime_get_with_offset(TK_OFFS_REAL);
}
static inline ktime_t ktime_get_coarse_real(void)
{
return ktime_get_coarse_with_offset(TK_OFFS_REAL);
}
/**
* ktime_get_boottime - Get monotonic time since boot in ktime_t format
*
* This is similar to CLOCK_MONTONIC/ktime_get, but also includes the
* time spent in suspend.
*
* Returns: monotonic time since boot in ktime_t format
*/
static inline ktime_t ktime_get_boottime(void)
{
return ktime_get_with_offset(TK_OFFS_BOOT);
}
static inline ktime_t ktime_get_coarse_boottime(void)
{
return ktime_get_coarse_with_offset(TK_OFFS_BOOT);
}
/**
* ktime_get_clocktai - Get the TAI time of day in ktime_t format
*
* Returns: the TAI time of day in ktime_t format
*/
static inline ktime_t ktime_get_clocktai(void)
{
return ktime_get_with_offset(TK_OFFS_TAI);
}
static inline ktime_t ktime_get_coarse_clocktai(void)
{
return ktime_get_coarse_with_offset(TK_OFFS_TAI);
}
static inline ktime_t ktime_get_coarse(void)
{
struct timespec64 ts;
ktime_get_coarse_ts64(&ts);
return timespec64_to_ktime(ts);
}
static inline u64 ktime_get_coarse_ns(void)
{
return ktime_to_ns(ktime_get_coarse());
}
static inline u64 ktime_get_coarse_real_ns(void)
{
return ktime_to_ns(ktime_get_coarse_real());
}
static inline u64 ktime_get_coarse_boottime_ns(void)
{
return ktime_to_ns(ktime_get_coarse_boottime());
}
static inline u64 ktime_get_coarse_clocktai_ns(void)
{
return ktime_to_ns(ktime_get_coarse_clocktai());
}
/**
* ktime_mono_to_real - Convert monotonic time to clock realtime
* @mono: monotonic time to convert
*
* Returns: time converted to realtime clock
*/
static inline ktime_t ktime_mono_to_real(ktime_t mono)
{
return ktime_mono_to_any(mono, TK_OFFS_REAL);
}
/**
* ktime_get_ns - Get the current time in nanoseconds
*
* Returns: current time converted to nanoseconds
*/
static inline u64 ktime_get_ns(void)
{
return ktime_to_ns(ktime_get());
}
/**
* ktime_get_real_ns - Get the current real/wall time in nanoseconds
*
* Returns: current real time converted to nanoseconds
*/
static inline u64 ktime_get_real_ns(void)
{
return ktime_to_ns(ktime_get_real());
}
/**
* ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds
*
* Returns: current boottime converted to nanoseconds
*/
static inline u64 ktime_get_boottime_ns(void)
{
return ktime_to_ns(ktime_get_boottime());
}
/**
* ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds
*
* Returns: current TAI time converted to nanoseconds
*/
static inline u64 ktime_get_clocktai_ns(void)
{
return ktime_to_ns(ktime_get_clocktai());
}
/**
* ktime_get_raw_ns - Get the raw monotonic time in nanoseconds
*
* Returns: current raw monotonic time converted to nanoseconds
*/
static inline u64 ktime_get_raw_ns(void)
{
return ktime_to_ns(ktime_get_raw());
}
extern u64 ktime_get_mono_fast_ns(void);
extern u64 ktime_get_raw_fast_ns(void);
extern u64 ktime_get_boot_fast_ns(void);
extern u64 ktime_get_tai_fast_ns(void);
extern u64 ktime_get_real_fast_ns(void);
/*
* timespec64/time64_t interfaces utilizing the ktime based ones
* for API completeness, these could be implemented more efficiently
* if needed.
*/
static inline void ktime_get_boottime_ts64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_boottime());
}
static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_coarse_boottime());
}
static inline time64_t ktime_get_boottime_seconds(void)
{
return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC);
}
static inline void ktime_get_clocktai_ts64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_clocktai());
}
static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_coarse_clocktai());
}
static inline time64_t ktime_get_clocktai_seconds(void)
{
return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC);
}
/*
* RTC specific
*/
extern bool timekeeping_rtc_skipsuspend(void);
extern bool timekeeping_rtc_skipresume(void);
extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
/**
* struct system_time_snapshot - simultaneous raw/real time capture with
* counter value
* @cycles: Clocksource counter value to produce the system times
* @real: Realtime system time
* @boot: Boot time
* @raw: Monotonic raw system time
* @cs_id: Clocksource ID
* @clock_was_set_seq: The sequence number of clock-was-set events
* @cs_was_changed_seq: The sequence number of clocksource change events
*/
struct system_time_snapshot {
u64 cycles;
ktime_t real;
ktime_t boot;
ktime_t raw;
enum clocksource_ids cs_id;
unsigned int clock_was_set_seq;
u8 cs_was_changed_seq;
};
/**
* struct system_device_crosststamp - system/device cross-timestamp
* (synchronized capture)
* @device: Device time
* @sys_realtime: Realtime simultaneous with device time
* @sys_monoraw: Monotonic raw simultaneous with device time
*/
struct system_device_crosststamp {
ktime_t device;
ktime_t sys_realtime;
ktime_t sys_monoraw;
};
/**
* struct system_counterval_t - system counter value with the ID of the
* corresponding clocksource
* @cycles: System counter value
* @cs_id: Clocksource ID corresponding to system counter value. Used by
* timekeeping code to verify comparability of two cycle values.
* The default ID, CSID_GENERIC, does not identify a specific
* clocksource.
* @use_nsecs: @cycles is in nanoseconds.
*/
struct system_counterval_t {
u64 cycles;
enum clocksource_ids cs_id;
bool use_nsecs;
};
extern bool ktime_real_to_base_clock(ktime_t treal,
enum clocksource_ids base_id, u64 *cycles);
extern bool timekeeping_clocksource_has_base(enum clocksource_ids id);
/*
* Get cross timestamp between system clock and device clock
*/
extern int get_device_system_crosststamp(
int (*get_time_fn)(ktime_t *device_time,
struct system_counterval_t *system_counterval,
void *ctx),
void *ctx,
struct system_time_snapshot *history,
struct system_device_crosststamp *xtstamp);
/*
* Simultaneously snapshot realtime and monotonic raw clocks
*/
extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
/*
* Persistent clock related interfaces
*/
extern int persistent_clock_is_local;
extern void read_persistent_clock64(struct timespec64 *ts);
void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock,
struct timespec64 *boot_offset);
#ifdef CONFIG_GENERIC_CMOS_UPDATE
extern int update_persistent_clock64(struct timespec64 now);
#endif
#endif
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* internal.h - printk internal definitions
*/
#include <linux/console.h>
#include <linux/percpu.h>
#include <linux/types.h>
#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
struct ctl_table;
void __init printk_sysctl_init(void);
int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
#else
#define printk_sysctl_init() do { } while (0)
#endif
#define con_printk(lvl, con, fmt, ...) \
printk(lvl pr_fmt("%s%sconsole [%s%d] " fmt), \
(con->flags & CON_NBCON) ? "" : "legacy ", \
(con->flags & CON_BOOT) ? "boot" : "", \
con->name, con->index, ##__VA_ARGS__)
/*
* Identify if legacy printing is forced in a dedicated kthread. If
* true, all printing via console lock occurs within a dedicated
* legacy printer thread. The only exception is on panic, after the
* nbcon consoles have had their chance to print the panic messages
* first.
*/
#ifdef CONFIG_PREEMPT_RT
# define force_legacy_kthread() (true)
#else
# define force_legacy_kthread() (false)
#endif
#ifdef CONFIG_PRINTK
#ifdef CONFIG_PRINTK_CALLER
#define PRINTK_PREFIX_MAX 48
#else
#define PRINTK_PREFIX_MAX 32
#endif
/*
* the maximum size of a formatted record (i.e. with prefix added
* per line and dropped messages or in extended message format)
*/
#define PRINTK_MESSAGE_MAX 2048
/* the maximum size allowed to be reserved for a record */
#define PRINTKRB_RECORD_MAX 1024
/* Flags for a single printk record. */
enum printk_info_flags {
/* always show on console, ignore console_loglevel */
LOG_FORCE_CON = 1,
LOG_NEWLINE = 2, /* text ended with a newline */
LOG_CONT = 8, /* text is a fragment of a continuation line */
};
struct printk_ringbuffer;
struct dev_printk_info;
extern struct printk_ringbuffer *prb;
extern bool printk_kthreads_running;
extern bool debug_non_panic_cpus;
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args);
__printf(1, 0) int vprintk_default(const char *fmt, va_list args);
__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
void __printk_safe_enter(void);
void __printk_safe_exit(void);
bool printk_percpu_data_ready(void);
#define printk_safe_enter_irqsave(flags) \
do { \
local_irq_save(flags); \
__printk_safe_enter(); \
} while (0)
#define printk_safe_exit_irqrestore(flags) \
do { \
__printk_safe_exit(); \
local_irq_restore(flags); \
} while (0)
void defer_console_output(void);
bool is_printk_legacy_deferred(void);
bool is_printk_force_console(void);
u16 printk_parse_prefix(const char *text, int *level,
enum printk_info_flags *flags);
void console_lock_spinning_enable(void);
int console_lock_spinning_disable_and_check(int cookie);
u64 nbcon_seq_read(struct console *con);
void nbcon_seq_force(struct console *con, u64 seq);
bool nbcon_alloc(struct console *con);
void nbcon_free(struct console *con);
enum nbcon_prio nbcon_get_default_prio(void);
void nbcon_atomic_flush_pending(void);
bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
int cookie, bool use_atomic);
bool nbcon_kthread_create(struct console *con);
void nbcon_kthread_stop(struct console *con);
void nbcon_kthreads_wake(void);
/*
* Check if the given console is currently capable and allowed to print
* records. Note that this function does not consider the current context,
* which can also play a role in deciding if @con can be used to print
* records.
*/
static inline bool console_is_usable(struct console *con, short flags, bool use_atomic)
{
if (!(flags & CON_ENABLED))
return false;
if ((flags & CON_SUSPENDED))
return false;
if (flags & CON_NBCON) {
/* The write_atomic() callback is optional. */
if (use_atomic && !con->write_atomic)
return false;
/*
* For the !use_atomic case, @printk_kthreads_running is not
* checked because the write_thread() callback is also used
* via the legacy loop when the printer threads are not
* available.
*/
} else {
if (!con->write)
return false;
}
/*
* Console drivers may assume that per-cpu resources have been
* allocated. So unless they're explicitly marked as being able to
* cope (CON_ANYTIME) don't call them until this CPU is officially up.
*/
if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME))
return false;
return true;
}
/**
* nbcon_kthread_wake - Wake up a console printing thread
* @con: Console to operate on
*/
static inline void nbcon_kthread_wake(struct console *con)
{
/*
* Guarantee any new records can be seen by tasks preparing to wait
* before this context checks if the rcuwait is empty.
*
* The full memory barrier in rcuwait_wake_up() pairs with the full
* memory barrier within set_current_state() of
* ___rcuwait_wait_event(), which is called after prepare_to_rcuwait()
* adds the waiter but before it has checked the wait condition.
*
* This pairs with nbcon_kthread_func:A.
*/
rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */
}
#else
#define PRINTK_PREFIX_MAX 0
#define PRINTK_MESSAGE_MAX 0
#define PRINTKRB_RECORD_MAX 0
#define printk_kthreads_running (false)
/*
* In !PRINTK builds we still export console_sem
* semaphore and some of console functions (console_unlock()/etc.), so
* printk-safe must preserve the existing local IRQ guarantees.
*/
#define printk_safe_enter_irqsave(flags) local_irq_save(flags)
#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
static inline bool printk_percpu_data_ready(void) { return false; }
static inline void defer_console_output(void) { }
static inline bool is_printk_legacy_deferred(void) { return false; }
static inline u64 nbcon_seq_read(struct console *con) { return 0; }
static inline void nbcon_seq_force(struct console *con, u64 seq) { }
static inline bool nbcon_alloc(struct console *con) { return false; }
static inline void nbcon_free(struct console *con) { }
static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_NONE; }
static inline void nbcon_atomic_flush_pending(void) { }
static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
int cookie, bool use_atomic) { return false; }
static inline void nbcon_kthread_wake(struct console *con) { }
static inline void nbcon_kthreads_wake(void) { }
static inline bool console_is_usable(struct console *con, short flags,
bool use_atomic) { return false; }
#endif /* CONFIG_PRINTK */
extern bool have_boot_console;
extern bool have_nbcon_console;
extern bool have_legacy_console;
extern bool legacy_allow_panic_sync;
/**
* struct console_flush_type - Define available console flush methods
* @nbcon_atomic: Flush directly using nbcon_atomic() callback
* @nbcon_offload: Offload flush to printer thread
* @legacy_direct: Call the legacy loop in this context
* @legacy_offload: Offload the legacy loop into IRQ or legacy thread
*
* Note that the legacy loop also flushes the nbcon consoles.
*/
struct console_flush_type {
bool nbcon_atomic;
bool nbcon_offload;
bool legacy_direct;
bool legacy_offload;
};
/*
* Identify which console flushing methods should be used in the context of
* the caller.
*/
static inline void printk_get_console_flush_type(struct console_flush_type *ft)
{
memset(ft, 0, sizeof(*ft));
switch (nbcon_get_default_prio()) {
case NBCON_PRIO_NORMAL:
if (have_nbcon_console && !have_boot_console) {
if (printk_kthreads_running)
ft->nbcon_offload = true;
else
ft->nbcon_atomic = true;
}
/* Legacy consoles are flushed directly when possible. */
if (have_legacy_console || have_boot_console) {
if (!is_printk_legacy_deferred())
ft->legacy_direct = true;
else
ft->legacy_offload = true;
}
break;
case NBCON_PRIO_EMERGENCY:
if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true;
/* Legacy consoles are flushed directly when possible. */
if (have_legacy_console || have_boot_console) {
if (!is_printk_legacy_deferred())
ft->legacy_direct = true;
else
ft->legacy_offload = true;
}
break;
case NBCON_PRIO_PANIC:
/*
* In panic, the nbcon consoles will directly print. But
* only allowed if there are no boot consoles.
*/
if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; if (have_legacy_console || have_boot_console) {
/*
* This is the same decision as NBCON_PRIO_NORMAL
* except that offloading never occurs in panic.
*
* Note that console_flush_on_panic() will flush
* legacy consoles anyway, even if unsafe.
*/
if (!is_printk_legacy_deferred()) ft->legacy_direct = true;
/*
* In panic, if nbcon atomic printing occurs,
* the legacy consoles must remain silent until
* explicitly allowed.
*/
if (ft->nbcon_atomic && !legacy_allow_panic_sync) ft->legacy_direct = false;
}
break;
default:
WARN_ON_ONCE(1);
break;
}
}
extern struct printk_buffers printk_shared_pbufs;
/**
* struct printk_buffers - Buffers to read/format/output printk messages.
* @outbuf: After formatting, contains text to output.
* @scratchbuf: Used as temporary ringbuffer reading and string-print space.
*/
struct printk_buffers {
char outbuf[PRINTK_MESSAGE_MAX];
char scratchbuf[PRINTKRB_RECORD_MAX];
};
/**
* struct printk_message - Container for a prepared printk message.
* @pbufs: printk buffers used to prepare the message.
* @outbuf_len: The length of prepared text in @pbufs->outbuf to output. This
* does not count the terminator. A value of 0 means there is
* nothing to output and this record should be skipped.
* @seq: The sequence number of the record used for @pbufs->outbuf.
* @dropped: The number of dropped records from reading @seq.
*/
struct printk_message {
struct printk_buffers *pbufs;
unsigned int outbuf_len;
u64 seq;
unsigned long dropped;
};
bool other_cpu_in_panic(void);
bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
bool is_extended, bool may_supress);
#ifdef CONFIG_PRINTK
void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped);
void console_prepend_replay(struct printk_message *pmsg);
#endif
#ifdef CONFIG_SMP
bool is_printk_cpu_sync_owner(void);
#else
static inline bool is_printk_cpu_sync_owner(void) { return false; }
#endif
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Common arm64 stack unwinder code.
*
* See: arch/arm64/kernel/stacktrace.c for the reference implementation.
*
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_STACKTRACE_COMMON_H
#define __ASM_STACKTRACE_COMMON_H
#include <linux/types.h>
struct stack_info {
unsigned long low;
unsigned long high;
};
/**
* struct unwind_state - state used for robust unwinding.
*
* @fp: The fp value in the frame record (or the real fp)
* @pc: The lr value in the frame record (or the real lr)
*
* @stack: The stack currently being unwound.
* @stacks: An array of stacks which can be unwound.
* @nr_stacks: The number of stacks in @stacks.
*/
struct unwind_state {
unsigned long fp;
unsigned long pc;
struct stack_info stack;
struct stack_info *stacks;
int nr_stacks;
};
static inline struct stack_info stackinfo_get_unknown(void)
{
return (struct stack_info) {
.low = 0,
.high = 0,
};
}
static inline bool stackinfo_on_stack(const struct stack_info *info,
unsigned long sp, unsigned long size)
{
if (!info->low)
return false;
if (sp < info->low || sp + size < sp || sp + size > info->high)
return false;
return true;
}
static inline void unwind_init_common(struct unwind_state *state)
{
state->stack = stackinfo_get_unknown();
}
/**
* unwind_find_stack() - Find the accessible stack which entirely contains an
* object.
*
* @state: the current unwind state.
* @sp: the base address of the object.
* @size: the size of the object.
*
* Return: a pointer to the relevant stack_info if found; NULL otherwise.
*/
static struct stack_info *unwind_find_stack(struct unwind_state *state,
unsigned long sp,
unsigned long size)
{
struct stack_info *info = &state->stack;
if (stackinfo_on_stack(info, sp, size))
return info;
for (int i = 0; i < state->nr_stacks; i++) {
info = &state->stacks[i];
if (stackinfo_on_stack(info, sp, size))
return info;
}
return NULL;
}
/**
* unwind_consume_stack() - Update stack boundaries so that future unwind steps
* cannot consume this object again.
*
* @state: the current unwind state.
* @info: the stack_info of the stack containing the object.
* @sp: the base address of the object.
* @size: the size of the object.
*
* Return: 0 upon success, an error code otherwise.
*/
static inline void unwind_consume_stack(struct unwind_state *state,
struct stack_info *info,
unsigned long sp,
unsigned long size)
{
struct stack_info tmp;
/*
* Stack transitions are strictly one-way, and once we've
* transitioned from one stack to another, it's never valid to
* unwind back to the old stack.
*
* Destroy the old stack info so that it cannot be found upon a
* subsequent transition. If the stack has not changed, we'll
* immediately restore the current stack info.
*
* Note that stacks can nest in several valid orders, e.g.
*
* TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
* TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
* HYP -> OVERFLOW
*
* ... so we do not check the specific order of stack
* transitions.
*/
tmp = *info;
*info = stackinfo_get_unknown();
state->stack = tmp;
/*
* Future unwind steps can only consume stack above this frame record.
* Update the current stack to start immediately above it.
*/
state->stack.low = sp + size;
}
/**
* unwind_next_frame_record() - Unwind to the next frame record.
*
* @state: the current unwind state.
*
* Return: 0 upon success, an error code otherwise.
*/
static inline int
unwind_next_frame_record(struct unwind_state *state)
{
struct stack_info *info;
struct frame_record *record;
unsigned long fp = state->fp;
if (fp & 0x7)
return -EINVAL;
info = unwind_find_stack(state, fp, sizeof(*record));
if (!info)
return -EINVAL;
unwind_consume_stack(state, info, fp, sizeof(*record));
/*
* Record this frame record's values.
*/
record = (struct frame_record *)fp;
state->fp = READ_ONCE(record->fp);
state->pc = READ_ONCE(record->lr);
return 0;
}
#endif /* __ASM_STACKTRACE_COMMON_H */
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* kref.h - library routines for handling generic reference counted objects
*
* Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2004 IBM Corp.
*
* based on kobject.h which was:
* Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org>
* Copyright (C) 2002-2003 Open Source Development Labs
*/
#ifndef _KREF_H_
#define _KREF_H_
#include <linux/spinlock.h>
#include <linux/refcount.h>
struct kref {
refcount_t refcount;
};
#define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), }
/**
* kref_init - initialize object.
* @kref: object in question.
*/
static inline void kref_init(struct kref *kref)
{
refcount_set(&kref->refcount, 1);
}
static inline unsigned int kref_read(const struct kref *kref)
{
return refcount_read(&kref->refcount);
}
/**
* kref_get - increment refcount for object.
* @kref: object.
*/
static inline void kref_get(struct kref *kref)
{
refcount_inc(&kref->refcount);
}
/**
* kref_put - Decrement refcount for object
* @kref: Object
* @release: Pointer to the function that will clean up the object when the
* last reference to the object is released.
*
* Decrement the refcount, and if 0, call @release. The caller may not
* pass NULL or kfree() as the release function.
*
* Return: 1 if this call removed the object, otherwise return 0. Beware,
* if this function returns 0, another caller may have removed the object
* by the time this function returns. The return value is only certain
* if you want to see if the object is definitely released.
*/
static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
{
if (refcount_dec_and_test(&kref->refcount)) { release(kref);
return 1;
}
return 0;
}
/**
* kref_put_mutex - Decrement refcount for object
* @kref: Object
* @release: Pointer to the function that will clean up the object when the
* last reference to the object is released.
* @mutex: Mutex which protects the release function.
*
* This variant of kref_lock() calls the @release function with the @mutex
* held. The @release function will release the mutex.
*/
static inline int kref_put_mutex(struct kref *kref,
void (*release)(struct kref *kref),
struct mutex *mutex)
{
if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) {
release(kref);
return 1;
}
return 0;
}
/**
* kref_put_lock - Decrement refcount for object
* @kref: Object
* @release: Pointer to the function that will clean up the object when the
* last reference to the object is released.
* @lock: Spinlock which protects the release function.
*
* This variant of kref_lock() calls the @release function with the @lock
* held. The @release function will release the lock.
*/
static inline int kref_put_lock(struct kref *kref,
void (*release)(struct kref *kref),
spinlock_t *lock)
{
if (refcount_dec_and_lock(&kref->refcount, lock)) {
release(kref);
return 1;
}
return 0;
}
/**
* kref_get_unless_zero - Increment refcount for object unless it is zero.
* @kref: object.
*
* This function is intended to simplify locking around refcounting for
* objects that can be looked up from a lookup structure, and which are
* removed from that lookup structure in the object destructor.
* Operations on such objects require at least a read lock around
* lookup + kref_get, and a write lock around kref_put + remove from lookup
* structure. Furthermore, RCU implementations become extremely tricky.
* With a lookup followed by a kref_get_unless_zero *with return value check*
* locking in the kref_put path can be deferred to the actual removal from
* the lookup structure and RCU lookups become trivial.
*
* Return: non-zero if the increment succeeded. Otherwise return 0.
*/
static inline int __must_check kref_get_unless_zero(struct kref *kref)
{
return refcount_inc_not_zero(&kref->refcount);
}
#endif /* _KREF_H_ */
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* VLAN An implementation of 802.1Q VLAN tagging.
*
* Authors: Ben Greear <greearb@candelatech.com>
*/
#ifndef _LINUX_IF_VLAN_H_
#define _LINUX_IF_VLAN_H_
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/rtnetlink.h>
#include <linux/bug.h>
#include <uapi/linux/if_vlan.h>
#define VLAN_HLEN 4 /* The additional bytes required by VLAN
* (in addition to the Ethernet header)
*/
#define VLAN_ETH_HLEN 18 /* Total octets in header. */
#define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */
/*
* According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan
*/
#define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */
#define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */
#define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */
/*
* struct vlan_hdr - vlan header
* @h_vlan_TCI: priority and VLAN ID
* @h_vlan_encapsulated_proto: packet type ID or len
*/
struct vlan_hdr {
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
/**
* struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr)
* @h_dest: destination ethernet address
* @h_source: source ethernet address
* @h_vlan_proto: ethernet protocol
* @h_vlan_TCI: priority and VLAN ID
* @h_vlan_encapsulated_proto: packet type ID or len
*/
struct vlan_ethhdr {
struct_group(addrs,
unsigned char h_dest[ETH_ALEN];
unsigned char h_source[ETH_ALEN];
);
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
#include <linux/skbuff.h>
static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
{
return (struct vlan_ethhdr *)skb_mac_header(skb);
}
/* Prefer this version in TX path, instead of
* skb_reset_mac_header() + vlan_eth_hdr()
*/
static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb)
{
return (struct vlan_ethhdr *)skb->data;
}
#define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */
#define VLAN_PRIO_SHIFT 13
#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */
#define VLAN_VID_MASK 0x0fff /* VLAN Identifier */
#define VLAN_N_VID 4096
/* found in socket.c */
extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
static inline bool is_vlan_dev(const struct net_device *dev)
{
return dev->priv_flags & IFF_802_1Q_VLAN;
}
#define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all)
#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci)
#define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK)
#define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK))
#define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
{
ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev));
}
static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev)
{
ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev);
}
static inline int vlan_get_rx_stag_filter_info(struct net_device *dev)
{
ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev));
}
static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev)
{
ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev);
}
/**
* struct vlan_pcpu_stats - VLAN percpu rx/tx stats
* @rx_packets: number of received packets
* @rx_bytes: number of received bytes
* @rx_multicast: number of received multicast packets
* @tx_packets: number of transmitted packets
* @tx_bytes: number of transmitted bytes
* @syncp: synchronization point for 64bit counters
* @rx_errors: number of rx errors
* @tx_dropped: number of tx drops
*/
struct vlan_pcpu_stats {
u64_stats_t rx_packets;
u64_stats_t rx_bytes;
u64_stats_t rx_multicast;
u64_stats_t tx_packets;
u64_stats_t tx_bytes;
struct u64_stats_sync syncp;
u32 rx_errors;
u32 tx_dropped;
};
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
__be16 vlan_proto, u16 vlan_id);
extern int vlan_for_each(struct net_device *dev,
int (*action)(struct net_device *dev, int vid,
void *arg), void *arg);
extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
/**
* struct vlan_priority_tci_mapping - vlan egress priority mappings
* @priority: skb priority
* @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000
* @next: pointer to next struct
*/
struct vlan_priority_tci_mapping {
u32 priority;
u16 vlan_qos;
struct vlan_priority_tci_mapping *next;
};
struct proc_dir_entry;
struct netpoll;
/**
* struct vlan_dev_priv - VLAN private device data
* @nr_ingress_mappings: number of ingress priority mappings
* @ingress_priority_map: ingress priority mappings
* @nr_egress_mappings: number of egress priority mappings
* @egress_priority_map: hash of egress priority mappings
* @vlan_proto: VLAN encapsulation protocol
* @vlan_id: VLAN identifier
* @flags: device flags
* @real_dev: underlying netdevice
* @dev_tracker: refcount tracker for @real_dev reference
* @real_dev_addr: address of underlying netdevice
* @dent: proc dir entry
* @vlan_pcpu_stats: ptr to percpu rx stats
* @netpoll: netpoll instance "propagated" down to @real_dev
*/
struct vlan_dev_priv {
unsigned int nr_ingress_mappings;
u32 ingress_priority_map[8];
unsigned int nr_egress_mappings;
struct vlan_priority_tci_mapping *egress_priority_map[16];
__be16 vlan_proto;
u16 vlan_id;
u16 flags;
struct net_device *real_dev;
netdevice_tracker dev_tracker;
unsigned char real_dev_addr[ETH_ALEN];
struct proc_dir_entry *dent;
struct vlan_pcpu_stats __percpu *vlan_pcpu_stats;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
};
static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
{
return netdev_priv(dev);
}
static inline u16
vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
{
struct vlan_priority_tci_mapping *mp;
smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)];
while (mp) {
if (mp->priority == skprio) {
return mp->vlan_qos; /* This should already be shifted
* to mask correctly with the
* VLAN's TCI */
}
mp = mp->next;
}
return 0;
}
extern bool vlan_do_receive(struct sk_buff **skb);
extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid);
extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid);
extern int vlan_vids_add_by_dev(struct net_device *dev,
const struct net_device *by_dev);
extern void vlan_vids_del_by_dev(struct net_device *dev,
const struct net_device *by_dev);
extern bool vlan_uses_dev(const struct net_device *dev);
#else
static inline struct net_device *
__vlan_find_dev_deep_rcu(struct net_device *real_dev,
__be16 vlan_proto, u16 vlan_id)
{
return NULL;
}
static inline int
vlan_for_each(struct net_device *dev,
int (*action)(struct net_device *dev, int vid, void *arg),
void *arg)
{
return 0;
}
static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
{
BUG();
return NULL;
}
static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
{
BUG();
return 0;
}
static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
{
BUG();
return 0;
}
static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
u32 skprio)
{
return 0;
}
static inline bool vlan_do_receive(struct sk_buff **skb)
{
return false;
}
static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid)
{
return 0;
}
static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid)
{
}
static inline int vlan_vids_add_by_dev(struct net_device *dev,
const struct net_device *by_dev)
{
return 0;
}
static inline void vlan_vids_del_by_dev(struct net_device *dev,
const struct net_device *by_dev)
{
}
static inline bool vlan_uses_dev(const struct net_device *dev)
{
return false;
}
#endif
/**
* eth_type_vlan - check for valid vlan ether type.
* @ethertype: ether type to check
*
* Returns: true if the ether type is a vlan ether type.
*/
static inline bool eth_type_vlan(__be16 ethertype)
{
switch (ethertype) {
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
return true;
default:
return false;
}
}
static inline bool vlan_hw_offload_capable(netdev_features_t features,
__be16 proto)
{
if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX)
return true;
if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX)
return true;
return false;
}
/**
* __vlan_insert_inner_tag - inner VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
* @mac_len: MAC header length including outer vlan headers
*
* Inserts the VLAN tag into @skb as part of the payload at offset mac_len
* Does not change skb->protocol so this function can be used during receive.
*
* Returns: error if skb_cow_head fails.
*/
static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci,
unsigned int mac_len)
{
struct vlan_ethhdr *veth;
if (skb_cow_head(skb, VLAN_HLEN) < 0)
return -ENOMEM;
skb_push(skb, VLAN_HLEN);
/* Move the mac header sans proto to the beginning of the new header. */
if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN;
veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN);
/* first, the ethernet type */
if (likely(mac_len >= ETH_TLEN)) {
/* h_vlan_encapsulated_proto should already be populated, and
* skb->data has space for h_vlan_proto
*/
veth->h_vlan_proto = vlan_proto;
} else {
/* h_vlan_encapsulated_proto should not be populated, and
* skb->data has no space for h_vlan_proto
*/
veth->h_vlan_encapsulated_proto = skb->protocol;
}
/* now, the TCI */
veth->h_vlan_TCI = htons(vlan_tci);
return 0;
}
/**
* __vlan_insert_tag - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Does not change skb->protocol so this function can be used during receive.
*
* Returns: error if skb_cow_head fails.
*/
static inline int __vlan_insert_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
}
/**
* vlan_insert_inner_tag - inner VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
* @mac_len: MAC header length including outer vlan headers
*
* Inserts the VLAN tag into @skb as part of the payload at offset mac_len
* Returns a VLAN tagged skb. This might change skb->head.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*
* Does not change skb->protocol so this function can be used during receive.
*
* Return: modified @skb on success, NULL on error (@skb is freed).
*/
static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
__be16 vlan_proto,
u16 vlan_tci,
unsigned int mac_len)
{
int err;
err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len);
if (err) {
dev_kfree_skb_any(skb);
return NULL;
}
return skb;
}
/**
* vlan_insert_tag - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Returns a VLAN tagged skb. This might change skb->head.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*
* Does not change skb->protocol so this function can be used during receive.
*
* Return: modified @skb on success, NULL on error (@skb is freed).
*/
static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
}
/**
* vlan_insert_tag_set_proto - regular VLAN tag inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Inserts the VLAN tag into @skb as part of the payload
* Returns a VLAN tagged skb. This might change skb->head.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*
* Return: modified @skb on success, NULL on error (@skb is freed).
*/
static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
__be16 vlan_proto,
u16 vlan_tci)
{
skb = vlan_insert_tag(skb, vlan_proto, vlan_tci);
if (skb)
skb->protocol = vlan_proto;
return skb;
}
/**
* __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info
* @skb: skbuff to clear
*
* Clears the VLAN information from @skb
*/
static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
{
skb->vlan_all = 0;
}
/**
* __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb
* @dst: skbuff to copy to
* @src: skbuff to copy from
*
* Copies VLAN information from @src to @dst (for branchless code)
*/
static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src)
{
dst->vlan_all = src->vlan_all;
}
/*
* __vlan_hwaccel_push_inside - pushes vlan tag to the payload
* @skb: skbuff to tag
*
* Pushes the VLAN tag from @skb->vlan_tci inside to the payload.
*
* Following the skb_unshare() example, in case of error, the calling function
* doesn't have to worry about freeing the original skb.
*/
static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
{
skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
skb_vlan_tag_get(skb));
if (likely(skb))
__vlan_hwaccel_clear_tag(skb);
return skb;
}
/**
* __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
* @skb: skbuff to tag
* @vlan_proto: VLAN encapsulation protocol
* @vlan_tci: VLAN TCI to insert
*
* Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest
*/
static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
__be16 vlan_proto, u16 vlan_tci)
{
skb->vlan_proto = vlan_proto;
skb->vlan_tci = vlan_tci;
}
/**
* __vlan_get_tag - get the VLAN ID that is part of the payload
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns: error if the skb is not of VLAN type
*/
static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
{
struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb);
if (!eth_type_vlan(veth->h_vlan_proto))
return -ENODATA;
*vlan_tci = ntohs(veth->h_vlan_TCI);
return 0;
}
/**
* __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[]
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns: error if @skb->vlan_tci is not set correctly
*/
static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
u16 *vlan_tci)
{
if (skb_vlan_tag_present(skb)) {
*vlan_tci = skb_vlan_tag_get(skb);
return 0;
} else {
*vlan_tci = 0;
return -ENODATA;
}
}
/**
* vlan_get_tag - get the VLAN ID from the skb
* @skb: skbuff to query
* @vlan_tci: buffer to store value
*
* Returns: error if the skb is not VLAN tagged
*/
static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
{
if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
return __vlan_hwaccel_get_tag(skb, vlan_tci);
} else {
return __vlan_get_tag(skb, vlan_tci);
}
}
/**
* __vlan_get_protocol_offset() - get protocol EtherType.
* @skb: skbuff to query
* @type: first vlan protocol
* @mac_offset: MAC offset
* @depth: buffer to store length of eth and vlan tags in bytes
*
* Returns: the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb,
__be16 type,
int mac_offset,
int *depth)
{
unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
/* if type is 802.1Q/AD then the header should already be
* present at mac_len - VLAN_HLEN (if mac_len > 0), or at
* ETH_HLEN otherwise
*/
if (eth_type_vlan(type)) {
if (vlan_depth) {
if (WARN_ON(vlan_depth < VLAN_HLEN))
return 0;
vlan_depth -= VLAN_HLEN;
} else {
vlan_depth = ETH_HLEN;
}
do {
struct vlan_hdr vhdr, *vh;
vh = skb_header_pointer(skb, mac_offset + vlan_depth,
sizeof(vhdr), &vhdr);
if (unlikely(!vh || !--parse_depth))
return 0;
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
} while (eth_type_vlan(type));
}
if (depth)
*depth = vlan_depth;
return type;
}
static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
int *depth)
{
return __vlan_get_protocol_offset(skb, type, 0, depth);
}
/**
* vlan_get_protocol - get protocol EtherType.
* @skb: skbuff to query
*
* Returns: the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
{
return __vlan_get_protocol(skb, skb->protocol, NULL);
}
/* This version of __vlan_get_protocol() also pulls mac header in skb->head */
static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb,
__be16 type, int *depth)
{
int maclen;
type = __vlan_get_protocol(skb, type, &maclen);
if (type) {
if (!pskb_may_pull(skb, maclen))
type = 0;
else if (depth)
*depth = maclen;
}
return type;
}
/* A getter for the SKB protocol field which will handle VLAN tags consistently
* whether VLAN acceleration is enabled or not.
*/
static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
{
if (!skip_vlan)
/* VLAN acceleration strips the VLAN header from the skb and
* moves it to skb->vlan_proto
*/
return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
return vlan_get_protocol(skb);
}
static inline void vlan_set_encap_proto(struct sk_buff *skb,
struct vlan_hdr *vhdr)
{
__be16 proto;
unsigned short *rawp;
/*
* Was a VLAN packet, grab the encapsulated protocol, which the layer
* three protocols care about.
*/
proto = vhdr->h_vlan_encapsulated_proto;
if (eth_proto_is_802_3(proto)) {
skb->protocol = proto;
return;
}
rawp = (unsigned short *)(vhdr + 1);
if (*rawp == 0xFFFF)
/*
* This is a magic hack to spot IPX packets. Older Novell
* breaks the protocol design and runs IPX over 802.3 without
* an 802.2 LLC layer. We look for FFFF which isn't a used
* 802.2 SSAP/DSAP. This won't work for fault tolerant netware
* but does for the rest.
*/
skb->protocol = htons(ETH_P_802_3);
else
/*
* Real 802.2 LLC
*/
skb->protocol = htons(ETH_P_802_2);
}
/**
* vlan_remove_tag - remove outer VLAN tag from payload
* @skb: skbuff to remove tag from
* @vlan_tci: buffer to store value
*
* Expects the skb to contain a VLAN tag in the payload, and to have skb->data
* pointing at the MAC header.
*
* Returns: a new pointer to skb->data, or NULL on failure to pull.
*/
static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci)
{
struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
*vlan_tci = ntohs(vhdr->h_vlan_TCI);
memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
vlan_set_encap_proto(skb, vhdr);
return __skb_pull(skb, VLAN_HLEN);
}
/**
* skb_vlan_tagged - check if skb is vlan tagged.
* @skb: skbuff to query
*
* Returns: true if the skb is tagged, regardless of whether it is hardware
* accelerated or not.
*/
static inline bool skb_vlan_tagged(const struct sk_buff *skb)
{
if (!skb_vlan_tag_present(skb) &&
likely(!eth_type_vlan(skb->protocol)))
return false;
return true;
}
/**
* skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers.
* @skb: skbuff to query
*
* Returns: true if the skb is tagged with multiple vlan headers, regardless
* of whether it is hardware accelerated or not.
*/
static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
if (!skb_vlan_tag_present(skb)) {
struct vlan_ethhdr *veh;
if (likely(!eth_type_vlan(protocol)))
return false;
if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
return false;
veh = skb_vlan_eth_hdr(skb);
protocol = veh->h_vlan_encapsulated_proto;
}
if (!eth_type_vlan(protocol))
return false;
return true;
}
/**
* vlan_features_check - drop unsafe features for skb with multiple tags.
* @skb: skbuff to query
* @features: features to be checked
*
* Returns: features without unsafe ones if the skb has multiple tags.
*/
static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tagged_multi(skb)) {
/* In the case of multi-tagged packets, use a direct mask
* instead of using netdev_interesect_features(), to make
* sure that only devices supporting NETIF_F_HW_CSUM will
* have checksum offloading support.
*/
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
}
return features;
}
/**
* compare_vlan_header - Compare two vlan headers
* @h1: Pointer to vlan header
* @h2: Pointer to vlan header
*
* Compare two vlan headers.
*
* Please note that alignment of h1 & h2 are only guaranteed to be 16 bits.
*
* Return: 0 if equal, arbitrary non-zero value if not equal.
*/
static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1,
const struct vlan_hdr *h2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return *(u32 *)h1 ^ *(u32 *)h2;
#else
return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) |
((__force u32)h1->h_vlan_encapsulated_proto ^
(__force u32)h2->h_vlan_encapsulated_proto);
#endif
}
#endif /* !(_LINUX_IF_VLAN_H_) */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BLK_CGROUP_PRIVATE_H
#define _BLK_CGROUP_PRIVATE_H
/*
* block cgroup private header
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*/
#include <linux/blk-cgroup.h>
#include <linux/cgroup.h>
#include <linux/kthread.h>
#include <linux/blk-mq.h>
#include <linux/llist.h>
#include "blk.h"
struct blkcg_gq;
struct blkg_policy_data;
/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */
#define BLKG_STAT_CPU_BATCH (INT_MAX / 2)
#ifdef CONFIG_BLK_CGROUP
enum blkg_iostat_type {
BLKG_IOSTAT_READ,
BLKG_IOSTAT_WRITE,
BLKG_IOSTAT_DISCARD,
BLKG_IOSTAT_NR,
};
struct blkg_iostat {
u64 bytes[BLKG_IOSTAT_NR];
u64 ios[BLKG_IOSTAT_NR];
};
struct blkg_iostat_set {
struct u64_stats_sync sync;
struct blkcg_gq *blkg;
struct llist_node lnode;
int lqueued; /* queued in llist */
struct blkg_iostat cur;
struct blkg_iostat last;
};
/* association between a blk cgroup and a request queue */
struct blkcg_gq {
/* Pointer to the associated request_queue */
struct request_queue *q;
struct list_head q_node;
struct hlist_node blkcg_node;
struct blkcg *blkcg;
/* all non-root blkcg_gq's are guaranteed to have access to parent */
struct blkcg_gq *parent;
/* reference count */
struct percpu_ref refcnt;
/* is this blkg online? protected by both blkcg and q locks */
bool online;
struct blkg_iostat_set __percpu *iostat_cpu;
struct blkg_iostat_set iostat;
struct blkg_policy_data *pd[BLKCG_MAX_POLS];
#ifdef CONFIG_BLK_CGROUP_PUNT_BIO
spinlock_t async_bio_lock;
struct bio_list async_bios;
#endif
union {
struct work_struct async_bio_work;
struct work_struct free_work;
};
atomic_t use_delay;
atomic64_t delay_nsec;
atomic64_t delay_start;
u64 last_delay;
int last_use;
struct rcu_head rcu_head;
};
struct blkcg {
struct cgroup_subsys_state css;
spinlock_t lock;
refcount_t online_pin;
/* If there is block congestion on this cgroup. */
atomic_t congestion_count;
struct radix_tree_root blkg_tree;
struct blkcg_gq __rcu *blkg_hint;
struct hlist_head blkg_list;
struct blkcg_policy_data *cpd[BLKCG_MAX_POLS];
struct list_head all_blkcgs_node;
/*
* List of updated percpu blkg_iostat_set's since the last flush.
*/
struct llist_head __percpu *lhead;
#ifdef CONFIG_BLK_CGROUP_FC_APPID
char fc_app_id[FC_APPID_LEN];
#endif
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
#endif
};
static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct blkcg, css) : NULL;
}
/*
* A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
* request_queue (q). This is used by blkcg policies which need to track
* information per blkcg - q pair.
*
* There can be multiple active blkcg policies and each blkg:policy pair is
* represented by a blkg_policy_data which is allocated and freed by each
* policy's pd_alloc/free_fn() methods. A policy can allocate private data
* area by allocating larger data structure which embeds blkg_policy_data
* at the beginning.
*/
struct blkg_policy_data {
/* the blkg and policy id this per-policy data belongs to */
struct blkcg_gq *blkg;
int plid;
bool online;
};
/*
* Policies that need to keep per-blkcg data which is independent from any
* request_queue associated to it should implement cpd_alloc/free_fn()
* methods. A policy can allocate private data area by allocating larger
* data structure which embeds blkcg_policy_data at the beginning.
* cpd_init() is invoked to let each policy handle per-blkcg data.
*/
struct blkcg_policy_data {
/* the blkcg and policy id this per-policy data belongs to */
struct blkcg *blkcg;
int plid;
};
typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);
typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(struct gendisk *disk,
struct blkcg *blkcg, gfp_t gfp);
typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd,
struct seq_file *s);
struct blkcg_policy {
int plid;
/* cgroup files for the policy */
struct cftype *dfl_cftypes;
struct cftype *legacy_cftypes;
/* operations */
blkcg_pol_alloc_cpd_fn *cpd_alloc_fn;
blkcg_pol_free_cpd_fn *cpd_free_fn;
blkcg_pol_alloc_pd_fn *pd_alloc_fn;
blkcg_pol_init_pd_fn *pd_init_fn;
blkcg_pol_online_pd_fn *pd_online_fn;
blkcg_pol_offline_pd_fn *pd_offline_fn;
blkcg_pol_free_pd_fn *pd_free_fn;
blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn;
blkcg_pol_stat_pd_fn *pd_stat_fn;
};
extern struct blkcg blkcg_root;
extern bool blkcg_debug_stats;
void blkg_init_queue(struct request_queue *q);
int blkcg_init_disk(struct gendisk *disk);
void blkcg_exit_disk(struct gendisk *disk);
/* Blkio controller policy registration */
int blkcg_policy_register(struct blkcg_policy *pol);
void blkcg_policy_unregister(struct blkcg_policy *pol);
int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol);
void blkcg_deactivate_policy(struct gendisk *disk,
const struct blkcg_policy *pol);
const char *blkg_dev_name(struct blkcg_gq *blkg);
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
u64 (*prfill)(struct seq_file *,
struct blkg_policy_data *, int),
const struct blkcg_policy *pol, int data,
bool show_total);
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
struct blkg_conf_ctx {
char *input;
char *body;
struct block_device *bdev;
struct blkcg_gq *blkg;
};
void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input);
int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx);
unsigned long blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx);
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
struct blkg_conf_ctx *ctx);
void blkg_conf_exit(struct blkg_conf_ctx *ctx);
void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags);
/**
* bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
* @bio: the target &bio
*
* Return: true if this bio needs to be submitted with the root blkg context.
*
* In order to avoid priority inversions we sometimes need to issue a bio as if
* it were attached to the root blkg, and then backcharge to the actual owning
* blkg. The idea is we do bio_blkcg_css() to look up the actual context for
* the bio and attach the appropriate blkg to the bio. Then we call this helper
* and if it is true run with the root blkg for that queue and then do any
* backcharging to the originating cgroup once the io is complete.
*/
static inline bool bio_issue_as_root_blkg(struct bio *bio)
{
return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
}
/**
* blkg_lookup - lookup blkg for the specified blkcg - q pair
* @blkcg: blkcg of interest
* @q: request_queue of interest
*
* Lookup blkg for the @blkcg - @q pair.
*
* Must be called in a RCU critical section.
*/
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
struct request_queue *q)
{
struct blkcg_gq *blkg;
if (blkcg == &blkcg_root)
return q->root_blkg;
blkg = rcu_dereference_check(blkcg->blkg_hint,
lockdep_is_held(&q->queue_lock));
if (blkg && blkg->q == q)
return blkg;
blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
if (blkg && blkg->q != q)
blkg = NULL;
return blkg;
}
/**
* blkg_to_pd - get policy private data
* @blkg: blkg of interest
* @pol: policy of interest
*
* Return pointer to private data associated with the @blkg-@pol pair.
*/
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
struct blkcg_policy *pol)
{
return blkg ? blkg->pd[pol->plid] : NULL;
}
static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
struct blkcg_policy *pol)
{
return blkcg ? blkcg->cpd[pol->plid] : NULL;
}
/**
* pd_to_blkg - get blkg associated with policy private data
* @pd: policy private data of interest
*
* @pd is policy private data. Determine the blkg it's associated with.
*/
static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
{
return pd ? pd->blkg : NULL;
}
static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
{
return cpd ? cpd->blkcg : NULL;
}
/**
* blkg_get - get a blkg reference
* @blkg: blkg to get
*
* The caller should be holding an existing reference.
*/
static inline void blkg_get(struct blkcg_gq *blkg)
{
percpu_ref_get(&blkg->refcnt);
}
/**
* blkg_tryget - try and get a blkg reference
* @blkg: blkg to get
*
* This is for use when doing an RCU lookup of the blkg. We may be in the midst
* of freeing this blkg, so we can only use it if the refcnt is not zero.
*/
static inline bool blkg_tryget(struct blkcg_gq *blkg)
{
return blkg && percpu_ref_tryget(&blkg->refcnt);
}
/**
* blkg_put - put a blkg reference
* @blkg: blkg to put
*/
static inline void blkg_put(struct blkcg_gq *blkg)
{
percpu_ref_put(&blkg->refcnt);
}
/**
* blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
* @d_blkg: loop cursor pointing to the current descendant
* @pos_css: used for iteration
* @p_blkg: target blkg to walk descendants of
*
* Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU
* read locked. If called under either blkcg or queue lock, the iteration
* is guaranteed to include all and only online blkgs. The caller may
* update @pos_css by calling css_rightmost_descendant() to skip subtree.
* @p_blkg is included in the iteration and the first node to be visited.
*/
#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \
css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \
if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \
(p_blkg)->q)))
/**
* blkg_for_each_descendant_post - post-order walk of a blkg's descendants
* @d_blkg: loop cursor pointing to the current descendant
* @pos_css: used for iteration
* @p_blkg: target blkg to walk descendants of
*
* Similar to blkg_for_each_descendant_pre() but performs post-order
* traversal instead. Synchronization rules are the same. @p_blkg is
* included in the iteration and the last node to be visited.
*/
#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \
css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \
if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \
(p_blkg)->q)))
static inline void blkcg_bio_issue_init(struct bio *bio)
{
bio_issue_init(&bio->bi_issue, bio_sectors(bio));
}
static inline void blkcg_use_delay(struct blkcg_gq *blkg)
{
if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
return;
if (atomic_add_return(1, &blkg->use_delay) == 1)
atomic_inc(&blkg->blkcg->congestion_count);
}
static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
{
int old = atomic_read(&blkg->use_delay);
if (WARN_ON_ONCE(old < 0))
return 0;
if (old == 0)
return 0;
/*
* We do this song and dance because we can race with somebody else
* adding or removing delay. If we just did an atomic_dec we'd end up
* negative and we'd already be in trouble. We need to subtract 1 and
* then check to see if we were the last delay so we can drop the
* congestion count on the cgroup.
*/
while (old && !atomic_try_cmpxchg(&blkg->use_delay, &old, old - 1))
;
if (old == 0)
return 0;
if (old == 1)
atomic_dec(&blkg->blkcg->congestion_count);
return 1;
}
/**
* blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount
* @blkg: target blkg
* @delay: delay duration in nsecs
*
* When enabled with this function, the delay is not decayed and must be
* explicitly cleared with blkcg_clear_delay(). Must not be mixed with
* blkcg_[un]use_delay() and blkcg_add_delay() usages.
*/
static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
{
int old = atomic_read(&blkg->use_delay);
/* We only want 1 person setting the congestion count for this blkg. */
if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1))
atomic_inc(&blkg->blkcg->congestion_count);
atomic64_set(&blkg->delay_nsec, delay);
}
/**
* blkcg_clear_delay - Disable allocator delay mechanism
* @blkg: target blkg
*
* Disable use_delay mechanism. See blkcg_set_delay().
*/
static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
{
int old = atomic_read(&blkg->use_delay);
/* We only want 1 person clearing the congestion count for this blkg. */
if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0))
atomic_dec(&blkg->blkcg->congestion_count);
}
/**
* blk_cgroup_mergeable - Determine whether to allow or disallow merges
* @rq: request to merge into
* @bio: bio to merge
*
* @bio and @rq should belong to the same cgroup and their issue_as_root should
* match. The latter is necessary as we don't want to throttle e.g. a metadata
* update because it happens to be next to a regular IO.
*/
static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio)
{
return rq->bio->bi_blkg == bio->bi_blkg &&
bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio);
}
void blk_cgroup_bio_start(struct bio *bio);
void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
#else /* CONFIG_BLK_CGROUP */
struct blkg_policy_data {
};
struct blkcg_policy_data {
};
struct blkcg_policy {
};
struct blkcg {
};
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
static inline void blkg_init_queue(struct request_queue *q) { }
static inline int blkcg_init_disk(struct gendisk *disk) { return 0; }
static inline void blkcg_exit_disk(struct gendisk *disk) { }
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
static inline int blkcg_activate_policy(struct gendisk *disk,
const struct blkcg_policy *pol) { return 0; }
static inline void blkcg_deactivate_policy(struct gendisk *disk,
const struct blkcg_policy *pol) { }
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
struct blkcg_policy *pol) { return NULL; }
static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
static inline void blkg_get(struct blkcg_gq *blkg) { }
static inline void blkg_put(struct blkcg_gq *blkg) { }
static inline void blkcg_bio_issue_init(struct bio *bio) { }
static inline void blk_cgroup_bio_start(struct bio *bio) { }
static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; }
#define blk_queue_for_each_rl(rl, q) \
for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
#endif /* CONFIG_BLK_CGROUP */
#endif /* _BLK_CGROUP_PRIVATE_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Fast batching percpu counters.
*/
#include <linux/percpu_counter.h>
#include <linux/mutex.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/debugobjects.h>
#ifdef CONFIG_HOTPLUG_CPU
static LIST_HEAD(percpu_counters);
static DEFINE_SPINLOCK(percpu_counters_lock);
#endif
#ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER
static const struct debug_obj_descr percpu_counter_debug_descr;
static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state)
{
struct percpu_counter *fbc = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
percpu_counter_destroy(fbc);
debug_object_free(fbc, &percpu_counter_debug_descr);
return true;
default:
return false;
}
}
static const struct debug_obj_descr percpu_counter_debug_descr = {
.name = "percpu_counter",
.fixup_free = percpu_counter_fixup_free,
};
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{
debug_object_init(fbc, &percpu_counter_debug_descr);
debug_object_activate(fbc, &percpu_counter_debug_descr);
}
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{
debug_object_deactivate(fbc, &percpu_counter_debug_descr);
debug_object_free(fbc, &percpu_counter_debug_descr);
}
#else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{ }
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{ }
#endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
{
int cpu;
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
for_each_possible_cpu(cpu) {
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
*pcount = 0;
}
fbc->count = amount;
raw_spin_unlock_irqrestore(&fbc->lock, flags);
}
EXPORT_SYMBOL(percpu_counter_set);
/*
* Add to a counter while respecting batch size.
*
* There are 2 implementations, both dealing with the following problem:
*
* The decision slow path/fast path and the actual update must be atomic.
* Otherwise a call in process context could check the current values and
* decide that the fast path can be used. If now an interrupt occurs before
* the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters),
* then the this_cpu_add() that is executed after the interrupt has completed
* can produce values larger than "batch" or even overflows.
*/
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
/*
* Safety against interrupts is achieved in 2 ways:
* 1. the fast path uses local cmpxchg (note: no lock prefix)
* 2. the slow path operates with interrupts disabled
*/
void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
{
s64 count;
unsigned long flags;
count = this_cpu_read(*fbc->counters);
do {
if (unlikely(abs(count + amount) >= batch)) {
raw_spin_lock_irqsave(&fbc->lock, flags);
/*
* Note: by now we might have migrated to another CPU
* or the value might have changed.
*/
count = __this_cpu_read(*fbc->counters);
fbc->count += count + amount;
__this_cpu_sub(*fbc->counters, count);
raw_spin_unlock_irqrestore(&fbc->lock, flags);
return;
}
} while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount));
}
#else
/*
* local_irq_save() is used to make the function irq safe:
* - The slow path would be ok as protected by an irq-safe spinlock.
* - this_cpu_add would be ok as it is irq-safe by definition.
*/
void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
{
s64 count;
unsigned long flags;
local_irq_save(flags);
count = __this_cpu_read(*fbc->counters) + amount;
if (abs(count) >= batch) {
raw_spin_lock(&fbc->lock);
fbc->count += count;
__this_cpu_sub(*fbc->counters, count - amount);
raw_spin_unlock(&fbc->lock);
} else {
this_cpu_add(*fbc->counters, amount);
}
local_irq_restore(flags);
}
#endif
EXPORT_SYMBOL(percpu_counter_add_batch);
/*
* For percpu_counter with a big batch, the devication of its count could
* be big, and there is requirement to reduce the deviation, like when the
* counter's batch could be runtime decreased to get a better accuracy,
* which can be achieved by running this sync function on each CPU.
*/
void percpu_counter_sync(struct percpu_counter *fbc)
{
unsigned long flags;
s64 count;
raw_spin_lock_irqsave(&fbc->lock, flags);
count = __this_cpu_read(*fbc->counters);
fbc->count += count;
__this_cpu_sub(*fbc->counters, count);
raw_spin_unlock_irqrestore(&fbc->lock, flags);
}
EXPORT_SYMBOL(percpu_counter_sync);
/*
* Add up all the per-cpu counts, return the result. This is a more accurate
* but much slower version of percpu_counter_read_positive().
*
* We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums
* from CPUs that are in the process of being taken offline. Dying cpus have
* been removed from the online mask, but may not have had the hotplug dead
* notifier called to fold the percpu count back into the global counter sum.
* By including dying CPUs in the iteration mask, we avoid this race condition
* so __percpu_counter_sum() just does the right thing when CPUs are being taken
* offline.
*/
s64 __percpu_counter_sum(struct percpu_counter *fbc)
{
s64 ret;
int cpu;
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
ret = fbc->count;
for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) {
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
ret += *pcount;
}
raw_spin_unlock_irqrestore(&fbc->lock, flags);
return ret;
}
EXPORT_SYMBOL(__percpu_counter_sum);
int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount,
gfp_t gfp, u32 nr_counters,
struct lock_class_key *key)
{
unsigned long flags __maybe_unused;
size_t counter_size;
s32 __percpu *counters;
u32 i;
counter_size = ALIGN(sizeof(*counters), __alignof__(*counters));
counters = __alloc_percpu_gfp(nr_counters * counter_size,
__alignof__(*counters), gfp);
if (!counters) {
fbc[0].counters = NULL;
return -ENOMEM;
}
for (i = 0; i < nr_counters; i++) {
raw_spin_lock_init(&fbc[i].lock);
lockdep_set_class(&fbc[i].lock, key);
#ifdef CONFIG_HOTPLUG_CPU
INIT_LIST_HEAD(&fbc[i].list);
#endif
fbc[i].count = amount;
fbc[i].counters = (void __percpu *)counters + i * counter_size;
debug_percpu_counter_activate(&fbc[i]);
}
#ifdef CONFIG_HOTPLUG_CPU
spin_lock_irqsave(&percpu_counters_lock, flags);
for (i = 0; i < nr_counters; i++)
list_add(&fbc[i].list, &percpu_counters);
spin_unlock_irqrestore(&percpu_counters_lock, flags);
#endif
return 0;
}
EXPORT_SYMBOL(__percpu_counter_init_many);
void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters)
{
unsigned long flags __maybe_unused;
u32 i;
if (WARN_ON_ONCE(!fbc))
return;
if (!fbc[0].counters)
return;
for (i = 0; i < nr_counters; i++)
debug_percpu_counter_deactivate(&fbc[i]);
#ifdef CONFIG_HOTPLUG_CPU
spin_lock_irqsave(&percpu_counters_lock, flags);
for (i = 0; i < nr_counters; i++)
list_del(&fbc[i].list);
spin_unlock_irqrestore(&percpu_counters_lock, flags);
#endif
free_percpu(fbc[0].counters);
for (i = 0; i < nr_counters; i++)
fbc[i].counters = NULL;
}
EXPORT_SYMBOL(percpu_counter_destroy_many);
int percpu_counter_batch __read_mostly = 32;
EXPORT_SYMBOL(percpu_counter_batch);
static int compute_batch_value(unsigned int cpu)
{
int nr = num_online_cpus();
percpu_counter_batch = max(32, nr*2);
return 0;
}
static int percpu_counter_cpu_dead(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
struct percpu_counter *fbc;
compute_batch_value(cpu);
spin_lock_irq(&percpu_counters_lock);
list_for_each_entry(fbc, &percpu_counters, list) {
s32 *pcount;
raw_spin_lock(&fbc->lock);
pcount = per_cpu_ptr(fbc->counters, cpu);
fbc->count += *pcount;
*pcount = 0;
raw_spin_unlock(&fbc->lock);
}
spin_unlock_irq(&percpu_counters_lock);
#endif
return 0;
}
/*
* Compare counter against given value.
* Return 1 if greater, 0 if equal and -1 if less
*/
int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
{
s64 count;
count = percpu_counter_read(fbc);
/* Check to see if rough count will be sufficient for comparison */
if (abs(count - rhs) > (batch * num_online_cpus())) {
if (count > rhs)
return 1;
else
return -1;
}
/* Need to use precise count */
count = percpu_counter_sum(fbc);
if (count > rhs)
return 1;
else if (count < rhs)
return -1;
else
return 0;
}
EXPORT_SYMBOL(__percpu_counter_compare);
/*
* Compare counter, and add amount if total is: less than or equal to limit if
* amount is positive, or greater than or equal to limit if amount is negative.
* Return true if amount is added, or false if total would be beyond the limit.
*
* Negative limit is allowed, but unusual.
* When negative amounts (subs) are given to percpu_counter_limited_add(),
* the limit would most naturally be 0 - but other limits are also allowed.
*
* Overflow beyond S64_MAX is not allowed for: counter, limit and amount
* are all assumed to be sane (far from S64_MIN and S64_MAX).
*/
bool __percpu_counter_limited_add(struct percpu_counter *fbc,
s64 limit, s64 amount, s32 batch)
{
s64 count;
s64 unknown;
unsigned long flags;
bool good = false;
if (amount == 0)
return true;
local_irq_save(flags);
unknown = batch * num_online_cpus();
count = __this_cpu_read(*fbc->counters);
/* Skip taking the lock when safe */
if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) ||
(amount < 0 && fbc->count - unknown >= limit))) {
this_cpu_add(*fbc->counters, amount); local_irq_restore(flags);
return true;
}
raw_spin_lock(&fbc->lock);
count = fbc->count + amount;
/* Skip percpu_counter_sum() when safe */
if (amount > 0) {
if (count - unknown > limit)
goto out;
if (count + unknown <= limit)
good = true;
} else {
if (count + unknown < limit)
goto out;
if (count - unknown >= limit)
good = true;
}
if (!good) {
s32 *pcount;
int cpu;
for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) {
pcount = per_cpu_ptr(fbc->counters, cpu);
count += *pcount;
}
if (amount > 0) {
if (count > limit)
goto out;
} else {
if (count < limit)
goto out;
}
good = true;
}
count = __this_cpu_read(*fbc->counters);
fbc->count += count + amount;
__this_cpu_sub(*fbc->counters, count);
out:
raw_spin_unlock(&fbc->lock);
local_irq_restore(flags);
return good;
}
static int __init percpu_counter_startup(void)
{
int ret;
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online",
compute_batch_value, NULL);
WARN_ON(ret < 0);
ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD,
"lib/percpu_cnt:dead", NULL,
percpu_counter_cpu_dead);
WARN_ON(ret < 0);
return 0;
}
module_init(percpu_counter_startup);
// SPDX-License-Identifier: GPL-2.0
/*
* Implementation of the multi-level security (MLS) policy.
*
* Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
*/
/*
* Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
* Support for enhanced MLS infrastructure.
* Copyright (C) 2004-2006 Trusted Computer Solutions, Inc.
*
* Updated: Hewlett-Packard <paul@paul-moore.com>
* Added support to import/export the MLS label from NetLabel
* Copyright (C) Hewlett-Packard Development Company, L.P., 2006
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <net/netlabel.h>
#include "sidtab.h"
#include "mls.h"
#include "policydb.h"
#include "services.h"
/*
* Return the length in bytes for the MLS fields of the
* security context string representation of `context'.
*/
int mls_compute_context_len(struct policydb *p, struct context *context)
{
int i, l, len, head, prev;
char *nm;
struct ebitmap *e;
struct ebitmap_node *node;
if (!p->mls_enabled)
return 0;
len = 1; /* for the beginning ":" */
for (l = 0; l < 2; l++) {
u32 index_sens = context->range.level[l].sens;
len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1));
/* categories */
head = -2;
prev = -2;
e = &context->range.level[l].cat;
ebitmap_for_each_positive_bit(e, node, i)
{
if (i - prev > 1) {
/* one or more negative bits are skipped */
if (head != prev) { nm = sym_name(p, SYM_CATS, prev);
len += strlen(nm) + 1;
}
nm = sym_name(p, SYM_CATS, i);
len += strlen(nm) + 1;
head = i;
}
prev = i;
}
if (prev != head) { nm = sym_name(p, SYM_CATS, prev);
len += strlen(nm) + 1;
}
if (l == 0) { if (mls_level_eq(&context->range.level[0],
&context->range.level[1]))
break;
else
len++;
}
}
return len;
}
/*
* Write the security context string representation of
* the MLS fields of `context' into the string `*scontext'.
* Update `*scontext' to point to the end of the MLS fields.
*/
void mls_sid_to_context(struct policydb *p, struct context *context,
char **scontext)
{
char *scontextp, *nm;
int i, l, head, prev;
struct ebitmap *e;
struct ebitmap_node *node;
if (!p->mls_enabled)
return;
scontextp = *scontext;
*scontextp = ':';
scontextp++;
for (l = 0; l < 2; l++) {
strcpy(scontextp, sym_name(p, SYM_LEVELS,
context->range.level[l].sens - 1));
scontextp += strlen(scontextp);
/* categories */
head = -2;
prev = -2;
e = &context->range.level[l].cat;
ebitmap_for_each_positive_bit(e, node, i)
{
if (i - prev > 1) {
/* one or more negative bits are skipped */
if (prev != head) { if (prev - head > 1)
*scontextp++ = '.';
else
*scontextp++ = ',';
nm = sym_name(p, SYM_CATS, prev);
strcpy(scontextp, nm);
scontextp += strlen(nm);
}
if (prev < 0)
*scontextp++ = ':';
else
*scontextp++ = ',';
nm = sym_name(p, SYM_CATS, i);
strcpy(scontextp, nm);
scontextp += strlen(nm);
head = i;
}
prev = i;
}
if (prev != head) { if (prev - head > 1)
*scontextp++ = '.';
else
*scontextp++ = ',';
nm = sym_name(p, SYM_CATS, prev);
strcpy(scontextp, nm);
scontextp += strlen(nm);
}
if (l == 0) { if (mls_level_eq(&context->range.level[0],
&context->range.level[1]))
break;
else
*scontextp++ = '-';
}
}
*scontext = scontextp;
}
int mls_level_isvalid(struct policydb *p, struct mls_level *l)
{
struct level_datum *levdatum;
if (!l->sens || l->sens > p->p_levels.nprim)
return 0;
levdatum = symtab_search(&p->p_levels,
sym_name(p, SYM_LEVELS, l->sens - 1));
if (!levdatum)
return 0;
/*
* Return 1 iff all the bits set in l->cat are also be set in
* levdatum->level->cat and no bit in l->cat is larger than
* p->p_cats.nprim.
*/
return ebitmap_contains(&levdatum->level.cat, &l->cat,
p->p_cats.nprim);
}
int mls_range_isvalid(struct policydb *p, struct mls_range *r)
{
return (mls_level_isvalid(p, &r->level[0]) &&
mls_level_isvalid(p, &r->level[1]) &&
mls_level_dom(&r->level[1], &r->level[0]));
}
/*
* Return 1 if the MLS fields in the security context
* structure `c' are valid. Return 0 otherwise.
*/
int mls_context_isvalid(struct policydb *p, struct context *c)
{
struct user_datum *usrdatum;
if (!p->mls_enabled)
return 1;
if (!mls_range_isvalid(p, &c->range))
return 0;
if (c->role == OBJECT_R_VAL)
return 1;
/*
* User must be authorized for the MLS range.
*/
if (!c->user || c->user > p->p_users.nprim)
return 0;
usrdatum = p->user_val_to_struct[c->user - 1];
if (!mls_range_contains(usrdatum->range, c->range))
return 0; /* user may not be associated with range */
return 1;
}
/*
* Set the MLS fields in the security context structure
* `context' based on the string representation in
* the string `scontext'.
*
* This function modifies the string in place, inserting
* NULL characters to terminate the MLS fields.
*
* If a def_sid is provided and no MLS field is present,
* copy the MLS field of the associated default context.
* Used for upgraded to MLS systems where objects may lack
* MLS fields.
*
* Policy read-lock must be held for sidtab lookup.
*
*/
int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext,
struct context *context, struct sidtab *s, u32 def_sid)
{
char *sensitivity, *cur_cat, *next_cat, *rngptr;
struct level_datum *levdatum;
struct cat_datum *catdatum, *rngdatum;
u32 i;
int l, rc;
char *rangep[2];
if (!pol->mls_enabled) {
/*
* With no MLS, only return -EINVAL if there is a MLS field
* and it did not come from an xattr.
*/
if (oldc && def_sid == SECSID_NULL)
return -EINVAL;
return 0;
}
/*
* No MLS component to the security context, try and map to
* default if provided.
*/
if (!oldc) {
struct context *defcon;
if (def_sid == SECSID_NULL)
return -EINVAL;
defcon = sidtab_search(s, def_sid);
if (!defcon)
return -EINVAL;
return mls_context_cpy(context, defcon);
}
/*
* If we're dealing with a range, figure out where the two parts
* of the range begin.
*/
rangep[0] = scontext;
rangep[1] = strchr(scontext, '-');
if (rangep[1]) {
rangep[1][0] = '\0';
rangep[1]++;
}
/* For each part of the range: */
for (l = 0; l < 2; l++) {
/* Split sensitivity and category set. */
sensitivity = rangep[l];
if (sensitivity == NULL)
break;
next_cat = strchr(sensitivity, ':');
if (next_cat)
*(next_cat++) = '\0';
/* Parse sensitivity. */
levdatum = symtab_search(&pol->p_levels, sensitivity);
if (!levdatum)
return -EINVAL;
context->range.level[l].sens = levdatum->level.sens;
/* Extract category set. */
while (next_cat != NULL) {
cur_cat = next_cat;
next_cat = strchr(next_cat, ',');
if (next_cat != NULL)
*(next_cat++) = '\0';
/* Separate into range if exists */
rngptr = strchr(cur_cat, '.');
if (rngptr != NULL) {
/* Remove '.' */
*rngptr++ = '\0';
}
catdatum = symtab_search(&pol->p_cats, cur_cat);
if (!catdatum)
return -EINVAL;
rc = ebitmap_set_bit(&context->range.level[l].cat,
catdatum->value - 1, 1);
if (rc)
return rc;
/* If range, set all categories in range */
if (rngptr == NULL)
continue;
rngdatum = symtab_search(&pol->p_cats, rngptr);
if (!rngdatum)
return -EINVAL;
if (catdatum->value >= rngdatum->value)
return -EINVAL;
for (i = catdatum->value; i < rngdatum->value; i++) {
rc = ebitmap_set_bit(
&context->range.level[l].cat, i, 1);
if (rc)
return rc;
}
}
}
/* If we didn't see a '-', the range start is also the range end. */
if (rangep[1] == NULL) {
context->range.level[1].sens = context->range.level[0].sens;
rc = ebitmap_cpy(&context->range.level[1].cat,
&context->range.level[0].cat);
if (rc)
return rc;
}
return 0;
}
/*
* Set the MLS fields in the security context structure
* `context' based on the string representation in
* the string `str'. This function will allocate temporary memory with the
* given constraints of gfp_mask.
*/
int mls_from_string(struct policydb *p, char *str, struct context *context,
gfp_t gfp_mask)
{
char *tmpstr;
int rc;
if (!p->mls_enabled)
return -EINVAL;
tmpstr = kstrdup(str, gfp_mask);
if (!tmpstr) {
rc = -ENOMEM;
} else {
rc = mls_context_to_sid(p, ':', tmpstr, context, NULL,
SECSID_NULL);
kfree(tmpstr);
}
return rc;
}
/*
* Copies the MLS range `range' into `context'.
*/
int mls_range_set(struct context *context, struct mls_range *range)
{
int l, rc = 0;
/* Copy the MLS range into the context */
for (l = 0; l < 2; l++) {
context->range.level[l].sens = range->level[l].sens;
rc = ebitmap_cpy(&context->range.level[l].cat,
&range->level[l].cat);
if (rc)
break;
}
return rc;
}
int mls_setup_user_range(struct policydb *p, struct context *fromcon,
struct user_datum *user, struct context *usercon)
{
if (p->mls_enabled) {
struct mls_level *fromcon_sen = &(fromcon->range.level[0]);
struct mls_level *fromcon_clr = &(fromcon->range.level[1]);
struct mls_level *user_low = &(user->range.level[0]);
struct mls_level *user_clr = &(user->range.level[1]);
struct mls_level *user_def = &(user->dfltlevel);
struct mls_level *usercon_sen = &(usercon->range.level[0]);
struct mls_level *usercon_clr = &(usercon->range.level[1]);
/* Honor the user's default level if we can */
if (mls_level_between(user_def, fromcon_sen, fromcon_clr))
*usercon_sen = *user_def;
else if (mls_level_between(fromcon_sen, user_def, user_clr))
*usercon_sen = *fromcon_sen;
else if (mls_level_between(fromcon_clr, user_low, user_def))
*usercon_sen = *user_low;
else
return -EINVAL;
/* Lower the clearance of available contexts
if the clearance of "fromcon" is lower than
that of the user's default clearance (but
only if the "fromcon" clearance dominates
the user's computed sensitivity level) */
if (mls_level_dom(user_clr, fromcon_clr))
*usercon_clr = *fromcon_clr;
else if (mls_level_dom(fromcon_clr, user_clr))
*usercon_clr = *user_clr;
else
return -EINVAL;
}
return 0;
}
/*
* Convert the MLS fields in the security context
* structure `oldc' from the values specified in the
* policy `oldp' to the values specified in the policy `newp',
* storing the resulting context in `newc'.
*/
int mls_convert_context(struct policydb *oldp, struct policydb *newp,
struct context *oldc, struct context *newc)
{
struct level_datum *levdatum;
struct cat_datum *catdatum;
struct ebitmap_node *node;
u32 i;
int l;
if (!oldp->mls_enabled || !newp->mls_enabled)
return 0;
for (l = 0; l < 2; l++) {
char *name = sym_name(oldp, SYM_LEVELS,
oldc->range.level[l].sens - 1);
levdatum = symtab_search(&newp->p_levels, name);
if (!levdatum)
return -EINVAL;
newc->range.level[l].sens = levdatum->level.sens;
ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node,
i)
{
int rc;
catdatum = symtab_search(&newp->p_cats,
sym_name(oldp, SYM_CATS, i));
if (!catdatum)
return -EINVAL;
rc = ebitmap_set_bit(&newc->range.level[l].cat,
catdatum->value - 1, 1);
if (rc)
return rc;
}
}
return 0;
}
int mls_compute_sid(struct policydb *p, struct context *scontext,
struct context *tcontext, u16 tclass, u32 specified,
struct context *newcontext, bool sock)
{
struct range_trans rtr;
struct mls_range *r;
struct class_datum *cladatum;
char default_range = 0;
if (!p->mls_enabled)
return 0;
switch (specified) {
case AVTAB_TRANSITION:
/* Look for a range transition rule. */
rtr.source_type = scontext->type;
rtr.target_type = tcontext->type;
rtr.target_class = tclass;
r = policydb_rangetr_search(p, &rtr);
if (r)
return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) {
cladatum = p->class_val_to_struct[tclass - 1];
if (cladatum)
default_range = cladatum->default_range;
}
switch (default_range) {
case DEFAULT_SOURCE_LOW:
return mls_context_cpy_low(newcontext, scontext);
case DEFAULT_SOURCE_HIGH:
return mls_context_cpy_high(newcontext, scontext);
case DEFAULT_SOURCE_LOW_HIGH:
return mls_context_cpy(newcontext, scontext);
case DEFAULT_TARGET_LOW:
return mls_context_cpy_low(newcontext, tcontext);
case DEFAULT_TARGET_HIGH:
return mls_context_cpy_high(newcontext, tcontext);
case DEFAULT_TARGET_LOW_HIGH:
return mls_context_cpy(newcontext, tcontext);
case DEFAULT_GLBLUB:
return mls_context_glblub(newcontext, scontext,
tcontext);
}
fallthrough;
case AVTAB_CHANGE:
if ((tclass == p->process_class) || sock)
/* Use the process MLS attributes. */
return mls_context_cpy(newcontext, scontext);
else
/* Use the process effective MLS attributes. */
return mls_context_cpy_low(newcontext, scontext);
case AVTAB_MEMBER:
/* Use the process effective MLS attributes. */
return mls_context_cpy_low(newcontext, scontext);
}
return -EINVAL;
}
#ifdef CONFIG_NETLABEL
/**
* mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel
* @p: the policy
* @context: the security context
* @secattr: the NetLabel security attributes
*
* Description:
* Given the security context copy the low MLS sensitivity level into the
* NetLabel MLS sensitivity level field.
*
*/
void mls_export_netlbl_lvl(struct policydb *p, struct context *context,
struct netlbl_lsm_secattr *secattr)
{
if (!p->mls_enabled)
return;
secattr->attr.mls.lvl = context->range.level[0].sens - 1;
secattr->flags |= NETLBL_SECATTR_MLS_LVL;
}
/**
* mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels
* @p: the policy
* @context: the security context
* @secattr: the NetLabel security attributes
*
* Description:
* Given the security context and the NetLabel security attributes, copy the
* NetLabel MLS sensitivity level into the context.
*
*/
void mls_import_netlbl_lvl(struct policydb *p, struct context *context,
struct netlbl_lsm_secattr *secattr)
{
if (!p->mls_enabled)
return;
context->range.level[0].sens = secattr->attr.mls.lvl + 1;
context->range.level[1].sens = context->range.level[0].sens;
}
/**
* mls_export_netlbl_cat - Export the MLS categories to NetLabel
* @p: the policy
* @context: the security context
* @secattr: the NetLabel security attributes
*
* Description:
* Given the security context copy the low MLS categories into the NetLabel
* MLS category field. Returns zero on success, negative values on failure.
*
*/
int mls_export_netlbl_cat(struct policydb *p, struct context *context,
struct netlbl_lsm_secattr *secattr)
{
int rc;
if (!p->mls_enabled)
return 0;
rc = ebitmap_netlbl_export(&context->range.level[0].cat,
&secattr->attr.mls.cat);
if (rc == 0 && secattr->attr.mls.cat != NULL)
secattr->flags |= NETLBL_SECATTR_MLS_CAT;
return rc;
}
/**
* mls_import_netlbl_cat - Import the MLS categories from NetLabel
* @p: the policy
* @context: the security context
* @secattr: the NetLabel security attributes
*
* Description:
* Copy the NetLabel security attributes into the SELinux context; since the
* NetLabel security attribute only contains a single MLS category use it for
* both the low and high categories of the context. Returns zero on success,
* negative values on failure.
*
*/
int mls_import_netlbl_cat(struct policydb *p, struct context *context,
struct netlbl_lsm_secattr *secattr)
{
int rc;
if (!p->mls_enabled)
return 0;
rc = ebitmap_netlbl_import(&context->range.level[0].cat,
secattr->attr.mls.cat);
if (rc)
goto import_netlbl_cat_failure;
memcpy(&context->range.level[1].cat, &context->range.level[0].cat,
sizeof(context->range.level[0].cat));
return 0;
import_netlbl_cat_failure:
ebitmap_destroy(&context->range.level[0].cat);
return rc;
}
#endif /* CONFIG_NETLABEL */
/*
* llc_input.c - Minimal input path for LLC
*
* Copyright (c) 1997 by Procom Technology, Inc.
* 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* This program can be redistributed or modified under the terms of the
* GNU General Public License as published by the Free Software Foundation.
* This program is distributed without any warranty or implied warranty
* of merchantability or fitness for a particular purpose.
*
* See the GNU General Public License for more details.
*/
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/llc.h>
#include <net/llc_pdu.h>
#include <net/llc_sap.h>
#if 0
#define dprintk(args...) printk(KERN_DEBUG args)
#else
#define dprintk(args...)
#endif
/*
* Packet handler for the station, registerable because in the minimal
* LLC core that is taking shape only the very minimal subset of LLC that
* is needed for things like IPX, Appletalk, etc will stay, with all the
* rest in the llc1 and llc2 modules.
*/
static void (*llc_station_handler)(struct sk_buff *skb);
/*
* Packet handlers for LLC_DEST_SAP and LLC_DEST_CONN.
*/
static void (*llc_type_handlers[2])(struct llc_sap *sap,
struct sk_buff *skb);
void llc_add_pack(int type, void (*handler)(struct llc_sap *sap,
struct sk_buff *skb))
{
smp_wmb(); /* ensure initialisation is complete before it's called */
if (type == LLC_DEST_SAP || type == LLC_DEST_CONN)
llc_type_handlers[type - 1] = handler;
}
void llc_remove_pack(int type)
{
if (type == LLC_DEST_SAP || type == LLC_DEST_CONN)
llc_type_handlers[type - 1] = NULL;
synchronize_net();
}
void llc_set_station_handler(void (*handler)(struct sk_buff *skb))
{
/* Ensure initialisation is complete before it's called */
if (handler)
smp_wmb();
llc_station_handler = handler;
if (!handler)
synchronize_net();
}
/**
* llc_pdu_type - returns which LLC component must handle for PDU
* @skb: input skb
*
* This function returns which LLC component must handle this PDU.
*/
static __inline__ int llc_pdu_type(struct sk_buff *skb)
{
int type = LLC_DEST_CONN; /* I-PDU or S-PDU type */
struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb);
if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) != LLC_PDU_TYPE_U)
goto out;
switch (LLC_U_PDU_CMD(pdu)) {
case LLC_1_PDU_CMD_XID:
case LLC_1_PDU_CMD_UI:
case LLC_1_PDU_CMD_TEST:
type = LLC_DEST_SAP;
break;
case LLC_2_PDU_CMD_SABME:
case LLC_2_PDU_CMD_DISC:
case LLC_2_PDU_RSP_UA:
case LLC_2_PDU_RSP_DM:
case LLC_2_PDU_RSP_FRMR:
break;
default:
type = LLC_DEST_INVALID;
break;
}
out:
return type;
}
/**
* llc_fixup_skb - initializes skb pointers
* @skb: This argument points to incoming skb
*
* Initializes internal skb pointer to start of network layer by deriving
* length of LLC header; finds length of LLC control field in LLC header
* by looking at the two lowest-order bits of the first control field
* byte; field is either 3 or 4 bytes long.
*/
static inline int llc_fixup_skb(struct sk_buff *skb)
{
u8 llc_len = 2;
struct llc_pdu_un *pdu;
if (unlikely(!pskb_may_pull(skb, sizeof(*pdu))))
return 0;
pdu = (struct llc_pdu_un *)skb->data;
if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) == LLC_PDU_TYPE_U)
llc_len = 1;
llc_len += 2;
if (unlikely(!pskb_may_pull(skb, llc_len)))
return 0;
skb_pull(skb, llc_len);
skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) {
__be16 pdulen;
s32 data_size;
if (skb->mac_len < ETH_HLEN)
return 0;
pdulen = eth_hdr(skb)->h_proto;
data_size = ntohs(pdulen) - llc_len;
if (data_size < 0 || !pskb_may_pull(skb, data_size))
return 0;
if (unlikely(pskb_trim_rcsum(skb, data_size)))
return 0;
}
return 1;
}
/**
* llc_rcv - 802.2 entry point from net lower layers
* @skb: received pdu
* @dev: device that receive pdu
* @pt: packet type
* @orig_dev: the original receive net device
*
* When the system receives a 802.2 frame this function is called. It
* checks SAP and connection of received pdu and passes frame to
* llc_{station,sap,conn}_rcv for sending to proper state machine. If
* the frame is related to a busy connection (a connection is sending
* data now), it queues this frame in the connection's backlog.
*/
int llc_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct llc_sap *sap;
struct llc_pdu_sn *pdu;
int dest;
int (*rcv)(struct sk_buff *, struct net_device *,
struct packet_type *, struct net_device *);
void (*sta_handler)(struct sk_buff *skb);
void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb);
/*
* When the interface is in promisc. mode, drop all the crap that it
* receives, do not try to analyse it.
*/
if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
dprintk("%s: PACKET_OTHERHOST\n", __func__);
goto drop;
}
skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb))
goto out;
if (unlikely(!llc_fixup_skb(skb)))
goto drop;
pdu = llc_pdu_sn_hdr(skb);
if (unlikely(!pdu->dsap)) /* NULL DSAP, refer to station */
goto handle_station;
sap = llc_sap_find(pdu->dsap);
if (unlikely(!sap)) {/* unknown SAP */
dprintk("%s: llc_sap_find(%02X) failed!\n", __func__,
pdu->dsap);
goto drop;
}
/*
* First the upper layer protocols that don't need the full
* LLC functionality
*/
rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb);
sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL;
if (unlikely(!sap_handler)) {
if (rcv)
rcv(skb, dev, pt, orig_dev);
else
kfree_skb(skb);
} else {
if (rcv) {
struct sk_buff *cskb = skb_clone(skb, GFP_ATOMIC);
if (cskb) rcv(cskb, dev, pt, orig_dev);
}
sap_handler(sap, skb);
}
llc_sap_put(sap);
out:
return 0;
drop:
kfree_skb(skb);
goto out;
handle_station:
sta_handler = READ_ONCE(llc_station_handler);
if (!sta_handler)
goto drop;
sta_handler(skb);
goto out;
}
EXPORT_SYMBOL(llc_add_pack);
EXPORT_SYMBOL(llc_remove_pack);
EXPORT_SYMBOL(llc_set_station_handler);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Memory merging support.
*
* This code enables dynamic sharing of identical pages found in different
* memory areas, even if they are not shared by fork()
*
* Copyright (C) 2008-2009 Red Hat, Inc.
* Authors:
* Izik Eidus
* Andrea Arcangeli
* Chris Wright
* Hugh Dickins
*/
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/cputime.h>
#include <linux/rwsem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/spinlock.h>
#include <linux/xxhash.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/memory.h>
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/ksm.h>
#include <linux/hashtable.h>
#include <linux/freezer.h>
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/pagewalk.h>
#include <asm/tlbflush.h>
#include "internal.h"
#include "mm_slot.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ksm.h>
#ifdef CONFIG_NUMA
#define NUMA(x) (x)
#define DO_NUMA(x) do { (x); } while (0)
#else
#define NUMA(x) (0)
#define DO_NUMA(x) do { } while (0)
#endif
typedef u8 rmap_age_t;
/**
* DOC: Overview
*
* A few notes about the KSM scanning process,
* to make it easier to understand the data structures below:
*
* In order to reduce excessive scanning, KSM sorts the memory pages by their
* contents into a data structure that holds pointers to the pages' locations.
*
* Since the contents of the pages may change at any moment, KSM cannot just
* insert the pages into a normal sorted tree and expect it to find anything.
* Therefore KSM uses two data structures - the stable and the unstable tree.
*
* The stable tree holds pointers to all the merged pages (ksm pages), sorted
* by their contents. Because each such page is write-protected, searching on
* this tree is fully assured to be working (except when pages are unmapped),
* and therefore this tree is called the stable tree.
*
* The stable tree node includes information required for reverse
* mapping from a KSM page to virtual addresses that map this page.
*
* In order to avoid large latencies of the rmap walks on KSM pages,
* KSM maintains two types of nodes in the stable tree:
*
* * the regular nodes that keep the reverse mapping structures in a
* linked list
* * the "chains" that link nodes ("dups") that represent the same
* write protected memory content, but each "dup" corresponds to a
* different KSM page copy of that content
*
* Internally, the regular nodes, "dups" and "chains" are represented
* using the same struct ksm_stable_node structure.
*
* In addition to the stable tree, KSM uses a second data structure called the
* unstable tree: this tree holds pointers to pages which have been found to
* be "unchanged for a period of time". The unstable tree sorts these pages
* by their contents, but since they are not write-protected, KSM cannot rely
* upon the unstable tree to work correctly - the unstable tree is liable to
* be corrupted as its contents are modified, and so it is called unstable.
*
* KSM solves this problem by several techniques:
*
* 1) The unstable tree is flushed every time KSM completes scanning all
* memory areas, and then the tree is rebuilt again from the beginning.
* 2) KSM will only insert into the unstable tree, pages whose hash value
* has not changed since the previous scan of all memory areas.
* 3) The unstable tree is a RedBlack Tree - so its balancing is based on the
* colors of the nodes and not on their contents, assuring that even when
* the tree gets "corrupted" it won't get out of balance, so scanning time
* remains the same (also, searching and inserting nodes in an rbtree uses
* the same algorithm, so we have no overhead when we flush and rebuild).
* 4) KSM never flushes the stable tree, which means that even if it were to
* take 10 attempts to find a page in the unstable tree, once it is found,
* it is secured in the stable tree. (When we scan a new page, we first
* compare it against the stable tree, and then against the unstable tree.)
*
* If the merge_across_nodes tunable is unset, then KSM maintains multiple
* stable trees and multiple unstable trees: one of each for each NUMA node.
*/
/**
* struct ksm_mm_slot - ksm information per mm that is being scanned
* @slot: hash lookup from mm to mm_slot
* @rmap_list: head for this mm_slot's singly-linked list of rmap_items
*/
struct ksm_mm_slot {
struct mm_slot slot;
struct ksm_rmap_item *rmap_list;
};
/**
* struct ksm_scan - cursor for scanning
* @mm_slot: the current mm_slot we are scanning
* @address: the next address inside that to be scanned
* @rmap_list: link to the next rmap to be scanned in the rmap_list
* @seqnr: count of completed full scans (needed when removing unstable node)
*
* There is only the one ksm_scan instance of this cursor structure.
*/
struct ksm_scan {
struct ksm_mm_slot *mm_slot;
unsigned long address;
struct ksm_rmap_item **rmap_list;
unsigned long seqnr;
};
/**
* struct ksm_stable_node - node of the stable rbtree
* @node: rb node of this ksm page in the stable tree
* @head: (overlaying parent) &migrate_nodes indicates temporarily on that list
* @hlist_dup: linked into the stable_node->hlist with a stable_node chain
* @list: linked into migrate_nodes, pending placement in the proper node tree
* @hlist: hlist head of rmap_items using this ksm page
* @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid)
* @chain_prune_time: time of the last full garbage collection
* @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN
* @nid: NUMA node id of stable tree in which linked (may not match kpfn)
*/
struct ksm_stable_node {
union {
struct rb_node node; /* when node of stable tree */
struct { /* when listed for migration */
struct list_head *head;
struct {
struct hlist_node hlist_dup;
struct list_head list;
};
};
};
struct hlist_head hlist;
union {
unsigned long kpfn;
unsigned long chain_prune_time;
};
/*
* STABLE_NODE_CHAIN can be any negative number in
* rmap_hlist_len negative range, but better not -1 to be able
* to reliably detect underflows.
*/
#define STABLE_NODE_CHAIN -1024
int rmap_hlist_len;
#ifdef CONFIG_NUMA
int nid;
#endif
};
/**
* struct ksm_rmap_item - reverse mapping item for virtual addresses
* @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list
* @anon_vma: pointer to anon_vma for this mm,address, when in stable tree
* @nid: NUMA node id of unstable tree in which linked (may not match page)
* @mm: the memory structure this rmap_item is pointing into
* @address: the virtual address this rmap_item tracks (+ flags in low bits)
* @oldchecksum: previous checksum of the page at that virtual address
* @node: rb node of this rmap_item in the unstable tree
* @head: pointer to stable_node heading this list in the stable tree
* @hlist: link into hlist of rmap_items hanging off that stable_node
* @age: number of scan iterations since creation
* @remaining_skips: how many scans to skip
*/
struct ksm_rmap_item {
struct ksm_rmap_item *rmap_list;
union {
struct anon_vma *anon_vma; /* when stable */
#ifdef CONFIG_NUMA
int nid; /* when node of unstable tree */
#endif
};
struct mm_struct *mm;
unsigned long address; /* + low bits used for flags below */
unsigned int oldchecksum; /* when unstable */
rmap_age_t age;
rmap_age_t remaining_skips;
union {
struct rb_node node; /* when node of unstable tree */
struct { /* when listed from stable tree */
struct ksm_stable_node *head;
struct hlist_node hlist;
};
};
};
#define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */
#define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */
#define STABLE_FLAG 0x200 /* is listed from the stable tree */
/* The stable and unstable tree heads */
static struct rb_root one_stable_tree[1] = { RB_ROOT };
static struct rb_root one_unstable_tree[1] = { RB_ROOT };
static struct rb_root *root_stable_tree = one_stable_tree;
static struct rb_root *root_unstable_tree = one_unstable_tree;
/* Recently migrated nodes of stable tree, pending proper placement */
static LIST_HEAD(migrate_nodes);
#define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev)
#define MM_SLOTS_HASH_BITS 10
static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct ksm_mm_slot ksm_mm_head = {
.slot.mm_node = LIST_HEAD_INIT(ksm_mm_head.slot.mm_node),
};
static struct ksm_scan ksm_scan = {
.mm_slot = &ksm_mm_head,
};
static struct kmem_cache *rmap_item_cache;
static struct kmem_cache *stable_node_cache;
static struct kmem_cache *mm_slot_cache;
/* Default number of pages to scan per batch */
#define DEFAULT_PAGES_TO_SCAN 100
/* The number of pages scanned */
static unsigned long ksm_pages_scanned;
/* The number of nodes in the stable tree */
static unsigned long ksm_pages_shared;
/* The number of page slots additionally sharing those nodes */
static unsigned long ksm_pages_sharing;
/* The number of nodes in the unstable tree */
static unsigned long ksm_pages_unshared;
/* The number of rmap_items in use: to calculate pages_volatile */
static unsigned long ksm_rmap_items;
/* The number of stable_node chains */
static unsigned long ksm_stable_node_chains;
/* The number of stable_node dups linked to the stable_node chains */
static unsigned long ksm_stable_node_dups;
/* Delay in pruning stale stable_node_dups in the stable_node_chains */
static unsigned int ksm_stable_node_chains_prune_millisecs = 2000;
/* Maximum number of page slots sharing a stable node */
static int ksm_max_page_sharing = 256;
/* Number of pages ksmd should scan in one batch */
static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN;
/* Milliseconds ksmd should sleep between batches */
static unsigned int ksm_thread_sleep_millisecs = 20;
/* Checksum of an empty (zeroed) page */
static unsigned int zero_checksum __read_mostly;
/* Whether to merge empty (zeroed) pages with actual zero pages */
static bool ksm_use_zero_pages __read_mostly;
/* Skip pages that couldn't be de-duplicated previously */
/* Default to true at least temporarily, for testing */
static bool ksm_smart_scan = true;
/* The number of zero pages which is placed by KSM */
atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0);
/* The number of pages that have been skipped due to "smart scanning" */
static unsigned long ksm_pages_skipped;
/* Don't scan more than max pages per batch. */
static unsigned long ksm_advisor_max_pages_to_scan = 30000;
/* Min CPU for scanning pages per scan */
#define KSM_ADVISOR_MIN_CPU 10
/* Max CPU for scanning pages per scan */
static unsigned int ksm_advisor_max_cpu = 70;
/* Target scan time in seconds to analyze all KSM candidate pages. */
static unsigned long ksm_advisor_target_scan_time = 200;
/* Exponentially weighted moving average. */
#define EWMA_WEIGHT 30
/**
* struct advisor_ctx - metadata for KSM advisor
* @start_scan: start time of the current scan
* @scan_time: scan time of previous scan
* @change: change in percent to pages_to_scan parameter
* @cpu_time: cpu time consumed by the ksmd thread in the previous scan
*/
struct advisor_ctx {
ktime_t start_scan;
unsigned long scan_time;
unsigned long change;
unsigned long long cpu_time;
};
static struct advisor_ctx advisor_ctx;
/* Define different advisor's */
enum ksm_advisor_type {
KSM_ADVISOR_NONE,
KSM_ADVISOR_SCAN_TIME,
};
static enum ksm_advisor_type ksm_advisor;
#ifdef CONFIG_SYSFS
/*
* Only called through the sysfs control interface:
*/
/* At least scan this many pages per batch. */
static unsigned long ksm_advisor_min_pages_to_scan = 500;
static void set_advisor_defaults(void)
{
if (ksm_advisor == KSM_ADVISOR_NONE) {
ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN;
} else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) {
advisor_ctx = (const struct advisor_ctx){ 0 };
ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan;
}
}
#endif /* CONFIG_SYSFS */
static inline void advisor_start_scan(void)
{
if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
advisor_ctx.start_scan = ktime_get();
}
/*
* Use previous scan time if available, otherwise use current scan time as an
* approximation for the previous scan time.
*/
static inline unsigned long prev_scan_time(struct advisor_ctx *ctx,
unsigned long scan_time)
{
return ctx->scan_time ? ctx->scan_time : scan_time;
}
/* Calculate exponential weighted moving average */
static unsigned long ewma(unsigned long prev, unsigned long curr)
{
return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100;
}
/*
* The scan time advisor is based on the current scan rate and the target
* scan rate.
*
* new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time)
*
* To avoid perturbations it calculates a change factor of previous changes.
* A new change factor is calculated for each iteration and it uses an
* exponentially weighted moving average. The new pages_to_scan value is
* multiplied with that change factor:
*
* new_pages_to_scan *= change facor
*
* The new_pages_to_scan value is limited by the cpu min and max values. It
* calculates the cpu percent for the last scan and calculates the new
* estimated cpu percent cost for the next scan. That value is capped by the
* cpu min and max setting.
*
* In addition the new pages_to_scan value is capped by the max and min
* limits.
*/
static void scan_time_advisor(void)
{
unsigned int cpu_percent;
unsigned long cpu_time;
unsigned long cpu_time_diff;
unsigned long cpu_time_diff_ms;
unsigned long pages;
unsigned long per_page_cost;
unsigned long factor;
unsigned long change;
unsigned long last_scan_time;
unsigned long scan_time;
/* Convert scan time to seconds */
scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan),
MSEC_PER_SEC);
scan_time = scan_time ? scan_time : 1;
/* Calculate CPU consumption of ksmd background thread */
cpu_time = task_sched_runtime(current);
cpu_time_diff = cpu_time - advisor_ctx.cpu_time;
cpu_time_diff_ms = cpu_time_diff / 1000 / 1000;
cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000);
cpu_percent = cpu_percent ? cpu_percent : 1;
last_scan_time = prev_scan_time(&advisor_ctx, scan_time);
/* Calculate scan time as percentage of target scan time */
factor = ksm_advisor_target_scan_time * 100 / scan_time;
factor = factor ? factor : 1;
/*
* Calculate scan time as percentage of last scan time and use
* exponentially weighted average to smooth it
*/
change = scan_time * 100 / last_scan_time;
change = change ? change : 1;
change = ewma(advisor_ctx.change, change);
/* Calculate new scan rate based on target scan rate. */
pages = ksm_thread_pages_to_scan * 100 / factor;
/* Update pages_to_scan by weighted change percentage. */
pages = pages * change / 100;
/* Cap new pages_to_scan value */
per_page_cost = ksm_thread_pages_to_scan / cpu_percent;
per_page_cost = per_page_cost ? per_page_cost : 1;
pages = min(pages, per_page_cost * ksm_advisor_max_cpu);
pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU);
pages = min(pages, ksm_advisor_max_pages_to_scan);
/* Update advisor context */
advisor_ctx.change = change;
advisor_ctx.scan_time = scan_time;
advisor_ctx.cpu_time = cpu_time;
ksm_thread_pages_to_scan = pages;
trace_ksm_advisor(scan_time, pages, cpu_percent);
}
static void advisor_stop_scan(void)
{
if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
scan_time_advisor();
}
#ifdef CONFIG_NUMA
/* Zeroed when merging across nodes is not allowed */
static unsigned int ksm_merge_across_nodes = 1;
static int ksm_nr_node_ids = 1;
#else
#define ksm_merge_across_nodes 1U
#define ksm_nr_node_ids 1
#endif
#define KSM_RUN_STOP 0
#define KSM_RUN_MERGE 1
#define KSM_RUN_UNMERGE 2
#define KSM_RUN_OFFLINE 4
static unsigned long ksm_run = KSM_RUN_STOP;
static void wait_while_offlining(void);
static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
static DEFINE_SPINLOCK(ksm_mmlist_lock);
static int __init ksm_slab_init(void)
{
rmap_item_cache = KMEM_CACHE(ksm_rmap_item, 0);
if (!rmap_item_cache)
goto out;
stable_node_cache = KMEM_CACHE(ksm_stable_node, 0);
if (!stable_node_cache)
goto out_free1;
mm_slot_cache = KMEM_CACHE(ksm_mm_slot, 0);
if (!mm_slot_cache)
goto out_free2;
return 0;
out_free2:
kmem_cache_destroy(stable_node_cache);
out_free1:
kmem_cache_destroy(rmap_item_cache);
out:
return -ENOMEM;
}
static void __init ksm_slab_free(void)
{
kmem_cache_destroy(mm_slot_cache);
kmem_cache_destroy(stable_node_cache);
kmem_cache_destroy(rmap_item_cache);
mm_slot_cache = NULL;
}
static __always_inline bool is_stable_node_chain(struct ksm_stable_node *chain)
{
return chain->rmap_hlist_len == STABLE_NODE_CHAIN;
}
static __always_inline bool is_stable_node_dup(struct ksm_stable_node *dup)
{
return dup->head == STABLE_NODE_DUP_HEAD;
}
static inline void stable_node_chain_add_dup(struct ksm_stable_node *dup,
struct ksm_stable_node *chain)
{
VM_BUG_ON(is_stable_node_dup(dup));
dup->head = STABLE_NODE_DUP_HEAD;
VM_BUG_ON(!is_stable_node_chain(chain));
hlist_add_head(&dup->hlist_dup, &chain->hlist);
ksm_stable_node_dups++;
}
static inline void __stable_node_dup_del(struct ksm_stable_node *dup)
{
VM_BUG_ON(!is_stable_node_dup(dup));
hlist_del(&dup->hlist_dup);
ksm_stable_node_dups--;
}
static inline void stable_node_dup_del(struct ksm_stable_node *dup)
{
VM_BUG_ON(is_stable_node_chain(dup));
if (is_stable_node_dup(dup))
__stable_node_dup_del(dup);
else
rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid));
#ifdef CONFIG_DEBUG_VM
dup->head = NULL;
#endif
}
static inline struct ksm_rmap_item *alloc_rmap_item(void)
{
struct ksm_rmap_item *rmap_item;
rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL |
__GFP_NORETRY | __GFP_NOWARN);
if (rmap_item)
ksm_rmap_items++;
return rmap_item;
}
static inline void free_rmap_item(struct ksm_rmap_item *rmap_item)
{
ksm_rmap_items--;
rmap_item->mm->ksm_rmap_items--;
rmap_item->mm = NULL; /* debug safety */
kmem_cache_free(rmap_item_cache, rmap_item);
}
static inline struct ksm_stable_node *alloc_stable_node(void)
{
/*
* The allocation can take too long with GFP_KERNEL when memory is under
* pressure, which may lead to hung task warnings. Adding __GFP_HIGH
* grants access to memory reserves, helping to avoid this problem.
*/
return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH);
}
static inline void free_stable_node(struct ksm_stable_node *stable_node)
{
VM_BUG_ON(stable_node->rmap_hlist_len &&
!is_stable_node_chain(stable_node));
kmem_cache_free(stable_node_cache, stable_node);
}
/*
* ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's
* page tables after it has passed through ksm_exit() - which, if necessary,
* takes mmap_lock briefly to serialize against them. ksm_exit() does not set
* a special flag: they can just back out as soon as mm_users goes to zero.
* ksm_test_exit() is used throughout to make this test for exit: in some
* places for correctness, in some places just to avoid unnecessary work.
*/
static inline bool ksm_test_exit(struct mm_struct *mm)
{
return atomic_read(&mm->mm_users) == 0;
}
/*
* We use break_ksm to break COW on a ksm page by triggering unsharing,
* such that the ksm page will get replaced by an exclusive anonymous page.
*
* We take great care only to touch a ksm page, in a VM_MERGEABLE vma,
* in case the application has unmapped and remapped mm,addr meanwhile.
* Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP
* mmap of /dev/mem, where we would not want to touch it.
*
* FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context
* of the process that owns 'vma'. We also do not want to enforce
* protection keys here anyway.
*/
static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma)
{
vm_fault_t ret = 0;
if (lock_vma)
vma_start_write(vma);
do {
bool ksm_page = false;
struct folio_walk fw;
struct folio *folio;
cond_resched();
folio = folio_walk_start(&fw, vma, addr,
FW_MIGRATION | FW_ZEROPAGE);
if (folio) {
/* Small folio implies FW_LEVEL_PTE. */
if (!folio_test_large(folio) &&
(folio_test_ksm(folio) || is_ksm_zero_pte(fw.pte)))
ksm_page = true;
folio_walk_end(&fw, vma);
}
if (!ksm_page)
return 0;
ret = handle_mm_fault(vma, addr,
FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
NULL);
} while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
/*
* We must loop until we no longer find a KSM page because
* handle_mm_fault() may back out if there's any difficulty e.g. if
* pte accessed bit gets updated concurrently.
*
* VM_FAULT_SIGBUS could occur if we race with truncation of the
* backing file, which also invalidates anonymous pages: that's
* okay, that truncation will have unmapped the KSM page for us.
*
* VM_FAULT_OOM: at the time of writing (late July 2009), setting
* aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
* current task has TIF_MEMDIE set, and will be OOM killed on return
* to user; and ksmd, having no mm, would never be chosen for that.
*
* But if the mm is in a limited mem_cgroup, then the fault may fail
* with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
* even ksmd can fail in this way - though it's usually breaking ksm
* just to undo a merge it made a moment before, so unlikely to oom.
*
* That's a pity: we might therefore have more kernel pages allocated
* than we're counting as nodes in the stable tree; but ksm_do_scan
* will retry to break_cow on each pass, so should recover the page
* in due course. The important thing is to not let VM_MERGEABLE
* be cleared while any such pages might remain in the area.
*/
return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
static bool vma_ksm_compatible(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP |
VM_IO | VM_DONTEXPAND | VM_HUGETLB |
VM_MIXEDMAP| VM_DROPPABLE))
return false; /* just ignore the advice */
if (vma_is_dax(vma))
return false;
#ifdef VM_SAO
if (vma->vm_flags & VM_SAO)
return false;
#endif
#ifdef VM_SPARC_ADI
if (vma->vm_flags & VM_SPARC_ADI)
return false;
#endif
return true;
}
static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
unsigned long addr)
{
struct vm_area_struct *vma;
if (ksm_test_exit(mm))
return NULL;
vma = vma_lookup(mm, addr);
if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
return NULL;
return vma;
}
static void break_cow(struct ksm_rmap_item *rmap_item)
{
struct mm_struct *mm = rmap_item->mm;
unsigned long addr = rmap_item->address;
struct vm_area_struct *vma;
/*
* It is not an accident that whenever we want to break COW
* to undo, we also need to drop a reference to the anon_vma.
*/
put_anon_vma(rmap_item->anon_vma);
mmap_read_lock(mm);
vma = find_mergeable_vma(mm, addr);
if (vma)
break_ksm(vma, addr, false);
mmap_read_unlock(mm);
}
static struct page *get_mergeable_page(struct ksm_rmap_item *rmap_item)
{
struct mm_struct *mm = rmap_item->mm;
unsigned long addr = rmap_item->address;
struct vm_area_struct *vma;
struct page *page = NULL;
struct folio_walk fw;
struct folio *folio;
mmap_read_lock(mm);
vma = find_mergeable_vma(mm, addr);
if (!vma)
goto out;
folio = folio_walk_start(&fw, vma, addr, 0);
if (folio) {
if (!folio_is_zone_device(folio) &&
folio_test_anon(folio)) {
folio_get(folio);
page = fw.page;
}
folio_walk_end(&fw, vma);
}
out:
if (page) {
flush_anon_page(vma, page, addr);
flush_dcache_page(page);
}
mmap_read_unlock(mm);
return page;
}
/*
* This helper is used for getting right index into array of tree roots.
* When merge_across_nodes knob is set to 1, there are only two rb-trees for
* stable and unstable pages from all nodes with roots in index 0. Otherwise,
* every node has its own stable and unstable tree.
*/
static inline int get_kpfn_nid(unsigned long kpfn)
{
return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn));
}
static struct ksm_stable_node *alloc_stable_node_chain(struct ksm_stable_node *dup,
struct rb_root *root)
{
struct ksm_stable_node *chain = alloc_stable_node();
VM_BUG_ON(is_stable_node_chain(dup));
if (likely(chain)) {
INIT_HLIST_HEAD(&chain->hlist);
chain->chain_prune_time = jiffies;
chain->rmap_hlist_len = STABLE_NODE_CHAIN;
#if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA)
chain->nid = NUMA_NO_NODE; /* debug */
#endif
ksm_stable_node_chains++;
/*
* Put the stable node chain in the first dimension of
* the stable tree and at the same time remove the old
* stable node.
*/
rb_replace_node(&dup->node, &chain->node, root);
/*
* Move the old stable node to the second dimension
* queued in the hlist_dup. The invariant is that all
* dup stable_nodes in the chain->hlist point to pages
* that are write protected and have the exact same
* content.
*/
stable_node_chain_add_dup(dup, chain);
}
return chain;
}
static inline void free_stable_node_chain(struct ksm_stable_node *chain,
struct rb_root *root)
{
rb_erase(&chain->node, root);
free_stable_node(chain);
ksm_stable_node_chains--;
}
static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node)
{
struct ksm_rmap_item *rmap_item;
/* check it's not STABLE_NODE_CHAIN or negative */
BUG_ON(stable_node->rmap_hlist_len < 0);
hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
if (rmap_item->hlist.next) {
ksm_pages_sharing--;
trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm);
} else {
ksm_pages_shared--;
}
rmap_item->mm->ksm_merging_pages--;
VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
stable_node->rmap_hlist_len--;
put_anon_vma(rmap_item->anon_vma);
rmap_item->address &= PAGE_MASK;
cond_resched();
}
/*
* We need the second aligned pointer of the migrate_nodes
* list_head to stay clear from the rb_parent_color union
* (aligned and different than any node) and also different
* from &migrate_nodes. This will verify that future list.h changes
* don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it.
*/
BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes);
BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1);
trace_ksm_remove_ksm_page(stable_node->kpfn);
if (stable_node->head == &migrate_nodes)
list_del(&stable_node->list);
else
stable_node_dup_del(stable_node);
free_stable_node(stable_node);
}
enum ksm_get_folio_flags {
KSM_GET_FOLIO_NOLOCK,
KSM_GET_FOLIO_LOCK,
KSM_GET_FOLIO_TRYLOCK
};
/*
* ksm_get_folio: checks if the page indicated by the stable node
* is still its ksm page, despite having held no reference to it.
* In which case we can trust the content of the page, and it
* returns the gotten page; but if the page has now been zapped,
* remove the stale node from the stable tree and return NULL.
* But beware, the stable node's page might be being migrated.
*
* You would expect the stable_node to hold a reference to the ksm page.
* But if it increments the page's count, swapping out has to wait for
* ksmd to come around again before it can free the page, which may take
* seconds or even minutes: much too unresponsive. So instead we use a
* "keyhole reference": access to the ksm page from the stable node peeps
* out through its keyhole to see if that page still holds the right key,
* pointing back to this stable node. This relies on freeing a PageAnon
* page to reset its page->mapping to NULL, and relies on no other use of
* a page to put something that might look like our key in page->mapping.
* is on its way to being freed; but it is an anomaly to bear in mind.
*/
static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node,
enum ksm_get_folio_flags flags)
{
struct folio *folio;
void *expected_mapping;
unsigned long kpfn;
expected_mapping = (void *)((unsigned long)stable_node |
PAGE_MAPPING_KSM);
again:
kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */
folio = pfn_folio(kpfn);
if (READ_ONCE(folio->mapping) != expected_mapping)
goto stale;
/*
* We cannot do anything with the page while its refcount is 0.
* Usually 0 means free, or tail of a higher-order page: in which
* case this node is no longer referenced, and should be freed;
* however, it might mean that the page is under page_ref_freeze().
* The __remove_mapping() case is easy, again the node is now stale;
* the same is in reuse_ksm_page() case; but if page is swapcache
* in folio_migrate_mapping(), it might still be our page,
* in which case it's essential to keep the node.
*/
while (!folio_try_get(folio)) {
/*
* Another check for folio->mapping != expected_mapping
* would work here too. We have chosen to test the
* swapcache flag to optimize the common case, when the
* folio is or is about to be freed: the swapcache flag
* is cleared (under spin_lock_irq) in the ref_freeze
* section of __remove_mapping(); but anon folio->mapping
* is reset to NULL later, in free_pages_prepare().
*/
if (!folio_test_swapcache(folio))
goto stale;
cpu_relax();
}
if (READ_ONCE(folio->mapping) != expected_mapping) {
folio_put(folio);
goto stale;
}
if (flags == KSM_GET_FOLIO_TRYLOCK) {
if (!folio_trylock(folio)) {
folio_put(folio);
return ERR_PTR(-EBUSY);
}
} else if (flags == KSM_GET_FOLIO_LOCK)
folio_lock(folio);
if (flags != KSM_GET_FOLIO_NOLOCK) {
if (READ_ONCE(folio->mapping) != expected_mapping) {
folio_unlock(folio);
folio_put(folio);
goto stale;
}
}
return folio;
stale:
/*
* We come here from above when folio->mapping or the swapcache flag
* suggests that the node is stale; but it might be under migration.
* We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(),
* before checking whether node->kpfn has been changed.
*/
smp_rmb();
if (READ_ONCE(stable_node->kpfn) != kpfn)
goto again;
remove_node_from_stable_tree(stable_node);
return NULL;
}
/*
* Removing rmap_item from stable or unstable tree.
* This function will clean the information from the stable/unstable tree.
*/
static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item)
{
if (rmap_item->address & STABLE_FLAG) {
struct ksm_stable_node *stable_node;
struct folio *folio;
stable_node = rmap_item->head;
folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK);
if (!folio)
goto out;
hlist_del(&rmap_item->hlist);
folio_unlock(folio);
folio_put(folio);
if (!hlist_empty(&stable_node->hlist))
ksm_pages_sharing--;
else
ksm_pages_shared--;
rmap_item->mm->ksm_merging_pages--;
VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
stable_node->rmap_hlist_len--;
put_anon_vma(rmap_item->anon_vma);
rmap_item->head = NULL;
rmap_item->address &= PAGE_MASK;
} else if (rmap_item->address & UNSTABLE_FLAG) {
unsigned char age;
/*
* Usually ksmd can and must skip the rb_erase, because
* root_unstable_tree was already reset to RB_ROOT.
* But be careful when an mm is exiting: do the rb_erase
* if this rmap_item was inserted by this scan, rather
* than left over from before.
*/
age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
BUG_ON(age > 1);
if (!age)
rb_erase(&rmap_item->node,
root_unstable_tree + NUMA(rmap_item->nid));
ksm_pages_unshared--;
rmap_item->address &= PAGE_MASK;
}
out:
cond_resched(); /* we're called from many long loops */
}
static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list)
{
while (*rmap_list) {
struct ksm_rmap_item *rmap_item = *rmap_list;
*rmap_list = rmap_item->rmap_list;
remove_rmap_item_from_tree(rmap_item);
free_rmap_item(rmap_item);
}
}
/*
* Though it's very tempting to unmerge rmap_items from stable tree rather
* than check every pte of a given vma, the locking doesn't quite work for
* that - an rmap_item is assigned to the stable tree after inserting ksm
* page and upping mmap_lock. Nor does it fit with the way we skip dup'ing
* rmap_items from parent to child at fork time (so as not to waste time
* if exit comes before the next scan reaches it).
*
* Similarly, although we'd like to remove rmap_items (so updating counts
* and freeing memory) when unmerging an area, it's easier to leave that
* to the next pass of ksmd - consider, for example, how ksmd might be
* in cmp_and_merge_page on one of the rmap_items we would be removing.
*/
static int unmerge_ksm_pages(struct vm_area_struct *vma,
unsigned long start, unsigned long end, bool lock_vma)
{
unsigned long addr;
int err = 0;
for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
if (ksm_test_exit(vma->vm_mm))
break;
if (signal_pending(current))
err = -ERESTARTSYS;
else
err = break_ksm(vma, addr, lock_vma);
}
return err;
}
static inline
struct ksm_stable_node *folio_stable_node(const struct folio *folio)
{
return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL;
}
static inline struct ksm_stable_node *page_stable_node(struct page *page)
{
return folio_stable_node(page_folio(page));
}
static inline void folio_set_stable_node(struct folio *folio,
struct ksm_stable_node *stable_node)
{
VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio);
folio->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM);
}
#ifdef CONFIG_SYSFS
/*
* Only called through the sysfs control interface:
*/
static int remove_stable_node(struct ksm_stable_node *stable_node)
{
struct folio *folio;
int err;
folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK);
if (!folio) {
/*
* ksm_get_folio did remove_node_from_stable_tree itself.
*/
return 0;
}
/*
* Page could be still mapped if this races with __mmput() running in
* between ksm_exit() and exit_mmap(). Just refuse to let
* merge_across_nodes/max_page_sharing be switched.
*/
err = -EBUSY;
if (!folio_mapped(folio)) {
/*
* The stable node did not yet appear stale to ksm_get_folio(),
* since that allows for an unmapped ksm folio to be recognized
* right up until it is freed; but the node is safe to remove.
* This folio might be in an LRU cache waiting to be freed,
* or it might be in the swapcache (perhaps under writeback),
* or it might have been removed from swapcache a moment ago.
*/
folio_set_stable_node(folio, NULL);
remove_node_from_stable_tree(stable_node);
err = 0;
}
folio_unlock(folio);
folio_put(folio);
return err;
}
static int remove_stable_node_chain(struct ksm_stable_node *stable_node,
struct rb_root *root)
{
struct ksm_stable_node *dup;
struct hlist_node *hlist_safe;
if (!is_stable_node_chain(stable_node)) {
VM_BUG_ON(is_stable_node_dup(stable_node));
if (remove_stable_node(stable_node))
return true;
else
return false;
}
hlist_for_each_entry_safe(dup, hlist_safe,
&stable_node->hlist, hlist_dup) {
VM_BUG_ON(!is_stable_node_dup(dup));
if (remove_stable_node(dup))
return true;
}
BUG_ON(!hlist_empty(&stable_node->hlist));
free_stable_node_chain(stable_node, root);
return false;
}
static int remove_all_stable_nodes(void)
{
struct ksm_stable_node *stable_node, *next;
int nid;
int err = 0;
for (nid = 0; nid < ksm_nr_node_ids; nid++) {
while (root_stable_tree[nid].rb_node) {
stable_node = rb_entry(root_stable_tree[nid].rb_node,
struct ksm_stable_node, node);
if (remove_stable_node_chain(stable_node,
root_stable_tree + nid)) {
err = -EBUSY;
break; /* proceed to next nid */
}
cond_resched();
}
}
list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
if (remove_stable_node(stable_node))
err = -EBUSY;
cond_resched();
}
return err;
}
static int unmerge_and_remove_all_rmap_items(void)
{
struct ksm_mm_slot *mm_slot;
struct mm_slot *slot;
struct mm_struct *mm;
struct vm_area_struct *vma;
int err = 0;
spin_lock(&ksm_mmlist_lock);
slot = list_entry(ksm_mm_head.slot.mm_node.next,
struct mm_slot, mm_node);
ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
spin_unlock(&ksm_mmlist_lock);
for (mm_slot = ksm_scan.mm_slot; mm_slot != &ksm_mm_head;
mm_slot = ksm_scan.mm_slot) {
VMA_ITERATOR(vmi, mm_slot->slot.mm, 0);
mm = mm_slot->slot.mm;
mmap_read_lock(mm);
/*
* Exit right away if mm is exiting to avoid lockdep issue in
* the maple tree
*/
if (ksm_test_exit(mm))
goto mm_exiting;
for_each_vma(vmi, vma) {
if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
continue;
err = unmerge_ksm_pages(vma,
vma->vm_start, vma->vm_end, false);
if (err)
goto error;
}
mm_exiting:
remove_trailing_rmap_items(&mm_slot->rmap_list);
mmap_read_unlock(mm);
spin_lock(&ksm_mmlist_lock);
slot = list_entry(mm_slot->slot.mm_node.next,
struct mm_slot, mm_node);
ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
if (ksm_test_exit(mm)) {
hash_del(&mm_slot->slot.hash);
list_del(&mm_slot->slot.mm_node);
spin_unlock(&ksm_mmlist_lock);
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmdrop(mm);
} else
spin_unlock(&ksm_mmlist_lock);
}
/* Clean up stable nodes, but don't worry if some are still busy */
remove_all_stable_nodes();
ksm_scan.seqnr = 0;
return 0;
error:
mmap_read_unlock(mm);
spin_lock(&ksm_mmlist_lock);
ksm_scan.mm_slot = &ksm_mm_head;
spin_unlock(&ksm_mmlist_lock);
return err;
}
#endif /* CONFIG_SYSFS */
static u32 calc_checksum(struct page *page)
{
u32 checksum;
void *addr = kmap_local_page(page);
checksum = xxhash(addr, PAGE_SIZE, 0);
kunmap_local(addr);
return checksum;
}
static int write_protect_page(struct vm_area_struct *vma, struct folio *folio,
pte_t *orig_pte)
{
struct mm_struct *mm = vma->vm_mm;
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0);
int swapped;
int err = -EFAULT;
struct mmu_notifier_range range;
bool anon_exclusive;
pte_t entry;
if (WARN_ON_ONCE(folio_test_large(folio)))
return err;
pvmw.address = page_address_in_vma(folio, folio_page(folio, 0), vma);
if (pvmw.address == -EFAULT)
goto out;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address,
pvmw.address + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
if (!page_vma_mapped_walk(&pvmw))
goto out_mn;
if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?"))
goto out_unlock;
entry = ptep_get(pvmw.pte);
/*
* Handle PFN swap PTEs, such as device-exclusive ones, that actually
* map pages: give up just like the next folio_walk would.
*/
if (unlikely(!pte_present(entry)))
goto out_unlock;
anon_exclusive = PageAnonExclusive(&folio->page);
if (pte_write(entry) || pte_dirty(entry) ||
anon_exclusive || mm_tlb_flush_pending(mm)) {
swapped = folio_test_swapcache(folio);
flush_cache_page(vma, pvmw.address, folio_pfn(folio));
/*
* Ok this is tricky, when get_user_pages_fast() run it doesn't
* take any lock, therefore the check that we are going to make
* with the pagecount against the mapcount is racy and
* O_DIRECT can happen right after the check.
* So we clear the pte and flush the tlb before the check
* this assure us that no O_DIRECT can happen after the check
* or in the middle of the check.
*
* No need to notify as we are downgrading page table to read
* only not changing it to point to a new page.
*
* See Documentation/mm/mmu_notifier.rst
*/
entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte);
/*
* Check that no O_DIRECT or similar I/O is in progress on the
* page
*/
if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) {
set_pte_at(mm, pvmw.address, pvmw.pte, entry);
goto out_unlock;
}
/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
if (anon_exclusive &&
folio_try_share_anon_rmap_pte(folio, &folio->page)) {
set_pte_at(mm, pvmw.address, pvmw.pte, entry);
goto out_unlock;
}
if (pte_dirty(entry))
folio_mark_dirty(folio);
entry = pte_mkclean(entry);
if (pte_write(entry))
entry = pte_wrprotect(entry);
set_pte_at(mm, pvmw.address, pvmw.pte, entry);
}
*orig_pte = entry;
err = 0;
out_unlock:
page_vma_mapped_walk_done(&pvmw);
out_mn:
mmu_notifier_invalidate_range_end(&range);
out:
return err;
}
/**
* replace_page - replace page in vma by new ksm page
* @vma: vma that holds the pte pointing to page
* @page: the page we are replacing by kpage
* @kpage: the ksm page we replace page by
* @orig_pte: the original value of the pte
*
* Returns 0 on success, -EFAULT on failure.
*/
static int replace_page(struct vm_area_struct *vma, struct page *page,
struct page *kpage, pte_t orig_pte)
{
struct folio *kfolio = page_folio(kpage);
struct mm_struct *mm = vma->vm_mm;
struct folio *folio = page_folio(page);
pmd_t *pmd;
pmd_t pmde;
pte_t *ptep;
pte_t newpte;
spinlock_t *ptl;
unsigned long addr;
int err = -EFAULT;
struct mmu_notifier_range range;
addr = page_address_in_vma(folio, page, vma);
if (addr == -EFAULT)
goto out;
pmd = mm_find_pmd(mm, addr);
if (!pmd)
goto out;
/*
* Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
* without holding anon_vma lock for write. So when looking for a
* genuine pmde (in which to find pte), test present and !THP together.
*/
pmde = pmdp_get_lockless(pmd);
if (!pmd_present(pmde) || pmd_trans_huge(pmde))
goto out;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
addr + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!ptep)
goto out_mn;
if (!pte_same(ptep_get(ptep), orig_pte)) {
pte_unmap_unlock(ptep, ptl);
goto out_mn;
}
VM_BUG_ON_PAGE(PageAnonExclusive(page), page);
VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage),
kfolio);
/*
* No need to check ksm_use_zero_pages here: we can only have a
* zero_page here if ksm_use_zero_pages was enabled already.
*/
if (!is_zero_pfn(page_to_pfn(kpage))) {
folio_get(kfolio);
folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE);
newpte = mk_pte(kpage, vma->vm_page_prot);
} else {
/*
* Use pte_mkdirty to mark the zero page mapped by KSM, and then
* we can easily track all KSM-placed zero pages by checking if
* the dirty bit in zero page's PTE is set.
*/
newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot)));
ksm_map_zero_page(mm);
/*
* We're replacing an anonymous page with a zero page, which is
* not anonymous. We need to do proper accounting otherwise we
* will get wrong values in /proc, and a BUG message in dmesg
* when tearing down the mm.
*/
dec_mm_counter(mm, MM_ANONPAGES);
}
flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep)));
/*
* No need to notify as we are replacing a read only page with another
* read only page with the same content.
*
* See Documentation/mm/mmu_notifier.rst
*/
ptep_clear_flush(vma, addr, ptep);
set_pte_at(mm, addr, ptep, newpte);
folio_remove_rmap_pte(folio, page, vma);
if (!folio_mapped(folio))
folio_free_swap(folio);
folio_put(folio);
pte_unmap_unlock(ptep, ptl);
err = 0;
out_mn:
mmu_notifier_invalidate_range_end(&range);
out:
return err;
}
/*
* try_to_merge_one_page - take two pages and merge them into one
* @vma: the vma that holds the pte pointing to page
* @page: the PageAnon page that we want to replace with kpage
* @kpage: the KSM page that we want to map instead of page,
* or NULL the first time when we want to use page as kpage.
*
* This function returns 0 if the pages were merged, -EFAULT otherwise.
*/
static int try_to_merge_one_page(struct vm_area_struct *vma,
struct page *page, struct page *kpage)
{
struct folio *folio = page_folio(page);
pte_t orig_pte = __pte(0);
int err = -EFAULT;
if (page == kpage) /* ksm page forked */
return 0;
if (!folio_test_anon(folio))
goto out;
/*
* We need the folio lock to read a stable swapcache flag in
* write_protect_page(). We trylock because we don't want to wait
* here - we prefer to continue scanning and merging different
* pages, then come back to this page when it is unlocked.
*/
if (!folio_trylock(folio))
goto out;
if (folio_test_large(folio)) {
if (split_huge_page(page))
goto out_unlock;
folio = page_folio(page);
}
/*
* If this anonymous page is mapped only here, its pte may need
* to be write-protected. If it's mapped elsewhere, all of its
* ptes are necessarily already write-protected. But in either
* case, we need to lock and check page_count is not raised.
*/
if (write_protect_page(vma, folio, &orig_pte) == 0) {
if (!kpage) {
/*
* While we hold folio lock, upgrade folio from
* anon to a NULL stable_node with the KSM flag set:
* stable_tree_insert() will update stable_node.
*/
folio_set_stable_node(folio, NULL);
folio_mark_accessed(folio);
/*
* Page reclaim just frees a clean folio with no dirty
* ptes: make sure that the ksm page would be swapped.
*/
if (!folio_test_dirty(folio))
folio_mark_dirty(folio);
err = 0;
} else if (pages_identical(page, kpage))
err = replace_page(vma, page, kpage, orig_pte);
}
out_unlock:
folio_unlock(folio);
out:
return err;
}
/*
* This function returns 0 if the pages were merged or if they are
* no longer merging candidates (e.g., VMA stale), -EFAULT otherwise.
*/
static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item,
struct page *page)
{
struct mm_struct *mm = rmap_item->mm;
int err = -EFAULT;
/*
* Same checksum as an empty page. We attempt to merge it with the
* appropriate zero page if the user enabled this via sysfs.
*/
if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) {
struct vm_area_struct *vma;
mmap_read_lock(mm);
vma = find_mergeable_vma(mm, rmap_item->address);
if (vma) {
err = try_to_merge_one_page(vma, page,
ZERO_PAGE(rmap_item->address));
trace_ksm_merge_one_page(
page_to_pfn(ZERO_PAGE(rmap_item->address)),
rmap_item, mm, err);
} else {
/*
* If the vma is out of date, we do not need to
* continue.
*/
err = 0;
}
mmap_read_unlock(mm);
}
return err;
}
/*
* try_to_merge_with_ksm_page - like try_to_merge_two_pages,
* but no new kernel page is allocated: kpage must already be a ksm page.
*
* This function returns 0 if the pages were merged, -EFAULT otherwise.
*/
static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item,
struct page *page, struct page *kpage)
{
struct mm_struct *mm = rmap_item->mm;
struct vm_area_struct *vma;
int err = -EFAULT;
mmap_read_lock(mm);
vma = find_mergeable_vma(mm, rmap_item->address);
if (!vma)
goto out;
err = try_to_merge_one_page(vma, page, kpage);
if (err)
goto out;
/* Unstable nid is in union with stable anon_vma: remove first */
remove_rmap_item_from_tree(rmap_item);
/* Must get reference to anon_vma while still holding mmap_lock */
rmap_item->anon_vma = vma->anon_vma;
get_anon_vma(vma->anon_vma);
out:
mmap_read_unlock(mm);
trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page),
rmap_item, mm, err);
return err;
}
/*
* try_to_merge_two_pages - take two identical pages and prepare them
* to be merged into one page.
*
* This function returns the kpage if we successfully merged two identical
* pages into one ksm page, NULL otherwise.
*
* Note that this function upgrades page to ksm page: if one of the pages
* is already a ksm page, try_to_merge_with_ksm_page should be used.
*/
static struct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item,
struct page *page,
struct ksm_rmap_item *tree_rmap_item,
struct page *tree_page)
{
int err;
err = try_to_merge_with_ksm_page(rmap_item, page, NULL);
if (!err) {
err = try_to_merge_with_ksm_page(tree_rmap_item,
tree_page, page);
/*
* If that fails, we have a ksm page with only one pte
* pointing to it: so break it.
*/
if (err)
break_cow(rmap_item);
}
return err ? NULL : page_folio(page);
}
static __always_inline
bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset)
{
VM_BUG_ON(stable_node->rmap_hlist_len < 0);
/*
* Check that at least one mapping still exists, otherwise
* there's no much point to merge and share with this
* stable_node, as the underlying tree_page of the other
* sharer is going to be freed soon.
*/
return stable_node->rmap_hlist_len &&
stable_node->rmap_hlist_len + offset < ksm_max_page_sharing;
}
static __always_inline
bool is_page_sharing_candidate(struct ksm_stable_node *stable_node)
{
return __is_page_sharing_candidate(stable_node, 0);
}
static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup,
struct ksm_stable_node **_stable_node,
struct rb_root *root,
bool prune_stale_stable_nodes)
{
struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node;
struct hlist_node *hlist_safe;
struct folio *folio, *tree_folio = NULL;
int found_rmap_hlist_len;
if (!prune_stale_stable_nodes ||
time_before(jiffies, stable_node->chain_prune_time +
msecs_to_jiffies(
ksm_stable_node_chains_prune_millisecs)))
prune_stale_stable_nodes = false;
else
stable_node->chain_prune_time = jiffies;
hlist_for_each_entry_safe(dup, hlist_safe,
&stable_node->hlist, hlist_dup) {
cond_resched();
/*
* We must walk all stable_node_dup to prune the stale
* stable nodes during lookup.
*
* ksm_get_folio can drop the nodes from the
* stable_node->hlist if they point to freed pages
* (that's why we do a _safe walk). The "dup"
* stable_node parameter itself will be freed from
* under us if it returns NULL.
*/
folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK);
if (!folio)
continue;
/* Pick the best candidate if possible. */
if (!found || (is_page_sharing_candidate(dup) &&
(!is_page_sharing_candidate(found) ||
dup->rmap_hlist_len > found_rmap_hlist_len))) {
if (found)
folio_put(tree_folio);
found = dup;
found_rmap_hlist_len = found->rmap_hlist_len;
tree_folio = folio;
/* skip put_page for found candidate */
if (!prune_stale_stable_nodes &&
is_page_sharing_candidate(found))
break;
continue;
}
folio_put(folio);
}
if (found) {
if (hlist_is_singular_node(&found->hlist_dup, &stable_node->hlist)) {
/*
* If there's not just one entry it would
* corrupt memory, better BUG_ON. In KSM
* context with no lock held it's not even
* fatal.
*/
BUG_ON(stable_node->hlist.first->next);
/*
* There's just one entry and it is below the
* deduplication limit so drop the chain.
*/
rb_replace_node(&stable_node->node, &found->node,
root);
free_stable_node(stable_node);
ksm_stable_node_chains--;
ksm_stable_node_dups--;
/*
* NOTE: the caller depends on the stable_node
* to be equal to stable_node_dup if the chain
* was collapsed.
*/
*_stable_node = found;
/*
* Just for robustness, as stable_node is
* otherwise left as a stable pointer, the
* compiler shall optimize it away at build
* time.
*/
stable_node = NULL;
} else if (stable_node->hlist.first != &found->hlist_dup &&
__is_page_sharing_candidate(found, 1)) {
/*
* If the found stable_node dup can accept one
* more future merge (in addition to the one
* that is underway) and is not at the head of
* the chain, put it there so next search will
* be quicker in the !prune_stale_stable_nodes
* case.
*
* NOTE: it would be inaccurate to use nr > 1
* instead of checking the hlist.first pointer
* directly, because in the
* prune_stale_stable_nodes case "nr" isn't
* the position of the found dup in the chain,
* but the total number of dups in the chain.
*/
hlist_del(&found->hlist_dup);
hlist_add_head(&found->hlist_dup,
&stable_node->hlist);
}
} else {
/* Its hlist must be empty if no one found. */
free_stable_node_chain(stable_node, root);
}
*_stable_node_dup = found;
return tree_folio;
}
/*
* Like for ksm_get_folio, this function can free the *_stable_node and
* *_stable_node_dup if the returned tree_page is NULL.
*
* It can also free and overwrite *_stable_node with the found
* stable_node_dup if the chain is collapsed (in which case
* *_stable_node will be equal to *_stable_node_dup like if the chain
* never existed). It's up to the caller to verify tree_page is not
* NULL before dereferencing *_stable_node or *_stable_node_dup.
*
* *_stable_node_dup is really a second output parameter of this
* function and will be overwritten in all cases, the caller doesn't
* need to initialize it.
*/
static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup,
struct ksm_stable_node **_stable_node,
struct rb_root *root,
bool prune_stale_stable_nodes)
{
struct ksm_stable_node *stable_node = *_stable_node;
if (!is_stable_node_chain(stable_node)) {
*_stable_node_dup = stable_node;
return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK);
}
return stable_node_dup(_stable_node_dup, _stable_node, root,
prune_stale_stable_nodes);
}
static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d,
struct ksm_stable_node **s_n,
struct rb_root *root)
{
return __stable_node_chain(s_n_d, s_n, root, true);
}
static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d,
struct ksm_stable_node **s_n,
struct rb_root *root)
{
return __stable_node_chain(s_n_d, s_n, root, false);
}
/*
* stable_tree_search - search for page inside the stable tree
*
* This function checks if there is a page inside the stable tree
* with identical content to the page that we are scanning right now.
*
* This function returns the stable tree node of identical content if found,
* -EBUSY if the stable node's page is being migrated, NULL otherwise.
*/
static struct folio *stable_tree_search(struct page *page)
{
int nid;
struct rb_root *root;
struct rb_node **new;
struct rb_node *parent;
struct ksm_stable_node *stable_node, *stable_node_dup;
struct ksm_stable_node *page_node;
struct folio *folio;
folio = page_folio(page);
page_node = folio_stable_node(folio);
if (page_node && page_node->head != &migrate_nodes) {
/* ksm page forked */
folio_get(folio);
return folio;
}
nid = get_kpfn_nid(folio_pfn(folio));
root = root_stable_tree + nid;
again:
new = &root->rb_node;
parent = NULL;
while (*new) {
struct folio *tree_folio;
int ret;
cond_resched();
stable_node = rb_entry(*new, struct ksm_stable_node, node);
tree_folio = chain_prune(&stable_node_dup, &stable_node, root);
if (!tree_folio) {
/*
* If we walked over a stale stable_node,
* ksm_get_folio() will call rb_erase() and it
* may rebalance the tree from under us. So
* restart the search from scratch. Returning
* NULL would be safe too, but we'd generate
* false negative insertions just because some
* stable_node was stale.
*/
goto again;
}
ret = memcmp_pages(page, &tree_folio->page);
folio_put(tree_folio);
parent = *new;
if (ret < 0)
new = &parent->rb_left;
else if (ret > 0)
new = &parent->rb_right;
else {
if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes);
/*
* If the mapcount of our migrated KSM folio is
* at most 1, we can merge it with another
* KSM folio where we know that we have space
* for one more mapping without exceeding the
* ksm_max_page_sharing limit: see
* chain_prune(). This way, we can avoid adding
* this stable node to the chain.
*/
if (folio_mapcount(folio) > 1)
goto chain_append;
}
if (!is_page_sharing_candidate(stable_node_dup)) {
/*
* If the stable_node is a chain and
* we got a payload match in memcmp
* but we cannot merge the scanned
* page in any of the existing
* stable_node dups because they're
* all full, we need to wait the
* scanned page to find itself a match
* in the unstable tree to create a
* brand new KSM page to add later to
* the dups of this stable_node.
*/
return NULL;
}
/*
* Lock and unlock the stable_node's page (which
* might already have been migrated) so that page
* migration is sure to notice its raised count.
* It would be more elegant to return stable_node
* than kpage, but that involves more changes.
*/
tree_folio = ksm_get_folio(stable_node_dup,
KSM_GET_FOLIO_TRYLOCK);
if (PTR_ERR(tree_folio) == -EBUSY)
return ERR_PTR(-EBUSY);
if (unlikely(!tree_folio))
/*
* The tree may have been rebalanced,
* so re-evaluate parent and new.
*/
goto again;
folio_unlock(tree_folio);
if (get_kpfn_nid(stable_node_dup->kpfn) !=
NUMA(stable_node_dup->nid)) {
folio_put(tree_folio);
goto replace;
}
return tree_folio;
}
}
if (!page_node)
return NULL;
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
rb_link_node(&page_node->node, parent, new);
rb_insert_color(&page_node->node, root);
out:
if (is_page_sharing_candidate(page_node)) {
folio_get(folio);
return folio;
} else
return NULL;
replace:
/*
* If stable_node was a chain and chain_prune collapsed it,
* stable_node has been updated to be the new regular
* stable_node. A collapse of the chain is indistinguishable
* from the case there was no chain in the stable
* rbtree. Otherwise stable_node is the chain and
* stable_node_dup is the dup to replace.
*/
if (stable_node_dup == stable_node) {
VM_BUG_ON(is_stable_node_chain(stable_node_dup));
VM_BUG_ON(is_stable_node_dup(stable_node_dup));
/* there is no chain */
if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
rb_replace_node(&stable_node_dup->node,
&page_node->node,
root);
if (is_page_sharing_candidate(page_node))
folio_get(folio);
else
folio = NULL;
} else {
rb_erase(&stable_node_dup->node, root);
folio = NULL;
}
} else {
VM_BUG_ON(!is_stable_node_chain(stable_node));
__stable_node_dup_del(stable_node_dup);
if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
stable_node_chain_add_dup(page_node, stable_node);
if (is_page_sharing_candidate(page_node))
folio_get(folio);
else
folio = NULL;
} else {
folio = NULL;
}
}
stable_node_dup->head = &migrate_nodes;
list_add(&stable_node_dup->list, stable_node_dup->head);
return folio;
chain_append:
/*
* If stable_node was a chain and chain_prune collapsed it,
* stable_node has been updated to be the new regular
* stable_node. A collapse of the chain is indistinguishable
* from the case there was no chain in the stable
* rbtree. Otherwise stable_node is the chain and
* stable_node_dup is the dup to replace.
*/
if (stable_node_dup == stable_node) {
VM_BUG_ON(is_stable_node_dup(stable_node_dup));
/* chain is missing so create it */
stable_node = alloc_stable_node_chain(stable_node_dup,
root);
if (!stable_node)
return NULL;
}
/*
* Add this stable_node dup that was
* migrated to the stable_node chain
* of the current nid for this page
* content.
*/
VM_BUG_ON(!is_stable_node_dup(stable_node_dup));
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
stable_node_chain_add_dup(page_node, stable_node);
goto out;
}
/*
* stable_tree_insert - insert stable tree node pointing to new ksm page
* into the stable tree.
*
* This function returns the stable tree node just allocated on success,
* NULL otherwise.
*/
static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio)
{
int nid;
unsigned long kpfn;
struct rb_root *root;
struct rb_node **new;
struct rb_node *parent;
struct ksm_stable_node *stable_node, *stable_node_dup;
bool need_chain = false;
kpfn = folio_pfn(kfolio);
nid = get_kpfn_nid(kpfn);
root = root_stable_tree + nid;
again:
parent = NULL;
new = &root->rb_node;
while (*new) {
struct folio *tree_folio;
int ret;
cond_resched();
stable_node = rb_entry(*new, struct ksm_stable_node, node);
tree_folio = chain(&stable_node_dup, &stable_node, root);
if (!tree_folio) {
/*
* If we walked over a stale stable_node,
* ksm_get_folio() will call rb_erase() and it
* may rebalance the tree from under us. So
* restart the search from scratch. Returning
* NULL would be safe too, but we'd generate
* false negative insertions just because some
* stable_node was stale.
*/
goto again;
}
ret = memcmp_pages(&kfolio->page, &tree_folio->page);
folio_put(tree_folio);
parent = *new;
if (ret < 0)
new = &parent->rb_left;
else if (ret > 0)
new = &parent->rb_right;
else {
need_chain = true;
break;
}
}
stable_node_dup = alloc_stable_node();
if (!stable_node_dup)
return NULL;
INIT_HLIST_HEAD(&stable_node_dup->hlist);
stable_node_dup->kpfn = kpfn;
stable_node_dup->rmap_hlist_len = 0;
DO_NUMA(stable_node_dup->nid = nid);
if (!need_chain) {
rb_link_node(&stable_node_dup->node, parent, new);
rb_insert_color(&stable_node_dup->node, root);
} else {
if (!is_stable_node_chain(stable_node)) {
struct ksm_stable_node *orig = stable_node;
/* chain is missing so create it */
stable_node = alloc_stable_node_chain(orig, root);
if (!stable_node) {
free_stable_node(stable_node_dup);
return NULL;
}
}
stable_node_chain_add_dup(stable_node_dup, stable_node);
}
folio_set_stable_node(kfolio, stable_node_dup);
return stable_node_dup;
}
/*
* unstable_tree_search_insert - search for identical page,
* else insert rmap_item into the unstable tree.
*
* This function searches for a page in the unstable tree identical to the
* page currently being scanned; and if no identical page is found in the
* tree, we insert rmap_item as a new object into the unstable tree.
*
* This function returns pointer to rmap_item found to be identical
* to the currently scanned page, NULL otherwise.
*
* This function does both searching and inserting, because they share
* the same walking algorithm in an rbtree.
*/
static
struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item,
struct page *page,
struct page **tree_pagep)
{
struct rb_node **new;
struct rb_root *root;
struct rb_node *parent = NULL;
int nid;
nid = get_kpfn_nid(page_to_pfn(page));
root = root_unstable_tree + nid;
new = &root->rb_node;
while (*new) {
struct ksm_rmap_item *tree_rmap_item;
struct page *tree_page;
int ret;
cond_resched();
tree_rmap_item = rb_entry(*new, struct ksm_rmap_item, node);
tree_page = get_mergeable_page(tree_rmap_item);
if (!tree_page)
return NULL;
/*
* Don't substitute a ksm page for a forked page.
*/
if (page == tree_page) {
put_page(tree_page);
return NULL;
}
ret = memcmp_pages(page, tree_page);
parent = *new;
if (ret < 0) {
put_page(tree_page);
new = &parent->rb_left;
} else if (ret > 0) {
put_page(tree_page);
new = &parent->rb_right;
} else if (!ksm_merge_across_nodes &&
page_to_nid(tree_page) != nid) {
/*
* If tree_page has been migrated to another NUMA node,
* it will be flushed out and put in the right unstable
* tree next time: only merge with it when across_nodes.
*/
put_page(tree_page);
return NULL;
} else {
*tree_pagep = tree_page;
return tree_rmap_item;
}
}
rmap_item->address |= UNSTABLE_FLAG;
rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK);
DO_NUMA(rmap_item->nid = nid);
rb_link_node(&rmap_item->node, parent, new);
rb_insert_color(&rmap_item->node, root);
ksm_pages_unshared++;
return NULL;
}
/*
* stable_tree_append - add another rmap_item to the linked list of
* rmap_items hanging off a given node of the stable tree, all sharing
* the same ksm page.
*/
static void stable_tree_append(struct ksm_rmap_item *rmap_item,
struct ksm_stable_node *stable_node,
bool max_page_sharing_bypass)
{
/*
* rmap won't find this mapping if we don't insert the
* rmap_item in the right stable_node
* duplicate. page_migration could break later if rmap breaks,
* so we can as well crash here. We really need to check for
* rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check
* for other negative values as an underflow if detected here
* for the first time (and not when decreasing rmap_hlist_len)
* would be sign of memory corruption in the stable_node.
*/
BUG_ON(stable_node->rmap_hlist_len < 0);
stable_node->rmap_hlist_len++;
if (!max_page_sharing_bypass)
/* possibly non fatal but unexpected overflow, only warn */
WARN_ON_ONCE(stable_node->rmap_hlist_len >
ksm_max_page_sharing);
rmap_item->head = stable_node;
rmap_item->address |= STABLE_FLAG;
hlist_add_head(&rmap_item->hlist, &stable_node->hlist);
if (rmap_item->hlist.next)
ksm_pages_sharing++;
else
ksm_pages_shared++;
rmap_item->mm->ksm_merging_pages++;
}
/*
* cmp_and_merge_page - first see if page can be merged into the stable tree;
* if not, compare checksum to previous and if it's the same, see if page can
* be inserted into the unstable tree, or merged with a page already there and
* both transferred to the stable tree.
*
* @page: the page that we are searching identical page to.
* @rmap_item: the reverse mapping into the virtual address of this page
*/
static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item)
{
struct ksm_rmap_item *tree_rmap_item;
struct page *tree_page = NULL;
struct ksm_stable_node *stable_node;
struct folio *kfolio;
unsigned int checksum;
int err;
bool max_page_sharing_bypass = false;
stable_node = page_stable_node(page);
if (stable_node) {
if (stable_node->head != &migrate_nodes &&
get_kpfn_nid(READ_ONCE(stable_node->kpfn)) !=
NUMA(stable_node->nid)) {
stable_node_dup_del(stable_node);
stable_node->head = &migrate_nodes;
list_add(&stable_node->list, stable_node->head);
}
if (stable_node->head != &migrate_nodes &&
rmap_item->head == stable_node)
return;
/*
* If it's a KSM fork, allow it to go over the sharing limit
* without warnings.
*/
if (!is_page_sharing_candidate(stable_node))
max_page_sharing_bypass = true;
} else {
remove_rmap_item_from_tree(rmap_item);
/*
* If the hash value of the page has changed from the last time
* we calculated it, this page is changing frequently: therefore we
* don't want to insert it in the unstable tree, and we don't want
* to waste our time searching for something identical to it there.
*/
checksum = calc_checksum(page);
if (rmap_item->oldchecksum != checksum) {
rmap_item->oldchecksum = checksum;
return;
}
if (!try_to_merge_with_zero_page(rmap_item, page))
return;
}
/* Start by searching for the folio in the stable tree */
kfolio = stable_tree_search(page);
if (&kfolio->page == page && rmap_item->head == stable_node) {
folio_put(kfolio);
return;
}
remove_rmap_item_from_tree(rmap_item);
if (kfolio) {
if (kfolio == ERR_PTR(-EBUSY))
return;
err = try_to_merge_with_ksm_page(rmap_item, page, &kfolio->page);
if (!err) {
/*
* The page was successfully merged:
* add its rmap_item to the stable tree.
*/
folio_lock(kfolio);
stable_tree_append(rmap_item, folio_stable_node(kfolio),
max_page_sharing_bypass);
folio_unlock(kfolio);
}
folio_put(kfolio);
return;
}
tree_rmap_item =
unstable_tree_search_insert(rmap_item, page, &tree_page);
if (tree_rmap_item) {
bool split;
kfolio = try_to_merge_two_pages(rmap_item, page,
tree_rmap_item, tree_page);
/*
* If both pages we tried to merge belong to the same compound
* page, then we actually ended up increasing the reference
* count of the same compound page twice, and split_huge_page
* failed.
* Here we set a flag if that happened, and we use it later to
* try split_huge_page again. Since we call put_page right
* afterwards, the reference count will be correct and
* split_huge_page should succeed.
*/
split = PageTransCompound(page)
&& compound_head(page) == compound_head(tree_page);
put_page(tree_page);
if (kfolio) {
/*
* The pages were successfully merged: insert new
* node in the stable tree and add both rmap_items.
*/
folio_lock(kfolio);
stable_node = stable_tree_insert(kfolio);
if (stable_node) {
stable_tree_append(tree_rmap_item, stable_node,
false);
stable_tree_append(rmap_item, stable_node,
false);
}
folio_unlock(kfolio);
/*
* If we fail to insert the page into the stable tree,
* we will have 2 virtual addresses that are pointing
* to a ksm page left outside the stable tree,
* in which case we need to break_cow on both.
*/
if (!stable_node) {
break_cow(tree_rmap_item);
break_cow(rmap_item);
}
} else if (split) {
/*
* We are here if we tried to merge two pages and
* failed because they both belonged to the same
* compound page. We will split the page now, but no
* merging will take place.
* We do not want to add the cost of a full lock; if
* the page is locked, it is better to skip it and
* perhaps try again later.
*/
if (!trylock_page(page))
return;
split_huge_page(page);
unlock_page(page);
}
}
}
static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot,
struct ksm_rmap_item **rmap_list,
unsigned long addr)
{
struct ksm_rmap_item *rmap_item;
while (*rmap_list) {
rmap_item = *rmap_list;
if ((rmap_item->address & PAGE_MASK) == addr)
return rmap_item;
if (rmap_item->address > addr)
break;
*rmap_list = rmap_item->rmap_list;
remove_rmap_item_from_tree(rmap_item);
free_rmap_item(rmap_item);
}
rmap_item = alloc_rmap_item();
if (rmap_item) {
/* It has already been zeroed */
rmap_item->mm = mm_slot->slot.mm;
rmap_item->mm->ksm_rmap_items++;
rmap_item->address = addr;
rmap_item->rmap_list = *rmap_list;
*rmap_list = rmap_item;
}
return rmap_item;
}
/*
* Calculate skip age for the ksm page age. The age determines how often
* de-duplicating has already been tried unsuccessfully. If the age is
* smaller, the scanning of this page is skipped for less scans.
*
* @age: rmap_item age of page
*/
static unsigned int skip_age(rmap_age_t age)
{
if (age <= 3)
return 1;
if (age <= 5)
return 2;
if (age <= 8)
return 4;
return 8;
}
/*
* Determines if a page should be skipped for the current scan.
*
* @folio: folio containing the page to check
* @rmap_item: associated rmap_item of page
*/
static bool should_skip_rmap_item(struct folio *folio,
struct ksm_rmap_item *rmap_item)
{
rmap_age_t age;
if (!ksm_smart_scan)
return false;
/*
* Never skip pages that are already KSM; pages cmp_and_merge_page()
* will essentially ignore them, but we still have to process them
* properly.
*/
if (folio_test_ksm(folio))
return false;
age = rmap_item->age;
if (age != U8_MAX)
rmap_item->age++;
/*
* Smaller ages are not skipped, they need to get a chance to go
* through the different phases of the KSM merging.
*/
if (age < 3)
return false;
/*
* Are we still allowed to skip? If not, then don't skip it
* and determine how much more often we are allowed to skip next.
*/
if (!rmap_item->remaining_skips) {
rmap_item->remaining_skips = skip_age(age);
return false;
}
/* Skip this page */
ksm_pages_skipped++;
rmap_item->remaining_skips--;
remove_rmap_item_from_tree(rmap_item);
return true;
}
static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
{
struct mm_struct *mm;
struct ksm_mm_slot *mm_slot;
struct mm_slot *slot;
struct vm_area_struct *vma;
struct ksm_rmap_item *rmap_item;
struct vma_iterator vmi;
int nid;
if (list_empty(&ksm_mm_head.slot.mm_node))
return NULL;
mm_slot = ksm_scan.mm_slot;
if (mm_slot == &ksm_mm_head) {
advisor_start_scan();
trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items);
/*
* A number of pages can hang around indefinitely in per-cpu
* LRU cache, raised page count preventing write_protect_page
* from merging them. Though it doesn't really matter much,
* it is puzzling to see some stuck in pages_volatile until
* other activity jostles them out, and they also prevented
* LTP's KSM test from succeeding deterministically; so drain
* them here (here rather than on entry to ksm_do_scan(),
* so we don't IPI too often when pages_to_scan is set low).
*/
lru_add_drain_all();
/*
* Whereas stale stable_nodes on the stable_tree itself
* get pruned in the regular course of stable_tree_search(),
* those moved out to the migrate_nodes list can accumulate:
* so prune them once before each full scan.
*/
if (!ksm_merge_across_nodes) {
struct ksm_stable_node *stable_node, *next;
struct folio *folio;
list_for_each_entry_safe(stable_node, next,
&migrate_nodes, list) {
folio = ksm_get_folio(stable_node,
KSM_GET_FOLIO_NOLOCK);
if (folio)
folio_put(folio);
cond_resched();
}
}
for (nid = 0; nid < ksm_nr_node_ids; nid++)
root_unstable_tree[nid] = RB_ROOT;
spin_lock(&ksm_mmlist_lock);
slot = list_entry(mm_slot->slot.mm_node.next,
struct mm_slot, mm_node);
mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
ksm_scan.mm_slot = mm_slot;
spin_unlock(&ksm_mmlist_lock);
/*
* Although we tested list_empty() above, a racing __ksm_exit
* of the last mm on the list may have removed it since then.
*/
if (mm_slot == &ksm_mm_head)
return NULL;
next_mm:
ksm_scan.address = 0;
ksm_scan.rmap_list = &mm_slot->rmap_list;
}
slot = &mm_slot->slot;
mm = slot->mm;
vma_iter_init(&vmi, mm, ksm_scan.address);
mmap_read_lock(mm);
if (ksm_test_exit(mm))
goto no_vmas;
for_each_vma(vmi, vma) {
if (!(vma->vm_flags & VM_MERGEABLE))
continue;
if (ksm_scan.address < vma->vm_start)
ksm_scan.address = vma->vm_start;
if (!vma->anon_vma)
ksm_scan.address = vma->vm_end;
while (ksm_scan.address < vma->vm_end) {
struct page *tmp_page = NULL;
struct folio_walk fw;
struct folio *folio;
if (ksm_test_exit(mm))
break;
folio = folio_walk_start(&fw, vma, ksm_scan.address, 0);
if (folio) {
if (!folio_is_zone_device(folio) &&
folio_test_anon(folio)) {
folio_get(folio);
tmp_page = fw.page;
}
folio_walk_end(&fw, vma);
}
if (tmp_page) {
flush_anon_page(vma, tmp_page, ksm_scan.address);
flush_dcache_page(tmp_page);
rmap_item = get_next_rmap_item(mm_slot,
ksm_scan.rmap_list, ksm_scan.address);
if (rmap_item) {
ksm_scan.rmap_list =
&rmap_item->rmap_list;
if (should_skip_rmap_item(folio, rmap_item)) {
folio_put(folio);
goto next_page;
}
ksm_scan.address += PAGE_SIZE;
*page = tmp_page;
} else {
folio_put(folio);
}
mmap_read_unlock(mm);
return rmap_item;
}
next_page:
ksm_scan.address += PAGE_SIZE;
cond_resched();
}
}
if (ksm_test_exit(mm)) {
no_vmas:
ksm_scan.address = 0;
ksm_scan.rmap_list = &mm_slot->rmap_list;
}
/*
* Nuke all the rmap_items that are above this current rmap:
* because there were no VM_MERGEABLE vmas with such addresses.
*/
remove_trailing_rmap_items(ksm_scan.rmap_list);
spin_lock(&ksm_mmlist_lock);
slot = list_entry(mm_slot->slot.mm_node.next,
struct mm_slot, mm_node);
ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
if (ksm_scan.address == 0) {
/*
* We've completed a full scan of all vmas, holding mmap_lock
* throughout, and found no VM_MERGEABLE: so do the same as
* __ksm_exit does to remove this mm from all our lists now.
* This applies either when cleaning up after __ksm_exit
* (but beware: we can reach here even before __ksm_exit),
* or when all VM_MERGEABLE areas have been unmapped (and
* mmap_lock then protects against race with MADV_MERGEABLE).
*/
hash_del(&mm_slot->slot.hash);
list_del(&mm_slot->slot.mm_node);
spin_unlock(&ksm_mmlist_lock);
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmap_read_unlock(mm);
mmdrop(mm);
} else {
mmap_read_unlock(mm);
/*
* mmap_read_unlock(mm) first because after
* spin_unlock(&ksm_mmlist_lock) run, the "mm" may
* already have been freed under us by __ksm_exit()
* because the "mm_slot" is still hashed and
* ksm_scan.mm_slot doesn't point to it anymore.
*/
spin_unlock(&ksm_mmlist_lock);
}
/* Repeat until we've completed scanning the whole list */
mm_slot = ksm_scan.mm_slot;
if (mm_slot != &ksm_mm_head)
goto next_mm;
advisor_stop_scan();
trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items);
ksm_scan.seqnr++;
return NULL;
}
/**
* ksm_do_scan - the ksm scanner main worker function.
* @scan_npages: number of pages we want to scan before we return.
*/
static void ksm_do_scan(unsigned int scan_npages)
{
struct ksm_rmap_item *rmap_item;
struct page *page;
while (scan_npages-- && likely(!freezing(current))) {
cond_resched();
rmap_item = scan_get_next_rmap_item(&page);
if (!rmap_item)
return;
cmp_and_merge_page(page, rmap_item);
put_page(page);
ksm_pages_scanned++;
}
}
static int ksmd_should_run(void)
{
return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node);
}
static int ksm_scan_thread(void *nothing)
{
unsigned int sleep_ms;
set_freezable();
set_user_nice(current, 5);
while (!kthread_should_stop()) {
mutex_lock(&ksm_thread_mutex);
wait_while_offlining();
if (ksmd_should_run())
ksm_do_scan(ksm_thread_pages_to_scan);
mutex_unlock(&ksm_thread_mutex);
if (ksmd_should_run()) {
sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs);
wait_event_freezable_timeout(ksm_iter_wait,
sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs),
msecs_to_jiffies(sleep_ms));
} else {
wait_event_freezable(ksm_thread_wait,
ksmd_should_run() || kthread_should_stop());
}
}
return 0;
}
static void __ksm_add_vma(struct vm_area_struct *vma)
{
unsigned long vm_flags = vma->vm_flags;
if (vm_flags & VM_MERGEABLE)
return;
if (vma_ksm_compatible(vma)) vm_flags_set(vma, VM_MERGEABLE);
}
static int __ksm_del_vma(struct vm_area_struct *vma)
{
int err;
if (!(vma->vm_flags & VM_MERGEABLE))
return 0;
if (vma->anon_vma) {
err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true);
if (err)
return err;
}
vm_flags_clear(vma, VM_MERGEABLE);
return 0;
}
/**
* ksm_add_vma - Mark vma as mergeable if compatible
*
* @vma: Pointer to vma
*/
void ksm_add_vma(struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) __ksm_add_vma(vma);
}
static void ksm_add_vmas(struct mm_struct *mm)
{
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, 0);
for_each_vma(vmi, vma)
__ksm_add_vma(vma);
}
static int ksm_del_vmas(struct mm_struct *mm)
{
struct vm_area_struct *vma;
int err;
VMA_ITERATOR(vmi, mm, 0);
for_each_vma(vmi, vma) {
err = __ksm_del_vma(vma);
if (err)
return err;
}
return 0;
}
/**
* ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all
* compatible VMA's
*
* @mm: Pointer to mm
*
* Returns 0 on success, otherwise error code
*/
int ksm_enable_merge_any(struct mm_struct *mm)
{
int err;
if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
return 0;
if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
err = __ksm_enter(mm);
if (err)
return err;
}
set_bit(MMF_VM_MERGE_ANY, &mm->flags);
ksm_add_vmas(mm);
return 0;
}
/**
* ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm,
* previously enabled via ksm_enable_merge_any().
*
* Disabling merging implies unmerging any merged pages, like setting
* MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and
* merging on all compatible VMA's remains enabled.
*
* @mm: Pointer to mm
*
* Returns 0 on success, otherwise error code
*/
int ksm_disable_merge_any(struct mm_struct *mm)
{
int err;
if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags))
return 0;
err = ksm_del_vmas(mm);
if (err) {
ksm_add_vmas(mm);
return err;
}
clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
return 0;
}
int ksm_disable(struct mm_struct *mm)
{
mmap_assert_write_locked(mm);
if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
return 0;
if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
return ksm_disable_merge_any(mm);
return ksm_del_vmas(mm);
}
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
int err;
switch (advice) {
case MADV_MERGEABLE:
if (vma->vm_flags & VM_MERGEABLE)
return 0;
if (!vma_ksm_compatible(vma))
return 0;
if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
err = __ksm_enter(mm);
if (err)
return err;
}
*vm_flags |= VM_MERGEABLE;
break;
case MADV_UNMERGEABLE:
if (!(*vm_flags & VM_MERGEABLE))
return 0; /* just ignore the advice */
if (vma->anon_vma) {
err = unmerge_ksm_pages(vma, start, end, true);
if (err)
return err;
}
*vm_flags &= ~VM_MERGEABLE;
break;
}
return 0;
}
EXPORT_SYMBOL_GPL(ksm_madvise);
int __ksm_enter(struct mm_struct *mm)
{
struct ksm_mm_slot *mm_slot;
struct mm_slot *slot;
int needs_wakeup;
mm_slot = mm_slot_alloc(mm_slot_cache);
if (!mm_slot)
return -ENOMEM;
slot = &mm_slot->slot;
/* Check ksm_run too? Would need tighter locking */
needs_wakeup = list_empty(&ksm_mm_head.slot.mm_node);
spin_lock(&ksm_mmlist_lock);
mm_slot_insert(mm_slots_hash, mm, slot);
/*
* When KSM_RUN_MERGE (or KSM_RUN_STOP),
* insert just behind the scanning cursor, to let the area settle
* down a little; when fork is followed by immediate exec, we don't
* want ksmd to waste time setting up and tearing down an rmap_list.
*
* But when KSM_RUN_UNMERGE, it's important to insert ahead of its
* scanning cursor, otherwise KSM pages in newly forked mms will be
* missed: then we might as well insert at the end of the list.
*/
if (ksm_run & KSM_RUN_UNMERGE)
list_add_tail(&slot->mm_node, &ksm_mm_head.slot.mm_node);
else
list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node);
spin_unlock(&ksm_mmlist_lock);
set_bit(MMF_VM_MERGEABLE, &mm->flags);
mmgrab(mm);
if (needs_wakeup)
wake_up_interruptible(&ksm_thread_wait);
trace_ksm_enter(mm);
return 0;
}
void __ksm_exit(struct mm_struct *mm)
{
struct ksm_mm_slot *mm_slot;
struct mm_slot *slot;
int easy_to_free = 0;
/*
* This process is exiting: if it's straightforward (as is the
* case when ksmd was never running), free mm_slot immediately.
* But if it's at the cursor or has rmap_items linked to it, use
* mmap_lock to synchronize with any break_cows before pagetables
* are freed, and leave the mm_slot on the list for ksmd to free.
* Beware: ksm may already have noticed it exiting and freed the slot.
*/
spin_lock(&ksm_mmlist_lock);
slot = mm_slot_lookup(mm_slots_hash, mm);
mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
if (mm_slot && ksm_scan.mm_slot != mm_slot) {
if (!mm_slot->rmap_list) {
hash_del(&slot->hash);
list_del(&slot->mm_node);
easy_to_free = 1;
} else {
list_move(&slot->mm_node,
&ksm_scan.mm_slot->slot.mm_node);
}
}
spin_unlock(&ksm_mmlist_lock);
if (easy_to_free) {
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
mmdrop(mm);
} else if (mm_slot) {
mmap_write_lock(mm);
mmap_write_unlock(mm);
}
trace_ksm_exit(mm);
}
struct folio *ksm_might_need_to_copy(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page = folio_page(folio, 0);
struct anon_vma *anon_vma = folio_anon_vma(folio);
struct folio *new_folio;
if (folio_test_large(folio))
return folio;
if (folio_test_ksm(folio)) {
if (folio_stable_node(folio) &&
!(ksm_run & KSM_RUN_UNMERGE))
return folio; /* no need to copy it */
} else if (!anon_vma) {
return folio; /* no need to copy it */
} else if (folio->index == linear_page_index(vma, addr) &&
anon_vma->root == vma->anon_vma->root) {
return folio; /* still no need to copy it */
}
if (PageHWPoison(page))
return ERR_PTR(-EHWPOISON);
if (!folio_test_uptodate(folio))
return folio; /* let do_swap_page report the error */
new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr);
if (new_folio &&
mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) {
folio_put(new_folio);
new_folio = NULL;
}
if (new_folio) {
if (copy_mc_user_highpage(folio_page(new_folio, 0), page,
addr, vma)) {
folio_put(new_folio);
return ERR_PTR(-EHWPOISON);
}
folio_set_dirty(new_folio);
__folio_mark_uptodate(new_folio);
__folio_set_locked(new_folio);
#ifdef CONFIG_SWAP
count_vm_event(KSM_SWPIN_COPY);
#endif
}
return new_folio;
}
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc)
{
struct ksm_stable_node *stable_node;
struct ksm_rmap_item *rmap_item;
int search_new_forks = 0;
VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio);
/*
* Rely on the page lock to protect against concurrent modifications
* to that page's node of the stable tree.
*/
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
stable_node = folio_stable_node(folio);
if (!stable_node)
return;
again:
hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
struct anon_vma *anon_vma = rmap_item->anon_vma;
struct anon_vma_chain *vmac;
struct vm_area_struct *vma;
cond_resched();
if (!anon_vma_trylock_read(anon_vma)) {
if (rwc->try_lock) {
rwc->contended = true;
return;
}
anon_vma_lock_read(anon_vma);
}
anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
0, ULONG_MAX) {
unsigned long addr;
cond_resched();
vma = vmac->vma;
/* Ignore the stable/unstable/sqnr flags */
addr = rmap_item->address & PAGE_MASK;
if (addr < vma->vm_start || addr >= vma->vm_end)
continue;
/*
* Initially we examine only the vma which covers this
* rmap_item; but later, if there is still work to do,
* we examine covering vmas in other mms: in case they
* were forked from the original since ksmd passed.
*/
if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
continue;
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
continue;
if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) {
anon_vma_unlock_read(anon_vma);
return;
}
if (rwc->done && rwc->done(folio)) {
anon_vma_unlock_read(anon_vma);
return;
}
}
anon_vma_unlock_read(anon_vma);
}
if (!search_new_forks++)
goto again;
}
#ifdef CONFIG_MEMORY_FAILURE
/*
* Collect processes when the error hit an ksm page.
*/
void collect_procs_ksm(const struct folio *folio, const struct page *page,
struct list_head *to_kill, int force_early)
{
struct ksm_stable_node *stable_node;
struct ksm_rmap_item *rmap_item;
struct vm_area_struct *vma;
struct task_struct *tsk;
stable_node = folio_stable_node(folio);
if (!stable_node)
return;
hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
struct anon_vma *av = rmap_item->anon_vma;
anon_vma_lock_read(av);
rcu_read_lock();
for_each_process(tsk) {
struct anon_vma_chain *vmac;
unsigned long addr;
struct task_struct *t =
task_early_kill(tsk, force_early);
if (!t)
continue;
anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0,
ULONG_MAX)
{
vma = vmac->vma;
if (vma->vm_mm == t->mm) {
addr = rmap_item->address & PAGE_MASK;
add_to_kill_ksm(t, page, vma, to_kill,
addr);
}
}
}
rcu_read_unlock();
anon_vma_unlock_read(av);
}
}
#endif
#ifdef CONFIG_MIGRATION
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio)
{
struct ksm_stable_node *stable_node;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio);
VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio);
stable_node = folio_stable_node(folio);
if (stable_node) {
VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio);
stable_node->kpfn = folio_pfn(newfolio);
/*
* newfolio->mapping was set in advance; now we need smp_wmb()
* to make sure that the new stable_node->kpfn is visible
* to ksm_get_folio() before it can see that folio->mapping
* has gone stale (or that the swapcache flag has been cleared).
*/
smp_wmb();
folio_set_stable_node(folio, NULL);
}
}
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_MEMORY_HOTREMOVE
static void wait_while_offlining(void)
{
while (ksm_run & KSM_RUN_OFFLINE) {
mutex_unlock(&ksm_thread_mutex);
wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
TASK_UNINTERRUPTIBLE);
mutex_lock(&ksm_thread_mutex);
}
}
static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node,
unsigned long start_pfn,
unsigned long end_pfn)
{
if (stable_node->kpfn >= start_pfn &&
stable_node->kpfn < end_pfn) {
/*
* Don't ksm_get_folio, page has already gone:
* which is why we keep kpfn instead of page*
*/
remove_node_from_stable_tree(stable_node);
return true;
}
return false;
}
static bool stable_node_chain_remove_range(struct ksm_stable_node *stable_node,
unsigned long start_pfn,
unsigned long end_pfn,
struct rb_root *root)
{
struct ksm_stable_node *dup;
struct hlist_node *hlist_safe;
if (!is_stable_node_chain(stable_node)) {
VM_BUG_ON(is_stable_node_dup(stable_node));
return stable_node_dup_remove_range(stable_node, start_pfn,
end_pfn);
}
hlist_for_each_entry_safe(dup, hlist_safe,
&stable_node->hlist, hlist_dup) {
VM_BUG_ON(!is_stable_node_dup(dup));
stable_node_dup_remove_range(dup, start_pfn, end_pfn);
}
if (hlist_empty(&stable_node->hlist)) {
free_stable_node_chain(stable_node, root);
return true; /* notify caller that tree was rebalanced */
} else
return false;
}
static void ksm_check_stable_tree(unsigned long start_pfn,
unsigned long end_pfn)
{
struct ksm_stable_node *stable_node, *next;
struct rb_node *node;
int nid;
for (nid = 0; nid < ksm_nr_node_ids; nid++) {
node = rb_first(root_stable_tree + nid);
while (node) {
stable_node = rb_entry(node, struct ksm_stable_node, node);
if (stable_node_chain_remove_range(stable_node,
start_pfn, end_pfn,
root_stable_tree +
nid))
node = rb_first(root_stable_tree + nid);
else
node = rb_next(node);
cond_resched();
}
}
list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
if (stable_node->kpfn >= start_pfn &&
stable_node->kpfn < end_pfn)
remove_node_from_stable_tree(stable_node);
cond_resched();
}
}
static int ksm_memory_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
struct memory_notify *mn = arg;
switch (action) {
case MEM_GOING_OFFLINE:
/*
* Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items()
* and remove_all_stable_nodes() while memory is going offline:
* it is unsafe for them to touch the stable tree at this time.
* But unmerge_ksm_pages(), rmap lookups and other entry points
* which do not need the ksm_thread_mutex are all safe.
*/
mutex_lock(&ksm_thread_mutex);
ksm_run |= KSM_RUN_OFFLINE;
mutex_unlock(&ksm_thread_mutex);
break;
case MEM_OFFLINE:
/*
* Most of the work is done by page migration; but there might
* be a few stable_nodes left over, still pointing to struct
* pages which have been offlined: prune those from the tree,
* otherwise ksm_get_folio() might later try to access a
* non-existent struct page.
*/
ksm_check_stable_tree(mn->start_pfn,
mn->start_pfn + mn->nr_pages);
fallthrough;
case MEM_CANCEL_OFFLINE:
mutex_lock(&ksm_thread_mutex);
ksm_run &= ~KSM_RUN_OFFLINE;
mutex_unlock(&ksm_thread_mutex);
smp_mb(); /* wake_up_bit advises this */
wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE));
break;
}
return NOTIFY_OK;
}
#else
static void wait_while_offlining(void)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
#ifdef CONFIG_PROC_FS
/*
* The process is mergeable only if any VMA is currently
* applicable to KSM.
*
* The mmap lock must be held in read mode.
*/
bool ksm_process_mergeable(struct mm_struct *mm)
{
struct vm_area_struct *vma;
mmap_assert_locked(mm);
VMA_ITERATOR(vmi, mm, 0);
for_each_vma(vmi, vma)
if (vma->vm_flags & VM_MERGEABLE)
return true;
return false;
}
long ksm_process_profit(struct mm_struct *mm)
{
return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE -
mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SYSFS
/*
* This all compiles without CONFIG_SYSFS, but is a waste of space.
*/
#define KSM_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define KSM_ATTR(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RW(_name)
static ssize_t sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_thread_sleep_millisecs);
}
static ssize_t sleep_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
ksm_thread_sleep_millisecs = msecs;
wake_up_interruptible(&ksm_iter_wait);
return count;
}
KSM_ATTR(sleep_millisecs);
static ssize_t pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_thread_pages_to_scan);
}
static ssize_t pages_to_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int nr_pages;
int err;
if (ksm_advisor != KSM_ADVISOR_NONE)
return -EINVAL;
err = kstrtouint(buf, 10, &nr_pages);
if (err)
return -EINVAL;
ksm_thread_pages_to_scan = nr_pages;
return count;
}
KSM_ATTR(pages_to_scan);
static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_run);
}
static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int flags;
int err;
err = kstrtouint(buf, 10, &flags);
if (err)
return -EINVAL;
if (flags > KSM_RUN_UNMERGE)
return -EINVAL;
/*
* KSM_RUN_MERGE sets ksmd running, and 0 stops it running.
* KSM_RUN_UNMERGE stops it running and unmerges all rmap_items,
* breaking COW to free the pages_shared (but leaves mm_slots
* on the list for when ksmd may be set running again).
*/
mutex_lock(&ksm_thread_mutex);
wait_while_offlining();
if (ksm_run != flags) {
ksm_run = flags;
if (flags & KSM_RUN_UNMERGE) {
set_current_oom_origin();
err = unmerge_and_remove_all_rmap_items();
clear_current_oom_origin();
if (err) {
ksm_run = KSM_RUN_STOP;
count = err;
}
}
}
mutex_unlock(&ksm_thread_mutex);
if (flags & KSM_RUN_MERGE)
wake_up_interruptible(&ksm_thread_wait);
return count;
}
KSM_ATTR(run);
#ifdef CONFIG_NUMA
static ssize_t merge_across_nodes_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_merge_across_nodes);
}
static ssize_t merge_across_nodes_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long knob;
err = kstrtoul(buf, 10, &knob);
if (err)
return err;
if (knob > 1)
return -EINVAL;
mutex_lock(&ksm_thread_mutex);
wait_while_offlining();
if (ksm_merge_across_nodes != knob) {
if (ksm_pages_shared || remove_all_stable_nodes())
err = -EBUSY;
else if (root_stable_tree == one_stable_tree) {
struct rb_root *buf;
/*
* This is the first time that we switch away from the
* default of merging across nodes: must now allocate
* a buffer to hold as many roots as may be needed.
* Allocate stable and unstable together:
* MAXSMP NODES_SHIFT 10 will use 16kB.
*/
buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf),
GFP_KERNEL);
/* Let us assume that RB_ROOT is NULL is zero */
if (!buf)
err = -ENOMEM;
else {
root_stable_tree = buf;
root_unstable_tree = buf + nr_node_ids;
/* Stable tree is empty but not the unstable */
root_unstable_tree[0] = one_unstable_tree[0];
}
}
if (!err) {
ksm_merge_across_nodes = knob;
ksm_nr_node_ids = knob ? 1 : nr_node_ids;
}
}
mutex_unlock(&ksm_thread_mutex);
return err ? err : count;
}
KSM_ATTR(merge_across_nodes);
#endif
static ssize_t use_zero_pages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_use_zero_pages);
}
static ssize_t use_zero_pages_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
bool value;
err = kstrtobool(buf, &value);
if (err)
return -EINVAL;
ksm_use_zero_pages = value;
return count;
}
KSM_ATTR(use_zero_pages);
static ssize_t max_page_sharing_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_max_page_sharing);
}
static ssize_t max_page_sharing_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
int knob;
err = kstrtoint(buf, 10, &knob);
if (err)
return err;
/*
* When a KSM page is created it is shared by 2 mappings. This
* being a signed comparison, it implicitly verifies it's not
* negative.
*/
if (knob < 2)
return -EINVAL;
if (READ_ONCE(ksm_max_page_sharing) == knob)
return count;
mutex_lock(&ksm_thread_mutex);
wait_while_offlining();
if (ksm_max_page_sharing != knob) {
if (ksm_pages_shared || remove_all_stable_nodes())
err = -EBUSY;
else
ksm_max_page_sharing = knob;
}
mutex_unlock(&ksm_thread_mutex);
return err ? err : count;
}
KSM_ATTR(max_page_sharing);
static ssize_t pages_scanned_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_pages_scanned);
}
KSM_ATTR_RO(pages_scanned);
static ssize_t pages_shared_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_pages_shared);
}
KSM_ATTR_RO(pages_shared);
static ssize_t pages_sharing_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_pages_sharing);
}
KSM_ATTR_RO(pages_sharing);
static ssize_t pages_unshared_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_pages_unshared);
}
KSM_ATTR_RO(pages_unshared);
static ssize_t pages_volatile_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
long ksm_pages_volatile;
ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared
- ksm_pages_sharing - ksm_pages_unshared;
/*
* It was not worth any locking to calculate that statistic,
* but it might therefore sometimes be negative: conceal that.
*/
if (ksm_pages_volatile < 0)
ksm_pages_volatile = 0;
return sysfs_emit(buf, "%ld\n", ksm_pages_volatile);
}
KSM_ATTR_RO(pages_volatile);
static ssize_t pages_skipped_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_pages_skipped);
}
KSM_ATTR_RO(pages_skipped);
static ssize_t ksm_zero_pages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages));
}
KSM_ATTR_RO(ksm_zero_pages);
static ssize_t general_profit_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
long general_profit;
general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE -
ksm_rmap_items * sizeof(struct ksm_rmap_item);
return sysfs_emit(buf, "%ld\n", general_profit);
}
KSM_ATTR_RO(general_profit);
static ssize_t stable_node_dups_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_stable_node_dups);
}
KSM_ATTR_RO(stable_node_dups);
static ssize_t stable_node_chains_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_stable_node_chains);
}
KSM_ATTR_RO(stable_node_chains);
static ssize_t
stable_node_chains_prune_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_stable_node_chains_prune_millisecs);
}
static ssize_t
stable_node_chains_prune_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
ksm_stable_node_chains_prune_millisecs = msecs;
return count;
}
KSM_ATTR(stable_node_chains_prune_millisecs);
static ssize_t full_scans_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_scan.seqnr);
}
KSM_ATTR_RO(full_scans);
static ssize_t smart_scan_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_smart_scan);
}
static ssize_t smart_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
bool value;
err = kstrtobool(buf, &value);
if (err)
return -EINVAL;
ksm_smart_scan = value;
return count;
}
KSM_ATTR(smart_scan);
static ssize_t advisor_mode_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
const char *output;
if (ksm_advisor == KSM_ADVISOR_NONE)
output = "[none] scan-time";
else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME)
output = "none [scan-time]";
return sysfs_emit(buf, "%s\n", output);
}
static ssize_t advisor_mode_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf,
size_t count)
{
enum ksm_advisor_type curr_advisor = ksm_advisor;
if (sysfs_streq("scan-time", buf))
ksm_advisor = KSM_ADVISOR_SCAN_TIME;
else if (sysfs_streq("none", buf))
ksm_advisor = KSM_ADVISOR_NONE;
else
return -EINVAL;
/* Set advisor default values */
if (curr_advisor != ksm_advisor)
set_advisor_defaults();
return count;
}
KSM_ATTR(advisor_mode);
static ssize_t advisor_max_cpu_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu);
}
static ssize_t advisor_max_cpu_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long value;
err = kstrtoul(buf, 10, &value);
if (err)
return -EINVAL;
ksm_advisor_max_cpu = value;
return count;
}
KSM_ATTR(advisor_max_cpu);
static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan);
}
static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long value;
err = kstrtoul(buf, 10, &value);
if (err)
return -EINVAL;
ksm_advisor_min_pages_to_scan = value;
return count;
}
KSM_ATTR(advisor_min_pages_to_scan);
static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan);
}
static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long value;
err = kstrtoul(buf, 10, &value);
if (err)
return -EINVAL;
ksm_advisor_max_pages_to_scan = value;
return count;
}
KSM_ATTR(advisor_max_pages_to_scan);
static ssize_t advisor_target_scan_time_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time);
}
static ssize_t advisor_target_scan_time_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long value;
err = kstrtoul(buf, 10, &value);
if (err)
return -EINVAL;
if (value < 1)
return -EINVAL;
ksm_advisor_target_scan_time = value;
return count;
}
KSM_ATTR(advisor_target_scan_time);
static struct attribute *ksm_attrs[] = {
&sleep_millisecs_attr.attr,
&pages_to_scan_attr.attr,
&run_attr.attr,
&pages_scanned_attr.attr,
&pages_shared_attr.attr,
&pages_sharing_attr.attr,
&pages_unshared_attr.attr,
&pages_volatile_attr.attr,
&pages_skipped_attr.attr,
&ksm_zero_pages_attr.attr,
&full_scans_attr.attr,
#ifdef CONFIG_NUMA
&merge_across_nodes_attr.attr,
#endif
&max_page_sharing_attr.attr,
&stable_node_chains_attr.attr,
&stable_node_dups_attr.attr,
&stable_node_chains_prune_millisecs_attr.attr,
&use_zero_pages_attr.attr,
&general_profit_attr.attr,
&smart_scan_attr.attr,
&advisor_mode_attr.attr,
&advisor_max_cpu_attr.attr,
&advisor_min_pages_to_scan_attr.attr,
&advisor_max_pages_to_scan_attr.attr,
&advisor_target_scan_time_attr.attr,
NULL,
};
static const struct attribute_group ksm_attr_group = {
.attrs = ksm_attrs,
.name = "ksm",
};
#endif /* CONFIG_SYSFS */
static int __init ksm_init(void)
{
struct task_struct *ksm_thread;
int err;
/* The correct value depends on page size and endianness */
zero_checksum = calc_checksum(ZERO_PAGE(0));
/* Default to false for backwards compatibility */
ksm_use_zero_pages = false;
err = ksm_slab_init();
if (err)
goto out;
ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd");
if (IS_ERR(ksm_thread)) {
pr_err("ksm: creating kthread failed\n");
err = PTR_ERR(ksm_thread);
goto out_free;
}
#ifdef CONFIG_SYSFS
err = sysfs_create_group(mm_kobj, &ksm_attr_group);
if (err) {
pr_err("ksm: register sysfs failed\n");
kthread_stop(ksm_thread);
goto out_free;
}
#else
ksm_run = KSM_RUN_MERGE; /* no way for user to start it */
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_MEMORY_HOTREMOVE
/* There is no significance to this priority 100 */
hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI);
#endif
return 0;
out_free:
ksm_slab_free();
out:
return err;
}
subsys_initcall(ksm_init);
// SPDX-License-Identifier: GPL-2.0
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/page_table_check.h>
#include <linux/rcupdate_wait.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/dax.h>
#include <linux/ksm.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
#include "mm_slot.h"
enum scan_result {
SCAN_FAIL,
SCAN_SUCCEED,
SCAN_PMD_NULL,
SCAN_PMD_NONE,
SCAN_PMD_MAPPED,
SCAN_EXCEED_NONE_PTE,
SCAN_EXCEED_SWAP_PTE,
SCAN_EXCEED_SHARED_PTE,
SCAN_PTE_NON_PRESENT,
SCAN_PTE_UFFD_WP,
SCAN_PTE_MAPPED_HUGEPAGE,
SCAN_PAGE_RO,
SCAN_LACK_REFERENCED_PAGE,
SCAN_PAGE_NULL,
SCAN_SCAN_ABORT,
SCAN_PAGE_COUNT,
SCAN_PAGE_LRU,
SCAN_PAGE_LOCK,
SCAN_PAGE_ANON,
SCAN_PAGE_COMPOUND,
SCAN_ANY_PROCESS,
SCAN_VMA_NULL,
SCAN_VMA_CHECK,
SCAN_ADDRESS_RANGE,
SCAN_DEL_PAGE_LRU,
SCAN_ALLOC_HUGE_PAGE_FAIL,
SCAN_CGROUP_CHARGE_FAIL,
SCAN_TRUNCATED,
SCAN_PAGE_HAS_PRIVATE,
SCAN_STORE_FAILED,
SCAN_COPY_MC,
SCAN_PAGE_FILLED,
};
#define CREATE_TRACE_POINTS
#include <trace/events/huge_memory.h>
static struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
/* during fragmentation poll the hugepage allocator once every minute */
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static unsigned long khugepaged_sleep_expire;
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
/*
* default collapse hugepages if there is at least one pte mapped like
* it would have happened if the vma was large enough during page
* fault.
*
* Note that these are only respected if collapse was initiated by khugepaged.
*/
unsigned int khugepaged_max_ptes_none __read_mostly;
static unsigned int khugepaged_max_ptes_swap __read_mostly;
static unsigned int khugepaged_max_ptes_shared __read_mostly;
#define MM_SLOTS_HASH_BITS 10
static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct kmem_cache *mm_slot_cache __ro_after_init;
struct collapse_control {
bool is_khugepaged;
/* Num pages scanned per node */
u32 node_load[MAX_NUMNODES];
/* nodemask for allocation fallback */
nodemask_t alloc_nmask;
};
/**
* struct khugepaged_mm_slot - khugepaged information per mm that is being scanned
* @slot: hash lookup from mm to mm_slot
*/
struct khugepaged_mm_slot {
struct mm_slot slot;
};
/**
* struct khugepaged_scan - cursor for scanning
* @mm_head: the head of the mm list to scan
* @mm_slot: the current mm_slot we are scanning
* @address: the next address inside that to be scanned
*
* There is only the one khugepaged_scan instance of this cursor structure.
*/
struct khugepaged_scan {
struct list_head mm_head;
struct khugepaged_mm_slot *mm_slot;
unsigned long address;
};
static struct khugepaged_scan khugepaged_scan = {
.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
};
#ifdef CONFIG_SYSFS
static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs);
}
static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
khugepaged_scan_sleep_millisecs = msecs;
khugepaged_sleep_expire = 0;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute scan_sleep_millisecs_attr =
__ATTR_RW(scan_sleep_millisecs);
static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs);
}
static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
khugepaged_alloc_sleep_millisecs = msecs;
khugepaged_sleep_expire = 0;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute alloc_sleep_millisecs_attr =
__ATTR_RW(alloc_sleep_millisecs);
static ssize_t pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan);
}
static ssize_t pages_to_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned int pages;
int err;
err = kstrtouint(buf, 10, &pages);
if (err || !pages)
return -EINVAL;
khugepaged_pages_to_scan = pages;
return count;
}
static struct kobj_attribute pages_to_scan_attr =
__ATTR_RW(pages_to_scan);
static ssize_t pages_collapsed_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed);
}
static struct kobj_attribute pages_collapsed_attr =
__ATTR_RO(pages_collapsed);
static ssize_t full_scans_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_full_scans);
}
static struct kobj_attribute full_scans_attr =
__ATTR_RO(full_scans);
static ssize_t defrag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_hugepage_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return single_hugepage_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static struct kobj_attribute khugepaged_defrag_attr =
__ATTR_RW(defrag);
/*
* max_ptes_none controls if khugepaged should collapse hugepages over
* any unmapped ptes in turn potentially increasing the memory
* footprint of the vmas. When max_ptes_none is 0 khugepaged will not
* reduce the available free memory in the system as it
* runs. Increasing max_ptes_none will instead potentially reduce the
* free memory in the system during the khugepaged scan.
*/
static ssize_t max_ptes_none_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none);
}
static ssize_t max_ptes_none_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_none;
err = kstrtoul(buf, 10, &max_ptes_none);
if (err || max_ptes_none > HPAGE_PMD_NR - 1)
return -EINVAL;
khugepaged_max_ptes_none = max_ptes_none;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_none_attr =
__ATTR_RW(max_ptes_none);
static ssize_t max_ptes_swap_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap);
}
static ssize_t max_ptes_swap_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_swap;
err = kstrtoul(buf, 10, &max_ptes_swap);
if (err || max_ptes_swap > HPAGE_PMD_NR - 1)
return -EINVAL;
khugepaged_max_ptes_swap = max_ptes_swap;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_swap_attr =
__ATTR_RW(max_ptes_swap);
static ssize_t max_ptes_shared_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared);
}
static ssize_t max_ptes_shared_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_shared;
err = kstrtoul(buf, 10, &max_ptes_shared);
if (err || max_ptes_shared > HPAGE_PMD_NR - 1)
return -EINVAL;
khugepaged_max_ptes_shared = max_ptes_shared;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_shared_attr =
__ATTR_RW(max_ptes_shared);
static struct attribute *khugepaged_attr[] = {
&khugepaged_defrag_attr.attr,
&khugepaged_max_ptes_none_attr.attr,
&khugepaged_max_ptes_swap_attr.attr,
&khugepaged_max_ptes_shared_attr.attr,
&pages_to_scan_attr.attr,
&pages_collapsed_attr.attr,
&full_scans_attr.attr,
&scan_sleep_millisecs_attr.attr,
&alloc_sleep_millisecs_attr.attr,
NULL,
};
struct attribute_group khugepaged_attr_group = {
.attrs = khugepaged_attr,
.name = "khugepaged",
};
#endif /* CONFIG_SYSFS */
int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
{
switch (advice) {
case MADV_HUGEPAGE:
#ifdef CONFIG_S390
/*
* qemu blindly sets MADV_HUGEPAGE on all allocations, but s390
* can't handle this properly after s390_enable_sie, so we simply
* ignore the madvise to prevent qemu from causing a SIGSEGV.
*/
if (mm_has_pgste(vma->vm_mm))
return 0;
#endif
*vm_flags &= ~VM_NOHUGEPAGE;
*vm_flags |= VM_HUGEPAGE;
/*
* If the vma become good for khugepaged to scan,
* register it here without waiting a page fault that
* may not happen any time soon.
*/
khugepaged_enter_vma(vma, *vm_flags);
break;
case MADV_NOHUGEPAGE:
*vm_flags &= ~VM_HUGEPAGE;
*vm_flags |= VM_NOHUGEPAGE;
/*
* Setting VM_NOHUGEPAGE will prevent khugepaged from scanning
* this vma even if we leave the mm registered in khugepaged if
* it got registered before VM_NOHUGEPAGE was set.
*/
break;
}
return 0;
}
int __init khugepaged_init(void)
{
mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0);
if (!mm_slot_cache)
return -ENOMEM;
khugepaged_pages_to_scan = HPAGE_PMD_NR * 8;
khugepaged_max_ptes_none = HPAGE_PMD_NR - 1;
khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8;
khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2;
return 0;
}
void __init khugepaged_destroy(void)
{
kmem_cache_destroy(mm_slot_cache);
}
static inline int hpage_collapse_test_exit(struct mm_struct *mm)
{
return atomic_read(&mm->mm_users) == 0;
}
static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
{
return hpage_collapse_test_exit(mm) ||
test_bit(MMF_DISABLE_THP, &mm->flags);
}
static bool hugepage_pmd_enabled(void)
{
/*
* We cover the anon, shmem and the file-backed case here; file-backed
* hugepages, when configured in, are determined by the global control.
* Anon pmd-sized hugepages are determined by the pmd-size control.
* Shmem pmd-sized hugepages are also determined by its pmd-size control,
* except when the global shmem_huge is set to SHMEM_HUGE_DENY.
*/
if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
hugepage_global_enabled())
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_always))
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
hugepage_global_enabled())
return true;
if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled())
return true;
return false;
}
void __khugepaged_enter(struct mm_struct *mm)
{
struct khugepaged_mm_slot *mm_slot;
struct mm_slot *slot;
int wakeup;
/* __khugepaged_exit() must not run from under us */
VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags)))
return;
mm_slot = mm_slot_alloc(mm_slot_cache);
if (!mm_slot)
return;
slot = &mm_slot->slot;
spin_lock(&khugepaged_mm_lock);
mm_slot_insert(mm_slots_hash, mm, slot);
/*
* Insert just behind the scanning cursor, to let the area settle
* down a little.
*/
wakeup = list_empty(&khugepaged_scan.mm_head);
list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head);
spin_unlock(&khugepaged_mm_lock);
mmgrab(mm);
if (wakeup)
wake_up_interruptible(&khugepaged_wait);
}
void khugepaged_enter_vma(struct vm_area_struct *vma,
unsigned long vm_flags)
{ if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS,
PMD_ORDER))
__khugepaged_enter(vma->vm_mm);
}
}
void __khugepaged_exit(struct mm_struct *mm)
{
struct khugepaged_mm_slot *mm_slot;
struct mm_slot *slot;
int free = 0;
spin_lock(&khugepaged_mm_lock);
slot = mm_slot_lookup(mm_slots_hash, mm);
mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot);
if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
hash_del(&slot->hash);
list_del(&slot->mm_node);
free = 1;
}
spin_unlock(&khugepaged_mm_lock);
if (free) {
clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
mm_slot_free(mm_slot_cache, mm_slot);
mmdrop(mm);
} else if (mm_slot) {
/*
* This is required to serialize against
* hpage_collapse_test_exit() (which is guaranteed to run
* under mmap sem read mode). Stop here (after we return all
* pagetables will be destroyed) until khugepaged has finished
* working on the pagetables under the mmap_lock.
*/
mmap_write_lock(mm);
mmap_write_unlock(mm);
}
}
static void release_pte_folio(struct folio *folio)
{
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
-folio_nr_pages(folio));
folio_unlock(folio);
folio_putback_lru(folio);
}
static void release_pte_pages(pte_t *pte, pte_t *_pte,
struct list_head *compound_pagelist)
{
struct folio *folio, *tmp;
while (--_pte >= pte) {
pte_t pteval = ptep_get(_pte);
unsigned long pfn;
if (pte_none(pteval))
continue;
pfn = pte_pfn(pteval);
if (is_zero_pfn(pfn))
continue;
folio = pfn_folio(pfn);
if (folio_test_large(folio))
continue;
release_pte_folio(folio);
}
list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) {
list_del(&folio->lru);
release_pte_folio(folio);
}
}
static bool is_refcount_suitable(struct folio *folio)
{
int expected_refcount = folio_mapcount(folio);
if (!folio_test_anon(folio) || folio_test_swapcache(folio))
expected_refcount += folio_nr_pages(folio);
if (folio_test_private(folio))
expected_refcount++;
return folio_ref_count(folio) == expected_refcount;
}
static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
unsigned long address,
pte_t *pte,
struct collapse_control *cc,
struct list_head *compound_pagelist)
{
struct page *page = NULL;
struct folio *folio = NULL;
pte_t *_pte;
int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
bool writable = false;
for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
pte_t pteval = ptep_get(_pte);
if (pte_none(pteval) || (pte_present(pteval) &&
is_zero_pfn(pte_pfn(pteval)))) {
++none_or_zero;
if (!userfaultfd_armed(vma) &&
(!cc->is_khugepaged ||
none_or_zero <= khugepaged_max_ptes_none)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
goto out;
}
}
if (!pte_present(pteval)) {
result = SCAN_PTE_NON_PRESENT;
goto out;
}
if (pte_uffd_wp(pteval)) {
result = SCAN_PTE_UFFD_WP;
goto out;
}
page = vm_normal_page(vma, address, pteval);
if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
result = SCAN_PAGE_NULL;
goto out;
}
folio = page_folio(page);
VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
/* See hpage_collapse_scan_pmd(). */
if (folio_maybe_mapped_shared(folio)) {
++shared;
if (cc->is_khugepaged &&
shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out;
}
}
if (folio_test_large(folio)) {
struct folio *f;
/*
* Check if we have dealt with the compound page
* already
*/
list_for_each_entry(f, compound_pagelist, lru) {
if (folio == f)
goto next;
}
}
/*
* We can do it before folio_isolate_lru because the
* folio can't be freed from under us. NOTE: PG_lock
* is needed to serialize against split_huge_page
* when invoked from the VM.
*/
if (!folio_trylock(folio)) {
result = SCAN_PAGE_LOCK;
goto out;
}
/*
* Check if the page has any GUP (or other external) pins.
*
* The page table that maps the page has been already unlinked
* from the page table tree and this process cannot get
* an additional pin on the page.
*
* New pins can come later if the page is shared across fork,
* but not from this process. The other process cannot write to
* the page, only trigger CoW.
*/
if (!is_refcount_suitable(folio)) {
folio_unlock(folio);
result = SCAN_PAGE_COUNT;
goto out;
}
/*
* Isolate the page to avoid collapsing an hugepage
* currently in use by the VM.
*/
if (!folio_isolate_lru(folio)) {
folio_unlock(folio);
result = SCAN_DEL_PAGE_LRU;
goto out;
}
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
if (folio_test_large(folio))
list_add_tail(&folio->lru, compound_pagelist);
next:
/*
* If collapse was initiated by khugepaged, check that there is
* enough young pte to justify collapsing the page
*/
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
address)))
referenced++;
if (pte_write(pteval))
writable = true;
}
if (unlikely(!writable)) {
result = SCAN_PAGE_RO;
} else if (unlikely(cc->is_khugepaged && !referenced)) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
referenced, writable, result);
return result;
}
out:
release_pte_pages(pte, _pte, compound_pagelist);
trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
referenced, writable, result);
return result;
}
static void __collapse_huge_page_copy_succeeded(pte_t *pte,
struct vm_area_struct *vma,
unsigned long address,
spinlock_t *ptl,
struct list_head *compound_pagelist)
{
struct folio *src, *tmp;
pte_t *_pte;
pte_t pteval;
for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
pteval = ptep_get(_pte);
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
if (is_zero_pfn(pte_pfn(pteval))) {
/*
* ptl mostly unnecessary.
*/
spin_lock(ptl);
ptep_clear(vma->vm_mm, address, _pte);
spin_unlock(ptl);
ksm_might_unmap_zero_page(vma->vm_mm, pteval);
}
} else {
struct page *src_page = pte_page(pteval);
src = page_folio(src_page);
if (!folio_test_large(src))
release_pte_folio(src);
/*
* ptl mostly unnecessary, but preempt has to
* be disabled to update the per-cpu stats
* inside folio_remove_rmap_pte().
*/
spin_lock(ptl);
ptep_clear(vma->vm_mm, address, _pte);
folio_remove_rmap_pte(src, src_page, vma);
spin_unlock(ptl);
free_page_and_swap_cache(src_page);
}
}
list_for_each_entry_safe(src, tmp, compound_pagelist, lru) {
list_del(&src->lru);
node_stat_sub_folio(src, NR_ISOLATED_ANON +
folio_is_file_lru(src));
folio_unlock(src);
free_swap_cache(src);
folio_putback_lru(src);
}
}
static void __collapse_huge_page_copy_failed(pte_t *pte,
pmd_t *pmd,
pmd_t orig_pmd,
struct vm_area_struct *vma,
struct list_head *compound_pagelist)
{
spinlock_t *pmd_ptl;
/*
* Re-establish the PMD to point to the original page table
* entry. Restoring PMD needs to be done prior to releasing
* pages. Since pages are still isolated and locked here,
* acquiring anon_vma_lock_write is unnecessary.
*/
pmd_ptl = pmd_lock(vma->vm_mm, pmd);
pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd));
spin_unlock(pmd_ptl);
/*
* Release both raw and compound pages isolated
* in __collapse_huge_page_isolate.
*/
release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist);
}
/*
* __collapse_huge_page_copy - attempts to copy memory contents from raw
* pages to a hugepage. Cleans up the raw pages if copying succeeds;
* otherwise restores the original page table and releases isolated raw pages.
* Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC.
*
* @pte: starting of the PTEs to copy from
* @folio: the new hugepage to copy contents to
* @pmd: pointer to the new hugepage's PMD
* @orig_pmd: the original raw pages' PMD
* @vma: the original raw pages' virtual memory area
* @address: starting address to copy
* @ptl: lock on raw pages' PTEs
* @compound_pagelist: list that stores compound pages
*/
static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma,
unsigned long address, spinlock_t *ptl,
struct list_head *compound_pagelist)
{
unsigned int i;
int result = SCAN_SUCCEED;
/*
* Copying pages' contents is subject to memory poison at any iteration.
*/
for (i = 0; i < HPAGE_PMD_NR; i++) {
pte_t pteval = ptep_get(pte + i);
struct page *page = folio_page(folio, i);
unsigned long src_addr = address + i * PAGE_SIZE;
struct page *src_page;
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
clear_user_highpage(page, src_addr);
continue;
}
src_page = pte_page(pteval);
if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) {
result = SCAN_COPY_MC;
break;
}
}
if (likely(result == SCAN_SUCCEED))
__collapse_huge_page_copy_succeeded(pte, vma, address, ptl,
compound_pagelist);
else
__collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma,
compound_pagelist);
return result;
}
static void khugepaged_alloc_sleep(void)
{
DEFINE_WAIT(wait);
add_wait_queue(&khugepaged_wait, &wait);
__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
remove_wait_queue(&khugepaged_wait, &wait);
}
struct collapse_control khugepaged_collapse_control = {
.is_khugepaged = true,
};
static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc)
{
int i;
/*
* If node_reclaim_mode is disabled, then no extra effort is made to
* allocate memory locally.
*/
if (!node_reclaim_enabled())
return false;
/* If there is a count for this node already, it must be acceptable */
if (cc->node_load[nid])
return false;
for (i = 0; i < MAX_NUMNODES; i++) {
if (!cc->node_load[i])
continue;
if (node_distance(nid, i) > node_reclaim_distance)
return true;
}
return false;
}
#define khugepaged_defrag() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG))
/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */
static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
{
return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT;
}
#ifdef CONFIG_NUMA
static int hpage_collapse_find_target_node(struct collapse_control *cc)
{
int nid, target_node = 0, max_value = 0;
/* find first node with max normal pages hit */
for (nid = 0; nid < MAX_NUMNODES; nid++)
if (cc->node_load[nid] > max_value) {
max_value = cc->node_load[nid];
target_node = nid;
}
for_each_online_node(nid) {
if (max_value == cc->node_load[nid])
node_set(nid, cc->alloc_nmask);
}
return target_node;
}
#else
static int hpage_collapse_find_target_node(struct collapse_control *cc)
{
return 0;
}
#endif
/*
* If mmap_lock temporarily dropped, revalidate vma
* before taking mmap_lock.
* Returns enum scan_result value.
*/
static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
bool expect_anon,
struct vm_area_struct **vmap,
struct collapse_control *cc)
{
struct vm_area_struct *vma;
unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0;
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
return SCAN_ANY_PROCESS;
*vmap = vma = find_vma(mm, address);
if (!vma)
return SCAN_VMA_NULL;
if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
return SCAN_ADDRESS_RANGE;
if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER))
return SCAN_VMA_CHECK;
/*
* Anon VMA expected, the address may be unmapped then
* remapped to file after khugepaged reaquired the mmap_lock.
*
* thp_vma_allowable_order may return true for qualified file
* vmas.
*/
if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
return SCAN_PAGE_ANON;
return SCAN_SUCCEED;
}
static inline int check_pmd_state(pmd_t *pmd)
{
pmd_t pmde = pmdp_get_lockless(pmd);
if (pmd_none(pmde))
return SCAN_PMD_NONE;
if (!pmd_present(pmde))
return SCAN_PMD_NULL;
if (pmd_trans_huge(pmde))
return SCAN_PMD_MAPPED;
if (pmd_devmap(pmde))
return SCAN_PMD_NULL;
if (pmd_bad(pmde))
return SCAN_PMD_NULL;
return SCAN_SUCCEED;
}
static int find_pmd_or_thp_or_none(struct mm_struct *mm,
unsigned long address,
pmd_t **pmd)
{
*pmd = mm_find_pmd(mm, address);
if (!*pmd)
return SCAN_PMD_NULL;
return check_pmd_state(*pmd);
}
static int check_pmd_still_valid(struct mm_struct *mm,
unsigned long address,
pmd_t *pmd)
{
pmd_t *new_pmd;
int result = find_pmd_or_thp_or_none(mm, address, &new_pmd);
if (result != SCAN_SUCCEED)
return result;
if (new_pmd != pmd)
return SCAN_FAIL;
return SCAN_SUCCEED;
}
/*
* Bring missing pages in from swap, to complete THP collapse.
* Only done if hpage_collapse_scan_pmd believes it is worthwhile.
*
* Called and returns without pte mapped or spinlocks held.
* Returns result: if not SCAN_SUCCEED, mmap_lock has been released.
*/
static int __collapse_huge_page_swapin(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd,
int referenced)
{
int swapped_in = 0;
vm_fault_t ret = 0;
unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
int result;
pte_t *pte = NULL;
spinlock_t *ptl;
for (address = haddr; address < end; address += PAGE_SIZE) {
struct vm_fault vmf = {
.vma = vma,
.address = address,
.pgoff = linear_page_index(vma, address),
.flags = FAULT_FLAG_ALLOW_RETRY,
.pmd = pmd,
};
if (!pte++) {
/*
* Here the ptl is only used to check pte_same() in
* do_swap_page(), so readonly version is enough.
*/
pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl);
if (!pte) {
mmap_read_unlock(mm);
result = SCAN_PMD_NULL;
goto out;
}
}
vmf.orig_pte = ptep_get_lockless(pte);
if (!is_swap_pte(vmf.orig_pte))
continue;
vmf.pte = pte;
vmf.ptl = ptl;
ret = do_swap_page(&vmf);
/* Which unmaps pte (after perhaps re-checking the entry) */
pte = NULL;
/*
* do_swap_page returns VM_FAULT_RETRY with released mmap_lock.
* Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because
* we do not retry here and swap entry will remain in pagetable
* resulting in later failure.
*/
if (ret & VM_FAULT_RETRY) {
/* Likely, but not guaranteed, that page lock failed */
result = SCAN_PAGE_LOCK;
goto out;
}
if (ret & VM_FAULT_ERROR) {
mmap_read_unlock(mm);
result = SCAN_FAIL;
goto out;
}
swapped_in++;
}
if (pte)
pte_unmap(pte);
/* Drain LRU cache to remove extra pin on the swapped in pages */
if (swapped_in)
lru_add_drain();
result = SCAN_SUCCEED;
out:
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result);
return result;
}
static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm,
struct collapse_control *cc)
{
gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() :
GFP_TRANSHUGE);
int node = hpage_collapse_find_target_node(cc);
struct folio *folio;
folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask);
if (!folio) {
*foliop = NULL;
count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
return SCAN_ALLOC_HUGE_PAGE_FAIL;
}
count_vm_event(THP_COLLAPSE_ALLOC);
if (unlikely(mem_cgroup_charge(folio, mm, gfp))) {
folio_put(folio);
*foliop = NULL;
return SCAN_CGROUP_CHARGE_FAIL;
}
count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1);
*foliop = folio;
return SCAN_SUCCEED;
}
static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
int referenced, int unmapped,
struct collapse_control *cc)
{
LIST_HEAD(compound_pagelist);
pmd_t *pmd, _pmd;
pte_t *pte;
pgtable_t pgtable;
struct folio *folio;
spinlock_t *pmd_ptl, *pte_ptl;
int result = SCAN_FAIL;
struct vm_area_struct *vma;
struct mmu_notifier_range range;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
/*
* Before allocating the hugepage, release the mmap_lock read lock.
* The allocation can take potentially a long time if it involves
* sync compaction, and we do not need to hold the mmap_lock during
* that. We will recheck the vma after taking it again in write mode.
*/
mmap_read_unlock(mm);
result = alloc_charge_folio(&folio, mm, cc);
if (result != SCAN_SUCCEED)
goto out_nolock;
mmap_read_lock(mm);
result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
if (result != SCAN_SUCCEED) {
mmap_read_unlock(mm);
goto out_nolock;
}
result = find_pmd_or_thp_or_none(mm, address, &pmd);
if (result != SCAN_SUCCEED) {
mmap_read_unlock(mm);
goto out_nolock;
}
if (unmapped) {
/*
* __collapse_huge_page_swapin will return with mmap_lock
* released when it fails. So we jump out_nolock directly in
* that case. Continuing to collapse causes inconsistency.
*/
result = __collapse_huge_page_swapin(mm, vma, address, pmd,
referenced);
if (result != SCAN_SUCCEED)
goto out_nolock;
}
mmap_read_unlock(mm);
/*
* Prevent all access to pagetables with the exception of
* gup_fast later handled by the ptep_clear_flush and the VM
* handled by the anon_vma lock + PG_lock.
*
* UFFDIO_MOVE is prevented to race as well thanks to the
* mmap_lock.
*/
mmap_write_lock(mm);
result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
if (result != SCAN_SUCCEED)
goto out_up_write;
/* check if the pmd is still valid */
result = check_pmd_still_valid(mm, address, pmd);
if (result != SCAN_SUCCEED)
goto out_up_write;
vma_start_write(vma);
anon_vma_lock_write(vma->anon_vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,
address + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
/*
* This removes any huge TLB entry from the CPU so we won't allow
* huge and small TLB entries for the same virtual address to
* avoid the risk of CPU bugs in that area.
*
* Parallel GUP-fast is fine since GUP-fast will back off when
* it detects PMD is changed.
*/
_pmd = pmdp_collapse_flush(vma, address, pmd);
spin_unlock(pmd_ptl);
mmu_notifier_invalidate_range_end(&range);
tlb_remove_table_sync_one();
pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
if (pte) {
result = __collapse_huge_page_isolate(vma, address, pte, cc,
&compound_pagelist);
spin_unlock(pte_ptl);
} else {
result = SCAN_PMD_NULL;
}
if (unlikely(result != SCAN_SUCCEED)) {
if (pte)
pte_unmap(pte);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
/*
* We can only use set_pmd_at when establishing
* hugepmds and never for establishing regular pmds that
* points to regular pagetables. Use pmd_populate for that
*/
pmd_populate(mm, pmd, pmd_pgtable(_pmd));
spin_unlock(pmd_ptl);
anon_vma_unlock_write(vma->anon_vma);
goto out_up_write;
}
/*
* All pages are isolated and locked so anon_vma rmap
* can't run anymore.
*/
anon_vma_unlock_write(vma->anon_vma);
result = __collapse_huge_page_copy(pte, folio, pmd, _pmd,
vma, address, pte_ptl,
&compound_pagelist);
pte_unmap(pte);
if (unlikely(result != SCAN_SUCCEED))
goto out_up_write;
/*
* The smp_wmb() inside __folio_mark_uptodate() ensures the
* copy_huge_page writes become visible before the set_pmd_at()
* write.
*/
__folio_mark_uptodate(folio);
pgtable = pmd_pgtable(_pmd);
_pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot);
_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache_pmd(vma, address, pmd);
deferred_split_folio(folio, false);
spin_unlock(pmd_ptl);
folio = NULL;
result = SCAN_SUCCEED;
out_up_write:
mmap_write_unlock(mm);
out_nolock:
if (folio)
folio_put(folio);
trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result);
return result;
}
static int hpage_collapse_scan_pmd(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address, bool *mmap_locked,
struct collapse_control *cc)
{
pmd_t *pmd;
pte_t *pte, *_pte;
int result = SCAN_FAIL, referenced = 0;
int none_or_zero = 0, shared = 0;
struct page *page = NULL;
struct folio *folio = NULL;
unsigned long _address;
spinlock_t *ptl;
int node = NUMA_NO_NODE, unmapped = 0;
bool writable = false;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
result = find_pmd_or_thp_or_none(mm, address, &pmd);
if (result != SCAN_SUCCEED)
goto out;
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte) {
result = SCAN_PMD_NULL;
goto out;
}
for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, _address += PAGE_SIZE) {
pte_t pteval = ptep_get(_pte);
if (is_swap_pte(pteval)) {
++unmapped;
if (!cc->is_khugepaged ||
unmapped <= khugepaged_max_ptes_swap) {
/*
* Always be strict with uffd-wp
* enabled swap entries. Please see
* comment below for pte_uffd_wp().
*/
if (pte_swp_uffd_wp_any(pteval)) {
result = SCAN_PTE_UFFD_WP;
goto out_unmap;
}
continue;
} else {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
goto out_unmap;
}
}
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
++none_or_zero;
if (!userfaultfd_armed(vma) &&
(!cc->is_khugepaged ||
none_or_zero <= khugepaged_max_ptes_none)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
goto out_unmap;
}
}
if (pte_uffd_wp(pteval)) {
/*
* Don't collapse the page if any of the small
* PTEs are armed with uffd write protection.
* Here we can also mark the new huge pmd as
* write protected if any of the small ones is
* marked but that could bring unknown
* userfault messages that falls outside of
* the registered range. So, just be simple.
*/
result = SCAN_PTE_UFFD_WP;
goto out_unmap;
}
if (pte_write(pteval))
writable = true;
page = vm_normal_page(vma, _address, pteval);
if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
result = SCAN_PAGE_NULL;
goto out_unmap;
}
folio = page_folio(page);
if (!folio_test_anon(folio)) {
result = SCAN_PAGE_ANON;
goto out_unmap;
}
/*
* We treat a single page as shared if any part of the THP
* is shared.
*/
if (folio_maybe_mapped_shared(folio)) {
++shared;
if (cc->is_khugepaged &&
shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out_unmap;
}
}
/*
* Record which node the original page is from and save this
* information to cc->node_load[].
* Khugepaged will allocate hugepage from the node has the max
* hit record.
*/
node = folio_nid(folio);
if (hpage_collapse_scan_abort(node, cc)) {
result = SCAN_SCAN_ABORT;
goto out_unmap;
}
cc->node_load[node]++;
if (!folio_test_lru(folio)) {
result = SCAN_PAGE_LRU;
goto out_unmap;
}
if (folio_test_locked(folio)) {
result = SCAN_PAGE_LOCK;
goto out_unmap;
}
/*
* Check if the page has any GUP (or other external) pins.
*
* Here the check may be racy:
* it may see folio_mapcount() > folio_ref_count().
* But such case is ephemeral we could always retry collapse
* later. However it may report false positive if the page
* has excessive GUP pins (i.e. 512). Anyway the same check
* will be done again later the risk seems low.
*/
if (!is_refcount_suitable(folio)) {
result = SCAN_PAGE_COUNT;
goto out_unmap;
}
/*
* If collapse was initiated by khugepaged, check that there is
* enough young pte to justify collapsing the page
*/
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
address)))
referenced++;
}
if (!writable) {
result = SCAN_PAGE_RO;
} else if (cc->is_khugepaged &&
(!referenced ||
(unmapped && referenced < HPAGE_PMD_NR / 2))) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
}
out_unmap:
pte_unmap_unlock(pte, ptl);
if (result == SCAN_SUCCEED) {
result = collapse_huge_page(mm, address, referenced,
unmapped, cc);
/* collapse_huge_page will return with the mmap_lock released */
*mmap_locked = false;
}
out:
trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced,
none_or_zero, result, unmapped);
return result;
}
static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot)
{
struct mm_slot *slot = &mm_slot->slot;
struct mm_struct *mm = slot->mm;
lockdep_assert_held(&khugepaged_mm_lock);
if (hpage_collapse_test_exit(mm)) {
/* free mm_slot */
hash_del(&slot->hash);
list_del(&slot->mm_node);
/*
* Not strictly needed because the mm exited already.
*
* clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
*/
/* khugepaged_mm_lock actually not necessary for the below */
mm_slot_free(mm_slot_cache, mm_slot);
mmdrop(mm);
}
}
#ifdef CONFIG_SHMEM
/* hpage must be locked, and mmap_lock must be held */
static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmdp, struct page *hpage)
{
struct vm_fault vmf = {
.vma = vma,
.address = addr,
.flags = 0,
.pmd = pmdp,
};
VM_BUG_ON(!PageTransHuge(hpage));
mmap_assert_locked(vma->vm_mm);
if (do_set_pmd(&vmf, hpage))
return SCAN_FAIL;
get_page(hpage);
return SCAN_SUCCEED;
}
/**
* collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at
* address haddr.
*
* @mm: process address space where collapse happens
* @addr: THP collapse address
* @install_pmd: If a huge PMD should be installed
*
* This function checks whether all the PTEs in the PMD are pointing to the
* right THP. If so, retract the page table so the THP can refault in with
* as pmd-mapped. Possibly install a huge PMD mapping the THP.
*/
int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
bool install_pmd)
{
struct mmu_notifier_range range;
bool notified = false;
unsigned long haddr = addr & HPAGE_PMD_MASK;
struct vm_area_struct *vma = vma_lookup(mm, haddr);
struct folio *folio;
pte_t *start_pte, *pte;
pmd_t *pmd, pgt_pmd;
spinlock_t *pml = NULL, *ptl;
int nr_ptes = 0, result = SCAN_FAIL;
int i;
mmap_assert_locked(mm);
/* First check VMA found, in case page tables are being torn down */
if (!vma || !vma->vm_file ||
!range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE))
return SCAN_VMA_CHECK;
/* Fast check before locking page if already PMD-mapped */
result = find_pmd_or_thp_or_none(mm, haddr, &pmd);
if (result == SCAN_PMD_MAPPED)
return result;
/*
* If we are here, we've succeeded in replacing all the native pages
* in the page cache with a single hugepage. If a mm were to fault-in
* this memory (mapped by a suitably aligned VMA), we'd get the hugepage
* and map it by a PMD, regardless of sysfs THP settings. As such, let's
* analogously elide sysfs THP settings here.
*/
if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER))
return SCAN_VMA_CHECK;
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
folio = filemap_lock_folio(vma->vm_file->f_mapping,
linear_page_index(vma, haddr));
if (IS_ERR(folio))
return SCAN_PAGE_NULL;
if (folio_order(folio) != HPAGE_PMD_ORDER) {
result = SCAN_PAGE_COMPOUND;
goto drop_folio;
}
result = find_pmd_or_thp_or_none(mm, haddr, &pmd);
switch (result) {
case SCAN_SUCCEED:
break;
case SCAN_PMD_NONE:
/*
* All pte entries have been removed and pmd cleared.
* Skip all the pte checks and just update the pmd mapping.
*/
goto maybe_install_pmd;
default:
goto drop_folio;
}
result = SCAN_FAIL;
start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
if (!start_pte) /* mmap_lock + page lock should prevent this */
goto drop_folio;
/* step 1: check all mapped PTEs are to the right huge page */
for (i = 0, addr = haddr, pte = start_pte;
i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
struct page *page;
pte_t ptent = ptep_get(pte);
/* empty pte, skip */
if (pte_none(ptent))
continue;
/* page swapped out, abort */
if (!pte_present(ptent)) {
result = SCAN_PTE_NON_PRESENT;
goto abort;
}
page = vm_normal_page(vma, addr, ptent);
if (WARN_ON_ONCE(page && is_zone_device_page(page)))
page = NULL;
/*
* Note that uprobe, debugger, or MAP_PRIVATE may change the
* page table, but the new page will not be a subpage of hpage.
*/
if (folio_page(folio, i) != page)
goto abort;
}
pte_unmap_unlock(start_pte, ptl);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
haddr, haddr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
notified = true;
/*
* pmd_lock covers a wider range than ptl, and (if split from mm's
* page_table_lock) ptl nests inside pml. The less time we hold pml,
* the better; but userfaultfd's mfill_atomic_pte() on a private VMA
* inserts a valid as-if-COWed PTE without even looking up page cache.
* So page lock of folio does not protect from it, so we must not drop
* ptl before pgt_pmd is removed, so uffd private needs pml taken now.
*/
if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED))
pml = pmd_lock(mm, pmd);
start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl);
if (!start_pte) /* mmap_lock + page lock should prevent this */
goto abort;
if (!pml)
spin_lock(ptl);
else if (ptl != pml)
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd))))
goto abort;
/* step 2: clear page table and adjust rmap */
for (i = 0, addr = haddr, pte = start_pte;
i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
struct page *page;
pte_t ptent = ptep_get(pte);
if (pte_none(ptent))
continue;
/*
* We dropped ptl after the first scan, to do the mmu_notifier:
* page lock stops more PTEs of the folio being faulted in, but
* does not stop write faults COWing anon copies from existing
* PTEs; and does not stop those being swapped out or migrated.
*/
if (!pte_present(ptent)) {
result = SCAN_PTE_NON_PRESENT;
goto abort;
}
page = vm_normal_page(vma, addr, ptent);
if (folio_page(folio, i) != page)
goto abort;
/*
* Must clear entry, or a racing truncate may re-remove it.
* TLB flush can be left until pmdp_collapse_flush() does it.
* PTE dirty? Shmem page is already dirty; file is read-only.
*/
ptep_clear(mm, addr, pte);
folio_remove_rmap_pte(folio, page, vma);
nr_ptes++;
}
if (!pml)
spin_unlock(ptl);
/* step 3: set proper refcount and mm_counters. */
if (nr_ptes) {
folio_ref_sub(folio, nr_ptes);
add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
}
/* step 4: remove empty page table */
if (!pml) {
pml = pmd_lock(mm, pmd);
if (ptl != pml) {
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) {
flush_tlb_mm(mm);
goto unlock;
}
}
}
pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd);
pmdp_get_lockless_sync();
pte_unmap_unlock(start_pte, ptl);
if (ptl != pml)
spin_unlock(pml);
mmu_notifier_invalidate_range_end(&range);
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, haddr, pgt_pmd);
pte_free_defer(mm, pmd_pgtable(pgt_pmd));
maybe_install_pmd:
/* step 5: install pmd entry */
result = install_pmd
? set_huge_pmd(vma, haddr, pmd, &folio->page)
: SCAN_SUCCEED;
goto drop_folio;
abort:
if (nr_ptes) {
flush_tlb_mm(mm);
folio_ref_sub(folio, nr_ptes);
add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
}
unlock:
if (start_pte)
pte_unmap_unlock(start_pte, ptl);
if (pml && pml != ptl)
spin_unlock(pml);
if (notified)
mmu_notifier_invalidate_range_end(&range);
drop_folio:
folio_unlock(folio);
folio_put(folio);
return result;
}
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
struct vm_area_struct *vma;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
struct mmu_notifier_range range;
struct mm_struct *mm;
unsigned long addr;
pmd_t *pmd, pgt_pmd;
spinlock_t *pml;
spinlock_t *ptl;
bool success = false;
/*
* Check vma->anon_vma to exclude MAP_PRIVATE mappings that
* got written to. These VMAs are likely not worth removing
* page tables from, as PMD-mapping is likely to be split later.
*/
if (READ_ONCE(vma->anon_vma))
continue;
addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
if (addr & ~HPAGE_PMD_MASK ||
vma->vm_end < addr + HPAGE_PMD_SIZE)
continue;
mm = vma->vm_mm;
if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED)
continue;
if (hpage_collapse_test_exit(mm))
continue;
/*
* When a vma is registered with uffd-wp, we cannot recycle
* the page table because there may be pte markers installed.
* Other vmas can still have the same file mapped hugely, but
* skip this one: it will always be mapped in small page size
* for uffd-wp registered ranges.
*/
if (userfaultfd_wp(vma))
continue;
/* PTEs were notified when unmapped; but now for the PMD? */
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
addr, addr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
pml = pmd_lock(mm, pmd);
/*
* The lock of new_folio is still held, we will be blocked in
* the page fault path, which prevents the pte entries from
* being set again. So even though the old empty PTE page may be
* concurrently freed and a new PTE page is filled into the pmd
* entry, it is still empty and can be removed.
*
* So here we only need to recheck if the state of pmd entry
* still meets our requirements, rather than checking pmd_same()
* like elsewhere.
*/
if (check_pmd_state(pmd) != SCAN_SUCCEED)
goto drop_pml;
ptl = pte_lockptr(mm, pmd);
if (ptl != pml)
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
/*
* Huge page lock is still held, so normally the page table
* must remain empty; and we have already skipped anon_vma
* and userfaultfd_wp() vmas. But since the mmap_lock is not
* held, it is still possible for a racing userfaultfd_ioctl()
* to have inserted ptes or markers. Now that we hold ptlock,
* repeating the anon_vma check protects from one category,
* and repeating the userfaultfd_wp() check from another.
*/
if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) {
pgt_pmd = pmdp_collapse_flush(vma, addr, pmd);
pmdp_get_lockless_sync();
success = true;
}
if (ptl != pml)
spin_unlock(ptl);
drop_pml:
spin_unlock(pml);
mmu_notifier_invalidate_range_end(&range);
if (success) {
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, addr, pgt_pmd);
pte_free_defer(mm, pmd_pgtable(pgt_pmd));
}
}
i_mmap_unlock_read(mapping);
}
/**
* collapse_file - collapse filemap/tmpfs/shmem pages into huge one.
*
* @mm: process address space where collapse happens
* @addr: virtual collapse start address
* @file: file that collapse on
* @start: collapse start address
* @cc: collapse context and scratchpad
*
* Basic scheme is simple, details are more complex:
* - allocate and lock a new huge page;
* - scan page cache, locking old pages
* + swap/gup in pages if necessary;
* - copy data to new page
* - handle shmem holes
* + re-validate that holes weren't filled by someone else
* + check for userfaultfd
* - finalize updates to the page cache;
* - if replacing succeeds:
* + unlock huge page;
* + free old pages;
* - if replacing failed;
* + unlock old pages
* + unlock and free huge page;
*/
static int collapse_file(struct mm_struct *mm, unsigned long addr,
struct file *file, pgoff_t start,
struct collapse_control *cc)
{
struct address_space *mapping = file->f_mapping;
struct page *dst;
struct folio *folio, *tmp, *new_folio;
pgoff_t index = 0, end = start + HPAGE_PMD_NR;
LIST_HEAD(pagelist);
XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
int nr_none = 0, result = SCAN_SUCCEED;
bool is_shmem = shmem_file(file);
VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
result = alloc_charge_folio(&new_folio, mm, cc);
if (result != SCAN_SUCCEED)
goto out;
mapping_set_update(&xas, mapping);
__folio_set_locked(new_folio);
if (is_shmem)
__folio_set_swapbacked(new_folio);
new_folio->index = start;
new_folio->mapping = mapping;
/*
* Ensure we have slots for all the pages in the range. This is
* almost certainly a no-op because most of the pages must be present
*/
do {
xas_lock_irq(&xas);
xas_create_range(&xas);
if (!xas_error(&xas))
break;
xas_unlock_irq(&xas);
if (!xas_nomem(&xas, GFP_KERNEL)) {
result = SCAN_FAIL;
goto rollback;
}
} while (1);
for (index = start; index < end;) {
xas_set(&xas, index);
folio = xas_load(&xas);
VM_BUG_ON(index != xas.xa_index);
if (is_shmem) {
if (!folio) {
/*
* Stop if extent has been truncated or
* hole-punched, and is now completely
* empty.
*/
if (index == start) {
if (!xas_next_entry(&xas, end - 1)) {
result = SCAN_TRUNCATED;
goto xa_locked;
}
}
nr_none++;
index++;
continue;
}
if (xa_is_value(folio) || !folio_test_uptodate(folio)) {
xas_unlock_irq(&xas);
/* swap in or instantiate fallocated page */
if (shmem_get_folio(mapping->host, index, 0,
&folio, SGP_NOALLOC)) {
result = SCAN_FAIL;
goto xa_unlocked;
}
/* drain lru cache to help folio_isolate_lru() */
lru_add_drain();
} else if (folio_trylock(folio)) {
folio_get(folio);
xas_unlock_irq(&xas);
} else {
result = SCAN_PAGE_LOCK;
goto xa_locked;
}
} else { /* !is_shmem */
if (!folio || xa_is_value(folio)) {
xas_unlock_irq(&xas);
page_cache_sync_readahead(mapping, &file->f_ra,
file, index,
end - index);
/* drain lru cache to help folio_isolate_lru() */
lru_add_drain();
folio = filemap_lock_folio(mapping, index);
if (IS_ERR(folio)) {
result = SCAN_FAIL;
goto xa_unlocked;
}
} else if (folio_test_dirty(folio)) {
/*
* khugepaged only works on read-only fd,
* so this page is dirty because it hasn't
* been flushed since first write. There
* won't be new dirty pages.
*
* Trigger async flush here and hope the
* writeback is done when khugepaged
* revisits this page.
*
* This is a one-off situation. We are not
* forcing writeback in loop.
*/
xas_unlock_irq(&xas);
filemap_flush(mapping);
result = SCAN_FAIL;
goto xa_unlocked;
} else if (folio_test_writeback(folio)) {
xas_unlock_irq(&xas);
result = SCAN_FAIL;
goto xa_unlocked;
} else if (folio_trylock(folio)) {
folio_get(folio);
xas_unlock_irq(&xas);
} else {
result = SCAN_PAGE_LOCK;
goto xa_locked;
}
}
/*
* The folio must be locked, so we can drop the i_pages lock
* without racing with truncate.
*/
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
/* make sure the folio is up to date */
if (unlikely(!folio_test_uptodate(folio))) {
result = SCAN_FAIL;
goto out_unlock;
}
/*
* If file was truncated then extended, or hole-punched, before
* we locked the first folio, then a THP might be there already.
* This will be discovered on the first iteration.
*/
if (folio_order(folio) == HPAGE_PMD_ORDER &&
folio->index == start) {
/* Maybe PMD-mapped */
result = SCAN_PTE_MAPPED_HUGEPAGE;
goto out_unlock;
}
if (folio_mapping(folio) != mapping) {
result = SCAN_TRUNCATED;
goto out_unlock;
}
if (!is_shmem && (folio_test_dirty(folio) ||
folio_test_writeback(folio))) {
/*
* khugepaged only works on read-only fd, so this
* folio is dirty because it hasn't been flushed
* since first write.
*/
result = SCAN_FAIL;
goto out_unlock;
}
if (!folio_isolate_lru(folio)) {
result = SCAN_DEL_PAGE_LRU;
goto out_unlock;
}
if (!filemap_release_folio(folio, GFP_KERNEL)) {
result = SCAN_PAGE_HAS_PRIVATE;
folio_putback_lru(folio);
goto out_unlock;
}
if (folio_mapped(folio))
try_to_unmap(folio,
TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH);
xas_lock_irq(&xas);
VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio);
/*
* We control 2 + nr_pages references to the folio:
* - we hold a pin on it;
* - nr_pages reference from page cache;
* - one from lru_isolate_folio;
* If those are the only references, then any new usage
* of the folio will have to fetch it from the page
* cache. That requires locking the folio to handle
* truncate, so any new usage will be blocked until we
* unlock folio after collapse/during rollback.
*/
if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) {
result = SCAN_PAGE_COUNT;
xas_unlock_irq(&xas);
folio_putback_lru(folio);
goto out_unlock;
}
/*
* Accumulate the folios that are being collapsed.
*/
list_add_tail(&folio->lru, &pagelist);
index += folio_nr_pages(folio);
continue;
out_unlock:
folio_unlock(folio);
folio_put(folio);
goto xa_unlocked;
}
if (!is_shmem) {
filemap_nr_thps_inc(mapping);
/*
* Paired with the fence in do_dentry_open() -> get_write_access()
* to ensure i_writecount is up to date and the update to nr_thps
* is visible. Ensures the page cache will be truncated if the
* file is opened writable.
*/
smp_mb();
if (inode_is_open_for_write(mapping->host)) {
result = SCAN_FAIL;
filemap_nr_thps_dec(mapping);
}
}
xa_locked:
xas_unlock_irq(&xas);
xa_unlocked:
/*
* If collapse is successful, flush must be done now before copying.
* If collapse is unsuccessful, does flush actually need to be done?
* Do it anyway, to clear the state.
*/
try_to_unmap_flush();
if (result == SCAN_SUCCEED && nr_none &&
!shmem_charge(mapping->host, nr_none))
result = SCAN_FAIL;
if (result != SCAN_SUCCEED) {
nr_none = 0;
goto rollback;
}
/*
* The old folios are locked, so they won't change anymore.
*/
index = start;
dst = folio_page(new_folio, 0);
list_for_each_entry(folio, &pagelist, lru) {
int i, nr_pages = folio_nr_pages(folio);
while (index < folio->index) {
clear_highpage(dst);
index++;
dst++;
}
for (i = 0; i < nr_pages; i++) {
if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) {
result = SCAN_COPY_MC;
goto rollback;
}
index++;
dst++;
}
}
while (index < end) {
clear_highpage(dst);
index++;
dst++;
}
if (nr_none) {
struct vm_area_struct *vma;
int nr_none_check = 0;
i_mmap_lock_read(mapping);
xas_lock_irq(&xas);
xas_set(&xas, start);
for (index = start; index < end; index++) {
if (!xas_next(&xas)) {
xas_store(&xas, XA_RETRY_ENTRY);
if (xas_error(&xas)) {
result = SCAN_STORE_FAILED;
goto immap_locked;
}
nr_none_check++;
}
}
if (nr_none != nr_none_check) {
result = SCAN_PAGE_FILLED;
goto immap_locked;
}
/*
* If userspace observed a missing page in a VMA with
* a MODE_MISSING userfaultfd, then it might expect a
* UFFD_EVENT_PAGEFAULT for that page. If so, we need to
* roll back to avoid suppressing such an event. Since
* wp/minor userfaultfds don't give userspace any
* guarantees that the kernel doesn't fill a missing
* page with a zero page, so they don't matter here.
*
* Any userfaultfds registered after this point will
* not be able to observe any missing pages due to the
* previously inserted retry entries.
*/
vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) {
if (userfaultfd_missing(vma)) {
result = SCAN_EXCEED_NONE_PTE;
goto immap_locked;
}
}
immap_locked:
i_mmap_unlock_read(mapping);
if (result != SCAN_SUCCEED) {
xas_set(&xas, start);
for (index = start; index < end; index++) {
if (xas_next(&xas) == XA_RETRY_ENTRY)
xas_store(&xas, NULL);
}
xas_unlock_irq(&xas);
goto rollback;
}
} else {
xas_lock_irq(&xas);
}
if (is_shmem)
__lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR);
else
__lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR);
if (nr_none) {
__lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none);
/* nr_none is always 0 for non-shmem. */
__lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none);
}
/*
* Mark new_folio as uptodate before inserting it into the
* page cache so that it isn't mistaken for an fallocated but
* unwritten page.
*/
folio_mark_uptodate(new_folio);
folio_ref_add(new_folio, HPAGE_PMD_NR - 1);
if (is_shmem)
folio_mark_dirty(new_folio);
folio_add_lru(new_folio);
/* Join all the small entries into a single multi-index entry. */
xas_set_order(&xas, start, HPAGE_PMD_ORDER);
xas_store(&xas, new_folio);
WARN_ON_ONCE(xas_error(&xas));
xas_unlock_irq(&xas);
/*
* Remove pte page tables, so we can re-fault the page as huge.
* If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp().
*/
retract_page_tables(mapping, start);
if (cc && !cc->is_khugepaged)
result = SCAN_PTE_MAPPED_HUGEPAGE;
folio_unlock(new_folio);
/*
* The collapse has succeeded, so free the old folios.
*/
list_for_each_entry_safe(folio, tmp, &pagelist, lru) {
list_del(&folio->lru);
folio->mapping = NULL;
folio_clear_active(folio);
folio_clear_unevictable(folio);
folio_unlock(folio);
folio_put_refs(folio, 2 + folio_nr_pages(folio));
}
goto out;
rollback:
/* Something went wrong: roll back page cache changes */
if (nr_none) {
xas_lock_irq(&xas);
mapping->nrpages -= nr_none;
xas_unlock_irq(&xas);
shmem_uncharge(mapping->host, nr_none);
}
list_for_each_entry_safe(folio, tmp, &pagelist, lru) {
list_del(&folio->lru);
folio_unlock(folio);
folio_putback_lru(folio);
folio_put(folio);
}
/*
* Undo the updates of filemap_nr_thps_inc for non-SHMEM
* file only. This undo is not needed unless failure is
* due to SCAN_COPY_MC.
*/
if (!is_shmem && result == SCAN_COPY_MC) {
filemap_nr_thps_dec(mapping);
/*
* Paired with the fence in do_dentry_open() -> get_write_access()
* to ensure the update to nr_thps is visible.
*/
smp_mb();
}
new_folio->mapping = NULL;
folio_unlock(new_folio);
folio_put(new_folio);
out:
VM_BUG_ON(!list_empty(&pagelist));
trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result);
return result;
}
static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
struct file *file, pgoff_t start,
struct collapse_control *cc)
{
struct folio *folio = NULL;
struct address_space *mapping = file->f_mapping;
XA_STATE(xas, &mapping->i_pages, start);
int present, swap;
int node = NUMA_NO_NODE;
int result = SCAN_SUCCEED;
present = 0;
swap = 0;
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
rcu_read_lock();
xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) {
if (xas_retry(&xas, folio))
continue;
if (xa_is_value(folio)) {
swap += 1 << xas_get_order(&xas);
if (cc->is_khugepaged &&
swap > khugepaged_max_ptes_swap) {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
break;
}
continue;
}
if (folio_order(folio) == HPAGE_PMD_ORDER &&
folio->index == start) {
/* Maybe PMD-mapped */
result = SCAN_PTE_MAPPED_HUGEPAGE;
/*
* For SCAN_PTE_MAPPED_HUGEPAGE, further processing
* by the caller won't touch the page cache, and so
* it's safe to skip LRU and refcount checks before
* returning.
*/
break;
}
node = folio_nid(folio);
if (hpage_collapse_scan_abort(node, cc)) {
result = SCAN_SCAN_ABORT;
break;
}
cc->node_load[node]++;
if (!folio_test_lru(folio)) {
result = SCAN_PAGE_LRU;
break;
}
if (!is_refcount_suitable(folio)) {
result = SCAN_PAGE_COUNT;
break;
}
/*
* We probably should check if the folio is referenced
* here, but nobody would transfer pte_young() to
* folio_test_referenced() for us. And rmap walk here
* is just too costly...
*/
present += folio_nr_pages(folio);
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
if (result == SCAN_SUCCEED) {
if (cc->is_khugepaged &&
present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
} else {
result = collapse_file(mm, addr, file, start, cc);
}
}
trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result);
return result;
}
#else
static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
struct file *file, pgoff_t start,
struct collapse_control *cc)
{
BUILD_BUG();
}
#endif
static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
struct collapse_control *cc)
__releases(&khugepaged_mm_lock)
__acquires(&khugepaged_mm_lock)
{
struct vma_iterator vmi;
struct khugepaged_mm_slot *mm_slot;
struct mm_slot *slot;
struct mm_struct *mm;
struct vm_area_struct *vma;
int progress = 0;
VM_BUG_ON(!pages);
lockdep_assert_held(&khugepaged_mm_lock);
*result = SCAN_FAIL;
if (khugepaged_scan.mm_slot) {
mm_slot = khugepaged_scan.mm_slot;
slot = &mm_slot->slot;
} else {
slot = list_entry(khugepaged_scan.mm_head.next,
struct mm_slot, mm_node);
mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot);
khugepaged_scan.address = 0;
khugepaged_scan.mm_slot = mm_slot;
}
spin_unlock(&khugepaged_mm_lock);
mm = slot->mm;
/*
* Don't wait for semaphore (to avoid long wait times). Just move to
* the next mm on the list.
*/
vma = NULL;
if (unlikely(!mmap_read_trylock(mm)))
goto breakouterloop_mmap_lock;
progress++;
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
goto breakouterloop;
vma_iter_init(&vmi, mm, khugepaged_scan.address);
for_each_vma(vmi, vma) {
unsigned long hstart, hend;
cond_resched();
if (unlikely(hpage_collapse_test_exit_or_disable(mm))) {
progress++;
break;
}
if (!thp_vma_allowable_order(vma, vma->vm_flags,
TVA_ENFORCE_SYSFS, PMD_ORDER)) {
skip:
progress++;
continue;
}
hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE);
hend = round_down(vma->vm_end, HPAGE_PMD_SIZE);
if (khugepaged_scan.address > hend)
goto skip;
if (khugepaged_scan.address < hstart)
khugepaged_scan.address = hstart;
VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
while (khugepaged_scan.address < hend) {
bool mmap_locked = true;
cond_resched();
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
goto breakouterloop;
VM_BUG_ON(khugepaged_scan.address < hstart ||
khugepaged_scan.address + HPAGE_PMD_SIZE >
hend);
if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
struct file *file = get_file(vma->vm_file);
pgoff_t pgoff = linear_page_index(vma,
khugepaged_scan.address);
mmap_read_unlock(mm);
mmap_locked = false;
*result = hpage_collapse_scan_file(mm,
khugepaged_scan.address, file, pgoff, cc);
fput(file);
if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
mmap_read_lock(mm);
if (hpage_collapse_test_exit_or_disable(mm))
goto breakouterloop;
*result = collapse_pte_mapped_thp(mm,
khugepaged_scan.address, false);
if (*result == SCAN_PMD_MAPPED)
*result = SCAN_SUCCEED;
mmap_read_unlock(mm);
}
} else {
*result = hpage_collapse_scan_pmd(mm, vma,
khugepaged_scan.address, &mmap_locked, cc);
}
if (*result == SCAN_SUCCEED)
++khugepaged_pages_collapsed;
/* move to next address */
khugepaged_scan.address += HPAGE_PMD_SIZE;
progress += HPAGE_PMD_NR;
if (!mmap_locked)
/*
* We released mmap_lock so break loop. Note
* that we drop mmap_lock before all hugepage
* allocations, so if allocation fails, we are
* guaranteed to break here and report the
* correct result back to caller.
*/
goto breakouterloop_mmap_lock;
if (progress >= pages)
goto breakouterloop;
}
}
breakouterloop:
mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */
breakouterloop_mmap_lock:
spin_lock(&khugepaged_mm_lock);
VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
/*
* Release the current mm_slot if this mm is about to die, or
* if we scanned all vmas of this mm.
*/
if (hpage_collapse_test_exit(mm) || !vma) {
/*
* Make sure that if mm_users is reaching zero while
* khugepaged runs here, khugepaged_exit will find
* mm_slot not pointing to the exiting mm.
*/
if (slot->mm_node.next != &khugepaged_scan.mm_head) {
slot = list_entry(slot->mm_node.next,
struct mm_slot, mm_node);
khugepaged_scan.mm_slot =
mm_slot_entry(slot, struct khugepaged_mm_slot, slot);
khugepaged_scan.address = 0;
} else {
khugepaged_scan.mm_slot = NULL;
khugepaged_full_scans++;
}
collect_mm_slot(mm_slot);
}
return progress;
}
static int khugepaged_has_work(void)
{
return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
}
static int khugepaged_wait_event(void)
{
return !list_empty(&khugepaged_scan.mm_head) ||
kthread_should_stop();
}
static void khugepaged_do_scan(struct collapse_control *cc)
{
unsigned int progress = 0, pass_through_head = 0;
unsigned int pages = READ_ONCE(khugepaged_pages_to_scan);
bool wait = true;
int result = SCAN_SUCCEED;
lru_add_drain_all();
while (true) {
cond_resched();
if (unlikely(kthread_should_stop()))
break;
spin_lock(&khugepaged_mm_lock);
if (!khugepaged_scan.mm_slot)
pass_through_head++;
if (khugepaged_has_work() &&
pass_through_head < 2)
progress += khugepaged_scan_mm_slot(pages - progress,
&result, cc);
else
progress = pages;
spin_unlock(&khugepaged_mm_lock);
if (progress >= pages)
break;
if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) {
/*
* If fail to allocate the first time, try to sleep for
* a while. When hit again, cancel the scan.
*/
if (!wait)
break;
wait = false;
khugepaged_alloc_sleep();
}
}
}
static bool khugepaged_should_wakeup(void)
{
return kthread_should_stop() ||
time_after_eq(jiffies, khugepaged_sleep_expire);
}
static void khugepaged_wait_work(void)
{
if (khugepaged_has_work()) {
const unsigned long scan_sleep_jiffies =
msecs_to_jiffies(khugepaged_scan_sleep_millisecs);
if (!scan_sleep_jiffies)
return;
khugepaged_sleep_expire = jiffies + scan_sleep_jiffies;
wait_event_freezable_timeout(khugepaged_wait,
khugepaged_should_wakeup(),
scan_sleep_jiffies);
return;
}
if (hugepage_pmd_enabled())
wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
}
static int khugepaged(void *none)
{
struct khugepaged_mm_slot *mm_slot;
set_freezable();
set_user_nice(current, MAX_NICE);
while (!kthread_should_stop()) {
khugepaged_do_scan(&khugepaged_collapse_control);
khugepaged_wait_work();
}
spin_lock(&khugepaged_mm_lock);
mm_slot = khugepaged_scan.mm_slot;
khugepaged_scan.mm_slot = NULL;
if (mm_slot)
collect_mm_slot(mm_slot);
spin_unlock(&khugepaged_mm_lock);
return 0;
}
static void set_recommended_min_free_kbytes(void)
{
struct zone *zone;
int nr_zones = 0;
unsigned long recommended_min;
if (!hugepage_pmd_enabled()) {
calculate_min_free_kbytes();
goto update_wmarks;
}
for_each_populated_zone(zone) {
/*
* We don't need to worry about fragmentation of
* ZONE_MOVABLE since it only has movable pages.
*/
if (zone_idx(zone) > gfp_zone(GFP_USER))
continue;
nr_zones++;
}
/* Ensure 2 pageblocks are free to assist fragmentation avoidance */
recommended_min = pageblock_nr_pages * nr_zones * 2;
/*
* Make sure that on average at least two pageblocks are almost free
* of another type, one for a migratetype to fall back to and a
* second to avoid subsequent fallbacks of other types There are 3
* MIGRATE_TYPES we care about.
*/
recommended_min += pageblock_nr_pages * nr_zones *
MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;
/* don't ever allow to reserve more than 5% of the lowmem */
recommended_min = min(recommended_min,
(unsigned long) nr_free_buffer_pages() / 20);
recommended_min <<= (PAGE_SHIFT-10);
if (recommended_min > min_free_kbytes) {
if (user_min_free_kbytes >= 0)
pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n",
min_free_kbytes, recommended_min);
min_free_kbytes = recommended_min;
}
update_wmarks:
setup_per_zone_wmarks();
}
int start_stop_khugepaged(void)
{
int err = 0;
mutex_lock(&khugepaged_mutex);
if (hugepage_pmd_enabled()) {
if (!khugepaged_thread)
khugepaged_thread = kthread_run(khugepaged, NULL,
"khugepaged");
if (IS_ERR(khugepaged_thread)) {
pr_err("khugepaged: kthread_run(khugepaged) failed\n");
err = PTR_ERR(khugepaged_thread);
khugepaged_thread = NULL;
goto fail;
}
if (!list_empty(&khugepaged_scan.mm_head))
wake_up_interruptible(&khugepaged_wait);
} else if (khugepaged_thread) {
kthread_stop(khugepaged_thread);
khugepaged_thread = NULL;
}
set_recommended_min_free_kbytes();
fail:
mutex_unlock(&khugepaged_mutex);
return err;
}
void khugepaged_min_free_kbytes_update(void)
{
mutex_lock(&khugepaged_mutex);
if (hugepage_pmd_enabled() && khugepaged_thread)
set_recommended_min_free_kbytes();
mutex_unlock(&khugepaged_mutex);
}
bool current_is_khugepaged(void)
{
return kthread_func(current) == khugepaged;
}
static int madvise_collapse_errno(enum scan_result r)
{
/*
* MADV_COLLAPSE breaks from existing madvise(2) conventions to provide
* actionable feedback to caller, so they may take an appropriate
* fallback measure depending on the nature of the failure.
*/
switch (r) {
case SCAN_ALLOC_HUGE_PAGE_FAIL:
return -ENOMEM;
case SCAN_CGROUP_CHARGE_FAIL:
case SCAN_EXCEED_NONE_PTE:
return -EBUSY;
/* Resource temporary unavailable - trying again might succeed */
case SCAN_PAGE_COUNT:
case SCAN_PAGE_LOCK:
case SCAN_PAGE_LRU:
case SCAN_DEL_PAGE_LRU:
case SCAN_PAGE_FILLED:
return -EAGAIN;
/*
* Other: Trying again likely not to succeed / error intrinsic to
* specified memory range. khugepaged likely won't be able to collapse
* either.
*/
default:
return -EINVAL;
}
}
int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
struct collapse_control *cc;
struct mm_struct *mm = vma->vm_mm;
unsigned long hstart, hend, addr;
int thps = 0, last_fail = SCAN_FAIL;
bool mmap_locked = true;
BUG_ON(vma->vm_start > start);
BUG_ON(vma->vm_end < end);
*prev = vma;
if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER))
return -EINVAL;
cc = kmalloc(sizeof(*cc), GFP_KERNEL);
if (!cc)
return -ENOMEM;
cc->is_khugepaged = false;
mmgrab(mm);
lru_add_drain_all();
hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = end & HPAGE_PMD_MASK;
for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
int result = SCAN_FAIL;
if (!mmap_locked) {
cond_resched();
mmap_read_lock(mm);
mmap_locked = true;
result = hugepage_vma_revalidate(mm, addr, false, &vma,
cc);
if (result != SCAN_SUCCEED) {
last_fail = result;
goto out_nolock;
}
hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
}
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
struct file *file = get_file(vma->vm_file);
pgoff_t pgoff = linear_page_index(vma, addr);
mmap_read_unlock(mm);
mmap_locked = false;
result = hpage_collapse_scan_file(mm, addr, file, pgoff,
cc);
fput(file);
} else {
result = hpage_collapse_scan_pmd(mm, vma, addr,
&mmap_locked, cc);
}
if (!mmap_locked)
*prev = NULL; /* Tell caller we dropped mmap_lock */
handle_result:
switch (result) {
case SCAN_SUCCEED:
case SCAN_PMD_MAPPED:
++thps;
break;
case SCAN_PTE_MAPPED_HUGEPAGE:
BUG_ON(mmap_locked);
BUG_ON(*prev);
mmap_read_lock(mm);
result = collapse_pte_mapped_thp(mm, addr, true);
mmap_read_unlock(mm);
goto handle_result;
/* Whitelisted set of results where continuing OK */
case SCAN_PMD_NULL:
case SCAN_PTE_NON_PRESENT:
case SCAN_PTE_UFFD_WP:
case SCAN_PAGE_RO:
case SCAN_LACK_REFERENCED_PAGE:
case SCAN_PAGE_NULL:
case SCAN_PAGE_COUNT:
case SCAN_PAGE_LOCK:
case SCAN_PAGE_COMPOUND:
case SCAN_PAGE_LRU:
case SCAN_DEL_PAGE_LRU:
last_fail = result;
break;
default:
last_fail = result;
/* Other error, exit */
goto out_maybelock;
}
}
out_maybelock:
/* Caller expects us to hold mmap_lock on return */
if (!mmap_locked)
mmap_read_lock(mm);
out_nolock:
mmap_assert_locked(mm);
mmdrop(mm);
kfree(cc);
return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0
: madvise_collapse_errno(last_fail);
}
// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/*
* Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
* Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
* Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved.
*
* This driver produces cryptographically secure pseudorandom data. It is divided
* into roughly six sections, each with a section header:
*
* - Initialization and readiness waiting.
* - Fast key erasure RNG, the "crng".
* - Entropy accumulation and extraction routines.
* - Entropy collection routines.
* - Userspace reader/writer interfaces.
* - Sysctl interface.
*
* The high level overview is that there is one input pool, into which
* various pieces of data are hashed. Prior to initialization, some of that
* data is then "credited" as having a certain number of bits of entropy.
* When enough bits of entropy are available, the hash is finalized and
* handed as a key to a stream cipher that expands it indefinitely for
* various consumers. This key is periodically refreshed as the various
* entropy collectors, described below, add data to the input pool.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
#include <linux/uaccess.h>
#include <linux/suspend.h>
#include <linux/siphash.h>
#include <linux/sched/isolation.h>
#include <crypto/chacha.h>
#include <crypto/blake2s.h>
#ifdef CONFIG_VDSO_GETRANDOM
#include <vdso/getrandom.h>
#include <vdso/datapage.h>
#include <vdso/vsyscall.h>
#endif
#include <asm/archrandom.h>
#include <asm/processor.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/io.h>
/*********************************************************************
*
* Initialization and readiness waiting.
*
* Much of the RNG infrastructure is devoted to various dependencies
* being able to wait until the RNG has collected enough entropy and
* is ready for safe consumption.
*
*********************************************************************/
/*
* crng_init is protected by base_crng->lock, and only increases
* its value (from empty->early->ready).
*/
static enum {
CRNG_EMPTY = 0, /* Little to no entropy collected */
CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */
CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */
} crng_init __read_mostly = CRNG_EMPTY;
static DEFINE_STATIC_KEY_FALSE(crng_is_ready);
#define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY)
/* Various types of waiters for crng_init->CRNG_READY transition. */
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
static struct fasync_struct *fasync;
static ATOMIC_NOTIFIER_HEAD(random_ready_notifier);
/* Control how we warn userspace. */
static struct ratelimit_state urandom_warning =
RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE);
static int ratelimit_disable __read_mostly =
IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM);
module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
/*
* Returns whether or not the input pool has been seeded and thus guaranteed
* to supply cryptographically secure random numbers. This applies to: the
* /dev/urandom device, the get_random_bytes function, and the get_random_{u8,
* u16,u32,u64,long} family of functions.
*
* Returns: true if the input pool has been seeded.
* false if the input pool has not been seeded.
*/
bool rng_is_initialized(void)
{
return crng_ready();
}
EXPORT_SYMBOL(rng_is_initialized);
static void __cold crng_set_ready(struct work_struct *work)
{
static_branch_enable(&crng_is_ready);
}
/* Used by wait_for_random_bytes(), and considered an entropy collector, below. */
static void try_to_generate_entropy(void);
/*
* Wait for the input pool to be seeded and thus guaranteed to supply
* cryptographically secure random numbers. This applies to: the /dev/urandom
* device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64,
* long} family of functions. Using any of these functions without first
* calling this function forfeits the guarantee of security.
*
* Returns: 0 if the input pool has been seeded.
* -ERESTARTSYS if the function was interrupted by a signal.
*/
int wait_for_random_bytes(void)
{
while (!crng_ready()) {
int ret;
try_to_generate_entropy();
ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ);
if (ret)
return ret > 0 ? 0 : ret;
}
return 0;
}
EXPORT_SYMBOL(wait_for_random_bytes);
/*
* Add a callback function that will be invoked when the crng is initialised,
* or immediately if it already has been. Only use this is you are absolutely
* sure it is required. Most users should instead be able to test
* `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`.
*/
int __cold execute_with_initialized_rng(struct notifier_block *nb)
{
unsigned long flags;
int ret = 0;
spin_lock_irqsave(&random_ready_notifier.lock, flags);
if (crng_ready())
nb->notifier_call(nb, 0, NULL);
else
ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb);
spin_unlock_irqrestore(&random_ready_notifier.lock, flags);
return ret;
}
#define warn_unseeded_randomness() \
if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \
printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \
__func__, (void *)_RET_IP_, crng_init)
/*********************************************************************
*
* Fast key erasure RNG, the "crng".
*
* These functions expand entropy from the entropy extractor into
* long streams for external consumption using the "fast key erasure"
* RNG described at <https://blog.cr.yp.to/20170723-random.html>.
*
* There are a few exported interfaces for use by other drivers:
*
* void get_random_bytes(void *buf, size_t len)
* u8 get_random_u8()
* u16 get_random_u16()
* u32 get_random_u32()
* u32 get_random_u32_below(u32 ceil)
* u32 get_random_u32_above(u32 floor)
* u32 get_random_u32_inclusive(u32 floor, u32 ceil)
* u64 get_random_u64()
* unsigned long get_random_long()
*
* These interfaces will return the requested number of random bytes
* into the given buffer or as a return value. This is equivalent to
* a read from /dev/urandom. The u8, u16, u32, u64, long family of
* functions may be higher performance for one-off random integers,
* because they do a bit of buffering and do not invoke reseeding
* until the buffer is emptied.
*
*********************************************************************/
enum {
CRNG_RESEED_START_INTERVAL = HZ,
CRNG_RESEED_INTERVAL = 60 * HZ
};
static struct {
u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long));
unsigned long generation;
spinlock_t lock;
} base_crng = {
.lock = __SPIN_LOCK_UNLOCKED(base_crng.lock)
};
struct crng {
u8 key[CHACHA_KEY_SIZE];
unsigned long generation;
local_lock_t lock;
};
static DEFINE_PER_CPU(struct crng, crngs) = {
.generation = ULONG_MAX,
.lock = INIT_LOCAL_LOCK(crngs.lock),
};
/*
* Return the interval until the next reseeding, which is normally
* CRNG_RESEED_INTERVAL, but during early boot, it is at an interval
* proportional to the uptime.
*/
static unsigned int crng_reseed_interval(void)
{
static bool early_boot = true;
if (unlikely(READ_ONCE(early_boot))) {
time64_t uptime = ktime_get_seconds();
if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2)
WRITE_ONCE(early_boot, false);
else
return max_t(unsigned int, CRNG_RESEED_START_INTERVAL,
(unsigned int)uptime / 2 * HZ);
}
return CRNG_RESEED_INTERVAL;
}
/* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */
static void extract_entropy(void *buf, size_t len);
/* This extracts a new crng key from the input pool. */
static void crng_reseed(struct work_struct *work)
{
static DECLARE_DELAYED_WORK(next_reseed, crng_reseed);
unsigned long flags;
unsigned long next_gen;
u8 key[CHACHA_KEY_SIZE];
/* Immediately schedule the next reseeding, so that it fires sooner rather than later. */
if (likely(system_unbound_wq))
queue_delayed_work(system_unbound_wq, &next_reseed, crng_reseed_interval());
extract_entropy(key, sizeof(key));
/*
* We copy the new key into the base_crng, overwriting the old one,
* and update the generation counter. We avoid hitting ULONG_MAX,
* because the per-cpu crngs are initialized to ULONG_MAX, so this
* forces new CPUs that come online to always initialize.
*/
spin_lock_irqsave(&base_crng.lock, flags);
memcpy(base_crng.key, key, sizeof(base_crng.key));
next_gen = base_crng.generation + 1;
if (next_gen == ULONG_MAX)
++next_gen;
WRITE_ONCE(base_crng.generation, next_gen);
#ifdef CONFIG_VDSO_GETRANDOM
/* base_crng.generation's invalid value is ULONG_MAX, while
* vdso_k_rng_data->generation's invalid value is 0, so add one to the
* former to arrive at the latter. Use smp_store_release so that this
* is ordered with the write above to base_crng.generation. Pairs with
* the smp_rmb() before the syscall in the vDSO code.
*
* Cast to unsigned long for 32-bit architectures, since atomic 64-bit
* operations are not supported on those architectures. This is safe
* because base_crng.generation is a 32-bit value. On big-endian
* architectures it will be stored in the upper 32 bits, but that's okay
* because the vDSO side only checks whether the value changed, without
* actually using or interpreting the value.
*/
smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1);
#endif
if (!static_branch_likely(&crng_is_ready))
crng_init = CRNG_READY;
spin_unlock_irqrestore(&base_crng.lock, flags);
memzero_explicit(key, sizeof(key));
}
/*
* This generates a ChaCha block using the provided key, and then
* immediately overwrites that key with half the block. It returns
* the resultant ChaCha state to the user, along with the second
* half of the block containing 32 bytes of random data that may
* be used; random_data_len may not be greater than 32.
*
* The returned ChaCha state contains within it a copy of the old
* key value, at index 4, so the state should always be zeroed out
* immediately after using in order to maintain forward secrecy.
* If the state cannot be erased in a timely manner, then it is
* safer to set the random_data parameter to &chacha_state[4] so
* that this function overwrites it before returning.
*/
static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE],
u32 chacha_state[CHACHA_STATE_WORDS],
u8 *random_data, size_t random_data_len)
{
u8 first_block[CHACHA_BLOCK_SIZE];
BUG_ON(random_data_len > 32);
chacha_init_consts(chacha_state);
memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE);
memset(&chacha_state[12], 0, sizeof(u32) * 4);
chacha20_block(chacha_state, first_block);
memcpy(key, first_block, CHACHA_KEY_SIZE);
memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len);
memzero_explicit(first_block, sizeof(first_block));
}
/*
* This function returns a ChaCha state that you may use for generating
* random data. It also returns up to 32 bytes on its own of random data
* that may be used; random_data_len may not be greater than 32.
*/
static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
u8 *random_data, size_t random_data_len)
{
unsigned long flags;
struct crng *crng;
BUG_ON(random_data_len > 32);
/*
* For the fast path, we check whether we're ready, unlocked first, and
* then re-check once locked later. In the case where we're really not
* ready, we do fast key erasure with the base_crng directly, extracting
* when crng_init is CRNG_EMPTY.
*/
if (!crng_ready()) {
bool ready;
spin_lock_irqsave(&base_crng.lock, flags);
ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key));
crng_fast_key_erasure(base_crng.key, chacha_state,
random_data, random_data_len);
}
spin_unlock_irqrestore(&base_crng.lock, flags);
if (!ready)
return;
}
local_lock_irqsave(&crngs.lock, flags);
crng = raw_cpu_ptr(&crngs);
/*
* If our per-cpu crng is older than the base_crng, then it means
* somebody reseeded the base_crng. In that case, we do fast key
* erasure on the base_crng, and use its output as the new key
* for our per-cpu crng. This brings us up to date with base_crng.
*/
if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock);
crng_fast_key_erasure(base_crng.key, chacha_state,
crng->key, sizeof(crng->key));
crng->generation = base_crng.generation;
spin_unlock(&base_crng.lock);
}
/*
* Finally, when we've made it this far, our per-cpu crng has an up
* to date key, and we can do fast key erasure with it to produce
* some random data and a ChaCha state for the caller. All other
* branches of this function are "unlikely", so most of the time we
* should wind up here immediately.
*/
crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len);
local_unlock_irqrestore(&crngs.lock, flags);
}
static void _get_random_bytes(void *buf, size_t len)
{ u32 chacha_state[CHACHA_STATE_WORDS];
u8 tmp[CHACHA_BLOCK_SIZE];
size_t first_block_len;
if (!len)
return;
first_block_len = min_t(size_t, 32, len);
crng_make_state(chacha_state, buf, first_block_len);
len -= first_block_len;
buf += first_block_len;
while (len) {
if (len < CHACHA_BLOCK_SIZE) {
chacha20_block(chacha_state, tmp);
memcpy(buf, tmp, len);
memzero_explicit(tmp, sizeof(tmp));
break;
}
chacha20_block(chacha_state, buf);
if (unlikely(chacha_state[12] == 0)) ++chacha_state[13];
len -= CHACHA_BLOCK_SIZE;
buf += CHACHA_BLOCK_SIZE;
}
memzero_explicit(chacha_state, sizeof(chacha_state));
}
/*
* This returns random bytes in arbitrary quantities. The quality of the
* random bytes is good as /dev/urandom. In order to ensure that the
* randomness provided by this function is okay, the function
* wait_for_random_bytes() should be called and return 0 at least once
* at any point prior.
*/
void get_random_bytes(void *buf, size_t len)
{
warn_unseeded_randomness();
_get_random_bytes(buf, len);
}
EXPORT_SYMBOL(get_random_bytes);
static ssize_t get_random_bytes_user(struct iov_iter *iter)
{
u32 chacha_state[CHACHA_STATE_WORDS];
u8 block[CHACHA_BLOCK_SIZE];
size_t ret = 0, copied;
if (unlikely(!iov_iter_count(iter)))
return 0;
/*
* Immediately overwrite the ChaCha key at index 4 with random
* bytes, in case userspace causes copy_to_iter() below to sleep
* forever, so that we still retain forward secrecy in that case.
*/
crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE);
/*
* However, if we're doing a read of len <= 32, we don't need to
* use chacha_state after, so we can simply return those bytes to
* the user directly.
*/
if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) {
ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter);
goto out_zero_chacha;
}
for (;;) {
chacha20_block(chacha_state, block);
if (unlikely(chacha_state[12] == 0))
++chacha_state[13];
copied = copy_to_iter(block, sizeof(block), iter);
ret += copied;
if (!iov_iter_count(iter) || copied != sizeof(block))
break;
BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0);
if (ret % PAGE_SIZE == 0) {
if (signal_pending(current))
break;
cond_resched();
}
}
memzero_explicit(block, sizeof(block));
out_zero_chacha:
memzero_explicit(chacha_state, sizeof(chacha_state));
return ret ? ret : -EFAULT;
}
/*
* Batched entropy returns random integers. The quality of the random
* number is good as /dev/urandom. In order to ensure that the randomness
* provided by this function is okay, the function wait_for_random_bytes()
* should be called and return 0 at least once at any point prior.
*/
#define DEFINE_BATCHED_ENTROPY(type) \
struct batch_ ##type { \
/* \
* We make this 1.5x a ChaCha block, so that we get the \
* remaining 32 bytes from fast key erasure, plus one full \
* block from the detached ChaCha state. We can increase \
* the size of this later if needed so long as we keep the \
* formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \
*/ \
type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \
local_lock_t lock; \
unsigned long generation; \
unsigned int position; \
}; \
\
static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \
.lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \
.position = UINT_MAX \
}; \
\
type get_random_ ##type(void) \
{ \
type ret; \
unsigned long flags; \
struct batch_ ##type *batch; \
unsigned long next_gen; \
\
warn_unseeded_randomness(); \
\
if (!crng_ready()) { \
_get_random_bytes(&ret, sizeof(ret)); \
return ret; \
} \
\
local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \
batch = raw_cpu_ptr(&batched_entropy_##type); \
\
next_gen = READ_ONCE(base_crng.generation); \
if (batch->position >= ARRAY_SIZE(batch->entropy) || \
next_gen != batch->generation) { \
_get_random_bytes(batch->entropy, sizeof(batch->entropy)); \
batch->position = 0; \
batch->generation = next_gen; \
} \
\
ret = batch->entropy[batch->position]; \
batch->entropy[batch->position] = 0; \
++batch->position; \
local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \
return ret; \
} \
EXPORT_SYMBOL(get_random_ ##type);
DEFINE_BATCHED_ENTROPY(u8)
DEFINE_BATCHED_ENTROPY(u16)
DEFINE_BATCHED_ENTROPY(u32)DEFINE_BATCHED_ENTROPY(u64)
u32 __get_random_u32_below(u32 ceil)
{
/*
* This is the slow path for variable ceil. It is still fast, most of
* the time, by doing traditional reciprocal multiplication and
* opportunistically comparing the lower half to ceil itself, before
* falling back to computing a larger bound, and then rejecting samples
* whose lower half would indicate a range indivisible by ceil. The use
* of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable
* in 32-bits.
*/
u32 rand = get_random_u32();
u64 mult;
/*
* This function is technically undefined for ceil == 0, and in fact
* for the non-underscored constant version in the header, we build bug
* on that. But for the non-constant case, it's convenient to have that
* evaluate to being a straight call to get_random_u32(), so that
* get_random_u32_inclusive() can work over its whole range without
* undefined behavior.
*/
if (unlikely(!ceil))
return rand;
mult = (u64)ceil * rand;
if (unlikely((u32)mult < ceil)) {
u32 bound = -ceil % ceil;
while (unlikely((u32)mult < bound))
mult = (u64)ceil * get_random_u32();
}
return mult >> 32;
}
EXPORT_SYMBOL(__get_random_u32_below);
#ifdef CONFIG_SMP
/*
* This function is called when the CPU is coming up, with entry
* CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP.
*/
int __cold random_prepare_cpu(unsigned int cpu)
{
/*
* When the cpu comes back online, immediately invalidate both
* the per-cpu crng and all batches, so that we serve fresh
* randomness.
*/
per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX;
per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX;
per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX;
per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX;
per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX;
return 0;
}
#endif
/**********************************************************************
*
* Entropy accumulation and extraction routines.
*
* Callers may add entropy via:
*
* static void mix_pool_bytes(const void *buf, size_t len)
*
* After which, if added entropy should be credited:
*
* static void credit_init_bits(size_t bits)
*
* Finally, extract entropy via:
*
* static void extract_entropy(void *buf, size_t len)
*
**********************************************************************/
enum {
POOL_BITS = BLAKE2S_HASH_SIZE * 8,
POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */
POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */
};
static struct {
struct blake2s_state hash;
spinlock_t lock;
unsigned int init_bits;
} input_pool = {
.hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE),
BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4,
BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 },
.hash.outlen = BLAKE2S_HASH_SIZE,
.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
};
static void _mix_pool_bytes(const void *buf, size_t len)
{
blake2s_update(&input_pool.hash, buf, len);
}
/*
* This function adds bytes into the input pool. It does not
* update the initialization bit counter; the caller should call
* credit_init_bits if this is appropriate.
*/
static void mix_pool_bytes(const void *buf, size_t len)
{
unsigned long flags;
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(buf, len);
spin_unlock_irqrestore(&input_pool.lock, flags);
}
/*
* This is an HKDF-like construction for using the hashed collected entropy
* as a PRF key, that's then expanded block-by-block.
*/
static void extract_entropy(void *buf, size_t len)
{
unsigned long flags;
u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE];
struct {
unsigned long rdseed[32 / sizeof(long)];
size_t counter;
} block;
size_t i, longs;
for (i = 0; i < ARRAY_SIZE(block.rdseed);) {
longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i);
if (longs) {
i += longs;
continue;
}
longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i);
if (longs) {
i += longs;
continue;
}
block.rdseed[i++] = random_get_entropy();
}
spin_lock_irqsave(&input_pool.lock, flags);
/* seed = HASHPRF(last_key, entropy_input) */
blake2s_final(&input_pool.hash, seed);
/* next_key = HASHPRF(seed, RDSEED || 0) */
block.counter = 0;
blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed));
blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key));
spin_unlock_irqrestore(&input_pool.lock, flags);
memzero_explicit(next_key, sizeof(next_key));
while (len) {
i = min_t(size_t, len, BLAKE2S_HASH_SIZE);
/* output = HASHPRF(seed, RDSEED || ++counter) */
++block.counter;
blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed));
len -= i;
buf += i;
}
memzero_explicit(seed, sizeof(seed));
memzero_explicit(&block, sizeof(block));
}
#define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits)
static void __cold _credit_init_bits(size_t bits)
{
static DECLARE_WORK(set_ready, crng_set_ready);
unsigned int new, orig, add;
unsigned long flags;
if (!bits)
return;
add = min_t(size_t, bits, POOL_BITS);
orig = READ_ONCE(input_pool.init_bits);
do {
new = min_t(unsigned int, POOL_BITS, orig + add);
} while (!try_cmpxchg(&input_pool.init_bits, &orig, new));
if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) {
crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */
if (static_key_initialized && system_unbound_wq)
queue_work(system_unbound_wq, &set_ready);
atomic_notifier_call_chain(&random_ready_notifier, 0, NULL);
#ifdef CONFIG_VDSO_GETRANDOM
WRITE_ONCE(vdso_k_rng_data->is_ready, true);
#endif
wake_up_interruptible(&crng_init_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
pr_notice("crng init done\n");
if (urandom_warning.missed)
pr_notice("%d urandom warning(s) missed due to ratelimiting\n",
urandom_warning.missed);
} else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) {
spin_lock_irqsave(&base_crng.lock, flags);
/* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */
if (crng_init == CRNG_EMPTY) {
extract_entropy(base_crng.key, sizeof(base_crng.key));
crng_init = CRNG_EARLY;
}
spin_unlock_irqrestore(&base_crng.lock, flags);
}
}
/**********************************************************************
*
* Entropy collection routines.
*
* The following exported functions are used for pushing entropy into
* the above entropy accumulation routines:
*
* void add_device_randomness(const void *buf, size_t len);
* void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after);
* void add_bootloader_randomness(const void *buf, size_t len);
* void add_vmfork_randomness(const void *unique_vm_id, size_t len);
* void add_interrupt_randomness(int irq);
* void add_input_randomness(unsigned int type, unsigned int code, unsigned int value);
* void add_disk_randomness(struct gendisk *disk);
*
* add_device_randomness() adds data to the input pool that
* is likely to differ between two devices (or possibly even per boot).
* This would be things like MAC addresses or serial numbers, or the
* read-out of the RTC. This does *not* credit any actual entropy to
* the pool, but it initializes the pool to different values for devices
* that might otherwise be identical and have very little entropy
* available to them (particularly common in the embedded world).
*
* add_hwgenerator_randomness() is for true hardware RNGs, and will credit
* entropy as specified by the caller. If the entropy pool is full it will
* block until more entropy is needed.
*
* add_bootloader_randomness() is called by bootloader drivers, such as EFI
* and device tree, and credits its input depending on whether or not the
* command line option 'random.trust_bootloader'.
*
* add_vmfork_randomness() adds a unique (but not necessarily secret) ID
* representing the current instance of a VM to the pool, without crediting,
* and then force-reseeds the crng so that it takes effect immediately.
*
* add_interrupt_randomness() uses the interrupt timing as random
* inputs to the entropy pool. Using the cycle counters and the irq source
* as inputs, it feeds the input pool roughly once a second or after 64
* interrupts, crediting 1 bit of entropy for whichever comes first.
*
* add_input_randomness() uses the input layer interrupt timing, as well
* as the event type information from the hardware.
*
* add_disk_randomness() uses what amounts to the seek time of block
* layer request events, on a per-disk_devt basis, as input to the
* entropy pool. Note that high-speed solid state drives with very low
* seek times do not make for good sources of entropy, as their seek
* times are usually fairly consistent.
*
* The last two routines try to estimate how many bits of entropy
* to credit. They do this by keeping track of the first and second
* order deltas of the event timings.
*
**********************************************************************/
static bool trust_cpu __initdata = true;
static bool trust_bootloader __initdata = true;
static int __init parse_trust_cpu(char *arg)
{
return kstrtobool(arg, &trust_cpu);
}
static int __init parse_trust_bootloader(char *arg)
{
return kstrtobool(arg, &trust_bootloader);
}
early_param("random.trust_cpu", parse_trust_cpu);
early_param("random.trust_bootloader", parse_trust_bootloader);
static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data)
{
unsigned long flags, entropy = random_get_entropy();
/*
* Encode a representation of how long the system has been suspended,
* in a way that is distinct from prior system suspends.
*/
ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() };
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(&action, sizeof(action));
_mix_pool_bytes(stamps, sizeof(stamps));
_mix_pool_bytes(&entropy, sizeof(entropy));
spin_unlock_irqrestore(&input_pool.lock, flags);
if (crng_ready() && (action == PM_RESTORE_PREPARE ||
(action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) &&
!IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) {
crng_reseed(NULL);
pr_notice("crng reseeded on system resumption\n");
}
return 0;
}
static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification };
/*
* This is called extremely early, before time keeping functionality is
* available, but arch randomness is. Interrupts are not yet enabled.
*/
void __init random_init_early(const char *command_line)
{
unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)];
size_t i, longs, arch_bits;
#if defined(LATENT_ENTROPY_PLUGIN)
static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy;
_mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed));
#endif
for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) {
longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i);
if (longs) {
_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
i += longs;
continue;
}
longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i);
if (longs) {
_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
i += longs;
continue;
}
arch_bits -= sizeof(*entropy) * 8;
++i;
}
_mix_pool_bytes(init_utsname(), sizeof(*(init_utsname())));
_mix_pool_bytes(command_line, strlen(command_line));
/* Reseed if already seeded by earlier phases. */
if (crng_ready())
crng_reseed(NULL);
else if (trust_cpu)
_credit_init_bits(arch_bits);
}
/*
* This is called a little bit after the prior function, and now there is
* access to timestamps counters. Interrupts are not yet enabled.
*/
void __init random_init(void)
{
unsigned long entropy = random_get_entropy();
ktime_t now = ktime_get_real();
_mix_pool_bytes(&now, sizeof(now));
_mix_pool_bytes(&entropy, sizeof(entropy));
add_latent_entropy();
/*
* If we were initialized by the cpu or bootloader before jump labels
* or workqueues are initialized, then we should enable the static
* branch here, where it's guaranteed that these have been initialized.
*/
if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY)
crng_set_ready(NULL);
/* Reseed if already seeded by earlier phases. */
if (crng_ready())
crng_reseed(NULL);
WARN_ON(register_pm_notifier(&pm_notifier));
WARN(!entropy, "Missing cycle counter and fallback timer; RNG "
"entropy collection will consequently suffer.");
}
/*
* Add device- or boot-specific data to the input pool to help
* initialize it.
*
* None of this adds any entropy; it is meant to avoid the problem of
* the entropy pool having similar initial state across largely
* identical devices.
*/
void add_device_randomness(const void *buf, size_t len)
{
unsigned long entropy = random_get_entropy();
unsigned long flags;
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(&entropy, sizeof(entropy));
_mix_pool_bytes(buf, len);
spin_unlock_irqrestore(&input_pool.lock, flags);
}
EXPORT_SYMBOL(add_device_randomness);
/*
* Interface for in-kernel drivers of true hardware RNGs. Those devices
* may produce endless random bits, so this function will sleep for
* some amount of time after, if the sleep_after parameter is true.
*/
void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after)
{
mix_pool_bytes(buf, len);
credit_init_bits(entropy);
/*
* Throttle writing to once every reseed interval, unless we're not yet
* initialized or no entropy is credited.
*/
if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy))
schedule_timeout_interruptible(crng_reseed_interval());
}
EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
/*
* Handle random seed passed by bootloader, and credit it depending
* on the command line option 'random.trust_bootloader'.
*/
void __init add_bootloader_randomness(const void *buf, size_t len)
{
mix_pool_bytes(buf, len);
if (trust_bootloader)
credit_init_bits(len * 8);
}
#if IS_ENABLED(CONFIG_VMGENID)
static BLOCKING_NOTIFIER_HEAD(vmfork_chain);
/*
* Handle a new unique VM ID, which is unique, not secret, so we
* don't credit it, but we do immediately force a reseed after so
* that it's used by the crng posthaste.
*/
void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len)
{
add_device_randomness(unique_vm_id, len);
if (crng_ready()) {
crng_reseed(NULL);
pr_notice("crng reseeded due to virtual machine fork\n");
}
blocking_notifier_call_chain(&vmfork_chain, 0, NULL);
}
#if IS_MODULE(CONFIG_VMGENID)
EXPORT_SYMBOL_GPL(add_vmfork_randomness);
#endif
int __cold register_random_vmfork_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&vmfork_chain, nb);
}
EXPORT_SYMBOL_GPL(register_random_vmfork_notifier);
int __cold unregister_random_vmfork_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&vmfork_chain, nb);
}
EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier);
#endif
struct fast_pool {
unsigned long pool[4];
unsigned long last;
unsigned int count;
struct timer_list mix;
};
static void mix_interrupt_randomness(struct timer_list *work);
static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
#ifdef CONFIG_64BIT
#define FASTMIX_PERM SIPHASH_PERMUTATION
.pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 },
#else
#define FASTMIX_PERM HSIPHASH_PERMUTATION
.pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 },
#endif
.mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0)
};
/*
* This is [Half]SipHash-1-x, starting from an empty key. Because
* the key is fixed, it assumes that its inputs are non-malicious,
* and therefore this has no security on its own. s represents the
* four-word SipHash state, while v represents a two-word input.
*/
static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2)
{
s[3] ^= v1;
FASTMIX_PERM(s[0], s[1], s[2], s[3]);
s[0] ^= v1;
s[3] ^= v2;
FASTMIX_PERM(s[0], s[1], s[2], s[3]);
s[0] ^= v2;
}
#ifdef CONFIG_SMP
/*
* This function is called when the CPU has just come online, with
* entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE.
*/
int __cold random_online_cpu(unsigned int cpu)
{
/*
* During CPU shutdown and before CPU onlining, add_interrupt_
* randomness() may schedule mix_interrupt_randomness(), and
* set the MIX_INFLIGHT flag. However, because the worker can
* be scheduled on a different CPU during this period, that
* flag will never be cleared. For that reason, we zero out
* the flag here, which runs just after workqueues are onlined
* for the CPU again. This also has the effect of setting the
* irq randomness count to zero so that new accumulated irqs
* are fresh.
*/
per_cpu_ptr(&irq_randomness, cpu)->count = 0;
return 0;
}
#endif
static void mix_interrupt_randomness(struct timer_list *work)
{
struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix);
/*
* The size of the copied stack pool is explicitly 2 longs so that we
* only ever ingest half of the siphash output each time, retaining
* the other half as the next "key" that carries over. The entropy is
* supposed to be sufficiently dispersed between bits so on average
* we don't wind up "losing" some.
*/
unsigned long pool[2];
unsigned int count;
/* Check to see if we're running on the wrong CPU due to hotplug. */
local_irq_disable();
if (fast_pool != this_cpu_ptr(&irq_randomness)) {
local_irq_enable();
return;
}
/*
* Copy the pool to the stack so that the mixer always has a
* consistent view, before we reenable irqs again.
*/
memcpy(pool, fast_pool->pool, sizeof(pool));
count = fast_pool->count;
fast_pool->count = 0;
fast_pool->last = jiffies;
local_irq_enable();
mix_pool_bytes(pool, sizeof(pool));
credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8));
memzero_explicit(pool, sizeof(pool));
}
void add_interrupt_randomness(int irq)
{
enum { MIX_INFLIGHT = 1U << 31 };
unsigned long entropy = random_get_entropy();
struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
struct pt_regs *regs = get_irq_regs();
unsigned int new_count;
fast_mix(fast_pool->pool, entropy,
(regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq));
new_count = ++fast_pool->count;
if (new_count & MIX_INFLIGHT)
return;
if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ))
return;
fast_pool->count |= MIX_INFLIGHT;
if (!timer_pending(&fast_pool->mix)) {
fast_pool->mix.expires = jiffies;
add_timer_on(&fast_pool->mix, raw_smp_processor_id());
}
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);
/* There is one of these per entropy source */
struct timer_rand_state {
unsigned long last_time;
long last_delta, last_delta2;
};
/*
* This function adds entropy to the entropy "pool" by using timing
* delays. It uses the timer_rand_state structure to make an estimate
* of how many bits of entropy this call has added to the pool. The
* value "num" is also added to the pool; it should somehow describe
* the type of event that just happened.
*/
static void add_timer_randomness(struct timer_rand_state *state, unsigned int num)
{
unsigned long entropy = random_get_entropy(), now = jiffies, flags;
long delta, delta2, delta3;
unsigned int bits;
/*
* If we're in a hard IRQ, add_interrupt_randomness() will be called
* sometime after, so mix into the fast pool.
*/
if (in_hardirq()) {
fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num);
} else {
spin_lock_irqsave(&input_pool.lock, flags);
_mix_pool_bytes(&entropy, sizeof(entropy));
_mix_pool_bytes(&num, sizeof(num));
spin_unlock_irqrestore(&input_pool.lock, flags);
}
if (crng_ready())
return;
/*
* Calculate number of bits of randomness we probably added.
* We take into account the first, second and third-order deltas
* in order to make our estimate.
*/
delta = now - READ_ONCE(state->last_time);
WRITE_ONCE(state->last_time, now);
delta2 = delta - READ_ONCE(state->last_delta);
WRITE_ONCE(state->last_delta, delta);
delta3 = delta2 - READ_ONCE(state->last_delta2);
WRITE_ONCE(state->last_delta2, delta2);
if (delta < 0)
delta = -delta;
if (delta2 < 0)
delta2 = -delta2;
if (delta3 < 0)
delta3 = -delta3;
if (delta > delta2)
delta = delta2;
if (delta > delta3)
delta = delta3;
/*
* delta is now minimum absolute delta. Round down by 1 bit
* on general principles, and limit entropy estimate to 11 bits.
*/
bits = min(fls(delta >> 1), 11);
/*
* As mentioned above, if we're in a hard IRQ, add_interrupt_randomness()
* will run after this, which uses a different crediting scheme of 1 bit
* per every 64 interrupts. In order to let that function do accounting
* close to the one in this function, we credit a full 64/64 bit per bit,
* and then subtract one to account for the extra one added.
*/
if (in_hardirq())
this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1;
else
_credit_init_bits(bits);
}
void add_input_randomness(unsigned int type, unsigned int code, unsigned int value)
{
static unsigned char last_value;
static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES };
/* Ignore autorepeat and the like. */
if (value == last_value)
return;
last_value = value;
add_timer_randomness(&input_timer_state,
(type << 4) ^ code ^ (code >> 4) ^ value);
}
EXPORT_SYMBOL_GPL(add_input_randomness);
#ifdef CONFIG_BLOCK
void add_disk_randomness(struct gendisk *disk)
{
if (!disk || !disk->random)
return;
/* First major is 1, so we get >= 0x200 here. */
add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
}
EXPORT_SYMBOL_GPL(add_disk_randomness);
void __cold rand_initialize_disk(struct gendisk *disk)
{
struct timer_rand_state *state;
/*
* If kzalloc returns null, we just won't use that entropy
* source.
*/
state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
if (state) {
state->last_time = INITIAL_JIFFIES;
disk->random = state;
}
}
#endif
struct entropy_timer_state {
unsigned long entropy;
struct timer_list timer;
atomic_t samples;
unsigned int samples_per_bit;
};
/*
* Each time the timer fires, we expect that we got an unpredictable jump in
* the cycle counter. Even if the timer is running on another CPU, the timer
* activity will be touching the stack of the CPU that is generating entropy.
*
* Note that we don't re-arm the timer in the timer itself - we are happy to be
* scheduled away, since that just makes the load more complex, but we do not
* want the timer to keep ticking unless the entropy loop is running.
*
* So the re-arming always happens in the entropy loop itself.
*/
static void __cold entropy_timer(struct timer_list *timer)
{
struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer);
unsigned long entropy = random_get_entropy();
mix_pool_bytes(&entropy, sizeof(entropy));
if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0)
credit_init_bits(1);
}
/*
* If we have an actual cycle counter, see if we can generate enough entropy
* with timing noise.
*/
static void __cold try_to_generate_entropy(void)
{
enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 };
u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1];
struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES);
unsigned int i, num_different = 0;
unsigned long last = random_get_entropy();
int cpu = -1;
for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) {
stack->entropy = random_get_entropy();
if (stack->entropy != last)
++num_different;
last = stack->entropy;
}
stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1);
if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT)
return;
atomic_set(&stack->samples, 0);
timer_setup_on_stack(&stack->timer, entropy_timer, 0);
while (!crng_ready() && !signal_pending(current)) {
/*
* Check !timer_pending() and then ensure that any previous callback has finished
* executing by checking try_to_del_timer_sync(), before queueing the next one.
*/
if (!timer_pending(&stack->timer) && try_to_del_timer_sync(&stack->timer) >= 0) {
struct cpumask timer_cpus;
unsigned int num_cpus;
/*
* Preemption must be disabled here, both to read the current CPU number
* and to avoid scheduling a timer on a dead CPU.
*/
preempt_disable();
/* Only schedule callbacks on timer CPUs that are online. */
cpumask_and(&timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask);
num_cpus = cpumask_weight(&timer_cpus);
/* In very bizarre case of misconfiguration, fallback to all online. */
if (unlikely(num_cpus == 0)) {
timer_cpus = *cpu_online_mask;
num_cpus = cpumask_weight(&timer_cpus);
}
/* Basic CPU round-robin, which avoids the current CPU. */
do {
cpu = cpumask_next(cpu, &timer_cpus);
if (cpu >= nr_cpu_ids)
cpu = cpumask_first(&timer_cpus);
} while (cpu == smp_processor_id() && num_cpus > 1);
/* Expiring the timer at `jiffies` means it's the next tick. */
stack->timer.expires = jiffies;
add_timer_on(&stack->timer, cpu);
preempt_enable();
}
mix_pool_bytes(&stack->entropy, sizeof(stack->entropy));
schedule();
stack->entropy = random_get_entropy();
}
mix_pool_bytes(&stack->entropy, sizeof(stack->entropy));
timer_delete_sync(&stack->timer);
destroy_timer_on_stack(&stack->timer);
}
/**********************************************************************
*
* Userspace reader/writer interfaces.
*
* getrandom(2) is the primary modern interface into the RNG and should
* be used in preference to anything else.
*
* Reading from /dev/random has the same functionality as calling
* getrandom(2) with flags=0. In earlier versions, however, it had
* vastly different semantics and should therefore be avoided, to
* prevent backwards compatibility issues.
*
* Reading from /dev/urandom has the same functionality as calling
* getrandom(2) with flags=GRND_INSECURE. Because it does not block
* waiting for the RNG to be ready, it should not be used.
*
* Writing to either /dev/random or /dev/urandom adds entropy to
* the input pool but does not credit it.
*
* Polling on /dev/random indicates when the RNG is initialized, on
* the read side, and when it wants new entropy, on the write side.
*
* Both /dev/random and /dev/urandom have the same set of ioctls for
* adding entropy, getting the entropy count, zeroing the count, and
* reseeding the crng.
*
**********************************************************************/
SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags)
{
struct iov_iter iter;
int ret;
if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
return -EINVAL;
/*
* Requesting insecure and blocking randomness at the same time makes
* no sense.
*/
if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
return -EINVAL;
if (!crng_ready() && !(flags & GRND_INSECURE)) {
if (flags & GRND_NONBLOCK)
return -EAGAIN;
ret = wait_for_random_bytes();
if (unlikely(ret))
return ret;
}
ret = import_ubuf(ITER_DEST, ubuf, len, &iter);
if (unlikely(ret))
return ret;
return get_random_bytes_user(&iter);
}
static __poll_t random_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &crng_init_wait, wait);
return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM;
}
static ssize_t write_pool_user(struct iov_iter *iter)
{
u8 block[BLAKE2S_BLOCK_SIZE];
ssize_t ret = 0;
size_t copied;
if (unlikely(!iov_iter_count(iter)))
return 0;
for (;;) {
copied = copy_from_iter(block, sizeof(block), iter);
ret += copied;
mix_pool_bytes(block, copied);
if (!iov_iter_count(iter) || copied != sizeof(block))
break;
BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0);
if (ret % PAGE_SIZE == 0) {
if (signal_pending(current))
break;
cond_resched();
}
}
memzero_explicit(block, sizeof(block));
return ret ? ret : -EFAULT;
}
static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
return write_pool_user(iter);
}
static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
static int maxwarn = 10;
/*
* Opportunistically attempt to initialize the RNG on platforms that
* have fast cycle counters, but don't (for now) require it to succeed.
*/
if (!crng_ready())
try_to_generate_entropy();
if (!crng_ready()) {
if (!ratelimit_disable && maxwarn <= 0)
++urandom_warning.missed;
else if (ratelimit_disable || __ratelimit(&urandom_warning)) {
--maxwarn;
pr_notice("%s: uninitialized urandom read (%zu bytes read)\n",
current->comm, iov_iter_count(iter));
}
}
return get_random_bytes_user(iter);
}
static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter)
{
int ret;
if (!crng_ready() &&
((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) ||
(kiocb->ki_filp->f_flags & O_NONBLOCK)))
return -EAGAIN;
ret = wait_for_random_bytes();
if (ret != 0)
return ret;
return get_random_bytes_user(iter);
}
static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
int __user *p = (int __user *)arg;
int ent_count;
switch (cmd) {
case RNDGETENTCNT:
/* Inherently racy, no point locking. */
if (put_user(input_pool.init_bits, p))
return -EFAULT;
return 0;
case RNDADDTOENTCNT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
if (ent_count < 0)
return -EINVAL;
credit_init_bits(ent_count);
return 0;
case RNDADDENTROPY: {
struct iov_iter iter;
ssize_t ret;
int len;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p++))
return -EFAULT;
if (ent_count < 0)
return -EINVAL;
if (get_user(len, p++))
return -EFAULT;
ret = import_ubuf(ITER_SOURCE, p, len, &iter);
if (unlikely(ret))
return ret;
ret = write_pool_user(&iter);
if (unlikely(ret < 0))
return ret;
/* Since we're crediting, enforce that it was all written into the pool. */
if (unlikely(ret != len))
return -EFAULT;
credit_init_bits(ent_count);
return 0;
}
case RNDZAPENTCNT:
case RNDCLEARPOOL:
/* No longer has any effect. */
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return 0;
case RNDRESEEDCRNG:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!crng_ready())
return -ENODATA;
crng_reseed(NULL);
return 0;
default:
return -EINVAL;
}
}
static int random_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &fasync);
}
const struct file_operations random_fops = {
.read_iter = random_read_iter,
.write_iter = random_write_iter,
.poll = random_poll,
.unlocked_ioctl = random_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
.splice_read = copy_splice_read,
.splice_write = iter_file_splice_write,
};
const struct file_operations urandom_fops = {
.read_iter = urandom_read_iter,
.write_iter = random_write_iter,
.unlocked_ioctl = random_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
.splice_read = copy_splice_read,
.splice_write = iter_file_splice_write,
};
/********************************************************************
*
* Sysctl interface.
*
* These are partly unused legacy knobs with dummy values to not break
* userspace and partly still useful things. They are usually accessible
* in /proc/sys/kernel/random/ and are as follows:
*
* - boot_id - a UUID representing the current boot.
*
* - uuid - a random UUID, different each time the file is read.
*
* - poolsize - the number of bits of entropy that the input pool can
* hold, tied to the POOL_BITS constant.
*
* - entropy_avail - the number of bits of entropy currently in the
* input pool. Always <= poolsize.
*
* - write_wakeup_threshold - the amount of entropy in the input pool
* below which write polls to /dev/random will unblock, requesting
* more entropy, tied to the POOL_READY_BITS constant. It is writable
* to avoid breaking old userspaces, but writing to it does not
* change any behavior of the RNG.
*
* - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL.
* It is writable to avoid breaking old userspaces, but writing
* to it does not change any behavior of the RNG.
*
********************************************************************/
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ;
static int sysctl_random_write_wakeup_bits = POOL_READY_BITS;
static int sysctl_poolsize = POOL_BITS;
static u8 sysctl_bootid[UUID_SIZE];
/*
* This function is used to return both the bootid UUID, and random
* UUID. The difference is in whether table->data is NULL; if it is,
* then a new UUID is generated and returned to the user.
*/
static int proc_do_uuid(const struct ctl_table *table, int write, void *buf,
size_t *lenp, loff_t *ppos)
{
u8 tmp_uuid[UUID_SIZE], *uuid;
char uuid_string[UUID_STRING_LEN + 1];
struct ctl_table fake_table = {
.data = uuid_string,
.maxlen = UUID_STRING_LEN
};
if (write)
return -EPERM;
uuid = table->data;
if (!uuid) {
uuid = tmp_uuid;
generate_random_uuid(uuid);
} else {
static DEFINE_SPINLOCK(bootid_spinlock);
spin_lock(&bootid_spinlock);
if (!uuid[8])
generate_random_uuid(uuid);
spin_unlock(&bootid_spinlock);
}
snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid);
return proc_dostring(&fake_table, 0, buf, lenp, ppos);
}
/* The same as proc_dointvec, but writes don't change anything. */
static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf,
size_t *lenp, loff_t *ppos)
{
return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
}
static const struct ctl_table random_table[] = {
{
.procname = "poolsize",
.data = &sysctl_poolsize,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "entropy_avail",
.data = &input_pool.init_bits,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "write_wakeup_threshold",
.data = &sysctl_random_write_wakeup_bits,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_do_rointvec,
},
{
.procname = "urandom_min_reseed_secs",
.data = &sysctl_random_min_urandom_seed,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_do_rointvec,
},
{
.procname = "boot_id",
.data = &sysctl_bootid,
.mode = 0444,
.proc_handler = proc_do_uuid,
},
{
.procname = "uuid",
.mode = 0444,
.proc_handler = proc_do_uuid,
},
};
/*
* random_init() is called before sysctl_init(),
* so we cannot call register_sysctl_init() in random_init()
*/
static int __init random_sysctls_init(void)
{
register_sysctl_init("kernel/random", random_table);
return 0;
}
device_initcall(random_sysctls_init);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Filesystem access notification for Linux
*
* Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
*/
#ifndef __LINUX_FSNOTIFY_BACKEND_H
#define __LINUX_FSNOTIFY_BACKEND_H
#ifdef __KERNEL__
#include <linux/idr.h> /* inotify uses this */
#include <linux/fs.h> /* struct inode */
#include <linux/list.h>
#include <linux/path.h> /* struct path */
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/user_namespace.h>
#include <linux/refcount.h>
#include <linux/mempool.h>
#include <linux/sched/mm.h>
/*
* IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
* convert between them. dnotify only needs conversion at watch creation
* so no perf loss there. fanotify isn't defined yet, so it can use the
* wholes if it needs more events.
*/
#define FS_ACCESS 0x00000001 /* File was accessed */
#define FS_MODIFY 0x00000002 /* File was modified */
#define FS_ATTRIB 0x00000004 /* Metadata changed */
#define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */
#define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */
#define FS_OPEN 0x00000020 /* File was opened */
#define FS_MOVED_FROM 0x00000040 /* File was moved from X */
#define FS_MOVED_TO 0x00000080 /* File was moved to Y */
#define FS_CREATE 0x00000100 /* Subfile was created */
#define FS_DELETE 0x00000200 /* Subfile was deleted */
#define FS_DELETE_SELF 0x00000400 /* Self was deleted */
#define FS_MOVE_SELF 0x00000800 /* Self was moved */
#define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */
#define FS_UNMOUNT 0x00002000 /* inode on umount fs */
#define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */
#define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */
/*
* FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify
* which does not support FS_ERROR.
*/
#define FS_IN_IGNORED 0x00008000 /* last inotify event here */
#define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */
#define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */
#define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */
/* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */
#define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */
#define FS_MNT_ATTACH 0x01000000 /* Mount was attached */
#define FS_MNT_DETACH 0x02000000 /* Mount was detached */
#define FS_MNT_MOVE (FS_MNT_ATTACH | FS_MNT_DETACH)
/*
* Set on inode mark that cares about things that happen to its children.
* Always set for dnotify and inotify.
* Set on inode/sb/mount marks that care about parent/name info.
*/
#define FS_EVENT_ON_CHILD 0x08000000
#define FS_RENAME 0x10000000 /* File was renamed */
#define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */
#define FS_ISDIR 0x40000000 /* event occurred against dir */
#define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO)
/*
* Directory entry modification events - reported only to directory
* where entry is modified and not to a watching parent.
* The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event
* when a directory entry inside a child subdir changes.
*/
#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME)
/* Mount namespace events */
#define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH)
/* Content events can be used to inspect file content */
#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \
FS_ACCESS_PERM)
/* Pre-content events can be used to fill file content */
#define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS)
#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \
FSNOTIFY_PRE_CONTENT_EVENTS)
/*
* This is a list of all events that may get sent to a parent that is watching
* with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory.
*/
#define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \
FS_ACCESS | FS_MODIFY | FS_ATTRIB | \
FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \
FS_OPEN | FS_OPEN_EXEC)
/*
* This is a list of all events that may get sent with the parent inode as the
* @to_tell argument of fsnotify().
* It may include events that can be sent to an inode/sb/mount mark, but cannot
* be sent to a parent watching children.
*/
#define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD)
/* Events that can be reported to backends */
#define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
FSNOTIFY_MNT_EVENTS | \
FS_EVENTS_POSS_ON_CHILD | \
FS_DELETE_SELF | FS_MOVE_SELF | \
FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
FS_ERROR)
/* Extra flags that may be reported with event or control handling of events */
#define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT)
#define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS)
struct fsnotify_group;
struct fsnotify_event;
struct fsnotify_mark;
struct fsnotify_event_private_data;
struct fsnotify_fname;
struct fsnotify_iter_info;
struct mem_cgroup;
/*
* Each group much define these ops. The fsnotify infrastructure will call
* these operations for each relevant group.
*
* handle_event - main call for a group to handle an fs event
* @group: group to notify
* @mask: event type and flags
* @data: object that event happened on
* @data_type: type of object for fanotify_data_XXX() accessors
* @dir: optional directory associated with event -
* if @file_name is not NULL, this is the directory that
* @file_name is relative to
* @file_name: optional file name associated with event
* @cookie: inotify rename cookie
* @iter_info: array of marks from this group that are interested in the event
*
* handle_inode_event - simple variant of handle_event() for groups that only
* have inode marks and don't have ignore mask
* @mark: mark to notify
* @mask: event type and flags
* @inode: inode that event happened on
* @dir: optional directory associated with event -
* if @file_name is not NULL, this is the directory that
* @file_name is relative to.
* Either @inode or @dir must be non-NULL.
* @file_name: optional file name associated with event
* @cookie: inotify rename cookie
*
* free_group_priv - called when a group refcnt hits 0 to clean up the private union
* freeing_mark - called when a mark is being destroyed for some reason. The group
* MUST be holding a reference on each mark and that reference must be
* dropped in this function. inotify uses this function to send
* userspace messages that marks have been removed.
*/
struct fsnotify_ops {
int (*handle_event)(struct fsnotify_group *group, u32 mask,
const void *data, int data_type, struct inode *dir,
const struct qstr *file_name, u32 cookie,
struct fsnotify_iter_info *iter_info);
int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask,
struct inode *inode, struct inode *dir,
const struct qstr *file_name, u32 cookie);
void (*free_group_priv)(struct fsnotify_group *group);
void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event);
/* called on final put+free to free memory */
void (*free_mark)(struct fsnotify_mark *mark);
};
/*
* all of the information about the original object we want to now send to
* a group. If you want to carry more info from the accessing task to the
* listener this structure is where you need to be adding fields.
*/
struct fsnotify_event {
struct list_head list;
};
/*
* fsnotify group priorities.
* Events are sent in order from highest priority to lowest priority.
*/
enum fsnotify_group_prio {
FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */
FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */
FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */
__FSNOTIFY_PRIO_NUM
};
/*
* A group is a "thing" that wants to receive notification about filesystem
* events. The mask holds the subset of event types this group cares about.
* refcnt on a group is up to the implementor and at any moment if it goes 0
* everything will be cleaned up.
*/
struct fsnotify_group {
const struct fsnotify_ops *ops; /* how this group handles things */
/*
* How the refcnt is used is up to each group. When the refcnt hits 0
* fsnotify will clean up all of the resources associated with this group.
* As an example, the dnotify group will always have a refcnt=1 and that
* will never change. Inotify, on the other hand, has a group per
* inotify_init() and the refcnt will hit 0 only when that fd has been
* closed.
*/
refcount_t refcnt; /* things with interest in this group */
/* needed to send notification to userspace */
spinlock_t notification_lock; /* protect the notification_list */
struct list_head notification_list; /* list of event_holder this group needs to send to userspace */
wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */
unsigned int q_len; /* events on the queue */
unsigned int max_events; /* maximum events allowed on the list */
enum fsnotify_group_prio priority; /* priority for sending events */
bool shutdown; /* group is being shut down, don't queue more events */
#define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */
#define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */
int flags;
unsigned int owner_flags; /* stored flags of mark_mutex owner */
/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
struct mutex mark_mutex; /* protect marks_list */
atomic_t user_waits; /* Number of tasks waiting for user
* response */
struct list_head marks_list; /* all inode marks for this group */
struct fasync_struct *fsn_fa; /* async notification */
struct fsnotify_event *overflow_event; /* Event we queue when the
* notification list is too
* full */
struct mem_cgroup *memcg; /* memcg to charge allocations */
/* groups can define private fields here or use the void *private */
union {
void *private;
#ifdef CONFIG_INOTIFY_USER
struct inotify_group_private_data {
spinlock_t idr_lock;
struct idr idr;
struct ucounts *ucounts;
} inotify_data;
#endif
#ifdef CONFIG_FANOTIFY
struct fanotify_group_private_data {
/* Hash table of events for merge */
struct hlist_head *merge_hash;
/* allows a group to block waiting for a userspace response */
struct list_head access_list;
wait_queue_head_t access_waitq;
int flags; /* flags from fanotify_init() */
int f_flags; /* event_f_flags from fanotify_init() */
struct ucounts *ucounts;
mempool_t error_events_pool;
} fanotify_data;
#endif /* CONFIG_FANOTIFY */
};
};
/*
* These helpers are used to prevent deadlock when reclaiming inodes with
* evictable marks of the same group that is allocating a new mark.
*/
static inline void fsnotify_group_lock(struct fsnotify_group *group)
{
mutex_lock(&group->mark_mutex);
group->owner_flags = memalloc_nofs_save();
}
static inline void fsnotify_group_unlock(struct fsnotify_group *group)
{
memalloc_nofs_restore(group->owner_flags);
mutex_unlock(&group->mark_mutex);
}
static inline void fsnotify_group_assert_locked(struct fsnotify_group *group)
{
WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
}
/* When calling fsnotify tell it if the data is a path or inode */
enum fsnotify_data_type {
FSNOTIFY_EVENT_NONE,
FSNOTIFY_EVENT_FILE_RANGE,
FSNOTIFY_EVENT_PATH,
FSNOTIFY_EVENT_INODE,
FSNOTIFY_EVENT_DENTRY,
FSNOTIFY_EVENT_MNT,
FSNOTIFY_EVENT_ERROR,
};
struct fs_error_report {
int error;
struct inode *inode;
struct super_block *sb;
};
struct file_range {
const struct path *path;
loff_t pos;
size_t count;
};
static inline const struct path *file_range_path(const struct file_range *range)
{
return range->path;
}
struct fsnotify_mnt {
const struct mnt_namespace *ns;
u64 mnt_id;
};
static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_INODE:
return (struct inode *)data;
case FSNOTIFY_EVENT_DENTRY:
return d_inode(data);
case FSNOTIFY_EVENT_PATH:
return d_inode(((const struct path *)data)->dentry);
case FSNOTIFY_EVENT_FILE_RANGE:
return d_inode(file_range_path(data)->dentry);
case FSNOTIFY_EVENT_ERROR:
return ((struct fs_error_report *)data)->inode;
default:
return NULL;
}
}
static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_DENTRY:
/* Non const is needed for dget() */
return (struct dentry *)data;
case FSNOTIFY_EVENT_PATH:
return ((const struct path *)data)->dentry;
case FSNOTIFY_EVENT_FILE_RANGE:
return file_range_path(data)->dentry;
default:
return NULL;
}
}
static inline const struct path *fsnotify_data_path(const void *data,
int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_PATH:
return data;
case FSNOTIFY_EVENT_FILE_RANGE:
return file_range_path(data);
default:
return NULL;
}
}
static inline struct super_block *fsnotify_data_sb(const void *data,
int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_INODE:
return ((struct inode *)data)->i_sb;
case FSNOTIFY_EVENT_DENTRY:
return ((struct dentry *)data)->d_sb;
case FSNOTIFY_EVENT_PATH:
return ((const struct path *)data)->dentry->d_sb;
case FSNOTIFY_EVENT_FILE_RANGE:
return file_range_path(data)->dentry->d_sb;
case FSNOTIFY_EVENT_ERROR:
return ((struct fs_error_report *) data)->sb;
default:
return NULL;
}
}
static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data,
int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_MNT:
return data;
default:
return NULL;
}
}
static inline u64 fsnotify_data_mnt_id(const void *data, int data_type)
{
const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
return mnt_data ? mnt_data->mnt_id : 0;
}
static inline struct fs_error_report *fsnotify_data_error_report(
const void *data,
int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_ERROR:
return (struct fs_error_report *) data;
default:
return NULL;
}
}
static inline const struct file_range *fsnotify_data_file_range(
const void *data,
int data_type)
{
switch (data_type) {
case FSNOTIFY_EVENT_FILE_RANGE:
return (struct file_range *)data;
default:
return NULL;
}
}
/*
* Index to merged marks iterator array that correlates to a type of watch.
* The type of watched object can be deduced from the iterator type, but not
* the other way around, because an event can match different watched objects
* of the same object type.
* For example, both parent and child are watching an object of type inode.
*/
enum fsnotify_iter_type {
FSNOTIFY_ITER_TYPE_INODE,
FSNOTIFY_ITER_TYPE_VFSMOUNT,
FSNOTIFY_ITER_TYPE_SB,
FSNOTIFY_ITER_TYPE_PARENT,
FSNOTIFY_ITER_TYPE_INODE2,
FSNOTIFY_ITER_TYPE_MNTNS,
FSNOTIFY_ITER_TYPE_COUNT
};
/* The type of object that a mark is attached to */
enum fsnotify_obj_type {
FSNOTIFY_OBJ_TYPE_ANY = -1,
FSNOTIFY_OBJ_TYPE_INODE,
FSNOTIFY_OBJ_TYPE_VFSMOUNT,
FSNOTIFY_OBJ_TYPE_SB,
FSNOTIFY_OBJ_TYPE_MNTNS,
FSNOTIFY_OBJ_TYPE_COUNT,
FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT
};
static inline bool fsnotify_valid_obj_type(unsigned int obj_type)
{
return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT);
}
struct fsnotify_iter_info {
struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT];
struct fsnotify_group *current_group;
unsigned int report_mask;
int srcu_idx;
};
static inline bool fsnotify_iter_should_report_type(
struct fsnotify_iter_info *iter_info, int iter_type)
{
return (iter_info->report_mask & (1U << iter_type));
}
static inline void fsnotify_iter_set_report_type(
struct fsnotify_iter_info *iter_info, int iter_type)
{
iter_info->report_mask |= (1U << iter_type);
}
static inline struct fsnotify_mark *fsnotify_iter_mark(
struct fsnotify_iter_info *iter_info, int iter_type)
{
if (fsnotify_iter_should_report_type(iter_info, iter_type))
return iter_info->marks[iter_type];
return NULL;
}
static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type,
struct fsnotify_mark **markp)
{
while (type < FSNOTIFY_ITER_TYPE_COUNT) {
*markp = fsnotify_iter_mark(iter, type);
if (*markp)
break;
type++;
}
return type;
}
#define FSNOTIFY_ITER_FUNCS(name, NAME) \
static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
struct fsnotify_iter_info *iter_info) \
{ \
return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \
}
FSNOTIFY_ITER_FUNCS(inode, INODE)
FSNOTIFY_ITER_FUNCS(parent, PARENT)
FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT)
FSNOTIFY_ITER_FUNCS(sb, SB)
#define fsnotify_foreach_iter_type(type) \
for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++)
#define fsnotify_foreach_iter_mark_type(iter, mark, type) \
for (type = 0; \
type = fsnotify_iter_step(iter, type, &mark), \
type < FSNOTIFY_ITER_TYPE_COUNT; \
type++)
/*
* Inode/vfsmount/sb point to this structure which tracks all marks attached to
* the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this
* structure. We destroy this structure when there are no more marks attached
* to it. The structure is protected by fsnotify_mark_srcu.
*/
struct fsnotify_mark_connector {
spinlock_t lock;
unsigned char type; /* Type of object [lock] */
unsigned char prio; /* Highest priority group */
#define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01
#define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02
unsigned short flags; /* flags [lock] */
union {
/* Object pointer [lock] */
void *obj;
/* Used listing heads to free after srcu period expires */
struct fsnotify_mark_connector *destroy_next;
};
struct hlist_head list;
};
/*
* Container for per-sb fsnotify state (sb marks and more).
* Attached lazily on first marked object on the sb and freed when killing sb.
*/
struct fsnotify_sb_info {
struct fsnotify_mark_connector __rcu *sb_marks;
/*
* Number of inode/mount/sb objects that are being watched in this sb.
* Note that inodes objects are currently double-accounted.
*
* The value in watched_objects[prio] is the number of objects that are
* watched by groups of priority >= prio, so watched_objects[0] is the
* total number of watched objects in this sb.
*/
atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM];
};
static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb)
{
#ifdef CONFIG_FSNOTIFY
return READ_ONCE(sb->s_fsnotify_info);
#else
return NULL;
#endif
}
static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb)
{
return &fsnotify_sb_info(sb)->watched_objects[0];
}
/*
* A mark is simply an object attached to an in core inode which allows an
* fsnotify listener to indicate they are either no longer interested in events
* of a type matching mask or only interested in those events.
*
* These are flushed when an inode is evicted from core and may be flushed
* when the inode is modified (as seen by fsnotify_access). Some fsnotify
* users (such as dnotify) will flush these when the open fd is closed and not
* at inode eviction or modification.
*
* Text in brackets is showing the lock(s) protecting modifications of a
* particular entry. obj_lock means either inode->i_lock or
* mnt->mnt_root->d_lock depending on the mark type.
*/
struct fsnotify_mark {
/* Mask this mark is for [mark->lock, group->mark_mutex] */
__u32 mask;
/* We hold one for presence in g_list. Also one ref for each 'thing'
* in kernel that found and may be using this mark. */
refcount_t refcnt;
/* Group this mark is for. Set on mark creation, stable until last ref
* is dropped */
struct fsnotify_group *group;
/* List of marks by group->marks_list. Also reused for queueing
* mark into destroy_list when it's waiting for the end of SRCU period
* before it can be freed. [group->mark_mutex] */
struct list_head g_list;
/* Protects inode / mnt pointers, flags, masks */
spinlock_t lock;
/* List of marks for inode / vfsmount [connector->lock, mark ref] */
struct hlist_node obj_list;
/* Head of list of marks for an object [mark ref] */
struct fsnotify_mark_connector *connector;
/* Events types and flags to ignore [mark->lock, group->mark_mutex] */
__u32 ignore_mask;
/* General fsnotify mark flags */
#define FSNOTIFY_MARK_FLAG_ALIVE 0x0001
#define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002
/* inotify mark flags */
#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010
#define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020
/* fanotify mark flags */
#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100
#define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200
#define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400
#define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800
#define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000
unsigned int flags; /* flags [mark->lock] */
};
#ifdef CONFIG_FSNOTIFY
/* called from the vfs helpers */
/* main fsnotify call to send events */
extern int fsnotify(__u32 mask, const void *data, int data_type,
struct inode *dir, const struct qstr *name,
struct inode *inode, u32 cookie);
extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
int data_type);
extern void __fsnotify_inode_delete(struct inode *inode);
extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
extern void fsnotify_sb_delete(struct super_block *sb);
extern void __fsnotify_mntns_delete(struct mnt_namespace *mntns);
extern void fsnotify_sb_free(struct super_block *sb);
extern u32 fsnotify_get_cookie(void);
extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt);
static inline __u32 fsnotify_parent_needed_mask(__u32 mask)
{
/* FS_EVENT_ON_CHILD is set on marks that want parent/name info */
if (!(mask & FS_EVENT_ON_CHILD))
return 0;
/*
* This object might be watched by a mark that cares about parent/name
* info, does it care about the specific set of events that can be
* reported with parent/name info?
*/
return mask & FS_EVENTS_POSS_TO_PARENT;
}
static inline int fsnotify_inode_watches_children(struct inode *inode)
{
__u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask);
/* FS_EVENT_ON_CHILD is set if the inode may care */
if (!(parent_mask & FS_EVENT_ON_CHILD))
return 0;
/* this inode might care about child events, does it care about the
* specific set of events that can happen on a child? */
return parent_mask & FS_EVENTS_POSS_ON_CHILD;
}
/*
* Update the dentry with a flag indicating the interest of its parent to receive
* filesystem events when those events happens to this dentry->d_inode.
*/
static inline void fsnotify_update_flags(struct dentry *dentry)
{
assert_spin_locked(&dentry->d_lock);
/*
* Serialisation of setting PARENT_WATCHED on the dentries is provided
* by d_lock. If inotify_inode_watched changes after we have taken
* d_lock, the following fsnotify_set_children_dentry_flags call will
* find our entry, so it will spin until we complete here, and update
* us with the new state.
*/
if (fsnotify_inode_watches_children(dentry->d_parent->d_inode))
dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
else
dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
}
/* called from fsnotify listeners, such as fanotify or dnotify */
/* create a new group */
extern struct fsnotify_group *fsnotify_alloc_group(
const struct fsnotify_ops *ops,
int flags);
/* get reference to a group */
extern void fsnotify_get_group(struct fsnotify_group *group);
/* drop reference on a group from fsnotify_alloc_group */
extern void fsnotify_put_group(struct fsnotify_group *group);
/* group destruction begins, stop queuing new events */
extern void fsnotify_group_stop_queueing(struct fsnotify_group *group);
/* destroy group */
extern void fsnotify_destroy_group(struct fsnotify_group *group);
/* fasync handler function */
extern int fsnotify_fasync(int fd, struct file *file, int on);
/* Free event from memory */
extern void fsnotify_destroy_event(struct fsnotify_group *group,
struct fsnotify_event *event);
/* attach the event to the group notification queue */
extern int fsnotify_insert_event(struct fsnotify_group *group,
struct fsnotify_event *event,
int (*merge)(struct fsnotify_group *,
struct fsnotify_event *),
void (*insert)(struct fsnotify_group *,
struct fsnotify_event *));
static inline int fsnotify_add_event(struct fsnotify_group *group,
struct fsnotify_event *event,
int (*merge)(struct fsnotify_group *,
struct fsnotify_event *))
{
return fsnotify_insert_event(group, event, merge, NULL);
}
/* Queue overflow event to a notification group */
static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
{
fsnotify_add_event(group, group->overflow_event, NULL);
}
static inline bool fsnotify_is_overflow_event(u32 mask)
{
return mask & FS_Q_OVERFLOW;
}
static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)
{
assert_spin_locked(&group->notification_lock);
return list_empty(&group->notification_list);
}
extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
/* return, but do not dequeue the first event on the notification queue */
extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group);
/* return AND dequeue the first event on the notification queue */
extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group);
/* Remove event queued in the notification list */
extern void fsnotify_remove_queued_event(struct fsnotify_group *group,
struct fsnotify_event *event);
/* functions used to manipulate the marks attached to inodes */
/*
* Canonical "ignore mask" including event flags.
*
* Note the subtle semantic difference from the legacy ->ignored_mask.
* ->ignored_mask traditionally only meant which events should be ignored,
* while ->ignore_mask also includes flags regarding the type of objects on
* which events should be ignored.
*/
static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark)
{
__u32 ignore_mask = mark->ignore_mask;
/* The event flags in ignore mask take effect */
if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
return ignore_mask;
/*
* Legacy behavior:
* - Always ignore events on dir
* - Ignore events on child if parent is watching children
*/
ignore_mask |= FS_ISDIR;
ignore_mask &= ~FS_EVENT_ON_CHILD;
ignore_mask |= mark->mask & FS_EVENT_ON_CHILD;
return ignore_mask;
}
/* Legacy ignored_mask - only event types to ignore */
static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark)
{
return mark->ignore_mask & ALL_FSNOTIFY_EVENTS;
}
/*
* Check if mask (or ignore mask) should be applied depending if victim is a
* directory and whether it is reported to a watching parent.
*/
static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir,
int iter_type)
{
/* Should mask be applied to a directory? */
if (is_dir && !(mask & FS_ISDIR))
return false;
/* Should mask be applied to a child? */
if (iter_type == FSNOTIFY_ITER_TYPE_PARENT &&
!(mask & FS_EVENT_ON_CHILD))
return false;
return true;
}
/*
* Effective ignore mask taking into account if event victim is a
* directory and whether it is reported to a watching parent.
*/
static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark,
bool is_dir, int iter_type)
{
__u32 ignore_mask = fsnotify_ignored_events(mark);
if (!ignore_mask)
return 0;
/* For non-dir and non-child, no need to consult the event flags */
if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT)
return ignore_mask;
ignore_mask = fsnotify_ignore_mask(mark);
if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type))
return 0;
return ignore_mask & ALL_FSNOTIFY_EVENTS;
}
/* Get mask for calculating object interest taking ignore mask into account */
static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark)
{
__u32 mask = mark->mask;
if (!fsnotify_ignored_events(mark))
return mask;
/* Interest in FS_MODIFY may be needed for clearing ignore mask */
if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
mask |= FS_MODIFY;
/*
* If mark is interested in ignoring events on children, the object must
* show interest in those events for fsnotify_parent() to notice it.
*/
return mask | mark->ignore_mask;
}
/* Get mask of events for a list of marks */
extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn);
/* Calculate mask of events for a list of marks */
extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
extern void fsnotify_init_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group);
/* Find mark belonging to given group in the list of marks */
struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type,
struct fsnotify_group *group);
/* attach the mark to the object */
int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags);
int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags);
/* attach the mark to the inode */
static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
struct inode *inode,
int add_flags)
{
return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE,
add_flags);
}
static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
struct inode *inode,
int add_flags)
{
return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE,
add_flags);
}
static inline struct fsnotify_mark *fsnotify_find_inode_mark(
struct inode *inode,
struct fsnotify_group *group)
{
return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group);
}
/* given a group and a mark, flag mark to be freed when all references are dropped */
extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
struct fsnotify_group *group);
/* detach mark from inode / mount list, group list, drop inode reference */
extern void fsnotify_detach_mark(struct fsnotify_mark *mark);
/* free mark */
extern void fsnotify_free_mark(struct fsnotify_mark *mark);
/* Wait until all marks queued for destruction are destroyed */
extern void fsnotify_wait_marks_destroyed(void);
/* Clear all of the marks of a group attached to a given object type */
extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
unsigned int obj_type);
/* run all the marks in a group, and clear all of the vfsmount marks */
static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
{
fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
}
/* run all the marks in a group, and clear all of the inode marks */
static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
{
fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
}
/* run all the marks in a group, and clear all of the sn marks */
static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
{
fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB);
}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
static inline void fsnotify_init_event(struct fsnotify_event *event)
{
INIT_LIST_HEAD(&event->list);
}
int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
size_t count);
#else
static inline int fsnotify_pre_content(const struct path *path,
const loff_t *ppos, size_t count)
{
return 0;
}
static inline int fsnotify(__u32 mask, const void *data, int data_type,
struct inode *dir, const struct qstr *name,
struct inode *inode, u32 cookie)
{
return 0;
}
static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask,
const void *data, int data_type)
{
return 0;
}
static inline void __fsnotify_inode_delete(struct inode *inode)
{}
static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
{}
static inline void fsnotify_sb_delete(struct super_block *sb)
{}
static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
{}
static inline void fsnotify_sb_free(struct super_block *sb)
{}
static inline void fsnotify_update_flags(struct dentry *dentry)
{}
static inline u32 fsnotify_get_cookie(void)
{
return 0;
}
static inline void fsnotify_unmount_inodes(struct super_block *sb)
{}
static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
{}
#endif /* CONFIG_FSNOTIFY */
#endif /* __KERNEL __ */
#endif /* __LINUX_FSNOTIFY_BACKEND_H */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* A hash table (hashtab) maintains associations between
* key values and datum values. The type of the key values
* and the type of the datum values is arbitrary. The
* functions for hash computation and key comparison are
* provided by the creator of the table.
*
* Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
*/
#ifndef _SS_HASHTAB_H_
#define _SS_HASHTAB_H_
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/sched.h>
#define HASHTAB_MAX_NODES U32_MAX
struct hashtab_key_params {
u32 (*hash)(const void *key); /* hash func */
int (*cmp)(const void *key1, const void *key2); /* comparison func */
};
struct hashtab_node {
void *key;
void *datum;
struct hashtab_node *next;
};
struct hashtab {
struct hashtab_node **htable; /* hash table */
u32 size; /* number of slots in hash table */
u32 nel; /* number of elements in hash table */
};
struct hashtab_info {
u32 slots_used;
u32 max_chain_len;
u64 chain2_len_sum;
};
/*
* Initializes a new hash table with the specified characteristics.
*
* Returns -ENOMEM if insufficient space is available or 0 otherwise.
*/
int hashtab_init(struct hashtab *h, u32 nel_hint);
int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key,
void *datum);
/*
* Inserts the specified (key, datum) pair into the specified hash table.
*
* Returns -ENOMEM on memory allocation error,
* -EEXIST if there is already an entry with the same key,
* -EINVAL for general errors or
0 otherwise.
*/
static inline int hashtab_insert(struct hashtab *h, void *key, void *datum,
struct hashtab_key_params key_params)
{
u32 hvalue;
struct hashtab_node *prev, *cur;
cond_resched();
if (!h->size || h->nel == HASHTAB_MAX_NODES)
return -EINVAL;
hvalue = key_params.hash(key) & (h->size - 1);
prev = NULL;
cur = h->htable[hvalue];
while (cur) {
int cmp = key_params.cmp(key, cur->key);
if (cmp == 0)
return -EEXIST;
if (cmp < 0)
break;
prev = cur;
cur = cur->next;
}
return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key,
datum);
}
/*
* Searches for the entry with the specified key in the hash table.
*
* Returns NULL if no entry has the specified key or
* the datum of the entry otherwise.
*/
static inline void *hashtab_search(struct hashtab *h, const void *key,
struct hashtab_key_params key_params)
{
u32 hvalue;
struct hashtab_node *cur;
if (!h->size)
return NULL;
hvalue = key_params.hash(key) & (h->size - 1);
cur = h->htable[hvalue];
while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0)
break;
cur = cur->next;
}
return NULL;
}
/*
* Destroys the specified hash table.
*/
void hashtab_destroy(struct hashtab *h);
/*
* Applies the specified apply function to (key,datum,args)
* for each entry in the specified hash table.
*
* The order in which the function is applied to the entries
* is dependent upon the internal structure of the hash table.
*
* If apply returns a non-zero status, then hashtab_map will cease
* iterating through the hash table and will propagate the error
* return to its caller.
*/
int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args),
void *args);
int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig,
int (*copy)(struct hashtab_node *new,
const struct hashtab_node *orig, void *args),
int (*destroy)(void *k, void *d, void *args), void *args);
#ifdef CONFIG_SECURITY_SELINUX_DEBUG
/* Fill info with some hash table statistics */
void hashtab_stat(struct hashtab *h, struct hashtab_info *info);
#else
static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info)
{
return;
}
#endif
#endif /* _SS_HASHTAB_H */
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/tlbflush.h
*
* Copyright (C) 1999-2003 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_TLBFLUSH_H
#define __ASM_TLBFLUSH_H
#ifndef __ASSEMBLY__
#include <linux/bitfield.h>
#include <linux/mm_types.h>
#include <linux/sched.h>
#include <linux/mmu_notifier.h>
#include <asm/cputype.h>
#include <asm/mmu.h>
/*
* Raw TLBI operations.
*
* Where necessary, use the __tlbi() macro to avoid asm()
* boilerplate. Drivers and most kernel code should use the TLB
* management routines in preference to the macro below.
*
* The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
* on whether a particular TLBI operation takes an argument or
* not. The macros handles invoking the asm with or without the
* register argument as appropriate.
*/
#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \
"tlbi " #op "\n" \
ALTERNATIVE("nop\n nop", \
"dsb ish\n tlbi " #op, \
ARM64_WORKAROUND_REPEAT_TLBI, \
CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \
: : )
#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \
"tlbi " #op ", %0\n" \
ALTERNATIVE("nop\n nop", \
"dsb ish\n tlbi " #op ", %0", \
ARM64_WORKAROUND_REPEAT_TLBI, \
CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \
: : "r" (arg))
#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0)
#define __tlbi_user(op, arg) do { \
if (arm64_kernel_unmapped_at_el0()) \
__tlbi(op, (arg) | USER_ASID_FLAG); \
} while (0)
/* This macro creates a properly formatted VA operand for the TLBI */
#define __TLBI_VADDR(addr, asid) \
({ \
unsigned long __ta = (addr) >> 12; \
__ta &= GENMASK_ULL(43, 0); \
__ta |= (unsigned long)(asid) << 48; \
__ta; \
})
/*
* Get translation granule of the system, which is decided by
* PAGE_SIZE. Used by TTL.
* - 4KB : 1
* - 16KB : 2
* - 64KB : 3
*/
#define TLBI_TTL_TG_4K 1
#define TLBI_TTL_TG_16K 2
#define TLBI_TTL_TG_64K 3
static inline unsigned long get_trans_granule(void)
{
switch (PAGE_SIZE) {
case SZ_4K:
return TLBI_TTL_TG_4K;
case SZ_16K:
return TLBI_TTL_TG_16K;
case SZ_64K:
return TLBI_TTL_TG_64K;
default:
return 0;
}
}
/*
* Level-based TLBI operations.
*
* When ARMv8.4-TTL exists, TLBI operations take an additional hint for
* the level at which the invalidation must take place. If the level is
* wrong, no invalidation may take place. In the case where the level
* cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform
* a non-hinted invalidation. Any provided level outside the hint range
* will also cause fall-back to non-hinted invalidation.
*
* For Stage-2 invalidation, use the level values provided to that effect
* in asm/stage2_pgtable.h.
*/
#define TLBI_TTL_MASK GENMASK_ULL(47, 44)
#define TLBI_TTL_UNKNOWN INT_MAX
#define __tlbi_level(op, addr, level) do { \
u64 arg = addr; \
\
if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) && \
level >= 0 && level <= 3) { \
u64 ttl = level & 3; \
ttl |= get_trans_granule() << 2; \
arg &= ~TLBI_TTL_MASK; \
arg |= FIELD_PREP(TLBI_TTL_MASK, ttl); \
} \
\
__tlbi(op, arg); \
} while(0)
#define __tlbi_user_level(op, arg, level) do { \
if (arm64_kernel_unmapped_at_el0()) \
__tlbi_level(op, (arg | USER_ASID_FLAG), level); \
} while (0)
/*
* This macro creates a properly formatted VA operand for the TLB RANGE. The
* value bit assignments are:
*
* +----------+------+-------+-------+-------+----------------------+
* | ASID | TG | SCALE | NUM | TTL | BADDR |
* +-----------------+-------+-------+-------+----------------------+
* |63 48|47 46|45 44|43 39|38 37|36 0|
*
* The address range is determined by below formula: [BADDR, BADDR + (NUM + 1) *
* 2^(5*SCALE + 1) * PAGESIZE)
*
* Note that the first argument, baddr, is pre-shifted; If LPA2 is in use, BADDR
* holds addr[52:16]. Else BADDR holds page number. See for example ARM DDI
* 0487J.a section C5.5.60 "TLBI VAE1IS, TLBI VAE1ISNXS, TLB Invalidate by VA,
* EL1, Inner Shareable".
*
*/
#define TLBIR_ASID_MASK GENMASK_ULL(63, 48)
#define TLBIR_TG_MASK GENMASK_ULL(47, 46)
#define TLBIR_SCALE_MASK GENMASK_ULL(45, 44)
#define TLBIR_NUM_MASK GENMASK_ULL(43, 39)
#define TLBIR_TTL_MASK GENMASK_ULL(38, 37)
#define TLBIR_BADDR_MASK GENMASK_ULL(36, 0)
#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \
({ \
unsigned long __ta = 0; \
unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \
__ta |= FIELD_PREP(TLBIR_BADDR_MASK, baddr); \
__ta |= FIELD_PREP(TLBIR_TTL_MASK, __ttl); \
__ta |= FIELD_PREP(TLBIR_NUM_MASK, num); \
__ta |= FIELD_PREP(TLBIR_SCALE_MASK, scale); \
__ta |= FIELD_PREP(TLBIR_TG_MASK, get_trans_granule()); \
__ta |= FIELD_PREP(TLBIR_ASID_MASK, asid); \
__ta; \
})
/* These macros are used by the TLBI RANGE feature. */
#define __TLBI_RANGE_PAGES(num, scale) \
((unsigned long)((num) + 1) << (5 * (scale) + 1))
#define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3)
/*
* Generate 'num' values from -1 to 31 with -1 rejected by the
* __flush_tlb_range() loop below. Its return value is only
* significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If
* 'pages' is more than that, you must iterate over the overall
* range.
*/
#define __TLBI_RANGE_NUM(pages, scale) \
({ \
int __pages = min((pages), \
__TLBI_RANGE_PAGES(31, (scale))); \
(__pages >> (5 * (scale) + 1)) - 1; \
})
/*
* TLB Invalidation
* ================
*
* This header file implements the low-level TLB invalidation routines
* (sometimes referred to as "flushing" in the kernel) for arm64.
*
* Every invalidation operation uses the following template:
*
* DSB ISHST // Ensure prior page-table updates have completed
* TLBI ... // Invalidate the TLB
* DSB ISH // Ensure the TLB invalidation has completed
* if (invalidated kernel mappings)
* ISB // Discard any instructions fetched from the old mapping
*
*
* The following functions form part of the "core" TLB invalidation API,
* as documented in Documentation/core-api/cachetlb.rst:
*
* flush_tlb_all()
* Invalidate the entire TLB (kernel + user) on all CPUs
*
* flush_tlb_mm(mm)
* Invalidate an entire user address space on all CPUs.
* The 'mm' argument identifies the ASID to invalidate.
*
* flush_tlb_range(vma, start, end)
* Invalidate the virtual-address range '[start, end)' on all
* CPUs for the user address space corresponding to 'vma->mm'.
* Note that this operation also invalidates any walk-cache
* entries associated with translations for the specified address
* range.
*
* flush_tlb_kernel_range(start, end)
* Same as flush_tlb_range(..., start, end), but applies to
* kernel mappings rather than a particular user address space.
* Whilst not explicitly documented, this function is used when
* unmapping pages from vmalloc/io space.
*
* flush_tlb_page(vma, addr)
* Invalidate a single user mapping for address 'addr' in the
* address space corresponding to 'vma->mm'. Note that this
* operation only invalidates a single, last-level page-table
* entry and therefore does not affect any walk-caches.
*
*
* Next, we have some undocumented invalidation routines that you probably
* don't want to call unless you know what you're doing:
*
* local_flush_tlb_all()
* Same as flush_tlb_all(), but only applies to the calling CPU.
*
* __flush_tlb_kernel_pgtable(addr)
* Invalidate a single kernel mapping for address 'addr' on all
* CPUs, ensuring that any walk-cache entries associated with the
* translation are also invalidated.
*
* __flush_tlb_range(vma, start, end, stride, last_level, tlb_level)
* Invalidate the virtual-address range '[start, end)' on all
* CPUs for the user address space corresponding to 'vma->mm'.
* The invalidation operations are issued at a granularity
* determined by 'stride' and only affect any walk-cache entries
* if 'last_level' is equal to false. tlb_level is the level at
* which the invalidation must take place. If the level is wrong,
* no invalidation may take place. In the case where the level
* cannot be easily determined, the value TLBI_TTL_UNKNOWN will
* perform a non-hinted invalidation.
*
*
* Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
* on top of these routines, since that is our interface to the mmu_gather
* API as used by munmap() and friends.
*/
static inline void local_flush_tlb_all(void)
{
dsb(nshst);
__tlbi(vmalle1);
dsb(nsh);
isb();
}
static inline void flush_tlb_all(void)
{
dsb(ishst);
__tlbi(vmalle1is);
dsb(ish);
isb();
}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
unsigned long asid;
dsb(ishst);
asid = __TLBI_VADDR(0, ASID(mm));
__tlbi(aside1is, asid);
__tlbi_user(aside1is, asid);
dsb(ish);
mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
}
static inline void __flush_tlb_page_nosync(struct mm_struct *mm,
unsigned long uaddr)
{
unsigned long addr;
dsb(ishst);
addr = __TLBI_VADDR(uaddr, ASID(mm));
__tlbi(vale1is, addr);
__tlbi_user(vale1is, addr); mmu_notifier_arch_invalidate_secondary_tlbs(mm, uaddr & PAGE_MASK,
(uaddr & PAGE_MASK) + PAGE_SIZE);
}
static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
unsigned long uaddr)
{
return __flush_tlb_page_nosync(vma->vm_mm, uaddr);
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long uaddr)
{
flush_tlb_page_nosync(vma, uaddr);
dsb(ish);
}
static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
{
/*
* TLB flush deferral is not required on systems which are affected by
* ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
* will have two consecutive TLBI instructions with a dsb(ish) in between
* defeating the purpose (i.e save overall 'dsb ish' cost).
*/
if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
return false;
return true;
}
/*
* If mprotect/munmap/etc occurs during TLB batched flushing, we need to
* synchronise all the TLBI issued with a DSB to avoid the race mentioned in
* flush_tlb_batched_pending().
*/
static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
{
dsb(ish);
}
/*
* To support TLB batched flush for multiple pages unmapping, we only send
* the TLBI for each page in arch_tlbbatch_add_pending() and wait for the
* completion at the end in arch_tlbbatch_flush(). Since we've already issued
* TLBI for each page so only a DSB is needed to synchronise its effect on the
* other CPUs.
*
* This will save the time waiting on DSB comparing issuing a TLBI;DSB sequence
* for each page.
*/
static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
dsb(ish);
}
/*
* This is meant to avoid soft lock-ups on large TLB flushing ranges and not
* necessarily a performance improvement.
*/
#define MAX_DVM_OPS PTRS_PER_PTE
/*
* __flush_tlb_range_op - Perform TLBI operation upon a range
*
* @op: TLBI instruction that operates on a range (has 'r' prefix)
* @start: The start address of the range
* @pages: Range as the number of pages from 'start'
* @stride: Flush granularity
* @asid: The ASID of the task (0 for IPA instructions)
* @tlb_level: Translation Table level hint, if known
* @tlbi_user: If 'true', call an additional __tlbi_user()
* (typically for user ASIDs). 'flase' for IPA instructions
* @lpa2: If 'true', the lpa2 scheme is used as set out below
*
* When the CPU does not support TLB range operations, flush the TLB
* entries one by one at the granularity of 'stride'. If the TLB
* range ops are supported, then:
*
* 1. If FEAT_LPA2 is in use, the start address of a range operation must be
* 64KB aligned, so flush pages one by one until the alignment is reached
* using the non-range operations. This step is skipped if LPA2 is not in
* use.
*
* 2. The minimum range granularity is decided by 'scale', so multiple range
* TLBI operations may be required. Start from scale = 3, flush the largest
* possible number of pages ((num+1)*2^(5*scale+1)) that fit into the
* requested range, then decrement scale and continue until one or zero pages
* are left. We must start from highest scale to ensure 64KB start alignment
* is maintained in the LPA2 case.
*
* 3. If there is 1 page remaining, flush it through non-range operations. Range
* operations can only span an even number of pages. We save this for last to
* ensure 64KB start alignment is maintained for the LPA2 case.
*/
#define __flush_tlb_range_op(op, start, pages, stride, \
asid, tlb_level, tlbi_user, lpa2) \
do { \
typeof(start) __flush_start = start; \
typeof(pages) __flush_pages = pages; \
int num = 0; \
int scale = 3; \
int shift = lpa2 ? 16 : PAGE_SHIFT; \
unsigned long addr; \
\
while (__flush_pages > 0) { \
if (!system_supports_tlb_range() || \
__flush_pages == 1 || \
(lpa2 && __flush_start != ALIGN(__flush_start, SZ_64K))) { \
addr = __TLBI_VADDR(__flush_start, asid); \
__tlbi_level(op, addr, tlb_level); \
if (tlbi_user) \
__tlbi_user_level(op, addr, tlb_level); \
__flush_start += stride; \
__flush_pages -= stride >> PAGE_SHIFT; \
continue; \
} \
\
num = __TLBI_RANGE_NUM(__flush_pages, scale); \
if (num >= 0) { \
addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
scale, num, tlb_level); \
__tlbi(r##op, addr); \
if (tlbi_user) \
__tlbi_user(r##op, addr); \
__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
__flush_pages -= __TLBI_RANGE_PAGES(num, scale);\
} \
scale--; \
} \
} while (0)
#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled());
static inline bool __flush_tlb_range_limit_excess(unsigned long start,
unsigned long end, unsigned long pages, unsigned long stride)
{
/*
* When the system does not support TLB range based flush
* operation, (MAX_DVM_OPS - 1) pages can be handled. But
* with TLB range based operation, MAX_TLBI_RANGE_PAGES
* pages can be handled.
*/
if ((!system_supports_tlb_range() && (end - start) >= (MAX_DVM_OPS * stride)) ||
pages > MAX_TLBI_RANGE_PAGES)
return true;
return false;
}
static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
unsigned long start, unsigned long end,
unsigned long stride, bool last_level,
int tlb_level)
{
unsigned long asid, pages;
start = round_down(start, stride);
end = round_up(end, stride);
pages = (end - start) >> PAGE_SHIFT;
if (__flush_tlb_range_limit_excess(start, end, pages, stride)) { flush_tlb_mm(mm);
return;
}
dsb(ishst);
asid = ASID(mm);
if (last_level)
__flush_tlb_range_op(vale1is, start, pages, stride, asid,
tlb_level, true, lpa2_is_enabled());
else
__flush_tlb_range_op(vae1is, start, pages, stride, asid,
tlb_level, true, lpa2_is_enabled());
mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
}
static inline void __flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long stride, bool last_level,
int tlb_level)
{
__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
last_level, tlb_level);
dsb(ish);
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
/*
* We cannot use leaf-only invalidation here, since we may be invalidating
* table entries as part of collapsing hugepages or moving page tables.
* Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough
* information here.
*/
__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
}
static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
const unsigned long stride = PAGE_SIZE;
unsigned long pages;
start = round_down(start, stride);
end = round_up(end, stride);
pages = (end - start) >> PAGE_SHIFT;
if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
flush_tlb_all();
return;
}
dsb(ishst);
__flush_tlb_range_op(vaale1is, start, pages, stride, 0,
TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
dsb(ish);
isb();
}
/*
* Used to invalidate the TLB (walk caches) corresponding to intermediate page
* table levels (pgd/pud/pmd).
*/
static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
{
unsigned long addr = __TLBI_VADDR(kaddr, 0);
dsb(ishst);
__tlbi(vaae1is, addr);
dsb(ish);
isb();
}
static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm, unsigned long start, unsigned long end)
{
__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
}
#endif
#endif
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Fast and scalable bitmaps.
*
* Copyright (C) 2016 Facebook
* Copyright (C) 2013-2014 Jens Axboe
*/
#ifndef __LINUX_SCALE_BITMAP_H
#define __LINUX_SCALE_BITMAP_H
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/log2.h>
#include <linux/minmax.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/types.h>
#include <linux/wait.h>
struct seq_file;
/**
* struct sbitmap_word - Word in a &struct sbitmap.
*/
struct sbitmap_word {
/**
* @word: word holding free bits
*/
unsigned long word;
/**
* @cleared: word holding cleared bits
*/
unsigned long cleared ____cacheline_aligned_in_smp;
/**
* @swap_lock: serializes simultaneous updates of ->word and ->cleared
*/
raw_spinlock_t swap_lock;
} ____cacheline_aligned_in_smp;
/**
* struct sbitmap - Scalable bitmap.
*
* A &struct sbitmap is spread over multiple cachelines to avoid ping-pong. This
* trades off higher memory usage for better scalability.
*/
struct sbitmap {
/**
* @depth: Number of bits used in the whole bitmap.
*/
unsigned int depth;
/**
* @shift: log2(number of bits used per word)
*/
unsigned int shift;
/**
* @map_nr: Number of words (cachelines) being used for the bitmap.
*/
unsigned int map_nr;
/**
* @round_robin: Allocate bits in strict round-robin order.
*/
bool round_robin;
/**
* @map: Allocated bitmap.
*/
struct sbitmap_word *map;
/*
* @alloc_hint: Cache of last successfully allocated or freed bit.
*
* This is per-cpu, which allows multiple users to stick to different
* cachelines until the map is exhausted.
*/
unsigned int __percpu *alloc_hint;
};
#define SBQ_WAIT_QUEUES 8
#define SBQ_WAKE_BATCH 8
/**
* struct sbq_wait_state - Wait queue in a &struct sbitmap_queue.
*/
struct sbq_wait_state {
/**
* @wait: Wait queue.
*/
wait_queue_head_t wait;
} ____cacheline_aligned_in_smp;
/**
* struct sbitmap_queue - Scalable bitmap with the added ability to wait on free
* bits.
*
* A &struct sbitmap_queue uses multiple wait queues and rolling wakeups to
* avoid contention on the wait queue spinlock. This ensures that we don't hit a
* scalability wall when we run out of free bits and have to start putting tasks
* to sleep.
*/
struct sbitmap_queue {
/**
* @sb: Scalable bitmap.
*/
struct sbitmap sb;
/**
* @wake_batch: Number of bits which must be freed before we wake up any
* waiters.
*/
unsigned int wake_batch;
/**
* @wake_index: Next wait queue in @ws to wake up.
*/
atomic_t wake_index;
/**
* @ws: Wait queues.
*/
struct sbq_wait_state *ws;
/*
* @ws_active: count of currently active ws waitqueues
*/
atomic_t ws_active;
/**
* @min_shallow_depth: The minimum shallow depth which may be passed to
* sbitmap_queue_get_shallow()
*/
unsigned int min_shallow_depth;
/**
* @completion_cnt: Number of bits cleared passed to the
* wakeup function.
*/
atomic_t completion_cnt;
/**
* @wakeup_cnt: Number of thread wake ups issued.
*/
atomic_t wakeup_cnt;
};
/**
* sbitmap_init_node() - Initialize a &struct sbitmap on a specific memory node.
* @sb: Bitmap to initialize.
* @depth: Number of bits to allocate.
* @shift: Use 2^@shift bits per word in the bitmap; if a negative number if
* given, a good default is chosen.
* @flags: Allocation flags.
* @node: Memory node to allocate on.
* @round_robin: If true, be stricter about allocation order; always allocate
* starting from the last allocated bit. This is less efficient
* than the default behavior (false).
* @alloc_hint: If true, apply percpu hint for where to start searching for
* a free bit.
*
* Return: Zero on success or negative errno on failure.
*/
int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
gfp_t flags, int node, bool round_robin, bool alloc_hint);
/* sbitmap internal helper */
static inline unsigned int __map_depth(const struct sbitmap *sb, int index)
{
if (index == sb->map_nr - 1)
return sb->depth - (index << sb->shift);
return 1U << sb->shift;
}
/**
* sbitmap_free() - Free memory used by a &struct sbitmap.
* @sb: Bitmap to free.
*/
static inline void sbitmap_free(struct sbitmap *sb)
{
free_percpu(sb->alloc_hint);
kvfree(sb->map);
sb->map = NULL;
}
/**
* sbitmap_resize() - Resize a &struct sbitmap.
* @sb: Bitmap to resize.
* @depth: New number of bits to resize to.
*
* Doesn't reallocate anything. It's up to the caller to ensure that the new
* depth doesn't exceed the depth that the sb was initialized with.
*/
void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
/**
* sbitmap_get() - Try to allocate a free bit from a &struct sbitmap.
* @sb: Bitmap to allocate from.
*
* This operation provides acquire barrier semantics if it succeeds.
*
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
int sbitmap_get(struct sbitmap *sb);
/**
* sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
* limiting the depth used from each word.
* @sb: Bitmap to allocate from.
* @shallow_depth: The maximum number of bits to allocate from a single word.
*
* This rather specific operation allows for having multiple users with
* different allocation limits. E.g., there can be a high-priority class that
* uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
* with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
* class can only allocate half of the total bits in the bitmap, preventing it
* from starving out the high-priority class.
*
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth);
/**
* sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
* @sb: Bitmap to check.
*
* Return: true if any bit in the bitmap is set, false otherwise.
*/
bool sbitmap_any_bit_set(const struct sbitmap *sb);
#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *);
/**
* __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
* @start: Where to start the iteration.
* @sb: Bitmap to iterate over.
* @fn: Callback. Should return true to continue or false to break early.
* @data: Pointer to pass to callback.
*
* This is inline even though it's non-trivial so that the function calls to the
* callback will hopefully get optimized away.
*/
static inline void __sbitmap_for_each_set(struct sbitmap *sb,
unsigned int start,
sb_for_each_fn fn, void *data)
{
unsigned int index;
unsigned int nr;
unsigned int scanned = 0;
if (start >= sb->depth)
start = 0;
index = SB_NR_TO_INDEX(sb, start);
nr = SB_NR_TO_BIT(sb, start);
while (scanned < sb->depth) {
unsigned long word;
unsigned int depth = min_t(unsigned int,
__map_depth(sb, index) - nr,
sb->depth - scanned);
scanned += depth;
word = sb->map[index].word & ~sb->map[index].cleared;
if (!word)
goto next;
/*
* On the first iteration of the outer loop, we need to add the
* bit offset back to the size of the word for find_next_bit().
* On all other iterations, nr is zero, so this is a noop.
*/
depth += nr;
while (1) {
nr = find_next_bit(&word, depth, nr);
if (nr >= depth)
break;
if (!fn(sb, (index << sb->shift) + nr, data))
return;
nr++;
}
next:
nr = 0;
if (++index >= sb->map_nr)
index = 0;
}
}
/**
* sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap.
* @sb: Bitmap to iterate over.
* @fn: Callback. Should return true to continue or false to break early.
* @data: Pointer to pass to callback.
*/
static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn,
void *data)
{
__sbitmap_for_each_set(sb, 0, fn, data);
}
static inline unsigned long *__sbitmap_word(struct sbitmap *sb,
unsigned int bitnr)
{
return &sb->map[SB_NR_TO_INDEX(sb, bitnr)].word;
}
/* Helpers equivalent to the operations in asm/bitops.h and linux/bitmap.h */
static inline void sbitmap_set_bit(struct sbitmap *sb, unsigned int bitnr)
{
set_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
}
static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr)
{
clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
}
/*
* This one is special, since it doesn't actually clear the bit, rather it
* sets the corresponding bit in the ->cleared mask instead. Paired with
* the caller doing sbitmap_deferred_clear() if a given index is full, which
* will clear the previously freed entries in the corresponding ->word.
*/
static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr)
{
unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared;
set_bit(SB_NR_TO_BIT(sb, bitnr), addr);
}
/*
* Pair of sbitmap_get, and this one applies both cleared bit and
* allocation hint.
*/
static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr)
{
sbitmap_deferred_clear_bit(sb, bitnr);
if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth))
*raw_cpu_ptr(sb->alloc_hint) = bitnr;
}
static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
{
return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
}
static inline int sbitmap_calculate_shift(unsigned int depth)
{
int shift = ilog2(BITS_PER_LONG);
/*
* If the bitmap is small, shrink the number of bits per word so
* we spread over a few cachelines, at least. If less than 4
* bits, just forget about it, it's not going to work optimally
* anyway.
*/
if (depth >= 4) {
while ((4U << shift) > depth)
shift--;
}
return shift;
}
/**
* sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
* @sb: Bitmap to show.
* @m: struct seq_file to write to.
*
* This is intended for debugging. The format may change at any time.
*/
void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
/**
* sbitmap_weight() - Return how many set and not cleared bits in a &struct
* sbitmap.
* @sb: Bitmap to check.
*
* Return: How many set and not cleared bits set
*/
unsigned int sbitmap_weight(const struct sbitmap *sb);
/**
* sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
* seq_file.
* @sb: Bitmap to show.
* @m: struct seq_file to write to.
*
* This is intended for debugging. The output isn't guaranteed to be internally
* consistent.
*/
void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m);
/**
* sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific
* memory node.
* @sbq: Bitmap queue to initialize.
* @depth: See sbitmap_init_node().
* @shift: See sbitmap_init_node().
* @round_robin: See sbitmap_get().
* @flags: Allocation flags.
* @node: Memory node to allocate on.
*
* Return: Zero on success or negative errno on failure.
*/
int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
int shift, bool round_robin, gfp_t flags, int node);
/**
* sbitmap_queue_free() - Free memory used by a &struct sbitmap_queue.
*
* @sbq: Bitmap queue to free.
*/
static inline void sbitmap_queue_free(struct sbitmap_queue *sbq)
{
kfree(sbq->ws);
sbitmap_free(&sbq->sb);
}
/**
* sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch
* @sbq: Bitmap queue to recalculate wake batch.
* @users: Number of shares.
*
* Like sbitmap_queue_update_wake_batch(), this will calculate wake batch
* by depth. This interface is for HCTX shared tags or queue shared tags.
*/
void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
unsigned int users);
/**
* sbitmap_queue_resize() - Resize a &struct sbitmap_queue.
* @sbq: Bitmap queue to resize.
* @depth: New number of bits to resize to.
*
* Like sbitmap_resize(), this doesn't reallocate anything. It has to do
* some extra work on the &struct sbitmap_queue, so it's not safe to just
* resize the underlying &struct sbitmap.
*/
void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
/**
* __sbitmap_queue_get() - Try to allocate a free bit from a &struct
* sbitmap_queue with preemption already disabled.
* @sbq: Bitmap queue to allocate from.
*
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
int __sbitmap_queue_get(struct sbitmap_queue *sbq);
/**
* __sbitmap_queue_get_batch() - Try to allocate a batch of free bits
* @sbq: Bitmap queue to allocate from.
* @nr_tags: number of tags requested
* @offset: offset to add to returned bits
*
* Return: Mask of allocated tags, 0 if none are found. Each tag allocated is
* a bit in the mask returned, and the caller must add @offset to the value to
* get the absolute tag value.
*/
unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
unsigned int *offset);
/**
* sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
* sbitmap_queue, limiting the depth used from each word, with preemption
* already disabled.
* @sbq: Bitmap queue to allocate from.
* @shallow_depth: The maximum number of bits to allocate from a single word.
* See sbitmap_get_shallow().
*
* If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
* initializing @sbq.
*
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
unsigned int shallow_depth);
/**
* sbitmap_queue_get() - Try to allocate a free bit from a &struct
* sbitmap_queue.
* @sbq: Bitmap queue to allocate from.
* @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
* sbitmap_queue_clear()).
*
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
unsigned int *cpu)
{
int nr;
*cpu = get_cpu();
nr = __sbitmap_queue_get(sbq);
put_cpu();
return nr;
}
/**
* sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
* minimum shallow depth that will be used.
* @sbq: Bitmap queue in question.
* @min_shallow_depth: The minimum shallow depth that will be passed to
* sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
*
* sbitmap_queue_clear() batches wakeups as an optimization. The batch size
* depends on the depth of the bitmap. Since the shallow allocation functions
* effectively operate with a different depth, the shallow depth must be taken
* into account when calculating the batch size. This function must be called
* with the minimum shallow depth that will be used. Failure to do so can result
* in missed wakeups.
*/
void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
unsigned int min_shallow_depth);
/**
* sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
* &struct sbitmap_queue.
* @sbq: Bitmap to free from.
* @nr: Bit number to free.
* @cpu: CPU the bit was allocated on.
*/
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu);
/**
* sbitmap_queue_clear_batch() - Free a batch of allocated bits
* &struct sbitmap_queue.
* @sbq: Bitmap to free from.
* @offset: offset for each tag in array
* @tags: array of tags
* @nr_tags: number of tags in array
*/
void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
int *tags, int nr_tags);
static inline int sbq_index_inc(int index)
{
return (index + 1) & (SBQ_WAIT_QUEUES - 1);
}
static inline void sbq_index_atomic_inc(atomic_t *index)
{
int old = atomic_read(index);
int new = sbq_index_inc(old);
atomic_cmpxchg(index, old, new);
}
/**
* sbq_wait_ptr() - Get the next wait queue to use for a &struct
* sbitmap_queue.
* @sbq: Bitmap queue to wait on.
* @wait_index: A counter per "user" of @sbq.
*/
static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
atomic_t *wait_index)
{
struct sbq_wait_state *ws;
ws = &sbq->ws[atomic_read(wait_index)];
sbq_index_atomic_inc(wait_index);
return ws;
}
/**
* sbitmap_queue_wake_all() - Wake up everything waiting on a &struct
* sbitmap_queue.
* @sbq: Bitmap queue to wake up.
*/
void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
/**
* sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue
* on a &struct sbitmap_queue.
* @sbq: Bitmap queue to wake up.
* @nr: Number of bits cleared.
*/
void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr);
/**
* sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
* seq_file.
* @sbq: Bitmap queue to show.
* @m: struct seq_file to write to.
*
* This is intended for debugging. The format may change at any time.
*/
void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
struct sbq_wait {
struct sbitmap_queue *sbq; /* if set, sbq_wait is accounted */
struct wait_queue_entry wait;
};
#define DEFINE_SBQ_WAIT(name) \
struct sbq_wait name = { \
.sbq = NULL, \
.wait = { \
.private = current, \
.func = autoremove_wake_function, \
.entry = LIST_HEAD_INIT((name).wait.entry), \
} \
}
/*
* Wrapper around prepare_to_wait_exclusive(), which maintains some extra
* internal state.
*/
void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq,
struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait, int state);
/*
* Must be paired with sbitmap_prepare_to_wait().
*/
void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait);
/*
* Wrapper around add_wait_queue(), which maintains some extra internal state
*/
void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait);
/*
* Must be paired with sbitmap_add_wait_queue()
*/
void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait);
#endif /* __LINUX_SCALE_BITMAP_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PAGE_REF_H
#define _LINUX_PAGE_REF_H
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <linux/tracepoint-defs.h>
DECLARE_TRACEPOINT(page_ref_set);
DECLARE_TRACEPOINT(page_ref_mod);
DECLARE_TRACEPOINT(page_ref_mod_and_test);
DECLARE_TRACEPOINT(page_ref_mod_and_return);
DECLARE_TRACEPOINT(page_ref_mod_unless);
DECLARE_TRACEPOINT(page_ref_freeze);
DECLARE_TRACEPOINT(page_ref_unfreeze);
#ifdef CONFIG_DEBUG_PAGE_REF
/*
* Ideally we would want to use the trace_<tracepoint>_enabled() helper
* functions. But due to include header file issues, that is not
* feasible. Instead we have to open code the static key functions.
*
* See trace_##name##_enabled(void) in include/linux/tracepoint.h
*/
#define page_ref_tracepoint_active(t) tracepoint_enabled(t)
extern void __page_ref_set(struct page *page, int v);
extern void __page_ref_mod(struct page *page, int v);
extern void __page_ref_mod_and_test(struct page *page, int v, int ret);
extern void __page_ref_mod_and_return(struct page *page, int v, int ret);
extern void __page_ref_mod_unless(struct page *page, int v, int u);
extern void __page_ref_freeze(struct page *page, int v, int ret);
extern void __page_ref_unfreeze(struct page *page, int v);
#else
#define page_ref_tracepoint_active(t) false
static inline void __page_ref_set(struct page *page, int v)
{
}
static inline void __page_ref_mod(struct page *page, int v)
{
}
static inline void __page_ref_mod_and_test(struct page *page, int v, int ret)
{
}
static inline void __page_ref_mod_and_return(struct page *page, int v, int ret)
{
}
static inline void __page_ref_mod_unless(struct page *page, int v, int u)
{
}
static inline void __page_ref_freeze(struct page *page, int v, int ret)
{
}
static inline void __page_ref_unfreeze(struct page *page, int v)
{
}
#endif
static inline int page_ref_count(const struct page *page)
{
return atomic_read(&page->_refcount);
}
/**
* folio_ref_count - The reference count on this folio.
* @folio: The folio.
*
* The refcount is usually incremented by calls to folio_get() and
* decremented by calls to folio_put(). Some typical users of the
* folio refcount:
*
* - Each reference from a page table
* - The page cache
* - Filesystem private data
* - The LRU list
* - Pipes
* - Direct IO which references this page in the process address space
*
* Return: The number of references to this folio.
*/
static inline int folio_ref_count(const struct folio *folio)
{
return page_ref_count(&folio->page);
}
static inline int page_count(const struct page *page)
{
return folio_ref_count(page_folio(page));
}
static inline void set_page_count(struct page *page, int v)
{
atomic_set(&page->_refcount, v);
if (page_ref_tracepoint_active(page_ref_set))
__page_ref_set(page, v);
}
static inline void folio_set_count(struct folio *folio, int v)
{
set_page_count(&folio->page, v);
}
/*
* Setup the page count before being freed into the page allocator for
* the first time (boot or memory hotplug)
*/
static inline void init_page_count(struct page *page)
{
set_page_count(page, 1);
}
static inline void page_ref_add(struct page *page, int nr)
{
atomic_add(nr, &page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, nr);
}
static inline void folio_ref_add(struct folio *folio, int nr)
{ page_ref_add(&folio->page, nr);
}
static inline void page_ref_sub(struct page *page, int nr)
{
atomic_sub(nr, &page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, -nr);
}
static inline void folio_ref_sub(struct folio *folio, int nr)
{
page_ref_sub(&folio->page, nr);
}
static inline int folio_ref_sub_return(struct folio *folio, int nr)
{
int ret = atomic_sub_return(nr, &folio->_refcount);
if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(&folio->page, -nr, ret);
return ret;
}
static inline void page_ref_inc(struct page *page)
{
atomic_inc(&page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, 1);
}
static inline void folio_ref_inc(struct folio *folio)
{
page_ref_inc(&folio->page);
}
static inline void page_ref_dec(struct page *page)
{
atomic_dec(&page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, -1);
}
static inline void folio_ref_dec(struct folio *folio)
{
page_ref_dec(&folio->page);
}
static inline int page_ref_sub_and_test(struct page *page, int nr)
{
int ret = atomic_sub_and_test(nr, &page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod_and_test))
__page_ref_mod_and_test(page, -nr, ret);
return ret;
}
static inline int folio_ref_sub_and_test(struct folio *folio, int nr)
{
return page_ref_sub_and_test(&folio->page, nr);
}
static inline int page_ref_inc_return(struct page *page)
{
int ret = atomic_inc_return(&page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(page, 1, ret);
return ret;
}
static inline int folio_ref_inc_return(struct folio *folio)
{
return page_ref_inc_return(&folio->page);
}
static inline int page_ref_dec_and_test(struct page *page)
{
int ret = atomic_dec_and_test(&page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod_and_test))
__page_ref_mod_and_test(page, -1, ret);
return ret;
}
static inline int folio_ref_dec_and_test(struct folio *folio)
{
return page_ref_dec_and_test(&folio->page);
}
static inline int page_ref_dec_return(struct page *page)
{
int ret = atomic_dec_return(&page->_refcount);
if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(page, -1, ret);
return ret;
}
static inline int folio_ref_dec_return(struct folio *folio)
{
return page_ref_dec_return(&folio->page);
}
static inline bool page_ref_add_unless(struct page *page, int nr, int u)
{
bool ret = false;
rcu_read_lock();
/* avoid writing to the vmemmap area being remapped */
if (page_count_writable(page, u))
ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock();
if (page_ref_tracepoint_active(page_ref_mod_unless))
__page_ref_mod_unless(page, nr, ret);
return ret;
}
static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u)
{
return page_ref_add_unless(&folio->page, nr, u);
}
/**
* folio_try_get - Attempt to increase the refcount on a folio.
* @folio: The folio.
*
* If you do not already have a reference to a folio, you can attempt to
* get one using this function. It may fail if, for example, the folio
* has been freed since you found a pointer to it, or it is frozen for
* the purposes of splitting or migration.
*
* Return: True if the reference count was successfully incremented.
*/
static inline bool folio_try_get(struct folio *folio)
{ return folio_ref_add_unless(folio, 1, 0);
}
static inline bool folio_ref_try_add(struct folio *folio, int count)
{
return folio_ref_add_unless(folio, count, 0);
}
static inline int page_ref_freeze(struct page *page, int count)
{
int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
if (page_ref_tracepoint_active(page_ref_freeze))
__page_ref_freeze(page, count, ret);
return ret;
}
static inline int folio_ref_freeze(struct folio *folio, int count)
{
return page_ref_freeze(&folio->page, count);
}
static inline void page_ref_unfreeze(struct page *page, int count)
{
VM_BUG_ON_PAGE(page_count(page) != 0, page);
VM_BUG_ON(count == 0);
atomic_set_release(&page->_refcount, count);
if (page_ref_tracepoint_active(page_ref_unfreeze))
__page_ref_unfreeze(page, count);
}
static inline void folio_ref_unfreeze(struct folio *folio, int count)
{
page_ref_unfreeze(&folio->page, count);
}
#endif
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/*
* Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2004 Infinicon Corporation. All rights reserved.
* Copyright (c) 2004, 2020 Intel Corporation. All rights reserved.
* Copyright (c) 2004 Topspin Corporation. All rights reserved.
* Copyright (c) 2004 Voltaire Corporation. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved.
*/
#ifndef IB_VERBS_H
#define IB_VERBS_H
#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/rwsem.h>
#include <linux/workqueue.h>
#include <linux/irq_poll.h>
#include <uapi/linux/if_ether.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/refcount.h>
#include <linux/if_link.h>
#include <linux/atomic.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/cgroup_rdma.h>
#include <linux/irqflags.h>
#include <linux/preempt.h>
#include <linux/dim.h>
#include <uapi/rdma/ib_user_verbs.h>
#include <rdma/rdma_counter.h>
#include <rdma/restrack.h>
#include <rdma/signature.h>
#include <uapi/rdma/rdma_user_ioctl.h>
#include <uapi/rdma/ib_user_ioctl_verbs.h>
#define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN
struct ib_umem_odp;
struct ib_uqp_object;
struct ib_usrq_object;
struct ib_uwq_object;
struct rdma_cm_id;
struct ib_port;
struct hw_stats_device_data;
extern struct workqueue_struct *ib_wq;
extern struct workqueue_struct *ib_comp_wq;
extern struct workqueue_struct *ib_comp_unbound_wq;
struct ib_ucq_object;
__printf(2, 3) __cold
void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_alert(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_crit(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_err(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_warn(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_notice(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_info(const struct ib_device *ibdev, const char *format, ...);
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define ibdev_dbg(__dev, format, args...) \
dynamic_ibdev_dbg(__dev, format, ##args)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {}
#endif
#define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
if (__ratelimit(&_rs)) \
ibdev_level(ibdev, fmt, ##__VA_ARGS__); \
} while (0)
#define ibdev_emerg_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_alert_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_crit_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_err_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_warn_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_notice_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_info_ratelimited(ibdev, fmt, ...) \
ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
/* descriptor check is first to prevent flooding with "callbacks suppressed" */
#define ibdev_dbg_ratelimited(ibdev, fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \
__dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \
##__VA_ARGS__); \
} while (0)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {}
#endif
union ib_gid {
u8 raw[16];
struct {
__be64 subnet_prefix;
__be64 interface_id;
} global;
};
extern union ib_gid zgid;
enum ib_gid_type {
IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB,
IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1,
IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2,
IB_GID_TYPE_SIZE
};
#define ROCE_V2_UDP_DPORT 4791
struct ib_gid_attr {
struct net_device __rcu *ndev;
struct ib_device *device;
union ib_gid gid;
enum ib_gid_type gid_type;
u16 index;
u32 port_num;
};
enum {
/* set the local administered indication */
IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2,
};
enum rdma_transport_type {
RDMA_TRANSPORT_IB,
RDMA_TRANSPORT_IWARP,
RDMA_TRANSPORT_USNIC,
RDMA_TRANSPORT_USNIC_UDP,
RDMA_TRANSPORT_UNSPECIFIED,
};
enum rdma_protocol_type {
RDMA_PROTOCOL_IB,
RDMA_PROTOCOL_IBOE,
RDMA_PROTOCOL_IWARP,
RDMA_PROTOCOL_USNIC_UDP
};
__attribute_const__ enum rdma_transport_type
rdma_node_get_transport(unsigned int node_type);
enum rdma_network_type {
RDMA_NETWORK_IB,
RDMA_NETWORK_ROCE_V1,
RDMA_NETWORK_IPV4,
RDMA_NETWORK_IPV6
};
static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type)
{
if (network_type == RDMA_NETWORK_IPV4 ||
network_type == RDMA_NETWORK_IPV6)
return IB_GID_TYPE_ROCE_UDP_ENCAP;
else if (network_type == RDMA_NETWORK_ROCE_V1)
return IB_GID_TYPE_ROCE;
else
return IB_GID_TYPE_IB;
}
static inline enum rdma_network_type
rdma_gid_attr_network_type(const struct ib_gid_attr *attr)
{
if (attr->gid_type == IB_GID_TYPE_IB)
return RDMA_NETWORK_IB;
if (attr->gid_type == IB_GID_TYPE_ROCE)
return RDMA_NETWORK_ROCE_V1;
if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid))
return RDMA_NETWORK_IPV4;
else
return RDMA_NETWORK_IPV6;
}
enum rdma_link_layer {
IB_LINK_LAYER_UNSPECIFIED,
IB_LINK_LAYER_INFINIBAND,
IB_LINK_LAYER_ETHERNET,
};
enum ib_device_cap_flags {
IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR,
IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR,
IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR,
IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI,
IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG,
IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT,
IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE,
IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD,
IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT,
/* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */
IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT,
IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID,
IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN,
IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE,
IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ,
/* Reserved, old SEND_W_INV = 1 << 16,*/
IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW,
/*
* Devices should set IB_DEVICE_UD_IP_SUM if they support
* insertion of UDP and TCP checksum on outgoing UD IPoIB
* messages and can verify the validity of checksum for
* incoming messages. Setting this flag implies that the
* IPoIB driver may set NETIF_F_IP_CSUM for datagram mode.
*/
IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM,
IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC,
/*
* This device supports the IB "base memory management extension",
* which includes support for fast registrations (IB_WR_REG_MR,
* IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should
* also be set by any iWarp device which must support FRs to comply
* to the iWarp verbs spec. iWarp devices also support the
* IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the
* stag.
*/
IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS,
IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A,
IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B,
IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM,
/* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */
IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM,
IB_DEVICE_MANAGED_FLOW_STEERING =
IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING,
/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS,
/* The device supports padding incoming writes to cacheline. */
IB_DEVICE_PCI_WRITE_END_PADDING =
IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING,
/* Placement type attributes */
IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL,
IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT,
IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE,
};
enum ib_kernel_cap_flags {
/*
* This device supports a per-device lkey or stag that can be
* used without performing a memory registration for the local
* memory. Note that ULPs should never check this flag, but
* instead of use the local_dma_lkey flag in the ib_pd structure,
* which will always contain a usable lkey.
*/
IBK_LOCAL_DMA_LKEY = 1 << 0,
/* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */
IBK_INTEGRITY_HANDOVER = 1 << 1,
/* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */
IBK_ON_DEMAND_PAGING = 1 << 2,
/* IB_MR_TYPE_SG_GAPS is supported */
IBK_SG_GAPS_REG = 1 << 3,
/* Driver supports RDMA_NLDEV_CMD_DELLINK */
IBK_ALLOW_USER_UNREG = 1 << 4,
/* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */
IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5,
/* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */
IBK_UD_TSO = 1 << 6,
/* iopib will use the device ops:
* get_vf_config
* get_vf_guid
* get_vf_stats
* set_vf_guid
* set_vf_link_state
*/
IBK_VIRTUAL_FUNCTION = 1 << 7,
/* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */
IBK_RDMA_NETDEV_OPA = 1 << 8,
};
enum ib_atomic_cap {
IB_ATOMIC_NONE,
IB_ATOMIC_HCA,
IB_ATOMIC_GLOB
};
enum ib_odp_general_cap_bits {
IB_ODP_SUPPORT = 1 << 0,
IB_ODP_SUPPORT_IMPLICIT = 1 << 1,
};
enum ib_odp_transport_cap_bits {
IB_ODP_SUPPORT_SEND = 1 << 0,
IB_ODP_SUPPORT_RECV = 1 << 1,
IB_ODP_SUPPORT_WRITE = 1 << 2,
IB_ODP_SUPPORT_READ = 1 << 3,
IB_ODP_SUPPORT_ATOMIC = 1 << 4,
IB_ODP_SUPPORT_SRQ_RECV = 1 << 5,
};
struct ib_odp_caps {
uint64_t general_caps;
struct {
uint32_t rc_odp_caps;
uint32_t uc_odp_caps;
uint32_t ud_odp_caps;
uint32_t xrc_odp_caps;
} per_transport_caps;
};
struct ib_rss_caps {
/* Corresponding bit will be set if qp type from
* 'enum ib_qp_type' is supported, e.g.
* supported_qpts |= 1 << IB_QPT_UD
*/
u32 supported_qpts;
u32 max_rwq_indirection_tables;
u32 max_rwq_indirection_table_size;
};
enum ib_tm_cap_flags {
/* Support tag matching with rendezvous offload for RC transport */
IB_TM_CAP_RNDV_RC = 1 << 0,
};
struct ib_tm_caps {
/* Max size of RNDV header */
u32 max_rndv_hdr_size;
/* Max number of entries in tag matching list */
u32 max_num_tags;
/* From enum ib_tm_cap_flags */
u32 flags;
/* Max number of outstanding list operations */
u32 max_ops;
/* Max number of SGE in tag matching entry */
u32 max_sge;
};
struct ib_cq_init_attr {
unsigned int cqe;
u32 comp_vector;
u32 flags;
};
enum ib_cq_attr_mask {
IB_CQ_MODERATE = 1 << 0,
};
struct ib_cq_caps {
u16 max_cq_moderation_count;
u16 max_cq_moderation_period;
};
struct ib_dm_mr_attr {
u64 length;
u64 offset;
u32 access_flags;
};
struct ib_dm_alloc_attr {
u64 length;
u32 alignment;
u32 flags;
};
struct ib_device_attr {
u64 fw_ver;
__be64 sys_image_guid;
u64 max_mr_size;
u64 page_size_cap;
u32 vendor_id;
u32 vendor_part_id;
u32 hw_ver;
int max_qp;
int max_qp_wr;
u64 device_cap_flags;
u64 kernel_cap_flags;
int max_send_sge;
int max_recv_sge;
int max_sge_rd;
int max_cq;
int max_cqe;
int max_mr;
int max_pd;
int max_qp_rd_atom;
int max_ee_rd_atom;
int max_res_rd_atom;
int max_qp_init_rd_atom;
int max_ee_init_rd_atom;
enum ib_atomic_cap atomic_cap;
enum ib_atomic_cap masked_atomic_cap;
int max_ee;
int max_rdd;
int max_mw;
int max_raw_ipv6_qp;
int max_raw_ethy_qp;
int max_mcast_grp;
int max_mcast_qp_attach;
int max_total_mcast_qp_attach;
int max_ah;
int max_srq;
int max_srq_wr;
int max_srq_sge;
unsigned int max_fast_reg_page_list_len;
unsigned int max_pi_fast_reg_page_list_len;
u16 max_pkeys;
u8 local_ca_ack_delay;
int sig_prot_cap;
int sig_guard_cap;
struct ib_odp_caps odp_caps;
uint64_t timestamp_mask;
uint64_t hca_core_clock; /* in KHZ */
struct ib_rss_caps rss_caps;
u32 max_wq_type_rq;
u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */
struct ib_tm_caps tm_caps;
struct ib_cq_caps cq_caps;
u64 max_dm_size;
/* Max entries for sgl for optimized performance per READ */
u32 max_sgl_rd;
};
enum ib_mtu {
IB_MTU_256 = 1,
IB_MTU_512 = 2,
IB_MTU_1024 = 3,
IB_MTU_2048 = 4,
IB_MTU_4096 = 5
};
enum opa_mtu {
OPA_MTU_8192 = 6,
OPA_MTU_10240 = 7
};
static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
{
switch (mtu) {
case IB_MTU_256: return 256;
case IB_MTU_512: return 512;
case IB_MTU_1024: return 1024;
case IB_MTU_2048: return 2048;
case IB_MTU_4096: return 4096;
default: return -1;
}
}
static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
{
if (mtu >= 4096)
return IB_MTU_4096;
else if (mtu >= 2048)
return IB_MTU_2048;
else if (mtu >= 1024)
return IB_MTU_1024;
else if (mtu >= 512)
return IB_MTU_512;
else
return IB_MTU_256;
}
static inline int opa_mtu_enum_to_int(enum opa_mtu mtu)
{
switch (mtu) {
case OPA_MTU_8192:
return 8192;
case OPA_MTU_10240:
return 10240;
default:
return(ib_mtu_enum_to_int((enum ib_mtu)mtu));
}
}
static inline enum opa_mtu opa_mtu_int_to_enum(int mtu)
{
if (mtu >= 10240)
return OPA_MTU_10240;
else if (mtu >= 8192)
return OPA_MTU_8192;
else
return ((enum opa_mtu)ib_mtu_int_to_enum(mtu));
}
enum ib_port_state {
IB_PORT_NOP = 0,
IB_PORT_DOWN = 1,
IB_PORT_INIT = 2,
IB_PORT_ARMED = 3,
IB_PORT_ACTIVE = 4,
IB_PORT_ACTIVE_DEFER = 5
};
static inline const char *__attribute_const__
ib_port_state_to_str(enum ib_port_state state)
{
const char * const states[] = {
[IB_PORT_NOP] = "NOP",
[IB_PORT_DOWN] = "DOWN",
[IB_PORT_INIT] = "INIT",
[IB_PORT_ARMED] = "ARMED",
[IB_PORT_ACTIVE] = "ACTIVE",
[IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER",
};
if (state < ARRAY_SIZE(states))
return states[state];
return "UNKNOWN";
}
enum ib_port_phys_state {
IB_PORT_PHYS_STATE_SLEEP = 1,
IB_PORT_PHYS_STATE_POLLING = 2,
IB_PORT_PHYS_STATE_DISABLED = 3,
IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4,
IB_PORT_PHYS_STATE_LINK_UP = 5,
IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6,
IB_PORT_PHYS_STATE_PHY_TEST = 7,
};
enum ib_port_width {
IB_WIDTH_1X = 1,
IB_WIDTH_2X = 16,
IB_WIDTH_4X = 2,
IB_WIDTH_8X = 4,
IB_WIDTH_12X = 8
};
static inline int ib_width_enum_to_int(enum ib_port_width width)
{
switch (width) {
case IB_WIDTH_1X: return 1;
case IB_WIDTH_2X: return 2;
case IB_WIDTH_4X: return 4;
case IB_WIDTH_8X: return 8;
case IB_WIDTH_12X: return 12;
default: return -1;
}
}
enum ib_port_speed {
IB_SPEED_SDR = 1,
IB_SPEED_DDR = 2,
IB_SPEED_QDR = 4,
IB_SPEED_FDR10 = 8,
IB_SPEED_FDR = 16,
IB_SPEED_EDR = 32,
IB_SPEED_HDR = 64,
IB_SPEED_NDR = 128,
IB_SPEED_XDR = 256,
};
enum ib_stat_flag {
IB_STAT_FLAG_OPTIONAL = 1 << 0,
};
/**
* struct rdma_stat_desc
* @name - The name of the counter
* @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL
* @priv - Driver private information; Core code should not use
*/
struct rdma_stat_desc {
const char *name;
unsigned int flags;
const void *priv;
};
/**
* struct rdma_hw_stats
* @lock - Mutex to protect parallel write access to lifespan and values
* of counters, which are 64bits and not guaranteed to be written
* atomicaly on 32bits systems.
* @timestamp - Used by the core code to track when the last update was
* @lifespan - Used by the core code to determine how old the counters
* should be before being updated again. Stored in jiffies, defaults
* to 10 milliseconds, drivers can override the default be specifying
* their own value during their allocation routine.
* @descs - Array of pointers to static descriptors used for the counters
* in directory.
* @is_disabled - A bitmap to indicate each counter is currently disabled
* or not.
* @num_counters - How many hardware counters there are. If name is
* shorter than this number, a kernel oops will result. Driver authors
* are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
* in their code to prevent this.
* @value - Array of u64 counters that are accessed by the sysfs code and
* filled in by the drivers get_stats routine
*/
struct rdma_hw_stats {
struct mutex lock; /* Protect lifespan and values[] */
unsigned long timestamp;
unsigned long lifespan;
const struct rdma_stat_desc *descs;
unsigned long *is_disabled;
int num_counters;
u64 value[] __counted_by(num_counters);
};
#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
const struct rdma_stat_desc *descs, int num_counters,
unsigned long lifespan);
void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats);
/* Define bits for the various functionality this port needs to be supported by
* the core.
*/
/* Management 0x00000FFF */
#define RDMA_CORE_CAP_IB_MAD 0x00000001
#define RDMA_CORE_CAP_IB_SMI 0x00000002
#define RDMA_CORE_CAP_IB_CM 0x00000004
#define RDMA_CORE_CAP_IW_CM 0x00000008
#define RDMA_CORE_CAP_IB_SA 0x00000010
#define RDMA_CORE_CAP_OPA_MAD 0x00000020
/* Address format 0x000FF000 */
#define RDMA_CORE_CAP_AF_IB 0x00001000
#define RDMA_CORE_CAP_ETH_AH 0x00002000
#define RDMA_CORE_CAP_OPA_AH 0x00004000
#define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000
/* Protocol 0xFFF00000 */
#define RDMA_CORE_CAP_PROT_IB 0x00100000
#define RDMA_CORE_CAP_PROT_ROCE 0x00200000
#define RDMA_CORE_CAP_PROT_IWARP 0x00400000
#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
#define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000
#define RDMA_CORE_CAP_PROT_USNIC 0x02000000
#define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \
| RDMA_CORE_CAP_PROT_ROCE \
| RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP)
#define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \
| RDMA_CORE_CAP_IB_MAD \
| RDMA_CORE_CAP_IB_SMI \
| RDMA_CORE_CAP_IB_CM \
| RDMA_CORE_CAP_IB_SA \
| RDMA_CORE_CAP_AF_IB)
#define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \
| RDMA_CORE_CAP_IB_MAD \
| RDMA_CORE_CAP_IB_CM \
| RDMA_CORE_CAP_AF_IB \
| RDMA_CORE_CAP_ETH_AH)
#define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \
(RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \
| RDMA_CORE_CAP_IB_MAD \
| RDMA_CORE_CAP_IB_CM \
| RDMA_CORE_CAP_AF_IB \
| RDMA_CORE_CAP_ETH_AH)
#define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \
| RDMA_CORE_CAP_IW_CM)
#define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \
| RDMA_CORE_CAP_OPA_MAD)
#define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET)
#define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC)
struct ib_port_attr {
u64 subnet_prefix;
enum ib_port_state state;
enum ib_mtu max_mtu;
enum ib_mtu active_mtu;
u32 phys_mtu;
int gid_tbl_len;
unsigned int ip_gids:1;
/* This is the value from PortInfo CapabilityMask, defined by IBA */
u32 port_cap_flags;
u32 max_msg_sz;
u32 bad_pkey_cntr;
u32 qkey_viol_cntr;
u16 pkey_tbl_len;
u32 sm_lid;
u32 lid;
u8 lmc;
u8 max_vl_num;
u8 sm_sl;
u8 subnet_timeout;
u8 init_type_reply;
u8 active_width;
u16 active_speed;
u8 phys_state;
u16 port_cap_flags2;
};
enum ib_device_modify_flags {
IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0,
IB_DEVICE_MODIFY_NODE_DESC = 1 << 1
};
#define IB_DEVICE_NODE_DESC_MAX 64
struct ib_device_modify {
u64 sys_image_guid;
char node_desc[IB_DEVICE_NODE_DESC_MAX];
};
enum ib_port_modify_flags {
IB_PORT_SHUTDOWN = 1,
IB_PORT_INIT_TYPE = (1<<2),
IB_PORT_RESET_QKEY_CNTR = (1<<3),
IB_PORT_OPA_MASK_CHG = (1<<4)
};
struct ib_port_modify {
u32 set_port_cap_mask;
u32 clr_port_cap_mask;
u8 init_type;
};
enum ib_event_type {
IB_EVENT_CQ_ERR,
IB_EVENT_QP_FATAL,
IB_EVENT_QP_REQ_ERR,
IB_EVENT_QP_ACCESS_ERR,
IB_EVENT_COMM_EST,
IB_EVENT_SQ_DRAINED,
IB_EVENT_PATH_MIG,
IB_EVENT_PATH_MIG_ERR,
IB_EVENT_DEVICE_FATAL,
IB_EVENT_PORT_ACTIVE,
IB_EVENT_PORT_ERR,
IB_EVENT_LID_CHANGE,
IB_EVENT_PKEY_CHANGE,
IB_EVENT_SM_CHANGE,
IB_EVENT_SRQ_ERR,
IB_EVENT_SRQ_LIMIT_REACHED,
IB_EVENT_QP_LAST_WQE_REACHED,
IB_EVENT_CLIENT_REREGISTER,
IB_EVENT_GID_CHANGE,
IB_EVENT_WQ_FATAL,
};
const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
struct ib_event {
struct ib_device *device;
union {
struct ib_cq *cq;
struct ib_qp *qp;
struct ib_srq *srq;
struct ib_wq *wq;
u32 port_num;
} element;
enum ib_event_type event;
};
struct ib_event_handler {
struct ib_device *device;
void (*handler)(struct ib_event_handler *, struct ib_event *);
struct list_head list;
};
#define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \
do { \
(_ptr)->device = _device; \
(_ptr)->handler = _handler; \
INIT_LIST_HEAD(&(_ptr)->list); \
} while (0)
struct ib_global_route {
const struct ib_gid_attr *sgid_attr;
union ib_gid dgid;
u32 flow_label;
u8 sgid_index;
u8 hop_limit;
u8 traffic_class;
};
struct ib_grh {
__be32 version_tclass_flow;
__be16 paylen;
u8 next_hdr;
u8 hop_limit;
union ib_gid sgid;
union ib_gid dgid;
};
union rdma_network_hdr {
struct ib_grh ibgrh;
struct {
/* The IB spec states that if it's IPv4, the header
* is located in the last 20 bytes of the header.
*/
u8 reserved[20];
struct iphdr roce4grh;
};
};
#define IB_QPN_MASK 0xFFFFFF
enum {
IB_MULTICAST_QPN = 0xffffff
};
#define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF)
#define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000)
enum ib_ah_flags {
IB_AH_GRH = 1
};
enum ib_rate {
IB_RATE_PORT_CURRENT = 0,
IB_RATE_2_5_GBPS = 2,
IB_RATE_5_GBPS = 5,
IB_RATE_10_GBPS = 3,
IB_RATE_20_GBPS = 6,
IB_RATE_30_GBPS = 4,
IB_RATE_40_GBPS = 7,
IB_RATE_60_GBPS = 8,
IB_RATE_80_GBPS = 9,
IB_RATE_120_GBPS = 10,
IB_RATE_14_GBPS = 11,
IB_RATE_56_GBPS = 12,
IB_RATE_112_GBPS = 13,
IB_RATE_168_GBPS = 14,
IB_RATE_25_GBPS = 15,
IB_RATE_100_GBPS = 16,
IB_RATE_200_GBPS = 17,
IB_RATE_300_GBPS = 18,
IB_RATE_28_GBPS = 19,
IB_RATE_50_GBPS = 20,
IB_RATE_400_GBPS = 21,
IB_RATE_600_GBPS = 22,
IB_RATE_800_GBPS = 23,
};
/**
* ib_rate_to_mult - Convert the IB rate enum to a multiple of the
* base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be
* converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec.
* @rate: rate to convert.
*/
__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
/**
* ib_rate_to_mbps - Convert the IB rate enum to Mbps.
* For example, IB_RATE_2_5_GBPS will be converted to 2500.
* @rate: rate to convert.
*/
__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
/**
* enum ib_mr_type - memory region type
* @IB_MR_TYPE_MEM_REG: memory region that is used for
* normal registration
* @IB_MR_TYPE_SG_GAPS: memory region that is capable to
* register any arbitrary sg lists (without
* the normal mr constraints - see
* ib_map_mr_sg)
* @IB_MR_TYPE_DM: memory region that is used for device
* memory registration
* @IB_MR_TYPE_USER: memory region that is used for the user-space
* application
* @IB_MR_TYPE_DMA: memory region that is used for DMA operations
* without address translations (VA=PA)
* @IB_MR_TYPE_INTEGRITY: memory region that is used for
* data integrity operations
*/
enum ib_mr_type {
IB_MR_TYPE_MEM_REG,
IB_MR_TYPE_SG_GAPS,
IB_MR_TYPE_DM,
IB_MR_TYPE_USER,
IB_MR_TYPE_DMA,
IB_MR_TYPE_INTEGRITY,
};
enum ib_mr_status_check {
IB_MR_CHECK_SIG_STATUS = 1,
};
/**
* struct ib_mr_status - Memory region status container
*
* @fail_status: Bitmask of MR checks status. For each
* failed check a corresponding status bit is set.
* @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS
* failure.
*/
struct ib_mr_status {
u32 fail_status;
struct ib_sig_err sig_err;
};
/**
* mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate
* enum.
* @mult: multiple to convert.
*/
__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
struct rdma_ah_init_attr {
struct rdma_ah_attr *ah_attr;
u32 flags;
struct net_device *xmit_slave;
};
enum rdma_ah_attr_type {
RDMA_AH_ATTR_TYPE_UNDEFINED,
RDMA_AH_ATTR_TYPE_IB,
RDMA_AH_ATTR_TYPE_ROCE,
RDMA_AH_ATTR_TYPE_OPA,
};
struct ib_ah_attr {
u16 dlid;
u8 src_path_bits;
};
struct roce_ah_attr {
u8 dmac[ETH_ALEN];
};
struct opa_ah_attr {
u32 dlid;
u8 src_path_bits;
bool make_grd;
};
struct rdma_ah_attr {
struct ib_global_route grh;
u8 sl;
u8 static_rate;
u32 port_num;
u8 ah_flags;
enum rdma_ah_attr_type type;
union {
struct ib_ah_attr ib;
struct roce_ah_attr roce;
struct opa_ah_attr opa;
};
};
enum ib_wc_status {
IB_WC_SUCCESS,
IB_WC_LOC_LEN_ERR,
IB_WC_LOC_QP_OP_ERR,
IB_WC_LOC_EEC_OP_ERR,
IB_WC_LOC_PROT_ERR,
IB_WC_WR_FLUSH_ERR,
IB_WC_MW_BIND_ERR,
IB_WC_BAD_RESP_ERR,
IB_WC_LOC_ACCESS_ERR,
IB_WC_REM_INV_REQ_ERR,
IB_WC_REM_ACCESS_ERR,
IB_WC_REM_OP_ERR,
IB_WC_RETRY_EXC_ERR,
IB_WC_RNR_RETRY_EXC_ERR,
IB_WC_LOC_RDD_VIOL_ERR,
IB_WC_REM_INV_RD_REQ_ERR,
IB_WC_REM_ABORT_ERR,
IB_WC_INV_EECN_ERR,
IB_WC_INV_EEC_STATE_ERR,
IB_WC_FATAL_ERR,
IB_WC_RESP_TIMEOUT_ERR,
IB_WC_GENERAL_ERR
};
const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);
enum ib_wc_opcode {
IB_WC_SEND = IB_UVERBS_WC_SEND,
IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE,
IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ,
IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP,
IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD,
IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW,
IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV,
IB_WC_LSO = IB_UVERBS_WC_TSO,
IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE,
IB_WC_REG_MR,
IB_WC_MASKED_COMP_SWAP,
IB_WC_MASKED_FETCH_ADD,
IB_WC_FLUSH = IB_UVERBS_WC_FLUSH,
/*
* Set value of IB_WC_RECV so consumers can test if a completion is a
* receive by testing (opcode & IB_WC_RECV).
*/
IB_WC_RECV = 1 << 7,
IB_WC_RECV_RDMA_WITH_IMM
};
enum ib_wc_flags {
IB_WC_GRH = 1,
IB_WC_WITH_IMM = (1<<1),
IB_WC_WITH_INVALIDATE = (1<<2),
IB_WC_IP_CSUM_OK = (1<<3),
IB_WC_WITH_SMAC = (1<<4),
IB_WC_WITH_VLAN = (1<<5),
IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6),
};
struct ib_wc {
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
enum ib_wc_status status;
enum ib_wc_opcode opcode;
u32 vendor_err;
u32 byte_len;
struct ib_qp *qp;
union {
__be32 imm_data;
u32 invalidate_rkey;
} ex;
u32 src_qp;
u32 slid;
int wc_flags;
u16 pkey_index;
u8 sl;
u8 dlid_path_bits;
u32 port_num; /* valid only for DR SMPs on switches */
u8 smac[ETH_ALEN];
u16 vlan_id;
u8 network_hdr_type;
};
enum ib_cq_notify_flags {
IB_CQ_SOLICITED = 1 << 0,
IB_CQ_NEXT_COMP = 1 << 1,
IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP,
IB_CQ_REPORT_MISSED_EVENTS = 1 << 2,
};
enum ib_srq_type {
IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC,
IB_SRQT_XRC = IB_UVERBS_SRQT_XRC,
IB_SRQT_TM = IB_UVERBS_SRQT_TM,
};
static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
{
return srq_type == IB_SRQT_XRC ||
srq_type == IB_SRQT_TM;
}
enum ib_srq_attr_mask {
IB_SRQ_MAX_WR = 1 << 0,
IB_SRQ_LIMIT = 1 << 1,
};
struct ib_srq_attr {
u32 max_wr;
u32 max_sge;
u32 srq_limit;
};
struct ib_srq_init_attr {
void (*event_handler)(struct ib_event *, void *);
void *srq_context;
struct ib_srq_attr attr;
enum ib_srq_type srq_type;
struct {
struct ib_cq *cq;
union {
struct {
struct ib_xrcd *xrcd;
} xrc;
struct {
u32 max_num_tags;
} tag_matching;
};
} ext;
};
struct ib_qp_cap {
u32 max_send_wr;
u32 max_recv_wr;
u32 max_send_sge;
u32 max_recv_sge;
u32 max_inline_data;
/*
* Maximum number of rdma_rw_ctx structures in flight at a time.
* ib_create_qp() will calculate the right amount of needed WRs
* and MRs based on this.
*/
u32 max_rdma_ctxs;
};
enum ib_sig_type {
IB_SIGNAL_ALL_WR,
IB_SIGNAL_REQ_WR
};
enum ib_qp_type {
/*
* IB_QPT_SMI and IB_QPT_GSI have to be the first two entries
* here (and in that order) since the MAD layer uses them as
* indices into a 2-entry table.
*/
IB_QPT_SMI,
IB_QPT_GSI,
IB_QPT_RC = IB_UVERBS_QPT_RC,
IB_QPT_UC = IB_UVERBS_QPT_UC,
IB_QPT_UD = IB_UVERBS_QPT_UD,
IB_QPT_RAW_IPV6,
IB_QPT_RAW_ETHERTYPE,
IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET,
IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI,
IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT,
IB_QPT_MAX,
IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER,
/* Reserve a range for qp types internal to the low level driver.
* These qp types will not be visible at the IB core layer, so the
* IB_QPT_MAX usages should not be affected in the core layer
*/
IB_QPT_RESERVED1 = 0x1000,
IB_QPT_RESERVED2,
IB_QPT_RESERVED3,
IB_QPT_RESERVED4,
IB_QPT_RESERVED5,
IB_QPT_RESERVED6,
IB_QPT_RESERVED7,
IB_QPT_RESERVED8,
IB_QPT_RESERVED9,
IB_QPT_RESERVED10,
};
enum ib_qp_create_flags {
IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0,
IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK =
IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
IB_QP_CREATE_CROSS_CHANNEL = 1 << 2,
IB_QP_CREATE_MANAGED_SEND = 1 << 3,
IB_QP_CREATE_MANAGED_RECV = 1 << 4,
IB_QP_CREATE_NETIF_QP = 1 << 5,
IB_QP_CREATE_INTEGRITY_EN = 1 << 6,
IB_QP_CREATE_NETDEV_USE = 1 << 7,
IB_QP_CREATE_SCATTER_FCS =
IB_UVERBS_QP_CREATE_SCATTER_FCS,
IB_QP_CREATE_CVLAN_STRIPPING =
IB_UVERBS_QP_CREATE_CVLAN_STRIPPING,
IB_QP_CREATE_SOURCE_QPN = 1 << 10,
IB_QP_CREATE_PCI_WRITE_END_PADDING =
IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING,
/* reserve bits 26-31 for low level drivers' internal use */
IB_QP_CREATE_RESERVED_START = 1 << 26,
IB_QP_CREATE_RESERVED_END = 1 << 31,
};
/*
* Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
* callback to destroy the passed in QP.
*/
struct ib_qp_init_attr {
/* This callback occurs in workqueue context */
void (*event_handler)(struct ib_event *, void *);
void *qp_context;
struct ib_cq *send_cq;
struct ib_cq *recv_cq;
struct ib_srq *srq;
struct ib_xrcd *xrcd; /* XRC TGT QPs only */
struct ib_qp_cap cap;
enum ib_sig_type sq_sig_type;
enum ib_qp_type qp_type;
u32 create_flags;
/*
* Only needed for special QP types, or when using the RW API.
*/
u32 port_num;
struct ib_rwq_ind_table *rwq_ind_tbl;
u32 source_qpn;
};
struct ib_qp_open_attr {
void (*event_handler)(struct ib_event *, void *);
void *qp_context;
u32 qp_num;
enum ib_qp_type qp_type;
};
enum ib_rnr_timeout {
IB_RNR_TIMER_655_36 = 0,
IB_RNR_TIMER_000_01 = 1,
IB_RNR_TIMER_000_02 = 2,
IB_RNR_TIMER_000_03 = 3,
IB_RNR_TIMER_000_04 = 4,
IB_RNR_TIMER_000_06 = 5,
IB_RNR_TIMER_000_08 = 6,
IB_RNR_TIMER_000_12 = 7,
IB_RNR_TIMER_000_16 = 8,
IB_RNR_TIMER_000_24 = 9,
IB_RNR_TIMER_000_32 = 10,
IB_RNR_TIMER_000_48 = 11,
IB_RNR_TIMER_000_64 = 12,
IB_RNR_TIMER_000_96 = 13,
IB_RNR_TIMER_001_28 = 14,
IB_RNR_TIMER_001_92 = 15,
IB_RNR_TIMER_002_56 = 16,
IB_RNR_TIMER_003_84 = 17,
IB_RNR_TIMER_005_12 = 18,
IB_RNR_TIMER_007_68 = 19,
IB_RNR_TIMER_010_24 = 20,
IB_RNR_TIMER_015_36 = 21,
IB_RNR_TIMER_020_48 = 22,
IB_RNR_TIMER_030_72 = 23,
IB_RNR_TIMER_040_96 = 24,
IB_RNR_TIMER_061_44 = 25,
IB_RNR_TIMER_081_92 = 26,
IB_RNR_TIMER_122_88 = 27,
IB_RNR_TIMER_163_84 = 28,
IB_RNR_TIMER_245_76 = 29,
IB_RNR_TIMER_327_68 = 30,
IB_RNR_TIMER_491_52 = 31
};
enum ib_qp_attr_mask {
IB_QP_STATE = 1,
IB_QP_CUR_STATE = (1<<1),
IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2),
IB_QP_ACCESS_FLAGS = (1<<3),
IB_QP_PKEY_INDEX = (1<<4),
IB_QP_PORT = (1<<5),
IB_QP_QKEY = (1<<6),
IB_QP_AV = (1<<7),
IB_QP_PATH_MTU = (1<<8),
IB_QP_TIMEOUT = (1<<9),
IB_QP_RETRY_CNT = (1<<10),
IB_QP_RNR_RETRY = (1<<11),
IB_QP_RQ_PSN = (1<<12),
IB_QP_MAX_QP_RD_ATOMIC = (1<<13),
IB_QP_ALT_PATH = (1<<14),
IB_QP_MIN_RNR_TIMER = (1<<15),
IB_QP_SQ_PSN = (1<<16),
IB_QP_MAX_DEST_RD_ATOMIC = (1<<17),
IB_QP_PATH_MIG_STATE = (1<<18),
IB_QP_CAP = (1<<19),
IB_QP_DEST_QPN = (1<<20),
IB_QP_RESERVED1 = (1<<21),
IB_QP_RESERVED2 = (1<<22),
IB_QP_RESERVED3 = (1<<23),
IB_QP_RESERVED4 = (1<<24),
IB_QP_RATE_LIMIT = (1<<25),
IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0),
};
enum ib_qp_state {
IB_QPS_RESET,
IB_QPS_INIT,
IB_QPS_RTR,
IB_QPS_RTS,
IB_QPS_SQD,
IB_QPS_SQE,
IB_QPS_ERR
};
enum ib_mig_state {
IB_MIG_MIGRATED,
IB_MIG_REARM,
IB_MIG_ARMED
};
enum ib_mw_type {
IB_MW_TYPE_1 = 1,
IB_MW_TYPE_2 = 2
};
struct ib_qp_attr {
enum ib_qp_state qp_state;
enum ib_qp_state cur_qp_state;
enum ib_mtu path_mtu;
enum ib_mig_state path_mig_state;
u32 qkey;
u32 rq_psn;
u32 sq_psn;
u32 dest_qp_num;
int qp_access_flags;
struct ib_qp_cap cap;
struct rdma_ah_attr ah_attr;
struct rdma_ah_attr alt_ah_attr;
u16 pkey_index;
u16 alt_pkey_index;
u8 en_sqd_async_notify;
u8 sq_draining;
u8 max_rd_atomic;
u8 max_dest_rd_atomic;
u8 min_rnr_timer;
u32 port_num;
u8 timeout;
u8 retry_cnt;
u8 rnr_retry;
u32 alt_port_num;
u8 alt_timeout;
u32 rate_limit;
struct net_device *xmit_slave;
};
enum ib_wr_opcode {
/* These are shared with userspace */
IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE,
IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM,
IB_WR_SEND = IB_UVERBS_WR_SEND,
IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM,
IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW,
IB_WR_LSO = IB_UVERBS_WR_TSO,
IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV,
IB_WR_MASKED_ATOMIC_CMP_AND_SWP =
IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
IB_WR_FLUSH = IB_UVERBS_WR_FLUSH,
IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE,
/* These are kernel only and can not be issued by userspace */
IB_WR_REG_MR = 0x20,
IB_WR_REG_MR_INTEGRITY,
/* reserve values for low level drivers' internal use.
* These values will not be used at all in the ib core layer.
*/
IB_WR_RESERVED1 = 0xf0,
IB_WR_RESERVED2,
IB_WR_RESERVED3,
IB_WR_RESERVED4,
IB_WR_RESERVED5,
IB_WR_RESERVED6,
IB_WR_RESERVED7,
IB_WR_RESERVED8,
IB_WR_RESERVED9,
IB_WR_RESERVED10,
};
enum ib_send_flags {
IB_SEND_FENCE = 1,
IB_SEND_SIGNALED = (1<<1),
IB_SEND_SOLICITED = (1<<2),
IB_SEND_INLINE = (1<<3),
IB_SEND_IP_CSUM = (1<<4),
/* reserve bits 26-31 for low level drivers' internal use */
IB_SEND_RESERVED_START = (1 << 26),
IB_SEND_RESERVED_END = (1 << 31),
};
struct ib_sge {
u64 addr;
u32 length;
u32 lkey;
};
struct ib_cqe {
void (*done)(struct ib_cq *cq, struct ib_wc *wc);
};
struct ib_send_wr {
struct ib_send_wr *next;
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
struct ib_sge *sg_list;
int num_sge;
enum ib_wr_opcode opcode;
int send_flags;
union {
__be32 imm_data;
u32 invalidate_rkey;
} ex;
};
struct ib_rdma_wr {
struct ib_send_wr wr;
u64 remote_addr;
u32 rkey;
};
static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_rdma_wr, wr);
}
struct ib_atomic_wr {
struct ib_send_wr wr;
u64 remote_addr;
u64 compare_add;
u64 swap;
u64 compare_add_mask;
u64 swap_mask;
u32 rkey;
};
static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_atomic_wr, wr);
}
struct ib_ud_wr {
struct ib_send_wr wr;
struct ib_ah *ah;
void *header;
int hlen;
int mss;
u32 remote_qpn;
u32 remote_qkey;
u16 pkey_index; /* valid for GSI only */
u32 port_num; /* valid for DR SMPs on switch only */
};
static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_ud_wr, wr);
}
struct ib_reg_wr {
struct ib_send_wr wr;
struct ib_mr *mr;
u32 key;
int access;
};
static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr)
{
return container_of(wr, struct ib_reg_wr, wr);
}
struct ib_recv_wr {
struct ib_recv_wr *next;
union {
u64 wr_id;
struct ib_cqe *wr_cqe;
};
struct ib_sge *sg_list;
int num_sge;
};
enum ib_access_flags {
IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE,
IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE,
IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ,
IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC,
IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND,
IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED,
IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING,
IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL,
IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT,
IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE,
IB_ACCESS_SUPPORTED =
((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL,
};
/*
* XXX: these are apparently used for ->rereg_user_mr, no idea why they
* are hidden here instead of a uapi header!
*/
enum ib_mr_rereg_flags {
IB_MR_REREG_TRANS = 1,
IB_MR_REREG_PD = (1<<1),
IB_MR_REREG_ACCESS = (1<<2),
IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1)
};
struct ib_umem;
enum rdma_remove_reason {
/*
* Userspace requested uobject deletion or initial try
* to remove uobject via cleanup. Call could fail
*/
RDMA_REMOVE_DESTROY,
/* Context deletion. This call should delete the actual object itself */
RDMA_REMOVE_CLOSE,
/* Driver is being hot-unplugged. This call should delete the actual object itself */
RDMA_REMOVE_DRIVER_REMOVE,
/* uobj is being cleaned-up before being committed */
RDMA_REMOVE_ABORT,
/* The driver failed to destroy the uobject and is being disconnected */
RDMA_REMOVE_DRIVER_FAILURE,
};
struct ib_rdmacg_object {
#ifdef CONFIG_CGROUP_RDMA
struct rdma_cgroup *cg; /* owner rdma cgroup */
#endif
};
struct ib_ucontext {
struct ib_device *device;
struct ib_uverbs_file *ufile;
struct ib_rdmacg_object cg_obj;
u64 enabled_caps;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
struct xarray mmap_xa;
};
struct ib_uobject {
u64 user_handle; /* handle given to us by userspace */
/* ufile & ucontext owning this object */
struct ib_uverbs_file *ufile;
/* FIXME, save memory: ufile->context == context */
struct ib_ucontext *context; /* associated user context */
void *object; /* containing object */
struct list_head list; /* link to context's list */
struct ib_rdmacg_object cg_obj; /* rdmacg object */
int id; /* index into kernel idr */
struct kref ref;
atomic_t usecnt; /* protects exclusive access */
struct rcu_head rcu; /* kfree_rcu() overhead */
const struct uverbs_api_object *uapi_object;
};
struct ib_udata {
const void __user *inbuf;
void __user *outbuf;
size_t inlen;
size_t outlen;
};
struct ib_pd {
u32 local_dma_lkey;
u32 flags;
struct ib_device *device;
struct ib_uobject *uobject;
atomic_t usecnt; /* count all resources */
u32 unsafe_global_rkey;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct ib_mr *__internal_mr;
struct rdma_restrack_entry res;
};
struct ib_xrcd {
struct ib_device *device;
atomic_t usecnt; /* count all exposed resources */
struct inode *inode;
struct rw_semaphore tgt_qps_rwsem;
struct xarray tgt_qps;
};
struct ib_ah {
struct ib_device *device;
struct ib_pd *pd;
struct ib_uobject *uobject;
const struct ib_gid_attr *sgid_attr;
enum rdma_ah_attr_type type;
};
typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
enum ib_poll_context {
IB_POLL_SOFTIRQ, /* poll from softirq context */
IB_POLL_WORKQUEUE, /* poll from workqueue */
IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */
IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE,
IB_POLL_DIRECT, /* caller context, no hw completions */
};
struct ib_cq {
struct ib_device *device;
struct ib_ucq_object *uobject;
ib_comp_handler comp_handler;
void (*event_handler)(struct ib_event *, void *);
void *cq_context;
int cqe;
unsigned int cqe_used;
atomic_t usecnt; /* count number of work queues */
enum ib_poll_context poll_ctx;
struct ib_wc *wc;
struct list_head pool_entry;
union {
struct irq_poll iop;
struct work_struct work;
};
struct workqueue_struct *comp_wq;
struct dim *dim;
/* updated only by trace points */
ktime_t timestamp;
u8 interrupt:1;
u8 shared:1;
unsigned int comp_vector;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
struct ib_srq {
struct ib_device *device;
struct ib_pd *pd;
struct ib_usrq_object *uobject;
void (*event_handler)(struct ib_event *, void *);
void *srq_context;
enum ib_srq_type srq_type;
atomic_t usecnt;
struct {
struct ib_cq *cq;
union {
struct {
struct ib_xrcd *xrcd;
u32 srq_num;
} xrc;
};
} ext;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
enum ib_raw_packet_caps {
/*
* Strip cvlan from incoming packet and report it in the matching work
* completion is supported.
*/
IB_RAW_PACKET_CAP_CVLAN_STRIPPING =
IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING,
/*
* Scatter FCS field of an incoming packet to host memory is supported.
*/
IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS,
/* Checksum offloads are supported (for both send and receive). */
IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM,
/*
* When a packet is received for an RQ with no receive WQEs, the
* packet processing is delayed.
*/
IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP,
};
enum ib_wq_type {
IB_WQT_RQ = IB_UVERBS_WQT_RQ,
};
enum ib_wq_state {
IB_WQS_RESET,
IB_WQS_RDY,
IB_WQS_ERR
};
struct ib_wq {
struct ib_device *device;
struct ib_uwq_object *uobject;
void *wq_context;
void (*event_handler)(struct ib_event *, void *);
struct ib_pd *pd;
struct ib_cq *cq;
u32 wq_num;
enum ib_wq_state state;
enum ib_wq_type wq_type;
atomic_t usecnt;
};
enum ib_wq_flags {
IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING,
IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS,
IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP,
IB_WQ_FLAGS_PCI_WRITE_END_PADDING =
IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING,
};
struct ib_wq_init_attr {
void *wq_context;
enum ib_wq_type wq_type;
u32 max_wr;
u32 max_sge;
struct ib_cq *cq;
void (*event_handler)(struct ib_event *, void *);
u32 create_flags; /* Use enum ib_wq_flags */
};
enum ib_wq_attr_mask {
IB_WQ_STATE = 1 << 0,
IB_WQ_CUR_STATE = 1 << 1,
IB_WQ_FLAGS = 1 << 2,
};
struct ib_wq_attr {
enum ib_wq_state wq_state;
enum ib_wq_state curr_wq_state;
u32 flags; /* Use enum ib_wq_flags */
u32 flags_mask; /* Use enum ib_wq_flags */
};
struct ib_rwq_ind_table {
struct ib_device *device;
struct ib_uobject *uobject;
atomic_t usecnt;
u32 ind_tbl_num;
u32 log_ind_tbl_size;
struct ib_wq **ind_tbl;
};
struct ib_rwq_ind_table_init_attr {
u32 log_ind_tbl_size;
/* Each entry is a pointer to Receive Work Queue */
struct ib_wq **ind_tbl;
};
enum port_pkey_state {
IB_PORT_PKEY_NOT_VALID = 0,
IB_PORT_PKEY_VALID = 1,
IB_PORT_PKEY_LISTED = 2,
};
struct ib_qp_security;
struct ib_port_pkey {
enum port_pkey_state state;
u16 pkey_index;
u32 port_num;
struct list_head qp_list;
struct list_head to_error_list;
struct ib_qp_security *sec;
};
struct ib_ports_pkeys {
struct ib_port_pkey main;
struct ib_port_pkey alt;
};
struct ib_qp_security {
struct ib_qp *qp;
struct ib_device *dev;
/* Hold this mutex when changing port and pkey settings. */
struct mutex mutex;
struct ib_ports_pkeys *ports_pkeys;
/* A list of all open shared QP handles. Required to enforce security
* properly for all users of a shared QP.
*/
struct list_head shared_qp_list;
void *security;
bool destroying;
atomic_t error_list_count;
struct completion error_complete;
int error_comps_pending;
};
/*
* @max_write_sge: Maximum SGE elements per RDMA WRITE request.
* @max_read_sge: Maximum SGE elements per RDMA READ request.
*/
struct ib_qp {
struct ib_device *device;
struct ib_pd *pd;
struct ib_cq *send_cq;
struct ib_cq *recv_cq;
spinlock_t mr_lock;
int mrs_used;
struct list_head rdma_mrs;
struct list_head sig_mrs;
struct ib_srq *srq;
struct completion srq_completion;
struct ib_xrcd *xrcd; /* XRC TGT QPs only */
struct list_head xrcd_list;
/* count times opened, mcast attaches, flow attaches */
atomic_t usecnt;
struct list_head open_list;
struct ib_qp *real_qp;
struct ib_uqp_object *uobject;
void (*event_handler)(struct ib_event *, void *);
void (*registered_event_handler)(struct ib_event *, void *);
void *qp_context;
/* sgid_attrs associated with the AV's */
const struct ib_gid_attr *av_sgid_attr;
const struct ib_gid_attr *alt_path_sgid_attr;
u32 qp_num;
u32 max_write_sge;
u32 max_read_sge;
enum ib_qp_type qp_type;
struct ib_rwq_ind_table *rwq_ind_tbl;
struct ib_qp_security *qp_sec;
u32 port;
bool integrity_en;
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
/* The counter the qp is bind to */
struct rdma_counter *counter;
};
struct ib_dm {
struct ib_device *device;
u32 length;
u32 flags;
struct ib_uobject *uobject;
atomic_t usecnt;
};
struct ib_mr {
struct ib_device *device;
struct ib_pd *pd;
u32 lkey;
u32 rkey;
u64 iova;
u64 length;
unsigned int page_size;
enum ib_mr_type type;
bool need_inval;
union {
struct ib_uobject *uobject; /* user */
struct list_head qp_entry; /* FR */
};
struct ib_dm *dm;
struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */
/*
* Implementation details of the RDMA core, don't use in drivers:
*/
struct rdma_restrack_entry res;
};
struct ib_mw {
struct ib_device *device;
struct ib_pd *pd;
struct ib_uobject *uobject;
u32 rkey;
enum ib_mw_type type;
};
/* Supported steering options */
enum ib_flow_attr_type {
/* steering according to rule specifications */
IB_FLOW_ATTR_NORMAL = 0x0,
/* default unicast and multicast rule -
* receive all Eth traffic which isn't steered to any QP
*/
IB_FLOW_ATTR_ALL_DEFAULT = 0x1,
/* default multicast rule -
* receive all Eth multicast traffic which isn't steered to any QP
*/
IB_FLOW_ATTR_MC_DEFAULT = 0x2,
/* sniffer rule - receive all port traffic */
IB_FLOW_ATTR_SNIFFER = 0x3
};
/* Supported steering header types */
enum ib_flow_spec_type {
/* L2 headers*/
IB_FLOW_SPEC_ETH = 0x20,
IB_FLOW_SPEC_IB = 0x22,
/* L3 header*/
IB_FLOW_SPEC_IPV4 = 0x30,
IB_FLOW_SPEC_IPV6 = 0x31,
IB_FLOW_SPEC_ESP = 0x34,
/* L4 headers*/
IB_FLOW_SPEC_TCP = 0x40,
IB_FLOW_SPEC_UDP = 0x41,
IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50,
IB_FLOW_SPEC_GRE = 0x51,
IB_FLOW_SPEC_MPLS = 0x60,
IB_FLOW_SPEC_INNER = 0x100,
/* Actions */
IB_FLOW_SPEC_ACTION_TAG = 0x1000,
IB_FLOW_SPEC_ACTION_DROP = 0x1001,
IB_FLOW_SPEC_ACTION_HANDLE = 0x1002,
IB_FLOW_SPEC_ACTION_COUNT = 0x1003,
};
#define IB_FLOW_SPEC_LAYER_MASK 0xF0
#define IB_FLOW_SPEC_SUPPORT_LAYERS 10
enum ib_flow_flags {
IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */
IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */
};
struct ib_flow_eth_filter {
u8 dst_mac[6];
u8 src_mac[6];
__be16 ether_type;
__be16 vlan_tag;
};
struct ib_flow_spec_eth {
u32 type;
u16 size;
struct ib_flow_eth_filter val;
struct ib_flow_eth_filter mask;
};
struct ib_flow_ib_filter {
__be16 dlid;
__u8 sl;
};
struct ib_flow_spec_ib {
u32 type;
u16 size;
struct ib_flow_ib_filter val;
struct ib_flow_ib_filter mask;
};
/* IPv4 header flags */
enum ib_ipv4_flags {
IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */
IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the
last have this flag set */
};
struct ib_flow_ipv4_filter {
__be32 src_ip;
__be32 dst_ip;
u8 proto;
u8 tos;
u8 ttl;
u8 flags;
};
struct ib_flow_spec_ipv4 {
u32 type;
u16 size;
struct ib_flow_ipv4_filter val;
struct ib_flow_ipv4_filter mask;
};
struct ib_flow_ipv6_filter {
u8 src_ip[16];
u8 dst_ip[16];
__be32 flow_label;
u8 next_hdr;
u8 traffic_class;
u8 hop_limit;
} __packed;
struct ib_flow_spec_ipv6 {
u32 type;
u16 size;
struct ib_flow_ipv6_filter val;
struct ib_flow_ipv6_filter mask;
};
struct ib_flow_tcp_udp_filter {
__be16 dst_port;
__be16 src_port;
};
struct ib_flow_spec_tcp_udp {
u32 type;
u16 size;
struct ib_flow_tcp_udp_filter val;
struct ib_flow_tcp_udp_filter mask;
};
struct ib_flow_tunnel_filter {
__be32 tunnel_id;
};
/* ib_flow_spec_tunnel describes the Vxlan tunnel
* the tunnel_id from val has the vni value
*/
struct ib_flow_spec_tunnel {
u32 type;
u16 size;
struct ib_flow_tunnel_filter val;
struct ib_flow_tunnel_filter mask;
};
struct ib_flow_esp_filter {
__be32 spi;
__be32 seq;
};
struct ib_flow_spec_esp {
u32 type;
u16 size;
struct ib_flow_esp_filter val;
struct ib_flow_esp_filter mask;
};
struct ib_flow_gre_filter {
__be16 c_ks_res0_ver;
__be16 protocol;
__be32 key;
};
struct ib_flow_spec_gre {
u32 type;
u16 size;
struct ib_flow_gre_filter val;
struct ib_flow_gre_filter mask;
};
struct ib_flow_mpls_filter {
__be32 tag;
};
struct ib_flow_spec_mpls {
u32 type;
u16 size;
struct ib_flow_mpls_filter val;
struct ib_flow_mpls_filter mask;
};
struct ib_flow_spec_action_tag {
enum ib_flow_spec_type type;
u16 size;
u32 tag_id;
};
struct ib_flow_spec_action_drop {
enum ib_flow_spec_type type;
u16 size;
};
struct ib_flow_spec_action_handle {
enum ib_flow_spec_type type;
u16 size;
struct ib_flow_action *act;
};
enum ib_counters_description {
IB_COUNTER_PACKETS,
IB_COUNTER_BYTES,
};
struct ib_flow_spec_action_count {
enum ib_flow_spec_type type;
u16 size;
struct ib_counters *counters;
};
union ib_flow_spec {
struct {
u32 type;
u16 size;
};
struct ib_flow_spec_eth eth;
struct ib_flow_spec_ib ib;
struct ib_flow_spec_ipv4 ipv4;
struct ib_flow_spec_tcp_udp tcp_udp;
struct ib_flow_spec_ipv6 ipv6;
struct ib_flow_spec_tunnel tunnel;
struct ib_flow_spec_esp esp;
struct ib_flow_spec_gre gre;
struct ib_flow_spec_mpls mpls;
struct ib_flow_spec_action_tag flow_tag;
struct ib_flow_spec_action_drop drop;
struct ib_flow_spec_action_handle action;
struct ib_flow_spec_action_count flow_count;
};
struct ib_flow_attr {
enum ib_flow_attr_type type;
u16 size;
u16 priority;
u32 flags;
u8 num_of_specs;
u32 port;
union ib_flow_spec flows[];
};
struct ib_flow {
struct ib_qp *qp;
struct ib_device *device;
struct ib_uobject *uobject;
};
enum ib_flow_action_type {
IB_FLOW_ACTION_UNSPECIFIED,
IB_FLOW_ACTION_ESP = 1,
};
struct ib_flow_action_attrs_esp_keymats {
enum ib_uverbs_flow_action_esp_keymat protocol;
union {
struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm;
} keymat;
};
struct ib_flow_action_attrs_esp_replays {
enum ib_uverbs_flow_action_esp_replay protocol;
union {
struct ib_uverbs_flow_action_esp_replay_bmp bmp;
} replay;
};
enum ib_flow_action_attrs_esp_flags {
/* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags
* This is done in order to share the same flags between user-space and
* kernel and spare an unnecessary translation.
*/
/* Kernel flags */
IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32,
IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33,
};
struct ib_flow_spec_list {
struct ib_flow_spec_list *next;
union ib_flow_spec spec;
};
struct ib_flow_action_attrs_esp {
struct ib_flow_action_attrs_esp_keymats *keymat;
struct ib_flow_action_attrs_esp_replays *replay;
struct ib_flow_spec_list *encap;
/* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled.
* Value of 0 is a valid value.
*/
u32 esn;
u32 spi;
u32 seq;
u32 tfc_pad;
/* Use enum ib_flow_action_attrs_esp_flags */
u64 flags;
u64 hard_limit_pkts;
};
struct ib_flow_action {
struct ib_device *device;
struct ib_uobject *uobject;
enum ib_flow_action_type type;
atomic_t usecnt;
};
struct ib_mad;
enum ib_process_mad_flags {
IB_MAD_IGNORE_MKEY = 1,
IB_MAD_IGNORE_BKEY = 2,
IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY
};
enum ib_mad_result {
IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */
IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */
IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */
IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */
};
struct ib_port_cache {
u64 subnet_prefix;
struct ib_pkey_cache *pkey;
struct ib_gid_table *gid;
u8 lmc;
enum ib_port_state port_state;
enum ib_port_state last_port_state;
};
struct ib_port_immutable {
int pkey_tbl_len;
int gid_tbl_len;
u32 core_cap_flags;
u32 max_mad_size;
};
struct ib_port_data {
struct ib_device *ib_dev;
struct ib_port_immutable immutable;
spinlock_t pkey_list_lock;
spinlock_t netdev_lock;
struct list_head pkey_list;
struct ib_port_cache cache;
struct net_device __rcu *netdev;
netdevice_tracker netdev_tracker;
struct hlist_node ndev_hash_link;
struct rdma_port_counter port_counter;
struct ib_port *sysfs;
};
/* rdma netdev type - specifies protocol type */
enum rdma_netdev_t {
RDMA_NETDEV_OPA_VNIC,
RDMA_NETDEV_IPOIB,
};
/**
* struct rdma_netdev - rdma netdev
* For cases where netstack interfacing is required.
*/
struct rdma_netdev {
void *clnt_priv;
struct ib_device *hca;
u32 port_num;
int mtu;
/*
* cleanup function must be specified.
* FIXME: This is only used for OPA_VNIC and that usage should be
* removed too.
*/
void (*free_rdma_netdev)(struct net_device *netdev);
/* control functions */
void (*set_id)(struct net_device *netdev, int id);
/* send packet */
int (*send)(struct net_device *dev, struct sk_buff *skb,
struct ib_ah *address, u32 dqpn);
/* multicast */
int (*attach_mcast)(struct net_device *dev, struct ib_device *hca,
union ib_gid *gid, u16 mlid,
int set_qkey, u32 qkey);
int (*detach_mcast)(struct net_device *dev, struct ib_device *hca,
union ib_gid *gid, u16 mlid);
/* timeout */
void (*tx_timeout)(struct net_device *dev, unsigned int txqueue);
};
struct rdma_netdev_alloc_params {
size_t sizeof_priv;
unsigned int txqs;
unsigned int rxqs;
void *param;
int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num,
struct net_device *netdev, void *param);
};
struct ib_odp_counters {
atomic64_t faults;
atomic64_t faults_handled;
atomic64_t invalidations;
atomic64_t invalidations_handled;
atomic64_t prefetch;
};
struct ib_counters {
struct ib_device *device;
struct ib_uobject *uobject;
/* num of objects attached */
atomic_t usecnt;
};
struct ib_counters_read_attr {
u64 *counters_buff;
u32 ncounters;
u32 flags; /* use enum ib_read_counters_flags */
};
struct uverbs_attr_bundle;
struct iw_cm_id;
struct iw_cm_conn_param;
#define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \
.size_##ib_struct = \
(sizeof(struct drv_struct) + \
BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \
BUILD_BUG_ON_ZERO( \
!__same_type(((struct drv_struct *)NULL)->member, \
struct ib_struct)))
#define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \
((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
gfp, false))
#define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \
((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
GFP_KERNEL, true))
#define rdma_zalloc_drv_obj(ib_dev, ib_type) \
rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL)
#define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct
struct rdma_user_mmap_entry {
struct kref ref;
struct ib_ucontext *ucontext;
unsigned long start_pgoff;
size_t npages;
bool driver_removed;
};
/* Return the offset (in bytes) the user should pass to libc's mmap() */
static inline u64
rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry)
{
return (u64)entry->start_pgoff << PAGE_SHIFT;
}
/**
* struct ib_device_ops - InfiniBand device operations
* This structure defines all the InfiniBand device operations, providers will
* need to define the supported operations, otherwise they will be set to null.
*/
struct ib_device_ops {
struct module *owner;
enum rdma_driver_id driver_id;
u32 uverbs_abi_ver;
unsigned int uverbs_no_driver_id_binding:1;
/*
* NOTE: New drivers should not make use of device_group; instead new
* device parameter should be exposed via netlink command. This
* mechanism exists only for existing drivers.
*/
const struct attribute_group *device_group;
const struct attribute_group **port_groups;
int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr,
const struct ib_send_wr **bad_send_wr);
int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr);
void (*drain_rq)(struct ib_qp *qp);
void (*drain_sq)(struct ib_qp *qp);
int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc);
int (*peek_cq)(struct ib_cq *cq, int wc_cnt);
int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags);
int (*post_srq_recv)(struct ib_srq *srq,
const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr);
int (*process_mad)(struct ib_device *device, int process_mad_flags,
u32 port_num, const struct ib_wc *in_wc,
const struct ib_grh *in_grh,
const struct ib_mad *in_mad, struct ib_mad *out_mad,
size_t *out_mad_size, u16 *out_mad_pkey_index);
int (*query_device)(struct ib_device *device,
struct ib_device_attr *device_attr,
struct ib_udata *udata);
int (*modify_device)(struct ib_device *device, int device_modify_mask,
struct ib_device_modify *device_modify);
void (*get_dev_fw_str)(struct ib_device *device, char *str);
const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
int comp_vector);
int (*query_port)(struct ib_device *device, u32 port_num,
struct ib_port_attr *port_attr);
int (*modify_port)(struct ib_device *device, u32 port_num,
int port_modify_mask,
struct ib_port_modify *port_modify);
/**
* The following mandatory functions are used only at device
* registration. Keep functions such as these at the end of this
* structure to avoid cache line misses when accessing struct ib_device
* in fast paths.
*/
int (*get_port_immutable)(struct ib_device *device, u32 port_num,
struct ib_port_immutable *immutable);
enum rdma_link_layer (*get_link_layer)(struct ib_device *device,
u32 port_num);
/**
* When calling get_netdev, the HW vendor's driver should return the
* net device of device @device at port @port_num or NULL if such
* a net device doesn't exist. The vendor driver should call dev_hold
* on this net device. The HW vendor's device driver must guarantee
* that this function returns NULL before the net device has finished
* NETDEV_UNREGISTER state.
*/
struct net_device *(*get_netdev)(struct ib_device *device,
u32 port_num);
/**
* rdma netdev operation
*
* Driver implementing alloc_rdma_netdev or rdma_netdev_get_params
* must return -EOPNOTSUPP if it doesn't support the specified type.
*/
struct net_device *(*alloc_rdma_netdev)(
struct ib_device *device, u32 port_num, enum rdma_netdev_t type,
const char *name, unsigned char name_assign_type,
void (*setup)(struct net_device *));
int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num,
enum rdma_netdev_t type,
struct rdma_netdev_alloc_params *params);
/**
* query_gid should be return GID value for @device, when @port_num
* link layer is either IB or iWarp. It is no-op if @port_num port
* is RoCE link layer.
*/
int (*query_gid)(struct ib_device *device, u32 port_num, int index,
union ib_gid *gid);
/**
* When calling add_gid, the HW vendor's driver should add the gid
* of device of port at gid index available at @attr. Meta-info of
* that gid (for example, the network device related to this gid) is
* available at @attr. @context allows the HW vendor driver to store
* extra information together with a GID entry. The HW vendor driver may
* allocate memory to contain this information and store it in @context
* when a new GID entry is written to. Params are consistent until the
* next call of add_gid or delete_gid. The function should return 0 on
* success or error otherwise. The function could be called
* concurrently for different ports. This function is only called when
* roce_gid_table is used.
*/
int (*add_gid)(const struct ib_gid_attr *attr, void **context);
/**
* When calling del_gid, the HW vendor's driver should delete the
* gid of device @device at gid index gid_index of port port_num
* available in @attr.
* Upon the deletion of a GID entry, the HW vendor must free any
* allocated memory. The caller will clear @context afterwards.
* This function is only called when roce_gid_table is used.
*/
int (*del_gid)(const struct ib_gid_attr *attr, void **context);
int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index,
u16 *pkey);
int (*alloc_ucontext)(struct ib_ucontext *context,
struct ib_udata *udata);
void (*dealloc_ucontext)(struct ib_ucontext *context);
int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma);
/**
* This will be called once refcount of an entry in mmap_xa reaches
* zero. The type of the memory that was mapped may differ between
* entries and is opaque to the rdma_user_mmap interface.
* Therefore needs to be implemented by the driver in mmap_free.
*/
void (*mmap_free)(struct rdma_user_mmap_entry *entry);
void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
struct ib_udata *udata);
int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
struct ib_udata *udata);
int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
int (*destroy_ah)(struct ib_ah *ah, u32 flags);
int (*create_srq)(struct ib_srq *srq,
struct ib_srq_init_attr *srq_init_attr,
struct ib_udata *udata);
int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr,
enum ib_srq_attr_mask srq_attr_mask,
struct ib_udata *udata);
int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata);
int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
struct ib_udata *udata);
int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
int qp_attr_mask, struct ib_udata *udata);
int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata);
int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
struct uverbs_attr_bundle *attrs);
int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int mr_access_flags,
struct ib_udata *udata);
struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset,
u64 length, u64 virt_addr, int fd,
int mr_access_flags,
struct uverbs_attr_bundle *attrs);
struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start,
u64 length, u64 virt_addr,
int mr_access_flags, struct ib_pd *pd,
struct ib_udata *udata);
int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata);
struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type,
u32 max_num_sg);
struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd,
u32 max_num_data_sg,
u32 max_num_meta_sg);
int (*advise_mr)(struct ib_pd *pd,
enum ib_uverbs_advise_mr_advice advice, u32 flags,
struct ib_sge *sg_list, u32 num_sge,
struct uverbs_attr_bundle *attrs);
/*
* Kernel users should universally support relaxed ordering (RO), as
* they are designed to read data only after observing the CQE and use
* the DMA API correctly.
*
* Some drivers implicitly enable RO if platform supports it.
*/
int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset);
int (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
struct ib_mr_status *mr_status);
int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata);
int (*dealloc_mw)(struct ib_mw *mw);
int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
struct ib_flow *(*create_flow)(struct ib_qp *qp,
struct ib_flow_attr *flow_attr,
struct ib_udata *udata);
int (*destroy_flow)(struct ib_flow *flow_id);
int (*destroy_flow_action)(struct ib_flow_action *action);
int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port,
int state);
int (*get_vf_config)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_info *ivf);
int (*get_vf_stats)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_stats *stats);
int (*get_vf_guid)(struct ib_device *device, int vf, u32 port,
struct ifla_vf_guid *node_guid,
struct ifla_vf_guid *port_guid);
int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid,
int type);
struct ib_wq *(*create_wq)(struct ib_pd *pd,
struct ib_wq_init_attr *init_attr,
struct ib_udata *udata);
int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata);
int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr,
u32 wq_attr_mask, struct ib_udata *udata);
int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table,
struct ib_rwq_ind_table_init_attr *init_attr,
struct ib_udata *udata);
int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
struct ib_dm *(*alloc_dm)(struct ib_device *device,
struct ib_ucontext *context,
struct ib_dm_alloc_attr *attr,
struct uverbs_attr_bundle *attrs);
int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs);
struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm,
struct ib_dm_mr_attr *attr,
struct uverbs_attr_bundle *attrs);
int (*create_counters)(struct ib_counters *counters,
struct uverbs_attr_bundle *attrs);
int (*destroy_counters)(struct ib_counters *counters);
int (*read_counters)(struct ib_counters *counters,
struct ib_counters_read_attr *counters_read_attr,
struct uverbs_attr_bundle *attrs);
int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg,
int data_sg_nents, unsigned int *data_sg_offset,
struct scatterlist *meta_sg, int meta_sg_nents,
unsigned int *meta_sg_offset);
/**
* alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and
* fill in the driver initialized data. The struct is kfree()'ed by
* the sysfs core when the device is removed. A lifespan of -1 in the
* return struct tells the core to set a default lifespan.
*/
struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device);
struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device,
u32 port_num);
/**
* get_hw_stats - Fill in the counter value(s) in the stats struct.
* @index - The index in the value array we wish to have updated, or
* num_counters if we want all stats updated
* Return codes -
* < 0 - Error, no counters updated
* index - Updated the single counter pointed to by index
* num_counters - Updated all counters (will reset the timestamp
* and prevent further calls for lifespan milliseconds)
* Drivers are allowed to update all counters in leiu of just the
* one given in index at their option
*/
int (*get_hw_stats)(struct ib_device *device,
struct rdma_hw_stats *stats, u32 port, int index);
/**
* modify_hw_stat - Modify the counter configuration
* @enable: true/false when enable/disable a counter
* Return codes - 0 on success or error code otherwise.
*/
int (*modify_hw_stat)(struct ib_device *device, u32 port,
unsigned int counter_index, bool enable);
/**
* Allows rdma drivers to add their own restrack attributes.
*/
int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr);
int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq);
int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq);
int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp);
int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp);
int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id);
int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq);
int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq);
/* Device lifecycle callbacks */
/*
* Called after the device becomes registered, before clients are
* attached
*/
int (*enable_driver)(struct ib_device *dev);
/*
* This is called as part of ib_dealloc_device().
*/
void (*dealloc_driver)(struct ib_device *dev);
/* iWarp CM callbacks */
void (*iw_add_ref)(struct ib_qp *qp);
void (*iw_rem_ref)(struct ib_qp *qp);
struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn);
int (*iw_connect)(struct iw_cm_id *cm_id,
struct iw_cm_conn_param *conn_param);
int (*iw_accept)(struct iw_cm_id *cm_id,
struct iw_cm_conn_param *conn_param);
int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata,
u8 pdata_len);
int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog);
int (*iw_destroy_listen)(struct iw_cm_id *cm_id);
/**
* counter_bind_qp - Bind a QP to a counter.
* @counter - The counter to be bound. If counter->id is zero then
* the driver needs to allocate a new counter and set counter->id
*/
int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp,
u32 port);
/**
* counter_unbind_qp - Unbind the qp from the dynamically-allocated
* counter and bind it onto the default one
*/
int (*counter_unbind_qp)(struct ib_qp *qp, u32 port);
/**
* counter_dealloc -De-allocate the hw counter
*/
int (*counter_dealloc)(struct rdma_counter *counter);
/**
* counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in
* the driver initialized data.
*/
struct rdma_hw_stats *(*counter_alloc_stats)(
struct rdma_counter *counter);
/**
* counter_update_stats - Query the stats value of this counter
*/
int (*counter_update_stats)(struct rdma_counter *counter);
/**
* counter_init - Initialize the driver specific rdma counter struct.
*/
void (*counter_init)(struct rdma_counter *counter);
/**
* Allows rdma drivers to add their own restrack attributes
* dumped via 'rdma stat' iproute2 command.
*/
int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
/* query driver for its ucontext properties */
int (*query_ucontext)(struct ib_ucontext *context,
struct uverbs_attr_bundle *attrs);
/*
* Provide NUMA node. This API exists for rdmavt/hfi1 only.
* Everyone else relies on Linux memory management model.
*/
int (*get_numa_node)(struct ib_device *dev);
/**
* add_sub_dev - Add a sub IB device
*/
struct ib_device *(*add_sub_dev)(struct ib_device *parent,
enum rdma_nl_dev_type type,
const char *name);
/**
* del_sub_dev - Delete a sub IB device
*/
void (*del_sub_dev)(struct ib_device *sub_dev);
/**
* ufile_cleanup - Attempt to cleanup ubojects HW resources inside
* the ufile.
*/
void (*ufile_hw_cleanup)(struct ib_uverbs_file *ufile);
/**
* report_port_event - Drivers need to implement this if they have
* some private stuff to handle when link status changes.
*/
void (*report_port_event)(struct ib_device *ibdev,
struct net_device *ndev, unsigned long event);
DECLARE_RDMA_OBJ_SIZE(ib_ah);
DECLARE_RDMA_OBJ_SIZE(ib_counters);
DECLARE_RDMA_OBJ_SIZE(ib_cq);
DECLARE_RDMA_OBJ_SIZE(ib_mw);
DECLARE_RDMA_OBJ_SIZE(ib_pd);
DECLARE_RDMA_OBJ_SIZE(ib_qp);
DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table);
DECLARE_RDMA_OBJ_SIZE(ib_srq);
DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
DECLARE_RDMA_OBJ_SIZE(ib_xrcd);
DECLARE_RDMA_OBJ_SIZE(rdma_counter);
};
struct ib_core_device {
/* device must be the first element in structure until,
* union of ib_core_device and device exists in ib_device.
*/
struct device dev;
possible_net_t rdma_net;
struct kobject *ports_kobj;
struct list_head port_list;
struct ib_device *owner; /* reach back to owner ib_device */
};
struct rdma_restrack_root;
struct ib_device {
/* Do not access @dma_device directly from ULP nor from HW drivers. */
struct device *dma_device;
struct ib_device_ops ops;
char name[IB_DEVICE_NAME_MAX];
struct rcu_head rcu_head;
struct list_head event_handler_list;
/* Protects event_handler_list */
struct rw_semaphore event_handler_rwsem;
/* Protects QP's event_handler calls and open_qp list */
spinlock_t qp_open_list_lock;
struct rw_semaphore client_data_rwsem;
struct xarray client_data;
struct mutex unregistration_lock;
/* Synchronize GID, Pkey cache entries, subnet prefix, LMC */
rwlock_t cache_lock;
/**
* port_data is indexed by port number
*/
struct ib_port_data *port_data;
int num_comp_vectors;
union {
struct device dev;
struct ib_core_device coredev;
};
/* First group is for device attributes,
* Second group is for driver provided attributes (optional).
* Third group is for the hw_stats
* It is a NULL terminated array.
*/
const struct attribute_group *groups[4];
u8 hw_stats_attr_index;
u64 uverbs_cmd_mask;
char node_desc[IB_DEVICE_NODE_DESC_MAX];
__be64 node_guid;
u32 local_dma_lkey;
u16 is_switch:1;
/* Indicates kernel verbs support, should not be used in drivers */
u16 kverbs_provider:1;
/* CQ adaptive moderation (RDMA DIM) */
u16 use_cq_dim:1;
u8 node_type;
u32 phys_port_cnt;
struct ib_device_attr attrs;
struct hw_stats_device_data *hw_stats_data;
#ifdef CONFIG_CGROUP_RDMA
struct rdmacg_device cg_device;
#endif
u32 index;
spinlock_t cq_pools_lock;
struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1];
struct rdma_restrack_root *res;
const struct uapi_definition *driver_def;
/*
* Positive refcount indicates that the device is currently
* registered and cannot be unregistered.
*/
refcount_t refcount;
struct completion unreg_completion;
struct work_struct unregistration_work;
const struct rdma_link_ops *link_ops;
/* Protects compat_devs xarray modifications */
struct mutex compat_devs_mutex;
/* Maintains compat devices for each net namespace */
struct xarray compat_devs;
/* Used by iWarp CM */
char iw_ifname[IFNAMSIZ];
u32 iw_driver_flags;
u32 lag_flags;
/* A parent device has a list of sub-devices */
struct mutex subdev_lock;
struct list_head subdev_list_head;
/* A sub device has a type and a parent */
enum rdma_nl_dev_type type;
struct ib_device *parent;
struct list_head subdev_list;
enum rdma_nl_name_assign_type name_assign_type;
};
static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
gfp_t gfp, bool is_numa_aware)
{
if (is_numa_aware && dev->ops.get_numa_node)
return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev));
return kzalloc(size, gfp);
}
struct ib_client_nl_info;
struct ib_client {
const char *name;
int (*add)(struct ib_device *ibdev);
void (*remove)(struct ib_device *, void *client_data);
void (*rename)(struct ib_device *dev, void *client_data);
int (*get_nl_info)(struct ib_device *ibdev, void *client_data,
struct ib_client_nl_info *res);
int (*get_global_nl_info)(struct ib_client_nl_info *res);
/* Returns the net_dev belonging to this ib_client and matching the
* given parameters.
* @dev: An RDMA device that the net_dev use for communication.
* @port: A physical port number on the RDMA device.
* @pkey: P_Key that the net_dev uses if applicable.
* @gid: A GID that the net_dev uses to communicate.
* @addr: An IP address the net_dev is configured with.
* @client_data: The device's client data set by ib_set_client_data().
*
* An ib_client that implements a net_dev on top of RDMA devices
* (such as IP over IB) should implement this callback, allowing the
* rdma_cm module to find the right net_dev for a given request.
*
* The caller is responsible for calling dev_put on the returned
* netdev. */
struct net_device *(*get_net_dev_by_params)(
struct ib_device *dev,
u32 port,
u16 pkey,
const union ib_gid *gid,
const struct sockaddr *addr,
void *client_data);
refcount_t uses;
struct completion uses_zero;
u32 client_id;
/* kverbs are not required by the client */
u8 no_kverbs_req:1;
};
/*
* IB block DMA iterator
*
* Iterates the DMA-mapped SGL in contiguous memory blocks aligned
* to a HW supported page size.
*/
struct ib_block_iter {
/* internal states */
struct scatterlist *__sg; /* sg holding the current aligned block */
dma_addr_t __dma_addr; /* unaligned DMA address of this block */
size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */
unsigned int __sg_nents; /* number of SG entries */
unsigned int __sg_advance; /* number of bytes to advance in sg in next step */
unsigned int __pg_bit; /* alignment of current block */
};
struct ib_device *_ib_alloc_device(size_t size);
#define ib_alloc_device(drv_struct, member) \
container_of(_ib_alloc_device(sizeof(struct drv_struct) + \
BUILD_BUG_ON_ZERO(offsetof( \
struct drv_struct, member))), \
struct drv_struct, member)
void ib_dealloc_device(struct ib_device *device);
void ib_get_device_fw_str(struct ib_device *device, char *str);
int ib_register_device(struct ib_device *device, const char *name,
struct device *dma_device);
void ib_unregister_device(struct ib_device *device);
void ib_unregister_driver(enum rdma_driver_id driver_id);
void ib_unregister_device_and_put(struct ib_device *device);
void ib_unregister_device_queued(struct ib_device *ib_dev);
int ib_register_client (struct ib_client *client);
void ib_unregister_client(struct ib_client *client);
void __rdma_block_iter_start(struct ib_block_iter *biter,
struct scatterlist *sglist,
unsigned int nents,
unsigned long pgsz);
bool __rdma_block_iter_next(struct ib_block_iter *biter);
/**
* rdma_block_iter_dma_address - get the aligned dma address of the current
* block held by the block iterator.
* @biter: block iterator holding the memory block
*/
static inline dma_addr_t
rdma_block_iter_dma_address(struct ib_block_iter *biter)
{
return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1);
}
/**
* rdma_for_each_block - iterate over contiguous memory blocks of the sg list
* @sglist: sglist to iterate over
* @biter: block iterator holding the memory block
* @nents: maximum number of sg entries to iterate over
* @pgsz: best HW supported page size to use
*
* Callers may use rdma_block_iter_dma_address() to get each
* blocks aligned DMA address.
*/
#define rdma_for_each_block(sglist, biter, nents, pgsz) \
for (__rdma_block_iter_start(biter, sglist, nents, \
pgsz); \
__rdma_block_iter_next(biter);)
/**
* ib_get_client_data - Get IB client context
* @device:Device to get context for
* @client:Client to get context for
*
* ib_get_client_data() returns the client context data set with
* ib_set_client_data(). This can only be called while the client is
* registered to the device, once the ib_client remove() callback returns this
* cannot be called.
*/
static inline void *ib_get_client_data(struct ib_device *device,
struct ib_client *client)
{
return xa_load(&device->client_data, client->client_id);
}
void ib_set_client_data(struct ib_device *device, struct ib_client *client,
void *data);
void ib_set_device_ops(struct ib_device *device,
const struct ib_device_ops *ops);
int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma,
unsigned long pfn, unsigned long size, pgprot_t prot,
struct rdma_user_mmap_entry *entry);
int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length);
int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length, u32 min_pgoff,
u32 max_pgoff);
#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
void rdma_user_mmap_disassociate(struct ib_device *device);
#else
static inline void rdma_user_mmap_disassociate(struct ib_device *device)
{
}
#endif
static inline int
rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext,
struct rdma_user_mmap_entry *entry,
size_t length, u32 pgoff)
{
return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff,
pgoff);
}
struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext,
unsigned long pgoff);
struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get(struct ib_ucontext *ucontext,
struct vm_area_struct *vma);
void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry);
void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry);
static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len)
{
return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0;
}
static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
{
return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
}
static inline bool ib_is_buffer_cleared(const void __user *p,
size_t len)
{
bool ret;
u8 *buf;
if (len > USHRT_MAX)
return false;
buf = memdup_user(p, len);
if (IS_ERR(buf))
return false;
ret = !memchr_inv(buf, 0, len);
kfree(buf);
return ret;
}
static inline bool ib_is_udata_cleared(struct ib_udata *udata,
size_t offset,
size_t len)
{
return ib_is_buffer_cleared(udata->inbuf + offset, len);
}
/**
* ib_modify_qp_is_ok - Check that the supplied attribute mask
* contains all required attributes and no attributes not allowed for
* the given QP state transition.
* @cur_state: Current QP state
* @next_state: Next QP state
* @type: QP type
* @mask: Mask of supplied QP attributes
*
* This function is a helper function that a low-level driver's
* modify_qp method can use to validate the consumer's input. It
* checks that cur_state and next_state are valid QP states, that a
* transition from cur_state to next_state is allowed by the IB spec,
* and that the attribute mask supplied is allowed for the transition.
*/
bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
enum ib_qp_type type, enum ib_qp_attr_mask mask);
void ib_register_event_handler(struct ib_event_handler *event_handler);
void ib_unregister_event_handler(struct ib_event_handler *event_handler);
void ib_dispatch_event(const struct ib_event *event);
int ib_query_port(struct ib_device *device,
u32 port_num, struct ib_port_attr *port_attr);
enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
u32 port_num);
/**
* rdma_cap_ib_switch - Check if the device is IB switch
* @device: Device to check
*
* Device driver is responsible for setting is_switch bit on
* in ib_device structure at init time.
*
* Return: true if the device is IB switch.
*/
static inline bool rdma_cap_ib_switch(const struct ib_device *device)
{
return device->is_switch;
}
/**
* rdma_start_port - Return the first valid port number for the device
* specified
*
* @device: Device to be checked
*
* Return start port number
*/
static inline u32 rdma_start_port(const struct ib_device *device)
{
return rdma_cap_ib_switch(device) ? 0 : 1;
}
/**
* rdma_for_each_port - Iterate over all valid port numbers of the IB device
* @device - The struct ib_device * to iterate over
* @iter - The unsigned int to store the port number
*/
#define rdma_for_each_port(device, iter) \
for (iter = rdma_start_port(device + \
BUILD_BUG_ON_ZERO(!__same_type(u32, \
iter))); \
iter <= rdma_end_port(device); iter++)
/**
* rdma_end_port - Return the last valid port number for the device
* specified
*
* @device: Device to be checked
*
* Return last port number
*/
static inline u32 rdma_end_port(const struct ib_device *device)
{
return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt;
}
static inline int rdma_is_port_valid(const struct ib_device *device,
unsigned int port)
{
return (port >= rdma_start_port(device) &&
port <= rdma_end_port(device));
}
static inline bool rdma_is_grh_required(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_PORT_IB_GRH_REQUIRED;
}
static inline bool rdma_protocol_ib(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_IB;
}
static inline bool rdma_protocol_roce(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
(RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP);
}
static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
}
static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_ROCE;
}
static inline bool rdma_protocol_iwarp(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_IWARP;
}
static inline bool rdma_ib_or_roce(const struct ib_device *device,
u32 port_num)
{
return rdma_protocol_ib(device, port_num) ||
rdma_protocol_roce(device, port_num);
}
static inline bool rdma_protocol_raw_packet(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_RAW_PACKET;
}
static inline bool rdma_protocol_usnic(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_PROT_USNIC;
}
/**
* rdma_cap_ib_mad - Check if the port of a device supports Infiniband
* Management Datagrams.
* @device: Device to check
* @port_num: Port number to check
*
* Management Datagrams (MAD) are a required part of the InfiniBand
* specification and are supported on all InfiniBand devices. A slightly
* extended version are also supported on OPA interfaces.
*
* Return: true if the port supports sending/receiving of MAD packets.
*/
static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_MAD;
}
/**
* rdma_cap_opa_mad - Check if the port of device provides support for OPA
* Management Datagrams.
* @device: Device to check
* @port_num: Port number to check
*
* Intel OmniPath devices extend and/or replace the InfiniBand Management
* datagrams with their own versions. These OPA MADs share many but not all of
* the characteristics of InfiniBand MADs.
*
* OPA MADs differ in the following ways:
*
* 1) MADs are variable size up to 2K
* IBTA defined MADs remain fixed at 256 bytes
* 2) OPA SMPs must carry valid PKeys
* 3) OPA SMP packets are a different format
*
* Return: true if the port supports OPA MAD packet formats.
*/
static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_OPA_MAD;
}
/**
* rdma_cap_ib_smi - Check if the port of a device provides an Infiniband
* Subnet Management Agent (SMA) on the Subnet Management Interface (SMI).
* @device: Device to check
* @port_num: Port number to check
*
* Each InfiniBand node is required to provide a Subnet Management Agent
* that the subnet manager can access. Prior to the fabric being fully
* configured by the subnet manager, the SMA is accessed via a well known
* interface called the Subnet Management Interface (SMI). This interface
* uses directed route packets to communicate with the SM to get around the
* chicken and egg problem of the SM needing to know what's on the fabric
* in order to configure the fabric, and needing to configure the fabric in
* order to send packets to the devices on the fabric. These directed
* route packets do not need the fabric fully configured in order to reach
* their destination. The SMI is the only method allowed to send
* directed route packets on an InfiniBand fabric.
*
* Return: true if the port provides an SMI.
*/
static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_SMI;
}
/**
* rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
* Communication Manager.
* @device: Device to check
* @port_num: Port number to check
*
* The InfiniBand Communication Manager is one of many pre-defined General
* Service Agents (GSA) that are accessed via the General Service
* Interface (GSI). It's role is to facilitate establishment of connections
* between nodes as well as other management related tasks for established
* connections.
*
* Return: true if the port supports an IB CM (this does not guarantee that
* a CM is actually running however).
*/
static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_CM;
}
/**
* rdma_cap_iw_cm - Check if the port of device has the capability IWARP
* Communication Manager.
* @device: Device to check
* @port_num: Port number to check
*
* Similar to above, but specific to iWARP connections which have a different
* managment protocol than InfiniBand.
*
* Return: true if the port supports an iWARP CM (this does not guarantee that
* a CM is actually running however).
*/
static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IW_CM;
}
/**
* rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
* Subnet Administration.
* @device: Device to check
* @port_num: Port number to check
*
* An InfiniBand Subnet Administration (SA) service is a pre-defined General
* Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand
* fabrics, devices should resolve routes to other hosts by contacting the
* SA to query the proper route.
*
* Return: true if the port should act as a client to the fabric Subnet
* Administration interface. This does not imply that the SA service is
* running locally.
*/
static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_IB_SA;
}
/**
* rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
* Multicast.
* @device: Device to check
* @port_num: Port number to check
*
* InfiniBand multicast registration is more complex than normal IPv4 or
* IPv6 multicast registration. Each Host Channel Adapter must register
* with the Subnet Manager when it wishes to join a multicast group. It
* should do so only once regardless of how many queue pairs it subscribes
* to this group. And it should leave the group only after all queue pairs
* attached to the group have been detached.
*
* Return: true if the port must undertake the additional adminstrative
* overhead of registering/unregistering with the SM and tracking of the
* total number of queue pairs attached to the multicast group.
*/
static inline bool rdma_cap_ib_mcast(const struct ib_device *device,
u32 port_num)
{
return rdma_cap_ib_sa(device, port_num);
}
/**
* rdma_cap_af_ib - Check if the port of device has the capability
* Native Infiniband Address.
* @device: Device to check
* @port_num: Port number to check
*
* InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default
* GID. RoCE uses a different mechanism, but still generates a GID via
* a prescribed mechanism and port specific data.
*
* Return: true if the port uses a GID address to identify devices on the
* network.
*/
static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_AF_IB;
}
/**
* rdma_cap_eth_ah - Check if the port of device has the capability
* Ethernet Address Handle.
* @device: Device to check
* @port_num: Port number to check
*
* RoCE is InfiniBand over Ethernet, and it uses a well defined technique
* to fabricate GIDs over Ethernet/IP specific addresses native to the
* port. Normally, packet headers are generated by the sending host
* adapter, but when sending connectionless datagrams, we must manually
* inject the proper headers for the fabric we are communicating over.
*
* Return: true if we are running as a RoCE port and must force the
* addition of a Global Route Header built from our Ethernet Address
* Handle into our header list for connectionless packets.
*/
static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num)
{
return device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_ETH_AH;
}
/**
* rdma_cap_opa_ah - Check if the port of device supports
* OPA Address handles
* @device: Device to check
* @port_num: Port number to check
*
* Return: true if we are running on an OPA device which supports
* the extended OPA addressing.
*/
static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num)
{
return (device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH;
}
/**
* rdma_max_mad_size - Return the max MAD size required by this RDMA Port.
*
* @device: Device
* @port_num: Port number
*
* This MAD size includes the MAD headers and MAD payload. No other headers
* are included.
*
* Return the max MAD size required by the Port. Will return 0 if the port
* does not support MADs
*/
static inline size_t rdma_max_mad_size(const struct ib_device *device,
u32 port_num)
{
return device->port_data[port_num].immutable.max_mad_size;
}
/**
* rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table
* @device: Device to check
* @port_num: Port number to check
*
* RoCE GID table mechanism manages the various GIDs for a device.
*
* NOTE: if allocating the port's GID table has failed, this call will still
* return true, but any RoCE GID table API will fail.
*
* Return: true if the port uses RoCE GID table mechanism in order to manage
* its GIDs.
*/
static inline bool rdma_cap_roce_gid_table(const struct ib_device *device,
u32 port_num)
{
return rdma_protocol_roce(device, port_num) &&
device->ops.add_gid && device->ops.del_gid;
}
/*
* Check if the device supports READ W/ INVALIDATE.
*/
static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
{
/*
* iWarp drivers must support READ W/ INVALIDATE. No other protocol
* has support for it yet.
*/
return rdma_protocol_iwarp(dev, port_num);
}
/**
* rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not.
* @device: Device
* @port_num: 1 based Port number
*
* Return true if port is an Intel OPA port , false if not
*/
static inline bool rdma_core_cap_opa_port(struct ib_device *device,
u32 port_num)
{
return (device->port_data[port_num].immutable.core_cap_flags &
RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA;
}
/**
* rdma_mtu_enum_to_int - Return the mtu of the port as an integer value.
* @device: Device
* @port_num: Port number
* @mtu: enum value of MTU
*
* Return the MTU size supported by the port as an integer value. Will return
* -1 if enum value of mtu is not supported.
*/
static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port,
int mtu)
{
if (rdma_core_cap_opa_port(device, port))
return opa_mtu_enum_to_int((enum opa_mtu)mtu);
else
return ib_mtu_enum_to_int((enum ib_mtu)mtu);
}
/**
* rdma_mtu_from_attr - Return the mtu of the port from the port attribute.
* @device: Device
* @port_num: Port number
* @attr: port attribute
*
* Return the MTU size supported by the port as an integer value.
*/
static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port,
struct ib_port_attr *attr)
{
if (rdma_core_cap_opa_port(device, port))
return attr->phys_mtu;
else
return ib_mtu_enum_to_int(attr->max_mtu);
}
int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port,
int state);
int ib_get_vf_config(struct ib_device *device, int vf, u32 port,
struct ifla_vf_info *info);
int ib_get_vf_stats(struct ib_device *device, int vf, u32 port,
struct ifla_vf_stats *stats);
int ib_get_vf_guid(struct ib_device *device, int vf, u32 port,
struct ifla_vf_guid *node_guid,
struct ifla_vf_guid *port_guid);
int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid,
int type);
int ib_query_pkey(struct ib_device *device,
u32 port_num, u16 index, u16 *pkey);
int ib_modify_device(struct ib_device *device,
int device_modify_mask,
struct ib_device_modify *device_modify);
int ib_modify_port(struct ib_device *device,
u32 port_num, int port_modify_mask,
struct ib_port_modify *port_modify);
int ib_find_gid(struct ib_device *device, union ib_gid *gid,
u32 *port_num, u16 *index);
int ib_find_pkey(struct ib_device *device,
u32 port_num, u16 pkey, u16 *index);
enum ib_pd_flags {
/*
* Create a memory registration for all memory in the system and place
* the rkey for it into pd->unsafe_global_rkey. This can be used by
* ULPs to avoid the overhead of dynamic MRs.
*
* This flag is generally considered unsafe and must only be used in
* extremly trusted environments. Every use of it will log a warning
* in the kernel log.
*/
IB_PD_UNSAFE_GLOBAL_RKEY = 0x01,
};
struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
const char *caller);
/**
* ib_alloc_pd - Allocates an unused protection domain.
* @device: The device on which to allocate the protection domain.
* @flags: protection domain flags
*
* A protection domain object provides an association between QPs, shared
* receive queues, address handles, memory regions, and memory windows.
*
* Every PD has a local_dma_lkey which can be used as the lkey value for local
* memory operations.
*/
#define ib_alloc_pd(device, flags) \
__ib_alloc_pd((device), (flags), KBUILD_MODNAME)
int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata);
/**
* ib_dealloc_pd - Deallocate kernel PD
* @pd: The protection domain
*
* NOTE: for user PD use ib_dealloc_pd_user with valid udata!
*/
static inline void ib_dealloc_pd(struct ib_pd *pd)
{
int ret = ib_dealloc_pd_user(pd, NULL);
WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail");
}
enum rdma_create_ah_flags {
/* In a sleepable context */
RDMA_CREATE_AH_SLEEPABLE = BIT(0),
};
/**
* rdma_create_ah - Creates an address handle for the given address vector.
* @pd: The protection domain associated with the address handle.
* @ah_attr: The attributes of the address vector.
* @flags: Create address handle flags (see enum rdma_create_ah_flags).
*
* The address handle is used to reference a local or global destination
* in all UD QP post sends.
*/
struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr,
u32 flags);
/**
* rdma_create_user_ah - Creates an address handle for the given address vector.
* It resolves destination mac address for ah attribute of RoCE type.
* @pd: The protection domain associated with the address handle.
* @ah_attr: The attributes of the address vector.
* @udata: pointer to user's input output buffer information need by
* provider driver.
*
* It returns 0 on success and returns appropriate error code on error.
* The address handle is used to reference a local or global destination
* in all UD QP post sends.
*/
struct ib_ah *rdma_create_user_ah(struct ib_pd *pd,
struct rdma_ah_attr *ah_attr,
struct ib_udata *udata);
/**
* ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header
* work completion.
* @hdr: the L3 header to parse
* @net_type: type of header to parse
* @sgid: place to store source gid
* @dgid: place to store destination gid
*/
int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
enum rdma_network_type net_type,
union ib_gid *sgid, union ib_gid *dgid);
/**
* ib_get_rdma_header_version - Get the header version
* @hdr: the L3 header to parse
*/
int ib_get_rdma_header_version(const union rdma_network_hdr *hdr);
/**
* ib_init_ah_attr_from_wc - Initializes address handle attributes from a
* work completion.
* @device: Device on which the received message arrived.
* @port_num: Port on which the received message arrived.
* @wc: Work completion associated with the received message.
* @grh: References the received global route header. This parameter is
* ignored unless the work completion indicates that the GRH is valid.
* @ah_attr: Returned attributes that can be used when creating an address
* handle for replying to the message.
* When ib_init_ah_attr_from_wc() returns success,
* (a) for IB link layer it optionally contains a reference to SGID attribute
* when GRH is present for IB link layer.
* (b) for RoCE link layer it contains a reference to SGID attribute.
* User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID
* attributes which are initialized using ib_init_ah_attr_from_wc().
*
*/
int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num,
const struct ib_wc *wc, const struct ib_grh *grh,
struct rdma_ah_attr *ah_attr);
/**
* ib_create_ah_from_wc - Creates an address handle associated with the
* sender of the specified work completion.
* @pd: The protection domain associated with the address handle.
* @wc: Work completion information associated with a received message.
* @grh: References the received global route header. This parameter is
* ignored unless the work completion indicates that the GRH is valid.
* @port_num: The outbound port number to associate with the address.
*
* The address handle is used to reference a local or global destination
* in all UD QP post sends.
*/
struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
const struct ib_grh *grh, u32 port_num);
/**
* rdma_modify_ah - Modifies the address vector associated with an address
* handle.
* @ah: The address handle to modify.
* @ah_attr: The new address vector attributes to associate with the
* address handle.
*/
int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
/**
* rdma_query_ah - Queries the address vector associated with an address
* handle.
* @ah: The address handle to query.
* @ah_attr: The address vector attributes associated with the address
* handle.
*/
int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
enum rdma_destroy_ah_flags {
/* In a sleepable context */
RDMA_DESTROY_AH_SLEEPABLE = BIT(0),
};
/**
* rdma_destroy_ah_user - Destroys an address handle.
* @ah: The address handle to destroy.
* @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags).
* @udata: Valid user data or NULL for kernel objects
*/
int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata);
/**
* rdma_destroy_ah - Destroys an kernel address handle.
* @ah: The address handle to destroy.
* @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags).
*
* NOTE: for user ah use rdma_destroy_ah_user with valid udata!
*/
static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags)
{
int ret = rdma_destroy_ah_user(ah, flags, NULL);
WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail");
}
struct ib_srq *ib_create_srq_user(struct ib_pd *pd,
struct ib_srq_init_attr *srq_init_attr,
struct ib_usrq_object *uobject,
struct ib_udata *udata);
static inline struct ib_srq *
ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr)
{
if (!pd->device->ops.create_srq)
return ERR_PTR(-EOPNOTSUPP);
return ib_create_srq_user(pd, srq_init_attr, NULL, NULL);
}
/**
* ib_modify_srq - Modifies the attributes for the specified SRQ.
* @srq: The SRQ to modify.
* @srq_attr: On input, specifies the SRQ attributes to modify. On output,
* the current values of selected SRQ attributes are returned.
* @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ
* are being modified.
*
* The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or
* IB_SRQ_LIMIT to set the SRQ's limit and request notification when
* the number of receives queued drops below the limit.
*/
int ib_modify_srq(struct ib_srq *srq,
struct ib_srq_attr *srq_attr,
enum ib_srq_attr_mask srq_attr_mask);
/**
* ib_query_srq - Returns the attribute list and current values for the
* specified SRQ.
* @srq: The SRQ to query.
* @srq_attr: The attributes of the specified SRQ.
*/
int ib_query_srq(struct ib_srq *srq,
struct ib_srq_attr *srq_attr);
/**
* ib_destroy_srq_user - Destroys the specified SRQ.
* @srq: The SRQ to destroy.
* @udata: Valid user data or NULL for kernel objects
*/
int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata);
/**
* ib_destroy_srq - Destroys the specified kernel SRQ.
* @srq: The SRQ to destroy.
*
* NOTE: for user srq use ib_destroy_srq_user with valid udata!
*/
static inline void ib_destroy_srq(struct ib_srq *srq)
{
int ret = ib_destroy_srq_user(srq, NULL);
WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail");
}
/**
* ib_post_srq_recv - Posts a list of work requests to the specified SRQ.
* @srq: The SRQ to post the work request on.
* @recv_wr: A list of work requests to post on the receive queue.
* @bad_recv_wr: On an immediate failure, this parameter will reference
* the work request that failed to be posted on the QP.
*/
static inline int ib_post_srq_recv(struct ib_srq *srq,
const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr)
{
const struct ib_recv_wr *dummy;
return srq->device->ops.post_srq_recv(srq, recv_wr,
bad_recv_wr ? : &dummy);
}
struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd,
struct ib_qp_init_attr *qp_init_attr,
const char *caller);
/**
* ib_create_qp - Creates a kernel QP associated with the specific protection
* domain.
* @pd: The protection domain associated with the QP.
* @init_attr: A list of initial attributes required to create the
* QP. If QP creation succeeds, then the attributes are updated to
* the actual capabilities of the created QP.
*/
static inline struct ib_qp *ib_create_qp(struct ib_pd *pd,
struct ib_qp_init_attr *init_attr)
{
return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME);
}
/**
* ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
* @qp: The QP to modify.
* @attr: On input, specifies the QP attributes to modify. On output,
* the current values of selected QP attributes are returned.
* @attr_mask: A bit-mask used to specify which attributes of the QP
* are being modified.
* @udata: pointer to user's input output buffer information
* are being modified.
* It returns 0 on success and returns appropriate error code on error.
*/
int ib_modify_qp_with_udata(struct ib_qp *qp,
struct ib_qp_attr *attr,
int attr_mask,
struct ib_udata *udata);
/**
* ib_modify_qp - Modifies the attributes for the specified QP and then
* transitions the QP to the given state.
* @qp: The QP to modify.
* @qp_attr: On input, specifies the QP attributes to modify. On output,
* the current values of selected QP attributes are returned.
* @qp_attr_mask: A bit-mask used to specify which attributes of the QP
* are being modified.
*/
int ib_modify_qp(struct ib_qp *qp,
struct ib_qp_attr *qp_attr,
int qp_attr_mask);
/**
* ib_query_qp - Returns the attribute list and current values for the
* specified QP.
* @qp: The QP to query.
* @qp_attr: The attributes of the specified QP.
* @qp_attr_mask: A bit-mask used to select specific attributes to query.
* @qp_init_attr: Additional attributes of the selected QP.
*
* The qp_attr_mask may be used to limit the query to gathering only the
* selected attributes.
*/
int ib_query_qp(struct ib_qp *qp,
struct ib_qp_attr *qp_attr,
int qp_attr_mask,
struct ib_qp_init_attr *qp_init_attr);
/**
* ib_destroy_qp - Destroys the specified QP.
* @qp: The QP to destroy.
* @udata: Valid udata or NULL for kernel objects
*/
int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata);
/**
* ib_destroy_qp - Destroys the specified kernel QP.
* @qp: The QP to destroy.
*
* NOTE: for user qp use ib_destroy_qp_user with valid udata!
*/
static inline int ib_destroy_qp(struct ib_qp *qp)
{
return ib_destroy_qp_user(qp, NULL);
}
/**
* ib_open_qp - Obtain a reference to an existing sharable QP.
* @xrcd - XRC domain
* @qp_open_attr: Attributes identifying the QP to open.
*
* Returns a reference to a sharable QP.
*/
struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd,
struct ib_qp_open_attr *qp_open_attr);
/**
* ib_close_qp - Release an external reference to a QP.
* @qp: The QP handle to release
*
* The opened QP handle is released by the caller. The underlying
* shared QP is not destroyed until all internal references are released.
*/
int ib_close_qp(struct ib_qp *qp);
/**
* ib_post_send - Posts a list of work requests to the send queue of
* the specified QP.
* @qp: The QP to post the work request on.
* @send_wr: A list of work requests to post on the send queue.
* @bad_send_wr: On an immediate failure, this parameter will reference
* the work request that failed to be posted on the QP.
*
* While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate
* error is returned, the QP state shall not be affected,
* ib_post_send() will return an immediate error after queueing any
* earlier work requests in the list.
*/
static inline int ib_post_send(struct ib_qp *qp,
const struct ib_send_wr *send_wr,
const struct ib_send_wr **bad_send_wr)
{
const struct ib_send_wr *dummy;
return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy);
}
/**
* ib_post_recv - Posts a list of work requests to the receive queue of
* the specified QP.
* @qp: The QP to post the work request on.
* @recv_wr: A list of work requests to post on the receive queue.
* @bad_recv_wr: On an immediate failure, this parameter will reference
* the work request that failed to be posted on the QP.
*/
static inline int ib_post_recv(struct ib_qp *qp,
const struct ib_recv_wr *recv_wr,
const struct ib_recv_wr **bad_recv_wr)
{
const struct ib_recv_wr *dummy;
return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy);
}
struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
int comp_vector, enum ib_poll_context poll_ctx,
const char *caller);
static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
int nr_cqe, int comp_vector,
enum ib_poll_context poll_ctx)
{
return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
KBUILD_MODNAME);
}
struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
int nr_cqe, enum ib_poll_context poll_ctx,
const char *caller);
/**
* ib_alloc_cq_any: Allocate kernel CQ
* @dev: The IB device
* @private: Private data attached to the CQE
* @nr_cqe: Number of CQEs in the CQ
* @poll_ctx: Context used for polling the CQ
*/
static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev,
void *private, int nr_cqe,
enum ib_poll_context poll_ctx)
{
return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx,
KBUILD_MODNAME);
}
void ib_free_cq(struct ib_cq *cq);
int ib_process_cq_direct(struct ib_cq *cq, int budget);
/**
* ib_create_cq - Creates a CQ on the specified device.
* @device: The device on which to create the CQ.
* @comp_handler: A user-specified callback that is invoked when a
* completion event occurs on the CQ.
* @event_handler: A user-specified callback that is invoked when an
* asynchronous event not associated with a completion occurs on the CQ.
* @cq_context: Context associated with the CQ returned to the user via
* the associated completion and event handlers.
* @cq_attr: The attributes the CQ should be created upon.
*
* Users can examine the cq structure to determine the actual CQ size.
*/
struct ib_cq *__ib_create_cq(struct ib_device *device,
ib_comp_handler comp_handler,
void (*event_handler)(struct ib_event *, void *),
void *cq_context,
const struct ib_cq_init_attr *cq_attr,
const char *caller);
#define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \
__ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME)
/**
* ib_resize_cq - Modifies the capacity of the CQ.
* @cq: The CQ to resize.
* @cqe: The minimum size of the CQ.
*
* Users can examine the cq structure to determine the actual CQ size.
*/
int ib_resize_cq(struct ib_cq *cq, int cqe);
/**
* rdma_set_cq_moderation - Modifies moderation params of the CQ
* @cq: The CQ to modify.
* @cq_count: number of CQEs that will trigger an event
* @cq_period: max period of time in usec before triggering an event
*
*/
int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period);
/**
* ib_destroy_cq_user - Destroys the specified CQ.
* @cq: The CQ to destroy.
* @udata: Valid user data or NULL for kernel objects
*/
int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata);
/**
* ib_destroy_cq - Destroys the specified kernel CQ.
* @cq: The CQ to destroy.
*
* NOTE: for user cq use ib_destroy_cq_user with valid udata!
*/
static inline void ib_destroy_cq(struct ib_cq *cq)
{
int ret = ib_destroy_cq_user(cq, NULL);
WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
}
/**
* ib_poll_cq - poll a CQ for completion(s)
* @cq:the CQ being polled
* @num_entries:maximum number of completions to return
* @wc:array of at least @num_entries &struct ib_wc where completions
* will be returned
*
* Poll a CQ for (possibly multiple) completions. If the return value
* is < 0, an error occurred. If the return value is >= 0, it is the
* number of completions returned. If the return value is
* non-negative and < num_entries, then the CQ was emptied.
*/
static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
struct ib_wc *wc)
{
return cq->device->ops.poll_cq(cq, num_entries, wc);
}
/**
* ib_req_notify_cq - Request completion notification on a CQ.
* @cq: The CQ to generate an event for.
* @flags:
* Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP
* to request an event on the next solicited event or next work
* completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS
* may also be |ed in to request a hint about missed events, as
* described below.
*
* Return Value:
* < 0 means an error occurred while requesting notification
* == 0 means notification was requested successfully, and if
* IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events
* were missed and it is safe to wait for another event. In
* this case is it guaranteed that any work completions added
* to the CQ since the last CQ poll will trigger a completion
* notification event.
* > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed
* in. It means that the consumer must poll the CQ again to
* make sure it is empty to avoid missing an event because of a
* race between requesting notification and an entry being
* added to the CQ. This return value means it is possible
* (but not guaranteed) that a work completion has been added
* to the CQ since the last poll without triggering a
* completion notification event.
*/
static inline int ib_req_notify_cq(struct ib_cq *cq,
enum ib_cq_notify_flags flags)
{
return cq->device->ops.req_notify_cq(cq, flags);
}
struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe,
int comp_vector_hint,
enum ib_poll_context poll_ctx);
void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe);
/*
* Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to
* NULL. This causes the ib_dma* helpers to just stash the kernel virtual
* address into the dma address.
*/
static inline bool ib_uses_virt_dma(struct ib_device *dev)
{
return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device;
}
/*
* Check if a IB device's underlying DMA mapping supports P2PDMA transfers.
*/
static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev)
{
if (ib_uses_virt_dma(dev))
return false;
return dma_pci_p2pdma_supported(dev->dma_device);
}
/**
* ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer
* @dma_addr: The DMA address
*
* Used by ib_uses_virt_dma() devices to get back to the kernel pointer after
* going through the dma_addr marshalling.
*/
static inline void *ib_virt_dma_to_ptr(u64 dma_addr)
{
/* virt_dma mode maps the kvs's directly into the dma addr */
return (void *)(uintptr_t)dma_addr;
}
/**
* ib_virt_dma_to_page - Convert a dma_addr to a struct page
* @dma_addr: The DMA address
*
* Used by ib_uses_virt_dma() device to get back to the struct page after going
* through the dma_addr marshalling.
*/
static inline struct page *ib_virt_dma_to_page(u64 dma_addr)
{
return virt_to_page(ib_virt_dma_to_ptr(dma_addr));
}
/**
* ib_dma_mapping_error - check a DMA addr for error
* @dev: The device for which the dma_addr was created
* @dma_addr: The DMA address to check
*/
static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
{
if (ib_uses_virt_dma(dev))
return 0;
return dma_mapping_error(dev->dma_device, dma_addr);
}
/**
* ib_dma_map_single - Map a kernel virtual address to DMA address
* @dev: The device for which the dma_addr is to be created
* @cpu_addr: The kernel virtual address
* @size: The size of the region in bytes
* @direction: The direction of the DMA
*/
static inline u64 ib_dma_map_single(struct ib_device *dev,
void *cpu_addr, size_t size,
enum dma_data_direction direction)
{
if (ib_uses_virt_dma(dev))
return (uintptr_t)cpu_addr;
return dma_map_single(dev->dma_device, cpu_addr, size, direction);
}
/**
* ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single()
* @dev: The device for which the DMA address was created
* @addr: The DMA address
* @size: The size of the region in bytes
* @direction: The direction of the DMA
*/
static inline void ib_dma_unmap_single(struct ib_device *dev,
u64 addr, size_t size,
enum dma_data_direction direction)
{
if (!ib_uses_virt_dma(dev))
dma_unmap_single(dev->dma_device, addr, size, direction);
}
/**
* ib_dma_map_page - Map a physical page to DMA address
* @dev: The device for which the dma_addr is to be created
* @page: The page to be mapped
* @offset: The offset within the page
* @size: The size of the region in bytes
* @direction: The direction of the DMA
*/
static inline u64 ib_dma_map_page(struct ib_device *dev,
struct page *page,
unsigned long offset,
size_t size,
enum dma_data_direction direction)
{
if (ib_uses_virt_dma(dev))
return (uintptr_t)(page_address(page) + offset);
return dma_map_page(dev->dma_device, page, offset, size, direction);
}
/**
* ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page()
* @dev: The device for which the DMA address was created
* @addr: The DMA address
* @size: The size of the region in bytes
* @direction: The direction of the DMA
*/
static inline void ib_dma_unmap_page(struct ib_device *dev,
u64 addr, size_t size,
enum dma_data_direction direction)
{
if (!ib_uses_virt_dma(dev))
dma_unmap_page(dev->dma_device, addr, size, direction);
}
int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents);
static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
if (ib_uses_virt_dma(dev))
return ib_dma_virt_map_sg(dev, sg, nents);
return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
dma_attrs);
}
static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
if (!ib_uses_virt_dma(dev))
dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction,
dma_attrs);
}
/**
* ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses
* @dev: The device for which the DMA addresses are to be created
* @sg: The sg_table object describing the buffer
* @direction: The direction of the DMA
* @attrs: Optional DMA attributes for the map operation
*/
static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev,
struct sg_table *sgt,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
int nents;
if (ib_uses_virt_dma(dev)) {
nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents);
if (!nents)
return -EIO;
sgt->nents = nents;
return 0;
}
return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs);
}
static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev,
struct sg_table *sgt,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
if (!ib_uses_virt_dma(dev))
dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs);
}
/**
* ib_dma_map_sg - Map a scatter/gather list to DMA addresses
* @dev: The device for which the DMA addresses are to be created
* @sg: The array of scatter/gather entries
* @nents: The number of scatter/gather entries
* @direction: The direction of the DMA
*/
static inline int ib_dma_map_sg(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction)
{
return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0);
}
/**
* ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses
* @dev: The device for which the DMA addresses were created
* @sg: The array of scatter/gather entries
* @nents: The number of scatter/gather entries
* @direction: The direction of the DMA
*/
static inline void ib_dma_unmap_sg(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction)
{
ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0);
}
/**
* ib_dma_max_seg_size - Return the size limit of a single DMA transfer
* @dev: The device to query
*
* The returned value represents a size in bytes.
*/
static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev)
{
if (ib_uses_virt_dma(dev))
return UINT_MAX;
return dma_get_max_seg_size(dev->dma_device);
}
/**
* ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU
* @dev: The device for which the DMA address was created
* @addr: The DMA address
* @size: The size of the region in bytes
* @dir: The direction of the DMA
*/
static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev,
u64 addr,
size_t size,
enum dma_data_direction dir)
{
if (!ib_uses_virt_dma(dev))
dma_sync_single_for_cpu(dev->dma_device, addr, size, dir);
}
/**
* ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device
* @dev: The device for which the DMA address was created
* @addr: The DMA address
* @size: The size of the region in bytes
* @dir: The direction of the DMA
*/
static inline void ib_dma_sync_single_for_device(struct ib_device *dev,
u64 addr,
size_t size,
enum dma_data_direction dir)
{
if (!ib_uses_virt_dma(dev))
dma_sync_single_for_device(dev->dma_device, addr, size, dir);
}
/* ib_reg_user_mr - register a memory region for virtual addresses from kernel
* space. This function should be called when 'current' is the owning MM.
*/
struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int mr_access_flags);
/* ib_advise_mr - give an advice about an address range in a memory region */
int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
u32 flags, struct ib_sge *sg_list, u32 num_sge);
/**
* ib_dereg_mr_user - Deregisters a memory region and removes it from the
* HCA translation table.
* @mr: The memory region to deregister.
* @udata: Valid user data or NULL for kernel object
*
* This function can fail, if the memory region has memory windows bound to it.
*/
int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata);
/**
* ib_dereg_mr - Deregisters a kernel memory region and removes it from the
* HCA translation table.
* @mr: The memory region to deregister.
*
* This function can fail, if the memory region has memory windows bound to it.
*
* NOTE: for user mr use ib_dereg_mr_user with valid udata!
*/
static inline int ib_dereg_mr(struct ib_mr *mr)
{
return ib_dereg_mr_user(mr, NULL);
}
struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
u32 max_num_sg);
struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
u32 max_num_data_sg,
u32 max_num_meta_sg);
/**
* ib_update_fast_reg_key - updates the key portion of the fast_reg MR
* R_Key and L_Key.
* @mr - struct ib_mr pointer to be updated.
* @newkey - new key to be used.
*/
static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey)
{
mr->lkey = (mr->lkey & 0xffffff00) | newkey;
mr->rkey = (mr->rkey & 0xffffff00) | newkey;
}
/**
* ib_inc_rkey - increments the key portion of the given rkey. Can be used
* for calculating a new rkey for type 2 memory windows.
* @rkey - the rkey to increment.
*/
static inline u32 ib_inc_rkey(u32 rkey)
{
const u32 mask = 0x000000ff;
return ((rkey + 1) & mask) | (rkey & ~mask);
}
/**
* ib_attach_mcast - Attaches the specified QP to a multicast group.
* @qp: QP to attach to the multicast group. The QP must be type
* IB_QPT_UD.
* @gid: Multicast group GID.
* @lid: Multicast group LID in host byte order.
*
* In order to send and receive multicast packets, subnet
* administration must have created the multicast group and configured
* the fabric appropriately. The port associated with the specified
* QP must also be a member of the multicast group.
*/
int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
/**
* ib_detach_mcast - Detaches the specified QP from a multicast group.
* @qp: QP to detach from the multicast group.
* @gid: Multicast group GID.
* @lid: Multicast group LID in host byte order.
*/
int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);
struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device,
struct inode *inode, struct ib_udata *udata);
int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata);
static inline int ib_check_mr_access(struct ib_device *ib_dev,
unsigned int flags)
{
u64 device_cap = ib_dev->attrs.device_cap_flags;
/*
* Local write permission is required if remote write or
* remote atomic permission is also requested.
*/
if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) &&
!(flags & IB_ACCESS_LOCAL_WRITE))
return -EINVAL;
if (flags & ~IB_ACCESS_SUPPORTED)
return -EINVAL;
if (flags & IB_ACCESS_ON_DEMAND &&
!(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING))
return -EOPNOTSUPP;
if ((flags & IB_ACCESS_FLUSH_GLOBAL &&
!(device_cap & IB_DEVICE_FLUSH_GLOBAL)) ||
(flags & IB_ACCESS_FLUSH_PERSISTENT &&
!(device_cap & IB_DEVICE_FLUSH_PERSISTENT)))
return -EOPNOTSUPP;
return 0;
}
static inline bool ib_access_writable(int access_flags)
{
/*
* We have writable memory backing the MR if any of the following
* access flags are set. "Local write" and "remote write" obviously
* require write access. "Remote atomic" can do things like fetch and
* add, which will modify memory, and "MW bind" can change permissions
* by binding a window.
*/
return access_flags &
(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND);
}
/**
* ib_check_mr_status: lightweight check of MR status.
* This routine may provide status checks on a selected
* ib_mr. first use is for signature status check.
*
* @mr: A memory region.
* @check_mask: Bitmask of which checks to perform from
* ib_mr_status_check enumeration.
* @mr_status: The container of relevant status checks.
* failed checks will be indicated in the status bitmask
* and the relevant info shall be in the error item.
*/
int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
struct ib_mr_status *mr_status);
/**
* ib_device_try_get: Hold a registration lock
* device: The device to lock
*
* A device under an active registration lock cannot become unregistered. It
* is only possible to obtain a registration lock on a device that is fully
* registered, otherwise this function returns false.
*
* The registration lock is only necessary for actions which require the
* device to still be registered. Uses that only require the device pointer to
* be valid should use get_device(&ibdev->dev) to hold the memory.
*
*/
static inline bool ib_device_try_get(struct ib_device *dev)
{
return refcount_inc_not_zero(&dev->refcount);
}
void ib_device_put(struct ib_device *device);
struct ib_device *ib_device_get_by_netdev(struct net_device *ndev,
enum rdma_driver_id driver_id);
struct ib_device *ib_device_get_by_name(const char *name,
enum rdma_driver_id driver_id);
struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port,
u16 pkey, const union ib_gid *gid,
const struct sockaddr *addr);
int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
unsigned int port);
struct net_device *ib_device_get_netdev(struct ib_device *ib_dev,
u32 port);
int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev,
u32 *port);
static inline enum ib_port_state ib_get_curr_port_state(struct net_device *net_dev)
{
return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ?
IB_PORT_ACTIVE : IB_PORT_DOWN;
}
void ib_dispatch_port_state_event(struct ib_device *ibdev,
struct net_device *ndev);
struct ib_wq *ib_create_wq(struct ib_pd *pd,
struct ib_wq_init_attr *init_attr);
int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata);
int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset, unsigned int page_size);
int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg,
int data_sg_nents, unsigned int *data_sg_offset,
struct scatterlist *meta_sg, int meta_sg_nents,
unsigned int *meta_sg_offset, unsigned int page_size);
static inline int
ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset, unsigned int page_size)
{
int n;
n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size);
mr->iova = 0;
return n;
}
int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64));
void ib_drain_rq(struct ib_qp *qp);
void ib_drain_sq(struct ib_qp *qp);
void ib_drain_qp(struct ib_qp *qp);
int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed,
u8 *width);
static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
{
if (attr->type == RDMA_AH_ATTR_TYPE_ROCE)
return attr->roce.dmac;
return NULL;
}
static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid)
{
if (attr->type == RDMA_AH_ATTR_TYPE_IB)
attr->ib.dlid = (u16)dlid;
else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
attr->opa.dlid = dlid;
}
static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr)
{
if (attr->type == RDMA_AH_ATTR_TYPE_IB)
return attr->ib.dlid;
else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
return attr->opa.dlid;
return 0;
}
static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl)
{
attr->sl = sl;
}
static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr)
{
return attr->sl;
}
static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr,
u8 src_path_bits)
{
if (attr->type == RDMA_AH_ATTR_TYPE_IB)
attr->ib.src_path_bits = src_path_bits;
else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
attr->opa.src_path_bits = src_path_bits;
}
static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr)
{
if (attr->type == RDMA_AH_ATTR_TYPE_IB)
return attr->ib.src_path_bits;
else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
return attr->opa.src_path_bits;
return 0;
}
static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr,
bool make_grd)
{
if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
attr->opa.make_grd = make_grd;
}
static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr)
{
if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
return attr->opa.make_grd;
return false;
}
static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num)
{
attr->port_num = port_num;
}
static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr)
{
return attr->port_num;
}
static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr,
u8 static_rate)
{
attr->static_rate = static_rate;
}
static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr)
{
return attr->static_rate;
}
static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr,
enum ib_ah_flags flag)
{
attr->ah_flags = flag;
}
static inline enum ib_ah_flags
rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr)
{
return attr->ah_flags;
}
static inline const struct ib_global_route
*rdma_ah_read_grh(const struct rdma_ah_attr *attr)
{
return &attr->grh;
}
/*To retrieve and modify the grh */
static inline struct ib_global_route
*rdma_ah_retrieve_grh(struct rdma_ah_attr *attr)
{
return &attr->grh;
}
static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid)
{
struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);
memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid));
}
static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr,
__be64 prefix)
{
struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);
grh->dgid.global.subnet_prefix = prefix;
}
static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr,
__be64 if_id)
{
struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);
grh->dgid.global.interface_id = if_id;
}
static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr,
union ib_gid *dgid, u32 flow_label,
u8 sgid_index, u8 hop_limit,
u8 traffic_class)
{
struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);
attr->ah_flags = IB_AH_GRH;
if (dgid)
grh->dgid = *dgid;
grh->flow_label = flow_label;
grh->sgid_index = sgid_index;
grh->hop_limit = hop_limit;
grh->traffic_class = traffic_class;
grh->sgid_attr = NULL;
}
void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr);
void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid,
u32 flow_label, u8 hop_limit, u8 traffic_class,
const struct ib_gid_attr *sgid_attr);
void rdma_copy_ah_attr(struct rdma_ah_attr *dest,
const struct rdma_ah_attr *src);
void rdma_replace_ah_attr(struct rdma_ah_attr *old,
const struct rdma_ah_attr *new);
void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src);
/**
* rdma_ah_find_type - Return address handle type.
*
* @dev: Device to be checked
* @port_num: Port number
*/
static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
u32 port_num)
{
if (rdma_protocol_roce(dev, port_num))
return RDMA_AH_ATTR_TYPE_ROCE;
if (rdma_protocol_ib(dev, port_num)) {
if (rdma_cap_opa_ah(dev, port_num))
return RDMA_AH_ATTR_TYPE_OPA;
return RDMA_AH_ATTR_TYPE_IB;
}
if (dev->type == RDMA_DEVICE_TYPE_SMI)
return RDMA_AH_ATTR_TYPE_IB;
return RDMA_AH_ATTR_TYPE_UNDEFINED;
}
/**
* ib_lid_cpu16 - Return lid in 16bit CPU encoding.
* In the current implementation the only way to
* get the 32bit lid is from other sources for OPA.
* For IB, lids will always be 16bits so cast the
* value accordingly.
*
* @lid: A 32bit LID
*/
static inline u16 ib_lid_cpu16(u32 lid)
{
WARN_ON_ONCE(lid & 0xFFFF0000);
return (u16)lid;
}
/**
* ib_lid_be16 - Return lid in 16bit BE encoding.
*
* @lid: A 32bit LID
*/
static inline __be16 ib_lid_be16(u32 lid)
{
WARN_ON_ONCE(lid & 0xFFFF0000);
return cpu_to_be16((u16)lid);
}
/**
* ib_get_vector_affinity - Get the affinity mappings of a given completion
* vector
* @device: the rdma device
* @comp_vector: index of completion vector
*
* Returns NULL on failure, otherwise a corresponding cpu map of the
* completion vector (returns all-cpus map if the device driver doesn't
* implement get_vector_affinity).
*/
static inline const struct cpumask *
ib_get_vector_affinity(struct ib_device *device, int comp_vector)
{
if (comp_vector < 0 || comp_vector >= device->num_comp_vectors ||
!device->ops.get_vector_affinity)
return NULL;
return device->ops.get_vector_affinity(device, comp_vector);
}
/**
* rdma_roce_rescan_device - Rescan all of the network devices in the system
* and add their gids, as needed, to the relevant RoCE devices.
*
* @device: the rdma device
*/
void rdma_roce_rescan_device(struct ib_device *ibdev);
void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port);
void roce_del_all_netdev_gids(struct ib_device *ib_dev,
u32 port, struct net_device *ndev);
struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile);
#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs);
#else
static inline int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs)
{
return 0;
}
#endif
struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num,
enum rdma_netdev_t type, const char *name,
unsigned char name_assign_type,
void (*setup)(struct net_device *));
int rdma_init_netdev(struct ib_device *device, u32 port_num,
enum rdma_netdev_t type, const char *name,
unsigned char name_assign_type,
void (*setup)(struct net_device *),
struct net_device *netdev);
/**
* rdma_device_to_ibdev - Get ib_device pointer from device pointer
*
* @device: device pointer for which ib_device pointer to retrieve
*
* rdma_device_to_ibdev() retrieves ib_device pointer from device.
*
*/
static inline struct ib_device *rdma_device_to_ibdev(struct device *device)
{
struct ib_core_device *coredev =
container_of(device, struct ib_core_device, dev);
return coredev->owner;
}
/**
* ibdev_to_node - return the NUMA node for a given ib_device
* @dev: device to get the NUMA node for.
*/
static inline int ibdev_to_node(struct ib_device *ibdev)
{
struct device *parent = ibdev->dev.parent;
if (!parent)
return NUMA_NO_NODE;
return dev_to_node(parent);
}
/**
* rdma_device_to_drv_device - Helper macro to reach back to driver's
* ib_device holder structure from device pointer.
*
* NOTE: New drivers should not make use of this API; This API is only for
* existing drivers who have exposed sysfs entries using
* ops->device_group.
*/
#define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \
container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member)
bool rdma_dev_access_netns(const struct ib_device *device,
const struct net *net);
#define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000)
#define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF)
#define IB_GRH_FLOWLABEL_MASK (0x000FFFFF)
/**
* rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based
* on the flow_label
*
* This function will convert the 20 bit flow_label input to a valid RoCE v2
* UDP src port 14 bit value. All RoCE V2 drivers should use this same
* convention.
*/
static inline u16 rdma_flow_label_to_udp_sport(u32 fl)
{
u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000;
fl_low ^= fl_high >> 14;
return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN);
}
/**
* rdma_calc_flow_label - generate a RDMA symmetric flow label value based on
* local and remote qpn values
*
* This function folded the multiplication results of two qpns, 24 bit each,
* fields, and converts it to a 20 bit results.
*
* This function will create symmetric flow_label value based on the local
* and remote qpn values. this will allow both the requester and responder
* to calculate the same flow_label for a given connection.
*
* This helper function should be used by driver in case the upper layer
* provide a zero flow_label value. This is to improve entropy of RDMA
* traffic in the network.
*/
static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn)
{
u64 v = (u64)lqpn * rqpn;
v ^= v >> 20;
v ^= v >> 40;
return (u32)(v & IB_GRH_FLOWLABEL_MASK);
}
/**
* rdma_get_udp_sport - Calculate and set UDP source port based on the flow
* label. If flow label is not defined in GRH then
* calculate it based on lqpn/rqpn.
*
* @fl: flow label from GRH
* @lqpn: local qp number
* @rqpn: remote qp number
*/
static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
{
if (!fl)
fl = rdma_calc_flow_label(lqpn, rqpn);
return rdma_flow_label_to_udp_sport(fl);
}
const struct ib_port_immutable*
ib_port_immutable_read(struct ib_device *dev, unsigned int port);
/** ib_add_sub_device - Add a sub IB device on an existing one
*
* @parent: The IB device that needs to add a sub device
* @type: The type of the new sub device
* @name: The name of the new sub device
*
*
* Return 0 on success, an error code otherwise
*/
int ib_add_sub_device(struct ib_device *parent,
enum rdma_nl_dev_type type,
const char *name);
/** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get'
*
* @sub: The sub device that is going to be deleted
*
* Return 0 on success, an error code otherwise
*/
int ib_del_sub_device_and_put(struct ib_device *sub);
static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev)
{
ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER;
}
#endif /* IB_VERBS_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/uaccess.h>
#include <clocksource/arm_arch_timer.h>
#include <asm/arch_timer.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_nested.h>
#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
#include "trace.h"
static struct timecounter *timecounter;
static unsigned int host_vtimer_irq;
static unsigned int host_ptimer_irq;
static u32 host_vtimer_irq_flags;
static u32 host_ptimer_irq_flags;
static DEFINE_STATIC_KEY_FALSE(has_gic_active_state);
DEFINE_STATIC_KEY_FALSE(broken_cntvoff_key);
static const u8 default_ppi[] = {
[TIMER_PTIMER] = 30,
[TIMER_VTIMER] = 27,
[TIMER_HPTIMER] = 26,
[TIMER_HVTIMER] = 28,
};
static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx);
static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
struct arch_timer_context *timer_ctx);
static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx);
static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
struct arch_timer_context *timer,
enum kvm_arch_timer_regs treg,
u64 val);
static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
struct arch_timer_context *timer,
enum kvm_arch_timer_regs treg);
static bool kvm_arch_timer_get_input_level(int vintid);
static struct irq_ops arch_timer_irq_ops = {
.get_input_level = kvm_arch_timer_get_input_level,
};
static int nr_timers(struct kvm_vcpu *vcpu)
{
if (!vcpu_has_nv(vcpu))
return NR_KVM_EL0_TIMERS;
return NR_KVM_TIMERS;
}
u32 timer_get_ctl(struct arch_timer_context *ctxt)
{
struct kvm_vcpu *vcpu = ctxt->vcpu;
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
case TIMER_PTIMER:
return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
case TIMER_HVTIMER:
return __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2);
case TIMER_HPTIMER:
return __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2);
default:
WARN_ON(1);
return 0;
}
}
u64 timer_get_cval(struct arch_timer_context *ctxt)
{
struct kvm_vcpu *vcpu = ctxt->vcpu;
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
case TIMER_PTIMER:
return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
case TIMER_HVTIMER:
return __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2);
case TIMER_HPTIMER:
return __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
default:
WARN_ON(1);
return 0;
}
}
static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
{
struct kvm_vcpu *vcpu = ctxt->vcpu;
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
break;
case TIMER_PTIMER:
__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
break;
case TIMER_HVTIMER:
__vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl;
break;
case TIMER_HPTIMER:
__vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl;
break;
default:
WARN_ON(1);
}
}
static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
{
struct kvm_vcpu *vcpu = ctxt->vcpu;
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
break;
case TIMER_PTIMER:
__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
break;
case TIMER_HVTIMER:
__vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval;
break;
case TIMER_HPTIMER:
__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval;
break;
default:
WARN_ON(1);
}
}
static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset)
{
if (!ctxt->offset.vm_offset) { WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt));
return;
}
WRITE_ONCE(*ctxt->offset.vm_offset, offset);
}
u64 kvm_phys_timer_read(void)
{
return timecounter->cc->read(timecounter->cc);
}
void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
{ if (vcpu_has_nv(vcpu)) { if (is_hyp_ctxt(vcpu)) {
map->direct_vtimer = vcpu_hvtimer(vcpu);
map->direct_ptimer = vcpu_hptimer(vcpu);
map->emul_vtimer = vcpu_vtimer(vcpu);
map->emul_ptimer = vcpu_ptimer(vcpu);
} else {
map->direct_vtimer = vcpu_vtimer(vcpu);
map->direct_ptimer = vcpu_ptimer(vcpu);
map->emul_vtimer = vcpu_hvtimer(vcpu);
map->emul_ptimer = vcpu_hptimer(vcpu);
}
} else if (has_vhe()) { map->direct_vtimer = vcpu_vtimer(vcpu);
map->direct_ptimer = vcpu_ptimer(vcpu);
map->emul_vtimer = NULL;
map->emul_ptimer = NULL;
} else {
map->direct_vtimer = vcpu_vtimer(vcpu);
map->direct_ptimer = NULL;
map->emul_vtimer = NULL;
map->emul_ptimer = vcpu_ptimer(vcpu);
}
trace_kvm_get_timer_map(vcpu->vcpu_id, map);
}
static inline bool userspace_irqchip(struct kvm *kvm)
{
return unlikely(!irqchip_in_kernel(kvm));
}
static void soft_timer_start(struct hrtimer *hrt, u64 ns)
{
hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns),
HRTIMER_MODE_ABS_HARD);
}
static void soft_timer_cancel(struct hrtimer *hrt)
{
hrtimer_cancel(hrt);
}
static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
{
struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
struct arch_timer_context *ctx;
struct timer_map map;
/*
* We may see a timer interrupt after vcpu_put() has been called which
* sets the CPU's vcpu pointer to NULL, because even though the timer
* has been disabled in timer_save_state(), the hardware interrupt
* signal may not have been retired from the interrupt controller yet.
*/
if (!vcpu)
return IRQ_HANDLED;
get_timer_map(vcpu, &map);
if (irq == host_vtimer_irq)
ctx = map.direct_vtimer;
else
ctx = map.direct_ptimer;
if (kvm_timer_should_fire(ctx))
kvm_timer_update_irq(vcpu, true, ctx);
if (userspace_irqchip(vcpu->kvm) &&
!static_branch_unlikely(&has_gic_active_state))
disable_percpu_irq(host_vtimer_irq);
return IRQ_HANDLED;
}
static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx,
u64 val)
{
u64 now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
if (now < val) {
u64 ns;
ns = cyclecounter_cyc2ns(timecounter->cc,
val - now,
timecounter->mask,
&timer_ctx->ns_frac);
return ns;
}
return 0;
}
static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
{
return kvm_counter_compute_delta(timer_ctx, timer_get_cval(timer_ctx));
}
static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
{
WARN_ON(timer_ctx && timer_ctx->loaded);
return timer_ctx &&
((timer_get_ctl(timer_ctx) &
(ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE);
}
static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu)
{
return (cpus_have_final_cap(ARM64_HAS_WFXT) &&
vcpu_get_flag(vcpu, IN_WFIT));
}
static u64 wfit_delay_ns(struct kvm_vcpu *vcpu)
{
u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
struct arch_timer_context *ctx;
ctx = is_hyp_ctxt(vcpu) ? vcpu_hvtimer(vcpu) : vcpu_vtimer(vcpu);
return kvm_counter_compute_delta(ctx, val);
}
/*
* Returns the earliest expiration time in ns among guest timers.
* Note that it will return 0 if none of timers can fire.
*/
static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu)
{
u64 min_delta = ULLONG_MAX;
int i;
for (i = 0; i < nr_timers(vcpu); i++) {
struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i];
WARN(ctx->loaded, "timer %d loaded\n", i);
if (kvm_timer_irq_can_fire(ctx))
min_delta = min(min_delta, kvm_timer_compute_delta(ctx));
}
if (vcpu_has_wfit_active(vcpu))
min_delta = min(min_delta, wfit_delay_ns(vcpu));
/* If none of timers can fire, then return 0 */
if (min_delta == ULLONG_MAX)
return 0;
return min_delta;
}
static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt)
{
struct arch_timer_cpu *timer;
struct kvm_vcpu *vcpu;
u64 ns;
timer = container_of(hrt, struct arch_timer_cpu, bg_timer);
vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
/*
* Check that the timer has really expired from the guest's
* PoV (NTP on the host may have forced it to expire
* early). If we should have slept longer, restart it.
*/
ns = kvm_timer_earliest_exp(vcpu);
if (unlikely(ns)) {
hrtimer_forward_now(hrt, ns_to_ktime(ns));
return HRTIMER_RESTART;
}
kvm_vcpu_wake_up(vcpu);
return HRTIMER_NORESTART;
}
static enum hrtimer_restart kvm_hrtimer_expire(struct hrtimer *hrt)
{
struct arch_timer_context *ctx;
struct kvm_vcpu *vcpu;
u64 ns;
ctx = container_of(hrt, struct arch_timer_context, hrtimer);
vcpu = ctx->vcpu;
trace_kvm_timer_hrtimer_expire(ctx);
/*
* Check that the timer has really expired from the guest's
* PoV (NTP on the host may have forced it to expire
* early). If not ready, schedule for a later time.
*/
ns = kvm_timer_compute_delta(ctx);
if (unlikely(ns)) {
hrtimer_forward_now(hrt, ns_to_ktime(ns));
return HRTIMER_RESTART;
}
kvm_timer_update_irq(vcpu, true, ctx);
return HRTIMER_NORESTART;
}
static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
{
enum kvm_arch_timers index;
u64 cval, now;
if (!timer_ctx)
return false;
index = arch_timer_ctx_index(timer_ctx);
if (timer_ctx->loaded) {
u32 cnt_ctl = 0;
switch (index) {
case TIMER_VTIMER:
case TIMER_HVTIMER:
cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL);
break;
case TIMER_PTIMER:
case TIMER_HPTIMER:
cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL);
break;
case NR_KVM_TIMERS:
/* GCC is braindead */
cnt_ctl = 0;
break;
}
return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) &&
(cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) &&
!(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK);
}
if (!kvm_timer_irq_can_fire(timer_ctx))
return false;
cval = timer_get_cval(timer_ctx);
now = kvm_phys_timer_read() - timer_get_offset(timer_ctx);
return cval <= now;
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{ return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0;
}
/*
* Reflect the timer output level into the kvm_run structure
*/
void kvm_timer_update_run(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
struct kvm_sync_regs *regs = &vcpu->run->s.regs;
/* Populate the device bitmap with the timer states */
regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
KVM_ARM_DEV_EL1_PTIMER);
if (kvm_timer_should_fire(vtimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; if (kvm_timer_should_fire(ptimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
}
static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level)
{
/*
* Paper over NV2 brokenness by publishing the interrupt status
* bit. This still results in a poor quality of emulation (guest
* writes will have no effect until the next exit).
*
* But hey, it's fast, right?
*/
if (is_hyp_ctxt(ctx->vcpu) && (ctx == vcpu_vtimer(ctx->vcpu) || ctx == vcpu_ptimer(ctx->vcpu))) { unsigned long val = timer_get_ctl(ctx);
__assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &val, level);
timer_set_ctl(ctx, val);
}
}
static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
struct arch_timer_context *timer_ctx)
{
kvm_timer_update_status(timer_ctx, new_level);
timer_ctx->irq.level = new_level;
trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx),
timer_ctx->irq.level);
if (userspace_irqchip(vcpu->kvm))
return;
kvm_vgic_inject_irq(vcpu->kvm, vcpu,
timer_irq(timer_ctx),
timer_ctx->irq.level,
timer_ctx);
}
/* Only called for a fully emulated timer */
static void timer_emulate(struct arch_timer_context *ctx)
{
bool should_fire = kvm_timer_should_fire(ctx);
trace_kvm_timer_emulate(ctx, should_fire);
if (should_fire != ctx->irq.level)
kvm_timer_update_irq(ctx->vcpu, should_fire, ctx);
kvm_timer_update_status(ctx, should_fire);
/*
* If the timer can fire now, we don't need to have a soft timer
* scheduled for the future. If the timer cannot fire at all,
* then we also don't need a soft timer.
*/
if (should_fire || !kvm_timer_irq_can_fire(ctx))
return;
soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx));
}
static void set_cntvoff(u64 cntvoff)
{
kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff);
}
static void set_cntpoff(u64 cntpoff)
{
if (has_cntpoff()) write_sysreg_s(cntpoff, SYS_CNTPOFF_EL2);
}
static void timer_save_state(struct arch_timer_context *ctx)
{
struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu);
enum kvm_arch_timers index = arch_timer_ctx_index(ctx);
unsigned long flags;
if (!timer->enabled)
return;
local_irq_save(flags); if (!ctx->loaded)
goto out;
switch (index) {
u64 cval;
case TIMER_VTIMER:
case TIMER_HVTIMER:
timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
cval = read_sysreg_el0(SYS_CNTV_CVAL);
if (has_broken_cntvoff()) cval -= timer_get_offset(ctx);
timer_set_cval(ctx, cval);
/* Disable the timer */
write_sysreg_el0(0, SYS_CNTV_CTL);
isb();
/*
* The kernel may decide to run userspace after
* calling vcpu_put, so we reset cntvoff to 0 to
* ensure a consistent read between user accesses to
* the virtual counter and kernel access to the
* physical counter of non-VHE case.
*
* For VHE, the virtual counter uses a fixed virtual
* offset of zero, so no need to zero CNTVOFF_EL2
* register, but this is actually useful when switching
* between EL1/vEL2 with NV.
*
* Do it unconditionally, as this is either unavoidable
* or dirt cheap.
*/
set_cntvoff(0);
break;
case TIMER_PTIMER:
case TIMER_HPTIMER:
timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
cval = read_sysreg_el0(SYS_CNTP_CVAL);
cval -= timer_get_offset(ctx);
timer_set_cval(ctx, cval);
/* Disable the timer */
write_sysreg_el0(0, SYS_CNTP_CTL);
isb();
set_cntpoff(0);
break;
case NR_KVM_TIMERS:
BUG();
}
trace_kvm_timer_save_state(ctx);
ctx->loaded = false;
out:
local_irq_restore(flags);
}
/*
* Schedule the background timer before calling kvm_vcpu_halt, so that this
* thread is removed from its waitqueue and made runnable when there's a timer
* interrupt to handle.
*/
static void kvm_timer_blocking(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
get_timer_map(vcpu, &map);
/*
* If no timers are capable of raising interrupts (disabled or
* masked), then there's no more work for us to do.
*/
if (!kvm_timer_irq_can_fire(map.direct_vtimer) && !kvm_timer_irq_can_fire(map.direct_ptimer) && !kvm_timer_irq_can_fire(map.emul_vtimer) && !kvm_timer_irq_can_fire(map.emul_ptimer) && !vcpu_has_wfit_active(vcpu))
return;
/*
* At least one guest time will expire. Schedule a background timer.
* Set the earliest expiration time among the guest timers.
*/
soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu));
}
static void kvm_timer_unblocking(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
soft_timer_cancel(&timer->bg_timer);
}
static void timer_restore_state(struct arch_timer_context *ctx)
{
struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu);
enum kvm_arch_timers index = arch_timer_ctx_index(ctx);
unsigned long flags;
if (!timer->enabled)
return;
local_irq_save(flags); if (ctx->loaded)
goto out;
switch (index) {
u64 cval, offset;
case TIMER_VTIMER:
case TIMER_HVTIMER:
cval = timer_get_cval(ctx);
offset = timer_get_offset(ctx);
if (has_broken_cntvoff()) {
set_cntvoff(0);
cval += offset;
} else {
set_cntvoff(offset);
}
write_sysreg_el0(cval, SYS_CNTV_CVAL);
isb();
write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
break;
case TIMER_PTIMER:
case TIMER_HPTIMER:
cval = timer_get_cval(ctx);
offset = timer_get_offset(ctx); set_cntpoff(offset);
cval += offset;
write_sysreg_el0(cval, SYS_CNTP_CVAL);
isb();
write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
break;
case NR_KVM_TIMERS:
BUG();
}
trace_kvm_timer_restore_state(ctx);
ctx->loaded = true;
out:
local_irq_restore(flags);
}
static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active)
{
int r;
r = irq_set_irqchip_state(ctx->host_timer_irq, IRQCHIP_STATE_ACTIVE, active);
WARN_ON(r);
}
static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx)
{
struct kvm_vcpu *vcpu = ctx->vcpu;
bool phys_active = false;
/*
* Update the timer output so that it is likely to match the
* state we're about to restore. If the timer expires between
* this point and the register restoration, we'll take the
* interrupt anyway.
*/
kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx);
if (irqchip_in_kernel(vcpu->kvm)) phys_active = kvm_vgic_map_is_active(vcpu, timer_irq(ctx));
phys_active |= ctx->irq.level;
set_timer_irq_phys_active(ctx, phys_active);
}
static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
/*
* Update the timer output so that it is likely to match the
* state we're about to restore. If the timer expires between
* this point and the register restoration, we'll take the
* interrupt anyway.
*/
kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer);
/*
* When using a userspace irqchip with the architected timers and a
* host interrupt controller that doesn't support an active state, we
* must still prevent continuously exiting from the guest, and
* therefore mask the physical interrupt by disabling it on the host
* interrupt controller when the virtual level is high, such that the
* guest can make forward progress. Once we detect the output level
* being de-asserted, we unmask the interrupt again so that we exit
* from the guest when the timer fires.
*/
if (vtimer->irq.level)
disable_percpu_irq(host_vtimer_irq);
else
enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}
/* If _pred is true, set bit in _set, otherwise set it in _clr */
#define assign_clear_set_bit(_pred, _bit, _clr, _set) \
do { \
if (_pred) \
(_set) |= (_bit); \
else \
(_clr) |= (_bit); \
} while (0)
static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
struct timer_map *map)
{
int hw, ret;
if (!irqchip_in_kernel(vcpu->kvm))
return;
/*
* We only ever unmap the vtimer irq on a VHE system that runs nested
* virtualization, in which case we have both a valid emul_vtimer,
* emul_ptimer, direct_vtimer, and direct_ptimer.
*
* Since this is called from kvm_timer_vcpu_load(), a change between
* vEL2 and vEL1/0 will have just happened, and the timer_map will
* represent this, and therefore we switch the emul/direct mappings
* below.
*/
hw = kvm_vgic_get_map(vcpu, timer_irq(map->direct_vtimer));
if (hw < 0) {
kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_vtimer));
kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_ptimer));
ret = kvm_vgic_map_phys_irq(vcpu,
map->direct_vtimer->host_timer_irq,
timer_irq(map->direct_vtimer),
&arch_timer_irq_ops);
WARN_ON_ONCE(ret);
ret = kvm_vgic_map_phys_irq(vcpu,
map->direct_ptimer->host_timer_irq,
timer_irq(map->direct_ptimer),
&arch_timer_irq_ops);
WARN_ON_ONCE(ret);
}
}
static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
{
bool tvt, tpt, tvc, tpc, tvt02, tpt02;
u64 clr, set;
/*
* No trapping gets configured here with nVHE. See
* __timer_enable_traps(), which is where the stuff happens.
*/
if (!has_vhe())
return;
/*
* Our default policy is not to trap anything. As we progress
* within this function, reality kicks in and we start adding
* traps based on emulation requirements.
*/
tvt = tpt = tvc = tpc = false;
tvt02 = tpt02 = false;
/*
* NV2 badly breaks the timer semantics by redirecting accesses to
* the EL1 timer state to memory, so let's call ECV to the rescue if
* available: we trap all CNT{P,V}_{CTL,CVAL,TVAL}_EL0 accesses.
*
* The treatment slightly varies depending whether we run a nVHE or
* VHE guest: nVHE will use the _EL0 registers directly, while VHE
* will use the _EL02 accessors. This translates in different trap
* bits.
*
* None of the trapping is required when running in non-HYP context,
* unless required by the L1 hypervisor settings once we advertise
* ECV+NV in the guest, or that we need trapping for other reasons.
*/
if (cpus_have_final_cap(ARM64_HAS_ECV) && is_hyp_ctxt(vcpu)) { if (vcpu_el2_e2h_is_set(vcpu))
tvt02 = tpt02 = true;
else
tvt = tpt = true;
}
/*
* We have two possibility to deal with a physical offset:
*
* - Either we have CNTPOFF (yay!) or the offset is 0:
* we let the guest freely access the HW
*
* - or neither of these condition apply:
* we trap accesses to the HW, but still use it
* after correcting the physical offset
*/
if (!has_cntpoff() && timer_get_offset(map->direct_ptimer))
tpt = tpc = true;
/*
* For the poor sods that could not correctly substract one value
* from another, trap the full virtual timer and counter.
*/
if (has_broken_cntvoff() && timer_get_offset(map->direct_vtimer))
tvt = tvc = true;
/*
* Apply the enable bits that the guest hypervisor has requested for
* its own guest. We can only add traps that wouldn't have been set
* above.
* Implementation choices: we do not support NV when E2H=0 in the
* guest, and we don't support configuration where E2H is writable
* by the guest (either FEAT_VHE or FEAT_E2H0 is implemented, but
* not both). This simplifies the handling of the EL1NV* bits.
*/
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2);
/* Use the VHE format for mental sanity */
if (!vcpu_el2_e2h_is_set(vcpu))
val = (val & (CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN)) << 10;
tpt |= !(val & (CNTHCTL_EL1PCEN << 10));
tpc |= !(val & (CNTHCTL_EL1PCTEN << 10));
tpt02 |= (val & CNTHCTL_EL1NVPCT);
tvt02 |= (val & CNTHCTL_EL1NVVCT);
}
/*
* Now that we have collected our requirements, compute the
* trap and enable bits.
*/
set = 0;
clr = 0;
assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr);
assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr);
assign_clear_set_bit(tvt, CNTHCTL_EL1TVT, clr, set);
assign_clear_set_bit(tvc, CNTHCTL_EL1TVCT, clr, set);
assign_clear_set_bit(tvt02, CNTHCTL_EL1NVVCT, clr, set);
assign_clear_set_bit(tpt02, CNTHCTL_EL1NVPCT, clr, set);
/* This only happens on VHE, so use the CNTHCTL_EL2 accessor. */
sysreg_clear_set(cnthctl_el2, clr, set);
}
void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
if (unlikely(!timer->enabled))
return;
get_timer_map(vcpu, &map);
if (static_branch_likely(&has_gic_active_state)) {
if (vcpu_has_nv(vcpu)) kvm_timer_vcpu_load_nested_switch(vcpu, &map); kvm_timer_vcpu_load_gic(map.direct_vtimer); if (map.direct_ptimer) kvm_timer_vcpu_load_gic(map.direct_ptimer);
} else {
kvm_timer_vcpu_load_nogic(vcpu);
}
kvm_timer_unblocking(vcpu);
timer_restore_state(map.direct_vtimer);
if (map.direct_ptimer) timer_restore_state(map.direct_ptimer); if (map.emul_vtimer) timer_emulate(map.emul_vtimer); if (map.emul_ptimer) timer_emulate(map.emul_ptimer); timer_set_traps(vcpu, &map);
}
bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
bool vlevel, plevel;
if (likely(irqchip_in_kernel(vcpu->kvm)))
return false;
vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER;
plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER;
return kvm_timer_should_fire(vtimer) != vlevel || kvm_timer_should_fire(ptimer) != plevel;
}
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
if (unlikely(!timer->enabled))
return;
get_timer_map(vcpu, &map);
timer_save_state(map.direct_vtimer);
if (map.direct_ptimer) timer_save_state(map.direct_ptimer);
/*
* Cancel soft timer emulation, because the only case where we
* need it after a vcpu_put is in the context of a sleeping VCPU, and
* in that case we already factor in the deadline for the physical
* timer when scheduling the bg_timer.
*
* In any case, we re-schedule the hrtimer for the physical timer when
* coming back to the VCPU thread in kvm_timer_vcpu_load().
*/
if (map.emul_vtimer) soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu);
}
void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
{
/*
* When NV2 is on, guest hypervisors have their EL1 timer register
* accesses redirected to the VNCR page. Any guest action taken on
* the timer is postponed until the next exit, leading to a very
* poor quality of emulation.
*
* This is an unmitigated disaster, only papered over by FEAT_ECV,
* which allows trapping of the timer registers even with NV2.
* Still, this is still worse than FEAT_NV on its own. Meh.
*/
if (!cpus_have_final_cap(ARM64_HAS_ECV)) {
/*
* For a VHE guest hypervisor, the EL2 state is directly
* stored in the host EL1 timers, while the emulated EL1
* state is stored in the VNCR page. The latter could have
* been updated behind our back, and we must reset the
* emulation of the timers.
*
* A non-VHE guest hypervisor doesn't have any direct access
* to its timers: the EL2 registers trap despite being
* notionally direct (we use the EL1 HW, as for VHE), while
* the EL1 registers access memory.
*
* In both cases, process the emulated timers on each guest
* exit. Boo.
*/
struct timer_map map;
get_timer_map(vcpu, &map);
soft_timer_cancel(&map.emul_vtimer->hrtimer);
soft_timer_cancel(&map.emul_ptimer->hrtimer);
timer_emulate(map.emul_vtimer);
timer_emulate(map.emul_ptimer);
}
}
/*
* With a userspace irqchip we have to check if the guest de-asserted the
* timer and if so, unmask the timer irq signal on the host interrupt
* controller to ensure that we see future timer signals.
*/
static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
if (!kvm_timer_should_fire(vtimer)) {
kvm_timer_update_irq(vcpu, false, vtimer);
if (static_branch_likely(&has_gic_active_state))
set_timer_irq_phys_active(vtimer, false);
else
enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}
}
void kvm_timer_sync_user(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
if (unlikely(!timer->enabled))
return;
if (unlikely(!irqchip_in_kernel(vcpu->kvm))) unmask_vtimer_irq_user(vcpu);
}
void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
get_timer_map(vcpu, &map);
/*
* The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
* and to 0 for ARMv7. We provide an implementation that always
* resets the timer to be disabled and unmasked and is compliant with
* the ARMv7 architecture.
*/
for (int i = 0; i < nr_timers(vcpu); i++)
timer_set_ctl(vcpu_get_timer(vcpu, i), 0);
/*
* A vcpu running at EL2 is in charge of the offset applied to
* the virtual timer, so use the physical VM offset, and point
* the vcpu offset to CNTVOFF_EL2.
*/
if (vcpu_has_nv(vcpu)) {
struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset;
offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset;
}
if (timer->enabled) { for (int i = 0; i < nr_timers(vcpu); i++)
kvm_timer_update_irq(vcpu, false,
vcpu_get_timer(vcpu, i));
if (irqchip_in_kernel(vcpu->kvm)) {
kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_vtimer));
if (map.direct_ptimer) kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_ptimer));
}
}
if (map.emul_vtimer) soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer);
}
static void timer_context_init(struct kvm_vcpu *vcpu, int timerid)
{
struct arch_timer_context *ctxt = vcpu_get_timer(vcpu, timerid);
struct kvm *kvm = vcpu->kvm;
ctxt->vcpu = vcpu;
if (timerid == TIMER_VTIMER)
ctxt->offset.vm_offset = &kvm->arch.timer_data.voffset;
else
ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset;
hrtimer_setup(&ctxt->hrtimer, kvm_hrtimer_expire, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
switch (timerid) {
case TIMER_PTIMER:
case TIMER_HPTIMER:
ctxt->host_timer_irq = host_ptimer_irq;
break;
case TIMER_VTIMER:
case TIMER_HVTIMER:
ctxt->host_timer_irq = host_vtimer_irq;
break;
}
}
void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
for (int i = 0; i < NR_KVM_TIMERS; i++)
timer_context_init(vcpu, i);
/* Synchronize offsets across timers of a VM if not already provided */
if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { timer_set_offset(vcpu_vtimer(vcpu), kvm_phys_timer_read()); timer_set_offset(vcpu_ptimer(vcpu), 0);
}
hrtimer_setup(&timer->bg_timer, kvm_bg_timer_expire, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS_HARD);
}
void kvm_timer_init_vm(struct kvm *kvm)
{
for (int i = 0; i < NR_KVM_TIMERS; i++)
kvm->arch.timer_data.ppi[i] = default_ppi[i];
}
void kvm_timer_cpu_up(void)
{
enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
if (host_ptimer_irq)
enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags);
}
void kvm_timer_cpu_down(void)
{
disable_percpu_irq(host_vtimer_irq);
if (host_ptimer_irq)
disable_percpu_irq(host_ptimer_irq);
}
int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
{
struct arch_timer_context *timer;
switch (regid) {
case KVM_REG_ARM_TIMER_CTL:
timer = vcpu_vtimer(vcpu);
kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value);
break;
case KVM_REG_ARM_TIMER_CNT:
if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET,
&vcpu->kvm->arch.flags)) {
timer = vcpu_vtimer(vcpu);
timer_set_offset(timer, kvm_phys_timer_read() - value);
}
break;
case KVM_REG_ARM_TIMER_CVAL:
timer = vcpu_vtimer(vcpu);
kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value);
break;
case KVM_REG_ARM_PTIMER_CTL:
timer = vcpu_ptimer(vcpu);
kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value);
break;
case KVM_REG_ARM_PTIMER_CNT:
if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET,
&vcpu->kvm->arch.flags)) {
timer = vcpu_ptimer(vcpu);
timer_set_offset(timer, kvm_phys_timer_read() - value);
}
break;
case KVM_REG_ARM_PTIMER_CVAL:
timer = vcpu_ptimer(vcpu);
kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value);
break;
default:
return -1;
}
return 0;
}
static u64 read_timer_ctl(struct arch_timer_context *timer)
{
/*
* Set ISTATUS bit if it's expired.
* Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is
* UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
* regardless of ENABLE bit for our implementation convenience.
*/
u32 ctl = timer_get_ctl(timer);
if (!kvm_timer_compute_delta(timer))
ctl |= ARCH_TIMER_CTRL_IT_STAT;
return ctl;
}
u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
{ switch (regid) {
case KVM_REG_ARM_TIMER_CTL:
return kvm_arm_timer_read(vcpu,
vcpu_vtimer(vcpu), TIMER_REG_CTL);
case KVM_REG_ARM_TIMER_CNT:
return kvm_arm_timer_read(vcpu,
vcpu_vtimer(vcpu), TIMER_REG_CNT);
case KVM_REG_ARM_TIMER_CVAL:
return kvm_arm_timer_read(vcpu,
vcpu_vtimer(vcpu), TIMER_REG_CVAL);
case KVM_REG_ARM_PTIMER_CTL:
return kvm_arm_timer_read(vcpu,
vcpu_ptimer(vcpu), TIMER_REG_CTL);
case KVM_REG_ARM_PTIMER_CNT:
return kvm_arm_timer_read(vcpu,
vcpu_ptimer(vcpu), TIMER_REG_CNT);
case KVM_REG_ARM_PTIMER_CVAL:
return kvm_arm_timer_read(vcpu,
vcpu_ptimer(vcpu), TIMER_REG_CVAL);
}
return (u64)-1;
}
static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
struct arch_timer_context *timer,
enum kvm_arch_timer_regs treg)
{
u64 val;
switch (treg) {
case TIMER_REG_TVAL:
val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer);
val = lower_32_bits(val);
break;
case TIMER_REG_CTL:
val = read_timer_ctl(timer);
break;
case TIMER_REG_CVAL:
val = timer_get_cval(timer);
break;
case TIMER_REG_CNT:
val = kvm_phys_timer_read() - timer_get_offset(timer);
break;
case TIMER_REG_VOFF:
val = *timer->offset.vcpu_offset;
break;
default:
BUG();
}
return val;
}
u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu,
enum kvm_arch_timers tmr,
enum kvm_arch_timer_regs treg)
{
struct arch_timer_context *timer;
struct timer_map map;
u64 val;
get_timer_map(vcpu, &map);
timer = vcpu_get_timer(vcpu, tmr);
if (timer == map.emul_vtimer || timer == map.emul_ptimer)
return kvm_arm_timer_read(vcpu, timer, treg);
preempt_disable();
timer_save_state(timer);
val = kvm_arm_timer_read(vcpu, timer, treg);
timer_restore_state(timer);
preempt_enable();
return val;
}
static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
struct arch_timer_context *timer,
enum kvm_arch_timer_regs treg,
u64 val)
{
switch (treg) {
case TIMER_REG_TVAL:
timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val);
break;
case TIMER_REG_CTL:
timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT);
break;
case TIMER_REG_CVAL:
timer_set_cval(timer, val);
break;
case TIMER_REG_VOFF:
*timer->offset.vcpu_offset = val;
break;
default:
BUG();
}
}
void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
enum kvm_arch_timers tmr,
enum kvm_arch_timer_regs treg,
u64 val)
{
struct arch_timer_context *timer;
struct timer_map map;
get_timer_map(vcpu, &map);
timer = vcpu_get_timer(vcpu, tmr);
if (timer == map.emul_vtimer || timer == map.emul_ptimer) {
soft_timer_cancel(&timer->hrtimer);
kvm_arm_timer_write(vcpu, timer, treg, val);
timer_emulate(timer);
} else {
preempt_disable();
timer_save_state(timer);
kvm_arm_timer_write(vcpu, timer, treg, val);
timer_restore_state(timer);
preempt_enable();
}
}
static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
{
if (vcpu)
irqd_set_forwarded_to_vcpu(d);
else
irqd_clr_forwarded_to_vcpu(d);
return 0;
}
static int timer_irq_set_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool val)
{
if (which != IRQCHIP_STATE_ACTIVE || !irqd_is_forwarded_to_vcpu(d))
return irq_chip_set_parent_state(d, which, val);
if (val)
irq_chip_mask_parent(d);
else
irq_chip_unmask_parent(d);
return 0;
}
static void timer_irq_eoi(struct irq_data *d)
{
if (!irqd_is_forwarded_to_vcpu(d))
irq_chip_eoi_parent(d);
}
static void timer_irq_ack(struct irq_data *d)
{
d = d->parent_data;
if (d->chip->irq_ack)
d->chip->irq_ack(d);
}
static struct irq_chip timer_chip = {
.name = "KVM",
.irq_ack = timer_irq_ack,
.irq_mask = irq_chip_mask_parent,
.irq_unmask = irq_chip_unmask_parent,
.irq_eoi = timer_irq_eoi,
.irq_set_type = irq_chip_set_type_parent,
.irq_set_vcpu_affinity = timer_irq_set_vcpu_affinity,
.irq_set_irqchip_state = timer_irq_set_irqchip_state,
};
static int timer_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
irq_hw_number_t hwirq = (uintptr_t)arg;
return irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
&timer_chip, NULL);
}
static void timer_irq_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
}
static const struct irq_domain_ops timer_domain_ops = {
.alloc = timer_irq_domain_alloc,
.free = timer_irq_domain_free,
};
static void kvm_irq_fixup_flags(unsigned int virq, u32 *flags)
{
*flags = irq_get_trigger_type(virq);
if (*flags != IRQF_TRIGGER_HIGH && *flags != IRQF_TRIGGER_LOW) {
kvm_err("Invalid trigger for timer IRQ%d, assuming level low\n",
virq);
*flags = IRQF_TRIGGER_LOW;
}
}
static int kvm_irq_init(struct arch_timer_kvm_info *info)
{
struct irq_domain *domain = NULL;
if (info->virtual_irq <= 0) {
kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
info->virtual_irq);
return -ENODEV;
}
host_vtimer_irq = info->virtual_irq;
kvm_irq_fixup_flags(host_vtimer_irq, &host_vtimer_irq_flags);
if (kvm_vgic_global_state.no_hw_deactivation) {
struct fwnode_handle *fwnode;
struct irq_data *data;
fwnode = irq_domain_alloc_named_fwnode("kvm-timer");
if (!fwnode)
return -ENOMEM;
/* Assume both vtimer and ptimer in the same parent */
data = irq_get_irq_data(host_vtimer_irq);
domain = irq_domain_create_hierarchy(data->domain, 0,
NR_KVM_TIMERS, fwnode,
&timer_domain_ops, NULL);
if (!domain) {
irq_domain_free_fwnode(fwnode);
return -ENOMEM;
}
arch_timer_irq_ops.flags |= VGIC_IRQ_SW_RESAMPLE;
WARN_ON(irq_domain_push_irq(domain, host_vtimer_irq,
(void *)TIMER_VTIMER));
}
if (info->physical_irq > 0) {
host_ptimer_irq = info->physical_irq;
kvm_irq_fixup_flags(host_ptimer_irq, &host_ptimer_irq_flags);
if (domain)
WARN_ON(irq_domain_push_irq(domain, host_ptimer_irq,
(void *)TIMER_PTIMER));
}
return 0;
}
static void kvm_timer_handle_errata(void)
{
u64 mmfr0, mmfr1, mmfr4;
/*
* CNTVOFF_EL2 is broken on some implementations. For those, we trap
* all virtual timer/counter accesses, requiring FEAT_ECV.
*
* However, a hypervisor supporting nesting is likely to mitigate the
* erratum at L0, and not require other levels to mitigate it (which
* would otherwise be a terrible performance sink due to trap
* amplification).
*
* Given that the affected HW implements both FEAT_VHE and FEAT_E2H0,
* and that NV is likely not to (because of limitations of the
* architecture), only enable the workaround when FEAT_VHE and
* FEAT_E2H0 are both detected. Time will tell if this actually holds.
*/
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
mmfr4 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR4_EL1);
if (SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1) &&
!SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4) &&
SYS_FIELD_GET(ID_AA64MMFR0_EL1, ECV, mmfr0) &&
(has_vhe() || has_hvhe()) &&
cpus_have_final_cap(ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF)) {
static_branch_enable(&broken_cntvoff_key);
kvm_info("Broken CNTVOFF_EL2, trapping virtual timer\n");
}
}
int __init kvm_timer_hyp_init(bool has_gic)
{
struct arch_timer_kvm_info *info;
int err;
info = arch_timer_get_kvm_info();
timecounter = &info->timecounter;
if (!timecounter->cc) {
kvm_err("kvm_arch_timer: uninitialized timecounter\n");
return -ENODEV;
}
err = kvm_irq_init(info);
if (err)
return err;
/* First, do the virtual EL1 timer irq */
err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
"kvm guest vtimer", kvm_get_running_vcpus());
if (err) {
kvm_err("kvm_arch_timer: can't request vtimer interrupt %d (%d)\n",
host_vtimer_irq, err);
return err;
}
if (has_gic) {
err = irq_set_vcpu_affinity(host_vtimer_irq,
kvm_get_running_vcpus());
if (err) {
kvm_err("kvm_arch_timer: error setting vcpu affinity\n");
goto out_free_vtimer_irq;
}
static_branch_enable(&has_gic_active_state);
}
kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq);
/* Now let's do the physical EL1 timer irq */
if (info->physical_irq > 0) {
err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler,
"kvm guest ptimer", kvm_get_running_vcpus());
if (err) {
kvm_err("kvm_arch_timer: can't request ptimer interrupt %d (%d)\n",
host_ptimer_irq, err);
goto out_free_vtimer_irq;
}
if (has_gic) {
err = irq_set_vcpu_affinity(host_ptimer_irq,
kvm_get_running_vcpus());
if (err) {
kvm_err("kvm_arch_timer: error setting vcpu affinity\n");
goto out_free_ptimer_irq;
}
}
kvm_debug("physical timer IRQ%d\n", host_ptimer_irq);
} else if (has_vhe()) {
kvm_err("kvm_arch_timer: invalid physical timer IRQ: %d\n",
info->physical_irq);
err = -ENODEV;
goto out_free_vtimer_irq;
}
kvm_timer_handle_errata();
return 0;
out_free_ptimer_irq:
if (info->physical_irq > 0)
free_percpu_irq(host_ptimer_irq, kvm_get_running_vcpus());
out_free_vtimer_irq:
free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus());
return err;
}
void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
soft_timer_cancel(&timer->bg_timer);
}
static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
{
u32 ppis = 0;
bool valid;
mutex_lock(&vcpu->kvm->arch.config_lock);
for (int i = 0; i < nr_timers(vcpu); i++) {
struct arch_timer_context *ctx;
int irq;
ctx = vcpu_get_timer(vcpu, i);
irq = timer_irq(ctx);
if (kvm_vgic_set_owner(vcpu, irq, ctx))
break;
/*
* We know by construction that we only have PPIs, so
* all values are less than 32.
*/
ppis |= BIT(irq);
}
valid = hweight32(ppis) == nr_timers(vcpu);
if (valid)
set_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags);
mutex_unlock(&vcpu->kvm->arch.config_lock);
return valid;
}
static bool kvm_arch_timer_get_input_level(int vintid)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
if (WARN(!vcpu, "No vcpu context!\n"))
return false;
for (int i = 0; i < nr_timers(vcpu); i++) {
struct arch_timer_context *ctx;
ctx = vcpu_get_timer(vcpu, i);
if (timer_irq(ctx) == vintid)
return kvm_timer_should_fire(ctx);
}
/* A timer IRQ has fired, but no matching timer was found? */
WARN_RATELIMIT(1, "timer INTID%d unknown\n", vintid);
return false;
}
int kvm_timer_enable(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = vcpu_timer(vcpu);
struct timer_map map;
int ret;
if (timer->enabled)
return 0;
/* Without a VGIC we do not map virtual IRQs to physical IRQs */
if (!irqchip_in_kernel(vcpu->kvm))
goto no_vgic;
/*
* At this stage, we have the guarantee that the vgic is both
* available and initialized.
*/
if (!timer_irqs_are_valid(vcpu)) { kvm_debug("incorrectly configured timer irqs\n");
return -EINVAL;
}
get_timer_map(vcpu, &map);
ret = kvm_vgic_map_phys_irq(vcpu,
map.direct_vtimer->host_timer_irq,
timer_irq(map.direct_vtimer),
&arch_timer_irq_ops);
if (ret)
return ret;
if (map.direct_ptimer) {
ret = kvm_vgic_map_phys_irq(vcpu,
map.direct_ptimer->host_timer_irq,
timer_irq(map.direct_ptimer),
&arch_timer_irq_ops);
}
if (ret)
return ret;
no_vgic:
timer->enabled = 1;
return 0;
}
/* If we have CNTPOFF, permanently set ECV to enable it */
void kvm_timer_init_vhe(void)
{
if (cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF))
sysreg_clear_set(cnthctl_el2, 0, CNTHCTL_ECV);
}
int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
int __user *uaddr = (int __user *)(long)attr->addr;
int irq, idx, ret = 0;
if (!irqchip_in_kernel(vcpu->kvm))
return -EINVAL;
if (get_user(irq, uaddr))
return -EFAULT;
if (!(irq_is_ppi(irq)))
return -EINVAL;
mutex_lock(&vcpu->kvm->arch.config_lock);
if (test_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE,
&vcpu->kvm->arch.flags)) {
ret = -EBUSY;
goto out;
}
switch (attr->attr) {
case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
idx = TIMER_VTIMER;
break;
case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
idx = TIMER_PTIMER;
break;
case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER:
idx = TIMER_HVTIMER;
break;
case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER:
idx = TIMER_HPTIMER;
break;
default:
ret = -ENXIO;
goto out;
}
/*
* We cannot validate the IRQ unicity before we run, so take it at
* face value. The verdict will be given on first vcpu run, for each
* vcpu. Yes this is late. Blame it on the stupid API.
*/
vcpu->kvm->arch.timer_data.ppi[idx] = irq;
out:
mutex_unlock(&vcpu->kvm->arch.config_lock);
return ret;
}
int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
int __user *uaddr = (int __user *)(long)attr->addr;
struct arch_timer_context *timer;
int irq;
switch (attr->attr) {
case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
timer = vcpu_vtimer(vcpu);
break;
case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
timer = vcpu_ptimer(vcpu);
break;
case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER:
timer = vcpu_hvtimer(vcpu);
break;
case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER:
timer = vcpu_hptimer(vcpu);
break;
default:
return -ENXIO;
}
irq = timer_irq(timer);
return put_user(irq, uaddr);
}
int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
switch (attr->attr) {
case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER:
case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER:
return 0;
}
return -ENXIO;
}
int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
struct kvm_arm_counter_offset *offset)
{
int ret = 0;
if (offset->reserved)
return -EINVAL;
mutex_lock(&kvm->lock);
if (lock_all_vcpus(kvm)) { set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags);
/*
* If userspace decides to set the offset using this
* API rather than merely restoring the counter
* values, the offset applies to both the virtual and
* physical views.
*/
kvm->arch.timer_data.voffset = offset->counter_offset;
kvm->arch.timer_data.poffset = offset->counter_offset;
unlock_all_vcpus(kvm);
} else {
ret = -EBUSY;
}
mutex_unlock(&kvm->lock);
return ret;
}
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memfd.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/secretmem.h>
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>
#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include "internal.h"
struct follow_page_context {
struct dev_pagemap *pgmap;
unsigned int page_mask;
};
static inline void sanity_check_pinned_pages(struct page **pages,
unsigned long npages)
{
if (!IS_ENABLED(CONFIG_DEBUG_VM))
return;
/*
* We only pin anonymous pages if they are exclusive. Once pinned, we
* can no longer turn them possibly shared and PageAnonExclusive() will
* stick around until the page is freed.
*
* We'd like to verify that our pinned anonymous pages are still mapped
* exclusively. The issue with anon THP is that we don't know how
* they are/were mapped when pinning them. However, for anon
* THP we can assume that either the given page (PTE-mapped THP) or
* the head page (PMD-mapped THP) should be PageAnonExclusive(). If
* neither is the case, there is certainly something wrong.
*/
for (; npages; npages--, pages++) {
struct page *page = *pages;
struct folio *folio;
if (!page)
continue;
folio = page_folio(page);
if (is_zero_page(page) ||
!folio_test_anon(folio))
continue;
if (!folio_test_large(folio) || folio_test_hugetlb(folio))
VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
else
/* Either a PTE-mapped or a PMD-mapped THP. */
VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
!PageAnonExclusive(page), page);
}
}
/*
* Return the folio with ref appropriately incremented,
* or NULL if that failed.
*/
static inline struct folio *try_get_folio(struct page *page, int refs)
{
struct folio *folio;
retry:
folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0))
return NULL;
if (unlikely(!folio_ref_try_add(folio, refs)))
return NULL;
/*
* At this point we have a stable reference to the folio; but it
* could be that between calling page_folio() and the refcount
* increment, the folio was split, in which case we'd end up
* holding a reference on a folio that has nothing to do with the page
* we were given anymore.
* So now that the folio is stable, recheck that the page still
* belongs to this folio.
*/
if (unlikely(page_folio(page) != folio)) { folio_put_refs(folio, refs);
goto retry;
}
return folio;
}
static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
{ if (flags & FOLL_PIN) { if (is_zero_folio(folio))
return;
node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_has_pincount(folio)) atomic_sub(refs, &folio->_pincount);
else
refs *= GUP_PIN_COUNTING_BIAS;
}
folio_put_refs(folio, refs);
}
/**
* try_grab_folio() - add a folio's refcount by a flag-dependent amount
* @folio: pointer to folio to be grabbed
* @refs: the value to (effectively) add to the folio's refcount
* @flags: gup flags: these are the FOLL_* flag values
*
* This might not do anything at all, depending on the flags argument.
*
* "grab" names in this file mean, "look at flags to decide whether to use
* FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
*
* Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
* time.
*
* Return: 0 for success, or if no action was required (if neither FOLL_PIN
* nor FOLL_GET was set, nothing is done). A negative error code for failure:
*
* -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not
* be grabbed.
*
* It is called when we have a stable reference for the folio, typically in
* GUP slow path.
*/
int __must_check try_grab_folio(struct folio *folio, int refs,
unsigned int flags)
{ if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
return -ENOMEM;
if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page)))
return -EREMOTEIO;
if (flags & FOLL_GET)
folio_ref_add(folio, refs); else if (flags & FOLL_PIN) {
/*
* Don't take a pin on the zero page - it's not going anywhere
* and it is used in a *lot* of places.
*/
if (is_zero_folio(folio))
return 0;
/*
* Increment the normal page refcount field at least once,
* so that the page really is pinned.
*/
if (folio_has_pincount(folio)) { folio_ref_add(folio, refs); atomic_add(refs, &folio->_pincount);
} else {
folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS);
}
node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
}
return 0;
}
/**
* unpin_user_page() - release a dma-pinned page
* @page: pointer to page to be released
*
* Pages that were pinned via pin_user_pages*() must be released via either
* unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
* that such pages can be separately tracked and uniquely handled. In
* particular, interactions with RDMA and filesystems need special handling.
*/
void unpin_user_page(struct page *page)
{
sanity_check_pinned_pages(&page, 1);
gup_put_folio(page_folio(page), 1, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_page);
/**
* unpin_folio() - release a dma-pinned folio
* @folio: pointer to folio to be released
*
* Folios that were pinned via memfd_pin_folios() or other similar routines
* must be released either using unpin_folio() or unpin_folios().
*/
void unpin_folio(struct folio *folio)
{
gup_put_folio(folio, 1, FOLL_PIN);
}
EXPORT_SYMBOL_GPL(unpin_folio);
/**
* folio_add_pin - Try to get an additional pin on a pinned folio
* @folio: The folio to be pinned
*
* Get an additional pin on a folio we already have a pin on. Makes no change
* if the folio is a zero_page.
*/
void folio_add_pin(struct folio *folio)
{
if (is_zero_folio(folio))
return;
/*
* Similar to try_grab_folio(): be sure to *also* increment the normal
* page refcount field at least once, so that the page really is
* pinned.
*/
if (folio_has_pincount(folio)) {
WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1);
folio_ref_inc(folio);
atomic_inc(&folio->_pincount);
} else {
WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS);
folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
}
}
static inline struct folio *gup_folio_range_next(struct page *start,
unsigned long npages, unsigned long i, unsigned int *ntails)
{
struct page *next = nth_page(start, i);
struct folio *folio = page_folio(next);
unsigned int nr = 1;
if (folio_test_large(folio))
nr = min_t(unsigned int, npages - i,
folio_nr_pages(folio) - folio_page_idx(folio, next));
*ntails = nr;
return folio;
}
static inline struct folio *gup_folio_next(struct page **list,
unsigned long npages, unsigned long i, unsigned int *ntails)
{
struct folio *folio = page_folio(list[i]);
unsigned int nr;
for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio)
break;
}
*ntails = nr - i;
return folio;
}
/**
* unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
* @pages: array of pages to be maybe marked dirty, and definitely released.
* @npages: number of pages in the @pages array.
* @make_dirty: whether to mark the pages dirty
*
* "gup-pinned page" refers to a page that has had one of the get_user_pages()
* variants called on that page.
*
* For each page in the @pages array, make that page (or its head page, if a
* compound page) dirty, if @make_dirty is true, and if the page was previously
* listed as clean. In any case, releases all pages using unpin_user_page(),
* possibly via unpin_user_pages(), for the non-dirty case.
*
* Please see the unpin_user_page() documentation for details.
*
* set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
* required, then the caller should a) verify that this is really correct,
* because _lock() is usually required, and b) hand code it:
* set_page_dirty_lock(), unpin_user_page().
*
*/
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
bool make_dirty)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
if (!make_dirty) {
unpin_user_pages(pages, npages);
return;
}
sanity_check_pinned_pages(pages, npages);
for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr);
/*
* Checking PageDirty at this point may race with
* clear_page_dirty_for_io(), but that's OK. Two key
* cases:
*
* 1) This code sees the page as already dirty, so it
* skips the call to set_page_dirty(). That could happen
* because clear_page_dirty_for_io() called
* folio_mkclean(), followed by set_page_dirty().
* However, now the page is going to get written back,
* which meets the original intention of setting it
* dirty, so all is well: clear_page_dirty_for_io() goes
* on to call TestClearPageDirty(), and write the page
* back.
*
* 2) This code sees the page as clean, so it calls
* set_page_dirty(). The page stays dirty, despite being
* written back, so it gets written back again in the
* next writeback cycle. This is harmless.
*/
if (!folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
/**
* unpin_user_page_range_dirty_lock() - release and optionally dirty
* gup-pinned page range
*
* @page: the starting page of a range maybe marked dirty, and definitely released.
* @npages: number of consecutive pages to release.
* @make_dirty: whether to mark the pages dirty
*
* "gup-pinned page range" refers to a range of pages that has had one of the
* pin_user_pages() variants called on that page.
*
* For the page ranges defined by [page .. page+npages], make that range (or
* its head pages, if a compound page) dirty, if @make_dirty is true, and if the
* page range was previously listed as clean.
*
* set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
* required, then the caller should a) verify that this is really correct,
* because _lock() is usually required, and b) hand code it:
* set_page_dirty_lock(), unpin_user_page().
*
*/
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
bool make_dirty)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
for (i = 0; i < npages; i += nr) {
folio = gup_folio_range_next(page, npages, i, &nr);
if (make_dirty && !folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
/*
* Don't perform any sanity checks because we might have raced with
* fork() and some anonymous pages might now actually be shared --
* which is why we're unpinning after all.
*/
for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
/**
* unpin_user_pages() - release an array of gup-pinned pages.
* @pages: array of pages to be marked dirty and released.
* @npages: number of pages in the @pages array.
*
* For each page in the @pages array, release the page using unpin_user_page().
*
* Please see the unpin_user_page() documentation for details.
*/
void unpin_user_pages(struct page **pages, unsigned long npages)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
/*
* If this WARN_ON() fires, then the system *might* be leaking pages (by
* leaving them pinned), but probably not. More likely, gup/pup returned
* a hard -ERRNO error to the caller, who erroneously passed it here.
*/
if (WARN_ON(IS_ERR_VALUE(npages)))
return;
sanity_check_pinned_pages(pages, npages);
for (i = 0; i < npages; i += nr) {
if (!pages[i]) {
nr = 1;
continue;
}
folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages);
/**
* unpin_user_folio() - release pages of a folio
* @folio: pointer to folio to be released
* @npages: number of pages of same folio
*
* Release npages of the folio
*/
void unpin_user_folio(struct folio *folio, unsigned long npages)
{
gup_put_folio(folio, npages, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_folio);
/**
* unpin_folios() - release an array of gup-pinned folios.
* @folios: array of folios to be marked dirty and released.
* @nfolios: number of folios in the @folios array.
*
* For each folio in the @folios array, release the folio using gup_put_folio.
*
* Please see the unpin_folio() documentation for details.
*/
void unpin_folios(struct folio **folios, unsigned long nfolios)
{
unsigned long i = 0, j;
/*
* If this WARN_ON() fires, then the system *might* be leaking folios
* (by leaving them pinned), but probably not. More likely, gup/pup
* returned a hard -ERRNO error to the caller, who erroneously passed
* it here.
*/
if (WARN_ON(IS_ERR_VALUE(nfolios)))
return;
while (i < nfolios) {
for (j = i + 1; j < nfolios; j++)
if (folios[i] != folios[j])
break;
if (folios[i])
gup_put_folio(folios[i], j - i, FOLL_PIN);
i = j;
}
}
EXPORT_SYMBOL_GPL(unpin_folios);
/*
* Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
* lifecycle. Avoid setting the bit unless necessary, or it might cause write
* cache bouncing on large SMP machines for concurrent pinned gups.
*/
static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
{
if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags);
}
#ifdef CONFIG_MMU
#ifdef CONFIG_HAVE_GUP_FAST
static int record_subpages(struct page *page, unsigned long sz,
unsigned long addr, unsigned long end,
struct page **pages)
{
struct page *start_page;
int nr;
start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
pages[nr] = nth_page(start_page, nr);
return nr;
}
/**
* try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
* @page: pointer to page to be grabbed
* @refs: the value to (effectively) add to the folio's refcount
* @flags: gup flags: these are the FOLL_* flag values.
*
* "grab" names in this file mean, "look at flags to decide whether to use
* FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
*
* Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
* same time. (That's true throughout the get_user_pages*() and
* pin_user_pages*() APIs.) Cases:
*
* FOLL_GET: folio's refcount will be incremented by @refs.
*
* FOLL_PIN on large folios: folio's refcount will be incremented by
* @refs, and its pincount will be incremented by @refs.
*
* FOLL_PIN on single-page folios: folio's refcount will be incremented by
* @refs * GUP_PIN_COUNTING_BIAS.
*
* Return: The folio containing @page (with refcount appropriately
* incremented) for success, or NULL upon failure. If neither FOLL_GET
* nor FOLL_PIN was set, that's considered failure, and furthermore,
* a likely bug in the caller, so a warning is also emitted.
*
* It uses add ref unless zero to elevate the folio refcount and must be called
* in fast path only.
*/
static struct folio *try_grab_folio_fast(struct page *page, int refs,
unsigned int flags)
{
struct folio *folio;
/* Raise warn if it is not called in fast GUP */
VM_WARN_ON_ONCE(!irqs_disabled()); if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0))
return NULL;
if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
return NULL;
if (flags & FOLL_GET)
return try_get_folio(page, refs);
/* FOLL_PIN is set */
/*
* Don't take a pin on the zero page - it's not going anywhere
* and it is used in a *lot* of places.
*/
if (is_zero_page(page))
return page_folio(page);
folio = try_get_folio(page, refs);
if (!folio)
return NULL;
/*
* Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
* right zone, so fail and let the caller fall back to the slow
* path.
*/
if (unlikely((flags & FOLL_LONGTERM) &&
!folio_is_longterm_pinnable(folio))) {
folio_put_refs(folio, refs);
return NULL;
}
/*
* When pinning a large folio, use an exact count to track it.
*
* However, be sure to *also* increment the normal folio
* refcount field at least once, so that the folio really
* is pinned. That's why the refcount from the earlier
* try_get_folio() is left intact.
*/
if (folio_has_pincount(folio)) atomic_add(refs, &folio->_pincount);
else
folio_ref_add(folio,
refs * (GUP_PIN_COUNTING_BIAS - 1));
/*
* Adjust the pincount before re-checking the PTE for changes.
* This is essentially a smp_mb() and is paired with a memory
* barrier in folio_try_share_anon_rmap_*().
*/
smp_mb__after_atomic();
node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
return folio;
}
#endif /* CONFIG_HAVE_GUP_FAST */
/* Common code for can_follow_write_* */
static inline bool can_follow_write_common(struct page *page,
struct vm_area_struct *vma, unsigned int flags)
{
/* Maybe FOLL_FORCE is set to override it? */
if (!(flags & FOLL_FORCE))
return false;
/* But FOLL_FORCE has no effect on shared mappings */
if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
return false;
/* ... or read-only private ones */
if (!(vma->vm_flags & VM_MAYWRITE))
return false;
/* ... or already writable ones that just need to take a write fault */
if (vma->vm_flags & VM_WRITE)
return false;
/*
* See can_change_pte_writable(): we broke COW and could map the page
* writable if we have an exclusive anonymous page ...
*/
return page && PageAnon(page) && PageAnonExclusive(page);
}
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags, unsigned long address)
{
if (!(flags & FOLL_DUMP))
return NULL;
/*
* When core dumping, we don't want to allocate unnecessary pages or
* page tables. Return error instead of NULL to skip handle_mm_fault,
* then get_dump_page() will return NULL to leave a hole in the dump.
* But we can only make this optimization where a hole would surely
* be zero-filled if handle_mm_fault() actually did handle it.
*/
if (is_vm_hugetlb_page(vma)) {
struct hstate *h = hstate_vma(vma);
if (!hugetlbfs_pagecache_present(h, vma, address))
return ERR_PTR(-EFAULT);
} else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) {
return ERR_PTR(-EFAULT);
}
return NULL;
}
#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
/* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */
static inline bool can_follow_write_pud(pud_t pud, struct page *page,
struct vm_area_struct *vma,
unsigned int flags)
{
/* If the pud is writable, we can write to the page. */
if (pud_write(pud))
return true;
return can_follow_write_common(page, vma, flags);
}
static struct page *follow_huge_pud(struct vm_area_struct *vma,
unsigned long addr, pud_t *pudp,
int flags, struct follow_page_context *ctx)
{
struct mm_struct *mm = vma->vm_mm;
struct page *page;
pud_t pud = *pudp;
unsigned long pfn = pud_pfn(pud);
int ret;
assert_spin_locked(pud_lockptr(mm, pudp)); if (!pud_present(pud))
return NULL;
if ((flags & FOLL_WRITE) && !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags))
return NULL;
pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
pud_devmap(pud)) {
/*
* device mapped pages can only be returned if the caller
* will manage the page reference count.
*
* At least one of FOLL_GET | FOLL_PIN must be set, so
* assert that here:
*/
if (!(flags & (FOLL_GET | FOLL_PIN)))
return ERR_PTR(-EEXIST);
if (flags & FOLL_TOUCH)
touch_pud(vma, addr, pudp, flags & FOLL_WRITE);
ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap);
if (!ctx->pgmap)
return ERR_PTR(-EFAULT);
}
page = pfn_to_page(pfn);
if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page))
return ERR_PTR(-EMLINK);
ret = try_grab_folio(page_folio(page), 1, flags);
if (ret)
page = ERR_PTR(ret);
else
ctx->page_mask = HPAGE_PUD_NR - 1;
return page;
}
/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */
static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
struct vm_area_struct *vma,
unsigned int flags)
{
/* If the pmd is writable, we can write to the page. */
if (pmd_write(pmd))
return true;
if (!can_follow_write_common(page, vma, flags))
return false;
/* ... and a write-fault isn't required for other reasons. */
if (pmd_needs_soft_dirty_wp(vma, pmd))
return false;
return !userfaultfd_huge_pmd_wp(vma, pmd);
}
static struct page *follow_huge_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd,
unsigned int flags,
struct follow_page_context *ctx)
{
struct mm_struct *mm = vma->vm_mm;
pmd_t pmdval = *pmd;
struct page *page;
int ret;
assert_spin_locked(pmd_lockptr(mm, pmd));
page = pmd_page(pmdval);
if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags))
return NULL;
/* Avoid dumping huge zero page */
if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval))
return ERR_PTR(-EFAULT);
if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))
return NULL;
if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page))
return ERR_PTR(-EMLINK);
VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
!PageAnonExclusive(page), page);
ret = try_grab_folio(page_folio(page), 1, flags);
if (ret)
return ERR_PTR(ret);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
ctx->page_mask = HPAGE_PMD_NR - 1;
return page;
}
#else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
static struct page *follow_huge_pud(struct vm_area_struct *vma,
unsigned long addr, pud_t *pudp,
int flags, struct follow_page_context *ctx)
{
return NULL;
}
static struct page *follow_huge_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd,
unsigned int flags,
struct follow_page_context *ctx)
{
return NULL;
}
#endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
pte_t *pte, unsigned int flags)
{
if (flags & FOLL_TOUCH) {
pte_t orig_entry = ptep_get(pte);
pte_t entry = orig_entry;
if (flags & FOLL_WRITE)
entry = pte_mkdirty(entry);
entry = pte_mkyoung(entry);
if (!pte_same(orig_entry, entry)) {
set_pte_at(vma->vm_mm, address, pte, entry);
update_mmu_cache(vma, address, pte);
}
}
/* Proper page table entry exists, but no corresponding struct page */
return -EEXIST;
}
/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */
static inline bool can_follow_write_pte(pte_t pte, struct page *page,
struct vm_area_struct *vma,
unsigned int flags)
{
/* If the pte is writable, we can write to the page. */
if (pte_write(pte))
return true;
if (!can_follow_write_common(page, vma, flags))
return false;
/* ... and a write-fault isn't required for other reasons. */
if (pte_needs_soft_dirty_wp(vma, pte))
return false;
return !userfaultfd_pte_wp(vma, pte);
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags,
struct dev_pagemap **pgmap)
{
struct mm_struct *mm = vma->vm_mm;
struct folio *folio;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
int ret;
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
(FOLL_PIN | FOLL_GET)))
return ERR_PTR(-EINVAL);
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!ptep)
return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte))
goto no_page;
if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags))
goto no_page;
page = vm_normal_page(vma, address, pte);
/*
* We only care about anon pages in can_follow_write_pte() and don't
* have to worry about pte_devmap() because they are never anon.
*/
if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) {
page = NULL;
goto out;
}
if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
/*
* Only return device mapping pages in the FOLL_GET or FOLL_PIN
* case since they are only valid while holding the pgmap
* reference.
*/
*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
if (*pgmap)
page = pte_page(pte);
else
goto no_page;
} else if (unlikely(!page)) { if (flags & FOLL_DUMP) {
/* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT);
goto out;
}
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
}
}
folio = page_folio(page); if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) {
page = ERR_PTR(-EMLINK);
goto out;
}
VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
!PageAnonExclusive(page), page);
/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
ret = try_grab_folio(folio, 1, flags);
if (unlikely(ret)) {
page = ERR_PTR(ret);
goto out;
}
/*
* We need to make the page accessible if and only if we are going
* to access its content (the FOLL_PIN case). Please see
* Documentation/core-api/pin_user_pages.rst for details.
*/
if (flags & FOLL_PIN) {
ret = arch_make_folio_accessible(folio);
if (ret) {
unpin_user_page(page);
page = ERR_PTR(ret);
goto out;
}
}
if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !folio_test_dirty(folio)) folio_mark_dirty(folio);
/*
* pte_mkyoung() would be more correct here, but atomic care
* is needed to avoid losing the dirty bit: it is easier to use
* folio_mark_accessed().
*/
folio_mark_accessed(folio);
}
out:
pte_unmap_unlock(ptep, ptl);
return page;
no_page:
pte_unmap_unlock(ptep, ptl); if (!pte_none(pte))
return NULL;
return no_page_table(vma, flags, address);
}
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
unsigned int flags,
struct follow_page_context *ctx)
{
pmd_t *pmd, pmdval;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
pmd = pmd_offset(pudp, address);
pmdval = pmdp_get_lockless(pmd);
if (pmd_none(pmdval))
return no_page_table(vma, flags, address);
if (!pmd_present(pmdval))
return no_page_table(vma, flags, address); if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
return no_page_table(vma, flags, address);
}
if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address);
ptl = pmd_lock(mm, pmd);
pmdval = *pmd;
if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl);
return no_page_table(vma, flags, address);
}
if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) {
spin_unlock(ptl);
split_huge_pmd(vma, pmd, address);
/* If pmd was left empty, stuff a page table in there quickly */
return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) :
follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
page = follow_huge_pmd(vma, address, pmd, flags, ctx);
spin_unlock(ptl);
return page;
}
static struct page *follow_pud_mask(struct vm_area_struct *vma,
unsigned long address, p4d_t *p4dp,
unsigned int flags,
struct follow_page_context *ctx)
{
pud_t *pudp, pud;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
pudp = pud_offset(p4dp, address);
pud = READ_ONCE(*pudp);
if (!pud_present(pud)) return no_page_table(vma, flags, address); if (pud_leaf(pud)) {
ptl = pud_lock(mm, pudp);
page = follow_huge_pud(vma, address, pudp, flags, ctx);
spin_unlock(ptl);
if (page)
return page;
return no_page_table(vma, flags, address);
}
if (unlikely(pud_bad(pud)))
return no_page_table(vma, flags, address);
return follow_pmd_mask(vma, address, pudp, flags, ctx);
}
static struct page *follow_p4d_mask(struct vm_area_struct *vma,
unsigned long address, pgd_t *pgdp,
unsigned int flags,
struct follow_page_context *ctx)
{
p4d_t *p4dp, p4d;
p4dp = p4d_offset(pgdp, address);
p4d = READ_ONCE(*p4dp);
BUILD_BUG_ON(p4d_leaf(p4d));
if (!p4d_present(p4d) || p4d_bad(p4d))
return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx);
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
* pointer to output page_mask
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
* the device's dev_pagemap metadata to avoid repeating expensive lookups.
*
* When getting an anonymous page and the caller has to trigger unsharing
* of a shared anonymous page first, -EMLINK is returned. The caller should
* trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
* relevant with FOLL_PIN and !FOLL_WRITE.
*
* On output, the @ctx->page_mask is set according to the size of the page.
*
* Return: the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
static struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
struct follow_page_context *ctx)
{
pgd_t *pgd;
struct mm_struct *mm = vma->vm_mm;
struct page *page;
vma_pgtable_walk_begin(vma);
ctx->page_mask = 0;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address);
else
page = follow_p4d_mask(vma, address, pgd, flags, ctx);
vma_pgtable_walk_end(vma);
return page;
}
static int get_gate_page(struct mm_struct *mm, unsigned long address,
unsigned int gup_flags, struct vm_area_struct **vma,
struct page **page)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
pte_t entry;
int ret = -EFAULT;
/* user gate pages are read-only */
if (gup_flags & FOLL_WRITE)
return -EFAULT;
if (address > TASK_SIZE)
pgd = pgd_offset_k(address);
else
pgd = pgd_offset_gate(mm, address);
if (pgd_none(*pgd))
return -EFAULT;
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d))
return -EFAULT;
pud = pud_offset(p4d, address);
if (pud_none(*pud))
return -EFAULT;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return -EFAULT;
pte = pte_offset_map(pmd, address);
if (!pte)
return -EFAULT;
entry = ptep_get(pte);
if (pte_none(entry))
goto unmap;
*vma = get_gate_vma(mm);
if (!page)
goto out;
*page = vm_normal_page(*vma, address, entry);
if (!*page) {
if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry)))
goto unmap;
*page = pte_page(entry);
}
ret = try_grab_folio(page_folio(*page), 1, gup_flags);
if (unlikely(ret))
goto unmap;
out:
ret = 0;
unmap:
pte_unmap(pte);
return ret;
}
/*
* mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not
* FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set
* to 0 and -EBUSY returned.
*/
static int faultin_page(struct vm_area_struct *vma,
unsigned long address, unsigned int flags, bool unshare,
int *locked)
{
unsigned int fault_flags = 0;
vm_fault_t ret;
if (flags & FOLL_NOFAULT)
return -EFAULT;
if (flags & FOLL_WRITE)
fault_flags |= FAULT_FLAG_WRITE;
if (flags & FOLL_REMOTE)
fault_flags |= FAULT_FLAG_REMOTE;
if (flags & FOLL_UNLOCKABLE) {
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/*
* FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set
* FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE.
* That's because some callers may not be prepared to
* handle early exits caused by non-fatal signals.
*/
if (flags & FOLL_INTERRUPTIBLE)
fault_flags |= FAULT_FLAG_INTERRUPTIBLE;
}
if (flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
if (flags & FOLL_TRIED) {
/*
* Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
* can co-exist
*/
fault_flags |= FAULT_FLAG_TRIED;
}
if (unshare) {
fault_flags |= FAULT_FLAG_UNSHARE;
/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
}
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) {
/*
* With FAULT_FLAG_RETRY_NOWAIT we'll never release the
* mmap lock in the page fault handler. Sanity check this.
*/
WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT);
*locked = 0;
/*
* We should do the same as VM_FAULT_RETRY, but let's not
* return -EBUSY since that's not reflecting the reality of
* what has happened - we've just fully completed a page
* fault, with the mmap lock released. Use -EAGAIN to show
* that we want to take the mmap lock _again_.
*/
return -EAGAIN;
}
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, flags);
if (err)
return err;
BUG();
}
if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0;
return -EBUSY;
}
return 0;
}
/*
* Writing to file-backed mappings which require folio dirty tracking using GUP
* is a fundamentally broken operation, as kernel write access to GUP mappings
* do not adhere to the semantics expected by a file system.
*
* Consider the following scenario:-
*
* 1. A folio is written to via GUP which write-faults the memory, notifying
* the file system and dirtying the folio.
* 2. Later, writeback is triggered, resulting in the folio being cleaned and
* the PTE being marked read-only.
* 3. The GUP caller writes to the folio, as it is mapped read/write via the
* direct mapping.
* 4. The GUP caller, now done with the page, unpins it and sets it dirty
* (though it does not have to).
*
* This results in both data being written to a folio without writenotify, and
* the folio being dirtied unexpectedly (if the caller decides to do so).
*/
static bool writable_file_mapping_allowed(struct vm_area_struct *vma,
unsigned long gup_flags)
{
/*
* If we aren't pinning then no problematic write can occur. A long term
* pin is the most egregious case so this is the case we disallow.
*/
if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) !=
(FOLL_PIN | FOLL_LONGTERM))
return true;
/*
* If the VMA does not require dirty tracking then no problematic write
* can occur either.
*/
return !vma_needs_dirty_tracking(vma);
}
static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
vm_flags_t vm_flags = vma->vm_flags;
int write = (gup_flags & FOLL_WRITE);
int foreign = (gup_flags & FOLL_REMOTE);
bool vma_anon = vma_is_anonymous(vma);
if (vm_flags & (VM_IO | VM_PFNMAP))
return -EFAULT;
if ((gup_flags & FOLL_ANON) && !vma_anon)
return -EFAULT;
if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
return -EOPNOTSUPP;
if ((gup_flags & FOLL_SPLIT_PMD) && is_vm_hugetlb_page(vma))
return -EOPNOTSUPP;
if (vma_is_secretmem(vma))
return -EFAULT;
if (write) {
if (!vma_anon &&
!writable_file_mapping_allowed(vma, gup_flags))
return -EFAULT;
if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE))
return -EFAULT;
/*
* We used to let the write,force case do COW in a
* VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
* set a breakpoint in a read-only mapping of an
* executable, without corrupting the file (yet only
* when that file had been opened for writing!).
* Anon pages in shared mappings are surprising: now
* just reject it.
*/
if (!is_cow_mapping(vm_flags))
return -EFAULT;
}
} else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE))
return -EFAULT;
/*
* Is there actually any vma we can reach here which does not
* have VM_MAYREAD set?
*/
if (!(vm_flags & VM_MAYREAD))
return -EFAULT;
}
/*
* gups are always data accesses, not instruction
* fetches, so execute=false here
*/
if (!arch_vma_access_permitted(vma, write, false, foreign))
return -EFAULT;
return 0;
}
/*
* This is "vma_lookup()", but with a warning if we would have
* historically expanded the stack in the GUP code.
*/
static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm,
unsigned long addr)
{
#ifdef CONFIG_STACK_GROWSUP
return vma_lookup(mm, addr);
#else
static volatile unsigned long next_warn;
struct vm_area_struct *vma;
unsigned long now, next;
vma = find_vma(mm, addr);
if (!vma || (addr >= vma->vm_start))
return vma;
/* Only warn for half-way relevant accesses */
if (!(vma->vm_flags & VM_GROWSDOWN))
return NULL;
if (vma->vm_start - addr > 65536)
return NULL;
/* Let's not warn more than once an hour.. */
now = jiffies; next = next_warn;
if (next && time_before(now, next))
return NULL;
next_warn = now + 60*60*HZ;
/* Let people know things may have changed. */
pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n",
current->comm, task_pid_nr(current),
vma->vm_start, vma->vm_end, addr);
dump_stack();
return NULL;
#endif
}
/**
* __get_user_pages() - pin user pages in memory
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
* @locked: whether we're still with the mmap_lock held
*
* Returns either number of pages pinned (which may be less than the
* number requested), or an error. Details about the return value:
*
* -- If nr_pages is 0, returns 0.
* -- If nr_pages is >0, but no pages were pinned, returns -errno.
* -- If nr_pages is >0, and some pages were pinned, returns the number of
* pages pinned. Again, this may be less than nr_pages.
* -- 0 return value is possible when the fault would need to be retried.
*
* The caller is responsible for releasing returned @pages, via put_page().
*
* Must be called with mmap_lock held. It may be released. See below.
*
* __get_user_pages walks a process's page tables and takes a reference to
* each struct page that each user address corresponds to at a given
* instant. That is, it takes the page that would be accessed if a user
* thread accesses the given user virtual address at that instant.
*
* This does not guarantee that the page exists in the user mappings when
* __get_user_pages returns, and there may even be a completely different
* page there in some cases (eg. if mmapped pagecache has been invalidated
* and subsequently re-faulted). However it does guarantee that the page
* won't be freed completely. And mostly callers simply care that the page
* contains data that was valid *at some point in time*. Typically, an IO
* or similar operation cannot guarantee anything stronger anyway because
* locks can't be held over the syscall boundary.
*
* If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
* the page is written to, set_page_dirty (or set_page_dirty_lock, as
* appropriate) must be called after the page is finished with, and
* before put_page is called.
*
* If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may
* be released. If this happens *@locked will be set to 0 on return.
*
* A caller using such a combination of @gup_flags must therefore hold the
* mmap_lock for reading only, and recognize when it's been released. Otherwise,
* it must be held for either reading or writing and will not be released.
*
* In most cases, get_user_pages or get_user_pages_fast should be used
* instead of __get_user_pages. __get_user_pages should be used only if
* you need some special @gup_flags.
*/
static long __get_user_pages(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked)
{
long ret = 0, i = 0;
struct vm_area_struct *vma = NULL;
struct follow_page_context ctx = { NULL };
if (!nr_pages)
return 0;
start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
do {
struct page *page;
unsigned int page_increm;
/* first iteration or cross vma bound */
if (!vma || start >= vma->vm_end) {
/*
* MADV_POPULATE_(READ|WRITE) wants to handle VMA
* lookups+error reporting differently.
*/
if (gup_flags & FOLL_MADV_POPULATE) {
vma = vma_lookup(mm, start);
if (!vma) {
ret = -ENOMEM;
goto out;
}
if (check_vma_flags(vma, gup_flags)) {
ret = -EINVAL;
goto out;
}
goto retry;
}
vma = gup_vma_lookup(mm, start);
if (!vma && in_gate_area(mm, start)) {
ret = get_gate_page(mm, start & PAGE_MASK,
gup_flags, &vma,
pages ? &page : NULL);
if (ret)
goto out;
ctx.page_mask = 0;
goto next_page;
}
if (!vma) {
ret = -EFAULT;
goto out;
}
ret = check_vma_flags(vma, gup_flags); if (ret)
goto out;
}
retry:
/*
* If we have a pending SIGKILL, don't keep faulting pages and
* potentially allocating memory.
*/
if (fatal_signal_pending(current)) {
ret = -EINTR;
goto out;
}
cond_resched();
page = follow_page_mask(vma, start, gup_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, gup_flags,
PTR_ERR(page) == -EMLINK, locked);
switch (ret) {
case 0:
goto retry;
case -EBUSY:
case -EAGAIN:
ret = 0;
fallthrough;
case -EFAULT:
case -ENOMEM:
case -EHWPOISON:
goto out;
}
BUG();
} else if (PTR_ERR(page) == -EEXIST) {
/*
* Proper page table entry exists, but no corresponding
* struct page. If the caller expects **pages to be
* filled in, bail out now, because that can't be done
* for this page.
*/
if (pages) {
ret = PTR_ERR(page);
goto out;
}
} else if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto out;
}
next_page:
page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
if (page_increm > nr_pages)
page_increm = nr_pages;
if (pages) {
struct page *subpage;
unsigned int j;
/*
* This must be a large folio (and doesn't need to
* be the whole folio; it can be part of it), do
* the refcount work for all the subpages too.
*
* NOTE: here the page may not be the head page
* e.g. when start addr is not thp-size aligned.
* try_grab_folio() should have taken care of tail
* pages.
*/
if (page_increm > 1) { struct folio *folio = page_folio(page);
/*
* Since we already hold refcount on the
* large folio, this should never fail.
*/
if (try_grab_folio(folio, page_increm - 1,
gup_flags)) {
/*
* Release the 1st page ref if the
* folio is problematic, fail hard.
*/
gup_put_folio(folio, 1, gup_flags);
ret = -EFAULT;
goto out;
}
}
for (j = 0; j < page_increm; j++) {
subpage = nth_page(page, j);
pages[i + j] = subpage;
flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
flush_dcache_page(subpage);
}
}
i += page_increm;
start += page_increm * PAGE_SIZE;
nr_pages -= page_increm;
} while (nr_pages);
out:
if (ctx.pgmap) put_dev_pagemap(ctx.pgmap);
return i ? i : ret;
}
static bool vma_permits_fault(struct vm_area_struct *vma,
unsigned int fault_flags)
{
bool write = !!(fault_flags & FAULT_FLAG_WRITE);
bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE);
vm_flags_t vm_flags = write ? VM_WRITE : VM_READ;
if (!(vm_flags & vma->vm_flags))
return false;
/*
* The architecture might have a hardware protection
* mechanism other than read/write that can deny access.
*
* gup always represents data access, not instruction
* fetches, so execute=false here:
*/
if (!arch_vma_access_permitted(vma, write, false, foreign))
return false;
return true;
}
/**
* fixup_user_fault() - manually resolve a user page fault
* @mm: mm_struct of target mm
* @address: user address
* @fault_flags:flags to pass down to handle_mm_fault()
* @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller
* does not allow retry. If NULL, the caller must guarantee
* that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY.
*
* This is meant to be called in the specific scenario where for locking reasons
* we try to access user memory in atomic context (within a pagefault_disable()
* section), this returns -EFAULT, and we want to resolve the user fault before
* trying again.
*
* Typically this is meant to be used by the futex code.
*
* The main difference with get_user_pages() is that this function will
* unconditionally call handle_mm_fault() which will in turn perform all the
* necessary SW fixup of the dirty and young bits in the PTE, while
* get_user_pages() only guarantees to update these in the struct page.
*
* This is important for some architectures where those bits also gate the
* access permission to the page because they are maintained in software. On
* such architectures, gup() will not be enough to make a subsequent access
* succeed.
*
* This function will not return with an unlocked mmap_lock. So it has not the
* same semantics wrt the @mm->mmap_lock as does filemap_fault().
*/
int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked)
{
struct vm_area_struct *vma;
vm_fault_t ret;
address = untagged_addr_remote(mm, address);
if (unlocked)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
retry:
vma = gup_vma_lookup(mm, address);
if (!vma)
return -EFAULT;
if (!vma_permits_fault(vma, fault_flags))
return -EFAULT;
if ((fault_flags & FAULT_FLAG_KILLABLE) &&
fatal_signal_pending(current))
return -EINTR;
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) {
/*
* NOTE: it's a pity that we need to retake the lock here
* to pair with the unlock() in the callers. Ideally we
* could tell the callers so they do not need to unlock.
*/
mmap_read_lock(mm);
*unlocked = true;
return 0;
}
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, 0);
if (err)
return err;
BUG();
}
if (ret & VM_FAULT_RETRY) {
mmap_read_lock(mm);
*unlocked = true;
fault_flags |= FAULT_FLAG_TRIED;
goto retry;
}
return 0;
}
EXPORT_SYMBOL_GPL(fixup_user_fault);
/*
* GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is
* specified, it'll also respond to generic signals. The caller of GUP
* that has FOLL_INTERRUPTIBLE should take care of the GUP interruption.
*/
static bool gup_signal_pending(unsigned int flags)
{
if (fatal_signal_pending(current))
return true;
if (!(flags & FOLL_INTERRUPTIBLE))
return false;
return signal_pending(current);
}
/*
* Locking: (*locked == 1) means that the mmap_lock has already been acquired by
* the caller. This function may drop the mmap_lock. If it does so, then it will
* set (*locked = 0).
*
* (*locked == 0) means that the caller expects this function to acquire and
* drop the mmap_lock. Therefore, the value of *locked will still be zero when
* the function returns, even though it may have changed temporarily during
* function execution.
*
* Please note that this function, unlike __get_user_pages(), will not return 0
* for nr_pages > 0, unless FOLL_NOWAIT is used.
*/
static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
struct page **pages,
int *locked,
unsigned int flags)
{
long ret, pages_done;
bool must_unlock = false;
if (!nr_pages)
return 0;
/*
* The internal caller expects GUP to manage the lock internally and the
* lock must be released when this returns.
*/
if (!*locked) {
if (mmap_read_lock_killable(mm))
return -EAGAIN;
must_unlock = true;
*locked = 1;
}
else
mmap_assert_locked(mm);
if (flags & FOLL_PIN)
mm_set_has_pinned_flag(&mm->flags);
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
* is to set FOLL_GET if the caller wants pages[] filled in (but has
* carelessly failed to specify FOLL_GET), so keep doing that, but only
* for FOLL_GET, not for the newer FOLL_PIN.
*
* FOLL_PIN always expects pages to be non-null, but no need to assert
* that here, as any failures will be obvious enough.
*/
if (pages && !(flags & FOLL_PIN))
flags |= FOLL_GET;
pages_done = 0;
for (;;) {
ret = __get_user_pages(mm, start, nr_pages, flags, pages,
locked);
if (!(flags & FOLL_UNLOCKABLE)) {
/* VM_FAULT_RETRY couldn't trigger, bypass */
pages_done = ret;
break;
}
/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages);
}
if (ret > 0) {
nr_pages -= ret;
pages_done += ret;
if (!nr_pages)
break;
}
if (*locked) {
/*
* VM_FAULT_RETRY didn't trigger or it was a
* FOLL_NOWAIT.
*/
if (!pages_done)
pages_done = ret;
break;
}
/*
* VM_FAULT_RETRY triggered, so seek to the faulting offset.
* For the prefault case (!pages) we only update counts.
*/
if (likely(pages))
pages += ret;
start += ret << PAGE_SHIFT;
/* The lock was temporarily dropped, so we must unlock later */
must_unlock = true;
retry:
/*
* Repeat on the address that fired VM_FAULT_RETRY
* with both FAULT_FLAG_ALLOW_RETRY and
* FAULT_FLAG_TRIED. Note that GUP can be interrupted
* by fatal signals of even common signals, depending on
* the caller's request. So we need to check it before we
* start trying again otherwise it can loop forever.
*/
if (gup_signal_pending(flags)) {
if (!pages_done)
pages_done = -EINTR;
break;
}
ret = mmap_read_lock_killable(mm);
if (ret) {
BUG_ON(ret > 0);
if (!pages_done)
pages_done = ret;
break;
}
*locked = 1;
ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
pages, locked);
if (!*locked) {
/* Continue to retry until we succeeded */
BUG_ON(ret != 0);
goto retry;
}
if (ret != 1) {
BUG_ON(ret > 1); if (!pages_done)
pages_done = ret;
break;
}
nr_pages--;
pages_done++;
if (!nr_pages)
break;
if (likely(pages))
pages++;
start += PAGE_SIZE;
}
if (must_unlock && *locked) {
/*
* We either temporarily dropped the lock, or the caller
* requested that we both acquire and drop the lock. Either way,
* we must now unlock, and notify the caller of that state.
*/
mmap_read_unlock(mm);
*locked = 0;
}
/*
* Failing to pin anything implies something has gone wrong (except when
* FOLL_NOWAIT is specified).
*/
if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT)))
return -EFAULT;
return pages_done;
}
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
* @locked: whether the mmap_lock is still held
*
* This takes care of mlocking the pages too if VM_LOCKED is set.
*
* Return either number of pages pinned in the vma, or a negative error
* code on error.
*
* vma->vm_mm->mmap_lock must be held.
*
* If @locked is NULL, it may be held for read or write and will
* be unperturbed.
*
* If @locked is non-NULL, it must held for read only and may be
* released. If it's released, *@locked will be set to 0.
*/
long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *locked)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
int local_locked = 1;
int gup_flags;
long ret;
VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm);
/*
* Rightly or wrongly, the VM_LOCKONFAULT case has never used
* faultin_page() to break COW, so it has no work to do here.
*/
if (vma->vm_flags & VM_LOCKONFAULT)
return nr_pages;
/* ... similarly, we've never faulted in PROT_NONE pages */
if (!vma_is_accessible(vma))
return -EFAULT;
gup_flags = FOLL_TOUCH;
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
* and we would not want to dirty them for nothing.
*
* Otherwise, do a read fault, and use FOLL_FORCE in case it's not
* readable (ie write-only or executable).
*/
if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE;
else
gup_flags |= FOLL_FORCE;
if (locked)
gup_flags |= FOLL_UNLOCKABLE;
/*
* We made sure addr is within a VMA, so the following will
* not result in a stack expansion that recurses back here.
*/
ret = __get_user_pages(mm, start, nr_pages, gup_flags,
NULL, locked ? locked : &local_locked);
lru_add_drain();
return ret;
}
/*
* faultin_page_range() - populate (prefault) page tables inside the
* given range readable/writable
*
* This takes care of mlocking the pages, too, if VM_LOCKED is set.
*
* @mm: the mm to populate page tables in
* @start: start address
* @end: end address
* @write: whether to prefault readable or writable
* @locked: whether the mmap_lock is still held
*
* Returns either number of processed pages in the MM, or a negative error
* code on error (see __get_user_pages()). Note that this function reports
* errors related to VMAs, such as incompatible mappings, as expected by
* MADV_POPULATE_(READ|WRITE).
*
* The range must be page-aligned.
*
* mm->mmap_lock must be held. If it's released, *@locked will be set to 0.
*/
long faultin_page_range(struct mm_struct *mm, unsigned long start,
unsigned long end, bool write, int *locked)
{
unsigned long nr_pages = (end - start) / PAGE_SIZE;
int gup_flags;
long ret;
VM_BUG_ON(!PAGE_ALIGNED(start));
VM_BUG_ON(!PAGE_ALIGNED(end));
mmap_assert_locked(mm);
/*
* FOLL_TOUCH: Mark page accessed and thereby young; will also mark
* the page dirty with FOLL_WRITE -- which doesn't make a
* difference with !FOLL_FORCE, because the page is writable
* in the page table.
* FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit
* a poisoned page.
* !FOLL_FORCE: Require proper access permissions.
*/
gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE |
FOLL_MADV_POPULATE;
if (write)
gup_flags |= FOLL_WRITE;
ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked,
gup_flags);
lru_add_drain();
return ret;
}
/*
* __mm_populate - populate and/or mlock pages within a range of address space.
*
* This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
* flags. VMAs must be already marked with the desired vm_flags, and
* mmap_lock must not be held.
*/
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
struct mm_struct *mm = current->mm;
unsigned long end, nstart, nend;
struct vm_area_struct *vma = NULL;
int locked = 0;
long ret = 0;
end = start + len;
for (nstart = start; nstart < end; nstart = nend) {
/*
* We want to fault in pages for [nstart; end) address range.
* Find first corresponding VMA.
*/
if (!locked) {
locked = 1;
mmap_read_lock(mm);
vma = find_vma_intersection(mm, nstart, end);
} else if (nstart >= vma->vm_end)
vma = find_vma_intersection(mm, vma->vm_end, end);
if (!vma)
break;
/*
* Set [nstart; nend) to intersection of desired address
* range with the first VMA. Also, skip undesirable VMA types.
*/
nend = min(end, vma->vm_end);
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
continue;
if (nstart < vma->vm_start)
nstart = vma->vm_start;
/*
* Now fault in a range of pages. populate_vma_page_range()
* double checks the vma flags, so that it won't mlock pages
* if the vma was already munlocked.
*/
ret = populate_vma_page_range(vma, nstart, nend, &locked);
if (ret < 0) {
if (ignore_errors) {
ret = 0;
continue; /* continue at next VMA */
}
break;
}
nend = nstart + ret * PAGE_SIZE;
ret = 0;
}
if (locked) mmap_read_unlock(mm);
return ret; /* 0 or negative error code */
}
#else /* CONFIG_MMU */
static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
unsigned long nr_pages, struct page **pages,
int *locked, unsigned int foll_flags)
{
struct vm_area_struct *vma;
bool must_unlock = false;
unsigned long vm_flags;
long i;
if (!nr_pages)
return 0;
/*
* The internal caller expects GUP to manage the lock internally and the
* lock must be released when this returns.
*/
if (!*locked) {
if (mmap_read_lock_killable(mm))
return -EAGAIN;
must_unlock = true;
*locked = 1;
}
/* calculate required read or write permissions.
* If FOLL_FORCE is set, we only require the "MAY" flags.
*/
vm_flags = (foll_flags & FOLL_WRITE) ?
(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
vm_flags &= (foll_flags & FOLL_FORCE) ?
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
for (i = 0; i < nr_pages; i++) {
vma = find_vma(mm, start);
if (!vma)
break;
/* protect what we can, including chardevs */
if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
!(vm_flags & vma->vm_flags))
break;
if (pages) {
pages[i] = virt_to_page((void *)start);
if (pages[i])
get_page(pages[i]);
}
start = (start + PAGE_SIZE) & PAGE_MASK;
}
if (must_unlock && *locked) {
mmap_read_unlock(mm);
*locked = 0;
}
return i ? : -EFAULT;
}
#endif /* !CONFIG_MMU */
/**
* fault_in_writeable - fault in userspace address range for writing
* @uaddr: start of address range
* @size: size of address range
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_writeable(char __user *uaddr, size_t size)
{
char __user *start = uaddr, *end;
if (unlikely(size == 0))
return 0;
if (!user_write_access_begin(uaddr, size))
return size;
if (!PAGE_ALIGNED(uaddr)) {
unsafe_put_user(0, uaddr, out);
uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr);
}
end = (char __user *)PAGE_ALIGN((unsigned long)start + size);
if (unlikely(end < start))
end = NULL;
while (uaddr != end) {
unsafe_put_user(0, uaddr, out);
uaddr += PAGE_SIZE;
}
out:
user_write_access_end();
if (size > uaddr - start)
return size - (uaddr - start);
return 0;
}
EXPORT_SYMBOL(fault_in_writeable);
/**
* fault_in_subpage_writeable - fault in an address range for writing
* @uaddr: start of address range
* @size: size of address range
*
* Fault in a user address range for writing while checking for permissions at
* sub-page granularity (e.g. arm64 MTE). This function should be used when
* the caller cannot guarantee forward progress of a copy_to_user() loop.
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_subpage_writeable(char __user *uaddr, size_t size)
{
size_t faulted_in;
/*
* Attempt faulting in at page granularity first for page table
* permission checking. The arch-specific probe_subpage_writeable()
* functions may not check for this.
*/
faulted_in = size - fault_in_writeable(uaddr, size);
if (faulted_in)
faulted_in -= probe_subpage_writeable(uaddr, faulted_in);
return size - faulted_in;
}
EXPORT_SYMBOL(fault_in_subpage_writeable);
/*
* fault_in_safe_writeable - fault in an address range for writing
* @uaddr: start of address range
* @size: length of address range
*
* Faults in an address range for writing. This is primarily useful when we
* already know that some or all of the pages in the address range aren't in
* memory.
*
* Unlike fault_in_writeable(), this function is non-destructive.
*
* Note that we don't pin or otherwise hold the pages referenced that we fault
* in. There's no guarantee that they'll stay in memory for any duration of
* time.
*
* Returns the number of bytes not faulted in, like copy_to_user() and
* copy_from_user().
*/
size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
{
unsigned long start = (unsigned long)uaddr, end;
struct mm_struct *mm = current->mm;
bool unlocked = false;
if (unlikely(size == 0))
return 0;
end = PAGE_ALIGN(start + size);
if (end < start)
end = 0;
mmap_read_lock(mm);
do {
if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked))
break;
start = (start + PAGE_SIZE) & PAGE_MASK;
} while (start != end);
mmap_read_unlock(mm);
if (size > start - (unsigned long)uaddr)
return size - (start - (unsigned long)uaddr);
return 0;
}
EXPORT_SYMBOL(fault_in_safe_writeable);
/**
* fault_in_readable - fault in userspace address range for reading
* @uaddr: start of user address range
* @size: size of user address range
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_readable(const char __user *uaddr, size_t size)
{
const char __user *start = uaddr, *end;
volatile char c;
if (unlikely(size == 0))
return 0;
if (!user_read_access_begin(uaddr, size))
return size;
if (!PAGE_ALIGNED(uaddr)) {
unsafe_get_user(c, uaddr, out);
uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr);
}
end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out);
uaddr += PAGE_SIZE;
}
out:
user_read_access_end();
(void)c;
if (size > uaddr - start)
return size - (uaddr - start);
return 0;
}
EXPORT_SYMBOL(fault_in_readable);
/**
* get_dump_page() - pin user page in memory while writing it to core dump
* @addr: user address
* @locked: a pointer to an int denoting whether the mmap sem is held
*
* Returns struct page pointer of user page pinned for dump,
* to be freed afterwards by put_page().
*
* Returns NULL on any kind of failure - a hole must then be inserted into
* the corefile, to preserve alignment with its headers; and also returns
* NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
* allowing a hole to be left in the corefile to save disk space.
*
* Called without mmap_lock (takes and releases the mmap_lock by itself).
*/
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr, int *locked)
{
struct page *page;
int ret;
ret = __get_user_pages_locked(current->mm, addr, 1, &page, locked,
FOLL_FORCE | FOLL_DUMP | FOLL_GET);
return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
#ifdef CONFIG_MIGRATION
/*
* An array of either pages or folios ("pofs"). Although it may seem tempting to
* avoid this complication, by simply interpreting a list of folios as a list of
* pages, that approach won't work in the longer term, because eventually the
* layouts of struct page and struct folio will become completely different.
* Furthermore, this pof approach avoids excessive page_folio() calls.
*/
struct pages_or_folios {
union {
struct page **pages;
struct folio **folios;
void **entries;
};
bool has_folios;
long nr_entries;
};
static struct folio *pofs_get_folio(struct pages_or_folios *pofs, long i)
{
if (pofs->has_folios)
return pofs->folios[i];
return page_folio(pofs->pages[i]);
}
static void pofs_clear_entry(struct pages_or_folios *pofs, long i)
{
pofs->entries[i] = NULL;
}
static void pofs_unpin(struct pages_or_folios *pofs)
{
if (pofs->has_folios)
unpin_folios(pofs->folios, pofs->nr_entries);
else
unpin_user_pages(pofs->pages, pofs->nr_entries);
}
/*
* Returns the number of collected folios. Return value is always >= 0.
*/
static void collect_longterm_unpinnable_folios(
struct list_head *movable_folio_list,
struct pages_or_folios *pofs)
{
struct folio *prev_folio = NULL;
bool drain_allow = true;
unsigned long i;
for (i = 0; i < pofs->nr_entries; i++) {
struct folio *folio = pofs_get_folio(pofs, i);
if (folio == prev_folio)
continue;
prev_folio = folio;
if (folio_is_longterm_pinnable(folio))
continue;
if (folio_is_device_coherent(folio))
continue;
if (folio_test_hugetlb(folio)) {
folio_isolate_hugetlb(folio, movable_folio_list);
continue;
}
if (!folio_test_lru(folio) && drain_allow) {
lru_add_drain_all();
drain_allow = false;
}
if (!folio_isolate_lru(folio))
continue;
list_add_tail(&folio->lru, movable_folio_list);
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
}
}
/*
* Unpins all folios and migrates device coherent folios and movable_folio_list.
* Returns -EAGAIN if all folios were successfully migrated or -errno for
* failure (or partial success).
*/
static int
migrate_longterm_unpinnable_folios(struct list_head *movable_folio_list,
struct pages_or_folios *pofs)
{
int ret;
unsigned long i;
for (i = 0; i < pofs->nr_entries; i++) {
struct folio *folio = pofs_get_folio(pofs, i);
if (folio_is_device_coherent(folio)) {
/*
* Migration will fail if the folio is pinned, so
* convert the pin on the source folio to a normal
* reference.
*/
pofs_clear_entry(pofs, i);
folio_get(folio);
gup_put_folio(folio, 1, FOLL_PIN);
if (migrate_device_coherent_folio(folio)) {
ret = -EBUSY;
goto err;
}
continue;
}
/*
* We can't migrate folios with unexpected references, so drop
* the reference obtained by __get_user_pages_locked().
* Migrating folios have been added to movable_folio_list after
* calling folio_isolate_lru() which takes a reference so the
* folio won't be freed if it's migrating.
*/
unpin_folio(folio);
pofs_clear_entry(pofs, i);
}
if (!list_empty(movable_folio_list)) {
struct migration_target_control mtc = {
.nid = NUMA_NO_NODE,
.gfp_mask = GFP_USER | __GFP_NOWARN,
.reason = MR_LONGTERM_PIN,
};
if (migrate_pages(movable_folio_list, alloc_migration_target,
NULL, (unsigned long)&mtc, MIGRATE_SYNC,
MR_LONGTERM_PIN, NULL)) {
ret = -ENOMEM;
goto err;
}
}
putback_movable_pages(movable_folio_list);
return -EAGAIN;
err:
pofs_unpin(pofs);
putback_movable_pages(movable_folio_list);
return ret;
}
static long
check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
{
LIST_HEAD(movable_folio_list);
collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
if (list_empty(&movable_folio_list))
return 0;
return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
}
/*
* Check whether all folios are *allowed* to be pinned indefinitely (long term).
* Rather confusingly, all folios in the range are required to be pinned via
* FOLL_PIN, before calling this routine.
*
* Return values:
*
* 0: if everything is OK and all folios in the range are allowed to be pinned,
* then this routine leaves all folios pinned and returns zero for success.
*
* -EAGAIN: if any folios in the range are not allowed to be pinned, then this
* routine will migrate those folios away, unpin all the folios in the range. If
* migration of the entire set of folios succeeds, then -EAGAIN is returned. The
* caller should re-pin the entire range with FOLL_PIN and then call this
* routine again.
*
* -ENOMEM, or any other -errno: if an error *other* than -EAGAIN occurs, this
* indicates a migration failure. The caller should give up, and propagate the
* error back up the call stack. The caller does not need to unpin any folios in
* that case, because this routine will do the unpinning.
*/
static long check_and_migrate_movable_folios(unsigned long nr_folios,
struct folio **folios)
{
struct pages_or_folios pofs = {
.folios = folios,
.has_folios = true,
.nr_entries = nr_folios,
};
return check_and_migrate_movable_pages_or_folios(&pofs);
}
/*
* Return values and behavior are the same as those for
* check_and_migrate_movable_folios().
*/
static long check_and_migrate_movable_pages(unsigned long nr_pages,
struct page **pages)
{
struct pages_or_folios pofs = {
.pages = pages,
.has_folios = false,
.nr_entries = nr_pages,
};
return check_and_migrate_movable_pages_or_folios(&pofs);
}
#else
static long check_and_migrate_movable_pages(unsigned long nr_pages,
struct page **pages)
{
return 0;
}
static long check_and_migrate_movable_folios(unsigned long nr_folios,
struct folio **folios)
{
return 0;
}
#endif /* CONFIG_MIGRATION */
/*
* __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
* allows us to process the FOLL_LONGTERM flag.
*/
static long __gup_longterm_locked(struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
struct page **pages,
int *locked,
unsigned int gup_flags)
{
unsigned int flags;
long rc, nr_pinned_pages;
if (!(gup_flags & FOLL_LONGTERM))
return __get_user_pages_locked(mm, start, nr_pages, pages,
locked, gup_flags);
flags = memalloc_pin_save();
do {
nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages,
pages, locked,
gup_flags);
if (nr_pinned_pages <= 0) {
rc = nr_pinned_pages;
break;
}
/* FOLL_LONGTERM implies FOLL_PIN */
rc = check_and_migrate_movable_pages(nr_pinned_pages, pages);
} while (rc == -EAGAIN);
memalloc_pin_restore(flags);
return rc ? rc : nr_pinned_pages;
}
/*
* Check that the given flags are valid for the exported gup/pup interface, and
* update them with the required flags that the caller must have set.
*/
static bool is_valid_gup_args(struct page **pages, int *locked,
unsigned int *gup_flags_p, unsigned int to_set)
{
unsigned int gup_flags = *gup_flags_p;
/*
* These flags not allowed to be specified externally to the gup
* interfaces:
* - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only
* - FOLL_REMOTE is internal only, set in (get|pin)_user_pages_remote()
* - FOLL_UNLOCKABLE is internal only and used if locked is !NULL
*/
if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS))
return false;
gup_flags |= to_set;
if (locked) {
/* At the external interface locked must be set */
if (WARN_ON_ONCE(*locked != 1))
return false;
gup_flags |= FOLL_UNLOCKABLE;
}
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) ==
(FOLL_PIN | FOLL_GET)))
return false;
/* LONGTERM can only be specified when pinning */
if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM)))
return false;
/* Pages input must be given if using GET/PIN */
if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages))
return false;
/* We want to allow the pgmap to be hot-unplugged at all times */
if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) &&
(gup_flags & FOLL_PCI_P2PDMA)))
return false;
*gup_flags_p = gup_flags;
return true;
}
#ifdef CONFIG_MMU
/**
* get_user_pages_remote() - pin user pages in memory
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
* @locked: pointer to lock flag indicating whether lock is held and
* subsequently whether VM_FAULT_RETRY functionality can be
* utilised. Lock must initially be held.
*
* Returns either number of pages pinned (which may be less than the
* number requested), or an error. Details about the return value:
*
* -- If nr_pages is 0, returns 0.
* -- If nr_pages is >0, but no pages were pinned, returns -errno.
* -- If nr_pages is >0, and some pages were pinned, returns the number of
* pages pinned. Again, this may be less than nr_pages.
*
* The caller is responsible for releasing returned @pages, via put_page().
*
* Must be called with mmap_lock held for read or write.
*
* get_user_pages_remote walks a process's page tables and takes a reference
* to each struct page that each user address corresponds to at a given
* instant. That is, it takes the page that would be accessed if a user
* thread accesses the given user virtual address at that instant.
*
* This does not guarantee that the page exists in the user mappings when
* get_user_pages_remote returns, and there may even be a completely different
* page there in some cases (eg. if mmapped pagecache has been invalidated
* and subsequently re-faulted). However it does guarantee that the page
* won't be freed completely. And mostly callers simply care that the page
* contains data that was valid *at some point in time*. Typically, an IO
* or similar operation cannot guarantee anything stronger anyway because
* locks can't be held over the syscall boundary.
*
* If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
* is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
* be called after the page is finished with, and before put_page is called.
*
* get_user_pages_remote is typically used for fewer-copy IO operations,
* to get a handle on the memory by some means other than accesses
* via the user virtual addresses. The pages may be submitted for
* DMA to devices or accessed via their kernel linear mapping (via the
* kmap APIs). Care should be taken to use the correct cache flushing APIs.
*
* See also get_user_pages_fast, for performance critical applications.
*
* get_user_pages_remote should be phased out in favor of
* get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
* should use get_user_pages_remote because it cannot pass
* FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
*/
long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked)
{
int local_locked = 1;
if (!is_valid_gup_args(pages, locked, &gup_flags,
FOLL_TOUCH | FOLL_REMOTE))
return -EINVAL;
return __get_user_pages_locked(mm, start, nr_pages, pages,
locked ? locked : &local_locked,
gup_flags);
}
EXPORT_SYMBOL(get_user_pages_remote);
#else /* CONFIG_MMU */
long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked)
{
return 0;
}
#endif /* !CONFIG_MMU */
/**
* get_user_pages() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
*
* This is the same as get_user_pages_remote(), just with a less-flexible
* calling convention where we assume that the mm being operated on belongs to
* the current task, and doesn't allow passing of a locked parameter. We also
* obviously don't pass FOLL_REMOTE in here.
*/
long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages)
{
int locked = 1;
if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH))
return -EINVAL;
return __get_user_pages_locked(current->mm, start, nr_pages, pages,
&locked, gup_flags);
}
EXPORT_SYMBOL(get_user_pages);
/*
* get_user_pages_unlocked() is suitable to replace the form:
*
* mmap_read_lock(mm);
* get_user_pages(mm, ..., pages, NULL);
* mmap_read_unlock(mm);
*
* with:
*
* get_user_pages_unlocked(mm, ..., pages);
*
* It is functionally equivalent to get_user_pages_fast so
* get_user_pages_fast should be used instead if specific gup_flags
* (e.g. FOLL_FORCE) are not required.
*/
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags)
{
int locked = 0;
if (!is_valid_gup_args(pages, NULL, &gup_flags,
FOLL_TOUCH | FOLL_UNLOCKABLE))
return -EINVAL;
return __get_user_pages_locked(current->mm, start, nr_pages, pages,
&locked, gup_flags);
}
EXPORT_SYMBOL(get_user_pages_unlocked);
/*
* GUP-fast
*
* get_user_pages_fast attempts to pin user pages by walking the page
* tables directly and avoids taking locks. Thus the walker needs to be
* protected from page table pages being freed from under it, and should
* block any THP splits.
*
* One way to achieve this is to have the walker disable interrupts, and
* rely on IPIs from the TLB flushing code blocking before the page table
* pages are freed. This is unsuitable for architectures that do not need
* to broadcast an IPI when invalidating TLBs.
*
* Another way to achieve this is to batch up page table containing pages
* belonging to more than one mm_user, then rcu_sched a callback to free those
* pages. Disabling interrupts will allow the gup_fast() walker to both block
* the rcu_sched callback, and an IPI that we broadcast for splitting THPs
* (which is a relatively rare event). The code below adopts this strategy.
*
* Before activating this code, please be aware that the following assumptions
* are currently made:
*
* *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
* free pages containing page tables or TLB flushing requires IPI broadcast.
*
* *) ptes can be read atomically by the architecture.
*
* *) valid user addesses are below TASK_MAX_SIZE
*
* The last two assumptions can be relaxed by the addition of helper functions.
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
#ifdef CONFIG_HAVE_GUP_FAST
/*
* Used in the GUP-fast path to determine whether GUP is permitted to work on
* a specific folio.
*
* This call assumes the caller has pinned the folio, that the lowest page table
* level still points to this folio, and that interrupts have been disabled.
*
* GUP-fast must reject all secretmem folios.
*
* Writing to pinned file-backed dirty tracked folios is inherently problematic
* (see comment describing the writable_file_mapping_allowed() function). We
* therefore try to avoid the most egregious case of a long-term mapping doing
* so.
*
* This function cannot be as thorough as that one as the VMA is not available
* in the fast path, so instead we whitelist known good cases and if in doubt,
* fall back to the slow path.
*/
static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags)
{
bool reject_file_backed = false;
struct address_space *mapping;
bool check_secretmem = false;
unsigned long mapping_flags;
/*
* If we aren't pinning then no problematic write can occur. A long term
* pin is the most egregious case so this is the one we disallow.
*/
if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) ==
(FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE))
reject_file_backed = true;
/* We hold a folio reference, so we can safely access folio fields. */
/* secretmem folios are always order-0 folios. */
if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio))
check_secretmem = true;
if (!reject_file_backed && !check_secretmem)
return true;
if (WARN_ON_ONCE(folio_test_slab(folio)))
return false;
/* hugetlb neither requires dirty-tracking nor can be secretmem. */
if (folio_test_hugetlb(folio))
return true;
/*
* GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods
* cannot proceed, which means no actions performed under RCU can
* proceed either.
*
* inodes and thus their mappings are freed under RCU, which means the
* mapping cannot be freed beneath us and thus we can safely dereference
* it.
*/
lockdep_assert_irqs_disabled();
/*
* However, there may be operations which _alter_ the mapping, so ensure
* we read it once and only once.
*/
mapping = READ_ONCE(folio->mapping);
/*
* The mapping may have been truncated, in any case we cannot determine
* if this mapping is safe - fall back to slow path to determine how to
* proceed.
*/
if (!mapping)
return false;
/* Anonymous folios pose no problem. */
mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS;
if (mapping_flags)
return mapping_flags & PAGE_MAPPING_ANON;
/*
* At this point, we know the mapping is non-null and points to an
* address_space object.
*/
if (check_secretmem && secretmem_mapping(mapping))
return false;
/* The only remaining allowed file system is shmem. */
return !reject_file_backed || shmem_mapping(mapping);
}
static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start,
unsigned int flags, struct page **pages)
{
while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio);
gup_put_folio(folio, 1, flags);
}
}
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
/*
* GUP-fast relies on pte change detection to avoid concurrent pgtable
* operations.
*
* To pin the page, GUP-fast needs to do below in order:
* (1) pin the page (by prefetching pte), then (2) check pte not changed.
*
* For the rest of pgtable operations where pgtable updates can be racy
* with GUP-fast, we need to do (1) clear pte, then (2) check whether page
* is pinned.
*
* Above will work for all pte-level operations, including THP split.
*
* For THP collapse, it's a bit more complicated because GUP-fast may be
* walking a pgtable page that is being freed (pte is still valid but pmd
* can be cleared already). To avoid race in such condition, we need to
* also check pmd here to make sure pmd doesn't change (corresponds to
* pmdp_collapse_flush() in the THP collapse code path).
*/
static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr, ret = 0;
pte_t *ptep, *ptem;
ptem = ptep = pte_offset_map(&pmd, addr);
if (!ptep)
return 0;
do {
pte_t pte = ptep_get_lockless(ptep);
struct page *page;
struct folio *folio;
/*
* Always fallback to ordinary GUP on PROT_NONE-mapped pages:
* pte_access_permitted() better should reject these pages
* either way: otherwise, GUP-fast might succeed in
* cases where ordinary GUP would fail due to VMA access
* permissions.
*/
if (pte_protnone(pte))
goto pte_unmap;
if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto pte_unmap;
if (pte_devmap(pte)) {
if (unlikely(flags & FOLL_LONGTERM))
goto pte_unmap;
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
goto pte_unmap;
}
} else if (pte_special(pte))
goto pte_unmap;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
folio = try_grab_folio_fast(page, 1, flags);
if (!folio)
goto pte_unmap;
if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
if (!gup_fast_folio_allowed(folio, flags)) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
/*
* We need to make the page accessible if and only if we are
* going to access its content (the FOLL_PIN case). Please
* see Documentation/core-api/pin_user_pages.rst for
* details.
*/
if (flags & FOLL_PIN) {
ret = arch_make_folio_accessible(folio);
if (ret) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
}
folio_set_referenced(folio);
pages[*nr] = page;
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
ret = 1;
pte_unmap:
if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem);
return ret;
}
#else
/*
* If we can't determine whether or not a pte is special, then fail immediately
* for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
* to be special.
*
* For a futex to be placed on a THP tail page, get_futex_key requires a
* get_user_pages_fast_only implementation that can pin pages. Thus it's still
* useful to have gup_fast_pmd_leaf even if we can't operate on ptes.
*/
static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages, int *nr)
{
int nr_start = *nr;
struct dev_pagemap *pgmap = NULL;
do {
struct folio *folio;
struct page *page = pfn_to_page(pfn);
pgmap = get_dev_pagemap(pfn, pgmap);
if (unlikely(!pgmap)) {
gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
break;
}
folio = try_grab_folio_fast(page, 1, flags);
if (!folio) {
gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
break;
}
folio_set_referenced(folio);
pages[*nr] = page;
(*nr)++;
pfn++;
} while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap);
return addr == end;
}
static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
#else
static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
BUILD_BUG();
return 0;
}
static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
BUILD_BUG();
return 0;
}
#endif
static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
struct page *page;
struct folio *folio;
int refs;
if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pmd_special(orig))
return 0;
if (pmd_devmap(orig)) {
if (unlikely(flags & FOLL_LONGTERM))
return 0;
return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags,
pages, nr);
}
page = pmd_page(orig);
refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
folio = try_grab_folio_fast(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!gup_fast_folio_allowed(folio, flags)) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
struct page *page;
struct folio *folio;
int refs;
if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pud_special(orig))
return 0;
if (pud_devmap(orig)) {
if (unlikely(flags & FOLL_LONGTERM))
return 0;
return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags,
pages, nr);
}
page = pud_page(orig);
refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
folio = try_grab_folio_fast(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!gup_fast_folio_allowed(folio, flags)) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
int refs;
struct page *page;
struct folio *folio;
if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
page = pgd_page(orig);
refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr);
folio = try_grab_folio_fast(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!gup_fast_folio_allowed(folio, flags)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
unsigned long next;
pmd_t *pmdp;
pmdp = pmd_offset_lockless(pudp, pud, addr);
do {
pmd_t pmd = pmdp_get_lockless(pmdp);
next = pmd_addr_end(addr, end);
if (!pmd_present(pmd))
return 0;
if (unlikely(pmd_leaf(pmd))) {
/* See gup_fast_pte_range() */
if (pmd_protnone(pmd))
return 0;
if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
} else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
return 1;
}
static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
unsigned long next;
pud_t *pudp;
pudp = pud_offset_lockless(p4dp, p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
if (unlikely(!pud_present(pud)))
return 0;
if (unlikely(pud_leaf(pud))) {
if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags,
pages, nr))
return 0;
} else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags,
pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages,
int *nr)
{
unsigned long next;
p4d_t *p4dp;
p4dp = p4d_offset_lockless(pgdp, pgd, addr);
do {
p4d_t p4d = READ_ONCE(*p4dp);
next = p4d_addr_end(addr, end);
if (!p4d_present(p4d))
return 0;
BUILD_BUG_ON(p4d_leaf(p4d));
if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags,
pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
return 1;
}
static void gup_fast_pgd_range(unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pgd_t *pgdp;
pgdp = pgd_offset(current->mm, addr);
do {
pgd_t pgd = READ_ONCE(*pgdp);
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
return;
if (unlikely(pgd_leaf(pgd))) {
if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags,
pages, nr))
return;
} else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags,
pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
#else
static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
}
#endif /* CONFIG_HAVE_GUP_FAST */
#ifndef gup_fast_permitted
/*
* Check if it's allowed to use get_user_pages_fast_only() for the range, or
* we need to fall back to the slow version:
*/
static bool gup_fast_permitted(unsigned long start, unsigned long end)
{
return true;
}
#endif
static unsigned long gup_fast(unsigned long start, unsigned long end,
unsigned int gup_flags, struct page **pages)
{
unsigned long flags;
int nr_pinned = 0;
unsigned seq;
if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) ||
!gup_fast_permitted(start, end))
return 0;
if (gup_flags & FOLL_PIN) { if (!raw_seqcount_try_begin(¤t->mm->write_protect_seq, seq))
return 0;
}
/*
* Disable interrupts. The nested form is used, in order to allow full,
* general purpose use of this routine.
*
* With interrupts disabled, we block page table pages from being freed
* from under us. See struct mmu_table_batch comments in
* include/asm-generic/tlb.h for more details.
*
* We do not adopt an rcu_read_lock() here as we also want to block IPIs
* that come from THPs splitting.
*/
local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags);
/*
* When pinning pages for DMA there could be a concurrent write protect
* from fork() via copy_page_range(), in this case always fail GUP-fast.
*/
if (gup_flags & FOLL_PIN) {
if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) {
gup_fast_unpin_user_pages(pages, nr_pinned);
return 0;
} else {
sanity_check_pinned_pages(pages, nr_pinned);
}
}
return nr_pinned;
}
static int gup_fast_fallback(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages)
{
unsigned long len, end;
unsigned long nr_pinned;
int locked = 0;
int ret;
if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
FOLL_FORCE | FOLL_PIN | FOLL_GET |
FOLL_FAST_ONLY | FOLL_NOFAULT |
FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT)))
return -EINVAL;
if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock);
start = untagged_addr(start) & PAGE_MASK;
len = nr_pages << PAGE_SHIFT;
if (check_add_overflow(start, len, &end))
return -EOVERFLOW;
if (end > TASK_SIZE_MAX)
return -EFAULT;
nr_pinned = gup_fast(start, end, gup_flags, pages);
if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
return nr_pinned;
/* Slow path: try to get the remaining pages with get_user_pages */
start += nr_pinned << PAGE_SHIFT;
pages += nr_pinned;
ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned,
pages, &locked,
gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE);
if (ret < 0) {
/*
* The caller has to unpin the pages we already pinned so
* returning -errno is not an option
*/
if (nr_pinned)
return nr_pinned;
return ret;
}
return ret + nr_pinned;
}
/**
* get_user_pages_fast_only() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
* the regular GUP.
*
* If the architecture does not support this function, simply return with no
* pages pinned.
*
* Careful, careful! COW breaking can go either way, so a non-write
* access can get ambiguous page results. If you call this function without
* 'write' set, you'd better be sure that you're ok with that ambiguity.
*/
int get_user_pages_fast_only(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
/*
* Internally (within mm/gup.c), gup fast variants must set FOLL_GET,
* because gup fast is always a "pin with a +1 page refcount" request.
*
* FOLL_FAST_ONLY is required in order to match the API description of
* this routine: no fall back to regular ("slow") GUP.
*/
if (!is_valid_gup_args(pages, NULL, &gup_flags,
FOLL_GET | FOLL_FAST_ONLY))
return -EINVAL;
return gup_fast_fallback(start, nr_pages, gup_flags, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
/**
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Attempt to pin user pages in memory without taking mm->mmap_lock.
* If not successful, it will fall back to taking the lock and
* calling get_user_pages().
*
* Returns number of pages pinned. This may be fewer than the number requested.
* If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
* -errno.
*/
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
/*
* The caller may or may not have explicitly set FOLL_GET; either way is
* OK. However, internally (within mm/gup.c), gup fast variants must set
* FOLL_GET, because gup fast is always a "pin with a +1 page refcount"
* request.
*/
if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET))
return -EINVAL;
return gup_fast_fallback(start, nr_pages, gup_flags, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
/**
* pin_user_pages_fast() - pin user pages in memory without taking locks
*
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See
* get_user_pages_fast() for documentation on the function arguments, because
* the arguments here are identical.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for further details.
*
* Note that if a zero_page is amongst the returned pages, it will not have
* pins in it and unpin_user_page() will not remove pins from it.
*/
int pin_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN))
return -EINVAL;
return gup_fast_fallback(start, nr_pages, gup_flags, pages);
}
EXPORT_SYMBOL_GPL(pin_user_pages_fast);
/**
* pin_user_pages_remote() - pin pages of a remote process
*
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
* @locked: pointer to lock flag indicating whether lock is held and
* subsequently whether VM_FAULT_RETRY functionality can be
* utilised. Lock must initially be held.
*
* Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
* get_user_pages_remote() for documentation on the function arguments, because
* the arguments here are identical.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for details.
*
* Note that if a zero_page is amongst the returned pages, it will not have
* pins in it and unpin_user_page*() will not remove pins from it.
*/
long pin_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
int *locked)
{
int local_locked = 1;
if (!is_valid_gup_args(pages, locked, &gup_flags,
FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE))
return 0;
return __gup_longterm_locked(mm, start, nr_pages, pages,
locked ? locked : &local_locked,
gup_flags);
}
EXPORT_SYMBOL(pin_user_pages_remote);
/**
* pin_user_pages() - pin user pages in memory for use by other devices
*
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
* FOLL_PIN is set.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for details.
*
* Note that if a zero_page is amongst the returned pages, it will not have
* pins in it and unpin_user_page*() will not remove pins from it.
*/
long pin_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages)
{
int locked = 1;
if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN))
return 0;
return __gup_longterm_locked(current->mm, start, nr_pages,
pages, &locked, gup_flags);
}
EXPORT_SYMBOL(pin_user_pages);
/*
* pin_user_pages_unlocked() is the FOLL_PIN variant of
* get_user_pages_unlocked(). Behavior is the same, except that this one sets
* FOLL_PIN and rejects FOLL_GET.
*
* Note that if a zero_page is amongst the returned pages, it will not have
* pins in it and unpin_user_page*() will not remove pins from it.
*/
long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags)
{
int locked = 0;
if (!is_valid_gup_args(pages, NULL, &gup_flags,
FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE))
return 0;
return __gup_longterm_locked(current->mm, start, nr_pages, pages,
&locked, gup_flags);
}
EXPORT_SYMBOL(pin_user_pages_unlocked);
/**
* memfd_pin_folios() - pin folios associated with a memfd
* @memfd: the memfd whose folios are to be pinned
* @start: the first memfd offset
* @end: the last memfd offset (inclusive)
* @folios: array that receives pointers to the folios pinned
* @max_folios: maximum number of entries in @folios
* @offset: the offset into the first folio
*
* Attempt to pin folios associated with a memfd in the contiguous range
* [start, end]. Given that a memfd is either backed by shmem or hugetlb,
* the folios can either be found in the page cache or need to be allocated
* if necessary. Once the folios are located, they are all pinned via
* FOLL_PIN and @offset is populatedwith the offset into the first folio.
* And, eventually, these pinned folios must be released either using
* unpin_folios() or unpin_folio().
*
* It must be noted that the folios may be pinned for an indefinite amount
* of time. And, in most cases, the duration of time they may stay pinned
* would be controlled by the userspace. This behavior is effectively the
* same as using FOLL_LONGTERM with other GUP APIs.
*
* Returns number of folios pinned, which could be less than @max_folios
* as it depends on the folio sizes that cover the range [start, end].
* If no folios were pinned, it returns -errno.
*/
long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
struct folio **folios, unsigned int max_folios,
pgoff_t *offset)
{
unsigned int flags, nr_folios, nr_found;
unsigned int i, pgshift = PAGE_SHIFT;
pgoff_t start_idx, end_idx, next_idx;
struct folio *folio = NULL;
struct folio_batch fbatch;
struct hstate *h;
long ret = -EINVAL;
if (start < 0 || start > end || !max_folios)
return -EINVAL;
if (!memfd)
return -EINVAL;
if (!shmem_file(memfd) && !is_file_hugepages(memfd))
return -EINVAL;
if (end >= i_size_read(file_inode(memfd)))
return -EINVAL;
if (is_file_hugepages(memfd)) {
h = hstate_file(memfd);
pgshift = huge_page_shift(h);
}
flags = memalloc_pin_save();
do {
nr_folios = 0;
start_idx = start >> pgshift;
end_idx = end >> pgshift;
if (is_file_hugepages(memfd)) {
start_idx <<= huge_page_order(h);
end_idx <<= huge_page_order(h);
}
folio_batch_init(&fbatch);
while (start_idx <= end_idx && nr_folios < max_folios) {
/*
* In most cases, we should be able to find the folios
* in the page cache. If we cannot find them for some
* reason, we try to allocate them and add them to the
* page cache.
*/
nr_found = filemap_get_folios_contig(memfd->f_mapping,
&start_idx,
end_idx,
&fbatch);
if (folio) {
folio_put(folio);
folio = NULL;
}
next_idx = 0;
for (i = 0; i < nr_found; i++) {
/*
* As there can be multiple entries for a
* given folio in the batch returned by
* filemap_get_folios_contig(), the below
* check is to ensure that we pin and return a
* unique set of folios between start and end.
*/
if (next_idx &&
next_idx != folio_index(fbatch.folios[i]))
continue;
folio = page_folio(&fbatch.folios[i]->page);
if (try_grab_folio(folio, 1, FOLL_PIN)) {
folio_batch_release(&fbatch);
ret = -EINVAL;
goto err;
}
if (nr_folios == 0)
*offset = offset_in_folio(folio, start);
folios[nr_folios] = folio;
next_idx = folio_next_index(folio);
if (++nr_folios == max_folios)
break;
}
folio = NULL;
folio_batch_release(&fbatch);
if (!nr_found) {
folio = memfd_alloc_folio(memfd, start_idx);
if (IS_ERR(folio)) {
ret = PTR_ERR(folio);
if (ret != -EEXIST)
goto err;
folio = NULL;
}
}
}
ret = check_and_migrate_movable_folios(nr_folios, folios);
} while (ret == -EAGAIN);
memalloc_pin_restore(flags);
return ret ? ret : nr_folios;
err:
memalloc_pin_restore(flags);
unpin_folios(folios, nr_folios);
return ret;
}
EXPORT_SYMBOL_GPL(memfd_pin_folios);
/**
* folio_add_pins() - add pins to an already-pinned folio
* @folio: the folio to add more pins to
* @pins: number of pins to add
*
* Try to add more pins to an already-pinned folio. The semantics
* of the pin (e.g., FOLL_WRITE) follow any existing pin and cannot
* be changed.
*
* This function is helpful when having obtained a pin on a large folio
* using memfd_pin_folios(), but wanting to logically unpin parts
* (e.g., individual pages) of the folio later, for example, using
* unpin_user_page_range_dirty_lock().
*
* This is not the right interface to initially pin a folio.
*/
int folio_add_pins(struct folio *folio, unsigned int pins)
{
VM_WARN_ON_ONCE(!folio_maybe_dma_pinned(folio));
return try_grab_folio(folio, pins, FOLL_PIN);
}
EXPORT_SYMBOL_GPL(folio_add_pins);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1993 Linus Torvalds
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
* Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
* Numa awareness, Christoph Lameter, SGI, June 2005
* Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019
*/
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/set_memory.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
#include <linux/io.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/memcontrol.h>
#include <linux/llist.h>
#include <linux/uio.h>
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
#include <linux/overflow.h>
#include <linux/pgtable.h>
#include <linux/hugetlb.h>
#include <linux/sched/mm.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
#include <linux/page_owner.h>
#define CREATE_TRACE_POINTS
#include <trace/events/vmalloc.h>
#include "internal.h"
#include "pgalloc-track.h"
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1;
static int __init set_nohugeiomap(char *str)
{
ioremap_max_page_shift = PAGE_SHIFT;
return 0;
}
early_param("nohugeiomap", set_nohugeiomap);
#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
static bool __ro_after_init vmap_allow_huge = true;
static int __init set_nohugevmalloc(char *str)
{
vmap_allow_huge = false;
return 0;
}
early_param("nohugevmalloc", set_nohugevmalloc);
#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
static const bool vmap_allow_huge = false;
#endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
bool is_vmalloc_addr(const void *x)
{
unsigned long addr = (unsigned long)kasan_reset_tag(x);
return addr >= VMALLOC_START && addr < VMALLOC_END;
}
EXPORT_SYMBOL(is_vmalloc_addr);
struct vfree_deferred {
struct llist_head list;
struct work_struct wq;
};
static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);
/*** Page table manipulation functions ***/
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pte_t *pte;
u64 pfn;
struct page *page;
unsigned long size = PAGE_SIZE;
pfn = phys_addr >> PAGE_SHIFT;
pte = pte_alloc_kernel_track(pmd, addr, mask);
if (!pte)
return -ENOMEM;
do {
if (unlikely(!pte_none(ptep_get(pte)))) {
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
dump_page(page, "remapping already mapped page");
}
BUG();
}
#ifdef CONFIG_HUGETLB_PAGE
size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
if (size != PAGE_SIZE) {
pte_t entry = pfn_pte(pfn, prot);
entry = arch_make_huge_pte(entry, ilog2(size), 0);
set_huge_pte_at(&init_mm, addr, pte, entry, size);
pfn += PFN_DOWN(size);
continue;
}
#endif
set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
} while (pte += PFN_DOWN(size), addr += size, addr != end);
*mask |= PGTBL_PTE_MODIFIED;
return 0;
}
static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift)
{
if (max_page_shift < PMD_SHIFT)
return 0;
if (!arch_vmap_pmd_supported(prot))
return 0;
if ((end - addr) != PMD_SIZE)
return 0;
if (!IS_ALIGNED(addr, PMD_SIZE))
return 0;
if (!IS_ALIGNED(phys_addr, PMD_SIZE))
return 0;
if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
return 0;
return pmd_set_huge(pmd, phys_addr, prot);
}
static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
max_page_shift)) {
*mask |= PGTBL_PMD_MODIFIED;
continue;
}
if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask))
return -ENOMEM;
} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift)
{
if (max_page_shift < PUD_SHIFT)
return 0;
if (!arch_vmap_pud_supported(prot))
return 0;
if ((end - addr) != PUD_SIZE)
return 0;
if (!IS_ALIGNED(addr, PUD_SIZE))
return 0;
if (!IS_ALIGNED(phys_addr, PUD_SIZE))
return 0;
if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
return 0;
return pud_set_huge(pud, phys_addr, prot);
}
static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc_track(&init_mm, p4d, addr, mask);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
max_page_shift)) {
*mask |= PGTBL_PUD_MODIFIED;
continue;
}
if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
max_page_shift, mask))
return -ENOMEM;
} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift)
{
if (max_page_shift < P4D_SHIFT)
return 0;
if (!arch_vmap_p4d_supported(prot))
return 0;
if ((end - addr) != P4D_SIZE)
return 0;
if (!IS_ALIGNED(addr, P4D_SIZE))
return 0;
if (!IS_ALIGNED(phys_addr, P4D_SIZE))
return 0;
if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
return 0;
return p4d_set_huge(p4d, phys_addr, prot);
}
static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
max_page_shift)) {
*mask |= PGTBL_P4D_MODIFIED;
continue;
}
if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
max_page_shift, mask))
return -ENOMEM;
} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_range_noflush(unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift)
{
pgd_t *pgd;
unsigned long start;
unsigned long next;
int err;
pgtbl_mod_mask mask = 0;
might_sleep();
BUG_ON(addr >= end);
start = addr;
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
max_page_shift, &mask);
if (err)
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
return err;
}
int vmap_page_range(unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot)
{
int err;
err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
ioremap_max_page_shift);
flush_cache_vmap(addr, end);
if (!err)
err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
ioremap_max_page_shift);
return err;
}
int ioremap_page_range(unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot)
{
struct vm_struct *area;
area = find_vm_area((void *)addr);
if (!area || !(area->flags & VM_IOREMAP)) {
WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr);
return -EINVAL;
}
if (addr != (unsigned long)area->addr ||
(void *)end != area->addr + get_vm_area_size(area)) {
WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n",
addr, end, (long)area->addr,
(long)area->addr + get_vm_area_size(area));
return -ERANGE;
}
return vmap_page_range(addr, end, phys_addr, prot);
}
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
{
pte_t *pte;
pte = pte_offset_kernel(pmd, addr);
do {
pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end);
*mask |= PGTBL_PTE_MODIFIED;
}
static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
int cleared;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
cleared = pmd_clear_huge(pmd);
if (cleared || pmd_bad(*pmd))
*mask |= PGTBL_PMD_MODIFIED;
if (cleared)
continue;
if (pmd_none_or_clear_bad(pmd))
continue;
vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end);
}
static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
int cleared;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
cleared = pud_clear_huge(pud);
if (cleared || pud_bad(*pud))
*mask |= PGTBL_PUD_MODIFIED;
if (cleared)
continue;
if (pud_none_or_clear_bad(pud))
continue;
vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end);
}
static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
p4d_clear_huge(p4d);
if (p4d_bad(*p4d))
*mask |= PGTBL_P4D_MODIFIED;
if (p4d_none_or_clear_bad(p4d))
continue;
vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end);
}
/*
* vunmap_range_noflush is similar to vunmap_range, but does not
* flush caches or TLBs.
*
* The caller is responsible for calling flush_cache_vmap() before calling
* this function, and flush_tlb_kernel_range after it has returned
* successfully (and before the addresses are expected to cause a page fault
* or be re-mapped for something else, if TLB flushes are being delayed or
* coalesced).
*
* This is an internal function only. Do not use outside mm/.
*/
void __vunmap_range_noflush(unsigned long start, unsigned long end)
{
unsigned long next;
pgd_t *pgd;
unsigned long addr = start;
pgtbl_mod_mask mask = 0;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED;
if (pgd_none_or_clear_bad(pgd))
continue;
vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
}
void vunmap_range_noflush(unsigned long start, unsigned long end)
{
kmsan_vunmap_range_noflush(start, end);
__vunmap_range_noflush(start, end);
}
/**
* vunmap_range - unmap kernel virtual addresses
* @addr: start of the VM area to unmap
* @end: end of the VM area to unmap (non-inclusive)
*
* Clears any present PTEs in the virtual address range, flushes TLBs and
* caches. Any subsequent access to the address before it has been re-mapped
* is a kernel bug.
*/
void vunmap_range(unsigned long addr, unsigned long end)
{
flush_cache_vunmap(addr, end);
vunmap_range_noflush(addr, end);
flush_tlb_kernel_range(addr, end);
}
static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
pte_t *pte;
/*
* nr is a running index into the array which helps higher level
* callers keep track of where we're up to.
*/
pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte)
return -ENOMEM;
do {
struct page *page = pages[*nr];
if (WARN_ON(!pte_none(ptep_get(pte))))
return -EBUSY;
if (WARN_ON(!page))
return -ENOMEM;
if (WARN_ON(!pfn_valid(page_to_pfn(page))))
return -EINVAL;
set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
(*nr)++;
} while (pte++, addr += PAGE_SIZE, addr != end);
*mask |= PGTBL_PTE_MODIFIED;
return 0;
}
static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
}
static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages)
{
unsigned long start = addr;
pgd_t *pgd;
unsigned long next;
int err = 0;
int nr = 0;
pgtbl_mod_mask mask = 0;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED;
err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err)
break;
} while (pgd++, addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
return err;
}
/*
* vmap_pages_range_noflush is similar to vmap_pages_range, but does not
* flush caches.
*
* The caller is responsible for calling flush_cache_vmap() after this
* function returns successfully and before the addresses are accessed.
*
* This is an internal function only. Do not use outside mm/.
*/
int __vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
WARN_ON(page_shift < PAGE_SHIFT); if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
page_shift == PAGE_SHIFT)
return vmap_small_pages_range_noflush(addr, end, prot, pages); for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
int err;
err = vmap_range_noflush(addr, addr + (1UL << page_shift),
page_to_phys(pages[i]), prot,
page_shift);
if (err)
return err;
addr += 1UL << page_shift;
}
return 0;
}
int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
page_shift);
if (ret)
return ret;
return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
}
/**
* vmap_pages_range - map pages to a kernel virtual address
* @addr: start of the VM area to map
* @end: end of the VM area to map (non-inclusive)
* @prot: page protection flags to use
* @pages: pages to map (always PAGE_SIZE pages)
* @page_shift: maximum shift that the pages may be mapped with, @pages must
* be aligned and contiguous up to at least this shift.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int vmap_pages_range(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
int err;
err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
flush_cache_vmap(addr, end);
return err;
}
static int check_sparse_vm_area(struct vm_struct *area, unsigned long start,
unsigned long end)
{
might_sleep();
if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS))
return -EINVAL;
if (WARN_ON_ONCE(area->flags & VM_NO_GUARD))
return -EINVAL;
if (WARN_ON_ONCE(!(area->flags & VM_SPARSE)))
return -EINVAL;
if ((end - start) >> PAGE_SHIFT > totalram_pages())
return -E2BIG;
if (start < (unsigned long)area->addr ||
(void *)end > area->addr + get_vm_area_size(area))
return -ERANGE;
return 0;
}
/**
* vm_area_map_pages - map pages inside given sparse vm_area
* @area: vm_area
* @start: start address inside vm_area
* @end: end address inside vm_area
* @pages: pages to map (always PAGE_SIZE pages)
*/
int vm_area_map_pages(struct vm_struct *area, unsigned long start,
unsigned long end, struct page **pages)
{
int err;
err = check_sparse_vm_area(area, start, end);
if (err)
return err;
return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT);
}
/**
* vm_area_unmap_pages - unmap pages inside given sparse vm_area
* @area: vm_area
* @start: start address inside vm_area
* @end: end address inside vm_area
*/
void vm_area_unmap_pages(struct vm_struct *area, unsigned long start,
unsigned long end)
{
if (check_sparse_vm_area(area, start, end))
return;
vunmap_range(start, end);
}
int is_vmalloc_or_module_addr(const void *x)
{
/*
* ARM, x86-64 and sparc64 put modules in a special place,
* and fall back on vmalloc() if that fails. Others
* just put it in the vmalloc space.
*/
#if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR)
unsigned long addr = (unsigned long)kasan_reset_tag(x);
if (addr >= MODULES_VADDR && addr < MODULES_END)
return 1;
#endif
return is_vmalloc_addr(x);
}
EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr);
/*
* Walk a vmap address to the struct page it maps. Huge vmap mappings will
* return the tail page that corresponds to the base page address, which
* matches small vmap mappings.
*/
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
/*
* XXX we might need to change this if we add VIRTUAL_BUG_ON for
* architectures that do not vmalloc module space
*/
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd))
return NULL;
if (WARN_ON_ONCE(pgd_leaf(*pgd)))
return NULL; /* XXX: no allowance for huge pgd */
if (WARN_ON_ONCE(pgd_bad(*pgd)))
return NULL;
p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d))
return NULL;
if (p4d_leaf(*p4d))
return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
if (WARN_ON_ONCE(p4d_bad(*p4d)))
return NULL;
pud = pud_offset(p4d, addr); if (pud_none(*pud))
return NULL;
if (pud_leaf(*pud))
return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud)))
return NULL;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return NULL;
if (pmd_leaf(*pmd))
return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd)))
return NULL;
ptep = pte_offset_kernel(pmd, addr);
pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte);
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
/*
* Map a vmalloc()-space virtual address to the physical page frame number.
*/
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
{
return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);
/*** Global kva allocator ***/
#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
static DEFINE_SPINLOCK(free_vmap_area_lock);
static bool vmap_initialized __read_mostly;
/*
* This kmem_cache is used for vmap_area objects. Instead of
* allocating from slab we reuse an object from this cache to
* make things faster. Especially in "no edge" splitting of
* free block.
*/
static struct kmem_cache *vmap_area_cachep;
/*
* This linked list is used in pair with free_vmap_area_root.
* It gives O(1) access to prev/next to perform fast coalescing.
*/
static LIST_HEAD(free_vmap_area_list);
/*
* This augment red-black tree represents the free vmap space.
* All vmap_area objects in this tree are sorted by va->va_start
* address. It is used for allocation and merging when a vmap
* object is released.
*
* Each vmap_area node contains a maximum available free block
* of its sub-tree, right or left. Therefore it is possible to
* find a lowest match of free area.
*/
static struct rb_root free_vmap_area_root = RB_ROOT;
/*
* Preload a CPU with one object for "no edge" split case. The
* aim is to get rid of allocations from the atomic context, thus
* to use more permissive allocation masks.
*/
static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);
/*
* This structure defines a single, solid model where a list and
* rb-tree are part of one entity protected by the lock. Nodes are
* sorted in ascending order, thus for O(1) access to left/right
* neighbors a list is used as well as for sequential traversal.
*/
struct rb_list {
struct rb_root root;
struct list_head head;
spinlock_t lock;
};
/*
* A fast size storage contains VAs up to 1M size. A pool consists
* of linked between each other ready to go VAs of certain sizes.
* An index in the pool-array corresponds to number of pages + 1.
*/
#define MAX_VA_SIZE_PAGES 256
struct vmap_pool {
struct list_head head;
unsigned long len;
};
/*
* An effective vmap-node logic. Users make use of nodes instead
* of a global heap. It allows to balance an access and mitigate
* contention.
*/
static struct vmap_node {
/* Simple size segregated storage. */
struct vmap_pool pool[MAX_VA_SIZE_PAGES];
spinlock_t pool_lock;
bool skip_populate;
/* Bookkeeping data of this node. */
struct rb_list busy;
struct rb_list lazy;
/*
* Ready-to-free areas.
*/
struct list_head purge_list;
struct work_struct purge_work;
unsigned long nr_purged;
} single;
/*
* Initial setup consists of one single node, i.e. a balancing
* is fully disabled. Later on, after vmap is initialized these
* parameters are updated based on a system capacity.
*/
static struct vmap_node *vmap_nodes = &single;
static __read_mostly unsigned int nr_vmap_nodes = 1;
static __read_mostly unsigned int vmap_zone_size = 1;
static inline unsigned int
addr_to_node_id(unsigned long addr)
{
return (addr / vmap_zone_size) % nr_vmap_nodes;
}
static inline struct vmap_node *
addr_to_node(unsigned long addr)
{
return &vmap_nodes[addr_to_node_id(addr)];
}
static inline struct vmap_node *
id_to_node(unsigned int id)
{
return &vmap_nodes[id % nr_vmap_nodes];
}
/*
* We use the value 0 to represent "no node", that is why
* an encoded value will be the node-id incremented by 1.
* It is always greater then 0. A valid node_id which can
* be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id
* is not valid 0 is returned.
*/
static unsigned int
encode_vn_id(unsigned int node_id)
{
/* Can store U8_MAX [0:254] nodes. */
if (node_id < nr_vmap_nodes)
return (node_id + 1) << BITS_PER_BYTE;
/* Warn and no node encoded. */
WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id);
return 0;
}
/*
* Returns an encoded node-id, the valid range is within
* [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is
* returned if extracted data is wrong.
*/
static unsigned int
decode_vn_id(unsigned int val)
{
unsigned int node_id = (val >> BITS_PER_BYTE) - 1;
/* Can store U8_MAX [0:254] nodes. */
if (node_id < nr_vmap_nodes)
return node_id;
/* If it was _not_ zero, warn. */
WARN_ONCE(node_id != UINT_MAX,
"Decode wrong node id (%d)\n", node_id);
return nr_vmap_nodes;
}
static bool
is_vn_id_valid(unsigned int node_id)
{
if (node_id < nr_vmap_nodes)
return true;
return false;
}
static __always_inline unsigned long
va_size(struct vmap_area *va)
{
return (va->va_end - va->va_start);
}
static __always_inline unsigned long
get_subtree_max_size(struct rb_node *node)
{
struct vmap_area *va;
va = rb_entry_safe(node, struct vmap_area, rb_node);
return va ? va->subtree_max_size : 0;
}
RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb,
struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size)
static void reclaim_and_purge_vmap_areas(void);
static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
static void drain_vmap_area_work(struct work_struct *work);
static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work);
static atomic_long_t nr_vmalloc_pages;
unsigned long vmalloc_nr_pages(void)
{
return atomic_long_read(&nr_vmalloc_pages);
}
static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
{
struct rb_node *n = root->rb_node;
addr = (unsigned long)kasan_reset_tag((void *)addr);
while (n) {
struct vmap_area *va;
va = rb_entry(n, struct vmap_area, rb_node);
if (addr < va->va_start)
n = n->rb_left;
else if (addr >= va->va_end)
n = n->rb_right;
else
return va;
}
return NULL;
}
/* Look up the first VA which satisfies addr < va_end, NULL if none. */
static struct vmap_area *
__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
{
struct vmap_area *va = NULL;
struct rb_node *n = root->rb_node;
addr = (unsigned long)kasan_reset_tag((void *)addr);
while (n) {
struct vmap_area *tmp;
tmp = rb_entry(n, struct vmap_area, rb_node);
if (tmp->va_end > addr) {
va = tmp;
if (tmp->va_start <= addr)
break;
n = n->rb_left;
} else
n = n->rb_right;
}
return va;
}
/*
* Returns a node where a first VA, that satisfies addr < va_end, resides.
* If success, a node is locked. A user is responsible to unlock it when a
* VA is no longer needed to be accessed.
*
* Returns NULL if nothing found.
*/
static struct vmap_node *
find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
{
unsigned long va_start_lowest;
struct vmap_node *vn;
int i;
repeat:
for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
*va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
if (*va)
if (!va_start_lowest || (*va)->va_start < va_start_lowest)
va_start_lowest = (*va)->va_start;
spin_unlock(&vn->busy.lock);
}
/*
* Check if found VA exists, it might have gone away. In this case we
* repeat the search because a VA has been removed concurrently and we
* need to proceed to the next one, which is a rare case.
*/
if (va_start_lowest) {
vn = addr_to_node(va_start_lowest);
spin_lock(&vn->busy.lock);
*va = __find_vmap_area(va_start_lowest, &vn->busy.root);
if (*va)
return vn;
spin_unlock(&vn->busy.lock);
goto repeat;
}
return NULL;
}
/*
* This function returns back addresses of parent node
* and its left or right link for further processing.
*
* Otherwise NULL is returned. In that case all further
* steps regarding inserting of conflicting overlap range
* have to be declined and actually considered as a bug.
*/
static __always_inline struct rb_node **
find_va_links(struct vmap_area *va,
struct rb_root *root, struct rb_node *from,
struct rb_node **parent)
{
struct vmap_area *tmp_va;
struct rb_node **link;
if (root) {
link = &root->rb_node;
if (unlikely(!*link)) {
*parent = NULL;
return link;
}
} else {
link = &from;
}
/*
* Go to the bottom of the tree. When we hit the last point
* we end up with parent rb_node and correct direction, i name
* it link, where the new va->rb_node will be attached to.
*/
do {
tmp_va = rb_entry(*link, struct vmap_area, rb_node);
/*
* During the traversal we also do some sanity check.
* Trigger the BUG() if there are sides(left/right)
* or full overlaps.
*/
if (va->va_end <= tmp_va->va_start)
link = &(*link)->rb_left;
else if (va->va_start >= tmp_va->va_end)
link = &(*link)->rb_right;
else {
WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n",
va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end);
return NULL;
}
} while (*link);
*parent = &tmp_va->rb_node;
return link;
}
static __always_inline struct list_head *
get_va_next_sibling(struct rb_node *parent, struct rb_node **link)
{
struct list_head *list;
if (unlikely(!parent))
/*
* The red-black tree where we try to find VA neighbors
* before merging or inserting is empty, i.e. it means
* there is no free vmap space. Normally it does not
* happen but we handle this case anyway.
*/
return NULL;
list = &rb_entry(parent, struct vmap_area, rb_node)->list;
return (&parent->rb_right == link ? list->next : list);
}
static __always_inline void
__link_va(struct vmap_area *va, struct rb_root *root,
struct rb_node *parent, struct rb_node **link,
struct list_head *head, bool augment)
{
/*
* VA is still not in the list, but we can
* identify its future previous list_head node.
*/
if (likely(parent)) {
head = &rb_entry(parent, struct vmap_area, rb_node)->list;
if (&parent->rb_right != link) head = head->prev;
}
/* Insert to the rb-tree */
rb_link_node(&va->rb_node, parent, link);
if (augment) {
/*
* Some explanation here. Just perform simple insertion
* to the tree. We do not set va->subtree_max_size to
* its current size before calling rb_insert_augmented().
* It is because we populate the tree from the bottom
* to parent levels when the node _is_ in the tree.
*
* Therefore we set subtree_max_size to zero after insertion,
* to let __augment_tree_propagate_from() puts everything to
* the correct order later on.
*/
rb_insert_augmented(&va->rb_node,
root, &free_vmap_area_rb_augment_cb);
va->subtree_max_size = 0;
} else {
rb_insert_color(&va->rb_node, root);
}
/* Address-sort this list */
list_add(&va->list, head);
}
static __always_inline void
link_va(struct vmap_area *va, struct rb_root *root,
struct rb_node *parent, struct rb_node **link,
struct list_head *head)
{
__link_va(va, root, parent, link, head, false);
}
static __always_inline void
link_va_augment(struct vmap_area *va, struct rb_root *root,
struct rb_node *parent, struct rb_node **link,
struct list_head *head)
{
__link_va(va, root, parent, link, head, true);
}
static __always_inline void
__unlink_va(struct vmap_area *va, struct rb_root *root, bool augment)
{
if (WARN_ON(RB_EMPTY_NODE(&va->rb_node)))
return;
if (augment)
rb_erase_augmented(&va->rb_node,
root, &free_vmap_area_rb_augment_cb);
else
rb_erase(&va->rb_node, root);
list_del_init(&va->list);
RB_CLEAR_NODE(&va->rb_node);
}
static __always_inline void
unlink_va(struct vmap_area *va, struct rb_root *root)
{
__unlink_va(va, root, false);
}
static __always_inline void
unlink_va_augment(struct vmap_area *va, struct rb_root *root)
{
__unlink_va(va, root, true);
}
#if DEBUG_AUGMENT_PROPAGATE_CHECK
/*
* Gets called when remove the node and rotate.
*/
static __always_inline unsigned long
compute_subtree_max_size(struct vmap_area *va)
{
return max3(va_size(va),
get_subtree_max_size(va->rb_node.rb_left),
get_subtree_max_size(va->rb_node.rb_right));
}
static void
augment_tree_propagate_check(void)
{
struct vmap_area *va;
unsigned long computed_size;
list_for_each_entry(va, &free_vmap_area_list, list) {
computed_size = compute_subtree_max_size(va);
if (computed_size != va->subtree_max_size)
pr_emerg("tree is corrupted: %lu, %lu\n",
va_size(va), va->subtree_max_size);
}
}
#endif
/*
* This function populates subtree_max_size from bottom to upper
* levels starting from VA point. The propagation must be done
* when VA size is modified by changing its va_start/va_end. Or
* in case of newly inserting of VA to the tree.
*
* It means that __augment_tree_propagate_from() must be called:
* - After VA has been inserted to the tree(free path);
* - After VA has been shrunk(allocation path);
* - After VA has been increased(merging path).
*
* Please note that, it does not mean that upper parent nodes
* and their subtree_max_size are recalculated all the time up
* to the root node.
*
* 4--8
* /\
* / \
* / \
* 2--2 8--8
*
* For example if we modify the node 4, shrinking it to 2, then
* no any modification is required. If we shrink the node 2 to 1
* its subtree_max_size is updated only, and set to 1. If we shrink
* the node 8 to 6, then its subtree_max_size is set to 6 and parent
* node becomes 4--6.
*/
static __always_inline void
augment_tree_propagate_from(struct vmap_area *va)
{
/*
* Populate the tree from bottom towards the root until
* the calculated maximum available size of checked node
* is equal to its current one.
*/
free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL);
#if DEBUG_AUGMENT_PROPAGATE_CHECK
augment_tree_propagate_check();
#endif
}
static void
insert_vmap_area(struct vmap_area *va,
struct rb_root *root, struct list_head *head)
{
struct rb_node **link;
struct rb_node *parent;
link = find_va_links(va, root, NULL, &parent);
if (link)
link_va(va, root, parent, link, head);
}
static void
insert_vmap_area_augment(struct vmap_area *va,
struct rb_node *from, struct rb_root *root,
struct list_head *head)
{
struct rb_node **link;
struct rb_node *parent;
if (from)
link = find_va_links(va, NULL, from, &parent);
else
link = find_va_links(va, root, NULL, &parent);
if (link) {
link_va_augment(va, root, parent, link, head);
augment_tree_propagate_from(va);
}
}
/*
* Merge de-allocated chunk of VA memory with previous
* and next free blocks. If coalesce is not done a new
* free area is inserted. If VA has been merged, it is
* freed.
*
* Please note, it can return NULL in case of overlap
* ranges, followed by WARN() report. Despite it is a
* buggy behaviour, a system can be alive and keep
* ongoing.
*/
static __always_inline struct vmap_area *
__merge_or_add_vmap_area(struct vmap_area *va,
struct rb_root *root, struct list_head *head, bool augment)
{
struct vmap_area *sibling;
struct list_head *next;
struct rb_node **link;
struct rb_node *parent;
bool merged = false;
/*
* Find a place in the tree where VA potentially will be
* inserted, unless it is merged with its sibling/siblings.
*/
link = find_va_links(va, root, NULL, &parent);
if (!link)
return NULL;
/*
* Get next node of VA to check if merging can be done.
*/
next = get_va_next_sibling(parent, link);
if (unlikely(next == NULL))
goto insert;
/*
* start end
* | |
* |<------VA------>|<-----Next----->|
* | |
* start end
*/
if (next != head) {
sibling = list_entry(next, struct vmap_area, list);
if (sibling->va_start == va->va_end) {
sibling->va_start = va->va_start;
/* Free vmap_area object. */
kmem_cache_free(vmap_area_cachep, va);
/* Point to the new merged area. */
va = sibling;
merged = true;
}
}
/*
* start end
* | |
* |<-----Prev----->|<------VA------>|
* | |
* start end
*/
if (next->prev != head) {
sibling = list_entry(next->prev, struct vmap_area, list);
if (sibling->va_end == va->va_start) {
/*
* If both neighbors are coalesced, it is important
* to unlink the "next" node first, followed by merging
* with "previous" one. Otherwise the tree might not be
* fully populated if a sibling's augmented value is
* "normalized" because of rotation operations.
*/
if (merged)
__unlink_va(va, root, augment);
sibling->va_end = va->va_end;
/* Free vmap_area object. */
kmem_cache_free(vmap_area_cachep, va);
/* Point to the new merged area. */
va = sibling;
merged = true;
}
}
insert:
if (!merged)
__link_va(va, root, parent, link, head, augment);
return va;
}
static __always_inline struct vmap_area *
merge_or_add_vmap_area(struct vmap_area *va,
struct rb_root *root, struct list_head *head)
{
return __merge_or_add_vmap_area(va, root, head, false);
}
static __always_inline struct vmap_area *
merge_or_add_vmap_area_augment(struct vmap_area *va,
struct rb_root *root, struct list_head *head)
{
va = __merge_or_add_vmap_area(va, root, head, true);
if (va)
augment_tree_propagate_from(va);
return va;
}
static __always_inline bool
is_within_this_va(struct vmap_area *va, unsigned long size,
unsigned long align, unsigned long vstart)
{
unsigned long nva_start_addr;
if (va->va_start > vstart)
nva_start_addr = ALIGN(va->va_start, align);
else
nva_start_addr = ALIGN(vstart, align);
/* Can be overflowed due to big size or alignment. */
if (nva_start_addr + size < nva_start_addr ||
nva_start_addr < vstart)
return false;
return (nva_start_addr + size <= va->va_end);
}
/*
* Find the first free block(lowest start address) in the tree,
* that will accomplish the request corresponding to passing
* parameters. Please note, with an alignment bigger than PAGE_SIZE,
* a search length is adjusted to account for worst case alignment
* overhead.
*/
static __always_inline struct vmap_area *
find_vmap_lowest_match(struct rb_root *root, unsigned long size,
unsigned long align, unsigned long vstart, bool adjust_search_size)
{
struct vmap_area *va;
struct rb_node *node;
unsigned long length;
/* Start from the root. */
node = root->rb_node;
/* Adjust the search size for alignment overhead. */
length = adjust_search_size ? size + align - 1 : size;
while (node) {
va = rb_entry(node, struct vmap_area, rb_node);
if (get_subtree_max_size(node->rb_left) >= length &&
vstart < va->va_start) {
node = node->rb_left;
} else {
if (is_within_this_va(va, size, align, vstart))
return va;
/*
* Does not make sense to go deeper towards the right
* sub-tree if it does not have a free block that is
* equal or bigger to the requested search length.
*/
if (get_subtree_max_size(node->rb_right) >= length) {
node = node->rb_right;
continue;
}
/*
* OK. We roll back and find the first right sub-tree,
* that will satisfy the search criteria. It can happen
* due to "vstart" restriction or an alignment overhead
* that is bigger then PAGE_SIZE.
*/
while ((node = rb_parent(node))) {
va = rb_entry(node, struct vmap_area, rb_node);
if (is_within_this_va(va, size, align, vstart))
return va;
if (get_subtree_max_size(node->rb_right) >= length &&
vstart <= va->va_start) {
/*
* Shift the vstart forward. Please note, we update it with
* parent's start address adding "1" because we do not want
* to enter same sub-tree after it has already been checked
* and no suitable free block found there.
*/
vstart = va->va_start + 1;
node = node->rb_right;
break;
}
}
}
}
return NULL;
}
#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
#include <linux/random.h>
static struct vmap_area *
find_vmap_lowest_linear_match(struct list_head *head, unsigned long size,
unsigned long align, unsigned long vstart)
{
struct vmap_area *va;
list_for_each_entry(va, head, list) {
if (!is_within_this_va(va, size, align, vstart))
continue;
return va;
}
return NULL;
}
static void
find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head,
unsigned long size, unsigned long align)
{
struct vmap_area *va_1, *va_2;
unsigned long vstart;
unsigned int rnd;
get_random_bytes(&rnd, sizeof(rnd));
vstart = VMALLOC_START + rnd;
va_1 = find_vmap_lowest_match(root, size, align, vstart, false);
va_2 = find_vmap_lowest_linear_match(head, size, align, vstart);
if (va_1 != va_2)
pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
va_1, va_2, vstart);
}
#endif
enum fit_type {
NOTHING_FIT = 0,
FL_FIT_TYPE = 1, /* full fit */
LE_FIT_TYPE = 2, /* left edge fit */
RE_FIT_TYPE = 3, /* right edge fit */
NE_FIT_TYPE = 4 /* no edge fit */
};
static __always_inline enum fit_type
classify_va_fit_type(struct vmap_area *va,
unsigned long nva_start_addr, unsigned long size)
{
enum fit_type type;
/* Check if it is within VA. */
if (nva_start_addr < va->va_start ||
nva_start_addr + size > va->va_end)
return NOTHING_FIT;
/* Now classify. */
if (va->va_start == nva_start_addr) {
if (va->va_end == nva_start_addr + size)
type = FL_FIT_TYPE;
else
type = LE_FIT_TYPE;
} else if (va->va_end == nva_start_addr + size) {
type = RE_FIT_TYPE;
} else {
type = NE_FIT_TYPE;
}
return type;
}
static __always_inline int
va_clip(struct rb_root *root, struct list_head *head,
struct vmap_area *va, unsigned long nva_start_addr,
unsigned long size)
{
struct vmap_area *lva = NULL;
enum fit_type type = classify_va_fit_type(va, nva_start_addr, size);
if (type == FL_FIT_TYPE) {
/*
* No need to split VA, it fully fits.
*
* | |
* V NVA V
* |---------------|
*/
unlink_va_augment(va, root);
kmem_cache_free(vmap_area_cachep, va);
} else if (type == LE_FIT_TYPE) {
/*
* Split left edge of fit VA.
*
* | |
* V NVA V R
* |-------|-------|
*/
va->va_start += size;
} else if (type == RE_FIT_TYPE) {
/*
* Split right edge of fit VA.
*
* | |
* L V NVA V
* |-------|-------|
*/
va->va_end = nva_start_addr;
} else if (type == NE_FIT_TYPE) {
/*
* Split no edge of fit VA.
*
* | |
* L V NVA V R
* |---|-------|---|
*/
lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
if (unlikely(!lva)) {
/*
* For percpu allocator we do not do any pre-allocation
* and leave it as it is. The reason is it most likely
* never ends up with NE_FIT_TYPE splitting. In case of
* percpu allocations offsets and sizes are aligned to
* fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
* are its main fitting cases.
*
* There are a few exceptions though, as an example it is
* a first allocation (early boot up) when we have "one"
* big free space that has to be split.
*
* Also we can hit this path in case of regular "vmap"
* allocations, if "this" current CPU was not preloaded.
* See the comment in alloc_vmap_area() why. If so, then
* GFP_NOWAIT is used instead to get an extra object for
* split purpose. That is rare and most time does not
* occur.
*
* What happens if an allocation gets failed. Basically,
* an "overflow" path is triggered to purge lazily freed
* areas to free some memory, then, the "retry" path is
* triggered to repeat one more time. See more details
* in alloc_vmap_area() function.
*/
lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
if (!lva)
return -1;
}
/*
* Build the remainder.
*/
lva->va_start = va->va_start;
lva->va_end = nva_start_addr;
/*
* Shrink this VA to remaining size.
*/
va->va_start = nva_start_addr + size;
} else {
return -1;
}
if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, root, head);
}
return 0;
}
static unsigned long
va_alloc(struct vmap_area *va,
struct rb_root *root, struct list_head *head,
unsigned long size, unsigned long align,
unsigned long vstart, unsigned long vend)
{
unsigned long nva_start_addr;
int ret;
if (va->va_start > vstart)
nva_start_addr = ALIGN(va->va_start, align);
else
nva_start_addr = ALIGN(vstart, align);
/* Check the "vend" restriction. */
if (nva_start_addr + size > vend)
return vend;
/* Update the free vmap_area. */
ret = va_clip(root, head, va, nva_start_addr, size);
if (WARN_ON_ONCE(ret))
return vend;
return nva_start_addr;
}
/*
* Returns a start address of the newly allocated area, if success.
* Otherwise a vend is returned that indicates failure.
*/
static __always_inline unsigned long
__alloc_vmap_area(struct rb_root *root, struct list_head *head,
unsigned long size, unsigned long align,
unsigned long vstart, unsigned long vend)
{
bool adjust_search_size = true;
unsigned long nva_start_addr;
struct vmap_area *va;
/*
* Do not adjust when:
* a) align <= PAGE_SIZE, because it does not make any sense.
* All blocks(their start addresses) are at least PAGE_SIZE
* aligned anyway;
* b) a short range where a requested size corresponds to exactly
* specified [vstart:vend] interval and an alignment > PAGE_SIZE.
* With adjusted search length an allocation would not succeed.
*/
if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size))
adjust_search_size = false;
va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va))
return vend;
nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend);
if (nva_start_addr == vend)
return vend;
#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
find_vmap_lowest_match_check(root, head, size, align);
#endif
return nva_start_addr;
}
/*
* Free a region of KVA allocated by alloc_vmap_area
*/
static void free_vmap_area(struct vmap_area *va)
{
struct vmap_node *vn = addr_to_node(va->va_start);
/*
* Remove from the busy tree/list.
*/
spin_lock(&vn->busy.lock);
unlink_va(va, &vn->busy.root);
spin_unlock(&vn->busy.lock);
/*
* Insert/Merge it back to the free tree/list.
*/
spin_lock(&free_vmap_area_lock);
merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
spin_unlock(&free_vmap_area_lock);
}
static inline void
preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
{
struct vmap_area *va = NULL, *tmp;
/*
* Preload this CPU with one extra vmap_area object. It is used
* when fit type of free area is NE_FIT_TYPE. It guarantees that
* a CPU that does an allocation is preloaded.
*
* We do it in non-atomic context, thus it allows us to use more
* permissive allocation masks to be more stable under low memory
* condition and high memory pressure.
*/
if (!this_cpu_read(ne_fit_preload_node))
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
spin_lock(lock);
tmp = NULL;
if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va);
}
static struct vmap_pool *
size_to_va_pool(struct vmap_node *vn, unsigned long size)
{
unsigned int idx = (size - 1) / PAGE_SIZE;
if (idx < MAX_VA_SIZE_PAGES)
return &vn->pool[idx];
return NULL;
}
static bool
node_pool_add_va(struct vmap_node *n, struct vmap_area *va)
{
struct vmap_pool *vp;
vp = size_to_va_pool(n, va_size(va));
if (!vp)
return false;
spin_lock(&n->pool_lock);
list_add(&va->list, &vp->head);
WRITE_ONCE(vp->len, vp->len + 1);
spin_unlock(&n->pool_lock);
return true;
}
static struct vmap_area *
node_pool_del_va(struct vmap_node *vn, unsigned long size,
unsigned long align, unsigned long vstart,
unsigned long vend)
{
struct vmap_area *va = NULL;
struct vmap_pool *vp;
int err = 0;
vp = size_to_va_pool(vn, size);
if (!vp || list_empty(&vp->head))
return NULL;
spin_lock(&vn->pool_lock);
if (!list_empty(&vp->head)) {
va = list_first_entry(&vp->head, struct vmap_area, list);
if (IS_ALIGNED(va->va_start, align)) {
/*
* Do some sanity check and emit a warning
* if one of below checks detects an error.
*/
err |= (va_size(va) != size);
err |= (va->va_start < vstart);
err |= (va->va_end > vend);
if (!WARN_ON_ONCE(err)) { list_del_init(&va->list);
WRITE_ONCE(vp->len, vp->len - 1);
} else {
va = NULL;
}
} else {
list_move_tail(&va->list, &vp->head);
va = NULL;
}
}
spin_unlock(&vn->pool_lock);
return va;
}
static struct vmap_area *
node_alloc(unsigned long size, unsigned long align,
unsigned long vstart, unsigned long vend,
unsigned long *addr, unsigned int *vn_id)
{
struct vmap_area *va;
*vn_id = 0;
*addr = vend;
/*
* Fallback to a global heap if not vmalloc or there
* is only one node.
*/
if (vstart != VMALLOC_START || vend != VMALLOC_END ||
nr_vmap_nodes == 1)
return NULL;
*vn_id = raw_smp_processor_id() % nr_vmap_nodes;
va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); *vn_id = encode_vn_id(*vn_id); if (va) *addr = va->va_start;
return va;
}
static inline void setup_vmalloc_vm(struct vm_struct *vm,
struct vmap_area *va, unsigned long flags, const void *caller)
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
vm->size = va_size(va);
vm->caller = caller;
va->vm = vm;
}
/*
* Allocate a region of KVA of the specified size and alignment, within the
* vstart and vend. If vm is passed in, the two will also be bound.
*/
static struct vmap_area *alloc_vmap_area(unsigned long size,
unsigned long align,
unsigned long vstart, unsigned long vend,
int node, gfp_t gfp_mask,
unsigned long va_flags, struct vm_struct *vm)
{
struct vmap_node *vn;
struct vmap_area *va;
unsigned long freed;
unsigned long addr;
unsigned int vn_id;
int purged = 0;
int ret;
if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align)))
return ERR_PTR(-EINVAL);
if (unlikely(!vmap_initialized))
return ERR_PTR(-EBUSY);
might_sleep();
/*
* If a VA is obtained from a global heap(if it fails here)
* it is anyway marked with this "vn_id" so it is returned
* to this pool's node later. Such way gives a possibility
* to populate pools based on users demand.
*
* On success a ready to go VA is returned.
*/
va = node_alloc(size, align, vstart, vend, &addr, &vn_id);
if (!va) {
gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
if (unlikely(!va))
return ERR_PTR(-ENOMEM);
/*
* Only scan the relevant parts containing pointers to other objects
* to avoid false negatives.
*/
kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask);
}
retry:
if (addr == vend) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list,
size, align, vstart, vend);
spin_unlock(&free_vmap_area_lock);
}
trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend);
/*
* If an allocation fails, the "vend" address is
* returned. Therefore trigger the overflow path.
*/
if (unlikely(addr == vend))
goto overflow;
va->va_start = addr;
va->va_end = addr + size;
va->vm = NULL;
va->flags = (va_flags | vn_id);
if (vm) { vm->addr = (void *)va->va_start;
vm->size = va_size(va);
va->vm = vm;
}
vn = addr_to_node(va->va_start);
spin_lock(&vn->busy.lock);
insert_vmap_area(va, &vn->busy.root, &vn->busy.head);
spin_unlock(&vn->busy.lock);
BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend);
ret = kasan_populate_vmalloc(addr, size);
if (ret) { free_vmap_area(va);
return ERR_PTR(ret);
}
return va;
overflow:
if (!purged) {
reclaim_and_purge_vmap_areas();
purged = 1;
goto retry;
}
freed = 0;
blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
if (freed > 0) {
purged = 0;
goto retry;
}
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n",
size, vstart, vend);
kmem_cache_free(vmap_area_cachep, va);
return ERR_PTR(-EBUSY);
}
int register_vmap_purge_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);
int unregister_vmap_purge_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
/*
* lazy_max_pages is the maximum amount of virtual address space we gather up
* before attempting to purge with a TLB flush.
*
* There is a tradeoff here: a larger number will cover more kernel page tables
* and take slightly longer to purge, but it will linearly reduce the number of
* global TLB flushes that must be performed. It would seem natural to scale
* this number up linearly with the number of CPUs (because vmapping activity
* could also scale linearly with the number of CPUs), however it is likely
* that in practice, workloads might be constrained in other ways that mean
* vmap activity will not scale linearly with CPUs. Also, I want to be
* conservative and not introduce a big latency on huge systems, so go with
* a less aggressive log scale. It will still be an improvement over the old
* code, and it will be simple to change the scale factor if we find that it
* becomes a problem on bigger systems.
*/
static unsigned long lazy_max_pages(void)
{
unsigned int log;
log = fls(num_online_cpus());
return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}
static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);
/*
* Serialize vmap purging. There is no actual critical section protected
* by this lock, but we want to avoid concurrent calls for performance
* reasons and to make the pcpu_get_vm_areas more deterministic.
*/
static DEFINE_MUTEX(vmap_purge_lock);
/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);
static cpumask_t purge_nodes;
static void
reclaim_list_global(struct list_head *head)
{
struct vmap_area *va, *n;
if (list_empty(head))
return;
spin_lock(&free_vmap_area_lock);
list_for_each_entry_safe(va, n, head, list)
merge_or_add_vmap_area_augment(va,
&free_vmap_area_root, &free_vmap_area_list);
spin_unlock(&free_vmap_area_lock);
}
static void
decay_va_pool_node(struct vmap_node *vn, bool full_decay)
{
LIST_HEAD(decay_list);
struct rb_root decay_root = RB_ROOT;
struct vmap_area *va, *nva;
unsigned long n_decay;
int i;
for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
LIST_HEAD(tmp_list);
if (list_empty(&vn->pool[i].head))
continue;
/* Detach the pool, so no-one can access it. */
spin_lock(&vn->pool_lock);
list_replace_init(&vn->pool[i].head, &tmp_list);
spin_unlock(&vn->pool_lock);
if (full_decay)
WRITE_ONCE(vn->pool[i].len, 0);
/* Decay a pool by ~25% out of left objects. */
n_decay = vn->pool[i].len >> 2;
list_for_each_entry_safe(va, nva, &tmp_list, list) {
list_del_init(&va->list);
merge_or_add_vmap_area(va, &decay_root, &decay_list);
if (!full_decay) {
WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1);
if (!--n_decay)
break;
}
}
/*
* Attach the pool back if it has been partly decayed.
* Please note, it is supposed that nobody(other contexts)
* can populate the pool therefore a simple list replace
* operation takes place here.
*/
if (!full_decay && !list_empty(&tmp_list)) {
spin_lock(&vn->pool_lock);
list_replace_init(&tmp_list, &vn->pool[i].head);
spin_unlock(&vn->pool_lock);
}
}
reclaim_list_global(&decay_list);
}
static void
kasan_release_vmalloc_node(struct vmap_node *vn)
{
struct vmap_area *va;
unsigned long start, end;
start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start;
end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end;
list_for_each_entry(va, &vn->purge_list, list) {
if (is_vmalloc_or_module_addr((void *) va->va_start))
kasan_release_vmalloc(va->va_start, va->va_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE);
}
kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH);
}
static void purge_vmap_node(struct work_struct *work)
{
struct vmap_node *vn = container_of(work,
struct vmap_node, purge_work);
unsigned long nr_purged_pages = 0;
struct vmap_area *va, *n_va;
LIST_HEAD(local_list);
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_release_vmalloc_node(vn);
vn->nr_purged = 0;
list_for_each_entry_safe(va, n_va, &vn->purge_list, list) {
unsigned long nr = va_size(va) >> PAGE_SHIFT;
unsigned int vn_id = decode_vn_id(va->flags);
list_del_init(&va->list);
nr_purged_pages += nr;
vn->nr_purged++;
if (is_vn_id_valid(vn_id) && !vn->skip_populate)
if (node_pool_add_va(vn, va))
continue;
/* Go back to global. */
list_add(&va->list, &local_list);
}
atomic_long_sub(nr_purged_pages, &vmap_lazy_nr);
reclaim_list_global(&local_list);
}
/*
* Purges all lazily-freed vmap areas.
*/
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end,
bool full_pool_decay)
{
unsigned long nr_purged_areas = 0;
unsigned int nr_purge_helpers;
unsigned int nr_purge_nodes;
struct vmap_node *vn;
int i;
lockdep_assert_held(&vmap_purge_lock);
/*
* Use cpumask to mark which node has to be processed.
*/
purge_nodes = CPU_MASK_NONE;
for (i = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
INIT_LIST_HEAD(&vn->purge_list);
vn->skip_populate = full_pool_decay;
decay_va_pool_node(vn, full_pool_decay);
if (RB_EMPTY_ROOT(&vn->lazy.root))
continue;
spin_lock(&vn->lazy.lock);
WRITE_ONCE(vn->lazy.root.rb_node, NULL);
list_replace_init(&vn->lazy.head, &vn->purge_list);
spin_unlock(&vn->lazy.lock);
start = min(start, list_first_entry(&vn->purge_list,
struct vmap_area, list)->va_start);
end = max(end, list_last_entry(&vn->purge_list,
struct vmap_area, list)->va_end);
cpumask_set_cpu(i, &purge_nodes);
}
nr_purge_nodes = cpumask_weight(&purge_nodes);
if (nr_purge_nodes > 0) {
flush_tlb_kernel_range(start, end);
/* One extra worker is per a lazy_max_pages() full set minus one. */
nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages();
nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1;
for_each_cpu(i, &purge_nodes) {
vn = &vmap_nodes[i];
if (nr_purge_helpers > 0) {
INIT_WORK(&vn->purge_work, purge_vmap_node);
if (cpumask_test_cpu(i, cpu_online_mask))
schedule_work_on(i, &vn->purge_work);
else
schedule_work(&vn->purge_work);
nr_purge_helpers--;
} else {
vn->purge_work.func = NULL;
purge_vmap_node(&vn->purge_work);
nr_purged_areas += vn->nr_purged;
}
}
for_each_cpu(i, &purge_nodes) {
vn = &vmap_nodes[i];
if (vn->purge_work.func) {
flush_work(&vn->purge_work);
nr_purged_areas += vn->nr_purged;
}
}
}
trace_purge_vmap_area_lazy(start, end, nr_purged_areas);
return nr_purged_areas > 0;
}
/*
* Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list.
*/
static void reclaim_and_purge_vmap_areas(void)
{
mutex_lock(&vmap_purge_lock);
purge_fragmented_blocks_allcpus();
__purge_vmap_area_lazy(ULONG_MAX, 0, true);
mutex_unlock(&vmap_purge_lock);
}
static void drain_vmap_area_work(struct work_struct *work)
{
mutex_lock(&vmap_purge_lock);
__purge_vmap_area_lazy(ULONG_MAX, 0, false);
mutex_unlock(&vmap_purge_lock);
}
/*
* Free a vmap area, caller ensuring that the area has been unmapped,
* unlinked and flush_cache_vunmap had been called for the correct
* range previously.
*/
static void free_vmap_area_noflush(struct vmap_area *va)
{
unsigned long nr_lazy_max = lazy_max_pages();
unsigned long va_start = va->va_start;
unsigned int vn_id = decode_vn_id(va->flags);
struct vmap_node *vn;
unsigned long nr_lazy;
if (WARN_ON_ONCE(!list_empty(&va->list)))
return;
nr_lazy = atomic_long_add_return(va_size(va) >> PAGE_SHIFT,
&vmap_lazy_nr);
/*
* If it was request by a certain node we would like to
* return it to that node, i.e. its pool for later reuse.
*/
vn = is_vn_id_valid(vn_id) ?
id_to_node(vn_id):addr_to_node(va->va_start);
spin_lock(&vn->lazy.lock);
insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head);
spin_unlock(&vn->lazy.lock);
trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max);
/* After this point, we may free va at any time */
if (unlikely(nr_lazy > nr_lazy_max)) schedule_work(&drain_vmap_work);
}
/*
* Free and unmap a vmap area
*/
static void free_unmap_vmap_area(struct vmap_area *va)
{
flush_cache_vunmap(va->va_start, va->va_end);
vunmap_range_noflush(va->va_start, va->va_end);
if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range(va->va_start, va->va_end);
free_vmap_area_noflush(va);
}
struct vmap_area *find_vmap_area(unsigned long addr)
{
struct vmap_node *vn;
struct vmap_area *va;
int i, j;
if (unlikely(!vmap_initialized))
return NULL;
/*
* An addr_to_node_id(addr) converts an address to a node index
* where a VA is located. If VA spans several zones and passed
* addr is not the same as va->va_start, what is not common, we
* may need to scan extra nodes. See an example:
*
* <----va---->
* -|-----|-----|-----|-----|-
* 1 2 0 1
*
* VA resides in node 1 whereas it spans 1, 2 an 0. If passed
* addr is within 2 or 0 nodes we should do extra work.
*/
i = j = addr_to_node_id(addr);
do {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
va = __find_vmap_area(addr, &vn->busy.root);
spin_unlock(&vn->busy.lock);
if (va)
return va;
} while ((i = (i + 1) % nr_vmap_nodes) != j);
return NULL;
}
static struct vmap_area *find_unlink_vmap_area(unsigned long addr)
{
struct vmap_node *vn;
struct vmap_area *va;
int i, j;
/*
* Check the comment in the find_vmap_area() about the loop.
*/
i = j = addr_to_node_id(addr);
do {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
va = __find_vmap_area(addr, &vn->busy.root); if (va) unlink_va(va, &vn->busy.root);
spin_unlock(&vn->busy.lock);
if (va)
return va;
} while ((i = (i + 1) % nr_vmap_nodes) != j);
return NULL;
}
/*** Per cpu kva allocator ***/
/*
* vmap space is limited especially on 32 bit architectures. Ensure there is
* room for at least 16 percpu vmap blocks per CPU.
*/
/*
* If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
* to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess
* instead (we just need a rough idea)
*/
#if BITS_PER_LONG == 32
#define VMALLOC_SPACE (128UL*1024*1024)
#else
#define VMALLOC_SPACE (128UL*1024*1024*1024)
#endif
#define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE)
#define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */
#define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */
#define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2)
#define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */
#define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */
#define VMAP_BBMAP_BITS \
VMAP_MIN(VMAP_BBMAP_BITS_MAX, \
VMAP_MAX(VMAP_BBMAP_BITS_MIN, \
VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
/*
* Purge threshold to prevent overeager purging of fragmented blocks for
* regular operations: Purge if vb->free is less than 1/4 of the capacity.
*/
#define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4)
#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/
#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/
#define VMAP_FLAGS_MASK 0x3
struct vmap_block_queue {
spinlock_t lock;
struct list_head free;
/*
* An xarray requires an extra memory dynamically to
* be allocated. If it is an issue, we can use rb-tree
* instead.
*/
struct xarray vmap_blocks;
};
struct vmap_block {
spinlock_t lock;
struct vmap_area *va;
unsigned long free, dirty;
DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS);
unsigned long dirty_min, dirty_max; /*< dirty range */
struct list_head free_list;
struct rcu_head rcu_head;
struct list_head purge;
unsigned int cpu;
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
/*
* In order to fast access to any "vmap_block" associated with a
* specific address, we use a hash.
*
* A per-cpu vmap_block_queue is used in both ways, to serialize
* an access to free block chains among CPUs(alloc path) and it
* also acts as a vmap_block hash(alloc/free paths). It means we
* overload it, since we already have the per-cpu array which is
* used as a hash table. When used as a hash a 'cpu' passed to
* per_cpu() is not actually a CPU but rather a hash index.
*
* A hash function is addr_to_vb_xa() which hashes any address
* to a specific index(in a hash) it belongs to. This then uses a
* per_cpu() macro to access an array with generated index.
*
* An example:
*
* CPU_1 CPU_2 CPU_0
* | | |
* V V V
* 0 10 20 30 40 50 60
* |------|------|------|------|------|------|...<vmap address space>
* CPU0 CPU1 CPU2 CPU0 CPU1 CPU2
*
* - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus
* it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock;
*
* - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus
* it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock;
*
* - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus
* it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock.
*
* This technique almost always avoids lock contention on insert/remove,
* however xarray spinlocks protect against any contention that remains.
*/
static struct xarray *
addr_to_vb_xa(unsigned long addr)
{
int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids;
/*
* Please note, nr_cpu_ids points on a highest set
* possible bit, i.e. we never invoke cpumask_next()
* if an index points on it which is nr_cpu_ids - 1.
*/
if (!cpu_possible(index))
index = cpumask_next(index, cpu_possible_mask);
return &per_cpu(vmap_block_queue, index).vmap_blocks;
}
/*
* We should probably have a fallback mechanism to allocate virtual memory
* out of partially filled vmap blocks. However vmap block sizing should be
* fairly reasonable according to the vmalloc size, so it shouldn't be a
* big problem.
*/
static unsigned long addr_to_vb_idx(unsigned long addr)
{
addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
addr /= VMAP_BLOCK_SIZE;
return addr;
}
static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off)
{
unsigned long addr;
addr = va_start + (pages_off << PAGE_SHIFT);
BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start));
return (void *)addr;
}
/**
* new_vmap_block - allocates new vmap_block and occupies 2^order pages in this
* block. Of course pages number can't exceed VMAP_BBMAP_BITS
* @order: how many 2^order pages should be occupied in newly allocated block
* @gfp_mask: flags for the page level allocator
*
* Return: virtual address in a newly allocated block or ERR_PTR(-errno)
*/
static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
{
struct vmap_block_queue *vbq;
struct vmap_block *vb;
struct vmap_area *va;
struct xarray *xa;
unsigned long vb_idx;
int node, err;
void *vaddr;
node = numa_node_id();
vb = kmalloc_node(sizeof(struct vmap_block),
gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!vb))
return ERR_PTR(-ENOMEM);
va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
VMALLOC_START, VMALLOC_END,
node, gfp_mask,
VMAP_RAM|VMAP_BLOCK, NULL);
if (IS_ERR(va)) {
kfree(vb);
return ERR_CAST(va);
}
vaddr = vmap_block_vaddr(va->va_start, 0);
spin_lock_init(&vb->lock);
vb->va = va;
/* At least something should be left free */
BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
bitmap_zero(vb->used_map, VMAP_BBMAP_BITS);
vb->free = VMAP_BBMAP_BITS - (1UL << order);
vb->dirty = 0;
vb->dirty_min = VMAP_BBMAP_BITS;
vb->dirty_max = 0;
bitmap_set(vb->used_map, 0, (1UL << order));
INIT_LIST_HEAD(&vb->free_list);
vb->cpu = raw_smp_processor_id();
xa = addr_to_vb_xa(va->va_start);
vb_idx = addr_to_vb_idx(va->va_start);
err = xa_insert(xa, vb_idx, vb, gfp_mask);
if (err) {
kfree(vb);
free_vmap_area(va);
return ERR_PTR(err);
}
/*
* list_add_tail_rcu could happened in another core
* rather than vb->cpu due to task migration, which
* is safe as list_add_tail_rcu will ensure the list's
* integrity together with list_for_each_rcu from read
* side.
*/
vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
return vaddr;
}
static void free_vmap_block(struct vmap_block *vb)
{
struct vmap_node *vn;
struct vmap_block *tmp;
struct xarray *xa;
xa = addr_to_vb_xa(vb->va->va_start);
tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start));
BUG_ON(tmp != vb);
vn = addr_to_node(vb->va->va_start);
spin_lock(&vn->busy.lock);
unlink_va(vb->va, &vn->busy.root);
spin_unlock(&vn->busy.lock);
free_vmap_area_noflush(vb->va);
kfree_rcu(vb, rcu_head);
}
static bool purge_fragmented_block(struct vmap_block *vb,
struct list_head *purge_list, bool force_purge)
{
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu);
if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
vb->dirty == VMAP_BBMAP_BITS)
return false;
/* Don't overeagerly purge usable blocks unless requested */
if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
return false;
/* prevent further allocs after releasing lock */
WRITE_ONCE(vb->free, 0);
/* prevent purging it again */
WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS);
vb->dirty_min = 0;
vb->dirty_max = VMAP_BBMAP_BITS;
spin_lock(&vbq->lock);
list_del_rcu(&vb->free_list);
spin_unlock(&vbq->lock);
list_add_tail(&vb->purge, purge_list);
return true;
}
static void free_purged_blocks(struct list_head *purge_list)
{
struct vmap_block *vb, *n_vb;
list_for_each_entry_safe(vb, n_vb, purge_list, purge) {
list_del(&vb->purge);
free_vmap_block(vb);
}
}
static void purge_fragmented_blocks(int cpu)
{
LIST_HEAD(purge);
struct vmap_block *vb;
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
rcu_read_lock();
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
unsigned long free = READ_ONCE(vb->free);
unsigned long dirty = READ_ONCE(vb->dirty);
if (free + dirty != VMAP_BBMAP_BITS ||
dirty == VMAP_BBMAP_BITS)
continue;
spin_lock(&vb->lock);
purge_fragmented_block(vb, &purge, true);
spin_unlock(&vb->lock);
}
rcu_read_unlock();
free_purged_blocks(&purge);
}
static void purge_fragmented_blocks_allcpus(void)
{
int cpu;
for_each_possible_cpu(cpu)
purge_fragmented_blocks(cpu);
}
static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
{
struct vmap_block_queue *vbq;
struct vmap_block *vb;
void *vaddr = NULL;
unsigned int order;
BUG_ON(offset_in_page(size));
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
if (WARN_ON(size == 0)) {
/*
* Allocating 0 bytes isn't what caller wants since
* get_order(0) returns funny result. Just warn and terminate
* early.
*/
return ERR_PTR(-EINVAL);
}
order = get_order(size);
rcu_read_lock();
vbq = raw_cpu_ptr(&vmap_block_queue);
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
unsigned long pages_off;
if (READ_ONCE(vb->free) < (1UL << order))
continue;
spin_lock(&vb->lock);
if (vb->free < (1UL << order)) {
spin_unlock(&vb->lock);
continue;
}
pages_off = VMAP_BBMAP_BITS - vb->free;
vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
WRITE_ONCE(vb->free, vb->free - (1UL << order));
bitmap_set(vb->used_map, pages_off, (1UL << order));
if (vb->free == 0) {
spin_lock(&vbq->lock);
list_del_rcu(&vb->free_list);
spin_unlock(&vbq->lock);
}
spin_unlock(&vb->lock);
break;
}
rcu_read_unlock();
/* Allocate new block if nothing was found */
if (!vaddr)
vaddr = new_vmap_block(order, gfp_mask);
return vaddr;
}
static void vb_free(unsigned long addr, unsigned long size)
{
unsigned long offset;
unsigned int order;
struct vmap_block *vb;
struct xarray *xa;
BUG_ON(offset_in_page(size));
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
flush_cache_vunmap(addr, addr + size);
order = get_order(size);
offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT;
xa = addr_to_vb_xa(addr);
vb = xa_load(xa, addr_to_vb_idx(addr));
spin_lock(&vb->lock);
bitmap_clear(vb->used_map, offset, (1UL << order));
spin_unlock(&vb->lock);
vunmap_range_noflush(addr, addr + size);
if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range(addr, addr + size);
spin_lock(&vb->lock);
/* Expand the not yet TLB flushed dirty range */
vb->dirty_min = min(vb->dirty_min, offset);
vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));
WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order));
if (vb->dirty == VMAP_BBMAP_BITS) {
BUG_ON(vb->free);
spin_unlock(&vb->lock);
free_vmap_block(vb);
} else
spin_unlock(&vb->lock);
}
static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
{
LIST_HEAD(purge_list);
int cpu;
if (unlikely(!vmap_initialized))
return;
mutex_lock(&vmap_purge_lock);
for_each_possible_cpu(cpu) {
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
struct vmap_block *vb;
unsigned long idx;
rcu_read_lock();
xa_for_each(&vbq->vmap_blocks, idx, vb) {
spin_lock(&vb->lock);
/*
* Try to purge a fragmented block first. If it's
* not purgeable, check whether there is dirty
* space to be flushed.
*/
if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
unsigned long va_start = vb->va->va_start;
unsigned long s, e;
s = va_start + (vb->dirty_min << PAGE_SHIFT);
e = va_start + (vb->dirty_max << PAGE_SHIFT);
start = min(s, start);
end = max(e, end);
/* Prevent that this is flushed again */
vb->dirty_min = VMAP_BBMAP_BITS;
vb->dirty_max = 0;
flush = 1;
}
spin_unlock(&vb->lock);
}
rcu_read_unlock();
}
free_purged_blocks(&purge_list);
if (!__purge_vmap_area_lazy(start, end, false) && flush)
flush_tlb_kernel_range(start, end);
mutex_unlock(&vmap_purge_lock);
}
/**
* vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
*
* The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
* to amortize TLB flushing overheads. What this means is that any page you
* have now, may, in a former life, have been mapped into kernel virtual
* address by the vmap layer and so there might be some CPUs with TLB entries
* still referencing that page (additional to the regular 1:1 kernel mapping).
*
* vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
* be sure that none of the pages we have control over will have any aliases
* from the vmap layer.
*/
void vm_unmap_aliases(void)
{
unsigned long start = ULONG_MAX, end = 0;
int flush = 0;
_vm_unmap_aliases(start, end, flush);
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
/**
* vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
* @mem: the pointer returned by vm_map_ram
* @count: the count passed to that vm_map_ram call (cannot unmap partial)
*/
void vm_unmap_ram(const void *mem, unsigned int count)
{
unsigned long size = (unsigned long)count << PAGE_SHIFT;
unsigned long addr = (unsigned long)kasan_reset_tag(mem);
struct vmap_area *va;
might_sleep();
BUG_ON(!addr);
BUG_ON(addr < VMALLOC_START);
BUG_ON(addr > VMALLOC_END);
BUG_ON(!PAGE_ALIGNED(addr));
kasan_poison_vmalloc(mem, size);
if (likely(count <= VMAP_MAX_ALLOC)) {
debug_check_no_locks_freed(mem, size);
vb_free(addr, size);
return;
}
va = find_unlink_vmap_area(addr);
if (WARN_ON_ONCE(!va))
return;
debug_check_no_locks_freed((void *)va->va_start, va_size(va));
free_unmap_vmap_area(va);
}
EXPORT_SYMBOL(vm_unmap_ram);
/**
* vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
* @pages: an array of pointers to the pages to be mapped
* @count: number of pages
* @node: prefer to allocate data structures on this node
*
* If you use this function for less than VMAP_MAX_ALLOC pages, it could be
* faster than vmap so it's good. But if you mix long-life and short-life
* objects with vm_map_ram(), it could consume lots of address space through
* fragmentation (especially on a 32bit machine). You could see failures in
* the end. Please use this function for short-lived objects.
*
* Returns: a pointer to the address that has been mapped, or %NULL on failure
*/
void *vm_map_ram(struct page **pages, unsigned int count, int node)
{
unsigned long size = (unsigned long)count << PAGE_SHIFT;
unsigned long addr;
void *mem;
if (likely(count <= VMAP_MAX_ALLOC)) {
mem = vb_alloc(size, GFP_KERNEL);
if (IS_ERR(mem))
return NULL;
addr = (unsigned long)mem;
} else {
struct vmap_area *va;
va = alloc_vmap_area(size, PAGE_SIZE,
VMALLOC_START, VMALLOC_END,
node, GFP_KERNEL, VMAP_RAM,
NULL);
if (IS_ERR(va))
return NULL;
addr = va->va_start;
mem = (void *)addr;
}
if (vmap_pages_range(addr, addr + size, PAGE_KERNEL,
pages, PAGE_SHIFT) < 0) {
vm_unmap_ram(mem, count);
return NULL;
}
/*
* Mark the pages as accessible, now that they are mapped.
* With hardware tag-based KASAN, marking is skipped for
* non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/
mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL);
return mem;
}
EXPORT_SYMBOL(vm_map_ram);
static struct vm_struct *vmlist __initdata;
static inline unsigned int vm_area_page_order(struct vm_struct *vm)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
return vm->page_order;
#else
return 0;
#endif
}
unsigned int get_vm_area_page_order(struct vm_struct *vm)
{
return vm_area_page_order(vm);
}
static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
vm->page_order = order;
#else
BUG_ON(order != 0);
#endif
}
/**
* vm_area_add_early - add vmap area early during boot
* @vm: vm_struct to add
*
* This function is used to add fixed kernel vm area to vmlist before
* vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags
* should contain proper values and the other fields should be zero.
*
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
*/
void __init vm_area_add_early(struct vm_struct *vm)
{
struct vm_struct *tmp, **p;
BUG_ON(vmap_initialized);
for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
if (tmp->addr >= vm->addr) {
BUG_ON(tmp->addr < vm->addr + vm->size);
break;
} else
BUG_ON(tmp->addr + tmp->size > vm->addr);
}
vm->next = *p;
*p = vm;
}
/**
* vm_area_register_early - register vmap area early during boot
* @vm: vm_struct to register
* @align: requested alignment
*
* This function is used to register kernel vm area before
* vmalloc_init() is called. @vm->size and @vm->flags should contain
* proper values on entry and other fields should be zero. On return,
* vm->addr contains the allocated address.
*
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
*/
void __init vm_area_register_early(struct vm_struct *vm, size_t align)
{
unsigned long addr = ALIGN(VMALLOC_START, align);
struct vm_struct *cur, **p;
BUG_ON(vmap_initialized);
for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) {
if ((unsigned long)cur->addr - addr >= vm->size)
break;
addr = ALIGN((unsigned long)cur->addr + cur->size, align);
}
BUG_ON(addr > VMALLOC_END - vm->size);
vm->addr = (void *)addr;
vm->next = *p;
*p = vm;
kasan_populate_early_vm_area_shadow(vm->addr, vm->size);
}
static void clear_vm_uninitialized_flag(struct vm_struct *vm)
{
/*
* Before removing VM_UNINITIALIZED,
* we should make sure that vm has proper values.
* Pair with smp_rmb() in show_numa_info().
*/
smp_wmb();
vm->flags &= ~VM_UNINITIALIZED;
}
struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long align, unsigned long shift, unsigned long flags,
unsigned long start, unsigned long end, int node,
gfp_t gfp_mask, const void *caller)
{
struct vmap_area *va;
struct vm_struct *area;
unsigned long requested_size = size;
BUG_ON(in_interrupt());
size = ALIGN(size, 1ul << shift);
if (unlikely(!size))
return NULL;
if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size),
PAGE_SHIFT, IOREMAP_MAX_ORDER);
area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!area))
return NULL;
if (!(flags & VM_NO_GUARD))
size += PAGE_SIZE;
area->flags = flags;
area->caller = caller;
va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
if (IS_ERR(va)) {
kfree(area);
return NULL;
}
/*
* Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a
* best-effort approach, as they can be mapped outside of vmalloc code.
* For VM_ALLOC mappings, the pages are marked as accessible after
* getting mapped in __vmalloc_node_range().
* With hardware tag-based KASAN, marking is skipped for
* non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/
if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size,
KASAN_VMALLOC_PROT_NORMAL);
return area;
}
struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end,
const void *caller)
{
return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end,
NUMA_NO_NODE, GFP_KERNEL, caller);
}
/**
* get_vm_area - reserve a contiguous kernel virtual area
* @size: size of the area
* @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
*
* Search an area of @size in the kernel virtual mapping area,
* and reserved it for out purposes. Returns the area descriptor
* on success or %NULL on failure.
*
* Return: the area descriptor on success or %NULL on failure.
*/
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
VMALLOC_START, VMALLOC_END,
NUMA_NO_NODE, GFP_KERNEL,
__builtin_return_address(0));
}
struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
const void *caller)
{
return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
VMALLOC_START, VMALLOC_END,
NUMA_NO_NODE, GFP_KERNEL, caller);
}
/**
* find_vm_area - find a continuous kernel virtual area
* @addr: base address
*
* Search for the kernel VM area starting at @addr, and return it.
* It is up to the caller to do all required locking to keep the returned
* pointer valid.
*
* Return: the area descriptor on success or %NULL on failure.
*/
struct vm_struct *find_vm_area(const void *addr)
{
struct vmap_area *va;
va = find_vmap_area((unsigned long)addr);
if (!va)
return NULL;
return va->vm;
}
/**
* remove_vm_area - find and remove a continuous kernel virtual area
* @addr: base address
*
* Search for the kernel VM area starting at @addr, and remove it.
* This function returns the found VM area, but using it is NOT safe
* on SMP machines, except for its size or flags.
*
* Return: the area descriptor on success or %NULL on failure.
*/
struct vm_struct *remove_vm_area(const void *addr)
{
struct vmap_area *va;
struct vm_struct *vm;
might_sleep();
if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
addr))
return NULL;
va = find_unlink_vmap_area((unsigned long)addr);
if (!va || !va->vm)
return NULL;
vm = va->vm;
debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm));
debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm));
kasan_free_module_shadow(vm);
kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm));
free_unmap_vmap_area(va);
return vm;
}
static inline void set_area_direct_map(const struct vm_struct *area,
int (*set_direct_map)(struct page *page))
{
int i;
/* HUGE_VMALLOC passes small pages to set_direct_map */
for (i = 0; i < area->nr_pages; i++)
if (page_address(area->pages[i]))
set_direct_map(area->pages[i]);
}
/*
* Flush the vm mapping and reset the direct map.
*/
static void vm_reset_perms(struct vm_struct *area)
{
unsigned long start = ULONG_MAX, end = 0;
unsigned int page_order = vm_area_page_order(area);
int flush_dmap = 0;
int i;
/*
* Find the start and end range of the direct mappings to make sure that
* the vm_unmap_aliases() flush includes the direct map.
*/
for (i = 0; i < area->nr_pages; i += 1U << page_order) {
unsigned long addr = (unsigned long)page_address(area->pages[i]);
if (addr) {
unsigned long page_size;
page_size = PAGE_SIZE << page_order;
start = min(addr, start);
end = max(addr + page_size, end);
flush_dmap = 1;
}
}
/*
* Set direct map to something invalid so that it won't be cached if
* there are any accesses after the TLB flush, then flush the TLB and
* reset the direct map permissions to the default.
*/
set_area_direct_map(area, set_direct_map_invalid_noflush);
_vm_unmap_aliases(start, end, flush_dmap);
set_area_direct_map(area, set_direct_map_default_noflush);
}
static void delayed_vfree_work(struct work_struct *w)
{
struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
struct llist_node *t, *llnode;
llist_for_each_safe(llnode, t, llist_del_all(&p->list))
vfree(llnode);
}
/**
* vfree_atomic - release memory allocated by vmalloc()
* @addr: memory base address
*
* This one is just like vfree() but can be called in any atomic context
* except NMIs.
*/
void vfree_atomic(const void *addr)
{
struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred);
BUG_ON(in_nmi());
kmemleak_free(addr);
/*
* Use raw_cpu_ptr() because this can be called from preemptible
* context. Preemption is absolutely fine here, because the llist_add()
* implementation is lockless, so it works even if we are adding to
* another cpu's list. schedule_work() should be fine with this too.
*/
if (addr && llist_add((struct llist_node *)addr, &p->list))
schedule_work(&p->wq);
}
/**
* vfree - Release memory allocated by vmalloc()
* @addr: Memory base address
*
* Free the virtually continuous memory area starting at @addr, as obtained
* from one of the vmalloc() family of APIs. This will usually also free the
* physical memory underlying the virtual allocation, but that memory is
* reference counted, so it will not be freed until the last user goes away.
*
* If @addr is NULL, no operation is performed.
*
* Context:
* May sleep if called *not* from interrupt context.
* Must not be called in NMI context (strictly speaking, it could be
* if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
* conventions for vfree() arch-dependent would be a really bad idea).
*/
void vfree(const void *addr)
{
struct vm_struct *vm;
int i;
if (unlikely(in_interrupt())) {
vfree_atomic(addr);
return;
}
BUG_ON(in_nmi());
kmemleak_free(addr);
might_sleep();
if (!addr)
return;
vm = remove_vm_area(addr);
if (unlikely(!vm)) {
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr);
return;
}
if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); for (i = 0; i < vm->nr_pages; i++) {
struct page *page = vm->pages[i];
BUG_ON(!page); if (!(vm->flags & VM_MAP_PUT_PAGES)) mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
/*
* High-order allocs for huge vmallocs are split, so
* can be freed as an array of order-0 allocations
*/
__free_page(page);
cond_resched();
}
if (!(vm->flags & VM_MAP_PUT_PAGES)) atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
kvfree(vm->pages);
kfree(vm);
}
EXPORT_SYMBOL(vfree);
/**
* vunmap - release virtual mapping obtained by vmap()
* @addr: memory base address
*
* Free the virtually contiguous memory area starting at @addr,
* which was created from the page array passed to vmap().
*
* Must not be called in interrupt context.
*/
void vunmap(const void *addr)
{
struct vm_struct *vm;
BUG_ON(in_interrupt());
might_sleep();
if (!addr)
return;
vm = remove_vm_area(addr);
if (unlikely(!vm)) {
WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n",
addr);
return;
}
kfree(vm);
}
EXPORT_SYMBOL(vunmap);
/**
* vmap - map an array of pages into virtually contiguous space
* @pages: array of page pointers
* @count: number of pages to map
* @flags: vm_area->flags
* @prot: page protection for the mapping
*
* Maps @count pages from @pages into contiguous kernel virtual space.
* If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself
* (which must be kmalloc or vmalloc memory) and one reference per pages in it
* are transferred from the caller to vmap(), and will be freed / dropped when
* vfree() is called on the return value.
*
* Return: the address of the area or %NULL on failure
*/
void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot)
{
struct vm_struct *area;
unsigned long addr;
unsigned long size; /* In bytes */
might_sleep();
if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS))
return NULL;
/*
* Your top guard is someone else's bottom guard. Not having a top
* guard compromises someone else's mappings too.
*/
if (WARN_ON_ONCE(flags & VM_NO_GUARD))
flags &= ~VM_NO_GUARD;
if (count > totalram_pages())
return NULL;
size = (unsigned long)count << PAGE_SHIFT;
area = get_vm_area_caller(size, flags, __builtin_return_address(0));
if (!area)
return NULL;
addr = (unsigned long)area->addr;
if (vmap_pages_range(addr, addr + size, pgprot_nx(prot),
pages, PAGE_SHIFT) < 0) {
vunmap(area->addr);
return NULL;
}
if (flags & VM_MAP_PUT_PAGES) {
area->pages = pages;
area->nr_pages = count;
}
return area->addr;
}
EXPORT_SYMBOL(vmap);
#ifdef CONFIG_VMAP_PFN
struct vmap_pfn_data {
unsigned long *pfns;
pgprot_t prot;
unsigned int idx;
};
static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private)
{
struct vmap_pfn_data *data = private;
unsigned long pfn = data->pfns[data->idx];
pte_t ptent;
if (WARN_ON_ONCE(pfn_valid(pfn)))
return -EINVAL;
ptent = pte_mkspecial(pfn_pte(pfn, data->prot));
set_pte_at(&init_mm, addr, pte, ptent);
data->idx++;
return 0;
}
/**
* vmap_pfn - map an array of PFNs into virtually contiguous space
* @pfns: array of PFNs
* @count: number of pages to map
* @prot: page protection for the mapping
*
* Maps @count PFNs from @pfns into contiguous kernel virtual space and returns
* the start address of the mapping.
*/
void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
{
struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) };
struct vm_struct *area;
area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
__builtin_return_address(0));
if (!area)
return NULL;
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
count * PAGE_SIZE, vmap_pfn_apply, &data)) {
free_vm_area(area);
return NULL;
}
flush_cache_vmap((unsigned long)area->addr,
(unsigned long)area->addr + count * PAGE_SIZE);
return area->addr;
}
EXPORT_SYMBOL_GPL(vmap_pfn);
#endif /* CONFIG_VMAP_PFN */
static inline unsigned int
vm_area_alloc_pages(gfp_t gfp, int nid,
unsigned int order, unsigned int nr_pages, struct page **pages)
{
unsigned int nr_allocated = 0;
struct page *page;
int i;
/*
* For order-0 pages we make use of bulk allocator, if
* the page array is partly or not at all populated due
* to fails, fallback to a single page allocator that is
* more permissive.
*/
if (!order) {
while (nr_allocated < nr_pages) {
unsigned int nr, nr_pages_request;
/*
* A maximum allowed request is hard-coded and is 100
* pages per call. That is done in order to prevent a
* long preemption off scenario in the bulk-allocator
* so the range is [1:100].
*/
nr_pages_request = min(100U, nr_pages - nr_allocated);
/* memory allocation should consider mempolicy, we can't
* wrongly use nearest node when nid == NUMA_NO_NODE,
* otherwise memory may be allocated in only one node,
* but mempolicy wants to alloc memory by interleaving.
*/
if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
nr = alloc_pages_bulk_mempolicy_noprof(gfp,
nr_pages_request,
pages + nr_allocated);
else
nr = alloc_pages_bulk_node_noprof(gfp, nid,
nr_pages_request,
pages + nr_allocated);
nr_allocated += nr;
cond_resched();
/*
* If zero or pages were obtained partly,
* fallback to a single page allocator.
*/
if (nr != nr_pages_request)
break;
}
}
/* High-order pages or fallback path if "bulk" fails. */
while (nr_allocated < nr_pages) { if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current))
break;
if (nid == NUMA_NO_NODE)
page = alloc_pages_noprof(gfp, order);
else
page = alloc_pages_node_noprof(nid, gfp, order);
if (unlikely(!page))
break;
/*
* High-order allocations must be able to be treated as
* independent small pages by callers (as they can with
* small-page vmallocs). Some drivers do their own refcounting
* on vmalloc_to_page() pages, some use page->mapping,
* page->lru, etc.
*/
if (order)
split_page(page, order);
/*
* Careful, we allocate and map page-order pages, but
* tracking is done per PAGE_SIZE page so as to keep the
* vm_struct APIs independent of the physical/mapped size.
*/
for (i = 0; i < (1U << order); i++)
pages[nr_allocated + i] = page + i;
cond_resched();
nr_allocated += 1U << order;
}
return nr_allocated;
}
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
pgprot_t prot, unsigned int page_shift,
int node)
{
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
bool nofail = gfp_mask & __GFP_NOFAIL;
unsigned long addr = (unsigned long)area->addr;
unsigned long size = get_vm_area_size(area);
unsigned long array_size;
unsigned int nr_small_pages = size >> PAGE_SHIFT;
unsigned int page_order;
unsigned int flags;
int ret;
array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
gfp_mask |= __GFP_HIGHMEM;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node,
area->caller);
} else {
area->pages = kmalloc_node_noprof(array_size, nested_gfp, node);
}
if (!area->pages) {
warn_alloc(gfp_mask, NULL,
"vmalloc error: size %lu, failed to allocated page array size %lu",
nr_small_pages * PAGE_SIZE, array_size);
free_vm_area(area);
return NULL;
}
set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
page_order = vm_area_page_order(area);
/*
* High-order nofail allocations are really expensive and
* potentially dangerous (pre-mature OOM, disruptive reclaim
* and compaction etc.
*
* Please note, the __vmalloc_node_range_noprof() falls-back
* to order-0 pages if high-order attempt is unsuccessful.
*/
area->nr_pages = vm_area_alloc_pages((page_order ?
gfp_mask & ~__GFP_NOFAIL : gfp_mask) | __GFP_NOWARN,
node, page_order, nr_small_pages, area->pages);
atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) {
int i;
for (i = 0; i < area->nr_pages; i++)
mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1);
}
/*
* If not enough pages were obtained to accomplish an
* allocation request, free them via vfree() if any.
*/
if (area->nr_pages != nr_small_pages) {
/*
* vm_area_alloc_pages() can fail due to insufficient memory but
* also:-
*
* - a pending fatal signal
* - insufficient huge page-order pages
*
* Since we always retry allocations at order-0 in the huge page
* case a warning for either is spurious.
*/
if (!fatal_signal_pending(current) && page_order == 0)
warn_alloc(gfp_mask, NULL,
"vmalloc error: size %lu, failed to allocate pages",
area->nr_pages * PAGE_SIZE);
goto fail;
}
/*
* page tables allocations ignore external gfp mask, enforce it
* by the scope API
*/
if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
flags = memalloc_nofs_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) flags = memalloc_noio_save();
do {
ret = vmap_pages_range(addr, addr + size, prot, area->pages,
page_shift);
if (nofail && (ret < 0))
schedule_timeout_uninterruptible(1);
} while (nofail && (ret < 0));
if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
memalloc_nofs_restore(flags); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) memalloc_noio_restore(flags);
if (ret < 0) {
warn_alloc(gfp_mask, NULL,
"vmalloc error: size %lu, failed to map pages",
area->nr_pages * PAGE_SIZE);
goto fail;
}
return area->addr;
fail:
vfree(area->addr);
return NULL;
}
/**
* __vmalloc_node_range - allocate virtually contiguous memory
* @size: allocation size
* @align: desired alignment
* @start: vm area range start
* @end: vm area range end
* @gfp_mask: flags for the page level allocator
* @prot: protection mask for the allocated pages
* @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD)
* @node: node to use for allocation or NUMA_NO_NODE
* @caller: caller's return address
*
* Allocate enough pages to cover @size from the page level
* allocator with @gfp_mask flags. Please note that the full set of gfp
* flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all
* supported.
* Zone modifiers are not supported. From the reclaim modifiers
* __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported)
* and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and
* __GFP_RETRY_MAYFAIL are not supported).
*
* __GFP_NOWARN can be used to suppress failures messages.
*
* Map them into contiguous kernel virtual space, using a pagetable
* protection of @prot.
*
* Return: the address of the area or %NULL on failure
*/
void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align,
unsigned long start, unsigned long end, gfp_t gfp_mask,
pgprot_t prot, unsigned long vm_flags, int node,
const void *caller)
{
struct vm_struct *area;
void *ret;
kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE;
unsigned long original_align = align;
unsigned int shift = PAGE_SHIFT;
if (WARN_ON_ONCE(!size))
return NULL;
if ((size >> PAGE_SHIFT) > totalram_pages()) {
warn_alloc(gfp_mask, NULL,
"vmalloc error: size %lu, exceeds total pages",
size);
return NULL;
}
if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) {
/*
* Try huge pages. Only try for PAGE_KERNEL allocations,
* others like modules don't yet expect huge pages in
* their allocations due to apply_to_page_range not
* supporting them.
*/
if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE)
shift = PMD_SHIFT;
else
shift = arch_vmap_pte_supported_shift(size);
align = max(original_align, 1UL << shift);
}
again:
area = __get_vm_area_node(size, align, shift, VM_ALLOC |
VM_UNINITIALIZED | vm_flags, start, end, node,
gfp_mask, caller);
if (!area) {
bool nofail = gfp_mask & __GFP_NOFAIL;
warn_alloc(gfp_mask, NULL,
"vmalloc error: size %lu, vm_struct allocation failed%s",
size, (nofail) ? ". Retrying." : "");
if (nofail) {
schedule_timeout_uninterruptible(1);
goto again;
}
goto fail;
}
/*
* Prepare arguments for __vmalloc_area_node() and
* kasan_unpoison_vmalloc().
*/
if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
if (kasan_hw_tags_enabled()) {
/*
* Modify protection bits to allow tagging.
* This must be done before mapping.
*/
prot = arch_vmap_pgprot_tagged(prot);
/*
* Skip page_alloc poisoning and zeroing for physical
* pages backing VM_ALLOC mapping. Memory is instead
* poisoned and zeroed by kasan_unpoison_vmalloc().
*/
gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO;
}
/* Take note that the mapping is PAGE_KERNEL. */
kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;
}
/* Allocate physical pages and map them into vmalloc space. */
ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret)
goto fail;
/*
* Mark the pages as accessible, now that they are mapped.
* The condition for setting KASAN_VMALLOC_INIT should complement the
* one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check
* to make sure that memory is initialized under the same conditions.
* Tag-based KASAN modes only assign tags to normal non-executable
* allocations, see __kasan_unpoison_vmalloc().
*/
kasan_flags |= KASAN_VMALLOC_VM_ALLOC;
if (!want_init_on_free() && want_init_on_alloc(gfp_mask) &&
(gfp_mask & __GFP_SKIP_ZERO))
kasan_flags |= KASAN_VMALLOC_INIT;
/* KASAN_VMALLOC_PROT_NORMAL already set if required. */
area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags);
/*
* In this function, newly allocated vm_struct has VM_UNINITIALIZED
* flag. It means that vm_struct is not fully initialized.
* Now, it is fully initialized, so remove this flag here.
*/
clear_vm_uninitialized_flag(area);
if (!(vm_flags & VM_DEFER_KMEMLEAK))
kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask);
return area->addr;
fail:
if (shift > PAGE_SHIFT) {
shift = PAGE_SHIFT;
align = original_align;
goto again;
}
return NULL;
}
/**
* __vmalloc_node - allocate virtually contiguous memory
* @size: allocation size
* @align: desired alignment
* @gfp_mask: flags for the page level allocator
* @node: node to use for allocation or NUMA_NO_NODE
* @caller: caller's return address
*
* Allocate enough pages to cover @size from the page level allocator with
* @gfp_mask flags. Map them into contiguous kernel virtual space.
*
* Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
* and __GFP_NOFAIL are not supported
*
* Any use of gfp flags outside of GFP_KERNEL should be consulted
* with mm people.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *__vmalloc_node_noprof(unsigned long size, unsigned long align,
gfp_t gfp_mask, int node, const void *caller)
{
return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END,
gfp_mask, PAGE_KERNEL, 0, node, caller);
}
/*
* This is only for performance analysis of vmalloc and stress purpose.
* It is required by vmalloc test module, therefore do not use it other
* than that.
*/
#ifdef CONFIG_TEST_VMALLOC_MODULE
EXPORT_SYMBOL_GPL(__vmalloc_node_noprof);
#endif
void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask)
{
return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc_noprof);
/**
* vmalloc - allocate virtually contiguous memory
* @size: allocation size
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_noprof(unsigned long size)
{
return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_noprof);
/**
* vmalloc_huge - allocate virtually contiguous memory, allow huge pages
* @size: allocation size
* @gfp_mask: flags for the page level allocator
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
* If @size is greater than or equal to PMD_SIZE, allow using
* huge pages for the memory
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask)
{
return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END,
gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP,
NUMA_NO_NODE, __builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(vmalloc_huge_noprof);
/**
* vzalloc - allocate virtually contiguous memory with zero fill
* @size: allocation size
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
* The memory allocated is set to zero.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vzalloc_noprof(unsigned long size)
{
return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_noprof);
/**
* vmalloc_user - allocate zeroed virtually contiguous memory for userspace
* @size: allocation size
*
* The resulting memory area is zeroed so it can be mapped to userspace
* without leaking data.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_user_noprof(unsigned long size)
{
return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user_noprof);
/**
* vmalloc_node - allocate memory on a specific node
* @size: allocation size
* @node: numa node
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_node_noprof(unsigned long size, int node)
{
return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node_noprof);
/**
* vzalloc_node - allocate memory on a specific node with zero fill
* @size: allocation size
* @node: numa node
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
* The memory allocated is set to zero.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vzalloc_node_noprof(unsigned long size, int node)
{
return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_node_noprof);
/**
* vrealloc - reallocate virtually contiguous memory; contents remain unchanged
* @p: object to reallocate memory for
* @size: the size to reallocate
* @flags: the flags for the page level allocator
*
* If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and
* @p is not a %NULL pointer, the object pointed to is freed.
*
* If __GFP_ZERO logic is requested, callers must ensure that, starting with the
* initial memory allocation, every subsequent call to this API for the same
* memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
* __GFP_ZERO is not fully honored by this API.
*
* In any case, the contents of the object pointed to are preserved up to the
* lesser of the new and old sizes.
*
* This function must not be called concurrently with itself or vfree() for the
* same memory allocation.
*
* Return: pointer to the allocated memory; %NULL if @size is zero or in case of
* failure
*/
void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
{
size_t old_size = 0;
void *n;
if (!size) {
vfree(p);
return NULL;
}
if (p) {
struct vm_struct *vm;
vm = find_vm_area(p);
if (unlikely(!vm)) {
WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
return NULL;
}
old_size = get_vm_area_size(vm);
}
/*
* TODO: Shrink the vm_area, i.e. unmap and free unused pages. What
* would be a good heuristic for when to shrink the vm_area?
*/
if (size <= old_size) {
/* Zero out spare memory. */
if (want_init_on_alloc(flags))
memset((void *)p + size, 0, old_size - size);
kasan_poison_vmalloc(p + size, old_size - size);
kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
return (void *)p;
}
/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
n = __vmalloc_noprof(size, flags);
if (!n)
return NULL;
if (p) {
memcpy(n, p, old_size);
vfree(p);
}
return n;
}
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL)
#else
/*
* 64b systems should always have either DMA or DMA32 zones. For others
* GFP_DMA32 should do the right thing and use the normal zone.
*/
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#endif
/**
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
* @size: allocation size
*
* Allocate enough 32bit PA addressable pages to cover @size from the
* page level allocator and map them into contiguous kernel virtual space.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_32_noprof(unsigned long size)
{
return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_noprof);
/**
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
* @size: allocation size
*
* The resulting memory area is 32bit addressable and zeroed so it can be
* mapped to userspace without leaking data.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_32_user_noprof(unsigned long size)
{
return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_user_noprof);
/*
* Atomically zero bytes in the iterator.
*
* Returns the number of zeroed bytes.
*/
static size_t zero_iter(struct iov_iter *iter, size_t count)
{
size_t remains = count;
while (remains > 0) {
size_t num, copied;
num = min_t(size_t, remains, PAGE_SIZE);
copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter);
remains -= copied;
if (copied < num)
break;
}
return count - remains;
}
/*
* small helper routine, copy contents to iter from addr.
* If the page is not present, fill zero.
*
* Returns the number of copied bytes.
*/
static size_t aligned_vread_iter(struct iov_iter *iter,
const char *addr, size_t count)
{
size_t remains = count;
struct page *page;
while (remains > 0) {
unsigned long offset, length;
size_t copied = 0;
offset = offset_in_page(addr);
length = PAGE_SIZE - offset;
if (length > remains)
length = remains;
page = vmalloc_to_page(addr);
/*
* To do safe access to this _mapped_ area, we need lock. But
* adding lock here means that we need to add overhead of
* vmalloc()/vfree() calls for this _debug_ interface, rarely
* used. Instead of that, we'll use an local mapping via
* copy_page_to_iter_nofault() and accept a small overhead in
* this access function.
*/
if (page)
copied = copy_page_to_iter_nofault(page, offset,
length, iter);
else
copied = zero_iter(iter, length);
addr += copied;
remains -= copied;
if (copied != length)
break;
}
return count - remains;
}
/*
* Read from a vm_map_ram region of memory.
*
* Returns the number of copied bytes.
*/
static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr,
size_t count, unsigned long flags)
{
char *start;
struct vmap_block *vb;
struct xarray *xa;
unsigned long offset;
unsigned int rs, re;
size_t remains, n;
/*
* If it's area created by vm_map_ram() interface directly, but
* not further subdividing and delegating management to vmap_block,
* handle it here.
*/
if (!(flags & VMAP_BLOCK))
return aligned_vread_iter(iter, addr, count);
remains = count;
/*
* Area is split into regions and tracked with vmap_block, read out
* each region and zero fill the hole between regions.
*/
xa = addr_to_vb_xa((unsigned long) addr);
vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr));
if (!vb)
goto finished_zero;
spin_lock(&vb->lock);
if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) {
spin_unlock(&vb->lock);
goto finished_zero;
}
for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) {
size_t copied;
if (remains == 0)
goto finished;
start = vmap_block_vaddr(vb->va->va_start, rs);
if (addr < start) {
size_t to_zero = min_t(size_t, start - addr, remains);
size_t zeroed = zero_iter(iter, to_zero);
addr += zeroed;
remains -= zeroed;
if (remains == 0 || zeroed != to_zero)
goto finished;
}
/*it could start reading from the middle of used region*/
offset = offset_in_page(addr);
n = ((re - rs + 1) << PAGE_SHIFT) - offset;
if (n > remains)
n = remains;
copied = aligned_vread_iter(iter, start + offset, n);
addr += copied;
remains -= copied;
if (copied != n)
goto finished;
}
spin_unlock(&vb->lock);
finished_zero:
/* zero-fill the left dirty or free regions */
return count - remains + zero_iter(iter, remains);
finished:
/* We couldn't copy/zero everything */
spin_unlock(&vb->lock);
return count - remains;
}
/**
* vread_iter() - read vmalloc area in a safe way to an iterator.
* @iter: the iterator to which data should be written.
* @addr: vm address.
* @count: number of bytes to be read.
*
* This function checks that addr is a valid vmalloc'ed area, and
* copy data from that area to a given buffer. If the given memory range
* of [addr...addr+count) includes some valid address, data is copied to
* proper area of @buf. If there are memory holes, they'll be zero-filled.
* IOREMAP area is treated as memory hole and no copy is done.
*
* If [addr...addr+count) doesn't includes any intersects with alive
* vm_struct area, returns 0. @buf should be kernel's buffer.
*
* Note: In usual ops, vread() is never necessary because the caller
* should know vmalloc() area is valid and can use memcpy().
* This is for routines which have to access vmalloc area without
* any information, as /proc/kcore.
*
* Return: number of bytes for which addr and buf should be increased
* (same number as @count) or %0 if [addr...addr+count) doesn't
* include any intersection with valid vmalloc area
*/
long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
{
struct vmap_node *vn;
struct vmap_area *va;
struct vm_struct *vm;
char *vaddr;
size_t n, size, flags, remains;
unsigned long next;
addr = kasan_reset_tag(addr);
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
remains = count;
vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va);
if (!vn)
goto finished_zero;
/* no intersects with alive vmap_area */
if ((unsigned long)addr + remains <= va->va_start)
goto finished_zero;
do {
size_t copied;
if (remains == 0)
goto finished;
vm = va->vm;
flags = va->flags & VMAP_FLAGS_MASK;
/*
* VMAP_BLOCK indicates a sub-type of vm_map_ram area, need
* be set together with VMAP_RAM.
*/
WARN_ON(flags == VMAP_BLOCK);
if (!vm && !flags)
goto next_va;
if (vm && (vm->flags & VM_UNINITIALIZED))
goto next_va;
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
smp_rmb();
vaddr = (char *) va->va_start;
size = vm ? get_vm_area_size(vm) : va_size(va);
if (addr >= vaddr + size)
goto next_va;
if (addr < vaddr) {
size_t to_zero = min_t(size_t, vaddr - addr, remains);
size_t zeroed = zero_iter(iter, to_zero);
addr += zeroed;
remains -= zeroed;
if (remains == 0 || zeroed != to_zero)
goto finished;
}
n = vaddr + size - addr;
if (n > remains)
n = remains;
if (flags & VMAP_RAM)
copied = vmap_ram_vread_iter(iter, addr, n, flags);
else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE))))
copied = aligned_vread_iter(iter, addr, n);
else /* IOREMAP | SPARSE area is treated as memory hole */
copied = zero_iter(iter, n);
addr += copied;
remains -= copied;
if (copied != n)
goto finished;
next_va:
next = va->va_end;
spin_unlock(&vn->busy.lock);
} while ((vn = find_vmap_area_exceed_addr_lock(next, &va)));
finished_zero:
if (vn)
spin_unlock(&vn->busy.lock);
/* zero-fill memory holes */
return count - remains + zero_iter(iter, remains);
finished:
/* Nothing remains, or We couldn't copy/zero everything. */
if (vn)
spin_unlock(&vn->busy.lock);
return count - remains;
}
/**
* remap_vmalloc_range_partial - map vmalloc pages to userspace
* @vma: vma to cover
* @uaddr: target user address to start at
* @kaddr: virtual address of vmalloc kernel memory
* @pgoff: offset from @kaddr to start at
* @size: size of map area
*
* Returns: 0 for success, -Exxx on failure
*
* This function checks that @kaddr is a valid vmalloc'ed area,
* and that it is big enough to cover the range starting at
* @uaddr in @vma. Will return failure if that criteria isn't
* met.
*
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
void *kaddr, unsigned long pgoff,
unsigned long size)
{
struct vm_struct *area;
unsigned long off;
unsigned long end_index;
if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
return -EINVAL;
size = PAGE_ALIGN(size);
if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
return -EINVAL;
area = find_vm_area(kaddr);
if (!area)
return -EINVAL;
if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
return -EINVAL;
if (check_add_overflow(size, off, &end_index) ||
end_index > get_vm_area_size(area))
return -EINVAL;
kaddr += off;
do {
struct page *page = vmalloc_to_page(kaddr);
int ret;
ret = vm_insert_page(vma, uaddr, page);
if (ret)
return ret;
uaddr += PAGE_SIZE;
kaddr += PAGE_SIZE;
size -= PAGE_SIZE;
} while (size > 0);
vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
return 0;
}
/**
* remap_vmalloc_range - map vmalloc pages to userspace
* @vma: vma to cover (map full range of vma)
* @addr: vmalloc memory
* @pgoff: number of pages into addr before first page to map
*
* Returns: 0 for success, -Exxx on failure
*
* This function checks that addr is a valid vmalloc'ed area, and
* that it is big enough to cover the vma. Will return failure if
* that criteria isn't met.
*
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff)
{
return remap_vmalloc_range_partial(vma, vma->vm_start,
addr, pgoff,
vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);
void free_vm_area(struct vm_struct *area)
{
struct vm_struct *ret;
ret = remove_vm_area(area->addr);
BUG_ON(ret != area); kfree(area);
}
EXPORT_SYMBOL_GPL(free_vm_area);
#ifdef CONFIG_SMP
static struct vmap_area *node_to_va(struct rb_node *n)
{
return rb_entry_safe(n, struct vmap_area, rb_node);
}
/**
* pvm_find_va_enclose_addr - find the vmap_area @addr belongs to
* @addr: target address
*
* Returns: vmap_area if it is found. If there is no such area
* the first highest(reverse order) vmap_area is returned
* i.e. va->va_start < addr && va->va_end < addr or NULL
* if there are no any areas before @addr.
*/
static struct vmap_area *
pvm_find_va_enclose_addr(unsigned long addr)
{
struct vmap_area *va, *tmp;
struct rb_node *n;
n = free_vmap_area_root.rb_node;
va = NULL;
while (n) {
tmp = rb_entry(n, struct vmap_area, rb_node);
if (tmp->va_start <= addr) {
va = tmp;
if (tmp->va_end >= addr)
break;
n = n->rb_right;
} else {
n = n->rb_left;
}
}
return va;
}
/**
* pvm_determine_end_from_reverse - find the highest aligned address
* of free block below VMALLOC_END
* @va:
* in - the VA we start the search(reverse order);
* out - the VA with the highest aligned end address.
* @align: alignment for required highest address
*
* Returns: determined end address within vmap_area
*/
static unsigned long
pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align)
{
unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
unsigned long addr;
if (likely(*va)) {
list_for_each_entry_from_reverse((*va),
&free_vmap_area_list, list) {
addr = min((*va)->va_end & ~(align - 1), vmalloc_end);
if ((*va)->va_start < addr)
return addr;
}
}
return 0;
}
/**
* pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
* @offsets: array containing offset of each area
* @sizes: array containing size of each area
* @nr_vms: the number of areas to allocate
* @align: alignment, all entries in @offsets and @sizes must be aligned to this
*
* Returns: kmalloc'd vm_struct pointer array pointing to allocated
* vm_structs on success, %NULL on failure
*
* Percpu allocator wants to use congruent vm areas so that it can
* maintain the offsets among percpu areas. This function allocates
* congruent vmalloc areas for it with GFP_KERNEL. These areas tend to
* be scattered pretty far, distance between two areas easily going up
* to gigabytes. To avoid interacting with regular vmallocs, these
* areas are allocated from top.
*
* Despite its complicated look, this allocator is rather simple. It
* does everything top-down and scans free blocks from the end looking
* for matching base. While scanning, if any of the areas do not fit the
* base address is pulled down to fit the area. Scanning is repeated till
* all the areas fit and then all necessary data structures are inserted
* and the result is returned.
*/
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align)
{
const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
struct vmap_area **vas, *va;
struct vm_struct **vms;
int area, area2, last_area, term_area;
unsigned long base, start, size, end, last_end, orig_start, orig_end;
bool purged = false;
/* verify parameters and allocate data structures */
BUG_ON(offset_in_page(align) || !is_power_of_2(align));
for (last_area = 0, area = 0; area < nr_vms; area++) {
start = offsets[area];
end = start + sizes[area];
/* is everything aligned properly? */
BUG_ON(!IS_ALIGNED(offsets[area], align));
BUG_ON(!IS_ALIGNED(sizes[area], align));
/* detect the area with the highest address */
if (start > offsets[last_area])
last_area = area;
for (area2 = area + 1; area2 < nr_vms; area2++) {
unsigned long start2 = offsets[area2];
unsigned long end2 = start2 + sizes[area2];
BUG_ON(start2 < end && start < end2);
}
}
last_end = offsets[last_area] + sizes[last_area];
if (vmalloc_end - vmalloc_start < last_end) {
WARN_ON(true);
return NULL;
}
vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL);
vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL);
if (!vas || !vms)
goto err_free2;
for (area = 0; area < nr_vms; area++) {
vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL);
vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL);
if (!vas[area] || !vms[area])
goto err_free;
}
retry:
spin_lock(&free_vmap_area_lock);
/* start scanning - we scan from the top, begin with the last area */
area = term_area = last_area;
start = offsets[area];
end = start + sizes[area];
va = pvm_find_va_enclose_addr(vmalloc_end);
base = pvm_determine_end_from_reverse(&va, align) - end;
while (true) {
/*
* base might have underflowed, add last_end before
* comparing.
*/
if (base + last_end < vmalloc_start + last_end)
goto overflow;
/*
* Fitting base has not been found.
*/
if (va == NULL)
goto overflow;
/*
* If required width exceeds current VA block, move
* base downwards and then recheck.
*/
if (base + end > va->va_end) {
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area;
continue;
}
/*
* If this VA does not fit, move base downwards and recheck.
*/
if (base + start < va->va_start) {
va = node_to_va(rb_prev(&va->rb_node));
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area;
continue;
}
/*
* This area fits, move on to the previous one. If
* the previous one is the terminal one, we're done.
*/
area = (area + nr_vms - 1) % nr_vms;
if (area == term_area)
break;
start = offsets[area];
end = start + sizes[area];
va = pvm_find_va_enclose_addr(base + end);
}
/* we've found a fitting base, insert all va's */
for (area = 0; area < nr_vms; area++) {
int ret;
start = base + offsets[area];
size = sizes[area];
va = pvm_find_va_enclose_addr(start);
if (WARN_ON_ONCE(va == NULL))
/* It is a BUG(), but trigger recovery instead. */
goto recovery;
ret = va_clip(&free_vmap_area_root,
&free_vmap_area_list, va, start, size);
if (WARN_ON_ONCE(unlikely(ret)))
/* It is a BUG(), but trigger recovery instead. */
goto recovery;
/* Allocated area. */
va = vas[area];
va->va_start = start;
va->va_end = start + size;
}
spin_unlock(&free_vmap_area_lock);
/* populate the kasan shadow space */
for (area = 0; area < nr_vms; area++) {
if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
goto err_free_shadow;
}
/* insert all vm's */
for (area = 0; area < nr_vms; area++) {
struct vmap_node *vn = addr_to_node(vas[area]->va_start);
spin_lock(&vn->busy.lock);
insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head);
setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
pcpu_get_vm_areas);
spin_unlock(&vn->busy.lock);
}
/*
* Mark allocated areas as accessible. Do it now as a best-effort
* approach, as they can be mapped outside of vmalloc code.
* With hardware tag-based KASAN, marking is skipped for
* non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/
for (area = 0; area < nr_vms; area++)
vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr,
vms[area]->size, KASAN_VMALLOC_PROT_NORMAL);
kfree(vas);
return vms;
recovery:
/*
* Remove previously allocated areas. There is no
* need in removing these areas from the busy tree,
* because they are inserted only on the final step
* and when pcpu_get_vm_areas() is success.
*/
while (area--) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
&free_vmap_area_list);
if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
}
overflow:
spin_unlock(&free_vmap_area_lock);
if (!purged) {
reclaim_and_purge_vmap_areas();
purged = true;
/* Before "retry", check if we recover. */
for (area = 0; area < nr_vms; area++) {
if (vas[area])
continue;
vas[area] = kmem_cache_zalloc(
vmap_area_cachep, GFP_KERNEL);
if (!vas[area])
goto err_free;
}
goto retry;
}
err_free:
for (area = 0; area < nr_vms; area++) {
if (vas[area])
kmem_cache_free(vmap_area_cachep, vas[area]);
kfree(vms[area]);
}
err_free2:
kfree(vas);
kfree(vms);
return NULL;
err_free_shadow:
spin_lock(&free_vmap_area_lock);
/*
* We release all the vmalloc shadows, even the ones for regions that
* hadn't been successfully added. This relies on kasan_release_vmalloc
* being able to tolerate this case.
*/
for (area = 0; area < nr_vms; area++) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
&free_vmap_area_list);
if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
kfree(vms[area]);
}
spin_unlock(&free_vmap_area_lock);
kfree(vas);
kfree(vms);
return NULL;
}
/**
* pcpu_free_vm_areas - free vmalloc areas for percpu allocator
* @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
* @nr_vms: the number of allocated areas
*
* Free vm_structs and the array allocated by pcpu_get_vm_areas().
*/
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
int i;
for (i = 0; i < nr_vms; i++)
free_vm_area(vms[i]);
kfree(vms);
}
#endif /* CONFIG_SMP */
#ifdef CONFIG_PRINTK
bool vmalloc_dump_obj(void *object)
{
const void *caller;
struct vm_struct *vm;
struct vmap_area *va;
struct vmap_node *vn;
unsigned long addr;
unsigned int nr_pages;
addr = PAGE_ALIGN((unsigned long) object);
vn = addr_to_node(addr);
if (!spin_trylock(&vn->busy.lock))
return false;
va = __find_vmap_area(addr, &vn->busy.root);
if (!va || !va->vm) {
spin_unlock(&vn->busy.lock);
return false;
}
vm = va->vm;
addr = (unsigned long) vm->addr;
caller = vm->caller;
nr_pages = vm->nr_pages;
spin_unlock(&vn->busy.lock);
pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
nr_pages, addr, caller);
return true;
}
#endif
#ifdef CONFIG_PROC_FS
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
{
if (IS_ENABLED(CONFIG_NUMA)) {
unsigned int nr, *counters = m->private;
unsigned int step = 1U << vm_area_page_order(v);
if (!counters)
return;
if (v->flags & VM_UNINITIALIZED)
return;
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
smp_rmb();
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr += step)
counters[page_to_nid(v->pages[nr])] += step;
for_each_node_state(nr, N_HIGH_MEMORY)
if (counters[nr])
seq_printf(m, " N%u=%u", nr, counters[nr]);
}
}
static void show_purge_info(struct seq_file *m)
{
struct vmap_node *vn;
struct vmap_area *va;
int i;
for (i = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
spin_lock(&vn->lazy.lock);
list_for_each_entry(va, &vn->lazy.head, list) {
seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
(void *)va->va_start, (void *)va->va_end,
va_size(va));
}
spin_unlock(&vn->lazy.lock);
}
}
static int vmalloc_info_show(struct seq_file *m, void *p)
{
struct vmap_node *vn;
struct vmap_area *va;
struct vm_struct *v;
int i;
for (i = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
list_for_each_entry(va, &vn->busy.head, list) {
if (!va->vm) {
if (va->flags & VMAP_RAM)
seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
(void *)va->va_start, (void *)va->va_end,
va_size(va));
continue;
}
v = va->vm;
seq_printf(m, "0x%pK-0x%pK %7ld",
v->addr, v->addr + v->size, v->size);
if (v->caller)
seq_printf(m, " %pS", v->caller);
if (v->nr_pages)
seq_printf(m, " pages=%d", v->nr_pages);
if (v->phys_addr)
seq_printf(m, " phys=%pa", &v->phys_addr);
if (v->flags & VM_IOREMAP)
seq_puts(m, " ioremap");
if (v->flags & VM_SPARSE)
seq_puts(m, " sparse");
if (v->flags & VM_ALLOC)
seq_puts(m, " vmalloc");
if (v->flags & VM_MAP)
seq_puts(m, " vmap");
if (v->flags & VM_USERMAP)
seq_puts(m, " user");
if (v->flags & VM_DMA_COHERENT)
seq_puts(m, " dma-coherent");
if (is_vmalloc_addr(v->pages))
seq_puts(m, " vpages");
show_numa_info(m, v);
seq_putc(m, '\n');
}
spin_unlock(&vn->busy.lock);
}
/*
* As a final step, dump "unpurged" areas.
*/
show_purge_info(m);
return 0;
}
static int __init proc_vmalloc_init(void)
{
void *priv_data = NULL;
if (IS_ENABLED(CONFIG_NUMA))
priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
proc_create_single_data("vmallocinfo",
0400, NULL, vmalloc_info_show, priv_data);
return 0;
}
module_init(proc_vmalloc_init);
#endif
static void __init vmap_init_free_space(void)
{
unsigned long vmap_start = 1;
const unsigned long vmap_end = ULONG_MAX;
struct vmap_area *free;
struct vm_struct *busy;
/*
* B F B B B F
* -|-----|.....|-----|-----|-----|.....|-
* | The KVA space |
* |<--------------------------------->|
*/
for (busy = vmlist; busy; busy = busy->next) {
if ((unsigned long) busy->addr - vmap_start > 0) {
free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (!WARN_ON_ONCE(!free)) {
free->va_start = vmap_start;
free->va_end = (unsigned long) busy->addr;
insert_vmap_area_augment(free, NULL,
&free_vmap_area_root,
&free_vmap_area_list);
}
}
vmap_start = (unsigned long) busy->addr + busy->size;
}
if (vmap_end - vmap_start > 0) {
free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (!WARN_ON_ONCE(!free)) {
free->va_start = vmap_start;
free->va_end = vmap_end;
insert_vmap_area_augment(free, NULL,
&free_vmap_area_root,
&free_vmap_area_list);
}
}
}
static void vmap_init_nodes(void)
{
struct vmap_node *vn;
int i, n;
#if BITS_PER_LONG == 64
/*
* A high threshold of max nodes is fixed and bound to 128,
* thus a scale factor is 1 for systems where number of cores
* are less or equal to specified threshold.
*
* As for NUMA-aware notes. For bigger systems, for example
* NUMA with multi-sockets, where we can end-up with thousands
* of cores in total, a "sub-numa-clustering" should be added.
*
* In this case a NUMA domain is considered as a single entity
* with dedicated sub-nodes in it which describe one group or
* set of cores. Therefore a per-domain purging is supposed to
* be added as well as a per-domain balancing.
*/
n = clamp_t(unsigned int, num_possible_cpus(), 1, 128);
if (n > 1) {
vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN);
if (vn) {
/* Node partition is 16 pages. */
vmap_zone_size = (1 << 4) * PAGE_SIZE;
nr_vmap_nodes = n;
vmap_nodes = vn;
} else {
pr_err("Failed to allocate an array. Disable a node layer\n");
}
}
#endif
for (n = 0; n < nr_vmap_nodes; n++) {
vn = &vmap_nodes[n];
vn->busy.root = RB_ROOT;
INIT_LIST_HEAD(&vn->busy.head);
spin_lock_init(&vn->busy.lock);
vn->lazy.root = RB_ROOT;
INIT_LIST_HEAD(&vn->lazy.head);
spin_lock_init(&vn->lazy.lock);
for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
INIT_LIST_HEAD(&vn->pool[i].head);
WRITE_ONCE(vn->pool[i].len, 0);
}
spin_lock_init(&vn->pool_lock);
}
}
static unsigned long
vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
unsigned long count;
struct vmap_node *vn;
int i, j;
for (count = 0, i = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
for (j = 0; j < MAX_VA_SIZE_PAGES; j++)
count += READ_ONCE(vn->pool[j].len);
}
return count ? count : SHRINK_EMPTY;
}
static unsigned long
vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
int i;
for (i = 0; i < nr_vmap_nodes; i++)
decay_va_pool_node(&vmap_nodes[i], true);
return SHRINK_STOP;
}
void __init vmalloc_init(void)
{
struct shrinker *vmap_node_shrinker;
struct vmap_area *va;
struct vmap_node *vn;
struct vm_struct *tmp;
int i;
/*
* Create the cache for vmap_area objects.
*/
vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC);
for_each_possible_cpu(i) {
struct vmap_block_queue *vbq;
struct vfree_deferred *p;
vbq = &per_cpu(vmap_block_queue, i);
spin_lock_init(&vbq->lock);
INIT_LIST_HEAD(&vbq->free);
p = &per_cpu(vfree_deferred, i);
init_llist_head(&p->list);
INIT_WORK(&p->wq, delayed_vfree_work);
xa_init(&vbq->vmap_blocks);
}
/*
* Setup nodes before importing vmlist.
*/
vmap_init_nodes();
/* Import existing vmlist entries. */
for (tmp = vmlist; tmp; tmp = tmp->next) {
va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (WARN_ON_ONCE(!va))
continue;
va->va_start = (unsigned long)tmp->addr;
va->va_end = va->va_start + tmp->size;
va->vm = tmp;
vn = addr_to_node(va->va_start);
insert_vmap_area(va, &vn->busy.root, &vn->busy.head);
}
/*
* Now we can initialize a free vmap space.
*/
vmap_init_free_space();
vmap_initialized = true;
vmap_node_shrinker = shrinker_alloc(0, "vmap-node");
if (!vmap_node_shrinker) {
pr_err("Failed to allocate vmap-node shrinker!\n");
return;
}
vmap_node_shrinker->count_objects = vmap_node_shrink_count;
vmap_node_shrinker->scan_objects = vmap_node_shrink_scan;
shrinker_register(vmap_node_shrinker);
}
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. NET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the Ethernet handlers.
*
* Version: @(#)eth.h 1.0.4 05/13/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* Relocated to include/linux where it belongs by Alan Cox
* <gw4pts@gw4pts.ampr.org>
*/
#ifndef _LINUX_ETHERDEVICE_H
#define _LINUX_ETHERDEVICE_H
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/random.h>
#include <linux/crc32.h>
#include <linux/unaligned.h>
#include <asm/bitsperlong.h>
#ifdef __KERNEL__
struct device;
struct fwnode_handle;
int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
int platform_get_ethdev_address(struct device *dev, struct net_device *netdev);
unsigned char *arch_get_platform_mac_address(void);
int nvmem_get_mac_address(struct device *dev, void *addrbuf);
int device_get_mac_address(struct device *dev, char *addr);
int device_get_ethdev_address(struct device *dev, struct net_device *netdev);
int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr);
u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len);
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
extern const struct header_ops eth_header_ops;
int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
const void *daddr, const void *saddr, unsigned len);
int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh,
__be16 type);
void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev,
const unsigned char *haddr);
__be16 eth_header_parse_protocol(const struct sk_buff *skb);
int eth_prepare_mac_addr_change(struct net_device *dev, void *p);
void eth_commit_mac_addr_change(struct net_device *dev, void *p);
int eth_mac_addr(struct net_device *dev, void *p);
int eth_validate_addr(struct net_device *dev);
struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
unsigned int rxqs);
#define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
#define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv,
unsigned int txqs,
unsigned int rxqs);
#define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1)
struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb);
int eth_gro_complete(struct sk_buff *skb, int nhoff);
/* Reserved Ethernet Addresses per IEEE 802.1Q */
static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
#define eth_stp_addr eth_reserved_addr_base
static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) =
{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) =
{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
/**
* is_link_local_ether_addr - Determine if given Ethernet address is link-local
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per
* IEEE 802.1Q 8.6.3 Frame filtering.
*
* Please note: addr must be aligned to u16.
*/
static inline bool is_link_local_ether_addr(const u8 *addr)
{
__be16 *a = (__be16 *)addr;
static const __be16 *b = (const __be16 *)eth_reserved_addr_base;
static const __be16 m = cpu_to_be16(0xfff0);
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return (((*(const u32 *)addr) ^ (*(const u32 *)b)) |
(__force int)((a[2] ^ b[2]) & m)) == 0;
#else
return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
#endif
}
/**
* is_zero_ether_addr - Determine if give Ethernet address is all zeros.
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if the address is all zeroes.
*
* Please note: addr must be aligned to u16.
*/
static inline bool is_zero_ether_addr(const u8 *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0;
#else
return (*(const u16 *)(addr + 0) |
*(const u16 *)(addr + 2) |
*(const u16 *)(addr + 4)) == 0;
#endif
}
/**
* is_multicast_ether_addr - Determine if the Ethernet address is a multicast.
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if the address is a multicast address.
* By definition the broadcast address is also a multicast address.
*/
static inline bool is_multicast_ether_addr(const u8 *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
u32 a = *(const u32 *)addr;
#else
u16 a = *(const u16 *)addr;
#endif
#ifdef __BIG_ENDIAN
return 0x01 & (a >> ((sizeof(a) * 8) - 8));
#else
return 0x01 & a;
#endif
}
static inline bool is_multicast_ether_addr_64bits(const u8 *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
#ifdef __BIG_ENDIAN
return 0x01 & ((*(const u64 *)addr) >> 56);
#else
return 0x01 & (*(const u64 *)addr);
#endif
#else
return is_multicast_ether_addr(addr);
#endif
}
/**
* is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802).
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if the address is a local address.
*/
static inline bool is_local_ether_addr(const u8 *addr)
{
return 0x02 & addr[0];
}
/**
* is_broadcast_ether_addr - Determine if the Ethernet address is broadcast
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if the address is the broadcast address.
*
* Please note: addr must be aligned to u16.
*/
static inline bool is_broadcast_ether_addr(const u8 *addr)
{
return (*(const u16 *)(addr + 0) &
*(const u16 *)(addr + 2) &
*(const u16 *)(addr + 4)) == 0xffff;
}
/**
* is_unicast_ether_addr - Determine if the Ethernet address is unicast
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: true if the address is a unicast address.
*/
static inline bool is_unicast_ether_addr(const u8 *addr)
{
return !is_multicast_ether_addr(addr);
}
/**
* is_valid_ether_addr - Determine if the given Ethernet address is valid
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not
* a multicast address, and is not FF:FF:FF:FF:FF:FF.
*
* Return: true if the address is valid.
*
* Please note: addr must be aligned to u16.
*/
static inline bool is_valid_ether_addr(const u8 *addr)
{
/* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to
* explicitly check for it here. */
return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr);
}
/**
* eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol
* @proto: Ethertype/length value to be tested
*
* Check that the value from the Ethertype/length field is a valid Ethertype.
*
* Return: true if the valid is an 802.3 supported Ethertype.
*/
static inline bool eth_proto_is_802_3(__be16 proto)
{
#ifndef __BIG_ENDIAN
/* if CPU is little endian mask off bits representing LSB */
proto &= htons(0xFF00);
#endif
/* cast both to u16 and compare since LSB can be ignored */
return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN);
}
/**
* eth_random_addr - Generate software assigned random Ethernet address
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Generate a random Ethernet address (MAC) that is not multicast
* and has the local assigned bit set.
*/
static inline void eth_random_addr(u8 *addr)
{
get_random_bytes(addr, ETH_ALEN);
addr[0] &= 0xfe; /* clear multicast bit */
addr[0] |= 0x02; /* set local assignment bit (IEEE802) */
}
/**
* eth_broadcast_addr - Assign broadcast address
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Assign the broadcast address to the given address array.
*/
static inline void eth_broadcast_addr(u8 *addr)
{
memset(addr, 0xff, ETH_ALEN);
}
/**
* eth_zero_addr - Assign zero address
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Assign the zero address to the given address array.
*/
static inline void eth_zero_addr(u8 *addr)
{
memset(addr, 0x00, ETH_ALEN);
}
/**
* eth_hw_addr_random - Generate software assigned random Ethernet and
* set device flag
* @dev: pointer to net_device structure
*
* Generate a random Ethernet address (MAC) to be used by a net device
* and set addr_assign_type so the state can be read by sysfs and be
* used by userspace.
*/
static inline void eth_hw_addr_random(struct net_device *dev)
{
u8 addr[ETH_ALEN];
eth_random_addr(addr);
__dev_addr_set(dev, addr, ETH_ALEN);
dev->addr_assign_type = NET_ADDR_RANDOM;
}
/**
* eth_hw_addr_crc - Calculate CRC from netdev_hw_addr
* @ha: pointer to hardware address
*
* Calculate CRC from a hardware address as basis for filter hashes.
*/
static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha)
{
return ether_crc(ETH_ALEN, ha->addr);
}
/**
* ether_addr_copy - Copy an Ethernet address
* @dst: Pointer to a six-byte array Ethernet address destination
* @src: Pointer to a six-byte array Ethernet address source
*
* Please note: dst & src must both be aligned to u16.
*/
static inline void ether_addr_copy(u8 *dst, const u8 *src)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
*(u32 *)dst = *(const u32 *)src;
*(u16 *)(dst + 4) = *(const u16 *)(src + 4);
#else
u16 *a = (u16 *)dst;
const u16 *b = (const u16 *)src;
a[0] = b[0];
a[1] = b[1];
a[2] = b[2];
#endif
}
/**
* eth_hw_addr_set - Assign Ethernet address to a net_device
* @dev: pointer to net_device structure
* @addr: address to assign
*
* Assign given address to the net_device, addr_assign_type is not changed.
*/
static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr)
{
__dev_addr_set(dev, addr, ETH_ALEN);
}
/**
* eth_hw_addr_inherit - Copy dev_addr from another net_device
* @dst: pointer to net_device to copy dev_addr to
* @src: pointer to net_device to copy dev_addr from
*
* Copy the Ethernet address from one net_device to another along with
* the address attributes (addr_assign_type).
*/
static inline void eth_hw_addr_inherit(struct net_device *dst,
struct net_device *src)
{
dst->addr_assign_type = src->addr_assign_type;
eth_hw_addr_set(dst, src->dev_addr);
}
/**
* ether_addr_equal - Compare two Ethernet addresses
* @addr1: Pointer to a six-byte array containing the Ethernet address
* @addr2: Pointer other six-byte array containing the Ethernet address
*
* Compare two Ethernet addresses, returns true if equal
*
* Please note: addr1 & addr2 must both be aligned to u16.
*/
static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) |
((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4)));
return fold == 0;
#else
const u16 *a = (const u16 *)addr1;
const u16 *b = (const u16 *)addr2;
return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
#endif
}
/**
* ether_addr_equal_64bits - Compare two Ethernet addresses
* @addr1: Pointer to an array of 8 bytes
* @addr2: Pointer to an other array of 8 bytes
*
* Compare two Ethernet addresses, returns true if equal, false otherwise.
*
* The function doesn't need any conditional branches and possibly uses
* word memory accesses on CPU allowing cheap unaligned memory reads.
* arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 }
*
* Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits.
*/
static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2);
#ifdef __BIG_ENDIAN
return (fold >> 16) == 0;
#else
return (fold << 16) == 0;
#endif
#else
return ether_addr_equal(addr1, addr2);
#endif
}
/**
* ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses
* @addr1: Pointer to a six-byte array containing the Ethernet address
* @addr2: Pointer other six-byte array containing the Ethernet address
*
* Compare two Ethernet addresses, returns true if equal
*
* Please note: Use only when any Ethernet address may not be u16 aligned.
*/
static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
return ether_addr_equal(addr1, addr2);
#else
return memcmp(addr1, addr2, ETH_ALEN) == 0;
#endif
}
/**
* ether_addr_equal_masked - Compare two Ethernet addresses with a mask
* @addr1: Pointer to a six-byte array containing the 1st Ethernet address
* @addr2: Pointer to a six-byte array containing the 2nd Ethernet address
* @mask: Pointer to a six-byte array containing the Ethernet address bitmask
*
* Compare two Ethernet addresses with a mask, returns true if for every bit
* set in the bitmask the equivalent bits in the ethernet addresses are equal.
* Using a mask with all bits set is a slower ether_addr_equal.
*/
static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2,
const u8 *mask)
{
int i;
for (i = 0; i < ETH_ALEN; i++) {
if ((addr1[i] ^ addr2[i]) & mask[i])
return false;
}
return true;
}
static inline bool ether_addr_is_ipv4_mcast(const u8 *addr)
{
u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 };
return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask);
}
static inline bool ether_addr_is_ipv6_mcast(const u8 *addr)
{
u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 };
return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask);
}
static inline bool ether_addr_is_ip_mcast(const u8 *addr)
{
return ether_addr_is_ipv4_mcast(addr) ||
ether_addr_is_ipv6_mcast(addr);
}
/**
* ether_addr_to_u64 - Convert an Ethernet address into a u64 value.
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Return: a u64 value of the address
*/
static inline u64 ether_addr_to_u64(const u8 *addr)
{
u64 u = 0;
int i;
for (i = 0; i < ETH_ALEN; i++)
u = u << 8 | addr[i];
return u;
}
/**
* u64_to_ether_addr - Convert a u64 to an Ethernet address.
* @u: u64 to convert to an Ethernet MAC address
* @addr: Pointer to a six-byte array to contain the Ethernet address
*/
static inline void u64_to_ether_addr(u64 u, u8 *addr)
{
int i;
for (i = ETH_ALEN - 1; i >= 0; i--) {
addr[i] = u & 0xff;
u = u >> 8;
}
}
/**
* eth_addr_dec - Decrement the given MAC address
*
* @addr: Pointer to a six-byte array containing Ethernet address to decrement
*/
static inline void eth_addr_dec(u8 *addr)
{
u64 u = ether_addr_to_u64(addr);
u--;
u64_to_ether_addr(u, addr);
}
/**
* eth_addr_inc() - Increment the given MAC address.
* @addr: Pointer to a six-byte array containing Ethernet address to increment.
*/
static inline void eth_addr_inc(u8 *addr)
{
u64 u = ether_addr_to_u64(addr);
u++;
u64_to_ether_addr(u, addr);
}
/**
* eth_addr_add() - Add (or subtract) an offset to/from the given MAC address.
*
* @offset: Offset to add.
* @addr: Pointer to a six-byte array containing Ethernet address to increment.
*/
static inline void eth_addr_add(u8 *addr, long offset)
{
u64 u = ether_addr_to_u64(addr);
u += offset;
u64_to_ether_addr(u, addr);
}
/**
* is_etherdev_addr - Tell if given Ethernet address belongs to the device.
* @dev: Pointer to a device structure
* @addr: Pointer to a six-byte array containing the Ethernet address
*
* Compare passed address with all addresses of the device. Return true if the
* address if one of the device addresses.
*
* Note that this function calls ether_addr_equal_64bits() so take care of
* the right padding.
*/
static inline bool is_etherdev_addr(const struct net_device *dev,
const u8 addr[6 + 2])
{
struct netdev_hw_addr *ha;
bool res = false;
rcu_read_lock();
for_each_dev_addr(dev, ha) {
res = ether_addr_equal_64bits(addr, ha->addr);
if (res)
break;
}
rcu_read_unlock();
return res;
}
#endif /* __KERNEL__ */
/**
* compare_ether_header - Compare two Ethernet headers
* @a: Pointer to Ethernet header
* @b: Pointer to Ethernet header
*
* Compare two Ethernet headers, returns 0 if equal.
* This assumes that the network header (i.e., IP header) is 4-byte
* aligned OR the platform can handle unaligned access. This is the
* case for all packets coming into netif_receive_skb or similar
* entry points.
*/
static inline unsigned long compare_ether_header(const void *a, const void *b)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
unsigned long fold;
/*
* We want to compare 14 bytes:
* [a0 ... a13] ^ [b0 ... b13]
* Use two long XOR, ORed together, with an overlap of two bytes.
* [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] |
* [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13]
* This means the [a6 a7] ^ [b6 b7] part is done two times.
*/
fold = *(unsigned long *)a ^ *(unsigned long *)b;
fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6);
return fold;
#else
u32 *a32 = (u32 *)((u8 *)a + 2);
u32 *b32 = (u32 *)((u8 *)b + 2);
return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) |
(a32[1] ^ b32[1]) | (a32[2] ^ b32[2]);
#endif
}
/**
* eth_hw_addr_gen - Generate and assign Ethernet address to a port
* @dev: pointer to port's net_device structure
* @base_addr: base Ethernet address
* @id: offset to add to the base address
*
* Generate a MAC address using a base address and an offset and assign it
* to a net_device. Commonly used by switch drivers which need to compute
* addresses for all their ports. addr_assign_type is not changed.
*/
static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr,
unsigned int id)
{
u64 u = ether_addr_to_u64(base_addr);
u8 addr[ETH_ALEN];
u += id;
u64_to_ether_addr(u, addr);
eth_hw_addr_set(dev, addr);
}
/**
* eth_skb_pkt_type - Assign packet type if destination address does not match
* @skb: Assigned a packet type if address does not match @dev address
* @dev: Network device used to compare packet address against
*
* If the destination MAC address of the packet does not match the network
* device address, assign an appropriate packet type.
*/
static inline void eth_skb_pkt_type(struct sk_buff *skb,
const struct net_device *dev)
{
const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) {
if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
} else {
skb->pkt_type = PACKET_OTHERHOST;
}
}
}
static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb)
{
struct ethhdr *eth = (struct ethhdr *)skb->data;
skb_pull_inline(skb, ETH_HLEN);
return eth;
}
/**
* eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame
* @skb: Buffer to pad
*
* An Ethernet frame should have a minimum size of 60 bytes. This function
* takes short frames and pads them with zeros up to the 60 byte limit.
*/
static inline int eth_skb_pad(struct sk_buff *skb)
{
return skb_put_padto(skb, ETH_ZLEN);
}
#endif /* _LINUX_ETHERDEVICE_H */
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/plist.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/freezer.h>
#include "futex.h"
/*
* READ this before attempting to hack on futexes!
*
* Basic futex operation and ordering guarantees
* =============================================
*
* The waiter reads the futex value in user space and calls
* futex_wait(). This function computes the hash bucket and acquires
* the hash bucket lock. After that it reads the futex user space value
* again and verifies that the data has not changed. If it has not changed
* it enqueues itself into the hash bucket, releases the hash bucket lock
* and schedules.
*
* The waker side modifies the user space value of the futex and calls
* futex_wake(). This function computes the hash bucket and acquires the
* hash bucket lock. Then it looks for waiters on that futex in the hash
* bucket and wakes them.
*
* In futex wake up scenarios where no tasks are blocked on a futex, taking
* the hb spinlock can be avoided and simply return. In order for this
* optimization to work, ordering guarantees must exist so that the waiter
* being added to the list is acknowledged when the list is concurrently being
* checked by the waker, avoiding scenarios like the following:
*
* CPU 0 CPU 1
* val = *futex;
* sys_futex(WAIT, futex, val);
* futex_wait(futex, val);
* uval = *futex;
* *futex = newval;
* sys_futex(WAKE, futex);
* futex_wake(futex);
* if (queue_empty())
* return;
* if (uval == val)
* lock(hash_bucket(futex));
* queue();
* unlock(hash_bucket(futex));
* schedule();
*
* This would cause the waiter on CPU 0 to wait forever because it
* missed the transition of the user space value from val to newval
* and the waker did not find the waiter in the hash bucket queue.
*
* The correct serialization ensures that a waiter either observes
* the changed user space value before blocking or is woken by a
* concurrent waker:
*
* CPU 0 CPU 1
* val = *futex;
* sys_futex(WAIT, futex, val);
* futex_wait(futex, val);
*
* waiters++; (a)
* smp_mb(); (A) <-- paired with -.
* |
* lock(hash_bucket(futex)); |
* |
* uval = *futex; |
* | *futex = newval;
* | sys_futex(WAKE, futex);
* | futex_wake(futex);
* |
* `--------> smp_mb(); (B)
* if (uval == val)
* queue();
* unlock(hash_bucket(futex));
* schedule(); if (waiters)
* lock(hash_bucket(futex));
* else wake_waiters(futex);
* waiters--; (b) unlock(hash_bucket(futex));
*
* Where (A) orders the waiters increment and the futex value read through
* atomic operations (see futex_hb_waiters_inc) and where (B) orders the write
* to futex and the waiters read (see futex_hb_waiters_pending()).
*
* This yields the following case (where X:=waiters, Y:=futex):
*
* X = Y = 0
*
* w[X]=1 w[Y]=1
* MB MB
* r[Y]=y r[X]=x
*
* Which guarantees that x==0 && y==0 is impossible; which translates back into
* the guarantee that we cannot both miss the futex variable change and the
* enqueue.
*
* Note that a new waiter is accounted for in (a) even when it is possible that
* the wait call can return error, in which case we backtrack from it in (b).
* Refer to the comment in futex_q_lock().
*
* Similarly, in order to account for waiters being requeued on another
* address we always increment the waiters for the destination bucket before
* acquiring the lock. It then decrements them again after releasing it -
* the code that actually moves the futex(es) between hash buckets (requeue_futex)
* will do the additional required waiter count housekeeping. This is done for
* double_lock_hb() and double_unlock_hb(), respectively.
*/
bool __futex_wake_mark(struct futex_q *q)
{
if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
return false;
__futex_unqueue(q);
/*
* The waiting task can free the futex_q as soon as q->lock_ptr = NULL
* is written, without taking any locks. This is possible in the event
* of a spurious wakeup, for example. A memory barrier is required here
* to prevent the following store to lock_ptr from getting ahead of the
* plist_del in __futex_unqueue().
*/
smp_store_release(&q->lock_ptr, NULL);
return true;
}
/*
* The hash bucket lock must be held when this is called.
* Afterwards, the futex_q must not be accessed. Callers
* must ensure to later call wake_up_q() for the actual
* wakeups to occur.
*/
void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
{
struct task_struct *p = q->task;
get_task_struct(p);
if (!__futex_wake_mark(q)) {
put_task_struct(p);
return;
}
/*
* Queue the task for later wakeup for after we've released
* the hb->lock.
*/
wake_q_add_safe(wake_q, p);
}
/*
* Wake up waiters matching bitset queued on this futex (uaddr).
*/
int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
union futex_key key = FUTEX_KEY_INIT;
DEFINE_WAKE_Q(wake_q);
int ret;
if (!bitset)
return -EINVAL;
ret = get_futex_key(uaddr, flags, &key, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
if ((flags & FLAGS_STRICT) && !nr_wake)
return 0;
hb = futex_hash(&key);
/* Make sure we really have tasks to wakeup */
if (!futex_hb_waiters_pending(hb))
return ret;
spin_lock(&hb->lock);
plist_for_each_entry_safe(this, next, &hb->chain, list) { if (futex_match (&this->key, &key)) { if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
break;
}
/* Check if one of the bits is set in both bitsets */
if (!(this->bitset & bitset))
continue;
this->wake(&wake_q, this);
if (++ret >= nr_wake)
break;
}
}
spin_unlock(&hb->lock);
wake_up_q(&wake_q);
return ret;
}
static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
{
unsigned int op = (encoded_op & 0x70000000) >> 28;
unsigned int cmp = (encoded_op & 0x0f000000) >> 24;
int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
int oldval, ret;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
if (oparg < 0 || oparg > 31) {
/*
* kill this print and return -EINVAL when userspace
* is sane again
*/
pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
current->comm, oparg);
oparg &= 31;
}
oparg = 1 << oparg;
}
pagefault_disable();
ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
pagefault_enable();
if (ret)
return ret;
switch (cmp) {
case FUTEX_OP_CMP_EQ:
return oldval == cmparg;
case FUTEX_OP_CMP_NE:
return oldval != cmparg;
case FUTEX_OP_CMP_LT:
return oldval < cmparg;
case FUTEX_OP_CMP_GE:
return oldval >= cmparg;
case FUTEX_OP_CMP_LE:
return oldval <= cmparg;
case FUTEX_OP_CMP_GT:
return oldval > cmparg;
default:
return -ENOSYS;
}
}
/*
* Wake up all waiters hashed on the physical page that is mapped
* to this virtual address:
*/
int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_wake2, int op)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
int ret, op_ret;
DEFINE_WAKE_Q(wake_q);
retry:
ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE);
if (unlikely(ret != 0))
return ret;
hb1 = futex_hash(&key1);
hb2 = futex_hash(&key2);
retry_private:
double_lock_hb(hb1, hb2);
op_ret = futex_atomic_op_inuser(op, uaddr2);
if (unlikely(op_ret < 0)) {
double_unlock_hb(hb1, hb2);
if (!IS_ENABLED(CONFIG_MMU) ||
unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
/*
* we don't get EFAULT from MMU faults if we don't have
* an MMU, but we might get them from range checking
*/
ret = op_ret;
return ret;
}
if (op_ret == -EFAULT) {
ret = fault_in_user_writeable(uaddr2);
if (ret)
return ret;
}
cond_resched();
if (!(flags & FLAGS_SHARED))
goto retry_private;
goto retry;
}
plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (futex_match (&this->key, &key1)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
goto out_unlock;
}
this->wake(&wake_q, this);
if (++ret >= nr_wake)
break;
}
}
if (op_ret > 0) {
op_ret = 0;
plist_for_each_entry_safe(this, next, &hb2->chain, list) {
if (futex_match (&this->key, &key2)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
goto out_unlock;
}
this->wake(&wake_q, this);
if (++op_ret >= nr_wake2)
break;
}
}
ret += op_ret;
}
out_unlock:
double_unlock_hb(hb1, hb2);
wake_up_q(&wake_q);
return ret;
}
static long futex_wait_restart(struct restart_block *restart);
/**
* futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal
* @hb: the futex hash bucket, must be locked by the caller
* @q: the futex_q to queue up on
* @timeout: the prepared hrtimer_sleeper, or null for no timeout
*/
void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
struct hrtimer_sleeper *timeout)
{
/*
* The task state is guaranteed to be set before another task can
* wake it. set_current_state() is implemented using smp_store_mb() and
* futex_queue() calls spin_unlock() upon completion, both serializing
* access to the hash list and forcing another memory barrier.
*/
set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
futex_queue(q, hb, current);
/* Arm the timer */
if (timeout)
hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS);
/*
* If we have been removed from the hash list, then another task
* has tried to wake us, and we can skip the call to schedule().
*/
if (likely(!plist_node_empty(&q->list))) {
/*
* If the timer has already expired, current will already be
* flagged for rescheduling. Only call schedule if there
* is no timeout, or if it has yet to expire.
*/
if (!timeout || timeout->task)
schedule();
}
__set_current_state(TASK_RUNNING);
}
/**
* futex_unqueue_multiple - Remove various futexes from their hash bucket
* @v: The list of futexes to unqueue
* @count: Number of futexes in the list
*
* Helper to unqueue a list of futexes. This can't fail.
*
* Return:
* - >=0 - Index of the last futex that was awoken;
* - -1 - No futex was awoken
*/
int futex_unqueue_multiple(struct futex_vector *v, int count)
{
int ret = -1, i;
for (i = 0; i < count; i++) {
if (!futex_unqueue(&v[i].q))
ret = i;
}
return ret;
}
/**
* futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes
* @vs: The futex list to wait on
* @count: The size of the list
* @woken: Index of the last woken futex, if any. Used to notify the
* caller that it can return this index to userspace (return parameter)
*
* Prepare multiple futexes in a single step and enqueue them. This may fail if
* the futex list is invalid or if any futex was already awoken. On success the
* task is ready to interruptible sleep.
*
* Return:
* - 1 - One of the futexes was woken by another thread
* - 0 - Success
* - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL
*/
int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
{
struct futex_hash_bucket *hb;
bool retry = false;
int ret, i;
u32 uval;
/*
* Enqueuing multiple futexes is tricky, because we need to enqueue
* each futex on the list before dealing with the next one to avoid
* deadlocking on the hash bucket. But, before enqueuing, we need to
* make sure that current->state is TASK_INTERRUPTIBLE, so we don't
* lose any wake events, which cannot be done before the get_futex_key
* of the next key, because it calls get_user_pages, which can sleep.
* Thus, we fetch the list of futexes keys in two steps, by first
* pinning all the memory keys in the futex key, and only then we read
* each key and queue the corresponding futex.
*
* Private futexes doesn't need to recalculate hash in retry, so skip
* get_futex_key() when retrying.
*/
retry:
for (i = 0; i < count; i++) {
if (!(vs[i].w.flags & FLAGS_SHARED) && retry)
continue;
ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr),
vs[i].w.flags,
&vs[i].q.key, FUTEX_READ);
if (unlikely(ret))
return ret;
}
set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
for (i = 0; i < count; i++) {
u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr;
struct futex_q *q = &vs[i].q;
u32 val = vs[i].w.val;
hb = futex_q_lock(q);
ret = futex_get_value_locked(&uval, uaddr);
if (!ret && uval == val) {
/*
* The bucket lock can't be held while dealing with the
* next futex. Queue each futex at this moment so hb can
* be unlocked.
*/
futex_queue(q, hb, current);
continue;
}
futex_q_unlock(hb);
__set_current_state(TASK_RUNNING);
/*
* Even if something went wrong, if we find out that a futex
* was woken, we don't return error and return this index to
* userspace
*/
*woken = futex_unqueue_multiple(vs, i);
if (*woken >= 0)
return 1;
if (ret) {
/*
* If we need to handle a page fault, we need to do so
* without any lock and any enqueued futex (otherwise
* we could lose some wakeup). So we do it here, after
* undoing all the work done so far. In success, we
* retry all the work.
*/
if (get_user(uval, uaddr))
return -EFAULT;
retry = true;
goto retry;
}
if (uval != val)
return -EWOULDBLOCK;
}
return 0;
}
/**
* futex_sleep_multiple - Check sleeping conditions and sleep
* @vs: List of futexes to wait for
* @count: Length of vs
* @to: Timeout
*
* Sleep if and only if the timeout hasn't expired and no futex on the list has
* been woken up.
*/
static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count,
struct hrtimer_sleeper *to)
{
if (to && !to->task)
return;
for (; count; count--, vs++) {
if (!READ_ONCE(vs->q.lock_ptr))
return;
}
schedule();
}
/**
* futex_wait_multiple - Prepare to wait on and enqueue several futexes
* @vs: The list of futexes to wait on
* @count: The number of objects
* @to: Timeout before giving up and returning to userspace
*
* Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function
* sleeps on a group of futexes and returns on the first futex that is
* wake, or after the timeout has elapsed.
*
* Return:
* - >=0 - Hint to the futex that was awoken
* - <0 - On error
*/
int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
struct hrtimer_sleeper *to)
{
int ret, hint = 0;
if (to)
hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
while (1) {
ret = futex_wait_multiple_setup(vs, count, &hint);
if (ret) {
if (ret > 0) {
/* A futex was woken during setup */
ret = hint;
}
return ret;
}
futex_sleep_multiple(vs, count, to);
__set_current_state(TASK_RUNNING);
ret = futex_unqueue_multiple(vs, count);
if (ret >= 0)
return ret;
if (to && !to->task)
return -ETIMEDOUT;
else if (signal_pending(current))
return -ERESTARTSYS;
/*
* The final case is a spurious wakeup, for
* which just retry.
*/
}
}
/**
* futex_wait_setup() - Prepare to wait on a futex
* @uaddr: the futex userspace address
* @val: the expected value
* @flags: futex flags (FLAGS_SHARED, etc.)
* @q: the associated futex_q
* @hb: storage for hash_bucket pointer to be returned to caller
*
* Setup the futex_q and locate the hash_bucket. Get the futex value and
* compare it with the expected value. Handle atomic faults internally.
* Return with the hb lock held on success, and unlocked on failure.
*
* Return:
* - 0 - uaddr contains val and hb has been locked;
* - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
*/
int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb)
{
u32 uval;
int ret;
/*
* Access the page AFTER the hash-bucket is locked.
* Order is important:
*
* Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
* Userspace waker: if (cond(var)) { var = new; futex_wake(&var); }
*
* The basic logical guarantee of a futex is that it blocks ONLY
* if cond(var) is known to be true at the time of blocking, for
* any cond. If we locked the hash-bucket after testing *uaddr, that
* would open a race condition where we could block indefinitely with
* cond(var) false, which would violate the guarantee.
*
* On the other hand, we insert q and release the hash-bucket only
* after testing *uaddr. This guarantees that futex_wait() will NOT
* absorb a wakeup if *uaddr does not match the desired values
* while the syscall executes.
*/
retry:
ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ);
if (unlikely(ret != 0))
return ret;
retry_private:
*hb = futex_q_lock(q);
ret = futex_get_value_locked(&uval, uaddr);
if (ret) {
futex_q_unlock(*hb);
ret = get_user(uval, uaddr);
if (ret)
return ret;
if (!(flags & FLAGS_SHARED))
goto retry_private;
goto retry;
}
if (uval != val) { futex_q_unlock(*hb);
ret = -EWOULDBLOCK;
}
return ret;
}
int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
struct hrtimer_sleeper *to, u32 bitset)
{
struct futex_q q = futex_q_init;
struct futex_hash_bucket *hb;
int ret;
if (!bitset)
return -EINVAL;
q.bitset = bitset;
retry:
/*
* Prepare to wait on uaddr. On success, it holds hb->lock and q
* is initialized.
*/
ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
return ret;
/* futex_queue and wait for wakeup, timeout, or a signal. */
futex_wait_queue(hb, &q, to);
/* If we were woken (and unqueued), we succeeded, whatever. */
if (!futex_unqueue(&q))
return 0;
if (to && !to->task)
return -ETIMEDOUT;
/*
* We expect signal_pending(current), but we might be the
* victim of a spurious wakeup as well.
*/
if (!signal_pending(current))
goto retry;
return -ERESTARTSYS;
}
int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset)
{
struct hrtimer_sleeper timeout, *to;
struct restart_block *restart;
int ret;
to = futex_setup_timer(abs_time, &timeout, flags,
current->timer_slack_ns);
ret = __futex_wait(uaddr, flags, val, to, bitset);
/* No timeout, nothing to clean up. */
if (!to)
return ret;
hrtimer_cancel(&to->timer);
destroy_hrtimer_on_stack(&to->timer);
if (ret == -ERESTARTSYS) {
restart = ¤t->restart_block;
restart->futex.uaddr = uaddr;
restart->futex.val = val;
restart->futex.time = *abs_time;
restart->futex.bitset = bitset;
restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
return set_restart_fn(restart, futex_wait_restart);
}
return ret;
}
static long futex_wait_restart(struct restart_block *restart)
{
u32 __user *uaddr = restart->futex.uaddr;
ktime_t t, *tp = NULL;
if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
t = restart->futex.time;
tp = &t;
}
restart->fn = do_no_restart_syscall;
return (long)futex_wait(uaddr, restart->futex.flags,
restart->futex.val, tp, restart->futex.bitset);
}
// SPDX-License-Identifier: GPL-2.0
/*
* SUCS NET3:
*
* Generic datagram handling routines. These are generic for all
* protocols. Possibly a generic IP version on top of these would
* make sense. Not tonight however 8-).
* This is used because UDP, RAW, PACKET, DDP, IPX, AX.25 and
* NetROM layer all have identical poll code and mostly
* identical recvmsg() code. So we share it here. The poll was
* shared before but buried in udp.c so I moved it.
*
* Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>. (datagram_poll() from old
* udp.c code)
*
* Fixes:
* Alan Cox : NULL return from skb_peek_copy()
* understood
* Alan Cox : Rewrote skb_read_datagram to avoid the
* skb_peek_copy stuff.
* Alan Cox : Added support for SOCK_SEQPACKET.
* IPX can no longer use the SO_TYPE hack
* but AX.25 now works right, and SPX is
* feasible.
* Alan Cox : Fixed write poll of non IP protocol
* crash.
* Florian La Roche: Changed for my new skbuff handling.
* Darryl Miles : Fixed non-blocking SOCK_SEQPACKET.
* Linus Torvalds : BSD semantic fixes.
* Alan Cox : Datagram iovec handling
* Darryl Miles : Fixed non-blocking SOCK_STREAM.
* Alan Cox : POSIXisms
* Pete Wyckoff : Unconnected accept() fix.
*
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/poll.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/iov_iter.h>
#include <linux/indirect_call_wrapper.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/checksum.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <trace/events/skb.h>
#include <net/busy_poll.h>
#include <crypto/hash.h>
/*
* Is a socket 'connection oriented' ?
*/
static inline int connection_based(struct sock *sk)
{
return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
}
static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
void *key)
{
/*
* Avoid a wakeup if event not interesting for us
*/
if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
return 0;
return autoremove_wake_function(wait, mode, sync, key);
}
/*
* Wait for the last received packet to be different from skb
*/
int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
int *err, long *timeo_p,
const struct sk_buff *skb)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Socket errors? */
error = sock_error(sk);
if (error)
goto out_err;
if (READ_ONCE(queue->prev) != skb)
goto out;
/* Socket shut down? */
if (sk->sk_shutdown & RCV_SHUTDOWN)
goto out_noerr;
/* Sequenced packets can come disconnected.
* If so we report the problem
*/
error = -ENOTCONN;
if (connection_based(sk) &&
!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
goto out_err;
/* handle signals */
if (signal_pending(current))
goto interrupted;
error = 0;
*timeo_p = schedule_timeout(*timeo_p);
out:
finish_wait(sk_sleep(sk), &wait);
return error;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
goto out;
out_noerr:
*err = 0;
error = 1;
goto out;
}
EXPORT_SYMBOL(__skb_wait_for_more_packets);
static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
{
struct sk_buff *nskb;
if (skb->peeked)
return skb;
/* We have to unshare an skb before modifying it. */
if (!skb_shared(skb))
goto done;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return ERR_PTR(-ENOMEM);
skb->prev->next = nskb;
skb->next->prev = nskb;
nskb->prev = skb->prev;
nskb->next = skb->next;
consume_skb(skb);
skb = nskb;
done:
skb->peeked = 1;
return skb;
}
struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
struct sk_buff_head *queue,
unsigned int flags,
int *off, int *err,
struct sk_buff **last)
{
bool peek_at_off = false;
struct sk_buff *skb;
int _off = 0;
if (unlikely(flags & MSG_PEEK && *off >= 0)) {
peek_at_off = true;
_off = *off;
}
*last = queue->prev;
skb_queue_walk(queue, skb) {
if (flags & MSG_PEEK) {
if (peek_at_off && _off >= skb->len &&
(_off || skb->peeked)) {
_off -= skb->len;
continue;
}
if (!skb->len) {
skb = skb_set_peeked(skb);
if (IS_ERR(skb)) {
*err = PTR_ERR(skb);
return NULL;
}
}
refcount_inc(&skb->users);
} else {
__skb_unlink(skb, queue);
}
*off = _off;
return skb;
}
return NULL;
}
/**
* __skb_try_recv_datagram - Receive a datagram skbuff
* @sk: socket
* @queue: socket queue from which to receive
* @flags: MSG\_ flags
* @off: an offset in bytes to peek skb from. Returns an offset
* within an skb where data actually starts
* @err: error code returned
* @last: set to last peeked message to inform the wait function
* what to look for when peeking
*
* Get a datagram skbuff, understands the peeking, nonblocking wakeups
* and possible races. This replaces identical code in packet, raw and
* udp, as well as the IPX AX.25 and Appletalk. It also finally fixes
* the long standing peek and read race for datagram sockets. If you
* alter this routine remember it must be re-entrant.
*
* This function will lock the socket if a skb is returned, so
* the caller needs to unlock the socket in that case (usually by
* calling skb_free_datagram). Returns NULL with @err set to
* -EAGAIN if no data was available or to some other value if an
* error was detected.
*
* * It does not lock socket since today. This function is
* * free of race conditions. This measure should/can improve
* * significantly datagram socket latencies at high loads,
* * when data copying to user space takes lots of time.
* * (BTW I've just killed the last cli() in IP/IPv6/core/netlink/packet
* * 8) Great win.)
* * --ANK (980729)
*
* The order of the tests when we find no data waiting are specified
* quite explicitly by POSIX 1003.1g, don't change them without having
* the standard around please.
*/
struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
struct sk_buff_head *queue,
unsigned int flags, int *off, int *err,
struct sk_buff **last)
{
struct sk_buff *skb;
unsigned long cpu_flags;
/*
* Caller is allowed not to check sk->sk_err before skb_recv_datagram()
*/
int error = sock_error(sk);
if (error)
goto no_packet;
do {
/* Again only user level code calls this function, so nothing
* interrupt level will suddenly eat the receive_queue.
*
* Look at current nfs client by the way...
* However, this function was correct in any case. 8)
*/
spin_lock_irqsave(&queue->lock, cpu_flags);
skb = __skb_try_recv_from_queue(sk, queue, flags, off, &error,
last);
spin_unlock_irqrestore(&queue->lock, cpu_flags);
if (error)
goto no_packet;
if (skb)
return skb;
if (!sk_can_busy_loop(sk))
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
} while (READ_ONCE(queue->prev) != *last);
error = -EAGAIN;
no_packet:
*err = error;
return NULL;
}
EXPORT_SYMBOL(__skb_try_recv_datagram);
struct sk_buff *__skb_recv_datagram(struct sock *sk,
struct sk_buff_head *sk_queue,
unsigned int flags, int *off, int *err)
{
struct sk_buff *skb, *last;
long timeo;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
skb = __skb_try_recv_datagram(sk, sk_queue, flags, off, err,
&last);
if (skb)
return skb;
if (*err != -EAGAIN)
break;
} while (timeo &&
!__skb_wait_for_more_packets(sk, sk_queue, err,
&timeo, last));
return NULL;
}
EXPORT_SYMBOL(__skb_recv_datagram);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
int *err)
{
int off = 0;
return __skb_recv_datagram(sk, &sk->sk_receive_queue, flags,
&off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);
void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
{
consume_skb(skb);
}
EXPORT_SYMBOL(skb_free_datagram);
int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
struct sk_buff *skb, unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb))
{
int err = 0;
if (flags & MSG_PEEK) {
err = -ENOENT;
spin_lock_bh(&sk_queue->lock);
if (skb->next) {
__skb_unlink(skb, sk_queue);
refcount_dec(&skb->users);
if (destructor)
destructor(sk, skb);
err = 0;
}
spin_unlock_bh(&sk_queue->lock);
}
atomic_inc(&sk->sk_drops);
return err;
}
EXPORT_SYMBOL(__sk_queue_drop_skb);
/**
* skb_kill_datagram - Free a datagram skbuff forcibly
* @sk: socket
* @skb: datagram skbuff
* @flags: MSG\_ flags
*
* This function frees a datagram skbuff that was received by
* skb_recv_datagram. The flags argument must match the one
* used for skb_recv_datagram.
*
* If the MSG_PEEK flag is set, and the packet is still on the
* receive queue of the socket, it will be taken off the queue
* before it is freed.
*
* This function currently only disables BH when acquiring the
* sk_receive_queue lock. Therefore it must not be used in a
* context where that lock is acquired in an IRQ context.
*
* It returns 0 if the packet was removed by us.
*/
int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
{
int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags,
NULL);
kfree_skb(skb);
return err;
}
EXPORT_SYMBOL(skb_kill_datagram);
INDIRECT_CALLABLE_DECLARE(static size_t simple_copy_to_iter(const void *addr,
size_t bytes,
void *data __always_unused,
struct iov_iter *i));
static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len, bool fault_short,
size_t (*cb)(const void *, size_t, void *,
struct iov_iter *), void *data)
{
int start = skb_headlen(skb);
int i, copy = start - offset, start_off = offset, n;
struct sk_buff *frag_iter;
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
skb->data + offset, copy, data, to);
offset += n;
if (n != copy)
goto short_copy;
if ((len -= copy) == 0)
return 0;
}
if (!skb_frags_readable(skb))
goto short_copy;
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
if (copy > len)
copy = len;
n = 0;
skb_frag_foreach_page(frag,
skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_local_page(p);
n += INDIRECT_CALL_1(cb, simple_copy_to_iter,
vaddr + p_off, p_len, data, to);
kunmap_local(vaddr);
}
offset += n;
if (n != copy)
goto short_copy;
if (!(len -= copy))
return 0;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (__skb_datagram_iter(frag_iter, offset - start,
to, copy, fault_short, cb, data))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
start = end;
}
if (!len)
return 0;
/* This is not really a user copy fault, but rather someone
* gave us a bogus length on the skb. We should probably
* print a warning here as it may indicate a kernel bug.
*/
fault:
iov_iter_revert(to, offset - start_off);
return -EFAULT;
short_copy:
if (fault_short || iov_iter_count(to))
goto fault;
return 0;
}
static size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
struct iov_iter *i)
{
#ifdef CONFIG_CRYPTO_HASH
struct ahash_request *hash = hashp;
struct scatterlist sg;
size_t copied;
copied = copy_to_iter(addr, bytes, i);
sg_init_one(&sg, addr, copied);
ahash_request_set_crypt(hash, &sg, NULL, copied);
crypto_ahash_update(hash);
return copied;
#else
return 0;
#endif
}
/**
* skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator
* and update a hash.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
* @to: iovec iterator to copy to
* @len: amount of data to copy from buffer to iovec
* @hash: hash request to update
*/
int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len,
struct ahash_request *hash)
{
return __skb_datagram_iter(skb, offset, to, len, true,
hash_and_copy_to_iter, hash);
}
EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter);
static size_t simple_copy_to_iter(const void *addr, size_t bytes,
void *data __always_unused, struct iov_iter *i)
{
return copy_to_iter(addr, bytes, i);
}
/**
* skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
* @to: iovec iterator to copy to
* @len: amount of data to copy from buffer to iovec
*/
int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len)
{
trace_skb_copy_datagram_iovec(skb, len);
return __skb_datagram_iter(skb, offset, to, len, false,
simple_copy_to_iter, NULL);
}
EXPORT_SYMBOL(skb_copy_datagram_iter);
/**
* skb_copy_datagram_from_iter - Copy a datagram from an iov_iter.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying to
* @from: the copy source
* @len: amount of data to copy to buffer from iovec
*
* Returns 0 or -EFAULT.
*/
int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
struct iov_iter *from,
int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
if (copy_from_iter(skb->data + offset, copy, from) != copy)
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
size_t copied;
if (copy > len)
copy = len;
copied = copy_page_from_iter(skb_frag_page(frag),
skb_frag_off(frag) + offset - start,
copy, from);
if (copied != copy)
goto fault;
if (!(len -= copy))
return 0;
offset += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_datagram_from_iter(frag_iter,
offset - start,
from, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
}
start = end;
}
if (!len)
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_datagram_from_iter);
int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
struct iov_iter *from, size_t length)
{
int frag = skb_shinfo(skb)->nr_frags;
if (!skb_frags_readable(skb))
return -EFAULT;
while (length && iov_iter_count(from)) {
struct page *head, *last_head = NULL;
struct page *pages[MAX_SKB_FRAGS];
int refs, order, n = 0;
size_t start;
ssize_t copied;
if (frag == MAX_SKB_FRAGS)
return -EMSGSIZE;
copied = iov_iter_get_pages2(from, pages, length,
MAX_SKB_FRAGS - frag, &start);
if (copied < 0)
return -EFAULT;
length -= copied;
skb->data_len += copied;
skb->len += copied;
skb->truesize += PAGE_ALIGN(copied + start);
head = compound_head(pages[n]);
order = compound_order(head);
for (refs = 0; copied != 0; start = 0) {
int size = min_t(int, copied, PAGE_SIZE - start);
if (pages[n] - head > (1UL << order) - 1) {
head = compound_head(pages[n]);
order = compound_order(head);
}
start += (pages[n] - head) << PAGE_SHIFT;
copied -= size;
n++;
if (frag) {
skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1];
if (head == skb_frag_page(last) &&
start == skb_frag_off(last) + skb_frag_size(last)) {
skb_frag_size_add(last, size);
/* We combined this page, we need to release
* a reference. Since compound pages refcount
* is shared among many pages, batch the refcount
* adjustments to limit false sharing.
*/
last_head = head;
refs++;
continue;
}
}
if (refs) {
page_ref_sub(last_head, refs);
refs = 0;
}
skb_fill_page_desc_noacc(skb, frag++, head, start, size);
}
if (refs)
page_ref_sub(last_head, refs);
}
return 0;
}
int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, struct iov_iter *from,
size_t length)
{
unsigned long orig_size = skb->truesize;
unsigned long truesize;
int ret;
if (msg && msg->msg_ubuf && msg->sg_from_iter)
ret = msg->sg_from_iter(skb, from, length);
else
ret = zerocopy_fill_skb_from_iter(skb, from, length);
truesize = skb->truesize - orig_size;
if (sk && sk->sk_type == SOCK_STREAM) {
sk_wmem_queued_add(sk, truesize);
if (!skb_zcopy_pure(skb))
sk_mem_charge(sk, truesize);
} else {
refcount_add(truesize, &skb->sk->sk_wmem_alloc);
}
return ret;
}
EXPORT_SYMBOL(__zerocopy_sg_from_iter);
/**
* zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter
* @skb: buffer to copy
* @from: the source to copy from
*
* The function will first copy up to headlen, and then pin the userspace
* pages and build frags through them.
*
* Returns 0, -EFAULT or -EMSGSIZE.
*/
int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
{
int copy = min_t(int, skb_headlen(skb), iov_iter_count(from));
/* copy up to skb headlen */
if (skb_copy_datagram_from_iter(skb, 0, from, copy))
return -EFAULT;
return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
}
EXPORT_SYMBOL(zerocopy_sg_from_iter);
static __always_inline
size_t copy_to_user_iter_csum(void __user *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
__wsum next, *csum = priv2;
next = csum_and_copy_to_user(from + progress, iter_to, len);
*csum = csum_block_add(*csum, next, progress);
return next ? 0 : len;
}
static __always_inline
size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
__wsum *csum = priv2;
__wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
*csum = csum_block_add(*csum, next, progress);
return 0;
}
struct csum_state {
__wsum csum;
size_t off;
};
static size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
struct iov_iter *i)
{
struct csum_state *csstate = _csstate;
__wsum sum;
if (WARN_ON_ONCE(i->data_source))
return 0;
if (unlikely(iov_iter_is_discard(i))) {
// can't use csum_memcpy() for that one - data is not copied
csstate->csum = csum_block_add(csstate->csum,
csum_partial(addr, bytes, 0),
csstate->off);
csstate->off += bytes;
return bytes;
}
sum = csum_shift(csstate->csum, csstate->off);
bytes = iterate_and_advance2(i, bytes, (void *)addr, &sum,
copy_to_user_iter_csum,
memcpy_to_iter_csum);
csstate->csum = csum_shift(sum, csstate->off);
csstate->off += bytes;
return bytes;
}
/**
* skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
* and update a checksum.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
* @to: iovec iterator to copy to
* @len: amount of data to copy from buffer to iovec
* @csump: checksum pointer
*/
static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len,
__wsum *csump)
{
struct csum_state csdata = { .csum = *csump };
int ret;
ret = __skb_datagram_iter(skb, offset, to, len, true,
csum_and_copy_to_iter, &csdata);
if (ret)
return ret;
*csump = csdata.csum;
return 0;
}
/**
* skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
* @skb: skbuff
* @hlen: hardware length
* @msg: destination
*
* Caller _must_ check that skb will fit to this iovec.
*
* Returns: 0 - success.
* -EINVAL - checksum failure.
* -EFAULT - fault during copy.
*/
int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
int hlen, struct msghdr *msg)
{
__wsum csum;
int chunk = skb->len - hlen;
if (!chunk)
return 0;
if (msg_data_left(msg) < chunk) {
if (__skb_checksum_complete(skb))
return -EINVAL;
if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
goto fault;
} else {
csum = csum_partial(skb->data, hlen, skb->csum);
if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
chunk, &csum))
goto fault;
if (csum_fold(csum)) {
iov_iter_revert(&msg->msg_iter, chunk);
return -EINVAL;
}
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
netdev_rx_csum_fault(NULL, skb);
}
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
/**
* datagram_poll - generic datagram poll
* @file: file struct
* @sock: socket
* @wait: poll table
*
* Datagram poll: Again totally generic. This also handles
* sequenced packet sockets providing the socket receive queue
* is only ever holding data ready to receive.
*
* Note: when you *don't* use this routine for this protocol,
* and you use a different write policy from sock_writeable()
* then please supply your own write_space callback.
*/
__poll_t datagram_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask;
u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
/* exceptional events? */
if (READ_ONCE(sk->sk_err) ||
!skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
shutdown = READ_ONCE(sk->sk_shutdown);
if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (connection_based(sk)) {
int state = READ_ONCE(sk->sk_state);
if (state == TCP_CLOSE)
mask |= EPOLLHUP;
/* connection hasn't started yet? */
if (state == TCP_SYN_SENT)
return mask;
}
/* writable? */
if (sock_writeable(sk))
mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return mask;
}
EXPORT_SYMBOL(datagram_poll);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* fscrypt_private.h
*
* Copyright (C) 2015, Google, Inc.
*
* Originally written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar.
* Heavily modified since then.
*/
#ifndef _FSCRYPT_PRIVATE_H
#define _FSCRYPT_PRIVATE_H
#include <linux/fscrypt.h>
#include <linux/siphash.h>
#include <crypto/hash.h>
#include <linux/blk-crypto.h>
#define CONST_STRLEN(str) (sizeof(str) - 1)
#define FSCRYPT_FILE_NONCE_SIZE 16
/*
* Minimum size of an fscrypt master key. Note: a longer key will be required
* if ciphers with a 256-bit security strength are used. This is just the
* absolute minimum, which applies when only 128-bit encryption is used.
*/
#define FSCRYPT_MIN_KEY_SIZE 16
#define FSCRYPT_CONTEXT_V1 1
#define FSCRYPT_CONTEXT_V2 2
/* Keep this in sync with include/uapi/linux/fscrypt.h */
#define FSCRYPT_MODE_MAX FSCRYPT_MODE_AES_256_HCTR2
struct fscrypt_context_v1 {
u8 version; /* FSCRYPT_CONTEXT_V1 */
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
};
struct fscrypt_context_v2 {
u8 version; /* FSCRYPT_CONTEXT_V2 */
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 log2_data_unit_size;
u8 __reserved[3];
u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
};
/*
* fscrypt_context - the encryption context of an inode
*
* This is the on-disk equivalent of an fscrypt_policy, stored alongside each
* encrypted file usually in a hidden extended attribute. It contains the
* fields from the fscrypt_policy, in order to identify the encryption algorithm
* and key with which the file is encrypted. It also contains a nonce that was
* randomly generated by fscrypt itself; this is used as KDF input or as a tweak
* to cause different files to be encrypted differently.
*/
union fscrypt_context {
u8 version;
struct fscrypt_context_v1 v1;
struct fscrypt_context_v2 v2;
};
/*
* Return the size expected for the given fscrypt_context based on its version
* number, or 0 if the context version is unrecognized.
*/
static inline int fscrypt_context_size(const union fscrypt_context *ctx)
{
switch (ctx->version) {
case FSCRYPT_CONTEXT_V1:
BUILD_BUG_ON(sizeof(ctx->v1) != 28);
return sizeof(ctx->v1);
case FSCRYPT_CONTEXT_V2:
BUILD_BUG_ON(sizeof(ctx->v2) != 40);
return sizeof(ctx->v2);
}
return 0;
}
/* Check whether an fscrypt_context has a recognized version number and size */
static inline bool fscrypt_context_is_valid(const union fscrypt_context *ctx,
int ctx_size)
{
return ctx_size >= 1 && ctx_size == fscrypt_context_size(ctx);
}
/* Retrieve the context's nonce, assuming the context was already validated */
static inline const u8 *fscrypt_context_nonce(const union fscrypt_context *ctx)
{
switch (ctx->version) {
case FSCRYPT_CONTEXT_V1:
return ctx->v1.nonce;
case FSCRYPT_CONTEXT_V2:
return ctx->v2.nonce;
}
WARN_ON_ONCE(1);
return NULL;
}
union fscrypt_policy {
u8 version;
struct fscrypt_policy_v1 v1;
struct fscrypt_policy_v2 v2;
};
/*
* Return the size expected for the given fscrypt_policy based on its version
* number, or 0 if the policy version is unrecognized.
*/
static inline int fscrypt_policy_size(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return sizeof(policy->v1);
case FSCRYPT_POLICY_V2:
return sizeof(policy->v2);
}
return 0;
}
/* Return the contents encryption mode of a valid encryption policy */
static inline u8
fscrypt_policy_contents_mode(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.contents_encryption_mode;
case FSCRYPT_POLICY_V2:
return policy->v2.contents_encryption_mode;
}
BUG();
}
/* Return the filenames encryption mode of a valid encryption policy */
static inline u8
fscrypt_policy_fnames_mode(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.filenames_encryption_mode;
case FSCRYPT_POLICY_V2:
return policy->v2.filenames_encryption_mode;
}
BUG();
}
/* Return the flags (FSCRYPT_POLICY_FLAG*) of a valid encryption policy */
static inline u8
fscrypt_policy_flags(const union fscrypt_policy *policy)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return policy->v1.flags;
case FSCRYPT_POLICY_V2:
return policy->v2.flags;
}
BUG();
}
static inline int
fscrypt_policy_v2_du_bits(const struct fscrypt_policy_v2 *policy,
const struct inode *inode)
{
return policy->log2_data_unit_size ?: inode->i_blkbits;
}
static inline int
fscrypt_policy_du_bits(const union fscrypt_policy *policy,
const struct inode *inode)
{
switch (policy->version) {
case FSCRYPT_POLICY_V1:
return inode->i_blkbits;
case FSCRYPT_POLICY_V2:
return fscrypt_policy_v2_du_bits(&policy->v2, inode);
}
BUG();
}
/*
* For encrypted symlinks, the ciphertext length is stored at the beginning
* of the string in little-endian format.
*/
struct fscrypt_symlink_data {
__le16 len;
char encrypted_path[];
} __packed;
/**
* struct fscrypt_prepared_key - a key prepared for actual encryption/decryption
* @tfm: crypto API transform object
* @blk_key: key for blk-crypto
*
* Normally only one of the fields will be non-NULL.
*/
struct fscrypt_prepared_key {
struct crypto_skcipher *tfm;
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
struct blk_crypto_key *blk_key;
#endif
};
/*
* fscrypt_inode_info - the "encryption key" for an inode
*
* When an encrypted file's key is made available, an instance of this struct is
* allocated and stored in ->i_crypt_info. Once created, it remains until the
* inode is evicted.
*/
struct fscrypt_inode_info {
/* The key in a form prepared for actual encryption/decryption */
struct fscrypt_prepared_key ci_enc_key;
/* True if ci_enc_key should be freed when this struct is freed */
u8 ci_owns_key : 1;
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
/*
* True if this inode will use inline encryption (blk-crypto) instead of
* the traditional filesystem-layer encryption.
*/
u8 ci_inlinecrypt : 1;
#endif
/* True if ci_dirhash_key is initialized */
u8 ci_dirhash_key_initialized : 1;
/*
* log2 of the data unit size (granularity of contents encryption) of
* this file. This is computable from ci_policy and ci_inode but is
* cached here for efficiency. Only used for regular files.
*/
u8 ci_data_unit_bits;
/* Cached value: log2 of number of data units per FS block */
u8 ci_data_units_per_block_bits;
/* Hashed inode number. Only set for IV_INO_LBLK_32 */
u32 ci_hashed_ino;
/*
* Encryption mode used for this inode. It corresponds to either the
* contents or filenames encryption mode, depending on the inode type.
*/
struct fscrypt_mode *ci_mode;
/* Back-pointer to the inode */
struct inode *ci_inode;
/*
* The master key with which this inode was unlocked (decrypted). This
* will be NULL if the master key was found in a process-subscribed
* keyring rather than in the filesystem-level keyring.
*/
struct fscrypt_master_key *ci_master_key;
/*
* Link in list of inodes that were unlocked with the master key.
* Only used when ->ci_master_key is set.
*/
struct list_head ci_master_key_link;
/*
* If non-NULL, then encryption is done using the master key directly
* and ci_enc_key will equal ci_direct_key->dk_key.
*/
struct fscrypt_direct_key *ci_direct_key;
/*
* This inode's hash key for filenames. This is a 128-bit SipHash-2-4
* key. This is only set for directories that use a keyed dirhash over
* the plaintext filenames -- currently just casefolded directories.
*/
siphash_key_t ci_dirhash_key;
/* The encryption policy used by this inode */
union fscrypt_policy ci_policy;
/* This inode's nonce, copied from the fscrypt_context */
u8 ci_nonce[FSCRYPT_FILE_NONCE_SIZE];
};
typedef enum {
FS_DECRYPT = 0,
FS_ENCRYPT,
} fscrypt_direction_t;
/* crypto.c */
extern struct kmem_cache *fscrypt_inode_info_cachep;
int fscrypt_initialize(struct super_block *sb);
int fscrypt_crypt_data_unit(const struct fscrypt_inode_info *ci,
fscrypt_direction_t rw, u64 index,
struct page *src_page, struct page *dest_page,
unsigned int len, unsigned int offs,
gfp_t gfp_flags);
struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags);
void __printf(3, 4) __cold
fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...);
#define fscrypt_warn(inode, fmt, ...) \
fscrypt_msg((inode), KERN_WARNING, fmt, ##__VA_ARGS__)
#define fscrypt_err(inode, fmt, ...) \
fscrypt_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__)
#define FSCRYPT_MAX_IV_SIZE 32
union fscrypt_iv {
struct {
/* zero-based index of data unit within the file */
__le64 index;
/* per-file nonce; only set in DIRECT_KEY mode */
u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
};
u8 raw[FSCRYPT_MAX_IV_SIZE];
__le64 dun[FSCRYPT_MAX_IV_SIZE / sizeof(__le64)];
};
void fscrypt_generate_iv(union fscrypt_iv *iv, u64 index,
const struct fscrypt_inode_info *ci);
/*
* Return the number of bits used by the maximum file data unit index that is
* possible on the given filesystem, using the given log2 data unit size.
*/
static inline int
fscrypt_max_file_dun_bits(const struct super_block *sb, int du_bits)
{
return fls64(sb->s_maxbytes - 1) - du_bits;
}
/* fname.c */
bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
u32 orig_len, u32 max_len,
u32 *encrypted_len_ret);
/* hkdf.c */
struct fscrypt_hkdf {
struct crypto_shash *hmac_tfm;
};
int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
unsigned int master_key_size);
/*
* The list of contexts in which fscrypt uses HKDF. These values are used as
* the first byte of the HKDF application-specific info string to guarantee that
* info strings are never repeated between contexts. This ensures that all HKDF
* outputs are unique and cryptographically isolated, i.e. knowledge of one
* output doesn't reveal another.
*/
#define HKDF_CONTEXT_KEY_IDENTIFIER 1 /* info=<empty> */
#define HKDF_CONTEXT_PER_FILE_ENC_KEY 2 /* info=file_nonce */
#define HKDF_CONTEXT_DIRECT_KEY 3 /* info=mode_num */
#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 /* info=mode_num||fs_uuid */
#define HKDF_CONTEXT_DIRHASH_KEY 5 /* info=file_nonce */
#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 /* info=mode_num||fs_uuid */
#define HKDF_CONTEXT_INODE_HASH_KEY 7 /* info=<empty> */
int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context,
const u8 *info, unsigned int infolen,
u8 *okm, unsigned int okmlen);
void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
/* inline_crypt.c */
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci);
static inline bool
fscrypt_using_inline_encryption(const struct fscrypt_inode_info *ci)
{
return ci->ci_inlinecrypt;
}
int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
const u8 *raw_key,
const struct fscrypt_inode_info *ci);
void fscrypt_destroy_inline_crypt_key(struct super_block *sb,
struct fscrypt_prepared_key *prep_key);
/*
* Check whether the crypto transform or blk-crypto key has been allocated in
* @prep_key, depending on which encryption implementation the file will use.
*/
static inline bool
fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key,
const struct fscrypt_inode_info *ci)
{
/*
* The two smp_load_acquire()'s here pair with the smp_store_release()'s
* in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key().
* I.e., in some cases (namely, if this prep_key is a per-mode
* encryption key) another task can publish blk_key or tfm concurrently,
* executing a RELEASE barrier. We need to use smp_load_acquire() here
* to safely ACQUIRE the memory the other task published.
*/
if (fscrypt_using_inline_encryption(ci))
return smp_load_acquire(&prep_key->blk_key) != NULL;
return smp_load_acquire(&prep_key->tfm) != NULL;
}
#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
static inline int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci)
{
return 0;
}
static inline bool
fscrypt_using_inline_encryption(const struct fscrypt_inode_info *ci)
{
return false;
}
static inline int
fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
const u8 *raw_key,
const struct fscrypt_inode_info *ci)
{
WARN_ON_ONCE(1);
return -EOPNOTSUPP;
}
static inline void
fscrypt_destroy_inline_crypt_key(struct super_block *sb,
struct fscrypt_prepared_key *prep_key)
{
}
static inline bool
fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key,
const struct fscrypt_inode_info *ci)
{
return smp_load_acquire(&prep_key->tfm) != NULL;
}
#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */
/* keyring.c */
/*
* fscrypt_master_key_secret - secret key material of an in-use master key
*/
struct fscrypt_master_key_secret {
/*
* For v2 policy keys: HKDF context keyed by this master key.
* For v1 policy keys: not set (hkdf.hmac_tfm == NULL).
*/
struct fscrypt_hkdf hkdf;
/*
* Size of the raw key in bytes. This remains set even if ->raw was
* zeroized due to no longer being needed. I.e. we still remember the
* size of the key even if we don't need to remember the key itself.
*/
u32 size;
/* For v1 policy keys: the raw key. Wiped for v2 policy keys. */
u8 raw[FSCRYPT_MAX_KEY_SIZE];
} __randomize_layout;
/*
* fscrypt_master_key - an in-use master key
*
* This represents a master encryption key which has been added to the
* filesystem. There are three high-level states that a key can be in:
*
* FSCRYPT_KEY_STATUS_PRESENT
* Key is fully usable; it can be used to unlock inodes that are encrypted
* with it (this includes being able to create new inodes). ->mk_present
* indicates whether the key is in this state. ->mk_secret exists, the key
* is in the keyring, and ->mk_active_refs > 0 due to ->mk_present.
*
* FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED
* Removal of this key has been initiated, but some inodes that were
* unlocked with it are still in-use. Like ABSENT, ->mk_secret is wiped,
* and the key can no longer be used to unlock inodes. Unlike ABSENT, the
* key is still in the keyring; ->mk_decrypted_inodes is nonempty; and
* ->mk_active_refs > 0, being equal to the size of ->mk_decrypted_inodes.
*
* This state transitions to ABSENT if ->mk_decrypted_inodes becomes empty,
* or to PRESENT if FS_IOC_ADD_ENCRYPTION_KEY is called again for this key.
*
* FSCRYPT_KEY_STATUS_ABSENT
* Key is fully removed. The key is no longer in the keyring,
* ->mk_decrypted_inodes is empty, ->mk_active_refs == 0, ->mk_secret is
* wiped, and the key can no longer be used to unlock inodes.
*/
struct fscrypt_master_key {
/*
* Link in ->s_master_keys->key_hashtable.
* Only valid if ->mk_active_refs > 0.
*/
struct hlist_node mk_node;
/* Semaphore that protects ->mk_secret, ->mk_users, and ->mk_present */
struct rw_semaphore mk_sem;
/*
* Active and structural reference counts. An active ref guarantees
* that the struct continues to exist, continues to be in the keyring
* ->s_master_keys, and that any embedded subkeys (e.g.
* ->mk_direct_keys) that have been prepared continue to exist.
* A structural ref only guarantees that the struct continues to exist.
*
* There is one active ref associated with ->mk_present being true, and
* one active ref for each inode in ->mk_decrypted_inodes.
*
* There is one structural ref associated with the active refcount being
* nonzero. Finding a key in the keyring also takes a structural ref,
* which is then held temporarily while the key is operated on.
*/
refcount_t mk_active_refs;
refcount_t mk_struct_refs;
struct rcu_head mk_rcu_head;
/*
* The secret key material. Wiped as soon as it is no longer needed;
* for details, see the fscrypt_master_key struct comment.
*
* Locking: protected by ->mk_sem.
*/
struct fscrypt_master_key_secret mk_secret;
/*
* For v1 policy keys: an arbitrary key descriptor which was assigned by
* userspace (->descriptor).
*
* For v2 policy keys: a cryptographic hash of this key (->identifier).
*/
struct fscrypt_key_specifier mk_spec;
/*
* Keyring which contains a key of type 'key_type_fscrypt_user' for each
* user who has added this key. Normally each key will be added by just
* one user, but it's possible that multiple users share a key, and in
* that case we need to keep track of those users so that one user can't
* remove the key before the others want it removed too.
*
* This is NULL for v1 policy keys; those can only be added by root.
*
* Locking: protected by ->mk_sem. (We don't just rely on the keyrings
* subsystem semaphore ->mk_users->sem, as we need support for atomic
* search+insert along with proper synchronization with other fields.)
*/
struct key *mk_users;
/*
* List of inodes that were unlocked using this key. This allows the
* inodes to be evicted efficiently if the key is removed.
*/
struct list_head mk_decrypted_inodes;
spinlock_t mk_decrypted_inodes_lock;
/*
* Per-mode encryption keys for the various types of encryption policies
* that use them. Allocated and derived on-demand.
*/
struct fscrypt_prepared_key mk_direct_keys[FSCRYPT_MODE_MAX + 1];
struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[FSCRYPT_MODE_MAX + 1];
struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[FSCRYPT_MODE_MAX + 1];
/* Hash key for inode numbers. Initialized only when needed. */
siphash_key_t mk_ino_hash_key;
bool mk_ino_hash_key_initialized;
/*
* Whether this key is in the "present" state, i.e. fully usable. For
* details, see the fscrypt_master_key struct comment.
*
* Locking: protected by ->mk_sem, but can be read locklessly using
* READ_ONCE(). Writers must use WRITE_ONCE() when concurrent readers
* are possible.
*/
bool mk_present;
} __randomize_layout;
static inline const char *master_key_spec_type(
const struct fscrypt_key_specifier *spec)
{
switch (spec->type) {
case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
return "descriptor";
case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
return "identifier";
}
return "[unknown]";
}
static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec)
{
switch (spec->type) {
case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
return FSCRYPT_KEY_DESCRIPTOR_SIZE;
case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
return FSCRYPT_KEY_IDENTIFIER_SIZE;
}
return 0;
}
void fscrypt_put_master_key(struct fscrypt_master_key *mk);
void fscrypt_put_master_key_activeref(struct super_block *sb,
struct fscrypt_master_key *mk);
struct fscrypt_master_key *
fscrypt_find_master_key(struct super_block *sb,
const struct fscrypt_key_specifier *mk_spec);
int fscrypt_get_test_dummy_key_identifier(
u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
int fscrypt_add_test_dummy_key(struct super_block *sb,
struct fscrypt_key_specifier *key_spec);
int fscrypt_verify_key_added(struct super_block *sb,
const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
int __init fscrypt_init_keyring(void);
/* keysetup.c */
struct fscrypt_mode {
const char *friendly_name;
const char *cipher_str;
int keysize; /* key size in bytes */
int security_strength; /* security strength in bytes */
int ivsize; /* IV size in bytes */
int logged_cryptoapi_impl;
int logged_blk_crypto_native;
int logged_blk_crypto_fallback;
enum blk_crypto_mode_num blk_crypto_mode;
};
extern struct fscrypt_mode fscrypt_modes[];
int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
const u8 *raw_key, const struct fscrypt_inode_info *ci);
void fscrypt_destroy_prepared_key(struct super_block *sb,
struct fscrypt_prepared_key *prep_key);
int fscrypt_set_per_file_enc_key(struct fscrypt_inode_info *ci,
const u8 *raw_key);
int fscrypt_derive_dirhash_key(struct fscrypt_inode_info *ci,
const struct fscrypt_master_key *mk);
void fscrypt_hash_inode_number(struct fscrypt_inode_info *ci,
const struct fscrypt_master_key *mk);
int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported);
/**
* fscrypt_require_key() - require an inode's encryption key
* @inode: the inode we need the key for
*
* If the inode is encrypted, set up its encryption key if not already done.
* Then require that the key be present and return -ENOKEY otherwise.
*
* No locks are needed, and the key will live as long as the struct inode --- so
* it won't go away from under you.
*
* Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
* if a problem occurred while setting up the encryption key.
*/
static inline int fscrypt_require_key(struct inode *inode)
{
if (IS_ENCRYPTED(inode)) {
int err = fscrypt_get_encryption_info(inode, false);
if (err)
return err;
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
return 0;
}
/* keysetup_v1.c */
void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
int fscrypt_setup_v1_file_key(struct fscrypt_inode_info *ci,
const u8 *raw_master_key);
int fscrypt_setup_v1_file_key_via_subscribed_keyrings(
struct fscrypt_inode_info *ci);
/* policy.c */
bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
const union fscrypt_policy *policy2);
int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy,
struct fscrypt_key_specifier *key_spec);
const union fscrypt_policy *fscrypt_get_dummy_policy(struct super_block *sb);
bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
const struct inode *inode);
int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
const union fscrypt_context *ctx_u,
int ctx_size);
const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir);
#endif /* _FSCRYPT_PRIVATE_H */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Fast Userspace Mutexes (which I call "Futexes!").
* (C) Rusty Russell, IBM 2002
*
* Generalized futexes, futex requeueing, misc fixes by Ingo Molnar
* (C) Copyright 2003 Red Hat Inc, All Rights Reserved
*
* Removed page pinning, fix privately mapped COW pages and other cleanups
* (C) Copyright 2003, 2004 Jamie Lokier
*
* Robust futex support started by Ingo Molnar
* (C) Copyright 2006 Red Hat Inc, All Rights Reserved
* Thanks to Thomas Gleixner for suggestions, analysis and fixes.
*
* PI-futex support started by Ingo Molnar and Thomas Gleixner
* Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
* Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
*
* PRIVATE futexes by Eric Dumazet
* Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
*
* Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
* Copyright (C) IBM Corporation, 2009
* Thanks to Thomas Gleixner for conceptual design and careful reviews.
*
* Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
* enough at me, Linus for the original (flawed) idea, Matthew
* Kirkwood for proof-of-concept implementation.
*
* "The futexes are also cursed."
* "But they come in a choice of three flavours!"
*/
#include <linux/compat.h>
#include <linux/jhash.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/plist.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
#include <linux/slab.h>
#include "futex.h"
#include "../locking/rtmutex_common.h"
/*
* The base of the bucket array and its size are always used together
* (after initialization only in futex_hash()), so ensure that they
* reside in the same cacheline.
*/
static struct {
struct futex_hash_bucket *queues;
unsigned long hashmask;
} __futex_data __read_mostly __aligned(2*sizeof(long));
#define futex_queues (__futex_data.queues)
#define futex_hashmask (__futex_data.hashmask)
/*
* Fault injections for futexes.
*/
#ifdef CONFIG_FAIL_FUTEX
static struct {
struct fault_attr attr;
bool ignore_private;
} fail_futex = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_private = false,
};
static int __init setup_fail_futex(char *str)
{
return setup_fault_attr(&fail_futex.attr, str);
}
__setup("fail_futex=", setup_fail_futex);
bool should_fail_futex(bool fshared)
{
if (fail_futex.ignore_private && !fshared)
return false;
return should_fail(&fail_futex.attr, 1);
}
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int __init fail_futex_debugfs(void)
{
umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
dir = fault_create_debugfs_attr("fail_futex", NULL,
&fail_futex.attr);
if (IS_ERR(dir))
return PTR_ERR(dir);
debugfs_create_bool("ignore-private", mode, dir,
&fail_futex.ignore_private);
return 0;
}
late_initcall(fail_futex_debugfs);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
#endif /* CONFIG_FAIL_FUTEX */
/**
* futex_hash - Return the hash bucket in the global hash
* @key: Pointer to the futex key for which the hash is calculated
*
* We hash on the keys returned from get_futex_key (see below) and return the
* corresponding hash bucket in the global hash.
*/
struct futex_hash_bucket *futex_hash(union futex_key *key)
{
u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
key->both.offset);
return &futex_queues[hash & futex_hashmask];
}
/**
* futex_setup_timer - set up the sleeping hrtimer.
* @time: ptr to the given timeout value
* @timeout: the hrtimer_sleeper structure to be set up
* @flags: futex flags
* @range_ns: optional range in ns
*
* Return: Initialized hrtimer_sleeper structure or NULL if no timeout
* value given
*/
struct hrtimer_sleeper *
futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
int flags, u64 range_ns)
{ if (!time)
return NULL;
hrtimer_setup_sleeper_on_stack(timeout,
(flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC,
HRTIMER_MODE_ABS);
/*
* If range_ns is 0, calling hrtimer_set_expires_range_ns() is
* effectively the same as calling hrtimer_set_expires().
*/
hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns);
return timeout;
}
/*
* Generate a machine wide unique identifier for this inode.
*
* This relies on u64 not wrapping in the life-time of the machine; which with
* 1ns resolution means almost 585 years.
*
* This further relies on the fact that a well formed program will not unmap
* the file while it has a (shared) futex waiting on it. This mapping will have
* a file reference which pins the mount and inode.
*
* If for some reason an inode gets evicted and read back in again, it will get
* a new sequence number and will _NOT_ match, even though it is the exact same
* file.
*
* It is important that futex_match() will never have a false-positive, esp.
* for PI futexes that can mess up the state. The above argues that false-negatives
* are only possible for malformed programs.
*/
static u64 get_inode_sequence_number(struct inode *inode)
{
static atomic64_t i_seq;
u64 old;
/* Does the inode already have a sequence number? */
old = atomic64_read(&inode->i_sequence);
if (likely(old))
return old;
for (;;) {
u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new))
continue;
old = 0;
if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old;
return new;
}
}
/**
* get_futex_key() - Get parameters which are the keys for a futex
* @uaddr: virtual address of the futex
* @flags: FLAGS_*
* @key: address where result is stored.
* @rw: mapping needs to be read/write (values: FUTEX_READ,
* FUTEX_WRITE)
*
* Return: a negative error code or 0
*
* The key words are stored in @key on success.
*
* For shared mappings (when @fshared), the key is:
*
* ( inode->i_sequence, page->index, offset_within_page )
*
* [ also see get_inode_sequence_number() ]
*
* For private mappings (or when !@fshared), the key is:
*
* ( current->mm, address, 0 )
*
* This allows (cross process, where applicable) identification of the futex
* without keeping the page pinned for the duration of the FUTEX_WAIT.
*
* lock_page() might sleep, the caller should not hold a spinlock.
*/
int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
enum futex_access rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
struct page *page;
struct folio *folio;
struct address_space *mapping;
int err, ro = 0;
bool fshared;
fshared = flags & FLAGS_SHARED;
/*
* The futex address must be "naturally" aligned.
*/
key->both.offset = address % PAGE_SIZE;
if (unlikely((address % sizeof(u32)) != 0))
return -EINVAL;
address -= key->both.offset;
if (unlikely(!access_ok(uaddr, sizeof(u32))))
return -EFAULT;
if (unlikely(should_fail_futex(fshared)))
return -EFAULT;
/*
* PROCESS_PRIVATE futexes are fast.
* As the mm cannot disappear under us and the 'key' only needs
* virtual address, we dont even have to find the underlying vma.
* Note : We do have to check 'uaddr' is a valid user address,
* but access_ok() should be faster than find_vma()
*/
if (!fshared) {
/*
* On no-MMU, shared futexes are treated as private, therefore
* we must not include the current process in the key. Since
* there is only one address space, the address is a unique key
* on its own.
*/
if (IS_ENABLED(CONFIG_MMU))
key->private.mm = mm;
else
key->private.mm = NULL;
key->private.address = address;
return 0;
}
again:
/* Ignore any VERIFY_READ mapping (futex common case) */
if (unlikely(should_fail_futex(true)))
return -EFAULT;
err = get_user_pages_fast(address, 1, FOLL_WRITE, &page);
/*
* If write access is not required (eg. FUTEX_WAIT), try
* and get read-only access.
*/
if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page);
ro = 1;
}
if (err < 0)
return err;
else
err = 0;
/*
* The treatment of mapping from this point on is critical. The folio
* lock protects many things but in this context the folio lock
* stabilizes mapping, prevents inode freeing in the shared
* file-backed region case and guards against movement to swap cache.
*
* Strictly speaking the folio lock is not needed in all cases being
* considered here and folio lock forces unnecessarily serialization.
* From this point on, mapping will be re-verified if necessary and
* folio lock will be acquired only if it is unavoidable
*
* Mapping checks require the folio so it is looked up now. For
* anonymous pages, it does not matter if the folio is split
* in the future as the key is based on the address. For
* filesystem-backed pages, the precise page is required as the
* index of the page determines the key.
*/
folio = page_folio(page);
mapping = READ_ONCE(folio->mapping);
/*
* If folio->mapping is NULL, then it cannot be an anonymous
* page; but it might be the ZERO_PAGE or in the gate area or
* in a special mapping (all cases which we are happy to fail);
* or it may have been a good file page when get_user_pages_fast
* found it, but truncated or holepunched or subjected to
* invalidate_complete_page2 before we got the folio lock (also
* cases which we are happy to fail). And we hold a reference,
* so refcount care in invalidate_inode_page's remove_mapping
* prevents drop_caches from setting mapping to NULL beneath us.
*
* The case we do have to guard against is when memory pressure made
* shmem_writepage move it from filecache to swapcache beneath us:
* an unlikely race, but we do need to retry for folio->mapping.
*/
if (unlikely(!mapping)) {
int shmem_swizzled;
/*
* Folio lock is required to identify which special case above
* applies. If this is really a shmem page then the folio lock
* will prevent unexpected transitions.
*/
folio_lock(folio);
shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio);
folio_put(folio);
if (shmem_swizzled)
goto again;
return -EFAULT;
}
/*
* Private mappings are handled in a simple way.
*
* If the futex key is stored in anonymous memory, then the associated
* object is the mm which is implicitly pinned by the calling process.
*
* NOTE: When userspace waits on a MAP_SHARED mapping, even if
* it's a read-only handle, it's expected that futexes attach to
* the object not the particular process.
*/
if (folio_test_anon(folio)) {
/*
* A RO anonymous page will never change and thus doesn't make
* sense for futex operations.
*/
if (unlikely(should_fail_futex(true)) || ro) {
err = -EFAULT;
goto out;
}
key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
key->private.mm = mm;
key->private.address = address;
} else {
struct inode *inode;
/*
* The associated futex object in this case is the inode and
* the folio->mapping must be traversed. Ordinarily this should
* be stabilised under folio lock but it's not strictly
* necessary in this case as we just want to pin the inode, not
* update i_pages or anything like that.
*
* The RCU read lock is taken as the inode is finally freed
* under RCU. If the mapping still matches expectations then the
* mapping->host can be safely accessed as being a valid inode.
*/
rcu_read_lock();
if (READ_ONCE(folio->mapping) != mapping) {
rcu_read_unlock(); folio_put(folio);
goto again;
}
inode = READ_ONCE(mapping->host);
if (!inode) {
rcu_read_unlock(); folio_put(folio);
goto again;
}
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.i_seq = get_inode_sequence_number(inode);
key->shared.pgoff = page_pgoff(folio, page);
rcu_read_unlock();
}
out:
folio_put(folio);
return err;
}
/**
* fault_in_user_writeable() - Fault in user address and verify RW access
* @uaddr: pointer to faulting user space address
*
* Slow path to fixup the fault we just took in the atomic write
* access to @uaddr.
*
* We have no generic implementation of a non-destructive write to the
* user address. We know that we faulted in the atomic pagefault
* disabled section so we can as well avoid the #PF overhead by
* calling get_user_pages() right away.
*/
int fault_in_user_writeable(u32 __user *uaddr)
{
struct mm_struct *mm = current->mm;
int ret;
mmap_read_lock(mm);
ret = fixup_user_fault(mm, (unsigned long)uaddr,
FAULT_FLAG_WRITE, NULL);
mmap_read_unlock(mm);
return ret < 0 ? ret : 0;
}
/**
* futex_top_waiter() - Return the highest priority waiter on a futex
* @hb: the hash bucket the futex_q's reside in
* @key: the futex key (to distinguish it from other futex futex_q's)
*
* Must be called with the hb lock held.
*/
struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key)
{
struct futex_q *this;
plist_for_each_entry(this, &hb->chain, list) {
if (futex_match(&this->key, key))
return this;
}
return NULL;
}
/**
* wait_for_owner_exiting - Block until the owner has exited
* @ret: owner's current futex lock status
* @exiting: Pointer to the exiting task
*
* Caller must hold a refcount on @exiting.
*/
void wait_for_owner_exiting(int ret, struct task_struct *exiting)
{
if (ret != -EBUSY) {
WARN_ON_ONCE(exiting);
return;
}
if (WARN_ON_ONCE(ret == -EBUSY && !exiting))
return;
mutex_lock(&exiting->futex_exit_mutex);
/*
* No point in doing state checking here. If the waiter got here
* while the task was in exec()->exec_futex_release() then it can
* have any FUTEX_STATE_* value when the waiter has acquired the
* mutex. OK, if running, EXITING or DEAD if it reached exit()
* already. Highly unlikely and not a problem. Just one more round
* through the futex maze.
*/
mutex_unlock(&exiting->futex_exit_mutex);
put_task_struct(exiting);
}
/**
* __futex_unqueue() - Remove the futex_q from its futex_hash_bucket
* @q: The futex_q to unqueue
*
* The q->lock_ptr must not be NULL and must be held by the caller.
*/
void __futex_unqueue(struct futex_q *q)
{
struct futex_hash_bucket *hb;
if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list)))
return;
lockdep_assert_held(q->lock_ptr);
hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
plist_del(&q->list, &hb->chain);
futex_hb_waiters_dec(hb);
}
/* The key must be already stored in q->key. */
struct futex_hash_bucket *futex_q_lock(struct futex_q *q)
__acquires(&hb->lock)
{
struct futex_hash_bucket *hb;
hb = futex_hash(&q->key);
/*
* Increment the counter before taking the lock so that
* a potential waker won't miss a to-be-slept task that is
* waiting for the spinlock. This is safe as all futex_q_lock()
* users end up calling futex_queue(). Similarly, for housekeeping,
* decrement the counter at futex_q_unlock() when some error has
* occurred and we don't end up adding the task to the list.
*/
futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */
q->lock_ptr = &hb->lock;
spin_lock(&hb->lock);
return hb;
}
void futex_q_unlock(struct futex_hash_bucket *hb)
__releases(&hb->lock)
{
spin_unlock(&hb->lock);
futex_hb_waiters_dec(hb);
}
void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
struct task_struct *task)
{
int prio;
/*
* The priority used to register this element is
* - either the real thread-priority for the real-time threads
* (i.e. threads with a priority lower than MAX_RT_PRIO)
* - or MAX_RT_PRIO for non-RT threads.
* Thus, all RT-threads are woken first in priority order, and
* the others are woken last, in FIFO order.
*/
prio = min(current->normal_prio, MAX_RT_PRIO);
plist_node_init(&q->list, prio);
plist_add(&q->list, &hb->chain);
q->task = task;
}
/**
* futex_unqueue() - Remove the futex_q from its futex_hash_bucket
* @q: The futex_q to unqueue
*
* The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must
* be paired with exactly one earlier call to futex_queue().
*
* Return:
* - 1 - if the futex_q was still queued (and we removed unqueued it);
* - 0 - if the futex_q was already removed by the waking thread
*/
int futex_unqueue(struct futex_q *q)
{
spinlock_t *lock_ptr;
int ret = 0;
/* In the common case we don't take the spinlock, which is nice. */
retry:
/*
* q->lock_ptr can change between this read and the following spin_lock.
* Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
* optimizing lock_ptr out of the logic below.
*/
lock_ptr = READ_ONCE(q->lock_ptr);
if (lock_ptr != NULL) {
spin_lock(lock_ptr);
/*
* q->lock_ptr can change between reading it and
* spin_lock(), causing us to take the wrong lock. This
* corrects the race condition.
*
* Reasoning goes like this: if we have the wrong lock,
* q->lock_ptr must have changed (maybe several times)
* between reading it and the spin_lock(). It can
* change again after the spin_lock() but only if it was
* already changed before the spin_lock(). It cannot,
* however, change back to the original value. Therefore
* we can detect whether we acquired the correct lock.
*/
if (unlikely(lock_ptr != q->lock_ptr)) {
spin_unlock(lock_ptr);
goto retry;
}
__futex_unqueue(q);
BUG_ON(q->pi_state);
spin_unlock(lock_ptr);
ret = 1;
}
return ret;
}
/*
* PI futexes can not be requeued and must remove themselves from the hash
* bucket. The hash bucket lock (i.e. lock_ptr) is held.
*/
void futex_unqueue_pi(struct futex_q *q)
{
/*
* If the lock was not acquired (due to timeout or signal) then the
* rt_waiter is removed before futex_q is. If this is observed by
* an unlocker after dropping the rtmutex wait lock and before
* acquiring the hash bucket lock, then the unlocker dequeues the
* futex_q from the hash bucket list to guarantee consistent state
* vs. userspace. Therefore the dequeue here must be conditional.
*/
if (!plist_node_empty(&q->list))
__futex_unqueue(q);
BUG_ON(!q->pi_state);
put_pi_state(q->pi_state);
q->pi_state = NULL;
}
/* Constants for the pending_op argument of handle_futex_death */
#define HANDLE_DEATH_PENDING true
#define HANDLE_DEATH_LIST false
/*
* Process a futex-list entry, check whether it's owned by the
* dying task, and do notification if so:
*/
static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
bool pi, bool pending_op)
{
u32 uval, nval, mval;
pid_t owner;
int err;
/* Futex address must be 32bit aligned */
if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
return -1;
retry:
if (get_user(uval, uaddr))
return -1;
/*
* Special case for regular (non PI) futexes. The unlock path in
* user space has two race scenarios:
*
* 1. The unlock path releases the user space futex value and
* before it can execute the futex() syscall to wake up
* waiters it is killed.
*
* 2. A woken up waiter is killed before it can acquire the
* futex in user space.
*
* In the second case, the wake up notification could be generated
* by the unlock path in user space after setting the futex value
* to zero or by the kernel after setting the OWNER_DIED bit below.
*
* In both cases the TID validation below prevents a wakeup of
* potential waiters which can cause these waiters to block
* forever.
*
* In both cases the following conditions are met:
*
* 1) task->robust_list->list_op_pending != NULL
* @pending_op == true
* 2) The owner part of user space futex value == 0
* 3) Regular futex: @pi == false
*
* If these conditions are met, it is safe to attempt waking up a
* potential waiter without touching the user space futex value and
* trying to set the OWNER_DIED bit. If the futex value is zero,
* the rest of the user space mutex state is consistent, so a woken
* waiter will just take over the uncontended futex. Setting the
* OWNER_DIED bit would create inconsistent state and malfunction
* of the user space owner died handling. Otherwise, the OWNER_DIED
* bit is already set, and the woken waiter is expected to deal with
* this.
*/
owner = uval & FUTEX_TID_MASK;
if (pending_op && !pi && !owner) {
futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
FUTEX_BITSET_MATCH_ANY);
return 0;
}
if (owner != task_pid_vnr(curr))
return 0;
/*
* Ok, this dying thread is truly holding a futex
* of interest. Set the OWNER_DIED bit atomically
* via cmpxchg, and if the value had FUTEX_WAITERS
* set, wake up a waiter (if any). (We have to do a
* futex_wake() even if OWNER_DIED is already set -
* to handle the rare but possible case of recursive
* thread-death.) The rest of the cleanup is done in
* userspace.
*/
mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
/*
* We are not holding a lock here, but we want to have
* the pagefault_disable/enable() protection because
* we want to handle the fault gracefully. If the
* access fails we try to fault in the futex with R/W
* verification via get_user_pages. get_user() above
* does not guarantee R/W access. If that fails we
* give up and leave the futex locked.
*/
if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) {
switch (err) {
case -EFAULT:
if (fault_in_user_writeable(uaddr))
return -1;
goto retry;
case -EAGAIN:
cond_resched();
goto retry;
default:
WARN_ON_ONCE(1);
return err;
}
}
if (nval != uval)
goto retry;
/*
* Wake robust non-PI futexes here. The wakeup of
* PI futexes happens in exit_pi_state():
*/
if (!pi && (uval & FUTEX_WAITERS)) {
futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
FUTEX_BITSET_MATCH_ANY);
}
return 0;
}
/*
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int fetch_robust_entry(struct robust_list __user **entry,
struct robust_list __user * __user *head,
unsigned int *pi)
{
unsigned long uentry;
if (get_user(uentry, (unsigned long __user *)head))
return -EFAULT;
*entry = (void __user *)(uentry & ~1UL);
*pi = uentry & 1;
return 0;
}
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
static void exit_robust_list(struct task_struct *curr)
{
struct robust_list_head __user *head = curr->robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
unsigned long futex_offset;
int rc;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
if (fetch_robust_entry(&entry, &head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
*/
if (get_user(futex_offset, &head->futex_offset))
return;
/*
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
return;
next_entry = NULL; /* avoid warning with gcc */
while (entry != &head->list) {
/*
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* don't process it twice:
*/
if (entry != pending) {
if (handle_futex_death((void __user *)entry + futex_offset,
curr, pi, HANDLE_DEATH_LIST))
return;
}
if (rc)
return;
entry = next_entry;
pi = next_pi;
/*
* Avoid excessively long or circular lists:
*/
if (!--limit)
break;
cond_resched();
}
if (pending) {
handle_futex_death((void __user *)pending + futex_offset,
curr, pip, HANDLE_DEATH_PENDING);
}
}
#ifdef CONFIG_COMPAT
static void __user *futex_uaddr(struct robust_list __user *entry,
compat_long_t futex_offset)
{
compat_uptr_t base = ptr_to_compat(entry);
void __user *uaddr = compat_ptr(base + futex_offset);
return uaddr;
}
/*
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int
compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
compat_uptr_t __user *head, unsigned int *pi)
{
if (get_user(*uentry, head))
return -EFAULT;
*entry = compat_ptr((*uentry) & ~1);
*pi = (unsigned int)(*uentry) & 1;
return 0;
}
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
static void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
compat_uptr_t uentry, next_uentry, upending;
compat_long_t futex_offset;
int rc;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
*/
if (get_user(futex_offset, &head->futex_offset))
return;
/*
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
if (compat_fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
next_entry = NULL; /* avoid warning with gcc */
while (entry != (struct robust_list __user *) &head->list) {
/*
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
rc = compat_fetch_robust_entry(&next_uentry, &next_entry,
(compat_uptr_t __user *)&entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* dont process it twice:
*/
if (entry != pending) {
void __user *uaddr = futex_uaddr(entry, futex_offset);
if (handle_futex_death(uaddr, curr, pi,
HANDLE_DEATH_LIST))
return;
}
if (rc)
return;
uentry = next_uentry;
entry = next_entry;
pi = next_pi;
/*
* Avoid excessively long or circular lists:
*/
if (!--limit)
break;
cond_resched();
}
if (pending) {
void __user *uaddr = futex_uaddr(pending, futex_offset);
handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
}
}
#endif
#ifdef CONFIG_FUTEX_PI
/*
* This task is holding PI mutexes at exit time => bad.
* Kernel cleans up PI-state, but userspace is likely hosed.
* (Robust-futex cleanup is separate and might save the day for userspace.)
*/
static void exit_pi_state_list(struct task_struct *curr)
{
struct list_head *next, *head = &curr->pi_state_list;
struct futex_pi_state *pi_state;
struct futex_hash_bucket *hb;
union futex_key key = FUTEX_KEY_INIT;
/*
* We are a ZOMBIE and nobody can enqueue itself on
* pi_state_list anymore, but we have to be careful
* versus waiters unqueueing themselves:
*/
raw_spin_lock_irq(&curr->pi_lock);
while (!list_empty(head)) {
next = head->next;
pi_state = list_entry(next, struct futex_pi_state, list);
key = pi_state->key;
hb = futex_hash(&key);
/*
* We can race against put_pi_state() removing itself from the
* list (a waiter going away). put_pi_state() will first
* decrement the reference count and then modify the list, so
* its possible to see the list entry but fail this reference
* acquire.
*
* In that case; drop the locks to let put_pi_state() make
* progress and retry the loop.
*/
if (!refcount_inc_not_zero(&pi_state->refcount)) {
raw_spin_unlock_irq(&curr->pi_lock);
cpu_relax();
raw_spin_lock_irq(&curr->pi_lock);
continue;
}
raw_spin_unlock_irq(&curr->pi_lock);
spin_lock(&hb->lock);
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
raw_spin_lock(&curr->pi_lock);
/*
* We dropped the pi-lock, so re-check whether this
* task still owns the PI-state:
*/
if (head->next != next) {
/* retain curr->pi_lock for the loop invariant */
raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
put_pi_state(pi_state);
continue;
}
WARN_ON(pi_state->owner != curr);
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
pi_state->owner = NULL;
raw_spin_unlock(&curr->pi_lock);
raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
rt_mutex_futex_unlock(&pi_state->pi_mutex);
put_pi_state(pi_state);
raw_spin_lock_irq(&curr->pi_lock);
}
raw_spin_unlock_irq(&curr->pi_lock);
}
#else
static inline void exit_pi_state_list(struct task_struct *curr) { }
#endif
static void futex_cleanup(struct task_struct *tsk)
{
if (unlikely(tsk->robust_list)) {
exit_robust_list(tsk);
tsk->robust_list = NULL;
}
#ifdef CONFIG_COMPAT
if (unlikely(tsk->compat_robust_list)) {
compat_exit_robust_list(tsk);
tsk->compat_robust_list = NULL;
}
#endif
if (unlikely(!list_empty(&tsk->pi_state_list)))
exit_pi_state_list(tsk);
}
/**
* futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
* @tsk: task to set the state on
*
* Set the futex exit state of the task lockless. The futex waiter code
* observes that state when a task is exiting and loops until the task has
* actually finished the futex cleanup. The worst case for this is that the
* waiter runs through the wait loop until the state becomes visible.
*
* This is called from the recursive fault handling path in make_task_dead().
*
* This is best effort. Either the futex exit code has run already or
* not. If the OWNER_DIED bit has been set on the futex then the waiter can
* take it over. If not, the problem is pushed back to user space. If the
* futex exit code did not run yet, then an already queued waiter might
* block forever, but there is nothing which can be done about that.
*/
void futex_exit_recursive(struct task_struct *tsk)
{
/* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */
if (tsk->futex_state == FUTEX_STATE_EXITING)
mutex_unlock(&tsk->futex_exit_mutex);
tsk->futex_state = FUTEX_STATE_DEAD;
}
static void futex_cleanup_begin(struct task_struct *tsk)
{
/*
* Prevent various race issues against a concurrent incoming waiter
* including live locks by forcing the waiter to block on
* tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in
* attach_to_pi_owner().
*/
mutex_lock(&tsk->futex_exit_mutex);
/*
* Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock.
*
* This ensures that all subsequent checks of tsk->futex_state in
* attach_to_pi_owner() must observe FUTEX_STATE_EXITING with
* tsk->pi_lock held.
*
* It guarantees also that a pi_state which was queued right before
* the state change under tsk->pi_lock by a concurrent waiter must
* be observed in exit_pi_state_list().
*/
raw_spin_lock_irq(&tsk->pi_lock);
tsk->futex_state = FUTEX_STATE_EXITING;
raw_spin_unlock_irq(&tsk->pi_lock);
}
static void futex_cleanup_end(struct task_struct *tsk, int state)
{
/*
* Lockless store. The only side effect is that an observer might
* take another loop until it becomes visible.
*/
tsk->futex_state = state;
/*
* Drop the exit protection. This unblocks waiters which observed
* FUTEX_STATE_EXITING to reevaluate the state.
*/
mutex_unlock(&tsk->futex_exit_mutex);
}
void futex_exec_release(struct task_struct *tsk)
{
/*
* The state handling is done for consistency, but in the case of
* exec() there is no way to prevent further damage as the PID stays
* the same. But for the unlikely and arguably buggy case that a
* futex is held on exec(), this provides at least as much state
* consistency protection which is possible.
*/
futex_cleanup_begin(tsk);
futex_cleanup(tsk);
/*
* Reset the state to FUTEX_STATE_OK. The task is alive and about
* exec a new binary.
*/
futex_cleanup_end(tsk, FUTEX_STATE_OK);
}
void futex_exit_release(struct task_struct *tsk)
{
futex_cleanup_begin(tsk);
futex_cleanup(tsk);
futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
}
static int __init futex_init(void)
{
unsigned long hashsize, i;
unsigned int futex_shift;
#ifdef CONFIG_BASE_SMALL
hashsize = 16;
#else
hashsize = roundup_pow_of_two(256 * num_possible_cpus());
#endif
futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
hashsize, 0, 0,
&futex_shift, NULL,
hashsize, hashsize);
hashsize = 1UL << futex_shift;
for (i = 0; i < hashsize; i++) {
atomic_set(&futex_queues[i].waiters, 0);
plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
futex_hashmask = hashsize - 1;
return 0;
}
core_initcall(futex_init);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Derived from arch/arm/kvm/handle_exit.c:
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/ubsan.h>
#include <asm/esr.h>
#include <asm/exception.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/debug-monitors.h>
#include <asm/stacktrace/nvhe.h>
#include <asm/traps.h>
#include <kvm/arm_hypercalls.h>
#define CREATE_TRACE_POINTS
#include "trace_handle_exit.h"
typedef int (*exit_handle_fn)(struct kvm_vcpu *);
static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
{
if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
kvm_inject_vabt(vcpu);
}
static int handle_hvc(struct kvm_vcpu *vcpu)
{ trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
kvm_vcpu_hvc_get_imm(vcpu));
vcpu->stat.hvc_exit_stat++;
/* Forward hvc instructions to the virtual EL2 if the guest has EL2. */
if (vcpu_has_nv(vcpu)) {
if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD)
kvm_inject_undefined(vcpu);
else
kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
return 1;
}
return kvm_smccc_call_handler(vcpu);
}
static int handle_smc(struct kvm_vcpu *vcpu)
{
/*
* Forward this trapped smc instruction to the virtual EL2 if
* the guest has asked for it.
*/
if (forward_smc_trap(vcpu))
return 1;
/*
* "If an SMC instruction executed at Non-secure EL1 is
* trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
* Trap exception, not a Secure Monitor Call exception [...]"
*
* We need to advance the PC after the trap, as it would
* otherwise return to the same address. Furthermore, pre-incrementing
* the PC before potentially exiting to userspace maintains the same
* abstraction for both SMCs and HVCs.
*/
kvm_incr_pc(vcpu);
/*
* SMCs with a nonzero immediate are reserved according to DEN0028E 2.9
* "SMC and HVC immediate value".
*/
if (kvm_vcpu_hvc_get_imm(vcpu)) {
vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
/*
* If imm is zero then it is likely an SMCCC call.
*
* Note that on ARMv8.3, even if EL3 is not implemented, SMC executed
* at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than
* being treated as UNDEFINED.
*/
return kvm_smccc_call_handler(vcpu);
}
/*
* This handles the cases where the system does not support FP/ASIMD or when
* we are running nested virtualization and the guest hypervisor is trapping
* FP/ASIMD accesses by its guest guest.
*
* All other handling of guest vs. host FP/ASIMD register state is handled in
* fixup_guest_exit().
*/
static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
{
if (guest_hyp_fpsimd_traps_enabled(vcpu))
return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
/* This is the case when the system doesn't support FP/ASIMD. */
kvm_inject_undefined(vcpu);
return 1;
}
/**
* kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
* instruction executed by a guest
*
* @vcpu: the vcpu pointer
*
* WFE[T]: Yield the CPU and come back to this vcpu when the scheduler
* decides to.
* WFI: Simply call kvm_vcpu_halt(), which will halt execution of
* world-switches and schedule other host processes until there is an
* incoming IRQ or FIQ to the VM.
* WFIT: Same as WFI, with a timed wakeup implemented as a background timer
*
* WF{I,E}T can immediately return if the deadline has already expired.
*/
static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE);
if (guest_hyp_wfx_traps_enabled(vcpu))
return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
if (is_wfe) {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
} else {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
}
if (esr & ESR_ELx_WFx_ISS_WFxT) {
if (esr & ESR_ELx_WFx_ISS_RV) {
u64 val, now;
now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT);
val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
if (now >= val)
goto out;
} else {
/* Treat WFxT as WFx if RN is invalid */
esr &= ~ESR_ELx_WFx_ISS_WFxT;
}
}
if (esr & ESR_ELx_WFx_ISS_WFE) {
kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
} else {
if (esr & ESR_ELx_WFx_ISS_WFxT) vcpu_set_flag(vcpu, IN_WFIT);
kvm_vcpu_wfi(vcpu);
}
out:
kvm_incr_pc(vcpu);
return 1;
}
/**
* kvm_handle_guest_debug - handle a debug exception instruction
*
* @vcpu: the vcpu pointer
*
* We route all debug exceptions through the same handler. If both the
* guest and host are using the same debug facilities it will be up to
* userspace to re-inject the correct exception for guest delivery.
*
* @return: 0 (while setting vcpu->run->exit_reason)
*/
static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
u64 esr = kvm_vcpu_get_esr(vcpu);
if (!vcpu->guest_debug && forward_debug_exception(vcpu))
return 1;
run->exit_reason = KVM_EXIT_DEBUG;
run->debug.arch.hsr = lower_32_bits(esr);
run->debug.arch.hsr_high = upper_32_bits(esr);
run->flags = KVM_DEBUG_ARCH_HSR_HIGH_VALID;
switch (ESR_ELx_EC(esr)) {
case ESR_ELx_EC_WATCHPT_LOW:
run->debug.arch.far = vcpu->arch.fault.far_el2;
break;
case ESR_ELx_EC_SOFTSTP_LOW:
*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
break;
}
return 0;
}
static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
kvm_pr_unimpl("Unknown exception class: esr: %#016llx -- %s\n",
esr, esr_get_class_string(esr));
kvm_inject_undefined(vcpu);
return 1;
}
/*
* Guest access to SVE registers should be routed to this handler only
* when the system doesn't support SVE.
*/
static int handle_sve(struct kvm_vcpu *vcpu)
{
if (guest_hyp_sve_traps_enabled(vcpu))
return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
kvm_inject_undefined(vcpu);
return 1;
}
/*
* Two possibilities to handle a trapping ptrauth instruction:
*
* - Guest usage of a ptrauth instruction (which the guest EL1 did not
* turn into a NOP). If we get here, it is because we didn't enable
* ptrauth for the guest. This results in an UNDEF, as it isn't
* supposed to use ptrauth without being told it could.
*
* - Running an L2 NV guest while L1 has left HCR_EL2.API==0, and for
* which we reinject the exception into L1.
*
* Anything else is an emulation bug (hence the WARN_ON + UNDEF).
*/
static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
{
if (!vcpu_has_ptrauth(vcpu)) {
kvm_inject_undefined(vcpu);
return 1;
}
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
return 1;
}
/* Really shouldn't be here! */
WARN_ON_ONCE(1);
kvm_inject_undefined(vcpu);
return 1;
}
static int kvm_handle_eret(struct kvm_vcpu *vcpu)
{
if (esr_iss_is_eretax(kvm_vcpu_get_esr(vcpu)) &&
!vcpu_has_ptrauth(vcpu))
return kvm_handle_ptrauth(vcpu);
/*
* If we got here, two possibilities:
*
* - the guest is in EL2, and we need to fully emulate ERET
*
* - the guest is in EL1, and we need to reinject the
* exception into the L1 hypervisor.
*
* If KVM ever traps ERET for its own use, we'll have to
* revisit this.
*/
if (is_hyp_ctxt(vcpu))
kvm_emulate_nested_eret(vcpu);
else
kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
return 1;
}
static int handle_svc(struct kvm_vcpu *vcpu)
{
/*
* So far, SVC traps only for NV via HFGITR_EL2. A SVC from a
* 32bit guest would be caught by vpcu_mode_is_bad_32bit(), so
* we should only have to deal with a 64 bit exception.
*/
kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
return 1;
}
static int kvm_handle_gcs(struct kvm_vcpu *vcpu)
{
/* We don't expect GCS, so treat it with contempt */
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, GCS, IMP))
WARN_ON_ONCE(1);
kvm_inject_undefined(vcpu);
return 1;
}
static int handle_other(struct kvm_vcpu *vcpu)
{
bool is_l2 = vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu);
u64 hcrx = __vcpu_sys_reg(vcpu, HCRX_EL2);
u64 esr = kvm_vcpu_get_esr(vcpu);
u64 iss = ESR_ELx_ISS(esr);
struct kvm *kvm = vcpu->kvm;
bool allowed, fwd = false;
/*
* We only trap for two reasons:
*
* - the feature is disabled, and the only outcome is to
* generate an UNDEF.
*
* - the feature is enabled, but a NV guest wants to trap the
* feature used by its L2 guest. We forward the exception in
* this case.
*
* What we don't expect is to end-up here if the guest is
* expected be be able to directly use the feature, hence the
* WARN_ON below.
*/
switch (iss) {
case ESR_ELx_ISS_OTHER_ST64BV:
allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V);
if (is_l2)
fwd = !(hcrx & HCRX_EL2_EnASR);
break;
case ESR_ELx_ISS_OTHER_ST64BV0:
allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA);
if (is_l2)
fwd = !(hcrx & HCRX_EL2_EnAS0);
break;
case ESR_ELx_ISS_OTHER_LDST64B:
allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64);
if (is_l2)
fwd = !(hcrx & HCRX_EL2_EnALS);
break;
case ESR_ELx_ISS_OTHER_TSBCSYNC:
allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1);
if (is_l2)
fwd = (__vcpu_sys_reg(vcpu, HFGITR2_EL2) & HFGITR2_EL2_TSBCSYNC);
break;
case ESR_ELx_ISS_OTHER_PSBCSYNC:
allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P5);
if (is_l2)
fwd = (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_PSBCSYNC);
break;
default:
/* Clearly, we're missing something. */
WARN_ON_ONCE(1);
allowed = false;
}
WARN_ON_ONCE(allowed && !fwd);
if (allowed && fwd)
kvm_inject_nested_sync(vcpu, esr);
else
kvm_inject_undefined(vcpu);
return 1;
}
static exit_handle_fn arm_exit_handlers[] = {
[0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec,
[ESR_ELx_EC_WFx] = kvm_handle_wfx,
[ESR_ELx_EC_CP15_32] = kvm_handle_cp15_32,
[ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64,
[ESR_ELx_EC_CP14_MR] = kvm_handle_cp14_32,
[ESR_ELx_EC_CP14_LS] = kvm_handle_cp14_load_store,
[ESR_ELx_EC_CP10_ID] = kvm_handle_cp10_id,
[ESR_ELx_EC_CP14_64] = kvm_handle_cp14_64,
[ESR_ELx_EC_OTHER] = handle_other,
[ESR_ELx_EC_HVC32] = handle_hvc,
[ESR_ELx_EC_SMC32] = handle_smc,
[ESR_ELx_EC_HVC64] = handle_hvc,
[ESR_ELx_EC_SMC64] = handle_smc,
[ESR_ELx_EC_SVC64] = handle_svc,
[ESR_ELx_EC_SYS64] = kvm_handle_sys_reg,
[ESR_ELx_EC_SVE] = handle_sve,
[ESR_ELx_EC_ERET] = kvm_handle_eret,
[ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort,
[ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort,
[ESR_ELx_EC_DABT_CUR] = kvm_handle_vncr_abort,
[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
[ESR_ELx_EC_WATCHPT_LOW]= kvm_handle_guest_debug,
[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
[ESR_ELx_EC_BKPT32] = kvm_handle_guest_debug,
[ESR_ELx_EC_BRK64] = kvm_handle_guest_debug,
[ESR_ELx_EC_FP_ASIMD] = kvm_handle_fpasimd,
[ESR_ELx_EC_PAC] = kvm_handle_ptrauth,
[ESR_ELx_EC_GCS] = kvm_handle_gcs,
};
static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
u8 esr_ec = ESR_ELx_EC(esr);
return arm_exit_handlers[esr_ec];
}
/*
* We may be single-stepping an emulated instruction. If the emulation
* has been completed in the kernel, we can return to userspace with a
* KVM_EXIT_DEBUG, otherwise userspace needs to complete its
* emulation first.
*/
static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
{
int handled;
/*
* See ARM ARM B1.14.1: "Hyp traps on instructions
* that fail their condition code check"
*/
if (!kvm_condition_valid(vcpu)) { kvm_incr_pc(vcpu);
handled = 1;
} else {
exit_handle_fn exit_handler;
exit_handler = kvm_get_exit_handler(vcpu);
handled = exit_handler(vcpu);
}
return handled;
}
/*
* Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
* proper exit to userspace.
*/
int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
{
struct kvm_run *run = vcpu->run;
if (ARM_SERROR_PENDING(exception_index)) {
/*
* The SError is handled by handle_exit_early(). If the guest
* survives it will re-execute the original instruction.
*/
return 1;
}
exception_index = ARM_EXCEPTION_CODE(exception_index);
switch (exception_index) {
case ARM_EXCEPTION_IRQ:
return 1;
case ARM_EXCEPTION_EL1_SERROR:
return 1;
case ARM_EXCEPTION_TRAP:
return handle_trap_exceptions(vcpu);
case ARM_EXCEPTION_HYP_GONE:
/*
* EL2 has been reset to the hyp-stub. This happens when a guest
* is pre-emptied by kvm_reboot()'s shutdown call.
*/
run->exit_reason = KVM_EXIT_FAIL_ENTRY;
return 0;
case ARM_EXCEPTION_IL:
/*
* We attempted an illegal exception return. Guest state must
* have been corrupted somehow. Give up.
*/
run->exit_reason = KVM_EXIT_FAIL_ENTRY;
return -EINVAL;
default:
kvm_pr_unimpl("Unsupported exception type: %d",
exception_index);
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
return 0;
}
}
/* For exit types that need handling before we can be preempted */
void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
{
if (ARM_SERROR_PENDING(exception_index)) {
if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
u64 disr = kvm_vcpu_get_disr(vcpu);
kvm_handle_guest_serror(vcpu, disr_to_esr(disr));
} else {
kvm_inject_vabt(vcpu);
}
return;
}
exception_index = ARM_EXCEPTION_CODE(exception_index);
if (exception_index == ARM_EXCEPTION_EL1_SERROR) kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
}
static void print_nvhe_hyp_panic(const char *name, u64 panic_addr)
{
kvm_err("nVHE hyp %s at: [<%016llx>] %pB!\n", name, panic_addr,
(void *)(panic_addr + kaslr_offset()));
}
static void kvm_nvhe_report_cfi_failure(u64 panic_addr)
{
print_nvhe_hyp_panic("CFI failure", panic_addr);
if (IS_ENABLED(CONFIG_CFI_PERMISSIVE))
kvm_err(" (CONFIG_CFI_PERMISSIVE ignored for hyp failures)\n");
}
void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
u64 elr_virt, u64 elr_phys,
u64 par, uintptr_t vcpu,
u64 far, u64 hpfar) {
u64 elr_in_kimg = __phys_to_kimg(elr_phys);
u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt;
u64 mode = spsr & PSR_MODE_MASK;
u64 panic_addr = elr_virt + hyp_offset;
if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
kvm_err("Invalid host exception to nVHE hyp!\n");
} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
esr_brk_comment(esr) == BUG_BRK_IMM) {
const char *file = NULL;
unsigned int line = 0;
/* All hyp bugs, including warnings, are treated as fatal. */
if (!is_protected_kvm_enabled() ||
IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
struct bug_entry *bug = find_bug(elr_in_kimg);
if (bug)
bug_get_file_line(bug, &file, &line);
}
if (file)
kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
else
print_nvhe_hyp_panic("BUG", panic_addr);
} else if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) {
kvm_nvhe_report_cfi_failure(panic_addr);
} else if (IS_ENABLED(CONFIG_UBSAN_KVM_EL2) &&
ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
esr_is_ubsan_brk(esr)) {
print_nvhe_hyp_panic(report_ubsan_failure(esr & UBSAN_BRK_MASK),
panic_addr);
} else {
print_nvhe_hyp_panic("panic", panic_addr);
}
/* Dump the nVHE hypervisor backtrace */
kvm_nvhe_dump_backtrace(hyp_offset);
/*
* Hyp has panicked and we're going to handle that by panicking the
* kernel. The kernel offset will be revealed in the panic so we're
* also safe to reveal the hyp offset as a debugging aid for translating
* hyp VAs to vmlinux addresses.
*/
kvm_err("Hyp Offset: 0x%llx\n", hyp_offset);
panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%016llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n",
spsr, elr_virt, esr, far, hpfar, par, vcpu);
}
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/inode.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 64-bit file support on 64-bit platforms by Jakub Jelinek
* (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
*/
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/rmap.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/iomap.h>
#include <linux/iversion.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"
#include <trace/events/ext4.h>
static void ext4_journalled_zero_new_buffers(handle_t *handle,
struct inode *inode,
struct folio *folio,
unsigned from, unsigned to);
static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__u16 dummy_csum = 0;
int offset = offsetof(struct ext4_inode, i_checksum_lo);
unsigned int csum_size = sizeof(dummy_csum);
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_GOOD_OLD_INODE_SIZE - offset);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
offset = offsetof(struct ext4_inode, i_checksum_hi);
csum = ext4_chksum(sbi, csum, (__u8 *)raw +
EXT4_GOOD_OLD_INODE_SIZE,
offset - EXT4_GOOD_OLD_INODE_SIZE);
if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
csum_size);
offset += csum_size;
}
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_INODE_SIZE(inode->i_sb) - offset);
}
return csum;
}
static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 provided, calculated;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_feature_metadata_csum(inode->i_sb))
return 1;
provided = le16_to_cpu(raw->i_checksum_lo);
calculated = ext4_inode_csum(inode, raw, ei);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16;
else
calculated &= 0xFFFF;
return provided == calculated;
}
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 csum;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_feature_metadata_csum(inode->i_sb))
return;
csum = ext4_inode_csum(inode, raw, ei);
raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
raw->i_checksum_hi = cpu_to_le16(csum >> 16);
}
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
trace_ext4_begin_ordered_truncate(inode, new_size);
/*
* If jinode is zero, then we never opened the file for
* writing, so there's no need to call
* jbd2_journal_begin_ordered_truncate() since there's no
* outstanding writes we need to flush.
*/
if (!EXT4_I(inode)->jinode)
return 0;
return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode,
new_size);
}
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents);
/*
* Test whether an inode is a fast symlink.
* A fast symlink has its symlink data stored in ext4_inode_info->i_data.
*/
int ext4_inode_is_fast_symlink(struct inode *inode)
{
if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
if (ext4_has_inline_data(inode))
return 0;
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
return S_ISLNK(inode->i_mode) && inode->i_size &&
(inode->i_size < EXT4_N_BLOCKS * 4);
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
/*
* Credits for final inode cleanup and freeing:
* sb + inode (ext4_orphan_del()), block bitmap, group descriptor
* (xattr block freeing), bitmap, group descriptor (inode freeing)
*/
int extra_credits = 6;
struct ext4_xattr_inode_array *ea_inode_array = NULL;
bool freeze_protected = false;
trace_ext4_evict_inode(inode);
dax_break_layout_final(inode);
if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
ext4_evict_ea_inode(inode);
if (inode->i_nlink) {
truncate_inode_pages_final(&inode->i_data);
goto no_delete;
}
if (is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages_final(&inode->i_data);
/*
* For inodes with journalled data, transaction commit could have
* dirtied the inode. And for inodes with dioread_nolock, unwritten
* extents converting worker could merge extents and also have dirtied
* the inode. Flush worker is ignoring it because of I_FREEING flag but
* we still need to remove the inode from the writeback lists.
*/
if (!list_empty_careful(&inode->i_io_list))
inode_io_list_del(inode);
/*
* Protect us against freezing - iput() caller didn't have to have any
* protection against it. When we are in a running transaction though,
* we are already protected against freezing and we cannot grab further
* protection due to lock ordering constraints.
*/
if (!ext4_journal_current_handle()) {
sb_start_intwrite(inode->i_sb);
freeze_protected = true;
}
if (!IS_NOQUOTA(inode))
extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
/*
* Block bitmap, group descriptor, and inode are accounted in both
* ext4_blocks_for_truncate() and extra_credits. So subtract 3.
*/
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
ext4_blocks_for_truncate(inode) + extra_credits - 3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
/*
* Set inode->i_size to 0 before calling ext4_truncate(). We need
* special handling of symlinks here because i_size is used to
* determine whether ext4_inode_info->i_data contains symlink data or
* block mappings. Setting i_size to 0 will remove its fast symlink
* status. Erase i_data so that it becomes a valid empty block map.
*/
if (ext4_inode_is_fast_symlink(inode))
memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data));
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_warning(inode->i_sb,
"couldn't mark inode dirty (err %d)", err);
goto stop_handle;
}
if (inode->i_blocks) {
err = ext4_truncate(inode);
if (err) {
ext4_error_err(inode->i_sb, -err,
"couldn't truncate inode %lu (err %d)",
inode->i_ino, err);
goto stop_handle;
}
}
/* Remove xattr references. */
err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array,
extra_credits);
if (err) {
ext4_warning(inode->i_sb, "xattr delete (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
goto no_delete;
}
/*
* Kill off the orphan record which ext4_truncate created.
* AKPM: I think this can be inside the above `if'.
* Note that ext4_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - this is because we don't
* know if ext4_truncate() actually created an orphan record.
* (Well, we could do this if we need to, but heck - it works)
*/
ext4_orphan_del(handle, inode);
EXT4_I(inode)->i_dtime = (__u32)ktime_get_real_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext4_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
if (freeze_protected)
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
/*
* Check out some where else accidentally dirty the evicting inode,
* which may probably cause inode use-after-free issues later.
*/
WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list));
if (!list_empty(&EXT4_I(inode)->i_fc_list))
ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
return &EXT4_I(inode)->i_reserved_quota;
}
#endif
/*
* Called with i_data_sem down, which is important since we can call
* ext4_discard_preallocations() from here.
*/
void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
"with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
WARN_ON(1);
used = ei->i_reserved_data_blocks;
}
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
spin_unlock(&ei->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
if ((ei->i_reserved_data_blocks == 0) &&
!inode_is_open_for_write(inode))
ext4_discard_preallocations(inode);
}
static int __check_block_validity(struct inode *inode, const char *func,
unsigned int line,
struct ext4_map_blocks *map)
{
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
if (journal && inode == journal->j_inode)
return 0;
if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock %llu "
"(length %d)", (unsigned long) map->m_lblk,
map->m_pblk, map->m_len);
return -EFSCORRUPTED;
}
return 0;
}
int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
ext4_lblk_t len)
{
int ret;
if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
if (ret > 0)
ret = 0;
return ret;
}
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
#ifdef ES_AGGRESSIVE_TEST
static void ext4_map_blocks_es_recheck(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *es_map,
struct ext4_map_blocks *map,
int flags)
{
int retval;
map->m_flags = 0;
/*
* There is a race window that the result is not the same.
* e.g. xfstests #223 when dioread_nolock enables. The reason
* is that we lookup a block mapping in extent status tree with
* out taking i_data_sem. So at the time the unwritten extent
* could be converted.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
/*
* We don't check m_len because extent will be collpased in status
* tree. So the m_len might not equal.
*/
if (es_map->m_lblk != map->m_lblk ||
es_map->m_flags != map->m_flags ||
es_map->m_pblk != map->m_pblk) {
printk("ES cache assertion failed for inode: %lu "
"es_cached ex [%d/%d/%llu/%x] != "
"found ex [%d/%d/%llu/%x] retval %d flags %x\n",
inode->i_ino, es_map->m_lblk, es_map->m_len,
es_map->m_pblk, es_map->m_flags, map->m_lblk,
map->m_len, map->m_pblk, map->m_flags,
retval, flags);
}
}
#endif /* ES_AGGRESSIVE_TEST */
static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map)
{
unsigned int status;
int retval;
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
retval = ext4_ext_map_blocks(handle, inode, map, 0);
else
retval = ext4_ind_map_blocks(handle, inode, map, 0);
if (retval <= 0)
return retval;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status, false);
return retval;
}
static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct extent_status es;
unsigned int status;
int err, retval = 0;
/*
* We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE
* indicates that the blocks and quotas has already been
* checked when the data was copied into the page cache.
*/
if (map->m_flags & EXT4_MAP_DELAYED)
flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
/*
* Here we clear m_flags because after allocating an new extent,
* it will be set again.
*/
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* We need to check for EXT4 here because migrate could have
* changed the inode type in between.
*/
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags);
/*
* We allocated new blocks which will result in i_data's
* format changing. Force the migrate to fail by clearing
* migrate flags.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_NEW) ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
if (retval <= 0)
return retval;
if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb,
"ES len assertion failed for inode %lu: "
"retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
/*
* We have to zeroout blocks before inserting them into extent
* status tree. Otherwise someone could look them up there and
* use them before they are really zeroed. We also have to
* unmap metadata before zeroing as otherwise writeback can
* overwrite zeros with stale data from block device.
*/
if (flags & EXT4_GET_BLOCKS_ZERO && map->m_flags & EXT4_MAP_MAPPED && map->m_flags & EXT4_MAP_NEW) { err = ext4_issue_zeroout(inode, map->m_lblk, map->m_pblk,
map->m_len);
if (err)
return err;
}
/*
* If the extent has been zeroed out, we don't need to update
* extent status tree.
*/
if (flags & EXT4_GET_BLOCKS_PRE_IO &&
ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es))
return retval;
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk,
status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
return retval;
}
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* and store the allocated blocks in the result buffer head and mark it
* mapped.
*
* If file type is extents based, it will call ext4_ext_map_blocks(),
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocated.
* If flags doesn't contain EXT4_GET_BLOCKS_CREATE the blocks are
* pre-allocated and unwritten, the resulting @map is marked as unwritten.
* If the flags contain EXT4_GET_BLOCKS_CREATE, it will mark @map as mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
* that case, @map is returned as unmapped but we still do fill map->m_len to
* indicate the length of a hole starting at map->m_lblk.
*
* It returns the error in case of allocation failure.
*/
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct extent_status es;
int retval;
int ret = 0;
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
map->m_flags = 0;
ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n",
flags, map->m_len, (unsigned long) map->m_lblk);
/*
* ext4_map_blocks returns an int, and m_len is an unsigned int
*/
if (unlikely(map->m_len > INT_MAX)) map->m_len = INT_MAX;
/* We can handle the block number less than EXT_MAX_BLOCKS */
if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
return -EFSCORRUPTED;
/* Lookup extent status tree firstly */
if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
map->m_flags |= ext4_es_is_written(&es) ?
EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
map->m_pblk = 0;
map->m_flags |= ext4_es_is_delayed(&es) ?
EXT4_MAP_DELAYED : 0;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
retval = 0;
} else {
BUG();
}
if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
return retval;
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(handle, inode, map,
&orig_map, flags);
#endif
goto found;
}
/*
* In the query cache no-wait mode, nothing we can do more if we
* cannot find extent in the cache.
*/
if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
return 0;
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
retval = ext4_map_query_blocks(handle, inode, map);
up_read((&EXT4_I(inode)->i_data_sem));
found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
/* If it is only a block(s) look up */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
* ext4_ext_map_blocks() returns with buffer head unmapped
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
/*
* If we need to convert extent to unwritten
* we continue and do the actual work in
* ext4_ext_map_blocks()
*/
if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
return retval;
/*
* New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_block()
* with create == 1 flag.
*/
down_write(&EXT4_I(inode)->i_data_sem);
retval = ext4_map_create_blocks(handle, inode, map, flags);
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
/*
* Inodes with freshly allocated blocks where contents will be
* visible after transaction commit must be on transaction's
* ordered data list.
*/
if (map->m_flags & EXT4_MAP_NEW &&
!(map->m_flags & EXT4_MAP_UNWRITTEN) &&
!(flags & EXT4_GET_BLOCKS_ZERO) &&
!ext4_is_quota_file(inode) &&
ext4_should_order_data(inode)) {
loff_t start_byte =
(loff_t)map->m_lblk << inode->i_blkbits;
loff_t length = (loff_t)map->m_len << inode->i_blkbits;
if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
ret = ext4_jbd2_inode_add_wait(handle, inode,
start_byte, length);
else
ret = ext4_jbd2_inode_add_write(handle, inode,
start_byte, length);
if (ret)
return ret;
}
}
if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN ||
map->m_flags & EXT4_MAP_MAPPED))
ext4_fc_track_range(handle, inode, map->m_lblk,
map->m_lblk + map->m_len - 1);
if (retval < 0)
ext_debug(inode, "failed with err %d\n", retval);
return retval;
}
/*
* Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
* we have to be careful as someone else may be manipulating b_state as well.
*/
static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
{
unsigned long old_state;
unsigned long new_state;
flags &= EXT4_MAP_FLAGS;
/* Dummy buffer_head? Set non-atomically. */
if (!bh->b_folio) {
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
return;
}
/*
* Someone else may be modifying b_state. Be careful! This is ugly but
* once we get rid of using bh as a container for mapping information
* to pass to / from get_block functions, this can go away.
*/
old_state = READ_ONCE(bh->b_state);
do {
new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
} while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
}
static int _ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int flags)
{
struct ext4_map_blocks map;
int ret = 0;
if (ext4_has_inline_data(inode))
return -ERANGE;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
flags);
if (ret > 0) {
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
} else if (ret == 0) {
/* hole case, need to fill in bh->b_size */
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
}
return ret;
}
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
return _ext4_get_block(inode, iblock, bh,
create ? EXT4_GET_BLOCKS_CREATE : 0);
}
/*
* Get block function used when preparing for buffered write if we require
* creating an unwritten extent if blocks haven't been allocated. The extent
* will be converted to written after the IO is complete.
*/
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret = 0;
ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
inode->i_ino, create);
ret = _ext4_get_block(inode, iblock, bh_result,
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT);
/*
* If the buffer is marked unwritten, mark it as new to make sure it is
* zeroed out correctly in case of partial writes. Otherwise, there is
* a chance of stale data getting exposed.
*/
if (ret == 0 && buffer_unwritten(bh_result))
set_buffer_new(bh_result);
return ret;
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
int create = map_flags & EXT4_GET_BLOCKS_CREATE;
bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT;
int err;
ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
|| handle != NULL || create == 0);
ASSERT(create == 0 || !nowait);
map.m_lblk = block;
map.m_len = 1;
err = ext4_map_blocks(handle, inode, &map, map_flags);
if (err == 0)
return create ? ERR_PTR(-ENOSPC) : NULL;
if (err < 0)
return ERR_PTR(err);
if (nowait)
return sb_find_get_block(inode->i_sb, map.m_pblk);
/*
* Since bh could introduce extra ref count such as referred by
* journal_head etc. Try to avoid using __GFP_MOVABLE here
* as it may fail the migration when journal_head remains.
*/
bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk,
inode->i_sb->s_blocksize);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
ASSERT(create != 0);
ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
|| (handle != NULL));
/*
* Now that we do not always journal data, we should
* keep in mind whether this should always journal the
* new buffer as metadata. For now, regular file
* writes use ext4_get_block instead, so it's not a
* problem.
*/
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
if (unlikely(err)) {
unlock_buffer(bh);
goto errout;
}
if (!buffer_uptodate(bh)) {
memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (unlikely(err))
goto errout;
} else
BUFFER_TRACE(bh, "not a new buffer");
return bh;
errout:
brelse(bh);
return ERR_PTR(err);
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct buffer_head *bh;
int ret;
bh = ext4_getblk(handle, inode, block, map_flags);
if (IS_ERR(bh))
return bh;
if (!bh || ext4_buffer_uptodate(bh))
return bh;
ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true);
if (ret) {
put_bh(bh);
return ERR_PTR(ret);
}
return bh;
}
/* Read a contiguous batch of blocks. */
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
bool wait, struct buffer_head **bhs)
{
int i, err;
for (i = 0; i < bh_count; i++) {
bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */);
if (IS_ERR(bhs[i])) {
err = PTR_ERR(bhs[i]);
bh_count = i;
goto out_brelse;
}
}
for (i = 0; i < bh_count; i++)
/* Note that NULL bhs[i] is valid because of holes. */
if (bhs[i] && !ext4_buffer_uptodate(bhs[i]))
ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false);
if (!wait)
return 0;
for (i = 0; i < bh_count; i++)
if (bhs[i])
wait_on_buffer(bhs[i]);
for (i = 0; i < bh_count; i++) {
if (bhs[i] && !buffer_uptodate(bhs[i])) {
err = -EIO;
goto out_brelse;
}
}
return 0;
out_brelse:
for (i = 0; i < bh_count; i++) {
brelse(bhs[i]);
bhs[i] = NULL;
}
return err;
}
int ext4_walk_page_buffers(handle_t *handle, struct inode *inode,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)(handle_t *handle, struct inode *inode,
struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
unsigned blocksize = head->b_size;
int err, ret = 0;
struct buffer_head *next;
for (bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
block_start = block_end, bh = next) {
next = bh->b_this_page;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (partial && !buffer_uptodate(bh))
*partial = 1;
continue;
}
err = (*fn)(handle, inode, bh);
if (!ret)
ret = err;
}
return ret;
}
/*
* Helper for handling dirtying of journalled data. We also mark the folio as
* dirty so that writeback code knows about this page (and inode) contains
* dirty data. ext4_writepages() then commits appropriate transaction to
* make data stable.
*/
static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh)
{
folio_mark_dirty(bh->b_folio);
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
BUFFER_TRACE(bh, "get write access");
return ext4_journal_get_write_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
}
int ext4_block_write_begin(handle_t *handle, struct folio *folio,
loff_t pos, unsigned len,
get_block_t *get_block)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned to = from + len;
struct inode *inode = folio->mapping->host;
unsigned block_start, block_end;
sector_t block;
int err = 0;
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned bbits;
struct buffer_head *bh, *head, *wait[2];
int nr_wait = 0;
int i;
bool should_journal_data = ext4_should_journal_data(inode);
BUG_ON(!folio_test_locked(folio));
BUG_ON(from > PAGE_SIZE);
BUG_ON(to > PAGE_SIZE);
BUG_ON(from > to);
head = folio_buffers(folio);
if (!head)
head = create_empty_buffers(folio, blocksize, 0);
bbits = ilog2(blocksize);
block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
for (bh = head, block_start = 0; bh != head || !block_start;
block++, block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (folio_test_uptodate(folio)) {
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
break;
if (buffer_new(bh)) {
/*
* We may be zeroing partial buffers or all new
* buffers in case of failure. Prepare JBD2 for
* that.
*/
if (should_journal_data)
do_journal_get_write_access(handle,
inode, bh);
if (folio_test_uptodate(folio)) {
/*
* Unlike __block_write_begin() we leave
* dirtying of new uptodate buffers to
* ->write_end() time or
* folio_zero_new_buffers().
*/
set_buffer_uptodate(bh);
continue;
}
if (block_end > to || block_start < from)
folio_zero_segments(folio, to,
block_end,
block_start, from);
continue;
}
}
if (folio_test_uptodate(folio)) {
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
ext4_read_bh_lock(bh, 0, false);
wait[nr_wait++] = bh;
}
}
/*
* If we issued read requests, let them complete.
*/
for (i = 0; i < nr_wait; i++) {
wait_on_buffer(wait[i]);
if (!buffer_uptodate(wait[i]))
err = -EIO;
}
if (unlikely(err)) {
if (should_journal_data)
ext4_journalled_zero_new_buffers(handle, inode, folio,
from, to);
else
folio_zero_new_buffers(folio, from, to);
} else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
for (i = 0; i < nr_wait; i++) {
int err2;
err2 = fscrypt_decrypt_pagecache_blocks(folio,
blocksize, bh_offset(wait[i]));
if (err2) {
clear_buffer_uptodate(wait[i]);
err = err2;
}
}
}
return err;
}
/*
* To preserve ordering, it is essential that the hole instantiation and
* the data write be encapsulated in a single transaction. We cannot
* close off a transaction and start a new one between the ext4_get_block()
* and the ext4_write_end(). So doing the jbd2_journal_start at the start of
* ext4_write_begin() is the right place.
*/
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata)
{
struct inode *inode = mapping->host;
int ret, needed_blocks;
handle_t *handle;
int retries = 0;
struct folio *folio;
pgoff_t index;
unsigned from, to;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
return ret;
trace_ext4_write_begin(inode, pos, len);
/*
* Reserve one block more for addition to orphan list in case
* we allocate blocks but write fails for some reason
*/
needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_SHIFT;
from = pos & (PAGE_SIZE - 1);
to = from + len;
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
foliop);
if (ret < 0)
return ret;
if (ret == 1)
return 0;
}
/*
* __filemap_get_folio() can take a long time if the
* system is thrashing due to memory pressure, or if the folio
* is being written back. So grab it first before we start
* the transaction handle. This also allows us to allocate
* the folio (if needed) without using GFP_NOFS.
*/
retry_grab:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
/*
* The same as page allocation, we prealloc buffer heads before
* starting the handle.
*/
if (!folio_buffers(folio))
create_empty_buffers(folio, inode->i_sb->s_blocksize, 0);
folio_unlock(folio);
retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
folio_put(folio);
return PTR_ERR(handle);
}
folio_lock(folio);
if (folio->mapping != mapping) {
/* The folio got truncated from under us */
folio_unlock(folio);
folio_put(folio);
ext4_journal_stop(handle);
goto retry_grab;
}
/* In case writeback began while the folio was unlocked */
folio_wait_stable(folio);
if (ext4_should_dioread_nolock(inode))
ret = ext4_block_write_begin(handle, folio, pos, len,
ext4_get_block_unwritten);
else
ret = ext4_block_write_begin(handle, folio, pos, len,
ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = ext4_walk_page_buffers(handle, inode,
folio_buffers(folio), from, to,
NULL, do_journal_get_write_access);
}
if (ret) {
bool extended = (pos + len > inode->i_size) &&
!ext4_verity_in_progress(inode);
folio_unlock(folio);
/*
* ext4_block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_rwsem.
*
* Add inode to orphan list in case we crash before
* truncate finishes
*/
if (extended && ext4_can_truncate(inode))
ext4_orphan_add(handle, inode);
ext4_journal_stop(handle);
if (extended) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
* make sure the inode is removed from the
* orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
folio_put(folio);
return ret;
}
*foliop = folio;
return ret;
}
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
ret = ext4_dirty_journalled_data(handle, bh);
clear_buffer_meta(bh);
clear_buffer_prio(bh);
return ret;
}
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
* ext4 never places buffers on inode->i_mapping->i_private_list. metadata
* buffers are managed internally.
*/
static int ext4_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
bool verity = ext4_verity_in_progress(inode);
trace_ext4_write_end(inode, pos, len, copied);
if (ext4_has_inline_data(inode) &&
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
/*
* it's important to update i_size while still holding folio lock:
* page writeout could otherwise come in and zero beyond i_size.
*
* If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree
* blocks are being written past EOF, so skip the i_size update.
*/
if (!verity)
i_size_changed = ext4_update_inode_size(inode, pos + copied);
folio_unlock(folio);
folio_put(folio);
if (old_size < pos && !verity) {
pagecache_isize_extended(inode, old_size, pos);
ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
}
/*
* Don't mark the inode dirty under folio lock. First, it unnecessarily
* makes the holding time of folio lock longer. Second, it forces lock
* ordering of folio lock and transaction start for journaling
* filesystems.
*/
if (i_size_changed)
ret = ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size && !verity) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* This is a private version of folio_zero_new_buffers() which doesn't
* set the buffer to be dirty, since in data=journalled mode we need
* to call ext4_dirty_journalled_data() instead.
*/
static void ext4_journalled_zero_new_buffers(handle_t *handle,
struct inode *inode,
struct folio *folio,
unsigned from, unsigned to)
{
unsigned int block_start = 0, block_end;
struct buffer_head *head, *bh;
bh = head = folio_buffers(folio);
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!folio_test_uptodate(folio)) {
unsigned start, size;
start = max(from, block_start);
size = min(to, block_end) - start;
folio_zero_range(folio, start, size);
}
clear_buffer_new(bh);
write_end_fn(handle, inode, bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
static int ext4_journalled_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
int size_changed = 0;
bool verity = ext4_verity_in_progress(inode);
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
to = from + len;
BUG_ON(!ext4_handle_valid(handle));
if (ext4_has_inline_data(inode))
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
if (unlikely(copied < len) && !folio_test_uptodate(folio)) {
copied = 0;
ext4_journalled_zero_new_buffers(handle, inode, folio,
from, to);
} else {
if (unlikely(copied < len))
ext4_journalled_zero_new_buffers(handle, inode, folio,
from + copied, to);
ret = ext4_walk_page_buffers(handle, inode,
folio_buffers(folio),
from, from + copied, &partial,
write_end_fn);
if (!partial)
folio_mark_uptodate(folio);
}
if (!verity)
size_changed = ext4_update_inode_size(inode, pos + copied);
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
folio_unlock(folio);
folio_put(folio);
if (old_size < pos && !verity) {
pagecache_isize_extended(inode, old_size, pos);
ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
}
if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size && !verity) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* Reserve space for 'nr_resv' clusters
*/
static int ext4_da_reserve_space(struct inode *inode, int nr_resv)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
int ret;
/*
* We will charge metadata quota at writeout time; this saves
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
ret = dquot_reserve_block(inode, EXT4_C2B(sbi, nr_resv));
if (ret)
return ret;
spin_lock(&ei->i_block_reservation_lock);
if (ext4_claim_free_clusters(sbi, nr_resv, 0)) {
spin_unlock(&ei->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, nr_resv));
return -ENOSPC;
}
ei->i_reserved_data_blocks += nr_resv;
trace_ext4_da_reserve_space(inode, nr_resv);
spin_unlock(&ei->i_block_reservation_lock);
return 0; /* success */
}
void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
trace_ext4_da_release_space(inode, to_free);
if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
* if there aren't enough reserved blocks, then the
* counter is messed up somewhere. Since this
* function is called from invalidate page, it's
* harmless to return without any action.
*/
ext4_warning(inode->i_sb, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
WARN_ON(1);
to_free = ei->i_reserved_data_blocks;
}
ei->i_reserved_data_blocks -= to_free;
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
/*
* Delayed allocation stuff
*/
struct mpage_da_data {
/* These are input fields for ext4_do_writepages() */
struct inode *inode;
struct writeback_control *wbc;
unsigned int can_map:1; /* Can writepages call map blocks? */
/* These are internal state of ext4_do_writepages() */
pgoff_t first_page; /* The first page to write */
pgoff_t next_page; /* Current page to examine */
pgoff_t last_page; /* Last page to examine */
/*
* Extent to map - this can be after first_page because that can be
* fully mapped. We somewhat abuse m_flags to store whether the extent
* is delalloc or unwritten.
*/
struct ext4_map_blocks map;
struct ext4_io_submit io_submit; /* IO submission data */
unsigned int do_map:1;
unsigned int scanned_until_end:1;
unsigned int journalled_more_data:1;
};
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
bool invalidate)
{
unsigned nr, i;
pgoff_t index, end;
struct folio_batch fbatch;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
/* This is necessary when next_page == 0. */
if (mpd->first_page >= mpd->next_page)
return;
mpd->scanned_until_end = 0;
index = mpd->first_page;
end = mpd->next_page - 1;
if (invalidate) {
ext4_lblk_t start, last;
start = index << (PAGE_SHIFT - inode->i_blkbits);
last = end << (PAGE_SHIFT - inode->i_blkbits);
/*
* avoid racing with extent status tree scans made by
* ext4_insert_delayed_block()
*/
down_write(&EXT4_I(inode)->i_data_sem);
ext4_es_remove_extent(inode, start, last - start + 1);
up_write(&EXT4_I(inode)->i_data_sem);
}
folio_batch_init(&fbatch);
while (index <= end) {
nr = filemap_get_folios(mapping, &index, end, &fbatch);
if (nr == 0)
break;
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
if (folio->index < mpd->first_page)
continue;
if (folio_next_index(folio) - 1 > end)
continue;
BUG_ON(!folio_test_locked(folio));
BUG_ON(folio_test_writeback(folio));
if (invalidate) {
if (folio_mapped(folio))
folio_clear_dirty_for_io(folio);
block_invalidate_folio(folio, 0,
folio_size(folio));
folio_clear_uptodate(folio);
}
folio_unlock(folio);
}
folio_batch_release(&fbatch);
}
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
EXT4_C2B(EXT4_SB(inode->i_sb),
ext4_count_free_clusters(sb)));
ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_freeclusters_counter)));
ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
ext4_msg(sb, KERN_CRIT, "Block reservation details");
ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
ei->i_reserved_data_blocks);
return;
}
/*
* Check whether the cluster containing lblk has been allocated or has
* delalloc reservation.
*
* Returns 0 if the cluster doesn't have either, 1 if it has delalloc
* reservation, 2 if it's already been allocated, negative error code on
* failure.
*/
static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
/* Has delalloc reservation? */
if (ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk))
return 1;
/* Already been allocated? */
if (ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk))
return 2;
ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk));
if (ret < 0)
return ret;
if (ret > 0)
return 2;
return 0;
}
/*
* ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents
* status tree, incrementing the reserved
* cluster/block count or making pending
* reservations where needed
*
* @inode - file containing the newly added block
* @lblk - start logical block to be added
* @len - length of blocks to be added
*
* Returns 0 on success, negative error code on failure.
*/
static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
bool lclu_allocated = false;
bool end_allocated = false;
ext4_lblk_t resv_clu;
ext4_lblk_t end = lblk + len - 1;
/*
* If the cluster containing lblk or end is shared with a delayed,
* written, or unwritten extent in a bigalloc file system, it's
* already been accounted for and does not need to be reserved.
* A pending reservation must be made for the cluster if it's
* shared with a written or unwritten extent and doesn't already
* have one. Written and unwritten extents can be purged from the
* extents status tree if the system is under memory pressure, so
* it's necessary to examine the extent tree if a search of the
* extents status tree doesn't get a match.
*/
if (sbi->s_cluster_ratio == 1) {
ret = ext4_da_reserve_space(inode, len);
if (ret != 0) /* ENOSPC */
return ret;
} else { /* bigalloc */
resv_clu = EXT4_B2C(sbi, end) - EXT4_B2C(sbi, lblk) + 1;
ret = ext4_clu_alloc_state(inode, lblk);
if (ret < 0)
return ret;
if (ret > 0) {
resv_clu--;
lclu_allocated = (ret == 2);
}
if (EXT4_B2C(sbi, lblk) != EXT4_B2C(sbi, end)) {
ret = ext4_clu_alloc_state(inode, end);
if (ret < 0)
return ret;
if (ret > 0) {
resv_clu--;
end_allocated = (ret == 2);
}
}
if (resv_clu) {
ret = ext4_da_reserve_space(inode, resv_clu);
if (ret != 0) /* ENOSPC */
return ret;
}
}
ext4_es_insert_delayed_extent(inode, lblk, len, lclu_allocated,
end_allocated);
return 0;
}
/*
* Looks up the requested blocks and sets the delalloc extent map.
* First try to look up for the extent entry that contains the requested
* blocks in the extent status tree without i_data_sem, then try to look
* up for the ondisk extent mapping with i_data_sem in read mode,
* finally hold i_data_sem in write mode, looks up again and add a
* delalloc extent entry if it still couldn't find any extent. Pass out
* the mapped extent through @map and return 0 on success.
*/
static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
{
struct extent_status es;
int retval;
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
map->m_flags = 0;
ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
(unsigned long) map->m_lblk);
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
map->m_len = min_t(unsigned int, map->m_len,
es.es_len - (map->m_lblk - es.es_lblk));
if (ext4_es_is_hole(&es))
goto add_delayed;
found:
/*
* Delayed extent could be allocated by fallocate.
* So we need to check it.
*/
if (ext4_es_is_delayed(&es)) {
map->m_flags |= EXT4_MAP_DELAYED;
return 0;
}
map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk;
if (ext4_es_is_written(&es))
map->m_flags |= EXT4_MAP_MAPPED;
else if (ext4_es_is_unwritten(&es))
map->m_flags |= EXT4_MAP_UNWRITTEN;
else
BUG();
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
#endif
return 0;
}
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode))
retval = 0;
else
retval = ext4_map_query_blocks(NULL, inode, map);
up_read(&EXT4_I(inode)->i_data_sem);
if (retval)
return retval < 0 ? retval : 0;
add_delayed:
down_write(&EXT4_I(inode)->i_data_sem);
/*
* Page fault path (ext4_page_mkwrite does not take i_rwsem)
* and fallocate path (no folio lock) can race. Make sure we
* lookup the extent status tree here again while i_data_sem
* is held in write mode, before inserting a new da entry in
* the extent status tree.
*/
if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
map->m_len = min_t(unsigned int, map->m_len,
es.es_len - (map->m_lblk - es.es_lblk));
if (!ext4_es_is_hole(&es)) {
up_write(&EXT4_I(inode)->i_data_sem);
goto found;
}
} else if (!ext4_has_inline_data(inode)) {
retval = ext4_map_query_blocks(NULL, inode, map);
if (retval) {
up_write(&EXT4_I(inode)->i_data_sem);
return retval < 0 ? retval : 0;
}
}
map->m_flags |= EXT4_MAP_DELAYED;
retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len);
up_write(&EXT4_I(inode)->i_data_sem);
return retval;
}
/*
* This is a special get_block_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
*
* For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
* We also have b_blocknr = -1 and b_bdev initialized properly
*
* For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
* We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
* initialized properly.
*/
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct ext4_map_blocks map;
sector_t invalid_block = ~((sector_t) 0xffff);
int ret = 0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
map.m_lblk = iblock;
map.m_len = 1;
/*
* first, we need to know whether the block is allocated already
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
ret = ext4_da_map_blocks(inode, &map);
if (ret < 0)
return ret;
if (map.m_flags & EXT4_MAP_DELAYED) {
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
return 0;
}
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
if (buffer_unwritten(bh)) {
/* A delayed write to unwritten bh should be marked
* new and mapped. Mapped ensures that we don't do
* get_block multiple times when we write to the same
* offset and new ensures that we do proper zero out
* for partial write.
*/
set_buffer_new(bh);
set_buffer_mapped(bh);
}
return 0;
}
static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio)
{
mpd->first_page += folio_nr_pages(folio);
folio_unlock(folio);
}
static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
{
size_t len;
loff_t size;
int err;
BUG_ON(folio->index != mpd->first_page);
folio_clear_dirty_for_io(folio);
/*
* We have to be very careful here! Nothing protects writeback path
* against i_size changes and the page can be writeably mapped into
* page tables. So an application can be growing i_size and writing
* data through mmap while writeback runs. folio_clear_dirty_for_io()
* write-protects our page in page tables and the page cannot get
* written to again until we release folio lock. So only after
* folio_clear_dirty_for_io() we are safe to sample i_size for
* ext4_bio_write_folio() to zero-out tail of the written page. We rely
* on the barrier provided by folio_test_clear_dirty() in
* folio_clear_dirty_for_io() to make sure i_size is really sampled only
* after page tables are updated.
*/
size = i_size_read(mpd->inode);
len = folio_size(folio);
if (folio_pos(folio) + len > size &&
!ext4_verity_in_progress(mpd->inode))
len = size & (len - 1);
err = ext4_bio_write_folio(&mpd->io_submit, folio, len);
if (!err)
mpd->wbc->nr_to_write--;
return err;
}
#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay))
/*
* mballoc gives us at most this number of blocks...
* XXX: That seems to be only a limitation of ext4_mb_normalize_request().
* The rest of mballoc seems to handle chunks up to full group size.
*/
#define MAX_WRITEPAGES_EXTENT_LEN 2048
/*
* mpage_add_bh_to_extent - try to add bh to extent of blocks to map
*
* @mpd - extent of blocks
* @lblk - logical number of the block in the file
* @bh - buffer head we want to add to the extent
*
* The function is used to collect contig. blocks in the same state. If the
* buffer doesn't require mapping for writeback and we haven't started the
* extent of buffers to map yet, the function returns 'true' immediately - the
* caller can write the buffer right away. Otherwise the function returns true
* if the block has been added to the extent, false if the block couldn't be
* added.
*/
static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
struct buffer_head *bh)
{
struct ext4_map_blocks *map = &mpd->map;
/* Buffer that doesn't need mapping for writeback? */
if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
(!buffer_delay(bh) && !buffer_unwritten(bh))) {
/* So far no extent to map => we write the buffer right away */
if (map->m_len == 0)
return true;
return false;
}
/* First block in the extent? */
if (map->m_len == 0) {
/* We cannot map unless handle is started... */
if (!mpd->do_map)
return false;
map->m_lblk = lblk;
map->m_len = 1;
map->m_flags = bh->b_state & BH_FLAGS;
return true;
}
/* Don't go larger than mballoc is willing to allocate */
if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
return false;
/* Can we merge the block to our big extent? */
if (lblk == map->m_lblk + map->m_len &&
(bh->b_state & BH_FLAGS) == map->m_flags) {
map->m_len++;
return true;
}
return false;
}
/*
* mpage_process_page_bufs - submit page buffers for IO or add them to extent
*
* @mpd - extent of blocks for mapping
* @head - the first buffer in the page
* @bh - buffer we should start processing from
* @lblk - logical number of the block in the file corresponding to @bh
*
* Walk through page buffers from @bh upto @head (exclusive) and either submit
* the page for IO if all buffers in this page were mapped and there's no
* accumulated extent of buffers to map or add buffers in the page to the
* extent of buffers to map. The function returns 1 if the caller can continue
* by processing the next page, 0 if it should stop adding buffers to the
* extent to map because we cannot extend it anymore. It can also return value
* < 0 in case of error during IO submission.
*/
static int mpage_process_page_bufs(struct mpage_da_data *mpd,
struct buffer_head *head,
struct buffer_head *bh,
ext4_lblk_t lblk)
{
struct inode *inode = mpd->inode;
int err;
ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
>> inode->i_blkbits;
if (ext4_verity_in_progress(inode))
blocks = EXT_MAX_BLOCKS;
do {
BUG_ON(buffer_locked(bh));
if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) {
/* Found extent to map? */
if (mpd->map.m_len)
return 0;
/* Buffer needs mapping and handle is not started? */
if (!mpd->do_map)
return 0;
/* Everything mapped so far and we hit EOF */
break;
}
} while (lblk++, (bh = bh->b_this_page) != head);
/* So far everything mapped? Submit the page for IO. */
if (mpd->map.m_len == 0) {
err = mpage_submit_folio(mpd, head->b_folio);
if (err < 0)
return err;
mpage_folio_done(mpd, head->b_folio);
}
if (lblk >= blocks) {
mpd->scanned_until_end = 1;
return 0;
}
return 1;
}
/*
* mpage_process_folio - update folio buffers corresponding to changed extent
* and may submit fully mapped page for IO
* @mpd: description of extent to map, on return next extent to map
* @folio: Contains these buffers.
* @m_lblk: logical block mapping.
* @m_pblk: corresponding physical mapping.
* @map_bh: determines on return whether this page requires any further
* mapping or not.
*
* Scan given folio buffers corresponding to changed extent and update buffer
* state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits.
* If the given folio is not fully mapped, we update @mpd to the next extent in
* the given folio that needs mapping & return @map_bh as true.
*/
static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio,
ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
bool *map_bh)
{
struct buffer_head *head, *bh;
ext4_io_end_t *io_end = mpd->io_submit.io_end;
ext4_lblk_t lblk = *m_lblk;
ext4_fsblk_t pblock = *m_pblk;
int err = 0;
int blkbits = mpd->inode->i_blkbits;
ssize_t io_end_size = 0;
struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
bh = head = folio_buffers(folio);
do {
if (lblk < mpd->map.m_lblk)
continue;
if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
/*
* Buffer after end of mapped extent.
* Find next buffer in the folio to map.
*/
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
io_end_vec->size += io_end_size;
err = mpage_process_page_bufs(mpd, head, bh, lblk);
if (err > 0)
err = 0;
if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
io_end_vec = ext4_alloc_io_end_vec(io_end);
if (IS_ERR(io_end_vec)) {
err = PTR_ERR(io_end_vec);
goto out;
}
io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits;
}
*map_bh = true;
goto out;
}
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock++;
}
clear_buffer_unwritten(bh);
io_end_size += (1 << blkbits);
} while (lblk++, (bh = bh->b_this_page) != head);
io_end_vec->size += io_end_size;
*map_bh = false;
out:
*m_lblk = lblk;
*m_pblk = pblock;
return err;
}
/*
* mpage_map_buffers - update buffers corresponding to changed extent and
* submit fully mapped pages for IO
*
* @mpd - description of extent to map, on return next extent to map
*
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
* and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
*/
static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
{
struct folio_batch fbatch;
unsigned nr, i;
struct inode *inode = mpd->inode;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
ext4_fsblk_t pblock;
int err;
bool map_bh = false;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
lblk = start << bpp_bits;
pblock = mpd->map.m_pblk;
folio_batch_init(&fbatch);
while (start <= end) {
nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch);
if (nr == 0)
break;
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
err = mpage_process_folio(mpd, folio, &lblk, &pblock,
&map_bh);
/*
* If map_bh is true, means page may require further bh
* mapping, or maybe the page was submitted for IO.
* So we return to call further extent mapping.
*/
if (err < 0 || map_bh)
goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_folio(mpd, folio);
if (err < 0)
goto out;
mpage_folio_done(mpd, folio);
}
folio_batch_release(&fbatch);
}
/* Extent fully mapped and matches with page boundary. We are done. */
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
out:
folio_batch_release(&fbatch);
return err;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
* to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
* writeback and there is nothing we can do about it so it might result
* in data loss. So use reserved blocks to allocate metadata if
* possible.
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL |
EXT4_GET_BLOCKS_IO_SUBMIT;
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
handle->h_rsv_handle = NULL;
}
ext4_set_io_unwritten_flag(mpd->io_submit.io_end);
}
BUG_ON(map->m_len == 0);
return 0;
}
/*
* mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
* mpd->len and submit pages underlying it for IO
*
* @handle - handle for journal operations
* @mpd - extent to map
* @give_up_on_write - we set this to true iff there is a fatal error and there
* is no hope of writing the data. The caller should discard
* dirty pages to avoid infinite loops.
*
* The function maps extent starting at mpd->lblk of length mpd->len. If it is
* delayed, blocks are allocated, if it is unwritten, we may need to convert
* them to initialized or split the described range from larger unwritten
* extent. Note that we need not map all the described range since allocation
* can return less blocks or the range is covered by more unwritten extents. We
* cannot map more because we are limited by reserved transaction credits. On
* the other hand we always make sure that the last touched page is fully
* mapped so that it can be written out (and thus forward progress is
* guaranteed). After mapping we submit all mapped pages for IO.
*/
static int mpage_map_and_submit_extent(handle_t *handle,
struct mpage_da_data *mpd,
bool *give_up_on_write)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int err;
loff_t disksize;
int progress = 0;
ext4_io_end_t *io_end = mpd->io_submit.io_end;
struct ext4_io_end_vec *io_end_vec;
io_end_vec = ext4_alloc_io_end_vec(io_end);
if (IS_ERR(io_end_vec))
return PTR_ERR(io_end_vec);
io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
struct super_block *sb = inode->i_sb;
if (ext4_emergency_state(sb))
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
* In the case of ENOSPC, if ext4_count_free_blocks()
* is non-zero, a commit should free up blocks.
*/
if ((err == -ENOMEM) ||
(err == -ENOSPC && ext4_count_free_clusters(sb))) {
if (progress)
goto update_disksize;
return err;
}
ext4_msg(sb, KERN_CRIT,
"Delayed block allocation failed for "
"inode %lu at logical offset %llu with"
" max blocks %u with error %d",
inode->i_ino,
(unsigned long long)map->m_lblk,
(unsigned)map->m_len, -err);
ext4_msg(sb, KERN_CRIT,
"This should not happen!! Data will "
"be lost\n");
if (err == -ENOSPC)
ext4_print_free_blocks(inode);
invalidate_dirty_pages:
*give_up_on_write = true;
return err;
}
progress = 1;
/*
* Update buffer state, submit mapped pages, and get us new
* extent to map
*/
err = mpage_map_and_submit_buffers(mpd);
if (err < 0)
goto update_disksize;
} while (map->m_len);
update_disksize:
/*
* Update on-disk size after IO is submitted. Races with
* truncate are avoided by checking i_size under i_data_sem.
*/
disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
int err2;
loff_t i_size;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = i_size_read(inode);
if (disksize > i_size)
disksize = i_size;
if (disksize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = disksize;
up_write(&EXT4_I(inode)->i_data_sem);
err2 = ext4_mark_inode_dirty(handle, inode);
if (err2) {
ext4_error_err(inode->i_sb, -err2,
"Failed to mark inode %lu dirty",
inode->i_ino);
}
if (!err)
err = err2;
}
return err;
}
/*
* Calculate the total number of credits to reserve for one writepages
* iteration. This is called from ext4_writepages(). We map an extent of
* up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
* the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
* bpp - 1 blocks in bpp different extents.
*/
static int ext4_da_writepages_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
return ext4_meta_trans_blocks(inode,
MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
}
static int ext4_journal_folio_buffers(handle_t *handle, struct folio *folio,
size_t len)
{
struct buffer_head *page_bufs = folio_buffers(folio);
struct inode *inode = folio->mapping->host;
int ret, err;
ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
NULL, do_journal_get_write_access);
err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len,
NULL, write_end_fn);
if (ret == 0)
ret = err;
err = ext4_jbd2_inode_add_write(handle, inode, folio_pos(folio), len);
if (ret == 0)
ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
return ret;
}
static int mpage_journal_page_buffers(handle_t *handle,
struct mpage_da_data *mpd,
struct folio *folio)
{
struct inode *inode = mpd->inode;
loff_t size = i_size_read(inode);
size_t len = folio_size(folio);
folio_clear_checked(folio);
mpd->wbc->nr_to_write--;
if (folio_pos(folio) + len > size &&
!ext4_verity_in_progress(inode))
len = size & (len - 1);
return ext4_journal_folio_buffers(handle, folio, len);
}
/*
* mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages
* needing mapping, submit mapped pages
*
* @mpd - where to look for pages
*
* Walk dirty pages in the mapping. If they are fully mapped, submit them for
* IO immediately. If we cannot map blocks, we submit just already mapped
* buffers in the page for IO and keep page dirty. When we can map blocks and
* we find a page which isn't mapped we start accumulating extent of buffers
* underlying these pages that needs mapping (formed by either delayed or
* unwritten buffers). We also lock the pages containing these buffers. The
* extent found is returned in @mpd structure (starting at mpd->lblk with
* length mpd->len blocks).
*
* Note that this function can attach bios to one io_end structure which are
* neither logically nor physically contiguous. Although it may seem as an
* unnecessary complication, it is actually inevitable in blocksize < pagesize
* case as we need to track IO to all buffers underlying a page in one io_end.
*/
static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
{
struct address_space *mapping = mpd->inode->i_mapping;
struct folio_batch fbatch;
unsigned int nr_folios;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
xa_mark_t tag;
int i, err = 0;
int blkbits = mpd->inode->i_blkbits;
ext4_lblk_t lblk;
struct buffer_head *head;
handle_t *handle = NULL;
int bpp = ext4_journal_blocks_per_page(mpd->inode);
if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
mpd->map.m_len = 0;
mpd->next_page = index;
if (ext4_should_journal_data(mpd->inode)) {
handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE,
bpp);
if (IS_ERR(handle))
return PTR_ERR(handle);
}
folio_batch_init(&fbatch);
while (index <= end) {
nr_folios = filemap_get_folios_tag(mapping, &index, end,
tag, &fbatch);
if (nr_folios == 0)
break;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
/*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to
* keep going because someone may be concurrently
* dirtying pages, and we might have synced a lot of
* newly appeared dirty pages, but have not synced all
* of the old dirty pages.
*/
if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
mpd->wbc->nr_to_write <=
mpd->map.m_len >> (PAGE_SHIFT - blkbits))
goto out;
/* If we can't merge this page, we are done. */
if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
goto out;
if (handle) {
err = ext4_journal_ensure_credits(handle, bpp,
0);
if (err < 0)
goto out;
}
folio_lock(folio);
/*
* If the page is no longer dirty, or its mapping no
* longer corresponds to inode we are writing (which
* means it has been truncated or invalidated), or the
* page is already under writeback and we are not doing
* a data integrity writeback, skip the page
*/
if (!folio_test_dirty(folio) ||
(folio_test_writeback(folio) &&
(mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
continue;
}
folio_wait_writeback(folio);
BUG_ON(folio_test_writeback(folio));
/*
* Should never happen but for buggy code in
* other subsystems that call
* set_page_dirty() without properly warning
* the file system first. See [1] for more
* information.
*
* [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
*/
if (!folio_buffers(folio)) {
ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index);
folio_clear_dirty(folio);
folio_unlock(folio);
continue;
}
if (mpd->map.m_len == 0)
mpd->first_page = folio->index;
mpd->next_page = folio_next_index(folio);
/*
* Writeout when we cannot modify metadata is simple.
* Just submit the page. For data=journal mode we
* first handle writeout of the page for checkpoint and
* only after that handle delayed page dirtying. This
* makes sure current data is checkpointed to the final
* location before possibly journalling it again which
* is desirable when the page is frequently dirtied
* through a pin.
*/
if (!mpd->can_map) {
err = mpage_submit_folio(mpd, folio);
if (err < 0)
goto out;
/* Pending dirtying of journalled data? */
if (folio_test_checked(folio)) {
err = mpage_journal_page_buffers(handle,
mpd, folio);
if (err < 0)
goto out;
mpd->journalled_more_data = 1;
}
mpage_folio_done(mpd, folio);
} else {
/* Add all dirty buffers to mpd */
lblk = ((ext4_lblk_t)folio->index) <<
(PAGE_SHIFT - blkbits);
head = folio_buffers(folio);
err = mpage_process_page_bufs(mpd, head, head,
lblk);
if (err <= 0)
goto out;
err = 0;
}
}
folio_batch_release(&fbatch);
cond_resched();
}
mpd->scanned_until_end = 1;
if (handle)
ext4_journal_stop(handle);
return 0;
out:
folio_batch_release(&fbatch);
if (handle)
ext4_journal_stop(handle);
return err;
}
static int ext4_do_writepages(struct mpage_da_data *mpd)
{
struct writeback_control *wbc = mpd->wbc;
pgoff_t writeback_index = 0;
long nr_to_write = wbc->nr_to_write;
int range_whole = 0;
int cycled = 1;
handle_t *handle = NULL;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
struct blk_plug plug;
bool give_up_on_write = false;
trace_ext4_writepages(inode, wbc);
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
* because that could violate lock ordering on umount
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
goto out_writepages;
/*
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
* will obscure the real source of the problem. We test
* fs shutdown state instead of sb->s_flag's SB_RDONLY because
* the latter could be true if the filesystem is mounted
* read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
ret = ext4_emergency_state(mapping->host->i_sb);
if (unlikely(ret))
goto out_writepages;
/*
* If we have inline data and arrive here, it means that
* we will soon create the block for the 1st page, so
* we'd better clear the inline data here.
*/
if (ext4_has_inline_data(inode)) {
/* Just inode will be modified... */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_writepages;
}
BUG_ON(ext4_test_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA));
ext4_destroy_inline_data(handle, inode);
ext4_journal_stop(handle);
}
/*
* data=journal mode does not do delalloc so we just need to writeout /
* journal already mapped buffers. On the other hand we need to commit
* transaction to make data stable. We expect all the data to be
* already in the journal (the only exception are DMA pinned pages
* dirtied behind our back) so we commit transaction here and run the
* writeback loop to checkpoint them. The checkpointing is not actually
* necessary to make data persistent *but* quite a few places (extent
* shifting operations, fsverity, ...) depend on being able to drop
* pagecache pages after calling filemap_write_and_wait() and for that
* checkpointing needs to happen.
*/
if (ext4_should_journal_data(inode)) {
mpd->can_map = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
ext4_fc_commit(sbi->s_journal,
EXT4_I(inode)->i_datasync_tid);
}
mpd->journalled_more_data = 0;
if (ext4_should_dioread_nolock(inode)) {
/*
* We may need to convert up to one extent per block in
* the page and we may dirty the inode.
*/
rsv_blocks = 1 + ext4_chunk_trans_blocks(inode,
PAGE_SIZE >> inode->i_blkbits);
}
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index;
if (writeback_index)
cycled = 0;
mpd->first_page = writeback_index;
mpd->last_page = -1;
} else {
mpd->first_page = wbc->range_start >> PAGE_SHIFT;
mpd->last_page = wbc->range_end >> PAGE_SHIFT;
}
ext4_io_submit_init(&mpd->io_submit, wbc);
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, mpd->first_page,
mpd->last_page);
blk_start_plug(&plug);
/*
* First writeback pages that don't need mapping - we can avoid
* starting a transaction unnecessarily and also avoid being blocked
* in the block layer on device congestion while having transaction
* started.
*/
mpd->do_map = 0;
mpd->scanned_until_end = 0;
mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd->io_submit.io_end) {
ret = -ENOMEM;
goto unplug;
}
ret = mpage_prepare_extent_to_map(mpd);
/* Unlock pages we didn't use */
mpage_release_unused_pages(mpd, false);
/* Submit prepared bio */
ext4_io_submit(&mpd->io_submit);
ext4_put_io_end_defer(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
if (ret < 0)
goto unplug;
while (!mpd->scanned_until_end && wbc->nr_to_write > 0) {
/* For each extent of pages we use new io_end */
mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd->io_submit.io_end) {
ret = -ENOMEM;
break;
}
WARN_ON_ONCE(!mpd->can_map);
/*
* We have two constraints: We find one extent to map and we
* must always write out whole page (makes a difference when
* blocksize < pagesize) so that we don't block on IO when we
* try to write out the rest of the page. Journalled mode is
* not supported by delalloc.
*/
BUG_ON(ext4_should_journal_data(inode));
needed_blocks = ext4_da_writepages_trans_blocks(inode);
/* start a new transaction */
handle = ext4_journal_start_with_reserve(inode,
EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
/* Release allocated io_end */
ext4_put_io_end(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
break;
}
mpd->do_map = 1;
trace_ext4_da_write_pages(inode, mpd->first_page, wbc);
ret = mpage_prepare_extent_to_map(mpd);
if (!ret && mpd->map.m_len)
ret = mpage_map_and_submit_extent(handle, mpd,
&give_up_on_write);
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
* to finish which may depend on writeback of pages to
* complete or on page lock to be released. In that
* case, we have to wait until after we have
* submitted all the IO, released page locks we hold,
* and dropped io_end reference (for extent conversion
* to be able to complete) before stopping the handle.
*/
if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
ext4_journal_stop(handle);
handle = NULL;
mpd->do_map = 0;
}
/* Unlock pages we didn't use */
mpage_release_unused_pages(mpd, give_up_on_write);
/* Submit prepared bio */
ext4_io_submit(&mpd->io_submit);
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
* we are still holding the transaction as we can
* release the last reference to io_end which may end
* up doing unwritten extent conversion.
*/
if (handle) {
ext4_put_io_end_defer(mpd->io_submit.io_end);
ext4_journal_stop(handle);
} else
ext4_put_io_end(mpd->io_submit.io_end);
mpd->io_submit.io_end = NULL;
if (ret == -ENOSPC && sbi->s_journal) {
/*
* Commit the transaction which would
* free blocks released in the transaction
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
ret = 0;
continue;
}
/* Fatal error - ENOMEM, EIO... */
if (ret)
break;
}
unplug:
blk_finish_plug(&plug);
if (!ret && !cycled && wbc->nr_to_write > 0) {
cycled = 1;
mpd->last_page = writeback_index - 1;
mpd->first_page = 0;
goto retry;
}
/* Update index */
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
* Set the writeback_index so that range_cyclic
* mode will write it back later
*/
mapping->writeback_index = mpd->first_page;
out_writepages:
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
return ret;
}
static int ext4_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct super_block *sb = mapping->host->i_sb;
struct mpage_da_data mpd = {
.inode = mapping->host,
.wbc = wbc,
.can_map = 1,
};
int ret;
int alloc_ctx;
ret = ext4_emergency_state(sb);
if (unlikely(ret))
return ret;
alloc_ctx = ext4_writepages_down_read(sb);
ret = ext4_do_writepages(&mpd);
/*
* For data=journal writeback we could have come across pages marked
* for delayed dirtying (PageChecked) which were just added to the
* running transaction. Try once more to get them to stable storage.
*/
if (!ret && mpd.journalled_more_data)
ret = ext4_do_writepages(&mpd);
ext4_writepages_up_read(sb, alloc_ctx);
return ret;
}
int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = jinode->i_dirty_start,
.range_end = jinode->i_dirty_end,
};
struct mpage_da_data mpd = {
.inode = jinode->i_vfs_inode,
.wbc = &wbc,
.can_map = 0,
};
return ext4_do_writepages(&mpd);
}
static int ext4_dax_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret;
long nr_to_write = wbc->nr_to_write;
struct inode *inode = mapping->host;
int alloc_ctx;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
return ret;
alloc_ctx = ext4_writepages_down_read(inode->i_sb);
trace_ext4_writepages(inode, wbc);
ret = dax_writeback_mapping_range(mapping,
EXT4_SB(inode->i_sb)->s_daxdev, wbc);
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
ext4_writepages_up_read(inode->i_sb, alloc_ctx);
return ret;
}
static int ext4_nonda_switch(struct super_block *sb)
{
s64 free_clusters, dirty_clusters;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
* switch to non delalloc mode if we are running low
* on free block. The free block accounting via percpu
* counters can get slightly wrong with percpu_counter_batch getting
* accumulated on each CPU without updating global counters
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
free_clusters =
percpu_counter_read_positive(&sbi->s_freeclusters_counter);
dirty_clusters =
percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
/*
* Start pushing delalloc when 1/2 of free blocks are dirty.
*/
if (dirty_clusters && (free_clusters < 2 * dirty_clusters))
try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
if (2 * free_clusters < 3 * dirty_clusters ||
free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
*/
return 1;
}
return 0;
}
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata)
{
int ret, retries = 0;
struct folio *folio;
pgoff_t index;
struct inode *inode = mapping->host;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
return ret;
index = pos >> PAGE_SHIFT;
if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
return ext4_write_begin(file, mapping, pos,
len, foliop, fsdata);
}
*fsdata = (void *)0;
trace_ext4_da_write_begin(inode, pos, len);
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_generic_write_inline_data(mapping, inode, pos, len,
foliop, fsdata, true);
if (ret < 0)
return ret;
if (ret == 1)
return 0;
}
retry:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
ret = ext4_block_write_begin(NULL, folio, pos, len,
ext4_da_get_block_prep);
if (ret < 0) {
folio_unlock(folio);
folio_put(folio);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold inode lock.
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
*foliop = folio;
return ret;
}
/*
* Check if we should update i_disksize
* when write to the end of file but not require block allocation
*/
static int ext4_da_should_update_i_disksize(struct folio *folio,
unsigned long offset)
{
struct buffer_head *bh;
struct inode *inode = folio->mapping->host;
unsigned int idx;
int i;
bh = folio_buffers(folio);
idx = offset >> inode->i_blkbits;
for (i = 0; i < idx; i++)
bh = bh->b_this_page;
if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
return 0;
return 1;
}
static int ext4_da_do_write_end(struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio)
{
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
bool disksize_changed = false;
loff_t new_i_size, zero_len = 0;
handle_t *handle;
if (unlikely(!folio_buffers(folio))) {
folio_unlock(folio);
folio_put(folio);
return -EIO;
}
/*
* block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
* flag, which all that's needed to trigger page writeback.
*/
copied = block_write_end(NULL, mapping, pos, len, copied,
folio, NULL);
new_i_size = pos + copied;
/*
* It's important to update i_size while still holding folio lock,
* because folio writeout could otherwise come in and zero beyond
* i_size.
*
* Since we are holding inode lock, we are sure i_disksize <=
* i_size. We also know that if i_disksize < i_size, there are
* delalloc writes pending in the range up to i_size. If the end of
* the current write is <= i_size, there's no need to touch
* i_disksize since writeback will push i_disksize up to i_size
* eventually. If the end of the current write is > i_size and
* inside an allocated block which ext4_da_should_update_i_disksize()
* checked, we need to update i_disksize here as certain
* ext4_writepages() paths not allocating blocks and update i_disksize.
*/
if (new_i_size > inode->i_size) {
unsigned long end;
i_size_write(inode, new_i_size);
end = (new_i_size - 1) & (PAGE_SIZE - 1);
if (copied && ext4_da_should_update_i_disksize(folio, end)) {
ext4_update_i_disksize(inode, new_i_size);
disksize_changed = true;
}
}
folio_unlock(folio);
folio_put(folio);
if (pos > old_size) {
pagecache_isize_extended(inode, old_size, pos);
zero_len = pos - old_size;
}
if (!disksize_changed && !zero_len)
return copied;
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle))
return PTR_ERR(handle);
if (zero_len)
ext4_zero_partial_blocks(handle, inode, old_size, zero_len);
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
return copied;
}
static int ext4_da_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
struct inode *inode = mapping->host;
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC)
return ext4_write_end(file, mapping, pos,
len, copied, folio, fsdata);
trace_ext4_da_write_end(inode, pos, len, copied);
if (write_mode != CONVERT_INLINE_DATA &&
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
ext4_has_inline_data(inode))
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
if (unlikely(copied < len) && !folio_test_uptodate(folio))
copied = 0;
return ext4_da_do_write_end(mapping, pos, len, copied, folio);
}
/*
* Force all delayed allocation blocks to be allocated for a given inode.
*/
int ext4_alloc_da_blocks(struct inode *inode)
{
trace_ext4_alloc_da_blocks(inode);
if (!EXT4_I(inode)->i_reserved_data_blocks)
return 0;
/*
* We do something simple for now. The filemap_flush() will
* also start triggering a write of the data blocks, which is
* not strictly speaking necessary (and for users of
* laptop_mode, not even desirable). However, to do otherwise
* would require replicating code paths in:
*
* ext4_writepages() ->
* write_cache_pages() ---> (via passed in callback function)
* __mpage_da_writepage() -->
* mpage_add_bh_to_extent()
* mpage_da_map_blocks()
*
* The problem is that write_cache_pages(), located in
* mm/page-writeback.c, marks pages clean in preparation for
* doing I/O, which is not desirable if we're not planning on
* doing I/O at all.
*
* We could call write_cache_pages(), and then redirty all of
* the pages by calling redirty_page_for_writepage() but that
* would be ugly in the extreme. So instead we would need to
* replicate parts of the code in the above functions,
* simplifying them because we wouldn't actually intend to
* write out the pages, but rather only collect contiguous
* logical block extents, call the multi-block allocator, and
* then update the buffer heads with the block allocations.
*
* For now, though, we'll cheat by calling filemap_flush(),
* which will map the blocks, and start the I/O, but not
* actually wait for the I/O to complete.
*/
return filemap_flush(inode->i_mapping);
}
/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
*
* Naturally, this is dangerous if the block concerned is still in the
* journal. If somebody makes a swapfile on an ext4 data-journaling
* filesystem and enables swap, then they may get a nasty shock when the
* data getting swapped to that swapfile suddenly gets overwritten by
* the original zero's written out previously to the journal and
* awaiting writeback in the kernel's buffer cache.
*
* So, if we see any bmap calls here on a modified, data-journaled file,
* take extra steps to flush any blocks which might be in the cache.
*/
static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
sector_t ret = 0;
inode_lock_shared(inode);
/*
* We can get here for an inline file via the FIBMAP ioctl
*/
if (ext4_has_inline_data(inode))
goto out;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
(test_opt(inode->i_sb, DELALLOC) ||
ext4_should_journal_data(inode))) {
/*
* With delalloc or journalled data we want to sync the file so
* that we can make sure we allocate blocks for file and data
* is in place for the user to see it
*/
filemap_write_and_wait(mapping);
}
ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
out:
inode_unlock_shared(inode);
return ret;
}
static int ext4_read_folio(struct file *file, struct folio *folio)
{
int ret = -EAGAIN;
struct inode *inode = folio->mapping->host;
trace_ext4_read_folio(inode, folio);
if (ext4_has_inline_data(inode))
ret = ext4_readpage_inline(inode, folio);
if (ret == -EAGAIN)
return ext4_mpage_readpages(inode, NULL, folio);
return ret;
}
static void ext4_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
/* If the file has inline data, no need to do readahead. */
if (ext4_has_inline_data(inode))
return;
ext4_mpage_readpages(inode, rac, NULL);
}
static void ext4_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
trace_ext4_invalidate_folio(folio, offset, length);
/* No journalling happens on data buffers when this function is used */
WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio)));
block_invalidate_folio(folio, offset, length);
}
static int __ext4_journalled_invalidate_folio(struct folio *folio,
size_t offset, size_t length)
{
journal_t *journal = EXT4_JOURNAL(folio->mapping->host);
trace_ext4_journalled_invalidate_folio(folio, offset, length);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
if (offset == 0 && length == folio_size(folio))
folio_clear_checked(folio);
return jbd2_journal_invalidate_folio(journal, folio, offset, length);
}
/* Wrapper for aops... */
static void ext4_journalled_invalidate_folio(struct folio *folio,
size_t offset,
size_t length)
{
WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0);
}
static bool ext4_release_folio(struct folio *folio, gfp_t wait)
{
struct inode *inode = folio->mapping->host;
journal_t *journal = EXT4_JOURNAL(inode);
trace_ext4_release_folio(inode, folio);
/* Page has dirty journalled data -> cannot release */
if (folio_test_checked(folio))
return false;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, folio);
else
return try_to_free_buffers(folio);
}
static bool ext4_inode_datasync_dirty(struct inode *inode)
{
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
if (journal) {
if (jbd2_transaction_committed(journal,
EXT4_I(inode)->i_datasync_tid))
return false;
if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
return !list_empty(&EXT4_I(inode)->i_fc_list);
return true;
}
/* Any metadata buffers to write? */
if (!list_empty(&inode->i_mapping->i_private_list))
return true;
return inode->i_state & I_DIRTY_DATASYNC;
}
static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
struct ext4_map_blocks *map, loff_t offset,
loff_t length, unsigned int flags)
{
u8 blkbits = inode->i_blkbits;
/*
* Writes that span EOF might trigger an I/O size update on completion,
* so consider them to be dirty for the purpose of O_DSYNC, even if
* there is no other metadata changes being made or are pending.
*/
iomap->flags = 0;
if (ext4_inode_datasync_dirty(inode) ||
offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
if (map->m_flags & EXT4_MAP_NEW)
iomap->flags |= IOMAP_F_NEW;
/* HW-offload atomics are always used */
if (flags & IOMAP_ATOMIC)
iomap->flags |= IOMAP_F_ATOMIC_BIO;
if (flags & IOMAP_DAX)
iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
else
iomap->bdev = inode->i_sb->s_bdev;
iomap->offset = (u64) map->m_lblk << blkbits;
iomap->length = (u64) map->m_len << blkbits;
if ((map->m_flags & EXT4_MAP_MAPPED) &&
!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
iomap->flags |= IOMAP_F_MERGED;
/*
* Flags passed to ext4_map_blocks() for direct I/O writes can result
* in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
* set. In order for any allocated unwritten extents to be converted
* into written extents correctly within the ->end_io() handler, we
* need to ensure that the iomap->type is set appropriately. Hence, the
* reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has
* been set first.
*/
if (map->m_flags & EXT4_MAP_UNWRITTEN) {
iomap->type = IOMAP_UNWRITTEN;
iomap->addr = (u64) map->m_pblk << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else if (map->m_flags & EXT4_MAP_MAPPED) {
iomap->type = IOMAP_MAPPED;
iomap->addr = (u64) map->m_pblk << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else if (map->m_flags & EXT4_MAP_DELAYED) {
iomap->type = IOMAP_DELALLOC;
iomap->addr = IOMAP_NULL_ADDR;
} else {
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
}
}
static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
unsigned int flags)
{
handle_t *handle;
u8 blkbits = inode->i_blkbits;
int ret, dio_credits, m_flags = 0, retries = 0;
/*
* Trim the mapping request to the maximum value that we can map at
* once for direct I/O.
*/
if (map->m_len > DIO_MAX_BLOCKS)
map->m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map->m_len);
retry:
/*
* Either we allocate blocks and then don't get an unwritten extent, so
* in that case we have reserved enough credits. Or, the blocks are
* already allocated and unwritten. In that case, the extent conversion
* fits into the credits as well.
*/
handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
/*
* DAX and direct I/O are the only two operations that are currently
* supported with IOMAP_WRITE.
*/
WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
if (flags & IOMAP_DAX)
m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
/*
* We use i_size instead of i_disksize here because delalloc writeback
* can complete at any point during the I/O and subsequently push the
* i_disksize out to i_size. This could be beyond where direct I/O is
* happening and thus expose allocated blocks to direct I/O reads.
*/
else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
m_flags = EXT4_GET_BLOCKS_CREATE;
else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
ret = ext4_map_blocks(handle, inode, map, m_flags);
/*
* We cannot fill holes in indirect tree based inodes as that could
* expose stale data in the case of a crash. Use the magic error code
* to fallback to buffered I/O.
*/
if (!m_flags && !ret)
ret = -ENOTBLK;
ext4_journal_stop(handle);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
int ret;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
return -ERANGE;
/*
* Calculate the first and last logical blocks respectively.
*/
map.m_lblk = offset >> blkbits;
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
if (flags & IOMAP_WRITE) {
/*
* We check here if the blocks are already allocated, then we
* don't need to start a journal txn and we can directly return
* the mapping information. This could boost performance
* especially in multi-threaded overwrite requests.
*/
if (offset + length <= i_size_read(inode)) {
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret > 0 && (map.m_flags & EXT4_MAP_MAPPED))
goto out;
}
ret = ext4_iomap_alloc(inode, &map, flags);
} else {
ret = ext4_map_blocks(NULL, inode, &map, 0);
}
if (ret < 0)
return ret;
out:
/*
* When inline encryption is enabled, sometimes I/O to an encrypted file
* has to be broken up to guarantee DUN contiguity. Handle this by
* limiting the length of the mapping returned.
*/
map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
ext4_set_iomap(inode, iomap, &map, offset, length, flags);
return 0;
}
static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
loff_t length, unsigned flags, struct iomap *iomap,
struct iomap *srcmap)
{
int ret;
/*
* Even for writes we don't need to allocate blocks, so just pretend
* we are reading to save overhead of starting a transaction.
*/
flags &= ~IOMAP_WRITE;
ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED);
return ret;
}
static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
{
/* must be a directio to fall back to buffered */
if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) !=
(IOMAP_WRITE | IOMAP_DIRECT))
return false;
/* atomic writes are all-or-nothing */
if (flags & IOMAP_ATOMIC)
return false;
/* can only try again if we wrote nothing */
return written == 0;
}
static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
/*
* Check to see whether an error occurred while writing out the data to
* the allocated blocks. If so, return the magic error code for
* non-atomic write so that we fallback to buffered I/O and attempt to
* complete the remainder of the I/O.
* For non-atomic writes, any blocks that may have been
* allocated in preparation for the direct I/O will be reused during
* buffered I/O. For atomic write, we never fallback to buffered-io.
*/
if (ext4_want_directio_fallback(flags, written))
return -ENOTBLK;
return 0;
}
const struct iomap_ops ext4_iomap_ops = {
.iomap_begin = ext4_iomap_begin,
.iomap_end = ext4_iomap_end,
};
const struct iomap_ops ext4_iomap_overwrite_ops = {
.iomap_begin = ext4_iomap_overwrite_begin,
.iomap_end = ext4_iomap_end,
};
static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
loff_t length, unsigned int flags,
struct iomap *iomap, struct iomap *srcmap)
{
int ret;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
if (ext4_has_inline_data(inode)) {
ret = ext4_inline_data_iomap(inode, iomap);
if (ret != -EAGAIN) {
if (ret == 0 && offset >= iomap->length)
ret = -ENOENT;
return ret;
}
}
/*
* Calculate the first and last logical block respectively.
*/
map.m_lblk = offset >> blkbits;
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
/*
* Fiemap callers may call for offset beyond s_bitmap_maxbytes.
* So handle it here itself instead of querying ext4_map_blocks().
* Since ext4_map_blocks() will warn about it and will return
* -EIO error.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (offset >= sbi->s_bitmap_maxbytes) {
map.m_flags = 0;
goto set_iomap;
}
}
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret < 0)
return ret;
set_iomap:
ext4_set_iomap(inode, iomap, &map, offset, length, flags);
return 0;
}
const struct iomap_ops ext4_iomap_report_ops = {
.iomap_begin = ext4_iomap_begin_report,
};
/*
* For data=journal mode, folio should be marked dirty only when it was
* writeably mapped. When that happens, it was already attached to the
* transaction and marked as jbddirty (we take care of this in
* ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings
* so we should have nothing to do here, except for the case when someone
* had the page pinned and dirtied the page through this pin (e.g. by doing
* direct IO to it). In that case we'd need to attach buffers here to the
* transaction but we cannot due to lock ordering. We cannot just dirty the
* folio and leave attached buffers clean, because the buffers' dirty state is
* "definitive". We cannot just set the buffers dirty or jbddirty because all
* the journalling code will explode. So what we do is to mark the folio
* "pending dirty" and next time ext4_writepages() is called, attach buffers
* to the transaction appropriately.
*/
static bool ext4_journalled_dirty_folio(struct address_space *mapping,
struct folio *folio)
{
WARN_ON_ONCE(!folio_buffers(folio));
if (folio_maybe_dma_pinned(folio))
folio_set_checked(folio);
return filemap_dirty_folio(mapping, folio);
}
static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio)
{
WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio));
WARN_ON_ONCE(!folio_buffers(folio));
return block_dirty_folio(mapping, folio);
}
static int ext4_iomap_swap_activate(struct swap_info_struct *sis,
struct file *file, sector_t *span)
{
return iomap_swapfile_activate(sis, file, span,
&ext4_iomap_report_ops);
}
static const struct address_space_operations ext4_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_write_end,
.dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_journalled_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.dirty_folio = ext4_journalled_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_journalled_invalidate_folio,
.release_folio = ext4_release_folio,
.migrate_folio = buffer_migrate_folio_norefs,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_da_aops = {
.read_folio = ext4_read_folio,
.readahead = ext4_readahead,
.writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
.invalidate_folio = ext4_invalidate_folio,
.release_folio = ext4_release_folio,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_dax_aops = {
.writepages = ext4_dax_writepages,
.dirty_folio = noop_dirty_folio,
.bmap = ext4_bmap,
.swap_activate = ext4_iomap_swap_activate,
};
void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
case EXT4_INODE_ORDERED_DATA_MODE:
case EXT4_INODE_WRITEBACK_DATA_MODE:
break;
case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
return;
default:
BUG();
}
if (IS_DAX(inode))
inode->i_mapping->a_ops = &ext4_dax_aops;
else if (test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else
inode->i_mapping->a_ops = &ext4_aops;
}
/*
* Here we can't skip an unwritten buffer even though it usually reads zero
* because it might have data in pagecache (eg, if called from ext4_zero_range,
* ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a
* racing writeback can come later and flush the stale pagecache to disk.
*/
static int __ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
ext4_fsblk_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize, pos;
ext4_lblk_t iblock;
struct inode *inode = mapping->host;
struct buffer_head *bh;
struct folio *folio;
int err = 0;
folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT,
FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
mapping_gfp_constraint(mapping, ~__GFP_FS));
if (IS_ERR(folio))
return PTR_ERR(folio);
blocksize = inode->i_sb->s_blocksize;
iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
bh = folio_buffers(folio);
if (!bh)
bh = create_empty_buffers(folio, blocksize, 0);
/* Find the buffer that contains "offset" */
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
if (buffer_freed(bh)) {
BUFFER_TRACE(bh, "freed: skip");
goto unlock;
}
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "unmapped");
ext4_get_block(inode, iblock, bh, 0);
/* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "still unmapped");
goto unlock;
}
}
/* Ok, it's mapped. Make sure it's up-to-date */
if (folio_test_uptodate(folio))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
err = ext4_read_bh_lock(bh, 0, true);
if (err)
goto unlock;
if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
err = fscrypt_decrypt_pagecache_blocks(folio,
blocksize,
bh_offset(bh));
if (err) {
clear_buffer_uptodate(bh);
goto unlock;
}
}
}
if (ext4_should_journal_data(inode)) {
BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
if (err)
goto unlock;
}
folio_zero_range(folio, offset, length);
BUFFER_TRACE(bh, "zeroed end of block");
if (ext4_should_journal_data(inode)) {
err = ext4_dirty_journalled_data(handle, bh);
} else {
err = 0;
mark_buffer_dirty(bh);
if (ext4_should_order_data(inode))
err = ext4_jbd2_inode_add_write(handle, inode, from,
length);
}
unlock:
folio_unlock(folio);
folio_put(folio);
return err;
}
/*
* ext4_block_zero_page_range() zeros out a mapping of length 'length'
* starting from file offset 'from'. The range to be zero'd must
* be contained with in one block. If the specified range exceeds
* the end of the block it will be shortened to end of the block
* that corresponds to 'from'
*/
static int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
struct inode *inode = mapping->host;
unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned max = blocksize - (offset & (blocksize - 1));
/*
* correct length if it does not fall between
* 'from' and the end of the block
*/
if (length > max || length < 0)
length = max;
if (IS_DAX(inode)) {
return dax_zero_range(inode, from, length, NULL,
&ext4_iomap_ops);
}
return __ext4_block_zero_page_range(handle, mapping, from, length);
}
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
static int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_SIZE-1);
unsigned length;
unsigned blocksize;
struct inode *inode = mapping->host;
/* If we are processing an encrypted inode during orphan list handling */
if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode))
return 0;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
return ext4_block_zero_page_range(handle, mapping, from, length);
}
int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t length)
{
struct super_block *sb = inode->i_sb;
struct address_space *mapping = inode->i_mapping;
unsigned partial_start, partial_end;
ext4_fsblk_t start, end;
loff_t byte_end = (lstart + length - 1);
int err = 0;
partial_start = lstart & (sb->s_blocksize - 1);
partial_end = byte_end & (sb->s_blocksize - 1);
start = lstart >> sb->s_blocksize_bits;
end = byte_end >> sb->s_blocksize_bits;
/* Handle partial zero within the single block */
if (start == end &&
(partial_start || (partial_end != sb->s_blocksize - 1))) {
err = ext4_block_zero_page_range(handle, mapping,
lstart, length);
return err;
}
/* Handle partial zero out on the start of the range */
if (partial_start) {
err = ext4_block_zero_page_range(handle, mapping,
lstart, sb->s_blocksize);
if (err)
return err;
}
/* Handle partial zero out on the end of the range */
if (partial_end != sb->s_blocksize - 1)
err = ext4_block_zero_page_range(handle, mapping,
byte_end - partial_end,
partial_end + 1);
return err;
}
int ext4_can_truncate(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
return 1;
if (S_ISDIR(inode->i_mode))
return 1;
if (S_ISLNK(inode->i_mode))
return !ext4_inode_is_fast_symlink(inode);
return 0;
}
/*
* We have to make sure i_disksize gets properly updated before we truncate
* page cache due to hole punching or zero range. Otherwise i_disksize update
* can get lost as it may have been postponed to submission of writeback but
* that will never happen after we truncate page cache.
*/
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
loff_t len)
{
handle_t *handle;
int ret;
loff_t size = i_size_read(inode);
WARN_ON(!inode_is_locked(inode));
if (offset > size || offset + len < size)
return 0;
if (EXT4_I(inode)->i_disksize >= size)
return 0;
handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_update_i_disksize(inode, size);
ret = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
return ret;
}
static inline void ext4_truncate_folio(struct inode *inode,
loff_t start, loff_t end)
{
unsigned long blocksize = i_blocksize(inode);
struct folio *folio;
/* Nothing to be done if no complete block needs to be truncated. */
if (round_up(start, blocksize) >= round_down(end, blocksize))
return;
folio = filemap_lock_folio(inode->i_mapping, start >> PAGE_SHIFT);
if (IS_ERR(folio))
return;
if (folio_mkclean(folio))
folio_mark_dirty(folio);
folio_unlock(folio);
folio_put(folio);
}
int ext4_truncate_page_cache_block_range(struct inode *inode,
loff_t start, loff_t end)
{
unsigned long blocksize = i_blocksize(inode);
int ret;
/*
* For journalled data we need to write (and checkpoint) pages
* before discarding page cache to avoid inconsitent data on disk
* in case of crash before freeing or unwritten converting trans
* is committed.
*/
if (ext4_should_journal_data(inode)) {
ret = filemap_write_and_wait_range(inode->i_mapping, start,
end - 1);
if (ret)
return ret;
goto truncate_pagecache;
}
/*
* If the block size is less than the page size, the file's mapped
* blocks within one page could be freed or converted to unwritten.
* So it's necessary to remove writable userspace mappings, and then
* ext4_page_mkwrite() can be called during subsequent write access
* to these partial folios.
*/
if (!IS_ALIGNED(start | end, PAGE_SIZE) &&
blocksize < PAGE_SIZE && start < inode->i_size) {
loff_t page_boundary = round_up(start, PAGE_SIZE);
ext4_truncate_folio(inode, start, min(page_boundary, end));
if (end > page_boundary)
ext4_truncate_folio(inode,
round_down(end, PAGE_SIZE), end);
}
truncate_pagecache:
truncate_pagecache_range(inode, start, end - 1);
return 0;
}
static void ext4_wait_dax_page(struct inode *inode)
{
filemap_invalidate_unlock(inode->i_mapping);
schedule();
filemap_invalidate_lock(inode->i_mapping);
}
int ext4_break_layouts(struct inode *inode)
{
if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
return -EINVAL;
return dax_break_layout_inode(inode, ext4_wait_dax_page);
}
/*
* ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
* @offset: The offset where the hole will begin
* @len: The length of the hole
*
* Returns: 0 on success or negative on failure
*/
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t start_lblk, end_lblk;
loff_t max_end = EXT4_SB(sb)->s_bitmap_maxbytes - sb->s_blocksize;
loff_t end = offset + length;
handle_t *handle;
unsigned int credits;
int ret;
trace_ext4_punch_hole(inode, offset, length, 0);
WARN_ON_ONCE(!inode_is_locked(inode));
/* No need to punch hole beyond i_size */
if (offset >= inode->i_size)
return 0;
/*
* If the hole extends beyond i_size, set the hole to end after
* the page that contains i_size, and also make sure that the hole
* within one block before last range.
*/
if (end > inode->i_size)
end = round_up(inode->i_size, PAGE_SIZE);
if (end > max_end)
end = max_end;
length = end - offset;
/*
* Attach jinode to inode for jbd2 if we do any zeroing of partial
* block.
*/
if (!IS_ALIGNED(offset | end, sb->s_blocksize)) {
ret = ext4_inode_attach_jinode(inode);
if (ret < 0)
return ret;
}
ret = ext4_update_disksize_before_punch(inode, offset, length);
if (ret)
return ret;
/* Now release the pages and zero block aligned part of pages*/
ret = ext4_truncate_page_cache_block_range(inode, offset, end);
if (ret)
return ret;
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_std_error(sb, ret);
return ret;
}
ret = ext4_zero_partial_blocks(handle, inode, offset, length);
if (ret)
goto out_handle;
/* If there are blocks to remove, do it */
start_lblk = EXT4_B_TO_LBLK(inode, offset);
end_lblk = end >> inode->i_blkbits;
if (end_lblk > start_lblk) {
ext4_lblk_t hole_len = end_lblk - start_lblk;
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, start_lblk, hole_len);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_remove_space(inode, start_lblk,
end_lblk - 1);
else
ret = ext4_ind_remove_space(handle, inode, start_lblk,
end_lblk);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_handle;
}
ext4_es_insert_extent(inode, start_lblk, hole_len, ~0,
EXTENT_STATUS_HOLE, 0);
up_write(&EXT4_I(inode)->i_data_sem);
}
ext4_fc_track_range(handle, inode, start_lblk, end_lblk);
ret = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret))
goto out_handle;
ext4_update_inode_fsync_trans(handle, inode, 1);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
out_handle:
ext4_journal_stop(handle);
return ret;
}
int ext4_inode_attach_jinode(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct jbd2_inode *jinode;
if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
return 0;
jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
return 0;
}
/*
* ext4_truncate()
*
* We block out ext4_get_block() block instantiations across the entire
* transaction, and VFS/VM ensures that ext4_truncate() cannot run
* simultaneously on behalf of the same inode.
*
* As we work through the truncate and commit bits of it to the journal there
* is one core, guiding principle: the file's tree must always be consistent on
* disk. We must be able to restart the truncate after a crash.
*
* The file's tree may be transiently inconsistent in memory (although it
* probably isn't), but whenever we close off and commit a journal transaction,
* the contents of (the filesystem + the journal) must be consistent and
* restartable. It's pretty simple, really: bottom up, right to left (although
* left-to-right works OK too).
*
* Note that at recovery time, journal replay occurs *before* the restart of
* truncate against the orphan inode list.
*
* The committed inode has the new, desired i_size (which is the same as
* i_disksize in this case). After a crash, ext4_orphan_cleanup() will see
* that this inode's truncate did not complete and it will again call
* ext4_truncate() to have another go. So there will be instantiated blocks
* to the right of the truncation point in a crashed ext4 filesystem. But
* that's fine - as long as they are linked from the inode, the post-crash
* ext4_truncate() run will find them and release them.
*/
int ext4_truncate(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int credits;
int err = 0, err2;
handle_t *handle;
struct address_space *mapping = inode->i_mapping;
/*
* There is a possibility that we're either freeing the inode
* or it's a completely new inode. In those cases we might not
* have i_rwsem locked because it's not necessary.
*/
if (!(inode->i_state & (I_NEW|I_FREEING)))
WARN_ON(!inode_is_locked(inode));
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
goto out_trace;
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
if (ext4_has_inline_data(inode)) {
int has_inline = 1;
err = ext4_inline_data_truncate(inode, &has_inline);
if (err || has_inline)
goto out_trace;
}
/* If we zero-out tail of the page, we have to create jinode for jbd2 */
if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
err = ext4_inode_attach_jinode(inode);
if (err)
goto out_trace;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_trace;
}
if (inode->i_size & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle, mapping, inode->i_size);
/*
* We add the inode to the orphan list, so that if this
* truncate spans multiple transactions, and we crash, we will
* resume the truncate when the filesystem recovers. It also
* marks the inode dirty, to catch the new size.
*
* Implication: the file must always be in a sane, consistent
* truncatable state while each transaction commits.
*/
err = ext4_orphan_add(handle, inode);
if (err)
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
err = ext4_ext_truncate(handle, inode);
else
ext4_ind_truncate(handle, inode);
up_write(&ei->i_data_sem);
if (err)
goto out_stop;
if (IS_SYNC(inode))
ext4_handle_sync(handle);
out_stop:
/*
* If this was a simple ftruncate() and the file will remain alive,
* then we need to clear up the orphan record which we created above.
* However, if this was a real unlink then we were called by
* ext4_evict_inode(), and we allow that function to clean up the
* orphan info for us.
*/
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
ext4_journal_stop(handle);
out_trace:
trace_ext4_truncate_exit(inode);
return err;
}
static inline u64 ext4_inode_peek_iversion(const struct inode *inode)
{
if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
return inode_peek_iversion_raw(inode);
else
return inode_peek_iversion(inode);
}
static int ext4_inode_blocks_set(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
struct inode *inode = &(ei->vfs_inode);
u64 i_blocks = READ_ONCE(inode->i_blocks);
struct super_block *sb = inode->i_sb;
if (i_blocks <= ~0U) {
/*
* i_blocks can be represented in a 32 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = 0;
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
return 0;
}
/*
* This should never happen since sb->s_maxbytes should not have
* allowed this, sb->s_maxbytes was set according to the huge_file
* feature in ext4_fill_super().
*/
if (!ext4_has_feature_huge_file(sb))
return -EFSCORRUPTED;
if (i_blocks <= 0xffffffffffffULL) {
/*
* i_blocks can be represented in a 48 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
} else {
ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
/* i_block is stored in file system block size */
i_blocks = i_blocks >> (inode->i_blkbits - 9);
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
}
return 0;
}
static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
uid_t i_uid;
gid_t i_gid;
projid_t i_projid;
int block;
int err;
err = ext4_inode_blocks_set(raw_inode, ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
i_uid = i_uid_read(inode);
i_gid = i_gid_read(inode);
i_projid = from_kprojid(&init_user_ns, ei->i_projid);
if (!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
/*
* Fix up interoperability with old kernels. Otherwise,
* old inodes get re-used with the upper 16 bits of the
* uid/gid intact.
*/
if (ei->i_dtime && list_empty(&ei->i_orphan)) {
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
} else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid));
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
EXT4_INODE_SET_CTIME(inode, raw_inode);
EXT4_INODE_SET_MTIME(inode, raw_inode);
EXT4_INODE_SET_ATIME(inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
ext4_isize_set(raw_inode, ei->i_disksize);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
raw_inode->i_block[0] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
raw_inode->i_block[1] = 0;
} else {
raw_inode->i_block[0] = 0;
raw_inode->i_block[1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
raw_inode->i_block[2] = 0;
}
} else if (!ext4_has_inline_data(inode)) {
for (block = 0; block < EXT4_N_BLOCKS; block++)
raw_inode->i_block[block] = ei->i_data[block];
}
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
u64 ivers = ext4_inode_peek_iversion(inode);
raw_inode->i_disk_version = cpu_to_le32(ivers);
if (ei->i_extra_isize) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
raw_inode->i_version_hi =
cpu_to_le32(ivers >> 32);
raw_inode->i_extra_isize =
cpu_to_le16(ei->i_extra_isize);
}
}
if (i_projid != EXT4_DEF_PROJID &&
!ext4_has_feature_project(inode->i_sb))
err = err ?: -EFSCORRUPTED;
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
raw_inode->i_projid = cpu_to_le32(i_projid);
ext4_inode_csum_set(inode, raw_inode, ei);
return err;
}
/*
* ext4_get_inode_loc returns with an extra refcount against the inode's
* underlying buffer_head on success. If we pass 'inode' and it does not
* have in-inode xattr, we have all inode data in memory that is needed
* to recreate the on-disk version of this inode.
*/
static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
struct inode *inode, struct ext4_iloc *iloc,
ext4_fsblk_t *ret_block)
{
struct ext4_group_desc *gdp;
struct buffer_head *bh;
ext4_fsblk_t block;
struct blk_plug plug;
int inodes_per_block, inode_offset;
iloc->bh = NULL;
if (ino < EXT4_ROOT_INO ||
ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return -EFSCORRUPTED;
iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
if (!gdp)
return -EIO;
/*
* Figure out the offset within the block group inode table
*/
inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
inode_offset = ((ino - 1) %
EXT4_INODES_PER_GROUP(sb));
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
block = ext4_inode_table(sb, gdp);
if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) ||
(block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) {
ext4_error(sb, "Invalid inode table block %llu in "
"block_group %u", block, iloc->block_group);
return -EFSCORRUPTED;
}
block += (inode_offset / inodes_per_block);
bh = sb_getblk(sb, block);
if (unlikely(!bh))
return -ENOMEM;
if (ext4_buffer_uptodate(bh))
goto has_buffer;
lock_buffer(bh);
if (ext4_buffer_uptodate(bh)) {
/* Someone brought it uptodate while we waited */
unlock_buffer(bh);
goto has_buffer;
}
/*
* If we have all information of the inode in memory and this
* is the only valid inode in the block, we need not read the
* block.
*/
if (inode && !ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct buffer_head *bitmap_bh;
int i, start;
start = inode_offset & ~(inodes_per_block - 1);
/* Is the inode bitmap in cache? */
bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
if (unlikely(!bitmap_bh))
goto make_io;
/*
* If the inode bitmap isn't in cache then the
* optimisation may end up performing two reads instead
* of one, so skip it.
*/
if (!buffer_uptodate(bitmap_bh)) {
brelse(bitmap_bh);
goto make_io;
}
for (i = start; i < start + inodes_per_block; i++) {
if (i == inode_offset)
continue;
if (ext4_test_bit(i, bitmap_bh->b_data))
break;
}
brelse(bitmap_bh);
if (i == start + inodes_per_block) {
struct ext4_inode *raw_inode =
(struct ext4_inode *) (bh->b_data + iloc->offset);
/* all other inodes are free, so skip I/O */
memset(bh->b_data, 0, bh->b_size);
if (!ext4_test_inode_state(inode, EXT4_STATE_NEW))
ext4_fill_raw_inode(inode, raw_inode);
set_buffer_uptodate(bh);
unlock_buffer(bh);
goto has_buffer;
}
}
make_io:
/*
* If we need to do any I/O, try to pre-readahead extra
* blocks from the inode table.
*/
blk_start_plug(&plug);
if (EXT4_SB(sb)->s_inode_readahead_blks) {
ext4_fsblk_t b, end, table;
unsigned num;
__u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks;
table = ext4_inode_table(sb, gdp);
/* s_inode_readahead_blks is always a power of 2 */
b = block & ~((ext4_fsblk_t) ra_blks - 1);
if (table > b)
b = table;
end = b + ra_blks;
num = EXT4_INODES_PER_GROUP(sb);
if (ext4_has_group_desc_csum(sb))
num -= ext4_itable_unused_count(sb, gdp);
table += num / inodes_per_block;
if (end > table)
end = table;
while (b <= end)
ext4_sb_breadahead_unmovable(sb, b++);
}
/*
* There are other valid inodes in the buffer, this inode
* has in-inode xattrs, or we don't have this inode in memory.
* Read the block from disk.
*/
trace_ext4_load_inode(sb, ino);
ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL,
ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO));
blk_finish_plug(&plug);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
if (ret_block)
*ret_block = block;
brelse(bh);
return -EIO;
}
has_buffer:
iloc->bh = bh;
return 0;
}
static int __ext4_get_inode_loc_noinmem(struct inode *inode,
struct ext4_iloc *iloc)
{
ext4_fsblk_t err_blk = 0;
int ret;
ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc,
&err_blk);
if (ret == -EIO)
ext4_error_inode_block(inode, err_blk, EIO,
"unable to read itable block");
return ret;
}
int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
ext4_fsblk_t err_blk = 0;
int ret;
ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc,
&err_blk);
if (ret == -EIO)
ext4_error_inode_block(inode, err_blk, EIO,
"unable to read itable block");
return ret;
}
int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
struct ext4_iloc *iloc)
{
return __ext4_get_inode_loc(sb, ino, NULL, iloc, NULL);
}
static bool ext4_should_enable_dax(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (test_opt2(inode->i_sb, DAX_NEVER))
return false;
if (!S_ISREG(inode->i_mode))
return false;
if (ext4_should_journal_data(inode))
return false;
if (ext4_has_inline_data(inode))
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT))
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
return false;
if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
return false;
if (test_opt(inode->i_sb, DAX_ALWAYS))
return true;
return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
}
void ext4_set_inode_flags(struct inode *inode, bool init)
{
unsigned int flags = EXT4_I(inode)->i_flags;
unsigned int new_fl = 0;
WARN_ON_ONCE(IS_DAX(inode) && init);
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
if (flags & EXT4_APPEND_FL)
new_fl |= S_APPEND;
if (flags & EXT4_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & EXT4_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
/* Because of the way inode_set_flags() works we must preserve S_DAX
* here if already set. */
new_fl |= (inode->i_flags & S_DAX);
if (init && ext4_should_enable_dax(inode))
new_fl |= S_DAX;
if (flags & EXT4_ENCRYPT_FL)
new_fl |= S_ENCRYPTED;
if (flags & EXT4_CASEFOLD_FL)
new_fl |= S_CASEFOLD;
if (flags & EXT4_VERITY_FL)
new_fl |= S_VERITY;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
S_ENCRYPTED|S_CASEFOLD|S_VERITY);
}
static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
blkcnt_t i_blocks ;
struct inode *inode = &(ei->vfs_inode);
struct super_block *sb = inode->i_sb;
if (ext4_has_feature_huge_file(sb)) {
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) {
/* i_blocks represent file system block size */
return i_blocks << (inode->i_blkbits - 9);
} else {
return i_blocks;
}
} else {
return le32_to_cpu(raw_inode->i_blocks_lo);
}
}
static inline int ext4_iget_extra_inode(struct inode *inode,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
if (EXT4_INODE_HAS_XATTR_SPACE(inode) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
int err;
err = xattr_check_inode(inode, IHDR(inode, raw_inode),
ITAIL(inode, raw_inode));
if (err)
return err;
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
err = ext4_find_inline_data_nolock(inode);
if (!err && ext4_has_inline_data(inode))
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
return err;
} else
EXT4_I(inode)->i_inline_off = 0;
return 0;
}
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
{
if (!ext4_has_feature_project(inode->i_sb))
return -EOPNOTSUPP;
*projid = EXT4_I(inode)->i_projid;
return 0;
}
/*
* ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of
* refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag
* set.
*/
static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
{
if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
inode_set_iversion_raw(inode, val);
else
inode_set_iversion_queried(inode, val);
}
static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
const char *function, unsigned int line)
{
const char *err_str;
if (flags & EXT4_IGET_EA_INODE) {
if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
err_str = "missing EA_INODE flag";
goto error;
}
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
EXT4_I(inode)->i_file_acl) {
err_str = "ea_inode with extended attributes";
goto error;
}
} else {
if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
/*
* open_by_handle_at() could provide an old inode number
* that has since been reused for an ea_inode; this does
* not indicate filesystem corruption
*/
if (flags & EXT4_IGET_HANDLE)
return -ESTALE;
err_str = "unexpected EA_INODE flag";
goto error;
}
}
if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) {
err_str = "unexpected bad inode w/o EXT4_IGET_BAD";
goto error;
}
return 0;
error:
ext4_error_inode(inode, function, line, 0, err_str);
return -EFSCORRUPTED;
}
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ext4_iget_flags flags, const char *function,
unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
loff_t size;
int block;
uid_t i_uid;
gid_t i_gid;
projid_t i_projid;
if ((!(flags & EXT4_IGET_SPECIAL) &&
((ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) ||
ino == le32_to_cpu(es->s_usr_quota_inum) ||
ino == le32_to_cpu(es->s_grp_quota_inum) ||
ino == le32_to_cpu(es->s_prj_quota_inum) ||
ino == le32_to_cpu(es->s_orphan_file_inum))) ||
(ino < EXT4_ROOT_INO) ||
(ino > le32_to_cpu(es->s_inodes_count))) {
if (flags & EXT4_IGET_HANDLE)
return ERR_PTR(-ESTALE);
__ext4_error(sb, function, line, false, EFSCORRUPTED, 0,
"inode #%lu: comm %s: iget: illegal inode #",
ino, current->comm);
return ERR_PTR(-EFSCORRUPTED);
}
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW)) {
ret = check_igot_inode(inode, flags, function, line);
if (ret) {
iput(inode);
return ERR_PTR(ret);
}
return inode;
}
ei = EXT4_I(inode);
iloc.bh = NULL;
ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (ret < 0)
goto bad_inode;
raw_inode = ext4_raw_inode(&iloc);
if ((flags & EXT4_IGET_HANDLE) &&
(raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) {
ret = -ESTALE;
goto bad_inode;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb) ||
(ei->i_extra_isize & 3)) {
ext4_error_inode(inode, function, line, 0,
"iget: bad extra_isize %u "
"(inode size %u)",
ei->i_extra_isize,
EXT4_INODE_SIZE(inode->i_sb));
ret = -EFSCORRUPTED;
goto bad_inode;
}
} else
ei->i_extra_isize = 0;
/* Precompute checksum seed for inode metadata */
if (ext4_has_feature_metadata_csum(sb)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le32 inum = cpu_to_le32(inode->i_ino);
__le32 gen = raw_inode->i_generation;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
sizeof(inum));
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen,
sizeof(gen));
}
if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
(!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
ext4_error_inode_err(inode, function, line, 0,
EFSBADCRC, "iget: checksum invalid");
ret = -EFSBADCRC;
goto bad_inode;
}
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
if (ext4_has_feature_project(sb) &&
EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
else
i_projid = EXT4_DEF_PROJID;
if (!(test_opt(inode->i_sb, NO_UID32))) {
i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
i_uid_write(inode, i_uid);
i_gid_write(inode, i_gid);
ei->i_projid = make_kprojid(&init_user_ns, i_projid);
set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ei->i_inline_off = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
* This is needed because nfsd might try to access dead inodes
* the test is that same one that e2fsck uses
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
ino != EXT4_BOOT_LOADER_INO) {
/* this inode is deleted or unallocated */
if (flags & EXT4_IGET_SPECIAL) {
ext4_error_inode(inode, function, line, 0,
"iget: special inode unallocated");
ret = -EFSCORRUPTED;
} else
ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
* valid i_mode and are being read by the orphan
* recovery code: that's fine, we're about to complete
* the process of deleting those.
* OR it is the EXT4_BOOT_LOADER_INO which is
* not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
ext4_set_inode_flags(inode, true);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (ext4_has_feature_64bit(sb))
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(sb, raw_inode);
if ((size = i_size_read(inode)) < 0) {
ext4_error_inode(inode, function, line, 0,
"iget: bad i_size value: %lld", size);
ret = -EFSCORRUPTED;
goto bad_inode;
}
/*
* If dir_index is not enabled but there's dir with INDEX flag set,
* we'd normally treat htree data as empty space. But with metadata
* checksumming that corrupts checksums so forbid that.
*/
if (!ext4_has_feature_dir_index(sb) &&
ext4_has_feature_metadata_csum(sb) &&
ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
ext4_error_inode(inode, function, line, 0,
"iget: Dir with htree data on filesystem without dir_index feature.");
ret = -EFSCORRUPTED;
goto bad_inode;
}
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
/*
* NOTE! The in-memory inode i_data array is in little-endian order
* even on big-endian machines: we do NOT byteswap the block numbers!
*/
for (block = 0; block < EXT4_N_BLOCKS; block++)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
ext4_fc_init_inode(&ei->vfs_inode);
/*
* Set transaction id's of transactions that have to be committed
* to finish f[data]sync. We set them to currently running transaction
* as we cannot be sure that the inode or some of its metadata isn't
* part of the transaction - the inode could have been reclaimed and
* now it is reread from disk.
*/
if (journal) {
transaction_t *transaction;
tid_t tid;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
transaction = journal->j_running_transaction;
else
transaction = journal->j_committing_transaction;
if (transaction)
tid = transaction->t_tid;
else
tid = journal->j_commit_sequence;
read_unlock(&journal->j_state_lock);
ei->i_sync_tid = tid;
ei->i_datasync_tid = tid;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
BUILD_BUG_ON(sizeof(struct ext4_inode) & 3);
ei->i_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
} else {
ret = ext4_iget_extra_inode(inode, raw_inode, ei);
if (ret)
goto bad_inode;
}
}
EXT4_INODE_GET_CTIME(inode, raw_inode);
EXT4_INODE_GET_ATIME(inode, raw_inode);
EXT4_INODE_GET_MTIME(inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
u64 ivers = le32_to_cpu(raw_inode->i_disk_version);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
ivers |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
ext4_inode_set_iversion_queried(inode, ivers);
}
ret = 0;
if (ei->i_file_acl &&
!ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
ext4_error_inode(inode, function, line, 0,
"iget: bad extended attribute block %llu",
ei->i_file_acl);
ret = -EFSCORRUPTED;
goto bad_inode;
} else if (!ext4_has_inline_data(inode)) {
/* validate the block references in the inode */
if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode)))) {
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_check_inode(inode);
else
ret = ext4_ind_check_inode(inode);
}
}
if (ret)
goto bad_inode;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
/* VFS does not allow setting these so must be corruption */
if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
ext4_error_inode(inode, function, line, 0,
"iget: immutable or append flags "
"not allowed on symlinks");
ret = -EFSCORRUPTED;
goto bad_inode;
}
if (IS_ENCRYPTED(inode)) {
inode->i_op = &ext4_encrypted_symlink_inode_operations;
} else if (ext4_inode_is_fast_symlink(inode)) {
inode->i_op = &ext4_fast_symlink_inode_operations;
if (inode->i_size == 0 ||
inode->i_size >= sizeof(ei->i_data) ||
strnlen((char *)ei->i_data, inode->i_size + 1) !=
inode->i_size) {
ext4_error_inode(inode, function, line, 0,
"invalid fast symlink length %llu",
(unsigned long long)inode->i_size);
ret = -EFSCORRUPTED;
goto bad_inode;
}
inode_set_cached_link(inode, (char *)ei->i_data,
inode->i_size);
} else {
inode->i_op = &ext4_symlink_inode_operations;
}
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &ext4_special_inode_operations;
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else if (ino == EXT4_BOOT_LOADER_INO) {
make_bad_inode(inode);
} else {
ret = -EFSCORRUPTED;
ext4_error_inode(inode, function, line, 0,
"iget: bogus i_mode (%o)", inode->i_mode);
goto bad_inode;
}
if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) {
ext4_error_inode(inode, function, line, 0,
"casefold flag without casefold feature");
ret = -EFSCORRUPTED;
goto bad_inode;
}
ret = check_igot_inode(inode, flags, function, line);
/*
* -ESTALE here means there is nothing inherently wrong with the inode,
* it's just not an inode we can return for an fhandle lookup.
*/
if (ret == -ESTALE) {
brelse(iloc.bh);
unlock_new_inode(inode);
iput(inode);
return ERR_PTR(-ESTALE);
}
if (ret)
goto bad_inode;
brelse(iloc.bh);
unlock_new_inode(inode);
return inode;
bad_inode:
brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
static void __ext4_update_other_inode_time(struct super_block *sb,
unsigned long orig_ino,
unsigned long ino,
struct ext4_inode *raw_inode)
{
struct inode *inode;
inode = find_inode_by_ino_rcu(sb, ino);
if (!inode)
return;
if (!inode_is_dirtytime_only(inode))
return;
spin_lock(&inode->i_lock);
if (inode_is_dirtytime_only(inode)) {
struct ext4_inode_info *ei = EXT4_I(inode);
inode->i_state &= ~I_DIRTY_TIME;
spin_unlock(&inode->i_lock);
spin_lock(&ei->i_raw_lock);
EXT4_INODE_SET_CTIME(inode, raw_inode);
EXT4_INODE_SET_MTIME(inode, raw_inode);
EXT4_INODE_SET_ATIME(inode, raw_inode);
ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
trace_ext4_other_inode_update_time(inode, orig_ino);
return;
}
spin_unlock(&inode->i_lock);
}
/*
* Opportunistically update the other time fields for other inodes in
* the same inode table block.
*/
static void ext4_update_other_inodes_time(struct super_block *sb,
unsigned long orig_ino, char *buf)
{
unsigned long ino;
int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
int inode_size = EXT4_INODE_SIZE(sb);
/*
* Calculate the first inode in the inode table block. Inode
* numbers are one-based. That is, the first inode in a block
* (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
*/
ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
rcu_read_lock();
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
__ext4_update_other_inode_time(sb, orig_ino, ino,
(struct ext4_inode *)buf);
}
rcu_read_unlock();
}
/*
* Post the struct inode info into an on-disk inode location in the
* buffer-cache. This gobbles the caller's reference to the
* buffer_head in the inode location struct.
*
* The caller must have write access to iloc->bh.
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
struct super_block *sb = inode->i_sb;
int err;
int need_datasync = 0, set_large_file = 0;
spin_lock(&ei->i_raw_lock);
/*
* For fields not tracked in the in-memory inode, initialise them
* to zero for new inodes.
*/
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode))
need_datasync = 1;
if (ei->i_disksize > 0x7fffffffULL) {
if (!ext4_has_feature_large_file(sb) ||
EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV))
set_large_file = 1;
}
err = ext4_fill_raw_inode(inode, raw_inode);
spin_unlock(&ei->i_raw_lock);
if (err) {
EXT4_ERROR_INODE(inode, "corrupted inode contents");
goto out_brelse;
}
if (inode->i_sb->s_flags & SB_LAZYTIME)
ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
bh->b_data);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out_error;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
if (set_large_file) {
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
err = ext4_journal_get_write_access(handle, sb,
EXT4_SB(sb)->s_sbh,
EXT4_JTR_NONE);
if (err)
goto out_error;
lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
ext4_superblock_csum_set(sb);
unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
err = ext4_handle_dirty_metadata(handle, NULL,
EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_error:
ext4_std_error(inode->i_sb, err);
out_brelse:
brelse(bh);
return err;
}
/*
* ext4_write_inode()
*
* We are called from a few places:
*
* - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
* transaction to commit.
*
* - Within flush work (sys_sync(), kupdate and such).
* We wait on commit, if told to.
*
* - Within iput_final() -> write_inode_now()
* We wait on commit, if told to.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
* ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL
* writeback.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
* which we are interested.
*
* It would be a bug for them to not do this. The code:
*
* mark_inode_dirty(inode)
* stuff();
* inode->i_size = expr;
*
* is in error because write_inode() could occur while `stuff()' is running,
* and the new i_size will be lost. Plus the inode will no longer be on the
* superblock's dirty inode list.
*/
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
return 0;
err = ext4_emergency_state(inode->i_sb);
if (unlikely(err))
return err;
if (EXT4_SB(inode->i_sb)->s_journal) {
if (ext4_journal_current_handle()) {
ext4_debug("called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
/*
* No need to force transaction in WB_SYNC_NONE mode. Also
* ext4_sync_fs() will force the commit after everything is
* written.
*/
if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
return 0;
err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
EXT4_I(inode)->i_sync_tid);
} else {
struct ext4_iloc iloc;
err = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (err)
return err;
/*
* sync(2) will flush the whole buffer cache. No need to do
* it here separately for each inode.
*/
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO,
"IO error syncing inode");
err = -EIO;
}
brelse(iloc.bh);
}
return err;
}
/*
* In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate
* buffers that are attached to a folio straddling i_size and are undergoing
* commit. In that case we have to wait for commit to finish and try again.
*/
static void ext4_wait_for_tail_page_commit(struct inode *inode)
{
unsigned offset;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid;
int ret;
bool has_transaction;
offset = inode->i_size & (PAGE_SIZE - 1);
/*
* If the folio is fully truncated, we don't need to wait for any commit
* (and we even should not as __ext4_journalled_invalidate_folio() may
* strip all buffers from the folio but keep the folio dirty which can then
* confuse e.g. concurrent ext4_writepages() seeing dirty folio without
* buffers). Also we don't need to wait for any commit if all buffers in
* the folio remain valid. This is most beneficial for the common case of
* blocksize == PAGESIZE.
*/
if (!offset || offset > (PAGE_SIZE - i_blocksize(inode)))
return;
while (1) {
struct folio *folio = filemap_lock_folio(inode->i_mapping,
inode->i_size >> PAGE_SHIFT);
if (IS_ERR(folio))
return;
ret = __ext4_journalled_invalidate_folio(folio, offset,
folio_size(folio) - offset);
folio_unlock(folio);
folio_put(folio);
if (ret != -EBUSY)
return;
has_transaction = false;
read_lock(&journal->j_state_lock);
if (journal->j_committing_transaction) {
commit_tid = journal->j_committing_transaction->t_tid;
has_transaction = true;
}
read_unlock(&journal->j_state_lock);
if (has_transaction)
jbd2_log_wait_commit(journal, commit_tid);
}
}
/*
* ext4_setattr()
*
* Called from notify_change.
*
* We want to trap VFS attempts to truncate the file as soon as
* possible. In particular, we want to make sure that when the VFS
* shrinks i_size, we put the inode on the orphan list and modify
* i_disksize immediately, so that during the subsequent flushing of
* dirty pages and freeing of disk blocks, we can guarantee that any
* commit will leave the blocks being flushed in an unused state on
* disk. (On recovery, the inode will get truncated and the blocks will
* be freed, so we have a strong guarantee that no future commit will
* leave these blocks visible to the user.)
*
* Another thing we have to assure is that if we are in ordered mode
* and inode is still attached to the committing transaction, we must
* we start writeout of all the dirty pages which are being truncated.
* This way we are sure that all the data written in the previous
* transaction are already on disk (truncate waits for pages under
* writeback).
*
* Called with inode->i_rwsem down.
*/
int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int error, rc = 0;
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
bool inc_ivers = true;
error = ext4_emergency_state(inode->i_sb);
if (unlikely(error))
return error;
if (unlikely(IS_IMMUTABLE(inode)))
return -EPERM;
if (unlikely(IS_APPEND(inode) &&
(ia_valid & (ATTR_MODE | ATTR_UID |
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
error = setattr_prepare(idmap, dentry, attr);
if (error)
return error;
error = fscrypt_prepare_setattr(dentry, attr);
if (error)
return error;
error = fsverity_prepare_setattr(dentry, attr);
if (error)
return error;
if (is_quota_modification(idmap, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
if (i_uid_needs_update(idmap, attr, inode) ||
i_gid_needs_update(idmap, attr, inode)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
(EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) +
EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
}
/* dquot_transfer() calls back ext4_get_inode_usage() which
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
error = dquot_transfer(idmap, inode, attr);
up_read(&EXT4_I(inode)->xattr_sem);
if (error) {
ext4_journal_stop(handle);
return error;
}
/* Update corresponding info in inode so that everything is in
* one transaction */
i_uid_update(idmap, attr, inode);
i_gid_update(idmap, attr, inode);
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error)) {
return error;
}
}
if (attr->ia_valid & ATTR_SIZE) {
handle_t *handle;
loff_t oldsize = inode->i_size;
loff_t old_disksize;
int shrink = (attr->ia_size < inode->i_size);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (attr->ia_size > sbi->s_bitmap_maxbytes) {
return -EFBIG;
}
}
if (!S_ISREG(inode->i_mode)) {
return -EINVAL;
}
if (attr->ia_size == inode->i_size)
inc_ivers = false;
if (shrink) {
if (ext4_should_order_data(inode)) {
error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
if (error)
goto err_out;
}
/*
* Blocks are going to be removed from the inode. Wait
* for dio in flight.
*/
inode_dio_wait(inode);
}
filemap_invalidate_lock(inode->i_mapping);
rc = ext4_break_layouts(inode);
if (rc) {
filemap_invalidate_unlock(inode->i_mapping);
goto err_out;
}
if (attr->ia_size != inode->i_size) {
/* attach jbd2 jinode for EOF folio tail zeroing */
if (attr->ia_size & (inode->i_sb->s_blocksize - 1) ||
oldsize & (inode->i_sb->s_blocksize - 1)) {
error = ext4_inode_attach_jinode(inode);
if (error)
goto out_mmap_sem;
}
handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto out_mmap_sem;
}
if (ext4_handle_valid(handle) && shrink) {
error = ext4_orphan_add(handle, inode);
orphan = 1;
}
/*
* Update c/mtime and tail zero the EOF folio on
* truncate up. ext4_truncate() handles the shrink case
* below.
*/
if (!shrink) {
inode_set_mtime_to_ts(inode,
inode_set_ctime_current(inode));
if (oldsize & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle,
inode->i_mapping, oldsize);
}
if (shrink)
ext4_fc_track_range(handle, inode,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits,
EXT_MAX_BLOCKS - 1);
else
ext4_fc_track_range(
handle, inode,
(oldsize > 0 ? oldsize - 1 : oldsize) >>
inode->i_sb->s_blocksize_bits,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits);
down_write(&EXT4_I(inode)->i_data_sem);
old_disksize = EXT4_I(inode)->i_disksize;
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
error = rc;
/*
* We have to update i_size under i_data_sem together
* with i_disksize to avoid races with writeback code
* running ext4_wb_update_i_disksize().
*/
if (!error)
i_size_write(inode, attr->ia_size);
else
EXT4_I(inode)->i_disksize = old_disksize;
up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
if (error)
goto out_mmap_sem;
if (!shrink) {
pagecache_isize_extended(inode, oldsize,
inode->i_size);
} else if (ext4_should_journal_data(inode)) {
ext4_wait_for_tail_page_commit(inode);
}
}
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
truncate_pagecache(inode, inode->i_size);
/*
* Call ext4_truncate() even if i_size didn't change to
* truncate possible preallocated blocks.
*/
if (attr->ia_size <= oldsize) {
rc = ext4_truncate(inode);
if (rc)
error = rc;
}
out_mmap_sem:
filemap_invalidate_unlock(inode->i_mapping);
}
if (!error) {
if (inc_ivers)
inode_inc_iversion(inode);
setattr_copy(idmap, inode, attr);
mark_inode_dirty(inode);
}
/*
* If the call to ext4_truncate failed to get a transaction handle at
* all, we need to clean up the in-core orphan list manually.
*/
if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
if (!error && (ia_valid & ATTR_MODE))
rc = posix_acl_chmod(idmap, dentry, inode->i_mode);
err_out:
if (error)
ext4_std_error(inode->i_sb, error);
if (!error)
error = rc;
return error;
}
u32 ext4_dio_alignment(struct inode *inode)
{
if (fsverity_active(inode))
return 0;
if (ext4_should_journal_data(inode))
return 0;
if (ext4_has_inline_data(inode))
return 0;
if (IS_ENCRYPTED(inode)) {
if (!fscrypt_dio_supported(inode))
return 0;
return i_blocksize(inode);
}
return 1; /* use the iomap defaults */
}
int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
if ((request_mask & STATX_BTIME) &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = ei->i_crtime.tv_sec;
stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
}
/*
* Return the DIO alignment restrictions if requested. We only return
* this information when requested, since on encrypted files it might
* take a fair bit of work to get if the file wasn't opened recently.
*/
if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
u32 dio_align = ext4_dio_alignment(inode);
stat->result_mask |= STATX_DIOALIGN;
if (dio_align == 1) {
struct block_device *bdev = inode->i_sb->s_bdev;
/* iomap defaults */
stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
stat->dio_offset_align = bdev_logical_block_size(bdev);
} else {
stat->dio_mem_align = dio_align;
stat->dio_offset_align = dio_align;
}
}
if ((request_mask & STATX_WRITE_ATOMIC) && S_ISREG(inode->i_mode)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned int awu_min = 0, awu_max = 0;
if (ext4_inode_can_atomic_write(inode)) {
awu_min = sbi->s_awu_min;
awu_max = sbi->s_awu_max;
}
generic_fill_statx_atomic_writes(stat, awu_min, awu_max);
}
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
if (flags & EXT4_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (flags & EXT4_COMPR_FL)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (flags & EXT4_ENCRYPT_FL)
stat->attributes |= STATX_ATTR_ENCRYPTED;
if (flags & EXT4_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & EXT4_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
if (flags & EXT4_VERITY_FL)
stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_COMPRESSED |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
generic_fillattr(idmap, request_mask, inode, stat);
return 0;
}
int ext4_file_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
u64 delalloc_blocks;
ext4_getattr(idmap, path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
* have data blocks allocated (it may have an external xattr block).
* Report at least one sector for such files, so tools like tar, rsync,
* others don't incorrectly think the file is completely sparse.
*/
if (unlikely(ext4_has_inline_data(inode)))
stat->blocks += (stat->size + 511) >> 9;
/*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
* allocation is done, we will have i_blocks inconsistent with
* on-disk file blocks.
* We always keep i_blocks updated together with real
* allocation. But to not confuse with user, stat
* will return the blocks that include the delayed allocation
* blocks for this file.
*/
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
EXT4_I(inode)->i_reserved_data_blocks);
stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9);
return 0;
}
static int ext4_index_trans_blocks(struct inode *inode, int lblocks,
int pextents)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_ind_trans_blocks(inode, lblocks);
return ext4_ext_index_trans_blocks(inode, pextents);
}
/*
* Account for index blocks, block groups bitmaps and block group
* descriptor blocks if modify datablocks and index blocks
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
* different block groups too. If they are contiguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
*/
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
int idxblocks;
int ret;
/*
* How many index blocks need to touch to map @lblocks logical blocks
* to @pextents physical extents?
*/
idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents);
ret = idxblocks;
/*
* Now let's see how many group bitmaps and group descriptors need
* to account
*/
groups = idxblocks + pextents;
gdpblocks = groups;
if (groups > ngroups)
groups = ngroups;
if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
/* bitmaps and block group descriptor blocks */
ret += groups + gdpblocks;
/* Blocks for super block, inode, quota and xattr blocks */
ret += EXT4_META_TRANS_BLOCKS(inode->i_sb);
return ret;
}
/*
* Calculate the total number of credits to reserve to fit
* the modification of a single pages into a single transaction,
* which may include multiple chunks of block allocations.
*
* This could be called via ext4_write_begin()
*
* We need to consider the worse case, when
* one new block per extent.
*/
int ext4_writepage_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
int ret;
ret = ext4_meta_trans_blocks(inode, bpp, bpp);
/* Account for data blocks for journalled mode */
if (ext4_should_journal_data(inode))
ret += bpp;
return ret;
}
/*
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
* ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
*/
int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
{
return ext4_meta_trans_blocks(inode, nrblocks, 1);
}
/*
* The caller must have previously called ext4_reserve_inode_write().
* Give this, we know that the caller already has write access to iloc->bh.
*/
int ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode, struct ext4_iloc *iloc)
{
int err = 0;
err = ext4_emergency_state(inode->i_sb);
if (unlikely(err)) {
put_bh(iloc->bh);
return err;
}
ext4_fc_track_inode(handle, inode);
/* the do_update_inode consumes one bh->b_count */
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
err = ext4_do_update_inode(handle, inode, iloc);
put_bh(iloc->bh);
return err;
}
/*
* On success, We end up with an outstanding reference count against
* iloc->bh. This _must_ be cleaned up later.
*/
int
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
int err;
err = ext4_emergency_state(inode->i_sb);
if (unlikely(err))
return err;
err = ext4_get_inode_loc(inode, iloc);
if (!err) {
BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, inode->i_sb,
iloc->bh, EXT4_JTR_NONE);
if (err) {
brelse(iloc->bh);
iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
return err;
}
static int __ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc *iloc,
handle_t *handle, int *no_expand)
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
int error;
/* this was checked at iget time, but double check for good measure */
if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) ||
(ei->i_extra_isize & 3)) {
EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)",
ei->i_extra_isize,
EXT4_INODE_SIZE(inode->i_sb));
return -EFSCORRUPTED;
}
if ((new_extra_isize < ei->i_extra_isize) ||
(new_extra_isize < 4) ||
(new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE))
return -EINVAL; /* Should never happen */
raw_inode = ext4_raw_inode(iloc);
header = IHDR(inode, raw_inode);
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize, 0,
new_extra_isize - EXT4_I(inode)->i_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
return 0;
}
/*
* We may need to allocate external xattr block so we need quotas
* initialized. Here we can be called with various locks held so we
* cannot affort to initialize quotas ourselves. So just bail.
*/
if (dquot_initialize_needed(inode))
return -EAGAIN;
/* try to expand with EAs present */
error = ext4_expand_extra_isize_ea(inode, new_extra_isize,
raw_inode, handle);
if (error) {
/*
* Inode size expansion failed; don't try again
*/
*no_expand = 1;
}
return error;
}
/*
* Expand an inode by new_extra_isize bytes.
* Returns 0 on success or negative error number on failure.
*/
static int ext4_try_to_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc iloc,
handle_t *handle)
{
int no_expand;
int error;
if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND))
return -EOVERFLOW;
/*
* In nojournal mode, we can immediately attempt to expand
* the inode. When journaled, we first need to obtain extra
* buffer credits since we may write into the EA block
* with this same handle. If journal_extend fails, then it will
* only result in a minor loss of functionality for that inode.
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
if (ext4_journal_extend(handle,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0)
return -ENOSPC;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
return -EBUSY;
error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc,
handle, &no_expand);
ext4_write_unlock_xattr(inode, &no_expand);
return error;
}
int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc *iloc)
{
handle_t *handle;
int no_expand;
int error, rc;
if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
brelse(iloc->bh);
return -EOVERFLOW;
}
handle = ext4_journal_start(inode, EXT4_HT_INODE,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
brelse(iloc->bh);
return error;
}
ext4_write_lock_xattr(inode, &no_expand);
BUFFER_TRACE(iloc->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, inode->i_sb, iloc->bh,
EXT4_JTR_NONE);
if (error) {
brelse(iloc->bh);
goto out_unlock;
}
error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc,
handle, &no_expand);
rc = ext4_mark_iloc_dirty(handle, inode, iloc);
if (!error)
error = rc;
out_unlock:
ext4_write_unlock_xattr(inode, &no_expand);
ext4_journal_stop(handle);
return error;
}
/*
* What we do here is to mark the in-core inode as clean with respect to inode
* dirtiness (it may still be data-dirty).
* This means that the in-core inode may be reaped by prune_icache
* without having to perform any I/O. This is a very good thing,
* because *any* task may call prune_icache - even ones which
* have a transaction open against a different journal.
*
* Is this cheating? Not really. Sure, we haven't written the
* inode out, but prune_icache isn't a user-visible syncing function.
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
*/
int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
const char *func, unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err;
might_sleep();
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out;
if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
iloc, handle);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
out:
if (unlikely(err))
ext4_error_inode_err(inode, func, line, 0, err,
"mark_inode_dirty error");
return err;
}
/*
* ext4_dirty_inode() is called from __mark_inode_dirty()
*
* We're really interested in the case where a file is being extended.
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
* Also, dquot_alloc_block() will always dirty the inode when blocks
* are allocated to the file.
*
* If the inode is marked synchronous, we don't honour that here - doing
* so would cause a commit on atime updates, which we don't bother doing.
* We handle synchronous inodes at the highest possible level.
*/
void ext4_dirty_inode(struct inode *inode, int flags)
{
handle_t *handle;
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle))
return;
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
}
int ext4_change_inode_journal_flag(struct inode *inode, int val)
{
journal_t *journal;
handle_t *handle;
int err;
int alloc_ctx;
/*
* We have to be very careful here: changing a data block's
* journaling status dynamically is dangerous. If we write a
* data block to the journal, change the status and then delete
* that block, we risk forgetting to revoke the old log record
* from the journal and so a subsequent replay can corrupt data.
* So, first we make sure that the journal is empty and that
* nobody is changing anything.
*/
journal = EXT4_JOURNAL(inode);
if (!journal)
return 0;
if (is_journal_aborted(journal))
return -EROFS;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
/*
* Before flushing the journal and switching inode's aops, we have
* to flush all dirty data the inode has. There can be outstanding
* delayed allocations, there can be unwritten extents created by
* fallocate or buffered writes in dioread_nolock mode covered by
* dirty data which can be converted only after flushing the dirty
* data (and journalled aops don't know how to handle these cases).
*/
if (val) {
filemap_invalidate_lock(inode->i_mapping);
err = filemap_write_and_wait(inode->i_mapping);
if (err < 0) {
filemap_invalidate_unlock(inode->i_mapping);
return err;
}
}
alloc_ctx = ext4_writepages_down_write(inode->i_sb);
jbd2_journal_lock_updates(journal);
/*
* OK, there are no updates running now, and all cached data is
* synced to disk. We are now in a completely consistent state
* which doesn't have anything in the journal, and we know that
* no filesystem updates are running, so it is safe to modify
* the inode's in-core data-journaling state flag now.
*/
if (val)
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else {
err = jbd2_journal_flush(journal, 0);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
ext4_writepages_up_write(inode->i_sb, alloc_ctx);
return err;
}
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
}
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
ext4_writepages_up_write(inode->i_sb, alloc_ctx);
if (val)
filemap_invalidate_unlock(inode->i_mapping);
/* Finally we can mark the inode as dirty. */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_fc_mark_ineligible(inode->i_sb,
EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
return err;
}
static int ext4_bh_unmapped(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
return !buffer_mapped(bh);
}
vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio = page_folio(vmf->page);
loff_t size;
unsigned long len;
int err;
vm_fault_t ret;
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
handle_t *handle;
get_block_t *get_block;
int retries = 0;
if (unlikely(IS_IMMUTABLE(inode)))
return VM_FAULT_SIGBUS;
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
filemap_invalidate_lock_shared(mapping);
err = ext4_convert_inline_data(inode);
if (err)
goto out_ret;
/*
* On data journalling we skip straight to the transaction handle:
* there's no delalloc; page truncated will be checked later; the
* early return w/ all buffers mapped (calculates size/len) can't
* be used; and there's no dioread_nolock, so only ext4_get_block.
*/
if (ext4_should_journal_data(inode))
goto retry_alloc;
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_nonda_switch(inode->i_sb)) {
do {
err = block_page_mkwrite(vma, vmf,
ext4_da_get_block_prep);
} while (err == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries));
goto out_ret;
}
folio_lock(folio);
size = i_size_read(inode);
/* Page got truncated from under us? */
if (folio->mapping != mapping || folio_pos(folio) > size) {
folio_unlock(folio);
ret = VM_FAULT_NOPAGE;
goto out;
}
len = folio_size(folio);
if (folio_pos(folio) + len > size)
len = size - folio_pos(folio);
/*
* Return if we have all the buffers mapped. This avoids the need to do
* journal_start/journal_stop which can block and take a long time
*
* This cannot be done for data journalling, as we have to add the
* inode to the transaction's list to writeprotect pages on commit.
*/
if (folio_buffers(folio)) {
if (!ext4_walk_page_buffers(NULL, inode, folio_buffers(folio),
0, len, NULL,
ext4_bh_unmapped)) {
/* Wait so that we don't change page under IO */
folio_wait_stable(folio);
ret = VM_FAULT_LOCKED;
goto out;
}
}
folio_unlock(folio);
/* OK, we need to fill the hole... */
if (ext4_should_dioread_nolock(inode))
get_block = ext4_get_block_unwritten;
else
get_block = ext4_get_block;
retry_alloc:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
goto out;
}
/*
* Data journalling can't use block_page_mkwrite() because it
* will set_buffer_dirty() before do_journal_get_write_access()
* thus might hit warning messages for dirty metadata buffers.
*/
if (!ext4_should_journal_data(inode)) {
err = block_page_mkwrite(vma, vmf, get_block);
} else {
folio_lock(folio);
size = i_size_read(inode);
/* Page got truncated from under us? */
if (folio->mapping != mapping || folio_pos(folio) > size) {
ret = VM_FAULT_NOPAGE;
goto out_error;
}
len = folio_size(folio);
if (folio_pos(folio) + len > size)
len = size - folio_pos(folio);
err = ext4_block_write_begin(handle, folio, 0, len,
ext4_get_block);
if (!err) {
ret = VM_FAULT_SIGBUS;
if (ext4_journal_folio_buffers(handle, folio, len))
goto out_error;
} else {
folio_unlock(folio);
}
}
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_alloc;
out_ret:
ret = vmf_fs_error(err);
out:
filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(inode->i_sb);
return ret;
out_error:
folio_unlock(folio);
ext4_journal_stop(handle);
goto out;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Simple NUMA memory policy for the Linux kernel.
*
* Copyright 2003,2004 Andi Kleen, SuSE Labs.
* (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
*
* NUMA policy allows the user to give hints in which node(s) memory should
* be allocated.
*
* Support six policies per VMA and per process:
*
* The VMA policy has priority over the process policy for a page fault.
*
* interleave Allocate memory interleaved over a set of nodes,
* with normal fallback if it fails.
* For VMA based allocations this interleaves based on the
* offset into the backing object or offset into the mapping
* for anonymous memory. For process policy an process counter
* is used.
*
* weighted interleave
* Allocate memory interleaved over a set of nodes based on
* a set of weights (per-node), with normal fallback if it
* fails. Otherwise operates the same as interleave.
* Example: nodeset(0,1) & weights (2,1) - 2 pages allocated
* on node 0 for every 1 page allocated on node 1.
*
* bind Only allocate memory on a specific set of nodes,
* no fallback.
* FIXME: memory is allocated starting with the first node
* to the last. It would be better if bind would truly restrict
* the allocation to memory nodes instead
*
* preferred Try a specific node first before normal fallback.
* As a special case NUMA_NO_NODE here means do the allocation
* on the local CPU. This is normally identical to default,
* but useful to set in a VMA when you have a non default
* process policy.
*
* preferred many Try a set of nodes first before normal fallback. This is
* similar to preferred without the special case.
*
* default Allocate on the local node first, or when on a VMA
* use the process policy. This is what Linux always did
* in a NUMA aware kernel and still does by, ahem, default.
*
* The process policy is applied for most non interrupt memory allocations
* in that process' context. Interrupts ignore the policies and always
* try to allocate on the local CPU. The VMA policy is only applied for memory
* allocations for a VMA in the VM.
*
* Currently there are a few corner cases in swapping where the policy
* is not applied, but the majority should be handled. When process policy
* is used it is not remembered over swap outs/swap ins.
*
* Only the highest zone in the zone hierarchy gets policied. Allocations
* requesting a lower zone just use default policy. This implies that
* on systems with highmem kernel lowmem allocation don't get policied.
* Same with GFP_DMA allocations.
*
* For shmem/tmpfs shared memory the policy is shared between
* all users and remembered even when nobody has memory mapped.
*/
/* Notebook:
fix mmap readahead to honour policy and enable policy for any page cache
object
statistics for bigpages
global policy for page cache? currently it uses process policy. Requires
first item above.
handle mremap for shared memory (currently ignored for the policy)
grows down?
make bind policy root only? It can trigger oom much faster and the
kernel is not always grateful with that.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mempolicy.h>
#include <linux/pagewalk.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/task.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/ptrace.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/migrate.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/printk.h>
#include <linux/swapops.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <linux/uaccess.h>
#include "internal.h"
/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */
#define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */
static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;
/* Highest zone. An specific allocation for a zone below that is not
policied. */
enum zone_type policy_zone = 0;
/*
* run-time system-wide default policy => local allocation
*/
static struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
.mode = MPOL_LOCAL,
};
static struct mempolicy preferred_node_policy[MAX_NUMNODES];
/*
* iw_table is the sysfs-set interleave weight table, a value of 0 denotes
* system-default value should be used. A NULL iw_table also denotes that
* system-default values should be used. Until the system-default table
* is implemented, the system-default is always 1.
*
* iw_table is RCU protected
*/
static u8 __rcu *iw_table;
static DEFINE_MUTEX(iw_table_lock);
static u8 get_il_weight(int node)
{
u8 *table;
u8 weight;
rcu_read_lock();
table = rcu_dereference(iw_table);
/* if no iw_table, use system default */
weight = table ? table[node] : 1;
/* if value in iw_table is 0, use system default */
weight = weight ? weight : 1;
rcu_read_unlock();
return weight;
}
/**
* numa_nearest_node - Find nearest node by state
* @node: Node id to start the search
* @state: State to filter the search
*
* Lookup the closest node by distance if @nid is not in state.
*
* Return: this @node if it is in state, otherwise the closest node by distance
*/
int numa_nearest_node(int node, unsigned int state)
{
int min_dist = INT_MAX, dist, n, min_node;
if (state >= NR_NODE_STATES)
return -EINVAL;
if (node == NUMA_NO_NODE || node_state(node, state))
return node;
min_node = node;
for_each_node_state(n, state) {
dist = node_distance(node, n);
if (dist < min_dist) {
min_dist = dist;
min_node = n;
}
}
return min_node;
}
EXPORT_SYMBOL_GPL(numa_nearest_node);
/**
* nearest_node_nodemask - Find the node in @mask at the nearest distance
* from @node.
*
* @node: a valid node ID to start the search from.
* @mask: a pointer to a nodemask representing the allowed nodes.
*
* This function iterates over all nodes in @mask and calculates the
* distance from the starting @node, then it returns the node ID that is
* the closest to @node, or MAX_NUMNODES if no node is found.
*
* Note that @node must be a valid node ID usable with node_distance(),
* providing an invalid node ID (e.g., NUMA_NO_NODE) may result in crashes
* or unexpected behavior.
*/
int nearest_node_nodemask(int node, nodemask_t *mask)
{
int dist, n, min_dist = INT_MAX, min_node = MAX_NUMNODES;
for_each_node_mask(n, *mask) {
dist = node_distance(node, n);
if (dist < min_dist) {
min_dist = dist;
min_node = n;
}
}
return min_node;
}
EXPORT_SYMBOL_GPL(nearest_node_nodemask);
struct mempolicy *get_task_policy(struct task_struct *p)
{
struct mempolicy *pol = p->mempolicy;
int node;
if (pol)
return pol;
node = numa_node_id();
if (node != NUMA_NO_NODE) {
pol = &preferred_node_policy[node];
/* preferred_node_policy is not initialised early in boot */
if (pol->mode)
return pol;
}
return &default_policy;
}
static const struct mempolicy_operations {
int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
} mpol_ops[MPOL_MAX];
static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
return pol->flags & MPOL_MODE_FLAGS;
}
static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
const nodemask_t *rel)
{
nodemask_t tmp;
nodes_fold(tmp, *orig, nodes_weight(*rel));
nodes_onto(*ret, tmp, *rel);
}
static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
{
if (nodes_empty(*nodes))
return -EINVAL;
pol->nodes = *nodes;
return 0;
}
static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
{
if (nodes_empty(*nodes))
return -EINVAL;
nodes_clear(pol->nodes);
node_set(first_node(*nodes), pol->nodes);
return 0;
}
/*
* mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
* any, for the new policy. mpol_new() has already validated the nodes
* parameter with respect to the policy mode and flags.
*
* Must be called holding task's alloc_lock to protect task's mems_allowed
* and mempolicy. May also be called holding the mmap_lock for write.
*/
static int mpol_set_nodemask(struct mempolicy *pol,
const nodemask_t *nodes, struct nodemask_scratch *nsc)
{
int ret;
/*
* Default (pol==NULL) resp. local memory policies are not a
* subject of any remapping. They also do not need any special
* constructor.
*/
if (!pol || pol->mode == MPOL_LOCAL)
return 0;
/* Check N_MEMORY */
nodes_and(nsc->mask1,
cpuset_current_mems_allowed, node_states[N_MEMORY]);
VM_BUG_ON(!nodes);
if (pol->flags & MPOL_F_RELATIVE_NODES)
mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1);
else
nodes_and(nsc->mask2, *nodes, nsc->mask1);
if (mpol_store_user_nodemask(pol))
pol->w.user_nodemask = *nodes;
else
pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed;
ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
return ret;
}
/*
* This function just creates a new policy, does some check and simple
* initialization. You must invoke mpol_set_nodemask() to set nodes.
*/
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
struct mempolicy *policy;
if (mode == MPOL_DEFAULT) {
if (nodes && !nodes_empty(*nodes))
return ERR_PTR(-EINVAL);
return NULL;
}
VM_BUG_ON(!nodes);
/*
* MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
* MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
* All other modes require a valid pointer to a non-empty nodemask.
*/
if (mode == MPOL_PREFERRED) {
if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) ||
(flags & MPOL_F_RELATIVE_NODES)))
return ERR_PTR(-EINVAL);
mode = MPOL_LOCAL;
}
} else if (mode == MPOL_LOCAL) {
if (!nodes_empty(*nodes) ||
(flags & MPOL_F_STATIC_NODES) ||
(flags & MPOL_F_RELATIVE_NODES))
return ERR_PTR(-EINVAL);
} else if (nodes_empty(*nodes))
return ERR_PTR(-EINVAL);
policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!policy)
return ERR_PTR(-ENOMEM);
atomic_set(&policy->refcnt, 1);
policy->mode = mode;
policy->flags = flags;
policy->home_node = NUMA_NO_NODE;
return policy;
}
/* Slow path of a mpol destructor. */
void __mpol_put(struct mempolicy *pol)
{
if (!atomic_dec_and_test(&pol->refcnt))
return;
kmem_cache_free(policy_cache, pol);
}
static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
{
}
static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
{
nodemask_t tmp;
if (pol->flags & MPOL_F_STATIC_NODES)
nodes_and(tmp, pol->w.user_nodemask, *nodes);
else if (pol->flags & MPOL_F_RELATIVE_NODES)
mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
else {
nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed,
*nodes);
pol->w.cpuset_mems_allowed = *nodes;
}
if (nodes_empty(tmp))
tmp = *nodes;
pol->nodes = tmp;
}
static void mpol_rebind_preferred(struct mempolicy *pol,
const nodemask_t *nodes)
{
pol->w.cpuset_mems_allowed = *nodes;
}
/*
* mpol_rebind_policy - Migrate a policy to a different set of nodes
*
* Per-vma policies are protected by mmap_lock. Allocations using per-task
* policies are protected by task->mems_allowed_seq to prevent a premature
* OOM/allocation failure due to parallel nodemask modification.
*/
static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
{
if (!pol || pol->mode == MPOL_LOCAL)
return;
if (!mpol_store_user_nodemask(pol) &&
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
return;
mpol_ops[pol->mode].rebind(pol, newmask);
}
/*
* Wrapper for mpol_rebind_policy() that just requires task
* pointer, and updates task mempolicy.
*
* Called with task's alloc_lock held.
*/
void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
{
mpol_rebind_policy(tsk->mempolicy, new);
}
/*
* Rebind each vma in mm to new nodemask.
*
* Call holding a reference to mm. Takes mm->mmap_lock during call.
*/
void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, 0);
mmap_write_lock(mm);
for_each_vma(vmi, vma) {
vma_start_write(vma);
mpol_rebind_policy(vma->vm_policy, new);
}
mmap_write_unlock(mm);
}
static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
[MPOL_DEFAULT] = {
.rebind = mpol_rebind_default,
},
[MPOL_INTERLEAVE] = {
.create = mpol_new_nodemask,
.rebind = mpol_rebind_nodemask,
},
[MPOL_PREFERRED] = {
.create = mpol_new_preferred,
.rebind = mpol_rebind_preferred,
},
[MPOL_BIND] = {
.create = mpol_new_nodemask,
.rebind = mpol_rebind_nodemask,
},
[MPOL_LOCAL] = {
.rebind = mpol_rebind_default,
},
[MPOL_PREFERRED_MANY] = {
.create = mpol_new_nodemask,
.rebind = mpol_rebind_preferred,
},
[MPOL_WEIGHTED_INTERLEAVE] = {
.create = mpol_new_nodemask,
.rebind = mpol_rebind_nodemask,
},
};
static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags);
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol,
pgoff_t ilx, int *nid);
static bool strictly_unmovable(unsigned long flags)
{
/*
* STRICT without MOVE flags lets do_mbind() fail immediately with -EIO
* if any misplaced page is found.
*/
return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ==
MPOL_MF_STRICT;
}
struct migration_mpol { /* for alloc_migration_target_by_mpol() */
struct mempolicy *pol;
pgoff_t ilx;
};
struct queue_pages {
struct list_head *pagelist;
unsigned long flags;
nodemask_t *nmask;
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
struct folio *large; /* note last large folio encountered */
long nr_failed; /* could not be isolated at this time */
};
/*
* Check if the folio's nid is in qp->nmask.
*
* If MPOL_MF_INVERT is set in qp->flags, check if the nid is
* in the invert of qp->nmask.
*/
static inline bool queue_folio_required(struct folio *folio,
struct queue_pages *qp)
{
int nid = folio_nid(folio);
unsigned long flags = qp->flags;
return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
}
static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk)
{
struct folio *folio;
struct queue_pages *qp = walk->private;
if (unlikely(is_pmd_migration_entry(*pmd))) {
qp->nr_failed++;
return;
}
folio = pmd_folio(*pmd);
if (is_huge_zero_folio(folio)) {
walk->action = ACTION_CONTINUE;
return;
}
if (!queue_folio_required(folio, qp))
return;
if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ||
!vma_migratable(walk->vma) ||
!migrate_folio_add(folio, qp->pagelist, qp->flags))
qp->nr_failed++;
}
/*
* Scan through folios, checking if they satisfy the required conditions,
* moving them from LRU to local pagelist for migration if they do (or not).
*
* queue_folios_pte_range() has two possible return values:
* 0 - continue walking to scan for more, even if an existing folio on the
* wrong node could not be isolated and queued for migration.
* -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL,
* and an existing folio was on a node that does not follow the policy.
*/
static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
queue_folios_pmd(pmd, walk);
spin_unlock(ptl);
goto out;
}
mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
if (!pte) {
walk->action = ACTION_AGAIN;
return 0;
}
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = ptep_get(pte);
if (pte_none(ptent))
continue;
if (!pte_present(ptent)) {
if (is_migration_entry(pte_to_swp_entry(ptent)))
qp->nr_failed++;
continue;
}
folio = vm_normal_folio(vma, addr, ptent);
if (!folio || folio_is_zone_device(folio))
continue;
/*
* vm_normal_folio() filters out zero pages, but there might
* still be reserved folios to skip, perhaps in a VDSO.
*/
if (folio_test_reserved(folio))
continue;
if (!queue_folio_required(folio, qp))
continue;
if (folio_test_large(folio)) {
/*
* A large folio can only be isolated from LRU once,
* but may be mapped by many PTEs (and Copy-On-Write may
* intersperse PTEs of other, order 0, folios). This is
* a common case, so don't mistake it for failure (but
* there can be other cases of multi-mapped pages which
* this quick check does not help to filter out - and a
* search of the pagelist might grow to be prohibitive).
*
* migrate_pages(&pagelist) returns nr_failed folios, so
* check "large" now so that queue_pages_range() returns
* a comparable nr_failed folios. This does imply that
* if folio could not be isolated for some racy reason
* at its first PTE, later PTEs will not give it another
* chance of isolation; but keeps the accounting simple.
*/
if (folio == qp->large)
continue;
qp->large = folio;
}
if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ||
!vma_migratable(vma) ||
!migrate_folio_add(folio, qp->pagelist, flags)) {
qp->nr_failed++;
if (strictly_unmovable(flags))
break;
}
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
out:
if (qp->nr_failed && strictly_unmovable(flags))
return -EIO;
return 0;
}
static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
struct folio *folio;
spinlock_t *ptl;
pte_t entry;
ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
entry = huge_ptep_get(walk->mm, addr, pte);
if (!pte_present(entry)) {
if (unlikely(is_hugetlb_entry_migration(entry)))
qp->nr_failed++;
goto unlock;
}
folio = pfn_folio(pte_pfn(entry));
if (!queue_folio_required(folio, qp))
goto unlock;
if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ||
!vma_migratable(walk->vma)) {
qp->nr_failed++;
goto unlock;
}
/*
* Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio.
* Choosing not to migrate a shared folio is not counted as a failure.
*
* See folio_maybe_mapped_shared() on possible imprecision when we
* cannot easily detect if a folio is shared.
*/
if ((flags & MPOL_MF_MOVE_ALL) ||
(!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(pte)))
if (!folio_isolate_hugetlb(folio, qp->pagelist))
qp->nr_failed++;
unlock:
spin_unlock(ptl);
if (qp->nr_failed && strictly_unmovable(flags))
return -EIO;
#endif
return 0;
}
#ifdef CONFIG_NUMA_BALANCING
/*
* This is used to mark a range of virtual addresses to be inaccessible.
* These are later cleared by a NUMA hinting fault. Depending on these
* faults, pages may be migrated for better NUMA placement.
*
* This is assuming that NUMA faults are handled using PROT_NONE. If
* an architecture makes a different choice, it will need further
* changes to the core.
*/
unsigned long change_prot_numa(struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
struct mmu_gather tlb;
long nr_updated;
tlb_gather_mmu(&tlb, vma->vm_mm);
nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA);
if (nr_updated > 0) {
count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated);
}
tlb_finish_mmu(&tlb);
return nr_updated;
}
#endif /* CONFIG_NUMA_BALANCING */
static int queue_pages_test_walk(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *next, *vma = walk->vma;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
/* range check first */
VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma);
if (!qp->first) {
qp->first = vma;
if (!(flags & MPOL_MF_DISCONTIG_OK) &&
(qp->start < vma->vm_start))
/* hole at head side of range */
return -EFAULT;
}
next = find_vma(vma->vm_mm, vma->vm_end);
if (!(flags & MPOL_MF_DISCONTIG_OK) &&
((vma->vm_end < qp->end) &&
(!next || vma->vm_end < next->vm_start)))
/* hole at middle or tail of range */
return -EFAULT;
/*
* Need check MPOL_MF_STRICT to return -EIO if possible
* regardless of vma_migratable
*/
if (!vma_migratable(vma) &&
!(flags & MPOL_MF_STRICT))
return 1;
/*
* Check page nodes, and queue pages to move, in the current vma.
* But if no moving, and no strict checking, the scan can be skipped.
*/
if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
return 0;
return 1;
}
static const struct mm_walk_ops queue_pages_walk_ops = {
.hugetlb_entry = queue_folios_hugetlb,
.pmd_entry = queue_folios_pte_range,
.test_walk = queue_pages_test_walk,
.walk_lock = PGWALK_RDLOCK,
};
static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = {
.hugetlb_entry = queue_folios_hugetlb,
.pmd_entry = queue_folios_pte_range,
.test_walk = queue_pages_test_walk,
.walk_lock = PGWALK_WRLOCK,
};
/*
* Walk through page tables and collect pages to be migrated.
*
* If pages found in a given range are not on the required set of @nodes,
* and migration is allowed, they are isolated and queued to @pagelist.
*
* queue_pages_range() may return:
* 0 - all pages already on the right node, or successfully queued for moving
* (or neither strict checking nor moving requested: only range checking).
* >0 - this number of misplaced folios could not be queued for moving
* (a hugetlbfs page or a transparent huge page being counted as 1).
* -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs.
* -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified.
*/
static long
queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
nodemask_t *nodes, unsigned long flags,
struct list_head *pagelist)
{
int err;
struct queue_pages qp = {
.pagelist = pagelist,
.flags = flags,
.nmask = nodes,
.start = start,
.end = end,
.first = NULL,
};
const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
return err ? : qp.nr_failed;
}
/*
* Apply policy to a single VMA
* This must be called with the mmap_lock held for writing.
*/
static int vma_replace_policy(struct vm_area_struct *vma,
struct mempolicy *pol)
{
int err;
struct mempolicy *old;
struct mempolicy *new;
vma_assert_write_locked(vma);
new = mpol_dup(pol);
if (IS_ERR(new))
return PTR_ERR(new);
if (vma->vm_ops && vma->vm_ops->set_policy) {
err = vma->vm_ops->set_policy(vma, new);
if (err)
goto err_out;
}
old = vma->vm_policy;
vma->vm_policy = new; /* protected by mmap_lock */
mpol_put(old);
return 0;
err_out:
mpol_put(new);
return err;
}
/* Split or merge the VMA (if required) and apply the new policy */
static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
unsigned long end, struct mempolicy *new_pol)
{
unsigned long vmstart, vmend;
vmend = min(end, vma->vm_end);
if (start > vma->vm_start) {
*prev = vma;
vmstart = start;
} else {
vmstart = vma->vm_start;
}
if (mpol_equal(vma->vm_policy, new_pol)) {
*prev = vma;
return 0;
}
vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol);
if (IS_ERR(vma))
return PTR_ERR(vma);
*prev = vma;
return vma_replace_policy(vma, new_pol);
}
/* Set the process memory policy */
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
struct mempolicy *new, *old;
NODEMASK_SCRATCH(scratch);
int ret;
if (!scratch)
return -ENOMEM;
new = mpol_new(mode, flags, nodes);
if (IS_ERR(new)) {
ret = PTR_ERR(new);
goto out;
}
task_lock(current);
ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
task_unlock(current);
mpol_put(new);
goto out;
}
old = current->mempolicy;
current->mempolicy = new;
if (new && (new->mode == MPOL_INTERLEAVE ||
new->mode == MPOL_WEIGHTED_INTERLEAVE)) {
current->il_prev = MAX_NUMNODES-1;
current->il_weight = 0;
}
task_unlock(current);
mpol_put(old);
ret = 0;
out:
NODEMASK_SCRATCH_FREE(scratch);
return ret;
}
/*
* Return nodemask for policy for get_mempolicy() query
*
* Called with task's alloc_lock held
*/
static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes)
{
nodes_clear(*nodes);
if (pol == &default_policy)
return;
switch (pol->mode) {
case MPOL_BIND:
case MPOL_INTERLEAVE:
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
case MPOL_WEIGHTED_INTERLEAVE:
*nodes = pol->nodes;
break;
case MPOL_LOCAL:
/* return empty node mask for local allocation */
break;
default:
BUG();
}
}
static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
struct page *p = NULL;
int ret;
ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p);
if (ret > 0) {
ret = page_to_nid(p);
put_page(p);
}
return ret;
}
/* Retrieve NUMA policy */
static long do_get_mempolicy(int *policy, nodemask_t *nmask,
unsigned long addr, unsigned long flags)
{
int err;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = NULL;
struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL;
if (flags &
~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
return -EINVAL;
if (flags & MPOL_F_MEMS_ALLOWED) {
if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
return -EINVAL;
*policy = 0; /* just so it's initialized */
task_lock(current);
*nmask = cpuset_current_mems_allowed;
task_unlock(current);
return 0;
}
if (flags & MPOL_F_ADDR) {
pgoff_t ilx; /* ignored here */
/*
* Do NOT fall back to task policy if the
* vma/shared policy at addr is NULL. We
* want to return MPOL_DEFAULT in this case.
*/
mmap_read_lock(mm);
vma = vma_lookup(mm, addr);
if (!vma) {
mmap_read_unlock(mm);
return -EFAULT;
}
pol = __get_vma_policy(vma, addr, &ilx);
} else if (addr)
return -EINVAL;
if (!pol)
pol = &default_policy; /* indicates default behavior */
if (flags & MPOL_F_NODE) {
if (flags & MPOL_F_ADDR) {
/*
* Take a refcount on the mpol, because we are about to
* drop the mmap_lock, after which only "pol" remains
* valid, "vma" is stale.
*/
pol_refcount = pol;
vma = NULL;
mpol_get(pol);
mmap_read_unlock(mm);
err = lookup_node(mm, addr);
if (err < 0)
goto out;
*policy = err;
} else if (pol == current->mempolicy &&
pol->mode == MPOL_INTERLEAVE) {
*policy = next_node_in(current->il_prev, pol->nodes);
} else if (pol == current->mempolicy &&
pol->mode == MPOL_WEIGHTED_INTERLEAVE) {
if (current->il_weight)
*policy = current->il_prev;
else
*policy = next_node_in(current->il_prev,
pol->nodes);
} else {
err = -EINVAL;
goto out;
}
} else {
*policy = pol == &default_policy ? MPOL_DEFAULT :
pol->mode;
/*
* Internal mempolicy flags must be masked off before exposing
* the policy to userspace.
*/
*policy |= (pol->flags & MPOL_MODE_FLAGS);
}
err = 0;
if (nmask) {
if (mpol_store_user_nodemask(pol)) {
*nmask = pol->w.user_nodemask;
} else {
task_lock(current);
get_policy_nodemask(pol, nmask);
task_unlock(current);
}
}
out:
mpol_cond_put(pol);
if (vma)
mmap_read_unlock(mm);
if (pol_refcount)
mpol_put(pol_refcount);
return err;
}
#ifdef CONFIG_MIGRATION
static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags)
{
/*
* Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio.
* Choosing not to migrate a shared folio is not counted as a failure.
*
* See folio_maybe_mapped_shared() on possible imprecision when we
* cannot easily detect if a folio is shared.
*/
if ((flags & MPOL_MF_MOVE_ALL) || !folio_maybe_mapped_shared(folio)) {
if (folio_isolate_lru(folio)) {
list_add_tail(&folio->lru, foliolist);
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
} else {
/*
* Non-movable folio may reach here. And, there may be
* temporary off LRU folios or non-LRU movable folios.
* Treat them as unmovable folios since they can't be
* isolated, so they can't be moved at the moment.
*/
return false;
}
}
return true;
}
/*
* Migrate pages from one node to a target node.
* Returns error or the number of pages not migrated.
*/
static long migrate_to_node(struct mm_struct *mm, int source, int dest,
int flags)
{
nodemask_t nmask;
struct vm_area_struct *vma;
LIST_HEAD(pagelist);
long nr_failed;
long err = 0;
struct migration_target_control mtc = {
.nid = dest,
.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
.reason = MR_SYSCALL,
};
nodes_clear(nmask);
node_set(source, nmask);
VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
mmap_read_lock(mm);
vma = find_vma(mm, 0);
if (unlikely(!vma)) {
mmap_read_unlock(mm);
return 0;
}
/*
* This does not migrate the range, but isolates all pages that
* need migration. Between passing in the full user address
* space range and MPOL_MF_DISCONTIG_OK, this call cannot fail,
* but passes back the count of pages which could not be isolated.
*/
nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask,
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
mmap_read_unlock(mm);
if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, alloc_migration_target, NULL,
(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL);
if (err)
putback_movable_pages(&pagelist);
}
if (err >= 0)
err += nr_failed;
return err;
}
/*
* Move pages between the two nodesets so as to preserve the physical
* layout as much as possible.
*
* Returns the number of page that could not be moved.
*/
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to, int flags)
{
long nr_failed = 0;
long err = 0;
nodemask_t tmp;
lru_cache_disable();
/*
* Find a 'source' bit set in 'tmp' whose corresponding 'dest'
* bit in 'to' is not also set in 'tmp'. Clear the found 'source'
* bit in 'tmp', and return that <source, dest> pair for migration.
* The pair of nodemasks 'to' and 'from' define the map.
*
* If no pair of bits is found that way, fallback to picking some
* pair of 'source' and 'dest' bits that are not the same. If the
* 'source' and 'dest' bits are the same, this represents a node
* that will be migrating to itself, so no pages need move.
*
* If no bits are left in 'tmp', or if all remaining bits left
* in 'tmp' correspond to the same bit in 'to', return false
* (nothing left to migrate).
*
* This lets us pick a pair of nodes to migrate between, such that
* if possible the dest node is not already occupied by some other
* source node, minimizing the risk of overloading the memory on a
* node that would happen if we migrated incoming memory to a node
* before migrating outgoing memory source that same node.
*
* A single scan of tmp is sufficient. As we go, we remember the
* most recent <s, d> pair that moved (s != d). If we find a pair
* that not only moved, but what's better, moved to an empty slot
* (d is not set in tmp), then we break out then, with that pair.
* Otherwise when we finish scanning from_tmp, we at least have the
* most recent <s, d> pair that moved. If we get all the way through
* the scan of tmp without finding any node that moved, much less
* moved to an empty node, then there is nothing left worth migrating.
*/
tmp = *from;
while (!nodes_empty(tmp)) {
int s, d;
int source = NUMA_NO_NODE;
int dest = 0;
for_each_node_mask(s, tmp) {
/*
* do_migrate_pages() tries to maintain the relative
* node relationship of the pages established between
* threads and memory areas.
*
* However if the number of source nodes is not equal to
* the number of destination nodes we can not preserve
* this node relative relationship. In that case, skip
* copying memory from a node that is in the destination
* mask.
*
* Example: [2,3,4] -> [3,4,5] moves everything.
* [0-7] - > [3,4,5] moves only 0,1,2,6,7.
*/
if ((nodes_weight(*from) != nodes_weight(*to)) &&
(node_isset(s, *to)))
continue;
d = node_remap(s, *from, *to);
if (s == d)
continue;
source = s; /* Node moved. Memorize */
dest = d;
/* dest not in remaining from nodes? */
if (!node_isset(dest, tmp))
break;
}
if (source == NUMA_NO_NODE)
break;
node_clear(source, tmp);
err = migrate_to_node(mm, source, dest, flags);
if (err > 0)
nr_failed += err;
if (err < 0)
break;
}
lru_cache_enable();
if (err < 0)
return err;
return (nr_failed < INT_MAX) ? nr_failed : INT_MAX;
}
/*
* Allocate a new folio for page migration, according to NUMA mempolicy.
*/
static struct folio *alloc_migration_target_by_mpol(struct folio *src,
unsigned long private)
{
struct migration_mpol *mmpol = (struct migration_mpol *)private;
struct mempolicy *pol = mmpol->pol;
pgoff_t ilx = mmpol->ilx;
unsigned int order;
int nid = numa_node_id();
gfp_t gfp;
order = folio_order(src);
ilx += src->index >> order;
if (folio_test_hugetlb(src)) {
nodemask_t *nodemask;
struct hstate *h;
h = folio_hstate(src);
gfp = htlb_alloc_mask(h);
nodemask = policy_nodemask(gfp, pol, ilx, &nid);
return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp,
htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND));
}
if (folio_test_large(src))
gfp = GFP_TRANSHUGE;
else
gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP;
return folio_alloc_mpol(gfp, order, pol, ilx, nid);
}
#else
static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
unsigned long flags)
{
return false;
}
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to, int flags)
{
return -ENOSYS;
}
static struct folio *alloc_migration_target_by_mpol(struct folio *src,
unsigned long private)
{
return NULL;
}
#endif
static long do_mbind(unsigned long start, unsigned long len,
unsigned short mode, unsigned short mode_flags,
nodemask_t *nmask, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
struct vma_iterator vmi;
struct migration_mpol mmpol;
struct mempolicy *new;
unsigned long end;
long err;
long nr_failed;
LIST_HEAD(pagelist);
if (flags & ~(unsigned long)MPOL_MF_VALID)
return -EINVAL;
if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
return -EPERM;
if (start & ~PAGE_MASK)
return -EINVAL;
if (mode == MPOL_DEFAULT)
flags &= ~MPOL_MF_STRICT;
len = PAGE_ALIGN(len);
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
new = mpol_new(mode, mode_flags, nmask);
if (IS_ERR(new))
return PTR_ERR(new);
/*
* If we are using the default policy then operation
* on discontinuous address spaces is okay after all
*/
if (!new)
flags |= MPOL_MF_DISCONTIG_OK;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
lru_cache_disable();
{
NODEMASK_SCRATCH(scratch);
if (scratch) {
mmap_write_lock(mm);
err = mpol_set_nodemask(new, nmask, scratch);
if (err)
mmap_write_unlock(mm);
} else
err = -ENOMEM;
NODEMASK_SCRATCH_FREE(scratch);
}
if (err)
goto mpol_out;
/*
* Lock the VMAs before scanning for pages to migrate,
* to ensure we don't miss a concurrently inserted page.
*/
nr_failed = queue_pages_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist);
if (nr_failed < 0) {
err = nr_failed;
nr_failed = 0;
} else {
vma_iter_init(&vmi, mm, start);
prev = vma_prev(&vmi);
for_each_vma_range(vmi, vma, end) {
err = mbind_range(&vmi, vma, &prev, start, end, new);
if (err)
break;
}
}
if (!err && !list_empty(&pagelist)) {
/* Convert MPOL_DEFAULT's NULL to task or default policy */
if (!new) {
new = get_task_policy(current);
mpol_get(new);
}
mmpol.pol = new;
mmpol.ilx = 0;
/*
* In the interleaved case, attempt to allocate on exactly the
* targeted nodes, for the first VMA to be migrated; for later
* VMAs, the nodes will still be interleaved from the targeted
* nodemask, but one by one may be selected differently.
*/
if (new->mode == MPOL_INTERLEAVE ||
new->mode == MPOL_WEIGHTED_INTERLEAVE) {
struct folio *folio;
unsigned int order;
unsigned long addr = -EFAULT;
list_for_each_entry(folio, &pagelist, lru) {
if (!folio_test_ksm(folio))
break;
}
if (!list_entry_is_head(folio, &pagelist, lru)) {
vma_iter_init(&vmi, mm, start);
for_each_vma_range(vmi, vma, end) {
addr = page_address_in_vma(folio,
folio_page(folio, 0), vma);
if (addr != -EFAULT)
break;
}
}
if (addr != -EFAULT) {
order = folio_order(folio);
/* We already know the pol, but not the ilx */
mpol_cond_put(get_vma_policy(vma, addr, order,
&mmpol.ilx));
/* Set base from which to increment by index */
mmpol.ilx -= folio->index >> order;
}
}
}
mmap_write_unlock(mm);
if (!err && !list_empty(&pagelist)) {
nr_failed |= migrate_pages(&pagelist,
alloc_migration_target_by_mpol, NULL,
(unsigned long)&mmpol, MIGRATE_SYNC,
MR_MEMPOLICY_MBIND, NULL);
}
if (nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
if (!list_empty(&pagelist))
putback_movable_pages(&pagelist);
mpol_out:
mpol_put(new);
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
lru_cache_enable();
return err;
}
/*
* User space interface with variable sized bitmaps for nodelists.
*/
static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask,
unsigned long maxnode)
{
unsigned long nlongs = BITS_TO_LONGS(maxnode);
int ret;
if (in_compat_syscall())
ret = compat_get_bitmap(mask,
(const compat_ulong_t __user *)nmask,
maxnode);
else
ret = copy_from_user(mask, nmask,
nlongs * sizeof(unsigned long));
if (ret)
return -EFAULT;
if (maxnode % BITS_PER_LONG)
mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1;
return 0;
}
/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
unsigned long maxnode)
{
--maxnode;
nodes_clear(*nodes);
if (maxnode == 0 || !nmask)
return 0;
if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
return -EINVAL;
/*
* When the user specified more nodes than supported just check
* if the non supported part is all zero, one word at a time,
* starting at the end.
*/
while (maxnode > MAX_NUMNODES) {
unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG);
unsigned long t;
if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits))
return -EFAULT;
if (maxnode - bits >= MAX_NUMNODES) {
maxnode -= bits;
} else {
maxnode = MAX_NUMNODES;
t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1);
}
if (t)
return -EINVAL;
}
return get_bitmap(nodes_addr(*nodes), nmask, maxnode);
}
/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
nodemask_t *nodes)
{
unsigned long copy = ALIGN(maxnode-1, 64) / 8;
unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long);
bool compat = in_compat_syscall();
if (compat)
nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t);
if (copy > nbytes) {
if (copy > PAGE_SIZE)
return -EINVAL;
if (clear_user((char __user *)mask + nbytes, copy - nbytes))
return -EFAULT;
copy = nbytes;
maxnode = nr_node_ids;
}
if (compat)
return compat_put_bitmap((compat_ulong_t __user *)mask,
nodes_addr(*nodes), maxnode);
return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}
/* Basic parameter sanity check used by both mbind() and set_mempolicy() */
static inline int sanitize_mpol_flags(int *mode, unsigned short *flags)
{
*flags = *mode & MPOL_MODE_FLAGS;
*mode &= ~MPOL_MODE_FLAGS;
if ((unsigned int)(*mode) >= MPOL_MAX)
return -EINVAL;
if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES))
return -EINVAL;
if (*flags & MPOL_F_NUMA_BALANCING) {
if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY)
*flags |= (MPOL_F_MOF | MPOL_F_MORON);
else
return -EINVAL;
}
return 0;
}
static long kernel_mbind(unsigned long start, unsigned long len,
unsigned long mode, const unsigned long __user *nmask,
unsigned long maxnode, unsigned int flags)
{
unsigned short mode_flags;
nodemask_t nodes;
int lmode = mode;
int err;
start = untagged_addr(start);
err = sanitize_mpol_flags(&lmode, &mode_flags);
if (err)
return err;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
}
SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len,
unsigned long, home_node, unsigned long, flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
struct mempolicy *new, *old;
unsigned long end;
int err = -ENOENT;
VMA_ITERATOR(vmi, mm, start);
start = untagged_addr(start);
if (start & ~PAGE_MASK)
return -EINVAL;
/*
* flags is used for future extension if any.
*/
if (flags != 0)
return -EINVAL;
/*
* Check home_node is online to avoid accessing uninitialized
* NODE_DATA.
*/
if (home_node >= MAX_NUMNODES || !node_online(home_node))
return -EINVAL;
len = PAGE_ALIGN(len);
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
mmap_write_lock(mm);
prev = vma_prev(&vmi);
for_each_vma_range(vmi, vma, end) {
/*
* If any vma in the range got policy other than MPOL_BIND
* or MPOL_PREFERRED_MANY we return error. We don't reset
* the home node for vmas we already updated before.
*/
old = vma_policy(vma);
if (!old) {
prev = vma;
continue;
}
if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) {
err = -EOPNOTSUPP;
break;
}
new = mpol_dup(old);
if (IS_ERR(new)) {
err = PTR_ERR(new);
break;
}
vma_start_write(vma);
new->home_node = home_node;
err = mbind_range(&vmi, vma, &prev, start, end, new);
mpol_put(new);
if (err)
break;
}
mmap_write_unlock(mm);
return err;
}
SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
unsigned long, mode, const unsigned long __user *, nmask,
unsigned long, maxnode, unsigned int, flags)
{
return kernel_mbind(start, len, mode, nmask, maxnode, flags);
}
/* Set the process memory policy */
static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
unsigned long maxnode)
{
unsigned short mode_flags;
nodemask_t nodes;
int lmode = mode;
int err;
err = sanitize_mpol_flags(&lmode, &mode_flags);
if (err)
return err;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
return do_set_mempolicy(lmode, mode_flags, &nodes);
}
SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
unsigned long, maxnode)
{
return kernel_set_mempolicy(mode, nmask, maxnode);
}
static int kernel_migrate_pages(pid_t pid, unsigned long maxnode,
const unsigned long __user *old_nodes,
const unsigned long __user *new_nodes)
{
struct mm_struct *mm = NULL;
struct task_struct *task;
nodemask_t task_nodes;
int err;
nodemask_t *old;
nodemask_t *new;
NODEMASK_SCRATCH(scratch);
if (!scratch)
return -ENOMEM;
old = &scratch->mask1;
new = &scratch->mask2;
err = get_nodes(old, old_nodes, maxnode);
if (err)
goto out;
err = get_nodes(new, new_nodes, maxnode);
if (err)
goto out;
/* Find the mm_struct */
rcu_read_lock();
task = pid ? find_task_by_vpid(pid) : current;
if (!task) {
rcu_read_unlock();
err = -ESRCH;
goto out;
}
get_task_struct(task);
err = -EINVAL;
/*
* Check if this process has the right to modify the specified process.
* Use the regular "ptrace_may_access()" checks.
*/
if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
rcu_read_unlock();
err = -EPERM;
goto out_put;
}
rcu_read_unlock();
task_nodes = cpuset_mems_allowed(task);
/* Is the user allowed to access the target nodes? */
if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) {
err = -EPERM;
goto out_put;
}
task_nodes = cpuset_mems_allowed(current);
nodes_and(*new, *new, task_nodes);
if (nodes_empty(*new))
goto out_put;
err = security_task_movememory(task);
if (err)
goto out_put;
mm = get_task_mm(task);
put_task_struct(task);
if (!mm) {
err = -EINVAL;
goto out;
}
err = do_migrate_pages(mm, old, new,
capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
mmput(mm);
out:
NODEMASK_SCRATCH_FREE(scratch);
return err;
out_put:
put_task_struct(task);
goto out;
}
SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
const unsigned long __user *, old_nodes,
const unsigned long __user *, new_nodes)
{
return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes);
}
/* Retrieve NUMA policy */
static int kernel_get_mempolicy(int __user *policy,
unsigned long __user *nmask,
unsigned long maxnode,
unsigned long addr,
unsigned long flags)
{
int err;
int pval;
nodemask_t nodes;
if (nmask != NULL && maxnode < nr_node_ids)
return -EINVAL;
addr = untagged_addr(addr);
err = do_get_mempolicy(&pval, &nodes, addr, flags);
if (err)
return err;
if (policy && put_user(pval, policy))
return -EFAULT;
if (nmask)
err = copy_nodes_to_user(nmask, maxnode, &nodes);
return err;
}
SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
unsigned long __user *, nmask, unsigned long, maxnode,
unsigned long, addr, unsigned long, flags)
{
return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags);
}
bool vma_migratable(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
return false;
/*
* DAX device mappings require predictable access latency, so avoid
* incurring periodic faults.
*/
if (vma_is_dax(vma))
return false;
if (is_vm_hugetlb_page(vma) &&
!hugepage_migration_supported(hstate_vma(vma)))
return false;
/*
* Migration allocates pages in the highest zone. If we cannot
* do so then migration (at least from node to node) is not
* possible.
*/
if (vma->vm_file &&
gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping))
< policy_zone)
return false;
return true;
}
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx)
{
*ilx = 0;
return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy;
}
/*
* get_vma_policy(@vma, @addr, @order, @ilx)
* @vma: virtual memory area whose policy is sought
* @addr: address in @vma for shared policy lookup
* @order: 0, or appropriate huge_page_order for interleaving
* @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or
* MPOL_WEIGHTED_INTERLEAVE
*
* Returns effective policy for a VMA at specified address.
* Falls back to current->mempolicy or system default policy, as necessary.
* Shared policies [those marked as MPOL_F_SHARED] require an extra reference
* count--added by the get_policy() vm_op, as appropriate--to protect against
* freeing by another task. It is the caller's responsibility to free the
* extra reference for shared policies.
*/
struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr, int order, pgoff_t *ilx)
{
struct mempolicy *pol;
pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE ||
pol->mode == MPOL_WEIGHTED_INTERLEAVE) {
*ilx += vma->vm_pgoff >> order;
*ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order);
}
return pol;
}
bool vma_policy_mof(struct vm_area_struct *vma)
{
struct mempolicy *pol;
if (vma->vm_ops && vma->vm_ops->get_policy) {
bool ret = false;
pgoff_t ilx; /* ignored here */
pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx);
if (pol && (pol->flags & MPOL_F_MOF))
ret = true;
mpol_cond_put(pol);
return ret;
}
pol = vma->vm_policy;
if (!pol)
pol = get_task_policy(current);
return pol->flags & MPOL_F_MOF;
}
bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
{
enum zone_type dynamic_policy_zone = policy_zone;
BUG_ON(dynamic_policy_zone == ZONE_MOVABLE);
/*
* if policy->nodes has movable memory only,
* we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only.
*
* policy->nodes is intersect with node_states[N_MEMORY].
* so if the following test fails, it implies
* policy->nodes has movable memory only.
*/
if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY]))
dynamic_policy_zone = ZONE_MOVABLE;
return zone >= dynamic_policy_zone;
}
static unsigned int weighted_interleave_nodes(struct mempolicy *policy)
{
unsigned int node;
unsigned int cpuset_mems_cookie;
retry:
/* to prevent miscount use tsk->mems_allowed_seq to detect rebind */
cpuset_mems_cookie = read_mems_allowed_begin();
node = current->il_prev;
if (!current->il_weight || !node_isset(node, policy->nodes)) {
node = next_node_in(node, policy->nodes);
if (read_mems_allowed_retry(cpuset_mems_cookie))
goto retry;
if (node == MAX_NUMNODES)
return node;
current->il_prev = node;
current->il_weight = get_il_weight(node);
}
current->il_weight--;
return node;
}
/* Do dynamic interleaving for a process */
static unsigned int interleave_nodes(struct mempolicy *policy)
{
unsigned int nid;
unsigned int cpuset_mems_cookie;
/* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */
do {
cpuset_mems_cookie = read_mems_allowed_begin();
nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid;
return nid;
}
/*
* Depending on the memory policy provide a node from which to allocate the
* next slab entry.
*/
unsigned int mempolicy_slab_node(void)
{
struct mempolicy *policy;
int node = numa_mem_id();
if (!in_task())
return node;
policy = current->mempolicy;
if (!policy)
return node;
switch (policy->mode) {
case MPOL_PREFERRED:
return first_node(policy->nodes);
case MPOL_INTERLEAVE:
return interleave_nodes(policy);
case MPOL_WEIGHTED_INTERLEAVE:
return weighted_interleave_nodes(policy);
case MPOL_BIND:
case MPOL_PREFERRED_MANY:
{
struct zoneref *z;
/*
* Follow bind policy behavior and start allocation at the
* first node.
*/
struct zonelist *zonelist;
enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK];
z = first_zones_zonelist(zonelist, highest_zoneidx,
&policy->nodes);
return zonelist_zone(z) ? zonelist_node_idx(z) : node;
}
case MPOL_LOCAL:
return node;
default:
BUG();
}
}
static unsigned int read_once_policy_nodemask(struct mempolicy *pol,
nodemask_t *mask)
{
/*
* barrier stabilizes the nodemask locally so that it can be iterated
* over safely without concern for changes. Allocators validate node
* selection does not violate mems_allowed, so this is safe.
*/
barrier();
memcpy(mask, &pol->nodes, sizeof(nodemask_t));
barrier();
return nodes_weight(*mask);
}
static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx)
{
nodemask_t nodemask;
unsigned int target, nr_nodes;
u8 *table;
unsigned int weight_total = 0;
u8 weight;
int nid;
nr_nodes = read_once_policy_nodemask(pol, &nodemask);
if (!nr_nodes)
return numa_node_id();
rcu_read_lock();
table = rcu_dereference(iw_table);
/* calculate the total weight */
for_each_node_mask(nid, nodemask) {
/* detect system default usage */
weight = table ? table[nid] : 1;
weight = weight ? weight : 1;
weight_total += weight;
}
/* Calculate the node offset based on totals */
target = ilx % weight_total;
nid = first_node(nodemask);
while (target) {
/* detect system default usage */
weight = table ? table[nid] : 1;
weight = weight ? weight : 1;
if (target < weight)
break;
target -= weight;
nid = next_node_in(nid, nodemask);
}
rcu_read_unlock();
return nid;
}
/*
* Do static interleaving for interleave index @ilx. Returns the ilx'th
* node in pol->nodes (starting from ilx=0), wrapping around if ilx
* exceeds the number of present nodes.
*/
static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx)
{
nodemask_t nodemask;
unsigned int target, nnodes;
int i;
int nid;
nnodes = read_once_policy_nodemask(pol, &nodemask);
if (!nnodes)
return numa_node_id();
target = ilx % nnodes;
nid = first_node(nodemask);
for (i = 0; i < target; i++)
nid = next_node(nid, nodemask);
return nid;
}
/*
* Return a nodemask representing a mempolicy for filtering nodes for
* page allocation, together with preferred node id (or the input node id).
*/
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol,
pgoff_t ilx, int *nid)
{
nodemask_t *nodemask = NULL;
switch (pol->mode) {
case MPOL_PREFERRED:
/* Override input node id */
*nid = first_node(pol->nodes);
break;
case MPOL_PREFERRED_MANY:
nodemask = &pol->nodes;
if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node;
break;
case MPOL_BIND:
/* Restrict to nodemask (but not on lower zones) */
if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes))
nodemask = &pol->nodes;
if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node;
/*
* __GFP_THISNODE shouldn't even be used with the bind policy
* because we might easily break the expectation to stay on the
* requested node and not break the policy.
*/
WARN_ON_ONCE(gfp & __GFP_THISNODE);
break;
case MPOL_INTERLEAVE:
/* Override input node id */
*nid = (ilx == NO_INTERLEAVE_INDEX) ?
interleave_nodes(pol) : interleave_nid(pol, ilx);
break;
case MPOL_WEIGHTED_INTERLEAVE:
*nid = (ilx == NO_INTERLEAVE_INDEX) ?
weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx);
break;
}
return nodemask;
}
#ifdef CONFIG_HUGETLBFS
/*
* huge_node(@vma, @addr, @gfp_flags, @mpol)
* @vma: virtual memory area whose policy is sought
* @addr: address in @vma for shared policy lookup and interleave policy
* @gfp_flags: for requested zone
* @mpol: pointer to mempolicy pointer for reference counted mempolicy
* @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy
*
* Returns a nid suitable for a huge page allocation and a pointer
* to the struct mempolicy for conditional unref after allocation.
* If the effective policy is 'bind' or 'prefer-many', returns a pointer
* to the mempolicy's @nodemask for filtering the zonelist.
*/
int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags,
struct mempolicy **mpol, nodemask_t **nodemask)
{
pgoff_t ilx;
int nid;
nid = numa_node_id();
*mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx);
*nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid);
return nid;
}
/*
* init_nodemask_of_mempolicy
*
* If the current task's mempolicy is "default" [NULL], return 'false'
* to indicate default policy. Otherwise, extract the policy nodemask
* for 'bind' or 'interleave' policy into the argument nodemask, or
* initialize the argument nodemask to contain the single node for
* 'preferred' or 'local' policy and return 'true' to indicate presence
* of non-default mempolicy.
*
* We don't bother with reference counting the mempolicy [mpol_get/put]
* because the current task is examining it's own mempolicy and a task's
* mempolicy is only ever changed by the task itself.
*
* N.B., it is the caller's responsibility to free a returned nodemask.
*/
bool init_nodemask_of_mempolicy(nodemask_t *mask)
{
struct mempolicy *mempolicy;
if (!(mask && current->mempolicy))
return false;
task_lock(current);
mempolicy = current->mempolicy;
switch (mempolicy->mode) {
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
case MPOL_BIND:
case MPOL_INTERLEAVE:
case MPOL_WEIGHTED_INTERLEAVE:
*mask = mempolicy->nodes;
break;
case MPOL_LOCAL:
init_nodemask_of_node(mask, numa_node_id());
break;
default:
BUG();
}
task_unlock(current);
return true;
}
#endif
/*
* mempolicy_in_oom_domain
*
* If tsk's mempolicy is "bind", check for intersection between mask and
* the policy nodemask. Otherwise, return true for all other policies
* including "interleave", as a tsk with "interleave" policy may have
* memory allocated from all nodes in system.
*
* Takes task_lock(tsk) to prevent freeing of its mempolicy.
*/
bool mempolicy_in_oom_domain(struct task_struct *tsk,
const nodemask_t *mask)
{
struct mempolicy *mempolicy;
bool ret = true;
if (!mask)
return ret;
task_lock(tsk);
mempolicy = tsk->mempolicy;
if (mempolicy && mempolicy->mode == MPOL_BIND)
ret = nodes_intersects(mempolicy->nodes, *mask);
task_unlock(tsk);
return ret;
}
static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
int nid, nodemask_t *nodemask)
{
struct page *page;
gfp_t preferred_gfp;
/*
* This is a two pass approach. The first pass will only try the
* preferred nodes but skip the direct reclaim and allow the
* allocation to fail, while the second pass will try all the
* nodes in system.
*/
preferred_gfp = gfp | __GFP_NOWARN;
preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask);
if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL);
return page;
}
/**
* alloc_pages_mpol - Allocate pages according to NUMA mempolicy.
* @gfp: GFP flags.
* @order: Order of the page allocation.
* @pol: Pointer to the NUMA mempolicy.
* @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()).
* @nid: Preferred node (usually numa_node_id() but @mpol may override it).
*
* Return: The page on success or NULL if allocation fails.
*/
static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
struct mempolicy *pol, pgoff_t ilx, int nid)
{
nodemask_t *nodemask;
struct page *page;
nodemask = policy_nodemask(gfp, pol, ilx, &nid);
if (pol->mode == MPOL_PREFERRED_MANY)
return alloc_pages_preferred_many(gfp, order, nid, nodemask);
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
/* filter "hugepage" allocation, unless from alloc_pages() */
order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) {
/*
* For hugepage allocation and non-interleave policy which
* allows the current node (or other explicitly preferred
* node) we only try to allocate from the current/preferred
* node and don't fall back to other nodes, as the cost of
* remote accesses would likely offset THP benefits.
*
* If the policy is interleave or does not allow the current
* node in its nodemask, we allocate the standard way.
*/
if (pol->mode != MPOL_INTERLEAVE &&
pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) {
/*
* First, try to allocate THP only on local node, but
* don't reclaim unnecessarily, just compact.
*/
page = __alloc_frozen_pages_noprof(
gfp | __GFP_THISNODE | __GFP_NORETRY, order,
nid, NULL);
if (page || !(gfp & __GFP_DIRECT_RECLAIM))
return page;
/*
* If hugepage allocations are configured to always
* synchronous compact or the vma has been madvised
* to prefer hugepage backing, retry allowing remote
* memory with both reclaim and compact as well.
*/
}
}
page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask);
if (unlikely(pol->mode == MPOL_INTERLEAVE ||
pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) {
/* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */
if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) {
preempt_disable();
__count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable();
}
}
return page;
}
struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
struct mempolicy *pol, pgoff_t ilx, int nid)
{
struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol,
ilx, nid);
if (!page)
return NULL;
set_page_refcounted(page); return page_rmappable_folio(page);
}
/**
* vma_alloc_folio - Allocate a folio for a VMA.
* @gfp: GFP flags.
* @order: Order of the folio.
* @vma: Pointer to VMA.
* @addr: Virtual address of the allocation. Must be inside @vma.
*
* Allocate a folio for a specific address in @vma, using the appropriate
* NUMA policy. The caller must hold the mmap_lock of the mm_struct of the
* VMA to prevent it from going away. Should be used for all allocations
* for folios that will be mapped into user space, excepting hugetlbfs, and
* excepting where direct use of folio_alloc_mpol() is more appropriate.
*
* Return: The folio on success or NULL if allocation fails.
*/
struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma,
unsigned long addr)
{
struct mempolicy *pol;
pgoff_t ilx;
struct folio *folio;
if (vma->vm_flags & VM_DROPPABLE)
gfp |= __GFP_NOWARN;
pol = get_vma_policy(vma, addr, order, &ilx);
folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id());
mpol_cond_put(pol);
return folio;
}
EXPORT_SYMBOL(vma_alloc_folio_noprof);
struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order)
{
struct mempolicy *pol = &default_policy;
/*
* No reference counting needed for current->mempolicy
* nor system default_policy
*/
if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current);
return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX,
numa_node_id());
}
/**
* alloc_pages - Allocate pages.
* @gfp: GFP flags.
* @order: Power of two of number of pages to allocate.
*
* Allocate 1 << @order contiguous pages. The physical address of the
* first page is naturally aligned (eg an order-3 allocation will be aligned
* to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current
* process is honoured when in process context.
*
* Context: Can be called from any context, providing the appropriate GFP
* flags are used.
* Return: The page on success or NULL if allocation fails.
*/
struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order)
{ struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page);
return page;
}
EXPORT_SYMBOL(alloc_pages_noprof);
struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
{ return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order));
}
EXPORT_SYMBOL(folio_alloc_noprof);
static unsigned long alloc_pages_bulk_interleave(gfp_t gfp,
struct mempolicy *pol, unsigned long nr_pages,
struct page **page_array)
{
int nodes;
unsigned long nr_pages_per_node;
int delta;
int i;
unsigned long nr_allocated;
unsigned long total_allocated = 0;
nodes = nodes_weight(pol->nodes);
nr_pages_per_node = nr_pages / nodes;
delta = nr_pages - nodes * nr_pages_per_node;
for (i = 0; i < nodes; i++) {
if (delta) {
nr_allocated = alloc_pages_bulk_noprof(gfp,
interleave_nodes(pol), NULL,
nr_pages_per_node + 1,
page_array);
delta--;
} else {
nr_allocated = alloc_pages_bulk_noprof(gfp,
interleave_nodes(pol), NULL,
nr_pages_per_node, page_array);
}
page_array += nr_allocated;
total_allocated += nr_allocated;
}
return total_allocated;
}
static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
struct mempolicy *pol, unsigned long nr_pages,
struct page **page_array)
{
struct task_struct *me = current;
unsigned int cpuset_mems_cookie;
unsigned long total_allocated = 0;
unsigned long nr_allocated = 0;
unsigned long rounds;
unsigned long node_pages, delta;
u8 *table, *weights, weight;
unsigned int weight_total = 0;
unsigned long rem_pages = nr_pages;
nodemask_t nodes;
int nnodes, node;
int resume_node = MAX_NUMNODES - 1;
u8 resume_weight = 0;
int prev_node;
int i;
if (!nr_pages)
return 0;
/* read the nodes onto the stack, retry if done during rebind */
do {
cpuset_mems_cookie = read_mems_allowed_begin();
nnodes = read_once_policy_nodemask(pol, &nodes);
} while (read_mems_allowed_retry(cpuset_mems_cookie));
/* if the nodemask has become invalid, we cannot do anything */
if (!nnodes)
return 0;
/* Continue allocating from most recent node and adjust the nr_pages */
node = me->il_prev;
weight = me->il_weight;
if (weight && node_isset(node, nodes)) {
node_pages = min(rem_pages, weight);
nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
page_array);
page_array += nr_allocated;
total_allocated += nr_allocated;
/* if that's all the pages, no need to interleave */
if (rem_pages <= weight) {
me->il_weight -= rem_pages;
return total_allocated;
}
/* Otherwise we adjust remaining pages, continue from there */
rem_pages -= weight;
}
/* clear active weight in case of an allocation failure */
me->il_weight = 0;
prev_node = node;
/* create a local copy of node weights to operate on outside rcu */
weights = kzalloc(nr_node_ids, GFP_KERNEL);
if (!weights)
return total_allocated;
rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock();
/* calculate total, detect system default usage */
for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1;
weight_total += weights[node];
}
/*
* Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls.
* Track which node weighted interleave should resume from.
*
* if (rounds > 0) and (delta == 0), resume_node will always be
* the node following prev_node and its weight.
*/
rounds = rem_pages / weight_total;
delta = rem_pages % weight_total;
resume_node = next_node_in(prev_node, nodes);
resume_weight = weights[resume_node];
for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes);
weight = weights[node];
node_pages = weight * rounds;
/* If a delta exists, add this node's portion of the delta */
if (delta > weight) {
node_pages += weight;
delta -= weight;
} else if (delta) {
/* when delta is depleted, resume from that node */
node_pages += delta;
resume_node = node;
resume_weight = weight - delta;
delta = 0;
}
/* node_pages can be 0 if an allocation fails and rounds == 0 */
if (!node_pages)
break;
nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
page_array);
page_array += nr_allocated;
total_allocated += nr_allocated;
if (total_allocated == nr_pages)
break;
prev_node = node;
}
me->il_prev = resume_node;
me->il_weight = resume_weight;
kfree(weights);
return total_allocated;
}
static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid,
struct mempolicy *pol, unsigned long nr_pages,
struct page **page_array)
{
gfp_t preferred_gfp;
unsigned long nr_allocated = 0;
preferred_gfp = gfp | __GFP_NOWARN;
preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes,
nr_pages, page_array);
if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL,
nr_pages - nr_allocated,
page_array + nr_allocated);
return nr_allocated;
}
/* alloc pages bulk and mempolicy should be considered at the
* same time in some situation such as vmalloc.
*
* It can accelerate memory allocation especially interleaving
* allocate memory.
*/
unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp,
unsigned long nr_pages, struct page **page_array)
{
struct mempolicy *pol = &default_policy;
nodemask_t *nodemask;
int nid;
if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current);
if (pol->mode == MPOL_INTERLEAVE)
return alloc_pages_bulk_interleave(gfp, pol,
nr_pages, page_array);
if (pol->mode == MPOL_WEIGHTED_INTERLEAVE)
return alloc_pages_bulk_weighted_interleave(
gfp, pol, nr_pages, page_array);
if (pol->mode == MPOL_PREFERRED_MANY)
return alloc_pages_bulk_preferred_many(gfp,
numa_node_id(), pol, nr_pages, page_array);
nid = numa_node_id();
nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid);
return alloc_pages_bulk_noprof(gfp, nid, nodemask,
nr_pages, page_array);
}
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{ struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol);
dst->vm_policy = pol;
return 0;
}
/*
* If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
* rebinds the mempolicy its copying by calling mpol_rebind_policy()
* with the mems_allowed returned by cpuset_mems_allowed(). This
* keeps mempolicies cpuset relative after its cpuset moves. See
* further kernel/cpuset.c update_nodemask().
*
* current's mempolicy may be rebinded by the other task(the task that changes
* cpuset's mems), so we needn't do rebind work for current task.
*/
/* Slow path of a mempolicy duplicate */
struct mempolicy *__mpol_dup(struct mempolicy *old)
{
struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!new)
return ERR_PTR(-ENOMEM);
/* task's mempolicy is protected by alloc_lock */
if (old == current->mempolicy) {
task_lock(current);
*new = *old;
task_unlock(current);
} else
*new = *old;
if (current_cpuset_is_being_rebound()) {
nodemask_t mems = cpuset_mems_allowed(current);
mpol_rebind_policy(new, &mems);
}
atomic_set(&new->refcnt, 1);
return new;
}
/* Slow path of a mempolicy comparison */
bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (!a || !b)
return false;
if (a->mode != b->mode)
return false;
if (a->flags != b->flags)
return false;
if (a->home_node != b->home_node)
return false;
if (mpol_store_user_nodemask(a))
if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
return false;
switch (a->mode) {
case MPOL_BIND:
case MPOL_INTERLEAVE:
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
case MPOL_WEIGHTED_INTERLEAVE:
return !!nodes_equal(a->nodes, b->nodes);
case MPOL_LOCAL:
return true;
default:
BUG();
return false;
}
}
/*
* Shared memory backing store policy support.
*
* Remember policies even when nobody has shared memory mapped.
* The policies are kept in Red-Black tree linked from the inode.
* They are protected by the sp->lock rwlock, which should be held
* for any accesses to the tree.
*/
/*
* lookup first element intersecting start-end. Caller holds sp->lock for
* reading or for writing
*/
static struct sp_node *sp_lookup(struct shared_policy *sp,
pgoff_t start, pgoff_t end)
{
struct rb_node *n = sp->root.rb_node;
while (n) {
struct sp_node *p = rb_entry(n, struct sp_node, nd);
if (start >= p->end)
n = n->rb_right;
else if (end <= p->start)
n = n->rb_left;
else
break;
}
if (!n)
return NULL;
for (;;) {
struct sp_node *w = NULL;
struct rb_node *prev = rb_prev(n);
if (!prev)
break;
w = rb_entry(prev, struct sp_node, nd);
if (w->end <= start)
break;
n = prev;
}
return rb_entry(n, struct sp_node, nd);
}
/*
* Insert a new shared policy into the list. Caller holds sp->lock for
* writing.
*/
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
struct rb_node **p = &sp->root.rb_node;
struct rb_node *parent = NULL;
struct sp_node *nd;
while (*p) {
parent = *p;
nd = rb_entry(parent, struct sp_node, nd);
if (new->start < nd->start)
p = &(*p)->rb_left;
else if (new->end > nd->end)
p = &(*p)->rb_right;
else
BUG();
}
rb_link_node(&new->nd, parent, p);
rb_insert_color(&new->nd, &sp->root);
}
/* Find shared policy intersecting idx */
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
pgoff_t idx)
{
struct mempolicy *pol = NULL;
struct sp_node *sn;
if (!sp->root.rb_node)
return NULL;
read_lock(&sp->lock);
sn = sp_lookup(sp, idx, idx+1);
if (sn) {
mpol_get(sn->policy);
pol = sn->policy;
}
read_unlock(&sp->lock);
return pol;
}
static void sp_free(struct sp_node *n)
{
mpol_put(n->policy);
kmem_cache_free(sn_cache, n);
}
/**
* mpol_misplaced - check whether current folio node is valid in policy
*
* @folio: folio to be checked
* @vmf: structure describing the fault
* @addr: virtual address in @vma for shared policy lookup and interleave policy
*
* Lookup current policy node id for vma,addr and "compare to" folio's
* node id. Policy determination "mimics" alloc_page_vma().
* Called from fault path where we know the vma and faulting address.
*
* Return: NUMA_NO_NODE if the page is in a node that is valid for this
* policy, or a suitable node ID to allocate a replacement folio from.
*/
int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
unsigned long addr)
{
struct mempolicy *pol;
pgoff_t ilx;
struct zoneref *z;
int curnid = folio_nid(folio);
struct vm_area_struct *vma = vmf->vma;
int thiscpu = raw_smp_processor_id();
int thisnid = numa_node_id();
int polnid = NUMA_NO_NODE;
int ret = NUMA_NO_NODE;
/*
* Make sure ptl is held so that we don't preempt and we
* have a stable smp processor id
*/
lockdep_assert_held(vmf->ptl);
pol = get_vma_policy(vma, addr, folio_order(folio), &ilx);
if (!(pol->flags & MPOL_F_MOF))
goto out;
switch (pol->mode) {
case MPOL_INTERLEAVE:
polnid = interleave_nid(pol, ilx);
break;
case MPOL_WEIGHTED_INTERLEAVE:
polnid = weighted_interleave_nid(pol, ilx);
break;
case MPOL_PREFERRED:
if (node_isset(curnid, pol->nodes))
goto out;
polnid = first_node(pol->nodes);
break;
case MPOL_LOCAL:
polnid = numa_node_id();
break;
case MPOL_BIND:
case MPOL_PREFERRED_MANY:
/*
* Even though MPOL_PREFERRED_MANY can allocate pages outside
* policy nodemask we don't allow numa migration to nodes
* outside policy nodemask for now. This is done so that if we
* want demotion to slow memory to happen, before allocating
* from some DRAM node say 'x', we will end up using a
* MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario
* we should not promote to node 'x' from slow memory node.
*/
if (pol->flags & MPOL_F_MORON) {
/*
* Optimize placement among multiple nodes
* via NUMA balancing
*/
if (node_isset(thisnid, pol->nodes))
break;
goto out;
}
/*
* use current page if in policy nodemask,
* else select nearest allowed node, if any.
* If no allowed nodes, use current [!misplaced].
*/
if (node_isset(curnid, pol->nodes))
goto out;
z = first_zones_zonelist(
node_zonelist(thisnid, GFP_HIGHUSER),
gfp_zone(GFP_HIGHUSER),
&pol->nodes);
polnid = zonelist_node_idx(z);
break;
default:
BUG();
}
/* Migrate the folio towards the node whose CPU is referencing it */
if (pol->flags & MPOL_F_MORON) {
polnid = thisnid;
if (!should_numa_migrate_memory(current, folio, curnid,
thiscpu))
goto out;
}
if (curnid != polnid)
ret = polnid;
out:
mpol_cond_put(pol);
return ret;
}
/*
* Drop the (possibly final) reference to task->mempolicy. It needs to be
* dropped after task->mempolicy is set to NULL so that any allocation done as
* part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
* policy.
*/
void mpol_put_task_policy(struct task_struct *task)
{
struct mempolicy *pol;
task_lock(task);
pol = task->mempolicy;
task->mempolicy = NULL;
task_unlock(task);
mpol_put(pol);
}
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
rb_erase(&n->nd, &sp->root);
sp_free(n);
}
static void sp_node_init(struct sp_node *node, unsigned long start,
unsigned long end, struct mempolicy *pol)
{
node->start = start;
node->end = end;
node->policy = pol;
}
static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
struct mempolicy *pol)
{
struct sp_node *n;
struct mempolicy *newpol;
n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
if (!n)
return NULL;
newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n);
return NULL;
}
newpol->flags |= MPOL_F_SHARED;
sp_node_init(n, start, end, newpol);
return n;
}
/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, pgoff_t start,
pgoff_t end, struct sp_node *new)
{
struct sp_node *n;
struct sp_node *n_new = NULL;
struct mempolicy *mpol_new = NULL;
int ret = 0;
restart:
write_lock(&sp->lock);
n = sp_lookup(sp, start, end);
/* Take care of old policies in the same range. */
while (n && n->start < end) {
struct rb_node *next = rb_next(&n->nd);
if (n->start >= start) {
if (n->end <= end)
sp_delete(sp, n);
else
n->start = end;
} else {
/* Old policy spanning whole new range. */
if (n->end > end) {
if (!n_new)
goto alloc_new;
*mpol_new = *n->policy;
atomic_set(&mpol_new->refcnt, 1);
sp_node_init(n_new, end, n->end, mpol_new);
n->end = start;
sp_insert(sp, n_new);
n_new = NULL;
mpol_new = NULL;
break;
} else
n->end = start;
}
if (!next)
break;
n = rb_entry(next, struct sp_node, nd);
}
if (new)
sp_insert(sp, new);
write_unlock(&sp->lock);
ret = 0;
err_out:
if (mpol_new)
mpol_put(mpol_new);
if (n_new)
kmem_cache_free(sn_cache, n_new);
return ret;
alloc_new:
write_unlock(&sp->lock);
ret = -ENOMEM;
n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
if (!n_new)
goto err_out;
mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!mpol_new)
goto err_out;
atomic_set(&mpol_new->refcnt, 1);
goto restart;
}
/**
* mpol_shared_policy_init - initialize shared policy for inode
* @sp: pointer to inode shared policy
* @mpol: struct mempolicy to install
*
* Install non-NULL @mpol in inode's shared policy rb-tree.
* On entry, the current task has a reference on a non-NULL @mpol.
* This must be released on exit.
* This is called at get_inode() calls and we can use GFP_KERNEL.
*/
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
int ret;
sp->root = RB_ROOT; /* empty tree == default mempolicy */
rwlock_init(&sp->lock);
if (mpol) {
struct sp_node *sn;
struct mempolicy *npol;
NODEMASK_SCRATCH(scratch);
if (!scratch)
goto put_mpol;
/* contextualize the tmpfs mount point mempolicy to this file */
npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol))
goto free_scratch; /* no valid nodemask intersection */
task_lock(current);
ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch);
task_unlock(current);
if (ret)
goto put_npol;
/* alloc node covering entire file; adds ref to file's npol */
sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol);
if (sn)
sp_insert(sp, sn);
put_npol:
mpol_put(npol); /* drop initial ref on file's npol */
free_scratch:
NODEMASK_SCRATCH_FREE(scratch);
put_mpol:
mpol_put(mpol); /* drop our incoming ref on sb mpol */
}
}
int mpol_set_shared_policy(struct shared_policy *sp,
struct vm_area_struct *vma, struct mempolicy *pol)
{
int err;
struct sp_node *new = NULL;
unsigned long sz = vma_pages(vma);
if (pol) {
new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol);
if (!new)
return -ENOMEM;
}
err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new);
if (err && new)
sp_free(new);
return err;
}
/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *sp)
{
struct sp_node *n;
struct rb_node *next;
if (!sp->root.rb_node)
return;
write_lock(&sp->lock);
next = rb_first(&sp->root);
while (next) {
n = rb_entry(next, struct sp_node, nd);
next = rb_next(&n->nd);
sp_delete(sp, n);
}
write_unlock(&sp->lock);
}
#ifdef CONFIG_NUMA_BALANCING
static int __initdata numabalancing_override;
static void __init check_numabalancing_enable(void)
{
bool numabalancing_default = false;
if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
numabalancing_default = true;
/* Parsed by setup_numabalancing. override == 1 enables, -1 disables */
if (numabalancing_override)
set_numabalancing_state(numabalancing_override == 1);
if (num_online_nodes() > 1 && !numabalancing_override) {
pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n",
numabalancing_default ? "Enabling" : "Disabling");
set_numabalancing_state(numabalancing_default);
}
}
static int __init setup_numabalancing(char *str)
{
int ret = 0;
if (!str)
goto out;
if (!strcmp(str, "enable")) {
numabalancing_override = 1;
ret = 1;
} else if (!strcmp(str, "disable")) {
numabalancing_override = -1;
ret = 1;
}
out:
if (!ret)
pr_warn("Unable to parse numa_balancing=\n");
return ret;
}
__setup("numa_balancing=", setup_numabalancing);
#else
static inline void __init check_numabalancing_enable(void)
{
}
#endif /* CONFIG_NUMA_BALANCING */
void __init numa_policy_init(void)
{
nodemask_t interleave_nodes;
unsigned long largest = 0;
int nid, prefer = 0;
policy_cache = kmem_cache_create("numa_policy",
sizeof(struct mempolicy),
0, SLAB_PANIC, NULL);
sn_cache = kmem_cache_create("shared_policy_node",
sizeof(struct sp_node),
0, SLAB_PANIC, NULL);
for_each_node(nid) {
preferred_node_policy[nid] = (struct mempolicy) {
.refcnt = ATOMIC_INIT(1),
.mode = MPOL_PREFERRED,
.flags = MPOL_F_MOF | MPOL_F_MORON,
.nodes = nodemask_of_node(nid),
};
}
/*
* Set interleaving policy for system init. Interleaving is only
* enabled across suitably sized nodes (default is >= 16MB), or
* fall back to the largest node if they're all smaller.
*/
nodes_clear(interleave_nodes);
for_each_node_state(nid, N_MEMORY) {
unsigned long total_pages = node_present_pages(nid);
/* Preserve the largest node */
if (largest < total_pages) {
largest = total_pages;
prefer = nid;
}
/* Interleave this node? */
if ((total_pages << PAGE_SHIFT) >= (16 << 20))
node_set(nid, interleave_nodes);
}
/* All too small, use the largest */
if (unlikely(nodes_empty(interleave_nodes)))
node_set(prefer, interleave_nodes);
if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
pr_err("%s: interleaving failed\n", __func__);
check_numabalancing_enable();
}
/* Reset policy of current process to default */
void numa_default_policy(void)
{
do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}
/*
* Parse and format mempolicy from/to strings
*/
static const char * const policy_modes[] =
{
[MPOL_DEFAULT] = "default",
[MPOL_PREFERRED] = "prefer",
[MPOL_BIND] = "bind",
[MPOL_INTERLEAVE] = "interleave",
[MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave",
[MPOL_LOCAL] = "local",
[MPOL_PREFERRED_MANY] = "prefer (many)",
};
#ifdef CONFIG_TMPFS
/**
* mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
* @str: string containing mempolicy to parse
* @mpol: pointer to struct mempolicy pointer, returned on success.
*
* Format of input:
* <mode>[=<flags>][:<nodelist>]
*
* Return: %0 on success, else %1
*/
int mpol_parse_str(char *str, struct mempolicy **mpol)
{
struct mempolicy *new = NULL;
unsigned short mode_flags;
nodemask_t nodes;
char *nodelist = strchr(str, ':');
char *flags = strchr(str, '=');
int err = 1, mode;
if (flags)
*flags++ = '\0'; /* terminate mode string */
if (nodelist) {
/* NUL-terminate mode or flags string */
*nodelist++ = '\0';
if (nodelist_parse(nodelist, nodes))
goto out;
if (!nodes_subset(nodes, node_states[N_MEMORY]))
goto out;
} else
nodes_clear(nodes);
mode = match_string(policy_modes, MPOL_MAX, str);
if (mode < 0)
goto out;
switch (mode) {
case MPOL_PREFERRED:
/*
* Insist on a nodelist of one node only, although later
* we use first_node(nodes) to grab a single node, so here
* nodelist (or nodes) cannot be empty.
*/
if (nodelist) {
char *rest = nodelist;
while (isdigit(*rest))
rest++;
if (*rest)
goto out;
if (nodes_empty(nodes))
goto out;
}
break;
case MPOL_INTERLEAVE:
case MPOL_WEIGHTED_INTERLEAVE:
/*
* Default to online nodes with memory if no nodelist
*/
if (!nodelist)
nodes = node_states[N_MEMORY];
break;
case MPOL_LOCAL:
/*
* Don't allow a nodelist; mpol_new() checks flags
*/
if (nodelist)
goto out;
break;
case MPOL_DEFAULT:
/*
* Insist on a empty nodelist
*/
if (!nodelist)
err = 0;
goto out;
case MPOL_PREFERRED_MANY:
case MPOL_BIND:
/*
* Insist on a nodelist
*/
if (!nodelist)
goto out;
}
mode_flags = 0;
if (flags) {
/*
* Currently, we only support two mutually exclusive
* mode flags.
*/
if (!strcmp(flags, "static"))
mode_flags |= MPOL_F_STATIC_NODES;
else if (!strcmp(flags, "relative"))
mode_flags |= MPOL_F_RELATIVE_NODES;
else
goto out;
}
new = mpol_new(mode, mode_flags, &nodes);
if (IS_ERR(new))
goto out;
/*
* Save nodes for mpol_to_str() to show the tmpfs mount options
* for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
*/
if (mode != MPOL_PREFERRED) {
new->nodes = nodes;
} else if (nodelist) {
nodes_clear(new->nodes);
node_set(first_node(nodes), new->nodes);
} else {
new->mode = MPOL_LOCAL;
}
/*
* Save nodes for contextualization: this will be used to "clone"
* the mempolicy in a specific context [cpuset] at a later time.
*/
new->w.user_nodemask = nodes;
err = 0;
out:
/* Restore string for error message */
if (nodelist)
*--nodelist = ':';
if (flags)
*--flags = '=';
if (!err)
*mpol = new;
return err;
}
#endif /* CONFIG_TMPFS */
/**
* mpol_to_str - format a mempolicy structure for printing
* @buffer: to contain formatted mempolicy string
* @maxlen: length of @buffer
* @pol: pointer to mempolicy to be formatted
*
* Convert @pol into a string. If @buffer is too short, truncate the string.
* Recommend a @maxlen of at least 51 for the longest mode, "weighted
* interleave", plus the longest flag flags, "relative|balancing", and to
* display at least a few node ids.
*/
void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
char *p = buffer;
nodemask_t nodes = NODE_MASK_NONE;
unsigned short mode = MPOL_DEFAULT;
unsigned short flags = 0;
if (pol &&
pol != &default_policy &&
!(pol >= &preferred_node_policy[0] &&
pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) {
mode = pol->mode;
flags = pol->flags;
}
switch (mode) {
case MPOL_DEFAULT:
case MPOL_LOCAL:
break;
case MPOL_PREFERRED:
case MPOL_PREFERRED_MANY:
case MPOL_BIND:
case MPOL_INTERLEAVE:
case MPOL_WEIGHTED_INTERLEAVE:
nodes = pol->nodes;
break;
default:
WARN_ON_ONCE(1);
snprintf(p, maxlen, "unknown");
return;
}
p += snprintf(p, maxlen, "%s", policy_modes[mode]);
if (flags & MPOL_MODE_FLAGS) {
p += snprintf(p, buffer + maxlen - p, "=");
/*
* Static and relative are mutually exclusive.
*/
if (flags & MPOL_F_STATIC_NODES)
p += snprintf(p, buffer + maxlen - p, "static");
else if (flags & MPOL_F_RELATIVE_NODES)
p += snprintf(p, buffer + maxlen - p, "relative");
if (flags & MPOL_F_NUMA_BALANCING) {
if (!is_power_of_2(flags & MPOL_MODE_FLAGS))
p += snprintf(p, buffer + maxlen - p, "|");
p += snprintf(p, buffer + maxlen - p, "balancing");
}
}
if (!nodes_empty(nodes))
p += scnprintf(p, buffer + maxlen - p, ":%*pbl",
nodemask_pr_args(&nodes));
}
#ifdef CONFIG_SYSFS
struct iw_node_attr {
struct kobj_attribute kobj_attr;
int nid;
};
static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
struct iw_node_attr *node_attr;
u8 weight;
node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
weight = get_il_weight(node_attr->nid);
return sysfs_emit(buf, "%d\n", weight);
}
static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t count)
{
struct iw_node_attr *node_attr;
u8 *new;
u8 *old;
u8 weight = 0;
node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
if (count == 0 || sysfs_streq(buf, ""))
weight = 0;
else if (kstrtou8(buf, 0, &weight))
return -EINVAL;
new = kzalloc(nr_node_ids, GFP_KERNEL);
if (!new)
return -ENOMEM;
mutex_lock(&iw_table_lock);
old = rcu_dereference_protected(iw_table,
lockdep_is_held(&iw_table_lock));
if (old)
memcpy(new, old, nr_node_ids);
new[node_attr->nid] = weight;
rcu_assign_pointer(iw_table, new);
mutex_unlock(&iw_table_lock);
synchronize_rcu();
kfree(old);
return count;
}
static struct iw_node_attr **node_attrs;
static void sysfs_wi_node_release(struct iw_node_attr *node_attr,
struct kobject *parent)
{
if (!node_attr)
return;
sysfs_remove_file(parent, &node_attr->kobj_attr.attr);
kfree(node_attr->kobj_attr.attr.name);
kfree(node_attr);
}
static void sysfs_wi_release(struct kobject *wi_kobj)
{
int i;
for (i = 0; i < nr_node_ids; i++)
sysfs_wi_node_release(node_attrs[i], wi_kobj);
kobject_put(wi_kobj);
}
static const struct kobj_type wi_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = sysfs_wi_release,
};
static int add_weight_node(int nid, struct kobject *wi_kobj)
{
struct iw_node_attr *node_attr;
char *name;
node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL);
if (!node_attr)
return -ENOMEM;
name = kasprintf(GFP_KERNEL, "node%d", nid);
if (!name) {
kfree(node_attr);
return -ENOMEM;
}
sysfs_attr_init(&node_attr->kobj_attr.attr);
node_attr->kobj_attr.attr.name = name;
node_attr->kobj_attr.attr.mode = 0644;
node_attr->kobj_attr.show = node_show;
node_attr->kobj_attr.store = node_store;
node_attr->nid = nid;
if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) {
kfree(node_attr->kobj_attr.attr.name);
kfree(node_attr);
pr_err("failed to add attribute to weighted_interleave\n");
return -ENOMEM;
}
node_attrs[nid] = node_attr;
return 0;
}
static int add_weighted_interleave_group(struct kobject *root_kobj)
{
struct kobject *wi_kobj;
int nid, err;
wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
if (!wi_kobj)
return -ENOMEM;
err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj,
"weighted_interleave");
if (err) {
kfree(wi_kobj);
return err;
}
for_each_node_state(nid, N_POSSIBLE) {
err = add_weight_node(nid, wi_kobj);
if (err) {
pr_err("failed to add sysfs [node%d]\n", nid);
break;
}
}
if (err)
kobject_put(wi_kobj);
return 0;
}
static void mempolicy_kobj_release(struct kobject *kobj)
{
u8 *old;
mutex_lock(&iw_table_lock);
old = rcu_dereference_protected(iw_table,
lockdep_is_held(&iw_table_lock));
rcu_assign_pointer(iw_table, NULL);
mutex_unlock(&iw_table_lock);
synchronize_rcu();
kfree(old);
kfree(node_attrs);
kfree(kobj);
}
static const struct kobj_type mempolicy_ktype = {
.release = mempolicy_kobj_release
};
static int __init mempolicy_sysfs_init(void)
{
int err;
static struct kobject *mempolicy_kobj;
mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL);
if (!mempolicy_kobj) {
err = -ENOMEM;
goto err_out;
}
node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *),
GFP_KERNEL);
if (!node_attrs) {
err = -ENOMEM;
goto mempol_out;
}
err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj,
"mempolicy");
if (err)
goto node_out;
err = add_weighted_interleave_group(mempolicy_kobj);
if (err) {
pr_err("mempolicy sysfs structure failed to initialize\n");
kobject_put(mempolicy_kobj);
return err;
}
return err;
node_out:
kfree(node_attrs);
mempol_out:
kfree(mempolicy_kobj);
err_out:
pr_err("failed to add mempolicy kobject to the system\n");
return err;
}
late_initcall(mempolicy_sysfs_init);
#endif /* CONFIG_SYSFS */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/init.c
*
* Copyright (C) 1995-2005 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/cache.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
#include <linux/gfp.h>
#include <linux/math.h>
#include <linux/memblock.h>
#include <linux/sort.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/hugetlb.h>
#include <linux/acpi_iort.h>
#include <linux/kmemleak.h>
#include <linux/execmem.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
#include <asm/kvm_host.h>
#include <asm/memory.h>
#include <asm/numa.h>
#include <asm/rsi.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <linux/sizes.h>
#include <asm/tlb.h>
#include <asm/alternative.h>
#include <asm/xen/swiotlb-xen.h>
/*
* We need to be able to catch inadvertent references to memstart_addr
* that occur (potentially in generic code) before arm64_memblock_init()
* executes, which assigns it its actual value. So use a default value
* that cannot be mistaken for a real physical address.
*/
s64 memstart_addr __ro_after_init = -1;
EXPORT_SYMBOL(memstart_addr);
/*
* If the corresponding config options are enabled, we create both ZONE_DMA
* and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
* unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
* In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
* otherwise it is empty.
*/
phys_addr_t __ro_after_init arm64_dma_phys_limit;
/*
* To make optimal use of block mappings when laying out the linear
* mapping, round down the base of physical memory to a size that can
* be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE
* (64k granule), or a multiple that can be mapped using contiguous bits
* in the page tables: 32 * PMD_SIZE (16k granule)
*/
#if defined(CONFIG_ARM64_4K_PAGES)
#define ARM64_MEMSTART_SHIFT PUD_SHIFT
#elif defined(CONFIG_ARM64_16K_PAGES)
#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT
#else
#define ARM64_MEMSTART_SHIFT PMD_SHIFT
#endif
/*
* sparsemem vmemmap imposes an additional requirement on the alignment of
* memstart_addr, due to the fact that the base of the vmemmap region
* has a direct correspondence, and needs to appear sufficiently aligned
* in the virtual address space.
*/
#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS
#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS)
#else
#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT)
#endif
static void __init arch_reserve_crashkernel(void)
{
unsigned long long low_size = 0;
unsigned long long crash_base, crash_size;
bool high = false;
int ret;
if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
return;
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base,
&low_size, &high);
if (ret)
return;
reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
}
static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
{
return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;
}
static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
phys_addr_t __maybe_unused acpi_zone_dma_limit;
phys_addr_t __maybe_unused dt_zone_dma_limit;
phys_addr_t __maybe_unused dma32_phys_limit =
max_zone_phys(DMA_BIT_MASK(32));
#ifdef CONFIG_ZONE_DMA
acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
/*
* Information we get from firmware (e.g. DT dma-ranges) describe DMA
* bus constraints. Devices using DMA might have their own limitations.
* Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
* DMA zone on platforms that have RAM there.
*/
if (memblock_start_of_DRAM() < U32_MAX)
zone_dma_limit = min(zone_dma_limit, U32_MAX);
arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
if (!arm64_dma_phys_limit)
arm64_dma_phys_limit = dma32_phys_limit;
#endif
if (!arm64_dma_phys_limit)
arm64_dma_phys_limit = PHYS_MASK + 1;
max_zone_pfns[ZONE_NORMAL] = max_pfn;
free_area_init(max_zone_pfns);
}
int pfn_is_map_memory(unsigned long pfn)
{ phys_addr_t addr = PFN_PHYS(pfn);
/* avoid false positives for bogus PFNs, see comment in pfn_valid() */
if (PHYS_PFN(addr) != pfn)
return 0;
return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_is_map_memory);
static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX;
/*
* Limit the memory size that was specified via FDT.
*/
static int __init early_mem(char *p)
{
if (!p)
return 1;
memory_limit = memparse(p, &p) & PAGE_MASK;
pr_notice("Memory limited to %lldMB\n", memory_limit >> 20);
return 0;
}
early_param("mem", early_mem);
void __init arm64_memblock_init(void)
{
s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);
/*
* Corner case: 52-bit VA capable systems running KVM in nVHE mode may
* be limited in their ability to support a linear map that exceeds 51
* bits of VA space, depending on the placement of the ID map. Given
* that the placement of the ID map may be randomized, let's simply
* limit the kernel's linear map to 51 bits as well if we detect this
* configuration.
*/
if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 &&
is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n");
linear_region_size = min_t(u64, linear_region_size, BIT(51));
}
/* Remove memory above our supported physical address size */
memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
/*
* Select a suitable value for the base of physical memory.
*/
memstart_addr = round_down(memblock_start_of_DRAM(),
ARM64_MEMSTART_ALIGN);
if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size)
pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n");
/*
* Remove the memory that we will not be able to cover with the
* linear mapping. Take care not to clip the kernel which may be
* high in memory.
*/
memblock_remove(max_t(u64, memstart_addr + linear_region_size,
__pa_symbol(_end)), ULLONG_MAX);
if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
/* ensure that memstart_addr remains sufficiently aligned */
memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
ARM64_MEMSTART_ALIGN);
memblock_remove(0, memstart_addr);
}
/*
* If we are running with a 52-bit kernel VA config on a system that
* does not support it, we have to place the available physical
* memory in the 48-bit addressable part of the linear region, i.e.,
* we have to move it upward. Since memstart_addr represents the
* physical address of PAGE_OFFSET, we have to *subtract* from it.
*/
if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52);
/*
* Apply the memory limit if it was set. Since the kernel may be loaded
* high up in memory, add back the kernel region that must be accessible
* via the linear mapping.
*/
if (memory_limit != PHYS_ADDR_MAX) {
memblock_mem_limit_remove_map(memory_limit);
memblock_add(__pa_symbol(_text), (u64)(_end - _text));
}
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
/*
* Add back the memory we just removed if it results in the
* initrd to become inaccessible via the linear mapping.
* Otherwise, this is a no-op
*/
u64 base = phys_initrd_start & PAGE_MASK;
u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
/*
* We can only add back the initrd memory if we don't end up
* with more memory than we can address via the linear mapping.
* It is up to the bootloader to position the kernel and the
* initrd reasonably close to each other (i.e., within 32 GB of
* each other) so that all granule/#levels combinations can
* always access both.
*/
if (WARN(base < memblock_start_of_DRAM() ||
base + size > memblock_start_of_DRAM() +
linear_region_size,
"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
phys_initrd_size = 0;
} else {
memblock_add(base, size);
memblock_clear_nomap(base, size);
memblock_reserve(base, size);
}
}
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
extern u16 memstart_offset_seed;
u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
int parange = cpuid_feature_extract_unsigned_field(
mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
s64 range = linear_region_size -
BIT(id_aa64mmfr0_parange_to_phys_shift(parange));
/*
* If the size of the linear region exceeds, by a sufficient
* margin, the size of the region that the physical memory can
* span, randomize the linear region as well.
*/
if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) {
range /= ARM64_MEMSTART_ALIGN;
memstart_addr -= ARM64_MEMSTART_ALIGN *
((range * memstart_offset_seed) >> 16);
}
}
/*
* Register the kernel text, kernel data, initrd, and initial
* pagetables with memblock.
*/
memblock_reserve(__pa_symbol(_stext), _end - _stext);
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
/* the generic initrd code expects virtual addresses */
initrd_start = __phys_to_virt(phys_initrd_start);
initrd_end = initrd_start + phys_initrd_size;
}
early_init_fdt_scan_reserved_mem();
}
void __init bootmem_init(void)
{
unsigned long min, max;
min = PFN_UP(memblock_start_of_DRAM());
max = PFN_DOWN(memblock_end_of_DRAM());
early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
max_pfn = max_low_pfn = max;
min_low_pfn = min;
arch_numa_init();
/*
* must be done after arch_numa_init() which calls numa_init() to
* initialize node_online_map that gets used in hugetlb_cma_reserve()
* while allocating required CMA size across online nodes.
*/
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
arm64_hugetlb_cma_reserve();
#endif
kvm_hyp_reserve();
/*
* sparse_init() tries to allocate memory from memblock, so must be
* done after the fixed reservations
*/
sparse_init();
zone_sizes_init();
/*
* Reserve the CMA area after arm64_dma_phys_limit was initialised.
*/
dma_contiguous_reserve(arm64_dma_phys_limit);
/*
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
*/
arch_reserve_crashkernel();
memblock_dump_all();
}
void __init arch_mm_preinit(void)
{
unsigned int flags = SWIOTLB_VERBOSE;
bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
if (is_realm_world()) {
swiotlb = true;
flags |= SWIOTLB_FORCE;
}
if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) {
/*
* If no bouncing needed for ZONE_DMA, reduce the swiotlb
* buffer for kmalloc() bouncing to 1MB per 1GB of RAM.
*/
unsigned long size =
DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
swiotlb = true;
}
swiotlb_init(swiotlb, flags);
swiotlb_update_mem_attributes();
/*
* Check boundaries twice: Some fundamental inconsistencies can be
* detected at build time already.
*/
#ifdef CONFIG_COMPAT
BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
#endif
/*
* Selected page table levels should match when derived from
* scratch using the virtual address range and page size.
*/
BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) !=
CONFIG_PGTABLE_LEVELS);
if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
extern int sysctl_overcommit_memory;
/*
* On a machine this small we won't get anywhere without
* overcommit, so turn it on by default.
*/
sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
}
}
void free_initmem(void)
{
void *lm_init_begin = lm_alias(__init_begin);
void *lm_init_end = lm_alias(__init_end);
WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE));
WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE));
/* Delete __init region from memblock.reserved. */
memblock_free(lm_init_begin, lm_init_end - lm_init_begin);
free_reserved_area(lm_init_begin, lm_init_end,
POISON_FREE_INITMEM, "unused kernel");
/*
* Unmap the __init region but leave the VM area in place. This
* prevents the region from being reused for kernel modules, which
* is not supported by kallsyms.
*/
vunmap_range((u64)__init_begin, (u64)__init_end);
}
void dump_mem_limit(void)
{
if (memory_limit != PHYS_ADDR_MAX) {
pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
} else {
pr_emerg("Memory Limit: none\n");
}
}
#ifdef CONFIG_EXECMEM
static u64 module_direct_base __ro_after_init = 0;
static u64 module_plt_base __ro_after_init = 0;
/*
* Choose a random page-aligned base address for a window of 'size' bytes which
* entirely contains the interval [start, end - 1].
*/
static u64 __init random_bounding_box(u64 size, u64 start, u64 end)
{
u64 max_pgoff, pgoff;
if ((end - start) >= size)
return 0;
max_pgoff = (size - (end - start)) / PAGE_SIZE;
pgoff = get_random_u32_inclusive(0, max_pgoff);
return start - pgoff * PAGE_SIZE;
}
/*
* Modules may directly reference data and text anywhere within the kernel
* image and other modules. References using PREL32 relocations have a +/-2G
* range, and so we need to ensure that the entire kernel image and all modules
* fall within a 2G window such that these are always within range.
*
* Modules may directly branch to functions and code within the kernel text,
* and to functions and code within other modules. These branches will use
* CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure
* that the entire kernel text and all module text falls within a 128M window
* such that these are always within range. With PLTs, we can expand this to a
* 2G window.
*
* We chose the 128M region to surround the entire kernel image (rather than
* just the text) as using the same bounds for the 128M and 2G regions ensures
* by construction that we never select a 128M region that is not a subset of
* the 2G region. For very large and unusual kernel configurations this means
* we may fall back to PLTs where they could have been avoided, but this keeps
* the logic significantly simpler.
*/
static int __init module_init_limits(void)
{
u64 kernel_end = (u64)_end;
u64 kernel_start = (u64)_text;
u64 kernel_size = kernel_end - kernel_start;
/*
* The default modules region is placed immediately below the kernel
* image, and is large enough to use the full 2G relocation range.
*/
BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END);
BUILD_BUG_ON(MODULES_VSIZE < SZ_2G);
if (!kaslr_enabled()) {
if (kernel_size < SZ_128M)
module_direct_base = kernel_end - SZ_128M;
if (kernel_size < SZ_2G)
module_plt_base = kernel_end - SZ_2G;
} else {
u64 min = kernel_start;
u64 max = kernel_end;
if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) {
pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n");
} else {
module_direct_base = random_bounding_box(SZ_128M, min, max);
if (module_direct_base) {
min = module_direct_base;
max = module_direct_base + SZ_128M;
}
}
module_plt_base = random_bounding_box(SZ_2G, min, max);
}
pr_info("%llu pages in range for non-PLT usage",
module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0);
pr_info("%llu pages in range for PLT usage",
module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0);
return 0;
}
static struct execmem_info execmem_info __ro_after_init;
struct execmem_info __init *execmem_arch_setup(void)
{
unsigned long fallback_start = 0, fallback_end = 0;
unsigned long start = 0, end = 0;
module_init_limits();
/*
* Where possible, prefer to allocate within direct branch range of the
* kernel such that no PLTs are necessary.
*/
if (module_direct_base) {
start = module_direct_base;
end = module_direct_base + SZ_128M;
if (module_plt_base) {
fallback_start = module_plt_base;
fallback_end = module_plt_base + SZ_2G;
}
} else if (module_plt_base) {
start = module_plt_base;
end = module_plt_base + SZ_2G;
}
execmem_info = (struct execmem_info){
.ranges = {
[EXECMEM_DEFAULT] = {
.start = start,
.end = end,
.pgprot = PAGE_KERNEL,
.alignment = 1,
.fallback_start = fallback_start,
.fallback_end = fallback_end,
},
[EXECMEM_KPROBES] = {
.start = VMALLOC_START,
.end = VMALLOC_END,
.pgprot = PAGE_KERNEL_ROX,
.alignment = 1,
},
[EXECMEM_BPF] = {
.start = VMALLOC_START,
.end = VMALLOC_END,
.pgprot = PAGE_KERNEL,
.alignment = 1,
},
},
};
return &execmem_info;
}
#endif /* CONFIG_EXECMEM */
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_address.h>
#include <linux/of_iommu.h>
#include <linux/of_reserved_mem.h>
#include <linux/dma-direct.h> /* for bus_dma_region */
#include <linux/dma-map-ops.h>
#include <linux/init.h>
#include <linux/mod_devicetable.h>
#include <linux/slab.h>
#include <linux/platform_device.h>
#include <asm/errno.h>
#include "of_private.h"
/**
* of_match_device - Tell if a struct device matches an of_device_id list
* @matches: array of of device match structures to search in
* @dev: the of device structure to match against
*
* Used by a driver to check whether an platform_device present in the
* system is in its list of supported devices.
*/
const struct of_device_id *of_match_device(const struct of_device_id *matches,
const struct device *dev)
{
if (!matches || !dev->of_node || dev->of_node_reused)
return NULL;
return of_match_node(matches, dev->of_node);
}
EXPORT_SYMBOL(of_match_device);
static void
of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
{
struct device_node *node, *of_node = dev->of_node;
int count, i;
if (!IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL))
return;
count = of_property_count_elems_of_size(of_node, "memory-region",
sizeof(u32));
/*
* If dev->of_node doesn't exist or doesn't contain memory-region, try
* the OF node having DMA configuration.
*/
if (count <= 0) {
of_node = np;
count = of_property_count_elems_of_size(
of_node, "memory-region", sizeof(u32));
}
for (i = 0; i < count; i++) {
node = of_parse_phandle(of_node, "memory-region", i);
/*
* There might be multiple memory regions, but only one
* restricted-dma-pool region is allowed.
*/
if (of_device_is_compatible(node, "restricted-dma-pool") &&
of_device_is_available(node)) {
of_node_put(node);
break;
}
of_node_put(node);
}
/*
* Attempt to initialize a restricted-dma-pool region if one was found.
* Note that count can hold a negative error code.
*/
if (i < count && of_reserved_mem_device_init_by_idx(dev, of_node, i))
dev_warn(dev, "failed to initialise \"restricted-dma-pool\" memory node\n");
}
/**
* of_dma_configure_id - Setup DMA configuration
* @dev: Device to apply DMA configuration
* @np: Pointer to OF node having DMA configuration
* @force_dma: Whether device is to be set up by of_dma_configure() even if
* DMA capability is not explicitly described by firmware.
* @id: Optional const pointer value input id
*
* Try to get devices's DMA configuration from DT and update it
* accordingly.
*
* If platform code needs to use its own special DMA configuration, it
* can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
* to fix up DMA configuration.
*/
int of_dma_configure_id(struct device *dev, struct device_node *np,
bool force_dma, const u32 *id)
{
const struct bus_dma_region *map = NULL;
struct device_node *bus_np;
u64 mask, end = 0;
bool coherent, set_map = false;
int ret;
if (dev->dma_range_map) {
dev_dbg(dev, "dma_range_map already set\n");
goto skip_map;
}
if (np == dev->of_node)
bus_np = __of_get_dma_parent(np);
else
bus_np = of_node_get(np);
ret = of_dma_get_range(bus_np, &map);
of_node_put(bus_np);
if (ret < 0) {
/*
* For legacy reasons, we have to assume some devices need
* DMA configuration regardless of whether "dma-ranges" is
* correctly specified or not.
*/
if (!force_dma)
return ret == -ENODEV ? 0 : ret;
} else {
/* Determine the overall bounds of all DMA regions */
end = dma_range_map_max(map);
set_map = true;
}
skip_map:
/*
* If @dev is expected to be DMA-capable then the bus code that created
* it should have initialised its dma_mask pointer by this point. For
* now, we'll continue the legacy behaviour of coercing it to the
* coherent mask if not, but we'll no longer do so quietly.
*/
if (!dev->dma_mask) {
dev_warn(dev, "DMA mask not set\n");
dev->dma_mask = &dev->coherent_dma_mask;
}
if (!end && dev->coherent_dma_mask)
end = dev->coherent_dma_mask;
else if (!end)
end = (1ULL << 32) - 1;
/*
* Limit coherent and dma mask based on size and default mask
* set by the driver.
*/
mask = DMA_BIT_MASK(ilog2(end) + 1);
dev->coherent_dma_mask &= mask;
*dev->dma_mask &= mask;
/* ...but only set bus limit and range map if we found valid dma-ranges earlier */
if (set_map) {
dev->bus_dma_limit = end;
dev->dma_range_map = map;
}
coherent = of_dma_is_coherent(np);
dev_dbg(dev, "device is%sdma coherent\n",
coherent ? " " : " not ");
ret = of_iommu_configure(dev, np, id);
if (ret == -EPROBE_DEFER) {
/* Don't touch range map if it wasn't set from a valid dma-ranges */
if (set_map)
dev->dma_range_map = NULL;
kfree(map);
return -EPROBE_DEFER;
}
/* Take all other IOMMU errors to mean we'll just carry on without it */
dev_dbg(dev, "device is%sbehind an iommu\n",
!ret ? " " : " not ");
arch_setup_dma_ops(dev, coherent);
if (ret)
of_dma_set_restricted_buffer(dev, np);
return 0;
}
EXPORT_SYMBOL_GPL(of_dma_configure_id);
const void *of_device_get_match_data(const struct device *dev)
{
const struct of_device_id *match;
match = of_match_device(dev->driver->of_match_table, dev);
if (!match)
return NULL;
return match->data;
}
EXPORT_SYMBOL(of_device_get_match_data);
/**
* of_device_modalias - Fill buffer with newline terminated modalias string
* @dev: Calling device
* @str: Modalias string
* @len: Size of @str
*/
ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len)
{
ssize_t sl;
if (!dev || !dev->of_node || dev->of_node_reused)
return -ENODEV;
sl = of_modalias(dev->of_node, str, len - 2);
if (sl < 0)
return sl;
if (sl > len - 2)
return -ENOMEM;
str[sl++] = '\n';
str[sl] = 0;
return sl;
}
EXPORT_SYMBOL_GPL(of_device_modalias);
/**
* of_device_uevent - Display OF related uevent information
* @dev: Device to display the uevent information for
* @env: Kernel object's userspace event reference to fill up
*/
void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env)
{
const char *compat, *type;
struct alias_prop *app;
struct property *p;
int seen = 0;
if ((!dev) || (!dev->of_node))
return;
add_uevent_var(env, "OF_NAME=%pOFn", dev->of_node);
add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node);
type = of_node_get_device_type(dev->of_node);
if (type) add_uevent_var(env, "OF_TYPE=%s", type);
/* Since the compatible field can contain pretty much anything
* it's not really legal to split it out with commas. We split it
* up using a number of environment variables instead. */
of_property_for_each_string(dev->of_node, "compatible", p, compat) {
add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat);
seen++;
}
add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen);
seen = 0;
mutex_lock(&of_mutex);
list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) {
add_uevent_var(env, "OF_ALIAS_%d=%s", seen,
app->alias);
seen++;
}
}
mutex_unlock(&of_mutex);
}
EXPORT_SYMBOL_GPL(of_device_uevent);
int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env)
{
int sl;
if ((!dev) || (!dev->of_node) || dev->of_node_reused)
return -ENODEV;
/* Devicetree modalias is tricky, we add it in 2 steps */
if (add_uevent_var(env, "MODALIAS="))
return -ENOMEM;
sl = of_modalias(dev->of_node, &env->buf[env->buflen-1],
sizeof(env->buf) - env->buflen);
if (sl < 0)
return sl;
if (sl >= (sizeof(env->buf) - env->buflen))
return -ENOMEM;
env->buflen += sl;
return 0;
}
EXPORT_SYMBOL_GPL(of_device_uevent_modalias);
/**
* of_device_make_bus_id - Use the device node data to assign a unique name
* @dev: pointer to device structure that is linked to a device tree node
*
* This routine will first try using the translated bus address to
* derive a unique name. If it cannot, then it will prepend names from
* parent nodes until a unique name can be derived.
*/
void of_device_make_bus_id(struct device *dev)
{
struct device_node *node = dev->of_node;
const __be32 *reg;
u64 addr;
u32 mask;
/* Construct the name, using parent nodes if necessary to ensure uniqueness */
while (node->parent) {
/*
* If the address can be translated, then that is as much
* uniqueness as we need. Make it the first component and return
*/
reg = of_get_property(node, "reg", NULL);
if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
if (!of_property_read_u32(node, "mask", &mask))
dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
addr, ffs(mask) - 1, node, dev_name(dev));
else
dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
addr, node, dev_name(dev));
return;
}
/* format arguments only used if dev_name() resolves to NULL */
dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
kbasename(node->full_name), dev_name(dev));
node = node->parent;
}
}
EXPORT_SYMBOL_GPL(of_device_make_bus_id);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_ERR_H
#define _LINUX_ERR_H
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/errno.h>
/*
* Kernel pointers have redundant information, so we can use a
* scheme where we can return either an error code or a normal
* pointer with the same return value.
*
* This should be a per-architecture thing, to allow different
* error and pointer decisions.
*/
#define MAX_ERRNO 4095
#ifndef __ASSEMBLY__
/**
* IS_ERR_VALUE - Detect an error pointer.
* @x: The pointer to check.
*
* Like IS_ERR(), but does not generate a compiler warning if result is unused.
*/
#define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)
/**
* ERR_PTR - Create an error pointer.
* @error: A negative error code.
*
* Encodes @error into a pointer value. Users should consider the result
* opaque and not assume anything about how the error is encoded.
*
* Return: A pointer with @error encoded within its value.
*/
static inline void * __must_check ERR_PTR(long error)
{
return (void *) error;
}
/* Return the pointer in the percpu address space. */
#define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error))
/* Cast an error pointer to __iomem. */
#define IOMEM_ERR_PTR(error) (__force void __iomem *)ERR_PTR(error)
/**
* PTR_ERR - Extract the error code from an error pointer.
* @ptr: An error pointer.
* Return: The error code within @ptr.
*/
static inline long __must_check PTR_ERR(__force const void *ptr)
{
return (long) ptr;
}
/* Read an error pointer from the percpu address space. */
#define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr)))
/**
* IS_ERR - Detect an error pointer.
* @ptr: The pointer to check.
* Return: true if @ptr is an error pointer, false otherwise.
*/
static inline bool __must_check IS_ERR(__force const void *ptr)
{
return IS_ERR_VALUE((unsigned long)ptr);
}
/* Read an error pointer from the percpu address space. */
#define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr)))
/**
* IS_ERR_OR_NULL - Detect an error pointer or a null pointer.
* @ptr: The pointer to check.
*
* Like IS_ERR(), but also returns true for a null pointer.
*/
static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
{
return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
}
/**
* ERR_CAST - Explicitly cast an error-valued pointer to another pointer type
* @ptr: The pointer to cast.
*
* Explicitly cast an error-valued pointer to another pointer type in such a
* way as to make it clear that's what's going on.
*/
static inline void * __must_check ERR_CAST(__force const void *ptr)
{
/* cast away the const */
return (void *) ptr;
}
/**
* PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one.
* @ptr: A potential error pointer.
*
* Convenience function that can be used inside a function that returns
* an error code to propagate errors received as error pointers.
* For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces:
*
* .. code-block:: c
*
* if (IS_ERR(ptr))
* return PTR_ERR(ptr);
* else
* return 0;
*
* Return: The error code within @ptr if it is an error pointer; 0 otherwise.
*/
static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
{
if (IS_ERR(ptr))
return PTR_ERR(ptr);
else
return 0;
}
#endif
#endif /* _LINUX_ERR_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SWAPOPS_H
#define _LINUX_SWAPOPS_H
#include <linux/radix-tree.h>
#include <linux/bug.h>
#include <linux/mm_types.h>
#ifdef CONFIG_MMU
#ifdef CONFIG_SWAP
#include <linux/swapfile.h>
#endif /* CONFIG_SWAP */
/*
* swapcache pages are stored in the swapper_space radix tree. We want to
* get good packing density in that tree, so the index should be dense in
* the low-order bits.
*
* We arrange the `type' and `offset' fields so that `type' is at the six
* high-order bits of the swp_entry_t and `offset' is right-aligned in the
* remaining bits. Although `type' itself needs only five bits, we allow for
* shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry().
*
* swp_entry_t's are *never* stored anywhere in their arch-dependent format.
*/
#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1)
/*
* Definitions only for PFN swap entries (see is_pfn_swap_entry()). To
* store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries
* can use the extra bits to store other information besides PFN.
*/
#ifdef MAX_PHYSMEM_BITS
#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
#else /* MAX_PHYSMEM_BITS */
#define SWP_PFN_BITS min_t(int, \
sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \
SWP_TYPE_SHIFT)
#endif /* MAX_PHYSMEM_BITS */
#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1)
/**
* Migration swap entry specific bitfield definitions. Layout:
*
* |----------+--------------------|
* | swp_type | swp_offset |
* |----------+--------+-+-+-------|
* | | resv |D|A| PFN |
* |----------+--------+-+-+-------|
*
* @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A)
* @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D)
*
* Note: A/D bits will be stored in migration entries iff there're enough
* free bits in arch specific swp offset. By default we'll ignore A/D bits
* when migrating a page. Please refer to migration_entry_supports_ad()
* for more information. If there're more bits besides PFN and A/D bits,
* they should be reserved and always be zeros.
*/
#define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS)
#define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1)
#define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2)
#define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT)
#define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT)
static inline bool is_pfn_swap_entry(swp_entry_t entry);
/* Clear all flags but only keep swp_entry_t related information */
static inline pte_t pte_swp_clear_flags(pte_t pte)
{
if (pte_swp_exclusive(pte))
pte = pte_swp_clear_exclusive(pte);
if (pte_swp_soft_dirty(pte))
pte = pte_swp_clear_soft_dirty(pte);
if (pte_swp_uffd_wp(pte))
pte = pte_swp_clear_uffd_wp(pte);
return pte;
}
/*
* Store a type+offset into a swp_entry_t in an arch-independent format
*/
static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
{
swp_entry_t ret;
ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK);
return ret;
}
/*
* Extract the `type' field from a swp_entry_t. The swp_entry_t is in
* arch-independent format
*/
static inline unsigned swp_type(swp_entry_t entry)
{
return (entry.val >> SWP_TYPE_SHIFT);
}
/*
* Extract the `offset' field from a swp_entry_t. The swp_entry_t is in
* arch-independent format
*/
static inline pgoff_t swp_offset(swp_entry_t entry)
{
return entry.val & SWP_OFFSET_MASK;
}
/*
* This should only be called upon a pfn swap entry to get the PFN stored
* in the swap entry. Please refers to is_pfn_swap_entry() for definition
* of pfn swap entry.
*/
static inline unsigned long swp_offset_pfn(swp_entry_t entry)
{
VM_BUG_ON(!is_pfn_swap_entry(entry));
return swp_offset(entry) & SWP_PFN_MASK;
}
/* check whether a pte points to a swap entry */
static inline int is_swap_pte(pte_t pte)
{
return !pte_none(pte) && !pte_present(pte);
}
/*
* Convert the arch-dependent pte representation of a swp_entry_t into an
* arch-independent swp_entry_t.
*/
static inline swp_entry_t pte_to_swp_entry(pte_t pte)
{
swp_entry_t arch_entry;
pte = pte_swp_clear_flags(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
/*
* Convert the arch-independent representation of a swp_entry_t into the
* arch-dependent pte representation.
*/
static inline pte_t swp_entry_to_pte(swp_entry_t entry)
{
swp_entry_t arch_entry;
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
return __swp_entry_to_pte(arch_entry);
}
static inline swp_entry_t radix_to_swp_entry(void *arg)
{
swp_entry_t entry;
entry.val = xa_to_value(arg);
return entry;
}
static inline void *swp_to_radix_entry(swp_entry_t entry)
{
return xa_mk_value(entry.val);
}
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
{
return swp_entry(SWP_DEVICE_READ, offset);
}
static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
{
return swp_entry(SWP_DEVICE_WRITE, offset);
}
static inline bool is_device_private_entry(swp_entry_t entry)
{
int type = swp_type(entry);
return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE;
}
static inline bool is_writable_device_private_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
}
static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset)
{
return swp_entry(SWP_DEVICE_EXCLUSIVE, offset);
}
static inline bool is_device_exclusive_entry(swp_entry_t entry)
{
return swp_type(entry) == SWP_DEVICE_EXCLUSIVE;
}
#else /* CONFIG_DEVICE_PRIVATE */
static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline bool is_device_private_entry(swp_entry_t entry)
{
return false;
}
static inline bool is_writable_device_private_entry(swp_entry_t entry)
{
return false;
}
static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline bool is_device_exclusive_entry(swp_entry_t entry)
{
return false;
}
#endif /* CONFIG_DEVICE_PRIVATE */
#ifdef CONFIG_MIGRATION
static inline int is_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE ||
swp_type(entry) == SWP_MIGRATION_WRITE);
}
static inline int is_writable_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
}
static inline int is_readable_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_READ);
}
static inline int is_readable_exclusive_migration_entry(swp_entry_t entry)
{
return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE);
}
static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
{
return swp_entry(SWP_MIGRATION_READ, offset);
}
static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
{
return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset);
}
static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
{
return swp_entry(SWP_MIGRATION_WRITE, offset);
}
/*
* Returns whether the host has large enough swap offset field to support
* carrying over pgtable A/D bits for page migrations. The result is
* pretty much arch specific.
*/
static inline bool migration_entry_supports_ad(void)
{
#ifdef CONFIG_SWAP
return swap_migration_ad_supported;
#else /* CONFIG_SWAP */
return false;
#endif /* CONFIG_SWAP */
}
static inline swp_entry_t make_migration_entry_young(swp_entry_t entry)
{
if (migration_entry_supports_ad())
return swp_entry(swp_type(entry),
swp_offset(entry) | SWP_MIG_YOUNG);
return entry;
}
static inline bool is_migration_entry_young(swp_entry_t entry)
{
if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG;
/* Keep the old behavior of aging page after migration */
return false;
}
static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry)
{
if (migration_entry_supports_ad())
return swp_entry(swp_type(entry),
swp_offset(entry) | SWP_MIG_DIRTY);
return entry;
}
static inline bool is_migration_entry_dirty(swp_entry_t entry)
{
if (migration_entry_supports_ad())
return swp_offset(entry) & SWP_MIG_DIRTY;
/* Keep the old behavior of clean page after migration */
return false;
}
extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address);
extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte);
#else /* CONFIG_MIGRATION */
static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
{
return swp_entry(0, 0);
}
static inline int is_migration_entry(swp_entry_t swp)
{
return 0;
}
static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
unsigned long address) { }
static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte) { }
static inline int is_writable_migration_entry(swp_entry_t entry)
{
return 0;
}
static inline int is_readable_migration_entry(swp_entry_t entry)
{
return 0;
}
static inline swp_entry_t make_migration_entry_young(swp_entry_t entry)
{
return entry;
}
static inline bool is_migration_entry_young(swp_entry_t entry)
{
return false;
}
static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry)
{
return entry;
}
static inline bool is_migration_entry_dirty(swp_entry_t entry)
{
return false;
}
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_MEMORY_FAILURE
/*
* Support for hardware poisoned pages
*/
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
BUG_ON(!PageLocked(page));
return swp_entry(SWP_HWPOISON, page_to_pfn(page));
}
static inline int is_hwpoison_entry(swp_entry_t entry)
{
return swp_type(entry) == SWP_HWPOISON;
}
#else
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
return swp_entry(0, 0);
}
static inline int is_hwpoison_entry(swp_entry_t swp)
{
return 0;
}
#endif
typedef unsigned long pte_marker;
#define PTE_MARKER_UFFD_WP BIT(0)
/*
* "Poisoned" here is meant in the very general sense of "future accesses are
* invalid", instead of referring very specifically to hardware memory errors.
* This marker is meant to represent any of various different causes of this.
*
* Note that, when encountered by the faulting logic, PTEs with this marker will
* result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error
* logic.
*/
#define PTE_MARKER_POISONED BIT(1)
/*
* Indicates that, on fault, this PTE will case a SIGSEGV signal to be
* sent. This means guard markers behave in effect as if the region were mapped
* PROT_NONE, rather than if they were a memory hole or equivalent.
*/
#define PTE_MARKER_GUARD BIT(2)
#define PTE_MARKER_MASK (BIT(3) - 1)
static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
{
return swp_entry(SWP_PTE_MARKER, marker);
}
static inline bool is_pte_marker_entry(swp_entry_t entry)
{
return swp_type(entry) == SWP_PTE_MARKER;
}
static inline pte_marker pte_marker_get(swp_entry_t entry)
{
return swp_offset(entry) & PTE_MARKER_MASK;
}
static inline bool is_pte_marker(pte_t pte)
{
return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte));
}
static inline pte_t make_pte_marker(pte_marker marker)
{
return swp_entry_to_pte(make_pte_marker_entry(marker));
}
static inline swp_entry_t make_poisoned_swp_entry(void)
{
return make_pte_marker_entry(PTE_MARKER_POISONED);
}
static inline int is_poisoned_swp_entry(swp_entry_t entry)
{
return is_pte_marker_entry(entry) &&
(pte_marker_get(entry) & PTE_MARKER_POISONED);
}
static inline swp_entry_t make_guard_swp_entry(void)
{
return make_pte_marker_entry(PTE_MARKER_GUARD);
}
static inline int is_guard_swp_entry(swp_entry_t entry)
{
return is_pte_marker_entry(entry) &&
(pte_marker_get(entry) & PTE_MARKER_GUARD);
}
/*
* This is a special version to check pte_none() just to cover the case when
* the pte is a pte marker. It existed because in many cases the pte marker
* should be seen as a none pte; it's just that we have stored some information
* onto the none pte so it becomes not-none any more.
*
* It should be used when the pte is file-backed, ram-based and backing
* userspace pages, like shmem. It is not needed upon pgtables that do not
* support pte markers at all. For example, it's not needed on anonymous
* memory, kernel-only memory (including when the system is during-boot),
* non-ram based generic file-system. It's fine to be used even there, but the
* extra pte marker check will be pure overhead.
*/
static inline int pte_none_mostly(pte_t pte)
{
return pte_none(pte) || is_pte_marker(pte);
}
static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
{
struct page *p = pfn_to_page(swp_offset_pfn(entry));
/*
* Any use of migration entries may only occur while the
* corresponding page is locked
*/
BUG_ON(is_migration_entry(entry) && !PageLocked(p));
return p;
}
static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry)
{
struct folio *folio = pfn_folio(swp_offset_pfn(entry));
/*
* Any use of migration entries may only occur while the
* corresponding folio is locked
*/
BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio));
return folio;
}
/*
* A pfn swap entry is a special type of swap entry that always has a pfn stored
* in the swap offset. They can either be used to represent unaddressable device
* memory, to restrict access to a page undergoing migration or to represent a
* pfn which has been hwpoisoned and unmapped.
*/
static inline bool is_pfn_swap_entry(swp_entry_t entry)
{
/* Make sure the swp offset can always store the needed fields */
BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
return is_migration_entry(entry) || is_device_private_entry(entry) ||
is_device_exclusive_entry(entry) || is_hwpoison_entry(entry);
}
struct page_vma_mapped_walk;
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
struct page *page);
extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
struct page *new);
extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd);
static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
{
swp_entry_t arch_entry;
if (pmd_swp_soft_dirty(pmd))
pmd = pmd_swp_clear_soft_dirty(pmd);
if (pmd_swp_uffd_wp(pmd))
pmd = pmd_swp_clear_uffd_wp(pmd);
arch_entry = __pmd_to_swp_entry(pmd);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
{
swp_entry_t arch_entry;
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
return __swp_entry_to_pmd(arch_entry);
}
static inline int is_pmd_migration_entry(pmd_t pmd)
{
return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
}
#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
struct page *page)
{
BUILD_BUG();
}
static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
struct page *new)
{
BUILD_BUG();
}
static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { }
static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
{
return swp_entry(0, 0);
}
static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
{
return __pmd(0);
}
static inline int is_pmd_migration_entry(pmd_t pmd)
{
return 0;
}
#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
static inline int non_swap_entry(swp_entry_t entry)
{
return swp_type(entry) >= MAX_SWAPFILES;
}
#endif /* CONFIG_MMU */
#endif /* _LINUX_SWAPOPS_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2016 Linaro
* Author: Christoffer Dall <christoffer.dall@linaro.org>
*/
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <linux/seq_file.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"
/*
* Structure to control looping through the entire vgic state. We start at
* zero for each field and move upwards. So, if dist_id is 0 we print the
* distributor info. When dist_id is 1, we have already printed it and move
* on.
*
* When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and
* so on.
*/
struct vgic_state_iter {
int nr_cpus;
int nr_spis;
int nr_lpis;
int dist_id;
int vcpu_id;
unsigned long intid;
int lpi_idx;
};
static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
{
struct vgic_dist *dist = &kvm->arch.vgic;
if (iter->dist_id == 0) {
iter->dist_id++;
return;
}
/*
* Let the xarray drive the iterator after the last SPI, as the iterator
* has exhausted the sequentially-allocated INTID space.
*/
if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) &&
iter->nr_lpis) {
if (iter->lpi_idx < iter->nr_lpis)
xa_find_after(&dist->lpi_xa, &iter->intid,
VGIC_LPI_MAX_INTID,
LPI_XA_MARK_DEBUG_ITER);
iter->lpi_idx++;
return;
}
iter->intid++;
if (iter->intid == VGIC_NR_PRIVATE_IRQS &&
++iter->vcpu_id < iter->nr_cpus)
iter->intid = 0;
}
static int iter_mark_lpis(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq;
unsigned long intid;
int nr_lpis = 0;
xa_for_each(&dist->lpi_xa, intid, irq) {
if (!vgic_try_get_irq_kref(irq))
continue;
xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
nr_lpis++;
}
return nr_lpis;
}
static void iter_unmark_lpis(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq;
unsigned long intid;
xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
vgic_put_irq(kvm, irq);
}
}
static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter,
loff_t pos)
{
int nr_cpus = atomic_read(&kvm->online_vcpus);
memset(iter, 0, sizeof(*iter));
iter->nr_cpus = nr_cpus;
iter->nr_spis = kvm->arch.vgic.nr_spis;
if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
iter->nr_lpis = iter_mark_lpis(kvm);
/* Fast forward to the right position if needed */
while (pos--)
iter_next(kvm, iter);
}
static bool end_of_vgic(struct vgic_state_iter *iter)
{
return iter->dist_id > 0 &&
iter->vcpu_id == iter->nr_cpus &&
iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) &&
(!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis);
}
static void *vgic_debug_start(struct seq_file *s, loff_t *pos)
{
struct kvm *kvm = s->private;
struct vgic_state_iter *iter;
mutex_lock(&kvm->arch.config_lock);
iter = kvm->arch.vgic.iter;
if (iter) {
iter = ERR_PTR(-EBUSY);
goto out;
}
iter = kmalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
iter = ERR_PTR(-ENOMEM);
goto out;
}
iter_init(kvm, iter, *pos);
kvm->arch.vgic.iter = iter;
if (end_of_vgic(iter))
iter = NULL;
out:
mutex_unlock(&kvm->arch.config_lock);
return iter;
}
static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
{
struct kvm *kvm = s->private;
struct vgic_state_iter *iter = kvm->arch.vgic.iter;
++*pos;
iter_next(kvm, iter);
if (end_of_vgic(iter))
iter = NULL;
return iter;
}
static void vgic_debug_stop(struct seq_file *s, void *v)
{
struct kvm *kvm = s->private;
struct vgic_state_iter *iter;
/*
* If the seq file wasn't properly opened, there's nothing to clearn
* up.
*/
if (IS_ERR(v))
return;
mutex_lock(&kvm->arch.config_lock);
iter = kvm->arch.vgic.iter;
iter_unmark_lpis(kvm);
kfree(iter);
kvm->arch.vgic.iter = NULL;
mutex_unlock(&kvm->arch.config_lock);
}
static void print_dist_state(struct seq_file *s, struct vgic_dist *dist,
struct vgic_state_iter *iter)
{
bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3;
seq_printf(s, "Distributor\n");
seq_printf(s, "===========\n");
seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2");
seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis);
if (v3)
seq_printf(s, "nr_lpis:\t%d\n", iter->nr_lpis);
seq_printf(s, "enabled:\t%d\n", dist->enabled);
seq_printf(s, "\n");
seq_printf(s, "P=pending_latch, L=line_level, A=active\n");
seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n");
seq_printf(s, "G=group\n");
}
static void print_header(struct seq_file *s, struct vgic_irq *irq,
struct kvm_vcpu *vcpu)
{
int id = 0;
char *hdr = "SPI ";
if (vcpu) {
hdr = "VCPU";
id = vcpu->vcpu_idx;
}
seq_printf(s, "\n");
seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id);
seq_printf(s, "----------------------------------------------------------------\n");
}
static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
struct kvm_vcpu *vcpu)
{
char *type;
bool pending;
if (irq->intid < VGIC_NR_SGIS)
type = "SGI";
else if (irq->intid < VGIC_NR_PRIVATE_IRQS)
type = "PPI";
else if (irq->intid < VGIC_MAX_SPI)
type = "SPI";
else
type = "LPI";
if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS)
print_header(s, irq, vcpu);
pending = irq->pending_latch;
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
int err;
err = irq_get_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
&pending);
WARN_ON_ONCE(err);
}
seq_printf(s, " %s %4d "
" %2d "
"%d%d%d%d%d%d%d "
"%8d "
"%8x "
" %2x "
"%3d "
" %2d "
"\n",
type, irq->intid,
(irq->target_vcpu) ? irq->target_vcpu->vcpu_idx : -1,
pending,
irq->line_level,
irq->active,
irq->enabled,
irq->hw,
irq->config == VGIC_CONFIG_LEVEL,
irq->group,
irq->hwintid,
irq->mpidr,
irq->source,
irq->priority,
(irq->vcpu) ? irq->vcpu->vcpu_idx : -1);
}
static int vgic_debug_show(struct seq_file *s, void *v)
{
struct kvm *kvm = s->private;
struct vgic_state_iter *iter = v;
struct vgic_irq *irq;
struct kvm_vcpu *vcpu = NULL;
unsigned long flags;
if (iter->dist_id == 0) {
print_dist_state(s, &kvm->arch.vgic, iter);
return 0;
}
if (!kvm->arch.vgic.initialized)
return 0;
if (iter->vcpu_id < iter->nr_cpus)
vcpu = kvm_get_vcpu(kvm, iter->vcpu_id);
/*
* Expect this to succeed, as iter_mark_lpis() takes a reference on
* every LPI to be visited.
*/
if (iter->intid < VGIC_NR_PRIVATE_IRQS)
irq = vgic_get_vcpu_irq(vcpu, iter->intid);
else
irq = vgic_get_irq(kvm, iter->intid);
if (WARN_ON_ONCE(!irq))
return -EINVAL;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
print_irq_state(s, irq, vcpu);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(kvm, irq);
return 0;
}
static const struct seq_operations vgic_debug_sops = {
.start = vgic_debug_start,
.next = vgic_debug_next,
.stop = vgic_debug_stop,
.show = vgic_debug_show
};
DEFINE_SEQ_ATTRIBUTE(vgic_debug);
void vgic_debug_init(struct kvm *kvm)
{
debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm,
&vgic_debug_fops);
}
void vgic_debug_destroy(struct kvm *kvm)
{
}
/**
* struct vgic_its_iter - Iterator for traversing VGIC ITS device tables.
* @dev: Pointer to the current its_device being processed.
* @ite: Pointer to the current its_ite within the device being processed.
*
* This structure is used to maintain the current position during iteration
* over the ITS device tables. It holds pointers to both the current device
* and the current ITE within that device.
*/
struct vgic_its_iter {
struct its_device *dev;
struct its_ite *ite;
};
/**
* end_of_iter - Checks if the iterator has reached the end.
* @iter: The iterator to check.
*
* When the iterator completed processing the final ITE in the last device
* table, it was marked to indicate the end of iteration by setting its
* device and ITE pointers to NULL.
* This function checks whether the iterator was marked as end.
*
* Return: True if the iterator is marked as end, false otherwise.
*/
static inline bool end_of_iter(struct vgic_its_iter *iter)
{
return !iter->dev && !iter->ite;
}
/**
* vgic_its_iter_next - Advances the iterator to the next entry in the ITS tables.
* @its: The VGIC ITS structure.
* @iter: The iterator to advance.
*
* This function moves the iterator to the next ITE within the current device,
* or to the first ITE of the next device if the current ITE is the last in
* the device. If the current device is the last device, the iterator is set
* to indicate the end of iteration.
*/
static void vgic_its_iter_next(struct vgic_its *its, struct vgic_its_iter *iter)
{
struct its_device *dev = iter->dev;
struct its_ite *ite = iter->ite;
if (!ite || list_is_last(&ite->ite_list, &dev->itt_head)) {
if (list_is_last(&dev->dev_list, &its->device_list)) {
dev = NULL;
ite = NULL;
} else {
dev = list_next_entry(dev, dev_list);
ite = list_first_entry_or_null(&dev->itt_head,
struct its_ite,
ite_list);
}
} else {
ite = list_next_entry(ite, ite_list);
}
iter->dev = dev;
iter->ite = ite;
}
/**
* vgic_its_debug_start - Start function for the seq_file interface.
* @s: The seq_file structure.
* @pos: The starting position (offset).
*
* This function initializes the iterator to the beginning of the ITS tables
* and advances it to the specified position. It acquires the its_lock mutex
* to protect shared data.
*
* Return: An iterator pointer on success, NULL if no devices are found or
* the end of the list is reached, or ERR_PTR(-ENOMEM) on memory
* allocation failure.
*/
static void *vgic_its_debug_start(struct seq_file *s, loff_t *pos)
{
struct vgic_its *its = s->private;
struct vgic_its_iter *iter;
struct its_device *dev;
loff_t offset = *pos;
mutex_lock(&its->its_lock);
dev = list_first_entry_or_null(&its->device_list,
struct its_device, dev_list);
if (!dev)
return NULL;
iter = kmalloc(sizeof(*iter), GFP_KERNEL);
if (!iter)
return ERR_PTR(-ENOMEM);
iter->dev = dev;
iter->ite = list_first_entry_or_null(&dev->itt_head,
struct its_ite, ite_list);
while (!end_of_iter(iter) && offset--)
vgic_its_iter_next(its, iter);
if (end_of_iter(iter)) {
kfree(iter);
return NULL;
}
return iter;
}
/**
* vgic_its_debug_next - Next function for the seq_file interface.
* @s: The seq_file structure.
* @v: The current iterator.
* @pos: The current position (offset).
*
* This function advances the iterator to the next entry and increments the
* position.
*
* Return: An iterator pointer on success, or NULL if the end of the list is
* reached.
*/
static void *vgic_its_debug_next(struct seq_file *s, void *v, loff_t *pos)
{
struct vgic_its *its = s->private;
struct vgic_its_iter *iter = v;
++*pos;
vgic_its_iter_next(its, iter);
if (end_of_iter(iter)) {
kfree(iter);
return NULL;
}
return iter;
}
/**
* vgic_its_debug_stop - Stop function for the seq_file interface.
* @s: The seq_file structure.
* @v: The current iterator.
*
* This function frees the iterator and releases the its_lock mutex.
*/
static void vgic_its_debug_stop(struct seq_file *s, void *v)
{
struct vgic_its *its = s->private;
struct vgic_its_iter *iter = v;
if (!IS_ERR_OR_NULL(iter))
kfree(iter);
mutex_unlock(&its->its_lock);
}
/**
* vgic_its_debug_show - Show function for the seq_file interface.
* @s: The seq_file structure.
* @v: The current iterator.
*
* This function formats and prints the ITS table entry information to the
* seq_file output.
*
* Return: 0 on success.
*/
static int vgic_its_debug_show(struct seq_file *s, void *v)
{
struct vgic_its_iter *iter = v;
struct its_device *dev = iter->dev;
struct its_ite *ite = iter->ite;
if (list_is_first(&ite->ite_list, &dev->itt_head)) {
seq_printf(s, "\n");
seq_printf(s, "Device ID: 0x%x, Event ID Range: [0 - %llu]\n",
dev->device_id, BIT_ULL(dev->num_eventid_bits) - 1);
seq_printf(s, "EVENT_ID INTID HWINTID TARGET COL_ID HW\n");
seq_printf(s, "-----------------------------------------------\n");
}
if (ite && ite->irq && ite->collection) {
seq_printf(s, "%8u %8u %8u %8u %8u %2d\n",
ite->event_id, ite->irq->intid, ite->irq->hwintid,
ite->collection->target_addr,
ite->collection->collection_id, ite->irq->hw);
}
return 0;
}
static const struct seq_operations vgic_its_debug_sops = {
.start = vgic_its_debug_start,
.next = vgic_its_debug_next,
.stop = vgic_its_debug_stop,
.show = vgic_its_debug_show
};
DEFINE_SEQ_ATTRIBUTE(vgic_its_debug);
/**
* vgic_its_debug_init - Initializes the debugfs interface for VGIC ITS.
* @dev: The KVM device structure.
*
* This function creates a debugfs file named "vgic-its-state@%its_base"
* to expose the ITS table information.
*
* Return: 0 on success.
*/
int vgic_its_debug_init(struct kvm_device *dev)
{
struct vgic_its *its = dev->private;
char *name;
name = kasprintf(GFP_KERNEL, "vgic-its-state@%llx", (u64)its->vgic_its_base);
if (!name)
return -ENOMEM;
debugfs_create_file(name, 0444, dev->kvm->debugfs_dentry, its, &vgic_its_debug_fops);
kfree(name);
return 0;
}
void vgic_its_debug_destroy(struct kvm_device *dev)
{
}
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* Credentials management - see Documentation/security/credentials.rst
*
* Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef _LINUX_CRED_H
#define _LINUX_CRED_H
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/key.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
#include <linux/uidgid.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
struct cred;
struct inode;
/*
* COW Supplementary groups list
*/
struct group_info {
refcount_t usage;
int ngroups;
kgid_t gid[];
} __randomize_layout;
/**
* get_group_info - Get a reference to a group info structure
* @group_info: The group info to reference
*
* This gets a reference to a set of supplementary groups.
*
* If the caller is accessing a task's credentials, they must hold the RCU read
* lock when reading.
*/
static inline struct group_info *get_group_info(struct group_info *gi)
{
refcount_inc(&gi->usage);
return gi;
}
/**
* put_group_info - Release a reference to a group info structure
* @group_info: The group info to release
*/
#define put_group_info(group_info) \
do { \
if (refcount_dec_and_test(&(group_info)->usage)) \
groups_free(group_info); \
} while (0)
#ifdef CONFIG_MULTIUSER
extern struct group_info *groups_alloc(int);
extern void groups_free(struct group_info *);
extern int in_group_p(kgid_t);
extern int in_egroup_p(kgid_t);
extern int groups_search(const struct group_info *, kgid_t);
extern int set_current_groups(struct group_info *);
extern void set_groups(struct cred *, struct group_info *);
extern bool may_setgroups(void);
extern void groups_sort(struct group_info *);
#else
static inline void groups_free(struct group_info *group_info)
{
}
static inline int in_group_p(kgid_t grp)
{
return 1;
}
static inline int in_egroup_p(kgid_t grp)
{
return 1;
}
static inline int groups_search(const struct group_info *group_info, kgid_t grp)
{
return 1;
}
#endif
/*
* The security context of a task
*
* The parts of the context break down into two categories:
*
* (1) The objective context of a task. These parts are used when some other
* task is attempting to affect this one.
*
* (2) The subjective context. These details are used when the task is acting
* upon another object, be that a file, a task, a key or whatever.
*
* Note that some members of this structure belong to both categories - the
* LSM security pointer for instance.
*
* A task has two security pointers. task->real_cred points to the objective
* context that defines that task's actual details. The objective part of this
* context is used whenever that task is acted upon.
*
* task->cred points to the subjective context that defines the details of how
* that task is going to act upon another object. This may be overridden
* temporarily to point to another security context, but normally points to the
* same context as task->real_cred.
*/
struct cred {
atomic_long_t usage;
kuid_t uid; /* real UID of the task */
kgid_t gid; /* real GID of the task */
kuid_t suid; /* saved UID of the task */
kgid_t sgid; /* saved GID of the task */
kuid_t euid; /* effective UID of the task */
kgid_t egid; /* effective GID of the task */
kuid_t fsuid; /* UID for VFS ops */
kgid_t fsgid; /* GID for VFS ops */
unsigned securebits; /* SUID-less security management */
kernel_cap_t cap_inheritable; /* caps our children can inherit */
kernel_cap_t cap_permitted; /* caps we're permitted */
kernel_cap_t cap_effective; /* caps we can actually use */
kernel_cap_t cap_bset; /* capability bounding set */
kernel_cap_t cap_ambient; /* Ambient capability set */
#ifdef CONFIG_KEYS
unsigned char jit_keyring; /* default keyring to attach requested
* keys to */
struct key *session_keyring; /* keyring inherited over fork */
struct key *process_keyring; /* keyring private to this process */
struct key *thread_keyring; /* keyring private to this thread */
struct key *request_key_auth; /* assumed request_key authority */
#endif
#ifdef CONFIG_SECURITY
void *security; /* LSM security */
#endif
struct user_struct *user; /* real user ID subscription */
struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
struct ucounts *ucounts;
struct group_info *group_info; /* supplementary groups for euid/fsgid */
/* RCU deletion */
union {
int non_rcu; /* Can we skip RCU deletion? */
struct rcu_head rcu; /* RCU deletion hook */
};
} __randomize_layout;
extern void __put_cred(struct cred *);
extern void exit_creds(struct task_struct *);
extern int copy_creds(struct task_struct *, unsigned long);
extern const struct cred *get_task_cred(struct task_struct *);
extern struct cred *cred_alloc_blank(void);
extern struct cred *prepare_creds(void);
extern struct cred *prepare_exec_creds(void);
extern int commit_creds(struct cred *);
extern void abort_creds(struct cred *);
extern struct cred *prepare_kernel_cred(struct task_struct *);
extern int set_security_override(struct cred *, u32);
extern int set_security_override_from_ctx(struct cred *, const char *);
extern int set_create_files_as(struct cred *, struct inode *);
extern int cred_fscmp(const struct cred *, const struct cred *);
extern void __init cred_init(void);
extern int set_cred_ucounts(struct cred *);
static inline bool cap_ambient_invariant_ok(const struct cred *cred)
{
return cap_issubset(cred->cap_ambient,
cap_intersect(cred->cap_permitted,
cred->cap_inheritable));
}
static inline const struct cred *override_creds(const struct cred *override_cred)
{
return rcu_replace_pointer(current->cred, override_cred, 1);
}
static inline const struct cred *revert_creds(const struct cred *revert_cred)
{
return rcu_replace_pointer(current->cred, revert_cred, 1);
}
/**
* get_cred_many - Get references on a set of credentials
* @cred: The credentials to reference
* @nr: Number of references to acquire
*
* Get references on the specified set of credentials. The caller must release
* all acquired reference. If %NULL is passed, it is returned with no action.
*
* This is used to deal with a committed set of credentials. Although the
* pointer is const, this will temporarily discard the const and increment the
* usage count. The purpose of this is to attempt to catch at compile time the
* accidental alteration of a set of credentials that should be considered
* immutable.
*/
static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
{
struct cred *nonconst_cred = (struct cred *) cred;
if (!cred)
return cred;
nonconst_cred->non_rcu = 0;
atomic_long_add(nr, &nonconst_cred->usage);
return cred;
}
/*
* get_cred - Get a reference on a set of credentials
* @cred: The credentials to reference
*
* Get a reference on the specified set of credentials. The caller must
* release the reference. If %NULL is passed, it is returned with no action.
*
* This is used to deal with a committed set of credentials.
*/
static inline const struct cred *get_cred(const struct cred *cred)
{
return get_cred_many(cred, 1);
}
static inline const struct cred *get_cred_rcu(const struct cred *cred)
{
struct cred *nonconst_cred = (struct cred *) cred;
if (!cred)
return NULL;
if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
return NULL;
nonconst_cred->non_rcu = 0;
return cred;
}
/**
* put_cred - Release a reference to a set of credentials
* @cred: The credentials to release
* @nr: Number of references to release
*
* Release a reference to a set of credentials, deleting them when the last ref
* is released. If %NULL is passed, nothing is done.
*
* This takes a const pointer to a set of credentials because the credentials
* on task_struct are attached by const pointers to prevent accidental
* alteration of otherwise immutable credential sets.
*/
static inline void put_cred_many(const struct cred *_cred, int nr)
{
struct cred *cred = (struct cred *) _cred;
if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred);
}
}
/*
* put_cred - Release a reference to a set of credentials
* @cred: The credentials to release
*
* Release a reference to a set of credentials, deleting them when the last ref
* is released. If %NULL is passed, nothing is done.
*/
static inline void put_cred(const struct cred *cred)
{
put_cred_many(cred, 1);
}
/**
* current_cred - Access the current task's subjective credentials
*
* Access the subjective credentials of the current task. RCU-safe,
* since nobody else can modify it.
*/
#define current_cred() \
rcu_dereference_protected(current->cred, 1)
/**
* current_real_cred - Access the current task's objective credentials
*
* Access the objective credentials of the current task. RCU-safe,
* since nobody else can modify it.
*/
#define current_real_cred() \
rcu_dereference_protected(current->real_cred, 1)
/**
* __task_cred - Access a task's objective credentials
* @task: The task to query
*
* Access the objective credentials of a task. The caller must hold the RCU
* readlock.
*
* The result of this function should not be passed directly to get_cred();
* rather get_task_cred() should be used instead.
*/
#define __task_cred(task) \
rcu_dereference((task)->real_cred)
/**
* get_current_cred - Get the current task's subjective credentials
*
* Get the subjective credentials of the current task, pinning them so that
* they can't go away. Accessing the current task's credentials directly is
* not permitted.
*/
#define get_current_cred() \
(get_cred(current_cred()))
/**
* get_current_user - Get the current task's user_struct
*
* Get the user record of the current task, pinning it so that it can't go
* away.
*/
#define get_current_user() \
({ \
struct user_struct *__u; \
const struct cred *__cred; \
__cred = current_cred(); \
__u = get_uid(__cred->user); \
__u; \
})
/**
* get_current_groups - Get the current task's supplementary group list
*
* Get the supplementary group list of the current task, pinning it so that it
* can't go away.
*/
#define get_current_groups() \
({ \
struct group_info *__groups; \
const struct cred *__cred; \
__cred = current_cred(); \
__groups = get_group_info(__cred->group_info); \
__groups; \
})
#define task_cred_xxx(task, xxx) \
({ \
__typeof__(((struct cred *)NULL)->xxx) ___val; \
rcu_read_lock(); \
___val = __task_cred((task))->xxx; \
rcu_read_unlock(); \
___val; \
})
#define task_uid(task) (task_cred_xxx((task), uid))
#define task_euid(task) (task_cred_xxx((task), euid))
#define task_ucounts(task) (task_cred_xxx((task), ucounts))
#define current_cred_xxx(xxx) \
({ \
current_cred()->xxx; \
})
#define current_uid() (current_cred_xxx(uid))
#define current_gid() (current_cred_xxx(gid))
#define current_euid() (current_cred_xxx(euid))
#define current_egid() (current_cred_xxx(egid))
#define current_suid() (current_cred_xxx(suid))
#define current_sgid() (current_cred_xxx(sgid))
#define current_fsuid() (current_cred_xxx(fsuid))
#define current_fsgid() (current_cred_xxx(fsgid))
#define current_cap() (current_cred_xxx(cap_effective))
#define current_user() (current_cred_xxx(user))
#define current_ucounts() (current_cred_xxx(ucounts))
extern struct user_namespace init_user_ns;
#ifdef CONFIG_USER_NS
#define current_user_ns() (current_cred_xxx(user_ns))
#else
static inline struct user_namespace *current_user_ns(void)
{
return &init_user_ns;
}
#endif
#define current_uid_gid(_uid, _gid) \
do { \
const struct cred *__cred; \
__cred = current_cred(); \
*(_uid) = __cred->uid; \
*(_gid) = __cred->gid; \
} while(0)
#define current_euid_egid(_euid, _egid) \
do { \
const struct cred *__cred; \
__cred = current_cred(); \
*(_euid) = __cred->euid; \
*(_egid) = __cred->egid; \
} while(0)
#define current_fsuid_fsgid(_fsuid, _fsgid) \
do { \
const struct cred *__cred; \
__cred = current_cred(); \
*(_fsuid) = __cred->fsuid; \
*(_fsgid) = __cred->fsgid; \
} while(0)
#endif /* _LINUX_CRED_H */
// SPDX-License-Identifier: GPL-2.0+
/*
* XArray implementation
* Copyright (c) 2017-2018 Microsoft Corporation
* Copyright (c) 2018-2020 Oracle
* Author: Matthew Wilcox <willy@infradead.org>
*/
#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/xarray.h>
#include "radix-tree.h"
/*
* Coding conventions in this file:
*
* @xa is used to refer to the entire xarray.
* @xas is the 'xarray operation state'. It may be either a pointer to
* an xa_state, or an xa_state stored on the stack. This is an unfortunate
* ambiguity.
* @index is the index of the entry being operated on
* @mark is an xa_mark_t; a small number indicating one of the mark bits.
* @node refers to an xa_node; usually the primary one being operated on by
* this function.
* @offset is the index into the slots array inside an xa_node.
* @parent refers to the @xa_node closer to the head than @node.
* @entry refers to something stored in a slot in the xarray
*/
static inline unsigned int xa_lock_type(const struct xarray *xa)
{
return (__force unsigned int)xa->xa_flags & 3;
}
static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type)
{
if (lock_type == XA_LOCK_IRQ)
xas_lock_irq(xas);
else if (lock_type == XA_LOCK_BH)
xas_lock_bh(xas);
else
xas_lock(xas);
}
static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type)
{
if (lock_type == XA_LOCK_IRQ)
xas_unlock_irq(xas);
else if (lock_type == XA_LOCK_BH)
xas_unlock_bh(xas);
else
xas_unlock(xas);
}
static inline bool xa_track_free(const struct xarray *xa)
{
return xa->xa_flags & XA_FLAGS_TRACK_FREE;
}
static inline bool xa_zero_busy(const struct xarray *xa)
{
return xa->xa_flags & XA_FLAGS_ZERO_BUSY;
}
static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
{
if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark);
}
static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark)
{
if (xa->xa_flags & XA_FLAGS_MARK(mark))
xa->xa_flags &= ~(XA_FLAGS_MARK(mark));
}
static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark)
{
return node->marks[(__force unsigned)mark];
}
static inline bool node_get_mark(struct xa_node *node,
unsigned int offset, xa_mark_t mark)
{
return test_bit(offset, node_marks(node, mark));
}
/* returns true if the bit was set */
static inline bool node_set_mark(struct xa_node *node, unsigned int offset,
xa_mark_t mark)
{
return __test_and_set_bit(offset, node_marks(node, mark));
}
/* returns true if the bit was set */
static inline bool node_clear_mark(struct xa_node *node, unsigned int offset,
xa_mark_t mark)
{
return __test_and_clear_bit(offset, node_marks(node, mark));
}
static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
{
return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
}
static inline void node_mark_all(struct xa_node *node, xa_mark_t mark)
{
bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE);
}
#define mark_inc(mark) do { \
mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \
} while (0)
/*
* xas_squash_marks() - Merge all marks to the first entry
* @xas: Array operation state.
*
* Set a mark on the first entry if any entry has it set. Clear marks on
* all sibling entries.
*/
static void xas_squash_marks(const struct xa_state *xas)
{
xa_mark_t mark = 0;
unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
for (;;) {
unsigned long *marks = node_marks(xas->xa_node, mark);
if (find_next_bit(marks, limit, xas->xa_offset + 1) != limit) { __set_bit(xas->xa_offset, marks);
bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
}
if (mark == XA_MARK_MAX)
break;
mark_inc(mark);
}
}
/* extracts the offset within this node from the index */
static unsigned int get_offset(unsigned long index, struct xa_node *node)
{
return (index >> node->shift) & XA_CHUNK_MASK;
}
static void xas_set_offset(struct xa_state *xas)
{
xas->xa_offset = get_offset(xas->xa_index, xas->xa_node);
}
/* move the index either forwards (find) or backwards (sibling slot) */
static void xas_move_index(struct xa_state *xas, unsigned long offset)
{
unsigned int shift = xas->xa_node->shift;
xas->xa_index &= ~XA_CHUNK_MASK << shift;
xas->xa_index += offset << shift;
}
static void xas_next_offset(struct xa_state *xas)
{
xas->xa_offset++;
xas_move_index(xas, xas->xa_offset);
}
static void *set_bounds(struct xa_state *xas)
{
xas->xa_node = XAS_BOUNDS;
return NULL;
}
/*
* Starts a walk. If the @xas is already valid, we assume that it's on
* the right path and just return where we've got to. If we're in an
* error state, return NULL. If the index is outside the current scope
* of the xarray, return NULL without changing @xas->xa_node. Otherwise
* set @xas->xa_node to NULL and return the current head of the array.
*/
static void *xas_start(struct xa_state *xas)
{
void *entry;
if (xas_valid(xas))
return xas_reload(xas); if (xas_error(xas))
return NULL;
entry = xa_head(xas->xa);
if (!xa_is_node(entry)) {
if (xas->xa_index) return set_bounds(xas);
} else {
if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas);
}
xas->xa_node = NULL;
return entry;
}
static __always_inline void *xas_descend(struct xa_state *xas,
struct xa_node *node)
{
unsigned int offset = get_offset(xas->xa_index, node);
void *entry = xa_entry(xas->xa, node, offset);
xas->xa_node = node;
while (xa_is_sibling(entry)) {
offset = xa_to_sibling(entry);
entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry))
entry = XA_RETRY_ENTRY;
}
xas->xa_offset = offset;
return entry;
}
/**
* xas_load() - Load an entry from the XArray (advanced).
* @xas: XArray operation state.
*
* Usually walks the @xas to the appropriate state to load the entry
* stored at xa_index. However, it will do nothing and return %NULL if
* @xas is in an error state. xas_load() will never expand the tree.
*
* If the xa_state is set up to operate on a multi-index entry, xas_load()
* may return %NULL or an internal entry, even if there are entries
* present within the range specified by @xas.
*
* Context: Any context. The caller should hold the xa_lock or the RCU lock.
* Return: Usually an entry in the XArray, but see description for exceptions.
*/
void *xas_load(struct xa_state *xas)
{
void *entry = xas_start(xas);
while (xa_is_node(entry)) {
struct xa_node *node = xa_to_node(entry);
if (xas->xa_shift > node->shift)
break;
entry = xas_descend(xas, node);
if (node->shift == 0)
break;
}
return entry;
}
EXPORT_SYMBOL_GPL(xas_load);
#define XA_RCU_FREE ((struct xarray *)1)
static void xa_node_free(struct xa_node *node)
{
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
node->array = XA_RCU_FREE;
call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
}
/*
* xas_destroy() - Free any resources allocated during the XArray operation.
* @xas: XArray operation state.
*
* Most users will not need to call this function; it is called for you
* by xas_nomem().
*/
void xas_destroy(struct xa_state *xas)
{
struct xa_node *next, *node = xas->xa_alloc;
while (node) {
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
next = rcu_dereference_raw(node->parent);
radix_tree_node_rcu_free(&node->rcu_head);
xas->xa_alloc = node = next;
}
}
EXPORT_SYMBOL_GPL(xas_destroy);
/**
* xas_nomem() - Allocate memory if needed.
* @xas: XArray operation state.
* @gfp: Memory allocation flags.
*
* If we need to add new nodes to the XArray, we try to allocate memory
* with GFP_NOWAIT while holding the lock, which will usually succeed.
* If it fails, @xas is flagged as needing memory to continue. The caller
* should drop the lock and call xas_nomem(). If xas_nomem() succeeds,
* the caller should retry the operation.
*
* Forward progress is guaranteed as one node is allocated here and
* stored in the xa_state where it will be found by xas_alloc(). More
* nodes will likely be found in the slab allocator, but we do not tie
* them up here.
*
* Return: true if memory was needed, and was successfully allocated.
*/
bool xas_nomem(struct xa_state *xas, gfp_t gfp)
{
if (xas->xa_node != XA_ERROR(-ENOMEM)) {
xas_destroy(xas);
return false;
}
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
gfp |= __GFP_ACCOUNT;
xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
if (!xas->xa_alloc)
return false;
xas->xa_alloc->parent = NULL;
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
xas->xa_node = XAS_RESTART;
return true;
}
EXPORT_SYMBOL_GPL(xas_nomem);
/*
* __xas_nomem() - Drop locks and allocate memory if needed.
* @xas: XArray operation state.
* @gfp: Memory allocation flags.
*
* Internal variant of xas_nomem().
*
* Return: true if memory was needed, and was successfully allocated.
*/
static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
__must_hold(xas->xa->xa_lock)
{
unsigned int lock_type = xa_lock_type(xas->xa);
if (xas->xa_node != XA_ERROR(-ENOMEM)) {
xas_destroy(xas);
return false;
}
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
gfp |= __GFP_ACCOUNT;
if (gfpflags_allow_blocking(gfp)) {
xas_unlock_type(xas, lock_type);
xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
xas_lock_type(xas, lock_type);
} else {
xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
}
if (!xas->xa_alloc)
return false;
xas->xa_alloc->parent = NULL;
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
xas->xa_node = XAS_RESTART;
return true;
}
static void xas_update(struct xa_state *xas, struct xa_node *node)
{
if (xas->xa_update) xas->xa_update(node);
else
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
}
static void *xas_alloc(struct xa_state *xas, unsigned int shift)
{
struct xa_node *parent = xas->xa_node;
struct xa_node *node = xas->xa_alloc;
if (xas_invalid(xas))
return NULL;
if (node) {
xas->xa_alloc = NULL;
} else {
gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN;
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
gfp |= __GFP_ACCOUNT;
node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
if (!node) { xas_set_err(xas, -ENOMEM);
return NULL;
}
}
if (parent) {
node->offset = xas->xa_offset;
parent->count++;
XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE);
xas_update(xas, parent);
}
XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
node->shift = shift;
node->count = 0;
node->nr_values = 0;
RCU_INIT_POINTER(node->parent, xas->xa_node);
node->array = xas->xa;
return node;
}
#ifdef CONFIG_XARRAY_MULTI
/* Returns the number of indices covered by a given xa_state */
static unsigned long xas_size(const struct xa_state *xas)
{
return (xas->xa_sibs + 1UL) << xas->xa_shift;
}
#endif
/*
* Use this to calculate the maximum index that will need to be created
* in order to add the entry described by @xas. Because we cannot store a
* multi-index entry at index 0, the calculation is a little more complex
* than you might expect.
*/
static unsigned long xas_max(struct xa_state *xas)
{
unsigned long max = xas->xa_index;
#ifdef CONFIG_XARRAY_MULTI
if (xas->xa_shift || xas->xa_sibs) {
unsigned long mask = xas_size(xas) - 1;
max |= mask;
if (mask == max)
max++;
}
#endif
return max;
}
/* The maximum index that can be contained in the array without expanding it */
static unsigned long max_index(void *entry)
{
if (!xa_is_node(entry))
return 0;
return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
}
static inline void *xa_zero_to_null(void *entry)
{
return xa_is_zero(entry) ? NULL : entry;
}
static void xas_shrink(struct xa_state *xas)
{
struct xarray *xa = xas->xa;
struct xa_node *node = xas->xa_node;
for (;;) {
void *entry;
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
if (node->count != 1)
break;
entry = xa_entry_locked(xa, node, 0); if (!entry)
break;
if (!xa_is_node(entry) && node->shift)
break;
if (xa_zero_busy(xa))
entry = xa_zero_to_null(entry);
xas->xa_node = XAS_BOUNDS;
RCU_INIT_POINTER(xa->xa_head, entry);
if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK);
node->count = 0;
node->nr_values = 0;
if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node);
xa_node_free(node);
if (!xa_is_node(entry))
break;
node = xa_to_node(entry);
node->parent = NULL;
}
}
/*
* xas_delete_node() - Attempt to delete an xa_node
* @xas: Array operation state.
*
* Attempts to delete the @xas->xa_node. This will fail if xa->node has
* a non-zero reference count.
*/
static void xas_delete_node(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
for (;;) {
struct xa_node *parent;
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
if (node->count)
break;
parent = xa_parent_locked(xas->xa, node);
xas->xa_node = parent;
xas->xa_offset = node->offset;
xa_node_free(node);
if (!parent) {
xas->xa->xa_head = NULL;
xas->xa_node = XAS_BOUNDS;
return;
}
parent->slots[xas->xa_offset] = NULL;
parent->count--;
XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE);
node = parent;
xas_update(xas, node);
}
if (!node->parent) xas_shrink(xas);
}
/**
* xas_free_nodes() - Free this node and all nodes that it references
* @xas: Array operation state.
* @top: Node to free
*
* This node has been removed from the tree. We must now free it and all
* of its subnodes. There may be RCU walkers with references into the tree,
* so we must replace all entries with retry markers.
*/
static void xas_free_nodes(struct xa_state *xas, struct xa_node *top)
{
unsigned int offset = 0;
struct xa_node *node = top;
for (;;) {
void *entry = xa_entry_locked(xas->xa, node, offset);
if (node->shift && xa_is_node(entry)) {
node = xa_to_node(entry);
offset = 0;
continue;
}
if (entry)
RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY);
offset++;
while (offset == XA_CHUNK_SIZE) {
struct xa_node *parent;
parent = xa_parent_locked(xas->xa, node);
offset = node->offset + 1;
node->count = 0;
node->nr_values = 0;
xas_update(xas, node);
xa_node_free(node);
if (node == top)
return;
node = parent;
}
}
}
/*
* xas_expand adds nodes to the head of the tree until it has reached
* sufficient height to be able to contain @xas->xa_index
*/
static int xas_expand(struct xa_state *xas, void *head)
{
struct xarray *xa = xas->xa;
struct xa_node *node = NULL;
unsigned int shift = 0;
unsigned long max = xas_max(xas);
if (!head) {
if (max == 0)
return 0;
while ((max >> shift) >= XA_CHUNK_SIZE)
shift += XA_CHUNK_SHIFT;
return shift + XA_CHUNK_SHIFT;
} else if (xa_is_node(head)) { node = xa_to_node(head);
shift = node->shift + XA_CHUNK_SHIFT;
}
xas->xa_node = NULL;
while (max > max_index(head)) {
xa_mark_t mark = 0;
XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
node = xas_alloc(xas, shift);
if (!node)
return -ENOMEM;
node->count = 1;
if (xa_is_value(head)) node->nr_values = 1;
RCU_INIT_POINTER(node->slots[0], head);
/* Propagate the aggregated mark info to the new child */
for (;;) {
if (xa_track_free(xa) && mark == XA_FREE_MARK) {
node_mark_all(node, XA_FREE_MARK);
if (!xa_marked(xa, XA_FREE_MARK)) {
node_clear_mark(node, 0, XA_FREE_MARK);
xa_mark_set(xa, XA_FREE_MARK);
}
} else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark);
}
if (mark == XA_MARK_MAX)
break;
mark_inc(mark);
}
/*
* Now that the new node is fully initialised, we can add
* it to the tree
*/
if (xa_is_node(head)) {
xa_to_node(head)->offset = 0;
rcu_assign_pointer(xa_to_node(head)->parent, node);
}
head = xa_mk_node(node);
rcu_assign_pointer(xa->xa_head, head);
xas_update(xas, node);
shift += XA_CHUNK_SHIFT;
}
xas->xa_node = node;
return shift;
}
/*
* xas_create() - Create a slot to store an entry in.
* @xas: XArray operation state.
* @allow_root: %true if we can store the entry in the root directly
*
* Most users will not need to call this function directly, as it is called
* by xas_store(). It is useful for doing conditional store operations
* (see the xa_cmpxchg() implementation for an example).
*
* Return: If the slot already existed, returns the contents of this slot.
* If the slot was newly created, returns %NULL. If it failed to create the
* slot, returns %NULL and indicates the error in @xas.
*/
static void *xas_create(struct xa_state *xas, bool allow_root)
{
struct xarray *xa = xas->xa;
void *entry;
void __rcu **slot;
struct xa_node *node = xas->xa_node;
int shift;
unsigned int order = xas->xa_shift;
if (xas_top(node)) {
entry = xa_head_locked(xa);
xas->xa_node = NULL;
if (!entry && xa_zero_busy(xa))
entry = XA_ZERO_ENTRY;
shift = xas_expand(xas, entry); if (shift < 0)
return NULL;
if (!shift && !allow_root)
shift = XA_CHUNK_SHIFT;
entry = xa_head_locked(xa);
slot = &xa->xa_head;
} else if (xas_error(xas)) {
return NULL;
} else if (node) {
unsigned int offset = xas->xa_offset;
shift = node->shift;
entry = xa_entry_locked(xa, node, offset);
slot = &node->slots[offset];
} else {
shift = 0;
entry = xa_head_locked(xa);
slot = &xa->xa_head;
}
while (shift > order) {
shift -= XA_CHUNK_SHIFT;
if (!entry) {
node = xas_alloc(xas, shift);
if (!node)
break;
if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK);
rcu_assign_pointer(*slot, xa_mk_node(node));
} else if (xa_is_node(entry)) { node = xa_to_node(entry);
} else {
break;
}
entry = xas_descend(xas, node);
slot = &node->slots[xas->xa_offset];
}
return entry;
}
/**
* xas_create_range() - Ensure that stores to this range will succeed
* @xas: XArray operation state.
*
* Creates all of the slots in the range covered by @xas. Sets @xas to
* create single-index entries and positions it at the beginning of the
* range. This is for the benefit of users which have not yet been
* converted to use multi-index entries.
*/
void xas_create_range(struct xa_state *xas)
{
unsigned long index = xas->xa_index;
unsigned char shift = xas->xa_shift;
unsigned char sibs = xas->xa_sibs;
xas->xa_index |= ((sibs + 1UL) << shift) - 1;
if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift)
xas->xa_offset |= sibs;
xas->xa_shift = 0;
xas->xa_sibs = 0;
for (;;) {
xas_create(xas, true);
if (xas_error(xas))
goto restore;
if (xas->xa_index <= (index | XA_CHUNK_MASK))
goto success;
xas->xa_index -= XA_CHUNK_SIZE;
for (;;) {
struct xa_node *node = xas->xa_node;
if (node->shift >= shift)
break;
xas->xa_node = xa_parent_locked(xas->xa, node);
xas->xa_offset = node->offset - 1;
if (node->offset != 0)
break;
}
}
restore:
xas->xa_shift = shift;
xas->xa_sibs = sibs;
xas->xa_index = index;
return;
success:
xas->xa_index = index;
if (xas->xa_node)
xas_set_offset(xas);
}
EXPORT_SYMBOL_GPL(xas_create_range);
static void update_node(struct xa_state *xas, struct xa_node *node,
int count, int values)
{
if (!node || (!count && !values))
return;
node->count += count;
node->nr_values += values;
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE);
xas_update(xas, node); if (count < 0) xas_delete_node(xas);
}
/**
* xas_store() - Store this entry in the XArray.
* @xas: XArray operation state.
* @entry: New entry.
*
* If @xas is operating on a multi-index entry, the entry returned by this
* function is essentially meaningless (it may be an internal entry or it
* may be %NULL, even if there are non-NULL entries at some of the indices
* covered by the range). This is not a problem for any current users,
* and can be changed if needed.
*
* Return: The old entry at this index.
*/
void *xas_store(struct xa_state *xas, void *entry)
{
struct xa_node *node;
void __rcu **slot = &xas->xa->xa_head;
unsigned int offset, max;
int count = 0;
int values = 0;
void *first, *next;
bool value = xa_is_value(entry);
if (entry) {
bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry);
first = xas_create(xas, allow_root);
} else {
first = xas_load(xas);
}
if (xas_invalid(xas))
return first;
node = xas->xa_node;
if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs)
return first;
next = first;
offset = xas->xa_offset;
max = xas->xa_offset + xas->xa_sibs;
if (node) {
slot = &node->slots[offset];
if (xas->xa_sibs) xas_squash_marks(xas);
}
if (!entry) xas_init_marks(xas);
for (;;) {
/*
* Must clear the marks before setting the entry to NULL,
* otherwise xas_for_each_marked may find a NULL entry and
* stop early. rcu_assign_pointer contains a release barrier
* so the mark clearing will appear to happen before the
* entry is set to NULL.
*/
rcu_assign_pointer(*slot, entry);
if (xa_is_node(next) && (!node || node->shift))
xas_free_nodes(xas, xa_to_node(next));
if (!node)
break;
count += !next - !entry;
values += !xa_is_value(first) - !value;
if (entry) {
if (offset == max)
break;
if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset);
} else {
if (offset == XA_CHUNK_MASK)
break;
}
next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max))
break;
first = next;
}
slot++;
}
update_node(xas, node, count, values);
return first;
}
EXPORT_SYMBOL_GPL(xas_store);
/**
* xas_get_mark() - Returns the state of this mark.
* @xas: XArray operation state.
* @mark: Mark number.
*
* Return: true if the mark is set, false if the mark is clear or @xas
* is in an error state.
*/
bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark)
{
if (xas_invalid(xas))
return false;
if (!xas->xa_node)
return xa_marked(xas->xa, mark);
return node_get_mark(xas->xa_node, xas->xa_offset, mark);
}
EXPORT_SYMBOL_GPL(xas_get_mark);
/**
* xas_set_mark() - Sets the mark on this entry and its parents.
* @xas: XArray operation state.
* @mark: Mark number.
*
* Sets the specified mark on this entry, and walks up the tree setting it
* on all the ancestor entries. Does nothing if @xas has not been walked to
* an entry, or is in an error state.
*/
void xas_set_mark(const struct xa_state *xas, xa_mark_t mark)
{
struct xa_node *node = xas->xa_node;
unsigned int offset = xas->xa_offset;
if (xas_invalid(xas))
return;
while (node) { if (node_set_mark(node, offset, mark))
return;
offset = node->offset;
node = xa_parent_locked(xas->xa, node);
}
if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark);
}
EXPORT_SYMBOL_GPL(xas_set_mark);
/**
* xas_clear_mark() - Clears the mark on this entry and its parents.
* @xas: XArray operation state.
* @mark: Mark number.
*
* Clears the specified mark on this entry, and walks back to the head
* attempting to clear it on all the ancestor entries. Does nothing if
* @xas has not been walked to an entry, or is in an error state.
*/
void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
{
struct xa_node *node = xas->xa_node;
unsigned int offset = xas->xa_offset;
if (xas_invalid(xas))
return;
while (node) { if (!node_clear_mark(node, offset, mark))
return;
if (node_any_mark(node, mark))
return;
offset = node->offset;
node = xa_parent_locked(xas->xa, node);
}
if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark);
}
EXPORT_SYMBOL_GPL(xas_clear_mark);
/**
* xas_init_marks() - Initialise all marks for the entry
* @xas: Array operations state.
*
* Initialise all marks for the entry specified by @xas. If we're tracking
* free entries with a mark, we need to set it on all entries. All other
* marks are cleared.
*
* This implementation is not as efficient as it could be; we may walk
* up the tree multiple times.
*/
void xas_init_marks(const struct xa_state *xas)
{
xa_mark_t mark = 0;
for (;;) {
if (xa_track_free(xas->xa) && mark == XA_FREE_MARK)
xas_set_mark(xas, mark);
else
xas_clear_mark(xas, mark);
if (mark == XA_MARK_MAX)
break;
mark_inc(mark);
}
}
EXPORT_SYMBOL_GPL(xas_init_marks);
#ifdef CONFIG_XARRAY_MULTI
static unsigned int node_get_marks(struct xa_node *node, unsigned int offset)
{
unsigned int marks = 0;
xa_mark_t mark = XA_MARK_0;
for (;;) {
if (node_get_mark(node, offset, mark))
marks |= 1 << (__force unsigned int)mark;
if (mark == XA_MARK_MAX)
break;
mark_inc(mark);
}
return marks;
}
static inline void node_mark_slots(struct xa_node *node, unsigned int sibs,
xa_mark_t mark)
{
int i;
if (sibs == 0)
node_mark_all(node, mark);
else {
for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1)
node_set_mark(node, i, mark);
}
}
static void node_set_marks(struct xa_node *node, unsigned int offset,
struct xa_node *child, unsigned int sibs,
unsigned int marks)
{
xa_mark_t mark = XA_MARK_0;
for (;;) {
if (marks & (1 << (__force unsigned int)mark)) {
node_set_mark(node, offset, mark);
if (child)
node_mark_slots(child, sibs, mark);
}
if (mark == XA_MARK_MAX)
break;
mark_inc(mark);
}
}
static void __xas_init_node_for_split(struct xa_state *xas,
struct xa_node *node, void *entry)
{
unsigned int i;
void *sibling = NULL;
unsigned int mask = xas->xa_sibs;
if (!node)
return;
node->array = xas->xa;
for (i = 0; i < XA_CHUNK_SIZE; i++) {
if ((i & mask) == 0) {
RCU_INIT_POINTER(node->slots[i], entry);
sibling = xa_mk_sibling(i);
} else {
RCU_INIT_POINTER(node->slots[i], sibling);
}
}
}
/**
* xas_split_alloc() - Allocate memory for splitting an entry.
* @xas: XArray operation state.
* @entry: New entry which will be stored in the array.
* @order: Current entry order.
* @gfp: Memory allocation flags.
*
* This function should be called before calling xas_split().
* If necessary, it will allocate new nodes (and fill them with @entry)
* to prepare for the upcoming split of an entry of @order size into
* entries of the order stored in the @xas.
*
* Context: May sleep if @gfp flags permit.
*/
void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
gfp_t gfp)
{
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
/* XXX: no support for splitting really large entries yet */
if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order))
goto nomem;
if (xas->xa_shift + XA_CHUNK_SHIFT > order)
return;
do {
struct xa_node *node;
node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
if (!node)
goto nomem;
__xas_init_node_for_split(xas, node, entry);
RCU_INIT_POINTER(node->parent, xas->xa_alloc);
xas->xa_alloc = node;
} while (sibs-- > 0);
return;
nomem:
xas_destroy(xas);
xas_set_err(xas, -ENOMEM);
}
EXPORT_SYMBOL_GPL(xas_split_alloc);
/**
* xas_split() - Split a multi-index entry into smaller entries.
* @xas: XArray operation state.
* @entry: New entry to store in the array.
* @order: Current entry order.
*
* The size of the new entries is set in @xas. The value in @entry is
* copied to all the replacement entries.
*
* Context: Any context. The caller should hold the xa_lock.
*/
void xas_split(struct xa_state *xas, void *entry, unsigned int order)
{
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
unsigned int offset, marks;
struct xa_node *node;
void *curr = xas_load(xas);
int values = 0;
node = xas->xa_node;
if (xas_top(node))
return;
marks = node_get_marks(node, xas->xa_offset);
offset = xas->xa_offset + sibs;
do {
if (xas->xa_shift < node->shift) {
struct xa_node *child = xas->xa_alloc;
xas->xa_alloc = rcu_dereference_raw(child->parent);
child->shift = node->shift - XA_CHUNK_SHIFT;
child->offset = offset;
child->count = XA_CHUNK_SIZE;
child->nr_values = xa_is_value(entry) ?
XA_CHUNK_SIZE : 0;
RCU_INIT_POINTER(child->parent, node);
node_set_marks(node, offset, child, xas->xa_sibs,
marks);
rcu_assign_pointer(node->slots[offset],
xa_mk_node(child));
if (xa_is_value(curr))
values--;
xas_update(xas, child);
} else {
unsigned int canon = offset - xas->xa_sibs;
node_set_marks(node, canon, NULL, 0, marks);
rcu_assign_pointer(node->slots[canon], entry);
while (offset > canon)
rcu_assign_pointer(node->slots[offset--],
xa_mk_sibling(canon));
values += (xa_is_value(entry) - xa_is_value(curr)) *
(xas->xa_sibs + 1);
}
} while (offset-- > xas->xa_offset);
node->nr_values += values;
xas_update(xas, node);
}
EXPORT_SYMBOL_GPL(xas_split);
/**
* xas_try_split_min_order() - Minimal split order xas_try_split() can accept
* @order: Current entry order.
*
* xas_try_split() can split a multi-index entry to smaller than @order - 1 if
* no new xa_node is needed. This function provides the minimal order
* xas_try_split() supports.
*
* Return: the minimal order xas_try_split() supports
*
* Context: Any context.
*
*/
unsigned int xas_try_split_min_order(unsigned int order)
{
if (order % XA_CHUNK_SHIFT == 0)
return order == 0 ? 0 : order - 1;
return order - (order % XA_CHUNK_SHIFT);
}
EXPORT_SYMBOL_GPL(xas_try_split_min_order);
/**
* xas_try_split() - Try to split a multi-index entry.
* @xas: XArray operation state.
* @entry: New entry to store in the array.
* @order: Current entry order.
*
* The size of the new entries is set in @xas. The value in @entry is
* copied to all the replacement entries. If and only if one new xa_node is
* needed, the function will use GFP_NOWAIT to get one if xas->xa_alloc is
* NULL. If more new xa_node are needed, the function gives EINVAL error.
*
* NOTE: use xas_try_split_min_order() to get next split order instead of
* @order - 1 if you want to minmize xas_try_split() calls.
*
* Context: Any context. The caller should hold the xa_lock.
*/
void xas_try_split(struct xa_state *xas, void *entry, unsigned int order)
{
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
unsigned int offset, marks;
struct xa_node *node;
void *curr = xas_load(xas);
int values = 0;
gfp_t gfp = GFP_NOWAIT;
node = xas->xa_node;
if (xas_top(node))
return;
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
gfp |= __GFP_ACCOUNT;
marks = node_get_marks(node, xas->xa_offset);
offset = xas->xa_offset + sibs;
if (xas->xa_shift < node->shift) {
struct xa_node *child = xas->xa_alloc;
unsigned int expected_sibs =
(1 << ((order - 1) % XA_CHUNK_SHIFT)) - 1;
/*
* No support for splitting sibling entries
* (horizontally) or cascade split (vertically), which
* requires two or more new xa_nodes.
* Since if one xa_node allocation fails,
* it is hard to free the prior allocations.
*/
if (sibs || xas->xa_sibs != expected_sibs) {
xas_destroy(xas);
xas_set_err(xas, -EINVAL);
return;
}
if (!child) {
child = kmem_cache_alloc_lru(radix_tree_node_cachep,
xas->xa_lru, gfp);
if (!child) {
xas_destroy(xas);
xas_set_err(xas, -ENOMEM);
return;
}
RCU_INIT_POINTER(child->parent, xas->xa_alloc);
}
__xas_init_node_for_split(xas, child, entry);
xas->xa_alloc = rcu_dereference_raw(child->parent);
child->shift = node->shift - XA_CHUNK_SHIFT;
child->offset = offset;
child->count = XA_CHUNK_SIZE;
child->nr_values = xa_is_value(entry) ?
XA_CHUNK_SIZE : 0;
RCU_INIT_POINTER(child->parent, node);
node_set_marks(node, offset, child, xas->xa_sibs,
marks);
rcu_assign_pointer(node->slots[offset],
xa_mk_node(child));
if (xa_is_value(curr))
values--;
xas_update(xas, child);
} else {
do {
unsigned int canon = offset - xas->xa_sibs;
node_set_marks(node, canon, NULL, 0, marks);
rcu_assign_pointer(node->slots[canon], entry);
while (offset > canon)
rcu_assign_pointer(node->slots[offset--],
xa_mk_sibling(canon));
values += (xa_is_value(entry) - xa_is_value(curr)) *
(xas->xa_sibs + 1);
} while (offset-- > xas->xa_offset);
}
node->nr_values += values;
xas_update(xas, node);
}
EXPORT_SYMBOL_GPL(xas_try_split);
#endif
/**
* xas_pause() - Pause a walk to drop a lock.
* @xas: XArray operation state.
*
* Some users need to pause a walk and drop the lock they're holding in
* order to yield to a higher priority thread or carry out an operation
* on an entry. Those users should call this function before they drop
* the lock. It resets the @xas to be suitable for the next iteration
* of the loop after the user has reacquired the lock. If most entries
* found during a walk require you to call xas_pause(), the xa_for_each()
* iterator may be more appropriate.
*
* Note that xas_pause() only works for forward iteration. If a user needs
* to pause a reverse iteration, we will need a xas_pause_rev().
*/
void xas_pause(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
if (xas_invalid(xas))
return;
xas->xa_node = XAS_RESTART;
if (node) {
unsigned long offset = xas->xa_offset;
while (++offset < XA_CHUNK_SIZE) {
if (!xa_is_sibling(xa_entry(xas->xa, node, offset)))
break;
}
xas->xa_index &= ~0UL << node->shift;
xas->xa_index += (offset - xas->xa_offset) << node->shift;
if (xas->xa_index == 0)
xas->xa_node = XAS_BOUNDS;
} else {
xas->xa_index++;
}
}
EXPORT_SYMBOL_GPL(xas_pause);
/*
* __xas_prev() - Find the previous entry in the XArray.
* @xas: XArray operation state.
*
* Helper function for xas_prev() which handles all the complex cases
* out of line.
*/
void *__xas_prev(struct xa_state *xas)
{
void *entry;
if (!xas_frozen(xas->xa_node))
xas->xa_index--;
if (!xas->xa_node)
return set_bounds(xas);
if (xas_not_node(xas->xa_node))
return xas_load(xas);
if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node))
xas->xa_offset--;
while (xas->xa_offset == 255) {
xas->xa_offset = xas->xa_node->offset - 1;
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
if (!xas->xa_node)
return set_bounds(xas);
}
for (;;) {
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
if (!xa_is_node(entry))
return entry;
xas->xa_node = xa_to_node(entry);
xas_set_offset(xas);
}
}
EXPORT_SYMBOL_GPL(__xas_prev);
/*
* __xas_next() - Find the next entry in the XArray.
* @xas: XArray operation state.
*
* Helper function for xas_next() which handles all the complex cases
* out of line.
*/
void *__xas_next(struct xa_state *xas)
{
void *entry;
if (!xas_frozen(xas->xa_node))
xas->xa_index++;
if (!xas->xa_node)
return set_bounds(xas);
if (xas_not_node(xas->xa_node))
return xas_load(xas);
if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node))
xas->xa_offset++;
while (xas->xa_offset == XA_CHUNK_SIZE) {
xas->xa_offset = xas->xa_node->offset + 1;
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
if (!xas->xa_node)
return set_bounds(xas);
}
for (;;) {
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
if (!xa_is_node(entry))
return entry;
xas->xa_node = xa_to_node(entry);
xas_set_offset(xas);
}
}
EXPORT_SYMBOL_GPL(__xas_next);
/**
* xas_find() - Find the next present entry in the XArray.
* @xas: XArray operation state.
* @max: Highest index to return.
*
* If the @xas has not yet been walked to an entry, return the entry
* which has an index >= xas.xa_index. If it has been walked, the entry
* currently being pointed at has been processed, and so we move to the
* next entry.
*
* If no entry is found and the array is smaller than @max, the iterator
* is set to the smallest index not yet in the array. This allows @xas
* to be immediately passed to xas_store().
*
* Return: The entry, if found, otherwise %NULL.
*/
void *xas_find(struct xa_state *xas, unsigned long max)
{
void *entry;
if (xas_error(xas) || xas->xa_node == XAS_BOUNDS)
return NULL;
if (xas->xa_index > max)
return set_bounds(xas);
if (!xas->xa_node) {
xas->xa_index = 1;
return set_bounds(xas);
} else if (xas->xa_node == XAS_RESTART) {
entry = xas_load(xas);
if (entry || xas_not_node(xas->xa_node))
return entry;
} else if (!xas->xa_node->shift &&
xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) {
xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1;
}
xas_next_offset(xas);
while (xas->xa_node && (xas->xa_index <= max)) {
if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) {
xas->xa_offset = xas->xa_node->offset + 1;
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
continue;
}
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
if (xa_is_node(entry)) {
xas->xa_node = xa_to_node(entry);
xas->xa_offset = 0;
continue;
}
if (entry && !xa_is_sibling(entry))
return entry;
xas_next_offset(xas);
}
if (!xas->xa_node)
xas->xa_node = XAS_BOUNDS;
return NULL;
}
EXPORT_SYMBOL_GPL(xas_find);
/**
* xas_find_marked() - Find the next marked entry in the XArray.
* @xas: XArray operation state.
* @max: Highest index to return.
* @mark: Mark number to search for.
*
* If the @xas has not yet been walked to an entry, return the marked entry
* which has an index >= xas.xa_index. If it has been walked, the entry
* currently being pointed at has been processed, and so we return the
* first marked entry with an index > xas.xa_index.
*
* If no marked entry is found and the array is smaller than @max, @xas is
* set to the bounds state and xas->xa_index is set to the smallest index
* not yet in the array. This allows @xas to be immediately passed to
* xas_store().
*
* If no entry is found before @max is reached, @xas is set to the restart
* state.
*
* Return: The entry, if found, otherwise %NULL.
*/
void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
{
bool advance = true;
unsigned int offset;
void *entry;
if (xas_error(xas))
return NULL;
if (xas->xa_index > max)
goto max;
if (!xas->xa_node) {
xas->xa_index = 1;
goto out;
} else if (xas_top(xas->xa_node)) {
advance = false;
entry = xa_head(xas->xa);
xas->xa_node = NULL;
if (xas->xa_index > max_index(entry))
goto out;
if (!xa_is_node(entry)) {
if (xa_marked(xas->xa, mark))
return entry;
xas->xa_index = 1;
goto out;
}
xas->xa_node = xa_to_node(entry);
xas->xa_offset = xas->xa_index >> xas->xa_node->shift;
}
while (xas->xa_index <= max) {
if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) {
xas->xa_offset = xas->xa_node->offset + 1;
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
if (!xas->xa_node)
break;
advance = false;
continue;
}
if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry);
xas_move_index(xas, xas->xa_offset);
}
}
offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) {
advance = false;
xas_move_index(xas, offset);
/* Mind the wrap */
if ((xas->xa_index - 1) >= max)
goto max;
xas->xa_offset = offset;
if (offset == XA_CHUNK_SIZE)
continue;
}
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK))
continue;
if (xa_is_sibling(entry))
continue;
if (!xa_is_node(entry))
return entry;
xas->xa_node = xa_to_node(entry);
xas_set_offset(xas);
}
out:
if (xas->xa_index > max)
goto max;
return set_bounds(xas);
max:
xas->xa_node = XAS_RESTART;
return NULL;
}
EXPORT_SYMBOL_GPL(xas_find_marked);
/**
* xas_find_conflict() - Find the next present entry in a range.
* @xas: XArray operation state.
*
* The @xas describes both a range and a position within that range.
*
* Context: Any context. Expects xa_lock to be held.
* Return: The next entry in the range covered by @xas or %NULL.
*/
void *xas_find_conflict(struct xa_state *xas)
{
void *curr;
if (xas_error(xas))
return NULL;
if (!xas->xa_node)
return NULL;
if (xas_top(xas->xa_node)) {
curr = xas_start(xas);
if (!curr)
return NULL;
while (xa_is_node(curr)) {
struct xa_node *node = xa_to_node(curr);
curr = xas_descend(xas, node);
}
if (curr)
return curr;
}
if (xas->xa_node->shift > xas->xa_shift)
return NULL;
for (;;) {
if (xas->xa_node->shift == xas->xa_shift) {
if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs)
break;
} else if (xas->xa_offset == XA_CHUNK_MASK) {
xas->xa_offset = xas->xa_node->offset;
xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node)
break;
continue;
}
curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr))
continue;
while (xa_is_node(curr)) {
xas->xa_node = xa_to_node(curr);
xas->xa_offset = 0;
curr = xa_entry_locked(xas->xa, xas->xa_node, 0);
}
if (curr)
return curr;
}
xas->xa_offset -= xas->xa_sibs;
return NULL;
}
EXPORT_SYMBOL_GPL(xas_find_conflict);
/**
* xa_load() - Load an entry from an XArray.
* @xa: XArray.
* @index: index into array.
*
* Context: Any context. Takes and releases the RCU lock.
* Return: The entry at @index in @xa.
*/
void *xa_load(struct xarray *xa, unsigned long index)
{
XA_STATE(xas, xa, index);
void *entry;
rcu_read_lock();
do {
entry = xa_zero_to_null(xas_load(&xas));
} while (xas_retry(&xas, entry)); rcu_read_unlock();
return entry;
}
EXPORT_SYMBOL(xa_load);
static void *xas_result(struct xa_state *xas, void *curr)
{
if (xas_error(xas))
curr = xas->xa_node;
return curr;
}
/**
* __xa_erase() - Erase this entry from the XArray while locked.
* @xa: XArray.
* @index: Index into array.
*
* After this function returns, loading from @index will return %NULL.
* If the index is part of a multi-index entry, all indices will be erased
* and none of the entries will be part of a multi-index entry.
*
* Context: Any context. Expects xa_lock to be held on entry.
* Return: The entry which used to be at this index.
*/
void *__xa_erase(struct xarray *xa, unsigned long index)
{
XA_STATE(xas, xa, index);
return xas_result(&xas, xa_zero_to_null(xas_store(&xas, NULL)));
}
EXPORT_SYMBOL(__xa_erase);
/**
* xa_erase() - Erase this entry from the XArray.
* @xa: XArray.
* @index: Index of entry.
*
* After this function returns, loading from @index will return %NULL.
* If the index is part of a multi-index entry, all indices will be erased
* and none of the entries will be part of a multi-index entry.
*
* Context: Any context. Takes and releases the xa_lock.
* Return: The entry which used to be at this index.
*/
void *xa_erase(struct xarray *xa, unsigned long index)
{
void *entry;
xa_lock(xa);
entry = __xa_erase(xa, index);
xa_unlock(xa);
return entry;
}
EXPORT_SYMBOL(xa_erase);
/**
* __xa_store() - Store this entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* You must already be holding the xa_lock when calling this function.
* It will drop the lock if needed to allocate memory, and then reacquire
* it afterwards.
*
* Context: Any context. Expects xa_lock to be held on entry. May
* release and reacquire xa_lock if @gfp flags permit.
* Return: The old entry at this index or xa_err() if an error happened.
*/
void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
{
XA_STATE(xas, xa, index);
void *curr;
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return XA_ERROR(-EINVAL);
if (xa_track_free(xa) && !entry)
entry = XA_ZERO_ENTRY;
do {
curr = xas_store(&xas, entry);
if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, xa_zero_to_null(curr));
}
EXPORT_SYMBOL(__xa_store);
/**
* xa_store() - Store this entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* After this function returns, loads from this index will return @entry.
* Storing into an existing multi-index entry updates the entry of every index.
* The marks associated with @index are unaffected unless @entry is %NULL.
*
* Context: Any context. Takes and releases the xa_lock.
* May sleep if the @gfp flags permit.
* Return: The old entry at this index on success, xa_err(-EINVAL) if @entry
* cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation
* failed.
*/
void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
{
void *curr;
xa_lock(xa);
curr = __xa_store(xa, index, entry, gfp);
xa_unlock(xa);
return curr;
}
EXPORT_SYMBOL(xa_store);
static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp);
/**
* __xa_cmpxchg() - Store this entry in the XArray.
* @xa: XArray.
* @index: Index into array.
* @old: Old value to test against.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* You must already be holding the xa_lock when calling this function.
* It will drop the lock if needed to allocate memory, and then reacquire
* it afterwards.
*
* Context: Any context. Expects xa_lock to be held on entry. May
* release and reacquire xa_lock if @gfp flags permit.
* Return: The old entry at this index or xa_err() if an error happened.
*/
void *__xa_cmpxchg(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp)
{ return xa_zero_to_null(__xa_cmpxchg_raw(xa, index, old, entry, gfp));
}
EXPORT_SYMBOL(__xa_cmpxchg);
static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index,
void *old, void *entry, gfp_t gfp)
{
XA_STATE(xas, xa, index);
void *curr;
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return XA_ERROR(-EINVAL);
do {
curr = xas_load(&xas);
if (curr == old) {
xas_store(&xas, entry);
if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK);
}
} while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr);
}
/**
* __xa_insert() - Store this entry in the XArray if no entry is present.
* @xa: XArray.
* @index: Index into array.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* Inserting a NULL entry will store a reserved entry (like xa_reserve())
* if no entry is present. Inserting will fail if a reserved entry is
* present, even though loading from this index will return NULL.
*
* Context: Any context. Expects xa_lock to be held on entry. May
* release and reacquire xa_lock if @gfp flags permit.
* Return: 0 if the store succeeded. -EBUSY if another entry was present.
* -ENOMEM if memory could not be allocated.
*/
int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
{
void *curr;
int errno;
if (!entry)
entry = XA_ZERO_ENTRY;
curr = __xa_cmpxchg_raw(xa, index, NULL, entry, gfp);
errno = xa_err(curr);
if (errno)
return errno;
return (curr != NULL) ? -EBUSY : 0;
}
EXPORT_SYMBOL(__xa_insert);
#ifdef CONFIG_XARRAY_MULTI
static void xas_set_range(struct xa_state *xas, unsigned long first,
unsigned long last)
{
unsigned int shift = 0;
unsigned long sibs = last - first;
unsigned int offset = XA_CHUNK_MASK;
xas_set(xas, first);
while ((first & XA_CHUNK_MASK) == 0) {
if (sibs < XA_CHUNK_MASK)
break;
if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK))
break;
shift += XA_CHUNK_SHIFT;
if (offset == XA_CHUNK_MASK)
offset = sibs & XA_CHUNK_MASK;
sibs >>= XA_CHUNK_SHIFT;
first >>= XA_CHUNK_SHIFT;
}
offset = first & XA_CHUNK_MASK;
if (offset + sibs > XA_CHUNK_MASK)
sibs = XA_CHUNK_MASK - offset;
if ((((first + sibs + 1) << shift) - 1) > last)
sibs -= 1;
xas->xa_shift = shift;
xas->xa_sibs = sibs;
}
/**
* xa_store_range() - Store this entry at a range of indices in the XArray.
* @xa: XArray.
* @first: First index to affect.
* @last: Last index to affect.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* After this function returns, loads from any index between @first and @last,
* inclusive will return @entry.
* Storing into an existing multi-index entry updates the entry of every index.
* The marks associated with @index are unaffected unless @entry is %NULL.
*
* Context: Process context. Takes and releases the xa_lock. May sleep
* if the @gfp flags permit.
* Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in
* an XArray, or xa_err(-ENOMEM) if memory allocation failed.
*/
void *xa_store_range(struct xarray *xa, unsigned long first,
unsigned long last, void *entry, gfp_t gfp)
{
XA_STATE(xas, xa, 0);
if (WARN_ON_ONCE(xa_is_internal(entry)))
return XA_ERROR(-EINVAL);
if (last < first)
return XA_ERROR(-EINVAL);
do {
xas_lock(&xas);
if (entry) {
unsigned int order = BITS_PER_LONG;
if (last + 1)
order = __ffs(last + 1);
xas_set_order(&xas, last, order);
xas_create(&xas, true);
if (xas_error(&xas))
goto unlock;
}
do {
xas_set_range(&xas, first, last);
xas_store(&xas, entry);
if (xas_error(&xas))
goto unlock;
first += xas_size(&xas);
} while (first <= last);
unlock:
xas_unlock(&xas);
} while (xas_nomem(&xas, gfp));
return xas_result(&xas, NULL);
}
EXPORT_SYMBOL(xa_store_range);
/**
* xas_get_order() - Get the order of an entry.
* @xas: XArray operation state.
*
* Called after xas_load, the xas should not be in an error state.
*
* Return: A number between 0 and 63 indicating the order of the entry.
*/
int xas_get_order(struct xa_state *xas)
{
int order = 0;
if (!xas->xa_node)
return 0;
for (;;) {
unsigned int slot = xas->xa_offset + (1 << order);
if (slot >= XA_CHUNK_SIZE)
break;
if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot)))
break;
order++;
}
order += xas->xa_node->shift;
return order;
}
EXPORT_SYMBOL_GPL(xas_get_order);
/**
* xa_get_order() - Get the order of an entry.
* @xa: XArray.
* @index: Index of the entry.
*
* Return: A number between 0 and 63 indicating the order of the entry.
*/
int xa_get_order(struct xarray *xa, unsigned long index)
{
XA_STATE(xas, xa, index);
int order = 0;
void *entry;
rcu_read_lock();
entry = xas_load(&xas);
if (entry)
order = xas_get_order(&xas);
rcu_read_unlock();
return order;
}
EXPORT_SYMBOL(xa_get_order);
#endif /* CONFIG_XARRAY_MULTI */
/**
* __xa_alloc() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @limit: Range for allocated ID.
* @entry: New entry.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Expects xa_lock to be held on entry. May
* release and reacquire xa_lock if @gfp flags permit.
* Return: 0 on success, -ENOMEM if memory could not be allocated or
* -EBUSY if there are no free entries in @limit.
*/
int __xa_alloc(struct xarray *xa, u32 *id, void *entry,
struct xa_limit limit, gfp_t gfp)
{
XA_STATE(xas, xa, 0);
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return -EINVAL;
if (WARN_ON_ONCE(!xa_track_free(xa)))
return -EINVAL;
if (!entry)
entry = XA_ZERO_ENTRY;
do {
xas.xa_index = limit.min;
xas_find_marked(&xas, limit.max, XA_FREE_MARK);
if (xas.xa_node == XAS_RESTART)
xas_set_err(&xas, -EBUSY);
else
*id = xas.xa_index;
xas_store(&xas, entry);
xas_clear_mark(&xas, XA_FREE_MARK);
} while (__xas_nomem(&xas, gfp));
return xas_error(&xas);
}
EXPORT_SYMBOL(__xa_alloc);
/**
* __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray.
* @xa: XArray.
* @id: Pointer to ID.
* @entry: New entry.
* @limit: Range of allocated ID.
* @next: Pointer to next ID to allocate.
* @gfp: Memory allocation flags.
*
* Finds an empty entry in @xa between @limit.min and @limit.max,
* stores the index into the @id pointer, then stores the entry at
* that index. A concurrent lookup will not see an uninitialised @id.
* The search for an empty entry will start at @next and will wrap
* around if necessary.
*
* Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set
* in xa_init_flags().
*
* Context: Any context. Expects xa_lock to be held on entry. May
* release and reacquire xa_lock if @gfp flags permit.
* Return: 0 if the allocation succeeded without wrapping. 1 if the
* allocation succeeded after wrapping, -ENOMEM if memory could not be
* allocated or -EBUSY if there are no free entries in @limit.
*/
int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry,
struct xa_limit limit, u32 *next, gfp_t gfp)
{
u32 min = limit.min;
int ret;
limit.min = max(min, *next);
ret = __xa_alloc(xa, id, entry, limit, gfp);
if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) {
xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED;
ret = 1;
}
if (ret < 0 && limit.min > min) {
limit.min = min;
ret = __xa_alloc(xa, id, entry, limit, gfp);
if (ret == 0)
ret = 1;
}
if (ret >= 0) {
*next = *id + 1;
if (*next == 0)
xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED;
}
return ret;
}
EXPORT_SYMBOL(__xa_alloc_cyclic);
/**
* __xa_set_mark() - Set this mark on this entry while locked.
* @xa: XArray.
* @index: Index of entry.
* @mark: Mark number.
*
* Attempting to set a mark on a %NULL entry does not succeed.
*
* Context: Any context. Expects xa_lock to be held on entry.
*/
void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
{
XA_STATE(xas, xa, index);
void *entry = xas_load(&xas);
if (entry)
xas_set_mark(&xas, mark);
}
EXPORT_SYMBOL(__xa_set_mark);
/**
* __xa_clear_mark() - Clear this mark on this entry while locked.
* @xa: XArray.
* @index: Index of entry.
* @mark: Mark number.
*
* Context: Any context. Expects xa_lock to be held on entry.
*/
void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
{
XA_STATE(xas, xa, index);
void *entry = xas_load(&xas);
if (entry)
xas_clear_mark(&xas, mark);
}
EXPORT_SYMBOL(__xa_clear_mark);
/**
* xa_get_mark() - Inquire whether this mark is set on this entry.
* @xa: XArray.
* @index: Index of entry.
* @mark: Mark number.
*
* This function uses the RCU read lock, so the result may be out of date
* by the time it returns. If you need the result to be stable, use a lock.
*
* Context: Any context. Takes and releases the RCU lock.
* Return: True if the entry at @index has this mark set, false if it doesn't.
*/
bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
{
XA_STATE(xas, xa, index);
void *entry;
rcu_read_lock();
entry = xas_start(&xas);
while (xas_get_mark(&xas, mark)) {
if (!xa_is_node(entry))
goto found;
entry = xas_descend(&xas, xa_to_node(entry));
}
rcu_read_unlock();
return false;
found:
rcu_read_unlock();
return true;
}
EXPORT_SYMBOL(xa_get_mark);
/**
* xa_set_mark() - Set this mark on this entry.
* @xa: XArray.
* @index: Index of entry.
* @mark: Mark number.
*
* Attempting to set a mark on a %NULL entry does not succeed.
*
* Context: Process context. Takes and releases the xa_lock.
*/
void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
{
xa_lock(xa);
__xa_set_mark(xa, index, mark);
xa_unlock(xa);
}
EXPORT_SYMBOL(xa_set_mark);
/**
* xa_clear_mark() - Clear this mark on this entry.
* @xa: XArray.
* @index: Index of entry.
* @mark: Mark number.
*
* Clearing a mark always succeeds.
*
* Context: Process context. Takes and releases the xa_lock.
*/
void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
{
xa_lock(xa);
__xa_clear_mark(xa, index, mark);
xa_unlock(xa);
}
EXPORT_SYMBOL(xa_clear_mark);
/**
* xa_find() - Search the XArray for an entry.
* @xa: XArray.
* @indexp: Pointer to an index.
* @max: Maximum index to search to.
* @filter: Selection criterion.
*
* Finds the entry in @xa which matches the @filter, and has the lowest
* index that is at least @indexp and no more than @max.
* If an entry is found, @indexp is updated to be the index of the entry.
* This function is protected by the RCU read lock, so it may not find
* entries which are being simultaneously added. It will not return an
* %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find().
*
* Context: Any context. Takes and releases the RCU lock.
* Return: The entry, if found, otherwise %NULL.
*/
void *xa_find(struct xarray *xa, unsigned long *indexp,
unsigned long max, xa_mark_t filter)
{
XA_STATE(xas, xa, *indexp);
void *entry;
rcu_read_lock();
do {
if ((__force unsigned int)filter < XA_MAX_MARKS)
entry = xas_find_marked(&xas, max, filter);
else
entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index;
return entry;
}
EXPORT_SYMBOL(xa_find);
static bool xas_sibling(struct xa_state *xas)
{
struct xa_node *node = xas->xa_node;
unsigned long mask;
if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node)
return false;
mask = (XA_CHUNK_SIZE << node->shift) - 1;
return (xas->xa_index & mask) >
((unsigned long)xas->xa_offset << node->shift);
}
/**
* xa_find_after() - Search the XArray for a present entry.
* @xa: XArray.
* @indexp: Pointer to an index.
* @max: Maximum index to search to.
* @filter: Selection criterion.
*
* Finds the entry in @xa which matches the @filter and has the lowest
* index that is above @indexp and no more than @max.
* If an entry is found, @indexp is updated to be the index of the entry.
* This function is protected by the RCU read lock, so it may miss entries
* which are being simultaneously added. It will not return an
* %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find().
*
* Context: Any context. Takes and releases the RCU lock.
* Return: The pointer, if found, otherwise %NULL.
*/
void *xa_find_after(struct xarray *xa, unsigned long *indexp,
unsigned long max, xa_mark_t filter)
{
XA_STATE(xas, xa, *indexp + 1);
void *entry;
if (xas.xa_index == 0)
return NULL;
rcu_read_lock();
for (;;) {
if ((__force unsigned int)filter < XA_MAX_MARKS)
entry = xas_find_marked(&xas, max, filter);
else
entry = xas_find(&xas, max); if (xas_invalid(&xas))
break;
if (xas_sibling(&xas))
continue;
if (!xas_retry(&xas, entry))
break;
}
rcu_read_unlock(); if (entry) *indexp = xas.xa_index;
return entry;
}
EXPORT_SYMBOL(xa_find_after);
static unsigned int xas_extract_present(struct xa_state *xas, void **dst,
unsigned long max, unsigned int n)
{
void *entry;
unsigned int i = 0;
rcu_read_lock();
xas_for_each(xas, entry, max) {
if (xas_retry(xas, entry))
continue;
dst[i++] = entry;
if (i == n)
break;
}
rcu_read_unlock();
return i;
}
static unsigned int xas_extract_marked(struct xa_state *xas, void **dst,
unsigned long max, unsigned int n, xa_mark_t mark)
{
void *entry;
unsigned int i = 0;
rcu_read_lock();
xas_for_each_marked(xas, entry, max, mark) {
if (xas_retry(xas, entry))
continue;
dst[i++] = entry;
if (i == n)
break;
}
rcu_read_unlock();
return i;
}
/**
* xa_extract() - Copy selected entries from the XArray into a normal array.
* @xa: The source XArray to copy from.
* @dst: The buffer to copy entries into.
* @start: The first index in the XArray eligible to be selected.
* @max: The last index in the XArray eligible to be selected.
* @n: The maximum number of entries to copy.
* @filter: Selection criterion.
*
* Copies up to @n entries that match @filter from the XArray. The
* copied entries will have indices between @start and @max, inclusive.
*
* The @filter may be an XArray mark value, in which case entries which are
* marked with that mark will be copied. It may also be %XA_PRESENT, in
* which case all entries which are not %NULL will be copied.
*
* The entries returned may not represent a snapshot of the XArray at a
* moment in time. For example, if another thread stores to index 5, then
* index 10, calling xa_extract() may return the old contents of index 5
* and the new contents of index 10. Indices not modified while this
* function is running will not be skipped.
*
* If you need stronger guarantees, holding the xa_lock across calls to this
* function will prevent concurrent modification.
*
* Context: Any context. Takes and releases the RCU lock.
* Return: The number of entries copied.
*/
unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start,
unsigned long max, unsigned int n, xa_mark_t filter)
{
XA_STATE(xas, xa, start);
if (!n)
return 0;
if ((__force unsigned int)filter < XA_MAX_MARKS)
return xas_extract_marked(&xas, dst, max, n, filter);
return xas_extract_present(&xas, dst, max, n);
}
EXPORT_SYMBOL(xa_extract);
/**
* xa_delete_node() - Private interface for workingset code.
* @node: Node to be removed from the tree.
* @update: Function to call to update ancestor nodes.
*
* Context: xa_lock must be held on entry and will not be released.
*/
void xa_delete_node(struct xa_node *node, xa_update_node_t update)
{
struct xa_state xas = {
.xa = node->array,
.xa_index = (unsigned long)node->offset <<
(node->shift + XA_CHUNK_SHIFT),
.xa_shift = node->shift + XA_CHUNK_SHIFT,
.xa_offset = node->offset,
.xa_node = xa_parent_locked(node->array, node),
.xa_update = update,
};
xas_store(&xas, NULL);
}
EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */
/**
* xa_destroy() - Free all internal data structures.
* @xa: XArray.
*
* After calling this function, the XArray is empty and has freed all memory
* allocated for its internal data structures. You are responsible for
* freeing the objects referenced by the XArray.
*
* Context: Any context. Takes and releases the xa_lock, interrupt-safe.
*/
void xa_destroy(struct xarray *xa)
{
XA_STATE(xas, xa, 0);
unsigned long flags;
void *entry;
xas.xa_node = NULL;
xas_lock_irqsave(&xas, flags);
entry = xa_head_locked(xa);
RCU_INIT_POINTER(xa->xa_head, NULL);
xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK);
/* lockdep checks we're still holding the lock in xas_free_nodes() */
if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry));
xas_unlock_irqrestore(&xas, flags);
}
EXPORT_SYMBOL(xa_destroy);
#ifdef XA_DEBUG
void xa_dump_node(const struct xa_node *node)
{
unsigned i, j;
if (!node)
return;
if ((unsigned long)node & 3) {
pr_cont("node %px\n", node);
return;
}
pr_cont("node %px %s %d parent %px shift %d count %d values %d "
"array %px list %px %px marks",
node, node->parent ? "offset" : "max", node->offset,
node->parent, node->shift, node->count, node->nr_values,
node->array, node->private_list.prev, node->private_list.next);
for (i = 0; i < XA_MAX_MARKS; i++)
for (j = 0; j < XA_MARK_LONGS; j++)
pr_cont(" %lx", node->marks[i][j]);
pr_cont("\n");
}
void xa_dump_index(unsigned long index, unsigned int shift)
{
if (!shift)
pr_info("%lu: ", index);
else if (shift >= BITS_PER_LONG)
pr_info("0-%lu: ", ~0UL);
else
pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1));
}
void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift)
{
if (!entry)
return;
xa_dump_index(index, shift);
if (xa_is_node(entry)) {
if (shift == 0) {
pr_cont("%px\n", entry);
} else {
unsigned long i;
struct xa_node *node = xa_to_node(entry);
xa_dump_node(node);
for (i = 0; i < XA_CHUNK_SIZE; i++)
xa_dump_entry(node->slots[i],
index + (i << node->shift), node->shift);
}
} else if (xa_is_value(entry))
pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry),
xa_to_value(entry), entry);
else if (!xa_is_internal(entry))
pr_cont("%px\n", entry);
else if (xa_is_retry(entry))
pr_cont("retry (%ld)\n", xa_to_internal(entry));
else if (xa_is_sibling(entry))
pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry));
else if (xa_is_zero(entry))
pr_cont("zero (%ld)\n", xa_to_internal(entry));
else
pr_cont("UNKNOWN ENTRY (%px)\n", entry);
}
void xa_dump(const struct xarray *xa)
{
void *entry = xa->xa_head;
unsigned int shift = 0;
pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
xa->xa_flags, xa_marked(xa, XA_MARK_0),
xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2));
if (xa_is_node(entry))
shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
xa_dump_entry(entry, 0, shift);
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* VGIC MMIO handling functions
*/
#include <linux/bitops.h>
#include <linux/bsearch.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <kvm/iodev.h>
#include <kvm/arm_arch_timer.h>
#include <kvm/arm_vgic.h>
#include "vgic.h"
#include "vgic-mmio.h"
unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return 0;
}
unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return -1UL;
}
void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
unsigned int len, unsigned long val)
{
/* Ignore */
}
int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
unsigned int len, unsigned long val)
{
/* Ignore */
return 0;
}
unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
int i;
/* Loop over all IRQs affected by this read */
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
if (irq->group)
value |= BIT(i);
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
static void vgic_update_vsgi(struct vgic_irq *irq)
{
WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group));
}
void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr,
unsigned int len, unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
irq->group = !!(val & BIT(i));
if (irq->hw && vgic_irq_is_sgi(irq->intid)) { vgic_update_vsgi(irq);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
} else {
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
}
vgic_put_irq(vcpu->kvm, irq);
}
}
/*
* Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value
* of the enabled bit, so there is only one function for both here.
*/
unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
int i;
/* Loop over all IRQs affected by this read */
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
if (irq->enabled)
value |= (1U << i);
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw && vgic_irq_is_sgi(irq->intid)) { if (!irq->enabled) {
struct irq_data *data;
irq->enabled = true;
data = &irq_to_desc(irq->host_irq)->irq_data;
while (irqd_irq_disabled(data))
enable_irq(irq->host_irq);
}
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
continue;
} else if (vgic_irq_is_mapped_level(irq)) {
bool was_high = irq->line_level;
/*
* We need to update the state of the interrupt because
* the guest might have changed the state of the device
* while the interrupt was disabled at the VGIC level.
*/
irq->line_level = vgic_get_phys_line_level(irq);
/*
* Deactivate the physical interrupt so the GIC will let
* us know when it is asserted again.
*/
if (!irq->active && was_high && !irq->line_level) vgic_irq_set_phys_active(irq, false);
}
irq->enabled = true;
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) disable_irq_nosync(irq->host_irq);
irq->enabled = false;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
irq->enabled = true;
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_put_irq(vcpu->kvm, irq);
}
return 0;
}
int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
irq->enabled = false;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
return 0;
}
static unsigned long __read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
bool is_user)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
int i;
/* Loop over all IRQs affected by this read */
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
unsigned long flags;
bool val;
/*
* When used from userspace with a GICv3 model:
*
* Pending state of interrupt is latched in pending_latch
* variable. Userspace will save and restore pending state
* and line_level separately.
* Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
* for handling of ISPENDR and ICPENDR.
*/
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
int err;
val = false;
err = irq_get_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
&val);
WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
} else if (!is_user && vgic_irq_is_mapped_level(irq)) {
val = vgic_get_phys_line_level(irq);
} else {
switch (vcpu->kvm->arch.vgic.vgic_model) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
if (is_user) {
val = irq->pending_latch;
break;
}
fallthrough;
default:
val = irq_is_pending(irq);
break;
}
}
value |= ((u32)val << i);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return __read_pending(vcpu, addr, len, false);
}
unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return __read_pending(vcpu, addr, len, true);
}
static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
return (vgic_irq_is_sgi(irq->intid) &&
vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
}
static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
unsigned long val, bool is_user)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
/* GICD_ISPENDR0 SGI bits are WI when written from the guest. */
if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
vgic_put_irq(vcpu->kvm, irq);
continue;
}
raw_spin_lock_irqsave(&irq->irq_lock, flags);
/*
* GICv2 SGIs are terribly broken. We can't restore
* the source of the interrupt, so just pick the vcpu
* itself as the source...
*/
if (is_vgic_v2_sgi(vcpu, irq))
irq->source |= BIT(vcpu->vcpu_id);
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
/* HW SGI? Ask the GIC to inject it */
int err;
err = irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
true);
WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
continue;
}
irq->pending_latch = true;
if (irq->hw && !is_user)
vgic_irq_set_phys_active(irq, true);
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
__set_pending(vcpu, addr, len, val, false);
}
int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
__set_pending(vcpu, addr, len, val, true);
return 0;
}
/* Must be called with irq->irq_lock held */
static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
irq->pending_latch = false;
/*
* We don't want the guest to effectively mask the physical
* interrupt by doing a write to SPENDR followed by a write to
* CPENDR for HW interrupts, so we clear the active state on
* the physical side if the virtual interrupt is not active.
* This may lead to taking an additional interrupt on the
* host, but that should not be a problem as the worst that
* can happen is an additional vgic injection. We also clear
* the pending state to maintain proper semantics for edge HW
* interrupts.
*/
vgic_irq_set_phys_pending(irq, false);
if (!irq->active)
vgic_irq_set_phys_active(irq, false);
}
static void __clear_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val, bool is_user)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
/* GICD_ICPENDR0 SGI bits are WI when written from the guest. */
if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
vgic_put_irq(vcpu->kvm, irq);
continue;
}
raw_spin_lock_irqsave(&irq->irq_lock, flags);
/*
* More fun with GICv2 SGIs! If we're clearing one of them
* from userspace, which source vcpu to clear? Let's not
* even think of it, and blow the whole set.
*/
if (is_vgic_v2_sgi(vcpu, irq))
irq->source = 0;
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
/* HW SGI? Ask the GIC to clear its pending bit */
int err;
err = irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
false);
WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
continue;
}
if (irq->hw && !is_user)
vgic_hw_irq_cpending(vcpu, irq);
else
irq->pending_latch = false;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
__clear_pending(vcpu, addr, len, val, false);
}
int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
__clear_pending(vcpu, addr, len, val, true);
return 0;
}
/*
* If we are fiddling with an IRQ's active state, we have to make sure the IRQ
* is not queued on some running VCPU's LRs, because then the change to the
* active state can be overwritten when the VCPU's state is synced coming back
* from the guest.
*
* For shared interrupts as well as GICv3 private interrupts accessed from the
* non-owning CPU, we have to stop all the VCPUs because interrupts can be
* migrated while we don't hold the IRQ locks and we don't want to be chasing
* moving targets.
*
* For GICv2 private interrupts we don't have to do anything because
* userspace accesses to the VGIC state already require all VCPUs to be
* stopped, and only the VCPU itself can modify its private interrupts
* active state, which guarantees that the VCPU is not running.
*/
static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
{
if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 &&
vcpu != kvm_get_running_vcpu()) ||
intid >= VGIC_NR_PRIVATE_IRQS)
kvm_arm_halt_guest(vcpu->kvm);
}
/* See vgic_access_active_prepare */
static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid)
{
if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 &&
vcpu != kvm_get_running_vcpu()) ||
intid >= VGIC_NR_PRIVATE_IRQS)
kvm_arm_resume_guest(vcpu->kvm);
}
static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
int i;
/* Loop over all IRQs affected by this read */
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
/*
* Even for HW interrupts, don't evaluate the HW state as
* all the guest is interested in is the virtual state.
*/
if (irq->active)
value |= (1U << i);
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 val;
mutex_lock(&vcpu->kvm->arch.config_lock);
vgic_access_active_prepare(vcpu, intid);
val = __vgic_mmio_read_active(vcpu, addr, len);
vgic_access_active_finish(vcpu, intid);
mutex_unlock(&vcpu->kvm->arch.config_lock);
return val;
}
unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return __vgic_mmio_read_active(vcpu, addr, len);
}
/* Must be called with irq->irq_lock held */
static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
bool active, bool is_uaccess)
{
if (is_uaccess)
return;
irq->active = active;
vgic_irq_set_phys_active(irq, active);
}
static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
bool active)
{
unsigned long flags;
struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu();
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
/*
* GICv4.1 VSGI feature doesn't track an active state,
* so let's not kid ourselves, there is nothing we can
* do here.
*/
irq->active = false;
} else {
u32 model = vcpu->kvm->arch.vgic.vgic_model;
u8 active_source;
irq->active = active;
/*
* The GICv2 architecture indicates that the source CPUID for
* an SGI should be provided during an EOI which implies that
* the active state is stored somewhere, but at the same time
* this state is not architecturally exposed anywhere and we
* have no way of knowing the right source.
*
* This may lead to a VCPU not being able to receive
* additional instances of a particular SGI after migration
* for a GICv2 VM on some GIC implementations. Oh well.
*/
active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && active && vgic_irq_is_sgi(irq->intid)) irq->active_source = active_source;
}
if (irq->active)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
else
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
}
static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
vgic_mmio_change_active(vcpu, irq, false);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
mutex_lock(&vcpu->kvm->arch.config_lock);
vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid);
mutex_unlock(&vcpu->kvm->arch.config_lock);
}
int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
__vgic_mmio_write_cactive(vcpu, addr, len, val);
return 0;
}
static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
vgic_mmio_change_active(vcpu, irq, true);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
mutex_lock(&vcpu->kvm->arch.config_lock);
vgic_access_active_prepare(vcpu, intid);
__vgic_mmio_write_sactive(vcpu, addr, len, val);
vgic_access_active_finish(vcpu, intid);
mutex_unlock(&vcpu->kvm->arch.config_lock);
}
int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{ __vgic_mmio_write_sactive(vcpu, addr, len, val);
return 0;
}
unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
int i;
u64 val = 0;
for (i = 0; i < len; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
val |= (u64)irq->priority << (i * 8);
vgic_put_irq(vcpu->kvm, irq);
}
return val;
}
/*
* We currently don't handle changing the priority of an interrupt that
* is already pending on a VCPU. If there is a need for this, we would
* need to make this VCPU exit and re-evaluate the priorities, potentially
* leading to this interrupt getting presented now to the guest (if it has
* been masked by the priority mask before).
*/
void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
int i;
unsigned long flags;
for (i = 0; i < len; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
/* Narrow the priority range to what we actually support */
irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
if (irq->hw && vgic_irq_is_sgi(irq->intid)) vgic_update_vsgi(irq);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
u32 value = 0;
int i;
for (i = 0; i < len * 4; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i);
if (irq->config == VGIC_CONFIG_EDGE)
value |= (2U << (i * 2));
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
int i;
unsigned long flags;
for (i = 0; i < len * 4; i++) {
struct vgic_irq *irq;
/*
* The configuration cannot be changed for SGIs in general,
* for PPIs this is IMPLEMENTATION DEFINED. The arch timer
* code relies on PPIs being level triggered, so we also
* make them read-only here.
*/
if (intid + i < VGIC_NR_PRIVATE_IRQS)
continue;
irq = vgic_get_irq(vcpu->kvm, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (test_bit(i * 2 + 1, &val))
irq->config = VGIC_CONFIG_EDGE;
else
irq->config = VGIC_CONFIG_LEVEL;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
u32 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid)
{
int i;
u32 val = 0;
int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
for (i = 0; i < 32; i++) {
struct vgic_irq *irq;
if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs)
continue;
irq = vgic_get_vcpu_irq(vcpu, intid + i);
if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) val |= (1U << i);
vgic_put_irq(vcpu->kvm, irq);
}
return val;
}
void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid,
const u32 val)
{
int i;
int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
unsigned long flags;
for (i = 0; i < 32; i++) {
struct vgic_irq *irq;
bool new_level;
if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs)
continue;
irq = vgic_get_vcpu_irq(vcpu, intid + i);
/*
* Line level is set irrespective of irq type
* (level or edge) to avoid dependency that VM should
* restore irq config before line level.
*/
new_level = !!(val & (1U << i));
raw_spin_lock_irqsave(&irq->irq_lock, flags);
irq->line_level = new_level;
if (new_level)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
else
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
static int match_region(const void *key, const void *elt)
{
const unsigned int offset = (unsigned long)key;
const struct vgic_register_region *region = elt;
if (offset < region->reg_offset)
return -1;
if (offset >= region->reg_offset + region->len)
return 1;
return 0;
}
const struct vgic_register_region *
vgic_find_mmio_region(const struct vgic_register_region *regions,
int nr_regions, unsigned int offset)
{
return bsearch((void *)(uintptr_t)offset, regions, nr_regions,
sizeof(regions[0]), match_region);
}
void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_set_vmcr(vcpu, vmcr);
else
vgic_v3_set_vmcr(vcpu, vmcr);
}
void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_get_vmcr(vcpu, vmcr);
else
vgic_v3_get_vmcr(vcpu, vmcr);
}
/*
* kvm_mmio_read_buf() returns a value in a format where it can be converted
* to a byte array and be directly observed as the guest wanted it to appear
* in memory if it had done the store itself, which is LE for the GIC, as the
* guest knows the GIC is always LE.
*
* We convert this value to the CPUs native format to deal with it as a data
* value.
*/
unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len)
{
unsigned long data = kvm_mmio_read_buf(val, len);
switch (len) {
case 1:
return data;
case 2:
return le16_to_cpu(data);
case 4:
return le32_to_cpu(data);
default:
return le64_to_cpu(data);
}
}
/*
* kvm_mmio_write_buf() expects a value in a format such that if converted to
* a byte array it is observed as the guest would see it if it could perform
* the load directly. Since the GIC is LE, and the guest knows this, the
* guest expects a value in little endian format.
*
* We convert the data value from the CPUs native format to LE so that the
* value is returned in the proper format.
*/
void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
unsigned long data)
{
switch (len) {
case 1:
break;
case 2:
data = cpu_to_le16(data);
break;
case 4:
data = cpu_to_le32(data);
break;
default:
data = cpu_to_le64(data);
}
kvm_mmio_write_buf(buf, len, data);
}
static
struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
{
return container_of(dev, struct vgic_io_device, dev);
}
static bool check_region(const struct kvm *kvm,
const struct vgic_register_region *region,
gpa_t addr, int len)
{
int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
switch (len) {
case sizeof(u8):
flags = VGIC_ACCESS_8bit;
break;
case sizeof(u32):
flags = VGIC_ACCESS_32bit;
break;
case sizeof(u64):
flags = VGIC_ACCESS_64bit;
break;
default:
return false;
}
if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { if (!region->bits_per_irq)
return true;
/* Do we access a non-allocated IRQ? */
return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs;
}
return false;
}
const struct vgic_register_region *
vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
gpa_t addr, int len)
{
const struct vgic_register_region *region;
region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
addr - iodev->base_addr);
if (!region || !check_region(vcpu->kvm, region, addr, len))
return NULL;
return region;
}
static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
gpa_t addr, u32 *val)
{
const struct vgic_register_region *region;
struct kvm_vcpu *r_vcpu;
region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32));
if (!region) {
*val = 0;
return 0;
}
r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
if (region->uaccess_read)
*val = region->uaccess_read(r_vcpu, addr, sizeof(u32));
else
*val = region->read(r_vcpu, addr, sizeof(u32));
return 0;
}
static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
gpa_t addr, const u32 *val)
{
const struct vgic_register_region *region;
struct kvm_vcpu *r_vcpu;
region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32));
if (!region)
return 0;
r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
if (region->uaccess_write)
return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); region->write(r_vcpu, addr, sizeof(u32), *val);
return 0;
}
/*
* Userland access to VGIC registers.
*/
int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev,
bool is_write, int offset, u32 *val)
{
if (is_write)
return vgic_uaccess_write(vcpu, dev, offset, val);
else
return vgic_uaccess_read(vcpu, dev, offset, val);
}
static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, void *val)
{
struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
const struct vgic_register_region *region;
unsigned long data = 0;
region = vgic_get_mmio_region(vcpu, iodev, addr, len);
if (!region) {
memset(val, 0, len);
return 0;
}
switch (iodev->iodev_type) {
case IODEV_CPUIF:
data = region->read(vcpu, addr, len);
break;
case IODEV_DIST:
data = region->read(vcpu, addr, len);
break;
case IODEV_REDIST:
data = region->read(iodev->redist_vcpu, addr, len);
break;
case IODEV_ITS:
data = region->its_read(vcpu->kvm, iodev->its, addr, len);
break;
}
vgic_data_host_to_mmio_bus(val, len, data);
return 0;
}
static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, const void *val)
{
struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
const struct vgic_register_region *region;
unsigned long data = vgic_data_mmio_bus_to_host(val, len); region = vgic_get_mmio_region(vcpu, iodev, addr, len);
if (!region)
return 0;
switch (iodev->iodev_type) {
case IODEV_CPUIF:
region->write(vcpu, addr, len, data);
break;
case IODEV_DIST:
region->write(vcpu, addr, len, data);
break;
case IODEV_REDIST:
region->write(iodev->redist_vcpu, addr, len, data);
break;
case IODEV_ITS:
region->its_write(vcpu->kvm, iodev->its, addr, len, data);
break;
}
return 0;
}
const struct kvm_io_device_ops kvm_io_gic_ops = {
.read = dispatch_mmio_read,
.write = dispatch_mmio_write,
};
int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
enum vgic_type type)
{
struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev;
unsigned int len;
switch (type) {
case VGIC_V2:
len = vgic_v2_init_dist_iodev(io_device);
break;
case VGIC_V3:
len = vgic_v3_init_dist_iodev(io_device);
break;
default:
BUG_ON(1);
}
io_device->base_addr = dist_base_address;
io_device->iodev_type = IODEV_DIST;
io_device->redist_vcpu = NULL;
return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address,
len, &io_device->dev);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MEMREMAP_H_
#define _LINUX_MEMREMAP_H_
#include <linux/mmzone.h>
#include <linux/range.h>
#include <linux/ioport.h>
#include <linux/percpu-refcount.h>
struct resource;
struct device;
/**
* struct vmem_altmap - pre-allocated storage for vmemmap_populate
* @base_pfn: base of the entire dev_pagemap mapping
* @reserve: pages mapped, but reserved for driver use (relative to @base)
* @free: free pages set aside in the mapping for memmap storage
* @align: pages reserved to meet allocation alignments
* @alloc: track pages consumed, private to vmemmap_populate()
*/
struct vmem_altmap {
unsigned long base_pfn;
const unsigned long end_pfn;
const unsigned long reserve;
unsigned long free;
unsigned long align;
unsigned long alloc;
bool inaccessible;
};
/*
* Specialize ZONE_DEVICE memory into multiple types each has a different
* usage.
*
* MEMORY_DEVICE_PRIVATE:
* Device memory that is not directly addressable by the CPU: CPU can neither
* read nor write private memory. In this case, we do still have struct pages
* backing the device memory. Doing so simplifies the implementation, but it is
* important to remember that there are certain points at which the struct page
* must be treated as an opaque object, rather than a "normal" struct page.
*
* A more complete discussion of unaddressable memory may be found in
* include/linux/hmm.h and Documentation/mm/hmm.rst.
*
* MEMORY_DEVICE_COHERENT:
* Device memory that is cache coherent from device and CPU point of view. This
* is used on platforms that have an advanced system bus (like CAPI or CXL). A
* driver can hotplug the device memory using ZONE_DEVICE and with that memory
* type. Any page of a process can be migrated to such memory. However no one
* should be allowed to pin such memory so that it can always be evicted.
*
* MEMORY_DEVICE_FS_DAX:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. In support of coordinating page
* pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
* wakeup event whenever a page is unpinned and becomes idle. This
* wakeup is used to coordinate physical address space management (ex:
* fs truncate/hole punch) vs pinned pages (ex: device dma).
*
* MEMORY_DEVICE_GENERIC:
* Host memory that has similar access semantics as System RAM i.e. DMA
* coherent and supports page pinning. This is for example used by DAX devices
* that expose memory using a character device.
*
* MEMORY_DEVICE_PCI_P2PDMA:
* Device memory residing in a PCI BAR intended for use with Peer-to-Peer
* transactions.
*/
enum memory_type {
/* 0 is reserved to catch uninitialized type fields */
MEMORY_DEVICE_PRIVATE = 1,
MEMORY_DEVICE_COHERENT,
MEMORY_DEVICE_FS_DAX,
MEMORY_DEVICE_GENERIC,
MEMORY_DEVICE_PCI_P2PDMA,
};
struct dev_pagemap_ops {
/*
* Called once the page refcount reaches 0. The reference count will be
* reset to one by the core code after the method is called to prepare
* for handing out the page again.
*/
void (*page_free)(struct page *page);
/*
* Used for private (un-addressable) device memory only. Must migrate
* the page back to a CPU accessible page.
*/
vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf);
/*
* Handle the memory failure happens on a range of pfns. Notify the
* processes who are using these pfns, and try to recover the data on
* them if necessary. The mf_flags is finally passed to the recover
* function through the whole notify routine.
*
* When this is not implemented, or it returns -EOPNOTSUPP, the caller
* will fall back to a common handler called mf_generic_kill_procs().
*/
int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
unsigned long nr_pages, int mf_flags);
};
#define PGMAP_ALTMAP_VALID (1 << 0)
/**
* struct dev_pagemap - metadata for ZONE_DEVICE mappings
* @altmap: pre-allocated/reserved memory for vmemmap allocations
* @ref: reference count that pins the devm_memremap_pages() mapping
* @done: completion for @ref
* @type: memory type: see MEMORY_* above in memremap.h
* @flags: PGMAP_* flags to specify defailed behavior
* @vmemmap_shift: structural definition of how the vmemmap page metadata
* is populated, specifically the metadata page order.
* A zero value (default) uses base pages as the vmemmap metadata
* representation. A bigger value will set up compound struct pages
* of the requested order value.
* @ops: method table
* @owner: an opaque pointer identifying the entity that manages this
* instance. Used by various helpers to make sure that no
* foreign ZONE_DEVICE memory is accessed.
* @nr_range: number of ranges to be mapped
* @range: range to be mapped when nr_range == 1
* @ranges: array of ranges to be mapped when nr_range > 1
*/
struct dev_pagemap {
struct vmem_altmap altmap;
struct percpu_ref ref;
struct completion done;
enum memory_type type;
unsigned int flags;
unsigned long vmemmap_shift;
const struct dev_pagemap_ops *ops;
void *owner;
int nr_range;
union {
struct range range;
DECLARE_FLEX_ARRAY(struct range, ranges);
};
};
static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap)
{
return pgmap->ops && pgmap->ops->memory_failure;
}
static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
{
if (pgmap->flags & PGMAP_ALTMAP_VALID)
return &pgmap->altmap;
return NULL;
}
static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap)
{
return 1 << pgmap->vmemmap_shift;
}
static inline bool is_device_private_page(const struct page *page)
{
return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
is_zone_device_page(page) &&
page_pgmap(page)->type == MEMORY_DEVICE_PRIVATE;
}
static inline bool folio_is_device_private(const struct folio *folio)
{
return is_device_private_page(&folio->page);
}
static inline bool is_pci_p2pdma_page(const struct page *page)
{
return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
is_zone_device_page(page) &&
page_pgmap(page)->type == MEMORY_DEVICE_PCI_P2PDMA;
}
static inline bool is_device_coherent_page(const struct page *page)
{
return is_zone_device_page(page) && page_pgmap(page)->type == MEMORY_DEVICE_COHERENT;
}
static inline bool folio_is_device_coherent(const struct folio *folio)
{
return is_device_coherent_page(&folio->page);
}
static inline bool is_fsdax_page(const struct page *page)
{
return is_zone_device_page(page) && page_pgmap(page)->type == MEMORY_DEVICE_FS_DAX;
}
static inline bool folio_is_fsdax(const struct folio *folio)
{
return is_fsdax_page(&folio->page);
}
#ifdef CONFIG_ZONE_DEVICE
void zone_device_page_init(struct page *page);
void *memremap_pages(struct dev_pagemap *pgmap, int nid);
void memunmap_pages(struct dev_pagemap *pgmap);
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
struct dev_pagemap *pgmap);
bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
unsigned long memremap_compat_align(void);
#else
static inline void *devm_memremap_pages(struct device *dev,
struct dev_pagemap *pgmap)
{
/*
* Fail attempts to call devm_memremap_pages() without
* ZONE_DEVICE support enabled, this requires callers to fall
* back to plain devm_memremap() based on config
*/
WARN_ON_ONCE(1);
return ERR_PTR(-ENXIO);
}
static inline void devm_memunmap_pages(struct device *dev,
struct dev_pagemap *pgmap)
{
}
static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
struct dev_pagemap *pgmap)
{
return NULL;
}
static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
{
return false;
}
/* when memremap_pages() is disabled all archs can remap a single page */
static inline unsigned long memremap_compat_align(void)
{
return PAGE_SIZE;
}
#endif /* CONFIG_ZONE_DEVICE */
static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
{
if (pgmap)
percpu_ref_put(&pgmap->ref);
}
#endif /* _LINUX_MEMREMAP_H_ */
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright 2019 Arm Limited
* Author: Andrew Murray <Andrew.Murray@arm.com>
*/
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
#include <linux/perf/arm_pmu.h>
#include <linux/perf/arm_pmuv3.h>
static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events);
/*
* Given the perf event attributes and system type, determine
* if we are going to need to switch counters at guest entry/exit.
*/
static bool kvm_pmu_switch_needed(struct perf_event_attr *attr)
{
/**
* With VHE the guest kernel runs at EL1 and the host at EL2,
* where user (EL0) is excluded then we have no reason to switch
* counters.
*/
if (has_vhe() && attr->exclude_user)
return false;
/* Only switch if attributes are different */
return (attr->exclude_host != attr->exclude_guest);
}
struct kvm_pmu_events *kvm_get_pmu_events(void)
{
return this_cpu_ptr(&kvm_pmu_events);
}
/*
* Add events to track that we may want to switch at guest entry/exit
* time.
*/
void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
if (!system_supports_pmuv3() || !kvm_pmu_switch_needed(attr))
return;
if (!attr->exclude_host) pmu->events_host |= set; if (!attr->exclude_guest) pmu->events_guest |= set;
}
/*
* Stop tracking events
*/
void kvm_clr_pmu_events(u64 clr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
if (!system_supports_pmuv3())
return;
pmu->events_host &= ~clr;
pmu->events_guest &= ~clr;
}
/*
* Read a value direct from PMEVTYPER<idx> where idx is 0-30
* or PMxCFILTR_EL0 where idx is 31-32.
*/
static u64 kvm_vcpu_pmu_read_evtype_direct(int idx)
{
if (idx == ARMV8_PMU_CYCLE_IDX)
return read_pmccfiltr();
else if (idx == ARMV8_PMU_INSTR_IDX)
return read_pmicfiltr(); return read_pmevtypern(idx);
}
/*
* Write a value direct to PMEVTYPER<idx> where idx is 0-30
* or PMxCFILTR_EL0 where idx is 31-32.
*/
static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val)
{
if (idx == ARMV8_PMU_CYCLE_IDX)
write_pmccfiltr(val);
else if (idx == ARMV8_PMU_INSTR_IDX)
write_pmicfiltr(val);
else
write_pmevtypern(idx, val);
}
/*
* Modify ARMv8 PMU events to include EL0 counting
*/
static void kvm_vcpu_pmu_enable_el0(unsigned long events)
{
u64 typer;
u32 counter;
for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) {
typer = kvm_vcpu_pmu_read_evtype_direct(counter);
typer &= ~ARMV8_PMU_EXCLUDE_EL0;
kvm_vcpu_pmu_write_evtype_direct(counter, typer);
}
}
/*
* Modify ARMv8 PMU events to exclude EL0 counting
*/
static void kvm_vcpu_pmu_disable_el0(unsigned long events)
{
u64 typer;
u32 counter;
for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) {
typer = kvm_vcpu_pmu_read_evtype_direct(counter);
typer |= ARMV8_PMU_EXCLUDE_EL0;
kvm_vcpu_pmu_write_evtype_direct(counter, typer);
}
}
/*
* On VHE ensure that only guest events have EL0 counting enabled.
* This is called from both vcpu_{load,put} and the sysreg handling.
* Since the latter is preemptible, special care must be taken to
* disable preemption.
*/
void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
{
struct kvm_pmu_events *pmu;
u64 events_guest, events_host;
if (!system_supports_pmuv3() || !has_vhe())
return;
preempt_disable();
pmu = kvm_get_pmu_events();
events_guest = pmu->events_guest;
events_host = pmu->events_host;
kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); preempt_enable();
}
/*
* On VHE ensure that only host events have EL0 counting enabled
*/
void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
{
struct kvm_pmu_events *pmu;
u64 events_guest, events_host;
if (!system_supports_pmuv3() || !has_vhe())
return;
pmu = kvm_get_pmu_events();
events_guest = pmu->events_guest;
events_host = pmu->events_host;
kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest);
}
/*
* With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU
* where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched
* to the value for the guest on vcpu_load(). The value for the host EL0
* will be restored on vcpu_put(), before returning to userspace.
* This isn't necessary for nVHE, as the register is context switched for
* every guest enter/exit.
*
* Return true if KVM takes care of the register. Otherwise return false.
*/
bool kvm_set_pmuserenr(u64 val)
{
struct kvm_cpu_context *hctxt;
struct kvm_vcpu *vcpu;
if (!system_supports_pmuv3() || !has_vhe())
return false;
vcpu = kvm_get_running_vcpu();
if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU))
return false;
hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val;
return true;
}
/*
* If we interrupted the guest to update the host PMU context, make
* sure we re-apply the guest EL0 state.
*/
void kvm_vcpu_pmu_resync_el0(void)
{
struct kvm_vcpu *vcpu;
if (!has_vhe() || !in_interrupt())
return;
vcpu = kvm_get_running_vcpu();
if (!vcpu)
return;
kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_LIST_BL_H
#define _LINUX_LIST_BL_H
#include <linux/list.h>
#include <linux/bit_spinlock.h>
/*
* Special version of lists, where head of the list has a lock in the lowest
* bit. This is useful for scalable hash tables without increasing memory
* footprint overhead.
*
* For modification operations, the 0 bit of hlist_bl_head->first
* pointer must be set.
*
* With some small modifications, this can easily be adapted to store several
* arbitrary bits (not just a single lock bit), if the need arises to store
* some fast and compact auxiliary data.
*/
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
#define LIST_BL_LOCKMASK 1UL
#else
#define LIST_BL_LOCKMASK 0UL
#endif
#ifdef CONFIG_DEBUG_LIST
#define LIST_BL_BUG_ON(x) BUG_ON(x)
#else
#define LIST_BL_BUG_ON(x)
#endif
struct hlist_bl_head {
struct hlist_bl_node *first;
};
struct hlist_bl_node {
struct hlist_bl_node *next, **pprev;
};
#define INIT_HLIST_BL_HEAD(ptr) \
((ptr)->first = NULL)
static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
{
h->next = NULL;
h->pprev = NULL;
}
#define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member)
static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h)
{
return !h->pprev;
}
static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h)
{
return (struct hlist_bl_node *)
((unsigned long)h->first & ~LIST_BL_LOCKMASK);
}
static inline void hlist_bl_set_first(struct hlist_bl_head *h,
struct hlist_bl_node *n)
{
LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) !=
LIST_BL_LOCKMASK);
h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK);
}
static inline bool hlist_bl_empty(const struct hlist_bl_head *h)
{
return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK);
}
static inline void hlist_bl_add_head(struct hlist_bl_node *n,
struct hlist_bl_head *h)
{
struct hlist_bl_node *first = hlist_bl_first(h);
n->next = first;
if (first) first->pprev = &n->next;
n->pprev = &h->first;
hlist_bl_set_first(h, n);
}
static inline void hlist_bl_add_before(struct hlist_bl_node *n,
struct hlist_bl_node *next)
{
struct hlist_bl_node **pprev = next->pprev;
n->pprev = pprev;
n->next = next;
next->pprev = &n->next;
/* pprev may be `first`, so be careful not to lose the lock bit */
WRITE_ONCE(*pprev,
(struct hlist_bl_node *)
((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK)));
}
static inline void hlist_bl_add_behind(struct hlist_bl_node *n,
struct hlist_bl_node *prev)
{
n->next = prev->next;
n->pprev = &prev->next;
prev->next = n;
if (n->next)
n->next->pprev = &n->next;
}
static inline void __hlist_bl_del(struct hlist_bl_node *n)
{
struct hlist_bl_node *next = n->next;
struct hlist_bl_node **pprev = n->pprev;
LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
/* pprev may be `first`, so be careful not to lose the lock bit */
WRITE_ONCE(*pprev,
(struct hlist_bl_node *)
((unsigned long)next |
((unsigned long)*pprev & LIST_BL_LOCKMASK)));
if (next) next->pprev = pprev;
}
static inline void hlist_bl_del(struct hlist_bl_node *n)
{
__hlist_bl_del(n);
n->next = LIST_POISON1;
n->pprev = LIST_POISON2;
}
static inline void hlist_bl_del_init(struct hlist_bl_node *n)
{
if (!hlist_bl_unhashed(n)) {
__hlist_bl_del(n);
INIT_HLIST_BL_NODE(n);
}
}
static inline void hlist_bl_lock(struct hlist_bl_head *b)
{
bit_spin_lock(0, (unsigned long *)b);
}
static inline void hlist_bl_unlock(struct hlist_bl_head *b)
{
__bit_spin_unlock(0, (unsigned long *)b);
}
static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
{
return bit_spin_is_locked(0, (unsigned long *)b);
}
/**
* hlist_bl_for_each_entry - iterate over list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*
*/
#define hlist_bl_for_each_entry(tpos, pos, head, member) \
for (pos = hlist_bl_first(head); \
pos && \
({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
/**
* hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_node to use as a loop cursor.
* @n: another &struct hlist_node to use as temporary storage
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \
for (pos = hlist_bl_first(head); \
pos && ({ n = pos->next; 1; }) && \
({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
pos = n)
#endif
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Definitions for the 'struct sk_buff' memory handlers.
*
* Authors:
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Florian La Roche, <rzsfl@rz.uni-sb.de>
*/
#ifndef _LINUX_SKBUFF_H
#define _LINUX_SKBUFF_H
#include <linux/kernel.h>
#include <linux/compiler.h>
#include <linux/time.h>
#include <linux/bug.h>
#include <linux/bvec.h>
#include <linux/cache.h>
#include <linux/rbtree.h>
#include <linux/socket.h>
#include <linux/refcount.h>
#include <linux/atomic.h>
#include <asm/types.h>
#include <linux/spinlock.h>
#include <net/checksum.h>
#include <linux/rcupdate.h>
#include <linux/dma-mapping.h>
#include <linux/netdev_features.h>
#include <net/flow_dissector.h>
#include <linux/in6.h>
#include <linux/if_packet.h>
#include <linux/llist.h>
#include <linux/page_frag_cache.h>
#include <net/flow.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <linux/netfilter/nf_conntrack_common.h>
#endif
#include <net/net_debug.h>
#include <net/dropreason-core.h>
#include <net/netmem.h>
/**
* DOC: skb checksums
*
* The interface for checksum offload between the stack and networking drivers
* is as follows...
*
* IP checksum related features
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* Drivers advertise checksum offload capabilities in the features of a device.
* From the stack's point of view these are capabilities offered by the driver.
* A driver typically only advertises features that it is capable of offloading
* to its device.
*
* .. flat-table:: Checksum related device features
* :widths: 1 10
*
* * - %NETIF_F_HW_CSUM
* - The driver (or its device) is able to compute one
* IP (one's complement) checksum for any combination
* of protocols or protocol layering. The checksum is
* computed and set in a packet per the CHECKSUM_PARTIAL
* interface (see below).
*
* * - %NETIF_F_IP_CSUM
* - Driver (device) is only able to checksum plain
* TCP or UDP packets over IPv4. These are specifically
* unencapsulated packets of the form IPv4|TCP or
* IPv4|UDP where the Protocol field in the IPv4 header
* is TCP or UDP. The IPv4 header may contain IP options.
* This feature cannot be set in features for a device
* with NETIF_F_HW_CSUM also set. This feature is being
* DEPRECATED (see below).
*
* * - %NETIF_F_IPV6_CSUM
* - Driver (device) is only able to checksum plain
* TCP or UDP packets over IPv6. These are specifically
* unencapsulated packets of the form IPv6|TCP or
* IPv6|UDP where the Next Header field in the IPv6
* header is either TCP or UDP. IPv6 extension headers
* are not supported with this feature. This feature
* cannot be set in features for a device with
* NETIF_F_HW_CSUM also set. This feature is being
* DEPRECATED (see below).
*
* * - %NETIF_F_RXCSUM
* - Driver (device) performs receive checksum offload.
* This flag is only used to disable the RX checksum
* feature for a device. The stack will accept receive
* checksum indication in packets received on a device
* regardless of whether NETIF_F_RXCSUM is set.
*
* Checksumming of received packets by device
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* Indication of checksum verification is set in &sk_buff.ip_summed.
* Possible values are:
*
* - %CHECKSUM_NONE
*
* Device did not checksum this packet e.g. due to lack of capabilities.
* The packet contains full (though not verified) checksum in packet but
* not in skb->csum. Thus, skb->csum is undefined in this case.
*
* - %CHECKSUM_UNNECESSARY
*
* The hardware you're dealing with doesn't calculate the full checksum
* (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums
* for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY
* if their checksums are okay. &sk_buff.csum is still undefined in this case
* though. A driver or device must never modify the checksum field in the
* packet even if checksum is verified.
*
* %CHECKSUM_UNNECESSARY is applicable to following protocols:
*
* - TCP: IPv6 and IPv4.
* - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
* zero UDP checksum for either IPv4 or IPv6, the networking stack
* may perform further validation in this case.
* - GRE: only if the checksum is present in the header.
* - SCTP: indicates the CRC in SCTP header has been validated.
* - FCOE: indicates the CRC in FC frame has been validated.
*
* &sk_buff.csum_level indicates the number of consecutive checksums found in
* the packet minus one that have been verified as %CHECKSUM_UNNECESSARY.
* For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet
* and a device is able to verify the checksums for UDP (possibly zero),
* GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to
* two. If the device were only able to verify the UDP checksum and not
* GRE, either because it doesn't support GRE checksum or because GRE
* checksum is bad, skb->csum_level would be set to zero (TCP checksum is
* not considered in this case).
*
* - %CHECKSUM_COMPLETE
*
* This is the most generic way. The device supplied checksum of the _whole_
* packet as seen by netif_rx() and fills in &sk_buff.csum. This means the
* hardware doesn't need to parse L3/L4 headers to implement this.
*
* Notes:
*
* - Even if device supports only some protocols, but is able to produce
* skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY.
* - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols.
*
* - %CHECKSUM_PARTIAL
*
* A checksum is set up to be offloaded to a device as described in the
* output description for CHECKSUM_PARTIAL. This may occur on a packet
* received directly from another Linux OS, e.g., a virtualized Linux kernel
* on the same host, or it may be set in the input path in GRO or remote
* checksum offload. For the purposes of checksum verification, the checksum
* referred to by skb->csum_start + skb->csum_offset and any preceding
* checksums in the packet are considered verified. Any checksums in the
* packet that are after the checksum being offloaded are not considered to
* be verified.
*
* Checksumming on transmit for non-GSO
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* The stack requests checksum offload in the &sk_buff.ip_summed for a packet.
* Values are:
*
* - %CHECKSUM_PARTIAL
*
* The driver is required to checksum the packet as seen by hard_start_xmit()
* from &sk_buff.csum_start up to the end, and to record/write the checksum at
* offset &sk_buff.csum_start + &sk_buff.csum_offset.
* A driver may verify that the
* csum_start and csum_offset values are valid values given the length and
* offset of the packet, but it should not attempt to validate that the
* checksum refers to a legitimate transport layer checksum -- it is the
* purview of the stack to validate that csum_start and csum_offset are set
* correctly.
*
* When the stack requests checksum offload for a packet, the driver MUST
* ensure that the checksum is set correctly. A driver can either offload the
* checksum calculation to the device, or call skb_checksum_help (in the case
* that the device does not support offload for a particular checksum).
*
* %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of
* %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate
* checksum offload capability.
* skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based
* on network device checksumming capabilities: if a packet does not match
* them, skb_checksum_help() or skb_crc32c_help() (depending on the value of
* &sk_buff.csum_not_inet, see :ref:`crc`)
* is called to resolve the checksum.
*
* - %CHECKSUM_NONE
*
* The skb was already checksummed by the protocol, or a checksum is not
* required.
*
* - %CHECKSUM_UNNECESSARY
*
* This has the same meaning as CHECKSUM_NONE for checksum offload on
* output.
*
* - %CHECKSUM_COMPLETE
*
* Not used in checksum output. If a driver observes a packet with this value
* set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set.
*
* .. _crc:
*
* Non-IP checksum (CRC) offloads
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* .. flat-table::
* :widths: 1 10
*
* * - %NETIF_F_SCTP_CRC
* - This feature indicates that a device is capable of
* offloading the SCTP CRC in a packet. To perform this offload the stack
* will set csum_start and csum_offset accordingly, set ip_summed to
* %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication
* in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c.
* A driver that supports both IP checksum offload and SCTP CRC32c offload
* must verify which offload is configured for a packet by testing the
* value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to
* resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1.
*
* * - %NETIF_F_FCOE_CRC
* - This feature indicates that a device is capable of offloading the FCOE
* CRC in a packet. To perform this offload the stack will set ip_summed
* to %CHECKSUM_PARTIAL and set csum_start and csum_offset
* accordingly. Note that there is no indication in the skbuff that the
* %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports
* both IP checksum offload and FCOE CRC offload must verify which offload
* is configured for a packet, presumably by inspecting packet headers.
*
* Checksumming on output with GSO
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* In the case of a GSO packet (skb_is_gso() is true), checksum offload
* is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the
* gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as
* part of the GSO operation is implied. If a checksum is being offloaded
* with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and
* csum_offset are set to refer to the outermost checksum being offloaded
* (two offloaded checksums are possible with UDP encapsulation).
*/
/* Don't change this without changing skb_csum_unnecessary! */
#define CHECKSUM_NONE 0
#define CHECKSUM_UNNECESSARY 1
#define CHECKSUM_COMPLETE 2
#define CHECKSUM_PARTIAL 3
/* Maximum value in skb->csum_level */
#define SKB_MAX_CSUM_LEVEL 3
#define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES)
#define SKB_WITH_OVERHEAD(X) \
((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
/* For X bytes available in skb->head, what is the minimal
* allocation needed, knowing struct skb_shared_info needs
* to be aligned.
*/
#define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define SKB_MAX_ORDER(X, ORDER) \
SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X))
#define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0))
#define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2))
/* return minimum truesize of one skb containing X bytes of data */
#define SKB_TRUESIZE(X) ((X) + \
SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
struct ahash_request;
struct net_device;
struct scatterlist;
struct pipe_inode_info;
struct iov_iter;
struct napi_struct;
struct bpf_prog;
union bpf_attr;
struct skb_ext;
struct ts_config;
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
struct nf_bridge_info {
enum {
BRNF_PROTO_UNCHANGED,
BRNF_PROTO_8021Q,
BRNF_PROTO_PPPOE
} orig_proto:8;
u8 pkt_otherhost:1;
u8 in_prerouting:1;
u8 bridged_dnat:1;
u8 sabotage_in_done:1;
__u16 frag_max_size;
int physinif;
/* always valid & non-NULL from FORWARD on, for physdev match */
struct net_device *physoutdev;
union {
/* prerouting: detect dnat in orig/reply direction */
__be32 ipv4_daddr;
struct in6_addr ipv6_daddr;
/* after prerouting + nat detected: store original source
* mac since neigh resolution overwrites it, only used while
* skb is out in neigh layer.
*/
char neigh_header[8];
};
};
#endif
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
/* Chain in tc_skb_ext will be used to share the tc chain with
* ovs recirc_id. It will be set to the current chain by tc
* and read by ovs to recirc_id.
*/
struct tc_skb_ext {
union {
u64 act_miss_cookie;
__u32 chain;
};
__u16 mru;
__u16 zone;
u8 post_ct:1;
u8 post_ct_snat:1;
u8 post_ct_dnat:1;
u8 act_miss:1; /* Set if act_miss_cookie is used */
u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */
};
#endif
struct sk_buff_head {
/* These two members must be first to match sk_buff. */
struct_group_tagged(sk_buff_list, list,
struct sk_buff *next;
struct sk_buff *prev;
);
__u32 qlen;
spinlock_t lock;
};
struct sk_buff;
#ifndef CONFIG_MAX_SKB_FRAGS
# define CONFIG_MAX_SKB_FRAGS 17
#endif
#define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS
/* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to
* segment using its current segmentation instead.
*/
#define GSO_BY_FRAGS 0xFFFF
typedef struct skb_frag {
netmem_ref netmem;
unsigned int len;
unsigned int offset;
} skb_frag_t;
/**
* skb_frag_size() - Returns the size of a skb fragment
* @frag: skb fragment
*/
static inline unsigned int skb_frag_size(const skb_frag_t *frag)
{
return frag->len;
}
/**
* skb_frag_size_set() - Sets the size of a skb fragment
* @frag: skb fragment
* @size: size of fragment
*/
static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size)
{
frag->len = size;
}
/**
* skb_frag_size_add() - Increments the size of a skb fragment by @delta
* @frag: skb fragment
* @delta: value to add
*/
static inline void skb_frag_size_add(skb_frag_t *frag, int delta)
{
frag->len += delta;
}
/**
* skb_frag_size_sub() - Decrements the size of a skb fragment by @delta
* @frag: skb fragment
* @delta: value to subtract
*/
static inline void skb_frag_size_sub(skb_frag_t *frag, int delta)
{
frag->len -= delta;
}
/**
* skb_frag_must_loop - Test if %p is a high memory page
* @p: fragment's page
*/
static inline bool skb_frag_must_loop(struct page *p)
{
#if defined(CONFIG_HIGHMEM)
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p))
return true;
#endif
return false;
}
/**
* skb_frag_foreach_page - loop over pages in a fragment
*
* @f: skb frag to operate on
* @f_off: offset from start of f->netmem
* @f_len: length from f_off to loop over
* @p: (temp var) current page
* @p_off: (temp var) offset from start of current page,
* non-zero only on first page.
* @p_len: (temp var) length in current page,
* < PAGE_SIZE only on first and last page.
* @copied: (temp var) length so far, excluding current p_len.
*
* A fragment can hold a compound page, in which case per-page
* operations, notably kmap_atomic, must be called for each
* regular page.
*/
#define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \
for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \
p_off = (f_off) & (PAGE_SIZE - 1), \
p_len = skb_frag_must_loop(p) ? \
min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \
copied = 0; \
copied < f_len; \
copied += p_len, p++, p_off = 0, \
p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \
/**
* struct skb_shared_hwtstamps - hardware time stamps
* @hwtstamp: hardware time stamp transformed into duration
* since arbitrary point in time
* @netdev_data: address/cookie of network device driver used as
* reference to actual hardware time stamp
*
* Software time stamps generated by ktime_get_real() are stored in
* skb->tstamp.
*
* hwtstamps can only be compared against other hwtstamps from
* the same device.
*
* This structure is attached to packets as part of the
* &skb_shared_info. Use skb_hwtstamps() to get a pointer.
*/
struct skb_shared_hwtstamps {
union {
ktime_t hwtstamp;
void *netdev_data;
};
};
/* Definitions for tx_flags in struct skb_shared_info */
enum {
/* generate hardware time stamp */
SKBTX_HW_TSTAMP_NOBPF = 1 << 0,
/* generate software time stamp when queueing packet to NIC */
SKBTX_SW_TSTAMP = 1 << 1,
/* device driver is going to provide hardware time stamp */
SKBTX_IN_PROGRESS = 1 << 2,
/* generate software time stamp on packet tx completion */
SKBTX_COMPLETION_TSTAMP = 1 << 3,
/* generate wifi status information (where possible) */
SKBTX_WIFI_STATUS = 1 << 4,
/* determine hardware time stamp based on time or cycles */
SKBTX_HW_TSTAMP_NETDEV = 1 << 5,
/* generate software time stamp when entering packet scheduling */
SKBTX_SCHED_TSTAMP = 1 << 6,
/* used for bpf extension when a bpf program is loaded */
SKBTX_BPF = 1 << 7,
};
#define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF)
#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \
SKBTX_SCHED_TSTAMP | \
SKBTX_BPF | \
SKBTX_COMPLETION_TSTAMP)
#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \
SKBTX_ANY_SW_TSTAMP)
/* Definitions for flags in struct skb_shared_info */
enum {
/* use zcopy routines */
SKBFL_ZEROCOPY_ENABLE = BIT(0),
/* This indicates at least one fragment might be overwritten
* (as in vmsplice(), sendfile() ...)
* If we need to compute a TX checksum, we'll need to copy
* all frags to avoid possible bad checksum
*/
SKBFL_SHARED_FRAG = BIT(1),
/* segment contains only zerocopy data and should not be
* charged to the kernel memory.
*/
SKBFL_PURE_ZEROCOPY = BIT(2),
SKBFL_DONT_ORPHAN = BIT(3),
/* page references are managed by the ubuf_info, so it's safe to
* use frags only up until ubuf_info is released
*/
SKBFL_MANAGED_FRAG_REFS = BIT(4),
};
#define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG)
#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \
SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS)
struct ubuf_info_ops {
void (*complete)(struct sk_buff *, struct ubuf_info *,
bool zerocopy_success);
/* has to be compatible with skb_zcopy_set() */
int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg);
};
/*
* The callback notifies userspace to release buffers when skb DMA is done in
* lower device, the skb last reference should be 0 when calling this.
* The zerocopy_success argument is true if zero copy transmit occurred,
* false on data copy or out of memory error caused by data copy attempt.
* The ctx field is used to track device context.
* The desc field is used to track userspace buffer index.
*/
struct ubuf_info {
const struct ubuf_info_ops *ops;
refcount_t refcnt;
u8 flags;
};
struct ubuf_info_msgzc {
struct ubuf_info ubuf;
union {
struct {
unsigned long desc;
void *ctx;
};
struct {
u32 id;
u16 len;
u16 zerocopy:1;
u32 bytelen;
};
};
struct mmpin {
struct user_struct *user;
unsigned int num_pg;
} mmp;
};
#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg))
#define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \
ubuf)
int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
void mm_unaccount_pinned_pages(struct mmpin *mmp);
/* Preserve some data across TX submission and completion.
*
* Note, this state is stored in the driver. Extending the layout
* might need some special care.
*/
struct xsk_tx_metadata_compl {
__u64 *tx_timestamp;
};
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
__u8 flags;
__u8 meta_len;
__u8 nr_frags;
__u8 tx_flags;
unsigned short gso_size;
/* Warning: this field is not always filled in (UFO)! */
unsigned short gso_segs;
struct sk_buff *frag_list;
union {
struct skb_shared_hwtstamps hwtstamps;
struct xsk_tx_metadata_compl xsk_meta;
};
unsigned int gso_type;
u32 tskey;
/*
* Warning : all fields before dataref are cleared in __alloc_skb()
*/
atomic_t dataref;
union {
struct {
u32 xdp_frags_size;
u32 xdp_frags_truesize;
};
/*
* Intermediate layers must ensure that destructor_arg
* remains valid until skb destructor.
*/
void *destructor_arg;
};
/* must be last field, see pskb_expand_head() */
skb_frag_t frags[MAX_SKB_FRAGS];
};
/**
* DOC: dataref and headerless skbs
*
* Transport layers send out clones of payload skbs they hold for
* retransmissions. To allow lower layers of the stack to prepend their headers
* we split &skb_shared_info.dataref into two halves.
* The lower 16 bits count the overall number of references.
* The higher 16 bits indicate how many of the references are payload-only.
* skb_header_cloned() checks if skb is allowed to add / write the headers.
*
* The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr
* (via __skb_header_release()). Any clone created from marked skb will get
* &sk_buff.hdr_len populated with the available headroom.
* If there's the only clone in existence it's able to modify the headroom
* at will. The sequence of calls inside the transport layer is::
*
* <alloc skb>
* skb_reserve()
* __skb_header_release()
* skb_clone()
* // send the clone down the stack
*
* This is not a very generic construct and it depends on the transport layers
* doing the right thing. In practice there's usually only one payload-only skb.
* Having multiple payload-only skbs with different lengths of hdr_len is not
* possible. The payload-only skbs should never leave their owner.
*/
#define SKB_DATAREF_SHIFT 16
#define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1)
enum {
SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */
SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */
SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */
};
enum {
SKB_GSO_TCPV4 = 1 << 0,
/* This indicates the skb is from an untrusted source. */
SKB_GSO_DODGY = 1 << 1,
/* This indicates the tcp segment has CWR set. */
SKB_GSO_TCP_ECN = 1 << 2,
SKB_GSO_TCP_FIXEDID = 1 << 3,
SKB_GSO_TCPV6 = 1 << 4,
SKB_GSO_FCOE = 1 << 5,
SKB_GSO_GRE = 1 << 6,
SKB_GSO_GRE_CSUM = 1 << 7,
SKB_GSO_IPXIP4 = 1 << 8,
SKB_GSO_IPXIP6 = 1 << 9,
SKB_GSO_UDP_TUNNEL = 1 << 10,
SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
SKB_GSO_PARTIAL = 1 << 12,
SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
SKB_GSO_SCTP = 1 << 14,
SKB_GSO_ESP = 1 << 15,
SKB_GSO_UDP = 1 << 16,
SKB_GSO_UDP_L4 = 1 << 17,
SKB_GSO_FRAGLIST = 1 << 18,
SKB_GSO_TCP_ACCECN = 1 << 19,
};
#if BITS_PER_LONG > 32
#define NET_SKBUFF_DATA_USES_OFFSET 1
#endif
#ifdef NET_SKBUFF_DATA_USES_OFFSET
typedef unsigned int sk_buff_data_t;
#else
typedef unsigned char *sk_buff_data_t;
#endif
enum skb_tstamp_type {
SKB_CLOCK_REALTIME,
SKB_CLOCK_MONOTONIC,
SKB_CLOCK_TAI,
__SKB_CLOCK_MAX = SKB_CLOCK_TAI,
};
/**
* DOC: Basic sk_buff geometry
*
* struct sk_buff itself is a metadata structure and does not hold any packet
* data. All the data is held in associated buffers.
*
* &sk_buff.head points to the main "head" buffer. The head buffer is divided
* into two parts:
*
* - data buffer, containing headers and sometimes payload;
* this is the part of the skb operated on by the common helpers
* such as skb_put() or skb_pull();
* - shared info (struct skb_shared_info) which holds an array of pointers
* to read-only data in the (page, offset, length) format.
*
* Optionally &skb_shared_info.frag_list may point to another skb.
*
* Basic diagram may look like this::
*
* ---------------
* | sk_buff |
* ---------------
* ,--------------------------- + head
* / ,----------------- + data
* / / ,----------- + tail
* | | | , + end
* | | | |
* v v v v
* -----------------------------------------------
* | headroom | data | tailroom | skb_shared_info |
* -----------------------------------------------
* + [page frag]
* + [page frag]
* + [page frag]
* + [page frag] ---------
* + frag_list --> | sk_buff |
* ---------
*
*/
/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
* @tstamp: Time we arrived/left
* @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point
* for retransmit timer
* @rbnode: RB tree node, alternative to next/prev for netem/tcp
* @list: queue head
* @ll_node: anchor in an llist (eg socket defer_list)
* @sk: Socket we are owned by
* @dev: Device we arrived on/are leaving by
* @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
* @cb: Control buffer. Free for use by every layer. Put private vars here
* @_skb_refdst: destination entry (with norefcount bit)
* @len: Length of actual data
* @data_len: Data length
* @mac_len: Length of link layer header
* @hdr_len: writable header length of cloned skb
* @csum: Checksum (must include start/offset pair)
* @csum_start: Offset from skb->head where checksumming should start
* @csum_offset: Offset from csum_start where checksum should be stored
* @priority: Packet queueing priority
* @ignore_df: allow local fragmentation
* @cloned: Head may be cloned (check refcnt to be sure)
* @ip_summed: Driver fed us an IP checksum
* @nohdr: Payload reference only, must not modify header
* @pkt_type: Packet class
* @fclone: skbuff clone status
* @ipvs_property: skbuff is owned by ipvs
* @inner_protocol_type: whether the inner protocol is
* ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
* @remcsum_offload: remote checksum offload is enabled
* @offload_fwd_mark: Packet was L2-forwarded in hardware
* @offload_l3_fwd_mark: Packet was L3-forwarded in hardware
* @tc_skip_classify: do not classify packet. set by IFB device
* @tc_at_ingress: used within tc_classify to distinguish in/egress
* @redirected: packet was redirected by packet classifier
* @from_ingress: packet was redirected from the ingress path
* @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h
* @peeked: this packet has been seen already, so stats have been
* done for it, don't do them again
* @nf_trace: netfilter packet trace flag
* @protocol: Packet protocol from driver
* @destructor: Destruct function
* @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
* @_sk_redir: socket redirection information for skmsg
* @_nfct: Associated connection, if any (with nfctinfo bits)
* @skb_iif: ifindex of device we arrived on
* @tc_index: Traffic control index
* @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
* @head_frag: skb was allocated from page fragments,
* not allocated by kmalloc() or vmalloc().
* @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
* @pp_recycle: mark the packet for recycling instead of freeing (implies
* page_pool support on driver)
* @active_extensions: active extensions (skb_ext_id types)
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
* @l4_hash: indicate hash is a canonical 4-tuple hash over transport
* ports.
* @sw_hash: indicates hash was computed in software stack
* @wifi_acked_valid: wifi_acked was set
* @wifi_acked: whether frame was acked on wifi or not
* @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS
* @encapsulation: indicates the inner headers in the skbuff are valid
* @encap_hdr_csum: software checksum is needed
* @csum_valid: checksum is already valid
* @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
* @csum_complete_sw: checksum was completed by software
* @csum_level: indicates the number of consecutive checksums found in
* the packet minus one that have been verified as
* CHECKSUM_UNNECESSARY (max 3)
* @unreadable: indicates that at least 1 of the fragments in this skb is
* unreadable.
* @dst_pending_confirm: need to confirm neighbour
* @decrypted: Decrypted SKB
* @slow_gro: state present at GRO time, slower prepare step required
* @tstamp_type: When set, skb->tstamp has the
* delivery_time clock base of skb->tstamp.
* @napi_id: id of the NAPI struct this skb came from
* @sender_cpu: (aka @napi_id) source CPU in XPS
* @alloc_cpu: CPU which did the skb allocation.
* @secmark: security marking
* @mark: Generic packet mark
* @reserved_tailroom: (aka @mark) number of bytes of free space available
* at the tail of an sk_buff
* @vlan_all: vlan fields (proto & tci)
* @vlan_proto: vlan encapsulation protocol
* @vlan_tci: vlan tag control information
* @inner_protocol: Protocol (encapsulation)
* @inner_ipproto: (aka @inner_protocol) stores ipproto when
* skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
* @inner_transport_header: Inner transport layer header (encapsulation)
* @inner_network_header: Network layer header (encapsulation)
* @inner_mac_header: Link layer header (encapsulation)
* @transport_header: Transport layer header
* @network_header: Network layer header
* @mac_header: Link layer header
* @kcov_handle: KCOV remote handle for remote coverage collection
* @tail: Tail pointer
* @end: End pointer
* @head: Head of buffer
* @data: Data head pointer
* @truesize: Buffer size
* @users: User count - see {datagram,tcp}.c
* @extensions: allocated extensions, valid if active_extensions is nonzero
*/
struct sk_buff {
union {
struct {
/* These two members must be first to match sk_buff_head. */
struct sk_buff *next;
struct sk_buff *prev;
union {
struct net_device *dev;
/* Some protocols might use this space to store information,
* while device pointer would be NULL.
* UDP receive path is one user.
*/
unsigned long dev_scratch;
};
};
struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */
struct list_head list;
struct llist_node ll_node;
};
struct sock *sk;
union {
ktime_t tstamp;
u64 skb_mstamp_ns; /* earliest departure time */
};
/*
* This is the control buffer. It is free to use for every
* layer. Please put your private variables there. If you
* want to keep them across layers you have to do a skb_clone()
* first. This is owned by whoever has the skb queued ATM.
*/
char cb[48] __aligned(8);
union {
struct {
unsigned long _skb_refdst;
void (*destructor)(struct sk_buff *skb);
};
struct list_head tcp_tsorted_anchor;
#ifdef CONFIG_NET_SOCK_MSG
unsigned long _sk_redir;
#endif
};
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
unsigned long _nfct;
#endif
unsigned int len,
data_len;
__u16 mac_len,
hdr_len;
/* Following fields are _not_ copied in __copy_skb_header()
* Note that queue_mapping is here mostly to fill a hole.
*/
__u16 queue_mapping;
/* if you move cloned around you also must adapt those constants */
#ifdef __BIG_ENDIAN_BITFIELD
#define CLONED_MASK (1 << 7)
#else
#define CLONED_MASK 1
#endif
#define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset)
/* private: */
__u8 __cloned_offset[0];
/* public: */
__u8 cloned:1,
nohdr:1,
fclone:2,
peeked:1,
head_frag:1,
pfmemalloc:1,
pp_recycle:1; /* page_pool recycle indicator */
#ifdef CONFIG_SKB_EXTENSIONS
__u8 active_extensions;
#endif
/* Fields enclosed in headers group are copied
* using a single memcpy() in __copy_skb_header()
*/
struct_group(headers,
/* private: */
__u8 __pkt_type_offset[0];
/* public: */
__u8 pkt_type:3; /* see PKT_TYPE_MAX */
__u8 ignore_df:1;
__u8 dst_pending_confirm:1;
__u8 ip_summed:2;
__u8 ooo_okay:1;
/* private: */
__u8 __mono_tc_offset[0];
/* public: */
__u8 tstamp_type:2; /* See skb_tstamp_type */
#ifdef CONFIG_NET_XGRESS
__u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */
__u8 tc_skip_classify:1;
#endif
__u8 remcsum_offload:1;
__u8 csum_complete_sw:1;
__u8 csum_level:2;
__u8 inner_protocol_type:1;
__u8 l4_hash:1;
__u8 sw_hash:1;
#ifdef CONFIG_WIRELESS
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
#endif
__u8 no_fcs:1;
/* Indicates the inner headers are valid in the skbuff. */
__u8 encapsulation:1;
__u8 encap_hdr_csum:1;
__u8 csum_valid:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
#if IS_ENABLED(CONFIG_IP_VS)
__u8 ipvs_property:1;
#endif
#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES)
__u8 nf_trace:1;
#endif
#ifdef CONFIG_NET_SWITCHDEV
__u8 offload_fwd_mark:1;
__u8 offload_l3_fwd_mark:1;
#endif
__u8 redirected:1;
#ifdef CONFIG_NET_REDIRECT
__u8 from_ingress:1;
#endif
#ifdef CONFIG_NETFILTER_SKIP_EGRESS
__u8 nf_skip_egress:1;
#endif
#ifdef CONFIG_SKB_DECRYPTED
__u8 decrypted:1;
#endif
__u8 slow_gro:1;
#if IS_ENABLED(CONFIG_IP_SCTP)
__u8 csum_not_inet:1;
#endif
__u8 unreadable:1;
#if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS)
__u16 tc_index; /* traffic control index */
#endif
u16 alloc_cpu;
union {
__wsum csum;
struct {
__u16 csum_start;
__u16 csum_offset;
};
};
__u32 priority;
int skb_iif;
__u32 hash;
union {
u32 vlan_all;
struct {
__be16 vlan_proto;
__u16 vlan_tci;
};
};
#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
union {
unsigned int napi_id;
unsigned int sender_cpu;
};
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
union {
__u32 mark;
__u32 reserved_tailroom;
};
union {
__be16 inner_protocol;
__u8 inner_ipproto;
};
__u16 inner_transport_header;
__u16 inner_network_header;
__u16 inner_mac_header;
__be16 protocol;
__u16 transport_header;
__u16 network_header;
__u16 mac_header;
#ifdef CONFIG_KCOV
u64 kcov_handle;
#endif
); /* end headers group */
/* These elements must be at the end, see alloc_skb() for details. */
sk_buff_data_t tail;
sk_buff_data_t end;
unsigned char *head,
*data;
unsigned int truesize;
refcount_t users;
#ifdef CONFIG_SKB_EXTENSIONS
/* only usable after checking ->active_extensions != 0 */
struct skb_ext *extensions;
#endif
};
/* if you move pkt_type around you also must adapt those constants */
#ifdef __BIG_ENDIAN_BITFIELD
#define PKT_TYPE_MAX (7 << 5)
#else
#define PKT_TYPE_MAX 7
#endif
#define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset)
/* if you move tc_at_ingress or tstamp_type
* around, you also must adapt these constants.
*/
#ifdef __BIG_ENDIAN_BITFIELD
#define SKB_TSTAMP_TYPE_MASK (3 << 6)
#define SKB_TSTAMP_TYPE_RSHIFT (6)
#define TC_AT_INGRESS_MASK (1 << 5)
#else
#define SKB_TSTAMP_TYPE_MASK (3)
#define TC_AT_INGRESS_MASK (1 << 2)
#endif
#define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset)
#ifdef __KERNEL__
/*
* Handling routines are only of interest to the kernel
*/
#define SKB_ALLOC_FCLONE 0x01
#define SKB_ALLOC_RX 0x02
#define SKB_ALLOC_NAPI 0x04
/**
* skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves
* @skb: buffer
*/
static inline bool skb_pfmemalloc(const struct sk_buff *skb)
{
return unlikely(skb->pfmemalloc);
}
/*
* skb might have a dst pointer attached, refcounted or not.
* _skb_refdst low order bit is set if refcount was _not_ taken
*/
#define SKB_DST_NOREF 1UL
#define SKB_DST_PTRMASK ~(SKB_DST_NOREF)
/**
* skb_dst - returns skb dst_entry
* @skb: buffer
*
* Returns: skb dst_entry, regardless of reference taken or not.
*/
static inline struct dst_entry *skb_dst(const struct sk_buff *skb)
{
/* If refdst was not refcounted, check we still are in a
* rcu_read_lock section
*/
WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) &&
!rcu_read_lock_held() &&
!rcu_read_lock_bh_held());
return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK);
}
/**
* skb_dst_set - sets skb dst
* @skb: buffer
* @dst: dst entry
*
* Sets skb dst, assuming a reference was taken on dst and should
* be released by skb_dst_drop()
*/
static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
{
skb->slow_gro |= !!dst;
skb->_skb_refdst = (unsigned long)dst;
}
/**
* skb_dst_set_noref - sets skb dst, hopefully, without taking reference
* @skb: buffer
* @dst: dst entry
*
* Sets skb dst, assuming a reference was not taken on dst.
* If dst entry is cached, we do not take reference and dst_release
* will be avoided by refdst_drop. If dst entry is not cached, we take
* reference, so that last dst_release can destroy the dst immediately.
*/
static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
{
WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
skb->slow_gro |= !!dst;
skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
}
/**
* skb_dst_is_noref - Test if skb dst isn't refcounted
* @skb: buffer
*/
static inline bool skb_dst_is_noref(const struct sk_buff *skb)
{
return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb);
}
/* For mangling skb->pkt_type from user space side from applications
* such as nft, tc, etc, we only allow a conservative subset of
* possible pkt_types to be set.
*/
static inline bool skb_pkt_type_ok(u32 ptype)
{
return ptype <= PACKET_OTHERHOST;
}
/**
* skb_napi_id - Returns the skb's NAPI id
* @skb: buffer
*/
static inline unsigned int skb_napi_id(const struct sk_buff *skb)
{
#ifdef CONFIG_NET_RX_BUSY_POLL
return skb->napi_id;
#else
return 0;
#endif
}
static inline bool skb_wifi_acked_valid(const struct sk_buff *skb)
{
#ifdef CONFIG_WIRELESS
return skb->wifi_acked_valid;
#else
return 0;
#endif
}
/**
* skb_unref - decrement the skb's reference count
* @skb: buffer
*
* Returns: true if we can free the skb.
*/
static inline bool skb_unref(struct sk_buff *skb)
{
if (unlikely(!skb))
return false;
if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1))
smp_rmb();
else if (likely(!refcount_dec_and_test(&skb->users)))
return false;
return true;
}
static inline bool skb_data_unref(const struct sk_buff *skb,
struct skb_shared_info *shinfo)
{
int bias;
if (!skb->cloned)
return true;
bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1;
if (atomic_read(&shinfo->dataref) == bias)
smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref))
return false;
return true;
}
void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb,
enum skb_drop_reason reason);
static inline void
kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
{
sk_skb_reason_drop(NULL, skb, reason);
}
/**
* kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason
* @skb: buffer to free
*/
static inline void kfree_skb(struct sk_buff *skb)
{
kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
}
void skb_release_head_state(struct sk_buff *skb);
void kfree_skb_list_reason(struct sk_buff *segs,
enum skb_drop_reason reason);
void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt);
void skb_tx_error(struct sk_buff *skb);
static inline void kfree_skb_list(struct sk_buff *segs)
{
kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED);
}
#ifdef CONFIG_TRACEPOINTS
void consume_skb(struct sk_buff *skb);
#else
static inline void consume_skb(struct sk_buff *skb)
{
return kfree_skb(skb);
}
#endif
void __consume_stateless_skb(struct sk_buff *skb);
void __kfree_skb(struct sk_buff *skb);
void kfree_skb_partial(struct sk_buff *skb, bool head_stolen);
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize);
struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
int node);
struct sk_buff *__build_skb(void *data, unsigned int frag_size);
struct sk_buff *build_skb(void *data, unsigned int frag_size);
struct sk_buff *build_skb_around(struct sk_buff *skb,
void *data, unsigned int frag_size);
void skb_attempt_defer_free(struct sk_buff *skb);
u32 napi_skb_cache_get_bulk(void **skbs, u32 n);
struct sk_buff *napi_build_skb(void *data, unsigned int frag_size);
struct sk_buff *slab_build_skb(void *data);
/**
* alloc_skb - allocate a network buffer
* @size: size to allocate
* @priority: allocation mask
*
* This function is a convenient wrapper around __alloc_skb().
*/
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
{
return __alloc_skb(size, priority, 0, NUMA_NO_NODE);
}
struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
unsigned long data_len,
int max_page_order,
int *errcode,
gfp_t gfp_mask);
struct sk_buff *alloc_skb_for_msg(struct sk_buff *first);
/* Layout of fast clones : [skb1][skb2][fclone_ref] */
struct sk_buff_fclones {
struct sk_buff skb1;
struct sk_buff skb2;
refcount_t fclone_ref;
};
/**
* skb_fclone_busy - check if fclone is busy
* @sk: socket
* @skb: buffer
*
* Returns: true if skb is a fast clone, and its clone is not freed.
* Some drivers call skb_orphan() in their ndo_start_xmit(),
* so we also check that didn't happen.
*/
static inline bool skb_fclone_busy(const struct sock *sk,
const struct sk_buff *skb)
{
const struct sk_buff_fclones *fclones;
fclones = container_of(skb, struct sk_buff_fclones, skb1);
return skb->fclone == SKB_FCLONE_ORIG &&
refcount_read(&fclones->fclone_ref) > 1 &&
READ_ONCE(fclones->skb2.sk) == sk;
}
/**
* alloc_skb_fclone - allocate a network buffer from fclone cache
* @size: size to allocate
* @priority: allocation mask
*
* This function is a convenient wrapper around __alloc_skb().
*/
static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
gfp_t priority)
{
return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
}
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
void skb_headers_offset_update(struct sk_buff *skb, int off);
int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
void skb_copy_header(struct sk_buff *new, const struct sk_buff *old);
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority);
struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
gfp_t gfp_mask, bool fclone);
static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom,
gfp_t gfp_mask)
{
return __pskb_copy_fclone(skb, headroom, gfp_mask, false);
}
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask);
struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
unsigned int headroom);
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom);
struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom,
int newtailroom, gfp_t priority);
int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
int offset, int len);
int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg,
int offset, int len);
int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer);
int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error);
/**
* skb_pad - zero pad the tail of an skb
* @skb: buffer to pad
* @pad: space to pad
*
* Ensure that a buffer is followed by a padding area that is zero
* filled. Used by network drivers which may DMA or transfer data
* beyond the buffer end onto the wire.
*
* May return error in out of memory cases. The skb is freed on error.
*/
static inline int skb_pad(struct sk_buff *skb, int pad)
{
return __skb_pad(skb, pad, true);
}
#define dev_kfree_skb(a) consume_skb(a)
int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
int offset, size_t size, size_t max_frags);
struct skb_seq_state {
__u32 lower_offset;
__u32 upper_offset;
__u32 frag_idx;
__u32 stepped_offset;
struct sk_buff *root_skb;
struct sk_buff *cur_skb;
__u8 *frag_data;
__u32 frag_off;
};
void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
unsigned int to, struct skb_seq_state *st);
unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
struct skb_seq_state *st);
void skb_abort_seq_read(struct skb_seq_state *st);
int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len);
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
unsigned int to, struct ts_config *config);
/*
* Packet hash types specify the type of hash in skb_set_hash.
*
* Hash types refer to the protocol layer addresses which are used to
* construct a packet's hash. The hashes are used to differentiate or identify
* flows of the protocol layer for the hash type. Hash types are either
* layer-2 (L2), layer-3 (L3), or layer-4 (L4).
*
* Properties of hashes:
*
* 1) Two packets in different flows have different hash values
* 2) Two packets in the same flow should have the same hash value
*
* A hash at a higher layer is considered to be more specific. A driver should
* set the most specific hash possible.
*
* A driver cannot indicate a more specific hash than the layer at which a hash
* was computed. For instance an L3 hash cannot be set as an L4 hash.
*
* A driver may indicate a hash level which is less specific than the
* actual layer the hash was computed on. For instance, a hash computed
* at L4 may be considered an L3 hash. This should only be done if the
* driver can't unambiguously determine that the HW computed the hash at
* the higher layer. Note that the "should" in the second property above
* permits this.
*/
enum pkt_hash_types {
PKT_HASH_TYPE_NONE, /* Undefined type */
PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */
PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */
PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */
};
static inline void skb_clear_hash(struct sk_buff *skb)
{
skb->hash = 0;
skb->sw_hash = 0;
skb->l4_hash = 0;
}
static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
{
if (!skb->l4_hash)
skb_clear_hash(skb);
}
static inline void
__skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4)
{
skb->l4_hash = is_l4;
skb->sw_hash = is_sw;
skb->hash = hash;
}
static inline void
skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
{
/* Used by drivers to set hash from HW */
__skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4);
}
static inline void
__skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
{
__skb_set_hash(skb, hash, true, is_l4);
}
u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb);
static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
{
return __skb_get_hash_symmetric_net(NULL, skb);
}
void __skb_get_hash_net(const struct net *net, struct sk_buff *skb);
u32 skb_get_poff(const struct sk_buff *skb);
u32 __skb_get_poff(const struct sk_buff *skb, const void *data,
const struct flow_keys_basic *keys, int hlen);
__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
const void *data, int hlen_proto);
void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
const struct flow_dissector_key *key,
unsigned int key_count);
struct bpf_flow_dissector;
u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
__be16 proto, int nhoff, int hlen, unsigned int flags);
bool __skb_flow_dissect(const struct net *net,
const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, const void *data,
__be16 proto, int nhoff, int hlen, unsigned int flags);
static inline bool skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, unsigned int flags)
{
return __skb_flow_dissect(NULL, skb, flow_dissector,
target_container, NULL, 0, 0, 0, flags);
}
static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
struct flow_keys *flow,
unsigned int flags)
{
memset(flow, 0, sizeof(*flow));
return __skb_flow_dissect(NULL, skb, &flow_keys_dissector,
flow, NULL, 0, 0, 0, flags);
}
static inline bool
skb_flow_dissect_flow_keys_basic(const struct net *net,
const struct sk_buff *skb,
struct flow_keys_basic *flow,
const void *data, __be16 proto,
int nhoff, int hlen, unsigned int flags)
{
memset(flow, 0, sizeof(*flow));
return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow,
data, proto, nhoff, hlen, flags);
}
void skb_flow_dissect_meta(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container);
/* Gets a skb connection tracking info, ctinfo map should be a
* map of mapsize to translate enum ip_conntrack_info states
* to user states.
*/
void
skb_flow_dissect_ct(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container,
u16 *ctinfo_map, size_t mapsize,
bool post_ct, u16 zone);
void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container);
void skb_flow_dissect_hash(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container);
static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb)
{
if (!skb->l4_hash && !skb->sw_hash)
__skb_get_hash_net(net, skb);
return skb->hash;
}
static inline __u32 skb_get_hash(struct sk_buff *skb)
{
if (!skb->l4_hash && !skb->sw_hash)
__skb_get_hash_net(NULL, skb);
return skb->hash;
}
static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6)
{
if (!skb->l4_hash && !skb->sw_hash) {
struct flow_keys keys;
__u32 hash = __get_hash_from_flowi6(fl6, &keys);
__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
}
return skb->hash;
}
__u32 skb_get_hash_perturb(const struct sk_buff *skb,
const siphash_key_t *perturb);
static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
{
return skb->hash;
}
static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
{
to->hash = from->hash;
to->sw_hash = from->sw_hash;
to->l4_hash = from->l4_hash;
};
static inline int skb_cmp_decrypted(const struct sk_buff *skb1,
const struct sk_buff *skb2)
{
#ifdef CONFIG_SKB_DECRYPTED
return skb2->decrypted - skb1->decrypted;
#else
return 0;
#endif
}
static inline bool skb_is_decrypted(const struct sk_buff *skb)
{
#ifdef CONFIG_SKB_DECRYPTED
return skb->decrypted;
#else
return false;
#endif
}
static inline void skb_copy_decrypted(struct sk_buff *to,
const struct sk_buff *from)
{
#ifdef CONFIG_SKB_DECRYPTED
to->decrypted = from->decrypted;
#endif
}
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
return skb->head + skb->end;
}
static inline unsigned int skb_end_offset(const struct sk_buff *skb)
{
return skb->end;
}
static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
{
skb->end = offset;
}
#else
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
return skb->end;
}
static inline unsigned int skb_end_offset(const struct sk_buff *skb)
{
return skb->end - skb->head;
}
static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
{
skb->end = skb->head + offset;
}
#endif
extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
struct ubuf_info *uarg);
void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, struct iov_iter *from,
size_t length);
int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
struct iov_iter *from, size_t length);
static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
struct msghdr *msg, int len)
{
return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
}
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
struct ubuf_info *uarg);
/* Internal */
#define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb)
{
return &skb_shinfo(skb)->hwtstamps;
}
static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb)
{
bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL;
}
static inline bool skb_zcopy_pure(const struct sk_buff *skb)
{
return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY;
}
static inline bool skb_zcopy_managed(const struct sk_buff *skb)
{
return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS;
}
static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1,
const struct sk_buff *skb2)
{
return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2);
}
static inline void net_zcopy_get(struct ubuf_info *uarg)
{
refcount_inc(&uarg->refcnt);
}
static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg)
{
skb_shinfo(skb)->destructor_arg = uarg;
skb_shinfo(skb)->flags |= uarg->flags;
}
static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg,
bool *have_ref)
{
if (skb && uarg && !skb_zcopy(skb)) {
if (unlikely(have_ref && *have_ref))
*have_ref = false;
else
net_zcopy_get(uarg);
skb_zcopy_init(skb, uarg);
}
}
static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
{
skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG;
}
static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
{
return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
}
static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
{
return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
}
static inline void net_zcopy_put(struct ubuf_info *uarg)
{
if (uarg)
uarg->ops->complete(NULL, uarg, true);
}
static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
if (uarg) {
if (uarg->ops == &msg_zerocopy_ubuf_ops)
msg_zerocopy_put_abort(uarg, have_uref);
else if (have_uref)
net_zcopy_put(uarg);
}
}
/* Release a reference on a zerocopy structure */
static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
{
struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success);
skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
}
}
void __skb_zcopy_downgrade_managed(struct sk_buff *skb);
static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb)
{
if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb);
}
/* Return true if frags in this skb are readable by the host. */
static inline bool skb_frags_readable(const struct sk_buff *skb)
{
return !skb->unreadable;
}
static inline void skb_mark_not_on_list(struct sk_buff *skb)
{
skb->next = NULL;
}
static inline void skb_poison_list(struct sk_buff *skb)
{
#ifdef CONFIG_DEBUG_NET
skb->next = SKB_LIST_POISON_NEXT;
#endif
}
/* Iterate through singly-linked GSO fragments of an skb. */
#define skb_list_walk_safe(first, skb, next_skb) \
for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \
(skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL)
static inline void skb_list_del_init(struct sk_buff *skb)
{
__list_del_entry(&skb->list);
skb_mark_not_on_list(skb);
}
/**
* skb_queue_empty - check if a queue is empty
* @list: queue head
*
* Returns true if the queue is empty, false otherwise.
*/
static inline int skb_queue_empty(const struct sk_buff_head *list)
{
return list->next == (const struct sk_buff *) list;
}
/**
* skb_queue_empty_lockless - check if a queue is empty
* @list: queue head
*
* Returns true if the queue is empty, false otherwise.
* This variant can be used in lockless contexts.
*/
static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list)
{
return READ_ONCE(list->next) == (const struct sk_buff *) list;
}
/**
* skb_queue_is_last - check if skb is the last entry in the queue
* @list: queue head
* @skb: buffer
*
* Returns true if @skb is the last buffer on the list.
*/
static inline bool skb_queue_is_last(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
return skb->next == (const struct sk_buff *) list;
}
/**
* skb_queue_is_first - check if skb is the first entry in the queue
* @list: queue head
* @skb: buffer
*
* Returns true if @skb is the first buffer on the list.
*/
static inline bool skb_queue_is_first(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
return skb->prev == (const struct sk_buff *) list;
}
/**
* skb_queue_next - return the next packet in the queue
* @list: queue head
* @skb: current buffer
*
* Return the next packet in @list after @skb. It is only valid to
* call this if skb_queue_is_last() evaluates to false.
*/
static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
/* This BUG_ON may seem severe, but if we just return then we
* are going to dereference garbage.
*/
BUG_ON(skb_queue_is_last(list, skb));
return skb->next;
}
/**
* skb_queue_prev - return the prev packet in the queue
* @list: queue head
* @skb: current buffer
*
* Return the prev packet in @list before @skb. It is only valid to
* call this if skb_queue_is_first() evaluates to false.
*/
static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list,
const struct sk_buff *skb)
{
/* This BUG_ON may seem severe, but if we just return then we
* are going to dereference garbage.
*/
BUG_ON(skb_queue_is_first(list, skb));
return skb->prev;
}
/**
* skb_get - reference buffer
* @skb: buffer to reference
*
* Makes another reference to a socket buffer and returns a pointer
* to the buffer.
*/
static inline struct sk_buff *skb_get(struct sk_buff *skb)
{
refcount_inc(&skb->users);
return skb;
}
/*
* If users == 1, we are the only owner and can avoid redundant atomic changes.
*/
/**
* skb_cloned - is the buffer a clone
* @skb: buffer to check
*
* Returns true if the buffer was generated with skb_clone() and is
* one of multiple shared copies of the buffer. Cloned buffers are
* shared data so must not be written to under normal circumstances.
*/
static inline int skb_cloned(const struct sk_buff *skb)
{
return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1;
}
static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
{
might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_cloned(skb))
return pskb_expand_head(skb, 0, 0, pri);
return 0;
}
/* This variant of skb_unclone() makes sure skb->truesize
* and skb_end_offset() are not changed, whenever a new skb->head is needed.
*
* Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X))
* when various debugging features are in place.
*/
int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri);
static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
{
might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_cloned(skb))
return __skb_unclone_keeptruesize(skb, pri);
return 0;
}
/**
* skb_header_cloned - is the header a clone
* @skb: buffer to check
*
* Returns true if modifying the header part of the buffer requires
* the data to be copied.
*/
static inline int skb_header_cloned(const struct sk_buff *skb)
{
int dataref;
if (!skb->cloned)
return 0;
dataref = atomic_read(&skb_shinfo(skb)->dataref);
dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT);
return dataref != 1;
}
static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
{
might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_header_cloned(skb))
return pskb_expand_head(skb, 0, 0, pri);
return 0;
}
/**
* __skb_header_release() - allow clones to use the headroom
* @skb: buffer to operate on
*
* See "DOC: dataref and headerless skbs".
*/
static inline void __skb_header_release(struct sk_buff *skb)
{
skb->nohdr = 1;
atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT));
}
/**
* skb_shared - is the buffer shared
* @skb: buffer to check
*
* Returns true if more than one person has a reference to this
* buffer.
*/
static inline int skb_shared(const struct sk_buff *skb)
{
return refcount_read(&skb->users) != 1;
}
/**
* skb_share_check - check if buffer is shared and if so clone it
* @skb: buffer to check
* @pri: priority for memory allocation
*
* If the buffer is shared the buffer is cloned and the old copy
* drops a reference. A new clone with a single reference is returned.
* If the buffer is not shared the original buffer is returned. When
* being called from interrupt status or with spinlocks held pri must
* be GFP_ATOMIC.
*
* NULL is returned on a memory allocation failure.
*/
static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
{
might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, pri);
if (likely(nskb)) consume_skb(skb);
else
kfree_skb(skb);
skb = nskb;
}
return skb;
}
/*
* Copy shared buffers into a new sk_buff. We effectively do COW on
* packets to handle cases where we have a local reader and forward
* and a couple of other messy ones. The normal one is tcpdumping
* a packet that's being forwarded.
*/
/**
* skb_unshare - make a copy of a shared buffer
* @skb: buffer to check
* @pri: priority for memory allocation
*
* If the socket buffer is a clone then this function creates a new
* copy of the data, drops a reference count on the old copy and returns
* the new copy with the reference count at 1. If the buffer is not a clone
* the original buffer is returned. When called with a spinlock held or
* from interrupt state @pri must be %GFP_ATOMIC
*
* %NULL is returned on a memory allocation failure.
*/
static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
gfp_t pri)
{
might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_cloned(skb)) {
struct sk_buff *nskb = skb_copy(skb, pri);
/* Free our shared copy */
if (likely(nskb))
consume_skb(skb);
else
kfree_skb(skb);
skb = nskb;
}
return skb;
}
/**
* skb_peek - peek at the head of an &sk_buff_head
* @list_: list to peek at
*
* Peek an &sk_buff. Unlike most other operations you _MUST_
* be careful with this one. A peek leaves the buffer on the
* list and someone else may run off with it. You must hold
* the appropriate locks or have a private queue to do this.
*
* Returns %NULL for an empty list or a pointer to the head element.
* The reference count is not incremented and the reference is therefore
* volatile. Use with caution.
*/
static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_)
{
struct sk_buff *skb = list_->next;
if (skb == (struct sk_buff *)list_)
skb = NULL;
return skb;
}
/**
* __skb_peek - peek at the head of a non-empty &sk_buff_head
* @list_: list to peek at
*
* Like skb_peek(), but the caller knows that the list is not empty.
*/
static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_)
{
return list_->next;
}
/**
* skb_peek_next - peek skb following the given one from a queue
* @skb: skb to start from
* @list_: list to peek at
*
* Returns %NULL when the end of the list is met or a pointer to the
* next element. The reference count is not incremented and the
* reference is therefore volatile. Use with caution.
*/
static inline struct sk_buff *skb_peek_next(struct sk_buff *skb,
const struct sk_buff_head *list_)
{
struct sk_buff *next = skb->next;
if (next == (struct sk_buff *)list_)
next = NULL;
return next;
}
/**
* skb_peek_tail - peek at the tail of an &sk_buff_head
* @list_: list to peek at
*
* Peek an &sk_buff. Unlike most other operations you _MUST_
* be careful with this one. A peek leaves the buffer on the
* list and someone else may run off with it. You must hold
* the appropriate locks or have a private queue to do this.
*
* Returns %NULL for an empty list or a pointer to the tail element.
* The reference count is not incremented and the reference is therefore
* volatile. Use with caution.
*/
static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_)
{
struct sk_buff *skb = READ_ONCE(list_->prev);
if (skb == (struct sk_buff *)list_)
skb = NULL;
return skb;
}
/**
* skb_queue_len - get queue length
* @list_: list to measure
*
* Return the length of an &sk_buff queue.
*/
static inline __u32 skb_queue_len(const struct sk_buff_head *list_)
{
return list_->qlen;
}
/**
* skb_queue_len_lockless - get queue length
* @list_: list to measure
*
* Return the length of an &sk_buff queue.
* This variant can be used in lockless contexts.
*/
static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_)
{
return READ_ONCE(list_->qlen);
}
/**
* __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head
* @list: queue to initialize
*
* This initializes only the list and queue length aspects of
* an sk_buff_head object. This allows to initialize the list
* aspects of an sk_buff_head without reinitializing things like
* the spinlock. It can also be used for on-stack sk_buff_head
* objects where the spinlock is known to not be used.
*/
static inline void __skb_queue_head_init(struct sk_buff_head *list)
{
list->prev = list->next = (struct sk_buff *)list;
list->qlen = 0;
}
/*
* This function creates a split out lock class for each invocation;
* this is needed for now since a whole lot of users of the skb-queue
* infrastructure in drivers have different locking usage (in hardirq)
* than the networking core (in softirq only). In the long run either the
* network layer or drivers should need annotation to consolidate the
* main types of usage into 3 classes.
*/
static inline void skb_queue_head_init(struct sk_buff_head *list)
{
spin_lock_init(&list->lock);
__skb_queue_head_init(list);
}
static inline void skb_queue_head_init_class(struct sk_buff_head *list,
struct lock_class_key *class)
{
skb_queue_head_init(list);
lockdep_set_class(&list->lock, class);
}
/*
* Insert an sk_buff on a list.
*
* The "__skb_xxxx()" functions are the non-atomic ones that
* can only be called with interrupts disabled.
*/
static inline void __skb_insert(struct sk_buff *newsk,
struct sk_buff *prev, struct sk_buff *next,
struct sk_buff_head *list)
{
/* See skb_queue_empty_lockless() and skb_peek_tail()
* for the opposite READ_ONCE()
*/
WRITE_ONCE(newsk->next, next);
WRITE_ONCE(newsk->prev, prev);
WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk);
WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk);
WRITE_ONCE(list->qlen, list->qlen + 1);
}
static inline void __skb_queue_splice(const struct sk_buff_head *list,
struct sk_buff *prev,
struct sk_buff *next)
{
struct sk_buff *first = list->next;
struct sk_buff *last = list->prev;
WRITE_ONCE(first->prev, prev);
WRITE_ONCE(prev->next, first);
WRITE_ONCE(last->next, next);
WRITE_ONCE(next->prev, last);
}
/**
* skb_queue_splice - join two skb lists, this is designed for stacks
* @list: the new list to add
* @head: the place to add it in the first list
*/
static inline void skb_queue_splice(const struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, (struct sk_buff *) head, head->next);
head->qlen += list->qlen;
}
}
/**
* skb_queue_splice_init - join two skb lists and reinitialise the emptied list
* @list: the new list to add
* @head: the place to add it in the first list
*
* The list at @list is reinitialised
*/
static inline void skb_queue_splice_init(struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, (struct sk_buff *) head, head->next);
head->qlen += list->qlen;
__skb_queue_head_init(list);
}
}
/**
* skb_queue_splice_tail - join two skb lists, each list being a queue
* @list: the new list to add
* @head: the place to add it in the first list
*/
static inline void skb_queue_splice_tail(const struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) {
__skb_queue_splice(list, head->prev, (struct sk_buff *) head);
head->qlen += list->qlen;
}
}
/**
* skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list
* @list: the new list to add
* @head: the place to add it in the first list
*
* Each of the lists is a queue.
* The list at @list is reinitialised
*/
static inline void skb_queue_splice_tail_init(struct sk_buff_head *list,
struct sk_buff_head *head)
{
if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head);
head->qlen += list->qlen;
__skb_queue_head_init(list);
}
}
/**
* __skb_queue_after - queue a buffer at the list head
* @list: list to use
* @prev: place after this buffer
* @newsk: buffer to queue
*
* Queue a buffer int the middle of a list. This function takes no locks
* and you must therefore hold required locks before calling it.
*
* A buffer cannot be placed on two lists at the same time.
*/
static inline void __skb_queue_after(struct sk_buff_head *list,
struct sk_buff *prev,
struct sk_buff *newsk)
{
__skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list);
}
void skb_append(struct sk_buff *old, struct sk_buff *newsk,
struct sk_buff_head *list);
static inline void __skb_queue_before(struct sk_buff_head *list,
struct sk_buff *next,
struct sk_buff *newsk)
{
__skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list);
}
/**
* __skb_queue_head - queue a buffer at the list head
* @list: list to use
* @newsk: buffer to queue
*
* Queue a buffer at the start of a list. This function takes no locks
* and you must therefore hold required locks before calling it.
*
* A buffer cannot be placed on two lists at the same time.
*/
static inline void __skb_queue_head(struct sk_buff_head *list,
struct sk_buff *newsk)
{
__skb_queue_after(list, (struct sk_buff *)list, newsk);
}
void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
/**
* __skb_queue_tail - queue a buffer at the list tail
* @list: list to use
* @newsk: buffer to queue
*
* Queue a buffer at the end of a list. This function takes no locks
* and you must therefore hold required locks before calling it.
*
* A buffer cannot be placed on two lists at the same time.
*/
static inline void __skb_queue_tail(struct sk_buff_head *list,
struct sk_buff *newsk)
{
__skb_queue_before(list, (struct sk_buff *)list, newsk);
}
void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk);
/*
* remove sk_buff from list. _Must_ be called atomically, and with
* the list known..
*/
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
{
struct sk_buff *next, *prev;
WRITE_ONCE(list->qlen, list->qlen - 1);
next = skb->next;
prev = skb->prev;
skb->next = skb->prev = NULL;
WRITE_ONCE(next->prev, prev);
WRITE_ONCE(prev->next, next);
}
/**
* __skb_dequeue - remove from the head of the queue
* @list: list to dequeue from
*
* Remove the head of the list. This function does not take any locks
* so must be used with appropriate locks held only. The head item is
* returned or %NULL if the list is empty.
*/
static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
{
struct sk_buff *skb = skb_peek(list);
if (skb)
__skb_unlink(skb, list);
return skb;
}
struct sk_buff *skb_dequeue(struct sk_buff_head *list);
/**
* __skb_dequeue_tail - remove from the tail of the queue
* @list: list to dequeue from
*
* Remove the tail of the list. This function does not take any locks
* so must be used with appropriate locks held only. The tail item is
* returned or %NULL if the list is empty.
*/
static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list)
{
struct sk_buff *skb = skb_peek_tail(list);
if (skb)
__skb_unlink(skb, list);
return skb;
}
struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list);
static inline bool skb_is_nonlinear(const struct sk_buff *skb)
{
return skb->data_len;
}
static inline unsigned int skb_headlen(const struct sk_buff *skb)
{
return skb->len - skb->data_len;
}
static inline unsigned int __skb_pagelen(const struct sk_buff *skb)
{
unsigned int i, len = 0;
for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--)
len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
return len;
}
static inline unsigned int skb_pagelen(const struct sk_buff *skb)
{
return skb_headlen(skb) + __skb_pagelen(skb);
}
static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag,
netmem_ref netmem, int off,
int size)
{
frag->netmem = netmem;
frag->offset = off;
skb_frag_size_set(frag, size);
}
static inline void skb_frag_fill_page_desc(skb_frag_t *frag,
struct page *page,
int off, int size)
{
skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size);
}
static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo,
int i, netmem_ref netmem,
int off, int size)
{
skb_frag_t *frag = &shinfo->frags[i];
skb_frag_fill_netmem_desc(frag, netmem, off, size);
}
static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo,
int i, struct page *page,
int off, int size)
{
__skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off,
size);
}
/**
* skb_len_add - adds a number to len fields of skb
* @skb: buffer to add len to
* @delta: number of bytes to add
*/
static inline void skb_len_add(struct sk_buff *skb, int delta)
{
skb->len += delta;
skb->data_len += delta;
skb->truesize += delta;
}
/**
* __skb_fill_netmem_desc - initialise a fragment in an skb
* @skb: buffer containing fragment to be initialised
* @i: fragment index to initialise
* @netmem: the netmem to use for this fragment
* @off: the offset to the data with @page
* @size: the length of the data
*
* Initialises the @i'th fragment of @skb to point to &size bytes at
* offset @off within @page.
*
* Does not take any additional reference on the fragment.
*/
static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i,
netmem_ref netmem, int off, int size)
{
struct page *page;
__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);
if (netmem_is_net_iov(netmem)) {
skb->unreadable = true;
return;
}
page = netmem_to_page(netmem);
/* Propagate page pfmemalloc to the skb if we can. The problem is
* that not all callers have unique ownership of the page but rely
* on page_is_pfmemalloc doing the right thing(tm).
*/
page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true;
}
static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
struct page *page, int off, int size)
{
__skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size);
}
static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i,
netmem_ref netmem, int off, int size)
{
__skb_fill_netmem_desc(skb, i, netmem, off, size);
skb_shinfo(skb)->nr_frags = i + 1;
}
/**
* skb_fill_page_desc - initialise a paged fragment in an skb
* @skb: buffer containing fragment to be initialised
* @i: paged fragment index to initialise
* @page: the page to use for this fragment
* @off: the offset to the data with @page
* @size: the length of the data
*
* As per __skb_fill_page_desc() -- initialises the @i'th fragment of
* @skb to point to @size bytes at offset @off within @page. In
* addition updates @skb such that @i is the last fragment.
*
* Does not take any additional reference on the fragment.
*/
static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
struct page *page, int off, int size)
{
skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size);
}
/**
* skb_fill_page_desc_noacc - initialise a paged fragment in an skb
* @skb: buffer containing fragment to be initialised
* @i: paged fragment index to initialise
* @page: the page to use for this fragment
* @off: the offset to the data with @page
* @size: the length of the data
*
* Variant of skb_fill_page_desc() which does not deal with
* pfmemalloc, if page is not owned by us.
*/
static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
struct page *page, int off,
int size)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
__skb_fill_page_desc_noacc(shinfo, i, page, off, size);
shinfo->nr_frags = i + 1;
}
void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem,
int off, int size, unsigned int truesize);
static inline void skb_add_rx_frag(struct sk_buff *skb, int i,
struct page *page, int off, int size,
unsigned int truesize)
{
skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size,
truesize);
}
void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
unsigned int truesize);
#define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb)
{
return skb->head + skb->tail;
}
static inline void skb_reset_tail_pointer(struct sk_buff *skb)
{
skb->tail = skb->data - skb->head;
}
static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
{
skb_reset_tail_pointer(skb);
skb->tail += offset;
}
#else /* NET_SKBUFF_DATA_USES_OFFSET */
static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb)
{
return skb->tail;
}
static inline void skb_reset_tail_pointer(struct sk_buff *skb)
{
skb->tail = skb->data;
}
static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
{
skb->tail = skb->data + offset;
}
#endif /* NET_SKBUFF_DATA_USES_OFFSET */
static inline void skb_assert_len(struct sk_buff *skb)
{
#ifdef CONFIG_DEBUG_NET
if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
#endif /* CONFIG_DEBUG_NET */
}
#if defined(CONFIG_FAIL_SKB_REALLOC)
void skb_might_realloc(struct sk_buff *skb);
#else
static inline void skb_might_realloc(struct sk_buff *skb) {}
#endif
/*
* Add data to an sk_buff
*/
void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
void *skb_put(struct sk_buff *skb, unsigned int len);
static inline void *__skb_put(struct sk_buff *skb, unsigned int len)
{
void *tmp = skb_tail_pointer(skb);
SKB_LINEAR_ASSERT(skb);
skb->tail += len;
skb->len += len;
return tmp;
}
static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len)
{
void *tmp = __skb_put(skb, len);
memset(tmp, 0, len);
return tmp;
}
static inline void *__skb_put_data(struct sk_buff *skb, const void *data,
unsigned int len)
{
void *tmp = __skb_put(skb, len);
memcpy(tmp, data, len);
return tmp;
}
static inline void __skb_put_u8(struct sk_buff *skb, u8 val)
{
*(u8 *)__skb_put(skb, 1) = val;
}
static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len)
{
void *tmp = skb_put(skb, len);
memset(tmp, 0, len);
return tmp;
}
static inline void *skb_put_data(struct sk_buff *skb, const void *data,
unsigned int len)
{
void *tmp = skb_put(skb, len);
memcpy(tmp, data, len);
return tmp;
}
static inline void skb_put_u8(struct sk_buff *skb, u8 val)
{
*(u8 *)skb_put(skb, 1) = val;
}
void *skb_push(struct sk_buff *skb, unsigned int len);
static inline void *__skb_push(struct sk_buff *skb, unsigned int len)
{
DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
skb->data -= len;
skb->len += len;
return skb->data;
}
void *skb_pull(struct sk_buff *skb, unsigned int len);
static inline void *__skb_pull(struct sk_buff *skb, unsigned int len)
{
DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
skb->len -= len;
if (unlikely(skb->len < skb->data_len)) {
#if defined(CONFIG_DEBUG_NET)
skb->len += len;
pr_err("__skb_pull(len=%u)\n", len);
skb_dump(KERN_ERR, skb, false);
#endif
BUG();
}
return skb->data += len;
}
static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len)
{
return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
}
void *skb_pull_data(struct sk_buff *skb, size_t len);
void *__pskb_pull_tail(struct sk_buff *skb, int delta);
static inline enum skb_drop_reason
pskb_may_pull_reason(struct sk_buff *skb, unsigned int len)
{
DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
skb_might_realloc(skb);
if (likely(len <= skb_headlen(skb)))
return SKB_NOT_DROPPED_YET;
if (unlikely(len > skb->len))
return SKB_DROP_REASON_PKT_TOO_SMALL;
if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb))))
return SKB_DROP_REASON_NOMEM;
return SKB_NOT_DROPPED_YET;
}
static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len)
{
return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET;
}
static inline void *pskb_pull(struct sk_buff *skb, unsigned int len)
{
if (!pskb_may_pull(skb, len))
return NULL;
skb->len -= len;
return skb->data += len;
}
void skb_condense(struct sk_buff *skb);
/**
* skb_headroom - bytes at buffer head
* @skb: buffer to check
*
* Return the number of bytes of free space at the head of an &sk_buff.
*/
static inline unsigned int skb_headroom(const struct sk_buff *skb)
{
return skb->data - skb->head;
}
/**
* skb_tailroom - bytes at buffer end
* @skb: buffer to check
*
* Return the number of bytes of free space at the tail of an sk_buff
*/
static inline int skb_tailroom(const struct sk_buff *skb)
{
return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail;
}
/**
* skb_availroom - bytes at buffer end
* @skb: buffer to check
*
* Return the number of bytes of free space at the tail of an sk_buff
* allocated by sk_stream_alloc()
*/
static inline int skb_availroom(const struct sk_buff *skb)
{
if (skb_is_nonlinear(skb))
return 0;
return skb->end - skb->tail - skb->reserved_tailroom;
}
/**
* skb_reserve - adjust headroom
* @skb: buffer to alter
* @len: bytes to move
*
* Increase the headroom of an empty &sk_buff by reducing the tail
* room. This is only allowed for an empty buffer.
*/
static inline void skb_reserve(struct sk_buff *skb, int len)
{
skb->data += len;
skb->tail += len;
}
/**
* skb_tailroom_reserve - adjust reserved_tailroom
* @skb: buffer to alter
* @mtu: maximum amount of headlen permitted
* @needed_tailroom: minimum amount of reserved_tailroom
*
* Set reserved_tailroom so that headlen can be as large as possible but
* not larger than mtu and tailroom cannot be smaller than
* needed_tailroom.
* The required headroom should already have been reserved before using
* this function.
*/
static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
unsigned int needed_tailroom)
{
SKB_LINEAR_ASSERT(skb);
if (mtu < skb_tailroom(skb) - needed_tailroom)
/* use at most mtu */
skb->reserved_tailroom = skb_tailroom(skb) - mtu;
else
/* use up to all available space */
skb->reserved_tailroom = needed_tailroom;
}
#define ENCAP_TYPE_ETHER 0
#define ENCAP_TYPE_IPPROTO 1
static inline void skb_set_inner_protocol(struct sk_buff *skb,
__be16 protocol)
{
skb->inner_protocol = protocol;
skb->inner_protocol_type = ENCAP_TYPE_ETHER;
}
static inline void skb_set_inner_ipproto(struct sk_buff *skb,
__u8 ipproto)
{
skb->inner_ipproto = ipproto;
skb->inner_protocol_type = ENCAP_TYPE_IPPROTO;
}
static inline void skb_reset_inner_headers(struct sk_buff *skb)
{
skb->inner_mac_header = skb->mac_header;
skb->inner_network_header = skb->network_header;
skb->inner_transport_header = skb->transport_header;
}
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
return skb->mac_header != (typeof(skb->mac_header))~0U;
}
static inline void skb_reset_mac_len(struct sk_buff *skb)
{
if (!skb_mac_header_was_set(skb)) {
DEBUG_NET_WARN_ON_ONCE(1);
skb->mac_len = 0;
} else {
skb->mac_len = skb->network_header - skb->mac_header;
}
}
static inline unsigned char *skb_inner_transport_header(const struct sk_buff
*skb)
{
return skb->head + skb->inner_transport_header;
}
static inline int skb_inner_transport_offset(const struct sk_buff *skb)
{
return skb_inner_transport_header(skb) - skb->data;
}
static inline void skb_reset_inner_transport_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset);
skb->inner_transport_header = offset;
}
static inline void skb_set_inner_transport_header(struct sk_buff *skb,
const int offset)
{
skb_reset_inner_transport_header(skb);
skb->inner_transport_header += offset;
}
static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb)
{
return skb->head + skb->inner_network_header;
}
static inline void skb_reset_inner_network_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset);
skb->inner_network_header = offset;
}
static inline void skb_set_inner_network_header(struct sk_buff *skb,
const int offset)
{
skb_reset_inner_network_header(skb);
skb->inner_network_header += offset;
}
static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb)
{
return skb->inner_network_header > 0;
}
static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb)
{
return skb->head + skb->inner_mac_header;
}
static inline void skb_reset_inner_mac_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset);
skb->inner_mac_header = offset;
}
static inline void skb_set_inner_mac_header(struct sk_buff *skb,
const int offset)
{
skb_reset_inner_mac_header(skb);
skb->inner_mac_header += offset;
}
static inline bool skb_transport_header_was_set(const struct sk_buff *skb)
{
return skb->transport_header != (typeof(skb->transport_header))~0U;
}
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb));
return skb->head + skb->transport_header;
}
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset);
skb->transport_header = offset;
}
static inline void skb_set_transport_header(struct sk_buff *skb,
const int offset)
{
skb_reset_transport_header(skb);
skb->transport_header += offset;
}
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
return skb->head + skb->network_header;
}
static inline void skb_reset_network_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset);
skb->network_header = offset;
}
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
skb_reset_network_header(skb);
skb->network_header += offset;
}
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb));
return skb->head + skb->mac_header;
}
static inline int skb_mac_offset(const struct sk_buff *skb)
{
return skb_mac_header(skb) - skb->data;
}
static inline u32 skb_mac_header_len(const struct sk_buff *skb)
{
DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb));
return skb->network_header - skb->mac_header;
}
static inline void skb_unset_mac_header(struct sk_buff *skb)
{
skb->mac_header = (typeof(skb->mac_header))~0U;
}
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
long offset = skb->data - skb->head;
DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset);
skb->mac_header = offset;
}
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
skb_reset_mac_header(skb);
skb->mac_header += offset;
}
static inline void skb_pop_mac_header(struct sk_buff *skb)
{
skb->mac_header = skb->network_header;
}
static inline void skb_probe_transport_header(struct sk_buff *skb)
{
struct flow_keys_basic keys;
if (skb_transport_header_was_set(skb))
return;
if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
NULL, 0, 0, 0, 0))
skb_set_transport_header(skb, keys.control.thoff);
}
static inline void skb_mac_header_rebuild(struct sk_buff *skb)
{
if (skb_mac_header_was_set(skb)) {
const unsigned char *old_mac = skb_mac_header(skb);
skb_set_mac_header(skb, -skb->mac_len);
memmove(skb_mac_header(skb), old_mac, skb->mac_len);
}
}
/* Move the full mac header up to current network_header.
* Leaves skb->data pointing at offset skb->mac_len into the mac_header.
* Must be provided the complete mac header length.
*/
static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len)
{
if (skb_mac_header_was_set(skb)) {
const unsigned char *old_mac = skb_mac_header(skb);
skb_set_mac_header(skb, -full_mac_len);
memmove(skb_mac_header(skb), old_mac, full_mac_len);
__skb_push(skb, full_mac_len - skb->mac_len);
}
}
static inline int skb_checksum_start_offset(const struct sk_buff *skb)
{
return skb->csum_start - skb_headroom(skb);
}
static inline unsigned char *skb_checksum_start(const struct sk_buff *skb)
{
return skb->head + skb->csum_start;
}
static inline int skb_transport_offset(const struct sk_buff *skb)
{
return skb_transport_header(skb) - skb->data;
}
static inline u32 skb_network_header_len(const struct sk_buff *skb)
{
DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb));
return skb->transport_header - skb->network_header;
}
static inline u32 skb_inner_network_header_len(const struct sk_buff *skb)
{
return skb->inner_transport_header - skb->inner_network_header;
}
static inline int skb_network_offset(const struct sk_buff *skb)
{
return skb_network_header(skb) - skb->data;
}
static inline int skb_inner_network_offset(const struct sk_buff *skb)
{
return skb_inner_network_header(skb) - skb->data;
}
static inline enum skb_drop_reason
pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len)
{
return pskb_may_pull_reason(skb, skb_network_offset(skb) + len);
}
static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
{
return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET;
}
/*
* CPUs often take a performance hit when accessing unaligned memory
* locations. The actual performance hit varies, it can be small if the
* hardware handles it or large if we have to take an exception and fix it
* in software.
*
* Since an ethernet header is 14 bytes network drivers often end up with
* the IP header at an unaligned offset. The IP header can be aligned by
* shifting the start of the packet by 2 bytes. Drivers should do this
* with:
*
* skb_reserve(skb, NET_IP_ALIGN);
*
* The downside to this alignment of the IP header is that the DMA is now
* unaligned. On some architectures the cost of an unaligned DMA is high
* and this cost outweighs the gains made by aligning the IP header.
*
* Since this trade off varies between architectures, we allow NET_IP_ALIGN
* to be overridden.
*/
#ifndef NET_IP_ALIGN
#define NET_IP_ALIGN 2
#endif
/*
* The networking layer reserves some headroom in skb data (via
* dev_alloc_skb). This is used to avoid having to reallocate skb data when
* the header has to grow. In the default case, if the header has to grow
* 32 bytes or less we avoid the reallocation.
*
* Unfortunately this headroom changes the DMA alignment of the resulting
* network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive
* on some architectures. An architecture can override this value,
* perhaps setting it to a cacheline in size (since that will maintain
* cacheline alignment of the DMA). It must be a power of 2.
*
* Various parts of the networking layer expect at least 32 bytes of
* headroom, you should not reduce this.
*
* Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS)
* to reduce average number of cache lines per packet.
* get_rps_cpu() for example only access one 64 bytes aligned block :
* NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8)
*/
#ifndef NET_SKB_PAD
#define NET_SKB_PAD max(32, L1_CACHE_BYTES)
#endif
int ___pskb_trim(struct sk_buff *skb, unsigned int len);
static inline void __skb_set_length(struct sk_buff *skb, unsigned int len)
{
if (WARN_ON(skb_is_nonlinear(skb)))
return;
skb->len = len; skb_set_tail_pointer(skb, len);
}
static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
{
__skb_set_length(skb, len);
}
void skb_trim(struct sk_buff *skb, unsigned int len);
static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
{
if (skb->data_len)
return ___pskb_trim(skb, len); __skb_trim(skb, len);
return 0;
}
static inline int pskb_trim(struct sk_buff *skb, unsigned int len)
{
skb_might_realloc(skb);
return (len < skb->len) ? __pskb_trim(skb, len) : 0;
}
/**
* pskb_trim_unique - remove end from a paged unique (not cloned) buffer
* @skb: buffer to alter
* @len: new length
*
* This is identical to pskb_trim except that the caller knows that
* the skb is not cloned so we should never get an error due to out-
* of-memory.
*/
static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len)
{
int err = pskb_trim(skb, len);
BUG_ON(err);
}
static inline int __skb_grow(struct sk_buff *skb, unsigned int len)
{
unsigned int diff = len - skb->len;
if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb),
GFP_ATOMIC);
if (ret)
return ret;
}
__skb_set_length(skb, len);
return 0;
}
/**
* skb_orphan - orphan a buffer
* @skb: buffer to orphan
*
* If a buffer currently has an owner then we call the owner's
* destructor function and make the @skb unowned. The buffer continues
* to exist but is no longer charged to its former owner.
*/
static inline void skb_orphan(struct sk_buff *skb)
{
if (skb->destructor) {
skb->destructor(skb);
skb->destructor = NULL;
skb->sk = NULL;
} else {
BUG_ON(skb->sk);
}
}
/**
* skb_orphan_frags - orphan the frags contained in a buffer
* @skb: buffer to orphan frags from
* @gfp_mask: allocation mask for replacement pages
*
* For each frag in the SKB which needs a destructor (i.e. has an
* owner) create a copy of that frag and release the original
* page by calling the destructor.
*/
static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask)
{
if (likely(!skb_zcopy(skb)))
return 0;
if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN)
return 0;
return skb_copy_ubufs(skb, gfp_mask);
}
/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */
static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask)
{
if (likely(!skb_zcopy(skb)))
return 0;
return skb_copy_ubufs(skb, gfp_mask);
}
/**
* __skb_queue_purge_reason - empty a list
* @list: list to empty
* @reason: drop reason
*
* Delete all buffers on an &sk_buff list. Each buffer is removed from
* the list and one reference dropped. This function does not take the
* list lock and the caller must hold the relevant locks to use it.
*/
static inline void __skb_queue_purge_reason(struct sk_buff_head *list,
enum skb_drop_reason reason)
{
struct sk_buff *skb;
while ((skb = __skb_dequeue(list)) != NULL)
kfree_skb_reason(skb, reason);
}
static inline void __skb_queue_purge(struct sk_buff_head *list)
{
__skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE);
}
void skb_queue_purge_reason(struct sk_buff_head *list,
enum skb_drop_reason reason);
static inline void skb_queue_purge(struct sk_buff_head *list)
{
skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE);
}
unsigned int skb_rbtree_purge(struct rb_root *root);
void skb_errqueue_purge(struct sk_buff_head *list);
void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
/**
* netdev_alloc_frag - allocate a page fragment
* @fragsz: fragment size
*
* Allocates a frag from a page for receive buffer.
* Uses GFP_ATOMIC allocations.
*/
static inline void *netdev_alloc_frag(unsigned int fragsz)
{
return __netdev_alloc_frag_align(fragsz, ~0u);
}
static inline void *netdev_alloc_frag_align(unsigned int fragsz,
unsigned int align)
{
WARN_ON_ONCE(!is_power_of_2(align));
return __netdev_alloc_frag_align(fragsz, -align);
}
struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length,
gfp_t gfp_mask);
/**
* netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
* @length: length to allocate
*
* Allocate a new &sk_buff and assign it a usage count of one. The
* buffer has unspecified headroom built in. Users should allocate
* the headroom they think they need without accounting for the
* built in space. The built in space is used for optimisations.
*
* %NULL is returned if there is no free memory. Although this function
* allocates memory it can be called from an interrupt.
*/
static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev,
unsigned int length)
{
return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
}
/* legacy helper around __netdev_alloc_skb() */
static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
gfp_t gfp_mask)
{
return __netdev_alloc_skb(NULL, length, gfp_mask);
}
/* legacy helper around netdev_alloc_skb() */
static inline struct sk_buff *dev_alloc_skb(unsigned int length)
{
return netdev_alloc_skb(NULL, length);
}
static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev,
unsigned int length, gfp_t gfp)
{
struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp);
if (NET_IP_ALIGN && skb)
skb_reserve(skb, NET_IP_ALIGN);
return skb;
}
static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
unsigned int length)
{
return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
}
static inline void skb_free_frag(void *addr)
{
page_frag_free(addr);
}
void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
static inline void *napi_alloc_frag(unsigned int fragsz)
{
return __napi_alloc_frag_align(fragsz, ~0u);
}
static inline void *napi_alloc_frag_align(unsigned int fragsz,
unsigned int align)
{
WARN_ON_ONCE(!is_power_of_2(align));
return __napi_alloc_frag_align(fragsz, -align);
}
struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length);
void napi_consume_skb(struct sk_buff *skb, int budget);
void napi_skb_free_stolen_head(struct sk_buff *skb);
void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason);
/**
* __dev_alloc_pages - allocate page for network Rx
* @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
* @order: size of the allocation
*
* Allocate a new page.
*
* %NULL is returned if there is no free memory.
*/
static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask,
unsigned int order)
{
/* This piece of code contains several assumptions.
* 1. This is for device Rx, therefore a cold page is preferred.
* 2. The expectation is the user wants a compound page.
* 3. If requesting a order 0 page it will not be compound
* due to the check to see if order has a value in prep_new_page
* 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to
* code in gfp_to_alloc_flags that should be enforcing this.
*/
gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order);
}
#define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__))
/*
* This specialized allocator has to be a macro for its allocations to be
* accounted separately (to have a separate alloc_tag).
*/
#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order)
/**
* __dev_alloc_page - allocate a page for network Rx
* @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
*
* Allocate a new page.
*
* %NULL is returned if there is no free memory.
*/
static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask)
{
return __dev_alloc_pages_noprof(gfp_mask, 0);
}
#define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__))
/*
* This specialized allocator has to be a macro for its allocations to be
* accounted separately (to have a separate alloc_tag).
*/
#define dev_alloc_page() dev_alloc_pages(0)
/**
* dev_page_is_reusable - check whether a page can be reused for network Rx
* @page: the page to test
*
* A page shouldn't be considered for reusing/recycling if it was allocated
* under memory pressure or at a distant memory node.
*
* Returns: false if this page should be returned to page allocator, true
* otherwise.
*/
static inline bool dev_page_is_reusable(const struct page *page)
{
return likely(page_to_nid(page) == numa_mem_id() &&
!page_is_pfmemalloc(page));
}
/**
* skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
* @page: The page that was allocated from skb_alloc_page
* @skb: The skb that may need pfmemalloc set
*/
static inline void skb_propagate_pfmemalloc(const struct page *page,
struct sk_buff *skb)
{
if (page_is_pfmemalloc(page)) skb->pfmemalloc = true;
}
/**
* skb_frag_off() - Returns the offset of a skb fragment
* @frag: the paged fragment
*/
static inline unsigned int skb_frag_off(const skb_frag_t *frag)
{
return frag->offset;
}
/**
* skb_frag_off_add() - Increments the offset of a skb fragment by @delta
* @frag: skb fragment
* @delta: value to add
*/
static inline void skb_frag_off_add(skb_frag_t *frag, int delta)
{
frag->offset += delta;
}
/**
* skb_frag_off_set() - Sets the offset of a skb fragment
* @frag: skb fragment
* @offset: offset of fragment
*/
static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset)
{
frag->offset = offset;
}
/**
* skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment
* @fragto: skb fragment where offset is set
* @fragfrom: skb fragment offset is copied from
*/
static inline void skb_frag_off_copy(skb_frag_t *fragto,
const skb_frag_t *fragfrom)
{
fragto->offset = fragfrom->offset;
}
/* Return: true if the skb_frag contains a net_iov. */
static inline bool skb_frag_is_net_iov(const skb_frag_t *frag)
{
return netmem_is_net_iov(frag->netmem);
}
/**
* skb_frag_net_iov - retrieve the net_iov referred to by fragment
* @frag: the fragment
*
* Return: the &struct net_iov associated with @frag. Returns NULL if this
* frag has no associated net_iov.
*/
static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag)
{
if (!skb_frag_is_net_iov(frag))
return NULL;
return netmem_to_net_iov(frag->netmem);
}
/**
* skb_frag_page - retrieve the page referred to by a paged fragment
* @frag: the paged fragment
*
* Return: the &struct page associated with @frag. Returns NULL if this frag
* has no associated page.
*/
static inline struct page *skb_frag_page(const skb_frag_t *frag)
{
if (skb_frag_is_net_iov(frag))
return NULL;
return netmem_to_page(frag->netmem);
}
/**
* skb_frag_netmem - retrieve the netmem referred to by a fragment
* @frag: the fragment
*
* Return: the &netmem_ref associated with @frag.
*/
static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag)
{
return frag->netmem;
}
int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
unsigned int headroom);
int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
const struct bpf_prog *prog);
/**
* skb_frag_address - gets the address of the data contained in a paged fragment
* @frag: the paged fragment buffer
*
* Returns: the address of the data within @frag. The page must already
* be mapped.
*/
static inline void *skb_frag_address(const skb_frag_t *frag)
{
if (!skb_frag_page(frag))
return NULL;
return page_address(skb_frag_page(frag)) + skb_frag_off(frag);
}
/**
* skb_frag_address_safe - gets the address of the data contained in a paged fragment
* @frag: the paged fragment buffer
*
* Returns: the address of the data within @frag. Checks that the page
* is mapped and returns %NULL otherwise.
*/
static inline void *skb_frag_address_safe(const skb_frag_t *frag)
{
void *ptr = page_address(skb_frag_page(frag));
if (unlikely(!ptr))
return NULL;
return ptr + skb_frag_off(frag);
}
/**
* skb_frag_page_copy() - sets the page in a fragment from another fragment
* @fragto: skb fragment where page is set
* @fragfrom: skb fragment page is copied from
*/
static inline void skb_frag_page_copy(skb_frag_t *fragto,
const skb_frag_t *fragfrom)
{
fragto->netmem = fragfrom->netmem;
}
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);
/**
* __skb_frag_dma_map - maps a paged fragment via the DMA API
* @dev: the device to map the fragment to
* @frag: the paged fragment to map
* @offset: the offset within the fragment (starting at the
* fragment's own offset)
* @size: the number of bytes to map
* @dir: the direction of the mapping (``PCI_DMA_*``)
*
* Maps the page associated with @frag to @device.
*/
static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
const skb_frag_t *frag,
size_t offset, size_t size,
enum dma_data_direction dir)
{
return dma_map_page(dev, skb_frag_page(frag),
skb_frag_off(frag) + offset, size, dir);
}
#define skb_frag_dma_map(dev, frag, ...) \
CONCATENATE(_skb_frag_dma_map, \
COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__)
#define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \
const skb_frag_t *uf = (frag); \
size_t uo = (offset); \
\
__skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \
DMA_TO_DEVICE); \
})
#define _skb_frag_dma_map1(dev, frag, offset) \
__skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \
__UNIQUE_ID(offset_))
#define _skb_frag_dma_map0(dev, frag) \
_skb_frag_dma_map1(dev, frag, 0)
#define _skb_frag_dma_map2(dev, frag, offset, size) \
__skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE)
#define _skb_frag_dma_map3(dev, frag, offset, size, dir) \
__skb_frag_dma_map(dev, frag, offset, size, dir)
static inline struct sk_buff *pskb_copy(struct sk_buff *skb,
gfp_t gfp_mask)
{
return __pskb_copy(skb, skb_headroom(skb), gfp_mask);
}
static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb,
gfp_t gfp_mask)
{
return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true);
}
/**
* skb_clone_writable - is the header of a clone writable
* @skb: buffer to check
* @len: length up to which to write
*
* Returns true if modifying the header part of the cloned buffer
* does not requires the data to be copied.
*/
static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len)
{
return !skb_header_cloned(skb) &&
skb_headroom(skb) + len <= skb->hdr_len;
}
static inline int skb_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
return skb_cloned(skb) && !skb_clone_writable(skb, write_len) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
}
static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
int cloned)
{
int delta = 0;
if (headroom > skb_headroom(skb))
delta = headroom - skb_headroom(skb);
if (delta || cloned)
return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0,
GFP_ATOMIC);
return 0;
}
/**
* skb_cow - copy header of skb when it is required
* @skb: buffer to cow
* @headroom: needed headroom
*
* If the skb passed lacks sufficient headroom or its data part
* is shared, data is reallocated. If reallocation fails, an error
* is returned and original skb is not changed.
*
* The result is skb with writable area skb->head...skb->tail
* and at least @headroom of space at head.
*/
static inline int skb_cow(struct sk_buff *skb, unsigned int headroom)
{
return __skb_cow(skb, headroom, skb_cloned(skb));
}
/**
* skb_cow_head - skb_cow but only making the head writable
* @skb: buffer to cow
* @headroom: needed headroom
*
* This function is identical to skb_cow except that we replace the
* skb_cloned check by skb_header_cloned. It should be used when
* you only need to push on some header and do not need to modify
* the data.
*/
static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom)
{
return __skb_cow(skb, headroom, skb_header_cloned(skb));
}
/**
* skb_padto - pad an skbuff up to a minimal size
* @skb: buffer to pad
* @len: minimal length
*
* Pads up a buffer to ensure the trailing bytes exist and are
* blanked. If the buffer already contains sufficient data it
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error.
*/
static inline int skb_padto(struct sk_buff *skb, unsigned int len)
{
unsigned int size = skb->len;
if (likely(size >= len))
return 0;
return skb_pad(skb, len - size);
}
/**
* __skb_put_padto - increase size and pad an skbuff up to a minimal size
* @skb: buffer to pad
* @len: minimal length
* @free_on_error: free buffer on error
*
* Pads up a buffer to ensure the trailing bytes exist and are
* blanked. If the buffer already contains sufficient data it
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error if @free_on_error is true.
*/
static inline int __must_check __skb_put_padto(struct sk_buff *skb,
unsigned int len,
bool free_on_error)
{
unsigned int size = skb->len;
if (unlikely(size < len)) {
len -= size;
if (__skb_pad(skb, len, free_on_error))
return -ENOMEM;
__skb_put(skb, len);
}
return 0;
}
/**
* skb_put_padto - increase size and pad an skbuff up to a minimal size
* @skb: buffer to pad
* @len: minimal length
*
* Pads up a buffer to ensure the trailing bytes exist and are
* blanked. If the buffer already contains sufficient data it
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error.
*/
static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
{
return __skb_put_padto(skb, len, true);
}
bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i)
__must_check;
static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
const struct page *page, int off)
{
if (skb_zcopy(skb))
return false;
if (i) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
return page == skb_frag_page(frag) &&
off == skb_frag_off(frag) + skb_frag_size(frag);
}
return false;
}
static inline int __skb_linearize(struct sk_buff *skb)
{
return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
}
/**
* skb_linearize - convert paged skb to linear one
* @skb: buffer to linarize
*
* If there is no free memory -ENOMEM is returned, otherwise zero
* is returned and the old skb data released.
*/
static inline int skb_linearize(struct sk_buff *skb)
{
return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0;
}
/**
* skb_has_shared_frag - can any frag be overwritten
* @skb: buffer to test
*
* Return: true if the skb has at least one frag that might be modified
* by an external entity (as in vmsplice()/sendfile())
*/
static inline bool skb_has_shared_frag(const struct sk_buff *skb)
{
return skb_is_nonlinear(skb) &&
skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG;
}
/**
* skb_linearize_cow - make sure skb is linear and writable
* @skb: buffer to process
*
* If there is no free memory -ENOMEM is returned, otherwise zero
* is returned and the old skb data released.
*/
static inline int skb_linearize_cow(struct sk_buff *skb)
{
return skb_is_nonlinear(skb) || skb_cloned(skb) ?
__skb_linearize(skb) : 0;
}
static __always_inline void
__skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len,
unsigned int off)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_block_sub(skb->csum,
csum_partial(start, len, 0), off);
else if (skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_start_offset(skb) < 0)
skb->ip_summed = CHECKSUM_NONE;
}
/**
* skb_postpull_rcsum - update checksum for received skb after pull
* @skb: buffer to update
* @start: start of data before pull
* @len: length of data pulled
*
* After doing a pull on a received packet, you need to call this to
* update the CHECKSUM_COMPLETE checksum, or set ip_summed to
* CHECKSUM_NONE so that it can be recomputed from scratch.
*/
static inline void skb_postpull_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = wsum_negate(csum_partial(start, len,
wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_start_offset(skb) < 0)
skb->ip_summed = CHECKSUM_NONE;
}
static __always_inline void
__skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len,
unsigned int off)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_block_add(skb->csum,
csum_partial(start, len, 0), off);
}
/**
* skb_postpush_rcsum - update checksum for received skb after push
* @skb: buffer to update
* @start: start of data after push
* @len: length of data pushed
*
* After doing a push on a received packet, you need to call this to
* update the CHECKSUM_COMPLETE checksum.
*/
static inline void skb_postpush_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
__skb_postpush_rcsum(skb, start, len, 0);
}
void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
/**
* skb_push_rcsum - push skb and update receive checksum
* @skb: buffer to update
* @len: length of data pulled
*
* This function performs an skb_push on the packet and updates
* the CHECKSUM_COMPLETE checksum. It should be used on
* receive path processing instead of skb_push unless you know
* that the checksum difference is zero (e.g., a valid IP header)
* or you are setting ip_summed to CHECKSUM_NONE.
*/
static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len)
{
skb_push(skb, len);
skb_postpush_rcsum(skb, skb->data, len);
return skb->data;
}
int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len);
/**
* pskb_trim_rcsum - trim received skb and update checksum
* @skb: buffer to trim
* @len: new length
*
* This is exactly the same as pskb_trim except that it ensures the
* checksum of received packets are still valid after the operation.
* It can change skb pointers.
*/
static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
{
skb_might_realloc(skb);
if (likely(len >= skb->len))
return 0;
return pskb_trim_rcsum_slow(skb, len);
}
static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
__skb_trim(skb, len);
return 0;
}
static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
return __skb_grow(skb, len);
}
#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
#define skb_rb_first(root) rb_to_skb(rb_first(root))
#define skb_rb_last(root) rb_to_skb(rb_last(root))
#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode))
#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode))
#define skb_queue_walk(queue, skb) \
for (skb = (queue)->next; \
skb != (struct sk_buff *)(queue); \
skb = skb->next)
#define skb_queue_walk_safe(queue, skb, tmp) \
for (skb = (queue)->next, tmp = skb->next; \
skb != (struct sk_buff *)(queue); \
skb = tmp, tmp = skb->next)
#define skb_queue_walk_from(queue, skb) \
for (; skb != (struct sk_buff *)(queue); \
skb = skb->next)
#define skb_rbtree_walk(skb, root) \
for (skb = skb_rb_first(root); skb != NULL; \
skb = skb_rb_next(skb))
#define skb_rbtree_walk_from(skb) \
for (; skb != NULL; \
skb = skb_rb_next(skb))
#define skb_rbtree_walk_from_safe(skb, tmp) \
for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \
skb = tmp)
#define skb_queue_walk_from_safe(queue, skb, tmp) \
for (tmp = skb->next; \
skb != (struct sk_buff *)(queue); \
skb = tmp, tmp = skb->next)
#define skb_queue_reverse_walk(queue, skb) \
for (skb = (queue)->prev; \
skb != (struct sk_buff *)(queue); \
skb = skb->prev)
#define skb_queue_reverse_walk_safe(queue, skb, tmp) \
for (skb = (queue)->prev, tmp = skb->prev; \
skb != (struct sk_buff *)(queue); \
skb = tmp, tmp = skb->prev)
#define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \
for (tmp = skb->prev; \
skb != (struct sk_buff *)(queue); \
skb = tmp, tmp = skb->prev)
static inline bool skb_has_frag_list(const struct sk_buff *skb)
{
return skb_shinfo(skb)->frag_list != NULL;
}
static inline void skb_frag_list_init(struct sk_buff *skb)
{
skb_shinfo(skb)->frag_list = NULL;
}
#define skb_walk_frags(skb, iter) \
for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue,
int *err, long *timeo_p,
const struct sk_buff *skb);
struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
struct sk_buff_head *queue,
unsigned int flags,
int *off, int *err,
struct sk_buff **last);
struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
struct sk_buff_head *queue,
unsigned int flags, int *off, int *err,
struct sk_buff **last);
struct sk_buff *__skb_recv_datagram(struct sock *sk,
struct sk_buff_head *sk_queue,
unsigned int flags, int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err);
__poll_t datagram_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
struct iov_iter *to, int size);
static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
struct msghdr *msg, int size)
{
return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size);
}
int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
struct msghdr *msg);
int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
struct iov_iter *to, int len,
struct ahash_request *hash);
int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
struct iov_iter *from, int len);
int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len);
int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len);
__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to,
int len);
int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int len,
unsigned int flags);
int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
int len);
int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len);
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
int len, int hlen);
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
void skb_scrub_packet(struct sk_buff *skb, bool xnet);
struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features,
unsigned int offset);
struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev);
int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
int skb_vlan_pop(struct sk_buff *skb);
int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
int skb_eth_pop(struct sk_buff *skb);
int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
const unsigned char *src);
int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
int mac_len, bool ethernet);
int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
bool ethernet);
int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
int skb_mpls_dec_ttl(struct sk_buff *skb);
struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
gfp_t gfp);
static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
{
return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT;
}
static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
{
return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
}
struct skb_checksum_ops {
__wsum (*update)(const void *mem, int len, __wsum wsum);
__wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len);
};
extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly;
__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
__wsum csum, const struct skb_checksum_ops *ops);
__wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
__wsum csum);
static inline void * __must_check
__skb_header_pointer(const struct sk_buff *skb, int offset, int len,
const void *data, int hlen, void *buffer)
{
if (likely(hlen - offset >= len))
return (void *)data + offset;
if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
return NULL;
return buffer;
}
static inline void * __must_check
skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer)
{ return __skb_header_pointer(skb, offset, len, skb->data,
skb_headlen(skb), buffer);
}
static inline void * __must_check
skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len)
{
if (likely(skb_headlen(skb) - offset >= len))
return skb->data + offset;
return NULL;
}
/**
* skb_needs_linearize - check if we need to linearize a given skb
* depending on the given device features.
* @skb: socket buffer to check
* @features: net device features
*
* Returns true if either:
* 1. skb has frag_list and the device doesn't support FRAGLIST, or
* 2. skb is fragmented and the device does not support SG.
*/
static inline bool skb_needs_linearize(struct sk_buff *skb,
netdev_features_t features)
{
return skb_is_nonlinear(skb) &&
((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) ||
(skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG)));
}
static inline void skb_copy_from_linear_data(const struct sk_buff *skb,
void *to,
const unsigned int len)
{
memcpy(to, skb->data, len);
}
static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb,
const int offset, void *to,
const unsigned int len)
{
memcpy(to, skb->data + offset, len);
}
static inline void skb_copy_to_linear_data(struct sk_buff *skb,
const void *from,
const unsigned int len)
{
memcpy(skb->data, from, len);
}
static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb,
const int offset,
const void *from,
const unsigned int len)
{
memcpy(skb->data + offset, from, len);
}
void skb_init(void);
static inline ktime_t skb_get_ktime(const struct sk_buff *skb)
{
return skb->tstamp;
}
/**
* skb_get_timestamp - get timestamp from a skb
* @skb: skb to get stamp from
* @stamp: pointer to struct __kernel_old_timeval to store stamp in
*
* Timestamps are stored in the skb as offsets to a base timestamp.
* This function converts the offset back to a struct timeval and stores
* it in stamp.
*/
static inline void skb_get_timestamp(const struct sk_buff *skb,
struct __kernel_old_timeval *stamp)
{
*stamp = ns_to_kernel_old_timeval(skb->tstamp);
}
static inline void skb_get_new_timestamp(const struct sk_buff *skb,
struct __kernel_sock_timeval *stamp)
{
struct timespec64 ts = ktime_to_timespec64(skb->tstamp);
stamp->tv_sec = ts.tv_sec;
stamp->tv_usec = ts.tv_nsec / 1000;
}
static inline void skb_get_timestampns(const struct sk_buff *skb,
struct __kernel_old_timespec *stamp)
{
struct timespec64 ts = ktime_to_timespec64(skb->tstamp);
stamp->tv_sec = ts.tv_sec;
stamp->tv_nsec = ts.tv_nsec;
}
static inline void skb_get_new_timestampns(const struct sk_buff *skb,
struct __kernel_timespec *stamp)
{
struct timespec64 ts = ktime_to_timespec64(skb->tstamp);
stamp->tv_sec = ts.tv_sec;
stamp->tv_nsec = ts.tv_nsec;
}
static inline void __net_timestamp(struct sk_buff *skb)
{
skb->tstamp = ktime_get_real();
skb->tstamp_type = SKB_CLOCK_REALTIME;
}
static inline ktime_t net_timedelta(ktime_t t)
{
return ktime_sub(ktime_get_real(), t);
}
static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
u8 tstamp_type)
{
skb->tstamp = kt;
if (kt)
skb->tstamp_type = tstamp_type;
else
skb->tstamp_type = SKB_CLOCK_REALTIME;
}
static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb,
ktime_t kt, clockid_t clockid)
{
u8 tstamp_type = SKB_CLOCK_REALTIME;
switch (clockid) {
case CLOCK_REALTIME:
break;
case CLOCK_MONOTONIC:
tstamp_type = SKB_CLOCK_MONOTONIC;
break;
case CLOCK_TAI:
tstamp_type = SKB_CLOCK_TAI;
break;
default:
WARN_ON_ONCE(1);
kt = 0;
}
skb_set_delivery_time(skb, kt, tstamp_type);
}
DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
/* It is used in the ingress path to clear the delivery_time.
* If needed, set the skb->tstamp to the (rcv) timestamp.
*/
static inline void skb_clear_delivery_time(struct sk_buff *skb)
{
if (skb->tstamp_type) {
skb->tstamp_type = SKB_CLOCK_REALTIME;
if (static_branch_unlikely(&netstamp_needed_key))
skb->tstamp = ktime_get_real();
else
skb->tstamp = 0;
}
}
static inline void skb_clear_tstamp(struct sk_buff *skb)
{
if (skb->tstamp_type)
return;
skb->tstamp = 0;
}
static inline ktime_t skb_tstamp(const struct sk_buff *skb)
{
if (skb->tstamp_type)
return 0;
return skb->tstamp;
}
static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond)
{
if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp)
return skb->tstamp;
if (static_branch_unlikely(&netstamp_needed_key) || cond)
return ktime_get_real();
return 0;
}
static inline u8 skb_metadata_len(const struct sk_buff *skb)
{
return skb_shinfo(skb)->meta_len;
}
static inline void *skb_metadata_end(const struct sk_buff *skb)
{
return skb_mac_header(skb);
}
static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
const struct sk_buff *skb_b,
u8 meta_len)
{
const void *a = skb_metadata_end(skb_a);
const void *b = skb_metadata_end(skb_b);
u64 diffs = 0;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
BITS_PER_LONG != 64)
goto slow;
/* Using more efficient variant than plain call to memcmp(). */
switch (meta_len) {
#define __it(x, op) (x -= sizeof(u##op))
#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
case 32: diffs |= __it_diff(a, b, 64);
fallthrough;
case 24: diffs |= __it_diff(a, b, 64);
fallthrough;
case 16: diffs |= __it_diff(a, b, 64);
fallthrough;
case 8: diffs |= __it_diff(a, b, 64);
break;
case 28: diffs |= __it_diff(a, b, 64);
fallthrough;
case 20: diffs |= __it_diff(a, b, 64);
fallthrough;
case 12: diffs |= __it_diff(a, b, 64);
fallthrough;
case 4: diffs |= __it_diff(a, b, 32);
break;
default:
slow:
return memcmp(a - meta_len, b - meta_len, meta_len);
}
return diffs;
}
static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
const struct sk_buff *skb_b)
{
u8 len_a = skb_metadata_len(skb_a);
u8 len_b = skb_metadata_len(skb_b);
if (!(len_a | len_b))
return false;
return len_a != len_b ?
true : __skb_metadata_differs(skb_a, skb_b, len_a);
}
static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len)
{
skb_shinfo(skb)->meta_len = meta_len;
}
static inline void skb_metadata_clear(struct sk_buff *skb)
{
skb_metadata_set(skb, 0);
}
struct sk_buff *skb_clone_sk(struct sk_buff *skb);
#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
void skb_clone_tx_timestamp(struct sk_buff *skb);
bool skb_defer_rx_timestamp(struct sk_buff *skb);
#else /* CONFIG_NETWORK_PHY_TIMESTAMPING */
static inline void skb_clone_tx_timestamp(struct sk_buff *skb)
{
}
static inline bool skb_defer_rx_timestamp(struct sk_buff *skb)
{
return false;
}
#endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */
/**
* skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps
*
* PHY drivers may accept clones of transmitted packets for
* timestamping via their phy_driver.txtstamp method. These drivers
* must call this function to return the skb back to the stack with a
* timestamp.
*
* @skb: clone of the original outgoing packet
* @hwtstamps: hardware time stamps
*
*/
void skb_complete_tx_timestamp(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps);
void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb,
struct skb_shared_hwtstamps *hwtstamps,
struct sock *sk, int tstype);
/**
* skb_tstamp_tx - queue clone of skb with send time stamps
* @orig_skb: the original outgoing packet
* @hwtstamps: hardware time stamps, may be NULL if not available
*
* If the skb has a socket associated, then this function clones the
* skb (thus sharing the actual data and optional structures), stores
* the optional hardware time stamping information (if non NULL) or
* generates a software time stamp (otherwise), then queues the clone
* to the error queue of the socket. Errors are silently ignored.
*/
void skb_tstamp_tx(struct sk_buff *orig_skb,
struct skb_shared_hwtstamps *hwtstamps);
/**
* skb_tx_timestamp() - Driver hook for transmit timestamping
*
* Ethernet MAC Drivers should call this function in their hard_xmit()
* function immediately before giving the sk_buff to the MAC hardware.
*
* Specifically, one should make absolutely sure that this function is
* called before TX completion of this packet can trigger. Otherwise
* the packet could potentially already be freed.
*
* @skb: A socket buffer.
*/
static inline void skb_tx_timestamp(struct sk_buff *skb)
{
skb_clone_tx_timestamp(skb);
if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF))
skb_tstamp_tx(skb, NULL);
}
/**
* skb_complete_wifi_ack - deliver skb with wifi status
*
* @skb: the original outgoing packet
* @acked: ack status
*
*/
void skb_complete_wifi_ack(struct sk_buff *skb, bool acked);
__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
__sum16 __skb_checksum_complete(struct sk_buff *skb);
static inline int skb_csum_unnecessary(const struct sk_buff *skb)
{
return ((skb->ip_summed == CHECKSUM_UNNECESSARY) ||
skb->csum_valid ||
(skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_start_offset(skb) >= 0));
}
/**
* skb_checksum_complete - Calculate checksum of an entire packet
* @skb: packet to process
*
* This function calculates the checksum over the entire packet plus
* the value of skb->csum. The latter can be used to supply the
* checksum of a pseudo header as used by TCP/UDP. It returns the
* checksum.
*
* For protocols that contain complete checksums such as ICMP/TCP/UDP,
* this function can be used to verify that checksum on received
* packets. In that case the function should return zero if the
* checksum is correct. In particular, this function will return zero
* if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the
* hardware has already verified the correctness of the checksum.
*/
static inline __sum16 skb_checksum_complete(struct sk_buff *skb)
{
return skb_csum_unnecessary(skb) ?
0 : __skb_checksum_complete(skb);
}
static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
if (skb->csum_level == 0)
skb->ip_summed = CHECKSUM_NONE;
else
skb->csum_level--;
}
}
static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
skb->csum_level++;
} else if (skb->ip_summed == CHECKSUM_NONE) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->csum_level = 0;
}
}
static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
skb->ip_summed = CHECKSUM_NONE;
skb->csum_level = 0;
}
}
/* Check if we need to perform checksum complete validation.
*
* Returns: true if checksum complete is needed, false otherwise
* (either checksum is unnecessary or zero checksum is allowed).
*/
static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
bool zero_okay,
__sum16 check)
{
if (skb_csum_unnecessary(skb) || (zero_okay && !check)) {
skb->csum_valid = 1;
__skb_decr_checksum_unnecessary(skb);
return false;
}
return true;
}
/* For small packets <= CHECKSUM_BREAK perform checksum complete directly
* in checksum_init.
*/
#define CHECKSUM_BREAK 76
/* Unset checksum-complete
*
* Unset checksum complete can be done when packet is being modified
* (uncompressed for instance) and checksum-complete value is
* invalidated.
*/
static inline void skb_checksum_complete_unset(struct sk_buff *skb)
{
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
}
/* Validate (init) checksum based on checksum complete.
*
* Return values:
* 0: checksum is validated or try to in skb_checksum_complete. In the latter
* case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo
* checksum is stored in skb->csum for use in __skb_checksum_complete
* non-zero: value of invalid checksum
*
*/
static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb,
bool complete,
__wsum psum)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
if (!csum_fold(csum_add(psum, skb->csum))) {
skb->csum_valid = 1;
return 0;
}
}
skb->csum = psum;
if (complete || skb->len <= CHECKSUM_BREAK) {
__sum16 csum;
csum = __skb_checksum_complete(skb);
skb->csum_valid = !csum;
return csum;
}
return 0;
}
static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto)
{
return 0;
}
/* Perform checksum validate (init). Note that this is a macro since we only
* want to calculate the pseudo header which is an input function if necessary.
* First we try to validate without any computation (checksum unnecessary) and
* then calculate based on checksum complete calling the function to compute
* pseudo header.
*
* Return values:
* 0: checksum is validated or try to in skb_checksum_complete
* non-zero: value of invalid checksum
*/
#define __skb_checksum_validate(skb, proto, complete, \
zero_okay, check, compute_pseudo) \
({ \
__sum16 __ret = 0; \
skb->csum_valid = 0; \
if (__skb_checksum_validate_needed(skb, zero_okay, check)) \
__ret = __skb_checksum_validate_complete(skb, \
complete, compute_pseudo(skb, proto)); \
__ret; \
})
#define skb_checksum_init(skb, proto, compute_pseudo) \
__skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo)
#define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \
__skb_checksum_validate(skb, proto, false, true, check, compute_pseudo)
#define skb_checksum_validate(skb, proto, compute_pseudo) \
__skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo)
#define skb_checksum_validate_zero_check(skb, proto, check, \
compute_pseudo) \
__skb_checksum_validate(skb, proto, true, true, check, compute_pseudo)
#define skb_checksum_simple_validate(skb) \
__skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo)
static inline bool __skb_checksum_convert_check(struct sk_buff *skb)
{
return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid);
}
static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo)
{
skb->csum = ~pseudo;
skb->ip_summed = CHECKSUM_COMPLETE;
}
#define skb_checksum_try_convert(skb, proto, compute_pseudo) \
do { \
if (__skb_checksum_convert_check(skb)) \
__skb_checksum_convert(skb, compute_pseudo(skb, proto)); \
} while (0)
static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr,
u16 start, u16 offset)
{
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = ((unsigned char *)ptr + start) - skb->head;
skb->csum_offset = offset - start;
}
/* Update skbuf and packet to reflect the remote checksum offload operation.
* When called, ptr indicates the starting point for skb->csum when
* ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete
* here, skb_postpull_rcsum is done so skb->csum start is ptr.
*/
static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr,
int start, int offset, bool nopartial)
{
__wsum delta;
if (!nopartial) {
skb_remcsum_adjust_partial(skb, ptr, start, offset);
return;
}
if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
__skb_checksum_complete(skb);
skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data);
}
delta = remcsum_adjust(ptr, skb->csum, start, offset);
/* Adjust skb->csum since we changed the packet */
skb->csum = csum_add(skb->csum, delta);
}
static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
return (void *)(skb->_nfct & NFCT_PTRMASK);
#else
return NULL;
#endif
}
static inline unsigned long skb_get_nfct(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
return skb->_nfct;
#else
return 0UL;
#endif
}
static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
skb->slow_gro |= !!nfct;
skb->_nfct = nfct;
#endif
}
#ifdef CONFIG_SKB_EXTENSIONS
enum skb_ext_id {
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
SKB_EXT_BRIDGE_NF,
#endif
#ifdef CONFIG_XFRM
SKB_EXT_SEC_PATH,
#endif
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
TC_SKB_EXT,
#endif
#if IS_ENABLED(CONFIG_MPTCP)
SKB_EXT_MPTCP,
#endif
#if IS_ENABLED(CONFIG_MCTP_FLOWS)
SKB_EXT_MCTP,
#endif
SKB_EXT_NUM, /* must be last */
};
/**
* struct skb_ext - sk_buff extensions
* @refcnt: 1 on allocation, deallocated on 0
* @offset: offset to add to @data to obtain extension address
* @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units
* @data: start of extension data, variable sized
*
* Note: offsets/lengths are stored in chunks of 8 bytes, this allows
* to use 'u8' types while allowing up to 2kb worth of extension data.
*/
struct skb_ext {
refcount_t refcnt;
u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */
u8 chunks; /* same */
char data[] __aligned(8);
};
struct skb_ext *__skb_ext_alloc(gfp_t flags);
void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
struct skb_ext *ext);
void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id);
void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id);
void __skb_ext_put(struct skb_ext *ext);
static inline void skb_ext_put(struct sk_buff *skb)
{
if (skb->active_extensions) __skb_ext_put(skb->extensions);
}
static inline void __skb_ext_copy(struct sk_buff *dst,
const struct sk_buff *src)
{
dst->active_extensions = src->active_extensions;
if (src->active_extensions) {
struct skb_ext *ext = src->extensions;
refcount_inc(&ext->refcnt);
dst->extensions = ext;
}
}
static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src)
{
skb_ext_put(dst);
__skb_ext_copy(dst, src);
}
static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i)
{
return !!ext->offset[i];
}
static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id)
{
return skb->active_extensions & (1 << id);
}
static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
{
if (skb_ext_exist(skb, id))
__skb_ext_del(skb, id);
}
static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id)
{
if (skb_ext_exist(skb, id)) {
struct skb_ext *ext = skb->extensions;
return (void *)ext + (ext->offset[id] << 3);
}
return NULL;
}
static inline void skb_ext_reset(struct sk_buff *skb)
{
if (unlikely(skb->active_extensions)) {
__skb_ext_put(skb->extensions);
skb->active_extensions = 0;
}
}
static inline bool skb_has_extensions(struct sk_buff *skb)
{
return unlikely(skb->active_extensions);
}
#else
static inline void skb_ext_put(struct sk_buff *skb) {}
static inline void skb_ext_reset(struct sk_buff *skb) {}
static inline void skb_ext_del(struct sk_buff *skb, int unused) {}
static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
static inline bool skb_has_extensions(struct sk_buff *skb) { return false; }
#endif /* CONFIG_SKB_EXTENSIONS */
static inline void nf_reset_ct(struct sk_buff *skb)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
nf_conntrack_put(skb_nfct(skb));
skb->_nfct = 0;
#endif
}
static inline void nf_reset_trace(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES)
skb->nf_trace = 0;
#endif
}
static inline void ipvs_reset(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IP_VS)
skb->ipvs_property = 0;
#endif
}
/* Note: This doesn't put any conntrack info in dst. */
static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
bool copy)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
dst->_nfct = src->_nfct;
nf_conntrack_get(skb_nfct(src));
#endif
#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES)
if (copy)
dst->nf_trace = src->nf_trace;
#endif
}
static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
nf_conntrack_put(skb_nfct(dst));
#endif
dst->slow_gro = src->slow_gro;
__nf_copy(dst, src, true);
}
#ifdef CONFIG_NETWORK_SECMARK
static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from)
{
to->secmark = from->secmark;
}
static inline void skb_init_secmark(struct sk_buff *skb)
{
skb->secmark = 0;
}
#else
static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from)
{ }
static inline void skb_init_secmark(struct sk_buff *skb)
{ }
#endif
static inline int secpath_exists(const struct sk_buff *skb)
{
#ifdef CONFIG_XFRM
return skb_ext_exist(skb, SKB_EXT_SEC_PATH);
#else
return 0;
#endif
}
static inline bool skb_irq_freeable(const struct sk_buff *skb)
{
return !skb->destructor &&
!secpath_exists(skb) &&
!skb_nfct(skb) &&
!skb->_skb_refdst &&
!skb_has_frag_list(skb);
}
static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping)
{
skb->queue_mapping = queue_mapping;
}
static inline u16 skb_get_queue_mapping(const struct sk_buff *skb)
{
return skb->queue_mapping;
}
static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from)
{
to->queue_mapping = from->queue_mapping;
}
static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue)
{
skb->queue_mapping = rx_queue + 1;
}
static inline u16 skb_get_rx_queue(const struct sk_buff *skb)
{
return skb->queue_mapping - 1;
}
static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
{
return skb->queue_mapping != 0;
}
static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val)
{
skb->dst_pending_confirm = val;
}
static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb)
{
return skb->dst_pending_confirm != 0;
}
static inline struct sec_path *skb_sec_path(const struct sk_buff *skb)
{
#ifdef CONFIG_XFRM
return skb_ext_find(skb, SKB_EXT_SEC_PATH);
#else
return NULL;
#endif
}
static inline bool skb_is_gso(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_size;
}
/* Note: Should be called only if skb_is_gso(skb) is true */
static inline bool skb_is_gso_v6(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6;
}
/* Note: Should be called only if skb_is_gso(skb) is true */
static inline bool skb_is_gso_sctp(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP;
}
/* Note: Should be called only if skb_is_gso(skb) is true */
static inline bool skb_is_gso_tcp(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6);
}
static inline void skb_gso_reset(struct sk_buff *skb)
{
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_segs = 0;
skb_shinfo(skb)->gso_type = 0;
}
static inline void skb_increase_gso_size(struct skb_shared_info *shinfo,
u16 increment)
{
if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS))
return;
shinfo->gso_size += increment;
}
static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo,
u16 decrement)
{
if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS))
return;
shinfo->gso_size -= decrement;
}
void __skb_warn_lro_forwarding(const struct sk_buff *skb);
static inline bool skb_warn_if_lro(const struct sk_buff *skb)
{
/* LRO sets gso_size but not gso_type, whereas if GSO is really
* wanted then gso_type will be set. */
const struct skb_shared_info *shinfo = skb_shinfo(skb);
if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 &&
unlikely(shinfo->gso_type == 0)) {
__skb_warn_lro_forwarding(skb);
return true;
}
return false;
}
static inline void skb_forward_csum(struct sk_buff *skb)
{
/* Unfortunately we don't support this one. Any brave souls? */
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
}
/**
* skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE
* @skb: skb to check
*
* fresh skbs have their ip_summed set to CHECKSUM_NONE.
* Instead of forcing ip_summed to CHECKSUM_NONE, we can
* use this helper, to document places where we make this assertion.
*/
static inline void skb_checksum_none_assert(const struct sk_buff *skb)
{
DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE);
}
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
unsigned int transport_len,
__sum16(*skb_chkf)(struct sk_buff *skb));
/**
* skb_head_is_locked - Determine if the skb->head is locked down
* @skb: skb to check
*
* The head on skbs build around a head frag can be removed if they are
* not cloned. This function returns true if the skb head is locked down
* due to either being allocated via kmalloc, or by being a clone with
* multiple references to the head.
*/
static inline bool skb_head_is_locked(const struct sk_buff *skb)
{
return !skb->head_frag || skb_cloned(skb);
}
/* Local Checksum Offload.
* Compute outer checksum based on the assumption that the
* inner checksum will be offloaded later.
* See Documentation/networking/checksum-offloads.rst for
* explanation of how this works.
* Fill in outer checksum adjustment (e.g. with sum of outer
* pseudo-header) before calling.
* Also ensure that inner checksum is in linear data area.
*/
static inline __wsum lco_csum(struct sk_buff *skb)
{
unsigned char *csum_start = skb_checksum_start(skb);
unsigned char *l4_hdr = skb_transport_header(skb);
__wsum partial;
/* Start with complement of inner checksum adjustment */
partial = ~csum_unfold(*(__force __sum16 *)(csum_start +
skb->csum_offset));
/* Add in checksum of our headers (incl. outer checksum
* adjustment filled in by caller) and return result.
*/
return csum_partial(l4_hdr, csum_start - l4_hdr, partial);
}
static inline bool skb_is_redirected(const struct sk_buff *skb)
{
return skb->redirected;
}
static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress)
{
skb->redirected = 1;
#ifdef CONFIG_NET_REDIRECT
skb->from_ingress = from_ingress;
if (skb->from_ingress)
skb_clear_tstamp(skb);
#endif
}
static inline void skb_reset_redirect(struct sk_buff *skb)
{
skb->redirected = 0;
}
static inline void skb_set_redirected_noclear(struct sk_buff *skb,
bool from_ingress)
{
skb->redirected = 1;
#ifdef CONFIG_NET_REDIRECT
skb->from_ingress = from_ingress;
#endif
}
static inline bool skb_csum_is_sctp(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IP_SCTP)
return skb->csum_not_inet;
#else
return 0;
#endif
}
static inline void skb_reset_csum_not_inet(struct sk_buff *skb)
{
skb->ip_summed = CHECKSUM_NONE;
#if IS_ENABLED(CONFIG_IP_SCTP)
skb->csum_not_inet = 0;
#endif
}
static inline void skb_set_kcov_handle(struct sk_buff *skb,
const u64 kcov_handle)
{
#ifdef CONFIG_KCOV
skb->kcov_handle = kcov_handle;
#endif
}
static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
{
#ifdef CONFIG_KCOV
return skb->kcov_handle;
#else
return 0;
#endif
}
static inline void skb_mark_for_recycle(struct sk_buff *skb)
{
#ifdef CONFIG_PAGE_POOL
skb->pp_recycle = 1;
#endif
}
ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
ssize_t maxsize, gfp_t gfp);
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
// SPDX-License-Identifier: GPL-2.0
/*
* fs/ext4/extents_status.h
*
* Written by Yongqiang Yang <xiaoqiangnk@gmail.com>
* Modified by
* Allison Henderson <achender@linux.vnet.ibm.com>
* Zheng Liu <wenqing.lz@taobao.com>
*
*/
#ifndef _EXT4_EXTENTS_STATUS_H
#define _EXT4_EXTENTS_STATUS_H
/*
* Turn on ES_DEBUG__ to get lots of info about extent status operations.
*/
#ifdef ES_DEBUG__
#define es_debug(fmt, ...) printk(fmt, ##__VA_ARGS__)
#else
#define es_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/*
* With ES_AGGRESSIVE_TEST defined, the result of es caching will be
* checked with old map_block's result.
*/
#define ES_AGGRESSIVE_TEST__
/*
* These flags live in the high bits of extent_status.es_pblk
*/
enum {
ES_WRITTEN_B,
ES_UNWRITTEN_B,
ES_DELAYED_B,
ES_HOLE_B,
ES_REFERENCED_B,
ES_FLAGS
};
#define ES_SHIFT (sizeof(ext4_fsblk_t)*8 - ES_FLAGS)
#define ES_MASK (~((ext4_fsblk_t)0) << ES_SHIFT)
/*
* Besides EXTENT_STATUS_REFERENCED, all these extent type masks
* are exclusive, only one type can be set at a time.
*/
#define EXTENT_STATUS_WRITTEN (1 << ES_WRITTEN_B)
#define EXTENT_STATUS_UNWRITTEN (1 << ES_UNWRITTEN_B)
#define EXTENT_STATUS_DELAYED (1 << ES_DELAYED_B)
#define EXTENT_STATUS_HOLE (1 << ES_HOLE_B)
#define EXTENT_STATUS_REFERENCED (1 << ES_REFERENCED_B)
#define ES_TYPE_MASK ((ext4_fsblk_t)(EXTENT_STATUS_WRITTEN | \
EXTENT_STATUS_UNWRITTEN | \
EXTENT_STATUS_DELAYED | \
EXTENT_STATUS_HOLE))
#define ES_TYPE_VALID(type) ((type) && !((type) & ((type) - 1)))
struct ext4_sb_info;
struct ext4_extent;
struct extent_status {
struct rb_node rb_node;
ext4_lblk_t es_lblk; /* first logical block extent covers */
ext4_lblk_t es_len; /* length of extent in block */
ext4_fsblk_t es_pblk; /* first physical block */
};
struct ext4_es_tree {
struct rb_root root;
struct extent_status *cache_es; /* recently accessed extent */
};
struct ext4_es_stats {
unsigned long es_stats_shrunk;
struct percpu_counter es_stats_cache_hits;
struct percpu_counter es_stats_cache_misses;
u64 es_stats_scan_time;
u64 es_stats_max_scan_time;
struct percpu_counter es_stats_all_cnt;
struct percpu_counter es_stats_shk_cnt;
};
/*
* Pending cluster reservations for bigalloc file systems
*
* A cluster with a pending reservation is a logical cluster shared by at
* least one extent in the extents status tree with delayed and unwritten
* status and at least one other written or unwritten extent. The
* reservation is said to be pending because a cluster reservation would
* have to be taken in the event all blocks in the cluster shared with
* written or unwritten extents were deleted while the delayed and
* unwritten blocks remained.
*
* The set of pending cluster reservations is an auxiliary data structure
* used with the extents status tree to implement reserved cluster/block
* accounting for bigalloc file systems. The set is kept in memory and
* records all pending cluster reservations.
*
* Its primary function is to avoid the need to read extents from the
* disk when invalidating pages as a result of a truncate, punch hole, or
* collapse range operation. Page invalidation requires a decrease in the
* reserved cluster count if it results in the removal of all delayed
* and unwritten extents (blocks) from a cluster that is not shared with a
* written or unwritten extent, and no decrease otherwise. Determining
* whether the cluster is shared can be done by searching for a pending
* reservation on it.
*
* Secondarily, it provides a potentially faster method for determining
* whether the reserved cluster count should be increased when a physical
* cluster is deallocated as a result of a truncate, punch hole, or
* collapse range operation. The necessary information is also present
* in the extents status tree, but might be more rapidly accessed in
* the pending reservation set in many cases due to smaller size.
*
* The pending cluster reservation set is implemented as a red-black tree
* with the goal of minimizing per page search time overhead.
*/
struct pending_reservation {
struct rb_node rb_node;
ext4_lblk_t lclu;
};
struct ext4_pending_tree {
struct rb_root root;
};
extern int __init ext4_init_es(void);
extern void ext4_exit_es(void);
extern void ext4_es_init_tree(struct ext4_es_tree *tree);
extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status,
bool delalloc_reserve_used);
extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status);
extern void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len);
extern void ext4_es_find_extent_range(struct inode *inode,
int (*match_fn)(struct extent_status *es),
ext4_lblk_t lblk, ext4_lblk_t end,
struct extent_status *es);
extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t *next_lblk,
struct extent_status *es);
extern bool ext4_es_scan_range(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk, ext4_lblk_t end);
extern bool ext4_es_scan_clu(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk);
static inline unsigned int ext4_es_status(struct extent_status *es)
{
return es->es_pblk >> ES_SHIFT;
}
static inline unsigned int ext4_es_type(struct extent_status *es)
{
return (es->es_pblk >> ES_SHIFT) & ES_TYPE_MASK;
}
static inline int ext4_es_is_written(struct extent_status *es)
{
return (ext4_es_type(es) & EXTENT_STATUS_WRITTEN) != 0;
}
static inline int ext4_es_is_unwritten(struct extent_status *es)
{
return (ext4_es_type(es) & EXTENT_STATUS_UNWRITTEN) != 0;
}
static inline int ext4_es_is_delayed(struct extent_status *es)
{
return (ext4_es_type(es) & EXTENT_STATUS_DELAYED) != 0;
}
static inline int ext4_es_is_hole(struct extent_status *es)
{
return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0;
}
static inline int ext4_es_is_mapped(struct extent_status *es)
{
return (ext4_es_is_written(es) || ext4_es_is_unwritten(es));
}
static inline void ext4_es_set_referenced(struct extent_status *es)
{
es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT;
}
static inline void ext4_es_clear_referenced(struct extent_status *es)
{
es->es_pblk &= ~(((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT);
}
static inline int ext4_es_is_referenced(struct extent_status *es)
{
return (ext4_es_status(es) & EXTENT_STATUS_REFERENCED) != 0;
}
static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
{
return es->es_pblk & ~ES_MASK;
}
static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es)
{
ext4_fsblk_t pblock = ext4_es_pblock(es);
return pblock == ~ES_MASK ? 0 : pblock;
}
static inline void ext4_es_store_pblock(struct extent_status *es,
ext4_fsblk_t pb)
{
ext4_fsblk_t block;
block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK);
es->es_pblk = block;
}
static inline void ext4_es_store_pblock_status(struct extent_status *es,
ext4_fsblk_t pb,
unsigned int status)
{
WARN_ON_ONCE(!ES_TYPE_VALID(status & ES_TYPE_MASK));
es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) |
(pb & ~ES_MASK);
}
extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v);
extern int __init ext4_init_pending(void);
extern void ext4_exit_pending(void);
extern void ext4_init_pending_tree(struct ext4_pending_tree *tree);
extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
extern void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, bool lclu_allocated,
bool end_allocated);
extern void ext4_clear_inode_es(struct inode *inode);
#endif /* _EXT4_EXTENTS_STATUS_H */
// SPDX-License-Identifier: GPL-2.0
/*
* fs/ext4/extents_status.c
*
* Written by Yongqiang Yang <xiaoqiangnk@gmail.com>
* Modified by
* Allison Henderson <achender@linux.vnet.ibm.com>
* Hugh Dickins <hughd@google.com>
* Zheng Liu <wenqing.lz@taobao.com>
*
* Ext4 extents status tree core functions.
*/
#include <linux/list_sort.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include "ext4.h"
#include <trace/events/ext4.h>
/*
* According to previous discussion in Ext4 Developer Workshop, we
* will introduce a new structure called io tree to track all extent
* status in order to solve some problems that we have met
* (e.g. Reservation space warning), and provide extent-level locking.
* Delay extent tree is the first step to achieve this goal. It is
* original built by Yongqiang Yang. At that time it is called delay
* extent tree, whose goal is only track delayed extents in memory to
* simplify the implementation of fiemap and bigalloc, and introduce
* lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called
* delay extent tree at the first commit. But for better understand
* what it does, it has been rename to extent status tree.
*
* Step1:
* Currently the first step has been done. All delayed extents are
* tracked in the tree. It maintains the delayed extent when a delayed
* allocation is issued, and the delayed extent is written out or
* invalidated. Therefore the implementation of fiemap and bigalloc
* are simplified, and SEEK_DATA/SEEK_HOLE are introduced.
*
* The following comment describes the implemenmtation of extent
* status tree and future works.
*
* Step2:
* In this step all extent status are tracked by extent status tree.
* Thus, we can first try to lookup a block mapping in this tree before
* finding it in extent tree. Hence, single extent cache can be removed
* because extent status tree can do a better job. Extents in status
* tree are loaded on-demand. Therefore, the extent status tree may not
* contain all of the extents in a file. Meanwhile we define a shrinker
* to reclaim memory from extent status tree because fragmented extent
* tree will make status tree cost too much memory. written/unwritten/-
* hole extents in the tree will be reclaimed by this shrinker when we
* are under high memory pressure. Delayed extents will not be
* reclimed because fiemap, bigalloc, and seek_data/hole need it.
*/
/*
* Extent status tree implementation for ext4.
*
*
* ==========================================================================
* Extent status tree tracks all extent status.
*
* 1. Why we need to implement extent status tree?
*
* Without extent status tree, ext4 identifies a delayed extent by looking
* up page cache, this has several deficiencies - complicated, buggy,
* and inefficient code.
*
* FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a
* block or a range of blocks are belonged to a delayed extent.
*
* Let us have a look at how they do without extent status tree.
* -- FIEMAP
* FIEMAP looks up page cache to identify delayed allocations from holes.
*
* -- SEEK_HOLE/DATA
* SEEK_HOLE/DATA has the same problem as FIEMAP.
*
* -- bigalloc
* bigalloc looks up page cache to figure out if a block is
* already under delayed allocation or not to determine whether
* quota reserving is needed for the cluster.
*
* -- writeout
* Writeout looks up whole page cache to see if a buffer is
* mapped, If there are not very many delayed buffers, then it is
* time consuming.
*
* With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA,
* bigalloc and writeout can figure out if a block or a range of
* blocks is under delayed allocation(belonged to a delayed extent) or
* not by searching the extent tree.
*
*
* ==========================================================================
* 2. Ext4 extent status tree impelmentation
*
* -- extent
* A extent is a range of blocks which are contiguous logically and
* physically. Unlike extent in extent tree, this extent in ext4 is
* a in-memory struct, there is no corresponding on-disk data. There
* is no limit on length of extent, so an extent can contain as many
* blocks as they are contiguous logically and physically.
*
* -- extent status tree
* Every inode has an extent status tree and all allocation blocks
* are added to the tree with different status. The extent in the
* tree are ordered by logical block no.
*
* -- operations on a extent status tree
* There are three important operations on a delayed extent tree: find
* next extent, adding a extent(a range of blocks) and removing a extent.
*
* -- race on a extent status tree
* Extent status tree is protected by inode->i_es_lock.
*
* -- memory consumption
* Fragmented extent tree will make extent status tree cost too much
* memory. Hence, we will reclaim written/unwritten/hole extents from
* the tree under a heavy memory pressure.
*
*
* ==========================================================================
* 3. Performance analysis
*
* -- overhead
* 1. There is a cache extent for write access, so if writes are
* not very random, adding space operaions are in O(1) time.
*
* -- gain
* 2. Code is much simpler, more readable, more maintainable and
* more efficient.
*
*
* ==========================================================================
* 4. TODO list
*
* -- Refactor delayed space reservation
*
* -- Extent-level locking
*/
static struct kmem_cache *ext4_es_cachep;
static struct kmem_cache *ext4_pending_cachep;
static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
struct extent_status *prealloc);
static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t end, int *reserved,
struct extent_status *prealloc);
static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan);
static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
struct ext4_inode_info *locked_ei);
static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len,
struct pending_reservation **prealloc);
int __init ext4_init_es(void)
{
ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT);
if (ext4_es_cachep == NULL)
return -ENOMEM;
return 0;
}
void ext4_exit_es(void)
{
kmem_cache_destroy(ext4_es_cachep);
}
void ext4_es_init_tree(struct ext4_es_tree *tree)
{
tree->root = RB_ROOT;
tree->cache_es = NULL;
}
#ifdef ES_DEBUG__
static void ext4_es_print_tree(struct inode *inode)
{
struct ext4_es_tree *tree;
struct rb_node *node;
printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino);
tree = &EXT4_I(inode)->i_es_tree;
node = rb_first(&tree->root);
while (node) {
struct extent_status *es;
es = rb_entry(node, struct extent_status, rb_node);
printk(KERN_DEBUG " [%u/%u) %llu %x",
es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
node = rb_next(node);
}
printk(KERN_DEBUG "\n");
}
#else
#define ext4_es_print_tree(inode)
#endif
static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
{
BUG_ON(es->es_lblk + es->es_len < es->es_lblk);
return es->es_lblk + es->es_len - 1;
}
/*
* search through the tree for an delayed extent with a given offset. If
* it can't be found, try to find next extent.
*/
static struct extent_status *__es_tree_search(struct rb_root *root,
ext4_lblk_t lblk)
{
struct rb_node *node = root->rb_node;
struct extent_status *es = NULL;
while (node) {
es = rb_entry(node, struct extent_status, rb_node);
if (lblk < es->es_lblk)
node = node->rb_left;
else if (lblk > ext4_es_end(es))
node = node->rb_right;
else
return es;
}
if (es && lblk < es->es_lblk)
return es;
if (es && lblk > ext4_es_end(es)) {
node = rb_next(&es->rb_node);
return node ? rb_entry(node, struct extent_status, rb_node) :
NULL;
}
return NULL;
}
/*
* ext4_es_find_extent_range - find extent with specified status within block
* range or next extent following block range in
* extents status tree
*
* @inode - file containing the range
* @matching_fn - pointer to function that matches extents with desired status
* @lblk - logical block defining start of range
* @end - logical block defining end of range
* @es - extent found, if any
*
* Find the first extent within the block range specified by @lblk and @end
* in the extents status tree that satisfies @matching_fn. If a match
* is found, it's returned in @es. If not, and a matching extent is found
* beyond the block range, it's returned in @es. If no match is found, an
* extent is returned in @es whose es_lblk, es_len, and es_pblk components
* are 0.
*/
static void __es_find_extent_range(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk, ext4_lblk_t end,
struct extent_status *es)
{
struct ext4_es_tree *tree = NULL;
struct extent_status *es1 = NULL;
struct rb_node *node;
WARN_ON(es == NULL);
WARN_ON(end < lblk);
tree = &EXT4_I(inode)->i_es_tree;
/* see if the extent has been cached */
es->es_lblk = es->es_len = es->es_pblk = 0;
es1 = READ_ONCE(tree->cache_es);
if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
es_debug("%u cached by [%u/%u) %llu %x\n",
lblk, es1->es_lblk, es1->es_len,
ext4_es_pblock(es1), ext4_es_status(es1));
goto out;
}
es1 = __es_tree_search(&tree->root, lblk);
out:
if (es1 && !matching_fn(es1)) {
while ((node = rb_next(&es1->rb_node)) != NULL) {
es1 = rb_entry(node, struct extent_status, rb_node);
if (es1->es_lblk > end) {
es1 = NULL;
break;
}
if (matching_fn(es1))
break;
}
}
if (es1 && matching_fn(es1)) {
WRITE_ONCE(tree->cache_es, es1);
es->es_lblk = es1->es_lblk;
es->es_len = es1->es_len;
es->es_pblk = es1->es_pblk;
}
}
/*
* Locking for __es_find_extent_range() for external use
*/
void ext4_es_find_extent_range(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk, ext4_lblk_t end,
struct extent_status *es)
{
es->es_lblk = es->es_len = es->es_pblk = 0;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
trace_ext4_es_find_extent_range_enter(inode, lblk);
read_lock(&EXT4_I(inode)->i_es_lock);
__es_find_extent_range(inode, matching_fn, lblk, end, es);
read_unlock(&EXT4_I(inode)->i_es_lock);
trace_ext4_es_find_extent_range_exit(inode, es);
}
/*
* __es_scan_range - search block range for block with specified status
* in extents status tree
*
* @inode - file containing the range
* @matching_fn - pointer to function that matches extents with desired status
* @lblk - logical block defining start of range
* @end - logical block defining end of range
*
* Returns true if at least one block in the specified block range satisfies
* the criterion specified by @matching_fn, and false if not. If at least
* one extent has the specified status, then there is at least one block
* in the cluster with that status. Should only be called by code that has
* taken i_es_lock.
*/
static bool __es_scan_range(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t start, ext4_lblk_t end)
{
struct extent_status es;
__es_find_extent_range(inode, matching_fn, start, end, &es);
if (es.es_len == 0)
return false; /* no matching extent in the tree */
else if (es.es_lblk <= start &&
start < es.es_lblk + es.es_len)
return true;
else if (start <= es.es_lblk && es.es_lblk <= end)
return true;
else
return false;
}
/*
* Locking for __es_scan_range() for external use
*/
bool ext4_es_scan_range(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk, ext4_lblk_t end)
{
bool ret;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return false;
read_lock(&EXT4_I(inode)->i_es_lock);
ret = __es_scan_range(inode, matching_fn, lblk, end);
read_unlock(&EXT4_I(inode)->i_es_lock);
return ret;
}
/*
* __es_scan_clu - search cluster for block with specified status in
* extents status tree
*
* @inode - file containing the cluster
* @matching_fn - pointer to function that matches extents with desired status
* @lblk - logical block in cluster to be searched
*
* Returns true if at least one extent in the cluster containing @lblk
* satisfies the criterion specified by @matching_fn, and false if not. If at
* least one extent has the specified status, then there is at least one block
* in the cluster with that status. Should only be called by code that has
* taken i_es_lock.
*/
static bool __es_scan_clu(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t lblk_start, lblk_end;
lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
return __es_scan_range(inode, matching_fn, lblk_start, lblk_end);
}
/*
* Locking for __es_scan_clu() for external use
*/
bool ext4_es_scan_clu(struct inode *inode,
int (*matching_fn)(struct extent_status *es),
ext4_lblk_t lblk)
{
bool ret;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return false;
read_lock(&EXT4_I(inode)->i_es_lock);
ret = __es_scan_clu(inode, matching_fn, lblk);
read_unlock(&EXT4_I(inode)->i_es_lock);
return ret;
}
static void ext4_es_list_add(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (!list_empty(&ei->i_es_list))
return;
spin_lock(&sbi->s_es_lock);
if (list_empty(&ei->i_es_list)) {
list_add_tail(&ei->i_es_list, &sbi->s_es_list);
sbi->s_es_nr_inode++;
}
spin_unlock(&sbi->s_es_lock);
}
static void ext4_es_list_del(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
spin_lock(&sbi->s_es_lock);
if (!list_empty(&ei->i_es_list)) {
list_del_init(&ei->i_es_list);
sbi->s_es_nr_inode--;
WARN_ON_ONCE(sbi->s_es_nr_inode < 0);
}
spin_unlock(&sbi->s_es_lock);
}
static inline struct pending_reservation *__alloc_pending(bool nofail)
{
if (!nofail)
return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC);
return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL);
}
static inline void __free_pending(struct pending_reservation *pr)
{
kmem_cache_free(ext4_pending_cachep, pr);
}
/*
* Returns true if we cannot fail to allocate memory for this extent_status
* entry and cannot reclaim it until its status changes.
*/
static inline bool ext4_es_must_keep(struct extent_status *es)
{
/* fiemap, bigalloc, and seek_data/hole need to use it. */
if (ext4_es_is_delayed(es))
return true;
return false;
}
static inline struct extent_status *__es_alloc_extent(bool nofail)
{
if (!nofail)
return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL);
}
static void ext4_es_init_extent(struct inode *inode, struct extent_status *es,
ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk)
{
es->es_lblk = lblk;
es->es_len = len;
es->es_pblk = pblk;
/* We never try to reclaim a must kept extent, so we don't count it. */
if (!ext4_es_must_keep(es)) {
if (!EXT4_I(inode)->i_es_shk_nr++)
ext4_es_list_add(inode);
percpu_counter_inc(&EXT4_SB(inode->i_sb)->
s_es_stats.es_stats_shk_cnt);
}
EXT4_I(inode)->i_es_all_nr++;
percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
}
static inline void __es_free_extent(struct extent_status *es)
{
kmem_cache_free(ext4_es_cachep, es);
}
static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
{
EXT4_I(inode)->i_es_all_nr--;
percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
/* Decrease the shrink counter when we can reclaim the extent. */
if (!ext4_es_must_keep(es)) {
BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0);
if (!--EXT4_I(inode)->i_es_shk_nr)
ext4_es_list_del(inode);
percpu_counter_dec(&EXT4_SB(inode->i_sb)->
s_es_stats.es_stats_shk_cnt);
}
__es_free_extent(es);
}
/*
* Check whether or not two extents can be merged
* Condition:
* - logical block number is contiguous
* - physical block number is contiguous
* - status is equal
*/
static int ext4_es_can_be_merged(struct extent_status *es1,
struct extent_status *es2)
{
if (ext4_es_type(es1) != ext4_es_type(es2))
return 0;
if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
pr_warn("ES assertion failed when merging extents. "
"The sum of lengths of es1 (%d) and es2 (%d) "
"is bigger than allowed file size (%d)\n",
es1->es_len, es2->es_len, EXT_MAX_BLOCKS);
WARN_ON(1);
return 0;
}
if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
return 0;
if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) &&
(ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2)))
return 1;
if (ext4_es_is_hole(es1))
return 1;
/* we need to check delayed extent */
if (ext4_es_is_delayed(es1))
return 1;
return 0;
}
static struct extent_status *
ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
node = rb_prev(&es->rb_node);
if (!node)
return es;
es1 = rb_entry(node, struct extent_status, rb_node);
if (ext4_es_can_be_merged(es1, es)) {
es1->es_len += es->es_len;
if (ext4_es_is_referenced(es))
ext4_es_set_referenced(es1);
rb_erase(&es->rb_node, &tree->root);
ext4_es_free_extent(inode, es);
es = es1;
}
return es;
}
static struct extent_status *
ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
node = rb_next(&es->rb_node);
if (!node)
return es;
es1 = rb_entry(node, struct extent_status, rb_node);
if (ext4_es_can_be_merged(es, es1)) {
es->es_len += es1->es_len;
if (ext4_es_is_referenced(es1))
ext4_es_set_referenced(es);
rb_erase(node, &tree->root);
ext4_es_free_extent(inode, es1);
}
return es;
}
#ifdef ES_AGGRESSIVE_TEST
#include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */
static void ext4_es_insert_extent_ext_check(struct inode *inode,
struct extent_status *es)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ex;
ext4_lblk_t ee_block;
ext4_fsblk_t ee_start;
unsigned short ee_len;
int depth, ee_status, es_status;
path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path))
return;
depth = ext_depth(inode);
ex = path[depth].p_ext;
if (ex) {
ee_block = le32_to_cpu(ex->ee_block);
ee_start = ext4_ext_pblock(ex);
ee_len = ext4_ext_get_actual_len(ex);
ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
es_status = ext4_es_is_unwritten(es) ? 1 : 0;
/*
* Make sure ex and es are not overlap when we try to insert
* a delayed/hole extent.
*/
if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
if (in_range(es->es_lblk, ee_block, ee_len)) {
pr_warn("ES insert assertion failed for "
"inode: %lu we can find an extent "
"at block [%d/%d/%llu/%c], but we "
"want to add a delayed/hole extent "
"[%d/%d/%llu/%x]\n",
inode->i_ino, ee_block, ee_len,
ee_start, ee_status ? 'u' : 'w',
es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
}
goto out;
}
/*
* We don't check ee_block == es->es_lblk, etc. because es
* might be a part of whole extent, vice versa.
*/
if (es->es_lblk < ee_block ||
ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
ext4_es_pblock(es), es_status ? 'u' : 'w');
goto out;
}
if (ee_status ^ es_status) {
pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
ext4_es_pblock(es), es_status ? 'u' : 'w');
}
} else {
/*
* We can't find an extent on disk. So we need to make sure
* that we don't want to add an written/unwritten extent.
*/
if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
pr_warn("ES insert assertion failed for inode: %lu "
"can't find an extent at block %d but we want "
"to add a written/unwritten extent "
"[%d/%d/%llu/%x]\n", inode->i_ino,
es->es_lblk, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
}
}
out:
ext4_free_ext_path(path);
}
static void ext4_es_insert_extent_ind_check(struct inode *inode,
struct extent_status *es)
{
struct ext4_map_blocks map;
int retval;
/*
* Here we call ext4_ind_map_blocks to lookup a block mapping because
* 'Indirect' structure is defined in indirect.c. So we couldn't
* access direct/indirect tree from outside. It is too dirty to define
* this function in indirect.c file.
*/
map.m_lblk = es->es_lblk;
map.m_len = es->es_len;
retval = ext4_ind_map_blocks(NULL, inode, &map, 0);
if (retval > 0) {
if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) {
/*
* We want to add a delayed/hole extent but this
* block has been allocated.
*/
pr_warn("ES insert assertion failed for inode: %lu "
"We can find blocks but we want to add a "
"delayed/hole extent [%d/%d/%llu/%x]\n",
inode->i_ino, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
return;
} else if (ext4_es_is_written(es)) {
if (retval != es->es_len) {
pr_warn("ES insert assertion failed for "
"inode: %lu retval %d != es_len %d\n",
inode->i_ino, retval, es->es_len);
return;
}
if (map.m_pblk != ext4_es_pblock(es)) {
pr_warn("ES insert assertion failed for "
"inode: %lu m_pblk %llu != "
"es_pblk %llu\n",
inode->i_ino, map.m_pblk,
ext4_es_pblock(es));
return;
}
} else {
/*
* We don't need to check unwritten extent because
* indirect-based file doesn't have it.
*/
BUG();
}
} else if (retval == 0) {
if (ext4_es_is_written(es)) {
pr_warn("ES insert assertion failed for inode: %lu "
"We can't find the block but we want to add "
"a written extent [%d/%d/%llu/%x]\n",
inode->i_ino, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
return;
}
}
}
static inline void ext4_es_insert_extent_check(struct inode *inode,
struct extent_status *es)
{
/*
* We don't need to worry about the race condition because
* caller takes i_data_sem locking.
*/
BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ext4_es_insert_extent_ext_check(inode, es);
else
ext4_es_insert_extent_ind_check(inode, es);
}
#else
static inline void ext4_es_insert_extent_check(struct inode *inode,
struct extent_status *es)
{
}
#endif
static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
struct extent_status *prealloc)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node **p = &tree->root.rb_node;
struct rb_node *parent = NULL;
struct extent_status *es;
while (*p) {
parent = *p;
es = rb_entry(parent, struct extent_status, rb_node);
if (newes->es_lblk < es->es_lblk) {
if (ext4_es_can_be_merged(newes, es)) {
/*
* Here we can modify es_lblk directly
* because it isn't overlapped.
*/
es->es_lblk = newes->es_lblk;
es->es_len += newes->es_len;
if (ext4_es_is_written(es) ||
ext4_es_is_unwritten(es))
ext4_es_store_pblock(es,
newes->es_pblk);
es = ext4_es_try_to_merge_left(inode, es);
goto out;
}
p = &(*p)->rb_left;
} else if (newes->es_lblk > ext4_es_end(es)) {
if (ext4_es_can_be_merged(es, newes)) {
es->es_len += newes->es_len;
es = ext4_es_try_to_merge_right(inode, es);
goto out;
}
p = &(*p)->rb_right;
} else {
BUG();
return -EINVAL;
}
}
if (prealloc)
es = prealloc;
else
es = __es_alloc_extent(false);
if (!es)
return -ENOMEM;
ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len,
newes->es_pblk);
rb_link_node(&es->rb_node, parent, p);
rb_insert_color(&es->rb_node, &tree->root);
out:
tree->cache_es = es;
return 0;
}
/*
* ext4_es_insert_extent() adds information to an inode's extent
* status tree.
*/
void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status, bool delalloc_reserve_used)
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
int err1 = 0, err2 = 0, err3 = 0;
int resv_used = 0, pending = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct extent_status *es1 = NULL;
struct extent_status *es2 = NULL;
struct pending_reservation *pr = NULL;
bool revise_pending = false;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
es_debug("add [%u/%u) %llu %x %d to extent status tree of inode %lu\n",
lblk, len, pblk, status, delalloc_reserve_used, inode->i_ino);
if (!len)
return;
BUG_ON(end < lblk);
WARN_ON_ONCE(status & EXTENT_STATUS_DELAYED);
newes.es_lblk = lblk;
newes.es_len = len;
ext4_es_store_pblock_status(&newes, pblk, status);
trace_ext4_es_insert_extent(inode, &newes);
ext4_es_insert_extent_check(inode, &newes);
revise_pending = sbi->s_cluster_ratio > 1 &&
test_opt(inode->i_sb, DELALLOC) &&
(status & (EXTENT_STATUS_WRITTEN |
EXTENT_STATUS_UNWRITTEN));
retry:
if (err1 && !es1)
es1 = __es_alloc_extent(true);
if ((err1 || err2) && !es2)
es2 = __es_alloc_extent(true);
if ((err1 || err2 || err3 < 0) && revise_pending && !pr)
pr = __alloc_pending(true);
write_lock(&EXT4_I(inode)->i_es_lock);
err1 = __es_remove_extent(inode, lblk, end, &resv_used, es1);
if (err1 != 0)
goto error;
/* Free preallocated extent if it didn't get used. */
if (es1) {
if (!es1->es_len)
__es_free_extent(es1);
es1 = NULL;
}
err2 = __es_insert_extent(inode, &newes, es2);
if (err2 == -ENOMEM && !ext4_es_must_keep(&newes))
err2 = 0;
if (err2 != 0)
goto error;
/* Free preallocated extent if it didn't get used. */
if (es2) {
if (!es2->es_len)
__es_free_extent(es2);
es2 = NULL;
}
if (revise_pending) {
err3 = __revise_pending(inode, lblk, len, &pr);
if (err3 < 0)
goto error;
if (pr) {
__free_pending(pr);
pr = NULL;
}
pending = err3;
}
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
/*
* Reduce the reserved cluster count to reflect successful deferred
* allocation of delayed allocated clusters or direct allocation of
* clusters discovered to be delayed allocated. Once allocated, a
* cluster is not included in the reserved count.
*
* When direct allocating (from fallocate, filemap, DIO, or clusters
* allocated when delalloc has been disabled by ext4_nonda_switch())
* an extent either 1) contains delayed blocks but start with
* non-delayed allocated blocks (e.g. hole) or 2) contains non-delayed
* allocated blocks which belong to delayed allocated clusters when
* bigalloc feature is enabled, quota has already been claimed by
* ext4_mb_new_blocks(), so release the quota reservations made for
* any previously delayed allocated clusters instead of claim them
* again.
*/
resv_used += pending;
if (resv_used)
ext4_da_update_reserve_space(inode, resv_used,
delalloc_reserve_used);
if (err1 || err2 || err3 < 0)
goto retry;
ext4_es_print_tree(inode);
return;
}
/*
* ext4_es_cache_extent() inserts information into the extent status
* tree if and only if there isn't information about the range in
* question already.
*/
void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status)
{
struct extent_status *es;
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
newes.es_lblk = lblk;
newes.es_len = len;
ext4_es_store_pblock_status(&newes, pblk, status);
trace_ext4_es_cache_extent(inode, &newes);
if (!len)
return;
BUG_ON(end < lblk);
write_lock(&EXT4_I(inode)->i_es_lock);
es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk);
if (!es || es->es_lblk > end)
__es_insert_extent(inode, &newes, NULL);
write_unlock(&EXT4_I(inode)->i_es_lock);
}
/*
* ext4_es_lookup_extent() looks up an extent in extent status tree.
*
* ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
*
* Return: 1 on found, 0 on not
*/
int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t *next_lblk,
struct extent_status *es)
{
struct ext4_es_tree *tree;
struct ext4_es_stats *stats;
struct extent_status *es1 = NULL;
struct rb_node *node;
int found = 0;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return 0;
trace_ext4_es_lookup_extent_enter(inode, lblk);
es_debug("lookup extent in block %u\n", lblk);
tree = &EXT4_I(inode)->i_es_tree;
read_lock(&EXT4_I(inode)->i_es_lock);
/* find extent in cache firstly */
es->es_lblk = es->es_len = es->es_pblk = 0;
es1 = READ_ONCE(tree->cache_es);
if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
es_debug("%u cached by [%u/%u)\n",
lblk, es1->es_lblk, es1->es_len);
found = 1;
goto out;
}
node = tree->root.rb_node;
while (node) {
es1 = rb_entry(node, struct extent_status, rb_node);
if (lblk < es1->es_lblk)
node = node->rb_left;
else if (lblk > ext4_es_end(es1))
node = node->rb_right;
else {
found = 1;
break;
}
}
out:
stats = &EXT4_SB(inode->i_sb)->s_es_stats;
if (found) {
BUG_ON(!es1);
es->es_lblk = es1->es_lblk;
es->es_len = es1->es_len;
es->es_pblk = es1->es_pblk;
if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1);
percpu_counter_inc(&stats->es_stats_cache_hits);
if (next_lblk) {
node = rb_next(&es1->rb_node);
if (node) {
es1 = rb_entry(node, struct extent_status,
rb_node);
*next_lblk = es1->es_lblk;
} else
*next_lblk = 0;
}
} else {
percpu_counter_inc(&stats->es_stats_cache_misses);
}
read_unlock(&EXT4_I(inode)->i_es_lock);
trace_ext4_es_lookup_extent_exit(inode, es, found);
return found;
}
struct rsvd_count {
int ndelayed;
bool first_do_lblk_found;
ext4_lblk_t first_do_lblk;
ext4_lblk_t last_do_lblk;
struct extent_status *left_es;
bool partial;
ext4_lblk_t lclu;
};
/*
* init_rsvd - initialize reserved count data before removing block range
* in file from extent status tree
*
* @inode - file containing range
* @lblk - first block in range
* @es - pointer to first extent in range
* @rc - pointer to reserved count data
*
* Assumes es is not NULL
*/
static void init_rsvd(struct inode *inode, ext4_lblk_t lblk,
struct extent_status *es, struct rsvd_count *rc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct rb_node *node;
rc->ndelayed = 0;
/*
* for bigalloc, note the first delayed block in the range has not
* been found, record the extent containing the block to the left of
* the region to be removed, if any, and note that there's no partial
* cluster to track
*/
if (sbi->s_cluster_ratio > 1) {
rc->first_do_lblk_found = false;
if (lblk > es->es_lblk) {
rc->left_es = es;
} else {
node = rb_prev(&es->rb_node);
rc->left_es = node ? rb_entry(node,
struct extent_status,
rb_node) : NULL;
}
rc->partial = false;
}
}
/*
* count_rsvd - count the clusters containing delayed blocks in a range
* within an extent and add to the running tally in rsvd_count
*
* @inode - file containing extent
* @lblk - first block in range
* @len - length of range in blocks
* @es - pointer to extent containing clusters to be counted
* @rc - pointer to reserved count data
*
* Tracks partial clusters found at the beginning and end of extents so
* they aren't overcounted when they span adjacent extents
*/
static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
struct extent_status *es, struct rsvd_count *rc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t i, end, nclu;
if (!ext4_es_is_delayed(es))
return;
WARN_ON(len <= 0);
if (sbi->s_cluster_ratio == 1) {
rc->ndelayed += (int) len;
return;
}
/* bigalloc */
i = (lblk < es->es_lblk) ? es->es_lblk : lblk;
end = lblk + (ext4_lblk_t) len - 1;
end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end;
/* record the first block of the first delayed extent seen */
if (!rc->first_do_lblk_found) {
rc->first_do_lblk = i;
rc->first_do_lblk_found = true;
}
/* update the last lblk in the region seen so far */
rc->last_do_lblk = end;
/*
* if we're tracking a partial cluster and the current extent
* doesn't start with it, count it and stop tracking
*/
if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) {
rc->ndelayed++;
rc->partial = false;
}
/*
* if the first cluster doesn't start on a cluster boundary but
* ends on one, count it
*/
if (EXT4_LBLK_COFF(sbi, i) != 0) {
if (end >= EXT4_LBLK_CFILL(sbi, i)) {
rc->ndelayed++;
rc->partial = false;
i = EXT4_LBLK_CFILL(sbi, i) + 1;
}
}
/*
* if the current cluster starts on a cluster boundary, count the
* number of whole delayed clusters in the extent
*/
if ((i + sbi->s_cluster_ratio - 1) <= end) {
nclu = (end - i + 1) >> sbi->s_cluster_bits;
rc->ndelayed += nclu;
i += nclu << sbi->s_cluster_bits;
}
/*
* start tracking a partial cluster if there's a partial at the end
* of the current extent and we're not already tracking one
*/
if (!rc->partial && i <= end) {
rc->partial = true;
rc->lclu = EXT4_B2C(sbi, i);
}
}
/*
* __pr_tree_search - search for a pending cluster reservation
*
* @root - root of pending reservation tree
* @lclu - logical cluster to search for
*
* Returns the pending reservation for the cluster identified by @lclu
* if found. If not, returns a reservation for the next cluster if any,
* and if not, returns NULL.
*/
static struct pending_reservation *__pr_tree_search(struct rb_root *root,
ext4_lblk_t lclu)
{
struct rb_node *node = root->rb_node;
struct pending_reservation *pr = NULL;
while (node) {
pr = rb_entry(node, struct pending_reservation, rb_node);
if (lclu < pr->lclu)
node = node->rb_left;
else if (lclu > pr->lclu)
node = node->rb_right;
else
return pr;
}
if (pr && lclu < pr->lclu)
return pr;
if (pr && lclu > pr->lclu) {
node = rb_next(&pr->rb_node);
return node ? rb_entry(node, struct pending_reservation,
rb_node) : NULL;
}
return NULL;
}
/*
* get_rsvd - calculates and returns the number of cluster reservations to be
* released when removing a block range from the extent status tree
* and releases any pending reservations within the range
*
* @inode - file containing block range
* @end - last block in range
* @right_es - pointer to extent containing next block beyond end or NULL
* @rc - pointer to reserved count data
*
* The number of reservations to be released is equal to the number of
* clusters containing delayed blocks within the range, minus the number of
* clusters still containing delayed blocks at the ends of the range, and
* minus the number of pending reservations within the range.
*/
static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
struct extent_status *right_es,
struct rsvd_count *rc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct pending_reservation *pr;
struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree;
struct rb_node *node;
ext4_lblk_t first_lclu, last_lclu;
bool left_delayed, right_delayed, count_pending;
struct extent_status *es;
if (sbi->s_cluster_ratio > 1) {
/* count any remaining partial cluster */
if (rc->partial)
rc->ndelayed++;
if (rc->ndelayed == 0)
return 0;
first_lclu = EXT4_B2C(sbi, rc->first_do_lblk);
last_lclu = EXT4_B2C(sbi, rc->last_do_lblk);
/*
* decrease the delayed count by the number of clusters at the
* ends of the range that still contain delayed blocks -
* these clusters still need to be reserved
*/
left_delayed = right_delayed = false;
es = rc->left_es;
while (es && ext4_es_end(es) >=
EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) {
if (ext4_es_is_delayed(es)) {
rc->ndelayed--;
left_delayed = true;
break;
}
node = rb_prev(&es->rb_node);
if (!node)
break;
es = rb_entry(node, struct extent_status, rb_node);
}
if (right_es && (!left_delayed || first_lclu != last_lclu)) {
if (end < ext4_es_end(right_es)) {
es = right_es;
} else {
node = rb_next(&right_es->rb_node);
es = node ? rb_entry(node, struct extent_status,
rb_node) : NULL;
}
while (es && es->es_lblk <=
EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) {
if (ext4_es_is_delayed(es)) {
rc->ndelayed--;
right_delayed = true;
break;
}
node = rb_next(&es->rb_node);
if (!node)
break;
es = rb_entry(node, struct extent_status,
rb_node);
}
}
/*
* Determine the block range that should be searched for
* pending reservations, if any. Clusters on the ends of the
* original removed range containing delayed blocks are
* excluded. They've already been accounted for and it's not
* possible to determine if an associated pending reservation
* should be released with the information available in the
* extents status tree.
*/
if (first_lclu == last_lclu) {
if (left_delayed | right_delayed)
count_pending = false;
else
count_pending = true;
} else {
if (left_delayed)
first_lclu++;
if (right_delayed)
last_lclu--;
if (first_lclu <= last_lclu)
count_pending = true;
else
count_pending = false;
}
/*
* a pending reservation found between first_lclu and last_lclu
* represents an allocated cluster that contained at least one
* delayed block, so the delayed total must be reduced by one
* for each pending reservation found and released
*/
if (count_pending) {
pr = __pr_tree_search(&tree->root, first_lclu);
while (pr && pr->lclu <= last_lclu) {
rc->ndelayed--;
node = rb_next(&pr->rb_node);
rb_erase(&pr->rb_node, &tree->root);
__free_pending(pr);
if (!node)
break;
pr = rb_entry(node, struct pending_reservation,
rb_node);
}
}
}
return rc->ndelayed;
}
/*
* __es_remove_extent - removes block range from extent status tree
*
* @inode - file containing range
* @lblk - first block in range
* @end - last block in range
* @reserved - number of cluster reservations released
* @prealloc - pre-allocated es to avoid memory allocation failures
*
* If @reserved is not NULL and delayed allocation is enabled, counts
* block/cluster reservations freed by removing range and if bigalloc
* enabled cancels pending reservations as needed. Returns 0 on success,
* error code on failure.
*/
static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t end, int *reserved,
struct extent_status *prealloc)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node *node;
struct extent_status *es;
struct extent_status orig_es;
ext4_lblk_t len1, len2;
ext4_fsblk_t block;
int err = 0;
bool count_reserved = true;
struct rsvd_count rc;
if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC))
count_reserved = false;
es = __es_tree_search(&tree->root, lblk);
if (!es)
goto out;
if (es->es_lblk > end)
goto out;
/* Simply invalidate cache_es. */
tree->cache_es = NULL;
if (count_reserved)
init_rsvd(inode, lblk, es, &rc);
orig_es.es_lblk = es->es_lblk;
orig_es.es_len = es->es_len;
orig_es.es_pblk = es->es_pblk;
len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0;
len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0;
if (len1 > 0)
es->es_len = len1;
if (len2 > 0) {
if (len1 > 0) {
struct extent_status newes;
newes.es_lblk = end + 1;
newes.es_len = len2;
block = 0x7FDEADBEEFULL;
if (ext4_es_is_written(&orig_es) ||
ext4_es_is_unwritten(&orig_es))
block = ext4_es_pblock(&orig_es) +
orig_es.es_len - len2;
ext4_es_store_pblock_status(&newes, block,
ext4_es_status(&orig_es));
err = __es_insert_extent(inode, &newes, prealloc);
if (err) {
if (!ext4_es_must_keep(&newes))
return 0;
es->es_lblk = orig_es.es_lblk;
es->es_len = orig_es.es_len;
goto out;
}
} else {
es->es_lblk = end + 1;
es->es_len = len2;
if (ext4_es_is_written(es) ||
ext4_es_is_unwritten(es)) {
block = orig_es.es_pblk + orig_es.es_len - len2;
ext4_es_store_pblock(es, block);
}
}
if (count_reserved)
count_rsvd(inode, orig_es.es_lblk + len1,
orig_es.es_len - len1 - len2, &orig_es, &rc);
goto out_get_reserved;
}
if (len1 > 0) {
if (count_reserved)
count_rsvd(inode, lblk, orig_es.es_len - len1,
&orig_es, &rc);
node = rb_next(&es->rb_node);
if (node)
es = rb_entry(node, struct extent_status, rb_node);
else
es = NULL;
}
while (es && ext4_es_end(es) <= end) {
if (count_reserved)
count_rsvd(inode, es->es_lblk, es->es_len, es, &rc);
node = rb_next(&es->rb_node);
rb_erase(&es->rb_node, &tree->root);
ext4_es_free_extent(inode, es);
if (!node) {
es = NULL;
break;
}
es = rb_entry(node, struct extent_status, rb_node);
}
if (es && es->es_lblk < end + 1) {
ext4_lblk_t orig_len = es->es_len;
len1 = ext4_es_end(es) - end;
if (count_reserved)
count_rsvd(inode, es->es_lblk, orig_len - len1,
es, &rc);
es->es_lblk = end + 1;
es->es_len = len1;
if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) {
block = es->es_pblk + orig_len - len1;
ext4_es_store_pblock(es, block);
}
}
out_get_reserved:
if (count_reserved)
*reserved = get_rsvd(inode, end, es, &rc);
out:
return err;
}
/*
* ext4_es_remove_extent - removes block range from extent status tree
*
* @inode - file containing range
* @lblk - first block in range
* @len - number of blocks to remove
*
* Reduces block/cluster reservation count and for bigalloc cancels pending
* reservations as needed.
*/
void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len)
{
ext4_lblk_t end;
int err = 0;
int reserved = 0;
struct extent_status *es = NULL;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
trace_ext4_es_remove_extent(inode, lblk, len);
es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
lblk, len, inode->i_ino);
if (!len)
return;
end = lblk + len - 1;
BUG_ON(end < lblk);
retry:
if (err && !es)
es = __es_alloc_extent(true);
/*
* ext4_clear_inode() depends on us taking i_es_lock unconditionally
* so that we are sure __es_shrink() is done with the inode before it
* is reclaimed.
*/
write_lock(&EXT4_I(inode)->i_es_lock);
err = __es_remove_extent(inode, lblk, end, &reserved, es);
/* Free preallocated extent if it didn't get used. */
if (es) {
if (!es->es_len)
__es_free_extent(es);
es = NULL;
}
write_unlock(&EXT4_I(inode)->i_es_lock);
if (err)
goto retry;
ext4_es_print_tree(inode);
ext4_da_release_space(inode, reserved);
}
static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
struct ext4_inode_info *locked_ei)
{
struct ext4_inode_info *ei;
struct ext4_es_stats *es_stats;
ktime_t start_time;
u64 scan_time;
int nr_to_walk;
int nr_shrunk = 0;
int retried = 0, nr_skipped = 0;
es_stats = &sbi->s_es_stats;
start_time = ktime_get();
retry:
spin_lock(&sbi->s_es_lock);
nr_to_walk = sbi->s_es_nr_inode;
while (nr_to_walk-- > 0) {
if (list_empty(&sbi->s_es_list)) {
spin_unlock(&sbi->s_es_lock);
goto out;
}
ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info,
i_es_list);
/* Move the inode to the tail */
list_move_tail(&ei->i_es_list, &sbi->s_es_list);
/*
* Normally we try hard to avoid shrinking precached inodes,
* but we will as a last resort.
*/
if (!retried && ext4_test_inode_state(&ei->vfs_inode,
EXT4_STATE_EXT_PRECACHED)) {
nr_skipped++;
continue;
}
if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) {
nr_skipped++;
continue;
}
/*
* Now we hold i_es_lock which protects us from inode reclaim
* freeing inode under us
*/
spin_unlock(&sbi->s_es_lock);
nr_shrunk += es_reclaim_extents(ei, &nr_to_scan);
write_unlock(&ei->i_es_lock);
if (nr_to_scan <= 0)
goto out;
spin_lock(&sbi->s_es_lock);
}
spin_unlock(&sbi->s_es_lock);
/*
* If we skipped any inodes, and we weren't able to make any
* forward progress, try again to scan precached inodes.
*/
if ((nr_shrunk == 0) && nr_skipped && !retried) {
retried++;
goto retry;
}
if (locked_ei && nr_shrunk == 0)
nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan);
out:
scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
if (likely(es_stats->es_stats_scan_time))
es_stats->es_stats_scan_time = (scan_time +
es_stats->es_stats_scan_time*3) / 4;
else
es_stats->es_stats_scan_time = scan_time;
if (scan_time > es_stats->es_stats_max_scan_time)
es_stats->es_stats_max_scan_time = scan_time;
if (likely(es_stats->es_stats_shrunk))
es_stats->es_stats_shrunk = (nr_shrunk +
es_stats->es_stats_shrunk*3) / 4;
else
es_stats->es_stats_shrunk = nr_shrunk;
trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time,
nr_skipped, retried);
return nr_shrunk;
}
static unsigned long ext4_es_count(struct shrinker *shrink,
struct shrink_control *sc)
{
unsigned long nr;
struct ext4_sb_info *sbi;
sbi = shrink->private_data;
nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr);
return nr;
}
static unsigned long ext4_es_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct ext4_sb_info *sbi = shrink->private_data;
int nr_to_scan = sc->nr_to_scan;
int ret, nr_shrunk;
ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL);
ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
return nr_shrunk;
}
int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v)
{
struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private);
struct ext4_es_stats *es_stats = &sbi->s_es_stats;
struct ext4_inode_info *ei, *max = NULL;
unsigned int inode_cnt = 0;
if (v != SEQ_START_TOKEN)
return 0;
/* here we just find an inode that has the max nr. of objects */
spin_lock(&sbi->s_es_lock);
list_for_each_entry(ei, &sbi->s_es_list, i_es_list) {
inode_cnt++;
if (max && max->i_es_all_nr < ei->i_es_all_nr)
max = ei;
else if (!max)
max = ei;
}
spin_unlock(&sbi->s_es_lock);
seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n",
percpu_counter_sum_positive(&es_stats->es_stats_all_cnt),
percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt));
seq_printf(seq, " %lld/%lld cache hits/misses\n",
percpu_counter_sum_positive(&es_stats->es_stats_cache_hits),
percpu_counter_sum_positive(&es_stats->es_stats_cache_misses));
if (inode_cnt)
seq_printf(seq, " %d inodes on list\n", inode_cnt);
seq_printf(seq, "average:\n %llu us scan time\n",
div_u64(es_stats->es_stats_scan_time, 1000));
seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk);
if (inode_cnt)
seq_printf(seq,
"maximum:\n %lu inode (%u objects, %u reclaimable)\n"
" %llu us max scan time\n",
max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr,
div_u64(es_stats->es_stats_max_scan_time, 1000));
return 0;
}
int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
{
int err;
/* Make sure we have enough bits for physical block number */
BUILD_BUG_ON(ES_SHIFT < 48);
INIT_LIST_HEAD(&sbi->s_es_list);
sbi->s_es_nr_inode = 0;
spin_lock_init(&sbi->s_es_lock);
sbi->s_es_stats.es_stats_shrunk = 0;
err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0,
GFP_KERNEL);
if (err)
return err;
err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0,
GFP_KERNEL);
if (err)
goto err1;
sbi->s_es_stats.es_stats_scan_time = 0;
sbi->s_es_stats.es_stats_max_scan_time = 0;
err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL);
if (err)
goto err2;
err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL);
if (err)
goto err3;
sbi->s_es_shrinker = shrinker_alloc(0, "ext4-es:%s", sbi->s_sb->s_id);
if (!sbi->s_es_shrinker) {
err = -ENOMEM;
goto err4;
}
sbi->s_es_shrinker->scan_objects = ext4_es_scan;
sbi->s_es_shrinker->count_objects = ext4_es_count;
sbi->s_es_shrinker->private_data = sbi;
shrinker_register(sbi->s_es_shrinker);
return 0;
err4:
percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
err3:
percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
err2:
percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
err1:
percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
return err;
}
void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
{
percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
shrinker_free(sbi->s_es_shrinker);
}
/*
* Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at
* most *nr_to_scan extents, update *nr_to_scan accordingly.
*
* Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan.
* Increment *nr_shrunk by the number of reclaimed extents. Also update
* ei->i_es_shrink_lblk to where we should continue scanning.
*/
static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
int *nr_to_scan, int *nr_shrunk)
{
struct inode *inode = &ei->vfs_inode;
struct ext4_es_tree *tree = &ei->i_es_tree;
struct extent_status *es;
struct rb_node *node;
es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk);
if (!es)
goto out_wrap;
while (*nr_to_scan > 0) {
if (es->es_lblk > end) {
ei->i_es_shrink_lblk = end + 1;
return 0;
}
(*nr_to_scan)--;
node = rb_next(&es->rb_node);
if (ext4_es_must_keep(es))
goto next;
if (ext4_es_is_referenced(es)) {
ext4_es_clear_referenced(es);
goto next;
}
rb_erase(&es->rb_node, &tree->root);
ext4_es_free_extent(inode, es);
(*nr_shrunk)++;
next:
if (!node)
goto out_wrap;
es = rb_entry(node, struct extent_status, rb_node);
}
ei->i_es_shrink_lblk = es->es_lblk;
return 1;
out_wrap:
ei->i_es_shrink_lblk = 0;
return 0;
}
static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan)
{
struct inode *inode = &ei->vfs_inode;
int nr_shrunk = 0;
ext4_lblk_t start = ei->i_es_shrink_lblk;
static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
if (ei->i_es_shk_nr == 0)
return 0;
if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
__ratelimit(&_rs))
ext4_warning(inode->i_sb, "forced shrink of precached extents");
if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) &&
start != 0)
es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk);
ei->i_es_tree.cache_es = NULL;
return nr_shrunk;
}
/*
* Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove
* discretionary entries from the extent status cache. (Some entries
* must be present for proper operations.)
*/
void ext4_clear_inode_es(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct extent_status *es;
struct ext4_es_tree *tree;
struct rb_node *node;
write_lock(&ei->i_es_lock);
tree = &EXT4_I(inode)->i_es_tree;
tree->cache_es = NULL;
node = rb_first(&tree->root);
while (node) {
es = rb_entry(node, struct extent_status, rb_node);
node = rb_next(node);
if (!ext4_es_must_keep(es)) {
rb_erase(&es->rb_node, &tree->root);
ext4_es_free_extent(inode, es);
}
}
ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
write_unlock(&ei->i_es_lock);
}
#ifdef ES_DEBUG__
static void ext4_print_pending_tree(struct inode *inode)
{
struct ext4_pending_tree *tree;
struct rb_node *node;
struct pending_reservation *pr;
printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino);
tree = &EXT4_I(inode)->i_pending_tree;
node = rb_first(&tree->root);
while (node) {
pr = rb_entry(node, struct pending_reservation, rb_node);
printk(KERN_DEBUG " %u", pr->lclu);
node = rb_next(node);
}
printk(KERN_DEBUG "\n");
}
#else
#define ext4_print_pending_tree(inode)
#endif
int __init ext4_init_pending(void)
{
ext4_pending_cachep = KMEM_CACHE(pending_reservation, SLAB_RECLAIM_ACCOUNT);
if (ext4_pending_cachep == NULL)
return -ENOMEM;
return 0;
}
void ext4_exit_pending(void)
{
kmem_cache_destroy(ext4_pending_cachep);
}
void ext4_init_pending_tree(struct ext4_pending_tree *tree)
{
tree->root = RB_ROOT;
}
/*
* __get_pending - retrieve a pointer to a pending reservation
*
* @inode - file containing the pending cluster reservation
* @lclu - logical cluster of interest
*
* Returns a pointer to a pending reservation if it's a member of
* the set, and NULL if not. Must be called holding i_es_lock.
*/
static struct pending_reservation *__get_pending(struct inode *inode,
ext4_lblk_t lclu)
{
struct ext4_pending_tree *tree;
struct rb_node *node;
struct pending_reservation *pr = NULL;
tree = &EXT4_I(inode)->i_pending_tree;
node = (&tree->root)->rb_node;
while (node) {
pr = rb_entry(node, struct pending_reservation, rb_node);
if (lclu < pr->lclu)
node = node->rb_left;
else if (lclu > pr->lclu)
node = node->rb_right;
else if (lclu == pr->lclu)
return pr;
}
return NULL;
}
/*
* __insert_pending - adds a pending cluster reservation to the set of
* pending reservations
*
* @inode - file containing the cluster
* @lblk - logical block in the cluster to be added
* @prealloc - preallocated pending entry
*
* Returns 1 on successful insertion and -ENOMEM on failure. If the
* pending reservation is already in the set, returns successfully.
*/
static int __insert_pending(struct inode *inode, ext4_lblk_t lblk,
struct pending_reservation **prealloc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree;
struct rb_node **p = &tree->root.rb_node;
struct rb_node *parent = NULL;
struct pending_reservation *pr;
ext4_lblk_t lclu;
int ret = 0;
lclu = EXT4_B2C(sbi, lblk);
/* search to find parent for insertion */
while (*p) {
parent = *p;
pr = rb_entry(parent, struct pending_reservation, rb_node);
if (lclu < pr->lclu) {
p = &(*p)->rb_left;
} else if (lclu > pr->lclu) {
p = &(*p)->rb_right;
} else {
/* pending reservation already inserted */
goto out;
}
}
if (likely(*prealloc == NULL)) {
pr = __alloc_pending(false);
if (!pr) {
ret = -ENOMEM;
goto out;
}
} else {
pr = *prealloc;
*prealloc = NULL;
}
pr->lclu = lclu;
rb_link_node(&pr->rb_node, parent, p);
rb_insert_color(&pr->rb_node, &tree->root);
ret = 1;
out:
return ret;
}
/*
* __remove_pending - removes a pending cluster reservation from the set
* of pending reservations
*
* @inode - file containing the cluster
* @lblk - logical block in the pending cluster reservation to be removed
*
* Returns successfully if pending reservation is not a member of the set.
*/
static void __remove_pending(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct pending_reservation *pr;
struct ext4_pending_tree *tree;
pr = __get_pending(inode, EXT4_B2C(sbi, lblk));
if (pr != NULL) {
tree = &EXT4_I(inode)->i_pending_tree;
rb_erase(&pr->rb_node, &tree->root);
__free_pending(pr);
}
}
/*
* ext4_remove_pending - removes a pending cluster reservation from the set
* of pending reservations
*
* @inode - file containing the cluster
* @lblk - logical block in the pending cluster reservation to be removed
*
* Locking for external use of __remove_pending.
*/
void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_inode_info *ei = EXT4_I(inode);
write_lock(&ei->i_es_lock);
__remove_pending(inode, lblk);
write_unlock(&ei->i_es_lock);
}
/*
* ext4_is_pending - determine whether a cluster has a pending reservation
* on it
*
* @inode - file containing the cluster
* @lblk - logical block in the cluster
*
* Returns true if there's a pending reservation for the cluster in the
* set of pending reservations, and false if not.
*/
bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
bool ret;
read_lock(&ei->i_es_lock);
ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL);
read_unlock(&ei->i_es_lock);
return ret;
}
/*
* ext4_es_insert_delayed_extent - adds some delayed blocks to the extents
* status tree, adding a pending reservation
* where needed
*
* @inode - file containing the newly added block
* @lblk - start logical block to be added
* @len - length of blocks to be added
* @lclu_allocated/end_allocated - indicates whether a physical cluster has
* been allocated for the logical cluster
* that contains the start/end block. Note that
* end_allocated should always be set to false
* if the start and the end block are in the
* same cluster
*/
void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, bool lclu_allocated,
bool end_allocated)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
int err1 = 0, err2 = 0, err3 = 0;
struct extent_status *es1 = NULL;
struct extent_status *es2 = NULL;
struct pending_reservation *pr1 = NULL;
struct pending_reservation *pr2 = NULL;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
es_debug("add [%u/%u) delayed to extent status tree of inode %lu\n",
lblk, len, inode->i_ino);
if (!len)
return;
WARN_ON_ONCE((EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) &&
end_allocated);
newes.es_lblk = lblk;
newes.es_len = len;
ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
end_allocated);
ext4_es_insert_extent_check(inode, &newes);
retry:
if (err1 && !es1)
es1 = __es_alloc_extent(true);
if ((err1 || err2) && !es2)
es2 = __es_alloc_extent(true);
if (err1 || err2 || err3 < 0) {
if (lclu_allocated && !pr1)
pr1 = __alloc_pending(true);
if (end_allocated && !pr2)
pr2 = __alloc_pending(true);
}
write_lock(&EXT4_I(inode)->i_es_lock);
err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
if (err1 != 0)
goto error;
/* Free preallocated extent if it didn't get used. */
if (es1) {
if (!es1->es_len)
__es_free_extent(es1);
es1 = NULL;
}
err2 = __es_insert_extent(inode, &newes, es2);
if (err2 != 0)
goto error;
/* Free preallocated extent if it didn't get used. */
if (es2) {
if (!es2->es_len)
__es_free_extent(es2);
es2 = NULL;
}
if (lclu_allocated) {
err3 = __insert_pending(inode, lblk, &pr1);
if (err3 < 0)
goto error;
if (pr1) {
__free_pending(pr1);
pr1 = NULL;
}
}
if (end_allocated) {
err3 = __insert_pending(inode, end, &pr2);
if (err3 < 0)
goto error;
if (pr2) {
__free_pending(pr2);
pr2 = NULL;
}
}
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
if (err1 || err2 || err3 < 0)
goto retry;
ext4_es_print_tree(inode);
ext4_print_pending_tree(inode);
return;
}
/*
* __revise_pending - makes, cancels, or leaves unchanged pending cluster
* reservations for a specified block range depending
* upon the presence or absence of delayed blocks
* outside the range within clusters at the ends of the
* range
*
* @inode - file containing the range
* @lblk - logical block defining the start of range
* @len - length of range in blocks
* @prealloc - preallocated pending entry
*
* Used after a newly allocated extent is added to the extents status tree.
* Requires that the extents in the range have either written or unwritten
* status. Must be called while holding i_es_lock. Returns number of new
* inserts pending cluster on insert pendings, returns 0 on remove pendings,
* return -ENOMEM on failure.
*/
static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len,
struct pending_reservation **prealloc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t end = lblk + len - 1;
ext4_lblk_t first, last;
bool f_del = false, l_del = false;
int pendings = 0;
int ret = 0;
if (len == 0)
return 0;
/*
* Two cases - block range within single cluster and block range
* spanning two or more clusters. Note that a cluster belonging
* to a range starting and/or ending on a cluster boundary is treated
* as if it does not contain a delayed extent. The new range may
* have allocated space for previously delayed blocks out to the
* cluster boundary, requiring that any pre-existing pending
* reservation be canceled. Because this code only looks at blocks
* outside the range, it should revise pending reservations
* correctly even if the extent represented by the range can't be
* inserted in the extents status tree due to ENOSPC.
*/
if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) {
first = EXT4_LBLK_CMASK(sbi, lblk);
if (first != lblk)
f_del = __es_scan_range(inode, &ext4_es_is_delayed,
first, lblk - 1);
if (f_del) {
ret = __insert_pending(inode, first, prealloc);
if (ret < 0)
goto out;
pendings += ret;
} else {
last = EXT4_LBLK_CMASK(sbi, end) +
sbi->s_cluster_ratio - 1;
if (last != end)
l_del = __es_scan_range(inode,
&ext4_es_is_delayed,
end + 1, last);
if (l_del) {
ret = __insert_pending(inode, last, prealloc);
if (ret < 0)
goto out;
pendings += ret;
} else
__remove_pending(inode, last);
}
} else {
first = EXT4_LBLK_CMASK(sbi, lblk);
if (first != lblk)
f_del = __es_scan_range(inode, &ext4_es_is_delayed,
first, lblk - 1);
if (f_del) {
ret = __insert_pending(inode, first, prealloc);
if (ret < 0)
goto out;
pendings += ret;
} else
__remove_pending(inode, first);
last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1;
if (last != end)
l_del = __es_scan_range(inode, &ext4_es_is_delayed,
end + 1, last);
if (l_del) {
ret = __insert_pending(inode, last, prealloc);
if (ret < 0)
goto out;
pendings += ret;
} else
__remove_pending(inode, last);
}
out:
return (ret < 0) ? ret : pendings;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* IRQ offload/bypass manager
*
* Copyright (C) 2015 Red Hat, Inc.
* Copyright (c) 2015 Linaro Ltd.
*
* Various virtualization hardware acceleration techniques allow bypassing or
* offloading interrupts received from devices around the host kernel. Posted
* Interrupts on Intel VT-d systems can allow interrupts to be received
* directly by a virtual machine. ARM IRQ Forwarding allows forwarded physical
* interrupts to be directly deactivated by the guest. This manager allows
* interrupt producers and consumers to find each other to enable this sort of
* bypass.
*/
#include <linux/irqbypass.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("IRQ bypass manager utility module");
static LIST_HEAD(producers);
static LIST_HEAD(consumers);
static DEFINE_MUTEX(lock);
/* @lock must be held when calling connect */
static int __connect(struct irq_bypass_producer *prod,
struct irq_bypass_consumer *cons)
{
int ret = 0;
if (prod->stop) prod->stop(prod); if (cons->stop) cons->stop(cons); if (prod->add_consumer)
ret = prod->add_consumer(prod, cons);
if (!ret) {
ret = cons->add_producer(cons, prod);
if (ret && prod->del_consumer) prod->del_consumer(prod, cons);
}
if (cons->start) cons->start(cons); if (prod->start) prod->start(prod);
return ret;
}
/* @lock must be held when calling disconnect */
static void __disconnect(struct irq_bypass_producer *prod,
struct irq_bypass_consumer *cons)
{
if (prod->stop)
prod->stop(prod);
if (cons->stop)
cons->stop(cons);
cons->del_producer(cons, prod);
if (prod->del_consumer)
prod->del_consumer(prod, cons);
if (cons->start)
cons->start(cons);
if (prod->start)
prod->start(prod);
}
/**
* irq_bypass_register_producer - register IRQ bypass producer
* @producer: pointer to producer structure
*
* Add the provided IRQ producer to the list of producers and connect
* with any matching token found on the IRQ consumers list.
*/
int irq_bypass_register_producer(struct irq_bypass_producer *producer)
{
struct irq_bypass_producer *tmp;
struct irq_bypass_consumer *consumer;
int ret;
if (!producer->token)
return -EINVAL;
might_sleep();
if (!try_module_get(THIS_MODULE))
return -ENODEV;
mutex_lock(&lock);
list_for_each_entry(tmp, &producers, node) {
if (tmp->token == producer->token) {
ret = -EBUSY;
goto out_err;
}
}
list_for_each_entry(consumer, &consumers, node) {
if (consumer->token == producer->token) {
ret = __connect(producer, consumer);
if (ret)
goto out_err;
break;
}
}
list_add(&producer->node, &producers);
mutex_unlock(&lock);
return 0;
out_err:
mutex_unlock(&lock);
module_put(THIS_MODULE);
return ret;
}
EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
/**
* irq_bypass_unregister_producer - unregister IRQ bypass producer
* @producer: pointer to producer structure
*
* Remove a previously registered IRQ producer from the list of producers
* and disconnect it from any connected IRQ consumer.
*/
void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
{
struct irq_bypass_producer *tmp;
struct irq_bypass_consumer *consumer;
if (!producer->token)
return;
might_sleep();
if (!try_module_get(THIS_MODULE))
return; /* nothing in the list anyway */
mutex_lock(&lock);
list_for_each_entry(tmp, &producers, node) {
if (tmp->token != producer->token)
continue;
list_for_each_entry(consumer, &consumers, node) {
if (consumer->token == producer->token) {
__disconnect(producer, consumer);
break;
}
}
list_del(&producer->node);
module_put(THIS_MODULE);
break;
}
mutex_unlock(&lock);
module_put(THIS_MODULE);
}
EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
/**
* irq_bypass_register_consumer - register IRQ bypass consumer
* @consumer: pointer to consumer structure
*
* Add the provided IRQ consumer to the list of consumers and connect
* with any matching token found on the IRQ producer list.
*/
int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
{
struct irq_bypass_consumer *tmp;
struct irq_bypass_producer *producer;
int ret;
if (!consumer->token || !consumer->add_producer || !consumer->del_producer)
return -EINVAL;
might_sleep();
if (!try_module_get(THIS_MODULE))
return -ENODEV;
mutex_lock(&lock);
list_for_each_entry(tmp, &consumers, node) {
if (tmp->token == consumer->token || tmp == consumer) {
ret = -EBUSY;
goto out_err;
}
}
list_for_each_entry(producer, &producers, node) { if (producer->token == consumer->token) { ret = __connect(producer, consumer); if (ret)
goto out_err;
break;
}
}
list_add(&consumer->node, &consumers);
mutex_unlock(&lock);
return 0;
out_err:
mutex_unlock(&lock);
module_put(THIS_MODULE);
return ret;
}
EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);
/**
* irq_bypass_unregister_consumer - unregister IRQ bypass consumer
* @consumer: pointer to consumer structure
*
* Remove a previously registered IRQ consumer from the list of consumers
* and disconnect it from any connected IRQ producer.
*/
void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
{
struct irq_bypass_consumer *tmp;
struct irq_bypass_producer *producer;
if (!consumer->token)
return;
might_sleep();
if (!try_module_get(THIS_MODULE))
return; /* nothing in the list anyway */
mutex_lock(&lock);
list_for_each_entry(tmp, &consumers, node) {
if (tmp != consumer)
continue;
list_for_each_entry(producer, &producers, node) {
if (producer->token == consumer->token) {
__disconnect(producer, consumer);
break;
}
}
list_del(&consumer->node);
module_put(THIS_MODULE);
break;
}
mutex_unlock(&lock);
module_put(THIS_MODULE);
}
EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer);
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* include/asm-generic/tlb.h
*
* Generic TLB shootdown code
*
* Copyright 2001 Red Hat, Inc.
* Based on code from mm/memory.c Copyright Linus Torvalds and others.
*
* Copyright 2011 Red Hat, Inc., Peter Zijlstra
*/
#ifndef _ASM_GENERIC__TLB_H
#define _ASM_GENERIC__TLB_H
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/hugetlb_inline.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
/*
* Blindly accessing user memory from NMI context can be dangerous
* if we're in the middle of switching the current user task or switching
* the loaded mm.
*/
#ifndef nmi_uaccess_okay
# define nmi_uaccess_okay() true
#endif
#ifdef CONFIG_MMU
/*
* Generic MMU-gather implementation.
*
* The mmu_gather data structure is used by the mm code to implement the
* correct and efficient ordering of freeing pages and TLB invalidations.
*
* This correct ordering is:
*
* 1) unhook page
* 2) TLB invalidate page
* 3) free page
*
* That is, we must never free a page before we have ensured there are no live
* translations left to it. Otherwise it might be possible to observe (or
* worse, change) the page content after it has been reused.
*
* The mmu_gather API consists of:
*
* - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu()
*
* start and finish a mmu_gather
*
* Finish in particular will issue a (final) TLB invalidate and free
* all (remaining) queued pages.
*
* - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
*
* Defaults to flushing at tlb_end_vma() to reset the range; helps when
* there's large holes between the VMAs.
*
* - tlb_remove_table()
*
* tlb_remove_table() is the basic primitive to free page-table directories
* (__p*_free_tlb()). In it's most primitive form it is an alias for
* tlb_remove_page() below, for when page directories are pages and have no
* additional constraints.
*
* See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE.
*
* - tlb_remove_page() / tlb_remove_page_size()
* - __tlb_remove_folio_pages() / __tlb_remove_page_size()
* - __tlb_remove_folio_pages_size()
*
* __tlb_remove_folio_pages_size() is the basic primitive that queues pages
* for freeing. It will return a boolean indicating if the queue is (now)
* full and a call to tlb_flush_mmu() is required.
*
* tlb_remove_page() and tlb_remove_page_size() imply the call to
* tlb_flush_mmu() when required and has no return value.
*
* __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(),
* however, instead of removing a single page, assume PAGE_SIZE and remove
* the given number of consecutive pages that are all part of the
* same (large) folio.
*
* - tlb_change_page_size()
*
* call before __tlb_remove_page*() to set the current page-size; implies a
* possible tlb_flush_mmu() call.
*
* - tlb_flush_mmu() / tlb_flush_mmu_tlbonly()
*
* tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
* related state, like the range)
*
* tlb_flush_mmu() - in addition to the above TLB invalidate, also frees
* whatever pages are still batched.
*
* - mmu_gather::fullmm
*
* A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free
* the entire mm; this allows a number of optimizations.
*
* - We can ignore tlb_{start,end}_vma(); because we don't
* care about ranges. Everything will be shot down.
*
* - (RISC) architectures that use ASIDs can cycle to a new ASID
* and delay the invalidation until ASID space runs out.
*
* - mmu_gather::need_flush_all
*
* A flag that can be set by the arch code if it wants to force
* flush the entire TLB irrespective of the range. For instance
* x86-PAE needs this when changing top-level entries.
*
* And allows the architecture to provide and implement tlb_flush():
*
* tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
* use of:
*
* - mmu_gather::start / mmu_gather::end
*
* which provides the range that needs to be flushed to cover the pages to
* be freed.
*
* - mmu_gather::freed_tables
*
* set when we freed page table pages
*
* - tlb_get_unmap_shift() / tlb_get_unmap_size()
*
* returns the smallest TLB entry size unmapped in this range.
*
* If an architecture does not provide tlb_flush() a default implementation
* based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is
* specified, in which case we'll default to flush_tlb_mm().
*
* Additionally there are a few opt-in features:
*
* MMU_GATHER_PAGE_SIZE
*
* This ensures we call tlb_flush() every time tlb_change_page_size() actually
* changes the size and provides mmu_gather::page_size to tlb_flush().
*
* This might be useful if your architecture has size specific TLB
* invalidation instructions.
*
* MMU_GATHER_TABLE_FREE
*
* This provides tlb_remove_table(), to be used instead of tlb_remove_page()
* for page directores (__p*_free_tlb()).
*
* Useful if your architecture has non-page page directories.
*
* When used, an architecture is expected to provide __tlb_remove_table() or
* use the generic __tlb_remove_table(), which does the actual freeing of these
* pages.
*
* MMU_GATHER_RCU_TABLE_FREE
*
* Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see
* comment below).
*
* Useful if your architecture doesn't use IPIs for remote TLB invalidates
* and therefore doesn't naturally serialize with software page-table walkers.
*
* MMU_GATHER_NO_FLUSH_CACHE
*
* Indicates the architecture has flush_cache_range() but it needs *NOT* be called
* before unmapping a VMA.
*
* NOTE: strictly speaking we shouldn't have this knob and instead rely on
* flush_cache_range() being a NOP, except Sparc64 seems to be
* different here.
*
* MMU_GATHER_MERGE_VMAS
*
* Indicates the architecture wants to merge ranges over VMAs; typical when
* multiple range invalidates are more expensive than a full invalidate.
*
* MMU_GATHER_NO_RANGE
*
* Use this if your architecture lacks an efficient flush_tlb_range(). This
* option implies MMU_GATHER_MERGE_VMAS above.
*
* MMU_GATHER_NO_GATHER
*
* If the option is set the mmu_gather will not track individual pages for
* delayed page free anymore. A platform that enables the option needs to
* provide its own implementation of the __tlb_remove_page_size() function to
* free pages.
*
* This is useful if your architecture already flushes TLB entries in the
* various ptep_get_and_clear() functions.
*/
#ifdef CONFIG_MMU_GATHER_TABLE_FREE
struct mmu_table_batch {
#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
struct rcu_head rcu;
#endif
unsigned int nr;
void *tables[];
};
#define MAX_TABLE_BATCH \
((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
#ifndef __HAVE_ARCH_TLB_REMOVE_TABLE
static inline void __tlb_remove_table(void *table)
{
struct ptdesc *ptdesc = (struct ptdesc *)table;
pagetable_dtor_free(ptdesc);
}
#endif
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#else /* !CONFIG_MMU_GATHER_TABLE_FREE */
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page);
/*
* Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based
* page directories and we can use the normal page batching to free them.
*/
static inline void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
struct ptdesc *ptdesc = (struct ptdesc *)table;
pagetable_dtor(ptdesc);
tlb_remove_page(tlb, ptdesc_page(ptdesc));
}
#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
/*
* This allows an architecture that does not use the linux page-tables for
* hardware to skip the TLBI when freeing page tables.
*/
#ifndef tlb_needs_table_invalidate
#define tlb_needs_table_invalidate() (true)
#endif
void tlb_remove_table_sync_one(void);
#else
#ifdef tlb_needs_table_invalidate
#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
#endif
static inline void tlb_remove_table_sync_one(void) { }
#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
#ifndef CONFIG_MMU_GATHER_NO_GATHER
/*
* If we can't allocate a page to make a big batch of page pointers
* to work on, then just handle a few from the on-stack structure.
*/
#define MMU_GATHER_BUNDLE 8
struct mmu_gather_batch {
struct mmu_gather_batch *next;
unsigned int nr;
unsigned int max;
struct encoded_page *encoded_pages[];
};
#define MAX_GATHER_BATCH \
((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
/*
* Limit the maximum number of mmu_gather batches to reduce a risk of soft
* lockups for non-preemptible kernels on huge machines when a lot of memory
* is zapped during unmapping.
* 10K pages freed at once should be safe even without a preemption point.
*/
#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH)
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
bool delay_rmap, int page_size);
bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
unsigned int nr_pages, bool delay_rmap);
#ifdef CONFIG_SMP
/*
* This both sets 'delayed_rmap', and returns true. It would be an inline
* function, except we define it before the 'struct mmu_gather'.
*/
#define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true)
extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma);
#endif
#endif
/*
* We have a no-op version of the rmap removal that doesn't
* delay anything. That is used on S390, which flushes remote
* TLBs synchronously, and on UP, which doesn't have any
* remote TLBs to flush and is not preemptible due to this
* all happening under the page table lock.
*/
#ifndef tlb_delay_rmap
#define tlb_delay_rmap(tlb) (false)
static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
#endif
/*
* struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
#ifdef CONFIG_MMU_GATHER_TABLE_FREE
struct mmu_table_batch *batch;
#endif
unsigned long start;
unsigned long end;
/*
* we are in the middle of an operation to clear
* a full mm and can make some optimizations
*/
unsigned int fullmm : 1;
/*
* we have performed an operation which
* requires a complete flush of the tlb
*/
unsigned int need_flush_all : 1;
/*
* we have removed page directories
*/
unsigned int freed_tables : 1;
/*
* Do we have pending delayed rmap removals?
*/
unsigned int delayed_rmap : 1;
/*
* at which levels have we cleared entries?
*/
unsigned int cleared_ptes : 1;
unsigned int cleared_pmds : 1;
unsigned int cleared_puds : 1;
unsigned int cleared_p4ds : 1;
/*
* tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
*/
unsigned int vma_exec : 1;
unsigned int vma_huge : 1;
unsigned int vma_pfn : 1;
unsigned int batch_count;
#ifndef CONFIG_MMU_GATHER_NO_GATHER
struct mmu_gather_batch *active;
struct mmu_gather_batch local;
struct page *__pages[MMU_GATHER_BUNDLE];
#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
unsigned int page_size;
#endif
#endif
};
void tlb_flush_mmu(struct mmu_gather *tlb);
static inline void __tlb_adjust_range(struct mmu_gather *tlb,
unsigned long address,
unsigned int range_size)
{
tlb->start = min(tlb->start, address);
tlb->end = max(tlb->end, address + range_size);
}
static inline void __tlb_reset_range(struct mmu_gather *tlb)
{
if (tlb->fullmm) {
tlb->start = tlb->end = ~0;
} else {
tlb->start = TASK_SIZE;
tlb->end = 0;
}
tlb->freed_tables = 0;
tlb->cleared_ptes = 0;
tlb->cleared_pmds = 0;
tlb->cleared_puds = 0;
tlb->cleared_p4ds = 0;
/*
* Do not reset mmu_gather::vma_* fields here, we do not
* call into tlb_start_vma() again to set them if there is an
* intermediate flush.
*/
}
#ifdef CONFIG_MMU_GATHER_NO_RANGE
#if defined(tlb_flush)
#error MMU_GATHER_NO_RANGE relies on default tlb_flush()
#endif
/*
* When an architecture does not have efficient means of range flushing TLBs
* there is no point in doing intermediate flushes on tlb_end_vma() to keep the
* range small. We equally don't have to worry about page granularity or other
* things.
*
* All we need to do is issue a full flush for any !0 range.
*/
static inline void tlb_flush(struct mmu_gather *tlb)
{
if (tlb->end)
flush_tlb_mm(tlb->mm);
}
#else /* CONFIG_MMU_GATHER_NO_RANGE */
#ifndef tlb_flush
/*
* When an architecture does not provide its own tlb_flush() implementation
* but does have a reasonably efficient flush_vma_range() implementation
* use that.
*/
static inline void tlb_flush(struct mmu_gather *tlb)
{
if (tlb->fullmm || tlb->need_flush_all) {
flush_tlb_mm(tlb->mm);
} else if (tlb->end) {
struct vm_area_struct vma = {
.vm_mm = tlb->mm,
.vm_flags = (tlb->vma_exec ? VM_EXEC : 0) |
(tlb->vma_huge ? VM_HUGETLB : 0),
};
flush_tlb_range(&vma, tlb->start, tlb->end);
}
}
#endif
#endif /* CONFIG_MMU_GATHER_NO_RANGE */
static inline void
tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
/*
* flush_tlb_range() implementations that look at VM_HUGETLB (tile,
* mips-4k) flush only large pages.
*
* flush_tlb_range() implementations that flush I-TLB also flush D-TLB
* (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
* range.
*
* We rely on tlb_end_vma() to issue a flush, such that when we reset
* these values the batch is empty.
*/
tlb->vma_huge = is_vm_hugetlb_page(vma);
tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
tlb->vma_pfn = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP));
}
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
/*
* Anything calling __tlb_adjust_range() also sets at least one of
* these bits.
*/
if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds ||
tlb->cleared_puds || tlb->cleared_p4ds))
return;
tlb_flush(tlb); __tlb_reset_range(tlb);
}
static inline void tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
if (__tlb_remove_page_size(tlb, page, false, page_size)) tlb_flush_mmu(tlb);
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
return tlb_remove_page_size(tlb, page, PAGE_SIZE);
}
static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt)
{
tlb_remove_table(tlb, pt);
}
static inline void tlb_change_page_size(struct mmu_gather *tlb,
unsigned int page_size)
{
#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
if (tlb->page_size && tlb->page_size != page_size) {
if (!tlb->fullmm && !tlb->need_flush_all)
tlb_flush_mmu(tlb);
}
tlb->page_size = page_size;
#endif
}
static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
{
if (tlb->cleared_ptes)
return PAGE_SHIFT;
if (tlb->cleared_pmds)
return PMD_SHIFT;
if (tlb->cleared_puds)
return PUD_SHIFT;
if (tlb->cleared_p4ds)
return P4D_SHIFT;
return PAGE_SHIFT;
}
static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
{
return 1UL << tlb_get_unmap_shift(tlb);
}
/*
* In the case of tlb vma handling, we can optimise these away in the
* case where we're doing a full MM flush. When we're doing a munmap,
* the vmas are adjusted to only cover the region to be torn down.
*/
static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (tlb->fullmm)
return;
tlb_update_vma_flags(tlb, vma);
#ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE
flush_cache_range(vma, vma->vm_start, vma->vm_end);
#endif
}
static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (tlb->fullmm)
return;
/*
* VM_PFNMAP is more fragile because the core mm will not track the
* page mapcount -- there might not be page-frames for these PFNs after
* all. Force flush TLBs for such ranges to avoid munmap() vs
* unmap_mapping_range() races.
*/
if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) {
/*
* Do a TLB flush and reset the range at VMA boundaries; this avoids
* the ranges growing with the unused space between consecutive VMAs.
*/
tlb_flush_mmu_tlbonly(tlb);
}
}
/*
* tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
* and set corresponding cleared_*.
*/
static inline void tlb_flush_pte_range(struct mmu_gather *tlb,
unsigned long address, unsigned long size)
{
__tlb_adjust_range(tlb, address, size);
tlb->cleared_ptes = 1;
}
static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
unsigned long address, unsigned long size)
{
__tlb_adjust_range(tlb, address, size);
tlb->cleared_pmds = 1;
}
static inline void tlb_flush_pud_range(struct mmu_gather *tlb,
unsigned long address, unsigned long size)
{
__tlb_adjust_range(tlb, address, size);
tlb->cleared_puds = 1;
}
static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
unsigned long address, unsigned long size)
{
__tlb_adjust_range(tlb, address, size);
tlb->cleared_p4ds = 1;
}
#ifndef __tlb_remove_tlb_entry
static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
{
}
#endif
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
* Record the fact that pte's were really unmapped by updating the range,
* so we can later optimise away the tlb invalidate. This helps when
* userspace is unmapping already-unmapped pages, which happens quite a lot.
*/
#define tlb_remove_tlb_entry(tlb, ptep, address) \
do { \
tlb_flush_pte_range(tlb, address, PAGE_SIZE); \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
/**
* tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for
* later tlb invalidation.
*
* Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple
* consecutive ptes instead of only a single one.
*/
static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb,
pte_t *ptep, unsigned int nr, unsigned long address)
{
tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr);
for (;;) {
__tlb_remove_tlb_entry(tlb, ptep, address);
if (--nr == 0)
break;
ptep++;
address += PAGE_SIZE;
}
}
#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
do { \
unsigned long _sz = huge_page_size(h); \
if (_sz >= P4D_SIZE) \
tlb_flush_p4d_range(tlb, address, _sz); \
else if (_sz >= PUD_SIZE) \
tlb_flush_pud_range(tlb, address, _sz); \
else if (_sz >= PMD_SIZE) \
tlb_flush_pmd_range(tlb, address, _sz); \
else \
tlb_flush_pte_range(tlb, address, _sz); \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
/**
* tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
* This is a nop so far, because only x86 needs it.
*/
#ifndef __tlb_remove_pmd_tlb_entry
#define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
#endif
#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \
do { \
tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
/**
* tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb
* invalidation. This is a nop so far, because only x86 needs it.
*/
#ifndef __tlb_remove_pud_tlb_entry
#define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0)
#endif
#define tlb_remove_pud_tlb_entry(tlb, pudp, address) \
do { \
tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \
__tlb_remove_pud_tlb_entry(tlb, pudp, address); \
} while (0)
/*
* For things like page tables caches (ie caching addresses "inside" the
* page tables, like x86 does), for legacy reasons, flushing an
* individual page had better flush the page table caches behind it. This
* is definitely how x86 works, for example. And if you have an
* architected non-legacy page table cache (which I'm not aware of
* anybody actually doing), you're going to have some architecturally
* explicit flushing for that, likely *separate* from a regular TLB entry
* flush, and thus you'd need more than just some range expansion..
*
* So if we ever find an architecture
* that would want something that odd, I think it is up to that
* architecture to do its own odd thing, not cause pain for others
* http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com
*
* For now w.r.t page table cache, mark the range_size as PAGE_SIZE
*/
#ifndef pte_free_tlb
#define pte_free_tlb(tlb, ptep, address) \
do { \
tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \
tlb->freed_tables = 1; \
__pte_free_tlb(tlb, ptep, address); \
} while (0)
#endif
#ifndef pmd_free_tlb
#define pmd_free_tlb(tlb, pmdp, address) \
do { \
tlb_flush_pud_range(tlb, address, PAGE_SIZE); \
tlb->freed_tables = 1; \
__pmd_free_tlb(tlb, pmdp, address); \
} while (0)
#endif
#ifndef pud_free_tlb
#define pud_free_tlb(tlb, pudp, address) \
do { \
tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \
tlb->freed_tables = 1; \
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#ifndef p4d_free_tlb
#define p4d_free_tlb(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address, PAGE_SIZE); \
tlb->freed_tables = 1; \
__p4d_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#ifndef pte_needs_flush
static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
{
return true;
}
#endif
#ifndef huge_pmd_needs_flush
static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
{
return true;
}
#endif
#endif /* CONFIG_MMU */
#endif /* _ASM_GENERIC__TLB_H */
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#ifndef __ASM__VIRT_H
#define __ASM__VIRT_H
/*
* The arm64 hcall implementation uses x0 to specify the hcall
* number. A value less than HVC_STUB_HCALL_NR indicates a special
* hcall, such as set vector. Any other value is handled in a
* hypervisor specific way.
*
* The hypercall is allowed to clobber any of the caller-saved
* registers (x0-x18), so it is advisable to use it through the
* indirection of a function call (as implemented in hyp-stub.S).
*/
/*
* HVC_SET_VECTORS - Set the value of the vbar_el2 register.
*
* @x1: Physical address of the new vector table.
*/
#define HVC_SET_VECTORS 0
/*
* HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
*/
#define HVC_SOFT_RESTART 1
/*
* HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs
*/
#define HVC_RESET_VECTORS 2
/*
* HVC_FINALISE_EL2 - Upgrade the CPU from EL1 to EL2, if possible
*/
#define HVC_FINALISE_EL2 3
/* Max number of HYP stub hypercalls */
#define HVC_STUB_HCALL_NR 4
/* Error returned when an invalid stub number is passed into x0 */
#define HVC_STUB_ERR 0xbadca11
#define BOOT_CPU_MODE_EL1 (0xe11)
#define BOOT_CPU_MODE_EL2 (0xe12)
/*
* Flags returned together with the boot mode, but not preserved in
* __boot_cpu_mode. Used by the idreg override code to work out the
* boot state.
*/
#define BOOT_CPU_FLAG_E2H BIT_ULL(32)
#ifndef __ASSEMBLY__
#include <asm/ptrace.h>
#include <asm/sections.h>
#include <asm/sysreg.h>
#include <asm/cpufeature.h>
/*
* __boot_cpu_mode records what mode CPUs were booted in.
* A correctly-implemented bootloader must start all CPUs in the same mode:
* In this case, both 32bit halves of __boot_cpu_mode will contain the
* same value (either 0 if booted in EL1, BOOT_CPU_MODE_EL2 if booted in EL2).
*
* Should the bootloader fail to do this, the two values will be different.
* This allows the kernel to flag an error when the secondaries have come up.
*/
extern u32 __boot_cpu_mode[2];
#define ARM64_VECTOR_TABLE_LEN SZ_2K
void __hyp_set_vectors(phys_addr_t phys_vector_base);
void __hyp_reset_vectors(void);
bool is_kvm_arm_initialised(void);
DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
static inline bool is_pkvm_initialized(void)
{
return IS_ENABLED(CONFIG_KVM) &&
static_branch_likely(&kvm_protected_mode_initialized);
}
/* Reports the availability of HYP mode */
static inline bool is_hyp_mode_available(void)
{
/*
* If KVM protected mode is initialized, all CPUs must have been booted
* in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
*/
if (is_pkvm_initialized())
return true;
return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 &&
__boot_cpu_mode[1] == BOOT_CPU_MODE_EL2);
}
/* Check if the bootloader has booted CPUs in different modes */
static inline bool is_hyp_mode_mismatched(void)
{
/*
* If KVM protected mode is initialized, all CPUs must have been booted
* in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
*/
if (is_pkvm_initialized())
return false;
return __boot_cpu_mode[0] != __boot_cpu_mode[1];
}
static __always_inline bool is_kernel_in_hyp_mode(void)
{
BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__) ||
__is_defined(__KVM_VHE_HYPERVISOR__));
return read_sysreg(CurrentEL) == CurrentEL_EL2;
}
static __always_inline bool has_vhe(void)
{
/*
* Code only run in VHE/NVHE hyp context can assume VHE is present or
* absent. Otherwise fall back to caps.
* This allows the compiler to discard VHE-specific code from the
* nVHE object, reducing the number of external symbol references
* needed to link.
*/
if (is_vhe_hyp_code())
return true;
else if (is_nvhe_hyp_code())
return false;
else
return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
}
static __always_inline bool is_protected_kvm_enabled(void)
{
if (is_vhe_hyp_code())
return false;
else
return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE);
}
static __always_inline bool has_hvhe(void)
{
if (is_vhe_hyp_code())
return false;
return cpus_have_final_cap(ARM64_KVM_HVHE);
}
static inline bool is_hyp_nvhe(void)
{
return is_hyp_mode_available() && !is_kernel_in_hyp_mode();
}
#endif /* __ASSEMBLY__ */
#endif /* ! __ASM__VIRT_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Implementation of the diskquota system for the LINUX operating system. QUOTA
* is implemented using the BSD system call interface as the means of
* communication with the user level. This file contains the generic routines
* called by the different filesystems on allocation of an inode or block.
* These routines take care of the administration needed to have a consistent
* diskquota tracking system. The ideas of both user and group quotas are based
* on the Melbourne quota system as used on BSD derived systems. The internal
* implementation is based on one of the several variants of the LINUX
* inode-subsystem with added complexity of the diskquota system.
*
* Author: Marco van Wieringen <mvw@planets.elm.net>
*
* Fixes: Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96
*
* Revised list management to avoid races
* -- Bill Hawes, <whawes@star.net>, 9/98
*
* Fixed races in dquot_transfer(), dqget() and dquot_alloc_...().
* As the consequence the locking was moved from dquot_decr_...(),
* dquot_incr_...() to calling functions.
* invalidate_dquots() now writes modified dquots.
* Serialized quota_off() and quota_on() for mount point.
* Fixed a few bugs in grow_dquots().
* Fixed deadlock in write_dquot() - we no longer account quotas on
* quota files
* remove_dquot_ref() moved to inode.c - it now traverses through inodes
* add_dquot_ref() restarts after blocking
* Added check for bogus uid and fixed check for group in quotactl.
* Jan Kara, <jack@suse.cz>, sponsored by SuSE CR, 10-11/99
*
* Used struct list_head instead of own list struct
* Invalidation of referenced dquots is no longer possible
* Improved free_dquots list management
* Quota and i_blocks are now updated in one place to avoid races
* Warnings are now delayed so we won't block in critical section
* Write updated not to require dquot lock
* Jan Kara, <jack@suse.cz>, 9/2000
*
* Added dynamic quota structure allocation
* Jan Kara <jack@suse.cz> 12/2000
*
* Rewritten quota interface. Implemented new quota format and
* formats registering.
* Jan Kara, <jack@suse.cz>, 2001,2002
*
* New SMP locking.
* Jan Kara, <jack@suse.cz>, 10/2002
*
* Added journalled quota support, fix lock inversion problems
* Jan Kara, <jack@suse.cz>, 2003,2004
*
* (C) Copyright 1994 - 1997 Marco van Wieringen
*/
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/mm.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/tty.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/kmod.h>
#include <linux/namei.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
/*
* There are five quota SMP locks:
* * dq_list_lock protects all lists with quotas and quota formats.
* * dquot->dq_dqb_lock protects data from dq_dqb
* * inode->i_lock protects inode->i_blocks, i_bytes and also guards
* consistency of dquot->dq_dqb with inode->i_blocks, i_bytes so that
* dquot_transfer() can stabilize amount it transfers
* * dq_data_lock protects mem_dqinfo structures and modifications of dquot
* pointers in the inode
* * dq_state_lock protects modifications of quota state (on quotaon and
* quotaoff) and readers who care about latest values take it as well.
*
* The spinlock ordering is hence:
* dq_data_lock > dq_list_lock > i_lock > dquot->dq_dqb_lock,
* dq_list_lock > dq_state_lock
*
* Note that some things (eg. sb pointer, type, id) doesn't change during
* the life of the dquot structure and so needn't to be protected by a lock
*
* Operation accessing dquots via inode pointers are protected by dquot_srcu.
* Operation of reading pointer needs srcu_read_lock(&dquot_srcu), and
* synchronize_srcu(&dquot_srcu) is called after clearing pointers from
* inode and before dropping dquot references to avoid use of dquots after
* they are freed. dq_data_lock is used to serialize the pointer setting and
* clearing operations.
* Special care needs to be taken about S_NOQUOTA inode flag (marking that
* inode is a quota file). Functions adding pointers from inode to dquots have
* to check this flag under dq_data_lock and then (if S_NOQUOTA is not set) they
* have to do all pointer modifications before dropping dq_data_lock. This makes
* sure they cannot race with quotaon which first sets S_NOQUOTA flag and
* then drops all pointers to dquots from an inode.
*
* Each dquot has its dq_lock mutex. Dquot is locked when it is being read to
* memory (or space for it is being allocated) on the first dqget(), when it is
* being written out, and when it is being released on the last dqput(). The
* allocation and release operations are serialized by the dq_lock and by
* checking the use count in dquot_release().
*
* Lock ordering (including related VFS locks) is the following:
* s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_sem
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_state_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock);
EXPORT_SYMBOL(dq_data_lock);
DEFINE_STATIC_SRCU(dquot_srcu);
static DECLARE_WAIT_QUEUE_HEAD(dquot_ref_wq);
void __quota_error(struct super_block *sb, const char *func,
const char *fmt, ...)
{
if (printk_ratelimit()) {
va_list args;
struct va_format vaf;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_ERR "Quota error (device %s): %s: %pV\n",
sb->s_id, func, &vaf);
va_end(args);
}
}
EXPORT_SYMBOL(__quota_error);
#if defined(CONFIG_QUOTA_DEBUG) || defined(CONFIG_PRINT_QUOTA_WARNING)
static char *quotatypes[] = INITQFNAMES;
#endif
static struct quota_format_type *quota_formats; /* List of registered formats */
static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES;
/* SLAB cache for dquot structures */
static struct kmem_cache *dquot_cachep;
void register_quota_format(struct quota_format_type *fmt)
{
spin_lock(&dq_list_lock);
fmt->qf_next = quota_formats;
quota_formats = fmt;
spin_unlock(&dq_list_lock);
}
EXPORT_SYMBOL(register_quota_format);
void unregister_quota_format(struct quota_format_type *fmt)
{
struct quota_format_type **actqf;
spin_lock(&dq_list_lock);
for (actqf = "a_formats; *actqf && *actqf != fmt;
actqf = &(*actqf)->qf_next)
;
if (*actqf)
*actqf = (*actqf)->qf_next;
spin_unlock(&dq_list_lock);
}
EXPORT_SYMBOL(unregister_quota_format);
static struct quota_format_type *find_quota_format(int id)
{
struct quota_format_type *actqf;
spin_lock(&dq_list_lock);
for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id;
actqf = actqf->qf_next)
;
if (!actqf || !try_module_get(actqf->qf_owner)) {
int qm;
spin_unlock(&dq_list_lock);
for (qm = 0; module_names[qm].qm_fmt_id &&
module_names[qm].qm_fmt_id != id; qm++)
;
if (!module_names[qm].qm_fmt_id ||
request_module(module_names[qm].qm_mod_name))
return NULL;
spin_lock(&dq_list_lock);
for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id;
actqf = actqf->qf_next)
;
if (actqf && !try_module_get(actqf->qf_owner))
actqf = NULL;
}
spin_unlock(&dq_list_lock);
return actqf;
}
static void put_quota_format(struct quota_format_type *fmt)
{
module_put(fmt->qf_owner);
}
/*
* Dquot List Management:
* The quota code uses five lists for dquot management: the inuse_list,
* releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array.
* A single dquot structure may be on some of those lists, depending on
* its current state.
*
* All dquots are placed to the end of inuse_list when first created, and this
* list is used for invalidate operation, which must look at every dquot.
*
* When the last reference of a dquot is dropped, the dquot is added to
* releasing_dquots. We'll then queue work item which will call
* synchronize_srcu() and after that perform the final cleanup of all the
* dquots on the list. Each cleaned up dquot is moved to free_dquots list.
* Both releasing_dquots and free_dquots use the dq_free list_head in the dquot
* struct.
*
* Unused and cleaned up dquots are in the free_dquots list and this list is
* searched whenever we need an available dquot. Dquots are removed from the
* list as soon as they are used again and dqstats.free_dquots gives the number
* of dquots on the list. When dquot is invalidated it's completely released
* from memory.
*
* Dirty dquots are added to the dqi_dirty_list of quota_info when mark
* dirtied, and this list is searched when writing dirty dquots back to
* quota file. Note that some filesystems do dirty dquot tracking on their
* own (e.g. in a journal) and thus don't use dqi_dirty_list.
*
* Dquots with a specific identity (device, type and id) are placed on
* one of the dquot_hash[] hash chains. The provides an efficient search
* mechanism to locate a specific dquot.
*/
static LIST_HEAD(inuse_list);
static LIST_HEAD(free_dquots);
static LIST_HEAD(releasing_dquots);
static unsigned int dq_hash_bits, dq_hash_mask;
static struct hlist_head *dquot_hash;
struct dqstats dqstats;
EXPORT_SYMBOL(dqstats);
static qsize_t inode_get_rsv_space(struct inode *inode);
static qsize_t __inode_get_rsv_space(struct inode *inode);
static int __dquot_initialize(struct inode *inode, int type);
static void quota_release_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn);
static inline unsigned int
hashfn(const struct super_block *sb, struct kqid qid)
{
unsigned int id = from_kqid(&init_user_ns, qid);
int type = qid.type;
unsigned long tmp;
tmp = (((unsigned long)sb>>L1_CACHE_SHIFT) ^ id) * (MAXQUOTAS - type);
return (tmp + (tmp >> dq_hash_bits)) & dq_hash_mask;
}
/*
* Following list functions expect dq_list_lock to be held
*/
static inline void insert_dquot_hash(struct dquot *dquot)
{
struct hlist_head *head;
head = dquot_hash + hashfn(dquot->dq_sb, dquot->dq_id);
hlist_add_head(&dquot->dq_hash, head);
}
static inline void remove_dquot_hash(struct dquot *dquot)
{
hlist_del_init(&dquot->dq_hash);
}
static struct dquot *find_dquot(unsigned int hashent, struct super_block *sb,
struct kqid qid)
{
struct dquot *dquot;
hlist_for_each_entry(dquot, dquot_hash+hashent, dq_hash)
if (dquot->dq_sb == sb && qid_eq(dquot->dq_id, qid))
return dquot;
return NULL;
}
/* Add a dquot to the tail of the free list */
static inline void put_dquot_last(struct dquot *dquot)
{
list_add_tail(&dquot->dq_free, &free_dquots);
dqstats_inc(DQST_FREE_DQUOTS);
}
static inline void put_releasing_dquots(struct dquot *dquot)
{
list_add_tail(&dquot->dq_free, &releasing_dquots);
set_bit(DQ_RELEASING_B, &dquot->dq_flags);
}
static inline void remove_free_dquot(struct dquot *dquot)
{
if (list_empty(&dquot->dq_free))
return;
list_del_init(&dquot->dq_free);
if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags))
dqstats_dec(DQST_FREE_DQUOTS);
else
clear_bit(DQ_RELEASING_B, &dquot->dq_flags);
}
static inline void put_inuse(struct dquot *dquot)
{
/* We add to the back of inuse list so we don't have to restart
* when traversing this list and we block */
list_add_tail(&dquot->dq_inuse, &inuse_list);
dqstats_inc(DQST_ALLOC_DQUOTS);
}
static inline void remove_inuse(struct dquot *dquot)
{
dqstats_dec(DQST_ALLOC_DQUOTS);
list_del(&dquot->dq_inuse);
}
/*
* End of list functions needing dq_list_lock
*/
static void wait_on_dquot(struct dquot *dquot)
{
mutex_lock(&dquot->dq_lock);
mutex_unlock(&dquot->dq_lock);
}
static inline int dquot_active(struct dquot *dquot)
{
return test_bit(DQ_ACTIVE_B, &dquot->dq_flags);
}
static inline int dquot_dirty(struct dquot *dquot)
{
return test_bit(DQ_MOD_B, &dquot->dq_flags);
}
static inline int mark_dquot_dirty(struct dquot *dquot)
{
return dquot->dq_sb->dq_op->mark_dirty(dquot);
}
/* Mark dquot dirty in atomic manner, and return it's old dirty flag state */
int dquot_mark_dquot_dirty(struct dquot *dquot)
{
int ret = 1;
if (!dquot_active(dquot))
return 0;
if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY)
return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags);
/* If quota is dirty already, we don't have to acquire dq_list_lock */
if (dquot_dirty(dquot))
return 1;
spin_lock(&dq_list_lock);
if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags)) {
list_add(&dquot->dq_dirty, &sb_dqopt(dquot->dq_sb)->
info[dquot->dq_id.type].dqi_dirty_list);
ret = 0;
}
spin_unlock(&dq_list_lock);
return ret;
}
EXPORT_SYMBOL(dquot_mark_dquot_dirty);
/* Dirtify all the dquots - this can block when journalling */
static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots)
{
int ret, err, cnt;
struct dquot *dquot;
ret = err = 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
if (dquot)
/* Even in case of error we have to continue */
ret = mark_dquot_dirty(dquot);
if (!err && ret < 0)
err = ret;
}
return err;
}
static inline void dqput_all(struct dquot **dquot)
{
unsigned int cnt;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
dqput(dquot[cnt]);
}
static inline int clear_dquot_dirty(struct dquot *dquot)
{
if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY)
return test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags);
spin_lock(&dq_list_lock);
if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) {
spin_unlock(&dq_list_lock);
return 0;
}
list_del_init(&dquot->dq_dirty);
spin_unlock(&dq_list_lock);
return 1;
}
void mark_info_dirty(struct super_block *sb, int type)
{
spin_lock(&dq_data_lock);
sb_dqopt(sb)->info[type].dqi_flags |= DQF_INFO_DIRTY;
spin_unlock(&dq_data_lock);
}
EXPORT_SYMBOL(mark_info_dirty);
/*
* Read dquot from disk and alloc space for it
*/
int dquot_acquire(struct dquot *dquot)
{
int ret = 0, ret2 = 0;
unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
memalloc = memalloc_nofs_save();
if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot);
if (ret < 0)
goto out_iolock;
}
/* Make sure flags update is visible after dquot has been filled */
smp_mb__before_atomic();
set_bit(DQ_READ_B, &dquot->dq_flags);
/* Instantiate dquot if needed */
if (!dquot_active(dquot) && !dquot->dq_off) {
ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
/* Write the info if needed */
if (info_dirty(&dqopt->info[dquot->dq_id.type])) {
ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info(
dquot->dq_sb, dquot->dq_id.type);
}
if (ret < 0)
goto out_iolock;
if (ret2 < 0) {
ret = ret2;
goto out_iolock;
}
}
/*
* Make sure flags update is visible after on-disk struct has been
* allocated. Paired with smp_rmb() in dqget().
*/
smp_mb__before_atomic();
set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_iolock:
memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
EXPORT_SYMBOL(dquot_acquire);
/*
* Write dquot to disk
*/
int dquot_commit(struct dquot *dquot)
{
int ret = 0;
unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
memalloc = memalloc_nofs_save();
if (!clear_dquot_dirty(dquot))
goto out_lock;
/* Inactive dquot can be only if there was error during read/init
* => we have better not writing it */
if (dquot_active(dquot))
ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
else
ret = -EIO;
out_lock:
memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
EXPORT_SYMBOL(dquot_commit);
/*
* Release dquot
*/
int dquot_release(struct dquot *dquot)
{
int ret = 0, ret2 = 0;
unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
memalloc = memalloc_nofs_save();
/* Check whether we are not racing with some other dqget() */
if (dquot_is_busy(dquot))
goto out_dqlock;
if (dqopt->ops[dquot->dq_id.type]->release_dqblk) {
ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot);
/* Write the info */
if (info_dirty(&dqopt->info[dquot->dq_id.type])) {
ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info(
dquot->dq_sb, dquot->dq_id.type);
}
if (ret >= 0)
ret = ret2;
}
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_dqlock:
memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
EXPORT_SYMBOL(dquot_release);
void dquot_destroy(struct dquot *dquot)
{
kmem_cache_free(dquot_cachep, dquot);
}
EXPORT_SYMBOL(dquot_destroy);
static inline void do_destroy_dquot(struct dquot *dquot)
{
dquot->dq_sb->dq_op->destroy_dquot(dquot);
}
/* Invalidate all dquots on the list. Note that this function is called after
* quota is disabled and pointers from inodes removed so there cannot be new
* quota users. There can still be some users of quotas due to inodes being
* just deleted or pruned by prune_icache() (those are not attached to any
* list) or parallel quotactl call. We have to wait for such users.
*/
static void invalidate_dquots(struct super_block *sb, int type)
{
struct dquot *dquot, *tmp;
restart:
flush_delayed_work("a_release_work);
spin_lock(&dq_list_lock);
list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) {
if (dquot->dq_sb != sb)
continue;
if (dquot->dq_id.type != type)
continue;
/* Wait for dquot users */
if (atomic_read(&dquot->dq_count)) {
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
/*
* Once dqput() wakes us up, we know it's time to free
* the dquot.
* IMPORTANT: we rely on the fact that there is always
* at most one process waiting for dquot to free.
* Otherwise dq_count would be > 1 and we would never
* wake up.
*/
wait_event(dquot_ref_wq,
atomic_read(&dquot->dq_count) == 1);
dqput(dquot);
/* At this moment dquot() need not exist (it could be
* reclaimed by prune_dqcache(). Hence we must
* restart. */
goto restart;
}
/*
* The last user already dropped its reference but dquot didn't
* get fully cleaned up yet. Restart the scan which flushes the
* work cleaning up released dquots.
*/
if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) {
spin_unlock(&dq_list_lock);
goto restart;
}
/*
* Quota now has no users and it has been written on last
* dqput()
*/
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
}
spin_unlock(&dq_list_lock);
}
/* Call callback for every active dquot on given filesystem */
int dquot_scan_active(struct super_block *sb,
int (*fn)(struct dquot *dquot, unsigned long priv),
unsigned long priv)
{
struct dquot *dquot, *old_dquot = NULL;
int ret = 0;
WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount));
spin_lock(&dq_list_lock);
list_for_each_entry(dquot, &inuse_list, dq_inuse) {
if (!dquot_active(dquot))
continue;
if (dquot->dq_sb != sb)
continue;
/* Now we have active dquot so we can just increase use count */
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
dqput(old_dquot);
old_dquot = dquot;
/*
* ->release_dquot() can be racing with us. Our reference
* protects us from new calls to it so just wait for any
* outstanding call and recheck the DQ_ACTIVE_B after that.
*/
wait_on_dquot(dquot);
if (dquot_active(dquot)) {
ret = fn(dquot, priv);
if (ret < 0)
goto out;
}
spin_lock(&dq_list_lock);
/* We are safe to continue now because our dquot could not
* be moved out of the inuse list while we hold the reference */
}
spin_unlock(&dq_list_lock);
out:
dqput(old_dquot);
return ret;
}
EXPORT_SYMBOL(dquot_scan_active);
static inline int dquot_write_dquot(struct dquot *dquot)
{
int ret = dquot->dq_sb->dq_op->write_dquot(dquot);
if (ret < 0) {
quota_error(dquot->dq_sb, "Can't write quota structure "
"(error %d). Quota may get out of sync!", ret);
/* Clear dirty bit anyway to avoid infinite loop. */
clear_dquot_dirty(dquot);
}
return ret;
}
/* Write all dquot structures to quota files */
int dquot_writeback_dquots(struct super_block *sb, int type)
{
struct list_head dirty;
struct dquot *dquot;
struct quota_info *dqopt = sb_dqopt(sb);
int cnt;
int err, ret = 0;
WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount));
flush_delayed_work("a_release_work);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_active(sb, cnt))
continue;
spin_lock(&dq_list_lock);
/* Move list away to avoid livelock. */
list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty);
while (!list_empty(&dirty)) {
dquot = list_first_entry(&dirty, struct dquot,
dq_dirty);
WARN_ON(!dquot_active(dquot));
/* If the dquot is releasing we should not touch it */
if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) {
spin_unlock(&dq_list_lock);
flush_delayed_work("a_release_work);
spin_lock(&dq_list_lock);
continue;
}
/* Now we have active dquot from which someone is
* holding reference so we can safely just increase
* use count */
dqgrab(dquot);
spin_unlock(&dq_list_lock);
err = dquot_write_dquot(dquot);
if (err && !ret)
ret = err;
dqput(dquot);
spin_lock(&dq_list_lock);
}
spin_unlock(&dq_list_lock);
}
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt)
&& info_dirty(&dqopt->info[cnt]))
sb->dq_op->write_info(sb, cnt);
dqstats_inc(DQST_SYNCS);
return ret;
}
EXPORT_SYMBOL(dquot_writeback_dquots);
/* Write all dquot structures to disk and make them visible from userspace */
int dquot_quota_sync(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
int cnt;
int ret;
ret = dquot_writeback_dquots(sb, type);
if (ret)
return ret;
if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
return 0;
/* This is not very clever (and fast) but currently I don't know about
* any other simple way of getting quota data to disk and we must get
* them there for userspace to be visible... */
if (sb->s_op->sync_fs) {
ret = sb->s_op->sync_fs(sb, 1);
if (ret)
return ret;
}
ret = sync_blockdev(sb->s_bdev);
if (ret)
return ret;
/*
* Now when everything is written we can discard the pagecache so
* that userspace sees the changes.
*/
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_active(sb, cnt))
continue;
inode_lock(dqopt->files[cnt]);
truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
inode_unlock(dqopt->files[cnt]);
}
return 0;
}
EXPORT_SYMBOL(dquot_quota_sync);
static unsigned long
dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct dquot *dquot;
unsigned long freed = 0;
spin_lock(&dq_list_lock);
while (!list_empty(&free_dquots) && sc->nr_to_scan) {
dquot = list_first_entry(&free_dquots, struct dquot, dq_free);
remove_dquot_hash(dquot);
remove_free_dquot(dquot);
remove_inuse(dquot);
do_destroy_dquot(dquot);
sc->nr_to_scan--;
freed++;
}
spin_unlock(&dq_list_lock);
return freed;
}
static unsigned long
dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
return vfs_pressure_ratio(
percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS]));
}
/*
* Safely release dquot and put reference to dquot.
*/
static void quota_release_workfn(struct work_struct *work)
{
struct dquot *dquot;
struct list_head rls_head;
spin_lock(&dq_list_lock);
/* Exchange the list head to avoid livelock. */
list_replace_init(&releasing_dquots, &rls_head);
spin_unlock(&dq_list_lock);
synchronize_srcu(&dquot_srcu);
restart:
spin_lock(&dq_list_lock);
while (!list_empty(&rls_head)) {
dquot = list_first_entry(&rls_head, struct dquot, dq_free);
WARN_ON_ONCE(atomic_read(&dquot->dq_count));
/*
* Note that DQ_RELEASING_B protects us from racing with
* invalidate_dquots() calls so we are safe to work with the
* dquot even after we drop dq_list_lock.
*/
if (dquot_dirty(dquot)) {
spin_unlock(&dq_list_lock);
/* Commit dquot before releasing */
dquot_write_dquot(dquot);
goto restart;
}
if (dquot_active(dquot)) {
spin_unlock(&dq_list_lock);
dquot->dq_sb->dq_op->release_dquot(dquot);
goto restart;
}
/* Dquot is inactive and clean, now move it to free list */
remove_free_dquot(dquot);
put_dquot_last(dquot);
}
spin_unlock(&dq_list_lock);
}
/*
* Put reference to dquot
*/
void dqput(struct dquot *dquot)
{
if (!dquot)
return;
#ifdef CONFIG_QUOTA_DEBUG
if (!atomic_read(&dquot->dq_count)) {
quota_error(dquot->dq_sb, "trying to free free dquot of %s %d",
quotatypes[dquot->dq_id.type],
from_kqid(&init_user_ns, dquot->dq_id));
BUG();
}
#endif
dqstats_inc(DQST_DROPS);
spin_lock(&dq_list_lock);
if (atomic_read(&dquot->dq_count) > 1) {
/* We have more than one user... nothing to do */
atomic_dec(&dquot->dq_count);
/* Releasing dquot during quotaoff phase? */
if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_id.type) &&
atomic_read(&dquot->dq_count) == 1)
wake_up(&dquot_ref_wq);
spin_unlock(&dq_list_lock);
return;
}
/* Need to release dquot? */
WARN_ON_ONCE(!list_empty(&dquot->dq_free));
put_releasing_dquots(dquot);
atomic_dec(&dquot->dq_count);
spin_unlock(&dq_list_lock);
queue_delayed_work(system_unbound_wq, "a_release_work, 1);
}
EXPORT_SYMBOL(dqput);
struct dquot *dquot_alloc(struct super_block *sb, int type)
{
return kmem_cache_zalloc(dquot_cachep, GFP_NOFS);
}
EXPORT_SYMBOL(dquot_alloc);
static struct dquot *get_empty_dquot(struct super_block *sb, int type)
{
struct dquot *dquot;
dquot = sb->dq_op->alloc_dquot(sb, type);
if(!dquot)
return NULL;
mutex_init(&dquot->dq_lock);
INIT_LIST_HEAD(&dquot->dq_free);
INIT_LIST_HEAD(&dquot->dq_inuse);
INIT_HLIST_NODE(&dquot->dq_hash);
INIT_LIST_HEAD(&dquot->dq_dirty);
dquot->dq_sb = sb;
dquot->dq_id = make_kqid_invalid(type);
atomic_set(&dquot->dq_count, 1);
spin_lock_init(&dquot->dq_dqb_lock);
return dquot;
}
/*
* Get reference to dquot
*
* Locking is slightly tricky here. We are guarded from parallel quotaoff()
* destroying our dquot by:
* a) checking for quota flags under dq_list_lock and
* b) getting a reference to dquot before we release dq_list_lock
*/
struct dquot *dqget(struct super_block *sb, struct kqid qid)
{
unsigned int hashent = hashfn(sb, qid);
struct dquot *dquot, *empty = NULL;
if (!qid_has_mapping(sb->s_user_ns, qid))
return ERR_PTR(-EINVAL);
if (!sb_has_quota_active(sb, qid.type))
return ERR_PTR(-ESRCH);
we_slept:
spin_lock(&dq_list_lock);
spin_lock(&dq_state_lock);
if (!sb_has_quota_active(sb, qid.type)) {
spin_unlock(&dq_state_lock);
spin_unlock(&dq_list_lock);
dquot = ERR_PTR(-ESRCH);
goto out;
}
spin_unlock(&dq_state_lock);
dquot = find_dquot(hashent, sb, qid);
if (!dquot) {
if (!empty) {
spin_unlock(&dq_list_lock);
empty = get_empty_dquot(sb, qid.type);
if (!empty)
schedule(); /* Try to wait for a moment... */
goto we_slept;
}
dquot = empty;
empty = NULL;
dquot->dq_id = qid;
/* all dquots go on the inuse_list */
put_inuse(dquot);
/* hash it first so it can be found */
insert_dquot_hash(dquot);
spin_unlock(&dq_list_lock);
dqstats_inc(DQST_LOOKUPS);
} else {
if (!atomic_read(&dquot->dq_count))
remove_free_dquot(dquot);
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
dqstats_inc(DQST_CACHE_HITS);
dqstats_inc(DQST_LOOKUPS);
}
/* Wait for dq_lock - after this we know that either dquot_release() is
* already finished or it will be canceled due to dq_count > 0 test */
wait_on_dquot(dquot);
/* Read the dquot / allocate space in quota file */
if (!dquot_active(dquot)) {
int err;
err = sb->dq_op->acquire_dquot(dquot);
if (err < 0) {
dqput(dquot);
dquot = ERR_PTR(err);
goto out;
}
}
/*
* Make sure following reads see filled structure - paired with
* smp_mb__before_atomic() in dquot_acquire().
*/
smp_rmb();
/* Has somebody invalidated entry under us? */
WARN_ON_ONCE(hlist_unhashed(&dquot->dq_hash));
out:
if (empty)
do_destroy_dquot(empty);
return dquot;
}
EXPORT_SYMBOL(dqget);
static inline struct dquot __rcu **i_dquot(struct inode *inode)
{
return inode->i_sb->s_op->get_dquots(inode);
}
static int dqinit_needed(struct inode *inode, int type)
{
struct dquot __rcu * const *dquots;
int cnt;
if (IS_NOQUOTA(inode))
return 0;
dquots = i_dquot(inode);
if (type != -1)
return !dquots[type];
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if (!dquots[cnt])
return 1;
return 0;
}
/* This routine is guarded by s_umount semaphore */
static int add_dquot_ref(struct super_block *sb, int type)
{
struct inode *inode, *old_inode = NULL;
#ifdef CONFIG_QUOTA_DEBUG
int reserved = 0;
#endif
int err = 0;
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
!atomic_read(&inode->i_writecount) ||
!dqinit_needed(inode, type)) {
spin_unlock(&inode->i_lock);
continue;
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_list_lock);
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
reserved = 1;
#endif
iput(old_inode);
err = __dquot_initialize(inode, type);
if (err) {
iput(inode);
goto out;
}
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
* s_inode_list_lock. We cannot iput the inode now as we can be
* holding the last reference and we cannot iput it under
* s_inode_list_lock. So we keep the reference and iput it
* later.
*/
old_inode = inode;
cond_resched();
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&sb->s_inode_list_lock);
iput(old_inode);
out:
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
quota_error(sb, "Writes happened before quota was turned on "
"thus quota information is probably inconsistent. "
"Please run quotacheck(8)");
}
#endif
return err;
}
static void remove_dquot_ref(struct super_block *sb, int type)
{
struct inode *inode;
#ifdef CONFIG_QUOTA_DEBUG
int reserved = 0;
#endif
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
/*
* We have to scan also I_NEW inodes because they can already
* have quota pointer initialized. Luckily, we need to touch
* only quota pointers and these have separate locking
* (dq_data_lock).
*/
spin_lock(&dq_data_lock);
if (!IS_NOQUOTA(inode)) {
struct dquot __rcu **dquots = i_dquot(inode);
struct dquot *dquot = srcu_dereference_check(
dquots[type], &dquot_srcu,
lockdep_is_held(&dq_data_lock));
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
reserved = 1;
#endif
rcu_assign_pointer(dquots[type], NULL);
if (dquot)
dqput(dquot);
}
spin_unlock(&dq_data_lock);
}
spin_unlock(&sb->s_inode_list_lock);
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
printk(KERN_WARNING "VFS (%s): Writes happened after quota"
" was disabled thus quota information is probably "
"inconsistent. Please run quotacheck(8).\n", sb->s_id);
}
#endif
}
/* Gather all references from inodes and drop them */
static void drop_dquot_ref(struct super_block *sb, int type)
{
if (sb->dq_op)
remove_dquot_ref(sb, type);
}
static inline
void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
{
if (dquot->dq_dqb.dqb_rsvspace >= number)
dquot->dq_dqb.dqb_rsvspace -= number;
else {
WARN_ON_ONCE(1);
dquot->dq_dqb.dqb_rsvspace = 0;
}
if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <=
dquot->dq_dqb.dqb_bsoftlimit)
dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags);
}
static void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
{
if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
dquot->dq_dqb.dqb_curinodes >= number)
dquot->dq_dqb.dqb_curinodes -= number;
else
dquot->dq_dqb.dqb_curinodes = 0; if (dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit) dquot->dq_dqb.dqb_itime = (time64_t) 0; clear_bit(DQ_INODES_B, &dquot->dq_flags);
}
static void dquot_decr_space(struct dquot *dquot, qsize_t number)
{
if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
dquot->dq_dqb.dqb_curspace >= number)
dquot->dq_dqb.dqb_curspace -= number;
else
dquot->dq_dqb.dqb_curspace = 0; if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <=
dquot->dq_dqb.dqb_bsoftlimit)
dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags);
}
struct dquot_warn {
struct super_block *w_sb;
struct kqid w_dq_id;
short w_type;
};
static int warning_issued(struct dquot *dquot, const int warntype)
{
int flag = (warntype == QUOTA_NL_BHARDWARN ||
warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B :
((warntype == QUOTA_NL_IHARDWARN ||
warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0);
if (!flag)
return 0;
return test_and_set_bit(flag, &dquot->dq_flags);
}
#ifdef CONFIG_PRINT_QUOTA_WARNING
static int flag_print_warnings = 1;
static int need_print_warning(struct dquot_warn *warn)
{
if (!flag_print_warnings)
return 0;
switch (warn->w_dq_id.type) {
case USRQUOTA:
return uid_eq(current_fsuid(), warn->w_dq_id.uid);
case GRPQUOTA:
return in_group_p(warn->w_dq_id.gid);
case PRJQUOTA:
return 1;
}
return 0;
}
/* Print warning to user which exceeded quota */
static void print_warning(struct dquot_warn *warn)
{
char *msg = NULL;
struct tty_struct *tty;
int warntype = warn->w_type;
if (warntype == QUOTA_NL_IHARDBELOW ||
warntype == QUOTA_NL_ISOFTBELOW ||
warntype == QUOTA_NL_BHARDBELOW ||
warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(warn))
return;
tty = get_current_tty();
if (!tty)
return;
tty_write_message(tty, warn->w_sb->s_id);
if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN)
tty_write_message(tty, ": warning, ");
else
tty_write_message(tty, ": write failed, ");
tty_write_message(tty, quotatypes[warn->w_dq_id.type]);
switch (warntype) {
case QUOTA_NL_IHARDWARN:
msg = " file limit reached.\r\n";
break;
case QUOTA_NL_ISOFTLONGWARN:
msg = " file quota exceeded too long.\r\n";
break;
case QUOTA_NL_ISOFTWARN:
msg = " file quota exceeded.\r\n";
break;
case QUOTA_NL_BHARDWARN:
msg = " block limit reached.\r\n";
break;
case QUOTA_NL_BSOFTLONGWARN:
msg = " block quota exceeded too long.\r\n";
break;
case QUOTA_NL_BSOFTWARN:
msg = " block quota exceeded.\r\n";
break;
}
tty_write_message(tty, msg);
tty_kref_put(tty);
}
#endif
static void prepare_warning(struct dquot_warn *warn, struct dquot *dquot,
int warntype)
{
if (warning_issued(dquot, warntype))
return;
warn->w_type = warntype;
warn->w_sb = dquot->dq_sb;
warn->w_dq_id = dquot->dq_id;
}
/*
* Write warnings to the console and send warning messages over netlink.
*
* Note that this function can call into tty and networking code.
*/
static void flush_warnings(struct dquot_warn *warn)
{
int i;
for (i = 0; i < MAXQUOTAS; i++) {
if (warn[i].w_type == QUOTA_NL_NOWARN)
continue;
#ifdef CONFIG_PRINT_QUOTA_WARNING
print_warning(&warn[i]);
#endif
quota_send_warning(warn[i].w_dq_id,
warn[i].w_sb->s_dev, warn[i].w_type);
}
}
static int ignore_hardlimit(struct dquot *dquot)
{
struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];
return capable(CAP_SYS_RESOURCE) &&
(info->dqi_format->qf_fmt_id != QFMT_VFS_OLD ||
!(info->dqi_flags & DQF_ROOT_SQUASH));
}
static int dquot_add_inodes(struct dquot *dquot, qsize_t inodes,
struct dquot_warn *warn)
{
qsize_t newinodes;
int ret = 0;
spin_lock(&dquot->dq_dqb_lock);
newinodes = dquot->dq_dqb.dqb_curinodes + inodes;
if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type) ||
test_bit(DQ_FAKE_B, &dquot->dq_flags))
goto add;
if (dquot->dq_dqb.dqb_ihardlimit &&
newinodes > dquot->dq_dqb.dqb_ihardlimit &&
!ignore_hardlimit(dquot)) {
prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN);
ret = -EDQUOT;
goto out;
}
if (dquot->dq_dqb.dqb_isoftlimit &&
newinodes > dquot->dq_dqb.dqb_isoftlimit &&
dquot->dq_dqb.dqb_itime &&
ktime_get_real_seconds() >= dquot->dq_dqb.dqb_itime &&
!ignore_hardlimit(dquot)) {
prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN);
ret = -EDQUOT;
goto out;
}
if (dquot->dq_dqb.dqb_isoftlimit &&
newinodes > dquot->dq_dqb.dqb_isoftlimit &&
dquot->dq_dqb.dqb_itime == 0) {
prepare_warning(warn, dquot, QUOTA_NL_ISOFTWARN);
dquot->dq_dqb.dqb_itime = ktime_get_real_seconds() +
sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type].dqi_igrace;
}
add:
dquot->dq_dqb.dqb_curinodes = newinodes;
out:
spin_unlock(&dquot->dq_dqb_lock);
return ret;
}
static int dquot_add_space(struct dquot *dquot, qsize_t space,
qsize_t rsv_space, unsigned int flags,
struct dquot_warn *warn)
{
qsize_t tspace;
struct super_block *sb = dquot->dq_sb;
int ret = 0;
spin_lock(&dquot->dq_dqb_lock);
if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) ||
test_bit(DQ_FAKE_B, &dquot->dq_flags))
goto finish;
tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace
+ space + rsv_space;
if (dquot->dq_dqb.dqb_bhardlimit &&
tspace > dquot->dq_dqb.dqb_bhardlimit &&
!ignore_hardlimit(dquot)) {
if (flags & DQUOT_SPACE_WARN)
prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN);
ret = -EDQUOT;
goto finish;
}
if (dquot->dq_dqb.dqb_bsoftlimit &&
tspace > dquot->dq_dqb.dqb_bsoftlimit &&
dquot->dq_dqb.dqb_btime &&
ktime_get_real_seconds() >= dquot->dq_dqb.dqb_btime &&
!ignore_hardlimit(dquot)) {
if (flags & DQUOT_SPACE_WARN)
prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN);
ret = -EDQUOT;
goto finish;
}
if (dquot->dq_dqb.dqb_bsoftlimit &&
tspace > dquot->dq_dqb.dqb_bsoftlimit &&
dquot->dq_dqb.dqb_btime == 0) {
if (flags & DQUOT_SPACE_WARN) {
prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN);
dquot->dq_dqb.dqb_btime = ktime_get_real_seconds() +
sb_dqopt(sb)->info[dquot->dq_id.type].dqi_bgrace;
} else {
/*
* We don't allow preallocation to exceed softlimit so exceeding will
* be always printed
*/
ret = -EDQUOT;
goto finish;
}
}
finish:
/*
* We have to be careful and go through warning generation & grace time
* setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it
* only here...
*/
if (flags & DQUOT_SPACE_NOFAIL)
ret = 0;
if (!ret) {
dquot->dq_dqb.dqb_rsvspace += rsv_space;
dquot->dq_dqb.dqb_curspace += space;
}
spin_unlock(&dquot->dq_dqb_lock);
return ret;
}
static int info_idq_free(struct dquot *dquot, qsize_t inodes)
{
qsize_t newinodes;
if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit ||
!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type))
return QUOTA_NL_NOWARN;
newinodes = dquot->dq_dqb.dqb_curinodes - inodes;
if (newinodes <= dquot->dq_dqb.dqb_isoftlimit)
return QUOTA_NL_ISOFTBELOW;
if (dquot->dq_dqb.dqb_curinodes >= dquot->dq_dqb.dqb_ihardlimit &&
newinodes < dquot->dq_dqb.dqb_ihardlimit)
return QUOTA_NL_IHARDBELOW;
return QUOTA_NL_NOWARN;
}
static int info_bdq_free(struct dquot *dquot, qsize_t space)
{
qsize_t tspace;
tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace;
if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
tspace <= dquot->dq_dqb.dqb_bsoftlimit)
return QUOTA_NL_NOWARN;
if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit)
return QUOTA_NL_BSOFTBELOW;
if (tspace >= dquot->dq_dqb.dqb_bhardlimit &&
tspace - space < dquot->dq_dqb.dqb_bhardlimit)
return QUOTA_NL_BHARDBELOW;
return QUOTA_NL_NOWARN;
}
static int inode_quota_active(const struct inode *inode)
{
struct super_block *sb = inode->i_sb;
if (IS_NOQUOTA(inode))
return 0;
return sb_any_quota_loaded(sb) & ~sb_any_quota_suspended(sb);
}
/*
* Initialize quota pointers in inode
*
* It is better to call this function outside of any transaction as it
* might need a lot of space in journal for dquot structure allocation.
*/
static int __dquot_initialize(struct inode *inode, int type)
{
int cnt, init_needed = 0;
struct dquot __rcu **dquots;
struct dquot *got[MAXQUOTAS] = {};
struct super_block *sb = inode->i_sb;
qsize_t rsv;
int ret = 0;
if (!inode_quota_active(inode))
return 0;
dquots = i_dquot(inode);
/* First get references to structures we might need. */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
struct kqid qid;
kprojid_t projid;
int rc;
struct dquot *dquot;
if (type != -1 && cnt != type)
continue;
/*
* The i_dquot should have been initialized in most cases,
* we check it without locking here to avoid unnecessary
* dqget()/dqput() calls.
*/
if (dquots[cnt])
continue;
if (!sb_has_quota_active(sb, cnt))
continue;
init_needed = 1;
switch (cnt) {
case USRQUOTA:
qid = make_kqid_uid(inode->i_uid);
break;
case GRPQUOTA:
qid = make_kqid_gid(inode->i_gid);
break;
case PRJQUOTA:
rc = inode->i_sb->dq_op->get_projid(inode, &projid);
if (rc)
continue;
qid = make_kqid_projid(projid);
break;
}
dquot = dqget(sb, qid);
if (IS_ERR(dquot)) {
/* We raced with somebody turning quotas off... */
if (PTR_ERR(dquot) != -ESRCH) {
ret = PTR_ERR(dquot);
goto out_put;
}
dquot = NULL;
}
got[cnt] = dquot;
}
/* All required i_dquot has been initialized */
if (!init_needed)
return 0;
spin_lock(&dq_data_lock);
if (IS_NOQUOTA(inode))
goto out_lock;
for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type)
continue;
/* Avoid races with quotaoff() */
if (!sb_has_quota_active(sb, cnt))
continue;
/* We could race with quotaon or dqget() could have failed */
if (!got[cnt])
continue;
if (!dquots[cnt]) {
rcu_assign_pointer(dquots[cnt], got[cnt]);
got[cnt] = NULL;
/*
* Make quota reservation system happy if someone
* did a write before quota was turned on
*/
rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { struct dquot *dquot = srcu_dereference_check(
dquots[cnt], &dquot_srcu,
lockdep_is_held(&dq_data_lock));
spin_lock(&inode->i_lock);
/* Get reservation again under proper lock */
rsv = __inode_get_rsv_space(inode);
spin_lock(&dquot->dq_dqb_lock);
dquot->dq_dqb.dqb_rsvspace += rsv;
spin_unlock(&dquot->dq_dqb_lock);
spin_unlock(&inode->i_lock);
}
}
}
out_lock:
spin_unlock(&dq_data_lock);
out_put:
/* Drop unused references */
dqput_all(got);
return ret;
}
int dquot_initialize(struct inode *inode)
{
return __dquot_initialize(inode, -1);
}
EXPORT_SYMBOL(dquot_initialize);
bool dquot_initialize_needed(struct inode *inode)
{
struct dquot __rcu **dquots;
int i;
if (!inode_quota_active(inode))
return false;
dquots = i_dquot(inode);
for (i = 0; i < MAXQUOTAS; i++)
if (!dquots[i] && sb_has_quota_active(inode->i_sb, i))
return true;
return false;
}
EXPORT_SYMBOL(dquot_initialize_needed);
/*
* Release all quotas referenced by inode.
*
* This function only be called on inode free or converting
* a file to quota file, no other users for the i_dquot in
* both cases, so we needn't call synchronize_srcu() after
* clearing i_dquot.
*/
static void __dquot_drop(struct inode *inode)
{
int cnt;
struct dquot __rcu **dquots = i_dquot(inode);
struct dquot *put[MAXQUOTAS];
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu,
lockdep_is_held(&dq_data_lock));
rcu_assign_pointer(dquots[cnt], NULL);
}
spin_unlock(&dq_data_lock);
dqput_all(put);
}
void dquot_drop(struct inode *inode)
{
struct dquot __rcu * const *dquots;
int cnt;
if (IS_NOQUOTA(inode))
return;
/*
* Test before calling to rule out calls from proc and such
* where we are not allowed to block. Note that this is
* actually reliable test even without the lock - the caller
* must assure that nobody can come after the DQUOT_DROP and
* add quota pointers back anyway.
*/
dquots = i_dquot(inode);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (dquots[cnt])
break;
}
if (cnt < MAXQUOTAS)
__dquot_drop(inode);
}
EXPORT_SYMBOL(dquot_drop);
/*
* inode_reserved_space is managed internally by quota, and protected by
* i_lock similar to i_blocks+i_bytes.
*/
static qsize_t *inode_reserved_space(struct inode * inode)
{
/* Filesystem must explicitly define it's own method in order to use
* quota reservation interface */
BUG_ON(!inode->i_sb->dq_op->get_reserved_space); return inode->i_sb->dq_op->get_reserved_space(inode);
}
static qsize_t __inode_get_rsv_space(struct inode *inode)
{
if (!inode->i_sb->dq_op->get_reserved_space)
return 0;
return *inode_reserved_space(inode);
}
static qsize_t inode_get_rsv_space(struct inode *inode)
{
qsize_t ret;
if (!inode->i_sb->dq_op->get_reserved_space)
return 0;
spin_lock(&inode->i_lock);
ret = __inode_get_rsv_space(inode);
spin_unlock(&inode->i_lock);
return ret;
}
/*
* This functions updates i_blocks+i_bytes fields and quota information
* (together with appropriate checks).
*
* NOTE: We absolutely rely on the fact that caller dirties the inode
* (usually helpers in quotaops.h care about this) and holds a handle for
* the current transaction so that dquot write and inode write go into the
* same transaction.
*/
/*
* This operation can block, but only after everything is updated
*/
int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
{
int cnt, ret = 0, index;
struct dquot_warn warn[MAXQUOTAS];
int reserve = flags & DQUOT_SPACE_RESERVE;
struct dquot __rcu **dquots;
struct dquot *dquot;
if (!inode_quota_active(inode)) {
if (reserve) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) += number;
spin_unlock(&inode->i_lock);
} else {
inode_add_bytes(inode, number);
}
goto out;
}
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
warn[cnt].w_type = QUOTA_NL_NOWARN;
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
if (reserve) {
ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]);
} else {
ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]);
}
if (ret) {
/* Back out changes we already did */
for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
spin_lock(&dquot->dq_dqb_lock);
if (reserve)
dquot_free_reserved_space(dquot, number);
else
dquot_decr_space(dquot, number);
spin_unlock(&dquot->dq_dqb_lock);
}
spin_unlock(&inode->i_lock);
goto out_flush_warn;
}
}
if (reserve)
*inode_reserved_space(inode) += number;
else
__inode_add_bytes(inode, number);
spin_unlock(&inode->i_lock);
if (reserve)
goto out_flush_warn;
ret = mark_all_dquot_dirty(dquots);
out_flush_warn:
srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn);
out:
return ret;
}
EXPORT_SYMBOL(__dquot_alloc_space);
/*
* This operation can block, but only after everything is updated
*/
int dquot_alloc_inode(struct inode *inode)
{
int cnt, ret = 0, index;
struct dquot_warn warn[MAXQUOTAS];
struct dquot __rcu * const *dquots;
struct dquot *dquot;
if (!inode_quota_active(inode))
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
warn[cnt].w_type = QUOTA_NL_NOWARN;
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
ret = dquot_add_inodes(dquot, 1, &warn[cnt]);
if (ret) { for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
/* Back out changes we already did */
spin_lock(&dquot->dq_dqb_lock);
dquot_decr_inodes(dquot, 1);
spin_unlock(&dquot->dq_dqb_lock);
}
goto warn_put_all;
}
}
warn_put_all:
spin_unlock(&inode->i_lock);
if (ret == 0)
ret = mark_all_dquot_dirty(dquots);
srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn);
return ret;
}
EXPORT_SYMBOL(dquot_alloc_inode);
/*
* Convert in-memory reserved quotas to real consumed quotas
*/
void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
{
struct dquot __rcu **dquots;
struct dquot *dquot;
int cnt, index;
if (!inode_quota_active(inode)) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) -= number;
__inode_add_bytes(inode, number);
spin_unlock(&inode->i_lock);
return;
}
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
/* Claim reserved quotas to allocated quotas */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
if (dquot) {
spin_lock(&dquot->dq_dqb_lock);
if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number))
number = dquot->dq_dqb.dqb_rsvspace;
dquot->dq_dqb.dqb_curspace += number;
dquot->dq_dqb.dqb_rsvspace -= number;
spin_unlock(&dquot->dq_dqb_lock);
}
}
/* Update inode bytes */
*inode_reserved_space(inode) -= number;
__inode_add_bytes(inode, number);
spin_unlock(&inode->i_lock);
mark_all_dquot_dirty(dquots);
srcu_read_unlock(&dquot_srcu, index);
}
EXPORT_SYMBOL(dquot_claim_space_nodirty);
/*
* Convert allocated space back to in-memory reserved quotas
*/
void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
{
struct dquot __rcu **dquots;
struct dquot *dquot;
int cnt, index;
if (!inode_quota_active(inode)) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) += number;
__inode_sub_bytes(inode, number);
spin_unlock(&inode->i_lock);
return;
}
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
/* Claim reserved quotas to allocated quotas */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
if (dquot) {
spin_lock(&dquot->dq_dqb_lock);
if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
number = dquot->dq_dqb.dqb_curspace;
dquot->dq_dqb.dqb_rsvspace += number;
dquot->dq_dqb.dqb_curspace -= number;
spin_unlock(&dquot->dq_dqb_lock);
}
}
/* Update inode bytes */
*inode_reserved_space(inode) += number;
__inode_sub_bytes(inode, number);
spin_unlock(&inode->i_lock);
mark_all_dquot_dirty(dquots);
srcu_read_unlock(&dquot_srcu, index);
}
EXPORT_SYMBOL(dquot_reclaim_space_nodirty);
/*
* This operation can block, but only after everything is updated
*/
void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
{
unsigned int cnt;
struct dquot_warn warn[MAXQUOTAS];
struct dquot __rcu **dquots;
struct dquot *dquot;
int reserve = flags & DQUOT_SPACE_RESERVE, index;
if (!inode_quota_active(inode)) {
if (reserve) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) -= number;
spin_unlock(&inode->i_lock);
} else {
inode_sub_bytes(inode, number);
}
return;
}
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
int wtype;
warn[cnt].w_type = QUOTA_NL_NOWARN;
dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
spin_lock(&dquot->dq_dqb_lock);
wtype = info_bdq_free(dquot, number);
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn[cnt], dquot, wtype);
if (reserve)
dquot_free_reserved_space(dquot, number);
else
dquot_decr_space(dquot, number);
spin_unlock(&dquot->dq_dqb_lock);
}
if (reserve)
*inode_reserved_space(inode) -= number;
else
__inode_sub_bytes(inode, number);
spin_unlock(&inode->i_lock);
if (reserve)
goto out_unlock;
mark_all_dquot_dirty(dquots);
out_unlock:
srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn);
}
EXPORT_SYMBOL(__dquot_free_space);
/*
* This operation can block, but only after everything is updated
*/
void dquot_free_inode(struct inode *inode)
{
unsigned int cnt;
struct dquot_warn warn[MAXQUOTAS];
struct dquot __rcu * const *dquots;
struct dquot *dquot;
int index;
if (!inode_quota_active(inode))
return;
dquots = i_dquot(inode);
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
int wtype;
warn[cnt].w_type = QUOTA_NL_NOWARN;
dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot)
continue;
spin_lock(&dquot->dq_dqb_lock);
wtype = info_idq_free(dquot, 1);
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn[cnt], dquot, wtype);
dquot_decr_inodes(dquot, 1);
spin_unlock(&dquot->dq_dqb_lock);
}
spin_unlock(&inode->i_lock);
mark_all_dquot_dirty(dquots);
srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn);
}
EXPORT_SYMBOL(dquot_free_inode);
/*
* Transfer the number of inode and blocks from one diskquota to an other.
* On success, dquot references in transfer_to are consumed and references
* to original dquots that need to be released are placed there. On failure,
* references are kept untouched.
*
* This operation can block, but only after everything is updated
* A transaction must be started when entering this function.
*
* We are holding reference on transfer_from & transfer_to, no need to
* protect them by srcu_read_lock().
*/
int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
{
qsize_t cur_space;
qsize_t rsv_space = 0;
qsize_t inode_usage = 1;
struct dquot __rcu **dquots;
struct dquot *transfer_from[MAXQUOTAS] = {};
int cnt, index, ret = 0, err;
char is_valid[MAXQUOTAS] = {};
struct dquot_warn warn_to[MAXQUOTAS];
struct dquot_warn warn_from_inodes[MAXQUOTAS];
struct dquot_warn warn_from_space[MAXQUOTAS];
if (IS_NOQUOTA(inode))
return 0;
if (inode->i_sb->dq_op->get_inode_usage) {
ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage);
if (ret)
return ret;
}
/* Initialize the arrays */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
warn_to[cnt].w_type = QUOTA_NL_NOWARN;
warn_from_inodes[cnt].w_type = QUOTA_NL_NOWARN;
warn_from_space[cnt].w_type = QUOTA_NL_NOWARN;
}
spin_lock(&dq_data_lock);
spin_lock(&inode->i_lock);
if (IS_NOQUOTA(inode)) { /* File without quota accounting? */
spin_unlock(&inode->i_lock);
spin_unlock(&dq_data_lock);
return 0;
}
cur_space = __inode_get_bytes(inode);
rsv_space = __inode_get_rsv_space(inode);
dquots = i_dquot(inode);
/*
* Build the transfer_from list, check limits, and update usage in
* the target structures.
*/
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
/*
* Skip changes for same uid or gid or for turned off quota-type.
*/
if (!transfer_to[cnt])
continue;
/* Avoid races with quotaoff() */
if (!sb_has_quota_active(inode->i_sb, cnt))
continue;
is_valid[cnt] = 1;
transfer_from[cnt] = srcu_dereference_check(dquots[cnt],
&dquot_srcu, lockdep_is_held(&dq_data_lock));
ret = dquot_add_inodes(transfer_to[cnt], inode_usage,
&warn_to[cnt]);
if (ret)
goto over_quota;
ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space,
DQUOT_SPACE_WARN, &warn_to[cnt]);
if (ret) {
spin_lock(&transfer_to[cnt]->dq_dqb_lock);
dquot_decr_inodes(transfer_to[cnt], inode_usage);
spin_unlock(&transfer_to[cnt]->dq_dqb_lock);
goto over_quota;
}
}
/* Decrease usage for source structures and update quota pointers */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (!is_valid[cnt])
continue;
/* Due to IO error we might not have transfer_from[] structure */
if (transfer_from[cnt]) {
int wtype;
spin_lock(&transfer_from[cnt]->dq_dqb_lock);
wtype = info_idq_free(transfer_from[cnt], inode_usage);
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn_from_inodes[cnt],
transfer_from[cnt], wtype);
wtype = info_bdq_free(transfer_from[cnt],
cur_space + rsv_space);
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn_from_space[cnt],
transfer_from[cnt], wtype);
dquot_decr_inodes(transfer_from[cnt], inode_usage);
dquot_decr_space(transfer_from[cnt], cur_space);
dquot_free_reserved_space(transfer_from[cnt],
rsv_space);
spin_unlock(&transfer_from[cnt]->dq_dqb_lock);
}
rcu_assign_pointer(dquots[cnt], transfer_to[cnt]);
}
spin_unlock(&inode->i_lock);
spin_unlock(&dq_data_lock);
/*
* These arrays are local and we hold dquot references so we don't need
* the srcu protection but still take dquot_srcu to avoid warning in
* mark_all_dquot_dirty().
*/
index = srcu_read_lock(&dquot_srcu);
err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_from);
if (err < 0)
ret = err;
err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_to);
if (err < 0)
ret = err;
srcu_read_unlock(&dquot_srcu, index);
flush_warnings(warn_to);
flush_warnings(warn_from_inodes);
flush_warnings(warn_from_space);
/* Pass back references to put */
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if (is_valid[cnt])
transfer_to[cnt] = transfer_from[cnt];
return ret;
over_quota:
/* Back out changes we already did */
for (cnt--; cnt >= 0; cnt--) {
if (!is_valid[cnt])
continue;
spin_lock(&transfer_to[cnt]->dq_dqb_lock);
dquot_decr_inodes(transfer_to[cnt], inode_usage);
dquot_decr_space(transfer_to[cnt], cur_space);
dquot_free_reserved_space(transfer_to[cnt], rsv_space);
spin_unlock(&transfer_to[cnt]->dq_dqb_lock);
}
spin_unlock(&inode->i_lock);
spin_unlock(&dq_data_lock);
flush_warnings(warn_to);
return ret;
}
EXPORT_SYMBOL(__dquot_transfer);
/* Wrapper for transferring ownership of an inode for uid/gid only
* Called from FSXXX_setattr()
*/
int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode,
struct iattr *iattr)
{
struct dquot *transfer_to[MAXQUOTAS] = {};
struct dquot *dquot;
struct super_block *sb = inode->i_sb;
int ret;
if (!inode_quota_active(inode))
return 0;
if (i_uid_needs_update(idmap, iattr, inode)) {
kuid_t kuid = from_vfsuid(idmap, i_user_ns(inode),
iattr->ia_vfsuid);
dquot = dqget(sb, make_kqid_uid(kuid));
if (IS_ERR(dquot)) {
if (PTR_ERR(dquot) != -ESRCH) {
ret = PTR_ERR(dquot);
goto out_put;
}
dquot = NULL;
}
transfer_to[USRQUOTA] = dquot;
}
if (i_gid_needs_update(idmap, iattr, inode)) {
kgid_t kgid = from_vfsgid(idmap, i_user_ns(inode),
iattr->ia_vfsgid);
dquot = dqget(sb, make_kqid_gid(kgid));
if (IS_ERR(dquot)) {
if (PTR_ERR(dquot) != -ESRCH) {
ret = PTR_ERR(dquot);
goto out_put;
}
dquot = NULL;
}
transfer_to[GRPQUOTA] = dquot;
}
ret = __dquot_transfer(inode, transfer_to);
out_put:
dqput_all(transfer_to);
return ret;
}
EXPORT_SYMBOL(dquot_transfer);
/*
* Write info of quota file to disk
*/
int dquot_commit_info(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
return dqopt->ops[type]->write_file_info(sb, type);
}
EXPORT_SYMBOL(dquot_commit_info);
int dquot_get_next_id(struct super_block *sb, struct kqid *qid)
{
struct quota_info *dqopt = sb_dqopt(sb);
if (!sb_has_quota_active(sb, qid->type))
return -ESRCH;
if (!dqopt->ops[qid->type]->get_next_id)
return -ENOSYS;
return dqopt->ops[qid->type]->get_next_id(sb, qid);
}
EXPORT_SYMBOL(dquot_get_next_id);
/*
* Definitions of diskquota operations.
*/
const struct dquot_operations dquot_operations = {
.write_dquot = dquot_commit,
.acquire_dquot = dquot_acquire,
.release_dquot = dquot_release,
.mark_dirty = dquot_mark_dquot_dirty,
.write_info = dquot_commit_info,
.alloc_dquot = dquot_alloc,
.destroy_dquot = dquot_destroy,
.get_next_id = dquot_get_next_id,
};
EXPORT_SYMBOL(dquot_operations);
/*
* Generic helper for ->open on filesystems supporting disk quotas.
*/
int dquot_file_open(struct inode *inode, struct file *file)
{
int error;
error = generic_file_open(inode, file);
if (!error && (file->f_mode & FMODE_WRITE))
error = dquot_initialize(inode);
return error;
}
EXPORT_SYMBOL(dquot_file_open);
static void vfs_cleanup_quota_inode(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
struct inode *inode = dqopt->files[type];
if (!inode)
return;
if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
inode_lock(inode);
inode->i_flags &= ~S_NOQUOTA;
inode_unlock(inode);
}
dqopt->files[type] = NULL;
iput(inode);
}
/*
* Turn quota off on a device. type == -1 ==> quotaoff for all types (umount)
*/
int dquot_disable(struct super_block *sb, int type, unsigned int flags)
{
int cnt;
struct quota_info *dqopt = sb_dqopt(sb);
rwsem_assert_held_write(&sb->s_umount);
/* Cannot turn off usage accounting without turning off limits, or
* suspend quotas and simultaneously turn quotas off. */
if ((flags & DQUOT_USAGE_ENABLED && !(flags & DQUOT_LIMITS_ENABLED))
|| (flags & DQUOT_SUSPENDED && flags & (DQUOT_LIMITS_ENABLED |
DQUOT_USAGE_ENABLED)))
return -EINVAL;
/*
* Skip everything if there's nothing to do. We have to do this because
* sometimes we are called when fill_super() failed and calling
* sync_fs() in such cases does no good.
*/
if (!sb_any_quota_loaded(sb))
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_loaded(sb, cnt))
continue;
if (flags & DQUOT_SUSPENDED) {
spin_lock(&dq_state_lock);
dqopt->flags |=
dquot_state_flag(DQUOT_SUSPENDED, cnt);
spin_unlock(&dq_state_lock);
} else {
spin_lock(&dq_state_lock);
dqopt->flags &= ~dquot_state_flag(flags, cnt);
/* Turning off suspended quotas? */
if (!sb_has_quota_loaded(sb, cnt) &&
sb_has_quota_suspended(sb, cnt)) {
dqopt->flags &= ~dquot_state_flag(
DQUOT_SUSPENDED, cnt);
spin_unlock(&dq_state_lock);
vfs_cleanup_quota_inode(sb, cnt);
continue;
}
spin_unlock(&dq_state_lock);
}
/* We still have to keep quota loaded? */
if (sb_has_quota_loaded(sb, cnt) && !(flags & DQUOT_SUSPENDED))
continue;
/* Note: these are blocking operations */
drop_dquot_ref(sb, cnt);
invalidate_dquots(sb, cnt);
/*
* Now all dquots should be invalidated, all writes done so we
* should be only users of the info. No locks needed.
*/
if (info_dirty(&dqopt->info[cnt]))
sb->dq_op->write_info(sb, cnt);
if (dqopt->ops[cnt]->free_file_info)
dqopt->ops[cnt]->free_file_info(sb, cnt);
put_quota_format(dqopt->info[cnt].dqi_format);
dqopt->info[cnt].dqi_flags = 0;
dqopt->info[cnt].dqi_igrace = 0;
dqopt->info[cnt].dqi_bgrace = 0;
dqopt->ops[cnt] = NULL;
}
/* Skip syncing and setting flags if quota files are hidden */
if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
goto put_inodes;
/* Sync the superblock so that buffers with quota data are written to
* disk (and so userspace sees correct data afterwards). */
if (sb->s_op->sync_fs)
sb->s_op->sync_fs(sb, 1);
sync_blockdev(sb->s_bdev);
/* Now the quota files are just ordinary files and we can set the
* inode flags back. Moreover we discard the pagecache so that
* userspace sees the writes we did bypassing the pagecache. We
* must also discard the blockdev buffers so that we see the
* changes done by userspace on the next quotaon() */
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if (!sb_has_quota_loaded(sb, cnt) && dqopt->files[cnt]) {
inode_lock(dqopt->files[cnt]);
truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
inode_unlock(dqopt->files[cnt]);
}
if (sb->s_bdev)
invalidate_bdev(sb->s_bdev);
put_inodes:
/* We are done when suspending quotas */
if (flags & DQUOT_SUSPENDED)
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
if (!sb_has_quota_loaded(sb, cnt))
vfs_cleanup_quota_inode(sb, cnt);
return 0;
}
EXPORT_SYMBOL(dquot_disable);
int dquot_quota_off(struct super_block *sb, int type)
{
return dquot_disable(sb, type,
DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
}
EXPORT_SYMBOL(dquot_quota_off);
/*
* Turn quotas on on a device
*/
static int vfs_setup_quota_inode(struct inode *inode, int type)
{
struct super_block *sb = inode->i_sb;
struct quota_info *dqopt = sb_dqopt(sb);
if (is_bad_inode(inode))
return -EUCLEAN;
if (!S_ISREG(inode->i_mode))
return -EACCES;
if (IS_RDONLY(inode))
return -EROFS;
if (sb_has_quota_loaded(sb, type))
return -EBUSY;
/*
* Quota files should never be encrypted. They should be thought of as
* filesystem metadata, not user data. New-style internal quota files
* cannot be encrypted by users anyway, but old-style external quota
* files could potentially be incorrectly created in an encrypted
* directory, hence this explicit check. Some reasons why encrypted
* quota files don't work include: (1) some filesystems that support
* encryption don't handle it in their quota_read and quota_write, and
* (2) cleaning up encrypted quota files at unmount would need special
* consideration, as quota files are cleaned up later than user files.
*/
if (IS_ENCRYPTED(inode))
return -EINVAL;
dqopt->files[type] = igrab(inode);
if (!dqopt->files[type])
return -EIO;
if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
/* We don't want quota and atime on quota files (deadlocks
* possible) Also nobody should write to the file - we use
* special IO operations which ignore the immutable bit. */
inode_lock(inode);
inode->i_flags |= S_NOQUOTA;
inode_unlock(inode);
/*
* When S_NOQUOTA is set, remove dquot references as no more
* references can be added
*/
__dquot_drop(inode);
}
return 0;
}
int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
unsigned int flags)
{
struct quota_format_type *fmt;
struct quota_info *dqopt = sb_dqopt(sb);
int error;
lockdep_assert_held_write(&sb->s_umount);
/* Just unsuspend quotas? */
if (WARN_ON_ONCE(flags & DQUOT_SUSPENDED))
return -EINVAL;
fmt = find_quota_format(format_id);
if (!fmt)
return -ESRCH;
if (!sb->dq_op || !sb->s_qcop ||
(type == PRJQUOTA && sb->dq_op->get_projid == NULL)) {
error = -EINVAL;
goto out_fmt;
}
/* Filesystems outside of init_user_ns not yet supported */
if (sb->s_user_ns != &init_user_ns) {
error = -EINVAL;
goto out_fmt;
}
/* Usage always has to be set... */
if (!(flags & DQUOT_USAGE_ENABLED)) {
error = -EINVAL;
goto out_fmt;
}
if (sb_has_quota_loaded(sb, type)) {
error = -EBUSY;
goto out_fmt;
}
if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
/* As we bypass the pagecache we must now flush all the
* dirty data and invalidate caches so that kernel sees
* changes from userspace. It is not enough to just flush
* the quota file since if blocksize < pagesize, invalidation
* of the cache could fail because of other unrelated dirty
* data */
sync_filesystem(sb);
invalidate_bdev(sb->s_bdev);
}
error = -EINVAL;
if (!fmt->qf_ops->check_quota_file(sb, type))
goto out_fmt;
dqopt->ops[type] = fmt->qf_ops;
dqopt->info[type].dqi_format = fmt;
dqopt->info[type].dqi_fmt_id = format_id;
INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list);
error = dqopt->ops[type]->read_file_info(sb, type);
if (error < 0)
goto out_fmt;
if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) {
spin_lock(&dq_data_lock);
dqopt->info[type].dqi_flags |= DQF_SYS_FILE;
spin_unlock(&dq_data_lock);
}
spin_lock(&dq_state_lock);
dqopt->flags |= dquot_state_flag(flags, type);
spin_unlock(&dq_state_lock);
error = add_dquot_ref(sb, type);
if (error)
dquot_disable(sb, type,
DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
return error;
out_fmt:
put_quota_format(fmt);
return error;
}
EXPORT_SYMBOL(dquot_load_quota_sb);
/*
* More powerful function for turning on quotas on given quota inode allowing
* setting of individual quota flags
*/
int dquot_load_quota_inode(struct inode *inode, int type, int format_id,
unsigned int flags)
{
int err;
err = vfs_setup_quota_inode(inode, type);
if (err < 0)
return err;
err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags);
if (err < 0)
vfs_cleanup_quota_inode(inode->i_sb, type);
return err;
}
EXPORT_SYMBOL(dquot_load_quota_inode);
/* Reenable quotas on remount RW */
int dquot_resume(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
int ret = 0, cnt;
unsigned int flags;
rwsem_assert_held_write(&sb->s_umount);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_suspended(sb, cnt))
continue;
spin_lock(&dq_state_lock);
flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED,
cnt);
dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, cnt);
spin_unlock(&dq_state_lock);
flags = dquot_generic_flag(flags, cnt);
ret = dquot_load_quota_sb(sb, cnt, dqopt->info[cnt].dqi_fmt_id,
flags);
if (ret < 0)
vfs_cleanup_quota_inode(sb, cnt);
}
return ret;
}
EXPORT_SYMBOL(dquot_resume);
int dquot_quota_on(struct super_block *sb, int type, int format_id,
const struct path *path)
{
int error = security_quota_on(path->dentry);
if (error)
return error;
/* Quota file not on the same filesystem? */
if (path->dentry->d_sb != sb)
error = -EXDEV;
else
error = dquot_load_quota_inode(d_inode(path->dentry), type,
format_id, DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED);
return error;
}
EXPORT_SYMBOL(dquot_quota_on);
/*
* This function is used when filesystem needs to initialize quotas
* during mount time.
*/
int dquot_quota_on_mount(struct super_block *sb, char *qf_name,
int format_id, int type)
{
struct dentry *dentry;
int error;
dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name));
if (IS_ERR(dentry))
return PTR_ERR(dentry);
error = security_quota_on(dentry);
if (!error)
error = dquot_load_quota_inode(d_inode(dentry), type, format_id,
DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
dput(dentry);
return error;
}
EXPORT_SYMBOL(dquot_quota_on_mount);
static int dquot_quota_enable(struct super_block *sb, unsigned int flags)
{
int ret;
int type;
struct quota_info *dqopt = sb_dqopt(sb);
if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
return -ENOSYS;
/* Accounting cannot be turned on while fs is mounted */
flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT);
if (!flags)
return -EINVAL;
for (type = 0; type < MAXQUOTAS; type++) {
if (!(flags & qtype_enforce_flag(type)))
continue;
/* Can't enforce without accounting */
if (!sb_has_quota_usage_enabled(sb, type)) {
ret = -EINVAL;
goto out_err;
}
if (sb_has_quota_limits_enabled(sb, type)) {
/* compatible with XFS */
ret = -EEXIST;
goto out_err;
}
spin_lock(&dq_state_lock);
dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type);
spin_unlock(&dq_state_lock);
}
return 0;
out_err:
/* Backout enforcement enablement we already did */
for (type--; type >= 0; type--) {
if (flags & qtype_enforce_flag(type))
dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
}
return ret;
}
static int dquot_quota_disable(struct super_block *sb, unsigned int flags)
{
int ret;
int type;
struct quota_info *dqopt = sb_dqopt(sb);
if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
return -ENOSYS;
/*
* We don't support turning off accounting via quotactl. In principle
* quota infrastructure can do this but filesystems don't expect
* userspace to be able to do it.
*/
if (flags &
(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT))
return -EOPNOTSUPP;
/* Filter out limits not enabled */
for (type = 0; type < MAXQUOTAS; type++)
if (!sb_has_quota_limits_enabled(sb, type))
flags &= ~qtype_enforce_flag(type);
/* Nothing left? */
if (!flags)
return -EEXIST;
for (type = 0; type < MAXQUOTAS; type++) {
if (flags & qtype_enforce_flag(type)) {
ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
if (ret < 0)
goto out_err;
}
}
return 0;
out_err:
/* Backout enforcement disabling we already did */
for (type--; type >= 0; type--) {
if (flags & qtype_enforce_flag(type)) {
spin_lock(&dq_state_lock);
dqopt->flags |=
dquot_state_flag(DQUOT_LIMITS_ENABLED, type);
spin_unlock(&dq_state_lock);
}
}
return ret;
}
/* Generic routine for getting common part of quota structure */
static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
{
struct mem_dqblk *dm = &dquot->dq_dqb;
memset(di, 0, sizeof(*di));
spin_lock(&dquot->dq_dqb_lock);
di->d_spc_hardlimit = dm->dqb_bhardlimit;
di->d_spc_softlimit = dm->dqb_bsoftlimit;
di->d_ino_hardlimit = dm->dqb_ihardlimit;
di->d_ino_softlimit = dm->dqb_isoftlimit;
di->d_space = dm->dqb_curspace + dm->dqb_rsvspace;
di->d_ino_count = dm->dqb_curinodes;
di->d_spc_timer = dm->dqb_btime;
di->d_ino_timer = dm->dqb_itime;
spin_unlock(&dquot->dq_dqb_lock);
}
int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
struct qc_dqblk *di)
{
struct dquot *dquot;
dquot = dqget(sb, qid);
if (IS_ERR(dquot))
return PTR_ERR(dquot);
do_get_dqblk(dquot, di);
dqput(dquot);
return 0;
}
EXPORT_SYMBOL(dquot_get_dqblk);
int dquot_get_next_dqblk(struct super_block *sb, struct kqid *qid,
struct qc_dqblk *di)
{
struct dquot *dquot;
int err;
if (!sb->dq_op->get_next_id)
return -ENOSYS;
err = sb->dq_op->get_next_id(sb, qid);
if (err < 0)
return err;
dquot = dqget(sb, *qid);
if (IS_ERR(dquot))
return PTR_ERR(dquot);
do_get_dqblk(dquot, di);
dqput(dquot);
return 0;
}
EXPORT_SYMBOL(dquot_get_next_dqblk);
#define VFS_QC_MASK \
(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
QC_SPC_TIMER | QC_INO_TIMER)
/* Generic routine for setting common part of quota structure */
static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
{
struct mem_dqblk *dm = &dquot->dq_dqb;
int check_blim = 0, check_ilim = 0;
struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];
int ret;
if (di->d_fieldmask & ~VFS_QC_MASK)
return -EINVAL;
if (((di->d_fieldmask & QC_SPC_SOFT) &&
di->d_spc_softlimit > dqi->dqi_max_spc_limit) ||
((di->d_fieldmask & QC_SPC_HARD) &&
di->d_spc_hardlimit > dqi->dqi_max_spc_limit) ||
((di->d_fieldmask & QC_INO_SOFT) &&
(di->d_ino_softlimit > dqi->dqi_max_ino_limit)) ||
((di->d_fieldmask & QC_INO_HARD) &&
(di->d_ino_hardlimit > dqi->dqi_max_ino_limit)))
return -ERANGE;
spin_lock(&dquot->dq_dqb_lock);
if (di->d_fieldmask & QC_SPACE) {
dm->dqb_curspace = di->d_space - dm->dqb_rsvspace;
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
}
if (di->d_fieldmask & QC_SPC_SOFT)
dm->dqb_bsoftlimit = di->d_spc_softlimit;
if (di->d_fieldmask & QC_SPC_HARD)
dm->dqb_bhardlimit = di->d_spc_hardlimit;
if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) {
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
}
if (di->d_fieldmask & QC_INO_COUNT) {
dm->dqb_curinodes = di->d_ino_count;
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
}
if (di->d_fieldmask & QC_INO_SOFT)
dm->dqb_isoftlimit = di->d_ino_softlimit;
if (di->d_fieldmask & QC_INO_HARD)
dm->dqb_ihardlimit = di->d_ino_hardlimit;
if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) {
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
}
if (di->d_fieldmask & QC_SPC_TIMER) {
dm->dqb_btime = di->d_spc_timer;
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
}
if (di->d_fieldmask & QC_INO_TIMER) {
dm->dqb_itime = di->d_ino_timer;
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
}
if (check_blim) {
if (!dm->dqb_bsoftlimit ||
dm->dqb_curspace + dm->dqb_rsvspace <= dm->dqb_bsoftlimit) {
dm->dqb_btime = 0;
clear_bit(DQ_BLKS_B, &dquot->dq_flags);
} else if (!(di->d_fieldmask & QC_SPC_TIMER))
/* Set grace only if user hasn't provided his own... */
dm->dqb_btime = ktime_get_real_seconds() + dqi->dqi_bgrace;
}
if (check_ilim) {
if (!dm->dqb_isoftlimit ||
dm->dqb_curinodes <= dm->dqb_isoftlimit) {
dm->dqb_itime = 0;
clear_bit(DQ_INODES_B, &dquot->dq_flags);
} else if (!(di->d_fieldmask & QC_INO_TIMER))
/* Set grace only if user hasn't provided his own... */
dm->dqb_itime = ktime_get_real_seconds() + dqi->dqi_igrace;
}
if (dm->dqb_bhardlimit || dm->dqb_bsoftlimit || dm->dqb_ihardlimit ||
dm->dqb_isoftlimit)
clear_bit(DQ_FAKE_B, &dquot->dq_flags);
else
set_bit(DQ_FAKE_B, &dquot->dq_flags);
spin_unlock(&dquot->dq_dqb_lock);
ret = mark_dquot_dirty(dquot);
if (ret < 0)
return ret;
return 0;
}
int dquot_set_dqblk(struct super_block *sb, struct kqid qid,
struct qc_dqblk *di)
{
struct dquot *dquot;
int rc;
dquot = dqget(sb, qid);
if (IS_ERR(dquot)) {
rc = PTR_ERR(dquot);
goto out;
}
rc = do_set_dqblk(dquot, di);
dqput(dquot);
out:
return rc;
}
EXPORT_SYMBOL(dquot_set_dqblk);
/* Generic routine for getting common part of quota file information */
int dquot_get_state(struct super_block *sb, struct qc_state *state)
{
struct mem_dqinfo *mi;
struct qc_type_state *tstate;
struct quota_info *dqopt = sb_dqopt(sb);
int type;
memset(state, 0, sizeof(*state));
for (type = 0; type < MAXQUOTAS; type++) {
if (!sb_has_quota_active(sb, type))
continue;
tstate = state->s_state + type;
mi = sb_dqopt(sb)->info + type;
tstate->flags = QCI_ACCT_ENABLED;
spin_lock(&dq_data_lock);
if (mi->dqi_flags & DQF_SYS_FILE)
tstate->flags |= QCI_SYSFILE;
if (mi->dqi_flags & DQF_ROOT_SQUASH)
tstate->flags |= QCI_ROOT_SQUASH;
if (sb_has_quota_limits_enabled(sb, type))
tstate->flags |= QCI_LIMITS_ENFORCED;
tstate->spc_timelimit = mi->dqi_bgrace;
tstate->ino_timelimit = mi->dqi_igrace;
if (dqopt->files[type]) {
tstate->ino = dqopt->files[type]->i_ino;
tstate->blocks = dqopt->files[type]->i_blocks;
}
tstate->nextents = 1; /* We don't know... */
spin_unlock(&dq_data_lock);
}
return 0;
}
EXPORT_SYMBOL(dquot_get_state);
/* Generic routine for setting common part of quota file information */
int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii)
{
struct mem_dqinfo *mi;
if ((ii->i_fieldmask & QC_WARNS_MASK) ||
(ii->i_fieldmask & QC_RT_SPC_TIMER))
return -EINVAL;
if (!sb_has_quota_active(sb, type))
return -ESRCH;
mi = sb_dqopt(sb)->info + type;
if (ii->i_fieldmask & QC_FLAGS) {
if ((ii->i_flags & QCI_ROOT_SQUASH &&
mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD))
return -EINVAL;
}
spin_lock(&dq_data_lock);
if (ii->i_fieldmask & QC_SPC_TIMER)
mi->dqi_bgrace = ii->i_spc_timelimit;
if (ii->i_fieldmask & QC_INO_TIMER)
mi->dqi_igrace = ii->i_ino_timelimit;
if (ii->i_fieldmask & QC_FLAGS) {
if (ii->i_flags & QCI_ROOT_SQUASH)
mi->dqi_flags |= DQF_ROOT_SQUASH;
else
mi->dqi_flags &= ~DQF_ROOT_SQUASH;
}
spin_unlock(&dq_data_lock);
mark_info_dirty(sb, type);
/* Force write to disk */
return sb->dq_op->write_info(sb, type);
}
EXPORT_SYMBOL(dquot_set_dqinfo);
const struct quotactl_ops dquot_quotactl_sysfile_ops = {
.quota_enable = dquot_quota_enable,
.quota_disable = dquot_quota_disable,
.quota_sync = dquot_quota_sync,
.get_state = dquot_get_state,
.set_info = dquot_set_dqinfo,
.get_dqblk = dquot_get_dqblk,
.get_nextdqblk = dquot_get_next_dqblk,
.set_dqblk = dquot_set_dqblk
};
EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
static int do_proc_dqstats(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int type = (unsigned long *)table->data - dqstats.stat;
s64 value = percpu_counter_sum(&dqstats.counter[type]);
/* Filter negative values for non-monotonic counters */
if (value < 0 && (type == DQST_ALLOC_DQUOTS ||
type == DQST_FREE_DQUOTS))
value = 0;
/* Update global table */
dqstats.stat[type] = value;
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static const struct ctl_table fs_dqstats_table[] = {
{
.procname = "lookups",
.data = &dqstats.stat[DQST_LOOKUPS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "drops",
.data = &dqstats.stat[DQST_DROPS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "reads",
.data = &dqstats.stat[DQST_READS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "writes",
.data = &dqstats.stat[DQST_WRITES],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "cache_hits",
.data = &dqstats.stat[DQST_CACHE_HITS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "allocated_dquots",
.data = &dqstats.stat[DQST_ALLOC_DQUOTS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "free_dquots",
.data = &dqstats.stat[DQST_FREE_DQUOTS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "syncs",
.data = &dqstats.stat[DQST_SYNCS],
.maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
#ifdef CONFIG_PRINT_QUOTA_WARNING
{
.procname = "warnings",
.data = &flag_print_warnings,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
};
static int __init dquot_init(void)
{
int i, ret;
unsigned long nr_hash, order;
struct shrinker *dqcache_shrinker;
printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__);
register_sysctl_init("fs/quota", fs_dqstats_table);
dquot_cachep = kmem_cache_create("dquot",
sizeof(struct dquot), sizeof(unsigned long) * 4,
(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
SLAB_PANIC),
NULL);
order = 0;
dquot_hash = (struct hlist_head *)__get_free_pages(GFP_KERNEL, order);
if (!dquot_hash)
panic("Cannot create dquot hash table");
ret = percpu_counter_init_many(dqstats.counter, 0, GFP_KERNEL,
_DQST_DQSTAT_LAST);
if (ret)
panic("Cannot create dquot stat counters");
/* Find power-of-two hlist_heads which can fit into allocation */
nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head);
dq_hash_bits = ilog2(nr_hash);
nr_hash = 1UL << dq_hash_bits;
dq_hash_mask = nr_hash - 1;
for (i = 0; i < nr_hash; i++)
INIT_HLIST_HEAD(dquot_hash + i);
pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld,"
" %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order));
dqcache_shrinker = shrinker_alloc(0, "dquota-cache");
if (!dqcache_shrinker)
panic("Cannot allocate dquot shrinker");
dqcache_shrinker->count_objects = dqcache_shrink_count;
dqcache_shrinker->scan_objects = dqcache_shrink_scan;
shrinker_register(dqcache_shrinker);
return 0;
}
fs_initcall(dquot_init);
// SPDX-License-Identifier: GPL-2.0
/*
* NETLINK Netlink attributes
*
* Authors: Thomas Graf <tgraf@suug.ch>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
*/
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/jiffies.h>
#include <linux/nospec.h>
#include <linux/skbuff.h>
#include <linux/string.h>
#include <linux/types.h>
#include <net/netlink.h>
/* For these data types, attribute length should be exactly the given
* size. However, to maintain compatibility with broken commands, if the
* attribute length does not match the expected size a warning is emitted
* to the user that the command is sending invalid data and needs to be fixed.
*/
static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
[NLA_U8] = sizeof(u8),
[NLA_U16] = sizeof(u16),
[NLA_U32] = sizeof(u32),
[NLA_U64] = sizeof(u64),
[NLA_S8] = sizeof(s8),
[NLA_S16] = sizeof(s16),
[NLA_S32] = sizeof(s32),
[NLA_S64] = sizeof(s64),
[NLA_BE16] = sizeof(__be16),
[NLA_BE32] = sizeof(__be32),
};
static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
[NLA_U8] = sizeof(u8),
[NLA_U16] = sizeof(u16),
[NLA_U32] = sizeof(u32),
[NLA_U64] = sizeof(u64),
[NLA_MSECS] = sizeof(u64),
[NLA_NESTED] = NLA_HDRLEN,
[NLA_S8] = sizeof(s8),
[NLA_S16] = sizeof(s16),
[NLA_S32] = sizeof(s32),
[NLA_S64] = sizeof(s64),
[NLA_BE16] = sizeof(__be16),
[NLA_BE32] = sizeof(__be32),
};
/*
* Nested policies might refer back to the original
* policy in some cases, and userspace could try to
* abuse that and recurse by nesting in the right
* ways. Limit recursion to avoid this problem.
*/
#define MAX_POLICY_RECURSION_DEPTH 10
static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
unsigned int validate,
struct netlink_ext_ack *extack,
struct nlattr **tb, unsigned int depth);
static int validate_nla_bitfield32(const struct nlattr *nla,
const u32 valid_flags_mask)
{
const struct nla_bitfield32 *bf = nla_data(nla);
if (!valid_flags_mask)
return -EINVAL;
/*disallow invalid bit selector */
if (bf->selector & ~valid_flags_mask)
return -EINVAL;
/*disallow invalid bit values */
if (bf->value & ~valid_flags_mask)
return -EINVAL;
/*disallow valid bit values that are not selected*/
if (bf->value & ~bf->selector)
return -EINVAL;
return 0;
}
static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack,
unsigned int validate, unsigned int depth)
{
const struct nlattr *entry;
int rem;
nla_for_each_attr(entry, head, len, rem) {
int ret;
if (nla_len(entry) == 0)
continue;
if (nla_len(entry) < NLA_HDRLEN) {
NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy,
"Array element too short");
return -ERANGE;
}
ret = __nla_validate_parse(nla_data(entry), nla_len(entry),
maxtype, policy, validate, extack,
NULL, depth + 1);
if (ret < 0)
return ret;
}
return 0;
}
void nla_get_range_unsigned(const struct nla_policy *pt,
struct netlink_range_validation *range)
{
WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR &&
(pt->min < 0 || pt->max < 0));
range->min = 0;
switch (pt->type) {
case NLA_U8:
range->max = U8_MAX;
break;
case NLA_U16:
case NLA_BE16:
case NLA_BINARY:
range->max = U16_MAX;
break;
case NLA_U32:
case NLA_BE32:
range->max = U32_MAX;
break;
case NLA_U64:
case NLA_UINT:
case NLA_MSECS:
range->max = U64_MAX;
break;
default:
WARN_ON_ONCE(1);
return;
}
switch (pt->validation_type) {
case NLA_VALIDATE_RANGE:
case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
range->min = pt->min;
range->max = pt->max;
break;
case NLA_VALIDATE_RANGE_PTR:
*range = *pt->range;
break;
case NLA_VALIDATE_MIN:
range->min = pt->min;
break;
case NLA_VALIDATE_MAX:
range->max = pt->max;
break;
default:
break;
}
}
static int nla_validate_range_unsigned(const struct nla_policy *pt,
const struct nlattr *nla,
struct netlink_ext_ack *extack,
unsigned int validate)
{
struct netlink_range_validation range;
u64 value;
switch (pt->type) {
case NLA_U8:
value = nla_get_u8(nla);
break;
case NLA_U16:
value = nla_get_u16(nla);
break;
case NLA_U32:
value = nla_get_u32(nla);
break;
case NLA_U64:
value = nla_get_u64(nla);
break;
case NLA_UINT:
value = nla_get_uint(nla);
break;
case NLA_MSECS:
value = nla_get_u64(nla);
break;
case NLA_BINARY:
value = nla_len(nla);
break;
case NLA_BE16:
value = ntohs(nla_get_be16(nla));
break;
case NLA_BE32:
value = ntohl(nla_get_be32(nla));
break;
default:
return -EINVAL;
}
nla_get_range_unsigned(pt, &range);
if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG &&
pt->type == NLA_BINARY && value > range.max) {
pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
current->comm, pt->type);
if (validate & NL_VALIDATE_STRICT_ATTRS) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"invalid attribute length");
return -EINVAL;
}
/* this assumes min <= max (don't validate against min) */
return 0;
}
if (value < range.min || value > range.max) {
bool binary = pt->type == NLA_BINARY;
if (binary)
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"binary attribute size out of range");
else
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"integer out of range");
return -ERANGE;
}
return 0;
}
void nla_get_range_signed(const struct nla_policy *pt,
struct netlink_range_validation_signed *range)
{
switch (pt->type) {
case NLA_S8:
range->min = S8_MIN;
range->max = S8_MAX;
break;
case NLA_S16:
range->min = S16_MIN;
range->max = S16_MAX;
break;
case NLA_S32:
range->min = S32_MIN;
range->max = S32_MAX;
break;
case NLA_S64:
case NLA_SINT:
range->min = S64_MIN;
range->max = S64_MAX;
break;
default:
WARN_ON_ONCE(1);
return;
}
switch (pt->validation_type) {
case NLA_VALIDATE_RANGE:
range->min = pt->min;
range->max = pt->max;
break;
case NLA_VALIDATE_RANGE_PTR:
*range = *pt->range_signed;
break;
case NLA_VALIDATE_MIN:
range->min = pt->min;
break;
case NLA_VALIDATE_MAX:
range->max = pt->max;
break;
default:
break;
}
}
static int nla_validate_int_range_signed(const struct nla_policy *pt,
const struct nlattr *nla,
struct netlink_ext_ack *extack)
{
struct netlink_range_validation_signed range;
s64 value;
switch (pt->type) {
case NLA_S8:
value = nla_get_s8(nla);
break;
case NLA_S16:
value = nla_get_s16(nla);
break;
case NLA_S32:
value = nla_get_s32(nla);
break;
case NLA_S64:
value = nla_get_s64(nla);
break;
case NLA_SINT:
value = nla_get_sint(nla);
break;
default:
return -EINVAL;
}
nla_get_range_signed(pt, &range);
if (value < range.min || value > range.max) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"integer out of range");
return -ERANGE;
}
return 0;
}
static int nla_validate_int_range(const struct nla_policy *pt,
const struct nlattr *nla,
struct netlink_ext_ack *extack,
unsigned int validate)
{
switch (pt->type) {
case NLA_U8:
case NLA_U16:
case NLA_U32:
case NLA_U64:
case NLA_UINT:
case NLA_MSECS:
case NLA_BINARY:
case NLA_BE16:
case NLA_BE32:
return nla_validate_range_unsigned(pt, nla, extack, validate);
case NLA_S8:
case NLA_S16:
case NLA_S32:
case NLA_S64:
case NLA_SINT:
return nla_validate_int_range_signed(pt, nla, extack);
default:
WARN_ON(1);
return -EINVAL;
}
}
static int nla_validate_mask(const struct nla_policy *pt,
const struct nlattr *nla,
struct netlink_ext_ack *extack)
{
u64 value;
switch (pt->type) {
case NLA_U8:
value = nla_get_u8(nla);
break;
case NLA_U16:
value = nla_get_u16(nla);
break;
case NLA_U32:
value = nla_get_u32(nla);
break;
case NLA_U64:
value = nla_get_u64(nla);
break;
case NLA_UINT:
value = nla_get_uint(nla);
break;
case NLA_BE16:
value = ntohs(nla_get_be16(nla));
break;
case NLA_BE32:
value = ntohl(nla_get_be32(nla));
break;
default:
return -EINVAL;
}
if (value & ~(u64)pt->mask) {
NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set");
return -EINVAL;
}
return 0;
}
static int validate_nla(const struct nlattr *nla, int maxtype,
const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack, unsigned int depth)
{
u16 strict_start_type = policy[0].strict_start_type;
const struct nla_policy *pt;
int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
int err = -ERANGE;
if (strict_start_type && type >= strict_start_type)
validate |= NL_VALIDATE_STRICT;
if (type <= 0 || type > maxtype)
return 0;
type = array_index_nospec(type, maxtype + 1);
pt = &policy[type];
BUG_ON(pt->type > NLA_TYPE_MAX);
if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) {
pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
current->comm, type);
if (validate & NL_VALIDATE_STRICT_ATTRS) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"invalid attribute length");
return -EINVAL;
}
}
if (validate & NL_VALIDATE_NESTED) {
if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
!(nla->nla_type & NLA_F_NESTED)) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"NLA_F_NESTED is missing");
return -EINVAL;
}
if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"NLA_F_NESTED not expected");
return -EINVAL;
}
}
switch (pt->type) {
case NLA_REJECT:
if (extack && pt->reject_message) {
NL_SET_BAD_ATTR(extack, nla);
extack->_msg = pt->reject_message;
return -EINVAL;
}
err = -EINVAL;
goto out_err;
case NLA_FLAG:
if (attrlen > 0)
goto out_err;
break;
case NLA_SINT:
case NLA_UINT:
if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) {
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"invalid attribute length");
return -EINVAL;
}
break;
case NLA_BITFIELD32:
if (attrlen != sizeof(struct nla_bitfield32))
goto out_err;
err = validate_nla_bitfield32(nla, pt->bitfield32_valid);
if (err)
goto out_err;
break;
case NLA_NUL_STRING:
if (pt->len)
minlen = min_t(int, attrlen, pt->len + 1);
else
minlen = attrlen;
if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) {
err = -EINVAL;
goto out_err;
}
fallthrough;
case NLA_STRING:
if (attrlen < 1)
goto out_err;
if (pt->len) {
char *buf = nla_data(nla);
if (buf[attrlen - 1] == '\0')
attrlen--;
if (attrlen > pt->len)
goto out_err;
}
break;
case NLA_BINARY:
if (pt->len && attrlen > pt->len)
goto out_err;
break;
case NLA_NESTED:
/* a nested attributes is allowed to be empty; if its not,
* it must have a size of at least NLA_HDRLEN.
*/
if (attrlen == 0)
break;
if (attrlen < NLA_HDRLEN)
goto out_err;
if (pt->nested_policy) {
err = __nla_validate_parse(nla_data(nla), nla_len(nla),
pt->len, pt->nested_policy,
validate, extack, NULL,
depth + 1);
if (err < 0) {
/*
* return directly to preserve the inner
* error message/attribute pointer
*/
return err;
}
}
break;
case NLA_NESTED_ARRAY:
/* a nested array attribute is allowed to be empty; if its not,
* it must have a size of at least NLA_HDRLEN.
*/
if (attrlen == 0)
break;
if (attrlen < NLA_HDRLEN)
goto out_err;
if (pt->nested_policy) {
int err;
err = nla_validate_array(nla_data(nla), nla_len(nla),
pt->len, pt->nested_policy,
extack, validate, depth);
if (err < 0) {
/*
* return directly to preserve the inner
* error message/attribute pointer
*/
return err;
}
}
break;
case NLA_UNSPEC:
if (validate & NL_VALIDATE_UNSPEC) {
NL_SET_ERR_MSG_ATTR(extack, nla,
"Unsupported attribute");
return -EINVAL;
}
if (attrlen < pt->len)
goto out_err;
break;
default:
if (pt->len)
minlen = pt->len;
else
minlen = nla_attr_minlen[pt->type];
if (attrlen < minlen)
goto out_err;
}
/* further validation */
switch (pt->validation_type) {
case NLA_VALIDATE_NONE:
/* nothing to do */
break;
case NLA_VALIDATE_RANGE_PTR:
case NLA_VALIDATE_RANGE:
case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
case NLA_VALIDATE_MIN:
case NLA_VALIDATE_MAX:
err = nla_validate_int_range(pt, nla, extack, validate);
if (err)
return err;
break;
case NLA_VALIDATE_MASK:
err = nla_validate_mask(pt, nla, extack);
if (err)
return err;
break;
case NLA_VALIDATE_FUNCTION:
if (pt->validate) {
err = pt->validate(nla, extack);
if (err)
return err;
}
break;
}
return 0;
out_err:
NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
"Attribute failed policy validation");
return err;
}
static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
unsigned int validate,
struct netlink_ext_ack *extack,
struct nlattr **tb, unsigned int depth)
{
const struct nlattr *nla;
int rem;
if (depth >= MAX_POLICY_RECURSION_DEPTH) {
NL_SET_ERR_MSG(extack,
"allowed policy recursion depth exceeded");
return -EINVAL;
}
if (tb)
memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
nla_for_each_attr(nla, head, len, rem) {
u16 type = nla_type(nla);
if (type == 0 || type > maxtype) {
if (validate & NL_VALIDATE_MAXTYPE) {
NL_SET_ERR_MSG_ATTR(extack, nla,
"Unknown attribute type");
return -EINVAL;
}
continue;
}
type = array_index_nospec(type, maxtype + 1);
if (policy) {
int err = validate_nla(nla, maxtype, policy,
validate, extack, depth);
if (err < 0)
return err;
}
if (tb)
tb[type] = (struct nlattr *)nla;
}
if (unlikely(rem > 0)) {
pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
rem, current->comm);
NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
if (validate & NL_VALIDATE_TRAILING)
return -EINVAL;
}
return 0;
}
/**
* __nla_validate - Validate a stream of attributes
* @head: head of attribute stream
* @len: length of attribute stream
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @validate: validation strictness
* @extack: extended ACK report struct
*
* Validates all attributes in the specified attribute stream against the
* specified policy. Validation depends on the validate flags passed, see
* &enum netlink_validation for more details on that.
* See documentation of struct nla_policy for more details.
*
* Returns 0 on success or a negative error code.
*/
int __nla_validate(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack)
{
return __nla_validate_parse(head, len, maxtype, policy, validate,
extack, NULL, 0);
}
EXPORT_SYMBOL(__nla_validate);
/**
* nla_policy_len - Determine the max. length of a policy
* @p: policy to use
* @n: number of policies
*
* Determines the max. length of the policy. It is currently used
* to allocated Netlink buffers roughly the size of the actual
* message.
*
* Returns 0 on success or a negative error code.
*/
int
nla_policy_len(const struct nla_policy *p, int n)
{
int i, len = 0;
for (i = 0; i < n; i++, p++) {
if (p->len)
len += nla_total_size(p->len);
else if (nla_attr_len[p->type])
len += nla_total_size(nla_attr_len[p->type]);
else if (nla_attr_minlen[p->type])
len += nla_total_size(nla_attr_minlen[p->type]);
}
return len;
}
EXPORT_SYMBOL(nla_policy_len);
/**
* __nla_parse - Parse a stream of attributes into a tb buffer
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @head: head of attribute stream
* @len: length of attribute stream
* @policy: validation policy
* @validate: validation strictness
* @extack: extended ACK pointer
*
* Parses a stream of attributes and stores a pointer to each attribute in
* the tb array accessible via the attribute type.
* Validation is controlled by the @validate parameter.
*
* Returns 0 on success or a negative error code.
*/
int __nla_parse(struct nlattr **tb, int maxtype,
const struct nlattr *head, int len,
const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack)
{
return __nla_validate_parse(head, len, maxtype, policy, validate,
extack, tb, 0);
}
EXPORT_SYMBOL(__nla_parse);
/**
* nla_find - Find a specific attribute in a stream of attributes
* @head: head of attribute stream
* @len: length of attribute stream
* @attrtype: type of attribute to look for
*
* Returns the first attribute in the stream matching the specified type.
*/
struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype)
{
const struct nlattr *nla;
int rem;
nla_for_each_attr(nla, head, len, rem)
if (nla_type(nla) == attrtype)
return (struct nlattr *)nla;
return NULL;
}
EXPORT_SYMBOL(nla_find);
/**
* nla_strscpy - Copy string attribute payload into a sized buffer
* @dst: Where to copy the string to.
* @nla: Attribute to copy the string from.
* @dstsize: Size of destination buffer.
*
* Copies at most dstsize - 1 bytes into the destination buffer.
* Unlike strscpy() the destination buffer is always padded out.
*
* Return:
* * srclen - Returns @nla length (not including the trailing %NUL).
* * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater
* than @dstsize.
*/
ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize)
{
size_t srclen = nla_len(nla);
char *src = nla_data(nla);
ssize_t ret;
size_t len;
if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX))
return -E2BIG;
if (srclen > 0 && src[srclen - 1] == '\0')
srclen--;
if (srclen >= dstsize) {
len = dstsize - 1;
ret = -E2BIG;
} else {
len = srclen;
ret = len;
}
memcpy(dst, src, len);
/* Zero pad end of dst. */
memset(dst + len, 0, dstsize - len);
return ret;
}
EXPORT_SYMBOL(nla_strscpy);
/**
* nla_strdup - Copy string attribute payload into a newly allocated buffer
* @nla: attribute to copy the string from
* @flags: the type of memory to allocate (see kmalloc).
*
* Returns a pointer to the allocated buffer or NULL on error.
*/
char *nla_strdup(const struct nlattr *nla, gfp_t flags)
{
size_t srclen = nla_len(nla);
char *src = nla_data(nla), *dst;
if (srclen > 0 && src[srclen - 1] == '\0')
srclen--;
dst = kmalloc(srclen + 1, flags);
if (dst != NULL) {
memcpy(dst, src, srclen);
dst[srclen] = '\0';
}
return dst;
}
EXPORT_SYMBOL(nla_strdup);
/**
* nla_memcpy - Copy a netlink attribute into another memory area
* @dest: where to copy to memcpy
* @src: netlink attribute to copy from
* @count: size of the destination area
*
* Note: The number of bytes copied is limited by the length of
* attribute's payload. memcpy
*
* Returns the number of bytes copied.
*/
int nla_memcpy(void *dest, const struct nlattr *src, int count)
{
int minlen = min_t(int, count, nla_len(src));
memcpy(dest, nla_data(src), minlen);
if (count > minlen)
memset(dest + minlen, 0, count - minlen);
return minlen;
}
EXPORT_SYMBOL(nla_memcpy);
/**
* nla_memcmp - Compare an attribute with sized memory area
* @nla: netlink attribute
* @data: memory area
* @size: size of memory area
*/
int nla_memcmp(const struct nlattr *nla, const void *data,
size_t size)
{
int d = nla_len(nla) - size;
if (d == 0)
d = memcmp(nla_data(nla), data, size);
return d;
}
EXPORT_SYMBOL(nla_memcmp);
/**
* nla_strcmp - Compare a string attribute against a string
* @nla: netlink string attribute
* @str: another string
*/
int nla_strcmp(const struct nlattr *nla, const char *str)
{
int len = strlen(str);
char *buf = nla_data(nla);
int attrlen = nla_len(nla);
int d;
while (attrlen > 0 && buf[attrlen - 1] == '\0')
attrlen--;
d = attrlen - len;
if (d == 0)
d = memcmp(nla_data(nla), str, len);
return d;
}
EXPORT_SYMBOL(nla_strcmp);
#ifdef CONFIG_NET
/**
* __nla_reserve - reserve room for attribute on the skb
* @skb: socket buffer to reserve room on
* @attrtype: attribute type
* @attrlen: length of attribute payload
*
* Adds a netlink attribute header to a socket buffer and reserves
* room for the payload but does not copy it.
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the attribute header and payload.
*/
struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen)
{
struct nlattr *nla;
nla = skb_put(skb, nla_total_size(attrlen));
nla->nla_type = attrtype;
nla->nla_len = nla_attr_size(attrlen);
memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen));
return nla;
}
EXPORT_SYMBOL(__nla_reserve);
/**
* __nla_reserve_64bit - reserve room for attribute on the skb and align it
* @skb: socket buffer to reserve room on
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @padattr: attribute type for the padding
*
* Adds a netlink attribute header to a socket buffer and reserves
* room for the payload but does not copy it. It also ensure that this
* attribute will have a 64-bit aligned nla_data() area.
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the attribute header and payload.
*/
struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype,
int attrlen, int padattr)
{
nla_align_64bit(skb, padattr);
return __nla_reserve(skb, attrtype, attrlen);
}
EXPORT_SYMBOL(__nla_reserve_64bit);
/**
* __nla_reserve_nohdr - reserve room for attribute without header
* @skb: socket buffer to reserve room on
* @attrlen: length of attribute payload
*
* Reserves room for attribute payload without a header.
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the payload.
*/
void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen)
{
return skb_put_zero(skb, NLA_ALIGN(attrlen));
}
EXPORT_SYMBOL(__nla_reserve_nohdr);
/**
* nla_reserve - reserve room for attribute on the skb
* @skb: socket buffer to reserve room on
* @attrtype: attribute type
* @attrlen: length of attribute payload
*
* Adds a netlink attribute header to a socket buffer and reserves
* room for the payload but does not copy it.
*
* Returns NULL if the tailroom of the skb is insufficient to store
* the attribute header and payload.
*/
struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen)
{ if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen)))
return NULL;
return __nla_reserve(skb, attrtype, attrlen);
}
EXPORT_SYMBOL(nla_reserve);
/**
* nla_reserve_64bit - reserve room for attribute on the skb and align it
* @skb: socket buffer to reserve room on
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @padattr: attribute type for the padding
*
* Adds a netlink attribute header to a socket buffer and reserves
* room for the payload but does not copy it. It also ensure that this
* attribute will have a 64-bit aligned nla_data() area.
*
* Returns NULL if the tailroom of the skb is insufficient to store
* the attribute header and payload.
*/
struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen,
int padattr)
{
size_t len;
if (nla_need_padding_for_64bit(skb))
len = nla_total_size_64bit(attrlen);
else
len = nla_total_size(attrlen);
if (unlikely(skb_tailroom(skb) < len))
return NULL;
return __nla_reserve_64bit(skb, attrtype, attrlen, padattr);
}
EXPORT_SYMBOL(nla_reserve_64bit);
/**
* nla_reserve_nohdr - reserve room for attribute without header
* @skb: socket buffer to reserve room on
* @attrlen: length of attribute payload
*
* Reserves room for attribute payload without a header.
*
* Returns NULL if the tailroom of the skb is insufficient to store
* the attribute payload.
*/
void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen)
{
if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
return NULL;
return __nla_reserve_nohdr(skb, attrlen);
}
EXPORT_SYMBOL(nla_reserve_nohdr);
/**
* __nla_put - Add a netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the attribute header and payload.
*/
void __nla_put(struct sk_buff *skb, int attrtype, int attrlen,
const void *data)
{
struct nlattr *nla;
nla = __nla_reserve(skb, attrtype, attrlen);
memcpy(nla_data(nla), data, attrlen);
}
EXPORT_SYMBOL(__nla_put);
/**
* __nla_put_64bit - Add a netlink attribute to a socket buffer and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @data: head of attribute payload
* @padattr: attribute type for the padding
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the attribute header and payload.
*/
void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen,
const void *data, int padattr)
{
struct nlattr *nla;
nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr);
memcpy(nla_data(nla), data, attrlen);
}
EXPORT_SYMBOL(__nla_put_64bit);
/**
* __nla_put_nohdr - Add a netlink attribute without header
* @skb: socket buffer to add attribute to
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
* The caller is responsible to ensure that the skb provides enough
* tailroom for the attribute payload.
*/
void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
{
void *start;
start = __nla_reserve_nohdr(skb, attrlen);
memcpy(start, data, attrlen);
}
EXPORT_SYMBOL(__nla_put_nohdr);
/**
* nla_put - Add a netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
* Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute header and payload.
*/
int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
{ if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen)))
return -EMSGSIZE;
__nla_put(skb, attrtype, attrlen, data);
return 0;
}
EXPORT_SYMBOL(nla_put);
/**
* nla_put_64bit - Add a netlink attribute to a socket buffer and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @attrlen: length of attribute payload
* @data: head of attribute payload
* @padattr: attribute type for the padding
*
* Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute header and payload.
*/
int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen,
const void *data, int padattr)
{
size_t len;
if (nla_need_padding_for_64bit(skb))
len = nla_total_size_64bit(attrlen);
else
len = nla_total_size(attrlen);
if (unlikely(skb_tailroom(skb) < len))
return -EMSGSIZE;
__nla_put_64bit(skb, attrtype, attrlen, data, padattr);
return 0;
}
EXPORT_SYMBOL(nla_put_64bit);
/**
* nla_put_nohdr - Add a netlink attribute without header
* @skb: socket buffer to add attribute to
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
* Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute payload.
*/
int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
{
if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
return -EMSGSIZE;
__nla_put_nohdr(skb, attrlen, data);
return 0;
}
EXPORT_SYMBOL(nla_put_nohdr);
/**
* nla_append - Add a netlink attribute without header or padding
* @skb: socket buffer to add attribute to
* @attrlen: length of attribute payload
* @data: head of attribute payload
*
* Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
* the attribute payload.
*/
int nla_append(struct sk_buff *skb, int attrlen, const void *data)
{
if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
return -EMSGSIZE;
skb_put_data(skb, data, attrlen);
return 0;
}
EXPORT_SYMBOL(nla_append);
#endif
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/sysctl.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
#include <linux/userfaultfd_k.h>
#include <linux/elf.h>
#include <linux/elf-randomize.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/processor.h>
#include <linux/sizes.h>
#include <linux/compat.h>
#include <linux/fsnotify.h>
#include <linux/uaccess.h>
#include <kunit/visibility.h>
#include "internal.h"
#include "swap.h"
/**
* kfree_const - conditionally free memory
* @x: pointer to the memory
*
* Function calls kfree only if @x is not in .rodata section.
*/
void kfree_const(const void *x)
{
if (!is_kernel_rodata((unsigned long)x))
kfree(x);
}
EXPORT_SYMBOL(kfree_const);
/**
* __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated.
* @s: The data to copy
* @len: The size of the data, not including the NUL terminator
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Return: newly allocated copy of @s with NUL-termination or %NULL in
* case of error
*/
static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{
char *buf;
/* '+1' for the NUL terminator */
buf = kmalloc_track_caller(len + 1, gfp);
if (!buf)
return NULL;
memcpy(buf, s, len);
/* Ensure the buf is always NUL-terminated, regardless of @s. */
buf[len] = '\0';
return buf;
}
/**
* kstrdup - allocate space for and copy an existing string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Return: newly allocated copy of @s or %NULL in case of error
*/
noinline
char *kstrdup(const char *s, gfp_t gfp)
{
return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL;
}
EXPORT_SYMBOL(kstrdup);
/**
* kstrdup_const - conditionally duplicate an existing const string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Note: Strings allocated by kstrdup_const should be freed by kfree_const and
* must not be passed to krealloc().
*
* Return: source string if it is in .rodata section otherwise
* fallback to kstrdup.
*/
const char *kstrdup_const(const char *s, gfp_t gfp)
{
if (is_kernel_rodata((unsigned long)s))
return s;
return kstrdup(s, gfp);
}
EXPORT_SYMBOL(kstrdup_const);
/**
* kstrndup - allocate space for and copy an existing string
* @s: the string to duplicate
* @max: read at most @max chars from @s
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Note: Use kmemdup_nul() instead if the size is known exactly.
*
* Return: newly allocated copy of @s or %NULL in case of error
*/
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL;
}
EXPORT_SYMBOL(kstrndup);
/**
* kmemdup - duplicate region of memory
*
* @src: memory region to duplicate
* @len: memory region length
* @gfp: GFP mask to use
*
* Return: newly allocated copy of @src or %NULL in case of error,
* result is physically contiguous. Use kfree() to free.
*/
void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp)
{
void *p;
p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_);
if (p) memcpy(p, src, len);
return p;
}
EXPORT_SYMBOL(kmemdup_noprof);
/**
* kmemdup_array - duplicate a given array.
*
* @src: array to duplicate.
* @count: number of elements to duplicate from array.
* @element_size: size of each element of array.
* @gfp: GFP mask to use.
*
* Return: duplicated array of @src or %NULL in case of error,
* result is physically contiguous. Use kfree() to free.
*/
void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp)
{
return kmemdup(src, size_mul(element_size, count), gfp);
}
EXPORT_SYMBOL(kmemdup_array);
/**
* kvmemdup - duplicate region of memory
*
* @src: memory region to duplicate
* @len: memory region length
* @gfp: GFP mask to use
*
* Return: newly allocated copy of @src or %NULL in case of error,
* result may be not physically contiguous. Use kvfree() to free.
*/
void *kvmemdup(const void *src, size_t len, gfp_t gfp)
{
void *p;
p = kvmalloc(len, gfp);
if (p)
memcpy(p, src, len);
return p;
}
EXPORT_SYMBOL(kvmemdup);
/**
* kmemdup_nul - Create a NUL-terminated string from unterminated data
* @s: The data to stringify
* @len: The size of the data
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Return: newly allocated copy of @s with NUL-termination or %NULL in
* case of error
*/
char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{
return s ? __kmemdup_nul(s, len, gfp) : NULL;
}
EXPORT_SYMBOL(kmemdup_nul);
static kmem_buckets *user_buckets __ro_after_init;
static int __init init_user_buckets(void)
{
user_buckets = kmem_buckets_create("memdup_user", 0, 0, INT_MAX, NULL);
return 0;
}
subsys_initcall(init_user_buckets);
/**
* memdup_user - duplicate memory region from user space
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure. Result is physically
* contiguous, to be freed by kfree().
*/
void *memdup_user(const void __user *src, size_t len)
{
void *p;
p = kmem_buckets_alloc_track_caller(user_buckets, len, GFP_USER | __GFP_NOWARN);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
return p;
}
EXPORT_SYMBOL(memdup_user);
/**
* vmemdup_user - duplicate memory region from user space
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure. Result may be not
* physically contiguous. Use kvfree() to free.
*/
void *vmemdup_user(const void __user *src, size_t len)
{
void *p;
p = kmem_buckets_valloc(user_buckets, len, GFP_USER);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kvfree(p);
return ERR_PTR(-EFAULT);
}
return p;
}
EXPORT_SYMBOL(vmemdup_user);
/**
* strndup_user - duplicate an existing string from user space
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
*
* Return: newly allocated copy of @s or an ERR_PTR() in case of error
*/
char *strndup_user(const char __user *s, long n)
{
char *p;
long length;
length = strnlen_user(s, n);
if (!length)
return ERR_PTR(-EFAULT);
if (length > n)
return ERR_PTR(-EINVAL);
p = memdup_user(s, length);
if (IS_ERR(p))
return p;
p[length - 1] = '\0';
return p;
}
EXPORT_SYMBOL(strndup_user);
/**
* memdup_user_nul - duplicate memory region from user space and NUL-terminate
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Return: an ERR_PTR() on failure.
*/
void *memdup_user_nul(const void __user *src, size_t len)
{
char *p;
p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
p[len] = '\0';
return p;
}
EXPORT_SYMBOL(memdup_user_nul);
/* Check if the vma is being used as a stack by this task */
int vma_is_stack_for_current(struct vm_area_struct *vma)
{
struct task_struct * __maybe_unused t = current;
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}
/*
* Change backing file, only valid to use during initial VMA setup.
*/
void vma_set_file(struct vm_area_struct *vma, struct file *file)
{
/* Changing an anonymous vma with this is illegal */
get_file(file);
swap(vma->vm_file, file);
fput(file);
}
EXPORT_SYMBOL(vma_set_file);
#ifndef STACK_RND_MASK
#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */
#endif
unsigned long randomize_stack_top(unsigned long stack_top)
{
unsigned long random_variable = 0;
if (current->flags & PF_RANDOMIZE) {
random_variable = get_random_long();
random_variable &= STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
#ifdef CONFIG_STACK_GROWSUP
return PAGE_ALIGN(stack_top) + random_variable;
#else
return PAGE_ALIGN(stack_top) - random_variable;
#endif
}
/**
* randomize_page - Generate a random, page aligned address
* @start: The smallest acceptable address the caller will take.
* @range: The size of the area, starting at @start, within which the
* random address must fall.
*
* If @start + @range would overflow, @range is capped.
*
* NOTE: Historical use of randomize_range, which this replaces, presumed that
* @start was already page aligned. We now align it regardless.
*
* Return: A page aligned address within [start, start + range). On error,
* @start is returned.
*/
unsigned long randomize_page(unsigned long start, unsigned long range)
{
if (!PAGE_ALIGNED(start)) {
range -= PAGE_ALIGN(start) - start;
start = PAGE_ALIGN(start);
}
if (start > ULONG_MAX - range)
range = ULONG_MAX - start;
range >>= PAGE_SHIFT;
if (range == 0)
return start;
return start + (get_random_long() % range << PAGE_SHIFT);
}
#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
unsigned long __weak arch_randomize_brk(struct mm_struct *mm)
{
/* Is the current task 32bit ? */
if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
return randomize_page(mm->brk, SZ_32M);
return randomize_page(mm->brk, SZ_1G);
}
unsigned long arch_mmap_rnd(void)
{
unsigned long rnd;
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
if (is_compat_task())
rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
else
#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */
rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
return rnd << PAGE_SHIFT;
}
static int mmap_is_legacy(struct rlimit *rlim_stack)
{
if (current->personality & ADDR_COMPAT_LAYOUT)
return 1;
/* On parisc the stack always grows up - so a unlimited stack should
* not be an indicator to use the legacy memory layout. */
if (rlim_stack->rlim_cur == RLIM_INFINITY &&
!IS_ENABLED(CONFIG_STACK_GROWSUP))
return 1;
return sysctl_legacy_va_layout;
}
/*
* Leave enough space between the mmap area and the stack to honour ulimit in
* the face of randomisation.
*/
#define MIN_GAP (SZ_128M)
#define MAX_GAP (STACK_TOP / 6 * 5)
static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
#ifdef CONFIG_STACK_GROWSUP
/*
* For an upwards growing stack the calculation is much simpler.
* Memory for the maximum stack size is reserved at the top of the
* task. mmap_base starts directly below the stack and grows
* downwards.
*/
return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd);
#else
unsigned long gap = rlim_stack->rlim_cur;
unsigned long pad = stack_guard_gap;
/* Account for stack randomization if necessary */
if (current->flags & PF_RANDOMIZE)
pad += (STACK_RND_MASK << PAGE_SHIFT);
/* Values close to RLIM_INFINITY can overflow. */
if (gap + pad > gap)
gap += pad;
if (gap < MIN_GAP && MIN_GAP < MAX_GAP)
gap = MIN_GAP;
else if (gap > MAX_GAP)
gap = MAX_GAP;
return PAGE_ALIGN(STACK_TOP - gap - rnd);
#endif
}
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
unsigned long random_factor = 0UL;
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
clear_bit(MMF_TOPDOWN, &mm->flags);
} else {
mm->mmap_base = mmap_base(random_factor, rlim_stack);
set_bit(MMF_TOPDOWN, &mm->flags);
}
}
#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
clear_bit(MMF_TOPDOWN, &mm->flags);
}
#endif
#ifdef CONFIG_MMU
EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout);
#endif
/**
* __account_locked_vm - account locked pages to an mm's locked_vm
* @mm: mm to account against
* @pages: number of pages to account
* @inc: %true if @pages should be considered positive, %false if not
* @task: task used to check RLIMIT_MEMLOCK
* @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
*
* Assumes @task and @mm are valid (i.e. at least one reference on each), and
* that mmap_lock is held as writer.
*
* Return:
* * 0 on success
* * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
struct task_struct *task, bool bypass_rlim)
{
unsigned long locked_vm, limit;
int ret = 0;
mmap_assert_write_locked(mm);
locked_vm = mm->locked_vm;
if (inc) {
if (!bypass_rlim) {
limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
if (locked_vm + pages > limit)
ret = -ENOMEM;
}
if (!ret)
mm->locked_vm = locked_vm + pages;
} else {
WARN_ON_ONCE(pages > locked_vm);
mm->locked_vm = locked_vm - pages;
}
pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
(void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
ret ? " - exceeded" : "");
return ret;
}
EXPORT_SYMBOL_GPL(__account_locked_vm);
/**
* account_locked_vm - account locked pages to an mm's locked_vm
* @mm: mm to account against, may be NULL
* @pages: number of pages to account
* @inc: %true if @pages should be considered positive, %false if not
*
* Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
*
* Return:
* * 0 on success, or if mm is NULL
* * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
{
int ret;
if (pages == 0 || !mm)
return 0;
mmap_write_lock(mm);
ret = __account_locked_vm(mm, pages, inc, current,
capable(CAP_IPC_LOCK));
mmap_write_unlock(mm);
return ret;
}
EXPORT_SYMBOL_GPL(account_locked_vm);
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)
{
unsigned long ret;
struct mm_struct *mm = current->mm;
unsigned long populate;
LIST_HEAD(uf);
ret = security_mmap_file(file, prot, flag);
if (!ret)
ret = fsnotify_mmap_perm(file, prot, pgoff >> PAGE_SHIFT, len); if (!ret) { if (mmap_write_lock_killable(mm))
return -EINTR;
ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate,
&uf);
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate) mm_populate(ret, populate);
}
return ret;
}
/*
* Perform a userland memory mapping into the current process address space. See
* the comment for do_mmap() for more details on this operation in general.
*
* This differs from do_mmap() in that:
*
* a. An offset parameter is provided rather than pgoff, which is both checked
* for overflow and page alignment.
* b. mmap locking is performed on the caller's behalf.
* c. Userfaultfd unmap events and memory population are handled.
*
* This means that this function performs essentially the same work as if
* userland were invoking mmap (2).
*
* Returns either an error, or the address at which the requested mapping has
* been performed.
*/
unsigned long vm_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long offset)
{
if (unlikely(offset + PAGE_ALIGN(len) < offset))
return -EINVAL;
if (unlikely(offset_in_page(offset)))
return -EINVAL;
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);
/**
* __vmalloc_array - allocate memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags)
{
size_t bytes;
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
return __vmalloc_noprof(bytes, flags);
}
EXPORT_SYMBOL(__vmalloc_array_noprof);
/**
* vmalloc_array - allocate memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
*/
void *vmalloc_array_noprof(size_t n, size_t size)
{
return __vmalloc_array_noprof(n, size, GFP_KERNEL);
}
EXPORT_SYMBOL(vmalloc_array_noprof);
/**
* __vcalloc - allocate and zero memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags)
{ return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(__vcalloc_noprof);
/**
* vcalloc - allocate and zero memory for a virtually contiguous array.
* @n: number of elements.
* @size: element size.
*/
void *vcalloc_noprof(size_t n, size_t size)
{
return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO);
}
EXPORT_SYMBOL(vcalloc_noprof);
struct anon_vma *folio_anon_vma(const struct folio *folio)
{
unsigned long mapping = (unsigned long)folio->mapping;
if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
return NULL;
return (void *)(mapping - PAGE_MAPPING_ANON);
}
/**
* folio_mapping - Find the mapping where this folio is stored.
* @folio: The folio.
*
* For folios which are in the page cache, return the mapping that this
* page belongs to. Folios in the swap cache return the swap mapping
* this page is stored in (which is different from the mapping for the
* swap file or swap device where the data is stored).
*
* You can call this for folios which aren't in the swap cache or page
* cache and it will return NULL.
*/
struct address_space *folio_mapping(struct folio *folio)
{
struct address_space *mapping;
/* This happens if someone calls flush_dcache_page on slab page */
if (unlikely(folio_test_slab(folio)))
return NULL;
if (unlikely(folio_test_swapcache(folio))) return swap_address_space(folio->swap);
mapping = folio->mapping;
if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
return NULL;
return mapping;
}
EXPORT_SYMBOL(folio_mapping);
/**
* folio_copy - Copy the contents of one folio to another.
* @dst: Folio to copy to.
* @src: Folio to copy from.
*
* The bytes in the folio represented by @src are copied to @dst.
* Assumes the caller has validated that @dst is at least as large as @src.
* Can be called in atomic context for order-0 folios, but if the folio is
* larger, it may sleep.
*/
void folio_copy(struct folio *dst, struct folio *src)
{
long i = 0;
long nr = folio_nr_pages(src);
for (;;) {
copy_highpage(folio_page(dst, i), folio_page(src, i));
if (++i == nr)
break;
cond_resched();
}
}
EXPORT_SYMBOL(folio_copy);
int folio_mc_copy(struct folio *dst, struct folio *src)
{
long nr = folio_nr_pages(src);
long i = 0;
for (;;) {
if (copy_mc_highpage(folio_page(dst, i), folio_page(src, i)))
return -EHWPOISON;
if (++i == nr)
break;
cond_resched();
}
return 0;
}
EXPORT_SYMBOL(folio_mc_copy);
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
static int sysctl_overcommit_ratio __read_mostly = 50;
static unsigned long sysctl_overcommit_kbytes __read_mostly;
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
#ifdef CONFIG_SYSCTL
static int overcommit_ratio_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_kbytes = 0;
return ret;
}
static void sync_overcommit_as(struct work_struct *dummy)
{
percpu_counter_sync(&vm_committed_as);
}
static int overcommit_policy_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int new_policy = -1;
int ret;
/*
* The deviation of sync_overcommit_as could be big with loose policy
* like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
* strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
* with the strict "NEVER", and to avoid possible race condition (even
* though user usually won't too frequently do the switching to policy
* OVERCOMMIT_NEVER), the switch is done in the following order:
* 1. changing the batch
* 2. sync percpu count on each CPU
* 3. switch the policy
*/
if (write) {
t = *table;
t.data = &new_policy;
ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (ret || new_policy == -1)
return ret;
mm_compute_batch(new_policy);
if (new_policy == OVERCOMMIT_NEVER)
schedule_on_each_cpu(sync_overcommit_as);
sysctl_overcommit_memory = new_policy;
} else {
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
return ret;
}
static int overcommit_kbytes_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_ratio = 0;
return ret;
}
static const struct ctl_table util_sysctl_table[] = {
{
.procname = "overcommit_memory",
.data = &sysctl_overcommit_memory,
.maxlen = sizeof(sysctl_overcommit_memory),
.mode = 0644,
.proc_handler = overcommit_policy_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "overcommit_ratio",
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
.proc_handler = overcommit_ratio_handler,
},
{
.procname = "overcommit_kbytes",
.data = &sysctl_overcommit_kbytes,
.maxlen = sizeof(sysctl_overcommit_kbytes),
.mode = 0644,
.proc_handler = overcommit_kbytes_handler,
},
{
.procname = "user_reserve_kbytes",
.data = &sysctl_user_reserve_kbytes,
.maxlen = sizeof(sysctl_user_reserve_kbytes),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "admin_reserve_kbytes",
.data = &sysctl_admin_reserve_kbytes,
.maxlen = sizeof(sysctl_admin_reserve_kbytes),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
};
static int __init init_vm_util_sysctls(void)
{
register_sysctl_init("vm", util_sysctl_table);
return 0;
}
subsys_initcall(init_vm_util_sysctls);
#endif /* CONFIG_SYSCTL */
/*
* Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
*/
unsigned long vm_commit_limit(void)
{
unsigned long allowed;
if (sysctl_overcommit_kbytes)
allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
else
allowed = ((totalram_pages() - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100);
allowed += total_swap_pages;
return allowed;
}
/*
* Make sure vm_committed_as in one cacheline and not cacheline shared with
* other variables. It can be updated by several CPUs frequently.
*/
struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
/*
* The global memory commitment made in the system can be a metric
* that can be used to drive ballooning decisions when Linux is hosted
* as a guest. On Hyper-V, the host implements a policy engine for dynamically
* balancing memory across competing virtual machines that are hosted.
* Several metrics drive this policy engine including the guest reported
* memory commitment.
*
* The time cost of this is very low for small platforms, and for big
* platform like a 2S/36C/72T Skylake server, in worst case where
* vm_committed_as's spinlock is under severe contention, the time cost
* could be about 30~40 microseconds.
*/
unsigned long vm_memory_committed(void)
{
return percpu_counter_sum_positive(&vm_committed_as);
}
EXPORT_SYMBOL_GPL(vm_memory_committed);
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
* succeed and -ENOMEM implies there is not.
*
* We currently support three overcommit policies, which are set via the
* vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst
*
* Strict overcommit modes added 2002 Feb 26 by Alan Cox.
* Additional code 2002 Jul 20 by Robert Love.
*
* cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
*
* Note this is a helper function intended to be used by LSMs which
* wish to use this logic.
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
long allowed;
unsigned long bytes_failed;
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
if (pages > totalram_pages() + total_swap_pages)
goto error;
return 0;
}
allowed = vm_commit_limit();
/*
* Reserve some for root
*/
if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
/*
* Don't let a single process grow so big a user can't recover
*/
if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
allowed -= min_t(long, mm->total_vm / 32, reserve);
}
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
bytes_failed = pages << PAGE_SHIFT; pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n",
__func__, current->pid, current->comm, bytes_failed);
vm_unacct_memory(pages);
return -ENOMEM;
}
/**
* get_cmdline() - copy the cmdline value to a buffer.
* @task: the task whose cmdline value to copy.
* @buffer: the buffer to copy to.
* @buflen: the length of the buffer. Larger cmdline values are truncated
* to this length.
*
* Return: the size of the cmdline field copied. Note that the copy does
* not guarantee an ending NULL byte.
*/
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
{
int res = 0;
unsigned int len;
struct mm_struct *mm = get_task_mm(task);
unsigned long arg_start, arg_end, env_start, env_end;
if (!mm)
goto out;
if (!mm->arg_end)
goto out_mm; /* Shh! No looking before we're done */
spin_lock(&mm->arg_lock);
arg_start = mm->arg_start;
arg_end = mm->arg_end;
env_start = mm->env_start;
env_end = mm->env_end;
spin_unlock(&mm->arg_lock);
len = arg_end - arg_start;
if (len > buflen)
len = buflen;
res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE);
/*
* If the nul at the end of args has been overwritten, then
* assume application is using setproctitle(3).
*/
if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
len = strnlen(buffer, res);
if (len < res) {
res = len;
} else {
len = env_end - env_start;
if (len > buflen - res)
len = buflen - res;
res += access_process_vm(task, env_start,
buffer+res, len,
FOLL_FORCE);
res = strnlen(buffer, res);
}
}
out_mm:
mmput(mm);
out:
return res;
}
int __weak memcmp_pages(struct page *page1, struct page *page2)
{
char *addr1, *addr2;
int ret;
addr1 = kmap_local_page(page1);
addr2 = kmap_local_page(page2);
ret = memcmp(addr1, addr2, PAGE_SIZE);
kunmap_local(addr2);
kunmap_local(addr1);
return ret;
}
#ifdef CONFIG_PRINTK
/**
* mem_dump_obj - Print available provenance information
* @object: object for which to find provenance information.
*
* This function uses pr_cont(), so that the caller is expected to have
* printed out whatever preamble is appropriate. The provenance information
* depends on the type of object and on how much debugging is enabled.
* For example, for a slab-cache object, the slab name is printed, and,
* if available, the return address and stack trace from the allocation
* and last free path of that object.
*/
void mem_dump_obj(void *object)
{
const char *type;
if (kmem_dump_obj(object))
return;
if (vmalloc_dump_obj(object))
return;
if (is_vmalloc_addr(object))
type = "vmalloc memory";
else if (virt_addr_valid(object))
type = "non-slab/vmalloc memory";
else if (object == NULL)
type = "NULL pointer";
else if (object == ZERO_SIZE_PTR)
type = "zero-size pointer";
else
type = "non-paged memory";
pr_cont(" %s\n", type);
}
EXPORT_SYMBOL_GPL(mem_dump_obj);
#endif
/*
* A driver might set a page logically offline -- PageOffline() -- and
* turn the page inaccessible in the hypervisor; after that, access to page
* content can be fatal.
*
* Some special PFN walkers -- i.e., /proc/kcore -- read content of random
* pages after checking PageOffline(); however, these PFN walkers can race
* with drivers that set PageOffline().
*
* page_offline_freeze()/page_offline_thaw() allows for a subsystem to
* synchronize with such drivers, achieving that a page cannot be set
* PageOffline() while frozen.
*
* page_offline_begin()/page_offline_end() is used by drivers that care about
* such races when setting a page PageOffline().
*/
static DECLARE_RWSEM(page_offline_rwsem);
void page_offline_freeze(void)
{
down_read(&page_offline_rwsem);
}
void page_offline_thaw(void)
{
up_read(&page_offline_rwsem);
}
void page_offline_begin(void)
{
down_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_begin);
void page_offline_end(void)
{
up_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_end);
#ifndef flush_dcache_folio
void flush_dcache_folio(struct folio *folio)
{
long i, nr = folio_nr_pages(folio);
for (i = 0; i < nr; i++)
flush_dcache_page(folio_page(folio, i));
}
EXPORT_SYMBOL(flush_dcache_folio);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PIPE_FS_I_H
#define _LINUX_PIPE_FS_I_H
#define PIPE_DEF_BUFFERS 16
#define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */
#define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */
#define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */
#define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */
#define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */
#define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */
#ifdef CONFIG_WATCH_QUEUE
#define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */
#endif
/**
* struct pipe_buffer - a linux kernel pipe buffer
* @page: the page containing the data for the pipe buffer
* @offset: offset of data inside the @page
* @len: length of data inside the @page
* @ops: operations associated with this buffer. See @pipe_buf_operations.
* @flags: pipe buffer flags. See above.
* @private: private data owned by the ops.
**/
struct pipe_buffer {
struct page *page;
unsigned int offset, len;
const struct pipe_buf_operations *ops;
unsigned int flags;
unsigned long private;
};
/*
* Really only alpha needs 32-bit fields, but
* might as well do it for 64-bit architectures
* since that's what we've historically done,
* and it makes 'head_tail' always be a simple
* 'unsigned long'.
*/
#ifdef CONFIG_64BIT
typedef unsigned int pipe_index_t;
#else
typedef unsigned short pipe_index_t;
#endif
/*
* We have to declare this outside 'struct pipe_inode_info',
* but then we can't use 'union pipe_index' for an anonymous
* union, so we end up having to duplicate this declaration
* below. Annoying.
*/
union pipe_index {
unsigned long head_tail;
struct {
pipe_index_t head;
pipe_index_t tail;
};
};
/**
* struct pipe_inode_info - a linux kernel pipe
* @mutex: mutex protecting the whole thing
* @rd_wait: reader wait point in case of empty pipe
* @wr_wait: writer wait point in case of full pipe
* @head: The point of buffer production
* @tail: The point of buffer consumption
* @head_tail: unsigned long union of @head and @tail
* @note_loss: The next read() should insert a data-lost message
* @max_usage: The maximum number of slots that may be used in the ring
* @ring_size: total number of buffers (should be a power of 2)
* @nr_accounted: The amount this pipe accounts for in user->pipe_bufs
* @tmp_page: cached released page
* @readers: number of current readers of this pipe
* @writers: number of current writers of this pipe
* @files: number of struct file referring this pipe (protected by ->i_lock)
* @r_counter: reader counter
* @w_counter: writer counter
* @poll_usage: is this pipe used for epoll, which has crazy wakeups?
* @fasync_readers: reader side fasync
* @fasync_writers: writer side fasync
* @bufs: the circular array of pipe buffers
* @user: the user who created this pipe
* @watch_queue: If this pipe is a watch_queue, this is the stuff for that
**/
struct pipe_inode_info {
struct mutex mutex;
wait_queue_head_t rd_wait, wr_wait;
/* This has to match the 'union pipe_index' above */
union {
unsigned long head_tail;
struct {
pipe_index_t head;
pipe_index_t tail;
};
};
unsigned int max_usage;
unsigned int ring_size;
unsigned int nr_accounted;
unsigned int readers;
unsigned int writers;
unsigned int files;
unsigned int r_counter;
unsigned int w_counter;
bool poll_usage;
#ifdef CONFIG_WATCH_QUEUE
bool note_loss;
#endif
struct page *tmp_page[2];
struct fasync_struct *fasync_readers;
struct fasync_struct *fasync_writers;
struct pipe_buffer *bufs;
struct user_struct *user;
#ifdef CONFIG_WATCH_QUEUE
struct watch_queue *watch_queue;
#endif
};
/*
* Note on the nesting of these functions:
*
* ->confirm()
* ->try_steal()
*
* That is, ->try_steal() must be called on a confirmed buffer. See below for
* the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the
* pipe and generic variants of these hooks.
*/
struct pipe_buf_operations {
/*
* ->confirm() verifies that the data in the pipe buffer is there
* and that the contents are good. If the pages in the pipe belong
* to a file system, we may need to wait for IO completion in this
* hook. Returns 0 for good, or a negative error value in case of
* error. If not present all pages are considered good.
*/
int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *);
/*
* When the contents of this pipe buffer has been completely
* consumed by a reader, ->release() is called.
*/
void (*release)(struct pipe_inode_info *, struct pipe_buffer *);
/*
* Attempt to take ownership of the pipe buffer and its contents.
* ->try_steal() returns %true for success, in which case the contents
* of the pipe (the buf->page) is locked and now completely owned by the
* caller. The page may then be transferred to a different mapping, the
* most often used case is insertion into different file address space
* cache.
*/
bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *);
/*
* Get a reference to the pipe buffer.
*/
bool (*get)(struct pipe_inode_info *, struct pipe_buffer *);
};
/**
* pipe_has_watch_queue - Check whether the pipe is a watch_queue,
* i.e. it was created with O_NOTIFICATION_PIPE
* @pipe: The pipe to check
*
* Return: true if pipe is a watch queue, false otherwise.
*/
static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe)
{
#ifdef CONFIG_WATCH_QUEUE
return pipe->watch_queue != NULL;
#else
return false;
#endif
}
/**
* pipe_occupancy - Return number of slots used in the pipe
* @head: The pipe ring head pointer
* @tail: The pipe ring tail pointer
*/
static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
{
return (pipe_index_t)(head - tail);
}
/**
* pipe_empty - Return true if the pipe is empty
* @head: The pipe ring head pointer
* @tail: The pipe ring tail pointer
*/
static inline bool pipe_empty(unsigned int head, unsigned int tail)
{
return !pipe_occupancy(head, tail);
}
/**
* pipe_full - Return true if the pipe is full
* @head: The pipe ring head pointer
* @tail: The pipe ring tail pointer
* @limit: The maximum amount of slots available.
*/
static inline bool pipe_full(unsigned int head, unsigned int tail,
unsigned int limit)
{
return pipe_occupancy(head, tail) >= limit;
}
/**
* pipe_is_full - Return true if the pipe is full
* @pipe: the pipe
*/
static inline bool pipe_is_full(const struct pipe_inode_info *pipe)
{
return pipe_full(pipe->head, pipe->tail, pipe->max_usage);
}
/**
* pipe_is_empty - Return true if the pipe is empty
* @pipe: the pipe
*/
static inline bool pipe_is_empty(const struct pipe_inode_info *pipe)
{
return pipe_empty(pipe->head, pipe->tail);
}
/**
* pipe_buf_usage - Return how many pipe buffers are in use
* @pipe: the pipe
*/
static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe)
{
return pipe_occupancy(pipe->head, pipe->tail);
}
/**
* pipe_buf - Return the pipe buffer for the specified slot in the pipe ring
* @pipe: The pipe to access
* @slot: The slot of interest
*/
static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe,
unsigned int slot)
{
return &pipe->bufs[slot & (pipe->ring_size - 1)];
}
/**
* pipe_head_buf - Return the pipe buffer at the head of the pipe ring
* @pipe: The pipe to access
*/
static inline struct pipe_buffer *pipe_head_buf(const struct pipe_inode_info *pipe)
{
return pipe_buf(pipe, pipe->head);
}
/**
* pipe_buf_get - get a reference to a pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to get a reference to
*
* Return: %true if the reference was successfully obtained.
*/
static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
return buf->ops->get(pipe, buf);
}
/**
* pipe_buf_release - put a reference to a pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to put a reference to
*/
static inline void pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
const struct pipe_buf_operations *ops = buf->ops;
buf->ops = NULL;
ops->release(pipe, buf);
}
/**
* pipe_buf_confirm - verify contents of the pipe buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to confirm
*/
static inline int pipe_buf_confirm(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
if (!buf->ops->confirm)
return 0;
return buf->ops->confirm(pipe, buf);
}
/**
* pipe_buf_try_steal - attempt to take ownership of a pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to attempt to steal
*/
static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
if (!buf->ops->try_steal)
return false;
return buf->ops->try_steal(pipe, buf);
}
/* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
memory allocation, whereas PIPE_BUF makes atomicity guarantees. */
#define PIPE_SIZE PAGE_SIZE
/* Pipe lock and unlock operations */
void pipe_lock(struct pipe_inode_info *);
void pipe_unlock(struct pipe_inode_info *);
void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
/* Wait for a pipe to be readable/writable while dropping the pipe lock */
void pipe_wait_readable(struct pipe_inode_info *);
void pipe_wait_writable(struct pipe_inode_info *);
struct pipe_inode_info *alloc_pipe_info(void);
void free_pipe_info(struct pipe_inode_info *);
/* Generic pipe buffer ops functions */
bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
unsigned long account_pipe_buffers(struct user_struct *user,
unsigned long old, unsigned long new);
bool too_many_pipe_buffers_soft(unsigned long user_bufs);
bool too_many_pipe_buffers_hard(unsigned long user_bufs);
bool pipe_is_unprivileged_user(void);
/* for F_SETPIPE_SZ and F_GETPIPE_SZ */
int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots);
long pipe_fcntl(struct file *, unsigned int, unsigned int arg);
struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice);
int create_pipe_files(struct file **, int);
unsigned int round_pipe_size(unsigned int size);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_UACCESS_H__
#define __LINUX_UACCESS_H__
#include <linux/fault-inject-usercopy.h>
#include <linux/instrumented.h>
#include <linux/minmax.h>
#include <linux/nospec.h>
#include <linux/sched.h>
#include <linux/ucopysize.h>
#include <asm/uaccess.h>
/*
* Architectures that support memory tagging (assigning tags to memory regions,
* embedding these tags into addresses that point to these memory regions, and
* checking that the memory and the pointer tags match on memory accesses)
* redefine this macro to strip tags from pointers.
*
* Passing down mm_struct allows to define untagging rules on per-process
* basis.
*
* It's defined as noop for architectures that don't support memory tagging.
*/
#ifndef untagged_addr
#define untagged_addr(addr) (addr)
#endif
#ifndef untagged_addr_remote
#define untagged_addr_remote(mm, addr) ({ \
mmap_assert_locked(mm); \
untagged_addr(addr); \
})
#endif
#ifdef masked_user_access_begin
#define can_do_masked_user_access() 1
#else
#define can_do_masked_user_access() 0
#define masked_user_access_begin(src) NULL
#define mask_user_address(src) (src)
#endif
/*
* Architectures should provide two primitives (raw_copy_{to,from}_user())
* and get rid of their private instances of copy_{to,from}_user() and
* __copy_{to,from}_user{,_inatomic}().
*
* raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and
* return the amount left to copy. They should assume that access_ok() has
* already been checked (and succeeded); they should *not* zero-pad anything.
* No KASAN or object size checks either - those belong here.
*
* Both of these functions should attempt to copy size bytes starting at from
* into the area starting at to. They must not fetch or store anything
* outside of those areas. Return value must be between 0 (everything
* copied successfully) and size (nothing copied).
*
* If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting
* at to must become equal to the bytes fetched from the corresponding area
* starting at from. All data past to + size - N must be left unmodified.
*
* If copying succeeds, the return value must be 0. If some data cannot be
* fetched, it is permitted to copy less than had been fetched; the only
* hard requirement is that not storing anything at all (i.e. returning size)
* should happen only when nothing could be copied. In other words, you don't
* have to squeeze as much as possible - it is allowed, but not necessary.
*
* For raw_copy_from_user() to always points to kernel memory and no faults
* on store should happen. Interpretation of from is affected by set_fs().
* For raw_copy_to_user() it's the other way round.
*
* Both can be inlined - it's up to architectures whether it wants to bother
* with that. They should not be used directly; they are used to implement
* the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic())
* that are used instead. Out of those, __... ones are inlined. Plain
* copy_{to,from}_user() might or might not be inlined. If you want them
* inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER.
*
* NOTE: only copy_from_user() zero-pads the destination in case of short copy.
* Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything
* at all; their callers absolutely must check the return value.
*
* Biarch ones should also provide raw_copy_in_user() - similar to the above,
* but both source and destination are __user pointers (affected by set_fs()
* as usual) and both source and destination can trigger faults.
*/
static __always_inline __must_check unsigned long
__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
{
unsigned long res;
instrument_copy_from_user_before(to, from, n);
check_object_size(to, n, false);
res = raw_copy_from_user(to, from, n);
instrument_copy_from_user_after(to, from, n, res);
return res;
}
static __always_inline __must_check unsigned long
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res;
might_fault();
instrument_copy_from_user_before(to, from, n);
if (should_fail_usercopy())
return n;
check_object_size(to, n, false);
res = raw_copy_from_user(to, from, n);
instrument_copy_from_user_after(to, from, n, res);
return res;
}
/**
* __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
* @to: Destination address, in user space.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
* Context: User context only.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* The caller should also make sure he pins the user space address
* so that we don't result in page fault and sleep.
*/
static __always_inline __must_check unsigned long
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
if (should_fail_usercopy())
return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
}
static __always_inline __must_check unsigned long
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
if (should_fail_usercopy())
return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
}
/*
* Architectures that #define INLINE_COPY_TO_USER use this function
* directly in the normal copy_to/from_user(), the other ones go
* through an extern _copy_to/from_user(), which expands the same code
* here.
*
* Rust code always uses the extern definition.
*/
static inline __must_check unsigned long
_inline_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
might_fault();
if (should_fail_usercopy())
goto fail;
if (can_do_masked_user_access())
from = mask_user_address(from);
else {
if (!access_ok(from, n))
goto fail;
/*
* Ensure that bad access_ok() speculation will not
* lead to nasty side effects *after* the copy is
* finished:
*/
barrier_nospec();
}
instrument_copy_from_user_before(to, from, n);
res = raw_copy_from_user(to, from, n);
instrument_copy_from_user_after(to, from, n, res);
if (likely(!res))
return 0;
fail:
memset(to + (n - res), 0, res);
return res;
}
extern __must_check unsigned long
_copy_from_user(void *, const void __user *, unsigned long);
static inline __must_check unsigned long
_inline_copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
if (should_fail_usercopy())
return n;
if (access_ok(to, n)) { instrument_copy_to_user(to, from, n);
n = raw_copy_to_user(to, from, n);
}
return n;
}
extern __must_check unsigned long
_copy_to_user(void __user *, const void *, unsigned long);
static __always_inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
if (!check_copy_size(to, n, false))
return n;
#ifdef INLINE_COPY_FROM_USER
return _inline_copy_from_user(to, from, n);
#else
return _copy_from_user(to, from, n);
#endif
}
static __always_inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
if (!check_copy_size(from, n, true))
return n;
#ifdef INLINE_COPY_TO_USER
return _inline_copy_to_user(to, from, n);
#else
return _copy_to_user(to, from, n);
#endif
}
#ifndef copy_mc_to_kernel
/*
* Without arch opt-in this generic copy_mc_to_kernel() will not handle
* #MC (or arch equivalent) during source read.
*/
static inline unsigned long __must_check
copy_mc_to_kernel(void *dst, const void *src, size_t cnt)
{
memcpy(dst, src, cnt);
return 0;
}
#endif
static __always_inline void pagefault_disabled_inc(void)
{
current->pagefault_disabled++;
}
static __always_inline void pagefault_disabled_dec(void)
{
current->pagefault_disabled--;
}
/*
* These routines enable/disable the pagefault handler. If disabled, it will
* not take any locks and go straight to the fixup table.
*
* User access methods will not sleep when called from a pagefault_disabled()
* environment.
*/
static inline void pagefault_disable(void)
{
pagefault_disabled_inc();
/*
* make sure to have issued the store before a pagefault
* can hit.
*/
barrier();
}
static inline void pagefault_enable(void)
{
/*
* make sure to issue those last loads/stores before enabling
* the pagefault handler again.
*/
barrier();
pagefault_disabled_dec();
}
/*
* Is the pagefault handler disabled? If so, user access methods will not sleep.
*/
static inline bool pagefault_disabled(void)
{
return current->pagefault_disabled != 0;
}
/*
* The pagefault handler is in general disabled by pagefault_disable() or
* when in irq context (via in_atomic()).
*
* This function should only be used by the fault handlers. Other users should
* stick to pagefault_disabled().
* Please NEVER use preempt_disable() to disable the fault handler. With
* !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
* in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
*/
#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
/**
* probe_subpage_writeable: probe the user range for write faults at sub-page
* granularity (e.g. arm64 MTE)
* @uaddr: start of address range
* @size: size of address range
*
* Returns 0 on success, the number of bytes not probed on fault.
*
* It is expected that the caller checked for the write permission of each
* page in the range either by put_user() or GUP. The architecture port can
* implement a more efficient get_user() probing if the same sub-page faults
* are triggered by either a read or a write.
*/
static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
#ifndef ARCH_HAS_NOCACHE_UACCESS
static inline __must_check unsigned long
__copy_from_user_inatomic_nocache(void *to, const void __user *from,
unsigned long n)
{
return __copy_from_user_inatomic(to, from, n);
}
#endif /* ARCH_HAS_NOCACHE_UACCESS */
extern __must_check int check_zeroed_user(const void __user *from, size_t size);
/**
* copy_struct_from_user: copy a struct from userspace
* @dst: Destination address, in kernel space. This buffer must be @ksize
* bytes long.
* @ksize: Size of @dst struct.
* @src: Source address, in userspace.
* @usize: (Alleged) size of @src struct.
*
* Copies a struct from userspace to kernel space, in a way that guarantees
* backwards-compatibility for struct syscall arguments (as long as future
* struct extensions are made such that all new fields are *appended* to the
* old struct, and zeroed-out new fields have the same meaning as the old
* struct).
*
* @ksize is just sizeof(*dst), and @usize should've been passed by userspace.
* The recommended usage is something like the following:
*
* SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize)
* {
* int err;
* struct foo karg = {};
*
* if (usize > PAGE_SIZE)
* return -E2BIG;
* if (usize < FOO_SIZE_VER0)
* return -EINVAL;
*
* err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize);
* if (err)
* return err;
*
* // ...
* }
*
* There are three cases to consider:
* * If @usize == @ksize, then it's copied verbatim.
* * If @usize < @ksize, then the userspace has passed an old struct to a
* newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize)
* are to be zero-filled.
* * If @usize > @ksize, then the userspace has passed a new struct to an
* older kernel. The trailing bytes unknown to the kernel (@usize - @ksize)
* are checked to ensure they are zeroed, otherwise -E2BIG is returned.
*
* Returns (in all cases, some data may have been copied):
* * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src.
* * -EFAULT: access to userspace failed.
*/
static __always_inline __must_check int
copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
size_t usize)
{
size_t size = min(ksize, usize);
size_t rest = max(ksize, usize) - size;
/* Double check if ksize is larger than a known object size. */
if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1)))
return -E2BIG;
/* Deal with trailing bytes. */
if (usize < ksize) {
memset(dst + size, 0, rest);
} else if (usize > ksize) {
int ret = check_zeroed_user(src + size, rest);
if (ret <= 0)
return ret ?: -E2BIG;
}
/* Copy the interoperable parts of the struct. */
if (copy_from_user(dst, src, size))
return -EFAULT;
return 0;
}
/**
* copy_struct_to_user: copy a struct to userspace
* @dst: Destination address, in userspace. This buffer must be @ksize
* bytes long.
* @usize: (Alleged) size of @dst struct.
* @src: Source address, in kernel space.
* @ksize: Size of @src struct.
* @ignored_trailing: Set to %true if there was a non-zero byte in @src that
* userspace cannot see because they are using an smaller struct.
*
* Copies a struct from kernel space to userspace, in a way that guarantees
* backwards-compatibility for struct syscall arguments (as long as future
* struct extensions are made such that all new fields are *appended* to the
* old struct, and zeroed-out new fields have the same meaning as the old
* struct).
*
* Some syscalls may wish to make sure that userspace knows about everything in
* the struct, and if there is a non-zero value that userspce doesn't know
* about, they want to return an error (such as -EMSGSIZE) or have some other
* fallback (such as adding a "you're missing some information" flag). If
* @ignored_trailing is non-%NULL, it will be set to %true if there was a
* non-zero byte that could not be copied to userspace (ie. was past @usize).
*
* While unconditionally returning an error in this case is the simplest
* solution, for maximum backward compatibility you should try to only return
* -EMSGSIZE if the user explicitly requested the data that couldn't be copied.
* Note that structure sizes can change due to header changes and simple
* recompilations without code changes(!), so if you care about
* @ignored_trailing you probably want to make sure that any new field data is
* associated with a flag. Otherwise you might assume that a program knows
* about data it does not.
*
* @ksize is just sizeof(*src), and @usize should've been passed by userspace.
* The recommended usage is something like the following:
*
* SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize)
* {
* int err;
* bool ignored_trailing;
* struct foo karg = {};
*
* if (usize > PAGE_SIZE)
* return -E2BIG;
* if (usize < FOO_SIZE_VER0)
* return -EINVAL;
*
* // ... modify karg somehow ...
*
* err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg),
* &ignored_trailing);
* if (err)
* return err;
* if (ignored_trailing)
* return -EMSGSIZE:
*
* // ...
* }
*
* There are three cases to consider:
* * If @usize == @ksize, then it's copied verbatim.
* * If @usize < @ksize, then the kernel is trying to pass userspace a newer
* struct than it supports. Thus we only copy the interoperable portions
* (@usize) and ignore the rest (but @ignored_trailing is set to %true if
* any of the trailing (@ksize - @usize) bytes are non-zero).
* * If @usize > @ksize, then the kernel is trying to pass userspace an older
* struct than userspace supports. In order to make sure the
* unknown-to-the-kernel fields don't contain garbage values, we zero the
* trailing (@usize - @ksize) bytes.
*
* Returns (in all cases, some data may have been copied):
* * -EFAULT: access to userspace failed.
*/
static __always_inline __must_check int
copy_struct_to_user(void __user *dst, size_t usize, const void *src,
size_t ksize, bool *ignored_trailing)
{
size_t size = min(ksize, usize);
size_t rest = max(ksize, usize) - size;
/* Double check if ksize is larger than a known object size. */
if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1)))
return -E2BIG;
/* Deal with trailing bytes. */
if (usize > ksize) {
if (clear_user(dst + size, rest))
return -EFAULT;
}
if (ignored_trailing)
*ignored_trailing = ksize < usize &&
memchr_inv(src + size, 0, rest) != NULL;
/* Copy the interoperable parts of the struct. */
if (copy_to_user(dst, src, size))
return -EFAULT;
return 0;
}
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size);
long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size);
long copy_from_user_nofault(void *dst, const void __user *src, size_t size);
long notrace copy_to_user_nofault(void __user *dst, const void *src,
size_t size);
long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,
long count);
long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
long count);
long strnlen_user_nofault(const void __user *unsafe_addr, long count);
#ifndef __get_kernel_nofault
#define __get_kernel_nofault(dst, src, type, label) \
do { \
type __user *p = (type __force __user *)(src); \
type data; \
if (__get_user(data, p)) \
goto label; \
*(type *)dst = data; \
} while (0)
#define __put_kernel_nofault(dst, src, type, label) \
do { \
type __user *p = (type __force __user *)(dst); \
type data = *(type *)src; \
if (__put_user(data, p)) \
goto label; \
} while (0)
#endif
/**
* get_kernel_nofault(): safely attempt to read from a location
* @val: read into this variable
* @ptr: address to read from
*
* Returns 0 on success, or -EFAULT.
*/
#define get_kernel_nofault(val, ptr) ({ \
const typeof(val) *__gk_ptr = (ptr); \
copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\
})
#ifndef user_access_begin
#define user_access_begin(ptr,len) access_ok(ptr, len)
#define user_access_end() do { } while (0)
#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
#define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e)
#define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e)
#define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e)
#define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e)
static inline unsigned long user_access_save(void) { return 0UL; }
static inline void user_access_restore(unsigned long flags) { }
#endif
#ifndef user_write_access_begin
#define user_write_access_begin user_access_begin
#define user_write_access_end user_access_end
#endif
#ifndef user_read_access_begin
#define user_read_access_begin user_access_begin
#define user_read_access_end user_access_end
#endif
#ifdef CONFIG_HARDENED_USERCOPY
void __noreturn usercopy_abort(const char *name, const char *detail,
bool to_user, unsigned long offset,
unsigned long len);
#endif
#endif /* __LINUX_UACCESS_H__ */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/madvise.c
*
* Copyright (C) 1999 Linus Torvalds
* Copyright (C) 2002 Christoph Hellwig
*/
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
#include <linux/page-isolation.h>
#include <linux/page_idle.h>
#include <linux/userfaultfd_k.h>
#include <linux/hugetlb.h>
#include <linux/falloc.h>
#include <linux/fadvise.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/mm_inline.h>
#include <linux/string.h>
#include <linux/uio.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/pagewalk.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>
#include <asm/tlb.h>
#include "internal.h"
#include "swap.h"
/*
* Maximum number of attempts we make to install guard pages before we give up
* and return -ERESTARTNOINTR to have userspace try again.
*/
#define MAX_MADVISE_GUARD_RETRIES 3
struct madvise_walk_private {
struct mmu_gather *tlb;
bool pageout;
};
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
* take mmap_lock for writing. Others, which simply traverse vmas, need
* to only take it for reading.
*/
static int madvise_need_mmap_write(int behavior)
{
switch (behavior) {
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
case MADV_DONTNEED_LOCKED:
case MADV_COLD:
case MADV_PAGEOUT:
case MADV_FREE:
case MADV_POPULATE_READ:
case MADV_POPULATE_WRITE:
case MADV_COLLAPSE:
case MADV_GUARD_INSTALL:
case MADV_GUARD_REMOVE:
return 0;
default:
/* be safe, default to 1. list exceptions explicitly */
return 1;
}
}
#ifdef CONFIG_ANON_VMA_NAME
struct anon_vma_name *anon_vma_name_alloc(const char *name)
{
struct anon_vma_name *anon_name;
size_t count;
/* Add 1 for NUL terminator at the end of the anon_name->name */
count = strlen(name) + 1;
anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL);
if (anon_name) {
kref_init(&anon_name->kref);
memcpy(anon_name->name, name, count);
}
return anon_name;
}
void anon_vma_name_free(struct kref *kref)
{
struct anon_vma_name *anon_name =
container_of(kref, struct anon_vma_name, kref);
kfree(anon_name);
}
struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
{ mmap_assert_locked(vma->vm_mm);
return vma->anon_name;
}
/* mmap_lock should be write-locked */
static int replace_anon_vma_name(struct vm_area_struct *vma,
struct anon_vma_name *anon_name)
{
struct anon_vma_name *orig_name = anon_vma_name(vma);
if (!anon_name) {
vma->anon_name = NULL;
anon_vma_name_put(orig_name);
return 0;
}
if (anon_vma_name_eq(orig_name, anon_name))
return 0;
vma->anon_name = anon_vma_name_reuse(anon_name);
anon_vma_name_put(orig_name);
return 0;
}
#else /* CONFIG_ANON_VMA_NAME */
static int replace_anon_vma_name(struct vm_area_struct *vma,
struct anon_vma_name *anon_name)
{
if (anon_name)
return -EINVAL;
return 0;
}
#endif /* CONFIG_ANON_VMA_NAME */
/*
* Update the vm_flags on region of a vma, splitting it or merging it as
* necessary. Must be called with mmap_lock held for writing;
* Caller should ensure anon_name stability by raising its refcount even when
* anon_name belongs to a valid vma because this function might free that vma.
*/
static int madvise_update_vma(struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
unsigned long end, unsigned long new_flags,
struct anon_vma_name *anon_name)
{
struct mm_struct *mm = vma->vm_mm;
int error;
VMA_ITERATOR(vmi, mm, start);
if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) {
*prev = vma;
return 0;
}
vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags,
anon_name);
if (IS_ERR(vma))
return PTR_ERR(vma);
*prev = vma;
/* vm_flags is protected by the mmap_lock held in write mode. */
vma_start_write(vma);
vm_flags_reset(vma, new_flags);
if (!vma->vm_file || vma_is_anon_shmem(vma)) {
error = replace_anon_vma_name(vma, anon_name);
if (error)
return error;
}
return 0;
}
#ifdef CONFIG_SWAP
static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->private;
struct swap_iocb *splug = NULL;
pte_t *ptep = NULL;
spinlock_t *ptl;
unsigned long addr;
for (addr = start; addr < end; addr += PAGE_SIZE) {
pte_t pte;
swp_entry_t entry;
struct folio *folio;
if (!ptep++) {
ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (!ptep)
break;
}
pte = ptep_get(ptep);
if (!is_swap_pte(pte))
continue;
entry = pte_to_swp_entry(pte);
if (unlikely(non_swap_entry(entry)))
continue;
pte_unmap_unlock(ptep, ptl);
ptep = NULL;
folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
vma, addr, &splug);
if (folio)
folio_put(folio);
}
if (ptep)
pte_unmap_unlock(ptep, ptl);
swap_read_unplug(splug);
cond_resched();
return 0;
}
static const struct mm_walk_ops swapin_walk_ops = {
.pmd_entry = swapin_walk_pmd_entry,
.walk_lock = PGWALK_RDLOCK,
};
static void shmem_swapin_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct address_space *mapping)
{
XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
pgoff_t end_index = linear_page_index(vma, end) - 1;
struct folio *folio;
struct swap_iocb *splug = NULL;
rcu_read_lock();
xas_for_each(&xas, folio, end_index) {
unsigned long addr;
swp_entry_t entry;
if (!xa_is_value(folio))
continue;
entry = radix_to_swp_entry(folio);
/* There might be swapin error entries in shmem mapping. */
if (non_swap_entry(entry))
continue;
addr = vma->vm_start +
((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT);
xas_pause(&xas);
rcu_read_unlock();
folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
vma, addr, &splug);
if (folio)
folio_put(folio);
rcu_read_lock();
}
rcu_read_unlock();
swap_read_unplug(splug);
}
#endif /* CONFIG_SWAP */
/*
* Schedule all required I/O operations. Do not wait for completion.
*/
static long madvise_willneed(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
loff_t offset;
*prev = vma;
#ifdef CONFIG_SWAP
if (!file) {
walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma);
lru_add_drain(); /* Push any new pages onto the LRU now */
return 0;
}
if (shmem_mapping(file->f_mapping)) {
shmem_swapin_range(vma, start, end, file->f_mapping);
lru_add_drain(); /* Push any new pages onto the LRU now */
return 0;
}
#else
if (!file)
return -EBADF;
#endif
if (IS_DAX(file_inode(file))) {
/* no bad return value, but ignore advice */
return 0;
}
/*
* Filesystem's fadvise may need to take various locks. We need to
* explicitly grab a reference because the vma (and hence the
* vma's reference to the file) can go away as soon as we drop
* mmap_lock.
*/
*prev = NULL; /* tell sys_madvise we drop mmap_lock */
get_file(file);
offset = (loff_t)(start - vma->vm_start)
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
mmap_read_unlock(mm);
vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
fput(file);
mmap_read_lock(mm);
return 0;
}
static inline bool can_do_file_pageout(struct vm_area_struct *vma)
{
if (!vma->vm_file)
return false;
/*
* paging out pagecache only for non-anonymous mappings that correspond
* to the files the calling process could (if tried) open for writing;
* otherwise we'd be including shared non-exclusive mappings, which
* opens a side channel.
*/
return inode_owner_or_capable(&nop_mnt_idmap,
file_inode(vma->vm_file)) ||
file_permission(vma->vm_file, MAY_WRITE) == 0;
}
static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end,
struct folio *folio, pte_t *ptep,
pte_t pte, bool *any_young,
bool *any_dirty)
{
const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
int max_nr = (end - addr) / PAGE_SIZE;
return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
any_young, any_dirty);
}
static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct madvise_walk_private *private = walk->private;
struct mmu_gather *tlb = private->tlb;
bool pageout = private->pageout;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
pte_t *start_pte, *pte, ptent;
spinlock_t *ptl;
struct folio *folio = NULL;
LIST_HEAD(folio_list);
bool pageout_anon_only_filter;
unsigned int batch_count = 0;
int nr;
if (fatal_signal_pending(current))
return -EINTR;
pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) &&
!can_do_file_pageout(vma);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (pmd_trans_huge(*pmd)) {
pmd_t orig_pmd;
unsigned long next = pmd_addr_end(addr, end);
tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = pmd_trans_huge_lock(pmd, vma);
if (!ptl)
return 0;
orig_pmd = *pmd;
if (is_huge_zero_pmd(orig_pmd))
goto huge_unlock;
if (unlikely(!pmd_present(orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(orig_pmd));
goto huge_unlock;
}
folio = pmd_folio(orig_pmd);
/* Do not interfere with other mappings of this folio */
if (folio_maybe_mapped_shared(folio))
goto huge_unlock;
if (pageout_anon_only_filter && !folio_test_anon(folio))
goto huge_unlock;
if (next - addr != HPAGE_PMD_SIZE) {
int err;
folio_get(folio);
spin_unlock(ptl);
folio_lock(folio);
err = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
if (!err)
goto regular_folio;
return 0;
}
if (!pageout && pmd_young(orig_pmd)) {
pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
set_pmd_at(mm, addr, pmd, orig_pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
}
folio_clear_referenced(folio);
folio_test_clear_young(folio);
if (folio_test_active(folio))
folio_set_workingset(folio);
if (pageout) {
if (folio_isolate_lru(folio)) {
if (folio_test_unevictable(folio))
folio_putback_lru(folio);
else
list_add(&folio->lru, &folio_list);
}
} else
folio_deactivate(folio);
huge_unlock:
spin_unlock(ptl);
if (pageout)
reclaim_pages(&folio_list);
return 0;
}
regular_folio:
#endif
tlb_change_page_size(tlb, PAGE_SIZE);
restart:
start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (!start_pte)
return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) {
nr = 1;
ptent = ptep_get(pte);
if (++batch_count == SWAP_CLUSTER_MAX) {
batch_count = 0;
if (need_resched()) {
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
cond_resched();
goto restart;
}
}
if (pte_none(ptent))
continue;
if (!pte_present(ptent))
continue;
folio = vm_normal_folio(vma, addr, ptent);
if (!folio || folio_is_zone_device(folio))
continue;
/*
* If we encounter a large folio, only split it if it is not
* fully mapped within the range we are operating on. Otherwise
* leave it as is so that it can be swapped out whole. If we
* fail to split a folio, leave it in place and advance to the
* next pte in the range.
*/
if (folio_test_large(folio)) {
bool any_young;
nr = madvise_folio_pte_batch(addr, end, folio, pte,
ptent, &any_young, NULL);
if (any_young)
ptent = pte_mkyoung(ptent);
if (nr < folio_nr_pages(folio)) {
int err;
if (folio_maybe_mapped_shared(folio))
continue;
if (pageout_anon_only_filter && !folio_test_anon(folio))
continue;
if (!folio_trylock(folio))
continue;
folio_get(folio);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
start_pte = NULL;
err = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
start_pte = pte =
pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!start_pte)
break;
arch_enter_lazy_mmu_mode();
if (!err)
nr = 0;
continue;
}
}
/*
* Do not interfere with other mappings of this folio and
* non-LRU folio. If we have a large folio at this point, we
* know it is fully mapped so if its mapcount is the same as its
* number of pages, it must be exclusive.
*/
if (!folio_test_lru(folio) ||
folio_mapcount(folio) != folio_nr_pages(folio))
continue;
if (pageout_anon_only_filter && !folio_test_anon(folio))
continue;
if (!pageout && pte_young(ptent)) {
clear_young_dirty_ptes(vma, addr, pte, nr,
CYDP_CLEAR_YOUNG);
tlb_remove_tlb_entries(tlb, pte, nr, addr);
}
/*
* We are deactivating a folio for accelerating reclaiming.
* VM couldn't reclaim the folio unless we clear PG_young.
* As a side effect, it makes confuse idle-page tracking
* because they will miss recent referenced history.
*/
folio_clear_referenced(folio);
folio_test_clear_young(folio);
if (folio_test_active(folio))
folio_set_workingset(folio);
if (pageout) {
if (folio_isolate_lru(folio)) {
if (folio_test_unevictable(folio))
folio_putback_lru(folio);
else
list_add(&folio->lru, &folio_list);
}
} else
folio_deactivate(folio);
}
if (start_pte) {
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
}
if (pageout)
reclaim_pages(&folio_list);
cond_resched();
return 0;
}
static const struct mm_walk_ops cold_walk_ops = {
.pmd_entry = madvise_cold_or_pageout_pte_range,
.walk_lock = PGWALK_RDLOCK,
};
static void madvise_cold_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
struct madvise_walk_private walk_private = {
.pageout = false,
.tlb = tlb,
};
tlb_start_vma(tlb, vma);
walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
tlb_end_vma(tlb, vma);
}
static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
{
return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB));
}
static long madvise_cold(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start_addr, unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
*prev = vma;
if (!can_madv_lru_vma(vma))
return -EINVAL;
lru_add_drain();
tlb_gather_mmu(&tlb, mm);
madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
tlb_finish_mmu(&tlb);
return 0;
}
static void madvise_pageout_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
struct madvise_walk_private walk_private = {
.pageout = true,
.tlb = tlb,
};
tlb_start_vma(tlb, vma);
walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
tlb_end_vma(tlb, vma);
}
static long madvise_pageout(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start_addr, unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
*prev = vma;
if (!can_madv_lru_vma(vma))
return -EINVAL;
/*
* If the VMA belongs to a private file mapping, there can be private
* dirty pages which can be paged out if even this process is neither
* owner nor write capable of the file. We allow private file mappings
* further to pageout dirty anon pages.
*/
if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) &&
(vma->vm_flags & VM_MAYSHARE)))
return 0;
lru_add_drain();
tlb_gather_mmu(&tlb, mm);
madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
tlb_finish_mmu(&tlb);
return 0;
}
static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY;
struct mmu_gather *tlb = walk->private;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
pte_t *start_pte, *pte, ptent;
struct folio *folio;
int nr_swap = 0;
unsigned long next;
int nr, max_nr;
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd))
if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
return 0;
tlb_change_page_size(tlb, PAGE_SIZE);
start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!start_pte)
return 0;
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) {
nr = 1;
ptent = ptep_get(pte);
if (pte_none(ptent))
continue;
/*
* If the pte has swp_entry, just clear page table to
* prevent swap-in which is more expensive rather than
* (page allocation + zeroing).
*/
if (!pte_present(ptent)) {
swp_entry_t entry;
entry = pte_to_swp_entry(ptent);
if (!non_swap_entry(entry)) {
max_nr = (end - addr) / PAGE_SIZE;
nr = swap_pte_batch(pte, max_nr, ptent);
nr_swap -= nr;
free_swap_and_cache_nr(entry, nr);
clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
} else if (is_hwpoison_entry(entry) ||
is_poisoned_swp_entry(entry)) {
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
}
continue;
}
folio = vm_normal_folio(vma, addr, ptent);
if (!folio || folio_is_zone_device(folio))
continue;
/*
* If we encounter a large folio, only split it if it is not
* fully mapped within the range we are operating on. Otherwise
* leave it as is so that it can be marked as lazyfree. If we
* fail to split a folio, leave it in place and advance to the
* next pte in the range.
*/
if (folio_test_large(folio)) {
bool any_young, any_dirty;
nr = madvise_folio_pte_batch(addr, end, folio, pte,
ptent, &any_young, &any_dirty);
if (nr < folio_nr_pages(folio)) {
int err;
if (folio_maybe_mapped_shared(folio))
continue;
if (!folio_trylock(folio))
continue;
folio_get(folio);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
start_pte = NULL;
err = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
start_pte = pte;
if (!start_pte)
break;
arch_enter_lazy_mmu_mode();
if (!err)
nr = 0;
continue;
}
if (any_young)
ptent = pte_mkyoung(ptent);
if (any_dirty)
ptent = pte_mkdirty(ptent);
}
if (folio_test_swapcache(folio) || folio_test_dirty(folio)) {
if (!folio_trylock(folio))
continue;
/*
* If we have a large folio at this point, we know it is
* fully mapped so if its mapcount is the same as its
* number of pages, it must be exclusive.
*/
if (folio_mapcount(folio) != folio_nr_pages(folio)) {
folio_unlock(folio);
continue;
}
if (folio_test_swapcache(folio) &&
!folio_free_swap(folio)) {
folio_unlock(folio);
continue;
}
folio_clear_dirty(folio);
folio_unlock(folio);
}
if (pte_young(ptent) || pte_dirty(ptent)) {
clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags);
tlb_remove_tlb_entries(tlb, pte, nr, addr);
}
folio_mark_lazyfree(folio);
}
if (nr_swap)
add_mm_counter(mm, MM_SWAPENTS, nr_swap);
if (start_pte) {
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
}
cond_resched();
return 0;
}
static const struct mm_walk_ops madvise_free_walk_ops = {
.pmd_entry = madvise_free_pte_range,
.walk_lock = PGWALK_RDLOCK,
};
static int madvise_free_single_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
struct mmu_gather tlb;
/* MADV_FREE works for only anon vma at the moment */
if (!vma_is_anonymous(vma))
return -EINVAL;
range.start = max(vma->vm_start, start_addr);
if (range.start >= vma->vm_end)
return -EINVAL;
range.end = min(vma->vm_end, end_addr);
if (range.end <= vma->vm_start)
return -EINVAL;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
range.start, range.end);
lru_add_drain();
tlb_gather_mmu(&tlb, mm);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(&range);
tlb_start_vma(&tlb, vma);
walk_page_range(vma->vm_mm, range.start, range.end,
&madvise_free_walk_ops, &tlb);
tlb_end_vma(&tlb, vma);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
return 0;
}
/*
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
* data it wants to keep. Be sure to free swap resources too. The
* zap_page_range_single call sets things up for shrink_active_list to actually
* free these pages later if no one else has touched them in the meantime,
* although we could add these pages to a global reuse list for
* shrink_active_list to pick up before reclaiming other pages.
*
* NB: This interface discards data rather than pushes it out to swap,
* as some implementations do. This has performance implications for
* applications like large transactional databases which want to discard
* pages in anonymous maps after committing to backing store the data
* that was kept in them. There is no reason to write this data out to
* the swap area if the application is discarding it.
*
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync(MS_INVALIDATE).
*/
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct zap_details details = {
.reclaim_pt = true,
.even_cows = true,
};
zap_page_range_single(vma, start, end - start, &details);
return 0;
}
static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
unsigned long start,
unsigned long *end,
int behavior)
{
if (!is_vm_hugetlb_page(vma)) {
unsigned int forbidden = VM_PFNMAP;
if (behavior != MADV_DONTNEED_LOCKED)
forbidden |= VM_LOCKED;
return !(vma->vm_flags & forbidden);
}
if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED)
return false;
if (start & ~huge_page_mask(hstate_vma(vma)))
return false;
/*
* Madvise callers expect the length to be rounded up to PAGE_SIZE
* boundaries, and may be unaware that this VMA uses huge pages.
* Avoid unexpected data loss by rounding down the number of
* huge pages freed.
*/
*end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma)));
return true;
}
static long madvise_dontneed_free(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
int behavior)
{
struct mm_struct *mm = vma->vm_mm;
*prev = vma;
if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior))
return -EINVAL;
if (start == end)
return 0;
if (!userfaultfd_remove(vma, start, end)) {
*prev = NULL; /* mmap_lock has been dropped, prev is stale */
mmap_read_lock(mm);
vma = vma_lookup(mm, start);
if (!vma)
return -ENOMEM;
/*
* Potential end adjustment for hugetlb vma is OK as
* the check below keeps end within vma.
*/
if (!madvise_dontneed_free_valid_vma(vma, start, &end,
behavior))
return -EINVAL;
if (end > vma->vm_end) {
/*
* Don't fail if end > vma->vm_end. If the old
* vma was split while the mmap_lock was
* released the effect of the concurrent
* operation may not cause madvise() to
* have an undefined result. There may be an
* adjacent next vma that we'll walk
* next. userfaultfd_remove() will generate an
* UFFD_EVENT_REMOVE repetition on the
* end-vma->vm_end range, but the manager can
* handle a repetition fine.
*/
end = vma->vm_end;
}
/*
* If the memory region between start and end was
* originally backed by 4kB pages and then remapped to
* be backed by hugepages while mmap_lock was dropped,
* the adjustment for hugetlb vma above may have rounded
* end down to the start address.
*/
if (start == end)
return 0;
VM_WARN_ON(start > end);
}
if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED)
return madvise_dontneed_single_vma(vma, start, end);
else if (behavior == MADV_FREE)
return madvise_free_single_vma(vma, start, end);
else
return -EINVAL;
}
static long madvise_populate(struct mm_struct *mm, unsigned long start,
unsigned long end, int behavior)
{
const bool write = behavior == MADV_POPULATE_WRITE;
int locked = 1;
long pages;
while (start < end) {
/* Populate (prefault) page tables readable/writable. */
pages = faultin_page_range(mm, start, end, write, &locked);
if (!locked) {
mmap_read_lock(mm);
locked = 1;
}
if (pages < 0) {
switch (pages) {
case -EINTR:
return -EINTR;
case -EINVAL: /* Incompatible mappings / permissions. */
return -EINVAL;
case -EHWPOISON:
return -EHWPOISON;
case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */
return -EFAULT;
default:
pr_warn_once("%s: unhandled return value: %ld\n",
__func__, pages);
fallthrough;
case -ENOMEM: /* No VMA or out of memory. */
return -ENOMEM;
}
}
start += pages * PAGE_SIZE;
}
return 0;
}
/*
* Application wants to free up the pages and associated backing store.
* This is effectively punching a hole into the middle of a file.
*/
static long madvise_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
loff_t offset;
int error;
struct file *f;
struct mm_struct *mm = vma->vm_mm;
*prev = NULL; /* tell sys_madvise we drop mmap_lock */
if (vma->vm_flags & VM_LOCKED)
return -EINVAL;
f = vma->vm_file;
if (!f || !f->f_mapping || !f->f_mapping->host) {
return -EINVAL;
}
if (!vma_is_shared_maywrite(vma))
return -EACCES;
offset = (loff_t)(start - vma->vm_start)
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
/*
* Filesystem's fallocate may need to take i_rwsem. We need to
* explicitly grab a reference because the vma (and hence the
* vma's reference to the file) can go away as soon as we drop
* mmap_lock.
*/
get_file(f);
if (userfaultfd_remove(vma, start, end)) {
/* mmap_lock was not released by userfaultfd_remove() */
mmap_read_unlock(mm);
}
error = vfs_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);
fput(f);
mmap_read_lock(mm);
return error;
}
static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked)
{
vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB;
/*
* A user could lock after setting a guard range but that's fine, as
* they'd not be able to fault in. The issue arises when we try to zap
* existing locked VMAs. We don't want to do that.
*/
if (!allow_locked)
disallowed |= VM_LOCKED;
return !(vma->vm_flags & disallowed);
}
static bool is_guard_pte_marker(pte_t ptent)
{
return is_pte_marker(ptent) &&
is_guard_swp_entry(pte_to_swp_entry(ptent));
}
static int guard_install_pud_entry(pud_t *pud, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pud_t pudval = pudp_get(pud);
/* If huge return >0 so we abort the operation + zap. */
return pud_trans_huge(pudval) || pud_devmap(pudval);
}
static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pmd_t pmdval = pmdp_get(pmd);
/* If huge return >0 so we abort the operation + zap. */
return pmd_trans_huge(pmdval) || pmd_devmap(pmdval);
}
static int guard_install_pte_entry(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pte_t pteval = ptep_get(pte);
unsigned long *nr_pages = (unsigned long *)walk->private;
/* If there is already a guard page marker, we have nothing to do. */
if (is_guard_pte_marker(pteval)) {
(*nr_pages)++;
return 0;
}
/* If populated return >0 so we abort the operation + zap. */
return 1;
}
static int guard_install_set_pte(unsigned long addr, unsigned long next,
pte_t *ptep, struct mm_walk *walk)
{
unsigned long *nr_pages = (unsigned long *)walk->private;
/* Simply install a PTE marker, this causes segfault on access. */
*ptep = make_pte_marker(PTE_MARKER_GUARD);
(*nr_pages)++;
return 0;
}
static const struct mm_walk_ops guard_install_walk_ops = {
.pud_entry = guard_install_pud_entry,
.pmd_entry = guard_install_pmd_entry,
.pte_entry = guard_install_pte_entry,
.install_pte = guard_install_set_pte,
.walk_lock = PGWALK_RDLOCK,
};
static long madvise_guard_install(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
long err;
int i;
*prev = vma;
if (!is_valid_guard_vma(vma, /* allow_locked = */false))
return -EINVAL;
/*
* If we install guard markers, then the range is no longer
* empty from a page table perspective and therefore it's
* appropriate to have an anon_vma.
*
* This ensures that on fork, we copy page tables correctly.
*/
err = anon_vma_prepare(vma);
if (err)
return err;
/*
* Optimistically try to install the guard marker pages first. If any
* non-guard pages are encountered, give up and zap the range before
* trying again.
*
* We try a few times before giving up and releasing back to userland to
* loop around, releasing locks in the process to avoid contention. This
* would only happen if there was a great many racing page faults.
*
* In most cases we should simply install the guard markers immediately
* with no zap or looping.
*/
for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) {
unsigned long nr_pages = 0;
/* Returns < 0 on error, == 0 if success, > 0 if zap needed. */
err = walk_page_range_mm(vma->vm_mm, start, end,
&guard_install_walk_ops, &nr_pages);
if (err < 0)
return err;
if (err == 0) {
unsigned long nr_expected_pages = PHYS_PFN(end - start);
VM_WARN_ON(nr_pages != nr_expected_pages);
return 0;
}
/*
* OK some of the range have non-guard pages mapped, zap
* them. This leaves existing guard pages in place.
*/
zap_page_range_single(vma, start, end - start, NULL);
}
/*
* We were unable to install the guard pages due to being raced by page
* faults. This should not happen ordinarily. We return to userspace and
* immediately retry, relieving lock contention.
*/
return restart_syscall();
}
static int guard_remove_pud_entry(pud_t *pud, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pud_t pudval = pudp_get(pud);
/* If huge, cannot have guard pages present, so no-op - skip. */
if (pud_trans_huge(pudval) || pud_devmap(pudval))
walk->action = ACTION_CONTINUE;
return 0;
}
static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pmd_t pmdval = pmdp_get(pmd);
/* If huge, cannot have guard pages present, so no-op - skip. */
if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval))
walk->action = ACTION_CONTINUE;
return 0;
}
static int guard_remove_pte_entry(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
pte_t ptent = ptep_get(pte);
if (is_guard_pte_marker(ptent)) {
/* Simply clear the PTE marker. */
pte_clear_not_present_full(walk->mm, addr, pte, false);
update_mmu_cache(walk->vma, addr, pte);
}
return 0;
}
static const struct mm_walk_ops guard_remove_walk_ops = {
.pud_entry = guard_remove_pud_entry,
.pmd_entry = guard_remove_pmd_entry,
.pte_entry = guard_remove_pte_entry,
.walk_lock = PGWALK_RDLOCK,
};
static long madvise_guard_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
*prev = vma;
/*
* We're ok with removing guards in mlock()'d ranges, as this is a
* non-destructive action.
*/
if (!is_valid_guard_vma(vma, /* allow_locked = */true))
return -EINVAL;
return walk_page_range(vma->vm_mm, start, end,
&guard_remove_walk_ops, NULL);
}
/*
* Apply an madvise behavior to a region of a vma. madvise_update_vma
* will handle splitting a vm area into separate areas, each area with its own
* behavior.
*/
static int madvise_vma_behavior(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
unsigned long behavior)
{
int error;
struct anon_vma_name *anon_name;
unsigned long new_flags = vma->vm_flags;
if (unlikely(!can_modify_vma_madv(vma, behavior)))
return -EPERM;
switch (behavior) {
case MADV_REMOVE:
return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
case MADV_COLD:
return madvise_cold(vma, prev, start, end);
case MADV_PAGEOUT:
return madvise_pageout(vma, prev, start, end);
case MADV_FREE:
case MADV_DONTNEED:
case MADV_DONTNEED_LOCKED:
return madvise_dontneed_free(vma, prev, start, end, behavior);
case MADV_NORMAL:
new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
break;
case MADV_SEQUENTIAL:
new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
break;
case MADV_RANDOM:
new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
break;
case MADV_DONTFORK:
new_flags |= VM_DONTCOPY;
break;
case MADV_DOFORK:
if (vma->vm_flags & VM_IO)
return -EINVAL;
new_flags &= ~VM_DONTCOPY;
break;
case MADV_WIPEONFORK:
/* MADV_WIPEONFORK is only supported on anonymous memory. */
if (vma->vm_file || vma->vm_flags & VM_SHARED)
return -EINVAL;
new_flags |= VM_WIPEONFORK;
break;
case MADV_KEEPONFORK:
if (vma->vm_flags & VM_DROPPABLE)
return -EINVAL;
new_flags &= ~VM_WIPEONFORK;
break;
case MADV_DONTDUMP:
new_flags |= VM_DONTDUMP;
break;
case MADV_DODUMP:
if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) ||
(vma->vm_flags & VM_DROPPABLE))
return -EINVAL;
new_flags &= ~VM_DONTDUMP;
break;
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
error = ksm_madvise(vma, start, end, behavior, &new_flags);
if (error)
goto out;
break;
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
error = hugepage_madvise(vma, &new_flags, behavior);
if (error)
goto out;
break;
case MADV_COLLAPSE:
return madvise_collapse(vma, prev, start, end);
case MADV_GUARD_INSTALL:
return madvise_guard_install(vma, prev, start, end);
case MADV_GUARD_REMOVE:
return madvise_guard_remove(vma, prev, start, end);
}
anon_name = anon_vma_name(vma);
anon_vma_name_get(anon_name);
error = madvise_update_vma(vma, prev, start, end, new_flags,
anon_name);
anon_vma_name_put(anon_name);
out:
/*
* madvise() returns EAGAIN if kernel resources, such as
* slab, are temporarily unavailable.
*/
if (error == -ENOMEM)
error = -EAGAIN;
return error;
}
#ifdef CONFIG_MEMORY_FAILURE
/*
* Error injection support for memory error handling.
*/
static int madvise_inject_error(int behavior,
unsigned long start, unsigned long end)
{
unsigned long size;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
for (; start < end; start += size) {
unsigned long pfn;
struct page *page;
int ret;
ret = get_user_pages_fast(start, 1, 0, &page);
if (ret != 1)
return ret;
pfn = page_to_pfn(page);
/*
* When soft offlining hugepages, after migrating the page
* we dissolve it, therefore in the second loop "page" will
* no longer be a compound page.
*/
size = page_size(compound_head(page));
if (behavior == MADV_SOFT_OFFLINE) {
pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
pfn, start);
ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
} else {
pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
pfn, start);
ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED);
if (ret == -EOPNOTSUPP)
ret = 0;
}
if (ret)
return ret;
}
return 0;
}
static bool is_memory_failure(int behavior)
{
switch (behavior) {
case MADV_HWPOISON:
case MADV_SOFT_OFFLINE:
return true;
default:
return false;
}
}
#else
static int madvise_inject_error(int behavior,
unsigned long start, unsigned long end)
{
return 0;
}
static bool is_memory_failure(int behavior)
{
return false;
}
#endif /* CONFIG_MEMORY_FAILURE */
static bool
madvise_behavior_valid(int behavior)
{
switch (behavior) {
case MADV_DOFORK:
case MADV_DONTFORK:
case MADV_NORMAL:
case MADV_SEQUENTIAL:
case MADV_RANDOM:
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
case MADV_DONTNEED_LOCKED:
case MADV_FREE:
case MADV_COLD:
case MADV_PAGEOUT:
case MADV_POPULATE_READ:
case MADV_POPULATE_WRITE:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
case MADV_COLLAPSE:
#endif
case MADV_DONTDUMP:
case MADV_DODUMP:
case MADV_WIPEONFORK:
case MADV_KEEPONFORK:
case MADV_GUARD_INSTALL:
case MADV_GUARD_REMOVE:
#ifdef CONFIG_MEMORY_FAILURE
case MADV_SOFT_OFFLINE:
case MADV_HWPOISON:
#endif
return true;
default:
return false;
}
}
/* Can we invoke process_madvise() on a remote mm for the specified behavior? */
static bool process_madvise_remote_valid(int behavior)
{
switch (behavior) {
case MADV_COLD:
case MADV_PAGEOUT:
case MADV_WILLNEED:
case MADV_COLLAPSE:
return true;
default:
return false;
}
}
/*
* Walk the vmas in range [start,end), and call the visit function on each one.
* The visit function will get start and end parameters that cover the overlap
* between the current vma and the original range. Any unmapped regions in the
* original range will result in this function returning -ENOMEM while still
* calling the visit function on all of the existing vmas in the range.
* Must be called with the mmap_lock held for reading or writing.
*/
static
int madvise_walk_vmas(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long arg,
int (*visit)(struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
unsigned long end, unsigned long arg))
{
struct vm_area_struct *vma;
struct vm_area_struct *prev;
unsigned long tmp;
int unmapped_error = 0;
/*
* If the interval [start,end) covers some unmapped address
* ranges, just ignore them, but return -ENOMEM at the end.
* - different from the way of handling in mlock etc.
*/
vma = find_vma_prev(mm, start, &prev);
if (vma && start > vma->vm_start)
prev = vma;
for (;;) {
int error;
/* Still start < end. */
if (!vma)
return -ENOMEM;
/* Here start < (end|vma->vm_end). */
if (start < vma->vm_start) {
unmapped_error = -ENOMEM;
start = vma->vm_start;
if (start >= end)
break;
}
/* Here vma->vm_start <= start < (end|vma->vm_end) */
tmp = vma->vm_end;
if (end < tmp)
tmp = end;
/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
error = visit(vma, &prev, start, tmp, arg);
if (error)
return error;
start = tmp;
if (prev && start < prev->vm_end)
start = prev->vm_end;
if (start >= end)
break;
if (prev)
vma = find_vma(mm, prev->vm_end);
else /* madvise_remove dropped mmap_lock */
vma = find_vma(mm, start);
}
return unmapped_error;
}
#ifdef CONFIG_ANON_VMA_NAME
static int madvise_vma_anon_name(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
unsigned long anon_name)
{
int error;
/* Only anonymous mappings can be named */
if (vma->vm_file && !vma_is_anon_shmem(vma))
return -EBADF;
error = madvise_update_vma(vma, prev, start, end, vma->vm_flags,
(struct anon_vma_name *)anon_name);
/*
* madvise() returns EAGAIN if kernel resources, such as
* slab, are temporarily unavailable.
*/
if (error == -ENOMEM)
error = -EAGAIN;
return error;
}
int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
unsigned long len_in, struct anon_vma_name *anon_name)
{
unsigned long end;
unsigned long len;
if (start & ~PAGE_MASK)
return -EINVAL;
len = (len_in + ~PAGE_MASK) & PAGE_MASK;
/* Check to see whether len was rounded up from small -ve to zero */
if (len_in && !len)
return -EINVAL;
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name,
madvise_vma_anon_name);
}
#endif /* CONFIG_ANON_VMA_NAME */
static int madvise_lock(struct mm_struct *mm, int behavior)
{
if (is_memory_failure(behavior))
return 0;
if (madvise_need_mmap_write(behavior)) {
if (mmap_write_lock_killable(mm))
return -EINTR;
} else {
mmap_read_lock(mm);
}
return 0;
}
static void madvise_unlock(struct mm_struct *mm, int behavior)
{
if (is_memory_failure(behavior))
return;
if (madvise_need_mmap_write(behavior))
mmap_write_unlock(mm);
else
mmap_read_unlock(mm);
}
static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior)
{
size_t len;
if (!madvise_behavior_valid(behavior))
return false;
if (!PAGE_ALIGNED(start))
return false;
len = PAGE_ALIGN(len_in);
/* Check to see whether len was rounded up from small -ve to zero */
if (len_in && !len)
return false;
if (start + len < start)
return false;
return true;
}
/*
* madvise_should_skip() - Return if the request is invalid or nothing.
* @start: Start address of madvise-requested address range.
* @len_in: Length of madvise-requested address range.
* @behavior: Requested madvise behavor.
* @err: Pointer to store an error code from the check.
*
* If the specified behaviour is invalid or nothing would occur, we skip the
* operation. This function returns true in the cases, otherwise false. In
* the former case we store an error on @err.
*/
static bool madvise_should_skip(unsigned long start, size_t len_in,
int behavior, int *err)
{
if (!is_valid_madvise(start, len_in, behavior)) {
*err = -EINVAL;
return true;
}
if (start + PAGE_ALIGN(len_in) == start) {
*err = 0;
return true;
}
return false;
}
static bool is_madvise_populate(int behavior)
{
switch (behavior) {
case MADV_POPULATE_READ:
case MADV_POPULATE_WRITE:
return true;
default:
return false;
}
}
static int madvise_do_behavior(struct mm_struct *mm,
unsigned long start, size_t len_in, int behavior)
{
struct blk_plug plug;
unsigned long end;
int error;
if (is_memory_failure(behavior))
return madvise_inject_error(behavior, start, start + len_in);
start = untagged_addr_remote(mm, start);
end = start + PAGE_ALIGN(len_in);
blk_start_plug(&plug);
if (is_madvise_populate(behavior))
error = madvise_populate(mm, start, end, behavior);
else
error = madvise_walk_vmas(mm, start, end, behavior,
madvise_vma_behavior);
blk_finish_plug(&plug);
return error;
}
/*
* The madvise(2) system call.
*
* Applications can use madvise() to advise the kernel how it should
* handle paging I/O in this VM area. The idea is to help the kernel
* use appropriate read-ahead and caching techniques. The information
* provided is advisory only, and can be safely disregarded by the
* kernel without affecting the correct operation of the application.
*
* behavior values:
* MADV_NORMAL - the default behavior is to read clusters. This
* results in some read-ahead and read-behind.
* MADV_RANDOM - the system should read the minimum amount of data
* on any access, since it is unlikely that the appli-
* cation will need more than what it asks for.
* MADV_SEQUENTIAL - pages in the given range will probably be accessed
* once, so they can be aggressively read ahead, and
* can be freed soon after they are accessed.
* MADV_WILLNEED - the application is notifying the system to read
* some pages ahead.
* MADV_DONTNEED - the application is finished with the given range,
* so the kernel can free resources associated with it.
* MADV_FREE - the application marks pages in the given range as lazy free,
* where actual purges are postponed until memory pressure happens.
* MADV_REMOVE - the application wants to free up the given range of
* pages and associated backing store.
* MADV_DONTFORK - omit this area from child's address space when forking:
* typically, to avoid COWing pages pinned by get_user_pages().
* MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
* MADV_WIPEONFORK - present the child process with zero-filled memory in this
* range after a fork.
* MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
* MADV_HWPOISON - trigger memory error handler as if the given memory range
* were corrupted by unrecoverable hardware memory failure.
* MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
* MADV_MERGEABLE - the application recommends that KSM try to merge pages in
* this area with pages of identical content from other such areas.
* MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
* MADV_HUGEPAGE - the application wants to back the given range by transparent
* huge pages in the future. Existing pages might be coalesced and
* new pages might be allocated as THP.
* MADV_NOHUGEPAGE - mark the given range as not worth being backed by
* transparent huge pages so the existing pages will not be
* coalesced into THP and new pages will not be allocated as THP.
* MADV_COLLAPSE - synchronously coalesce pages into new THP.
* MADV_DONTDUMP - the application wants to prevent pages in the given range
* from being included in its core dump.
* MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
* MADV_COLD - the application is not expected to use this memory soon,
* deactivate pages in this range so that they can be reclaimed
* easily if memory pressure happens.
* MADV_PAGEOUT - the application is not expected to use this memory soon,
* page out the pages in this range immediately.
* MADV_POPULATE_READ - populate (prefault) page tables readable by
* triggering read faults if required
* MADV_POPULATE_WRITE - populate (prefault) page tables writable by
* triggering write faults if required
*
* return values:
* zero - success
* -EINVAL - start + len < 0, start is not page-aligned,
* "behavior" is not a valid value, or application
* is attempting to release locked or shared pages,
* or the specified address range includes file, Huge TLB,
* MAP_SHARED or VMPFNMAP range.
* -ENOMEM - addresses in the specified range are not currently
* mapped, or are outside the AS of the process.
* -EIO - an I/O error occurred while paging in data.
* -EBADF - map exists, but area maps something that isn't a file.
* -EAGAIN - a kernel resource was temporarily unavailable.
* -EPERM - memory is sealed.
*/
int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
{
int error;
if (madvise_should_skip(start, len_in, behavior, &error))
return error;
error = madvise_lock(mm, behavior);
if (error)
return error;
error = madvise_do_behavior(mm, start, len_in, behavior);
madvise_unlock(mm, behavior);
return error;
}
SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
{
return do_madvise(current->mm, start, len_in, behavior);
}
/* Perform an madvise operation over a vector of addresses and lengths. */
static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter,
int behavior)
{
ssize_t ret = 0;
size_t total_len;
total_len = iov_iter_count(iter);
ret = madvise_lock(mm, behavior);
if (ret)
return ret;
while (iov_iter_count(iter)) {
unsigned long start = (unsigned long)iter_iov_addr(iter);
size_t len_in = iter_iov_len(iter);
int error;
if (madvise_should_skip(start, len_in, behavior, &error))
ret = error;
else
ret = madvise_do_behavior(mm, start, len_in, behavior);
/*
* An madvise operation is attempting to restart the syscall,
* but we cannot proceed as it would not be correct to repeat
* the operation in aggregate, and would be surprising to the
* user.
*
* We drop and reacquire locks so it is safe to just loop and
* try again. We check for fatal signals in case we need exit
* early anyway.
*/
if (ret == -ERESTARTNOINTR) {
if (fatal_signal_pending(current)) {
ret = -EINTR;
break;
}
/* Drop and reacquire lock to unwind race. */
madvise_unlock(mm, behavior);
madvise_lock(mm, behavior);
continue;
}
if (ret < 0)
break;
iov_iter_advance(iter, iter_iov_len(iter));
}
madvise_unlock(mm, behavior);
ret = (total_len - iov_iter_count(iter)) ? : ret;
return ret;
}
SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
size_t, vlen, int, behavior, unsigned int, flags)
{
ssize_t ret;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
struct task_struct *task;
struct mm_struct *mm;
unsigned int f_flags;
if (flags != 0) {
ret = -EINVAL;
goto out;
}
ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret < 0)
goto out;
task = pidfd_get_task(pidfd, &f_flags);
if (IS_ERR(task)) {
ret = PTR_ERR(task);
goto free_iov;
}
/* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR(mm)) {
ret = PTR_ERR(mm);
goto release_task;
}
/*
* We need only perform this check if we are attempting to manipulate a
* remote process's address space.
*/
if (mm != current->mm && !process_madvise_remote_valid(behavior)) {
ret = -EINVAL;
goto release_mm;
}
/*
* Require CAP_SYS_NICE for influencing process performance. Note that
* only non-destructive hints are currently supported for remote
* processes.
*/
if (mm != current->mm && !capable(CAP_SYS_NICE)) {
ret = -EPERM;
goto release_mm;
}
ret = vector_madvise(mm, &iter, behavior);
release_mm:
mmput(mm);
release_task:
put_task_struct(task);
free_iov:
kfree(iov);
out:
return ret;
}
/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <net/net_namespace.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/hashtable.h>
#include <rdma/rdma_netlink.h>
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
#include <rdma/rdma_counter.h>
#include "core_priv.h"
#include "restrack.h"
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("core kernel InfiniBand API");
MODULE_LICENSE("Dual BSD/GPL");
struct workqueue_struct *ib_comp_wq;
struct workqueue_struct *ib_comp_unbound_wq;
struct workqueue_struct *ib_wq;
EXPORT_SYMBOL_GPL(ib_wq);
static struct workqueue_struct *ib_unreg_wq;
/*
* Each of the three rwsem locks (devices, clients, client_data) protects the
* xarray of the same name. Specifically it allows the caller to assert that
* the MARK will/will not be changing under the lock, and for devices and
* clients, that the value in the xarray is still a valid pointer. Change of
* the MARK is linked to the object state, so holding the lock and testing the
* MARK also asserts that the contained object is in a certain state.
*
* This is used to build a two stage register/unregister flow where objects
* can continue to be in the xarray even though they are still in progress to
* register/unregister.
*
* The xarray itself provides additional locking, and restartable iteration,
* which is also relied on.
*
* Locks should not be nested, with the exception of client_data, which is
* allowed to nest under the read side of the other two locks.
*
* The devices_rwsem also protects the device name list, any change or
* assignment of device name must also hold the write side to guarantee unique
* names.
*/
/*
* devices contains devices that have had their names assigned. The
* devices may not be registered. Users that care about the registration
* status need to call ib_device_try_get() on the device to ensure it is
* registered, and keep it registered, for the required duration.
*
*/
static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC);
static DECLARE_RWSEM(devices_rwsem);
#define DEVICE_REGISTERED XA_MARK_1
static u32 highest_client_id;
#define CLIENT_REGISTERED XA_MARK_1
static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC);
static DECLARE_RWSEM(clients_rwsem);
static void ib_client_put(struct ib_client *client)
{
if (refcount_dec_and_test(&client->uses))
complete(&client->uses_zero);
}
/*
* If client_data is registered then the corresponding client must also still
* be registered.
*/
#define CLIENT_DATA_REGISTERED XA_MARK_1
unsigned int rdma_dev_net_id;
/*
* A list of net namespaces is maintained in an xarray. This is necessary
* because we can't get the locking right using the existing net ns list. We
* would require a init_net callback after the list is updated.
*/
static DEFINE_XARRAY_FLAGS(rdma_nets, XA_FLAGS_ALLOC);
/*
* rwsem to protect accessing the rdma_nets xarray entries.
*/
static DECLARE_RWSEM(rdma_nets_rwsem);
bool ib_devices_shared_netns = true;
module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444);
MODULE_PARM_DESC(netns_mode,
"Share device among net namespaces; default=1 (shared)");
/**
* rdma_dev_access_netns() - Return whether an rdma device can be accessed
* from a specified net namespace or not.
* @dev: Pointer to rdma device which needs to be checked
* @net: Pointer to net namesapce for which access to be checked
*
* When the rdma device is in shared mode, it ignores the net namespace.
* When the rdma device is exclusive to a net namespace, rdma device net
* namespace is checked against the specified one.
*/
bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net)
{
return (ib_devices_shared_netns ||
net_eq(read_pnet(&dev->coredev.rdma_net), net));
}
EXPORT_SYMBOL(rdma_dev_access_netns);
/*
* xarray has this behavior where it won't iterate over NULL values stored in
* allocated arrays. So we need our own iterator to see all values stored in
* the array. This does the same thing as xa_for_each except that it also
* returns NULL valued entries if the array is allocating. Simplified to only
* work on simple xarrays.
*/
static void *xan_find_marked(struct xarray *xa, unsigned long *indexp,
xa_mark_t filter)
{
XA_STATE(xas, xa, *indexp);
void *entry;
rcu_read_lock();
do {
entry = xas_find_marked(&xas, ULONG_MAX, filter);
if (xa_is_zero(entry))
break;
} while (xas_retry(&xas, entry));
rcu_read_unlock();
if (entry) {
*indexp = xas.xa_index;
if (xa_is_zero(entry))
return NULL;
return entry;
}
return XA_ERROR(-ENOENT);
}
#define xan_for_each_marked(xa, index, entry, filter) \
for (index = 0, entry = xan_find_marked(xa, &(index), filter); \
!xa_is_err(entry); \
(index)++, entry = xan_find_marked(xa, &(index), filter))
/* RCU hash table mapping netdevice pointers to struct ib_port_data */
static DEFINE_SPINLOCK(ndev_hash_lock);
static DECLARE_HASHTABLE(ndev_hash, 5);
static void free_netdevs(struct ib_device *ib_dev);
static void ib_unregister_work(struct work_struct *work);
static void __ib_unregister_device(struct ib_device *device);
static int ib_security_change(struct notifier_block *nb, unsigned long event,
void *lsm_data);
static void ib_policy_change_task(struct work_struct *work);
static DECLARE_WORK(ib_policy_change_work, ib_policy_change_task);
static void __ibdev_printk(const char *level, const struct ib_device *ibdev,
struct va_format *vaf)
{
if (ibdev && ibdev->dev.parent)
dev_printk_emit(level[1] - '0',
ibdev->dev.parent,
"%s %s %s: %pV",
dev_driver_string(ibdev->dev.parent),
dev_name(ibdev->dev.parent),
dev_name(&ibdev->dev),
vaf);
else if (ibdev)
printk("%s%s: %pV",
level, dev_name(&ibdev->dev), vaf);
else
printk("%s(NULL ib_device): %pV", level, vaf);
}
#define define_ibdev_printk_level(func, level) \
void func(const struct ib_device *ibdev, const char *fmt, ...) \
{ \
struct va_format vaf; \
va_list args; \
\
va_start(args, fmt); \
\
vaf.fmt = fmt; \
vaf.va = &args; \
\
__ibdev_printk(level, ibdev, &vaf); \
\
va_end(args); \
} \
EXPORT_SYMBOL(func);
define_ibdev_printk_level(ibdev_emerg, KERN_EMERG);
define_ibdev_printk_level(ibdev_alert, KERN_ALERT);
define_ibdev_printk_level(ibdev_crit, KERN_CRIT);
define_ibdev_printk_level(ibdev_err, KERN_ERR);
define_ibdev_printk_level(ibdev_warn, KERN_WARNING);
define_ibdev_printk_level(ibdev_notice, KERN_NOTICE);
define_ibdev_printk_level(ibdev_info, KERN_INFO);
static struct notifier_block ibdev_lsm_nb = {
.notifier_call = ib_security_change,
};
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
struct net *net);
/* Pointer to the RCU head at the start of the ib_port_data array */
struct ib_port_data_rcu {
struct rcu_head rcu_head;
struct ib_port_data pdata[];
};
static void ib_device_check_mandatory(struct ib_device *device)
{
#define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device_ops, x), #x }
static const struct {
size_t offset;
char *name;
} mandatory_table[] = {
IB_MANDATORY_FUNC(query_device),
IB_MANDATORY_FUNC(query_port),
IB_MANDATORY_FUNC(alloc_pd),
IB_MANDATORY_FUNC(dealloc_pd),
IB_MANDATORY_FUNC(create_qp),
IB_MANDATORY_FUNC(modify_qp),
IB_MANDATORY_FUNC(destroy_qp),
IB_MANDATORY_FUNC(post_send),
IB_MANDATORY_FUNC(post_recv),
IB_MANDATORY_FUNC(create_cq),
IB_MANDATORY_FUNC(destroy_cq),
IB_MANDATORY_FUNC(poll_cq),
IB_MANDATORY_FUNC(req_notify_cq),
IB_MANDATORY_FUNC(get_dma_mr),
IB_MANDATORY_FUNC(reg_user_mr),
IB_MANDATORY_FUNC(dereg_mr),
IB_MANDATORY_FUNC(get_port_immutable)
};
int i;
device->kverbs_provider = true;
for (i = 0; i < ARRAY_SIZE(mandatory_table); ++i) {
if (!*(void **) ((void *) &device->ops +
mandatory_table[i].offset)) {
device->kverbs_provider = false;
break;
}
}
}
/*
* Caller must perform ib_device_put() to return the device reference count
* when ib_device_get_by_index() returns valid device pointer.
*/
struct ib_device *ib_device_get_by_index(const struct net *net, u32 index)
{
struct ib_device *device;
down_read(&devices_rwsem);
device = xa_load(&devices, index);
if (device) {
if (!rdma_dev_access_netns(device, net)) {
device = NULL;
goto out;
}
if (!ib_device_try_get(device))
device = NULL;
}
out:
up_read(&devices_rwsem);
return device;
}
/**
* ib_device_put - Release IB device reference
* @device: device whose reference to be released
*
* ib_device_put() releases reference to the IB device to allow it to be
* unregistered and eventually free.
*/
void ib_device_put(struct ib_device *device)
{
if (refcount_dec_and_test(&device->refcount))
complete(&device->unreg_completion);
}
EXPORT_SYMBOL(ib_device_put);
static struct ib_device *__ib_device_get_by_name(const char *name)
{
struct ib_device *device;
unsigned long index;
xa_for_each (&devices, index, device)
if (!strcmp(name, dev_name(&device->dev)))
return device;
return NULL;
}
/**
* ib_device_get_by_name - Find an IB device by name
* @name: The name to look for
* @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all)
*
* Find and hold an ib_device by its name. The caller must call
* ib_device_put() on the returned pointer.
*/
struct ib_device *ib_device_get_by_name(const char *name,
enum rdma_driver_id driver_id)
{
struct ib_device *device;
down_read(&devices_rwsem);
device = __ib_device_get_by_name(name);
if (device && driver_id != RDMA_DRIVER_UNKNOWN &&
device->ops.driver_id != driver_id)
device = NULL;
if (device) {
if (!ib_device_try_get(device))
device = NULL;
}
up_read(&devices_rwsem);
return device;
}
EXPORT_SYMBOL(ib_device_get_by_name);
static int rename_compat_devs(struct ib_device *device)
{
struct ib_core_device *cdev;
unsigned long index;
int ret = 0;
mutex_lock(&device->compat_devs_mutex);
xa_for_each (&device->compat_devs, index, cdev) {
ret = device_rename(&cdev->dev, dev_name(&device->dev));
if (ret) {
dev_warn(&cdev->dev,
"Fail to rename compatdev to new name %s\n",
dev_name(&device->dev));
break;
}
}
mutex_unlock(&device->compat_devs_mutex);
return ret;
}
int ib_device_rename(struct ib_device *ibdev, const char *name)
{
unsigned long index;
void *client_data;
int ret;
down_write(&devices_rwsem);
if (!strcmp(name, dev_name(&ibdev->dev))) {
up_write(&devices_rwsem);
return 0;
}
if (__ib_device_get_by_name(name)) {
up_write(&devices_rwsem);
return -EEXIST;
}
ret = device_rename(&ibdev->dev, name);
if (ret) {
up_write(&devices_rwsem);
return ret;
}
strscpy(ibdev->name, name, IB_DEVICE_NAME_MAX);
ret = rename_compat_devs(ibdev);
downgrade_write(&devices_rwsem);
down_read(&ibdev->client_data_rwsem);
xan_for_each_marked(&ibdev->client_data, index, client_data,
CLIENT_DATA_REGISTERED) {
struct ib_client *client = xa_load(&clients, index);
if (!client || !client->rename)
continue;
client->rename(ibdev, client_data);
}
up_read(&ibdev->client_data_rwsem);
rdma_nl_notify_event(ibdev, 0, RDMA_RENAME_EVENT);
up_read(&devices_rwsem);
return 0;
}
int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
{
if (use_dim > 1)
return -EINVAL;
ibdev->use_cq_dim = use_dim;
return 0;
}
static int alloc_name(struct ib_device *ibdev, const char *name)
{
struct ib_device *device;
unsigned long index;
struct ida inuse;
int rc;
int i;
lockdep_assert_held_write(&devices_rwsem);
ida_init(&inuse);
xa_for_each (&devices, index, device) {
char buf[IB_DEVICE_NAME_MAX];
if (sscanf(dev_name(&device->dev), name, &i) != 1)
continue;
if (i < 0 || i >= INT_MAX)
continue;
snprintf(buf, sizeof buf, name, i);
if (strcmp(buf, dev_name(&device->dev)) != 0)
continue;
rc = ida_alloc_range(&inuse, i, i, GFP_KERNEL);
if (rc < 0)
goto out;
}
rc = ida_alloc(&inuse, GFP_KERNEL);
if (rc < 0)
goto out;
rc = dev_set_name(&ibdev->dev, name, rc);
out:
ida_destroy(&inuse);
return rc;
}
static void ib_device_release(struct device *device)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
free_netdevs(dev);
WARN_ON(refcount_read(&dev->refcount));
if (dev->hw_stats_data)
ib_device_release_hw_stats(dev->hw_stats_data);
if (dev->port_data) {
ib_cache_release_one(dev);
ib_security_release_port_pkey_list(dev);
rdma_counter_release(dev);
kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu,
pdata[0]),
rcu_head);
}
mutex_destroy(&dev->subdev_lock);
mutex_destroy(&dev->unregistration_lock);
mutex_destroy(&dev->compat_devs_mutex);
xa_destroy(&dev->compat_devs);
xa_destroy(&dev->client_data);
kfree_rcu(dev, rcu_head);
}
static int ib_device_uevent(const struct device *device,
struct kobj_uevent_env *env)
{
if (add_uevent_var(env, "NAME=%s", dev_name(device)))
return -ENOMEM;
/*
* It would be nice to pass the node GUID with the event...
*/
return 0;
}
static const void *net_namespace(const struct device *d)
{
const struct ib_core_device *coredev =
container_of(d, struct ib_core_device, dev);
return read_pnet(&coredev->rdma_net);
}
static struct class ib_class = {
.name = "infiniband",
.dev_release = ib_device_release,
.dev_uevent = ib_device_uevent,
.ns_type = &net_ns_type_operations,
.namespace = net_namespace,
};
static void rdma_init_coredev(struct ib_core_device *coredev,
struct ib_device *dev, struct net *net)
{
bool is_full_dev = &dev->coredev == coredev;
/* This BUILD_BUG_ON is intended to catch layout change
* of union of ib_core_device and device.
* dev must be the first element as ib_core and providers
* driver uses it. Adding anything in ib_core_device before
* device will break this assumption.
*/
BUILD_BUG_ON(offsetof(struct ib_device, coredev.dev) !=
offsetof(struct ib_device, dev));
coredev->dev.class = &ib_class;
coredev->dev.groups = dev->groups;
/*
* Don't expose hw counters outside of the init namespace.
*/
if (!is_full_dev && dev->hw_stats_attr_index)
coredev->dev.groups[dev->hw_stats_attr_index] = NULL;
device_initialize(&coredev->dev);
coredev->owner = dev;
INIT_LIST_HEAD(&coredev->port_list);
write_pnet(&coredev->rdma_net, net);
}
/**
* _ib_alloc_device - allocate an IB device struct
* @size:size of structure to allocate
*
* Low-level drivers should use ib_alloc_device() to allocate &struct
* ib_device. @size is the size of the structure to be allocated,
* including any private data used by the low-level driver.
* ib_dealloc_device() must be used to free structures allocated with
* ib_alloc_device().
*/
struct ib_device *_ib_alloc_device(size_t size)
{
struct ib_device *device;
unsigned int i;
if (WARN_ON(size < sizeof(struct ib_device)))
return NULL;
device = kzalloc(size, GFP_KERNEL);
if (!device)
return NULL;
if (rdma_restrack_init(device)) {
kfree(device);
return NULL;
}
rdma_init_coredev(&device->coredev, device, &init_net);
INIT_LIST_HEAD(&device->event_handler_list);
spin_lock_init(&device->qp_open_list_lock);
init_rwsem(&device->event_handler_rwsem);
mutex_init(&device->unregistration_lock);
/*
* client_data needs to be alloc because we don't want our mark to be
* destroyed if the user stores NULL in the client data.
*/
xa_init_flags(&device->client_data, XA_FLAGS_ALLOC);
init_rwsem(&device->client_data_rwsem);
xa_init_flags(&device->compat_devs, XA_FLAGS_ALLOC);
mutex_init(&device->compat_devs_mutex);
init_completion(&device->unreg_completion);
INIT_WORK(&device->unregistration_work, ib_unregister_work);
spin_lock_init(&device->cq_pools_lock);
for (i = 0; i < ARRAY_SIZE(device->cq_pools); i++)
INIT_LIST_HEAD(&device->cq_pools[i]);
rwlock_init(&device->cache_lock);
device->uverbs_cmd_mask =
BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW) |
BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD) |
BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST) |
BIT_ULL(IB_USER_VERBS_CMD_CLOSE_XRCD) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_AH) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_CQ) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_QP) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_SRQ) |
BIT_ULL(IB_USER_VERBS_CMD_CREATE_XSRQ) |
BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW) |
BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_PD) |
BIT_ULL(IB_USER_VERBS_CMD_DEREG_MR) |
BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH) |
BIT_ULL(IB_USER_VERBS_CMD_DESTROY_CQ) |
BIT_ULL(IB_USER_VERBS_CMD_DESTROY_QP) |
BIT_ULL(IB_USER_VERBS_CMD_DESTROY_SRQ) |
BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST) |
BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) |
BIT_ULL(IB_USER_VERBS_CMD_MODIFY_QP) |
BIT_ULL(IB_USER_VERBS_CMD_MODIFY_SRQ) |
BIT_ULL(IB_USER_VERBS_CMD_OPEN_QP) |
BIT_ULL(IB_USER_VERBS_CMD_OPEN_XRCD) |
BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE) |
BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT) |
BIT_ULL(IB_USER_VERBS_CMD_QUERY_QP) |
BIT_ULL(IB_USER_VERBS_CMD_QUERY_SRQ) |
BIT_ULL(IB_USER_VERBS_CMD_REG_MR) |
BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) |
BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ);
mutex_init(&device->subdev_lock);
INIT_LIST_HEAD(&device->subdev_list_head);
INIT_LIST_HEAD(&device->subdev_list);
return device;
}
EXPORT_SYMBOL(_ib_alloc_device);
/**
* ib_dealloc_device - free an IB device struct
* @device:structure to free
*
* Free a structure allocated with ib_alloc_device().
*/
void ib_dealloc_device(struct ib_device *device)
{
if (device->ops.dealloc_driver)
device->ops.dealloc_driver(device);
/*
* ib_unregister_driver() requires all devices to remain in the xarray
* while their ops are callable. The last op we call is dealloc_driver
* above. This is needed to create a fence on op callbacks prior to
* allowing the driver module to unload.
*/
down_write(&devices_rwsem);
if (xa_load(&devices, device->index) == device)
xa_erase(&devices, device->index);
up_write(&devices_rwsem);
/* Expedite releasing netdev references */
free_netdevs(device);
WARN_ON(!xa_empty(&device->compat_devs));
WARN_ON(!xa_empty(&device->client_data));
WARN_ON(refcount_read(&device->refcount));
rdma_restrack_clean(device);
/* Balances with device_initialize */
put_device(&device->dev);
}
EXPORT_SYMBOL(ib_dealloc_device);
/*
* add_client_context() and remove_client_context() must be safe against
* parallel calls on the same device - registration/unregistration of both the
* device and client can be occurring in parallel.
*
* The routines need to be a fence, any caller must not return until the add
* or remove is fully completed.
*/
static int add_client_context(struct ib_device *device,
struct ib_client *client)
{
int ret = 0;
if (!device->kverbs_provider && !client->no_kverbs_req)
return 0;
down_write(&device->client_data_rwsem);
/*
* So long as the client is registered hold both the client and device
* unregistration locks.
*/
if (!refcount_inc_not_zero(&client->uses))
goto out_unlock;
refcount_inc(&device->refcount);
/*
* Another caller to add_client_context got here first and has already
* completely initialized context.
*/
if (xa_get_mark(&device->client_data, client->client_id,
CLIENT_DATA_REGISTERED))
goto out;
ret = xa_err(xa_store(&device->client_data, client->client_id, NULL,
GFP_KERNEL));
if (ret)
goto out;
downgrade_write(&device->client_data_rwsem);
if (client->add) {
if (client->add(device)) {
/*
* If a client fails to add then the error code is
* ignored, but we won't call any more ops on this
* client.
*/
xa_erase(&device->client_data, client->client_id);
up_read(&device->client_data_rwsem);
ib_device_put(device);
ib_client_put(client);
return 0;
}
}
/* Readers shall not see a client until add has been completed */
xa_set_mark(&device->client_data, client->client_id,
CLIENT_DATA_REGISTERED);
up_read(&device->client_data_rwsem);
return 0;
out:
ib_device_put(device);
ib_client_put(client);
out_unlock:
up_write(&device->client_data_rwsem);
return ret;
}
static void remove_client_context(struct ib_device *device,
unsigned int client_id)
{
struct ib_client *client;
void *client_data;
down_write(&device->client_data_rwsem);
if (!xa_get_mark(&device->client_data, client_id,
CLIENT_DATA_REGISTERED)) {
up_write(&device->client_data_rwsem);
return;
}
client_data = xa_load(&device->client_data, client_id);
xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED);
client = xa_load(&clients, client_id);
up_write(&device->client_data_rwsem);
/*
* Notice we cannot be holding any exclusive locks when calling the
* remove callback as the remove callback can recurse back into any
* public functions in this module and thus try for any locks those
* functions take.
*
* For this reason clients and drivers should not call the
* unregistration functions will holdling any locks.
*/
if (client->remove)
client->remove(device, client_data);
xa_erase(&device->client_data, client_id);
ib_device_put(device);
ib_client_put(client);
}
static int alloc_port_data(struct ib_device *device)
{
struct ib_port_data_rcu *pdata_rcu;
u32 port;
if (device->port_data)
return 0;
/* This can only be called once the physical port range is defined */
if (WARN_ON(!device->phys_port_cnt))
return -EINVAL;
/* Reserve U32_MAX so the logic to go over all the ports is sane */
if (WARN_ON(device->phys_port_cnt == U32_MAX))
return -EINVAL;
/*
* device->port_data is indexed directly by the port number to make
* access to this data as efficient as possible.
*
* Therefore port_data is declared as a 1 based array with potential
* empty slots at the beginning.
*/
pdata_rcu = kzalloc(struct_size(pdata_rcu, pdata,
size_add(rdma_end_port(device), 1)),
GFP_KERNEL);
if (!pdata_rcu)
return -ENOMEM;
/*
* The rcu_head is put in front of the port data array and the stored
* pointer is adjusted since we never need to see that member until
* kfree_rcu.
*/
device->port_data = pdata_rcu->pdata;
rdma_for_each_port (device, port) {
struct ib_port_data *pdata = &device->port_data[port];
pdata->ib_dev = device;
spin_lock_init(&pdata->pkey_list_lock);
INIT_LIST_HEAD(&pdata->pkey_list);
spin_lock_init(&pdata->netdev_lock);
INIT_HLIST_NODE(&pdata->ndev_hash_link);
}
return 0;
}
static int verify_immutable(const struct ib_device *dev, u32 port)
{
return WARN_ON(!rdma_cap_ib_mad(dev, port) &&
rdma_max_mad_size(dev, port) != 0);
}
static int setup_port_data(struct ib_device *device)
{
u32 port;
int ret;
ret = alloc_port_data(device);
if (ret)
return ret;
rdma_for_each_port (device, port) {
struct ib_port_data *pdata = &device->port_data[port];
ret = device->ops.get_port_immutable(device, port,
&pdata->immutable);
if (ret)
return ret;
if (verify_immutable(device, port))
return -EINVAL;
}
return 0;
}
/**
* ib_port_immutable_read() - Read rdma port's immutable data
* @dev: IB device
* @port: port number whose immutable data to read. It starts with index 1 and
* valid upto including rdma_end_port().
*/
const struct ib_port_immutable*
ib_port_immutable_read(struct ib_device *dev, unsigned int port)
{
WARN_ON(!rdma_is_port_valid(dev, port));
return &dev->port_data[port].immutable;
}
EXPORT_SYMBOL(ib_port_immutable_read);
void ib_get_device_fw_str(struct ib_device *dev, char *str)
{
if (dev->ops.get_dev_fw_str)
dev->ops.get_dev_fw_str(dev, str);
else
str[0] = '\0';
}
EXPORT_SYMBOL(ib_get_device_fw_str);
static void ib_policy_change_task(struct work_struct *work)
{
struct ib_device *dev;
unsigned long index;
down_read(&devices_rwsem);
xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
unsigned int i;
rdma_for_each_port (dev, i) {
u64 sp;
ib_get_cached_subnet_prefix(dev, i, &sp);
ib_security_cache_change(dev, i, sp);
}
}
up_read(&devices_rwsem);
}
static int ib_security_change(struct notifier_block *nb, unsigned long event,
void *lsm_data)
{
if (event != LSM_POLICY_CHANGE)
return NOTIFY_DONE;
schedule_work(&ib_policy_change_work);
ib_mad_agent_security_change();
return NOTIFY_OK;
}
static void compatdev_release(struct device *dev)
{
struct ib_core_device *cdev =
container_of(dev, struct ib_core_device, dev);
kfree(cdev);
}
static int add_one_compat_dev(struct ib_device *device,
struct rdma_dev_net *rnet)
{
struct ib_core_device *cdev;
int ret;
lockdep_assert_held(&rdma_nets_rwsem);
if (!ib_devices_shared_netns)
return 0;
/*
* Create and add compat device in all namespaces other than where it
* is currently bound to.
*/
if (net_eq(read_pnet(&rnet->net),
read_pnet(&device->coredev.rdma_net)))
return 0;
/*
* The first of init_net() or ib_register_device() to take the
* compat_devs_mutex wins and gets to add the device. Others will wait
* for completion here.
*/
mutex_lock(&device->compat_devs_mutex);
cdev = xa_load(&device->compat_devs, rnet->id);
if (cdev) {
ret = 0;
goto done;
}
ret = xa_reserve(&device->compat_devs, rnet->id, GFP_KERNEL);
if (ret)
goto done;
cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
if (!cdev) {
ret = -ENOMEM;
goto cdev_err;
}
cdev->dev.parent = device->dev.parent;
rdma_init_coredev(cdev, device, read_pnet(&rnet->net));
cdev->dev.release = compatdev_release;
ret = dev_set_name(&cdev->dev, "%s", dev_name(&device->dev));
if (ret)
goto add_err;
ret = device_add(&cdev->dev);
if (ret)
goto add_err;
ret = ib_setup_port_attrs(cdev);
if (ret)
goto port_err;
ret = xa_err(xa_store(&device->compat_devs, rnet->id,
cdev, GFP_KERNEL));
if (ret)
goto insert_err;
mutex_unlock(&device->compat_devs_mutex);
return 0;
insert_err:
ib_free_port_attrs(cdev);
port_err:
device_del(&cdev->dev);
add_err:
put_device(&cdev->dev);
cdev_err:
xa_release(&device->compat_devs, rnet->id);
done:
mutex_unlock(&device->compat_devs_mutex);
return ret;
}
static void remove_one_compat_dev(struct ib_device *device, u32 id)
{
struct ib_core_device *cdev;
mutex_lock(&device->compat_devs_mutex);
cdev = xa_erase(&device->compat_devs, id);
mutex_unlock(&device->compat_devs_mutex);
if (cdev) {
ib_free_port_attrs(cdev);
device_del(&cdev->dev);
put_device(&cdev->dev);
}
}
static void remove_compat_devs(struct ib_device *device)
{
struct ib_core_device *cdev;
unsigned long index;
xa_for_each (&device->compat_devs, index, cdev)
remove_one_compat_dev(device, index);
}
static int add_compat_devs(struct ib_device *device)
{
struct rdma_dev_net *rnet;
unsigned long index;
int ret = 0;
lockdep_assert_held(&devices_rwsem);
down_read(&rdma_nets_rwsem);
xa_for_each (&rdma_nets, index, rnet) {
ret = add_one_compat_dev(device, rnet);
if (ret)
break;
}
up_read(&rdma_nets_rwsem);
return ret;
}
static void remove_all_compat_devs(void)
{
struct ib_compat_device *cdev;
struct ib_device *dev;
unsigned long index;
down_read(&devices_rwsem);
xa_for_each (&devices, index, dev) {
unsigned long c_index = 0;
/* Hold nets_rwsem so that any other thread modifying this
* system param can sync with this thread.
*/
down_read(&rdma_nets_rwsem);
xa_for_each (&dev->compat_devs, c_index, cdev)
remove_one_compat_dev(dev, c_index);
up_read(&rdma_nets_rwsem);
}
up_read(&devices_rwsem);
}
static int add_all_compat_devs(void)
{
struct rdma_dev_net *rnet;
struct ib_device *dev;
unsigned long index;
int ret = 0;
down_read(&devices_rwsem);
xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
unsigned long net_index = 0;
/* Hold nets_rwsem so that any other thread modifying this
* system param can sync with this thread.
*/
down_read(&rdma_nets_rwsem);
xa_for_each (&rdma_nets, net_index, rnet) {
ret = add_one_compat_dev(dev, rnet);
if (ret)
break;
}
up_read(&rdma_nets_rwsem);
}
up_read(&devices_rwsem);
if (ret)
remove_all_compat_devs();
return ret;
}
int rdma_compatdev_set(u8 enable)
{
struct rdma_dev_net *rnet;
unsigned long index;
int ret = 0;
down_write(&rdma_nets_rwsem);
if (ib_devices_shared_netns == enable) {
up_write(&rdma_nets_rwsem);
return 0;
}
/* enable/disable of compat devices is not supported
* when more than default init_net exists.
*/
xa_for_each (&rdma_nets, index, rnet) {
ret++;
break;
}
if (!ret)
ib_devices_shared_netns = enable;
up_write(&rdma_nets_rwsem);
if (ret)
return -EBUSY;
if (enable)
ret = add_all_compat_devs();
else
remove_all_compat_devs();
return ret;
}
static void rdma_dev_exit_net(struct net *net)
{
struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
struct ib_device *dev;
unsigned long index;
int ret;
down_write(&rdma_nets_rwsem);
/*
* Prevent the ID from being re-used and hide the id from xa_for_each.
*/
ret = xa_err(xa_store(&rdma_nets, rnet->id, NULL, GFP_KERNEL));
WARN_ON(ret);
up_write(&rdma_nets_rwsem);
down_read(&devices_rwsem);
xa_for_each (&devices, index, dev) {
get_device(&dev->dev);
/*
* Release the devices_rwsem so that pontentially blocking
* device_del, doesn't hold the devices_rwsem for too long.
*/
up_read(&devices_rwsem);
remove_one_compat_dev(dev, rnet->id);
/*
* If the real device is in the NS then move it back to init.
*/
rdma_dev_change_netns(dev, net, &init_net);
put_device(&dev->dev);
down_read(&devices_rwsem);
}
up_read(&devices_rwsem);
rdma_nl_net_exit(rnet);
xa_erase(&rdma_nets, rnet->id);
}
static __net_init int rdma_dev_init_net(struct net *net)
{
struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
unsigned long index;
struct ib_device *dev;
int ret;
write_pnet(&rnet->net, net);
ret = rdma_nl_net_init(rnet);
if (ret)
return ret;
/* No need to create any compat devices in default init_net. */
if (net_eq(net, &init_net))
return 0;
ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL);
if (ret) {
rdma_nl_net_exit(rnet);
return ret;
}
down_read(&devices_rwsem);
xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
/* Hold nets_rwsem so that netlink command cannot change
* system configuration for device sharing mode.
*/
down_read(&rdma_nets_rwsem);
ret = add_one_compat_dev(dev, rnet);
up_read(&rdma_nets_rwsem);
if (ret)
break;
}
up_read(&devices_rwsem);
if (ret)
rdma_dev_exit_net(net);
return ret;
}
/*
* Assign the unique string device name and the unique device index. This is
* undone by ib_dealloc_device.
*/
static int assign_name(struct ib_device *device, const char *name)
{
static u32 last_id;
int ret;
down_write(&devices_rwsem);
/* Assign a unique name to the device */
if (strchr(name, '%'))
ret = alloc_name(device, name);
else
ret = dev_set_name(&device->dev, name);
if (ret)
goto out;
if (__ib_device_get_by_name(dev_name(&device->dev))) {
ret = -ENFILE;
goto out;
}
strscpy(device->name, dev_name(&device->dev), IB_DEVICE_NAME_MAX);
ret = xa_alloc_cyclic(&devices, &device->index, device, xa_limit_31b,
&last_id, GFP_KERNEL);
if (ret > 0)
ret = 0;
out:
up_write(&devices_rwsem);
return ret;
}
/*
* setup_device() allocates memory and sets up data that requires calling the
* device ops, this is the only reason these actions are not done during
* ib_alloc_device. It is undone by ib_dealloc_device().
*/
static int setup_device(struct ib_device *device)
{
struct ib_udata uhw = {.outlen = 0, .inlen = 0};
int ret;
ib_device_check_mandatory(device);
ret = setup_port_data(device);
if (ret) {
dev_warn(&device->dev, "Couldn't create per-port data\n");
return ret;
}
memset(&device->attrs, 0, sizeof(device->attrs));
ret = device->ops.query_device(device, &device->attrs, &uhw);
if (ret) {
dev_warn(&device->dev,
"Couldn't query the device attributes\n");
return ret;
}
return 0;
}
static void disable_device(struct ib_device *device)
{
u32 cid;
WARN_ON(!refcount_read(&device->refcount));
down_write(&devices_rwsem);
xa_clear_mark(&devices, device->index, DEVICE_REGISTERED);
up_write(&devices_rwsem);
/*
* Remove clients in LIFO order, see assign_client_id. This could be
* more efficient if xarray learns to reverse iterate. Since no new
* clients can be added to this ib_device past this point we only need
* the maximum possible client_id value here.
*/
down_read(&clients_rwsem);
cid = highest_client_id;
up_read(&clients_rwsem);
while (cid) {
cid--;
remove_client_context(device, cid);
}
ib_cq_pool_cleanup(device);
/* Pairs with refcount_set in enable_device */
ib_device_put(device);
wait_for_completion(&device->unreg_completion);
/*
* compat devices must be removed after device refcount drops to zero.
* Otherwise init_net() may add more compatdevs after removing compat
* devices and before device is disabled.
*/
remove_compat_devs(device);
}
/*
* An enabled device is visible to all clients and to all the public facing
* APIs that return a device pointer. This always returns with a new get, even
* if it fails.
*/
static int enable_device_and_get(struct ib_device *device)
{
struct ib_client *client;
unsigned long index;
int ret = 0;
/*
* One ref belongs to the xa and the other belongs to this
* thread. This is needed to guard against parallel unregistration.
*/
refcount_set(&device->refcount, 2);
down_write(&devices_rwsem);
xa_set_mark(&devices, device->index, DEVICE_REGISTERED);
/*
* By using downgrade_write() we ensure that no other thread can clear
* DEVICE_REGISTERED while we are completing the client setup.
*/
downgrade_write(&devices_rwsem);
if (device->ops.enable_driver) {
ret = device->ops.enable_driver(device);
if (ret)
goto out;
}
down_read(&clients_rwsem);
xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) {
ret = add_client_context(device, client);
if (ret)
break;
}
up_read(&clients_rwsem);
if (!ret)
ret = add_compat_devs(device);
out:
up_read(&devices_rwsem);
return ret;
}
static void prevent_dealloc_device(struct ib_device *ib_dev)
{
}
static void ib_device_notify_register(struct ib_device *device)
{
struct net_device *netdev;
u32 port;
int ret;
down_read(&devices_rwsem);
ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT);
if (ret)
goto out;
rdma_for_each_port(device, port) {
netdev = ib_device_get_netdev(device, port);
if (!netdev)
continue;
ret = rdma_nl_notify_event(device, port,
RDMA_NETDEV_ATTACH_EVENT);
dev_put(netdev);
if (ret)
goto out;
}
out:
up_read(&devices_rwsem);
}
/**
* ib_register_device - Register an IB device with IB core
* @device: Device to register
* @name: unique string device name. This may include a '%' which will
* cause a unique index to be added to the passed device name.
* @dma_device: pointer to a DMA-capable device. If %NULL, then the IB
* device will be used. In this case the caller should fully
* setup the ibdev for DMA. This usually means using dma_virt_ops.
*
* Low-level drivers use ib_register_device() to register their
* devices with the IB core. All registered clients will receive a
* callback for each device that is added. @device must be allocated
* with ib_alloc_device().
*
* If the driver uses ops.dealloc_driver and calls any ib_unregister_device()
* asynchronously then the device pointer may become freed as soon as this
* function returns.
*/
int ib_register_device(struct ib_device *device, const char *name,
struct device *dma_device)
{
int ret;
ret = assign_name(device, name);
if (ret)
return ret;
/*
* If the caller does not provide a DMA capable device then the IB core
* will set up ib_sge and scatterlist structures that stash the kernel
* virtual address into the address field.
*/
WARN_ON(dma_device && !dma_device->dma_parms);
device->dma_device = dma_device;
ret = setup_device(device);
if (ret)
return ret;
ret = ib_cache_setup_one(device);
if (ret) {
dev_warn(&device->dev,
"Couldn't set up InfiniBand P_Key/GID cache\n");
return ret;
}
device->groups[0] = &ib_dev_attr_group;
device->groups[1] = device->ops.device_group;
ret = ib_setup_device_attrs(device);
if (ret)
goto cache_cleanup;
ib_device_register_rdmacg(device);
rdma_counter_init(device);
/*
* Ensure that ADD uevent is not fired because it
* is too early amd device is not initialized yet.
*/
dev_set_uevent_suppress(&device->dev, true);
ret = device_add(&device->dev);
if (ret)
goto cg_cleanup;
ret = ib_setup_port_attrs(&device->coredev);
if (ret) {
dev_warn(&device->dev,
"Couldn't register device with driver model\n");
goto dev_cleanup;
}
ret = enable_device_and_get(device);
if (ret) {
void (*dealloc_fn)(struct ib_device *);
/*
* If we hit this error flow then we don't want to
* automatically dealloc the device since the caller is
* expected to call ib_dealloc_device() after
* ib_register_device() fails. This is tricky due to the
* possibility for a parallel unregistration along with this
* error flow. Since we have a refcount here we know any
* parallel flow is stopped in disable_device and will see the
* special dealloc_driver pointer, causing the responsibility to
* ib_dealloc_device() to revert back to this thread.
*/
dealloc_fn = device->ops.dealloc_driver;
device->ops.dealloc_driver = prevent_dealloc_device;
ib_device_put(device);
__ib_unregister_device(device);
device->ops.dealloc_driver = dealloc_fn;
dev_set_uevent_suppress(&device->dev, false);
return ret;
}
dev_set_uevent_suppress(&device->dev, false);
/* Mark for userspace that device is ready */
kobject_uevent(&device->dev.kobj, KOBJ_ADD);
ib_device_notify_register(device);
ib_device_put(device);
return 0;
dev_cleanup:
device_del(&device->dev);
cg_cleanup:
dev_set_uevent_suppress(&device->dev, false);
ib_device_unregister_rdmacg(device);
cache_cleanup:
ib_cache_cleanup_one(device);
return ret;
}
EXPORT_SYMBOL(ib_register_device);
/* Callers must hold a get on the device. */
static void __ib_unregister_device(struct ib_device *ib_dev)
{
struct ib_device *sub, *tmp;
mutex_lock(&ib_dev->subdev_lock);
list_for_each_entry_safe_reverse(sub, tmp,
&ib_dev->subdev_list_head,
subdev_list) {
list_del(&sub->subdev_list);
ib_dev->ops.del_sub_dev(sub);
ib_device_put(ib_dev);
}
mutex_unlock(&ib_dev->subdev_lock);
/*
* We have a registration lock so that all the calls to unregister are
* fully fenced, once any unregister returns the device is truely
* unregistered even if multiple callers are unregistering it at the
* same time. This also interacts with the registration flow and
* provides sane semantics if register and unregister are racing.
*/
mutex_lock(&ib_dev->unregistration_lock);
if (!refcount_read(&ib_dev->refcount))
goto out;
disable_device(ib_dev);
rdma_nl_notify_event(ib_dev, 0, RDMA_UNREGISTER_EVENT);
/* Expedite removing unregistered pointers from the hash table */
free_netdevs(ib_dev);
ib_free_port_attrs(&ib_dev->coredev);
device_del(&ib_dev->dev);
ib_device_unregister_rdmacg(ib_dev);
ib_cache_cleanup_one(ib_dev);
/*
* Drivers using the new flow may not call ib_dealloc_device except
* in error unwind prior to registration success.
*/
if (ib_dev->ops.dealloc_driver &&
ib_dev->ops.dealloc_driver != prevent_dealloc_device) {
WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1);
ib_dealloc_device(ib_dev);
}
out:
mutex_unlock(&ib_dev->unregistration_lock);
}
/**
* ib_unregister_device - Unregister an IB device
* @ib_dev: The device to unregister
*
* Unregister an IB device. All clients will receive a remove callback.
*
* Callers should call this routine only once, and protect against races with
* registration. Typically it should only be called as part of a remove
* callback in an implementation of driver core's struct device_driver and
* related.
*
* If ops.dealloc_driver is used then ib_dev will be freed upon return from
* this function.
*/
void ib_unregister_device(struct ib_device *ib_dev)
{
get_device(&ib_dev->dev);
__ib_unregister_device(ib_dev);
put_device(&ib_dev->dev);
}
EXPORT_SYMBOL(ib_unregister_device);
/**
* ib_unregister_device_and_put - Unregister a device while holding a 'get'
* @ib_dev: The device to unregister
*
* This is the same as ib_unregister_device(), except it includes an internal
* ib_device_put() that should match a 'get' obtained by the caller.
*
* It is safe to call this routine concurrently from multiple threads while
* holding the 'get'. When the function returns the device is fully
* unregistered.
*
* Drivers using this flow MUST use the driver_unregister callback to clean up
* their resources associated with the device and dealloc it.
*/
void ib_unregister_device_and_put(struct ib_device *ib_dev)
{
WARN_ON(!ib_dev->ops.dealloc_driver);
get_device(&ib_dev->dev);
ib_device_put(ib_dev);
__ib_unregister_device(ib_dev);
put_device(&ib_dev->dev);
}
EXPORT_SYMBOL(ib_unregister_device_and_put);
/**
* ib_unregister_driver - Unregister all IB devices for a driver
* @driver_id: The driver to unregister
*
* This implements a fence for device unregistration. It only returns once all
* devices associated with the driver_id have fully completed their
* unregistration and returned from ib_unregister_device*().
*
* If device's are not yet unregistered it goes ahead and starts unregistering
* them.
*
* This does not block creation of new devices with the given driver_id, that
* is the responsibility of the caller.
*/
void ib_unregister_driver(enum rdma_driver_id driver_id)
{
struct ib_device *ib_dev;
unsigned long index;
down_read(&devices_rwsem);
xa_for_each (&devices, index, ib_dev) {
if (ib_dev->ops.driver_id != driver_id)
continue;
get_device(&ib_dev->dev);
up_read(&devices_rwsem);
WARN_ON(!ib_dev->ops.dealloc_driver);
__ib_unregister_device(ib_dev);
put_device(&ib_dev->dev);
down_read(&devices_rwsem);
}
up_read(&devices_rwsem);
}
EXPORT_SYMBOL(ib_unregister_driver);
static void ib_unregister_work(struct work_struct *work)
{
struct ib_device *ib_dev =
container_of(work, struct ib_device, unregistration_work);
__ib_unregister_device(ib_dev);
put_device(&ib_dev->dev);
}
/**
* ib_unregister_device_queued - Unregister a device using a work queue
* @ib_dev: The device to unregister
*
* This schedules an asynchronous unregistration using a WQ for the device. A
* driver should use this to avoid holding locks while doing unregistration,
* such as holding the RTNL lock.
*
* Drivers using this API must use ib_unregister_driver before module unload
* to ensure that all scheduled unregistrations have completed.
*/
void ib_unregister_device_queued(struct ib_device *ib_dev)
{
WARN_ON(!refcount_read(&ib_dev->refcount));
WARN_ON(!ib_dev->ops.dealloc_driver);
get_device(&ib_dev->dev);
if (!queue_work(ib_unreg_wq, &ib_dev->unregistration_work))
put_device(&ib_dev->dev);
}
EXPORT_SYMBOL(ib_unregister_device_queued);
/*
* The caller must pass in a device that has the kref held and the refcount
* released. If the device is in cur_net and still registered then it is moved
* into net.
*/
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
struct net *net)
{
int ret2 = -EINVAL;
int ret;
mutex_lock(&device->unregistration_lock);
/*
* If a device not under ib_device_get() or if the unregistration_lock
* is not held, the namespace can be changed, or it can be unregistered.
* Check again under the lock.
*/
if (refcount_read(&device->refcount) == 0 ||
!net_eq(cur_net, read_pnet(&device->coredev.rdma_net))) {
ret = -ENODEV;
goto out;
}
kobject_uevent(&device->dev.kobj, KOBJ_REMOVE);
disable_device(device);
/*
* At this point no one can be using the device, so it is safe to
* change the namespace.
*/
write_pnet(&device->coredev.rdma_net, net);
down_read(&devices_rwsem);
/*
* Currently rdma devices are system wide unique. So the device name
* is guaranteed free in the new namespace. Publish the new namespace
* at the sysfs level.
*/
ret = device_rename(&device->dev, dev_name(&device->dev));
up_read(&devices_rwsem);
if (ret) {
dev_warn(&device->dev,
"%s: Couldn't rename device after namespace change\n",
__func__);
/* Try and put things back and re-enable the device */
write_pnet(&device->coredev.rdma_net, cur_net);
}
ret2 = enable_device_and_get(device);
if (ret2) {
/*
* This shouldn't really happen, but if it does, let the user
* retry at later point. So don't disable the device.
*/
dev_warn(&device->dev,
"%s: Couldn't re-enable device after namespace change\n",
__func__);
}
kobject_uevent(&device->dev.kobj, KOBJ_ADD);
ib_device_put(device);
out:
mutex_unlock(&device->unregistration_lock);
if (ret)
return ret;
return ret2;
}
int ib_device_set_netns_put(struct sk_buff *skb,
struct ib_device *dev, u32 ns_fd)
{
struct net *net;
int ret;
net = get_net_ns_by_fd(ns_fd);
if (IS_ERR(net)) {
ret = PTR_ERR(net);
goto net_err;
}
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
goto ns_err;
}
/*
* All the ib_clients, including uverbs, are reset when the namespace is
* changed and this cannot be blocked waiting for userspace to do
* something, so disassociation is mandatory.
*/
if (!dev->ops.disassociate_ucontext || ib_devices_shared_netns) {
ret = -EOPNOTSUPP;
goto ns_err;
}
get_device(&dev->dev);
ib_device_put(dev);
ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net);
put_device(&dev->dev);
put_net(net);
return ret;
ns_err:
put_net(net);
net_err:
ib_device_put(dev);
return ret;
}
static struct pernet_operations rdma_dev_net_ops = {
.init = rdma_dev_init_net,
.exit = rdma_dev_exit_net,
.id = &rdma_dev_net_id,
.size = sizeof(struct rdma_dev_net),
};
static int assign_client_id(struct ib_client *client)
{
int ret;
lockdep_assert_held(&clients_rwsem);
/*
* The add/remove callbacks must be called in FIFO/LIFO order. To
* achieve this we assign client_ids so they are sorted in
* registration order.
*/
client->client_id = highest_client_id;
ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL);
if (ret)
return ret;
highest_client_id++;
xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED);
return 0;
}
static void remove_client_id(struct ib_client *client)
{
down_write(&clients_rwsem);
xa_erase(&clients, client->client_id);
for (; highest_client_id; highest_client_id--)
if (xa_load(&clients, highest_client_id - 1))
break;
up_write(&clients_rwsem);
}
/**
* ib_register_client - Register an IB client
* @client:Client to register
*
* Upper level users of the IB drivers can use ib_register_client() to
* register callbacks for IB device addition and removal. When an IB
* device is added, each registered client's add method will be called
* (in the order the clients were registered), and when a device is
* removed, each client's remove method will be called (in the reverse
* order that clients were registered). In addition, when
* ib_register_client() is called, the client will receive an add
* callback for all devices already registered.
*/
int ib_register_client(struct ib_client *client)
{
struct ib_device *device;
unsigned long index;
bool need_unreg = false;
int ret;
refcount_set(&client->uses, 1);
init_completion(&client->uses_zero);
/*
* The devices_rwsem is held in write mode to ensure that a racing
* ib_register_device() sees a consisent view of clients and devices.
*/
down_write(&devices_rwsem);
down_write(&clients_rwsem);
ret = assign_client_id(client);
if (ret)
goto out;
need_unreg = true;
xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) {
ret = add_client_context(device, client);
if (ret)
goto out;
}
ret = 0;
out:
up_write(&clients_rwsem);
up_write(&devices_rwsem);
if (need_unreg && ret)
ib_unregister_client(client);
return ret;
}
EXPORT_SYMBOL(ib_register_client);
/**
* ib_unregister_client - Unregister an IB client
* @client:Client to unregister
*
* Upper level users use ib_unregister_client() to remove their client
* registration. When ib_unregister_client() is called, the client
* will receive a remove callback for each IB device still registered.
*
* This is a full fence, once it returns no client callbacks will be called,
* or are running in another thread.
*/
void ib_unregister_client(struct ib_client *client)
{
struct ib_device *device;
unsigned long index;
down_write(&clients_rwsem);
ib_client_put(client);
xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED);
up_write(&clients_rwsem);
/* We do not want to have locks while calling client->remove() */
rcu_read_lock();
xa_for_each (&devices, index, device) {
if (!ib_device_try_get(device))
continue;
rcu_read_unlock();
remove_client_context(device, client->client_id);
ib_device_put(device);
rcu_read_lock();
}
rcu_read_unlock();
/*
* remove_client_context() is not a fence, it can return even though a
* removal is ongoing. Wait until all removals are completed.
*/
wait_for_completion(&client->uses_zero);
remove_client_id(client);
}
EXPORT_SYMBOL(ib_unregister_client);
static int __ib_get_global_client_nl_info(const char *client_name,
struct ib_client_nl_info *res)
{
struct ib_client *client;
unsigned long index;
int ret = -ENOENT;
down_read(&clients_rwsem);
xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) {
if (strcmp(client->name, client_name) != 0)
continue;
if (!client->get_global_nl_info) {
ret = -EOPNOTSUPP;
break;
}
ret = client->get_global_nl_info(res);
if (WARN_ON(ret == -ENOENT))
ret = -EINVAL;
if (!ret && res->cdev)
get_device(res->cdev);
break;
}
up_read(&clients_rwsem);
return ret;
}
static int __ib_get_client_nl_info(struct ib_device *ibdev,
const char *client_name,
struct ib_client_nl_info *res)
{
unsigned long index;
void *client_data;
int ret = -ENOENT;
down_read(&ibdev->client_data_rwsem);
xan_for_each_marked (&ibdev->client_data, index, client_data,
CLIENT_DATA_REGISTERED) {
struct ib_client *client = xa_load(&clients, index);
if (!client || strcmp(client->name, client_name) != 0)
continue;
if (!client->get_nl_info) {
ret = -EOPNOTSUPP;
break;
}
ret = client->get_nl_info(ibdev, client_data, res);
if (WARN_ON(ret == -ENOENT))
ret = -EINVAL;
/*
* The cdev is guaranteed valid as long as we are inside the
* client_data_rwsem as remove_one can't be called. Keep it
* valid for the caller.
*/
if (!ret && res->cdev)
get_device(res->cdev);
break;
}
up_read(&ibdev->client_data_rwsem);
return ret;
}
/**
* ib_get_client_nl_info - Fetch the nl_info from a client
* @ibdev: IB device
* @client_name: Name of the client
* @res: Result of the query
*/
int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name,
struct ib_client_nl_info *res)
{
int ret;
if (ibdev)
ret = __ib_get_client_nl_info(ibdev, client_name, res);
else
ret = __ib_get_global_client_nl_info(client_name, res);
#ifdef CONFIG_MODULES
if (ret == -ENOENT) {
request_module("rdma-client-%s", client_name);
if (ibdev)
ret = __ib_get_client_nl_info(ibdev, client_name, res);
else
ret = __ib_get_global_client_nl_info(client_name, res);
}
#endif
if (ret) {
if (ret == -ENOENT)
return -EOPNOTSUPP;
return ret;
}
if (WARN_ON(!res->cdev))
return -EINVAL;
return 0;
}
/**
* ib_set_client_data - Set IB client context
* @device:Device to set context for
* @client:Client to set context for
* @data:Context to set
*
* ib_set_client_data() sets client context data that can be retrieved with
* ib_get_client_data(). This can only be called while the client is
* registered to the device, once the ib_client remove() callback returns this
* cannot be called.
*/
void ib_set_client_data(struct ib_device *device, struct ib_client *client,
void *data)
{
void *rc;
if (WARN_ON(IS_ERR(data)))
data = NULL;
rc = xa_store(&device->client_data, client->client_id, data,
GFP_KERNEL);
WARN_ON(xa_is_err(rc));
}
EXPORT_SYMBOL(ib_set_client_data);
/**
* ib_register_event_handler - Register an IB event handler
* @event_handler:Handler to register
*
* ib_register_event_handler() registers an event handler that will be
* called back when asynchronous IB events occur (as defined in
* chapter 11 of the InfiniBand Architecture Specification). This
* callback occurs in workqueue context.
*/
void ib_register_event_handler(struct ib_event_handler *event_handler)
{
down_write(&event_handler->device->event_handler_rwsem);
list_add_tail(&event_handler->list,
&event_handler->device->event_handler_list);
up_write(&event_handler->device->event_handler_rwsem);
}
EXPORT_SYMBOL(ib_register_event_handler);
/**
* ib_unregister_event_handler - Unregister an event handler
* @event_handler:Handler to unregister
*
* Unregister an event handler registered with
* ib_register_event_handler().
*/
void ib_unregister_event_handler(struct ib_event_handler *event_handler)
{
down_write(&event_handler->device->event_handler_rwsem);
list_del(&event_handler->list);
up_write(&event_handler->device->event_handler_rwsem);
}
EXPORT_SYMBOL(ib_unregister_event_handler);
void ib_dispatch_event_clients(struct ib_event *event)
{
struct ib_event_handler *handler;
down_read(&event->device->event_handler_rwsem);
list_for_each_entry(handler, &event->device->event_handler_list, list)
handler->handler(handler, event);
up_read(&event->device->event_handler_rwsem);
}
static int iw_query_port(struct ib_device *device,
u32 port_num,
struct ib_port_attr *port_attr)
{
struct in_device *inetdev;
struct net_device *netdev;
memset(port_attr, 0, sizeof(*port_attr));
netdev = ib_device_get_netdev(device, port_num);
if (!netdev)
return -ENODEV;
port_attr->max_mtu = IB_MTU_4096;
port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
if (!netif_carrier_ok(netdev)) {
port_attr->state = IB_PORT_DOWN;
port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
} else {
rcu_read_lock();
inetdev = __in_dev_get_rcu(netdev);
if (inetdev && inetdev->ifa_list) {
port_attr->state = IB_PORT_ACTIVE;
port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
} else {
port_attr->state = IB_PORT_INIT;
port_attr->phys_state =
IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING;
}
rcu_read_unlock();
}
dev_put(netdev);
return device->ops.query_port(device, port_num, port_attr);
}
static int __ib_query_port(struct ib_device *device,
u32 port_num,
struct ib_port_attr *port_attr)
{
int err;
memset(port_attr, 0, sizeof(*port_attr));
err = device->ops.query_port(device, port_num, port_attr);
if (err || port_attr->subnet_prefix)
return err;
if (rdma_port_get_link_layer(device, port_num) !=
IB_LINK_LAYER_INFINIBAND)
return 0;
ib_get_cached_subnet_prefix(device, port_num,
&port_attr->subnet_prefix);
return 0;
}
/**
* ib_query_port - Query IB port attributes
* @device:Device to query
* @port_num:Port number to query
* @port_attr:Port attributes
*
* ib_query_port() returns the attributes of a port through the
* @port_attr pointer.
*/
int ib_query_port(struct ib_device *device,
u32 port_num,
struct ib_port_attr *port_attr)
{
if (!rdma_is_port_valid(device, port_num))
return -EINVAL;
if (rdma_protocol_iwarp(device, port_num))
return iw_query_port(device, port_num, port_attr);
else
return __ib_query_port(device, port_num, port_attr);
}
EXPORT_SYMBOL(ib_query_port);
static void add_ndev_hash(struct ib_port_data *pdata)
{
unsigned long flags;
might_sleep();
spin_lock_irqsave(&ndev_hash_lock, flags);
if (hash_hashed(&pdata->ndev_hash_link)) {
hash_del_rcu(&pdata->ndev_hash_link);
spin_unlock_irqrestore(&ndev_hash_lock, flags);
/*
* We cannot do hash_add_rcu after a hash_del_rcu until the
* grace period
*/
synchronize_rcu();
spin_lock_irqsave(&ndev_hash_lock, flags);
}
if (pdata->netdev)
hash_add_rcu(ndev_hash, &pdata->ndev_hash_link,
(uintptr_t)pdata->netdev);
spin_unlock_irqrestore(&ndev_hash_lock, flags);
}
/**
* ib_device_set_netdev - Associate the ib_dev with an underlying net_device
* @ib_dev: Device to modify
* @ndev: net_device to affiliate, may be NULL
* @port: IB port the net_device is connected to
*
* Drivers should use this to link the ib_device to a netdev so the netdev
* shows up in interfaces like ib_enum_roce_netdev. Only one netdev may be
* affiliated with any port.
*
* The caller must ensure that the given ndev is not unregistered or
* unregistering, and that either the ib_device is unregistered or
* ib_device_set_netdev() is called with NULL when the ndev sends a
* NETDEV_UNREGISTER event.
*/
int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
u32 port)
{
enum rdma_nl_notify_event_type etype;
struct net_device *old_ndev;
struct ib_port_data *pdata;
unsigned long flags;
int ret;
if (!rdma_is_port_valid(ib_dev, port))
return -EINVAL;
/*
* Drivers wish to call this before ib_register_driver, so we have to
* setup the port data early.
*/
ret = alloc_port_data(ib_dev);
if (ret)
return ret;
pdata = &ib_dev->port_data[port];
spin_lock_irqsave(&pdata->netdev_lock, flags);
old_ndev = rcu_dereference_protected(
pdata->netdev, lockdep_is_held(&pdata->netdev_lock));
if (old_ndev == ndev) {
spin_unlock_irqrestore(&pdata->netdev_lock, flags);
return 0;
}
rcu_assign_pointer(pdata->netdev, ndev);
netdev_put(old_ndev, &pdata->netdev_tracker);
netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC);
spin_unlock_irqrestore(&pdata->netdev_lock, flags);
add_ndev_hash(pdata);
/* Make sure that the device is registered before we send events */
if (xa_load(&devices, ib_dev->index) != ib_dev)
return 0;
etype = ndev ? RDMA_NETDEV_ATTACH_EVENT : RDMA_NETDEV_DETACH_EVENT;
rdma_nl_notify_event(ib_dev, port, etype);
return 0;
}
EXPORT_SYMBOL(ib_device_set_netdev);
static void free_netdevs(struct ib_device *ib_dev)
{
unsigned long flags;
u32 port;
if (!ib_dev->port_data)
return;
rdma_for_each_port (ib_dev, port) {
struct ib_port_data *pdata = &ib_dev->port_data[port];
struct net_device *ndev;
spin_lock_irqsave(&pdata->netdev_lock, flags);
ndev = rcu_dereference_protected(
pdata->netdev, lockdep_is_held(&pdata->netdev_lock));
if (ndev) {
spin_lock(&ndev_hash_lock);
hash_del_rcu(&pdata->ndev_hash_link);
spin_unlock(&ndev_hash_lock);
/*
* If this is the last dev_put there is still a
* synchronize_rcu before the netdev is kfreed, so we
* can continue to rely on unlocked pointer
* comparisons after the put
*/
rcu_assign_pointer(pdata->netdev, NULL);
netdev_put(ndev, &pdata->netdev_tracker);
}
spin_unlock_irqrestore(&pdata->netdev_lock, flags);
}
}
struct net_device *ib_device_get_netdev(struct ib_device *ib_dev,
u32 port)
{
struct ib_port_data *pdata;
struct net_device *res;
if (!rdma_is_port_valid(ib_dev, port))
return NULL;
if (!ib_dev->port_data)
return NULL;
pdata = &ib_dev->port_data[port];
/*
* New drivers should use ib_device_set_netdev() not the legacy
* get_netdev().
*/
if (ib_dev->ops.get_netdev)
res = ib_dev->ops.get_netdev(ib_dev, port);
else {
spin_lock(&pdata->netdev_lock);
res = rcu_dereference_protected(
pdata->netdev, lockdep_is_held(&pdata->netdev_lock));
dev_hold(res);
spin_unlock(&pdata->netdev_lock);
}
return res;
}
EXPORT_SYMBOL(ib_device_get_netdev);
/**
* ib_query_netdev_port - Query the port number of a net_device
* associated with an ibdev
* @ibdev: IB device
* @ndev: Network device
* @port: IB port the net_device is connected to
*/
int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev,
u32 *port)
{
struct net_device *ib_ndev;
u32 port_num;
rdma_for_each_port(ibdev, port_num) {
ib_ndev = ib_device_get_netdev(ibdev, port_num);
if (ndev == ib_ndev) {
*port = port_num;
dev_put(ib_ndev);
return 0;
}
dev_put(ib_ndev);
}
return -ENOENT;
}
EXPORT_SYMBOL(ib_query_netdev_port);
/**
* ib_device_get_by_netdev - Find an IB device associated with a netdev
* @ndev: netdev to locate
* @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all)
*
* Find and hold an ib_device that is associated with a netdev via
* ib_device_set_netdev(). The caller must call ib_device_put() on the
* returned pointer.
*/
struct ib_device *ib_device_get_by_netdev(struct net_device *ndev,
enum rdma_driver_id driver_id)
{
struct ib_device *res = NULL;
struct ib_port_data *cur;
rcu_read_lock(); hash_for_each_possible_rcu (ndev_hash, cur, ndev_hash_link,
(uintptr_t)ndev) {
if (rcu_access_pointer(cur->netdev) == ndev && (driver_id == RDMA_DRIVER_UNKNOWN || cur->ib_dev->ops.driver_id == driver_id) && ib_device_try_get(cur->ib_dev)) { res = cur->ib_dev;
break;
}
}
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL(ib_device_get_by_netdev);
/**
* ib_enum_roce_netdev - enumerate all RoCE ports
* @ib_dev : IB device we want to query
* @filter: Should we call the callback?
* @filter_cookie: Cookie passed to filter
* @cb: Callback to call for each found RoCE ports
* @cookie: Cookie passed back to the callback
*
* Enumerates all of the physical RoCE ports of ib_dev
* which are related to netdevice and calls callback() on each
* device for which filter() function returns non zero.
*/
void ib_enum_roce_netdev(struct ib_device *ib_dev,
roce_netdev_filter filter,
void *filter_cookie,
roce_netdev_callback cb,
void *cookie)
{
u32 port;
rdma_for_each_port (ib_dev, port)
if (rdma_protocol_roce(ib_dev, port)) {
struct net_device *idev =
ib_device_get_netdev(ib_dev, port);
if (filter(ib_dev, port, idev, filter_cookie))
cb(ib_dev, port, idev, cookie);
dev_put(idev);
}
}
/**
* ib_enum_all_roce_netdevs - enumerate all RoCE devices
* @filter: Should we call the callback?
* @filter_cookie: Cookie passed to filter
* @cb: Callback to call for each found RoCE ports
* @cookie: Cookie passed back to the callback
*
* Enumerates all RoCE devices' physical ports which are related
* to netdevices and calls callback() on each device for which
* filter() function returns non zero.
*/
void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
void *filter_cookie,
roce_netdev_callback cb,
void *cookie)
{
struct ib_device *dev;
unsigned long index;
down_read(&devices_rwsem);
xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED)
ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie);
up_read(&devices_rwsem);
}
/*
* ib_enum_all_devs - enumerate all ib_devices
* @cb: Callback to call for each found ib_device
*
* Enumerates all ib_devices and calls callback() on each device.
*/
int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
struct netlink_callback *cb)
{
unsigned long index;
struct ib_device *dev;
unsigned int idx = 0;
int ret = 0;
down_read(&devices_rwsem);
xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
if (!rdma_dev_access_netns(dev, sock_net(skb->sk)))
continue;
ret = nldev_cb(dev, skb, cb, idx);
if (ret)
break;
idx++;
}
up_read(&devices_rwsem);
return ret;
}
/**
* ib_query_pkey - Get P_Key table entry
* @device:Device to query
* @port_num:Port number to query
* @index:P_Key table index to query
* @pkey:Returned P_Key
*
* ib_query_pkey() fetches the specified P_Key table entry.
*/
int ib_query_pkey(struct ib_device *device,
u32 port_num, u16 index, u16 *pkey)
{
if (!rdma_is_port_valid(device, port_num))
return -EINVAL;
if (!device->ops.query_pkey)
return -EOPNOTSUPP;
return device->ops.query_pkey(device, port_num, index, pkey);
}
EXPORT_SYMBOL(ib_query_pkey);
/**
* ib_modify_device - Change IB device attributes
* @device:Device to modify
* @device_modify_mask:Mask of attributes to change
* @device_modify:New attribute values
*
* ib_modify_device() changes a device's attributes as specified by
* the @device_modify_mask and @device_modify structure.
*/
int ib_modify_device(struct ib_device *device,
int device_modify_mask,
struct ib_device_modify *device_modify)
{
if (!device->ops.modify_device)
return -EOPNOTSUPP;
return device->ops.modify_device(device, device_modify_mask,
device_modify);
}
EXPORT_SYMBOL(ib_modify_device);
/**
* ib_modify_port - Modifies the attributes for the specified port.
* @device: The device to modify.
* @port_num: The number of the port to modify.
* @port_modify_mask: Mask used to specify which attributes of the port
* to change.
* @port_modify: New attribute values for the port.
*
* ib_modify_port() changes a port's attributes as specified by the
* @port_modify_mask and @port_modify structure.
*/
int ib_modify_port(struct ib_device *device,
u32 port_num, int port_modify_mask,
struct ib_port_modify *port_modify)
{
int rc;
if (!rdma_is_port_valid(device, port_num))
return -EINVAL;
if (device->ops.modify_port)
rc = device->ops.modify_port(device, port_num,
port_modify_mask,
port_modify);
else if (rdma_protocol_roce(device, port_num) &&
((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 ||
(port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0))
rc = 0;
else
rc = -EOPNOTSUPP;
return rc;
}
EXPORT_SYMBOL(ib_modify_port);
/**
* ib_find_gid - Returns the port number and GID table index where
* a specified GID value occurs. Its searches only for IB link layer.
* @device: The device to query.
* @gid: The GID value to search for.
* @port_num: The port number of the device where the GID value was found.
* @index: The index into the GID table where the GID was found. This
* parameter may be NULL.
*/
int ib_find_gid(struct ib_device *device, union ib_gid *gid,
u32 *port_num, u16 *index)
{
union ib_gid tmp_gid;
u32 port;
int ret, i;
rdma_for_each_port (device, port) {
if (!rdma_protocol_ib(device, port))
continue;
for (i = 0; i < device->port_data[port].immutable.gid_tbl_len;
++i) {
ret = rdma_query_gid(device, port, i, &tmp_gid);
if (ret)
continue;
if (!memcmp(&tmp_gid, gid, sizeof *gid)) {
*port_num = port;
if (index)
*index = i;
return 0;
}
}
}
return -ENOENT;
}
EXPORT_SYMBOL(ib_find_gid);
/**
* ib_find_pkey - Returns the PKey table index where a specified
* PKey value occurs.
* @device: The device to query.
* @port_num: The port number of the device to search for the PKey.
* @pkey: The PKey value to search for.
* @index: The index into the PKey table where the PKey was found.
*/
int ib_find_pkey(struct ib_device *device,
u32 port_num, u16 pkey, u16 *index)
{
int ret, i;
u16 tmp_pkey;
int partial_ix = -1;
for (i = 0; i < device->port_data[port_num].immutable.pkey_tbl_len;
++i) {
ret = ib_query_pkey(device, port_num, i, &tmp_pkey);
if (ret)
return ret;
if ((pkey & 0x7fff) == (tmp_pkey & 0x7fff)) {
/* if there is full-member pkey take it.*/
if (tmp_pkey & 0x8000) {
*index = i;
return 0;
}
if (partial_ix < 0)
partial_ix = i;
}
}
/*no full-member, if exists take the limited*/
if (partial_ix >= 0) {
*index = partial_ix;
return 0;
}
return -ENOENT;
}
EXPORT_SYMBOL(ib_find_pkey);
/**
* ib_get_net_dev_by_params() - Return the appropriate net_dev
* for a received CM request
* @dev: An RDMA device on which the request has been received.
* @port: Port number on the RDMA device.
* @pkey: The Pkey the request came on.
* @gid: A GID that the net_dev uses to communicate.
* @addr: Contains the IP address that the request specified as its
* destination.
*
*/
struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
u32 port,
u16 pkey,
const union ib_gid *gid,
const struct sockaddr *addr)
{
struct net_device *net_dev = NULL;
unsigned long index;
void *client_data;
if (!rdma_protocol_ib(dev, port))
return NULL;
/*
* Holding the read side guarantees that the client will not become
* unregistered while we are calling get_net_dev_by_params()
*/
down_read(&dev->client_data_rwsem);
xan_for_each_marked (&dev->client_data, index, client_data,
CLIENT_DATA_REGISTERED) {
struct ib_client *client = xa_load(&clients, index);
if (!client || !client->get_net_dev_by_params)
continue;
net_dev = client->get_net_dev_by_params(dev, port, pkey, gid,
addr, client_data);
if (net_dev)
break;
}
up_read(&dev->client_data_rwsem);
return net_dev;
}
EXPORT_SYMBOL(ib_get_net_dev_by_params);
void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
{
struct ib_device_ops *dev_ops = &dev->ops;
#define SET_DEVICE_OP(ptr, name) \
do { \
if (ops->name) \
if (!((ptr)->name)) \
(ptr)->name = ops->name; \
} while (0)
#define SET_OBJ_SIZE(ptr, name) SET_DEVICE_OP(ptr, size_##name)
if (ops->driver_id != RDMA_DRIVER_UNKNOWN) {
WARN_ON(dev_ops->driver_id != RDMA_DRIVER_UNKNOWN &&
dev_ops->driver_id != ops->driver_id);
dev_ops->driver_id = ops->driver_id;
}
if (ops->owner) {
WARN_ON(dev_ops->owner && dev_ops->owner != ops->owner);
dev_ops->owner = ops->owner;
}
if (ops->uverbs_abi_ver)
dev_ops->uverbs_abi_ver = ops->uverbs_abi_ver;
dev_ops->uverbs_no_driver_id_binding |=
ops->uverbs_no_driver_id_binding;
SET_DEVICE_OP(dev_ops, add_gid);
SET_DEVICE_OP(dev_ops, add_sub_dev);
SET_DEVICE_OP(dev_ops, advise_mr);
SET_DEVICE_OP(dev_ops, alloc_dm);
SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
SET_DEVICE_OP(dev_ops, alloc_hw_port_stats);
SET_DEVICE_OP(dev_ops, alloc_mr);
SET_DEVICE_OP(dev_ops, alloc_mr_integrity);
SET_DEVICE_OP(dev_ops, alloc_mw);
SET_DEVICE_OP(dev_ops, alloc_pd);
SET_DEVICE_OP(dev_ops, alloc_rdma_netdev);
SET_DEVICE_OP(dev_ops, alloc_ucontext);
SET_DEVICE_OP(dev_ops, alloc_xrcd);
SET_DEVICE_OP(dev_ops, attach_mcast);
SET_DEVICE_OP(dev_ops, check_mr_status);
SET_DEVICE_OP(dev_ops, counter_alloc_stats);
SET_DEVICE_OP(dev_ops, counter_bind_qp);
SET_DEVICE_OP(dev_ops, counter_dealloc);
SET_DEVICE_OP(dev_ops, counter_init);
SET_DEVICE_OP(dev_ops, counter_unbind_qp);
SET_DEVICE_OP(dev_ops, counter_update_stats);
SET_DEVICE_OP(dev_ops, create_ah);
SET_DEVICE_OP(dev_ops, create_counters);
SET_DEVICE_OP(dev_ops, create_cq);
SET_DEVICE_OP(dev_ops, create_flow);
SET_DEVICE_OP(dev_ops, create_qp);
SET_DEVICE_OP(dev_ops, create_rwq_ind_table);
SET_DEVICE_OP(dev_ops, create_srq);
SET_DEVICE_OP(dev_ops, create_user_ah);
SET_DEVICE_OP(dev_ops, create_wq);
SET_DEVICE_OP(dev_ops, dealloc_dm);
SET_DEVICE_OP(dev_ops, dealloc_driver);
SET_DEVICE_OP(dev_ops, dealloc_mw);
SET_DEVICE_OP(dev_ops, dealloc_pd);
SET_DEVICE_OP(dev_ops, dealloc_ucontext);
SET_DEVICE_OP(dev_ops, dealloc_xrcd);
SET_DEVICE_OP(dev_ops, del_gid);
SET_DEVICE_OP(dev_ops, del_sub_dev);
SET_DEVICE_OP(dev_ops, dereg_mr);
SET_DEVICE_OP(dev_ops, destroy_ah);
SET_DEVICE_OP(dev_ops, destroy_counters);
SET_DEVICE_OP(dev_ops, destroy_cq);
SET_DEVICE_OP(dev_ops, destroy_flow);
SET_DEVICE_OP(dev_ops, destroy_flow_action);
SET_DEVICE_OP(dev_ops, destroy_qp);
SET_DEVICE_OP(dev_ops, destroy_rwq_ind_table);
SET_DEVICE_OP(dev_ops, destroy_srq);
SET_DEVICE_OP(dev_ops, destroy_wq);
SET_DEVICE_OP(dev_ops, device_group);
SET_DEVICE_OP(dev_ops, detach_mcast);
SET_DEVICE_OP(dev_ops, disassociate_ucontext);
SET_DEVICE_OP(dev_ops, drain_rq);
SET_DEVICE_OP(dev_ops, drain_sq);
SET_DEVICE_OP(dev_ops, enable_driver);
SET_DEVICE_OP(dev_ops, fill_res_cm_id_entry);
SET_DEVICE_OP(dev_ops, fill_res_cq_entry);
SET_DEVICE_OP(dev_ops, fill_res_cq_entry_raw);
SET_DEVICE_OP(dev_ops, fill_res_mr_entry);
SET_DEVICE_OP(dev_ops, fill_res_mr_entry_raw);
SET_DEVICE_OP(dev_ops, fill_res_qp_entry);
SET_DEVICE_OP(dev_ops, fill_res_qp_entry_raw);
SET_DEVICE_OP(dev_ops, fill_res_srq_entry);
SET_DEVICE_OP(dev_ops, fill_res_srq_entry_raw);
SET_DEVICE_OP(dev_ops, fill_stat_mr_entry);
SET_DEVICE_OP(dev_ops, get_dev_fw_str);
SET_DEVICE_OP(dev_ops, get_dma_mr);
SET_DEVICE_OP(dev_ops, get_hw_stats);
SET_DEVICE_OP(dev_ops, get_link_layer);
SET_DEVICE_OP(dev_ops, get_netdev);
SET_DEVICE_OP(dev_ops, get_numa_node);
SET_DEVICE_OP(dev_ops, get_port_immutable);
SET_DEVICE_OP(dev_ops, get_vector_affinity);
SET_DEVICE_OP(dev_ops, get_vf_config);
SET_DEVICE_OP(dev_ops, get_vf_guid);
SET_DEVICE_OP(dev_ops, get_vf_stats);
SET_DEVICE_OP(dev_ops, iw_accept);
SET_DEVICE_OP(dev_ops, iw_add_ref);
SET_DEVICE_OP(dev_ops, iw_connect);
SET_DEVICE_OP(dev_ops, iw_create_listen);
SET_DEVICE_OP(dev_ops, iw_destroy_listen);
SET_DEVICE_OP(dev_ops, iw_get_qp);
SET_DEVICE_OP(dev_ops, iw_reject);
SET_DEVICE_OP(dev_ops, iw_rem_ref);
SET_DEVICE_OP(dev_ops, map_mr_sg);
SET_DEVICE_OP(dev_ops, map_mr_sg_pi);
SET_DEVICE_OP(dev_ops, mmap);
SET_DEVICE_OP(dev_ops, mmap_free);
SET_DEVICE_OP(dev_ops, modify_ah);
SET_DEVICE_OP(dev_ops, modify_cq);
SET_DEVICE_OP(dev_ops, modify_device);
SET_DEVICE_OP(dev_ops, modify_hw_stat);
SET_DEVICE_OP(dev_ops, modify_port);
SET_DEVICE_OP(dev_ops, modify_qp);
SET_DEVICE_OP(dev_ops, modify_srq);
SET_DEVICE_OP(dev_ops, modify_wq);
SET_DEVICE_OP(dev_ops, peek_cq);
SET_DEVICE_OP(dev_ops, poll_cq);
SET_DEVICE_OP(dev_ops, port_groups);
SET_DEVICE_OP(dev_ops, post_recv);
SET_DEVICE_OP(dev_ops, post_send);
SET_DEVICE_OP(dev_ops, post_srq_recv);
SET_DEVICE_OP(dev_ops, process_mad);
SET_DEVICE_OP(dev_ops, query_ah);
SET_DEVICE_OP(dev_ops, query_device);
SET_DEVICE_OP(dev_ops, query_gid);
SET_DEVICE_OP(dev_ops, query_pkey);
SET_DEVICE_OP(dev_ops, query_port);
SET_DEVICE_OP(dev_ops, query_qp);
SET_DEVICE_OP(dev_ops, query_srq);
SET_DEVICE_OP(dev_ops, query_ucontext);
SET_DEVICE_OP(dev_ops, rdma_netdev_get_params);
SET_DEVICE_OP(dev_ops, read_counters);
SET_DEVICE_OP(dev_ops, reg_dm_mr);
SET_DEVICE_OP(dev_ops, reg_user_mr);
SET_DEVICE_OP(dev_ops, reg_user_mr_dmabuf);
SET_DEVICE_OP(dev_ops, req_notify_cq);
SET_DEVICE_OP(dev_ops, rereg_user_mr);
SET_DEVICE_OP(dev_ops, resize_cq);
SET_DEVICE_OP(dev_ops, set_vf_guid);
SET_DEVICE_OP(dev_ops, set_vf_link_state);
SET_DEVICE_OP(dev_ops, ufile_hw_cleanup);
SET_DEVICE_OP(dev_ops, report_port_event);
SET_OBJ_SIZE(dev_ops, ib_ah);
SET_OBJ_SIZE(dev_ops, ib_counters);
SET_OBJ_SIZE(dev_ops, ib_cq);
SET_OBJ_SIZE(dev_ops, ib_mw);
SET_OBJ_SIZE(dev_ops, ib_pd);
SET_OBJ_SIZE(dev_ops, ib_qp);
SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table);
SET_OBJ_SIZE(dev_ops, ib_srq);
SET_OBJ_SIZE(dev_ops, ib_ucontext);
SET_OBJ_SIZE(dev_ops, ib_xrcd);
SET_OBJ_SIZE(dev_ops, rdma_counter);
}
EXPORT_SYMBOL(ib_set_device_ops);
int ib_add_sub_device(struct ib_device *parent,
enum rdma_nl_dev_type type,
const char *name)
{
struct ib_device *sub;
int ret = 0;
if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev)
return -EOPNOTSUPP;
if (!ib_device_try_get(parent))
return -EINVAL;
sub = parent->ops.add_sub_dev(parent, type, name);
if (IS_ERR(sub)) {
ib_device_put(parent);
return PTR_ERR(sub);
}
sub->type = type;
sub->parent = parent;
mutex_lock(&parent->subdev_lock);
list_add_tail(&parent->subdev_list_head, &sub->subdev_list);
mutex_unlock(&parent->subdev_lock);
return ret;
}
EXPORT_SYMBOL(ib_add_sub_device);
int ib_del_sub_device_and_put(struct ib_device *sub)
{
struct ib_device *parent = sub->parent;
if (!parent)
return -EOPNOTSUPP;
mutex_lock(&parent->subdev_lock);
list_del(&sub->subdev_list);
mutex_unlock(&parent->subdev_lock);
ib_device_put(sub);
parent->ops.del_sub_dev(sub);
ib_device_put(parent);
return 0;
}
EXPORT_SYMBOL(ib_del_sub_device_and_put);
#ifdef CONFIG_INFINIBAND_VIRT_DMA
int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents)
{
struct scatterlist *s;
int i;
for_each_sg(sg, s, nents, i) {
sg_dma_address(s) = (uintptr_t)sg_virt(s);
sg_dma_len(s) = s->length;
}
return nents;
}
EXPORT_SYMBOL(ib_dma_virt_map_sg);
#endif /* CONFIG_INFINIBAND_VIRT_DMA */
static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = {
[RDMA_NL_LS_OP_RESOLVE] = {
.doit = ib_nl_handle_resolve_resp,
.flags = RDMA_NL_ADMIN_PERM,
},
[RDMA_NL_LS_OP_SET_TIMEOUT] = {
.doit = ib_nl_handle_set_timeout,
.flags = RDMA_NL_ADMIN_PERM,
},
[RDMA_NL_LS_OP_IP_RESOLVE] = {
.doit = ib_nl_handle_ip_res_resp,
.flags = RDMA_NL_ADMIN_PERM,
},
};
void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev)
{
enum ib_port_state curr_state;
struct ib_event ibevent = {};
u32 port;
if (ib_query_netdev_port(ibdev, ndev, &port))
return;
curr_state = ib_get_curr_port_state(ndev);
write_lock_irq(&ibdev->cache_lock);
if (ibdev->port_data[port].cache.last_port_state == curr_state) {
write_unlock_irq(&ibdev->cache_lock);
return;
}
ibdev->port_data[port].cache.last_port_state = curr_state;
write_unlock_irq(&ibdev->cache_lock);
ibevent.event = (curr_state == IB_PORT_DOWN) ?
IB_EVENT_PORT_ERR : IB_EVENT_PORT_ACTIVE;
ibevent.device = ibdev;
ibevent.element.port_num = port;
ib_dispatch_event(&ibevent);
}
EXPORT_SYMBOL(ib_dispatch_port_state_event);
static void handle_port_event(struct net_device *ndev, unsigned long event)
{
struct ib_device *ibdev;
/* Currently, link events in bonding scenarios are still
* reported by drivers that support bonding.
*/
if (netif_is_lag_master(ndev) || netif_is_lag_port(ndev))
return;
ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN);
if (!ibdev)
return;
if (ibdev->ops.report_port_event) {
ibdev->ops.report_port_event(ibdev, ndev, event);
goto put_ibdev;
}
ib_dispatch_port_state_event(ibdev, ndev);
put_ibdev:
ib_device_put(ibdev);
};
static int ib_netdevice_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
struct ib_device *ibdev;
u32 port;
switch (event) {
case NETDEV_CHANGENAME:
ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_UNKNOWN);
if (!ibdev)
return NOTIFY_DONE;
if (ib_query_netdev_port(ibdev, ndev, &port)) {
ib_device_put(ibdev);
break;
}
rdma_nl_notify_event(ibdev, port, RDMA_NETDEV_RENAME_EVENT);
ib_device_put(ibdev);
break;
case NETDEV_UP:
case NETDEV_CHANGE:
case NETDEV_DOWN:
handle_port_event(ndev, event);
break;
default:
break;
}
return NOTIFY_DONE;
}
static struct notifier_block nb_netdevice = {
.notifier_call = ib_netdevice_event,
};
static int __init ib_core_init(void)
{
int ret = -ENOMEM;
ib_wq = alloc_workqueue("infiniband", 0, 0);
if (!ib_wq)
return -ENOMEM;
ib_unreg_wq = alloc_workqueue("ib-unreg-wq", WQ_UNBOUND,
WQ_UNBOUND_MAX_ACTIVE);
if (!ib_unreg_wq)
goto err;
ib_comp_wq = alloc_workqueue("ib-comp-wq",
WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
if (!ib_comp_wq)
goto err_unbound;
ib_comp_unbound_wq =
alloc_workqueue("ib-comp-unb-wq",
WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM |
WQ_SYSFS, WQ_UNBOUND_MAX_ACTIVE);
if (!ib_comp_unbound_wq)
goto err_comp;
ret = class_register(&ib_class);
if (ret) {
pr_warn("Couldn't create InfiniBand device class\n");
goto err_comp_unbound;
}
rdma_nl_init();
ret = addr_init();
if (ret) {
pr_warn("Couldn't init IB address resolution\n");
goto err_ibnl;
}
ret = ib_mad_init();
if (ret) {
pr_warn("Couldn't init IB MAD\n");
goto err_addr;
}
ret = ib_sa_init();
if (ret) {
pr_warn("Couldn't init SA\n");
goto err_mad;
}
ret = register_blocking_lsm_notifier(&ibdev_lsm_nb);
if (ret) {
pr_warn("Couldn't register LSM notifier. ret %d\n", ret);
goto err_sa;
}
ret = register_pernet_device(&rdma_dev_net_ops);
if (ret) {
pr_warn("Couldn't init compat dev. ret %d\n", ret);
goto err_compat;
}
nldev_init();
rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
ret = roce_gid_mgmt_init();
if (ret) {
pr_warn("Couldn't init RoCE GID management\n");
goto err_parent;
}
register_netdevice_notifier(&nb_netdevice);
return 0;
err_parent:
rdma_nl_unregister(RDMA_NL_LS);
nldev_exit();
unregister_pernet_device(&rdma_dev_net_ops);
err_compat:
unregister_blocking_lsm_notifier(&ibdev_lsm_nb);
err_sa:
ib_sa_cleanup();
err_mad:
ib_mad_cleanup();
err_addr:
addr_cleanup();
err_ibnl:
class_unregister(&ib_class);
err_comp_unbound:
destroy_workqueue(ib_comp_unbound_wq);
err_comp:
destroy_workqueue(ib_comp_wq);
err_unbound:
destroy_workqueue(ib_unreg_wq);
err:
destroy_workqueue(ib_wq);
return ret;
}
static void __exit ib_core_cleanup(void)
{
unregister_netdevice_notifier(&nb_netdevice);
roce_gid_mgmt_cleanup();
rdma_nl_unregister(RDMA_NL_LS);
nldev_exit();
unregister_pernet_device(&rdma_dev_net_ops);
unregister_blocking_lsm_notifier(&ibdev_lsm_nb);
ib_sa_cleanup();
ib_mad_cleanup();
addr_cleanup();
rdma_nl_exit();
class_unregister(&ib_class);
destroy_workqueue(ib_comp_unbound_wq);
destroy_workqueue(ib_comp_wq);
/* Make sure that any pending umem accounting work is done. */
destroy_workqueue(ib_wq);
destroy_workqueue(ib_unreg_wq);
WARN_ON(!xa_empty(&clients));
WARN_ON(!xa_empty(&devices));
}
MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4);
/* ib core relies on netdev stack to first register net_ns_type_operations
* ns kobject type before ib_core initialization.
*/
fs_initcall(ib_core_init);
module_exit(ib_core_cleanup);
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/truncate.c - code for taking down pages from address_spaces
*
* Copyright (C) 2002, Linus Torvalds
*
* 10Sep2002 Andrew Morton
* Initial version.
*/
#include <linux/kernel.h>
#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
#include "internal.h"
static void clear_shadow_entries(struct address_space *mapping,
unsigned long start, unsigned long max)
{
XA_STATE(xas, &mapping->i_pages, start);
struct folio *folio;
/* Handled by shmem itself, or for DAX we do nothing. */
if (shmem_mapping(mapping) || dax_mapping(mapping))
return;
xas_set_update(&xas, workingset_update_node);
spin_lock(&mapping->host->i_lock);
xas_lock_irq(&xas);
/* Clear all shadow entries from start to max */
xas_for_each(&xas, folio, max) {
if (xa_is_value(folio))
xas_store(&xas, NULL);
}
xas_unlock_irq(&xas);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
}
/*
* Unconditionally remove exceptional entries. Usually called from truncate
* path. Note that the folio_batch may be altered by this function by removing
* exceptional entries similar to what folio_batch_remove_exceptionals() does.
* Please note that indices[] has entries in ascending order as guaranteed by
* either find_get_entries() or find_lock_entries().
*/
static void truncate_folio_batch_exceptionals(struct address_space *mapping,
struct folio_batch *fbatch, pgoff_t *indices)
{
XA_STATE(xas, &mapping->i_pages, indices[0]);
int nr = folio_batch_count(fbatch);
struct folio *folio;
int i, j;
/* Handled by shmem itself */
if (shmem_mapping(mapping))
return;
for (j = 0; j < nr; j++)
if (xa_is_value(fbatch->folios[j]))
break;
if (j == nr)
return;
if (dax_mapping(mapping)) {
for (i = j; i < nr; i++) {
if (xa_is_value(fbatch->folios[i])) {
/*
* File systems should already have called
* dax_break_layout_entry() to remove all DAX
* entries while holding a lock to prevent
* establishing new entries. Therefore we
* shouldn't find any here.
*/
WARN_ON_ONCE(1);
/*
* Delete the mapping so truncate_pagecache()
* doesn't loop forever.
*/
dax_delete_mapping_entry(mapping, indices[i]);
}
}
goto out;
}
xas_set(&xas, indices[j]);
xas_set_update(&xas, workingset_update_node);
spin_lock(&mapping->host->i_lock);
xas_lock_irq(&xas);
xas_for_each(&xas, folio, indices[nr-1]) {
if (xa_is_value(folio))
xas_store(&xas, NULL);
}
xas_unlock_irq(&xas);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
out:
folio_batch_remove_exceptionals(fbatch);
}
/**
* folio_invalidate - Invalidate part or all of a folio.
* @folio: The folio which is affected.
* @offset: start of the range to invalidate
* @length: length of the range to invalidate
*
* folio_invalidate() is called when all or part of the folio has become
* invalidated by a truncate operation.
*
* folio_invalidate() does not have to release all buffers, but it must
* ensure that no dirty buffer is left outside @offset and that no I/O
* is underway against any of the blocks which are outside the truncation
* point. Because the caller is about to free (and possibly reuse) those
* blocks on-disk.
*/
void folio_invalidate(struct folio *folio, size_t offset, size_t length)
{
const struct address_space_operations *aops = folio->mapping->a_ops;
if (aops->invalidate_folio)
aops->invalidate_folio(folio, offset, length);
}
EXPORT_SYMBOL_GPL(folio_invalidate);
/*
* If truncate cannot remove the fs-private metadata from the page, the page
* becomes orphaned. It will be left on the LRU and may even be mapped into
* user pagetables if we're racing with filemap_fault().
*
* We need to bail out if page->mapping is no longer equal to the original
* mapping. This happens a) when the VM reclaimed the page while we waited on
* its lock, b) when a concurrent invalidate_mapping_pages got there first and
* c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
*/
static void truncate_cleanup_folio(struct folio *folio)
{ if (folio_mapped(folio)) unmap_mapping_folio(folio); if (folio_needs_release(folio)) folio_invalidate(folio, 0, folio_size(folio));
/*
* Some filesystems seem to re-dirty the page even after
* the VM has canceled the dirty bit (eg ext3 journaling).
* Hence dirty accounting check is placed after invalidation.
*/
folio_cancel_dirty(folio);
}
int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
{ if (folio->mapping != mapping)
return -EIO;
truncate_cleanup_folio(folio);
filemap_remove_folio(folio);
return 0;
}
/*
* Handle partial folios. The folio may be entirely within the
* range if a split has raced with us. If not, we zero the part of the
* folio that's within the [start, end] range, and then split the folio if
* it's large. split_page_range() will discard pages which now lie beyond
* i_size, and we rely on the caller to discard pages which lie within a
* newly created hole.
*
* Returns false if splitting failed so the caller can avoid
* discarding the entire folio which is stubbornly unsplit.
*/
bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
{
loff_t pos = folio_pos(folio);
unsigned int offset, length;
struct page *split_at, *split_at2;
if (pos < start)
offset = start - pos;
else
offset = 0;
length = folio_size(folio);
if (pos + length <= (u64)end)
length = length - offset;
else
length = end + 1 - pos - offset;
folio_wait_writeback(folio);
if (length == folio_size(folio)) {
truncate_inode_folio(folio->mapping, folio);
return true;
}
/*
* We may be zeroing pages we're about to discard, but it avoids
* doing a complex calculation here, and then doing the zeroing
* anyway if the page split fails.
*/
if (!mapping_inaccessible(folio->mapping))
folio_zero_range(folio, offset, length);
if (folio_needs_release(folio))
folio_invalidate(folio, offset, length);
if (!folio_test_large(folio))
return true;
split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE);
split_at2 = folio_page(folio,
PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE);
if (!try_folio_split(folio, split_at, NULL)) {
/*
* try to split at offset + length to make sure folios within
* the range can be dropped, especially to avoid memory waste
* for shmem truncate
*/
struct folio *folio2 = page_folio(split_at2);
if (!folio_try_get(folio2))
goto no_split;
if (!folio_test_large(folio2))
goto out;
if (!folio_trylock(folio2))
goto out;
/*
* make sure folio2 is large and does not change its mapping.
* Its split result does not matter here.
*/
if (folio_test_large(folio2) &&
folio2->mapping == folio->mapping)
try_folio_split(folio2, split_at2, NULL);
folio_unlock(folio2);
out:
folio_put(folio2);
no_split:
return true;
}
if (folio_test_dirty(folio))
return false;
truncate_inode_folio(folio->mapping, folio);
return true;
}
/*
* Used to get rid of pages on hardware memory corruption.
*/
int generic_error_remove_folio(struct address_space *mapping,
struct folio *folio)
{
if (!mapping)
return -EINVAL;
/*
* Only punch for normal data pages for now.
* Handling other types like directories would need more auditing.
*/
if (!S_ISREG(mapping->host->i_mode))
return -EIO;
return truncate_inode_folio(mapping, folio);
}
EXPORT_SYMBOL(generic_error_remove_folio);
/**
* mapping_evict_folio() - Remove an unused folio from the page-cache.
* @mapping: The mapping this folio belongs to.
* @folio: The folio to remove.
*
* Safely remove one folio from the page cache.
* It only drops clean, unused folios.
*
* Context: Folio must be locked.
* Return: The number of pages successfully removed.
*/
long mapping_evict_folio(struct address_space *mapping, struct folio *folio)
{
/* The page may have been truncated before it was locked */
if (!mapping)
return 0;
if (folio_test_dirty(folio) || folio_test_writeback(folio))
return 0;
/* The refcount will be elevated if any page in the folio is mapped */
if (folio_ref_count(folio) >
folio_nr_pages(folio) + folio_has_private(folio) + 1)
return 0;
if (!filemap_release_folio(folio, 0))
return 0;
return remove_mapping(mapping, folio);
}
/**
* truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
* @lend: offset to which to truncate (inclusive)
*
* Truncate the page cache, removing the pages that are between
* specified offsets (and zeroing out partial pages
* if lstart or lend + 1 is not page aligned).
*
* Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass
* will wait. This is to prevent as much IO as possible in the affected region.
* The first pass will remove most pages, so the search cost of the second pass
* is low.
*
* We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order.
*
* Note that since ->invalidate_folio() accepts range to invalidate
* truncate_inode_pages_range is able to handle cases where lend + 1 is not
* page aligned properly.
*/
void truncate_inode_pages_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
pgoff_t start; /* inclusive */
pgoff_t end; /* exclusive */
struct folio_batch fbatch;
pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index;
int i;
struct folio *folio;
bool same_folio;
if (mapping_empty(mapping))
return;
/*
* 'start' and 'end' always covers the range of pages to be fully
* truncated. Partial pages are covered with 'partial_start' at the
* start of the range and 'partial_end' at the end of the range.
* Note that 'end' is exclusive while 'lend' is inclusive.
*/
start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (lend == -1)
/*
* lend == -1 indicates end-of-file so we have to set 'end'
* to the highest possible pgoff_t and since the type is
* unsigned we're using -1.
*/
end = -1;
else
end = (lend + 1) >> PAGE_SHIFT;
folio_batch_init(&fbatch);
index = start;
while (index < end && find_lock_entries(mapping, &index, end - 1,
&fbatch, indices)) {
truncate_folio_batch_exceptionals(mapping, &fbatch, indices);
for (i = 0; i < folio_batch_count(&fbatch); i++)
truncate_cleanup_folio(fbatch.folios[i]);
delete_from_page_cache_batch(mapping, &fbatch);
for (i = 0; i < folio_batch_count(&fbatch); i++)
folio_unlock(fbatch.folios[i]);
folio_batch_release(&fbatch);
cond_resched();
}
same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0);
if (!IS_ERR(folio)) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio_next_index(folio);
if (same_folio)
end = folio->index;
}
folio_unlock(folio);
folio_put(folio);
folio = NULL;
}
if (!same_folio) {
folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT,
FGP_LOCK, 0);
if (!IS_ERR(folio)) { if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index;
folio_unlock(folio);
folio_put(folio);
}
}
index = start;
while (index < end) {
cond_resched();
if (!find_get_entries(mapping, &index, end - 1, &fbatch,
indices)) {
/* If all gone from start onwards, we're done */
if (index == start)
break;
/* Otherwise restart to make sure all gone */
index = start;
continue;
}
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
/* We rely upon deletion not changing page->index */
if (xa_is_value(folio))
continue;
folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio);
folio_wait_writeback(folio);
truncate_inode_folio(mapping, folio);
folio_unlock(folio);
}
truncate_folio_batch_exceptionals(mapping, &fbatch, indices);
folio_batch_release(&fbatch);
}
}
EXPORT_SYMBOL(truncate_inode_pages_range);
/**
* truncate_inode_pages - truncate *all* the pages from an offset
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
*
* Called under (and serialised by) inode->i_rwsem and
* mapping->invalidate_lock.
*
* Note: When this function returns, there can be a page in the process of
* deletion (inside __filemap_remove_folio()) in the specified range. Thus
* mapping->nrpages can be non-zero when this function returns even after
* truncation of the whole mapping.
*/
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
}
EXPORT_SYMBOL(truncate_inode_pages);
/**
* truncate_inode_pages_final - truncate *all* pages before inode dies
* @mapping: mapping to truncate
*
* Called under (and serialized by) inode->i_rwsem.
*
* Filesystems have to use this in the .evict_inode path to inform the
* VM that this is the final truncate and the inode is going away.
*/
void truncate_inode_pages_final(struct address_space *mapping)
{
/*
* Page reclaim can not participate in regular inode lifetime
* management (can't call iput()) and thus can race with the
* inode teardown. Tell it when the address space is exiting,
* so that it does not install eviction information after the
* final truncate has begun.
*/
mapping_set_exiting(mapping); if (!mapping_empty(mapping)) {
/*
* As truncation uses a lockless tree lookup, cycle
* the tree lock to make sure any ongoing tree
* modification that does not see AS_EXITING is
* completed before starting the final truncate.
*/
xa_lock_irq(&mapping->i_pages);
xa_unlock_irq(&mapping->i_pages);
}
truncate_inode_pages(mapping, 0);
}
EXPORT_SYMBOL(truncate_inode_pages_final);
/**
* mapping_try_invalidate - Invalidate all the evictable folios of one inode
* @mapping: the address_space which holds the folios to invalidate
* @start: the offset 'from' which to invalidate
* @end: the offset 'to' which to invalidate (inclusive)
* @nr_failed: How many folio invalidations failed
*
* This function is similar to invalidate_mapping_pages(), except that it
* returns the number of folios which could not be evicted in @nr_failed.
*/
unsigned long mapping_try_invalidate(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_failed)
{
pgoff_t indices[PAGEVEC_SIZE];
struct folio_batch fbatch;
pgoff_t index = start;
unsigned long ret;
unsigned long count = 0;
int i;
folio_batch_init(&fbatch);
while (find_lock_entries(mapping, &index, end, &fbatch, indices)) {
bool xa_has_values = false;
int nr = folio_batch_count(&fbatch);
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
/* We rely upon deletion not changing folio->index */
if (xa_is_value(folio)) {
xa_has_values = true;
count++;
continue;
}
ret = mapping_evict_folio(mapping, folio);
folio_unlock(folio);
/*
* Invalidation is a hint that the folio is no longer
* of interest and try to speed up its reclaim.
*/
if (!ret) {
deactivate_file_folio(folio);
/* Likely in the lru cache of a remote CPU */
if (nr_failed)
(*nr_failed)++;
}
count += ret;
}
if (xa_has_values)
clear_shadow_entries(mapping, indices[0], indices[nr-1]);
folio_batch_remove_exceptionals(&fbatch);
folio_batch_release(&fbatch);
cond_resched();
}
return count;
}
/**
* invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode
* @mapping: the address_space which holds the cache to invalidate
* @start: the offset 'from' which to invalidate
* @end: the offset 'to' which to invalidate (inclusive)
*
* This function removes pages that are clean, unmapped and unlocked,
* as well as shadow entries. It will not block on IO activity.
*
* If you want to remove all the pages of one inode, regardless of
* their use and writeback state, use truncate_inode_pages().
*
* Return: The number of indices that had their contents invalidated
*/
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
return mapping_try_invalidate(mapping, start, end, NULL);
}
EXPORT_SYMBOL(invalidate_mapping_pages);
static int folio_launder(struct address_space *mapping, struct folio *folio)
{
if (!folio_test_dirty(folio))
return 0;
if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
return 0;
return mapping->a_ops->launder_folio(folio);
}
/*
* This is like mapping_evict_folio(), except it ignores the folio's
* refcount. We do this because invalidate_inode_pages2() needs stronger
* invalidation guarantees, and cannot afford to leave folios behind because
* shrink_folio_list() has a temp ref on them, or because they're transiently
* sitting in the folio_add_lru() caches.
*/
int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
gfp_t gfp)
{
int ret;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (folio_mapped(folio))
unmap_mapping_folio(folio);
BUG_ON(folio_mapped(folio));
ret = folio_launder(mapping, folio);
if (ret)
return ret;
if (folio->mapping != mapping)
return -EBUSY;
if (!filemap_release_folio(folio, gfp))
return -EBUSY;
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
if (folio_test_dirty(folio))
goto failed;
BUG_ON(folio_has_private(folio));
__filemap_remove_folio(folio, NULL);
xa_unlock_irq(&mapping->i_pages);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
filemap_free_folio(mapping, folio);
return 1;
failed:
xa_unlock_irq(&mapping->i_pages);
spin_unlock(&mapping->host->i_lock);
return -EBUSY;
}
/**
* invalidate_inode_pages2_range - remove range of pages from an address_space
* @mapping: the address_space
* @start: the page offset 'from' which to invalidate
* @end: the page offset 'to' which to invalidate (inclusive)
*
* Any pages which are found to be mapped into pagetables are unmapped prior to
* invalidation.
*
* Return: -EBUSY if any pages could not be invalidated.
*/
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
pgoff_t indices[PAGEVEC_SIZE];
struct folio_batch fbatch;
pgoff_t index;
int i;
int ret = 0;
int ret2 = 0;
int did_range_unmap = 0;
if (mapping_empty(mapping))
return 0;
folio_batch_init(&fbatch);
index = start;
while (find_get_entries(mapping, &index, end, &fbatch, indices)) {
bool xa_has_values = false;
int nr = folio_batch_count(&fbatch);
for (i = 0; i < nr; i++) {
struct folio *folio = fbatch.folios[i];
/* We rely upon deletion not changing folio->index */
if (xa_is_value(folio)) {
xa_has_values = true;
if (dax_mapping(mapping) &&
!dax_invalidate_mapping_entry_sync(mapping, indices[i]))
ret = -EBUSY;
continue;
}
if (!did_range_unmap && folio_mapped(folio)) {
/*
* If folio is mapped, before taking its lock,
* zap the rest of the file in one hit.
*/
unmap_mapping_pages(mapping, indices[i],
(1 + end - indices[i]), false);
did_range_unmap = 1;
}
folio_lock(folio);
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
continue;
}
VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio);
folio_wait_writeback(folio);
ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL);
if (ret2 < 0)
ret = ret2;
folio_unlock(folio);
}
if (xa_has_values)
clear_shadow_entries(mapping, indices[0], indices[nr-1]);
folio_batch_remove_exceptionals(&fbatch);
folio_batch_release(&fbatch);
cond_resched();
}
/*
* For DAX we invalidate page tables after invalidating page cache. We
* could invalidate page tables while invalidating each entry however
* that would be expensive. And doing range unmapping before doesn't
* work as we have no cheap way to find whether page cache entry didn't
* get remapped later.
*/
if (dax_mapping(mapping)) {
unmap_mapping_pages(mapping, start, end - start + 1, false);
}
return ret;
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
/**
* invalidate_inode_pages2 - remove all pages from an address_space
* @mapping: the address_space
*
* Any pages which are found to be mapped into pagetables are unmapped prior to
* invalidation.
*
* Return: -EBUSY if any pages could not be invalidated.
*/
int invalidate_inode_pages2(struct address_space *mapping)
{
return invalidate_inode_pages2_range(mapping, 0, -1);
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
/**
* truncate_pagecache - unmap and remove pagecache that has been truncated
* @inode: inode
* @newsize: new file size
*
* inode's new i_size must already be written before truncate_pagecache
* is called.
*
* This function should typically be called before the filesystem
* releases resources associated with the freed range (eg. deallocates
* blocks). This way, pagecache will always stay logically coherent
* with on-disk format, and the filesystem would not have to deal with
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
void truncate_pagecache(struct inode *inode, loff_t newsize)
{
struct address_space *mapping = inode->i_mapping;
loff_t holebegin = round_up(newsize, PAGE_SIZE);
/*
* unmap_mapping_range is called twice, first simply for
* efficiency so that truncate_inode_pages does fewer
* single-page unmaps. However after this first call, and
* before truncate_inode_pages finishes, it is possible for
* private pages to be COWed, which remain after
* truncate_inode_pages finishes, hence the second
* unmap_mapping_range call must be made for correctness.
*/
unmap_mapping_range(mapping, holebegin, 0, 1);
truncate_inode_pages(mapping, newsize);
unmap_mapping_range(mapping, holebegin, 0, 1);
}
EXPORT_SYMBOL(truncate_pagecache);
/**
* truncate_setsize - update inode and pagecache for a new file size
* @inode: inode
* @newsize: new file size
*
* truncate_setsize updates i_size and performs pagecache truncation (if
* necessary) to @newsize. It will be typically be called from the filesystem's
* setattr function when ATTR_SIZE is passed in.
*
* Must be called with a lock serializing truncates and writes (generally
* i_rwsem but e.g. xfs uses a different lock) and before all filesystem
* specific block truncation has been performed.
*/
void truncate_setsize(struct inode *inode, loff_t newsize)
{
loff_t oldsize = inode->i_size;
i_size_write(inode, newsize);
if (newsize > oldsize)
pagecache_isize_extended(inode, oldsize, newsize);
truncate_pagecache(inode, newsize);
}
EXPORT_SYMBOL(truncate_setsize);
/**
* pagecache_isize_extended - update pagecache after extension of i_size
* @inode: inode for which i_size was extended
* @from: original inode size
* @to: new inode size
*
* Handle extension of inode size either caused by extending truncate or
* by write starting after current i_size. We mark the page straddling
* current i_size RO so that page_mkwrite() is called on the first
* write access to the page. The filesystem will update its per-block
* information before user writes to the page via mmap after the i_size
* has been changed.
*
* The function must be called after i_size is updated so that page fault
* coming after we unlock the folio will already see the new i_size.
* The function must be called while we still hold i_rwsem - this not only
* makes sure i_size is stable but also that userspace cannot observe new
* i_size value before we are prepared to store mmap writes at new inode size.
*/
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
{
int bsize = i_blocksize(inode);
loff_t rounded_from;
struct folio *folio;
WARN_ON(to > inode->i_size);
if (from >= to || bsize >= PAGE_SIZE)
return;
/* Page straddling @from will not have any hole block created? */
rounded_from = round_up(from, bsize);
if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1)))
return;
folio = filemap_lock_folio(inode->i_mapping, from / PAGE_SIZE);
/* Folio not cached? Nothing to do */
if (IS_ERR(folio))
return;
/*
* See folio_clear_dirty_for_io() for details why folio_mark_dirty()
* is needed.
*/
if (folio_mkclean(folio))
folio_mark_dirty(folio);
/*
* The post-eof range of the folio must be zeroed before it is exposed
* to the file. Writeback normally does this, but since i_size has been
* increased we handle it here.
*/
if (folio_test_dirty(folio)) {
unsigned int offset, end;
offset = from - folio_pos(folio);
end = min_t(unsigned int, to - folio_pos(folio),
folio_size(folio));
folio_zero_segment(folio, offset, end);
}
folio_unlock(folio);
folio_put(folio);
}
EXPORT_SYMBOL(pagecache_isize_extended);
/**
* truncate_pagecache_range - unmap and remove pagecache that is hole-punched
* @inode: inode
* @lstart: offset of beginning of hole
* @lend: offset of last byte of hole
*
* This function should typically be called before the filesystem
* releases resources associated with the freed range (eg. deallocates
* blocks). This way, pagecache will always stay logically coherent
* with on-disk format, and the filesystem would not have to deal with
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
{
struct address_space *mapping = inode->i_mapping;
loff_t unmap_start = round_up(lstart, PAGE_SIZE);
loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
/*
* This rounding is currently just for example: unmap_mapping_range
* expands its hole outwards, whereas we want it to contract the hole
* inwards. However, existing callers of truncate_pagecache_range are
* doing their own page rounding first. Note that unmap_mapping_range
* allows holelen 0 for all, and we allow lend -1 for end of file.
*/
/*
* Unlike in truncate_pagecache, unmap_mapping_range is called only
* once (before truncating pagecache), and without "even_cows" flag:
* hole-punching should not remove private COWed pages from the hole.
*/
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
truncate_inode_pages_range(mapping, lstart, lend);
}
EXPORT_SYMBOL(truncate_pagecache_range);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Handle detection, reporting and mitigation of Spectre v1, v2, v3a and v4, as
* detailed at:
*
* https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
*
* This code was originally written hastily under an awful lot of stress and so
* aspects of it are somewhat hacky. Unfortunately, changing anything in here
* instantly makes me feel ill. Thanks, Jann. Thann.
*
* Copyright (C) 2018 ARM Ltd, All Rights Reserved.
* Copyright (C) 2020 Google LLC
*
* "If there's something strange in your neighbourhood, who you gonna call?"
*
* Authors: Will Deacon <will@kernel.org> and Marc Zyngier <maz@kernel.org>
*/
#include <linux/arm-smccc.h>
#include <linux/bpf.h>
#include <linux/cpu.h>
#include <linux/device.h>
#include <linux/nospec.h>
#include <linux/prctl.h>
#include <linux/sched/task_stack.h>
#include <asm/debug-monitors.h>
#include <asm/insn.h>
#include <asm/spectre.h>
#include <asm/traps.h>
#include <asm/vectors.h>
#include <asm/virt.h>
/*
* We try to ensure that the mitigation state can never change as the result of
* onlining a late CPU.
*/
static void update_mitigation_state(enum mitigation_state *oldp,
enum mitigation_state new)
{
enum mitigation_state state;
do {
state = READ_ONCE(*oldp);
if (new <= state)
break;
/* Userspace almost certainly can't deal with this. */
if (WARN_ON(system_capabilities_finalized()))
break;
} while (cmpxchg_relaxed(oldp, state, new) != state);
}
/*
* Spectre v1.
*
* The kernel can't protect userspace for this one: it's each person for
* themselves. Advertise what we're doing and be done with it.
*/
ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "Mitigation: __user pointer sanitization\n");
}
/*
* Spectre v2.
*
* This one sucks. A CPU is either:
*
* - Mitigated in hardware and advertised by ID_AA64PFR0_EL1.CSV2.
* - Mitigated in hardware and listed in our "safe list".
* - Mitigated in software by firmware.
* - Mitigated in software by a CPU-specific dance in the kernel and a
* firmware call at EL2.
* - Vulnerable.
*
* It's not unlikely for different CPUs in a big.LITTLE system to fall into
* different camps.
*/
static enum mitigation_state spectre_v2_state;
static bool __read_mostly __nospectre_v2;
static int __init parse_spectre_v2_param(char *str)
{
__nospectre_v2 = true;
return 0;
}
early_param("nospectre_v2", parse_spectre_v2_param);
static bool spectre_v2_mitigations_off(void)
{
bool ret = __nospectre_v2 || cpu_mitigations_off();
if (ret)
pr_info_once("spectre-v2 mitigation disabled by command line option\n");
return ret;
}
static const char *get_bhb_affected_string(enum mitigation_state bhb_state)
{
switch (bhb_state) {
case SPECTRE_UNAFFECTED:
return "";
default:
case SPECTRE_VULNERABLE:
return ", but not BHB";
case SPECTRE_MITIGATED:
return ", BHB";
}
}
static bool _unprivileged_ebpf_enabled(void)
{
#ifdef CONFIG_BPF_SYSCALL
return !sysctl_unprivileged_bpf_disabled;
#else
return false;
#endif
}
ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
char *buf)
{
enum mitigation_state bhb_state = arm64_get_spectre_bhb_state();
const char *bhb_str = get_bhb_affected_string(bhb_state);
const char *v2_str = "Branch predictor hardening";
switch (spectre_v2_state) {
case SPECTRE_UNAFFECTED:
if (bhb_state == SPECTRE_UNAFFECTED)
return sprintf(buf, "Not affected\n");
/*
* Platforms affected by Spectre-BHB can't report
* "Not affected" for Spectre-v2.
*/
v2_str = "CSV2";
fallthrough;
case SPECTRE_MITIGATED:
if (bhb_state == SPECTRE_MITIGATED && _unprivileged_ebpf_enabled())
return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n");
return sprintf(buf, "Mitigation: %s%s\n", v2_str, bhb_str);
case SPECTRE_VULNERABLE:
fallthrough;
default:
return sprintf(buf, "Vulnerable\n");
}
}
static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void)
{
u64 pfr0;
static const struct midr_range spectre_v2_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ }
};
/* If the CPU has CSV2 set, we're safe */
pfr0 = read_cpuid(ID_AA64PFR0_EL1);
if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT))
return SPECTRE_UNAFFECTED;
/* Alternatively, we have a list of unaffected CPUs */
if (is_midr_in_range_list(spectre_v2_safe_list))
return SPECTRE_UNAFFECTED;
return SPECTRE_VULNERABLE;
}
static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void)
{
int ret;
struct arm_smccc_res res;
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_ARCH_WORKAROUND_1, &res);
ret = res.a0;
switch (ret) {
case SMCCC_RET_SUCCESS:
return SPECTRE_MITIGATED;
case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
return SPECTRE_UNAFFECTED;
default:
fallthrough;
case SMCCC_RET_NOT_SUPPORTED:
return SPECTRE_VULNERABLE;
}
}
bool has_spectre_v2(const struct arm64_cpu_capabilities *entry, int scope)
{
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
if (spectre_v2_get_cpu_hw_mitigation_state() == SPECTRE_UNAFFECTED)
return false;
if (spectre_v2_get_cpu_fw_mitigation_state() == SPECTRE_UNAFFECTED)
return false;
return true;
}
enum mitigation_state arm64_get_spectre_v2_state(void)
{
return spectre_v2_state;
}
DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
static void install_bp_hardening_cb(bp_hardening_cb_t fn)
{
__this_cpu_write(bp_hardening_data.fn, fn);
/*
* Vinz Clortho takes the hyp_vecs start/end "keys" at
* the door when we're a guest. Skip the hyp-vectors work.
*/
if (!is_hyp_mode_available())
return;
__this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT);
}
/* Called during entry so must be noinstr */
static noinstr void call_smc_arch_workaround_1(void)
{
arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
}
/* Called during entry so must be noinstr */
static noinstr void call_hvc_arch_workaround_1(void)
{
arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
}
/* Called during entry so must be noinstr */
static noinstr void qcom_link_stack_sanitisation(void)
{
u64 tmp;
asm volatile("mov %0, x30 \n"
".rept 16 \n"
"bl . + 4 \n"
".endr \n"
"mov x30, %0 \n"
: "=&r" (tmp));
}
static bp_hardening_cb_t spectre_v2_get_sw_mitigation_cb(void)
{
u32 midr = read_cpuid_id();
if (((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR) &&
((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR_V1))
return NULL;
return qcom_link_stack_sanitisation;
}
static enum mitigation_state spectre_v2_enable_fw_mitigation(void)
{
bp_hardening_cb_t cb;
enum mitigation_state state;
state = spectre_v2_get_cpu_fw_mitigation_state();
if (state != SPECTRE_MITIGATED)
return state;
if (spectre_v2_mitigations_off())
return SPECTRE_VULNERABLE;
switch (arm_smccc_1_1_get_conduit()) {
case SMCCC_CONDUIT_HVC:
cb = call_hvc_arch_workaround_1;
break;
case SMCCC_CONDUIT_SMC:
cb = call_smc_arch_workaround_1;
break;
default:
return SPECTRE_VULNERABLE;
}
/*
* Prefer a CPU-specific workaround if it exists. Note that we
* still rely on firmware for the mitigation at EL2.
*/
cb = spectre_v2_get_sw_mitigation_cb() ?: cb;
install_bp_hardening_cb(cb);
return SPECTRE_MITIGATED;
}
void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
{
enum mitigation_state state;
WARN_ON(preemptible());
state = spectre_v2_get_cpu_hw_mitigation_state();
if (state == SPECTRE_VULNERABLE)
state = spectre_v2_enable_fw_mitigation();
update_mitigation_state(&spectre_v2_state, state);
}
/*
* Spectre-v3a.
*
* Phew, there's not an awful lot to do here! We just instruct EL2 to use
* an indirect trampoline for the hyp vectors so that guests can't read
* VBAR_EL2 to defeat randomisation of the hypervisor VA layout.
*/
bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope)
{
static const struct midr_range spectre_v3a_unsafe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
{},
};
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
return is_midr_in_range_list(spectre_v3a_unsafe_list);
}
void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
{
struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
if (this_cpu_has_cap(ARM64_SPECTRE_V3A))
data->slot += HYP_VECTOR_INDIRECT;
}
/*
* Spectre v4.
*
* If you thought Spectre v2 was nasty, wait until you see this mess. A CPU is
* either:
*
* - Mitigated in hardware and listed in our "safe list".
* - Mitigated in hardware via PSTATE.SSBS.
* - Mitigated in software by firmware (sometimes referred to as SSBD).
*
* Wait, that doesn't sound so bad, does it? Keep reading...
*
* A major source of headaches is that the software mitigation is enabled both
* on a per-task basis, but can also be forced on for the kernel, necessitating
* both context-switch *and* entry/exit hooks. To make it even worse, some CPUs
* allow EL0 to toggle SSBS directly, which can end up with the prctl() state
* being stale when re-entering the kernel. The usual big.LITTLE caveats apply,
* so you can have systems that have both firmware and SSBS mitigations. This
* means we actually have to reject late onlining of CPUs with mitigations if
* all of the currently onlined CPUs are safelisted, as the mitigation tends to
* be opt-in for userspace. Yes, really, the cure is worse than the disease.
*
* The only good part is that if the firmware mitigation is present, then it is
* present for all CPUs, meaning we don't have to worry about late onlining of a
* vulnerable CPU if one of the boot CPUs is using the firmware mitigation.
*
* Give me a VAX-11/780 any day of the week...
*/
static enum mitigation_state spectre_v4_state;
/* This is the per-cpu state tracking whether we need to talk to firmware */
DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
enum spectre_v4_policy {
SPECTRE_V4_POLICY_MITIGATION_DYNAMIC,
SPECTRE_V4_POLICY_MITIGATION_ENABLED,
SPECTRE_V4_POLICY_MITIGATION_DISABLED,
};
static enum spectre_v4_policy __read_mostly __spectre_v4_policy;
static const struct spectre_v4_param {
const char *str;
enum spectre_v4_policy policy;
} spectre_v4_params[] = {
{ "force-on", SPECTRE_V4_POLICY_MITIGATION_ENABLED, },
{ "force-off", SPECTRE_V4_POLICY_MITIGATION_DISABLED, },
{ "kernel", SPECTRE_V4_POLICY_MITIGATION_DYNAMIC, },
};
static int __init parse_spectre_v4_param(char *str)
{
int i;
if (!str || !str[0])
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(spectre_v4_params); i++) {
const struct spectre_v4_param *param = &spectre_v4_params[i];
if (strncmp(str, param->str, strlen(param->str)))
continue;
__spectre_v4_policy = param->policy;
return 0;
}
return -EINVAL;
}
early_param("ssbd", parse_spectre_v4_param);
/*
* Because this was all written in a rush by people working in different silos,
* we've ended up with multiple command line options to control the same thing.
* Wrap these up in some helpers, which prefer disabling the mitigation if faced
* with contradictory parameters. The mitigation is always either "off",
* "dynamic" or "on".
*/
static bool spectre_v4_mitigations_off(void)
{
bool ret = cpu_mitigations_off() ||
__spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED;
if (ret)
pr_info_once("spectre-v4 mitigation disabled by command-line option\n");
return ret;
}
/* Do we need to toggle the mitigation state on entry to/exit from the kernel? */
static bool spectre_v4_mitigations_dynamic(void)
{
return !spectre_v4_mitigations_off() &&
__spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DYNAMIC;
}
static bool spectre_v4_mitigations_on(void)
{
return !spectre_v4_mitigations_off() &&
__spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_ENABLED;
}
ssize_t cpu_show_spec_store_bypass(struct device *dev,
struct device_attribute *attr, char *buf)
{
switch (spectre_v4_state) {
case SPECTRE_UNAFFECTED:
return sprintf(buf, "Not affected\n");
case SPECTRE_MITIGATED:
return sprintf(buf, "Mitigation: Speculative Store Bypass disabled via prctl\n");
case SPECTRE_VULNERABLE:
fallthrough;
default:
return sprintf(buf, "Vulnerable\n");
}
}
enum mitigation_state arm64_get_spectre_v4_state(void)
{
return spectre_v4_state;
}
static enum mitigation_state spectre_v4_get_cpu_hw_mitigation_state(void)
{
static const struct midr_range spectre_v4_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ },
};
if (is_midr_in_range_list(spectre_v4_safe_list))
return SPECTRE_UNAFFECTED;
/* CPU features are detected first */
if (this_cpu_has_cap(ARM64_SSBS))
return SPECTRE_MITIGATED;
return SPECTRE_VULNERABLE;
}
static enum mitigation_state spectre_v4_get_cpu_fw_mitigation_state(void)
{
int ret;
struct arm_smccc_res res;
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_ARCH_WORKAROUND_2, &res);
ret = res.a0;
switch (ret) {
case SMCCC_RET_SUCCESS:
return SPECTRE_MITIGATED;
case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
fallthrough;
case SMCCC_RET_NOT_REQUIRED:
return SPECTRE_UNAFFECTED;
default:
fallthrough;
case SMCCC_RET_NOT_SUPPORTED:
return SPECTRE_VULNERABLE;
}
}
bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope)
{
enum mitigation_state state;
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
state = spectre_v4_get_cpu_hw_mitigation_state();
if (state == SPECTRE_VULNERABLE)
state = spectre_v4_get_cpu_fw_mitigation_state();
return state != SPECTRE_UNAFFECTED;
}
bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr)
{
const u32 instr_mask = ~(1U << PSTATE_Imm_shift);
const u32 instr_val = 0xd500401f | PSTATE_SSBS;
if ((instr & instr_mask) != instr_val)
return false;
if (instr & BIT(PSTATE_Imm_shift))
regs->pstate |= PSR_SSBS_BIT;
else
regs->pstate &= ~PSR_SSBS_BIT;
arm64_skip_faulting_instruction(regs, 4);
return true;
}
static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
{
enum mitigation_state state;
/*
* If the system is mitigated but this CPU doesn't have SSBS, then
* we must be on the safelist and there's nothing more to do.
*/
state = spectre_v4_get_cpu_hw_mitigation_state();
if (state != SPECTRE_MITIGATED || !this_cpu_has_cap(ARM64_SSBS))
return state;
if (spectre_v4_mitigations_off()) {
sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
set_pstate_ssbs(1);
return SPECTRE_VULNERABLE;
}
/* SCTLR_EL1.DSSBS was initialised to 0 during boot */
set_pstate_ssbs(0);
/*
* SSBS is self-synchronizing and is intended to affect subsequent
* speculative instructions, but some CPUs can speculate with a stale
* value of SSBS.
*
* Mitigate this with an unconditional speculation barrier, as CPUs
* could mis-speculate branches and bypass a conditional barrier.
*/
if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386))
spec_bar();
return SPECTRE_MITIGATED;
}
/*
* Patch a branch over the Spectre-v4 mitigation code with a NOP so that
* we fallthrough and check whether firmware needs to be called on this CPU.
*/
void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt,
__le32 *origptr,
__le32 *updptr, int nr_inst)
{
BUG_ON(nr_inst != 1); /* Branch -> NOP */
if (spectre_v4_mitigations_off())
return;
if (cpus_have_cap(ARM64_SSBS))
return;
if (spectre_v4_mitigations_dynamic())
*updptr = cpu_to_le32(aarch64_insn_gen_nop());
}
/*
* Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction
* to call into firmware to adjust the mitigation state.
*/
void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt,
__le32 *origptr,
__le32 *updptr, int nr_inst)
{
u32 insn;
BUG_ON(nr_inst != 1); /* NOP -> HVC/SMC */
switch (arm_smccc_1_1_get_conduit()) {
case SMCCC_CONDUIT_HVC:
insn = aarch64_insn_get_hvc_value();
break;
case SMCCC_CONDUIT_SMC:
insn = aarch64_insn_get_smc_value();
break;
default:
return;
}
*updptr = cpu_to_le32(insn);
}
static enum mitigation_state spectre_v4_enable_fw_mitigation(void)
{
enum mitigation_state state;
state = spectre_v4_get_cpu_fw_mitigation_state();
if (state != SPECTRE_MITIGATED)
return state;
if (spectre_v4_mitigations_off()) {
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, false, NULL);
return SPECTRE_VULNERABLE;
}
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, true, NULL);
if (spectre_v4_mitigations_dynamic())
__this_cpu_write(arm64_ssbd_callback_required, 1);
return SPECTRE_MITIGATED;
}
void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
{
enum mitigation_state state;
WARN_ON(preemptible());
state = spectre_v4_enable_hw_mitigation();
if (state == SPECTRE_VULNERABLE)
state = spectre_v4_enable_fw_mitigation();
update_mitigation_state(&spectre_v4_state, state);
}
static void __update_pstate_ssbs(struct pt_regs *regs, bool state)
{
u64 bit = compat_user_mode(regs) ? PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
if (state)
regs->pstate |= bit;
else
regs->pstate &= ~bit;
}
void spectre_v4_enable_task_mitigation(struct task_struct *tsk)
{
struct pt_regs *regs = task_pt_regs(tsk);
bool ssbs = false, kthread = tsk->flags & PF_KTHREAD;
if (spectre_v4_mitigations_off())
ssbs = true;
else if (spectre_v4_mitigations_dynamic() && !kthread)
ssbs = !test_tsk_thread_flag(tsk, TIF_SSBD);
__update_pstate_ssbs(regs, ssbs);
}
/*
* The Spectre-v4 mitigation can be controlled via a prctl() from userspace.
* This is interesting because the "speculation disabled" behaviour can be
* configured so that it is preserved across exec(), which means that the
* prctl() may be necessary even when PSTATE.SSBS can be toggled directly
* from userspace.
*/
static void ssbd_prctl_enable_mitigation(struct task_struct *task)
{
task_clear_spec_ssb_noexec(task);
task_set_spec_ssb_disable(task);
set_tsk_thread_flag(task, TIF_SSBD);
}
static void ssbd_prctl_disable_mitigation(struct task_struct *task)
{
task_clear_spec_ssb_noexec(task);
task_clear_spec_ssb_disable(task);
clear_tsk_thread_flag(task, TIF_SSBD);
}
static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
{
switch (ctrl) {
case PR_SPEC_ENABLE:
/* Enable speculation: disable mitigation */
/*
* Force disabled speculation prevents it from being
* re-enabled.
*/
if (task_spec_ssb_force_disable(task))
return -EPERM;
/*
* If the mitigation is forced on, then speculation is forced
* off and we again prevent it from being re-enabled.
*/
if (spectre_v4_mitigations_on())
return -EPERM;
ssbd_prctl_disable_mitigation(task);
break;
case PR_SPEC_FORCE_DISABLE:
/* Force disable speculation: force enable mitigation */
/*
* If the mitigation is forced off, then speculation is forced
* on and we prevent it from being disabled.
*/
if (spectre_v4_mitigations_off())
return -EPERM;
task_set_spec_ssb_force_disable(task);
fallthrough;
case PR_SPEC_DISABLE:
/* Disable speculation: enable mitigation */
/* Same as PR_SPEC_FORCE_DISABLE */
if (spectre_v4_mitigations_off())
return -EPERM;
ssbd_prctl_enable_mitigation(task);
break;
case PR_SPEC_DISABLE_NOEXEC:
/* Disable speculation until execve(): enable mitigation */
/*
* If the mitigation state is forced one way or the other, then
* we must fail now before we try to toggle it on execve().
*/
if (task_spec_ssb_force_disable(task) ||
spectre_v4_mitigations_off() ||
spectre_v4_mitigations_on()) {
return -EPERM;
}
ssbd_prctl_enable_mitigation(task);
task_set_spec_ssb_noexec(task);
break;
default:
return -ERANGE;
}
spectre_v4_enable_task_mitigation(task);
return 0;
}
int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
unsigned long ctrl)
{
switch (which) {
case PR_SPEC_STORE_BYPASS:
return ssbd_prctl_set(task, ctrl);
default:
return -ENODEV;
}
}
static int ssbd_prctl_get(struct task_struct *task)
{
switch (spectre_v4_state) {
case SPECTRE_UNAFFECTED:
return PR_SPEC_NOT_AFFECTED;
case SPECTRE_MITIGATED:
if (spectre_v4_mitigations_on())
return PR_SPEC_NOT_AFFECTED;
if (spectre_v4_mitigations_dynamic())
break;
/* Mitigations are disabled, so we're vulnerable. */
fallthrough;
case SPECTRE_VULNERABLE:
fallthrough;
default:
return PR_SPEC_ENABLE;
}
/* Check the mitigation state for this task */
if (task_spec_ssb_force_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
if (task_spec_ssb_noexec(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC;
if (task_spec_ssb_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
}
int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
{
switch (which) {
case PR_SPEC_STORE_BYPASS:
return ssbd_prctl_get(task);
default:
return -ENODEV;
}
}
/*
* Spectre BHB.
*
* A CPU is either:
* - Mitigated by a branchy loop a CPU specific number of times, and listed
* in our "loop mitigated list".
* - Mitigated in software by the firmware Spectre v2 call.
* - Has the ClearBHB instruction to perform the mitigation.
* - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no
* software mitigation in the vectors is needed.
* - Has CSV2.3, so is unaffected.
*/
static enum mitigation_state spectre_bhb_state;
enum mitigation_state arm64_get_spectre_bhb_state(void)
{
return spectre_bhb_state;
}
enum bhb_mitigation_bits {
BHB_LOOP,
BHB_FW,
BHB_HW,
BHB_INSN,
};
static unsigned long system_bhb_mitigations;
/*
* This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any
* SCOPE_SYSTEM call will give the right answer.
*/
static bool is_spectre_bhb_safe(int scope)
{
static const struct midr_range spectre_bhb_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A520),
MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{},
};
static bool all_safe = true;
if (scope != SCOPE_LOCAL_CPU)
return all_safe;
if (is_midr_in_range_list(spectre_bhb_safe_list))
return true;
all_safe = false;
return false;
}
static u8 spectre_bhb_loop_affected(void)
{
u8 k = 0;
static const struct midr_range spectre_bhb_k132_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
};
static const struct midr_range spectre_bhb_k38_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
};
static const struct midr_range spectre_bhb_k32_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
{},
};
static const struct midr_range spectre_bhb_k24_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A76AE),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD),
MIDR_ALL_VERSIONS(MIDR_HISI_HIP09),
{},
};
static const struct midr_range spectre_bhb_k11_list[] = {
MIDR_ALL_VERSIONS(MIDR_AMPERE1),
{},
};
static const struct midr_range spectre_bhb_k8_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
{},
};
if (is_midr_in_range_list(spectre_bhb_k132_list))
k = 132;
else if (is_midr_in_range_list(spectre_bhb_k38_list))
k = 38;
else if (is_midr_in_range_list(spectre_bhb_k32_list))
k = 32;
else if (is_midr_in_range_list(spectre_bhb_k24_list))
k = 24;
else if (is_midr_in_range_list(spectre_bhb_k11_list))
k = 11;
else if (is_midr_in_range_list(spectre_bhb_k8_list))
k = 8;
return k;
}
static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void)
{
int ret;
struct arm_smccc_res res;
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_ARCH_WORKAROUND_3, &res);
ret = res.a0;
switch (ret) {
case SMCCC_RET_SUCCESS:
return SPECTRE_MITIGATED;
case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
return SPECTRE_UNAFFECTED;
default:
fallthrough;
case SMCCC_RET_NOT_SUPPORTED:
return SPECTRE_VULNERABLE;
}
}
static bool has_spectre_bhb_fw_mitigation(void)
{
enum mitigation_state fw_state;
bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE;
fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
return has_smccc && fw_state == SPECTRE_MITIGATED;
}
static bool supports_ecbhb(int scope)
{
u64 mmfr1;
if (scope == SCOPE_LOCAL_CPU)
mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1);
else
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
return cpuid_feature_extract_unsigned_field(mmfr1,
ID_AA64MMFR1_EL1_ECBHB_SHIFT);
}
static u8 max_bhb_k;
bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
int scope)
{
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
if (supports_csv2p3(scope))
return false;
if (is_spectre_bhb_safe(scope))
return false;
/*
* At this point the core isn't known to be "safe" so we're going to
* assume it's vulnerable. We still need to update `max_bhb_k` though,
* but only if we aren't mitigating with clearbhb though.
*/
if (scope == SCOPE_LOCAL_CPU && !supports_clearbhb(SCOPE_LOCAL_CPU))
max_bhb_k = max(max_bhb_k, spectre_bhb_loop_affected());
return true;
}
static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
{
const char *v = arm64_get_bp_hardening_vector(slot);
__this_cpu_write(this_cpu_vector, v);
/*
* When KPTI is in use, the vectors are switched when exiting to
* user-space.
*/
if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0))
return;
write_sysreg(v, vbar_el1);
isb();
}
static bool __read_mostly __nospectre_bhb;
static int __init parse_spectre_bhb_param(char *str)
{
__nospectre_bhb = true;
return 0;
}
early_param("nospectre_bhb", parse_spectre_bhb_param);
void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
{
bp_hardening_cb_t cpu_cb;
enum mitigation_state state = SPECTRE_VULNERABLE;
struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU))
return;
if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) {
/* No point mitigating Spectre-BHB alone. */
} else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) {
pr_info_once("spectre-bhb mitigation disabled by compile time option\n");
} else if (cpu_mitigations_off() || __nospectre_bhb) {
pr_info_once("spectre-bhb mitigation disabled by command line option\n");
} else if (supports_ecbhb(SCOPE_LOCAL_CPU)) {
state = SPECTRE_MITIGATED;
set_bit(BHB_HW, &system_bhb_mitigations);
} else if (supports_clearbhb(SCOPE_LOCAL_CPU)) {
/*
* Ensure KVM uses the indirect vector which will have ClearBHB
* added.
*/
if (!data->slot)
data->slot = HYP_VECTOR_INDIRECT;
this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
state = SPECTRE_MITIGATED;
set_bit(BHB_INSN, &system_bhb_mitigations);
} else if (spectre_bhb_loop_affected()) {
/*
* Ensure KVM uses the indirect vector which will have the
* branchy-loop added. A57/A72-r0 will already have selected
* the spectre-indirect vector, which is sufficient for BHB
* too.
*/
if (!data->slot)
data->slot = HYP_VECTOR_INDIRECT;
this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
state = SPECTRE_MITIGATED;
set_bit(BHB_LOOP, &system_bhb_mitigations);
} else if (has_spectre_bhb_fw_mitigation()) {
/*
* Ensure KVM uses one of the spectre bp_hardening
* vectors. The indirect vector doesn't include the EL3
* call, so needs upgrading to
* HYP_VECTOR_SPECTRE_INDIRECT.
*/
if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
data->slot += 1;
this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
/*
* The WA3 call in the vectors supersedes the WA1 call
* made during context-switch. Uninstall any firmware
* bp_hardening callback.
*/
cpu_cb = spectre_v2_get_sw_mitigation_cb();
if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
__this_cpu_write(bp_hardening_data.fn, NULL);
state = SPECTRE_MITIGATED;
set_bit(BHB_FW, &system_bhb_mitigations);
}
update_mitigation_state(&spectre_bhb_state, state);
}
/* Patched to NOP when enabled */
void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
__le32 *origptr,
__le32 *updptr, int nr_inst)
{
BUG_ON(nr_inst != 1);
if (test_bit(BHB_LOOP, &system_bhb_mitigations))
*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
}
/* Patched to NOP when enabled */
void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt,
__le32 *origptr,
__le32 *updptr, int nr_inst)
{
BUG_ON(nr_inst != 1);
if (test_bit(BHB_FW, &system_bhb_mitigations))
*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
}
/* Patched to correct the immediate */
void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
u8 rd;
u32 insn;
BUG_ON(nr_inst != 1); /* MOV -> MOV */
if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY))
return;
insn = le32_to_cpu(*origptr);
rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
insn = aarch64_insn_gen_movewide(rd, max_bhb_k, 0,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_ZERO);
*updptr++ = cpu_to_le32(insn);
}
/* Patched to mov WA3 when supported */
void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
u8 rd;
u32 insn;
BUG_ON(nr_inst != 1); /* MOV -> MOV */
if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) ||
!test_bit(BHB_FW, &system_bhb_mitigations))
return;
insn = le32_to_cpu(*origptr);
rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_ORR,
AARCH64_INSN_VARIANT_32BIT,
AARCH64_INSN_REG_ZR, rd,
ARM_SMCCC_ARCH_WORKAROUND_3);
if (WARN_ON_ONCE(insn == AARCH64_BREAK_FAULT))
return;
*updptr++ = cpu_to_le32(insn);
}
/* Patched to NOP when not supported */
void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
BUG_ON(nr_inst != 2);
if (test_bit(BHB_INSN, &system_bhb_mitigations))
return;
*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
}
#ifdef CONFIG_BPF_SYSCALL
#define EBPF_WARN "Unprivileged eBPF is enabled, data leaks possible via Spectre v2 BHB attacks!\n"
void unpriv_ebpf_notify(int new_state)
{
if (spectre_v2_state == SPECTRE_VULNERABLE ||
spectre_bhb_state != SPECTRE_MITIGATED)
return;
if (!new_state)
pr_err("WARNING: %s", EBPF_WARN);
}
#endif
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1994, Karl Keyte: Added support for disk statistics
* Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
* Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
* kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au>
* - July2000
* bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
*/
/*
* This handles all read/write requests to block devices
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-pm.h>
#include <linux/blk-integrity.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
#include <linux/delay.h>
#include <linux/ratelimit.h>
#include <linux/pm_runtime.h>
#include <linux/t10-pi.h>
#include <linux/debugfs.h>
#include <linux/bpf.h>
#include <linux/part_stat.h>
#include <linux/sched/sysctl.h>
#include <linux/blk-crypto.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-pm.h"
#include "blk-cgroup.h"
#include "blk-throttle.h"
#include "blk-ioprio.h"
struct dentry *blk_debugfs_root;
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert);
static DEFINE_IDA(blk_queue_ida);
/*
* For queue allocation
*/
static struct kmem_cache *blk_requestq_cachep;
/*
* Controlling structure to kblockd
*/
static struct workqueue_struct *kblockd_workqueue;
/**
* blk_queue_flag_set - atomically set a queue flag
* @flag: flag to be set
* @q: request queue
*/
void blk_queue_flag_set(unsigned int flag, struct request_queue *q)
{
set_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_set);
/**
* blk_queue_flag_clear - atomically clear a queue flag
* @flag: flag to be cleared
* @q: request queue
*/
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
{
clear_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_clear);
#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
static const char *const blk_op_name[] = {
REQ_OP_NAME(READ),
REQ_OP_NAME(WRITE),
REQ_OP_NAME(FLUSH),
REQ_OP_NAME(DISCARD),
REQ_OP_NAME(SECURE_ERASE),
REQ_OP_NAME(ZONE_RESET),
REQ_OP_NAME(ZONE_RESET_ALL),
REQ_OP_NAME(ZONE_OPEN),
REQ_OP_NAME(ZONE_CLOSE),
REQ_OP_NAME(ZONE_FINISH),
REQ_OP_NAME(ZONE_APPEND),
REQ_OP_NAME(WRITE_ZEROES),
REQ_OP_NAME(DRV_IN),
REQ_OP_NAME(DRV_OUT),
};
#undef REQ_OP_NAME
/**
* blk_op_str - Return string XXX in the REQ_OP_XXX.
* @op: REQ_OP_XXX.
*
* Description: Centralize block layer function to convert REQ_OP_XXX into
* string format. Useful in the debugging and tracing bio or request. For
* invalid REQ_OP_XXX it returns string "UNKNOWN".
*/
inline const char *blk_op_str(enum req_op op)
{
const char *op_str = "UNKNOWN";
if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op])
op_str = blk_op_name[op];
return op_str;
}
EXPORT_SYMBOL_GPL(blk_op_str);
static const struct {
int errno;
const char *name;
} blk_errors[] = {
[BLK_STS_OK] = { 0, "" },
[BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" },
[BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" },
[BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" },
[BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" },
[BLK_STS_TARGET] = { -EREMOTEIO, "critical target" },
[BLK_STS_RESV_CONFLICT] = { -EBADE, "reservation conflict" },
[BLK_STS_MEDIUM] = { -ENODATA, "critical medium" },
[BLK_STS_PROTECTION] = { -EILSEQ, "protection" },
[BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" },
[BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" },
[BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" },
[BLK_STS_OFFLINE] = { -ENODEV, "device offline" },
/* device mapper special case, should not leak out: */
[BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" },
/* zone device specific errors */
[BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" },
[BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" },
/* Command duration limit device-side timeout */
[BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" },
[BLK_STS_INVAL] = { -EINVAL, "invalid" },
/* everything else not covered above: */
[BLK_STS_IOERR] = { -EIO, "I/O" },
};
blk_status_t errno_to_blk_status(int errno)
{
int i;
for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
if (blk_errors[i].errno == errno)
return (__force blk_status_t)i;
}
return BLK_STS_IOERR;
}
EXPORT_SYMBOL_GPL(errno_to_blk_status);
int blk_status_to_errno(blk_status_t status)
{
int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
return -EIO;
return blk_errors[idx].errno;
}
EXPORT_SYMBOL_GPL(blk_status_to_errno);
const char *blk_status_to_str(blk_status_t status)
{
int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
return "<null>";
return blk_errors[idx].name;
}
EXPORT_SYMBOL_GPL(blk_status_to_str);
/**
* blk_sync_queue - cancel any pending callbacks on a queue
* @q: the queue
*
* Description:
* The block layer may perform asynchronous callback activity
* on a queue, such as calling the unplug function after a timeout.
* A block device may call blk_sync_queue to ensure that any
* such activity is cancelled, thus allowing it to release resources
* that the callbacks might use. The caller must already have made sure
* that its ->submit_bio will not re-add plugging prior to calling
* this function.
*
* This function does not cancel any asynchronous activity arising
* out of elevator or throttling code. That would require elevator_exit()
* and blkcg_exit_queue() to be called with queue lock initialized.
*
*/
void blk_sync_queue(struct request_queue *q)
{
timer_delete_sync(&q->timeout);
cancel_work_sync(&q->timeout_work);
}
EXPORT_SYMBOL(blk_sync_queue);
/**
* blk_set_pm_only - increment pm_only counter
* @q: request queue pointer
*/
void blk_set_pm_only(struct request_queue *q)
{
atomic_inc(&q->pm_only);
}
EXPORT_SYMBOL_GPL(blk_set_pm_only);
void blk_clear_pm_only(struct request_queue *q)
{
int pm_only;
pm_only = atomic_dec_return(&q->pm_only);
WARN_ON_ONCE(pm_only < 0);
if (pm_only == 0)
wake_up_all(&q->mq_freeze_wq);
}
EXPORT_SYMBOL_GPL(blk_clear_pm_only);
static void blk_free_queue_rcu(struct rcu_head *rcu_head)
{
struct request_queue *q = container_of(rcu_head,
struct request_queue, rcu_head);
percpu_ref_exit(&q->q_usage_counter);
kmem_cache_free(blk_requestq_cachep, q);
}
static void blk_free_queue(struct request_queue *q)
{
blk_free_queue_stats(q->stats);
if (queue_is_mq(q))
blk_mq_release(q);
ida_free(&blk_queue_ida, q->id);
lockdep_unregister_key(&q->io_lock_cls_key);
lockdep_unregister_key(&q->q_lock_cls_key);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
/**
* blk_put_queue - decrement the request_queue refcount
* @q: the request_queue structure to decrement the refcount for
*
* Decrements the refcount of the request_queue and free it when the refcount
* reaches 0.
*/
void blk_put_queue(struct request_queue *q)
{
if (refcount_dec_and_test(&q->refs))
blk_free_queue(q);
}
EXPORT_SYMBOL(blk_put_queue);
bool blk_queue_start_drain(struct request_queue *q)
{
/*
* When queue DYING flag is set, we need to block new req
* entering queue, so we call blk_freeze_queue_start() to
* prevent I/O from crossing blk_queue_enter().
*/
bool freeze = __blk_freeze_queue_start(q, current);
if (queue_is_mq(q))
blk_mq_wake_waiters(q);
/* Make blk_queue_enter() reexamine the DYING flag. */
wake_up_all(&q->mq_freeze_wq);
return freeze;
}
/**
* blk_queue_enter() - try to increase q->q_usage_counter
* @q: request queue pointer
* @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
*/
int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
{
const bool pm = flags & BLK_MQ_REQ_PM;
while (!blk_try_enter_queue(q, pm)) {
if (flags & BLK_MQ_REQ_NOWAIT)
return -EAGAIN;
/*
* read pair of barrier in blk_freeze_queue_start(), we need to
* order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
* reading .mq_freeze_depth or queue dying flag, otherwise the
* following wait may never return if the two reads are
* reordered.
*/
smp_rmb();
wait_event(q->mq_freeze_wq,
(!q->mq_freeze_depth &&
blk_pm_resume_queue(pm, q)) ||
blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
}
rwsem_acquire_read(&q->q_lockdep_map, 0, 0, _RET_IP_);
rwsem_release(&q->q_lockdep_map, _RET_IP_);
return 0;
}
int __bio_queue_enter(struct request_queue *q, struct bio *bio)
{
while (!blk_try_enter_queue(q, false)) {
struct gendisk *disk = bio->bi_bdev->bd_disk;
if (bio->bi_opf & REQ_NOWAIT) {
if (test_bit(GD_DEAD, &disk->state))
goto dead;
bio_wouldblock_error(bio);
return -EAGAIN;
}
/*
* read pair of barrier in blk_freeze_queue_start(), we need to
* order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
* reading .mq_freeze_depth or queue dying flag, otherwise the
* following wait may never return if the two reads are
* reordered.
*/
smp_rmb();
wait_event(q->mq_freeze_wq,
(!q->mq_freeze_depth &&
blk_pm_resume_queue(false, q)) ||
test_bit(GD_DEAD, &disk->state));
if (test_bit(GD_DEAD, &disk->state))
goto dead;
}
rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_);
rwsem_release(&q->io_lockdep_map, _RET_IP_);
return 0;
dead:
bio_io_error(bio);
return -ENODEV;
}
void blk_queue_exit(struct request_queue *q)
{
percpu_ref_put(&q->q_usage_counter);
}
static void blk_queue_usage_counter_release(struct percpu_ref *ref)
{
struct request_queue *q =
container_of(ref, struct request_queue, q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
static void blk_rq_timed_out_timer(struct timer_list *t)
{
struct request_queue *q = from_timer(q, t, timeout);
kblockd_schedule_work(&q->timeout_work);
}
static void blk_timeout_work(struct work_struct *work)
{
}
struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
{
struct request_queue *q;
int error;
q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
node_id);
if (!q)
return ERR_PTR(-ENOMEM);
q->last_merge = NULL;
q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
if (q->id < 0) {
error = q->id;
goto fail_q;
}
q->stats = blk_alloc_queue_stats();
if (!q->stats) {
error = -ENOMEM;
goto fail_id;
}
error = blk_set_default_limits(lim);
if (error)
goto fail_stats;
q->limits = *lim;
q->node = node_id;
atomic_set(&q->nr_active_requests_shared_tags, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
INIT_WORK(&q->timeout_work, blk_timeout_work);
INIT_LIST_HEAD(&q->icq_list);
refcount_set(&q->refs, 1);
mutex_init(&q->debugfs_mutex);
mutex_init(&q->elevator_lock);
mutex_init(&q->sysfs_lock);
mutex_init(&q->limits_lock);
mutex_init(&q->rq_qos_mutex);
spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq);
mutex_init(&q->mq_freeze_lock);
blkg_init_queue(q);
/*
* Init percpu_ref in atomic mode so that it's faster to shutdown.
* See blk_register_queue() for details.
*/
error = percpu_ref_init(&q->q_usage_counter,
blk_queue_usage_counter_release,
PERCPU_REF_INIT_ATOMIC, GFP_KERNEL);
if (error)
goto fail_stats;
lockdep_register_key(&q->io_lock_cls_key);
lockdep_register_key(&q->q_lock_cls_key);
lockdep_init_map(&q->io_lockdep_map, "&q->q_usage_counter(io)",
&q->io_lock_cls_key, 0);
lockdep_init_map(&q->q_lockdep_map, "&q->q_usage_counter(queue)",
&q->q_lock_cls_key, 0);
/* Teach lockdep about lock ordering (reclaim WRT queue freeze lock). */
fs_reclaim_acquire(GFP_KERNEL);
rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_);
rwsem_release(&q->io_lockdep_map, _RET_IP_);
fs_reclaim_release(GFP_KERNEL);
q->nr_requests = BLKDEV_DEFAULT_RQ;
return q;
fail_stats:
blk_free_queue_stats(q->stats);
fail_id:
ida_free(&blk_queue_ida, q->id);
fail_q:
kmem_cache_free(blk_requestq_cachep, q);
return ERR_PTR(error);
}
/**
* blk_get_queue - increment the request_queue refcount
* @q: the request_queue structure to increment the refcount for
*
* Increment the refcount of the request_queue kobject.
*
* Context: Any context.
*/
bool blk_get_queue(struct request_queue *q)
{
if (unlikely(blk_queue_dying(q)))
return false;
refcount_inc(&q->refs);
return true;
}
EXPORT_SYMBOL(blk_get_queue);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static DECLARE_FAULT_ATTR(fail_make_request);
static int __init setup_fail_make_request(char *str)
{
return setup_fault_attr(&fail_make_request, str);
}
__setup("fail_make_request=", setup_fail_make_request);
bool should_fail_request(struct block_device *part, unsigned int bytes)
{
return bdev_test_flag(part, BD_MAKE_IT_FAIL) &&
should_fail(&fail_make_request, bytes);
}
static int __init fail_make_request_debugfs(void)
{
struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
NULL, &fail_make_request);
return PTR_ERR_OR_ZERO(dir);
}
late_initcall(fail_make_request_debugfs);
#endif /* CONFIG_FAIL_MAKE_REQUEST */
static inline void bio_check_ro(struct bio *bio)
{
if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
return;
if (bdev_test_flag(bio->bi_bdev, BD_RO_WARNED))
return;
bdev_set_flag(bio->bi_bdev, BD_RO_WARNED);
/*
* Use ioctl to set underlying disk of raid/dm to read-only
* will trigger this.
*/
pr_warn("Trying to write to read-only block-device %pg\n",
bio->bi_bdev);
}
}
static noinline int should_fail_bio(struct bio *bio)
{
if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size))
return -EIO;
return 0;
}
ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
/*
* Check whether this bio extends beyond the end of the device or partition.
* This may well happen - the kernel calls bread() without checking the size of
* the device, e.g., when mounting a file system.
*/
static inline int bio_check_eod(struct bio *bio)
{
sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);
unsigned int nr_sectors = bio_sectors(bio);
if (nr_sectors &&
(nr_sectors > maxsector ||
bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
pr_info_ratelimited("%s: attempt to access beyond end of device\n"
"%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n",
current->comm, bio->bi_bdev, bio->bi_opf,
bio->bi_iter.bi_sector, nr_sectors, maxsector);
return -EIO;
}
return 0;
}
/*
* Remap block n of partition p to block n+start(p) of the disk.
*/
static int blk_partition_remap(struct bio *bio)
{
struct block_device *p = bio->bi_bdev;
if (unlikely(should_fail_request(p, bio->bi_iter.bi_size)))
return -EIO;
if (bio_sectors(bio)) {
bio->bi_iter.bi_sector += p->bd_start_sect;
trace_block_bio_remap(bio, p->bd_dev,
bio->bi_iter.bi_sector -
p->bd_start_sect);
}
bio_set_flag(bio, BIO_REMAPPED);
return 0;
}
/*
* Check write append to a zoned block device.
*/
static inline blk_status_t blk_check_zone_append(struct request_queue *q,
struct bio *bio)
{
int nr_sectors = bio_sectors(bio);
/* Only applicable to zoned block devices */
if (!bdev_is_zoned(bio->bi_bdev))
return BLK_STS_NOTSUPP;
/* The bio sector must point to the start of a sequential zone */
if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
return BLK_STS_IOERR;
/*
* Not allowed to cross zone boundaries. Otherwise, the BIO will be
* split and could result in non-contiguous sectors being written in
* different zones.
*/
if (nr_sectors > q->limits.chunk_sectors)
return BLK_STS_IOERR;
/* Make sure the BIO is small enough and will not get split */
if (nr_sectors > q->limits.max_zone_append_sectors)
return BLK_STS_IOERR;
bio->bi_opf |= REQ_NOMERGE;
return BLK_STS_OK;
}
static void __submit_bio(struct bio *bio)
{
/* If plug is not used, add new plug here to cache nsecs time. */
struct blk_plug plug;
if (unlikely(!blk_crypto_bio_prep(&bio)))
return;
blk_start_plug(&plug);
if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) {
blk_mq_submit_bio(bio);
} else if (likely(bio_queue_enter(bio) == 0)) {
struct gendisk *disk = bio->bi_bdev->bd_disk;
if ((bio->bi_opf & REQ_POLLED) &&
!(disk->queue->limits.features & BLK_FEAT_POLL)) {
bio->bi_status = BLK_STS_NOTSUPP;
bio_endio(bio);
} else {
disk->fops->submit_bio(bio);
}
blk_queue_exit(disk->queue);
}
blk_finish_plug(&plug);
}
/*
* The loop in this function may be a bit non-obvious, and so deserves some
* explanation:
*
* - Before entering the loop, bio->bi_next is NULL (as all callers ensure
* that), so we have a list with a single bio.
* - We pretend that we have just taken it off a longer list, so we assign
* bio_list to a pointer to the bio_list_on_stack, thus initialising the
* bio_list of new bios to be added. ->submit_bio() may indeed add some more
* bios through a recursive call to submit_bio_noacct. If it did, we find a
* non-NULL value in bio_list and re-enter the loop from the top.
* - In this case we really did just take the bio of the top of the list (no
* pretending) and so remove it from bio_list, and call into ->submit_bio()
* again.
*
* bio_list_on_stack[0] contains bios submitted by the current ->submit_bio.
* bio_list_on_stack[1] contains bios that were submitted before the current
* ->submit_bio, but that haven't been processed yet.
*/
static void __submit_bio_noacct(struct bio *bio)
{
struct bio_list bio_list_on_stack[2];
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack[0]);
current->bio_list = bio_list_on_stack;
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
struct bio_list lower, same;
/*
* Create a fresh bio_list for all subordinate requests.
*/
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
__submit_bio(bio);
/*
* Sort new bios into those for a lower level and those for the
* same level.
*/
bio_list_init(&lower);
bio_list_init(&same);
while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
if (q == bdev_get_queue(bio->bi_bdev))
bio_list_add(&same, bio);
else
bio_list_add(&lower, bio);
/*
* Now assemble so we handle the lowest level first.
*/
bio_list_merge(&bio_list_on_stack[0], &lower);
bio_list_merge(&bio_list_on_stack[0], &same);
bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
current->bio_list = NULL;
}
static void __submit_bio_noacct_mq(struct bio *bio)
{
struct bio_list bio_list[2] = { };
current->bio_list = bio_list;
do {
__submit_bio(bio);
} while ((bio = bio_list_pop(&bio_list[0])));
current->bio_list = NULL;
}
void submit_bio_noacct_nocheck(struct bio *bio)
{
blk_cgroup_bio_start(bio);
blkcg_bio_issue_init(bio);
if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_queue(bio);
/*
* Now that enqueuing has been traced, we need to trace
* completion as well.
*/
bio_set_flag(bio, BIO_TRACE_COMPLETION);
}
/*
* We only want one ->submit_bio to be active at a time, else stack
* usage with stacked devices could be a problem. Use current->bio_list
* to collect a list of requests submited by a ->submit_bio method while
* it is active, and then process them after it returned.
*/
if (current->bio_list)
bio_list_add(¤t->bio_list[0], bio);
else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO))
__submit_bio_noacct_mq(bio);
else
__submit_bio_noacct(bio);
}
static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q,
struct bio *bio)
{
if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q))
return BLK_STS_INVAL;
if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q))
return BLK_STS_INVAL;
return BLK_STS_OK;
}
/**
* submit_bio_noacct - re-submit a bio to the block device layer for I/O
* @bio: The bio describing the location in memory and on the device.
*
* This is a version of submit_bio() that shall only be used for I/O that is
* resubmitted to lower level drivers by stacking block drivers. All file
* systems and other upper level users of the block layer should use
* submit_bio() instead.
*/
void submit_bio_noacct(struct bio *bio)
{
struct block_device *bdev = bio->bi_bdev;
struct request_queue *q = bdev_get_queue(bdev);
blk_status_t status = BLK_STS_IOERR;
might_sleep();
/*
* For a REQ_NOWAIT based request, return -EOPNOTSUPP
* if queue does not support NOWAIT.
*/
if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev))
goto not_supported;
if (should_fail_bio(bio))
goto end_io;
bio_check_ro(bio);
if (!bio_flagged(bio, BIO_REMAPPED)) {
if (unlikely(bio_check_eod(bio)))
goto end_io;
if (bdev_is_partition(bdev) &&
unlikely(blk_partition_remap(bio)))
goto end_io;
}
/*
* Filter flush bio's early so that bio based drivers without flush
* support don't have to worry about them.
*/
if (op_is_flush(bio->bi_opf)) {
if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE &&
bio_op(bio) != REQ_OP_ZONE_APPEND))
goto end_io;
if (!bdev_write_cache(bdev)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
if (!bio_sectors(bio)) {
status = BLK_STS_OK;
goto end_io;
}
}
}
switch (bio_op(bio)) {
case REQ_OP_READ:
break;
case REQ_OP_WRITE:
if (bio->bi_opf & REQ_ATOMIC) {
status = blk_validate_atomic_write_op_size(q, bio);
if (status != BLK_STS_OK)
goto end_io;
}
break;
case REQ_OP_FLUSH:
/*
* REQ_OP_FLUSH can't be submitted through bios, it is only
* synthetized in struct request by the flush state machine.
*/
goto not_supported;
case REQ_OP_DISCARD:
if (!bdev_max_discard_sectors(bdev))
goto not_supported;
break;
case REQ_OP_SECURE_ERASE:
if (!bdev_max_secure_erase_sectors(bdev))
goto not_supported;
break;
case REQ_OP_ZONE_APPEND:
status = blk_check_zone_append(q, bio);
if (status != BLK_STS_OK)
goto end_io;
break;
case REQ_OP_WRITE_ZEROES:
if (!q->limits.max_write_zeroes_sectors)
goto not_supported;
break;
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
case REQ_OP_ZONE_RESET_ALL:
if (!bdev_is_zoned(bio->bi_bdev))
goto not_supported;
break;
case REQ_OP_DRV_IN:
case REQ_OP_DRV_OUT:
/*
* Driver private operations are only used with passthrough
* requests.
*/
fallthrough;
default:
goto not_supported;
}
if (blk_throtl_bio(bio))
return;
submit_bio_noacct_nocheck(bio);
return;
not_supported:
status = BLK_STS_NOTSUPP;
end_io:
bio->bi_status = status;
bio_endio(bio);
}
EXPORT_SYMBOL(submit_bio_noacct);
static void bio_set_ioprio(struct bio *bio)
{
/* Nobody set ioprio so far? Initialize it based on task's nice value */
if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
bio->bi_ioprio = get_current_ioprio();
blkcg_set_ioprio(bio);
}
/**
* submit_bio - submit a bio to the block device layer for I/O
* @bio: The &struct bio which describes the I/O
*
* submit_bio() is used to submit I/O requests to block devices. It is passed a
* fully set up &struct bio that describes the I/O that needs to be done. The
* bio will be send to the device described by the bi_bdev field.
*
* The success/failure status of the request, along with notification of
* completion, is delivered asynchronously through the ->bi_end_io() callback
* in @bio. The bio must NOT be touched by the caller until ->bi_end_io() has
* been called.
*/
void submit_bio(struct bio *bio)
{
if (bio_op(bio) == REQ_OP_READ) {
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, bio_sectors(bio));
} else if (bio_op(bio) == REQ_OP_WRITE) {
count_vm_events(PGPGOUT, bio_sectors(bio));
}
bio_set_ioprio(bio);
submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio);
/**
* bio_poll - poll for BIO completions
* @bio: bio to poll for
* @iob: batches of IO
* @flags: BLK_POLL_* flags that control the behavior
*
* Poll for completions on queue associated with the bio. Returns number of
* completed entries found.
*
* Note: the caller must either be the context that submitted @bio, or
* be in a RCU critical section to prevent freeing of @bio.
*/
int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
{
blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
struct block_device *bdev;
struct request_queue *q;
int ret = 0;
bdev = READ_ONCE(bio->bi_bdev);
if (!bdev)
return 0;
q = bdev_get_queue(bdev);
if (cookie == BLK_QC_T_NONE)
return 0;
blk_flush_plug(current->plug, false);
/*
* We need to be able to enter a frozen queue, similar to how
* timeouts also need to do that. If that is blocked, then we can
* have pending IO when a queue freeze is started, and then the
* wait for the freeze to finish will wait for polled requests to
* timeout as the poller is preventer from entering the queue and
* completing them. As long as we prevent new IO from being queued,
* that should be all that matters.
*/
if (!percpu_ref_tryget(&q->q_usage_counter))
return 0;
if (queue_is_mq(q)) {
ret = blk_mq_poll(q, cookie, iob, flags);
} else {
struct gendisk *disk = q->disk;
if ((q->limits.features & BLK_FEAT_POLL) && disk &&
disk->fops->poll_bio)
ret = disk->fops->poll_bio(bio, iob, flags);
}
blk_queue_exit(q);
return ret;
}
EXPORT_SYMBOL_GPL(bio_poll);
/*
* Helper to implement file_operations.iopoll. Requires the bio to be stored
* in iocb->private, and cleared before freeing the bio.
*/
int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
unsigned int flags)
{
struct bio *bio;
int ret = 0;
/*
* Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can
* point to a freshly allocated bio at this point. If that happens
* we have a few cases to consider:
*
* 1) the bio is beeing initialized and bi_bdev is NULL. We can just
* simply nothing in this case
* 2) the bio points to a not poll enabled device. bio_poll will catch
* this and return 0
* 3) the bio points to a poll capable device, including but not
* limited to the one that the original bio pointed to. In this
* case we will call into the actual poll method and poll for I/O,
* even if we don't need to, but it won't cause harm either.
*
* For cases 2) and 3) above the RCU grace period ensures that bi_bdev
* is still allocated. Because partitions hold a reference to the whole
* device bdev and thus disk, the disk is also still valid. Grabbing
* a reference to the queue in bio_poll() ensures the hctxs and requests
* are still valid as well.
*/
rcu_read_lock();
bio = READ_ONCE(kiocb->private);
if (bio)
ret = bio_poll(bio, iob, flags);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(iocb_bio_iopoll);
void update_io_ticks(struct block_device *part, unsigned long now, bool end)
{
unsigned long stamp;
again:
stamp = READ_ONCE(part->bd_stamp);
if (unlikely(time_after(now, stamp)) &&
likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
(end || part_in_flight(part)))
__part_stat_add(part, io_ticks, now - stamp);
if (bdev_is_partition(part)) {
part = bdev_whole(part);
goto again;
}
}
unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op,
unsigned long start_time)
{
part_stat_lock();
update_io_ticks(bdev, start_time, false);
part_stat_local_inc(bdev, in_flight[op_is_write(op)]);
part_stat_unlock();
return start_time;
}
EXPORT_SYMBOL(bdev_start_io_acct);
/**
* bio_start_io_acct - start I/O accounting for bio based drivers
* @bio: bio to start account for
*
* Returns the start time that should be passed back to bio_end_io_acct().
*/
unsigned long bio_start_io_acct(struct bio *bio)
{
return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies);
}
EXPORT_SYMBOL_GPL(bio_start_io_acct);
void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
unsigned int sectors, unsigned long start_time)
{
const int sgrp = op_stat_group(op);
unsigned long now = READ_ONCE(jiffies);
unsigned long duration = now - start_time;
part_stat_lock();
update_io_ticks(bdev, now, true);
part_stat_inc(bdev, ios[sgrp]);
part_stat_add(bdev, sectors[sgrp], sectors);
part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration));
part_stat_local_dec(bdev, in_flight[op_is_write(op)]);
part_stat_unlock();
}
EXPORT_SYMBOL(bdev_end_io_acct);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
struct block_device *orig_bdev)
{
bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time);
}
EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped);
/**
* blk_lld_busy - Check if underlying low-level drivers of a device are busy
* @q : the queue of the device being checked
*
* Description:
* Check if underlying low-level drivers of a device are busy.
* If the drivers want to export their busy state, they must set own
* exporting function using blk_queue_lld_busy() first.
*
* Basically, this function is used only by request stacking drivers
* to stop dispatching requests to underlying devices when underlying
* devices are busy. This behavior helps more I/O merging on the queue
* of the request stacking driver and prevents I/O throughput regression
* on burst I/O load.
*
* Return:
* 0 - Not busy (The request stacking driver should dispatch request)
* 1 - Busy (The request stacking driver should stop dispatching request)
*/
int blk_lld_busy(struct request_queue *q)
{
if (queue_is_mq(q) && q->mq_ops->busy)
return q->mq_ops->busy(q);
return 0;
}
EXPORT_SYMBOL_GPL(blk_lld_busy);
int kblockd_schedule_work(struct work_struct *work)
{
return queue_work(kblockd_workqueue, work);
}
EXPORT_SYMBOL(kblockd_schedule_work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
unsigned long delay)
{
return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
}
EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
{
struct task_struct *tsk = current;
/*
* If this is a nested plug, don't actually assign it.
*/
if (tsk->plug)
return;
plug->cur_ktime = 0;
rq_list_init(&plug->mq_list);
rq_list_init(&plug->cached_rqs);
plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
plug->rq_count = 0;
plug->multiple_queues = false;
plug->has_elevator = false;
INIT_LIST_HEAD(&plug->cb_list);
/*
* Store ordering should not be needed here, since a potential
* preempt will imply a full memory barrier
*/
tsk->plug = plug;
}
/**
* blk_start_plug - initialize blk_plug and track it inside the task_struct
* @plug: The &struct blk_plug that needs to be initialized
*
* Description:
* blk_start_plug() indicates to the block layer an intent by the caller
* to submit multiple I/O requests in a batch. The block layer may use
* this hint to defer submitting I/Os from the caller until blk_finish_plug()
* is called. However, the block layer may choose to submit requests
* before a call to blk_finish_plug() if the number of queued I/Os
* exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than
* %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if
* the task schedules (see below).
*
* Tracking blk_plug inside the task_struct will help with auto-flushing the
* pending I/O should the task end up blocking between blk_start_plug() and
* blk_finish_plug(). This is important from a performance perspective, but
* also ensures that we don't deadlock. For instance, if the task is blocking
* for a memory allocation, memory reclaim could end up wanting to free a
* page belonging to that request that is currently residing in our private
* plug. By flushing the pending I/O when the process goes to sleep, we avoid
* this kind of deadlock.
*/
void blk_start_plug(struct blk_plug *plug)
{ blk_start_plug_nr_ios(plug, 1);
}
EXPORT_SYMBOL(blk_start_plug);
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
{
LIST_HEAD(callbacks);
while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) {
struct blk_plug_cb *cb = list_first_entry(&callbacks,
struct blk_plug_cb,
list);
list_del(&cb->list);
cb->callback(cb, from_schedule);
}
}
}
struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
int size)
{
struct blk_plug *plug = current->plug;
struct blk_plug_cb *cb;
if (!plug)
return NULL;
list_for_each_entry(cb, &plug->cb_list, list)
if (cb->callback == unplug && cb->data == data)
return cb;
/* Not currently on the callback list */
BUG_ON(size < sizeof(*cb));
cb = kzalloc(size, GFP_ATOMIC);
if (cb) {
cb->data = data;
cb->callback = unplug;
list_add(&cb->list, &plug->cb_list);
}
return cb;
}
EXPORT_SYMBOL(blk_check_plugged);
void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
{ if (!list_empty(&plug->cb_list)) flush_plug_callbacks(plug, from_schedule);
blk_mq_flush_plug_list(plug, from_schedule);
/*
* Unconditionally flush out cached requests, even if the unplug
* event came from schedule. Since we know hold references to the
* queue for cached requests, we don't want a blocked task holding
* up a queue freeze/quiesce event.
*/
if (unlikely(!rq_list_empty(&plug->cached_rqs))) blk_mq_free_plug_rqs(plug);
plug->cur_ktime = 0;
current->flags &= ~PF_BLOCK_TS;
}
/**
* blk_finish_plug - mark the end of a batch of submitted I/O
* @plug: The &struct blk_plug passed to blk_start_plug()
*
* Description:
* Indicate that a batch of I/O submissions is complete. This function
* must be paired with an initial call to blk_start_plug(). The intent
* is to allow the block layer to optimize I/O submission. See the
* documentation for blk_start_plug() for more information.
*/
void blk_finish_plug(struct blk_plug *plug)
{ if (plug == current->plug) { __blk_flush_plug(plug, false);
current->plug = NULL;
}
}
EXPORT_SYMBOL(blk_finish_plug);
void blk_io_schedule(void)
{
/* Prevent hang_check timer from firing at us during very long I/O */
unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
if (timeout)
io_schedule_timeout(timeout);
else
io_schedule();
}
EXPORT_SYMBOL_GPL(blk_io_schedule);
int __init blk_dev_init(void)
{
BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS));
BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
sizeof_field(struct request, cmd_flags));
BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
sizeof_field(struct bio, bi_opf));
/* used for unplugging and affects IO latency/throughput - HIGHPRI */
kblockd_workqueue = alloc_workqueue("kblockd",
WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC);
blk_debugfs_root = debugfs_create_dir("block", NULL);
return 0;
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
/*
* Define 'struct task_struct' and provide the main scheduler
* APIs (schedule(), wakeup variants, etc.)
*/
#include <uapi/linux/sched.h>
#include <asm/current.h>
#include <asm/processor.h>
#include <linux/thread_info.h>
#include <linux/preempt.h>
#include <linux/cpumask_types.h>
#include <linux/cache.h>
#include <linux/irqflags_types.h>
#include <linux/smp_types.h>
#include <linux/pid_types.h>
#include <linux/sem_types.h>
#include <linux/shm.h>
#include <linux/kmsan_types.h>
#include <linux/mutex_types.h>
#include <linux/plist_types.h>
#include <linux/hrtimer_types.h>
#include <linux/timer_types.h>
#include <linux/seccomp_types.h>
#include <linux/nodemask_types.h>
#include <linux/refcount_types.h>
#include <linux/resource.h>
#include <linux/latencytop.h>
#include <linux/sched/prio.h>
#include <linux/sched/types.h>
#include <linux/signal_types.h>
#include <linux/syscall_user_dispatch_types.h>
#include <linux/mm_types_task.h>
#include <linux/netdevice_xmit.h>
#include <linux/task_io_accounting.h>
#include <linux/posix-timers_types.h>
#include <linux/restart_block.h>
#include <uapi/linux/rseq.h>
#include <linux/seqlock_types.h>
#include <linux/kcsan.h>
#include <linux/rv.h>
#include <linux/livepatch_sched.h>
#include <linux/uidgid_types.h>
#include <linux/tracepoint-defs.h>
#include <asm/kmap_size.h>
/* task_struct member predeclarations (sorted alphabetically): */
struct audit_context;
struct bio_list;
struct blk_plug;
struct bpf_local_storage;
struct bpf_run_ctx;
struct bpf_net_context;
struct capture_control;
struct cfs_rq;
struct fs_struct;
struct futex_pi_state;
struct io_context;
struct io_uring_task;
struct mempolicy;
struct nameidata;
struct nsproxy;
struct perf_event_context;
struct perf_ctx_data;
struct pid_namespace;
struct pipe_inode_info;
struct rcu_node;
struct reclaim_state;
struct robust_list_head;
struct root_domain;
struct rq;
struct sched_attr;
struct sched_dl_entity;
struct seq_file;
struct sighand_struct;
struct signal_struct;
struct task_delay_info;
struct task_group;
struct task_struct;
struct user_event_mm;
#include <linux/sched/ext.h>
/*
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
*
* We have two separate sets of flags: task->__state
* is about runnability, while task->exit_state are
* about the task exiting. Confusing, but this way
* modifying one set can't modify the other one by
* mistake.
*/
/* Used in tsk->__state: */
#define TASK_RUNNING 0x00000000
#define TASK_INTERRUPTIBLE 0x00000001
#define TASK_UNINTERRUPTIBLE 0x00000002
#define __TASK_STOPPED 0x00000004
#define __TASK_TRACED 0x00000008
/* Used in tsk->exit_state: */
#define EXIT_DEAD 0x00000010
#define EXIT_ZOMBIE 0x00000020
#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
/* Used in tsk->__state again: */
#define TASK_PARKED 0x00000040
#define TASK_DEAD 0x00000080
#define TASK_WAKEKILL 0x00000100
#define TASK_WAKING 0x00000200
#define TASK_NOLOAD 0x00000400
#define TASK_NEW 0x00000800
#define TASK_RTLOCK_WAIT 0x00001000
#define TASK_FREEZABLE 0x00002000
#define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP))
#define TASK_FROZEN 0x00008000
#define TASK_STATE_MAX 0x00010000
#define TASK_ANY (TASK_STATE_MAX-1)
/*
* DO NOT ADD ANY NEW USERS !
*/
#define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE)
/* Convenience macros for the sake of set_current_state: */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED __TASK_TRACED
#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
/* Convenience macros for the sake of wake_up(): */
#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
/* get_task_state(): */
#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \
TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
__TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
TASK_PARKED)
#define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING)
#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0)
#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0)
#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0)
/*
* Special states are those that do not use the normal wait-loop pattern. See
* the comment with set_special_state().
*/
#define is_special_task_state(state) \
((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \
TASK_DEAD | TASK_FROZEN))
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
# define debug_normal_state_change(state_value) \
do { \
WARN_ON_ONCE(is_special_task_state(state_value)); \
current->task_state_change = _THIS_IP_; \
} while (0)
# define debug_special_state_change(state_value) \
do { \
WARN_ON_ONCE(!is_special_task_state(state_value)); \
current->task_state_change = _THIS_IP_; \
} while (0)
# define debug_rtlock_wait_set_state() \
do { \
current->saved_state_change = current->task_state_change;\
current->task_state_change = _THIS_IP_; \
} while (0)
# define debug_rtlock_wait_restore_state() \
do { \
current->task_state_change = current->saved_state_change;\
} while (0)
#else
# define debug_normal_state_change(cond) do { } while (0)
# define debug_special_state_change(cond) do { } while (0)
# define debug_rtlock_wait_set_state() do { } while (0)
# define debug_rtlock_wait_restore_state() do { } while (0)
#endif
#define trace_set_current_state(state_value) \
do { \
if (tracepoint_enabled(sched_set_state_tp)) \
__trace_set_current_state(state_value); \
} while (0)
/*
* set_current_state() includes a barrier so that the write of current->__state
* is correctly serialised wrt the caller's subsequent test of whether to
* actually sleep:
*
* for (;;) {
* set_current_state(TASK_UNINTERRUPTIBLE);
* if (CONDITION)
* break;
*
* schedule();
* }
* __set_current_state(TASK_RUNNING);
*
* If the caller does not need such serialisation (because, for instance, the
* CONDITION test and condition change and wakeup are under the same lock) then
* use __set_current_state().
*
* The above is typically ordered against the wakeup, which does:
*
* CONDITION = 1;
* wake_up_state(p, TASK_UNINTERRUPTIBLE);
*
* where wake_up_state()/try_to_wake_up() executes a full memory barrier before
* accessing p->__state.
*
* Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is,
* once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
* TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
*
* However, with slightly different timing the wakeup TASK_RUNNING store can
* also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not
* a problem either because that will result in one extra go around the loop
* and our @cond test will save the day.
*
* Also see the comments of try_to_wake_up().
*/
#define __set_current_state(state_value) \
do { \
debug_normal_state_change((state_value)); \
trace_set_current_state(state_value); \
WRITE_ONCE(current->__state, (state_value)); \
} while (0)
#define set_current_state(state_value) \
do { \
debug_normal_state_change((state_value)); \
trace_set_current_state(state_value); \
smp_store_mb(current->__state, (state_value)); \
} while (0)
/*
* set_special_state() should be used for those states when the blocking task
* can not use the regular condition based wait-loop. In that case we must
* serialize against wakeups such that any possible in-flight TASK_RUNNING
* stores will not collide with our state change.
*/
#define set_special_state(state_value) \
do { \
unsigned long flags; /* may shadow */ \
\
raw_spin_lock_irqsave(¤t->pi_lock, flags); \
debug_special_state_change((state_value)); \
trace_set_current_state(state_value); \
WRITE_ONCE(current->__state, (state_value)); \
raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
} while (0)
/*
* PREEMPT_RT specific variants for "sleeping" spin/rwlocks
*
* RT's spin/rwlock substitutions are state preserving. The state of the
* task when blocking on the lock is saved in task_struct::saved_state and
* restored after the lock has been acquired. These operations are
* serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT
* lock related wakeups while the task is blocked on the lock are
* redirected to operate on task_struct::saved_state to ensure that these
* are not dropped. On restore task_struct::saved_state is set to
* TASK_RUNNING so any wakeup attempt redirected to saved_state will fail.
*
* The lock operation looks like this:
*
* current_save_and_set_rtlock_wait_state();
* for (;;) {
* if (try_lock())
* break;
* raw_spin_unlock_irq(&lock->wait_lock);
* schedule_rtlock();
* raw_spin_lock_irq(&lock->wait_lock);
* set_current_state(TASK_RTLOCK_WAIT);
* }
* current_restore_rtlock_saved_state();
*/
#define current_save_and_set_rtlock_wait_state() \
do { \
lockdep_assert_irqs_disabled(); \
raw_spin_lock(¤t->pi_lock); \
current->saved_state = current->__state; \
debug_rtlock_wait_set_state(); \
trace_set_current_state(TASK_RTLOCK_WAIT); \
WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \
raw_spin_unlock(¤t->pi_lock); \
} while (0);
#define current_restore_rtlock_saved_state() \
do { \
lockdep_assert_irqs_disabled(); \
raw_spin_lock(¤t->pi_lock); \
debug_rtlock_wait_restore_state(); \
trace_set_current_state(current->saved_state); \
WRITE_ONCE(current->__state, current->saved_state); \
current->saved_state = TASK_RUNNING; \
raw_spin_unlock(¤t->pi_lock); \
} while (0);
#define get_current_state() READ_ONCE(current->__state)
/*
* Define the task command name length as enum, then it can be visible to
* BPF programs.
*/
enum {
TASK_COMM_LEN = 16,
};
extern void sched_tick(void);
#define MAX_SCHEDULE_TIMEOUT LONG_MAX
extern long schedule_timeout(long timeout);
extern long schedule_timeout_interruptible(long timeout);
extern long schedule_timeout_killable(long timeout);
extern long schedule_timeout_uninterruptible(long timeout);
extern long schedule_timeout_idle(long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
asmlinkage void preempt_schedule_irq(void);
#ifdef CONFIG_PREEMPT_RT
extern void schedule_rtlock(void);
#endif
extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);
/* wrapper function to trace from this header file */
DECLARE_TRACEPOINT(sched_set_state_tp);
extern void __trace_set_current_state(int state_value);
/**
* struct prev_cputime - snapshot of system and user cputime
* @utime: time spent in user mode
* @stime: time spent in system mode
* @lock: protects the above two fields
*
* Stores previous user/system time values such that we can guarantee
* monotonicity.
*/
struct prev_cputime {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
u64 utime;
u64 stime;
raw_spinlock_t lock;
#endif
};
enum vtime_state {
/* Task is sleeping or running in a CPU with VTIME inactive: */
VTIME_INACTIVE = 0,
/* Task is idle */
VTIME_IDLE,
/* Task runs in kernelspace in a CPU with VTIME active: */
VTIME_SYS,
/* Task runs in userspace in a CPU with VTIME active: */
VTIME_USER,
/* Task runs as guests in a CPU with VTIME active: */
VTIME_GUEST,
};
struct vtime {
seqcount_t seqcount;
unsigned long long starttime;
enum vtime_state state;
unsigned int cpu;
u64 utime;
u64 stime;
u64 gtime;
};
/*
* Utilization clamp constraints.
* @UCLAMP_MIN: Minimum utilization
* @UCLAMP_MAX: Maximum utilization
* @UCLAMP_CNT: Utilization clamp constraints count
*/
enum uclamp_id {
UCLAMP_MIN = 0,
UCLAMP_MAX,
UCLAMP_CNT
};
#ifdef CONFIG_SMP
extern struct root_domain def_root_domain;
extern struct mutex sched_domains_mutex;
extern void sched_domains_mutex_lock(void);
extern void sched_domains_mutex_unlock(void);
#else
static inline void sched_domains_mutex_lock(void) { }
static inline void sched_domains_mutex_unlock(void) { }
#endif
struct sched_param {
int sched_priority;
};
struct sched_info {
#ifdef CONFIG_SCHED_INFO
/* Cumulative counters: */
/* # of times we have run on this CPU: */
unsigned long pcount;
/* Time spent waiting on a runqueue: */
unsigned long long run_delay;
/* Max time spent waiting on a runqueue: */
unsigned long long max_run_delay;
/* Min time spent waiting on a runqueue: */
unsigned long long min_run_delay;
/* Timestamps: */
/* When did we last run on a CPU? */
unsigned long long last_arrival;
/* When were we last queued to run? */
unsigned long long last_queued;
#endif /* CONFIG_SCHED_INFO */
};
/*
* Integer metrics need fixed point arithmetic, e.g., sched/fair
* has a few: load, load_avg, util_avg, freq, and capacity.
*
* We define a basic fixed point arithmetic range, and then formalize
* all these metrics based on that basic range.
*/
# define SCHED_FIXEDPOINT_SHIFT 10
# define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT)
/* Increase resolution of cpu_capacity calculations */
# define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
# define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
struct load_weight {
unsigned long weight;
u32 inv_weight;
};
/*
* The load/runnable/util_avg accumulates an infinite geometric series
* (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
*
* [load_avg definition]
*
* load_avg = runnable% * scale_load_down(load)
*
* [runnable_avg definition]
*
* runnable_avg = runnable% * SCHED_CAPACITY_SCALE
*
* [util_avg definition]
*
* util_avg = running% * SCHED_CAPACITY_SCALE
*
* where runnable% is the time ratio that a sched_entity is runnable and
* running% the time ratio that a sched_entity is running.
*
* For cfs_rq, they are the aggregated values of all runnable and blocked
* sched_entities.
*
* The load/runnable/util_avg doesn't directly factor frequency scaling and CPU
* capacity scaling. The scaling is done through the rq_clock_pelt that is used
* for computing those signals (see update_rq_clock_pelt())
*
* N.B., the above ratios (runnable% and running%) themselves are in the
* range of [0, 1]. To do fixed point arithmetics, we therefore scale them
* to as large a range as necessary. This is for example reflected by
* util_avg's SCHED_CAPACITY_SCALE.
*
* [Overflow issue]
*
* The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
* with the highest load (=88761), always runnable on a single cfs_rq,
* and should not overflow as the number already hits PID_MAX_LIMIT.
*
* For all other cases (including 32-bit kernels), struct load_weight's
* weight will overflow first before we do, because:
*
* Max(load_avg) <= Max(load.weight)
*
* Then it is the load_weight's responsibility to consider overflow
* issues.
*/
struct sched_avg {
u64 last_update_time;
u64 load_sum;
u64 runnable_sum;
u32 util_sum;
u32 period_contrib;
unsigned long load_avg;
unsigned long runnable_avg;
unsigned long util_avg;
unsigned int util_est;
} ____cacheline_aligned;
/*
* The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
* updates. When a task is dequeued, its util_est should not be updated if its
* util_avg has not been updated in the meantime.
* This information is mapped into the MSB bit of util_est at dequeue time.
* Since max value of util_est for a task is 1024 (PELT util_avg for a task)
* it is safe to use MSB.
*/
#define UTIL_EST_WEIGHT_SHIFT 2
#define UTIL_AVG_UNCHANGED 0x80000000
struct sched_statistics {
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
u64 wait_count;
u64 wait_sum;
u64 iowait_count;
u64 iowait_sum;
u64 sleep_start;
u64 sleep_max;
s64 sum_sleep_runtime;
u64 block_start;
u64 block_max;
s64 sum_block_runtime;
s64 exec_max;
u64 slice_max;
u64 nr_migrations_cold;
u64 nr_failed_migrations_affine;
u64 nr_failed_migrations_running;
u64 nr_failed_migrations_hot;
u64 nr_forced_migrations;
u64 nr_wakeups;
u64 nr_wakeups_sync;
u64 nr_wakeups_migrate;
u64 nr_wakeups_local;
u64 nr_wakeups_remote;
u64 nr_wakeups_affine;
u64 nr_wakeups_affine_attempts;
u64 nr_wakeups_passive;
u64 nr_wakeups_idle;
#ifdef CONFIG_SCHED_CORE
u64 core_forceidle_sum;
#endif
#endif /* CONFIG_SCHEDSTATS */
} ____cacheline_aligned;
struct sched_entity {
/* For load-balancing: */
struct load_weight load;
struct rb_node run_node;
u64 deadline;
u64 min_vruntime;
u64 min_slice;
struct list_head group_node;
unsigned char on_rq;
unsigned char sched_delayed;
unsigned char rel_deadline;
unsigned char custom_slice;
/* hole */
u64 exec_start;
u64 sum_exec_runtime;
u64 prev_sum_exec_runtime;
u64 vruntime;
s64 vlag;
u64 slice;
u64 nr_migrations;
#ifdef CONFIG_FAIR_GROUP_SCHED
int depth;
struct sched_entity *parent;
/* rq on which this entity is (to be) queued: */
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
/* cached value of my_q->h_nr_running */
unsigned long runnable_weight;
#endif
#ifdef CONFIG_SMP
/*
* Per entity load average tracking.
*
* Put into separate cache line so it does not
* collide with read-mostly values above.
*/
struct sched_avg avg;
#endif
};
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
unsigned long watchdog_stamp;
unsigned int time_slice;
unsigned short on_rq;
unsigned short on_list;
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
struct sched_rt_entity *parent;
/* rq on which this entity is (to be) queued: */
struct rt_rq *rt_rq;
/* rq "owned" by this entity/group: */
struct rt_rq *my_q;
#endif
} __randomize_layout;
typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
struct sched_dl_entity {
struct rb_node rb_node;
/*
* Original scheduling parameters. Copied here from sched_attr
* during sched_setattr(), they will remain the same until
* the next sched_setattr().
*/
u64 dl_runtime; /* Maximum runtime for each instance */
u64 dl_deadline; /* Relative deadline of each instance */
u64 dl_period; /* Separation of two instances (period) */
u64 dl_bw; /* dl_runtime / dl_period */
u64 dl_density; /* dl_runtime / dl_deadline */
/*
* Actual scheduling parameters. Initialized with the values above,
* they are continuously updated during task execution. Note that
* the remaining runtime could be < 0 in case we are in overrun.
*/
s64 runtime; /* Remaining runtime for this instance */
u64 deadline; /* Absolute deadline for this instance */
unsigned int flags; /* Specifying the scheduler behaviour */
/*
* Some bool flags:
*
* @dl_throttled tells if we exhausted the runtime. If so, the
* task has to wait for a replenishment to be performed at the
* next firing of dl_timer.
*
* @dl_yielded tells if task gave up the CPU before consuming
* all its available runtime during the last job.
*
* @dl_non_contending tells if the task is inactive while still
* contributing to the active utilization. In other words, it
* indicates if the inactive timer has been armed and its handler
* has not been executed yet. This flag is useful to avoid race
* conditions between the inactive timer handler and the wakeup
* code.
*
* @dl_overrun tells if the task asked to be informed about runtime
* overruns.
*
* @dl_server tells if this is a server entity.
*
* @dl_defer tells if this is a deferred or regular server. For
* now only defer server exists.
*
* @dl_defer_armed tells if the deferrable server is waiting
* for the replenishment timer to activate it.
*
* @dl_server_active tells if the dlserver is active(started).
* dlserver is started on first cfs enqueue on an idle runqueue
* and is stopped when a dequeue results in 0 cfs tasks on the
* runqueue. In other words, dlserver is active only when cpu's
* runqueue has atleast one cfs task.
*
* @dl_defer_running tells if the deferrable server is actually
* running, skipping the defer phase.
*/
unsigned int dl_throttled : 1;
unsigned int dl_yielded : 1;
unsigned int dl_non_contending : 1;
unsigned int dl_overrun : 1;
unsigned int dl_server : 1;
unsigned int dl_server_active : 1;
unsigned int dl_defer : 1;
unsigned int dl_defer_armed : 1;
unsigned int dl_defer_running : 1;
/*
* Bandwidth enforcement timer. Each -deadline task has its
* own bandwidth to be enforced, thus we need one timer per task.
*/
struct hrtimer dl_timer;
/*
* Inactive timer, responsible for decreasing the active utilization
* at the "0-lag time". When a -deadline task blocks, it contributes
* to GRUB's active utilization until the "0-lag time", hence a
* timer is needed to decrease the active utilization at the correct
* time.
*/
struct hrtimer inactive_timer;
/*
* Bits for DL-server functionality. Also see the comment near
* dl_server_update().
*
* @rq the runqueue this server is for
*
* @server_has_tasks() returns true if @server_pick return a
* runnable task.
*/
struct rq *rq;
dl_server_has_tasks_f server_has_tasks;
dl_server_pick_f server_pick_task;
#ifdef CONFIG_RT_MUTEXES
/*
* Priority Inheritance. When a DEADLINE scheduling entity is boosted
* pi_se points to the donor, otherwise points to the dl_se it belongs
* to (the original one/itself).
*/
struct sched_dl_entity *pi_se;
#endif
};
#ifdef CONFIG_UCLAMP_TASK
/* Number of utilization clamp buckets (shorter alias) */
#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT
/*
* Utilization clamp for a scheduling entity
* @value: clamp value "assigned" to a se
* @bucket_id: bucket index corresponding to the "assigned" value
* @active: the se is currently refcounted in a rq's bucket
* @user_defined: the requested clamp value comes from user-space
*
* The bucket_id is the index of the clamp bucket matching the clamp value
* which is pre-computed and stored to avoid expensive integer divisions from
* the fast path.
*
* The active bit is set whenever a task has got an "effective" value assigned,
* which can be different from the clamp value "requested" from user-space.
* This allows to know a task is refcounted in the rq's bucket corresponding
* to the "effective" bucket_id.
*
* The user_defined bit is set whenever a task has got a task-specific clamp
* value requested from userspace, i.e. the system defaults apply to this task
* just as a restriction. This allows to relax default clamps when a less
* restrictive task-specific value has been requested, thus allowing to
* implement a "nice" semantic. For example, a task running with a 20%
* default boost can still drop its own boosting to 0%.
*/
struct uclamp_se {
unsigned int value : bits_per(SCHED_CAPACITY_SCALE);
unsigned int bucket_id : bits_per(UCLAMP_BUCKETS);
unsigned int active : 1;
unsigned int user_defined : 1;
};
#endif /* CONFIG_UCLAMP_TASK */
union rcu_special {
struct {
u8 blocked;
u8 need_qs;
u8 exp_hint; /* Hint for performance. */
u8 need_mb; /* Readers need smp_mb(). */
} b; /* Bits. */
u32 s; /* Set of bits. */
};
enum perf_event_task_context {
perf_invalid_context = -1,
perf_hw_context = 0,
perf_sw_context,
perf_nr_task_contexts,
};
/*
* Number of contexts where an event can trigger:
* task, softirq, hardirq, nmi.
*/
#define PERF_NR_CONTEXTS 4
struct wake_q_node {
struct wake_q_node *next;
};
struct kmap_ctrl {
#ifdef CONFIG_KMAP_LOCAL
int idx;
pte_t pteval[KM_MAX_IDX];
#endif
};
struct task_struct {
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
* For reasons of header soup (see current_thread_info()), this
* must be the first element of task_struct.
*/
struct thread_info thread_info;
#endif
unsigned int __state;
/* saved state for "spinlock sleepers" */
unsigned int saved_state;
/*
* This begins the randomizable portion of task_struct. Only
* scheduling-critical items should be added above here.
*/
randomized_struct_fields_start
void *stack;
refcount_t usage;
/* Per task flags (PF_*), defined further below: */
unsigned int flags;
unsigned int ptrace;
#ifdef CONFIG_MEM_ALLOC_PROFILING
struct alloc_tag *alloc_tag;
#endif
#ifdef CONFIG_SMP
int on_cpu;
struct __call_single_node wake_entry;
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
/*
* recent_used_cpu is initially set as the last CPU used by a task
* that wakes affine another task. Waker/wakee relationships can
* push tasks around a CPU where each wakeup moves to the next one.
* Tracking a recently used CPU allows a quick search for a recently
* used CPU that may be idle.
*/
int recent_used_cpu;
int wake_cpu;
#endif
int on_rq;
int prio;
int static_prio;
int normal_prio;
unsigned int rt_priority;
struct sched_entity se;
struct sched_rt_entity rt;
struct sched_dl_entity dl;
struct sched_dl_entity *dl_server;
#ifdef CONFIG_SCHED_CLASS_EXT
struct sched_ext_entity scx;
#endif
const struct sched_class *sched_class;
#ifdef CONFIG_SCHED_CORE
struct rb_node core_node;
unsigned long core_cookie;
unsigned int core_occupation;
#endif
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
#ifdef CONFIG_UCLAMP_TASK
/*
* Clamp values requested for a scheduling entity.
* Must be updated with task_rq_lock() held.
*/
struct uclamp_se uclamp_req[UCLAMP_CNT];
/*
* Effective clamp values used for a scheduling entity.
* Must be updated with task_rq_lock() held.
*/
struct uclamp_se uclamp[UCLAMP_CNT];
#endif
struct sched_statistics stats;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* List of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
#endif
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned int policy;
unsigned long max_allowed_capacity;
int nr_cpus_allowed;
const cpumask_t *cpus_ptr;
cpumask_t *user_cpus_ptr;
cpumask_t cpus_mask;
void *migration_pending;
#ifdef CONFIG_SMP
unsigned short migration_disabled;
#endif
unsigned short migration_flags;
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
union rcu_special rcu_read_unlock_special;
struct list_head rcu_node_entry;
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
unsigned long rcu_tasks_nvcsw;
u8 rcu_tasks_holdout;
u8 rcu_tasks_idx;
int rcu_tasks_idle_cpu;
struct list_head rcu_tasks_holdout_list;
int rcu_tasks_exit_cpu;
struct list_head rcu_tasks_exit_list;
#endif /* #ifdef CONFIG_TASKS_RCU */
#ifdef CONFIG_TASKS_TRACE_RCU
int trc_reader_nesting;
int trc_ipi_to_cpu;
union rcu_special trc_reader_special;
struct list_head trc_holdout_list;
struct list_head trc_blkd_node;
int trc_blkd_cpu;
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
struct sched_info sched_info;
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
#endif
struct mm_struct *mm;
struct mm_struct *active_mm;
struct address_space *faults_disabled_mapping;
int exit_state;
int exit_code;
int exit_signal;
/* The signal sent when the parent dies: */
int pdeath_signal;
/* JOBCTL_*, siglock protected: */
unsigned long jobctl;
/* Used for emulating ABI behavior of previous Linux versions: */
unsigned int personality;
/* Scheduler bits, serialized by scheduler locks: */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_task_hot:1;
/* Force alignment to the next boundary: */
unsigned :0;
/* Unserialized, strictly 'current' */
/*
* This field must not be in the scheduler word above due to wakelist
* queueing no longer being serialized by p->on_cpu. However:
*
* p->XXX = X; ttwu()
* schedule() if (p->on_rq && ..) // false
* smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true
* deactivate_task() ttwu_queue_wakelist())
* p->on_rq = 0; p->sched_remote_wakeup = Y;
*
* guarantees all stores of 'current' are visible before
* ->sched_remote_wakeup gets used, so it can be in this word.
*/
unsigned sched_remote_wakeup:1;
#ifdef CONFIG_RT_MUTEXES
unsigned sched_rt_mutex:1;
#endif
/* Bit to tell TOMOYO we're in execve(): */
unsigned in_execve:1;
unsigned in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG_V1
unsigned in_user_fault:1;
#endif
#ifdef CONFIG_LRU_GEN
/* whether the LRU algorithm may apply to this access */
unsigned in_lru_fault:1;
#endif
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
#ifdef CONFIG_CGROUPS
/* disallow userland-initiated cgroup migration */
unsigned no_cgroup_migration:1;
/* task is frozen/stopped (used by the cgroup freezer) */
unsigned frozen:1;
#endif
#ifdef CONFIG_BLK_CGROUP
unsigned use_memdelay:1;
#endif
#ifdef CONFIG_PSI
/* Stalled due to lack of memory */
unsigned in_memstall:1;
#endif
#ifdef CONFIG_PAGE_OWNER
/* Used by page_owner=on to detect recursion in page tracking. */
unsigned in_page_owner:1;
#endif
#ifdef CONFIG_EVENTFD
/* Recursion prevention for eventfd_signal() */
unsigned in_eventfd:1;
#endif
#ifdef CONFIG_ARCH_HAS_CPU_PASID
unsigned pasid_activated:1;
#endif
#ifdef CONFIG_X86_BUS_LOCK_DETECT
unsigned reported_split_lock:1;
#endif
#ifdef CONFIG_TASK_DELAY_ACCT
/* delay due to memory thrashing */
unsigned in_thrashing:1;
#endif
#ifdef CONFIG_PREEMPT_RT
struct netdev_xmit net_xmit;
#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
struct restart_block restart_block;
pid_t pid;
pid_t tgid;
#ifdef CONFIG_STACKPROTECTOR
/* Canary value for the -fstack-protector GCC feature: */
unsigned long stack_canary;
#endif
/*
* Pointers to the (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
/* Real parent process: */
struct task_struct __rcu *real_parent;
/* Recipient of SIGCHLD, wait4() reports: */
struct task_struct __rcu *parent;
/*
* Children/sibling form the list of natural children:
*/
struct list_head children;
struct list_head sibling;
struct task_struct *group_leader;
/*
* 'ptraced' is the list of tasks this task is using ptrace() on.
*
* This includes both natural children and PTRACE_ATTACH targets.
* 'ptrace_entry' is this task's link on the p->parent->ptraced list.
*/
struct list_head ptraced;
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid *thread_pid;
struct hlist_node pid_links[PIDTYPE_MAX];
struct list_head thread_node;
struct completion *vfork_done;
/* CLONE_CHILD_SETTID: */
int __user *set_child_tid;
/* CLONE_CHILD_CLEARTID: */
int __user *clear_child_tid;
/* PF_KTHREAD | PF_IO_WORKER */
void *worker_private;
u64 utime;
u64 stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
u64 utimescaled;
u64 stimescaled;
#endif
u64 gtime;
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
/* Context switch counts: */
unsigned long nvcsw;
unsigned long nivcsw;
/* Monotonic time in nsecs: */
u64 start_time;
/* Boot based time in nsecs: */
u64 start_boottime;
/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
unsigned long min_flt;
unsigned long maj_flt;
/* Empty if CONFIG_POSIX_CPUTIMERS=n */
struct posix_cputimers posix_cputimers;
#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
struct posix_cputimers_work posix_cputimers_work;
#endif
/* Process credentials: */
/* Tracer's credentials at attach: */
const struct cred __rcu *ptracer_cred;
/* Objective and real subjective task credentials (COW): */
const struct cred __rcu *real_cred;
/* Effective (overridable) subjective task credentials (COW): */
const struct cred __rcu *cred;
#ifdef CONFIG_KEYS
/* Cached requested key. */
struct key *cached_requested_key;
#endif
/*
* executable name, excluding path.
*
* - normally initialized begin_new_exec()
* - set it with set_task_comm()
* - strscpy_pad() to ensure it is always NUL-terminated and
* zero-padded
* - task_lock() to ensure the operation is atomic and the name is
* fully updated.
*/
char comm[TASK_COMM_LEN];
struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
struct sysv_sem sysvsem;
struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
unsigned long last_switch_count;
unsigned long last_switch_time;
#endif
/* Filesystem information: */
struct fs_struct *fs;
/* Open file information: */
struct files_struct *files;
#ifdef CONFIG_IO_URING
struct io_uring_task *io_uring;
#endif
/* Namespaces: */
struct nsproxy *nsproxy;
/* Signal handlers: */
struct signal_struct *signal;
struct sighand_struct __rcu *sighand;
sigset_t blocked;
sigset_t real_blocked;
/* Restored if set_restore_sigmask() was used: */
sigset_t saved_sigmask;
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
unsigned int sas_ss_flags;
struct callback_head *task_works;
#ifdef CONFIG_AUDIT
#ifdef CONFIG_AUDITSYSCALL
struct audit_context *audit_context;
#endif
kuid_t loginuid;
unsigned int sessionid;
#endif
struct seccomp seccomp;
struct syscall_user_dispatch syscall_dispatch;
/* Thread group tracking: */
u64 parent_exec_id;
u64 self_exec_id;
/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
spinlock_t alloc_lock;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
struct wake_q_node wake_q;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task: */
struct rb_root_cached pi_waiters;
/* Updated under owner's pi_lock and rq lock */
struct task_struct *pi_top_task;
/* Deadlock detection and priority inheritance handling: */
struct rt_mutex_waiter *pi_blocked_on;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* Mutex deadlock detection: */
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
struct mutex *blocker_mutex;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
int non_block_count;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
struct irqtrace_events irqtrace;
unsigned int hardirq_threaded;
u64 hardirq_chain_key;
int softirqs_enabled;
int softirq_context;
int irq_config;
#endif
#ifdef CONFIG_PREEMPT_RT
int softirq_disable_cnt;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
u64 curr_chain_key;
int lockdep_depth;
unsigned int lockdep_recursion;
struct held_lock held_locks[MAX_LOCK_DEPTH];
#endif
#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
unsigned int in_ubsan;
#endif
/* Journalling filesystem info: */
void *journal_info;
/* Stacked block device info: */
struct bio_list *bio_list;
/* Stack plugging: */
struct blk_plug *plug;
/* VM state: */
struct reclaim_state *reclaim_state;
struct io_context *io_context;
#ifdef CONFIG_COMPACTION
struct capture_control *capture_control;
#endif
/* Ptrace state: */
unsigned long ptrace_message;
kernel_siginfo_t *last_siginfo;
struct task_io_accounting ioac;
#ifdef CONFIG_PSI
/* Pressure stall state */
unsigned int psi_flags;
#endif
#ifdef CONFIG_TASK_XACCT
/* Accumulated RSS usage: */
u64 acct_rss_mem1;
/* Accumulated virtual memory usage: */
u64 acct_vm_mem1;
/* stime + utime since last update: */
u64 acct_timexpd;
#endif
#ifdef CONFIG_CPUSETS
/* Protected by ->alloc_lock: */
nodemask_t mems_allowed;
/* Sequence number to catch updates: */
seqcount_spinlock_t mems_allowed_seq;
int cpuset_mem_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock: */
struct css_set __rcu *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock: */
struct list_head cg_list;
#endif
#ifdef CONFIG_X86_CPU_RESCTRL
u32 closid;
u32 rmid;
#endif
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
struct mutex futex_exit_mutex;
unsigned int futex_state;
#endif
#ifdef CONFIG_PERF_EVENTS
u8 perf_recursion[PERF_NR_CONTEXTS];
struct perf_event_context *perf_event_ctxp;
struct mutex perf_event_mutex;
struct list_head perf_event_list;
struct perf_ctx_data __rcu *perf_ctx_data;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
unsigned long preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
/* Protected by alloc_lock: */
struct mempolicy *mempolicy;
short il_prev;
u8 il_weight;
short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
int numa_scan_seq;
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
int numa_preferred_nid;
unsigned long numa_migrate_retry;
/* Migration stamp: */
u64 node_stamp;
u64 last_task_numa_placement;
u64 last_sum_exec_runtime;
struct callback_head numa_work;
/*
* This pointer is only modified for current in syscall and
* pagefault context (and for tasks being destroyed), so it can be read
* from any of the following contexts:
* - RCU read-side critical section
* - current->numa_group from everywhere
* - task's runqueue locked, task not running
*/
struct numa_group __rcu *numa_group;
/*
* numa_faults is an array split into four regions:
* faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
* in this precise order.
*
* faults_memory: Exponential decaying average of faults on a per-node
* basis. Scheduling placement decisions are made based on these
* counts. The values remain static for the duration of a PTE scan.
* faults_cpu: Track the nodes the process was running on when a NUMA
* hinting fault was incurred.
* faults_memory_buffer and faults_cpu_buffer: Record faults per node
* during the current scan window. When the scan completes, the counts
* in faults_memory and faults_cpu decay and these values are copied.
*/
unsigned long *numa_faults;
unsigned long total_numa_faults;
/*
* numa_faults_locality tracks if faults recorded during the last
* scan window were remote/local or failed to migrate. The task scan
* period is adapted based on the locality of the faults with different
* weights depending on whether they were shared or private faults
*/
unsigned long numa_faults_locality[3];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_RSEQ
struct rseq __user *rseq;
u32 rseq_len;
u32 rseq_sig;
/*
* RmW on rseq_event_mask must be performed atomically
* with respect to preemption.
*/
unsigned long rseq_event_mask;
# ifdef CONFIG_DEBUG_RSEQ
/*
* This is a place holder to save a copy of the rseq fields for
* validation of read-only fields. The struct rseq has a
* variable-length array at the end, so it cannot be used
* directly. Reserve a size large enough for the known fields.
*/
char rseq_fields[sizeof(struct rseq)];
# endif
#endif
#ifdef CONFIG_SCHED_MM_CID
int mm_cid; /* Current cid in mm */
int last_mm_cid; /* Most recent cid in mm */
int migrate_from_cpu;
int mm_cid_active; /* Whether cid bitmap is active */
struct callback_head cid_work;
#endif
struct tlbflush_unmap_batch tlb_ubc;
/* Cache last used pipe for splice(): */
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
unsigned int fail_nth;
#endif
/*
* When (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for a dirty throttling pause:
*/
int nr_dirtied;
int nr_dirtied_pause;
/* Start of a write-and-pause period: */
unsigned long dirty_paused_when;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
/*
* Time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
*/
u64 timer_slack_ns;
u64 default_timer_slack_ns;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
unsigned int kasan_depth;
#endif
#ifdef CONFIG_KCSAN
struct kcsan_ctx kcsan_ctx;
#ifdef CONFIG_TRACE_IRQFLAGS
struct irqtrace_events kcsan_save_irqtrace;
#endif
#ifdef CONFIG_KCSAN_WEAK_MEMORY
int kcsan_stack_depth;
#endif
#endif
#ifdef CONFIG_KMSAN
struct kmsan_ctx kmsan_ctx;
#endif
#if IS_ENABLED(CONFIG_KUNIT)
struct kunit *kunit_test;
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* Index of current stored address in ret_stack: */
int curr_ret_stack;
int curr_ret_depth;
/* Stack of return addresses for return function tracing: */
unsigned long *ret_stack;
/* Timestamp for last schedule: */
unsigned long long ftrace_timestamp;
unsigned long long ftrace_sleeptime;
/*
* Number of functions that haven't been traced
* because of depth overrun:
*/
atomic_t trace_overrun;
/* Pause tracing: */
atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
/* Bitmask and counter of trace recursion: */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_KCOV
/* See kernel/kcov.c for more details. */
/* Coverage collection mode enabled for this task (0 if disabled): */
unsigned int kcov_mode;
/* Size of the kcov_area: */
unsigned int kcov_size;
/* Buffer for coverage collection: */
void *kcov_area;
/* KCOV descriptor wired with this task or NULL: */
struct kcov *kcov;
/* KCOV common handle for remote coverage collection: */
u64 kcov_handle;
/* KCOV sequence number: */
int kcov_sequence;
/* Collect coverage from softirq context: */
unsigned int kcov_softirq;
#endif
#ifdef CONFIG_MEMCG_V1
struct mem_cgroup *memcg_in_oom;
#endif
#ifdef CONFIG_MEMCG
/* Number of pages to reclaim on returning to userland: */
unsigned int memcg_nr_pages_over_high;
/* Used by memcontrol for targeted memcg charge: */
struct mem_cgroup *active_memcg;
/* Cache for current->cgroups->memcg->objcg lookups: */
struct obj_cgroup *objcg;
#endif
#ifdef CONFIG_BLK_CGROUP
struct gendisk *throttle_disk;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
unsigned int sequential_io;
unsigned int sequential_io_avg;
#endif
struct kmap_ctrl kmap_ctrl;
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
# ifdef CONFIG_PREEMPT_RT
unsigned long saved_state_change;
# endif
#endif
struct rcu_head rcu;
refcount_t rcu_users;
int pagefault_disabled;
#ifdef CONFIG_MMU
struct task_struct *oom_reaper_list;
struct timer_list oom_reaper_timer;
#endif
#ifdef CONFIG_VMAP_STACK
struct vm_struct *stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* A live task holds one reference: */
refcount_t stack_refcount;
#endif
#ifdef CONFIG_LIVEPATCH
int patch_state;
#endif
#ifdef CONFIG_SECURITY
/* Used by LSM modules for access restriction: */
void *security;
#endif
#ifdef CONFIG_BPF_SYSCALL
/* Used by BPF task local storage */
struct bpf_local_storage __rcu *bpf_storage;
/* Used for BPF run context */
struct bpf_run_ctx *bpf_ctx;
#endif
/* Used by BPF for per-TASK xdp storage */
struct bpf_net_context *bpf_net_context;
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
unsigned long lowest_stack;
unsigned long prev_lowest_stack;
#endif
#ifdef CONFIG_X86_MCE
void __user *mce_vaddr;
__u64 mce_kflags;
u64 mce_addr;
__u64 mce_ripv : 1,
mce_whole_page : 1,
__mce_reserved : 62;
struct callback_head mce_kill_me;
int mce_count;
#endif
#ifdef CONFIG_KRETPROBES
struct llist_head kretprobe_instances;
#endif
#ifdef CONFIG_RETHOOK
struct llist_head rethooks;
#endif
#ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH
/*
* If L1D flush is supported on mm context switch
* then we use this callback head to queue kill work
* to kill tasks that are not running on SMT disabled
* cores
*/
struct callback_head l1d_flush_kill;
#endif
#ifdef CONFIG_RV
/*
* Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS.
* If we find justification for more monitors, we can think
* about adding more or developing a dynamic method. So far,
* none of these are justified.
*/
union rv_task_monitor rv[RV_PER_TASK_MONITORS];
#endif
#ifdef CONFIG_USER_EVENTS
struct user_event_mm *user_event_mm;
#endif
/*
* New fields for task_struct should be added above here, so that
* they are included in the randomized portion of task_struct.
*/
randomized_struct_fields_end
/* CPU-specific state of this task: */
struct thread_struct thread;
/*
* WARNING: on x86, 'thread_struct' contains a variable-sized
* structure. It *MUST* be at the end of 'task_struct'.
*
* Do not put anything below here!
*/
};
#define TASK_REPORT_IDLE (TASK_REPORT + 1)
#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
static inline unsigned int __task_state_index(unsigned int tsk_state,
unsigned int tsk_exit_state)
{
unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
if ((tsk_state & TASK_IDLE) == TASK_IDLE)
state = TASK_REPORT_IDLE;
/*
* We're lying here, but rather than expose a completely new task state
* to userspace, we can make this appear as if the task has gone through
* a regular rt_mutex_lock() call.
* Report frozen tasks as uninterruptible.
*/
if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN))
state = TASK_UNINTERRUPTIBLE;
return fls(state);
}
static inline unsigned int task_state_index(struct task_struct *tsk)
{
return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
}
static inline char task_index_to_char(unsigned int state)
{
static const char state_char[] = "RSDTtXZPI";
BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1));
return state_char[state];
}
static inline char task_state_to_char(struct task_struct *tsk)
{
return task_index_to_char(task_state_index(tsk));
}
extern struct pid *cad_pid;
/*
* Per process flags
*/
#define PF_VCPU 0x00000001 /* I'm a virtual CPU */
#define PF_IDLE 0x00000002 /* I am an IDLE thread */
#define PF_EXITING 0x00000004 /* Getting shut down */
#define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */
#define PF_IO_WORKER 0x00000010 /* Task is an IO worker */
#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */
#define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */
#define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */
#define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* Dumped core */
#define PF_SIGNALED 0x00000400 /* Killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */
#define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */
#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */
#define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */
#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */
#define PF_KSWAPD 0x00020000 /* I am kswapd */
#define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
#define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */
#define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to,
* I am cleaning dirty pages from some other bdi. */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */
#define PF__HOLE__00800000 0x00800000
#define PF__HOLE__01000000 0x01000000
#define PF__HOLE__02000000 0x02000000
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning.
* See memalloc_pin_save() */
#define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */
#define PF__HOLE__40000000 0x40000000
#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
/*
* Only the _current_ task can read/write to tsk->flags, but other
* tasks can access tsk->flags in readonly mode for example
* with tsk_used_math (like during threaded core dumping).
* There is however an exception to this rule during ptrace
* or during fork: the ptracer task is allowed to write to the
* child->flags of its traced child (same goes for fork, the parent
* can write to the child->flags), because we're guaranteed the
* child is not running and in turn not changing child->flags
* at the same time the parent does it.
*/
#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math() clear_stopped_child_used_math(current)
#define set_used_math() set_stopped_child_used_math(current)
#define conditional_stopped_child_used_math(condition, child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
#define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current)
#define copy_to_stopped_child_used_math(child) \
do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
static __always_inline bool is_percpu_thread(void)
{
#ifdef CONFIG_SMP
return (current->flags & PF_NO_SETAFFINITY) &&
(current->nr_cpus_allowed == 1);
#else
return true;
#endif
}
/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */
#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */
#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */
#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/
#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */
#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */
#define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */
#define TASK_PFA_TEST(name, func) \
static inline bool task_##func(struct task_struct *p) \
{ return test_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_SET(name, func) \
static inline void task_set_##func(struct task_struct *p) \
{ set_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_CLEAR(name, func) \
static inline void task_clear_##func(struct task_struct *p) \
{ clear_bit(PFA_##name, &p->atomic_flags); }
TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)
TASK_PFA_TEST(SPREAD_PAGE, spread_page)
TASK_PFA_SET(SPREAD_PAGE, spread_page)
TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)
TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec)
TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec)
TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec)
TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
static inline void
current_restore_flags(unsigned long orig_flags, unsigned long flags)
{
current->flags &= ~flags;
current->flags |= orig_flags & flags;
}
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p);
extern int dl_bw_alloc(int cpu, u64 dl_bw);
extern void dl_bw_free(int cpu, u64 dl_bw);
#ifdef CONFIG_SMP
/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
/**
* set_cpus_allowed_ptr - set CPU affinity mask of a task
* @p: the task
* @new_mask: CPU affinity mask
*
* Return: zero if successful, or a negative error code
*/
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node);
extern void release_user_cpus_ptr(struct task_struct *p);
extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask);
extern void force_compatible_cpus_allowed_ptr(struct task_struct *p);
extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p);
#else
static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
}
static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
/* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */
if ((*cpumask_bits(new_mask) & 1) == 0)
return -EINVAL;
return 0;
}
static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
{
if (src->user_cpus_ptr)
return -EINVAL;
return 0;
}
static inline void release_user_cpus_ptr(struct task_struct *p)
{
WARN_ON(p->user_cpus_ptr);
}
static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
{
return 0;
}
#endif
extern int yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
/**
* task_nice - return the nice value of a given task.
* @p: the task in question.
*
* Return: The nice value [ -20 ... 0 ... 19 ].
*/
static inline int task_nice(const struct task_struct *p)
{
return PRIO_TO_NICE((p)->static_prio);
}
extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
extern int available_idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
extern void sched_set_fifo(struct task_struct *p);
extern void sched_set_fifo_low(struct task_struct *p);
extern void sched_set_normal(struct task_struct *p, int nice);
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);
/**
* is_idle_task - is the specified task an idle task?
* @p: the task in question.
*
* Return: 1 if @p is an idle task. 0 otherwise.
*/
static __always_inline bool is_idle_task(const struct task_struct *p)
{
return !!(p->flags & PF_IDLE);
}
extern struct task_struct *curr_task(int cpu);
extern void ia64_set_curr_task(int cpu, struct task_struct *p);
void yield(void);
union thread_union {
struct task_struct task;
#ifndef CONFIG_THREAD_INFO_IN_TASK
struct thread_info thread_info;
#endif
unsigned long stack[THREAD_SIZE/sizeof(long)];
};
#ifndef CONFIG_THREAD_INFO_IN_TASK
extern struct thread_info init_thread_info;
#endif
extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];
#ifdef CONFIG_THREAD_INFO_IN_TASK
# define task_thread_info(task) (&(task)->thread_info)
#else
# define task_thread_info(task) ((struct thread_info *)(task)->stack)
#endif
/*
* find a task by one of its numerical ids
*
* find_task_by_pid_ns():
* finds a task by its pid in the specified namespace
* find_task_by_vpid():
* finds a task by its virtual pid
*
* see also find_vpid() etc in include/linux/pid.h
*/
extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns);
/*
* find a task by its virtual pid and get the task struct
*/
extern struct task_struct *find_get_task_by_vpid(pid_t nr);
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk);
#ifdef CONFIG_SMP
extern void kick_process(struct task_struct *tsk);
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
#define set_task_comm(tsk, from) ({ \
BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \
__set_task_comm(tsk, from, false); \
})
/*
* - Why not use task_lock()?
* User space can randomly change their names anyway, so locking for readers
* doesn't make sense. For writers, locking is probably necessary, as a race
* condition could lead to long-term mixed results.
* The strscpy_pad() in __set_task_comm() can ensure that the task comm is
* always NUL-terminated and zero-padded. Therefore the race condition between
* reader and writer is not an issue.
*
* - BUILD_BUG_ON() can help prevent the buf from being truncated.
* Since the callers don't perform any return value checks, this safeguard is
* necessary.
*/
#define get_task_comm(buf, tsk) ({ \
BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \
strscpy_pad(buf, (tsk)->comm); \
buf; \
})
#ifdef CONFIG_SMP
static __always_inline void scheduler_ipi(void)
{
/*
* Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
* TIF_NEED_RESCHED remotely (for the first time) will also send
* this IPI.
*/
preempt_fold_need_resched();
}
#else
static inline void scheduler_ipi(void) { }
#endif
extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state);
/*
* Set thread flags in other task's structures.
* See asm/thread_info.h for TIF_xxxx flags available:
*/
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
set_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
clear_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag,
bool value)
{
update_ti_thread_flag(task_thread_info(tsk), flag, value);
}
static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
return test_ti_thread_flag(task_thread_info(tsk), flag);
}
static inline void set_tsk_need_resched(struct task_struct *tsk)
{
set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY,
(atomic_long_t *)&task_thread_info(tsk)->flags);
}
static inline int test_tsk_need_resched(struct task_struct *tsk)
{
return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}
/*
* cond_resched() and cond_resched_lock(): latency reduction via
* explicit rescheduling in places that are safe. The return
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
*/
#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
extern int __cond_resched(void);
#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
void sched_dynamic_klp_enable(void);
void sched_dynamic_klp_disable(void);
DECLARE_STATIC_CALL(cond_resched, __cond_resched);
static __always_inline int _cond_resched(void)
{
return static_call_mod(cond_resched)();
}
#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
extern int dynamic_cond_resched(void);
static __always_inline int _cond_resched(void)
{
return dynamic_cond_resched();
}
#else /* !CONFIG_PREEMPTION */
static inline int _cond_resched(void)
{
klp_sched_try_switch();
return __cond_resched();
}
#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */
static inline int _cond_resched(void)
{
klp_sched_try_switch();
return 0;
}
#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */
#define cond_resched() ({ \
__might_resched(__FILE__, __LINE__, 0); \
_cond_resched(); \
})
extern int __cond_resched_lock(spinlock_t *lock);
extern int __cond_resched_rwlock_read(rwlock_t *lock);
extern int __cond_resched_rwlock_write(rwlock_t *lock);
#define MIGHT_RESCHED_RCU_SHIFT 8
#define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1)
#ifndef CONFIG_PREEMPT_RT
/*
* Non RT kernels have an elevated preempt count due to the held lock,
* but are not allowed to be inside a RCU read side critical section
*/
# define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET
#else
/*
* spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in
* cond_resched*lock() has to take that into account because it checks for
* preempt_count() and rcu_preempt_depth().
*/
# define PREEMPT_LOCK_RESCHED_OFFSETS \
(PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT))
#endif
#define cond_resched_lock(lock) ({ \
__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \
__cond_resched_lock(lock); \
})
#define cond_resched_rwlock_read(lock) ({ \
__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \
__cond_resched_rwlock_read(lock); \
})
#define cond_resched_rwlock_write(lock) ({ \
__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \
__cond_resched_rwlock_write(lock); \
})
static __always_inline bool need_resched(void)
{
return unlikely(tif_need_resched());
}
/*
* Wrappers for p->thread_info->cpu access. No-op on UP.
*/
#ifdef CONFIG_SMP
static inline unsigned int task_cpu(const struct task_struct *p)
{
return READ_ONCE(task_thread_info(p)->cpu);
}
extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
#else
static inline unsigned int task_cpu(const struct task_struct *p)
{
return 0;
}
static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
}
#endif /* CONFIG_SMP */
static inline bool task_is_runnable(struct task_struct *p)
{
return p->on_rq && !p->se.sched_delayed;
}
extern bool sched_task_on_rq(struct task_struct *p);
extern unsigned long get_wchan(struct task_struct *p);
extern struct task_struct *cpu_curr_snapshot(int cpu);
#include <linux/spinlock.h>
/*
* In order to reduce various lock holder preemption latencies provide an
* interface to see if a vCPU is currently running or not.
*
* This allows us to terminate optimistic spin loops and block, analogous to
* the native optimistic spin heuristic of testing if the lock owner task is
* running or not.
*/
#ifndef vcpu_is_preempted
static inline bool vcpu_is_preempted(int cpu)
{
return false;
}
#endif
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
#ifdef CONFIG_SMP
static inline bool owner_on_cpu(struct task_struct *owner)
{
/*
* As lock holder preemption issue, we both skip spinning if
* task is not on cpu or its cpu is preempted
*/
return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner));
}
/* Returns effective CPU energy utilization, as seen by the scheduler */
unsigned long sched_cpu_util(int cpu);
#endif /* CONFIG_SMP */
#ifdef CONFIG_SCHED_CORE
extern void sched_core_free(struct task_struct *tsk);
extern void sched_core_fork(struct task_struct *p);
extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type,
unsigned long uaddr);
extern int sched_core_idle_cpu(int cpu);
#else
static inline void sched_core_free(struct task_struct *tsk) { }
static inline void sched_core_fork(struct task_struct *p) { }
static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); }
#endif
extern void sched_set_stop_task(int cpu, struct task_struct *stop);
#ifdef CONFIG_MEM_ALLOC_PROFILING
static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag)
{
swap(current->alloc_tag, tag);
return tag;
}
static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old)
{
#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n");
#endif
current->alloc_tag = old;
}
#else
#define alloc_tag_save(_tag) NULL
#define alloc_tag_restore(_tag, _old) do {} while (0)
#endif
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2009 Red Hat, Inc.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/swapops.h>
#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/mm_types.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/pfn_t.h>
#include <linux/mman.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/migrate.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/page_owner.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>
#include <linux/compat.h>
#include <linux/pgalloc_tag.h>
#include <linux/pagewalk.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
#include "swap.h"
#define CREATE_TRACE_POINTS
#include <trace/events/thp.h>
/*
* By default, transparent hugepage support is disabled in order to avoid
* risking an increased memory footprint for applications that are not
* guaranteed to benefit from it. When transparent hugepage support is
* enabled, it is for all mappings, and khugepaged scans all mappings.
* Defrag is invoked by khugepaged hugepage allocations and by page faults
* for all hugepage allocations.
*/
unsigned long transparent_hugepage_flags __read_mostly =
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
(1<<TRANSPARENT_HUGEPAGE_FLAG)|
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
static struct shrinker *deferred_split_shrinker;
static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc);
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc);
static bool split_underused_thp = true;
static atomic_t huge_zero_refcount;
struct folio *huge_zero_folio __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
static bool anon_orders_configured __initdata;
static inline bool file_thp_enabled(struct vm_area_struct *vma)
{
struct inode *inode;
if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
return false;
if (!vma->vm_file)
return false;
inode = file_inode(vma->vm_file);
return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
}
unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
unsigned long vm_flags,
unsigned long tva_flags,
unsigned long orders)
{
bool smaps = tva_flags & TVA_SMAPS;
bool in_pf = tva_flags & TVA_IN_PF;
bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS;
unsigned long supported_orders;
/* Check the intersection of requested and supported orders. */
if (vma_is_anonymous(vma))
supported_orders = THP_ORDERS_ALL_ANON;
else if (vma_is_special_huge(vma))
supported_orders = THP_ORDERS_ALL_SPECIAL;
else
supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;
orders &= supported_orders;
if (!orders)
return 0;
if (!vma->vm_mm) /* vdso */
return 0;
if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags))
return 0;
/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
if (vma_is_dax(vma)) return in_pf ? orders : 0;
/*
* khugepaged special VMA and hugetlb VMA.
* Must be checked after dax since some dax mappings may have
* VM_MIXEDMAP set.
*/
if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED))
return 0;
/*
* Check alignment for file vma and size for both file and anon vma by
* filtering out the unsuitable orders.
*
* Skip the check for page fault. Huge fault does the check in fault
* handlers.
*/
if (!in_pf) {
int order = highest_order(orders);
unsigned long addr;
while (orders) {
addr = vma->vm_end - (PAGE_SIZE << order);
if (thp_vma_suitable_order(vma, addr, order))
break;
order = next_order(&orders, order);
}
if (!orders)
return 0;
}
/*
* Enabled via shmem mount options or sysfs settings.
* Must be done before hugepage flags check since shmem has its
* own flags.
*/
if (!in_pf && shmem_file(vma->vm_file)) return shmem_allowable_huge_orders(file_inode(vma->vm_file),
vma, vma->vm_pgoff, 0,
!enforce_sysfs);
if (!vma_is_anonymous(vma)) {
/*
* Enforce sysfs THP requirements as necessary. Anonymous vmas
* were already handled in thp_vma_allowable_orders().
*/
if (enforce_sysfs && (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
!hugepage_global_always())))
return 0;
/*
* Trust that ->huge_fault() handlers know what they are doing
* in fault path.
*/
if (((in_pf || smaps)) && vma->vm_ops->huge_fault)
return orders;
/* Only regular file is valid in collapse path */
if (((!in_pf || smaps)) && file_thp_enabled(vma))
return orders;
return 0;
}
if (vma_is_temporary_stack(vma))
return 0;
/*
* THPeligible bit of smaps should show 1 for proper VMAs even
* though anon_vma is not initialized yet.
*
* Allow page fault since anon_vma may be not initialized until
* the first page fault.
*/
if (!vma->anon_vma)
return (smaps || in_pf) ? orders : 0;
return orders;
}
static bool get_huge_zero_page(void)
{
struct folio *zero_folio;
retry:
if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
return true;
zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
HPAGE_PMD_ORDER);
if (!zero_folio) {
count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
return false;
}
/* Ensure zero folio won't have large_rmappable flag set. */
folio_clear_large_rmappable(zero_folio);
preempt_disable();
if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
preempt_enable();
folio_put(zero_folio);
goto retry;
}
WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio));
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
preempt_enable();
count_vm_event(THP_ZERO_PAGE_ALLOC);
return true;
}
static void put_huge_zero_page(void)
{
/*
* Counter should never go to zero here. Only shrinker can put
* last reference.
*/
BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}
struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
{
if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
return READ_ONCE(huge_zero_folio);
if (!get_huge_zero_page())
return NULL;
if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
put_huge_zero_page();
return READ_ONCE(huge_zero_folio);
}
void mm_put_huge_zero_folio(struct mm_struct *mm)
{
if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
put_huge_zero_page();
}
static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
struct shrink_control *sc)
{
/* we can free zero page only if last reference remains */
return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
}
static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct folio *zero_folio = xchg(&huge_zero_folio, NULL);
BUG_ON(zero_folio == NULL);
WRITE_ONCE(huge_zero_pfn, ~0UL);
folio_put(zero_folio);
return HPAGE_PMD_NR;
}
return 0;
}
static struct shrinker *huge_zero_page_shrinker;
#ifdef CONFIG_SYSFS
static ssize_t enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
const char *output;
if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
output = "[always] madvise never";
else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags))
output = "always [madvise] never";
else
output = "always madvise [never]";
return sysfs_emit(buf, "%s\n", output);
}
static ssize_t enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret = count;
if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else
ret = -EINVAL;
if (ret > 0) {
int err = start_stop_khugepaged();
if (err)
ret = err;
}
return ret;
}
static struct kobj_attribute enabled_attr = __ATTR_RW(enabled);
ssize_t single_hugepage_flag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf,
enum transparent_hugepage_flag flag)
{
return sysfs_emit(buf, "%d\n",
!!test_bit(flag, &transparent_hugepage_flags));
}
ssize_t single_hugepage_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag flag)
{
unsigned long value;
int ret;
ret = kstrtoul(buf, 10, &value);
if (ret < 0)
return ret;
if (value > 1)
return -EINVAL;
if (value)
set_bit(flag, &transparent_hugepage_flags);
else
clear_bit(flag, &transparent_hugepage_flags);
return count;
}
static ssize_t defrag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
const char *output;
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
&transparent_hugepage_flags))
output = "[always] defer defer+madvise madvise never";
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
&transparent_hugepage_flags))
output = "always [defer] defer+madvise madvise never";
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
&transparent_hugepage_flags))
output = "always defer [defer+madvise] madvise never";
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
&transparent_hugepage_flags))
output = "always defer defer+madvise [madvise] never";
else
output = "always defer defer+madvise madvise [never]";
return sysfs_emit(buf, "%s\n", output);
}
static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "defer+madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "defer")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else
return -EINVAL;
return count;
}
static struct kobj_attribute defrag_attr = __ATTR_RW(defrag);
static ssize_t use_zero_page_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_hugepage_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static ssize_t use_zero_page_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
return single_hugepage_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page);
static ssize_t hpage_pmd_size_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE);
}
static struct kobj_attribute hpage_pmd_size_attr =
__ATTR_RO(hpage_pmd_size);
static ssize_t split_underused_thp_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%d\n", split_underused_thp);
}
static ssize_t split_underused_thp_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err = kstrtobool(buf, &split_underused_thp);
if (err < 0)
return err;
return count;
}
static struct kobj_attribute split_underused_thp_attr = __ATTR(
shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store);
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
&use_zero_page_attr.attr,
&hpage_pmd_size_attr.attr,
#ifdef CONFIG_SHMEM
&shmem_enabled_attr.attr,
#endif
&split_underused_thp_attr.attr,
NULL,
};
static const struct attribute_group hugepage_attr_group = {
.attrs = hugepage_attr,
};
static void hugepage_exit_sysfs(struct kobject *hugepage_kobj);
static void thpsize_release(struct kobject *kobj);
static DEFINE_SPINLOCK(huge_anon_orders_lock);
static LIST_HEAD(thpsize_list);
static ssize_t anon_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
int order = to_thpsize(kobj)->order;
const char *output;
if (test_bit(order, &huge_anon_orders_always))
output = "[always] inherit madvise never";
else if (test_bit(order, &huge_anon_orders_inherit))
output = "always [inherit] madvise never";
else if (test_bit(order, &huge_anon_orders_madvise))
output = "always inherit [madvise] never";
else
output = "always inherit madvise [never]";
return sysfs_emit(buf, "%s\n", output);
}
static ssize_t anon_enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int order = to_thpsize(kobj)->order;
ssize_t ret = count;
if (sysfs_streq(buf, "always")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_inherit);
clear_bit(order, &huge_anon_orders_madvise);
set_bit(order, &huge_anon_orders_always);
spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "inherit")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_madvise);
set_bit(order, &huge_anon_orders_inherit);
spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "madvise")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_inherit);
set_bit(order, &huge_anon_orders_madvise);
spin_unlock(&huge_anon_orders_lock);
} else if (sysfs_streq(buf, "never")) {
spin_lock(&huge_anon_orders_lock);
clear_bit(order, &huge_anon_orders_always);
clear_bit(order, &huge_anon_orders_inherit);
clear_bit(order, &huge_anon_orders_madvise);
spin_unlock(&huge_anon_orders_lock);
} else
ret = -EINVAL;
if (ret > 0) {
int err;
err = start_stop_khugepaged();
if (err)
ret = err;
}
return ret;
}
static struct kobj_attribute anon_enabled_attr =
__ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store);
static struct attribute *anon_ctrl_attrs[] = {
&anon_enabled_attr.attr,
NULL,
};
static const struct attribute_group anon_ctrl_attr_grp = {
.attrs = anon_ctrl_attrs,
};
static struct attribute *file_ctrl_attrs[] = {
#ifdef CONFIG_SHMEM
&thpsize_shmem_enabled_attr.attr,
#endif
NULL,
};
static const struct attribute_group file_ctrl_attr_grp = {
.attrs = file_ctrl_attrs,
};
static struct attribute *any_ctrl_attrs[] = {
NULL,
};
static const struct attribute_group any_ctrl_attr_grp = {
.attrs = any_ctrl_attrs,
};
static const struct kobj_type thpsize_ktype = {
.release = &thpsize_release,
.sysfs_ops = &kobj_sysfs_ops,
};
DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}};
static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item)
{
unsigned long sum = 0;
int cpu;
for_each_possible_cpu(cpu) {
struct mthp_stat *this = &per_cpu(mthp_stats, cpu);
sum += this->stats[order][item];
}
return sum;
}
#define DEFINE_MTHP_STAT_ATTR(_name, _index) \
static ssize_t _name##_show(struct kobject *kobj, \
struct kobj_attribute *attr, char *buf) \
{ \
int order = to_thpsize(kobj)->order; \
\
return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index)); \
} \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK);
DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
#ifdef CONFIG_SHMEM
DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC);
DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK);
DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE);
#endif
DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT);
DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
static struct attribute *anon_stats_attrs[] = {
&anon_fault_alloc_attr.attr,
&anon_fault_fallback_attr.attr,
&anon_fault_fallback_charge_attr.attr,
#ifndef CONFIG_SHMEM
&zswpout_attr.attr,
&swpin_attr.attr,
&swpin_fallback_attr.attr,
&swpin_fallback_charge_attr.attr,
&swpout_attr.attr,
&swpout_fallback_attr.attr,
#endif
&split_deferred_attr.attr,
&nr_anon_attr.attr,
&nr_anon_partially_mapped_attr.attr,
NULL,
};
static struct attribute_group anon_stats_attr_grp = {
.name = "stats",
.attrs = anon_stats_attrs,
};
static struct attribute *file_stats_attrs[] = {
#ifdef CONFIG_SHMEM
&shmem_alloc_attr.attr,
&shmem_fallback_attr.attr,
&shmem_fallback_charge_attr.attr,
#endif
NULL,
};
static struct attribute_group file_stats_attr_grp = {
.name = "stats",
.attrs = file_stats_attrs,
};
static struct attribute *any_stats_attrs[] = {
#ifdef CONFIG_SHMEM
&zswpout_attr.attr,
&swpin_attr.attr,
&swpin_fallback_attr.attr,
&swpin_fallback_charge_attr.attr,
&swpout_attr.attr,
&swpout_fallback_attr.attr,
#endif
&split_attr.attr,
&split_failed_attr.attr,
NULL,
};
static struct attribute_group any_stats_attr_grp = {
.name = "stats",
.attrs = any_stats_attrs,
};
static int sysfs_add_group(struct kobject *kobj,
const struct attribute_group *grp)
{
int ret = -ENOENT;
/*
* If the group is named, try to merge first, assuming the subdirectory
* was already created. This avoids the warning emitted by
* sysfs_create_group() if the directory already exists.
*/
if (grp->name)
ret = sysfs_merge_group(kobj, grp);
if (ret)
ret = sysfs_create_group(kobj, grp);
return ret;
}
static struct thpsize *thpsize_create(int order, struct kobject *parent)
{
unsigned long size = (PAGE_SIZE << order) / SZ_1K;
struct thpsize *thpsize;
int ret = -ENOMEM;
thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
if (!thpsize)
goto err;
thpsize->order = order;
ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
"hugepages-%lukB", size);
if (ret) {
kfree(thpsize);
goto err;
}
ret = sysfs_add_group(&thpsize->kobj, &any_ctrl_attr_grp);
if (ret)
goto err_put;
ret = sysfs_add_group(&thpsize->kobj, &any_stats_attr_grp);
if (ret)
goto err_put;
if (BIT(order) & THP_ORDERS_ALL_ANON) {
ret = sysfs_add_group(&thpsize->kobj, &anon_ctrl_attr_grp);
if (ret)
goto err_put;
ret = sysfs_add_group(&thpsize->kobj, &anon_stats_attr_grp);
if (ret)
goto err_put;
}
if (BIT(order) & THP_ORDERS_ALL_FILE_DEFAULT) {
ret = sysfs_add_group(&thpsize->kobj, &file_ctrl_attr_grp);
if (ret)
goto err_put;
ret = sysfs_add_group(&thpsize->kobj, &file_stats_attr_grp);
if (ret)
goto err_put;
}
return thpsize;
err_put:
kobject_put(&thpsize->kobj);
err:
return ERR_PTR(ret);
}
static void thpsize_release(struct kobject *kobj)
{
kfree(to_thpsize(kobj));
}
static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
int err;
struct thpsize *thpsize;
unsigned long orders;
int order;
/*
* Default to setting PMD-sized THP to inherit the global setting and
* disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
* constant so we have to do this here.
*/
if (!anon_orders_configured)
huge_anon_orders_inherit = BIT(PMD_ORDER);
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
pr_err("failed to create transparent hugepage kobject\n");
return -ENOMEM;
}
err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
if (err) {
pr_err("failed to register transparent hugepage group\n");
goto delete_obj;
}
err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
if (err) {
pr_err("failed to register transparent hugepage group\n");
goto remove_hp_group;
}
orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT;
order = highest_order(orders);
while (orders) {
thpsize = thpsize_create(order, *hugepage_kobj);
if (IS_ERR(thpsize)) {
pr_err("failed to create thpsize for order %d\n", order);
err = PTR_ERR(thpsize);
goto remove_all;
}
list_add(&thpsize->node, &thpsize_list);
order = next_order(&orders, order);
}
return 0;
remove_all:
hugepage_exit_sysfs(*hugepage_kobj);
return err;
remove_hp_group:
sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
kobject_put(*hugepage_kobj);
return err;
}
static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
struct thpsize *thpsize, *tmp;
list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) {
list_del(&thpsize->node);
kobject_put(&thpsize->kobj);
}
sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
kobject_put(hugepage_kobj);
}
#else
static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
return 0;
}
static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
}
#endif /* CONFIG_SYSFS */
static int __init thp_shrinker_init(void)
{
huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero");
if (!huge_zero_page_shrinker)
return -ENOMEM;
deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE |
SHRINKER_MEMCG_AWARE |
SHRINKER_NONSLAB,
"thp-deferred_split");
if (!deferred_split_shrinker) {
shrinker_free(huge_zero_page_shrinker);
return -ENOMEM;
}
huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count;
huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan;
shrinker_register(huge_zero_page_shrinker);
deferred_split_shrinker->count_objects = deferred_split_count;
deferred_split_shrinker->scan_objects = deferred_split_scan;
shrinker_register(deferred_split_shrinker);
return 0;
}
static void __init thp_shrinker_exit(void)
{
shrinker_free(huge_zero_page_shrinker);
shrinker_free(deferred_split_shrinker);
}
static int __init hugepage_init(void)
{
int err;
struct kobject *hugepage_kobj;
if (!has_transparent_hugepage()) {
transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED;
return -EINVAL;
}
/*
* hugepages can't be allocated by the buddy allocator
*/
MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER);
err = hugepage_init_sysfs(&hugepage_kobj);
if (err)
goto err_sysfs;
err = khugepaged_init();
if (err)
goto err_slab;
err = thp_shrinker_init();
if (err)
goto err_shrinker;
/*
* By default disable transparent hugepages on smaller systems,
* where the extra memory used could hurt more than TLB overhead
* is likely to save. The admin can still enable it through /sys.
*/
if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) {
transparent_hugepage_flags = 0;
return 0;
}
err = start_stop_khugepaged();
if (err)
goto err_khugepaged;
return 0;
err_khugepaged:
thp_shrinker_exit();
err_shrinker:
khugepaged_destroy();
err_slab:
hugepage_exit_sysfs(hugepage_kobj);
err_sysfs:
return err;
}
subsys_initcall(hugepage_init);
static int __init setup_transparent_hugepage(char *str)
{
int ret = 0;
if (!str)
goto out;
if (!strcmp(str, "always")) {
set_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
} else if (!strcmp(str, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
} else if (!strcmp(str, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
}
out:
if (!ret)
pr_warn("transparent_hugepage= cannot parse, ignored\n");
return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
static char str_dup[PAGE_SIZE] __initdata;
static int __init setup_thp_anon(char *str)
{
char *token, *range, *policy, *subtoken;
unsigned long always, inherit, madvise;
char *start_size, *end_size;
int start, end, nr;
char *p;
if (!str || strlen(str) + 1 > PAGE_SIZE)
goto err;
strscpy(str_dup, str);
always = huge_anon_orders_always;
madvise = huge_anon_orders_madvise;
inherit = huge_anon_orders_inherit;
p = str_dup;
while ((token = strsep(&p, ";")) != NULL) {
range = strsep(&token, ":");
policy = token;
if (!policy)
goto err;
while ((subtoken = strsep(&range, ",")) != NULL) {
if (strchr(subtoken, '-')) {
start_size = strsep(&subtoken, "-");
end_size = subtoken;
start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON);
end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON);
} else {
start_size = end_size = subtoken;
start = end = get_order_from_str(subtoken,
THP_ORDERS_ALL_ANON);
}
if (start == -EINVAL) {
pr_err("invalid size %s in thp_anon boot parameter\n", start_size);
goto err;
}
if (end == -EINVAL) {
pr_err("invalid size %s in thp_anon boot parameter\n", end_size);
goto err;
}
if (start < 0 || end < 0 || start > end)
goto err;
nr = end - start + 1;
if (!strcmp(policy, "always")) {
bitmap_set(&always, start, nr);
bitmap_clear(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
} else if (!strcmp(policy, "madvise")) {
bitmap_set(&madvise, start, nr);
bitmap_clear(&inherit, start, nr);
bitmap_clear(&always, start, nr);
} else if (!strcmp(policy, "inherit")) {
bitmap_set(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
bitmap_clear(&always, start, nr);
} else if (!strcmp(policy, "never")) {
bitmap_clear(&inherit, start, nr);
bitmap_clear(&madvise, start, nr);
bitmap_clear(&always, start, nr);
} else {
pr_err("invalid policy %s in thp_anon boot parameter\n", policy);
goto err;
}
}
}
huge_anon_orders_always = always;
huge_anon_orders_madvise = madvise;
huge_anon_orders_inherit = inherit;
anon_orders_configured = true;
return 1;
err:
pr_warn("thp_anon=%s: error parsing string, ignoring setting\n", str);
return 0;
}
__setup("thp_anon=", setup_thp_anon);
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pmd = pmd_mkwrite(pmd, vma);
return pmd;
}
#ifdef CONFIG_MEMCG
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
struct mem_cgroup *memcg = folio_memcg(folio);
struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
if (memcg)
return &memcg->deferred_split_queue;
else
return &pgdat->deferred_split_queue;
}
#else
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
return &pgdat->deferred_split_queue;
}
#endif
static inline bool is_transparent_hugepage(const struct folio *folio)
{
if (!folio_test_large(folio))
return false;
return is_huge_zero_folio(folio) ||
folio_test_large_rmappable(folio);
}
static unsigned long __thp_get_unmapped_area(struct file *filp,
unsigned long addr, unsigned long len,
loff_t off, unsigned long flags, unsigned long size,
vm_flags_t vm_flags)
{
loff_t off_end = off + len;
loff_t off_align = round_up(off, size);
unsigned long len_pad, ret, off_sub;
if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
return 0;
if (off_end <= off_align || (off_end - off_align) < size)
return 0;
len_pad = len + size;
if (len_pad < len || (off + len_pad) < off)
return 0;
ret = mm_get_unmapped_area_vmflags(current->mm, filp, addr, len_pad,
off >> PAGE_SHIFT, flags, vm_flags);
/*
* The failure might be due to length padding. The caller will retry
* without the padding.
*/
if (IS_ERR_VALUE(ret))
return 0;
/*
* Do not try to align to THP boundary if allocation at the address
* hint succeeds.
*/
if (ret == addr)
return addr;
off_sub = (off - ret) & (size - 1);
if (test_bit(MMF_TOPDOWN, ¤t->mm->flags) && !off_sub)
return ret + size;
ret += off_sub;
return ret;
}
unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags,
vm_flags_t vm_flags)
{
unsigned long ret;
loff_t off = (loff_t)pgoff << PAGE_SHIFT;
ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags);
if (ret)
return ret;
return mm_get_unmapped_area_vmflags(current->mm, filp, addr, len, pgoff, flags,
vm_flags);
}
unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
unsigned long addr)
{
gfp_t gfp = vma_thp_gfp_mask(vma);
const int order = HPAGE_PMD_ORDER;
struct folio *folio;
folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK);
if (unlikely(!folio)) {
count_vm_event(THP_FAULT_FALLBACK);
count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
return NULL;
}
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
folio_put(folio);
count_vm_event(THP_FAULT_FALLBACK);
count_vm_event(THP_FAULT_FALLBACK_CHARGE);
count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
return NULL;
}
folio_throttle_swaprate(folio, gfp);
/*
* When a folio is not zeroed during allocation (__GFP_ZERO not used)
* or user folios require special handling, folio_zero_user() is used to
* make sure that the page corresponding to the faulting address will be
* hot in the cache after zeroing.
*/
if (user_alloc_needs_zeroing())
folio_zero_user(folio, addr);
/*
* The memory barrier inside __folio_mark_uptodate makes sure that
* folio_zero_user writes become visible before the set_pmd_at()
* write.
*/
__folio_mark_uptodate(folio);
return folio;
}
static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd,
struct vm_area_struct *vma, unsigned long haddr)
{
pmd_t entry;
entry = mk_huge_pmd(&folio->page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
set_pmd_at(vma->vm_mm, haddr, pmd, entry);
update_mmu_cache_pmd(vma, haddr, pmd);
add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
count_vm_event(THP_FAULT_ALLOC);
count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
}
static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
{
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
pgtable_t pgtable;
vm_fault_t ret = 0;
folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
if (unlikely(!folio))
return VM_FAULT_FALLBACK;
pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable)) {
ret = VM_FAULT_OOM;
goto release;
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_none(*vmf->pmd))) {
goto unlock_release;
} else {
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto unlock_release;
/* Deliver the page fault to userland */
if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
folio_put(folio);
pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
return ret;
}
pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
mm_inc_nr_ptes(vma->vm_mm);
deferred_split_folio(folio, false);
spin_unlock(vmf->ptl);
}
return 0;
unlock_release:
spin_unlock(vmf->ptl);
release:
if (pgtable)
pte_free(vma->vm_mm, pgtable);
folio_put(folio);
return ret;
}
/*
* always: directly stall for all thp allocations
* defer: wake kswapd and fail if not immediately available
* defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
* fail if not immediately available
* madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
* available
* never: never stall for any thp allocation
*/
gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma)
{
const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE);
/* Always do synchronous compaction */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
/* Kick kcompactd and fail quickly */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
/* Synchronous compaction if madvised, otherwise kick kcompactd */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT |
(vma_madvised ? __GFP_DIRECT_RECLAIM :
__GFP_KSWAPD_RECLAIM);
/* Only do synchronous compaction if madvised */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT |
(vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
return GFP_TRANSHUGE_LIGHT;
}
/* Caller must hold page table lock. */
static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
struct folio *zero_folio)
{
pmd_t entry;
entry = mk_pmd(&zero_folio->page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
mm_inc_nr_ptes(mm);
}
vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
vm_fault_t ret;
if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
return VM_FAULT_FALLBACK;
ret = vmf_anon_prepare(vmf);
if (ret)
return ret;
khugepaged_enter_vma(vma, vma->vm_flags);
if (!(vmf->flags & FAULT_FLAG_WRITE) &&
!mm_forbids_zeropage(vma->vm_mm) &&
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct folio *zero_folio;
vm_fault_t ret;
pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable))
return VM_FAULT_OOM;
zero_folio = mm_get_huge_zero_folio(vma->vm_mm);
if (unlikely(!zero_folio)) {
pte_free(vma->vm_mm, pgtable);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
ret = 0;
if (pmd_none(*vmf->pmd)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret) {
spin_unlock(vmf->ptl);
pte_free(vma->vm_mm, pgtable);
} else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
set_huge_zero_folio(pgtable, vma->vm_mm, vma,
haddr, vmf->pmd, zero_folio);
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
spin_unlock(vmf->ptl);
}
} else {
spin_unlock(vmf->ptl);
pte_free(vma->vm_mm, pgtable);
}
return ret;
}
return __do_huge_pmd_anonymous_page(vmf);
}
static int insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
pgtable_t pgtable)
{
struct mm_struct *mm = vma->vm_mm;
pmd_t entry;
lockdep_assert_held(pmd_lockptr(mm, pmd));
if (!pmd_none(*pmd)) {
if (write) {
if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
return -EEXIST;
}
entry = pmd_mkyoung(*pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
update_mmu_cache_pmd(vma, addr, pmd);
}
return -EEXIST;
}
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
else
entry = pmd_mkspecial(entry);
if (write) {
entry = pmd_mkyoung(pmd_mkdirty(entry));
entry = maybe_pmd_mkwrite(entry, vma);
}
if (pgtable) {
pgtable_trans_huge_deposit(mm, pmd, pgtable);
mm_inc_nr_ptes(mm);
}
set_pmd_at(mm, addr, pmd, entry);
update_mmu_cache_pmd(vma, addr, pmd);
return 0;
}
/**
* vmf_insert_pfn_pmd - insert a pmd size pfn
* @vmf: Structure describing the fault
* @pfn: pfn to insert
* @write: whether it's a write fault
*
* Insert a pmd size pfn. See vmf_insert_pfn() for additional info.
*
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
{
unsigned long addr = vmf->address & PMD_MASK;
struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
pgtable_t pgtable = NULL;
spinlock_t *ptl;
int error;
/*
* If we had pmd_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
* can't support a 'special' bit.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
!pfn_t_devmap(pfn));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (arch_needs_pgtable_deposit()) {
pgtable = pte_alloc_one(vma->vm_mm);
if (!pgtable)
return VM_FAULT_OOM;
}
track_pfn_insert(vma, &pgprot, pfn);
ptl = pmd_lock(vma->vm_mm, vmf->pmd);
error = insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write,
pgtable);
spin_unlock(ptl);
if (error && pgtable)
pte_free(vma->vm_mm, pgtable);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
bool write)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address & PMD_MASK;
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
pgtable_t pgtable = NULL;
int error;
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER))
return VM_FAULT_SIGBUS;
if (arch_needs_pgtable_deposit()) {
pgtable = pte_alloc_one(vma->vm_mm);
if (!pgtable)
return VM_FAULT_OOM;
}
ptl = pmd_lock(mm, vmf->pmd);
if (pmd_none(*vmf->pmd)) {
folio_get(folio);
folio_add_file_rmap_pmd(folio, &folio->page, vma);
add_mm_counter(mm, mm_counter_file(folio), HPAGE_PMD_NR);
}
error = insert_pfn_pmd(vma, addr, vmf->pmd,
pfn_to_pfn_t(folio_pfn(folio)), vma->vm_page_prot,
write, pgtable);
spin_unlock(ptl);
if (error && pgtable)
pte_free(mm, pgtable);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_folio_pmd);
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pud = pud_mkwrite(pud);
return pud;
}
static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, pfn_t pfn, bool write)
{
struct mm_struct *mm = vma->vm_mm;
pgprot_t prot = vma->vm_page_prot;
pud_t entry;
if (!pud_none(*pud)) {
if (write) {
if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
return;
entry = pud_mkyoung(*pud);
entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
if (pudp_set_access_flags(vma, addr, pud, entry, 1))
update_mmu_cache_pud(vma, addr, pud);
}
return;
}
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
else
entry = pud_mkspecial(entry);
if (write) {
entry = pud_mkyoung(pud_mkdirty(entry));
entry = maybe_pud_mkwrite(entry, vma);
}
set_pud_at(mm, addr, pud, entry);
update_mmu_cache_pud(vma, addr, pud);
}
/**
* vmf_insert_pfn_pud - insert a pud size pfn
* @vmf: Structure describing the fault
* @pfn: pfn to insert
* @write: whether it's a write fault
*
* Insert a pud size pfn. See vmf_insert_pfn() for additional info.
*
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
{
unsigned long addr = vmf->address & PUD_MASK;
struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
spinlock_t *ptl;
/*
* If we had pud_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
* can't support a 'special' bit.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
!pfn_t_devmap(pfn));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
track_pfn_insert(vma, &pgprot, pfn);
ptl = pud_lock(vma->vm_mm, vmf->pud);
insert_pfn_pud(vma, addr, vmf->pud, pfn, write);
spin_unlock(ptl);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
/**
* vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry
* @vmf: Structure describing the fault
* @folio: folio to insert
* @write: whether it's a write fault
*
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
bool write)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address & PUD_MASK;
pud_t *pud = vmf->pud;
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER))
return VM_FAULT_SIGBUS;
ptl = pud_lock(mm, pud);
/*
* If there is already an entry present we assume the folio is
* already mapped, hence no need to take another reference. We
* still call insert_pfn_pud() though in case the mapping needs
* upgrading to writeable.
*/
if (pud_none(*vmf->pud)) {
folio_get(folio);
folio_add_file_rmap_pud(folio, &folio->page, vma);
add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
}
insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)),
write);
spin_unlock(ptl);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_folio_pud);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, bool write)
{
pmd_t _pmd;
_pmd = pmd_mkyoung(*pmd);
if (write)
_pmd = pmd_mkdirty(_pmd);
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
pmd, _pmd, write))
update_mmu_cache_pmd(vma, addr, pmd);
}
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
{
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
struct page *page;
int ret;
assert_spin_locked(pmd_lockptr(mm, pmd));
if (flags & FOLL_WRITE && !pmd_write(*pmd))
return NULL;
if (pmd_present(*pmd) && pmd_devmap(*pmd))
/* pass */;
else
return NULL;
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
/*
* device mapped pages can only be returned if the
* caller will manage the page reference count.
*/
if (!(flags & (FOLL_GET | FOLL_PIN)))
return ERR_PTR(-EEXIST);
pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
*pgmap = get_dev_pagemap(pfn, *pgmap);
if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
ret = try_grab_folio(page_folio(page), 1, flags);
if (ret)
page = ERR_PTR(ret);
return page;
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
spinlock_t *dst_ptl, *src_ptl;
struct page *src_page;
struct folio *src_folio;
pmd_t pmd;
pgtable_t pgtable = NULL;
int ret = -ENOMEM;
pmd = pmdp_get_lockless(src_pmd);
if (unlikely(pmd_present(pmd) && pmd_special(pmd))) {
dst_ptl = pmd_lock(dst_mm, dst_pmd);
src_ptl = pmd_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
/*
* No need to recheck the pmd, it can't change with write
* mmap lock held here.
*
* Meanwhile, making sure it's not a CoW VMA with writable
* mapping, otherwise it means either the anon page wrongly
* applied special bit, or we made the PRIVATE mapping be
* able to wrongly write to the backend MMIO.
*/
VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd));
goto set_pmd;
}
/* Skip if can be re-fill on fault */
if (!vma_is_anonymous(dst_vma))
return 0;
pgtable = pte_alloc_one(dst_mm);
if (unlikely(!pgtable))
goto out;
dst_ptl = pmd_lock(dst_mm, dst_pmd);
src_ptl = pmd_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
ret = -EAGAIN;
pmd = *src_pmd;
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
if (unlikely(is_swap_pmd(pmd))) {
swp_entry_t entry = pmd_to_swp_entry(pmd);
VM_BUG_ON(!is_pmd_migration_entry(pmd));
if (!is_readable_migration_entry(entry)) {
entry = make_readable_migration_entry(
swp_offset(entry));
pmd = swp_entry_to_pmd(entry);
if (pmd_swp_soft_dirty(*src_pmd))
pmd = pmd_swp_mksoft_dirty(pmd);
if (pmd_swp_uffd_wp(*src_pmd))
pmd = pmd_swp_mkuffd_wp(pmd);
set_pmd_at(src_mm, addr, src_pmd, pmd);
}
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
mm_inc_nr_ptes(dst_mm);
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
if (!userfaultfd_wp(dst_vma))
pmd = pmd_swp_clear_uffd_wp(pmd);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
goto out_unlock;
}
#endif
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
goto out_unlock;
}
/*
* When page table lock is held, the huge zero pmd should not be
* under splitting since we don't split the page itself, only pmd to
* a page table.
*/
if (is_huge_zero_pmd(pmd)) {
/*
* mm_get_huge_zero_folio() will never allocate a new
* folio here, since we already have a zero page to
* copy. It just takes a reference.
*/
mm_get_huge_zero_folio(dst_mm);
goto out_zero_page;
}
src_page = pmd_page(pmd);
VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
src_folio = page_folio(src_page);
folio_get(src_folio);
if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, dst_vma, src_vma))) {
/* Page maybe pinned: split and retry the fault on PTEs. */
folio_put(src_folio);
pte_free(dst_mm, pgtable);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
__split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
return -EAGAIN;
}
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
out_zero_page:
mm_inc_nr_ptes(dst_mm);
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
pmdp_set_wrprotect(src_mm, addr, src_pmd);
if (!userfaultfd_wp(dst_vma))
pmd = pmd_clear_uffd_wp(pmd);
pmd = pmd_wrprotect(pmd);
set_pmd:
pmd = pmd_mkold(pmd);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
out_unlock:
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
out:
return ret;
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
void touch_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, bool write)
{
pud_t _pud;
_pud = pud_mkyoung(*pud);
if (write)
_pud = pud_mkdirty(_pud);
if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
pud, _pud, write))
update_mmu_cache_pud(vma, addr, pud);
}
int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
struct vm_area_struct *vma)
{
spinlock_t *dst_ptl, *src_ptl;
pud_t pud;
int ret;
dst_ptl = pud_lock(dst_mm, dst_pud);
src_ptl = pud_lockptr(src_mm, src_pud);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
ret = -EAGAIN;
pud = *src_pud;
if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
goto out_unlock;
/*
* TODO: once we support anonymous pages, use
* folio_try_dup_anon_rmap_*() and split if duplicating fails.
*/
if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) {
pudp_set_wrprotect(src_mm, addr, src_pud);
pud = pud_wrprotect(pud);
}
pud = pud_mkold(pud);
set_pud_at(dst_mm, addr, dst_pud, pud);
ret = 0;
out_unlock:
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
return ret;
}
void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
{
bool write = vmf->flags & FAULT_FLAG_WRITE;
vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
if (unlikely(!pud_same(*vmf->pud, orig_pud)))
goto unlock;
touch_pud(vmf->vma, vmf->address, vmf->pud, write);
unlock:
spin_unlock(vmf->ptl);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
void huge_pmd_set_accessed(struct vm_fault *vmf)
{
bool write = vmf->flags & FAULT_FLAG_WRITE;
vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd)))
goto unlock;
touch_pmd(vmf->vma, vmf->address, vmf->pmd, write);
unlock:
spin_unlock(vmf->ptl);
}
static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf)
{
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
struct vm_area_struct *vma = vmf->vma;
struct mmu_notifier_range range;
struct folio *folio;
vm_fault_t ret = 0;
folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
if (unlikely(!folio))
return VM_FAULT_FALLBACK;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr,
haddr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd)))
goto release;
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto release;
(void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd);
map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
goto unlock;
release:
folio_put(folio);
unlock:
spin_unlock(vmf->ptl);
mmu_notifier_invalidate_range_end(&range);
return ret;
}
vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
{
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
pmd_t orig_pmd = vmf->orig_pmd;
vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
VM_BUG_ON_VMA(!vma->anon_vma, vma);
if (is_huge_zero_pmd(orig_pmd)) {
vm_fault_t ret = do_huge_zero_wp_pmd(vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
/* Fallback to splitting PMD if THP cannot be allocated */
goto fallback;
}
spin_lock(vmf->ptl);
if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
spin_unlock(vmf->ptl);
return 0;
}
page = pmd_page(orig_pmd);
folio = page_folio(page);
VM_BUG_ON_PAGE(!PageHead(page), page);
/* Early check when only holding the PT lock. */
if (PageAnonExclusive(page))
goto reuse;
if (!folio_trylock(folio)) {
folio_get(folio);
spin_unlock(vmf->ptl);
folio_lock(folio);
spin_lock(vmf->ptl);
if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
spin_unlock(vmf->ptl);
folio_unlock(folio);
folio_put(folio);
return 0;
}
folio_put(folio);
}
/* Recheck after temporarily dropping the PT lock. */
if (PageAnonExclusive(page)) {
folio_unlock(folio);
goto reuse;
}
/*
* See do_wp_page(): we can only reuse the folio exclusively if
* there are no additional references. Note that we always drain
* the LRU cache immediately after adding a THP.
*/
if (folio_ref_count(folio) >
1 + folio_test_swapcache(folio) * folio_nr_pages(folio))
goto unlock_fallback;
if (folio_test_swapcache(folio))
folio_free_swap(folio);
if (folio_ref_count(folio) == 1) {
pmd_t entry;
folio_move_anon_rmap(folio, vma);
SetPageAnonExclusive(page);
folio_unlock(folio);
reuse:
if (unlikely(unshare)) {
spin_unlock(vmf->ptl);
return 0;
}
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
spin_unlock(vmf->ptl);
return 0;
}
unlock_fallback:
folio_unlock(folio);
spin_unlock(vmf->ptl);
fallback:
__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
return VM_FAULT_FALLBACK;
}
static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd)
{
struct page *page;
if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
return false;
/* Don't touch entries that are not even readable (NUMA hinting). */
if (pmd_protnone(pmd))
return false;
/* Do we need write faults for softdirty tracking? */
if (pmd_needs_soft_dirty_wp(vma, pmd))
return false;
/* Do we need write faults for uffd-wp tracking? */
if (userfaultfd_huge_pmd_wp(vma, pmd))
return false;
if (!(vma->vm_flags & VM_SHARED)) {
/* See can_change_pte_writable(). */
page = vm_normal_page_pmd(vma, addr, pmd);
return page && PageAnon(page) && PageAnonExclusive(page);
}
/* See can_change_pte_writable(). */
return pmd_dirty(pmd);
}
/* NUMA hinting page fault entry point for trans huge pmds */
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct folio *folio;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
int nid = NUMA_NO_NODE;
int target_nid, last_cpupid;
pmd_t pmd, old_pmd;
bool writable = false;
int flags = 0;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
old_pmd = pmdp_get(vmf->pmd);
if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) {
spin_unlock(vmf->ptl);
return 0;
}
pmd = pmd_modify(old_pmd, vma->vm_page_prot);
/*
* Detect now whether the PMD could be writable; this information
* is only valid while holding the PT lock.
*/
writable = pmd_write(pmd);
if (!writable && vma_wants_manual_pte_write_upgrade(vma) &&
can_change_pmd_writable(vma, vmf->address, pmd))
writable = true;
folio = vm_normal_folio_pmd(vma, haddr, pmd);
if (!folio)
goto out_map;
nid = folio_nid(folio);
target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable,
&last_cpupid);
if (target_nid == NUMA_NO_NODE)
goto out_map;
if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
flags |= TNF_MIGRATE_FAIL;
goto out_map;
}
/* The folio is isolated and isolation code holds a folio reference. */
spin_unlock(vmf->ptl);
writable = false;
if (!migrate_misplaced_folio(folio, target_nid)) {
flags |= TNF_MIGRATED;
nid = target_nid;
task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
return 0;
}
flags |= TNF_MIGRATE_FAIL;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) {
spin_unlock(vmf->ptl);
return 0;
}
out_map:
/* Restore the PMD */
pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot);
pmd = pmd_mkyoung(pmd);
if (writable)
pmd = pmd_mkwrite(pmd, vma);
set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
spin_unlock(vmf->ptl);
if (nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
return 0;
}
/*
* Return true if we do MADV_FREE successfully on entire pmd page.
* Otherwise, return false.
*/
bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr, unsigned long next)
{
spinlock_t *ptl;
pmd_t orig_pmd;
struct folio *folio;
struct mm_struct *mm = tlb->mm;
bool ret = false;
tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = pmd_trans_huge_lock(pmd, vma);
if (!ptl)
goto out_unlocked;
orig_pmd = *pmd;
if (is_huge_zero_pmd(orig_pmd))
goto out;
if (unlikely(!pmd_present(orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(orig_pmd));
goto out;
}
folio = pmd_folio(orig_pmd);
/*
* If other processes are mapping this folio, we couldn't discard
* the folio unless they all do MADV_FREE so let's skip the folio.
*/
if (folio_maybe_mapped_shared(folio))
goto out;
if (!folio_trylock(folio))
goto out;
/*
* If user want to discard part-pages of THP, split it so MADV_FREE
* will deactivate only them.
*/
if (next - addr != HPAGE_PMD_SIZE) {
folio_get(folio);
spin_unlock(ptl);
split_folio(folio);
folio_unlock(folio);
folio_put(folio);
goto out_unlocked;
}
if (folio_test_dirty(folio))
folio_clear_dirty(folio);
folio_unlock(folio);
if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
orig_pmd = pmd_mkclean(orig_pmd);
set_pmd_at(mm, addr, pmd, orig_pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
}
folio_mark_lazyfree(folio);
ret = true;
out:
spin_unlock(ptl);
out_unlocked:
return ret;
}
static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
{
pgtable_t pgtable;
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pte_free(mm, pgtable);
mm_dec_nr_ptes(mm);
}
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr)
{
pmd_t orig_pmd;
spinlock_t *ptl;
tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
return 0;
/*
* For architectures like ppc64 we look at deposited pgtable
* when calling pmdp_huge_get_and_clear. So do the
* pgtable_trans_huge_withdraw after finishing pmdp related
* operations.
*/
orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd,
tlb->fullmm);
arch_check_zapped_pmd(vma, orig_pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
if (arch_needs_pgtable_deposit())
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
} else if (is_huge_zero_pmd(orig_pmd)) {
if (!vma_is_dax(vma) || arch_needs_pgtable_deposit())
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
} else {
struct folio *folio = NULL;
int flush_needed = 1;
if (pmd_present(orig_pmd)) {
struct page *page = pmd_page(orig_pmd);
folio = page_folio(page);
folio_remove_rmap_pmd(folio, page, vma);
WARN_ON_ONCE(folio_mapcount(folio) < 0);
VM_BUG_ON_PAGE(!PageHead(page), page);
} else if (thp_migration_supported()) {
swp_entry_t entry;
VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
entry = pmd_to_swp_entry(orig_pmd);
folio = pfn_swap_entry_folio(entry);
flush_needed = 0;
} else
WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");
if (folio_test_anon(folio)) {
zap_deposited_table(tlb->mm, pmd);
add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
} else {
if (arch_needs_pgtable_deposit())
zap_deposited_table(tlb->mm, pmd);
add_mm_counter(tlb->mm, mm_counter_file(folio),
-HPAGE_PMD_NR);
}
spin_unlock(ptl);
if (flush_needed)
tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE);
}
return 1;
}
#ifndef pmd_move_must_withdraw
static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
spinlock_t *old_pmd_ptl,
struct vm_area_struct *vma)
{
/*
* With split pmd lock we also need to move preallocated
* PTE page table if new_pmd is on different PMD page table.
*
* We also don't deposit and withdraw tables for file pages.
*/
return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
}
#endif
static pmd_t move_soft_dirty_pmd(pmd_t pmd)
{
#ifdef CONFIG_MEM_SOFT_DIRTY
if (unlikely(is_pmd_migration_entry(pmd)))
pmd = pmd_swp_mksoft_dirty(pmd);
else if (pmd_present(pmd))
pmd = pmd_mksoft_dirty(pmd);
#endif
return pmd;
}
static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
{
if (pmd_present(pmd))
pmd = pmd_clear_uffd_wp(pmd);
else if (is_swap_pmd(pmd))
pmd = pmd_swp_clear_uffd_wp(pmd);
return pmd;
}
bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
{
spinlock_t *old_ptl, *new_ptl;
pmd_t pmd;
struct mm_struct *mm = vma->vm_mm;
bool force_flush = false;
/*
* The destination pmd shouldn't be established, free_pgtables()
* should have released it; but move_page_tables() might have already
* inserted a page table, if racing against shmem/file collapse.
*/
if (!pmd_none(*new_pmd)) {
VM_BUG_ON(pmd_trans_huge(*new_pmd));
return false;
}
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
*/
old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
if (old_ptl) {
new_ptl = pmd_lockptr(mm, new_pmd);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
if (pmd_present(pmd))
force_flush = true;
VM_BUG_ON(!pmd_none(*new_pmd));
if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) {
pgtable_t pgtable;
pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
}
pmd = move_soft_dirty_pmd(pmd);
if (vma_has_uffd_without_event_remap(vma))
pmd = clear_uffd_wp_pmd(pmd);
set_pmd_at(mm, new_addr, new_pmd, pmd);
if (force_flush)
flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
return true;
}
return false;
}
/*
* Returns
* - 0 if PMD could not be locked
* - 1 if PMD was locked but protections unchanged and TLB flush unnecessary
* or if prot_numa but THP migration is not supported
* - HPAGE_PMD_NR if protections changed and TLB flush necessary
*/
int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr, pgprot_t newprot,
unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
pmd_t oldpmd, entry;
bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
int ret = 1;
tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
if (prot_numa && !thp_migration_supported())
return 1;
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
return 0;
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
if (is_swap_pmd(*pmd)) {
swp_entry_t entry = pmd_to_swp_entry(*pmd);
struct folio *folio = pfn_swap_entry_folio(entry);
pmd_t newpmd;
VM_BUG_ON(!is_pmd_migration_entry(*pmd));
if (is_writable_migration_entry(entry)) {
/*
* A protection check is difficult so
* just be safe and disable write
*/
if (folio_test_anon(folio))
entry = make_readable_exclusive_migration_entry(swp_offset(entry));
else
entry = make_readable_migration_entry(swp_offset(entry));
newpmd = swp_entry_to_pmd(entry);
if (pmd_swp_soft_dirty(*pmd))
newpmd = pmd_swp_mksoft_dirty(newpmd);
} else {
newpmd = *pmd;
}
if (uffd_wp)
newpmd = pmd_swp_mkuffd_wp(newpmd);
else if (uffd_wp_resolve)
newpmd = pmd_swp_clear_uffd_wp(newpmd);
if (!pmd_same(*pmd, newpmd))
set_pmd_at(mm, addr, pmd, newpmd);
goto unlock;
}
#endif
if (prot_numa) {
struct folio *folio;
bool toptier;
/*
* Avoid trapping faults against the zero page. The read-only
* data is likely to be read-cached on the local CPU and
* local/remote hits to the zero page are not interesting.
*/
if (is_huge_zero_pmd(*pmd))
goto unlock;
if (pmd_protnone(*pmd))
goto unlock;
folio = pmd_folio(*pmd);
toptier = node_is_toptier(folio_nid(folio));
/*
* Skip scanning top tier node if normal numa
* balancing is disabled
*/
if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
toptier)
goto unlock;
if (folio_use_access_time(folio))
folio_xchg_access_time(folio,
jiffies_to_msecs(jiffies));
}
/*
* In case prot_numa, we are under mmap_read_lock(mm). It's critical
* to not clear pmd intermittently to avoid race with MADV_DONTNEED
* which is also under mmap_read_lock(mm):
*
* CPU0: CPU1:
* change_huge_pmd(prot_numa=1)
* pmdp_huge_get_and_clear_notify()
* madvise_dontneed()
* zap_pmd_range()
* pmd_trans_huge(*pmd) == 0 (without ptl)
* // skip the pmd
* set_pmd_at();
* // pmd is re-established
*
* The race makes MADV_DONTNEED miss the huge pmd and don't clear it
* which may break userspace.
*
* pmdp_invalidate_ad() is required to make sure we don't miss
* dirty/young flags set by hardware.
*/
oldpmd = pmdp_invalidate_ad(vma, addr, pmd);
entry = pmd_modify(oldpmd, newprot);
if (uffd_wp)
entry = pmd_mkuffd_wp(entry);
else if (uffd_wp_resolve)
/*
* Leave the write bit to be handled by PF interrupt
* handler, then things like COW could be properly
* handled.
*/
entry = pmd_clear_uffd_wp(entry);
/* See change_pte_range(). */
if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) &&
can_change_pmd_writable(vma, addr, entry))
entry = pmd_mkwrite(entry, vma);
ret = HPAGE_PMD_NR;
set_pmd_at(mm, addr, pmd, entry);
if (huge_pmd_needs_flush(oldpmd, entry))
tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
unlock:
spin_unlock(ptl);
return ret;
}
/*
* Returns:
*
* - 0: if pud leaf changed from under us
* - 1: if pud can be skipped
* - HPAGE_PUD_NR: if pud was successfully processed
*/
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
pud_t *pudp, unsigned long addr, pgprot_t newprot,
unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
pud_t oldpud, entry;
spinlock_t *ptl;
tlb_change_page_size(tlb, HPAGE_PUD_SIZE);
/* NUMA balancing doesn't apply to dax */
if (cp_flags & MM_CP_PROT_NUMA)
return 1;
/*
* Huge entries on userfault-wp only works with anonymous, while we
* don't have anonymous PUDs yet.
*/
if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL))
return 1;
ptl = __pud_trans_huge_lock(pudp, vma);
if (!ptl)
return 0;
/*
* Can't clear PUD or it can race with concurrent zapping. See
* change_huge_pmd().
*/
oldpud = pudp_invalidate(vma, addr, pudp);
entry = pud_modify(oldpud, newprot);
set_pud_at(mm, addr, pudp, entry);
tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE);
spin_unlock(ptl);
return HPAGE_PUD_NR;
}
#endif
#ifdef CONFIG_USERFAULTFD
/*
* The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by
* the caller, but it must return after releasing the page_table_lock.
* Just move the page from src_pmd to dst_pmd if possible.
* Return zero if succeeded in moving the page, -EAGAIN if it needs to be
* repeated by the caller, or other errors in case of failure.
*/
int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
unsigned long dst_addr, unsigned long src_addr)
{
pmd_t _dst_pmd, src_pmdval;
struct page *src_page;
struct folio *src_folio;
struct anon_vma *src_anon_vma;
spinlock_t *src_ptl, *dst_ptl;
pgtable_t src_pgtable;
struct mmu_notifier_range range;
int err = 0;
src_pmdval = *src_pmd;
src_ptl = pmd_lockptr(mm, src_pmd);
lockdep_assert_held(src_ptl);
vma_assert_locked(src_vma);
vma_assert_locked(dst_vma);
/* Sanity checks before the operation */
if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) ||
WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) {
spin_unlock(src_ptl);
return -EINVAL;
}
if (!pmd_trans_huge(src_pmdval)) {
spin_unlock(src_ptl);
if (is_pmd_migration_entry(src_pmdval)) {
pmd_migration_entry_wait(mm, &src_pmdval);
return -EAGAIN;
}
return -ENOENT;
}
src_page = pmd_page(src_pmdval);
if (!is_huge_zero_pmd(src_pmdval)) {
if (unlikely(!PageAnonExclusive(src_page))) {
spin_unlock(src_ptl);
return -EBUSY;
}
src_folio = page_folio(src_page);
folio_get(src_folio);
} else
src_folio = NULL;
spin_unlock(src_ptl);
flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr,
src_addr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
if (src_folio) {
folio_lock(src_folio);
/*
* split_huge_page walks the anon_vma chain without the page
* lock. Serialize against it with the anon_vma lock, the page
* lock is not enough.
*/
src_anon_vma = folio_get_anon_vma(src_folio);
if (!src_anon_vma) {
err = -EAGAIN;
goto unlock_folio;
}
anon_vma_lock_write(src_anon_vma);
} else
src_anon_vma = NULL;
dst_ptl = pmd_lockptr(mm, dst_pmd);
double_pt_lock(src_ptl, dst_ptl);
if (unlikely(!pmd_same(*src_pmd, src_pmdval) ||
!pmd_same(*dst_pmd, dst_pmdval))) {
err = -EAGAIN;
goto unlock_ptls;
}
if (src_folio) {
if (folio_maybe_dma_pinned(src_folio) ||
!PageAnonExclusive(&src_folio->page)) {
err = -EBUSY;
goto unlock_ptls;
}
if (WARN_ON_ONCE(!folio_test_head(src_folio)) ||
WARN_ON_ONCE(!folio_test_anon(src_folio))) {
err = -EBUSY;
goto unlock_ptls;
}
src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
/* Folio got pinned from under us. Put it back and fail the move. */
if (folio_maybe_dma_pinned(src_folio)) {
set_pmd_at(mm, src_addr, src_pmd, src_pmdval);
err = -EBUSY;
goto unlock_ptls;
}
folio_move_anon_rmap(src_folio, dst_vma);
src_folio->index = linear_page_index(dst_vma, dst_addr);
_dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot);
/* Follow mremap() behavior and treat the entry dirty after the move */
_dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
} else {
src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
_dst_pmd = mk_huge_pmd(src_page, dst_vma->vm_page_prot);
}
set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);
src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd);
pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable);
unlock_ptls:
double_pt_unlock(src_ptl, dst_ptl);
if (src_anon_vma) {
anon_vma_unlock_write(src_anon_vma);
put_anon_vma(src_anon_vma);
}
unlock_folio:
/* unblock rmap walks */
if (src_folio)
folio_unlock(src_folio);
mmu_notifier_invalidate_range_end(&range);
if (src_folio)
folio_put(src_folio);
return err;
}
#endif /* CONFIG_USERFAULTFD */
/*
* Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
*
* Note that if it returns page table lock pointer, this routine returns without
* unlocking page table lock. So callers must unlock it.
*/
spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
{
spinlock_t *ptl;
ptl = pmd_lock(vma->vm_mm, pmd);
if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
pmd_devmap(*pmd)))
return ptl;
spin_unlock(ptl);
return NULL;
}
/*
* Returns page table lock pointer if a given pud maps a thp, NULL otherwise.
*
* Note that if it returns page table lock pointer, this routine returns without
* unlocking page table lock. So callers must unlock it.
*/
spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
{
spinlock_t *ptl;
ptl = pud_lock(vma->vm_mm, pud);
if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
return ptl;
spin_unlock(ptl);
return NULL;
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
pud_t *pud, unsigned long addr)
{
spinlock_t *ptl;
pud_t orig_pud;
ptl = __pud_trans_huge_lock(pud, vma);
if (!ptl)
return 0;
orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
arch_check_zapped_pud(vma, orig_pud);
tlb_remove_pud_tlb_entry(tlb, pud, addr);
if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
spin_unlock(ptl);
/* No zero page support yet */
} else {
struct page *page = NULL;
struct folio *folio;
/* No support for anonymous PUD pages or migration yet */
VM_WARN_ON_ONCE(vma_is_anonymous(vma) ||
!pud_present(orig_pud));
page = pud_page(orig_pud);
folio = page_folio(page);
folio_remove_rmap_pud(folio, page, vma);
add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR);
spin_unlock(ptl);
tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE);
}
return 1;
}
static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
unsigned long haddr)
{
struct folio *folio;
struct page *page;
pud_t old_pud;
VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
count_vm_event(THP_SPLIT_PUD);
old_pud = pudp_huge_clear_flush(vma, haddr, pud);
if (!vma_is_dax(vma))
return;
page = pud_page(old_pud);
folio = page_folio(page);
if (!folio_test_dirty(folio) && pud_dirty(old_pud))
folio_mark_dirty(folio);
if (!folio_test_referenced(folio) && pud_young(old_pud))
folio_set_referenced(folio);
folio_remove_rmap_pud(folio, page, vma);
folio_put(folio);
add_mm_counter(vma->vm_mm, mm_counter_file(folio),
-HPAGE_PUD_NR);
}
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
unsigned long address)
{
spinlock_t *ptl;
struct mmu_notifier_range range;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address & HPAGE_PUD_MASK,
(address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
mmu_notifier_invalidate_range_start(&range);
ptl = pud_lock(vma->vm_mm, pud);
if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
goto out;
__split_huge_pud_locked(vma, pud, range.start);
out:
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
}
#else
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
unsigned long address)
{
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd)
{
struct mm_struct *mm = vma->vm_mm;
pgtable_t pgtable;
pmd_t _pmd, old_pmd;
unsigned long addr;
pte_t *pte;
int i;
/*
* Leave pmd empty until pte is filled note that it is fine to delay
* notification until mmu_notifier_invalidate_range_end() as we are
* replacing a zero pmd write protected page with a zero pte write
* protected page.
*
* See Documentation/mm/mmu_notifier.rst
*/
old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte); for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
pte_t entry;
entry = pfn_pte(my_zero_pfn(addr), vma->vm_page_prot);
entry = pte_mkspecial(entry);
if (pmd_uffd_wp(old_pmd)) entry = pte_mkuffd_wp(entry); VM_BUG_ON(!pte_none(ptep_get(pte))); set_pte_at(mm, addr, pte, entry);
pte++;
}
pte_unmap(pte - 1);
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
}
static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long haddr, bool freeze)
{
struct mm_struct *mm = vma->vm_mm;
struct folio *folio;
struct page *page;
pgtable_t pgtable;
pmd_t old_pmd, _pmd;
bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
bool anon_exclusive = false, dirty = false;
unsigned long addr;
pte_t *pte;
int i;
VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
&& !pmd_devmap(*pmd));
count_vm_event(THP_SPLIT_PMD);
if (!vma_is_anonymous(vma)) {
old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);
/*
* We are going to unmap this huge page. So
* just go ahead and zap it
*/
if (arch_needs_pgtable_deposit())
zap_deposited_table(mm, pmd);
if (!vma_is_dax(vma) && vma_is_special_huge(vma))
return;
if (unlikely(is_pmd_migration_entry(old_pmd))) {
swp_entry_t entry;
entry = pmd_to_swp_entry(old_pmd);
folio = pfn_swap_entry_folio(entry);
} else if (is_huge_zero_pmd(old_pmd)) {
return;
} else {
page = pmd_page(old_pmd);
folio = page_folio(page); if (!folio_test_dirty(folio) && pmd_dirty(old_pmd)) folio_mark_dirty(folio); if (!folio_test_referenced(folio) && pmd_young(old_pmd)) folio_set_referenced(folio);
folio_remove_rmap_pmd(folio, page, vma);
folio_put(folio);
}
add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR);
return;
}
if (is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_arch_invalidate_secondary_tlbs() see comments below
* inside __split_huge_pmd() ?
*
* We are going from a zero huge page write protected to zero
* small page also write protected so it does not seems useful
* to invalidate secondary mmu at this time.
*/
return __split_huge_zero_page_pmd(vma, haddr, pmd);
}
pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) {
swp_entry_t entry;
old_pmd = *pmd;
entry = pmd_to_swp_entry(old_pmd);
page = pfn_swap_entry_to_page(entry);
write = is_writable_migration_entry(entry);
if (PageAnon(page))
anon_exclusive = is_readable_exclusive_migration_entry(entry);
young = is_migration_entry_young(entry);
dirty = is_migration_entry_dirty(entry);
soft_dirty = pmd_swp_soft_dirty(old_pmd);
uffd_wp = pmd_swp_uffd_wp(old_pmd);
} else {
/*
* Up to this point the pmd is present and huge and userland has
* the whole access to the hugepage during the split (which
* happens in place). If we overwrite the pmd with the not-huge
* version pointing to the pte here (which of course we could if
* all CPUs were bug free), userland could trigger a small page
* size TLB miss on the small sized TLB while the hugepage TLB
* entry is still established in the huge TLB. Some CPU doesn't
* like that. See
* http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum
* 383 on page 105. Intel should be safe but is also warns that
* it's only safe if the permission and cache attributes of the
* two entries loaded in the two TLB is identical (which should
* be the case here). But it is generally safer to never allow
* small and huge TLB entries for the same virtual address to be
* loaded simultaneously. So instead of doing "pmd_populate();
* flush_pmd_tlb_range();" we first mark the current pmd
* notpresent (atomically because here the pmd_trans_huge must
* remain set at all times on the pmd until the split is
* complete for this pmd), then we flush the SMP TLB and finally
* we write the non-huge version of the pmd entry with
* pmd_populate.
*/
old_pmd = pmdp_invalidate(vma, haddr, pmd);
page = pmd_page(old_pmd);
folio = page_folio(page); if (pmd_dirty(old_pmd)) {
dirty = true;
folio_set_dirty(folio);
}
write = pmd_write(old_pmd);
young = pmd_young(old_pmd);
soft_dirty = pmd_soft_dirty(old_pmd);
uffd_wp = pmd_uffd_wp(old_pmd);
VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
/*
* Without "freeze", we'll simply split the PMD, propagating the
* PageAnonExclusive() flag for each PTE by setting it for
* each subpage -- no need to (temporarily) clear.
*
* With "freeze" we want to replace mapped pages by
* migration entries right away. This is only possible if we
* managed to clear PageAnonExclusive() -- see
* set_pmd_migration_entry().
*
* In case we cannot clear PageAnonExclusive(), split the PMD
* only and let try_to_migrate_one() fail later.
*
* See folio_try_share_anon_rmap_pmd(): invalidate PMD first.
*/
anon_exclusive = PageAnonExclusive(page);
if (freeze && anon_exclusive &&
folio_try_share_anon_rmap_pmd(folio, page))
freeze = false;
if (!freeze) {
rmap_t rmap_flags = RMAP_NONE;
folio_ref_add(folio, HPAGE_PMD_NR - 1);
if (anon_exclusive)
rmap_flags |= RMAP_EXCLUSIVE;
folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
vma, haddr, rmap_flags);
}
}
/*
* Withdraw the table only after we mark the pmd entry invalid.
* This's critical for some architectures (Power).
*/
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte);
/*
* Note that NUMA hinting access restrictions are not transferred to
* avoid any possibility of altering permissions across VMAs.
*/
if (freeze || pmd_migration) {
for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
pte_t entry;
swp_entry_t swp_entry;
if (write)
swp_entry = make_writable_migration_entry(
page_to_pfn(page + i));
else if (anon_exclusive)
swp_entry = make_readable_exclusive_migration_entry(
page_to_pfn(page + i));
else
swp_entry = make_readable_migration_entry(
page_to_pfn(page + i));
if (young) swp_entry = make_migration_entry_young(swp_entry); if (dirty) swp_entry = make_migration_entry_dirty(swp_entry);
entry = swp_entry_to_pte(swp_entry);
if (soft_dirty)
entry = pte_swp_mksoft_dirty(entry);
if (uffd_wp)
entry = pte_swp_mkuffd_wp(entry);
VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_pte_at(mm, addr, pte + i, entry);
}
} else {
pte_t entry;
entry = mk_pte(page, READ_ONCE(vma->vm_page_prot));
if (write)
entry = pte_mkwrite(entry, vma);
if (!young)
entry = pte_mkold(entry);
/* NOTE: this may set soft-dirty too on some archs */
if (dirty) entry = pte_mkdirty(entry);
if (soft_dirty)
entry = pte_mksoft_dirty(entry);
if (uffd_wp) entry = pte_mkuffd_wp(entry); for (i = 0; i < HPAGE_PMD_NR; i++) VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_ptes(mm, haddr, pte, entry, HPAGE_PMD_NR);
}
pte_unmap(pte); if (!pmd_migration) folio_remove_rmap_pmd(folio, page, vma); if (freeze) put_page(page);
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
}
void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, bool freeze, struct folio *folio)
{ VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio)); VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); VM_BUG_ON(freeze && !folio);
/*
* When the caller requests to set up a migration entry, we
* require a folio to check the PMD against. Otherwise, there
* is a risk of replacing the wrong folio.
*/
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
is_pmd_migration_entry(*pmd)) {
if (folio && folio != pmd_folio(*pmd))
return;
__split_huge_pmd_locked(vma, pmd, address, freeze);
}
}
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze, struct folio *folio)
{
spinlock_t *ptl;
struct mmu_notifier_range range;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
address & HPAGE_PMD_MASK,
(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
ptl = pmd_lock(vma->vm_mm, pmd);
split_huge_pmd_locked(vma, range.start, pmd, freeze, folio);
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
}
void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
bool freeze, struct folio *folio)
{
pmd_t *pmd = mm_find_pmd(vma->vm_mm, address);
if (!pmd)
return;
__split_huge_pmd(vma, pmd, address, freeze, folio);
}
static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address)
{
/*
* If the new address isn't hpage aligned and it could previously
* contain an hugepage: check if we need to split an huge pmd.
*/
if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE),
ALIGN(address, HPAGE_PMD_SIZE)))
split_huge_pmd_address(vma, address, false, NULL);
}
void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
struct vm_area_struct *next)
{
/* Check if we need to split start first. */
split_huge_pmd_if_needed(vma, start);
/* Check if we need to split end next. */
split_huge_pmd_if_needed(vma, end);
/* If we're incrementing next->vm_start, we might need to split it. */
if (next) split_huge_pmd_if_needed(next, end);
}
static void unmap_folio(struct folio *folio)
{
enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC |
TTU_BATCH_FLUSH;
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
if (folio_test_pmd_mappable(folio))
ttu_flags |= TTU_SPLIT_HUGE_PMD;
/*
* Anon pages need migration entries to preserve them, but file
* pages can simply be left unmapped, then faulted back on demand.
* If that is ever changed (perhaps for mlock), update remap_page().
*/
if (folio_test_anon(folio))
try_to_migrate(folio, ttu_flags);
else
try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK);
try_to_unmap_flush();
}
static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp,
struct folio *folio)
{
struct mm_struct *mm = vma->vm_mm;
int ref_count, map_count;
pmd_t orig_pmd = *pmdp;
if (pmd_dirty(orig_pmd))
folio_set_dirty(folio);
if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) {
folio_set_swapbacked(folio);
return false;
}
orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp);
/*
* Syncing against concurrent GUP-fast:
* - clear PMD; barrier; read refcount
* - inc refcount; barrier; read PMD
*/
smp_mb();
ref_count = folio_ref_count(folio);
map_count = folio_mapcount(folio);
/*
* Order reads for folio refcount and dirty flag
* (see comments in __remove_mapping()).
*/
smp_rmb();
/*
* If the folio or its PMD is redirtied at this point, or if there
* are unexpected references, we will give up to discard this folio
* and remap it.
*
* The only folio refs must be one from isolation plus the rmap(s).
*/
if (pmd_dirty(orig_pmd))
folio_set_dirty(folio);
if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) {
folio_set_swapbacked(folio);
set_pmd_at(mm, addr, pmdp, orig_pmd);
return false;
}
if (ref_count != map_count + 1) {
set_pmd_at(mm, addr, pmdp, orig_pmd);
return false;
}
folio_remove_rmap_pmd(folio, pmd_page(orig_pmd), vma);
zap_deposited_table(mm, pmdp);
add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR);
if (vma->vm_flags & VM_LOCKED)
mlock_drain_local();
folio_put(folio);
return true;
}
bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmdp, struct folio *folio)
{
VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio);
VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
VM_WARN_ON_FOLIO(folio_test_swapbacked(folio), folio);
VM_WARN_ON_ONCE(!IS_ALIGNED(addr, HPAGE_PMD_SIZE));
return __discard_anon_folio_pmd_locked(vma, addr, pmdp, folio);
}
static void remap_page(struct folio *folio, unsigned long nr, int flags)
{
int i = 0;
/* If unmap_folio() uses try_to_migrate() on file, remove this check */
if (!folio_test_anon(folio))
return;
for (;;) {
remove_migration_ptes(folio, folio, RMP_LOCKED | flags);
i += folio_nr_pages(folio);
if (i >= nr)
break;
folio = folio_next(folio);
}
}
static void lru_add_split_folio(struct folio *folio, struct folio *new_folio,
struct lruvec *lruvec, struct list_head *list)
{
VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio);
lockdep_assert_held(&lruvec->lru_lock);
if (list) {
/* page reclaim is reclaiming a huge page */
VM_WARN_ON(folio_test_lru(folio));
folio_get(new_folio);
list_add_tail(&new_folio->lru, list);
} else {
/* head is still on lru (and we have it frozen) */
VM_WARN_ON(!folio_test_lru(folio));
if (folio_test_unevictable(folio))
new_folio->mlock_count = 0;
else
list_add_tail(&new_folio->lru, &folio->lru);
folio_set_lru(new_folio);
}
}
/* Racy check whether the huge page can be split */
bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
{
int extra_pins;
/* Additional pins from page cache */
if (folio_test_anon(folio))
extra_pins = folio_test_swapcache(folio) ?
folio_nr_pages(folio) : 0;
else
extra_pins = folio_nr_pages(folio);
if (pextra_pins)
*pextra_pins = extra_pins;
return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins -
caller_pins;
}
/*
* It splits @folio into @new_order folios and copies the @folio metadata to
* all the resulting folios.
*/
static void __split_folio_to_order(struct folio *folio, int old_order,
int new_order)
{
long new_nr_pages = 1 << new_order;
long nr_pages = 1 << old_order;
long i;
/*
* Skip the first new_nr_pages, since the new folio from them have all
* the flags from the original folio.
*/
for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) {
struct page *new_head = &folio->page + i;
/*
* Careful: new_folio is not a "real" folio before we cleared PageTail.
* Don't pass it around before clear_compound_head().
*/
struct folio *new_folio = (struct folio *)new_head;
VM_BUG_ON_PAGE(atomic_read(&new_folio->_mapcount) != -1, new_head);
/*
* Clone page flags before unfreezing refcount.
*
* After successful get_page_unless_zero() might follow flags change,
* for example lock_page() which set PG_waiters.
*
* Note that for mapped sub-pages of an anonymous THP,
* PG_anon_exclusive has been cleared in unmap_folio() and is stored in
* the migration entry instead from where remap_page() will restore it.
* We can still have PG_anon_exclusive set on effectively unmapped and
* unreferenced sub-pages of an anonymous THP: we can simply drop
* PG_anon_exclusive (-> PG_mappedtodisk) for these here.
*/
new_folio->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
new_folio->flags |= (folio->flags &
((1L << PG_referenced) |
(1L << PG_swapbacked) |
(1L << PG_swapcache) |
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
(1L << PG_workingset) |
(1L << PG_locked) |
(1L << PG_unevictable) |
#ifdef CONFIG_ARCH_USES_PG_ARCH_2
(1L << PG_arch_2) |
#endif
#ifdef CONFIG_ARCH_USES_PG_ARCH_3
(1L << PG_arch_3) |
#endif
(1L << PG_dirty) |
LRU_GEN_MASK | LRU_REFS_MASK));
new_folio->mapping = folio->mapping;
new_folio->index = folio->index + i;
/*
* page->private should not be set in tail pages. Fix up and warn once
* if private is unexpectedly set.
*/
if (unlikely(new_folio->private)) {
VM_WARN_ON_ONCE_PAGE(true, new_head);
new_folio->private = NULL;
}
if (folio_test_swapcache(folio))
new_folio->swap.val = folio->swap.val + i;
/* Page flags must be visible before we make the page non-compound. */
smp_wmb();
/*
* Clear PageTail before unfreezing page refcount.
*
* After successful get_page_unless_zero() might follow put_page()
* which needs correct compound_head().
*/
clear_compound_head(new_head);
if (new_order) {
prep_compound_page(new_head, new_order);
folio_set_large_rmappable(new_folio);
}
if (folio_test_young(folio))
folio_set_young(new_folio);
if (folio_test_idle(folio))
folio_set_idle(new_folio);
#ifdef CONFIG_MEMCG
new_folio->memcg_data = folio->memcg_data;
#endif
folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio));
}
if (new_order)
folio_set_order(folio, new_order);
else
ClearPageCompound(&folio->page);
}
/*
* It splits an unmapped @folio to lower order smaller folios in two ways.
* @folio: the to-be-split folio
* @new_order: the smallest order of the after split folios (since buddy
* allocator like split generates folios with orders from @folio's
* order - 1 to new_order).
* @split_at: in buddy allocator like split, the folio containing @split_at
* will be split until its order becomes @new_order.
* @lock_at: the folio containing @lock_at is left locked for caller.
* @list: the after split folios will be added to @list if it is not NULL,
* otherwise to LRU lists.
* @end: the end of the file @folio maps to. -1 if @folio is anonymous memory.
* @xas: xa_state pointing to folio->mapping->i_pages and locked by caller
* @mapping: @folio->mapping
* @uniform_split: if the split is uniform or not (buddy allocator like split)
*
*
* 1. uniform split: the given @folio into multiple @new_order small folios,
* where all small folios have the same order. This is done when
* uniform_split is true.
* 2. buddy allocator like (non-uniform) split: the given @folio is split into
* half and one of the half (containing the given page) is split into half
* until the given @page's order becomes @new_order. This is done when
* uniform_split is false.
*
* The high level flow for these two methods are:
* 1. uniform split: a single __split_folio_to_order() is called to split the
* @folio into @new_order, then we traverse all the resulting folios one by
* one in PFN ascending order and perform stats, unfreeze, adding to list,
* and file mapping index operations.
* 2. non-uniform split: in general, folio_order - @new_order calls to
* __split_folio_to_order() are made in a for loop to split the @folio
* to one lower order at a time. The resulting small folios are processed
* like what is done during the traversal in 1, except the one containing
* @page, which is split in next for loop.
*
* After splitting, the caller's folio reference will be transferred to the
* folio containing @page. The other folios may be freed if they are not mapped.
*
* In terms of locking, after splitting,
* 1. uniform split leaves @page (or the folio contains it) locked;
* 2. buddy allocator like (non-uniform) split leaves @folio locked.
*
*
* For !uniform_split, when -ENOMEM is returned, the original folio might be
* split. The caller needs to check the input folio.
*/
static int __split_unmapped_folio(struct folio *folio, int new_order,
struct page *split_at, struct page *lock_at,
struct list_head *list, pgoff_t end,
struct xa_state *xas, struct address_space *mapping,
bool uniform_split)
{
struct lruvec *lruvec;
struct address_space *swap_cache = NULL;
struct folio *origin_folio = folio;
struct folio *next_folio = folio_next(folio);
struct folio *new_folio;
struct folio *next;
int order = folio_order(folio);
int split_order;
int start_order = uniform_split ? new_order : order - 1;
int nr_dropped = 0;
int ret = 0;
bool stop_split = false;
if (folio_test_swapcache(folio)) {
VM_BUG_ON(mapping);
/* a swapcache folio can only be uniformly split to order-0 */
if (!uniform_split || new_order != 0)
return -EINVAL;
swap_cache = swap_address_space(folio->swap);
xa_lock(&swap_cache->i_pages);
}
if (folio_test_anon(folio))
mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
/* lock lru list/PageCompound, ref frozen by page_ref_freeze */
lruvec = folio_lruvec_lock(folio);
folio_clear_has_hwpoisoned(folio);
/*
* split to new_order one order at a time. For uniform split,
* folio is split to new_order directly.
*/
for (split_order = start_order;
split_order >= new_order && !stop_split;
split_order--) {
int old_order = folio_order(folio);
struct folio *release;
struct folio *end_folio = folio_next(folio);
/* order-1 anonymous folio is not supported */
if (folio_test_anon(folio) && split_order == 1)
continue;
if (uniform_split && split_order != new_order)
continue;
if (mapping) {
/*
* uniform split has xas_split_alloc() called before
* irq is disabled to allocate enough memory, whereas
* non-uniform split can handle ENOMEM.
*/
if (uniform_split)
xas_split(xas, folio, old_order);
else {
xas_set_order(xas, folio->index, split_order);
xas_try_split(xas, folio, old_order);
if (xas_error(xas)) {
ret = xas_error(xas);
stop_split = true;
goto after_split;
}
}
}
folio_split_memcg_refs(folio, old_order, split_order);
split_page_owner(&folio->page, old_order, split_order);
pgalloc_tag_split(folio, old_order, split_order);
__split_folio_to_order(folio, old_order, split_order);
after_split:
/*
* Iterate through after-split folios and perform related
* operations. But in buddy allocator like split, the folio
* containing the specified page is skipped until its order
* is new_order, since the folio will be worked on in next
* iteration.
*/
for (release = folio; release != end_folio; release = next) {
next = folio_next(release);
/*
* for buddy allocator like split, the folio containing
* page will be split next and should not be released,
* until the folio's order is new_order or stop_split
* is set to true by the above xas_split() failure.
*/
if (release == page_folio(split_at)) {
folio = release;
if (split_order != new_order && !stop_split)
continue;
}
if (folio_test_anon(release)) {
mod_mthp_stat(folio_order(release),
MTHP_STAT_NR_ANON, 1);
}
/*
* origin_folio should be kept frozon until page cache
* entries are updated with all the other after-split
* folios to prevent others seeing stale page cache
* entries.
*/
if (release == origin_folio)
continue;
folio_ref_unfreeze(release, 1 +
((mapping || swap_cache) ?
folio_nr_pages(release) : 0));
lru_add_split_folio(origin_folio, release, lruvec,
list);
/* Some pages can be beyond EOF: drop them from cache */
if (release->index >= end) {
if (shmem_mapping(mapping))
nr_dropped += folio_nr_pages(release);
else if (folio_test_clear_dirty(release))
folio_account_cleaned(release,
inode_to_wb(mapping->host));
__filemap_remove_folio(release, NULL);
folio_put_refs(release, folio_nr_pages(release));
} else if (mapping) {
__xa_store(&mapping->i_pages,
release->index, release, 0);
} else if (swap_cache) {
__xa_store(&swap_cache->i_pages,
swap_cache_index(release->swap),
release, 0);
}
}
}
/*
* Unfreeze origin_folio only after all page cache entries, which used
* to point to it, have been updated with new folios. Otherwise,
* a parallel folio_try_get() can grab origin_folio and its caller can
* see stale page cache entries.
*/
folio_ref_unfreeze(origin_folio, 1 +
((mapping || swap_cache) ? folio_nr_pages(origin_folio) : 0));
unlock_page_lruvec(lruvec);
if (swap_cache)
xa_unlock(&swap_cache->i_pages);
if (mapping)
xa_unlock(&mapping->i_pages);
/* Caller disabled irqs, so they are still disabled here */
local_irq_enable();
if (nr_dropped)
shmem_uncharge(mapping->host, nr_dropped);
remap_page(origin_folio, 1 << order,
folio_test_anon(origin_folio) ?
RMP_USE_SHARED_ZEROPAGE : 0);
/*
* At this point, folio should contain the specified page.
* For uniform split, it is left for caller to unlock.
* For buddy allocator like split, the first after-split folio is left
* for caller to unlock.
*/
for (new_folio = origin_folio; new_folio != next_folio; new_folio = next) {
next = folio_next(new_folio);
if (new_folio == page_folio(lock_at))
continue;
folio_unlock(new_folio);
/*
* Subpages may be freed if there wasn't any mapping
* like if add_to_swap() is running on a lru page that
* had its mapping zapped. And freeing these pages
* requires taking the lru_lock so we do the put_page
* of the tail pages after the split is complete.
*/
free_page_and_swap_cache(&new_folio->page);
}
return ret;
}
bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
bool warns)
{
if (folio_test_anon(folio)) {
/* order-1 is not supported for anonymous THP. */
VM_WARN_ONCE(warns && new_order == 1,
"Cannot split to order-1 folio");
return new_order != 1;
} else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
!mapping_large_folio_support(folio->mapping)) {
/*
* No split if the file system does not support large folio.
* Note that we might still have THPs in such mappings due to
* CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping
* does not actually support large folios properly.
*/
VM_WARN_ONCE(warns,
"Cannot split file folio to non-0 order");
return false;
}
/* Only swapping a whole PMD-mapped folio is supported */
if (folio_test_swapcache(folio)) {
VM_WARN_ONCE(warns,
"Cannot split swapcache folio to non-0 order");
return false;
}
return true;
}
/* See comments in non_uniform_split_supported() */
bool uniform_split_supported(struct folio *folio, unsigned int new_order,
bool warns)
{
if (folio_test_anon(folio)) {
VM_WARN_ONCE(warns && new_order == 1,
"Cannot split to order-1 folio");
return new_order != 1;
} else if (new_order) {
if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
!mapping_large_folio_support(folio->mapping)) {
VM_WARN_ONCE(warns,
"Cannot split file folio to non-0 order");
return false;
}
}
if (new_order && folio_test_swapcache(folio)) {
VM_WARN_ONCE(warns,
"Cannot split swapcache folio to non-0 order");
return false;
}
return true;
}
/*
* __folio_split: split a folio at @split_at to a @new_order folio
* @folio: folio to split
* @new_order: the order of the new folio
* @split_at: a page within the new folio
* @lock_at: a page within @folio to be left locked to caller
* @list: after-split folios will be put on it if non NULL
* @uniform_split: perform uniform split or not (non-uniform split)
*
* It calls __split_unmapped_folio() to perform uniform and non-uniform split.
* It is in charge of checking whether the split is supported or not and
* preparing @folio for __split_unmapped_folio().
*
* return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be
* split but not to @new_order, the caller needs to check)
*/
static int __folio_split(struct folio *folio, unsigned int new_order,
struct page *split_at, struct page *lock_at,
struct list_head *list, bool uniform_split)
{
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
XA_STATE(xas, &folio->mapping->i_pages, folio->index);
bool is_anon = folio_test_anon(folio);
struct address_space *mapping = NULL;
struct anon_vma *anon_vma = NULL;
int order = folio_order(folio);
int extra_pins, ret;
pgoff_t end;
bool is_hzp;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
if (folio != page_folio(split_at) || folio != page_folio(lock_at))
return -EINVAL;
if (new_order >= folio_order(folio))
return -EINVAL;
if (uniform_split && !uniform_split_supported(folio, new_order, true))
return -EINVAL;
if (!uniform_split &&
!non_uniform_split_supported(folio, new_order, true))
return -EINVAL;
is_hzp = is_huge_zero_folio(folio);
if (is_hzp) {
pr_warn_ratelimited("Called split_huge_page for huge zero page\n");
return -EBUSY;
}
if (folio_test_writeback(folio))
return -EBUSY;
if (is_anon) {
/*
* The caller does not necessarily hold an mmap_lock that would
* prevent the anon_vma disappearing so we first we take a
* reference to it and then lock the anon_vma for write. This
* is similar to folio_lock_anon_vma_read except the write lock
* is taken to serialise against parallel split or collapse
* operations.
*/
anon_vma = folio_get_anon_vma(folio);
if (!anon_vma) {
ret = -EBUSY;
goto out;
}
end = -1;
mapping = NULL;
anon_vma_lock_write(anon_vma);
} else {
unsigned int min_order;
gfp_t gfp;
mapping = folio->mapping;
/* Truncated ? */
/*
* TODO: add support for large shmem folio in swap cache.
* When shmem is in swap cache, mapping is NULL and
* folio_test_swapcache() is true.
*/
if (!mapping) {
ret = -EBUSY;
goto out;
}
min_order = mapping_min_folio_order(folio->mapping);
if (new_order < min_order) {
VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
min_order);
ret = -EINVAL;
goto out;
}
gfp = current_gfp_context(mapping_gfp_mask(mapping) &
GFP_RECLAIM_MASK);
if (!filemap_release_folio(folio, gfp)) {
ret = -EBUSY;
goto out;
}
if (uniform_split) {
xas_set_order(&xas, folio->index, new_order);
xas_split_alloc(&xas, folio, folio_order(folio), gfp);
if (xas_error(&xas)) {
ret = xas_error(&xas);
goto out;
}
}
anon_vma = NULL;
i_mmap_lock_read(mapping);
/*
*__split_unmapped_folio() may need to trim off pages beyond
* EOF: but on 32-bit, i_size_read() takes an irq-unsafe
* seqlock, which cannot be nested inside the page tree lock.
* So note end now: i_size itself may be changed at any moment,
* but folio lock is good enough to serialize the trimming.
*/
end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
if (shmem_mapping(mapping))
end = shmem_fallocend(mapping->host, end);
}
/*
* Racy check if we can split the page, before unmap_folio() will
* split PMDs
*/
if (!can_split_folio(folio, 1, &extra_pins)) {
ret = -EAGAIN;
goto out_unlock;
}
unmap_folio(folio);
/* block interrupt reentry in xa_lock and spinlock */
local_irq_disable();
if (mapping) {
/*
* Check if the folio is present in page cache.
* We assume all tail are present too, if folio is there.
*/
xas_lock(&xas);
xas_reset(&xas);
if (xas_load(&xas) != folio)
goto fail;
}
/* Prevent deferred_split_scan() touching ->_refcount */
spin_lock(&ds_queue->split_queue_lock);
if (folio_ref_freeze(folio, 1 + extra_pins)) {
if (folio_order(folio) > 1 &&
!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
if (folio_test_partially_mapped(folio)) {
folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
/*
* Reinitialize page_deferred_list after removing the
* page from the split_queue, otherwise a subsequent
* split will see list corruption when checking the
* page_deferred_list.
*/
list_del_init(&folio->_deferred_list);
}
spin_unlock(&ds_queue->split_queue_lock);
if (mapping) {
int nr = folio_nr_pages(folio);
if (folio_test_pmd_mappable(folio) &&
new_order < HPAGE_PMD_ORDER) {
if (folio_test_swapbacked(folio)) {
__lruvec_stat_mod_folio(folio,
NR_SHMEM_THPS, -nr);
} else {
__lruvec_stat_mod_folio(folio,
NR_FILE_THPS, -nr);
filemap_nr_thps_dec(mapping);
}
}
}
ret = __split_unmapped_folio(folio, new_order,
split_at, lock_at, list, end, &xas, mapping,
uniform_split);
} else {
spin_unlock(&ds_queue->split_queue_lock);
fail:
if (mapping)
xas_unlock(&xas);
local_irq_enable();
remap_page(folio, folio_nr_pages(folio), 0);
ret = -EAGAIN;
}
out_unlock:
if (anon_vma) {
anon_vma_unlock_write(anon_vma);
put_anon_vma(anon_vma);
}
if (mapping)
i_mmap_unlock_read(mapping);
out:
xas_destroy(&xas);
if (order == HPAGE_PMD_ORDER)
count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
count_mthp_stat(order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED);
return ret;
}
/*
* This function splits a large folio into smaller folios of order @new_order.
* @page can point to any page of the large folio to split. The split operation
* does not change the position of @page.
*
* Prerequisites:
*
* 1) The caller must hold a reference on the @page's owning folio, also known
* as the large folio.
*
* 2) The large folio must be locked.
*
* 3) The folio must not be pinned. Any unexpected folio references, including
* GUP pins, will result in the folio not getting split; instead, the caller
* will receive an -EAGAIN.
*
* 4) @new_order > 1, usually. Splitting to order-1 anonymous folios is not
* supported for non-file-backed folios, because folio->_deferred_list, which
* is used by partially mapped folios, is stored in subpage 2, but an order-1
* folio only has subpages 0 and 1. File-backed order-1 folios are supported,
* since they do not use _deferred_list.
*
* After splitting, the caller's folio reference will be transferred to @page,
* resulting in a raised refcount of @page after this call. The other pages may
* be freed if they are not mapped.
*
* If @list is null, tail pages will be added to LRU list, otherwise, to @list.
*
* Pages in @new_order will inherit the mapping, flags, and so on from the
* huge page.
*
* Returns 0 if the huge page was split successfully.
*
* Returns -EAGAIN if the folio has unexpected reference (e.g., GUP) or if
* the folio was concurrently removed from the page cache.
*
* Returns -EBUSY when trying to split the huge zeropage, if the folio is
* under writeback, if fs-specific folio metadata cannot currently be
* released, or if some unexpected race happened (e.g., anon VMA disappeared,
* truncation).
*
* Callers should ensure that the order respects the address space mapping
* min-order if one is set for non-anonymous folios.
*
* Returns -EINVAL when trying to split to an order that is incompatible
* with the folio. Splitting to order 0 is compatible with all folios.
*/
int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
unsigned int new_order)
{
struct folio *folio = page_folio(page);
return __folio_split(folio, new_order, &folio->page, page, list, true);
}
/*
* folio_split: split a folio at @split_at to a @new_order folio
* @folio: folio to split
* @new_order: the order of the new folio
* @split_at: a page within the new folio
*
* return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be
* split but not to @new_order, the caller needs to check)
*
* It has the same prerequisites and returns as
* split_huge_page_to_list_to_order().
*
* Split a folio at @split_at to a new_order folio, leave the
* remaining subpages of the original folio as large as possible. For example,
* in the case of splitting an order-9 folio at its third order-3 subpages to
* an order-3 folio, there are 2^(9-3)=64 order-3 subpages in the order-9 folio.
* After the split, there will be a group of folios with different orders and
* the new folio containing @split_at is marked in bracket:
* [order-4, {order-3}, order-3, order-5, order-6, order-7, order-8].
*
* After split, folio is left locked for caller.
*/
int folio_split(struct folio *folio, unsigned int new_order,
struct page *split_at, struct list_head *list)
{
return __folio_split(folio, new_order, split_at, &folio->page, list,
false);
}
int min_order_for_split(struct folio *folio)
{
if (folio_test_anon(folio))
return 0;
if (!folio->mapping) {
if (folio_test_pmd_mappable(folio))
count_vm_event(THP_SPLIT_PAGE_FAILED);
return -EBUSY;
}
return mapping_min_folio_order(folio->mapping);
}
int split_folio_to_list(struct folio *folio, struct list_head *list)
{
int ret = min_order_for_split(folio);
if (ret < 0)
return ret;
return split_huge_page_to_list_to_order(&folio->page, list, ret);
}
/*
* __folio_unqueue_deferred_split() is not to be called directly:
* the folio_unqueue_deferred_split() inline wrapper in mm/internal.h
* limits its calls to those folios which may have a _deferred_list for
* queueing THP splits, and that list is (racily observed to be) non-empty.
*
* It is unsafe to call folio_unqueue_deferred_split() until folio refcount is
* zero: because even when split_queue_lock is held, a non-empty _deferred_list
* might be in use on deferred_split_scan()'s unlocked on-stack list.
*
* If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is
* therefore important to unqueue deferred split before changing folio memcg.
*/
bool __folio_unqueue_deferred_split(struct folio *folio)
{
struct deferred_split *ds_queue;
unsigned long flags;
bool unqueued = false;
WARN_ON_ONCE(folio_ref_count(folio));
WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio));
ds_queue = get_deferred_split_queue(folio);
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
if (folio_test_partially_mapped(folio)) {
folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
list_del_init(&folio->_deferred_list);
unqueued = true;
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
return unqueued; /* useful for debug warnings */
}
/* partially_mapped=false won't clear PG_partially_mapped folio flag */
void deferred_split_folio(struct folio *folio, bool partially_mapped)
{
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg = folio_memcg(folio);
#endif
unsigned long flags;
/*
* Order 1 folios have no space for a deferred list, but we also
* won't waste much memory by not adding them to the deferred list.
*/
if (folio_order(folio) <= 1)
return;
if (!partially_mapped && !split_underused_thp)
return;
/*
* Exclude swapcache: originally to avoid a corrupt deferred split
* queue. Nowadays that is fully prevented by memcg1_swapout();
* but if page reclaim is already handling the same folio, it is
* unnecessary to handle it again in the shrinker, so excluding
* swapcache here may still be a useful optimization.
*/
if (folio_test_swapcache(folio))
return;
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (partially_mapped) {
if (!folio_test_partially_mapped(folio)) {
folio_set_partially_mapped(folio);
if (folio_test_pmd_mappable(folio))
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1);
}
} else {
/* partially mapped folios cannot become non-partially mapped */
VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
}
if (list_empty(&folio->_deferred_list)) {
list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
ds_queue->split_queue_len++;
#ifdef CONFIG_MEMCG
if (memcg)
set_shrinker_bit(memcg, folio_nid(folio),
deferred_split_shrinker->id);
#endif
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}
static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
#ifdef CONFIG_MEMCG
if (sc->memcg)
ds_queue = &sc->memcg->deferred_split_queue;
#endif
return READ_ONCE(ds_queue->split_queue_len);
}
static bool thp_underused(struct folio *folio)
{
int num_zero_pages = 0, num_filled_pages = 0;
void *kaddr;
int i;
if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1)
return false;
for (i = 0; i < folio_nr_pages(folio); i++) {
kaddr = kmap_local_folio(folio, i * PAGE_SIZE);
if (!memchr_inv(kaddr, 0, PAGE_SIZE)) {
num_zero_pages++;
if (num_zero_pages > khugepaged_max_ptes_none) {
kunmap_local(kaddr);
return true;
}
} else {
/*
* Another path for early exit once the number
* of non-zero filled pages exceeds threshold.
*/
num_filled_pages++;
if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) {
kunmap_local(kaddr);
return false;
}
}
kunmap_local(kaddr);
}
return false;
}
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
unsigned long flags;
LIST_HEAD(list);
struct folio *folio, *next, *prev = NULL;
int split = 0, removed = 0;
#ifdef CONFIG_MEMCG
if (sc->memcg)
ds_queue = &sc->memcg->deferred_split_queue;
#endif
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
/* Take pin on all head pages to avoid freeing them under us */
list_for_each_entry_safe(folio, next, &ds_queue->split_queue,
_deferred_list) {
if (folio_try_get(folio)) {
list_move(&folio->_deferred_list, &list);
} else {
/* We lost race with folio_put() */
if (folio_test_partially_mapped(folio)) {
folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
list_del_init(&folio->_deferred_list);
ds_queue->split_queue_len--;
}
if (!--sc->nr_to_scan)
break;
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
list_for_each_entry_safe(folio, next, &list, _deferred_list) {
bool did_split = false;
bool underused = false;
if (!folio_test_partially_mapped(folio)) {
underused = thp_underused(folio);
if (!underused)
goto next;
}
if (!folio_trylock(folio))
goto next;
if (!split_folio(folio)) {
did_split = true;
if (underused)
count_vm_event(THP_UNDERUSED_SPLIT_PAGE);
split++;
}
folio_unlock(folio);
next:
/*
* split_folio() removes folio from list on success.
* Only add back to the queue if folio is partially mapped.
* If thp_underused returns false, or if split_folio fails
* in the case it was underused, then consider it used and
* don't add it back to split_queue.
*/
if (did_split) {
; /* folio already removed from list */
} else if (!folio_test_partially_mapped(folio)) {
list_del_init(&folio->_deferred_list);
removed++;
} else {
/*
* That unlocked list_del_init() above would be unsafe,
* unless its folio is separated from any earlier folios
* left on the list (which may be concurrently unqueued)
* by one safe folio with refcount still raised.
*/
swap(folio, prev);
}
if (folio)
folio_put(folio);
}
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
list_splice_tail(&list, &ds_queue->split_queue);
ds_queue->split_queue_len -= removed;
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
if (prev)
folio_put(prev);
/*
* Stop shrinker if we didn't split any page, but the queue is empty.
* This can happen if pages were freed under us.
*/
if (!split && list_empty(&ds_queue->split_queue))
return SHRINK_STOP;
return split;
}
#ifdef CONFIG_DEBUG_FS
static void split_huge_pages_all(void)
{
struct zone *zone;
struct page *page;
struct folio *folio;
unsigned long pfn, max_zone_pfn;
unsigned long total = 0, split = 0;
pr_debug("Split all THPs\n");
for_each_zone(zone) {
if (!managed_zone(zone))
continue;
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
int nr_pages;
page = pfn_to_online_page(pfn);
if (!page || PageTail(page))
continue;
folio = page_folio(page);
if (!folio_try_get(folio))
continue;
if (unlikely(page_folio(page) != folio))
goto next;
if (zone != folio_zone(folio))
goto next;
if (!folio_test_large(folio)
|| folio_test_hugetlb(folio)
|| !folio_test_lru(folio))
goto next;
total++;
folio_lock(folio);
nr_pages = folio_nr_pages(folio);
if (!split_folio(folio))
split++;
pfn += nr_pages - 1;
folio_unlock(folio);
next:
folio_put(folio);
cond_resched();
}
}
pr_debug("%lu of %lu THP split\n", split, total);
}
static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma)
{
return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) ||
is_vm_hugetlb_page(vma);
}
static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
unsigned long vaddr_end, unsigned int new_order,
long in_folio_offset)
{
int ret = 0;
struct task_struct *task;
struct mm_struct *mm;
unsigned long total = 0, split = 0;
unsigned long addr;
vaddr_start &= PAGE_MASK;
vaddr_end &= PAGE_MASK;
task = find_get_task_by_vpid(pid);
if (!task) {
ret = -ESRCH;
goto out;
}
/* Find the mm_struct */
mm = get_task_mm(task);
put_task_struct(task);
if (!mm) {
ret = -EINVAL;
goto out;
}
pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
pid, vaddr_start, vaddr_end);
mmap_read_lock(mm);
/*
* always increase addr by PAGE_SIZE, since we could have a PTE page
* table filled with PTE-mapped THPs, each of which is distinct.
*/
for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
struct vm_area_struct *vma = vma_lookup(mm, addr);
struct folio_walk fw;
struct folio *folio;
struct address_space *mapping;
unsigned int target_order = new_order;
if (!vma)
break;
/* skip special VMA and hugetlb VMA */
if (vma_not_suitable_for_thp_split(vma)) {
addr = vma->vm_end;
continue;
}
folio = folio_walk_start(&fw, vma, addr, 0);
if (!folio)
continue;
if (!is_transparent_hugepage(folio))
goto next;
if (!folio_test_anon(folio)) {
mapping = folio->mapping;
target_order = max(new_order,
mapping_min_folio_order(mapping));
}
if (target_order >= folio_order(folio))
goto next;
total++;
/*
* For folios with private, split_huge_page_to_list_to_order()
* will try to drop it before split and then check if the folio
* can be split or not. So skip the check here.
*/
if (!folio_test_private(folio) &&
!can_split_folio(folio, 0, NULL))
goto next;
if (!folio_trylock(folio))
goto next;
folio_get(folio);
folio_walk_end(&fw, vma);
if (!folio_test_anon(folio) && folio->mapping != mapping)
goto unlock;
if (in_folio_offset < 0 ||
in_folio_offset >= folio_nr_pages(folio)) {
if (!split_folio_to_order(folio, target_order))
split++;
} else {
struct page *split_at = folio_page(folio,
in_folio_offset);
if (!folio_split(folio, target_order, split_at, NULL))
split++;
}
unlock:
folio_unlock(folio);
folio_put(folio);
cond_resched();
continue;
next:
folio_walk_end(&fw, vma);
cond_resched();
}
mmap_read_unlock(mm);
mmput(mm);
pr_debug("%lu of %lu THP split\n", split, total);
out:
return ret;
}
static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
pgoff_t off_end, unsigned int new_order,
long in_folio_offset)
{
struct filename *file;
struct file *candidate;
struct address_space *mapping;
int ret = -EINVAL;
pgoff_t index;
int nr_pages = 1;
unsigned long total = 0, split = 0;
unsigned int min_order;
unsigned int target_order;
file = getname_kernel(file_path);
if (IS_ERR(file))
return ret;
candidate = file_open_name(file, O_RDONLY, 0);
if (IS_ERR(candidate))
goto out;
pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n",
file_path, off_start, off_end);
mapping = candidate->f_mapping;
min_order = mapping_min_folio_order(mapping);
target_order = max(new_order, min_order);
for (index = off_start; index < off_end; index += nr_pages) {
struct folio *folio = filemap_get_folio(mapping, index);
nr_pages = 1;
if (IS_ERR(folio))
continue;
if (!folio_test_large(folio))
goto next;
total++;
nr_pages = folio_nr_pages(folio);
if (target_order >= folio_order(folio))
goto next;
if (!folio_trylock(folio))
goto next;
if (folio->mapping != mapping)
goto unlock;
if (in_folio_offset < 0 || in_folio_offset >= nr_pages) {
if (!split_folio_to_order(folio, target_order))
split++;
} else {
struct page *split_at = folio_page(folio,
in_folio_offset);
if (!folio_split(folio, target_order, split_at, NULL))
split++;
}
unlock:
folio_unlock(folio);
next:
folio_put(folio);
cond_resched();
}
filp_close(candidate, NULL);
ret = 0;
pr_debug("%lu of %lu file-backed THP split\n", split, total);
out:
putname(file);
return ret;
}
#define MAX_INPUT_BUF_SZ 255
static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppops)
{
static DEFINE_MUTEX(split_debug_mutex);
ssize_t ret;
/*
* hold pid, start_vaddr, end_vaddr, new_order or
* file_path, off_start, off_end, new_order
*/
char input_buf[MAX_INPUT_BUF_SZ];
int pid;
unsigned long vaddr_start, vaddr_end;
unsigned int new_order = 0;
long in_folio_offset = -1;
ret = mutex_lock_interruptible(&split_debug_mutex);
if (ret)
return ret;
ret = -EFAULT;
memset(input_buf, 0, MAX_INPUT_BUF_SZ);
if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ)))
goto out;
input_buf[MAX_INPUT_BUF_SZ - 1] = '\0';
if (input_buf[0] == '/') {
char *tok;
char *tok_buf = input_buf;
char file_path[MAX_INPUT_BUF_SZ];
pgoff_t off_start = 0, off_end = 0;
size_t input_len = strlen(input_buf);
tok = strsep(&tok_buf, ",");
if (tok && tok_buf) {
strscpy(file_path, tok);
} else {
ret = -EINVAL;
goto out;
}
ret = sscanf(tok_buf, "0x%lx,0x%lx,%d,%ld", &off_start, &off_end,
&new_order, &in_folio_offset);
if (ret != 2 && ret != 3 && ret != 4) {
ret = -EINVAL;
goto out;
}
ret = split_huge_pages_in_file(file_path, off_start, off_end,
new_order, in_folio_offset);
if (!ret)
ret = input_len;
goto out;
}
ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d,%ld", &pid, &vaddr_start,
&vaddr_end, &new_order, &in_folio_offset);
if (ret == 1 && pid == 1) {
split_huge_pages_all();
ret = strlen(input_buf);
goto out;
} else if (ret != 3 && ret != 4 && ret != 5) {
ret = -EINVAL;
goto out;
}
ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order,
in_folio_offset);
if (!ret)
ret = strlen(input_buf);
out:
mutex_unlock(&split_debug_mutex);
return ret;
}
static const struct file_operations split_huge_pages_fops = {
.owner = THIS_MODULE,
.write = split_huge_pages_write,
};
static int __init split_huge_pages_debugfs(void)
{
debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
&split_huge_pages_fops);
return 0;
}
late_initcall(split_huge_pages_debugfs);
#endif
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
struct page *page)
{
struct folio *folio = page_folio(page);
struct vm_area_struct *vma = pvmw->vma;
struct mm_struct *mm = vma->vm_mm;
unsigned long address = pvmw->address;
bool anon_exclusive;
pmd_t pmdval;
swp_entry_t entry;
pmd_t pmdswp;
if (!(pvmw->pmd && !pvmw->pte))
return 0;
flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
/* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) {
set_pmd_at(mm, address, pvmw->pmd, pmdval);
return -EBUSY;
}
if (pmd_dirty(pmdval))
folio_mark_dirty(folio);
if (pmd_write(pmdval))
entry = make_writable_migration_entry(page_to_pfn(page));
else if (anon_exclusive)
entry = make_readable_exclusive_migration_entry(page_to_pfn(page));
else
entry = make_readable_migration_entry(page_to_pfn(page));
if (pmd_young(pmdval))
entry = make_migration_entry_young(entry);
if (pmd_dirty(pmdval))
entry = make_migration_entry_dirty(entry);
pmdswp = swp_entry_to_pmd(entry);
if (pmd_soft_dirty(pmdval))
pmdswp = pmd_swp_mksoft_dirty(pmdswp);
if (pmd_uffd_wp(pmdval))
pmdswp = pmd_swp_mkuffd_wp(pmdswp);
set_pmd_at(mm, address, pvmw->pmd, pmdswp);
folio_remove_rmap_pmd(folio, page, vma);
folio_put(folio);
trace_set_migration_pmd(address, pmd_val(pmdswp));
return 0;
}
void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
{
struct folio *folio = page_folio(new);
struct vm_area_struct *vma = pvmw->vma;
struct mm_struct *mm = vma->vm_mm;
unsigned long address = pvmw->address;
unsigned long haddr = address & HPAGE_PMD_MASK;
pmd_t pmde;
swp_entry_t entry;
if (!(pvmw->pmd && !pvmw->pte))
return;
entry = pmd_to_swp_entry(*pvmw->pmd);
folio_get(folio);
pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
if (pmd_swp_soft_dirty(*pvmw->pmd))
pmde = pmd_mksoft_dirty(pmde);
if (is_writable_migration_entry(entry))
pmde = pmd_mkwrite(pmde, vma);
if (pmd_swp_uffd_wp(*pvmw->pmd))
pmde = pmd_mkuffd_wp(pmde);
if (!is_migration_entry_young(entry))
pmde = pmd_mkold(pmde);
/* NOTE: this may contain setting soft-dirty on some archs */
if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
pmde = pmd_mkdirty(pmde);
if (folio_test_anon(folio)) {
rmap_t rmap_flags = RMAP_NONE;
if (!is_readable_migration_entry(entry))
rmap_flags |= RMAP_EXCLUSIVE;
folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags);
} else {
folio_add_file_rmap_pmd(folio, new, vma);
}
VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new));
set_pmd_at(mm, haddr, pvmw->pmd, pmde);
/* No need to invalidate - it was non-present before */
update_mmu_cache_pmd(vma, address, pvmw->pmd);
trace_remove_migration_pmd(address, pmd_val(pmde));
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic pidhash and scalable, time-bounded PID allocator
*
* (C) 2002-2003 Nadia Yvette Chambers, IBM
* (C) 2004 Nadia Yvette Chambers, Oracle
* (C) 2002-2004 Ingo Molnar, Red Hat
*
* pid-structures are backing objects for tasks sharing a given ID to chain
* against. There is very little to them aside from hashing them and
* parking tasks using given ID's on a list.
*
* The hash is always changed with the tasklist_lock write-acquired,
* and the hash is only accessed with the tasklist_lock at least
* read-acquired, so there's no additional SMP locking needed here.
*
* We have a list of bitmap pages, which bitmaps represent the PID space.
* Allocating and freeing PIDs is completely lockless. The worst-case
* allocation scenario when all but one out of 1 million PIDs possible are
* allocated already: the scanning of 32 list entries and at most PAGE_SIZE
* bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
*
* Pid namespaces:
* (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
* (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
* Many thanks to Oleg Nesterov for comments and help
*
*/
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/memblock.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/refcount.h>
#include <linux/anon_inodes.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/idr.h>
#include <linux/pidfs.h>
#include <linux/seqlock.h>
#include <net/sock.h>
#include <uapi/linux/pidfd.h>
struct pid init_struct_pid = {
.count = REFCOUNT_INIT(1),
.tasks = {
{ .first = NULL },
{ .first = NULL },
{ .first = NULL },
},
.level = 0,
.numbers = { {
.nr = 0,
.ns = &init_pid_ns,
}, }
};
static int pid_max_min = RESERVED_PIDS + 1;
static int pid_max_max = PID_MAX_LIMIT;
/*
* PID-map pages start out as NULL, they get allocated upon
* first use and are never deallocated. This way a low pid_max
* value does not cause lots of bitmaps to be allocated, but
* the scheme scales to up to 4 million PIDs, runtime.
*/
struct pid_namespace init_pid_ns = {
.ns.count = REFCOUNT_INIT(2),
.idr = IDR_INIT(init_pid_ns.idr),
.pid_allocated = PIDNS_ADDING,
.level = 0,
.child_reaper = &init_task,
.user_ns = &init_user_ns,
.ns.inum = PROC_PID_INIT_INO,
#ifdef CONFIG_PID_NS
.ns.ops = &pidns_operations,
#endif
.pid_max = PID_MAX_DEFAULT,
#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
#endif
};
EXPORT_SYMBOL_GPL(init_pid_ns);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock);
void put_pid(struct pid *pid)
{
struct pid_namespace *ns;
if (!pid)
return;
ns = pid->numbers[pid->level].ns;
if (refcount_dec_and_test(&pid->count)) {
kmem_cache_free(ns->pid_cachep, pid);
put_pid_ns(ns);
}
}
EXPORT_SYMBOL_GPL(put_pid);
static void delayed_put_pid(struct rcu_head *rhp)
{
struct pid *pid = container_of(rhp, struct pid, rcu);
put_pid(pid);
}
void free_pid(struct pid *pid)
{
int i;
lockdep_assert_not_held(&tasklist_lock);
spin_lock(&pidmap_lock);
for (i = 0; i <= pid->level; i++) {
struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns;
switch (--ns->pid_allocated) {
case 2:
case 1:
/* When all that is left in the pid namespace
* is the reaper wake up the reaper. The reaper
* may be sleeping in zap_pid_ns_processes().
*/
wake_up_process(ns->child_reaper);
break;
case PIDNS_ADDING:
/* Handle a fork failure of the first process */
WARN_ON(ns->child_reaper);
ns->pid_allocated = 0;
break;
}
idr_remove(&ns->idr, upid->nr);
}
pidfs_remove_pid(pid);
spin_unlock(&pidmap_lock);
call_rcu(&pid->rcu, delayed_put_pid);
}
void free_pids(struct pid **pids)
{
int tmp;
/*
* This can batch pidmap_lock.
*/
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (pids[tmp])
free_pid(pids[tmp]);
}
struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
size_t set_tid_size)
{
struct pid *pid;
enum pid_type type;
int i, nr;
struct pid_namespace *tmp;
struct upid *upid;
int retval = -ENOMEM;
/*
* set_tid_size contains the size of the set_tid array. Starting at
* the most nested currently active PID namespace it tells alloc_pid()
* which PID to set for a process in that most nested PID namespace
* up to set_tid_size PID namespaces. It does not have to set the PID
* for a process in all nested PID namespaces but set_tid_size must
* never be greater than the current ns->level + 1.
*/
if (set_tid_size > ns->level + 1)
return ERR_PTR(-EINVAL);
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
return ERR_PTR(retval);
tmp = ns;
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
int tid = 0;
int pid_max = READ_ONCE(tmp->pid_max);
if (set_tid_size) {
tid = set_tid[ns->level - i];
retval = -EINVAL;
if (tid < 1 || tid >= pid_max)
goto out_free;
/*
* Also fail if a PID != 1 is requested and
* no PID 1 exists.
*/
if (tid != 1 && !tmp->child_reaper)
goto out_free;
retval = -EPERM;
if (!checkpoint_restore_ns_capable(tmp->user_ns))
goto out_free;
set_tid_size--;
}
idr_preload(GFP_KERNEL);
spin_lock(&pidmap_lock);
if (tid) {
nr = idr_alloc(&tmp->idr, NULL, tid,
tid + 1, GFP_ATOMIC);
/*
* If ENOSPC is returned it means that the PID is
* alreay in use. Return EEXIST in that case.
*/
if (nr == -ENOSPC)
nr = -EEXIST;
} else {
int pid_min = 1;
/*
* init really needs pid 1, but after reaching the
* maximum wrap back to RESERVED_PIDS
*/
if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
pid_min = RESERVED_PIDS;
/*
* Store a null pointer so find_pid_ns does not find
* a partially initialized PID (see below).
*/
nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
pid_max, GFP_ATOMIC);
}
spin_unlock(&pidmap_lock);
idr_preload_end();
if (nr < 0) {
retval = (nr == -ENOSPC) ? -EAGAIN : nr;
goto out_free;
}
pid->numbers[i].nr = nr;
pid->numbers[i].ns = tmp;
tmp = tmp->parent;
}
/*
* ENOMEM is not the most obvious choice especially for the case
* where the child subreaper has already exited and the pid
* namespace denies the creation of any new processes. But ENOMEM
* is what we have exposed to userspace for a long time and it is
* documented behavior for pid namespaces. So we can't easily
* change it even if there were an error code better suited.
*/
retval = -ENOMEM;
get_pid_ns(ns);
refcount_set(&pid->count, 1);
spin_lock_init(&pid->lock);
for (type = 0; type < PIDTYPE_MAX; ++type)
INIT_HLIST_HEAD(&pid->tasks[type]);
init_waitqueue_head(&pid->wait_pidfd);
INIT_HLIST_HEAD(&pid->inodes);
upid = pid->numbers + ns->level;
idr_preload(GFP_KERNEL);
spin_lock(&pidmap_lock);
if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
pidfs_add_pid(pid);
for ( ; upid >= pid->numbers; --upid) {
/* Make the PID visible to find_pid_ns. */
idr_replace(&upid->ns->idr, pid, upid->nr);
upid->ns->pid_allocated++;
}
spin_unlock(&pidmap_lock);
idr_preload_end();
return pid;
out_unlock:
spin_unlock(&pidmap_lock);
idr_preload_end();
put_pid_ns(ns);
out_free:
spin_lock(&pidmap_lock);
while (++i <= ns->level) {
upid = pid->numbers + i;
idr_remove(&upid->ns->idr, upid->nr);
}
/* On failure to allocate the first pid, reset the state */
if (ns->pid_allocated == PIDNS_ADDING)
idr_set_cursor(&ns->idr, 0);
spin_unlock(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid);
return ERR_PTR(retval);
}
void disable_pid_allocation(struct pid_namespace *ns)
{
spin_lock(&pidmap_lock);
ns->pid_allocated &= ~PIDNS_ADDING;
spin_unlock(&pidmap_lock);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
return idr_find(&ns->idr, nr);
}
EXPORT_SYMBOL_GPL(find_pid_ns);
struct pid *find_vpid(int nr)
{
return find_pid_ns(nr, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(find_vpid);
static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type)
{
return (type == PIDTYPE_PID) ?
&task->thread_pid : &task->signal->pids[type];
}
/*
* attach_pid() must be called with the tasklist_lock write-held.
*/
void attach_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
lockdep_assert_held_write(&tasklist_lock);
pid = *task_pid_ptr(task, type);
hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]);
}
static void __change_pid(struct pid **pids, struct task_struct *task,
enum pid_type type, struct pid *new)
{
struct pid **pid_ptr, *pid;
int tmp;
lockdep_assert_held_write(&tasklist_lock);
pid_ptr = task_pid_ptr(task, type);
pid = *pid_ptr;
hlist_del_rcu(&task->pid_links[type]);
*pid_ptr = new;
if (type == PIDTYPE_PID) {
WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID));
wake_up_all(&pid->wait_pidfd);
}
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (pid_has_task(pid, tmp))
return;
WARN_ON(pids[type]);
pids[type] = pid;
}
void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type type)
{
__change_pid(pids, task, type, NULL);
}
void change_pid(struct pid **pids, struct task_struct *task, enum pid_type type,
struct pid *pid)
{
__change_pid(pids, task, type, pid);
attach_pid(task, type);
}
void exchange_tids(struct task_struct *left, struct task_struct *right)
{
struct pid *pid1 = left->thread_pid;
struct pid *pid2 = right->thread_pid;
struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID];
struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID];
lockdep_assert_held_write(&tasklist_lock);
/* Swap the single entry tid lists */
hlists_swap_heads_rcu(head1, head2);
/* Swap the per task_struct pid */
rcu_assign_pointer(left->thread_pid, pid2);
rcu_assign_pointer(right->thread_pid, pid1);
/* Swap the cached value */
WRITE_ONCE(left->pid, pid_nr(pid2));
WRITE_ONCE(right->pid, pid_nr(pid1));
}
/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type type)
{
WARN_ON_ONCE(type == PIDTYPE_PID);
lockdep_assert_held_write(&tasklist_lock);
hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
}
struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result = NULL;
if (pid) {
struct hlist_node *first;
first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
lockdep_tasklist_lock_is_held());
if (first)
result = hlist_entry(first, struct task_struct, pid_links[(type)]);
}
return result;
}
EXPORT_SYMBOL(pid_task);
/*
* Must be called under rcu_read_lock().
*/
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"find_task_by_pid_ns() needs rcu_read_lock() protection");
return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
struct task_struct *find_task_by_vpid(pid_t vnr)
{
return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
}
struct task_struct *find_get_task_by_vpid(pid_t nr)
{
struct task_struct *task;
rcu_read_lock();
task = find_task_by_vpid(nr);
if (task)
get_task_struct(task);
rcu_read_unlock();
return task;
}
struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(get_task_pid);
struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result;
rcu_read_lock();
result = pid_task(pid, type);
if (result)
get_task_struct(result);
rcu_read_unlock();
return result;
}
EXPORT_SYMBOL_GPL(get_pid_task);
struct pid *find_get_pid(pid_t nr)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(find_vpid(nr));
rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(find_get_pid);
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
{
struct upid *upid;
pid_t nr = 0;
if (pid && ns->level <= pid->level) {
upid = &pid->numbers[ns->level];
if (upid->ns == ns)
nr = upid->nr;
}
return nr;
}
EXPORT_SYMBOL_GPL(pid_nr_ns);
pid_t pid_vnr(struct pid *pid)
{
return pid_nr_ns(pid, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(pid_vnr);
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
struct pid_namespace *ns)
{
pid_t nr = 0;
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
rcu_read_unlock();
return nr;
}
EXPORT_SYMBOL(__task_pid_nr_ns);
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{ return ns_of_pid(task_pid(tsk));
}
EXPORT_SYMBOL_GPL(task_active_pid_ns);
/*
* Used by proc to find the first pid that is greater than or equal to nr.
*
* If there is a pid at nr this function is exactly the same as find_pid_ns.
*/
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
return idr_get_next(&ns->idr, &nr);
}
EXPORT_SYMBOL_GPL(find_ge_pid);
struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
{
CLASS(fd, f)(fd);
struct pid *pid;
if (fd_empty(f))
return ERR_PTR(-EBADF);
pid = pidfd_pid(fd_file(f));
if (!IS_ERR(pid)) {
get_pid(pid);
*flags = fd_file(f)->f_flags;
}
return pid;
}
/**
* pidfd_get_task() - Get the task associated with a pidfd
*
* @pidfd: pidfd for which to get the task
* @flags: flags associated with this pidfd
*
* Return the task associated with @pidfd. The function takes a reference on
* the returned task. The caller is responsible for releasing that reference.
*
* Return: On success, the task_struct associated with the pidfd.
* On error, a negative errno number will be returned.
*/
struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
{
unsigned int f_flags = 0;
struct pid *pid;
struct task_struct *task;
enum pid_type type;
switch (pidfd) {
case PIDFD_SELF_THREAD:
type = PIDTYPE_PID;
pid = get_task_pid(current, type);
break;
case PIDFD_SELF_THREAD_GROUP:
type = PIDTYPE_TGID;
pid = get_task_pid(current, type);
break;
default:
pid = pidfd_get_pid(pidfd, &f_flags);
if (IS_ERR(pid))
return ERR_CAST(pid);
type = PIDTYPE_TGID;
break;
}
task = get_pid_task(pid, type);
put_pid(pid);
if (!task)
return ERR_PTR(-ESRCH);
*flags = f_flags;
return task;
}
/**
* pidfd_create() - Create a new pid file descriptor.
*
* @pid: struct pid that the pidfd will reference
* @flags: flags to pass
*
* This creates a new pid file descriptor with the O_CLOEXEC flag set.
*
* Note, that this function can only be called after the fd table has
* been unshared to avoid leaking the pidfd to the new process.
*
* This symbol should not be explicitly exported to loadable modules.
*
* Return: On success, a cloexec pidfd is returned.
* On error, a negative errno number will be returned.
*/
static int pidfd_create(struct pid *pid, unsigned int flags)
{
int pidfd;
struct file *pidfd_file;
pidfd = pidfd_prepare(pid, flags, &pidfd_file);
if (pidfd < 0)
return pidfd;
fd_install(pidfd, pidfd_file);
return pidfd;
}
/**
* sys_pidfd_open() - Open new pid file descriptor.
*
* @pid: pid for which to retrieve a pidfd
* @flags: flags to pass
*
* This creates a new pid file descriptor with the O_CLOEXEC flag set for
* the task identified by @pid. Without PIDFD_THREAD flag the target task
* must be a thread-group leader.
*
* Return: On success, a cloexec pidfd is returned.
* On error, a negative errno number will be returned.
*/
SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
{
int fd;
struct pid *p;
if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD))
return -EINVAL;
if (pid <= 0)
return -EINVAL;
p = find_get_pid(pid);
if (!p)
return -ESRCH;
fd = pidfd_create(p, flags);
put_pid(p);
return fd;
}
#ifdef CONFIG_SYSCTL
static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root)
{
return &task_active_pid_ns(current)->set;
}
static int set_is_seen(struct ctl_table_set *set)
{
return &task_active_pid_ns(current)->set == set;
}
static int pid_table_root_permissions(struct ctl_table_header *head,
const struct ctl_table *table)
{
struct pid_namespace *pidns =
container_of(head->set, struct pid_namespace, set);
int mode = table->mode;
if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) ||
uid_eq(current_euid(), make_kuid(pidns->user_ns, 0)))
mode = (mode & S_IRWXU) >> 6;
else if (in_egroup_p(make_kgid(pidns->user_ns, 0)))
mode = (mode & S_IRWXG) >> 3;
else
mode = mode & S_IROTH;
return (mode << 6) | (mode << 3) | mode;
}
static void pid_table_root_set_ownership(struct ctl_table_header *head,
kuid_t *uid, kgid_t *gid)
{
struct pid_namespace *pidns =
container_of(head->set, struct pid_namespace, set);
kuid_t ns_root_uid;
kgid_t ns_root_gid;
ns_root_uid = make_kuid(pidns->user_ns, 0);
if (uid_valid(ns_root_uid))
*uid = ns_root_uid;
ns_root_gid = make_kgid(pidns->user_ns, 0);
if (gid_valid(ns_root_gid))
*gid = ns_root_gid;
}
static struct ctl_table_root pid_table_root = {
.lookup = pid_table_root_lookup,
.permissions = pid_table_root_permissions,
.set_ownership = pid_table_root_set_ownership,
};
static const struct ctl_table pid_table[] = {
{
.procname = "pid_max",
.data = &init_pid_ns.pid_max,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &pid_max_min,
.extra2 = &pid_max_max,
},
};
#endif
int register_pidns_sysctls(struct pid_namespace *pidns)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen);
tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL);
if (!tbl)
return -ENOMEM;
tbl->data = &pidns->pid_max;
pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max,
PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl,
ARRAY_SIZE(pid_table));
if (!pidns->sysctls) {
kfree(tbl);
retire_sysctl_set(&pidns->set);
return -ENOMEM;
}
#endif
return 0;
}
void unregister_pidns_sysctls(struct pid_namespace *pidns)
{
#ifdef CONFIG_SYSCTL
const struct ctl_table *tbl;
tbl = pidns->sysctls->ctl_table_arg;
unregister_sysctl_table(pidns->sysctls);
retire_sysctl_set(&pidns->set);
kfree(tbl);
#endif
}
void __init pid_idr_init(void)
{
/* Verify no one has done anything silly: */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
/* bump default and minimum pid_max based on number of cpus */
init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max,
PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
pid_max_min = max_t(int, pid_max_min,
PIDS_PER_CPU_MIN * num_possible_cpus());
pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min);
idr_init(&init_pid_ns.idr);
init_pid_ns.pid_cachep = kmem_cache_create("pid",
struct_size_t(struct pid, numbers, 1),
__alignof__(struct pid),
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
NULL);
}
static __init int pid_namespace_sysctl_init(void)
{
#ifdef CONFIG_SYSCTL
/* "kernel" directory will have already been initialized. */
BUG_ON(register_pidns_sysctls(&init_pid_ns));
#endif
return 0;
}
subsys_initcall(pid_namespace_sysctl_init);
static struct file *__pidfd_fget(struct task_struct *task, int fd)
{
struct file *file;
int ret;
ret = down_read_killable(&task->signal->exec_update_lock);
if (ret)
return ERR_PTR(ret);
if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
file = fget_task(task, fd);
else
file = ERR_PTR(-EPERM);
up_read(&task->signal->exec_update_lock);
if (!file) {
/*
* It is possible that the target thread is exiting; it can be
* either:
* 1. before exit_signals(), which gives a real fd
* 2. before exit_files() takes the task_lock() gives a real fd
* 3. after exit_files() releases task_lock(), ->files is NULL;
* this has PF_EXITING, since it was set in exit_signals(),
* __pidfd_fget() returns EBADF.
* In case 3 we get EBADF, but that really means ESRCH, since
* the task is currently exiting and has freed its files
* struct, so we fix it up.
*/
if (task->flags & PF_EXITING)
file = ERR_PTR(-ESRCH);
else
file = ERR_PTR(-EBADF);
}
return file;
}
static int pidfd_getfd(struct pid *pid, int fd)
{
struct task_struct *task;
struct file *file;
int ret;
task = get_pid_task(pid, PIDTYPE_PID);
if (!task)
return -ESRCH;
file = __pidfd_fget(task, fd);
put_task_struct(task);
if (IS_ERR(file))
return PTR_ERR(file);
ret = receive_fd(file, NULL, O_CLOEXEC);
fput(file);
return ret;
}
/**
* sys_pidfd_getfd() - Get a file descriptor from another process
*
* @pidfd: the pidfd file descriptor of the process
* @fd: the file descriptor number to get
* @flags: flags on how to get the fd (reserved)
*
* This syscall gets a copy of a file descriptor from another process
* based on the pidfd, and file descriptor number. It requires that
* the calling process has the ability to ptrace the process represented
* by the pidfd. The process which is having its file descriptor copied
* is otherwise unaffected.
*
* Return: On success, a cloexec file descriptor is returned.
* On error, a negative errno number will be returned.
*/
SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
unsigned int, flags)
{
struct pid *pid;
/* flags is currently unused - make sure it's unset */
if (flags)
return -EINVAL;
CLASS(fd, f)(pidfd);
if (fd_empty(f))
return -EBADF;
pid = pidfd_pid(fd_file(f));
if (IS_ERR(pid))
return PTR_ERR(pid);
return pidfd_getfd(pid, fd);
}
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* internal.h: mm/ internal definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
#include <linux/fs.h>
#include <linux/khugepaged.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/pagemap.h>
#include <linux/pagewalk.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/swap_cgroup.h>
#include <linux/tracepoint-defs.h>
/* Internal core VMA manipulation functions. */
#include "vma.h"
struct folio_batch;
/*
* Maintains state across a page table move. The operation assumes both source
* and destination VMAs already exist and are specified by the user.
*
* Partial moves are permitted, but the old and new ranges must both reside
* within a VMA.
*
* mmap lock must be held in write and VMA write locks must be held on any VMA
* that is visible.
*
* Use the PAGETABLE_MOVE() macro to initialise this struct.
*
* The old_addr and new_addr fields are updated as the page table move is
* executed.
*
* NOTE: The page table move is affected by reading from [old_addr, old_end),
* and old_addr may be updated for better page table alignment, so len_in
* represents the length of the range being copied as specified by the user.
*/
struct pagetable_move_control {
struct vm_area_struct *old; /* Source VMA. */
struct vm_area_struct *new; /* Destination VMA. */
unsigned long old_addr; /* Address from which the move begins. */
unsigned long old_end; /* Exclusive address at which old range ends. */
unsigned long new_addr; /* Address to move page tables to. */
unsigned long len_in; /* Bytes to remap specified by user. */
bool need_rmap_locks; /* Do rmap locks need to be taken? */
bool for_stack; /* Is this an early temp stack being moved? */
};
#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \
struct pagetable_move_control name = { \
.old = old_, \
.new = new_, \
.old_addr = old_addr_, \
.old_end = (old_addr_) + (len_), \
.new_addr = new_addr_, \
.len_in = len_, \
}
/*
* The set of flags that only affect watermark checking and reclaim
* behaviour. This is used by the MM to obey the caller constraints
* about IO, FS and watermark checking while ignoring placement
* hints such as HIGHMEM usage.
*/
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
__GFP_NOLOCKDEP)
/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
/* Control allocation cpuset and node placement constraints */
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
/*
* Different from WARN_ON_ONCE(), no warning will be issued
* when we specify __GFP_NOWARN.
*/
#define WARN_ON_ONCE_GFP(cond, gfp) ({ \
static bool __section(".data..once") __warned; \
int __ret_warn_once = !!(cond); \
\
if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \
__warned = true; \
WARN_ON(1); \
} \
unlikely(__ret_warn_once); \
})
void page_writeback_init(void);
/*
* If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages,
* its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit
* above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently
* leaves nr_pages_mapped at 0, but avoid surprise if it participates later.
*/
#define ENTIRELY_MAPPED 0x800000
#define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1)
/*
* Flags passed to __show_mem() and show_free_areas() to suppress output in
* various contexts.
*/
#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */
/*
* How many individual pages have an elevated _mapcount. Excludes
* the folio's entire_mapcount.
*
* Don't use this function outside of debugging code.
*/
static inline int folio_nr_pages_mapped(const struct folio *folio)
{
if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT))
return -1;
return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
}
/*
* Retrieve the first entry of a folio based on a provided entry within the
* folio. We cannot rely on folio->swap as there is no guarantee that it has
* been initialized. Used for calling arch_swap_restore()
*/
static inline swp_entry_t folio_swap(swp_entry_t entry,
const struct folio *folio)
{
swp_entry_t swap = {
.val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)),
};
return swap;
}
static inline void *folio_raw_mapping(const struct folio *folio)
{
unsigned long mapping = (unsigned long)folio->mapping;
return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
}
/*
* This is a file-backed mapping, and is about to be memory mapped - invoke its
* mmap hook and safely handle error conditions. On error, VMA hooks will be
* mutated.
*
* @file: File which backs the mapping.
* @vma: VMA which we are mapping.
*
* Returns: 0 if success, error otherwise.
*/
static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
{
int err = call_mmap(file, vma);
if (likely(!err))
return 0;
/*
* OK, we tried to call the file hook for mmap(), but an error
* arose. The mapping is in an inconsistent state and we most not invoke
* any further hooks on it.
*/
vma->vm_ops = &vma_dummy_vm_ops;
return err;
}
/*
* If the VMA has a close hook then close it, and since closing it might leave
* it in an inconsistent state which makes the use of any hooks suspect, clear
* them down by installing dummy empty hooks.
*/
static inline void vma_close(struct vm_area_struct *vma)
{
if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma);
/*
* The mapping is in an inconsistent state, and no further hooks
* may be invoked upon it.
*/
vma->vm_ops = &vma_dummy_vm_ops;
}
}
#ifdef CONFIG_MMU
/* Flags for folio_pte_batch(). */
typedef int __bitwise fpb_t;
/* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */
#define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0))
/* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */
#define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1))
static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
{
if (flags & FPB_IGNORE_DIRTY)
pte = pte_mkclean(pte);
if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
pte = pte_clear_soft_dirty(pte);
return pte_wrprotect(pte_mkold(pte));
}
/**
* folio_pte_batch - detect a PTE batch for a large folio
* @folio: The large folio to detect a PTE batch for.
* @addr: The user virtual address the first page is mapped at.
* @start_ptep: Page table pointer for the first entry.
* @pte: Page table entry for the first page.
* @max_nr: The maximum number of table entries to consider.
* @flags: Flags to modify the PTE batch semantics.
* @any_writable: Optional pointer to indicate whether any entry except the
* first one is writable.
* @any_young: Optional pointer to indicate whether any entry except the
* first one is young.
* @any_dirty: Optional pointer to indicate whether any entry except the
* first one is dirty.
*
* Detect a PTE batch: consecutive (present) PTEs that map consecutive
* pages of the same large folio.
*
* All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
* the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
* soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
*
* start_ptep must map any page of the folio. max_nr must be at least one and
* must be limited by the caller so scanning cannot exceed a single page table.
*
* Return: the number of table entries in the batch.
*/
static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
bool *any_writable, bool *any_young, bool *any_dirty)
{
unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
const pte_t *end_ptep = start_ptep + max_nr;
pte_t expected_pte, *ptep;
bool writable, young, dirty;
int nr;
if (any_writable)
*any_writable = false;
if (any_young)
*any_young = false;
if (any_dirty)
*any_dirty = false;
VM_WARN_ON_FOLIO(!pte_present(pte), folio);
VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
nr = pte_batch_hint(start_ptep, pte);
expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
ptep = start_ptep + nr;
while (ptep < end_ptep) {
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
if (any_young)
young = !!pte_young(pte);
if (any_dirty)
dirty = !!pte_dirty(pte);
pte = __pte_batch_clear_ignored(pte, flags);
if (!pte_same(pte, expected_pte))
break;
/*
* Stop immediately once we reached the end of the folio. In
* corner cases the next PFN might fall into a different
* folio.
*/
if (pte_pfn(pte) >= folio_end_pfn)
break;
if (any_writable)
*any_writable |= writable;
if (any_young)
*any_young |= young;
if (any_dirty)
*any_dirty |= dirty;
nr = pte_batch_hint(ptep, pte);
expected_pte = pte_advance_pfn(expected_pte, nr);
ptep += nr;
}
return min(ptep - start_ptep, max_nr);
}
/**
* pte_move_swp_offset - Move the swap entry offset field of a swap pte
* forward or backward by delta
* @pte: The initial pte state; is_swap_pte(pte) must be true and
* non_swap_entry() must be false.
* @delta: The direction and the offset we are moving; forward if delta
* is positive; backward if delta is negative
*
* Moves the swap offset, while maintaining all other fields, including
* swap type, and any swp pte bits. The resulting pte is returned.
*/
static inline pte_t pte_move_swp_offset(pte_t pte, long delta)
{
swp_entry_t entry = pte_to_swp_entry(pte);
pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry),
(swp_offset(entry) + delta)));
if (pte_swp_soft_dirty(pte))
new = pte_swp_mksoft_dirty(new);
if (pte_swp_exclusive(pte))
new = pte_swp_mkexclusive(new);
if (pte_swp_uffd_wp(pte))
new = pte_swp_mkuffd_wp(new);
return new;
}
/**
* pte_next_swp_offset - Increment the swap entry offset field of a swap pte.
* @pte: The initial pte state; is_swap_pte(pte) must be true and
* non_swap_entry() must be false.
*
* Increments the swap offset, while maintaining all other fields, including
* swap type, and any swp pte bits. The resulting pte is returned.
*/
static inline pte_t pte_next_swp_offset(pte_t pte)
{
return pte_move_swp_offset(pte, 1);
}
/**
* swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
* @start_ptep: Page table pointer for the first entry.
* @max_nr: The maximum number of table entries to consider.
* @pte: Page table entry for the first entry.
*
* Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
* containing swap entries all with consecutive offsets and targeting the same
* swap type, all with matching swp pte bits.
*
* max_nr must be at least one and must be limited by the caller so scanning
* cannot exceed a single page table.
*
* Return: the number of table entries in the batch.
*/
static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
{
pte_t expected_pte = pte_next_swp_offset(pte);
const pte_t *end_ptep = start_ptep + max_nr;
swp_entry_t entry = pte_to_swp_entry(pte);
pte_t *ptep = start_ptep + 1;
unsigned short cgroup_id;
VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte));
VM_WARN_ON(non_swap_entry(entry));
cgroup_id = lookup_swap_cgroup_id(entry);
while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte))
break;
if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id)
break;
expected_pte = pte_next_swp_offset(expected_pte);
ptep++;
}
return ptep - start_ptep;
}
#endif /* CONFIG_MMU */
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
int nr_throttled);
static inline void acct_reclaim_writeback(struct folio *folio)
{
pg_data_t *pgdat = folio_pgdat(folio);
int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled);
if (nr_throttled)
__acct_reclaim_writeback(pgdat, folio, nr_throttled);
}
static inline void wake_throttle_isolated(pg_data_t *pgdat)
{
wait_queue_head_t *wqh;
wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED];
if (waitqueue_active(wqh))
wake_up(wqh);
}
vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf);
static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
{
vm_fault_t ret = __vmf_anon_prepare(vmf);
if (unlikely(ret & VM_FAULT_RETRY))
vma_end_read(vmf->vma);
return ret;
}
vm_fault_t do_swap_page(struct vm_fault *vmf);
void folio_rotate_reclaimable(struct folio *folio);
bool __folio_end_writeback(struct folio *folio);
void deactivate_file_folio(struct folio *folio);
void folio_activate(struct folio *folio);
void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
struct vm_area_struct *start_vma, unsigned long floor,
unsigned long ceiling, bool mm_wr_locked);
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
struct zap_details;
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details);
int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
gfp_t gfp);
void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
unsigned int order);
void force_page_cache_ra(struct readahead_control *, unsigned long nr);
static inline void force_page_cache_readahead(struct address_space *mapping,
struct file *file, pgoff_t index, unsigned long nr_to_read)
{
DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index);
force_page_cache_ra(&ractl, nr_to_read);
}
unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
void filemap_free_folio(struct address_space *mapping, struct folio *folio);
int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
loff_t end);
long mapping_evict_folio(struct address_space *mapping, struct folio *folio);
unsigned long mapping_try_invalidate(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_failed);
/**
* folio_evictable - Test whether a folio is evictable.
* @folio: The folio to test.
*
* Test whether @folio is evictable -- i.e., should be placed on
* active/inactive lists vs unevictable list.
*
* Reasons folio might not be evictable:
* 1. folio's mapping marked unevictable
* 2. One of the pages in the folio is part of an mlocked VMA
*/
static inline bool folio_evictable(struct folio *folio)
{
bool ret;
/* Prevent address_space of inode and swap cache from being freed */
rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock();
return ret;
}
/*
* Turn a non-refcounted page (->_refcount == 0) into refcounted with
* a count of one.
*/
static inline void set_page_refcounted(struct page *page)
{
VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1);
}
/*
* Return true if a folio needs ->release_folio() calling upon it.
*/
static inline bool folio_needs_release(struct folio *folio)
{
struct address_space *mapping = folio_mapping(folio);
return folio_has_private(folio) || (mapping && mapping_release_always(mapping));
}
extern unsigned long highest_memmap_pfn;
/*
* Maximum number of reclaim retries without progress before the OOM
* killer is consider the only way forward.
*/
#define MAX_RECLAIM_RETRIES 16
/*
* in mm/vmscan.c:
*/
bool folio_isolate_lru(struct folio *folio);
void folio_putback_lru(struct folio *folio);
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
/*
* in mm/rmap.c:
*/
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
/*
* in mm/page_alloc.c
*/
#define K(x) ((x) << (PAGE_SHIFT-10))
extern char * const zone_names[MAX_NR_ZONES];
/* perform sanity checks on struct pages being allocated or freed */
DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
extern int min_free_kbytes;
extern int defrag_mode;
void setup_per_zone_wmarks(void);
void calculate_min_free_kbytes(void);
int __meminit init_per_zone_wmark_min(void);
void page_alloc_sysctl_init(void);
/*
* Structure for holding the mostly immutable allocation parameters passed
* between functions involved in allocations, including the alloc_pages*
* family of functions.
*
* nodemask, migratetype and highest_zoneidx are initialized only once in
* __alloc_pages() and then never change.
*
* zonelist, preferred_zone and highest_zoneidx are set first in
* __alloc_pages() for the fast path, and might be later changed
* in __alloc_pages_slowpath(). All other functions pass the whole structure
* by a const pointer.
*/
struct alloc_context {
struct zonelist *zonelist;
nodemask_t *nodemask;
struct zoneref *preferred_zoneref;
int migratetype;
/*
* highest_zoneidx represents highest usable zone index of
* the allocation request. Due to the nature of the zone,
* memory on lower zone than the highest_zoneidx will be
* protected by lowmem_reserve[highest_zoneidx].
*
* highest_zoneidx is also used by reclaim/compaction to limit
* the target zone since higher zone than this index cannot be
* usable for this allocation request.
*/
enum zone_type highest_zoneidx;
bool spread_dirty_pages;
};
/*
* This function returns the order of a free page in the buddy system. In
* general, page_zone(page)->lock must be held by the caller to prevent the
* page from being allocated in parallel and returning garbage as the order.
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
* page cannot be allocated or merged in parallel. Alternatively, it must
* handle invalid values gracefully, and use buddy_order_unsafe() below.
*/
static inline unsigned int buddy_order(struct page *page)
{
/* PageBuddy() must be checked by the caller */
return page_private(page);
}
/*
* Like buddy_order(), but for callers who cannot afford to hold the zone lock.
* PageBuddy() should be checked first by the caller to minimize race window,
* and invalid values must be handled gracefully.
*
* READ_ONCE is used so that if the caller assigns the result into a local
* variable and e.g. tests it for valid range before using, the compiler cannot
* decide to remove the variable and inline the page_private(page) multiple
* times, potentially observing different values in the tests and the actual
* use of the result.
*/
#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
/*
* This function checks whether a page is free && is the buddy
* we can coalesce a page and its buddy if
* (a) the buddy is not in a hole (check before calling!) &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
* For recording whether a page is in the buddy system, we set PageBuddy.
* Setting, clearing, and testing PageBuddy is serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
static inline bool page_is_buddy(struct page *page, struct page *buddy,
unsigned int order)
{
if (!page_is_guard(buddy) && !PageBuddy(buddy))
return false;
if (buddy_order(buddy) != order)
return false;
/*
* zone check is done late to avoid uselessly calculating
* zone/node ids for pages that could never merge.
*/
if (page_zone_id(page) != page_zone_id(buddy))
return false;
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
return true;
}
/*
* Locate the struct page for both the matching buddy in our
* pair (buddy1) and the combined O(n+1) page they form (page).
*
* 1) Any buddy B1 will have an order O twin B2 which satisfies
* the following equation:
* B2 = B1 ^ (1 << O)
* For example, if the starting buddy (buddy2) is #8 its order
* 1 buddy is #10:
* B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
*
* 2) Any buddy B will have an order O+1 parent P which
* satisfies the following equation:
* P = B & ~(1 << O)
*
* Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER
*/
static inline unsigned long
__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
{
return page_pfn ^ (1 << order);
}
/*
* Find the buddy of @page and validate it.
* @page: The input page
* @pfn: The pfn of the page, it saves a call to page_to_pfn() when the
* function is used in the performance-critical __free_one_page().
* @order: The order of the page
* @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to
* page_to_pfn().
*
* The found buddy can be a non PageBuddy, out of @page's zone, or its order is
* not the same as @page. The validation is necessary before use it.
*
* Return: the found buddy page or NULL if not found.
*/
static inline struct page *find_buddy_page_pfn(struct page *page,
unsigned long pfn, unsigned int order, unsigned long *buddy_pfn)
{
unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order);
struct page *buddy;
buddy = page + (__buddy_pfn - pfn);
if (buddy_pfn)
*buddy_pfn = __buddy_pfn;
if (page_is_buddy(page, buddy, order))
return buddy;
return NULL;
}
extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone);
static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
unsigned long end_pfn, struct zone *zone)
{
if (zone->contiguous)
return pfn_to_page(start_pfn);
return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}
void set_zone_contiguous(struct zone *zone);
bool pfn_range_intersects_zones(int nid, unsigned long start_pfn,
unsigned long nr_pages);
static inline void clear_zone_contiguous(struct zone *zone)
{
zone->contiguous = false;
}
extern int __isolate_free_page(struct page *page, unsigned int order);
extern void __putback_isolated_page(struct page *page, unsigned int order,
int mt);
extern void memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order);
extern void __free_pages_core(struct page *page, unsigned int order,
enum meminit_context context);
/*
* This will have no effect, other than possibly generating a warning, if the
* caller passes in a non-large folio.
*/
static inline void folio_set_order(struct folio *folio, unsigned int order)
{
if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
return;
folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
#ifdef NR_PAGES_IN_LARGE_FOLIO
folio->_nr_pages = 1U << order;
#endif
}
bool __folio_unqueue_deferred_split(struct folio *folio);
static inline bool folio_unqueue_deferred_split(struct folio *folio)
{
if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio))
return false;
/*
* At this point, there is no one trying to add the folio to
* deferred_list. If folio is not in deferred_list, it's safe
* to check without acquiring the split_queue_lock.
*/
if (data_race(list_empty(&folio->_deferred_list)))
return false;
return __folio_unqueue_deferred_split(folio);
}
static inline struct folio *page_rmappable_folio(struct page *page)
{
struct folio *folio = (struct folio *)page;
if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio);
return folio;
}
static inline void prep_compound_head(struct page *page, unsigned int order)
{
struct folio *folio = (struct folio *)page;
folio_set_order(folio, order);
atomic_set(&folio->_large_mapcount, -1);
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
atomic_set(&folio->_nr_pages_mapped, 0);
if (IS_ENABLED(CONFIG_MM_ID)) {
folio->_mm_ids = 0;
folio->_mm_id_mapcount[0] = -1;
folio->_mm_id_mapcount[1] = -1;
}
if (IS_ENABLED(CONFIG_64BIT) || order > 1) {
atomic_set(&folio->_pincount, 0);
atomic_set(&folio->_entire_mapcount, -1);
}
if (order > 1)
INIT_LIST_HEAD(&folio->_deferred_list);
}
static inline void prep_compound_tail(struct page *head, int tail_idx)
{
struct page *p = head + tail_idx;
p->mapping = TAIL_MAPPING;
set_compound_head(p, head);
set_page_private(p, 0);
}
void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags);
extern bool free_pages_prepare(struct page *page, unsigned int order);
extern int user_min_free_kbytes;
struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid,
nodemask_t *);
#define __alloc_frozen_pages(...) \
alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__))
void free_frozen_pages(struct page *page, unsigned int order);
void free_unref_folios(struct folio_batch *fbatch);
#ifdef CONFIG_NUMA
struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order);
#else
static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order)
{
return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL);
}
#endif
#define alloc_frozen_pages(...) \
alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__))
extern void zone_pcp_reset(struct zone *zone);
extern void zone_pcp_disable(struct zone *zone);
extern void zone_pcp_enable(struct zone *zone);
extern void zone_pcp_init(struct zone *zone);
extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr,
int nid, bool exact_nid);
void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
unsigned long, enum meminit_context, struct vmem_altmap *, int);
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/*
* in mm/compaction.c
*/
/*
* compact_control is used to track pages being migrated and the free pages
* they are being migrated to during memory compaction. The free_pfn starts
* at the end of a zone and migrate_pfn begins at the start. Movable pages
* are moved to the end of a zone during a compaction run and the run
* completes when free_pfn <= migrate_pfn
*/
struct compact_control {
struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */
struct list_head migratepages; /* List of pages being migrated */
unsigned int nr_freepages; /* Number of isolated free pages */
unsigned int nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
/*
* Acts as an in/out parameter to page isolation for migration.
* isolate_migratepages uses it as a search base.
* isolate_migratepages_block will update the value to the next pfn
* after the last isolated one.
*/
unsigned long migrate_pfn;
unsigned long fast_start_pfn; /* a pfn to start linear scan from */
struct zone *zone;
unsigned long total_migrate_scanned;
unsigned long total_free_scanned;
unsigned short fast_search_fail;/* failures to use free list searches */
short search_order; /* order to start a fast search at */
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
int order; /* order a direct compactor needs */
int migratetype; /* migratetype of direct compactor */
const unsigned int alloc_flags; /* alloc flags of a direct compactor */
const int highest_zoneidx; /* zone index of a direct compactor */
enum migrate_mode mode; /* Async or sync migration mode */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
bool no_set_skip_hint; /* Don't mark blocks for skipping */
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
bool direct_compaction; /* False from kcompactd or /proc/... */
bool proactive_compaction; /* kcompactd proactive compaction */
bool whole_zone; /* Whole zone should/has been scanned */
bool contended; /* Signal lock contention */
bool finish_pageblock; /* Scan the remainder of a pageblock. Used
* when there are potentially transient
* isolation or migration failures to
* ensure forward progress.
*/
bool alloc_contig; /* alloc_contig_range allocation */
};
/*
* Used in direct compaction when a page should be taken from the freelists
* immediately when one is created during the free path.
*/
struct capture_control {
struct compact_control *cc;
struct page *page;
};
unsigned long
isolate_freepages_range(struct compact_control *cc,
unsigned long start_pfn, unsigned long end_pfn);
int
isolate_migratepages_range(struct compact_control *cc,
unsigned long low_pfn, unsigned long end_pfn);
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void init_cma_reserved_pageblock(struct page *page);
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
struct cma;
#ifdef CONFIG_CMA
void *cma_reserve_early(struct cma *cma, unsigned long size);
void init_cma_pageblock(struct page *page);
#else
static inline void *cma_reserve_early(struct cma *cma, unsigned long size)
{
return NULL;
}
static inline void init_cma_pageblock(struct page *page)
{
}
#endif
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool claim_only, bool *claim_block);
static inline bool free_area_empty(struct free_area *area, int migratetype)
{
return list_empty(&area->free_list[migratetype]);
}
/* mm/util.c */
struct anon_vma *folio_anon_vma(const struct folio *folio);
#ifdef CONFIG_MMU
void unmap_mapping_folio(struct folio *folio);
extern long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *locked);
extern long faultin_page_range(struct mm_struct *mm, unsigned long start,
unsigned long end, bool write, int *locked);
extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
unsigned long bytes);
/*
* NOTE: This function can't tell whether the folio is "fully mapped" in the
* range.
* "fully mapped" means all the pages of folio is associated with the page
* table of range while this function just check whether the folio range is
* within the range [start, end). Function caller needs to do page table
* check if it cares about the page table association.
*
* Typical usage (like mlock or madvise) is:
* Caller knows at least 1 page of folio is associated with page table of VMA
* and the range [start, end) is intersect with the VMA range. Caller wants
* to know whether the folio is fully associated with the range. It calls
* this function to check whether the folio is in the range first. Then checks
* the page table to know whether the folio is fully mapped to the range.
*/
static inline bool
folio_within_range(struct folio *folio, struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
pgoff_t pgoff, addr;
unsigned long vma_pglen = vma_pages(vma);
VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio);
if (start > end)
return false;
if (start < vma->vm_start)
start = vma->vm_start;
if (end > vma->vm_end)
end = vma->vm_end;
pgoff = folio_pgoff(folio);
/* if folio start address is not in vma range */
if (!in_range(pgoff, vma->vm_pgoff, vma_pglen))
return false;
addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
return !(addr < start || end - addr < folio_size(folio));
}
static inline bool
folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
{
return folio_within_range(folio, vma, vma->vm_start, vma->vm_end);
}
/*
* mlock_vma_folio() and munlock_vma_folio():
* should be called with vma's mmap_lock held for read or write,
* under page table lock for the pte/pmd being added or removed.
*
* mlock is usually called at the end of folio_add_*_rmap_*(), munlock at
* the end of folio_remove_rmap_*(); but new anon folios are managed by
* folio_add_lru_vma() calling mlock_new_folio().
*/
void mlock_folio(struct folio *folio);
static inline void mlock_vma_folio(struct folio *folio,
struct vm_area_struct *vma)
{
/*
* The VM_SPECIAL check here serves two purposes.
* 1) VM_IO check prevents migration from double-counting during mlock.
* 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED
* is never left set on a VM_SPECIAL vma, there is an interval while
* file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may
* still be set while VM_SPECIAL bits are added: so ignore it then.
*/
if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio);
}
void munlock_folio(struct folio *folio);
static inline void munlock_vma_folio(struct folio *folio,
struct vm_area_struct *vma)
{
/*
* munlock if the function is called. Ideally, we should only
* do munlock if any page of folio is unmapped from VMA and
* cause folio not fully mapped to VMA.
*
* But it's not easy to confirm that's the situation. So we
* always munlock the folio and page reclaim will correct it
* if it's wrong.
*/
if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio);
}
void mlock_new_folio(struct folio *folio);
bool need_mlock_drain(int cpu);
void mlock_drain_local(void);
void mlock_drain_remote(int cpu);
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/**
* vma_address - Find the virtual address a page range is mapped at
* @vma: The vma which maps this object.
* @pgoff: The page offset within its object.
* @nr_pages: The number of pages to consider.
*
* If any page in this range is mapped by this VMA, return the first address
* where any of these pages appear. Otherwise, return -EFAULT.
*/
static inline unsigned long vma_address(const struct vm_area_struct *vma,
pgoff_t pgoff, unsigned long nr_pages)
{
unsigned long address;
if (pgoff >= vma->vm_pgoff) {
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address >= vma->vm_end)
address = -EFAULT;
} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
/* Test above avoids possibility of wrap to 0 on 32-bit */
address = vma->vm_start;
} else {
address = -EFAULT;
}
return address;
}
/*
* Then at what user virtual address will none of the range be found in vma?
* Assumes that vma_address() already returned a good starting address.
*/
static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw)
{
struct vm_area_struct *vma = pvmw->vma;
pgoff_t pgoff;
unsigned long address;
/* Common case, plus ->pgoff is invalid for KSM */
if (pvmw->nr_pages == 1)
return pvmw->address + PAGE_SIZE;
pgoff = pvmw->pgoff + pvmw->nr_pages;
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address > vma->vm_end)
address = vma->vm_end;
return address;
}
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
struct file *fpin)
{
int flags = vmf->flags;
if (fpin)
return fpin;
/*
* FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
* anything, so we only pin the file and drop the mmap_lock if only
* FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
*/
if (fault_flag_allow_retry_first(flags) &&
!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf);
}
return fpin;
}
#else /* !CONFIG_MMU */
static inline void unmap_mapping_folio(struct folio *folio) { }
static inline void mlock_new_folio(struct folio *folio) { }
static inline bool need_mlock_drain(int cpu) { return false; }
static inline void mlock_drain_local(void) { }
static inline void mlock_drain_remote(int cpu) { }
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
{
}
#endif /* !CONFIG_MMU */
/* Memory initialisation debug and verification */
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
DECLARE_STATIC_KEY_TRUE(deferred_pages);
bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
enum mminit_level {
MMINIT_WARNING,
MMINIT_VERIFY,
MMINIT_TRACE
};
#ifdef CONFIG_DEBUG_MEMORY_INIT
extern int mminit_loglevel;
#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
if (level < mminit_loglevel) { \
if (level <= MMINIT_WARNING) \
pr_warn("mminit::" prefix " " fmt, ##arg); \
else \
printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
} \
} while (0)
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_zonelist(void);
#else
static inline void mminit_dprintk(enum mminit_level level,
const char *prefix, const char *fmt, ...)
{
}
static inline void mminit_verify_pageflags_layout(void)
{
}
static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */
#define NODE_RECLAIM_NOSCAN -2
#define NODE_RECLAIM_FULL -1
#define NODE_RECLAIM_SOME 0
#define NODE_RECLAIM_SUCCESS 1
#ifdef CONFIG_NUMA
extern int node_reclaim_mode;
extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
extern int find_next_best_node(int node, nodemask_t *used_node_mask);
#else
#define node_reclaim_mode 0
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
unsigned int order)
{
return NODE_RECLAIM_NOSCAN;
}
static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
{
return NUMA_NO_NODE;
}
#endif
static inline bool node_reclaim_enabled(void)
{
/* Is any node_reclaim_mode bit set? */
return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP);
}
/*
* mm/memory-failure.c
*/
#ifdef CONFIG_MEMORY_FAILURE
int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
void shake_folio(struct folio *folio);
extern int hwpoison_filter(struct page *p);
extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
#define MAGIC_HWPOISON 0x48575053U /* HWPS */
void SetPageHWPoisonTakenOff(struct page *page);
void ClearPageHWPoisonTakenOff(struct page *page);
bool take_page_off_buddy(struct page *page);
bool put_page_back_buddy(struct page *page);
struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
void add_to_kill_ksm(struct task_struct *tsk, const struct page *p,
struct vm_area_struct *vma, struct list_head *to_kill,
unsigned long ksm_addr);
unsigned long page_mapped_in_vma(const struct page *page,
struct vm_area_struct *vma);
#else
static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
{
return -EBUSY;
}
#endif
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
extern void set_pageblock_order(void);
struct folio *alloc_migrate_folio(struct folio *src, unsigned long private);
unsigned long reclaim_pages(struct list_head *folio_list);
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *folio_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN WMARK_MIN
#define ALLOC_WMARK_LOW WMARK_LOW
#define ALLOC_WMARK_HIGH WMARK_HIGH
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1)
/*
* Only MMU archs have async oom victim reclaim - aka oom_reaper so we
* cannot assume a reduced access to memory reserves is sufficient for
* !MMU
*/
#ifdef CONFIG_MMU
#define ALLOC_OOM 0x08
#else
#define ALLOC_OOM ALLOC_NO_WATERMARKS
#endif
#define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access
* to 25% of the min watermark or
* 62.5% if __GFP_HIGH is set.
*/
#define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50%
* of the min watermark.
*/
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
#ifdef CONFIG_ZONE_DMA32
#define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */
#else
#define ALLOC_NOFRAGMENT 0x0
#endif
#define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_TRYLOCK 0x400 /* Only use spin_trylock in allocation path */
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
/* Flags that allow allocations below the min watermark. */
#define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
enum ttu_flags;
struct tlbflush_unmap_batch;
/*
* only for MM internal work items which do not depend on
* any allocations or locks which might depend on allocations
*/
extern struct workqueue_struct *mm_percpu_wq;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
void flush_tlb_batched_pending(struct mm_struct *mm);
#else
static inline void try_to_unmap_flush(void)
{
}
static inline void try_to_unmap_flush_dirty(void)
{
}
static inline void flush_tlb_batched_pending(struct mm_struct *mm)
{
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
extern const struct trace_print_flags pageflag_names[];
extern const struct trace_print_flags vmaflag_names[];
extern const struct trace_print_flags gfpflag_names[];
static inline bool is_migrate_highatomic(enum migratetype migratetype)
{
return migratetype == MIGRATE_HIGHATOMIC;
}
void setup_zone_pageset(struct zone *zone);
struct migration_target_control {
int nid; /* preferred node id */
nodemask_t *nmask;
gfp_t gfp_mask;
enum migrate_reason reason;
};
/*
* mm/filemap.c
*/
size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
struct folio *folio, loff_t fpos, size_t size);
/*
* mm/vmalloc.c
*/
#ifdef CONFIG_MMU
void __init vmalloc_init(void);
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift);
unsigned int get_vm_area_page_order(struct vm_struct *vm);
#else
static inline void vmalloc_init(void)
{
}
static inline
int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
return -EINVAL;
}
#endif
int __must_check __vmap_pages_range_noflush(unsigned long addr,
unsigned long end, pgprot_t prot,
struct page **pages, unsigned int page_shift);
void vunmap_range_noflush(unsigned long start, unsigned long end);
void __vunmap_range_noflush(unsigned long start, unsigned long end);
int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
unsigned long addr, int *flags, bool writable,
int *last_cpupid);
void free_zone_device_folio(struct folio *folio);
int migrate_device_coherent_folio(struct folio *folio);
struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long align, unsigned long shift,
unsigned long flags, unsigned long start,
unsigned long end, int node, gfp_t gfp_mask,
const void *caller);
/*
* mm/gup.c
*/
int __must_check try_grab_folio(struct folio *folio, int refs,
unsigned int flags);
/*
* mm/huge_memory.c
*/
void touch_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, bool write);
void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, bool write);
/*
* Parses a string with mem suffixes into its order. Useful to parse kernel
* parameters.
*/
static inline int get_order_from_str(const char *size_str,
unsigned long valid_orders)
{
unsigned long size;
char *endptr;
int order;
size = memparse(size_str, &endptr);
if (!is_power_of_2(size))
return -EINVAL;
order = get_order(size);
if (BIT(order) & ~valid_orders)
return -EINVAL;
return order;
}
enum {
/* mark page accessed */
FOLL_TOUCH = 1 << 16,
/* a retry, previous pass started an IO */
FOLL_TRIED = 1 << 17,
/* we are working on non-current tsk/mm */
FOLL_REMOTE = 1 << 18,
/* pages must be released via unpin_user_page */
FOLL_PIN = 1 << 19,
/* gup_fast: prevent fall-back to slow gup */
FOLL_FAST_ONLY = 1 << 20,
/* allow unlocking the mmap lock */
FOLL_UNLOCKABLE = 1 << 21,
/* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */
FOLL_MADV_POPULATE = 1 << 22,
};
#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \
FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \
FOLL_MADV_POPULATE)
/*
* Indicates for which pages that are write-protected in the page table,
* whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
* GUP pin will remain consistent with the pages mapped into the page tables
* of the MM.
*
* Temporary unmapping of PageAnonExclusive() pages or clearing of
* PageAnonExclusive() has to protect against concurrent GUP:
* * Ordinary GUP: Using the PT lock
* * GUP-fast and fork(): mm->write_protect_seq
* * GUP-fast and KSM or temporary unmapping (swap, migration): see
* folio_try_share_anon_rmap_*()
*
* Must be called with the (sub)page that's actually referenced via the
* page table entry, which might not necessarily be the head page for a
* PTE-mapped THP.
*
* If the vma is NULL, we're coming from the GUP-fast path and might have
* to fallback to the slow path just to lookup the vma.
*/
static inline bool gup_must_unshare(struct vm_area_struct *vma,
unsigned int flags, struct page *page)
{
/*
* FOLL_WRITE is implicitly handled correctly as the page table entry
* has to be writable -- and if it references (part of) an anonymous
* folio, that part is required to be marked exclusive.
*/
if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
return false;
/*
* Note: PageAnon(page) is stable until the page is actually getting
* freed.
*/
if (!PageAnon(page)) {
/*
* We only care about R/O long-term pining: R/O short-term
* pinning does not have the semantics to observe successive
* changes through the process page tables.
*/
if (!(flags & FOLL_LONGTERM))
return false;
/* We really need the vma ... */
if (!vma)
return true;
/*
* ... because we only care about writable private ("COW")
* mappings where we have to break COW early.
*/
return is_cow_mapping(vma->vm_flags);
}
/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_rmb();
/*
* Note that KSM pages cannot be exclusive, and consequently,
* cannot get pinned.
*/
return !PageAnonExclusive(page);
}
extern bool mirrored_kernelcore;
bool memblock_has_mirror(void);
void memblock_free_all(void);
static __always_inline void vma_set_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
pgoff_t pgoff)
{
vma->vm_start = start;
vma->vm_end = end;
vma->vm_pgoff = pgoff;
}
static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
{
/*
* NOTE: we must check this before VM_SOFTDIRTY on soft-dirty
* enablements, because when without soft-dirty being compiled in,
* VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY)
* will be constantly true.
*/
if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY))
return false;
/*
* Soft-dirty is kind of special: its tracking is enabled when the
* vma flags not set.
*/
return !(vma->vm_flags & VM_SOFTDIRTY);
}
static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd)
{
return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd);
}
static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte)
{
return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte);
}
void __meminit __init_single_page(struct page *page, unsigned long pfn,
unsigned long zone, int nid);
void __meminit __init_page_from_nid(unsigned long pfn, int nid);
/* shrinker related functions */
unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
int priority);
#ifdef CONFIG_SHRINKER_DEBUG
static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
struct shrinker *shrinker, const char *fmt, va_list ap)
{
shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
return shrinker->name ? 0 : -ENOMEM;
}
static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
kfree_const(shrinker->name);
shrinker->name = NULL;
}
extern int shrinker_debugfs_add(struct shrinker *shrinker);
extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
int *debugfs_id);
extern void shrinker_debugfs_remove(struct dentry *debugfs_entry,
int debugfs_id);
#else /* CONFIG_SHRINKER_DEBUG */
static inline int shrinker_debugfs_add(struct shrinker *shrinker)
{
return 0;
}
static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker,
const char *fmt, va_list ap)
{
return 0;
}
static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
{
}
static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
int *debugfs_id)
{
*debugfs_id = -1;
return NULL;
}
static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
int debugfs_id)
{
}
#endif /* CONFIG_SHRINKER_DEBUG */
/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
extern struct list_lru shadow_nodes;
#define mapping_set_update(xas, mapping) do { \
if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \
xas_set_update(xas, workingset_update_node); \
xas_set_lru(xas, &shadow_nodes); \
} \
} while (0)
/* mremap.c */
unsigned long move_page_tables(struct pagetable_move_control *pmc);
#ifdef CONFIG_UNACCEPTED_MEMORY
void accept_page(struct page *page);
void unaccepted_cleanup_work(struct work_struct *work);
#else /* CONFIG_UNACCEPTED_MEMORY */
static inline void accept_page(struct page *page)
{
}
#endif /* CONFIG_UNACCEPTED_MEMORY */
/* pagewalk.c */
int walk_page_range_mm(struct mm_struct *mm, unsigned long start,
unsigned long end, const struct mm_walk_ops *ops,
void *private);
/* pt_reclaim.c */
bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval);
void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb,
pmd_t pmdval);
void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr,
struct mmu_gather *tlb);
#ifdef CONFIG_PT_RECLAIM
bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
struct zap_details *details);
#else
static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
struct zap_details *details)
{
return false;
}
#endif /* CONFIG_PT_RECLAIM */
#endif /* __MM_INTERNAL_H */
open /syzkaller/managers/ci-qemu-native-arm64-kvm/kernel/security/selinux/flask.h: no such file or directory
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/userfaultfd.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
* Copyright (C) 2008-2009 Red Hat, Inc.
* Copyright (C) 2015 Red Hat, Inc.
*
* Some part derived from fs/eventfd.c (anon inode setup) and
* mm/ksm.c (mm hashing).
*/
#include <linux/list.h>
#include <linux/hashtable.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/file.h>
#include <linux/bug.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/userfaultfd_k.h>
#include <linux/mempolicy.h>
#include <linux/ioctl.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/swapops.h>
#include <linux/miscdevice.h>
#include <linux/uio.h>
static int sysctl_unprivileged_userfaultfd __read_mostly;
#ifdef CONFIG_SYSCTL
static const struct ctl_table vm_userfaultfd_table[] = {
{
.procname = "unprivileged_userfaultfd",
.data = &sysctl_unprivileged_userfaultfd,
.maxlen = sizeof(sysctl_unprivileged_userfaultfd),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
};
#endif
static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
struct userfaultfd_fork_ctx {
struct userfaultfd_ctx *orig;
struct userfaultfd_ctx *new;
struct list_head list;
};
struct userfaultfd_unmap_ctx {
struct userfaultfd_ctx *ctx;
unsigned long start;
unsigned long end;
struct list_head list;
};
struct userfaultfd_wait_queue {
struct uffd_msg msg;
wait_queue_entry_t wq;
struct userfaultfd_ctx *ctx;
bool waken;
};
struct userfaultfd_wake_range {
unsigned long start;
unsigned long len;
};
/* internal indication that UFFD_API ioctl was successfully executed */
#define UFFD_FEATURE_INITIALIZED (1u << 31)
static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
{
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx)
{
return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC);
}
/*
* Whether WP_UNPOPULATED is enabled on the uffd context. It is only
* meaningful when userfaultfd_wp()==true on the vma and when it's
* anonymous.
*/
bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
{
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx)
return false;
return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
}
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
struct userfaultfd_wake_range *range = key;
int ret;
struct userfaultfd_wait_queue *uwq;
unsigned long start, len;
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
ret = 0;
/* len == 0 means wake all */
start = range->start;
len = range->len;
if (len && (start > uwq->msg.arg.pagefault.address ||
start + len <= uwq->msg.arg.pagefault.address))
goto out;
WRITE_ONCE(uwq->waken, true);
/*
* The Program-Order guarantees provided by the scheduler
* ensure uwq->waken is visible before the task is woken.
*/
ret = wake_up_state(wq->private, mode);
if (ret) {
/*
* Wake only once, autoremove behavior.
*
* After the effect of list_del_init is visible to the other
* CPUs, the waitqueue may disappear from under us, see the
* !list_empty_careful() in handle_userfault().
*
* try_to_wake_up() has an implicit smp_mb(), and the
* wq->private is read before calling the extern function
* "wake_up_state" (which in turns calls try_to_wake_up).
*/
list_del_init(&wq->entry);
}
out:
return ret;
}
/**
* userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to the userfaultfd context.
*/
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
refcount_inc(&ctx->refcount);
}
/**
* userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to userfaultfd context.
*
* The userfaultfd context reference must have been previously acquired either
* with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
*/
static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
{
if (refcount_dec_and_test(&ctx->refcount)) {
VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
mmdrop(ctx->mm);
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
}
}
static inline void msg_init(struct uffd_msg *msg)
{
BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
/*
* Must use memset to zero out the paddings or kernel data is
* leaked to userland.
*/
memset(msg, 0, sizeof(struct uffd_msg));
}
static inline struct uffd_msg userfault_msg(unsigned long address,
unsigned long real_address,
unsigned int flags,
unsigned long reason,
unsigned int features)
{
struct uffd_msg msg;
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
real_address : address;
/*
* These flags indicate why the userfault occurred:
* - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
* - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
* - Neither of these flags being set indicates a MISSING fault.
*
* Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
* fault. Otherwise, it was a read fault.
*/
if (flags & FAULT_FLAG_WRITE)
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
if (reason & VM_UFFD_WP)
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
if (reason & VM_UFFD_MINOR)
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
if (features & UFFD_FEATURE_THREAD_ID)
msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
return msg;
}
#ifdef CONFIG_HUGETLB_PAGE
/*
* Same functionality as userfaultfd_must_wait below with modifications for
* hugepmd ranges.
*/
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
struct vm_fault *vmf,
unsigned long reason)
{
struct vm_area_struct *vma = vmf->vma;
pte_t *ptep, pte;
bool ret = true;
assert_fault_locked(vmf);
ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma));
if (!ptep)
goto out;
ret = false;
pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep);
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us. PTE markers should be handled the same as none
* ptes here.
*/
if (huge_pte_none_mostly(pte))
ret = true;
if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
ret = true;
out:
return ret;
}
#else
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
struct vm_fault *vmf,
unsigned long reason)
{
return false; /* should never get here */
}
#endif /* CONFIG_HUGETLB_PAGE */
/*
* Verify the pagetables are still not ok after having reigstered into
* the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
* userfault that has already been resolved, if userfaultfd_read_iter and
* UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
* threads.
*/
static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
struct vm_fault *vmf,
unsigned long reason)
{
struct mm_struct *mm = ctx->mm;
unsigned long address = vmf->address;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd, _pmd;
pte_t *pte;
pte_t ptent;
bool ret = true;
assert_fault_locked(vmf);
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out;
p4d = p4d_offset(pgd, address);
if (!p4d_present(*p4d))
goto out;
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
again:
_pmd = pmdp_get_lockless(pmd);
if (pmd_none(_pmd))
goto out;
ret = false;
if (!pmd_present(_pmd) || pmd_devmap(_pmd))
goto out;
if (pmd_trans_huge(_pmd)) {
if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
ret = true;
goto out;
}
pte = pte_offset_map(pmd, address);
if (!pte) {
ret = true;
goto again;
}
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us. PTE markers should be handled the same as none
* ptes here.
*/
ptent = ptep_get(pte);
if (pte_none_mostly(ptent))
ret = true;
if (!pte_write(ptent) && (reason & VM_UFFD_WP))
ret = true;
pte_unmap(pte);
out:
return ret;
}
static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags)
{
if (flags & FAULT_FLAG_INTERRUPTIBLE)
return TASK_INTERRUPTIBLE;
if (flags & FAULT_FLAG_KILLABLE)
return TASK_KILLABLE;
return TASK_UNINTERRUPTIBLE;
}
/*
* The locking rules involved in returning VM_FAULT_RETRY depending on
* FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
* FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
* recommendation in __lock_page_or_retry is not an understatement.
*
* If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released
* before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
* not set.
*
* If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
* set, VM_FAULT_RETRY can still be returned if and only if there are
* fatal_signal_pending()s, and the mmap_lock must be released before
* returning it.
*/
vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
{
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue uwq;
vm_fault_t ret = VM_FAULT_SIGBUS;
bool must_wait;
unsigned int blocking_state;
/*
* We don't do userfault handling for the final child pid update
* and when coredumping (faults triggered by get_dump_page()).
*/
if (current->flags & (PF_EXITING|PF_DUMPCORE))
goto out;
assert_fault_locked(vmf);
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx)
goto out;
BUG_ON(ctx->mm != mm);
/* Any unrecognized flag is a bug. */
VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
/* 0 or > 1 flags set is a bug; we expect exactly 1. */
VM_BUG_ON(!reason || (reason & (reason - 1)));
if (ctx->features & UFFD_FEATURE_SIGBUS)
goto out;
if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
goto out;
/*
* Check that we can return VM_FAULT_RETRY.
*
* NOTE: it should become possible to return VM_FAULT_RETRY
* even if FAULT_FLAG_TRIED is set without leading to gup()
* -EBUSY failures, if the userfaultfd is to be extended for
* VM_UFFD_WP tracking and we intend to arm the userfault
* without first stopping userland access to the memory. For
* VM_UFFD_MISSING userfaults this is enough for now.
*/
if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
/*
* Validate the invariant that nowait must allow retry
* to be sure not to return SIGBUS erroneously on
* nowait invocations.
*/
BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
#ifdef CONFIG_DEBUG_VM
if (printk_ratelimit()) {
printk(KERN_WARNING
"FAULT_FLAG_ALLOW_RETRY missing %x\n",
vmf->flags);
dump_stack();
}
#endif
goto out;
}
/*
* Handle nowait, not much to do other than tell it to retry
* and wait.
*/
ret = VM_FAULT_RETRY;
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
goto out;
if (unlikely(READ_ONCE(ctx->released))) {
/*
* If a concurrent release is detected, do not return
* VM_FAULT_SIGBUS or VM_FAULT_NOPAGE, but instead always
* return VM_FAULT_RETRY with lock released proactively.
*
* If we were to return VM_FAULT_SIGBUS here, the non
* cooperative manager would be instead forced to
* always call UFFDIO_UNREGISTER before it can safely
* close the uffd, to avoid involuntary SIGBUS triggered.
*
* If we were to return VM_FAULT_NOPAGE, it would work for
* the fault path, in which the lock will be released
* later. However for GUP, faultin_page() does nothing
* special on NOPAGE, so GUP would spin retrying without
* releasing the mmap read lock, causing possible livelock.
*
* Here only VM_FAULT_RETRY would make sure the mmap lock
* be released immediately, so that the thread concurrently
* releasing the userfault would always make progress.
*/
release_fault_lock(vmf);
goto out;
}
/* take the reference before dropping the mmap_lock */
userfaultfd_ctx_get(ctx);
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
uwq.wq.private = current;
uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
reason, ctx->features);
uwq.ctx = ctx;
uwq.waken = false;
blocking_state = userfaultfd_get_blocking_state(vmf->flags);
/*
* Take the vma lock now, in order to safely call
* userfaultfd_huge_must_wait() later. Since acquiring the
* (sleepable) vma lock can modify the current task state, that
* must be before explicitly calling set_current_state().
*/
if (is_vm_hugetlb_page(vma))
hugetlb_vma_lock_read(vma);
spin_lock_irq(&ctx->fault_pending_wqh.lock);
/*
* After the __add_wait_queue the uwq is visible to userland
* through poll/read().
*/
__add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
/*
* The smp_mb() after __set_current_state prevents the reads
* following the spin_unlock to happen before the list_add in
* __add_wait_queue.
*/
set_current_state(blocking_state);
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
if (!is_vm_hugetlb_page(vma))
must_wait = userfaultfd_must_wait(ctx, vmf, reason);
else
must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason);
if (is_vm_hugetlb_page(vma))
hugetlb_vma_unlock_read(vma);
release_fault_lock(vmf);
if (likely(must_wait && !READ_ONCE(ctx->released))) {
wake_up_poll(&ctx->fd_wqh, EPOLLIN);
schedule();
}
__set_current_state(TASK_RUNNING);
/*
* Here we race with the list_del; list_add in
* userfaultfd_ctx_read(), however because we don't ever run
* list_del_init() to refile across the two lists, the prev
* and next pointers will never point to self. list_add also
* would never let any of the two pointers to point to
* self. So list_empty_careful won't risk to see both pointers
* pointing to self at any time during the list refile. The
* only case where list_del_init() is called is the full
* removal in the wake function and there we don't re-list_add
* and it's fine not to block on the spinlock. The uwq on this
* kernel stack can be released after the list_del_init.
*/
if (!list_empty_careful(&uwq.wq.entry)) {
spin_lock_irq(&ctx->fault_pending_wqh.lock);
/*
* No need of list_del_init(), the uwq on the stack
* will be freed shortly anyway.
*/
list_del(&uwq.wq.entry);
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
}
/*
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
userfaultfd_ctx_put(ctx);
out:
return ret;
}
static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
{
struct userfaultfd_ctx *release_new_ctx;
if (WARN_ON_ONCE(current->flags & PF_EXITING))
goto out;
ewq->ctx = ctx;
init_waitqueue_entry(&ewq->wq, current);
release_new_ctx = NULL;
spin_lock_irq(&ctx->event_wqh.lock);
/*
* After the __add_wait_queue the uwq is visible to userland
* through poll/read().
*/
__add_wait_queue(&ctx->event_wqh, &ewq->wq);
for (;;) {
set_current_state(TASK_KILLABLE);
if (ewq->msg.event == 0)
break;
if (READ_ONCE(ctx->released) ||
fatal_signal_pending(current)) {
/*
* &ewq->wq may be queued in fork_event, but
* __remove_wait_queue ignores the head
* parameter. It would be a problem if it
* didn't.
*/
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
if (ewq->msg.event == UFFD_EVENT_FORK) {
struct userfaultfd_ctx *new;
new = (struct userfaultfd_ctx *)
(unsigned long)
ewq->msg.arg.reserved.reserved1;
release_new_ctx = new;
}
break;
}
spin_unlock_irq(&ctx->event_wqh.lock);
wake_up_poll(&ctx->fd_wqh, EPOLLIN);
schedule();
spin_lock_irq(&ctx->event_wqh.lock);
}
__set_current_state(TASK_RUNNING);
spin_unlock_irq(&ctx->event_wqh.lock);
if (release_new_ctx) {
userfaultfd_release_new(release_new_ctx);
userfaultfd_ctx_put(release_new_ctx);
}
/*
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
out:
atomic_dec(&ctx->mmap_changing);
VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0);
userfaultfd_ctx_put(ctx);
}
static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
{
ewq->msg.event = 0;
wake_up_locked(&ctx->event_wqh);
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
}
int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
{
struct userfaultfd_ctx *ctx = NULL, *octx;
struct userfaultfd_fork_ctx *fctx;
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx)
return 0;
if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) {
userfaultfd_reset_ctx(vma);
return 0;
}
list_for_each_entry(fctx, fcs, list)
if (fctx->orig == octx) {
ctx = fctx->new;
break;
}
if (!ctx) {
fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
if (!fctx)
return -ENOMEM;
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
if (!ctx) {
kfree(fctx);
return -ENOMEM;
}
refcount_set(&ctx->refcount, 1);
ctx->flags = octx->flags;
ctx->features = octx->features;
ctx->released = false;
init_rwsem(&ctx->map_changing_lock);
atomic_set(&ctx->mmap_changing, 0);
ctx->mm = vma->vm_mm;
mmgrab(ctx->mm);
userfaultfd_ctx_get(octx);
down_write(&octx->map_changing_lock);
atomic_inc(&octx->mmap_changing);
up_write(&octx->map_changing_lock);
fctx->orig = octx;
fctx->new = ctx;
list_add_tail(&fctx->list, fcs);
}
vma->vm_userfaultfd_ctx.ctx = ctx;
return 0;
}
static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
{
struct userfaultfd_ctx *ctx = fctx->orig;
struct userfaultfd_wait_queue ewq;
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_FORK;
ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
userfaultfd_event_wait_completion(ctx, &ewq);
}
void dup_userfaultfd_complete(struct list_head *fcs)
{
struct userfaultfd_fork_ctx *fctx, *n;
list_for_each_entry_safe(fctx, n, fcs, list) {
dup_fctx(fctx);
list_del(&fctx->list);
kfree(fctx);
}
}
void dup_userfaultfd_fail(struct list_head *fcs)
{
struct userfaultfd_fork_ctx *fctx, *n;
/*
* An error has occurred on fork, we will tear memory down, but have
* allocated memory for fctx's and raised reference counts for both the
* original and child contexts (and on the mm for each as a result).
*
* These would ordinarily be taken care of by a user handling the event,
* but we are no longer doing so, so manually clean up here.
*
* mm tear down will take care of cleaning up VMA contexts.
*/
list_for_each_entry_safe(fctx, n, fcs, list) {
struct userfaultfd_ctx *octx = fctx->orig;
struct userfaultfd_ctx *ctx = fctx->new;
atomic_dec(&octx->mmap_changing);
VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
userfaultfd_ctx_put(octx);
userfaultfd_ctx_put(ctx);
list_del(&fctx->list);
kfree(fctx);
}
}
void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *vm_ctx)
{
struct userfaultfd_ctx *ctx;
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx)
return;
if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
vm_ctx->ctx = ctx;
userfaultfd_ctx_get(ctx);
down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
up_write(&ctx->map_changing_lock);
} else {
/* Drop uffd context if remap feature not enabled */
userfaultfd_reset_ctx(vma);
}
}
void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
unsigned long from, unsigned long to,
unsigned long len)
{
struct userfaultfd_ctx *ctx = vm_ctx->ctx;
struct userfaultfd_wait_queue ewq;
if (!ctx)
return;
if (to & ~PAGE_MASK) {
userfaultfd_ctx_put(ctx);
return;
}
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMAP;
ewq.msg.arg.remap.from = from;
ewq.msg.arg.remap.to = to;
ewq.msg.arg.remap.len = len;
userfaultfd_event_wait_completion(ctx, &ewq);
}
bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue ewq;
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
return true;
userfaultfd_ctx_get(ctx);
down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
up_write(&ctx->map_changing_lock);
mmap_read_unlock(mm);
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMOVE;
ewq.msg.arg.remove.start = start;
ewq.msg.arg.remove.end = end;
userfaultfd_event_wait_completion(ctx, &ewq);
return false;
}
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
unsigned long start, unsigned long end)
{
struct userfaultfd_unmap_ctx *unmap_ctx;
list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
unmap_ctx->end == end)
return true;
return false;
}
int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct list_head *unmaps)
{
struct userfaultfd_unmap_ctx *unmap_ctx;
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end))
return 0;
unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
if (!unmap_ctx)
return -ENOMEM;
userfaultfd_ctx_get(ctx);
down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
up_write(&ctx->map_changing_lock);
unmap_ctx->ctx = ctx;
unmap_ctx->start = start;
unmap_ctx->end = end;
list_add_tail(&unmap_ctx->list, unmaps);
return 0;
}
void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
{
struct userfaultfd_unmap_ctx *ctx, *n;
struct userfaultfd_wait_queue ewq;
list_for_each_entry_safe(ctx, n, uf, list) {
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_UNMAP;
ewq.msg.arg.remove.start = ctx->start;
ewq.msg.arg.remove.end = ctx->end;
userfaultfd_event_wait_completion(ctx->ctx, &ewq);
list_del(&ctx->list);
kfree(ctx);
}
}
static int userfaultfd_release(struct inode *inode, struct file *file)
{
struct userfaultfd_ctx *ctx = file->private_data;
struct mm_struct *mm = ctx->mm;
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
WRITE_ONCE(ctx->released, true);
userfaultfd_release_all(mm, ctx);
/*
* After no new page faults can wait on this fault_*wqh, flush
* the last page faults that may have been already waiting on
* the fault_*wqh.
*/
spin_lock_irq(&ctx->fault_pending_wqh.lock);
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range);
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
/* Flush pending events that may still wait on event_wqh */
wake_up_all(&ctx->event_wqh);
wake_up_poll(&ctx->fd_wqh, EPOLLHUP);
userfaultfd_ctx_put(ctx);
return 0;
}
/* fault_pending_wqh.lock must be hold by the caller */
static inline struct userfaultfd_wait_queue *find_userfault_in(
wait_queue_head_t *wqh)
{
wait_queue_entry_t *wq;
struct userfaultfd_wait_queue *uwq;
lockdep_assert_held(&wqh->lock);
uwq = NULL;
if (!waitqueue_active(wqh))
goto out;
/* walk in reverse to provide FIFO behavior to read userfaults */
wq = list_last_entry(&wqh->head, typeof(*wq), entry);
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
out:
return uwq;
}
static inline struct userfaultfd_wait_queue *find_userfault(
struct userfaultfd_ctx *ctx)
{
return find_userfault_in(&ctx->fault_pending_wqh);
}
static inline struct userfaultfd_wait_queue *find_userfault_evt(
struct userfaultfd_ctx *ctx)
{
return find_userfault_in(&ctx->event_wqh);
}
static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
{
struct userfaultfd_ctx *ctx = file->private_data;
__poll_t ret;
poll_wait(file, &ctx->fd_wqh, wait);
if (!userfaultfd_is_initialized(ctx))
return EPOLLERR;
/*
* poll() never guarantees that read won't block.
* userfaults can be waken before they're read().
*/
if (unlikely(!(file->f_flags & O_NONBLOCK)))
return EPOLLERR;
/*
* lockless access to see if there are pending faults
* __pollwait last action is the add_wait_queue but
* the spin_unlock would allow the waitqueue_active to
* pass above the actual list_add inside
* add_wait_queue critical section. So use a full
* memory barrier to serialize the list_add write of
* add_wait_queue() with the waitqueue_active read
* below.
*/
ret = 0;
smp_mb();
if (waitqueue_active(&ctx->fault_pending_wqh))
ret = EPOLLIN;
else if (waitqueue_active(&ctx->event_wqh))
ret = EPOLLIN;
return ret;
}
static const struct file_operations userfaultfd_fops;
static int resolve_userfault_fork(struct userfaultfd_ctx *new,
struct inode *inode,
struct uffd_msg *msg)
{
int fd;
fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
if (fd < 0)
return fd;
msg->arg.reserved.reserved1 = 0;
msg->arg.fork.ufd = fd;
return 0;
}
static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
struct uffd_msg *msg, struct inode *inode)
{
ssize_t ret;
DECLARE_WAITQUEUE(wait, current);
struct userfaultfd_wait_queue *uwq;
/*
* Handling fork event requires sleeping operations, so
* we drop the event_wqh lock, then do these ops, then
* lock it back and wake up the waiter. While the lock is
* dropped the ewq may go away so we keep track of it
* carefully.
*/
LIST_HEAD(fork_event);
struct userfaultfd_ctx *fork_nctx = NULL;
/* always take the fd_wqh lock before the fault_pending_wqh lock */
spin_lock_irq(&ctx->fd_wqh.lock);
__add_wait_queue(&ctx->fd_wqh, &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
spin_lock(&ctx->fault_pending_wqh.lock);
uwq = find_userfault(ctx);
if (uwq) {
/*
* Use a seqcount to repeat the lockless check
* in wake_userfault() to avoid missing
* wakeups because during the refile both
* waitqueue could become empty if this is the
* only userfault.
*/
write_seqcount_begin(&ctx->refile_seq);
/*
* The fault_pending_wqh.lock prevents the uwq
* to disappear from under us.
*
* Refile this userfault from
* fault_pending_wqh to fault_wqh, it's not
* pending anymore after we read it.
*
* Use list_del() by hand (as
* userfaultfd_wake_function also uses
* list_del_init() by hand) to be sure nobody
* changes __remove_wait_queue() to use
* list_del_init() in turn breaking the
* !list_empty_careful() check in
* handle_userfault(). The uwq->wq.head list
* must never be empty at any time during the
* refile, or the waitqueue could disappear
* from under us. The "wait_queue_head_t"
* parameter of __remove_wait_queue() is unused
* anyway.
*/
list_del(&uwq->wq.entry);
add_wait_queue(&ctx->fault_wqh, &uwq->wq);
write_seqcount_end(&ctx->refile_seq);
/* careful to always initialize msg if ret == 0 */
*msg = uwq->msg;
spin_unlock(&ctx->fault_pending_wqh.lock);
ret = 0;
break;
}
spin_unlock(&ctx->fault_pending_wqh.lock);
spin_lock(&ctx->event_wqh.lock);
uwq = find_userfault_evt(ctx);
if (uwq) {
*msg = uwq->msg;
if (uwq->msg.event == UFFD_EVENT_FORK) {
fork_nctx = (struct userfaultfd_ctx *)
(unsigned long)
uwq->msg.arg.reserved.reserved1;
list_move(&uwq->wq.entry, &fork_event);
/*
* fork_nctx can be freed as soon as
* we drop the lock, unless we take a
* reference on it.
*/
userfaultfd_ctx_get(fork_nctx);
spin_unlock(&ctx->event_wqh.lock);
ret = 0;
break;
}
userfaultfd_event_complete(ctx, uwq);
spin_unlock(&ctx->event_wqh.lock);
ret = 0;
break;
}
spin_unlock(&ctx->event_wqh.lock);
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
}
if (no_wait) {
ret = -EAGAIN;
break;
}
spin_unlock_irq(&ctx->fd_wqh.lock);
schedule();
spin_lock_irq(&ctx->fd_wqh.lock);
}
__remove_wait_queue(&ctx->fd_wqh, &wait);
__set_current_state(TASK_RUNNING);
spin_unlock_irq(&ctx->fd_wqh.lock);
if (!ret && msg->event == UFFD_EVENT_FORK) {
ret = resolve_userfault_fork(fork_nctx, inode, msg);
spin_lock_irq(&ctx->event_wqh.lock);
if (!list_empty(&fork_event)) {
/*
* The fork thread didn't abort, so we can
* drop the temporary refcount.
*/
userfaultfd_ctx_put(fork_nctx);
uwq = list_first_entry(&fork_event,
typeof(*uwq),
wq.entry);
/*
* If fork_event list wasn't empty and in turn
* the event wasn't already released by fork
* (the event is allocated on fork kernel
* stack), put the event back to its place in
* the event_wq. fork_event head will be freed
* as soon as we return so the event cannot
* stay queued there no matter the current
* "ret" value.
*/
list_del(&uwq->wq.entry);
__add_wait_queue(&ctx->event_wqh, &uwq->wq);
/*
* Leave the event in the waitqueue and report
* error to userland if we failed to resolve
* the userfault fork.
*/
if (likely(!ret))
userfaultfd_event_complete(ctx, uwq);
} else {
/*
* Here the fork thread aborted and the
* refcount from the fork thread on fork_nctx
* has already been released. We still hold
* the reference we took before releasing the
* lock above. If resolve_userfault_fork
* failed we've to drop it because the
* fork_nctx has to be freed in such case. If
* it succeeded we'll hold it because the new
* uffd references it.
*/
if (ret)
userfaultfd_ctx_put(fork_nctx);
}
spin_unlock_irq(&ctx->event_wqh.lock);
}
return ret;
}
static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct userfaultfd_ctx *ctx = file->private_data;
ssize_t _ret, ret = 0;
struct uffd_msg msg;
struct inode *inode = file_inode(file);
bool no_wait;
if (!userfaultfd_is_initialized(ctx))
return -EINVAL;
no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT;
for (;;) {
if (iov_iter_count(to) < sizeof(msg))
return ret ? ret : -EINVAL;
_ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode);
if (_ret < 0)
return ret ? ret : _ret;
_ret = !copy_to_iter_full(&msg, sizeof(msg), to);
if (_ret)
return ret ? ret : -EFAULT;
ret += sizeof(msg);
/*
* Allow to read more than one fault at time but only
* block if waiting for the very first one.
*/
no_wait = true;
}
}
static void __wake_userfault(struct userfaultfd_ctx *ctx,
struct userfaultfd_wake_range *range)
{
spin_lock_irq(&ctx->fault_pending_wqh.lock);
/* wake all in the range and autoremove */
if (waitqueue_active(&ctx->fault_pending_wqh))
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
range);
if (waitqueue_active(&ctx->fault_wqh))
__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range);
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
}
static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
struct userfaultfd_wake_range *range)
{
unsigned seq;
bool need_wakeup;
/*
* To be sure waitqueue_active() is not reordered by the CPU
* before the pagetable update, use an explicit SMP memory
* barrier here. PT lock release or mmap_read_unlock(mm) still
* have release semantics that can allow the
* waitqueue_active() to be reordered before the pte update.
*/
smp_mb();
/*
* Use waitqueue_active because it's very frequent to
* change the address space atomically even if there are no
* userfaults yet. So we take the spinlock only when we're
* sure we've userfaults to wake.
*/
do {
seq = read_seqcount_begin(&ctx->refile_seq);
need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
waitqueue_active(&ctx->fault_wqh);
cond_resched();
} while (read_seqcount_retry(&ctx->refile_seq, seq));
if (need_wakeup)
__wake_userfault(ctx, range);
}
static __always_inline int validate_unaligned_range(
struct mm_struct *mm, __u64 start, __u64 len)
{
__u64 task_size = mm->task_size;
if (len & ~PAGE_MASK)
return -EINVAL;
if (!len)
return -EINVAL;
if (start < mmap_min_addr)
return -EINVAL;
if (start >= task_size)
return -EINVAL;
if (len > task_size - start)
return -EINVAL;
if (start + len <= start)
return -EINVAL;
return 0;
}
static __always_inline int validate_range(struct mm_struct *mm,
__u64 start, __u64 len)
{
if (start & ~PAGE_MASK)
return -EINVAL;
return validate_unaligned_range(mm, start, len);
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct mm_struct *mm = ctx->mm;
struct vm_area_struct *vma, *cur;
int ret;
struct uffdio_register uffdio_register;
struct uffdio_register __user *user_uffdio_register;
unsigned long vm_flags;
bool found;
bool basic_ioctls;
unsigned long start, end;
struct vma_iterator vmi;
bool wp_async = userfaultfd_wp_async_ctx(ctx);
user_uffdio_register = (struct uffdio_register __user *) arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_register, user_uffdio_register,
sizeof(uffdio_register)-sizeof(__u64)))
goto out;
ret = -EINVAL;
if (!uffdio_register.mode)
goto out;
if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
goto out;
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
goto out;
#endif
vm_flags |= VM_UFFD_WP;
}
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
goto out;
#endif
vm_flags |= VM_UFFD_MINOR;
}
ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
if (ret)
goto out;
start = uffdio_register.range.start;
end = start + uffdio_register.range.len;
ret = -ENOMEM;
if (!mmget_not_zero(mm))
goto out;
ret = -EINVAL;
mmap_write_lock(mm);
vma_iter_init(&vmi, mm, start);
vma = vma_find(&vmi, end);
if (!vma)
goto out_unlock;
/*
* If the first vma contains huge pages, make sure start address
* is aligned to huge page size.
*/
if (is_vm_hugetlb_page(vma)) {
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
if (start & (vma_hpagesize - 1))
goto out_unlock;
}
/*
* Search for not compatible vmas.
*/
found = false;
basic_ioctls = false;
cur = vma;
do {
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
!!(cur->vm_flags & __VM_UFFD_FLAGS));
/* check not compatible vmas */
ret = -EINVAL;
if (!vma_can_userfault(cur, vm_flags, wp_async))
goto out_unlock;
/*
* UFFDIO_COPY will fill file holes even without
* PROT_WRITE. This check enforces that if this is a
* MAP_SHARED, the process has write permission to the backing
* file. If VM_MAYWRITE is set it also enforces that on a
* MAP_SHARED vma: there is no F_WRITE_SEAL and no further
* F_WRITE_SEAL can be taken until the vma is destroyed.
*/
ret = -EPERM;
if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
goto out_unlock;
/*
* If this vma contains ending address, and huge pages
* check alignment.
*/
if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
end > cur->vm_start) {
unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
ret = -EINVAL;
if (end & (vma_hpagesize - 1))
goto out_unlock;
}
if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
goto out_unlock;
/*
* Check that this vma isn't already owned by a
* different userfaultfd. We can't allow more than one
* userfaultfd to own a single vma simultaneously or we
* wouldn't know which one to deliver the userfaults to.
*/
ret = -EBUSY;
if (cur->vm_userfaultfd_ctx.ctx &&
cur->vm_userfaultfd_ctx.ctx != ctx)
goto out_unlock;
/*
* Note vmas containing huge pages
*/
if (is_vm_hugetlb_page(cur))
basic_ioctls = true;
found = true;
} for_each_vma_range(vmi, cur, end);
BUG_ON(!found);
ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end,
wp_async);
out_unlock:
mmap_write_unlock(mm);
mmput(mm);
if (!ret) {
__u64 ioctls_out;
ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
UFFD_API_RANGE_IOCTLS;
/*
* Declare the WP ioctl only if the WP mode is
* specified and all checks passed with the range
*/
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
/* CONTINUE ioctl is only supported for MINOR ranges. */
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
/*
* Now that we scanned all vmas we can already tell
* userland which ioctls methods are guaranteed to
* succeed on this range.
*/
if (put_user(ioctls_out, &user_uffdio_register->ioctls))
ret = -EFAULT;
}
out:
return ret;
}
static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct mm_struct *mm = ctx->mm;
struct vm_area_struct *vma, *prev, *cur;
int ret;
struct uffdio_range uffdio_unregister;
bool found;
unsigned long start, end, vma_end;
const void __user *buf = (void __user *)arg;
struct vma_iterator vmi;
bool wp_async = userfaultfd_wp_async_ctx(ctx);
ret = -EFAULT;
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
goto out;
ret = validate_range(mm, uffdio_unregister.start,
uffdio_unregister.len);
if (ret)
goto out;
start = uffdio_unregister.start;
end = start + uffdio_unregister.len;
ret = -ENOMEM;
if (!mmget_not_zero(mm))
goto out;
mmap_write_lock(mm);
ret = -EINVAL;
vma_iter_init(&vmi, mm, start);
vma = vma_find(&vmi, end);
if (!vma)
goto out_unlock;
/*
* If the first vma contains huge pages, make sure start address
* is aligned to huge page size.
*/
if (is_vm_hugetlb_page(vma)) {
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
if (start & (vma_hpagesize - 1))
goto out_unlock;
}
/*
* Search for not compatible vmas.
*/
found = false;
cur = vma;
do {
cond_resched();
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
!!(cur->vm_flags & __VM_UFFD_FLAGS));
/*
* Check not compatible vmas, not strictly required
* here as not compatible vmas cannot have an
* userfaultfd_ctx registered on them, but this
* provides for more strict behavior to notice
* unregistration errors.
*/
if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
goto out_unlock;
found = true;
} for_each_vma_range(vmi, cur, end);
BUG_ON(!found);
vma_iter_set(&vmi, start);
prev = vma_prev(&vmi);
if (vma->vm_start < start)
prev = vma;
ret = 0;
for_each_vma_range(vmi, vma, end) {
cond_resched();
BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async));
/*
* Nothing to do: this vma is already registered into this
* userfaultfd and with the right tracking mode too.
*/
if (!vma->vm_userfaultfd_ctx.ctx)
goto skip;
WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
if (vma->vm_start > start)
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
if (userfaultfd_missing(vma)) {
/*
* Wake any concurrent pending userfault while
* we unregister, so they will not hang
* permanently and it avoids userland to call
* UFFDIO_WAKE explicitly.
*/
struct userfaultfd_wake_range range;
range.start = start;
range.len = vma_end - start;
wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
}
vma = userfaultfd_clear_vma(&vmi, prev, vma,
start, vma_end);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
break;
}
skip:
prev = vma;
start = vma->vm_end;
}
out_unlock:
mmap_write_unlock(mm);
mmput(mm);
out:
return ret;
}
/*
* userfaultfd_wake may be used in combination with the
* UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
*/
static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
int ret;
struct uffdio_range uffdio_wake;
struct userfaultfd_wake_range range;
const void __user *buf = (void __user *)arg;
ret = -EFAULT;
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
goto out;
ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
if (ret)
goto out;
range.start = uffdio_wake.start;
range.len = uffdio_wake.len;
/*
* len == 0 means wake all and we don't want to wake all here,
* so check it again to be sure.
*/
VM_BUG_ON(!range.len);
wake_userfault(ctx, &range);
ret = 0;
out:
return ret;
}
static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
__s64 ret;
struct uffdio_copy uffdio_copy;
struct uffdio_copy __user *user_uffdio_copy;
struct userfaultfd_wake_range range;
uffd_flags_t flags = 0;
user_uffdio_copy = (struct uffdio_copy __user *) arg;
ret = -EAGAIN;
if (atomic_read(&ctx->mmap_changing))
goto out;
ret = -EFAULT;
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
/* don't copy "copy" last field */
sizeof(uffdio_copy)-sizeof(__s64)))
goto out;
ret = validate_unaligned_range(ctx->mm, uffdio_copy.src,
uffdio_copy.len);
if (ret)
goto out;
ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
if (ret)
goto out;
ret = -EINVAL;
if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
goto out;
if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src,
uffdio_copy.len, flags);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
if (ret < 0)
goto out;
BUG_ON(!ret);
/* len == 0 would wake all */
range.len = ret;
if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
range.start = uffdio_copy.dst;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
out:
return ret;
}
static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
__s64 ret;
struct uffdio_zeropage uffdio_zeropage;
struct uffdio_zeropage __user *user_uffdio_zeropage;
struct userfaultfd_wake_range range;
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
ret = -EAGAIN;
if (atomic_read(&ctx->mmap_changing))
goto out;
ret = -EFAULT;
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
/* don't copy "zeropage" last field */
sizeof(uffdio_zeropage)-sizeof(__s64)))
goto out;
ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
if (ret)
goto out;
ret = -EINVAL;
if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
goto out;
if (mmget_not_zero(ctx->mm)) {
ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
return -EFAULT;
if (ret < 0)
goto out;
/* len == 0 would wake all */
BUG_ON(!ret);
range.len = ret;
if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
range.start = uffdio_zeropage.range.start;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
out:
return ret;
}
static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
int ret;
struct uffdio_writeprotect uffdio_wp;
struct uffdio_writeprotect __user *user_uffdio_wp;
struct userfaultfd_wake_range range;
bool mode_wp, mode_dontwake;
if (atomic_read(&ctx->mmap_changing))
return -EAGAIN;
user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
if (copy_from_user(&uffdio_wp, user_uffdio_wp,
sizeof(struct uffdio_writeprotect)))
return -EFAULT;
ret = validate_range(ctx->mm, uffdio_wp.range.start,
uffdio_wp.range.len);
if (ret)
return ret;
if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
UFFDIO_WRITEPROTECT_MODE_WP))
return -EINVAL;
mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
if (mode_wp && mode_dontwake)
return -EINVAL;
if (mmget_not_zero(ctx->mm)) {
ret = mwriteprotect_range(ctx, uffdio_wp.range.start,
uffdio_wp.range.len, mode_wp);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (ret)
return ret;
if (!mode_wp && !mode_dontwake) {
range.start = uffdio_wp.range.start;
range.len = uffdio_wp.range.len;
wake_userfault(ctx, &range);
}
return ret;
}
static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
{
__s64 ret;
struct uffdio_continue uffdio_continue;
struct uffdio_continue __user *user_uffdio_continue;
struct userfaultfd_wake_range range;
uffd_flags_t flags = 0;
user_uffdio_continue = (struct uffdio_continue __user *)arg;
ret = -EAGAIN;
if (atomic_read(&ctx->mmap_changing))
goto out;
ret = -EFAULT;
if (copy_from_user(&uffdio_continue, user_uffdio_continue,
/* don't copy the output fields */
sizeof(uffdio_continue) - (sizeof(__s64))))
goto out;
ret = validate_range(ctx->mm, uffdio_continue.range.start,
uffdio_continue.range.len);
if (ret)
goto out;
ret = -EINVAL;
if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
UFFDIO_CONTINUE_MODE_WP))
goto out;
if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
ret = mfill_atomic_continue(ctx, uffdio_continue.range.start,
uffdio_continue.range.len, flags);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
return -EFAULT;
if (ret < 0)
goto out;
/* len == 0 would wake all */
BUG_ON(!ret);
range.len = ret;
if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
range.start = uffdio_continue.range.start;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
out:
return ret;
}
static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg)
{
__s64 ret;
struct uffdio_poison uffdio_poison;
struct uffdio_poison __user *user_uffdio_poison;
struct userfaultfd_wake_range range;
user_uffdio_poison = (struct uffdio_poison __user *)arg;
ret = -EAGAIN;
if (atomic_read(&ctx->mmap_changing))
goto out;
ret = -EFAULT;
if (copy_from_user(&uffdio_poison, user_uffdio_poison,
/* don't copy the output fields */
sizeof(uffdio_poison) - (sizeof(__s64))))
goto out;
ret = validate_range(ctx->mm, uffdio_poison.range.start,
uffdio_poison.range.len);
if (ret)
goto out;
ret = -EINVAL;
if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE)
goto out;
if (mmget_not_zero(ctx->mm)) {
ret = mfill_atomic_poison(ctx, uffdio_poison.range.start,
uffdio_poison.range.len, 0);
mmput(ctx->mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
return -EFAULT;
if (ret < 0)
goto out;
/* len == 0 would wake all */
BUG_ON(!ret);
range.len = ret;
if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) {
range.start = uffdio_poison.range.start;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN;
out:
return ret;
}
bool userfaultfd_wp_async(struct vm_area_struct *vma)
{
return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx);
}
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
* For the current set of features the bits just coincide. Set
* UFFD_FEATURE_INITIALIZED to mark the features as enabled.
*/
return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
}
static int userfaultfd_move(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
__s64 ret;
struct uffdio_move uffdio_move;
struct uffdio_move __user *user_uffdio_move;
struct userfaultfd_wake_range range;
struct mm_struct *mm = ctx->mm;
user_uffdio_move = (struct uffdio_move __user *) arg;
if (atomic_read(&ctx->mmap_changing))
return -EAGAIN;
if (copy_from_user(&uffdio_move, user_uffdio_move,
/* don't copy "move" last field */
sizeof(uffdio_move)-sizeof(__s64)))
return -EFAULT;
/* Do not allow cross-mm moves. */
if (mm != current->mm)
return -EINVAL;
ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
if (ret)
return ret;
ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
if (ret)
return ret;
if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
UFFDIO_MOVE_MODE_DONTWAKE))
return -EINVAL;
if (mmget_not_zero(mm)) {
ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src,
uffdio_move.len, uffdio_move.mode);
mmput(mm);
} else {
return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_move->move)))
return -EFAULT;
if (ret < 0)
goto out;
/* len == 0 would wake all */
VM_WARN_ON(!ret);
range.len = ret;
if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
range.start = uffdio_move.dst;
wake_userfault(ctx, &range);
}
ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
out:
return ret;
}
/*
* userland asks for a certain API version and we return which bits
* and ioctl commands are implemented in this kernel for such API
* version or -EINVAL if unknown.
*/
static int userfaultfd_api(struct userfaultfd_ctx *ctx,
unsigned long arg)
{
struct uffdio_api uffdio_api;
void __user *buf = (void __user *)arg;
unsigned int ctx_features;
int ret;
__u64 features;
ret = -EFAULT;
if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
goto out;
features = uffdio_api.features;
ret = -EINVAL;
if (uffdio_api.api != UFFD_API)
goto err_out;
ret = -EPERM;
if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
goto err_out;
/* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */
if (features & UFFD_FEATURE_WP_ASYNC)
features |= UFFD_FEATURE_WP_UNPOPULATED;
/* report all available features and ioctls to userland */
uffdio_api.features = UFFD_API_FEATURES;
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
uffdio_api.features &=
~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
#endif
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
#endif
#ifndef CONFIG_PTE_MARKER_UFFD_WP
uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
#endif
ret = -EINVAL;
if (features & ~uffdio_api.features)
goto err_out;
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
goto out;
/* only enable the requested features for this uffd context */
ctx_features = uffd_ctx_features(features);
ret = -EINVAL;
if (cmpxchg(&ctx->features, 0, ctx_features) != 0)
goto err_out;
ret = 0;
out:
return ret;
err_out:
memset(&uffdio_api, 0, sizeof(uffdio_api));
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
ret = -EFAULT;
goto out;
}
static long userfaultfd_ioctl(struct file *file, unsigned cmd,
unsigned long arg)
{
int ret = -EINVAL;
struct userfaultfd_ctx *ctx = file->private_data;
if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx))
return -EINVAL;
switch(cmd) {
case UFFDIO_API:
ret = userfaultfd_api(ctx, arg);
break;
case UFFDIO_REGISTER:
ret = userfaultfd_register(ctx, arg);
break;
case UFFDIO_UNREGISTER:
ret = userfaultfd_unregister(ctx, arg);
break;
case UFFDIO_WAKE:
ret = userfaultfd_wake(ctx, arg);
break;
case UFFDIO_COPY:
ret = userfaultfd_copy(ctx, arg);
break;
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
case UFFDIO_MOVE:
ret = userfaultfd_move(ctx, arg);
break;
case UFFDIO_WRITEPROTECT:
ret = userfaultfd_writeprotect(ctx, arg);
break;
case UFFDIO_CONTINUE:
ret = userfaultfd_continue(ctx, arg);
break;
case UFFDIO_POISON:
ret = userfaultfd_poison(ctx, arg);
break;
}
return ret;
}
#ifdef CONFIG_PROC_FS
static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
{
struct userfaultfd_ctx *ctx = f->private_data;
wait_queue_entry_t *wq;
unsigned long pending = 0, total = 0;
spin_lock_irq(&ctx->fault_pending_wqh.lock);
list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
pending++;
total++;
}
list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
total++;
}
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
/*
* If more protocols will be added, there will be all shown
* separated by a space. Like this:
* protocols: aa:... bb:...
*/
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
pending, total, UFFD_API, ctx->features,
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif
static const struct file_operations userfaultfd_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = userfaultfd_show_fdinfo,
#endif
.release = userfaultfd_release,
.poll = userfaultfd_poll,
.read_iter = userfaultfd_read_iter,
.unlocked_ioctl = userfaultfd_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
static void init_once_userfaultfd_ctx(void *mem)
{
struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;
init_waitqueue_head(&ctx->fault_pending_wqh);
init_waitqueue_head(&ctx->fault_wqh);
init_waitqueue_head(&ctx->event_wqh);
init_waitqueue_head(&ctx->fd_wqh);
seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
}
static int new_userfaultfd(int flags)
{
struct userfaultfd_ctx *ctx;
struct file *file;
int fd;
BUG_ON(!current->mm);
/* Check the UFFD_* constants for consistency. */
BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
return -EINVAL;
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
if (!ctx)
return -ENOMEM;
refcount_set(&ctx->refcount, 1);
ctx->flags = flags;
ctx->features = 0;
ctx->released = false;
init_rwsem(&ctx->map_changing_lock);
atomic_set(&ctx->mmap_changing, 0);
ctx->mm = current->mm;
fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
if (fd < 0)
goto err_out;
/* Create a new inode so that the LSM can block the creation. */
file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
if (IS_ERR(file)) {
put_unused_fd(fd);
fd = PTR_ERR(file);
goto err_out;
}
/* prevent the mm struct to be freed */
mmgrab(ctx->mm);
file->f_mode |= FMODE_NOWAIT;
fd_install(fd, file);
return fd;
err_out:
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
return fd;
}
static inline bool userfaultfd_syscall_allowed(int flags)
{
/* Userspace-only page faults are always allowed */
if (flags & UFFD_USER_MODE_ONLY)
return true;
/*
* The user is requesting a userfaultfd which can handle kernel faults.
* Privileged users are always allowed to do this.
*/
if (capable(CAP_SYS_PTRACE))
return true;
/* Otherwise, access to kernel fault handling is sysctl controlled. */
return sysctl_unprivileged_userfaultfd;
}
SYSCALL_DEFINE1(userfaultfd, int, flags)
{
if (!userfaultfd_syscall_allowed(flags))
return -EPERM;
return new_userfaultfd(flags);
}
static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
{
if (cmd != USERFAULTFD_IOC_NEW)
return -EINVAL;
return new_userfaultfd(flags);
}
static const struct file_operations userfaultfd_dev_fops = {
.unlocked_ioctl = userfaultfd_dev_ioctl,
.compat_ioctl = userfaultfd_dev_ioctl,
.owner = THIS_MODULE,
.llseek = noop_llseek,
};
static struct miscdevice userfaultfd_misc = {
.minor = MISC_DYNAMIC_MINOR,
.name = "userfaultfd",
.fops = &userfaultfd_dev_fops
};
static int __init userfaultfd_init(void)
{
int ret;
ret = misc_register(&userfaultfd_misc);
if (ret)
return ret;
userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
sizeof(struct userfaultfd_ctx),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
init_once_userfaultfd_ctx);
#ifdef CONFIG_SYSCTL
register_sysctl_init("vm", vm_userfaultfd_table);
#endif
return 0;
}
__initcall(userfaultfd_init);
/* SPDX-License-Identifier: GPL-2.0
*
* Network memory
*
* Author: Mina Almasry <almasrymina@google.com>
*/
#ifndef _NET_NETMEM_H
#define _NET_NETMEM_H
#include <linux/mm.h>
#include <net/net_debug.h>
/* net_iov */
DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
/* We overload the LSB of the struct page pointer to indicate whether it's
* a page or net_iov.
*/
#define NET_IOV 0x01UL
struct net_iov {
unsigned long __unused_padding;
unsigned long pp_magic;
struct page_pool *pp;
struct net_iov_area *owner;
unsigned long dma_addr;
atomic_long_t pp_ref_count;
};
struct net_iov_area {
/* Array of net_iovs for this area. */
struct net_iov *niovs;
size_t num_niovs;
/* Offset into the dma-buf where this chunk starts. */
unsigned long base_virtual;
};
/* These fields in struct page are used by the page_pool and net stack:
*
* struct {
* unsigned long pp_magic;
* struct page_pool *pp;
* unsigned long _pp_mapping_pad;
* unsigned long dma_addr;
* atomic_long_t pp_ref_count;
* };
*
* We mirror the page_pool fields here so the page_pool can access these fields
* without worrying whether the underlying fields belong to a page or net_iov.
*
* The non-net stack fields of struct page are private to the mm stack and must
* never be mirrored to net_iov.
*/
#define NET_IOV_ASSERT_OFFSET(pg, iov) \
static_assert(offsetof(struct page, pg) == \
offsetof(struct net_iov, iov))
NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
NET_IOV_ASSERT_OFFSET(pp, pp);
NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
#undef NET_IOV_ASSERT_OFFSET
static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov)
{
return niov->owner;
}
static inline unsigned int net_iov_idx(const struct net_iov *niov)
{
return niov - net_iov_owner(niov)->niovs;
}
/* netmem */
/**
* typedef netmem_ref - a nonexistent type marking a reference to generic
* network memory.
*
* A netmem_ref currently is always a reference to a struct page. This
* abstraction is introduced so support for new memory types can be added.
*
* Use the supplied helpers to obtain the underlying memory pointer and fields.
*/
typedef unsigned long __bitwise netmem_ref;
static inline bool netmem_is_net_iov(const netmem_ref netmem)
{
return (__force unsigned long)netmem & NET_IOV;
}
/**
* __netmem_to_page - unsafely get pointer to the &page backing @netmem
* @netmem: netmem reference to convert
*
* Unsafe version of netmem_to_page(). When @netmem is always page-backed,
* e.g. when it's a header buffer, performs faster and generates smaller
* object code (no check for the LSB, no WARN). When @netmem points to IOV,
* provokes undefined behaviour.
*
* Return: pointer to the &page (garbage if @netmem is not page-backed).
*/
static inline struct page *__netmem_to_page(netmem_ref netmem)
{
return (__force struct page *)netmem;
}
/* This conversion fails (returns NULL) if the netmem_ref is not struct page
* backed.
*/
static inline struct page *netmem_to_page(netmem_ref netmem)
{
if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
return NULL;
return __netmem_to_page(netmem);
}
static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem)
{
if (netmem_is_net_iov(netmem))
return (struct net_iov *)((__force unsigned long)netmem &
~NET_IOV);
DEBUG_NET_WARN_ON_ONCE(true);
return NULL;
}
static inline netmem_ref net_iov_to_netmem(struct net_iov *niov)
{
return (__force netmem_ref)((unsigned long)niov | NET_IOV);
}
static inline netmem_ref page_to_netmem(struct page *page)
{
return (__force netmem_ref)page;
}
/**
* virt_to_netmem - convert virtual memory pointer to a netmem reference
* @data: host memory pointer to convert
*
* Return: netmem reference to the &page backing this virtual address.
*/
static inline netmem_ref virt_to_netmem(const void *data)
{
return page_to_netmem(virt_to_page(data));
}
static inline int netmem_ref_count(netmem_ref netmem)
{
/* The non-pp refcount of net_iov is always 1. On net_iov, we only
* support pp refcounting which uses the pp_ref_count field.
*/
if (netmem_is_net_iov(netmem))
return 1;
return page_ref_count(netmem_to_page(netmem));
}
static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
{
if (netmem_is_net_iov(netmem))
return 0;
return page_to_pfn(netmem_to_page(netmem));
}
static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
{
return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV);
}
/**
* __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem
* @netmem: netmem reference to get the pointer from
*
* Unsafe version of netmem_get_pp(). When @netmem is always page-backed,
* e.g. when it's a header buffer, performs faster and generates smaller
* object code (avoids clearing the LSB). When @netmem points to IOV,
* provokes invalid memory access.
*
* Return: pointer to the &page_pool (garbage if @netmem is not page-backed).
*/
static inline struct page_pool *__netmem_get_pp(netmem_ref netmem)
{
return __netmem_to_page(netmem)->pp;
}
static inline struct page_pool *netmem_get_pp(netmem_ref netmem)
{
return __netmem_clear_lsb(netmem)->pp;
}
static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem)
{
return &__netmem_clear_lsb(netmem)->pp_ref_count;
}
static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid)
{
/* NUMA node preference only makes sense if we're allocating
* system memory. Memory providers (which give us net_iovs)
* choose for us.
*/
if (netmem_is_net_iov(netmem))
return true;
return page_to_nid(netmem_to_page(netmem)) == pref_nid;
}
static inline netmem_ref netmem_compound_head(netmem_ref netmem)
{
/* niov are never compounded */
if (netmem_is_net_iov(netmem))
return netmem;
return page_to_netmem(compound_head(netmem_to_page(netmem)));
}
/**
* __netmem_address - unsafely get pointer to the memory backing @netmem
* @netmem: netmem reference to get the pointer for
*
* Unsafe version of netmem_address(). When @netmem is always page-backed,
* e.g. when it's a header buffer, performs faster and generates smaller
* object code (no check for the LSB). When @netmem points to IOV, provokes
* undefined behaviour.
*
* Return: pointer to the memory (garbage if @netmem is not page-backed).
*/
static inline void *__netmem_address(netmem_ref netmem)
{
return page_address(__netmem_to_page(netmem));
}
static inline void *netmem_address(netmem_ref netmem)
{
if (netmem_is_net_iov(netmem))
return NULL;
return __netmem_address(netmem);
}
/**
* netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure
* @netmem: netmem reference to check
*
* Return: true if @netmem is page-backed and the page was allocated under
* memory pressure, false otherwise.
*/
static inline bool netmem_is_pfmemalloc(netmem_ref netmem)
{
if (netmem_is_net_iov(netmem))
return false;
return page_is_pfmemalloc(netmem_to_page(netmem));
}
static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
{
return __netmem_clear_lsb(netmem)->dma_addr;
}
#endif /* _NET_NETMEM_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/swapfile.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*/
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shmem_fs.h>
#include <linux/blk-cgroup.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
#include <linux/swapfile.h>
#include <linux/export.h>
#include <linux/sort.h>
#include <linux/completion.h>
#include <linux/suspend.h>
#include <linux/zswap.h>
#include <linux/plist.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
#include <linux/swap_cgroup.h>
#include "internal.h"
#include "swap.h"
static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
unsigned char);
static void free_swap_count_continuations(struct swap_info_struct *);
static void swap_entry_range_free(struct swap_info_struct *si,
struct swap_cluster_info *ci,
swp_entry_t entry, unsigned int nr_pages);
static void swap_range_alloc(struct swap_info_struct *si,
unsigned int nr_entries);
static bool folio_swapcache_freeable(struct folio *folio);
static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
unsigned long offset);
static inline void unlock_cluster(struct swap_cluster_info *ci);
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
atomic_long_t nr_swap_pages;
/*
* Some modules use swappable objects and may try to swap them out under
* memory pressure (via the shrinker). Before doing so, they may wish to
* check to see if any swap space is available.
*/
EXPORT_SYMBOL_GPL(nr_swap_pages);
/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */
long total_swap_pages;
static int least_priority = -1;
unsigned long swapfile_maximum_size;
#ifdef CONFIG_MIGRATION
bool swap_migration_ad_supported;
#endif /* CONFIG_MIGRATION */
static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
/*
* all active swap_info_structs
* protected with swap_lock, and ordered by priority.
*/
static PLIST_HEAD(swap_active_head);
/*
* all available (active, not full) swap_info_structs
* protected with swap_avail_lock, ordered by priority.
* This is used by folio_alloc_swap() instead of swap_active_head
* because swap_active_head includes all swap_info_structs,
* but folio_alloc_swap() doesn't need to look at full ones.
* This uses its own lock instead of swap_lock because when a
* swap_info_struct changes between not-full/full, it needs to
* add/remove itself to/from this list, but the swap_info_struct->lock
* is held and the locking order requires swap_lock to be taken
* before any swap_info_struct->lock.
*/
static struct plist_head *swap_avail_heads;
static DEFINE_SPINLOCK(swap_avail_lock);
static struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
/* Activity counter to indicate that a swapon or swapoff has occurred */
static atomic_t proc_poll_event = ATOMIC_INIT(0);
atomic_t nr_rotate_swap = ATOMIC_INIT(0);
struct percpu_swap_cluster {
struct swap_info_struct *si[SWAP_NR_ORDERS];
unsigned long offset[SWAP_NR_ORDERS];
local_lock_t lock;
};
static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = {
.si = { NULL },
.offset = { SWAP_ENTRY_INVALID },
.lock = INIT_LOCAL_LOCK(),
};
static struct swap_info_struct *swap_type_to_swap_info(int type)
{
if (type >= MAX_SWAPFILES)
return NULL;
return READ_ONCE(swap_info[type]); /* rcu_dereference() */
}
static inline unsigned char swap_count(unsigned char ent)
{
return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */
}
/*
* Use the second highest bit of inuse_pages counter as the indicator
* if one swap device is on the available plist, so the atomic can
* still be updated arithmetically while having special data embedded.
*
* inuse_pages counter is the only thing indicating if a device should
* be on avail_lists or not (except swapon / swapoff). By embedding the
* off-list bit in the atomic counter, updates no longer need any lock
* to check the list status.
*
* This bit will be set if the device is not on the plist and not
* usable, will be cleared if the device is on the plist.
*/
#define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2))
#define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT)
static long swap_usage_in_pages(struct swap_info_struct *si)
{
return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK;
}
/* Reclaim the swap entry anyway if possible */
#define TTRS_ANYWAY 0x1
/*
* Reclaim the swap entry if there are no more mappings of the
* corresponding page
*/
#define TTRS_UNMAPPED 0x2
/* Reclaim the swap entry if swap is getting full */
#define TTRS_FULL 0x4
static bool swap_only_has_cache(struct swap_info_struct *si,
unsigned long offset, int nr_pages)
{
unsigned char *map = si->swap_map + offset;
unsigned char *map_end = map + nr_pages;
do {
VM_BUG_ON(!(*map & SWAP_HAS_CACHE));
if (*map != SWAP_HAS_CACHE)
return false;
} while (++map < map_end);
return true;
}
static bool swap_is_last_map(struct swap_info_struct *si,
unsigned long offset, int nr_pages, bool *has_cache)
{
unsigned char *map = si->swap_map + offset;
unsigned char *map_end = map + nr_pages;
unsigned char count = *map;
if (swap_count(count) != 1)
return false;
while (++map < map_end) {
if (*map != count)
return false;
}
*has_cache = !!(count & SWAP_HAS_CACHE);
return true;
}
/*
* returns number of pages in the folio that backs the swap entry. If positive,
* the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no
* folio was associated with the swap entry.
*/
static int __try_to_reclaim_swap(struct swap_info_struct *si,
unsigned long offset, unsigned long flags)
{
swp_entry_t entry = swp_entry(si->type, offset);
struct address_space *address_space = swap_address_space(entry);
struct swap_cluster_info *ci;
struct folio *folio;
int ret, nr_pages;
bool need_reclaim;
again:
folio = filemap_get_folio(address_space, swap_cache_index(entry));
if (IS_ERR(folio))
return 0;
nr_pages = folio_nr_pages(folio);
ret = -nr_pages;
/*
* When this function is called from scan_swap_map_slots() and it's
* called by vmscan.c at reclaiming folios. So we hold a folio lock
* here. We have to use trylock for avoiding deadlock. This is a special
* case and you should use folio_free_swap() with explicit folio_lock()
* in usual operations.
*/
if (!folio_trylock(folio))
goto out;
/*
* Offset could point to the middle of a large folio, or folio
* may no longer point to the expected offset before it's locked.
*/
entry = folio->swap;
if (offset < swp_offset(entry) || offset >= swp_offset(entry) + nr_pages) {
folio_unlock(folio);
folio_put(folio);
goto again;
}
offset = swp_offset(entry);
need_reclaim = ((flags & TTRS_ANYWAY) ||
((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) ||
((flags & TTRS_FULL) && mem_cgroup_swap_full(folio)));
if (!need_reclaim || !folio_swapcache_freeable(folio))
goto out_unlock;
/*
* It's safe to delete the folio from swap cache only if the folio's
* swap_map is HAS_CACHE only, which means the slots have no page table
* reference or pending writeback, and can't be allocated to others.
*/
ci = lock_cluster(si, offset);
need_reclaim = swap_only_has_cache(si, offset, nr_pages);
unlock_cluster(ci);
if (!need_reclaim)
goto out_unlock;
delete_from_swap_cache(folio);
folio_set_dirty(folio);
ret = nr_pages;
out_unlock:
folio_unlock(folio);
out:
folio_put(folio);
return ret;
}
static inline struct swap_extent *first_se(struct swap_info_struct *sis)
{
struct rb_node *rb = rb_first(&sis->swap_extent_root);
return rb_entry(rb, struct swap_extent, rb_node);
}
static inline struct swap_extent *next_se(struct swap_extent *se)
{
struct rb_node *rb = rb_next(&se->rb_node);
return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL;
}
/*
* swapon tell device that all the old swap contents can be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static int discard_swap(struct swap_info_struct *si)
{
struct swap_extent *se;
sector_t start_block;
sector_t nr_blocks;
int err = 0;
/* Do not discard the swap header page! */
se = first_se(si);
start_block = (se->start_block + 1) << (PAGE_SHIFT - 9);
nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
if (nr_blocks) {
err = blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_KERNEL);
if (err)
return err;
cond_resched();
}
for (se = next_se(se); se; se = next_se(se)) {
start_block = se->start_block << (PAGE_SHIFT - 9);
nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
err = blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_KERNEL);
if (err)
break;
cond_resched();
}
return err; /* That will often be -EOPNOTSUPP */
}
static struct swap_extent *
offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset)
{
struct swap_extent *se;
struct rb_node *rb;
rb = sis->swap_extent_root.rb_node;
while (rb) {
se = rb_entry(rb, struct swap_extent, rb_node);
if (offset < se->start_page)
rb = rb->rb_left;
else if (offset >= se->start_page + se->nr_pages)
rb = rb->rb_right;
else
return se;
}
/* It *must* be present */
BUG();
}
sector_t swap_folio_sector(struct folio *folio)
{
struct swap_info_struct *sis = swp_swap_info(folio->swap);
struct swap_extent *se;
sector_t sector;
pgoff_t offset;
offset = swp_offset(folio->swap);
se = offset_to_swap_extent(sis, offset);
sector = se->start_block + (offset - se->start_page);
return sector << (PAGE_SHIFT - 9);
}
/*
* swap allocation tell device that a cluster of swap can now be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static void discard_swap_cluster(struct swap_info_struct *si,
pgoff_t start_page, pgoff_t nr_pages)
{
struct swap_extent *se = offset_to_swap_extent(si, start_page);
while (nr_pages) {
pgoff_t offset = start_page - se->start_page;
sector_t start_block = se->start_block + offset;
sector_t nr_blocks = se->nr_pages - offset;
if (nr_blocks > nr_pages)
nr_blocks = nr_pages;
start_page += nr_blocks;
nr_pages -= nr_blocks;
start_block <<= PAGE_SHIFT - 9;
nr_blocks <<= PAGE_SHIFT - 9;
if (blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_NOIO))
break;
se = next_se(se);
}
}
#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER HPAGE_PMD_NR
#define swap_entry_order(order) (order)
#else
#define SWAPFILE_CLUSTER 256
/*
* Define swap_entry_order() as constant to let compiler to optimize
* out some code if !CONFIG_THP_SWAP
*/
#define swap_entry_order(order) 0
#endif
#define LATENCY_LIMIT 256
static inline bool cluster_is_empty(struct swap_cluster_info *info)
{
return info->count == 0;
}
static inline bool cluster_is_discard(struct swap_cluster_info *info)
{
return info->flags == CLUSTER_FLAG_DISCARD;
}
static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order)
{
if (unlikely(ci->flags > CLUSTER_FLAG_USABLE))
return false;
if (!order)
return true;
return cluster_is_empty(ci) || order == ci->order;
}
static inline unsigned int cluster_index(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
return ci - si->cluster_info;
}
static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si,
unsigned long offset)
{
return &si->cluster_info[offset / SWAPFILE_CLUSTER];
}
static inline unsigned int cluster_offset(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
return cluster_index(si, ci) * SWAPFILE_CLUSTER;
}
static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
unsigned long offset)
{
struct swap_cluster_info *ci;
ci = offset_to_cluster(si, offset);
spin_lock(&ci->lock);
return ci;
}
static inline void unlock_cluster(struct swap_cluster_info *ci)
{
spin_unlock(&ci->lock);
}
static void move_cluster(struct swap_info_struct *si,
struct swap_cluster_info *ci, struct list_head *list,
enum swap_cluster_flags new_flags)
{
VM_WARN_ON(ci->flags == new_flags);
BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX);
lockdep_assert_held(&ci->lock);
spin_lock(&si->lock);
if (ci->flags == CLUSTER_FLAG_NONE)
list_add_tail(&ci->list, list);
else
list_move_tail(&ci->list, list);
spin_unlock(&si->lock);
if (ci->flags == CLUSTER_FLAG_FRAG)
atomic_long_dec(&si->frag_cluster_nr[ci->order]);
else if (new_flags == CLUSTER_FLAG_FRAG)
atomic_long_inc(&si->frag_cluster_nr[ci->order]);
ci->flags = new_flags;
}
/* Add a cluster to discard list and schedule it to do discard */
static void swap_cluster_schedule_discard(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD);
schedule_work(&si->discard_work);
}
static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
{
lockdep_assert_held(&ci->lock);
move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE);
ci->order = 0;
}
/*
* Isolate and lock the first cluster that is not contented on a list,
* clean its flag before taken off-list. Cluster flag must be in sync
* with list status, so cluster updaters can always know the cluster
* list status without touching si lock.
*
* Note it's possible that all clusters on a list are contented so
* this returns NULL for an non-empty list.
*/
static struct swap_cluster_info *isolate_lock_cluster(
struct swap_info_struct *si, struct list_head *list)
{
struct swap_cluster_info *ci, *ret = NULL;
spin_lock(&si->lock);
if (unlikely(!(si->flags & SWP_WRITEOK)))
goto out;
list_for_each_entry(ci, list, list) {
if (!spin_trylock(&ci->lock))
continue;
/* We may only isolate and clear flags of following lists */
VM_BUG_ON(!ci->flags);
VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE &&
ci->flags != CLUSTER_FLAG_FULL);
list_del(&ci->list);
ci->flags = CLUSTER_FLAG_NONE;
ret = ci;
break;
}
out:
spin_unlock(&si->lock);
return ret;
}
/*
* Doing discard actually. After a cluster discard is finished, the cluster
* will be added to free cluster list. Discard cluster is a bit special as
* they don't participate in allocation or reclaim, so clusters marked as
* CLUSTER_FLAG_DISCARD must remain off-list or on discard list.
*/
static bool swap_do_scheduled_discard(struct swap_info_struct *si)
{
struct swap_cluster_info *ci;
bool ret = false;
unsigned int idx;
spin_lock(&si->lock);
while (!list_empty(&si->discard_clusters)) {
ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
/*
* Delete the cluster from list to prepare for discard, but keep
* the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be
* pointing to it, or ran into by relocate_cluster.
*/
list_del(&ci->list);
idx = cluster_index(si, ci);
spin_unlock(&si->lock);
discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
SWAPFILE_CLUSTER);
spin_lock(&ci->lock);
/*
* Discard is done, clear its flags as it's off-list, then
* return the cluster to allocation list.
*/
ci->flags = CLUSTER_FLAG_NONE;
__free_cluster(si, ci);
spin_unlock(&ci->lock);
ret = true;
spin_lock(&si->lock);
}
spin_unlock(&si->lock);
return ret;
}
static void swap_discard_work(struct work_struct *work)
{
struct swap_info_struct *si;
si = container_of(work, struct swap_info_struct, discard_work);
swap_do_scheduled_discard(si);
}
static void swap_users_ref_free(struct percpu_ref *ref)
{
struct swap_info_struct *si;
si = container_of(ref, struct swap_info_struct, users);
complete(&si->comp);
}
/*
* Must be called after freeing if ci->count == 0, moves the cluster to free
* or discard list.
*/
static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
{
VM_BUG_ON(ci->count != 0);
VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
lockdep_assert_held(&ci->lock);
/*
* If the swap is discardable, prepare discard the cluster
* instead of free it immediately. The cluster will be freed
* after discard.
*/
if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
(SWP_WRITEOK | SWP_PAGE_DISCARD)) {
swap_cluster_schedule_discard(si, ci);
return;
}
__free_cluster(si, ci);
}
/*
* Must be called after freeing if ci->count != 0, moves the cluster to
* nonfull list.
*/
static void partial_free_cluster(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER);
lockdep_assert_held(&ci->lock);
if (ci->flags != CLUSTER_FLAG_NONFULL)
move_cluster(si, ci, &si->nonfull_clusters[ci->order],
CLUSTER_FLAG_NONFULL);
}
/*
* Must be called after allocation, moves the cluster to full or frag list.
* Note: allocation doesn't acquire si lock, and may drop the ci lock for
* reclaim, so the cluster could be any where when called.
*/
static void relocate_cluster(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
lockdep_assert_held(&ci->lock);
/* Discard cluster must remain off-list or on discard list */
if (cluster_is_discard(ci))
return;
if (!ci->count) {
if (ci->flags != CLUSTER_FLAG_FREE)
free_cluster(si, ci);
} else if (ci->count != SWAPFILE_CLUSTER) {
if (ci->flags != CLUSTER_FLAG_FRAG)
move_cluster(si, ci, &si->frag_clusters[ci->order],
CLUSTER_FLAG_FRAG);
} else {
if (ci->flags != CLUSTER_FLAG_FULL)
move_cluster(si, ci, &si->full_clusters,
CLUSTER_FLAG_FULL);
}
}
/*
* The cluster corresponding to page_nr will be used. The cluster will not be
* added to free cluster list and its usage counter will be increased by 1.
* Only used for initialization.
*/
static void inc_cluster_info_page(struct swap_info_struct *si,
struct swap_cluster_info *cluster_info, unsigned long page_nr)
{
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
struct swap_cluster_info *ci;
ci = cluster_info + idx;
ci->count++;
VM_BUG_ON(ci->count > SWAPFILE_CLUSTER);
VM_BUG_ON(ci->flags);
}
static bool cluster_reclaim_range(struct swap_info_struct *si,
struct swap_cluster_info *ci,
unsigned long start, unsigned long end)
{
unsigned char *map = si->swap_map;
unsigned long offset = start;
int nr_reclaim;
spin_unlock(&ci->lock);
do {
switch (READ_ONCE(map[offset])) {
case 0:
offset++;
break;
case SWAP_HAS_CACHE:
nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
if (nr_reclaim > 0)
offset += nr_reclaim;
else
goto out;
break;
default:
goto out;
}
} while (offset < end);
out:
spin_lock(&ci->lock);
/*
* Recheck the range no matter reclaim succeeded or not, the slot
* could have been be freed while we are not holding the lock.
*/
for (offset = start; offset < end; offset++)
if (READ_ONCE(map[offset]))
return false;
return true;
}
static bool cluster_scan_range(struct swap_info_struct *si,
struct swap_cluster_info *ci,
unsigned long start, unsigned int nr_pages,
bool *need_reclaim)
{
unsigned long offset, end = start + nr_pages;
unsigned char *map = si->swap_map;
if (cluster_is_empty(ci))
return true;
for (offset = start; offset < end; offset++) {
switch (READ_ONCE(map[offset])) {
case 0:
continue;
case SWAP_HAS_CACHE:
if (!vm_swap_full())
return false;
*need_reclaim = true;
continue;
default:
return false;
}
}
return true;
}
static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci,
unsigned int start, unsigned char usage,
unsigned int order)
{
unsigned int nr_pages = 1 << order;
lockdep_assert_held(&ci->lock);
if (!(si->flags & SWP_WRITEOK))
return false;
/*
* The first allocation in a cluster makes the
* cluster exclusive to this order
*/
if (cluster_is_empty(ci))
ci->order = order;
memset(si->swap_map + start, usage, nr_pages);
swap_range_alloc(si, nr_pages);
ci->count += nr_pages;
return true;
}
/* Try use a new cluster for current CPU and allocate from it. */
static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
struct swap_cluster_info *ci,
unsigned long offset,
unsigned int order,
unsigned char usage)
{
unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER);
unsigned long end = min(start + SWAPFILE_CLUSTER, si->max);
unsigned int nr_pages = 1 << order;
bool need_reclaim, ret;
lockdep_assert_held(&ci->lock);
if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER)
goto out;
for (end -= nr_pages; offset <= end; offset += nr_pages) {
need_reclaim = false;
if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim))
continue;
if (need_reclaim) {
ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages);
/*
* Reclaim drops ci->lock and cluster could be used
* by another order. Not checking flag as off-list
* cluster has no flag set, and change of list
* won't cause fragmentation.
*/
if (!cluster_is_usable(ci, order))
goto out;
if (cluster_is_empty(ci))
offset = start;
/* Reclaim failed but cluster is usable, try next */
if (!ret)
continue;
}
if (!cluster_alloc_range(si, ci, offset, usage, order))
break;
found = offset;
offset += nr_pages;
if (ci->count < SWAPFILE_CLUSTER && offset <= end)
next = offset;
break;
}
out:
relocate_cluster(si, ci);
unlock_cluster(ci);
if (si->flags & SWP_SOLIDSTATE) {
this_cpu_write(percpu_swap_cluster.offset[order], next);
this_cpu_write(percpu_swap_cluster.si[order], si);
} else {
si->global_cluster->next[order] = next;
}
return found;
}
static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
{
long to_scan = 1;
unsigned long offset, end;
struct swap_cluster_info *ci;
unsigned char *map = si->swap_map;
int nr_reclaim;
if (force)
to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER;
while ((ci = isolate_lock_cluster(si, &si->full_clusters))) {
offset = cluster_offset(si, ci);
end = min(si->max, offset + SWAPFILE_CLUSTER);
to_scan--;
while (offset < end) {
if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
spin_unlock(&ci->lock);
nr_reclaim = __try_to_reclaim_swap(si, offset,
TTRS_ANYWAY);
spin_lock(&ci->lock);
if (nr_reclaim) {
offset += abs(nr_reclaim);
continue;
}
}
offset++;
}
/* in case no swap cache is reclaimed */
if (ci->flags == CLUSTER_FLAG_NONE)
relocate_cluster(si, ci);
unlock_cluster(ci);
if (to_scan <= 0)
break;
}
}
static void swap_reclaim_work(struct work_struct *work)
{
struct swap_info_struct *si;
si = container_of(work, struct swap_info_struct, reclaim_work);
swap_reclaim_full_clusters(si, true);
}
/*
* Try to allocate swap entries with specified order and try set a new
* cluster for current CPU too.
*/
static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order,
unsigned char usage)
{
struct swap_cluster_info *ci;
unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
/*
* Swapfile is not block device so unable
* to allocate large entries.
*/
if (order && !(si->flags & SWP_BLKDEV))
return 0;
if (!(si->flags & SWP_SOLIDSTATE)) {
/* Serialize HDD SWAP allocation for each device. */
spin_lock(&si->global_cluster_lock);
offset = si->global_cluster->next[order];
if (offset == SWAP_ENTRY_INVALID)
goto new_cluster;
ci = lock_cluster(si, offset);
/* Cluster could have been used by another order */
if (cluster_is_usable(ci, order)) {
if (cluster_is_empty(ci))
offset = cluster_offset(si, ci);
found = alloc_swap_scan_cluster(si, ci, offset,
order, usage);
} else {
unlock_cluster(ci);
}
if (found)
goto done;
}
new_cluster:
ci = isolate_lock_cluster(si, &si->free_clusters);
if (ci) {
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
order, usage);
if (found)
goto done;
}
/* Try reclaim from full clusters if free clusters list is drained */
if (vm_swap_full())
swap_reclaim_full_clusters(si, false);
if (order < PMD_ORDER) {
unsigned int frags = 0, frags_existing;
while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) {
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
order, usage);
if (found)
goto done;
/* Clusters failed to allocate are moved to frag_clusters */
frags++;
}
frags_existing = atomic_long_read(&si->frag_cluster_nr[order]);
while (frags < frags_existing &&
(ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) {
atomic_long_dec(&si->frag_cluster_nr[order]);
/*
* Rotate the frag list to iterate, they were all
* failing high order allocation or moved here due to
* per-CPU usage, but they could contain newly released
* reclaimable (eg. lazy-freed swap cache) slots.
*/
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
order, usage);
if (found)
goto done;
frags++;
}
}
/*
* We don't have free cluster but have some clusters in
* discarding, do discard now and reclaim them, then
* reread cluster_next_cpu since we dropped si->lock
*/
if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si))
goto new_cluster;
if (order)
goto done;
/* Order 0 stealing from higher order */
for (int o = 1; o < SWAP_NR_ORDERS; o++) {
/*
* Clusters here have at least one usable slots and can't fail order 0
* allocation, but reclaim may drop si->lock and race with another user.
*/
while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
atomic_long_dec(&si->frag_cluster_nr[o]);
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
0, usage);
if (found)
goto done;
}
while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) {
found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
0, usage);
if (found)
goto done;
}
}
done:
if (!(si->flags & SWP_SOLIDSTATE))
spin_unlock(&si->global_cluster_lock);
return found;
}
/* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */
static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
{
int nid;
unsigned long pages;
spin_lock(&swap_avail_lock);
if (swapoff) {
/*
* Forcefully remove it. Clear the SWP_WRITEOK flags for
* swapoff here so it's synchronized by both si->lock and
* swap_avail_lock, to ensure the result can be seen by
* add_to_avail_list.
*/
lockdep_assert_held(&si->lock);
si->flags &= ~SWP_WRITEOK;
atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
} else {
/*
* If not called by swapoff, take it off-list only if it's
* full and SWAP_USAGE_OFFLIST_BIT is not set (strictly
* si->inuse_pages == pages), any concurrent slot freeing,
* or device already removed from plist by someone else
* will make this return false.
*/
pages = si->pages;
if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
pages | SWAP_USAGE_OFFLIST_BIT))
goto skip;
}
for_each_node(nid)
plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]);
skip:
spin_unlock(&swap_avail_lock);
}
/* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */
static void add_to_avail_list(struct swap_info_struct *si, bool swapon)
{
int nid;
long val;
unsigned long pages;
spin_lock(&swap_avail_lock);
/* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */
if (swapon) {
lockdep_assert_held(&si->lock);
si->flags |= SWP_WRITEOK;
} else {
if (!(READ_ONCE(si->flags) & SWP_WRITEOK))
goto skip;
}
if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT))
goto skip;
val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
/*
* When device is full and device is on the plist, only one updater will
* see (inuse_pages == si->pages) and will call del_from_avail_list. If
* that updater happen to be here, just skip adding.
*/
pages = si->pages;
if (val == pages) {
/* Just like the cmpxchg in del_from_avail_list */
if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
pages | SWAP_USAGE_OFFLIST_BIT))
goto skip;
}
for_each_node(nid)
plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]);
skip:
spin_unlock(&swap_avail_lock);
}
/*
* swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock
* within each cluster, so the total contribution to the global counter should
* always be positive and cannot exceed the total number of usable slots.
*/
static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries)
{
long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages);
/*
* If device is full, and SWAP_USAGE_OFFLIST_BIT is not set,
* remove it from the plist.
*/
if (unlikely(val == si->pages)) {
del_from_avail_list(si, false);
return true;
}
return false;
}
static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries)
{
long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages);
/*
* If device is not full, and SWAP_USAGE_OFFLIST_BIT is set,
* add it to the plist.
*/
if (unlikely(val & SWAP_USAGE_OFFLIST_BIT))
add_to_avail_list(si, false);
}
static void swap_range_alloc(struct swap_info_struct *si,
unsigned int nr_entries)
{
if (swap_usage_add(si, nr_entries)) {
if (vm_swap_full())
schedule_work(&si->reclaim_work);
}
}
static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
unsigned int nr_entries)
{
unsigned long begin = offset;
unsigned long end = offset + nr_entries - 1;
void (*swap_slot_free_notify)(struct block_device *, unsigned long);
unsigned int i;
/*
* Use atomic clear_bit operations only on zeromap instead of non-atomic
* bitmap_clear to prevent adjacent bits corruption due to simultaneous writes.
*/
for (i = 0; i < nr_entries; i++) {
clear_bit(offset + i, si->zeromap);
zswap_invalidate(swp_entry(si->type, offset + i));
}
if (si->flags & SWP_BLKDEV)
swap_slot_free_notify =
si->bdev->bd_disk->fops->swap_slot_free_notify;
else
swap_slot_free_notify = NULL;
while (offset <= end) {
arch_swap_invalidate_page(si->type, offset);
if (swap_slot_free_notify)
swap_slot_free_notify(si->bdev, offset);
offset++;
}
clear_shadow_from_swap_cache(si->type, begin, end);
/*
* Make sure that try_to_unuse() observes si->inuse_pages reaching 0
* only after the above cleanups are done.
*/
smp_wmb();
atomic_long_add(nr_entries, &nr_swap_pages);
swap_usage_sub(si, nr_entries);
}
static bool get_swap_device_info(struct swap_info_struct *si)
{
if (!percpu_ref_tryget_live(&si->users))
return false;
/*
* Guarantee the si->users are checked before accessing other
* fields of swap_info_struct, and si->flags (SWP_WRITEOK) is
* up to dated.
*
* Paired with the spin_unlock() after setup_swap_info() in
* enable_swap_info(), and smp_wmb() in swapoff.
*/
smp_rmb();
return true;
}
/*
* Fast path try to get swap entries with specified order from current
* CPU's swap entry pool (a cluster).
*/
static bool swap_alloc_fast(swp_entry_t *entry,
int order)
{
struct swap_cluster_info *ci;
struct swap_info_struct *si;
unsigned int offset, found = SWAP_ENTRY_INVALID;
/*
* Once allocated, swap_info_struct will never be completely freed,
* so checking it's liveness by get_swap_device_info is enough.
*/
si = this_cpu_read(percpu_swap_cluster.si[order]);
offset = this_cpu_read(percpu_swap_cluster.offset[order]);
if (!si || !offset || !get_swap_device_info(si))
return false;
ci = lock_cluster(si, offset);
if (cluster_is_usable(ci, order)) {
if (cluster_is_empty(ci))
offset = cluster_offset(si, ci);
found = alloc_swap_scan_cluster(si, ci, offset, order, SWAP_HAS_CACHE);
if (found)
*entry = swp_entry(si->type, found);
} else {
unlock_cluster(ci);
}
put_swap_device(si);
return !!found;
}
/* Rotate the device and switch to a new cluster */
static bool swap_alloc_slow(swp_entry_t *entry,
int order)
{
int node;
unsigned long offset;
struct swap_info_struct *si, *next;
node = numa_node_id();
spin_lock(&swap_avail_lock);
start_over:
plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
/* Rotate the device and switch to a new cluster */
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
if (get_swap_device_info(si)) {
offset = cluster_alloc_swap_entry(si, order, SWAP_HAS_CACHE);
put_swap_device(si);
if (offset) {
*entry = swp_entry(si->type, offset);
return true;
}
if (order)
return false;
}
spin_lock(&swap_avail_lock);
/*
* if we got here, it's likely that si was almost full before,
* and since scan_swap_map_slots() can drop the si->lock,
* multiple callers probably all tried to get a page from the
* same si and it filled up before we could get one; or, the si
* filled up between us dropping swap_avail_lock and taking
* si->lock. Since we dropped the swap_avail_lock, the
* swap_avail_head list may have been modified; so if next is
* still in the swap_avail_head list then try it, otherwise
* start over if we have not gotten any slots.
*/
if (plist_node_empty(&next->avail_lists[node]))
goto start_over;
}
spin_unlock(&swap_avail_lock);
return false;
}
/**
* folio_alloc_swap - allocate swap space for a folio
* @folio: folio we want to move to swap
* @gfp: gfp mask for shadow nodes
*
* Allocate swap space for the folio and add the folio to the
* swap cache.
*
* Context: Caller needs to hold the folio lock.
* Return: Whether the folio was added to the swap cache.
*/
int folio_alloc_swap(struct folio *folio, gfp_t gfp)
{
unsigned int order = folio_order(folio);
unsigned int size = 1 << order;
swp_entry_t entry = {};
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
/*
* Should not even be attempting large allocations when huge
* page swap is disabled. Warn and fail the allocation.
*/
if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
VM_WARN_ON_ONCE(1);
return -EINVAL;
}
local_lock(&percpu_swap_cluster.lock);
if (!swap_alloc_fast(&entry, order))
swap_alloc_slow(&entry, order);
local_unlock(&percpu_swap_cluster.lock);
/* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */
if (mem_cgroup_try_charge_swap(folio, entry))
goto out_free;
if (!entry.val)
return -ENOMEM;
/*
* XArray node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
if (add_to_swap_cache(folio, entry, gfp | __GFP_NOMEMALLOC, NULL))
goto out_free;
atomic_long_sub(size, &nr_swap_pages);
return 0;
out_free:
put_swap_folio(folio, entry);
return -ENOMEM;
}
static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
{
struct swap_info_struct *si;
unsigned long offset;
if (!entry.val)
goto out;
si = swp_swap_info(entry);
if (!si)
goto bad_nofile;
if (data_race(!(si->flags & SWP_USED)))
goto bad_device;
offset = swp_offset(entry);
if (offset >= si->max)
goto bad_offset;
if (data_race(!si->swap_map[swp_offset(entry)]))
goto bad_free;
return si;
bad_free:
pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val);
goto out;
bad_offset:
pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val);
goto out;
bad_device:
pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val);
goto out;
bad_nofile:
pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
out:
return NULL;
}
static unsigned char __swap_entry_free_locked(struct swap_info_struct *si,
unsigned long offset,
unsigned char usage)
{
unsigned char count;
unsigned char has_cache;
count = si->swap_map[offset];
has_cache = count & SWAP_HAS_CACHE;
count &= ~SWAP_HAS_CACHE;
if (usage == SWAP_HAS_CACHE) {
VM_BUG_ON(!has_cache);
has_cache = 0;
} else if (count == SWAP_MAP_SHMEM) {
/*
* Or we could insist on shmem.c using a special
* swap_shmem_free() and free_shmem_swap_and_cache()...
*/
count = 0;
} else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) {
if (count == COUNT_CONTINUED) {
if (swap_count_continued(si, offset, count))
count = SWAP_MAP_MAX | COUNT_CONTINUED;
else
count = SWAP_MAP_MAX;
} else
count--;
}
usage = count | has_cache;
if (usage)
WRITE_ONCE(si->swap_map[offset], usage);
else
WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE);
return usage;
}
/*
* When we get a swap entry, if there aren't some other ways to
* prevent swapoff, such as the folio in swap cache is locked, RCU
* reader side is locked, etc., the swap entry may become invalid
* because of swapoff. Then, we need to enclose all swap related
* functions with get_swap_device() and put_swap_device(), unless the
* swap functions call get/put_swap_device() by themselves.
*
* RCU reader side lock (including any spinlock) is sufficient to
* prevent swapoff, because synchronize_rcu() is called in swapoff()
* before freeing data structures.
*
* Check whether swap entry is valid in the swap device. If so,
* return pointer to swap_info_struct, and keep the swap entry valid
* via preventing the swap device from being swapoff, until
* put_swap_device() is called. Otherwise return NULL.
*
* Notice that swapoff or swapoff+swapon can still happen before the
* percpu_ref_tryget_live() in get_swap_device() or after the
* percpu_ref_put() in put_swap_device() if there isn't any other way
* to prevent swapoff. The caller must be prepared for that. For
* example, the following situation is possible.
*
* CPU1 CPU2
* do_swap_page()
* ... swapoff+swapon
* __read_swap_cache_async()
* swapcache_prepare()
* __swap_duplicate()
* // check swap_map
* // verify PTE not changed
*
* In __swap_duplicate(), the swap_map need to be checked before
* changing partly because the specified swap entry may be for another
* swap device which has been swapoff. And in do_swap_page(), after
* the page is read from the swap device, the PTE is verified not
* changed with the page table locked to check whether the swap device
* has been swapoff or swapoff+swapon.
*/
struct swap_info_struct *get_swap_device(swp_entry_t entry)
{
struct swap_info_struct *si;
unsigned long offset;
if (!entry.val)
goto out;
si = swp_swap_info(entry);
if (!si)
goto bad_nofile;
if (!get_swap_device_info(si))
goto out;
offset = swp_offset(entry);
if (offset >= si->max)
goto put_out;
return si;
bad_nofile:
pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
out:
return NULL;
put_out:
pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val);
percpu_ref_put(&si->users);
return NULL;
}
static unsigned char __swap_entry_free(struct swap_info_struct *si,
swp_entry_t entry)
{
struct swap_cluster_info *ci;
unsigned long offset = swp_offset(entry);
unsigned char usage;
ci = lock_cluster(si, offset);
usage = __swap_entry_free_locked(si, offset, 1);
if (!usage)
swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
unlock_cluster(ci);
return usage;
}
static bool __swap_entries_free(struct swap_info_struct *si,
swp_entry_t entry, int nr)
{
unsigned long offset = swp_offset(entry);
unsigned int type = swp_type(entry);
struct swap_cluster_info *ci;
bool has_cache = false;
unsigned char count;
int i;
if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1)
goto fallback;
/* cross into another cluster */
if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER)
goto fallback;
ci = lock_cluster(si, offset);
if (!swap_is_last_map(si, offset, nr, &has_cache)) {
unlock_cluster(ci);
goto fallback;
}
for (i = 0; i < nr; i++)
WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
if (!has_cache)
swap_entry_range_free(si, ci, entry, nr);
unlock_cluster(ci);
return has_cache;
fallback:
for (i = 0; i < nr; i++) {
if (data_race(si->swap_map[offset + i])) {
count = __swap_entry_free(si, swp_entry(type, offset + i));
if (count == SWAP_HAS_CACHE)
has_cache = true;
} else {
WARN_ON_ONCE(1);
}
}
return has_cache;
}
/*
* Drop the last HAS_CACHE flag of swap entries, caller have to
* ensure all entries belong to the same cgroup.
*/
static void swap_entry_range_free(struct swap_info_struct *si,
struct swap_cluster_info *ci,
swp_entry_t entry, unsigned int nr_pages)
{
unsigned long offset = swp_offset(entry);
unsigned char *map = si->swap_map + offset;
unsigned char *map_end = map + nr_pages;
/* It should never free entries across different clusters */
VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1));
VM_BUG_ON(cluster_is_empty(ci));
VM_BUG_ON(ci->count < nr_pages);
ci->count -= nr_pages;
do {
VM_BUG_ON(*map != SWAP_HAS_CACHE);
*map = 0;
} while (++map < map_end);
mem_cgroup_uncharge_swap(entry, nr_pages);
swap_range_free(si, offset, nr_pages);
if (!ci->count)
free_cluster(si, ci);
else
partial_free_cluster(si, ci);
}
static void cluster_swap_free_nr(struct swap_info_struct *si,
unsigned long offset, int nr_pages,
unsigned char usage)
{
struct swap_cluster_info *ci;
unsigned long end = offset + nr_pages;
ci = lock_cluster(si, offset);
do {
if (!__swap_entry_free_locked(si, offset, usage))
swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
} while (++offset < end);
unlock_cluster(ci);
}
/*
* Caller has made sure that the swap device corresponding to entry
* is still around or has not been recycled.
*/
void swap_free_nr(swp_entry_t entry, int nr_pages)
{
int nr;
struct swap_info_struct *sis;
unsigned long offset = swp_offset(entry);
sis = _swap_info_get(entry);
if (!sis)
return;
while (nr_pages) {
nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
cluster_swap_free_nr(sis, offset, nr, 1);
offset += nr;
nr_pages -= nr;
}
}
/*
* Called after dropping swapcache to decrease refcnt to swap entries.
*/
void put_swap_folio(struct folio *folio, swp_entry_t entry)
{
unsigned long offset = swp_offset(entry);
struct swap_cluster_info *ci;
struct swap_info_struct *si;
int size = 1 << swap_entry_order(folio_order(folio));
si = _swap_info_get(entry);
if (!si)
return;
ci = lock_cluster(si, offset);
if (swap_only_has_cache(si, offset, size))
swap_entry_range_free(si, ci, entry, size);
else {
for (int i = 0; i < size; i++, entry.val++) {
if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE))
swap_entry_range_free(si, ci, entry, 1);
}
}
unlock_cluster(ci);
}
int __swap_count(swp_entry_t entry)
{
struct swap_info_struct *si = swp_swap_info(entry);
pgoff_t offset = swp_offset(entry);
return swap_count(si->swap_map[offset]);
}
/*
* How many references to @entry are currently swapped out?
* This does not give an exact answer when swap count is continued,
* but does include the high COUNT_CONTINUED flag to allow for that.
*/
bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry)
{
pgoff_t offset = swp_offset(entry);
struct swap_cluster_info *ci;
int count;
ci = lock_cluster(si, offset);
count = swap_count(si->swap_map[offset]);
unlock_cluster(ci);
return !!count;
}
/*
* How many references to @entry are currently swapped out?
* This considers COUNT_CONTINUED so it returns exact answer.
*/
int swp_swapcount(swp_entry_t entry)
{
int count, tmp_count, n;
struct swap_info_struct *si;
struct swap_cluster_info *ci;
struct page *page;
pgoff_t offset;
unsigned char *map;
si = _swap_info_get(entry);
if (!si)
return 0;
offset = swp_offset(entry);
ci = lock_cluster(si, offset);
count = swap_count(si->swap_map[offset]);
if (!(count & COUNT_CONTINUED))
goto out;
count &= ~COUNT_CONTINUED;
n = SWAP_MAP_MAX + 1;
page = vmalloc_to_page(si->swap_map + offset);
offset &= ~PAGE_MASK;
VM_BUG_ON(page_private(page) != SWP_CONTINUED);
do {
page = list_next_entry(page, lru);
map = kmap_local_page(page);
tmp_count = map[offset];
kunmap_local(map);
count += (tmp_count & ~COUNT_CONTINUED) * n;
n *= (SWAP_CONT_MAX + 1);
} while (tmp_count & COUNT_CONTINUED);
out:
unlock_cluster(ci);
return count;
}
static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
swp_entry_t entry, int order)
{
struct swap_cluster_info *ci;
unsigned char *map = si->swap_map;
unsigned int nr_pages = 1 << order;
unsigned long roffset = swp_offset(entry);
unsigned long offset = round_down(roffset, nr_pages);
int i;
bool ret = false;
ci = lock_cluster(si, offset);
if (nr_pages == 1) {
if (swap_count(map[roffset]))
ret = true;
goto unlock_out;
}
for (i = 0; i < nr_pages; i++) {
if (swap_count(map[offset + i])) {
ret = true;
break;
}
}
unlock_out:
unlock_cluster(ci);
return ret;
}
static bool folio_swapped(struct folio *folio)
{
swp_entry_t entry = folio->swap;
struct swap_info_struct *si = _swap_info_get(entry);
if (!si)
return false;
if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio)))
return swap_entry_swapped(si, entry);
return swap_page_trans_huge_swapped(si, entry, folio_order(folio));
}
static bool folio_swapcache_freeable(struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (!folio_test_swapcache(folio))
return false;
if (folio_test_writeback(folio))
return false;
/*
* Once hibernation has begun to create its image of memory,
* there's a danger that one of the calls to folio_free_swap()
* - most probably a call from __try_to_reclaim_swap() while
* hibernation is allocating its own swap pages for the image,
* but conceivably even a call from memory reclaim - will free
* the swap from a folio which has already been recorded in the
* image as a clean swapcache folio, and then reuse its swap for
* another page of the image. On waking from hibernation, the
* original folio might be freed under memory pressure, then
* later read back in from swap, now with the wrong data.
*
* Hibernation suspends storage while it is writing the image
* to disk so check that here.
*/
if (pm_suspended_storage())
return false;
return true;
}
/**
* folio_free_swap() - Free the swap space used for this folio.
* @folio: The folio to remove.
*
* If swap is getting full, or if there are no more mappings of this folio,
* then call folio_free_swap to free its swap space.
*
* Return: true if we were able to release the swap space.
*/
bool folio_free_swap(struct folio *folio)
{
if (!folio_swapcache_freeable(folio))
return false;
if (folio_swapped(folio))
return false;
delete_from_swap_cache(folio);
folio_set_dirty(folio);
return true;
}
/**
* free_swap_and_cache_nr() - Release reference on range of swap entries and
* reclaim their cache if no more references remain.
* @entry: First entry of range.
* @nr: Number of entries in range.
*
* For each swap entry in the contiguous range, release a reference. If any swap
* entries become free, try to reclaim their underlying folios, if present. The
* offset range is defined by [entry.offset, entry.offset + nr).
*/
void free_swap_and_cache_nr(swp_entry_t entry, int nr)
{
const unsigned long start_offset = swp_offset(entry);
const unsigned long end_offset = start_offset + nr;
struct swap_info_struct *si;
bool any_only_cache = false;
unsigned long offset;
si = get_swap_device(entry);
if (!si)
return;
if (WARN_ON(end_offset > si->max))
goto out;
/*
* First free all entries in the range.
*/
any_only_cache = __swap_entries_free(si, entry, nr);
/*
* Short-circuit the below loop if none of the entries had their
* reference drop to zero.
*/
if (!any_only_cache)
goto out;
/*
* Now go back over the range trying to reclaim the swap cache. This is
* more efficient for large folios because we will only try to reclaim
* the swap once per folio in the common case. If we do
* __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the
* latter will get a reference and lock the folio for every individual
* page but will only succeed once the swap slot for every subpage is
* zero.
*/
for (offset = start_offset; offset < end_offset; offset += nr) {
nr = 1;
if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
/*
* Folios are always naturally aligned in swap so
* advance forward to the next boundary. Zero means no
* folio was found for the swap entry, so advance by 1
* in this case. Negative value means folio was found
* but could not be reclaimed. Here we can still advance
* to the next boundary.
*/
nr = __try_to_reclaim_swap(si, offset,
TTRS_UNMAPPED | TTRS_FULL);
if (nr == 0)
nr = 1;
else if (nr < 0)
nr = -nr;
nr = ALIGN(offset + 1, nr) - offset;
}
}
out:
put_swap_device(si);
}
#ifdef CONFIG_HIBERNATION
swp_entry_t get_swap_page_of_type(int type)
{
struct swap_info_struct *si = swap_type_to_swap_info(type);
unsigned long offset;
swp_entry_t entry = {0};
if (!si)
goto fail;
/* This is called for allocating swap entry, not cache */
if (get_swap_device_info(si)) {
if (si->flags & SWP_WRITEOK) {
offset = cluster_alloc_swap_entry(si, 0, 1);
if (offset) {
entry = swp_entry(si->type, offset);
atomic_long_dec(&nr_swap_pages);
}
}
put_swap_device(si);
}
fail:
return entry;
}
/*
* Find the swap type that corresponds to given device (if any).
*
* @offset - number of the PAGE_SIZE-sized block of the device, starting
* from 0, in which the swap header is expected to be located.
*
* This is needed for the suspend to disk (aka swsusp).
*/
int swap_type_of(dev_t device, sector_t offset)
{
int type;
if (!device)
return -1;
spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
struct swap_info_struct *sis = swap_info[type];
if (!(sis->flags & SWP_WRITEOK))
continue;
if (device == sis->bdev->bd_dev) {
struct swap_extent *se = first_se(sis);
if (se->start_block == offset) {
spin_unlock(&swap_lock);
return type;
}
}
}
spin_unlock(&swap_lock);
return -ENODEV;
}
int find_first_swap(dev_t *device)
{
int type;
spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
struct swap_info_struct *sis = swap_info[type];
if (!(sis->flags & SWP_WRITEOK))
continue;
*device = sis->bdev->bd_dev;
spin_unlock(&swap_lock);
return type;
}
spin_unlock(&swap_lock);
return -ENODEV;
}
/*
* Get the (PAGE_SIZE) block corresponding to given offset on the swapdev
* corresponding to given index in swap_info (swap type).
*/
sector_t swapdev_block(int type, pgoff_t offset)
{
struct swap_info_struct *si = swap_type_to_swap_info(type);
struct swap_extent *se;
if (!si || !(si->flags & SWP_WRITEOK))
return 0;
se = offset_to_swap_extent(si, offset);
return se->start_block + (offset - se->start_page);
}
/*
* Return either the total number of swap pages of given type, or the number
* of free pages of that type (depending on @free)
*
* This is needed for software suspend
*/
unsigned int count_swap_pages(int type, int free)
{
unsigned int n = 0;
spin_lock(&swap_lock);
if ((unsigned int)type < nr_swapfiles) {
struct swap_info_struct *sis = swap_info[type];
spin_lock(&sis->lock);
if (sis->flags & SWP_WRITEOK) {
n = sis->pages;
if (free)
n -= swap_usage_in_pages(sis);
}
spin_unlock(&sis->lock);
}
spin_unlock(&swap_lock);
return n;
}
#endif /* CONFIG_HIBERNATION */
static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
{
return pte_same(pte_swp_clear_flags(pte), swp_pte);
}
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
* force COW, vm_page_prot omits write permission from any private vma.
*/
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct folio *folio)
{
struct page *page;
struct folio *swapcache;
spinlock_t *ptl;
pte_t *pte, new_pte, old_pte;
bool hwpoisoned = false;
int ret = 1;
swapcache = folio;
folio = ksm_might_need_to_copy(folio, vma, addr);
if (unlikely(!folio))
return -ENOMEM;
else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
hwpoisoned = true;
folio = swapcache;
}
page = folio_file_page(folio, swp_offset(entry));
if (PageHWPoison(page))
hwpoisoned = true;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
swp_entry_to_pte(entry)))) {
ret = 0;
goto out;
}
old_pte = ptep_get(pte);
if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) {
swp_entry_t swp_entry;
dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
if (hwpoisoned) {
swp_entry = make_hwpoison_entry(page);
} else {
swp_entry = make_poisoned_swp_entry();
}
new_pte = swp_entry_to_pte(swp_entry);
ret = 0;
goto setpte;
}
/*
* Some architectures may have to restore extra metadata to the page
* when reading from swap. This metadata may be indexed by swap entry
* so this must be called before swap_free().
*/
arch_swap_restore(folio_swap(entry, folio), folio);
dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
folio_get(folio);
if (folio == swapcache) {
rmap_t rmap_flags = RMAP_NONE;
/*
* See do_swap_page(): writeback would be problematic.
* However, we do a folio_wait_writeback() just before this
* call and have the folio locked.
*/
VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
if (pte_swp_exclusive(old_pte))
rmap_flags |= RMAP_EXCLUSIVE;
/*
* We currently only expect small !anon folios, which are either
* fully exclusive or fully shared. If we ever get large folios
* here, we have to be careful.
*/
if (!folio_test_anon(folio)) {
VM_WARN_ON_ONCE(folio_test_large(folio));
VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
folio_add_new_anon_rmap(folio, vma, addr, rmap_flags);
} else {
folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags);
}
} else { /* ksm created a completely new copy */
folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
}
new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot));
if (pte_swp_soft_dirty(old_pte))
new_pte = pte_mksoft_dirty(new_pte);
if (pte_swp_uffd_wp(old_pte))
new_pte = pte_mkuffd_wp(new_pte);
setpte:
set_pte_at(vma->vm_mm, addr, pte, new_pte);
swap_free(entry);
out:
if (pte)
pte_unmap_unlock(pte, ptl);
if (folio != swapcache) {
folio_unlock(folio);
folio_put(folio);
}
return ret;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned int type)
{
pte_t *pte = NULL;
struct swap_info_struct *si;
si = swap_info[type];
do {
struct folio *folio;
unsigned long offset;
unsigned char swp_count;
swp_entry_t entry;
int ret;
pte_t ptent;
if (!pte++) {
pte = pte_offset_map(pmd, addr);
if (!pte)
break;
}
ptent = ptep_get_lockless(pte);
if (!is_swap_pte(ptent))
continue;
entry = pte_to_swp_entry(ptent);
if (swp_type(entry) != type)
continue;
offset = swp_offset(entry);
pte_unmap(pte);
pte = NULL;
folio = swap_cache_get_folio(entry, vma, addr);
if (!folio) {
struct vm_fault vmf = {
.vma = vma,
.address = addr,
.real_address = addr,
.pmd = pmd,
};
folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
&vmf);
}
if (!folio) {
swp_count = READ_ONCE(si->swap_map[offset]);
if (swp_count == 0 || swp_count == SWAP_MAP_BAD)
continue;
return -ENOMEM;
}
folio_lock(folio);
folio_wait_writeback(folio);
ret = unuse_pte(vma, pmd, addr, entry, folio);
if (ret < 0) {
folio_unlock(folio);
folio_put(folio);
return ret;
}
folio_free_swap(folio);
folio_unlock(folio);
folio_put(folio);
} while (addr += PAGE_SIZE, addr != end);
if (pte)
pte_unmap(pte);
return 0;
}
static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned int type)
{
pmd_t *pmd;
unsigned long next;
int ret;
pmd = pmd_offset(pud, addr);
do {
cond_resched();
next = pmd_addr_end(addr, end);
ret = unuse_pte_range(vma, pmd, addr, next, type);
if (ret)
return ret;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned int type)
{
pud_t *pud;
unsigned long next;
int ret;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
ret = unuse_pmd_range(vma, pud, addr, next, type);
if (ret)
return ret;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned int type)
{
p4d_t *p4d;
unsigned long next;
int ret;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d))
continue;
ret = unuse_pud_range(vma, p4d, addr, next, type);
if (ret)
return ret;
} while (p4d++, addr = next, addr != end);
return 0;
}
static int unuse_vma(struct vm_area_struct *vma, unsigned int type)
{
pgd_t *pgd;
unsigned long addr, end, next;
int ret;
addr = vma->vm_start;
end = vma->vm_end;
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
ret = unuse_p4d_range(vma, pgd, addr, next, type);
if (ret)
return ret;
} while (pgd++, addr = next, addr != end);
return 0;
}
static int unuse_mm(struct mm_struct *mm, unsigned int type)
{
struct vm_area_struct *vma;
int ret = 0;
VMA_ITERATOR(vmi, mm, 0);
mmap_read_lock(mm);
for_each_vma(vmi, vma) {
if (vma->anon_vma && !is_vm_hugetlb_page(vma)) {
ret = unuse_vma(vma, type);
if (ret)
break;
}
cond_resched();
}
mmap_read_unlock(mm);
return ret;
}
/*
* Scan swap_map from current position to next entry still in use.
* Return 0 if there are no inuse entries after prev till end of
* the map.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
unsigned int prev)
{
unsigned int i;
unsigned char count;
/*
* No need for swap_lock here: we're just looking
* for whether an entry is in use, not modifying it; false
* hits are okay, and sys_swapoff() has already prevented new
* allocations from this area (while holding swap_lock).
*/
for (i = prev + 1; i < si->max; i++) {
count = READ_ONCE(si->swap_map[i]);
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
if ((i % LATENCY_LIMIT) == 0)
cond_resched();
}
if (i == si->max)
i = 0;
return i;
}
static int try_to_unuse(unsigned int type)
{
struct mm_struct *prev_mm;
struct mm_struct *mm;
struct list_head *p;
int retval = 0;
struct swap_info_struct *si = swap_info[type];
struct folio *folio;
swp_entry_t entry;
unsigned int i;
if (!swap_usage_in_pages(si))
goto success;
retry:
retval = shmem_unuse(type);
if (retval)
return retval;
prev_mm = &init_mm;
mmget(prev_mm);
spin_lock(&mmlist_lock);
p = &init_mm.mmlist;
while (swap_usage_in_pages(si) &&
!signal_pending(current) &&
(p = p->next) != &init_mm.mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!mmget_not_zero(mm))
continue;
spin_unlock(&mmlist_lock);
mmput(prev_mm);
prev_mm = mm;
retval = unuse_mm(mm, type);
if (retval) {
mmput(prev_mm);
return retval;
}
/*
* Make sure that we aren't completely killing
* interactive performance.
*/
cond_resched();
spin_lock(&mmlist_lock);
}
spin_unlock(&mmlist_lock);
mmput(prev_mm);
i = 0;
while (swap_usage_in_pages(si) &&
!signal_pending(current) &&
(i = find_next_to_unuse(si, i)) != 0) {
entry = swp_entry(type, i);
folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
if (IS_ERR(folio))
continue;
/*
* It is conceivable that a racing task removed this folio from
* swap cache just before we acquired the page lock. The folio
* might even be back in swap cache on another swap area. But
* that is okay, folio_free_swap() only removes stale folios.
*/
folio_lock(folio);
folio_wait_writeback(folio);
folio_free_swap(folio);
folio_unlock(folio);
folio_put(folio);
}
/*
* Lets check again to see if there are still swap entries in the map.
* If yes, we would need to do retry the unuse logic again.
* Under global memory pressure, swap entries can be reinserted back
* into process space after the mmlist loop above passes over them.
*
* Limit the number of retries? No: when mmget_not_zero()
* above fails, that mm is likely to be freeing swap from
* exit_mmap(), which proceeds at its own independent pace;
* and even shmem_writepage() could have been preempted after
* folio_alloc_swap(), temporarily hiding that swap. It's easy
* and robust (though cpu-intensive) just to keep retrying.
*/
if (swap_usage_in_pages(si)) {
if (!signal_pending(current))
goto retry;
return -EINTR;
}
success:
/*
* Make sure that further cleanups after try_to_unuse() returns happen
* after swap_range_free() reduces si->inuse_pages to 0.
*/
smp_mb();
return 0;
}
/*
* After a successful try_to_unuse, if no swap is now in use, we know
* we can empty the mmlist. swap_lock must be held on entry and exit.
* Note that mmlist_lock nests inside swap_lock, and an mm must be
* added to the mmlist just after page_duplicate - before would be racy.
*/
static void drain_mmlist(void)
{
struct list_head *p, *next;
unsigned int type;
for (type = 0; type < nr_swapfiles; type++)
if (swap_usage_in_pages(swap_info[type]))
return;
spin_lock(&mmlist_lock);
list_for_each_safe(p, next, &init_mm.mmlist)
list_del_init(p);
spin_unlock(&mmlist_lock);
}
/*
* Free all of a swapdev's extent information
*/
static void destroy_swap_extents(struct swap_info_struct *sis)
{
while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) {
struct rb_node *rb = sis->swap_extent_root.rb_node;
struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node);
rb_erase(rb, &sis->swap_extent_root);
kfree(se);
}
if (sis->flags & SWP_ACTIVATED) {
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
sis->flags &= ~SWP_ACTIVATED;
if (mapping->a_ops->swap_deactivate)
mapping->a_ops->swap_deactivate(swap_file);
}
}
/*
* Add a block range (and the corresponding page range) into this swapdev's
* extent tree.
*
* This function rather assumes that it is called in ascending page order.
*/
int
add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block)
{
struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL;
struct swap_extent *se;
struct swap_extent *new_se;
/*
* place the new node at the right most since the
* function is called in ascending page order.
*/
while (*link) {
parent = *link;
link = &parent->rb_right;
}
if (parent) {
se = rb_entry(parent, struct swap_extent, rb_node);
BUG_ON(se->start_page + se->nr_pages != start_page);
if (se->start_block + se->nr_pages == start_block) {
/* Merge it */
se->nr_pages += nr_pages;
return 0;
}
}
/* No merge, insert a new extent. */
new_se = kmalloc(sizeof(*se), GFP_KERNEL);
if (new_se == NULL)
return -ENOMEM;
new_se->start_page = start_page;
new_se->nr_pages = nr_pages;
new_se->start_block = start_block;
rb_link_node(&new_se->rb_node, parent, link);
rb_insert_color(&new_se->rb_node, &sis->swap_extent_root);
return 1;
}
EXPORT_SYMBOL_GPL(add_swap_extent);
/*
* A `swap extent' is a simple thing which maps a contiguous range of pages
* onto a contiguous range of disk blocks. A rbtree of swap extents is
* built at swapon time and is then used at swap_writepage/swap_read_folio
* time for locating where on disk a page belongs.
*
* If the swapfile is an S_ISBLK block device, a single extent is installed.
* This is done so that the main operating code can treat S_ISBLK and S_ISREG
* swap files identically.
*
* Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
* extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK
* swapfiles are handled *identically* after swapon time.
*
* For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
* and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray
* blocks are found which do not fall within the PAGE_SIZE alignment
* requirements, they are simply tossed out - we will never use those blocks
* for swapping.
*
* For all swap devices we set S_SWAPFILE across the life of the swapon. This
* prevents users from writing to the swap device, which will corrupt memory.
*
* The amount of disk space which a single swap extent represents varies.
* Typically it is in the 1-4 megabyte range. So we can have hundreds of
* extents in the rbtree. - akpm.
*/
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
{
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
int ret;
if (S_ISBLK(inode->i_mode)) {
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
return ret;
}
if (mapping->a_ops->swap_activate) {
ret = mapping->a_ops->swap_activate(sis, swap_file, span);
if (ret < 0)
return ret;
sis->flags |= SWP_ACTIVATED;
if ((sis->flags & SWP_FS_OPS) &&
sio_pool_init() != 0) {
destroy_swap_extents(sis);
return -ENOMEM;
}
return ret;
}
return generic_swapfile_activate(sis, swap_file, span);
}
static int swap_node(struct swap_info_struct *si)
{
struct block_device *bdev;
if (si->bdev)
bdev = si->bdev;
else
bdev = si->swap_file->f_inode->i_sb->s_bdev;
return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE;
}
static void setup_swap_info(struct swap_info_struct *si, int prio,
unsigned char *swap_map,
struct swap_cluster_info *cluster_info,
unsigned long *zeromap)
{
int i;
if (prio >= 0)
si->prio = prio;
else
si->prio = --least_priority;
/*
* the plist prio is negated because plist ordering is
* low-to-high, while swap ordering is high-to-low
*/
si->list.prio = -si->prio;
for_each_node(i) {
if (si->prio >= 0)
si->avail_lists[i].prio = -si->prio;
else {
if (swap_node(si) == i)
si->avail_lists[i].prio = 1;
else
si->avail_lists[i].prio = -si->prio;
}
}
si->swap_map = swap_map;
si->cluster_info = cluster_info;
si->zeromap = zeromap;
}
static void _enable_swap_info(struct swap_info_struct *si)
{
atomic_long_add(si->pages, &nr_swap_pages);
total_swap_pages += si->pages;
assert_spin_locked(&swap_lock);
/*
* both lists are plists, and thus priority ordered.
* swap_active_head needs to be priority ordered for swapoff(),
* which on removal of any swap_info_struct with an auto-assigned
* (i.e. negative) priority increments the auto-assigned priority
* of any lower-priority swap_info_structs.
* swap_avail_head needs to be priority ordered for folio_alloc_swap(),
* which allocates swap pages from the highest available priority
* swap_info_struct.
*/
plist_add(&si->list, &swap_active_head);
/* Add back to available list */
add_to_avail_list(si, true);
}
static void enable_swap_info(struct swap_info_struct *si, int prio,
unsigned char *swap_map,
struct swap_cluster_info *cluster_info,
unsigned long *zeromap)
{
spin_lock(&swap_lock);
spin_lock(&si->lock);
setup_swap_info(si, prio, swap_map, cluster_info, zeromap);
spin_unlock(&si->lock);
spin_unlock(&swap_lock);
/*
* Finished initializing swap device, now it's safe to reference it.
*/
percpu_ref_resurrect(&si->users);
spin_lock(&swap_lock);
spin_lock(&si->lock);
_enable_swap_info(si);
spin_unlock(&si->lock);
spin_unlock(&swap_lock);
}
static void reinsert_swap_info(struct swap_info_struct *si)
{
spin_lock(&swap_lock);
spin_lock(&si->lock);
setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap);
_enable_swap_info(si);
spin_unlock(&si->lock);
spin_unlock(&swap_lock);
}
/*
* Called after clearing SWP_WRITEOK, ensures cluster_alloc_range
* see the updated flags, so there will be no more allocations.
*/
static void wait_for_allocation(struct swap_info_struct *si)
{
unsigned long offset;
unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER);
struct swap_cluster_info *ci;
BUG_ON(si->flags & SWP_WRITEOK);
for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
ci = lock_cluster(si, offset);
unlock_cluster(ci);
}
}
/*
* Called after swap device's reference count is dead, so
* neither scan nor allocation will use it.
*/
static void flush_percpu_swap_cluster(struct swap_info_struct *si)
{
int cpu, i;
struct swap_info_struct **pcp_si;
for_each_possible_cpu(cpu) {
pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu);
/*
* Invalidate the percpu swap cluster cache, si->users
* is dead, so no new user will point to it, just flush
* any existing user.
*/
for (i = 0; i < SWAP_NR_ORDERS; i++)
cmpxchg(&pcp_si[i], si, NULL);
}
}
SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
{
struct swap_info_struct *p = NULL;
unsigned char *swap_map;
unsigned long *zeromap;
struct swap_cluster_info *cluster_info;
struct file *swap_file, *victim;
struct address_space *mapping;
struct inode *inode;
struct filename *pathname;
int err, found = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
BUG_ON(!current->mm);
pathname = getname(specialfile);
if (IS_ERR(pathname))
return PTR_ERR(pathname);
victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0);
err = PTR_ERR(victim);
if (IS_ERR(victim))
goto out;
mapping = victim->f_mapping;
spin_lock(&swap_lock);
plist_for_each_entry(p, &swap_active_head, list) {
if (p->flags & SWP_WRITEOK) {
if (p->swap_file->f_mapping == mapping) {
found = 1;
break;
}
}
}
if (!found) {
err = -EINVAL;
spin_unlock(&swap_lock);
goto out_dput;
}
if (!security_vm_enough_memory_mm(current->mm, p->pages))
vm_unacct_memory(p->pages);
else {
err = -ENOMEM;
spin_unlock(&swap_lock);
goto out_dput;
}
spin_lock(&p->lock);
del_from_avail_list(p, true);
if (p->prio < 0) {
struct swap_info_struct *si = p;
int nid;
plist_for_each_entry_continue(si, &swap_active_head, list) {
si->prio++;
si->list.prio--;
for_each_node(nid) {
if (si->avail_lists[nid].prio != 1)
si->avail_lists[nid].prio--;
}
}
least_priority++;
}
plist_del(&p->list, &swap_active_head);
atomic_long_sub(p->pages, &nr_swap_pages);
total_swap_pages -= p->pages;
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
wait_for_allocation(p);
set_current_oom_origin();
err = try_to_unuse(p->type);
clear_current_oom_origin();
if (err) {
/* re-insert swap space back into swap_list */
reinsert_swap_info(p);
goto out_dput;
}
/*
* Wait for swap operations protected by get/put_swap_device()
* to complete. Because of synchronize_rcu() here, all swap
* operations protected by RCU reader side lock (including any
* spinlock) will be waited too. This makes it easy to
* prevent folio_test_swapcache() and the following swap cache
* operations from racing with swapoff.
*/
percpu_ref_kill(&p->users);
synchronize_rcu();
wait_for_completion(&p->comp);
flush_work(&p->discard_work);
flush_work(&p->reclaim_work);
flush_percpu_swap_cluster(p);
destroy_swap_extents(p);
if (p->flags & SWP_CONTINUED)
free_swap_count_continuations(p);
if (!p->bdev || !bdev_nonrot(p->bdev))
atomic_dec(&nr_rotate_swap);
mutex_lock(&swapon_mutex);
spin_lock(&swap_lock);
spin_lock(&p->lock);
drain_mmlist();
swap_file = p->swap_file;
p->swap_file = NULL;
p->max = 0;
swap_map = p->swap_map;
p->swap_map = NULL;
zeromap = p->zeromap;
p->zeromap = NULL;
cluster_info = p->cluster_info;
p->cluster_info = NULL;
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
arch_swap_invalidate_area(p->type);
zswap_swapoff(p->type);
mutex_unlock(&swapon_mutex);
kfree(p->global_cluster);
p->global_cluster = NULL;
vfree(swap_map);
kvfree(zeromap);
kvfree(cluster_info);
/* Destroy swap account information */
swap_cgroup_swapoff(p->type);
exit_swap_address_space(p->type);
inode = mapping->host;
inode_lock(inode);
inode->i_flags &= ~S_SWAPFILE;
inode_unlock(inode);
filp_close(swap_file, NULL);
/*
* Clear the SWP_USED flag after all resources are freed so that swapon
* can reuse this swap_info in alloc_swap_info() safely. It is ok to
* not hold p->lock after we cleared its SWP_WRITEOK.
*/
spin_lock(&swap_lock);
p->flags = 0;
spin_unlock(&swap_lock);
err = 0;
atomic_inc(&proc_poll_event);
wake_up_interruptible(&proc_poll_wait);
out_dput:
filp_close(victim, NULL);
out:
putname(pathname);
return err;
}
#ifdef CONFIG_PROC_FS
static __poll_t swaps_poll(struct file *file, poll_table *wait)
{
struct seq_file *seq = file->private_data;
poll_wait(file, &proc_poll_wait, wait);
if (seq->poll_event != atomic_read(&proc_poll_event)) {
seq->poll_event = atomic_read(&proc_poll_event);
return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI;
}
return EPOLLIN | EPOLLRDNORM;
}
/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos)
{
struct swap_info_struct *si;
int type;
loff_t l = *pos;
mutex_lock(&swapon_mutex);
if (!l)
return SEQ_START_TOKEN;
for (type = 0; (si = swap_type_to_swap_info(type)); type++) {
if (!(si->flags & SWP_USED) || !si->swap_map)
continue;
if (!--l)
return si;
}
return NULL;
}
static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
{
struct swap_info_struct *si = v;
int type;
if (v == SEQ_START_TOKEN)
type = 0;
else
type = si->type + 1;
++(*pos);
for (; (si = swap_type_to_swap_info(type)); type++) {
if (!(si->flags & SWP_USED) || !si->swap_map)
continue;
return si;
}
return NULL;
}
static void swap_stop(struct seq_file *swap, void *v)
{
mutex_unlock(&swapon_mutex);
}
static int swap_show(struct seq_file *swap, void *v)
{
struct swap_info_struct *si = v;
struct file *file;
int len;
unsigned long bytes, inuse;
if (si == SEQ_START_TOKEN) {
seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n");
return 0;
}
bytes = K(si->pages);
inuse = K(swap_usage_in_pages(si));
file = si->swap_file;
len = seq_file_path(swap, file, " \t\n\\");
seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n",
len < 40 ? 40 - len : 1, " ",
S_ISBLK(file_inode(file)->i_mode) ?
"partition" : "file\t",
bytes, bytes < 10000000 ? "\t" : "",
inuse, inuse < 10000000 ? "\t" : "",
si->prio);
return 0;
}
static const struct seq_operations swaps_op = {
.start = swap_start,
.next = swap_next,
.stop = swap_stop,
.show = swap_show
};
static int swaps_open(struct inode *inode, struct file *file)
{
struct seq_file *seq;
int ret;
ret = seq_open(file, &swaps_op);
if (ret)
return ret;
seq = file->private_data;
seq->poll_event = atomic_read(&proc_poll_event);
return 0;
}
static const struct proc_ops swaps_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = swaps_open,
.proc_read = seq_read,
.proc_lseek = seq_lseek,
.proc_release = seq_release,
.proc_poll = swaps_poll,
};
static int __init procswaps_init(void)
{
proc_create("swaps", 0, NULL, &swaps_proc_ops);
return 0;
}
__initcall(procswaps_init);
#endif /* CONFIG_PROC_FS */
#ifdef MAX_SWAPFILES_CHECK
static int __init max_swapfiles_check(void)
{
MAX_SWAPFILES_CHECK();
return 0;
}
late_initcall(max_swapfiles_check);
#endif
static struct swap_info_struct *alloc_swap_info(void)
{
struct swap_info_struct *p;
struct swap_info_struct *defer = NULL;
unsigned int type;
int i;
p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
if (percpu_ref_init(&p->users, swap_users_ref_free,
PERCPU_REF_INIT_DEAD, GFP_KERNEL)) {
kvfree(p);
return ERR_PTR(-ENOMEM);
}
spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
if (!(swap_info[type]->flags & SWP_USED))
break;
}
if (type >= MAX_SWAPFILES) {
spin_unlock(&swap_lock);
percpu_ref_exit(&p->users);
kvfree(p);
return ERR_PTR(-EPERM);
}
if (type >= nr_swapfiles) {
p->type = type;
/*
* Publish the swap_info_struct after initializing it.
* Note that kvzalloc() above zeroes all its fields.
*/
smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */
nr_swapfiles++;
} else {
defer = p;
p = swap_info[type];
/*
* Do not memset this entry: a racing procfs swap_next()
* would be relying on p->type to remain valid.
*/
}
p->swap_extent_root = RB_ROOT;
plist_node_init(&p->list, 0);
for_each_node(i)
plist_node_init(&p->avail_lists[i], 0);
p->flags = SWP_USED;
spin_unlock(&swap_lock);
if (defer) {
percpu_ref_exit(&defer->users);
kvfree(defer);
}
spin_lock_init(&p->lock);
spin_lock_init(&p->cont_lock);
atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT);
init_completion(&p->comp);
return p;
}
static int claim_swapfile(struct swap_info_struct *si, struct inode *inode)
{
if (S_ISBLK(inode->i_mode)) {
si->bdev = I_BDEV(inode);
/*
* Zoned block devices contain zones that have a sequential
* write only restriction. Hence zoned block devices are not
* suitable for swapping. Disallow them here.
*/
if (bdev_is_zoned(si->bdev))
return -EINVAL;
si->flags |= SWP_BLKDEV;
} else if (S_ISREG(inode->i_mode)) {
si->bdev = inode->i_sb->s_bdev;
}
return 0;
}
/*
* Find out how many pages are allowed for a single swap device. There
* are two limiting factors:
* 1) the number of bits for the swap offset in the swp_entry_t type, and
* 2) the number of bits in the swap pte, as defined by the different
* architectures.
*
* In order to find the largest possible bit mask, a swap entry with
* swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
* decoded to a swp_entry_t again, and finally the swap offset is
* extracted.
*
* This will mask all the bits from the initial ~0UL mask that can't
* be encoded in either the swp_entry_t or the architecture definition
* of a swap pte.
*/
unsigned long generic_max_swapfile_size(void)
{
return swp_offset(pte_to_swp_entry(
swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
}
/* Can be overridden by an architecture for additional checks. */
__weak unsigned long arch_max_swapfile_size(void)
{
return generic_max_swapfile_size();
}
static unsigned long read_swap_header(struct swap_info_struct *si,
union swap_header *swap_header,
struct inode *inode)
{
int i;
unsigned long maxpages;
unsigned long swapfilepages;
unsigned long last_page;
if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
pr_err("Unable to find swap-space signature\n");
return 0;
}
/* swap partition endianness hack... */
if (swab32(swap_header->info.version) == 1) {
swab32s(&swap_header->info.version);
swab32s(&swap_header->info.last_page);
swab32s(&swap_header->info.nr_badpages);
if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
return 0;
for (i = 0; i < swap_header->info.nr_badpages; i++)
swab32s(&swap_header->info.badpages[i]);
}
/* Check the swap header's sub-version */
if (swap_header->info.version != 1) {
pr_warn("Unable to handle swap header version %d\n",
swap_header->info.version);
return 0;
}
maxpages = swapfile_maximum_size;
last_page = swap_header->info.last_page;
if (!last_page) {
pr_warn("Empty swap-file\n");
return 0;
}
if (last_page > maxpages) {
pr_warn("Truncating oversized swap area, only using %luk out of %luk\n",
K(maxpages), K(last_page));
}
if (maxpages > last_page) {
maxpages = last_page + 1;
/* p->max is an unsigned int: don't overflow it */
if ((unsigned int)maxpages == 0)
maxpages = UINT_MAX;
}
if (!maxpages)
return 0;
swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
if (swapfilepages && maxpages > swapfilepages) {
pr_warn("Swap area shorter than signature indicates\n");
return 0;
}
if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
return 0;
if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
return 0;
return maxpages;
}
static int setup_swap_map_and_extents(struct swap_info_struct *si,
union swap_header *swap_header,
unsigned char *swap_map,
unsigned long maxpages,
sector_t *span)
{
unsigned int nr_good_pages;
unsigned long i;
int nr_extents;
nr_good_pages = maxpages - 1; /* omit header page */
for (i = 0; i < swap_header->info.nr_badpages; i++) {
unsigned int page_nr = swap_header->info.badpages[i];
if (page_nr == 0 || page_nr > swap_header->info.last_page)
return -EINVAL;
if (page_nr < maxpages) {
swap_map[page_nr] = SWAP_MAP_BAD;
nr_good_pages--;
}
}
if (nr_good_pages) {
swap_map[0] = SWAP_MAP_BAD;
si->max = maxpages;
si->pages = nr_good_pages;
nr_extents = setup_swap_extents(si, span);
if (nr_extents < 0)
return nr_extents;
nr_good_pages = si->pages;
}
if (!nr_good_pages) {
pr_warn("Empty swap-file\n");
return -EINVAL;
}
return nr_extents;
}
#define SWAP_CLUSTER_INFO_COLS \
DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info))
#define SWAP_CLUSTER_SPACE_COLS \
DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER)
#define SWAP_CLUSTER_COLS \
max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS)
static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
union swap_header *swap_header,
unsigned long maxpages)
{
unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
struct swap_cluster_info *cluster_info;
unsigned long i, j, idx;
int err = -ENOMEM;
cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL);
if (!cluster_info)
goto err;
for (i = 0; i < nr_clusters; i++)
spin_lock_init(&cluster_info[i].lock);
if (!(si->flags & SWP_SOLIDSTATE)) {
si->global_cluster = kmalloc(sizeof(*si->global_cluster),
GFP_KERNEL);
if (!si->global_cluster)
goto err_free;
for (i = 0; i < SWAP_NR_ORDERS; i++)
si->global_cluster->next[i] = SWAP_ENTRY_INVALID;
spin_lock_init(&si->global_cluster_lock);
}
/*
* Mark unusable pages as unavailable. The clusters aren't
* marked free yet, so no list operations are involved yet.
*
* See setup_swap_map_and_extents(): header page, bad pages,
* and the EOF part of the last cluster.
*/
inc_cluster_info_page(si, cluster_info, 0);
for (i = 0; i < swap_header->info.nr_badpages; i++)
inc_cluster_info_page(si, cluster_info,
swap_header->info.badpages[i]);
for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++)
inc_cluster_info_page(si, cluster_info, i);
INIT_LIST_HEAD(&si->free_clusters);
INIT_LIST_HEAD(&si->full_clusters);
INIT_LIST_HEAD(&si->discard_clusters);
for (i = 0; i < SWAP_NR_ORDERS; i++) {
INIT_LIST_HEAD(&si->nonfull_clusters[i]);
INIT_LIST_HEAD(&si->frag_clusters[i]);
atomic_long_set(&si->frag_cluster_nr[i], 0);
}
/*
* Reduce false cache line sharing between cluster_info and
* sharing same address space.
*/
for (j = 0; j < SWAP_CLUSTER_COLS; j++) {
for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
struct swap_cluster_info *ci;
idx = i * SWAP_CLUSTER_COLS + j;
ci = cluster_info + idx;
if (idx >= nr_clusters)
continue;
if (ci->count) {
ci->flags = CLUSTER_FLAG_NONFULL;
list_add_tail(&ci->list, &si->nonfull_clusters[0]);
continue;
}
ci->flags = CLUSTER_FLAG_FREE;
list_add_tail(&ci->list, &si->free_clusters);
}
}
return cluster_info;
err_free:
kvfree(cluster_info);
err:
return ERR_PTR(err);
}
SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
{
struct swap_info_struct *si;
struct filename *name;
struct file *swap_file = NULL;
struct address_space *mapping;
struct dentry *dentry;
int prio;
int error;
union swap_header *swap_header;
int nr_extents;
sector_t span;
unsigned long maxpages;
unsigned char *swap_map = NULL;
unsigned long *zeromap = NULL;
struct swap_cluster_info *cluster_info = NULL;
struct folio *folio = NULL;
struct inode *inode = NULL;
bool inced_nr_rotate_swap = false;
if (swap_flags & ~SWAP_FLAGS_VALID)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!swap_avail_heads)
return -ENOMEM;
si = alloc_swap_info();
if (IS_ERR(si))
return PTR_ERR(si);
INIT_WORK(&si->discard_work, swap_discard_work);
INIT_WORK(&si->reclaim_work, swap_reclaim_work);
name = getname(specialfile);
if (IS_ERR(name)) {
error = PTR_ERR(name);
name = NULL;
goto bad_swap;
}
swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0);
if (IS_ERR(swap_file)) {
error = PTR_ERR(swap_file);
swap_file = NULL;
goto bad_swap;
}
si->swap_file = swap_file;
mapping = swap_file->f_mapping;
dentry = swap_file->f_path.dentry;
inode = mapping->host;
error = claim_swapfile(si, inode);
if (unlikely(error))
goto bad_swap;
inode_lock(inode);
if (d_unlinked(dentry) || cant_mount(dentry)) {
error = -ENOENT;
goto bad_swap_unlock_inode;
}
if (IS_SWAPFILE(inode)) {
error = -EBUSY;
goto bad_swap_unlock_inode;
}
/*
* Read the swap header.
*/
if (!mapping->a_ops->read_folio) {
error = -EINVAL;
goto bad_swap_unlock_inode;
}
folio = read_mapping_folio(mapping, 0, swap_file);
if (IS_ERR(folio)) {
error = PTR_ERR(folio);
goto bad_swap_unlock_inode;
}
swap_header = kmap_local_folio(folio, 0);
maxpages = read_swap_header(si, swap_header, inode);
if (unlikely(!maxpages)) {
error = -EINVAL;
goto bad_swap_unlock_inode;
}
/* OK, set up the swap map and apply the bad block list */
swap_map = vzalloc(maxpages);
if (!swap_map) {
error = -ENOMEM;
goto bad_swap_unlock_inode;
}
error = swap_cgroup_swapon(si->type, maxpages);
if (error)
goto bad_swap_unlock_inode;
nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map,
maxpages, &span);
if (unlikely(nr_extents < 0)) {
error = nr_extents;
goto bad_swap_unlock_inode;
}
/*
* Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
* be above MAX_PAGE_ORDER incase of a large swap file.
*/
zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long),
GFP_KERNEL | __GFP_ZERO);
if (!zeromap) {
error = -ENOMEM;
goto bad_swap_unlock_inode;
}
if (si->bdev && bdev_stable_writes(si->bdev))
si->flags |= SWP_STABLE_WRITES;
if (si->bdev && bdev_synchronous(si->bdev))
si->flags |= SWP_SYNCHRONOUS_IO;
if (si->bdev && bdev_nonrot(si->bdev)) {
si->flags |= SWP_SOLIDSTATE;
} else {
atomic_inc(&nr_rotate_swap);
inced_nr_rotate_swap = true;
}
cluster_info = setup_clusters(si, swap_header, maxpages);
if (IS_ERR(cluster_info)) {
error = PTR_ERR(cluster_info);
cluster_info = NULL;
goto bad_swap_unlock_inode;
}
if ((swap_flags & SWAP_FLAG_DISCARD) &&
si->bdev && bdev_max_discard_sectors(si->bdev)) {
/*
* When discard is enabled for swap with no particular
* policy flagged, we set all swap discard flags here in
* order to sustain backward compatibility with older
* swapon(8) releases.
*/
si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
SWP_PAGE_DISCARD);
/*
* By flagging sys_swapon, a sysadmin can tell us to
* either do single-time area discards only, or to just
* perform discards for released swap page-clusters.
* Now it's time to adjust the p->flags accordingly.
*/
if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
si->flags &= ~SWP_PAGE_DISCARD;
else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
si->flags &= ~SWP_AREA_DISCARD;
/* issue a swapon-time discard if it's still required */
if (si->flags & SWP_AREA_DISCARD) {
int err = discard_swap(si);
if (unlikely(err))
pr_err("swapon: discard_swap(%p): %d\n",
si, err);
}
}
error = init_swap_address_space(si->type, maxpages);
if (error)
goto bad_swap_unlock_inode;
error = zswap_swapon(si->type, maxpages);
if (error)
goto free_swap_address_space;
/*
* Flush any pending IO and dirty mappings before we start using this
* swap device.
*/
inode->i_flags |= S_SWAPFILE;
error = inode_drain_writes(inode);
if (error) {
inode->i_flags &= ~S_SWAPFILE;
goto free_swap_zswap;
}
mutex_lock(&swapon_mutex);
prio = -1;
if (swap_flags & SWAP_FLAG_PREFER)
prio = swap_flags & SWAP_FLAG_PRIO_MASK;
enable_swap_info(si, prio, swap_map, cluster_info, zeromap);
pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n",
K(si->pages), name->name, si->prio, nr_extents,
K((unsigned long long)span),
(si->flags & SWP_SOLIDSTATE) ? "SS" : "",
(si->flags & SWP_DISCARDABLE) ? "D" : "",
(si->flags & SWP_AREA_DISCARD) ? "s" : "",
(si->flags & SWP_PAGE_DISCARD) ? "c" : "");
mutex_unlock(&swapon_mutex);
atomic_inc(&proc_poll_event);
wake_up_interruptible(&proc_poll_wait);
error = 0;
goto out;
free_swap_zswap:
zswap_swapoff(si->type);
free_swap_address_space:
exit_swap_address_space(si->type);
bad_swap_unlock_inode:
inode_unlock(inode);
bad_swap:
kfree(si->global_cluster);
si->global_cluster = NULL;
inode = NULL;
destroy_swap_extents(si);
swap_cgroup_swapoff(si->type);
spin_lock(&swap_lock);
si->swap_file = NULL;
si->flags = 0;
spin_unlock(&swap_lock);
vfree(swap_map);
kvfree(zeromap);
kvfree(cluster_info);
if (inced_nr_rotate_swap)
atomic_dec(&nr_rotate_swap);
if (swap_file)
filp_close(swap_file, NULL);
out:
if (!IS_ERR_OR_NULL(folio))
folio_release_kmap(folio, swap_header);
if (name)
putname(name);
if (inode)
inode_unlock(inode);
return error;
}
void si_swapinfo(struct sysinfo *val)
{
unsigned int type;
unsigned long nr_to_be_unused = 0;
spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
struct swap_info_struct *si = swap_info[type];
if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK))
nr_to_be_unused += swap_usage_in_pages(si);
}
val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused;
val->totalswap = total_swap_pages + nr_to_be_unused;
spin_unlock(&swap_lock);
}
/*
* Verify that nr swap entries are valid and increment their swap map counts.
*
* Returns error code in following case.
* - success -> 0
* - swp_entry is invalid -> EINVAL
* - swap-cache reference is requested but there is already one. -> EEXIST
* - swap-cache reference is requested but the entry is not used. -> ENOENT
* - swap-mapped reference requested but needs continued swap count. -> ENOMEM
*/
static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
{
struct swap_info_struct *si;
struct swap_cluster_info *ci;
unsigned long offset;
unsigned char count;
unsigned char has_cache;
int err, i;
si = swp_swap_info(entry);
if (WARN_ON_ONCE(!si)) {
pr_err("%s%08lx\n", Bad_file, entry.val);
return -EINVAL;
}
offset = swp_offset(entry);
VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
VM_WARN_ON(usage == 1 && nr > 1);
ci = lock_cluster(si, offset);
err = 0;
for (i = 0; i < nr; i++) {
count = si->swap_map[offset + i];
/*
* swapin_readahead() doesn't check if a swap entry is valid, so the
* swap entry could be SWAP_MAP_BAD. Check here with lock held.
*/
if (unlikely(swap_count(count) == SWAP_MAP_BAD)) {
err = -ENOENT;
goto unlock_out;
}
has_cache = count & SWAP_HAS_CACHE;
count &= ~SWAP_HAS_CACHE;
if (!count && !has_cache) {
err = -ENOENT;
} else if (usage == SWAP_HAS_CACHE) {
if (has_cache)
err = -EEXIST;
} else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) {
err = -EINVAL;
}
if (err)
goto unlock_out;
}
for (i = 0; i < nr; i++) {
count = si->swap_map[offset + i];
has_cache = count & SWAP_HAS_CACHE;
count &= ~SWAP_HAS_CACHE;
if (usage == SWAP_HAS_CACHE)
has_cache = SWAP_HAS_CACHE;
else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX)
count += usage;
else if (swap_count_continued(si, offset + i, count))
count = COUNT_CONTINUED;
else {
/*
* Don't need to rollback changes, because if
* usage == 1, there must be nr == 1.
*/
err = -ENOMEM;
goto unlock_out;
}
WRITE_ONCE(si->swap_map[offset + i], count | has_cache);
}
unlock_out:
unlock_cluster(ci);
return err;
}
/*
* Help swapoff by noting that swap entry belongs to shmem/tmpfs
* (in which case its reference count is never incremented).
*/
void swap_shmem_alloc(swp_entry_t entry, int nr)
{
__swap_duplicate(entry, SWAP_MAP_SHMEM, nr);
}
/*
* Increase reference count of swap entry by 1.
* Returns 0 for success, or -ENOMEM if a swap_count_continuation is required
* but could not be atomically allocated. Returns 0, just as if it succeeded,
* if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which
* might occur if a page table entry has got corrupted.
*/
int swap_duplicate(swp_entry_t entry)
{
int err = 0;
while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM)
err = add_swap_count_continuation(entry, GFP_ATOMIC);
return err;
}
/*
* @entry: first swap entry from which we allocate nr swap cache.
*
* Called when allocating swap cache for existing swap entries,
* This can return error codes. Returns 0 at success.
* -EEXIST means there is a swap cache.
* Note: return code is different from swap_duplicate().
*/
int swapcache_prepare(swp_entry_t entry, int nr)
{
return __swap_duplicate(entry, SWAP_HAS_CACHE, nr);
}
void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr)
{
unsigned long offset = swp_offset(entry);
cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE);
}
struct swap_info_struct *swp_swap_info(swp_entry_t entry)
{
return swap_type_to_swap_info(swp_type(entry));
}
/*
* out-of-line methods to avoid include hell.
*/
struct address_space *swapcache_mapping(struct folio *folio)
{
return swp_swap_info(folio->swap)->swap_file->f_mapping;
}
EXPORT_SYMBOL_GPL(swapcache_mapping);
pgoff_t __folio_swap_cache_index(struct folio *folio)
{
return swap_cache_index(folio->swap);
}
EXPORT_SYMBOL_GPL(__folio_swap_cache_index);
/*
* add_swap_count_continuation - called when a swap count is duplicated
* beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's
* page of the original vmalloc'ed swap_map, to hold the continuation count
* (for that entry and for its neighbouring PAGE_SIZE swap entries). Called
* again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc.
*
* These continuation pages are seldom referenced: the common paths all work
* on the original swap_map, only referring to a continuation page when the
* low "digit" of a count is incremented or decremented through SWAP_MAP_MAX.
*
* add_swap_count_continuation(, GFP_ATOMIC) can be called while holding
* page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL)
* can be called after dropping locks.
*/
int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
{
struct swap_info_struct *si;
struct swap_cluster_info *ci;
struct page *head;
struct page *page;
struct page *list_page;
pgoff_t offset;
unsigned char count;
int ret = 0;
/*
* When debugging, it's easier to use __GFP_ZERO here; but it's better
* for latency not to zero a page while GFP_ATOMIC and holding locks.
*/
page = alloc_page(gfp_mask | __GFP_HIGHMEM);
si = get_swap_device(entry);
if (!si) {
/*
* An acceptable race has occurred since the failing
* __swap_duplicate(): the swap device may be swapoff
*/
goto outer;
}
offset = swp_offset(entry);
ci = lock_cluster(si, offset);
count = swap_count(si->swap_map[offset]);
if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) {
/*
* The higher the swap count, the more likely it is that tasks
* will race to add swap count continuation: we need to avoid
* over-provisioning.
*/
goto out;
}
if (!page) {
ret = -ENOMEM;
goto out;
}
head = vmalloc_to_page(si->swap_map + offset);
offset &= ~PAGE_MASK;
spin_lock(&si->cont_lock);
/*
* Page allocation does not initialize the page's lru field,
* but it does always reset its private field.
*/
if (!page_private(head)) {
BUG_ON(count & COUNT_CONTINUED);
INIT_LIST_HEAD(&head->lru);
set_page_private(head, SWP_CONTINUED);
si->flags |= SWP_CONTINUED;
}
list_for_each_entry(list_page, &head->lru, lru) {
unsigned char *map;
/*
* If the previous map said no continuation, but we've found
* a continuation page, free our allocation and use this one.
*/
if (!(count & COUNT_CONTINUED))
goto out_unlock_cont;
map = kmap_local_page(list_page) + offset;
count = *map;
kunmap_local(map);
/*
* If this continuation count now has some space in it,
* free our allocation and use this one.
*/
if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX)
goto out_unlock_cont;
}
list_add_tail(&page->lru, &head->lru);
page = NULL; /* now it's attached, don't free it */
out_unlock_cont:
spin_unlock(&si->cont_lock);
out:
unlock_cluster(ci);
put_swap_device(si);
outer:
if (page)
__free_page(page);
return ret;
}
/*
* swap_count_continued - when the original swap_map count is incremented
* from SWAP_MAP_MAX, check if there is already a continuation page to carry
* into, carry if so, or else fail until a new continuation page is allocated;
* when the original swap_map count is decremented from 0 with continuation,
* borrow from the continuation and report whether it still holds more.
* Called while __swap_duplicate() or caller of __swap_entry_free_locked()
* holds cluster lock.
*/
static bool swap_count_continued(struct swap_info_struct *si,
pgoff_t offset, unsigned char count)
{
struct page *head;
struct page *page;
unsigned char *map;
bool ret;
head = vmalloc_to_page(si->swap_map + offset);
if (page_private(head) != SWP_CONTINUED) {
BUG_ON(count & COUNT_CONTINUED);
return false; /* need to add count continuation */
}
spin_lock(&si->cont_lock);
offset &= ~PAGE_MASK;
page = list_next_entry(head, lru);
map = kmap_local_page(page) + offset;
if (count == SWAP_MAP_MAX) /* initial increment from swap_map */
goto init_map; /* jump over SWAP_CONT_MAX checks */
if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */
/*
* Think of how you add 1 to 999
*/
while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) {
kunmap_local(map);
page = list_next_entry(page, lru);
BUG_ON(page == head);
map = kmap_local_page(page) + offset;
}
if (*map == SWAP_CONT_MAX) {
kunmap_local(map);
page = list_next_entry(page, lru);
if (page == head) {
ret = false; /* add count continuation */
goto out;
}
map = kmap_local_page(page) + offset;
init_map: *map = 0; /* we didn't zero the page */
}
*map += 1;
kunmap_local(map);
while ((page = list_prev_entry(page, lru)) != head) {
map = kmap_local_page(page) + offset;
*map = COUNT_CONTINUED;
kunmap_local(map);
}
ret = true; /* incremented */
} else { /* decrementing */
/*
* Think of how you subtract 1 from 1000
*/
BUG_ON(count != COUNT_CONTINUED);
while (*map == COUNT_CONTINUED) {
kunmap_local(map);
page = list_next_entry(page, lru);
BUG_ON(page == head);
map = kmap_local_page(page) + offset;
}
BUG_ON(*map == 0);
*map -= 1;
if (*map == 0)
count = 0;
kunmap_local(map);
while ((page = list_prev_entry(page, lru)) != head) {
map = kmap_local_page(page) + offset;
*map = SWAP_CONT_MAX | count;
count = COUNT_CONTINUED;
kunmap_local(map);
}
ret = count == COUNT_CONTINUED;
}
out:
spin_unlock(&si->cont_lock);
return ret;
}
/*
* free_swap_count_continuations - swapoff free all the continuation pages
* appended to the swap_map, after swap_map is quiesced, before vfree'ing it.
*/
static void free_swap_count_continuations(struct swap_info_struct *si)
{
pgoff_t offset;
for (offset = 0; offset < si->max; offset += PAGE_SIZE) {
struct page *head;
head = vmalloc_to_page(si->swap_map + offset);
if (page_private(head)) {
struct page *page, *next;
list_for_each_entry_safe(page, next, &head->lru, lru) {
list_del(&page->lru);
__free_page(page);
}
}
}
}
#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
static bool __has_usable_swap(void)
{
return !plist_head_empty(&swap_active_head);
}
void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
{
struct swap_info_struct *si, *next;
int nid = folio_nid(folio); if (!(gfp & __GFP_IO))
return;
if (!__has_usable_swap())
return;
if (!blk_cgroup_congested())
return;
/*
* We've already scheduled a throttle, avoid taking the global swap
* lock.
*/
if (current->throttle_disk)
return;
spin_lock(&swap_avail_lock);
plist_for_each_entry_safe(si, next, &swap_avail_heads[nid],
avail_lists[nid]) {
if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true);
break;
}
}
spin_unlock(&swap_avail_lock);
}
#endif
static int __init swapfile_init(void)
{
int nid;
swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head),
GFP_KERNEL);
if (!swap_avail_heads) {
pr_emerg("Not enough memory for swap heads, swap is disabled\n");
return -ENOMEM;
}
for_each_node(nid)
plist_head_init(&swap_avail_heads[nid]);
swapfile_maximum_size = arch_max_swapfile_size();
#ifdef CONFIG_MIGRATION
if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS))
swap_migration_ad_supported = true;
#endif /* CONFIG_MIGRATION */
return 0;
}
subsys_initcall(swapfile_init);
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
*/
/* Devmaps primary use is as a backend map for XDP BPF helper call
* bpf_redirect_map(). Because XDP is mostly concerned with performance we
* spent some effort to ensure the datapath with redirect maps does not use
* any locking. This is a quick note on the details.
*
* We have three possible paths to get into the devmap control plane bpf
* syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall
* will invoke an update, delete, or lookup operation. To ensure updates and
* deletes appear atomic from the datapath side xchg() is used to modify the
* netdev_map array. Then because the datapath does a lookup into the netdev_map
* array (read-only) from an RCU critical section we use call_rcu() to wait for
* an rcu grace period before free'ing the old data structures. This ensures the
* datapath always has a valid copy. However, the datapath does a "flush"
* operation that pushes any pending packets in the driver outside the RCU
* critical section. Each bpf_dtab_netdev tracks these pending operations using
* a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until
* this list is empty, indicating outstanding flush operations have completed.
*
* BPF syscalls may race with BPF program calls on any of the update, delete
* or lookup operations. As noted above the xchg() operation also keep the
* netdev_map consistent in this case. From the devmap side BPF programs
* calling into these operations are the same as multiple user space threads
* making system calls.
*
* Finally, any of the above may race with a netdev_unregister notifier. The
* unregister notifier must search for net devices in the map structure that
* contain a reference to the net device and remove them. This is a two step
* process (a) dereference the bpf_dtab_netdev object in netdev_map and (b)
* check to see if the ifindex is the same as the net_device being removed.
* When removing the dev a cmpxchg() is used to ensure the correct dev is
* removed, in the case of a concurrent update or delete operation it is
* possible that the initially referenced dev is no longer in the map. As the
* notifier hook walks the map we know that new dev references can not be
* added by the user because core infrastructure ensures dev_get_by_index()
* calls will fail at this point.
*
* The devmap_hash type is a map type which interprets keys as ifindexes and
* indexes these using a hashmap. This allows maps that use ifindex as key to be
* densely packed instead of having holes in the lookup array for unused
* ifindexes. The setup and packet enqueue/send code is shared between the two
* types of devmap; only the lookup and insertion is different.
*/
#include <linux/bpf.h>
#include <net/xdp.h>
#include <linux/filter.h>
#include <trace/events/xdp.h>
#include <linux/btf_ids.h>
#define DEV_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
struct xdp_dev_bulk_queue {
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
struct list_head flush_node;
struct net_device *dev;
struct net_device *dev_rx;
struct bpf_prog *xdp_prog;
unsigned int count;
};
struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
struct bpf_prog *xdp_prog;
struct rcu_head rcu;
unsigned int idx;
struct bpf_devmap_val val;
};
struct bpf_dtab {
struct bpf_map map;
struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */
struct list_head list;
/* these are only used for DEVMAP_HASH type maps */
struct hlist_head *dev_index_head;
spinlock_t index_lock;
unsigned int items;
u32 n_buckets;
};
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
static struct hlist_head *dev_map_create_hash(unsigned int entries,
int numa_node)
{
int i;
struct hlist_head *hash;
hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node);
if (hash != NULL)
for (i = 0; i < entries; i++)
INIT_HLIST_HEAD(&hash[i]);
return hash;
}
static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
int idx)
{
return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
}
static int dev_map_alloc_check(union bpf_attr *attr)
{
u32 valsize = attr->value_size;
/* check sanity of attributes. 2 value sizes supported:
* 4 bytes: ifindex
* 8 bytes: ifindex + prog fd
*/
if (attr->max_entries == 0 || attr->key_size != 4 ||
(valsize != offsetofend(struct bpf_devmap_val, ifindex) &&
valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) ||
attr->map_flags & ~DEV_CREATE_FLAG_MASK)
return -EINVAL;
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
/* Hash table size must be power of 2; roundup_pow_of_two()
* can overflow into UB on 32-bit arches
*/
if (attr->max_entries > 1UL << 31)
return -EINVAL;
}
return 0;
}
static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
{
/* Lookup returns a pointer straight to dev->ifindex, so make sure the
* verifier prevents writes from the BPF side
*/
attr->map_flags |= BPF_F_RDONLY_PROG;
bpf_map_init_from_attr(&dtab->map, attr);
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
/* Hash table size must be power of 2 */
dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
dtab->map.numa_node);
if (!dtab->dev_index_head)
return -ENOMEM;
spin_lock_init(&dtab->index_lock);
} else {
dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries *
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
return -ENOMEM;
}
return 0;
}
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
{
struct bpf_dtab *dtab;
int err;
dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE);
if (!dtab)
return ERR_PTR(-ENOMEM);
err = dev_map_init_map(dtab, attr);
if (err) {
bpf_map_area_free(dtab);
return ERR_PTR(err);
}
spin_lock(&dev_map_lock);
list_add_tail_rcu(&dtab->list, &dev_map_list);
spin_unlock(&dev_map_lock);
return &dtab->map;
}
static void dev_map_free(struct bpf_map *map)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
u32 i;
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. The following synchronize_rcu() guarantees
* both rcu read critical sections complete and waits for
* preempt-disable regions (NAPI being the relevant context here) so we
* are certain there will be no further reads against the netdev_map and
* all flush operations are complete. Flush operations can only be done
* from NAPI context for this reason.
*/
spin_lock(&dev_map_lock);
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
/* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map()
* during NAPI callback and cleared after the XDP redirect. There is no
* explicit RCU read section which protects bpf_redirect_info->map but
* local_bh_disable() also marks the beginning an RCU section. This
* makes the complete softirq callback RCU protected. Thus after
* following synchronize_rcu() there no bpf_redirect_info->map == map
* assignment.
*/
synchronize_rcu();
/* Make sure prior __dev_map_entry_free() have completed. */
rcu_barrier();
if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
for (i = 0; i < dtab->n_buckets; i++) {
struct bpf_dtab_netdev *dev;
struct hlist_head *head;
struct hlist_node *next;
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
hlist_del_rcu(&dev->index_hlist);
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
dev_put(dev->dev);
kfree(dev);
}
}
bpf_map_area_free(dtab->dev_index_head);
} else {
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev;
dev = rcu_dereference_raw(dtab->netdev_map[i]);
if (!dev)
continue;
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
dev_put(dev->dev);
kfree(dev);
}
bpf_map_area_free(dtab->netdev_map);
}
bpf_map_area_free(dtab);
}
static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
u32 index = key ? *(u32 *)key : U32_MAX;
u32 *next = next_key;
if (index >= dtab->map.max_entries) {
*next = 0;
return 0;
}
if (index == dtab->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
*/
static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct hlist_head *head = dev_map_index_hash(dtab, key);
struct bpf_dtab_netdev *dev;
hlist_for_each_entry_rcu(dev, head, index_hlist,
lockdep_is_held(&dtab->index_lock))
if (dev->idx == key)
return dev;
return NULL;
}
static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
u32 idx, *next = next_key;
struct bpf_dtab_netdev *dev, *next_dev;
struct hlist_head *head;
int i = 0;
if (!key)
goto find_first;
idx = *(u32 *)key;
dev = __dev_map_hash_lookup_elem(map, idx);
if (!dev)
goto find_first;
next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)),
struct bpf_dtab_netdev, index_hlist);
if (next_dev) {
*next = next_dev->idx;
return 0;
}
i = idx & (dtab->n_buckets - 1);
i++;
find_first:
for (; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
struct bpf_dtab_netdev,
index_hlist);
if (next_dev) {
*next = next_dev->idx;
return 0;
}
}
return -ENOENT;
}
static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
struct xdp_frame **frames, int n,
struct net_device *tx_dev,
struct net_device *rx_dev)
{
struct xdp_txq_info txq = { .dev = tx_dev };
struct xdp_rxq_info rxq = { .dev = rx_dev };
struct xdp_buff xdp;
int i, nframes = 0;
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
u32 act;
int err;
xdp_convert_frame_to_buff(xdpf, &xdp);
xdp.txq = &txq;
xdp.rxq = &rxq;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
err = xdp_update_frame_from_buff(&xdp, xdpf);
if (unlikely(err < 0))
xdp_return_frame_rx_napi(xdpf);
else
frames[nframes++] = xdpf;
break;
default:
bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(tx_dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
xdp_return_frame_rx_napi(xdpf);
break;
}
}
return nframes; /* sent frames count */
}
static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
struct net_device *dev = bq->dev;
unsigned int cnt = bq->count;
int sent = 0, err = 0;
int to_send = cnt;
int i;
if (unlikely(!cnt))
return;
for (i = 0; i < cnt; i++) {
struct xdp_frame *xdpf = bq->q[i];
prefetch(xdpf);
}
if (bq->xdp_prog) {
to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx);
if (!to_send)
goto out;
}
sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
if (sent < 0) {
/* If ndo_xdp_xmit fails with an errno, no frames have
* been xmit'ed.
*/
err = sent;
sent = 0;
}
/* If not all frames have been transmitted, it is our
* responsibility to free them
*/
for (i = sent; unlikely(i < to_send); i++)
xdp_return_frame_rx_napi(bq->q[i]);
out:
bq->count = 0;
trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
}
/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the
* driver before returning from its napi->poll() routine. See the comment above
* xdp_do_flush() in filter.c.
*/
void __dev_flush(struct list_head *flush_list)
{
struct xdp_dev_bulk_queue *bq, *tmp;
list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
bq_xmit_all(bq, XDP_XMIT_FLUSH);
bq->dev_rx = NULL;
bq->xdp_prog = NULL;
__list_del_clearprev(&bq->flush_node);
}
}
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
*/
static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *obj;
if (key >= map->max_entries)
return NULL;
obj = rcu_dereference_check(dtab->netdev_map[key],
rcu_read_lock_bh_held());
return obj;
}
/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
* variable access, and map elements stick around. See comment above
* xdp_do_flush() in filter.c.
*/
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx, struct bpf_prog *xdp_prog)
{
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
bq_xmit_all(bq, 0);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
* from net_device drivers NAPI func end.
*
* Do the same with xdp_prog and flush_list since these fields
* are only ever modified together.
*/
if (!bq->dev_rx) {
struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
bq->dev_rx = dev_rx;
bq->xdp_prog = xdp_prog;
list_add(&bq->flush_node, flush_list);
}
bq->q[bq->count++] = xdpf;
}
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx,
struct bpf_prog *xdp_prog)
{
int err;
if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
return -EOPNOTSUPP;
if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
xdp_frame_has_frags(xdpf)))
return -EOPNOTSUPP;
err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf));
if (unlikely(err))
return err;
bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
return 0;
}
static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst)
{
struct xdp_txq_info txq = { .dev = dst->dev };
struct xdp_buff xdp;
u32 act;
if (!dst->xdp_prog)
return XDP_PASS;
__skb_pull(skb, skb->mac_len);
xdp.txq = &txq;
act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog);
switch (act) {
case XDP_PASS:
__skb_push(skb, skb->mac_len);
break;
default:
bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dst->dev, dst->xdp_prog, act);
fallthrough;
case XDP_DROP:
kfree_skb(skb);
break;
}
return act;
}
int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
return __xdp_enqueue(dev, xdpf, dev_rx, NULL);
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
struct net_device *dev = dst->dev;
return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog);
}
static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf)
{
if (!obj)
return false;
if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
return false;
if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
xdp_frame_has_frags(xdpf)))
return false;
if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf)))
return false;
return true;
}
static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
struct net_device *dev_rx,
struct xdp_frame *xdpf)
{
struct xdp_frame *nxdpf;
nxdpf = xdpf_clone(xdpf);
if (!nxdpf)
return -ENOMEM;
bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
return 0;
}
static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex)
{
while (num_excluded--) {
if (ifindex == excluded[num_excluded])
return true;
}
return false;
}
/* Get ifindex of each upper device. 'indexes' must be able to hold at
* least MAX_NEST_DEV elements.
* Returns the number of ifindexes added.
*/
static int get_upper_ifindexes(struct net_device *dev, int *indexes)
{
struct net_device *upper;
struct list_head *iter;
int n = 0;
netdev_for_each_upper_dev_rcu(dev, upper, iter) {
indexes[n++] = upper->ifindex;
}
return n;
}
int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
struct bpf_map *map, bool exclude_ingress)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dst, *last_dst = NULL;
int excluded_devices[1+MAX_NEST_DEV];
struct hlist_head *head;
int num_excluded = 0;
unsigned int i;
int err;
if (exclude_ingress) {
num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
excluded_devices[num_excluded++] = dev_rx->ifindex;
}
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
dst = rcu_dereference_check(dtab->netdev_map[i],
rcu_read_lock_bh_held());
if (!is_valid_dst(dst, xdpf))
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
if (err)
return err;
last_dst = dst;
}
} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
for (i = 0; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_rcu(dst, head, index_hlist,
lockdep_is_held(&dtab->index_lock)) {
if (!is_valid_dst(dst, xdpf))
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded,
dst->dev->ifindex))
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
if (err)
return err;
last_dst = dst;
}
}
}
/* consume the last copy of the frame */
if (last_dst)
bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
else
xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
return 0;
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
const struct bpf_prog *xdp_prog)
{
int err;
err = xdp_ok_fwd_dev(dst->dev, skb->len);
if (unlikely(err))
return err;
/* Redirect has already succeeded semantically at this point, so we just
* return 0 even if packet is dropped. Helper below takes care of
* freeing skb.
*/
if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS)
return 0;
skb->dev = dst->dev;
generic_xdp_tx(skb, xdp_prog);
return 0;
}
static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
const struct bpf_prog *xdp_prog)
{
struct sk_buff *nskb;
int err;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
err = dev_map_generic_redirect(dst, nskb, xdp_prog);
if (unlikely(err)) {
consume_skb(nskb);
return err;
}
return 0;
}
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
const struct bpf_prog *xdp_prog,
struct bpf_map *map, bool exclude_ingress)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dst, *last_dst = NULL;
int excluded_devices[1+MAX_NEST_DEV];
struct hlist_head *head;
struct hlist_node *next;
int num_excluded = 0;
unsigned int i;
int err;
if (exclude_ingress) {
num_excluded = get_upper_ifindexes(dev, excluded_devices);
excluded_devices[num_excluded++] = dev->ifindex;
}
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
dst = rcu_dereference_check(dtab->netdev_map[i],
rcu_read_lock_bh_held());
if (!dst)
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
if (err)
return err;
last_dst = dst;
}
} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
for (i = 0; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dst, next, head, index_hlist) {
if (is_ifindex_excluded(excluded_devices, num_excluded,
dst->dev->ifindex))
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
if (err)
return err;
last_dst = dst;
}
}
}
/* consume the first skb and return */
if (last_dst)
return dev_map_generic_redirect(last_dst, skb, xdp_prog);
/* dtab is empty */
consume_skb(skb);
return 0;
}
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
return obj ? &obj->val : NULL;
}
static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
*(u32 *)key);
return obj ? &obj->val : NULL;
}
static void __dev_map_entry_free(struct rcu_head *rcu)
{
struct bpf_dtab_netdev *dev;
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
dev_put(dev->dev);
kfree(dev);
}
static long dev_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *old_dev;
u32 k = *(u32 *)key;
if (k >= map->max_entries)
return -EINVAL;
old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
if (old_dev) {
call_rcu(&old_dev->rcu, __dev_map_entry_free);
atomic_dec((atomic_t *)&dtab->items);
}
return 0;
}
static long dev_map_hash_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *old_dev;
u32 k = *(u32 *)key;
unsigned long flags;
int ret = -ENOENT;
spin_lock_irqsave(&dtab->index_lock, flags);
old_dev = __dev_map_hash_lookup_elem(map, k);
if (old_dev) {
dtab->items--;
hlist_del_init_rcu(&old_dev->index_hlist);
call_rcu(&old_dev->rcu, __dev_map_entry_free);
ret = 0;
}
spin_unlock_irqrestore(&dtab->index_lock, flags);
return ret;
}
static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
struct bpf_dtab *dtab,
struct bpf_devmap_val *val,
unsigned int idx)
{
struct bpf_prog *prog = NULL;
struct bpf_dtab_netdev *dev;
dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
GFP_NOWAIT | __GFP_NOWARN,
dtab->map.numa_node);
if (!dev)
return ERR_PTR(-ENOMEM);
dev->dev = dev_get_by_index(net, val->ifindex);
if (!dev->dev)
goto err_out;
if (val->bpf_prog.fd > 0) {
prog = bpf_prog_get_type_dev(val->bpf_prog.fd,
BPF_PROG_TYPE_XDP, false);
if (IS_ERR(prog))
goto err_put_dev;
if (prog->expected_attach_type != BPF_XDP_DEVMAP ||
!bpf_prog_map_compatible(&dtab->map, prog))
goto err_put_prog;
}
dev->idx = idx;
if (prog) {
dev->xdp_prog = prog;
dev->val.bpf_prog.id = prog->aux->id;
} else {
dev->xdp_prog = NULL;
dev->val.bpf_prog.id = 0;
}
dev->val.ifindex = val->ifindex;
return dev;
err_put_prog:
bpf_prog_put(prog);
err_put_dev:
dev_put(dev->dev);
err_out:
kfree(dev);
return ERR_PTR(-EINVAL);
}
static long __dev_map_update_elem(struct net *net, struct bpf_map *map,
void *key, void *value, u64 map_flags)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dev, *old_dev;
struct bpf_devmap_val val = {};
u32 i = *(u32 *)key;
if (unlikely(map_flags > BPF_EXIST))
return -EINVAL;
if (unlikely(i >= dtab->map.max_entries))
return -E2BIG;
if (unlikely(map_flags == BPF_NOEXIST))
return -EEXIST;
/* already verified value_size <= sizeof val */
memcpy(&val, value, map->value_size);
if (!val.ifindex) {
dev = NULL;
/* can not specify fd if ifindex is 0 */
if (val.bpf_prog.fd > 0)
return -EINVAL;
} else {
dev = __dev_map_alloc_node(net, dtab, &val, i);
if (IS_ERR(dev))
return PTR_ERR(dev);
}
/* Use call_rcu() here to ensure rcu critical sections have completed
* Remembering the driver side flush operation will happen before the
* net device is removed.
*/
old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
else
atomic_inc((atomic_t *)&dtab->items);
return 0;
}
static long dev_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
return __dev_map_update_elem(current->nsproxy->net_ns,
map, key, value, map_flags);
}
static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
void *key, void *value, u64 map_flags)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dev, *old_dev;
struct bpf_devmap_val val = {};
u32 idx = *(u32 *)key;
unsigned long flags;
int err = -EEXIST;
/* already verified value_size <= sizeof val */
memcpy(&val, value, map->value_size);
if (unlikely(map_flags > BPF_EXIST || !val.ifindex))
return -EINVAL;
spin_lock_irqsave(&dtab->index_lock, flags);
old_dev = __dev_map_hash_lookup_elem(map, idx);
if (old_dev && (map_flags & BPF_NOEXIST))
goto out_err;
dev = __dev_map_alloc_node(net, dtab, &val, idx);
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
goto out_err;
}
if (old_dev) {
hlist_del_rcu(&old_dev->index_hlist);
} else {
if (dtab->items >= dtab->map.max_entries) {
spin_unlock_irqrestore(&dtab->index_lock, flags);
call_rcu(&dev->rcu, __dev_map_entry_free);
return -E2BIG;
}
dtab->items++;
}
hlist_add_head_rcu(&dev->index_hlist,
dev_map_index_hash(dtab, idx));
spin_unlock_irqrestore(&dtab->index_lock, flags);
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
return 0;
out_err:
spin_unlock_irqrestore(&dtab->index_lock, flags);
return err;
}
static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
return __dev_map_hash_update_elem(current->nsproxy->net_ns,
map, key, value, map_flags);
}
static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags,
BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
__dev_map_lookup_elem);
}
static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags,
BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
__dev_map_hash_lookup_elem);
}
static u64 dev_map_mem_usage(const struct bpf_map *map)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
u64 usage = sizeof(struct bpf_dtab);
if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)
usage += (u64)dtab->n_buckets * sizeof(struct hlist_head);
else
usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *);
usage += atomic_read((atomic_t *)&dtab->items) *
(u64)sizeof(struct bpf_dtab_netdev);
return usage;
}
BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab)
const struct bpf_map_ops dev_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = dev_map_alloc_check,
.map_alloc = dev_map_alloc,
.map_free = dev_map_free,
.map_get_next_key = dev_map_get_next_key,
.map_lookup_elem = dev_map_lookup_elem,
.map_update_elem = dev_map_update_elem,
.map_delete_elem = dev_map_delete_elem,
.map_check_btf = map_check_no_btf,
.map_mem_usage = dev_map_mem_usage,
.map_btf_id = &dev_map_btf_ids[0],
.map_redirect = dev_map_redirect,
};
const struct bpf_map_ops dev_map_hash_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = dev_map_alloc_check,
.map_alloc = dev_map_alloc,
.map_free = dev_map_free,
.map_get_next_key = dev_map_hash_get_next_key,
.map_lookup_elem = dev_map_hash_lookup_elem,
.map_update_elem = dev_map_hash_update_elem,
.map_delete_elem = dev_map_hash_delete_elem,
.map_check_btf = map_check_no_btf,
.map_mem_usage = dev_map_mem_usage,
.map_btf_id = &dev_map_btf_ids[0],
.map_redirect = dev_hash_map_redirect,
};
static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
struct net_device *netdev)
{
unsigned long flags;
u32 i;
spin_lock_irqsave(&dtab->index_lock, flags);
for (i = 0; i < dtab->n_buckets; i++) {
struct bpf_dtab_netdev *dev;
struct hlist_head *head;
struct hlist_node *next;
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev)
continue;
dtab->items--;
hlist_del_rcu(&dev->index_hlist);
call_rcu(&dev->rcu, __dev_map_entry_free);
}
}
spin_unlock_irqrestore(&dtab->index_lock, flags);
}
static int dev_map_notification(struct notifier_block *notifier,
ulong event, void *ptr)
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
struct bpf_dtab *dtab;
int i, cpu;
switch (event) {
case NETDEV_REGISTER:
if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
break;
/* will be freed in free_netdev() */
netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue);
if (!netdev->xdp_bulkq)
return NOTIFY_BAD;
for_each_possible_cpu(cpu)
per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
break;
case NETDEV_UNREGISTER:
/* This rcu_read_lock/unlock pair is needed because
* dev_map_list is an RCU list AND to ensure a delete
* operation does not free a netdev_map entry while we
* are comparing it against the netdev being unregistered.
*/
rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) {
if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dev_map_hash_remove_netdev(dtab, netdev);
continue;
}
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev, *odev;
dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev)
continue;
odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) {
call_rcu(&dev->rcu,
__dev_map_entry_free);
atomic_dec((atomic_t *)&dtab->items);
}
}
}
rcu_read_unlock();
break;
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block dev_map_notifier = {
.notifier_call = dev_map_notification,
};
static int __init dev_map_init(void)
{
/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
offsetof(struct _bpf_dtab_netdev, dev));
register_netdevice_notifier(&dev_map_notifier);
return 0;
}
subsys_initcall(dev_map_init);
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
*/
#ifndef __ASM_CPUFEATURE_H
#define __ASM_CPUFEATURE_H
#include <asm/alternative-macros.h>
#include <asm/cpucaps.h>
#include <asm/cputype.h>
#include <asm/hwcap.h>
#include <asm/sysreg.h>
#define MAX_CPU_FEATURES 192
#define cpu_feature(x) KERNEL_HWCAP_ ## x
#define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0
#define ARM64_SW_FEATURE_OVERRIDE_HVHE 4
#define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8
#ifndef __ASSEMBLY__
#include <linux/bug.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/cpumask.h>
/*
* CPU feature register tracking
*
* The safe value of a CPUID feature field is dependent on the implications
* of the values assigned to it by the architecture. Based on the relationship
* between the values, the features are classified into 3 types - LOWER_SAFE,
* HIGHER_SAFE and EXACT.
*
* The lowest value of all the CPUs is chosen for LOWER_SAFE and highest
* for HIGHER_SAFE. It is expected that all CPUs have the same value for
* a field when EXACT is specified, failing which, the safe value specified
* in the table is chosen.
*/
enum ftr_type {
FTR_EXACT, /* Use a predefined safe value */
FTR_LOWER_SAFE, /* Smaller value is safe */
FTR_HIGHER_SAFE, /* Bigger value is safe */
FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */
};
#define FTR_STRICT true /* SANITY check strict matching required */
#define FTR_NONSTRICT false /* SANITY check ignored */
#define FTR_SIGNED true /* Value should be treated as signed */
#define FTR_UNSIGNED false /* Value should be treated as unsigned */
#define FTR_VISIBLE true /* Feature visible to the user space */
#define FTR_HIDDEN false /* Feature is hidden from the user */
#define FTR_VISIBLE_IF_IS_ENABLED(config) \
(IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN)
struct arm64_ftr_bits {
bool sign; /* Value is signed ? */
bool visible;
bool strict; /* CPU Sanity check: strict matching required ? */
enum ftr_type type;
u8 shift;
u8 width;
s64 safe_val; /* safe value for FTR_EXACT features */
};
/*
* Describe the early feature override to the core override code:
*
* @val Values that are to be merged into the final
* sanitised value of the register. Only the bitfields
* set to 1 in @mask are valid
* @mask Mask of the features that are overridden by @val
*
* A @mask field set to full-1 indicates that the corresponding field
* in @val is a valid override.
*
* A @mask field set to full-0 with the corresponding @val field set
* to full-0 denotes that this field has no override
*
* A @mask field set to full-0 with the corresponding @val field set
* to full-1 denotes that this field has an invalid override.
*/
struct arm64_ftr_override {
u64 val;
u64 mask;
};
/*
* @arm64_ftr_reg - Feature register
* @strict_mask Bits which should match across all CPUs for sanity.
* @sys_val Safe value across the CPUs (system view)
*/
struct arm64_ftr_reg {
const char *name;
u64 strict_mask;
u64 user_mask;
u64 sys_val;
u64 user_val;
struct arm64_ftr_override *override;
const struct arm64_ftr_bits *ftr_bits;
};
extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
/*
* CPU capabilities:
*
* We use arm64_cpu_capabilities to represent system features, errata work
* arounds (both used internally by kernel and tracked in system_cpucaps) and
* ELF HWCAPs (which are exposed to user).
*
* To support systems with heterogeneous CPUs, we need to make sure that we
* detect the capabilities correctly on the system and take appropriate
* measures to ensure there are no incompatibilities.
*
* This comment tries to explain how we treat the capabilities.
* Each capability has the following list of attributes :
*
* 1) Scope of Detection : The system detects a given capability by
* performing some checks at runtime. This could be, e.g, checking the
* value of a field in CPU ID feature register or checking the cpu
* model. The capability provides a call back ( @matches() ) to
* perform the check. Scope defines how the checks should be performed.
* There are three cases:
*
* a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one
* matches. This implies, we have to run the check on all the
* booting CPUs, until the system decides that state of the
* capability is finalised. (See section 2 below)
* Or
* b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs
* matches. This implies, we run the check only once, when the
* system decides to finalise the state of the capability. If the
* capability relies on a field in one of the CPU ID feature
* registers, we use the sanitised value of the register from the
* CPU feature infrastructure to make the decision.
* Or
* c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the
* feature. This category is for features that are "finalised"
* (or used) by the kernel very early even before the SMP cpus
* are brought up.
*
* The process of detection is usually denoted by "update" capability
* state in the code.
*
* 2) Finalise the state : The kernel should finalise the state of a
* capability at some point during its execution and take necessary
* actions if any. Usually, this is done, after all the boot-time
* enabled CPUs are brought up by the kernel, so that it can make
* better decision based on the available set of CPUs. However, there
* are some special cases, where the action is taken during the early
* boot by the primary boot CPU. (e.g, running the kernel at EL2 with
* Virtualisation Host Extensions). The kernel usually disallows any
* changes to the state of a capability once it finalises the capability
* and takes any action, as it may be impossible to execute the actions
* safely. A CPU brought up after a capability is "finalised" is
* referred to as "Late CPU" w.r.t the capability. e.g, all secondary
* CPUs are treated "late CPUs" for capabilities determined by the boot
* CPU.
*
* At the moment there are two passes of finalising the capabilities.
* a) Boot CPU scope capabilities - Finalised by primary boot CPU via
* setup_boot_cpu_capabilities().
* b) Everything except (a) - Run via setup_system_capabilities().
*
* 3) Verification: When a CPU is brought online (e.g, by user or by the
* kernel), the kernel should make sure that it is safe to use the CPU,
* by verifying that the CPU is compliant with the state of the
* capabilities finalised already. This happens via :
*
* secondary_start_kernel()-> check_local_cpu_capabilities()
*
* As explained in (2) above, capabilities could be finalised at
* different points in the execution. Each newly booted CPU is verified
* against the capabilities that have been finalised by the time it
* boots.
*
* a) SCOPE_BOOT_CPU : All CPUs are verified against the capability
* except for the primary boot CPU.
*
* b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the
* user after the kernel boot are verified against the capability.
*
* If there is a conflict, the kernel takes an action, based on the
* severity (e.g, a CPU could be prevented from booting or cause a
* kernel panic). The CPU is allowed to "affect" the state of the
* capability, if it has not been finalised already. See section 5
* for more details on conflicts.
*
* 4) Action: As mentioned in (2), the kernel can take an action for each
* detected capability, on all CPUs on the system. Appropriate actions
* include, turning on an architectural feature, modifying the control
* registers (e.g, SCTLR, TCR etc.) or patching the kernel via
* alternatives. The kernel patching is batched and performed at later
* point. The actions are always initiated only after the capability
* is finalised. This is usally denoted by "enabling" the capability.
* The actions are initiated as follows :
* a) Action is triggered on all online CPUs, after the capability is
* finalised, invoked within the stop_machine() context from
* enable_cpu_capabilitie().
*
* b) Any late CPU, brought up after (1), the action is triggered via:
*
* check_local_cpu_capabilities() -> verify_local_cpu_capabilities()
*
* 5) Conflicts: Based on the state of the capability on a late CPU vs.
* the system state, we could have the following combinations :
*
* x-----------------------------x
* | Type | System | Late CPU |
* |-----------------------------|
* | a | y | n |
* |-----------------------------|
* | b | n | y |
* x-----------------------------x
*
* Two separate flag bits are defined to indicate whether each kind of
* conflict can be allowed:
* ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed
* ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed
*
* Case (a) is not permitted for a capability that the system requires
* all CPUs to have in order for the capability to be enabled. This is
* typical for capabilities that represent enhanced functionality.
*
* Case (b) is not permitted for a capability that must be enabled
* during boot if any CPU in the system requires it in order to run
* safely. This is typical for erratum work arounds that cannot be
* enabled after the corresponding capability is finalised.
*
* In some non-typical cases either both (a) and (b), or neither,
* should be permitted. This can be described by including neither
* or both flags in the capability's type field.
*
* In case of a conflict, the CPU is prevented from booting. If the
* ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability,
* then a kernel panic is triggered.
*/
/*
* Decide how the capability is detected.
* On any local CPU vs System wide vs the primary boot CPU
*/
#define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0))
#define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1))
/*
* The capabilitiy is detected on the Boot CPU and is used by kernel
* during early boot. i.e, the capability should be "detected" and
* "enabled" as early as possibly on all booting CPUs.
*/
#define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2))
#define ARM64_CPUCAP_SCOPE_MASK \
(ARM64_CPUCAP_SCOPE_SYSTEM | \
ARM64_CPUCAP_SCOPE_LOCAL_CPU | \
ARM64_CPUCAP_SCOPE_BOOT_CPU)
#define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM
#define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU
#define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU
#define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK
/*
* Is it permitted for a late CPU to have this capability when system
* hasn't already enabled it ?
*/
#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4))
/* Is it safe for a late CPU to miss this capability when system has it */
#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5))
/* Panic when a conflict is detected */
#define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6))
/*
* CPU errata workarounds that need to be enabled at boot time if one or
* more CPUs in the system requires it. When one of these capabilities
* has been enabled, it is safe to allow any CPU to boot that doesn't
* require the workaround. However, it is not safe if a "late" CPU
* requires a workaround and the system hasn't enabled it already.
*/
#define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \
(ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU)
/*
* CPU feature detected at boot time based on system-wide value of a
* feature. It is safe for a late CPU to have this feature even though
* the system hasn't enabled it, although the feature will not be used
* by Linux in this case. If the system has enabled this feature already,
* then every late CPU must have it.
*/
#define ARM64_CPUCAP_SYSTEM_FEATURE \
(ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
/*
* CPU feature detected at boot time based on feature of one or more CPUs.
* All possible conflicts for a late CPU are ignored.
* NOTE: this means that a late CPU with the feature will *not* cause the
* capability to be advertised by cpus_have_*cap()!
*/
#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \
(ARM64_CPUCAP_SCOPE_LOCAL_CPU | \
ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \
ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
/*
* CPU feature detected at boot time, on one or more CPUs. A late CPU
* is not allowed to have the capability when the system doesn't have it.
* It is Ok for a late CPU to miss the feature.
*/
#define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \
(ARM64_CPUCAP_SCOPE_LOCAL_CPU | \
ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU)
/*
* CPU feature used early in the boot based on the boot CPU. All secondary
* CPUs must match the state of the capability as detected by the boot CPU. In
* case of a conflict, a kernel panic is triggered.
*/
#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \
(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT)
/*
* CPU feature used early in the boot based on the boot CPU. It is safe for a
* late CPU to have this feature even though the boot CPU hasn't enabled it,
* although the feature will not be used by Linux in this case. If the boot CPU
* has enabled this feature already, then every late CPU must have it.
*/
#define ARM64_CPUCAP_BOOT_CPU_FEATURE \
(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
struct arm64_cpu_capabilities {
const char *desc;
u16 capability;
u16 type;
bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
/*
* Take the appropriate actions to configure this capability
* for this CPU. If the capability is detected by the kernel
* this will be called on all the CPUs in the system,
* including the hotplugged CPUs, regardless of whether the
* capability is available on that specific CPU. This is
* useful for some capabilities (e.g, working around CPU
* errata), where all the CPUs must take some action (e.g,
* changing system control/configuration). Thus, if an action
* is required only if the CPU has the capability, then the
* routine must check it before taking any action.
*/
void (*cpu_enable)(const struct arm64_cpu_capabilities *cap);
union {
struct { /* To be used for erratum handling only */
struct midr_range midr_range;
const struct arm64_midr_revidr {
u32 midr_rv; /* revision/variant */
u32 revidr_mask;
} * const fixed_revs;
};
const struct midr_range *midr_range_list;
struct { /* Feature register checking */
u32 sys_reg;
u8 field_pos;
u8 field_width;
u8 min_field_value;
u8 max_field_value;
u8 hwcap_type;
bool sign;
unsigned long hwcap;
};
};
/*
* An optional list of "matches/cpu_enable" pair for the same
* "capability" of the same "type" as described by the parent.
* Only matches(), cpu_enable() and fields relevant to these
* methods are significant in the list. The cpu_enable is
* invoked only if the corresponding entry "matches()".
* However, if a cpu_enable() method is associated
* with multiple matches(), care should be taken that either
* the match criteria are mutually exclusive, or that the
* method is robust against being called multiple times.
*/
const struct arm64_cpu_capabilities *match_list;
const struct cpumask *cpus;
};
static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
{
return cap->type & ARM64_CPUCAP_SCOPE_MASK;
}
/*
* Generic helper for handling capabilities with multiple (match,enable) pairs
* of call backs, sharing the same capability bit.
* Iterate over each entry to see if at least one matches.
*/
static inline bool
cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry,
int scope)
{
const struct arm64_cpu_capabilities *caps;
for (caps = entry->match_list; caps->matches; caps++)
if (caps->matches(caps, scope))
return true;
return false;
}
static __always_inline bool is_vhe_hyp_code(void)
{
/* Only defined for code run in VHE hyp context */
return __is_defined(__KVM_VHE_HYPERVISOR__);
}
static __always_inline bool is_nvhe_hyp_code(void)
{
/* Only defined for code run in NVHE hyp context */
return __is_defined(__KVM_NVHE_HYPERVISOR__);
}
static __always_inline bool is_hyp_code(void)
{
return is_vhe_hyp_code() || is_nvhe_hyp_code();
}
extern DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS);
extern DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
#define for_each_available_cap(cap) \
for_each_set_bit(cap, system_cpucaps, ARM64_NCAPS)
bool this_cpu_has_cap(unsigned int cap);
void cpu_set_feature(unsigned int num);
bool cpu_have_feature(unsigned int num);
unsigned long cpu_get_elf_hwcap(void);
unsigned long cpu_get_elf_hwcap2(void);
unsigned long cpu_get_elf_hwcap3(void);
#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
static __always_inline bool boot_capabilities_finalized(void)
{
return alternative_has_cap_likely(ARM64_ALWAYS_BOOT);
}
static __always_inline bool system_capabilities_finalized(void)
{
return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM);
}
/*
* Test for a capability with a runtime check.
*
* Before the capability is detected, this returns false.
*/
static __always_inline bool cpus_have_cap(unsigned int num)
{
if (__builtin_constant_p(num) && !cpucap_is_possible(num))
return false;
if (num >= ARM64_NCAPS)
return false;
return arch_test_bit(num, system_cpucaps);
}
/*
* Test for a capability without a runtime check.
*
* Before boot capabilities are finalized, this will BUG().
* After boot capabilities are finalized, this is patched to avoid a runtime
* check.
*
* @num must be a compile-time constant.
*/
static __always_inline bool cpus_have_final_boot_cap(int num)
{
if (boot_capabilities_finalized())
return alternative_has_cap_unlikely(num);
else
BUG();
}
/*
* Test for a capability without a runtime check.
*
* Before system capabilities are finalized, this will BUG().
* After system capabilities are finalized, this is patched to avoid a runtime
* check.
*
* @num must be a compile-time constant.
*/
static __always_inline bool cpus_have_final_cap(int num)
{
if (system_capabilities_finalized()) return alternative_has_cap_unlikely(num);
else
BUG();
}
static inline int __attribute_const__
cpuid_feature_extract_signed_field_width(u64 features, int field, int width)
{
return (s64)(features << (64 - width - field)) >> (64 - width);
}
static inline int __attribute_const__
cpuid_feature_extract_signed_field(u64 features, int field)
{
return cpuid_feature_extract_signed_field_width(features, field, 4);
}
static __always_inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
{
return (u64)(features << (64 - width - field)) >> (64 - width);
}
static __always_inline unsigned int __attribute_const__
cpuid_feature_extract_unsigned_field(u64 features, int field)
{
return cpuid_feature_extract_unsigned_field_width(features, field, 4);
}
static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
{
return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
}
static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg)
{
return (reg->user_val | (reg->sys_val & reg->user_mask));
}
static inline int __attribute_const__
cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign)
{
if (WARN_ON_ONCE(!width))
width = 4;
return (sign) ?
cpuid_feature_extract_signed_field_width(features, field, width) :
cpuid_feature_extract_unsigned_field_width(features, field, width);
}
static inline int __attribute_const__
cpuid_feature_extract_field(u64 features, int field, bool sign)
{
return cpuid_feature_extract_field_width(features, field, 4, sign);
}
static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
{
return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign);
}
static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
{
return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 ||
cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1;
}
static inline bool id_aa64pfr0_32bit_el1(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT);
return val == ID_AA64PFR0_EL1_EL1_AARCH32;
}
static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT);
return val == ID_AA64PFR0_EL1_EL0_AARCH32;
}
static inline bool id_aa64pfr0_sve(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT);
return val > 0;
}
static inline bool id_aa64pfr1_sme(u64 pfr1)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT);
return val > 0;
}
static inline bool id_aa64pfr0_mpam(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT);
return val > 0;
}
static inline bool id_aa64pfr1_mte(u64 pfr1)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT);
return val >= ID_AA64PFR1_EL1_MTE_MTE2;
}
void __init setup_boot_cpu_features(void);
void __init setup_system_features(void);
void __init setup_user_features(void);
void check_local_cpu_capabilities(void);
u64 read_sanitised_ftr_reg(u32 id);
u64 __read_sysreg_by_encoding(u32 sys_id);
static inline bool cpu_supports_mixed_endian_el0(void)
{
return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
}
static inline bool supports_csv2p3(int scope)
{
u64 pfr0;
u8 csv2_val;
if (scope == SCOPE_LOCAL_CPU)
pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
else
pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
csv2_val = cpuid_feature_extract_unsigned_field(pfr0,
ID_AA64PFR0_EL1_CSV2_SHIFT);
return csv2_val == 3;
}
static inline bool supports_clearbhb(int scope)
{
u64 isar2;
if (scope == SCOPE_LOCAL_CPU)
isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
else
isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
return cpuid_feature_extract_unsigned_field(isar2,
ID_AA64ISAR2_EL1_CLRBHB_SHIFT);
}
const struct cpumask *system_32bit_el0_cpumask(void);
const struct cpumask *fallback_32bit_el0_cpumask(void);
DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
static inline bool system_supports_32bit_el0(void)
{
u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
return static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
id_aa64pfr0_32bit_el0(pfr0);
}
static inline bool system_supports_4kb_granule(void)
{
u64 mmfr0;
u32 val;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_TGRAN4_SHIFT);
return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) &&
(val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX);
}
static inline bool system_supports_64kb_granule(void)
{
u64 mmfr0;
u32 val;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_TGRAN64_SHIFT);
return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) &&
(val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX);
}
static inline bool system_supports_16kb_granule(void)
{
u64 mmfr0;
u32 val;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_TGRAN16_SHIFT);
return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) &&
(val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX);
}
static inline bool system_supports_mixed_endian_el0(void)
{
return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1));
}
static inline bool system_supports_mixed_endian(void)
{
u64 mmfr0;
u32 val;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_BIGEND_SHIFT);
return val == 0x1;
}
static __always_inline bool system_supports_fpsimd(void)
{
return alternative_has_cap_likely(ARM64_HAS_FPSIMD);
}
static inline bool system_uses_hw_pan(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_PAN);
}
static inline bool system_uses_ttbr0_pan(void)
{
return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
!system_uses_hw_pan();
}
static __always_inline bool system_supports_sve(void)
{
return alternative_has_cap_unlikely(ARM64_SVE);
}
static __always_inline bool system_supports_sme(void)
{
return alternative_has_cap_unlikely(ARM64_SME);
}
static __always_inline bool system_supports_sme2(void)
{
return alternative_has_cap_unlikely(ARM64_SME2);
}
static __always_inline bool system_supports_fa64(void)
{
return alternative_has_cap_unlikely(ARM64_SME_FA64);
}
static __always_inline bool system_supports_tpidr2(void)
{
return system_supports_sme();
}
static __always_inline bool system_supports_fpmr(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_FPMR);
}
static __always_inline bool system_supports_cnp(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_CNP);
}
static inline bool system_supports_address_auth(void)
{
return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH);
}
static inline bool system_supports_generic_auth(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH);
}
static inline bool system_has_full_ptr_auth(void)
{
return system_supports_address_auth() && system_supports_generic_auth();
}
static __always_inline bool system_uses_irq_prio_masking(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
}
static inline bool system_supports_mte(void)
{
return alternative_has_cap_unlikely(ARM64_MTE);
}
static inline bool system_has_prio_mask_debugging(void)
{
return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) &&
system_uses_irq_prio_masking();
}
static inline bool system_supports_bti(void)
{
return cpus_have_final_cap(ARM64_BTI);
}
static inline bool system_supports_bti_kernel(void)
{
return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
cpus_have_final_boot_cap(ARM64_BTI);
}
static inline bool system_supports_tlb_range(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE);
}
static inline bool system_supports_lpa2(void)
{
return cpus_have_final_cap(ARM64_HAS_LPA2);
}
static inline bool system_supports_poe(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_S1POE);
}
static inline bool system_supports_gcs(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_GCS);
}
static inline bool system_supports_haft(void)
{
return cpus_have_final_cap(ARM64_HAFT);
}
static __always_inline bool system_supports_mpam(void)
{
return alternative_has_cap_unlikely(ARM64_MPAM);
}
static __always_inline bool system_supports_mpam_hcr(void)
{
return alternative_has_cap_unlikely(ARM64_MPAM_HCR);
}
static inline bool system_supports_pmuv3(void)
{
return cpus_have_final_cap(ARM64_HAS_PMUV3);
}
int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
{
switch (parange) {
case ID_AA64MMFR0_EL1_PARANGE_32: return 32;
case ID_AA64MMFR0_EL1_PARANGE_36: return 36;
case ID_AA64MMFR0_EL1_PARANGE_40: return 40;
case ID_AA64MMFR0_EL1_PARANGE_42: return 42;
case ID_AA64MMFR0_EL1_PARANGE_44: return 44;
case ID_AA64MMFR0_EL1_PARANGE_48: return 48;
case ID_AA64MMFR0_EL1_PARANGE_52: return 52;
/*
* A future PE could use a value unknown to the kernel.
* However, by the "D10.1.4 Principles of the ID scheme
* for fields in ID registers", ARM DDI 0487C.a, any new
* value is guaranteed to be higher than what we know already.
* As a safe limit, we return the limit supported by the kernel.
*/
default: return CONFIG_ARM64_PA_BITS;
}
}
/* Check whether hardware update of the Access flag is supported */
static inline bool cpu_has_hw_af(void)
{
u64 mmfr1;
if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
return false;
/*
* Use cached version to avoid emulated msr operation on KVM
* guests.
*/
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
return cpuid_feature_extract_unsigned_field(mmfr1,
ID_AA64MMFR1_EL1_HAFDBS_SHIFT);
}
static inline bool cpu_has_pan(void)
{
u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
return cpuid_feature_extract_unsigned_field(mmfr1,
ID_AA64MMFR1_EL1_PAN_SHIFT);
}
#ifdef CONFIG_ARM64_AMU_EXTN
/* Check whether the cpu supports the Activity Monitors Unit (AMU) */
extern bool cpu_has_amu_feat(int cpu);
#else
static inline bool cpu_has_amu_feat(int cpu)
{
return false;
}
#endif
/* Get a cpu that supports the Activity Monitors Unit (AMU) */
extern int get_cpu_with_amu_feat(void);
static inline unsigned int get_vmid_bits(u64 mmfr1)
{
int vmid_bits;
vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1,
ID_AA64MMFR1_EL1_VMIDBits_SHIFT);
if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16)
return 16;
/*
* Return the default here even if any reserved
* value is fetched from the system register.
*/
return 8;
}
s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur);
struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id);
extern struct arm64_ftr_override id_aa64mmfr0_override;
extern struct arm64_ftr_override id_aa64mmfr1_override;
extern struct arm64_ftr_override id_aa64mmfr2_override;
extern struct arm64_ftr_override id_aa64pfr0_override;
extern struct arm64_ftr_override id_aa64pfr1_override;
extern struct arm64_ftr_override id_aa64zfr0_override;
extern struct arm64_ftr_override id_aa64smfr0_override;
extern struct arm64_ftr_override id_aa64isar1_override;
extern struct arm64_ftr_override id_aa64isar2_override;
extern struct arm64_ftr_override arm64_sw_feature_override;
static inline
u64 arm64_apply_feature_override(u64 val, int feat, int width,
const struct arm64_ftr_override *override)
{
u64 oval = override->val;
/*
* When it encounters an invalid override (e.g., an override that
* cannot be honoured due to a missing CPU feature), the early idreg
* override code will set the mask to 0x0 and the value to non-zero for
* the field in question. In order to determine whether the override is
* valid or not for the field we are interested in, we first need to
* disregard bits belonging to other fields.
*/
oval &= GENMASK_ULL(feat + width - 1, feat);
/*
* The override is valid if all value bits are accounted for in the
* mask. If so, replace the masked bits with the override value.
*/
if (oval == (oval & override->mask)) {
val &= ~override->mask;
val |= oval;
}
/* Extract the field from the updated value */
return cpuid_feature_extract_unsigned_field(val, feat);
}
static inline bool arm64_test_sw_feature_override(int feat)
{
/*
* Software features are pseudo CPU features that have no underlying
* CPUID system register value to apply the override to.
*/
return arm64_apply_feature_override(0, feat, 4,
&arm64_sw_feature_override);
}
static inline bool kaslr_disabled_cmdline(void)
{
return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR);
}
u32 get_kvm_ipa_limit(void);
void dump_cpu_features(void);
static inline bool cpu_has_bti(void)
{
if (!IS_ENABLED(CONFIG_ARM64_BTI))
return false;
return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1),
ID_AA64PFR1_EL1_BT_SHIFT, 4,
&id_aa64pfr1_override);
}
static inline bool cpu_has_pac(void)
{
u64 isar1, isar2;
if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH))
return false;
isar1 = read_cpuid(ID_AA64ISAR1_EL1);
isar2 = read_cpuid(ID_AA64ISAR2_EL1);
if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4,
&id_aa64isar1_override))
return true;
if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4,
&id_aa64isar1_override))
return true;
return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4,
&id_aa64isar2_override);
}
static inline bool cpu_has_lva(void)
{
u64 mmfr2;
mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1);
mmfr2 &= ~id_aa64mmfr2_override.mask;
mmfr2 |= id_aa64mmfr2_override.val;
return cpuid_feature_extract_unsigned_field(mmfr2,
ID_AA64MMFR2_EL1_VARange_SHIFT);
}
static inline bool cpu_has_lpa2(void)
{
#ifdef CONFIG_ARM64_LPA2
u64 mmfr0;
int feat;
mmfr0 = read_sysreg(id_aa64mmfr0_el1);
mmfr0 &= ~id_aa64mmfr0_override.mask;
mmfr0 |= id_aa64mmfr0_override.val;
feat = cpuid_feature_extract_signed_field(mmfr0,
ID_AA64MMFR0_EL1_TGRAN_SHIFT);
return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2;
#else
return false;
#endif
}
#endif /* __ASSEMBLY__ */
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_DCACHE_H
#define __LINUX_DCACHE_H
#include <linux/atomic.h>
#include <linux/list.h>
#include <linux/math.h>
#include <linux/rculist.h>
#include <linux/rculist_bl.h>
#include <linux/spinlock.h>
#include <linux/seqlock.h>
#include <linux/cache.h>
#include <linux/rcupdate.h>
#include <linux/lockref.h>
#include <linux/stringhash.h>
#include <linux/wait.h>
struct path;
struct file;
struct vfsmount;
/*
* linux/include/linux/dcache.h
*
* Dirent cache data structures
*
* (C) Copyright 1997 Thomas Schoebel-Theuer,
* with heavy changes by Linus Torvalds
*/
#define IS_ROOT(x) ((x) == (x)->d_parent)
/* The hash is always the low bits of hash_len */
#ifdef __LITTLE_ENDIAN
#define HASH_LEN_DECLARE u32 hash; u32 len
#define bytemask_from_count(cnt) (~(~0ul << (cnt)*8))
#else
#define HASH_LEN_DECLARE u32 len; u32 hash
#define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8))
#endif
/*
* "quick string" -- eases parameter passing, but more importantly
* saves "metadata" about the string (ie length and the hash).
*
* hash comes first so it snuggles against d_parent in the
* dentry.
*/
struct qstr {
union {
struct {
HASH_LEN_DECLARE;
};
u64 hash_len;
};
const unsigned char *name;
};
#define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n))
extern const struct qstr empty_name;
extern const struct qstr slash_name;
extern const struct qstr dotdot_name;
/*
* Try to keep struct dentry aligned on 64 byte cachelines (this will
* give reasonable cacheline footprint with larger lines without the
* large memory footprint increase).
*/
#ifdef CONFIG_64BIT
# define DNAME_INLINE_WORDS 5 /* 192 bytes */
#else
# ifdef CONFIG_SMP
# define DNAME_INLINE_WORDS 9 /* 128 bytes */
# else
# define DNAME_INLINE_WORDS 11 /* 128 bytes */
# endif
#endif
#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long))
union shortname_store {
unsigned char string[DNAME_INLINE_LEN];
unsigned long words[DNAME_INLINE_WORDS];
};
#define d_lock d_lockref.lock
#define d_iname d_shortname.string
struct dentry {
/* RCU lookup touched fields */
unsigned int d_flags; /* protected by d_lock */
seqcount_spinlock_t d_seq; /* per dentry seqlock */
struct hlist_bl_node d_hash; /* lookup hash list */
struct dentry *d_parent; /* parent directory */
struct qstr d_name;
struct inode *d_inode; /* Where the name belongs to - NULL is
* negative */
union shortname_store d_shortname;
/* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */
/* Ref lookup also touches following */
const struct dentry_operations *d_op;
struct super_block *d_sb; /* The root of the dentry tree */
unsigned long d_time; /* used by d_revalidate */
void *d_fsdata; /* fs-specific data */
/* --- cacheline 2 boundary (128 bytes) --- */
struct lockref d_lockref; /* per-dentry lock and refcount
* keep separate from RCU lookup area if
* possible!
*/
union {
struct list_head d_lru; /* LRU list */
wait_queue_head_t *d_wait; /* in-lookup ones only */
};
struct hlist_node d_sib; /* child of parent list */
struct hlist_head d_children; /* our children */
/*
* d_alias and d_rcu can share memory
*/
union {
struct hlist_node d_alias; /* inode alias list */
struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */
struct rcu_head d_rcu;
} d_u;
};
/*
* dentry->d_lock spinlock nesting subclasses:
*
* 0: normal
* 1: nested
*/
enum dentry_d_lock_class
{
DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */
DENTRY_D_LOCK_NESTED
};
enum d_real_type {
D_REAL_DATA,
D_REAL_METADATA,
};
struct dentry_operations {
int (*d_revalidate)(struct inode *, const struct qstr *,
struct dentry *, unsigned int);
int (*d_weak_revalidate)(struct dentry *, unsigned int);
int (*d_hash)(const struct dentry *, struct qstr *);
int (*d_compare)(const struct dentry *,
unsigned int, const char *, const struct qstr *);
int (*d_delete)(const struct dentry *);
int (*d_init)(struct dentry *);
void (*d_release)(struct dentry *);
void (*d_prune)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
struct vfsmount *(*d_automount)(struct path *);
int (*d_manage)(const struct path *, bool);
struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
bool (*d_unalias_trylock)(const struct dentry *);
void (*d_unalias_unlock)(const struct dentry *);
} ____cacheline_aligned;
/*
* Locking rules for dentry_operations callbacks are to be found in
* Documentation/filesystems/locking.rst. Keep it updated!
*
* FUrther descriptions are found in Documentation/filesystems/vfs.rst.
* Keep it updated too!
*/
/* d_flags entries */
enum dentry_flags {
DCACHE_OP_HASH = BIT(0),
DCACHE_OP_COMPARE = BIT(1),
DCACHE_OP_REVALIDATE = BIT(2),
DCACHE_OP_DELETE = BIT(3),
DCACHE_OP_PRUNE = BIT(4),
/*
* This dentry is possibly not currently connected to the dcache tree,
* in which case its parent will either be itself, or will have this
* flag as well. nfsd will not use a dentry with this bit set, but will
* first endeavour to clear the bit either by discovering that it is
* connected, or by performing lookup operations. Any filesystem which
* supports nfsd_operations MUST have a lookup function which, if it
* finds a directory inode with a DCACHE_DISCONNECTED dentry, will
* d_move that dentry into place and return that dentry rather than the
* passed one, typically using d_splice_alias.
*/
DCACHE_DISCONNECTED = BIT(5),
DCACHE_REFERENCED = BIT(6), /* Recently used, don't discard. */
DCACHE_DONTCACHE = BIT(7), /* Purge from memory on final dput() */
DCACHE_CANT_MOUNT = BIT(8),
DCACHE_GENOCIDE = BIT(9),
DCACHE_SHRINK_LIST = BIT(10),
DCACHE_OP_WEAK_REVALIDATE = BIT(11),
/*
* this dentry has been "silly renamed" and has to be deleted on the
* last dput()
*/
DCACHE_NFSFS_RENAMED = BIT(12),
DCACHE_FSNOTIFY_PARENT_WATCHED = BIT(13), /* Parent inode is watched by some fsnotify listener */
DCACHE_DENTRY_KILLED = BIT(14),
DCACHE_MOUNTED = BIT(15), /* is a mountpoint */
DCACHE_NEED_AUTOMOUNT = BIT(16), /* handle automount on this dir */
DCACHE_MANAGE_TRANSIT = BIT(17), /* manage transit from this dirent */
DCACHE_LRU_LIST = BIT(18),
DCACHE_ENTRY_TYPE = (7 << 19), /* bits 19..21 are for storing type: */
DCACHE_MISS_TYPE = (0 << 19), /* Negative dentry */
DCACHE_WHITEOUT_TYPE = (1 << 19), /* Whiteout dentry (stop pathwalk) */
DCACHE_DIRECTORY_TYPE = (2 << 19), /* Normal directory */
DCACHE_AUTODIR_TYPE = (3 << 19), /* Lookupless directory (presumed automount) */
DCACHE_REGULAR_TYPE = (4 << 19), /* Regular file type */
DCACHE_SPECIAL_TYPE = (5 << 19), /* Other file type */
DCACHE_SYMLINK_TYPE = (6 << 19), /* Symlink */
DCACHE_NOKEY_NAME = BIT(22), /* Encrypted name encoded without key */
DCACHE_OP_REAL = BIT(23),
DCACHE_PAR_LOOKUP = BIT(24), /* being looked up (with parent locked shared) */
DCACHE_DENTRY_CURSOR = BIT(25),
DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */
};
#define DCACHE_MANAGED_DENTRY \
(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
extern seqlock_t rename_lock;
/*
* These are the low-level FS interfaces to the dcache..
*/
extern void d_instantiate(struct dentry *, struct inode *);
extern void d_instantiate_new(struct dentry *, struct inode *);
extern void __d_drop(struct dentry *dentry);
extern void d_drop(struct dentry *dentry);
extern void d_delete(struct dentry *);
extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op);
/* allocate/de-allocate */
extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
extern struct dentry * d_alloc_anon(struct super_block *);
extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
wait_queue_head_t *);
extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
const struct qstr *name);
extern struct dentry *d_find_any_alias(struct inode *inode);
extern struct dentry * d_obtain_alias(struct inode *);
extern struct dentry * d_obtain_root(struct inode *);
extern void shrink_dcache_sb(struct super_block *);
extern void shrink_dcache_parent(struct dentry *);
extern void d_invalidate(struct dentry *);
/* only used at mount-time */
extern struct dentry * d_make_root(struct inode *);
extern void d_mark_tmpfile(struct file *, struct inode *);
extern void d_tmpfile(struct file *, struct inode *);
extern struct dentry *d_find_alias(struct inode *);
extern void d_prune_aliases(struct inode *);
extern struct dentry *d_find_alias_rcu(struct inode *);
/* test whether we have any submounts in a subdir tree */
extern int path_has_submounts(const struct path *);
/*
* This adds the entry to the hash queues.
*/
extern void d_rehash(struct dentry *);
extern void d_add(struct dentry *, struct inode *);
/* used for rename() and baskets */
extern void d_move(struct dentry *, struct dentry *);
extern void d_exchange(struct dentry *, struct dentry *);
extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
extern struct dentry *d_lookup(const struct dentry *, const struct qstr *);
extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *);
static inline unsigned d_count(const struct dentry *dentry)
{
return dentry->d_lockref.count;
}
ino_t d_parent_ino(struct dentry *dentry);
/*
* helper function for dentry_operations.d_dname() members
*/
extern __printf(3, 4)
char *dynamic_dname(char *, int, const char *, ...);
extern char *__d_path(const struct path *, const struct path *, char *, int);
extern char *d_absolute_path(const struct path *, char *, int);
extern char *d_path(const struct path *, char *, int);
extern char *dentry_path_raw(const struct dentry *, char *, int);
extern char *dentry_path(const struct dentry *, char *, int);
/* Allocation counts.. */
/**
* dget_dlock - get a reference to a dentry
* @dentry: dentry to get a reference to
*
* Given a live dentry, increment the reference count and return the dentry.
* Caller must hold @dentry->d_lock. Making sure that dentry is alive is
* caller's resonsibility. There are many conditions sufficient to guarantee
* that; e.g. anything with non-negative refcount is alive, so's anything
* hashed, anything positive, anyone's parent, etc.
*/
static inline struct dentry *dget_dlock(struct dentry *dentry)
{
dentry->d_lockref.count++;
return dentry;
}
/**
* dget - get a reference to a dentry
* @dentry: dentry to get a reference to
*
* Given a dentry or %NULL pointer increment the reference count
* if appropriate and return the dentry. A dentry will not be
* destroyed when it has references. Conversely, a dentry with
* no references can disappear for any number of reasons, starting
* with memory pressure. In other words, that primitive is
* used to clone an existing reference; using it on something with
* zero refcount is a bug.
*
* NOTE: it will spin if @dentry->d_lock is held. From the deadlock
* avoidance point of view it is equivalent to spin_lock()/increment
* refcount/spin_unlock(), so calling it under @dentry->d_lock is
* always a bug; so's calling it under ->d_lock on any of its descendents.
*
*/
static inline struct dentry *dget(struct dentry *dentry)
{
if (dentry) lockref_get(&dentry->d_lockref);
return dentry;
}
extern struct dentry *dget_parent(struct dentry *dentry);
/**
* d_unhashed - is dentry hashed
* @dentry: entry to check
*
* Returns true if the dentry passed is not currently hashed.
*/
static inline int d_unhashed(const struct dentry *dentry)
{
return hlist_bl_unhashed(&dentry->d_hash);
}
static inline int d_unlinked(const struct dentry *dentry)
{
return d_unhashed(dentry) && !IS_ROOT(dentry);
}
static inline int cant_mount(const struct dentry *dentry)
{
return (dentry->d_flags & DCACHE_CANT_MOUNT);
}
static inline void dont_mount(struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
dentry->d_flags |= DCACHE_CANT_MOUNT;
spin_unlock(&dentry->d_lock);
}
extern void __d_lookup_unhash_wake(struct dentry *dentry);
static inline int d_in_lookup(const struct dentry *dentry)
{
return dentry->d_flags & DCACHE_PAR_LOOKUP;
}
static inline void d_lookup_done(struct dentry *dentry)
{
if (unlikely(d_in_lookup(dentry))) __d_lookup_unhash_wake(dentry);
}
extern void dput(struct dentry *);
static inline bool d_managed(const struct dentry *dentry)
{
return dentry->d_flags & DCACHE_MANAGED_DENTRY;
}
static inline bool d_mountpoint(const struct dentry *dentry)
{
return dentry->d_flags & DCACHE_MOUNTED;
}
/*
* Directory cache entry type accessor functions.
*/
static inline unsigned __d_entry_type(const struct dentry *dentry)
{
return dentry->d_flags & DCACHE_ENTRY_TYPE;
}
static inline bool d_is_miss(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_MISS_TYPE;
}
static inline bool d_is_whiteout(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE;
}
static inline bool d_can_lookup(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
}
static inline bool d_is_autodir(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
}
static inline bool d_is_dir(const struct dentry *dentry)
{
return d_can_lookup(dentry) || d_is_autodir(dentry);
}
static inline bool d_is_symlink(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;
}
static inline bool d_is_reg(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE;
}
static inline bool d_is_special(const struct dentry *dentry)
{
return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE;
}
static inline bool d_is_file(const struct dentry *dentry)
{
return d_is_reg(dentry) || d_is_special(dentry);
}
static inline bool d_is_negative(const struct dentry *dentry)
{
// TODO: check d_is_whiteout(dentry) also.
return d_is_miss(dentry);
}
static inline bool d_flags_negative(unsigned flags)
{
return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE;
}
static inline bool d_is_positive(const struct dentry *dentry)
{
return !d_is_negative(dentry);
}
/**
* d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs)
* @dentry: The dentry in question
*
* Returns true if the dentry represents either an absent name or a name that
* doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent
* a true miss, a whiteout that isn't represented by a 0,0 chardev or a
* fallthrough marker in an opaque directory.
*
* Note! (1) This should be used *only* by a filesystem to examine its own
* dentries. It should not be used to look at some other filesystem's
* dentries. (2) It should also be used in combination with d_inode() to get
* the inode. (3) The dentry may have something attached to ->d_lower and the
* type field of the flags may be set to something other than miss or whiteout.
*/
static inline bool d_really_is_negative(const struct dentry *dentry)
{
return dentry->d_inode == NULL;
}
/**
* d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs)
* @dentry: The dentry in question
*
* Returns true if the dentry represents a name that maps to an inode
* (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if
* that is represented on medium as a 0,0 chardev.
*
* Note! (1) This should be used *only* by a filesystem to examine its own
* dentries. It should not be used to look at some other filesystem's
* dentries. (2) It should also be used in combination with d_inode() to get
* the inode.
*/
static inline bool d_really_is_positive(const struct dentry *dentry)
{
return dentry->d_inode != NULL;
}
static inline int simple_positive(const struct dentry *dentry)
{
return d_really_is_positive(dentry) && !d_unhashed(dentry);
}
unsigned long vfs_pressure_ratio(unsigned long val);
/**
* d_inode - Get the actual inode of this dentry
* @dentry: The dentry to query
*
* This is the helper normal filesystems should use to get at their own inodes
* in their own dentries and ignore the layering superimposed upon them.
*/
static inline struct inode *d_inode(const struct dentry *dentry)
{
return dentry->d_inode;
}
/**
* d_inode_rcu - Get the actual inode of this dentry with READ_ONCE()
* @dentry: The dentry to query
*
* This is the helper normal filesystems should use to get at their own inodes
* in their own dentries and ignore the layering superimposed upon them.
*/
static inline struct inode *d_inode_rcu(const struct dentry *dentry)
{
return READ_ONCE(dentry->d_inode);
}
/**
* d_backing_inode - Get upper or lower inode we should be using
* @upper: The upper layer
*
* This is the helper that should be used to get at the inode that will be used
* if this dentry were to be opened as a file. The inode may be on the upper
* dentry or it may be on a lower dentry pinned by the upper.
*
* Normal filesystems should not use this to access their own inodes.
*/
static inline struct inode *d_backing_inode(const struct dentry *upper)
{
struct inode *inode = upper->d_inode;
return inode;
}
/**
* d_real - Return the real dentry
* @dentry: the dentry to query
* @type: the type of real dentry (data or metadata)
*
* If dentry is on a union/overlay, then return the underlying, real dentry.
* Otherwise return the dentry itself.
*
* See also: Documentation/filesystems/vfs.rst
*/
static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type)
{
if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, type);
else
return dentry;
}
/**
* d_real_inode - Return the real inode hosting the data
* @dentry: The dentry to query
*
* If dentry is on a union/overlay, then return the underlying, real inode.
* Otherwise return d_inode().
*/
static inline struct inode *d_real_inode(const struct dentry *dentry)
{
/* This usage of d_real() results in const dentry */
return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA));
}
struct name_snapshot {
struct qstr name;
union shortname_store inline_name;
};
void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
void release_dentry_name_snapshot(struct name_snapshot *);
static inline struct dentry *d_first_child(const struct dentry *dentry)
{
return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib);
}
static inline struct dentry *d_next_sibling(const struct dentry *dentry)
{
return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
}
#endif /* __LINUX_DCACHE_H */
// SPDX-License-Identifier: GPL-2.0
/*
* drivers/base/core.c - core driver model code (device registration, etc)
*
* Copyright (c) 2002-3 Patrick Mochel
* Copyright (c) 2002-3 Open Source Development Labs
* Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2006 Novell, Inc.
*/
#include <linux/acpi.h>
#include <linux/blkdev.h>
#include <linux/cleanup.h>
#include <linux/cpufreq.h>
#include <linux/device.h>
#include <linux/dma-map-ops.h> /* for dma_default_coherent */
#include <linux/err.h>
#include <linux/fwnode.h>
#include <linux/init.h>
#include <linux/kdev_t.h>
#include <linux/kstrtox.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/notifier.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/pm_runtime.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/string_helpers.h>
#include <linux/swiotlb.h>
#include <linux/sysfs.h>
#include "base.h"
#include "physical_location.h"
#include "power/power.h"
/* Device links support. */
static LIST_HEAD(deferred_sync);
static unsigned int defer_sync_state_count = 1;
static DEFINE_MUTEX(fwnode_link_lock);
static bool fw_devlink_is_permissive(void);
static void __fw_devlink_link_to_consumers(struct device *dev);
static bool fw_devlink_drv_reg_done;
static bool fw_devlink_best_effort;
static struct workqueue_struct *device_link_wq;
/**
* __fwnode_link_add - Create a link between two fwnode_handles.
* @con: Consumer end of the link.
* @sup: Supplier end of the link.
* @flags: Link flags.
*
* Create a fwnode link between fwnode handles @con and @sup. The fwnode link
* represents the detail that the firmware lists @sup fwnode as supplying a
* resource to @con.
*
* The driver core will use the fwnode link to create a device link between the
* two device objects corresponding to @con and @sup when they are created. The
* driver core will automatically delete the fwnode link between @con and @sup
* after doing that.
*
* Attempts to create duplicate links between the same pair of fwnode handles
* are ignored and there is no reference counting.
*/
static int __fwnode_link_add(struct fwnode_handle *con,
struct fwnode_handle *sup, u8 flags)
{
struct fwnode_link *link;
list_for_each_entry(link, &sup->consumers, s_hook)
if (link->consumer == con) {
link->flags |= flags;
return 0;
}
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link)
return -ENOMEM;
link->supplier = sup;
INIT_LIST_HEAD(&link->s_hook);
link->consumer = con;
INIT_LIST_HEAD(&link->c_hook);
link->flags = flags;
list_add(&link->s_hook, &sup->consumers);
list_add(&link->c_hook, &con->suppliers);
pr_debug("%pfwf Linked as a fwnode consumer to %pfwf\n",
con, sup);
return 0;
}
int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup,
u8 flags)
{
guard(mutex)(&fwnode_link_lock);
return __fwnode_link_add(con, sup, flags);
}
/**
* __fwnode_link_del - Delete a link between two fwnode_handles.
* @link: the fwnode_link to be deleted
*
* The fwnode_link_lock needs to be held when this function is called.
*/
static void __fwnode_link_del(struct fwnode_link *link)
{
pr_debug("%pfwf Dropping the fwnode link to %pfwf\n",
link->consumer, link->supplier);
list_del(&link->s_hook);
list_del(&link->c_hook);
kfree(link);
}
/**
* __fwnode_link_cycle - Mark a fwnode link as being part of a cycle.
* @link: the fwnode_link to be marked
*
* The fwnode_link_lock needs to be held when this function is called.
*/
static void __fwnode_link_cycle(struct fwnode_link *link)
{
pr_debug("%pfwf: cycle: depends on %pfwf\n",
link->consumer, link->supplier);
link->flags |= FWLINK_FLAG_CYCLE;
}
/**
* fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle.
* @fwnode: fwnode whose supplier links need to be deleted
*
* Deletes all supplier links connecting directly to @fwnode.
*/
static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode)
{
struct fwnode_link *link, *tmp;
guard(mutex)(&fwnode_link_lock);
list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook)
__fwnode_link_del(link);
}
/**
* fwnode_links_purge_consumers - Delete all consumer links of fwnode_handle.
* @fwnode: fwnode whose consumer links need to be deleted
*
* Deletes all consumer links connecting directly to @fwnode.
*/
static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode)
{
struct fwnode_link *link, *tmp;
guard(mutex)(&fwnode_link_lock);
list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook)
__fwnode_link_del(link);
}
/**
* fwnode_links_purge - Delete all links connected to a fwnode_handle.
* @fwnode: fwnode whose links needs to be deleted
*
* Deletes all links connecting directly to a fwnode.
*/
void fwnode_links_purge(struct fwnode_handle *fwnode)
{
fwnode_links_purge_suppliers(fwnode);
fwnode_links_purge_consumers(fwnode);
}
void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode)
{
struct fwnode_handle *child;
/* Don't purge consumer links of an added child */
if (fwnode->dev)
return;
fwnode->flags |= FWNODE_FLAG_NOT_DEVICE;
fwnode_links_purge_consumers(fwnode);
fwnode_for_each_available_child_node(fwnode, child)
fw_devlink_purge_absent_suppliers(child);
}
EXPORT_SYMBOL_GPL(fw_devlink_purge_absent_suppliers);
/**
* __fwnode_links_move_consumers - Move consumer from @from to @to fwnode_handle
* @from: move consumers away from this fwnode
* @to: move consumers to this fwnode
*
* Move all consumer links from @from fwnode to @to fwnode.
*/
static void __fwnode_links_move_consumers(struct fwnode_handle *from,
struct fwnode_handle *to)
{
struct fwnode_link *link, *tmp;
list_for_each_entry_safe(link, tmp, &from->consumers, s_hook) {
__fwnode_link_add(link->consumer, to, link->flags);
__fwnode_link_del(link);
}
}
/**
* __fw_devlink_pickup_dangling_consumers - Pick up dangling consumers
* @fwnode: fwnode from which to pick up dangling consumers
* @new_sup: fwnode of new supplier
*
* If the @fwnode has a corresponding struct device and the device supports
* probing (that is, added to a bus), then we want to let fw_devlink create
* MANAGED device links to this device, so leave @fwnode and its descendant's
* fwnode links alone.
*
* Otherwise, move its consumers to the new supplier @new_sup.
*/
static void __fw_devlink_pickup_dangling_consumers(struct fwnode_handle *fwnode,
struct fwnode_handle *new_sup)
{
struct fwnode_handle *child;
if (fwnode->dev && fwnode->dev->bus)
return;
fwnode->flags |= FWNODE_FLAG_NOT_DEVICE;
__fwnode_links_move_consumers(fwnode, new_sup);
fwnode_for_each_available_child_node(fwnode, child)
__fw_devlink_pickup_dangling_consumers(child, new_sup);
}
static DEFINE_MUTEX(device_links_lock);
DEFINE_STATIC_SRCU(device_links_srcu);
static inline void device_links_write_lock(void)
{
mutex_lock(&device_links_lock);
}
static inline void device_links_write_unlock(void)
{
mutex_unlock(&device_links_lock);
}
int device_links_read_lock(void) __acquires(&device_links_srcu)
{
return srcu_read_lock(&device_links_srcu);
}
void device_links_read_unlock(int idx) __releases(&device_links_srcu)
{
srcu_read_unlock(&device_links_srcu, idx);
}
int device_links_read_lock_held(void)
{
return srcu_read_lock_held(&device_links_srcu);
}
static void device_link_synchronize_removal(void)
{
synchronize_srcu(&device_links_srcu);
}
static void device_link_remove_from_lists(struct device_link *link)
{
list_del_rcu(&link->s_node);
list_del_rcu(&link->c_node);
}
static bool device_is_ancestor(struct device *dev, struct device *target)
{
while (target->parent) {
target = target->parent;
if (dev == target)
return true;
}
return false;
}
#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \
DL_FLAG_CYCLE | \
DL_FLAG_MANAGED)
static inline bool device_link_flag_is_sync_state_only(u32 flags)
{
return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY;
}
/**
* device_is_dependent - Check if one device depends on another one
* @dev: Device to check dependencies for.
* @target: Device to check against.
*
* Check if @target depends on @dev or any device dependent on it (its child or
* its consumer etc). Return 1 if that is the case or 0 otherwise.
*/
static int device_is_dependent(struct device *dev, void *target)
{
struct device_link *link;
int ret;
/*
* The "ancestors" check is needed to catch the case when the target
* device has not been completely initialized yet and it is still
* missing from the list of children of its parent device.
*/
if (dev == target || device_is_ancestor(dev, target))
return 1;
ret = device_for_each_child(dev, target, device_is_dependent);
if (ret)
return ret;
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (device_link_flag_is_sync_state_only(link->flags))
continue;
if (link->consumer == target)
return 1;
ret = device_is_dependent(link->consumer, target);
if (ret)
break;
}
return ret;
}
static void device_link_init_status(struct device_link *link,
struct device *consumer,
struct device *supplier)
{
switch (supplier->links.status) {
case DL_DEV_PROBING:
switch (consumer->links.status) {
case DL_DEV_PROBING:
/*
* A consumer driver can create a link to a supplier
* that has not completed its probing yet as long as it
* knows that the supplier is already functional (for
* example, it has just acquired some resources from the
* supplier).
*/
link->status = DL_STATE_CONSUMER_PROBE;
break;
default:
link->status = DL_STATE_DORMANT;
break;
}
break;
case DL_DEV_DRIVER_BOUND:
switch (consumer->links.status) {
case DL_DEV_PROBING:
link->status = DL_STATE_CONSUMER_PROBE;
break;
case DL_DEV_DRIVER_BOUND:
link->status = DL_STATE_ACTIVE;
break;
default:
link->status = DL_STATE_AVAILABLE;
break;
}
break;
case DL_DEV_UNBINDING:
link->status = DL_STATE_SUPPLIER_UNBIND;
break;
default:
link->status = DL_STATE_DORMANT;
break;
}
}
static int device_reorder_to_tail(struct device *dev, void *not_used)
{
struct device_link *link;
/*
* Devices that have not been registered yet will be put to the ends
* of the lists during the registration, so skip them here.
*/
if (device_is_registered(dev))
devices_kset_move_last(dev);
if (device_pm_initialized(dev))
device_pm_move_last(dev);
device_for_each_child(dev, NULL, device_reorder_to_tail);
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (device_link_flag_is_sync_state_only(link->flags))
continue;
device_reorder_to_tail(link->consumer, NULL);
}
return 0;
}
/**
* device_pm_move_to_tail - Move set of devices to the end of device lists
* @dev: Device to move
*
* This is a device_reorder_to_tail() wrapper taking the requisite locks.
*
* It moves the @dev along with all of its children and all of its consumers
* to the ends of the device_kset and dpm_list, recursively.
*/
void device_pm_move_to_tail(struct device *dev)
{
int idx;
idx = device_links_read_lock();
device_pm_lock();
device_reorder_to_tail(dev, NULL);
device_pm_unlock();
device_links_read_unlock(idx);
}
#define to_devlink(dev) container_of((dev), struct device_link, link_dev)
static ssize_t status_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
const char *output;
switch (to_devlink(dev)->status) {
case DL_STATE_NONE:
output = "not tracked";
break;
case DL_STATE_DORMANT:
output = "dormant";
break;
case DL_STATE_AVAILABLE:
output = "available";
break;
case DL_STATE_CONSUMER_PROBE:
output = "consumer probing";
break;
case DL_STATE_ACTIVE:
output = "active";
break;
case DL_STATE_SUPPLIER_UNBIND:
output = "supplier unbinding";
break;
default:
output = "unknown";
break;
}
return sysfs_emit(buf, "%s\n", output);
}
static DEVICE_ATTR_RO(status);
static ssize_t auto_remove_on_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct device_link *link = to_devlink(dev);
const char *output;
if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
output = "supplier unbind";
else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
output = "consumer unbind";
else
output = "never";
return sysfs_emit(buf, "%s\n", output);
}
static DEVICE_ATTR_RO(auto_remove_on);
static ssize_t runtime_pm_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct device_link *link = to_devlink(dev);
return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME));
}
static DEVICE_ATTR_RO(runtime_pm);
static ssize_t sync_state_only_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct device_link *link = to_devlink(dev);
return sysfs_emit(buf, "%d\n",
!!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
}
static DEVICE_ATTR_RO(sync_state_only);
static struct attribute *devlink_attrs[] = {
&dev_attr_status.attr,
&dev_attr_auto_remove_on.attr,
&dev_attr_runtime_pm.attr,
&dev_attr_sync_state_only.attr,
NULL,
};
ATTRIBUTE_GROUPS(devlink);
static void device_link_release_fn(struct work_struct *work)
{
struct device_link *link = container_of(work, struct device_link, rm_work);
/* Ensure that all references to the link object have been dropped. */
device_link_synchronize_removal();
pm_runtime_release_supplier(link);
/*
* If supplier_preactivated is set, the link has been dropped between
* the pm_runtime_get_suppliers() and pm_runtime_put_suppliers() calls
* in __driver_probe_device(). In that case, drop the supplier's
* PM-runtime usage counter to remove the reference taken by
* pm_runtime_get_suppliers().
*/
if (link->supplier_preactivated)
pm_runtime_put_noidle(link->supplier);
pm_request_idle(link->supplier);
put_device(link->consumer);
put_device(link->supplier);
kfree(link);
}
static void devlink_dev_release(struct device *dev)
{
struct device_link *link = to_devlink(dev);
INIT_WORK(&link->rm_work, device_link_release_fn);
/*
* It may take a while to complete this work because of the SRCU
* synchronization in device_link_release_fn() and if the consumer or
* supplier devices get deleted when it runs, so put it into the
* dedicated workqueue.
*/
queue_work(device_link_wq, &link->rm_work);
}
/**
* device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate
*/
void device_link_wait_removal(void)
{
/*
* devlink removal jobs are queued in the dedicated work queue.
* To be sure that all removal jobs are terminated, ensure that any
* scheduled work has run to completion.
*/
flush_workqueue(device_link_wq);
}
EXPORT_SYMBOL_GPL(device_link_wait_removal);
static const struct class devlink_class = {
.name = "devlink",
.dev_groups = devlink_groups,
.dev_release = devlink_dev_release,
};
static int devlink_add_symlinks(struct device *dev)
{
char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL;
int ret;
struct device_link *link = to_devlink(dev);
struct device *sup = link->supplier;
struct device *con = link->consumer;
ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier");
if (ret)
goto out;
ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer");
if (ret)
goto err_con;
buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
if (!buf_con) {
ret = -ENOMEM;
goto err_con_dev;
}
ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf_con);
if (ret)
goto err_con_dev;
buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
if (!buf_sup) {
ret = -ENOMEM;
goto err_sup_dev;
}
ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf_sup);
if (ret)
goto err_sup_dev;
goto out;
err_sup_dev:
sysfs_remove_link(&sup->kobj, buf_con);
err_con_dev:
sysfs_remove_link(&link->link_dev.kobj, "consumer");
err_con:
sysfs_remove_link(&link->link_dev.kobj, "supplier");
out:
return ret;
}
static void devlink_remove_symlinks(struct device *dev)
{
char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL;
struct device_link *link = to_devlink(dev);
struct device *sup = link->supplier;
struct device *con = link->consumer;
sysfs_remove_link(&link->link_dev.kobj, "consumer");
sysfs_remove_link(&link->link_dev.kobj, "supplier");
if (device_is_registered(con)) {
buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
if (!buf_sup)
goto out;
sysfs_remove_link(&con->kobj, buf_sup);
}
buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
if (!buf_con)
goto out;
sysfs_remove_link(&sup->kobj, buf_con);
return;
out:
WARN(1, "Unable to properly free device link symlinks!\n");
}
static struct class_interface devlink_class_intf = {
.class = &devlink_class,
.add_dev = devlink_add_symlinks,
.remove_dev = devlink_remove_symlinks,
};
static int __init devlink_class_init(void)
{
int ret;
ret = class_register(&devlink_class);
if (ret)
return ret;
ret = class_interface_register(&devlink_class_intf);
if (ret)
class_unregister(&devlink_class);
return ret;
}
postcore_initcall(devlink_class_init);
#define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \
DL_FLAG_AUTOREMOVE_SUPPLIER | \
DL_FLAG_AUTOPROBE_CONSUMER | \
DL_FLAG_SYNC_STATE_ONLY | \
DL_FLAG_INFERRED | \
DL_FLAG_CYCLE)
#define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \
DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE)
/**
* device_link_add - Create a link between two devices.
* @consumer: Consumer end of the link.
* @supplier: Supplier end of the link.
* @flags: Link flags.
*
* Return: On success, a device_link struct will be returned.
* On error or invalid flag settings, NULL will be returned.
*
* The caller is responsible for the proper synchronization of the link creation
* with runtime PM. First, setting the DL_FLAG_PM_RUNTIME flag will cause the
* runtime PM framework to take the link into account. Second, if the
* DL_FLAG_RPM_ACTIVE flag is set in addition to it, the supplier devices will
* be forced into the active meta state and reference-counted upon the creation
* of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
* ignored.
*
* If DL_FLAG_STATELESS is set in @flags, the caller of this function is
* expected to release the link returned by it directly with the help of either
* device_link_del() or device_link_remove().
*
* If that flag is not set, however, the caller of this function is handing the
* management of the link over to the driver core entirely and its return value
* can only be used to check whether or not the link is present. In that case,
* the DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_AUTOREMOVE_SUPPLIER device link
* flags can be used to indicate to the driver core when the link can be safely
* deleted. Namely, setting one of them in @flags indicates to the driver core
* that the link is not going to be used (by the given caller of this function)
* after unbinding the consumer or supplier driver, respectively, from its
* device, so the link can be deleted at that point. If none of them is set,
* the link will be maintained until one of the devices pointed to by it (either
* the consumer or the supplier) is unregistered.
*
* Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and
* DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent
* managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can
* be used to request the driver core to automatically probe for a consumer
* driver after successfully binding a driver to the supplier device.
*
* The combination of DL_FLAG_STATELESS and one of DL_FLAG_AUTOREMOVE_CONSUMER,
* DL_FLAG_AUTOREMOVE_SUPPLIER, or DL_FLAG_AUTOPROBE_CONSUMER set in @flags at
* the same time is invalid and will cause NULL to be returned upfront.
* However, if a device link between the given @consumer and @supplier pair
* exists already when this function is called for them, the existing link will
* be returned regardless of its current type and status (the link's flags may
* be modified then). The caller of this function is then expected to treat
* the link as though it has just been created, so (in particular) if
* DL_FLAG_STATELESS was passed in @flags, the link needs to be released
* explicitly when not needed any more (as stated above).
*
* A side effect of the link creation is re-ordering of dpm_list and the
* devices_kset list by moving the consumer device and all devices depending
* on it to the ends of these lists (that does not happen to devices that have
* not been registered when this function is called).
*
* The supplier device is required to be registered when this function is called
* and NULL will be returned if that is not the case. The consumer device need
* not be registered, however.
*/
struct device_link *device_link_add(struct device *consumer,
struct device *supplier, u32 flags)
{
struct device_link *link;
if (!consumer || !supplier || consumer == supplier ||
flags & ~DL_ADD_VALID_FLAGS ||
(flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) ||
(flags & DL_FLAG_AUTOPROBE_CONSUMER &&
flags & (DL_FLAG_AUTOREMOVE_CONSUMER |
DL_FLAG_AUTOREMOVE_SUPPLIER)))
return NULL;
if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) {
if (pm_runtime_get_sync(supplier) < 0) {
pm_runtime_put_noidle(supplier);
return NULL;
}
}
if (!(flags & DL_FLAG_STATELESS))
flags |= DL_FLAG_MANAGED;
if (flags & DL_FLAG_SYNC_STATE_ONLY &&
!device_link_flag_is_sync_state_only(flags))
return NULL;
device_links_write_lock();
device_pm_lock();
/*
* If the supplier has not been fully registered yet or there is a
* reverse (non-SYNC_STATE_ONLY) dependency between the consumer and
* the supplier already in the graph, return NULL. If the link is a
* SYNC_STATE_ONLY link, we don't check for reverse dependencies
* because it only affects sync_state() callbacks.
*/
if (!device_pm_initialized(supplier)
|| (!(flags & DL_FLAG_SYNC_STATE_ONLY) &&
device_is_dependent(consumer, supplier))) {
link = NULL;
goto out;
}
/*
* SYNC_STATE_ONLY links are useless once a consumer device has probed.
* So, only create it if the consumer hasn't probed yet.
*/
if (flags & DL_FLAG_SYNC_STATE_ONLY &&
consumer->links.status != DL_DEV_NO_DRIVER &&
consumer->links.status != DL_DEV_PROBING) {
link = NULL;
goto out;
}
/*
* DL_FLAG_AUTOREMOVE_SUPPLIER indicates that the link will be needed
* longer than for DL_FLAG_AUTOREMOVE_CONSUMER and setting them both
* together doesn't make sense, so prefer DL_FLAG_AUTOREMOVE_SUPPLIER.
*/
if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER;
list_for_each_entry(link, &supplier->links.consumers, s_node) {
if (link->consumer != consumer)
continue;
if (link->flags & DL_FLAG_INFERRED &&
!(flags & DL_FLAG_INFERRED))
link->flags &= ~DL_FLAG_INFERRED;
if (flags & DL_FLAG_PM_RUNTIME) {
if (!(link->flags & DL_FLAG_PM_RUNTIME)) {
pm_runtime_new_link(consumer);
link->flags |= DL_FLAG_PM_RUNTIME;
}
if (flags & DL_FLAG_RPM_ACTIVE)
refcount_inc(&link->rpm_active);
}
if (flags & DL_FLAG_STATELESS) {
kref_get(&link->kref);
if (link->flags & DL_FLAG_SYNC_STATE_ONLY &&
!(link->flags & DL_FLAG_STATELESS)) {
link->flags |= DL_FLAG_STATELESS;
goto reorder;
} else {
link->flags |= DL_FLAG_STATELESS;
goto out;
}
}
/*
* If the life time of the link following from the new flags is
* longer than indicated by the flags of the existing link,
* update the existing link to stay around longer.
*/
if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) {
if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) {
link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER;
link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER;
}
} else if (!(flags & DL_FLAG_AUTOREMOVE_CONSUMER)) {
link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER |
DL_FLAG_AUTOREMOVE_SUPPLIER);
}
if (!(link->flags & DL_FLAG_MANAGED)) {
kref_get(&link->kref);
link->flags |= DL_FLAG_MANAGED;
device_link_init_status(link, consumer, supplier);
}
if (link->flags & DL_FLAG_SYNC_STATE_ONLY &&
!(flags & DL_FLAG_SYNC_STATE_ONLY)) {
link->flags &= ~DL_FLAG_SYNC_STATE_ONLY;
goto reorder;
}
goto out;
}
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link)
goto out;
refcount_set(&link->rpm_active, 1);
get_device(supplier);
link->supplier = supplier;
INIT_LIST_HEAD(&link->s_node);
get_device(consumer);
link->consumer = consumer;
INIT_LIST_HEAD(&link->c_node);
link->flags = flags;
kref_init(&link->kref);
link->link_dev.class = &devlink_class;
device_set_pm_not_required(&link->link_dev);
dev_set_name(&link->link_dev, "%s:%s--%s:%s",
dev_bus_name(supplier), dev_name(supplier),
dev_bus_name(consumer), dev_name(consumer));
if (device_register(&link->link_dev)) {
put_device(&link->link_dev);
link = NULL;
goto out;
}
if (flags & DL_FLAG_PM_RUNTIME) {
if (flags & DL_FLAG_RPM_ACTIVE)
refcount_inc(&link->rpm_active);
pm_runtime_new_link(consumer);
}
/* Determine the initial link state. */
if (flags & DL_FLAG_STATELESS)
link->status = DL_STATE_NONE;
else
device_link_init_status(link, consumer, supplier);
/*
* Some callers expect the link creation during consumer driver probe to
* resume the supplier even without DL_FLAG_RPM_ACTIVE.
*/
if (link->status == DL_STATE_CONSUMER_PROBE &&
flags & DL_FLAG_PM_RUNTIME)
pm_runtime_resume(supplier);
list_add_tail_rcu(&link->s_node, &supplier->links.consumers);
list_add_tail_rcu(&link->c_node, &consumer->links.suppliers);
if (flags & DL_FLAG_SYNC_STATE_ONLY) {
dev_dbg(consumer,
"Linked as a sync state only consumer to %s\n",
dev_name(supplier));
goto out;
}
reorder:
/*
* Move the consumer and all of the devices depending on it to the end
* of dpm_list and the devices_kset list.
*
* It is necessary to hold dpm_list locked throughout all that or else
* we may end up suspending with a wrong ordering of it.
*/
device_reorder_to_tail(consumer, NULL);
dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier));
out:
device_pm_unlock();
device_links_write_unlock();
if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link)
pm_runtime_put(supplier);
return link;
}
EXPORT_SYMBOL_GPL(device_link_add);
static void __device_link_del(struct kref *kref)
{
struct device_link *link = container_of(kref, struct device_link, kref);
dev_dbg(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
pm_runtime_drop_link(link);
device_link_remove_from_lists(link);
device_unregister(&link->link_dev);
}
static void device_link_put_kref(struct device_link *link)
{
if (link->flags & DL_FLAG_STATELESS)
kref_put(&link->kref, __device_link_del);
else if (!device_is_registered(link->consumer))
__device_link_del(&link->kref);
else
WARN(1, "Unable to drop a managed device link reference\n");
}
/**
* device_link_del - Delete a stateless link between two devices.
* @link: Device link to delete.
*
* The caller must ensure proper synchronization of this function with runtime
* PM. If the link was added multiple times, it needs to be deleted as often.
* Care is required for hotplugged devices: Their links are purged on removal
* and calling device_link_del() is then no longer allowed.
*/
void device_link_del(struct device_link *link)
{
device_links_write_lock();
device_link_put_kref(link);
device_links_write_unlock();
}
EXPORT_SYMBOL_GPL(device_link_del);
/**
* device_link_remove - Delete a stateless link between two devices.
* @consumer: Consumer end of the link.
* @supplier: Supplier end of the link.
*
* The caller must ensure proper synchronization of this function with runtime
* PM.
*/
void device_link_remove(void *consumer, struct device *supplier)
{
struct device_link *link;
if (WARN_ON(consumer == supplier))
return;
device_links_write_lock();
list_for_each_entry(link, &supplier->links.consumers, s_node) {
if (link->consumer == consumer) {
device_link_put_kref(link);
break;
}
}
device_links_write_unlock();
}
EXPORT_SYMBOL_GPL(device_link_remove);
static void device_links_missing_supplier(struct device *dev)
{
struct device_link *link;
list_for_each_entry(link, &dev->links.suppliers, c_node) {
if (link->status != DL_STATE_CONSUMER_PROBE)
continue;
if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) {
WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
} else {
WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
WRITE_ONCE(link->status, DL_STATE_DORMANT);
}
}
}
static bool dev_is_best_effort(struct device *dev)
{
return (fw_devlink_best_effort && dev->can_match) ||
(dev->fwnode && (dev->fwnode->flags & FWNODE_FLAG_BEST_EFFORT));
}
static struct fwnode_handle *fwnode_links_check_suppliers(
struct fwnode_handle *fwnode)
{
struct fwnode_link *link;
if (!fwnode || fw_devlink_is_permissive())
return NULL;
list_for_each_entry(link, &fwnode->suppliers, c_hook)
if (!(link->flags &
(FWLINK_FLAG_CYCLE | FWLINK_FLAG_IGNORE)))
return link->supplier;
return NULL;
}
/**
* device_links_check_suppliers - Check presence of supplier drivers.
* @dev: Consumer device.
*
* Check links from this device to any suppliers. Walk the list of the device's
* links to suppliers and see if all of them are available. If not, simply
* return -EPROBE_DEFER.
*
* We need to guarantee that the supplier will not go away after the check has
* been positive here. It only can go away in __device_release_driver() and
* that function checks the device's links to consumers. This means we need to
* mark the link as "consumer probe in progress" to make the supplier removal
* wait for us to complete (or bad things may happen).
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
int device_links_check_suppliers(struct device *dev)
{
struct device_link *link;
int ret = 0, fwnode_ret = 0;
struct fwnode_handle *sup_fw;
/*
* Device waiting for supplier to become available is not allowed to
* probe.
*/
scoped_guard(mutex, &fwnode_link_lock) {
sup_fw = fwnode_links_check_suppliers(dev->fwnode);
if (sup_fw) {
if (dev_is_best_effort(dev))
fwnode_ret = -EAGAIN;
else
return dev_err_probe(dev, -EPROBE_DEFER,
"wait for supplier %pfwf\n", sup_fw);
}
}
device_links_write_lock();
list_for_each_entry(link, &dev->links.suppliers, c_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
if (link->status != DL_STATE_AVAILABLE &&
!(link->flags & DL_FLAG_SYNC_STATE_ONLY)) {
if (dev_is_best_effort(dev) &&
link->flags & DL_FLAG_INFERRED &&
!link->supplier->can_match) {
ret = -EAGAIN;
continue;
}
device_links_missing_supplier(dev);
ret = dev_err_probe(dev, -EPROBE_DEFER,
"supplier %s not ready\n", dev_name(link->supplier));
break;
}
WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE);
}
dev->links.status = DL_DEV_PROBING;
device_links_write_unlock();
return ret ? ret : fwnode_ret;
}
/**
* __device_links_queue_sync_state - Queue a device for sync_state() callback
* @dev: Device to call sync_state() on
* @list: List head to queue the @dev on
*
* Queues a device for a sync_state() callback when the device links write lock
* isn't held. This allows the sync_state() execution flow to use device links
* APIs. The caller must ensure this function is called with
* device_links_write_lock() held.
*
* This function does a get_device() to make sure the device is not freed while
* on this list.
*
* So the caller must also ensure that device_links_flush_sync_list() is called
* as soon as the caller releases device_links_write_lock(). This is necessary
* to make sure the sync_state() is called in a timely fashion and the
* put_device() is called on this device.
*/
static void __device_links_queue_sync_state(struct device *dev,
struct list_head *list)
{
struct device_link *link;
if (!dev_has_sync_state(dev))
return;
if (dev->state_synced)
return;
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
if (link->status != DL_STATE_ACTIVE)
return;
}
/*
* Set the flag here to avoid adding the same device to a list more
* than once. This can happen if new consumers get added to the device
* and probed before the list is flushed.
*/
dev->state_synced = true;
if (WARN_ON(!list_empty(&dev->links.defer_sync)))
return;
get_device(dev);
list_add_tail(&dev->links.defer_sync, list);
}
/**
* device_links_flush_sync_list - Call sync_state() on a list of devices
* @list: List of devices to call sync_state() on
* @dont_lock_dev: Device for which lock is already held by the caller
*
* Calls sync_state() on all the devices that have been queued for it. This
* function is used in conjunction with __device_links_queue_sync_state(). The
* @dont_lock_dev parameter is useful when this function is called from a
* context where a device lock is already held.
*/
static void device_links_flush_sync_list(struct list_head *list,
struct device *dont_lock_dev)
{
struct device *dev, *tmp;
list_for_each_entry_safe(dev, tmp, list, links.defer_sync) {
list_del_init(&dev->links.defer_sync);
if (dev != dont_lock_dev)
device_lock(dev);
dev_sync_state(dev);
if (dev != dont_lock_dev)
device_unlock(dev);
put_device(dev);
}
}
void device_links_supplier_sync_state_pause(void)
{
device_links_write_lock();
defer_sync_state_count++;
device_links_write_unlock();
}
void device_links_supplier_sync_state_resume(void)
{
struct device *dev, *tmp;
LIST_HEAD(sync_list);
device_links_write_lock();
if (!defer_sync_state_count) {
WARN(true, "Unmatched sync_state pause/resume!");
goto out;
}
defer_sync_state_count--;
if (defer_sync_state_count)
goto out;
list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) {
/*
* Delete from deferred_sync list before queuing it to
* sync_list because defer_sync is used for both lists.
*/
list_del_init(&dev->links.defer_sync);
__device_links_queue_sync_state(dev, &sync_list);
}
out:
device_links_write_unlock();
device_links_flush_sync_list(&sync_list, NULL);
}
static int sync_state_resume_initcall(void)
{
device_links_supplier_sync_state_resume();
return 0;
}
late_initcall(sync_state_resume_initcall);
static void __device_links_supplier_defer_sync(struct device *sup)
{
if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup))
list_add_tail(&sup->links.defer_sync, &deferred_sync);
}
static void device_link_drop_managed(struct device_link *link)
{
link->flags &= ~DL_FLAG_MANAGED;
WRITE_ONCE(link->status, DL_STATE_NONE);
kref_put(&link->kref, __device_link_del);
}
static ssize_t waiting_for_supplier_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
bool val;
device_lock(dev);
scoped_guard(mutex, &fwnode_link_lock)
val = !!fwnode_links_check_suppliers(dev->fwnode);
device_unlock(dev);
return sysfs_emit(buf, "%u\n", val);
}
static DEVICE_ATTR_RO(waiting_for_supplier);
/**
* device_links_force_bind - Prepares device to be force bound
* @dev: Consumer device.
*
* device_bind_driver() force binds a device to a driver without calling any
* driver probe functions. So the consumer really isn't going to wait for any
* supplier before it's bound to the driver. We still want the device link
* states to be sensible when this happens.
*
* In preparation for device_bind_driver(), this function goes through each
* supplier device links and checks if the supplier is bound. If it is, then
* the device link status is set to CONSUMER_PROBE. Otherwise, the device link
* is dropped. Links without the DL_FLAG_MANAGED flag set are ignored.
*/
void device_links_force_bind(struct device *dev)
{
struct device_link *link, *ln;
device_links_write_lock();
list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
if (link->status != DL_STATE_AVAILABLE) {
device_link_drop_managed(link);
continue;
}
WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE);
}
dev->links.status = DL_DEV_PROBING;
device_links_write_unlock();
}
/**
* device_links_driver_bound - Update device links after probing its driver.
* @dev: Device to update the links for.
*
* The probe has been successful, so update links from this device to any
* consumers by changing their status to "available".
*
* Also change the status of @dev's links to suppliers to "active".
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
void device_links_driver_bound(struct device *dev)
{
struct device_link *link, *ln;
LIST_HEAD(sync_list);
/*
* If a device binds successfully, it's expected to have created all
* the device links it needs to or make new device links as it needs
* them. So, fw_devlink no longer needs to create device links to any
* of the device's suppliers.
*
* Also, if a child firmware node of this bound device is not added as a
* device by now, assume it is never going to be added. Make this bound
* device the fallback supplier to the dangling consumers of the child
* firmware node because this bound device is probably implementing the
* child firmware node functionality and we don't want the dangling
* consumers to defer probe indefinitely waiting for a device for the
* child firmware node.
*/
if (dev->fwnode && dev->fwnode->dev == dev) {
struct fwnode_handle *child;
fwnode_links_purge_suppliers(dev->fwnode);
guard(mutex)(&fwnode_link_lock);
fwnode_for_each_available_child_node(dev->fwnode, child)
__fw_devlink_pickup_dangling_consumers(child,
dev->fwnode);
__fw_devlink_link_to_consumers(dev);
}
device_remove_file(dev, &dev_attr_waiting_for_supplier);
device_links_write_lock();
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
/*
* Links created during consumer probe may be in the "consumer
* probe" state to start with if the supplier is still probing
* when they are created and they may become "active" if the
* consumer probe returns first. Skip them here.
*/
if (link->status == DL_STATE_CONSUMER_PROBE ||
link->status == DL_STATE_ACTIVE)
continue;
WARN_ON(link->status != DL_STATE_DORMANT);
WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER)
driver_deferred_probe_add(link->consumer);
}
if (defer_sync_state_count)
__device_links_supplier_defer_sync(dev);
else
__device_links_queue_sync_state(dev, &sync_list);
list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) {
struct device *supplier;
if (!(link->flags & DL_FLAG_MANAGED))
continue;
supplier = link->supplier;
if (link->flags & DL_FLAG_SYNC_STATE_ONLY) {
/*
* When DL_FLAG_SYNC_STATE_ONLY is set, it means no
* other DL_MANAGED_LINK_FLAGS have been set. So, it's
* save to drop the managed link completely.
*/
device_link_drop_managed(link);
} else if (dev_is_best_effort(dev) &&
link->flags & DL_FLAG_INFERRED &&
link->status != DL_STATE_CONSUMER_PROBE &&
!link->supplier->can_match) {
/*
* When dev_is_best_effort() is true, we ignore device
* links to suppliers that don't have a driver. If the
* consumer device still managed to probe, there's no
* point in maintaining a device link in a weird state
* (consumer probed before supplier). So delete it.
*/
device_link_drop_managed(link);
} else {
WARN_ON(link->status != DL_STATE_CONSUMER_PROBE);
WRITE_ONCE(link->status, DL_STATE_ACTIVE);
}
/*
* This needs to be done even for the deleted
* DL_FLAG_SYNC_STATE_ONLY device link in case it was the last
* device link that was preventing the supplier from getting a
* sync_state() call.
*/
if (defer_sync_state_count)
__device_links_supplier_defer_sync(supplier);
else
__device_links_queue_sync_state(supplier, &sync_list);
}
dev->links.status = DL_DEV_DRIVER_BOUND;
device_links_write_unlock();
device_links_flush_sync_list(&sync_list, dev);
}
/**
* __device_links_no_driver - Update links of a device without a driver.
* @dev: Device without a drvier.
*
* Delete all non-persistent links from this device to any suppliers.
*
* Persistent links stay around, but their status is changed to "available",
* unless they already are in the "supplier unbind in progress" state in which
* case they need not be updated.
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
static void __device_links_no_driver(struct device *dev)
{
struct device_link *link, *ln;
list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) {
device_link_drop_managed(link);
continue;
}
if (link->status != DL_STATE_CONSUMER_PROBE &&
link->status != DL_STATE_ACTIVE)
continue;
if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) {
WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
} else {
WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
WRITE_ONCE(link->status, DL_STATE_DORMANT);
}
}
dev->links.status = DL_DEV_NO_DRIVER;
}
/**
* device_links_no_driver - Update links after failing driver probe.
* @dev: Device whose driver has just failed to probe.
*
* Clean up leftover links to consumers for @dev and invoke
* %__device_links_no_driver() to update links to suppliers for it as
* appropriate.
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
void device_links_no_driver(struct device *dev)
{
struct device_link *link;
device_links_write_lock();
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
/*
* The probe has failed, so if the status of the link is
* "consumer probe" or "active", it must have been added by
* a probing consumer while this device was still probing.
* Change its state to "dormant", as it represents a valid
* relationship, but it is not functionally meaningful.
*/
if (link->status == DL_STATE_CONSUMER_PROBE ||
link->status == DL_STATE_ACTIVE)
WRITE_ONCE(link->status, DL_STATE_DORMANT);
}
__device_links_no_driver(dev);
device_links_write_unlock();
}
/**
* device_links_driver_cleanup - Update links after driver removal.
* @dev: Device whose driver has just gone away.
*
* Update links to consumers for @dev by changing their status to "dormant" and
* invoke %__device_links_no_driver() to update links to suppliers for it as
* appropriate.
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
void device_links_driver_cleanup(struct device *dev)
{
struct device_link *link, *ln;
device_links_write_lock();
list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
/*
* autoremove the links between this @dev and its consumer
* devices that are not active, i.e. where the link state
* has moved to DL_STATE_SUPPLIER_UNBIND.
*/
if (link->status == DL_STATE_SUPPLIER_UNBIND &&
link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
device_link_drop_managed(link);
WRITE_ONCE(link->status, DL_STATE_DORMANT);
}
list_del_init(&dev->links.defer_sync);
__device_links_no_driver(dev);
device_links_write_unlock();
}
/**
* device_links_busy - Check if there are any busy links to consumers.
* @dev: Device to check.
*
* Check each consumer of the device and return 'true' if its link's status
* is one of "consumer probe" or "active" (meaning that the given consumer is
* probing right now or its driver is present). Otherwise, change the link
* state to "supplier unbind" to prevent the consumer from being probed
* successfully going forward.
*
* Return 'false' if there are no probing or active consumers.
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
bool device_links_busy(struct device *dev)
{
struct device_link *link;
bool ret = false;
device_links_write_lock();
list_for_each_entry(link, &dev->links.consumers, s_node) {
if (!(link->flags & DL_FLAG_MANAGED))
continue;
if (link->status == DL_STATE_CONSUMER_PROBE
|| link->status == DL_STATE_ACTIVE) {
ret = true;
break;
}
WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND);
}
dev->links.status = DL_DEV_UNBINDING;
device_links_write_unlock();
return ret;
}
/**
* device_links_unbind_consumers - Force unbind consumers of the given device.
* @dev: Device to unbind the consumers of.
*
* Walk the list of links to consumers for @dev and if any of them is in the
* "consumer probe" state, wait for all device probes in progress to complete
* and start over.
*
* If that's not the case, change the status of the link to "supplier unbind"
* and check if the link was in the "active" state. If so, force the consumer
* driver to unbind and start over (the consumer will not re-probe as we have
* changed the state of the link already).
*
* Links without the DL_FLAG_MANAGED flag set are ignored.
*/
void device_links_unbind_consumers(struct device *dev)
{
struct device_link *link;
start:
device_links_write_lock();
list_for_each_entry(link, &dev->links.consumers, s_node) {
enum device_link_state status;
if (!(link->flags & DL_FLAG_MANAGED) ||
link->flags & DL_FLAG_SYNC_STATE_ONLY)
continue;
status = link->status;
if (status == DL_STATE_CONSUMER_PROBE) {
device_links_write_unlock();
wait_for_device_probe();
goto start;
}
WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND);
if (status == DL_STATE_ACTIVE) {
struct device *consumer = link->consumer;
get_device(consumer);
device_links_write_unlock();
device_release_driver_internal(consumer, NULL,
consumer->parent);
put_device(consumer);
goto start;
}
}
device_links_write_unlock();
}
/**
* device_links_purge - Delete existing links to other devices.
* @dev: Target device.
*/
static void device_links_purge(struct device *dev)
{
struct device_link *link, *ln;
if (dev->class == &devlink_class)
return;
/*
* Delete all of the remaining links from this device to any other
* devices (either consumers or suppliers).
*/
device_links_write_lock();
list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) {
WARN_ON(link->status == DL_STATE_ACTIVE);
__device_link_del(&link->kref);
}
list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) {
WARN_ON(link->status != DL_STATE_DORMANT &&
link->status != DL_STATE_NONE);
__device_link_del(&link->kref);
}
device_links_write_unlock();
}
#define FW_DEVLINK_FLAGS_PERMISSIVE (DL_FLAG_INFERRED | \
DL_FLAG_SYNC_STATE_ONLY)
#define FW_DEVLINK_FLAGS_ON (DL_FLAG_INFERRED | \
DL_FLAG_AUTOPROBE_CONSUMER)
#define FW_DEVLINK_FLAGS_RPM (FW_DEVLINK_FLAGS_ON | \
DL_FLAG_PM_RUNTIME)
static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_RPM;
static int __init fw_devlink_setup(char *arg)
{
if (!arg)
return -EINVAL;
if (strcmp(arg, "off") == 0) {
fw_devlink_flags = 0;
} else if (strcmp(arg, "permissive") == 0) {
fw_devlink_flags = FW_DEVLINK_FLAGS_PERMISSIVE;
} else if (strcmp(arg, "on") == 0) {
fw_devlink_flags = FW_DEVLINK_FLAGS_ON;
} else if (strcmp(arg, "rpm") == 0) {
fw_devlink_flags = FW_DEVLINK_FLAGS_RPM;
}
return 0;
}
early_param("fw_devlink", fw_devlink_setup);
static bool fw_devlink_strict;
static int __init fw_devlink_strict_setup(char *arg)
{
return kstrtobool(arg, &fw_devlink_strict);
}
early_param("fw_devlink.strict", fw_devlink_strict_setup);
#define FW_DEVLINK_SYNC_STATE_STRICT 0
#define FW_DEVLINK_SYNC_STATE_TIMEOUT 1
#ifndef CONFIG_FW_DEVLINK_SYNC_STATE_TIMEOUT
static int fw_devlink_sync_state;
#else
static int fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT;
#endif
static int __init fw_devlink_sync_state_setup(char *arg)
{
if (!arg)
return -EINVAL;
if (strcmp(arg, "strict") == 0) {
fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_STRICT;
return 0;
} else if (strcmp(arg, "timeout") == 0) {
fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT;
return 0;
}
return -EINVAL;
}
early_param("fw_devlink.sync_state", fw_devlink_sync_state_setup);
static inline u32 fw_devlink_get_flags(u8 fwlink_flags)
{
if (fwlink_flags & FWLINK_FLAG_CYCLE)
return FW_DEVLINK_FLAGS_PERMISSIVE | DL_FLAG_CYCLE;
return fw_devlink_flags;
}
static bool fw_devlink_is_permissive(void)
{
return fw_devlink_flags == FW_DEVLINK_FLAGS_PERMISSIVE;
}
bool fw_devlink_is_strict(void)
{
return fw_devlink_strict && !fw_devlink_is_permissive();
}
static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode)
{
if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED)
return;
fwnode_call_int_op(fwnode, add_links);
fwnode->flags |= FWNODE_FLAG_LINKS_ADDED;
}
static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode)
{
struct fwnode_handle *child = NULL;
fw_devlink_parse_fwnode(fwnode);
while ((child = fwnode_get_next_available_child_node(fwnode, child)))
fw_devlink_parse_fwtree(child);
}
static void fw_devlink_relax_link(struct device_link *link)
{
if (!(link->flags & DL_FLAG_INFERRED))
return;
if (device_link_flag_is_sync_state_only(link->flags))
return;
pm_runtime_drop_link(link);
link->flags = DL_FLAG_MANAGED | FW_DEVLINK_FLAGS_PERMISSIVE;
dev_dbg(link->consumer, "Relaxing link with %s\n",
dev_name(link->supplier));
}
static int fw_devlink_no_driver(struct device *dev, void *data)
{
struct device_link *link = to_devlink(dev);
if (!link->supplier->can_match)
fw_devlink_relax_link(link);
return 0;
}
void fw_devlink_drivers_done(void)
{
fw_devlink_drv_reg_done = true;
device_links_write_lock();
class_for_each_device(&devlink_class, NULL, NULL,
fw_devlink_no_driver);
device_links_write_unlock();
}
static int fw_devlink_dev_sync_state(struct device *dev, void *data)
{
struct device_link *link = to_devlink(dev);
struct device *sup = link->supplier;
if (!(link->flags & DL_FLAG_MANAGED) ||
link->status == DL_STATE_ACTIVE || sup->state_synced ||
!dev_has_sync_state(sup))
return 0;
if (fw_devlink_sync_state == FW_DEVLINK_SYNC_STATE_STRICT) {
dev_warn(sup, "sync_state() pending due to %s\n",
dev_name(link->consumer));
return 0;
}
if (!list_empty(&sup->links.defer_sync))
return 0;
dev_warn(sup, "Timed out. Forcing sync_state()\n");
sup->state_synced = true;
get_device(sup);
list_add_tail(&sup->links.defer_sync, data);
return 0;
}
void fw_devlink_probing_done(void)
{
LIST_HEAD(sync_list);
device_links_write_lock();
class_for_each_device(&devlink_class, NULL, &sync_list,
fw_devlink_dev_sync_state);
device_links_write_unlock();
device_links_flush_sync_list(&sync_list, NULL);
}
/**
* wait_for_init_devices_probe - Try to probe any device needed for init
*
* Some devices might need to be probed and bound successfully before the kernel
* boot sequence can finish and move on to init/userspace. For example, a
* network interface might need to be bound to be able to mount a NFS rootfs.
*
* With fw_devlink=on by default, some of these devices might be blocked from
* probing because they are waiting on a optional supplier that doesn't have a
* driver. While fw_devlink will eventually identify such devices and unblock
* the probing automatically, it might be too late by the time it unblocks the
* probing of devices. For example, the IP4 autoconfig might timeout before
* fw_devlink unblocks probing of the network interface.
*
* This function is available to temporarily try and probe all devices that have
* a driver even if some of their suppliers haven't been added or don't have
* drivers.
*
* The drivers can then decide which of the suppliers are optional vs mandatory
* and probe the device if possible. By the time this function returns, all such
* "best effort" probes are guaranteed to be completed. If a device successfully
* probes in this mode, we delete all fw_devlink discovered dependencies of that
* device where the supplier hasn't yet probed successfully because they have to
* be optional dependencies.
*
* Any devices that didn't successfully probe go back to being treated as if
* this function was never called.
*
* This also means that some devices that aren't needed for init and could have
* waited for their optional supplier to probe (when the supplier's module is
* loaded later on) would end up probing prematurely with limited functionality.
* So call this function only when boot would fail without it.
*/
void __init wait_for_init_devices_probe(void)
{
if (!fw_devlink_flags || fw_devlink_is_permissive())
return;
/*
* Wait for all ongoing probes to finish so that the "best effort" is
* only applied to devices that can't probe otherwise.
*/
wait_for_device_probe();
pr_info("Trying to probe devices needed for running init ...\n");
fw_devlink_best_effort = true;
driver_deferred_probe_trigger();
/*
* Wait for all "best effort" probes to finish before going back to
* normal enforcement.
*/
wait_for_device_probe();
fw_devlink_best_effort = false;
}
static void fw_devlink_unblock_consumers(struct device *dev)
{
struct device_link *link;
if (!fw_devlink_flags || fw_devlink_is_permissive())
return;
device_links_write_lock();
list_for_each_entry(link, &dev->links.consumers, s_node)
fw_devlink_relax_link(link);
device_links_write_unlock();
}
#define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev)
static bool fwnode_init_without_drv(struct fwnode_handle *fwnode)
{
struct device *dev;
bool ret;
if (!(fwnode->flags & FWNODE_FLAG_INITIALIZED))
return false;
dev = get_dev_from_fwnode(fwnode);
ret = !dev || dev->links.status == DL_DEV_NO_DRIVER;
put_device(dev);
return ret;
}
static bool fwnode_ancestor_init_without_drv(struct fwnode_handle *fwnode)
{
struct fwnode_handle *parent;
fwnode_for_each_parent_node(fwnode, parent) {
if (fwnode_init_without_drv(parent)) {
fwnode_handle_put(parent);
return true;
}
}
return false;
}
/**
* fwnode_is_ancestor_of - Test if @ancestor is ancestor of @child
* @ancestor: Firmware which is tested for being an ancestor
* @child: Firmware which is tested for being the child
*
* A node is considered an ancestor of itself too.
*
* Return: true if @ancestor is an ancestor of @child. Otherwise, returns false.
*/
static bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor,
const struct fwnode_handle *child)
{
struct fwnode_handle *parent;
if (IS_ERR_OR_NULL(ancestor))
return false;
if (child == ancestor)
return true;
fwnode_for_each_parent_node(child, parent) {
if (parent == ancestor) {
fwnode_handle_put(parent);
return true;
}
}
return false;
}
/**
* fwnode_get_next_parent_dev - Find device of closest ancestor fwnode
* @fwnode: firmware node
*
* Given a firmware node (@fwnode), this function finds its closest ancestor
* firmware node that has a corresponding struct device and returns that struct
* device.
*
* The caller is responsible for calling put_device() on the returned device
* pointer.
*
* Return: a pointer to the device of the @fwnode's closest ancestor.
*/
static struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode)
{
struct fwnode_handle *parent;
struct device *dev;
fwnode_for_each_parent_node(fwnode, parent) {
dev = get_dev_from_fwnode(parent);
if (dev) {
fwnode_handle_put(parent);
return dev;
}
}
return NULL;
}
/**
* __fw_devlink_relax_cycles - Relax and mark dependency cycles.
* @con_handle: Potential consumer device fwnode.
* @sup_handle: Potential supplier's fwnode.
*
* Needs to be called with fwnode_lock and device link lock held.
*
* Check if @sup_handle or any of its ancestors or suppliers direct/indirectly
* depend on @con. This function can detect multiple cyles between @sup_handle
* and @con. When such dependency cycles are found, convert all device links
* created solely by fw_devlink into SYNC_STATE_ONLY device links. Also, mark
* all fwnode links in the cycle with FWLINK_FLAG_CYCLE so that when they are
* converted into a device link in the future, they are created as
* SYNC_STATE_ONLY device links. This is the equivalent of doing
* fw_devlink=permissive just between the devices in the cycle. We need to do
* this because, at this point, fw_devlink can't tell which of these
* dependencies is not a real dependency.
*
* Return true if one or more cycles were found. Otherwise, return false.
*/
static bool __fw_devlink_relax_cycles(struct fwnode_handle *con_handle,
struct fwnode_handle *sup_handle)
{
struct device *sup_dev = NULL, *par_dev = NULL, *con_dev = NULL;
struct fwnode_link *link;
struct device_link *dev_link;
bool ret = false;
if (!sup_handle)
return false;
/*
* We aren't trying to find all cycles. Just a cycle between con and
* sup_handle.
*/
if (sup_handle->flags & FWNODE_FLAG_VISITED)
return false;
sup_handle->flags |= FWNODE_FLAG_VISITED;
/* Termination condition. */
if (sup_handle == con_handle) {
pr_debug("----- cycle: start -----\n");
ret = true;
goto out;
}
sup_dev = get_dev_from_fwnode(sup_handle);
con_dev = get_dev_from_fwnode(con_handle);
/*
* If sup_dev is bound to a driver and @con hasn't started binding to a
* driver, sup_dev can't be a consumer of @con. So, no need to check
* further.
*/
if (sup_dev && sup_dev->links.status == DL_DEV_DRIVER_BOUND &&
con_dev && con_dev->links.status == DL_DEV_NO_DRIVER) {
ret = false;
goto out;
}
list_for_each_entry(link, &sup_handle->suppliers, c_hook) {
if (link->flags & FWLINK_FLAG_IGNORE)
continue;
if (__fw_devlink_relax_cycles(con_handle, link->supplier)) {
__fwnode_link_cycle(link);
ret = true;
}
}
/*
* Give priority to device parent over fwnode parent to account for any
* quirks in how fwnodes are converted to devices.
*/
if (sup_dev)
par_dev = get_device(sup_dev->parent);
else
par_dev = fwnode_get_next_parent_dev(sup_handle);
if (par_dev && __fw_devlink_relax_cycles(con_handle, par_dev->fwnode)) {
pr_debug("%pfwf: cycle: child of %pfwf\n", sup_handle,
par_dev->fwnode);
ret = true;
}
if (!sup_dev)
goto out;
list_for_each_entry(dev_link, &sup_dev->links.suppliers, c_node) {
/*
* Ignore a SYNC_STATE_ONLY flag only if it wasn't marked as
* such due to a cycle.
*/
if (device_link_flag_is_sync_state_only(dev_link->flags) &&
!(dev_link->flags & DL_FLAG_CYCLE))
continue;
if (__fw_devlink_relax_cycles(con_handle,
dev_link->supplier->fwnode)) {
pr_debug("%pfwf: cycle: depends on %pfwf\n", sup_handle,
dev_link->supplier->fwnode);
fw_devlink_relax_link(dev_link);
dev_link->flags |= DL_FLAG_CYCLE;
ret = true;
}
}
out:
sup_handle->flags &= ~FWNODE_FLAG_VISITED;
put_device(sup_dev);
put_device(con_dev);
put_device(par_dev);
return ret;
}
/**
* fw_devlink_create_devlink - Create a device link from a consumer to fwnode
* @con: consumer device for the device link
* @sup_handle: fwnode handle of supplier
* @link: fwnode link that's being converted to a device link
*
* This function will try to create a device link between the consumer device
* @con and the supplier device represented by @sup_handle.
*
* The supplier has to be provided as a fwnode because incorrect cycles in
* fwnode links can sometimes cause the supplier device to never be created.
* This function detects such cases and returns an error if it cannot create a
* device link from the consumer to a missing supplier.
*
* Returns,
* 0 on successfully creating a device link
* -EINVAL if the device link cannot be created as expected
* -EAGAIN if the device link cannot be created right now, but it may be
* possible to do that in the future
*/
static int fw_devlink_create_devlink(struct device *con,
struct fwnode_handle *sup_handle,
struct fwnode_link *link)
{
struct device *sup_dev;
int ret = 0;
u32 flags;
if (link->flags & FWLINK_FLAG_IGNORE)
return 0;
/*
* In some cases, a device P might also be a supplier to its child node
* C. However, this would defer the probe of C until the probe of P
* completes successfully. This is perfectly fine in the device driver
* model. device_add() doesn't guarantee probe completion of the device
* by the time it returns.
*
* However, there are a few drivers that assume C will finish probing
* as soon as it's added and before P finishes probing. So, we provide
* a flag to let fw_devlink know not to delay the probe of C until the
* probe of P completes successfully.
*
* When such a flag is set, we can't create device links where P is the
* supplier of C as that would delay the probe of C.
*/
if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD &&
fwnode_is_ancestor_of(sup_handle, con->fwnode))
return -EINVAL;
/*
* Don't try to optimize by not calling the cycle detection logic under
* certain conditions. There's always some corner case that won't get
* detected.
*/
device_links_write_lock();
if (__fw_devlink_relax_cycles(link->consumer, sup_handle)) {
__fwnode_link_cycle(link);
pr_debug("----- cycle: end -----\n");
pr_info("%pfwf: Fixed dependency cycle(s) with %pfwf\n",
link->consumer, sup_handle);
}
device_links_write_unlock();
if (con->fwnode == link->consumer)
flags = fw_devlink_get_flags(link->flags);
else
flags = FW_DEVLINK_FLAGS_PERMISSIVE;
if (sup_handle->flags & FWNODE_FLAG_NOT_DEVICE)
sup_dev = fwnode_get_next_parent_dev(sup_handle);
else
sup_dev = get_dev_from_fwnode(sup_handle);
if (sup_dev) {
/*
* If it's one of those drivers that don't actually bind to
* their device using driver core, then don't wait on this
* supplier device indefinitely.
*/
if (sup_dev->links.status == DL_DEV_NO_DRIVER &&
sup_handle->flags & FWNODE_FLAG_INITIALIZED) {
dev_dbg(con,
"Not linking %pfwf - dev might never probe\n",
sup_handle);
ret = -EINVAL;
goto out;
}
if (con != sup_dev && !device_link_add(con, sup_dev, flags)) {
dev_err(con, "Failed to create device link (0x%x) with supplier %s for %pfwf\n",
flags, dev_name(sup_dev), link->consumer);
ret = -EINVAL;
}
goto out;
}
/*
* Supplier or supplier's ancestor already initialized without a struct
* device or being probed by a driver.
*/
if (fwnode_init_without_drv(sup_handle) ||
fwnode_ancestor_init_without_drv(sup_handle)) {
dev_dbg(con, "Not linking %pfwf - might never become dev\n",
sup_handle);
return -EINVAL;
}
ret = -EAGAIN;
out:
put_device(sup_dev);
return ret;
}
/**
* __fw_devlink_link_to_consumers - Create device links to consumers of a device
* @dev: Device that needs to be linked to its consumers
*
* This function looks at all the consumer fwnodes of @dev and creates device
* links between the consumer device and @dev (supplier).
*
* If the consumer device has not been added yet, then this function creates a
* SYNC_STATE_ONLY link between @dev (supplier) and the closest ancestor device
* of the consumer fwnode. This is necessary to make sure @dev doesn't get a
* sync_state() callback before the real consumer device gets to be added and
* then probed.
*
* Once device links are created from the real consumer to @dev (supplier), the
* fwnode links are deleted.
*/
static void __fw_devlink_link_to_consumers(struct device *dev)
{
struct fwnode_handle *fwnode = dev->fwnode;
struct fwnode_link *link, *tmp;
list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) {
struct device *con_dev;
bool own_link = true;
int ret;
con_dev = get_dev_from_fwnode(link->consumer);
/*
* If consumer device is not available yet, make a "proxy"
* SYNC_STATE_ONLY link from the consumer's parent device to
* the supplier device. This is necessary to make sure the
* supplier doesn't get a sync_state() callback before the real
* consumer can create a device link to the supplier.
*
* This proxy link step is needed to handle the case where the
* consumer's parent device is added before the supplier.
*/
if (!con_dev) {
con_dev = fwnode_get_next_parent_dev(link->consumer);
/*
* However, if the consumer's parent device is also the
* parent of the supplier, don't create a
* consumer-supplier link from the parent to its child
* device. Such a dependency is impossible.
*/
if (con_dev &&
fwnode_is_ancestor_of(con_dev->fwnode, fwnode)) {
put_device(con_dev);
con_dev = NULL;
} else {
own_link = false;
}
}
if (!con_dev)
continue;
ret = fw_devlink_create_devlink(con_dev, fwnode, link);
put_device(con_dev);
if (!own_link || ret == -EAGAIN)
continue;
__fwnode_link_del(link);
}
}
/**
* __fw_devlink_link_to_suppliers - Create device links to suppliers of a device
* @dev: The consumer device that needs to be linked to its suppliers
* @fwnode: Root of the fwnode tree that is used to create device links
*
* This function looks at all the supplier fwnodes of fwnode tree rooted at
* @fwnode and creates device links between @dev (consumer) and all the
* supplier devices of the entire fwnode tree at @fwnode.
*
* The function creates normal (non-SYNC_STATE_ONLY) device links between @dev
* and the real suppliers of @dev. Once these device links are created, the
* fwnode links are deleted.
*
* In addition, it also looks at all the suppliers of the entire fwnode tree
* because some of the child devices of @dev that have not been added yet
* (because @dev hasn't probed) might already have their suppliers added to
* driver core. So, this function creates SYNC_STATE_ONLY device links between
* @dev (consumer) and these suppliers to make sure they don't execute their
* sync_state() callbacks before these child devices have a chance to create
* their device links. The fwnode links that correspond to the child devices
* aren't delete because they are needed later to create the device links
* between the real consumer and supplier devices.
*/
static void __fw_devlink_link_to_suppliers(struct device *dev,
struct fwnode_handle *fwnode)
{
bool own_link = (dev->fwnode == fwnode);
struct fwnode_link *link, *tmp;
struct fwnode_handle *child = NULL;
list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) {
int ret;
struct fwnode_handle *sup = link->supplier;
ret = fw_devlink_create_devlink(dev, sup, link);
if (!own_link || ret == -EAGAIN)
continue;
__fwnode_link_del(link);
}
/*
* Make "proxy" SYNC_STATE_ONLY device links to represent the needs of
* all the descendants. This proxy link step is needed to handle the
* case where the supplier is added before the consumer's parent device
* (@dev).
*/
while ((child = fwnode_get_next_available_child_node(fwnode, child)))
__fw_devlink_link_to_suppliers(dev, child);
}
static void fw_devlink_link_device(struct device *dev)
{
struct fwnode_handle *fwnode = dev->fwnode;
if (!fw_devlink_flags)
return;
fw_devlink_parse_fwtree(fwnode);
guard(mutex)(&fwnode_link_lock);
__fw_devlink_link_to_consumers(dev);
__fw_devlink_link_to_suppliers(dev, fwnode);
}
/* Device links support end. */
static struct kobject *dev_kobj;
/* /sys/dev/char */
static struct kobject *sysfs_dev_char_kobj;
/* /sys/dev/block */
static struct kobject *sysfs_dev_block_kobj;
static DEFINE_MUTEX(device_hotplug_lock);
void lock_device_hotplug(void)
{
mutex_lock(&device_hotplug_lock);
}
void unlock_device_hotplug(void)
{
mutex_unlock(&device_hotplug_lock);
}
int lock_device_hotplug_sysfs(void)
{
if (mutex_trylock(&device_hotplug_lock))
return 0;
/* Avoid busy looping (5 ms of sleep should do). */
msleep(5);
return restart_syscall();
}
#ifdef CONFIG_BLOCK
static inline int device_is_not_partition(struct device *dev)
{
return !(dev->type == &part_type);
}
#else
static inline int device_is_not_partition(struct device *dev)
{
return 1;
}
#endif
static void device_platform_notify(struct device *dev)
{
acpi_device_notify(dev);
software_node_notify(dev);
}
static void device_platform_notify_remove(struct device *dev)
{
software_node_notify_remove(dev);
acpi_device_notify_remove(dev);
}
/**
* dev_driver_string - Return a device's driver name, if at all possible
* @dev: struct device to get the name of
*
* Will return the device's driver's name if it is bound to a device. If
* the device is not bound to a driver, it will return the name of the bus
* it is attached to. If it is not attached to a bus either, an empty
* string will be returned.
*/
const char *dev_driver_string(const struct device *dev)
{
struct device_driver *drv;
/* dev->driver can change to NULL underneath us because of unbinding,
* so be careful about accessing it. dev->bus and dev->class should
* never change once they are set, so they don't need special care.
*/
drv = READ_ONCE(dev->driver);
return drv ? drv->name : dev_bus_name(dev);
}
EXPORT_SYMBOL(dev_driver_string);
#define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr)
static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct device_attribute *dev_attr = to_dev_attr(attr);
struct device *dev = kobj_to_dev(kobj);
ssize_t ret = -EIO;
if (dev_attr->show)
ret = dev_attr->show(dev, dev_attr, buf);
if (ret >= (ssize_t)PAGE_SIZE) {
printk("dev_attr_show: %pS returned bad count\n",
dev_attr->show);
}
return ret;
}
static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct device_attribute *dev_attr = to_dev_attr(attr);
struct device *dev = kobj_to_dev(kobj);
ssize_t ret = -EIO;
if (dev_attr->store)
ret = dev_attr->store(dev, dev_attr, buf, count);
return ret;
}
static const struct sysfs_ops dev_sysfs_ops = {
.show = dev_attr_show,
.store = dev_attr_store,
};
#define to_ext_attr(x) container_of(x, struct dev_ext_attribute, attr)
ssize_t device_store_ulong(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
int ret;
unsigned long new;
ret = kstrtoul(buf, 0, &new);
if (ret)
return ret;
*(unsigned long *)(ea->var) = new;
/* Always return full write size even if we didn't consume all */
return size;
}
EXPORT_SYMBOL_GPL(device_store_ulong);
ssize_t device_show_ulong(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return sysfs_emit(buf, "%lx\n", *(unsigned long *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_ulong);
ssize_t device_store_int(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
int ret;
long new;
ret = kstrtol(buf, 0, &new);
if (ret)
return ret;
if (new > INT_MAX || new < INT_MIN)
return -EINVAL;
*(int *)(ea->var) = new;
/* Always return full write size even if we didn't consume all */
return size;
}
EXPORT_SYMBOL_GPL(device_store_int);
ssize_t device_show_int(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return sysfs_emit(buf, "%d\n", *(int *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_int);
ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
if (kstrtobool(buf, ea->var) < 0)
return -EINVAL;
return size;
}
EXPORT_SYMBOL_GPL(device_store_bool);
ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return sysfs_emit(buf, "%d\n", *(bool *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_bool);
ssize_t device_show_string(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return sysfs_emit(buf, "%s\n", (char *)ea->var);
}
EXPORT_SYMBOL_GPL(device_show_string);
/**
* device_release - free device structure.
* @kobj: device's kobject.
*
* This is called once the reference count for the object
* reaches 0. We forward the call to the device's release
* method, which should handle actually freeing the structure.
*/
static void device_release(struct kobject *kobj)
{
struct device *dev = kobj_to_dev(kobj);
struct device_private *p = dev->p;
/*
* Some platform devices are driven without driver attached
* and managed resources may have been acquired. Make sure
* all resources are released.
*
* Drivers still can add resources into device after device
* is deleted but alive, so release devres here to avoid
* possible memory leak.
*/
devres_release_all(dev);
kfree(dev->dma_range_map);
if (dev->release)
dev->release(dev);
else if (dev->type && dev->type->release)
dev->type->release(dev);
else if (dev->class && dev->class->dev_release)
dev->class->dev_release(dev);
else
WARN(1, KERN_ERR "Device '%s' does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
dev_name(dev));
kfree(p);
}
static const void *device_namespace(const struct kobject *kobj)
{
const struct device *dev = kobj_to_dev(kobj);
const void *ns = NULL;
if (dev->class && dev->class->namespace)
ns = dev->class->namespace(dev);
return ns;
}
static void device_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid)
{
const struct device *dev = kobj_to_dev(kobj);
if (dev->class && dev->class->get_ownership)
dev->class->get_ownership(dev, uid, gid);
}
static const struct kobj_type device_ktype = {
.release = device_release,
.sysfs_ops = &dev_sysfs_ops,
.namespace = device_namespace,
.get_ownership = device_get_ownership,
};
static int dev_uevent_filter(const struct kobject *kobj)
{
const struct kobj_type *ktype = get_ktype(kobj);
if (ktype == &device_ktype) {
const struct device *dev = kobj_to_dev(kobj);
if (dev->bus)
return 1;
if (dev->class)
return 1;
}
return 0;
}
static const char *dev_uevent_name(const struct kobject *kobj)
{
const struct device *dev = kobj_to_dev(kobj);
if (dev->bus)
return dev->bus->name;
if (dev->class)
return dev->class->name;
return NULL;
}
/*
* Try filling "DRIVER=<name>" uevent variable for a device. Because this
* function may race with binding and unbinding the device from a driver,
* we need to be careful. Binding is generally safe, at worst we miss the
* fact that the device is already bound to a driver (but the driver
* information that is delivered through uevents is best-effort, it may
* become obsolete as soon as it is generated anyways). Unbinding is more
* risky as driver pointer is transitioning to NULL, so READ_ONCE() should
* be used to make sure we are dealing with the same pointer, and to
* ensure that driver structure is not going to disappear from under us
* we take bus' drivers klist lock. The assumption that only registered
* driver can be bound to a device, and to unregister a driver bus code
* will take the same lock.
*/
static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
{
struct subsys_private *sp = bus_to_subsys(dev->bus);
if (sp) {
scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
struct device_driver *drv = READ_ONCE(dev->driver);
if (drv) add_uevent_var(env, "DRIVER=%s", drv->name);
}
subsys_put(sp);
}
}
static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
{
const struct device *dev = kobj_to_dev(kobj);
int retval = 0;
/* add device node properties if present */
if (MAJOR(dev->devt)) {
const char *tmp;
const char *name;
umode_t mode = 0;
kuid_t uid = GLOBAL_ROOT_UID;
kgid_t gid = GLOBAL_ROOT_GID;
add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt));
add_uevent_var(env, "MINOR=%u", MINOR(dev->devt));
name = device_get_devnode(dev, &mode, &uid, &gid, &tmp);
if (name) {
add_uevent_var(env, "DEVNAME=%s", name);
if (mode) add_uevent_var(env, "DEVMODE=%#o", mode & 0777); if (!uid_eq(uid, GLOBAL_ROOT_UID))
add_uevent_var(env, "DEVUID=%u", from_kuid(&init_user_ns, uid));
if (!gid_eq(gid, GLOBAL_ROOT_GID))
add_uevent_var(env, "DEVGID=%u", from_kgid(&init_user_ns, gid));
kfree(tmp);
}
}
if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
/* Add "DRIVER=%s" variable if the device is bound to a driver */
dev_driver_uevent(dev, env);
/* Add common DT information about the device */
of_device_uevent(dev, env);
/* have the bus specific function add its stuff */
if (dev->bus && dev->bus->uevent) {
retval = dev->bus->uevent(dev, env);
if (retval) pr_debug("device: '%s': %s: bus uevent() returned %d\n",
dev_name(dev), __func__, retval);
}
/* have the class specific function add its stuff */
if (dev->class && dev->class->dev_uevent) {
retval = dev->class->dev_uevent(dev, env);
if (retval) pr_debug("device: '%s': %s: class uevent() "
"returned %d\n", dev_name(dev),
__func__, retval);
}
/* have the device type specific function add its stuff */
if (dev->type && dev->type->uevent) {
retval = dev->type->uevent(dev, env);
if (retval) pr_debug("device: '%s': %s: dev_type uevent() "
"returned %d\n", dev_name(dev),
__func__, retval);
}
return retval;
}
static const struct kset_uevent_ops device_uevent_ops = {
.filter = dev_uevent_filter,
.name = dev_uevent_name,
.uevent = dev_uevent,
};
static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct kobject *top_kobj;
struct kset *kset;
struct kobj_uevent_env *env = NULL;
int i;
int len = 0;
int retval;
/* search the kset, the device belongs to */
top_kobj = &dev->kobj;
while (!top_kobj->kset && top_kobj->parent)
top_kobj = top_kobj->parent;
if (!top_kobj->kset)
goto out;
kset = top_kobj->kset;
if (!kset->uevent_ops || !kset->uevent_ops->uevent)
goto out;
/* respect filter */
if (kset->uevent_ops && kset->uevent_ops->filter)
if (!kset->uevent_ops->filter(&dev->kobj))
goto out;
env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL);
if (!env)
return -ENOMEM;
/* let the kset specific function add its keys */
retval = kset->uevent_ops->uevent(&dev->kobj, env);
if (retval)
goto out;
/* copy keys to file */
for (i = 0; i < env->envp_idx; i++)
len += sysfs_emit_at(buf, len, "%s\n", env->envp[i]);
out:
kfree(env);
return len;
}
static ssize_t uevent_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int rc;
rc = kobject_synth_uevent(&dev->kobj, buf, count);
if (rc) {
dev_err(dev, "uevent: failed to send synthetic uevent: %d\n", rc);
return rc;
}
return count;
}
static DEVICE_ATTR_RW(uevent);
static ssize_t online_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
bool val;
device_lock(dev);
val = !dev->offline;
device_unlock(dev);
return sysfs_emit(buf, "%u\n", val);
}
static ssize_t online_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
bool val;
int ret;
ret = kstrtobool(buf, &val);
if (ret < 0)
return ret;
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
ret = val ? device_online(dev) : device_offline(dev);
unlock_device_hotplug();
return ret < 0 ? ret : count;
}
static DEVICE_ATTR_RW(online);
static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
const char *loc;
switch (dev->removable) {
case DEVICE_REMOVABLE:
loc = "removable";
break;
case DEVICE_FIXED:
loc = "fixed";
break;
default:
loc = "unknown";
}
return sysfs_emit(buf, "%s\n", loc);
}
static DEVICE_ATTR_RO(removable);
int device_add_groups(struct device *dev, const struct attribute_group **groups)
{
return sysfs_create_groups(&dev->kobj, groups);
}
EXPORT_SYMBOL_GPL(device_add_groups);
void device_remove_groups(struct device *dev,
const struct attribute_group **groups)
{
sysfs_remove_groups(&dev->kobj, groups);
}
EXPORT_SYMBOL_GPL(device_remove_groups);
union device_attr_group_devres {
const struct attribute_group *group;
const struct attribute_group **groups;
};
static void devm_attr_group_remove(struct device *dev, void *res)
{
union device_attr_group_devres *devres = res;
const struct attribute_group *group = devres->group;
dev_dbg(dev, "%s: removing group %p\n", __func__, group);
sysfs_remove_group(&dev->kobj, group);
}
/**
* devm_device_add_group - given a device, create a managed attribute group
* @dev: The device to create the group for
* @grp: The attribute group to create
*
* This function creates a group for the first time. It will explicitly
* warn and error if any of the attribute files being created already exist.
*
* Returns 0 on success or error code on failure.
*/
int devm_device_add_group(struct device *dev, const struct attribute_group *grp)
{
union device_attr_group_devres *devres;
int error;
devres = devres_alloc(devm_attr_group_remove,
sizeof(*devres), GFP_KERNEL);
if (!devres)
return -ENOMEM;
error = sysfs_create_group(&dev->kobj, grp);
if (error) {
devres_free(devres);
return error;
}
devres->group = grp;
devres_add(dev, devres);
return 0;
}
EXPORT_SYMBOL_GPL(devm_device_add_group);
static int device_add_attrs(struct device *dev)
{
const struct class *class = dev->class;
const struct device_type *type = dev->type;
int error;
if (class) {
error = device_add_groups(dev, class->dev_groups);
if (error)
return error;
}
if (type) {
error = device_add_groups(dev, type->groups);
if (error)
goto err_remove_class_groups;
}
error = device_add_groups(dev, dev->groups);
if (error)
goto err_remove_type_groups;
if (device_supports_offline(dev) && !dev->offline_disabled) {
error = device_create_file(dev, &dev_attr_online);
if (error)
goto err_remove_dev_groups;
}
if (fw_devlink_flags && !fw_devlink_is_permissive() && dev->fwnode) {
error = device_create_file(dev, &dev_attr_waiting_for_supplier);
if (error)
goto err_remove_dev_online;
}
if (dev_removable_is_valid(dev)) {
error = device_create_file(dev, &dev_attr_removable);
if (error)
goto err_remove_dev_waiting_for_supplier;
}
if (dev_add_physical_location(dev)) {
error = device_add_group(dev,
&dev_attr_physical_location_group);
if (error)
goto err_remove_dev_removable;
}
return 0;
err_remove_dev_removable:
device_remove_file(dev, &dev_attr_removable);
err_remove_dev_waiting_for_supplier:
device_remove_file(dev, &dev_attr_waiting_for_supplier);
err_remove_dev_online:
device_remove_file(dev, &dev_attr_online);
err_remove_dev_groups:
device_remove_groups(dev, dev->groups);
err_remove_type_groups:
if (type)
device_remove_groups(dev, type->groups);
err_remove_class_groups:
if (class)
device_remove_groups(dev, class->dev_groups);
return error;
}
static void device_remove_attrs(struct device *dev)
{
const struct class *class = dev->class;
const struct device_type *type = dev->type;
if (dev->physical_location) {
device_remove_group(dev, &dev_attr_physical_location_group);
kfree(dev->physical_location);
}
device_remove_file(dev, &dev_attr_removable);
device_remove_file(dev, &dev_attr_waiting_for_supplier);
device_remove_file(dev, &dev_attr_online);
device_remove_groups(dev, dev->groups);
if (type)
device_remove_groups(dev, type->groups);
if (class)
device_remove_groups(dev, class->dev_groups);
}
static ssize_t dev_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
return print_dev_t(buf, dev->devt);
}
static DEVICE_ATTR_RO(dev);
/* /sys/devices/ */
struct kset *devices_kset;
/**
* devices_kset_move_before - Move device in the devices_kset's list.
* @deva: Device to move.
* @devb: Device @deva should come before.
*/
static void devices_kset_move_before(struct device *deva, struct device *devb)
{
if (!devices_kset)
return;
pr_debug("devices_kset: Moving %s before %s\n",
dev_name(deva), dev_name(devb));
spin_lock(&devices_kset->list_lock);
list_move_tail(&deva->kobj.entry, &devb->kobj.entry);
spin_unlock(&devices_kset->list_lock);
}
/**
* devices_kset_move_after - Move device in the devices_kset's list.
* @deva: Device to move
* @devb: Device @deva should come after.
*/
static void devices_kset_move_after(struct device *deva, struct device *devb)
{
if (!devices_kset)
return;
pr_debug("devices_kset: Moving %s after %s\n",
dev_name(deva), dev_name(devb));
spin_lock(&devices_kset->list_lock);
list_move(&deva->kobj.entry, &devb->kobj.entry);
spin_unlock(&devices_kset->list_lock);
}
/**
* devices_kset_move_last - move the device to the end of devices_kset's list.
* @dev: device to move
*/
void devices_kset_move_last(struct device *dev)
{
if (!devices_kset)
return;
pr_debug("devices_kset: Moving %s to end of list\n", dev_name(dev));
spin_lock(&devices_kset->list_lock);
list_move_tail(&dev->kobj.entry, &devices_kset->list);
spin_unlock(&devices_kset->list_lock);
}
/**
* device_create_file - create sysfs attribute file for device.
* @dev: device.
* @attr: device attribute descriptor.
*/
int device_create_file(struct device *dev,
const struct device_attribute *attr)
{
int error = 0;
if (dev) {
WARN(((attr->attr.mode & S_IWUGO) && !attr->store),
"Attribute %s: write permission without 'store'\n",
attr->attr.name);
WARN(((attr->attr.mode & S_IRUGO) && !attr->show),
"Attribute %s: read permission without 'show'\n",
attr->attr.name);
error = sysfs_create_file(&dev->kobj, &attr->attr);
}
return error;
}
EXPORT_SYMBOL_GPL(device_create_file);
/**
* device_remove_file - remove sysfs attribute file.
* @dev: device.
* @attr: device attribute descriptor.
*/
void device_remove_file(struct device *dev,
const struct device_attribute *attr)
{
if (dev)
sysfs_remove_file(&dev->kobj, &attr->attr);
}
EXPORT_SYMBOL_GPL(device_remove_file);
/**
* device_remove_file_self - remove sysfs attribute file from its own method.
* @dev: device.
* @attr: device attribute descriptor.
*
* See kernfs_remove_self() for details.
*/
bool device_remove_file_self(struct device *dev,
const struct device_attribute *attr)
{
if (dev)
return sysfs_remove_file_self(&dev->kobj, &attr->attr);
else
return false;
}
EXPORT_SYMBOL_GPL(device_remove_file_self);
/**
* device_create_bin_file - create sysfs binary attribute file for device.
* @dev: device.
* @attr: device binary attribute descriptor.
*/
int device_create_bin_file(struct device *dev,
const struct bin_attribute *attr)
{
int error = -EINVAL;
if (dev)
error = sysfs_create_bin_file(&dev->kobj, attr);
return error;
}
EXPORT_SYMBOL_GPL(device_create_bin_file);
/**
* device_remove_bin_file - remove sysfs binary attribute file
* @dev: device.
* @attr: device binary attribute descriptor.
*/
void device_remove_bin_file(struct device *dev,
const struct bin_attribute *attr)
{
if (dev)
sysfs_remove_bin_file(&dev->kobj, attr);
}
EXPORT_SYMBOL_GPL(device_remove_bin_file);
static void klist_children_get(struct klist_node *n)
{
struct device_private *p = to_device_private_parent(n);
struct device *dev = p->device;
get_device(dev);
}
static void klist_children_put(struct klist_node *n)
{
struct device_private *p = to_device_private_parent(n);
struct device *dev = p->device;
put_device(dev);
}
/**
* device_initialize - init device structure.
* @dev: device.
*
* This prepares the device for use by other layers by initializing
* its fields.
* It is the first half of device_register(), if called by
* that function, though it can also be called separately, so one
* may use @dev's fields. In particular, get_device()/put_device()
* may be used for reference counting of @dev after calling this
* function.
*
* All fields in @dev must be initialized by the caller to 0, except
* for those explicitly set to some other value. The simplest
* approach is to use kzalloc() to allocate the structure containing
* @dev.
*
* NOTE: Use put_device() to give up your reference instead of freeing
* @dev directly once you have called this function.
*/
void device_initialize(struct device *dev)
{
dev->kobj.kset = devices_kset;
kobject_init(&dev->kobj, &device_ktype);
INIT_LIST_HEAD(&dev->dma_pools);
mutex_init(&dev->mutex);
lockdep_set_novalidate_class(&dev->mutex);
spin_lock_init(&dev->devres_lock);
INIT_LIST_HEAD(&dev->devres_head);
device_pm_init(dev);
set_dev_node(dev, NUMA_NO_NODE);
INIT_LIST_HEAD(&dev->links.consumers);
INIT_LIST_HEAD(&dev->links.suppliers);
INIT_LIST_HEAD(&dev->links.defer_sync);
dev->links.status = DL_DEV_NO_DRIVER;
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
dev->dma_coherent = dma_default_coherent;
#endif
swiotlb_dev_init(dev);
}
EXPORT_SYMBOL_GPL(device_initialize);
struct kobject *virtual_device_parent(void)
{
static struct kobject *virtual_dir = NULL;
if (!virtual_dir)
virtual_dir = kobject_create_and_add("virtual",
&devices_kset->kobj);
return virtual_dir;
}
struct class_dir {
struct kobject kobj;
const struct class *class;
};
#define to_class_dir(obj) container_of(obj, struct class_dir, kobj)
static void class_dir_release(struct kobject *kobj)
{
struct class_dir *dir = to_class_dir(kobj);
kfree(dir);
}
static const
struct kobj_ns_type_operations *class_dir_child_ns_type(const struct kobject *kobj)
{
const struct class_dir *dir = to_class_dir(kobj);
return dir->class->ns_type;
}
static const struct kobj_type class_dir_ktype = {
.release = class_dir_release,
.sysfs_ops = &kobj_sysfs_ops,
.child_ns_type = class_dir_child_ns_type
};
static struct kobject *class_dir_create_and_add(struct subsys_private *sp,
struct kobject *parent_kobj)
{
struct class_dir *dir;
int retval;
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
if (!dir)
return ERR_PTR(-ENOMEM);
dir->class = sp->class;
kobject_init(&dir->kobj, &class_dir_ktype);
dir->kobj.kset = &sp->glue_dirs;
retval = kobject_add(&dir->kobj, parent_kobj, "%s", sp->class->name);
if (retval < 0) {
kobject_put(&dir->kobj);
return ERR_PTR(retval);
}
return &dir->kobj;
}
static DEFINE_MUTEX(gdp_mutex);
static struct kobject *get_device_parent(struct device *dev,
struct device *parent)
{
struct subsys_private *sp = class_to_subsys(dev->class);
struct kobject *kobj = NULL;
if (sp) {
struct kobject *parent_kobj;
struct kobject *k;
/*
* If we have no parent, we live in "virtual".
* Class-devices with a non class-device as parent, live
* in a "glue" directory to prevent namespace collisions.
*/
if (parent == NULL)
parent_kobj = virtual_device_parent();
else if (parent->class && !dev->class->ns_type) {
subsys_put(sp);
return &parent->kobj;
} else {
parent_kobj = &parent->kobj;
}
mutex_lock(&gdp_mutex);
/* find our class-directory at the parent and reference it */
spin_lock(&sp->glue_dirs.list_lock);
list_for_each_entry(k, &sp->glue_dirs.list, entry)
if (k->parent == parent_kobj) {
kobj = kobject_get(k);
break;
}
spin_unlock(&sp->glue_dirs.list_lock);
if (kobj) {
mutex_unlock(&gdp_mutex);
subsys_put(sp);
return kobj;
}
/* or create a new class-directory at the parent device */
k = class_dir_create_and_add(sp, parent_kobj);
/* do not emit an uevent for this simple "glue" directory */
mutex_unlock(&gdp_mutex);
subsys_put(sp);
return k;
}
/* subsystems can specify a default root directory for their devices */
if (!parent && dev->bus) {
struct device *dev_root = bus_get_dev_root(dev->bus);
if (dev_root) {
kobj = &dev_root->kobj;
put_device(dev_root);
return kobj;
}
}
if (parent)
return &parent->kobj;
return NULL;
}
static inline bool live_in_glue_dir(struct kobject *kobj,
struct device *dev)
{
struct subsys_private *sp;
bool retval;
if (!kobj || !dev->class)
return false;
sp = class_to_subsys(dev->class);
if (!sp)
return false;
if (kobj->kset == &sp->glue_dirs)
retval = true;
else
retval = false;
subsys_put(sp);
return retval;
}
static inline struct kobject *get_glue_dir(struct device *dev)
{
return dev->kobj.parent;
}
/**
* kobject_has_children - Returns whether a kobject has children.
* @kobj: the object to test
*
* This will return whether a kobject has other kobjects as children.
*
* It does NOT account for the presence of attribute files, only sub
* directories. It also assumes there is no concurrent addition or
* removal of such children, and thus relies on external locking.
*/
static inline bool kobject_has_children(struct kobject *kobj)
{
WARN_ON_ONCE(kref_read(&kobj->kref) == 0);
return kobj->sd && kobj->sd->dir.subdirs;
}
/*
* make sure cleaning up dir as the last step, we need to make
* sure .release handler of kobject is run with holding the
* global lock
*/
static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
{
unsigned int ref;
/* see if we live in a "glue" directory */
if (!live_in_glue_dir(glue_dir, dev))
return;
mutex_lock(&gdp_mutex);
/**
* There is a race condition between removing glue directory
* and adding a new device under the glue directory.
*
* CPU1: CPU2:
*
* device_add()
* get_device_parent()
* class_dir_create_and_add()
* kobject_add_internal()
* create_dir() // create glue_dir
*
* device_add()
* get_device_parent()
* kobject_get() // get glue_dir
*
* device_del()
* cleanup_glue_dir()
* kobject_del(glue_dir)
*
* kobject_add()
* kobject_add_internal()
* create_dir() // in glue_dir
* sysfs_create_dir_ns()
* kernfs_create_dir_ns(sd)
*
* sysfs_remove_dir() // glue_dir->sd=NULL
* sysfs_put() // free glue_dir->sd
*
* // sd is freed
* kernfs_new_node(sd)
* kernfs_get(glue_dir)
* kernfs_add_one()
* kernfs_put()
*
* Before CPU1 remove last child device under glue dir, if CPU2 add
* a new device under glue dir, the glue_dir kobject reference count
* will be increase to 2 in kobject_get(k). And CPU2 has been called
* kernfs_create_dir_ns(). Meanwhile, CPU1 call sysfs_remove_dir()
* and sysfs_put(). This result in glue_dir->sd is freed.
*
* Then the CPU2 will see a stale "empty" but still potentially used
* glue dir around in kernfs_new_node().
*
* In order to avoid this happening, we also should make sure that
* kernfs_node for glue_dir is released in CPU1 only when refcount
* for glue_dir kobj is 1.
*/
ref = kref_read(&glue_dir->kref);
if (!kobject_has_children(glue_dir) && !--ref)
kobject_del(glue_dir);
kobject_put(glue_dir);
mutex_unlock(&gdp_mutex);
}
static int device_add_class_symlinks(struct device *dev)
{
struct device_node *of_node = dev_of_node(dev);
struct subsys_private *sp;
int error;
if (of_node) {
error = sysfs_create_link(&dev->kobj, of_node_kobj(of_node), "of_node");
if (error)
dev_warn(dev, "Error %d creating of_node link\n",error);
/* An error here doesn't warrant bringing down the device */
}
sp = class_to_subsys(dev->class);
if (!sp)
return 0;
error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem");
if (error)
goto out_devnode;
if (dev->parent && device_is_not_partition(dev)) {
error = sysfs_create_link(&dev->kobj, &dev->parent->kobj,
"device");
if (error)
goto out_subsys;
}
/* link in the class directory pointing to the device */
error = sysfs_create_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev));
if (error)
goto out_device;
goto exit;
out_device:
sysfs_remove_link(&dev->kobj, "device");
out_subsys:
sysfs_remove_link(&dev->kobj, "subsystem");
out_devnode:
sysfs_remove_link(&dev->kobj, "of_node");
exit:
subsys_put(sp);
return error;
}
static void device_remove_class_symlinks(struct device *dev)
{
struct subsys_private *sp = class_to_subsys(dev->class);
if (dev_of_node(dev))
sysfs_remove_link(&dev->kobj, "of_node");
if (!sp)
return;
if (dev->parent && device_is_not_partition(dev))
sysfs_remove_link(&dev->kobj, "device");
sysfs_remove_link(&dev->kobj, "subsystem");
sysfs_delete_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev));
subsys_put(sp);
}
/**
* dev_set_name - set a device name
* @dev: device
* @fmt: format string for the device's name
*/
int dev_set_name(struct device *dev, const char *fmt, ...)
{
va_list vargs;
int err;
va_start(vargs, fmt);
err = kobject_set_name_vargs(&dev->kobj, fmt, vargs);
va_end(vargs);
return err;
}
EXPORT_SYMBOL_GPL(dev_set_name);
/* select a /sys/dev/ directory for the device */
static struct kobject *device_to_dev_kobj(struct device *dev)
{
if (is_blockdev(dev))
return sysfs_dev_block_kobj;
else
return sysfs_dev_char_kobj;
}
static int device_create_sys_dev_entry(struct device *dev)
{
struct kobject *kobj = device_to_dev_kobj(dev);
int error = 0;
char devt_str[15];
if (kobj) {
format_dev_t(devt_str, dev->devt);
error = sysfs_create_link(kobj, &dev->kobj, devt_str);
}
return error;
}
static void device_remove_sys_dev_entry(struct device *dev)
{
struct kobject *kobj = device_to_dev_kobj(dev);
char devt_str[15];
if (kobj) {
format_dev_t(devt_str, dev->devt);
sysfs_remove_link(kobj, devt_str);
}
}
static int device_private_init(struct device *dev)
{
dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL);
if (!dev->p)
return -ENOMEM;
dev->p->device = dev;
klist_init(&dev->p->klist_children, klist_children_get,
klist_children_put);
INIT_LIST_HEAD(&dev->p->deferred_probe);
return 0;
}
/**
* device_add - add device to device hierarchy.
* @dev: device.
*
* This is part 2 of device_register(), though may be called
* separately _iff_ device_initialize() has been called separately.
*
* This adds @dev to the kobject hierarchy via kobject_add(), adds it
* to the global and sibling lists for the device, then
* adds it to the other relevant subsystems of the driver model.
*
* Do not call this routine or device_register() more than once for
* any device structure. The driver model core is not designed to work
* with devices that get unregistered and then spring back to life.
* (Among other things, it's very hard to guarantee that all references
* to the previous incarnation of @dev have been dropped.) Allocate
* and register a fresh new struct device instead.
*
* NOTE: _Never_ directly free @dev after calling this function, even
* if it returned an error! Always use put_device() to give up your
* reference instead.
*
* Rule of thumb is: if device_add() succeeds, you should call
* device_del() when you want to get rid of it. If device_add() has
* *not* succeeded, use *only* put_device() to drop the reference
* count.
*/
int device_add(struct device *dev)
{
struct subsys_private *sp;
struct device *parent;
struct kobject *kobj;
struct class_interface *class_intf;
int error = -EINVAL;
struct kobject *glue_dir = NULL;
dev = get_device(dev);
if (!dev)
goto done;
if (!dev->p) {
error = device_private_init(dev);
if (error)
goto done;
}
/*
* for statically allocated devices, which should all be converted
* some day, we need to initialize the name. We prevent reading back
* the name, and force the use of dev_name()
*/
if (dev->init_name) {
error = dev_set_name(dev, "%s", dev->init_name);
dev->init_name = NULL;
}
if (dev_name(dev))
error = 0;
/* subsystems can specify simple device enumeration */
else if (dev->bus && dev->bus->dev_name)
error = dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id);
else
error = -EINVAL;
if (error)
goto name_error;
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
parent = get_device(dev->parent);
kobj = get_device_parent(dev, parent);
if (IS_ERR(kobj)) {
error = PTR_ERR(kobj);
goto parent_error;
}
if (kobj)
dev->kobj.parent = kobj;
/* use parent numa_node */
if (parent && (dev_to_node(dev) == NUMA_NO_NODE))
set_dev_node(dev, dev_to_node(parent));
/* first, register with generic layer. */
/* we require the name to be set before, and pass NULL */
error = kobject_add(&dev->kobj, dev->kobj.parent, NULL);
if (error) {
glue_dir = kobj;
goto Error;
}
/* notify platform of device entry */
device_platform_notify(dev);
error = device_create_file(dev, &dev_attr_uevent);
if (error)
goto attrError;
error = device_add_class_symlinks(dev);
if (error)
goto SymlinkError;
error = device_add_attrs(dev);
if (error)
goto AttrsError;
error = bus_add_device(dev);
if (error)
goto BusError;
error = dpm_sysfs_add(dev);
if (error)
goto DPMError;
device_pm_add(dev);
if (MAJOR(dev->devt)) {
error = device_create_file(dev, &dev_attr_dev);
if (error)
goto DevAttrError;
error = device_create_sys_dev_entry(dev);
if (error)
goto SysEntryError;
devtmpfs_create_node(dev);
}
/* Notify clients of device addition. This call must come
* after dpm_sysfs_add() and before kobject_uevent().
*/
bus_notify(dev, BUS_NOTIFY_ADD_DEVICE);
kobject_uevent(&dev->kobj, KOBJ_ADD);
/*
* Check if any of the other devices (consumers) have been waiting for
* this device (supplier) to be added so that they can create a device
* link to it.
*
* This needs to happen after device_pm_add() because device_link_add()
* requires the supplier be registered before it's called.
*
* But this also needs to happen before bus_probe_device() to make sure
* waiting consumers can link to it before the driver is bound to the
* device and the driver sync_state callback is called for this device.
*/
if (dev->fwnode && !dev->fwnode->dev) {
dev->fwnode->dev = dev;
fw_devlink_link_device(dev);
}
bus_probe_device(dev);
/*
* If all driver registration is done and a newly added device doesn't
* match with any driver, don't block its consumers from probing in
* case the consumer device is able to operate without this supplier.
*/
if (dev->fwnode && fw_devlink_drv_reg_done && !dev->can_match)
fw_devlink_unblock_consumers(dev);
if (parent)
klist_add_tail(&dev->p->knode_parent,
&parent->p->klist_children);
sp = class_to_subsys(dev->class);
if (sp) {
mutex_lock(&sp->mutex);
/* tie the class to the device */
klist_add_tail(&dev->p->knode_class, &sp->klist_devices);
/* notify any interfaces that the device is here */
list_for_each_entry(class_intf, &sp->interfaces, node)
if (class_intf->add_dev)
class_intf->add_dev(dev);
mutex_unlock(&sp->mutex);
subsys_put(sp);
}
done:
put_device(dev);
return error;
SysEntryError:
if (MAJOR(dev->devt))
device_remove_file(dev, &dev_attr_dev);
DevAttrError:
device_pm_remove(dev);
dpm_sysfs_remove(dev);
DPMError:
device_set_driver(dev, NULL);
bus_remove_device(dev);
BusError:
device_remove_attrs(dev);
AttrsError:
device_remove_class_symlinks(dev);
SymlinkError:
device_remove_file(dev, &dev_attr_uevent);
attrError:
device_platform_notify_remove(dev);
kobject_uevent(&dev->kobj, KOBJ_REMOVE);
glue_dir = get_glue_dir(dev);
kobject_del(&dev->kobj);
Error:
cleanup_glue_dir(dev, glue_dir);
parent_error:
put_device(parent);
name_error:
kfree(dev->p);
dev->p = NULL;
goto done;
}
EXPORT_SYMBOL_GPL(device_add);
/**
* device_register - register a device with the system.
* @dev: pointer to the device structure
*
* This happens in two clean steps - initialize the device
* and add it to the system. The two steps can be called
* separately, but this is the easiest and most common.
* I.e. you should only call the two helpers separately if
* have a clearly defined need to use and refcount the device
* before it is added to the hierarchy.
*
* For more information, see the kerneldoc for device_initialize()
* and device_add().
*
* NOTE: _Never_ directly free @dev after calling this function, even
* if it returned an error! Always use put_device() to give up the
* reference initialized in this function instead.
*/
int device_register(struct device *dev)
{
device_initialize(dev);
return device_add(dev);
}
EXPORT_SYMBOL_GPL(device_register);
/**
* get_device - increment reference count for device.
* @dev: device.
*
* This simply forwards the call to kobject_get(), though
* we do take care to provide for the case that we get a NULL
* pointer passed in.
*/
struct device *get_device(struct device *dev)
{
return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL;
}
EXPORT_SYMBOL_GPL(get_device);
/**
* put_device - decrement reference count.
* @dev: device in question.
*/
void put_device(struct device *dev)
{
/* might_sleep(); */
if (dev)
kobject_put(&dev->kobj);
}
EXPORT_SYMBOL_GPL(put_device);
bool kill_device(struct device *dev)
{
/*
* Require the device lock and set the "dead" flag to guarantee that
* the update behavior is consistent with the other bitfields near
* it and that we cannot have an asynchronous probe routine trying
* to run while we are tearing out the bus/class/sysfs from
* underneath the device.
*/
device_lock_assert(dev);
if (dev->p->dead)
return false;
dev->p->dead = true;
return true;
}
EXPORT_SYMBOL_GPL(kill_device);
/**
* device_del - delete device from system.
* @dev: device.
*
* This is the first part of the device unregistration
* sequence. This removes the device from the lists we control
* from here, has it removed from the other driver model
* subsystems it was added to in device_add(), and removes it
* from the kobject hierarchy.
*
* NOTE: this should be called manually _iff_ device_add() was
* also called manually.
*/
void device_del(struct device *dev)
{
struct subsys_private *sp;
struct device *parent = dev->parent;
struct kobject *glue_dir = NULL;
struct class_interface *class_intf;
unsigned int noio_flag;
device_lock(dev);
kill_device(dev);
device_unlock(dev);
if (dev->fwnode && dev->fwnode->dev == dev)
dev->fwnode->dev = NULL;
/* Notify clients of device removal. This call must come
* before dpm_sysfs_remove().
*/
noio_flag = memalloc_noio_save();
bus_notify(dev, BUS_NOTIFY_DEL_DEVICE);
dpm_sysfs_remove(dev);
if (parent)
klist_del(&dev->p->knode_parent);
if (MAJOR(dev->devt)) {
devtmpfs_delete_node(dev);
device_remove_sys_dev_entry(dev);
device_remove_file(dev, &dev_attr_dev);
}
sp = class_to_subsys(dev->class);
if (sp) {
device_remove_class_symlinks(dev);
mutex_lock(&sp->mutex);
/* notify any interfaces that the device is now gone */
list_for_each_entry(class_intf, &sp->interfaces, node)
if (class_intf->remove_dev)
class_intf->remove_dev(dev);
/* remove the device from the class list */
klist_del(&dev->p->knode_class);
mutex_unlock(&sp->mutex);
subsys_put(sp);
}
device_remove_file(dev, &dev_attr_uevent);
device_remove_attrs(dev);
bus_remove_device(dev);
device_pm_remove(dev);
driver_deferred_probe_del(dev);
device_platform_notify_remove(dev);
device_links_purge(dev);
/*
* If a device does not have a driver attached, we need to clean
* up any managed resources. We do this in device_release(), but
* it's never called (and we leak the device) if a managed
* resource holds a reference to the device. So release all
* managed resources here, like we do in driver_detach(). We
* still need to do so again in device_release() in case someone
* adds a new resource after this point, though.
*/
devres_release_all(dev);
bus_notify(dev, BUS_NOTIFY_REMOVED_DEVICE);
kobject_uevent(&dev->kobj, KOBJ_REMOVE);
glue_dir = get_glue_dir(dev);
kobject_del(&dev->kobj);
cleanup_glue_dir(dev, glue_dir);
memalloc_noio_restore(noio_flag);
put_device(parent);
}
EXPORT_SYMBOL_GPL(device_del);
/**
* device_unregister - unregister device from system.
* @dev: device going away.
*
* We do this in two parts, like we do device_register(). First,
* we remove it from all the subsystems with device_del(), then
* we decrement the reference count via put_device(). If that
* is the final reference count, the device will be cleaned up
* via device_release() above. Otherwise, the structure will
* stick around until the final reference to the device is dropped.
*/
void device_unregister(struct device *dev)
{
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
device_del(dev);
put_device(dev);
}
EXPORT_SYMBOL_GPL(device_unregister);
static struct device *prev_device(struct klist_iter *i)
{
struct klist_node *n = klist_prev(i);
struct device *dev = NULL;
struct device_private *p;
if (n) {
p = to_device_private_parent(n);
dev = p->device;
}
return dev;
}
static struct device *next_device(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct device *dev = NULL;
struct device_private *p;
if (n) {
p = to_device_private_parent(n);
dev = p->device;
}
return dev;
}
/**
* device_get_devnode - path of device node file
* @dev: device
* @mode: returned file access mode
* @uid: returned file owner
* @gid: returned file group
* @tmp: possibly allocated string
*
* Return the relative path of a possible device node.
* Non-default names may need to allocate a memory to compose
* a name. This memory is returned in tmp and needs to be
* freed by the caller.
*/
const char *device_get_devnode(const struct device *dev,
umode_t *mode, kuid_t *uid, kgid_t *gid,
const char **tmp)
{
char *s;
*tmp = NULL;
/* the device type may provide a specific name */
if (dev->type && dev->type->devnode) *tmp = dev->type->devnode(dev, mode, uid, gid); if (*tmp)
return *tmp;
/* the class may provide a specific name */
if (dev->class && dev->class->devnode) *tmp = dev->class->devnode(dev, mode); if (*tmp)
return *tmp;
/* return name without allocation, tmp == NULL */
if (strchr(dev_name(dev), '!') == NULL)
return dev_name(dev);
/* replace '!' in the name with '/' */
s = kstrdup_and_replace(dev_name(dev), '!', '/', GFP_KERNEL);
if (!s)
return NULL;
return *tmp = s;
}
/**
* device_for_each_child - device child iterator.
* @parent: parent struct device.
* @fn: function to be called for each device.
* @data: data for the callback.
*
* Iterate over @parent's child devices, and call @fn for each,
* passing it @data.
*
* We check the return of @fn each time. If it returns anything
* other than 0, we break out and return that value.
*/
int device_for_each_child(struct device *parent, void *data,
device_iter_t fn)
{
struct klist_iter i;
struct device *child;
int error = 0;
if (!parent || !parent->p)
return 0;
klist_iter_init(&parent->p->klist_children, &i);
while (!error && (child = next_device(&i)))
error = fn(child, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(device_for_each_child);
/**
* device_for_each_child_reverse - device child iterator in reversed order.
* @parent: parent struct device.
* @fn: function to be called for each device.
* @data: data for the callback.
*
* Iterate over @parent's child devices, and call @fn for each,
* passing it @data.
*
* We check the return of @fn each time. If it returns anything
* other than 0, we break out and return that value.
*/
int device_for_each_child_reverse(struct device *parent, void *data,
device_iter_t fn)
{
struct klist_iter i;
struct device *child;
int error = 0;
if (!parent || !parent->p)
return 0;
klist_iter_init(&parent->p->klist_children, &i);
while ((child = prev_device(&i)) && !error)
error = fn(child, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(device_for_each_child_reverse);
/**
* device_for_each_child_reverse_from - device child iterator in reversed order.
* @parent: parent struct device.
* @from: optional starting point in child list
* @fn: function to be called for each device.
* @data: data for the callback.
*
* Iterate over @parent's child devices, starting at @from, and call @fn
* for each, passing it @data. This helper is identical to
* device_for_each_child_reverse() when @from is NULL.
*
* @fn is checked each iteration. If it returns anything other than 0,
* iteration stop and that value is returned to the caller of
* device_for_each_child_reverse_from();
*/
int device_for_each_child_reverse_from(struct device *parent,
struct device *from, void *data,
device_iter_t fn)
{
struct klist_iter i;
struct device *child;
int error = 0;
if (!parent || !parent->p)
return 0;
klist_iter_init_node(&parent->p->klist_children, &i,
(from ? &from->p->knode_parent : NULL));
while ((child = prev_device(&i)) && !error)
error = fn(child, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from);
/**
* device_find_child - device iterator for locating a particular device.
* @parent: parent struct device
* @match: Callback function to check device
* @data: Data to pass to match function
*
* This is similar to the device_for_each_child() function above, but it
* returns a reference to a device that is 'found' for later use, as
* determined by the @match callback.
*
* The callback should return 0 if the device doesn't match and non-zero
* if it does. If the callback returns non-zero and a reference to the
* current device can be obtained, this function will return to the caller
* and not iterate over any more devices.
*
* NOTE: you will need to drop the reference with put_device() after use.
*/
struct device *device_find_child(struct device *parent, const void *data,
device_match_t match)
{
struct klist_iter i;
struct device *child;
if (!parent || !parent->p)
return NULL;
klist_iter_init(&parent->p->klist_children, &i);
while ((child = next_device(&i))) {
if (match(child, data)) {
get_device(child);
break;
}
}
klist_iter_exit(&i);
return child;
}
EXPORT_SYMBOL_GPL(device_find_child);
int __init devices_init(void)
{
devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL);
if (!devices_kset)
return -ENOMEM;
dev_kobj = kobject_create_and_add("dev", NULL);
if (!dev_kobj)
goto dev_kobj_err;
sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj);
if (!sysfs_dev_block_kobj)
goto block_kobj_err;
sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj);
if (!sysfs_dev_char_kobj)
goto char_kobj_err;
device_link_wq = alloc_workqueue("device_link_wq", 0, 0);
if (!device_link_wq)
goto wq_err;
return 0;
wq_err:
kobject_put(sysfs_dev_char_kobj);
char_kobj_err:
kobject_put(sysfs_dev_block_kobj);
block_kobj_err:
kobject_put(dev_kobj);
dev_kobj_err:
kset_unregister(devices_kset);
return -ENOMEM;
}
static int device_check_offline(struct device *dev, void *not_used)
{
int ret;
ret = device_for_each_child(dev, NULL, device_check_offline);
if (ret)
return ret;
return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0;
}
/**
* device_offline - Prepare the device for hot-removal.
* @dev: Device to be put offline.
*
* Execute the device bus type's .offline() callback, if present, to prepare
* the device for a subsequent hot-removal. If that succeeds, the device must
* not be used until either it is removed or its bus type's .online() callback
* is executed.
*
* Call under device_hotplug_lock.
*/
int device_offline(struct device *dev)
{
int ret;
if (dev->offline_disabled)
return -EPERM;
ret = device_for_each_child(dev, NULL, device_check_offline);
if (ret)
return ret;
device_lock(dev);
if (device_supports_offline(dev)) {
if (dev->offline) {
ret = 1;
} else {
ret = dev->bus->offline(dev);
if (!ret) {
kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
dev->offline = true;
}
}
}
device_unlock(dev);
return ret;
}
/**
* device_online - Put the device back online after successful device_offline().
* @dev: Device to be put back online.
*
* If device_offline() has been successfully executed for @dev, but the device
* has not been removed subsequently, execute its bus type's .online() callback
* to indicate that the device can be used again.
*
* Call under device_hotplug_lock.
*/
int device_online(struct device *dev)
{
int ret = 0;
device_lock(dev);
if (device_supports_offline(dev)) {
if (dev->offline) {
ret = dev->bus->online(dev);
if (!ret) {
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
dev->offline = false;
}
} else {
ret = 1;
}
}
device_unlock(dev);
return ret;
}
struct root_device {
struct device dev;
struct module *owner;
};
static inline struct root_device *to_root_device(struct device *d)
{
return container_of(d, struct root_device, dev);
}
static void root_device_release(struct device *dev)
{
kfree(to_root_device(dev));
}
/**
* __root_device_register - allocate and register a root device
* @name: root device name
* @owner: owner module of the root device, usually THIS_MODULE
*
* This function allocates a root device and registers it
* using device_register(). In order to free the returned
* device, use root_device_unregister().
*
* Root devices are dummy devices which allow other devices
* to be grouped under /sys/devices. Use this function to
* allocate a root device and then use it as the parent of
* any device which should appear under /sys/devices/{name}
*
* The /sys/devices/{name} directory will also contain a
* 'module' symlink which points to the @owner directory
* in sysfs.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*
* Note: You probably want to use root_device_register().
*/
struct device *__root_device_register(const char *name, struct module *owner)
{
struct root_device *root;
int err = -ENOMEM;
root = kzalloc(sizeof(struct root_device), GFP_KERNEL);
if (!root)
return ERR_PTR(err);
err = dev_set_name(&root->dev, "%s", name);
if (err) {
kfree(root);
return ERR_PTR(err);
}
root->dev.release = root_device_release;
err = device_register(&root->dev);
if (err) {
put_device(&root->dev);
return ERR_PTR(err);
}
#ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */
if (owner) {
struct module_kobject *mk = &owner->mkobj;
err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module");
if (err) {
device_unregister(&root->dev);
return ERR_PTR(err);
}
root->owner = owner;
}
#endif
return &root->dev;
}
EXPORT_SYMBOL_GPL(__root_device_register);
/**
* root_device_unregister - unregister and free a root device
* @dev: device going away
*
* This function unregisters and cleans up a device that was created by
* root_device_register().
*/
void root_device_unregister(struct device *dev)
{
struct root_device *root = to_root_device(dev);
if (root->owner)
sysfs_remove_link(&root->dev.kobj, "module");
device_unregister(dev);
}
EXPORT_SYMBOL_GPL(root_device_unregister);
static void device_create_release(struct device *dev)
{
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
kfree(dev);
}
static __printf(6, 0) struct device *
device_create_groups_vargs(const struct class *class, struct device *parent,
dev_t devt, void *drvdata,
const struct attribute_group **groups,
const char *fmt, va_list args)
{
struct device *dev = NULL;
int retval = -ENODEV;
if (IS_ERR_OR_NULL(class))
goto error;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev) {
retval = -ENOMEM;
goto error;
}
device_initialize(dev);
dev->devt = devt;
dev->class = class;
dev->parent = parent;
dev->groups = groups;
dev->release = device_create_release;
dev_set_drvdata(dev, drvdata);
retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
if (retval)
goto error;
retval = device_add(dev);
if (retval)
goto error;
return dev;
error:
put_device(dev);
return ERR_PTR(retval);
}
/**
* device_create - creates a device and registers it with sysfs
* @class: pointer to the struct class that this device should be registered to
* @parent: pointer to the parent struct device of this new device, if any
* @devt: the dev_t for the char device to be added
* @drvdata: the data to be added to the device for callbacks
* @fmt: string for the device's name
*
* This function can be used by char device classes. A struct device
* will be created in sysfs, registered to the specified class.
*
* A "dev" file will be created, showing the dev_t for the device, if
* the dev_t is not 0,0.
* If a pointer to a parent struct device is passed in, the newly created
* struct device will be a child of that device in sysfs.
* The pointer to the struct device will be returned from the call.
* Any further sysfs files that might be required can be created using this
* pointer.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*/
struct device *device_create(const struct class *class, struct device *parent,
dev_t devt, void *drvdata, const char *fmt, ...)
{
va_list vargs;
struct device *dev;
va_start(vargs, fmt);
dev = device_create_groups_vargs(class, parent, devt, drvdata, NULL,
fmt, vargs);
va_end(vargs);
return dev;
}
EXPORT_SYMBOL_GPL(device_create);
/**
* device_create_with_groups - creates a device and registers it with sysfs
* @class: pointer to the struct class that this device should be registered to
* @parent: pointer to the parent struct device of this new device, if any
* @devt: the dev_t for the char device to be added
* @drvdata: the data to be added to the device for callbacks
* @groups: NULL-terminated list of attribute groups to be created
* @fmt: string for the device's name
*
* This function can be used by char device classes. A struct device
* will be created in sysfs, registered to the specified class.
* Additional attributes specified in the groups parameter will also
* be created automatically.
*
* A "dev" file will be created, showing the dev_t for the device, if
* the dev_t is not 0,0.
* If a pointer to a parent struct device is passed in, the newly created
* struct device will be a child of that device in sysfs.
* The pointer to the struct device will be returned from the call.
* Any further sysfs files that might be required can be created using this
* pointer.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*/
struct device *device_create_with_groups(const struct class *class,
struct device *parent, dev_t devt,
void *drvdata,
const struct attribute_group **groups,
const char *fmt, ...)
{
va_list vargs;
struct device *dev;
va_start(vargs, fmt);
dev = device_create_groups_vargs(class, parent, devt, drvdata, groups,
fmt, vargs);
va_end(vargs);
return dev;
}
EXPORT_SYMBOL_GPL(device_create_with_groups);
/**
* device_destroy - removes a device that was created with device_create()
* @class: pointer to the struct class that this device was registered with
* @devt: the dev_t of the device that was previously registered
*
* This call unregisters and cleans up a device that was created with a
* call to device_create().
*/
void device_destroy(const struct class *class, dev_t devt)
{
struct device *dev;
dev = class_find_device_by_devt(class, devt);
if (dev) {
put_device(dev);
device_unregister(dev);
}
}
EXPORT_SYMBOL_GPL(device_destroy);
/**
* device_rename - renames a device
* @dev: the pointer to the struct device to be renamed
* @new_name: the new name of the device
*
* It is the responsibility of the caller to provide mutual
* exclusion between two different calls of device_rename
* on the same device to ensure that new_name is valid and
* won't conflict with other devices.
*
* Note: given that some subsystems (networking and infiniband) use this
* function, with no immediate plans for this to change, we cannot assume or
* require that this function not be called at all.
*
* However, if you're writing new code, do not call this function. The following
* text from Kay Sievers offers some insight:
*
* Renaming devices is racy at many levels, symlinks and other stuff are not
* replaced atomically, and you get a "move" uevent, but it's not easy to
* connect the event to the old and new device. Device nodes are not renamed at
* all, there isn't even support for that in the kernel now.
*
* In the meantime, during renaming, your target name might be taken by another
* driver, creating conflicts. Or the old name is taken directly after you
* renamed it -- then you get events for the same DEVPATH, before you even see
* the "move" event. It's just a mess, and nothing new should ever rely on
* kernel device renaming. Besides that, it's not even implemented now for
* other things than (driver-core wise very simple) network devices.
*
* Make up a "real" name in the driver before you register anything, or add
* some other attributes for userspace to find the device, or use udev to add
* symlinks -- but never rename kernel devices later, it's a complete mess. We
* don't even want to get into that and try to implement the missing pieces in
* the core. We really have other pieces to fix in the driver core mess. :)
*/
int device_rename(struct device *dev, const char *new_name)
{
struct subsys_private *sp = NULL;
struct kobject *kobj = &dev->kobj;
char *old_device_name = NULL;
int error;
bool is_link_renamed = false;
dev = get_device(dev);
if (!dev)
return -EINVAL;
dev_dbg(dev, "renaming to %s\n", new_name);
old_device_name = kstrdup(dev_name(dev), GFP_KERNEL);
if (!old_device_name) {
error = -ENOMEM;
goto out;
}
if (dev->class) {
sp = class_to_subsys(dev->class);
if (!sp) {
error = -EINVAL;
goto out;
}
error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name,
new_name, kobject_namespace(kobj));
if (error)
goto out;
is_link_renamed = true;
}
error = kobject_rename(kobj, new_name);
out:
if (error && is_link_renamed)
sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name,
old_device_name, kobject_namespace(kobj));
subsys_put(sp);
put_device(dev);
kfree(old_device_name);
return error;
}
EXPORT_SYMBOL_GPL(device_rename);
static int device_move_class_links(struct device *dev,
struct device *old_parent,
struct device *new_parent)
{
int error = 0;
if (old_parent)
sysfs_remove_link(&dev->kobj, "device");
if (new_parent)
error = sysfs_create_link(&dev->kobj, &new_parent->kobj,
"device");
return error;
}
/**
* device_move - moves a device to a new parent
* @dev: the pointer to the struct device to be moved
* @new_parent: the new parent of the device (can be NULL)
* @dpm_order: how to reorder the dpm_list
*/
int device_move(struct device *dev, struct device *new_parent,
enum dpm_order dpm_order)
{
int error;
struct device *old_parent;
struct kobject *new_parent_kobj;
dev = get_device(dev);
if (!dev)
return -EINVAL;
device_pm_lock();
new_parent = get_device(new_parent);
new_parent_kobj = get_device_parent(dev, new_parent);
if (IS_ERR(new_parent_kobj)) {
error = PTR_ERR(new_parent_kobj);
put_device(new_parent);
goto out;
}
pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev),
__func__, new_parent ? dev_name(new_parent) : "<NULL>");
error = kobject_move(&dev->kobj, new_parent_kobj);
if (error) {
cleanup_glue_dir(dev, new_parent_kobj);
put_device(new_parent);
goto out;
}
old_parent = dev->parent;
dev->parent = new_parent;
if (old_parent)
klist_remove(&dev->p->knode_parent);
if (new_parent) {
klist_add_tail(&dev->p->knode_parent,
&new_parent->p->klist_children);
set_dev_node(dev, dev_to_node(new_parent));
}
if (dev->class) {
error = device_move_class_links(dev, old_parent, new_parent);
if (error) {
/* We ignore errors on cleanup since we're hosed anyway... */
device_move_class_links(dev, new_parent, old_parent);
if (!kobject_move(&dev->kobj, &old_parent->kobj)) {
if (new_parent)
klist_remove(&dev->p->knode_parent);
dev->parent = old_parent;
if (old_parent) {
klist_add_tail(&dev->p->knode_parent,
&old_parent->p->klist_children);
set_dev_node(dev, dev_to_node(old_parent));
}
}
cleanup_glue_dir(dev, new_parent_kobj);
put_device(new_parent);
goto out;
}
}
switch (dpm_order) {
case DPM_ORDER_NONE:
break;
case DPM_ORDER_DEV_AFTER_PARENT:
device_pm_move_after(dev, new_parent);
devices_kset_move_after(dev, new_parent);
break;
case DPM_ORDER_PARENT_BEFORE_DEV:
device_pm_move_before(new_parent, dev);
devices_kset_move_before(new_parent, dev);
break;
case DPM_ORDER_DEV_LAST:
device_pm_move_last(dev);
devices_kset_move_last(dev);
break;
}
put_device(old_parent);
out:
device_pm_unlock();
put_device(dev);
return error;
}
EXPORT_SYMBOL_GPL(device_move);
static int device_attrs_change_owner(struct device *dev, kuid_t kuid,
kgid_t kgid)
{
struct kobject *kobj = &dev->kobj;
const struct class *class = dev->class;
const struct device_type *type = dev->type;
int error;
if (class) {
/*
* Change the device groups of the device class for @dev to
* @kuid/@kgid.
*/
error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid,
kgid);
if (error)
return error;
}
if (type) {
/*
* Change the device groups of the device type for @dev to
* @kuid/@kgid.
*/
error = sysfs_groups_change_owner(kobj, type->groups, kuid,
kgid);
if (error)
return error;
}
/* Change the device groups of @dev to @kuid/@kgid. */
error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid);
if (error)
return error;
if (device_supports_offline(dev) && !dev->offline_disabled) {
/* Change online device attributes of @dev to @kuid/@kgid. */
error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name,
kuid, kgid);
if (error)
return error;
}
return 0;
}
/**
* device_change_owner - change the owner of an existing device.
* @dev: device.
* @kuid: new owner's kuid
* @kgid: new owner's kgid
*
* This changes the owner of @dev and its corresponding sysfs entries to
* @kuid/@kgid. This function closely mirrors how @dev was added via driver
* core.
*
* Returns 0 on success or error code on failure.
*/
int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid)
{
int error;
struct kobject *kobj = &dev->kobj;
struct subsys_private *sp;
dev = get_device(dev);
if (!dev)
return -EINVAL;
/*
* Change the kobject and the default attributes and groups of the
* ktype associated with it to @kuid/@kgid.
*/
error = sysfs_change_owner(kobj, kuid, kgid);
if (error)
goto out;
/*
* Change the uevent file for @dev to the new owner. The uevent file
* was created in a separate step when @dev got added and we mirror
* that step here.
*/
error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid,
kgid);
if (error)
goto out;
/*
* Change the device groups, the device groups associated with the
* device class, and the groups associated with the device type of @dev
* to @kuid/@kgid.
*/
error = device_attrs_change_owner(dev, kuid, kgid);
if (error)
goto out;
error = dpm_sysfs_change_owner(dev, kuid, kgid);
if (error)
goto out;
/*
* Change the owner of the symlink located in the class directory of
* the device class associated with @dev which points to the actual
* directory entry for @dev to @kuid/@kgid. This ensures that the
* symlink shows the same permissions as its target.
*/
sp = class_to_subsys(dev->class);
if (!sp) {
error = -EINVAL;
goto out;
}
error = sysfs_link_change_owner(&sp->subsys.kobj, &dev->kobj, dev_name(dev), kuid, kgid);
subsys_put(sp);
out:
put_device(dev);
return error;
}
EXPORT_SYMBOL_GPL(device_change_owner);
/**
* device_shutdown - call ->shutdown() on each device to shutdown.
*/
void device_shutdown(void)
{
struct device *dev, *parent;
wait_for_device_probe();
device_block_probing();
cpufreq_suspend();
spin_lock(&devices_kset->list_lock);
/*
* Walk the devices list backward, shutting down each in turn.
* Beware that device unplug events may also start pulling
* devices offline, even as the system is shutting down.
*/
while (!list_empty(&devices_kset->list)) {
dev = list_entry(devices_kset->list.prev, struct device,
kobj.entry);
/*
* hold reference count of device's parent to
* prevent it from being freed because parent's
* lock is to be held
*/
parent = get_device(dev->parent);
get_device(dev);
/*
* Make sure the device is off the kset list, in the
* event that dev->*->shutdown() doesn't remove it.
*/
list_del_init(&dev->kobj.entry);
spin_unlock(&devices_kset->list_lock);
/* hold lock to avoid race with probe/release */
if (parent)
device_lock(parent);
device_lock(dev);
/* Don't allow any more runtime suspends */
pm_runtime_get_noresume(dev);
pm_runtime_barrier(dev);
if (dev->class && dev->class->shutdown_pre) {
if (initcall_debug)
dev_info(dev, "shutdown_pre\n");
dev->class->shutdown_pre(dev);
}
if (dev->bus && dev->bus->shutdown) {
if (initcall_debug)
dev_info(dev, "shutdown\n");
dev->bus->shutdown(dev);
} else if (dev->driver && dev->driver->shutdown) {
if (initcall_debug)
dev_info(dev, "shutdown\n");
dev->driver->shutdown(dev);
}
device_unlock(dev);
if (parent)
device_unlock(parent);
put_device(dev);
put_device(parent);
spin_lock(&devices_kset->list_lock);
}
spin_unlock(&devices_kset->list_lock);
}
/*
* Device logging functions
*/
#ifdef CONFIG_PRINTK
static void
set_dev_info(const struct device *dev, struct dev_printk_info *dev_info)
{
const char *subsys;
memset(dev_info, 0, sizeof(*dev_info));
if (dev->class)
subsys = dev->class->name;
else if (dev->bus)
subsys = dev->bus->name;
else
return;
strscpy(dev_info->subsystem, subsys);
/*
* Add device identifier DEVICE=:
* b12:8 block dev_t
* c127:3 char dev_t
* n8 netdev ifindex
* +sound:card0 subsystem:devname
*/
if (MAJOR(dev->devt)) {
char c;
if (strcmp(subsys, "block") == 0)
c = 'b';
else
c = 'c';
snprintf(dev_info->device, sizeof(dev_info->device),
"%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt));
} else if (strcmp(subsys, "net") == 0) {
struct net_device *net = to_net_dev(dev);
snprintf(dev_info->device, sizeof(dev_info->device),
"n%u", net->ifindex);
} else {
snprintf(dev_info->device, sizeof(dev_info->device),
"+%s:%s", subsys, dev_name(dev));
}
}
int dev_vprintk_emit(int level, const struct device *dev,
const char *fmt, va_list args)
{
struct dev_printk_info dev_info;
set_dev_info(dev, &dev_info);
return vprintk_emit(0, level, &dev_info, fmt, args);
}
EXPORT_SYMBOL(dev_vprintk_emit);
int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = dev_vprintk_emit(level, dev, fmt, args);
va_end(args);
return r;
}
EXPORT_SYMBOL(dev_printk_emit);
static void __dev_printk(const char *level, const struct device *dev,
struct va_format *vaf)
{
if (dev)
dev_printk_emit(level[1] - '0', dev, "%s %s: %pV",
dev_driver_string(dev), dev_name(dev), vaf);
else
printk("%s(NULL device *): %pV", level, vaf);
}
void _dev_printk(const char *level, const struct device *dev,
const char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
__dev_printk(level, dev, &vaf);
va_end(args);
}
EXPORT_SYMBOL(_dev_printk);
#define define_dev_printk_level(func, kern_level) \
void func(const struct device *dev, const char *fmt, ...) \
{ \
struct va_format vaf; \
va_list args; \
\
va_start(args, fmt); \
\
vaf.fmt = fmt; \
vaf.va = &args; \
\
__dev_printk(kern_level, dev, &vaf); \
\
va_end(args); \
} \
EXPORT_SYMBOL(func);
define_dev_printk_level(_dev_emerg, KERN_EMERG);
define_dev_printk_level(_dev_alert, KERN_ALERT);
define_dev_printk_level(_dev_crit, KERN_CRIT);
define_dev_printk_level(_dev_err, KERN_ERR);
define_dev_printk_level(_dev_warn, KERN_WARNING);
define_dev_printk_level(_dev_notice, KERN_NOTICE);
define_dev_printk_level(_dev_info, KERN_INFO);
#endif
static void __dev_probe_failed(const struct device *dev, int err, bool fatal,
const char *fmt, va_list vargsp)
{
struct va_format vaf;
va_list vargs;
/*
* On x86_64 and possibly on other architectures, va_list is actually a
* size-1 array containing a structure. As a result, function parameter
* vargsp decays from T[1] to T*, and &vargsp has type T** rather than
* T(*)[1], which is expected by its assignment to vaf.va below.
*
* One standard way to solve this mess is by creating a copy in a local
* variable of type va_list and then using a pointer to that local copy
* instead, which is the approach employed here.
*/
va_copy(vargs, vargsp);
vaf.fmt = fmt;
vaf.va = &vargs;
switch (err) {
case -EPROBE_DEFER:
device_set_deferred_probe_reason(dev, &vaf);
dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
break;
case -ENOMEM:
/* Don't print anything on -ENOMEM, there's already enough output */
break;
default:
/* Log fatal final failures as errors, otherwise produce warnings */
if (fatal)
dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
else
dev_warn(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
break;
}
va_end(vargs);
}
/**
* dev_err_probe - probe error check and log helper
* @dev: the pointer to the struct device
* @err: error value to test
* @fmt: printf-style format string
* @...: arguments as specified in the format string
*
* This helper implements common pattern present in probe functions for error
* checking: print debug or error message depending if the error value is
* -EPROBE_DEFER and propagate error upwards.
* In case of -EPROBE_DEFER it sets also defer probe reason, which can be
* checked later by reading devices_deferred debugfs attribute.
* It replaces the following code sequence::
*
* if (err != -EPROBE_DEFER)
* dev_err(dev, ...);
* else
* dev_dbg(dev, ...);
* return err;
*
* with::
*
* return dev_err_probe(dev, err, ...);
*
* Using this helper in your probe function is totally fine even if @err
* is known to never be -EPROBE_DEFER.
* The benefit compared to a normal dev_err() is the standardized format
* of the error code, which is emitted symbolically (i.e. you get "EAGAIN"
* instead of "-35"), and having the error code returned allows more
* compact error paths.
*
* Returns @err.
*/
int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
{
va_list vargs;
va_start(vargs, fmt);
/* Use dev_err() for logging when err doesn't equal -EPROBE_DEFER */
__dev_probe_failed(dev, err, true, fmt, vargs);
va_end(vargs);
return err;
}
EXPORT_SYMBOL_GPL(dev_err_probe);
/**
* dev_warn_probe - probe error check and log helper
* @dev: the pointer to the struct device
* @err: error value to test
* @fmt: printf-style format string
* @...: arguments as specified in the format string
*
* This helper implements common pattern present in probe functions for error
* checking: print debug or warning message depending if the error value is
* -EPROBE_DEFER and propagate error upwards.
* In case of -EPROBE_DEFER it sets also defer probe reason, which can be
* checked later by reading devices_deferred debugfs attribute.
* It replaces the following code sequence::
*
* if (err != -EPROBE_DEFER)
* dev_warn(dev, ...);
* else
* dev_dbg(dev, ...);
* return err;
*
* with::
*
* return dev_warn_probe(dev, err, ...);
*
* Using this helper in your probe function is totally fine even if @err
* is known to never be -EPROBE_DEFER.
* The benefit compared to a normal dev_warn() is the standardized format
* of the error code, which is emitted symbolically (i.e. you get "EAGAIN"
* instead of "-35"), and having the error code returned allows more
* compact error paths.
*
* Returns @err.
*/
int dev_warn_probe(const struct device *dev, int err, const char *fmt, ...)
{
va_list vargs;
va_start(vargs, fmt);
/* Use dev_warn() for logging when err doesn't equal -EPROBE_DEFER */
__dev_probe_failed(dev, err, false, fmt, vargs);
va_end(vargs);
return err;
}
EXPORT_SYMBOL_GPL(dev_warn_probe);
static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
{
return fwnode && !IS_ERR(fwnode->secondary);
}
/**
* set_primary_fwnode - Change the primary firmware node of a given device.
* @dev: Device to handle.
* @fwnode: New primary firmware node of the device.
*
* Set the device's firmware node pointer to @fwnode, but if a secondary
* firmware node of the device is present, preserve it.
*
* Valid fwnode cases are:
* - primary --> secondary --> -ENODEV
* - primary --> NULL
* - secondary --> -ENODEV
* - NULL
*/
void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
{
struct device *parent = dev->parent;
struct fwnode_handle *fn = dev->fwnode;
if (fwnode) {
if (fwnode_is_primary(fn))
fn = fn->secondary;
if (fn) {
WARN_ON(fwnode->secondary);
fwnode->secondary = fn;
}
dev->fwnode = fwnode;
} else {
if (fwnode_is_primary(fn)) {
dev->fwnode = fn->secondary;
/* Skip nullifying fn->secondary if the primary is shared */
if (parent && fn == parent->fwnode)
return;
/* Set fn->secondary = NULL, so fn remains the primary fwnode */
fn->secondary = NULL;
} else {
dev->fwnode = NULL;
}
}
}
EXPORT_SYMBOL_GPL(set_primary_fwnode);
/**
* set_secondary_fwnode - Change the secondary firmware node of a given device.
* @dev: Device to handle.
* @fwnode: New secondary firmware node of the device.
*
* If a primary firmware node of the device is present, set its secondary
* pointer to @fwnode. Otherwise, set the device's firmware node pointer to
* @fwnode.
*/
void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
{
if (fwnode)
fwnode->secondary = ERR_PTR(-ENODEV);
if (fwnode_is_primary(dev->fwnode))
dev->fwnode->secondary = fwnode;
else
dev->fwnode = fwnode;
}
EXPORT_SYMBOL_GPL(set_secondary_fwnode);
/**
* device_remove_of_node - Remove an of_node from a device
* @dev: device whose device tree node is being removed
*/
void device_remove_of_node(struct device *dev)
{
dev = get_device(dev);
if (!dev)
return;
if (!dev->of_node)
goto end;
if (dev->fwnode == of_fwnode_handle(dev->of_node))
dev->fwnode = NULL;
of_node_put(dev->of_node);
dev->of_node = NULL;
end:
put_device(dev);
}
EXPORT_SYMBOL_GPL(device_remove_of_node);
/**
* device_add_of_node - Add an of_node to an existing device
* @dev: device whose device tree node is being added
* @of_node: of_node to add
*
* Return: 0 on success or error code on failure.
*/
int device_add_of_node(struct device *dev, struct device_node *of_node)
{
int ret;
if (!of_node)
return -EINVAL;
dev = get_device(dev);
if (!dev)
return -EINVAL;
if (dev->of_node) {
dev_err(dev, "Cannot replace node %pOF with %pOF\n",
dev->of_node, of_node);
ret = -EBUSY;
goto end;
}
dev->of_node = of_node_get(of_node);
if (!dev->fwnode)
dev->fwnode = of_fwnode_handle(of_node);
ret = 0;
end:
put_device(dev);
return ret;
}
EXPORT_SYMBOL_GPL(device_add_of_node);
/**
* device_set_of_node_from_dev - reuse device-tree node of another device
* @dev: device whose device-tree node is being set
* @dev2: device whose device-tree node is being reused
*
* Takes another reference to the new device-tree node after first dropping
* any reference held to the old node.
*/
void device_set_of_node_from_dev(struct device *dev, const struct device *dev2)
{
of_node_put(dev->of_node);
dev->of_node = of_node_get(dev2->of_node);
dev->of_node_reused = true;
}
EXPORT_SYMBOL_GPL(device_set_of_node_from_dev);
void device_set_node(struct device *dev, struct fwnode_handle *fwnode)
{
dev->fwnode = fwnode;
dev->of_node = to_of_node(fwnode);
}
EXPORT_SYMBOL_GPL(device_set_node);
int device_match_name(struct device *dev, const void *name)
{
return sysfs_streq(dev_name(dev), name);
}
EXPORT_SYMBOL_GPL(device_match_name);
int device_match_type(struct device *dev, const void *type)
{
return dev->type == type;
}
EXPORT_SYMBOL_GPL(device_match_type);
int device_match_of_node(struct device *dev, const void *np)
{
return np && dev->of_node == np;
}
EXPORT_SYMBOL_GPL(device_match_of_node);
int device_match_fwnode(struct device *dev, const void *fwnode)
{
return fwnode && dev_fwnode(dev) == fwnode;
}
EXPORT_SYMBOL_GPL(device_match_fwnode);
int device_match_devt(struct device *dev, const void *pdevt)
{
return dev->devt == *(dev_t *)pdevt;
}
EXPORT_SYMBOL_GPL(device_match_devt);
int device_match_acpi_dev(struct device *dev, const void *adev)
{
return adev && ACPI_COMPANION(dev) == adev;
}
EXPORT_SYMBOL(device_match_acpi_dev);
int device_match_acpi_handle(struct device *dev, const void *handle)
{
return handle && ACPI_HANDLE(dev) == handle;
}
EXPORT_SYMBOL(device_match_acpi_handle);
int device_match_any(struct device *dev, const void *unused)
{
return 1;
}
EXPORT_SYMBOL_GPL(device_match_any);
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/crypto/hooks.c
*
* Encryption hooks for higher-level filesystem operations.
*/
#include "fscrypt_private.h"
/**
* fscrypt_file_open() - prepare to open a possibly-encrypted regular file
* @inode: the inode being opened
* @filp: the struct file being set up
*
* Currently, an encrypted regular file can only be opened if its encryption key
* is available; access to the raw encrypted contents is not supported.
* Therefore, we first set up the inode's encryption key (if not already done)
* and return an error if it's unavailable.
*
* We also verify that if the parent directory (from the path via which the file
* is being opened) is encrypted, then the inode being opened uses the same
* encryption policy. This is needed as part of the enforcement that all files
* in an encrypted directory tree use the same encryption policy, as a
* protection against certain types of offline attacks. Note that this check is
* needed even when opening an *unencrypted* file, since it's forbidden to have
* an unencrypted file in an encrypted directory.
*
* Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
*/
int fscrypt_file_open(struct inode *inode, struct file *filp)
{
int err;
struct dentry *dentry, *dentry_parent;
struct inode *inode_parent;
err = fscrypt_require_key(inode);
if (err)
return err;
dentry = file_dentry(filp);
/*
* Getting a reference to the parent dentry is needed for the actual
* encryption policy comparison, but it's expensive on multi-core
* systems. Since this function runs on unencrypted files too, start
* with a lightweight RCU-mode check for the parent directory being
* unencrypted (in which case it's fine for the child to be either
* unencrypted, or encrypted with any policy). Only continue on to the
* full policy check if the parent directory is actually encrypted.
*/
rcu_read_lock();
dentry_parent = READ_ONCE(dentry->d_parent);
inode_parent = d_inode_rcu(dentry_parent);
if (inode_parent != NULL && !IS_ENCRYPTED(inode_parent)) {
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
dentry_parent = dget_parent(dentry);
if (!fscrypt_has_permitted_context(d_inode(dentry_parent), inode)) {
fscrypt_warn(inode,
"Inconsistent encryption context (parent directory: %lu)",
d_inode(dentry_parent)->i_ino);
err = -EPERM;
}
dput(dentry_parent);
return err;
}
EXPORT_SYMBOL_GPL(fscrypt_file_open);
int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
struct dentry *dentry)
{
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
/*
* We don't need to separately check that the directory inode's key is
* available, as it's implied by the dentry not being a no-key name.
*/
if (!fscrypt_has_permitted_context(dir, inode))
return -EXDEV;
return 0;
}
EXPORT_SYMBOL_GPL(__fscrypt_prepare_link);
int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
if (fscrypt_is_nokey_name(old_dentry) ||
fscrypt_is_nokey_name(new_dentry))
return -ENOKEY;
/*
* We don't need to separately check that the directory inodes' keys are
* available, as it's implied by the dentries not being no-key names.
*/
if (old_dir != new_dir) {
if (IS_ENCRYPTED(new_dir) &&
!fscrypt_has_permitted_context(new_dir,
d_inode(old_dentry)))
return -EXDEV;
if ((flags & RENAME_EXCHANGE) &&
IS_ENCRYPTED(old_dir) &&
!fscrypt_has_permitted_context(old_dir,
d_inode(new_dentry)))
return -EXDEV;
}
return 0;
}
EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename);
int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
struct fscrypt_name *fname)
{
int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname);
if (err && err != -ENOENT)
return err;
fscrypt_prepare_dentry(dentry, fname->is_nokey_name);
return err;
}
EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
/**
* fscrypt_prepare_lookup_partial() - prepare lookup without filename setup
* @dir: the encrypted directory being searched
* @dentry: the dentry being looked up in @dir
*
* This function should be used by the ->lookup and ->atomic_open methods of
* filesystems that handle filename encryption and no-key name encoding
* themselves and thus can't use fscrypt_prepare_lookup(). Like
* fscrypt_prepare_lookup(), this will try to set up the directory's encryption
* key and will set DCACHE_NOKEY_NAME on the dentry if the key is unavailable.
* However, this function doesn't set up a struct fscrypt_name for the filename.
*
* Return: 0 on success; -errno on error. Note that the encryption key being
* unavailable is not considered an error. It is also not an error if
* the encryption policy is unsupported by this kernel; that is treated
* like the key being unavailable, so that files can still be deleted.
*/
int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry)
{
int err = fscrypt_get_encryption_info(dir, true);
bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir));
fscrypt_prepare_dentry(dentry, is_nokey_name);
return err;
}
EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial);
int __fscrypt_prepare_readdir(struct inode *dir)
{
return fscrypt_get_encryption_info(dir, true);
}
EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir);
int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr)
{
if (attr->ia_valid & ATTR_SIZE)
return fscrypt_require_key(d_inode(dentry));
return 0;
}
EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr);
/**
* fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS
* @inode: the inode on which flags are being changed
* @oldflags: the old flags
* @flags: the new flags
*
* The caller should be holding i_rwsem for write.
*
* Return: 0 on success; -errno if the flags change isn't allowed or if
* another error occurs.
*/
int fscrypt_prepare_setflags(struct inode *inode,
unsigned int oldflags, unsigned int flags)
{
struct fscrypt_inode_info *ci;
struct fscrypt_master_key *mk;
int err;
/*
* When the CASEFOLD flag is set on an encrypted directory, we must
* derive the secret key needed for the dirhash. This is only possible
* if the directory uses a v2 encryption policy.
*/
if (IS_ENCRYPTED(inode) && (flags & ~oldflags & FS_CASEFOLD_FL)) { err = fscrypt_require_key(inode);
if (err)
return err;
ci = inode->i_crypt_info;
if (ci->ci_policy.version != FSCRYPT_POLICY_V2)
return -EINVAL;
mk = ci->ci_master_key;
down_read(&mk->mk_sem);
if (mk->mk_present) err = fscrypt_derive_dirhash_key(ci, mk);
else
err = -ENOKEY;
up_read(&mk->mk_sem);
return err;
}
return 0;
}
/**
* fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
* @dir: directory in which the symlink is being created
* @target: plaintext symlink target
* @len: length of @target excluding null terminator
* @max_len: space the filesystem has available to store the symlink target
* @disk_link: (out) the on-disk symlink target being prepared
*
* This function computes the size the symlink target will require on-disk,
* stores it in @disk_link->len, and validates it against @max_len. An
* encrypted symlink may be longer than the original.
*
* Additionally, @disk_link->name is set to @target if the symlink will be
* unencrypted, but left NULL if the symlink will be encrypted. For encrypted
* symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
* on-disk target later. (The reason for the two-step process is that some
* filesystems need to know the size of the symlink target before creating the
* inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
*
* Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
* -ENOKEY if the encryption key is missing, or another -errno code if a problem
* occurred while setting up the encryption key.
*/
int fscrypt_prepare_symlink(struct inode *dir, const char *target,
unsigned int len, unsigned int max_len,
struct fscrypt_str *disk_link)
{
const union fscrypt_policy *policy;
/*
* To calculate the size of the encrypted symlink target we need to know
* the amount of NUL padding, which is determined by the flags set in
* the encryption policy which will be inherited from the directory.
*/
policy = fscrypt_policy_to_inherit(dir);
if (policy == NULL) {
/* Not encrypted */
disk_link->name = (unsigned char *)target;
disk_link->len = len + 1;
if (disk_link->len > max_len)
return -ENAMETOOLONG;
return 0;
}
if (IS_ERR(policy))
return PTR_ERR(policy);
/*
* Calculate the size of the encrypted symlink and verify it won't
* exceed max_len. Note that for historical reasons, encrypted symlink
* targets are prefixed with the ciphertext length, despite this
* actually being redundant with i_size. This decreases by 2 bytes the
* longest symlink target we can accept.
*
* We could recover 1 byte by not counting a null terminator, but
* counting it (even though it is meaningless for ciphertext) is simpler
* for now since filesystems will assume it is there and subtract it.
*/
if (!__fscrypt_fname_encrypted_size(policy, len,
max_len - sizeof(struct fscrypt_symlink_data) - 1,
&disk_link->len))
return -ENAMETOOLONG;
disk_link->len += sizeof(struct fscrypt_symlink_data) + 1;
disk_link->name = NULL;
return 0;
}
EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink);
int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
unsigned int len, struct fscrypt_str *disk_link)
{
int err;
struct qstr iname = QSTR_INIT(target, len);
struct fscrypt_symlink_data *sd;
unsigned int ciphertext_len;
/*
* fscrypt_prepare_new_inode() should have already set up the new
* symlink inode's encryption key. We don't wait until now to do it,
* since we may be in a filesystem transaction now.
*/
if (WARN_ON_ONCE(!fscrypt_has_encryption_key(inode)))
return -ENOKEY;
if (disk_link->name) {
/* filesystem-provided buffer */
sd = (struct fscrypt_symlink_data *)disk_link->name;
} else {
sd = kmalloc(disk_link->len, GFP_NOFS);
if (!sd)
return -ENOMEM;
}
ciphertext_len = disk_link->len - sizeof(*sd) - 1;
sd->len = cpu_to_le16(ciphertext_len);
err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path,
ciphertext_len);
if (err)
goto err_free_sd;
/*
* Null-terminating the ciphertext doesn't make sense, but we still
* count the null terminator in the length, so we might as well
* initialize it just in case the filesystem writes it out.
*/
sd->encrypted_path[ciphertext_len] = '\0';
/* Cache the plaintext symlink target for later use by get_link() */
err = -ENOMEM;
inode->i_link = kmemdup(target, len + 1, GFP_NOFS);
if (!inode->i_link)
goto err_free_sd;
if (!disk_link->name)
disk_link->name = (unsigned char *)sd;
return 0;
err_free_sd:
if (!disk_link->name)
kfree(sd);
return err;
}
EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
/**
* fscrypt_get_symlink() - get the target of an encrypted symlink
* @inode: the symlink inode
* @caddr: the on-disk contents of the symlink
* @max_size: size of @caddr buffer
* @done: if successful, will be set up to free the returned target if needed
*
* If the symlink's encryption key is available, we decrypt its target.
* Otherwise, we encode its target for presentation.
*
* This may sleep, so the filesystem must have dropped out of RCU mode already.
*
* Return: the presentable symlink target or an ERR_PTR()
*/
const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
unsigned int max_size,
struct delayed_call *done)
{
const struct fscrypt_symlink_data *sd;
struct fscrypt_str cstr, pstr;
bool has_key;
int err;
/* This is for encrypted symlinks only */
if (WARN_ON_ONCE(!IS_ENCRYPTED(inode)))
return ERR_PTR(-EINVAL);
/* If the decrypted target is already cached, just return it. */
pstr.name = READ_ONCE(inode->i_link);
if (pstr.name)
return pstr.name;
/*
* Try to set up the symlink's encryption key, but we can continue
* regardless of whether the key is available or not.
*/
err = fscrypt_get_encryption_info(inode, false);
if (err)
return ERR_PTR(err);
has_key = fscrypt_has_encryption_key(inode);
/*
* For historical reasons, encrypted symlink targets are prefixed with
* the ciphertext length, even though this is redundant with i_size.
*/
if (max_size < sizeof(*sd) + 1)
return ERR_PTR(-EUCLEAN);
sd = caddr;
cstr.name = (unsigned char *)sd->encrypted_path;
cstr.len = le16_to_cpu(sd->len);
if (cstr.len == 0)
return ERR_PTR(-EUCLEAN);
if (cstr.len + sizeof(*sd) > max_size)
return ERR_PTR(-EUCLEAN);
err = fscrypt_fname_alloc_buffer(cstr.len, &pstr);
if (err)
return ERR_PTR(err);
err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
if (err)
goto err_kfree;
err = -EUCLEAN;
if (pstr.name[0] == '\0')
goto err_kfree;
pstr.name[pstr.len] = '\0';
/*
* Cache decrypted symlink targets in i_link for later use. Don't cache
* symlink targets encoded without the key, since those become outdated
* once the key is added. This pairs with the READ_ONCE() above and in
* the VFS path lookup code.
*/
if (!has_key ||
cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL)
set_delayed_call(done, kfree_link, pstr.name);
return pstr.name;
err_kfree:
kfree(pstr.name);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(fscrypt_get_symlink);
/**
* fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks
* @path: the path for the encrypted symlink being queried
* @stat: the struct being filled with the symlink's attributes
*
* Override st_size of encrypted symlinks to be the length of the decrypted
* symlink target (or the no-key encoded symlink target, if the key is
* unavailable) rather than the length of the encrypted symlink target. This is
* necessary for st_size to match the symlink target that userspace actually
* sees. POSIX requires this, and some userspace programs depend on it.
*
* This requires reading the symlink target from disk if needed, setting up the
* inode's encryption key if possible, and then decrypting or encoding the
* symlink target. This makes lstat() more heavyweight than is normally the
* case. However, decrypted symlink targets will be cached in ->i_link, so
* usually the symlink won't have to be read and decrypted again later if/when
* it is actually followed, readlink() is called, or lstat() is called again.
*
* Return: 0 on success, -errno on failure
*/
int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat)
{
struct dentry *dentry = path->dentry;
struct inode *inode = d_inode(dentry);
const char *link;
DEFINE_DELAYED_CALL(done);
/*
* To get the symlink target that userspace will see (whether it's the
* decrypted target or the no-key encoded target), we can just get it in
* the same way the VFS does during path resolution and readlink().
*/
link = READ_ONCE(inode->i_link);
if (!link) {
link = inode->i_op->get_link(dentry, inode, &done);
if (IS_ERR(link))
return PTR_ERR(link);
}
stat->size = strlen(link);
do_delayed_call(&done);
return 0;
}
EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr);
/*
* Linux Security Module interfaces
*
* Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
* Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com>
* Copyright (C) 2001 James Morris <jmorris@intercode.com.au>
* Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group)
* Copyright (C) 2015 Intel Corporation.
* Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com>
* Copyright (C) 2016 Mellanox Techonologies
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* Due to this file being licensed under the GPL there is controversy over
* whether this permits you to write a module that #includes this file
* without placing your module under the GPL. Please consult a lawyer for
* advice before doing this.
*
*/
#ifndef __LINUX_LSM_HOOKS_H
#define __LINUX_LSM_HOOKS_H
#include <uapi/linux/lsm.h>
#include <linux/security.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/xattr.h>
#include <linux/static_call.h>
#include <linux/unroll.h>
#include <linux/jump_label.h>
#include <linux/lsm_count.h>
union security_list_options {
#define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__);
#include "lsm_hook_defs.h"
#undef LSM_HOOK
void *lsm_func_addr;
};
/*
* @key: static call key as defined by STATIC_CALL_KEY
* @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP
* @hl: The security_hook_list as initialized by the owning LSM.
* @active: Enabled when the static call has an LSM hook associated.
*/
struct lsm_static_call {
struct static_call_key *key;
void *trampoline;
struct security_hook_list *hl;
/* this needs to be true or false based on what the key defaults to */
struct static_key_false *active;
} __randomize_layout;
/*
* Table of the static calls for each LSM hook.
* Once the LSMs are initialized, their callbacks will be copied to these
* tables such that the calls are filled backwards (from last to first).
* This way, we can jump directly to the first used static call, and execute
* all of them after. This essentially makes the entry point
* dynamic to adapt the number of static calls to the number of callbacks.
*/
struct lsm_static_calls_table {
#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
struct lsm_static_call NAME[MAX_LSM_COUNT];
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
} __packed __randomize_layout;
/**
* struct lsm_id - Identify a Linux Security Module.
* @lsm: name of the LSM, must be approved by the LSM maintainers
* @id: LSM ID number from uapi/linux/lsm.h
*
* Contains the information that identifies the LSM.
*/
struct lsm_id {
const char *name;
u64 id;
};
/*
* Security module hook list structure.
* For use with generic list macros for common operations.
*
* struct security_hook_list - Contents of a cacheable, mappable object.
* @scalls: The beginning of the array of static calls assigned to this hook.
* @hook: The callback for the hook.
* @lsm: The name of the lsm that owns this hook.
*/
struct security_hook_list {
struct lsm_static_call *scalls;
union security_list_options hook;
const struct lsm_id *lsmid;
} __randomize_layout;
/*
* Security blob size or offset data.
*/
struct lsm_blob_sizes {
int lbs_cred;
int lbs_file;
int lbs_ib;
int lbs_inode;
int lbs_sock;
int lbs_superblock;
int lbs_ipc;
int lbs_key;
int lbs_msg_msg;
int lbs_perf_event;
int lbs_task;
int lbs_xattr_count; /* number of xattr slots in new_xattrs array */
int lbs_tun_dev;
int lbs_bdev;
};
/*
* LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void
* LSM hooks (in include/linux/lsm_hook_defs.h).
*/
#define LSM_RET_VOID ((void) 0)
/*
* Initializing a security_hook_list structure takes
* up a lot of space in a source file. This macro takes
* care of the common case and reduces the amount of
* text involved.
*/
#define LSM_HOOK_INIT(NAME, HOOK) \
{ \
.scalls = static_calls_table.NAME, \
.hook = { .NAME = HOOK } \
}
extern void security_add_hooks(struct security_hook_list *hooks, int count,
const struct lsm_id *lsmid);
#define LSM_FLAG_LEGACY_MAJOR BIT(0)
#define LSM_FLAG_EXCLUSIVE BIT(1)
enum lsm_order {
LSM_ORDER_FIRST = -1, /* This is only for capabilities. */
LSM_ORDER_MUTABLE = 0,
LSM_ORDER_LAST = 1, /* This is only for integrity. */
};
struct lsm_info {
const char *name; /* Required. */
enum lsm_order order; /* Optional: default is LSM_ORDER_MUTABLE */
unsigned long flags; /* Optional: flags describing LSM */
int *enabled; /* Optional: controlled by CONFIG_LSM */
int (*init)(void); /* Required. */
struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */
};
#define DEFINE_LSM(lsm) \
static struct lsm_info __lsm_##lsm \
__used __section(".lsm_info.init") \
__aligned(sizeof(unsigned long))
#define DEFINE_EARLY_LSM(lsm) \
static struct lsm_info __early_lsm_##lsm \
__used __section(".early_lsm_info.init") \
__aligned(sizeof(unsigned long))
/* DO NOT tamper with these variables outside of the LSM framework */
extern char *lsm_names;
extern struct lsm_static_calls_table static_calls_table __ro_after_init;
extern struct lsm_info __start_lsm_info[], __end_lsm_info[];
extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
/**
* lsm_get_xattr_slot - Return the next available slot and increment the index
* @xattrs: array storing LSM-provided xattrs
* @xattr_count: number of already stored xattrs (updated)
*
* Retrieve the first available slot in the @xattrs array to fill with an xattr,
* and increment @xattr_count.
*
* Return: The slot to fill in @xattrs if non-NULL, NULL otherwise.
*/
static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs,
int *xattr_count)
{
if (unlikely(!xattrs))
return NULL;
return &xattrs[(*xattr_count)++];
}
#endif /* ! __LINUX_LSM_HOOKS_H */
/*
* memfd_create system call and file sealing support
*
* Code was originally included in shmem.c, and broken out to facilitate
* use by hugetlbfs as well as tmpfs.
*
* This file is released under the GPL.
*/
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/khugepaged.h>
#include <linux/syscalls.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/memfd.h>
#include <linux/pid_namespace.h>
#include <uapi/linux/memfd.h>
/*
* We need a tag: a new tag would expand every xa_node by 8 bytes,
* so reuse a tag which we firmly believe is never set or cleared on tmpfs
* or hugetlbfs because they are memory only filesystems.
*/
#define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE
#define LAST_SCAN 4 /* about 150ms max */
static bool memfd_folio_has_extra_refs(struct folio *folio)
{
return folio_ref_count(folio) - folio_mapcount(folio) !=
folio_nr_pages(folio);
}
static void memfd_tag_pins(struct xa_state *xas)
{
struct folio *folio;
int latency = 0;
lru_add_drain();
xas_lock_irq(xas);
xas_for_each(xas, folio, ULONG_MAX) {
if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio))
xas_set_mark(xas, MEMFD_TAG_PINNED);
if (++latency < XA_CHECK_SCHED)
continue;
latency = 0;
xas_pause(xas);
xas_unlock_irq(xas);
cond_resched();
xas_lock_irq(xas);
}
xas_unlock_irq(xas);
}
/*
* This is a helper function used by memfd_pin_user_pages() in GUP (gup.c).
* It is mainly called to allocate a folio in a memfd when the caller
* (memfd_pin_folios()) cannot find a folio in the page cache at a given
* index in the mapping.
*/
struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
{
#ifdef CONFIG_HUGETLB_PAGE
struct folio *folio;
gfp_t gfp_mask;
int err;
if (is_file_hugepages(memfd)) {
/*
* The folio would most likely be accessed by a DMA driver,
* therefore, we have zone memory constraints where we can
* alloc from. Also, the folio will be pinned for an indefinite
* amount of time, so it is not expected to be migrated away.
*/
struct hstate *h = hstate_file(memfd);
gfp_mask = htlb_alloc_mask(h);
gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE);
idx >>= huge_page_order(h);
folio = alloc_hugetlb_folio_reserve(h,
numa_node_id(),
NULL,
gfp_mask);
if (folio) {
err = hugetlb_add_to_page_cache(folio,
memfd->f_mapping,
idx);
if (err) {
folio_put(folio);
return ERR_PTR(err);
}
folio_unlock(folio);
return folio;
}
return ERR_PTR(-ENOMEM);
}
#endif
return shmem_read_folio(memfd->f_mapping, idx);
}
/*
* Setting SEAL_WRITE requires us to verify there's no pending writer. However,
* via get_user_pages(), drivers might have some pending I/O without any active
* user-space mappings (eg., direct-IO, AIO). Therefore, we look at all folios
* and see whether it has an elevated ref-count. If so, we tag them and wait for
* them to be dropped.
* The caller must guarantee that no new user will acquire writable references
* to those folios to avoid races.
*/
static int memfd_wait_for_pins(struct address_space *mapping)
{
XA_STATE(xas, &mapping->i_pages, 0);
struct folio *folio;
int error, scan;
memfd_tag_pins(&xas);
error = 0;
for (scan = 0; scan <= LAST_SCAN; scan++) {
int latency = 0;
if (!xas_marked(&xas, MEMFD_TAG_PINNED))
break;
if (!scan)
lru_add_drain_all();
else if (schedule_timeout_killable((HZ << scan) / 200))
scan = LAST_SCAN;
xas_set(&xas, 0);
xas_lock_irq(&xas);
xas_for_each_marked(&xas, folio, ULONG_MAX, MEMFD_TAG_PINNED) {
bool clear = true;
if (!xa_is_value(folio) &&
memfd_folio_has_extra_refs(folio)) {
/*
* On the last scan, we clean up all those tags
* we inserted; but make a note that we still
* found folios pinned.
*/
if (scan == LAST_SCAN)
error = -EBUSY;
else
clear = false;
}
if (clear)
xas_clear_mark(&xas, MEMFD_TAG_PINNED);
if (++latency < XA_CHECK_SCHED)
continue;
latency = 0;
xas_pause(&xas);
xas_unlock_irq(&xas);
cond_resched();
xas_lock_irq(&xas);
}
xas_unlock_irq(&xas);
}
return error;
}
static unsigned int *memfd_file_seals_ptr(struct file *file)
{
if (shmem_file(file))
return &SHMEM_I(file_inode(file))->seals;
#ifdef CONFIG_HUGETLBFS
if (is_file_hugepages(file))
return &HUGETLBFS_I(file_inode(file))->seals;
#endif
return NULL;
}
#define F_ALL_SEALS (F_SEAL_SEAL | \
F_SEAL_EXEC | \
F_SEAL_SHRINK | \
F_SEAL_GROW | \
F_SEAL_WRITE | \
F_SEAL_FUTURE_WRITE)
static int memfd_add_seals(struct file *file, unsigned int seals)
{
struct inode *inode = file_inode(file);
unsigned int *file_seals;
int error;
/*
* SEALING
* Sealing allows multiple parties to share a tmpfs or hugetlbfs file
* but restrict access to a specific subset of file operations. Seals
* can only be added, but never removed. This way, mutually untrusted
* parties can share common memory regions with a well-defined policy.
* A malicious peer can thus never perform unwanted operations on a
* shared object.
*
* Seals are only supported on special tmpfs or hugetlbfs files and
* always affect the whole underlying inode. Once a seal is set, it
* may prevent some kinds of access to the file. Currently, the
* following seals are defined:
* SEAL_SEAL: Prevent further seals from being set on this file
* SEAL_SHRINK: Prevent the file from shrinking
* SEAL_GROW: Prevent the file from growing
* SEAL_WRITE: Prevent write access to the file
* SEAL_EXEC: Prevent modification of the exec bits in the file mode
*
* As we don't require any trust relationship between two parties, we
* must prevent seals from being removed. Therefore, sealing a file
* only adds a given set of seals to the file, it never touches
* existing seals. Furthermore, the "setting seals"-operation can be
* sealed itself, which basically prevents any further seal from being
* added.
*
* Semantics of sealing are only defined on volatile files. Only
* anonymous tmpfs and hugetlbfs files support sealing. More
* importantly, seals are never written to disk. Therefore, there's
* no plan to support it on other file types.
*/
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
if (seals & ~(unsigned int)F_ALL_SEALS)
return -EINVAL;
inode_lock(inode);
file_seals = memfd_file_seals_ptr(file);
if (!file_seals) {
error = -EINVAL;
goto unlock;
}
if (*file_seals & F_SEAL_SEAL) {
error = -EPERM;
goto unlock;
}
if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) {
error = mapping_deny_writable(file->f_mapping);
if (error)
goto unlock;
error = memfd_wait_for_pins(file->f_mapping);
if (error) {
mapping_allow_writable(file->f_mapping);
goto unlock;
}
}
/*
* SEAL_EXEC implies SEAL_WRITE, making W^X from the start.
*/
if (seals & F_SEAL_EXEC && inode->i_mode & 0111)
seals |= F_SEAL_SHRINK|F_SEAL_GROW|F_SEAL_WRITE|F_SEAL_FUTURE_WRITE;
*file_seals |= seals;
error = 0;
unlock:
inode_unlock(inode);
return error;
}
static int memfd_get_seals(struct file *file)
{
unsigned int *seals = memfd_file_seals_ptr(file);
return seals ? *seals : -EINVAL;
}
long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
{
long error;
switch (cmd) {
case F_ADD_SEALS:
error = memfd_add_seals(file, arg);
break;
case F_GET_SEALS:
error = memfd_get_seals(file);
break;
default:
error = -EINVAL;
break;
}
return error;
}
#define MFD_NAME_PREFIX "memfd:"
#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC)
static int check_sysctl_memfd_noexec(unsigned int *flags)
{
#ifdef CONFIG_SYSCTL
struct pid_namespace *ns = task_active_pid_ns(current);
int sysctl = pidns_memfd_noexec_scope(ns);
if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL)
*flags |= MFD_NOEXEC_SEAL;
else
*flags |= MFD_EXEC;
}
if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) {
pr_err_ratelimited(
"%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n",
current->comm, task_pid_nr(current), sysctl);
return -EACCES;
}
#endif
return 0;
}
static inline bool is_write_sealed(unsigned int seals)
{
return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
}
static int check_write_seal(unsigned long *vm_flags_ptr)
{
unsigned long vm_flags = *vm_flags_ptr;
unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE);
/* If a private mapping then writability is irrelevant. */
if (!(mask & VM_SHARED))
return 0;
/*
* New PROT_WRITE and MAP_SHARED mmaps are not allowed when
* write seals are active.
*/
if (mask & VM_WRITE)
return -EPERM;
/*
* This is a read-only mapping, disallow mprotect() from making a
* write-sealed mapping writable in future.
*/
*vm_flags_ptr &= ~VM_MAYWRITE;
return 0;
}
int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr)
{
int err = 0;
unsigned int *seals_ptr = memfd_file_seals_ptr(file); unsigned int seals = seals_ptr ? *seals_ptr : 0; if (is_write_sealed(seals)) err = check_write_seal(vm_flags_ptr);
return err;
}
static int sanitize_flags(unsigned int *flags_ptr)
{
unsigned int flags = *flags_ptr;
if (!(flags & MFD_HUGETLB)) {
if (flags & ~(unsigned int)MFD_ALL_FLAGS)
return -EINVAL;
} else {
/* Allow huge page size encoding in flags. */
if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
return -EINVAL;
}
/* Invalid if both EXEC and NOEXEC_SEAL are set.*/
if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL))
return -EINVAL;
return check_sysctl_memfd_noexec(flags_ptr);
}
static char *alloc_name(const char __user *uname)
{
int error;
char *name;
long len;
name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
if (!name)
return ERR_PTR(-ENOMEM);
strcpy(name, MFD_NAME_PREFIX);
/* returned length does not include terminating zero */
len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1);
if (len < 0) {
error = -EFAULT;
goto err_name;
} else if (len > MFD_NAME_MAX_LEN) {
error = -EINVAL;
goto err_name;
}
return name;
err_name:
kfree(name);
return ERR_PTR(error);
}
static struct file *alloc_file(const char *name, unsigned int flags)
{
unsigned int *file_seals;
struct file *file;
if (flags & MFD_HUGETLB) {
file = hugetlb_file_setup(name, 0, VM_NORESERVE,
HUGETLB_ANONHUGE_INODE,
(flags >> MFD_HUGE_SHIFT) &
MFD_HUGE_MASK);
} else {
file = shmem_file_setup(name, 0, VM_NORESERVE);
}
if (IS_ERR(file))
return file;
file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
file->f_flags |= O_LARGEFILE;
if (flags & MFD_NOEXEC_SEAL) {
struct inode *inode = file_inode(file);
inode->i_mode &= ~0111;
file_seals = memfd_file_seals_ptr(file);
if (file_seals) {
*file_seals &= ~F_SEAL_SEAL;
*file_seals |= F_SEAL_EXEC;
}
} else if (flags & MFD_ALLOW_SEALING) {
/* MFD_EXEC and MFD_ALLOW_SEALING are set */
file_seals = memfd_file_seals_ptr(file);
if (file_seals)
*file_seals &= ~F_SEAL_SEAL;
}
return file;
}
SYSCALL_DEFINE2(memfd_create,
const char __user *, uname,
unsigned int, flags)
{
struct file *file;
int fd, error;
char *name;
error = sanitize_flags(&flags);
if (error < 0)
return error;
name = alloc_name(uname);
if (IS_ERR(name))
return PTR_ERR(name);
fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
if (fd < 0) {
error = fd;
goto err_name;
}
file = alloc_file(name, flags);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_fd;
}
fd_install(fd, file);
kfree(name);
return fd;
err_fd:
put_unused_fd(fd);
err_name:
kfree(name);
return error;
}
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM capability
#if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_CAPABILITY_H
#include <linux/cred.h>
#include <linux/tracepoint.h>
#include <linux/user_namespace.h>
/**
* cap_capable - called after it's determined if a task has a particular
* effective capability
*
* @cred: The credentials used
* @target_ns: The user namespace of the resource being accessed
* @capable_ns: The user namespace in which the credential provides the
* capability to access the targeted resource.
* This will be NULL if ret is not 0.
* @cap: The capability to check for
* @ret: The return value of the check: 0 if it does, -ve if it does not
*
* Allows to trace calls to cap_capable in commoncap.c
*/
TRACE_EVENT(cap_capable,
TP_PROTO(const struct cred *cred, struct user_namespace *target_ns,
const struct user_namespace *capable_ns, int cap, int ret),
TP_ARGS(cred, target_ns, capable_ns, cap, ret),
TP_STRUCT__entry(
__field(const struct cred *, cred)
__field(struct user_namespace *, target_ns)
__field(const struct user_namespace *, capable_ns)
__field(int, cap)
__field(int, ret)
),
TP_fast_assign(
__entry->cred = cred;
__entry->target_ns = target_ns;
__entry->capable_ns = ret == 0 ? capable_ns : NULL;
__entry->cap = cap;
__entry->ret = ret;
),
TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d",
__entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap,
__entry->ret)
);
#endif /* _TRACE_CAPABILITY_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _LINUX_FILE_REF_H
#define _LINUX_FILE_REF_H
#include <linux/atomic.h>
#include <linux/preempt.h>
#include <linux/types.h>
/*
* file_ref is a reference count implementation specifically for use by
* files. It takes inspiration from rcuref but differs in key aspects
* such as support for SLAB_TYPESAFE_BY_RCU type caches.
*
* FILE_REF_ONEREF FILE_REF_MAXREF
* 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL
* <-------------------valid ------------------->
*
* FILE_REF_SATURATED
* 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL
* <-----------------------saturation zone---------------------->
*
* FILE_REF_RELEASED FILE_REF_DEAD
* 0xC000000000000000UL 0xE000000000000000UL
* <-------------------dead zone------------------->
*
* FILE_REF_NOREF
* 0xFFFFFFFFFFFFFFFFUL
*/
#ifdef CONFIG_64BIT
#define FILE_REF_ONEREF 0x0000000000000000UL
#define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL
#define FILE_REF_SATURATED 0xA000000000000000UL
#define FILE_REF_RELEASED 0xC000000000000000UL
#define FILE_REF_DEAD 0xE000000000000000UL
#define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL
#else
#define FILE_REF_ONEREF 0x00000000U
#define FILE_REF_MAXREF 0x7FFFFFFFU
#define FILE_REF_SATURATED 0xA0000000U
#define FILE_REF_RELEASED 0xC0000000U
#define FILE_REF_DEAD 0xE0000000U
#define FILE_REF_NOREF 0xFFFFFFFFU
#endif
typedef struct {
#ifdef CONFIG_64BIT
atomic64_t refcnt;
#else
atomic_t refcnt;
#endif
} file_ref_t;
/**
* file_ref_init - Initialize a file reference count
* @ref: Pointer to the reference count
* @cnt: The initial reference count typically '1'
*/
static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
{
atomic_long_set(&ref->refcnt, cnt - 1);
}
bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
/**
* file_ref_get - Acquire one reference on a file
* @ref: Pointer to the reference count
*
* Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF.
*
* Provides full memory ordering.
*
* Return: False if the attempt to acquire a reference failed. This happens
* when the last reference has been put already. True if a reference
* was successfully acquired
*/
static __always_inline __must_check bool file_ref_get(file_ref_t *ref)
{
/*
* Unconditionally increase the reference count with full
* ordering. The saturation and dead zones provide enough
* tolerance for this.
*
* If this indicates negative the file in question the fail can
* be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU.
* Hence, unconditionally altering the file reference count to
* e.g., reset the file reference count back to the middle of
* the deadzone risk end up marking someone else's file as dead
* behind their back.
*
* It would be possible to do a careful:
*
* cnt = atomic_long_inc_return();
* if (likely(cnt >= 0))
* return true;
*
* and then something like:
*
* if (cnt >= FILE_REF_RELEASE)
* atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD),
*
* to set the value back to the middle of the deadzone. But it's
* practically impossible to go from FILE_REF_DEAD to
* FILE_REF_ONEREF. It would need 2305843009213693952/2^61
* file_ref_get()s to resurrect such a dead file.
*/
return !atomic_long_add_negative(1, &ref->refcnt);
}
/**
* file_ref_inc - Acquire one reference on a file
* @ref: Pointer to the reference count
*
* Acquire an additional reference on a file. Warns if the caller didn't
* already hold a reference.
*/
static __always_inline void file_ref_inc(file_ref_t *ref)
{
long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference");
}
/**
* file_ref_put -- Release a file reference
* @ref: Pointer to the reference count
*
* Provides release memory ordering, such that prior loads and stores
* are done before, and provides an acquire ordering on success such
* that free() must come after.
*
* Return: True if this was the last reference with no future references
* possible. This signals the caller that it can safely release
* the object which is protected by the reference counter.
* False if there are still active references or the put() raced
* with a concurrent get()/put() pair. Caller is not allowed to
* release the protected object.
*/
static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
{
long cnt;
/*
* While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put()
* calls don't risk UAFs when a file is recyclyed, it is still
* vulnerable to UAFs caused by freeing the whole slab page once
* it becomes unused. Prevent file_ref_put() from being
* preempted protects against this.
*/
guard(preempt)();
/*
* Unconditionally decrease the reference count. The saturation
* and dead zones provide enough tolerance for this. If this
* fails then we need to handle the last reference drop and
* cases inside the saturation and dead zones.
*/
cnt = atomic_long_dec_return(&ref->refcnt); if (cnt >= 0)
return false;
return __file_ref_put(ref, cnt);}
/**
* file_ref_put_close - drop a reference expecting it would transition to FILE_REF_NOREF
* @ref: Pointer to the reference count
*
* Semantically it is equivalent to calling file_ref_put(), but it trades lower
* performance in face of other CPUs also modifying the refcount for higher
* performance when this happens to be the last reference.
*
* For the last reference file_ref_put() issues 2 atomics. One to drop the
* reference and another to transition it to FILE_REF_DEAD. This routine does
* the work in one step, but in order to do it has to pre-read the variable which
* decreases scalability.
*
* Use with close() et al, stick to file_ref_put() by default.
*/
static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
{
long old;
old = atomic_long_read(&ref->refcnt);
if (likely(old == FILE_REF_ONEREF)) { if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
return true;
}
return file_ref_put(ref);}
/**
* file_ref_read - Read the number of file references
* @ref: Pointer to the reference count
*
* Return: The number of held references (0 ... N)
*/
static inline unsigned long file_ref_read(file_ref_t *ref)
{
unsigned long c = atomic_long_read(&ref->refcnt);
/* Return 0 if within the DEAD zone. */
return c >= FILE_REF_RELEASED ? 0 : c + 1;
}
/*
* __file_ref_read_raw - Return the value stored in ref->refcnt
* @ref: Pointer to the reference count
*
* Return: The raw value found in the counter
*
* A hack for file_needs_f_pos_lock(), you probably want to use
* file_ref_read() instead.
*/
static inline unsigned long __file_ref_read_raw(file_ref_t *ref)
{
return atomic_long_read(&ref->refcnt);
}
#endif
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* NOHZ implementation for low and high resolution timers
*
* Started by: Thomas Gleixner and Ingo Molnar
*/
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.h>
#include <linux/nmi.h>
#include <linux/profile.h>
#include <linux/sched/signal.h>
#include <linux/sched/clock.h>
#include <linux/sched/stat.h>
#include <linux/sched/nohz.h>
#include <linux/sched/loadavg.h>
#include <linux/module.h>
#include <linux/irq_work.h>
#include <linux/posix-timers.h>
#include <linux/context_tracking.h>
#include <linux/mm.h>
#include <asm/irq_regs.h>
#include "tick-internal.h"
#include <trace/events/timer.h>
/*
* Per-CPU nohz control structure
*/
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
struct tick_sched *tick_get_tick_sched(int cpu)
{
return &per_cpu(tick_cpu_sched, cpu);
}
/*
* The time when the last jiffy update happened. Write access must hold
* jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a
* consistent view of jiffies and last_jiffies_update.
*/
static ktime_t last_jiffies_update;
/*
* Must be called with interrupts disabled !
*/
static void tick_do_update_jiffies64(ktime_t now)
{
unsigned long ticks = 1;
ktime_t delta, nextp;
/*
* 64-bit can do a quick check without holding the jiffies lock and
* without looking at the sequence count. The smp_load_acquire()
* pairs with the update done later in this function.
*
* 32-bit cannot do that because the store of 'tick_next_period'
* consists of two 32-bit stores, and the first store could be
* moved by the CPU to a random point in the future.
*/
if (IS_ENABLED(CONFIG_64BIT)) {
if (ktime_before(now, smp_load_acquire(&tick_next_period)))
return;
} else {
unsigned int seq;
/*
* Avoid contention on 'jiffies_lock' and protect the quick
* check with the sequence count.
*/
do {
seq = read_seqcount_begin(&jiffies_seq);
nextp = tick_next_period;
} while (read_seqcount_retry(&jiffies_seq, seq));
if (ktime_before(now, nextp))
return;
}
/* Quick check failed, i.e. update is required. */
raw_spin_lock(&jiffies_lock);
/*
* Re-evaluate with the lock held. Another CPU might have done the
* update already.
*/
if (ktime_before(now, tick_next_period)) {
raw_spin_unlock(&jiffies_lock);
return;
}
write_seqcount_begin(&jiffies_seq);
delta = ktime_sub(now, tick_next_period);
if (unlikely(delta >= TICK_NSEC)) {
/* Slow path for long idle sleep times */
s64 incr = TICK_NSEC;
ticks += ktime_divns(delta, incr);
last_jiffies_update = ktime_add_ns(last_jiffies_update,
incr * ticks);
} else {
last_jiffies_update = ktime_add_ns(last_jiffies_update,
TICK_NSEC);
}
/* Advance jiffies to complete the 'jiffies_seq' protected job */
jiffies_64 += ticks;
/* Keep the tick_next_period variable up to date */
nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC);
if (IS_ENABLED(CONFIG_64BIT)) {
/*
* Pairs with smp_load_acquire() in the lockless quick
* check above, and ensures that the update to 'jiffies_64' is
* not reordered vs. the store to 'tick_next_period', neither
* by the compiler nor by the CPU.
*/
smp_store_release(&tick_next_period, nextp);
} else {
/*
* A plain store is good enough on 32-bit, as the quick check
* above is protected by the sequence count.
*/
tick_next_period = nextp;
}
/*
* Release the sequence count. calc_global_load() below is not
* protected by it, but 'jiffies_lock' needs to be held to prevent
* concurrent invocations.
*/
write_seqcount_end(&jiffies_seq);
calc_global_load();
raw_spin_unlock(&jiffies_lock);
update_wall_time();
}
/*
* Initialize and return retrieve the jiffies update.
*/
static ktime_t tick_init_jiffy_update(void)
{
ktime_t period;
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
/* Have we started the jiffies update yet ? */
if (last_jiffies_update == 0) {
u32 rem;
/*
* Ensure that the tick is aligned to a multiple of
* TICK_NSEC.
*/
div_u64_rem(tick_next_period, TICK_NSEC, &rem);
if (rem)
tick_next_period += TICK_NSEC - rem;
last_jiffies_update = tick_next_period;
}
period = last_jiffies_update;
write_seqcount_end(&jiffies_seq);
raw_spin_unlock(&jiffies_lock);
return period;
}
static inline int tick_sched_flag_test(struct tick_sched *ts,
unsigned long flag)
{
return !!(ts->flags & flag);
}
static inline void tick_sched_flag_set(struct tick_sched *ts,
unsigned long flag)
{
lockdep_assert_irqs_disabled();
ts->flags |= flag;
}
static inline void tick_sched_flag_clear(struct tick_sched *ts,
unsigned long flag)
{
lockdep_assert_irqs_disabled();
ts->flags &= ~flag;
}
#define MAX_STALLED_JIFFIES 5
static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
{
int tick_cpu, cpu = smp_processor_id();
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the CPU in charge went
* into a long sleep. If two CPUs happen to assign themselves to
* this duty, then the jiffies update is still serialized by
* 'jiffies_lock'.
*
* If nohz_full is enabled, this should not happen because the
* 'tick_do_timer_cpu' CPU never relinquishes.
*/
tick_cpu = READ_ONCE(tick_do_timer_cpu);
if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) {
#ifdef CONFIG_NO_HZ_FULL
WARN_ON_ONCE(tick_nohz_full_running);
#endif
WRITE_ONCE(tick_do_timer_cpu, cpu);
tick_cpu = cpu;
}
/* Check if jiffies need an update */
if (tick_cpu == cpu)
tick_do_update_jiffies64(now);
/*
* If the jiffies update stalled for too long (timekeeper in stop_machine()
* or VMEXIT'ed for several msecs), force an update.
*/
if (ts->last_tick_jiffies != jiffies) {
ts->stalled_jiffies = 0;
ts->last_tick_jiffies = READ_ONCE(jiffies);
} else {
if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
tick_do_update_jiffies64(now);
ts->stalled_jiffies = 0;
ts->last_tick_jiffies = READ_ONCE(jiffies);
}
}
if (tick_sched_flag_test(ts, TS_FLAG_INIDLE))
ts->got_idle_tick = 1;
}
static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
{
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
* time. This happens on completely idle SMP systems while
* waiting on the login prompt. We also increment the "start of
* idle" jiffy stamp so the idle accounting adjustment we do
* when we go busy again does not account too many ticks.
*/
if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
touch_softlockup_watchdog_sched();
if (is_idle_task(current))
ts->idle_jiffies++;
/*
* In case the current tick fired too early past its expected
* expiration, make sure we don't bypass the next clock reprogramming
* to the same deadline.
*/
ts->next_tick = 0;
}
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
}
/*
* We rearm the timer until we get disabled by the idle code.
* Called with interrupts disabled.
*/
static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer)
{
struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
tick_sched_do_timer(ts, now);
/*
* Do not call when we are not in IRQ context and have
* no valid 'regs' pointer
*/
if (regs)
tick_sched_handle(ts, regs);
else
ts->next_tick = 0;
/*
* In dynticks mode, tick reprogram is deferred:
* - to the idle task if in dynticks-idle
* - to IRQ exit if in full-dynticks.
*/
if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED)))
return HRTIMER_NORESTART;
hrtimer_forward(timer, now, TICK_NSEC);
return HRTIMER_RESTART;
}
#ifdef CONFIG_NO_HZ_FULL
cpumask_var_t tick_nohz_full_mask;
EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
bool tick_nohz_full_running;
EXPORT_SYMBOL_GPL(tick_nohz_full_running);
static atomic_t tick_dep_mask;
static bool check_tick_dependency(atomic_t *dep)
{
int val = atomic_read(dep);
if (val & TICK_DEP_MASK_POSIX_TIMER) {
trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
return true;
}
if (val & TICK_DEP_MASK_PERF_EVENTS) {
trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
return true;
}
if (val & TICK_DEP_MASK_SCHED) {
trace_tick_stop(0, TICK_DEP_MASK_SCHED);
return true;
}
if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) {
trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
return true;
}
if (val & TICK_DEP_MASK_RCU) {
trace_tick_stop(0, TICK_DEP_MASK_RCU);
return true;
}
if (val & TICK_DEP_MASK_RCU_EXP) {
trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP);
return true;
}
return false;
}
static bool can_stop_full_tick(int cpu, struct tick_sched *ts)
{
lockdep_assert_irqs_disabled();
if (unlikely(!cpu_online(cpu)))
return false;
if (check_tick_dependency(&tick_dep_mask))
return false;
if (check_tick_dependency(&ts->tick_dep_mask))
return false;
if (check_tick_dependency(¤t->tick_dep_mask))
return false;
if (check_tick_dependency(¤t->signal->tick_dep_mask))
return false;
return true;
}
static void nohz_full_kick_func(struct irq_work *work)
{
/* Empty, the tick restart happens on tick_nohz_irq_exit() */
}
static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) =
IRQ_WORK_INIT_HARD(nohz_full_kick_func);
/*
* Kick this CPU if it's full dynticks in order to force it to
* re-evaluate its dependency on the tick and restart it if necessary.
* This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
* is NMI safe.
*/
static void tick_nohz_full_kick(void)
{
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
irq_work_queue(this_cpu_ptr(&nohz_full_kick_work));
}
/*
* Kick the CPU if it's full dynticks in order to force it to
* re-evaluate its dependency on the tick and restart it if necessary.
*/
void tick_nohz_full_kick_cpu(int cpu)
{
if (!tick_nohz_full_cpu(cpu))
return;
irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
}
static void tick_nohz_kick_task(struct task_struct *tsk)
{
int cpu;
/*
* If the task is not running, run_posix_cpu_timers()
* has nothing to elapse, and an IPI can then be optimized out.
*
* activate_task() STORE p->tick_dep_mask
* STORE p->on_rq
* __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or())
* LOCK rq->lock LOAD p->on_rq
* smp_mb__after_spin_lock()
* tick_nohz_task_switch()
* LOAD p->tick_dep_mask
*
* XXX given a task picks up the dependency on schedule(), should we
* only care about tasks that are currently on the CPU instead of all
* that are on the runqueue?
*
* That is, does this want to be: task_on_cpu() / task_curr()?
*/
if (!sched_task_on_rq(tsk))
return;
/*
* If the task concurrently migrates to another CPU,
* we guarantee it sees the new tick dependency upon
* schedule.
*
* set_task_cpu(p, cpu);
* STORE p->cpu = @cpu
* __schedule() (switch to task 'p')
* LOCK rq->lock
* smp_mb__after_spin_lock() STORE p->tick_dep_mask
* tick_nohz_task_switch() smp_mb() (atomic_fetch_or())
* LOAD p->tick_dep_mask LOAD p->cpu
*/
cpu = task_cpu(tsk);
preempt_disable();
if (cpu_online(cpu))
tick_nohz_full_kick_cpu(cpu);
preempt_enable();
}
/*
* Kick all full dynticks CPUs in order to force these to re-evaluate
* their dependency on the tick and restart it if necessary.
*/
static void tick_nohz_full_kick_all(void)
{
int cpu;
if (!tick_nohz_full_running)
return;
preempt_disable();
for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
tick_nohz_full_kick_cpu(cpu);
preempt_enable();
}
static void tick_nohz_dep_set_all(atomic_t *dep,
enum tick_dep_bits bit)
{
int prev;
prev = atomic_fetch_or(BIT(bit), dep);
if (!prev)
tick_nohz_full_kick_all();
}
/*
* Set a global tick dependency. Used by perf events that rely on freq and
* unstable clocks.
*/
void tick_nohz_dep_set(enum tick_dep_bits bit)
{
tick_nohz_dep_set_all(&tick_dep_mask, bit);
}
void tick_nohz_dep_clear(enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &tick_dep_mask);
}
/*
* Set per-CPU tick dependency. Used by scheduler and perf events in order to
* manage event-throttling.
*/
void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
{
int prev;
struct tick_sched *ts;
ts = per_cpu_ptr(&tick_cpu_sched, cpu);
prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask);
if (!prev) {
preempt_disable();
/* Perf needs local kick that is NMI safe */
if (cpu == smp_processor_id()) {
tick_nohz_full_kick();
} else {
/* Remote IRQ work not NMI-safe */
if (!WARN_ON_ONCE(in_nmi()))
tick_nohz_full_kick_cpu(cpu);
}
preempt_enable();
}
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
{
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
atomic_andnot(BIT(bit), &ts->tick_dep_mask);
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
/*
* Set a per-task tick dependency. RCU needs this. Also posix CPU timers
* in order to elapse per task timers.
*/
void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask))
tick_nohz_kick_task(tsk);
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
/*
* Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
* per process timers.
*/
void tick_nohz_dep_set_signal(struct task_struct *tsk,
enum tick_dep_bits bit)
{
int prev;
struct signal_struct *sig = tsk->signal;
prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask);
if (!prev) {
struct task_struct *t;
lockdep_assert_held(&tsk->sighand->siglock);
__for_each_thread(sig, t)
tick_nohz_kick_task(t);
}
}
void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &sig->tick_dep_mask);
}
/*
* Re-evaluate the need for the tick as we switch the current task.
* It might need the tick due to per task/process properties:
* perf events, posix CPU timers, ...
*/
void __tick_nohz_task_switch(void)
{
struct tick_sched *ts;
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
ts = this_cpu_ptr(&tick_cpu_sched);
if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
if (atomic_read(¤t->tick_dep_mask) ||
atomic_read(¤t->signal->tick_dep_mask))
tick_nohz_full_kick();
}
}
/* Get the boot-time nohz CPU list from the kernel parameters. */
void __init tick_nohz_full_setup(cpumask_var_t cpumask)
{
alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
cpumask_copy(tick_nohz_full_mask, cpumask);
tick_nohz_full_running = true;
}
bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
{
/*
* The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound
* timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu)
return false;
return true;
}
static int tick_nohz_cpu_down(unsigned int cpu)
{
return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY;
}
void __init tick_nohz_init(void)
{
int cpu, ret;
if (!tick_nohz_full_running)
return;
/*
* Full dynticks uses IRQ work to drive the tick rescheduling on safe
* locking contexts. But then we need IRQ work to raise its own
* interrupts to avoid circular dependency on the tick.
*/
if (!arch_irq_work_has_interrupt()) {
pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n");
cpumask_clear(tick_nohz_full_mask);
tick_nohz_full_running = false;
return;
}
if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
pr_warn("NO_HZ: Clearing %d from nohz_full range "
"for timekeeping\n", cpu);
cpumask_clear_cpu(cpu, tick_nohz_full_mask);
}
}
for_each_cpu(cpu, tick_nohz_full_mask)
ct_cpu_track_user(cpu);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"kernel/nohz:predown", NULL,
tick_nohz_cpu_down);
WARN_ON(ret < 0);
pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
cpumask_pr_args(tick_nohz_full_mask));
}
#endif /* #ifdef CONFIG_NO_HZ_FULL */
/*
* NOHZ - aka dynamic tick functionality
*/
#ifdef CONFIG_NO_HZ_COMMON
/*
* NO HZ enabled ?
*/
bool tick_nohz_enabled __read_mostly = true;
unsigned long tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
static int __init setup_tick_nohz(char *str)
{
return (kstrtobool(str, &tick_nohz_enabled) == 0);
}
__setup("nohz=", setup_tick_nohz);
bool tick_nohz_tick_stopped(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
return tick_sched_flag_test(ts, TS_FLAG_STOPPED);
}
bool tick_nohz_tick_stopped_cpu(int cpu)
{
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
return tick_sched_flag_test(ts, TS_FLAG_STOPPED);
}
/**
* tick_nohz_update_jiffies - update jiffies when idle was interrupted
* @now: current ktime_t
*
* Called from interrupt entry when the CPU was idle
*
* In case the sched_tick was stopped on this CPU, we have to check if jiffies
* must be updated. Otherwise an interrupt handler could use a stale jiffy
* value. We do this unconditionally on any CPU, as we don't know whether the
* CPU, which has the update task assigned, is in a long sleep.
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
unsigned long flags;
__this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
local_irq_restore(flags);
touch_softlockup_watchdog_sched();
}
static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
ktime_t delta;
if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)))
return;
delta = ktime_sub(now, ts->idle_entrytime);
write_seqcount_begin(&ts->idle_sleeptime_seq);
if (nr_iowait_cpu(smp_processor_id()) > 0)
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
else
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
ts->idle_entrytime = now;
tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE);
write_seqcount_end(&ts->idle_sleeptime_seq);
sched_clock_idle_wakeup_event();
}
static void tick_nohz_start_idle(struct tick_sched *ts)
{
write_seqcount_begin(&ts->idle_sleeptime_seq);
ts->idle_entrytime = ktime_get();
tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE);
write_seqcount_end(&ts->idle_sleeptime_seq);
sched_clock_idle_sleep_event();
}
static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
bool compute_delta, u64 *last_update_time)
{
ktime_t now, idle;
unsigned int seq;
if (!tick_nohz_active)
return -1;
now = ktime_get();
if (last_update_time)
*last_update_time = ktime_to_us(now);
do {
seq = read_seqcount_begin(&ts->idle_sleeptime_seq);
if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) {
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
idle = ktime_add(*sleeptime, delta);
} else {
idle = *sleeptime;
}
} while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq));
return ktime_to_us(idle);
}
/**
* get_cpu_idle_time_us - get the total idle time of a CPU
* @cpu: CPU number to query
* @last_update_time: variable to store update time in. Do not update
* counters if NULL.
*
* Return the cumulative idle time (since boot) for a given
* CPU, in microseconds. Note that this is partially broken due to
* the counter of iowait tasks that can be remotely updated without
* any synchronization. Therefore it is possible to observe backward
* values within two consecutive reads.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
*/
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime,
!nr_iowait_cpu(cpu), last_update_time);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
/**
* get_cpu_iowait_time_us - get the total iowait time of a CPU
* @cpu: CPU number to query
* @last_update_time: variable to store update time in. Do not update
* counters if NULL.
*
* Return the cumulative iowait time (since boot) for a given
* CPU, in microseconds. Note this is partially broken due to
* the counter of iowait tasks that can be remotely updated without
* any synchronization. Therefore it is possible to observe backward
* values within two consecutive reads.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
*/
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime,
nr_iowait_cpu(cpu), last_update_time);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
{
hrtimer_cancel(&ts->sched_timer);
hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
/* Forward the time to expire in the future */
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) {
hrtimer_start_expires(&ts->sched_timer,
HRTIMER_MODE_ABS_PINNED_HARD);
} else {
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
/*
* Reset to make sure the next tick stop doesn't get fooled by past
* cached clock deadline.
*/
ts->next_tick = 0;
}
static inline bool local_timer_softirq_pending(void)
{
return local_timers_pending() & BIT(TIMER_SOFTIRQ);
}
/*
* Read jiffies and the time when jiffies were updated last
*/
u64 get_jiffies_update(unsigned long *basej)
{
unsigned long basejiff;
unsigned int seq;
u64 basemono;
do {
seq = read_seqcount_begin(&jiffies_seq);
basemono = last_jiffies_update;
basejiff = jiffies;
} while (read_seqcount_retry(&jiffies_seq, seq));
*basej = basejiff;
return basemono;
}
/**
* tick_nohz_next_event() - return the clock monotonic based next event
* @ts: pointer to tick_sched struct
* @cpu: CPU number
*
* Return:
* *%0 - When the next event is a maximum of TICK_NSEC in the future
* and the tick is not stopped yet
* *%next_event - Next event based on clock monotonic
*/
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
{
u64 basemono, next_tick, delta, expires;
unsigned long basejiff;
int tick_cpu;
basemono = get_jiffies_update(&basejiff);
ts->last_jiffies = basejiff;
ts->timer_expires_base = basemono;
/*
* Keep the periodic tick, when RCU, architecture or irq_work
* requests it.
* Aside of that, check whether the local timer softirq is
* pending. If so, its a bad idea to call get_next_timer_interrupt(),
* because there is an already expired timer, so it will request
* immediate expiry, which rearms the hardware timer with a
* minimal delta, which brings us back to this place
* immediately. Lather, rinse and repeat...
*/
if (rcu_needs_cpu() || arch_needs_cpu() ||
irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
* Get the next pending timer. If high resolution
* timers are enabled this only takes the timer wheel
* timers into account. If high resolution timers are
* disabled this also looks at the next expiring
* hrtimer.
*/
next_tick = get_next_timer_interrupt(basejiff, basemono);
ts->next_timer = next_tick;
}
/* Make sure next_tick is never before basemono! */
if (WARN_ON_ONCE(basemono > next_tick))
next_tick = basemono;
/*
* If the tick is due in the next period, keep it ticking or
* force prod the timer.
*/
delta = next_tick - basemono;
if (delta <= (u64)TICK_NSEC) {
/*
* We've not stopped the tick yet, and there's a timer in the
* next period, so no point in stopping it either, bail.
*/
if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
ts->timer_expires = 0;
goto out;
}
}
/*
* If this CPU is the one which had the do_timer() duty last, we limit
* the sleep time to the timekeeping 'max_deferment' value.
* Otherwise we can sleep as long as we want.
*/
delta = timekeeping_max_deferment();
tick_cpu = READ_ONCE(tick_do_timer_cpu);
if (tick_cpu != cpu &&
(tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
delta = KTIME_MAX;
/* Calculate the next expiry time */
if (delta < (KTIME_MAX - basemono))
expires = basemono + delta;
else
expires = KTIME_MAX;
ts->timer_expires = min_t(u64, expires, next_tick);
out:
return ts->timer_expires;
}
static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
unsigned long basejiff = ts->last_jiffies;
u64 basemono = ts->timer_expires_base;
bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
int tick_cpu;
u64 expires;
/* Make sure we won't be trying to stop it twice in a row. */
ts->timer_expires_base = 0;
/*
* Now the tick should be stopped definitely - so the timer base needs
* to be marked idle as well to not miss a newly queued timer.
*/
expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle);
if (expires > ts->timer_expires) {
/*
* This path could only happen when the first timer was removed
* between calculating the possible sleep length and now (when
* high resolution mode is not active, timer could also be a
* hrtimer).
*
* We have to stick to the original calculated expiry value to
* not stop the tick for too long with a shallow C-state (which
* was programmed by cpuidle because of an early next expiration
* value).
*/
expires = ts->timer_expires;
}
/* If the timer base is not idle, retain the not yet stopped tick. */
if (!timer_idle)
return;
/*
* If this CPU is the one which updates jiffies, then give up
* the assignment and let it be taken by the CPU which runs
* the tick timer next, which might be this CPU as well. If we
* don't drop this here, the jiffies might be stale and
* do_timer() never gets invoked. Keep track of the fact that it
* was the one which had the do_timer() duty last.
*/
tick_cpu = READ_ONCE(tick_do_timer_cpu);
if (tick_cpu == cpu) {
WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE);
tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST);
} else if (tick_cpu != TICK_DO_TIMER_NONE) {
tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST);
}
/* Skip reprogram of event if it's not changed */
if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) {
/* Sanity check: make sure clockevent is actually programmed */
if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
return;
WARN_ONCE(1, "basemono: %llu ts->next_tick: %llu dev->next_event: %llu "
"timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick,
dev->next_event, hrtimer_active(&ts->sched_timer),
hrtimer_get_expires(&ts->sched_timer));
}
/*
* tick_nohz_stop_tick() can be called several times before
* tick_nohz_restart_sched_tick() is called. This happens when
* interrupts arrive which do not cause a reschedule. In the first
* call we save the current tick time, so we can restart the
* scheduler tick in tick_nohz_restart_sched_tick().
*/
if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
calc_load_nohz_start();
quiet_vmstat();
ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
tick_sched_flag_set(ts, TS_FLAG_STOPPED);
trace_tick_stop(1, TICK_DEP_MASK_NONE);
}
ts->next_tick = expires;
/*
* If the expiration time == KTIME_MAX, then we simply stop
* the tick timer.
*/
if (unlikely(expires == KTIME_MAX)) {
if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES))
hrtimer_cancel(&ts->sched_timer);
else
tick_program_event(KTIME_MAX, 1);
return;
}
if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED_HARD);
} else {
hrtimer_set_expires(&ts->sched_timer, expires);
tick_program_event(expires, 1);
}
}
static void tick_nohz_retain_tick(struct tick_sched *ts)
{
ts->timer_expires_base = 0;
}
#ifdef CONFIG_NO_HZ_FULL
static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu)
{
if (tick_nohz_next_event(ts, cpu))
tick_nohz_stop_tick(ts, cpu);
else
tick_nohz_retain_tick(ts);
}
#endif /* CONFIG_NO_HZ_FULL */
static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
/* Update jiffies first */
tick_do_update_jiffies64(now);
/*
* Clear the timer idle flag, so we avoid IPIs on remote queueing and
* the clock forward checks in the enqueue path:
*/
timer_clear_idle();
calc_load_nohz_stop();
touch_softlockup_watchdog_sched();
/* Cancel the scheduled timer and restore the tick: */
tick_sched_flag_clear(ts, TS_FLAG_STOPPED);
tick_nohz_restart(ts, now);
}
static void __tick_nohz_full_update_tick(struct tick_sched *ts,
ktime_t now)
{
#ifdef CONFIG_NO_HZ_FULL
int cpu = smp_processor_id();
if (can_stop_full_tick(cpu, ts))
tick_nohz_full_stop_tick(ts, cpu);
else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
tick_nohz_restart_sched_tick(ts, now);
#endif
}
static void tick_nohz_full_update_tick(struct tick_sched *ts)
{
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ))
return;
__tick_nohz_full_update_tick(ts, ktime_get());
}
/*
* A pending softirq outside an IRQ (or softirq disabled section) context
* should be waiting for ksoftirqd to handle it. Therefore we shouldn't
* reach this code due to the need_resched() early check in can_stop_idle_tick().
*
* However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the
* cpu_down() process, softirqs can still be raised while ksoftirqd is parked,
* triggering the code below, since wakep_softirqd() is ignored.
*
*/
static bool report_idle_softirq(void)
{
static int ratelimit;
unsigned int pending = local_softirq_pending();
if (likely(!pending))
return false;
/* Some softirqs claim to be safe against hotplug and ksoftirqd parking */
if (!cpu_active(smp_processor_id())) {
pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK;
if (!pending)
return false;
}
if (ratelimit >= 10)
return false;
/* On RT, softirq handling may be waiting on some lock */
if (local_bh_blocked())
return false;
pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
pending);
ratelimit++;
return true;
}
static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
{
WARN_ON_ONCE(cpu_is_offline(cpu));
if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ)))
return false;
if (need_resched())
return false;
if (unlikely(report_idle_softirq()))
return false;
if (tick_nohz_full_enabled()) {
int tick_cpu = READ_ONCE(tick_do_timer_cpu);
/*
* Keep the tick alive to guarantee timekeeping progression
* if there are full dynticks CPUs around
*/
if (tick_cpu == cpu)
return false;
/* Should not happen for nohz-full */
if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE))
return false;
}
return true;
}
/**
* tick_nohz_idle_stop_tick - stop the idle tick from the idle task
*
* When the next event is more than a tick into the future, stop the idle tick
*/
void tick_nohz_idle_stop_tick(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
int cpu = smp_processor_id();
ktime_t expires;
/*
* If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the
* tick timer expiration time is known already.
*/
if (ts->timer_expires_base)
expires = ts->timer_expires;
else if (can_stop_idle_tick(cpu, ts))
expires = tick_nohz_next_event(ts, cpu);
else
return;
ts->idle_calls++;
if (expires > 0LL) {
int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
tick_nohz_stop_tick(ts, cpu);
ts->idle_sleeps++;
ts->idle_expires = expires;
if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
ts->idle_jiffies = ts->last_jiffies;
nohz_balance_enter_idle(cpu);
}
} else {
tick_nohz_retain_tick(ts);
}
}
void tick_nohz_idle_retain_tick(void)
{
tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
}
/**
* tick_nohz_idle_enter - prepare for entering idle on the current CPU
*
* Called when we start the idle loop.
*/
void tick_nohz_idle_enter(void)
{
struct tick_sched *ts;
lockdep_assert_irqs_enabled();
local_irq_disable();
ts = this_cpu_ptr(&tick_cpu_sched);
WARN_ON_ONCE(ts->timer_expires_base);
tick_sched_flag_set(ts, TS_FLAG_INIDLE);
tick_nohz_start_idle(ts);
local_irq_enable();
}
/**
* tick_nohz_irq_exit - Notify the tick about IRQ exit
*
* A timer may have been added/modified/deleted either by the current IRQ,
* or by another place using this IRQ as a notification. This IRQ may have
* also updated the RCU callback list. These events may require a
* re-evaluation of the next tick. Depending on the context:
*
* 1) If the CPU is idle and no resched is pending, just proceed with idle
* time accounting. The next tick will be re-evaluated on the next idle
* loop iteration.
*
* 2) If the CPU is nohz_full:
*
* 2.1) If there is any tick dependency, restart the tick if stopped.
*
* 2.2) If there is no tick dependency, (re-)evaluate the next tick and
* stop/update it accordingly.
*/
void tick_nohz_irq_exit(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (tick_sched_flag_test(ts, TS_FLAG_INIDLE))
tick_nohz_start_idle(ts);
else
tick_nohz_full_update_tick(ts);
}
/**
* tick_nohz_idle_got_tick - Check whether or not the tick handler has run
*
* Return: %true if the tick handler has run, otherwise %false
*/
bool tick_nohz_idle_got_tick(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (ts->got_idle_tick) {
ts->got_idle_tick = 0;
return true;
}
return false;
}
/**
* tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
* or the tick, whichever expires first. Note that, if the tick has been
* stopped, it returns the next hrtimer.
*
* Called from power state control code with interrupts disabled
*
* Return: the next expiration time
*/
ktime_t tick_nohz_get_next_hrtimer(void)
{
return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
}
/**
* tick_nohz_get_sleep_length - return the expected length of the current sleep
* @delta_next: duration until the next event if the tick cannot be stopped
*
* Called from power state control code with interrupts disabled.
*
* The return value of this function and/or the value returned by it through the
* @delta_next pointer can be negative which must be taken into account by its
* callers.
*
* Return: the expected length of the current sleep
*/
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
int cpu = smp_processor_id();
/*
* The idle entry time is expected to be a sufficient approximation of
* the current time at this point.
*/
ktime_t now = ts->idle_entrytime;
ktime_t next_event;
WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE));
*delta_next = ktime_sub(dev->next_event, now);
if (!can_stop_idle_tick(cpu, ts))
return *delta_next;
next_event = tick_nohz_next_event(ts, cpu);
if (!next_event)
return *delta_next;
/*
* If the next highres timer to expire is earlier than 'next_event', the
* idle governor needs to know that.
*/
next_event = min_t(u64, next_event,
hrtimer_next_event_without(&ts->sched_timer));
return ktime_sub(next_event, now);
}
/**
* tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
* for a particular CPU.
* @cpu: target CPU number
*
* Called from the schedutil frequency scaling governor in scheduler context.
*
* Return: the current idle calls counter value for @cpu
*/
unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
{
struct tick_sched *ts = tick_get_tick_sched(cpu);
return ts->idle_calls;
}
static void tick_nohz_account_idle_time(struct tick_sched *ts,
ktime_t now)
{
unsigned long ticks;
ts->idle_exittime = now;
if (vtime_accounting_enabled_this_cpu())
return;
/*
* We stopped the tick in idle. update_process_times() would miss the
* time we slept, as it does only a 1 tick accounting.
* Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
if (ticks && ticks < LONG_MAX)
account_idle_ticks(ticks);
}
void tick_nohz_idle_restart_tick(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
ktime_t now = ktime_get();
tick_nohz_restart_sched_tick(ts, now);
tick_nohz_account_idle_time(ts, now);
}
}
static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
{
if (tick_nohz_full_cpu(smp_processor_id()))
__tick_nohz_full_update_tick(ts, now);
else
tick_nohz_restart_sched_tick(ts, now);
tick_nohz_account_idle_time(ts, now);
}
/**
* tick_nohz_idle_exit - Update the tick upon idle task exit
*
* When the idle task exits, update the tick depending on the
* following situations:
*
* 1) If the CPU is not in nohz_full mode (most cases), then
* restart the tick.
*
* 2) If the CPU is in nohz_full mode (corner case):
* 2.1) If the tick can be kept stopped (no tick dependencies)
* then re-evaluate the next tick and try to keep it stopped
* as long as possible.
* 2.2) If the tick has dependencies, restart the tick.
*
*/
void tick_nohz_idle_exit(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
bool idle_active, tick_stopped;
ktime_t now;
local_irq_disable();
WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE));
WARN_ON_ONCE(ts->timer_expires_base);
tick_sched_flag_clear(ts, TS_FLAG_INIDLE);
idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE);
tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
if (idle_active || tick_stopped)
now = ktime_get();
if (idle_active)
tick_nohz_stop_idle(ts, now);
if (tick_stopped)
tick_nohz_idle_update_tick(ts, now);
local_irq_enable();
}
/*
* In low-resolution mode, the tick handler must be implemented directly
* at the clockevent level. hrtimer can't be used instead, because its
* infrastructure actually relies on the tick itself as a backend in
* low-resolution mode (see hrtimer_run_queues()).
*/
static void tick_nohz_lowres_handler(struct clock_event_device *dev)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
dev->next_event = KTIME_MAX;
if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART))
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
static inline void tick_nohz_activate(struct tick_sched *ts)
{
if (!tick_nohz_enabled)
return;
tick_sched_flag_set(ts, TS_FLAG_NOHZ);
/* One update is enough */
if (!test_and_set_bit(0, &tick_nohz_active))
timers_update_nohz();
}
/**
* tick_nohz_switch_to_nohz - switch to NOHZ mode
*/
static void tick_nohz_switch_to_nohz(void)
{
if (!tick_nohz_enabled)
return;
if (tick_switch_to_oneshot(tick_nohz_lowres_handler))
return;
/*
* Recycle the hrtimer in 'ts', so we can share the
* highres code.
*/
tick_setup_sched_timer(false);
}
static inline void tick_nohz_irq_enter(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
ktime_t now;
if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE))
return;
now = ktime_get();
if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))
tick_nohz_stop_idle(ts, now);
/*
* If all CPUs are idle we may need to update a stale jiffies value.
* Note nohz_full is a special case: a timekeeper is guaranteed to stay
* alive but it might be busy looping with interrupts disabled in some
* rare case (typically stop machine). So we must make sure we have a
* last resort.
*/
if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
tick_nohz_update_jiffies(now);
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
static inline void tick_nohz_irq_enter(void) { }
static inline void tick_nohz_activate(struct tick_sched *ts) { }
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter() to notify about the possible interruption of idle()
*/
void tick_irq_enter(void)
{
tick_check_oneshot_broadcast_this_cpu();
tick_nohz_irq_enter();
}
static int sched_skew_tick;
static int __init skew_tick(char *str)
{
get_option(&str, &sched_skew_tick);
return 0;
}
early_param("skew_tick", skew_tick);
/**
* tick_setup_sched_timer - setup the tick emulation timer
* @hrtimer: whether to use the hrtimer or not
*/
void tick_setup_sched_timer(bool hrtimer)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
/* Emulate tick processing via per-CPU hrtimers: */
hrtimer_setup(&ts->sched_timer, tick_nohz_handler, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer)
tick_sched_flag_set(ts, TS_FLAG_HIGHRES);
/* Get the next period (per-CPU) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
/* Offset the tick to avert 'jiffies_lock' contention. */
if (sched_skew_tick) {
u64 offset = TICK_NSEC >> 1;
do_div(offset, num_possible_cpus());
offset *= smp_processor_id();
hrtimer_add_expires_ns(&ts->sched_timer, offset);
}
hrtimer_forward_now(&ts->sched_timer, TICK_NSEC);
if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer)
hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD);
else
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
tick_nohz_activate(ts);
}
/*
* Shut down the tick and make sure the CPU won't try to retake the timekeeping
* duty before disabling IRQs in idle for the last time.
*/
void tick_sched_timer_dying(int cpu)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t idle_sleeptime, iowait_sleeptime;
unsigned long idle_calls, idle_sleeps;
/* This must happen before hrtimers are migrated! */
if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES))
hrtimer_cancel(&ts->sched_timer);
idle_sleeptime = ts->idle_sleeptime;
iowait_sleeptime = ts->iowait_sleeptime;
idle_calls = ts->idle_calls;
idle_sleeps = ts->idle_sleeps;
memset(ts, 0, sizeof(*ts));
ts->idle_sleeptime = idle_sleeptime;
ts->iowait_sleeptime = iowait_sleeptime;
ts->idle_calls = idle_calls;
ts->idle_sleeps = idle_sleeps;
}
/*
* Async notification about clocksource changes
*/
void tick_clock_notify(void)
{
int cpu;
for_each_possible_cpu(cpu)
set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
}
/*
* Async notification about clock event changes
*/
void tick_oneshot_notify(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
set_bit(0, &ts->check_clocks);
}
/*
* Check if a change happened, which makes oneshot possible.
*
* Called cyclically from the hrtimer softirq (driven by the timer
* softirq). 'allow_nohz' signals that we can switch into low-res NOHZ
* mode, because high resolution timers are disabled (either compile
* or runtime). Called with interrupts disabled.
*/
int tick_check_oneshot_change(int allow_nohz)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (!test_and_clear_bit(0, &ts->check_clocks))
return 0;
if (tick_sched_flag_test(ts, TS_FLAG_NOHZ))
return 0;
if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available())
return 0;
if (!allow_nohz)
return 1;
tick_nohz_switch_to_nohz();
return 0;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine (KVM) Hypervisor
*
* Copyright (C) 2006 Qumranet, Inc.
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
* Yaniv Kamay <yaniv@qumranet.com>
*/
#include <kvm/iodev.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/syscore_ops.h>
#include <linux/cpu.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/sched/stat.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
#include <linux/kvm_para.h>
#include <linux/pagemap.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/compat.h>
#include <linux/srcu.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/bsearch.h>
#include <linux/io.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
#include <linux/suspend.h>
#include <asm/processor.h>
#include <asm/ioctl.h>
#include <linux/uaccess.h>
#include "coalesced_mmio.h"
#include "async_pf.h"
#include "kvm_mm.h"
#include "vfio.h"
#include <trace/events/ipi.h>
#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>
#include <linux/kvm_dirty_ring.h>
/* Worst case buffer size needed for holding an integer. */
#define ITOA_MAX_LEN 12
MODULE_AUTHOR("Qumranet");
MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor");
MODULE_LICENSE("GPL");
/* Architectures should define their poll value according to the halt latency */
unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
module_param(halt_poll_ns, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns);
/* Default doubles per-vcpu halt_poll_ns. */
unsigned int halt_poll_ns_grow = 2;
module_param(halt_poll_ns_grow, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
/* The start value to grow halt_poll_ns from */
unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
module_param(halt_poll_ns_grow_start, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
/* Default halves per-vcpu halt_poll_ns. */
unsigned int halt_poll_ns_shrink = 2;
module_param(halt_poll_ns_shrink, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
/*
* Allow direct access (from KVM or the CPU) without MMU notifier protection
* to unpinned pages.
*/
static bool allow_unsafe_mappings;
module_param(allow_unsafe_mappings, bool, 0444);
/*
* Ordering of locks:
*
* kvm->lock --> kvm->slots_lock --> kvm->irq_lock
*/
DEFINE_MUTEX(kvm_lock);
LIST_HEAD(vm_list);
static struct kmem_cache *kvm_vcpu_cache;
static __read_mostly struct preempt_ops kvm_preempt_ops;
static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);
static struct dentry *kvm_debugfs_dir;
static const struct file_operations stat_fops_per_vm;
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#define KVM_COMPAT(c) .compat_ioctl = (c)
#else
/*
* For architectures that don't implement a compat infrastructure,
* adopt a double line of defense:
* - Prevent a compat task from opening /dev/kvm
* - If the open has been done by a 64bit task, and the KVM fd
* passed to a compat task, let the ioctls fail.
*/
static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg) { return -EINVAL; }
static int kvm_no_compat_open(struct inode *inode, struct file *file)
{
return is_compat_task() ? -ENODEV : 0;
}
#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \
.open = kvm_no_compat_open
#endif
static int kvm_enable_virtualization(void);
static void kvm_disable_virtualization(void);
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
#define KVM_EVENT_CREATE_VM 0
#define KVM_EVENT_DESTROY_VM 1
static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
static unsigned long long kvm_createvm_count;
static unsigned long long kvm_active_vms;
static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);
__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
{
}
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
void vcpu_load(struct kvm_vcpu *vcpu)
{
int cpu = get_cpu();
__this_cpu_write(kvm_running_vcpu, vcpu);
preempt_notifier_register(&vcpu->preempt_notifier);
kvm_arch_vcpu_load(vcpu, cpu);
put_cpu();
}
EXPORT_SYMBOL_GPL(vcpu_load);
void vcpu_put(struct kvm_vcpu *vcpu)
{
preempt_disable();
kvm_arch_vcpu_put(vcpu);
preempt_notifier_unregister(&vcpu->preempt_notifier);
__this_cpu_write(kvm_running_vcpu, NULL);
preempt_enable();
}
EXPORT_SYMBOL_GPL(vcpu_put);
/* TODO: merge with kvm_arch_vcpu_should_kick */
static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
{
int mode = kvm_vcpu_exiting_guest_mode(vcpu);
/*
* We need to wait for the VCPU to reenable interrupts and get out of
* READING_SHADOW_PAGE_TABLES mode.
*/
if (req & KVM_REQUEST_WAIT)
return mode != OUTSIDE_GUEST_MODE;
/*
* Need to kick a running VCPU, but otherwise there is nothing to do.
*/
return mode == IN_GUEST_MODE;
}
static void ack_kick(void *_completed)
{
}
static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
{
if (cpumask_empty(cpus))
return false;
smp_call_function_many(cpus, ack_kick, NULL, wait);
return true;
}
static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req,
struct cpumask *tmp, int current_cpu)
{
int cpu;
if (likely(!(req & KVM_REQUEST_NO_ACTION))) __kvm_make_request(req, vcpu); if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
return;
/*
* Note, the vCPU could get migrated to a different pCPU at any point
* after kvm_request_needs_ipi(), which could result in sending an IPI
* to the previous pCPU. But, that's OK because the purpose of the IPI
* is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is
* satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES
* after this point is also OK, as the requirement is only that KVM wait
* for vCPUs that were reading SPTEs _before_ any changes were
* finalized. See kvm_vcpu_kick() for more details on handling requests.
*/
if (kvm_request_needs_ipi(vcpu, req)) {
cpu = READ_ONCE(vcpu->cpu);
if (cpu != -1 && cpu != current_cpu) __cpumask_set_cpu(cpu, tmp);
}
}
bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
unsigned long *vcpu_bitmap)
{
struct kvm_vcpu *vcpu;
struct cpumask *cpus;
int i, me;
bool called;
me = get_cpu();
cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
cpumask_clear(cpus);
for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
vcpu = kvm_get_vcpu(kvm, i);
if (!vcpu)
continue;
kvm_make_vcpu_request(vcpu, req, cpus, me);
}
called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
put_cpu();
return called;
}
bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
struct kvm_vcpu *vcpu;
struct cpumask *cpus;
unsigned long i;
bool called;
int me;
me = get_cpu();
cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
cpumask_clear(cpus);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_vcpu_request(vcpu, req, cpus, me);
called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu();
return called;
}
EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
++kvm->stat.generic.remote_tlb_flush_requests;
/*
* We want to publish modifications to the page tables before reading
* mode. Pairs with a memory barrier in arch-specific code.
* - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest
* and smp_mb in walk_shadow_page_lockless_begin/end.
* - powerpc: smp_mb in kvmppc_prepare_to_enter.
*
* There is already an smp_mb__after_atomic() before
* kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
* barrier here.
*/
if (!kvm_arch_flush_remote_tlbs(kvm)
|| kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.generic.remote_tlb_flush;
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
{
if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
return;
/*
* Fall back to a flushing entire TLBs if the architecture range-based
* TLB invalidation is unsupported or can't be performed for whatever
* reason.
*/
kvm_flush_remote_tlbs(kvm);
}
void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
/*
* All current use cases for flushing the TLBs for a specific memslot
* are related to dirty logging, and many do the TLB flush out of
* mmu_lock. The interaction between the various operations on memslot
* must be serialized by slots_locks to ensure the TLB flush from one
* operation is observed by any other operation on the same memslot.
*/
lockdep_assert_held(&kvm->slots_lock); kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
}
static void kvm_flush_shadow_all(struct kvm *kvm)
{
kvm_arch_flush_shadow_all(kvm);
kvm_arch_guest_memory_reclaimed(kvm);
}
#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
gfp_t gfp_flags)
{
void *page;
gfp_flags |= mc->gfp_zero;
if (mc->kmem_cache)
return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
page = (void *)__get_free_page(gfp_flags);
if (page && mc->init_value) memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64));
return page;
}
int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
{
gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT;
void *obj;
if (mc->nobjs >= min)
return 0;
if (unlikely(!mc->objects)) { if (WARN_ON_ONCE(!capacity))
return -EIO;
/*
* Custom init values can be used only for page allocations,
* and obviously conflict with __GFP_ZERO.
*/
if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero)))
return -EIO;
mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp); if (!mc->objects)
return -ENOMEM;
mc->capacity = capacity;
}
/* It is illegal to request a different capacity across topups. */
if (WARN_ON_ONCE(mc->capacity != capacity))
return -EIO;
while (mc->nobjs < mc->capacity) { obj = mmu_memory_cache_alloc_obj(mc, gfp);
if (!obj)
return mc->nobjs >= min ? 0 : -ENOMEM;
mc->objects[mc->nobjs++] = obj;
}
return 0;
}
int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
{
return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
}
int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
{
return mc->nobjs;
}
void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
{ while (mc->nobjs) {
if (mc->kmem_cache)
kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]);
else
free_page((unsigned long)mc->objects[--mc->nobjs]);
}
kvfree(mc->objects);
mc->objects = NULL;
mc->capacity = 0;
}
void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
{
void *p;
if (WARN_ON(!mc->nobjs))
p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT);
else
p = mc->objects[--mc->nobjs]; BUG_ON(!p); return p;
}
#endif
static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
mutex_init(&vcpu->mutex);
vcpu->cpu = -1;
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
rwlock_init(&vcpu->pid_lock);
#ifndef __KVM_HAVE_ARCH_WQP
rcuwait_init(&vcpu->wait);
#endif
kvm_async_pf_vcpu_init(vcpu);
kvm_vcpu_set_in_spin_loop(vcpu, false);
kvm_vcpu_set_dy_eligible(vcpu, false);
vcpu->preempted = false;
vcpu->ready = false;
preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
vcpu->last_used_slot = NULL;
/* Fill the stats id string for the vcpu */
snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d",
task_pid_nr(current), id);
}
static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
kvm_arch_vcpu_destroy(vcpu);
kvm_dirty_ring_free(&vcpu->dirty_ring);
/*
* No need for rcu_read_lock as VCPU_RUN is the only place that changes
* the vcpu->pid pointer, and at destruction time all file descriptors
* are already gone.
*/
put_pid(vcpu->pid);
free_page((unsigned long)vcpu->run);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
void kvm_destroy_vcpus(struct kvm *kvm)
{
unsigned long i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_vcpu_destroy(vcpu);
xa_erase(&kvm->vcpu_array, i);
/*
* Assert that the vCPU isn't visible in any way, to ensure KVM
* doesn't trigger a use-after-free if destroying vCPUs results
* in VM-wide request, e.g. to flush remote TLBs when tearing
* down MMUs, or to mark the VM dead if a KVM_BUG_ON() fires.
*/
WARN_ON_ONCE(xa_load(&kvm->vcpu_array, i) || kvm_get_vcpu(kvm, i));
}
atomic_set(&kvm->online_vcpus, 0);
}
EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
{
return container_of(mn, struct kvm, mmu_notifier);
}
typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
typedef void (*on_lock_fn_t)(struct kvm *kvm);
struct kvm_mmu_notifier_range {
/*
* 64-bit addresses, as KVM notifiers can operate on host virtual
* addresses (unsigned long) and guest physical addresses (64-bit).
*/
u64 start;
u64 end;
union kvm_mmu_notifier_arg arg;
gfn_handler_t handler;
on_lock_fn_t on_lock;
bool flush_on_ret;
bool may_block;
bool lockless;
};
/*
* The inner-most helper returns a tuple containing the return value from the
* arch- and action-specific handler, plus a flag indicating whether or not at
* least one memslot was found, i.e. if the handler found guest memory.
*
* Note, most notifiers are averse to booleans, so even though KVM tracks the
* return from arch code as a bool, outer helpers will cast it to an int. :-(
*/
typedef struct kvm_mmu_notifier_return {
bool ret;
bool found_memslot;
} kvm_mn_ret_t;
/*
* Use a dedicated stub instead of NULL to indicate that there is no callback
* function/handler. The compiler technically can't guarantee that a real
* function will have a non-zero address, and so it will generate code to
* check for !NULL, whereas comparing against a stub will be elided at compile
* time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
*/
static void kvm_null_fn(void)
{
}
#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
/* Iterate over each memslot intersecting [start, last] (inclusive) range */
#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \
for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
node; \
node = interval_tree_iter_next(node, start, last)) \
static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
const struct kvm_mmu_notifier_range *range)
{
struct kvm_mmu_notifier_return r = {
.ret = false,
.found_memslot = false,
};
struct kvm_gfn_range gfn_range;
struct kvm_memory_slot *slot;
struct kvm_memslots *slots;
int i, idx;
if (WARN_ON_ONCE(range->end <= range->start))
return r;
/* A null handler is allowed if and only if on_lock() is provided. */
if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
IS_KVM_NULL_FN(range->handler)))
return r;
/* on_lock will never be called for lockless walks */
if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock)))
return r;
idx = srcu_read_lock(&kvm->srcu);
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
struct interval_tree_node *node;
slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_hva_range(node, slots,
range->start, range->end - 1) {
unsigned long hva_start, hva_end;
slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
hva_start = max_t(unsigned long, range->start, slot->userspace_addr);
hva_end = min_t(unsigned long, range->end,
slot->userspace_addr + (slot->npages << PAGE_SHIFT));
/*
* To optimize for the likely case where the address
* range is covered by zero or one memslots, don't
* bother making these conditional (to avoid writes on
* the second or later invocation of the handler).
*/
gfn_range.arg = range->arg;
gfn_range.may_block = range->may_block;
/*
* HVA-based notifications aren't relevant to private
* mappings as they don't have a userspace mapping.
*/
gfn_range.attr_filter = KVM_FILTER_SHARED;
/*
* {gfn(page) | page intersects with [hva_start, hva_end)} =
* {gfn_start, gfn_start+1, ..., gfn_end-1}.
*/
gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
gfn_range.slot = slot;
gfn_range.lockless = range->lockless;
if (!r.found_memslot) {
r.found_memslot = true;
if (!range->lockless) {
KVM_MMU_LOCK(kvm);
if (!IS_KVM_NULL_FN(range->on_lock))
range->on_lock(kvm);
if (IS_KVM_NULL_FN(range->handler))
goto mmu_unlock;
}
}
r.ret |= range->handler(kvm, &gfn_range);
}
}
if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm);
mmu_unlock:
if (r.found_memslot && !range->lockless) KVM_MMU_UNLOCK(kvm); srcu_read_unlock(&kvm->srcu, idx);
return r;
}
static __always_inline int kvm_age_hva_range(struct mmu_notifier *mn,
unsigned long start,
unsigned long end,
gfn_handler_t handler,
bool flush_on_ret)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
const struct kvm_mmu_notifier_range range = {
.start = start,
.end = end,
.handler = handler,
.on_lock = (void *)kvm_null_fn,
.flush_on_ret = flush_on_ret,
.may_block = false,
.lockless = IS_ENABLED(CONFIG_KVM_MMU_LOCKLESS_AGING),
};
return kvm_handle_hva_range(kvm, &range).ret;
}
static __always_inline int kvm_age_hva_range_no_flush(struct mmu_notifier *mn,
unsigned long start,
unsigned long end,
gfn_handler_t handler)
{
return kvm_age_hva_range(mn, start, end, handler, false);
}
void kvm_mmu_invalidate_begin(struct kvm *kvm)
{
lockdep_assert_held_write(&kvm->mmu_lock);
/*
* The count increase must become visible at unlock time as no
* spte can be established without taking the mmu_lock and
* count is also read inside the mmu_lock critical section.
*/
kvm->mmu_invalidate_in_progress++;
if (likely(kvm->mmu_invalidate_in_progress == 1)) {
kvm->mmu_invalidate_range_start = INVALID_GPA;
kvm->mmu_invalidate_range_end = INVALID_GPA;
}
}
void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
{
lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);
if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
kvm->mmu_invalidate_range_start = start;
kvm->mmu_invalidate_range_end = end;
} else {
/*
* Fully tracking multiple concurrent ranges has diminishing
* returns. Keep things simple and just find the minimal range
* which includes the current and new ranges. As there won't be
* enough information to subtract a range after its invalidate
* completes, any ranges invalidated concurrently will
* accumulate and persist until all outstanding invalidates
* complete.
*/
kvm->mmu_invalidate_range_start =
min(kvm->mmu_invalidate_range_start, start);
kvm->mmu_invalidate_range_end =
max(kvm->mmu_invalidate_range_end, end);
}
}
bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
return kvm_unmap_gfn_range(kvm, range);
}
static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
const struct kvm_mmu_notifier_range hva_range = {
.start = range->start,
.end = range->end,
.handler = kvm_mmu_unmap_gfn_range,
.on_lock = kvm_mmu_invalidate_begin,
.flush_on_ret = true,
.may_block = mmu_notifier_range_blockable(range),
};
trace_kvm_unmap_hva_range(range->start, range->end);
/*
* Prevent memslot modification between range_start() and range_end()
* so that conditionally locking provides the same result in both
* functions. Without that guarantee, the mmu_invalidate_in_progress
* adjustments will be imbalanced.
*
* Pairs with the decrement in range_end().
*/
spin_lock(&kvm->mn_invalidate_lock);
kvm->mn_active_invalidate_count++;
spin_unlock(&kvm->mn_invalidate_lock);
/*
* Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
* before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
* each cache's lock. There are relatively few caches in existence at
* any given time, and the caches themselves can check for hva overlap,
* i.e. don't need to rely on memslot overlap checks for performance.
* Because this runs without holding mmu_lock, the pfn caches must use
* mn_active_invalidate_count (see above) instead of
* mmu_invalidate_in_progress.
*/
gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end);
/*
* If one or more memslots were found and thus zapped, notify arch code
* that guest memory has been reclaimed. This needs to be done *after*
* dropping mmu_lock, as x86's reclaim path is slooooow.
*/
if (kvm_handle_hva_range(kvm, &hva_range).found_memslot) kvm_arch_guest_memory_reclaimed(kvm);
return 0;
}
void kvm_mmu_invalidate_end(struct kvm *kvm)
{
lockdep_assert_held_write(&kvm->mmu_lock);
/*
* This sequence increase will notify the kvm page fault that
* the page that is going to be mapped in the spte could have
* been freed.
*/
kvm->mmu_invalidate_seq++;
smp_wmb();
/*
* The above sequence increase must be visible before the
* below count decrease, which is ensured by the smp_wmb above
* in conjunction with the smp_rmb in mmu_invalidate_retry().
*/
kvm->mmu_invalidate_in_progress--;
KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
/*
* Assert that at least one range was added between start() and end().
* Not adding a range isn't fatal, but it is a KVM bug.
*/
WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
const struct kvm_mmu_notifier_range hva_range = {
.start = range->start,
.end = range->end,
.handler = (void *)kvm_null_fn,
.on_lock = kvm_mmu_invalidate_end,
.flush_on_ret = false,
.may_block = mmu_notifier_range_blockable(range),
};
bool wake;
kvm_handle_hva_range(kvm, &hva_range);
/* Pairs with the increment in range_start(). */
spin_lock(&kvm->mn_invalidate_lock);
if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count)) --kvm->mn_active_invalidate_count;
wake = !kvm->mn_active_invalidate_count;
spin_unlock(&kvm->mn_invalidate_lock);
/*
* There can only be one waiter, since the wait happens under
* slots_lock.
*/
if (wake) rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
}
static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
trace_kvm_age_hva(start, end);
return kvm_age_hva_range(mn, start, end, kvm_age_gfn,
!IS_ENABLED(CONFIG_KVM_ELIDE_TLB_FLUSH_IF_YOUNG));
}
static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
trace_kvm_age_hva(start, end);
/*
* Even though we do not flush TLB, this will still adversely
* affect performance on pre-Haswell Intel EPT, where there is
* no EPT Access Bit to clear so that we have to tear down EPT
* tables instead. If we find this unacceptable, we can always
* add a parameter to kvm_age_hva so that it effectively doesn't
* do anything on clear_young.
*
* Also note that currently we never issue secondary TLB flushes
* from clear_young, leaving this job up to the regular system
* cadence. If we find this inaccurate, we might come up with a
* more sophisticated heuristic later.
*/
return kvm_age_hva_range_no_flush(mn, start, end, kvm_age_gfn);
}
static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address)
{
trace_kvm_test_age_hva(address);
return kvm_age_hva_range_no_flush(mn, address, address + 1,
kvm_test_age_gfn);
}
static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int idx;
idx = srcu_read_lock(&kvm->srcu);
kvm_flush_shadow_all(kvm);
srcu_read_unlock(&kvm->srcu, idx);
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
.clear_young = kvm_mmu_notifier_clear_young,
.test_young = kvm_mmu_notifier_test_young,
.release = kvm_mmu_notifier_release,
};
static int kvm_init_mmu_notifier(struct kvm *kvm)
{
kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;
return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
}
#else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
static int kvm_init_mmu_notifier(struct kvm *kvm)
{
return 0;
}
#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
static int kvm_pm_notifier_call(struct notifier_block *bl,
unsigned long state,
void *unused)
{
struct kvm *kvm = container_of(bl, struct kvm, pm_notifier);
return kvm_arch_pm_notifier(kvm, state);
}
static void kvm_init_pm_notifier(struct kvm *kvm)
{
kvm->pm_notifier.notifier_call = kvm_pm_notifier_call;
/* Suspend KVM before we suspend ftrace, RCU, etc. */
kvm->pm_notifier.priority = INT_MAX;
register_pm_notifier(&kvm->pm_notifier);
}
static void kvm_destroy_pm_notifier(struct kvm *kvm)
{
unregister_pm_notifier(&kvm->pm_notifier);
}
#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */
static void kvm_init_pm_notifier(struct kvm *kvm)
{
}
static void kvm_destroy_pm_notifier(struct kvm *kvm)
{
}
#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */
static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
{
if (!memslot->dirty_bitmap)
return;
vfree(memslot->dirty_bitmap);
memslot->dirty_bitmap = NULL;
}
/* This does not remove the slot from struct kvm_memslots data structures */
static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
if (slot->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(slot); kvm_destroy_dirty_bitmap(slot);
kvm_arch_free_memslot(kvm, slot);
kfree(slot);
}
static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
{
struct hlist_node *idnode;
struct kvm_memory_slot *memslot;
int bkt;
/*
* The same memslot objects live in both active and inactive sets,
* arbitrarily free using index '1' so the second invocation of this
* function isn't operating over a structure with dangling pointers
* (even though this function isn't actually touching them).
*/
if (!slots->node_idx)
return;
hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot);
}
static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
{
switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
case KVM_STATS_TYPE_INSTANT:
return 0444;
case KVM_STATS_TYPE_CUMULATIVE:
case KVM_STATS_TYPE_PEAK:
default:
return 0644;
}
}
static void kvm_destroy_vm_debugfs(struct kvm *kvm)
{
int i;
int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
kvm_vcpu_stats_header.num_desc;
if (IS_ERR(kvm->debugfs_dentry))
return;
debugfs_remove_recursive(kvm->debugfs_dentry);
if (kvm->debugfs_stat_data) { for (i = 0; i < kvm_debugfs_num_entries; i++)
kfree(kvm->debugfs_stat_data[i]);
kfree(kvm->debugfs_stat_data);
}
}
static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
{
static DEFINE_MUTEX(kvm_debugfs_lock);
struct dentry *dent;
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
const struct _kvm_stats_desc *pdesc;
int i, ret = -ENOMEM;
int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
kvm_vcpu_stats_header.num_desc;
if (!debugfs_initialized())
return 0;
snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname);
mutex_lock(&kvm_debugfs_lock);
dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
if (dent) {
pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
dput(dent);
mutex_unlock(&kvm_debugfs_lock);
return 0;
}
dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
mutex_unlock(&kvm_debugfs_lock);
if (IS_ERR(dent))
return 0;
kvm->debugfs_dentry = dent;
kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
sizeof(*kvm->debugfs_stat_data),
GFP_KERNEL_ACCOUNT);
if (!kvm->debugfs_stat_data)
goto out_err;
for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
pdesc = &kvm_vm_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
goto out_err;
stat_data->kvm = kvm;
stat_data->desc = pdesc;
stat_data->kind = KVM_STAT_VM;
kvm->debugfs_stat_data[i] = stat_data;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
}
for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
pdesc = &kvm_vcpu_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
goto out_err;
stat_data->kvm = kvm;
stat_data->desc = pdesc;
stat_data->kind = KVM_STAT_VCPU;
kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
}
kvm_arch_create_vm_debugfs(kvm);
return 0;
out_err:
kvm_destroy_vm_debugfs(kvm);
return ret;
}
/*
* Called just after removing the VM from the vm_list, but before doing any
* other destruction.
*/
void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
{
}
/*
* Called after per-vm debugfs created. When called kvm->debugfs_dentry should
* be setup already, so we can create arch-specific debugfs entries under it.
* Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so
* a per-arch destroy interface is not needed.
*/
void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm)
{
}
static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
{
struct kvm *kvm = kvm_arch_alloc_vm();
struct kvm_memslots *slots;
int r, i, j;
if (!kvm)
return ERR_PTR(-ENOMEM);
KVM_MMU_LOCK_INIT(kvm);
mmgrab(current->mm);
kvm->mm = current->mm;
kvm_eventfd_init(kvm);
mutex_init(&kvm->lock);
mutex_init(&kvm->irq_lock);
mutex_init(&kvm->slots_lock);
mutex_init(&kvm->slots_arch_lock);
spin_lock_init(&kvm->mn_invalidate_lock);
rcuwait_init(&kvm->mn_memslots_update_rcuwait);
xa_init(&kvm->vcpu_array);
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
xa_init(&kvm->mem_attr_array);
#endif
INIT_LIST_HEAD(&kvm->gpc_list);
spin_lock_init(&kvm->gpc_lock);
INIT_LIST_HEAD(&kvm->devices);
kvm->max_vcpus = KVM_MAX_VCPUS;
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
/*
* Force subsequent debugfs file creations to fail if the VM directory
* is not created (by kvm_create_vm_debugfs()).
*/
kvm->debugfs_dentry = ERR_PTR(-ENOENT);
snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d",
task_pid_nr(current));
r = -ENOMEM;
if (init_srcu_struct(&kvm->srcu))
goto out_err_no_srcu;
if (init_srcu_struct(&kvm->irq_srcu))
goto out_err_no_irq_srcu;
r = kvm_init_irq_routing(kvm);
if (r)
goto out_err_no_irq_routing;
refcount_set(&kvm->users_count, 1);
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
for (j = 0; j < 2; j++) {
slots = &kvm->__memslots[i][j];
atomic_long_set(&slots->last_used_slot, (unsigned long)NULL);
slots->hva_tree = RB_ROOT_CACHED;
slots->gfn_tree = RB_ROOT;
hash_init(slots->id_hash);
slots->node_idx = j;
/* Generations must be different for each address space. */
slots->generation = i;
}
rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]);
}
r = -ENOMEM;
for (i = 0; i < KVM_NR_BUSES; i++) {
rcu_assign_pointer(kvm->buses[i],
kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
if (!kvm->buses[i])
goto out_err_no_arch_destroy_vm;
}
r = kvm_arch_init_vm(kvm, type);
if (r)
goto out_err_no_arch_destroy_vm;
r = kvm_enable_virtualization();
if (r)
goto out_err_no_disable;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif
r = kvm_init_mmu_notifier(kvm);
if (r)
goto out_err_no_mmu_notifier;
r = kvm_coalesced_mmio_init(kvm);
if (r < 0)
goto out_no_coalesced_mmio;
r = kvm_create_vm_debugfs(kvm, fdname);
if (r)
goto out_err_no_debugfs;
mutex_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
mutex_unlock(&kvm_lock);
preempt_notifier_inc();
kvm_init_pm_notifier(kvm);
return kvm;
out_err_no_debugfs:
kvm_coalesced_mmio_free(kvm);
out_no_coalesced_mmio:
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
#endif
out_err_no_mmu_notifier:
kvm_disable_virtualization();
out_err_no_disable:
kvm_arch_destroy_vm(kvm);
out_err_no_arch_destroy_vm:
WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); kvm_free_irq_routing(kvm);
out_err_no_irq_routing:
cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
out_err_no_srcu:
kvm_arch_free_vm(kvm);
mmdrop(current->mm);
return ERR_PTR(r);
}
static void kvm_destroy_devices(struct kvm *kvm)
{
struct kvm_device *dev, *tmp;
/*
* We do not need to take the kvm->lock here, because nobody else
* has a reference to the struct kvm at this point and therefore
* cannot access the devices list anyhow.
*
* The device list is generally managed as an rculist, but list_del()
* is used intentionally here. If a bug in KVM introduced a reader that
* was not backed by a reference on the kvm struct, the hope is that
* it'd consume the poisoned forward pointer instead of suffering a
* use-after-free, even though this cannot be guaranteed.
*/
list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node);
dev->ops->destroy(dev);
}
}
static void kvm_destroy_vm(struct kvm *kvm)
{
int i;
struct mm_struct *mm = kvm->mm;
kvm_destroy_pm_notifier(kvm);
kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
kvm_destroy_vm_debugfs(kvm);
mutex_lock(&kvm_lock);
list_del(&kvm->vm_list);
mutex_unlock(&kvm_lock);
kvm_arch_pre_destroy_vm(kvm);
kvm_free_irq_routing(kvm);
for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); if (bus) kvm_io_bus_destroy(bus);
kvm->buses[i] = NULL;
}
kvm_coalesced_mmio_free(kvm);
#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
/*
* At this point, pending calls to invalidate_range_start()
* have completed but no more MMU notifiers will run, so
* mn_active_invalidate_count may remain unbalanced.
* No threads can be waiting in kvm_swap_active_memslots() as the
* last reference on KVM has been dropped, but freeing
* memslots would deadlock without this manual intervention.
*
* If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU
* notifier between a start() and end(), then there shouldn't be any
* in-progress invalidations.
*/
WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait));
if (kvm->mn_active_invalidate_count)
kvm->mn_active_invalidate_count = 0;
else
WARN_ON(kvm->mmu_invalidate_in_progress);
#else
kvm_flush_shadow_all(kvm);
#endif
kvm_arch_destroy_vm(kvm);
kvm_destroy_devices(kvm);
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
kvm_free_memslots(kvm, &kvm->__memslots[i][0]); kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
}
cleanup_srcu_struct(&kvm->irq_srcu);
cleanup_srcu_struct(&kvm->srcu);
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
xa_destroy(&kvm->mem_attr_array);
#endif
kvm_arch_free_vm(kvm);
preempt_notifier_dec();
kvm_disable_virtualization(); mmdrop(mm);
}
void kvm_get_kvm(struct kvm *kvm)
{ refcount_inc(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm);
/*
* Make sure the vm is not during destruction, which is a safe version of
* kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise.
*/
bool kvm_get_kvm_safe(struct kvm *kvm)
{
return refcount_inc_not_zero(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm_safe);
void kvm_put_kvm(struct kvm *kvm)
{ if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_put_kvm);
/*
* Used to put a reference that was taken on behalf of an object associated
* with a user-visible file descriptor, e.g. a vcpu or device, if installation
* of the new file descriptor fails and the reference cannot be transferred to
* its final owner. In such cases, the caller is still actively using @kvm and
* will fail miserably if the refcount unexpectedly hits zero.
*/
void kvm_put_kvm_no_destroy(struct kvm *kvm)
{
WARN_ON(refcount_dec_and_test(&kvm->users_count));
}
EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy);
static int kvm_vm_release(struct inode *inode, struct file *filp)
{
struct kvm *kvm = filp->private_data;
kvm_irqfd_release(kvm);
kvm_put_kvm(kvm);
return 0;
}
/*
* Allocation size is twice as large as the actual dirty bitmap size.
* See kvm_vm_ioctl_get_dirty_log() why this is needed.
*/
static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot)
{
unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot);
memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT);
if (!memslot->dirty_bitmap)
return -ENOMEM;
return 0;
}
static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id)
{
struct kvm_memslots *active = __kvm_memslots(kvm, as_id);
int node_idx_inactive = active->node_idx ^ 1;
return &kvm->__memslots[as_id][node_idx_inactive];
}
/*
* Helper to get the address space ID when one of memslot pointers may be NULL.
* This also serves as a sanity that at least one of the pointers is non-NULL,
* and that their address space IDs don't diverge.
*/
static int kvm_memslots_get_as_id(struct kvm_memory_slot *a,
struct kvm_memory_slot *b)
{
if (WARN_ON_ONCE(!a && !b))
return 0;
if (!a)
return b->as_id; if (!b)
return a->as_id;
WARN_ON_ONCE(a->as_id != b->as_id);
return a->as_id;
}
static void kvm_insert_gfn_node(struct kvm_memslots *slots,
struct kvm_memory_slot *slot)
{
struct rb_root *gfn_tree = &slots->gfn_tree;
struct rb_node **node, *parent;
int idx = slots->node_idx;
parent = NULL;
for (node = &gfn_tree->rb_node; *node; ) {
struct kvm_memory_slot *tmp;
tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]);
parent = *node;
if (slot->base_gfn < tmp->base_gfn)
node = &(*node)->rb_left;
else if (slot->base_gfn > tmp->base_gfn)
node = &(*node)->rb_right;
else
BUG();
}
rb_link_node(&slot->gfn_node[idx], parent, node);
rb_insert_color(&slot->gfn_node[idx], gfn_tree);
}
static void kvm_erase_gfn_node(struct kvm_memslots *slots,
struct kvm_memory_slot *slot)
{
rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree);
}
static void kvm_replace_gfn_node(struct kvm_memslots *slots,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new)
{
int idx = slots->node_idx;
WARN_ON_ONCE(old->base_gfn != new->base_gfn);
rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx],
&slots->gfn_tree);
}
/*
* Replace @old with @new in the inactive memslots.
*
* With NULL @old this simply adds @new.
* With NULL @new this simply removes @old.
*
* If @new is non-NULL its hva_node[slots_idx] range has to be set
* appropriately.
*/
static void kvm_replace_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new)
{ int as_id = kvm_memslots_get_as_id(old, new);
struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
int idx = slots->node_idx;
if (old) { hash_del(&old->id_node[idx]);
interval_tree_remove(&old->hva_node[idx], &slots->hva_tree);
if ((long)old == atomic_long_read(&slots->last_used_slot)) atomic_long_set(&slots->last_used_slot, (long)new); if (!new) { kvm_erase_gfn_node(slots, old);
return;
}
}
/*
* Initialize @new's hva range. Do this even when replacing an @old
* slot, kvm_copy_memslot() deliberately does not touch node data.
*/
new->hva_node[idx].start = new->userspace_addr;
new->hva_node[idx].last = new->userspace_addr +
(new->npages << PAGE_SHIFT) - 1;
/*
* (Re)Add the new memslot. There is no O(1) interval_tree_replace(),
* hva_node needs to be swapped with remove+insert even though hva can't
* change when replacing an existing slot.
*/
hash_add(slots->id_hash, &new->id_node[idx], new->id);
interval_tree_insert(&new->hva_node[idx], &slots->hva_tree);
/*
* If the memslot gfn is unchanged, rb_replace_node() can be used to
* switch the node in the gfn tree instead of removing the old and
* inserting the new as two separate operations. Replacement is a
* single O(1) operation versus two O(log(n)) operations for
* remove+insert.
*/
if (old && old->base_gfn == new->base_gfn) { kvm_replace_gfn_node(slots, old, new);
} else {
if (old)
kvm_erase_gfn_node(slots, old); kvm_insert_gfn_node(slots, new);
}
}
/*
* Flags that do not access any of the extra space of struct
* kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS
* only allows these.
*/
#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
static int check_memory_region_flags(struct kvm *kvm,
const struct kvm_userspace_memory_region2 *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
if (kvm_arch_has_private_mem(kvm))
valid_flags |= KVM_MEM_GUEST_MEMFD;
/* Dirty logging private memory is not currently supported. */
if (mem->flags & KVM_MEM_GUEST_MEMFD)
valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
/*
* GUEST_MEMFD is incompatible with read-only memslots, as writes to
* read-only memslots have emulated MMIO, not page fault, semantics,
* and KVM doesn't allow emulated MMIO for private memory.
*/
if (kvm_arch_has_readonly_mem(kvm) &&
!(mem->flags & KVM_MEM_GUEST_MEMFD))
valid_flags |= KVM_MEM_READONLY;
if (mem->flags & ~valid_flags)
return -EINVAL;
return 0;
}
static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
{
struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id);
/* Grab the generation from the activate memslots. */
u64 gen = __kvm_memslots(kvm, as_id)->generation;
WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
/*
* Do not store the new memslots while there are invalidations in
* progress, otherwise the locking in invalidate_range_start and
* invalidate_range_end will be unbalanced.
*/
spin_lock(&kvm->mn_invalidate_lock);
prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait);
while (kvm->mn_active_invalidate_count) { set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock(&kvm->mn_invalidate_lock);
schedule();
spin_lock(&kvm->mn_invalidate_lock);
}
finish_rcuwait(&kvm->mn_memslots_update_rcuwait);
rcu_assign_pointer(kvm->memslots[as_id], slots);
spin_unlock(&kvm->mn_invalidate_lock);
/*
* Acquired in kvm_set_memslot. Must be released before synchronize
* SRCU below in order to avoid deadlock with another thread
* acquiring the slots_arch_lock in an srcu critical section.
*/
mutex_unlock(&kvm->slots_arch_lock);
synchronize_srcu_expedited(&kvm->srcu);
/*
* Increment the new memslot generation a second time, dropping the
* update in-progress flag and incrementing the generation based on
* the number of address spaces. This provides a unique and easily
* identifiable generation number while the memslots are in flux.
*/
gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
/*
* Generations must be unique even across address spaces. We do not need
* a global counter for that, instead the generation space is evenly split
* across address spaces. For example, with two address spaces, address
* space 0 will use generations 0, 2, 4, ... while address space 1 will
* use generations 1, 3, 5, ...
*/
gen += kvm_arch_nr_memslot_as_ids(kvm);
kvm_arch_memslots_updated(kvm, gen);
slots->generation = gen;
}
static int kvm_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
int r;
/*
* If dirty logging is disabled, nullify the bitmap; the old bitmap
* will be freed on "commit". If logging is enabled in both old and
* new, reuse the existing bitmap. If logging is enabled only in the
* new and KVM isn't using a ring buffer, allocate and initialize a
* new bitmap.
*/
if (change != KVM_MR_DELETE) {
if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; else if (kvm_use_dirty_bitmap(kvm)) {
r = kvm_alloc_dirty_bitmap(new);
if (r)
return r;
if (kvm_dirty_log_manual_protect_and_init_set(kvm)) bitmap_set(new->dirty_bitmap, 0, new->npages);
}
}
r = kvm_arch_prepare_memory_region(kvm, old, new, change);
/* Free the bitmap on failure if it was allocated above. */
if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap))
kvm_destroy_dirty_bitmap(new);
return r;
}
static void kvm_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
int old_flags = old ? old->flags : 0; int new_flags = new ? new->flags : 0;
/*
* Update the total number of memslot pages before calling the arch
* hook so that architectures can consume the result directly.
*/
if (change == KVM_MR_DELETE) kvm->nr_memslot_pages -= old->npages;
else if (change == KVM_MR_CREATE)
kvm->nr_memslot_pages += new->npages; if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) { int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1;
atomic_set(&kvm->nr_memslots_dirty_logging,
atomic_read(&kvm->nr_memslots_dirty_logging) + change);
}
kvm_arch_commit_memory_region(kvm, old, new, change);
switch (change) {
case KVM_MR_CREATE:
/* Nothing more to do. */
break;
case KVM_MR_DELETE:
/* Free the old memslot and all its metadata. */
kvm_free_memslot(kvm, old);
break;
case KVM_MR_MOVE:
case KVM_MR_FLAGS_ONLY:
/*
* Free the dirty bitmap as needed; the below check encompasses
* both the flags and whether a ring buffer is being used)
*/
if (old->dirty_bitmap && !new->dirty_bitmap) kvm_destroy_dirty_bitmap(old);
/*
* The final quirk. Free the detached, old slot, but only its
* memory, not any metadata. Metadata, including arch specific
* data, may be reused by @new.
*/
kfree(old);
break;
default:
BUG();
}
}
/*
* Activate @new, which must be installed in the inactive slots by the caller,
* by swapping the active slots and then propagating @new to @old once @old is
* unreachable and can be safely modified.
*
* With NULL @old this simply adds @new to @active (while swapping the sets).
* With NULL @new this simply removes @old from @active and frees it
* (while also swapping the sets).
*/
static void kvm_activate_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new)
{
int as_id = kvm_memslots_get_as_id(old, new);
kvm_swap_active_memslots(kvm, as_id);
/* Propagate the new memslot to the now inactive memslots. */
kvm_replace_memslot(kvm, old, new);
}
static void kvm_copy_memslot(struct kvm_memory_slot *dest,
const struct kvm_memory_slot *src)
{
dest->base_gfn = src->base_gfn;
dest->npages = src->npages;
dest->dirty_bitmap = src->dirty_bitmap;
dest->arch = src->arch;
dest->userspace_addr = src->userspace_addr;
dest->flags = src->flags;
dest->id = src->id;
dest->as_id = src->as_id;
}
static void kvm_invalidate_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *invalid_slot)
{
/*
* Mark the current slot INVALID. As with all memslot modifications,
* this must be done on an unreachable slot to avoid modifying the
* current slot in the active tree.
*/
kvm_copy_memslot(invalid_slot, old);
invalid_slot->flags |= KVM_MEMSLOT_INVALID;
kvm_replace_memslot(kvm, old, invalid_slot);
/*
* Activate the slot that is now marked INVALID, but don't propagate
* the slot to the now inactive slots. The slot is either going to be
* deleted or recreated as a new slot.
*/
kvm_swap_active_memslots(kvm, old->as_id);
/*
* From this point no new shadow pages pointing to a deleted, or moved,
* memslot will be created. Validation of sp->gfn happens in:
* - gfn_to_hva (kvm_read_guest, gfn_to_pfn)
* - kvm_is_visible_gfn (mmu_check_root)
*/
kvm_arch_flush_shadow_memslot(kvm, old);
kvm_arch_guest_memory_reclaimed(kvm);
/* Was released by kvm_swap_active_memslots(), reacquire. */
mutex_lock(&kvm->slots_arch_lock);
/*
* Copy the arch-specific field of the newly-installed slot back to the
* old slot as the arch data could have changed between releasing
* slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock
* above. Writers are required to retrieve memslots *after* acquiring
* slots_arch_lock, thus the active slot's data is guaranteed to be fresh.
*/
old->arch = invalid_slot->arch;
}
static void kvm_create_memslot(struct kvm *kvm,
struct kvm_memory_slot *new)
{
/* Add the new memslot to the inactive set and activate. */
kvm_replace_memslot(kvm, NULL, new);
kvm_activate_memslot(kvm, NULL, new);
}
static void kvm_delete_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *invalid_slot)
{
/*
* Remove the old memslot (in the inactive memslots) by passing NULL as
* the "new" slot, and for the invalid version in the active slots.
*/
kvm_replace_memslot(kvm, old, NULL);
kvm_activate_memslot(kvm, invalid_slot, NULL);
}
static void kvm_move_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
struct kvm_memory_slot *invalid_slot)
{
/*
* Replace the old memslot in the inactive slots, and then swap slots
* and replace the current INVALID with the new as well.
*/
kvm_replace_memslot(kvm, old, new);
kvm_activate_memslot(kvm, invalid_slot, new);
}
static void kvm_update_flags_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new)
{
/*
* Similar to the MOVE case, but the slot doesn't need to be zapped as
* an intermediate step. Instead, the old memslot is simply replaced
* with a new, updated copy in both memslot sets.
*/
kvm_replace_memslot(kvm, old, new);
kvm_activate_memslot(kvm, old, new);
}
static int kvm_set_memslot(struct kvm *kvm,
struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
struct kvm_memory_slot *invalid_slot;
int r;
/*
* Released in kvm_swap_active_memslots().
*
* Must be held from before the current memslots are copied until after
* the new memslots are installed with rcu_assign_pointer, then
* released before the synchronize srcu in kvm_swap_active_memslots().
*
* When modifying memslots outside of the slots_lock, must be held
* before reading the pointer to the current memslots until after all
* changes to those memslots are complete.
*
* These rules ensure that installing new memslots does not lose
* changes made to the previous memslots.
*/
mutex_lock(&kvm->slots_arch_lock);
/*
* Invalidate the old slot if it's being deleted or moved. This is
* done prior to actually deleting/moving the memslot to allow vCPUs to
* continue running by ensuring there are no mappings or shadow pages
* for the memslot when it is deleted/moved. Without pre-invalidation
* (and without a lock), a window would exist between effecting the
* delete/move and committing the changes in arch code where KVM or a
* guest could access a non-existent memslot.
*
* Modifications are done on a temporary, unreachable slot. The old
* slot needs to be preserved in case a later step fails and the
* invalidation needs to be reverted.
*/
if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT);
if (!invalid_slot) {
mutex_unlock(&kvm->slots_arch_lock);
return -ENOMEM;
}
kvm_invalidate_memslot(kvm, old, invalid_slot);
}
r = kvm_prepare_memory_region(kvm, old, new, change); if (r) {
/*
* For DELETE/MOVE, revert the above INVALID change. No
* modifications required since the original slot was preserved
* in the inactive slots. Changing the active memslots also
* release slots_arch_lock.
*/
if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
kvm_activate_memslot(kvm, invalid_slot, old);
kfree(invalid_slot);
} else {
mutex_unlock(&kvm->slots_arch_lock);
}
return r;
}
/*
* For DELETE and MOVE, the working slot is now active as the INVALID
* version of the old slot. MOVE is particularly special as it reuses
* the old slot and returns a copy of the old slot (in working_slot).
* For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the
* old slot is detached but otherwise preserved.
*/
if (change == KVM_MR_CREATE)
kvm_create_memslot(kvm, new);
else if (change == KVM_MR_DELETE)
kvm_delete_memslot(kvm, old, invalid_slot);
else if (change == KVM_MR_MOVE)
kvm_move_memslot(kvm, old, new, invalid_slot);
else if (change == KVM_MR_FLAGS_ONLY)
kvm_update_flags_memslot(kvm, old, new);
else
BUG();
/* Free the temporary INVALID slot used for DELETE and MOVE. */
if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
kfree(invalid_slot);
/*
* No need to refresh new->arch, changes after dropping slots_arch_lock
* will directly hit the final, active memslot. Architectures are
* responsible for knowing that new->arch may be stale.
*/
kvm_commit_memory_region(kvm, old, new, change);
return 0;
}
static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
gfn_t start, gfn_t end)
{
struct kvm_memslot_iter iter;
kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { if (iter.slot->id != id)
return true;
}
return false;
}
static int kvm_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region2 *mem)
{
struct kvm_memory_slot *old, *new;
struct kvm_memslots *slots;
enum kvm_mr_change change;
unsigned long npages;
gfn_t base_gfn;
int as_id, id;
int r;
lockdep_assert_held(&kvm->slots_lock);
r = check_memory_region_flags(kvm, mem);
if (r)
return r;
as_id = mem->slot >> 16;
id = (u16)mem->slot;
/* General sanity checks */
if ((mem->memory_size & (PAGE_SIZE - 1)) ||
(mem->memory_size != (unsigned long)mem->memory_size))
return -EINVAL;
if (mem->guest_phys_addr & (PAGE_SIZE - 1))
return -EINVAL;
/* We can read the guest memory with __xxx_user() later on. */
if ((mem->userspace_addr & (PAGE_SIZE - 1)) || (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
!access_ok((void __user *)(unsigned long)mem->userspace_addr,
mem->memory_size))
return -EINVAL;
if (mem->flags & KVM_MEM_GUEST_MEMFD && (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
return -EINVAL;
if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
return -EINVAL;
if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
return -EINVAL;
/*
* The size of userspace-defined memory regions is restricted in order
* to play nice with dirty bitmap operations, which are indexed with an
* "unsigned int". KVM's internal memory regions don't support dirty
* logging, and so are exempt.
*/
if (id < KVM_USER_MEM_SLOTS &&
(mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
/*
* Note, the old memslot (and the pointer itself!) may be invalidated
* and/or destroyed by kvm_set_memslot().
*/
old = id_to_memslot(slots, id);
if (!mem->memory_size) {
if (!old || !old->npages)
return -EINVAL;
if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages))
return -EIO;
return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE);
}
base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT);
npages = (mem->memory_size >> PAGE_SHIFT);
if (!old || !old->npages) {
change = KVM_MR_CREATE;
/*
* To simplify KVM internals, the total number of pages across
* all memslots must fit in an unsigned long.
*/
if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
return -EINVAL;
} else { /* Modify an existing slot. */
/* Private memslots are immutable, they can only be deleted. */
if (mem->flags & KVM_MEM_GUEST_MEMFD)
return -EINVAL;
if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) ||
((mem->flags ^ old->flags) & KVM_MEM_READONLY))
return -EINVAL;
if (base_gfn != old->base_gfn)
change = KVM_MR_MOVE;
else if (mem->flags != old->flags)
change = KVM_MR_FLAGS_ONLY;
else /* Nothing to change. */
return 0;
}
if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) &&
kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages))
return -EEXIST;
/* Allocate a slot that will persist in the memslot. */
new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT);
if (!new)
return -ENOMEM;
new->as_id = as_id;
new->id = id;
new->base_gfn = base_gfn;
new->npages = npages;
new->flags = mem->flags;
new->userspace_addr = mem->userspace_addr;
if (mem->flags & KVM_MEM_GUEST_MEMFD) {
r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
if (r)
goto out;
}
r = kvm_set_memslot(kvm, old, new, change);
if (r)
goto out_unbind;
return 0;
out_unbind:
if (mem->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(new);
out:
kfree(new);
return r;
}
int kvm_set_internal_memslot(struct kvm *kvm,
const struct kvm_userspace_memory_region2 *mem)
{
if (WARN_ON_ONCE(mem->slot < KVM_USER_MEM_SLOTS))
return -EINVAL;
if (WARN_ON_ONCE(mem->flags))
return -EINVAL;
return kvm_set_memory_region(kvm, mem);
}
EXPORT_SYMBOL_GPL(kvm_set_internal_memslot);
static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region2 *mem)
{ if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
return -EINVAL;
guard(mutex)(&kvm->slots_lock);
return kvm_set_memory_region(kvm, mem);
}
#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
/**
* kvm_get_dirty_log - get a snapshot of dirty pages
* @kvm: pointer to kvm instance
* @log: slot id and address to which we copy the log
* @is_dirty: set to '1' if any dirty pages were found
* @memslot: set to the associated memslot, always valid on success
*/
int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
int *is_dirty, struct kvm_memory_slot **memslot)
{
struct kvm_memslots *slots;
int i, as_id, id;
unsigned long n;
unsigned long any = 0;
/* Dirty ring tracking may be exclusive to dirty log tracking */
if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
*memslot = NULL;
*is_dirty = 0;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
*memslot = id_to_memslot(slots, id);
if (!(*memslot) || !(*memslot)->dirty_bitmap)
return -ENOENT;
kvm_arch_sync_dirty_log(kvm, *memslot);
n = kvm_dirty_bitmap_bytes(*memslot);
for (i = 0; !any && i < n/sizeof(long); ++i)
any = (*memslot)->dirty_bitmap[i];
if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n))
return -EFAULT;
if (any)
*is_dirty = 1;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
#else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
/**
* kvm_get_dirty_log_protect - get a snapshot of dirty pages
* and reenable dirty page tracking for the corresponding pages.
* @kvm: pointer to kvm instance
* @log: slot id and address to which we copy the log
*
* We need to keep it in mind that VCPU threads can write to the bitmap
* concurrently. So, to avoid losing track of dirty pages we keep the
* following order:
*
* 1. Take a snapshot of the bit and clear it if needed.
* 2. Write protect the corresponding page.
* 3. Copy the snapshot to the userspace.
* 4. Upon return caller flushes TLB's if needed.
*
* Between 2 and 4, the guest may write to the page using the remaining TLB
* entry. This is not a problem because the page is reported dirty using
* the snapshot taken before and step 4 ensures that writes done after
* exiting to userspace will be logged for the next call.
*
*/
static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i, as_id, id;
unsigned long n;
unsigned long *dirty_bitmap;
unsigned long *dirty_bitmap_buffer;
bool flush;
/* Dirty ring tracking may be exclusive to dirty log tracking */
if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap)
return -ENOENT;
dirty_bitmap = memslot->dirty_bitmap;
kvm_arch_sync_dirty_log(kvm, memslot);
n = kvm_dirty_bitmap_bytes(memslot);
flush = false;
if (kvm->manual_dirty_log_protect) {
/*
* Unlike kvm_get_dirty_log, we always return false in *flush,
* because no flush is needed until KVM_CLEAR_DIRTY_LOG. There
* is some code duplication between this function and
* kvm_get_dirty_log, but hopefully all architecture
* transition to kvm_get_dirty_log_protect and kvm_get_dirty_log
* can be eliminated.
*/
dirty_bitmap_buffer = dirty_bitmap;
} else {
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
memset(dirty_bitmap_buffer, 0, n);
KVM_MMU_LOCK(kvm);
for (i = 0; i < n / sizeof(long); i++) {
unsigned long mask;
gfn_t offset;
if (!dirty_bitmap[i])
continue;
flush = true;
mask = xchg(&dirty_bitmap[i], 0);
dirty_bitmap_buffer[i] = mask;
offset = i * BITS_PER_LONG;
kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
offset, mask);
}
KVM_MMU_UNLOCK(kvm);
}
if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
return -EFAULT;
return 0;
}
/**
* kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
* @kvm: kvm instance
* @log: slot id and address to which we copy the log
*
* Steps 1-4 below provide general overview of dirty page logging. See
* kvm_get_dirty_log_protect() function description for additional details.
*
* We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
* always flush the TLB (step 4) even if previous step failed and the dirty
* bitmap may be corrupt. Regardless of previous outcome the KVM logging API
* does not preclude user space subsequent dirty log read. Flushing TLB ensures
* writes will be marked dirty for next log read.
*
* 1. Take a snapshot of the bit and clear it if needed.
* 2. Write protect the corresponding page.
* 3. Copy the snapshot to the userspace.
* 4. Flush TLB's if needed.
*/
static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log)
{
int r;
mutex_lock(&kvm->slots_lock);
r = kvm_get_dirty_log_protect(kvm, log);
mutex_unlock(&kvm->slots_lock);
return r;
}
/**
* kvm_clear_dirty_log_protect - clear dirty bits in the bitmap
* and reenable dirty page tracking for the corresponding pages.
* @kvm: pointer to kvm instance
* @log: slot id and address from which to fetch the bitmap of dirty pages
*/
static int kvm_clear_dirty_log_protect(struct kvm *kvm,
struct kvm_clear_dirty_log *log)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int as_id, id;
gfn_t offset;
unsigned long i, n;
unsigned long *dirty_bitmap;
unsigned long *dirty_bitmap_buffer;
bool flush;
/* Dirty ring tracking may be exclusive to dirty log tracking */
if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
if (log->first_page & 63)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap)
return -ENOENT;
dirty_bitmap = memslot->dirty_bitmap;
n = ALIGN(log->num_pages, BITS_PER_LONG) / 8;
if (log->first_page > memslot->npages || log->num_pages > memslot->npages - log->first_page || (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
return -EINVAL;
kvm_arch_sync_dirty_log(kvm, memslot);
flush = false;
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
return -EFAULT;
KVM_MMU_LOCK(kvm);
for (offset = log->first_page, i = offset / BITS_PER_LONG,
n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
i++, offset += BITS_PER_LONG) {
unsigned long mask = *dirty_bitmap_buffer++;
atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
if (!mask)
continue;
mask &= atomic_long_fetch_andnot(mask, p);
/*
* mask contains the bits that really have been cleared. This
* never includes any bits beyond the length of the memslot (if
* the length is not aligned to 64 pages), therefore it is not
* a problem if userspace sets them in log->dirty_bitmap.
*/
if (mask) {
flush = true;
kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
offset, mask);
}
}
KVM_MMU_UNLOCK(kvm); if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot);
return 0;
}
static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
struct kvm_clear_dirty_log *log)
{
int r;
mutex_lock(&kvm->slots_lock);
r = kvm_clear_dirty_log_protect(kvm, log);
mutex_unlock(&kvm->slots_lock);
return r;
}
#endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
static u64 kvm_supported_mem_attributes(struct kvm *kvm)
{
if (!kvm || kvm_arch_has_private_mem(kvm))
return KVM_MEMORY_ATTRIBUTE_PRIVATE;
return 0;
}
/*
* Returns true if _all_ gfns in the range [@start, @end) have attributes
* such that the bits in @mask match @attrs.
*/
bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
unsigned long mask, unsigned long attrs)
{
XA_STATE(xas, &kvm->mem_attr_array, start);
unsigned long index;
void *entry;
mask &= kvm_supported_mem_attributes(kvm);
if (attrs & ~mask)
return false;
if (end == start + 1)
return (kvm_get_memory_attributes(kvm, start) & mask) == attrs;
guard(rcu)();
if (!attrs)
return !xas_find(&xas, end - 1);
for (index = start; index < end; index++) {
do {
entry = xas_next(&xas);
} while (xas_retry(&xas, entry));
if (xas.xa_index != index ||
(xa_to_value(entry) & mask) != attrs)
return false;
}
return true;
}
static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
struct kvm_mmu_notifier_range *range)
{
struct kvm_gfn_range gfn_range;
struct kvm_memory_slot *slot;
struct kvm_memslots *slots;
struct kvm_memslot_iter iter;
bool found_memslot = false;
bool ret = false;
int i;
gfn_range.arg = range->arg;
gfn_range.may_block = range->may_block;
/*
* If/when KVM supports more attributes beyond private .vs shared, this
* _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target
* range already has the desired private vs. shared state (it's unclear
* if that is a net win). For now, KVM reaches this point if and only
* if the private flag is being toggled, i.e. all mappings are in play.
*/
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
slots = __kvm_memslots(kvm, i);
kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
slot = iter.slot;
gfn_range.slot = slot;
gfn_range.start = max(range->start, slot->base_gfn);
gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
if (gfn_range.start >= gfn_range.end)
continue;
if (!found_memslot) {
found_memslot = true;
KVM_MMU_LOCK(kvm);
if (!IS_KVM_NULL_FN(range->on_lock))
range->on_lock(kvm);
}
ret |= range->handler(kvm, &gfn_range);
}
}
if (range->flush_on_ret && ret)
kvm_flush_remote_tlbs(kvm);
if (found_memslot)
KVM_MMU_UNLOCK(kvm);
}
static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range)
{
/*
* Unconditionally add the range to the invalidation set, regardless of
* whether or not the arch callback actually needs to zap SPTEs. E.g.
* if KVM supports RWX attributes in the future and the attributes are
* going from R=>RW, zapping isn't strictly necessary. Unconditionally
* adding the range allows KVM to require that MMU invalidations add at
* least one range between begin() and end(), e.g. allows KVM to detect
* bugs where the add() is missed. Relaxing the rule *might* be safe,
* but it's not obvious that allowing new mappings while the attributes
* are in flux is desirable or worth the complexity.
*/
kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
return kvm_arch_pre_set_memory_attributes(kvm, range);
}
/* Set @attributes for the gfn range [@start, @end). */
static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
unsigned long attributes)
{
struct kvm_mmu_notifier_range pre_set_range = {
.start = start,
.end = end,
.arg.attributes = attributes,
.handler = kvm_pre_set_memory_attributes,
.on_lock = kvm_mmu_invalidate_begin,
.flush_on_ret = true,
.may_block = true,
};
struct kvm_mmu_notifier_range post_set_range = {
.start = start,
.end = end,
.arg.attributes = attributes,
.handler = kvm_arch_post_set_memory_attributes,
.on_lock = kvm_mmu_invalidate_end,
.may_block = true,
};
unsigned long i;
void *entry;
int r = 0;
entry = attributes ? xa_mk_value(attributes) : NULL;
mutex_lock(&kvm->slots_lock);
/* Nothing to do if the entire range as the desired attributes. */
if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes))
goto out_unlock;
/*
* Reserve memory ahead of time to avoid having to deal with failures
* partway through setting the new attributes.
*/
for (i = start; i < end; i++) {
r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
if (r)
goto out_unlock;
}
kvm_handle_gfn_range(kvm, &pre_set_range);
for (i = start; i < end; i++) {
r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
GFP_KERNEL_ACCOUNT));
KVM_BUG_ON(r, kvm);
}
kvm_handle_gfn_range(kvm, &post_set_range);
out_unlock:
mutex_unlock(&kvm->slots_lock);
return r;
}
static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
struct kvm_memory_attributes *attrs)
{
gfn_t start, end;
/* flags is currently not used. */
if (attrs->flags)
return -EINVAL;
if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
return -EINVAL;
if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
return -EINVAL;
if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
return -EINVAL;
start = attrs->address >> PAGE_SHIFT;
end = (attrs->address + attrs->size) >> PAGE_SHIFT;
/*
* xarray tracks data using "unsigned long", and as a result so does
* KVM. For simplicity, supports generic attributes only on 64-bit
* architectures.
*/
BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
}
#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{ return __gfn_to_memslot(kvm_memslots(kvm), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_memslot);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu);
u64 gen = slots->generation;
struct kvm_memory_slot *slot;
/*
* This also protects against using a memslot from a different address space,
* since different address spaces have different generation numbers.
*/
if (unlikely(gen != vcpu->last_used_slot_gen)) {
vcpu->last_used_slot = NULL;
vcpu->last_used_slot_gen = gen;
}
slot = try_get_memslot(vcpu->last_used_slot, gfn);
if (slot)
return slot;
/*
* Fall back to searching all memslots. We purposely use
* search_memslots() instead of __gfn_to_memslot() to avoid
* thrashing the VM-wide last_used_slot in kvm_memslots.
*/
slot = search_memslots(slots, gfn, false);
if (slot) {
vcpu->last_used_slot = slot;
return slot;
}
return NULL;
}
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
{ struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); return kvm_is_visible_memslot(memslot);
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
return kvm_is_visible_memslot(memslot);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn);
unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct vm_area_struct *vma;
unsigned long addr, size;
size = PAGE_SIZE;
addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
if (kvm_is_error_hva(addr))
return PAGE_SIZE;
mmap_read_lock(current->mm);
vma = find_vma(current->mm, addr);
if (!vma)
goto out;
size = vma_kernel_pagesize(vma);
out:
mmap_read_unlock(current->mm);
return size;
}
static bool memslot_is_readonly(const struct kvm_memory_slot *slot)
{
return slot->flags & KVM_MEM_READONLY;
}
static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn,
gfn_t *nr_pages, bool write)
{
if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
return KVM_HVA_ERR_BAD;
if (memslot_is_readonly(slot) && write)
return KVM_HVA_ERR_RO_BAD;
if (nr_pages)
*nr_pages = slot->npages - (gfn - slot->base_gfn);
return __gfn_to_hva_memslot(slot, gfn);
}
static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
gfn_t *nr_pages)
{
return __gfn_to_hva_many(slot, gfn, nr_pages, true);
}
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
gfn_t gfn)
{
return gfn_to_hva_many(slot, gfn, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
{ return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_hva);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn)
{
return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva);
/*
* Return the hva of a @gfn and the R/W attribute if possible.
*
* @slot: the kvm_memory_slot which contains @gfn
* @gfn: the gfn to be translated
* @writable: used to return the read/write attribute of the @slot if the hva
* is valid and @writable is not NULL
*/
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
gfn_t gfn, bool *writable)
{ unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); if (!kvm_is_error_hva(hva) && writable) *writable = !memslot_is_readonly(slot);
return hva;
}
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
{
struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
return gfn_to_hva_memslot_prot(slot, gfn, writable);
}
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable)
{
struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
return gfn_to_hva_memslot_prot(slot, gfn, writable);
}
static bool kvm_is_ad_tracked_page(struct page *page)
{
/*
* Per page-flags.h, pages tagged PG_reserved "should in general not be
* touched (e.g. set dirty) except by its owner".
*/
return !PageReserved(page);
}
static void kvm_set_page_dirty(struct page *page)
{ if (kvm_is_ad_tracked_page(page)) SetPageDirty(page);
}
static void kvm_set_page_accessed(struct page *page)
{
if (kvm_is_ad_tracked_page(page)) mark_page_accessed(page);
}
void kvm_release_page_clean(struct page *page)
{ if (!page)
return;
kvm_set_page_accessed(page); put_page(page);
}
EXPORT_SYMBOL_GPL(kvm_release_page_clean);
void kvm_release_page_dirty(struct page *page)
{ if (!page)
return;
kvm_set_page_dirty(page);
kvm_release_page_clean(page);
}
EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
static kvm_pfn_t kvm_resolve_pfn(struct kvm_follow_pfn *kfp, struct page *page,
struct follow_pfnmap_args *map, bool writable)
{
kvm_pfn_t pfn;
WARN_ON_ONCE(!!page == !!map); if (kfp->map_writable) *kfp->map_writable = writable;
if (map)
pfn = map->pfn;
else
pfn = page_to_pfn(page);
*kfp->refcounted_page = page;
return pfn;
}
/*
* The fast path to get the writable pfn which will be stored in @pfn,
* true indicates success, otherwise false is returned.
*/
static bool hva_to_pfn_fast(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn)
{
struct page *page;
bool r;
/*
* Try the fast-only path when the caller wants to pin/get the page for
* writing. If the caller only wants to read the page, KVM must go
* down the full, slow path in order to avoid racing an operation that
* breaks Copy-on-Write (CoW), e.g. so that KVM doesn't end up pointing
* at the old, read-only page while mm/ points at a new, writable page.
*/
if (!((kfp->flags & FOLL_WRITE) || kfp->map_writable))
return false;
if (kfp->pin)
r = pin_user_pages_fast(kfp->hva, 1, FOLL_WRITE, &page) == 1;
else
r = get_user_page_fast_only(kfp->hva, FOLL_WRITE, &page);
if (r) { *pfn = kvm_resolve_pfn(kfp, page, NULL, true);
return true;
}
return false;
}
/*
* The slow path to get the pfn of the specified host virtual address,
* 1 indicates success, -errno is returned if error is detected.
*/
static int hva_to_pfn_slow(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn)
{
/*
* When a VCPU accesses a page that is not mapped into the secondary
* MMU, we lookup the page using GUP to map it, so the guest VCPU can
* make progress. We always want to honor NUMA hinting faults in that
* case, because GUP usage corresponds to memory accesses from the VCPU.
* Otherwise, we'd not trigger NUMA hinting faults once a page is
* mapped into the secondary MMU and gets accessed by a VCPU.
*
* Note that get_user_page_fast_only() and FOLL_WRITE for now
* implicitly honor NUMA hinting faults and don't need this flag.
*/
unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT | kfp->flags;
struct page *page, *wpage;
int npages;
if (kfp->pin)
npages = pin_user_pages_unlocked(kfp->hva, 1, &page, flags);
else
npages = get_user_pages_unlocked(kfp->hva, 1, &page, flags);
if (npages != 1)
return npages;
/*
* Pinning is mutually exclusive with opportunistically mapping a read
* fault as writable, as KVM should never pin pages when mapping memory
* into the guest (pinning is only for direct accesses from KVM).
*/
if (WARN_ON_ONCE(kfp->map_writable && kfp->pin))
goto out;
/* map read fault as writable if possible */
if (!(flags & FOLL_WRITE) && kfp->map_writable &&
get_user_page_fast_only(kfp->hva, FOLL_WRITE, &wpage)) {
put_page(page);
page = wpage;
flags |= FOLL_WRITE;
}
out:
*pfn = kvm_resolve_pfn(kfp, page, NULL, flags & FOLL_WRITE);
return npages;
}
static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
{
if (unlikely(!(vma->vm_flags & VM_READ)))
return false;
if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE))))
return false;
return true;
}
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
struct kvm_follow_pfn *kfp, kvm_pfn_t *p_pfn)
{
struct follow_pfnmap_args args = { .vma = vma, .address = kfp->hva };
bool write_fault = kfp->flags & FOLL_WRITE;
int r;
/*
* Remapped memory cannot be pinned in any meaningful sense. Bail if
* the caller wants to pin the page, i.e. access the page outside of
* MMU notifier protection, and unsafe umappings are disallowed.
*/
if (kfp->pin && !allow_unsafe_mappings)
return -EINVAL;
r = follow_pfnmap_start(&args);
if (r) {
/*
* get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
* not call the fault handler, so do it here.
*/
bool unlocked = false;
r = fixup_user_fault(current->mm, kfp->hva,
(write_fault ? FAULT_FLAG_WRITE : 0),
&unlocked);
if (unlocked)
return -EAGAIN;
if (r)
return r;
r = follow_pfnmap_start(&args);
if (r)
return r;
}
if (write_fault && !args.writable) {
*p_pfn = KVM_PFN_ERR_RO_FAULT;
goto out;
}
*p_pfn = kvm_resolve_pfn(kfp, NULL, &args, args.writable);
out:
follow_pfnmap_end(&args);
return r;
}
kvm_pfn_t hva_to_pfn(struct kvm_follow_pfn *kfp)
{
struct vm_area_struct *vma;
kvm_pfn_t pfn;
int npages, r;
might_sleep();
if (WARN_ON_ONCE(!kfp->refcounted_page))
return KVM_PFN_ERR_FAULT;
if (hva_to_pfn_fast(kfp, &pfn))
return pfn;
npages = hva_to_pfn_slow(kfp, &pfn); if (npages == 1)
return pfn;
if (npages == -EINTR || npages == -EAGAIN)
return KVM_PFN_ERR_SIGPENDING;
if (npages == -EHWPOISON)
return KVM_PFN_ERR_HWPOISON; mmap_read_lock(current->mm);
retry:
vma = vma_lookup(current->mm, kfp->hva);
if (vma == NULL)
pfn = KVM_PFN_ERR_FAULT;
else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
r = hva_to_pfn_remapped(vma, kfp, &pfn); if (r == -EAGAIN)
goto retry;
if (r < 0)
pfn = KVM_PFN_ERR_FAULT;
} else {
if ((kfp->flags & FOLL_NOWAIT) &&
vma_is_valid(vma, kfp->flags & FOLL_WRITE))
pfn = KVM_PFN_ERR_NEEDS_IO;
else
pfn = KVM_PFN_ERR_FAULT;
}
mmap_read_unlock(current->mm);
return pfn;
}
static kvm_pfn_t kvm_follow_pfn(struct kvm_follow_pfn *kfp)
{
kfp->hva = __gfn_to_hva_many(kfp->slot, kfp->gfn, NULL,
kfp->flags & FOLL_WRITE);
if (kfp->hva == KVM_HVA_ERR_RO_BAD)
return KVM_PFN_ERR_RO_FAULT;
if (kvm_is_error_hva(kfp->hva))
return KVM_PFN_NOSLOT;
if (memslot_is_readonly(kfp->slot) && kfp->map_writable) { *kfp->map_writable = false;
kfp->map_writable = NULL;
}
return hva_to_pfn(kfp);
}
kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn,
unsigned int foll, bool *writable,
struct page **refcounted_page)
{
struct kvm_follow_pfn kfp = {
.slot = slot,
.gfn = gfn,
.flags = foll,
.map_writable = writable,
.refcounted_page = refcounted_page,
};
if (WARN_ON_ONCE(!writable || !refcounted_page))
return KVM_PFN_ERR_FAULT;
*writable = false;
*refcounted_page = NULL;
return kvm_follow_pfn(&kfp);
}
EXPORT_SYMBOL_GPL(__kvm_faultin_pfn);
int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn,
struct page **pages, int nr_pages)
{
unsigned long addr;
gfn_t entry = 0;
addr = gfn_to_hva_many(slot, gfn, &entry);
if (kvm_is_error_hva(addr))
return -1;
if (entry < nr_pages)
return 0;
return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages);
}
EXPORT_SYMBOL_GPL(kvm_prefetch_pages);
/*
* Don't use this API unless you are absolutely, positively certain that KVM
* needs to get a struct page, e.g. to pin the page for firmware DMA.
*
* FIXME: Users of this API likely need to FOLL_PIN the page, not just elevate
* its refcount.
*/
struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write)
{
struct page *refcounted_page = NULL;
struct kvm_follow_pfn kfp = {
.slot = gfn_to_memslot(kvm, gfn),
.gfn = gfn,
.flags = write ? FOLL_WRITE : 0,
.refcounted_page = &refcounted_page,
};
(void)kvm_follow_pfn(&kfp);
return refcounted_page;
}
EXPORT_SYMBOL_GPL(__gfn_to_page);
int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
bool writable)
{
struct kvm_follow_pfn kfp = {
.slot = gfn_to_memslot(vcpu->kvm, gfn),
.gfn = gfn,
.flags = writable ? FOLL_WRITE : 0,
.refcounted_page = &map->pinned_page,
.pin = true,
};
map->pinned_page = NULL;
map->page = NULL;
map->hva = NULL;
map->gfn = gfn;
map->writable = writable;
map->pfn = kvm_follow_pfn(&kfp);
if (is_error_noslot_pfn(map->pfn))
return -EINVAL;
if (pfn_valid(map->pfn)) {
map->page = pfn_to_page(map->pfn);
map->hva = kmap(map->page);
#ifdef CONFIG_HAS_IOMEM
} else {
map->hva = memremap(pfn_to_hpa(map->pfn), PAGE_SIZE, MEMREMAP_WB);
#endif
}
return map->hva ? 0 : -EFAULT;
}
EXPORT_SYMBOL_GPL(__kvm_vcpu_map);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map)
{
if (!map->hva)
return;
if (map->page)
kunmap(map->page);
#ifdef CONFIG_HAS_IOMEM
else
memunmap(map->hva);
#endif
if (map->writable)
kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
if (map->pinned_page) {
if (map->writable)
kvm_set_page_dirty(map->pinned_page);
kvm_set_page_accessed(map->pinned_page);
unpin_user_page(map->pinned_page);
}
map->hva = NULL;
map->page = NULL;
map->pinned_page = NULL;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
static int next_segment(unsigned long len, int offset)
{
if (len > PAGE_SIZE - offset)
return PAGE_SIZE - offset;
else
return len;
}
/* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */
static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn,
void *data, int offset, int len)
{
int r;
unsigned long addr;
if (WARN_ON_ONCE(offset + len > PAGE_SIZE))
return -EFAULT;
addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr))
return -EFAULT;
r = __copy_from_user(data, (void __user *)addr + offset, len);
if (r)
return -EFAULT;
return 0;
}
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len)
{ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
return __kvm_read_guest_page(slot, gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data,
int offset, int len)
{
struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
return __kvm_read_guest_page(slot, gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest);
int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest);
static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
void *data, int offset, unsigned long len)
{
int r;
unsigned long addr;
if (WARN_ON_ONCE(offset + len > PAGE_SIZE))
return -EFAULT;
addr = gfn_to_hva_memslot_prot(slot, gfn, NULL);
if (kvm_is_error_hva(addr))
return -EFAULT;
pagefault_disable();
r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
pagefault_enable();
if (r)
return -EFAULT;
return 0;
}
int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
void *data, unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
int offset = offset_in_page(gpa);
return __kvm_read_guest_atomic(slot, gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
/* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */
static int __kvm_write_guest_page(struct kvm *kvm,
struct kvm_memory_slot *memslot, gfn_t gfn,
const void *data, int offset, int len)
{
int r;
unsigned long addr;
if (WARN_ON_ONCE(offset + len > PAGE_SIZE))
return -EFAULT;
addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr))
return -EFAULT;
r = __copy_to_user((void __user *)addr + offset, data, len); if (r)
return -EFAULT;
mark_page_dirty_in_slot(kvm, memslot, gfn);
return 0;
}
int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
const void *data, int offset, int len)
{ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_write_guest_page);
int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
const void *data, int offset, int len)
{
struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest);
int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest);
static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots,
struct gfn_to_hva_cache *ghc,
gpa_t gpa, unsigned long len)
{
int offset = offset_in_page(gpa);
gfn_t start_gfn = gpa >> PAGE_SHIFT;
gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
gfn_t nr_pages_avail;
/* Update ghc->generation before performing any error checks. */
ghc->generation = slots->generation;
if (start_gfn > end_gfn) {
ghc->hva = KVM_HVA_ERR_BAD;
return -EINVAL;
}
/*
* If the requested region crosses two memslots, we still
* verify that the entire region is valid here.
*/
for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) {
ghc->memslot = __gfn_to_memslot(slots, start_gfn);
ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
&nr_pages_avail);
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
}
/* Use the slow path for cross page reads and writes. */
if (nr_pages_needed == 1)
ghc->hva += offset;
else
ghc->memslot = NULL;
ghc->gpa = gpa;
ghc->len = len;
return 0;
}
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
gpa_t gpa, unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len);
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;
gpa_t gpa = ghc->gpa + offset;
if (WARN_ON_ONCE(len + offset > ghc->len))
return -EINVAL;
if (slots->generation != ghc->generation) {
if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
return -EFAULT;
}
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
if (unlikely(!ghc->memslot))
return kvm_write_guest(kvm, gpa, data, len);
r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
if (r)
return -EFAULT;
mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached);
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len)
{
return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len);
}
EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;
gpa_t gpa = ghc->gpa + offset;
if (WARN_ON_ONCE(len + offset > ghc->len))
return -EINVAL;
if (slots->generation != ghc->generation) {
if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
return -EFAULT;
}
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
if (unlikely(!ghc->memslot))
return kvm_read_guest(kvm, gpa, data, len);
r = __copy_from_user(data, (void __user *)ghc->hva + offset, len);
if (r)
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached);
int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len)
{
return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
{
const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);
void mark_page_dirty_in_slot(struct kvm *kvm,
const struct kvm_memory_slot *memslot,
gfn_t gfn)
{ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
#ifdef CONFIG_HAVE_KVM_DIRTY_RING
if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm))
return;
WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm));
#endif
if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
u32 slot = (memslot->as_id << 16) | memslot->id;
if (kvm->dirty_ring_size && vcpu)
kvm_dirty_ring_push(vcpu, slot, rel_gfn);
else if (memslot->dirty_bitmap) set_bit_le(rel_gfn, memslot->dirty_bitmap);
}
}
EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
struct kvm_memory_slot *memslot;
memslot = gfn_to_memslot(kvm, gfn);
mark_page_dirty_in_slot(kvm, memslot, gfn);
}
EXPORT_SYMBOL_GPL(mark_page_dirty);
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_memory_slot *memslot;
memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
void kvm_sigset_activate(struct kvm_vcpu *vcpu)
{ if (!vcpu->sigset_active)
return;
/*
* This does a lockless modification of ->real_blocked, which is fine
* because, only current can change ->real_blocked and all readers of
* ->real_blocked don't care as long ->real_blocked is always a subset
* of ->blocked.
*/
sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked);
}
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu)
{ if (!vcpu->sigset_active)
return;
sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL);
sigemptyset(¤t->real_blocked);
}
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
unsigned int old, val, grow, grow_start;
old = val = vcpu->halt_poll_ns;
grow_start = READ_ONCE(halt_poll_ns_grow_start);
grow = READ_ONCE(halt_poll_ns_grow);
if (!grow)
goto out;
val *= grow;
if (val < grow_start)
val = grow_start;
vcpu->halt_poll_ns = val;
out:
trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
}
static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
{
unsigned int old, val, shrink, grow_start;
old = val = vcpu->halt_poll_ns;
shrink = READ_ONCE(halt_poll_ns_shrink);
grow_start = READ_ONCE(halt_poll_ns_grow_start);
if (shrink == 0)
val = 0;
else
val /= shrink;
if (val < grow_start)
val = 0;
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
}
static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
{
int ret = -EINTR;
int idx = srcu_read_lock(&vcpu->kvm->srcu);
if (kvm_arch_vcpu_runnable(vcpu))
goto out;
if (kvm_cpu_has_pending_timer(vcpu))
goto out;
if (signal_pending(current))
goto out;
if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu))
goto out;
ret = 0;
out:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
/*
* Block the vCPU until the vCPU is runnable, an event arrives, or a signal is
* pending. This is mostly used when halting a vCPU, but may also be used
* directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI.
*/
bool kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
bool waited = false;
vcpu->stat.generic.blocking = 1;
preempt_disable();
kvm_arch_vcpu_blocking(vcpu);
prepare_to_rcuwait(wait);
preempt_enable();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0)
break;
waited = true;
schedule();
}
preempt_disable();
finish_rcuwait(wait);
kvm_arch_vcpu_unblocking(vcpu);
preempt_enable();
vcpu->stat.generic.blocking = 0;
return waited;
}
static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start,
ktime_t end, bool success)
{
struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic;
u64 poll_ns = ktime_to_ns(ktime_sub(end, start));
++vcpu->stat.generic.halt_attempted_poll; if (success) {
++vcpu->stat.generic.halt_successful_poll;
if (!vcpu_valid_wakeup(vcpu))
++vcpu->stat.generic.halt_poll_invalid;
stats->halt_poll_success_ns += poll_ns;
KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns);
} else {
stats->halt_poll_fail_ns += poll_ns;
KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns);
}
}
static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
if (kvm->override_halt_poll_ns) {
/*
* Ensure kvm->max_halt_poll_ns is not read before
* kvm->override_halt_poll_ns.
*
* Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL.
*/
smp_rmb();
return READ_ONCE(kvm->max_halt_poll_ns);
}
return READ_ONCE(halt_poll_ns);
}
/*
* Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt
* polling is enabled, busy wait for a short time before blocking to avoid the
* expensive block+unblock sequence if a wake event arrives soon after the vCPU
* is halted.
*/
void kvm_vcpu_halt(struct kvm_vcpu *vcpu)
{ unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
bool halt_poll_allowed = !kvm_arch_no_poll(vcpu);
ktime_t start, cur, poll_end;
bool waited = false;
bool do_halt_poll;
u64 halt_ns;
if (vcpu->halt_poll_ns > max_halt_poll_ns) vcpu->halt_poll_ns = max_halt_poll_ns;
do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns;
start = cur = poll_end = ktime_get();
if (do_halt_poll) {
ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns);
do {
if (kvm_vcpu_check_block(vcpu) < 0)
goto out;
cpu_relax();
poll_end = cur = ktime_get();
} while (kvm_vcpu_can_poll(cur, stop));
}
waited = kvm_vcpu_block(vcpu);
cur = ktime_get();
if (waited) {
vcpu->stat.generic.halt_wait_ns +=
ktime_to_ns(cur) - ktime_to_ns(poll_end);
KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist,
ktime_to_ns(cur) - ktime_to_ns(poll_end));
}
out:
/* The total time the vCPU was "halted", including polling time. */
halt_ns = ktime_to_ns(cur) - ktime_to_ns(start);
/*
* Note, halt-polling is considered successful so long as the vCPU was
* never actually scheduled out, i.e. even if the wake event arrived
* after of the halt-polling loop itself, but before the full wait.
*/
if (do_halt_poll) update_halt_poll_stats(vcpu, start, poll_end, !waited);
if (halt_poll_allowed) {
/* Recompute the max halt poll time in case it changed. */
max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu);
if (!vcpu_valid_wakeup(vcpu)) {
shrink_halt_poll_ns(vcpu);
} else if (max_halt_poll_ns) {
if (halt_ns <= vcpu->halt_poll_ns)
;
/* we had a long block, shrink polling */
else if (vcpu->halt_poll_ns &&
halt_ns > max_halt_poll_ns)
shrink_halt_poll_ns(vcpu);
/* we had a short halt and our poll time is too small */
else if (vcpu->halt_poll_ns < max_halt_poll_ns &&
halt_ns < max_halt_poll_ns)
grow_halt_poll_ns(vcpu);
} else {
vcpu->halt_poll_ns = 0;
}
}
trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu));
}
EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true);
++vcpu->stat.generic.halt_wakeup;
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
#ifndef CONFIG_S390
/*
* Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
*/
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int me, cpu;
if (kvm_vcpu_wake_up(vcpu))
return;
me = get_cpu();
/*
* The only state change done outside the vcpu mutex is IN_GUEST_MODE
* to EXITING_GUEST_MODE. Therefore the moderately expensive "should
* kick" check does not need atomic operations if kvm_vcpu_kick is used
* within the vCPU thread itself.
*/
if (vcpu == __this_cpu_read(kvm_running_vcpu)) {
if (vcpu->mode == IN_GUEST_MODE) WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE);
goto out;
}
/*
* Note, the vCPU could get migrated to a different pCPU at any point
* after kvm_arch_vcpu_should_kick(), which could result in sending an
* IPI to the previous pCPU. But, that's ok because the purpose of the
* IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the
* vCPU also requires it to leave IN_GUEST_MODE.
*/
if (kvm_arch_vcpu_should_kick(vcpu)) {
cpu = READ_ONCE(vcpu->cpu);
if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu);
}
out:
put_cpu();
}
EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
#endif /* !CONFIG_S390 */
int kvm_vcpu_yield_to(struct kvm_vcpu *target)
{
struct task_struct *task = NULL;
int ret;
if (!read_trylock(&target->pid_lock))
return 0;
if (target->pid)
task = get_pid_task(target->pid, PIDTYPE_PID);
read_unlock(&target->pid_lock);
if (!task)
return 0;
ret = yield_to(task, 1);
put_task_struct(task);
return ret;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
/*
* Helper that checks whether a VCPU is eligible for directed yield.
* Most eligible candidate to yield is decided by following heuristics:
*
* (a) VCPU which has not done pl-exit or cpu relax intercepted recently
* (preempted lock holder), indicated by @in_spin_loop.
* Set at the beginning and cleared at the end of interception/PLE handler.
*
* (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
* chance last time (mostly it has become eligible now since we have probably
* yielded to lockholder in last iteration. This is done by toggling
* @dy_eligible each time a VCPU checked for eligibility.)
*
* Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
* to preempted lock-holder could result in wrong VCPU selection and CPU
* burning. Giving priority for a potential lock-holder increases lock
* progress.
*
* Since algorithm is based on heuristics, accessing another VCPU data without
* locking does not harm. It may result in trying to yield to same VCPU, fail
* and continue with next VCPU and so on.
*/
static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
bool eligible;
eligible = !vcpu->spin_loop.in_spin_loop ||
vcpu->spin_loop.dy_eligible;
if (vcpu->spin_loop.in_spin_loop)
kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
return eligible;
#else
return true;
#endif
}
/*
* Unlike kvm_arch_vcpu_runnable, this function is called outside
* a vcpu_load/vcpu_put pair. However, for most architectures
* kvm_arch_vcpu_runnable does not require vcpu_load.
*/
bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
{
return kvm_arch_vcpu_runnable(vcpu);
}
static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
{
if (kvm_arch_dy_runnable(vcpu))
return true;
#ifdef CONFIG_KVM_ASYNC_PF
if (!list_empty_careful(&vcpu->async_pf.done))
return true;
#endif
return false;
}
/*
* By default, simply query the target vCPU's current mode when checking if a
* vCPU was preempted in kernel mode. All architectures except x86 (or more
* specifical, except VMX) allow querying whether or not a vCPU is in kernel
* mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel()
* directly for cross-vCPU checks is functionally correct and accurate.
*/
bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu)
{
return kvm_arch_vcpu_in_kernel(vcpu);
}
bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
return false;
}
void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
int nr_vcpus, start, i, idx, yielded;
struct kvm *kvm = me->kvm;
struct kvm_vcpu *vcpu;
int try = 3;
nr_vcpus = atomic_read(&kvm->online_vcpus);
if (nr_vcpus < 2)
return;
/* Pairs with the smp_wmb() in kvm_vm_ioctl_create_vcpu(). */
smp_rmb();
kvm_vcpu_set_in_spin_loop(me, true);
/*
* The current vCPU ("me") is spinning in kernel mode, i.e. is likely
* waiting for a resource to become available. Attempt to yield to a
* vCPU that is runnable, but not currently running, e.g. because the
* vCPU was preempted by a higher priority task. With luck, the vCPU
* that was preempted is holding a lock or some other resource that the
* current vCPU is waiting to acquire, and yielding to the other vCPU
* will allow it to make forward progress and release the lock (or kick
* the spinning vCPU, etc).
*
* Since KVM has no insight into what exactly the guest is doing,
* approximate a round-robin selection by iterating over all vCPUs,
* starting at the last boosted vCPU. I.e. if N=kvm->last_boosted_vcpu,
* iterate over vCPU[N+1]..vCPU[N-1], wrapping as needed.
*
* Note, this is inherently racy, e.g. if multiple vCPUs are spinning,
* they may all try to yield to the same vCPU(s). But as above, this
* is all best effort due to KVM's lack of visibility into the guest.
*/
start = READ_ONCE(kvm->last_boosted_vcpu) + 1;
for (i = 0; i < nr_vcpus; i++) {
idx = (start + i) % nr_vcpus;
if (idx == me->vcpu_idx)
continue;
vcpu = xa_load(&kvm->vcpu_array, idx);
if (!READ_ONCE(vcpu->ready))
continue;
if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu))
continue;
/*
* Treat the target vCPU as being in-kernel if it has a pending
* interrupt, as the vCPU trying to yield may be spinning
* waiting on IPI delivery, i.e. the target vCPU is in-kernel
* for the purposes of directed yield.
*/
if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
!kvm_arch_dy_has_pending_interrupt(vcpu) &&
!kvm_arch_vcpu_preempted_in_kernel(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
yielded = kvm_vcpu_yield_to(vcpu);
if (yielded > 0) {
WRITE_ONCE(kvm->last_boosted_vcpu, i);
break;
} else if (yielded < 0 && !--try) {
break;
}
}
kvm_vcpu_set_in_spin_loop(me, false);
/* Ensure vcpu is not eligible during next spinloop */
kvm_vcpu_set_dy_eligible(me, false);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
{
#ifdef CONFIG_HAVE_KVM_DIRTY_RING
return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
(pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
kvm->dirty_ring_size / PAGE_SIZE);
#else
return false;
#endif
}
static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
{
struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
struct page *page;
if (vmf->pgoff == 0)
page = virt_to_page(vcpu->run);
#ifdef CONFIG_X86
else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
page = virt_to_page(vcpu->arch.pio_data);
#endif
#ifdef CONFIG_KVM_MMIO
else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
#endif
else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
page = kvm_dirty_ring_get_page(
&vcpu->dirty_ring,
vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
else
return kvm_arch_vcpu_fault(vcpu, vmf);
get_page(page);
vmf->page = page;
return 0;
}
static const struct vm_operations_struct kvm_vcpu_vm_ops = {
.fault = kvm_vcpu_fault,
};
static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
{
struct kvm_vcpu *vcpu = file->private_data;
unsigned long pages = vma_pages(vma);
if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
return -EINVAL;
vma->vm_ops = &kvm_vcpu_vm_ops;
return 0;
}
static int kvm_vcpu_release(struct inode *inode, struct file *filp)
{
struct kvm_vcpu *vcpu = filp->private_data;
kvm_put_kvm(vcpu->kvm);
return 0;
}
static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
.mmap = kvm_vcpu_mmap,
.llseek = noop_llseek,
KVM_COMPAT(kvm_vcpu_compat_ioctl),
};
/*
* Allocates an inode for the vcpu.
*/
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
char name[8 + 1 + ITOA_MAX_LEN + 1];
snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id);
return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
static int vcpu_get_pid(void *data, u64 *val)
{
struct kvm_vcpu *vcpu = data;
read_lock(&vcpu->pid_lock);
*val = pid_nr(vcpu->pid);
read_unlock(&vcpu->pid_lock);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n");
static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
struct dentry *debugfs_dentry;
char dir_name[ITOA_MAX_LEN * 2];
if (!debugfs_initialized())
return;
snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
debugfs_dentry = debugfs_create_dir(dir_name,
vcpu->kvm->debugfs_dentry);
debugfs_create_file("pid", 0444, debugfs_dentry, vcpu,
&vcpu_get_pid_fops);
kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry);
}
#endif
/*
* Creates some virtual cpus. Good luck creating more than one.
*/
static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id)
{
int r;
struct kvm_vcpu *vcpu;
struct page *page;
/*
* KVM tracks vCPU IDs as 'int', be kind to userspace and reject
* too-large values instead of silently truncating.
*
* Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first
* changing the storage type (at the very least, IDs should be tracked
* as unsigned ints).
*/
BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX);
if (id >= KVM_MAX_VCPU_IDS)
return -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus >= kvm->max_vcpus) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
r = kvm_arch_vcpu_precreate(kvm, id);
if (r) {
mutex_unlock(&kvm->lock);
return r;
}
kvm->created_vcpus++;
mutex_unlock(&kvm->lock);
vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
if (!vcpu) {
r = -ENOMEM;
goto vcpu_decrement;
}
BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE);
page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!page) {
r = -ENOMEM;
goto vcpu_free;
}
vcpu->run = page_address(page);
kvm_vcpu_init(vcpu, kvm, id);
r = kvm_arch_vcpu_create(vcpu);
if (r)
goto vcpu_free_run_page;
if (kvm->dirty_ring_size) {
r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
id, kvm->dirty_ring_size);
if (r)
goto arch_vcpu_destroy;
}
mutex_lock(&kvm->lock);
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;
}
vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT);
WARN_ON_ONCE(r == -EBUSY);
if (r)
goto unlock_vcpu_destroy;
/*
* Now it's all set up, let userspace reach it. Grab the vCPU's mutex
* so that userspace can't invoke vCPU ioctl()s until the vCPU is fully
* visible (per online_vcpus), e.g. so that KVM doesn't get tricked
* into a NULL-pointer dereference because KVM thinks the _current_
* vCPU doesn't exist. As a bonus, taking vcpu->mutex ensures lockdep
* knows it's taken *inside* kvm->lock.
*/
mutex_lock(&vcpu->mutex);
kvm_get_kvm(kvm);
r = create_vcpu_fd(vcpu);
if (r < 0)
goto kvm_put_xa_erase;
/*
* Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu
* pointer before kvm->online_vcpu's incremented value.
*/
smp_wmb();
atomic_inc(&kvm->online_vcpus);
mutex_unlock(&vcpu->mutex);
mutex_unlock(&kvm->lock);
kvm_arch_vcpu_postcreate(vcpu);
kvm_create_vcpu_debugfs(vcpu);
return r;
kvm_put_xa_erase:
mutex_unlock(&vcpu->mutex);
kvm_put_kvm_no_destroy(kvm);
xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx);
unlock_vcpu_destroy:
mutex_unlock(&kvm->lock);
kvm_dirty_ring_free(&vcpu->dirty_ring);
arch_vcpu_destroy:
kvm_arch_vcpu_destroy(vcpu);
vcpu_free_run_page:
free_page((unsigned long)vcpu->run);
vcpu_free:
kmem_cache_free(kvm_vcpu_cache, vcpu);
vcpu_decrement:
mutex_lock(&kvm->lock);
kvm->created_vcpus--;
mutex_unlock(&kvm->lock);
return r;
}
static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
{
if (sigset) {
sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
vcpu->sigset_active = 1;
vcpu->sigset = *sigset;
} else
vcpu->sigset_active = 0;
return 0;
}
static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer,
size_t size, loff_t *offset)
{
struct kvm_vcpu *vcpu = file->private_data;
return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header,
&kvm_vcpu_stats_desc[0], &vcpu->stat,
sizeof(vcpu->stat), user_buffer, size, offset);
}
static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
{
struct kvm_vcpu *vcpu = file->private_data;
kvm_put_kvm(vcpu->kvm);
return 0;
}
static const struct file_operations kvm_vcpu_stats_fops = {
.owner = THIS_MODULE,
.read = kvm_vcpu_stats_read,
.release = kvm_vcpu_stats_release,
.llseek = noop_llseek,
};
static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
{
int fd;
struct file *file;
char name[15 + ITOA_MAX_LEN + 1];
snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id);
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
return fd;
file = anon_inode_getfile_fmode(name, &kvm_vcpu_stats_fops, vcpu,
O_RDONLY, FMODE_PREAD);
if (IS_ERR(file)) {
put_unused_fd(fd);
return PTR_ERR(file);
}
kvm_get_kvm(vcpu->kvm);
fd_install(fd, file);
return fd;
}
#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
struct kvm_pre_fault_memory *range)
{
int idx;
long r;
u64 full_size;
if (range->flags)
return -EINVAL;
if (!PAGE_ALIGNED(range->gpa) ||
!PAGE_ALIGNED(range->size) ||
range->gpa + range->size <= range->gpa)
return -EINVAL;
vcpu_load(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
full_size = range->size;
do {
if (signal_pending(current)) {
r = -EINTR;
break;
}
r = kvm_arch_vcpu_pre_fault_memory(vcpu, range);
if (WARN_ON_ONCE(r == 0 || r == -EIO))
break;
if (r < 0)
break;
range->size -= r;
range->gpa += r;
cond_resched();
} while (range->size);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
vcpu_put(vcpu);
/* Return success if at least one page was mapped successfully. */
return full_size == range->size ? r : 0;
}
#endif
static int kvm_wait_for_vcpu_online(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
/*
* In practice, this happy path will always be taken, as a well-behaved
* VMM will never invoke a vCPU ioctl() before KVM_CREATE_VCPU returns.
*/
if (likely(vcpu->vcpu_idx < atomic_read(&kvm->online_vcpus)))
return 0;
/*
* Acquire and release the vCPU's mutex to wait for vCPU creation to
* complete (kvm_vm_ioctl_create_vcpu() holds the mutex until the vCPU
* is fully online).
*/
if (mutex_lock_killable(&vcpu->mutex))
return -EINTR;
mutex_unlock(&vcpu->mutex);
if (WARN_ON_ONCE(!kvm_get_vcpu(kvm, vcpu->vcpu_idx)))
return -EIO;
return 0;
}
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
int r;
struct kvm_fpu *fpu = NULL;
struct kvm_sregs *kvm_sregs = NULL;
if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
return -EIO;
if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
return -EINVAL;
/*
* Wait for the vCPU to be online before handling the ioctl(), as KVM
* assumes the vCPU is reachable via vcpu_array, i.e. may dereference
* a NULL pointer if userspace invokes an ioctl() before KVM is ready.
*/
r = kvm_wait_for_vcpu_online(vcpu);
if (r)
return r;
/*
* Some architectures have vcpu ioctls that are asynchronous to vcpu
* execution; mutex_lock() would break them.
*/
r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg);
if (r != -ENOIOCTLCMD)
return r;
if (mutex_lock_killable(&vcpu->mutex))
return -EINTR;
switch (ioctl) {
case KVM_RUN: {
struct pid *oldpid;
r = -EINVAL;
if (arg)
goto out;
/*
* Note, vcpu->pid is primarily protected by vcpu->mutex. The
* dedicated r/w lock allows other tasks, e.g. other vCPUs, to
* read vcpu->pid while this vCPU is in KVM_RUN, e.g. to yield
* directly to this vCPU
*/
oldpid = vcpu->pid;
if (unlikely(oldpid != task_pid(current))) {
/* The thread running this VCPU changed. */
struct pid *newpid;
r = kvm_arch_vcpu_run_pid_change(vcpu);
if (r)
break;
newpid = get_task_pid(current, PIDTYPE_PID);
write_lock(&vcpu->pid_lock);
vcpu->pid = newpid;
write_unlock(&vcpu->pid_lock);
put_pid(oldpid);
}
vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);
r = kvm_arch_vcpu_ioctl_run(vcpu);
vcpu->wants_to_run = false;
trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
break;
}
case KVM_GET_REGS: {
struct kvm_regs *kvm_regs;
r = -ENOMEM;
kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
if (!kvm_regs)
goto out;
r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
if (r)
goto out_free1;
r = -EFAULT;
if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
goto out_free1;
r = 0;
out_free1:
kfree(kvm_regs);
break;
}
case KVM_SET_REGS: {
struct kvm_regs *kvm_regs;
kvm_regs = memdup_user(argp, sizeof(*kvm_regs));
if (IS_ERR(kvm_regs)) {
r = PTR_ERR(kvm_regs);
goto out;
}
r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
kfree(kvm_regs);
break;
}
case KVM_GET_SREGS: {
kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
r = -ENOMEM;
if (!kvm_sregs)
goto out;
r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs)))
goto out;
r = 0;
break;
}
case KVM_SET_SREGS: {
kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs));
if (IS_ERR(kvm_sregs)) {
r = PTR_ERR(kvm_sregs);
kvm_sregs = NULL;
goto out;
}
r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
break;
}
case KVM_GET_MP_STATE: {
struct kvm_mp_state mp_state;
r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, &mp_state, sizeof(mp_state)))
goto out;
r = 0;
break;
}
case KVM_SET_MP_STATE: {
struct kvm_mp_state mp_state;
r = -EFAULT;
if (copy_from_user(&mp_state, argp, sizeof(mp_state)))
goto out;
r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
break;
}
case KVM_TRANSLATE: {
struct kvm_translation tr;
r = -EFAULT;
if (copy_from_user(&tr, argp, sizeof(tr)))
goto out;
r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, &tr, sizeof(tr)))
goto out;
r = 0;
break;
}
case KVM_SET_GUEST_DEBUG: {
struct kvm_guest_debug dbg;
r = -EFAULT;
if (copy_from_user(&dbg, argp, sizeof(dbg)))
goto out;
r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
break;
}
case KVM_SET_SIGNAL_MASK: {
struct kvm_signal_mask __user *sigmask_arg = argp;
struct kvm_signal_mask kvm_sigmask;
sigset_t sigset, *p;
p = NULL;
if (argp) {
r = -EFAULT;
if (copy_from_user(&kvm_sigmask, argp,
sizeof(kvm_sigmask)))
goto out;
r = -EINVAL;
if (kvm_sigmask.len != sizeof(sigset))
goto out;
r = -EFAULT;
if (copy_from_user(&sigset, sigmask_arg->sigset,
sizeof(sigset)))
goto out;
p = &sigset;
}
r = kvm_vcpu_ioctl_set_sigmask(vcpu, p);
break;
}
case KVM_GET_FPU: {
fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
r = -ENOMEM;
if (!fpu)
goto out;
r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu)))
goto out;
r = 0;
break;
}
case KVM_SET_FPU: {
fpu = memdup_user(argp, sizeof(*fpu));
if (IS_ERR(fpu)) {
r = PTR_ERR(fpu);
fpu = NULL;
goto out;
}
r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
break;
}
case KVM_GET_STATS_FD: {
r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
break;
}
#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
case KVM_PRE_FAULT_MEMORY: {
struct kvm_pre_fault_memory range;
r = -EFAULT;
if (copy_from_user(&range, argp, sizeof(range)))
break;
r = kvm_vcpu_pre_fault_memory(vcpu, &range);
/* Pass back leftover range. */
if (copy_to_user(argp, &range, sizeof(range)))
r = -EFAULT;
break;
}
#endif
default:
r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
}
out:
mutex_unlock(&vcpu->mutex);
kfree(fpu);
kfree(kvm_sregs);
return r;
}
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = compat_ptr(arg);
int r;
if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
return -EIO;
switch (ioctl) {
case KVM_SET_SIGNAL_MASK: {
struct kvm_signal_mask __user *sigmask_arg = argp;
struct kvm_signal_mask kvm_sigmask;
sigset_t sigset;
if (argp) {
r = -EFAULT;
if (copy_from_user(&kvm_sigmask, argp,
sizeof(kvm_sigmask)))
goto out;
r = -EINVAL;
if (kvm_sigmask.len != sizeof(compat_sigset_t))
goto out;
r = -EFAULT;
if (get_compat_sigset(&sigset,
(compat_sigset_t __user *)sigmask_arg->sigset))
goto out;
r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
} else
r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL);
break;
}
default:
r = kvm_vcpu_ioctl(filp, ioctl, arg);
}
out:
return r;
}
#endif
static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct kvm_device *dev = filp->private_data;
if (dev->ops->mmap) return dev->ops->mmap(dev, vma);
return -ENODEV;
}
static int kvm_device_ioctl_attr(struct kvm_device *dev,
int (*accessor)(struct kvm_device *dev,
struct kvm_device_attr *attr),
unsigned long arg)
{
struct kvm_device_attr attr;
if (!accessor)
return -EPERM;
if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
return -EFAULT;
return accessor(dev, &attr);
}
static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
struct kvm_device *dev = filp->private_data;
if (dev->kvm->mm != current->mm || dev->kvm->vm_dead)
return -EIO;
switch (ioctl) {
case KVM_SET_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
case KVM_GET_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg);
case KVM_HAS_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg);
default:
if (dev->ops->ioctl) return dev->ops->ioctl(dev, ioctl, arg);
return -ENOTTY;
}
}
static int kvm_device_release(struct inode *inode, struct file *filp)
{
struct kvm_device *dev = filp->private_data;
struct kvm *kvm = dev->kvm;
if (dev->ops->release) {
mutex_lock(&kvm->lock);
list_del_rcu(&dev->vm_node);
synchronize_rcu();
dev->ops->release(dev);
mutex_unlock(&kvm->lock);
}
kvm_put_kvm(kvm);
return 0;
}
static struct file_operations kvm_device_fops = {
.unlocked_ioctl = kvm_device_ioctl,
.release = kvm_device_release,
KVM_COMPAT(kvm_device_ioctl),
.mmap = kvm_device_mmap,
};
struct kvm_device *kvm_device_from_filp(struct file *filp)
{
if (filp->f_op != &kvm_device_fops)
return NULL;
return filp->private_data;
}
static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
#ifdef CONFIG_KVM_MPIC
[KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
[KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
#endif
};
int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type)
{
if (type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENOSPC;
if (kvm_device_ops_table[type] != NULL)
return -EEXIST;
kvm_device_ops_table[type] = ops;
return 0;
}
void kvm_unregister_device_ops(u32 type)
{
if (kvm_device_ops_table[type] != NULL)
kvm_device_ops_table[type] = NULL;
}
static int kvm_ioctl_create_device(struct kvm *kvm,
struct kvm_create_device *cd)
{
const struct kvm_device_ops *ops;
struct kvm_device *dev;
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
int type;
int ret;
if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
ops = kvm_device_ops_table[type];
if (ops == NULL)
return -ENODEV;
if (test)
return 0;
dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT);
if (!dev)
return -ENOMEM;
dev->ops = ops;
dev->kvm = kvm;
mutex_lock(&kvm->lock);
ret = ops->create(dev, type);
if (ret < 0) {
mutex_unlock(&kvm->lock);
kfree(dev);
return ret;
}
list_add_rcu(&dev->vm_node, &kvm->devices);
mutex_unlock(&kvm->lock);
if (ops->init) ops->init(dev); kvm_get_kvm(kvm);
ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
if (ret < 0) {
kvm_put_kvm_no_destroy(kvm);
mutex_lock(&kvm->lock);
list_del_rcu(&dev->vm_node);
synchronize_rcu();
if (ops->release) ops->release(dev);
mutex_unlock(&kvm->lock);
if (ops->destroy) ops->destroy(dev);
return ret;
}
cd->fd = ret;
return 0;
}
static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
{ switch (arg) {
case KVM_CAP_USER_MEMORY:
case KVM_CAP_USER_MEMORY2:
case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
case KVM_CAP_INTERNAL_ERROR_DATA:
#ifdef CONFIG_HAVE_KVM_MSI
case KVM_CAP_SIGNAL_MSI:
#endif
#ifdef CONFIG_HAVE_KVM_IRQCHIP
case KVM_CAP_IRQFD:
#endif
case KVM_CAP_IOEVENTFD_ANY_LENGTH:
case KVM_CAP_CHECK_EXTENSION_VM:
case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_HALT_POLL:
return 1;
#ifdef CONFIG_KVM_MMIO
case KVM_CAP_COALESCED_MMIO:
return KVM_COALESCED_MMIO_PAGE_OFFSET;
case KVM_CAP_COALESCED_PIO:
return 1;
#endif
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
return KVM_DIRTY_LOG_MANUAL_CAPS;
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
case KVM_CAP_IRQ_ROUTING:
return KVM_MAX_IRQ_ROUTES;
#endif
#if KVM_MAX_NR_ADDRESS_SPACES > 1
case KVM_CAP_MULTI_ADDRESS_SPACE:
if (kvm)
return kvm_arch_nr_memslot_as_ids(kvm);
return KVM_MAX_NR_ADDRESS_SPACES;
#endif
case KVM_CAP_NR_MEMSLOTS:
return KVM_USER_MEM_SLOTS;
case KVM_CAP_DIRTY_LOG_RING:
#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO
return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
#else
return 0;
#endif
case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL
return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
#else
return 0;
#endif
#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP:
#endif
case KVM_CAP_BINARY_STATS_FD:
case KVM_CAP_SYSTEM_EVENT_DATA:
case KVM_CAP_DEVICE_CTRL:
return 1;
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
case KVM_CAP_MEMORY_ATTRIBUTES:
return kvm_supported_mem_attributes(kvm);
#endif
#ifdef CONFIG_KVM_PRIVATE_MEM
case KVM_CAP_GUEST_MEMFD:
return !kvm || kvm_arch_has_private_mem(kvm);
#endif
default:
break;
}
return kvm_vm_ioctl_check_extension(kvm, arg);
}
static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
{
int r;
if (!KVM_DIRTY_LOG_PAGE_OFFSET)
return -EINVAL;
/* the size should be power of 2 */
if (!size || (size & (size - 1)))
return -EINVAL;
/* Should be bigger to keep the reserved entries, or a page */
if (size < kvm_dirty_ring_get_rsvd_entries() *
sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
return -EINVAL;
if (size > KVM_DIRTY_RING_MAX_ENTRIES *
sizeof(struct kvm_dirty_gfn))
return -E2BIG;
/* We only allow it to set once */
if (kvm->dirty_ring_size)
return -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
/* We don't allow to change this value after vcpu created */
r = -EINVAL;
} else {
kvm->dirty_ring_size = size;
r = 0;
}
mutex_unlock(&kvm->lock);
return r;
}
static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
{
unsigned long i;
struct kvm_vcpu *vcpu;
int cleared = 0;
if (!kvm->dirty_ring_size)
return -EINVAL;
mutex_lock(&kvm->slots_lock);
kvm_for_each_vcpu(i, vcpu, kvm)
cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
mutex_unlock(&kvm->slots_lock); if (cleared) kvm_flush_remote_tlbs(kvm);
return cleared;
}
int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
return -EINVAL;
}
bool kvm_are_all_memslots_empty(struct kvm *kvm)
{
int i;
lockdep_assert_held(&kvm->slots_lock);
for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
return false;
}
return true;
}
EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty);
static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
struct kvm_enable_cap *cap)
{ switch (cap->cap) {
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: {
u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE;
if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE)
allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS;
if (cap->flags || (cap->args[0] & ~allowed_options))
return -EINVAL;
kvm->manual_dirty_log_protect = cap->args[0];
return 0;
}
#endif
case KVM_CAP_HALT_POLL: {
if (cap->flags || cap->args[0] != (unsigned int)cap->args[0])
return -EINVAL;
kvm->max_halt_poll_ns = cap->args[0];
/*
* Ensure kvm->override_halt_poll_ns does not become visible
* before kvm->max_halt_poll_ns.
*
* Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns().
*/
smp_wmb();
kvm->override_halt_poll_ns = true;
return 0;
}
case KVM_CAP_DIRTY_LOG_RING:
case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap))
return -EINVAL;
return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: {
int r = -EINVAL;
if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) ||
!kvm->dirty_ring_size || cap->flags)
return r;
mutex_lock(&kvm->slots_lock);
/*
* For simplicity, allow enabling ring+bitmap if and only if
* there are no memslots, e.g. to ensure all memslots allocate
* a bitmap after the capability is enabled.
*/
if (kvm_are_all_memslots_empty(kvm)) { kvm->dirty_ring_with_bitmap = true;
r = 0;
}
mutex_unlock(&kvm->slots_lock);
return r;
}
default:
return kvm_vm_ioctl_enable_cap(kvm, cap);
}
}
static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer,
size_t size, loff_t *offset)
{
struct kvm *kvm = file->private_data;
return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header,
&kvm_vm_stats_desc[0], &kvm->stat,
sizeof(kvm->stat), user_buffer, size, offset);
}
static int kvm_vm_stats_release(struct inode *inode, struct file *file)
{
struct kvm *kvm = file->private_data;
kvm_put_kvm(kvm);
return 0;
}
static const struct file_operations kvm_vm_stats_fops = {
.owner = THIS_MODULE,
.read = kvm_vm_stats_read,
.release = kvm_vm_stats_release,
.llseek = noop_llseek,
};
static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
{
int fd;
struct file *file;
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
return fd;
file = anon_inode_getfile_fmode("kvm-vm-stats",
&kvm_vm_stats_fops, kvm, O_RDONLY, FMODE_PREAD);
if (IS_ERR(file)) {
put_unused_fd(fd);
return PTR_ERR(file);
}
kvm_get_kvm(kvm);
fd_install(fd, file);
return fd;
}
#define SANITY_CHECK_MEM_REGION_FIELD(field) \
do { \
BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \
offsetof(struct kvm_userspace_memory_region2, field)); \
BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \
sizeof_field(struct kvm_userspace_memory_region2, field)); \
} while (0)
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm *kvm = filp->private_data;
void __user *argp = (void __user *)arg;
int r;
if (kvm->mm != current->mm || kvm->vm_dead)
return -EIO;
switch (ioctl) {
case KVM_CREATE_VCPU:
r = kvm_vm_ioctl_create_vcpu(kvm, arg);
break;
case KVM_ENABLE_CAP: {
struct kvm_enable_cap cap;
r = -EFAULT;
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
break;
}
case KVM_SET_USER_MEMORY_REGION2:
case KVM_SET_USER_MEMORY_REGION: {
struct kvm_userspace_memory_region2 mem;
unsigned long size;
if (ioctl == KVM_SET_USER_MEMORY_REGION) {
/*
* Fields beyond struct kvm_userspace_memory_region shouldn't be
* accessed, but avoid leaking kernel memory in case of a bug.
*/
memset(&mem, 0, sizeof(mem));
size = sizeof(struct kvm_userspace_memory_region);
} else {
size = sizeof(struct kvm_userspace_memory_region2);
}
/* Ensure the common parts of the two structs are identical. */
SANITY_CHECK_MEM_REGION_FIELD(slot);
SANITY_CHECK_MEM_REGION_FIELD(flags);
SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
SANITY_CHECK_MEM_REGION_FIELD(memory_size);
SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
r = -EFAULT;
if (copy_from_user(&mem, argp, size))
goto out;
r = -EINVAL;
if (ioctl == KVM_SET_USER_MEMORY_REGION &&
(mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
goto out;
r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
break;
}
case KVM_GET_DIRTY_LOG: {
struct kvm_dirty_log log;
r = -EFAULT;
if (copy_from_user(&log, argp, sizeof(log)))
goto out;
r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
break;
}
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
case KVM_CLEAR_DIRTY_LOG: {
struct kvm_clear_dirty_log log;
r = -EFAULT;
if (copy_from_user(&log, argp, sizeof(log)))
goto out;
r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
break;
}
#endif
#ifdef CONFIG_KVM_MMIO
case KVM_REGISTER_COALESCED_MMIO: {
struct kvm_coalesced_mmio_zone zone;
r = -EFAULT;
if (copy_from_user(&zone, argp, sizeof(zone)))
goto out;
r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
break;
}
case KVM_UNREGISTER_COALESCED_MMIO: {
struct kvm_coalesced_mmio_zone zone;
r = -EFAULT;
if (copy_from_user(&zone, argp, sizeof(zone)))
goto out;
r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
break;
}
#endif
case KVM_IRQFD: {
struct kvm_irqfd data;
r = -EFAULT;
if (copy_from_user(&data, argp, sizeof(data)))
goto out;
r = kvm_irqfd(kvm, &data);
break;
}
case KVM_IOEVENTFD: {
struct kvm_ioeventfd data;
r = -EFAULT;
if (copy_from_user(&data, argp, sizeof(data)))
goto out;
r = kvm_ioeventfd(kvm, &data);
break;
}
#ifdef CONFIG_HAVE_KVM_MSI
case KVM_SIGNAL_MSI: {
struct kvm_msi msi;
r = -EFAULT;
if (copy_from_user(&msi, argp, sizeof(msi)))
goto out;
r = kvm_send_userspace_msi(kvm, &msi);
break;
}
#endif
#ifdef __KVM_HAVE_IRQ_LINE
case KVM_IRQ_LINE_STATUS:
case KVM_IRQ_LINE: {
struct kvm_irq_level irq_event;
r = -EFAULT;
if (copy_from_user(&irq_event, argp, sizeof(irq_event)))
goto out;
r = kvm_vm_ioctl_irq_line(kvm, &irq_event,
ioctl == KVM_IRQ_LINE_STATUS);
if (r)
goto out;
r = -EFAULT;
if (ioctl == KVM_IRQ_LINE_STATUS) { if (copy_to_user(argp, &irq_event, sizeof(irq_event)))
goto out;
}
r = 0;
break;
}
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
case KVM_SET_GSI_ROUTING: {
struct kvm_irq_routing routing;
struct kvm_irq_routing __user *urouting;
struct kvm_irq_routing_entry *entries = NULL;
r = -EFAULT;
if (copy_from_user(&routing, argp, sizeof(routing)))
goto out;
r = -EINVAL;
if (!kvm_arch_can_set_irq_routing(kvm))
goto out;
if (routing.nr > KVM_MAX_IRQ_ROUTES)
goto out;
if (routing.flags)
goto out;
if (routing.nr) {
urouting = argp;
entries = vmemdup_array_user(urouting->entries,
routing.nr, sizeof(*entries));
if (IS_ERR(entries)) { r = PTR_ERR(entries);
goto out;
}
}
r = kvm_set_irq_routing(kvm, entries, routing.nr,
routing.flags);
kvfree(entries);
break;
}
#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
case KVM_SET_MEMORY_ATTRIBUTES: {
struct kvm_memory_attributes attrs;
r = -EFAULT;
if (copy_from_user(&attrs, argp, sizeof(attrs)))
goto out;
r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
break;
}
#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
case KVM_CREATE_DEVICE: {
struct kvm_create_device cd;
r = -EFAULT;
if (copy_from_user(&cd, argp, sizeof(cd)))
goto out;
r = kvm_ioctl_create_device(kvm, &cd);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, &cd, sizeof(cd)))
goto out;
r = 0;
break;
}
case KVM_CHECK_EXTENSION:
r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
break;
case KVM_RESET_DIRTY_RINGS:
r = kvm_vm_ioctl_reset_dirty_pages(kvm);
break;
case KVM_GET_STATS_FD:
r = kvm_vm_ioctl_get_stats_fd(kvm);
break;
#ifdef CONFIG_KVM_PRIVATE_MEM
case KVM_CREATE_GUEST_MEMFD: {
struct kvm_create_guest_memfd guest_memfd;
r = -EFAULT;
if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
goto out;
r = kvm_gmem_create(kvm, &guest_memfd);
break;
}
#endif
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
out:
return r;
}
#ifdef CONFIG_KVM_COMPAT
struct compat_kvm_dirty_log {
__u32 slot;
__u32 padding1;
union {
compat_uptr_t dirty_bitmap; /* one bit per page */
__u64 padding2;
};
};
struct compat_kvm_clear_dirty_log {
__u32 slot;
__u32 num_pages;
__u64 first_page;
union {
compat_uptr_t dirty_bitmap; /* one bit per page */
__u64 padding2;
};
};
long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
return -ENOTTY;
}
static long kvm_vm_compat_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm *kvm = filp->private_data;
int r;
if (kvm->mm != current->mm || kvm->vm_dead)
return -EIO;
r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg);
if (r != -ENOTTY)
return r;
switch (ioctl) {
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
case KVM_CLEAR_DIRTY_LOG: {
struct compat_kvm_clear_dirty_log compat_log;
struct kvm_clear_dirty_log log;
if (copy_from_user(&compat_log, (void __user *)arg,
sizeof(compat_log)))
return -EFAULT;
log.slot = compat_log.slot;
log.num_pages = compat_log.num_pages;
log.first_page = compat_log.first_page;
log.padding2 = compat_log.padding2;
log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
break;
}
#endif
case KVM_GET_DIRTY_LOG: {
struct compat_kvm_dirty_log compat_log;
struct kvm_dirty_log log;
if (copy_from_user(&compat_log, (void __user *)arg,
sizeof(compat_log)))
return -EFAULT;
log.slot = compat_log.slot;
log.padding1 = compat_log.padding1;
log.padding2 = compat_log.padding2;
log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
break;
}
default:
r = kvm_vm_ioctl(filp, ioctl, arg);
}
return r;
}
#endif
static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
.llseek = noop_llseek,
KVM_COMPAT(kvm_vm_compat_ioctl),
};
bool file_is_kvm(struct file *file)
{
return file && file->f_op == &kvm_vm_fops;
}
EXPORT_SYMBOL_GPL(file_is_kvm);
static int kvm_dev_ioctl_create_vm(unsigned long type)
{
char fdname[ITOA_MAX_LEN + 1];
int r, fd;
struct kvm *kvm;
struct file *file;
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
return fd;
snprintf(fdname, sizeof(fdname), "%d", fd);
kvm = kvm_create_vm(type, fdname); if (IS_ERR(kvm)) {
r = PTR_ERR(kvm);
goto put_fd;
}
file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
if (IS_ERR(file)) {
r = PTR_ERR(file);
goto put_kvm;
}
/*
* Don't call kvm_put_kvm anymore at this point; file->f_op is
* already set, with ->release() being kvm_vm_release(). In error
* cases it will be called by the final fput(file) and will take
* care of doing kvm_put_kvm(kvm).
*/
kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm);
fd_install(fd, file);
return fd;
put_kvm:
kvm_put_kvm(kvm);
put_fd:
put_unused_fd(fd);
return r;
}
static long kvm_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
int r = -EINVAL;
switch (ioctl) {
case KVM_GET_API_VERSION:
if (arg)
goto out;
r = KVM_API_VERSION;
break;
case KVM_CREATE_VM:
r = kvm_dev_ioctl_create_vm(arg);
break;
case KVM_CHECK_EXTENSION:
r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
break;
case KVM_GET_VCPU_MMAP_SIZE:
if (arg)
goto out;
r = PAGE_SIZE; /* struct kvm_run */
#ifdef CONFIG_X86
r += PAGE_SIZE; /* pio data page */
#endif
#ifdef CONFIG_KVM_MMIO
r += PAGE_SIZE; /* coalesced mmio ring page */
#endif
break;
default:
return kvm_arch_dev_ioctl(filp, ioctl, arg);
}
out:
return r;
}
static struct file_operations kvm_chardev_ops = {
.unlocked_ioctl = kvm_dev_ioctl,
.llseek = noop_llseek,
KVM_COMPAT(kvm_dev_ioctl),
};
static struct miscdevice kvm_dev = {
KVM_MINOR,
"kvm",
&kvm_chardev_ops,
};
#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
static bool enable_virt_at_load = true;
module_param(enable_virt_at_load, bool, 0444);
__visible bool kvm_rebooting;
EXPORT_SYMBOL_GPL(kvm_rebooting);
static DEFINE_PER_CPU(bool, virtualization_enabled);
static DEFINE_MUTEX(kvm_usage_lock);
static int kvm_usage_count;
__weak void kvm_arch_enable_virtualization(void)
{
}
__weak void kvm_arch_disable_virtualization(void)
{
}
static int kvm_enable_virtualization_cpu(void)
{
if (__this_cpu_read(virtualization_enabled))
return 0;
if (kvm_arch_enable_virtualization_cpu()) {
pr_info("kvm: enabling virtualization on CPU%d failed\n",
raw_smp_processor_id());
return -EIO;
}
__this_cpu_write(virtualization_enabled, true);
return 0;
}
static int kvm_online_cpu(unsigned int cpu)
{
/*
* Abort the CPU online process if hardware virtualization cannot
* be enabled. Otherwise running VMs would encounter unrecoverable
* errors when scheduled to this CPU.
*/
return kvm_enable_virtualization_cpu();
}
static void kvm_disable_virtualization_cpu(void *ign)
{
if (!__this_cpu_read(virtualization_enabled))
return;
kvm_arch_disable_virtualization_cpu();
__this_cpu_write(virtualization_enabled, false);
}
static int kvm_offline_cpu(unsigned int cpu)
{
kvm_disable_virtualization_cpu(NULL);
return 0;
}
static void kvm_shutdown(void)
{
/*
* Disable hardware virtualization and set kvm_rebooting to indicate
* that KVM has asynchronously disabled hardware virtualization, i.e.
* that relevant errors and exceptions aren't entirely unexpected.
* Some flavors of hardware virtualization need to be disabled before
* transferring control to firmware (to perform shutdown/reboot), e.g.
* on x86, virtualization can block INIT interrupts, which are used by
* firmware to pull APs back under firmware control. Note, this path
* is used for both shutdown and reboot scenarios, i.e. neither name is
* 100% comprehensive.
*/
pr_info("kvm: exiting hardware virtualization\n");
kvm_rebooting = true;
on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1);
}
static int kvm_suspend(void)
{
/*
* Secondary CPUs and CPU hotplug are disabled across the suspend/resume
* callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage
* count is stable. Assert that kvm_usage_lock is not held to ensure
* the system isn't suspended while KVM is enabling hardware. Hardware
* enabling can be preempted, but the task cannot be frozen until it has
* dropped all locks (userspace tasks are frozen via a fake signal).
*/
lockdep_assert_not_held(&kvm_usage_lock);
lockdep_assert_irqs_disabled();
kvm_disable_virtualization_cpu(NULL);
return 0;
}
static void kvm_resume(void)
{
lockdep_assert_not_held(&kvm_usage_lock);
lockdep_assert_irqs_disabled();
WARN_ON_ONCE(kvm_enable_virtualization_cpu());
}
static struct syscore_ops kvm_syscore_ops = {
.suspend = kvm_suspend,
.resume = kvm_resume,
.shutdown = kvm_shutdown,
};
static int kvm_enable_virtualization(void)
{
int r;
guard(mutex)(&kvm_usage_lock);
if (kvm_usage_count++)
return 0;
kvm_arch_enable_virtualization();
r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online",
kvm_online_cpu, kvm_offline_cpu);
if (r)
goto err_cpuhp;
register_syscore_ops(&kvm_syscore_ops);
/*
* Undo virtualization enabling and bail if the system is going down.
* If userspace initiated a forced reboot, e.g. reboot -f, then it's
* possible for an in-flight operation to enable virtualization after
* syscore_shutdown() is called, i.e. without kvm_shutdown() being
* invoked. Note, this relies on system_state being set _before_
* kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked
* or this CPU observes the impending shutdown. Which is why KVM uses
* a syscore ops hook instead of registering a dedicated reboot
* notifier (the latter runs before system_state is updated).
*/
if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF ||
system_state == SYSTEM_RESTART) {
r = -EBUSY;
goto err_rebooting;
}
return 0;
err_rebooting:
unregister_syscore_ops(&kvm_syscore_ops);
cpuhp_remove_state(CPUHP_AP_KVM_ONLINE);
err_cpuhp:
kvm_arch_disable_virtualization();
--kvm_usage_count;
return r;
}
static void kvm_disable_virtualization(void)
{
guard(mutex)(&kvm_usage_lock);
if (--kvm_usage_count)
return;
unregister_syscore_ops(&kvm_syscore_ops);
cpuhp_remove_state(CPUHP_AP_KVM_ONLINE);
kvm_arch_disable_virtualization();
}
static int kvm_init_virtualization(void)
{
if (enable_virt_at_load)
return kvm_enable_virtualization();
return 0;
}
static void kvm_uninit_virtualization(void)
{
if (enable_virt_at_load)
kvm_disable_virtualization();
}
#else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
static int kvm_enable_virtualization(void)
{
return 0;
}
static int kvm_init_virtualization(void)
{
return 0;
}
static void kvm_disable_virtualization(void)
{
}
static void kvm_uninit_virtualization(void)
{
}
#endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
static void kvm_iodevice_destructor(struct kvm_io_device *dev)
{
if (dev->ops->destructor) dev->ops->destructor(dev);
}
static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
{
int i;
for (i = 0; i < bus->dev_count; i++) {
struct kvm_io_device *pos = bus->range[i].dev;
kvm_iodevice_destructor(pos);
}
kfree(bus);
}
static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
const struct kvm_io_range *r2)
{
gpa_t addr1 = r1->addr;
gpa_t addr2 = r2->addr;
if (addr1 < addr2)
return -1;
/* If r2->len == 0, match the exact address. If r2->len != 0,
* accept any overlapping write. Any order is acceptable for
* overlapping ranges, because kvm_io_bus_get_first_dev ensures
* we process all of them.
*/
if (r2->len) { addr1 += r1->len;
addr2 += r2->len;
}
if (addr1 > addr2)
return 1;
return 0;
}
static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
{ return kvm_io_bus_cmp(p1, p2);
}
static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
gpa_t addr, int len)
{
struct kvm_io_range *range, key;
int off;
key = (struct kvm_io_range) {
.addr = addr,
.len = len,
};
range = bsearch(&key, bus->range, bus->dev_count,
sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp);
if (range == NULL)
return -ENOENT;
off = range - bus->range;
while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0)
off--;
return off;
}
static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
struct kvm_io_range *range, const void *val)
{
int idx;
idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0)
return -EOPNOTSUPP;
while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr,
range->len, val))
return idx;
idx++;
}
return -EOPNOTSUPP;
}
/* kvm_io_bus_write - called under kvm->slots_lock */
int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, const void *val)
{
struct kvm_io_bus *bus;
struct kvm_io_range range;
int r;
range = (struct kvm_io_range) {
.addr = addr,
.len = len,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus)
return -ENOMEM;
r = __kvm_io_bus_write(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
EXPORT_SYMBOL_GPL(kvm_io_bus_write);
/* kvm_io_bus_write_cookie - called under kvm->slots_lock */
int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
gpa_t addr, int len, const void *val, long cookie)
{
struct kvm_io_bus *bus;
struct kvm_io_range range;
range = (struct kvm_io_range) {
.addr = addr,
.len = len,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
if (!bus)
return -ENOMEM;
/* First try the device referenced by cookie. */
if ((cookie >= 0) && (cookie < bus->dev_count) &&
(kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len,
val))
return cookie;
/*
* cookie contained garbage; fall back to search and return the
* correct cookie value.
*/
return __kvm_io_bus_write(vcpu, bus, &range, val);
}
static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus,
struct kvm_io_range *range, void *val)
{
int idx;
idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0)
return -EOPNOTSUPP;
while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr,
range->len, val))
return idx;
idx++;
}
return -EOPNOTSUPP;
}
/* kvm_io_bus_read - called under kvm->slots_lock */
int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val)
{
struct kvm_io_bus *bus;
struct kvm_io_range range;
int r;
range = (struct kvm_io_range) {
.addr = addr,
.len = len,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus)
return -ENOMEM;
r = __kvm_io_bus_read(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, struct kvm_io_device *dev)
{
int i;
struct kvm_io_bus *new_bus, *bus;
struct kvm_io_range range;
lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus)
return -ENOMEM;
/* exclude ioeventfd which is limited by maximum fd */
if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
return -ENOSPC;
new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1),
GFP_KERNEL_ACCOUNT);
if (!new_bus)
return -ENOMEM;
range = (struct kvm_io_range) {
.addr = addr,
.len = len,
.dev = dev,
};
for (i = 0; i < bus->dev_count; i++) if (kvm_io_bus_cmp(&bus->range[i], &range) > 0)
break;
memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
new_bus->dev_count++;
new_bus->range[i] = range;
memcpy(new_bus->range + i + 1, bus->range + i,
(bus->dev_count - i) * sizeof(struct kvm_io_range));
rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
synchronize_srcu_expedited(&kvm->srcu);
kfree(bus);
return 0;
}
int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
struct kvm_io_device *dev)
{
int i;
struct kvm_io_bus *new_bus, *bus;
lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus)
return 0;
for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) {
break;
}
}
if (i == bus->dev_count)
return 0;
new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
GFP_KERNEL_ACCOUNT);
if (new_bus) {
memcpy(new_bus, bus, struct_size(bus, range, i));
new_bus->dev_count--;
memcpy(new_bus->range + i, bus->range + i + 1,
flex_array_size(new_bus, range, new_bus->dev_count - i));
}
rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
synchronize_srcu_expedited(&kvm->srcu);
/*
* If NULL bus is installed, destroy the old bus, including all the
* attached devices. Otherwise, destroy the caller's device only.
*/
if (!new_bus) {
pr_err("kvm: failed to shrink bus, removing it completely\n");
kvm_io_bus_destroy(bus);
return -ENOMEM;
}
kvm_iodevice_destructor(dev);
kfree(bus);
return 0;
}
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr)
{
struct kvm_io_bus *bus;
int dev_idx, srcu_idx;
struct kvm_io_device *iodev = NULL;
srcu_idx = srcu_read_lock(&kvm->srcu);
bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); if (!bus)
goto out_unlock;
dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0)
goto out_unlock;
iodev = bus->range[dev_idx].dev;
out_unlock:
srcu_read_unlock(&kvm->srcu, srcu_idx);
return iodev;
}
EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev);
static int kvm_debugfs_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt)
{
int ret;
struct kvm_stat_data *stat_data = inode->i_private;
/*
* The debugfs files are a reference to the kvm struct which
* is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe
* avoids the race between open and the removal of the debugfs directory.
*/
if (!kvm_get_kvm_safe(stat_data->kvm))
return -ENOENT;
ret = simple_attr_open(inode, file, get,
kvm_stats_debugfs_mode(stat_data->desc) & 0222
? set : NULL, fmt);
if (ret)
kvm_put_kvm(stat_data->kvm);
return ret;
}
static int kvm_debugfs_release(struct inode *inode, struct file *file)
{
struct kvm_stat_data *stat_data = inode->i_private;
simple_attr_release(inode, file);
kvm_put_kvm(stat_data->kvm);
return 0;
}
static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val)
{
*val = *(u64 *)((void *)(&kvm->stat) + offset);
return 0;
}
static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
{
*(u64 *)((void *)(&kvm->stat) + offset) = 0;
return 0;
}
static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val)
{
unsigned long i;
struct kvm_vcpu *vcpu;
*val = 0;
kvm_for_each_vcpu(i, vcpu, kvm)
*val += *(u64 *)((void *)(&vcpu->stat) + offset);
return 0;
}
static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset)
{
unsigned long i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
*(u64 *)((void *)(&vcpu->stat) + offset) = 0;
return 0;
}
static int kvm_stat_data_get(void *data, u64 *val)
{
int r = -EFAULT;
struct kvm_stat_data *stat_data = data;
switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_get_stat_per_vm(stat_data->kvm,
stat_data->desc->desc.offset, val);
break;
case KVM_STAT_VCPU:
r = kvm_get_stat_per_vcpu(stat_data->kvm,
stat_data->desc->desc.offset, val);
break;
}
return r;
}
static int kvm_stat_data_clear(void *data, u64 val)
{
int r = -EFAULT;
struct kvm_stat_data *stat_data = data;
if (val)
return -EINVAL;
switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_clear_stat_per_vm(stat_data->kvm,
stat_data->desc->desc.offset);
break;
case KVM_STAT_VCPU:
r = kvm_clear_stat_per_vcpu(stat_data->kvm,
stat_data->desc->desc.offset);
break;
}
return r;
}
static int kvm_stat_data_open(struct inode *inode, struct file *file)
{
__simple_attr_check_format("%llu\n", 0ull);
return kvm_debugfs_open(inode, file, kvm_stat_data_get,
kvm_stat_data_clear, "%llu\n");
}
static const struct file_operations stat_fops_per_vm = {
.owner = THIS_MODULE,
.open = kvm_stat_data_open,
.release = kvm_debugfs_release,
.read = simple_attr_read,
.write = simple_attr_write,
};
static int vm_stat_get(void *_offset, u64 *val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
u64 tmp_val;
*val = 0;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_get_stat_per_vm(kvm, offset, &tmp_val);
*val += tmp_val;
}
mutex_unlock(&kvm_lock);
return 0;
}
static int vm_stat_clear(void *_offset, u64 val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
if (val)
return -EINVAL;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_clear_stat_per_vm(kvm, offset);
}
mutex_unlock(&kvm_lock);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n");
static int vcpu_stat_get(void *_offset, u64 *val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
u64 tmp_val;
*val = 0;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_get_stat_per_vcpu(kvm, offset, &tmp_val);
*val += tmp_val;
}
mutex_unlock(&kvm_lock);
return 0;
}
static int vcpu_stat_clear(void *_offset, u64 val)
{
unsigned offset = (long)_offset;
struct kvm *kvm;
if (val)
return -EINVAL;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_clear_stat_per_vcpu(kvm, offset);
}
mutex_unlock(&kvm_lock);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
"%llu\n");
DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n");
static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
{
struct kobj_uevent_env *env;
unsigned long long created, active;
if (!kvm_dev.this_device || !kvm)
return;
mutex_lock(&kvm_lock);
if (type == KVM_EVENT_CREATE_VM) { kvm_createvm_count++;
kvm_active_vms++;
} else if (type == KVM_EVENT_DESTROY_VM) {
kvm_active_vms--;
}
created = kvm_createvm_count;
active = kvm_active_vms;
mutex_unlock(&kvm_lock);
env = kzalloc(sizeof(*env), GFP_KERNEL);
if (!env)
return;
add_uevent_var(env, "CREATED=%llu", created);
add_uevent_var(env, "COUNT=%llu", active);
if (type == KVM_EVENT_CREATE_VM) {
add_uevent_var(env, "EVENT=create");
kvm->userspace_pid = task_pid_nr(current);
} else if (type == KVM_EVENT_DESTROY_VM) {
add_uevent_var(env, "EVENT=destroy");
}
add_uevent_var(env, "PID=%d", kvm->userspace_pid);
if (!IS_ERR(kvm->debugfs_dentry)) {
char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
if (p) {
tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);
if (!IS_ERR(tmp)) add_uevent_var(env, "STATS_PATH=%s", tmp);
kfree(p);
}
}
/* no need for checks, since we are adding at most only 5 keys */
env->envp[env->envp_idx++] = NULL;
kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp);
kfree(env);
}
static void kvm_init_debug(void)
{
const struct file_operations *fops;
const struct _kvm_stats_desc *pdesc;
int i;
kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
pdesc = &kvm_vm_stats_desc[i];
if (kvm_stats_debugfs_mode(pdesc) & 0222)
fops = &vm_stat_fops;
else
fops = &vm_stat_readonly_fops;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm_debugfs_dir,
(void *)(long)pdesc->desc.offset, fops);
}
for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
pdesc = &kvm_vcpu_stats_desc[i];
if (kvm_stats_debugfs_mode(pdesc) & 0222)
fops = &vcpu_stat_fops;
else
fops = &vcpu_stat_readonly_fops;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm_debugfs_dir,
(void *)(long)pdesc->desc.offset, fops);
}
}
static inline
struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
{
return container_of(pn, struct kvm_vcpu, preempt_notifier);
}
static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
{
struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
WRITE_ONCE(vcpu->preempted, false);
WRITE_ONCE(vcpu->ready, false);
__this_cpu_write(kvm_running_vcpu, vcpu);
kvm_arch_vcpu_load(vcpu, cpu);
WRITE_ONCE(vcpu->scheduled_out, false);
}
static void kvm_sched_out(struct preempt_notifier *pn,
struct task_struct *next)
{
struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
WRITE_ONCE(vcpu->scheduled_out, true);
if (task_is_runnable(current) && vcpu->wants_to_run) {
WRITE_ONCE(vcpu->preempted, true);
WRITE_ONCE(vcpu->ready, true);
}
kvm_arch_vcpu_put(vcpu);
__this_cpu_write(kvm_running_vcpu, NULL);
}
/**
* kvm_get_running_vcpu - get the vcpu running on the current CPU.
*
* We can disable preemption locally around accessing the per-CPU variable,
* and use the resolved vcpu pointer after enabling preemption again,
* because even if the current thread is migrated to another CPU, reading
* the per-CPU value later will give us the same value as we update the
* per-CPU variable in the preempt notifier handlers.
*/
struct kvm_vcpu *kvm_get_running_vcpu(void)
{
struct kvm_vcpu *vcpu;
preempt_disable();
vcpu = __this_cpu_read(kvm_running_vcpu);
preempt_enable();
return vcpu;
}
EXPORT_SYMBOL_GPL(kvm_get_running_vcpu);
/**
* kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.
*/
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
{
return &kvm_running_vcpu;
}
#ifdef CONFIG_GUEST_PERF_EVENTS
static unsigned int kvm_guest_state(void)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
unsigned int state;
if (!kvm_arch_pmi_in_guest(vcpu))
return 0;
state = PERF_GUEST_ACTIVE;
if (!kvm_arch_vcpu_in_kernel(vcpu))
state |= PERF_GUEST_USER;
return state;
}
static unsigned long kvm_guest_get_ip(void)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
/* Retrieving the IP must be guarded by a call to kvm_guest_state(). */
if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)))
return 0;
return kvm_arch_vcpu_get_ip(vcpu);
}
static struct perf_guest_info_callbacks kvm_guest_cbs = {
.state = kvm_guest_state,
.get_ip = kvm_guest_get_ip,
.handle_intel_pt_intr = NULL,
};
void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void))
{
kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler;
perf_register_guest_info_callbacks(&kvm_guest_cbs);
}
void kvm_unregister_perf_callbacks(void)
{
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
}
#endif
int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
{
int r;
int cpu;
/* A kmem cache lets us meet the alignment requirements of fx_save. */
if (!vcpu_align)
vcpu_align = __alignof__(struct kvm_vcpu);
kvm_vcpu_cache =
kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
SLAB_ACCOUNT,
offsetof(struct kvm_vcpu, arch),
offsetofend(struct kvm_vcpu, stats_id)
- offsetof(struct kvm_vcpu, arch),
NULL);
if (!kvm_vcpu_cache)
return -ENOMEM;
for_each_possible_cpu(cpu) {
if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu))) {
r = -ENOMEM;
goto err_cpu_kick_mask;
}
}
r = kvm_irqfd_init();
if (r)
goto err_irqfd;
r = kvm_async_pf_init();
if (r)
goto err_async_pf;
kvm_chardev_ops.owner = module;
kvm_vm_fops.owner = module;
kvm_vcpu_fops.owner = module;
kvm_device_fops.owner = module;
kvm_preempt_ops.sched_in = kvm_sched_in;
kvm_preempt_ops.sched_out = kvm_sched_out;
kvm_init_debug();
r = kvm_vfio_ops_init();
if (WARN_ON_ONCE(r))
goto err_vfio;
kvm_gmem_init(module);
r = kvm_init_virtualization();
if (r)
goto err_virt;
/*
* Registration _must_ be the very last thing done, as this exposes
* /dev/kvm to userspace, i.e. all infrastructure must be setup!
*/
r = misc_register(&kvm_dev);
if (r) {
pr_err("kvm: misc device register failed\n");
goto err_register;
}
return 0;
err_register:
kvm_uninit_virtualization();
err_virt:
kvm_vfio_ops_exit();
err_vfio:
kvm_async_pf_deinit();
err_async_pf:
kvm_irqfd_exit();
err_irqfd:
err_cpu_kick_mask:
for_each_possible_cpu(cpu)
free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
kmem_cache_destroy(kvm_vcpu_cache);
return r;
}
EXPORT_SYMBOL_GPL(kvm_init);
void kvm_exit(void)
{
int cpu;
/*
* Note, unregistering /dev/kvm doesn't strictly need to come first,
* fops_get(), a.k.a. try_module_get(), prevents acquiring references
* to KVM while the module is being stopped.
*/
misc_deregister(&kvm_dev);
kvm_uninit_virtualization();
debugfs_remove_recursive(kvm_debugfs_dir);
for_each_possible_cpu(cpu)
free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
kmem_cache_destroy(kvm_vcpu_cache);
kvm_vfio_ops_exit();
kvm_async_pf_deinit();
kvm_irqfd_exit();
}
EXPORT_SYMBOL_GPL(kvm_exit);
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/fs-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
*
* Contains all the functions related to writing back and waiting
* upon dirty inodes against superblocks, and writing back dirty
* pages against inodes. ie: data writeback. Writeout of the
* inode itself is not handled here.
*
* 10Apr2002 Andrew Morton
* Split out of fs/inode.c
* Additions for address_space-based writeback
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/tracepoint.h>
#include <linux/device.h>
#include <linux/memcontrol.h>
#include "internal.h"
/*
* 4MB minimal write chunk size
*/
#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10))
/*
* Passed into wb_writeback(), essentially a subset of writeback_control
*/
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
unsigned int auto_free:1; /* free on completion */
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
struct wb_completion *done; /* set if the caller waits */
};
/*
* If an inode is constantly having its pages dirtied, but then the
* updates stop dirtytime_expire_interval seconds in the past, it's
* possible for the worst case time between when an inode has its
* timestamps updated and when they finally get written out to be two
* dirtytime_expire_intervals. We set the default to 12 hours (in
* seconds), which means most of the time inodes will have their
* timestamps written to disk after 12 hours, but in the worst case a
* few inodes might not their timestamps updated for 24 hours.
*/
static unsigned int dirtytime_expire_interval = 12 * 60 * 60;
static inline struct inode *wb_inode(struct list_head *head)
{
return list_entry(head, struct inode, i_io_list);
}
/*
* Include the creation of the trace points after defining the
* wb_writeback_work structure and inline functions so that the definition
* remains local to this file.
*/
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
static bool wb_io_lists_populated(struct bdi_writeback *wb)
{
if (wb_has_dirty_io(wb)) {
return false;
} else {
set_bit(WB_has_dirty_io, &wb->state);
WARN_ON_ONCE(!wb->avg_write_bandwidth);
atomic_long_add(wb->avg_write_bandwidth,
&wb->bdi->tot_write_bandwidth);
return true;
}
}
static void wb_io_lists_depopulated(struct bdi_writeback *wb)
{
if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) {
clear_bit(WB_has_dirty_io, &wb->state);
WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth,
&wb->bdi->tot_write_bandwidth) < 0);
}
}
/**
* inode_io_list_move_locked - move an inode onto a bdi_writeback IO list
* @inode: inode to be moved
* @wb: target bdi_writeback
* @head: one of @wb->b_{dirty|io|more_io|dirty_time}
*
* Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io.
* Returns %true if @inode is the first occupant of the !dirty_time IO
* lists; otherwise, %false.
*/
static bool inode_io_list_move_locked(struct inode *inode,
struct bdi_writeback *wb,
struct list_head *head)
{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
WARN_ON_ONCE(inode->i_state & I_FREEING);
list_move(&inode->i_io_list, head);
/* dirty_time doesn't count as dirty_io until expiration */
if (head != &wb->b_dirty_time)
return wb_io_lists_populated(wb);
wb_io_lists_depopulated(wb);
return false;
}
static void wb_wakeup(struct bdi_writeback *wb)
{
spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state))
mod_delayed_work(bdi_wq, &wb->dwork, 0);
spin_unlock_irq(&wb->work_lock);
}
/*
* This function is used when the first inode for this wb is marked dirty. It
* wakes-up the corresponding bdi thread which should then take care of the
* periodic background write-out of dirty inodes. Since the write-out would
* starts only 'dirty_writeback_interval' centisecs from now anyway, we just
* set up a timer which wakes the bdi thread up later.
*
* Note, we wouldn't bother setting up the timer, but this function is on the
* fast-path (used by '__mark_inode_dirty()'), so we save few context switches
* by delaying the wake-up.
*
* We have to be careful not to postpone flush work if it is scheduled for
* earlier. Thus we use queue_delayed_work().
*/
static void wb_wakeup_delayed(struct bdi_writeback *wb)
{
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state))
queue_delayed_work(bdi_wq, &wb->dwork, timeout);
spin_unlock_irq(&wb->work_lock);
}
static void finish_writeback_work(struct wb_writeback_work *work)
{
struct wb_completion *done = work->done;
if (work->auto_free)
kfree(work);
if (done) {
wait_queue_head_t *waitq = done->waitq;
/* @done can't be accessed after the following dec */
if (atomic_dec_and_test(&done->cnt))
wake_up_all(waitq);
}
}
static void wb_queue_work(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
trace_writeback_queue(wb, work);
if (work->done)
atomic_inc(&work->done->cnt);
spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state)) {
list_add_tail(&work->list, &wb->work_list);
mod_delayed_work(bdi_wq, &wb->dwork, 0);
} else
finish_writeback_work(work);
spin_unlock_irq(&wb->work_lock);
}
/**
* wb_wait_for_completion - wait for completion of bdi_writeback_works
* @done: target wb_completion
*
* Wait for one or more work items issued to @bdi with their ->done field
* set to @done, which should have been initialized with
* DEFINE_WB_COMPLETION(). This function returns after all such work items
* are completed. Work items which are waited upon aren't freed
* automatically on completion.
*/
void wb_wait_for_completion(struct wb_completion *done)
{
atomic_dec(&done->cnt); /* put down the initial count */
wait_event(*done->waitq, !atomic_read(&done->cnt));
}
#ifdef CONFIG_CGROUP_WRITEBACK
/*
* Parameters for foreign inode detection, see wbc_detach_inode() to see
* how they're used.
*
* These paramters are inherently heuristical as the detection target
* itself is fuzzy. All we want to do is detaching an inode from the
* current owner if it's being written to by some other cgroups too much.
*
* The current cgroup writeback is built on the assumption that multiple
* cgroups writing to the same inode concurrently is very rare and a mode
* of operation which isn't well supported. As such, the goal is not
* taking too long when a different cgroup takes over an inode while
* avoiding too aggressive flip-flops from occasional foreign writes.
*
* We record, very roughly, 2s worth of IO time history and if more than
* half of that is foreign, trigger the switch. The recording is quantized
* to 16 slots. To avoid tiny writes from swinging the decision too much,
* writes smaller than 1/8 of avg size are ignored.
*/
#define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */
#define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */
#define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */
#define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */
#define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */
#define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS)
/* each slot's duration is 2s / 16 */
#define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2)
/* if foreign slots >= 8, switch */
#define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1)
/* one round can affect upto 5 slots */
#define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */
/*
* Maximum inodes per isw. A specific value has been chosen to make
* struct inode_switch_wbs_context fit into 1024 bytes kmalloc.
*/
#define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \
/ sizeof(struct inode *))
static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
static struct workqueue_struct *isw_wq;
void __inode_attach_wb(struct inode *inode, struct folio *folio)
{
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct bdi_writeback *wb = NULL;
if (inode_cgwb_enabled(inode)) {
struct cgroup_subsys_state *memcg_css;
if (folio) {
memcg_css = mem_cgroup_css_from_folio(folio);
wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
} else {
/* must pin memcg_css, see wb_get_create() */
memcg_css = task_get_css(current, memory_cgrp_id);
wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
css_put(memcg_css);
}
}
if (!wb)
wb = &bdi->wb;
/*
* There may be multiple instances of this function racing to
* update the same inode. Use cmpxchg() to tell the winner.
*/
if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb);
}
/**
* inode_cgwb_move_to_attached - put the inode onto wb->b_attached list
* @inode: inode of interest with i_lock held
* @wb: target bdi_writeback
*
* Remove the inode from wb's io lists and if necessarily put onto b_attached
* list. Only inodes attached to cgwb's are kept on this list.
*/
static void inode_cgwb_move_to_attached(struct inode *inode,
struct bdi_writeback *wb)
{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
WARN_ON_ONCE(inode->i_state & I_FREEING);
inode->i_state &= ~I_SYNC_QUEUED;
if (wb != &wb->bdi->wb)
list_move(&inode->i_io_list, &wb->b_attached);
else
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
}
/**
* locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it
* @inode: inode of interest with i_lock held
*
* Returns @inode's wb with its list_lock held. @inode->i_lock must be
* held on entry and is released on return. The returned wb is guaranteed
* to stay @inode's associated wb until its list_lock is released.
*/
static struct bdi_writeback *
locked_inode_to_wb_and_lock_list(struct inode *inode)
__releases(&inode->i_lock)
__acquires(&wb->list_lock)
{
while (true) {
struct bdi_writeback *wb = inode_to_wb(inode);
/*
* inode_to_wb() association is protected by both
* @inode->i_lock and @wb->list_lock but list_lock nests
* outside i_lock. Drop i_lock and verify that the
* association hasn't changed after acquiring list_lock.
*/
wb_get(wb);
spin_unlock(&inode->i_lock);
spin_lock(&wb->list_lock);
/* i_wb may have changed inbetween, can't use inode_to_wb() */
if (likely(wb == inode->i_wb)) {
wb_put(wb); /* @inode already has ref */
return wb;
}
spin_unlock(&wb->list_lock);
wb_put(wb);
cpu_relax();
spin_lock(&inode->i_lock);
}
}
/**
* inode_to_wb_and_lock_list - determine an inode's wb and lock it
* @inode: inode of interest
*
* Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held
* on entry.
*/
static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode)
__acquires(&wb->list_lock)
{
spin_lock(&inode->i_lock);
return locked_inode_to_wb_and_lock_list(inode);
}
struct inode_switch_wbs_context {
struct rcu_work work;
/*
* Multiple inodes can be switched at once. The switching procedure
* consists of two parts, separated by a RCU grace period. To make
* sure that the second part is executed for each inode gone through
* the first part, all inode pointers are placed into a NULL-terminated
* array embedded into struct inode_switch_wbs_context. Otherwise
* an inode could be left in a non-consistent state.
*/
struct bdi_writeback *new_wb;
struct inode *inodes[];
};
static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi)
{
down_write(&bdi->wb_switch_rwsem);
}
static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi)
{
up_write(&bdi->wb_switch_rwsem);
}
static bool inode_do_switch_wbs(struct inode *inode,
struct bdi_writeback *old_wb,
struct bdi_writeback *new_wb)
{
struct address_space *mapping = inode->i_mapping;
XA_STATE(xas, &mapping->i_pages, 0);
struct folio *folio;
bool switched = false;
spin_lock(&inode->i_lock);
xa_lock_irq(&mapping->i_pages);
/*
* Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction
* path owns the inode and we shouldn't modify ->i_io_list.
*/
if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE)))
goto skip_switch;
trace_inode_switch_wbs(inode, old_wb, new_wb);
/*
* Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points
* to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to
* folios actually under writeback.
*/
xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) {
if (folio_test_dirty(folio)) {
long nr = folio_nr_pages(folio);
wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr);
wb_stat_mod(new_wb, WB_RECLAIMABLE, nr);
}
}
xas_set(&xas, 0);
xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) {
long nr = folio_nr_pages(folio);
WARN_ON_ONCE(!folio_test_writeback(folio));
wb_stat_mod(old_wb, WB_WRITEBACK, -nr);
wb_stat_mod(new_wb, WB_WRITEBACK, nr);
}
if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
atomic_dec(&old_wb->writeback_inodes);
atomic_inc(&new_wb->writeback_inodes);
}
wb_get(new_wb);
/*
* Transfer to @new_wb's IO list if necessary. If the @inode is dirty,
* the specific list @inode was on is ignored and the @inode is put on
* ->b_dirty which is always correct including from ->b_dirty_time.
* The transfer preserves @inode->dirtied_when ordering. If the @inode
* was clean, it means it was on the b_attached list, so move it onto
* the b_attached list of @new_wb.
*/
if (!list_empty(&inode->i_io_list)) {
inode->i_wb = new_wb;
if (inode->i_state & I_DIRTY_ALL) {
struct inode *pos;
list_for_each_entry(pos, &new_wb->b_dirty, i_io_list)
if (time_after_eq(inode->dirtied_when,
pos->dirtied_when))
break;
inode_io_list_move_locked(inode, new_wb,
pos->i_io_list.prev);
} else {
inode_cgwb_move_to_attached(inode, new_wb);
}
} else {
inode->i_wb = new_wb;
}
/* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */
inode->i_wb_frn_winner = 0;
inode->i_wb_frn_avg_time = 0;
inode->i_wb_frn_history = 0;
switched = true;
skip_switch:
/*
* Paired with load_acquire in unlocked_inode_to_wb_begin() and
* ensures that the new wb is visible if they see !I_WB_SWITCH.
*/
smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH);
xa_unlock_irq(&mapping->i_pages);
spin_unlock(&inode->i_lock);
return switched;
}
static void inode_switch_wbs_work_fn(struct work_struct *work)
{
struct inode_switch_wbs_context *isw =
container_of(to_rcu_work(work), struct inode_switch_wbs_context, work);
struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]);
struct bdi_writeback *old_wb = isw->inodes[0]->i_wb;
struct bdi_writeback *new_wb = isw->new_wb;
unsigned long nr_switched = 0;
struct inode **inodep;
/*
* If @inode switches cgwb membership while sync_inodes_sb() is
* being issued, sync_inodes_sb() might miss it. Synchronize.
*/
down_read(&bdi->wb_switch_rwsem);
/*
* By the time control reaches here, RCU grace period has passed
* since I_WB_SWITCH assertion and all wb stat update transactions
* between unlocked_inode_to_wb_begin/end() are guaranteed to be
* synchronizing against the i_pages lock.
*
* Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock
* gives us exclusion against all wb related operations on @inode
* including IO list manipulations and stat updates.
*/
if (old_wb < new_wb) {
spin_lock(&old_wb->list_lock);
spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING);
} else {
spin_lock(&new_wb->list_lock);
spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING);
}
for (inodep = isw->inodes; *inodep; inodep++) {
WARN_ON_ONCE((*inodep)->i_wb != old_wb);
if (inode_do_switch_wbs(*inodep, old_wb, new_wb))
nr_switched++;
}
spin_unlock(&new_wb->list_lock);
spin_unlock(&old_wb->list_lock);
up_read(&bdi->wb_switch_rwsem);
if (nr_switched) {
wb_wakeup(new_wb);
wb_put_many(old_wb, nr_switched);
}
for (inodep = isw->inodes; *inodep; inodep++)
iput(*inodep);
wb_put(new_wb);
kfree(isw);
atomic_dec(&isw_nr_in_flight);
}
static bool inode_prepare_wbs_switch(struct inode *inode,
struct bdi_writeback *new_wb)
{
/*
* Paired with smp_mb() in cgroup_writeback_umount().
* isw_nr_in_flight must be increased before checking SB_ACTIVE and
* grabbing an inode, otherwise isw_nr_in_flight can be observed as 0
* in cgroup_writeback_umount() and the isw_wq will be not flushed.
*/
smp_mb();
if (IS_DAX(inode))
return false;
/* while holding I_WB_SWITCH, no one else can update the association */
spin_lock(&inode->i_lock);
if (!(inode->i_sb->s_flags & SB_ACTIVE) ||
inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) ||
inode_to_wb(inode) == new_wb) {
spin_unlock(&inode->i_lock);
return false;
}
inode->i_state |= I_WB_SWITCH;
__iget(inode);
spin_unlock(&inode->i_lock);
return true;
}
/**
* inode_switch_wbs - change the wb association of an inode
* @inode: target inode
* @new_wb_id: ID of the new wb
*
* Switch @inode's wb association to the wb identified by @new_wb_id. The
* switching is performed asynchronously and may fail silently.
*/
static void inode_switch_wbs(struct inode *inode, int new_wb_id)
{
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct cgroup_subsys_state *memcg_css;
struct inode_switch_wbs_context *isw;
/* noop if seems to be already in progress */
if (inode->i_state & I_WB_SWITCH)
return;
/* avoid queueing a new switch if too many are already in flight */
if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT)
return;
isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC);
if (!isw)
return;
atomic_inc(&isw_nr_in_flight);
/* find and pin the new wb */
rcu_read_lock();
memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys);
if (memcg_css && !css_tryget(memcg_css))
memcg_css = NULL;
rcu_read_unlock();
if (!memcg_css)
goto out_free;
isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
css_put(memcg_css);
if (!isw->new_wb)
goto out_free;
if (!inode_prepare_wbs_switch(inode, isw->new_wb))
goto out_free;
isw->inodes[0] = inode;
/*
* In addition to synchronizing among switchers, I_WB_SWITCH tells
* the RCU protected stat update paths to grab the i_page
* lock so that stat transfer can synchronize against them.
* Let's continue after I_WB_SWITCH is guaranteed to be visible.
*/
INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn);
queue_rcu_work(isw_wq, &isw->work);
return;
out_free:
atomic_dec(&isw_nr_in_flight);
if (isw->new_wb)
wb_put(isw->new_wb);
kfree(isw);
}
static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw,
struct list_head *list, int *nr)
{
struct inode *inode;
list_for_each_entry(inode, list, i_io_list) {
if (!inode_prepare_wbs_switch(inode, isw->new_wb))
continue;
isw->inodes[*nr] = inode;
(*nr)++;
if (*nr >= WB_MAX_INODES_PER_ISW - 1)
return true;
}
return false;
}
/**
* cleanup_offline_cgwb - detach associated inodes
* @wb: target wb
*
* Switch all inodes attached to @wb to a nearest living ancestor's wb in order
* to eventually release the dying @wb. Returns %true if not all inodes were
* switched and the function has to be restarted.
*/
bool cleanup_offline_cgwb(struct bdi_writeback *wb)
{
struct cgroup_subsys_state *memcg_css;
struct inode_switch_wbs_context *isw;
int nr;
bool restart = false;
isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW),
GFP_KERNEL);
if (!isw)
return restart;
atomic_inc(&isw_nr_in_flight);
for (memcg_css = wb->memcg_css->parent; memcg_css;
memcg_css = memcg_css->parent) {
isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL);
if (isw->new_wb)
break;
}
if (unlikely(!isw->new_wb))
isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */
nr = 0;
spin_lock(&wb->list_lock);
/*
* In addition to the inodes that have completed writeback, also switch
* cgwbs for those inodes only with dirty timestamps. Otherwise, those
* inodes won't be written back for a long time when lazytime is
* enabled, and thus pinning the dying cgwbs. It won't break the
* bandwidth restrictions, as writeback of inode metadata is not
* accounted for.
*/
restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr);
if (!restart)
restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr);
spin_unlock(&wb->list_lock);
/* no attached inodes? bail out */
if (nr == 0) {
atomic_dec(&isw_nr_in_flight);
wb_put(isw->new_wb);
kfree(isw);
return restart;
}
/*
* In addition to synchronizing among switchers, I_WB_SWITCH tells
* the RCU protected stat update paths to grab the i_page
* lock so that stat transfer can synchronize against them.
* Let's continue after I_WB_SWITCH is guaranteed to be visible.
*/
INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn);
queue_rcu_work(isw_wq, &isw->work);
return restart;
}
/**
* wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it
* @wbc: writeback_control of interest
* @inode: target inode
*
* @inode is locked and about to be written back under the control of @wbc.
* Record @inode's writeback context into @wbc and unlock the i_lock. On
* writeback completion, wbc_detach_inode() should be called. This is used
* to track the cgroup writeback context.
*/
static void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
struct inode *inode)
__releases(&inode->i_lock)
{
if (!inode_cgwb_enabled(inode)) {
spin_unlock(&inode->i_lock);
return;
}
wbc->wb = inode_to_wb(inode);
wbc->inode = inode;
wbc->wb_id = wbc->wb->memcg_css->id;
wbc->wb_lcand_id = inode->i_wb_frn_winner;
wbc->wb_tcand_id = 0;
wbc->wb_bytes = 0;
wbc->wb_lcand_bytes = 0;
wbc->wb_tcand_bytes = 0;
wb_get(wbc->wb);
spin_unlock(&inode->i_lock);
/*
* A dying wb indicates that either the blkcg associated with the
* memcg changed or the associated memcg is dying. In the first
* case, a replacement wb should already be available and we should
* refresh the wb immediately. In the second case, trying to
* refresh will keep failing.
*/
if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
inode_switch_wbs(inode, wbc->wb_id);
}
/**
* wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite
* @wbc: writeback_control of interest
* @inode: target inode
*
* This function is to be used by __filemap_fdatawrite_range(), which is an
* alternative entry point into writeback code, and first ensures @inode is
* associated with a bdi_writeback and attaches it to @wbc.
*/
void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode)
{
spin_lock(&inode->i_lock);
inode_attach_wb(inode, NULL);
wbc_attach_and_unlock_inode(wbc, inode);
}
EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode);
/**
* wbc_detach_inode - disassociate wbc from inode and perform foreign detection
* @wbc: writeback_control of the just finished writeback
*
* To be called after a writeback attempt of an inode finishes and undoes
* wbc_attach_and_unlock_inode(). Can be called under any context.
*
* As concurrent write sharing of an inode is expected to be very rare and
* memcg only tracks page ownership on first-use basis severely confining
* the usefulness of such sharing, cgroup writeback tracks ownership
* per-inode. While the support for concurrent write sharing of an inode
* is deemed unnecessary, an inode being written to by different cgroups at
* different points in time is a lot more common, and, more importantly,
* charging only by first-use can too readily lead to grossly incorrect
* behaviors (single foreign page can lead to gigabytes of writeback to be
* incorrectly attributed).
*
* To resolve this issue, cgroup writeback detects the majority dirtier of
* an inode and transfers the ownership to it. To avoid unnecessary
* oscillation, the detection mechanism keeps track of history and gives
* out the switch verdict only if the foreign usage pattern is stable over
* a certain amount of time and/or writeback attempts.
*
* On each writeback attempt, @wbc tries to detect the majority writer
* using Boyer-Moore majority vote algorithm. In addition to the byte
* count from the majority voting, it also counts the bytes written for the
* current wb and the last round's winner wb (max of last round's current
* wb, the winner from two rounds ago, and the last round's majority
* candidate). Keeping track of the historical winner helps the algorithm
* to semi-reliably detect the most active writer even when it's not the
* absolute majority.
*
* Once the winner of the round is determined, whether the winner is
* foreign or not and how much IO time the round consumed is recorded in
* inode->i_wb_frn_history. If the amount of recorded foreign IO time is
* over a certain threshold, the switch verdict is given.
*/
void wbc_detach_inode(struct writeback_control *wbc)
{
struct bdi_writeback *wb = wbc->wb;
struct inode *inode = wbc->inode;
unsigned long avg_time, max_bytes, max_time;
u16 history;
int max_id;
if (!wb)
return;
history = inode->i_wb_frn_history;
avg_time = inode->i_wb_frn_avg_time;
/* pick the winner of this round */
if (wbc->wb_bytes >= wbc->wb_lcand_bytes &&
wbc->wb_bytes >= wbc->wb_tcand_bytes) {
max_id = wbc->wb_id;
max_bytes = wbc->wb_bytes;
} else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) {
max_id = wbc->wb_lcand_id;
max_bytes = wbc->wb_lcand_bytes;
} else {
max_id = wbc->wb_tcand_id;
max_bytes = wbc->wb_tcand_bytes;
}
/*
* Calculate the amount of IO time the winner consumed and fold it
* into the running average kept per inode. If the consumed IO
* time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for
* deciding whether to switch or not. This is to prevent one-off
* small dirtiers from skewing the verdict.
*/
max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT,
wb->avg_write_bandwidth);
if (avg_time)
avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) -
(avg_time >> WB_FRN_TIME_AVG_SHIFT);
else
avg_time = max_time; /* immediate catch up on first run */
if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) {
int slots;
/*
* The switch verdict is reached if foreign wb's consume
* more than a certain proportion of IO time in a
* WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot
* history mask where each bit represents one sixteenth of
* the period. Determine the number of slots to shift into
* history from @max_time.
*/
slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT),
(unsigned long)WB_FRN_HIST_MAX_SLOTS);
history <<= slots;
if (wbc->wb_id != max_id)
history |= (1U << slots) - 1;
if (history)
trace_inode_foreign_history(inode, wbc, history);
/*
* Switch if the current wb isn't the consistent winner.
* If there are multiple closely competing dirtiers, the
* inode may switch across them repeatedly over time, which
* is okay. The main goal is avoiding keeping an inode on
* the wrong wb for an extended period of time.
*/
if (hweight16(history) > WB_FRN_HIST_THR_SLOTS)
inode_switch_wbs(inode, max_id);
}
/*
* Multiple instances of this function may race to update the
* following fields but we don't mind occassional inaccuracies.
*/
inode->i_wb_frn_winner = max_id;
inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX);
inode->i_wb_frn_history = history;
wb_put(wbc->wb);
wbc->wb = NULL;
}
EXPORT_SYMBOL_GPL(wbc_detach_inode);
/**
* wbc_account_cgroup_owner - account writeback to update inode cgroup ownership
* @wbc: writeback_control of the writeback in progress
* @folio: folio being written out
* @bytes: number of bytes being written out
*
* @bytes from @folio are about to written out during the writeback
* controlled by @wbc. Keep the book for foreign inode detection. See
* wbc_detach_inode().
*/
void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
size_t bytes)
{
struct cgroup_subsys_state *css;
int id;
/*
* pageout() path doesn't attach @wbc to the inode being written
* out. This is intentional as we don't want the function to block
* behind a slow cgroup. Ultimately, we want pageout() to kick off
* regular writeback instead of writing things out itself.
*/
if (!wbc->wb || wbc->no_cgroup_owner)
return;
css = mem_cgroup_css_from_folio(folio);
/* dead cgroups shouldn't contribute to inode ownership arbitration */
if (!(css->flags & CSS_ONLINE))
return;
id = css->id;
if (id == wbc->wb_id) {
wbc->wb_bytes += bytes;
return;
}
if (id == wbc->wb_lcand_id)
wbc->wb_lcand_bytes += bytes;
/* Boyer-Moore majority vote algorithm */
if (!wbc->wb_tcand_bytes)
wbc->wb_tcand_id = id;
if (id == wbc->wb_tcand_id)
wbc->wb_tcand_bytes += bytes;
else
wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes);
}
EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner);
/**
* wb_split_bdi_pages - split nr_pages to write according to bandwidth
* @wb: target bdi_writeback to split @nr_pages to
* @nr_pages: number of pages to write for the whole bdi
*
* Split @wb's portion of @nr_pages according to @wb's write bandwidth in
* relation to the total write bandwidth of all wb's w/ dirty inodes on
* @wb->bdi.
*/
static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
unsigned long this_bw = wb->avg_write_bandwidth;
unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
if (nr_pages == LONG_MAX)
return LONG_MAX;
/*
* This may be called on clean wb's and proportional distribution
* may not make sense, just use the original @nr_pages in those
* cases. In general, we wanna err on the side of writing more.
*/
if (!tot_bw || this_bw >= tot_bw)
return nr_pages;
else
return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw);
}
/**
* bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi
* @bdi: target backing_dev_info
* @base_work: wb_writeback_work to issue
* @skip_if_busy: skip wb's which already have writeback in progress
*
* Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which
* have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's
* distributed to the busy wbs according to each wb's proportion in the
* total active write bandwidth of @bdi.
*/
static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
struct wb_writeback_work *base_work,
bool skip_if_busy)
{
struct bdi_writeback *last_wb = NULL;
struct bdi_writeback *wb = list_entry(&bdi->wb_list,
struct bdi_writeback, bdi_node);
might_sleep();
restart:
rcu_read_lock();
list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) {
DEFINE_WB_COMPLETION(fallback_work_done, bdi);
struct wb_writeback_work fallback_work;
struct wb_writeback_work *work;
long nr_pages;
if (last_wb) {
wb_put(last_wb);
last_wb = NULL;
}
/* SYNC_ALL writes out I_DIRTY_TIME too */
if (!wb_has_dirty_io(wb) &&
(base_work->sync_mode == WB_SYNC_NONE ||
list_empty(&wb->b_dirty_time)))
continue;
if (skip_if_busy && writeback_in_progress(wb))
continue;
nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages);
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
*work = *base_work;
work->nr_pages = nr_pages;
work->auto_free = 1;
wb_queue_work(wb, work);
continue;
}
/*
* If wb_tryget fails, the wb has been shutdown, skip it.
*
* Pin @wb so that it stays on @bdi->wb_list. This allows
* continuing iteration from @wb after dropping and
* regrabbing rcu read lock.
*/
if (!wb_tryget(wb))
continue;
/* alloc failed, execute synchronously using on-stack fallback */
work = &fallback_work;
*work = *base_work;
work->nr_pages = nr_pages;
work->auto_free = 0;
work->done = &fallback_work_done;
wb_queue_work(wb, work);
last_wb = wb;
rcu_read_unlock();
wb_wait_for_completion(&fallback_work_done);
goto restart;
}
rcu_read_unlock();
if (last_wb)
wb_put(last_wb);
}
/**
* cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
* @bdi_id: target bdi id
* @memcg_id: target memcg css id
* @reason: reason why some writeback work initiated
* @done: target wb_completion
*
* Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id
* with the specified parameters.
*/
int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
enum wb_reason reason, struct wb_completion *done)
{
struct backing_dev_info *bdi;
struct cgroup_subsys_state *memcg_css;
struct bdi_writeback *wb;
struct wb_writeback_work *work;
unsigned long dirty;
int ret;
/* lookup bdi and memcg */
bdi = bdi_get_by_id(bdi_id);
if (!bdi)
return -ENOENT;
rcu_read_lock();
memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys);
if (memcg_css && !css_tryget(memcg_css))
memcg_css = NULL;
rcu_read_unlock();
if (!memcg_css) {
ret = -ENOENT;
goto out_bdi_put;
}
/*
* And find the associated wb. If the wb isn't there already
* there's nothing to flush, don't create one.
*/
wb = wb_get_lookup(bdi, memcg_css);
if (!wb) {
ret = -ENOENT;
goto out_css_put;
}
/*
* The caller is attempting to write out most of
* the currently dirty pages. Let's take the current dirty page
* count and inflate it by 25% which should be large enough to
* flush out most dirty pages while avoiding getting livelocked by
* concurrent dirtiers.
*
* BTW the memcg stats are flushed periodically and this is best-effort
* estimation, so some potential error is ok.
*/
dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY);
dirty = dirty * 10 / 8;
/* issue the writeback work */
work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN);
if (work) {
work->nr_pages = dirty;
work->sync_mode = WB_SYNC_NONE;
work->range_cyclic = 1;
work->reason = reason;
work->done = done;
work->auto_free = 1;
wb_queue_work(wb, work);
ret = 0;
} else {
ret = -ENOMEM;
}
wb_put(wb);
out_css_put:
css_put(memcg_css);
out_bdi_put:
bdi_put(bdi);
return ret;
}
/**
* cgroup_writeback_umount - flush inode wb switches for umount
* @sb: target super_block
*
* This function is called when a super_block is about to be destroyed and
* flushes in-flight inode wb switches. An inode wb switch goes through
* RCU and then workqueue, so the two need to be flushed in order to ensure
* that all previously scheduled switches are finished. As wb switches are
* rare occurrences and synchronize_rcu() can take a while, perform
* flushing iff wb switches are in flight.
*/
void cgroup_writeback_umount(struct super_block *sb)
{
if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK))
return;
/*
* SB_ACTIVE should be reliably cleared before checking
* isw_nr_in_flight, see generic_shutdown_super().
*/
smp_mb();
if (atomic_read(&isw_nr_in_flight)) {
/*
* Use rcu_barrier() to wait for all pending callbacks to
* ensure that all in-flight wb switches are in the workqueue.
*/
rcu_barrier();
flush_workqueue(isw_wq);
}
}
static int __init cgroup_writeback_init(void)
{
isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
if (!isw_wq)
return -ENOMEM;
return 0;
}
fs_initcall(cgroup_writeback_init);
#else /* CONFIG_CGROUP_WRITEBACK */
static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
static void inode_cgwb_move_to_attached(struct inode *inode,
struct bdi_writeback *wb)
{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
WARN_ON_ONCE(inode->i_state & I_FREEING);
inode->i_state &= ~I_SYNC_QUEUED;
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
}
static struct bdi_writeback *
locked_inode_to_wb_and_lock_list(struct inode *inode)
__releases(&inode->i_lock)
__acquires(&wb->list_lock)
{
struct bdi_writeback *wb = inode_to_wb(inode);
spin_unlock(&inode->i_lock);
spin_lock(&wb->list_lock);
return wb;
}
static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode)
__acquires(&wb->list_lock)
{
struct bdi_writeback *wb = inode_to_wb(inode);
spin_lock(&wb->list_lock);
return wb;
}
static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
return nr_pages;
}
static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
struct wb_writeback_work *base_work,
bool skip_if_busy)
{
might_sleep();
if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) {
base_work->auto_free = 0;
wb_queue_work(&bdi->wb, base_work);
}
}
static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
struct inode *inode)
__releases(&inode->i_lock)
{
spin_unlock(&inode->i_lock);
}
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* Add in the number of potentially dirty inodes, because each inode
* write can dirty pagecache in the underlying blockdev.
*/
static unsigned long get_nr_dirty_pages(void)
{
return global_node_page_state(NR_FILE_DIRTY) +
get_nr_dirty_inodes();
}
static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason)
{
if (!wb_has_dirty_io(wb))
return;
/*
* All callers of this function want to start writeback of all
* dirty pages. Places like vmscan can call this at a very
* high frequency, causing pointless allocations of tons of
* work items and keeping the flusher threads busy retrieving
* that work. Ensure that we only allow one of them pending and
* inflight at the time.
*/
if (test_bit(WB_start_all, &wb->state) ||
test_and_set_bit(WB_start_all, &wb->state))
return;
wb->start_all_reason = reason;
wb_wakeup(wb);
}
/**
* wb_start_background_writeback - start background writeback
* @wb: bdi_writback to write from
*
* Description:
* This makes sure WB_SYNC_NONE background writeback happens. When
* this function returns, it is only guaranteed that for given wb
* some IO is happening if we are over background dirty threshold.
* Caller need not hold sb s_umount semaphore.
*/
void wb_start_background_writeback(struct bdi_writeback *wb)
{
/*
* We just wake up the flusher thread. It will perform background
* writeback as soon as there is no other work to do.
*/
trace_writeback_wake_background(wb);
wb_wakeup(wb);
}
/*
* Remove the inode from the writeback list it is on.
*/
void inode_io_list_del(struct inode *inode)
{
struct bdi_writeback *wb;
wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
inode->i_state &= ~I_SYNC_QUEUED;
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
}
EXPORT_SYMBOL(inode_io_list_del);
/*
* mark an inode as under writeback on the sb
*/
void sb_mark_inode_writeback(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
unsigned long flags;
if (list_empty(&inode->i_wb_list)) {
spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
if (list_empty(&inode->i_wb_list)) {
list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb);
trace_sb_mark_inode_writeback(inode);
}
spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
}
}
/*
* clear an inode as under writeback on the sb
*/
void sb_clear_inode_writeback(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
unsigned long flags;
if (!list_empty(&inode->i_wb_list)) {
spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
if (!list_empty(&inode->i_wb_list)) {
list_del_init(&inode->i_wb_list);
trace_sb_clear_inode_writeback(inode);
}
spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
}
}
/*
* Redirty an inode: set its when-it-was dirtied timestamp and move it to the
* furthest end of its superblock's dirty-inode list.
*
* Before stamping the inode's ->dirtied_when, we check to see whether it is
* already the most-recently-dirtied inode on the b_dirty list. If that is
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb)
{
assert_spin_locked(&inode->i_lock);
inode->i_state &= ~I_SYNC_QUEUED;
/*
* When the inode is being freed just don't bother with dirty list
* tracking. Flush worker will ignore this inode anyway and it will
* trigger assertions in inode_io_list_move_locked().
*/
if (inode->i_state & I_FREEING) {
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
return;
}
if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
tail = wb_inode(wb->b_dirty.next);
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
inode_io_list_move_locked(inode, wb, &wb->b_dirty);
}
static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
{
spin_lock(&inode->i_lock);
redirty_tail_locked(inode, wb);
spin_unlock(&inode->i_lock);
}
/*
* requeue inode for re-scanning after bdi->b_io list is exhausted.
*/
static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
{
inode_io_list_move_locked(inode, wb, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
{
assert_spin_locked(&inode->i_lock);
inode->i_state &= ~I_SYNC;
/* If inode is clean an unused, put it into LRU now... */
inode_add_lru(inode);
/* Called with inode->i_lock which ensures memory ordering. */
inode_wake_up_bit(inode, __I_SYNC);
}
static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
/*
* For inodes being constantly redirtied, dirtied_when can get stuck.
* It _appears_ to be in the future, but is actually in distant past.
* This test is necessary to prevent such wrapped-around relative times
* from permanently stopping the whole bdi writeback.
*/
ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
return ret;
}
/*
* Move expired (dirtied before dirtied_before) dirty inodes from
* @delaying_queue to @dispatch_queue.
*/
static int move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
unsigned long dirtied_before)
{
LIST_HEAD(tmp);
struct list_head *pos, *node;
struct super_block *sb = NULL;
struct inode *inode;
int do_sb_sort = 0;
int moved = 0;
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
if (inode_dirtied_after(inode, dirtied_before))
break;
spin_lock(&inode->i_lock);
list_move(&inode->i_io_list, &tmp);
moved++;
inode->i_state |= I_SYNC_QUEUED;
spin_unlock(&inode->i_lock);
if (sb_is_blkdev_sb(inode->i_sb))
continue;
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
}
/* just one sb in list, splice to dispatch_queue and we're done */
if (!do_sb_sort) {
list_splice(&tmp, dispatch_queue);
goto out;
}
/*
* Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue',
* we don't take inode->i_lock here because it is just a pointless overhead.
* Inode is already marked as I_SYNC_QUEUED so writeback list handling is
* fully under our control.
*/
while (!list_empty(&tmp)) {
sb = wb_inode(tmp.prev)->i_sb;
list_for_each_prev_safe(pos, node, &tmp) {
inode = wb_inode(pos);
if (inode->i_sb == sb)
list_move(&inode->i_io_list, dispatch_queue);
}
}
out:
return moved;
}
/*
* Queue all expired dirty inodes for io, eldest first.
* Before
* newly dirtied b_dirty b_io b_more_io
* =============> gf edc BA
* After
* newly dirtied b_dirty b_io b_more_io
* =============> g fBAedc
* |
* +--> dequeue for IO
*/
static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
unsigned long dirtied_before)
{
int moved;
unsigned long time_expire_jif = dirtied_before;
assert_spin_locked(&wb->list_lock);
list_splice_init(&wb->b_more_io, &wb->b_io);
moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before);
if (!work->for_sync)
time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
time_expire_jif);
if (moved)
wb_io_lists_populated(wb);
trace_writeback_queue_io(wb, work, dirtied_before, moved);
}
static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
int ret;
if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
trace_writeback_write_inode_start(inode, wbc);
ret = inode->i_sb->s_op->write_inode(inode, wbc);
trace_writeback_write_inode(inode, wbc);
return ret;
}
return 0;
}
/*
* Wait for writeback on an inode to complete. Called with i_lock held.
* Caller must make sure inode cannot go away when we drop i_lock.
*/
void inode_wait_for_writeback(struct inode *inode)
{
struct wait_bit_queue_entry wqe;
struct wait_queue_head *wq_head;
assert_spin_locked(&inode->i_lock); if (!(inode->i_state & I_SYNC))
return;
wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
for (;;) {
prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
if (!(inode->i_state & I_SYNC))
break;
spin_unlock(&inode->i_lock);
schedule();
spin_lock(&inode->i_lock);
}
finish_wait(wq_head, &wqe.wq_entry);
}
/*
* Sleep until I_SYNC is cleared. This function must be called with i_lock
* held and drops it. It is aimed for callers not holding any inode reference
* so once i_lock is dropped, inode can go away.
*/
static void inode_sleep_on_writeback(struct inode *inode)
__releases(inode->i_lock)
{
struct wait_bit_queue_entry wqe;
struct wait_queue_head *wq_head;
bool sleep;
assert_spin_locked(&inode->i_lock);
wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
sleep = !!(inode->i_state & I_SYNC);
spin_unlock(&inode->i_lock);
if (sleep)
schedule();
finish_wait(wq_head, &wqe.wq_entry);
}
/*
* Find proper writeback list for the inode depending on its current state and
* possibly also change of its state while we were doing writeback. Here we
* handle things such as livelock prevention or fairness of writeback among
* inodes. This function can be called only by flusher thread - noone else
* processes all inodes in writeback lists and requeueing inodes behind flusher
* thread's back can have unexpected consequences.
*/
static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
struct writeback_control *wbc,
unsigned long dirtied_before)
{
if (inode->i_state & I_FREEING)
return;
/*
* Sync livelock prevention. Each inode is tagged and synced in one
* shot. If still dirty, it will be redirty_tail()'ed below. Update
* the dirty time to prevent enqueue and sync it again.
*/
if ((inode->i_state & I_DIRTY) &&
(wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
inode->dirtied_when = jiffies;
if (wbc->pages_skipped) {
/*
* Writeback is not making progress due to locked buffers.
* Skip this inode for now. Although having skipped pages
* is odd for clean inodes, it can happen for some
* filesystems so handle that gracefully.
*/
if (inode->i_state & I_DIRTY_ALL)
redirty_tail_locked(inode, wb);
else
inode_cgwb_move_to_attached(inode, wb);
return;
}
if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything.
*/
if (wbc->nr_to_write <= 0 &&
!inode_dirtied_after(inode, dirtied_before)) {
/* Slice used up. Queue for next turn. */
requeue_io(inode, wb);
} else {
/*
* Writeback blocked by something other than
* congestion. Delay the inode for some time to
* avoid spinning on the CPU (100% iowait)
* retrying writeback of the dirty page/inode
* that cannot be performed immediately.
*/
redirty_tail_locked(inode, wb);
}
} else if (inode->i_state & I_DIRTY) {
/*
* Filesystems can dirty the inode during writeback operations,
* such as delayed allocation during submission or metadata
* updates after data IO completion.
*/
redirty_tail_locked(inode, wb);
} else if (inode->i_state & I_DIRTY_TIME) {
inode->dirtied_when = jiffies;
inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
inode->i_state &= ~I_SYNC_QUEUED;
} else {
/* The inode is clean. Remove from writeback lists. */
inode_cgwb_move_to_attached(inode, wb);
}
}
/*
* Write out an inode and its dirty pages (or some of its dirty pages, depending
* on @wbc->nr_to_write), and clear the relevant dirty flags from i_state.
*
* This doesn't remove the inode from the writeback list it is on, except
* potentially to move it from b_dirty_time to b_dirty due to timestamp
* expiration. The caller is otherwise responsible for writeback list handling.
*
* The caller is also responsible for setting the I_SYNC flag beforehand and
* calling inode_sync_complete() to clear it afterwards.
*/
static int
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
struct address_space *mapping = inode->i_mapping;
long nr_to_write = wbc->nr_to_write;
unsigned dirty;
int ret;
WARN_ON(!(inode->i_state & I_SYNC));
trace_writeback_single_inode_start(inode, wbc, nr_to_write);
ret = do_writepages(mapping, wbc);
/*
* Make sure to wait on the data before writing out the metadata.
* This is important for filesystems that modify metadata on data
* I/O completion. We don't do it for sync(2) writeback because it has a
* separate, external IO completion path and ->sync_fs for guaranteeing
* inode metadata is written back correctly.
*/
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
/*
* If the inode has dirty timestamps and we need to write them, call
* mark_inode_dirty_sync() to notify the filesystem about it and to
* change I_DIRTY_TIME into I_DIRTY_SYNC.
*/
if ((inode->i_state & I_DIRTY_TIME) &&
(wbc->sync_mode == WB_SYNC_ALL ||
time_after(jiffies, inode->dirtied_time_when +
dirtytime_expire_interval * HZ))) {
trace_writeback_lazytime(inode);
mark_inode_dirty_sync(inode);
}
/*
* Get and clear the dirty flags from i_state. This needs to be done
* after calling writepages because some filesystems may redirty the
* inode during writepages due to delalloc. It also needs to be done
* after handling timestamp expiration, as that may dirty the inode too.
*/
spin_lock(&inode->i_lock);
dirty = inode->i_state & I_DIRTY;
inode->i_state &= ~dirty;
/*
* Paired with smp_mb() in __mark_inode_dirty(). This allows
* __mark_inode_dirty() to test i_state without grabbing i_lock -
* either they see the I_DIRTY bits cleared or we see the dirtied
* inode.
*
* I_DIRTY_PAGES is always cleared together above even if @mapping
* still has dirty pages. The flag is reinstated after smp_mb() if
* necessary. This guarantees that either __mark_inode_dirty()
* sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
*/
smp_mb();
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
inode->i_state |= I_DIRTY_PAGES;
else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) {
if (!(inode->i_state & I_DIRTY_PAGES)) {
inode->i_state &= ~I_PINNING_NETFS_WB;
wbc->unpinned_netfs_wb = true;
dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */
}
}
spin_unlock(&inode->i_lock);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & ~I_DIRTY_PAGES) {
int err = write_inode(inode, wbc);
if (ret == 0)
ret = err;
}
wbc->unpinned_netfs_wb = false;
trace_writeback_single_inode(inode, wbc, nr_to_write);
return ret;
}
/*
* Write out an inode's dirty data and metadata on-demand, i.e. separately from
* the regular batched writeback done by the flusher threads in
* writeback_sb_inodes(). @wbc controls various aspects of the write, such as
* whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE).
*
* To prevent the inode from going away, either the caller must have a reference
* to the inode, or the inode must have I_WILL_FREE or I_FREEING set.
*/
static int writeback_single_inode(struct inode *inode,
struct writeback_control *wbc)
{
struct bdi_writeback *wb;
int ret = 0;
spin_lock(&inode->i_lock);
if (!atomic_read(&inode->i_count))
WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
else
WARN_ON(inode->i_state & I_WILL_FREE);
if (inode->i_state & I_SYNC) {
/*
* Writeback is already running on the inode. For WB_SYNC_NONE,
* that's enough and we can just return. For WB_SYNC_ALL, we
* must wait for the existing writeback to complete, then do
* writeback again if there's anything left.
*/
if (wbc->sync_mode != WB_SYNC_ALL)
goto out;
inode_wait_for_writeback(inode);
}
WARN_ON(inode->i_state & I_SYNC);
/*
* If the inode is already fully clean, then there's nothing to do.
*
* For data-integrity syncs we also need to check whether any pages are
* still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If
* there are any such pages, we'll need to wait for them.
*/
if (!(inode->i_state & I_DIRTY_ALL) &&
(wbc->sync_mode != WB_SYNC_ALL ||
!mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
goto out;
inode->i_state |= I_SYNC;
wbc_attach_and_unlock_inode(wbc, inode);
ret = __writeback_single_inode(inode, wbc);
wbc_detach_inode(wbc);
wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
/*
* If the inode is freeing, its i_io_list shoudn't be updated
* as it can be finally deleted at this moment.
*/
if (!(inode->i_state & I_FREEING)) {
/*
* If the inode is now fully clean, then it can be safely
* removed from its writeback list (if any). Otherwise the
* flusher threads are responsible for the writeback lists.
*/
if (!(inode->i_state & I_DIRTY_ALL))
inode_cgwb_move_to_attached(inode, wb);
else if (!(inode->i_state & I_SYNC_QUEUED)) {
if ((inode->i_state & I_DIRTY))
redirty_tail_locked(inode, wb);
else if (inode->i_state & I_DIRTY_TIME) {
inode->dirtied_when = jiffies;
inode_io_list_move_locked(inode,
wb,
&wb->b_dirty_time);
}
}
}
spin_unlock(&wb->list_lock);
inode_sync_complete(inode);
out:
spin_unlock(&inode->i_lock);
return ret;
}
static long writeback_chunk_size(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
long pages;
/*
* WB_SYNC_ALL mode does livelock avoidance by syncing dirty
* inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
* here avoids calling into writeback_inodes_wb() more than once.
*
* The intended call sequence for WB_SYNC_ALL writeback is:
*
* wb_writeback()
* writeback_sb_inodes() <== called only once
* write_cache_pages() <== called once for each inode
* (quickly) tag currently dirty pages
* (maybe slowly) sync all tagged pages
*/
if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
pages = LONG_MAX;
else {
pages = min(wb->avg_write_bandwidth / 2,
global_wb_domain.dirty_limit / DIRTY_SCOPE);
pages = min(pages, work->nr_pages);
pages = round_down(pages + MIN_WRITEBACK_PAGES,
MIN_WRITEBACK_PAGES);
}
return pages;
}
/*
* Write a portion of b_io inodes which belong to @sb.
*
* Return the number of pages and/or inodes written.
*
* NOTE! This is called with wb->list_lock held, and will
* unlock and relock that for each inode it ends up doing
* IO for.
*/
static long writeback_sb_inodes(struct super_block *sb,
struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
struct writeback_control wbc = {
.sync_mode = work->sync_mode,
.tagged_writepages = work->tagged_writepages,
.for_kupdate = work->for_kupdate,
.for_background = work->for_background,
.for_sync = work->for_sync,
.range_cyclic = work->range_cyclic,
.range_start = 0,
.range_end = LLONG_MAX,
};
unsigned long start_time = jiffies;
long write_chunk;
long total_wrote = 0; /* count both pages and inodes */
unsigned long dirtied_before = jiffies;
if (work->for_kupdate)
dirtied_before = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
while (!list_empty(&wb->b_io)) {
struct inode *inode = wb_inode(wb->b_io.prev);
struct bdi_writeback *tmp_wb;
long wrote;
if (inode->i_sb != sb) {
if (work->sb) {
/*
* We only want to write back data for this
* superblock, move all inodes not belonging
* to it back onto the dirty list.
*/
redirty_tail(inode, wb);
continue;
}
/*
* The inode belongs to a different superblock.
* Bounce back to the caller to unpin this and
* pin the next superblock.
*/
break;
}
/*
* Don't bother with new inodes or inodes being freed, first
* kind does not need periodic writeout yet, and for the latter
* kind writeout is handled by the freer.
*/
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
redirty_tail_locked(inode, wb);
spin_unlock(&inode->i_lock);
continue;
}
if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
/*
* If this inode is locked for writeback and we are not
* doing writeback-for-data-integrity, move it to
* b_more_io so that writeback can proceed with the
* other inodes on s_io.
*
* We'll have another go at writing back this inode
* when we completed a full scan of b_io.
*/
requeue_io(inode, wb);
spin_unlock(&inode->i_lock);
trace_writeback_sb_inodes_requeue(inode);
continue;
}
spin_unlock(&wb->list_lock);
/*
* We already requeued the inode if it had I_SYNC set and we
* are doing WB_SYNC_NONE writeback. So this catches only the
* WB_SYNC_ALL case.
*/
if (inode->i_state & I_SYNC) {
/* Wait for I_SYNC. This function drops i_lock... */
inode_sleep_on_writeback(inode);
/* Inode may be gone, start again */
spin_lock(&wb->list_lock);
continue;
}
inode->i_state |= I_SYNC;
wbc_attach_and_unlock_inode(&wbc, inode);
write_chunk = writeback_chunk_size(wb, work);
wbc.nr_to_write = write_chunk;
wbc.pages_skipped = 0;
/*
* We use I_SYNC to pin the inode in memory. While it is set
* evict_inode() will wait so the inode cannot be freed.
*/
__writeback_single_inode(inode, &wbc);
wbc_detach_inode(&wbc);
work->nr_pages -= write_chunk - wbc.nr_to_write;
wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped;
wrote = wrote < 0 ? 0 : wrote;
total_wrote += wrote;
if (need_resched()) {
/*
* We're trying to balance between building up a nice
* long list of IOs to improve our merge rate, and
* getting those IOs out quickly for anyone throttling
* in balance_dirty_pages(). cond_resched() doesn't
* unplug, so get our IOs out the door before we
* give up the CPU.
*/
blk_flush_plug(current->plug, false);
cond_resched();
}
/*
* Requeue @inode if still dirty. Be careful as @inode may
* have been switched to another wb in the meantime.
*/
tmp_wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
if (!(inode->i_state & I_DIRTY_ALL))
total_wrote++;
requeue_inode(inode, tmp_wb, &wbc, dirtied_before);
inode_sync_complete(inode);
spin_unlock(&inode->i_lock);
if (unlikely(tmp_wb != wb)) {
spin_unlock(&tmp_wb->list_lock);
spin_lock(&wb->list_lock);
}
/*
* bail out to wb_writeback() often enough to check
* background threshold and other termination conditions.
*/
if (total_wrote) {
if (time_is_before_jiffies(start_time + HZ / 10UL))
break;
if (work->nr_pages <= 0)
break;
}
}
return total_wrote;
}
static long __writeback_inodes_wb(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
unsigned long start_time = jiffies;
long wrote = 0;
while (!list_empty(&wb->b_io)) {
struct inode *inode = wb_inode(wb->b_io.prev);
struct super_block *sb = inode->i_sb;
if (!super_trylock_shared(sb)) {
/*
* super_trylock_shared() may fail consistently due to
* s_umount being grabbed by someone else. Don't use
* requeue_io() to avoid busy retrying the inode/sb.
*/
redirty_tail(inode, wb);
continue;
}
wrote += writeback_sb_inodes(sb, wb, work);
up_read(&sb->s_umount);
/* refer to the same tests at the end of writeback_sb_inodes */
if (wrote) {
if (time_is_before_jiffies(start_time + HZ / 10UL))
break;
if (work->nr_pages <= 0)
break;
}
}
/* Leave any unwritten inodes on b_io */
return wrote;
}
static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
enum wb_reason reason)
{
struct wb_writeback_work work = {
.nr_pages = nr_pages,
.sync_mode = WB_SYNC_NONE,
.range_cyclic = 1,
.reason = reason,
};
struct blk_plug plug;
blk_start_plug(&plug);
spin_lock(&wb->list_lock);
if (list_empty(&wb->b_io))
queue_io(wb, &work, jiffies);
__writeback_inodes_wb(wb, &work);
spin_unlock(&wb->list_lock);
blk_finish_plug(&plug);
return nr_pages - work.nr_pages;
}
/*
* Explicit flushing or periodic writeback of "old" data.
*
* Define "old": the first time one of an inode's pages is dirtied, we mark the
* dirtying-time in the inode's address_space. So this periodic writeback code
* just walks the superblock inode list, writing back any inodes which are
* older than a specific point in time.
*
* Try to run once per dirty_writeback_interval. But if a writeback event
* takes longer than a dirty_writeback_interval interval, then leave a
* one-second gap.
*
* dirtied_before takes precedence over nr_to_write. So we'll only write back
* all dirty pages if they are all attached to "old" mappings.
*/
static long wb_writeback(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
long nr_pages = work->nr_pages;
unsigned long dirtied_before = jiffies;
struct inode *inode;
long progress;
struct blk_plug plug;
bool queued = false;
blk_start_plug(&plug);
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
*/
if (work->nr_pages <= 0)
break;
/*
* Background writeout and kupdate-style writeback may
* run forever. Stop them if there is other work to do
* so that e.g. sync can proceed. They'll be restarted
* after the other works are all done.
*/
if ((work->for_background || work->for_kupdate) &&
!list_empty(&wb->work_list))
break;
/*
* For background writeout, stop when we are below the
* background dirty threshold
*/
if (work->for_background && !wb_over_bg_thresh(wb))
break;
spin_lock(&wb->list_lock);
trace_writeback_start(wb, work);
if (list_empty(&wb->b_io)) {
/*
* Kupdate and background works are special and we want
* to include all inodes that need writing. Livelock
* avoidance is handled by these works yielding to any
* other work so we are safe.
*/
if (work->for_kupdate) {
dirtied_before = jiffies -
msecs_to_jiffies(dirty_expire_interval *
10);
} else if (work->for_background)
dirtied_before = jiffies;
queue_io(wb, work, dirtied_before);
queued = true;
}
if (work->sb)
progress = writeback_sb_inodes(work->sb, wb, work);
else
progress = __writeback_inodes_wb(wb, work);
trace_writeback_written(wb, work);
/*
* Did we write something? Try for more
*
* Dirty inodes are moved to b_io for writeback in batches.
* The completion of the current batch does not necessarily
* mean the overall work is done. So we keep looping as long
* as made some progress on cleaning pages or inodes.
*/
if (progress || !queued) {
spin_unlock(&wb->list_lock);
continue;
}
/*
* No more inodes for IO, bail
*/
if (list_empty(&wb->b_more_io)) {
spin_unlock(&wb->list_lock);
break;
}
/*
* Nothing written. Wait for some inode to
* become available for writeback. Otherwise
* we'll just busyloop.
*/
trace_writeback_wait(wb, work);
inode = wb_inode(wb->b_more_io.prev);
spin_lock(&inode->i_lock);
spin_unlock(&wb->list_lock);
/* This function drops i_lock... */
inode_sleep_on_writeback(inode);
}
blk_finish_plug(&plug);
return nr_pages - work->nr_pages;
}
/*
* Return the next wb_writeback_work struct that hasn't been processed yet.
*/
static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
{
struct wb_writeback_work *work = NULL;
spin_lock_irq(&wb->work_lock);
if (!list_empty(&wb->work_list)) {
work = list_entry(wb->work_list.next,
struct wb_writeback_work, list);
list_del_init(&work->list);
}
spin_unlock_irq(&wb->work_lock);
return work;
}
static long wb_check_background_flush(struct bdi_writeback *wb)
{
if (wb_over_bg_thresh(wb)) {
struct wb_writeback_work work = {
.nr_pages = LONG_MAX,
.sync_mode = WB_SYNC_NONE,
.for_background = 1,
.range_cyclic = 1,
.reason = WB_REASON_BACKGROUND,
};
return wb_writeback(wb, &work);
}
return 0;
}
static long wb_check_old_data_flush(struct bdi_writeback *wb)
{
unsigned long expired;
long nr_pages;
/*
* When set to zero, disable periodic writeback
*/
if (!dirty_writeback_interval)
return 0;
expired = wb->last_old_flush +
msecs_to_jiffies(dirty_writeback_interval * 10);
if (time_before(jiffies, expired))
return 0;
wb->last_old_flush = jiffies;
nr_pages = get_nr_dirty_pages();
if (nr_pages) {
struct wb_writeback_work work = {
.nr_pages = nr_pages,
.sync_mode = WB_SYNC_NONE,
.for_kupdate = 1,
.range_cyclic = 1,
.reason = WB_REASON_PERIODIC,
};
return wb_writeback(wb, &work);
}
return 0;
}
static long wb_check_start_all(struct bdi_writeback *wb)
{
long nr_pages;
if (!test_bit(WB_start_all, &wb->state))
return 0;
nr_pages = get_nr_dirty_pages();
if (nr_pages) {
struct wb_writeback_work work = {
.nr_pages = wb_split_bdi_pages(wb, nr_pages),
.sync_mode = WB_SYNC_NONE,
.range_cyclic = 1,
.reason = wb->start_all_reason,
};
nr_pages = wb_writeback(wb, &work);
}
clear_bit(WB_start_all, &wb->state);
return nr_pages;
}
/*
* Retrieve work items and do the writeback they describe
*/
static long wb_do_writeback(struct bdi_writeback *wb)
{
struct wb_writeback_work *work;
long wrote = 0;
set_bit(WB_writeback_running, &wb->state);
while ((work = get_next_work_item(wb)) != NULL) {
trace_writeback_exec(wb, work);
wrote += wb_writeback(wb, work);
finish_writeback_work(work);
}
/*
* Check for a flush-everything request
*/
wrote += wb_check_start_all(wb);
/*
* Check for periodic writeback, kupdated() style
*/
wrote += wb_check_old_data_flush(wb);
wrote += wb_check_background_flush(wb);
clear_bit(WB_writeback_running, &wb->state);
return wrote;
}
/*
* Handle writeback of dirty data for the device backed by this bdi. Also
* reschedules periodically and does kupdated style flushing.
*/
void wb_workfn(struct work_struct *work)
{
struct bdi_writeback *wb = container_of(to_delayed_work(work),
struct bdi_writeback, dwork);
long pages_written;
set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
if (likely(!current_is_workqueue_rescuer() ||
!test_bit(WB_registered, &wb->state))) {
/*
* The normal path. Keep writing back @wb until its
* work_list is empty. Note that this path is also taken
* if @wb is shutting down even when we're running off the
* rescuer as work_list needs to be drained.
*/
do {
pages_written = wb_do_writeback(wb);
trace_writeback_pages_written(pages_written);
} while (!list_empty(&wb->work_list));
} else {
/*
* bdi_wq can't get enough workers and we're running off
* the emergency worker. Don't hog it. Hopefully, 1024 is
* enough for efficient IO.
*/
pages_written = writeback_inodes_wb(wb, 1024,
WB_REASON_FORKER_THREAD);
trace_writeback_pages_written(pages_written);
}
if (!list_empty(&wb->work_list))
wb_wakeup(wb);
else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
wb_wakeup_delayed(wb);
}
/*
* Start writeback of all dirty pages on this bdi.
*/
static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
enum wb_reason reason)
{
struct bdi_writeback *wb;
if (!bdi_has_dirty_io(bdi))
return;
list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
wb_start_writeback(wb, reason);
}
void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
enum wb_reason reason)
{
rcu_read_lock();
__wakeup_flusher_threads_bdi(bdi, reason);
rcu_read_unlock();
}
/*
* Wakeup the flusher threads to start writeback of all currently dirty pages
*/
void wakeup_flusher_threads(enum wb_reason reason)
{
struct backing_dev_info *bdi;
/*
* If we are expecting writeback progress we must submit plugged IO.
*/
blk_flush_plug(current->plug, true);
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
__wakeup_flusher_threads_bdi(bdi, reason);
rcu_read_unlock();
}
/*
* Wake up bdi's periodically to make sure dirtytime inodes gets
* written back periodically. We deliberately do *not* check the
* b_dirtytime list in wb_has_dirty_io(), since this would cause the
* kernel to be constantly waking up once there are any dirtytime
* inodes on the system. So instead we define a separate delayed work
* function which gets called much more rarely. (By default, only
* once every 12 hours.)
*
* If there is any other write activity going on in the file system,
* this function won't be necessary. But if the only thing that has
* happened on the file system is a dirtytime inode caused by an atime
* update, we need this infrastructure below to make sure that inode
* eventually gets pushed out to disk.
*/
static void wakeup_dirtytime_writeback(struct work_struct *w);
static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback);
static void wakeup_dirtytime_writeback(struct work_struct *w)
{
struct backing_dev_info *bdi;
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
struct bdi_writeback *wb;
list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
if (!list_empty(&wb->b_dirty_time))
wb_wakeup(wb);
}
rcu_read_unlock();
schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
}
static int dirtytime_interval_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
mod_delayed_work(system_wq, &dirtytime_work, 0);
return ret;
}
static const struct ctl_table vm_fs_writeback_table[] = {
{
.procname = "dirtytime_expire_seconds",
.data = &dirtytime_expire_interval,
.maxlen = sizeof(dirtytime_expire_interval),
.mode = 0644,
.proc_handler = dirtytime_interval_handler,
.extra1 = SYSCTL_ZERO,
},
};
static int __init start_dirtytime_writeback(void)
{
schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
register_sysctl_init("vm", vm_fs_writeback_table);
return 0;
}
__initcall(start_dirtytime_writeback);
/**
* __mark_inode_dirty - internal function to mark an inode dirty
*
* @inode: inode to mark
* @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of
* multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined
* with I_DIRTY_PAGES.
*
* Mark an inode as dirty. We notify the filesystem, then update the inode's
* dirty flags. Then, if needed we add the inode to the appropriate dirty list.
*
* Most callers should use mark_inode_dirty() or mark_inode_dirty_sync()
* instead of calling this directly.
*
* CAREFUL! We only add the inode to the dirty list if it is hashed or if it
* refers to a blockdev. Unhashed inodes will never be added to the dirty list
* even if they are later hashed, as they will have been marked dirty already.
*
* In short, ensure you hash any inodes _before_ you start marking them dirty.
*
* Note that for blockdevs, inode->dirtied_when represents the dirtying time of
* the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
* the kernel-internal blockdev inode represents the dirtying time of the
* blockdev's pages. This is why for I_DIRTY_PAGES we always use
* page->mapping->host, so the page-dirtying time is recorded in the internal
* blockdev inode.
*/
void __mark_inode_dirty(struct inode *inode, int flags)
{
struct super_block *sb = inode->i_sb;
int dirtytime = 0;
struct bdi_writeback *wb = NULL;
trace_writeback_mark_inode_dirty(inode, flags);
if (flags & I_DIRTY_INODE) {
/*
* Inode timestamp update will piggback on this dirtying.
* We tell ->dirty_inode callback that timestamps need to
* be updated by setting I_DIRTY_TIME in flags.
*/
if (inode->i_state & I_DIRTY_TIME) {
spin_lock(&inode->i_lock);
if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME;
flags |= I_DIRTY_TIME;
}
spin_unlock(&inode->i_lock);
}
/*
* Notify the filesystem about the inode being dirtied, so that
* (if needed) it can update on-disk fields and journal the
* inode. This is only needed when the inode itself is being
* dirtied now. I.e. it's only needed for I_DIRTY_INODE, not
* for just I_DIRTY_PAGES or I_DIRTY_TIME.
*/
trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode)
sb->s_op->dirty_inode(inode,
flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags);
/* I_DIRTY_INODE supersedes I_DIRTY_TIME. */
flags &= ~I_DIRTY_TIME;
} else {
/*
* Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing.
* (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME
* in one call to __mark_inode_dirty().)
*/
dirtytime = flags & I_DIRTY_TIME;
WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME);
}
/*
* Paired with smp_mb() in __writeback_single_inode() for the
* following lockless i_state test. See there for details.
*/
smp_mb();
if ((inode->i_state & flags) == flags)
return;
spin_lock(&inode->i_lock);
if ((inode->i_state & flags) != flags) {
const int was_dirty = inode->i_state & I_DIRTY;
inode_attach_wb(inode, NULL);
inode->i_state |= flags;
/*
* Grab inode's wb early because it requires dropping i_lock and we
* need to make sure following checks happen atomically with dirty
* list handling so that we don't move inodes under flush worker's
* hands.
*/
if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
}
/*
* If the inode is queued for writeback by flush worker, just
* update its dirty state. Once the flush worker is done with
* the inode it will place it on the appropriate superblock
* list, based upon its state.
*/
if (inode->i_state & I_SYNC_QUEUED)
goto out_unlock;
/*
* Only add valid (hashed) inodes to the superblock's
* dirty list. Add blockdev inodes as well.
*/
if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode))
goto out_unlock;
}
if (inode->i_state & I_FREEING)
goto out_unlock;
/*
* If the inode was already on b_dirty/b_io/b_more_io, don't
* reposition it (that would break b_dirty time-ordering).
*/
if (!was_dirty) {
struct list_head *dirty_list;
bool wakeup_bdi = false;
inode->dirtied_when = jiffies;
if (dirtytime) inode->dirtied_time_when = jiffies;
if (inode->i_state & I_DIRTY)
dirty_list = &wb->b_dirty;
else
dirty_list = &wb->b_dirty_time;
wakeup_bdi = inode_io_list_move_locked(inode, wb,
dirty_list);
spin_unlock(&wb->list_lock);
spin_unlock(&inode->i_lock);
trace_writeback_dirty_inode_enqueue(inode);
/*
* If this is the first dirty inode for this bdi,
* we have to wake-up the corresponding bdi thread
* to make sure background write-back happens
* later.
*/
if (wakeup_bdi &&
(wb->bdi->capabilities & BDI_CAP_WRITEBACK))
wb_wakeup_delayed(wb);
return;
}
}
out_unlock:
if (wb) spin_unlock(&wb->list_lock);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(__mark_inode_dirty);
/*
* The @s_sync_lock is used to serialise concurrent sync operations
* to avoid lock contention problems with concurrent wait_sb_inodes() calls.
* Concurrent callers will block on the s_sync_lock rather than doing contending
* walks. The queueing maintains sync(2) required behaviour as all the IO that
* has been issued up to the time this function is enter is guaranteed to be
* completed by the time we have gained the lock and waited for all IO that is
* in progress regardless of the order callers are granted the lock.
*/
static void wait_sb_inodes(struct super_block *sb)
{
LIST_HEAD(sync_list);
/*
* We need to be protected against the filesystem going from
* r/o to r/w or vice versa.
*/
WARN_ON(!rwsem_is_locked(&sb->s_umount));
mutex_lock(&sb->s_sync_lock);
/*
* Splice the writeback list onto a temporary list to avoid waiting on
* inodes that have started writeback after this point.
*
* Use rcu_read_lock() to keep the inodes around until we have a
* reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as
* the local list because inodes can be dropped from either by writeback
* completion.
*/
rcu_read_lock();
spin_lock_irq(&sb->s_inode_wblist_lock);
list_splice_init(&sb->s_inodes_wb, &sync_list);
/*
* Data integrity sync. Must wait for all pages under writeback, because
* there may have been pages dirtied before our sync call, but which had
* writeout started before we write it out. In which case, the inode
* may not be on the dirty list, but we still have to wait for that
* writeout.
*/
while (!list_empty(&sync_list)) {
struct inode *inode = list_first_entry(&sync_list, struct inode,
i_wb_list);
struct address_space *mapping = inode->i_mapping;
/*
* Move each inode back to the wb list before we drop the lock
* to preserve consistency between i_wb_list and the mapping
* writeback tag. Writeback completion is responsible to remove
* the inode from either list once the writeback tag is cleared.
*/
list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb);
/*
* The mapping can appear untagged while still on-list since we
* do not have the mapping lock. Skip it here, wb completion
* will remove it.
*/
if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
continue;
spin_unlock_irq(&sb->s_inode_wblist_lock);
spin_lock(&inode->i_lock);
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
spin_unlock(&inode->i_lock);
spin_lock_irq(&sb->s_inode_wblist_lock);
continue;
}
__iget(inode);
spin_unlock(&inode->i_lock);
rcu_read_unlock();
/*
* We keep the error status of individual mapping so that
* applications can catch the writeback error using fsync(2).
* See filemap_fdatawait_keep_errors() for details.
*/
filemap_fdatawait_keep_errors(mapping);
cond_resched();
iput(inode);
rcu_read_lock();
spin_lock_irq(&sb->s_inode_wblist_lock);
}
spin_unlock_irq(&sb->s_inode_wblist_lock);
rcu_read_unlock();
mutex_unlock(&sb->s_sync_lock);
}
static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
enum wb_reason reason, bool skip_if_busy)
{
struct backing_dev_info *bdi = sb->s_bdi;
DEFINE_WB_COMPLETION(done, bdi);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_NONE,
.tagged_writepages = 1,
.done = &done,
.nr_pages = nr,
.reason = reason,
};
if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy);
wb_wait_for_completion(&done);
}
/**
* writeback_inodes_sb_nr - writeback dirty inodes from given super_block
* @sb: the superblock
* @nr: the number of pages to write
* @reason: reason why some writeback work initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
* for IO completion of submitted IO.
*/
void writeback_inodes_sb_nr(struct super_block *sb,
unsigned long nr,
enum wb_reason reason)
{
__writeback_inodes_sb_nr(sb, nr, reason, false);
}
EXPORT_SYMBOL(writeback_inodes_sb_nr);
/**
* writeback_inodes_sb - writeback dirty inodes from given super_block
* @sb: the superblock
* @reason: reason why some writeback work was initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
* for IO completion of submitted IO.
*/
void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
}
EXPORT_SYMBOL(writeback_inodes_sb);
/**
* try_to_writeback_inodes_sb - try to start writeback if none underway
* @sb: the superblock
* @reason: reason why some writeback work was initiated
*
* Invoke __writeback_inodes_sb_nr if no writeback is currently underway.
*/
void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
if (!down_read_trylock(&sb->s_umount))
return;
__writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true);
up_read(&sb->s_umount);
}
EXPORT_SYMBOL(try_to_writeback_inodes_sb);
/**
* sync_inodes_sb - sync sb inode pages
* @sb: the superblock
*
* This function writes and waits on any dirty inode belonging to this
* super_block.
*/
void sync_inodes_sb(struct super_block *sb)
{
struct backing_dev_info *bdi = sb->s_bdi;
DEFINE_WB_COMPLETION(done, bdi);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
.nr_pages = LONG_MAX,
.range_cyclic = 0,
.done = &done,
.reason = WB_REASON_SYNC,
.for_sync = 1,
};
/*
* Can't skip on !bdi_has_dirty() because we should wait for !dirty
* inodes under writeback and I_DIRTY_TIME inodes ignored by
* bdi_has_dirty() need to be written out too.
*/
if (bdi == &noop_backing_dev_info)
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
/* protect against inode wb switch, see inode_switch_wbs_work_fn() */
bdi_down_write_wb_switch_rwsem(bdi);
bdi_split_work_to_wbs(bdi, &work, false);
wb_wait_for_completion(&done);
bdi_up_write_wb_switch_rwsem(bdi);
wait_sb_inodes(sb);
}
EXPORT_SYMBOL(sync_inodes_sb);
/**
* write_inode_now - write an inode to disk
* @inode: inode to write to disk
* @sync: whether the write should be synchronous or not
*
* This function commits an inode to disk immediately if it is dirty. This is
* primarily needed by knfsd.
*
* The caller must either have a ref on the inode or must have set I_WILL_FREE.
*/
int write_inode_now(struct inode *inode, int sync)
{
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
};
if (!mapping_can_writeback(inode->i_mapping))
wbc.nr_to_write = 0;
might_sleep();
return writeback_single_inode(inode, &wbc);
}
EXPORT_SYMBOL(write_inode_now);
/**
* sync_inode_metadata - write an inode to disk
* @inode: the inode to sync
* @wait: wait for I/O to complete.
*
* Write an inode to disk and adjust its dirty state after completion.
*
* Note: only writes the actual inode, no associated data or other metadata.
*/
int sync_inode_metadata(struct inode *inode, int wait)
{
struct writeback_control wbc = {
.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
.nr_to_write = 0, /* metadata-only */
};
return writeback_single_inode(inode, &wbc);
}
EXPORT_SYMBOL(sync_inode_metadata);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2020 Google LLC
* Author: Will Deacon <will@kernel.org>
*/
#ifndef __ARM64_KVM_PGTABLE_H__
#define __ARM64_KVM_PGTABLE_H__
#include <linux/bits.h>
#include <linux/kvm_host.h>
#include <linux/types.h>
#define KVM_PGTABLE_FIRST_LEVEL -1
#define KVM_PGTABLE_LAST_LEVEL 3
/*
* The largest supported block sizes for KVM (no 52-bit PA support):
* - 4K (level 1): 1GB
* - 16K (level 2): 32MB
* - 64K (level 2): 512MB
*/
#ifdef CONFIG_ARM64_4K_PAGES
#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1
#else
#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2
#endif
#define kvm_lpa2_is_enabled() system_supports_lpa2()
static inline u64 kvm_get_parange_max(void)
{
if (kvm_lpa2_is_enabled() ||
(IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16))
return ID_AA64MMFR0_EL1_PARANGE_52;
else
return ID_AA64MMFR0_EL1_PARANGE_48;
}
static inline u64 kvm_get_parange(u64 mmfr0)
{
u64 parange_max = kvm_get_parange_max();
u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_EL1_PARANGE_SHIFT);
if (parange > parange_max)
parange = parange_max;
return parange;
}
typedef u64 kvm_pte_t;
#define KVM_PTE_VALID BIT(0)
#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT)
#define KVM_PTE_ADDR_51_48 GENMASK(15, 12)
#define KVM_PTE_ADDR_MASK_LPA2 GENMASK(49, PAGE_SHIFT)
#define KVM_PTE_ADDR_51_50_LPA2 GENMASK(9, 8)
#define KVM_PHYS_INVALID (-1ULL)
#define KVM_PTE_TYPE BIT(1)
#define KVM_PTE_TYPE_BLOCK 0
#define KVM_PTE_TYPE_PAGE 1
#define KVM_PTE_TYPE_TABLE 1
#define KVM_PTE_LEAF_ATTR_LO GENMASK(11, 2)
#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX GENMASK(4, 2)
#define KVM_PTE_LEAF_ATTR_LO_S1_AP GENMASK(7, 6)
#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO \
({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW \
({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
#define KVM_PTE_LEAF_ATTR_LO_S1_SH GENMASK(9, 8)
#define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS 3
#define KVM_PTE_LEAF_ATTR_LO_S1_AF BIT(10)
#define KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR GENMASK(5, 2)
#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R BIT(6)
#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W BIT(7)
#define KVM_PTE_LEAF_ATTR_LO_S2_SH GENMASK(9, 8)
#define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS 3
#define KVM_PTE_LEAF_ATTR_LO_S2_AF BIT(10)
#define KVM_PTE_LEAF_ATTR_HI GENMASK(63, 50)
#define KVM_PTE_LEAF_ATTR_HI_SW GENMASK(58, 55)
#define KVM_PTE_LEAF_ATTR_HI_S1_XN BIT(54)
#define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54)
#define KVM_PTE_LEAF_ATTR_HI_S1_GP BIT(50)
#define KVM_PTE_LEAF_ATTR_S2_PERMS (KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
KVM_PTE_LEAF_ATTR_HI_S2_XN)
#define KVM_INVALID_PTE_OWNER_MASK GENMASK(9, 2)
#define KVM_MAX_OWNER_ID 1
/*
* Used to indicate a pte for which a 'break-before-make' sequence is in
* progress.
*/
#define KVM_INVALID_PTE_LOCKED BIT(10)
static inline bool kvm_pte_valid(kvm_pte_t pte)
{
return pte & KVM_PTE_VALID;
}
static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
{
u64 pa;
if (kvm_lpa2_is_enabled()) { pa = pte & KVM_PTE_ADDR_MASK_LPA2;
pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50;
} else {
pa = pte & KVM_PTE_ADDR_MASK;
if (PAGE_SHIFT == 16)
pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
}
return pa;
}
static inline kvm_pte_t kvm_phys_to_pte(u64 pa)
{
kvm_pte_t pte;
if (kvm_lpa2_is_enabled()) { pte = pa & KVM_PTE_ADDR_MASK_LPA2;
pa &= GENMASK(51, 50);
pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50);
} else {
pte = pa & KVM_PTE_ADDR_MASK;
if (PAGE_SHIFT == 16) {
pa &= GENMASK(51, 48);
pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
}
}
return pte;
}
static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte)
{
return __phys_to_pfn(kvm_pte_to_phys(pte));
}
static inline u64 kvm_granule_shift(s8 level)
{
/* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */
return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
}
static inline u64 kvm_granule_size(s8 level)
{
return BIT(kvm_granule_shift(level));
}
static inline bool kvm_level_supports_block_mapping(s8 level)
{
return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
}
static inline u32 kvm_supported_block_sizes(void)
{
s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
u32 r = 0;
for (; level <= KVM_PGTABLE_LAST_LEVEL; level++)
r |= BIT(kvm_granule_shift(level));
return r;
}
static inline bool kvm_is_block_size_supported(u64 size)
{
bool is_power_of_two = IS_ALIGNED(size, size);
return is_power_of_two && (size & kvm_supported_block_sizes());
}
/**
* struct kvm_pgtable_mm_ops - Memory management callbacks.
* @zalloc_page: Allocate a single zeroed memory page.
* The @arg parameter can be used by the walker
* to pass a memcache. The initial refcount of
* the page is 1.
* @zalloc_pages_exact: Allocate an exact number of zeroed memory pages.
* The @size parameter is in bytes, and is rounded
* up to the next page boundary. The resulting
* allocation is physically contiguous.
* @free_pages_exact: Free an exact number of memory pages previously
* allocated by zalloc_pages_exact.
* @free_unlinked_table: Free an unlinked paging structure by unlinking and
* dropping references.
* @get_page: Increment the refcount on a page.
* @put_page: Decrement the refcount on a page. When the
* refcount reaches 0 the page is automatically
* freed.
* @page_count: Return the refcount of a page.
* @phys_to_virt: Convert a physical address into a virtual
* address mapped in the current context.
* @virt_to_phys: Convert a virtual address mapped in the current
* context into a physical address.
* @dcache_clean_inval_poc: Clean and invalidate the data cache to the PoC
* for the specified memory address range.
* @icache_inval_pou: Invalidate the instruction cache to the PoU
* for the specified memory address range.
*/
struct kvm_pgtable_mm_ops {
void* (*zalloc_page)(void *arg);
void* (*zalloc_pages_exact)(size_t size);
void (*free_pages_exact)(void *addr, size_t size);
void (*free_unlinked_table)(void *addr, s8 level);
void (*get_page)(void *addr);
void (*put_page)(void *addr);
int (*page_count)(void *addr);
void* (*phys_to_virt)(phys_addr_t phys);
phys_addr_t (*virt_to_phys)(void *addr);
void (*dcache_clean_inval_poc)(void *addr, size_t size);
void (*icache_inval_pou)(void *addr, size_t size);
};
/**
* enum kvm_pgtable_stage2_flags - Stage-2 page-table flags.
* @KVM_PGTABLE_S2_NOFWB: Don't enforce Normal-WB even if the CPUs have
* ARM64_HAS_STAGE2_FWB.
* @KVM_PGTABLE_S2_IDMAP: Only use identity mappings.
*/
enum kvm_pgtable_stage2_flags {
KVM_PGTABLE_S2_NOFWB = BIT(0),
KVM_PGTABLE_S2_IDMAP = BIT(1),
};
/**
* enum kvm_pgtable_prot - Page-table permissions and attributes.
* @KVM_PGTABLE_PROT_X: Execute permission.
* @KVM_PGTABLE_PROT_W: Write permission.
* @KVM_PGTABLE_PROT_R: Read permission.
* @KVM_PGTABLE_PROT_DEVICE: Device attributes.
* @KVM_PGTABLE_PROT_NORMAL_NC: Normal noncacheable attributes.
* @KVM_PGTABLE_PROT_SW0: Software bit 0.
* @KVM_PGTABLE_PROT_SW1: Software bit 1.
* @KVM_PGTABLE_PROT_SW2: Software bit 2.
* @KVM_PGTABLE_PROT_SW3: Software bit 3.
*/
enum kvm_pgtable_prot {
KVM_PGTABLE_PROT_X = BIT(0),
KVM_PGTABLE_PROT_W = BIT(1),
KVM_PGTABLE_PROT_R = BIT(2),
KVM_PGTABLE_PROT_DEVICE = BIT(3),
KVM_PGTABLE_PROT_NORMAL_NC = BIT(4),
KVM_PGTABLE_PROT_SW0 = BIT(55),
KVM_PGTABLE_PROT_SW1 = BIT(56),
KVM_PGTABLE_PROT_SW2 = BIT(57),
KVM_PGTABLE_PROT_SW3 = BIT(58),
};
#define KVM_PGTABLE_PROT_RW (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
#define KVM_PGTABLE_PROT_RWX (KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X)
#define PKVM_HOST_MEM_PROT KVM_PGTABLE_PROT_RWX
#define PKVM_HOST_MMIO_PROT KVM_PGTABLE_PROT_RW
#define PAGE_HYP KVM_PGTABLE_PROT_RW
#define PAGE_HYP_EXEC (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X)
#define PAGE_HYP_RO (KVM_PGTABLE_PROT_R)
#define PAGE_HYP_DEVICE (PAGE_HYP | KVM_PGTABLE_PROT_DEVICE)
typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
enum kvm_pgtable_prot prot);
/**
* enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
* @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid
* entries.
* @KVM_PGTABLE_WALK_TABLE_PRE: Visit table entries before their
* children.
* @KVM_PGTABLE_WALK_TABLE_POST: Visit table entries after their
* children.
* @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared
* with other software walkers.
* @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was
* invoked from a fault handler.
* @KVM_PGTABLE_WALK_SKIP_BBM_TLBI: Visit and update table entries
* without Break-before-make's
* TLB invalidation.
* @KVM_PGTABLE_WALK_SKIP_CMO: Visit and update table entries
* without Cache maintenance
* operations required.
*/
enum kvm_pgtable_walk_flags {
KVM_PGTABLE_WALK_LEAF = BIT(0),
KVM_PGTABLE_WALK_TABLE_PRE = BIT(1),
KVM_PGTABLE_WALK_TABLE_POST = BIT(2),
KVM_PGTABLE_WALK_SHARED = BIT(3),
KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4),
KVM_PGTABLE_WALK_SKIP_BBM_TLBI = BIT(5),
KVM_PGTABLE_WALK_SKIP_CMO = BIT(6),
};
struct kvm_pgtable_visit_ctx {
kvm_pte_t *ptep;
kvm_pte_t old;
void *arg;
struct kvm_pgtable_mm_ops *mm_ops;
u64 start;
u64 addr;
u64 end;
s8 level;
enum kvm_pgtable_walk_flags flags;
};
typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx,
enum kvm_pgtable_walk_flags visit);
static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx)
{
return ctx->flags & KVM_PGTABLE_WALK_SHARED;
}
/**
* struct kvm_pgtable_walker - Hook into a page-table walk.
* @cb: Callback function to invoke during the walk.
* @arg: Argument passed to the callback function.
* @flags: Bitwise-OR of flags to identify the entry types on which to
* invoke the callback function.
*/
struct kvm_pgtable_walker {
const kvm_pgtable_visitor_fn_t cb;
void * const arg;
const enum kvm_pgtable_walk_flags flags;
};
/*
* RCU cannot be used in a non-kernel context such as the hyp. As such, page
* table walkers used in hyp do not call into RCU and instead use other
* synchronization mechanisms (such as a spinlock).
*/
#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
typedef kvm_pte_t *kvm_pteref_t;
static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker,
kvm_pteref_t pteref)
{
return pteref;
}
static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
{
/*
* Due to the lack of RCU (or a similar protection scheme), only
* non-shared table walkers are allowed in the hypervisor.
*/
if (walker->flags & KVM_PGTABLE_WALK_SHARED)
return -EPERM;
return 0;
}
static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {}
static inline bool kvm_pgtable_walk_lock_held(void)
{
return true;
}
#else
typedef kvm_pte_t __rcu *kvm_pteref_t;
static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker,
kvm_pteref_t pteref)
{
return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED));
}
static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
{
if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_lock();
return 0;
}
static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker)
{
if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_unlock();
}
static inline bool kvm_pgtable_walk_lock_held(void)
{
return rcu_read_lock_held();
}
#endif
/**
* struct kvm_pgtable - KVM page-table.
* @ia_bits: Maximum input address size, in bits.
* @start_level: Level at which the page-table walk starts.
* @pgd: Pointer to the first top-level entry of the page-table.
* @mm_ops: Memory management callbacks.
* @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
* @flags: Stage-2 page-table flags.
* @force_pte_cb: Function that returns true if page level mappings must
* be used instead of block mappings.
*/
struct kvm_pgtable {
union {
struct rb_root_cached pkvm_mappings;
struct {
u32 ia_bits;
s8 start_level;
kvm_pteref_t pgd;
struct kvm_pgtable_mm_ops *mm_ops;
/* Stage-2 only */
enum kvm_pgtable_stage2_flags flags;
kvm_pgtable_force_pte_cb_t force_pte_cb;
};
};
struct kvm_s2_mmu *mmu;
};
/**
* kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table.
* @pgt: Uninitialised page-table structure to initialise.
* @va_bits: Maximum virtual address bits.
* @mm_ops: Memory management callbacks.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
struct kvm_pgtable_mm_ops *mm_ops);
/**
* kvm_pgtable_hyp_destroy() - Destroy an unused hypervisor stage-1 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_hyp_init().
*
* The page-table is assumed to be unreachable by any hardware walkers prior
* to freeing and therefore no TLB invalidation is performed.
*/
void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt);
/**
* kvm_pgtable_hyp_map() - Install a mapping in a hypervisor stage-1 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_hyp_init().
* @addr: Virtual address at which to place the mapping.
* @size: Size of the mapping.
* @phys: Physical address of the memory to map.
* @prot: Permissions and attributes for the mapping.
*
* The offset of @addr within a page is ignored, @size is rounded-up to
* the next page boundary and @phys is rounded-down to the previous page
* boundary.
*
* If device attributes are not explicitly requested in @prot, then the
* mapping will be normal, cacheable. Attempts to install a new mapping
* for a virtual address that is already mapped will be rejected with an
* error and a WARN().
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
enum kvm_pgtable_prot prot);
/**
* kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_hyp_init().
* @addr: Virtual address from which to remove the mapping.
* @size: Size of the mapping.
*
* The offset of @addr within a page is ignored, @size is rounded-up to
* the next page boundary and @phys is rounded-down to the previous page
* boundary.
*
* TLB invalidation is performed for each page-table entry cleared during the
* unmapping operation and the reference count for the page-table page
* containing the cleared entry is decremented, with unreferenced pages being
* freed. The unmapping operation will stop early if it encounters either an
* invalid page-table entry or a valid block mapping which maps beyond the range
* being unmapped.
*
* Return: Number of bytes unmapped, which may be 0.
*/
u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
/**
* kvm_get_vtcr() - Helper to construct VTCR_EL2
* @mmfr0: Sanitized value of SYS_ID_AA64MMFR0_EL1 register.
* @mmfr1: Sanitized value of SYS_ID_AA64MMFR1_EL1 register.
* @phys_shfit: Value to set in VTCR_EL2.T0SZ.
*
* The VTCR value is common across all the physical CPUs on the system.
* We use system wide sanitised values to fill in different fields,
* except for Hardware Management of Access Flags. HA Flag is set
* unconditionally on all CPUs, as it is safe to run with or without
* the feature and the bit is RES0 on CPUs that don't support it.
*
* Return: VTCR_EL2 value
*/
u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
/**
* kvm_pgtable_stage2_pgd_size() - Helper to compute size of a stage-2 PGD
* @vtcr: Content of the VTCR register.
*
* Return: the size (in bytes) of the stage-2 PGD
*/
size_t kvm_pgtable_stage2_pgd_size(u64 vtcr);
/**
* __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
* @pgt: Uninitialised page-table structure to initialise.
* @mmu: S2 MMU context for this S2 translation
* @mm_ops: Memory management callbacks.
* @flags: Stage-2 configuration flags.
* @force_pte_cb: Function that returns true if page level mappings must
* be used instead of block mappings.
*
* Return: 0 on success, negative error code on failure.
*/
int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
struct kvm_pgtable_mm_ops *mm_ops,
enum kvm_pgtable_stage2_flags flags,
kvm_pgtable_force_pte_cb_t force_pte_cb);
static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
struct kvm_pgtable_mm_ops *mm_ops)
{
return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL);
}
/**
* kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
*
* The page-table is assumed to be unreachable by any hardware walkers prior
* to freeing and therefore no TLB invalidation is performed.
*/
void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
/**
* kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
* @mm_ops: Memory management callbacks.
* @pgtable: Unlinked stage-2 paging structure to be freed.
* @level: Level of the stage-2 paging structure to be freed.
*
* The page-table is assumed to be unreachable by any hardware walkers prior to
* freeing and therefore no TLB invalidation is performed.
*/
void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
/**
* kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @phys: Physical address of the memory to map.
* @level: Starting level of the stage-2 paging structure to be created.
* @prot: Permissions and attributes for the mapping.
* @mc: Cache of pre-allocated and zeroed memory from which to allocate
* page-table pages.
* @force_pte: Force mappings to PAGE_SIZE granularity.
*
* Returns an unlinked page-table tree. This new page-table tree is
* not reachable (i.e., it is unlinked) from the root pgd and it's
* therefore unreachableby the hardware page-table walker. No TLB
* invalidation or CMOs are performed.
*
* If device attributes are not explicitly requested in @prot, then the
* mapping will be normal, cacheable.
*
* Return: The fully populated (unlinked) stage-2 paging structure, or
* an ERR_PTR(error) on failure.
*/
kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
u64 phys, s8 level,
enum kvm_pgtable_prot prot,
void *mc, bool force_pte);
/**
* kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address at which to place the mapping.
* @size: Size of the mapping.
* @phys: Physical address of the memory to map.
* @prot: Permissions and attributes for the mapping.
* @mc: Cache of pre-allocated and zeroed memory from which to allocate
* page-table pages.
* @flags: Flags to control the page-table walk (ex. a shared walk)
*
* The offset of @addr within a page is ignored, @size is rounded-up to
* the next page boundary and @phys is rounded-down to the previous page
* boundary.
*
* If device attributes are not explicitly requested in @prot, then the
* mapping will be normal, cacheable.
*
* Note that the update of a valid leaf PTE in this function will be aborted,
* if it's trying to recreate the exact same mapping or only change the access
* permissions. Instead, the vCPU will exit one more time from guest if still
* needed and then go through the path of relaxing permissions.
*
* Note that this function will both coalesce existing table entries and split
* existing block mappings, relying on page-faults to fault back areas outside
* of the new mapping lazily.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
u64 phys, enum kvm_pgtable_prot prot,
void *mc, enum kvm_pgtable_walk_flags flags);
/**
* kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to
* track ownership.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Base intermediate physical address to annotate.
* @size: Size of the annotated range.
* @mc: Cache of pre-allocated and zeroed memory from which to allocate
* page-table pages.
* @owner_id: Unique identifier for the owner of the page.
*
* By default, all page-tables are owned by identifier 0. This function can be
* used to mark portions of the IPA space as owned by other entities. When a
* stage 2 is used with identity-mappings, these annotations allow to use the
* page-table data structure as a simple rmap.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
void *mc, u8 owner_id);
/**
* kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address from which to remove the mapping.
* @size: Size of the mapping.
*
* The offset of @addr within a page is ignored and @size is rounded-up to
* the next page boundary.
*
* TLB invalidation is performed for each page-table entry cleared during the
* unmapping operation and the reference count for the page-table page
* containing the cleared entry is decremented, with unreferenced pages being
* freed. Unmapping a cacheable page will ensure that it is clean to the PoC if
* FWB is not supported by the CPU.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
/**
* kvm_pgtable_stage2_wrprotect() - Write-protect guest stage-2 address range
* without TLB invalidation.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address from which to write-protect,
* @size: Size of the range.
*
* The offset of @addr within a page is ignored and @size is rounded-up to
* the next page boundary.
*
* Note that it is the caller's responsibility to invalidate the TLB after
* calling this function to ensure that the updated permissions are visible
* to the CPUs.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
/**
* kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address to identify the page-table entry.
* @flags: Flags to control the page-table walk (ex. a shared walk)
*
* The offset of @addr within a page is ignored.
*
* If there is a valid, leaf page-table entry used to translate @addr, then
* set the access flag in that entry.
*/
void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
enum kvm_pgtable_walk_flags flags);
/**
* kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
* flag in a page-table entry.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address to identify the page-table entry.
* @size: Size of the address range to visit.
* @mkold: True if the access flag should be cleared.
*
* The offset of @addr within a page is ignored.
*
* Tests and conditionally clears the access flag for every valid, leaf
* page-table entry used to translate the range [@addr, @addr + @size).
*
* Note that it is the caller's responsibility to invalidate the TLB after
* calling this function to ensure that the updated permissions are visible
* to the CPUs.
*
* Return: True if any of the visited PTEs had the access flag set.
*/
bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
u64 size, bool mkold);
/**
* kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a
* page-table entry.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address to identify the page-table entry.
* @prot: Additional permissions to grant for the mapping.
* @flags: Flags to control the page-table walk (ex. a shared walk)
*
* The offset of @addr within a page is ignored.
*
* If there is a valid, leaf page-table entry used to translate @addr, then
* relax the permissions in that entry according to the read, write and
* execute permissions specified by @prot. No permissions are removed, and
* TLB invalidation is performed after updating the entry. Software bits cannot
* be set or cleared using kvm_pgtable_stage2_relax_perms().
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
enum kvm_pgtable_prot prot,
enum kvm_pgtable_walk_flags flags);
/**
* kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
* of Coherency for guest stage-2 address
* range.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
* @addr: Intermediate physical address from which to flush.
* @size: Size of the range.
*
* The offset of @addr within a page is ignored and @size is rounded-up to
* the next page boundary.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
/**
* kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing
* to PAGE_SIZE guest pages.
* @pgt: Page-table structure initialised by kvm_pgtable_stage2_init().
* @addr: Intermediate physical address from which to split.
* @size: Size of the range.
* @mc: Cache of pre-allocated and zeroed memory from which to allocate
* page-table pages.
*
* The function tries to split any level 1 or 2 entry that overlaps
* with the input range (given by @addr and @size).
*
* Return: 0 on success, negative error code on failure. Note that
* kvm_pgtable_stage2_split() is best effort: it tries to break as many
* blocks in the input range as allowed by @mc_capacity.
*/
int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
struct kvm_mmu_memory_cache *mc);
/**
* kvm_pgtable_walk() - Walk a page-table.
* @pgt: Page-table structure initialised by kvm_pgtable_*_init().
* @addr: Input address for the start of the walk.
* @size: Size of the range to walk.
* @walker: Walker callback description.
*
* The offset of @addr within a page is ignored and @size is rounded-up to
* the next page boundary.
*
* The walker will walk the page-table entries corresponding to the input
* address range specified, visiting entries according to the walker flags.
* Invalid entries are treated as leaf entries. The visited page table entry is
* reloaded after invoking the walker callback, allowing the walker to descend
* into a newly installed table.
*
* Returning a negative error code from the walker callback function will
* terminate the walk immediately with the same error code.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
struct kvm_pgtable_walker *walker);
/**
* kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry
* with its level.
* @pgt: Page-table structure initialised by kvm_pgtable_*_init()
* or a similar initialiser.
* @addr: Input address for the start of the walk.
* @ptep: Pointer to storage for the retrieved PTE.
* @level: Pointer to storage for the level of the retrieved PTE.
*
* The offset of @addr within a page is ignored.
*
* The walker will walk the page-table entries corresponding to the input
* address specified, retrieving the leaf corresponding to this address.
* Invalid entries are treated as leaf entries.
*
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
kvm_pte_t *ptep, s8 *level);
/**
* kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
* stage-2 Page-Table Entry.
* @pte: Page-table entry
*
* Return: protection attributes of the page-table entry in the enum
* kvm_pgtable_prot format.
*/
enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
/**
* kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1
* Page-Table Entry.
* @pte: Page-table entry
*
* Return: protection attributes of the page-table entry in the enum
* kvm_pgtable_prot format.
*/
enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
/**
* kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries
*
* @mmu: Stage-2 KVM MMU struct
* @addr: The base Intermediate physical address from which to invalidate
* @size: Size of the range from the base to invalidate
*/
void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
phys_addr_t addr, size_t size);
#endif /* __ARM64_KVM_PGTABLE_H__ */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RCULIST_NULLS_H
#define _LINUX_RCULIST_NULLS_H
#ifdef __KERNEL__
/*
* RCU-protected list version
*/
#include <linux/list_nulls.h>
#include <linux/rcupdate.h>
/**
* hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on the node return true after this. It is
* useful for RCU based read lockfree traversal if the writer side
* must know if the list entry is still hashed or already unhashed.
*
* In particular, it means that we can not poison the forward pointers
* that may still be used for walking the hash list and we can only
* zero the pprev pointer so list_unhashed() will return true after
* this.
*
* The caller must take whatever precautions are necessary (such as
* holding appropriate locks) to avoid racing with another
* list-mutation primitive, such as hlist_nulls_add_head_rcu() or
* hlist_nulls_del_rcu(), running on this same list. However, it is
* perfectly legal to run concurrently with the _rcu list-traversal
* primitives, such as hlist_nulls_for_each_entry_rcu().
*/
static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
{
if (!hlist_nulls_unhashed(n)) {
__hlist_nulls_del(n);
WRITE_ONCE(n->pprev, NULL);
}
}
/**
* hlist_nulls_first_rcu - returns the first element of the hash list.
* @head: the head of the list.
*/
#define hlist_nulls_first_rcu(head) \
(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
/**
* hlist_nulls_next_rcu - returns the element of the list after @node.
* @node: element of the list.
*/
#define hlist_nulls_next_rcu(node) \
(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
/**
* hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the hash list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry().
*/
static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
WRITE_ONCE(n->pprev, LIST_POISON2);
}
/**
* hlist_nulls_add_head_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_nulls,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *first = h->first;
WRITE_ONCE(n->next, first);
WRITE_ONCE(n->pprev, &h->first);
rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
if (!is_a_nulls(first))
WRITE_ONCE(first->pprev, &n->next);
}
/**
* hlist_nulls_add_tail_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_nulls,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *i, *last = NULL;
/* Note: write side code, so rcu accessors are not needed. */
for (i = h->first; !is_a_nulls(i); i = i->next)
last = i;
if (last) {
WRITE_ONCE(n->next, last->next);
n->pprev = &last->next;
rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
} else {
hlist_nulls_add_head_rcu(n, h);
}
}
/* after that hlist_nulls_del will work */
static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
{
n->pprev = &n->next;
n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
}
/**
* hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head of the list.
* @member: the name of the hlist_nulls_node within the struct.
*
* The barrier() is needed to make sure compiler doesn't cache first element [1],
* as this loop can be restarted [2]
* [1] Documentation/memory-barriers.txt around line 1533
* [2] Documentation/RCU/rculist_nulls.rst around line 146
*/
#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
/**
* hlist_nulls_for_each_entry_safe -
* iterate over list of given type safe against removal of list entry
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head of the list.
* @member: the name of the hlist_nulls_node within the struct.
*/
#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
#endif
#endif
/* SPDX-License-Identifier: GPL-2.0 */
/*
* include/linux/pagevec.h
*
* In many places it is efficient to batch an operation up against multiple
* folios. A folio_batch is a container which is used for that.
*/
#ifndef _LINUX_PAGEVEC_H
#define _LINUX_PAGEVEC_H
#include <linux/types.h>
/* 31 pointers + header align the folio_batch structure to a power of two */
#define PAGEVEC_SIZE 31
struct folio;
/**
* struct folio_batch - A collection of folios.
*
* The folio_batch is used to amortise the cost of retrieving and
* operating on a set of folios. The order of folios in the batch may be
* significant (eg delete_from_page_cache_batch()). Some users of the
* folio_batch store "exceptional" entries in it which can be removed
* by calling folio_batch_remove_exceptionals().
*/
struct folio_batch {
unsigned char nr;
unsigned char i;
bool percpu_pvec_drained;
struct folio *folios[PAGEVEC_SIZE];
};
/**
* folio_batch_init() - Initialise a batch of folios
* @fbatch: The folio batch.
*
* A freshly initialised folio_batch contains zero folios.
*/
static inline void folio_batch_init(struct folio_batch *fbatch)
{
fbatch->nr = 0;
fbatch->i = 0;
fbatch->percpu_pvec_drained = false;
}
static inline void folio_batch_reinit(struct folio_batch *fbatch)
{
fbatch->nr = 0;
fbatch->i = 0;
}
static inline unsigned int folio_batch_count(struct folio_batch *fbatch)
{
return fbatch->nr;
}
static inline unsigned int folio_batch_space(struct folio_batch *fbatch)
{
return PAGEVEC_SIZE - fbatch->nr;
}
/**
* folio_batch_add() - Add a folio to a batch.
* @fbatch: The folio batch.
* @folio: The folio to add.
*
* The folio is added to the end of the batch.
* The batch must have previously been initialised using folio_batch_init().
*
* Return: The number of slots still available.
*/
static inline unsigned folio_batch_add(struct folio_batch *fbatch,
struct folio *folio)
{
fbatch->folios[fbatch->nr++] = folio;
return folio_batch_space(fbatch);
}
/**
* folio_batch_next - Return the next folio to process.
* @fbatch: The folio batch being processed.
*
* Use this function to implement a queue of folios.
*
* Return: The next folio in the queue, or NULL if the queue is empty.
*/
static inline struct folio *folio_batch_next(struct folio_batch *fbatch)
{
if (fbatch->i == fbatch->nr)
return NULL;
return fbatch->folios[fbatch->i++];
}
void __folio_batch_release(struct folio_batch *pvec);
static inline void folio_batch_release(struct folio_batch *fbatch)
{
if (folio_batch_count(fbatch)) __folio_batch_release(fbatch);
}
void folio_batch_remove_exceptionals(struct folio_batch *fbatch);
#endif /* _LINUX_PAGEVEC_H */
/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _LINUX_MEMBLOCK_H
#define _LINUX_MEMBLOCK_H
/*
* Logical memory blocks.
*
* Copyright (C) 2001 Peter Bergner, IBM Corp.
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <asm/dma.h>
extern unsigned long max_low_pfn;
extern unsigned long min_low_pfn;
/*
* highest page
*/
extern unsigned long max_pfn;
/*
* highest possible page
*/
extern unsigned long long max_possible_pfn;
/**
* enum memblock_flags - definition of memory region attributes
* @MEMBLOCK_NONE: no special request
* @MEMBLOCK_HOTPLUG: memory region indicated in the firmware-provided memory
* map during early boot as hot(un)pluggable system RAM (e.g., memory range
* that might get hotunplugged later). With "movable_node" set on the kernel
* commandline, try keeping this memory region hotunpluggable. Does not apply
* to memblocks added ("hotplugged") after early boot.
* @MEMBLOCK_MIRROR: mirrored region
* @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as
* reserved in the memory map; refer to memblock_mark_nomap() description
* for further details
* @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added
* via a driver, and never indicated in the firmware-provided memory map as
* system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
* kernel resource tree.
* @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
* not initialized (only for reserved regions).
*/
enum memblock_flags {
MEMBLOCK_NONE = 0x0, /* No special request */
MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */
MEMBLOCK_MIRROR = 0x2, /* mirrored region */
MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */
MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */
MEMBLOCK_RSRV_NOINIT = 0x10, /* don't initialize struct pages */
};
/**
* struct memblock_region - represents a memory region
* @base: base address of the region
* @size: size of the region
* @flags: memory region attributes
* @nid: NUMA node id
*/
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
enum memblock_flags flags;
#ifdef CONFIG_NUMA
int nid;
#endif
};
/**
* struct memblock_type - collection of memory regions of certain type
* @cnt: number of regions
* @max: size of the allocated array
* @total_size: size of all regions
* @regions: array of regions
* @name: the memory type symbolic name
*/
struct memblock_type {
unsigned long cnt;
unsigned long max;
phys_addr_t total_size;
struct memblock_region *regions;
char *name;
};
/**
* struct memblock - memblock allocator metadata
* @bottom_up: is bottom up direction?
* @current_limit: physical address of the current allocation limit
* @memory: usable memory regions
* @reserved: reserved memory regions
*/
struct memblock {
bool bottom_up; /* is bottom up direction? */
phys_addr_t current_limit;
struct memblock_type memory;
struct memblock_type reserved;
};
extern struct memblock memblock;
#ifndef CONFIG_ARCH_KEEP_MEMBLOCK
#define __init_memblock __meminit
#define __initdata_memblock __meminitdata
void memblock_discard(void);
#else
#define __init_memblock
#define __initdata_memblock
static inline void memblock_discard(void) {}
#endif
void memblock_allow_resize(void);
int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid,
enum memblock_flags flags);
int memblock_add(phys_addr_t base, phys_addr_t size);
int memblock_remove(phys_addr_t base, phys_addr_t size);
int memblock_phys_free(phys_addr_t base, phys_addr_t size);
int memblock_reserve(phys_addr_t base, phys_addr_t size);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
#endif
void memblock_trim_memory(phys_addr_t align);
unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
phys_addr_t base2, phys_addr_t size2);
bool memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size);
bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
void memblock_free(void *ptr, size_t size);
void reset_all_zones_managed_pages(void);
/* Low level functions */
void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
void memblock_free_late(phys_addr_t base, phys_addr_t size);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
phys_addr_t *out_start,
phys_addr_t *out_end)
{
extern struct memblock_type physmem;
__next_mem_range(idx, NUMA_NO_NODE, MEMBLOCK_NONE, &physmem, type,
out_start, out_end, NULL);
}
/**
* for_each_physmem_range - iterate through physmem areas not included in type.
* @i: u64 used as loop variable
* @type: ptr to memblock_type which excludes from the iteration, can be %NULL
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*/
#define for_each_physmem_range(i, type, p_start, p_end) \
for (i = 0, __next_physmem_range(&i, type, p_start, p_end); \
i != (u64)ULLONG_MAX; \
__next_physmem_range(&i, type, p_start, p_end))
#endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */
/**
* __for_each_mem_range - iterate through memblock areas from type_a and not
* included in type_b. Or just type_a if type_b is NULL.
* @i: u64 used as loop variable
* @type_a: ptr to memblock_type to iterate
* @type_b: ptr to memblock_type which excludes from the iteration
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*/
#define __for_each_mem_range(i, type_a, type_b, nid, flags, \
p_start, p_end, p_nid) \
for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_mem_range(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid))
/**
* __for_each_mem_range_rev - reverse iterate through memblock areas from
* type_a and not included in type_b. Or just type_a if type_b is NULL.
* @i: u64 used as loop variable
* @type_a: ptr to memblock_type to iterate
* @type_b: ptr to memblock_type which excludes from the iteration
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*/
#define __for_each_mem_range_rev(i, type_a, type_b, nid, flags, \
p_start, p_end, p_nid) \
for (i = (u64)ULLONG_MAX, \
__next_mem_range_rev(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_mem_range_rev(&i, nid, flags, type_a, type_b, \
p_start, p_end, p_nid))
/**
* for_each_mem_range - iterate through memory areas.
* @i: u64 used as loop variable
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*/
#define for_each_mem_range(i, p_start, p_end) \
__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \
MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \
p_start, p_end, NULL)
/**
* for_each_mem_range_rev - reverse iterate through memblock areas from
* type_a and not included in type_b. Or just type_a if type_b is NULL.
* @i: u64 used as loop variable
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*/
#define for_each_mem_range_rev(i, p_start, p_end) \
__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\
p_start, p_end, NULL)
/**
* for_each_reserved_mem_range - iterate over all reserved memblock areas
* @i: u64 used as loop variable
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*
* Walks over reserved areas of memblock. Available as soon as memblock
* is initialized.
*/
#define for_each_reserved_mem_range(i, p_start, p_end) \
__for_each_mem_range(i, &memblock.reserved, NULL, NUMA_NO_NODE, \
MEMBLOCK_NONE, p_start, p_end, NULL)
static inline bool memblock_is_hotpluggable(struct memblock_region *m)
{
return m->flags & MEMBLOCK_HOTPLUG;
}
static inline bool memblock_is_mirror(struct memblock_region *m)
{
return m->flags & MEMBLOCK_MIRROR;
}
static inline bool memblock_is_nomap(struct memblock_region *m)
{
return m->flags & MEMBLOCK_NOMAP;
}
static inline bool memblock_is_reserved_noinit(struct memblock_region *m)
{
return m->flags & MEMBLOCK_RSRV_NOINIT;
}
static inline bool memblock_is_driver_managed(struct memblock_region *m)
{
return m->flags & MEMBLOCK_DRIVER_MANAGED;
}
int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
unsigned long *end_pfn);
void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid);
/**
* for_each_mem_pfn_range - early memory pfn range iterator
* @i: an integer used as loop variable
* @nid: node selector, %MAX_NUMNODES for all nodes
* @p_start: ptr to ulong for start pfn of the range, can be %NULL
* @p_end: ptr to ulong for end pfn of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over configured memory ranges.
*/
#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \
for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
unsigned long *out_spfn,
unsigned long *out_epfn);
/**
* for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific
* free memblock areas from a given point
* @i: u64 used as loop variable
* @zone: zone in which all of the memory blocks reside
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*
* Walks over free (memory && !reserved) areas of memblock in a specific
* zone, continuing from current position. Available as soon as memblock is
* initialized.
*/
#define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \
for (; i != U64_MAX; \
__next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
/**
* for_each_free_mem_range - iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over free (memory && !reserved) areas of memblock. Available as
* soon as memblock is initialized.
*/
#define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid) \
__for_each_mem_range(i, &memblock.memory, &memblock.reserved, \
nid, flags, p_start, p_end, p_nid)
/**
* for_each_free_mem_range_reverse - rev-iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over free (memory && !reserved) areas of memblock in reverse
* order. Available as soon as memblock is initialized.
*/
#define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end, \
p_nid) \
__for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \
nid, flags, p_start, p_end, p_nid)
int memblock_set_node(phys_addr_t base, phys_addr_t size,
struct memblock_type *type, int nid);
#ifdef CONFIG_NUMA
static inline void memblock_set_region_node(struct memblock_region *r, int nid)
{
r->nid = nid;
}
static inline int memblock_get_region_node(const struct memblock_region *r)
{
return r->nid;
}
#else
static inline void memblock_set_region_node(struct memblock_region *r, int nid)
{
}
static inline int memblock_get_region_node(const struct memblock_region *r)
{
return 0;
}
#endif /* CONFIG_NUMA */
/* Flags for memblock allocation APIs */
#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0)
#define MEMBLOCK_ALLOC_ACCESSIBLE 0
/*
* MEMBLOCK_ALLOC_NOLEAKTRACE avoids kmemleak tracing. It implies
* MEMBLOCK_ALLOC_ACCESSIBLE
*/
#define MEMBLOCK_ALLOC_NOLEAKTRACE 1
/* We are using top down, so it is safe to use 0 here */
#define MEMBLOCK_LOW_LIMIT 0
#ifndef ARCH_LOW_ADDRESS_LIMIT
#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL
#endif
phys_addr_t memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end);
phys_addr_t memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid, bool exact_nid);
phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
phys_addr_t align)
{
return memblock_phys_alloc_range(size, align, 0,
MEMBLOCK_ALLOC_ACCESSIBLE);
}
void *memblock_alloc_exact_nid_raw(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid);
void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid);
void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid);
static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
}
void *__memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
const char *func);
#define memblock_alloc_or_panic(size, align) \
__memblock_alloc_or_panic(size, align, __func__)
static inline void *memblock_alloc_raw(phys_addr_t size,
phys_addr_t align)
{
return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT,
MEMBLOCK_ALLOC_ACCESSIBLE,
NUMA_NO_NODE);
}
static inline void *memblock_alloc_from(phys_addr_t size,
phys_addr_t align,
phys_addr_t min_addr)
{
return memblock_alloc_try_nid(size, align, min_addr,
MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
}
static inline void *memblock_alloc_low(phys_addr_t size,
phys_addr_t align)
{
return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE);
}
static inline void *memblock_alloc_node(phys_addr_t size,
phys_addr_t align, int nid)
{
return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
MEMBLOCK_ALLOC_ACCESSIBLE, nid);
}
/*
* Set the allocation direction to bottom-up or top-down.
*/
static inline __init_memblock void memblock_set_bottom_up(bool enable)
{
memblock.bottom_up = enable;
}
/*
* Check if the allocation direction is bottom-up or not.
* if this is true, that said, memblock will allocate memory
* in bottom-up direction.
*/
static inline __init_memblock bool memblock_bottom_up(void)
{
return memblock.bottom_up;
}
phys_addr_t memblock_phys_mem_size(void);
phys_addr_t memblock_reserved_size(void);
unsigned long memblock_estimated_nr_free_pages(void);
phys_addr_t memblock_start_of_DRAM(void);
phys_addr_t memblock_end_of_DRAM(void);
void memblock_enforce_memory_limit(phys_addr_t memory_limit);
void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size);
void memblock_mem_limit_remove_map(phys_addr_t limit);
bool memblock_is_memory(phys_addr_t addr);
bool memblock_is_map_memory(phys_addr_t addr);
bool memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
bool memblock_is_reserved(phys_addr_t addr);
bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
void memblock_dump_all(void);
/**
* memblock_set_current_limit - Set the current allocation limit to allow
* limiting allocations to what is currently
* accessible during boot
* @limit: New limit value (physical address)
*/
void memblock_set_current_limit(phys_addr_t limit);
phys_addr_t memblock_get_current_limit(void);
/*
* pfn conversion functions
*
* While the memory MEMBLOCKs should always be page aligned, the reserved
* MEMBLOCKs may not be. This accessor attempt to provide a very clear
* idea of what they return for such non aligned MEMBLOCKs.
*/
/**
* memblock_region_memory_base_pfn - get the lowest pfn of the memory region
* @reg: memblock_region structure
*
* Return: the lowest pfn intersecting with the memory region
*/
static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
{
return PFN_UP(reg->base);
}
/**
* memblock_region_memory_end_pfn - get the end pfn of the memory region
* @reg: memblock_region structure
*
* Return: the end_pfn of the reserved region
*/
static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
{
return PFN_DOWN(reg->base + reg->size);
}
/**
* memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region
* @reg: memblock_region structure
*
* Return: the lowest pfn intersecting with the reserved region
*/
static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
{
return PFN_DOWN(reg->base);
}
/**
* memblock_region_reserved_end_pfn - get the end pfn of the reserved region
* @reg: memblock_region structure
*
* Return: the end_pfn of the reserved region
*/
static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
{
return PFN_UP(reg->base + reg->size);
}
/**
* for_each_mem_region - iterate over memory regions
* @region: loop variable
*/
#define for_each_mem_region(region) \
for (region = memblock.memory.regions; \
region < (memblock.memory.regions + memblock.memory.cnt); \
region++)
/**
* for_each_reserved_mem_region - itereate over reserved memory regions
* @region: loop variable
*/
#define for_each_reserved_mem_region(region) \
for (region = memblock.reserved.regions; \
region < (memblock.reserved.regions + memblock.reserved.cnt); \
region++)
extern void *alloc_large_system_hash(const char *tablename,
unsigned long bucketsize,
unsigned long numentries,
int scale,
int flags,
unsigned int *_hash_shift,
unsigned int *_hash_mask,
unsigned long low_limit,
unsigned long high_limit);
#define HASH_EARLY 0x00000001 /* Allocating during early boot? */
#define HASH_ZERO 0x00000002 /* Zero allocated hash table */
/* Only NUMA needs hash distribution. 64bit NUMA architectures have
* sufficient vmalloc space.
*/
#ifdef CONFIG_NUMA
#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT)
extern int hashdist; /* Distribute hashes across NUMA nodes? */
#else
#define hashdist (0)
#endif
#ifdef CONFIG_MEMTEST
void early_memtest(phys_addr_t start, phys_addr_t end);
void memtest_report_meminfo(struct seq_file *m);
#else
static inline void early_memtest(phys_addr_t start, phys_addr_t end) { }
static inline void memtest_report_meminfo(struct seq_file *m) { }
#endif
#endif /* _LINUX_MEMBLOCK_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/namespace.c
*
* (C) Copyright Al Viro 2000, 2001
*
* Based on code from fs/super.c, copyright Linus Torvalds and others.
* Heavily rewritten.
*/
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/capability.h>
#include <linux/mnt_namespace.h>
#include <linux/user_namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/idr.h>
#include <linux/init.h> /* init_rootfs */
#include <linux/fs_struct.h> /* get_fs_root et.al. */
#include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */
#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/task_work.h>
#include <linux/sched/task.h>
#include <uapi/linux/mount.h>
#include <linux/fs_context.h>
#include <linux/shmem_fs.h>
#include <linux/mnt_idmapping.h>
#include <linux/pidfs.h>
#include "pnode.h"
#include "internal.h"
/* Maximum number of mounts in a mount namespace */
static unsigned int sysctl_mount_max __read_mostly = 100000;
static unsigned int m_hash_mask __ro_after_init;
static unsigned int m_hash_shift __ro_after_init;
static unsigned int mp_hash_mask __ro_after_init;
static unsigned int mp_hash_shift __ro_after_init;
static __initdata unsigned long mhash_entries;
static int __init set_mhash_entries(char *str)
{
if (!str)
return 0;
mhash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("mhash_entries=", set_mhash_entries);
static __initdata unsigned long mphash_entries;
static int __init set_mphash_entries(char *str)
{
if (!str)
return 0;
mphash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("mphash_entries=", set_mphash_entries);
static u64 event;
static DEFINE_XARRAY_FLAGS(mnt_id_xa, XA_FLAGS_ALLOC);
static DEFINE_IDA(mnt_group_ida);
/* Don't allow confusion with old 32bit mount ID */
#define MNT_UNIQUE_ID_OFFSET (1ULL << 31)
static u64 mnt_id_ctr = MNT_UNIQUE_ID_OFFSET;
static struct hlist_head *mount_hashtable __ro_after_init;
static struct hlist_head *mountpoint_hashtable __ro_after_init;
static struct kmem_cache *mnt_cache __ro_after_init;
static DECLARE_RWSEM(namespace_sem);
static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
static DEFINE_SEQLOCK(mnt_ns_tree_lock);
#ifdef CONFIG_FSNOTIFY
LIST_HEAD(notify_list); /* protected by namespace_sem */
#endif
static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */
static LIST_HEAD(mnt_ns_list); /* protected by mnt_ns_tree_lock */
enum mount_kattr_flags_t {
MOUNT_KATTR_RECURSE = (1 << 0),
MOUNT_KATTR_IDMAP_REPLACE = (1 << 1),
};
struct mount_kattr {
unsigned int attr_set;
unsigned int attr_clr;
unsigned int propagation;
unsigned int lookup_flags;
enum mount_kattr_flags_t kflags;
struct user_namespace *mnt_userns;
struct mnt_idmap *mnt_idmap;
};
/* /sys/fs */
struct kobject *fs_kobj __ro_after_init;
EXPORT_SYMBOL_GPL(fs_kobj);
/*
* vfsmount lock may be taken for read to prevent changes to the
* vfsmount hash, ie. during mountpoint lookups or walking back
* up the tree.
*
* It should be taken for write in all cases where the vfsmount
* tree or hash is modified or when a vfsmount structure is modified.
*/
__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node)
{
if (!node)
return NULL;
return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node);
}
static int mnt_ns_cmp(struct rb_node *a, const struct rb_node *b)
{
struct mnt_namespace *ns_a = node_to_mnt_ns(a);
struct mnt_namespace *ns_b = node_to_mnt_ns(b);
u64 seq_a = ns_a->seq;
u64 seq_b = ns_b->seq;
if (seq_a < seq_b)
return -1;
if (seq_a > seq_b)
return 1;
return 0;
}
static inline void mnt_ns_tree_write_lock(void)
{
write_seqlock(&mnt_ns_tree_lock);
}
static inline void mnt_ns_tree_write_unlock(void)
{
write_sequnlock(&mnt_ns_tree_lock);
}
static void mnt_ns_tree_add(struct mnt_namespace *ns)
{
struct rb_node *node, *prev;
mnt_ns_tree_write_lock();
node = rb_find_add_rcu(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_cmp);
/*
* If there's no previous entry simply add it after the
* head and if there is add it after the previous entry.
*/
prev = rb_prev(&ns->mnt_ns_tree_node);
if (!prev)
list_add_rcu(&ns->mnt_ns_list, &mnt_ns_list);
else
list_add_rcu(&ns->mnt_ns_list, &node_to_mnt_ns(prev)->mnt_ns_list);
mnt_ns_tree_write_unlock();
WARN_ON_ONCE(node);
}
static void mnt_ns_release(struct mnt_namespace *ns)
{
/* keep alive for {list,stat}mount() */
if (refcount_dec_and_test(&ns->passive)) {
fsnotify_mntns_delete(ns);
put_user_ns(ns->user_ns);
kfree(ns);
}
}
DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T))
static void mnt_ns_release_rcu(struct rcu_head *rcu)
{
mnt_ns_release(container_of(rcu, struct mnt_namespace, mnt_ns_rcu));
}
static void mnt_ns_tree_remove(struct mnt_namespace *ns)
{
/* remove from global mount namespace list */
if (!is_anon_ns(ns)) {
mnt_ns_tree_write_lock();
rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree);
list_bidir_del_rcu(&ns->mnt_ns_list);
mnt_ns_tree_write_unlock();
}
call_rcu(&ns->mnt_ns_rcu, mnt_ns_release_rcu);
}
static int mnt_ns_find(const void *key, const struct rb_node *node)
{
const u64 mnt_ns_id = *(u64 *)key;
const struct mnt_namespace *ns = node_to_mnt_ns(node);
if (mnt_ns_id < ns->seq)
return -1;
if (mnt_ns_id > ns->seq)
return 1;
return 0;
}
/*
* Lookup a mount namespace by id and take a passive reference count. Taking a
* passive reference means the mount namespace can be emptied if e.g., the last
* task holding an active reference exits. To access the mounts of the
* namespace the @namespace_sem must first be acquired. If the namespace has
* already shut down before acquiring @namespace_sem, {list,stat}mount() will
* see that the mount rbtree of the namespace is empty.
*
* Note the lookup is lockless protected by a sequence counter. We only
* need to guard against false negatives as false positives aren't
* possible. So if we didn't find a mount namespace and the sequence
* counter has changed we need to retry. If the sequence counter is
* still the same we know the search actually failed.
*/
static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id)
{
struct mnt_namespace *ns;
struct rb_node *node;
unsigned int seq;
guard(rcu)();
do {
seq = read_seqbegin(&mnt_ns_tree_lock);
node = rb_find_rcu(&mnt_ns_id, &mnt_ns_tree, mnt_ns_find);
if (node)
break;
} while (read_seqretry(&mnt_ns_tree_lock, seq));
if (!node)
return NULL;
/*
* The last reference count is put with RCU delay so we can
* unconditonally acquire a reference here.
*/
ns = node_to_mnt_ns(node);
refcount_inc(&ns->passive);
return ns;
}
static inline void lock_mount_hash(void)
{
write_seqlock(&mount_lock);
}
static inline void unlock_mount_hash(void)
{
write_sequnlock(&mount_lock);
}
static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
tmp = tmp + (tmp >> m_hash_shift);
return &mount_hashtable[tmp & m_hash_mask];
}
static inline struct hlist_head *mp_hash(struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
tmp = tmp + (tmp >> mp_hash_shift);
return &mountpoint_hashtable[tmp & mp_hash_mask];
}
static int mnt_alloc_id(struct mount *mnt)
{
int res;
xa_lock(&mnt_id_xa);
res = __xa_alloc(&mnt_id_xa, &mnt->mnt_id, mnt, XA_LIMIT(1, INT_MAX), GFP_KERNEL);
if (!res)
mnt->mnt_id_unique = ++mnt_id_ctr;
xa_unlock(&mnt_id_xa);
return res;
}
static void mnt_free_id(struct mount *mnt)
{
xa_erase(&mnt_id_xa, mnt->mnt_id);
}
/*
* Allocate a new peer group ID
*/
static int mnt_alloc_group_id(struct mount *mnt)
{
int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL);
if (res < 0)
return res;
mnt->mnt_group_id = res;
return 0;
}
/*
* Release a peer group ID
*/
void mnt_release_group_id(struct mount *mnt)
{
ida_free(&mnt_group_ida, mnt->mnt_group_id);
mnt->mnt_group_id = 0;
}
/*
* vfsmount lock must be held for read
*/
static inline void mnt_add_count(struct mount *mnt, int n)
{
#ifdef CONFIG_SMP
this_cpu_add(mnt->mnt_pcp->mnt_count, n);
#else
preempt_disable();
mnt->mnt_count += n;
preempt_enable();
#endif
}
/*
* vfsmount lock must be held for write
*/
int mnt_get_count(struct mount *mnt)
{
#ifdef CONFIG_SMP
int count = 0;
int cpu;
for_each_possible_cpu(cpu) {
count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count;
}
return count;
#else
return mnt->mnt_count;
#endif
}
static struct mount *alloc_vfsmnt(const char *name)
{
struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
if (mnt) {
int err;
err = mnt_alloc_id(mnt);
if (err)
goto out_free_cache;
if (name) {
mnt->mnt_devname = kstrdup_const(name,
GFP_KERNEL_ACCOUNT);
if (!mnt->mnt_devname)
goto out_free_id;
}
#ifdef CONFIG_SMP
mnt->mnt_pcp = alloc_percpu(struct mnt_pcp);
if (!mnt->mnt_pcp)
goto out_free_devname;
this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
#else
mnt->mnt_count = 1;
mnt->mnt_writers = 0;
#endif
INIT_HLIST_NODE(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_list);
INIT_LIST_HEAD(&mnt->mnt_expire);
INIT_LIST_HEAD(&mnt->mnt_share);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
INIT_HLIST_NODE(&mnt->mnt_mp_list);
INIT_LIST_HEAD(&mnt->mnt_umounting);
INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
RB_CLEAR_NODE(&mnt->mnt_node);
mnt->mnt.mnt_idmap = &nop_mnt_idmap;
}
return mnt;
#ifdef CONFIG_SMP
out_free_devname:
kfree_const(mnt->mnt_devname);
#endif
out_free_id:
mnt_free_id(mnt);
out_free_cache:
kmem_cache_free(mnt_cache, mnt);
return NULL;
}
/*
* Most r/o checks on a fs are for operations that take
* discrete amounts of time, like a write() or unlink().
* We must keep track of when those operations start
* (for permission checks) and when they end, so that
* we can determine when writes are able to occur to
* a filesystem.
*/
/*
* __mnt_is_readonly: check whether a mount is read-only
* @mnt: the mount to check for its write status
*
* This shouldn't be used directly ouside of the VFS.
* It does not guarantee that the filesystem will stay
* r/w, just that it is right *now*. This can not and
* should not be used in place of IS_RDONLY(inode).
* mnt_want/drop_write() will _keep_ the filesystem
* r/w.
*/
bool __mnt_is_readonly(struct vfsmount *mnt)
{
return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb);
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);
static inline void mnt_inc_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
this_cpu_inc(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers++;
#endif
}
static inline void mnt_dec_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
this_cpu_dec(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers--;
#endif
}
static unsigned int mnt_get_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
unsigned int count = 0;
int cpu;
for_each_possible_cpu(cpu) {
count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers;
}
return count;
#else
return mnt->mnt_writers;
#endif
}
static int mnt_is_readonly(struct vfsmount *mnt)
{
if (READ_ONCE(mnt->mnt_sb->s_readonly_remount))
return 1;
/*
* The barrier pairs with the barrier in sb_start_ro_state_change()
* making sure if we don't see s_readonly_remount set yet, we also will
* not see any superblock / mount flag changes done by remount.
* It also pairs with the barrier in sb_end_ro_state_change()
* assuring that if we see s_readonly_remount already cleared, we will
* see the values of superblock / mount flags updated by remount.
*/
smp_rmb();
return __mnt_is_readonly(mnt);
}
/*
* Most r/o & frozen checks on a fs are for operations that take discrete
* amounts of time, like a write() or unlink(). We must keep track of when
* those operations start (for permission checks) and when they end, so that we
* can determine when writes are able to occur to a filesystem.
*/
/**
* mnt_get_write_access - get write access to a mount without freeze protection
* @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is about to be performed to
* it, and makes sure that writes are allowed (mnt it read-write) before
* returning success. This operation does not protect against filesystem being
* frozen. When the write operation is finished, mnt_put_write_access() must be
* called. This is effectively a refcount.
*/
int mnt_get_write_access(struct vfsmount *m)
{
struct mount *mnt = real_mount(m);
int ret = 0;
preempt_disable();
mnt_inc_writers(mnt);
/*
* The store to mnt_inc_writers must be visible before we pass
* MNT_WRITE_HOLD loop below, so that the slowpath can see our
* incremented count after it has set MNT_WRITE_HOLD.
*/
smp_mb();
might_lock(&mount_lock.lock);
while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
cpu_relax();
} else {
/*
* This prevents priority inversion, if the task
* setting MNT_WRITE_HOLD got preempted on a remote
* CPU, and it prevents life lock if the task setting
* MNT_WRITE_HOLD has a lower priority and is bound to
* the same CPU as the task that is spinning here.
*/
preempt_enable();
lock_mount_hash();
unlock_mount_hash();
preempt_disable();
}
}
/*
* The barrier pairs with the barrier sb_start_ro_state_change() making
* sure that if we see MNT_WRITE_HOLD cleared, we will also see
* s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in
* mnt_is_readonly() and bail in case we are racing with remount
* read-only.
*/
smp_rmb();
if (mnt_is_readonly(m)) { mnt_dec_writers(mnt);
ret = -EROFS;
}
preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(mnt_get_write_access);
/**
* mnt_want_write - get write access to a mount
* @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is about to be performed to
* it, and makes sure that writes are allowed (mount is read-write, filesystem
* is not frozen) before returning success. When the write operation is
* finished, mnt_drop_write() must be called. This is effectively a refcount.
*/
int mnt_want_write(struct vfsmount *m)
{
int ret;
sb_start_write(m->mnt_sb);
ret = mnt_get_write_access(m);
if (ret) sb_end_write(m->mnt_sb);
return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write);
/**
* mnt_get_write_access_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
* This is like mnt_get_write_access, but if @file is already open for write it
* skips incrementing mnt_writers (since the open file already has a reference)
* and instead only does the check for emergency r/o remounts. This must be
* paired with mnt_put_write_access_file.
*/
int mnt_get_write_access_file(struct file *file)
{
if (file->f_mode & FMODE_WRITER) {
/*
* Superblock may have become readonly while there are still
* writable fd's, e.g. due to a fs error with errors=remount-ro
*/
if (__mnt_is_readonly(file->f_path.mnt))
return -EROFS;
return 0;
}
return mnt_get_write_access(file->f_path.mnt);
}
/**
* mnt_want_write_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
* This is like mnt_want_write, but if the file is already open for writing it
* skips incrementing mnt_writers (since the open file already has a reference)
* and instead only does the freeze protection and the check for emergency r/o
* remounts. This must be paired with mnt_drop_write_file.
*/
int mnt_want_write_file(struct file *file)
{
int ret;
sb_start_write(file_inode(file)->i_sb);
ret = mnt_get_write_access_file(file); if (ret)
sb_end_write(file_inode(file)->i_sb);
return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write_file);
/**
* mnt_put_write_access - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* Tells the low-level filesystem that we are done
* performing writes to it. Must be matched with
* mnt_get_write_access() call above.
*/
void mnt_put_write_access(struct vfsmount *mnt)
{
preempt_disable();
mnt_dec_writers(real_mount(mnt)); preempt_enable();
}
EXPORT_SYMBOL_GPL(mnt_put_write_access);
/**
* mnt_drop_write - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* Tells the low-level filesystem that we are done performing writes to it and
* also allows filesystem to be frozen again. Must be matched with
* mnt_want_write() call above.
*/
void mnt_drop_write(struct vfsmount *mnt)
{
mnt_put_write_access(mnt);
sb_end_write(mnt->mnt_sb);
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
void mnt_put_write_access_file(struct file *file)
{ if (!(file->f_mode & FMODE_WRITER)) mnt_put_write_access(file->f_path.mnt);
}
void mnt_drop_write_file(struct file *file)
{ mnt_put_write_access_file(file);
sb_end_write(file_inode(file)->i_sb);
}
EXPORT_SYMBOL(mnt_drop_write_file);
/**
* mnt_hold_writers - prevent write access to the given mount
* @mnt: mnt to prevent write access to
*
* Prevents write access to @mnt if there are no active writers for @mnt.
* This function needs to be called and return successfully before changing
* properties of @mnt that need to remain stable for callers with write access
* to @mnt.
*
* After this functions has been called successfully callers must pair it with
* a call to mnt_unhold_writers() in order to stop preventing write access to
* @mnt.
*
* Context: This function expects lock_mount_hash() to be held serializing
* setting MNT_WRITE_HOLD.
* Return: On success 0 is returned.
* On error, -EBUSY is returned.
*/
static inline int mnt_hold_writers(struct mount *mnt)
{
mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
/*
* After storing MNT_WRITE_HOLD, we'll read the counters. This store
* should be visible before we do.
*/
smp_mb();
/*
* With writers on hold, if this value is zero, then there are
* definitely no active writers (although held writers may subsequently
* increment the count, they'll have to wait, and decrement it after
* seeing MNT_READONLY).
*
* It is OK to have counter incremented on one CPU and decremented on
* another: the sum will add up correctly. The danger would be when we
* sum up each counter, if we read a counter before it is incremented,
* but then read another CPU's count which it has been subsequently
* decremented from -- we would see more decrements than we should.
* MNT_WRITE_HOLD protects against this scenario, because
* mnt_want_write first increments count, then smp_mb, then spins on
* MNT_WRITE_HOLD, so it can't be decremented by another CPU while
* we're counting up here.
*/
if (mnt_get_writers(mnt) > 0)
return -EBUSY;
return 0;
}
/**
* mnt_unhold_writers - stop preventing write access to the given mount
* @mnt: mnt to stop preventing write access to
*
* Stop preventing write access to @mnt allowing callers to gain write access
* to @mnt again.
*
* This function can only be called after a successful call to
* mnt_hold_writers().
*
* Context: This function expects lock_mount_hash() to be held.
*/
static inline void mnt_unhold_writers(struct mount *mnt)
{
/*
* MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
* that become unheld will see MNT_READONLY.
*/
smp_wmb();
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
}
static int mnt_make_readonly(struct mount *mnt)
{
int ret;
ret = mnt_hold_writers(mnt);
if (!ret)
mnt->mnt.mnt_flags |= MNT_READONLY;
mnt_unhold_writers(mnt);
return ret;
}
int sb_prepare_remount_readonly(struct super_block *sb)
{
struct mount *mnt;
int err = 0;
/* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */
if (atomic_long_read(&sb->s_remove_count))
return -EBUSY;
lock_mount_hash();
list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
if (!(mnt->mnt.mnt_flags & MNT_READONLY)) {
err = mnt_hold_writers(mnt);
if (err)
break;
}
}
if (!err && atomic_long_read(&sb->s_remove_count))
err = -EBUSY;
if (!err)
sb_start_ro_state_change(sb);
list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
}
unlock_mount_hash();
return err;
}
static void free_vfsmnt(struct mount *mnt)
{
mnt_idmap_put(mnt_idmap(&mnt->mnt));
kfree_const(mnt->mnt_devname);
#ifdef CONFIG_SMP
free_percpu(mnt->mnt_pcp);
#endif
kmem_cache_free(mnt_cache, mnt);
}
static void delayed_free_vfsmnt(struct rcu_head *head)
{
free_vfsmnt(container_of(head, struct mount, mnt_rcu));
}
/* call under rcu_read_lock */
int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
{
struct mount *mnt;
if (read_seqretry(&mount_lock, seq))
return 1;
if (bastard == NULL)
return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
smp_mb(); // see mntput_no_expire()
if (likely(!read_seqretry(&mount_lock, seq)))
return 0;
if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
mnt_add_count(mnt, -1);
return 1;
}
lock_mount_hash();
if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
mnt_add_count(mnt, -1);
unlock_mount_hash();
return 1;
}
unlock_mount_hash();
/* caller will mntput() */
return -1;
}
/* call under rcu_read_lock */
static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
{
int res = __legitimize_mnt(bastard, seq);
if (likely(!res))
return true;
if (unlikely(res < 0)) {
rcu_read_unlock();
mntput(bastard); rcu_read_lock();
}
return false;
}
/**
* __lookup_mnt - find first child mount
* @mnt: parent mount
* @dentry: mountpoint
*
* If @mnt has a child mount @c mounted @dentry find and return it.
*
* Note that the child mount @c need not be unique. There are cases
* where shadow mounts are created. For example, during mount
* propagation when a source mount @mnt whose root got overmounted by a
* mount @o after path lookup but before @namespace_sem could be
* acquired gets copied and propagated. So @mnt gets copied including
* @o. When @mnt is propagated to a destination mount @d that already
* has another mount @n mounted at the same mountpoint then the source
* mount @mnt will be tucked beneath @n, i.e., @n will be mounted on
* @mnt and @mnt mounted on @d. Now both @n and @o are mounted at @mnt
* on @dentry.
*
* Return: The first child of @mnt mounted @dentry or NULL.
*/
struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
struct hlist_head *head = m_hash(mnt, dentry);
struct mount *p;
hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
return p;
return NULL;
}
/*
* lookup_mnt - Return the first child mount mounted at path
*
* "First" means first mounted chronologically. If you create the
* following mounts:
*
* mount /dev/sda1 /mnt
* mount /dev/sda2 /mnt
* mount /dev/sda3 /mnt
*
* Then lookup_mnt() on the base /mnt dentry in the root mount will
* return successively the root dentry and vfsmount of /dev/sda1, then
* /dev/sda2, then /dev/sda3, then NULL.
*
* lookup_mnt takes a reference to the found vfsmount.
*/
struct vfsmount *lookup_mnt(const struct path *path)
{
struct mount *child_mnt;
struct vfsmount *m;
unsigned seq;
rcu_read_lock();
do {
seq = read_seqbegin(&mount_lock);
child_mnt = __lookup_mnt(path->mnt, path->dentry);
m = child_mnt ? &child_mnt->mnt : NULL;
} while (!legitimize_mnt(m, seq)); rcu_read_unlock();
return m;
}
/*
* __is_local_mountpoint - Test to see if dentry is a mountpoint in the
* current mount namespace.
*
* The common case is dentries are not mountpoints at all and that
* test is handled inline. For the slow case when we are actually
* dealing with a mountpoint of some kind, walk through all of the
* mounts in the current mount namespace and test to see if the dentry
* is a mountpoint.
*
* The mount_hashtable is not usable in the context because we
* need to identify all mounts that may be in the current mount
* namespace not just a mount that happens to have some specified
* parent mount.
*/
bool __is_local_mountpoint(struct dentry *dentry)
{
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
struct mount *mnt, *n;
bool is_covered = false;
down_read(&namespace_sem);
rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
is_covered = (mnt->mnt_mountpoint == dentry);
if (is_covered)
break;
}
up_read(&namespace_sem);
return is_covered;
}
static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
{
struct hlist_head *chain = mp_hash(dentry);
struct mountpoint *mp;
hlist_for_each_entry(mp, chain, m_hash) {
if (mp->m_dentry == dentry) {
mp->m_count++;
return mp;
}
}
return NULL;
}
static struct mountpoint *get_mountpoint(struct dentry *dentry)
{
struct mountpoint *mp, *new = NULL;
int ret;
if (d_mountpoint(dentry)) {
/* might be worth a WARN_ON() */
if (d_unlinked(dentry))
return ERR_PTR(-ENOENT);
mountpoint:
read_seqlock_excl(&mount_lock);
mp = lookup_mountpoint(dentry);
read_sequnlock_excl(&mount_lock);
if (mp)
goto done;
}
if (!new)
new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
if (!new)
return ERR_PTR(-ENOMEM);
/* Exactly one processes may set d_mounted */
ret = d_set_mounted(dentry);
/* Someone else set d_mounted? */
if (ret == -EBUSY)
goto mountpoint;
/* The dentry is not available as a mountpoint? */
mp = ERR_PTR(ret);
if (ret)
goto done;
/* Add the new mountpoint to the hash table */
read_seqlock_excl(&mount_lock);
new->m_dentry = dget(dentry);
new->m_count = 1;
hlist_add_head(&new->m_hash, mp_hash(dentry));
INIT_HLIST_HEAD(&new->m_list);
read_sequnlock_excl(&mount_lock);
mp = new;
new = NULL;
done:
kfree(new);
return mp;
}
/*
* vfsmount lock must be held. Additionally, the caller is responsible
* for serializing calls for given disposal list.
*/
static void __put_mountpoint(struct mountpoint *mp, struct list_head *list)
{
if (!--mp->m_count) {
struct dentry *dentry = mp->m_dentry;
BUG_ON(!hlist_empty(&mp->m_list));
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_MOUNTED;
spin_unlock(&dentry->d_lock);
dput_to_list(dentry, list);
hlist_del(&mp->m_hash);
kfree(mp);
}
}
/* called with namespace_lock and vfsmount lock */
static void put_mountpoint(struct mountpoint *mp)
{
__put_mountpoint(mp, &ex_mountpoints);
}
static inline int check_mnt(struct mount *mnt)
{
return mnt->mnt_ns == current->nsproxy->mnt_ns;
}
static inline bool check_anonymous_mnt(struct mount *mnt)
{
u64 seq;
if (!is_anon_ns(mnt->mnt_ns))
return false;
seq = mnt->mnt_ns->seq_origin;
return !seq || (seq == current->nsproxy->mnt_ns->seq);
}
/*
* vfsmount lock must be held for write
*/
static void touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns) {
ns->event = ++event;
wake_up_interruptible(&ns->poll);
}
}
/*
* vfsmount lock must be held for write
*/
static void __touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns && ns->event != event) {
ns->event = event;
wake_up_interruptible(&ns->poll);
}
}
/*
* vfsmount lock must be held for write
*/
static struct mountpoint *unhash_mnt(struct mount *mnt)
{
struct mountpoint *mp;
mnt->mnt_parent = mnt;
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
list_del_init(&mnt->mnt_child);
hlist_del_init_rcu(&mnt->mnt_hash);
hlist_del_init(&mnt->mnt_mp_list);
mp = mnt->mnt_mp;
mnt->mnt_mp = NULL;
return mp;
}
/*
* vfsmount lock must be held for write
*/
static void umount_mnt(struct mount *mnt)
{
put_mountpoint(unhash_mnt(mnt));
}
/*
* vfsmount lock must be held for write
*/
void mnt_set_mountpoint(struct mount *mnt,
struct mountpoint *mp,
struct mount *child_mnt)
{
mp->m_count++;
mnt_add_count(mnt, 1); /* essentially, that's mntget */
child_mnt->mnt_mountpoint = mp->m_dentry;
child_mnt->mnt_parent = mnt;
child_mnt->mnt_mp = mp;
hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
}
/**
* mnt_set_mountpoint_beneath - mount a mount beneath another one
*
* @new_parent: the source mount
* @top_mnt: the mount beneath which @new_parent is mounted
* @new_mp: the new mountpoint of @top_mnt on @new_parent
*
* Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and
* parent @top_mnt->mnt_parent and mount it on top of @new_parent at
* @new_mp. And mount @new_parent on the old parent and old
* mountpoint of @top_mnt.
*
* Context: This function expects namespace_lock() and lock_mount_hash()
* to have been acquired in that order.
*/
static void mnt_set_mountpoint_beneath(struct mount *new_parent,
struct mount *top_mnt,
struct mountpoint *new_mp)
{
struct mount *old_top_parent = top_mnt->mnt_parent;
struct mountpoint *old_top_mp = top_mnt->mnt_mp;
mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent);
mnt_change_mountpoint(new_parent, new_mp, top_mnt);
}
static void __attach_mnt(struct mount *mnt, struct mount *parent)
{
hlist_add_head_rcu(&mnt->mnt_hash,
m_hash(&parent->mnt, mnt->mnt_mountpoint));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
}
/**
* attach_mnt - mount a mount, attach to @mount_hashtable and parent's
* list of child mounts
* @parent: the parent
* @mnt: the new mount
* @mp: the new mountpoint
* @beneath: whether to mount @mnt beneath or on top of @parent
*
* If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt
* to @parent's child mount list and to @mount_hashtable.
*
* If @beneath is true, remove @mnt from its current parent and
* mountpoint and mount it on @mp on @parent, and mount @parent on the
* old parent and old mountpoint of @mnt. Finally, attach @parent to
* @mnt_hashtable and @parent->mnt_parent->mnt_mounts.
*
* Note, when __attach_mnt() is called @mnt->mnt_parent already points
* to the correct parent.
*
* Context: This function expects namespace_lock() and lock_mount_hash()
* to have been acquired in that order.
*/
static void attach_mnt(struct mount *mnt, struct mount *parent,
struct mountpoint *mp, bool beneath)
{
if (beneath)
mnt_set_mountpoint_beneath(mnt, parent, mp);
else
mnt_set_mountpoint(parent, mp, mnt);
/*
* Note, @mnt->mnt_parent has to be used. If @mnt was mounted
* beneath @parent then @mnt will need to be attached to
* @parent's old parent, not @parent. IOW, @mnt->mnt_parent
* isn't the same mount as @parent.
*/
__attach_mnt(mnt, mnt->mnt_parent);
}
void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
{
struct mountpoint *old_mp = mnt->mnt_mp;
struct mount *old_parent = mnt->mnt_parent;
list_del_init(&mnt->mnt_child);
hlist_del_init(&mnt->mnt_mp_list);
hlist_del_init_rcu(&mnt->mnt_hash);
attach_mnt(mnt, parent, mp, false);
put_mountpoint(old_mp);
mnt_add_count(old_parent, -1);
}
static inline struct mount *node_to_mount(struct rb_node *node)
{
return node ? rb_entry(node, struct mount, mnt_node) : NULL;
}
static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
{
struct rb_node **link = &ns->mounts.rb_node;
struct rb_node *parent = NULL;
bool mnt_first_node = true, mnt_last_node = true;
WARN_ON(mnt_ns_attached(mnt));
mnt->mnt_ns = ns;
while (*link) {
parent = *link;
if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) {
link = &parent->rb_left;
mnt_last_node = false;
} else {
link = &parent->rb_right;
mnt_first_node = false;
}
}
if (mnt_last_node)
ns->mnt_last_node = &mnt->mnt_node;
if (mnt_first_node)
ns->mnt_first_node = &mnt->mnt_node;
rb_link_node(&mnt->mnt_node, parent, link);
rb_insert_color(&mnt->mnt_node, &ns->mounts);
mnt_notify_add(mnt);
}
/*
* vfsmount lock must be held for write
*/
static void commit_tree(struct mount *mnt)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m;
LIST_HEAD(head);
struct mnt_namespace *n = parent->mnt_ns;
BUG_ON(parent == mnt);
list_add_tail(&head, &mnt->mnt_list);
while (!list_empty(&head)) {
m = list_first_entry(&head, typeof(*m), mnt_list);
list_del(&m->mnt_list);
mnt_add_to_ns(n, m);
}
n->nr_mounts += n->pending_mounts;
n->pending_mounts = 0;
__attach_mnt(mnt, parent);
touch_mnt_namespace(n);
}
static struct mount *next_mnt(struct mount *p, struct mount *root)
{
struct list_head *next = p->mnt_mounts.next;
if (next == &p->mnt_mounts) {
while (1) {
if (p == root)
return NULL;
next = p->mnt_child.next;
if (next != &p->mnt_parent->mnt_mounts)
break;
p = p->mnt_parent;
}
}
return list_entry(next, struct mount, mnt_child);
}
static struct mount *skip_mnt_tree(struct mount *p)
{
struct list_head *prev = p->mnt_mounts.prev;
while (prev != &p->mnt_mounts) {
p = list_entry(prev, struct mount, mnt_child);
prev = p->mnt_mounts.prev;
}
return p;
}
/**
* vfs_create_mount - Create a mount for a configured superblock
* @fc: The configuration context with the superblock attached
*
* Create a mount to an already configured superblock. If necessary, the
* caller should invoke vfs_get_tree() before calling this.
*
* Note that this does not attach the mount to anything.
*/
struct vfsmount *vfs_create_mount(struct fs_context *fc)
{
struct mount *mnt;
if (!fc->root)
return ERR_PTR(-EINVAL);
mnt = alloc_vfsmnt(fc->source ?: "none");
if (!mnt)
return ERR_PTR(-ENOMEM);
if (fc->sb_flags & SB_KERNMOUNT)
mnt->mnt.mnt_flags = MNT_INTERNAL;
atomic_inc(&fc->root->d_sb->s_active);
mnt->mnt.mnt_sb = fc->root->d_sb;
mnt->mnt.mnt_root = dget(fc->root);
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
unlock_mount_hash();
return &mnt->mnt;
}
EXPORT_SYMBOL(vfs_create_mount);
struct vfsmount *fc_mount(struct fs_context *fc)
{
int err = vfs_get_tree(fc);
if (!err) {
up_write(&fc->root->d_sb->s_umount);
return vfs_create_mount(fc);
}
return ERR_PTR(err);
}
EXPORT_SYMBOL(fc_mount);
struct vfsmount *vfs_kern_mount(struct file_system_type *type,
int flags, const char *name,
void *data)
{
struct fs_context *fc;
struct vfsmount *mnt;
int ret = 0;
if (!type)
return ERR_PTR(-EINVAL);
fc = fs_context_for_mount(type, flags);
if (IS_ERR(fc))
return ERR_CAST(fc);
if (name)
ret = vfs_parse_fs_string(fc, "source",
name, strlen(name));
if (!ret)
ret = parse_monolithic_mount_data(fc, data);
if (!ret)
mnt = fc_mount(fc);
else
mnt = ERR_PTR(ret);
put_fs_context(fc);
return mnt;
}
EXPORT_SYMBOL_GPL(vfs_kern_mount);
struct vfsmount *
vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
const char *name, void *data)
{
/* Until it is worked out how to pass the user namespace
* through from the parent mount to the submount don't support
* unprivileged mounts with submounts.
*/
if (mountpoint->d_sb->s_user_ns != &init_user_ns)
return ERR_PTR(-EPERM);
return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
}
EXPORT_SYMBOL_GPL(vfs_submount);
static struct mount *clone_mnt(struct mount *old, struct dentry *root,
int flag)
{
struct super_block *sb = old->mnt.mnt_sb;
struct mount *mnt;
int err;
mnt = alloc_vfsmnt(old->mnt_devname);
if (!mnt)
return ERR_PTR(-ENOMEM);
if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE))
mnt->mnt_group_id = 0; /* not a peer of original */
else
mnt->mnt_group_id = old->mnt_group_id;
if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
err = mnt_alloc_group_id(mnt);
if (err)
goto out_free;
}
mnt->mnt.mnt_flags = old->mnt.mnt_flags;
mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
atomic_inc(&sb->s_active);
mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt));
mnt->mnt.mnt_sb = sb;
mnt->mnt.mnt_root = dget(root);
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
unlock_mount_hash();
if ((flag & CL_SLAVE) ||
((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
list_add(&mnt->mnt_slave, &old->mnt_slave_list);
mnt->mnt_master = old;
CLEAR_MNT_SHARED(mnt);
} else if (!(flag & CL_PRIVATE)) {
if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
list_add(&mnt->mnt_share, &old->mnt_share);
if (IS_MNT_SLAVE(old))
list_add(&mnt->mnt_slave, &old->mnt_slave);
mnt->mnt_master = old->mnt_master;
} else {
CLEAR_MNT_SHARED(mnt);
}
if (flag & CL_MAKE_SHARED)
set_mnt_shared(mnt);
/* stick the duplicate mount on the same expiry list
* as the original if that was on one */
if (flag & CL_EXPIRE) {
if (!list_empty(&old->mnt_expire))
list_add(&mnt->mnt_expire, &old->mnt_expire);
}
return mnt;
out_free:
mnt_free_id(mnt);
free_vfsmnt(mnt);
return ERR_PTR(err);
}
static void cleanup_mnt(struct mount *mnt)
{
struct hlist_node *p;
struct mount *m;
/*
* The warning here probably indicates that somebody messed
* up a mnt_want/drop_write() pair. If this happens, the
* filesystem was probably unable to make r/w->r/o transitions.
* The locking used to deal with mnt_count decrement provides barriers,
* so mnt_get_writers() below is safe.
*/
WARN_ON(mnt_get_writers(mnt));
if (unlikely(mnt->mnt_pins.first))
mnt_pin_kill(mnt);
hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) {
hlist_del(&m->mnt_umount);
mntput(&m->mnt);
}
fsnotify_vfsmount_delete(&mnt->mnt);
dput(mnt->mnt.mnt_root);
deactivate_super(mnt->mnt.mnt_sb);
mnt_free_id(mnt);
call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
}
static void __cleanup_mnt(struct rcu_head *head)
{
cleanup_mnt(container_of(head, struct mount, mnt_rcu));
}
static LLIST_HEAD(delayed_mntput_list);
static void delayed_mntput(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&delayed_mntput_list);
struct mount *m, *t;
llist_for_each_entry_safe(m, t, node, mnt_llist)
cleanup_mnt(m);
}
static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
static void mntput_no_expire(struct mount *mnt)
{
LIST_HEAD(list);
int count;
rcu_read_lock();
if (likely(READ_ONCE(mnt->mnt_ns))) {
/*
* Since we don't do lock_mount_hash() here,
* ->mnt_ns can change under us. However, if it's
* non-NULL, then there's a reference that won't
* be dropped until after an RCU delay done after
* turning ->mnt_ns NULL. So if we observe it
* non-NULL under rcu_read_lock(), the reference
* we are dropping is not the final one.
*/
mnt_add_count(mnt, -1); rcu_read_unlock();
return;
}
lock_mount_hash();
/*
* make sure that if __legitimize_mnt() has not seen us grab
* mount_lock, we'll see their refcount increment here.
*/
smp_mb();
mnt_add_count(mnt, -1);
count = mnt_get_count(mnt);
if (count != 0) {
WARN_ON(count < 0);
rcu_read_unlock();
unlock_mount_hash();
return;
}
if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) {
rcu_read_unlock();
unlock_mount_hash();
return;
}
mnt->mnt.mnt_flags |= MNT_DOOMED;
rcu_read_unlock();
list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) {
struct mount *p, *tmp;
list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) {
__put_mountpoint(unhash_mnt(p), &list);
hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children);
}
}
unlock_mount_hash();
shrink_dentry_list(&list);
if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
struct task_struct *task = current;
if (likely(!(task->flags & PF_KTHREAD))) {
init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME))
return;
}
if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1);
return;
}
cleanup_mnt(mnt);
}
void mntput(struct vfsmount *mnt)
{ if (mnt) {
struct mount *m = real_mount(mnt);
/* avoid cacheline pingpong */
if (unlikely(m->mnt_expiry_mark)) WRITE_ONCE(m->mnt_expiry_mark, 0);
mntput_no_expire(m);
}
}
EXPORT_SYMBOL(mntput);
struct vfsmount *mntget(struct vfsmount *mnt)
{ if (mnt) mnt_add_count(real_mount(mnt), 1);
return mnt;
}
EXPORT_SYMBOL(mntget);
/*
* Make a mount point inaccessible to new lookups.
* Because there may still be current users, the caller MUST WAIT
* for an RCU grace period before destroying the mount point.
*/
void mnt_make_shortterm(struct vfsmount *mnt)
{
if (mnt)
real_mount(mnt)->mnt_ns = NULL;
}
/**
* path_is_mountpoint() - Check if path is a mount in the current namespace.
* @path: path to check
*
* d_mountpoint() can only be used reliably to establish if a dentry is
* not mounted in any namespace and that common case is handled inline.
* d_mountpoint() isn't aware of the possibility there may be multiple
* mounts using a given dentry in a different namespace. This function
* checks if the passed in path is a mountpoint rather than the dentry
* alone.
*/
bool path_is_mountpoint(const struct path *path)
{
unsigned seq;
bool res;
if (!d_mountpoint(path->dentry))
return false;
rcu_read_lock();
do {
seq = read_seqbegin(&mount_lock);
res = __path_is_mountpoint(path);
} while (read_seqretry(&mount_lock, seq));
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL(path_is_mountpoint);
struct vfsmount *mnt_clone_internal(const struct path *path)
{
struct mount *p;
p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE);
if (IS_ERR(p))
return ERR_CAST(p);
p->mnt.mnt_flags |= MNT_INTERNAL;
return &p->mnt;
}
/*
* Returns the mount which either has the specified mnt_id, or has the next
* smallest id afer the specified one.
*/
static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id)
{
struct rb_node *node = ns->mounts.rb_node;
struct mount *ret = NULL;
while (node) {
struct mount *m = node_to_mount(node);
if (mnt_id <= m->mnt_id_unique) {
ret = node_to_mount(node);
if (mnt_id == m->mnt_id_unique)
break;
node = node->rb_left;
} else {
node = node->rb_right;
}
}
return ret;
}
/*
* Returns the mount which either has the specified mnt_id, or has the next
* greater id before the specified one.
*/
static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id)
{
struct rb_node *node = ns->mounts.rb_node;
struct mount *ret = NULL;
while (node) {
struct mount *m = node_to_mount(node);
if (mnt_id >= m->mnt_id_unique) {
ret = node_to_mount(node);
if (mnt_id == m->mnt_id_unique)
break;
node = node->rb_right;
} else {
node = node->rb_left;
}
}
return ret;
}
#ifdef CONFIG_PROC_FS
/* iterator; we want it to have access to namespace_sem, thus here... */
static void *m_start(struct seq_file *m, loff_t *pos)
{
struct proc_mounts *p = m->private;
down_read(&namespace_sem);
return mnt_find_id_at(p->ns, *pos);
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
struct mount *next = NULL, *mnt = v;
struct rb_node *node = rb_next(&mnt->mnt_node);
++*pos;
if (node) {
next = node_to_mount(node);
*pos = next->mnt_id_unique;
}
return next;
}
static void m_stop(struct seq_file *m, void *v)
{
up_read(&namespace_sem);
}
static int m_show(struct seq_file *m, void *v)
{
struct proc_mounts *p = m->private;
struct mount *r = v;
return p->show(m, &r->mnt);
}
const struct seq_operations mounts_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = m_show,
};
#endif /* CONFIG_PROC_FS */
/**
* may_umount_tree - check if a mount tree is busy
* @m: root of mount tree
*
* This is called to check if a tree of mounts has any
* open files, pwds, chroots or sub mounts that are
* busy.
*/
int may_umount_tree(struct vfsmount *m)
{
struct mount *mnt = real_mount(m);
int actual_refs = 0;
int minimum_refs = 0;
struct mount *p;
BUG_ON(!m);
/* write lock needed for mnt_get_count */
lock_mount_hash();
for (p = mnt; p; p = next_mnt(p, mnt)) {
actual_refs += mnt_get_count(p);
minimum_refs += 2;
}
unlock_mount_hash();
if (actual_refs > minimum_refs)
return 0;
return 1;
}
EXPORT_SYMBOL(may_umount_tree);
/**
* may_umount - check if a mount point is busy
* @mnt: root of mount
*
* This is called to check if a mount point has any
* open files, pwds, chroots or sub mounts. If the
* mount has sub mounts this will return busy
* regardless of whether the sub mounts are busy.
*
* Doesn't take quota and stuff into account. IOW, in some cases it will
* give false negatives. The main reason why it's here is that we need
* a non-destructive way to look for easily umountable filesystems.
*/
int may_umount(struct vfsmount *mnt)
{
int ret = 1;
down_read(&namespace_sem);
lock_mount_hash();
if (propagate_mount_busy(real_mount(mnt), 2))
ret = 0;
unlock_mount_hash();
up_read(&namespace_sem);
return ret;
}
EXPORT_SYMBOL(may_umount);
#ifdef CONFIG_FSNOTIFY
static void mnt_notify(struct mount *p)
{
if (!p->prev_ns && p->mnt_ns) {
fsnotify_mnt_attach(p->mnt_ns, &p->mnt);
} else if (p->prev_ns && !p->mnt_ns) {
fsnotify_mnt_detach(p->prev_ns, &p->mnt);
} else if (p->prev_ns == p->mnt_ns) {
fsnotify_mnt_move(p->mnt_ns, &p->mnt);
} else {
fsnotify_mnt_detach(p->prev_ns, &p->mnt);
fsnotify_mnt_attach(p->mnt_ns, &p->mnt);
}
p->prev_ns = p->mnt_ns;
}
static void notify_mnt_list(void)
{
struct mount *m, *tmp;
/*
* Notify about mounts that were added/reparented/detached/remain
* connected after unmount.
*/
list_for_each_entry_safe(m, tmp, ¬ify_list, to_notify) {
mnt_notify(m);
list_del_init(&m->to_notify);
}
}
static bool need_notify_mnt_list(void)
{
return !list_empty(¬ify_list);
}
#else
static void notify_mnt_list(void)
{
}
static bool need_notify_mnt_list(void)
{
return false;
}
#endif
static void namespace_unlock(void)
{
struct hlist_head head;
struct hlist_node *p;
struct mount *m;
LIST_HEAD(list);
hlist_move_list(&unmounted, &head);
list_splice_init(&ex_mountpoints, &list);
if (need_notify_mnt_list()) {
/*
* No point blocking out concurrent readers while notifications
* are sent. This will also allow statmount()/listmount() to run
* concurrently.
*/
downgrade_write(&namespace_sem);
notify_mnt_list();
up_read(&namespace_sem);
} else {
up_write(&namespace_sem);
}
shrink_dentry_list(&list);
if (likely(hlist_empty(&head)))
return;
synchronize_rcu_expedited();
hlist_for_each_entry_safe(m, p, &head, mnt_umount) {
hlist_del(&m->mnt_umount);
mntput(&m->mnt);
}
}
static inline void namespace_lock(void)
{
down_write(&namespace_sem);
}
DEFINE_GUARD(namespace_lock, struct rw_semaphore *, namespace_lock(), namespace_unlock())
enum umount_tree_flags {
UMOUNT_SYNC = 1,
UMOUNT_PROPAGATE = 2,
UMOUNT_CONNECTED = 4,
};
static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how)
{
/* Leaving mounts connected is only valid for lazy umounts */
if (how & UMOUNT_SYNC)
return true;
/* A mount without a parent has nothing to be connected to */
if (!mnt_has_parent(mnt))
return true;
/* Because the reference counting rules change when mounts are
* unmounted and connected, umounted mounts may not be
* connected to mounted mounts.
*/
if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT))
return true;
/* Has it been requested that the mount remain connected? */
if (how & UMOUNT_CONNECTED)
return false;
/* Is the mount locked such that it needs to remain connected? */
if (IS_MNT_LOCKED(mnt))
return false;
/* By default disconnect the mount */
return true;
}
/*
* mount_lock must be held
* namespace_sem must be held for write
*/
static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
{
LIST_HEAD(tmp_list);
struct mount *p;
if (how & UMOUNT_PROPAGATE)
propagate_mount_unlock(mnt);
/* Gather the mounts to umount */
for (p = mnt; p; p = next_mnt(p, mnt)) {
p->mnt.mnt_flags |= MNT_UMOUNT;
if (mnt_ns_attached(p))
move_from_ns(p, &tmp_list);
else
list_move(&p->mnt_list, &tmp_list);
}
/* Hide the mounts from mnt_mounts */
list_for_each_entry(p, &tmp_list, mnt_list) {
list_del_init(&p->mnt_child);
}
/* Add propagated mounts to the tmp_list */
if (how & UMOUNT_PROPAGATE)
propagate_umount(&tmp_list);
while (!list_empty(&tmp_list)) {
struct mnt_namespace *ns;
bool disconnect;
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
ns = p->mnt_ns;
if (ns) {
ns->nr_mounts--;
__touch_mnt_namespace(ns);
}
p->mnt_ns = NULL;
if (how & UMOUNT_SYNC)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
disconnect = disconnect_mount(p, how);
if (mnt_has_parent(p)) {
mnt_add_count(p->mnt_parent, -1);
if (!disconnect) {
/* Don't forget about p */
list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts);
} else {
umount_mnt(p);
}
}
change_mnt_propagation(p, MS_PRIVATE);
if (disconnect)
hlist_add_head(&p->mnt_umount, &unmounted);
/*
* At this point p->mnt_ns is NULL, notification will be queued
* only if
*
* - p->prev_ns is non-NULL *and*
* - p->prev_ns->n_fsnotify_marks is non-NULL
*
* This will preclude queuing the mount if this is a cleanup
* after a failed copy_tree() or destruction of an anonymous
* namespace, etc.
*/
mnt_notify_add(p);
}
}
static void shrink_submounts(struct mount *mnt);
static int do_umount_root(struct super_block *sb)
{
int ret = 0;
down_write(&sb->s_umount);
if (!sb_rdonly(sb)) {
struct fs_context *fc;
fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY,
SB_RDONLY);
if (IS_ERR(fc)) {
ret = PTR_ERR(fc);
} else {
ret = parse_monolithic_mount_data(fc, NULL);
if (!ret)
ret = reconfigure_super(fc);
put_fs_context(fc);
}
}
up_write(&sb->s_umount);
return ret;
}
static int do_umount(struct mount *mnt, int flags)
{
struct super_block *sb = mnt->mnt.mnt_sb;
int retval;
retval = security_sb_umount(&mnt->mnt, flags);
if (retval)
return retval;
/*
* Allow userspace to request a mountpoint be expired rather than
* unmounting unconditionally. Unmount only happens if:
* (1) the mark is already set (the mark is cleared by mntput())
* (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
*/
if (flags & MNT_EXPIRE) {
if (&mnt->mnt == current->fs->root.mnt ||
flags & (MNT_FORCE | MNT_DETACH))
return -EINVAL;
/*
* probably don't strictly need the lock here if we examined
* all race cases, but it's a slowpath.
*/
lock_mount_hash();
if (mnt_get_count(mnt) != 2) {
unlock_mount_hash();
return -EBUSY;
}
unlock_mount_hash();
if (!xchg(&mnt->mnt_expiry_mark, 1))
return -EAGAIN;
}
/*
* If we may have to abort operations to get out of this
* mount, and they will themselves hold resources we must
* allow the fs to do things. In the Unix tradition of
* 'Gee thats tricky lets do it in userspace' the umount_begin
* might fail to complete on the first run through as other tasks
* must return, and the like. Thats for the mount program to worry
* about for the moment.
*/
if (flags & MNT_FORCE && sb->s_op->umount_begin) {
sb->s_op->umount_begin(sb);
}
/*
* No sense to grab the lock for this test, but test itself looks
* somewhat bogus. Suggestions for better replacement?
* Ho-hum... In principle, we might treat that as umount + switch
* to rootfs. GC would eventually take care of the old vfsmount.
* Actually it makes sense, especially if rootfs would contain a
* /reboot - static binary that would close all descriptors and
* call reboot(9). Then init(8) could umount root and exec /reboot.
*/
if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
/*
* Special case for "unmounting" root ...
* we just try to remount it readonly.
*/
if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
return do_umount_root(sb);
}
namespace_lock();
lock_mount_hash();
/* Recheck MNT_LOCKED with the locks held */
retval = -EINVAL;
if (mnt->mnt.mnt_flags & MNT_LOCKED)
goto out;
event++;
if (flags & MNT_DETACH) {
if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
} else {
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
retval = 0;
}
}
out:
unlock_mount_hash();
namespace_unlock();
return retval;
}
/*
* __detach_mounts - lazily unmount all mounts on the specified dentry
*
* During unlink, rmdir, and d_drop it is possible to loose the path
* to an existing mountpoint, and wind up leaking the mount.
* detach_mounts allows lazily unmounting those mounts instead of
* leaking them.
*
* The caller may hold dentry->d_inode->i_mutex.
*/
void __detach_mounts(struct dentry *dentry)
{
struct mountpoint *mp;
struct mount *mnt;
namespace_lock();
lock_mount_hash();
mp = lookup_mountpoint(dentry);
if (!mp)
goto out_unlock;
event++;
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
umount_mnt(mnt);
hlist_add_head(&mnt->mnt_umount, &unmounted);
}
else umount_tree(mnt, UMOUNT_CONNECTED);
}
put_mountpoint(mp);
out_unlock:
unlock_mount_hash();
namespace_unlock();
}
/*
* Is the caller allowed to modify his namespace?
*/
bool may_mount(void)
{
return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
}
static void warn_mandlock(void)
{
pr_warn_once("=======================================================\n"
"WARNING: The mand mount option has been deprecated and\n"
" and is ignored by this kernel. Remove the mand\n"
" option from the mount to silence this warning.\n"
"=======================================================\n");
}
static int can_umount(const struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
struct super_block *sb = path->dentry->d_sb;
if (!may_mount())
return -EPERM;
if (!path_mounted(path))
return -EINVAL;
if (!check_mnt(mnt))
return -EINVAL;
if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */
return -EINVAL;
if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
// caller is responsible for flags being sane
int path_umount(struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
int ret;
ret = can_umount(path, flags);
if (!ret)
ret = do_umount(mnt, flags);
/* we mustn't call path_put() as that would clear mnt_expiry_mark */
dput(path->dentry);
mntput_no_expire(mnt);
return ret;
}
static int ksys_umount(char __user *name, int flags)
{
int lookup_flags = LOOKUP_MOUNTPOINT;
struct path path;
int ret;
// basic validity checks done first
if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
return -EINVAL;
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
if (ret)
return ret;
return path_umount(&path, flags);
}
SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
{
return ksys_umount(name, flags);
}
#ifdef __ARCH_WANT_SYS_OLDUMOUNT
/*
* The 2.0 compatible umount. No flags.
*/
SYSCALL_DEFINE1(oldumount, char __user *, name)
{
return ksys_umount(name, 0);
}
#endif
static bool is_mnt_ns_file(struct dentry *dentry)
{
struct ns_common *ns;
/* Is this a proxy for a mount namespace? */
if (dentry->d_op != &ns_dentry_operations)
return false;
ns = d_inode(dentry)->i_private;
return ns->ops == &mntns_operations;
}
struct ns_common *from_mnt_ns(struct mnt_namespace *mnt)
{
return &mnt->ns;
}
struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool previous)
{
guard(rcu)();
for (;;) {
struct list_head *list;
if (previous)
list = rcu_dereference(list_bidir_prev_rcu(&mntns->mnt_ns_list));
else
list = rcu_dereference(list_next_rcu(&mntns->mnt_ns_list));
if (list_is_head(list, &mnt_ns_list))
return ERR_PTR(-ENOENT);
mntns = list_entry_rcu(list, struct mnt_namespace, mnt_ns_list);
/*
* The last passive reference count is put with RCU
* delay so accessing the mount namespace is not just
* safe but all relevant members are still valid.
*/
if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN))
continue;
/*
* We need an active reference count as we're persisting
* the mount namespace and it might already be on its
* deathbed.
*/
if (!refcount_inc_not_zero(&mntns->ns.count))
continue;
return mntns;
}
}
struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry)
{
if (!is_mnt_ns_file(dentry))
return NULL;
return to_mnt_ns(get_proc_ns(dentry->d_inode));
}
static bool mnt_ns_loop(struct dentry *dentry)
{
/* Could bind mounting the mount namespace inode cause a
* mount namespace loop?
*/
struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry);
if (!mnt_ns)
return false;
return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
}
struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
int flag)
{
struct mount *res, *src_parent, *src_root_child, *src_mnt,
*dst_parent, *dst_mnt;
if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_root))
return ERR_PTR(-EINVAL);
if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry))
return ERR_PTR(-EINVAL);
res = dst_mnt = clone_mnt(src_root, dentry, flag);
if (IS_ERR(dst_mnt))
return dst_mnt;
src_parent = src_root;
dst_mnt->mnt_mountpoint = src_root->mnt_mountpoint;
list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) {
if (!is_subdir(src_root_child->mnt_mountpoint, dentry))
continue;
for (src_mnt = src_root_child; src_mnt;
src_mnt = next_mnt(src_mnt, src_root_child)) {
if (!(flag & CL_COPY_UNBINDABLE) &&
IS_MNT_UNBINDABLE(src_mnt)) {
if (src_mnt->mnt.mnt_flags & MNT_LOCKED) {
/* Both unbindable and locked. */
dst_mnt = ERR_PTR(-EPERM);
goto out;
} else {
src_mnt = skip_mnt_tree(src_mnt);
continue;
}
}
if (!(flag & CL_COPY_MNT_NS_FILE) &&
is_mnt_ns_file(src_mnt->mnt.mnt_root)) {
src_mnt = skip_mnt_tree(src_mnt);
continue;
}
while (src_parent != src_mnt->mnt_parent) {
src_parent = src_parent->mnt_parent;
dst_mnt = dst_mnt->mnt_parent;
}
src_parent = src_mnt;
dst_parent = dst_mnt;
dst_mnt = clone_mnt(src_mnt, src_mnt->mnt.mnt_root, flag);
if (IS_ERR(dst_mnt))
goto out;
lock_mount_hash();
list_add_tail(&dst_mnt->mnt_list, &res->mnt_list);
attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp, false);
unlock_mount_hash();
}
}
return res;
out:
if (res) {
lock_mount_hash();
umount_tree(res, UMOUNT_SYNC);
unlock_mount_hash();
}
return dst_mnt;
}
/* Caller should check returned pointer for errors */
struct vfsmount *collect_mounts(const struct path *path)
{
struct mount *tree;
namespace_lock();
if (!check_mnt(real_mount(path->mnt)))
tree = ERR_PTR(-EINVAL);
else
tree = copy_tree(real_mount(path->mnt), path->dentry,
CL_COPY_ALL | CL_PRIVATE);
namespace_unlock();
if (IS_ERR(tree))
return ERR_CAST(tree);
return &tree->mnt;
}
static void free_mnt_ns(struct mnt_namespace *);
static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
static inline bool must_dissolve(struct mnt_namespace *mnt_ns)
{
/*
* This mount belonged to an anonymous mount namespace
* but was moved to a non-anonymous mount namespace and
* then unmounted.
*/
if (unlikely(!mnt_ns))
return false;
/*
* This mount belongs to a non-anonymous mount namespace
* and we know that such a mount can never transition to
* an anonymous mount namespace again.
*/
if (!is_anon_ns(mnt_ns)) {
/*
* A detached mount either belongs to an anonymous mount
* namespace or a non-anonymous mount namespace. It
* should never belong to something purely internal.
*/
VFS_WARN_ON_ONCE(mnt_ns == MNT_NS_INTERNAL);
return false;
}
return true;
}
void dissolve_on_fput(struct vfsmount *mnt)
{
struct mnt_namespace *ns;
struct mount *m = real_mount(mnt);
scoped_guard(rcu) {
if (!must_dissolve(READ_ONCE(m->mnt_ns)))
return;
}
scoped_guard(namespace_lock, &namespace_sem) {
ns = m->mnt_ns;
if (!must_dissolve(ns))
return;
/*
* After must_dissolve() we know that this is a detached
* mount in an anonymous mount namespace.
*
* Now when mnt_has_parent() reports that this mount
* tree has a parent, we know that this anonymous mount
* tree has been moved to another anonymous mount
* namespace.
*
* So when closing this file we cannot unmount the mount
* tree. This will be done when the file referring to
* the root of the anonymous mount namespace will be
* closed (It could already be closed but it would sync
* on @namespace_sem and wait for us to finish.).
*/
if (mnt_has_parent(m))
return;
lock_mount_hash();
umount_tree(m, UMOUNT_CONNECTED);
unlock_mount_hash();
}
/* Make sure we notice when we leak mounts. */
VFS_WARN_ON_ONCE(!mnt_ns_empty(ns));
free_mnt_ns(ns);
}
void drop_collected_mounts(struct vfsmount *mnt)
{
namespace_lock();
lock_mount_hash();
umount_tree(real_mount(mnt), 0);
unlock_mount_hash();
namespace_unlock();
}
bool has_locked_children(struct mount *mnt, struct dentry *dentry)
{
struct mount *child;
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
if (!is_subdir(child->mnt_mountpoint, dentry))
continue;
if (child->mnt.mnt_flags & MNT_LOCKED)
return true;
}
return false;
}
/*
* Check that there aren't references to earlier/same mount namespaces in the
* specified subtree. Such references can act as pins for mount namespaces
* that aren't checked by the mount-cycle checking code, thereby allowing
* cycles to be made.
*/
static bool check_for_nsfs_mounts(struct mount *subtree)
{
struct mount *p;
bool ret = false;
lock_mount_hash();
for (p = subtree; p; p = next_mnt(p, subtree))
if (mnt_ns_loop(p->mnt.mnt_root))
goto out;
ret = true;
out:
unlock_mount_hash();
return ret;
}
/**
* clone_private_mount - create a private clone of a path
* @path: path to clone
*
* This creates a new vfsmount, which will be the clone of @path. The new mount
* will not be attached anywhere in the namespace and will be private (i.e.
* changes to the originating mount won't be propagated into this).
*
* This assumes caller has called or done the equivalent of may_mount().
*
* Release with mntput().
*/
struct vfsmount *clone_private_mount(const struct path *path)
{
struct mount *old_mnt = real_mount(path->mnt);
struct mount *new_mnt;
guard(rwsem_read)(&namespace_sem);
if (IS_MNT_UNBINDABLE(old_mnt))
return ERR_PTR(-EINVAL);
if (mnt_has_parent(old_mnt)) {
if (!check_mnt(old_mnt))
return ERR_PTR(-EINVAL);
} else {
if (!is_mounted(&old_mnt->mnt))
return ERR_PTR(-EINVAL);
/* Make sure this isn't something purely kernel internal. */
if (!is_anon_ns(old_mnt->mnt_ns))
return ERR_PTR(-EINVAL);
/* Make sure we don't create mount namespace loops. */
if (!check_for_nsfs_mounts(old_mnt))
return ERR_PTR(-EINVAL);
}
if (has_locked_children(old_mnt, path->dentry))
return ERR_PTR(-EINVAL);
new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
if (IS_ERR(new_mnt))
return ERR_PTR(-EINVAL);
/* Longterm mount to be removed by kern_unmount*() */
new_mnt->mnt_ns = MNT_NS_INTERNAL;
return &new_mnt->mnt;
}
EXPORT_SYMBOL_GPL(clone_private_mount);
int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
struct vfsmount *root)
{
struct mount *mnt;
int res = f(root, arg);
if (res)
return res;
list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
res = f(&mnt->mnt, arg);
if (res)
return res;
}
return 0;
}
static void lock_mnt_tree(struct mount *mnt)
{
struct mount *p;
for (p = mnt; p; p = next_mnt(p, mnt)) {
int flags = p->mnt.mnt_flags;
/* Don't allow unprivileged users to change mount flags */
flags |= MNT_LOCK_ATIME;
if (flags & MNT_READONLY)
flags |= MNT_LOCK_READONLY;
if (flags & MNT_NODEV)
flags |= MNT_LOCK_NODEV;
if (flags & MNT_NOSUID)
flags |= MNT_LOCK_NOSUID;
if (flags & MNT_NOEXEC)
flags |= MNT_LOCK_NOEXEC;
/* Don't allow unprivileged users to reveal what is under a mount */
if (list_empty(&p->mnt_expire))
flags |= MNT_LOCKED;
p->mnt.mnt_flags = flags;
}
}
static void cleanup_group_ids(struct mount *mnt, struct mount *end)
{
struct mount *p;
for (p = mnt; p != end; p = next_mnt(p, mnt)) {
if (p->mnt_group_id && !IS_MNT_SHARED(p))
mnt_release_group_id(p);
}
}
static int invent_group_ids(struct mount *mnt, bool recurse)
{
struct mount *p;
for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
int err = mnt_alloc_group_id(p);
if (err) {
cleanup_group_ids(mnt, p);
return err;
}
}
}
return 0;
}
int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
{
unsigned int max = READ_ONCE(sysctl_mount_max);
unsigned int mounts = 0;
struct mount *p;
if (ns->nr_mounts >= max)
return -ENOSPC;
max -= ns->nr_mounts;
if (ns->pending_mounts >= max)
return -ENOSPC;
max -= ns->pending_mounts;
for (p = mnt; p; p = next_mnt(p, mnt))
mounts++;
if (mounts > max)
return -ENOSPC;
ns->pending_mounts += mounts;
return 0;
}
enum mnt_tree_flags_t {
MNT_TREE_MOVE = BIT(0),
MNT_TREE_BENEATH = BIT(1),
MNT_TREE_PROPAGATION = BIT(2),
};
/**
* attach_recursive_mnt - attach a source mount tree
* @source_mnt: mount tree to be attached
* @top_mnt: mount that @source_mnt will be mounted on or mounted beneath
* @dest_mp: the mountpoint @source_mnt will be mounted at
* @flags: modify how @source_mnt is supposed to be attached
*
* NOTE: in the table below explains the semantics when a source mount
* of a given type is attached to a destination mount of a given type.
* ---------------------------------------------------------------------------
* | BIND MOUNT OPERATION |
* |**************************************************************************
* | source-->| shared | private | slave | unbindable |
* | dest | | | | |
* | | | | | | |
* | v | | | | |
* |**************************************************************************
* | shared | shared (++) | shared (+) | shared(+++)| invalid |
* | | | | | |
* |non-shared| shared (+) | private | slave (*) | invalid |
* ***************************************************************************
* A bind operation clones the source mount and mounts the clone on the
* destination mount.
*
* (++) the cloned mount is propagated to all the mounts in the propagation
* tree of the destination mount and the cloned mount is added to
* the peer group of the source mount.
* (+) the cloned mount is created under the destination mount and is marked
* as shared. The cloned mount is added to the peer group of the source
* mount.
* (+++) the mount is propagated to all the mounts in the propagation tree
* of the destination mount and the cloned mount is made slave
* of the same master as that of the source mount. The cloned mount
* is marked as 'shared and slave'.
* (*) the cloned mount is made a slave of the same master as that of the
* source mount.
*
* ---------------------------------------------------------------------------
* | MOVE MOUNT OPERATION |
* |**************************************************************************
* | source-->| shared | private | slave | unbindable |
* | dest | | | | |
* | | | | | | |
* | v | | | | |
* |**************************************************************************
* | shared | shared (+) | shared (+) | shared(+++) | invalid |
* | | | | | |
* |non-shared| shared (+*) | private | slave (*) | unbindable |
* ***************************************************************************
*
* (+) the mount is moved to the destination. And is then propagated to
* all the mounts in the propagation tree of the destination mount.
* (+*) the mount is moved to the destination.
* (+++) the mount is moved to the destination and is then propagated to
* all the mounts belonging to the destination mount's propagation tree.
* the mount is marked as 'shared and slave'.
* (*) the mount continues to be a slave at the new location.
*
* if the source mount is a tree, the operations explained above is
* applied to each mount in the tree.
* Must be called without spinlocks held, since this function can sleep
* in allocations.
*
* Context: The function expects namespace_lock() to be held.
* Return: If @source_mnt was successfully attached 0 is returned.
* Otherwise a negative error code is returned.
*/
static int attach_recursive_mnt(struct mount *source_mnt,
struct mount *top_mnt,
struct mountpoint *dest_mp,
enum mnt_tree_flags_t flags)
{
struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
HLIST_HEAD(tree_list);
struct mnt_namespace *ns = top_mnt->mnt_ns;
struct mountpoint *smp;
struct mount *child, *dest_mnt, *p;
struct hlist_node *n;
int err = 0;
bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH;
/*
* Preallocate a mountpoint in case the new mounts need to be
* mounted beneath mounts on the same mountpoint.
*/
smp = get_mountpoint(source_mnt->mnt.mnt_root);
if (IS_ERR(smp))
return PTR_ERR(smp);
/* Is there space to add these mounts to the mount namespace? */
if (!moving) {
err = count_mounts(ns, source_mnt);
if (err)
goto out;
}
if (beneath)
dest_mnt = top_mnt->mnt_parent;
else
dest_mnt = top_mnt;
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
goto out;
err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
}
lock_mount_hash();
if (err)
goto out_cleanup_ids;
if (IS_MNT_SHARED(dest_mnt)) {
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
}
if (moving) {
if (beneath)
dest_mp = smp;
unhash_mnt(source_mnt);
attach_mnt(source_mnt, top_mnt, dest_mp, beneath);
mnt_notify_add(source_mnt);
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
if (source_mnt->mnt_ns) {
LIST_HEAD(head);
/* move from anon - the caller will destroy */
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
move_from_ns(p, &head);
list_del_init(&head);
}
if (beneath)
mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp);
else
mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
commit_tree(source_mnt);
}
hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
struct mount *q;
hlist_del_init(&child->mnt_hash);
q = __lookup_mnt(&child->mnt_parent->mnt,
child->mnt_mountpoint);
if (q)
mnt_change_mountpoint(child, smp, q);
/* Notice when we are propagating across user namespaces */
if (child->mnt_parent->mnt_ns->user_ns != user_ns)
lock_mnt_tree(child);
child->mnt.mnt_flags &= ~MNT_LOCKED;
commit_tree(child);
}
put_mountpoint(smp);
unlock_mount_hash();
return 0;
out_cleanup_ids:
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
child->mnt_parent->mnt_ns->pending_mounts = 0;
umount_tree(child, UMOUNT_SYNC);
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
out:
ns->pending_mounts = 0;
read_seqlock_excl(&mount_lock);
put_mountpoint(smp);
read_sequnlock_excl(&mount_lock);
return err;
}
/**
* do_lock_mount - lock mount and mountpoint
* @path: target path
* @beneath: whether the intention is to mount beneath @path
*
* Follow the mount stack on @path until the top mount @mnt is found. If
* the initial @path->{mnt,dentry} is a mountpoint lookup the first
* mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root}
* until nothing is stacked on top of it anymore.
*
* Acquire the inode_lock() on the top mount's ->mnt_root to protect
* against concurrent removal of the new mountpoint from another mount
* namespace.
*
* If @beneath is requested, acquire inode_lock() on @mnt's mountpoint
* @mp on @mnt->mnt_parent must be acquired. This protects against a
* concurrent unlink of @mp->mnt_dentry from another mount namespace
* where @mnt doesn't have a child mount mounted @mp. A concurrent
* removal of @mnt->mnt_root doesn't matter as nothing will be mounted
* on top of it for @beneath.
*
* In addition, @beneath needs to make sure that @mnt hasn't been
* unmounted or moved from its current mountpoint in between dropping
* @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt
* being unmounted would be detected later by e.g., calling
* check_mnt(mnt) in the function it's called from. For the @beneath
* case however, it's useful to detect it directly in do_lock_mount().
* If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points
* to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will
* point to @mnt->mnt_root and @mnt->mnt_mp will be NULL.
*
* Return: Either the target mountpoint on the top mount or the top
* mount's mountpoint.
*/
static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
{
struct vfsmount *mnt = path->mnt;
struct dentry *dentry;
struct mountpoint *mp = ERR_PTR(-ENOENT);
struct path under = {};
for (;;) {
struct mount *m = real_mount(mnt);
if (beneath) {
path_put(&under);
read_seqlock_excl(&mount_lock);
under.mnt = mntget(&m->mnt_parent->mnt);
under.dentry = dget(m->mnt_mountpoint);
read_sequnlock_excl(&mount_lock);
dentry = under.dentry;
} else {
dentry = path->dentry;
}
inode_lock(dentry->d_inode);
namespace_lock();
if (unlikely(cant_mount(dentry) || !is_mounted(mnt)))
break; // not to be mounted on
if (beneath && unlikely(m->mnt_mountpoint != dentry ||
&m->mnt_parent->mnt != under.mnt)) {
namespace_unlock();
inode_unlock(dentry->d_inode);
continue; // got moved
}
mnt = lookup_mnt(path);
if (unlikely(mnt)) {
namespace_unlock();
inode_unlock(dentry->d_inode);
path_put(path);
path->mnt = mnt;
path->dentry = dget(mnt->mnt_root);
continue; // got overmounted
}
mp = get_mountpoint(dentry);
if (IS_ERR(mp))
break;
if (beneath) {
/*
* @under duplicates the references that will stay
* at least until namespace_unlock(), so the path_put()
* below is safe (and OK to do under namespace_lock -
* we are not dropping the final references here).
*/
path_put(&under);
}
return mp;
}
namespace_unlock();
inode_unlock(dentry->d_inode);
if (beneath)
path_put(&under);
return mp;
}
static inline struct mountpoint *lock_mount(struct path *path)
{
return do_lock_mount(path, false);
}
static void unlock_mount(struct mountpoint *where)
{
inode_unlock(where->m_dentry->d_inode);
read_seqlock_excl(&mount_lock);
put_mountpoint(where);
read_sequnlock_excl(&mount_lock);
namespace_unlock();
}
static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
{
if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER)
return -EINVAL;
if (d_is_dir(mp->m_dentry) !=
d_is_dir(mnt->mnt.mnt_root))
return -ENOTDIR;
return attach_recursive_mnt(mnt, p, mp, 0);
}
/*
* Sanity check the flags to change_mnt_propagation.
*/
static int flags_to_propagation_type(int ms_flags)
{
int type = ms_flags & ~(MS_REC | MS_SILENT);
/* Fail if any non-propagation flags are set */
if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
return 0;
/* Only one propagation flag should be set */
if (!is_power_of_2(type))
return 0;
return type;
}
/*
* recursively change the type of the mountpoint.
*/
static int do_change_type(struct path *path, int ms_flags)
{
struct mount *m;
struct mount *mnt = real_mount(path->mnt);
int recurse = ms_flags & MS_REC;
int type;
int err = 0;
if (!path_mounted(path))
return -EINVAL;
type = flags_to_propagation_type(ms_flags);
if (!type)
return -EINVAL;
namespace_lock();
if (type == MS_SHARED) {
err = invent_group_ids(mnt, recurse);
if (err)
goto out_unlock;
}
lock_mount_hash();
for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
change_mnt_propagation(m, type);
unlock_mount_hash();
out_unlock:
namespace_unlock();
return err;
}
/* may_copy_tree() - check if a mount tree can be copied
* @path: path to the mount tree to be copied
*
* This helper checks if the caller may copy the mount tree starting
* from @path->mnt. The caller may copy the mount tree under the
* following circumstances:
*
* (1) The caller is located in the mount namespace of the mount tree.
* This also implies that the mount does not belong to an anonymous
* mount namespace.
* (2) The caller tries to copy an nfs mount referring to a mount
* namespace, i.e., the caller is trying to copy a mount namespace
* entry from nsfs.
* (3) The caller tries to copy a pidfs mount referring to a pidfd.
* (4) The caller is trying to copy a mount tree that belongs to an
* anonymous mount namespace.
*
* For that to be safe, this helper enforces that the origin mount
* namespace the anonymous mount namespace was created from is the
* same as the caller's mount namespace by comparing the sequence
* numbers.
*
* This is not strictly necessary. The current semantics of the new
* mount api enforce that the caller must be located in the same
* mount namespace as the mount tree it interacts with. Using the
* origin sequence number preserves these semantics even for
* anonymous mount namespaces. However, one could envision extending
* the api to directly operate across mount namespace if needed.
*
* The ownership of a non-anonymous mount namespace such as the
* caller's cannot change.
* => We know that the caller's mount namespace is stable.
*
* If the origin sequence number of the anonymous mount namespace is
* the same as the sequence number of the caller's mount namespace.
* => The owning namespaces are the same.
*
* ==> The earlier capability check on the owning namespace of the
* caller's mount namespace ensures that the caller has the
* ability to copy the mount tree.
*
* Returns true if the mount tree can be copied, false otherwise.
*/
static inline bool may_copy_tree(struct path *path)
{
struct mount *mnt = real_mount(path->mnt);
const struct dentry_operations *d_op;
if (check_mnt(mnt))
return true;
d_op = path->dentry->d_op;
if (d_op == &ns_dentry_operations)
return true;
if (d_op == &pidfs_dentry_operations)
return true;
if (!is_mounted(path->mnt))
return false;
return check_anonymous_mnt(mnt);
}
static struct mount *__do_loopback(struct path *old_path, int recurse)
{
struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);
if (IS_MNT_UNBINDABLE(old))
return mnt;
if (!may_copy_tree(old_path))
return mnt;
if (!recurse && has_locked_children(old, old_path->dentry))
return mnt;
if (recurse)
mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE);
else
mnt = clone_mnt(old, old_path->dentry, 0);
if (!IS_ERR(mnt))
mnt->mnt.mnt_flags &= ~MNT_LOCKED;
return mnt;
}
/*
* do loopback mount.
*/
static int do_loopback(struct path *path, const char *old_name,
int recurse)
{
struct path old_path;
struct mount *mnt = NULL, *parent;
struct mountpoint *mp;
int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
if (err)
return err;
err = -EINVAL;
if (mnt_ns_loop(old_path.dentry))
goto out;
mp = lock_mount(path);
if (IS_ERR(mp)) {
err = PTR_ERR(mp);
goto out;
}
parent = real_mount(path->mnt);
if (!check_mnt(parent))
goto out2;
mnt = __do_loopback(&old_path, recurse);
if (IS_ERR(mnt)) {
err = PTR_ERR(mnt);
goto out2;
}
err = graft_tree(mnt, parent, mp);
if (err) {
lock_mount_hash();
umount_tree(mnt, UMOUNT_SYNC);
unlock_mount_hash();
}
out2:
unlock_mount(mp);
out:
path_put(&old_path);
return err;
}
static struct file *open_detached_copy(struct path *path, bool recursive)
{
struct mnt_namespace *ns, *mnt_ns = current->nsproxy->mnt_ns, *src_mnt_ns;
struct user_namespace *user_ns = mnt_ns->user_ns;
struct mount *mnt, *p;
struct file *file;
ns = alloc_mnt_ns(user_ns, true);
if (IS_ERR(ns))
return ERR_CAST(ns);
namespace_lock();
/*
* Record the sequence number of the source mount namespace.
* This needs to hold namespace_sem to ensure that the mount
* doesn't get attached.
*/
if (is_mounted(path->mnt)) {
src_mnt_ns = real_mount(path->mnt)->mnt_ns;
if (is_anon_ns(src_mnt_ns))
ns->seq_origin = src_mnt_ns->seq_origin;
else
ns->seq_origin = src_mnt_ns->seq;
}
mnt = __do_loopback(path, recursive);
if (IS_ERR(mnt)) {
namespace_unlock();
free_mnt_ns(ns);
return ERR_CAST(mnt);
}
lock_mount_hash();
for (p = mnt; p; p = next_mnt(p, mnt)) {
mnt_add_to_ns(ns, p);
ns->nr_mounts++;
}
ns->root = mnt;
mntget(&mnt->mnt);
unlock_mount_hash();
namespace_unlock();
mntput(path->mnt);
path->mnt = &mnt->mnt;
file = dentry_open(path, O_PATH, current_cred());
if (IS_ERR(file))
dissolve_on_fput(path->mnt);
else
file->f_mode |= FMODE_NEED_UNMOUNT;
return file;
}
static struct file *vfs_open_tree(int dfd, const char __user *filename, unsigned int flags)
{
int ret;
struct path path __free(path_put) = {};
int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
bool detached = flags & OPEN_TREE_CLONE;
BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC);
if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE |
AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE |
OPEN_TREE_CLOEXEC))
return ERR_PTR(-EINVAL);
if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE)
return ERR_PTR(-EINVAL);
if (flags & AT_NO_AUTOMOUNT)
lookup_flags &= ~LOOKUP_AUTOMOUNT;
if (flags & AT_SYMLINK_NOFOLLOW)
lookup_flags &= ~LOOKUP_FOLLOW;
if (flags & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
if (detached && !may_mount())
return ERR_PTR(-EPERM);
ret = user_path_at(dfd, filename, lookup_flags, &path);
if (unlikely(ret))
return ERR_PTR(ret);
if (detached)
return open_detached_copy(&path, flags & AT_RECURSIVE);
return dentry_open(&path, O_PATH, current_cred());
}
SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags)
{
int fd;
struct file *file __free(fput) = NULL;
file = vfs_open_tree(dfd, filename, flags);
if (IS_ERR(file))
return PTR_ERR(file);
fd = get_unused_fd_flags(flags & O_CLOEXEC);
if (fd < 0)
return fd;
fd_install(fd, no_free_ptr(file));
return fd;
}
/*
* Don't allow locked mount flags to be cleared.
*
* No locks need to be held here while testing the various MNT_LOCK
* flags because those flags can never be cleared once they are set.
*/
static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags)
{
unsigned int fl = mnt->mnt.mnt_flags;
if ((fl & MNT_LOCK_READONLY) &&
!(mnt_flags & MNT_READONLY))
return false;
if ((fl & MNT_LOCK_NODEV) &&
!(mnt_flags & MNT_NODEV))
return false;
if ((fl & MNT_LOCK_NOSUID) &&
!(mnt_flags & MNT_NOSUID))
return false;
if ((fl & MNT_LOCK_NOEXEC) &&
!(mnt_flags & MNT_NOEXEC))
return false;
if ((fl & MNT_LOCK_ATIME) &&
((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK)))
return false;
return true;
}
static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags)
{
bool readonly_request = (mnt_flags & MNT_READONLY);
if (readonly_request == __mnt_is_readonly(&mnt->mnt))
return 0;
if (readonly_request)
return mnt_make_readonly(mnt);
mnt->mnt.mnt_flags &= ~MNT_READONLY;
return 0;
}
static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags)
{
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
}
static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt)
{
struct super_block *sb = mnt->mnt_sb;
if (!__mnt_is_readonly(mnt) &&
(!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) &&
(ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) {
char *buf, *mntpath;
buf = (char *)__get_free_page(GFP_KERNEL);
if (buf)
mntpath = d_path(mountpoint, buf, PAGE_SIZE);
else
mntpath = ERR_PTR(-ENOMEM);
if (IS_ERR(mntpath))
mntpath = "(unknown)";
pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n",
sb->s_type->name,
is_mounted(mnt) ? "remounted" : "mounted",
mntpath, &sb->s_time_max,
(unsigned long long)sb->s_time_max);
sb->s_iflags |= SB_I_TS_EXPIRY_WARNED;
if (buf)
free_page((unsigned long)buf);
}
}
/*
* Handle reconfiguration of the mountpoint only without alteration of the
* superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND
* to mount(2).
*/
static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags)
{
struct super_block *sb = path->mnt->mnt_sb;
struct mount *mnt = real_mount(path->mnt);
int ret;
if (!check_mnt(mnt))
return -EINVAL;
if (!path_mounted(path))
return -EINVAL;
if (!can_change_locked_flags(mnt, mnt_flags))
return -EPERM;
/*
* We're only checking whether the superblock is read-only not
* changing it, so only take down_read(&sb->s_umount).
*/
down_read(&sb->s_umount);
lock_mount_hash();
ret = change_mount_ro_state(mnt, mnt_flags);
if (ret == 0)
set_mount_attributes(mnt, mnt_flags);
unlock_mount_hash();
up_read(&sb->s_umount);
mnt_warn_timestamp_expiry(path, &mnt->mnt);
return ret;
}
/*
* change filesystem flags. dir should be a physical root of filesystem.
* If you've mounted a non-root directory somewhere and want to do remount
* on it - tough luck.
*/
static int do_remount(struct path *path, int ms_flags, int sb_flags,
int mnt_flags, void *data)
{
int err;
struct super_block *sb = path->mnt->mnt_sb;
struct mount *mnt = real_mount(path->mnt);
struct fs_context *fc;
if (!check_mnt(mnt))
return -EINVAL;
if (!path_mounted(path))
return -EINVAL;
if (!can_change_locked_flags(mnt, mnt_flags))
return -EPERM;
fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK);
if (IS_ERR(fc))
return PTR_ERR(fc);
/*
* Indicate to the filesystem that the remount request is coming
* from the legacy mount system call.
*/
fc->oldapi = true;
err = parse_monolithic_mount_data(fc, data);
if (!err) {
down_write(&sb->s_umount);
err = -EPERM;
if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) {
err = reconfigure_super(fc);
if (!err) {
lock_mount_hash();
set_mount_attributes(mnt, mnt_flags);
unlock_mount_hash();
}
}
up_write(&sb->s_umount);
}
mnt_warn_timestamp_expiry(path, &mnt->mnt);
put_fs_context(fc);
return err;
}
static inline int tree_contains_unbindable(struct mount *mnt)
{
struct mount *p;
for (p = mnt; p; p = next_mnt(p, mnt)) {
if (IS_MNT_UNBINDABLE(p))
return 1;
}
return 0;
}
static int do_set_group(struct path *from_path, struct path *to_path)
{
struct mount *from, *to;
int err;
from = real_mount(from_path->mnt);
to = real_mount(to_path->mnt);
namespace_lock();
err = -EINVAL;
/* To and From must be mounted */
if (!is_mounted(&from->mnt))
goto out;
if (!is_mounted(&to->mnt))
goto out;
err = -EPERM;
/* We should be allowed to modify mount namespaces of both mounts */
if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN))
goto out;
if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN))
goto out;
err = -EINVAL;
/* To and From paths should be mount roots */
if (!path_mounted(from_path))
goto out;
if (!path_mounted(to_path))
goto out;
/* Setting sharing groups is only allowed across same superblock */
if (from->mnt.mnt_sb != to->mnt.mnt_sb)
goto out;
/* From mount root should be wider than To mount root */
if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root))
goto out;
/* From mount should not have locked children in place of To's root */
if (has_locked_children(from, to->mnt.mnt_root))
goto out;
/* Setting sharing groups is only allowed on private mounts */
if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to))
goto out;
/* From should not be private */
if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from))
goto out;
if (IS_MNT_SLAVE(from)) {
struct mount *m = from->mnt_master;
list_add(&to->mnt_slave, &m->mnt_slave_list);
to->mnt_master = m;
}
if (IS_MNT_SHARED(from)) {
to->mnt_group_id = from->mnt_group_id;
list_add(&to->mnt_share, &from->mnt_share);
lock_mount_hash();
set_mnt_shared(to);
unlock_mount_hash();
}
err = 0;
out:
namespace_unlock();
return err;
}
/**
* path_overmounted - check if path is overmounted
* @path: path to check
*
* Check if path is overmounted, i.e., if there's a mount on top of
* @path->mnt with @path->dentry as mountpoint.
*
* Context: This function expects namespace_lock() to be held.
* Return: If path is overmounted true is returned, false if not.
*/
static inline bool path_overmounted(const struct path *path)
{
rcu_read_lock();
if (unlikely(__lookup_mnt(path->mnt, path->dentry))) {
rcu_read_unlock();
return true;
}
rcu_read_unlock();
return false;
}
/**
* can_move_mount_beneath - check that we can mount beneath the top mount
* @from: mount to mount beneath
* @to: mount under which to mount
* @mp: mountpoint of @to
*
* - Make sure that @to->dentry is actually the root of a mount under
* which we can mount another mount.
* - Make sure that nothing can be mounted beneath the caller's current
* root or the rootfs of the namespace.
* - Make sure that the caller can unmount the topmost mount ensuring
* that the caller could reveal the underlying mountpoint.
* - Ensure that nothing has been mounted on top of @from before we
* grabbed @namespace_sem to avoid creating pointless shadow mounts.
* - Prevent mounting beneath a mount if the propagation relationship
* between the source mount, parent mount, and top mount would lead to
* nonsensical mount trees.
*
* Context: This function expects namespace_lock() to be held.
* Return: On success 0, and on error a negative error code is returned.
*/
static int can_move_mount_beneath(const struct path *from,
const struct path *to,
const struct mountpoint *mp)
{
struct mount *mnt_from = real_mount(from->mnt),
*mnt_to = real_mount(to->mnt),
*parent_mnt_to = mnt_to->mnt_parent;
if (!mnt_has_parent(mnt_to))
return -EINVAL;
if (!path_mounted(to))
return -EINVAL;
if (IS_MNT_LOCKED(mnt_to))
return -EINVAL;
/* Avoid creating shadow mounts during mount propagation. */
if (path_overmounted(from))
return -EINVAL;
/*
* Mounting beneath the rootfs only makes sense when the
* semantics of pivot_root(".", ".") are used.
*/
if (&mnt_to->mnt == current->fs->root.mnt)
return -EINVAL;
if (parent_mnt_to == current->nsproxy->mnt_ns->root)
return -EINVAL;
for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent)
if (p == mnt_to)
return -EINVAL;
/*
* If the parent mount propagates to the child mount this would
* mean mounting @mnt_from on @mnt_to->mnt_parent and then
* propagating a copy @c of @mnt_from on top of @mnt_to. This
* defeats the whole purpose of mounting beneath another mount.
*/
if (propagation_would_overmount(parent_mnt_to, mnt_to, mp))
return -EINVAL;
/*
* If @mnt_to->mnt_parent propagates to @mnt_from this would
* mean propagating a copy @c of @mnt_from on top of @mnt_from.
* Afterwards @mnt_from would be mounted on top of
* @mnt_to->mnt_parent and @mnt_to would be unmounted from
* @mnt->mnt_parent and remounted on @mnt_from. But since @c is
* already mounted on @mnt_from, @mnt_to would ultimately be
* remounted on top of @c. Afterwards, @mnt_from would be
* covered by a copy @c of @mnt_from and @c would be covered by
* @mnt_from itself. This defeats the whole purpose of mounting
* @mnt_from beneath @mnt_to.
*/
if (propagation_would_overmount(parent_mnt_to, mnt_from, mp))
return -EINVAL;
return 0;
}
/* may_use_mount() - check if a mount tree can be used
* @mnt: vfsmount to be used
*
* This helper checks if the caller may use the mount tree starting
* from @path->mnt. The caller may use the mount tree under the
* following circumstances:
*
* (1) The caller is located in the mount namespace of the mount tree.
* This also implies that the mount does not belong to an anonymous
* mount namespace.
* (2) The caller is trying to use a mount tree that belongs to an
* anonymous mount namespace.
*
* For that to be safe, this helper enforces that the origin mount
* namespace the anonymous mount namespace was created from is the
* same as the caller's mount namespace by comparing the sequence
* numbers.
*
* The ownership of a non-anonymous mount namespace such as the
* caller's cannot change.
* => We know that the caller's mount namespace is stable.
*
* If the origin sequence number of the anonymous mount namespace is
* the same as the sequence number of the caller's mount namespace.
* => The owning namespaces are the same.
*
* ==> The earlier capability check on the owning namespace of the
* caller's mount namespace ensures that the caller has the
* ability to use the mount tree.
*
* Returns true if the mount tree can be used, false otherwise.
*/
static inline bool may_use_mount(struct mount *mnt)
{
if (check_mnt(mnt))
return true;
/*
* Make sure that noone unmounted the target path or somehow
* managed to get their hands on something purely kernel
* internal.
*/
if (!is_mounted(&mnt->mnt))
return false;
return check_anonymous_mnt(mnt);
}
static int do_move_mount(struct path *old_path,
struct path *new_path, enum mnt_tree_flags_t flags)
{
struct mnt_namespace *ns;
struct mount *p;
struct mount *old;
struct mount *parent;
struct mountpoint *mp, *old_mp;
int err;
bool attached, beneath = flags & MNT_TREE_BENEATH;
mp = do_lock_mount(new_path, beneath);
if (IS_ERR(mp))
return PTR_ERR(mp);
old = real_mount(old_path->mnt);
p = real_mount(new_path->mnt);
parent = old->mnt_parent;
attached = mnt_has_parent(old);
if (attached)
flags |= MNT_TREE_MOVE;
old_mp = old->mnt_mp;
ns = old->mnt_ns;
err = -EINVAL;
if (!may_use_mount(p))
goto out;
/* The thing moved must be mounted... */
if (!is_mounted(&old->mnt))
goto out;
/* ... and either ours or the root of anon namespace */
if (!(attached ? check_mnt(old) : is_anon_ns(ns)))
goto out;
if (is_anon_ns(ns)) {
/*
* Ending up with two files referring to the root of the
* same anonymous mount namespace would cause an error
* as this would mean trying to move the same mount
* twice into the mount tree which would be rejected
* later. But be explicit about it right here.
*/
if ((is_anon_ns(p->mnt_ns) && ns == p->mnt_ns))
goto out;
/*
* If this is an anonymous mount tree ensure that mount
* propagation can detect mounts that were just
* propagated to the target mount tree so we don't
* propagate onto them.
*/
ns->mntns_flags |= MNTNS_PROPAGATING;
} else if (is_anon_ns(p->mnt_ns)) {
/*
* Don't allow moving an attached mount tree to an
* anonymous mount tree.
*/
goto out;
}
if (old->mnt.mnt_flags & MNT_LOCKED)
goto out;
if (!path_mounted(old_path))
goto out;
if (d_is_dir(new_path->dentry) !=
d_is_dir(old_path->dentry))
goto out;
/*
* Don't move a mount residing in a shared parent.
*/
if (attached && IS_MNT_SHARED(parent))
goto out;
if (beneath) {
err = can_move_mount_beneath(old_path, new_path, mp);
if (err)
goto out;
err = -EINVAL;
p = p->mnt_parent;
flags |= MNT_TREE_BENEATH;
}
/*
* Don't move a mount tree containing unbindable mounts to a destination
* mount which is shared.
*/
if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
goto out;
err = -ELOOP;
if (!check_for_nsfs_mounts(old))
goto out;
for (; mnt_has_parent(p); p = p->mnt_parent)
if (p == old)
goto out;
err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags);
if (err)
goto out;
if (is_anon_ns(ns))
ns->mntns_flags &= ~MNTNS_PROPAGATING;
/* if the mount is moved, it should no longer be expire
* automatically */
list_del_init(&old->mnt_expire);
if (attached)
put_mountpoint(old_mp);
out:
unlock_mount(mp);
if (!err) {
if (attached) {
mntput_no_expire(parent);
} else {
/* Make sure we notice when we leak mounts. */
VFS_WARN_ON_ONCE(!mnt_ns_empty(ns));
free_mnt_ns(ns);
}
}
return err;
}
static int do_move_mount_old(struct path *path, const char *old_name)
{
struct path old_path;
int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
if (err)
return err;
err = do_move_mount(&old_path, path, 0);
path_put(&old_path);
return err;
}
/*
* add a mount into a namespace's mount tree
*/
static int do_add_mount(struct mount *newmnt, struct mountpoint *mp,
const struct path *path, int mnt_flags)
{
struct mount *parent = real_mount(path->mnt);
mnt_flags &= ~MNT_INTERNAL_FLAGS;
if (unlikely(!check_mnt(parent))) {
/* that's acceptable only for automounts done in private ns */
if (!(mnt_flags & MNT_SHRINKABLE))
return -EINVAL;
/* ... and for those we'd better have mountpoint still alive */
if (!parent->mnt_ns)
return -EINVAL;
}
/* Refuse the same filesystem on the same mount point */
if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path_mounted(path))
return -EBUSY;
if (d_is_symlink(newmnt->mnt.mnt_root))
return -EINVAL;
newmnt->mnt.mnt_flags = mnt_flags;
return graft_tree(newmnt, parent, mp);
}
static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags);
/*
* Create a new mount using a superblock configuration and request it
* be added to the namespace tree.
*/
static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
unsigned int mnt_flags)
{
struct vfsmount *mnt;
struct mountpoint *mp;
struct super_block *sb = fc->root->d_sb;
int error;
error = security_sb_kern_mount(sb);
if (!error && mount_too_revealing(sb, &mnt_flags))
error = -EPERM;
if (unlikely(error)) {
fc_drop_locked(fc);
return error;
}
up_write(&sb->s_umount);
mnt = vfs_create_mount(fc);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
mnt_warn_timestamp_expiry(mountpoint, mnt);
mp = lock_mount(mountpoint);
if (IS_ERR(mp)) {
mntput(mnt);
return PTR_ERR(mp);
}
error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags);
unlock_mount(mp);
if (error < 0)
mntput(mnt);
return error;
}
/*
* create a new mount for userspace and request it to be added into the
* namespace's tree
*/
static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
int mnt_flags, const char *name, void *data)
{
struct file_system_type *type;
struct fs_context *fc;
const char *subtype = NULL;
int err = 0;
if (!fstype)
return -EINVAL;
type = get_fs_type(fstype);
if (!type)
return -ENODEV;
if (type->fs_flags & FS_HAS_SUBTYPE) {
subtype = strchr(fstype, '.');
if (subtype) {
subtype++;
if (!*subtype) {
put_filesystem(type);
return -EINVAL;
}
}
}
fc = fs_context_for_mount(type, sb_flags);
put_filesystem(type);
if (IS_ERR(fc))
return PTR_ERR(fc);
/*
* Indicate to the filesystem that the mount request is coming
* from the legacy mount system call.
*/
fc->oldapi = true;
if (subtype)
err = vfs_parse_fs_string(fc, "subtype",
subtype, strlen(subtype));
if (!err && name)
err = vfs_parse_fs_string(fc, "source", name, strlen(name));
if (!err)
err = parse_monolithic_mount_data(fc, data);
if (!err && !mount_capable(fc))
err = -EPERM;
if (!err)
err = vfs_get_tree(fc);
if (!err)
err = do_new_mount_fc(fc, path, mnt_flags);
put_fs_context(fc);
return err;
}
int finish_automount(struct vfsmount *m, const struct path *path)
{
struct dentry *dentry = path->dentry;
struct mountpoint *mp;
struct mount *mnt;
int err;
if (!m)
return 0;
if (IS_ERR(m))
return PTR_ERR(m);
mnt = real_mount(m);
/* The new mount record should have at least 2 refs to prevent it being
* expired before we get a chance to add it
*/
BUG_ON(mnt_get_count(mnt) < 2);
if (m->mnt_sb == path->mnt->mnt_sb &&
m->mnt_root == dentry) {
err = -ELOOP;
goto discard;
}
/*
* we don't want to use lock_mount() - in this case finding something
* that overmounts our mountpoint to be means "quitely drop what we've
* got", not "try to mount it on top".
*/
inode_lock(dentry->d_inode);
namespace_lock();
if (unlikely(cant_mount(dentry))) {
err = -ENOENT;
goto discard_locked;
}
if (path_overmounted(path)) {
err = 0;
goto discard_locked;
}
mp = get_mountpoint(dentry);
if (IS_ERR(mp)) {
err = PTR_ERR(mp);
goto discard_locked;
}
err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
unlock_mount(mp);
if (unlikely(err))
goto discard;
mntput(m);
return 0;
discard_locked:
namespace_unlock();
inode_unlock(dentry->d_inode);
discard:
/* remove m from any expiration list it may be on */
if (!list_empty(&mnt->mnt_expire)) {
namespace_lock();
list_del_init(&mnt->mnt_expire);
namespace_unlock();
}
mntput(m);
mntput(m);
return err;
}
/**
* mnt_set_expiry - Put a mount on an expiration list
* @mnt: The mount to list.
* @expiry_list: The list to add the mount to.
*/
void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
{
namespace_lock();
list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list);
namespace_unlock();
}
EXPORT_SYMBOL(mnt_set_expiry);
/*
* process a list of expirable mountpoints with the intent of discarding any
* mountpoints that aren't in use and haven't been touched since last we came
* here
*/
void mark_mounts_for_expiry(struct list_head *mounts)
{
struct mount *mnt, *next;
LIST_HEAD(graveyard);
if (list_empty(mounts))
return;
namespace_lock();
lock_mount_hash();
/* extract from the expiration list every vfsmount that matches the
* following criteria:
* - only referenced by its parent vfsmount
* - still marked for expiry (marked on the last call here; marks are
* cleared by mntput())
*/
list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
if (!xchg(&mnt->mnt_expiry_mark, 1) ||
propagate_mount_busy(mnt, 1))
continue;
list_move(&mnt->mnt_expire, &graveyard);
}
while (!list_empty(&graveyard)) {
mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
touch_mnt_namespace(mnt->mnt_ns);
umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
unlock_mount_hash();
namespace_unlock();
}
EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
/*
* Ripoff of 'select_parent()'
*
* search the list of submounts for a given mountpoint, and move any
* shrinkable submounts to the 'graveyard' list.
*/
static int select_submounts(struct mount *parent, struct list_head *graveyard)
{
struct mount *this_parent = parent;
struct list_head *next;
int found = 0;
repeat:
next = this_parent->mnt_mounts.next;
resume:
while (next != &this_parent->mnt_mounts) {
struct list_head *tmp = next;
struct mount *mnt = list_entry(tmp, struct mount, mnt_child);
next = tmp->next;
if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE))
continue;
/*
* Descend a level if the d_mounts list is non-empty.
*/
if (!list_empty(&mnt->mnt_mounts)) {
this_parent = mnt;
goto repeat;
}
if (!propagate_mount_busy(mnt, 1)) {
list_move_tail(&mnt->mnt_expire, graveyard);
found++;
}
}
/*
* All done at this level ... ascend and resume the search
*/
if (this_parent != parent) {
next = this_parent->mnt_child.next;
this_parent = this_parent->mnt_parent;
goto resume;
}
return found;
}
/*
* process a list of expirable mountpoints with the intent of discarding any
* submounts of a specific parent mountpoint
*
* mount_lock must be held for write
*/
static void shrink_submounts(struct mount *mnt)
{
LIST_HEAD(graveyard);
struct mount *m;
/* extract submounts of 'mountpoint' from the expiration list */
while (select_submounts(mnt, &graveyard)) {
while (!list_empty(&graveyard)) {
m = list_first_entry(&graveyard, struct mount,
mnt_expire);
touch_mnt_namespace(m->mnt_ns);
umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
}
}
static void *copy_mount_options(const void __user * data)
{
char *copy;
unsigned left, offset;
if (!data)
return NULL;
copy = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!copy)
return ERR_PTR(-ENOMEM);
left = copy_from_user(copy, data, PAGE_SIZE);
/*
* Not all architectures have an exact copy_from_user(). Resort to
* byte at a time.
*/
offset = PAGE_SIZE - left;
while (left) {
char c;
if (get_user(c, (const char __user *)data + offset))
break;
copy[offset] = c;
left--;
offset++;
}
if (left == PAGE_SIZE) {
kfree(copy);
return ERR_PTR(-EFAULT);
}
return copy;
}
static char *copy_mount_string(const void __user *data)
{
return data ? strndup_user(data, PATH_MAX) : NULL;
}
/*
* Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
* be given to the mount() call (ie: read-only, no-dev, no-suid etc).
*
* data is a (void *) that can point to any structure up to
* PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
* information (or be NULL).
*
* Pre-0.97 versions of mount() didn't have a flags word.
* When the flags word was introduced its top half was required
* to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.
* Therefore, if this magic number is present, it carries no information
* and must be discarded.
*/
int path_mount(const char *dev_name, struct path *path,
const char *type_page, unsigned long flags, void *data_page)
{
unsigned int mnt_flags = 0, sb_flags;
int ret;
/* Discard magic */
if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
flags &= ~MS_MGC_MSK;
/* Basic sanity checks */
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
if (flags & MS_NOUSER)
return -EINVAL;
ret = security_sb_mount(dev_name, path, type_page, flags, data_page);
if (ret)
return ret;
if (!may_mount())
return -EPERM;
if (flags & SB_MANDLOCK)
warn_mandlock();
/* Default to relatime unless overriden */
if (!(flags & MS_NOATIME))
mnt_flags |= MNT_RELATIME;
/* Separate the per-mountpoint flags */
if (flags & MS_NOSUID)
mnt_flags |= MNT_NOSUID;
if (flags & MS_NODEV)
mnt_flags |= MNT_NODEV;
if (flags & MS_NOEXEC)
mnt_flags |= MNT_NOEXEC;
if (flags & MS_NOATIME)
mnt_flags |= MNT_NOATIME;
if (flags & MS_NODIRATIME)
mnt_flags |= MNT_NODIRATIME;
if (flags & MS_STRICTATIME)
mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
if (flags & MS_NOSYMFOLLOW)
mnt_flags |= MNT_NOSYMFOLLOW;
/* The default atime for remount is preservation */
if ((flags & MS_REMOUNT) &&
((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
MS_STRICTATIME)) == 0)) {
mnt_flags &= ~MNT_ATIME_MASK;
mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK;
}
sb_flags = flags & (SB_RDONLY |
SB_SYNCHRONOUS |
SB_MANDLOCK |
SB_DIRSYNC |
SB_SILENT |
SB_POSIXACL |
SB_LAZYTIME |
SB_I_VERSION);
if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND))
return do_reconfigure_mnt(path, mnt_flags);
if (flags & MS_REMOUNT)
return do_remount(path, flags, sb_flags, mnt_flags, data_page);
if (flags & MS_BIND)
return do_loopback(path, dev_name, flags & MS_REC);
if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
return do_change_type(path, flags);
if (flags & MS_MOVE)
return do_move_mount_old(path, dev_name);
return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name,
data_page);
}
int do_mount(const char *dev_name, const char __user *dir_name,
const char *type_page, unsigned long flags, void *data_page)
{
struct path path;
int ret;
ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path);
if (ret)
return ret;
ret = path_mount(dev_name, &path, type_page, flags, data_page);
path_put(&path);
return ret;
}
static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES);
}
static void dec_mnt_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES);
}
static void free_mnt_ns(struct mnt_namespace *ns)
{
if (!is_anon_ns(ns))
ns_free_inum(&ns->ns);
dec_mnt_namespaces(ns->ucounts);
mnt_ns_tree_remove(ns);
}
/*
* Assign a sequence number so we can detect when we attempt to bind
* mount a reference to an older mount namespace into the current
* mount namespace, preventing reference counting loops. A 64bit
* number incrementing at 10Ghz will take 12,427 years to wrap which
* is effectively never, so we can ignore the possibility.
*/
static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon)
{
struct mnt_namespace *new_ns;
struct ucounts *ucounts;
int ret;
ucounts = inc_mnt_namespaces(user_ns);
if (!ucounts)
return ERR_PTR(-ENOSPC);
new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT);
if (!new_ns) {
dec_mnt_namespaces(ucounts);
return ERR_PTR(-ENOMEM);
}
if (!anon) {
ret = ns_alloc_inum(&new_ns->ns);
if (ret) {
kfree(new_ns);
dec_mnt_namespaces(ucounts);
return ERR_PTR(ret);
}
}
new_ns->ns.ops = &mntns_operations;
if (!anon)
new_ns->seq = atomic64_inc_return(&mnt_ns_seq);
refcount_set(&new_ns->ns.count, 1);
refcount_set(&new_ns->passive, 1);
new_ns->mounts = RB_ROOT;
INIT_LIST_HEAD(&new_ns->mnt_ns_list);
RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node);
init_waitqueue_head(&new_ns->poll);
new_ns->user_ns = get_user_ns(user_ns);
new_ns->ucounts = ucounts;
return new_ns;
}
__latent_entropy
struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
struct user_namespace *user_ns, struct fs_struct *new_fs)
{
struct mnt_namespace *new_ns;
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
struct mount *p, *q;
struct mount *old;
struct mount *new;
int copy_flags;
BUG_ON(!ns);
if (likely(!(flags & CLONE_NEWNS))) {
get_mnt_ns(ns);
return ns;
}
old = ns->root;
new_ns = alloc_mnt_ns(user_ns, false);
if (IS_ERR(new_ns))
return new_ns;
namespace_lock();
/* First pass: copy the tree topology */
copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE;
if (user_ns != ns->user_ns)
copy_flags |= CL_SHARED_TO_SLAVE;
new = copy_tree(old, old->mnt.mnt_root, copy_flags);
if (IS_ERR(new)) {
namespace_unlock();
ns_free_inum(&new_ns->ns);
dec_mnt_namespaces(new_ns->ucounts);
mnt_ns_release(new_ns);
return ERR_CAST(new);
}
if (user_ns != ns->user_ns) {
lock_mount_hash();
lock_mnt_tree(new);
unlock_mount_hash();
}
new_ns->root = new;
/*
* Second pass: switch the tsk->fs->* elements and mark new vfsmounts
* as belonging to new namespace. We have already acquired a private
* fs_struct, so tsk->fs->lock is not needed.
*/
p = old;
q = new;
while (p) {
mnt_add_to_ns(new_ns, q);
new_ns->nr_mounts++;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
rootmnt = &p->mnt;
}
if (&p->mnt == new_fs->pwd.mnt) {
new_fs->pwd.mnt = mntget(&q->mnt);
pwdmnt = &p->mnt;
}
}
p = next_mnt(p, old);
q = next_mnt(q, new);
if (!q)
break;
// an mntns binding we'd skipped?
while (p->mnt.mnt_root != q->mnt.mnt_root)
p = next_mnt(skip_mnt_tree(p), old);
}
namespace_unlock();
if (rootmnt)
mntput(rootmnt);
if (pwdmnt)
mntput(pwdmnt);
mnt_ns_tree_add(new_ns);
return new_ns;
}
struct dentry *mount_subtree(struct vfsmount *m, const char *name)
{
struct mount *mnt = real_mount(m);
struct mnt_namespace *ns;
struct super_block *s;
struct path path;
int err;
ns = alloc_mnt_ns(&init_user_ns, true);
if (IS_ERR(ns)) {
mntput(m);
return ERR_CAST(ns);
}
ns->root = mnt;
ns->nr_mounts++;
mnt_add_to_ns(ns, mnt);
err = vfs_path_lookup(m->mnt_root, m,
name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
put_mnt_ns(ns);
if (err)
return ERR_PTR(err);
/* trade a vfsmount reference for active sb one */
s = path.mnt->mnt_sb;
atomic_inc(&s->s_active);
mntput(path.mnt);
/* lock the sucker */
down_write(&s->s_umount);
/* ... and return the root of (sub)tree on it */
return path.dentry;
}
EXPORT_SYMBOL(mount_subtree);
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
{
int ret;
char *kernel_type;
char *kernel_dev;
void *options;
kernel_type = copy_mount_string(type);
ret = PTR_ERR(kernel_type);
if (IS_ERR(kernel_type))
goto out_type;
kernel_dev = copy_mount_string(dev_name);
ret = PTR_ERR(kernel_dev);
if (IS_ERR(kernel_dev))
goto out_dev;
options = copy_mount_options(data);
ret = PTR_ERR(options);
if (IS_ERR(options))
goto out_data;
ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
kfree(options);
out_data:
kfree(kernel_dev);
out_dev:
kfree(kernel_type);
out_type:
return ret;
}
#define FSMOUNT_VALID_FLAGS \
(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \
MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \
MOUNT_ATTR_NOSYMFOLLOW)
#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP)
#define MOUNT_SETATTR_PROPAGATION_FLAGS \
(MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED)
static unsigned int attr_flags_to_mnt_flags(u64 attr_flags)
{
unsigned int mnt_flags = 0;
if (attr_flags & MOUNT_ATTR_RDONLY)
mnt_flags |= MNT_READONLY;
if (attr_flags & MOUNT_ATTR_NOSUID)
mnt_flags |= MNT_NOSUID;
if (attr_flags & MOUNT_ATTR_NODEV)
mnt_flags |= MNT_NODEV;
if (attr_flags & MOUNT_ATTR_NOEXEC)
mnt_flags |= MNT_NOEXEC;
if (attr_flags & MOUNT_ATTR_NODIRATIME)
mnt_flags |= MNT_NODIRATIME;
if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW)
mnt_flags |= MNT_NOSYMFOLLOW;
return mnt_flags;
}
/*
* Create a kernel mount representation for a new, prepared superblock
* (specified by fs_fd) and attach to an open_tree-like file descriptor.
*/
SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
unsigned int, attr_flags)
{
struct mnt_namespace *ns;
struct fs_context *fc;
struct file *file;
struct path newmount;
struct mount *mnt;
unsigned int mnt_flags = 0;
long ret;
if (!may_mount())
return -EPERM;
if ((flags & ~(FSMOUNT_CLOEXEC)) != 0)
return -EINVAL;
if (attr_flags & ~FSMOUNT_VALID_FLAGS)
return -EINVAL;
mnt_flags = attr_flags_to_mnt_flags(attr_flags);
switch (attr_flags & MOUNT_ATTR__ATIME) {
case MOUNT_ATTR_STRICTATIME:
break;
case MOUNT_ATTR_NOATIME:
mnt_flags |= MNT_NOATIME;
break;
case MOUNT_ATTR_RELATIME:
mnt_flags |= MNT_RELATIME;
break;
default:
return -EINVAL;
}
CLASS(fd, f)(fs_fd);
if (fd_empty(f))
return -EBADF;
if (fd_file(f)->f_op != &fscontext_fops)
return -EINVAL;
fc = fd_file(f)->private_data;
ret = mutex_lock_interruptible(&fc->uapi_mutex);
if (ret < 0)
return ret;
/* There must be a valid superblock or we can't mount it */
ret = -EINVAL;
if (!fc->root)
goto err_unlock;
ret = -EPERM;
if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
pr_warn("VFS: Mount too revealing\n");
goto err_unlock;
}
ret = -EBUSY;
if (fc->phase != FS_CONTEXT_AWAITING_MOUNT)
goto err_unlock;
if (fc->sb_flags & SB_MANDLOCK)
warn_mandlock();
newmount.mnt = vfs_create_mount(fc);
if (IS_ERR(newmount.mnt)) {
ret = PTR_ERR(newmount.mnt);
goto err_unlock;
}
newmount.dentry = dget(fc->root);
newmount.mnt->mnt_flags = mnt_flags;
/* We've done the mount bit - now move the file context into more or
* less the same state as if we'd done an fspick(). We don't want to
* do any memory allocation or anything like that at this point as we
* don't want to have to handle any errors incurred.
*/
vfs_clean_context(fc);
ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true);
if (IS_ERR(ns)) {
ret = PTR_ERR(ns);
goto err_path;
}
mnt = real_mount(newmount.mnt);
ns->root = mnt;
ns->nr_mounts = 1;
mnt_add_to_ns(ns, mnt);
mntget(newmount.mnt);
/* Attach to an apparent O_PATH fd with a note that we need to unmount
* it, not just simply put it.
*/
file = dentry_open(&newmount, O_PATH, fc->cred);
if (IS_ERR(file)) {
dissolve_on_fput(newmount.mnt);
ret = PTR_ERR(file);
goto err_path;
}
file->f_mode |= FMODE_NEED_UNMOUNT;
ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0);
if (ret >= 0)
fd_install(ret, file);
else
fput(file);
err_path:
path_put(&newmount);
err_unlock:
mutex_unlock(&fc->uapi_mutex);
return ret;
}
static inline int vfs_move_mount(struct path *from_path, struct path *to_path,
enum mnt_tree_flags_t mflags)
{
int ret;
ret = security_move_mount(from_path, to_path);
if (ret)
return ret;
if (mflags & MNT_TREE_PROPAGATION)
return do_set_group(from_path, to_path);
return do_move_mount(from_path, to_path, mflags);
}
/*
* Move a mount from one place to another. In combination with
* fsopen()/fsmount() this is used to install a new mount and in combination
* with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy
* a mount subtree.
*
* Note the flags value is a combination of MOVE_MOUNT_* flags.
*/
SYSCALL_DEFINE5(move_mount,
int, from_dfd, const char __user *, from_pathname,
int, to_dfd, const char __user *, to_pathname,
unsigned int, flags)
{
struct path to_path __free(path_put) = {};
struct path from_path __free(path_put) = {};
struct filename *to_name __free(putname) = NULL;
struct filename *from_name __free(putname) = NULL;
unsigned int lflags, uflags;
enum mnt_tree_flags_t mflags = 0;
int ret = 0;
if (!may_mount())
return -EPERM;
if (flags & ~MOVE_MOUNT__MASK)
return -EINVAL;
if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) ==
(MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP))
return -EINVAL;
if (flags & MOVE_MOUNT_SET_GROUP) mflags |= MNT_TREE_PROPAGATION;
if (flags & MOVE_MOUNT_BENEATH) mflags |= MNT_TREE_BENEATH;
lflags = 0;
if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW;
if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT;
uflags = 0;
if (flags & MOVE_MOUNT_F_EMPTY_PATH) uflags = AT_EMPTY_PATH;
from_name = getname_maybe_null(from_pathname, uflags);
if (IS_ERR(from_name))
return PTR_ERR(from_name);
lflags = 0;
if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW;
if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT;
uflags = 0;
if (flags & MOVE_MOUNT_T_EMPTY_PATH) uflags = AT_EMPTY_PATH;
to_name = getname_maybe_null(to_pathname, uflags);
if (IS_ERR(to_name))
return PTR_ERR(to_name);
if (!to_name && to_dfd >= 0) {
CLASS(fd_raw, f_to)(to_dfd);
if (fd_empty(f_to))
return -EBADF;
to_path = fd_file(f_to)->f_path;
path_get(&to_path);
} else {
ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL);
if (ret)
return ret;
}
if (!from_name && from_dfd >= 0) {
CLASS(fd_raw, f_from)(from_dfd);
if (fd_empty(f_from))
return -EBADF;
return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags);
}
ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL);
if (ret)
return ret;
return vfs_move_mount(&from_path, &to_path, mflags);
}
/*
* Return true if path is reachable from root
*
* namespace_sem or mount_lock is held
*/
bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
const struct path *root)
{
while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) {
dentry = mnt->mnt_mountpoint;
mnt = mnt->mnt_parent;
}
return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry);
}
bool path_is_under(const struct path *path1, const struct path *path2)
{
bool res;
read_seqlock_excl(&mount_lock);
res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
read_sequnlock_excl(&mount_lock);
return res;
}
EXPORT_SYMBOL(path_is_under);
/*
* pivot_root Semantics:
* Moves the root file system of the current process to the directory put_old,
* makes new_root as the new root file system of the current process, and sets
* root/cwd of all processes which had them on the current root to new_root.
*
* Restrictions:
* The new_root and put_old must be directories, and must not be on the
* same file system as the current process root. The put_old must be
* underneath new_root, i.e. adding a non-zero number of /.. to the string
* pointed to by put_old must yield the same directory as new_root. No other
* file system may be mounted on put_old. After all, new_root is a mountpoint.
*
* Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem.
* See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives
* in this situation.
*
* Notes:
* - we don't move root/cwd if they are not at the root (reason: if something
* cared enough to change them, it's probably wrong to force them elsewhere)
* - it's okay to pick a root that isn't the root of a file system, e.g.
* /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
* though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
* first.
*/
SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
const char __user *, put_old)
{
struct path new, old, root;
struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent;
struct mountpoint *old_mp, *root_mp;
int error;
if (!may_mount())
return -EPERM;
error = user_path_at(AT_FDCWD, new_root,
LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new);
if (error)
goto out0;
error = user_path_at(AT_FDCWD, put_old,
LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old);
if (error)
goto out1;
error = security_sb_pivotroot(&old, &new);
if (error)
goto out2;
get_fs_root(current->fs, &root);
old_mp = lock_mount(&old);
error = PTR_ERR(old_mp);
if (IS_ERR(old_mp))
goto out3;
error = -EINVAL;
new_mnt = real_mount(new.mnt);
root_mnt = real_mount(root.mnt);
old_mnt = real_mount(old.mnt);
ex_parent = new_mnt->mnt_parent;
root_parent = root_mnt->mnt_parent;
if (IS_MNT_SHARED(old_mnt) ||
IS_MNT_SHARED(ex_parent) ||
IS_MNT_SHARED(root_parent))
goto out4;
if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
goto out4;
if (new_mnt->mnt.mnt_flags & MNT_LOCKED)
goto out4;
error = -ENOENT;
if (d_unlinked(new.dentry))
goto out4;
error = -EBUSY;
if (new_mnt == root_mnt || old_mnt == root_mnt)
goto out4; /* loop, on the same file system */
error = -EINVAL;
if (!path_mounted(&root))
goto out4; /* not a mountpoint */
if (!mnt_has_parent(root_mnt))
goto out4; /* not attached */
if (!path_mounted(&new))
goto out4; /* not a mountpoint */
if (!mnt_has_parent(new_mnt))
goto out4; /* not attached */
/* make sure we can reach put_old from new_root */
if (!is_path_reachable(old_mnt, old.dentry, &new))
goto out4;
/* make certain new is below the root */
if (!is_path_reachable(new_mnt, new.dentry, &root))
goto out4;
lock_mount_hash();
umount_mnt(new_mnt);
root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */
if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
new_mnt->mnt.mnt_flags |= MNT_LOCKED;
root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
}
/* mount old root on put_old */
attach_mnt(root_mnt, old_mnt, old_mp, false);
/* mount new_root on / */
attach_mnt(new_mnt, root_parent, root_mp, false);
mnt_add_count(root_parent, -1);
touch_mnt_namespace(current->nsproxy->mnt_ns);
/* A moved mount should not expire automatically */
list_del_init(&new_mnt->mnt_expire);
put_mountpoint(root_mp);
unlock_mount_hash();
mnt_notify_add(root_mnt);
mnt_notify_add(new_mnt);
chroot_fs_refs(&root, &new);
error = 0;
out4:
unlock_mount(old_mp);
if (!error)
mntput_no_expire(ex_parent);
out3:
path_put(&root);
out2:
path_put(&old);
out1:
path_put(&new);
out0:
return error;
}
static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt)
{
unsigned int flags = mnt->mnt.mnt_flags;
/* flags to clear */
flags &= ~kattr->attr_clr;
/* flags to raise */
flags |= kattr->attr_set;
return flags;
}
static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
{
struct vfsmount *m = &mnt->mnt;
struct user_namespace *fs_userns = m->mnt_sb->s_user_ns;
if (!kattr->mnt_idmap)
return 0;
/*
* Creating an idmapped mount with the filesystem wide idmapping
* doesn't make sense so block that. We don't allow mushy semantics.
*/
if (kattr->mnt_userns == m->mnt_sb->s_user_ns)
return -EINVAL;
/*
* We only allow an mount to change it's idmapping if it has
* never been accessible to userspace.
*/
if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE) && is_idmapped_mnt(m))
return -EPERM;
/* The underlying filesystem doesn't support idmapped mounts yet. */
if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP))
return -EINVAL;
/* The filesystem has turned off idmapped mounts. */
if (m->mnt_sb->s_iflags & SB_I_NOIDMAP)
return -EINVAL;
/* We're not controlling the superblock. */
if (!ns_capable(fs_userns, CAP_SYS_ADMIN))
return -EPERM;
/* Mount has already been visible in the filesystem hierarchy. */
if (!is_anon_ns(mnt->mnt_ns))
return -EINVAL;
return 0;
}
/**
* mnt_allow_writers() - check whether the attribute change allows writers
* @kattr: the new mount attributes
* @mnt: the mount to which @kattr will be applied
*
* Check whether thew new mount attributes in @kattr allow concurrent writers.
*
* Return: true if writers need to be held, false if not
*/
static inline bool mnt_allow_writers(const struct mount_kattr *kattr,
const struct mount *mnt)
{
return (!(kattr->attr_set & MNT_READONLY) ||
(mnt->mnt.mnt_flags & MNT_READONLY)) &&
!kattr->mnt_idmap;
}
static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt)
{
struct mount *m;
int err;
for (m = mnt; m; m = next_mnt(m, mnt)) {
if (!can_change_locked_flags(m, recalc_flags(kattr, m))) {
err = -EPERM;
break;
}
err = can_idmap_mount(kattr, m);
if (err)
break;
if (!mnt_allow_writers(kattr, m)) {
err = mnt_hold_writers(m);
if (err)
break;
}
if (!(kattr->kflags & MOUNT_KATTR_RECURSE))
return 0;
}
if (err) {
struct mount *p;
/*
* If we had to call mnt_hold_writers() MNT_WRITE_HOLD will
* be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all
* mounts and needs to take care to include the first mount.
*/
for (p = mnt; p; p = next_mnt(p, mnt)) {
/* If we had to hold writers unblock them. */
if (p->mnt.mnt_flags & MNT_WRITE_HOLD)
mnt_unhold_writers(p);
/*
* We're done once the first mount we changed got
* MNT_WRITE_HOLD unset.
*/
if (p == m)
break;
}
}
return err;
}
static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
{
struct mnt_idmap *old_idmap;
if (!kattr->mnt_idmap)
return;
old_idmap = mnt_idmap(&mnt->mnt);
/* Pairs with smp_load_acquire() in mnt_idmap(). */
smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap));
mnt_idmap_put(old_idmap);
}
static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt)
{
struct mount *m;
for (m = mnt; m; m = next_mnt(m, mnt)) {
unsigned int flags;
do_idmap_mount(kattr, m);
flags = recalc_flags(kattr, m);
WRITE_ONCE(m->mnt.mnt_flags, flags);
/* If we had to hold writers unblock them. */
if (m->mnt.mnt_flags & MNT_WRITE_HOLD)
mnt_unhold_writers(m);
if (kattr->propagation)
change_mnt_propagation(m, kattr->propagation);
if (!(kattr->kflags & MOUNT_KATTR_RECURSE))
break;
}
touch_mnt_namespace(mnt->mnt_ns);
}
static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
{
struct mount *mnt = real_mount(path->mnt);
int err = 0;
if (!path_mounted(path))
return -EINVAL;
if (kattr->mnt_userns) {
struct mnt_idmap *mnt_idmap;
mnt_idmap = alloc_mnt_idmap(kattr->mnt_userns);
if (IS_ERR(mnt_idmap))
return PTR_ERR(mnt_idmap);
kattr->mnt_idmap = mnt_idmap;
}
if (kattr->propagation) {
/*
* Only take namespace_lock() if we're actually changing
* propagation.
*/
namespace_lock();
if (kattr->propagation == MS_SHARED) {
err = invent_group_ids(mnt, kattr->kflags & MOUNT_KATTR_RECURSE);
if (err) {
namespace_unlock();
return err;
}
}
}
err = -EINVAL;
lock_mount_hash();
/* Ensure that this isn't anything purely vfs internal. */
if (!is_mounted(&mnt->mnt))
goto out;
/*
* If this is an attached mount make sure it's located in the callers
* mount namespace. If it's not don't let the caller interact with it.
*
* If this mount doesn't have a parent it's most often simply a
* detached mount with an anonymous mount namespace. IOW, something
* that's simply not attached yet. But there are apparently also users
* that do change mount properties on the rootfs itself. That obviously
* neither has a parent nor is it a detached mount so we cannot
* unconditionally check for detached mounts.
*/
if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
goto out;
/*
* First, we get the mount tree in a shape where we can change mount
* properties without failure. If we succeeded to do so we commit all
* changes and if we failed we clean up.
*/
err = mount_setattr_prepare(kattr, mnt);
if (!err)
mount_setattr_commit(kattr, mnt);
out:
unlock_mount_hash();
if (kattr->propagation) {
if (err)
cleanup_group_ids(mnt, NULL);
namespace_unlock();
}
return err;
}
static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
struct mount_kattr *kattr)
{
struct ns_common *ns;
struct user_namespace *mnt_userns;
if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
return 0;
if (attr->attr_clr & MOUNT_ATTR_IDMAP) {
/*
* We can only remove an idmapping if it's never been
* exposed to userspace.
*/
if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE))
return -EINVAL;
/*
* Removal of idmappings is equivalent to setting
* nop_mnt_idmap.
*/
if (!(attr->attr_set & MOUNT_ATTR_IDMAP)) {
kattr->mnt_idmap = &nop_mnt_idmap;
return 0;
}
}
if (attr->userns_fd > INT_MAX)
return -EINVAL;
CLASS(fd, f)(attr->userns_fd);
if (fd_empty(f))
return -EBADF;
if (!proc_ns_file(fd_file(f)))
return -EINVAL;
ns = get_proc_ns(file_inode(fd_file(f)));
if (ns->ops->type != CLONE_NEWUSER)
return -EINVAL;
/*
* The initial idmapping cannot be used to create an idmapped
* mount. We use the initial idmapping as an indicator of a mount
* that is not idmapped. It can simply be passed into helpers that
* are aware of idmapped mounts as a convenient shortcut. A user
* can just create a dedicated identity mapping to achieve the same
* result.
*/
mnt_userns = container_of(ns, struct user_namespace, ns);
if (mnt_userns == &init_user_ns)
return -EPERM;
/* We're not controlling the target namespace. */
if (!ns_capable(mnt_userns, CAP_SYS_ADMIN))
return -EPERM;
kattr->mnt_userns = get_user_ns(mnt_userns);
return 0;
}
static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
struct mount_kattr *kattr)
{
if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS)
return -EINVAL;
if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1)
return -EINVAL;
kattr->propagation = attr->propagation;
if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS)
return -EINVAL;
kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set);
kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr);
/*
* Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap,
* users wanting to transition to a different atime setting cannot
* simply specify the atime setting in @attr_set, but must also
* specify MOUNT_ATTR__ATIME in the @attr_clr field.
* So ensure that MOUNT_ATTR__ATIME can't be partially set in
* @attr_clr and that @attr_set can't have any atime bits set if
* MOUNT_ATTR__ATIME isn't set in @attr_clr.
*/
if (attr->attr_clr & MOUNT_ATTR__ATIME) {
if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME)
return -EINVAL;
/*
* Clear all previous time settings as they are mutually
* exclusive.
*/
kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME;
switch (attr->attr_set & MOUNT_ATTR__ATIME) {
case MOUNT_ATTR_RELATIME:
kattr->attr_set |= MNT_RELATIME;
break;
case MOUNT_ATTR_NOATIME:
kattr->attr_set |= MNT_NOATIME;
break;
case MOUNT_ATTR_STRICTATIME:
break;
default:
return -EINVAL;
}
} else {
if (attr->attr_set & MOUNT_ATTR__ATIME)
return -EINVAL;
}
return build_mount_idmapped(attr, usize, kattr);
}
static void finish_mount_kattr(struct mount_kattr *kattr)
{
if (kattr->mnt_userns) {
put_user_ns(kattr->mnt_userns);
kattr->mnt_userns = NULL;
}
if (kattr->mnt_idmap)
mnt_idmap_put(kattr->mnt_idmap);
}
static int wants_mount_setattr(struct mount_attr __user *uattr, size_t usize,
struct mount_kattr *kattr)
{
int ret;
struct mount_attr attr;
BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0);
if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
if (unlikely(usize < MOUNT_ATTR_SIZE_VER0))
return -EINVAL;
if (!may_mount())
return -EPERM;
ret = copy_struct_from_user(&attr, sizeof(attr), uattr, usize);
if (ret)
return ret;
/* Don't bother walking through the mounts if this is a nop. */
if (attr.attr_set == 0 &&
attr.attr_clr == 0 &&
attr.propagation == 0)
return 0; /* Tell caller to not bother. */
ret = build_mount_kattr(&attr, usize, kattr);
if (ret < 0)
return ret;
return 1;
}
SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
unsigned int, flags, struct mount_attr __user *, uattr,
size_t, usize)
{
int err;
struct path target;
struct mount_kattr kattr;
unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
if (flags & ~(AT_EMPTY_PATH |
AT_RECURSIVE |
AT_SYMLINK_NOFOLLOW |
AT_NO_AUTOMOUNT))
return -EINVAL;
if (flags & AT_NO_AUTOMOUNT)
lookup_flags &= ~LOOKUP_AUTOMOUNT;
if (flags & AT_SYMLINK_NOFOLLOW)
lookup_flags &= ~LOOKUP_FOLLOW;
if (flags & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
kattr = (struct mount_kattr) {
.lookup_flags = lookup_flags,
};
if (flags & AT_RECURSIVE)
kattr.kflags |= MOUNT_KATTR_RECURSE;
err = wants_mount_setattr(uattr, usize, &kattr);
if (err <= 0)
return err;
err = user_path_at(dfd, path, kattr.lookup_flags, &target);
if (!err) {
err = do_mount_setattr(&target, &kattr);
path_put(&target);
}
finish_mount_kattr(&kattr);
return err;
}
SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
unsigned, flags, struct mount_attr __user *, uattr,
size_t, usize)
{
struct file __free(fput) *file = NULL;
int fd;
if (!uattr && usize)
return -EINVAL;
file = vfs_open_tree(dfd, filename, flags);
if (IS_ERR(file))
return PTR_ERR(file);
if (uattr) {
int ret;
struct mount_kattr kattr = {};
kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
if (flags & AT_RECURSIVE)
kattr.kflags |= MOUNT_KATTR_RECURSE;
ret = wants_mount_setattr(uattr, usize, &kattr);
if (ret < 0)
return ret;
if (ret) {
ret = do_mount_setattr(&file->f_path, &kattr);
if (ret)
return ret;
finish_mount_kattr(&kattr);
}
}
fd = get_unused_fd_flags(flags & O_CLOEXEC);
if (fd < 0)
return fd;
fd_install(fd, no_free_ptr(file));
return fd;
}
int show_path(struct seq_file *m, struct dentry *root)
{
if (root->d_sb->s_op->show_path)
return root->d_sb->s_op->show_path(m, root);
seq_dentry(m, root, " \t\n\\");
return 0;
}
static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns)
{
struct mount *mnt = mnt_find_id_at(ns, id);
if (!mnt || mnt->mnt_id_unique != id)
return NULL;
return &mnt->mnt;
}
struct kstatmount {
struct statmount __user *buf;
size_t bufsize;
struct vfsmount *mnt;
struct mnt_idmap *idmap;
u64 mask;
struct path root;
struct seq_file seq;
/* Must be last --ends in a flexible-array member. */
struct statmount sm;
};
static u64 mnt_to_attr_flags(struct vfsmount *mnt)
{
unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags);
u64 attr_flags = 0;
if (mnt_flags & MNT_READONLY)
attr_flags |= MOUNT_ATTR_RDONLY;
if (mnt_flags & MNT_NOSUID)
attr_flags |= MOUNT_ATTR_NOSUID;
if (mnt_flags & MNT_NODEV)
attr_flags |= MOUNT_ATTR_NODEV;
if (mnt_flags & MNT_NOEXEC)
attr_flags |= MOUNT_ATTR_NOEXEC;
if (mnt_flags & MNT_NODIRATIME)
attr_flags |= MOUNT_ATTR_NODIRATIME;
if (mnt_flags & MNT_NOSYMFOLLOW)
attr_flags |= MOUNT_ATTR_NOSYMFOLLOW;
if (mnt_flags & MNT_NOATIME)
attr_flags |= MOUNT_ATTR_NOATIME;
else if (mnt_flags & MNT_RELATIME)
attr_flags |= MOUNT_ATTR_RELATIME;
else
attr_flags |= MOUNT_ATTR_STRICTATIME;
if (is_idmapped_mnt(mnt))
attr_flags |= MOUNT_ATTR_IDMAP;
return attr_flags;
}
static u64 mnt_to_propagation_flags(struct mount *m)
{
u64 propagation = 0;
if (IS_MNT_SHARED(m))
propagation |= MS_SHARED;
if (IS_MNT_SLAVE(m))
propagation |= MS_SLAVE;
if (IS_MNT_UNBINDABLE(m))
propagation |= MS_UNBINDABLE;
if (!propagation)
propagation |= MS_PRIVATE;
return propagation;
}
static void statmount_sb_basic(struct kstatmount *s)
{
struct super_block *sb = s->mnt->mnt_sb;
s->sm.mask |= STATMOUNT_SB_BASIC;
s->sm.sb_dev_major = MAJOR(sb->s_dev);
s->sm.sb_dev_minor = MINOR(sb->s_dev);
s->sm.sb_magic = sb->s_magic;
s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME);
}
static void statmount_mnt_basic(struct kstatmount *s)
{
struct mount *m = real_mount(s->mnt);
s->sm.mask |= STATMOUNT_MNT_BASIC;
s->sm.mnt_id = m->mnt_id_unique;
s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
s->sm.mnt_id_old = m->mnt_id;
s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
s->sm.mnt_propagation = mnt_to_propagation_flags(m);
s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0;
s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0;
}
static void statmount_propagate_from(struct kstatmount *s)
{
struct mount *m = real_mount(s->mnt);
s->sm.mask |= STATMOUNT_PROPAGATE_FROM;
if (IS_MNT_SLAVE(m))
s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root);
}
static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq)
{
int ret;
size_t start = seq->count;
ret = show_path(seq, s->mnt->mnt_root);
if (ret)
return ret;
if (unlikely(seq_has_overflowed(seq)))
return -EAGAIN;
/*
* Unescape the result. It would be better if supplied string was not
* escaped in the first place, but that's a pretty invasive change.
*/
seq->buf[seq->count] = '\0';
seq->count = start;
seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
return 0;
}
static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq)
{
struct vfsmount *mnt = s->mnt;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
int err;
err = seq_path_root(seq, &mnt_path, &s->root, "");
return err == SEQ_SKIP ? 0 : err;
}
static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq)
{
struct super_block *sb = s->mnt->mnt_sb;
seq_puts(seq, sb->s_type->name);
return 0;
}
static void statmount_fs_subtype(struct kstatmount *s, struct seq_file *seq)
{
struct super_block *sb = s->mnt->mnt_sb;
if (sb->s_subtype)
seq_puts(seq, sb->s_subtype);
}
static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq)
{
struct super_block *sb = s->mnt->mnt_sb;
struct mount *r = real_mount(s->mnt);
if (sb->s_op->show_devname) {
size_t start = seq->count;
int ret;
ret = sb->s_op->show_devname(seq, s->mnt->mnt_root);
if (ret)
return ret;
if (unlikely(seq_has_overflowed(seq)))
return -EAGAIN;
/* Unescape the result */
seq->buf[seq->count] = '\0';
seq->count = start;
seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
} else if (r->mnt_devname) {
seq_puts(seq, r->mnt_devname);
}
return 0;
}
static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns)
{
s->sm.mask |= STATMOUNT_MNT_NS_ID;
s->sm.mnt_ns_id = ns->seq;
}
static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
{
struct vfsmount *mnt = s->mnt;
struct super_block *sb = mnt->mnt_sb;
size_t start = seq->count;
int err;
err = security_sb_show_options(seq, sb);
if (err)
return err;
if (sb->s_op->show_options) {
err = sb->s_op->show_options(seq, mnt->mnt_root);
if (err)
return err;
}
if (unlikely(seq_has_overflowed(seq)))
return -EAGAIN;
if (seq->count == start)
return 0;
/* skip leading comma */
memmove(seq->buf + start, seq->buf + start + 1,
seq->count - start - 1);
seq->count--;
return 0;
}
static inline int statmount_opt_process(struct seq_file *seq, size_t start)
{
char *buf_end, *opt_end, *src, *dst;
int count = 0;
if (unlikely(seq_has_overflowed(seq)))
return -EAGAIN;
buf_end = seq->buf + seq->count;
dst = seq->buf + start;
src = dst + 1; /* skip initial comma */
if (src >= buf_end) {
seq->count = start;
return 0;
}
*buf_end = '\0';
for (; src < buf_end; src = opt_end + 1) {
opt_end = strchrnul(src, ',');
*opt_end = '\0';
dst += string_unescape(src, dst, 0, UNESCAPE_OCTAL) + 1;
if (WARN_ON_ONCE(++count == INT_MAX))
return -EOVERFLOW;
}
seq->count = dst - 1 - seq->buf;
return count;
}
static int statmount_opt_array(struct kstatmount *s, struct seq_file *seq)
{
struct vfsmount *mnt = s->mnt;
struct super_block *sb = mnt->mnt_sb;
size_t start = seq->count;
int err;
if (!sb->s_op->show_options)
return 0;
err = sb->s_op->show_options(seq, mnt->mnt_root);
if (err)
return err;
err = statmount_opt_process(seq, start);
if (err < 0)
return err;
s->sm.opt_num = err;
return 0;
}
static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq)
{
struct vfsmount *mnt = s->mnt;
struct super_block *sb = mnt->mnt_sb;
size_t start = seq->count;
int err;
err = security_sb_show_options(seq, sb);
if (err)
return err;
err = statmount_opt_process(seq, start);
if (err < 0)
return err;
s->sm.opt_sec_num = err;
return 0;
}
static inline int statmount_mnt_uidmap(struct kstatmount *s, struct seq_file *seq)
{
int ret;
ret = statmount_mnt_idmap(s->idmap, seq, true);
if (ret < 0)
return ret;
s->sm.mnt_uidmap_num = ret;
/*
* Always raise STATMOUNT_MNT_UIDMAP even if there are no valid
* mappings. This allows userspace to distinguish between a
* non-idmapped mount and an idmapped mount where none of the
* individual mappings are valid in the caller's idmapping.
*/
if (is_valid_mnt_idmap(s->idmap))
s->sm.mask |= STATMOUNT_MNT_UIDMAP;
return 0;
}
static inline int statmount_mnt_gidmap(struct kstatmount *s, struct seq_file *seq)
{
int ret;
ret = statmount_mnt_idmap(s->idmap, seq, false);
if (ret < 0)
return ret;
s->sm.mnt_gidmap_num = ret;
/*
* Always raise STATMOUNT_MNT_GIDMAP even if there are no valid
* mappings. This allows userspace to distinguish between a
* non-idmapped mount and an idmapped mount where none of the
* individual mappings are valid in the caller's idmapping.
*/
if (is_valid_mnt_idmap(s->idmap))
s->sm.mask |= STATMOUNT_MNT_GIDMAP;
return 0;
}
static int statmount_string(struct kstatmount *s, u64 flag)
{
int ret = 0;
size_t kbufsize;
struct seq_file *seq = &s->seq;
struct statmount *sm = &s->sm;
u32 start, *offp;
/* Reserve an empty string at the beginning for any unset offsets */
if (!seq->count)
seq_putc(seq, 0);
start = seq->count;
switch (flag) {
case STATMOUNT_FS_TYPE:
offp = &sm->fs_type;
ret = statmount_fs_type(s, seq);
break;
case STATMOUNT_MNT_ROOT:
offp = &sm->mnt_root;
ret = statmount_mnt_root(s, seq);
break;
case STATMOUNT_MNT_POINT:
offp = &sm->mnt_point;
ret = statmount_mnt_point(s, seq);
break;
case STATMOUNT_MNT_OPTS:
offp = &sm->mnt_opts;
ret = statmount_mnt_opts(s, seq);
break;
case STATMOUNT_OPT_ARRAY:
offp = &sm->opt_array;
ret = statmount_opt_array(s, seq);
break;
case STATMOUNT_OPT_SEC_ARRAY:
offp = &sm->opt_sec_array;
ret = statmount_opt_sec_array(s, seq);
break;
case STATMOUNT_FS_SUBTYPE:
offp = &sm->fs_subtype;
statmount_fs_subtype(s, seq);
break;
case STATMOUNT_SB_SOURCE:
offp = &sm->sb_source;
ret = statmount_sb_source(s, seq);
break;
case STATMOUNT_MNT_UIDMAP:
sm->mnt_uidmap = start;
ret = statmount_mnt_uidmap(s, seq);
break;
case STATMOUNT_MNT_GIDMAP:
sm->mnt_gidmap = start;
ret = statmount_mnt_gidmap(s, seq);
break;
default:
WARN_ON_ONCE(true);
return -EINVAL;
}
/*
* If nothing was emitted, return to avoid setting the flag
* and terminating the buffer.
*/
if (seq->count == start)
return ret;
if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize)))
return -EOVERFLOW;
if (kbufsize >= s->bufsize)
return -EOVERFLOW;
/* signal a retry */
if (unlikely(seq_has_overflowed(seq)))
return -EAGAIN;
if (ret)
return ret;
seq->buf[seq->count++] = '\0';
sm->mask |= flag;
*offp = start;
return 0;
}
static int copy_statmount_to_user(struct kstatmount *s)
{
struct statmount *sm = &s->sm;
struct seq_file *seq = &s->seq;
char __user *str = ((char __user *)s->buf) + sizeof(*sm);
size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm));
if (seq->count && copy_to_user(str, seq->buf, seq->count))
return -EFAULT;
/* Return the number of bytes copied to the buffer */
sm->size = copysize + seq->count;
if (copy_to_user(s->buf, sm, copysize))
return -EFAULT;
return 0;
}
static struct mount *listmnt_next(struct mount *curr, bool reverse)
{
struct rb_node *node;
if (reverse)
node = rb_prev(&curr->mnt_node);
else
node = rb_next(&curr->mnt_node);
return node_to_mount(node);
}
static int grab_requested_root(struct mnt_namespace *ns, struct path *root)
{
struct mount *first, *child;
rwsem_assert_held(&namespace_sem);
/* We're looking at our own ns, just use get_fs_root. */
if (ns == current->nsproxy->mnt_ns) {
get_fs_root(current->fs, root);
return 0;
}
/*
* We have to find the first mount in our ns and use that, however it
* may not exist, so handle that properly.
*/
if (mnt_ns_empty(ns))
return -ENOENT;
first = child = ns->root;
for (;;) {
child = listmnt_next(child, false);
if (!child)
return -ENOENT;
if (child->mnt_parent == first)
break;
}
root->mnt = mntget(&child->mnt);
root->dentry = dget(root->mnt->mnt_root);
return 0;
}
/* This must be updated whenever a new flag is added */
#define STATMOUNT_SUPPORTED (STATMOUNT_SB_BASIC | \
STATMOUNT_MNT_BASIC | \
STATMOUNT_PROPAGATE_FROM | \
STATMOUNT_MNT_ROOT | \
STATMOUNT_MNT_POINT | \
STATMOUNT_FS_TYPE | \
STATMOUNT_MNT_NS_ID | \
STATMOUNT_MNT_OPTS | \
STATMOUNT_FS_SUBTYPE | \
STATMOUNT_SB_SOURCE | \
STATMOUNT_OPT_ARRAY | \
STATMOUNT_OPT_SEC_ARRAY | \
STATMOUNT_SUPPORTED_MASK)
static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
struct mnt_namespace *ns)
{
struct path root __free(path_put) = {};
struct mount *m;
int err;
/* Has the namespace already been emptied? */
if (mnt_ns_id && mnt_ns_empty(ns))
return -ENOENT;
s->mnt = lookup_mnt_in_ns(mnt_id, ns);
if (!s->mnt)
return -ENOENT;
err = grab_requested_root(ns, &root);
if (err)
return err;
/*
* Don't trigger audit denials. We just want to determine what
* mounts to show users.
*/
m = real_mount(s->mnt);
if (!is_path_reachable(m, m->mnt.mnt_root, &root) &&
!ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
err = security_sb_statfs(s->mnt->mnt_root);
if (err)
return err;
s->root = root;
s->idmap = mnt_idmap(s->mnt);
if (s->mask & STATMOUNT_SB_BASIC)
statmount_sb_basic(s);
if (s->mask & STATMOUNT_MNT_BASIC)
statmount_mnt_basic(s);
if (s->mask & STATMOUNT_PROPAGATE_FROM)
statmount_propagate_from(s);
if (s->mask & STATMOUNT_FS_TYPE)
err = statmount_string(s, STATMOUNT_FS_TYPE);
if (!err && s->mask & STATMOUNT_MNT_ROOT)
err = statmount_string(s, STATMOUNT_MNT_ROOT);
if (!err && s->mask & STATMOUNT_MNT_POINT)
err = statmount_string(s, STATMOUNT_MNT_POINT);
if (!err && s->mask & STATMOUNT_MNT_OPTS)
err = statmount_string(s, STATMOUNT_MNT_OPTS);
if (!err && s->mask & STATMOUNT_OPT_ARRAY)
err = statmount_string(s, STATMOUNT_OPT_ARRAY);
if (!err && s->mask & STATMOUNT_OPT_SEC_ARRAY)
err = statmount_string(s, STATMOUNT_OPT_SEC_ARRAY);
if (!err && s->mask & STATMOUNT_FS_SUBTYPE)
err = statmount_string(s, STATMOUNT_FS_SUBTYPE);
if (!err && s->mask & STATMOUNT_SB_SOURCE)
err = statmount_string(s, STATMOUNT_SB_SOURCE);
if (!err && s->mask & STATMOUNT_MNT_UIDMAP)
err = statmount_string(s, STATMOUNT_MNT_UIDMAP);
if (!err && s->mask & STATMOUNT_MNT_GIDMAP)
err = statmount_string(s, STATMOUNT_MNT_GIDMAP);
if (!err && s->mask & STATMOUNT_MNT_NS_ID)
statmount_mnt_ns_id(s, ns);
if (!err && s->mask & STATMOUNT_SUPPORTED_MASK) {
s->sm.mask |= STATMOUNT_SUPPORTED_MASK;
s->sm.supported_mask = STATMOUNT_SUPPORTED;
}
if (err)
return err;
/* Are there bits in the return mask not present in STATMOUNT_SUPPORTED? */
WARN_ON_ONCE(~STATMOUNT_SUPPORTED & s->sm.mask);
return 0;
}
static inline bool retry_statmount(const long ret, size_t *seq_size)
{
if (likely(ret != -EAGAIN))
return false;
if (unlikely(check_mul_overflow(*seq_size, 2, seq_size)))
return false;
if (unlikely(*seq_size > MAX_RW_COUNT))
return false;
return true;
}
#define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \
STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS | \
STATMOUNT_FS_SUBTYPE | STATMOUNT_SB_SOURCE | \
STATMOUNT_OPT_ARRAY | STATMOUNT_OPT_SEC_ARRAY | \
STATMOUNT_MNT_UIDMAP | STATMOUNT_MNT_GIDMAP)
static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
struct statmount __user *buf, size_t bufsize,
size_t seq_size)
{
if (!access_ok(buf, bufsize))
return -EFAULT;
memset(ks, 0, sizeof(*ks));
ks->mask = kreq->param;
ks->buf = buf;
ks->bufsize = bufsize;
if (ks->mask & STATMOUNT_STRING_REQ) {
if (bufsize == sizeof(ks->sm))
return -EOVERFLOW;
ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT);
if (!ks->seq.buf)
return -ENOMEM;
ks->seq.size = seq_size;
}
return 0;
}
static int copy_mnt_id_req(const struct mnt_id_req __user *req,
struct mnt_id_req *kreq)
{
int ret;
size_t usize;
BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1);
ret = get_user(usize, &req->size);
if (ret)
return -EFAULT;
if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
if (unlikely(usize < MNT_ID_REQ_SIZE_VER0))
return -EINVAL;
memset(kreq, 0, sizeof(*kreq));
ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
if (ret)
return ret;
if (kreq->spare != 0)
return -EINVAL;
/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET)
return -EINVAL;
return 0;
}
/*
* If the user requested a specific mount namespace id, look that up and return
* that, or if not simply grab a passive reference on our mount namespace and
* return that.
*/
static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq)
{
struct mnt_namespace *mnt_ns;
if (kreq->mnt_ns_id && kreq->spare)
return ERR_PTR(-EINVAL);
if (kreq->mnt_ns_id)
return lookup_mnt_ns(kreq->mnt_ns_id);
if (kreq->spare) {
struct ns_common *ns;
CLASS(fd, f)(kreq->spare);
if (fd_empty(f))
return ERR_PTR(-EBADF);
if (!proc_ns_file(fd_file(f)))
return ERR_PTR(-EINVAL);
ns = get_proc_ns(file_inode(fd_file(f)));
if (ns->ops->type != CLONE_NEWNS)
return ERR_PTR(-EINVAL);
mnt_ns = to_mnt_ns(ns);
} else {
mnt_ns = current->nsproxy->mnt_ns;
}
refcount_inc(&mnt_ns->passive);
return mnt_ns;
}
SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
struct statmount __user *, buf, size_t, bufsize,
unsigned int, flags)
{
struct mnt_namespace *ns __free(mnt_ns_release) = NULL;
struct kstatmount *ks __free(kfree) = NULL;
struct mnt_id_req kreq;
/* We currently support retrieval of 3 strings. */
size_t seq_size = 3 * PATH_MAX;
int ret;
if (flags)
return -EINVAL;
ret = copy_mnt_id_req(req, &kreq);
if (ret)
return ret;
ns = grab_requested_mnt_ns(&kreq);
if (!ns)
return -ENOENT;
if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) &&
!ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
return -ENOENT;
ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT);
if (!ks)
return -ENOMEM;
retry:
ret = prepare_kstatmount(ks, &kreq, buf, bufsize, seq_size);
if (ret)
return ret;
scoped_guard(rwsem_read, &namespace_sem)
ret = do_statmount(ks, kreq.mnt_id, kreq.mnt_ns_id, ns);
if (!ret)
ret = copy_statmount_to_user(ks);
kvfree(ks->seq.buf);
if (retry_statmount(ret, &seq_size))
goto retry;
return ret;
}
static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id,
u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids,
bool reverse)
{
struct path root __free(path_put) = {};
struct path orig;
struct mount *r, *first;
ssize_t ret;
rwsem_assert_held(&namespace_sem);
ret = grab_requested_root(ns, &root);
if (ret)
return ret;
if (mnt_parent_id == LSMT_ROOT) {
orig = root;
} else {
orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
if (!orig.mnt)
return -ENOENT;
orig.dentry = orig.mnt->mnt_root;
}
/*
* Don't trigger audit denials. We just want to determine what
* mounts to show users.
*/
if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &root) &&
!ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
ret = security_sb_statfs(orig.dentry);
if (ret)
return ret;
if (!last_mnt_id) {
if (reverse)
first = node_to_mount(ns->mnt_last_node);
else
first = node_to_mount(ns->mnt_first_node);
} else {
if (reverse)
first = mnt_find_id_at_reverse(ns, last_mnt_id - 1);
else
first = mnt_find_id_at(ns, last_mnt_id + 1);
}
for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) {
if (r->mnt_id_unique == mnt_parent_id)
continue;
if (!is_path_reachable(r, r->mnt.mnt_root, &orig))
continue;
*mnt_ids = r->mnt_id_unique;
mnt_ids++;
nr_mnt_ids--;
ret++;
}
return ret;
}
SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
{
u64 *kmnt_ids __free(kvfree) = NULL;
const size_t maxcount = 1000000;
struct mnt_namespace *ns __free(mnt_ns_release) = NULL;
struct mnt_id_req kreq;
u64 last_mnt_id;
ssize_t ret;
if (flags & ~LISTMOUNT_REVERSE)
return -EINVAL;
/*
* If the mount namespace really has more than 1 million mounts the
* caller must iterate over the mount namespace (and reconsider their
* system design...).
*/
if (unlikely(nr_mnt_ids > maxcount))
return -EOVERFLOW;
if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids)))
return -EFAULT;
ret = copy_mnt_id_req(req, &kreq);
if (ret)
return ret;
last_mnt_id = kreq.param;
/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET)
return -EINVAL;
kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kmnt_ids),
GFP_KERNEL_ACCOUNT);
if (!kmnt_ids)
return -ENOMEM;
ns = grab_requested_mnt_ns(&kreq);
if (!ns)
return -ENOENT;
if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) &&
!ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
return -ENOENT;
scoped_guard(rwsem_read, &namespace_sem)
ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids,
nr_mnt_ids, (flags & LISTMOUNT_REVERSE));
if (ret <= 0)
return ret;
if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids)))
return -EFAULT;
return ret;
}
static void __init init_mount_tree(void)
{
struct vfsmount *mnt;
struct mount *m;
struct mnt_namespace *ns;
struct path root;
mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL);
if (IS_ERR(mnt))
panic("Can't create rootfs");
ns = alloc_mnt_ns(&init_user_ns, false);
if (IS_ERR(ns))
panic("Can't allocate initial namespace");
m = real_mount(mnt);
ns->root = m;
ns->nr_mounts = 1;
mnt_add_to_ns(ns, m);
init_task.nsproxy->mnt_ns = ns;
get_mnt_ns(ns);
root.mnt = mnt;
root.dentry = mnt->mnt_root;
mnt->mnt_flags |= MNT_LOCKED;
set_fs_pwd(current->fs, &root);
set_fs_root(current->fs, &root);
mnt_ns_tree_add(ns);
}
void __init mnt_init(void)
{
int err;
mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
mount_hashtable = alloc_large_system_hash("Mount-cache",
sizeof(struct hlist_head),
mhash_entries, 19,
HASH_ZERO,
&m_hash_shift, &m_hash_mask, 0, 0);
mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
sizeof(struct hlist_head),
mphash_entries, 19,
HASH_ZERO,
&mp_hash_shift, &mp_hash_mask, 0, 0);
if (!mount_hashtable || !mountpoint_hashtable)
panic("Failed to allocate mount hash table\n");
kernfs_init();
err = sysfs_init();
if (err)
printk(KERN_WARNING "%s: sysfs_init error: %d\n",
__func__, err);
fs_kobj = kobject_create_and_add("fs", NULL);
if (!fs_kobj)
printk(KERN_WARNING "%s: kobj create error\n", __func__);
shmem_init();
init_rootfs();
init_mount_tree();
}
void put_mnt_ns(struct mnt_namespace *ns)
{
if (!refcount_dec_and_test(&ns->ns.count))
return;
drop_collected_mounts(&ns->root->mnt);
free_mnt_ns(ns);
}
struct vfsmount *kern_mount(struct file_system_type *type)
{
struct vfsmount *mnt;
mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
if (!IS_ERR(mnt)) {
/*
* it is a longterm mount, don't release mnt until
* we unmount before file sys is unregistered
*/
real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
}
return mnt;
}
EXPORT_SYMBOL_GPL(kern_mount);
void kern_unmount(struct vfsmount *mnt)
{
/* release long term mount so mount point can be released */
if (!IS_ERR(mnt)) {
mnt_make_shortterm(mnt);
synchronize_rcu(); /* yecchhh... */
mntput(mnt);
}
}
EXPORT_SYMBOL(kern_unmount);
void kern_unmount_array(struct vfsmount *mnt[], unsigned int num)
{
unsigned int i;
for (i = 0; i < num; i++)
mnt_make_shortterm(mnt[i]);
synchronize_rcu_expedited();
for (i = 0; i < num; i++)
mntput(mnt[i]);
}
EXPORT_SYMBOL(kern_unmount_array);
bool our_mnt(struct vfsmount *mnt)
{
return check_mnt(real_mount(mnt));
}
bool current_chrooted(void)
{
/* Does the current process have a non-standard root */
struct path ns_root;
struct path fs_root;
bool chrooted;
/* Find the namespace root */
ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt;
ns_root.dentry = ns_root.mnt->mnt_root;
path_get(&ns_root);
while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
;
get_fs_root(current->fs, &fs_root);
chrooted = !path_equal(&fs_root, &ns_root);
path_put(&fs_root);
path_put(&ns_root);
return chrooted;
}
static bool mnt_already_visible(struct mnt_namespace *ns,
const struct super_block *sb,
int *new_mnt_flags)
{
int new_flags = *new_mnt_flags;
struct mount *mnt, *n;
bool visible = false;
down_read(&namespace_sem);
rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
struct mount *child;
int mnt_flags;
if (mnt->mnt.mnt_sb->s_type != sb->s_type)
continue;
/* This mount is not fully visible if it's root directory
* is not the root directory of the filesystem.
*/
if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
continue;
/* A local view of the mount flags */
mnt_flags = mnt->mnt.mnt_flags;
/* Don't miss readonly hidden in the superblock flags */
if (sb_rdonly(mnt->mnt.mnt_sb))
mnt_flags |= MNT_LOCK_READONLY;
/* Verify the mount flags are equal to or more permissive
* than the proposed new mount.
*/
if ((mnt_flags & MNT_LOCK_READONLY) &&
!(new_flags & MNT_READONLY))
continue;
if ((mnt_flags & MNT_LOCK_ATIME) &&
((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
continue;
/* This mount is not fully visible if there are any
* locked child mounts that cover anything except for
* empty directories.
*/
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
/* Only worry about locked mounts */
if (!(child->mnt.mnt_flags & MNT_LOCKED))
continue;
/* Is the directory permanently empty? */
if (!is_empty_dir_inode(inode))
goto next;
}
/* Preserve the locked attributes */
*new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \
MNT_LOCK_ATIME);
visible = true;
goto found;
next: ;
}
found:
up_read(&namespace_sem);
return visible;
}
static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags)
{
const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV;
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
unsigned long s_iflags;
if (ns->user_ns == &init_user_ns)
return false;
/* Can this filesystem be too revealing? */
s_iflags = sb->s_iflags;
if (!(s_iflags & SB_I_USERNS_VISIBLE))
return false;
if ((s_iflags & required_iflags) != required_iflags) {
WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n",
required_iflags);
return true;
}
return !mnt_already_visible(ns, sb, new_mnt_flags);
}
bool mnt_may_suid(struct vfsmount *mnt)
{
/*
* Foreign mounts (accessed via fchdir or through /proc
* symlinks) are always treated as if they are nosuid. This
* prevents namespaces from trusting potentially unsafe
* suid/sgid bits, file caps, or security labels that originate
* in other namespaces.
*/
return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) &&
current_in_userns(mnt->mnt_sb->s_user_ns);
}
static struct ns_common *mntns_get(struct task_struct *task)
{
struct ns_common *ns = NULL;
struct nsproxy *nsproxy;
task_lock(task);
nsproxy = task->nsproxy;
if (nsproxy) {
ns = &nsproxy->mnt_ns->ns;
get_mnt_ns(to_mnt_ns(ns));
}
task_unlock(task);
return ns;
}
static void mntns_put(struct ns_common *ns)
{
put_mnt_ns(to_mnt_ns(ns));
}
static int mntns_install(struct nsset *nsset, struct ns_common *ns)
{
struct nsproxy *nsproxy = nsset->nsproxy;
struct fs_struct *fs = nsset->fs;
struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns;
struct user_namespace *user_ns = nsset->cred->user_ns;
struct path root;
int err;
if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(user_ns, CAP_SYS_CHROOT) ||
!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
if (is_anon_ns(mnt_ns))
return -EINVAL;
if (fs->users != 1)
return -EINVAL;
get_mnt_ns(mnt_ns);
old_mnt_ns = nsproxy->mnt_ns;
nsproxy->mnt_ns = mnt_ns;
/* Find the root */
err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt,
"/", LOOKUP_DOWN, &root);
if (err) {
/* revert to old namespace */
nsproxy->mnt_ns = old_mnt_ns;
put_mnt_ns(mnt_ns);
return err;
}
put_mnt_ns(old_mnt_ns);
/* Update the pwd and root */
set_fs_pwd(fs, &root);
set_fs_root(fs, &root);
path_put(&root);
return 0;
}
static struct user_namespace *mntns_owner(struct ns_common *ns)
{
return to_mnt_ns(ns)->user_ns;
}
const struct proc_ns_operations mntns_operations = {
.name = "mnt",
.type = CLONE_NEWNS,
.get = mntns_get,
.put = mntns_put,
.install = mntns_install,
.owner = mntns_owner,
};
#ifdef CONFIG_SYSCTL
static const struct ctl_table fs_namespace_sysctls[] = {
{
.procname = "mount-max",
.data = &sysctl_mount_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
},
};
static int __init init_fs_namespace_sysctls(void)
{
register_sysctl_init("fs", fs_namespace_sysctls);
return 0;
}
fs_initcall(init_fs_namespace_sysctls);
#endif /* CONFIG_SYSCTL */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_HIGHMEM_H
#define _LINUX_HIGHMEM_H
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/bug.h>
#include <linux/cacheflush.h>
#include <linux/kmsan.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include "highmem-internal.h"
/**
* kmap - Map a page for long term usage
* @page: Pointer to the page to be mapped
*
* Returns: The virtual address of the mapping
*
* Can only be invoked from preemptible task context because on 32bit
* systems with CONFIG_HIGHMEM enabled this function might sleep.
*
* For systems with CONFIG_HIGHMEM=n and for pages in the low memory area
* this returns the virtual address of the direct kernel mapping.
*
* The returned virtual address is globally visible and valid up to the
* point where it is unmapped via kunmap(). The pointer can be handed to
* other contexts.
*
* For highmem pages on 32bit systems this can be slow as the mapping space
* is limited and protected by a global lock. In case that there is no
* mapping slot available the function blocks until a slot is released via
* kunmap().
*/
static inline void *kmap(struct page *page);
/**
* kunmap - Unmap the virtual address mapped by kmap()
* @page: Pointer to the page which was mapped by kmap()
*
* Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
* pages in the low memory area.
*/
static inline void kunmap(struct page *page);
/**
* kmap_to_page - Get the page for a kmap'ed address
* @addr: The address to look up
*
* Returns: The page which is mapped to @addr.
*/
static inline struct page *kmap_to_page(void *addr);
/**
* kmap_flush_unused - Flush all unused kmap mappings in order to
* remove stray mappings
*/
static inline void kmap_flush_unused(void);
/**
* kmap_local_page - Map a page for temporary usage
* @page: Pointer to the page to be mapped
*
* Returns: The virtual address of the mapping
*
* Can be invoked from any context, including interrupts.
*
* Requires careful handling when nesting multiple mappings because the map
* management is stack based. The unmap has to be in the reverse order of
* the map operation:
*
* addr1 = kmap_local_page(page1);
* addr2 = kmap_local_page(page2);
* ...
* kunmap_local(addr2);
* kunmap_local(addr1);
*
* Unmapping addr1 before addr2 is invalid and causes malfunction.
*
* Contrary to kmap() mappings the mapping is only valid in the context of
* the caller and cannot be handed to other contexts.
*
* On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
* virtual address of the direct mapping. Only real highmem pages are
* temporarily mapped.
*
* While kmap_local_page() is significantly faster than kmap() for the highmem
* case it comes with restrictions about the pointer validity.
*
* On HIGHMEM enabled systems mapping a highmem page has the side effect of
* disabling migration in order to keep the virtual address stable across
* preemption. No caller of kmap_local_page() can rely on this side effect.
*/
static inline void *kmap_local_page(struct page *page);
/**
* kmap_local_folio - Map a page in this folio for temporary usage
* @folio: The folio containing the page.
* @offset: The byte offset within the folio which identifies the page.
*
* Requires careful handling when nesting multiple mappings because the map
* management is stack based. The unmap has to be in the reverse order of
* the map operation::
*
* addr1 = kmap_local_folio(folio1, offset1);
* addr2 = kmap_local_folio(folio2, offset2);
* ...
* kunmap_local(addr2);
* kunmap_local(addr1);
*
* Unmapping addr1 before addr2 is invalid and causes malfunction.
*
* Contrary to kmap() mappings the mapping is only valid in the context of
* the caller and cannot be handed to other contexts.
*
* On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
* virtual address of the direct mapping. Only real highmem pages are
* temporarily mapped.
*
* While it is significantly faster than kmap() for the highmem case it
* comes with restrictions about the pointer validity.
*
* On HIGHMEM enabled systems mapping a highmem page has the side effect of
* disabling migration in order to keep the virtual address stable across
* preemption. No caller of kmap_local_folio() can rely on this side effect.
*
* Context: Can be invoked from any context.
* Return: The virtual address of @offset.
*/
static inline void *kmap_local_folio(struct folio *folio, size_t offset);
/**
* kmap_atomic - Atomically map a page for temporary usage - Deprecated!
* @page: Pointer to the page to be mapped
*
* Returns: The virtual address of the mapping
*
* In fact a wrapper around kmap_local_page() which also disables pagefaults
* and, depending on PREEMPT_RT configuration, also CPU migration and
* preemption. Therefore users should not count on the latter two side effects.
*
* Mappings should always be released by kunmap_atomic().
*
* Do not use in new code. Use kmap_local_page() instead.
*
* It is used in atomic context when code wants to access the contents of a
* page that might be allocated from high memory (see __GFP_HIGHMEM), for
* example a page in the pagecache. The API has two functions, and they
* can be used in a manner similar to the following::
*
* // Find the page of interest.
* struct page *page = find_get_page(mapping, offset);
*
* // Gain access to the contents of that page.
* void *vaddr = kmap_atomic(page);
*
* // Do something to the contents of that page.
* memset(vaddr, 0, PAGE_SIZE);
*
* // Unmap that page.
* kunmap_atomic(vaddr);
*
* Note that the kunmap_atomic() call takes the result of the kmap_atomic()
* call, not the argument.
*
* If you need to map two pages because you want to copy from one page to
* another you need to keep the kmap_atomic calls strictly nested, like:
*
* vaddr1 = kmap_atomic(page1);
* vaddr2 = kmap_atomic(page2);
*
* memcpy(vaddr1, vaddr2, PAGE_SIZE);
*
* kunmap_atomic(vaddr2);
* kunmap_atomic(vaddr1);
*/
static inline void *kmap_atomic(struct page *page);
/* Highmem related interfaces for management code */
static inline unsigned long nr_free_highpages(void);
static inline unsigned long totalhigh_pages(void);
#ifndef ARCH_HAS_FLUSH_ANON_PAGE
static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
{
}
#endif
#ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE
static inline void flush_kernel_vmap_range(void *vaddr, int size)
{
}
static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
{
}
#endif
/* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
#ifndef clear_user_highpage
static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
{
void *addr = kmap_local_page(page);
clear_user_page(addr, vaddr, page);
kunmap_local(addr);
}
#endif
#ifndef vma_alloc_zeroed_movable_folio
/**
* vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA.
* @vma: The VMA the page is to be allocated for.
* @vaddr: The virtual address the page will be inserted into.
*
* This function will allocate a page suitable for inserting into this
* VMA at this virtual address. It may be allocated from highmem or
* the movable zone. An architecture may provide its own implementation.
*
* Return: A folio containing one allocated and zeroed page or NULL if
* we are out of memory.
*/
static inline
struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
unsigned long vaddr)
{
struct folio *folio;
folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
if (folio && user_alloc_needs_zeroing())
clear_user_highpage(&folio->page, vaddr);
return folio;
}
#endif
static inline void clear_highpage(struct page *page)
{
void *kaddr = kmap_local_page(page);
clear_page(kaddr);
kunmap_local(kaddr);
}
static inline void clear_highpage_kasan_tagged(struct page *page)
{
void *kaddr = kmap_local_page(page);
clear_page(kasan_reset_tag(kaddr));
kunmap_local(kaddr);
}
#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
static inline void tag_clear_highpage(struct page *page)
{
}
#endif
/*
* If we pass in a base or tail page, we can zero up to PAGE_SIZE.
* If we pass in a head page, we can zero up to the size of the compound page.
*/
#ifdef CONFIG_HIGHMEM
void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
unsigned start2, unsigned end2);
#else
static inline void zero_user_segments(struct page *page,
unsigned start1, unsigned end1,
unsigned start2, unsigned end2)
{ void *kaddr = kmap_local_page(page);
unsigned int i;
BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2);
kunmap_local(kaddr);
for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i);}
#endif
static inline void zero_user_segment(struct page *page,
unsigned start, unsigned end)
{
zero_user_segments(page, start, end, 0, 0);
}
static inline void zero_user(struct page *page,
unsigned start, unsigned size)
{
zero_user_segments(page, start, start + size, 0, 0);
}
#ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE
static inline void copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
char *vfrom, *vto;
vfrom = kmap_local_page(from);
vto = kmap_local_page(to);
copy_user_page(vto, vfrom, vaddr, to);
kmsan_unpoison_memory(page_address(to), PAGE_SIZE);
kunmap_local(vto);
kunmap_local(vfrom);
}
#endif
#ifndef __HAVE_ARCH_COPY_HIGHPAGE
static inline void copy_highpage(struct page *to, struct page *from)
{
char *vfrom, *vto;
vfrom = kmap_local_page(from);
vto = kmap_local_page(to);
copy_page(vto, vfrom);
kmsan_copy_page_meta(to, from);
kunmap_local(vto);
kunmap_local(vfrom);
}
#endif
#ifdef copy_mc_to_kernel
/*
* If architecture supports machine check exception handling, define the
* #MC versions of copy_user_highpage and copy_highpage. They copy a memory
* page with #MC in source page (@from) handled, and return the number
* of bytes not copied if there was a #MC, otherwise 0 for success.
*/
static inline int copy_mc_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
unsigned long ret;
char *vfrom, *vto;
vfrom = kmap_local_page(from);
vto = kmap_local_page(to);
ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE);
if (!ret)
kmsan_unpoison_memory(page_address(to), PAGE_SIZE);
kunmap_local(vto);
kunmap_local(vfrom);
if (ret)
memory_failure_queue(page_to_pfn(from), 0);
return ret;
}
static inline int copy_mc_highpage(struct page *to, struct page *from)
{
unsigned long ret;
char *vfrom, *vto;
vfrom = kmap_local_page(from);
vto = kmap_local_page(to);
ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE);
if (!ret)
kmsan_copy_page_meta(to, from);
kunmap_local(vto);
kunmap_local(vfrom);
if (ret)
memory_failure_queue(page_to_pfn(from), 0);
return ret;
}
#else
static inline int copy_mc_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
copy_user_highpage(to, from, vaddr, vma);
return 0;
}
static inline int copy_mc_highpage(struct page *to, struct page *from)
{
copy_highpage(to, from);
return 0;
}
#endif
static inline void memcpy_page(struct page *dst_page, size_t dst_off,
struct page *src_page, size_t src_off,
size_t len)
{
char *dst = kmap_local_page(dst_page);
char *src = kmap_local_page(src_page);
VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE);
memcpy(dst + dst_off, src + src_off, len);
kunmap_local(src);
kunmap_local(dst);
}
static inline void memset_page(struct page *page, size_t offset, int val,
size_t len)
{
char *addr = kmap_local_page(page);
VM_BUG_ON(offset + len > PAGE_SIZE);
memset(addr + offset, val, len);
kunmap_local(addr);
}
static inline void memcpy_from_page(char *to, struct page *page,
size_t offset, size_t len)
{
char *from = kmap_local_page(page);
VM_BUG_ON(offset + len > PAGE_SIZE);
memcpy(to, from + offset, len);
kunmap_local(from);
}
static inline void memcpy_to_page(struct page *page, size_t offset,
const char *from, size_t len)
{
char *to = kmap_local_page(page);
VM_BUG_ON(offset + len > PAGE_SIZE);
memcpy(to + offset, from, len);
flush_dcache_page(page);
kunmap_local(to);
}
static inline void memzero_page(struct page *page, size_t offset, size_t len)
{
char *addr = kmap_local_page(page);
VM_BUG_ON(offset + len > PAGE_SIZE);
memset(addr + offset, 0, len);
flush_dcache_page(page);
kunmap_local(addr);
}
/**
* memcpy_from_folio - Copy a range of bytes from a folio.
* @to: The memory to copy to.
* @folio: The folio to read from.
* @offset: The first byte in the folio to read.
* @len: The number of bytes to copy.
*/
static inline void memcpy_from_folio(char *to, struct folio *folio,
size_t offset, size_t len)
{
VM_BUG_ON(offset + len > folio_size(folio));
do {
const char *from = kmap_local_folio(folio, offset);
size_t chunk = len;
if (folio_test_highmem(folio) &&
chunk > PAGE_SIZE - offset_in_page(offset))
chunk = PAGE_SIZE - offset_in_page(offset);
memcpy(to, from, chunk);
kunmap_local(from);
to += chunk;
offset += chunk;
len -= chunk;
} while (len > 0);
}
/**
* memcpy_to_folio - Copy a range of bytes to a folio.
* @folio: The folio to write to.
* @offset: The first byte in the folio to store to.
* @from: The memory to copy from.
* @len: The number of bytes to copy.
*/
static inline void memcpy_to_folio(struct folio *folio, size_t offset,
const char *from, size_t len)
{
VM_BUG_ON(offset + len > folio_size(folio));
do {
char *to = kmap_local_folio(folio, offset);
size_t chunk = len;
if (folio_test_highmem(folio) &&
chunk > PAGE_SIZE - offset_in_page(offset))
chunk = PAGE_SIZE - offset_in_page(offset);
memcpy(to, from, chunk);
kunmap_local(to);
from += chunk;
offset += chunk;
len -= chunk;
} while (len > 0);
flush_dcache_folio(folio);
}
/**
* folio_zero_tail - Zero the tail of a folio.
* @folio: The folio to zero.
* @offset: The byte offset in the folio to start zeroing at.
* @kaddr: The address the folio is currently mapped to.
*
* If you have already used kmap_local_folio() to map a folio, written
* some data to it and now need to zero the end of the folio (and flush
* the dcache), you can use this function. If you do not have the
* folio kmapped (eg the folio has been partially populated by DMA),
* use folio_zero_range() or folio_zero_segment() instead.
*
* Return: An address which can be passed to kunmap_local().
*/
static inline __must_check void *folio_zero_tail(struct folio *folio,
size_t offset, void *kaddr)
{
size_t len = folio_size(folio) - offset;
if (folio_test_highmem(folio)) {
size_t max = PAGE_SIZE - offset_in_page(offset);
while (len > max) {
memset(kaddr, 0, max);
kunmap_local(kaddr);
len -= max;
offset += max;
max = PAGE_SIZE;
kaddr = kmap_local_folio(folio, offset);
}
}
memset(kaddr, 0, len);
flush_dcache_folio(folio);
return kaddr;
}
/**
* folio_fill_tail - Copy some data to a folio and pad with zeroes.
* @folio: The destination folio.
* @offset: The offset into @folio at which to start copying.
* @from: The data to copy.
* @len: How many bytes of data to copy.
*
* This function is most useful for filesystems which support inline data.
* When they want to copy data from the inode into the page cache, this
* function does everything for them. It supports large folios even on
* HIGHMEM configurations.
*/
static inline void folio_fill_tail(struct folio *folio, size_t offset,
const char *from, size_t len)
{
char *to = kmap_local_folio(folio, offset);
VM_BUG_ON(offset + len > folio_size(folio));
if (folio_test_highmem(folio)) {
size_t max = PAGE_SIZE - offset_in_page(offset);
while (len > max) {
memcpy(to, from, max);
kunmap_local(to);
len -= max;
from += max;
offset += max;
max = PAGE_SIZE;
to = kmap_local_folio(folio, offset);
}
}
memcpy(to, from, len);
to = folio_zero_tail(folio, offset + len, to + len);
kunmap_local(to);
}
/**
* memcpy_from_file_folio - Copy some bytes from a file folio.
* @to: The destination buffer.
* @folio: The folio to copy from.
* @pos: The position in the file.
* @len: The maximum number of bytes to copy.
*
* Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE
* if the folio comes from HIGHMEM, and by the size of the folio.
*
* Return: The number of bytes copied from the folio.
*/
static inline size_t memcpy_from_file_folio(char *to, struct folio *folio,
loff_t pos, size_t len)
{
size_t offset = offset_in_folio(folio, pos);
char *from = kmap_local_folio(folio, offset);
if (folio_test_highmem(folio)) {
offset = offset_in_page(offset);
len = min_t(size_t, len, PAGE_SIZE - offset);
} else
len = min(len, folio_size(folio) - offset);
memcpy(to, from, len);
kunmap_local(from);
return len;
}
/**
* folio_zero_segments() - Zero two byte ranges in a folio.
* @folio: The folio to write to.
* @start1: The first byte to zero.
* @xend1: One more than the last byte in the first range.
* @start2: The first byte to zero in the second range.
* @xend2: One more than the last byte in the second range.
*/
static inline void folio_zero_segments(struct folio *folio,
size_t start1, size_t xend1, size_t start2, size_t xend2)
{
zero_user_segments(&folio->page, start1, xend1, start2, xend2);
}
/**
* folio_zero_segment() - Zero a byte range in a folio.
* @folio: The folio to write to.
* @start: The first byte to zero.
* @xend: One more than the last byte to zero.
*/
static inline void folio_zero_segment(struct folio *folio,
size_t start, size_t xend)
{ zero_user_segments(&folio->page, start, xend, 0, 0);}
/**
* folio_zero_range() - Zero a byte range in a folio.
* @folio: The folio to write to.
* @start: The first byte to zero.
* @length: The number of bytes to zero.
*/
static inline void folio_zero_range(struct folio *folio,
size_t start, size_t length)
{
zero_user_segments(&folio->page, start, start + length, 0, 0);
}
/**
* folio_release_kmap - Unmap a folio and drop a refcount.
* @folio: The folio to release.
* @addr: The address previously returned by a call to kmap_local_folio().
*
* It is common, eg in directory handling to kmap a folio. This function
* unmaps the folio and drops the refcount that was being held to keep the
* folio alive while we accessed it.
*/
static inline void folio_release_kmap(struct folio *folio, void *addr)
{
kunmap_local(addr);
folio_put(folio);
}
static inline void unmap_and_put_page(struct page *page, void *addr)
{
folio_release_kmap(page_folio(page), addr);
}
#endif /* _LINUX_HIGHMEM_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __FS_NOTIFY_FSNOTIFY_H_
#define __FS_NOTIFY_FSNOTIFY_H_
#include <linux/list.h>
#include <linux/fsnotify.h>
#include <linux/srcu.h>
#include <linux/types.h>
#include "../mount.h"
/*
* fsnotify_connp_t is what we embed in objects which connector can be attached
* to.
*/
typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
static inline struct inode *fsnotify_conn_inode(
struct fsnotify_mark_connector *conn)
{
return conn->obj;
}
static inline struct mount *fsnotify_conn_mount(
struct fsnotify_mark_connector *conn)
{
return real_mount(conn->obj);
}
static inline struct super_block *fsnotify_conn_sb(
struct fsnotify_mark_connector *conn)
{
return conn->obj;
}
static inline struct mnt_namespace *fsnotify_conn_mntns(
struct fsnotify_mark_connector *conn)
{
return conn->obj;
}
static inline struct super_block *fsnotify_object_sb(void *obj,
enum fsnotify_obj_type obj_type)
{
switch (obj_type) {
case FSNOTIFY_OBJ_TYPE_INODE:
return ((struct inode *)obj)->i_sb;
case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
return ((struct vfsmount *)obj)->mnt_sb;
case FSNOTIFY_OBJ_TYPE_SB:
return (struct super_block *)obj;
default:
return NULL;
}
}
static inline struct super_block *fsnotify_connector_sb(
struct fsnotify_mark_connector *conn)
{
return fsnotify_object_sb(conn->obj, conn->type);
}
static inline fsnotify_connp_t *fsnotify_sb_marks(struct super_block *sb)
{
struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
return sbinfo ? &sbinfo->sb_marks : NULL;
}
/* destroy all events sitting in this groups notification queue */
extern void fsnotify_flush_notify(struct fsnotify_group *group);
/* protects reads of inode and vfsmount marks list */
extern struct srcu_struct fsnotify_mark_srcu;
/* compare two groups for sorting of marks lists */
extern int fsnotify_compare_groups(struct fsnotify_group *a,
struct fsnotify_group *b);
/* Destroy all marks attached to an object via connector */
extern void fsnotify_destroy_marks(fsnotify_connp_t *connp);
/* run the list of all marks associated with inode and destroy them */
static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
{
fsnotify_destroy_marks(&inode->i_fsnotify_marks);
}
/* run the list of all marks associated with vfsmount and destroy them */
static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
{
fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
}
/* run the list of all marks associated with sb and destroy them */
static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
{
fsnotify_destroy_marks(fsnotify_sb_marks(sb));
}
static inline void fsnotify_clear_marks_by_mntns(struct mnt_namespace *mntns)
{
fsnotify_destroy_marks(&mntns->n_fsnotify_marks);
}
/*
* update the dentry->d_flags of all of inode's children to indicate if inode cares
* about events that happen to its children.
*/
extern void fsnotify_set_children_dentry_flags(struct inode *inode);
extern struct kmem_cache *fsnotify_mark_connector_cachep;
#endif /* __FS_NOTIFY_FSNOTIFY_H_ */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Access kernel or user memory without faulting.
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
#include <asm/tlb.h>
bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src,
size_t size)
{
return true;
}
/*
* The below only uses kmsan_check_memory() to ensure uninitialized kernel
* memory isn't leaked.
*/
#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \
while (len >= sizeof(type)) { \
__get_kernel_nofault(dst, src, type, err_label); \
kmsan_check_memory(src, sizeof(type)); \
dst += sizeof(type); \
src += sizeof(type); \
len -= sizeof(type); \
}
long copy_from_kernel_nofault(void *dst, const void *src, size_t size)
{
unsigned long align = 0;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
align = (unsigned long)dst | (unsigned long)src;
if (!copy_from_kernel_nofault_allowed(src, size))
return -ERANGE;
pagefault_disable();
if (!(align & 7))
copy_from_kernel_nofault_loop(dst, src, size, u64, Efault);
if (!(align & 3))
copy_from_kernel_nofault_loop(dst, src, size, u32, Efault);
if (!(align & 1))
copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); copy_from_kernel_nofault_loop(dst, src, size, u8, Efault);
pagefault_enable();
return 0;
Efault:
pagefault_enable();
return -EFAULT;
}
EXPORT_SYMBOL_GPL(copy_from_kernel_nofault);
#define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \
while (len >= sizeof(type)) { \
__put_kernel_nofault(dst, src, type, err_label); \
instrument_write(dst, sizeof(type)); \
dst += sizeof(type); \
src += sizeof(type); \
len -= sizeof(type); \
}
long copy_to_kernel_nofault(void *dst, const void *src, size_t size)
{
unsigned long align = 0;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
align = (unsigned long)dst | (unsigned long)src;
pagefault_disable();
if (!(align & 7))
copy_to_kernel_nofault_loop(dst, src, size, u64, Efault);
if (!(align & 3))
copy_to_kernel_nofault_loop(dst, src, size, u32, Efault);
if (!(align & 1))
copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); copy_to_kernel_nofault_loop(dst, src, size, u8, Efault);
pagefault_enable();
return 0;
Efault:
pagefault_enable();
return -EFAULT;
}
EXPORT_SYMBOL_GPL(copy_to_kernel_nofault);
long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)
{
const void *src = unsafe_addr;
if (unlikely(count <= 0))
return 0;
if (!copy_from_kernel_nofault_allowed(unsafe_addr, count))
return -ERANGE;
pagefault_disable();
do {
__get_kernel_nofault(dst, src, u8, Efault);
dst++;
src++;
} while (dst[-1] && src - unsafe_addr < count);
pagefault_enable();
dst[-1] = '\0';
return src - unsafe_addr;
Efault:
pagefault_enable();
dst[0] = '\0';
return -EFAULT;
}
/**
* copy_from_user_nofault(): safely attempt to read from a user-space location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from. This must be a user address.
* @size: size of the data chunk
*
* Safely read from user address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long copy_from_user_nofault(void *dst, const void __user *src, size_t size)
{
long ret = -EFAULT;
if (!__access_ok(src, size))
return ret;
if (!nmi_uaccess_okay())
return ret;
pagefault_disable();
ret = __copy_from_user_inatomic(dst, src, size);
pagefault_enable();
if (ret)
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(copy_from_user_nofault);
/**
* copy_to_user_nofault(): safely attempt to write to a user-space location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
*
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long copy_to_user_nofault(void __user *dst, const void *src, size_t size)
{
long ret = -EFAULT;
if (access_ok(dst, size)) {
pagefault_disable();
ret = __copy_to_user_inatomic(dst, src, size);
pagefault_enable();
}
if (ret)
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(copy_to_user_nofault);
/**
* strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user
* address.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @unsafe_addr: Unsafe user address.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from unsafe user address to kernel buffer.
*
* On success, returns the length of the string INCLUDING the trailing NUL.
*
* If access fails, returns -EFAULT (some data may have been copied
* and the trailing NUL added).
*
* If @count is smaller than the length of the string, copies @count-1 bytes,
* sets the last byte of @dst buffer to NUL and returns @count.
*/
long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,
long count)
{
long ret;
if (unlikely(count <= 0))
return 0;
pagefault_disable();
ret = strncpy_from_user(dst, unsafe_addr, count);
pagefault_enable();
if (ret >= count) {
ret = count;
dst[ret - 1] = '\0';
} else if (ret > 0) {
ret++;
}
return ret;
}
/**
* strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL.
* @unsafe_addr: The string to measure.
* @count: Maximum count (including NUL)
*
* Get the size of a NUL-terminated string in user space without pagefault.
*
* Returns the size of the string INCLUDING the terminating NUL.
*
* If the string is too long, returns a number larger than @count. User
* has to check the return value against "> count".
* On exception (or invalid count), returns 0.
*
* Unlike strnlen_user, this can be used from IRQ handler etc. because
* it disables pagefaults.
*/
long strnlen_user_nofault(const void __user *unsafe_addr, long count)
{
int ret;
pagefault_disable();
ret = strnlen_user(unsafe_addr, count);
pagefault_enable();
return ret;
}
void __copy_overflow(int size, unsigned long count)
{
WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
}
EXPORT_SYMBOL(__copy_overflow);
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/readpage.c
*
* Copyright (C) 2002, Linus Torvalds.
* Copyright (C) 2015, Google, Inc.
*
* This was originally taken from fs/mpage.c
*
* The ext4_mpage_readpages() function here is intended to
* replace mpage_readahead() in the general case, not just for
* encrypted files. It has some limitations (see below), where it
* will fall back to read_block_full_page(), but these limitations
* should only be hit when page_size != block_size.
*
* This will allow us to attach a callback function to support ext4
* encryption.
*
* If anything unusual happens, such as:
*
* - encountering a page which has buffers
* - encountering a page which has a non-hole after a hole
* - encountering a page with non-contiguous blocks
*
* then this code just gives up and calls the buffer_head-based read function.
* It does handle a page which has holes at the end - that is a common case:
* the end-of-file on blocksize < PAGE_SIZE setups.
*
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include "ext4.h"
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
static mempool_t *bio_post_read_ctx_pool;
/* postprocessing steps for read bios */
enum bio_post_read_step {
STEP_INITIAL = 0,
STEP_DECRYPT,
STEP_VERITY,
STEP_MAX,
};
struct bio_post_read_ctx {
struct bio *bio;
struct work_struct work;
unsigned int cur_step;
unsigned int enabled_steps;
};
static void __read_end_io(struct bio *bio)
{
struct folio_iter fi;
bio_for_each_folio_all(fi, bio)
folio_end_read(fi.folio, bio->bi_status == 0);
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
static void decrypt_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
if (fscrypt_decrypt_bio(bio))
bio_post_read_processing(ctx);
else
__read_end_io(bio);
}
static void verity_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
/*
* fsverity_verify_bio() may call readahead() again, and although verity
* will be disabled for that, decryption may still be needed, causing
* another bio_post_read_ctx to be allocated. So to guarantee that
* mempool_alloc() never deadlocks we must free the current ctx first.
* This is safe because verity is the last post-read step.
*/
BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX);
mempool_free(ctx, bio_post_read_ctx_pool);
bio->bi_private = NULL;
fsverity_verify_bio(bio);
__read_end_io(bio);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
{
/*
* We use different work queues for decryption and for verity because
* verity may require reading metadata pages that need decryption, and
* we shouldn't recurse to the same workqueue.
*/
switch (++ctx->cur_step) {
case STEP_DECRYPT:
if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
INIT_WORK(&ctx->work, decrypt_work);
fscrypt_enqueue_decrypt_work(&ctx->work);
return;
}
ctx->cur_step++;
fallthrough;
case STEP_VERITY:
if (ctx->enabled_steps & (1 << STEP_VERITY)) {
INIT_WORK(&ctx->work, verity_work);
fsverity_enqueue_verify_work(&ctx->work);
return;
}
ctx->cur_step++;
fallthrough;
default:
__read_end_io(ctx->bio);
}
}
static bool bio_post_read_required(struct bio *bio)
{
return bio->bi_private && !bio->bi_status;
}
/*
* I/O completion handler for multipage BIOs.
*
* The mpage code never puts partial pages into a BIO (except for end-of-file).
* If a page does not map to a contiguous run of blocks then it simply falls
* back to block_read_full_folio().
*
* Why is this? If a page's completion depends on a number of different BIOs
* which can complete in any order (or at the same time) then determining the
* status of that page is hard. See end_buffer_async_read() for the details.
* There is no point in duplicating all that complexity.
*/
static void mpage_end_io(struct bio *bio)
{
if (bio_post_read_required(bio)) {
struct bio_post_read_ctx *ctx = bio->bi_private;
ctx->cur_step = STEP_INITIAL;
bio_post_read_processing(ctx);
return;
}
__read_end_io(bio);
}
static inline bool ext4_need_verity(const struct inode *inode, pgoff_t idx)
{
return fsverity_active(inode) &&
idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}
static void ext4_set_bio_post_read_ctx(struct bio *bio,
const struct inode *inode,
pgoff_t first_idx)
{
unsigned int post_read_steps = 0;
if (fscrypt_inode_uses_fs_layer_crypto(inode))
post_read_steps |= 1 << STEP_DECRYPT;
if (ext4_need_verity(inode, first_idx))
post_read_steps |= 1 << STEP_VERITY;
if (post_read_steps) {
/* Due to the mempool, this never fails. */
struct bio_post_read_ctx *ctx =
mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
ctx->bio = bio;
ctx->enabled_steps = post_read_steps;
bio->bi_private = ctx;
}
}
static inline loff_t ext4_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
return inode->i_sb->s_maxbytes; return i_size_read(inode);
}
int ext4_mpage_readpages(struct inode *inode,
struct readahead_control *rac, struct folio *folio)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t next_block;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t first_block;
unsigned page_block;
struct block_device *bdev = inode->i_sb->s_bdev;
int length;
unsigned relative_block = 0;
struct ext4_map_blocks map;
unsigned int nr_pages = rac ? readahead_count(rac) : 1;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
for (; nr_pages; nr_pages--) {
int fully_mapped = 1;
unsigned first_hole = blocks_per_page;
if (rac) folio = readahead_folio(rac);
prefetchw(&folio->flags);
if (folio_buffers(folio))
goto confused;
block_in_file = next_block =
(sector_t)folio->index << (PAGE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (ext4_readpage_limit(inode) +
blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the previous result first.
*/
if ((map.m_flags & EXT4_MAP_MAPPED) && block_in_file > map.m_lblk &&
block_in_file < (map.m_lblk + map.m_len)) {
unsigned map_offset = block_in_file - map.m_lblk;
unsigned last = map.m_len - map_offset;
first_block = map.m_pblk + map_offset;
for (relative_block = 0; ; relative_block++) { if (relative_block == last) {
/* needed? */
map.m_flags &= ~EXT4_MAP_MAPPED;
break;
}
if (page_block == blocks_per_page)
break;
page_block++;
block_in_file++;
}
}
/*
* Then do more ext4_map_blocks() calls until we are
* done with this folio.
*/
while (page_block < blocks_per_page) { if (block_in_file < last_block) {
map.m_lblk = block_in_file;
map.m_len = last_block - block_in_file;
if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
set_error_page:
folio_zero_segment(folio, 0,
folio_size(folio));
folio_unlock(folio);
goto next_page;
}
}
if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (!page_block) first_block = map.m_pblk; else if (first_block + page_block != map.m_pblk)
goto confused;
for (relative_block = 0; ; relative_block++) { if (relative_block == map.m_len) {
/* needed? */
map.m_flags &= ~EXT4_MAP_MAPPED;
break;
} else if (page_block == blocks_per_page)
break;
page_block++;
block_in_file++;
}
}
if (first_hole != blocks_per_page) {
folio_zero_segment(folio, first_hole << blkbits,
folio_size(folio)); if (first_hole == 0) { if (ext4_need_verity(inode, folio->index) && !fsverity_verify_folio(folio))
goto set_error_page;
folio_end_read(folio, true);
continue;
}
} else if (fully_mapped) { folio_set_mappedtodisk(folio);
}
/*
* This folio will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && (last_block_in_bio != first_block - 1 ||
!fscrypt_mergeable_bio(bio, inode, next_block))) {
submit_and_realloc:
submit_bio(bio);
bio = NULL;
}
if (bio == NULL) {
/*
* bio_alloc will _always_ be able to allocate a bio if
* __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
*/
bio = bio_alloc(bdev, bio_max_segs(nr_pages),
REQ_OP_READ, GFP_KERNEL);
fscrypt_set_bio_crypt_ctx(bio, inode, next_block,
GFP_KERNEL);
ext4_set_bio_post_read_ctx(bio, inode, folio->index);
bio->bi_iter.bi_sector = first_block << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
if (rac) bio->bi_opf |= REQ_RAHEAD;
}
length = first_hole << blkbits;
if (!bio_add_folio(bio, folio, length, 0))
goto submit_and_realloc;
if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
(relative_block == map.m_len)) ||
(first_hole != blocks_per_page)) {
submit_bio(bio);
bio = NULL;
} else
last_block_in_bio = first_block + blocks_per_page - 1;
continue;
confused:
if (bio) { submit_bio(bio);
bio = NULL;
}
if (!folio_test_uptodate(folio)) block_read_full_folio(folio, ext4_get_block);
else
folio_unlock(folio);
next_page:
; /* A label shall be followed by a statement until C23 */
}
if (bio) submit_bio(bio);
return 0;
}
int __init ext4_init_post_read_processing(void)
{
bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, SLAB_RECLAIM_ACCOUNT);
if (!bio_post_read_ctx_cache)
goto fail;
bio_post_read_ctx_pool =
mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
bio_post_read_ctx_cache);
if (!bio_post_read_ctx_pool)
goto fail_free_cache;
return 0;
fail_free_cache:
kmem_cache_destroy(bio_post_read_ctx_cache);
fail:
return -ENOMEM;
}
void ext4_exit_post_read_processing(void)
{
mempool_destroy(bio_post_read_ctx_pool);
kmem_cache_destroy(bio_post_read_ctx_cache);
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Variant of atomic_t specialized for reference counts.
*
* The interface matches the atomic_t interface (to aid in porting) but only
* provides the few functions one should use for reference counting.
*
* Saturation semantics
* ====================
*
* refcount_t differs from atomic_t in that the counter saturates at
* REFCOUNT_SATURATED and will not move once there. This avoids wrapping the
* counter and causing 'spurious' use-after-free issues. In order to avoid the
* cost associated with introducing cmpxchg() loops into all of the saturating
* operations, we temporarily allow the counter to take on an unchecked value
* and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow
* or overflow has occurred. Although this is racy when multiple threads
* access the refcount concurrently, by placing REFCOUNT_SATURATED roughly
* equidistant from 0 and INT_MAX we minimise the scope for error:
*
* INT_MAX REFCOUNT_SATURATED UINT_MAX
* 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff)
* +--------------------------------+----------------+----------------+
* <---------- bad value! ---------->
*
* (in a signed view of the world, the "bad value" range corresponds to
* a negative counter value).
*
* As an example, consider a refcount_inc() operation that causes the counter
* to overflow:
*
* int old = atomic_fetch_add_relaxed(r);
* // old is INT_MAX, refcount now INT_MIN (0x8000_0000)
* if (old < 0)
* atomic_set(r, REFCOUNT_SATURATED);
*
* If another thread also performs a refcount_inc() operation between the two
* atomic operations, then the count will continue to edge closer to 0. If it
* reaches a value of 1 before /any/ of the threads reset it to the saturated
* value, then a concurrent refcount_dec_and_test() may erroneously free the
* underlying object.
* Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently
* 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK).
* With the current PID limit, if no batched refcounting operations are used and
* the attacker can't repeatedly trigger kernel oopses in the middle of refcount
* operations, this makes it impossible for a saturated refcount to leave the
* saturation range, even if it is possible for multiple uses of the same
* refcount to nest in the context of a single task:
*
* (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT =
* 0x40000000 / 0x400000 = 0x100 = 256
*
* If hundreds of references are added/removed with a single refcounting
* operation, it may potentially be possible to leave the saturation range; but
* given the precise timing details involved with the round-robin scheduling of
* each thread manipulating the refcount and the need to hit the race multiple
* times in succession, there doesn't appear to be a practical avenue of attack
* even if using refcount_add() operations with larger increments.
*
* Memory ordering
* ===============
*
* Memory ordering rules are slightly relaxed wrt regular atomic_t functions
* and provide only what is strictly required for refcounts.
*
* The increments are fully relaxed; these will not provide ordering. The
* rationale is that whatever is used to obtain the object we're increasing the
* reference count on will provide the ordering. For locked data structures,
* its the lock acquire, for RCU/lockless data structures its the dependent
* load.
*
* Do note that inc_not_zero() provides a control dependency which will order
* future stores against the inc, this ensures we'll never modify the object
* if we did not in fact acquire a reference.
*
* The decrements will provide release order, such that all the prior loads and
* stores will be issued before, it also provides a control dependency, which
* will order us against the subsequent free().
*
* The control dependency is against the load of the cmpxchg (ll/sc) that
* succeeded. This means the stores aren't fully ordered, but this is fine
* because the 1->0 transition indicates no concurrency.
*
* Note that the allocator is responsible for ordering things between free()
* and alloc().
*
* The decrements dec_and_test() and sub_and_test() also provide acquire
* ordering on success.
*
* refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide
* acquire and release ordering for cases when the memory occupied by the
* object might be reused to store another object. This is important for the
* cases where secondary validation is required to detect such reuse, e.g.
* SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after
* the refcount is taken, hence acquire order is necessary. Similarly, when the
* object is initialized, all stores to its attributes should be visible before
* the refcount is set, otherwise a stale attribute value might be used by
* another task which succeeds in taking a refcount to the new object.
*/
#ifndef _LINUX_REFCOUNT_H
#define _LINUX_REFCOUNT_H
#include <linux/atomic.h>
#include <linux/bug.h>
#include <linux/compiler.h>
#include <linux/limits.h>
#include <linux/refcount_types.h>
#include <linux/spinlock_types.h>
struct mutex;
#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), }
#define REFCOUNT_MAX INT_MAX
#define REFCOUNT_SATURATED (INT_MIN / 2)
enum refcount_saturation_type {
REFCOUNT_ADD_NOT_ZERO_OVF,
REFCOUNT_ADD_OVF,
REFCOUNT_ADD_UAF,
REFCOUNT_SUB_UAF,
REFCOUNT_DEC_LEAK,
};
void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t);
/**
* refcount_set - set a refcount's value
* @r: the refcount
* @n: value to which the refcount will be set
*/
static inline void refcount_set(refcount_t *r, int n)
{
atomic_set(&r->refs, n);
}
/**
* refcount_set_release - set a refcount's value with release ordering
* @r: the refcount
* @n: value to which the refcount will be set
*
* This function should be used when memory occupied by the object might be
* reused to store another object -- consider SLAB_TYPESAFE_BY_RCU.
*
* Provides release memory ordering which will order previous memory operations
* against this store. This ensures all updates to this object are visible
* once the refcount is set and stale values from the object previously
* occupying this memory are overwritten with new ones.
*
* This function should be called only after new object is fully initialized.
* After this call the object should be considered visible to other tasks even
* if it was not yet added into an object collection normally used to discover
* it. This is because other tasks might have discovered the object previously
* occupying the same memory and after memory reuse they can succeed in taking
* refcount to the new object and start using it.
*/
static inline void refcount_set_release(refcount_t *r, int n)
{
atomic_set_release(&r->refs, n);
}
/**
* refcount_read - get a refcount's value
* @r: the refcount
*
* Return: the refcount's value
*/
static inline unsigned int refcount_read(const refcount_t *r)
{
return atomic_read(&r->refs);
}
static inline __must_check __signed_wrap
bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
{
int old = refcount_read(r);
do {
if (!old)
break;
} while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i));
if (oldp)
*oldp = old;
if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF);
return old;
}
/**
* refcount_add_not_zero - add a value to a refcount unless it is 0
* @i: the value to add to the refcount
* @r: the refcount
*
* Will saturate at REFCOUNT_SATURATED and WARN.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* and thereby orders future stores. See the comment on top.
*
* Use of this function is not recommended for the normal reference counting
* use case in which references are taken and released one at a time. In these
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
*
* Return: false if the passed refcount is 0, true otherwise
*/
static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
{
return __refcount_add_not_zero(i, r, NULL);
}
static inline __must_check __signed_wrap
bool __refcount_add_not_zero_limited_acquire(int i, refcount_t *r, int *oldp,
int limit)
{
int old = refcount_read(r);
do {
if (!old)
break;
if (i > limit - old) {
if (oldp)
*oldp = old;
return false;
}
} while (!atomic_try_cmpxchg_acquire(&r->refs, &old, old + i));
if (oldp)
*oldp = old;
if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF);
return old;
}
static inline __must_check bool
__refcount_inc_not_zero_limited_acquire(refcount_t *r, int *oldp, int limit)
{
return __refcount_add_not_zero_limited_acquire(1, r, oldp, limit);
}
static inline __must_check __signed_wrap
bool __refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp)
{
return __refcount_add_not_zero_limited_acquire(i, r, oldp, INT_MAX);
}
/**
* refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0
*
* @i: the value to add to the refcount
* @r: the refcount
*
* Will saturate at REFCOUNT_SATURATED and WARN.
*
* This function should be used when memory occupied by the object might be
* reused to store another object -- consider SLAB_TYPESAFE_BY_RCU.
*
* Provides acquire memory ordering on success, it is assumed the caller has
* guaranteed the object memory to be stable (RCU, etc.). It does provide a
* control dependency and thereby orders future stores. See the comment on top.
*
* Use of this function is not recommended for the normal reference counting
* use case in which references are taken and released one at a time. In these
* cases, refcount_inc_not_zero_acquire() should instead be used to increment a
* reference count.
*
* Return: false if the passed refcount is 0, true otherwise
*/
static inline __must_check bool refcount_add_not_zero_acquire(int i, refcount_t *r)
{
return __refcount_add_not_zero_acquire(i, r, NULL);
}
static inline __signed_wrap
void __refcount_add(int i, refcount_t *r, int *oldp)
{
int old = atomic_fetch_add_relaxed(i, &r->refs);
if (oldp)
*oldp = old;
if (unlikely(!old))
refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
else if (unlikely(old < 0 || old + i < 0))
refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
}
/**
* refcount_add - add a value to a refcount
* @i: the value to add to the refcount
* @r: the refcount
*
* Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* and thereby orders future stores. See the comment on top.
*
* Use of this function is not recommended for the normal reference counting
* use case in which references are taken and released one at a time. In these
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
*/
static inline void refcount_add(int i, refcount_t *r)
{
__refcount_add(i, r, NULL);
}
static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
{
return __refcount_add_not_zero(1, r, oldp);
}
/**
* refcount_inc_not_zero - increment a refcount unless it is 0
* @r: the refcount to increment
*
* Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED
* and WARN.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* and thereby orders future stores. See the comment on top.
*
* Return: true if the increment was successful, false otherwise
*/
static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
{
return __refcount_inc_not_zero(r, NULL);
}
static inline __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp)
{
return __refcount_add_not_zero_acquire(1, r, oldp);
}
/**
* refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0
* @r: the refcount to increment
*
* Similar to refcount_inc_not_zero(), but provides acquire memory ordering on
* success.
*
* This function should be used when memory occupied by the object might be
* reused to store another object -- consider SLAB_TYPESAFE_BY_RCU.
*
* Provides acquire memory ordering on success, it is assumed the caller has
* guaranteed the object memory to be stable (RCU, etc.). It does provide a
* control dependency and thereby orders future stores. See the comment on top.
*
* Return: true if the increment was successful, false otherwise
*/
static inline __must_check bool refcount_inc_not_zero_acquire(refcount_t *r)
{
return __refcount_inc_not_zero_acquire(r, NULL);
}
static inline void __refcount_inc(refcount_t *r, int *oldp)
{
__refcount_add(1, r, oldp);
}
/**
* refcount_inc - increment a refcount
* @r: the refcount to increment
*
* Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN.
*
* Provides no memory ordering, it is assumed the caller already has a
* reference on the object.
*
* Will WARN if the refcount is 0, as this represents a possible use-after-free
* condition.
*/
static inline void refcount_inc(refcount_t *r)
{
__refcount_inc(r, NULL);
}
static inline __must_check __signed_wrap
bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
{
int old = atomic_fetch_sub_release(i, &r->refs);
if (oldp)
*oldp = old;
if (old > 0 && old == i) {
smp_acquire__after_ctrl_dep();
return true;
}
if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
return false;
}
/**
* refcount_sub_and_test - subtract from a refcount and test if it is 0
* @i: amount to subtract from the refcount
* @r: the refcount
*
* Similar to atomic_dec_and_test(), but it will WARN, return false and
* ultimately leak on underflow and will fail to decrement when saturated
* at REFCOUNT_SATURATED.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides an acquire ordering on success such that free()
* must come after.
*
* Use of this function is not recommended for the normal reference counting
* use case in which references are taken and released one at a time. In these
* cases, refcount_dec(), or one of its variants, should instead be used to
* decrement a reference count.
*
* Return: true if the resulting refcount is 0, false otherwise
*/
static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
{
return __refcount_sub_and_test(i, r, NULL);
}
static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
{
return __refcount_sub_and_test(1, r, oldp);
}
/**
* refcount_dec_and_test - decrement a refcount and test if it is 0
* @r: the refcount
*
* Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
* decrement when saturated at REFCOUNT_SATURATED.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides an acquire ordering on success such that free()
* must come after.
*
* Return: true if the resulting refcount is 0, false otherwise
*/
static inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
return __refcount_dec_and_test(r, NULL);
}
static inline void __refcount_dec(refcount_t *r, int *oldp)
{
int old = atomic_fetch_sub_release(1, &r->refs);
if (oldp)
*oldp = old;
if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
}
/**
* refcount_dec - decrement a refcount
* @r: the refcount
*
* Similar to atomic_dec(), it will WARN on underflow and fail to decrement
* when saturated at REFCOUNT_SATURATED.
*
* Provides release memory ordering, such that prior loads and stores are done
* before.
*/
static inline void refcount_dec(refcount_t *r)
{
__refcount_dec(r, NULL);
}
extern __must_check bool refcount_dec_if_one(refcount_t *r);
extern __must_check bool refcount_dec_not_one(refcount_t *r);
extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(lock);
extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(lock);
extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r,
spinlock_t *lock,
unsigned long *flags) __cond_acquires(lock);
#endif /* _LINUX_REFCOUNT_H */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/drivers/char/misc.c
*
* Generic misc open routine by Johan Myreen
*
* Based on code from Linus
*
* Teemu Rantanen's Microsoft Busmouse support and Derrick Cole's
* changes incorporated into 0.97pl4
* by Peter Cervasio (pete%q106fm.uucp@wupost.wustl.edu) (08SEP92)
* See busmouse.c for particulars.
*
* Made things a lot mode modular - easy to compile in just one or two
* of the misc drivers, as they are now completely independent. Linus.
*
* Support for loadable modules. 8-Sep-95 Philip Blundell <pjb27@cam.ac.uk>
*
* Fixed a failing symbol register to free the device registration
* Alan Cox <alan@lxorguk.ukuu.org.uk> 21-Jan-96
*
* Dynamic minors and /proc/mice by Alessandro Rubini. 26-Mar-96
*
* Renamed to misc and miscdevice to be more accurate. Alan Cox 26-Mar-96
*
* Handling of mouse minor numbers for kerneld:
* Idea by Jacques Gelinas <jack@solucorp.qc.ca>,
* adapted by Bjorn Ekwall <bj0rn@blox.se>
* corrected by Alan Cox <alan@lxorguk.ukuu.org.uk>
*
* Changes for kmod (from kerneld):
* Cyrus Durgin <cider@speakeasy.org>
*
* Added devfs support. Richard Gooch <rgooch@atnf.csiro.au> 10-Jan-1998
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/errno.h>
#include <linux/miscdevice.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/tty.h>
#include <linux/kmod.h>
#include <linux/gfp.h>
/*
* Head entry for the doubly linked miscdevice list
*/
static LIST_HEAD(misc_list);
static DEFINE_MUTEX(misc_mtx);
/*
* Assigned numbers, used for dynamic minors
*/
#define DYNAMIC_MINORS 128 /* like dynamic majors */
static DEFINE_IDA(misc_minors_ida);
static int misc_minor_alloc(int minor)
{
int ret = 0;
if (minor == MISC_DYNAMIC_MINOR) {
/* allocate free id */
ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL);
if (ret >= 0) {
ret = DYNAMIC_MINORS - ret - 1;
} else {
ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1,
MINORMASK, GFP_KERNEL);
}
} else {
/* specific minor, check if it is in dynamic or misc dynamic range */
if (minor < DYNAMIC_MINORS) {
minor = DYNAMIC_MINORS - minor - 1;
ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
} else if (minor > MISC_DYNAMIC_MINOR) {
ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
} else {
/* case of non-dynamic minors, no need to allocate id */
ret = 0;
}
}
return ret;
}
static void misc_minor_free(int minor)
{
if (minor < DYNAMIC_MINORS)
ida_free(&misc_minors_ida, DYNAMIC_MINORS - minor - 1);
else if (minor > MISC_DYNAMIC_MINOR)
ida_free(&misc_minors_ida, minor);
}
#ifdef CONFIG_PROC_FS
static void *misc_seq_start(struct seq_file *seq, loff_t *pos)
{
mutex_lock(&misc_mtx);
return seq_list_start(&misc_list, *pos);
}
static void *misc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
return seq_list_next(v, &misc_list, pos);
}
static void misc_seq_stop(struct seq_file *seq, void *v)
{
mutex_unlock(&misc_mtx);
}
static int misc_seq_show(struct seq_file *seq, void *v)
{
const struct miscdevice *p = list_entry(v, struct miscdevice, list);
seq_printf(seq, "%3i %s\n", p->minor, p->name ? p->name : "");
return 0;
}
static const struct seq_operations misc_seq_ops = {
.start = misc_seq_start,
.next = misc_seq_next,
.stop = misc_seq_stop,
.show = misc_seq_show,
};
#endif
static int misc_open(struct inode *inode, struct file *file)
{
int minor = iminor(inode);
struct miscdevice *c = NULL, *iter;
int err = -ENODEV;
const struct file_operations *new_fops = NULL;
mutex_lock(&misc_mtx);
list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor)
continue;
c = iter;
new_fops = fops_get(iter->fops);
break;
}
if (!new_fops) {
mutex_unlock(&misc_mtx);
request_module("char-major-%d-%d", MISC_MAJOR, minor);
mutex_lock(&misc_mtx);
list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor)
continue;
c = iter;
new_fops = fops_get(iter->fops);
break;
}
if (!new_fops)
goto fail;
}
/*
* Place the miscdevice in the file's
* private_data so it can be used by the
* file operations, including f_op->open below
*/
file->private_data = c;
err = 0;
replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file);
fail:
mutex_unlock(&misc_mtx);
return err;
}
static char *misc_devnode(const struct device *dev, umode_t *mode)
{
const struct miscdevice *c = dev_get_drvdata(dev);
if (mode && c->mode) *mode = c->mode; if (c->nodename) return kstrdup(c->nodename, GFP_KERNEL);
return NULL;
}
static const struct class misc_class = {
.name = "misc",
.devnode = misc_devnode,
};
static const struct file_operations misc_fops = {
.owner = THIS_MODULE,
.open = misc_open,
.llseek = noop_llseek,
};
/**
* misc_register - register a miscellaneous device
* @misc: device structure
*
* Register a miscellaneous device with the kernel. If the minor
* number is set to %MISC_DYNAMIC_MINOR a minor number is assigned
* and placed in the minor field of the structure. For other cases
* the minor number requested is used.
*
* The structure passed is linked into the kernel and may not be
* destroyed until it has been unregistered. By default, an open()
* syscall to the device sets file->private_data to point to the
* structure. Drivers don't need open in fops for this.
*
* A zero is returned on success and a negative errno code for
* failure.
*/
int misc_register(struct miscdevice *misc)
{
dev_t dev;
int err = 0;
bool is_dynamic = (misc->minor == MISC_DYNAMIC_MINOR);
INIT_LIST_HEAD(&misc->list);
mutex_lock(&misc_mtx);
if (is_dynamic) {
int i = misc_minor_alloc(misc->minor);
if (i < 0) {
err = -EBUSY;
goto out;
}
misc->minor = i;
} else {
struct miscdevice *c;
int i;
list_for_each_entry(c, &misc_list, list) {
if (c->minor == misc->minor) {
err = -EBUSY;
goto out;
}
}
i = misc_minor_alloc(misc->minor);
if (i < 0) {
err = -EBUSY;
goto out;
}
}
dev = MKDEV(MISC_MAJOR, misc->minor);
misc->this_device =
device_create_with_groups(&misc_class, misc->parent, dev,
misc, misc->groups, "%s", misc->name);
if (IS_ERR(misc->this_device)) {
misc_minor_free(misc->minor);
if (is_dynamic) {
misc->minor = MISC_DYNAMIC_MINOR;
}
err = PTR_ERR(misc->this_device);
goto out;
}
/*
* Add it to the front, so that later devices can "override"
* earlier defaults
*/
list_add(&misc->list, &misc_list);
out:
mutex_unlock(&misc_mtx);
return err;
}
EXPORT_SYMBOL(misc_register);
/**
* misc_deregister - unregister a miscellaneous device
* @misc: device to unregister
*
* Unregister a miscellaneous device that was previously
* successfully registered with misc_register().
*/
void misc_deregister(struct miscdevice *misc)
{
if (WARN_ON(list_empty(&misc->list)))
return;
mutex_lock(&misc_mtx);
list_del(&misc->list);
device_destroy(&misc_class, MKDEV(MISC_MAJOR, misc->minor));
misc_minor_free(misc->minor);
mutex_unlock(&misc_mtx);
}
EXPORT_SYMBOL(misc_deregister);
static int __init misc_init(void)
{
int err;
struct proc_dir_entry *ret;
ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops);
err = class_register(&misc_class);
if (err)
goto fail_remove;
err = -EIO;
if (__register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops))
goto fail_printk;
return 0;
fail_printk:
pr_err("unable to get major %d for misc devices\n", MISC_MAJOR);
class_unregister(&misc_class);
fail_remove:
if (ret)
remove_proc_entry("misc", NULL);
return err;
}
subsys_initcall(misc_init);
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/dcache.c
*
* Complete reimplementation
* (C) 1997 Thomas Schoebel-Theuer,
* with heavy changes by Linus Torvalds
*/
/*
* Notes on the allocation strategy:
*
* The dcache is a master of the icache - whenever a dcache entry
* exists, the inode will always exist. "iput()" is done either when
* the dcache entry is deleted or garbage collected.
*/
#include <linux/ratelimit.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/fscrypt.h>
#include <linux/fsnotify.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/cache.h>
#include <linux/export.h>
#include <linux/security.h>
#include <linux/seqlock.h>
#include <linux/memblock.h>
#include <linux/bit_spinlock.h>
#include <linux/rculist_bl.h>
#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"
#include <asm/runtime-const.h>
/*
* Usage:
* dcache->d_inode->i_lock protects:
* - i_dentry, d_u.d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* s_roots bl list spinlock protects:
* - the s_roots list (see __d_drop)
* dentry->d_sb->s_dentry_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_flags
* - d_name
* - d_lru
* - d_count
* - d_unhashed()
* - d_parent and d_chilren
* - childrens' d_sib and d_parent
* - d_u.d_alias, d_inode
*
* Ordering:
* dentry->d_inode->i_lock
* dentry->d_lock
* dentry->d_sb->s_dentry_lru_lock
* dcache_hash_bucket lock
* s_roots lock
*
* If there is an ancestor relationship:
* dentry->d_parent->...->d_parent->d_lock
* ...
* dentry->d_parent->d_lock
* dentry->d_lock
*
* If no ancestor relationship:
* arbitrary, since it's serialized on rename_lock
*/
static int sysctl_vfs_cache_pressure __read_mostly = 100;
unsigned long vfs_pressure_ratio(unsigned long val)
{
return mult_frac(val, sysctl_vfs_cache_pressure, 100);
}
EXPORT_SYMBOL_GPL(vfs_pressure_ratio);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
static struct kmem_cache *dentry_cache __ro_after_init;
const struct qstr empty_name = QSTR_INIT("", 0);
EXPORT_SYMBOL(empty_name);
const struct qstr slash_name = QSTR_INIT("/", 1);
EXPORT_SYMBOL(slash_name);
const struct qstr dotdot_name = QSTR_INIT("..", 2);
EXPORT_SYMBOL(dotdot_name);
/*
* This is the single most critical data structure when it comes
* to the dcache: the hashtable for lookups. Somebody should try
* to make this good - I've just made it work.
*
* This hash-function tries to avoid losing too many bits of hash
* information, yet avoid using a prime hash-size or similar.
*
* Marking the variables "used" ensures that the compiler doesn't
* optimize them away completely on architectures with runtime
* constant infrastructure, this allows debuggers to see their
* values. But updating these values has no effect on those arches.
*/
static unsigned int d_hash_shift __ro_after_init __used;
static struct hlist_bl_head *dentry_hashtable __ro_after_init __used;
static inline struct hlist_bl_head *d_hash(unsigned long hashlen)
{
return runtime_const_ptr(dentry_hashtable) +
runtime_const_shift_right_32(hashlen, d_hash_shift);
}
#define IN_LOOKUP_SHIFT 10
static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT];
static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
unsigned int hash)
{
hash += (unsigned long) parent / L1_CACHE_BYTES;
return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
}
struct dentry_stat_t {
long nr_dentry;
long nr_unused;
long age_limit; /* age in seconds */
long want_pages; /* pages requested by system */
long nr_negative; /* # of unused negative dentries */
long dummy; /* Reserved for future use */
};
static DEFINE_PER_CPU(long, nr_dentry);
static DEFINE_PER_CPU(long, nr_dentry_unused);
static DEFINE_PER_CPU(long, nr_dentry_negative);
static int dentry_negative_policy;
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
/* Statistics gathering. */
static struct dentry_stat_t dentry_stat = {
.age_limit = 45,
};
/*
* Here we resort to our own counters instead of using generic per-cpu counters
* for consistency with what the vfs inode code does. We are expected to harvest
* better code and performance by having our own specialized counters.
*
* Please note that the loop is done over all possible CPUs, not over all online
* CPUs. The reason for this is that we don't want to play games with CPUs going
* on and off. If one of them goes off, we will just keep their counters.
*
* glommer: See cffbc8a for details, and if you ever intend to change this,
* please update all vfs counters to match.
*/
static long get_nr_dentry(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry, i);
return sum < 0 ? 0 : sum;
}
static long get_nr_dentry_unused(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry_unused, i);
return sum < 0 ? 0 : sum;
}
static long get_nr_dentry_negative(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry_negative, i);
return sum < 0 ? 0 : sum;
}
static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
dentry_stat.nr_unused = get_nr_dentry_unused();
dentry_stat.nr_negative = get_nr_dentry_negative();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static const struct ctl_table fs_dcache_sysctls[] = {
{
.procname = "dentry-state",
.data = &dentry_stat,
.maxlen = 6*sizeof(long),
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
{
.procname = "dentry-negative",
.data = &dentry_negative_policy,
.maxlen = sizeof(dentry_negative_policy),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
};
static const struct ctl_table vm_dcache_sysctls[] = {
{
.procname = "vfs_cache_pressure",
.data = &sysctl_vfs_cache_pressure,
.maxlen = sizeof(sysctl_vfs_cache_pressure),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
};
static int __init init_fs_dcache_sysctls(void)
{
register_sysctl_init("vm", vm_dcache_sysctls);
register_sysctl_init("fs", fs_dcache_sysctls);
return 0;
}
fs_initcall(init_fs_dcache_sysctls);
#endif
/*
* Compare 2 name strings, return 0 if they match, otherwise non-zero.
* The strings are both count bytes long, and count is non-zero.
*/
#ifdef CONFIG_DCACHE_WORD_ACCESS
#include <asm/word-at-a-time.h>
/*
* NOTE! 'cs' and 'scount' come from a dentry, so it has a
* aligned allocation for this particular component. We don't
* strictly need the load_unaligned_zeropad() safety, but it
* doesn't hurt either.
*
* In contrast, 'ct' and 'tcount' can be from a pathname, and do
* need the careful unaligned handling.
*/
static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
unsigned long a,b,mask;
for (;;) {
a = read_word_at_a_time(cs);
b = load_unaligned_zeropad(ct);
if (tcount < sizeof(unsigned long))
break;
if (unlikely(a != b))
return 1;
cs += sizeof(unsigned long);
ct += sizeof(unsigned long);
tcount -= sizeof(unsigned long);
if (!tcount)
return 0;
}
mask = bytemask_from_count(tcount);
return unlikely(!!((a ^ b) & mask));
}
#else
static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
do {
if (*cs != *ct)
return 1;
cs++;
ct++;
tcount--;
} while (tcount);
return 0;
}
#endif
static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
{
/*
* Be careful about RCU walk racing with rename:
* use 'READ_ONCE' to fetch the name pointer.
*
* NOTE! Even if a rename will mean that the length
* was not loaded atomically, we don't care. The
* RCU walk will check the sequence count eventually,
* and catch it. And we won't overrun the buffer,
* because we're reading the name pointer atomically,
* and a dentry name is guaranteed to be properly
* terminated with a NUL byte.
*
* End result: even if 'len' is wrong, we'll exit
* early because the data cannot match (there can
* be no NUL in the ct/tcount data)
*/
const unsigned char *cs = READ_ONCE(dentry->d_name.name);
return dentry_string_cmp(cs, ct, tcount);
}
/*
* long names are allocated separately from dentry and never modified.
* Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot()
* for the reason why ->count and ->head can't be combined into a union.
* dentry_string_cmp() relies upon ->name[] being word-aligned.
*/
struct external_name {
atomic_t count;
struct rcu_head head;
unsigned char name[] __aligned(sizeof(unsigned long));
};
static inline struct external_name *external_name(struct dentry *dentry)
{
return container_of(dentry->d_name.name, struct external_name, name[0]);
}
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
kmem_cache_free(dentry_cache, dentry);
}
static void __d_free_external(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
kfree(external_name(dentry));
kmem_cache_free(dentry_cache, dentry);
}
static inline int dname_external(const struct dentry *dentry)
{
return dentry->d_name.name != dentry->d_shortname.string;
}
void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
{
unsigned seq;
const unsigned char *s;
rcu_read_lock();
retry:
seq = read_seqcount_begin(&dentry->d_seq);
s = READ_ONCE(dentry->d_name.name);
name->name.hash_len = dentry->d_name.hash_len;
name->name.name = name->inline_name.string;
if (likely(s == dentry->d_shortname.string)) {
name->inline_name = dentry->d_shortname;
} else {
struct external_name *p;
p = container_of(s, struct external_name, name[0]);
// get a valid reference
if (unlikely(!atomic_inc_not_zero(&p->count)))
goto retry;
name->name.name = s;
}
if (read_seqcount_retry(&dentry->d_seq, seq)) {
release_dentry_name_snapshot(name);
goto retry;
}
rcu_read_unlock();
}
EXPORT_SYMBOL(take_dentry_name_snapshot);
void release_dentry_name_snapshot(struct name_snapshot *name)
{
if (unlikely(name->name.name != name->inline_name.string)) {
struct external_name *p;
p = container_of(name->name.name, struct external_name, name[0]);
if (unlikely(atomic_dec_and_test(&p->count)))
kfree_rcu(p, head);
}
}
EXPORT_SYMBOL(release_dentry_name_snapshot);
static inline void __d_set_inode_and_type(struct dentry *dentry,
struct inode *inode,
unsigned type_flags)
{
unsigned flags;
dentry->d_inode = inode;
flags = READ_ONCE(dentry->d_flags);
flags &= ~DCACHE_ENTRY_TYPE;
flags |= type_flags;
smp_store_release(&dentry->d_flags, flags);
}
static inline void __d_clear_type_and_inode(struct dentry *dentry)
{
unsigned flags = READ_ONCE(dentry->d_flags);
flags &= ~DCACHE_ENTRY_TYPE;
WRITE_ONCE(dentry->d_flags, flags);
dentry->d_inode = NULL;
/*
* The negative counter only tracks dentries on the LRU. Don't inc if
* d_lru is on another list.
*/
if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative);
}
static void dentry_free(struct dentry *dentry)
{ WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) {
struct external_name *p = external_name(dentry);
if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external);
return;
}
}
/* if dentry was never visible to RCU, immediate free is OK */
if (dentry->d_flags & DCACHE_NORCU)
__d_free(&dentry->d_u.d_rcu);
else
call_rcu(&dentry->d_u.d_rcu, __d_free);
}
/*
* Release the dentry's inode, using the filesystem
* d_iput() operation if defined.
*/
static void dentry_unlink_inode(struct dentry * dentry)
__releases(dentry->d_lock)
__releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
raw_write_seqcount_begin(&dentry->d_seq);
__d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias);
raw_write_seqcount_end(&dentry->d_seq);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode);
else
iput(inode);
}
/*
* The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry
* is in use - which includes both the "real" per-superblock
* LRU list _and_ the DCACHE_SHRINK_LIST use.
*
* The DCACHE_SHRINK_LIST bit is set whenever the dentry is
* on the shrink list (ie not on the superblock LRU list).
*
* The per-cpu "nr_dentry_unused" counters are updated with
* the DCACHE_LRU_LIST bit.
*
* The per-cpu "nr_dentry_negative" counters are only updated
* when deleted from or added to the per-superblock LRU list, not
* from/to the shrink list. That is to avoid an unneeded dec/inc
* pair when moving from LRU to shrink list in select_collect().
*
* These helper functions make sure we always follow the
* rules. d_lock must be held by the caller.
*/
#define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x))
static void d_lru_add(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, 0);
dentry->d_flags |= DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_inc(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_add_obj(
&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_lru_del(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_dec(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_del_obj(
&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_shrink_del(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
list_del_init(&dentry->d_lru);
dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
this_cpu_dec(nr_dentry_unused);
}
static void d_shrink_add(struct dentry *dentry, struct list_head *list)
{
D_FLAG_VERIFY(dentry, 0);
list_add(&dentry->d_lru, list);
dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
}
/*
* These can only be called under the global LRU lock, ie during the
* callback for freeing the LRU list. "isolate" removes it from the
* LRU lists entirely, while shrink_move moves it to the indicated
* private list.
*/
static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_dec(nr_dentry_negative);
list_lru_isolate(lru, &dentry->d_lru);
}
static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
struct list_head *list)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags |= DCACHE_SHRINK_LIST;
if (d_is_negative(dentry))
this_cpu_dec(nr_dentry_negative);
list_lru_isolate_move(lru, &dentry->d_lru, list);
}
static void ___d_drop(struct dentry *dentry)
{
struct hlist_bl_head *b;
/*
* Hashed dentries are normally on the dentry hashtable,
* with the exception of those newly allocated by
* d_obtain_root, which are always IS_ROOT:
*/
if (unlikely(IS_ROOT(dentry)))
b = &dentry->d_sb->s_roots;
else
b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b);
}
void __d_drop(struct dentry *dentry)
{
if (!d_unhashed(dentry)) { ___d_drop(dentry);
dentry->d_hash.pprev = NULL;
write_seqcount_invalidate(&dentry->d_seq);
}
}
EXPORT_SYMBOL(__d_drop);
/**
* d_drop - drop a dentry
* @dentry: dentry to drop
*
* d_drop() unhashes the entry from the parent dentry hashes, so that it won't
* be found through a VFS lookup any more. Note that this is different from
* deleting the dentry - d_delete will try to mark the dentry negative if
* possible, giving a successful _negative_ lookup, while d_drop will
* just make the cache lookup fail.
*
* d_drop() is used mainly for stuff that wants to invalidate a dentry for some
* reason (NFS timeouts or autofs deletes).
*
* __d_drop requires dentry->d_lock
*
* ___d_drop doesn't mark dentry as "unhashed"
* (dentry->d_hash.pprev will be LIST_POISON2, not NULL).
*/
void d_drop(struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(d_drop);
static inline void dentry_unlist(struct dentry *dentry)
{
struct dentry *next;
/*
* Inform d_walk() and shrink_dentry_list() that we are no longer
* attached to the dentry tree
*/
dentry->d_flags |= DCACHE_DENTRY_KILLED;
if (unlikely(hlist_unhashed(&dentry->d_sib)))
return;
__hlist_del(&dentry->d_sib);
/*
* Cursors can move around the list of children. While we'd been
* a normal list member, it didn't matter - ->d_sib.next would've
* been updated. However, from now on it won't be and for the
* things like d_walk() it might end up with a nasty surprise.
* Normally d_walk() doesn't care about cursors moving around -
* ->d_lock on parent prevents that and since a cursor has no children
* of its own, we get through it without ever unlocking the parent.
* There is one exception, though - if we ascend from a child that
* gets killed as soon as we unlock it, the next sibling is found
* using the value left in its ->d_sib.next. And if _that_
* pointed to a cursor, and cursor got moved (e.g. by lseek())
* before d_walk() regains parent->d_lock, we'll end up skipping
* everything the cursor had been moved past.
*
* Solution: make sure that the pointer left behind in ->d_sib.next
* points to something that won't be moving around. I.e. skip the
* cursors.
*/
while (dentry->d_sib.next) {
next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib);
if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
break;
dentry->d_sib.next = next->d_sib.next;
}
}
static struct dentry *__dentry_kill(struct dentry *dentry)
{
struct dentry *parent = NULL;
bool can_free = true;
/*
* The dentry is now unrecoverably dead to the world.
*/
lockref_mark_dead(&dentry->d_lockref);
/*
* inform the fs via d_prune that this dentry is about to be
* unhashed and destroyed.
*/
if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) {
if (!(dentry->d_flags & DCACHE_SHRINK_LIST))
d_lru_del(dentry);
}
/* if it was on the hash then remove it */
__d_drop(dentry);
if (dentry->d_inode)
dentry_unlink_inode(dentry);
else
spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry);
cond_resched();
/* now that it's negative, ->d_parent is stable */
if (!IS_ROOT(dentry)) {
parent = dentry->d_parent;
spin_lock(&parent->d_lock);
}
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
dentry_unlist(dentry);
if (dentry->d_flags & DCACHE_SHRINK_LIST)
can_free = false;
spin_unlock(&dentry->d_lock);
if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) {
spin_unlock(&parent->d_lock);
return NULL;
}
return parent;
}
/*
* Lock a dentry for feeding it to __dentry_kill().
* Called under rcu_read_lock() and dentry->d_lock; the former
* guarantees that nothing we access will be freed under us.
* Note that dentry is *not* protected from concurrent dentry_kill(),
* d_delete(), etc.
*
* Return false if dentry is busy. Otherwise, return true and have
* that dentry's inode locked.
*/
static bool lock_for_kill(struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
if (unlikely(dentry->d_lockref.count))
return false;
if (!inode || likely(spin_trylock(&inode->i_lock)))
return true;
do {
spin_unlock(&dentry->d_lock);
spin_lock(&inode->i_lock);
spin_lock(&dentry->d_lock);
if (likely(inode == dentry->d_inode))
break;
spin_unlock(&inode->i_lock);
inode = dentry->d_inode;
} while (inode); if (likely(!dentry->d_lockref.count))
return true;
if (inode) spin_unlock(&inode->i_lock);
return false;
}
/*
* Decide if dentry is worth retaining. Usually this is called with dentry
* locked; if not locked, we are more limited and might not be able to tell
* without a lock. False in this case means "punt to locked path and recheck".
*
* In case we aren't locked, these predicates are not "stable". However, it is
* sufficient that at some point after we dropped the reference the dentry was
* hashed and the flags had the proper value. Other dentry users may have
* re-gotten a reference to the dentry and change that, but our work is done -
* we can leave the dentry around with a zero refcount.
*/
static inline bool retain_dentry(struct dentry *dentry, bool locked)
{
unsigned int d_flags;
smp_rmb();
d_flags = READ_ONCE(dentry->d_flags);
// Unreachable? Nobody would be able to look it up, no point retaining
if (unlikely(d_unhashed(dentry)))
return false;
// Same if it's disconnected
if (unlikely(d_flags & DCACHE_DISCONNECTED))
return false;
// ->d_delete() might tell us not to bother, but that requires
// ->d_lock; can't decide without it
if (unlikely(d_flags & DCACHE_OP_DELETE)) {
if (!locked || dentry->d_op->d_delete(dentry))
return false;
}
// Explicitly told not to bother
if (unlikely(d_flags & DCACHE_DONTCACHE))
return false;
// At this point it looks like we ought to keep it. We also might
// need to do something - put it on LRU if it wasn't there already
// and mark it referenced if it was on LRU, but not marked yet.
// Unfortunately, both actions require ->d_lock, so in lockless
// case we'd have to punt rather than doing those.
if (unlikely(!(d_flags & DCACHE_LRU_LIST))) {
if (!locked)
return false;
d_lru_add(dentry);
} else if (unlikely(!(d_flags & DCACHE_REFERENCED))) {
if (!locked)
return false;
dentry->d_flags |= DCACHE_REFERENCED;
}
return true;
}
void d_mark_dontcache(struct inode *inode)
{
struct dentry *de;
spin_lock(&inode->i_lock);
hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) {
spin_lock(&de->d_lock);
de->d_flags |= DCACHE_DONTCACHE;
spin_unlock(&de->d_lock);
}
inode->i_state |= I_DONTCACHE;
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_mark_dontcache);
/*
* Try to do a lockless dput(), and return whether that was successful.
*
* If unsuccessful, we return false, having already taken the dentry lock.
* In that case refcount is guaranteed to be zero and we have already
* decided that it's not worth keeping around.
*
* The caller needs to hold the RCU read lock, so that the dentry is
* guaranteed to stay around even if the refcount goes down to zero!
*/
static inline bool fast_dput(struct dentry *dentry)
{
int ret;
/*
* try to decrement the lockref optimistically.
*/
ret = lockref_put_return(&dentry->d_lockref);
/*
* If the lockref_put_return() failed due to the lock being held
* by somebody else, the fast path has failed. We will need to
* get the lock, and then check the count again.
*/
if (unlikely(ret < 0)) {
spin_lock(&dentry->d_lock);
if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) {
spin_unlock(&dentry->d_lock);
return true;
}
dentry->d_lockref.count--;
goto locked;
}
/*
* If we weren't the last ref, we're done.
*/
if (ret)
return true;
/*
* Can we decide that decrement of refcount is all we needed without
* taking the lock? There's a very common case when it's all we need -
* dentry looks like it ought to be retained and there's nothing else
* to do.
*/
if (retain_dentry(dentry, false))
return true;
/*
* Either not worth retaining or we can't tell without the lock.
* Get the lock, then. We've already decremented the refcount to 0,
* but we'll need to re-check the situation after getting the lock.
*/
spin_lock(&dentry->d_lock);
/*
* Did somebody else grab a reference to it in the meantime, and
* we're no longer the last user after all? Alternatively, somebody
* else could have killed it and marked it dead. Either way, we
* don't need to do anything else.
*/
locked:
if (dentry->d_lockref.count || retain_dentry(dentry, true)) {
spin_unlock(&dentry->d_lock);
return true;
}
return false;
}
/*
* This is dput
*
* This is complicated by the fact that we do not want to put
* dentries that are no longer on any hash chain on the unused
* list: we'd much rather just get rid of them immediately.
*
* However, that implies that we have to traverse the dentry
* tree upwards to the parents which might _also_ now be
* scheduled for deletion (it may have been only waiting for
* its last child to go away).
*
* This tail recursion is done by hand as we don't want to depend
* on the compiler to always get this right (gcc generally doesn't).
* Real recursion would eat up our stack space.
*/
/*
* dput - release a dentry
* @dentry: dentry to release
*
* Release a dentry. This will drop the usage count and if appropriate
* call the dentry unlink method as well as removing it from the queues and
* releasing its resources. If the parent dentries were scheduled for release
* they too may now get deleted.
*/
void dput(struct dentry *dentry)
{ if (!dentry)
return;
might_sleep();
rcu_read_lock();
if (likely(fast_dput(dentry))) {
rcu_read_unlock();
return;
}
while (lock_for_kill(dentry)) {
rcu_read_unlock();
dentry = __dentry_kill(dentry);
if (!dentry)
return;
if (retain_dentry(dentry, true)) {
spin_unlock(&dentry->d_lock);
return;
}
rcu_read_lock();
}
rcu_read_unlock();
spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(dput);
static void to_shrink_list(struct dentry *dentry, struct list_head *list)
__must_hold(&dentry->d_lock)
{
if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
if (dentry->d_flags & DCACHE_LRU_LIST)
d_lru_del(dentry);
d_shrink_add(dentry, list);
}
}
void dput_to_list(struct dentry *dentry, struct list_head *list)
{
rcu_read_lock();
if (likely(fast_dput(dentry))) {
rcu_read_unlock();
return;
}
rcu_read_unlock();
to_shrink_list(dentry, list);
spin_unlock(&dentry->d_lock);
}
struct dentry *dget_parent(struct dentry *dentry)
{
int gotref;
struct dentry *ret;
unsigned seq;
/*
* Do optimistic parent lookup without any
* locking.
*/
rcu_read_lock();
seq = raw_seqcount_begin(&dentry->d_seq);
ret = READ_ONCE(dentry->d_parent);
gotref = lockref_get_not_zero(&ret->d_lockref);
rcu_read_unlock();
if (likely(gotref)) {
if (!read_seqcount_retry(&dentry->d_seq, seq))
return ret;
dput(ret);
}
repeat:
/*
* Don't need rcu_dereference because we re-check it was correct under
* the lock.
*/
rcu_read_lock();
ret = dentry->d_parent;
spin_lock(&ret->d_lock);
if (unlikely(ret != dentry->d_parent)) {
spin_unlock(&ret->d_lock);
rcu_read_unlock();
goto repeat;
}
rcu_read_unlock();
BUG_ON(!ret->d_lockref.count);
ret->d_lockref.count++;
spin_unlock(&ret->d_lock);
return ret;
}
EXPORT_SYMBOL(dget_parent);
static struct dentry * __d_find_any_alias(struct inode *inode)
{
struct dentry *alias;
if (hlist_empty(&inode->i_dentry))
return NULL;
alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
lockref_get(&alias->d_lockref);
return alias;
}
/**
* d_find_any_alias - find any alias for a given inode
* @inode: inode to find an alias for
*
* If any aliases exist for the given inode, take and return a
* reference for one of them. If no aliases exist, return %NULL.
*/
struct dentry *d_find_any_alias(struct inode *inode)
{
struct dentry *de;
spin_lock(&inode->i_lock);
de = __d_find_any_alias(inode);
spin_unlock(&inode->i_lock);
return de;
}
EXPORT_SYMBOL(d_find_any_alias);
static struct dentry *__d_find_alias(struct inode *inode)
{
struct dentry *alias;
if (S_ISDIR(inode->i_mode))
return __d_find_any_alias(inode);
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
if (!d_unhashed(alias)) {
dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
}
spin_unlock(&alias->d_lock);
}
return NULL;
}
/**
* d_find_alias - grab a hashed alias of inode
* @inode: inode in question
*
* If inode has a hashed alias, or is a directory and has any alias,
* acquire the reference to alias and return it. Otherwise return NULL.
* Notice that if inode is a directory there can be only one alias and
* it can be unhashed only if it has no children, or if it is the root
* of a filesystem, or if the directory was renamed and d_revalidate
* was the first vfs operation to notice.
*
* If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
* any other hashed alias over that one.
*/
struct dentry *d_find_alias(struct inode *inode)
{
struct dentry *de = NULL;
if (!hlist_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
de = __d_find_alias(inode);
spin_unlock(&inode->i_lock);
}
return de;
}
EXPORT_SYMBOL(d_find_alias);
/*
* Caller MUST be holding rcu_read_lock() and be guaranteed
* that inode won't get freed until rcu_read_unlock().
*/
struct dentry *d_find_alias_rcu(struct inode *inode)
{
struct hlist_head *l = &inode->i_dentry;
struct dentry *de = NULL;
spin_lock(&inode->i_lock);
// ->i_dentry and ->i_rcu are colocated, but the latter won't be
// used without having I_FREEING set, which means no aliases left
if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) {
de = hlist_entry(l->first, struct dentry, d_u.d_alias);
} else {
hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de))
break;
}
}
spin_unlock(&inode->i_lock);
return de;
}
/*
* Try to kill dentries associated with this inode.
* WARNING: you must own a reference to inode.
*/
void d_prune_aliases(struct inode *inode)
{
LIST_HEAD(dispose);
struct dentry *dentry;
spin_lock(&inode->i_lock);
hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_lockref.count)
to_shrink_list(dentry, &dispose);
spin_unlock(&dentry->d_lock);
}
spin_unlock(&inode->i_lock);
shrink_dentry_list(&dispose);
}
EXPORT_SYMBOL(d_prune_aliases);
static inline void shrink_kill(struct dentry *victim)
{
do {
rcu_read_unlock();
victim = __dentry_kill(victim);
rcu_read_lock();
} while (victim && lock_for_kill(victim));
rcu_read_unlock();
if (victim)
spin_unlock(&victim->d_lock);
}
void shrink_dentry_list(struct list_head *list)
{
while (!list_empty(list)) {
struct dentry *dentry;
dentry = list_entry(list->prev, struct dentry, d_lru);
spin_lock(&dentry->d_lock);
rcu_read_lock();
if (!lock_for_kill(dentry)) {
bool can_free;
rcu_read_unlock();
d_shrink_del(dentry);
can_free = dentry->d_flags & DCACHE_DENTRY_KILLED;
spin_unlock(&dentry->d_lock);
if (can_free)
dentry_free(dentry);
continue;
}
d_shrink_del(dentry);
shrink_kill(dentry);
}
}
static enum lru_status dentry_lru_isolate(struct list_head *item,
struct list_lru_one *lru, void *arg)
{
struct list_head *freeable = arg;
struct dentry *dentry = container_of(item, struct dentry, d_lru);
/*
* we are inverting the lru lock/dentry->d_lock here,
* so use a trylock. If we fail to get the lock, just skip
* it
*/
if (!spin_trylock(&dentry->d_lock))
return LRU_SKIP;
/*
* Referenced dentries are still in use. If they have active
* counts, just remove them from the LRU. Otherwise give them
* another pass through the LRU.
*/
if (dentry->d_lockref.count) {
d_lru_isolate(lru, dentry);
spin_unlock(&dentry->d_lock);
return LRU_REMOVED;
}
if (dentry->d_flags & DCACHE_REFERENCED) {
dentry->d_flags &= ~DCACHE_REFERENCED;
spin_unlock(&dentry->d_lock);
/*
* The list move itself will be made by the common LRU code. At
* this point, we've dropped the dentry->d_lock but keep the
* lru lock. This is safe to do, since every list movement is
* protected by the lru lock even if both locks are held.
*
* This is guaranteed by the fact that all LRU management
* functions are intermediated by the LRU API calls like
* list_lru_add_obj and list_lru_del_obj. List movement in this file
* only ever occur through this functions or through callbacks
* like this one, that are called from the LRU API.
*
* The only exceptions to this are functions like
* shrink_dentry_list, and code that first checks for the
* DCACHE_SHRINK_LIST flag. Those are guaranteed to be
* operating only with stack provided lists after they are
* properly isolated from the main list. It is thus, always a
* local access.
*/
return LRU_ROTATE;
}
d_lru_shrink_move(lru, dentry, freeable);
spin_unlock(&dentry->d_lock);
return LRU_REMOVED;
}
/**
* prune_dcache_sb - shrink the dcache
* @sb: superblock
* @sc: shrink control, passed to list_lru_shrink_walk()
*
* Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
* is done when we need more memory and called from the superblock shrinker
* function.
*
* This function may fail to free any resources if all the dentries are in
* use.
*/
long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
{
LIST_HEAD(dispose);
long freed;
freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
dentry_lru_isolate, &dispose);
shrink_dentry_list(&dispose);
return freed;
}
static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
struct list_lru_one *lru, void *arg)
{
struct list_head *freeable = arg;
struct dentry *dentry = container_of(item, struct dentry, d_lru);
/*
* we are inverting the lru lock/dentry->d_lock here,
* so use a trylock. If we fail to get the lock, just skip
* it
*/
if (!spin_trylock(&dentry->d_lock))
return LRU_SKIP;
d_lru_shrink_move(lru, dentry, freeable);
spin_unlock(&dentry->d_lock);
return LRU_REMOVED;
}
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
*
* Shrink the dcache for the specified super block. This is used to free
* the dcache before unmounting a file system.
*/
void shrink_dcache_sb(struct super_block *sb)
{
do {
LIST_HEAD(dispose);
list_lru_walk(&sb->s_dentry_lru,
dentry_lru_isolate_shrink, &dispose, 1024);
shrink_dentry_list(&dispose);
} while (list_lru_count(&sb->s_dentry_lru) > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);
/**
* enum d_walk_ret - action to talke during tree walk
* @D_WALK_CONTINUE: contrinue walk
* @D_WALK_QUIT: quit walk
* @D_WALK_NORETRY: quit when retry is needed
* @D_WALK_SKIP: skip this dentry and its children
*/
enum d_walk_ret {
D_WALK_CONTINUE,
D_WALK_QUIT,
D_WALK_NORETRY,
D_WALK_SKIP,
};
/**
* d_walk - walk the dentry tree
* @parent: start of walk
* @data: data passed to @enter() and @finish()
* @enter: callback when first entering the dentry
*
* The @enter() callbacks are called with d_lock held.
*/
static void d_walk(struct dentry *parent, void *data,
enum d_walk_ret (*enter)(void *, struct dentry *))
{
struct dentry *this_parent, *dentry;
unsigned seq = 0;
enum d_walk_ret ret;
bool retry = true;
again:
read_seqbegin_or_lock(&rename_lock, &seq);
this_parent = parent;
spin_lock(&this_parent->d_lock);
ret = enter(data, this_parent);
switch (ret) {
case D_WALK_CONTINUE:
break;
case D_WALK_QUIT:
case D_WALK_SKIP:
goto out_unlock;
case D_WALK_NORETRY:
retry = false;
break;
}
repeat:
dentry = d_first_child(this_parent);
resume:
hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
continue;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
ret = enter(data, dentry);
switch (ret) {
case D_WALK_CONTINUE:
break;
case D_WALK_QUIT:
spin_unlock(&dentry->d_lock);
goto out_unlock;
case D_WALK_NORETRY:
retry = false;
break;
case D_WALK_SKIP:
spin_unlock(&dentry->d_lock);
continue;
}
if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock);
spin_release(&dentry->d_lock.dep_map, _RET_IP_);
this_parent = dentry;
spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
goto repeat;
}
spin_unlock(&dentry->d_lock);
}
/*
* All done at this level ... ascend and resume the search.
*/
rcu_read_lock();
ascend:
if (this_parent != parent) {
dentry = this_parent;
this_parent = dentry->d_parent;
spin_unlock(&dentry->d_lock);
spin_lock(&this_parent->d_lock);
/* might go back up the wrong parent if we have had a rename. */
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
/* go into the first sibling still alive */
hlist_for_each_entry_continue(dentry, d_sib) {
if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
rcu_read_unlock();
goto resume;
}
}
goto ascend;
}
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
rcu_read_unlock();
out_unlock:
spin_unlock(&this_parent->d_lock);
done_seqretry(&rename_lock, seq);
return;
rename_retry:
spin_unlock(&this_parent->d_lock);
rcu_read_unlock();
BUG_ON(seq & 1);
if (!retry)
return;
seq = 1;
goto again;
}
struct check_mount {
struct vfsmount *mnt;
unsigned int mounted;
};
static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry)
{
struct check_mount *info = data;
struct path path = { .mnt = info->mnt, .dentry = dentry };
if (likely(!d_mountpoint(dentry)))
return D_WALK_CONTINUE;
if (__path_is_mountpoint(&path)) {
info->mounted = 1;
return D_WALK_QUIT;
}
return D_WALK_CONTINUE;
}
/**
* path_has_submounts - check for mounts over a dentry in the
* current namespace.
* @parent: path to check.
*
* Return true if the parent or its subdirectories contain
* a mount point in the current namespace.
*/
int path_has_submounts(const struct path *parent)
{
struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };
read_seqlock_excl(&mount_lock);
d_walk(parent->dentry, &data, path_check_mount);
read_sequnlock_excl(&mount_lock);
return data.mounted;
}
EXPORT_SYMBOL(path_has_submounts);
/*
* Called by mount code to set a mountpoint and check if the mountpoint is
* reachable (e.g. NFS can unhash a directory dentry and then the complete
* subtree can become unreachable).
*
* Only one of d_invalidate() and d_set_mounted() must succeed. For
* this reason take rename_lock and d_lock on dentry and ancestors.
*/
int d_set_mounted(struct dentry *dentry)
{
struct dentry *p;
int ret = -ENOENT;
write_seqlock(&rename_lock);
for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
/* Need exclusion wrt. d_invalidate() */
spin_lock(&p->d_lock);
if (unlikely(d_unhashed(p))) {
spin_unlock(&p->d_lock);
goto out;
}
spin_unlock(&p->d_lock);
}
spin_lock(&dentry->d_lock);
if (!d_unlinked(dentry)) {
ret = -EBUSY;
if (!d_mountpoint(dentry)) {
dentry->d_flags |= DCACHE_MOUNTED;
ret = 0;
}
}
spin_unlock(&dentry->d_lock);
out:
write_sequnlock(&rename_lock);
return ret;
}
/*
* Search the dentry child list of the specified parent,
* and move any unused dentries to the end of the unused
* list for prune_dcache(). We descend to the next level
* whenever the d_children list is non-empty and continue
* searching.
*
* It returns zero iff there are no unused children,
* otherwise it returns the number of children moved to
* the end of the unused list. This may not be the total
* number of unused children, because select_parent can
* drop the lock and return early due to latency
* constraints.
*/
struct select_data {
struct dentry *start;
union {
long found;
struct dentry *victim;
};
struct list_head dispose;
};
static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
{
struct select_data *data = _data;
enum d_walk_ret ret = D_WALK_CONTINUE;
if (data->start == dentry)
goto out;
if (dentry->d_flags & DCACHE_SHRINK_LIST) {
data->found++;
} else if (!dentry->d_lockref.count) {
to_shrink_list(dentry, &data->dispose);
data->found++;
} else if (dentry->d_lockref.count < 0) {
data->found++;
}
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
* the rest.
*/
if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY;
out:
return ret;
}
static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry)
{
struct select_data *data = _data;
enum d_walk_ret ret = D_WALK_CONTINUE;
if (data->start == dentry)
goto out;
if (!dentry->d_lockref.count) {
if (dentry->d_flags & DCACHE_SHRINK_LIST) {
rcu_read_lock();
data->victim = dentry;
return D_WALK_QUIT;
}
to_shrink_list(dentry, &data->dispose);
}
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
* the rest.
*/
if (!list_empty(&data->dispose))
ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY;
out:
return ret;
}
/**
* shrink_dcache_parent - prune dcache
* @parent: parent of entries to prune
*
* Prune the dcache to remove unused children of the parent dentry.
*/
void shrink_dcache_parent(struct dentry *parent)
{
for (;;) {
struct select_data data = {.start = parent};
INIT_LIST_HEAD(&data.dispose);
d_walk(parent, &data, select_collect);
if (!list_empty(&data.dispose)) {
shrink_dentry_list(&data.dispose);
continue;
}
cond_resched();
if (!data.found)
break;
data.victim = NULL;
d_walk(parent, &data, select_collect2);
if (data.victim) {
spin_lock(&data.victim->d_lock);
if (!lock_for_kill(data.victim)) {
spin_unlock(&data.victim->d_lock);
rcu_read_unlock();
} else {
shrink_kill(data.victim);
}
}
if (!list_empty(&data.dispose))
shrink_dentry_list(&data.dispose);
}
}
EXPORT_SYMBOL(shrink_dcache_parent);
static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
{
/* it has busy descendents; complain about those instead */
if (!hlist_empty(&dentry->d_children))
return D_WALK_CONTINUE;
/* root with refcount 1 is fine */
if (dentry == _data && dentry->d_lockref.count == 1)
return D_WALK_CONTINUE;
WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} "
" still in use (%d) [unmount of %s %s]\n",
dentry,
dentry->d_inode ?
dentry->d_inode->i_ino : 0UL,
dentry,
dentry->d_lockref.count,
dentry->d_sb->s_type->name,
dentry->d_sb->s_id);
return D_WALK_CONTINUE;
}
static void do_one_tree(struct dentry *dentry)
{
shrink_dcache_parent(dentry);
d_walk(dentry, dentry, umount_check);
d_drop(dentry);
dput(dentry);
}
/*
* destroy the dentries attached to a superblock on unmounting
*/
void shrink_dcache_for_umount(struct super_block *sb)
{
struct dentry *dentry;
rwsem_assert_held_write(&sb->s_umount);
dentry = sb->s_root;
sb->s_root = NULL;
do_one_tree(dentry);
while (!hlist_bl_empty(&sb->s_roots)) {
dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash));
do_one_tree(dentry);
}
}
static enum d_walk_ret find_submount(void *_data, struct dentry *dentry)
{
struct dentry **victim = _data;
if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry);
return D_WALK_QUIT;
}
return D_WALK_CONTINUE;
}
/**
* d_invalidate - detach submounts, prune dcache, and drop
* @dentry: dentry to invalidate (aka detach, prune and drop)
*/
void d_invalidate(struct dentry *dentry)
{
bool had_submounts = false;
spin_lock(&dentry->d_lock);
if (d_unhashed(dentry)) {
spin_unlock(&dentry->d_lock);
return;
}
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
/* Negative dentries can be dropped without further checks */
if (!dentry->d_inode)
return;
shrink_dcache_parent(dentry);
for (;;) {
struct dentry *victim = NULL;
d_walk(dentry, &victim, find_submount);
if (!victim) {
if (had_submounts)
shrink_dcache_parent(dentry);
return;
}
had_submounts = true;
detach_mounts(victim);
dput(victim);
}
}
EXPORT_SYMBOL(d_invalidate);
/**
* __d_alloc - allocate a dcache entry
* @sb: filesystem it will belong to
* @name: qstr of the name
*
* Allocates a dentry. It returns %NULL if there is insufficient memory
* available. On a success the dentry is returned. The name passed in is
* copied and the copy passed in may be reused after this call.
*/
static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
{
struct dentry *dentry;
char *dname;
int err;
dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru,
GFP_KERNEL);
if (!dentry)
return NULL;
/*
* We guarantee that the inline name is always NUL-terminated.
* This way the memcpy() done by the name switching in rename
* will still always have a NUL at the end, even if we might
* be overwriting an internal NUL character
*/
dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0;
if (unlikely(!name)) {
name = &slash_name;
dname = dentry->d_shortname.string;
} else if (name->len > DNAME_INLINE_LEN-1) {
size_t size = offsetof(struct external_name, name[1]);
struct external_name *p = kmalloc(size + name->len,
GFP_KERNEL_ACCOUNT |
__GFP_RECLAIMABLE);
if (!p) {
kmem_cache_free(dentry_cache, dentry);
return NULL;
}
atomic_set(&p->count, 1);
dname = p->name;
} else {
dname = dentry->d_shortname.string;
}
dentry->d_name.len = name->len;
dentry->d_name.hash = name->hash;
memcpy(dname, name->name, name->len);
dname[name->len] = 0;
/* Make sure we always see the terminating NUL character */
smp_store_release(&dentry->d_name.name, dname); /* ^^^ */
dentry->d_flags = 0;
lockref_init(&dentry->d_lockref);
seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
dentry->d_inode = NULL;
dentry->d_parent = dentry;
dentry->d_sb = sb;
dentry->d_op = NULL;
dentry->d_fsdata = NULL;
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_HLIST_HEAD(&dentry->d_children);
INIT_HLIST_NODE(&dentry->d_u.d_alias);
INIT_HLIST_NODE(&dentry->d_sib);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
if (dentry->d_op && dentry->d_op->d_init) {
err = dentry->d_op->d_init(dentry);
if (err) { if (dname_external(dentry)) kfree(external_name(dentry));
kmem_cache_free(dentry_cache, dentry);
return NULL;
}
}
this_cpu_inc(nr_dentry);
return dentry;
}
/**
* d_alloc - allocate a dcache entry
* @parent: parent of entry to allocate
* @name: qstr of the name
*
* Allocates a dentry. It returns %NULL if there is insufficient memory
* available. On a success the dentry is returned. The name passed in is
* copied and the copy passed in may be reused after this call.
*/
struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
{
struct dentry *dentry = __d_alloc(parent->d_sb, name);
if (!dentry)
return NULL;
spin_lock(&parent->d_lock);
/*
* don't need child lock because it is not subject
* to concurrency here
*/
dentry->d_parent = dget_dlock(parent);
hlist_add_head(&dentry->d_sib, &parent->d_children);
spin_unlock(&parent->d_lock);
return dentry;
}
EXPORT_SYMBOL(d_alloc);
struct dentry *d_alloc_anon(struct super_block *sb)
{
return __d_alloc(sb, NULL);
}
EXPORT_SYMBOL(d_alloc_anon);
struct dentry *d_alloc_cursor(struct dentry * parent)
{
struct dentry *dentry = d_alloc_anon(parent->d_sb);
if (dentry) {
dentry->d_flags |= DCACHE_DENTRY_CURSOR;
dentry->d_parent = dget(parent);
}
return dentry;
}
/**
* d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
* @sb: the superblock
* @name: qstr of the name
*
* For a filesystem that just pins its dentries in memory and never
* performs lookups at all, return an unhashed IS_ROOT dentry.
* This is used for pipes, sockets et.al. - the stuff that should
* never be anyone's children or parents. Unlike all other
* dentries, these will not have RCU delay between dropping the
* last reference and freeing them.
*
* The only user is alloc_file_pseudo() and that's what should
* be considered a public interface. Don't use directly.
*/
struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
{
static const struct dentry_operations anon_ops = {
.d_dname = simple_dname
};
struct dentry *dentry = __d_alloc(sb, name);
if (likely(dentry)) {
dentry->d_flags |= DCACHE_NORCU;
if (!sb->s_d_op) d_set_d_op(dentry, &anon_ops);
}
return dentry;
}
struct dentry *d_alloc_name(struct dentry *parent, const char *name)
{
struct qstr q;
q.name = name;
q.hash_len = hashlen_string(parent, name);
return d_alloc(parent, &q);
}
EXPORT_SYMBOL(d_alloc_name);
void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
{ WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH |
DCACHE_OP_COMPARE |
DCACHE_OP_REVALIDATE |
DCACHE_OP_WEAK_REVALIDATE |
DCACHE_OP_DELETE |
DCACHE_OP_REAL));
dentry->d_op = op;
if (!op)
return;
if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL;
}
EXPORT_SYMBOL(d_set_d_op);
static unsigned d_flags_for_inode(struct inode *inode)
{
unsigned add_flags = DCACHE_REGULAR_TYPE;
if (!inode)
return DCACHE_MISS_TYPE;
if (S_ISDIR(inode->i_mode)) {
add_flags = DCACHE_DIRECTORY_TYPE;
if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup))
add_flags = DCACHE_AUTODIR_TYPE;
else
inode->i_opflags |= IOP_LOOKUP;
}
goto type_determined;
}
if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) {
add_flags = DCACHE_SYMLINK_TYPE;
goto type_determined;
}
inode->i_opflags |= IOP_NOFOLLOW;
}
if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE;
type_determined:
if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT;
return add_flags;
}
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{ unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry));
spin_lock(&dentry->d_lock);
/*
* The negative counter only tracks dentries on the LRU. Don't dec if
* d_lru is on another list.
*/
if ((dentry->d_flags &
(DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
raw_write_seqcount_end(&dentry->d_seq);
fsnotify_update_flags(dentry);
spin_unlock(&dentry->d_lock);
}
/**
* d_instantiate - fill in inode information for a dentry
* @entry: dentry to complete
* @inode: inode to attach to this dentry
*
* Fill in inode information in the entry.
*
* This turns negative dentries into productive full members
* of society.
*
* NOTE! This assumes that the inode count has been incremented
* (or otherwise set) by the caller to indicate that it is now
* in use by the dcache.
*/
void d_instantiate(struct dentry *entry, struct inode * inode)
{ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
}
}
EXPORT_SYMBOL(d_instantiate);
/*
* This should be equivalent to d_instantiate() + unlock_new_inode(),
* with lockdep-related part of unlock_new_inode() done before
* anything else. Use that instead of open-coding d_instantiate()/
* unlock_new_inode() combinations.
*/
void d_instantiate_new(struct dentry *entry, struct inode *inode)
{
BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
BUG_ON(!inode);
lockdep_annotate_inode_mutex_key(inode);
security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW & ~I_CREATING;
/*
* Pairs with the barrier in prepare_to_wait_event() to make sure
* ___wait_var_event() either sees the bit cleared or
* waitqueue_active() check in wake_up_var() sees the waiter.
*/
smp_mb();
inode_wake_up_bit(inode, __I_NEW);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_instantiate_new);
struct dentry *d_make_root(struct inode *root_inode)
{
struct dentry *res = NULL;
if (root_inode) {
res = d_alloc_anon(root_inode->i_sb);
if (res)
d_instantiate(res, root_inode);
else
iput(root_inode);
}
return res;
}
EXPORT_SYMBOL(d_make_root);
static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected)
{
struct super_block *sb;
struct dentry *new, *res;
if (!inode)
return ERR_PTR(-ESTALE);
if (IS_ERR(inode))
return ERR_CAST(inode);
sb = inode->i_sb;
res = d_find_any_alias(inode); /* existing alias? */
if (res)
goto out;
new = d_alloc_anon(sb);
if (!new) {
res = ERR_PTR(-ENOMEM);
goto out;
}
security_d_instantiate(new, inode);
spin_lock(&inode->i_lock);
res = __d_find_any_alias(inode); /* recheck under lock */
if (likely(!res)) { /* still no alias, attach a disconnected dentry */
unsigned add_flags = d_flags_for_inode(inode);
if (disconnected)
add_flags |= DCACHE_DISCONNECTED;
spin_lock(&new->d_lock);
__d_set_inode_and_type(new, inode, add_flags);
hlist_add_head(&new->d_u.d_alias, &inode->i_dentry);
if (!disconnected) {
hlist_bl_lock(&sb->s_roots);
hlist_bl_add_head(&new->d_hash, &sb->s_roots);
hlist_bl_unlock(&sb->s_roots);
}
spin_unlock(&new->d_lock);
spin_unlock(&inode->i_lock);
inode = NULL; /* consumed by new->d_inode */
res = new;
} else {
spin_unlock(&inode->i_lock);
dput(new);
}
out:
iput(inode);
return res;
}
/**
* d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode
* @inode: inode to allocate the dentry for
*
* Obtain a dentry for an inode resulting from NFS filehandle conversion or
* similar open by handle operations. The returned dentry may be anonymous,
* or may have a full name (if the inode was already in the cache).
*
* When called on a directory inode, we must ensure that the inode only ever
* has one dentry. If a dentry is found, that is returned instead of
* allocating a new one.
*
* On successful return, the reference to the inode has been transferred
* to the dentry. In case of an error the reference on the inode is released.
* To make it easier to use in export operations a %NULL or IS_ERR inode may
* be passed in and the error will be propagated to the return value,
* with a %NULL @inode replaced by ERR_PTR(-ESTALE).
*/
struct dentry *d_obtain_alias(struct inode *inode)
{
return __d_obtain_alias(inode, true);
}
EXPORT_SYMBOL(d_obtain_alias);
/**
* d_obtain_root - find or allocate a dentry for a given inode
* @inode: inode to allocate the dentry for
*
* Obtain an IS_ROOT dentry for the root of a filesystem.
*
* We must ensure that directory inodes only ever have one dentry. If a
* dentry is found, that is returned instead of allocating a new one.
*
* On successful return, the reference to the inode has been transferred
* to the dentry. In case of an error the reference on the inode is
* released. A %NULL or IS_ERR inode may be passed in and will be the
* error will be propagate to the return value, with a %NULL @inode
* replaced by ERR_PTR(-ESTALE).
*/
struct dentry *d_obtain_root(struct inode *inode)
{
return __d_obtain_alias(inode, false);
}
EXPORT_SYMBOL(d_obtain_root);
/**
* d_add_ci - lookup or allocate new dentry with case-exact name
* @dentry: the negative dentry that was passed to the parent's lookup func
* @inode: the inode case-insensitive lookup has found
* @name: the case-exact name to be associated with the returned dentry
*
* This is to avoid filling the dcache with case-insensitive names to the
* same inode, only the actual correct case is stored in the dcache for
* case-insensitive filesystems.
*
* For a case-insensitive lookup match and if the case-exact dentry
* already exists in the dcache, use it and return it.
*
* If no entry exists with the exact case name, allocate new dentry with
* the exact case, and return the spliced entry.
*/
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
struct dentry *found, *res;
/*
* First check if a dentry matching the name already exists,
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
if (found) {
iput(inode);
return found;
}
if (d_in_lookup(dentry)) {
found = d_alloc_parallel(dentry->d_parent, name,
dentry->d_wait);
if (IS_ERR(found) || !d_in_lookup(found)) {
iput(inode);
return found;
}
} else {
found = d_alloc(dentry->d_parent, name);
if (!found) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
}
res = d_splice_alias(inode, found);
if (res) {
d_lookup_done(found);
dput(found);
return res;
}
return found;
}
EXPORT_SYMBOL(d_add_ci);
/**
* d_same_name - compare dentry name with case-exact name
* @dentry: the negative dentry that was passed to the parent's lookup func
* @parent: parent dentry
* @name: the case-exact name to be associated with the returned dentry
*
* Return: true if names are same, or false
*/
bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
const struct qstr *name)
{
if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) {
if (dentry->d_name.len != name->len)
return false;
return dentry_cmp(dentry, name->name, name->len) == 0;
}
return parent->d_op->d_compare(dentry,
dentry->d_name.len, dentry->d_name.name,
name) == 0;
}
EXPORT_SYMBOL_GPL(d_same_name);
/*
* This is __d_lookup_rcu() when the parent dentry has
* DCACHE_OP_COMPARE, which makes things much nastier.
*/
static noinline struct dentry *__d_lookup_rcu_op_compare(
const struct dentry *parent,
const struct qstr *name,
unsigned *seqp)
{
u64 hashlen = name->hash_len;
struct hlist_bl_head *b = d_hash(hashlen);
struct hlist_bl_node *node;
struct dentry *dentry;
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
int tlen;
const char *tname;
unsigned seq;
seqretry:
seq = raw_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
continue;
if (dentry->d_name.hash != hashlen_hash(hashlen))
continue;
tlen = dentry->d_name.len;
tname = dentry->d_name.name;
/* we want a consistent (name,len) pair */
if (read_seqcount_retry(&dentry->d_seq, seq)) {
cpu_relax();
goto seqretry;
}
if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0)
continue;
*seqp = seq;
return dentry;
}
return NULL;
}
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
* @name: qstr of name we wish to find
* @seqp: returns d_seq value at the point where the dentry was found
* Returns: dentry, or NULL
*
* __d_lookup_rcu is the dcache lookup function for rcu-walk name
* resolution (store-free path walking) design described in
* Documentation/filesystems/path-lookup.txt.
*
* This is not to be used outside core vfs.
*
* __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock
* held, and rcu_read_lock held. The returned dentry must not be stored into
* without taking d_lock and checking d_seq sequence count against @seq
* returned here.
*
* Alternatively, __d_lookup_rcu may be called again to look up the child of
* the returned dentry, so long as its parent's seqlock is checked after the
* child is looked up. Thus, an interlocking stepping of sequence lock checks
* is formed, giving integrity down the path walk.
*
* NOTE! The caller *has* to check the resulting dentry against the sequence
* number we've returned before using any of the resulting dentry state!
*/
struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
unsigned *seqp)
{
u64 hashlen = name->hash_len;
const unsigned char *str = name->name;
struct hlist_bl_head *b = d_hash(hashlen);
struct hlist_bl_node *node;
struct dentry *dentry;
/*
* Note: There is significant duplication with __d_lookup_rcu which is
* required to prevent single threaded performance regressions
* especially on architectures where smp_rmb (in seqcounts) are costly.
* Keep the two functions in sync.
*/
if (unlikely(parent->d_flags & DCACHE_OP_COMPARE))
return __d_lookup_rcu_op_compare(parent, name, seqp);
/*
* The hash list is protected using RCU.
*
* Carefully use d_seq when comparing a candidate dentry, to avoid
* races with d_move().
*
* It is possible that concurrent renames can mess up our list
* walk here and result in missing our dentry, resulting in the
* false-negative result. d_lookup() protects against concurrent
* renames using rename_lock seqlock.
*
* See Documentation/filesystems/path-lookup.txt for more details.
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
unsigned seq;
/*
* The dentry sequence count protects us from concurrent
* renames, and thus protects parent and name fields.
*
* The caller must perform a seqcount check in order
* to do anything useful with the returned dentry.
*
* NOTE! We do a "raw" seqcount_begin here. That means that
* we don't wait for the sequence count to stabilize if it
* is in the middle of a sequence change. If we do the slow
* dentry compare, we will do seqretries until it is stable,
* and if we end up with a successful lookup, we actually
* want to exit RCU lookup anyway.
*
* Note that raw_seqcount_begin still *does* smp_rmb(), so
* we are still guaranteed NUL-termination of ->d_name.name.
*/
seq = raw_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
continue;
if (dentry->d_name.hash_len != hashlen)
continue;
if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
continue;
*seqp = seq;
return dentry;
}
return NULL;
}
/**
* d_lookup - search for a dentry
* @parent: parent dentry
* @name: qstr of name we wish to find
* Returns: dentry, or NULL
*
* d_lookup searches the children of the parent dentry for the name in
* question. If the dentry is found its reference count is incremented and the
* dentry is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned if the dentry does not exist.
*/
struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
{
struct dentry *dentry;
unsigned seq;
do {
seq = read_seqbegin(&rename_lock);
dentry = __d_lookup(parent, name);
if (dentry)
break;
} while (read_seqretry(&rename_lock, seq));
return dentry;
}
EXPORT_SYMBOL(d_lookup);
/**
* __d_lookup - search for a dentry (racy)
* @parent: parent dentry
* @name: qstr of name we wish to find
* Returns: dentry, or NULL
*
* __d_lookup is like d_lookup, however it may (rarely) return a
* false-negative result due to unrelated rename activity.
*
* __d_lookup is slightly faster by avoiding rename_lock read seqlock,
* however it must be used carefully, eg. with a following d_lookup in
* the case of failure.
*
* __d_lookup callers must be commented.
*/
struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
{
unsigned int hash = name->hash;
struct hlist_bl_head *b = d_hash(hash);
struct hlist_bl_node *node;
struct dentry *found = NULL;
struct dentry *dentry;
/*
* Note: There is significant duplication with __d_lookup_rcu which is
* required to prevent single threaded performance regressions
* especially on architectures where smp_rmb (in seqcounts) are costly.
* Keep the two functions in sync.
*/
/*
* The hash list is protected using RCU.
*
* Take d_lock when comparing a candidate dentry, to avoid races
* with d_move().
*
* It is possible that concurrent renames can mess up our list
* walk here and result in missing our dentry, resulting in the
* false-negative result. d_lookup() protects against concurrent
* renames using rename_lock seqlock.
*
* See Documentation/filesystems/path-lookup.txt for more details.
*/
rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash)
continue;
spin_lock(&dentry->d_lock);
if (dentry->d_parent != parent)
goto next;
if (d_unhashed(dentry))
goto next;
if (!d_same_name(dentry, parent, name))
goto next;
dentry->d_lockref.count++;
found = dentry;
spin_unlock(&dentry->d_lock);
break;
next:
spin_unlock(&dentry->d_lock);
}
rcu_read_unlock();
return found;
}
/**
* d_hash_and_lookup - hash the qstr then search for a dentry
* @dir: Directory to search in
* @name: qstr of name we wish to find
*
* On lookup failure NULL is returned; on bad name - ERR_PTR(-error)
*/
struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
{
/*
* Check for a fs-specific hash function. Note that we must
* calculate the standard hash first, as the d_op->d_hash()
* routine may choose to leave the hash value unchanged.
*/
name->hash = full_name_hash(dir, name->name, name->len);
if (dir->d_flags & DCACHE_OP_HASH) {
int err = dir->d_op->d_hash(dir, name);
if (unlikely(err < 0))
return ERR_PTR(err);
}
return d_lookup(dir, name);
}
EXPORT_SYMBOL(d_hash_and_lookup);
/*
* When a file is deleted, we have two options:
* - turn this dentry into a negative dentry
* - unhash this dentry and free it.
*
* Usually, we want to just turn this into
* a negative dentry, but if anybody else is
* currently using the dentry or the inode
* we can't do that and we fall back on removing
* it from the hash queues and waiting for
* it to be deleted later when it has no users
*/
/**
* d_delete - delete a dentry
* @dentry: The dentry to delete
*
* Turn the dentry into a negative dentry if possible, otherwise
* remove it from the hash queues so it can be deleted later
*/
void d_delete(struct dentry * dentry)
{
struct inode *inode = dentry->d_inode;
spin_lock(&inode->i_lock);
spin_lock(&dentry->d_lock);
/*
* Are we the only user?
*/
if (dentry->d_lockref.count == 1) {
if (dentry_negative_policy)
__d_drop(dentry);
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
dentry_unlink_inode(dentry);
} else {
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
}
}
EXPORT_SYMBOL(d_delete);
static void __d_rehash(struct dentry *entry)
{
struct hlist_bl_head *b = d_hash(entry->d_name.hash);
hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b);
}
/**
* d_rehash - add an entry back to the hash
* @entry: dentry to add to the hash
*
* Adds a dentry to the hash according to its name.
*/
void d_rehash(struct dentry * entry)
{
spin_lock(&entry->d_lock);
__d_rehash(entry);
spin_unlock(&entry->d_lock);
}
EXPORT_SYMBOL(d_rehash);
static inline unsigned start_dir_add(struct inode *dir)
{ preempt_disable_nested();
for (;;) {
unsigned n = dir->i_dir_seq;
if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
return n;
cpu_relax();
}
}
static inline void end_dir_add(struct inode *dir, unsigned int n,
wait_queue_head_t *d_wait)
{
smp_store_release(&dir->i_dir_seq, n + 2);
preempt_enable_nested();
if (wq_has_sleeper(d_wait)) wake_up_all(d_wait);
}
static void d_wait_lookup(struct dentry *dentry)
{
if (d_in_lookup(dentry)) {
DECLARE_WAITQUEUE(wait, current);
add_wait_queue(dentry->d_wait, &wait);
do {
set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock(&dentry->d_lock);
schedule();
spin_lock(&dentry->d_lock);
} while (d_in_lookup(dentry));
}
}
struct dentry *d_alloc_parallel(struct dentry *parent,
const struct qstr *name,
wait_queue_head_t *wq)
{
unsigned int hash = name->hash;
struct hlist_bl_head *b = in_lookup_hash(parent, hash);
struct hlist_bl_node *node;
struct dentry *new = d_alloc(parent, name);
struct dentry *dentry;
unsigned seq, r_seq, d_seq;
if (unlikely(!new))
return ERR_PTR(-ENOMEM);
retry:
rcu_read_lock();
seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
r_seq = read_seqbegin(&rename_lock);
dentry = __d_lookup_rcu(parent, name, &d_seq);
if (unlikely(dentry)) {
if (!lockref_get_not_dead(&dentry->d_lockref)) {
rcu_read_unlock();
goto retry;
}
if (read_seqcount_retry(&dentry->d_seq, d_seq)) {
rcu_read_unlock();
dput(dentry);
goto retry;
}
rcu_read_unlock();
dput(new);
return dentry;
}
if (unlikely(read_seqretry(&rename_lock, r_seq))) {
rcu_read_unlock();
goto retry;
}
if (unlikely(seq & 1)) {
rcu_read_unlock();
goto retry;
}
hlist_bl_lock(b);
if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) {
hlist_bl_unlock(b);
rcu_read_unlock();
goto retry;
}
/*
* No changes for the parent since the beginning of d_lookup().
* Since all removals from the chain happen with hlist_bl_lock(),
* any potential in-lookup matches are going to stay here until
* we unlock the chain. All fields are stable in everything
* we encounter.
*/
hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash)
continue;
if (dentry->d_parent != parent)
continue;
if (!d_same_name(dentry, parent, name))
continue;
hlist_bl_unlock(b);
/* now we can try to grab a reference */
if (!lockref_get_not_dead(&dentry->d_lockref)) {
rcu_read_unlock();
goto retry;
}
rcu_read_unlock();
/*
* somebody is likely to be still doing lookup for it;
* wait for them to finish
*/
spin_lock(&dentry->d_lock);
d_wait_lookup(dentry);
/*
* it's not in-lookup anymore; in principle we should repeat
* everything from dcache lookup, but it's likely to be what
* d_lookup() would've found anyway. If it is, just return it;
* otherwise we really have to repeat the whole thing.
*/
if (unlikely(dentry->d_name.hash != hash))
goto mismatch;
if (unlikely(dentry->d_parent != parent))
goto mismatch;
if (unlikely(d_unhashed(dentry)))
goto mismatch;
if (unlikely(!d_same_name(dentry, parent, name)))
goto mismatch;
/* OK, it *is* a hashed match; return it */
spin_unlock(&dentry->d_lock);
dput(new);
return dentry;
}
rcu_read_unlock();
/* we can't take ->d_lock here; it's OK, though. */
new->d_flags |= DCACHE_PAR_LOOKUP;
new->d_wait = wq;
hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b);
return new;
mismatch:
spin_unlock(&dentry->d_lock);
dput(dentry);
goto retry;
}
EXPORT_SYMBOL(d_alloc_parallel);
/*
* - Unhash the dentry
* - Retrieve and clear the waitqueue head in dentry
* - Return the waitqueue head
*/
static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry)
{
wait_queue_head_t *d_wait;
struct hlist_bl_head *b;
lockdep_assert_held(&dentry->d_lock);
b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash);
hlist_bl_lock(b);
dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
d_wait = dentry->d_wait;
dentry->d_wait = NULL;
hlist_bl_unlock(b);
INIT_HLIST_NODE(&dentry->d_u.d_alias);
INIT_LIST_HEAD(&dentry->d_lru);
return d_wait;
}
void __d_lookup_unhash_wake(struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
wake_up_all(__d_lookup_unhash(dentry));
spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(__d_lookup_unhash_wake);
/* inode->i_lock held if inode is non-NULL */
static inline void __d_add(struct dentry *dentry, struct inode *inode)
{
wait_queue_head_t *d_wait;
struct inode *dir = NULL;
unsigned n;
spin_lock(&dentry->d_lock);
if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode;
n = start_dir_add(dir);
d_wait = __d_lookup_unhash(dentry);
}
if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
raw_write_seqcount_end(&dentry->d_seq);
fsnotify_update_flags(dentry);
}
__d_rehash(dentry);
if (dir) end_dir_add(dir, n, d_wait);
spin_unlock(&dentry->d_lock);
if (inode) spin_unlock(&inode->i_lock);
}
/**
* d_add - add dentry to hash queues
* @entry: dentry to add
* @inode: The inode to attach to this dentry
*
* This adds the entry to the hash queues and initializes @inode.
* The entry was actually filled in earlier during d_alloc().
*/
void d_add(struct dentry *entry, struct inode *inode)
{ if (inode) { security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
}
__d_add(entry, inode);
}
EXPORT_SYMBOL(d_add);
static void swap_names(struct dentry *dentry, struct dentry *target)
{
if (unlikely(dname_external(target))) {
if (unlikely(dname_external(dentry))) {
/*
* Both external: swap the pointers
*/
swap(target->d_name.name, dentry->d_name.name);
} else {
/*
* dentry:internal, target:external. Steal target's
* storage and make target internal.
*/
dentry->d_name.name = target->d_name.name;
target->d_shortname = dentry->d_shortname;
target->d_name.name = target->d_shortname.string;
}
} else {
if (unlikely(dname_external(dentry))) {
/*
* dentry:external, target:internal. Give dentry's
* storage to target and make dentry internal
*/
target->d_name.name = dentry->d_name.name;
dentry->d_shortname = target->d_shortname;
dentry->d_name.name = dentry->d_shortname.string;
} else {
/*
* Both are internal.
*/
for (int i = 0; i < DNAME_INLINE_WORDS; i++)
swap(dentry->d_shortname.words[i],
target->d_shortname.words[i]);
}
}
swap(dentry->d_name.hash_len, target->d_name.hash_len);
}
static void copy_name(struct dentry *dentry, struct dentry *target)
{
struct external_name *old_name = NULL;
if (unlikely(dname_external(dentry)))
old_name = external_name(dentry);
if (unlikely(dname_external(target))) {
atomic_inc(&external_name(target)->count);
dentry->d_name = target->d_name;
} else {
dentry->d_shortname = target->d_shortname;
dentry->d_name.name = dentry->d_shortname.string;
dentry->d_name.hash_len = target->d_name.hash_len;
}
if (old_name && likely(atomic_dec_and_test(&old_name->count)))
kfree_rcu(old_name, head);
}
/*
* __d_move - move a dentry
* @dentry: entry to move
* @target: new dentry
* @exchange: exchange the two dentries
*
* Update the dcache to reflect the move of a file name. Negative
* dcache entries should not be moved in this way. Caller must hold
* rename_lock, the i_mutex of the source and target directories,
* and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
*/
static void __d_move(struct dentry *dentry, struct dentry *target,
bool exchange)
{
struct dentry *old_parent, *p;
wait_queue_head_t *d_wait;
struct inode *dir = NULL;
unsigned n;
WARN_ON(!dentry->d_inode);
if (WARN_ON(dentry == target))
return;
BUG_ON(d_ancestor(target, dentry));
old_parent = dentry->d_parent;
p = d_ancestor(old_parent, target);
if (IS_ROOT(dentry)) {
BUG_ON(p);
spin_lock(&target->d_parent->d_lock);
} else if (!p) {
/* target is not a descendent of dentry->d_parent */
spin_lock(&target->d_parent->d_lock);
spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED);
} else {
BUG_ON(p == dentry);
spin_lock(&old_parent->d_lock);
if (p != target)
spin_lock_nested(&target->d_parent->d_lock,
DENTRY_D_LOCK_NESTED);
}
spin_lock_nested(&dentry->d_lock, 2);
spin_lock_nested(&target->d_lock, 3);
if (unlikely(d_in_lookup(target))) {
dir = target->d_parent->d_inode;
n = start_dir_add(dir);
d_wait = __d_lookup_unhash(target);
}
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
/* unhash both */
if (!d_unhashed(dentry))
___d_drop(dentry);
if (!d_unhashed(target))
___d_drop(target);
/* ... and switch them in the tree */
dentry->d_parent = target->d_parent;
if (!exchange) {
copy_name(dentry, target);
target->d_hash.pprev = NULL;
dentry->d_parent->d_lockref.count++;
if (dentry != old_parent) /* wasn't IS_ROOT */
WARN_ON(!--old_parent->d_lockref.count);
} else {
target->d_parent = old_parent;
swap_names(dentry, target);
if (!hlist_unhashed(&target->d_sib))
__hlist_del(&target->d_sib);
hlist_add_head(&target->d_sib, &target->d_parent->d_children);
__d_rehash(target);
fsnotify_update_flags(target);
}
if (!hlist_unhashed(&dentry->d_sib))
__hlist_del(&dentry->d_sib);
hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children);
__d_rehash(dentry);
fsnotify_update_flags(dentry);
fscrypt_handle_d_move(dentry);
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
if (dir)
end_dir_add(dir, n, d_wait);
if (dentry->d_parent != old_parent)
spin_unlock(&dentry->d_parent->d_lock);
if (dentry != old_parent)
spin_unlock(&old_parent->d_lock);
spin_unlock(&target->d_lock);
spin_unlock(&dentry->d_lock);
}
/*
* d_move - move a dentry
* @dentry: entry to move
* @target: new dentry
*
* Update the dcache to reflect the move of a file name. Negative
* dcache entries should not be moved in this way. See the locking
* requirements for __d_move.
*/
void d_move(struct dentry *dentry, struct dentry *target)
{
write_seqlock(&rename_lock);
__d_move(dentry, target, false);
write_sequnlock(&rename_lock);
}
EXPORT_SYMBOL(d_move);
/*
* d_exchange - exchange two dentries
* @dentry1: first dentry
* @dentry2: second dentry
*/
void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
{
write_seqlock(&rename_lock);
WARN_ON(!dentry1->d_inode);
WARN_ON(!dentry2->d_inode);
WARN_ON(IS_ROOT(dentry1));
WARN_ON(IS_ROOT(dentry2));
__d_move(dentry1, dentry2, true);
write_sequnlock(&rename_lock);
}
/**
* d_ancestor - search for an ancestor
* @p1: ancestor dentry
* @p2: child dentry
*
* Returns the ancestor dentry of p2 which is a child of p1, if p1 is
* an ancestor of p2, else NULL.
*/
struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
{
struct dentry *p;
for (p = p2; !IS_ROOT(p); p = p->d_parent) {
if (p->d_parent == p1)
return p;
}
return NULL;
}
/*
* This helper attempts to cope with remotely renamed directories
*
* It assumes that the caller is already holding
* dentry->d_parent->d_inode->i_mutex, and rename_lock
*
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
*/
static int __d_unalias(struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL;
struct rw_semaphore *m2 = NULL;
int ret = -ESTALE;
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
goto out_unalias;
/* See lock_rename() */
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
if (!inode_trylock_shared(alias->d_parent->d_inode))
goto out_err;
m2 = &alias->d_parent->d_inode->i_rwsem;
out_unalias:
if (alias->d_op && alias->d_op->d_unalias_trylock &&
!alias->d_op->d_unalias_trylock(alias))
goto out_err;
__d_move(alias, dentry, false);
if (alias->d_op && alias->d_op->d_unalias_unlock)
alias->d_op->d_unalias_unlock(alias);
ret = 0;
out_err:
if (m2)
up_read(m2);
if (m1)
mutex_unlock(m1);
return ret;
}
/**
* d_splice_alias - splice a disconnected dentry into the tree if one exists
* @inode: the inode which may have a disconnected dentry
* @dentry: a negative dentry which we want to point to the inode.
*
* If inode is a directory and has an IS_ROOT alias, then d_move that in
* place of the given dentry and return it, else simply d_add the inode
* to the dentry and return NULL.
*
* If a non-IS_ROOT directory is found, the filesystem is corrupt, and
* we should error out: directories can't have multiple aliases.
*
* This is needed in the lookup routine of any filesystem that is exportable
* (via knfsd) so that we can build dcache paths to directories effectively.
*
* If a dentry was found and moved, then it is returned. Otherwise NULL
* is returned. This matches the expected return value of ->lookup.
*
* Cluster filesystems may call this function with a negative, hashed dentry.
* In that case, we know that the inode will be a regular file, and also this
* will only occur during atomic_open. So we need to check for the dentry
* being already hashed only in the final case.
*/
struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
{
if (IS_ERR(inode))
return ERR_CAST(inode);
BUG_ON(!d_unhashed(dentry));
if (!inode)
goto out;
security_d_instantiate(dentry, inode);
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode)) {
struct dentry *new = __d_find_any_alias(inode);
if (unlikely(new)) {
/* The reference to new ensures it remains an alias */
spin_unlock(&inode->i_lock);
write_seqlock(&rename_lock);
if (unlikely(d_ancestor(new, dentry))) {
write_sequnlock(&rename_lock);
dput(new);
new = ERR_PTR(-ELOOP);
pr_warn_ratelimited(
"VFS: Lookup of '%s' in %s %s"
" would have caused loop\n",
dentry->d_name.name,
inode->i_sb->s_type->name,
inode->i_sb->s_id);
} else if (!IS_ROOT(new)) {
struct dentry *old_parent = dget(new->d_parent);
int err = __d_unalias(dentry, new);
write_sequnlock(&rename_lock);
if (err) {
dput(new);
new = ERR_PTR(err);
}
dput(old_parent);
} else {
__d_move(new, dentry, false);
write_sequnlock(&rename_lock);
}
iput(inode);
return new;
}
}
out:
__d_add(dentry, inode);
return NULL;
}
EXPORT_SYMBOL(d_splice_alias);
/*
* Test whether new_dentry is a subdirectory of old_dentry.
*
* Trivially implemented using the dcache structure
*/
/**
* is_subdir - is new dentry a subdirectory of old_dentry
* @new_dentry: new dentry
* @old_dentry: old dentry
*
* Returns true if new_dentry is a subdirectory of the parent (at any depth).
* Returns false otherwise.
* Caller must ensure that "new_dentry" is pinned before calling is_subdir()
*/
bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
{
bool subdir;
unsigned seq;
if (new_dentry == old_dentry)
return true;
/* Access d_parent under rcu as d_move() may change it. */
rcu_read_lock();
seq = read_seqbegin(&rename_lock);
subdir = d_ancestor(old_dentry, new_dentry);
/* Try lockless once... */
if (read_seqretry(&rename_lock, seq)) {
/* ...else acquire lock for progress even on deep chains. */
read_seqlock_excl(&rename_lock);
subdir = d_ancestor(old_dentry, new_dentry);
read_sequnlock_excl(&rename_lock);
}
rcu_read_unlock();
return subdir;
}
EXPORT_SYMBOL(is_subdir);
static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
{
struct dentry *root = data;
if (dentry != root) {
if (d_unhashed(dentry) || !dentry->d_inode)
return D_WALK_SKIP;
if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
dentry->d_flags |= DCACHE_GENOCIDE;
dentry->d_lockref.count--;
}
}
return D_WALK_CONTINUE;
}
void d_genocide(struct dentry *parent)
{
d_walk(parent, parent, d_genocide_kill);
}
void d_mark_tmpfile(struct file *file, struct inode *inode)
{
struct dentry *dentry = file->f_path.dentry;
BUG_ON(dname_external(dentry) ||
!hlist_unhashed(&dentry->d_u.d_alias) ||
!d_unlinked(dentry));
spin_lock(&dentry->d_parent->d_lock);
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu",
(unsigned long long)inode->i_ino);
spin_unlock(&dentry->d_lock);
spin_unlock(&dentry->d_parent->d_lock);
}
EXPORT_SYMBOL(d_mark_tmpfile);
void d_tmpfile(struct file *file, struct inode *inode)
{
struct dentry *dentry = file->f_path.dentry;
inode_dec_link_count(inode);
d_mark_tmpfile(file, inode);
d_instantiate(dentry, inode);
}
EXPORT_SYMBOL(d_tmpfile);
/*
* Obtain inode number of the parent dentry.
*/
ino_t d_parent_ino(struct dentry *dentry)
{
struct dentry *parent;
struct inode *iparent;
unsigned seq;
ino_t ret;
scoped_guard(rcu) {
seq = raw_seqcount_begin(&dentry->d_seq);
parent = READ_ONCE(dentry->d_parent);
iparent = d_inode_rcu(parent);
if (likely(iparent)) {
ret = iparent->i_ino;
if (!read_seqcount_retry(&dentry->d_seq, seq))
return ret;
}
}
spin_lock(&dentry->d_lock);
ret = dentry->d_parent->d_inode->i_ino;
spin_unlock(&dentry->d_lock);
return ret;
}
EXPORT_SYMBOL(d_parent_ino);
static __initdata unsigned long dhash_entries;
static int __init set_dhash_entries(char *str)
{
if (!str)
return 0;
dhash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("dhash_entries=", set_dhash_entries);
static void __init dcache_init_early(void)
{
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
sizeof(struct hlist_bl_head),
dhash_entries,
13,
HASH_EARLY | HASH_ZERO,
&d_hash_shift,
NULL,
0,
0);
d_hash_shift = 32 - d_hash_shift;
runtime_const_init(shift, d_hash_shift);
runtime_const_init(ptr, dentry_hashtable);
}
static void __init dcache_init(void)
{
/*
* A constructor could be added for stable state like the lists,
* but it is probably not worth it because of the cache nature
* of the dcache.
*/
dentry_cache = KMEM_CACHE_USERCOPY(dentry,
SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
d_shortname.string);
/* Hash may have been set up in dcache_init_early */
if (!hashdist)
return;
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
sizeof(struct hlist_bl_head),
dhash_entries,
13,
HASH_ZERO,
&d_hash_shift,
NULL,
0,
0);
d_hash_shift = 32 - d_hash_shift;
runtime_const_init(shift, d_hash_shift);
runtime_const_init(ptr, dentry_hashtable);
}
/* SLAB cache for __getname() consumers */
struct kmem_cache *names_cachep __ro_after_init;
EXPORT_SYMBOL(names_cachep);
void __init vfs_caches_init_early(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++)
INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]);
dcache_init_early();
inode_init_early();
}
void __init vfs_caches_init(void)
{
names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL);
dcache_init();
inode_init();
files_init();
files_maxfiles_init();
mnt_init();
bdev_cache_init();
chrdev_init();
}
// SPDX-License-Identifier: GPL-2.0
/*
* SafeSetID Linux Security Module
*
* Author: Micah Morton <mortonm@chromium.org>
*
* Copyright (C) 2018 The Chromium OS Authors.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2, as
* published by the Free Software Foundation.
*
*/
#define pr_fmt(fmt) "SafeSetID: " fmt
#include <linux/lsm_hooks.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/sched/task_stack.h>
#include <linux/security.h>
#include <uapi/linux/lsm.h>
#include "lsm.h"
/* Flag indicating whether initialization completed */
int safesetid_initialized __initdata;
struct setid_ruleset __rcu *safesetid_setuid_rules;
struct setid_ruleset __rcu *safesetid_setgid_rules;
/* Compute a decision for a transition from @src to @dst under @policy. */
enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy,
kid_t src, kid_t dst)
{
struct setid_rule *rule;
enum sid_policy_type result = SIDPOL_DEFAULT;
if (policy->type == UID) {
hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) {
if (!uid_eq(rule->src_id.uid, src.uid))
continue;
if (uid_eq(rule->dst_id.uid, dst.uid))
return SIDPOL_ALLOWED;
result = SIDPOL_CONSTRAINED;
}
} else if (policy->type == GID) {
hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) {
if (!gid_eq(rule->src_id.gid, src.gid))
continue;
if (gid_eq(rule->dst_id.gid, dst.gid)){
return SIDPOL_ALLOWED;
}
result = SIDPOL_CONSTRAINED;
}
} else {
/* Should not reach here, report the ID as contrainsted */
result = SIDPOL_CONSTRAINED;
}
return result;
}
/*
* Compute a decision for a transition from @src to @dst under the active
* policy.
*/
static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type)
{
enum sid_policy_type result = SIDPOL_DEFAULT;
struct setid_ruleset *pol;
rcu_read_lock();
if (new_type == UID)
pol = rcu_dereference(safesetid_setuid_rules);
else if (new_type == GID)
pol = rcu_dereference(safesetid_setgid_rules);
else { /* Should not reach here */
result = SIDPOL_CONSTRAINED;
rcu_read_unlock();
return result;
}
if (pol) {
pol->type = new_type;
result = _setid_policy_lookup(pol, src, dst);
}
rcu_read_unlock();
return result;
}
static int safesetid_security_capable(const struct cred *cred,
struct user_namespace *ns,
int cap,
unsigned int opts)
{
/* We're only interested in CAP_SETUID and CAP_SETGID. */
if (cap != CAP_SETUID && cap != CAP_SETGID)
return 0;
/*
* If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we
* want to let it go through here; the real security check happens later, in
* the task_fix_set{u/g}id or task_fix_setgroups hooks.
*/
if ((opts & CAP_OPT_INSETID) != 0)
return 0;
switch (cap) {
case CAP_SETUID:
/*
* If no policy applies to this task, allow the use of CAP_SETUID for
* other purposes.
*/
if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT)
return 0;
/*
* Reject use of CAP_SETUID for functionality other than calling
* set*uid() (e.g. setting up userns uid mappings).
*/
pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n",
__kuid_val(cred->uid));
return -EPERM;
case CAP_SETGID:
/*
* If no policy applies to this task, allow the use of CAP_SETGID for
* other purposes.
*/
if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
return 0;
/*
* Reject use of CAP_SETUID for functionality other than calling
* set*gid() (e.g. setting up userns gid mappings).
*/
pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n",
__kgid_val(cred->gid));
return -EPERM;
default:
/* Error, the only capabilities were checking for is CAP_SETUID/GID */
return 0;
}
return 0;
}
/*
* Check whether a caller with old credentials @old is allowed to switch to
* credentials that contain @new_id.
*/
static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type)
{
bool permitted;
/* If our old creds already had this ID in it, it's fine. */
if (new_type == UID) {
if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) ||
uid_eq(new_id.uid, old->suid))
return true;
} else if (new_type == GID){
if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) ||
gid_eq(new_id.gid, old->sgid))
return true;
} else /* Error, new_type is an invalid type */
return false;
/*
* Transitions to new UIDs require a check against the policy of the old
* RUID.
*/
permitted =
setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED;
if (!permitted) {
if (new_type == UID) {
pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n",
__kuid_val(old->uid), __kuid_val(old->euid),
__kuid_val(old->suid), __kuid_val(new_id.uid));
} else if (new_type == GID) {
pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n",
__kgid_val(old->gid), __kgid_val(old->egid),
__kgid_val(old->sgid), __kgid_val(new_id.gid));
} else /* Error, new_type is an invalid type */
return false;
}
return permitted;
}
/*
* Check whether there is either an exception for user under old cred struct to
* set*uid to user under new cred struct, or the UID transition is allowed (by
* Linux set*uid rules) even without CAP_SETUID.
*/
static int safesetid_task_fix_setuid(struct cred *new,
const struct cred *old,
int flags)
{
/* Do nothing if there are no setuid restrictions for our old RUID. */
if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT)
return 0;
if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) &&
id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) &&
id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) &&
id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID))
return 0;
/*
* Kill this process to avoid potential security vulnerabilities
* that could arise from a missing allowlist entry preventing a
* privileged process from dropping to a lesser-privileged one.
*/
force_sig(SIGKILL);
return -EACCES;
}
static int safesetid_task_fix_setgid(struct cred *new,
const struct cred *old,
int flags)
{
/* Do nothing if there are no setgid restrictions for our old RGID. */
if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
return 0;
if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) &&
id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) &&
id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) &&
id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID))
return 0;
/*
* Kill this process to avoid potential security vulnerabilities
* that could arise from a missing allowlist entry preventing a
* privileged process from dropping to a lesser-privileged one.
*/
force_sig(SIGKILL);
return -EACCES;
}
static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old)
{
int i;
/* Do nothing if there are no setgid restrictions for our old RGID. */
if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
return 0;
get_group_info(new->group_info);
for (i = 0; i < new->group_info->ngroups; i++) {
if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) {
put_group_info(new->group_info);
/*
* Kill this process to avoid potential security vulnerabilities
* that could arise from a missing allowlist entry preventing a
* privileged process from dropping to a lesser-privileged one.
*/
force_sig(SIGKILL);
return -EACCES;
}
}
put_group_info(new->group_info);
return 0;
}
static const struct lsm_id safesetid_lsmid = {
.name = "safesetid",
.id = LSM_ID_SAFESETID,
};
static struct security_hook_list safesetid_security_hooks[] = {
LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid),
LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid),
LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups),
LSM_HOOK_INIT(capable, safesetid_security_capable)
};
static int __init safesetid_security_init(void)
{
security_add_hooks(safesetid_security_hooks,
ARRAY_SIZE(safesetid_security_hooks),
&safesetid_lsmid);
/* Report that SafeSetID successfully initialized */
safesetid_initialized = 1;
return 0;
}
DEFINE_LSM(safesetid_security_init) = {
.init = safesetid_security_init,
.name = "safesetid",
};
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef LINUX_MM_INLINE_H
#define LINUX_MM_INLINE_H
#include <linux/atomic.h>
#include <linux/huge_mm.h>
#include <linux/mm_types.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/userfaultfd_k.h>
#include <linux/swapops.h>
/**
* folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
* @folio: The folio to test.
*
* We would like to get this info without a page flag, but the state
* needs to survive until the folio is last deleted from the LRU, which
* could be as far down as __page_cache_release.
*
* Return: An integer (not a boolean!) used to sort a folio onto the
* right LRU list and to account folios correctly.
* 1 if @folio is a regular filesystem backed page cache folio
* or a lazily freed anonymous folio (e.g. via MADV_FREE).
* 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
* ram or swap backed folio.
*/
static inline int folio_is_file_lru(struct folio *folio)
{
return !folio_test_swapbacked(folio);
}
static inline int page_is_file_lru(struct page *page)
{
return folio_is_file_lru(page_folio(page));
}
static __always_inline void __update_lru_size(struct lruvec *lruvec,
enum lru_list lru, enum zone_type zid,
long nr_pages)
{
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages);
__mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
__mod_zone_page_state(&pgdat->node_zones[zid],
NR_ZONE_LRU_BASE + lru, nr_pages);
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
enum lru_list lru, enum zone_type zid,
long nr_pages)
{
__update_lru_size(lruvec, lru, zid, nr_pages);
#ifdef CONFIG_MEMCG
mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
#endif
}
/**
* __folio_clear_lru_flags - Clear page lru flags before releasing a page.
* @folio: The folio that was on lru and now has a zero reference.
*/
static __always_inline void __folio_clear_lru_flags(struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio);
__folio_clear_lru(folio);
/* this shouldn't happen, so leave the flags to bad_page() */
if (folio_test_active(folio) && folio_test_unevictable(folio))
return;
__folio_clear_active(folio);
__folio_clear_unevictable(folio);
}
/**
* folio_lru_list - Which LRU list should a folio be on?
* @folio: The folio to test.
*
* Return: The LRU list a folio should be on, as an index
* into the array of LRU lists.
*/
static __always_inline enum lru_list folio_lru_list(struct folio *folio)
{
enum lru_list lru;
VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio))
return LRU_UNEVICTABLE;
lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio))
lru += LRU_ACTIVE;
return lru;
}
#ifdef CONFIG_LRU_GEN
#ifdef CONFIG_LRU_GEN_ENABLED
static inline bool lru_gen_enabled(void)
{
DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]);
return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]);
}
#else
static inline bool lru_gen_enabled(void)
{
DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]);
return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]);
}
#endif
static inline bool lru_gen_in_fault(void)
{
return current->in_lru_fault;
}
static inline int lru_gen_from_seq(unsigned long seq)
{
return seq % MAX_NR_GENS;
}
static inline int lru_hist_from_seq(unsigned long seq)
{
return seq % NR_HIST_GENS;
}
static inline int lru_tier_from_refs(int refs, bool workingset)
{
VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));
/* see the comment on MAX_NR_TIERS */
return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs);
}
static inline int folio_lru_refs(struct folio *folio)
{
unsigned long flags = READ_ONCE(folio->flags);
if (!(flags & BIT(PG_referenced)))
return 0;
/*
* Return the total number of accesses including PG_referenced. Also see
* the comment on LRU_REFS_FLAGS.
*/
return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1;
}
static inline int folio_lru_gen(struct folio *folio)
{
unsigned long flags = READ_ONCE(folio->flags);
return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
}
static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
{
unsigned long max_seq = lruvec->lrugen.max_seq;
VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
/* see the comment on MIN_NR_GENS */
return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1);
}
static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio,
int old_gen, int new_gen)
{ int type = folio_is_file_lru(folio);
int zone = folio_zonenum(folio);
int delta = folio_nr_pages(folio);
enum lru_list lru = type * LRU_INACTIVE_FILE;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS);
VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS);
VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1);
if (old_gen >= 0)
WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone],
lrugen->nr_pages[old_gen][type][zone] - delta);
if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone],
lrugen->nr_pages[new_gen][type][zone] + delta);
/* addition */
if (old_gen < 0) {
if (lru_gen_is_active(lruvec, new_gen))
lru += LRU_ACTIVE;
__update_lru_size(lruvec, lru, zone, delta);
return;
}
/* deletion */
if (new_gen < 0) {
if (lru_gen_is_active(lruvec, old_gen))
lru += LRU_ACTIVE;
__update_lru_size(lruvec, lru, zone, -delta);
return;
}
/* promotion */
if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
}
/* demotion requires isolation, e.g., lru_deactivate_fn() */
VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
}
static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio,
bool reclaiming)
{
int gen;
int type = folio_is_file_lru(folio);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
/*
* +-----------------------------------+-----------------------------------+
* | Accessed through page tables and | Accessed through file descriptors |
* | promoted by folio_update_gen() | and protected by folio_inc_gen() |
* +-----------------------------------+-----------------------------------+
* | PG_active (set while isolated) | |
* +-----------------+-----------------+-----------------+-----------------+
* | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS |
* +-----------------------------------+-----------------------------------+
* |<---------- MIN_NR_GENS ---------->| |
* |<---------------------------- MAX_NR_GENS ---------------------------->|
*/
if (folio_test_active(folio))
gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming)
gen = MAX_NR_GENS;
else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio))))
gen = MIN_NR_GENS;
else
gen = MAX_NR_GENS - folio_test_workingset(folio);
return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
}
static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
unsigned long seq;
unsigned long flags;
int gen = folio_lru_gen(folio);
int type = folio_is_file_lru(folio);
int zone = folio_zonenum(folio);
struct lru_gen_folio *lrugen = &lruvec->lrugen;
VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled)
return false;
seq = lru_gen_folio_seq(lruvec, folio, reclaiming);
gen = lru_gen_from_seq(seq);
flags = (gen + 1UL) << LRU_GEN_PGOFF;
/* see the comment on MIN_NR_GENS about PG_active */
set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);
lru_gen_update_size(lruvec, folio, -1, gen);
/* for folio_rotate_reclaimable() */
if (reclaiming)
list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
else
list_add(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;
}
static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
unsigned long flags;
int gen = folio_lru_gen(folio);
if (gen < 0)
return false;
VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
/* for folio_migrate_flags() */
flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags);
gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
lru_gen_update_size(lruvec, folio, gen, -1);
list_del(&folio->lru);
return true;
}
static inline void folio_migrate_refs(struct folio *new, struct folio *old)
{
unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK;
set_mask_bits(&new->flags, LRU_REFS_MASK, refs);
}
#else /* !CONFIG_LRU_GEN */
static inline bool lru_gen_enabled(void)
{
return false;
}
static inline bool lru_gen_in_fault(void)
{
return false;
}
static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
return false;
}
static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
return false;
}
static inline void folio_migrate_refs(struct folio *new, struct folio *old)
{
}
#endif /* CONFIG_LRU_GEN */
static __always_inline
void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
{
enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false))
return;
update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]);
}
static __always_inline
void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
{
enum lru_list lru = folio_lru_list(folio);
if (lru_gen_add_folio(lruvec, folio, true))
return;
update_lru_size(lruvec, lru, folio_zonenum(folio),
folio_nr_pages(folio));
/* This is not expected to be used on LRU_UNEVICTABLE */
list_add_tail(&folio->lru, &lruvec->lists[lru]);
}
static __always_inline
void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
{
enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false))
return;
if (lru != LRU_UNEVICTABLE)
list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio));
}
#ifdef CONFIG_ANON_VMA_NAME
/* mmap_lock should be read-locked */
static inline void anon_vma_name_get(struct anon_vma_name *anon_name)
{
if (anon_name)
kref_get(&anon_name->kref);
}
static inline void anon_vma_name_put(struct anon_vma_name *anon_name)
{
if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free);
}
static inline
struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name)
{
/* Prevent anon_name refcount saturation early on */
if (kref_read(&anon_name->kref) < REFCOUNT_MAX) {
anon_vma_name_get(anon_name);
return anon_name;
}
return anon_vma_name_alloc(anon_name->name);
}
static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
struct vm_area_struct *new_vma)
{
struct anon_vma_name *anon_name = anon_vma_name(orig_vma);
if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name);
}
static inline void free_anon_vma_name(struct vm_area_struct *vma)
{
/*
* Not using anon_vma_name because it generates a warning if mmap_lock
* is not held, which might be the case here.
*/
anon_vma_name_put(vma->anon_name);
}
static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
struct anon_vma_name *anon_name2)
{
if (anon_name1 == anon_name2)
return true;
return anon_name1 && anon_name2 &&
!strcmp(anon_name1->name, anon_name2->name);
}
#else /* CONFIG_ANON_VMA_NAME */
static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {}
static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {}
static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
struct vm_area_struct *new_vma) {}
static inline void free_anon_vma_name(struct vm_area_struct *vma) {}
static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
struct anon_vma_name *anon_name2)
{
return true;
}
#endif /* CONFIG_ANON_VMA_NAME */
static inline void init_tlb_flush_pending(struct mm_struct *mm)
{
atomic_set(&mm->tlb_flush_pending, 0);
}
static inline void inc_tlb_flush_pending(struct mm_struct *mm)
{
atomic_inc(&mm->tlb_flush_pending);
/*
* The only time this value is relevant is when there are indeed pages
* to flush. And we'll only flush pages after changing them, which
* requires the PTL.
*
* So the ordering here is:
*
* atomic_inc(&mm->tlb_flush_pending);
* spin_lock(&ptl);
* ...
* set_pte_at();
* spin_unlock(&ptl);
*
* spin_lock(&ptl)
* mm_tlb_flush_pending();
* ....
* spin_unlock(&ptl);
*
* flush_tlb_range();
* atomic_dec(&mm->tlb_flush_pending);
*
* Where the increment if constrained by the PTL unlock, it thus
* ensures that the increment is visible if the PTE modification is
* visible. After all, if there is no PTE modification, nobody cares
* about TLB flushes either.
*
* This very much relies on users (mm_tlb_flush_pending() and
* mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
* therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
* locks (PPC) the unlock of one doesn't order against the lock of
* another PTL.
*
* The decrement is ordered by the flush_tlb_range(), such that
* mm_tlb_flush_pending() will not return false unless all flushes have
* completed.
*/
}
static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
/*
* See inc_tlb_flush_pending().
*
* This cannot be smp_mb__before_atomic() because smp_mb() simply does
* not order against TLB invalidate completion, which is what we need.
*
* Therefore we must rely on tlb_flush_*() to guarantee order.
*/
atomic_dec(&mm->tlb_flush_pending);
}
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
/*
* Must be called after having acquired the PTL; orders against that
* PTLs release and therefore ensures that if we observe the modified
* PTE we must also observe the increment from inc_tlb_flush_pending().
*
* That is, it only guarantees to return true if there is a flush
* pending for _this_ PTL.
*/
return atomic_read(&mm->tlb_flush_pending);
}
static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
{
/*
* Similar to mm_tlb_flush_pending(), we must have acquired the PTL
* for which there is a TLB flush pending in order to guarantee
* we've seen both that PTE modification and the increment.
*
* (no requirement on actually still holding the PTL, that is irrelevant)
*/
return atomic_read(&mm->tlb_flush_pending) > 1;
}
#ifdef CONFIG_MMU
/*
* Computes the pte marker to copy from the given source entry into dst_vma.
* If no marker should be copied, returns 0.
* The caller should insert a new pte created with make_pte_marker().
*/
static inline pte_marker copy_pte_marker(
swp_entry_t entry, struct vm_area_struct *dst_vma)
{
pte_marker srcm = pte_marker_get(entry);
/* Always copy error entries. */
pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD);
/* Only copy PTE markers if UFFD register matches. */
if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma))
dstm |= PTE_MARKER_UFFD_WP;
return dstm;
}
#endif
/*
* If this pte is wr-protected by uffd-wp in any form, arm the special pte to
* replace a none pte. NOTE! This should only be called when *pte is already
* cleared so we will never accidentally replace something valuable. Meanwhile
* none pte also means we are not demoting the pte so tlb flushed is not needed.
* E.g., when pte cleared the caller should have taken care of the tlb flush.
*
* Must be called with pgtable lock held so that no thread will see the none
* pte, and if they see it, they'll fault and serialize at the pgtable lock.
*
* Returns true if an uffd-wp pte was installed, false otherwise.
*/
static inline bool
pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
pte_t *pte, pte_t pteval)
{
#ifdef CONFIG_PTE_MARKER_UFFD_WP
bool arm_uffd_pte = false;
/* The current status of the pte should be "cleared" before calling */
WARN_ON_ONCE(!pte_none(ptep_get(pte)));
/*
* NOTE: userfaultfd_wp_unpopulated() doesn't need this whole
* thing, because when zapping either it means it's dropping the
* page, or in TTU where the present pte will be quickly replaced
* with a swap pte. There's no way of leaking the bit.
*/
if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
return false;
/* A uffd-wp wr-protected normal pte */
if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
arm_uffd_pte = true;
/*
* A uffd-wp wr-protected swap pte. Note: this should even cover an
* existing pte marker with uffd-wp bit set.
*/
if (unlikely(pte_swp_uffd_wp_any(pteval)))
arm_uffd_pte = true;
if (unlikely(arm_uffd_pte)) {
set_pte_at(vma->vm_mm, addr, pte,
make_pte_marker(PTE_MARKER_UFFD_WP));
return true;
}
#endif
return false;
}
static inline bool vma_has_recency(struct vm_area_struct *vma)
{
if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
return false;
if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE))
return false;
return true;
}
#endif
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef __KVM_MM_H__
#define __KVM_MM_H__ 1
/*
* Architectures can choose whether to use an rwlock or spinlock
* for the mmu_lock. These macros, for use in common code
* only, avoids using #ifdefs in places that must deal with
* multiple architectures.
*/
#ifdef KVM_HAVE_MMU_RWLOCK
#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock)
#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock)
#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock)
#else
#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock)
#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock)
#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
#endif /* KVM_HAVE_MMU_RWLOCK */
struct kvm_follow_pfn {
const struct kvm_memory_slot *slot;
const gfn_t gfn;
unsigned long hva;
/* FOLL_* flags modifying lookup behavior, e.g. FOLL_WRITE. */
unsigned int flags;
/*
* Pin the page (effectively FOLL_PIN, which is an mm/ internal flag).
* The page *must* be pinned if KVM will write to the page via a kernel
* mapping, e.g. via kmap(), mremap(), etc.
*/
bool pin;
/*
* If non-NULL, try to get a writable mapping even for a read fault.
* Set to true if a writable mapping was obtained.
*/
bool *map_writable;
/*
* Optional output. Set to a valid "struct page" if the returned pfn
* is for a refcounted or pinned struct page, NULL if the returned pfn
* has no struct page or if the struct page is not being refcounted
* (e.g. tail pages of non-compound higher order allocations from
* IO/PFNMAP mappings).
*/
struct page **refcounted_page;
};
kvm_pfn_t hva_to_pfn(struct kvm_follow_pfn *kfp);
#ifdef CONFIG_HAVE_KVM_PFNCACHE
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
unsigned long start,
unsigned long end);
#else
static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
unsigned long start,
unsigned long end)
{
}
#endif /* HAVE_KVM_PFNCACHE */
#ifdef CONFIG_KVM_PRIVATE_MEM
void kvm_gmem_init(struct module *module);
int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned int fd, loff_t offset);
void kvm_gmem_unbind(struct kvm_memory_slot *slot);
#else
static inline void kvm_gmem_init(struct module *module)
{
}
static inline int kvm_gmem_bind(struct kvm *kvm,
struct kvm_memory_slot *slot,
unsigned int fd, loff_t offset)
{
WARN_ON_ONCE(1);
return -EIO;
}
static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
{
WARN_ON_ONCE(1);
}
#endif /* CONFIG_KVM_PRIVATE_MEM */
#endif /* __KVM_MM_H__ */
// SPDX-License-Identifier: GPL-2.0
/*
* inode.c - part of debugfs, a tiny little debug file system
*
* Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (C) 2004 IBM Inc.
* Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org>
*
* debugfs is for people to use instead of /proc or /sys.
* See ./Documentation/core-api/kernel-api.rst for more details.
*/
#define pr_fmt(fmt) "debugfs: " fmt
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/namei.h>
#include <linux/debugfs.h>
#include <linux/fsnotify.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/security.h>
#include "internal.h"
#define DEBUGFS_DEFAULT_MODE 0700
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS;
/*
* Don't allow access attributes to be changed whilst the kernel is locked down
* so that we can use the file mode as part of a heuristic to determine whether
* to lock down individual files.
*/
static int debugfs_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *ia)
{
int ret;
if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) {
ret = security_locked_down(LOCKDOWN_DEBUGFS);
if (ret)
return ret;
}
return simple_setattr(&nop_mnt_idmap, dentry, ia);
}
static const struct inode_operations debugfs_file_inode_operations = {
.setattr = debugfs_setattr,
};
static const struct inode_operations debugfs_dir_inode_operations = {
.lookup = simple_lookup,
.setattr = debugfs_setattr,
};
static const struct inode_operations debugfs_symlink_inode_operations = {
.get_link = simple_get_link,
.setattr = debugfs_setattr,
};
static struct inode *debugfs_get_inode(struct super_block *sb)
{
struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
simple_inode_init_ts(inode);
}
return inode;
}
struct debugfs_fs_info {
kuid_t uid;
kgid_t gid;
umode_t mode;
/* Opt_* bitfield. */
unsigned int opts;
};
enum {
Opt_uid,
Opt_gid,
Opt_mode,
Opt_source,
};
static const struct fs_parameter_spec debugfs_param_specs[] = {
fsparam_gid ("gid", Opt_gid),
fsparam_u32oct ("mode", Opt_mode),
fsparam_uid ("uid", Opt_uid),
fsparam_string ("source", Opt_source),
{}
};
static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct debugfs_fs_info *opts = fc->s_fs_info;
struct fs_parse_result result;
int opt;
opt = fs_parse(fc, debugfs_param_specs, param, &result);
if (opt < 0) {
/*
* We might like to report bad mount options here; but
* traditionally debugfs has ignored all mount options
*/
if (opt == -ENOPARAM)
return 0;
return opt;
}
switch (opt) {
case Opt_uid:
opts->uid = result.uid;
break;
case Opt_gid:
opts->gid = result.gid;
break;
case Opt_mode:
opts->mode = result.uint_32 & S_IALLUGO;
break;
case Opt_source:
if (fc->source)
return invalfc(fc, "Multiple sources specified");
fc->source = param->string;
param->string = NULL;
break;
/*
* We might like to report bad mount options here;
* but traditionally debugfs has ignored all mount options
*/
}
opts->opts |= BIT(opt);
return 0;
}
static void _debugfs_apply_options(struct super_block *sb, bool remount)
{
struct debugfs_fs_info *fsi = sb->s_fs_info;
struct inode *inode = d_inode(sb->s_root);
/*
* On remount, only reset mode/uid/gid if they were provided as mount
* options.
*/
if (!remount || fsi->opts & BIT(Opt_mode)) {
inode->i_mode &= ~S_IALLUGO;
inode->i_mode |= fsi->mode;
}
if (!remount || fsi->opts & BIT(Opt_uid))
inode->i_uid = fsi->uid;
if (!remount || fsi->opts & BIT(Opt_gid))
inode->i_gid = fsi->gid;
}
static void debugfs_apply_options(struct super_block *sb)
{
_debugfs_apply_options(sb, false);
}
static void debugfs_apply_options_remount(struct super_block *sb)
{
_debugfs_apply_options(sb, true);
}
static int debugfs_reconfigure(struct fs_context *fc)
{
struct super_block *sb = fc->root->d_sb;
struct debugfs_fs_info *sb_opts = sb->s_fs_info;
struct debugfs_fs_info *new_opts = fc->s_fs_info;
sync_filesystem(sb);
/* structure copy of new mount options to sb */
*sb_opts = *new_opts;
debugfs_apply_options_remount(sb);
return 0;
}
static int debugfs_show_options(struct seq_file *m, struct dentry *root)
{
struct debugfs_fs_info *fsi = root->d_sb->s_fs_info;
if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
from_kuid_munged(&init_user_ns, fsi->uid));
if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, fsi->gid));
if (fsi->mode != DEBUGFS_DEFAULT_MODE)
seq_printf(m, ",mode=%o", fsi->mode);
return 0;
}
static struct kmem_cache *debugfs_inode_cachep __ro_after_init;
static void init_once(void *foo)
{
struct debugfs_inode_info *info = foo;
inode_init_once(&info->vfs_inode);
}
static struct inode *debugfs_alloc_inode(struct super_block *sb)
{
struct debugfs_inode_info *info;
info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL);
if (!info)
return NULL;
return &info->vfs_inode;
}
static void debugfs_free_inode(struct inode *inode)
{
if (S_ISLNK(inode->i_mode))
kfree(inode->i_link);
kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode));
}
static const struct super_operations debugfs_super_operations = {
.statfs = simple_statfs,
.show_options = debugfs_show_options,
.alloc_inode = debugfs_alloc_inode,
.free_inode = debugfs_free_inode,
};
static void debugfs_release_dentry(struct dentry *dentry)
{
struct debugfs_fsdata *fsd = dentry->d_fsdata;
if (fsd) { WARN_ON(!list_empty(&fsd->cancellations));
mutex_destroy(&fsd->cancellations_mtx);
}
kfree(fsd);
}
static struct vfsmount *debugfs_automount(struct path *path)
{
struct inode *inode = path->dentry->d_inode;
return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private);
}
static const struct dentry_operations debugfs_dops = {
.d_delete = always_delete_dentry,
.d_release = debugfs_release_dentry,
.d_automount = debugfs_automount,
};
static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
static const struct tree_descr debug_files[] = {{""}};
int err;
err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
if (err)
return err;
sb->s_op = &debugfs_super_operations;
sb->s_d_op = &debugfs_dops;
debugfs_apply_options(sb);
return 0;
}
static int debugfs_get_tree(struct fs_context *fc)
{
if (!(debugfs_allow & DEBUGFS_ALLOW_API))
return -EPERM;
return get_tree_single(fc, debugfs_fill_super);
}
static void debugfs_free_fc(struct fs_context *fc)
{
kfree(fc->s_fs_info);
}
static const struct fs_context_operations debugfs_context_ops = {
.free = debugfs_free_fc,
.parse_param = debugfs_parse_param,
.get_tree = debugfs_get_tree,
.reconfigure = debugfs_reconfigure,
};
static int debugfs_init_fs_context(struct fs_context *fc)
{
struct debugfs_fs_info *fsi;
fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
if (!fsi)
return -ENOMEM;
fsi->mode = DEBUGFS_DEFAULT_MODE;
fc->s_fs_info = fsi;
fc->ops = &debugfs_context_ops;
return 0;
}
static struct file_system_type debug_fs_type = {
.owner = THIS_MODULE,
.name = "debugfs",
.init_fs_context = debugfs_init_fs_context,
.parameters = debugfs_param_specs,
.kill_sb = kill_litter_super,
};
MODULE_ALIAS_FS("debugfs");
/**
* debugfs_lookup() - look up an existing debugfs file
* @name: a pointer to a string containing the name of the file to look up.
* @parent: a pointer to the parent dentry of the file.
*
* This function will return a pointer to a dentry if it succeeds. If the file
* doesn't exist or an error occurs, %NULL will be returned. The returned
* dentry must be passed to dput() when it is no longer needed.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
{
struct dentry *dentry;
if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent))
return NULL;
if (!parent) parent = debugfs_mount->mnt_root;
dentry = lookup_positive_unlocked(name, parent, strlen(name));
if (IS_ERR(dentry))
return NULL;
return dentry;
}
EXPORT_SYMBOL_GPL(debugfs_lookup);
static struct dentry *start_creating(const char *name, struct dentry *parent)
{
struct dentry *dentry;
int error;
if (!(debugfs_allow & DEBUGFS_ALLOW_API))
return ERR_PTR(-EPERM);
if (!debugfs_initialized())
return ERR_PTR(-ENOENT);
pr_debug("creating file '%s'\n", name); if (IS_ERR(parent))
return parent;
error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
&debugfs_mount_count);
if (error) {
pr_err("Unable to pin filesystem for file '%s'\n", name);
return ERR_PTR(error);
}
/* If the parent is not specified, we create it in the root.
* We need the root dentry to do this, which is in the super
* block. A pointer to that is in the struct vfsmount that we
* have around.
*/
if (!parent) parent = debugfs_mount->mnt_root;
inode_lock(d_inode(parent));
if (unlikely(IS_DEADDIR(d_inode(parent))))
dentry = ERR_PTR(-ENOENT);
else
dentry = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry))
pr_err("Directory '%s' with parent '%s' already present!\n",
name, parent->d_name.name);
else
pr_err("File '%s' in directory '%s' already present!\n",
name, parent->d_name.name);
dput(dentry);
dentry = ERR_PTR(-EEXIST);
}
if (IS_ERR(dentry)) {
inode_unlock(d_inode(parent));
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
return dentry;
}
static struct dentry *failed_creating(struct dentry *dentry)
{
inode_unlock(d_inode(dentry->d_parent));
dput(dentry);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
return ERR_PTR(-ENOMEM);
}
static struct dentry *end_creating(struct dentry *dentry)
{
inode_unlock(d_inode(dentry->d_parent));
return dentry;
}
static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
const void *aux,
const struct file_operations *proxy_fops,
const void *real_fops)
{
struct dentry *dentry;
struct inode *inode;
if (!(mode & S_IFMT))
mode |= S_IFREG;
BUG_ON(!S_ISREG(mode));
dentry = start_creating(name, parent);
if (IS_ERR(dentry))
return dentry;
if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
failed_creating(dentry);
return ERR_PTR(-EPERM);
}
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode)) {
pr_err("out of free dentries, can not create file '%s'\n",
name);
return failed_creating(dentry);
}
inode->i_mode = mode;
inode->i_private = data;
inode->i_op = &debugfs_file_inode_operations;
if (!real_fops)
proxy_fops = &debugfs_noop_file_operations;
inode->i_fop = proxy_fops;
DEBUGFS_I(inode)->raw = real_fops;
DEBUGFS_I(inode)->aux = aux;
d_instantiate(dentry, inode);
fsnotify_create(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
struct dentry *debugfs_create_file_full(const char *name, umode_t mode,
struct dentry *parent, void *data,
const void *aux,
const struct file_operations *fops)
{
return __debugfs_create_file(name, mode, parent, data, aux,
&debugfs_full_proxy_file_operations,
fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_file_full);
struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
struct dentry *parent, void *data,
const void *aux,
const struct debugfs_short_fops *fops)
{
return __debugfs_create_file(name, mode, parent, data, aux,
&debugfs_full_short_proxy_file_operations,
fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_file_short);
/**
* debugfs_create_file_unsafe - create a file in the debugfs filesystem
* @name: a pointer to a string containing the name of the file to create.
* @mode: the permission that the file should have.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* file will be created in the root of the debugfs filesystem.
* @data: a pointer to something that the caller will want to get to later
* on. The inode.i_private pointer will point to this value on
* the open() call.
* @fops: a pointer to a struct file_operations that should be used for
* this file.
*
* debugfs_create_file_unsafe() is completely analogous to
* debugfs_create_file(), the only difference being that the fops
* handed it will not get protected against file removals by the
* debugfs core.
*
* It is your responsibility to protect your struct file_operation
* methods against file removals by means of debugfs_file_get()
* and debugfs_file_put(). ->open() is still protected by
* debugfs though.
*
* Any struct file_operations defined by means of
* DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and
* thus, may be used here.
*/
struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops)
{
return __debugfs_create_file(name, mode, parent, data, NULL,
&debugfs_open_proxy_file_operations,
fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
/**
* debugfs_create_file_size - create a file in the debugfs filesystem
* @name: a pointer to a string containing the name of the file to create.
* @mode: the permission that the file should have.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* file will be created in the root of the debugfs filesystem.
* @data: a pointer to something that the caller will want to get to later
* on. The inode.i_private pointer will point to this value on
* the open() call.
* @fops: a pointer to a struct file_operations that should be used for
* this file.
* @file_size: initial file size
*
* This is the basic "create a file" function for debugfs. It allows for a
* wide range of flexibility in creating a file, or a directory (if you want
* to create a directory, the debugfs_create_dir() function is
* recommended to be used instead.)
*/
void debugfs_create_file_size(const char *name, umode_t mode,
struct dentry *parent, void *data,
const struct file_operations *fops,
loff_t file_size)
{
struct dentry *de = debugfs_create_file(name, mode, parent, data, fops);
if (!IS_ERR(de))
d_inode(de)->i_size = file_size;
}
EXPORT_SYMBOL_GPL(debugfs_create_file_size);
/**
* debugfs_create_dir - create a directory in the debugfs filesystem
* @name: a pointer to a string containing the name of the directory to
* create.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* directory will be created in the root of the debugfs filesystem.
*
* This function creates a directory in debugfs with the given name.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
* you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*
* NOTE: it's expected that most callers should _ignore_ the errors returned
* by this function. Other debugfs functions handle the fact that the "dentry"
* passed to them could be an error and they don't crash in that case.
* Drivers should generally work fine even if debugfs fails to init anyway.
*/
struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
{
struct dentry *dentry = start_creating(name, parent);
struct inode *inode;
if (IS_ERR(dentry))
return dentry;
if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
failed_creating(dentry);
return ERR_PTR(-EPERM);
}
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode)) {
pr_err("out of free dentries, can not create directory '%s'\n",
name);
return failed_creating(dentry);
}
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
inode->i_op = &debugfs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
d_instantiate(dentry, inode);
inc_nlink(d_inode(dentry->d_parent));
fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
EXPORT_SYMBOL_GPL(debugfs_create_dir);
/**
* debugfs_create_automount - create automount point in the debugfs filesystem
* @name: a pointer to a string containing the name of the file to create.
* @parent: a pointer to the parent dentry for this file. This should be a
* directory dentry if set. If this parameter is NULL, then the
* file will be created in the root of the debugfs filesystem.
* @f: function to be called when pathname resolution steps on that one.
* @data: opaque argument to pass to f().
*
* @f should return what ->d_automount() would.
*/
struct dentry *debugfs_create_automount(const char *name,
struct dentry *parent,
debugfs_automount_t f,
void *data)
{
struct dentry *dentry = start_creating(name, parent);
struct inode *inode;
if (IS_ERR(dentry))
return dentry;
if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
failed_creating(dentry);
return ERR_PTR(-EPERM);
}
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode)) {
pr_err("out of free dentries, can not create automount '%s'\n",
name);
return failed_creating(dentry);
}
make_empty_dir_inode(inode);
inode->i_flags |= S_AUTOMOUNT;
inode->i_private = data;
DEBUGFS_I(inode)->automount = f;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
d_instantiate(dentry, inode);
inc_nlink(d_inode(dentry->d_parent));
fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
return end_creating(dentry);
}
EXPORT_SYMBOL(debugfs_create_automount);
/**
* debugfs_create_symlink- create a symbolic link in the debugfs filesystem
* @name: a pointer to a string containing the name of the symbolic link to
* create.
* @parent: a pointer to the parent dentry for this symbolic link. This
* should be a directory dentry if set. If this parameter is NULL,
* then the symbolic link will be created in the root of the debugfs
* filesystem.
* @target: a pointer to a string containing the path to the target of the
* symbolic link.
*
* This function creates a symbolic link with the given name in debugfs that
* links to the given target path.
*
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the symbolic
* link is to be removed (no automatic cleanup happens if your module is
* unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR)
* will be returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
const char *target)
{
struct dentry *dentry;
struct inode *inode;
char *link = kstrdup(target, GFP_KERNEL);
if (!link)
return ERR_PTR(-ENOMEM);
dentry = start_creating(name, parent);
if (IS_ERR(dentry)) {
kfree(link);
return dentry;
}
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode)) {
pr_err("out of free dentries, can not create symlink '%s'\n",
name);
kfree(link);
return failed_creating(dentry);
}
inode->i_mode = S_IFLNK | S_IRWXUGO;
inode->i_op = &debugfs_symlink_inode_operations;
inode->i_link = link;
d_instantiate(dentry, inode);
return end_creating(dentry);
}
EXPORT_SYMBOL_GPL(debugfs_create_symlink);
static void __debugfs_file_removed(struct dentry *dentry)
{
struct debugfs_fsdata *fsd;
/*
* Paired with the closing smp_mb() implied by a successful
* cmpxchg() in debugfs_file_get(): either
* debugfs_file_get() must see a dead dentry or we must see a
* debugfs_fsdata instance at ->d_fsdata here (or both).
*/
smp_mb();
fsd = READ_ONCE(dentry->d_fsdata);
if (!fsd)
return;
/* if this was the last reference, we're done */
if (refcount_dec_and_test(&fsd->active_users))
return;
/*
* If there's still a reference, the code that obtained it can
* be in different states:
* - The common case of not using cancellations, or already
* after debugfs_leave_cancellation(), where we just need
* to wait for debugfs_file_put() which signals the completion;
* - inside a cancellation section, i.e. between
* debugfs_enter_cancellation() and debugfs_leave_cancellation(),
* in which case we need to trigger the ->cancel() function,
* and then wait for debugfs_file_put() just like in the
* previous case;
* - before debugfs_enter_cancellation() (but obviously after
* debugfs_file_get()), in which case we may not see the
* cancellation in the list on the first round of the loop,
* but debugfs_enter_cancellation() signals the completion
* after adding it, so this code gets woken up to call the
* ->cancel() function.
*/
while (refcount_read(&fsd->active_users)) {
struct debugfs_cancellation *c;
/*
* Lock the cancellations. Note that the cancellations
* structs are meant to be on the stack, so we need to
* ensure we either use them here or don't touch them,
* and debugfs_leave_cancellation() will wait for this
* to be finished processing before exiting one. It may
* of course win and remove the cancellation, but then
* chances are we never even got into this bit, we only
* do if the refcount isn't zero already.
*/
mutex_lock(&fsd->cancellations_mtx);
while ((c = list_first_entry_or_null(&fsd->cancellations,
typeof(*c), list))) {
list_del_init(&c->list);
c->cancel(dentry, c->cancel_data);
}
mutex_unlock(&fsd->cancellations_mtx);
wait_for_completion(&fsd->active_users_drained);
}
}
static void remove_one(struct dentry *victim)
{ if (d_is_reg(victim)) __debugfs_file_removed(victim);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
/**
* debugfs_remove - recursively removes a directory
* @dentry: a pointer to a the dentry of the directory to be removed. If this
* parameter is NULL or an error value, nothing will be done.
*
* This function recursively removes a directory tree in debugfs that
* was previously created with a call to another debugfs function
* (like debugfs_create_file() or variants thereof.)
*
* This function is required to be called in order for the file to be
* removed, no automatic cleanup of files will happen when a module is
* removed, you are responsible here.
*/
void debugfs_remove(struct dentry *dentry)
{ if (IS_ERR_OR_NULL(dentry))
return;
simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count);
simple_recursive_removal(dentry, remove_one);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
EXPORT_SYMBOL_GPL(debugfs_remove);
/**
* debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
* @name: a pointer to a string containing the name of the item to look up.
* @parent: a pointer to the parent dentry of the item.
*
* This is the equlivant of doing something like
* debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
* handled for the directory being looked up.
*/
void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
{
struct dentry *dentry;
dentry = debugfs_lookup(name, parent);
if (!dentry)
return;
debugfs_remove(dentry);
dput(dentry);
}
EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
/**
* debugfs_change_name - rename a file/directory in the debugfs filesystem
* @dentry: dentry of an object to be renamed.
* @fmt: format for new name
*
* This function renames a file/directory in debugfs. The target must not
* exist for rename to succeed.
*
* This function will return 0 on success and -E... on failure.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
*/
int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...)
{
int error = 0;
const char *new_name;
struct name_snapshot old_name;
struct dentry *parent, *target;
struct inode *dir;
va_list ap;
if (IS_ERR_OR_NULL(dentry))
return 0;
va_start(ap, fmt);
new_name = kvasprintf_const(GFP_KERNEL, fmt, ap);
va_end(ap);
if (!new_name)
return -ENOMEM;
parent = dget_parent(dentry);
dir = d_inode(parent);
inode_lock(dir);
take_dentry_name_snapshot(&old_name, dentry);
if (WARN_ON_ONCE(dentry->d_parent != parent)) {
error = -EINVAL;
goto out;
}
if (strcmp(old_name.name.name, new_name) == 0)
goto out;
target = lookup_one_len(new_name, parent, strlen(new_name));
if (IS_ERR(target)) {
error = PTR_ERR(target);
goto out;
}
if (d_really_is_positive(target)) {
dput(target);
error = -EINVAL;
goto out;
}
simple_rename_timestamp(dir, dentry, dir, target);
d_move(dentry, target);
dput(target);
fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry);
out:
release_dentry_name_snapshot(&old_name);
inode_unlock(dir);
dput(parent);
kfree_const(new_name);
return error;
}
EXPORT_SYMBOL_GPL(debugfs_change_name);
/**
* debugfs_initialized - Tells whether debugfs has been registered
*/
bool debugfs_initialized(void)
{
return debugfs_registered;
}
EXPORT_SYMBOL_GPL(debugfs_initialized);
static int __init debugfs_kernel(char *str)
{
if (str) {
if (!strcmp(str, "on"))
debugfs_allow = DEBUGFS_ALLOW_API | DEBUGFS_ALLOW_MOUNT;
else if (!strcmp(str, "no-mount"))
debugfs_allow = DEBUGFS_ALLOW_API;
else if (!strcmp(str, "off"))
debugfs_allow = 0;
}
return 0;
}
early_param("debugfs", debugfs_kernel);
static int __init debugfs_init(void)
{
int retval;
if (!(debugfs_allow & DEBUGFS_ALLOW_MOUNT))
return -EPERM;
retval = sysfs_create_mount_point(kernel_kobj, "debug");
if (retval)
return retval;
debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache",
sizeof(struct debugfs_inode_info), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
init_once);
if (debugfs_inode_cachep == NULL) {
sysfs_remove_mount_point(kernel_kobj, "debug");
return -ENOMEM;
}
retval = register_filesystem(&debug_fs_type);
if (retval) { // Really not going to happen
sysfs_remove_mount_point(kernel_kobj, "debug");
kmem_cache_destroy(debugfs_inode_cachep);
return retval;
}
debugfs_registered = true;
return 0;
}
core_initcall(debugfs_init);
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/buffer.c
*
* Copyright (C) 1991, 1992, 2002 Linus Torvalds
*/
/*
* Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95
*
* Removed a lot of unnecessary code and simplified things now that
* the buffer cache isn't our primary cache - Andrew Tridgell 12/96
*
* Speed up hash, lru, and free list operations. Use gfp() for allocating
* hash table, use SLAB cache for buffer heads. SMP threading. -DaveM
*
* Added 32k buffer block sizes - these are required older ARM systems. - RMK
*
* async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de>
*/
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
#include <linux/buffer_head.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/bio.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <trace/events/block.h>
#include <linux/fscrypt.h>
#include <linux/fsverity.h>
#include <linux/sched/isolation.h>
#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
enum rw_hint hint, struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
inline void touch_buffer(struct buffer_head *bh)
{
trace_block_touch_buffer(bh);
folio_mark_accessed(bh->b_folio);
}
EXPORT_SYMBOL(touch_buffer);
void __lock_buffer(struct buffer_head *bh)
{
wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);
void unlock_buffer(struct buffer_head *bh)
{
clear_bit_unlock(BH_Lock, &bh->b_state);
smp_mb__after_atomic();
wake_up_bit(&bh->b_state, BH_Lock);
}
EXPORT_SYMBOL(unlock_buffer);
/*
* Returns if the folio has dirty or writeback buffers. If all the buffers
* are unlocked and clean then the folio_test_dirty information is stale. If
* any of the buffers are locked, it is assumed they are locked for IO.
*/
void buffer_check_dirty_writeback(struct folio *folio,
bool *dirty, bool *writeback)
{
struct buffer_head *head, *bh;
*dirty = false;
*writeback = false;
BUG_ON(!folio_test_locked(folio));
head = folio_buffers(folio);
if (!head)
return;
if (folio_test_writeback(folio))
*writeback = true;
bh = head;
do {
if (buffer_locked(bh))
*writeback = true;
if (buffer_dirty(bh))
*dirty = true;
bh = bh->b_this_page;
} while (bh != head);
}
/*
* Block until a buffer comes unlocked. This doesn't stop it
* from becoming locked again - you have to lock it yourself
* if you want to preserve its state.
*/
void __wait_on_buffer(struct buffer_head * bh)
{
wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);
static void buffer_io_error(struct buffer_head *bh, char *msg)
{
if (!test_bit(BH_Quiet, &bh->b_state))
printk_ratelimited(KERN_ERR
"Buffer I/O error on dev %pg, logical block %llu%s\n",
bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
}
/*
* End-of-IO handler helper function which does not touch the bh after
* unlocking it.
* Note: unlock_buffer() sort-of does touch the bh after unlocking it, but
* a race there is benign: unlock_buffer() only use the bh's address for
* hashing after unlocking the buffer, so it doesn't actually touch the bh
* itself.
*/
static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
{
if (uptodate) {
set_buffer_uptodate(bh);
} else {
/* This happens, due to failed read-ahead attempts. */
clear_buffer_uptodate(bh);
}
unlock_buffer(bh);
}
/*
* Default synchronous end-of-IO handler.. Just mark it up-to-date and
* unlock the buffer.
*/
void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
{
__end_buffer_read_notouch(bh, uptodate);
put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_read_sync);
void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
if (uptodate) {
set_buffer_uptodate(bh);
} else {
buffer_io_error(bh, ", lost sync page write");
mark_buffer_write_io_error(bh);
clear_buffer_uptodate(bh);
}
unlock_buffer(bh);
put_bh(bh);
}
EXPORT_SYMBOL(end_buffer_write_sync);
static struct buffer_head *
__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic)
{
struct address_space *bd_mapping = bdev->bd_mapping;
const int blkbits = bd_mapping->host->i_blkbits;
struct buffer_head *ret = NULL;
pgoff_t index;
struct buffer_head *bh;
struct buffer_head *head;
struct folio *folio;
int all_mapped = 1;
static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
index = ((loff_t)block << blkbits) / PAGE_SIZE;
folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0);
if (IS_ERR(folio))
goto out;
/*
* Folio lock protects the buffers. Callers that cannot block
* will fallback to serializing vs try_to_free_buffers() via
* the i_private_lock.
*/
if (atomic)
spin_lock(&bd_mapping->i_private_lock);
else
folio_lock(folio);
head = folio_buffers(folio);
if (!head)
goto out_unlock;
/*
* Upon a noref migration, the folio lock serializes here;
* otherwise bail.
*/
if (test_bit_acquire(BH_Migrate, &head->b_state)) {
WARN_ON(!atomic);
goto out_unlock;
}
bh = head;
do {
if (!buffer_mapped(bh))
all_mapped = 0;
else if (bh->b_blocknr == block) {
ret = bh;
get_bh(bh);
goto out_unlock;
}
bh = bh->b_this_page;
} while (bh != head);
/* we might be here because some of the buffers on this page are
* not mapped. This is due to various races between
* file io on the block device and getblk. It gets dealt with
* elsewhere, don't buffer_error if we had some unmapped buffers
*/
ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
if (all_mapped && __ratelimit(&last_warned)) {
printk("__find_get_block_slow() failed. block=%llu, "
"b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
"device %pg blocksize: %d\n",
(unsigned long long)block,
(unsigned long long)bh->b_blocknr,
bh->b_state, bh->b_size, bdev,
1 << blkbits);
}
out_unlock:
if (atomic)
spin_unlock(&bd_mapping->i_private_lock);
else
folio_unlock(folio);
folio_put(folio);
out:
return ret;
}
static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
{
unsigned long flags;
struct buffer_head *first;
struct buffer_head *tmp;
struct folio *folio;
int folio_uptodate = 1;
BUG_ON(!buffer_async_read(bh));
folio = bh->b_folio;
if (uptodate) {
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
buffer_io_error(bh, ", async page read");
}
/*
* Be _very_ careful from here on. Bad things can happen if
* two buffer heads end IO at almost the same time and both
* decide that the page is now completely done.
*/
first = folio_buffers(folio);
spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
do {
if (!buffer_uptodate(tmp))
folio_uptodate = 0;
if (buffer_async_read(tmp)) {
BUG_ON(!buffer_locked(tmp));
goto still_busy;
}
tmp = tmp->b_this_page;
} while (tmp != bh);
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
folio_end_read(folio, folio_uptodate);
return;
still_busy:
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
struct postprocess_bh_ctx {
struct work_struct work;
struct buffer_head *bh;
};
static void verify_bh(struct work_struct *work)
{
struct postprocess_bh_ctx *ctx =
container_of(work, struct postprocess_bh_ctx, work);
struct buffer_head *bh = ctx->bh;
bool valid;
valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh));
end_buffer_async_read(bh, valid);
kfree(ctx);
}
static bool need_fsverity(struct buffer_head *bh)
{
struct folio *folio = bh->b_folio;
struct inode *inode = folio->mapping->host;
return fsverity_active(inode) &&
/* needed by ext4 */
folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}
static void decrypt_bh(struct work_struct *work)
{
struct postprocess_bh_ctx *ctx =
container_of(work, struct postprocess_bh_ctx, work);
struct buffer_head *bh = ctx->bh;
int err;
err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size,
bh_offset(bh));
if (err == 0 && need_fsverity(bh)) {
/*
* We use different work queues for decryption and for verity
* because verity may require reading metadata pages that need
* decryption, and we shouldn't recurse to the same workqueue.
*/
INIT_WORK(&ctx->work, verify_bh);
fsverity_enqueue_verify_work(&ctx->work);
return;
}
end_buffer_async_read(bh, err == 0);
kfree(ctx);
}
/*
* I/O completion handler for block_read_full_folio() - pages
* which come unlocked at the end of I/O.
*/
static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
{
struct inode *inode = bh->b_folio->mapping->host;
bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode);
bool verify = need_fsverity(bh);
/* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */
if (uptodate && (decrypt || verify)) {
struct postprocess_bh_ctx *ctx =
kmalloc(sizeof(*ctx), GFP_ATOMIC);
if (ctx) {
ctx->bh = bh;
if (decrypt) {
INIT_WORK(&ctx->work, decrypt_bh);
fscrypt_enqueue_decrypt_work(&ctx->work);
} else {
INIT_WORK(&ctx->work, verify_bh);
fsverity_enqueue_verify_work(&ctx->work);
}
return;
}
uptodate = 0;
}
end_buffer_async_read(bh, uptodate);
}
/*
* Completion handler for block_write_full_folio() - folios which are unlocked
* during I/O, and which have the writeback flag cleared upon I/O completion.
*/
static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
unsigned long flags;
struct buffer_head *first;
struct buffer_head *tmp;
struct folio *folio;
BUG_ON(!buffer_async_write(bh));
folio = bh->b_folio;
if (uptodate) {
set_buffer_uptodate(bh);
} else {
buffer_io_error(bh, ", lost async page write");
mark_buffer_write_io_error(bh);
clear_buffer_uptodate(bh);
}
first = folio_buffers(folio);
spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_write(bh);
unlock_buffer(bh);
tmp = bh->b_this_page;
while (tmp != bh) {
if (buffer_async_write(tmp)) {
BUG_ON(!buffer_locked(tmp));
goto still_busy;
}
tmp = tmp->b_this_page;
}
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
folio_end_writeback(folio);
return;
still_busy:
spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
/*
* If a page's buffers are under async readin (end_buffer_async_read
* completion) then there is a possibility that another thread of
* control could lock one of the buffers after it has completed
* but while some of the other buffers have not completed. This
* locked buffer would confuse end_buffer_async_read() into not unlocking
* the page. So the absence of BH_Async_Read tells end_buffer_async_read()
* that this buffer is not under async I/O.
*
* The page comes unlocked when it has no locked buffer_async buffers
* left.
*
* PageLocked prevents anyone starting new async I/O reads any of
* the buffers.
*
* PageWriteback is used to prevent simultaneous writeout of the same
* page.
*
* PageLocked prevents anyone from starting writeback of a page which is
* under read I/O (PageWriteback is only ever set against a locked page).
*/
static void mark_buffer_async_read(struct buffer_head *bh)
{
bh->b_end_io = end_buffer_async_read_io;
set_buffer_async_read(bh);
}
static void mark_buffer_async_write_endio(struct buffer_head *bh,
bh_end_io_t *handler)
{
bh->b_end_io = handler;
set_buffer_async_write(bh);
}
void mark_buffer_async_write(struct buffer_head *bh)
{
mark_buffer_async_write_endio(bh, end_buffer_async_write);
}
EXPORT_SYMBOL(mark_buffer_async_write);
/*
* fs/buffer.c contains helper functions for buffer-backed address space's
* fsync functions. A common requirement for buffer-based filesystems is
* that certain data from the backing blockdev needs to be written out for
* a successful fsync(). For example, ext2 indirect blocks need to be
* written back and waited upon before fsync() returns.
*
* The functions mark_buffer_dirty_inode(), fsync_inode_buffers(),
* inode_has_buffers() and invalidate_inode_buffers() are provided for the
* management of a list of dependent buffers at ->i_mapping->i_private_list.
*
* Locking is a little subtle: try_to_free_buffers() will remove buffers
* from their controlling inode's queue when they are being freed. But
* try_to_free_buffers() will be operating against the *blockdev* mapping
* at the time, not against the S_ISREG file which depends on those buffers.
* So the locking for i_private_list is via the i_private_lock in the address_space
* which backs the buffers. Which is different from the address_space
* against which the buffers are listed. So for a particular address_space,
* mapping->i_private_lock does *not* protect mapping->i_private_list! In fact,
* mapping->i_private_list will always be protected by the backing blockdev's
* ->i_private_lock.
*
* Which introduces a requirement: all buffers on an address_space's
* ->i_private_list must be from the same address_space: the blockdev's.
*
* address_spaces which do not place buffers at ->i_private_list via these
* utility functions are free to use i_private_lock and i_private_list for
* whatever they want. The only requirement is that list_empty(i_private_list)
* be true at clear_inode() time.
*
* FIXME: clear_inode should not call invalidate_inode_buffers(). The
* filesystems should do that. invalidate_inode_buffers() should just go
* BUG_ON(!list_empty).
*
* FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should
* take an address_space, not an inode. And it should be called
* mark_buffer_dirty_fsync() to clearly define why those buffers are being
* queued up.
*
* FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the
* list if it is already on a list. Because if the buffer is on a list,
* it *must* already be on the right one. If not, the filesystem is being
* silly. This will save a ton of locking. But first we have to ensure
* that buffers are taken *off* the old inode's list when they are freed
* (presumably in truncate). That requires careful auditing of all
* filesystems (do it inside bforget()). It could also be done by bringing
* b_inode back.
*/
/*
* The buffer's backing address_space's i_private_lock must be held
*/
static void __remove_assoc_queue(struct buffer_head *bh)
{
list_del_init(&bh->b_assoc_buffers);
WARN_ON(!bh->b_assoc_map);
bh->b_assoc_map = NULL;
}
int inode_has_buffers(struct inode *inode)
{
return !list_empty(&inode->i_data.i_private_list);
}
/*
* osync is designed to support O_SYNC io. It waits synchronously for
* all already-submitted IO to complete, but does not queue any new
* writes to the disk.
*
* To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer
* as you dirty the buffers, and then use osync_inode_buffers to wait for
* completion. Any other dirty buffers which are not yet queued for
* write will not be flushed to disk by the osync.
*/
static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
{
struct buffer_head *bh;
struct list_head *p;
int err = 0;
spin_lock(lock);
repeat:
list_for_each_prev(p, list) {
bh = BH_ENTRY(p);
if (buffer_locked(bh)) {
get_bh(bh);
spin_unlock(lock);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
err = -EIO;
brelse(bh);
spin_lock(lock);
goto repeat;
}
}
spin_unlock(lock);
return err;
}
/**
* sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
* @mapping: the mapping which wants those buffers written
*
* Starts I/O against the buffers at mapping->i_private_list, and waits upon
* that I/O.
*
* Basically, this is a convenience function for fsync().
* @mapping is a file or directory which needs those buffers to be written for
* a successful fsync().
*/
int sync_mapping_buffers(struct address_space *mapping)
{
struct address_space *buffer_mapping = mapping->i_private_data;
if (buffer_mapping == NULL || list_empty(&mapping->i_private_list))
return 0;
return fsync_buffers_list(&buffer_mapping->i_private_lock,
&mapping->i_private_list);
}
EXPORT_SYMBOL(sync_mapping_buffers);
/**
* generic_buffers_fsync_noflush - generic buffer fsync implementation
* for simple filesystems with no inode lock
*
* @file: file to synchronize
* @start: start offset in bytes
* @end: end offset in bytes (inclusive)
* @datasync: only synchronize essential metadata if true
*
* This is a generic implementation of the fsync method for simple
* filesystems which track all non-inode metadata in the buffers list
* hanging off the address_space structure.
*/
int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
bool datasync)
{
struct inode *inode = file->f_mapping->host;
int err;
int ret;
err = file_write_and_wait_range(file, start, end);
if (err)
return err;
ret = sync_mapping_buffers(inode->i_mapping);
if (!(inode->i_state & I_DIRTY_ALL))
goto out;
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
goto out;
err = sync_inode_metadata(inode, 1);
if (ret == 0)
ret = err;
out:
/* check and advance again to catch errors after syncing out buffers */
err = file_check_and_advance_wb_err(file);
if (ret == 0)
ret = err;
return ret;
}
EXPORT_SYMBOL(generic_buffers_fsync_noflush);
/**
* generic_buffers_fsync - generic buffer fsync implementation
* for simple filesystems with no inode lock
*
* @file: file to synchronize
* @start: start offset in bytes
* @end: end offset in bytes (inclusive)
* @datasync: only synchronize essential metadata if true
*
* This is a generic implementation of the fsync method for simple
* filesystems which track all non-inode metadata in the buffers list
* hanging off the address_space structure. This also makes sure that
* a device cache flush operation is called at the end.
*/
int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
bool datasync)
{
struct inode *inode = file->f_mapping->host;
int ret;
ret = generic_buffers_fsync_noflush(file, start, end, datasync);
if (!ret)
ret = blkdev_issue_flush(inode->i_sb->s_bdev);
return ret;
}
EXPORT_SYMBOL(generic_buffers_fsync);
/*
* Called when we've recently written block `bblock', and it is known that
* `bblock' was for a buffer_boundary() buffer. This means that the block at
* `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's
* dirty, schedule it for IO. So that indirects merge nicely with their data.
*/
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize)
{
struct buffer_head *bh;
bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
write_dirty_buffer(bh, 0);
put_bh(bh);
}
}
void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
{
struct address_space *mapping = inode->i_mapping;
struct address_space *buffer_mapping = bh->b_folio->mapping;
mark_buffer_dirty(bh);
if (!mapping->i_private_data) {
mapping->i_private_data = buffer_mapping;
} else {
BUG_ON(mapping->i_private_data != buffer_mapping);
}
if (!bh->b_assoc_map) {
spin_lock(&buffer_mapping->i_private_lock);
list_move_tail(&bh->b_assoc_buffers,
&mapping->i_private_list);
bh->b_assoc_map = mapping;
spin_unlock(&buffer_mapping->i_private_lock);
}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);
/**
* block_dirty_folio - Mark a folio as dirty.
* @mapping: The address space containing this folio.
* @folio: The folio to mark dirty.
*
* Filesystems which use buffer_heads can use this function as their
* ->dirty_folio implementation. Some filesystems need to do a little
* work before calling this function. Filesystems which do not use
* buffer_heads should call filemap_dirty_folio() instead.
*
* If the folio has buffers, the uptodate buffers are set dirty, to
* preserve dirty-state coherency between the folio and the buffers.
* Buffers added to a dirty folio are created dirty.
*
* The buffers are dirtied before the folio is dirtied. There's a small
* race window in which writeback may see the folio cleanness but not the
* buffer dirtiness. That's fine. If this code were to set the folio
* dirty before the buffers, writeback could clear the folio dirty flag,
* see a bunch of clean buffers and we'd end up with dirty buffers/clean
* folio on the dirty folio list.
*
* We use i_private_lock to lock against try_to_free_buffers() while
* using the folio's buffer list. This also prevents clean buffers
* being added to the folio after it was set dirty.
*
* Context: May only be called from process context. Does not sleep.
* Caller must ensure that @folio cannot be truncated during this call,
* typically by holding the folio lock or having a page in the folio
* mapped and holding the page table lock.
*
* Return: True if the folio was dirtied; false if it was already dirtied.
*/
bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
{
struct buffer_head *head;
bool newly_dirty;
spin_lock(&mapping->i_private_lock);
head = folio_buffers(folio);
if (head) {
struct buffer_head *bh = head;
do {
set_buffer_dirty(bh);
bh = bh->b_this_page;
} while (bh != head);
}
/*
* Lock out page's memcg migration to keep PageDirty
* synchronized with per-memcg dirty page counters.
*/
newly_dirty = !folio_test_set_dirty(folio);
spin_unlock(&mapping->i_private_lock);
if (newly_dirty)
__folio_mark_dirty(folio, mapping, 1);
if (newly_dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
return newly_dirty;
}
EXPORT_SYMBOL(block_dirty_folio);
/*
* Write out and wait upon a list of buffers.
*
* We have conflicting pressures: we want to make sure that all
* initially dirty buffers get waited on, but that any subsequently
* dirtied buffers don't. After all, we don't want fsync to last
* forever if somebody is actively writing to the file.
*
* Do this in two main stages: first we copy dirty buffers to a
* temporary inode list, queueing the writes as we go. Then we clean
* up, waiting for those writes to complete.
*
* During this second stage, any subsequent updates to the file may end
* up refiling the buffer on the original inode's dirty list again, so
* there is a chance we will end up with a buffer queued for write but
* not yet completed on that list. So, as a final cleanup we go through
* the osync code to catch these locked, dirty buffers without requeuing
* any newly dirty buffers for write.
*/
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
{
struct buffer_head *bh;
struct address_space *mapping;
int err = 0, err2;
struct blk_plug plug;
LIST_HEAD(tmp);
blk_start_plug(&plug);
spin_lock(lock);
while (!list_empty(list)) {
bh = BH_ENTRY(list->next);
mapping = bh->b_assoc_map;
__remove_assoc_queue(bh);
/* Avoid race with mark_buffer_dirty_inode() which does
* a lockless check and we rely on seeing the dirty bit */
smp_mb();
if (buffer_dirty(bh) || buffer_locked(bh)) {
list_add(&bh->b_assoc_buffers, &tmp);
bh->b_assoc_map = mapping;
if (buffer_dirty(bh)) {
get_bh(bh);
spin_unlock(lock);
/*
* Ensure any pending I/O completes so that
* write_dirty_buffer() actually writes the
* current contents - it is a noop if I/O is
* still in flight on potentially older
* contents.
*/
write_dirty_buffer(bh, REQ_SYNC);
/*
* Kick off IO for the previous mapping. Note
* that we will not run the very last mapping,
* wait_on_buffer() will do that for us
* through sync_buffer().
*/
brelse(bh);
spin_lock(lock);
}
}
}
spin_unlock(lock);
blk_finish_plug(&plug);
spin_lock(lock);
while (!list_empty(&tmp)) {
bh = BH_ENTRY(tmp.prev);
get_bh(bh);
mapping = bh->b_assoc_map;
__remove_assoc_queue(bh);
/* Avoid race with mark_buffer_dirty_inode() which does
* a lockless check and we rely on seeing the dirty bit */
smp_mb();
if (buffer_dirty(bh)) {
list_add(&bh->b_assoc_buffers,
&mapping->i_private_list);
bh->b_assoc_map = mapping;
}
spin_unlock(lock);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
err = -EIO;
brelse(bh);
spin_lock(lock);
}
spin_unlock(lock);
err2 = osync_buffers_list(lock, list);
if (err)
return err;
else
return err2;
}
/*
* Invalidate any and all dirty buffers on a given inode. We are
* probably unmounting the fs, but that doesn't mean we have already
* done a sync(). Just drop the buffers from the inode list.
*
* NOTE: we take the inode's blockdev's mapping's i_private_lock. Which
* assumes that all the buffers are against the blockdev.
*/
void invalidate_inode_buffers(struct inode *inode)
{
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
struct list_head *list = &mapping->i_private_list;
struct address_space *buffer_mapping = mapping->i_private_data;
spin_lock(&buffer_mapping->i_private_lock);
while (!list_empty(list))
__remove_assoc_queue(BH_ENTRY(list->next));
spin_unlock(&buffer_mapping->i_private_lock);
}
}
EXPORT_SYMBOL(invalidate_inode_buffers);
/*
* Remove any clean buffers from the inode's buffer list. This is called
* when we're trying to free the inode itself. Those buffers can pin it.
*
* Returns true if all buffers were removed.
*/
int remove_inode_buffers(struct inode *inode)
{
int ret = 1;
if (inode_has_buffers(inode)) {
struct address_space *mapping = &inode->i_data;
struct list_head *list = &mapping->i_private_list;
struct address_space *buffer_mapping = mapping->i_private_data;
spin_lock(&buffer_mapping->i_private_lock);
while (!list_empty(list)) {
struct buffer_head *bh = BH_ENTRY(list->next);
if (buffer_dirty(bh)) {
ret = 0;
break;
}
__remove_assoc_queue(bh);
}
spin_unlock(&buffer_mapping->i_private_lock);
}
return ret;
}
/*
* Create the appropriate buffers when given a folio for data area and
* the size of each buffer.. Use the bh->b_this_page linked list to
* follow the buffers created. Return NULL if unable to create more
* buffers.
*
* The retry flag is used to differentiate async IO (paging, swapping)
* which may not fail from ordinary buffer allocations.
*/
struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
gfp_t gfp)
{
struct buffer_head *bh, *head;
long offset;
struct mem_cgroup *memcg, *old_memcg;
/* The folio lock pins the memcg */
memcg = folio_memcg(folio);
old_memcg = set_active_memcg(memcg);
head = NULL;
offset = folio_size(folio);
while ((offset -= size) >= 0) {
bh = alloc_buffer_head(gfp);
if (!bh)
goto no_grow;
bh->b_this_page = head;
bh->b_blocknr = -1;
head = bh;
bh->b_size = size;
/* Link the buffer to its folio */
folio_set_bh(bh, folio, offset);
}
out:
set_active_memcg(old_memcg);
return head;
/*
* In case anything failed, we just free everything we got.
*/
no_grow:
if (head) {
do {
bh = head;
head = head->b_this_page;
free_buffer_head(bh);
} while (head);
}
goto out;
}
EXPORT_SYMBOL_GPL(folio_alloc_buffers);
struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size)
{
gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
return folio_alloc_buffers(page_folio(page), size, gfp);
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);
static inline void link_dev_buffers(struct folio *folio,
struct buffer_head *head)
{
struct buffer_head *bh, *tail;
bh = head;
do {
tail = bh;
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
folio_attach_private(folio, head);
}
static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
{
sector_t retval = ~((sector_t)0);
loff_t sz = bdev_nr_bytes(bdev);
if (sz) {
unsigned int sizebits = blksize_bits(size);
retval = (sz >> sizebits);
}
return retval;
}
/*
* Initialise the state of a blockdev folio's buffers.
*/
static sector_t folio_init_buffers(struct folio *folio,
struct block_device *bdev, unsigned size)
{
struct buffer_head *head = folio_buffers(folio);
struct buffer_head *bh = head;
bool uptodate = folio_test_uptodate(folio);
sector_t block = div_u64(folio_pos(folio), size);
sector_t end_block = blkdev_max_block(bdev, size);
do {
if (!buffer_mapped(bh)) {
bh->b_end_io = NULL;
bh->b_private = NULL;
bh->b_bdev = bdev;
bh->b_blocknr = block;
if (uptodate)
set_buffer_uptodate(bh);
if (block < end_block)
set_buffer_mapped(bh);
}
block++;
bh = bh->b_this_page;
} while (bh != head);
/*
* Caller needs to validate requested block against end of device.
*/
return end_block;
}
/*
* Create the page-cache folio that contains the requested block.
*
* This is used purely for blockdev mappings.
*
* Returns false if we have a failure which cannot be cured by retrying
* without sleeping. Returns true if we succeeded, or the caller should retry.
*/
static bool grow_dev_folio(struct block_device *bdev, sector_t block,
pgoff_t index, unsigned size, gfp_t gfp)
{
struct address_space *mapping = bdev->bd_mapping;
struct folio *folio;
struct buffer_head *bh;
sector_t end_block = 0;
folio = __filemap_get_folio(mapping, index,
FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
if (IS_ERR(folio))
return false;
bh = folio_buffers(folio);
if (bh) {
if (bh->b_size == size) {
end_block = folio_init_buffers(folio, bdev, size);
goto unlock;
}
/*
* Retrying may succeed; for example the folio may finish
* writeback, or buffers may be cleaned. This should not
* happen very often; maybe we have old buffers attached to
* this blockdev's page cache and we're trying to change
* the block size?
*/
if (!try_to_free_buffers(folio)) {
end_block = ~0ULL;
goto unlock;
}
}
bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT);
if (!bh)
goto unlock;
/*
* Link the folio to the buffers and initialise them. Take the
* lock to be atomic wrt __find_get_block(), which does not
* run under the folio lock.
*/
spin_lock(&mapping->i_private_lock);
link_dev_buffers(folio, bh);
end_block = folio_init_buffers(folio, bdev, size);
spin_unlock(&mapping->i_private_lock);
unlock:
folio_unlock(folio);
folio_put(folio);
return block < end_block;
}
/*
* Create buffers for the specified block device block's folio. If
* that folio was dirty, the buffers are set dirty also. Returns false
* if we've hit a permanent error.
*/
static bool grow_buffers(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
loff_t pos;
/*
* Check for a block which lies outside our maximum possible
* pagecache index.
*/
if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) {
printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n",
__func__, (unsigned long long)block,
bdev);
return false;
}
/* Create a folio with the proper size buffers */
return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp);
}
static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
/* Size must be multiple of hard sectorsize */
if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
printk(KERN_ERR "getblk(): invalid block size %d requested\n",
size);
printk(KERN_ERR "logical block size: %d\n",
bdev_logical_block_size(bdev));
dump_stack();
return NULL;
}
for (;;) {
struct buffer_head *bh;
bh = __find_get_block(bdev, block, size);
if (bh)
return bh;
if (!grow_buffers(bdev, block, size, gfp))
return NULL;
}
}
/*
* The relationship between dirty buffers and dirty pages:
*
* Whenever a page has any dirty buffers, the page's dirty bit is set, and
* the page is tagged dirty in the page cache.
*
* At all times, the dirtiness of the buffers represents the dirtiness of
* subsections of the page. If the page has buffers, the page dirty bit is
* merely a hint about the true dirty state.
*
* When a page is set dirty in its entirety, all its buffers are marked dirty
* (if the page has buffers).
*
* When a buffer is marked dirty, its page is dirtied, but the page's other
* buffers are not.
*
* Also. When blockdev buffers are explicitly read with bread(), they
* individually become uptodate. But their backing page remains not
* uptodate - even if all of its buffers are uptodate. A subsequent
* block_read_full_folio() against that folio will discover all the uptodate
* buffers, will set the folio uptodate and will perform no I/O.
*/
/**
* mark_buffer_dirty - mark a buffer_head as needing writeout
* @bh: the buffer_head to mark dirty
*
* mark_buffer_dirty() will set the dirty bit against the buffer, then set
* its backing page dirty, then tag the page as dirty in the page cache
* and then attach the address_space's inode to its superblock's dirty
* inode list.
*
* mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock,
* i_pages lock and mapping->host->i_lock.
*/
void mark_buffer_dirty(struct buffer_head *bh)
{
WARN_ON_ONCE(!buffer_uptodate(bh));
trace_block_dirty_buffer(bh);
/*
* Very *carefully* optimize the it-is-already-dirty case.
*
* Don't let the final "is it dirty" escape to before we
* perhaps modified the buffer.
*/
if (buffer_dirty(bh)) {
smp_mb();
if (buffer_dirty(bh))
return;
}
if (!test_set_buffer_dirty(bh)) {
struct folio *folio = bh->b_folio;
struct address_space *mapping = NULL;
if (!folio_test_set_dirty(folio)) {
mapping = folio->mapping;
if (mapping)
__folio_mark_dirty(folio, mapping, 0);
}
if (mapping)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
}
EXPORT_SYMBOL(mark_buffer_dirty);
void mark_buffer_write_io_error(struct buffer_head *bh)
{
set_buffer_write_io_error(bh);
/* FIXME: do we need to set this in both places? */
if (bh->b_folio && bh->b_folio->mapping)
mapping_set_error(bh->b_folio->mapping, -EIO);
if (bh->b_assoc_map) {
mapping_set_error(bh->b_assoc_map, -EIO);
errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
}
}
EXPORT_SYMBOL(mark_buffer_write_io_error);
/**
* __brelse - Release a buffer.
* @bh: The buffer to release.
*
* This variant of brelse() can be called if @bh is guaranteed to not be NULL.
*/
void __brelse(struct buffer_head *bh)
{
if (atomic_read(&bh->b_count)) {
put_bh(bh);
return;
}
WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
EXPORT_SYMBOL(__brelse);
/**
* __bforget - Discard any dirty data in a buffer.
* @bh: The buffer to forget.
*
* This variant of bforget() can be called if @bh is guaranteed to not
* be NULL.
*/
void __bforget(struct buffer_head *bh)
{
clear_buffer_dirty(bh);
if (bh->b_assoc_map) {
struct address_space *buffer_mapping = bh->b_folio->mapping;
spin_lock(&buffer_mapping->i_private_lock);
list_del_init(&bh->b_assoc_buffers);
bh->b_assoc_map = NULL;
spin_unlock(&buffer_mapping->i_private_lock);
}
__brelse(bh);
}
EXPORT_SYMBOL(__bforget);
static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
return bh;
} else {
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
}
brelse(bh);
return NULL;
}
/*
* Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block().
* The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their
* refcount elevated by one when they're in an LRU. A buffer can only appear
* once in a particular CPU's LRU. A single buffer can be present in multiple
* CPU's LRUs at the same time.
*
* This is a transparent caching front-end to sb_bread(), sb_getblk() and
* sb_find_get_block().
*
* The LRUs themselves only need locking against invalidate_bh_lrus. We use
* a local interrupt disable for that.
*/
#define BH_LRU_SIZE 16
struct bh_lru {
struct buffer_head *bhs[BH_LRU_SIZE];
};
static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};
#ifdef CONFIG_SMP
#define bh_lru_lock() local_irq_disable()
#define bh_lru_unlock() local_irq_enable()
#else
#define bh_lru_lock() preempt_disable()
#define bh_lru_unlock() preempt_enable()
#endif
static inline void check_irqs_on(void)
{
#ifdef irqs_disabled
BUG_ON(irqs_disabled());
#endif
}
/*
* Install a buffer_head into this cpu's LRU. If not already in the LRU, it is
* inserted at the front, and the buffer_head at the back if any is evicted.
* Or, if already in the LRU it is moved to the front.
*/
static void bh_lru_install(struct buffer_head *bh)
{
struct buffer_head *evictee = bh;
struct bh_lru *b;
int i;
check_irqs_on();
bh_lru_lock();
/*
* the refcount of buffer_head in bh_lru prevents dropping the
* attached page(i.e., try_to_free_buffers) so it could cause
* failing page migration.
* Skip putting upcoming bh into bh_lru until migration is done.
*/
if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) {
bh_lru_unlock();
return;
}
b = this_cpu_ptr(&bh_lrus);
for (i = 0; i < BH_LRU_SIZE; i++) {
swap(evictee, b->bhs[i]);
if (evictee == bh) {
bh_lru_unlock();
return;
}
}
get_bh(bh);
bh_lru_unlock();
brelse(evictee);
}
/*
* Look up the bh in this cpu's LRU. If it's there, move it to the head.
*/
static struct buffer_head *
lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *ret = NULL;
unsigned int i;
check_irqs_on();
bh_lru_lock();
if (cpu_is_isolated(smp_processor_id())) {
bh_lru_unlock();
return NULL;
}
for (i = 0; i < BH_LRU_SIZE; i++) {
struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
bh->b_size == size) {
if (i) {
while (i) {
__this_cpu_write(bh_lrus.bhs[i],
__this_cpu_read(bh_lrus.bhs[i - 1]));
i--;
}
__this_cpu_write(bh_lrus.bhs[0], bh);
}
get_bh(bh);
ret = bh;
break;
}
}
bh_lru_unlock();
return ret;
}
/*
* Perform a pagecache lookup for the matching buffer. If it's there, refresh
* it in the LRU and mark it as accessed. If it is not present then return
* NULL. Atomic context callers may also return NULL if the buffer is being
* migrated; similarly the page is not marked accessed either.
*/
static struct buffer_head *
find_get_block_common(struct block_device *bdev, sector_t block,
unsigned size, bool atomic)
{
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
if (bh == NULL) {
/* __find_get_block_slow will mark the page accessed */
bh = __find_get_block_slow(bdev, block, atomic);
if (bh)
bh_lru_install(bh);
} else
touch_buffer(bh);
return bh;
}
struct buffer_head *
__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
{
return find_get_block_common(bdev, block, size, true);
}
EXPORT_SYMBOL(__find_get_block);
/* same as __find_get_block() but allows sleeping contexts */
struct buffer_head *
__find_get_block_nonatomic(struct block_device *bdev, sector_t block,
unsigned size)
{
return find_get_block_common(bdev, block, size, false);
}
EXPORT_SYMBOL(__find_get_block_nonatomic);
/**
* bdev_getblk - Get a buffer_head in a block device's buffer cache.
* @bdev: The block device.
* @block: The block number.
* @size: The size of buffer_heads for this @bdev.
* @gfp: The memory allocation flags to use.
*
* The returned buffer head has its reference count incremented, but is
* not locked. The caller should call brelse() when it has finished
* with the buffer. The buffer may not be uptodate. If needed, the
* caller can bring it uptodate either by reading it or overwriting it.
*
* Return: The buffer head, or NULL if memory could not be allocated.
*/
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
struct buffer_head *bh;
if (gfpflags_allow_blocking(gfp))
bh = __find_get_block_nonatomic(bdev, block, size);
else
bh = __find_get_block(bdev, block, size);
might_alloc(gfp);
if (bh)
return bh;
return __getblk_slow(bdev, block, size, gfp);
}
EXPORT_SYMBOL(bdev_getblk);
/*
* Do async read-ahead on a buffer..
*/
void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = bdev_getblk(bdev, block, size,
GFP_NOWAIT | __GFP_MOVABLE);
if (likely(bh)) {
bh_readahead(bh, REQ_RAHEAD);
brelse(bh);
}
}
EXPORT_SYMBOL(__breadahead);
/**
* __bread_gfp() - Read a block.
* @bdev: The block device to read from.
* @block: Block number in units of block size.
* @size: The block size of this device in bytes.
* @gfp: Not page allocation flags; see below.
*
* You are not expected to call this function. You should use one of
* sb_bread(), sb_bread_unmovable() or __bread().
*
* Read a specified block, and return the buffer head that refers to it.
* If @gfp is 0, the memory will be allocated using the block device's
* default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be
* allocated from a movable area. Do not pass in a complete set of
* GFP flags.
*
* The returned buffer head has its refcount increased. The caller should
* call brelse() when it has finished with the buffer.
*
* Context: May sleep waiting for I/O.
* Return: NULL if the block was unreadable.
*/
struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
struct buffer_head *bh;
gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
/*
* Prefer looping in the allocator rather than here, at least that
* code knows what it's doing.
*/
gfp |= __GFP_NOFAIL;
bh = bdev_getblk(bdev, block, size, gfp);
if (likely(bh) && !buffer_uptodate(bh))
bh = __bread_slow(bh);
return bh;
}
EXPORT_SYMBOL(__bread_gfp);
static void __invalidate_bh_lrus(struct bh_lru *b)
{
int i;
for (i = 0; i < BH_LRU_SIZE; i++) {
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
}
/*
* invalidate_bh_lrus() is called rarely - but not only at unmount.
* This doesn't race because it runs in each cpu either in irq
* or with preempt disabled.
*/
static void invalidate_bh_lru(void *arg)
{
struct bh_lru *b = &get_cpu_var(bh_lrus);
__invalidate_bh_lrus(b);
put_cpu_var(bh_lrus);
}
bool has_bh_in_lru(int cpu, void *dummy)
{
struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
int i;
for (i = 0; i < BH_LRU_SIZE; i++) {
if (b->bhs[i])
return true;
}
return false;
}
void invalidate_bh_lrus(void)
{
on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
/*
* It's called from workqueue context so we need a bh_lru_lock to close
* the race with preemption/irq.
*/
void invalidate_bh_lrus_cpu(void)
{
struct bh_lru *b;
bh_lru_lock();
b = this_cpu_ptr(&bh_lrus);
__invalidate_bh_lrus(b);
bh_lru_unlock();
}
void folio_set_bh(struct buffer_head *bh, struct folio *folio,
unsigned long offset)
{
bh->b_folio = folio;
BUG_ON(offset >= folio_size(folio));
if (folio_test_highmem(folio))
/*
* This catches illegal uses and preserves the offset:
*/
bh->b_data = (char *)(0 + offset);
else
bh->b_data = folio_address(folio) + offset;
}
EXPORT_SYMBOL(folio_set_bh);
/*
* Called when truncating a buffer on a page completely.
*/
/* Bits that are cleared during an invalidate */
#define BUFFER_FLAGS_DISCARD \
(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
1 << BH_Delay | 1 << BH_Unwritten)
static void discard_buffer(struct buffer_head * bh)
{
unsigned long b_state;
lock_buffer(bh);
clear_buffer_dirty(bh);
bh->b_bdev = NULL;
b_state = READ_ONCE(bh->b_state);
do {
} while (!try_cmpxchg(&bh->b_state, &b_state,
b_state & ~BUFFER_FLAGS_DISCARD));
unlock_buffer(bh);
}
/**
* block_invalidate_folio - Invalidate part or all of a buffer-backed folio.
* @folio: The folio which is affected.
* @offset: start of the range to invalidate
* @length: length of the range to invalidate
*
* block_invalidate_folio() is called when all or part of the folio has been
* invalidated by a truncate operation.
*
* block_invalidate_folio() does not have to release all buffers, but it must
* ensure that no dirty buffer is left outside @offset and that no I/O
* is underway against any of the blocks which are outside the truncation
* point. Because the caller is about to free (and possibly reuse) those
* blocks on-disk.
*/
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length)
{
struct buffer_head *head, *bh, *next;
size_t curr_off = 0;
size_t stop = length + offset;
BUG_ON(!folio_test_locked(folio));
/*
* Check for overflow
*/
BUG_ON(stop > folio_size(folio) || stop < length);
head = folio_buffers(folio);
if (!head)
return;
bh = head;
do {
size_t next_off = curr_off + bh->b_size;
next = bh->b_this_page;
/*
* Are we still fully in range ?
*/
if (next_off > stop)
goto out;
/*
* is this block fully invalidated?
*/
if (offset <= curr_off)
discard_buffer(bh);
curr_off = next_off;
bh = next;
} while (bh != head);
/*
* We release buffers only if the entire folio is being invalidated.
* The get_block cached value has been unconditionally invalidated,
* so real IO is not possible anymore.
*/
if (length == folio_size(folio))
filemap_release_folio(folio, 0);
out:
folio_clear_mappedtodisk(folio);
return;
}
EXPORT_SYMBOL(block_invalidate_folio);
/*
* We attach and possibly dirty the buffers atomically wrt
* block_dirty_folio() via i_private_lock. try_to_free_buffers
* is already excluded via the folio lock.
*/
struct buffer_head *create_empty_buffers(struct folio *folio,
unsigned long blocksize, unsigned long b_state)
{
struct buffer_head *bh, *head, *tail;
gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL;
head = folio_alloc_buffers(folio, blocksize, gfp);
bh = head;
do {
bh->b_state |= b_state;
tail = bh;
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
spin_lock(&folio->mapping->i_private_lock);
if (folio_test_uptodate(folio) || folio_test_dirty(folio)) {
bh = head;
do {
if (folio_test_dirty(folio))
set_buffer_dirty(bh);
if (folio_test_uptodate(folio))
set_buffer_uptodate(bh);
bh = bh->b_this_page;
} while (bh != head);
}
folio_attach_private(folio, head);
spin_unlock(&folio->mapping->i_private_lock);
return head;
}
EXPORT_SYMBOL(create_empty_buffers);
/**
* clean_bdev_aliases: clean a range of buffers in block device
* @bdev: Block device to clean buffers in
* @block: Start of a range of blocks to clean
* @len: Number of blocks to clean
*
* We are taking a range of blocks for data and we don't want writeback of any
* buffer-cache aliases starting from return from this function and until the
* moment when something will explicitly mark the buffer dirty (hopefully that
* will not happen until we will free that block ;-) We don't even need to mark
* it not-uptodate - nobody can expect anything from a newly allocated buffer
* anyway. We used to use unmap_buffer() for such invalidation, but that was
* wrong. We definitely don't want to mark the alias unmapped, for example - it
* would confuse anyone who might pick it with bread() afterwards...
*
* Also.. Note that bforget() doesn't lock the buffer. So there can be
* writeout I/O going on against recently-freed buffers. We don't wait on that
* I/O in bforget() - it's more efficient to wait on the I/O only if we really
* need to. That happens here.
*/
void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
{
struct address_space *bd_mapping = bdev->bd_mapping;
const int blkbits = bd_mapping->host->i_blkbits;
struct folio_batch fbatch;
pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE;
pgoff_t end;
int i, count;
struct buffer_head *bh;
struct buffer_head *head;
end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE;
folio_batch_init(&fbatch);
while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) {
count = folio_batch_count(&fbatch);
for (i = 0; i < count; i++) {
struct folio *folio = fbatch.folios[i];
if (!folio_buffers(folio))
continue;
/*
* We use folio lock instead of bd_mapping->i_private_lock
* to pin buffers here since we can afford to sleep and
* it scales better than a global spinlock lock.
*/
folio_lock(folio);
/* Recheck when the folio is locked which pins bhs */
head = folio_buffers(folio);
if (!head)
goto unlock_page;
bh = head;
do {
if (!buffer_mapped(bh) || (bh->b_blocknr < block))
goto next;
if (bh->b_blocknr >= block + len)
break;
clear_buffer_dirty(bh);
wait_on_buffer(bh);
clear_buffer_req(bh);
next:
bh = bh->b_this_page;
} while (bh != head);
unlock_page:
folio_unlock(folio);
}
folio_batch_release(&fbatch);
cond_resched();
/* End of range already reached? */
if (index > end || !index)
break;
}
}
EXPORT_SYMBOL(clean_bdev_aliases);
static struct buffer_head *folio_create_buffers(struct folio *folio,
struct inode *inode,
unsigned int b_state)
{
struct buffer_head *bh;
BUG_ON(!folio_test_locked(folio));
bh = folio_buffers(folio);
if (!bh)
bh = create_empty_buffers(folio,
1 << READ_ONCE(inode->i_blkbits), b_state);
return bh;
}
/*
* NOTE! All mapped/uptodate combinations are valid:
*
* Mapped Uptodate Meaning
*
* No No "unknown" - must do get_block()
* No Yes "hole" - zero-filled
* Yes No "allocated" - allocated on disk, not read in
* Yes Yes "valid" - allocated and up-to-date in memory.
*
* "Dirty" is valid only with the last case (mapped+uptodate).
*/
/*
* While block_write_full_folio is writing back the dirty buffers under
* the page lock, whoever dirtied the buffers may decide to clean them
* again at any time. We handle that by only looking at the buffer
* state inside lock_buffer().
*
* If block_write_full_folio() is called for regular writeback
* (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
* locked buffer. This only can happen if someone has written the buffer
* directly, with submit_bh(). At the address_space level PageWriteback
* prevents this contention from occurring.
*
* If block_write_full_folio() is called with wbc->sync_mode ==
* WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
* causes the writes to be flagged as synchronous writes.
*/
int __block_write_full_folio(struct inode *inode, struct folio *folio,
get_block_t *get_block, struct writeback_control *wbc)
{
int err;
sector_t block;
sector_t last_block;
struct buffer_head *bh, *head;
size_t blocksize;
int nr_underway = 0;
blk_opf_t write_flags = wbc_to_write_flags(wbc);
head = folio_create_buffers(folio, inode,
(1 << BH_Dirty) | (1 << BH_Uptodate));
/*
* Be very careful. We have no exclusion from block_dirty_folio
* here, and the (potentially unmapped) buffers may become dirty at
* any time. If a buffer becomes dirty here after we've inspected it
* then we just miss that fact, and the folio stays dirty.
*
* Buffers outside i_size may be dirtied by block_dirty_folio;
* handle that here by just cleaning them.
*/
bh = head;
blocksize = bh->b_size;
block = div_u64(folio_pos(folio), blocksize);
last_block = div_u64(i_size_read(inode) - 1, blocksize);
/*
* Get all the dirty buffers mapped to disk addresses and
* handle any aliases from the underlying blockdev's mapping.
*/
do {
if (block > last_block) {
/*
* mapped buffers outside i_size will occur, because
* this folio can be outside i_size when there is a
* truncate in progress.
*/
/*
* The buffer was zeroed by block_write_full_folio()
*/
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
buffer_dirty(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
goto recover;
clear_buffer_delay(bh);
if (buffer_new(bh)) {
/* blockdev mappings never come here */
clear_buffer_new(bh);
clean_bdev_bh_alias(bh);
}
}
bh = bh->b_this_page;
block++;
} while (bh != head);
do {
if (!buffer_mapped(bh))
continue;
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the folio. Note that this can
* potentially cause a busy-wait loop from writeback threads
* and kswapd activity, but those code paths have their own
* higher-level throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
folio_redirty_for_writepage(wbc, folio);
continue;
}
if (test_clear_buffer_dirty(bh)) {
mark_buffer_async_write_endio(bh,
end_buffer_async_write);
} else {
unlock_buffer(bh);
}
} while ((bh = bh->b_this_page) != head);
/*
* The folio and its buffers are protected by the writeback flag,
* so we can drop the bh refcounts early.
*/
BUG_ON(folio_test_writeback(folio));
folio_start_writeback(folio);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
inode->i_write_hint, wbc);
nr_underway++;
}
bh = next;
} while (bh != head);
folio_unlock(folio);
err = 0;
done:
if (nr_underway == 0) {
/*
* The folio was marked dirty, but the buffers were
* clean. Someone wrote them back by hand with
* write_dirty_buffer/submit_bh. A rare case.
*/
folio_end_writeback(folio);
/*
* The folio and buffer_heads can be released at any time from
* here on.
*/
}
return err;
recover:
/*
* ENOSPC, or some other error. We may already have added some
* blocks to the file, so we need to write these out to avoid
* exposing stale data.
* The folio is currently locked and not marked for writeback
*/
bh = head;
/* Recovery: lock and submit the mapped buffers */
do {
if (buffer_mapped(bh) && buffer_dirty(bh) &&
!buffer_delay(bh)) {
lock_buffer(bh);
mark_buffer_async_write_endio(bh,
end_buffer_async_write);
} else {
/*
* The buffer may have been set dirty during
* attachment to a dirty folio.
*/
clear_buffer_dirty(bh);
}
} while ((bh = bh->b_this_page) != head);
BUG_ON(folio_test_writeback(folio));
mapping_set_error(folio->mapping, err);
folio_start_writeback(folio);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
inode->i_write_hint, wbc);
nr_underway++;
}
bh = next;
} while (bh != head);
folio_unlock(folio);
goto done;
}
EXPORT_SYMBOL(__block_write_full_folio);
/*
* If a folio has any new buffers, zero them out here, and mark them uptodate
* and dirty so they'll be written out (in order to prevent uninitialised
* block data from leaking). And clear the new bit.
*/
void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to)
{
size_t block_start, block_end;
struct buffer_head *head, *bh;
BUG_ON(!folio_test_locked(folio));
head = folio_buffers(folio);
if (!head)
return;
bh = head;
block_start = 0;
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!folio_test_uptodate(folio)) {
size_t start, xend;
start = max(from, block_start);
xend = min(to, block_end);
folio_zero_segment(folio, start, xend);
set_buffer_uptodate(bh);
}
clear_buffer_new(bh);
mark_buffer_dirty(bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
EXPORT_SYMBOL(folio_zero_new_buffers);
static int
iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
const struct iomap *iomap)
{
loff_t offset = (loff_t)block << inode->i_blkbits;
bh->b_bdev = iomap->bdev;
/*
* Block points to offset in file we need to map, iomap contains
* the offset at which the map starts. If the map ends before the
* current block, then do not map the buffer and let the caller
* handle it.
*/
if (offset >= iomap->offset + iomap->length)
return -EIO;
switch (iomap->type) {
case IOMAP_HOLE:
/*
* If the buffer is not up to date or beyond the current EOF,
* we need to mark it as new to ensure sub-block zeroing is
* executed if necessary.
*/
if (!buffer_uptodate(bh) ||
(offset >= i_size_read(inode)))
set_buffer_new(bh);
return 0;
case IOMAP_DELALLOC:
if (!buffer_uptodate(bh) ||
(offset >= i_size_read(inode)))
set_buffer_new(bh);
set_buffer_uptodate(bh);
set_buffer_mapped(bh);
set_buffer_delay(bh);
return 0;
case IOMAP_UNWRITTEN:
/*
* For unwritten regions, we always need to ensure that regions
* in the block we are not writing to are zeroed. Mark the
* buffer as new to ensure this.
*/
set_buffer_new(bh);
set_buffer_unwritten(bh);
fallthrough;
case IOMAP_MAPPED:
if ((iomap->flags & IOMAP_F_NEW) ||
offset >= i_size_read(inode)) {
/*
* This can happen if truncating the block device races
* with the check in the caller as i_size updates on
* block devices aren't synchronized by i_rwsem for
* block devices.
*/
if (S_ISBLK(inode->i_mode))
return -EIO;
set_buffer_new(bh);
}
bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
inode->i_blkbits;
set_buffer_mapped(bh);
return 0;
default:
WARN_ON_ONCE(1);
return -EIO;
}
}
int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
get_block_t *get_block, const struct iomap *iomap)
{
size_t from = offset_in_folio(folio, pos);
size_t to = from + len;
struct inode *inode = folio->mapping->host;
size_t block_start, block_end;
sector_t block;
int err = 0;
size_t blocksize;
struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
BUG_ON(!folio_test_locked(folio));
BUG_ON(to > folio_size(folio));
BUG_ON(from > to);
head = folio_create_buffers(folio, inode, 0);
blocksize = head->b_size;
block = div_u64(folio_pos(folio), blocksize);
for (bh = head, block_start = 0; bh != head || !block_start;
block++, block_start=block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (folio_test_uptodate(folio)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
if (get_block)
err = get_block(inode, block, bh, 1);
else
err = iomap_to_bh(inode, block, bh, iomap);
if (err)
break;
if (buffer_new(bh)) {
clean_bdev_bh_alias(bh);
if (folio_test_uptodate(folio)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
continue;
}
if (block_end > to || block_start < from)
folio_zero_segments(folio,
to, block_end,
block_start, from);
continue;
}
}
if (folio_test_uptodate(folio)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
bh_read_nowait(bh, 0);
*wait_bh++=bh;
}
}
/*
* If we issued read requests - let them complete.
*/
while(wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
if (unlikely(err))
folio_zero_new_buffers(folio, from, to);
return err;
}
int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
get_block_t *get_block)
{
return __block_write_begin_int(folio, pos, len, get_block, NULL);
}
EXPORT_SYMBOL(__block_write_begin);
void block_commit_write(struct folio *folio, size_t from, size_t to)
{
size_t block_start, block_end;
bool partial = false;
unsigned blocksize;
struct buffer_head *bh, *head;
bh = head = folio_buffers(folio);
if (!bh)
return;
blocksize = bh->b_size;
block_start = 0;
do {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
partial = true;
} else {
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
}
if (buffer_new(bh))
clear_buffer_new(bh);
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
/*
* If this is a partial write which happened to make all buffers
* uptodate then we can optimize away a bogus read_folio() for
* the next read(). Here we 'discover' whether the folio went
* uptodate as a result of this (potentially partial) write.
*/
if (!partial)
folio_mark_uptodate(folio);
}
EXPORT_SYMBOL(block_commit_write);
/*
* block_write_begin takes care of the basic task of block allocation and
* bringing partial write blocks uptodate first.
*
* The filesystem needs to handle block truncation upon failure.
*/
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
struct folio **foliop, get_block_t *get_block)
{
pgoff_t index = pos >> PAGE_SHIFT;
struct folio *folio;
int status;
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
status = __block_write_begin_int(folio, pos, len, get_block, NULL);
if (unlikely(status)) {
folio_unlock(folio);
folio_put(folio);
folio = NULL;
}
*foliop = folio;
return status;
}
EXPORT_SYMBOL(block_write_begin);
int block_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
size_t start = pos - folio_pos(folio);
if (unlikely(copied < len)) {
/*
* The buffers that were written will now be uptodate, so
* we don't have to worry about a read_folio reading them
* and overwriting a partial write. However if we have
* encountered a short write and only partially written
* into a buffer, it will not be marked uptodate, so a
* read_folio might come in and destroy our partial write.
*
* Do the simplest thing, and just treat any short write to a
* non uptodate folio as a zero-length write, and force the
* caller to redo the whole thing.
*/
if (!folio_test_uptodate(folio))
copied = 0;
folio_zero_new_buffers(folio, start+copied, start+len);
}
flush_dcache_folio(folio);
/* This could be a short (even 0-length) commit */
block_commit_write(folio, start, start + copied);
return copied;
}
EXPORT_SYMBOL(block_write_end);
int generic_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
bool i_size_changed = false;
copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
/*
* No need to use i_size_read() here, the i_size cannot change under us
* because we hold i_rwsem.
*
* But it's important to update i_size while still holding folio lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
if (pos + copied > inode->i_size) {
i_size_write(inode, pos + copied);
i_size_changed = true;
}
folio_unlock(folio);
folio_put(folio);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
/*
* Don't mark the inode dirty under page lock. First, it unnecessarily
* makes the holding time of page lock longer. Second, it forces lock
* ordering of page lock and transaction start for journaling
* filesystems.
*/
if (i_size_changed)
mark_inode_dirty(inode);
return copied;
}
EXPORT_SYMBOL(generic_write_end);
/*
* block_is_partially_uptodate checks whether buffers within a folio are
* uptodate or not.
*
* Returns true if all buffers which correspond to the specified part
* of the folio are uptodate.
*/
bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
{
unsigned block_start, block_end, blocksize;
unsigned to;
struct buffer_head *bh, *head;
bool ret = true;
head = folio_buffers(folio);
if (!head)
return false;
blocksize = head->b_size;
to = min_t(unsigned, folio_size(folio) - from, count);
to = from + to;
if (from < blocksize && to > folio_size(folio) - blocksize)
return false;
bh = head;
block_start = 0;
do {
block_end = block_start + blocksize;
if (block_end > from && block_start < to) {
if (!buffer_uptodate(bh)) {
ret = false;
break;
}
if (block_end >= to)
break;
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
return ret;
}
EXPORT_SYMBOL(block_is_partially_uptodate);
/*
* Generic "read_folio" function for block devices that have the normal
* get_block functionality. This is most of the block device filesystems.
* Reads the folio asynchronously --- the unlock_buffer() and
* set/clear_buffer_uptodate() functions propagate buffer state into the
* folio once IO has completed.
*/
int block_read_full_folio(struct folio *folio, get_block_t *get_block)
{
struct inode *inode = folio->mapping->host;
sector_t iblock, lblock;
struct buffer_head *bh, *head, *prev = NULL;
size_t blocksize;
int fully_mapped = 1;
bool page_error = false;
loff_t limit = i_size_read(inode);
/* This is needed for ext4. */
if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
limit = inode->i_sb->s_maxbytes;
head = folio_create_buffers(folio, inode, 0);
blocksize = head->b_size;
iblock = div_u64(folio_pos(folio), blocksize);
lblock = div_u64(limit + blocksize - 1, blocksize);
bh = head;
do {
if (buffer_uptodate(bh))
continue;
if (!buffer_mapped(bh)) {
int err = 0;
fully_mapped = 0;
if (iblock < lblock) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
page_error = true;
}
if (!buffer_mapped(bh)) {
folio_zero_range(folio, bh_offset(bh),
blocksize);
if (!err)
set_buffer_uptodate(bh);
continue;
}
/*
* get_block() might have updated the buffer
* synchronously
*/
if (buffer_uptodate(bh))
continue;
}
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
continue;
}
mark_buffer_async_read(bh);
if (prev)
submit_bh(REQ_OP_READ, prev);
prev = bh;
} while (iblock++, (bh = bh->b_this_page) != head);
if (fully_mapped)
folio_set_mappedtodisk(folio);
/*
* All buffers are uptodate or get_block() returned an error
* when trying to map them - we must finish the read because
* end_buffer_async_read() will never be called on any buffer
* in this folio.
*/
if (prev)
submit_bh(REQ_OP_READ, prev);
else
folio_end_read(folio, !page_error);
return 0;
}
EXPORT_SYMBOL(block_read_full_folio);
/* utility function for filesystems that need to do work on expanding
* truncates. Uses filesystem pagecache writes to allow the filesystem to
* deal with the hole.
*/
int generic_cont_expand_simple(struct inode *inode, loff_t size)
{
struct address_space *mapping = inode->i_mapping;
const struct address_space_operations *aops = mapping->a_ops;
struct folio *folio;
void *fsdata = NULL;
int err;
err = inode_newsize_ok(inode, size);
if (err)
goto out;
err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata);
if (err)
goto out;
err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata);
BUG_ON(err > 0);
out:
return err;
}
EXPORT_SYMBOL(generic_cont_expand_simple);
static int cont_expand_zero(struct file *file, struct address_space *mapping,
loff_t pos, loff_t *bytes)
{
struct inode *inode = mapping->host;
const struct address_space_operations *aops = mapping->a_ops;
unsigned int blocksize = i_blocksize(inode);
struct folio *folio;
void *fsdata = NULL;
pgoff_t index, curidx;
loff_t curpos;
unsigned zerofrom, offset, len;
int err = 0;
index = pos >> PAGE_SHIFT;
offset = pos & ~PAGE_MASK;
while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) {
zerofrom = curpos & ~PAGE_MASK;
if (zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
len = PAGE_SIZE - zerofrom;
err = aops->write_begin(file, mapping, curpos, len,
&folio, &fsdata);
if (err)
goto out;
folio_zero_range(folio, offset_in_folio(folio, curpos), len);
err = aops->write_end(file, mapping, curpos, len, len,
folio, fsdata);
if (err < 0)
goto out;
BUG_ON(err != len);
err = 0;
balance_dirty_pages_ratelimited(mapping);
if (fatal_signal_pending(current)) {
err = -EINTR;
goto out;
}
}
/* page covers the boundary, find the boundary offset */
if (index == curidx) {
zerofrom = curpos & ~PAGE_MASK;
/* if we will expand the thing last block will be filled */
if (offset <= zerofrom) {
goto out;
}
if (zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
len = offset - zerofrom;
err = aops->write_begin(file, mapping, curpos, len,
&folio, &fsdata);
if (err)
goto out;
folio_zero_range(folio, offset_in_folio(folio, curpos), len);
err = aops->write_end(file, mapping, curpos, len, len,
folio, fsdata);
if (err < 0)
goto out;
BUG_ON(err != len);
err = 0;
}
out:
return err;
}
/*
* For moronic filesystems that do not allow holes in file.
* We may have to extend the file.
*/
int cont_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata,
get_block_t *get_block, loff_t *bytes)
{
struct inode *inode = mapping->host;
unsigned int blocksize = i_blocksize(inode);
unsigned int zerofrom;
int err;
err = cont_expand_zero(file, mapping, pos, bytes);
if (err)
return err;
zerofrom = *bytes & ~PAGE_MASK;
if (pos+len > *bytes && zerofrom & (blocksize-1)) {
*bytes |= (blocksize-1);
(*bytes)++;
}
return block_write_begin(mapping, pos, len, foliop, get_block);
}
EXPORT_SYMBOL(cont_write_begin);
/*
* block_page_mkwrite() is not allowed to change the file size as it gets
* called from a page fault handler when a page is first dirtied. Hence we must
* be careful to check for EOF conditions here. We set the page up correctly
* for a written page which means we get ENOSPC checking when writing into
* holes and correct delalloc and unwritten extent mapping on filesystems that
* support these features.
*
* We are not allowed to take the i_mutex here so we have to play games to
* protect against truncate races as the page could now be beyond EOF. Because
* truncate writes the inode size before removing pages, once we have the
* page lock we can determine safely if the page is beyond EOF. If it is not
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
*
* Direct callers of this function should protect against filesystem freezing
* using sb_start_pagefault() - sb_end_pagefault() functions.
*/
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
struct folio *folio = page_folio(vmf->page);
struct inode *inode = file_inode(vma->vm_file);
unsigned long end;
loff_t size;
int ret;
folio_lock(folio);
size = i_size_read(inode);
if ((folio->mapping != inode->i_mapping) ||
(folio_pos(folio) >= size)) {
/* We overload EFAULT to mean page got truncated */
ret = -EFAULT;
goto out_unlock;
}
end = folio_size(folio);
/* folio is wholly or partially inside EOF */
if (folio_pos(folio) + end > size)
end = size - folio_pos(folio);
ret = __block_write_begin_int(folio, 0, end, get_block, NULL);
if (unlikely(ret))
goto out_unlock;
block_commit_write(folio, 0, end);
folio_mark_dirty(folio);
folio_wait_stable(folio);
return 0;
out_unlock:
folio_unlock(folio);
return ret;
}
EXPORT_SYMBOL(block_page_mkwrite);
int block_truncate_page(struct address_space *mapping,
loff_t from, get_block_t *get_block)
{
pgoff_t index = from >> PAGE_SHIFT;
unsigned blocksize;
sector_t iblock;
size_t offset, length, pos;
struct inode *inode = mapping->host;
struct folio *folio;
struct buffer_head *bh;
int err = 0;
blocksize = i_blocksize(inode);
length = from & (blocksize - 1);
/* Block boundary? Nothing to do */
if (!length)
return 0;
length = blocksize - length;
iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits;
folio = filemap_grab_folio(mapping, index);
if (IS_ERR(folio))
return PTR_ERR(folio);
bh = folio_buffers(folio);
if (!bh)
bh = create_empty_buffers(folio, blocksize, 0);
/* Find the buffer that contains "offset" */
offset = offset_in_folio(folio, from);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, iblock, bh, 0);
if (err)
goto unlock;
/* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh))
goto unlock;
}
/* Ok, it's mapped. Make sure it's up-to-date */
if (folio_test_uptodate(folio))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
err = bh_read(bh, 0);
/* Uhhuh. Read error. Complain and punt. */
if (err < 0)
goto unlock;
}
folio_zero_range(folio, offset, length);
mark_buffer_dirty(bh);
unlock:
folio_unlock(folio);
folio_put(folio);
return err;
}
EXPORT_SYMBOL(block_truncate_page);
/*
* The generic ->writepage function for buffer-backed address_spaces
*/
int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
void *get_block)
{
struct inode * const inode = folio->mapping->host;
loff_t i_size = i_size_read(inode);
/* Is the folio fully inside i_size? */
if (folio_pos(folio) + folio_size(folio) <= i_size)
return __block_write_full_folio(inode, folio, get_block, wbc);
/* Is the folio fully outside i_size? (truncate in progress) */
if (folio_pos(folio) >= i_size) {
folio_unlock(folio);
return 0; /* don't care */
}
/*
* The folio straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
* in multiples of the page size. For a file that is not a multiple of
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
folio_zero_segment(folio, offset_in_folio(folio, i_size),
folio_size(folio));
return __block_write_full_folio(inode, folio, get_block, wbc);
}
sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
get_block_t *get_block)
{
struct inode *inode = mapping->host;
struct buffer_head tmp = {
.b_size = i_blocksize(inode),
};
get_block(inode, block, &tmp, 0);
return tmp.b_blocknr;
}
EXPORT_SYMBOL(generic_block_bmap);
static void end_bio_bh_io_sync(struct bio *bio)
{
struct buffer_head *bh = bio->bi_private;
if (unlikely(bio_flagged(bio, BIO_QUIET)))
set_bit(BH_Quiet, &bh->b_state);
bh->b_end_io(bh, !bio->bi_status);
bio_put(bio);
}
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
enum rw_hint write_hint,
struct writeback_control *wbc)
{
const enum req_op op = opf & REQ_OP_MASK;
struct bio *bio;
BUG_ON(!buffer_locked(bh));
BUG_ON(!buffer_mapped(bh));
BUG_ON(!bh->b_end_io);
BUG_ON(buffer_delay(bh));
BUG_ON(buffer_unwritten(bh));
/*
* Only clear out a write error when rewriting
*/
if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
clear_buffer_write_io_error(bh);
if (buffer_meta(bh))
opf |= REQ_META;
if (buffer_prio(bh))
opf |= REQ_PRIO;
bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_write_hint = write_hint;
bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh));
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
/* Take care of bh's that straddle the end of the device */
guard_bio_eod(bio);
if (wbc) {
wbc_init_bio(wbc, bio);
wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size);
}
submit_bio(bio);
}
void submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL);
}
EXPORT_SYMBOL(submit_bh);
void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
lock_buffer(bh);
if (!test_clear_buffer_dirty(bh)) {
unlock_buffer(bh);
return;
}
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
submit_bh(REQ_OP_WRITE | op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);
/*
* For a data-integrity writeout, we need to wait upon any in-progress I/O
* and then start new I/O and then wait upon it. The caller must have a ref on
* the buffer_head.
*/
int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
WARN_ON(atomic_read(&bh->b_count) < 1);
lock_buffer(bh);
if (test_clear_buffer_dirty(bh)) {
/*
* The bh should be mapped, but it might not be if the
* device was hot-removed. Not much we can do but fail the I/O.
*/
if (!buffer_mapped(bh)) {
unlock_buffer(bh);
return -EIO;
}
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
submit_bh(REQ_OP_WRITE | op_flags, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
return -EIO;
} else {
unlock_buffer(bh);
}
return 0;
}
EXPORT_SYMBOL(__sync_dirty_buffer);
int sync_dirty_buffer(struct buffer_head *bh)
{
return __sync_dirty_buffer(bh, REQ_SYNC);
}
EXPORT_SYMBOL(sync_dirty_buffer);
static inline int buffer_busy(struct buffer_head *bh)
{
return atomic_read(&bh->b_count) |
(bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock)));
}
static bool
drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free)
{
struct buffer_head *head = folio_buffers(folio);
struct buffer_head *bh;
bh = head;
do {
if (buffer_busy(bh))
goto failed;
bh = bh->b_this_page;
} while (bh != head);
do {
struct buffer_head *next = bh->b_this_page;
if (bh->b_assoc_map)
__remove_assoc_queue(bh);
bh = next;
} while (bh != head);
*buffers_to_free = head;
folio_detach_private(folio);
return true;
failed:
return false;
}
/**
* try_to_free_buffers - Release buffers attached to this folio.
* @folio: The folio.
*
* If any buffers are in use (dirty, under writeback, elevated refcount),
* no buffers will be freed.
*
* If the folio is dirty but all the buffers are clean then we need to
* be sure to mark the folio clean as well. This is because the folio
* may be against a block device, and a later reattachment of buffers
* to a dirty folio will set *all* buffers dirty. Which would corrupt
* filesystem data on the same device.
*
* The same applies to regular filesystem folios: if all the buffers are
* clean then we set the folio clean and proceed. To do that, we require
* total exclusion from block_dirty_folio(). That is obtained with
* i_private_lock.
*
* Exclusion against try_to_free_buffers may be obtained by either
* locking the folio or by holding its mapping's i_private_lock.
*
* Context: Process context. @folio must be locked. Will not sleep.
* Return: true if all buffers attached to this folio were freed.
*/
bool try_to_free_buffers(struct folio *folio)
{
struct address_space * const mapping = folio->mapping;
struct buffer_head *buffers_to_free = NULL;
bool ret = 0;
BUG_ON(!folio_test_locked(folio));
if (folio_test_writeback(folio))
return false;
if (mapping == NULL) { /* can this still happen? */
ret = drop_buffers(folio, &buffers_to_free);
goto out;
}
spin_lock(&mapping->i_private_lock);
ret = drop_buffers(folio, &buffers_to_free);
/*
* If the filesystem writes its buffers by hand (eg ext3)
* then we can have clean buffers against a dirty folio. We
* clean the folio here; otherwise the VM will never notice
* that the filesystem did any IO at all.
*
* Also, during truncate, discard_buffer will have marked all
* the folio's buffers clean. We discover that here and clean
* the folio also.
*
* i_private_lock must be held over this entire operation in order
* to synchronise against block_dirty_folio and prevent the
* dirty bit from being lost.
*/
if (ret)
folio_cancel_dirty(folio);
spin_unlock(&mapping->i_private_lock);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
do {
struct buffer_head *next = bh->b_this_page;
free_buffer_head(bh);
bh = next;
} while (bh != buffers_to_free);
}
return ret;
}
EXPORT_SYMBOL(try_to_free_buffers);
/*
* Buffer-head allocation
*/
static struct kmem_cache *bh_cachep __ro_after_init;
/*
* Once the number of bh's in the machine exceeds this level, we start
* stripping them in writeback.
*/
static unsigned long max_buffer_heads __ro_after_init;
int buffer_heads_over_limit;
struct bh_accounting {
int nr; /* Number of live bh's */
int ratelimit; /* Limit cacheline bouncing */
};
static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};
static void recalc_bh_state(void)
{
int i;
int tot = 0;
if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
return;
__this_cpu_write(bh_accounting.ratelimit, 0);
for_each_online_cpu(i)
tot += per_cpu(bh_accounting, i).nr;
buffer_heads_over_limit = (tot > max_buffer_heads);
}
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
{
struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
INIT_LIST_HEAD(&ret->b_assoc_buffers);
spin_lock_init(&ret->b_uptodate_lock);
preempt_disable();
__this_cpu_inc(bh_accounting.nr);
recalc_bh_state();
preempt_enable();
}
return ret;
}
EXPORT_SYMBOL(alloc_buffer_head);
void free_buffer_head(struct buffer_head *bh)
{
BUG_ON(!list_empty(&bh->b_assoc_buffers));
kmem_cache_free(bh_cachep, bh);
preempt_disable();
__this_cpu_dec(bh_accounting.nr);
recalc_bh_state();
preempt_enable();
}
EXPORT_SYMBOL(free_buffer_head);
static int buffer_exit_cpu_dead(unsigned int cpu)
{
int i;
struct bh_lru *b = &per_cpu(bh_lrus, cpu);
for (i = 0; i < BH_LRU_SIZE; i++) {
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
per_cpu(bh_accounting, cpu).nr = 0;
return 0;
}
/**
* bh_uptodate_or_lock - Test whether the buffer is uptodate
* @bh: struct buffer_head
*
* Return true if the buffer is up-to-date and false,
* with the buffer locked, if not.
*/
int bh_uptodate_or_lock(struct buffer_head *bh)
{
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
if (!buffer_uptodate(bh))
return 0;
unlock_buffer(bh);
}
return 1;
}
EXPORT_SYMBOL(bh_uptodate_or_lock);
/**
* __bh_read - Submit read for a locked buffer
* @bh: struct buffer_head
* @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
* @wait: wait until reading finish
*
* Returns zero on success or don't wait, and -EIO on error.
*/
int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
{
int ret = 0;
BUG_ON(!buffer_locked(bh));
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ | op_flags, bh);
if (wait) {
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
ret = -EIO;
}
return ret;
}
EXPORT_SYMBOL(__bh_read);
/**
* __bh_read_batch - Submit read for a batch of unlocked buffers
* @nr: entry number of the buffer batch
* @bhs: a batch of struct buffer_head
* @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
* @force_lock: force to get a lock on the buffer if set, otherwise drops any
* buffer that cannot lock.
*
* Returns zero on success or don't wait, and -EIO on error.
*/
void __bh_read_batch(int nr, struct buffer_head *bhs[],
blk_opf_t op_flags, bool force_lock)
{
int i;
for (i = 0; i < nr; i++) {
struct buffer_head *bh = bhs[i];
if (buffer_uptodate(bh))
continue;
if (force_lock)
lock_buffer(bh);
else
if (!trylock_buffer(bh))
continue;
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
continue;
}
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
submit_bh(REQ_OP_READ | op_flags, bh);
}
}
EXPORT_SYMBOL(__bh_read_batch);
void __init buffer_init(void)
{
unsigned long nrpages;
int ret;
bh_cachep = KMEM_CACHE(buffer_head,
SLAB_RECLAIM_ACCOUNT|SLAB_PANIC);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL
*/
nrpages = (nr_free_buffer_pages() * 10) / 100;
max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead",
NULL, buffer_exit_cpu_dead);
WARN_ON(ret < 0);
}
// SPDX-License-Identifier: GPL-2.0
/*
* Kernel internal schedule timeout and sleeping functions
*/
#include <linux/delay.h>
#include <linux/jiffies.h>
#include <linux/timer.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include "tick-internal.h"
/*
* Since schedule_timeout()'s timer is defined on the stack, it must store
* the target task on the stack as well.
*/
struct process_timer {
struct timer_list timer;
struct task_struct *task;
};
static void process_timeout(struct timer_list *t)
{
struct process_timer *timeout = from_timer(timeout, t, timer);
wake_up_process(timeout->task);
}
/**
* schedule_timeout - sleep until timeout
* @timeout: timeout value in jiffies
*
* Make the current task sleep until @timeout jiffies have elapsed.
* The function behavior depends on the current task state
* (see also set_current_state() description):
*
* %TASK_RUNNING - the scheduler is called, but the task does not sleep
* at all. That happens because sched_submit_work() does nothing for
* tasks in %TASK_RUNNING state.
*
* %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
* pass before the routine returns unless the current task is explicitly
* woken up, (e.g. by wake_up_process()).
*
* %TASK_INTERRUPTIBLE - the routine may return early if a signal is
* delivered to the current task or the current task is explicitly woken
* up.
*
* The current task state is guaranteed to be %TASK_RUNNING when this
* routine returns.
*
* Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
* the CPU away without a bound on the timeout. In this case the return
* value will be %MAX_SCHEDULE_TIMEOUT.
*
* Returns: 0 when the timer has expired otherwise the remaining time in
* jiffies will be returned. In all cases the return value is guaranteed
* to be non-negative.
*/
signed long __sched schedule_timeout(signed long timeout)
{
struct process_timer timer;
unsigned long expire;
switch (timeout) {
case MAX_SCHEDULE_TIMEOUT:
/*
* These two special cases are useful to be comfortable
* in the caller. Nothing more. We could take
* MAX_SCHEDULE_TIMEOUT from one of the negative value
* but I' d like to return a valid offset (>=0) to allow
* the caller to do everything it want with the retval.
*/
schedule();
goto out;
default:
/*
* Another bit of PARANOID. Note that the retval will be
* 0 since no piece of kernel is supposed to do a check
* for a negative retval of schedule_timeout() (since it
* should never happens anyway). You just have the printk()
* that will tell you if something is gone wrong and where.
*/
if (timeout < 0) {
pr_err("%s: wrong timeout value %lx\n", __func__, timeout);
dump_stack();
__set_current_state(TASK_RUNNING);
goto out;
}
}
expire = timeout + jiffies;
timer.task = current;
timer_setup_on_stack(&timer.timer, process_timeout, 0);
timer.timer.expires = expire;
add_timer(&timer.timer);
schedule();
timer_delete_sync(&timer.timer);
/* Remove the timer from the object tracker */
destroy_timer_on_stack(&timer.timer);
timeout = expire - jiffies;
out:
return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);
/*
* __set_current_state() can be used in schedule_timeout_*() functions, because
* schedule_timeout() calls schedule() unconditionally.
*/
/**
* schedule_timeout_interruptible - sleep until timeout (interruptible)
* @timeout: timeout value in jiffies
*
* See schedule_timeout() for details.
*
* Task state is set to TASK_INTERRUPTIBLE before starting the timeout.
*/
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
__set_current_state(TASK_INTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_interruptible);
/**
* schedule_timeout_killable - sleep until timeout (killable)
* @timeout: timeout value in jiffies
*
* See schedule_timeout() for details.
*
* Task state is set to TASK_KILLABLE before starting the timeout.
*/
signed long __sched schedule_timeout_killable(signed long timeout)
{
__set_current_state(TASK_KILLABLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_killable);
/**
* schedule_timeout_uninterruptible - sleep until timeout (uninterruptible)
* @timeout: timeout value in jiffies
*
* See schedule_timeout() for details.
*
* Task state is set to TASK_UNINTERRUPTIBLE before starting the timeout.
*/
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
__set_current_state(TASK_UNINTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);
/**
* schedule_timeout_idle - sleep until timeout (idle)
* @timeout: timeout value in jiffies
*
* See schedule_timeout() for details.
*
* Task state is set to TASK_IDLE before starting the timeout. It is similar to
* schedule_timeout_uninterruptible(), except this task will not contribute to
* load average.
*/
signed long __sched schedule_timeout_idle(signed long timeout)
{
__set_current_state(TASK_IDLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_idle);
/**
* schedule_hrtimeout_range_clock - sleep until timeout
* @expires: timeout value (ktime_t)
* @delta: slack in expires timeout (ktime_t)
* @mode: timer mode
* @clock_id: timer clock to be used
*
* Details are explained in schedule_hrtimeout_range() function description as
* this function is commonly used.
*/
int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode, clockid_t clock_id)
{
struct hrtimer_sleeper t;
/*
* Optimize when a zero timeout value is given. It does not
* matter whether this is an absolute or a relative time.
*/
if (expires && *expires == 0) {
__set_current_state(TASK_RUNNING);
return 0;
}
/*
* A NULL parameter means "infinite"
*/
if (!expires) {
schedule();
return -EINTR;
}
hrtimer_setup_sleeper_on_stack(&t, clock_id, mode);
hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
hrtimer_sleeper_start_expires(&t, mode);
if (likely(t.task))
schedule();
hrtimer_cancel(&t.timer);
destroy_hrtimer_on_stack(&t.timer);
__set_current_state(TASK_RUNNING);
return !t.task ? 0 : -EINTR;
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
/**
* schedule_hrtimeout_range - sleep until timeout
* @expires: timeout value (ktime_t)
* @delta: slack in expires timeout (ktime_t)
* @mode: timer mode
*
* Make the current task sleep until the given expiry time has
* elapsed. The routine will return immediately unless
* the current task state has been set (see set_current_state()).
*
* The @delta argument gives the kernel the freedom to schedule the
* actual wakeup to a time that is both power and performance friendly
* for regular (non RT/DL) tasks.
* The kernel give the normal best effort behavior for "@expires+@delta",
* but may decide to fire the timer earlier, but no earlier than @expires.
*
* You can set the task state as follows -
*
* %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
* pass before the routine returns unless the current task is explicitly
* woken up, (e.g. by wake_up_process()).
*
* %TASK_INTERRUPTIBLE - the routine may return early if a signal is
* delivered to the current task or the current task is explicitly woken
* up.
*
* The current task state is guaranteed to be TASK_RUNNING when this
* routine returns.
*
* Returns: 0 when the timer has expired. If the task was woken before the
* timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or
* by an explicit wakeup, it returns -EINTR.
*/
int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode)
{
return schedule_hrtimeout_range_clock(expires, delta, mode,
CLOCK_MONOTONIC);
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
/**
* schedule_hrtimeout - sleep until timeout
* @expires: timeout value (ktime_t)
* @mode: timer mode
*
* See schedule_hrtimeout_range() for details. @delta argument of
* schedule_hrtimeout_range() is set to 0 and has therefore no impact.
*/
int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode)
{
return schedule_hrtimeout_range(expires, 0, mode);
}
EXPORT_SYMBOL_GPL(schedule_hrtimeout);
/**
* msleep - sleep safely even with waitqueue interruptions
* @msecs: Requested sleep duration in milliseconds
*
* msleep() uses jiffy based timeouts for the sleep duration. Because of the
* design of the timer wheel, the maximum additional percentage delay (slack) is
* 12.5%. This is only valid for timers which will end up in level 1 or a higher
* level of the timer wheel. For explanation of those 12.5% please check the
* detailed description about the basics of the timer wheel.
*
* The slack of timers which will end up in level 0 depends on sleep duration
* (msecs) and HZ configuration and can be calculated in the following way (with
* the timer wheel design restriction that the slack is not less than 12.5%):
*
* ``slack = MSECS_PER_TICK / msecs``
*
* When the allowed slack of the callsite is known, the calculation could be
* turned around to find the minimal allowed sleep duration to meet the
* constraints. For example:
*
* * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``:
* all sleep durations greater or equal 4ms will meet the constraints.
* * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``:
* all sleep durations greater or equal 8ms will meet the constraints.
* * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``:
* all sleep durations greater or equal 16ms will meet the constraints.
* * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``:
* all sleep durations greater or equal 32ms will meet the constraints.
*
* See also the signal aware variant msleep_interruptible().
*/
void msleep(unsigned int msecs)
{
unsigned long timeout = msecs_to_jiffies(msecs);
while (timeout)
timeout = schedule_timeout_uninterruptible(timeout);
}
EXPORT_SYMBOL(msleep);
/**
* msleep_interruptible - sleep waiting for signals
* @msecs: Requested sleep duration in milliseconds
*
* See msleep() for some basic information.
*
* The difference between msleep() and msleep_interruptible() is that the sleep
* could be interrupted by a signal delivery and then returns early.
*
* Returns: The remaining time of the sleep duration transformed to msecs (see
* schedule_timeout() for details).
*/
unsigned long msleep_interruptible(unsigned int msecs)
{
unsigned long timeout = msecs_to_jiffies(msecs);
while (timeout && !signal_pending(current))
timeout = schedule_timeout_interruptible(timeout);
return jiffies_to_msecs(timeout);
}
EXPORT_SYMBOL(msleep_interruptible);
/**
* usleep_range_state - Sleep for an approximate time in a given state
* @min: Minimum time in usecs to sleep
* @max: Maximum time in usecs to sleep
* @state: State of the current task that will be while sleeping
*
* usleep_range_state() sleeps at least for the minimum specified time but not
* longer than the maximum specified amount of time. The range might reduce
* power usage by allowing hrtimers to coalesce an already scheduled interrupt
* with this hrtimer. In the worst case, an interrupt is scheduled for the upper
* bound.
*
* The sleeping task is set to the specified state before starting the sleep.
*
* In non-atomic context where the exact wakeup time is flexible, use
* usleep_range() or its variants instead of udelay(). The sleep improves
* responsiveness by avoiding the CPU-hogging busy-wait of udelay().
*/
void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state)
{
ktime_t exp = ktime_add_us(ktime_get(), min);
u64 delta = (u64)(max - min) * NSEC_PER_USEC;
if (WARN_ON_ONCE(max < min))
delta = 0;
for (;;) {
__set_current_state(state);
/* Do not return before the requested sleep time has elapsed */
if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
break;
}
}
EXPORT_SYMBOL(usleep_range_state);
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2015 Imagination Technologies Ltd
* Author: Qais Yousef <qais.yousef@imgtec.com>
*
* This file contains driver APIs to the IPI subsystem.
*/
#define pr_fmt(fmt) "genirq/ipi: " fmt
#include <linux/irqdomain.h>
#include <linux/irq.h>
/**
* irq_reserve_ipi() - Setup an IPI to destination cpumask
* @domain: IPI domain
* @dest: cpumask of CPUs which can receive the IPI
*
* Allocate a virq that can be used to send IPI to any CPU in dest mask.
*
* Return: Linux IRQ number on success or error code on failure
*/
int irq_reserve_ipi(struct irq_domain *domain,
const struct cpumask *dest)
{
unsigned int nr_irqs, offset;
struct irq_data *data;
int virq, i;
if (!domain ||!irq_domain_is_ipi(domain)) {
pr_warn("Reservation on a non IPI domain\n");
return -EINVAL;
}
if (!cpumask_subset(dest, cpu_possible_mask)) {
pr_warn("Reservation is not in possible_cpu_mask\n");
return -EINVAL;
}
nr_irqs = cpumask_weight(dest);
if (!nr_irqs) {
pr_warn("Reservation for empty destination mask\n");
return -EINVAL;
}
if (irq_domain_is_ipi_single(domain)) {
/*
* If the underlying implementation uses a single HW irq on
* all cpus then we only need a single Linux irq number for
* it. We have no restrictions vs. the destination mask. The
* underlying implementation can deal with holes nicely.
*/
nr_irqs = 1;
offset = 0;
} else {
unsigned int next;
/*
* The IPI requires a separate HW irq on each CPU. We require
* that the destination mask is consecutive. If an
* implementation needs to support holes, it can reserve
* several IPI ranges.
*/
offset = cpumask_first(dest);
/*
* Find a hole and if found look for another set bit after the
* hole. For now we don't support this scenario.
*/
next = cpumask_next_zero(offset, dest);
if (next < nr_cpu_ids)
next = cpumask_next(next, dest);
if (next < nr_cpu_ids) {
pr_warn("Destination mask has holes\n");
return -EINVAL;
}
}
virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL);
if (virq <= 0) {
pr_warn("Can't reserve IPI, failed to alloc descs\n");
return -ENOMEM;
}
virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE,
(void *) dest, true, NULL);
if (virq <= 0) {
pr_warn("Can't reserve IPI, failed to alloc hw irqs\n");
goto free_descs;
}
for (i = 0; i < nr_irqs; i++) {
data = irq_get_irq_data(virq + i);
cpumask_copy(data->common->affinity, dest);
data->common->ipi_offset = offset;
irq_set_status_flags(virq + i, IRQ_NO_BALANCING);
}
return virq;
free_descs:
irq_free_descs(virq, nr_irqs);
return -EBUSY;
}
/**
* irq_destroy_ipi() - unreserve an IPI that was previously allocated
* @irq: Linux IRQ number to be destroyed
* @dest: cpumask of CPUs which should have the IPI removed
*
* The IPIs allocated with irq_reserve_ipi() are returned to the system
* destroying all virqs associated with them.
*
* Return: %0 on success or error code on failure.
*/
int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest)
{
struct irq_data *data = irq_get_irq_data(irq);
const struct cpumask *ipimask;
struct irq_domain *domain;
unsigned int nr_irqs;
if (!irq || !data)
return -EINVAL;
domain = data->domain;
if (WARN_ON(domain == NULL))
return -EINVAL;
if (!irq_domain_is_ipi(domain)) {
pr_warn("Trying to destroy a non IPI domain!\n");
return -EINVAL;
}
ipimask = irq_data_get_affinity_mask(data);
if (!ipimask || WARN_ON(!cpumask_subset(dest, ipimask)))
/*
* Must be destroying a subset of CPUs to which this IPI
* was set up to target
*/
return -EINVAL;
if (irq_domain_is_ipi_per_cpu(domain)) {
irq = irq + cpumask_first(dest) - data->common->ipi_offset;
nr_irqs = cpumask_weight(dest);
} else {
nr_irqs = 1;
}
irq_domain_free_irqs(irq, nr_irqs);
return 0;
}
/**
* ipi_get_hwirq - Get the hwirq associated with an IPI to a CPU
* @irq: Linux IRQ number
* @cpu: the target CPU
*
* When dealing with coprocessors IPI, we need to inform the coprocessor of
* the hwirq it needs to use to receive and send IPIs.
*
* Return: hwirq value on success or INVALID_HWIRQ on failure.
*/
irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu)
{
struct irq_data *data = irq_get_irq_data(irq);
const struct cpumask *ipimask;
if (!data || cpu >= nr_cpu_ids)
return INVALID_HWIRQ;
ipimask = irq_data_get_affinity_mask(data);
if (!ipimask || !cpumask_test_cpu(cpu, ipimask))
return INVALID_HWIRQ;
/*
* Get the real hardware irq number if the underlying implementation
* uses a separate irq per cpu. If the underlying implementation uses
* a single hardware irq for all cpus then the IPI send mechanism
* needs to take care of the cpu destinations.
*/
if (irq_domain_is_ipi_per_cpu(data->domain))
data = irq_get_irq_data(irq + cpu - data->common->ipi_offset);
return data ? irqd_to_hwirq(data) : INVALID_HWIRQ;
}
EXPORT_SYMBOL_GPL(ipi_get_hwirq);
static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data,
const struct cpumask *dest, unsigned int cpu)
{
const struct cpumask *ipimask;
if (!chip || !data)
return -EINVAL;
if (!chip->ipi_send_single && !chip->ipi_send_mask)
return -EINVAL;
if (cpu >= nr_cpu_ids)
return -EINVAL;
ipimask = irq_data_get_affinity_mask(data);
if (!ipimask)
return -EINVAL;
if (dest) {
if (!cpumask_subset(dest, ipimask))
return -EINVAL;
} else {
if (!cpumask_test_cpu(cpu, ipimask))
return -EINVAL;
}
return 0;
}
/**
* __ipi_send_single - send an IPI to a target Linux SMP CPU
* @desc: pointer to irq_desc of the IRQ
* @cpu: destination CPU, must in the destination mask passed to
* irq_reserve_ipi()
*
* This function is for architecture or core code to speed up IPI sending. Not
* usable from driver code.
*
* Return: %0 on success or negative error number on failure.
*/
int __ipi_send_single(struct irq_desc *desc, unsigned int cpu)
{
struct irq_data *data = irq_desc_get_irq_data(desc);
struct irq_chip *chip = irq_data_get_irq_chip(data);
#ifdef DEBUG
/*
* Minimise the overhead by omitting the checks for Linux SMP IPIs.
* Since the callers should be arch or core code which is generally
* trusted, only check for errors when debugging.
*/
if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu)))
return -EINVAL;
#endif
if (!chip->ipi_send_single) {
chip->ipi_send_mask(data, cpumask_of(cpu));
return 0;
}
/* FIXME: Store this information in irqdata flags */
if (irq_domain_is_ipi_per_cpu(data->domain) &&
cpu != data->common->ipi_offset) {
/* use the correct data for that cpu */
unsigned irq = data->irq + cpu - data->common->ipi_offset;
data = irq_get_irq_data(irq);
}
chip->ipi_send_single(data, cpu);
return 0;
}
/**
* __ipi_send_mask - send an IPI to target Linux SMP CPU(s)
* @desc: pointer to irq_desc of the IRQ
* @dest: dest CPU(s), must be a subset of the mask passed to
* irq_reserve_ipi()
*
* This function is for architecture or core code to speed up IPI sending. Not
* usable from driver code.
*
* Return: %0 on success or negative error number on failure.
*/
int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest)
{
struct irq_data *data = irq_desc_get_irq_data(desc);
struct irq_chip *chip = irq_data_get_irq_chip(data);
unsigned int cpu;
#ifdef DEBUG
/*
* Minimise the overhead by omitting the checks for Linux SMP IPIs.
* Since the callers should be arch or core code which is generally
* trusted, only check for errors when debugging.
*/
if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0)))
return -EINVAL;
#endif
if (chip->ipi_send_mask) {
chip->ipi_send_mask(data, dest);
return 0;
}
if (irq_domain_is_ipi_per_cpu(data->domain)) {
unsigned int base = data->irq;
for_each_cpu(cpu, dest) {
unsigned irq = base + cpu - data->common->ipi_offset;
data = irq_get_irq_data(irq);
chip->ipi_send_single(data, cpu);
}
} else {
for_each_cpu(cpu, dest)
chip->ipi_send_single(data, cpu);
}
return 0;
}
/**
* ipi_send_single - Send an IPI to a single CPU
* @virq: Linux IRQ number from irq_reserve_ipi()
* @cpu: destination CPU, must in the destination mask passed to
* irq_reserve_ipi()
*
* Return: %0 on success or negative error number on failure.
*/
int ipi_send_single(unsigned int virq, unsigned int cpu)
{
struct irq_desc *desc = irq_to_desc(virq);
struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL;
struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL;
if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu)))
return -EINVAL;
return __ipi_send_single(desc, cpu);
}
EXPORT_SYMBOL_GPL(ipi_send_single);
/**
* ipi_send_mask - Send an IPI to target CPU(s)
* @virq: Linux IRQ number from irq_reserve_ipi()
* @dest: dest CPU(s), must be a subset of the mask passed to
* irq_reserve_ipi()
*
* Return: %0 on success or negative error number on failure.
*/
int ipi_send_mask(unsigned int virq, const struct cpumask *dest)
{
struct irq_desc *desc = irq_to_desc(virq);
struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL;
struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL;
if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0)))
return -EINVAL;
return __ipi_send_mask(desc, dest);
}
EXPORT_SYMBOL_GPL(ipi_send_mask);
// SPDX-License-Identifier: GPL-2.0
/*
* Kernel timekeeping code and accessor functions. Based on code from
* timer.c, moved in commit 8524070b7982.
*/
#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/clock.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/timex.h>
#include <linux/tick.h>
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
#include <linux/compiler.h>
#include <linux/audit.h>
#include <linux/random.h>
#include "tick-internal.h"
#include "ntp_internal.h"
#include "timekeeping_internal.h"
#define TK_CLEAR_NTP (1 << 0)
#define TK_CLOCK_WAS_SET (1 << 1)
#define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET)
enum timekeeping_adv_mode {
/* Update timekeeper when a tick has passed */
TK_ADV_TICK,
/* Update timekeeper on a direct frequency change */
TK_ADV_FREQ
};
/*
* The most important data for readout fits into a single 64 byte
* cache line.
*/
struct tk_data {
seqcount_raw_spinlock_t seq;
struct timekeeper timekeeper;
struct timekeeper shadow_timekeeper;
raw_spinlock_t lock;
} ____cacheline_aligned;
static struct tk_data tk_core;
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
/**
* struct tk_fast - NMI safe timekeeper
* @seq: Sequence counter for protecting updates. The lowest bit
* is the index for the tk_read_base array
* @base: tk_read_base array. Access is indexed by the lowest bit of
* @seq.
*
* See @update_fast_timekeeper() below.
*/
struct tk_fast {
seqcount_latch_t seq;
struct tk_read_base base[2];
};
/* Suspend-time cycles value for halted fast timekeeper. */
static u64 cycles_at_suspend;
static u64 dummy_clock_read(struct clocksource *cs)
{
if (timekeeping_suspended)
return cycles_at_suspend;
return local_clock();
}
static struct clocksource dummy_clock = {
.read = dummy_clock_read,
};
/*
* Boot time initialization which allows local_clock() to be utilized
* during early boot when clocksources are not available. local_clock()
* returns nanoseconds already so no conversion is required, hence mult=1
* and shift=0. When the first proper clocksource is installed then
* the fast time keepers are updated with the correct values.
*/
#define FAST_TK_INIT \
{ \
.clock = &dummy_clock, \
.mask = CLOCKSOURCE_MASK(64), \
.mult = 1, \
.shift = 0, \
}
static struct tk_fast tk_fast_mono ____cacheline_aligned = {
.seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq),
.base[0] = FAST_TK_INIT,
.base[1] = FAST_TK_INIT,
};
static struct tk_fast tk_fast_raw ____cacheline_aligned = {
.seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq),
.base[0] = FAST_TK_INIT,
.base[1] = FAST_TK_INIT,
};
unsigned long timekeeper_lock_irqsave(void)
{
unsigned long flags;
raw_spin_lock_irqsave(&tk_core.lock, flags);
return flags;
}
void timekeeper_unlock_irqrestore(unsigned long flags)
{
raw_spin_unlock_irqrestore(&tk_core.lock, flags);
}
/*
* Multigrain timestamps require tracking the latest fine-grained timestamp
* that has been issued, and never returning a coarse-grained timestamp that is
* earlier than that value.
*
* mg_floor represents the latest fine-grained time that has been handed out as
* a file timestamp on the system. This is tracked as a monotonic ktime_t, and
* converted to a realtime clock value on an as-needed basis.
*
* Maintaining mg_floor ensures the multigrain interfaces never issue a
* timestamp earlier than one that has been previously issued.
*
* The exception to this rule is when there is a backward realtime clock jump. If
* such an event occurs, a timestamp can appear to be earlier than a previous one.
*/
static __cacheline_aligned_in_smp atomic64_t mg_floor;
static inline void tk_normalize_xtime(struct timekeeper *tk)
{
while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
tk->xtime_sec++;
}
while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) {
tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
tk->raw_sec++;
}
}
static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
{
struct timespec64 ts;
ts.tv_sec = tk->xtime_sec;
ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
return ts;
}
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec += ts->tv_sec;
tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
tk_normalize_xtime(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
{
struct timespec64 tmp;
/*
* Verify consistency of: offset_real = -wall_to_monotonic
* before modifying anything
*/
set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec,
-tk->wall_to_monotonic.tv_nsec);
WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp));
tk->wall_to_monotonic = wtm;
set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
/* Paired with READ_ONCE() in ktime_mono_to_any() */
WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp));
WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)));
}
static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
/* Paired with READ_ONCE() in ktime_mono_to_any() */
WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta));
/*
* Timespec representation for VDSO update to avoid 64bit division
* on every update.
*/
tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot);
}
/*
* tk_clock_read - atomic clocksource read() helper
*
* This helper is necessary to use in the read paths because, while the
* seqcount ensures we don't return a bad value while structures are updated,
* it doesn't protect from potential crashes. There is the possibility that
* the tkr's clocksource may change between the read reference, and the
* clock reference passed to the read function. This can cause crashes if
* the wrong clocksource is passed to the wrong read function.
* This isn't necessary to use when holding the tk_core.lock or doing
* a read of the fast-timekeeper tkrs (which is protected by its own locking
* and update logic).
*/
static inline u64 tk_clock_read(const struct tk_read_base *tkr)
{
struct clocksource *clock = READ_ONCE(tkr->clock);
return clock->read(clock);
}
/**
* tk_setup_internals - Set up internals to use clocksource clock.
*
* @tk: The target timekeeper to setup.
* @clock: Pointer to clocksource.
*
* Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
* pair and interval request.
*
* Unless you're the timekeeping code, you should not be using this!
*/
static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
{
u64 interval;
u64 tmp, ntpinterval;
struct clocksource *old_clock;
++tk->cs_was_changed_seq;
old_clock = tk->tkr_mono.clock;
tk->tkr_mono.clock = clock;
tk->tkr_mono.mask = clock->mask;
tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);
tk->tkr_raw.clock = clock;
tk->tkr_raw.mask = clock->mask;
tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
/* Do the ns -> cycle conversion first, using original mult */
tmp = NTP_INTERVAL_LENGTH;
tmp <<= clock->shift;
ntpinterval = tmp;
tmp += clock->mult/2;
do_div(tmp, clock->mult);
if (tmp == 0)
tmp = 1;
interval = (u64) tmp;
tk->cycle_interval = interval;
/* Go back from cycles -> shifted ns */
tk->xtime_interval = interval * clock->mult;
tk->xtime_remainder = ntpinterval - tk->xtime_interval;
tk->raw_interval = interval * clock->mult;
/* if changing clocks, convert xtime_nsec shift units */
if (old_clock) {
int shift_change = clock->shift - old_clock->shift;
if (shift_change < 0) {
tk->tkr_mono.xtime_nsec >>= -shift_change;
tk->tkr_raw.xtime_nsec >>= -shift_change;
} else {
tk->tkr_mono.xtime_nsec <<= shift_change;
tk->tkr_raw.xtime_nsec <<= shift_change;
}
}
tk->tkr_mono.shift = clock->shift;
tk->tkr_raw.shift = clock->shift;
tk->ntp_error = 0;
tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
tk->ntp_tick = ntpinterval << tk->ntp_error_shift;
/*
* The timekeeper keeps its own mult values for the currently
* active clocksource. These value will be adjusted via NTP
* to counteract clock drifting.
*/
tk->tkr_mono.mult = clock->mult;
tk->tkr_raw.mult = clock->mult;
tk->ntp_err_mult = 0;
tk->skip_second_overflow = 0;
}
/* Timekeeper helper functions. */
static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta)
{
return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift);
}
static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
{
/* Calculate the delta since the last update_wall_time() */
u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask;
/*
* This detects both negative motion and the case where the delta
* overflows the multiplication with tkr->mult.
*/
if (unlikely(delta > tkr->clock->max_cycles)) {
/*
* Handle clocksource inconsistency between CPUs to prevent
* time from going backwards by checking for the MSB of the
* mask being set in the delta.
*/
if (delta & ~(mask >> 1))
return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta);
}
return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift;
}
static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
{
return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr));
}
/**
* update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
* @tkr: Timekeeping readout base from which we take the update
* @tkf: Pointer to NMI safe timekeeper
*
* We want to use this from any context including NMI and tracing /
* instrumenting the timekeeping code itself.
*
* Employ the latch technique; see @write_seqcount_latch.
*
* So if a NMI hits the update of base[0] then it will use base[1]
* which is still consistent. In the worst case this can result is a
* slightly wrong timestamp (a few nanoseconds). See
* @ktime_get_mono_fast_ns.
*/
static void update_fast_timekeeper(const struct tk_read_base *tkr,
struct tk_fast *tkf)
{
struct tk_read_base *base = tkf->base;
/* Force readers off to base[1] */
write_seqcount_latch_begin(&tkf->seq);
/* Update base[0] */
memcpy(base, tkr, sizeof(*base));
/* Force readers back to base[0] */
write_seqcount_latch(&tkf->seq);
/* Update base[1] */
memcpy(base + 1, base, sizeof(*base));
write_seqcount_latch_end(&tkf->seq);
}
static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
{
struct tk_read_base *tkr;
unsigned int seq;
u64 now;
do {
seq = read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
now = ktime_to_ns(tkr->base);
now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq));
return now;
}
/**
* ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic
*
* This timestamp is not guaranteed to be monotonic across an update.
* The timestamp is calculated by:
*
* now = base_mono + clock_delta * slope
*
* So if the update lowers the slope, readers who are forced to the
* not yet updated second array are still using the old steeper slope.
*
* tmono
* ^
* | o n
* | o n
* | u
* | o
* |o
* |12345678---> reader order
*
* o = old slope
* u = update
* n = new slope
*
* So reader 6 will observe time going backwards versus reader 5.
*
* While other CPUs are likely to be able to observe that, the only way
* for a CPU local observation is when an NMI hits in the middle of
* the update. Timestamps taken from that NMI context might be ahead
* of the following timestamps. Callers need to be aware of that and
* deal with it.
*/
u64 notrace ktime_get_mono_fast_ns(void)
{ return __ktime_get_fast_ns(&tk_fast_mono);
}
EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
/**
* ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw
*
* Contrary to ktime_get_mono_fast_ns() this is always correct because the
* conversion factor is not affected by NTP/PTP correction.
*/
u64 notrace ktime_get_raw_fast_ns(void)
{
return __ktime_get_fast_ns(&tk_fast_raw);
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
/**
* ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
*
* To keep it NMI safe since we're accessing from tracing, we're not using a
* separate timekeeper with updates to monotonic clock and boot offset
* protected with seqcounts. This has the following minor side effects:
*
* (1) Its possible that a timestamp be taken after the boot offset is updated
* but before the timekeeper is updated. If this happens, the new boot offset
* is added to the old timekeeping making the clock appear to update slightly
* earlier:
* CPU 0 CPU 1
* timekeeping_inject_sleeptime64()
* __timekeeping_inject_sleeptime(tk, delta);
* timestamp();
* timekeeping_update_staged(tkd, TK_CLEAR_NTP...);
*
* (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
* partially updated. Since the tk->offs_boot update is a rare event, this
* should be a rare occurrence which postprocessing should be able to handle.
*
* The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns()
* apply as well.
*/
u64 notrace ktime_get_boot_fast_ns(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot)));
}
EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
/**
* ktime_get_tai_fast_ns - NMI safe and fast access to tai clock.
*
* The same limitations as described for ktime_get_boot_fast_ns() apply. The
* mono time and the TAI offset are not read atomically which may yield wrong
* readouts. However, an update of the TAI offset is an rare event e.g., caused
* by settime or adjtimex with an offset. The user of this function has to deal
* with the possibility of wrong timestamps in post processing.
*/
u64 notrace ktime_get_tai_fast_ns(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai)));
}
EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns);
/**
* ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime.
*
* See ktime_get_mono_fast_ns() for documentation of the time stamp ordering.
*/
u64 ktime_get_real_fast_ns(void)
{
struct tk_fast *tkf = &tk_fast_mono;
struct tk_read_base *tkr;
u64 baser, delta;
unsigned int seq;
do {
seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
baser = ktime_to_ns(tkr->base_real);
delta = timekeeping_get_ns(tkr);
} while (raw_read_seqcount_latch_retry(&tkf->seq, seq));
return baser + delta;
}
EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
/**
* halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
* @tk: Timekeeper to snapshot.
*
* It generally is unsafe to access the clocksource after timekeeping has been
* suspended, so take a snapshot of the readout base of @tk and use it as the
* fast timekeeper's readout base while suspended. It will return the same
* number of cycles every time until timekeeping is resumed at which time the
* proper readout base for the fast timekeeper will be restored automatically.
*/
static void halt_fast_timekeeper(const struct timekeeper *tk)
{
static struct tk_read_base tkr_dummy;
const struct tk_read_base *tkr = &tk->tkr_mono;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
cycles_at_suspend = tk_clock_read(tkr);
tkr_dummy.clock = &dummy_clock;
tkr_dummy.base_real = tkr->base + tk->offs_real;
update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
tkr = &tk->tkr_raw;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
tkr_dummy.clock = &dummy_clock;
update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
}
static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
{
raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
}
/**
* pvclock_gtod_register_notifier - register a pvclock timedata update listener
* @nb: Pointer to the notifier block to register
*/
int pvclock_gtod_register_notifier(struct notifier_block *nb)
{
struct timekeeper *tk = &tk_core.timekeeper;
int ret;
guard(raw_spinlock_irqsave)(&tk_core.lock);
ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
update_pvclock_gtod(tk, true);
return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
/**
* pvclock_gtod_unregister_notifier - unregister a pvclock
* timedata update listener
* @nb: Pointer to the notifier block to unregister
*/
int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
{
guard(raw_spinlock_irqsave)(&tk_core.lock);
return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
/*
* tk_update_leap_state - helper to update the next_leap_ktime
*/
static inline void tk_update_leap_state(struct timekeeper *tk)
{
tk->next_leap_ktime = ntp_get_next_leap();
if (tk->next_leap_ktime != KTIME_MAX)
/* Convert to monotonic time */
tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
}
/*
* Leap state update for both shadow and the real timekeeper
* Separate to spare a full memcpy() of the timekeeper.
*/
static void tk_update_leap_state_all(struct tk_data *tkd)
{
write_seqcount_begin(&tkd->seq);
tk_update_leap_state(&tkd->shadow_timekeeper);
tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime;
write_seqcount_end(&tkd->seq);
}
/*
* Update the ktime_t based scalar nsec members of the timekeeper
*/
static inline void tk_update_ktime_data(struct timekeeper *tk)
{
u64 seconds;
u32 nsec;
/*
* The xtime based monotonic readout is:
* nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now();
* The ktime based monotonic readout is:
* nsec = base_mono + now();
* ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec
*/
seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
nsec = (u32) tk->wall_to_monotonic.tv_nsec;
tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
/*
* The sum of the nanoseconds portions of xtime and
* wall_to_monotonic can be greater/equal one second. Take
* this into account before updating tk->ktime_sec.
*/
nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
if (nsec >= NSEC_PER_SEC)
seconds++;
tk->ktime_sec = seconds;
/* Update the monotonic raw base */
tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC);
}
/*
* Restore the shadow timekeeper from the real timekeeper.
*/
static void timekeeping_restore_shadow(struct tk_data *tkd)
{
lockdep_assert_held(&tkd->lock);
memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper));
}
static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action)
{
struct timekeeper *tk = &tk_core.shadow_timekeeper;
lockdep_assert_held(&tkd->lock);
/*
* Block out readers before running the updates below because that
* updates VDSO and other time related infrastructure. Not blocking
* the readers might let a reader see time going backwards when
* reading from the VDSO after the VDSO update and then reading in
* the kernel from the timekeeper before that got updated.
*/
write_seqcount_begin(&tkd->seq);
if (action & TK_CLEAR_NTP) {
tk->ntp_error = 0;
ntp_clear();
}
tk_update_leap_state(tk);
tk_update_ktime_data(tk);
update_vsyscall(tk);
update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real;
update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw);
if (action & TK_CLOCK_WAS_SET)
tk->clock_was_set_seq++;
/*
* Update the real timekeeper.
*
* We could avoid this memcpy() by switching pointers, but that has
* the downside that the reader side does not longer benefit from
* the cacheline optimized data layout of the timekeeper and requires
* another indirection.
*/
memcpy(&tkd->timekeeper, tk, sizeof(*tk));
write_seqcount_end(&tkd->seq);
}
/**
* timekeeping_forward_now - update clock to the current time
* @tk: Pointer to the timekeeper to update
*
* Forward the current clock to update its state since the last call to
* update_wall_time(). This is useful before significant clock changes,
* as it avoids having to deal with this time offset explicitly.
*/
static void timekeeping_forward_now(struct timekeeper *tk)
{
u64 cycle_now, delta;
cycle_now = tk_clock_read(&tk->tkr_mono);
delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
tk->tkr_mono.cycle_last = cycle_now;
tk->tkr_raw.cycle_last = cycle_now;
while (delta > 0) {
u64 max = tk->tkr_mono.clock->max_cycles;
u64 incr = delta < max ? delta : max;
tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult;
tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult;
tk_normalize_xtime(tk);
delta -= incr;
}
}
/**
* ktime_get_real_ts64 - Returns the time of day in a timespec64.
* @ts: pointer to the timespec to be set
*
* Returns the time of day in a timespec64 (WARN if suspended).
*/
void ktime_get_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
ts->tv_sec = tk->xtime_sec;
nsecs = timekeeping_get_ns(&tk->tkr_mono);
} while (read_seqcount_retry(&tk_core.seq, seq));
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(ktime_get_real_ts64);
ktime_t ktime_get(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base;
u64 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
base = tk->tkr_mono.base;
nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get);
u32 ktime_get_resolution_ns(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
u32 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift;
} while (read_seqcount_retry(&tk_core.seq, seq));
return nsecs;
}
EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
static ktime_t *offsets[TK_OFFS_MAX] = {
[TK_OFFS_REAL] = &tk_core.timekeeper.offs_real,
[TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot,
[TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai,
};
ktime_t ktime_get_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base, *offset = offsets[offs];
u64 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
nsecs = timekeeping_get_ns(&tk->tkr_mono);
} while (read_seqcount_retry(&tk_core.seq, seq));
return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get_with_offset);
ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base, *offset = offsets[offs];
u64 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
} while (read_seqcount_retry(&tk_core.seq, seq));
return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
/**
* ktime_mono_to_any() - convert monotonic time to any other time
* @tmono: time to convert.
* @offs: which offset to use
*/
ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
{
ktime_t *offset = offsets[offs];
unsigned int seq;
ktime_t tconv;
if (IS_ENABLED(CONFIG_64BIT)) {
/*
* Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and
* tk_update_sleep_time().
*/
return ktime_add(tmono, READ_ONCE(*offset));
}
do {
seq = read_seqcount_begin(&tk_core.seq);
tconv = ktime_add(tmono, *offset);
} while (read_seqcount_retry(&tk_core.seq, seq));
return tconv;
}
EXPORT_SYMBOL_GPL(ktime_mono_to_any);
/**
* ktime_get_raw - Returns the raw monotonic time in ktime_t format
*/
ktime_t ktime_get_raw(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base;
u64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
base = tk->tkr_raw.base;
nsecs = timekeeping_get_ns(&tk->tkr_raw);
} while (read_seqcount_retry(&tk_core.seq, seq));
return ktime_add_ns(base, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get_raw);
/**
* ktime_get_ts64 - get the monotonic clock in timespec64 format
* @ts: pointer to timespec variable
*
* The function calculates the monotonic clock from the realtime
* clock and the wall_to_monotonic offset and stores the result
* in normalized timespec64 format in the variable pointed to by @ts.
*/
void ktime_get_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
struct timespec64 tomono;
unsigned int seq;
u64 nsec;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
ts->tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(&tk->tkr_mono);
tomono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
ts->tv_sec += tomono.tv_sec;
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);
/**
* ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
*
* Returns the seconds portion of CLOCK_MONOTONIC with a single non
* serialized read. tk->ktime_sec is of type 'unsigned long' so this
* works on both 32 and 64 bit systems. On 32 bit systems the readout
* covers ~136 years of uptime which should be enough to prevent
* premature wrap arounds.
*/
time64_t ktime_get_seconds(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
WARN_ON(timekeeping_suspended);
return tk->ktime_sec;
}
EXPORT_SYMBOL_GPL(ktime_get_seconds);
/**
* ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME
*
* Returns the wall clock seconds since 1970.
*
* For 64bit systems the fast access to tk->xtime_sec is preserved. On
* 32bit systems the access must be protected with the sequence
* counter to provide "atomic" access to the 64bit tk->xtime_sec
* value.
*/
time64_t ktime_get_real_seconds(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
time64_t seconds;
unsigned int seq;
if (IS_ENABLED(CONFIG_64BIT))
return tk->xtime_sec;
do {
seq = read_seqcount_begin(&tk_core.seq);
seconds = tk->xtime_sec;
} while (read_seqcount_retry(&tk_core.seq, seq));
return seconds;
}
EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
/**
* __ktime_get_real_seconds - The same as ktime_get_real_seconds
* but without the sequence counter protect. This internal function
* is called just when timekeeping lock is already held.
*/
noinstr time64_t __ktime_get_real_seconds(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
return tk->xtime_sec;
}
/**
* ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
* @systime_snapshot: pointer to struct receiving the system time snapshot
*/
void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base_raw;
ktime_t base_real;
ktime_t base_boot;
u64 nsec_raw;
u64 nsec_real;
u64 now;
WARN_ON_ONCE(timekeeping_suspended);
do {
seq = read_seqcount_begin(&tk_core.seq);
now = tk_clock_read(&tk->tkr_mono);
systime_snapshot->cs_id = tk->tkr_mono.clock->id;
systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
base_real = ktime_add(tk->tkr_mono.base,
tk_core.timekeeper.offs_real);
base_boot = ktime_add(tk->tkr_mono.base,
tk_core.timekeeper.offs_boot);
base_raw = tk->tkr_raw.base;
nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq));
systime_snapshot->cycles = now;
systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real);
systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
}
EXPORT_SYMBOL_GPL(ktime_get_snapshot);
/* Scale base by mult/div checking for overflow */
static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
{
u64 tmp, rem;
tmp = div64_u64_rem(*base, div, &rem);
if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) ||
((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
return -EOVERFLOW;
tmp *= mult;
rem = div64_u64(rem * mult, div);
*base = tmp + rem;
return 0;
}
/**
* adjust_historical_crosststamp - adjust crosstimestamp previous to current interval
* @history: Snapshot representing start of history
* @partial_history_cycles: Cycle offset into history (fractional part)
* @total_history_cycles: Total history length in cycles
* @discontinuity: True indicates clock was set on history period
* @ts: Cross timestamp that should be adjusted using
* partial/total ratio
*
* Helper function used by get_device_system_crosststamp() to correct the
* crosstimestamp corresponding to the start of the current interval to the
* system counter value (timestamp point) provided by the driver. The
* total_history_* quantities are the total history starting at the provided
* reference point and ending at the start of the current interval. The cycle
* count between the driver timestamp point and the start of the current
* interval is partial_history_cycles.
*/
static int adjust_historical_crosststamp(struct system_time_snapshot *history,
u64 partial_history_cycles,
u64 total_history_cycles,
bool discontinuity,
struct system_device_crosststamp *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
u64 corr_raw, corr_real;
bool interp_forward;
int ret;
if (total_history_cycles == 0 || partial_history_cycles == 0)
return 0;
/* Interpolate shortest distance from beginning or end of history */
interp_forward = partial_history_cycles > total_history_cycles / 2;
partial_history_cycles = interp_forward ?
total_history_cycles - partial_history_cycles :
partial_history_cycles;
/*
* Scale the monotonic raw time delta by:
* partial_history_cycles / total_history_cycles
*/
corr_raw = (u64)ktime_to_ns(
ktime_sub(ts->sys_monoraw, history->raw));
ret = scale64_check_overflow(partial_history_cycles,
total_history_cycles, &corr_raw);
if (ret)
return ret;
/*
* If there is a discontinuity in the history, scale monotonic raw
* correction by:
* mult(real)/mult(raw) yielding the realtime correction
* Otherwise, calculate the realtime correction similar to monotonic
* raw calculation
*/
if (discontinuity) {
corr_real = mul_u64_u32_div
(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
} else {
corr_real = (u64)ktime_to_ns(
ktime_sub(ts->sys_realtime, history->real));
ret = scale64_check_overflow(partial_history_cycles,
total_history_cycles, &corr_real);
if (ret)
return ret;
}
/* Fixup monotonic raw and real time time values */
if (interp_forward) {
ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw);
ts->sys_realtime = ktime_add_ns(history->real, corr_real);
} else {
ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw);
ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real);
}
return 0;
}
/*
* timestamp_in_interval - true if ts is chronologically in [start, end]
*
* True if ts occurs chronologically at or after start, and before or at end.
*/
static bool timestamp_in_interval(u64 start, u64 end, u64 ts)
{
if (ts >= start && ts <= end)
return true;
if (start > end && (ts >= start || ts <= end))
return true;
return false;
}
static bool convert_clock(u64 *val, u32 numerator, u32 denominator)
{
u64 rem, res;
if (!numerator || !denominator)
return false;
res = div64_u64_rem(*val, denominator, &rem) * numerator;
*val = res + div_u64(rem * numerator, denominator);
return true;
}
static bool convert_base_to_cs(struct system_counterval_t *scv)
{
struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock;
struct clocksource_base *base;
u32 num, den;
/* The timestamp was taken from the time keeper clock source */
if (cs->id == scv->cs_id)
return true;
/*
* Check whether cs_id matches the base clock. Prevent the compiler from
* re-evaluating @base as the clocksource might change concurrently.
*/
base = READ_ONCE(cs->base);
if (!base || base->id != scv->cs_id)
return false;
num = scv->use_nsecs ? cs->freq_khz : base->numerator;
den = scv->use_nsecs ? USEC_PER_SEC : base->denominator;
if (!convert_clock(&scv->cycles, num, den))
return false;
scv->cycles += base->offset;
return true;
}
static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id)
{
struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock;
struct clocksource_base *base;
/*
* Check whether base_id matches the base clock. Prevent the compiler from
* re-evaluating @base as the clocksource might change concurrently.
*/
base = READ_ONCE(cs->base);
if (!base || base->id != base_id)
return false;
*cycles -= base->offset;
if (!convert_clock(cycles, base->denominator, base->numerator))
return false;
return true;
}
static bool convert_ns_to_cs(u64 *delta)
{
struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono;
if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta))
return false;
*delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult);
return true;
}
/**
* ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp
* @treal: CLOCK_REALTIME timestamp to convert
* @base_id: base clocksource id
* @cycles: pointer to store the converted base clock timestamp
*
* Converts a supplied, future realtime clock value to the corresponding base clock value.
*
* Return: true if the conversion is successful, false otherwise.
*/
bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
u64 delta;
do {
seq = read_seqcount_begin(&tk_core.seq);
if ((u64)treal < tk->tkr_mono.base_real)
return false;
delta = (u64)treal - tk->tkr_mono.base_real;
if (!convert_ns_to_cs(&delta))
return false;
*cycles = tk->tkr_mono.cycle_last + delta;
if (!convert_cs_to_base(cycles, base_id))
return false;
} while (read_seqcount_retry(&tk_core.seq, seq));
return true;
}
EXPORT_SYMBOL_GPL(ktime_real_to_base_clock);
/**
* get_device_system_crosststamp - Synchronously capture system/device timestamp
* @get_time_fn: Callback to get simultaneous device time and
* system counter from the device driver
* @ctx: Context passed to get_time_fn()
* @history_begin: Historical reference point used to interpolate system
* time when counter provided by the driver is before the current interval
* @xtstamp: Receives simultaneously captured system and device time
*
* Reads a timestamp from a device and correlates it to system time
*/
int get_device_system_crosststamp(int (*get_time_fn)
(ktime_t *device_time,
struct system_counterval_t *sys_counterval,
void *ctx),
void *ctx,
struct system_time_snapshot *history_begin,
struct system_device_crosststamp *xtstamp)
{
struct system_counterval_t system_counterval;
struct timekeeper *tk = &tk_core.timekeeper;
u64 cycles, now, interval_start;
unsigned int clock_was_set_seq = 0;
ktime_t base_real, base_raw;
u64 nsec_real, nsec_raw;
u8 cs_was_changed_seq;
unsigned int seq;
bool do_interp;
int ret;
do {
seq = read_seqcount_begin(&tk_core.seq);
/*
* Try to synchronously capture device time and a system
* counter value calling back into the device driver
*/
ret = get_time_fn(&xtstamp->device, &system_counterval, ctx);
if (ret)
return ret;
/*
* Verify that the clocksource ID associated with the captured
* system counter value is the same as for the currently
* installed timekeeper clocksource
*/
if (system_counterval.cs_id == CSID_GENERIC ||
!convert_base_to_cs(&system_counterval))
return -ENODEV;
cycles = system_counterval.cycles;
/*
* Check whether the system counter value provided by the
* device driver is on the current timekeeping interval.
*/
now = tk_clock_read(&tk->tkr_mono);
interval_start = tk->tkr_mono.cycle_last;
if (!timestamp_in_interval(interval_start, now, cycles)) {
clock_was_set_seq = tk->clock_was_set_seq;
cs_was_changed_seq = tk->cs_was_changed_seq;
cycles = interval_start;
do_interp = true;
} else {
do_interp = false;
}
base_real = ktime_add(tk->tkr_mono.base,
tk_core.timekeeper.offs_real);
base_raw = tk->tkr_raw.base;
nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles);
nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles);
} while (read_seqcount_retry(&tk_core.seq, seq));
xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw);
/*
* Interpolate if necessary, adjusting back from the start of the
* current interval
*/
if (do_interp) {
u64 partial_history_cycles, total_history_cycles;
bool discontinuity;
/*
* Check that the counter value is not before the provided
* history reference and that the history doesn't cross a
* clocksource change
*/
if (!history_begin ||
!timestamp_in_interval(history_begin->cycles,
cycles, system_counterval.cycles) ||
history_begin->cs_was_changed_seq != cs_was_changed_seq)
return -EINVAL;
partial_history_cycles = cycles - system_counterval.cycles;
total_history_cycles = cycles - history_begin->cycles;
discontinuity =
history_begin->clock_was_set_seq != clock_was_set_seq;
ret = adjust_historical_crosststamp(history_begin,
partial_history_cycles,
total_history_cycles,
discontinuity, xtstamp);
if (ret)
return ret;
}
return 0;
}
EXPORT_SYMBOL_GPL(get_device_system_crosststamp);
/**
* timekeeping_clocksource_has_base - Check whether the current clocksource
* is based on given a base clock
* @id: base clocksource ID
*
* Note: The return value is a snapshot which can become invalid right
* after the function returns.
*
* Return: true if the timekeeper clocksource has a base clock with @id,
* false otherwise
*/
bool timekeeping_clocksource_has_base(enum clocksource_ids id)
{
/*
* This is a snapshot, so no point in using the sequence
* count. Just prevent the compiler from re-evaluating @base as the
* clocksource might change concurrently.
*/
struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base);
return base ? base->id == id : false;
}
EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base);
/**
* do_settimeofday64 - Sets the time of day.
* @ts: pointer to the timespec64 variable containing the new time
*
* Sets the time of day to the new time and update NTP and notify hrtimers
*/
int do_settimeofday64(const struct timespec64 *ts)
{
struct timespec64 ts_delta, xt;
if (!timespec64_valid_settod(ts))
return -EINVAL;
scoped_guard (raw_spinlock_irqsave, &tk_core.lock) {
struct timekeeper *tks = &tk_core.shadow_timekeeper;
timekeeping_forward_now(tks);
xt = tk_xtime(tks);
ts_delta = timespec64_sub(*ts, xt);
if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) {
timekeeping_restore_shadow(&tk_core);
return -EINVAL;
}
tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta));
tk_set_xtime(tks, ts);
timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL);
}
/* Signal hrtimers about time change */
clock_was_set(CLOCK_SET_WALL);
audit_tk_injoffset(ts_delta);
add_device_randomness(ts, sizeof(*ts));
return 0;
}
EXPORT_SYMBOL(do_settimeofday64);
/**
* timekeeping_inject_offset - Adds or subtracts from the current time.
* @ts: Pointer to the timespec variable containing the offset
*
* Adds or subtracts an offset value from the current time.
*/
static int timekeeping_inject_offset(const struct timespec64 *ts)
{
if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
scoped_guard (raw_spinlock_irqsave, &tk_core.lock) {
struct timekeeper *tks = &tk_core.shadow_timekeeper;
struct timespec64 tmp;
timekeeping_forward_now(tks);
/* Make sure the proposed value is valid */
tmp = timespec64_add(tk_xtime(tks), *ts);
if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 ||
!timespec64_valid_settod(&tmp)) {
timekeeping_restore_shadow(&tk_core);
return -EINVAL;
}
tk_xtime_add(tks, ts);
tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts));
timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL);
}
/* Signal hrtimers about time change */
clock_was_set(CLOCK_SET_WALL);
return 0;
}
/*
* Indicates if there is an offset between the system clock and the hardware
* clock/persistent clock/rtc.
*/
int persistent_clock_is_local;
/*
* Adjust the time obtained from the CMOS to be UTC time instead of
* local time.
*
* This is ugly, but preferable to the alternatives. Otherwise we
* would either need to write a program to do it in /etc/rc (and risk
* confusion if the program gets run more than once; it would also be
* hard to make the program warp the clock precisely n hours) or
* compile in the timezone information into the kernel. Bad, bad....
*
* - TYT, 1992-01-01
*
* The best thing to do is to keep the CMOS clock in universal time (UTC)
* as real UNIX machines always do it. This avoids all headaches about
* daylight saving times and warping kernel clocks.
*/
void timekeeping_warp_clock(void)
{
if (sys_tz.tz_minuteswest != 0) {
struct timespec64 adjust;
persistent_clock_is_local = 1;
adjust.tv_sec = sys_tz.tz_minuteswest * 60;
adjust.tv_nsec = 0;
timekeeping_inject_offset(&adjust);
}
}
/*
* __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic
*/
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
tk->tai_offset = tai_offset;
tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}
/*
* change_clocksource - Swaps clocksources if a new one is available
*
* Accumulates current time interval and initializes new clocksource
*/
static int change_clocksource(void *data)
{
struct clocksource *new = data, *old = NULL;
/*
* If the clocksource is in a module, get a module reference.
* Succeeds for built-in code (owner == NULL) as well. Abort if the
* reference can't be acquired.
*/
if (!try_module_get(new->owner))
return 0;
/* Abort if the device can't be enabled */
if (new->enable && new->enable(new) != 0) {
module_put(new->owner);
return 0;
}
scoped_guard (raw_spinlock_irqsave, &tk_core.lock) {
struct timekeeper *tks = &tk_core.shadow_timekeeper;
timekeeping_forward_now(tks);
old = tks->tkr_mono.clock;
tk_setup_internals(tks, new);
timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL);
}
if (old) {
if (old->disable)
old->disable(old);
module_put(old->owner);
}
return 0;
}
/**
* timekeeping_notify - Install a new clock source
* @clock: pointer to the clock source
*
* This function is called from clocksource.c after a new, better clock
* source has been registered. The caller holds the clocksource_mutex.
*/
int timekeeping_notify(struct clocksource *clock)
{
struct timekeeper *tk = &tk_core.timekeeper;
if (tk->tkr_mono.clock == clock)
return 0;
stop_machine(change_clocksource, clock, NULL);
tick_clock_notify();
return tk->tkr_mono.clock == clock ? 0 : -1;
}
/**
* ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec
* @ts: pointer to the timespec64 to be set
*
* Returns the raw monotonic time (completely un-modified by ntp)
*/
void ktime_get_raw_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
u64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
ts->tv_sec = tk->raw_sec;
nsecs = timekeeping_get_ns(&tk->tkr_raw);
} while (read_seqcount_retry(&tk_core.seq, seq));
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(ktime_get_raw_ts64);
/**
* timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
*/
int timekeeping_valid_for_hres(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
int ret;
do {
seq = read_seqcount_begin(&tk_core.seq);
ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
} while (read_seqcount_retry(&tk_core.seq, seq));
return ret;
}
/**
* timekeeping_max_deferment - Returns max time the clocksource can be deferred
*/
u64 timekeeping_max_deferment(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
u64 ret;
do {
seq = read_seqcount_begin(&tk_core.seq);
ret = tk->tkr_mono.clock->max_idle_ns;
} while (read_seqcount_retry(&tk_core.seq, seq));
return ret;
}
/**
* read_persistent_clock64 - Return time from the persistent clock.
* @ts: Pointer to the storage for the readout value
*
* Weak dummy function for arches that do not yet support it.
* Reads the time from the battery backed persistent clock.
* Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
*
* XXX - Do be sure to remove it once all arches implement it.
*/
void __weak read_persistent_clock64(struct timespec64 *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
}
/**
* read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
* from the boot.
* @wall_time: current time as returned by persistent clock
* @boot_offset: offset that is defined as wall_time - boot_time
*
* Weak dummy function for arches that do not yet support it.
*
* The default function calculates offset based on the current value of
* local_clock(). This way architectures that support sched_clock() but don't
* support dedicated boot time clock will provide the best estimate of the
* boot time.
*/
void __weak __init
read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
struct timespec64 *boot_offset)
{
read_persistent_clock64(wall_time);
*boot_offset = ns_to_timespec64(local_clock());
}
static __init void tkd_basic_setup(struct tk_data *tkd)
{
raw_spin_lock_init(&tkd->lock);
seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock);
}
/*
* Flag reflecting whether timekeeping_resume() has injected sleeptime.
*
* The flag starts of false and is only set when a suspend reaches
* timekeeping_suspend(), timekeeping_resume() sets it to false when the
* timekeeper clocksource is not stopping across suspend and has been
* used to update sleep time. If the timekeeper clocksource has stopped
* then the flag stays true and is used by the RTC resume code to decide
* whether sleeptime must be injected and if so the flag gets false then.
*
* If a suspend fails before reaching timekeeping_resume() then the flag
* stays false and prevents erroneous sleeptime injection.
*/
static bool suspend_timing_needed;
/* Flag for if there is a persistent clock on this platform */
static bool persistent_clock_exists;
/*
* timekeeping_init - Initializes the clocksource and common timekeeping values
*/
void __init timekeeping_init(void)
{
struct timespec64 wall_time, boot_offset, wall_to_mono;
struct timekeeper *tks = &tk_core.shadow_timekeeper;
struct clocksource *clock;
tkd_basic_setup(&tk_core);
read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
if (timespec64_valid_settod(&wall_time) &&
timespec64_to_ns(&wall_time) > 0) {
persistent_clock_exists = true;
} else if (timespec64_to_ns(&wall_time) != 0) {
pr_warn("Persistent clock returned invalid value");
wall_time = (struct timespec64){0};
}
if (timespec64_compare(&wall_time, &boot_offset) < 0)
boot_offset = (struct timespec64){0};
/*
* We want set wall_to_mono, so the following is true:
* wall time + wall_to_mono = boot time
*/
wall_to_mono = timespec64_sub(boot_offset, wall_time);
guard(raw_spinlock_irqsave)(&tk_core.lock);
ntp_init();
clock = clocksource_default_clock();
if (clock->enable)
clock->enable(clock);
tk_setup_internals(tks, clock);
tk_set_xtime(tks, &wall_time);
tks->raw_sec = 0;
tk_set_wall_to_mono(tks, wall_to_mono);
timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET);
}
/* time in seconds when suspend began for persistent clock */
static struct timespec64 timekeeping_suspend_time;
/**
* __timekeeping_inject_sleeptime - Internal function to add sleep interval
* @tk: Pointer to the timekeeper to be updated
* @delta: Pointer to the delta value in timespec64 format
*
* Takes a timespec offset measuring a suspend interval and properly
* adds the sleep offset to the timekeeping variables.
*/
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
const struct timespec64 *delta)
{
if (!timespec64_valid_strict(delta)) {
printk_deferred(KERN_WARNING
"__timekeeping_inject_sleeptime: Invalid "
"sleep delta value!\n");
return;
}
tk_xtime_add(tk, delta);
tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
tk_debug_account_sleep_time(delta);
}
#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
/*
* We have three kinds of time sources to use for sleep time
* injection, the preference order is:
* 1) non-stop clocksource
* 2) persistent clock (ie: RTC accessible when irqs are off)
* 3) RTC
*
* 1) and 2) are used by timekeeping, 3) by RTC subsystem.
* If system has neither 1) nor 2), 3) will be used finally.
*
*
* If timekeeping has injected sleeptime via either 1) or 2),
* 3) becomes needless, so in this case we don't need to call
* rtc_resume(), and this is what timekeeping_rtc_skipresume()
* means.
*/
bool timekeeping_rtc_skipresume(void)
{
return !suspend_timing_needed;
}
/*
* 1) can be determined whether to use or not only when doing
* timekeeping_resume() which is invoked after rtc_suspend(),
* so we can't skip rtc_suspend() surely if system has 1).
*
* But if system has 2), 2) will definitely be used, so in this
* case we don't need to call rtc_suspend(), and this is what
* timekeeping_rtc_skipsuspend() means.
*/
bool timekeeping_rtc_skipsuspend(void)
{
return persistent_clock_exists;
}
/**
* timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values
* @delta: pointer to a timespec64 delta value
*
* This hook is for architectures that cannot support read_persistent_clock64
* because their RTC/persistent clock is only accessible when irqs are enabled.
* and also don't have an effective nonstop clocksource.
*
* This function should only be called by rtc_resume(), and allows
* a suspend offset to be injected into the timekeeping values.
*/
void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
{
scoped_guard(raw_spinlock_irqsave, &tk_core.lock) {
struct timekeeper *tks = &tk_core.shadow_timekeeper;
suspend_timing_needed = false;
timekeeping_forward_now(tks);
__timekeeping_inject_sleeptime(tks, delta);
timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL);
}
/* Signal hrtimers about time change */
clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT);
}
#endif
/**
* timekeeping_resume - Resumes the generic timekeeping subsystem.
*/
void timekeeping_resume(void)
{
struct timekeeper *tks = &tk_core.shadow_timekeeper;
struct clocksource *clock = tks->tkr_mono.clock;
struct timespec64 ts_new, ts_delta;
bool inject_sleeptime = false;
u64 cycle_now, nsec;
unsigned long flags;
read_persistent_clock64(&ts_new);
clockevents_resume();
clocksource_resume();
raw_spin_lock_irqsave(&tk_core.lock, flags);
/*
* After system resumes, we need to calculate the suspended time and
* compensate it for the OS time. There are 3 sources that could be
* used: Nonstop clocksource during suspend, persistent clock and rtc
* device.
*
* One specific platform may have 1 or 2 or all of them, and the
* preference will be:
* suspend-nonstop clocksource -> persistent clock -> rtc
* The less preferred source will only be tried if there is no better
* usable source. The rtc part is handled separately in rtc core code.
*/
cycle_now = tk_clock_read(&tks->tkr_mono);
nsec = clocksource_stop_suspend_timing(clock, cycle_now);
if (nsec > 0) {
ts_delta = ns_to_timespec64(nsec);
inject_sleeptime = true;
} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
inject_sleeptime = true;
}
if (inject_sleeptime) {
suspend_timing_needed = false;
__timekeeping_inject_sleeptime(tks, &ts_delta);
}
/* Re-base the last cycle value */
tks->tkr_mono.cycle_last = cycle_now;
tks->tkr_raw.cycle_last = cycle_now;
tks->ntp_error = 0;
timekeeping_suspended = 0;
timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET);
raw_spin_unlock_irqrestore(&tk_core.lock, flags);
touch_softlockup_watchdog();
/* Resume the clockevent device(s) and hrtimers */
tick_resume();
/* Notify timerfd as resume is equivalent to clock_was_set() */
timerfd_resume();
}
int timekeeping_suspend(void)
{
struct timekeeper *tks = &tk_core.shadow_timekeeper;
struct timespec64 delta, delta_delta;
static struct timespec64 old_delta;
struct clocksource *curr_clock;
unsigned long flags;
u64 cycle_now;
read_persistent_clock64(&timekeeping_suspend_time);
/*
* On some systems the persistent_clock can not be detected at
* timekeeping_init by its return value, so if we see a valid
* value returned, update the persistent_clock_exists flag.
*/
if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
persistent_clock_exists = true;
suspend_timing_needed = true;
raw_spin_lock_irqsave(&tk_core.lock, flags);
timekeeping_forward_now(tks);
timekeeping_suspended = 1;
/*
* Since we've called forward_now, cycle_last stores the value
* just read from the current clocksource. Save this to potentially
* use in suspend timing.
*/
curr_clock = tks->tkr_mono.clock;
cycle_now = tks->tkr_mono.cycle_last;
clocksource_start_suspend_timing(curr_clock, cycle_now);
if (persistent_clock_exists) {
/*
* To avoid drift caused by repeated suspend/resumes,
* which each can add ~1 second drift error,
* try to compensate so the difference in system time
* and persistent_clock time stays close to constant.
*/
delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time);
delta_delta = timespec64_sub(delta, old_delta);
if (abs(delta_delta.tv_sec) >= 2) {
/*
* if delta_delta is too large, assume time correction
* has occurred and set old_delta to the current delta.
*/
old_delta = delta;
} else {
/* Otherwise try to adjust old_system to compensate */
timekeeping_suspend_time =
timespec64_add(timekeeping_suspend_time, delta_delta);
}
}
timekeeping_update_from_shadow(&tk_core, 0);
halt_fast_timekeeper(tks);
raw_spin_unlock_irqrestore(&tk_core.lock, flags);
tick_suspend();
clocksource_suspend();
clockevents_suspend();
return 0;
}
/* sysfs resume/suspend bits for timekeeping */
static struct syscore_ops timekeeping_syscore_ops = {
.resume = timekeeping_resume,
.suspend = timekeeping_suspend,
};
static int __init timekeeping_init_ops(void)
{
register_syscore_ops(&timekeeping_syscore_ops);
return 0;
}
device_initcall(timekeeping_init_ops);
/*
* Apply a multiplier adjustment to the timekeeper
*/
static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
s64 offset,
s32 mult_adj)
{
s64 interval = tk->cycle_interval;
if (mult_adj == 0) {
return;
} else if (mult_adj == -1) {
interval = -interval;
offset = -offset;
} else if (mult_adj != 1) {
interval *= mult_adj;
offset *= mult_adj;
}
/*
* So the following can be confusing.
*
* To keep things simple, lets assume mult_adj == 1 for now.
*
* When mult_adj != 1, remember that the interval and offset values
* have been appropriately scaled so the math is the same.
*
* The basic idea here is that we're increasing the multiplier
* by one, this causes the xtime_interval to be incremented by
* one cycle_interval. This is because:
* xtime_interval = cycle_interval * mult
* So if mult is being incremented by one:
* xtime_interval = cycle_interval * (mult + 1)
* Its the same as:
* xtime_interval = (cycle_interval * mult) + cycle_interval
* Which can be shortened to:
* xtime_interval += cycle_interval
*
* So offset stores the non-accumulated cycles. Thus the current
* time (in shifted nanoseconds) is:
* now = (offset * adj) + xtime_nsec
* Now, even though we're adjusting the clock frequency, we have
* to keep time consistent. In other words, we can't jump back
* in time, and we also want to avoid jumping forward in time.
*
* So given the same offset value, we need the time to be the same
* both before and after the freq adjustment.
* now = (offset * adj_1) + xtime_nsec_1
* now = (offset * adj_2) + xtime_nsec_2
* So:
* (offset * adj_1) + xtime_nsec_1 =
* (offset * adj_2) + xtime_nsec_2
* And we know:
* adj_2 = adj_1 + 1
* So:
* (offset * adj_1) + xtime_nsec_1 =
* (offset * (adj_1+1)) + xtime_nsec_2
* (offset * adj_1) + xtime_nsec_1 =
* (offset * adj_1) + offset + xtime_nsec_2
* Canceling the sides:
* xtime_nsec_1 = offset + xtime_nsec_2
* Which gives us:
* xtime_nsec_2 = xtime_nsec_1 - offset
* Which simplifies to:
* xtime_nsec -= offset
*/
if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
/* NTP adjustment caused clocksource mult overflow */
WARN_ON_ONCE(1);
return;
}
tk->tkr_mono.mult += mult_adj;
tk->xtime_interval += interval;
tk->tkr_mono.xtime_nsec -= offset;
}
/*
* Adjust the timekeeper's multiplier to the correct frequency
* and also to reduce the accumulated error value.
*/
static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
{
u64 ntp_tl = ntp_tick_length();
u32 mult;
/*
* Determine the multiplier from the current NTP tick length.
* Avoid expensive division when the tick length doesn't change.
*/
if (likely(tk->ntp_tick == ntp_tl)) {
mult = tk->tkr_mono.mult - tk->ntp_err_mult;
} else {
tk->ntp_tick = ntp_tl;
mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) -
tk->xtime_remainder, tk->cycle_interval);
}
/*
* If the clock is behind the NTP time, increase the multiplier by 1
* to catch up with it. If it's ahead and there was a remainder in the
* tick division, the clock will slow down. Otherwise it will stay
* ahead until the tick length changes to a non-divisible value.
*/
tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0;
mult += tk->ntp_err_mult;
timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult);
if (unlikely(tk->tkr_mono.clock->maxadj &&
(abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult)
> tk->tkr_mono.clock->maxadj))) {
printk_once(KERN_WARNING
"Adjusting %s more than 11%% (%ld vs %ld)\n",
tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult,
(long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj);
}
/*
* It may be possible that when we entered this function, xtime_nsec
* was very small. Further, if we're slightly speeding the clocksource
* in the code above, its possible the required corrective factor to
* xtime_nsec could cause it to underflow.
*
* Now, since we have already accumulated the second and the NTP
* subsystem has been notified via second_overflow(), we need to skip
* the next update.
*/
if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) {
tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC <<
tk->tkr_mono.shift;
tk->xtime_sec--;
tk->skip_second_overflow = 1;
}
}
/*
* accumulate_nsecs_to_secs - Accumulates nsecs into secs
*
* Helper function that accumulates the nsecs greater than a second
* from the xtime_nsec field to the xtime_secs field.
* It also calls into the NTP code to handle leapsecond processing.
*/
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
unsigned int clock_set = 0;
while (tk->tkr_mono.xtime_nsec >= nsecps) {
int leap;
tk->tkr_mono.xtime_nsec -= nsecps;
tk->xtime_sec++;
/*
* Skip NTP update if this second was accumulated before,
* i.e. xtime_nsec underflowed in timekeeping_adjust()
*/
if (unlikely(tk->skip_second_overflow)) {
tk->skip_second_overflow = 0;
continue;
}
/* Figure out if its a leap sec and apply if needed */
leap = second_overflow(tk->xtime_sec);
if (unlikely(leap)) {
struct timespec64 ts;
tk->xtime_sec += leap;
ts.tv_sec = leap;
ts.tv_nsec = 0;
tk_set_wall_to_mono(tk,
timespec64_sub(tk->wall_to_monotonic, ts));
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
clock_set = TK_CLOCK_WAS_SET;
}
}
return clock_set;
}
/*
* logarithmic_accumulation - shifted accumulation of cycles
*
* This functions accumulates a shifted interval of cycles into
* a shifted interval nanoseconds. Allows for O(log) accumulation
* loop.
*
* Returns the unconsumed cycles.
*/
static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
u32 shift, unsigned int *clock_set)
{
u64 interval = tk->cycle_interval << shift;
u64 snsec_per_sec;
/* If the offset is smaller than a shifted interval, do nothing */
if (offset < interval)
return offset;
/* Accumulate one shifted interval */
offset -= interval;
tk->tkr_mono.cycle_last += interval;
tk->tkr_raw.cycle_last += interval;
tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift;
*clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
tk->tkr_raw.xtime_nsec -= snsec_per_sec;
tk->raw_sec++;
}
/* Accumulate error between NTP and clock interval */
tk->ntp_error += tk->ntp_tick << shift;
tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
(tk->ntp_error_shift + shift);
return offset;
}
/*
* timekeeping_advance - Updates the timekeeper to the current time and
* current NTP tick length
*/
static bool timekeeping_advance(enum timekeeping_adv_mode mode)
{
struct timekeeper *tk = &tk_core.shadow_timekeeper;
struct timekeeper *real_tk = &tk_core.timekeeper;
unsigned int clock_set = 0;
int shift = 0, maxshift;
u64 offset;
guard(raw_spinlock_irqsave)(&tk_core.lock);
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
return false;
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
/* Check if there's really nothing to do */
if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
return false;
/*
* With NO_HZ we may have to accumulate many cycle_intervals
* (think "ticks") worth of time at once. To do this efficiently,
* we calculate the largest doubling multiple of cycle_intervals
* that is smaller than the offset. We then accumulate that
* chunk in one go, and then try to consume the next smaller
* doubled multiple.
*/
shift = ilog2(offset) - ilog2(tk->cycle_interval);
shift = max(0, shift);
/* Bound shift to one less than what overflows tick_length */
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
offset = logarithmic_accumulation(tk, offset, shift, &clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
/* Adjust the multiplier to correct NTP error */
timekeeping_adjust(tk, offset);
/*
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
clock_set |= accumulate_nsecs_to_secs(tk);
timekeeping_update_from_shadow(&tk_core, clock_set);
return !!clock_set;
}
/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
*/
void update_wall_time(void)
{
if (timekeeping_advance(TK_ADV_TICK))
clock_was_set_delayed();
}
/**
* getboottime64 - Return the real time of system boot.
* @ts: pointer to the timespec64 to be set
*
* Returns the wall-time of boot in a timespec64.
*
* This is based on the wall_to_monotonic offset and the total suspend
* time. Calls to settimeofday will affect the value returned (which
* basically means that however wrong your real time clock is at boot time,
* you get the right time here).
*/
void getboottime64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
*ts = ktime_to_timespec64(t);
}
EXPORT_SYMBOL_GPL(getboottime64);
void ktime_get_coarse_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
*ts = tk_xtime(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));}
EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
/**
* ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor
* @ts: timespec64 to be filled
*
* Fetch the global mg_floor value, convert it to realtime and compare it
* to the current coarse-grained time. Fill @ts with whichever is
* latest. Note that this is a filesystem-specific interface and should be
* avoided outside of that context.
*/
void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
u64 floor = atomic64_read(&mg_floor);
ktime_t f_real, offset, coarse;
unsigned int seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
*ts = tk_xtime(tk);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
coarse = timespec64_to_ktime(*ts);
f_real = ktime_add(floor, offset);
if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real);
}
/**
* ktime_get_real_ts64_mg - attempt to update floor value and return result
* @ts: pointer to the timespec to be set
*
* Get a monotonic fine-grained time value and attempt to swap it into
* mg_floor. If that succeeds then accept the new floor value. If it fails
* then another task raced in during the interim time and updated the
* floor. Since any update to the floor must be later than the previous
* floor, either outcome is acceptable.
*
* Typically this will be called after calling ktime_get_coarse_real_ts64_mg(),
* and determining that the resulting coarse-grained timestamp did not effect
* a change in ctime. Any more recent floor value would effect a change to
* ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure.
*
* @ts will be filled with the latest floor value, regardless of the outcome of
* the cmpxchg. Note that this is a filesystem specific interface and should be
* avoided outside of that context.
*/
void ktime_get_real_ts64_mg(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
ktime_t old = atomic64_read(&mg_floor);
ktime_t offset, mono;
unsigned int seq;
u64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
ts->tv_sec = tk->xtime_sec;
mono = tk->tkr_mono.base;
nsecs = timekeeping_get_ns(&tk->tkr_mono);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
mono = ktime_add_ns(mono, nsecs);
/*
* Attempt to update the floor with the new time value. As any
* update must be later then the existing floor, and would effect
* a change to ctime from the perspective of the current task,
* accept the resulting floor value regardless of the outcome of
* the swap.
*/
if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) {
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
timekeeping_inc_mg_floor_swaps();
} else {
/*
* Another task changed mg_floor since "old" was fetched.
* "old" has been updated with the latest value of "mg_floor".
* That value is newer than the previous floor value, which
* is enough to effect a change to ctime. Accept it.
*/
*ts = ktime_to_timespec64(ktime_add(old, offset));
}
}
void ktime_get_coarse_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
struct timespec64 now, mono;
unsigned int seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
now = tk_xtime(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
now.tv_nsec + mono.tv_nsec);
}
EXPORT_SYMBOL(ktime_get_coarse_ts64);
/*
* Must hold jiffies_lock
*/
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
calc_global_load();
}
/**
* ktime_get_update_offsets_now - hrtimer helper
* @cwsseq: pointer to check and store the clock was set sequence number
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets if the
* sequence number in @cwsseq and timekeeper.clock_was_set_seq are
* different.
*
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
ktime_t *offs_boot, ktime_t *offs_tai)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
ktime_t base;
u64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
base = tk->tkr_mono.base;
nsecs = timekeeping_get_ns(&tk->tkr_mono);
base = ktime_add_ns(base, nsecs);
if (*cwsseq != tk->clock_was_set_seq) {
*cwsseq = tk->clock_was_set_seq;
*offs_real = tk->offs_real;
*offs_boot = tk->offs_boot;
*offs_tai = tk->offs_tai;
}
/* Handle leapsecond insertion adjustments */
if (unlikely(base >= tk->next_leap_ktime))
*offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));
} while (read_seqcount_retry(&tk_core.seq, seq));
return base;
}
/*
* timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
static int timekeeping_validate_timex(const struct __kernel_timex *txc)
{
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
return -EINVAL;
if (!(txc->modes & ADJ_OFFSET_READONLY) &&
!capable(CAP_SYS_TIME))
return -EPERM;
} else {
/* In order to modify anything, you gotta be super-user! */
if (txc->modes && !capable(CAP_SYS_TIME))
return -EPERM;
/*
* if the quartz is off by more than 10% then
* something is VERY wrong!
*/
if (txc->modes & ADJ_TICK &&
(txc->tick < 900000/USER_HZ ||
txc->tick > 1100000/USER_HZ))
return -EINVAL;
}
if (txc->modes & ADJ_SETOFFSET) {
/* In order to inject time, you gotta be super-user! */
if (!capable(CAP_SYS_TIME))
return -EPERM;
/*
* Validate if a timespec/timeval used to inject a time
* offset is valid. Offsets can be positive or negative, so
* we don't check tv_sec. The value of the timeval/timespec
* is the sum of its fields,but *NOTE*:
* The field tv_usec/tv_nsec must always be non-negative and
* we can't have more nanoseconds/microseconds than a second.
*/
if (txc->time.tv_usec < 0)
return -EINVAL;
if (txc->modes & ADJ_NANO) {
if (txc->time.tv_usec >= NSEC_PER_SEC)
return -EINVAL;
} else {
if (txc->time.tv_usec >= USEC_PER_SEC)
return -EINVAL;
}
}
/*
* Check for potential multiplication overflows that can
* only happen on 64-bit systems:
*/
if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
if (LLONG_MIN / PPM_SCALE > txc->freq)
return -EINVAL;
if (LLONG_MAX / PPM_SCALE < txc->freq)
return -EINVAL;
}
return 0;
}
/**
* random_get_entropy_fallback - Returns the raw clock source value,
* used by random.c for platforms with no valid random_get_entropy().
*/
unsigned long random_get_entropy_fallback(void)
{
struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono;
struct clocksource *clock = READ_ONCE(tkr->clock);
if (unlikely(timekeeping_suspended || !clock))
return 0;
return clock->read(clock);
}
EXPORT_SYMBOL_GPL(random_get_entropy_fallback);
/**
* do_adjtimex() - Accessor function to NTP __do_adjtimex function
* @txc: Pointer to kernel_timex structure containing NTP parameters
*/
int do_adjtimex(struct __kernel_timex *txc)
{
struct audit_ntp_data ad;
bool offset_set = false;
bool clock_set = false;
struct timespec64 ts;
int ret;
/* Validate the data before disabling interrupts */
ret = timekeeping_validate_timex(txc);
if (ret)
return ret;
add_device_randomness(txc, sizeof(*txc));
if (txc->modes & ADJ_SETOFFSET) {
struct timespec64 delta;
delta.tv_sec = txc->time.tv_sec;
delta.tv_nsec = txc->time.tv_usec;
if (!(txc->modes & ADJ_NANO))
delta.tv_nsec *= 1000;
ret = timekeeping_inject_offset(&delta);
if (ret)
return ret;
offset_set = delta.tv_sec != 0;
audit_tk_injoffset(delta);
}
audit_ntp_init(&ad);
ktime_get_real_ts64(&ts);
add_device_randomness(&ts, sizeof(ts));
scoped_guard (raw_spinlock_irqsave, &tk_core.lock) {
struct timekeeper *tks = &tk_core.shadow_timekeeper;
s32 orig_tai, tai;
orig_tai = tai = tks->tai_offset;
ret = __do_adjtimex(txc, &ts, &tai, &ad);
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tks, tai);
timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET);
clock_set = true;
} else {
tk_update_leap_state_all(&tk_core);
}
}
audit_ntp_log(&ad);
/* Update the multiplier immediately if frequency was set directly */
if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
clock_set |= timekeeping_advance(TK_ADV_FREQ);
if (clock_set)
clock_was_set(CLOCK_SET_WALL);
ntp_notify_cmos_timer(offset_set);
return ret;
}
#ifdef CONFIG_NTP_PPS
/**
* hardpps() - Accessor function to NTP __hardpps function
* @phase_ts: Pointer to timespec64 structure representing phase timestamp
* @raw_ts: Pointer to timespec64 structure representing raw timestamp
*/
void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
{
guard(raw_spinlock_irqsave)(&tk_core.lock);
__hardpps(phase_ts, raw_ts);
}
EXPORT_SYMBOL(hardpps);
#endif /* CONFIG_NTP_PPS */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Routines having to do with the 'struct sk_buff' memory handlers.
*
* Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>
* Florian La Roche <rzsfl@rz.uni-sb.de>
*
* Fixes:
* Alan Cox : Fixed the worst of the load
* balancer bugs.
* Dave Platt : Interrupt stacking fix.
* Richard Kooijman : Timestamp fixes.
* Alan Cox : Changed buffer format.
* Alan Cox : destructor hook for AF_UNIX etc.
* Linus Torvalds : Better skb_clone.
* Alan Cox : Added skb_copy.
* Alan Cox : Added all the changed routines Linus
* only put in the headers
* Ray VanTassle : Fixed --skb->lock in free
* Alan Cox : skb_copy copy arp field
* Andi Kleen : slabified it.
* Robert Olsson : Removed skb_head_pool
*
* NOTE:
* The __skb_ routines should be called with interrupts
* disabled, or you better be *real* sure that the operation is atomic
* with respect to whatever list is being frobbed (e.g. via lock_sock()
* or via disabling bottom half handlers, etc).
*/
/*
* The functions in this file will not compile correctly with gcc 2.4.x
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/sctp.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/skbuff_ref.h>
#include <linux/splice.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/scatterlist.h>
#include <linux/errqueue.h>
#include <linux/prefetch.h>
#include <linux/bitfield.h>
#include <linux/if_vlan.h>
#include <linux/mpls.h>
#include <linux/kcov.h>
#include <linux/iov_iter.h>
#include <net/protocol.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/gro.h>
#include <net/gso.h>
#include <net/hotdata.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/mpls.h>
#include <net/mptcp.h>
#include <net/mctp.h>
#include <net/page_pool/helpers.h>
#include <net/dropreason.h>
#include <linux/uaccess.h>
#include <trace/events/skb.h>
#include <linux/highmem.h>
#include <linux/capability.h>
#include <linux/user_namespace.h>
#include <linux/indirect_call_wrapper.h>
#include <linux/textsearch.h>
#include "dev.h"
#include "netmem_priv.h"
#include "sock_destructor.h"
#ifdef CONFIG_SKB_EXTENSIONS
static struct kmem_cache *skbuff_ext_cache __ro_after_init;
#endif
#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN)
#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \
GRO_MAX_HEAD_PAD))
/* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two.
* This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique
* size, and we can differentiate heads from skb_small_head_cache
* vs system slabs by looking at their size (skb_end_offset()).
*/
#define SKB_SMALL_HEAD_CACHE_SIZE \
(is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \
(SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \
SKB_SMALL_HEAD_SIZE)
#define SKB_SMALL_HEAD_HEADROOM \
SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE)
/* kcm_write_msgs() relies on casting paged frags to bio_vec to use
* iov_iter_bvec(). These static asserts ensure the cast is valid is long as the
* netmem is a page.
*/
static_assert(offsetof(struct bio_vec, bv_page) ==
offsetof(skb_frag_t, netmem));
static_assert(sizeof_field(struct bio_vec, bv_page) ==
sizeof_field(skb_frag_t, netmem));
static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len));
static_assert(sizeof_field(struct bio_vec, bv_len) ==
sizeof_field(skb_frag_t, len));
static_assert(offsetof(struct bio_vec, bv_offset) ==
offsetof(skb_frag_t, offset));
static_assert(sizeof_field(struct bio_vec, bv_offset) ==
sizeof_field(skb_frag_t, offset));
#undef FN
#define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
static const char * const drop_reasons[] = {
[SKB_CONSUMED] = "CONSUMED",
DEFINE_DROP_REASON(FN, FN)
};
static const struct drop_reason_list drop_reasons_core = {
.reasons = drop_reasons,
.n_reasons = ARRAY_SIZE(drop_reasons),
};
const struct drop_reason_list __rcu *
drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = {
[SKB_DROP_REASON_SUBSYS_CORE] = RCU_INITIALIZER(&drop_reasons_core),
};
EXPORT_SYMBOL(drop_reasons_by_subsys);
/**
* drop_reasons_register_subsys - register another drop reason subsystem
* @subsys: the subsystem to register, must not be the core
* @list: the list of drop reasons within the subsystem, must point to
* a statically initialized list
*/
void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys,
const struct drop_reason_list *list)
{
if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE ||
subsys >= ARRAY_SIZE(drop_reasons_by_subsys),
"invalid subsystem %d\n", subsys))
return;
/* must point to statically allocated memory, so INIT is OK */
RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], list);
}
EXPORT_SYMBOL_GPL(drop_reasons_register_subsys);
/**
* drop_reasons_unregister_subsys - unregister a drop reason subsystem
* @subsys: the subsystem to remove, must not be the core
*
* Note: This will synchronize_rcu() to ensure no users when it returns.
*/
void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys)
{
if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE ||
subsys >= ARRAY_SIZE(drop_reasons_by_subsys),
"invalid subsystem %d\n", subsys))
return;
RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], NULL);
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(drop_reasons_unregister_subsys);
/**
* skb_panic - private function for out-of-line support
* @skb: buffer
* @sz: size
* @addr: address
* @msg: skb_over_panic or skb_under_panic
*
* Out-of-line support for skb_put() and skb_push().
* Called via the wrapper skb_over_panic() or skb_under_panic().
* Keep out of line to prevent kernel bloat.
* __builtin_return_address is not used because it is not always reliable.
*/
static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr,
const char msg[])
{
pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n",
msg, addr, skb->len, sz, skb->head, skb->data,
(unsigned long)skb->tail, (unsigned long)skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
skb_panic(skb, sz, addr, __func__);
}
static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
skb_panic(skb, sz, addr, __func__);
}
#define NAPI_SKB_CACHE_SIZE 64
#define NAPI_SKB_CACHE_BULK 16
#define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2)
struct napi_alloc_cache {
local_lock_t bh_lock;
struct page_frag_cache page;
unsigned int skb_count;
void *skb_cache[NAPI_SKB_CACHE_SIZE];
};
static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = {
.bh_lock = INIT_LOCAL_LOCK(bh_lock),
};
void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
void *data;
fragsz = SKB_DATA_ALIGN(fragsz);
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
data = __page_frag_alloc_align(&nc->page, fragsz,
GFP_ATOMIC | __GFP_NOWARN, align_mask);
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
return data;
}
EXPORT_SYMBOL(__napi_alloc_frag_align);
void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
{
void *data;
if (in_hardirq() || irqs_disabled()) {
struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
fragsz = SKB_DATA_ALIGN(fragsz);
data = __page_frag_alloc_align(nc, fragsz,
GFP_ATOMIC | __GFP_NOWARN,
align_mask);
} else {
local_bh_disable();
data = __napi_alloc_frag_align(fragsz, align_mask);
local_bh_enable();
}
return data;
}
EXPORT_SYMBOL(__netdev_alloc_frag_align);
static struct sk_buff *napi_skb_cache_get(void)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
struct sk_buff *skb;
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
if (unlikely(!nc->skb_count)) {
nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN,
NAPI_SKB_CACHE_BULK,
nc->skb_cache);
if (unlikely(!nc->skb_count)) {
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
return NULL;
}
}
skb = nc->skb_cache[--nc->skb_count];
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache));
return skb;
}
/**
* napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache
* @skbs: pointer to an at least @n-sized array to fill with skb pointers
* @n: number of entries to provide
*
* Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes
* the pointers into the provided array @skbs. If there are less entries
* available, tries to replenish the cache and bulk-allocates the diff from
* the MM layer if needed.
* The heads are being zeroed with either memset() or %__GFP_ZERO, so they are
* ready for {,__}build_skb_around() and don't have any data buffers attached.
* Must be called *only* from the BH context.
*
* Return: number of successfully allocated skbs (@n if no actual allocation
* needed or kmem_cache_alloc_bulk() didn't fail).
*/
u32 napi_skb_cache_get_bulk(void **skbs, u32 n)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
u32 bulk, total = n;
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
if (nc->skb_count >= n)
goto get;
/* No enough cached skbs. Try refilling the cache first */
bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK);
nc->skb_count += kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN, bulk,
&nc->skb_cache[nc->skb_count]);
if (likely(nc->skb_count >= n))
goto get;
/* Still not enough. Bulk-allocate the missing part directly, zeroed */
n -= kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN,
n - nc->skb_count, &skbs[nc->skb_count]);
if (likely(nc->skb_count >= n))
goto get;
/* kmem_cache didn't allocate the number we need, limit the output */
total -= n - nc->skb_count;
n = nc->skb_count;
get:
for (u32 base = nc->skb_count - n, i = 0; i < n; i++) {
u32 cache_size = kmem_cache_size(net_hotdata.skbuff_cache);
skbs[i] = nc->skb_cache[base + i];
kasan_mempool_unpoison_object(skbs[i], cache_size);
memset(skbs[i], 0, offsetof(struct sk_buff, tail));
}
nc->skb_count -= n;
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
return total;
}
EXPORT_SYMBOL_GPL(napi_skb_cache_get_bulk);
static inline void __finalize_skb_around(struct sk_buff *skb, void *data,
unsigned int size)
{
struct skb_shared_info *shinfo;
size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
/* Assumes caller memset cleared SKB */
skb->truesize = SKB_TRUESIZE(size);
refcount_set(&skb->users, 1);
skb->head = data;
skb->data = data;
skb_reset_tail_pointer(skb);
skb_set_end_offset(skb, size);
skb->mac_header = (typeof(skb->mac_header))~0U;
skb->transport_header = (typeof(skb->transport_header))~0U;
skb->alloc_cpu = raw_smp_processor_id();
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
skb_set_kcov_handle(skb, kcov_common_handle());
}
static inline void *__slab_build_skb(struct sk_buff *skb, void *data,
unsigned int *size)
{
void *resized;
/* Must find the allocation size (and grow it to match). */
*size = ksize(data);
/* krealloc() will immediately return "data" when
* "ksize(data)" is requested: it is the existing upper
* bounds. As a result, GFP_ATOMIC will be ignored. Note
* that this "new" pointer needs to be passed back to the
* caller for use so the __alloc_size hinting will be
* tracked correctly.
*/
resized = krealloc(data, *size, GFP_ATOMIC);
WARN_ON_ONCE(resized != data);
return resized;
}
/* build_skb() variant which can operate on slab buffers.
* Note that this should be used sparingly as slab buffers
* cannot be combined efficiently by GRO!
*/
struct sk_buff *slab_build_skb(void *data)
{
struct sk_buff *skb;
unsigned int size;
skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
data = __slab_build_skb(skb, data, &size);
__finalize_skb_around(skb, data, size);
return skb;
}
EXPORT_SYMBOL(slab_build_skb);
/* Caller must provide SKB that is memset cleared */
static void __build_skb_around(struct sk_buff *skb, void *data,
unsigned int frag_size)
{
unsigned int size = frag_size;
/* frag_size == 0 is considered deprecated now. Callers
* using slab buffer should use slab_build_skb() instead.
*/
if (WARN_ONCE(size == 0, "Use slab_build_skb() instead")) data = __slab_build_skb(skb, data, &size);
__finalize_skb_around(skb, data, size);
}
/**
* __build_skb - build a network buffer
* @data: data buffer provided by caller
* @frag_size: size of data (must not be 0)
*
* Allocate a new &sk_buff. Caller provides space holding head and
* skb_shared_info. @data must have been allocated from the page
* allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc()
* allocation is deprecated, and callers should use slab_build_skb()
* instead.)
* The return is the new skb buffer.
* On a failure the return is %NULL, and @data is not freed.
* Notes :
* Before IO, driver allocates only data buffer where NIC put incoming frame
* Driver should add room at head (NET_SKB_PAD) and
* MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info))
* After IO, driver calls build_skb(), to allocate sk_buff and populate it
* before giving packet to stack.
* RX rings only contains data buffers, not full skbs.
*/
struct sk_buff *__build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb;
skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, frag_size);
return skb;
}
/* build_skb() is wrapper over __build_skb(), that specifically
* takes care of skb->head and skb->pfmemalloc
*/
struct sk_buff *build_skb(void *data, unsigned int frag_size)
{ struct sk_buff *skb = __build_skb(data, frag_size); if (likely(skb && frag_size)) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(build_skb);
/**
* build_skb_around - build a network buffer around provided skb
* @skb: sk_buff provide by caller, must be memset cleared
* @data: data buffer provided by caller
* @frag_size: size of data
*/
struct sk_buff *build_skb_around(struct sk_buff *skb,
void *data, unsigned int frag_size)
{
if (unlikely(!skb))
return NULL;
__build_skb_around(skb, data, frag_size);
if (frag_size) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(build_skb_around);
/**
* __napi_build_skb - build a network buffer
* @data: data buffer provided by caller
* @frag_size: size of data
*
* Version of __build_skb() that uses NAPI percpu caches to obtain
* skbuff_head instead of inplace allocation.
*
* Returns a new &sk_buff on success, %NULL on allocation failure.
*/
static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb;
skb = napi_skb_cache_get();
if (unlikely(!skb))
return NULL;
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, frag_size);
return skb;
}
/**
* napi_build_skb - build a network buffer
* @data: data buffer provided by caller
* @frag_size: size of data
*
* Version of __napi_build_skb() that takes care of skb->head_frag
* and skb->pfmemalloc when the data is a page or page fragment.
*
* Returns a new &sk_buff on success, %NULL on allocation failure.
*/
struct sk_buff *napi_build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb = __napi_build_skb(data, frag_size);
if (likely(skb) && frag_size) {
skb->head_frag = 1;
skb_propagate_pfmemalloc(virt_to_head_page(data), skb);
}
return skb;
}
EXPORT_SYMBOL(napi_build_skb);
/*
* kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
* the caller if emergency pfmemalloc reserves are being used. If it is and
* the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
* may be used. Otherwise, the packet data may be discarded until enough
* memory is free
*/
static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
bool *pfmemalloc)
{
bool ret_pfmemalloc = false;
size_t obj_size;
void *obj;
obj_size = SKB_HEAD_ALIGN(*size);
if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
!(flags & KMALLOC_NOT_NORMAL_BITS)) {
obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache,
flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
node);
*size = SKB_SMALL_HEAD_CACHE_SIZE;
if (obj || !(gfp_pfmemalloc_allowed(flags)))
goto out;
/* Try again but now we are using pfmemalloc reserves */
ret_pfmemalloc = true;
obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node);
goto out;
}
obj_size = kmalloc_size_roundup(obj_size);
/* The following cast might truncate high-order bits of obj_size, this
* is harmless because kmalloc(obj_size >= 2^32) will fail anyway.
*/
*size = (unsigned int)obj_size;
/*
* Try a regular allocation, when that fails and we're not entitled
* to the reserves, fail.
*/
obj = kmalloc_node_track_caller(obj_size,
flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
node);
if (obj || !(gfp_pfmemalloc_allowed(flags)))
goto out;
/* Try again but now we are using pfmemalloc reserves */
ret_pfmemalloc = true;
obj = kmalloc_node_track_caller(obj_size, flags, node);
out:
if (pfmemalloc) *pfmemalloc = ret_pfmemalloc;
return obj;
}
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
*
*/
/**
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
* @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
* instead of head cache and allocate a cloned (child) skb.
* If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
* allocations in case the data is required for writeback
* @node: numa node to allocate memory on
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
* tail room of at least size bytes. The object has a reference count
* of one. The return is the buffer. On a failure the return is %NULL.
*
* Buffers may only be allocated from interrupts using a @gfp_mask of
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
int flags, int node)
{
struct kmem_cache *cache;
struct sk_buff *skb;
bool pfmemalloc;
u8 *data;
cache = (flags & SKB_ALLOC_FCLONE)
? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache;
if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
gfp_mask |= __GFP_MEMALLOC;
/* Get the HEAD */
if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && likely(node == NUMA_NO_NODE || node == numa_mem_id()))
skb = napi_skb_cache_get();
else
skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node);
if (unlikely(!skb))
return NULL;
prefetchw(skb);
/* We do our best to align skb_shared_info on a separate cache
* line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives
* aligned memory blocks, unless SLUB/SLAB debug is enabled.
* Both skb->head and skb_shared_info are cache line aligned.
*/
data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc);
if (unlikely(!data))
goto nodata;
/* kmalloc_size_roundup() might give us more room than requested.
* Put skb_shared_info exactly at the end of allocated zone,
* to allow max possible filling before reallocation.
*/
prefetchw(data + SKB_WITH_OVERHEAD(size));
/*
* Only clear those fields we need to clear, not those that we will
* actually initialise below. Hence, don't put any more fields after
* the tail pointer in struct sk_buff!
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
__build_skb_around(skb, data, size);
skb->pfmemalloc = pfmemalloc;
if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff_fclones *fclones;
fclones = container_of(skb, struct sk_buff_fclones, skb1);
skb->fclone = SKB_FCLONE_ORIG;
refcount_set(&fclones->fclone_ref, 1);
}
return skb;
nodata:
kmem_cache_free(cache, skb);
return NULL;
}
EXPORT_SYMBOL(__alloc_skb);
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
* @len: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
*
* Allocate a new &sk_buff and assign it a usage count of one. The
* buffer has NET_SKB_PAD headroom built in. Users should allocate
* the headroom they think they need without accounting for the
* built in space. The built in space is used for optimisations.
*
* %NULL is returned if there is no free memory.
*/
struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
gfp_t gfp_mask)
{
struct page_frag_cache *nc;
struct sk_buff *skb;
bool pfmemalloc;
void *data;
len += NET_SKB_PAD;
/* If requested length is either too small or too big,
* we use kmalloc() for skb->head allocation.
*/
if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) ||
len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
if (!skb)
goto skb_fail;
goto skb_success;
}
len = SKB_HEAD_ALIGN(len);
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
if (in_hardirq() || irqs_disabled()) {
nc = this_cpu_ptr(&netdev_alloc_cache);
data = page_frag_alloc(nc, len, gfp_mask);
pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
} else {
local_bh_disable();
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
nc = this_cpu_ptr(&napi_alloc_cache.page);
data = page_frag_alloc(nc, len, gfp_mask);
pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
local_bh_enable();
}
if (unlikely(!data))
return NULL;
skb = __build_skb(data, len);
if (unlikely(!skb)) {
skb_free_frag(data);
return NULL;
}
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
skb_success:
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
skb_fail:
return skb;
}
EXPORT_SYMBOL(__netdev_alloc_skb);
/**
* napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
* @napi: napi instance this buffer was allocated for
* @len: length to allocate
*
* Allocate a new sk_buff for use in NAPI receive. This buffer will
* attempt to allocate the head from a special reserved region used
* only for NAPI Rx allocation. By doing this we can save several
* CPU cycles by avoiding having to disable and re-enable IRQs.
*
* %NULL is returned if there is no free memory.
*/
struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
{
gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN;
struct napi_alloc_cache *nc;
struct sk_buff *skb;
bool pfmemalloc;
void *data;
DEBUG_NET_WARN_ON_ONCE(!in_softirq());
len += NET_SKB_PAD + NET_IP_ALIGN;
/* If requested length is either too small or too big,
* we use kmalloc() for skb->head allocation.
*/
if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) ||
len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI,
NUMA_NO_NODE);
if (!skb)
goto skb_fail;
goto skb_success;
}
len = SKB_HEAD_ALIGN(len);
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
nc = this_cpu_ptr(&napi_alloc_cache);
data = page_frag_alloc(&nc->page, len, gfp_mask);
pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page);
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
if (unlikely(!data))
return NULL;
skb = __napi_build_skb(data, len);
if (unlikely(!skb)) {
skb_free_frag(data);
return NULL;
}
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
skb_success:
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
skb->dev = napi->dev;
skb_fail:
return skb;
}
EXPORT_SYMBOL(napi_alloc_skb);
void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem,
int off, int size, unsigned int truesize)
{
DEBUG_NET_WARN_ON_ONCE(size > truesize);
skb_fill_netmem_desc(skb, i, netmem, off, size);
skb->len += size;
skb->data_len += size;
skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_add_rx_frag_netmem);
void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
unsigned int truesize)
{
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
DEBUG_NET_WARN_ON_ONCE(size > truesize);
skb_frag_size_add(frag, size);
skb->len += size;
skb->data_len += size;
skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_coalesce_rx_frag);
static void skb_drop_list(struct sk_buff **listp)
{
kfree_skb_list(*listp);
*listp = NULL;
}
static inline void skb_drop_fraglist(struct sk_buff *skb)
{
skb_drop_list(&skb_shinfo(skb)->frag_list);
}
static void skb_clone_fraglist(struct sk_buff *skb)
{
struct sk_buff *list;
skb_walk_frags(skb, list) skb_get(list);
}
static bool is_pp_netmem(netmem_ref netmem)
{
return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
}
int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
unsigned int headroom)
{
#if IS_ENABLED(CONFIG_PAGE_POOL)
u32 size, truesize, len, max_head_size, off;
struct sk_buff *skb = *pskb, *nskb;
int err, i, head_off;
void *data;
/* XDP does not support fraglist so we need to linearize
* the skb.
*/
if (skb_has_frag_list(skb))
return -EOPNOTSUPP;
max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom);
if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE)
return -ENOMEM;
size = min_t(u32, skb->len, max_head_size);
truesize = SKB_HEAD_ALIGN(size) + headroom;
data = page_pool_dev_alloc_va(pool, &truesize);
if (!data)
return -ENOMEM;
nskb = napi_build_skb(data, truesize);
if (!nskb) {
page_pool_free_va(pool, data, true);
return -ENOMEM;
}
skb_reserve(nskb, headroom);
skb_copy_header(nskb, skb);
skb_mark_for_recycle(nskb);
err = skb_copy_bits(skb, 0, nskb->data, size);
if (err) {
consume_skb(nskb);
return err;
}
skb_put(nskb, size);
head_off = skb_headroom(nskb) - skb_headroom(skb);
skb_headers_offset_update(nskb, head_off);
off = size;
len = skb->len - off;
for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
struct page *page;
u32 page_off;
size = min_t(u32, len, PAGE_SIZE);
truesize = size;
page = page_pool_dev_alloc(pool, &page_off, &truesize);
if (!page) {
consume_skb(nskb);
return -ENOMEM;
}
skb_add_rx_frag(nskb, i, page, page_off, size, truesize);
err = skb_copy_bits(skb, off, page_address(page) + page_off,
size);
if (err) {
consume_skb(nskb);
return err;
}
len -= size;
off += size;
}
consume_skb(skb);
*pskb = nskb;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
EXPORT_SYMBOL(skb_pp_cow_data);
int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
const struct bpf_prog *prog)
{
if (!prog->aux->xdp_has_frags)
return -EINVAL;
return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM);
}
EXPORT_SYMBOL(skb_cow_data_for_xdp);
#if IS_ENABLED(CONFIG_PAGE_POOL)
bool napi_pp_put_page(netmem_ref netmem)
{
netmem = netmem_compound_head(netmem);
/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
* in order to preserve any existing bits, such as bit 0 for the
* head page of compound page and bit 1 for pfmemalloc page, so
* mask those bits for freeing side when doing below checking,
* and page_is_pfmemalloc() is checked in __page_pool_put_page()
* to avoid recycling the pfmemalloc page.
*/
if (unlikely(!is_pp_netmem(netmem)))
return false;
page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
return true;
}
EXPORT_SYMBOL(napi_pp_put_page);
#endif
static bool skb_pp_recycle(struct sk_buff *skb, void *data)
{
if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
return false;
return napi_pp_put_page(page_to_netmem(virt_to_page(data)));
}
/**
* skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
* @skb: page pool aware skb
*
* Increase the fragment reference count (pp_ref_count) of a skb. This is
* intended to gain fragment references only for page pool aware skbs,
* i.e. when skb->pp_recycle is true, and not for fragments in a
* non-pp-recycling skb. It has a fallback to increase references on normal
* pages, as page pool aware skbs may also have normal page fragments.
*/
static int skb_pp_frag_ref(struct sk_buff *skb)
{
struct skb_shared_info *shinfo;
netmem_ref head_netmem;
int i;
if (!skb->pp_recycle)
return -EINVAL;
shinfo = skb_shinfo(skb);
for (i = 0; i < shinfo->nr_frags; i++) {
head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
if (likely(is_pp_netmem(head_netmem)))
page_pool_ref_netmem(head_netmem);
else
page_ref_inc(netmem_to_page(head_netmem));
}
return 0;
}
static void skb_kfree_head(void *head, unsigned int end_offset)
{
if (end_offset == SKB_SMALL_HEAD_HEADROOM)
kmem_cache_free(net_hotdata.skb_small_head_cache, head);
else
kfree(head);
}
static void skb_free_head(struct sk_buff *skb)
{
unsigned char *head = skb->head;
if (skb->head_frag) {
if (skb_pp_recycle(skb, head))
return;
skb_free_frag(head);
} else {
skb_kfree_head(head, skb_end_offset(skb));
}
}
static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
int i;
if (!skb_data_unref(skb, shinfo))
goto exit;
if (skb_zcopy(skb)) {
bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS;
skb_zcopy_clear(skb, true);
if (skip_unref)
goto free_head;
}
for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
free_head:
if (shinfo->frag_list) kfree_skb_list_reason(shinfo->frag_list, reason);
skb_free_head(skb);
exit:
/* When we clone an SKB we copy the reycling bit. The pp_recycle
* bit is only set on the head though, so in order to avoid races
* while trying to recycle fragments on __skb_frag_unref() we need
* to make one SKB responsible for triggering the recycle path.
* So disable the recycling bit if an SKB is cloned and we have
* additional references to the fragmented part of the SKB.
* Eventually the last SKB will have the recycling bit set and it's
* dataref set to 0, which will trigger the recycling
*/
skb->pp_recycle = 0;
}
/*
* Free an skbuff by memory without cleaning the state.
*/
static void kfree_skbmem(struct sk_buff *skb)
{
struct sk_buff_fclones *fclones;
switch (skb->fclone) {
case SKB_FCLONE_UNAVAILABLE:
kmem_cache_free(net_hotdata.skbuff_cache, skb);
return;
case SKB_FCLONE_ORIG:
fclones = container_of(skb, struct sk_buff_fclones, skb1);
/* We usually free the clone (TX completion) before original skb
* This test would have no chance to be true for the clone,
* while here, branch prediction will be good.
*/
if (refcount_read(&fclones->fclone_ref) == 1)
goto fastpath;
break;
default: /* SKB_FCLONE_CLONE */
fclones = container_of(skb, struct sk_buff_fclones, skb2);
break;
}
if (!refcount_dec_and_test(&fclones->fclone_ref))
return;
fastpath:
kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones);
}
void skb_release_head_state(struct sk_buff *skb)
{ skb_dst_drop(skb); if (skb->destructor) { DEBUG_NET_WARN_ON_ONCE(in_hardirq());
skb->destructor(skb);
}
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb_nfct(skb));
#endif
skb_ext_put(skb);
}
/* Free everything but the sk_buff shell. */
static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason)
{
skb_release_head_state(skb);
if (likely(skb->head)) skb_release_data(skb, reason);
}
/**
* __kfree_skb - private function
* @skb: buffer
*
* Free an sk_buff. Release anything attached to the buffer.
* Clean the state. This is an internal helper function. Users should
* always call kfree_skb
*/
void __kfree_skb(struct sk_buff *skb)
{
skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED);
kfree_skbmem(skb);
}
EXPORT_SYMBOL(__kfree_skb);
static __always_inline
bool __sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb,
enum skb_drop_reason reason)
{
if (unlikely(!skb_unref(skb)))
return false;
DEBUG_NET_WARN_ON_ONCE(reason == SKB_NOT_DROPPED_YET ||
u32_get_bits(reason,
SKB_DROP_REASON_SUBSYS_MASK) >=
SKB_DROP_REASON_SUBSYS_NUM);
if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0));
else
trace_kfree_skb(skb, __builtin_return_address(0), reason, sk);
return true;
}
/**
* sk_skb_reason_drop - free an sk_buff with special reason
* @sk: the socket to receive @skb, or NULL if not applicable
* @skb: buffer to free
* @reason: reason why this skb is dropped
*
* Drop a reference to the buffer and free it if the usage count has hit
* zero. Meanwhile, pass the receiving socket and drop reason to
* 'kfree_skb' tracepoint.
*/
void __fix_address
sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason)
{ if (__sk_skb_reason_drop(sk, skb, reason)) __kfree_skb(skb);
}
EXPORT_SYMBOL(sk_skb_reason_drop);
#define KFREE_SKB_BULK_SIZE 16
struct skb_free_array {
unsigned int skb_count;
void *skb_array[KFREE_SKB_BULK_SIZE];
};
static void kfree_skb_add_bulk(struct sk_buff *skb,
struct skb_free_array *sa,
enum skb_drop_reason reason)
{
/* if SKB is a clone, don't handle this case */
if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) {
__kfree_skb(skb);
return;
}
skb_release_all(skb, reason);
sa->skb_array[sa->skb_count++] = skb;
if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) {
kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE,
sa->skb_array);
sa->skb_count = 0;
}
}
void __fix_address
kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason)
{
struct skb_free_array sa;
sa.skb_count = 0;
while (segs) {
struct sk_buff *next = segs->next;
if (__sk_skb_reason_drop(NULL, segs, reason)) {
skb_poison_list(segs);
kfree_skb_add_bulk(segs, &sa, reason);
}
segs = next;
}
if (sa.skb_count)
kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array);
}
EXPORT_SYMBOL(kfree_skb_list_reason);
/* Dump skb information and contents.
*
* Must only be called from net_ratelimit()-ed paths.
*
* Dumps whole packets if full_pkt, only headers otherwise.
*/
void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
{
struct skb_shared_info *sh = skb_shinfo(skb);
struct net_device *dev = skb->dev;
struct sock *sk = skb->sk;
struct sk_buff *list_skb;
bool has_mac, has_trans;
int headroom, tailroom;
int i, len, seg_len;
if (full_pkt)
len = skb->len;
else
len = min_t(int, skb->len, MAX_HEADER + 128);
headroom = skb_headroom(skb);
tailroom = skb_tailroom(skb);
has_mac = skb_mac_header_was_set(skb);
has_trans = skb_transport_header_was_set(skb);
printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n"
"mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n"
"shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n"
"csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n"
"hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n"
"priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n"
"encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n",
level, skb->len, headroom, skb_headlen(skb), tailroom,
has_mac ? skb->mac_header : -1,
has_mac ? skb_mac_header_len(skb) : -1,
skb->mac_len,
skb->network_header,
has_trans ? skb_network_header_len(skb) : -1,
has_trans ? skb->transport_header : -1,
sh->tx_flags, sh->nr_frags,
sh->gso_size, sh->gso_type, sh->gso_segs,
skb->csum, skb->csum_start, skb->csum_offset, skb->ip_summed,
skb->csum_complete_sw, skb->csum_valid, skb->csum_level,
skb->hash, skb->sw_hash, skb->l4_hash,
ntohs(skb->protocol), skb->pkt_type, skb->skb_iif,
skb->priority, skb->mark, skb->alloc_cpu, skb->vlan_all,
skb->encapsulation, skb->inner_protocol, skb->inner_mac_header,
skb->inner_network_header, skb->inner_transport_header);
if (dev)
printk("%sdev name=%s feat=%pNF\n",
level, dev->name, &dev->features);
if (sk)
printk("%ssk family=%hu type=%u proto=%u\n",
level, sk->sk_family, sk->sk_type, sk->sk_protocol);
if (full_pkt && headroom)
print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET,
16, 1, skb->head, headroom, false);
seg_len = min_t(int, skb_headlen(skb), len);
if (seg_len)
print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET,
16, 1, skb->data, seg_len, false);
len -= seg_len;
if (full_pkt && tailroom)
print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET,
16, 1, skb_tail_pointer(skb), tailroom, false);
for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
if (skb_frag_is_net_iov(frag)) {
printk("%sskb frag %d: not readable\n", level, i);
len -= skb_frag_size(frag);
if (!len)
break;
continue;
}
skb_frag_foreach_page(frag, skb_frag_off(frag),
skb_frag_size(frag), p, p_off, p_len,
copied) {
seg_len = min_t(int, p_len, len);
vaddr = kmap_atomic(p);
print_hex_dump(level, "skb frag: ",
DUMP_PREFIX_OFFSET,
16, 1, vaddr + p_off, seg_len, false);
kunmap_atomic(vaddr);
len -= seg_len;
if (!len)
break;
}
}
if (full_pkt && skb_has_frag_list(skb)) {
printk("skb fraglist:\n");
skb_walk_frags(skb, list_skb)
skb_dump(level, list_skb, true);
}
}
EXPORT_SYMBOL(skb_dump);
/**
* skb_tx_error - report an sk_buff xmit error
* @skb: buffer that triggered an error
*
* Report xmit error if a device callback is tracking this skb.
* skb must be freed afterwards.
*/
void skb_tx_error(struct sk_buff *skb)
{
if (skb) {
skb_zcopy_downgrade_managed(skb);
skb_zcopy_clear(skb, true);
}
}
EXPORT_SYMBOL(skb_tx_error);
#ifdef CONFIG_TRACEPOINTS
/**
* consume_skb - free an skbuff
* @skb: buffer to free
*
* Drop a ref to the buffer and free it if the usage count has hit zero
* Functions identically to kfree_skb, but kfree_skb assumes that the frame
* is being dropped after a failure and notes that
*/
void consume_skb(struct sk_buff *skb)
{ if (!skb_unref(skb))
return;
trace_consume_skb(skb, __builtin_return_address(0));
__kfree_skb(skb);
}
EXPORT_SYMBOL(consume_skb);
#endif
/**
* __consume_stateless_skb - free an skbuff, assuming it is stateless
* @skb: buffer to free
*
* Alike consume_skb(), but this variant assumes that this is the last
* skb reference and all the head states have been already dropped
*/
void __consume_stateless_skb(struct sk_buff *skb)
{
trace_consume_skb(skb, __builtin_return_address(0));
skb_release_data(skb, SKB_CONSUMED);
kfree_skbmem(skb);
}
static void napi_skb_cache_put(struct sk_buff *skb)
{
struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
u32 i;
if (!kasan_mempool_poison_object(skb))
return;
local_lock_nested_bh(&napi_alloc_cache.bh_lock);
nc->skb_cache[nc->skb_count++] = skb;
if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
kasan_mempool_unpoison_object(nc->skb_cache[i],
kmem_cache_size(net_hotdata.skbuff_cache));
kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF,
nc->skb_cache + NAPI_SKB_CACHE_HALF);
nc->skb_count = NAPI_SKB_CACHE_HALF;
}
local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
}
void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason)
{
skb_release_all(skb, reason);
napi_skb_cache_put(skb);
}
void napi_skb_free_stolen_head(struct sk_buff *skb)
{
if (unlikely(skb->slow_gro)) {
nf_reset_ct(skb);
skb_dst_drop(skb);
skb_ext_put(skb);
skb_orphan(skb);
skb->slow_gro = 0;
}
napi_skb_cache_put(skb);
}
void napi_consume_skb(struct sk_buff *skb, int budget)
{
/* Zero budget indicate non-NAPI context called us, like netpoll */
if (unlikely(!budget)) {
dev_consume_skb_any(skb);
return;
}
DEBUG_NET_WARN_ON_ONCE(!in_softirq());
if (!skb_unref(skb))
return;
/* if reaching here SKB is ready to free */
trace_consume_skb(skb, __builtin_return_address(0));
/* if SKB is a clone, don't handle this case */
if (skb->fclone != SKB_FCLONE_UNAVAILABLE) {
__kfree_skb(skb);
return;
}
skb_release_all(skb, SKB_CONSUMED);
napi_skb_cache_put(skb);
}
EXPORT_SYMBOL(napi_consume_skb);
/* Make sure a field is contained by headers group */
#define CHECK_SKB_FIELD(field) \
BUILD_BUG_ON(offsetof(struct sk_buff, field) != \
offsetof(struct sk_buff, headers.field)); \
static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
new->tstamp = old->tstamp;
/* We do not copy old->sk */
new->dev = old->dev;
memcpy(new->cb, old->cb, sizeof(old->cb));
skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false);
/* Note : this field could be in the headers group.
* It is not yet because we do not want to have a 16 bit hole
*/
new->queue_mapping = old->queue_mapping;
memcpy(&new->headers, &old->headers, sizeof(new->headers));
CHECK_SKB_FIELD(protocol);
CHECK_SKB_FIELD(csum);
CHECK_SKB_FIELD(hash);
CHECK_SKB_FIELD(priority);
CHECK_SKB_FIELD(skb_iif);
CHECK_SKB_FIELD(vlan_proto);
CHECK_SKB_FIELD(vlan_tci);
CHECK_SKB_FIELD(transport_header);
CHECK_SKB_FIELD(network_header);
CHECK_SKB_FIELD(mac_header);
CHECK_SKB_FIELD(inner_protocol);
CHECK_SKB_FIELD(inner_transport_header);
CHECK_SKB_FIELD(inner_network_header);
CHECK_SKB_FIELD(inner_mac_header);
CHECK_SKB_FIELD(mark);
#ifdef CONFIG_NETWORK_SECMARK
CHECK_SKB_FIELD(secmark);
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
CHECK_SKB_FIELD(napi_id);
#endif
CHECK_SKB_FIELD(alloc_cpu);
#ifdef CONFIG_XPS
CHECK_SKB_FIELD(sender_cpu);
#endif
#ifdef CONFIG_NET_SCHED
CHECK_SKB_FIELD(tc_index);
#endif
}
/*
* You should not add any new code to this function. Add it to
* __copy_skb_header above instead.
*/
static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
{
#define C(x) n->x = skb->x
n->next = n->prev = NULL;
n->sk = NULL;
__copy_skb_header(n, skb);
C(len);
C(data_len);
C(mac_len);
n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
n->cloned = 1;
n->nohdr = 0;
n->peeked = 0;
C(pfmemalloc);
C(pp_recycle);
n->destructor = NULL;
C(tail);
C(end);
C(head);
C(head_frag);
C(data);
C(truesize);
refcount_set(&n->users, 1);
atomic_inc(&(skb_shinfo(skb)->dataref));
skb->cloned = 1;
return n;
#undef C
}
/**
* alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg
* @first: first sk_buff of the msg
*/
struct sk_buff *alloc_skb_for_msg(struct sk_buff *first)
{
struct sk_buff *n;
n = alloc_skb(0, GFP_ATOMIC);
if (!n)
return NULL;
n->len = first->len;
n->data_len = first->len;
n->truesize = first->truesize;
skb_shinfo(n)->frag_list = first;
__copy_skb_header(n, first);
n->destructor = NULL;
return n;
}
EXPORT_SYMBOL_GPL(alloc_skb_for_msg);
/**
* skb_morph - morph one skb into another
* @dst: the skb to receive the contents
* @src: the skb to supply the contents
*
* This is identical to skb_clone except that the target skb is
* supplied by the user.
*
* The target skb is returned upon exit.
*/
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
{
skb_release_all(dst, SKB_CONSUMED);
return __skb_clone(dst, src);
}
EXPORT_SYMBOL_GPL(skb_morph);
int mm_account_pinned_pages(struct mmpin *mmp, size_t size)
{
unsigned long max_pg, num_pg, new_pg, old_pg, rlim;
struct user_struct *user;
if (capable(CAP_IPC_LOCK) || !size)
return 0;
rlim = rlimit(RLIMIT_MEMLOCK);
if (rlim == RLIM_INFINITY)
return 0;
num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */
max_pg = rlim >> PAGE_SHIFT;
user = mmp->user ? : current_user();
old_pg = atomic_long_read(&user->locked_vm);
do {
new_pg = old_pg + num_pg;
if (new_pg > max_pg)
return -ENOBUFS;
} while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg));
if (!mmp->user) {
mmp->user = get_uid(user);
mmp->num_pg = num_pg;
} else {
mmp->num_pg += num_pg;
}
return 0;
}
EXPORT_SYMBOL_GPL(mm_account_pinned_pages);
void mm_unaccount_pinned_pages(struct mmpin *mmp)
{
if (mmp->user) {
atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm);
free_uid(mmp->user);
}
}
EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
{
struct ubuf_info_msgzc *uarg;
struct sk_buff *skb;
WARN_ON_ONCE(!in_task());
skb = sock_omalloc(sk, 0, GFP_KERNEL);
if (!skb)
return NULL;
BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb));
uarg = (void *)skb->cb;
uarg->mmp.user = NULL;
if (mm_account_pinned_pages(&uarg->mmp, size)) {
kfree_skb(skb);
return NULL;
}
uarg->ubuf.ops = &msg_zerocopy_ubuf_ops;
uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1;
uarg->len = 1;
uarg->bytelen = size;
uarg->zerocopy = 1;
uarg->ubuf.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
refcount_set(&uarg->ubuf.refcnt, 1);
sock_hold(sk);
return &uarg->ubuf;
}
static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg)
{
return container_of((void *)uarg, struct sk_buff, cb);
}
struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
struct ubuf_info *uarg)
{
if (uarg) {
struct ubuf_info_msgzc *uarg_zc;
const u32 byte_limit = 1 << 19; /* limit to a few TSO */
u32 bytelen, next;
/* there might be non MSG_ZEROCOPY users */
if (uarg->ops != &msg_zerocopy_ubuf_ops)
return NULL;
/* realloc only when socket is locked (TCP, UDP cork),
* so uarg->len and sk_zckey access is serialized
*/
if (!sock_owned_by_user(sk)) {
WARN_ON_ONCE(1);
return NULL;
}
uarg_zc = uarg_to_msgzc(uarg);
bytelen = uarg_zc->bytelen + size;
if (uarg_zc->len == USHRT_MAX - 1 || bytelen > byte_limit) {
/* TCP can create new skb to attach new uarg */
if (sk->sk_type == SOCK_STREAM)
goto new_alloc;
return NULL;
}
next = (u32)atomic_read(&sk->sk_zckey);
if ((u32)(uarg_zc->id + uarg_zc->len) == next) {
if (mm_account_pinned_pages(&uarg_zc->mmp, size))
return NULL;
uarg_zc->len++;
uarg_zc->bytelen = bytelen;
atomic_set(&sk->sk_zckey, ++next);
/* no extra ref when appending to datagram (MSG_MORE) */
if (sk->sk_type == SOCK_STREAM)
net_zcopy_get(uarg);
return uarg;
}
}
new_alloc:
return msg_zerocopy_alloc(sk, size);
}
EXPORT_SYMBOL_GPL(msg_zerocopy_realloc);
static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
u32 old_lo, old_hi;
u64 sum_len;
old_lo = serr->ee.ee_info;
old_hi = serr->ee.ee_data;
sum_len = old_hi - old_lo + 1ULL + len;
if (sum_len >= (1ULL << 32))
return false;
if (lo != old_hi + 1)
return false;
serr->ee.ee_data += len;
return true;
}
static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg)
{
struct sk_buff *tail, *skb = skb_from_uarg(uarg);
struct sock_exterr_skb *serr;
struct sock *sk = skb->sk;
struct sk_buff_head *q;
unsigned long flags;
bool is_zerocopy;
u32 lo, hi;
u16 len;
mm_unaccount_pinned_pages(&uarg->mmp);
/* if !len, there was only 1 call, and it was aborted
* so do not queue a completion notification
*/
if (!uarg->len || sock_flag(sk, SOCK_DEAD))
goto release;
len = uarg->len;
lo = uarg->id;
hi = uarg->id + len - 1;
is_zerocopy = uarg->zerocopy;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = 0;
serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY;
serr->ee.ee_data = hi;
serr->ee.ee_info = lo;
if (!is_zerocopy)
serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED;
q = &sk->sk_error_queue;
spin_lock_irqsave(&q->lock, flags);
tail = skb_peek_tail(q);
if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY ||
!skb_zerocopy_notify_extend(tail, lo, len)) {
__skb_queue_tail(q, skb);
skb = NULL;
}
spin_unlock_irqrestore(&q->lock, flags);
sk_error_report(sk);
release:
consume_skb(skb);
sock_put(sk);
}
static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg,
bool success)
{
struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg);
uarg_zc->zerocopy = uarg_zc->zerocopy & success;
if (refcount_dec_and_test(&uarg->refcnt))
__msg_zerocopy_callback(uarg_zc);
}
void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
struct sock *sk = skb_from_uarg(uarg_to_msgzc(uarg))->sk;
atomic_dec(&sk->sk_zckey);
uarg_to_msgzc(uarg)->len--;
if (have_uref)
msg_zerocopy_complete(NULL, uarg, true);
}
EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort);
const struct ubuf_info_ops msg_zerocopy_ubuf_ops = {
.complete = msg_zerocopy_complete,
};
EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops);
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
struct ubuf_info *uarg)
{
int err, orig_len = skb->len;
if (uarg->ops->link_skb) {
err = uarg->ops->link_skb(skb, uarg);
if (err)
return err;
} else {
struct ubuf_info *orig_uarg = skb_zcopy(skb);
/* An skb can only point to one uarg. This edge case happens
* when TCP appends to an skb, but zerocopy_realloc triggered
* a new alloc.
*/
if (orig_uarg && uarg != orig_uarg)
return -EEXIST;
}
err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
struct sock *save_sk = skb->sk;
/* Streams do not free skb on error. Reset to prev state. */
iov_iter_revert(&msg->msg_iter, skb->len - orig_len);
skb->sk = sk;
___pskb_trim(skb, orig_len);
skb->sk = save_sk;
return err;
}
skb_zcopy_set(skb, uarg, NULL);
return skb->len - orig_len;
}
EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
void __skb_zcopy_downgrade_managed(struct sk_buff *skb)
{
int i;
skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i);
}
EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed);
static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig,
gfp_t gfp_mask)
{
if (skb_zcopy(orig)) {
if (skb_zcopy(nskb)) {
/* !gfp_mask callers are verified to !skb_zcopy(nskb) */
if (!gfp_mask) {
WARN_ON_ONCE(1);
return -ENOMEM;
}
if (skb_uarg(nskb) == skb_uarg(orig))
return 0;
if (skb_copy_ubufs(nskb, GFP_ATOMIC))
return -EIO;
}
skb_zcopy_set(nskb, skb_uarg(orig), NULL);
}
return 0;
}
/**
* skb_copy_ubufs - copy userspace skb frags buffers to kernel
* @skb: the skb to modify
* @gfp_mask: allocation priority
*
* This must be called on skb with SKBFL_ZEROCOPY_ENABLE.
* It will copy all frags into kernel and drop the reference
* to userspace pages.
*
* If this function is called from an interrupt gfp_mask() must be
* %GFP_ATOMIC.
*
* Returns 0 on success or a negative error code on failure
* to allocate kernel memory to copy to.
*/
int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
{
int num_frags = skb_shinfo(skb)->nr_frags;
struct page *page, *head = NULL;
int i, order, psize, new_frags;
u32 d_off;
if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
return -EINVAL;
if (!skb_frags_readable(skb))
return -EFAULT;
if (!num_frags)
goto release;
/* We might have to allocate high order pages, so compute what minimum
* page order is needed.
*/
order = 0;
while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb))
order++;
psize = (PAGE_SIZE << order);
new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order);
for (i = 0; i < new_frags; i++) {
page = alloc_pages(gfp_mask | __GFP_COMP, order);
if (!page) {
while (head) {
struct page *next = (struct page *)page_private(head);
put_page(head);
head = next;
}
return -ENOMEM;
}
set_page_private(page, (unsigned long)head);
head = page;
}
page = head;
d_off = 0;
for (i = 0; i < num_frags; i++) {
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f),
p, p_off, p_len, copied) {
u32 copy, done = 0;
vaddr = kmap_atomic(p);
while (done < p_len) {
if (d_off == psize) {
d_off = 0;
page = (struct page *)page_private(page);
}
copy = min_t(u32, psize - d_off, p_len - done);
memcpy(page_address(page) + d_off,
vaddr + p_off + done, copy);
done += copy;
d_off += copy;
}
kunmap_atomic(vaddr);
}
}
/* skb frags release userspace buffers */
for (i = 0; i < num_frags; i++)
skb_frag_unref(skb, i);
/* skb frags point to kernel buffers */
for (i = 0; i < new_frags - 1; i++) {
__skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize);
head = (struct page *)page_private(head);
}
__skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0,
d_off);
skb_shinfo(skb)->nr_frags = new_frags;
release:
skb_zcopy_clear(skb, false);
return 0;
}
EXPORT_SYMBOL_GPL(skb_copy_ubufs);
/**
* skb_clone - duplicate an sk_buff
* @skb: buffer to clone
* @gfp_mask: allocation priority
*
* Duplicate an &sk_buff. The new one is not owned by a socket. Both
* copies share the same packet data but not structure. The new
* buffer has a reference count of 1. If the allocation fails the
* function returns %NULL otherwise the new buffer is returned.
*
* If this function is called from an interrupt gfp_mask() must be
* %GFP_ATOMIC.
*/
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff_fclones *fclones = container_of(skb,
struct sk_buff_fclones,
skb1);
struct sk_buff *n;
if (skb_orphan_frags(skb, gfp_mask))
return NULL;
if (skb->fclone == SKB_FCLONE_ORIG &&
refcount_read(&fclones->fclone_ref) == 1) {
n = &fclones->skb2;
refcount_set(&fclones->fclone_ref, 2);
n->fclone = SKB_FCLONE_CLONE;
} else {
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask);
if (!n)
return NULL;
n->fclone = SKB_FCLONE_UNAVAILABLE;
}
return __skb_clone(n, skb);
}
EXPORT_SYMBOL(skb_clone);
void skb_headers_offset_update(struct sk_buff *skb, int off)
{
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += off;
/* {transport,network,mac}_header and tail are relative to skb->head */
skb->transport_header += off;
skb->network_header += off;
if (skb_mac_header_was_set(skb)) skb->mac_header += off;
skb->inner_transport_header += off;
skb->inner_network_header += off;
skb->inner_mac_header += off;
}
EXPORT_SYMBOL(skb_headers_offset_update);
void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
{
__copy_skb_header(new, old);
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
EXPORT_SYMBOL(skb_copy_header);
static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
{
if (skb_pfmemalloc(skb))
return SKB_ALLOC_RX;
return 0;
}
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data. This is used when the
* caller wishes to modify the data and needs a private copy of the
* data to alter. Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* As by-product this function converts non-linear &sk_buff to linear
* one, so that &sk_buff becomes completely private and caller is allowed
* to modify all the data of returned buffer. This means that this
* function is not recommended for use in circumstances when only
* header is going to be modified. Use pskb_copy() instead.
*/
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff *n;
unsigned int size;
int headerlen;
if (!skb_frags_readable(skb))
return NULL;
if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
return NULL;
headerlen = skb_headroom(skb);
size = skb_end_offset(skb) + skb->data_len;
n = __alloc_skb(size, gfp_mask,
skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
/* Set the data pointer */
skb_reserve(n, headerlen);
/* Set the tail pointer and length */
skb_put(n, skb->len);
BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
skb_copy_header(n, skb);
return n;
}
EXPORT_SYMBOL(skb_copy);
/**
* __pskb_copy_fclone - create copy of an sk_buff with private head.
* @skb: buffer to copy
* @headroom: headroom of new skb
* @gfp_mask: allocation priority
* @fclone: if true allocate the copy of the skb from the fclone
* cache instead of the head cache; it is recommended to set this
* to true for the cases where the copy will likely be cloned
*
* Make a copy of both an &sk_buff and part of its data, located
* in header. Fragmented data remain shared. This is used when
* the caller wishes to modify only header of &sk_buff and needs
* private copy of the header to alter. Returns %NULL on failure
* or the pointer to the buffer on success.
* The returned buffer has a reference count of 1.
*/
struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
gfp_t gfp_mask, bool fclone)
{
unsigned int size = skb_headlen(skb) + headroom;
int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0);
struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE);
if (!n)
goto out;
/* Set the data pointer */
skb_reserve(n, headroom);
/* Set the tail pointer and length */
skb_put(n, skb_headlen(skb));
/* Copy the bytes */
skb_copy_from_linear_data(skb, n->data, n->len);
n->truesize += skb->data_len;
n->data_len = skb->data_len;
n->len = skb->len;
if (skb_shinfo(skb)->nr_frags) {
int i;
if (skb_orphan_frags(skb, gfp_mask) ||
skb_zerocopy_clone(n, skb, gfp_mask)) {
kfree_skb(n);
n = NULL;
goto out;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
skb_frag_ref(skb, i);
}
skb_shinfo(n)->nr_frags = i;
}
if (skb_has_frag_list(skb)) {
skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list;
skb_clone_fraglist(n);
}
skb_copy_header(n, skb);
out:
return n;
}
EXPORT_SYMBOL(__pskb_copy_fclone);
/**
* pskb_expand_head - reallocate header of &sk_buff
* @skb: buffer to reallocate
* @nhead: room to add at head
* @ntail: room to add at tail
* @gfp_mask: allocation priority
*
* Expands (or creates identical copy, if @nhead and @ntail are zero)
* header of @skb. &sk_buff itself is not changed. &sk_buff MUST have
* reference count of 1. Returns zero in the case of success or error,
* if expansion failed. In the last case, &sk_buff is not changed.
*
* All the pointers pointing into skb header may change and must be
* reloaded after call to this function.
*/
int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
gfp_t gfp_mask)
{
unsigned int osize = skb_end_offset(skb);
unsigned int size = osize + nhead + ntail;
long off;
u8 *data;
int i;
BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); skb_zcopy_downgrade_managed(skb);
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
goto nodata;
size = SKB_WITH_OVERHEAD(size);
/* Copy only real data... and, alas, header. This should be
* optimized for the cases when header is void.
*/
memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head);
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb),
offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags]));
/*
* if shinfo is shared we must drop the old head gracefully, but if it
* is not we can just drop the old head and let the existing refcount
* be since all we did is relocate the values
*/
if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask))
goto nofrags;
if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb);
skb_release_data(skb, SKB_CONSUMED);
} else {
skb_free_head(skb);
}
off = (data + nhead) - skb->head;
skb->head = data;
skb->head_frag = 0;
skb->data += off;
skb_set_end_offset(skb, size);
#ifdef NET_SKBUFF_DATA_USES_OFFSET
off = nhead;
#endif
skb->tail += off;
skb_headers_offset_update(skb, nhead);
skb->cloned = 0;
skb->hdr_len = 0;
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
skb_metadata_clear(skb);
/* It is not generally safe to change skb->truesize.
* For the moment, we really care of rx path, or
* when skb is orphaned (not attached to a socket).
*/
if (!skb->sk || skb->destructor == sock_edemux)
skb->truesize += size - osize;
return 0;
nofrags:
skb_kfree_head(data, size);
nodata:
return -ENOMEM;
}
EXPORT_SYMBOL(pskb_expand_head);
/* Make private copy of skb with writable head and some headroom */
struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
{
struct sk_buff *skb2;
int delta = headroom - skb_headroom(skb);
if (delta <= 0)
skb2 = pskb_copy(skb, GFP_ATOMIC);
else {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0,
GFP_ATOMIC)) {
kfree_skb(skb2);
skb2 = NULL;
}
}
return skb2;
}
EXPORT_SYMBOL(skb_realloc_headroom);
/* Note: We plan to rework this in linux-6.4 */
int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
{
unsigned int saved_end_offset, saved_truesize;
struct skb_shared_info *shinfo;
int res;
saved_end_offset = skb_end_offset(skb);
saved_truesize = skb->truesize;
res = pskb_expand_head(skb, 0, 0, pri);
if (res)
return res;
skb->truesize = saved_truesize;
if (likely(skb_end_offset(skb) == saved_end_offset))
return 0;
/* We can not change skb->end if the original or new value
* is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head().
*/
if (saved_end_offset == SKB_SMALL_HEAD_HEADROOM ||
skb_end_offset(skb) == SKB_SMALL_HEAD_HEADROOM) {
/* We think this path should not be taken.
* Add a temporary trace to warn us just in case.
*/
pr_err_once("__skb_unclone_keeptruesize() skb_end_offset() %u -> %u\n",
saved_end_offset, skb_end_offset(skb));
WARN_ON_ONCE(1);
return 0;
}
shinfo = skb_shinfo(skb);
/* We are about to change back skb->end,
* we need to move skb_shinfo() to its new location.
*/
memmove(skb->head + saved_end_offset,
shinfo,
offsetof(struct skb_shared_info, frags[shinfo->nr_frags]));
skb_set_end_offset(skb, saved_end_offset);
return 0;
}
/**
* skb_expand_head - reallocate header of &sk_buff
* @skb: buffer to reallocate
* @headroom: needed headroom
*
* Unlike skb_realloc_headroom, this one does not allocate a new skb
* if possible; copies skb->sk to new skb as needed
* and frees original skb in case of failures.
*
* It expect increased headroom and generates warning otherwise.
*/
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
{
int delta = headroom - skb_headroom(skb);
int osize = skb_end_offset(skb);
struct sock *sk = skb->sk;
if (WARN_ONCE(delta <= 0,
"%s is expecting an increase in the headroom", __func__))
return skb;
delta = SKB_DATA_ALIGN(delta);
/* pskb_expand_head() might crash, if skb is shared. */
if (skb_shared(skb) || !is_skb_wmem(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb))
goto fail;
if (sk)
skb_set_owner_w(nskb, sk);
consume_skb(skb);
skb = nskb;
}
if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
goto fail;
if (sk && is_skb_wmem(skb)) {
delta = skb_end_offset(skb) - osize;
refcount_add(delta, &sk->sk_wmem_alloc);
skb->truesize += delta;
}
return skb;
fail:
kfree_skb(skb);
return NULL;
}
EXPORT_SYMBOL(skb_expand_head);
/**
* skb_copy_expand - copy and expand sk_buff
* @skb: buffer to copy
* @newheadroom: new free bytes at head
* @newtailroom: new free bytes at tail
* @gfp_mask: allocation priority
*
* Make a copy of both an &sk_buff and its data and while doing so
* allocate additional space.
*
* This is used when the caller wishes to modify the data and needs a
* private copy of the data to alter as well as more space for new fields.
* Returns %NULL on failure or the pointer to the buffer
* on success. The returned buffer has a reference count of 1.
*
* You must pass %GFP_ATOMIC as the allocation priority if this function
* is called from an interrupt.
*/
struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
int newheadroom, int newtailroom,
gfp_t gfp_mask)
{
/*
* Allocate the copy buffer
*/
int head_copy_len, head_copy_off;
struct sk_buff *n;
int oldheadroom;
if (!skb_frags_readable(skb))
return NULL;
if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
return NULL;
oldheadroom = skb_headroom(skb);
n = __alloc_skb(newheadroom + skb->len + newtailroom,
gfp_mask, skb_alloc_rx_flag(skb),
NUMA_NO_NODE);
if (!n)
return NULL;
skb_reserve(n, newheadroom);
/* Set the tail pointer and length */
skb_put(n, skb->len);
head_copy_len = oldheadroom;
head_copy_off = 0;
if (newheadroom <= head_copy_len)
head_copy_len = newheadroom;
else
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
skb->len + head_copy_len));
skb_copy_header(n, skb);
skb_headers_offset_update(n, newheadroom - oldheadroom);
return n;
}
EXPORT_SYMBOL(skb_copy_expand);
/**
* __skb_pad - zero pad the tail of an skb
* @skb: buffer to pad
* @pad: space to pad
* @free_on_error: free buffer on error
*
* Ensure that a buffer is followed by a padding area that is zero
* filled. Used by network drivers which may DMA or transfer data
* beyond the buffer end onto the wire.
*
* May return error in out of memory cases. The skb is freed on error
* if @free_on_error is true.
*/
int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error)
{
int err;
int ntail;
/* If the skbuff is non linear tailroom is always zero.. */
if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
memset(skb->data+skb->len, 0, pad);
return 0;
}
ntail = skb->data_len + pad - (skb->end - skb->tail);
if (likely(skb_cloned(skb) || ntail > 0)) {
err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC);
if (unlikely(err))
goto free_skb;
}
/* FIXME: The use of this function with non-linear skb's really needs
* to be audited.
*/
err = skb_linearize(skb);
if (unlikely(err))
goto free_skb;
memset(skb->data + skb->len, 0, pad);
return 0;
free_skb:
if (free_on_error)
kfree_skb(skb);
return err;
}
EXPORT_SYMBOL(__skb_pad);
/**
* pskb_put - add data to the tail of a potentially fragmented buffer
* @skb: start of the buffer to use
* @tail: tail fragment of the buffer to use
* @len: amount of data to add
*
* This function extends the used data area of the potentially
* fragmented buffer. @tail must be the last fragment of @skb -- or
* @skb itself. If this would exceed the total buffer size the kernel
* will panic. A pointer to the first byte of the extra data is
* returned.
*/
void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
{
if (tail != skb) {
skb->data_len += len;
skb->len += len;
}
return skb_put(tail, len);
}
EXPORT_SYMBOL_GPL(pskb_put);
/**
* skb_put - add data to a buffer
* @skb: buffer to use
* @len: amount of data to add
*
* This function extends the used data area of the buffer. If this would
* exceed the total buffer size the kernel will panic. A pointer to the
* first byte of the extra data is returned.
*/
void *skb_put(struct sk_buff *skb, unsigned int len)
{ void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb);
skb->tail += len;
skb->len += len;
if (unlikely(skb->tail > skb->end))
skb_over_panic(skb, len, __builtin_return_address(0));
return tmp;
}
EXPORT_SYMBOL(skb_put);
/**
* skb_push - add data to the start of a buffer
* @skb: buffer to use
* @len: amount of data to add
*
* This function extends the used data area of the buffer at the buffer
* start. If this would exceed the total buffer headroom the kernel will
* panic. A pointer to the first byte of the extra data is returned.
*/
void *skb_push(struct sk_buff *skb, unsigned int len)
{
skb->data -= len;
skb->len += len;
if (unlikely(skb->data < skb->head))
skb_under_panic(skb, len, __builtin_return_address(0));
return skb->data;
}
EXPORT_SYMBOL(skb_push);
/**
* skb_pull - remove data from the start of a buffer
* @skb: buffer to use
* @len: amount of data to remove
*
* This function removes data from the start of a buffer, returning
* the memory to the headroom. A pointer to the next data in the buffer
* is returned. Once the data has been pulled future pushes will overwrite
* the old data.
*/
void *skb_pull(struct sk_buff *skb, unsigned int len)
{ return skb_pull_inline(skb, len);
}
EXPORT_SYMBOL(skb_pull);
/**
* skb_pull_data - remove data from the start of a buffer returning its
* original position.
* @skb: buffer to use
* @len: amount of data to remove
*
* This function removes data from the start of a buffer, returning
* the memory to the headroom. A pointer to the original data in the buffer
* is returned after checking if there is enough data to pull. Once the
* data has been pulled future pushes will overwrite the old data.
*/
void *skb_pull_data(struct sk_buff *skb, size_t len)
{
void *data = skb->data;
if (skb->len < len)
return NULL;
skb_pull(skb, len);
return data;
}
EXPORT_SYMBOL(skb_pull_data);
/**
* skb_trim - remove end from a buffer
* @skb: buffer to alter
* @len: new length
*
* Cut the length of a buffer down by removing data from the tail. If
* the buffer is already under the length specified it is not modified.
* The skb must be linear.
*/
void skb_trim(struct sk_buff *skb, unsigned int len)
{ if (skb->len > len) __skb_trim(skb, len);
}
EXPORT_SYMBOL(skb_trim);
/* Trims skb to length len. It can change skb pointers.
*/
int ___pskb_trim(struct sk_buff *skb, unsigned int len)
{
struct sk_buff **fragp;
struct sk_buff *frag;
int offset = skb_headlen(skb);
int nfrags = skb_shinfo(skb)->nr_frags;
int i;
int err;
if (skb_cloned(skb) &&
unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
return err;
i = 0;
if (offset >= len)
goto drop_pages;
for (; i < nfrags; i++) {
int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (end < len) {
offset = end;
continue;
}
skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset);
drop_pages:
skb_shinfo(skb)->nr_frags = i;
for (; i < nfrags; i++)
skb_frag_unref(skb, i);
if (skb_has_frag_list(skb)) skb_drop_fraglist(skb);
goto done;
}
for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp);
fragp = &frag->next) {
int end = offset + frag->len;
if (skb_shared(frag)) {
struct sk_buff *nfrag;
nfrag = skb_clone(frag, GFP_ATOMIC);
if (unlikely(!nfrag))
return -ENOMEM;
nfrag->next = frag->next;
consume_skb(frag);
frag = nfrag;
*fragp = frag;
}
if (end < len) {
offset = end;
continue;
}
if (end > len && unlikely((err = pskb_trim(frag, len - offset))))
return err;
if (frag->next) skb_drop_list(&frag->next);
break;
}
done:
if (len > skb_headlen(skb)) {
skb->data_len -= skb->len - len;
skb->len = len;
} else {
skb->len = len;
skb->data_len = 0;
skb_set_tail_pointer(skb, len);
}
if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb);
return 0;
}
EXPORT_SYMBOL(___pskb_trim);
/* Note : use pskb_trim_rcsum() instead of calling this directly
*/
int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
{ if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len;
skb->csum = csum_block_sub(skb->csum,
skb_checksum(skb, len, delta, 0),
len);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len;
int offset = skb_checksum_start_offset(skb) + skb->csum_offset;
if (offset + sizeof(__sum16) > hdlen)
return -EINVAL;
}
return __pskb_trim(skb, len);
}
EXPORT_SYMBOL(pskb_trim_rcsum_slow);
/**
* __pskb_pull_tail - advance tail of skb header
* @skb: buffer to reallocate
* @delta: number of bytes to advance tail
*
* The function makes a sense only on a fragmented &sk_buff,
* it expands header moving its tail forward and copying necessary
* data from fragmented part.
*
* &sk_buff MUST have reference count of 1.
*
* Returns %NULL (and &sk_buff does not change) if pull failed
* or value of new tail of skb in the case of success.
*
* All the pointers pointing into skb header may change and must be
* reloaded after call to this function.
*/
/* Moves tail of skb head forward, copying data from fragmented part,
* when it is necessary.
* 1. It may fail due to malloc failure.
* 2. It may change skb pointers.
*
* It is pretty complicated. Luckily, it is called only in exceptional cases.
*/
void *__pskb_pull_tail(struct sk_buff *skb, int delta)
{
/* If skb has not enough free space at tail, get new one
* plus 128 bytes for future expansions. If we have enough
* room at tail, reallocate without expansion only if skb is cloned.
*/
int i, k, eat = (skb->tail + delta) - skb->end;
if (!skb_frags_readable(skb))
return NULL;
if (eat > 0 || skb_cloned(skb)) {
if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
GFP_ATOMIC))
return NULL;
}
BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
skb_tail_pointer(skb), delta));
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
*/
if (!skb_has_frag_list(skb))
goto pull_pages;
/* Estimate size of pulled pages. */
eat = delta;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (size >= eat)
goto pull_pages;
eat -= size;
}
/* If we need update frag list, we are in troubles.
* Certainly, it is possible to add an offset to skb data,
* but taking into account that pulling is expected to
* be very rare operation, it is worth to fight against
* further bloating skb head and crucify ourselves here instead.
* Pure masohism, indeed. 8)8)
*/
if (eat) {
struct sk_buff *list = skb_shinfo(skb)->frag_list;
struct sk_buff *clone = NULL;
struct sk_buff *insp = NULL;
do {
if (list->len <= eat) {
/* Eaten as whole. */
eat -= list->len;
list = list->next;
insp = list;
} else {
/* Eaten partially. */
if (skb_is_gso(skb) && !list->head_frag &&
skb_headlen(list))
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
if (skb_shared(list)) {
/* Sucks! We need to fork list. :-( */
clone = skb_clone(list, GFP_ATOMIC);
if (!clone)
return NULL;
insp = list->next;
list = clone;
} else {
/* This may be pulled without
* problems. */
insp = list;
}
if (!pskb_pull(list, eat)) {
kfree_skb(clone);
return NULL;
}
break;
}
} while (eat);
/* Free pulled out fragments. */
while ((list = skb_shinfo(skb)->frag_list) != insp) {
skb_shinfo(skb)->frag_list = list->next;
consume_skb(list);
}
/* And insert new clone at head. */
if (clone) {
clone->next = list;
skb_shinfo(skb)->frag_list = clone;
}
}
/* Success! Now we may commit changes to skb data. */
pull_pages:
eat = delta;
k = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (size <= eat) {
skb_frag_unref(skb, i);
eat -= size;
} else {
skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
*frag = skb_shinfo(skb)->frags[i];
if (eat) {
skb_frag_off_add(frag, eat);
skb_frag_size_sub(frag, eat);
if (!i)
goto end;
eat = 0;
}
k++;
}
}
skb_shinfo(skb)->nr_frags = k;
end:
skb->tail += delta;
skb->data_len -= delta;
if (!skb->data_len)
skb_zcopy_clear(skb, false);
return skb_tail_pointer(skb);
}
EXPORT_SYMBOL(__pskb_pull_tail);
/**
* skb_copy_bits - copy bits from skb to kernel buffer
* @skb: source skb
* @offset: offset in source
* @to: destination buffer
* @len: number of bytes to copy
*
* Copy the specified number of bytes from the source skb to the
* destination buffer.
*
* CAUTION ! :
* If its prototype is ever changed,
* check arch/{*}/net/{*}.S files,
* since it is called from BPF assembly code.
*/
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
int start = skb_headlen(skb);
struct sk_buff *frag_iter;
int i, copy;
if (offset > (int)skb->len - len)
goto fault;
/* Copy header. */
if ((copy = start - offset) > 0) {
if (copy > len)
copy = len;
skb_copy_from_linear_data_offset(skb, offset, to, copy);
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
if (!skb_frags_readable(skb))
goto fault;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(f);
if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
if (copy > len)
copy = len;
skb_frag_foreach_page(f,
skb_frag_off(f) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
memcpy(to + copied, vaddr + p_off, p_len);
kunmap_atomic(vaddr);
}
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_copy_bits(frag_iter, offset - start, to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
to += copy;
}
start = end;
}
if (!len)
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_copy_bits);
/*
* Callback from splice_to_pipe(), if we need to release some pages
* at the end of the spd in case we error'ed out in filling the pipe.
*/
static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
{
put_page(spd->pages[i]);
}
static struct page *linear_to_page(struct page *page, unsigned int *len,
unsigned int *offset,
struct sock *sk)
{
struct page_frag *pfrag = sk_page_frag(sk);
if (!sk_page_frag_refill(sk, pfrag))
return NULL;
*len = min_t(unsigned int, *len, pfrag->size - pfrag->offset);
memcpy(page_address(pfrag->page) + pfrag->offset,
page_address(page) + *offset, *len);
*offset = pfrag->offset;
pfrag->offset += *len;
return pfrag->page;
}
static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
struct page *page,
unsigned int offset)
{
return spd->nr_pages &&
spd->pages[spd->nr_pages - 1] == page &&
(spd->partial[spd->nr_pages - 1].offset +
spd->partial[spd->nr_pages - 1].len == offset);
}
/*
* Fill page/offset/length into spd, if it can hold more pages.
*/
static bool spd_fill_page(struct splice_pipe_desc *spd,
struct pipe_inode_info *pipe, struct page *page,
unsigned int *len, unsigned int offset,
bool linear,
struct sock *sk)
{
if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
return true;
if (linear) {
page = linear_to_page(page, len, &offset, sk);
if (!page)
return true;
}
if (spd_can_coalesce(spd, page, offset)) {
spd->partial[spd->nr_pages - 1].len += *len;
return false;
}
get_page(page);
spd->pages[spd->nr_pages] = page;
spd->partial[spd->nr_pages].len = *len;
spd->partial[spd->nr_pages].offset = offset;
spd->nr_pages++;
return false;
}
static bool __splice_segment(struct page *page, unsigned int poff,
unsigned int plen, unsigned int *off,
unsigned int *len,
struct splice_pipe_desc *spd, bool linear,
struct sock *sk,
struct pipe_inode_info *pipe)
{
if (!*len)
return true;
/* skip this segment if already processed */
if (*off >= plen) {
*off -= plen;
return false;
}
/* ignore any bits we already processed */
poff += *off;
plen -= *off;
*off = 0;
do {
unsigned int flen = min(*len, plen);
if (spd_fill_page(spd, pipe, page, &flen, poff,
linear, sk))
return true;
poff += flen;
plen -= flen;
*len -= flen;
} while (*len && plen);
return false;
}
/*
* Map linear and fragment data from the skb to spd. It reports true if the
* pipe is full or if we already spliced the requested length.
*/
static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
unsigned int *offset, unsigned int *len,
struct splice_pipe_desc *spd, struct sock *sk)
{
int seg;
struct sk_buff *iter;
/* map the linear part :
* If skb->head_frag is set, this 'linear' part is backed by a
* fragment, and if the head is not shared with any clones then
* we can avoid a copy since we own the head portion of this page.
*/
if (__splice_segment(virt_to_page(skb->data),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
offset, len, spd,
skb_head_is_locked(skb),
sk, pipe))
return true;
/*
* then map the fragments
*/
if (!skb_frags_readable(skb))
return false;
for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
if (WARN_ON_ONCE(!skb_frag_page(f)))
return false;
if (__splice_segment(skb_frag_page(f),
skb_frag_off(f), skb_frag_size(f),
offset, len, spd, false, sk, pipe))
return true;
}
skb_walk_frags(skb, iter) {
if (*offset >= iter->len) {
*offset -= iter->len;
continue;
}
/* __skb_splice_bits() only fails if the output has no room
* left, so no point in going over the frag_list for the error
* case.
*/
if (__skb_splice_bits(iter, pipe, offset, len, spd, sk))
return true;
}
return false;
}
/*
* Map data from the skb to a pipe. Should handle both the linear part,
* the fragments, and the frag list.
*/
int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
unsigned int flags)
{
struct partial_page partial[MAX_SKB_FRAGS];
struct page *pages[MAX_SKB_FRAGS];
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.nr_pages_max = MAX_SKB_FRAGS,
.ops = &nosteal_pipe_buf_ops,
.spd_release = sock_spd_release,
};
int ret = 0;
__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk);
if (spd.nr_pages)
ret = splice_to_pipe(pipe, &spd);
return ret;
}
EXPORT_SYMBOL_GPL(skb_splice_bits);
static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
size_t size = msg_data_left(msg);
if (!sock)
return -EINVAL;
if (!sock->ops->sendmsg_locked)
return sock_no_sendmsg_locked(sk, msg, size);
return sock->ops->sendmsg_locked(sk, msg, size);
}
static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
if (!sock)
return -EINVAL;
return sock_sendmsg(sock, msg);
}
typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
int len, sendmsg_func sendmsg)
{
unsigned int orig_len = len;
struct sk_buff *head = skb;
unsigned short fragidx;
int slen, ret;
do_frag_list:
/* Deal with head data */
while (offset < skb_headlen(skb) && len) {
struct kvec kv;
struct msghdr msg;
slen = min_t(int, len, skb_headlen(skb) - offset);
kv.iov_base = skb->data + offset;
kv.iov_len = slen;
memset(&msg, 0, sizeof(msg));
msg.msg_flags = MSG_DONTWAIT;
iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
offset += ret;
len -= ret;
}
/* All the data was skb head? */
if (!len)
goto out;
/* Make offset relative to start of frags */
offset -= skb_headlen(skb);
/* Find where we are in frag list */
for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
if (offset < skb_frag_size(frag))
break;
offset -= skb_frag_size(frag);
}
for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
slen = min_t(size_t, len, skb_frag_size(frag) - offset);
while (slen) {
struct bio_vec bvec;
struct msghdr msg = {
.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
};
bvec_set_page(&bvec, skb_frag_page(frag), slen,
skb_frag_off(frag) + offset);
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
slen);
ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
len -= ret;
offset += ret;
slen -= ret;
}
offset = 0;
}
if (len) {
/* Process any frag lists */
if (skb == head) {
if (skb_has_frag_list(skb)) {
skb = skb_shinfo(skb)->frag_list;
goto do_frag_list;
}
} else if (skb->next) {
skb = skb->next;
goto do_frag_list;
}
}
out:
return orig_len - len;
error:
return orig_len == len ? ret : orig_len - len;
}
/* Send skb data on a socket. Socket must be locked. */
int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
int len)
{
return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
/* Send skb data on a socket. Socket must be unlocked. */
int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
{
return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
}
/**
* skb_store_bits - store bits from kernel buffer to skb
* @skb: destination buffer
* @offset: offset in destination
* @from: source buffer
* @len: number of bytes to copy
*
* Copy the specified number of bytes from the source buffer to the
* destination skb. This function handles all the messy bits of
* traversing fragment lists and such.
*/
int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
{
int start = skb_headlen(skb);
struct sk_buff *frag_iter;
int i, copy;
if (offset > (int)skb->len - len)
goto fault;
if ((copy = start - offset) > 0) {
if (copy > len)
copy = len;
skb_copy_to_linear_data_offset(skb, offset, from, copy);
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
if (!skb_frags_readable(skb))
goto fault;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied;
struct page *p;
u8 *vaddr;
if (copy > len)
copy = len;
skb_frag_foreach_page(frag,
skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
memcpy(vaddr + p_off, from + copied, p_len);
kunmap_atomic(vaddr);
}
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
if (skb_store_bits(frag_iter, offset - start,
from, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
from += copy;
}
start = end;
}
if (!len)
return 0;
fault:
return -EFAULT;
}
EXPORT_SYMBOL(skb_store_bits);
/* Checksum skb data. */
__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
__wsum csum, const struct skb_checksum_ops *ops)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int pos = 0;
/* Checksum header. */
if (copy > 0) {
if (copy > len)
copy = len;
csum = INDIRECT_CALL_1(ops->update, csum_partial_ext,
skb->data + offset, copy, csum);
if ((len -= copy) == 0)
return csum;
offset += copy;
pos = copy;
}
if (WARN_ON_ONCE(!skb_frags_readable(skb)))
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
u32 p_off, p_len, copied;
struct page *p;
__wsum csum2;
u8 *vaddr;
if (copy > len)
copy = len;
skb_frag_foreach_page(frag,
skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
csum2 = INDIRECT_CALL_1(ops->update,
csum_partial_ext,
vaddr + p_off, p_len, 0);
kunmap_atomic(vaddr);
csum = INDIRECT_CALL_1(ops->combine,
csum_block_add_ext, csum,
csum2, pos, p_len);
pos += p_len;
}
if (!(len -= copy))
return csum;
offset += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
__wsum csum2;
if (copy > len)
copy = len;
csum2 = __skb_checksum(frag_iter, offset - start,
copy, 0, ops);
csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext,
csum, csum2, pos, copy);
if ((len -= copy) == 0)
return csum;
offset += copy;
pos += copy;
}
start = end;
}
BUG_ON(len);
return csum;
}
EXPORT_SYMBOL(__skb_checksum);
__wsum skb_checksum(const struct sk_buff *skb, int offset,
int len, __wsum csum)
{
const struct skb_checksum_ops ops = {
.update = csum_partial_ext,
.combine = csum_block_add_ext,
};
return __skb_checksum(skb, offset, len, csum, &ops);
}
EXPORT_SYMBOL(skb_checksum);
/* Both of above in one bottle. */
__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
u8 *to, int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int pos = 0;
__wsum csum = 0;
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
csum = csum_partial_copy_nocheck(skb->data + offset, to,
copy);
if ((len -= copy) == 0)
return csum;
offset += copy;
to += copy;
pos = copy;
}
if (!skb_frags_readable(skb))
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
u32 p_off, p_len, copied;
struct page *p;
__wsum csum2;
u8 *vaddr;
if (copy > len)
copy = len;
skb_frag_foreach_page(frag,
skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
csum2 = csum_partial_copy_nocheck(vaddr + p_off,
to + copied,
p_len);
kunmap_atomic(vaddr);
csum = csum_block_add(csum, csum2, pos);
pos += p_len;
}
if (!(len -= copy))
return csum;
offset += copy;
to += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
__wsum csum2;
int end;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
csum2 = skb_copy_and_csum_bits(frag_iter,
offset - start,
to, copy);
csum = csum_block_add(csum, csum2, pos);
if ((len -= copy) == 0)
return csum;
offset += copy;
to += copy;
pos += copy;
}
start = end;
}
BUG_ON(len);
return csum;
}
EXPORT_SYMBOL(skb_copy_and_csum_bits);
__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
{
__sum16 sum;
sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
/* See comments in __skb_checksum_complete(). */
if (likely(!sum)) {
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev, skb);
}
if (!skb_shared(skb))
skb->csum_valid = !sum;
return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete_head);
/* This function assumes skb->csum already holds pseudo header's checksum,
* which has been changed from the hardware checksum, for example, by
* __skb_checksum_validate_complete(). And, the original skb->csum must
* have been validated unsuccessfully for CHECKSUM_COMPLETE case.
*
* It returns non-zero if the recomputed checksum is still invalid, otherwise
* zero. The new checksum is stored back into skb->csum unless the skb is
* shared.
*/
__sum16 __skb_checksum_complete(struct sk_buff *skb)
{
__wsum csum;
__sum16 sum;
csum = skb_checksum(skb, 0, skb->len, 0);
sum = csum_fold(csum_add(skb->csum, csum));
/* This check is inverted, because we already knew the hardware
* checksum is invalid before calling this function. So, if the
* re-computed checksum is valid instead, then we have a mismatch
* between the original skb->csum and skb_checksum(). This means either
* the original hardware checksum is incorrect or we screw up skb->csum
* when moving skb->data around.
*/
if (likely(!sum)) {
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev, skb);
}
if (!skb_shared(skb)) {
/* Save full packet checksum */
skb->csum = csum;
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum_complete_sw = 1;
skb->csum_valid = !sum;
}
return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete);
static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
{
net_warn_ratelimited(
"%s: attempt to compute crc32c without libcrc32c.ko\n",
__func__);
return 0;
}
static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2,
int offset, int len)
{
net_warn_ratelimited(
"%s: attempt to compute crc32c without libcrc32c.ko\n",
__func__);
return 0;
}
static const struct skb_checksum_ops default_crc32c_ops = {
.update = warn_crc32c_csum_update,
.combine = warn_crc32c_csum_combine,
};
const struct skb_checksum_ops *crc32c_csum_stub __read_mostly =
&default_crc32c_ops;
EXPORT_SYMBOL(crc32c_csum_stub);
/**
* skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
* @from: source buffer
*
* Calculates the amount of linear headroom needed in the 'to' skb passed
* into skb_zerocopy().
*/
unsigned int
skb_zerocopy_headlen(const struct sk_buff *from)
{
unsigned int hlen = 0;
if (!from->head_frag ||
skb_headlen(from) < L1_CACHE_BYTES ||
skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) {
hlen = skb_headlen(from);
if (!hlen)
hlen = from->len;
}
if (skb_has_frag_list(from))
hlen = from->len;
return hlen;
}
EXPORT_SYMBOL_GPL(skb_zerocopy_headlen);
/**
* skb_zerocopy - Zero copy skb to skb
* @to: destination buffer
* @from: source buffer
* @len: number of bytes to copy from source buffer
* @hlen: size of linear headroom in destination buffer
*
* Copies up to `len` bytes from `from` to `to` by creating references
* to the frags in the source buffer.
*
* The `hlen` as calculated by skb_zerocopy_headlen() specifies the
* headroom in the `to` buffer.
*
* Return value:
* 0: everything is OK
* -ENOMEM: couldn't orphan frags of @from due to lack of memory
* -EFAULT: skb_copy_bits() found some problem with skb geometry
*/
int
skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
{
int i, j = 0;
int plen = 0; /* length of skb->head fragment */
int ret;
struct page *page;
unsigned int offset;
BUG_ON(!from->head_frag && !hlen);
/* dont bother with small payloads */
if (len <= skb_tailroom(to))
return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
if (unlikely(ret))
return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len);
if (plen) {
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
__skb_fill_netmem_desc(to, 0, page_to_netmem(page),
offset, plen);
get_page(page);
j = 1;
len -= plen;
}
}
skb_len_add(to, len + plen);
if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
skb_tx_error(from);
return -ENOMEM;
}
skb_zerocopy_clone(to, from, GFP_ATOMIC);
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
int size;
if (!len)
break;
skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]),
len);
skb_frag_size_set(&skb_shinfo(to)->frags[j], size);
len -= size;
skb_frag_ref(to, j);
j++;
}
skb_shinfo(to)->nr_frags = j;
return 0;
}
EXPORT_SYMBOL_GPL(skb_zerocopy);
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
{
__wsum csum;
long csstart;
if (skb->ip_summed == CHECKSUM_PARTIAL)
csstart = skb_checksum_start_offset(skb);
else
csstart = skb_headlen(skb);
BUG_ON(csstart > skb_headlen(skb));
skb_copy_from_linear_data(skb, to, csstart);
csum = 0;
if (csstart != skb->len)
csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
skb->len - csstart);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
long csstuff = csstart + skb->csum_offset;
*((__sum16 *)(to + csstuff)) = csum_fold(csum);
}
}
EXPORT_SYMBOL(skb_copy_and_csum_dev);
/**
* skb_dequeue - remove from the head of the queue
* @list: list to dequeue from
*
* Remove the head of the list. The list lock is taken so the function
* may be used safely with other locking list functions. The head item is
* returned or %NULL if the list is empty.
*/
struct sk_buff *skb_dequeue(struct sk_buff_head *list)
{
unsigned long flags;
struct sk_buff *result;
spin_lock_irqsave(&list->lock, flags);
result = __skb_dequeue(list);
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
EXPORT_SYMBOL(skb_dequeue);
/**
* skb_dequeue_tail - remove from the tail of the queue
* @list: list to dequeue from
*
* Remove the tail of the list. The list lock is taken so the function
* may be used safely with other locking list functions. The tail item is
* returned or %NULL if the list is empty.
*/
struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list)
{
unsigned long flags;
struct sk_buff *result;
spin_lock_irqsave(&list->lock, flags);
result = __skb_dequeue_tail(list);
spin_unlock_irqrestore(&list->lock, flags);
return result;
}
EXPORT_SYMBOL(skb_dequeue_tail);
/**
* skb_queue_purge_reason - empty a list
* @list: list to empty
* @reason: drop reason
*
* Delete all buffers on an &sk_buff list. Each buffer is removed from
* the list and one reference dropped. This function takes the list
* lock and is atomic with respect to other list locking functions.
*/
void skb_queue_purge_reason(struct sk_buff_head *list,
enum skb_drop_reason reason)
{
struct sk_buff_head tmp;
unsigned long flags;
if (skb_queue_empty_lockless(list))
return;
__skb_queue_head_init(&tmp);
spin_lock_irqsave(&list->lock, flags);
skb_queue_splice_init(list, &tmp);
spin_unlock_irqrestore(&list->lock, flags);
__skb_queue_purge_reason(&tmp, reason);
}
EXPORT_SYMBOL(skb_queue_purge_reason);
/**
* skb_rbtree_purge - empty a skb rbtree
* @root: root of the rbtree to empty
* Return value: the sum of truesizes of all purged skbs.
*
* Delete all buffers on an &sk_buff rbtree. Each buffer is removed from
* the list and one reference dropped. This function does not take
* any lock. Synchronization should be handled by the caller (e.g., TCP
* out-of-order queue is protected by the socket lock).
*/
unsigned int skb_rbtree_purge(struct rb_root *root)
{
struct rb_node *p = rb_first(root);
unsigned int sum = 0;
while (p) {
struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
p = rb_next(p);
rb_erase(&skb->rbnode, root);
sum += skb->truesize;
kfree_skb(skb);
}
return sum;
}
void skb_errqueue_purge(struct sk_buff_head *list)
{
struct sk_buff *skb, *next;
struct sk_buff_head kill;
unsigned long flags;
__skb_queue_head_init(&kill);
spin_lock_irqsave(&list->lock, flags);
skb_queue_walk_safe(list, skb, next) {
if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY ||
SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING)
continue;
__skb_unlink(skb, list);
__skb_queue_tail(&kill, skb);
}
spin_unlock_irqrestore(&list->lock, flags);
__skb_queue_purge(&kill);
}
EXPORT_SYMBOL(skb_errqueue_purge);
/**
* skb_queue_head - queue a buffer at the list head
* @list: list to use
* @newsk: buffer to queue
*
* Queue a buffer at the start of the list. This function takes the
* list lock and can be used safely with other locking &sk_buff functions
* safely.
*
* A buffer cannot be placed on two lists at the same time.
*/
void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_queue_head(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
EXPORT_SYMBOL(skb_queue_head);
/**
* skb_queue_tail - queue a buffer at the list tail
* @list: list to use
* @newsk: buffer to queue
*
* Queue a buffer at the tail of the list. This function takes the
* list lock and can be used safely with other locking &sk_buff functions
* safely.
*
* A buffer cannot be placed on two lists at the same time.
*/
void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_queue_tail(list, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
EXPORT_SYMBOL(skb_queue_tail);
/**
* skb_unlink - remove a buffer from a list
* @skb: buffer to remove
* @list: list to use
*
* Remove a packet from a list. The list locks are taken and this
* function is atomic with respect to other list locked calls
*
* You must know what list the SKB is on.
*/
void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_unlink(skb, list);
spin_unlock_irqrestore(&list->lock, flags);
}
EXPORT_SYMBOL(skb_unlink);
/**
* skb_append - append a buffer
* @old: buffer to insert after
* @newsk: buffer to insert
* @list: list to use
*
* Place a packet after a given packet in a list. The list locks are taken
* and this function is atomic with respect to other list locked calls.
* A buffer cannot be placed on two lists at the same time.
*/
void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
{
unsigned long flags;
spin_lock_irqsave(&list->lock, flags);
__skb_queue_after(list, old, newsk);
spin_unlock_irqrestore(&list->lock, flags);
}
EXPORT_SYMBOL(skb_append);
static inline void skb_split_inside_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, const int pos)
{
int i;
skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len),
pos - len);
/* And move data appendix as is. */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
skb1->unreadable = skb->unreadable;
skb_shinfo(skb)->nr_frags = 0;
skb1->data_len = skb->data_len;
skb1->len += skb1->data_len;
skb->data_len = 0;
skb->len = len;
skb_set_tail_pointer(skb, len);
}
static inline void skb_split_no_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, int pos)
{
int i, k = 0;
const int nfrags = skb_shinfo(skb)->nr_frags;
skb_shinfo(skb)->nr_frags = 0;
skb1->len = skb1->data_len = skb->len - len;
skb->len = len;
skb->data_len = len - pos;
for (i = 0; i < nfrags; i++) {
int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (pos + size > len) {
skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < len) {
/* Split frag.
* We have two variants in this case:
* 1. Move all the frag to the second
* part, if it is possible. F.e.
* this approach is mandatory for TUX,
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
skb_frag_ref(skb, i);
skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos);
skb_shinfo(skb)->nr_frags++;
}
k++;
} else
skb_shinfo(skb)->nr_frags++;
pos += size;
}
skb_shinfo(skb1)->nr_frags = k;
skb1->unreadable = skb->unreadable;
}
/**
* skb_split - Split fragmented skb to two parts at length len.
* @skb: the buffer to split
* @skb1: the buffer to receive the second part
* @len: new length for skb
*/
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
{
int pos = skb_headlen(skb);
const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY;
skb_zcopy_downgrade_managed(skb);
skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags;
skb_zerocopy_clone(skb1, skb, 0);
if (len < pos) /* Split line is inside header. */
skb_split_inside_header(skb, skb1, len, pos);
else /* Second chunk has no header, nothing to copy. */
skb_split_no_header(skb, skb1, len, pos);
}
EXPORT_SYMBOL(skb_split);
/* Shifting from/to a cloned skb is a no-go.
*
* Caller cannot keep skb_shinfo related pointers past calling here!
*/
static int skb_prepare_for_shift(struct sk_buff *skb)
{
return skb_unclone_keeptruesize(skb, GFP_ATOMIC);
}
/**
* skb_shift - Shifts paged data partially from skb to another
* @tgt: buffer into which tail data gets added
* @skb: buffer from which the paged data comes from
* @shiftlen: shift up to this many bytes
*
* Attempts to shift up to shiftlen worth of bytes, which may be less than
* the length of the skb, from skb to tgt. Returns number bytes shifted.
* It's up to caller to free skb if everything was shifted.
*
* If @tgt runs out of frags, the whole operation is aborted.
*
* Skb cannot include anything else but paged data while tgt is allowed
* to have non-paged data as well.
*
* TODO: full sized shift could be optimized but that would need
* specialized skb free'er to handle frags without up-to-date nr_frags.
*/
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
{
int from, to, merge, todo;
skb_frag_t *fragfrom, *fragto;
BUG_ON(shiftlen > skb->len);
if (skb_headlen(skb))
return 0;
if (skb_zcopy(tgt) || skb_zcopy(skb))
return 0;
DEBUG_NET_WARN_ON_ONCE(tgt->pp_recycle != skb->pp_recycle);
DEBUG_NET_WARN_ON_ONCE(skb_cmp_decrypted(tgt, skb));
todo = shiftlen;
from = 0;
to = skb_shinfo(tgt)->nr_frags;
fragfrom = &skb_shinfo(skb)->frags[from];
/* Actual merge is delayed until the point when we know we can
* commit all, so that we don't have to undo partial changes
*/
if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
skb_frag_off(fragfrom))) {
merge = -1;
} else {
merge = to - 1;
todo -= skb_frag_size(fragfrom);
if (todo < 0) {
if (skb_prepare_for_shift(skb) ||
skb_prepare_for_shift(tgt))
return 0;
/* All previous frag pointers might be stale! */
fragfrom = &skb_shinfo(skb)->frags[from];
fragto = &skb_shinfo(tgt)->frags[merge];
skb_frag_size_add(fragto, shiftlen);
skb_frag_size_sub(fragfrom, shiftlen);
skb_frag_off_add(fragfrom, shiftlen);
goto onlymerged;
}
from++;
}
/* Skip full, not-fitting skb to avoid expensive operations */
if ((shiftlen == skb->len) &&
(skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to))
return 0;
if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt))
return 0;
while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) {
if (to == MAX_SKB_FRAGS)
return 0;
fragfrom = &skb_shinfo(skb)->frags[from];
fragto = &skb_shinfo(tgt)->frags[to];
if (todo >= skb_frag_size(fragfrom)) {
*fragto = *fragfrom;
todo -= skb_frag_size(fragfrom);
from++;
to++;
} else {
__skb_frag_ref(fragfrom);
skb_frag_page_copy(fragto, fragfrom);
skb_frag_off_copy(fragto, fragfrom);
skb_frag_size_set(fragto, todo);
skb_frag_off_add(fragfrom, todo);
skb_frag_size_sub(fragfrom, todo);
todo = 0;
to++;
break;
}
}
/* Ready to "commit" this state change to tgt */
skb_shinfo(tgt)->nr_frags = to;
if (merge >= 0) {
fragfrom = &skb_shinfo(skb)->frags[0];
fragto = &skb_shinfo(tgt)->frags[merge];
skb_frag_size_add(fragto, skb_frag_size(fragfrom));
__skb_frag_unref(fragfrom, skb->pp_recycle);
}
/* Reposition in the original skb */
to = 0;
while (from < skb_shinfo(skb)->nr_frags)
skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
skb_shinfo(skb)->nr_frags = to;
BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);
onlymerged:
/* Most likely the tgt won't ever need its checksum anymore, skb on
* the other hand might need it if it needs to be resent
*/
tgt->ip_summed = CHECKSUM_PARTIAL;
skb->ip_summed = CHECKSUM_PARTIAL;
skb_len_add(skb, -shiftlen);
skb_len_add(tgt, shiftlen);
return shiftlen;
}
/**
* skb_prepare_seq_read - Prepare a sequential read of skb data
* @skb: the buffer to read
* @from: lower offset of data to be read
* @to: upper offset of data to be read
* @st: state variable
*
* Initializes the specified state variable. Must be called before
* invoking skb_seq_read() for the first time.
*/
void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
unsigned int to, struct skb_seq_state *st)
{
st->lower_offset = from;
st->upper_offset = to;
st->root_skb = st->cur_skb = skb;
st->frag_idx = st->stepped_offset = 0;
st->frag_data = NULL;
st->frag_off = 0;
}
EXPORT_SYMBOL(skb_prepare_seq_read);
/**
* skb_seq_read - Sequentially read skb data
* @consumed: number of bytes consumed by the caller so far
* @data: destination pointer for data to be returned
* @st: state variable
*
* Reads a block of skb data at @consumed relative to the
* lower offset specified to skb_prepare_seq_read(). Assigns
* the head of the data block to @data and returns the length
* of the block or 0 if the end of the skb data or the upper
* offset has been reached.
*
* The caller is not required to consume all of the data
* returned, i.e. @consumed is typically set to the number
* of bytes already consumed and the next call to
* skb_seq_read() will return the remaining part of the block.
*
* Note 1: The size of each block of data returned can be arbitrary,
* this limitation is the cost for zerocopy sequential
* reads of potentially non linear data.
*
* Note 2: Fragment lists within fragments are not implemented
* at the moment, state->root_skb could be replaced with
* a stack for this purpose.
*/
unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
struct skb_seq_state *st)
{
unsigned int block_limit, abs_offset = consumed + st->lower_offset;
skb_frag_t *frag;
if (unlikely(abs_offset >= st->upper_offset)) {
if (st->frag_data) {
kunmap_atomic(st->frag_data);
st->frag_data = NULL;
}
return 0;
}
next_skb:
block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
if (abs_offset < block_limit && !st->frag_data) {
*data = st->cur_skb->data + (abs_offset - st->stepped_offset);
return block_limit - abs_offset;
}
if (!skb_frags_readable(st->cur_skb))
return 0;
if (st->frag_idx == 0 && !st->frag_data)
st->stepped_offset += skb_headlen(st->cur_skb);
while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
unsigned int pg_idx, pg_off, pg_sz;
frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
pg_idx = 0;
pg_off = skb_frag_off(frag);
pg_sz = skb_frag_size(frag);
if (skb_frag_must_loop(skb_frag_page(frag))) {
pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
pg_off = offset_in_page(pg_off + st->frag_off);
pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
PAGE_SIZE - pg_off);
}
block_limit = pg_sz + st->stepped_offset;
if (abs_offset < block_limit) {
if (!st->frag_data)
st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
*data = (u8 *)st->frag_data + pg_off +
(abs_offset - st->stepped_offset);
return block_limit - abs_offset;
}
if (st->frag_data) {
kunmap_atomic(st->frag_data);
st->frag_data = NULL;
}
st->stepped_offset += pg_sz;
st->frag_off += pg_sz;
if (st->frag_off == skb_frag_size(frag)) {
st->frag_off = 0;
st->frag_idx++;
}
}
if (st->frag_data) {
kunmap_atomic(st->frag_data);
st->frag_data = NULL;
}
if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) {
st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
st->frag_idx = 0;
goto next_skb;
} else if (st->cur_skb->next) {
st->cur_skb = st->cur_skb->next;
st->frag_idx = 0;
goto next_skb;
}
return 0;
}
EXPORT_SYMBOL(skb_seq_read);
/**
* skb_abort_seq_read - Abort a sequential read of skb data
* @st: state variable
*
* Must be called if skb_seq_read() was not called until it
* returned 0.
*/
void skb_abort_seq_read(struct skb_seq_state *st)
{
if (st->frag_data)
kunmap_atomic(st->frag_data);
}
EXPORT_SYMBOL(skb_abort_seq_read);
/**
* skb_copy_seq_read() - copy from a skb_seq_state to a buffer
* @st: source skb_seq_state
* @offset: offset in source
* @to: destination buffer
* @len: number of bytes to copy
*
* Copy @len bytes from @offset bytes into the source @st to the destination
* buffer @to. `offset` should increase (or be unchanged) with each subsequent
* call to this function. If offset needs to decrease from the previous use `st`
* should be reset first.
*
* Return: 0 on success or -EINVAL if the copy ended early
*/
int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len)
{
const u8 *data;
u32 sqlen;
for (;;) {
sqlen = skb_seq_read(offset, &data, st);
if (sqlen == 0)
return -EINVAL;
if (sqlen >= len) {
memcpy(to, data, len);
return 0;
}
memcpy(to, data, sqlen);
to += sqlen;
offset += sqlen;
len -= sqlen;
}
}
EXPORT_SYMBOL(skb_copy_seq_read);
#define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb))
static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
struct ts_config *conf,
struct ts_state *state)
{
return skb_seq_read(offset, text, TS_SKB_CB(state));
}
static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
{
skb_abort_seq_read(TS_SKB_CB(state));
}
/**
* skb_find_text - Find a text pattern in skb data
* @skb: the buffer to look in
* @from: search offset
* @to: search limit
* @config: textsearch configuration
*
* Finds a pattern in the skb data according to the specified
* textsearch configuration. Use textsearch_next() to retrieve
* subsequent occurrences of the pattern. Returns the offset
* to the first occurrence or UINT_MAX if no match was found.
*/
unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
unsigned int to, struct ts_config *config)
{
unsigned int patlen = config->ops->get_pattern_len(config);
struct ts_state state;
unsigned int ret;
BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb));
config->get_next_block = skb_ts_get_next_block;
config->finish = skb_ts_finish;
skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state));
ret = textsearch_find(config, &state);
return (ret + patlen <= to - from ? ret : UINT_MAX);
}
EXPORT_SYMBOL(skb_find_text);
int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
int offset, size_t size, size_t max_frags)
{
int i = skb_shinfo(skb)->nr_frags;
if (skb_can_coalesce(skb, i, page, offset)) {
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
} else if (i < max_frags) {
skb_zcopy_downgrade_managed(skb);
get_page(page);
skb_fill_page_desc_noacc(skb, i, page, offset, size);
} else {
return -EMSGSIZE;
}
return 0;
}
EXPORT_SYMBOL_GPL(skb_append_pagefrags);
/**
* skb_pull_rcsum - pull skb and update receive checksum
* @skb: buffer to update
* @len: length of data pulled
*
* This function performs an skb_pull on the packet and updates
* the CHECKSUM_COMPLETE checksum. It should be used on
* receive path processing instead of skb_pull unless you know
* that the checksum difference is zero (e.g., a valid IP header)
* or you are setting ip_summed to CHECKSUM_NONE.
*/
void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
unsigned char *data = skb->data;
BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len);
return skb->data;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb)
{
skb_frag_t head_frag;
struct page *page;
page = virt_to_head_page(frag_skb->head);
skb_frag_fill_page_desc(&head_frag, page, frag_skb->data -
(unsigned char *)page_address(page),
skb_headlen(frag_skb));
return head_frag;
}
struct sk_buff *skb_segment_list(struct sk_buff *skb,
netdev_features_t features,
unsigned int offset)
{
struct sk_buff *list_skb = skb_shinfo(skb)->frag_list;
unsigned int tnl_hlen = skb_tnl_header_len(skb);
unsigned int delta_truesize = 0;
unsigned int delta_len = 0;
struct sk_buff *tail = NULL;
struct sk_buff *nskb, *tmp;
int len_diff, err;
skb_push(skb, -skb_network_offset(skb) + offset);
/* Ensure the head is writeable before touching the shared info */
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto err_linearize;
skb_shinfo(skb)->frag_list = NULL;
while (list_skb) {
nskb = list_skb;
list_skb = list_skb->next;
err = 0;
delta_truesize += nskb->truesize;
if (skb_shared(nskb)) {
tmp = skb_clone(nskb, GFP_ATOMIC);
if (tmp) {
consume_skb(nskb);
nskb = tmp;
err = skb_unclone(nskb, GFP_ATOMIC);
} else {
err = -ENOMEM;
}
}
if (!tail)
skb->next = nskb;
else
tail->next = nskb;
if (unlikely(err)) {
nskb->next = list_skb;
goto err_linearize;
}
tail = nskb;
delta_len += nskb->len;
skb_push(nskb, -skb_network_offset(nskb) + offset);
skb_release_head_state(nskb);
len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb);
__copy_skb_header(nskb, skb);
skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb));
nskb->transport_header += len_diff;
skb_copy_from_linear_data_offset(skb, -tnl_hlen,
nskb->data - tnl_hlen,
offset + tnl_hlen);
if (skb_needs_linearize(nskb, features) &&
__skb_linearize(nskb))
goto err_linearize;
}
skb->truesize = skb->truesize - delta_truesize;
skb->data_len = skb->data_len - delta_len;
skb->len = skb->len - delta_len;
skb_gso_reset(skb);
skb->prev = tail;
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
goto err_linearize;
skb_get(skb);
return skb;
err_linearize:
kfree_skb_list(skb->next);
skb->next = NULL;
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(skb_segment_list);
/**
* skb_segment - Perform protocol segmentation on skb.
* @head_skb: buffer to segment
* @features: features for the output path (see dev->features)
*
* This function performs segmentation on the given skb. It returns
* a pointer to the first in a list of new skbs for the segments.
* In case of error it returns ERR_PTR(err).
*/
struct sk_buff *skb_segment(struct sk_buff *head_skb,
netdev_features_t features)
{
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
unsigned int mss = skb_shinfo(head_skb)->gso_size;
unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
unsigned int offset = doffset;
unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int partial_segs = 0;
unsigned int headroom;
unsigned int len = head_skb->len;
struct sk_buff *frag_skb;
skb_frag_t *frag;
__be16 proto;
bool csum, sg;
int err = -ENOMEM;
int i = 0;
int nfrags, pos;
if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) {
struct sk_buff *check_skb;
for (check_skb = list_skb; check_skb; check_skb = check_skb->next) {
if (skb_headlen(check_skb) && !check_skb->head_frag) {
/* gso_size is untrusted, and we have a frag_list with
* a linear non head_frag item.
*
* If head_skb's headlen does not fit requested gso_size,
* it means that the frag_list members do NOT terminate
* on exact gso_size boundaries. Hence we cannot perform
* skb_frag_t page sharing. Therefore we must fallback to
* copying the frag_list skbs; we do so by disabling SG.
*/
features &= ~NETIF_F_SG;
break;
}
}
}
__skb_push(head_skb, doffset);
proto = skb_network_protocol(head_skb, NULL);
if (unlikely(!proto))
return ERR_PTR(-EINVAL);
sg = !!(features & NETIF_F_SG);
csum = !!can_checksum_protocol(features, proto);
if (sg && csum && (mss != GSO_BY_FRAGS)) {
if (!(features & NETIF_F_GSO_PARTIAL)) {
struct sk_buff *iter;
unsigned int frag_len;
if (!list_skb ||
!net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
goto normal;
/* If we get here then all the required
* GSO features except frag_list are supported.
* Try to split the SKB to multiple GSO SKBs
* with no frag_list.
* Currently we can do that only when the buffers don't
* have a linear part and all the buffers except
* the last are of the same length.
*/
frag_len = list_skb->len;
skb_walk_frags(head_skb, iter) {
if (frag_len != iter->len && iter->next)
goto normal;
if (skb_headlen(iter) && !iter->head_frag)
goto normal;
len -= iter->len;
}
if (len != frag_len)
goto normal;
}
/* GSO partial only requires that we trim off any excess that
* doesn't fit into an MSS sized block, so take care of that
* now.
* Cap len to not accidentally hit GSO_BY_FRAGS.
*/
partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
if (partial_segs > 1)
mss *= partial_segs;
else
partial_segs = 0;
}
normal:
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
if (skb_orphan_frags(head_skb, GFP_ATOMIC))
return ERR_PTR(-ENOMEM);
nfrags = skb_shinfo(head_skb)->nr_frags;
frag = skb_shinfo(head_skb)->frags;
frag_skb = head_skb;
do {
struct sk_buff *nskb;
skb_frag_t *nskb_frag;
int hsize;
int size;
if (unlikely(mss == GSO_BY_FRAGS)) {
len = list_skb->len;
} else {
len = head_skb->len - offset;
if (len > mss)
len = mss;
}
hsize = skb_headlen(head_skb) - offset;
if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) &&
(skb_headlen(list_skb) == len || sg)) {
BUG_ON(skb_headlen(list_skb) > len);
nskb = skb_clone(list_skb, GFP_ATOMIC);
if (unlikely(!nskb))
goto err;
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
frag_skb = list_skb;
pos += skb_headlen(list_skb);
while (pos < offset + len) {
BUG_ON(i >= nfrags);
size = skb_frag_size(frag);
if (pos + size > offset + len)
break;
i++;
pos += size;
frag++;
}
list_skb = list_skb->next;
if (unlikely(pskb_trim(nskb, len))) {
kfree_skb(nskb);
goto err;
}
hsize = skb_end_offset(nskb);
if (skb_cow_head(nskb, doffset + headroom)) {
kfree_skb(nskb);
goto err;
}
nskb->truesize += skb_end_offset(nskb) - hsize;
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
if (hsize < 0)
hsize = 0;
if (hsize > len || !sg)
hsize = len;
nskb = __alloc_skb(hsize + doffset + headroom,
GFP_ATOMIC, skb_alloc_rx_flag(head_skb),
NUMA_NO_NODE);
if (unlikely(!nskb))
goto err;
skb_reserve(nskb, headroom);
__skb_put(nskb, doffset);
}
if (segs)
tail->next = nskb;
else
segs = nskb;
tail = nskb;
__copy_skb_header(nskb, head_skb);
skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
skb_reset_mac_len(nskb);
skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
nskb->data - tnl_hlen,
doffset + tnl_hlen);
if (nskb->len == len + doffset)
goto perform_csum_check;
if (!sg) {
if (!csum) {
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
skb_copy_and_csum_bits(head_skb, offset,
skb_put(nskb,
len),
len);
SKB_GSO_CB(nskb)->csum_start =
skb_headroom(nskb) + doffset;
} else {
if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
goto err;
}
continue;
}
nskb_frag = skb_shinfo(nskb)->frags;
skb_copy_from_linear_data_offset(head_skb, offset,
skb_put(nskb, hsize), hsize);
skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags &
SKBFL_SHARED_FRAG;
if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
if (i >= nfrags) {
if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
skb_zerocopy_clone(nskb, list_skb,
GFP_ATOMIC))
goto err;
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
frag_skb = list_skb;
if (!skb_headlen(list_skb)) {
BUG_ON(!nfrags);
} else {
BUG_ON(!list_skb->head_frag);
/* to make room for head_frag. */
i--;
frag--;
}
list_skb = list_skb->next;
}
if (unlikely(skb_shinfo(nskb)->nr_frags >=
MAX_SKB_FRAGS)) {
net_warn_ratelimited(
"skb_segment: too many frags: %u %u\n",
pos, mss);
err = -EINVAL;
goto err;
}
*nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag;
__skb_frag_ref(nskb_frag);
size = skb_frag_size(nskb_frag);
if (pos < offset) {
skb_frag_off_add(nskb_frag, offset - pos);
skb_frag_size_sub(nskb_frag, offset - pos);
}
skb_shinfo(nskb)->nr_frags++;
if (pos + size <= offset + len) {
i++;
frag++;
pos += size;
} else {
skb_frag_size_sub(nskb_frag, pos + size - (offset + len));
goto skip_fraglist;
}
nskb_frag++;
}
skip_fraglist:
nskb->data_len = len - hsize;
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
perform_csum_check:
if (!csum) {
if (skb_has_shared_frag(nskb) &&
__skb_linearize(nskb))
goto err;
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
skb_checksum(nskb, doffset,
nskb->len - doffset, 0);
SKB_GSO_CB(nskb)->csum_start =
skb_headroom(nskb) + doffset;
}
} while ((offset += len) < head_skb->len);
/* Some callers want to get the end of the list.
* Put it in segs->prev to avoid walking the list.
* (see validate_xmit_skb_list() for example)
*/
segs->prev = tail;
if (partial_segs) {
struct sk_buff *iter;
int type = skb_shinfo(head_skb)->gso_type;
unsigned short gso_size = skb_shinfo(head_skb)->gso_size;
/* Update type to add partial and then remove dodgy if set */
type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL;
type &= ~SKB_GSO_DODGY;
/* Update GSO info and prepare to start updating headers on
* our way back down the stack of protocols.
*/
for (iter = segs; iter; iter = iter->next) {
skb_shinfo(iter)->gso_size = gso_size;
skb_shinfo(iter)->gso_segs = partial_segs;
skb_shinfo(iter)->gso_type = type;
SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset;
}
if (tail->len - doffset <= gso_size)
skb_shinfo(tail)->gso_size = 0;
else if (tail != segs)
skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size);
}
/* Following permits correct backpressure, for protocols
* using skb_set_owner_w().
* Idea is to tranfert ownership from head_skb to last segment.
*/
if (head_skb->destructor == sock_wfree) {
swap(tail->truesize, head_skb->truesize);
swap(tail->destructor, head_skb->destructor);
swap(tail->sk, head_skb->sk);
}
return segs;
err:
kfree_skb_list(segs);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(skb_segment);
#ifdef CONFIG_SKB_EXTENSIONS
#define SKB_EXT_ALIGN_VALUE 8
#define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE)
static const u8 skb_ext_type_len[] = {
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
[SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info),
#endif
#ifdef CONFIG_XFRM
[SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path),
#endif
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
[TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext),
#endif
#if IS_ENABLED(CONFIG_MPTCP)
[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
#endif
#if IS_ENABLED(CONFIG_MCTP_FLOWS)
[SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow),
#endif
};
static __always_inline unsigned int skb_ext_total_length(void)
{
unsigned int l = SKB_EXT_CHUNKSIZEOF(struct skb_ext);
int i;
for (i = 0; i < ARRAY_SIZE(skb_ext_type_len); i++)
l += skb_ext_type_len[i];
return l;
}
static void skb_extensions_init(void)
{
BUILD_BUG_ON(SKB_EXT_NUM >= 8);
#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL)
BUILD_BUG_ON(skb_ext_total_length() > 255);
#endif
skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
}
#else
static void skb_extensions_init(void) {}
#endif
/* The SKB kmem_cache slab is critical for network performance. Never
* merge/alias the slab with similar sized objects. This avoids fragmentation
* that hurts performance of kmem_cache_{alloc,free}_bulk APIs.
*/
#ifndef CONFIG_SLUB_TINY
#define FLAG_SKB_NO_MERGE SLAB_NO_MERGE
#else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */
#define FLAG_SKB_NO_MERGE 0
#endif
void __init skb_init(void)
{
net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
sizeof(struct sk_buff),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|
FLAG_SKB_NO_MERGE,
offsetof(struct sk_buff, cb),
sizeof_field(struct sk_buff, cb),
NULL);
net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
sizeof(struct sk_buff_fclones),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
/* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes.
* struct skb_shared_info is located at the end of skb->head,
* and should not be copied to/from user.
*/
net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
SKB_SMALL_HEAD_CACHE_SIZE,
0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC,
0,
SKB_SMALL_HEAD_HEADROOM,
NULL);
skb_extensions_init();
}
static int
__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len,
unsigned int recursion_level)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int elt = 0;
if (unlikely(recursion_level >= 24))
return -EMSGSIZE;
if (copy > 0) {
if (copy > len)
copy = len;
sg_set_buf(sg, skb->data + offset, copy);
elt++;
if ((len -= copy) == 0)
return elt;
offset += copy;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (unlikely(elt && sg_is_last(&sg[elt - 1])))
return -EMSGSIZE;
if (copy > len)
copy = len;
sg_set_page(&sg[elt], skb_frag_page(frag), copy,
skb_frag_off(frag) + offset - start);
elt++;
if (!(len -= copy))
return elt;
offset += copy;
}
start = end;
}
skb_walk_frags(skb, frag_iter) {
int end, ret;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
if (unlikely(elt && sg_is_last(&sg[elt - 1])))
return -EMSGSIZE;
if (copy > len)
copy = len;
ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start,
copy, recursion_level + 1);
if (unlikely(ret < 0))
return ret;
elt += ret;
if ((len -= copy) == 0)
return elt;
offset += copy;
}
start = end;
}
BUG_ON(len);
return elt;
}
/**
* skb_to_sgvec - Fill a scatter-gather list from a socket buffer
* @skb: Socket buffer containing the buffers to be mapped
* @sg: The scatter-gather list to map into
* @offset: The offset into the buffer's contents to start mapping
* @len: Length of buffer space to be mapped
*
* Fill the specified scatter-gather list with mappings/pointers into a
* region of the buffer space attached to a socket buffer. Returns either
* the number of scatterlist items used, or -EMSGSIZE if the contents
* could not fit.
*/
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
int nsg = __skb_to_sgvec(skb, sg, offset, len, 0);
if (nsg <= 0)
return nsg;
sg_mark_end(&sg[nsg - 1]);
return nsg;
}
EXPORT_SYMBOL_GPL(skb_to_sgvec);
/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
* sglist without mark the sg which contain last skb data as the end.
* So the caller can mannipulate sg list as will when padding new data after
* the first call without calling sg_unmark_end to expend sg list.
*
* Scenario to use skb_to_sgvec_nomark:
* 1. sg_init_table
* 2. skb_to_sgvec_nomark(payload1)
* 3. skb_to_sgvec_nomark(payload2)
*
* This is equivalent to:
* 1. sg_init_table
* 2. skb_to_sgvec(payload1)
* 3. sg_unmark_end
* 4. skb_to_sgvec(payload2)
*
* When mapping multiple payload conditionally, skb_to_sgvec_nomark
* is more preferable.
*/
int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
int offset, int len)
{
return __skb_to_sgvec(skb, sg, offset, len, 0);
}
EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
/**
* skb_cow_data - Check that a socket buffer's data buffers are writable
* @skb: The socket buffer to check.
* @tailbits: Amount of trailing space to be added
* @trailer: Returned pointer to the skb where the @tailbits space begins
*
* Make sure that the data buffers attached to a socket buffer are
* writable. If they are not, private copies are made of the data buffers
* and the socket buffer is set to use these instead.
*
* If @tailbits is given, make sure that there is space to write @tailbits
* bytes of data beyond current end of socket buffer. @trailer will be
* set to point to the skb in which this space begins.
*
* The number of scatterlist elements required to completely map the
* COW'd and extended socket buffer will be returned.
*/
int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
{
int copyflag;
int elt;
struct sk_buff *skb1, **skb_p;
/* If skb is cloned or its head is paged, reallocate
* head pulling out all the pages (pages are considered not writable
* at the moment even if they are anonymous).
*/
if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
!__pskb_pull_tail(skb, __skb_pagelen(skb)))
return -ENOMEM;
/* Easy case. Most of packets will go this way. */
if (!skb_has_frag_list(skb)) {
/* A little of trouble, not enough of space for trailer.
* This should not happen, when stack is tuned to generate
* good frames. OK, on miss we reallocate and reserve even more
* space, 128 bytes is fair. */
if (skb_tailroom(skb) < tailbits &&
pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC))
return -ENOMEM;
/* Voila! */
*trailer = skb;
return 1;
}
/* Misery. We are in troubles, going to mincer fragments... */
elt = 1;
skb_p = &skb_shinfo(skb)->frag_list;
copyflag = 0;
while ((skb1 = *skb_p) != NULL) {
int ntail = 0;
/* The fragment is partially pulled by someone,
* this can happen on input. Copy it and everything
* after it. */
if (skb_shared(skb1))
copyflag = 1;
/* If the skb is the last, worry about trailer. */
if (skb1->next == NULL && tailbits) {
if (skb_shinfo(skb1)->nr_frags ||
skb_has_frag_list(skb1) ||
skb_tailroom(skb1) < tailbits)
ntail = tailbits + 128;
}
if (copyflag ||
skb_cloned(skb1) ||
ntail ||
skb_shinfo(skb1)->nr_frags ||
skb_has_frag_list(skb1)) {
struct sk_buff *skb2;
/* Fuck, we are miserable poor guys... */
if (ntail == 0)
skb2 = skb_copy(skb1, GFP_ATOMIC);
else
skb2 = skb_copy_expand(skb1,
skb_headroom(skb1),
ntail,
GFP_ATOMIC);
if (unlikely(skb2 == NULL))
return -ENOMEM;
if (skb1->sk)
skb_set_owner_w(skb2, skb1->sk);
/* Looking around. Are we still alive?
* OK, link new skb, drop old one */
skb2->next = skb1->next;
*skb_p = skb2;
kfree_skb(skb1);
skb1 = skb2;
}
elt++;
*trailer = skb1;
skb_p = &skb1->next;
}
return elt;
}
EXPORT_SYMBOL_GPL(skb_cow_data);
static void sock_rmem_free(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
}
static void skb_set_err_queue(struct sk_buff *skb)
{
/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
* So, it is safe to (mis)use it to mark skbs on the error queue.
*/
skb->pkt_type = PACKET_OUTGOING;
BUILD_BUG_ON(PACKET_OUTGOING == 0);
}
/*
* Note: We dont mem charge error packets (no sk_forward_alloc changes)
*/
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsigned int)READ_ONCE(sk->sk_rcvbuf))
return -ENOMEM;
skb_orphan(skb);
skb->sk = sk;
skb->destructor = sock_rmem_free;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
skb_set_err_queue(skb);
/* before exiting rcu section, make sure dst is refcounted */
skb_dst_force(skb);
skb_queue_tail(&sk->sk_error_queue, skb);
if (!sock_flag(sk, SOCK_DEAD))
sk_error_report(sk);
return 0;
}
EXPORT_SYMBOL(sock_queue_err_skb);
static bool is_icmp_err_skb(const struct sk_buff *skb)
{
return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6);
}
struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
{
struct sk_buff_head *q = &sk->sk_error_queue;
struct sk_buff *skb, *skb_next = NULL;
bool icmp_next = false;
unsigned long flags;
if (skb_queue_empty_lockless(q))
return NULL;
spin_lock_irqsave(&q->lock, flags);
skb = __skb_dequeue(q);
if (skb && (skb_next = skb_peek(q))) {
icmp_next = is_icmp_err_skb(skb_next);
if (icmp_next)
sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
}
spin_unlock_irqrestore(&q->lock, flags);
if (is_icmp_err_skb(skb) && !icmp_next)
sk->sk_err = 0;
if (skb_next)
sk_error_report(sk);
return skb;
}
EXPORT_SYMBOL(sock_dequeue_err_skb);
/**
* skb_clone_sk - create clone of skb, and take reference to socket
* @skb: the skb to clone
*
* This function creates a clone of a buffer that holds a reference on
* sk_refcnt. Buffers created via this function are meant to be
* returned using sock_queue_err_skb, or free via kfree_skb.
*
* When passing buffers allocated with this function to sock_queue_err_skb
* it is necessary to wrap the call with sock_hold/sock_put in order to
* prevent the socket from being released prior to being enqueued on
* the sk_error_queue.
*/
struct sk_buff *skb_clone_sk(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct sk_buff *clone;
if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return NULL;
clone = skb_clone(skb, GFP_ATOMIC);
if (!clone) {
sock_put(sk);
return NULL;
}
clone->sk = sk;
clone->destructor = sock_efree;
return clone;
}
EXPORT_SYMBOL(skb_clone_sk);
static void __skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk,
int tstype,
bool opt_stats)
{
struct sock_exterr_skb *serr;
int err;
BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb));
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
serr->ee.ee_info = tstype;
serr->opt_stats = opt_stats;
serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
if (sk_is_tcp(sk))
serr->ee.ee_data -= atomic_read(&sk->sk_tskey);
}
err = sock_queue_err_skb(sk, skb);
if (err)
kfree_skb(skb);
}
static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
{
bool ret;
if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data)))
return true;
read_lock_bh(&sk->sk_callback_lock);
ret = sk->sk_socket && sk->sk_socket->file &&
file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
read_unlock_bh(&sk->sk_callback_lock);
return ret;
}
void skb_complete_tx_timestamp(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps)
{
struct sock *sk = skb->sk;
if (!skb_may_tx_timestamp(sk, false))
goto err;
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
*/
if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
sock_put(sk);
return;
}
err:
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps,
int tstype)
{
switch (tstype) {
case SCM_TSTAMP_SCHED:
return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
case SCM_TSTAMP_SND:
return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
SKBTX_SW_TSTAMP);
case SCM_TSTAMP_ACK:
return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK;
case SCM_TSTAMP_COMPLETION:
return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP;
}
return false;
}
static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps,
struct sock *sk,
int tstype)
{
int op;
switch (tstype) {
case SCM_TSTAMP_SCHED:
op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
break;
case SCM_TSTAMP_SND:
if (hwtstamps) {
op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB;
*skb_hwtstamps(skb) = *hwtstamps;
} else {
op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
}
break;
case SCM_TSTAMP_ACK:
op = BPF_SOCK_OPS_TSTAMP_ACK_CB;
break;
default:
return;
}
bpf_skops_tx_timestamping(sk, skb, op);
}
void __skb_tstamp_tx(struct sk_buff *orig_skb,
const struct sk_buff *ack_skb,
struct skb_shared_hwtstamps *hwtstamps,
struct sock *sk, int tstype)
{
struct sk_buff *skb;
bool tsonly, opt_stats = false;
u32 tsflags;
if (!sk)
return;
if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF)
skb_tstamp_tx_report_bpf_timestamping(orig_skb, hwtstamps,
sk, tstype);
if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
return;
tsflags = READ_ONCE(sk->sk_tsflags);
if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
return;
tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
if (!skb_may_tx_timestamp(sk, tsonly))
return;
if (tsonly) {
#ifdef CONFIG_INET
if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
sk_is_tcp(sk)) {
skb = tcp_get_timestamping_opt_stats(sk, orig_skb,
ack_skb);
opt_stats = true;
} else
#endif
skb = alloc_skb(0, GFP_ATOMIC);
} else {
skb = skb_clone(orig_skb, GFP_ATOMIC);
if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) {
kfree_skb(skb);
return;
}
}
if (!skb)
return;
if (tsonly) {
skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags &
SKBTX_ANY_TSTAMP;
skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey;
}
if (hwtstamps)
*skb_hwtstamps(skb) = *hwtstamps;
else
__net_timestamp(skb);
__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
}
EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
void skb_tstamp_tx(struct sk_buff *orig_skb,
struct skb_shared_hwtstamps *hwtstamps)
{
return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk,
SCM_TSTAMP_SND);
}
EXPORT_SYMBOL_GPL(skb_tstamp_tx);
#ifdef CONFIG_WIRELESS
void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
{
struct sock *sk = skb->sk;
struct sock_exterr_skb *serr;
int err = 1;
skb->wifi_acked_valid = 1;
skb->wifi_acked = acked;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
*/
if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) {
err = sock_queue_err_skb(sk, skb);
sock_put(sk);
}
if (err)
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
#endif /* CONFIG_WIRELESS */
/**
* skb_partial_csum_set - set up and verify partial csum values for packet
* @skb: the skb to set
* @start: the number of bytes after skb->data to start checksumming.
* @off: the offset from start to place the checksum.
*
* For untrusted partially-checksummed packets, we need to make sure the values
* for skb->csum_start and skb->csum_offset are valid so we don't oops.
*
* This function checks and sets those values and skb->ip_summed: if this
* returns false you should drop the packet.
*/
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
{
u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
u32 csum_start = skb_headroom(skb) + (u32)start;
if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) {
net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
start, off, skb_headroom(skb), skb_headlen(skb));
return false;
}
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = csum_start;
skb->csum_offset = off;
skb->transport_header = csum_start;
return true;
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
unsigned int max)
{
if (skb_headlen(skb) >= len)
return 0;
/* If we need to pullup then pullup to the max, so we
* won't need to do it again.
*/
if (max > skb->len)
max = skb->len;
if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
return -ENOMEM;
if (skb_headlen(skb) < len)
return -EPROTO;
return 0;
}
#define MAX_TCP_HDR_LEN (15 * 4)
static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
typeof(IPPROTO_IP) proto,
unsigned int off)
{
int err;
switch (proto) {
case IPPROTO_TCP:
err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
off + MAX_TCP_HDR_LEN);
if (!err && !skb_partial_csum_set(skb, off,
offsetof(struct tcphdr,
check)))
err = -EPROTO;
return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
case IPPROTO_UDP:
err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
off + sizeof(struct udphdr));
if (!err && !skb_partial_csum_set(skb, off,
offsetof(struct udphdr,
check)))
err = -EPROTO;
return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
}
return ERR_PTR(-EPROTO);
}
/* This value should be large enough to cover a tagged ethernet header plus
* maximally sized IP and TCP or UDP headers.
*/
#define MAX_IP_HDR_LEN 128
static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
{
unsigned int off;
bool fragment;
__sum16 *csum;
int err;
fragment = false;
err = skb_maybe_pull_tail(skb,
sizeof(struct iphdr),
MAX_IP_HDR_LEN);
if (err < 0)
goto out;
if (ip_is_fragment(ip_hdr(skb)))
fragment = true;
off = ip_hdrlen(skb);
err = -EPROTO;
if (fragment)
goto out;
csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
if (IS_ERR(csum))
return PTR_ERR(csum);
if (recalculate)
*csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr,
skb->len - off,
ip_hdr(skb)->protocol, 0);
err = 0;
out:
return err;
}
/* This value should be large enough to cover a tagged ethernet header plus
* an IPv6 header, all options, and a maximal TCP or UDP header.
*/
#define MAX_IPV6_HDR_LEN 256
#define OPT_HDR(type, skb, off) \
(type *)(skb_network_header(skb) + (off))
static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
{
int err;
u8 nexthdr;
unsigned int off;
unsigned int len;
bool fragment;
bool done;
__sum16 *csum;
fragment = false;
done = false;
off = sizeof(struct ipv6hdr);
err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
if (err < 0)
goto out;
nexthdr = ipv6_hdr(skb)->nexthdr;
len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
while (off <= len && !done) {
switch (nexthdr) {
case IPPROTO_DSTOPTS:
case IPPROTO_HOPOPTS:
case IPPROTO_ROUTING: {
struct ipv6_opt_hdr *hp;
err = skb_maybe_pull_tail(skb,
off +
sizeof(struct ipv6_opt_hdr),
MAX_IPV6_HDR_LEN);
if (err < 0)
goto out;
hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
nexthdr = hp->nexthdr;
off += ipv6_optlen(hp);
break;
}
case IPPROTO_AH: {
struct ip_auth_hdr *hp;
err = skb_maybe_pull_tail(skb,
off +
sizeof(struct ip_auth_hdr),
MAX_IPV6_HDR_LEN);
if (err < 0)
goto out;
hp = OPT_HDR(struct ip_auth_hdr, skb, off);
nexthdr = hp->nexthdr;
off += ipv6_authlen(hp);
break;
}
case IPPROTO_FRAGMENT: {
struct frag_hdr *hp;
err = skb_maybe_pull_tail(skb,
off +
sizeof(struct frag_hdr),
MAX_IPV6_HDR_LEN);
if (err < 0)
goto out;
hp = OPT_HDR(struct frag_hdr, skb, off);
if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
fragment = true;
nexthdr = hp->nexthdr;
off += sizeof(struct frag_hdr);
break;
}
default:
done = true;
break;
}
}
err = -EPROTO;
if (!done || fragment)
goto out;
csum = skb_checksum_setup_ip(skb, nexthdr, off);
if (IS_ERR(csum))
return PTR_ERR(csum);
if (recalculate)
*csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr,
skb->len - off, nexthdr, 0);
err = 0;
out:
return err;
}
/**
* skb_checksum_setup - set up partial checksum offset
* @skb: the skb to set up
* @recalculate: if true the pseudo-header checksum will be recalculated
*/
int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
{
int err;
switch (skb->protocol) {
case htons(ETH_P_IP):
err = skb_checksum_setup_ipv4(skb, recalculate);
break;
case htons(ETH_P_IPV6):
err = skb_checksum_setup_ipv6(skb, recalculate);
break;
default:
err = -EPROTO;
break;
}
return err;
}
EXPORT_SYMBOL(skb_checksum_setup);
/**
* skb_checksum_maybe_trim - maybe trims the given skb
* @skb: the skb to check
* @transport_len: the data length beyond the network header
*
* Checks whether the given skb has data beyond the given transport length.
* If so, returns a cloned skb trimmed to this transport length.
* Otherwise returns the provided skb. Returns NULL in error cases
* (e.g. transport_len exceeds skb length or out-of-memory).
*
* Caller needs to set the skb transport header and free any returned skb if it
* differs from the provided skb.
*/
static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb,
unsigned int transport_len)
{
struct sk_buff *skb_chk;
unsigned int len = skb_transport_offset(skb) + transport_len;
int ret;
if (skb->len < len)
return NULL;
else if (skb->len == len)
return skb;
skb_chk = skb_clone(skb, GFP_ATOMIC);
if (!skb_chk)
return NULL;
ret = pskb_trim_rcsum(skb_chk, len);
if (ret) {
kfree_skb(skb_chk);
return NULL;
}
return skb_chk;
}
/**
* skb_checksum_trimmed - validate checksum of an skb
* @skb: the skb to check
* @transport_len: the data length beyond the network header
* @skb_chkf: checksum function to use
*
* Applies the given checksum function skb_chkf to the provided skb.
* Returns a checked and maybe trimmed skb. Returns NULL on error.
*
* If the skb has data beyond the given transport length, then a
* trimmed & cloned skb is checked and returned.
*
* Caller needs to set the skb transport header and free any returned skb if it
* differs from the provided skb.
*/
struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
unsigned int transport_len,
__sum16(*skb_chkf)(struct sk_buff *skb))
{
struct sk_buff *skb_chk;
unsigned int offset = skb_transport_offset(skb);
__sum16 ret;
skb_chk = skb_checksum_maybe_trim(skb, transport_len);
if (!skb_chk)
goto err;
if (!pskb_may_pull(skb_chk, offset))
goto err;
skb_pull_rcsum(skb_chk, offset);
ret = skb_chkf(skb_chk);
skb_push_rcsum(skb_chk, offset);
if (ret)
goto err;
return skb_chk;
err:
if (skb_chk && skb_chk != skb)
kfree_skb(skb_chk);
return NULL;
}
EXPORT_SYMBOL(skb_checksum_trimmed);
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
skb->dev->name);
}
EXPORT_SYMBOL(__skb_warn_lro_forwarding);
void kfree_skb_partial(struct sk_buff *skb, bool head_stolen)
{
if (head_stolen) {
skb_release_head_state(skb);
kmem_cache_free(net_hotdata.skbuff_cache, skb);
} else {
__kfree_skb(skb);
}
}
EXPORT_SYMBOL(kfree_skb_partial);
/**
* skb_try_coalesce - try to merge skb to prior one
* @to: prior buffer
* @from: buffer to add
* @fragstolen: pointer to boolean
* @delta_truesize: how much more was allocated than was requested
*/
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
{
struct skb_shared_info *to_shinfo, *from_shinfo;
int i, delta, len = from->len;
*fragstolen = false;
if (skb_cloned(to))
return false;
/* In general, avoid mixing page_pool and non-page_pool allocated
* pages within the same SKB. In theory we could take full
* references if @from is cloned and !@to->pp_recycle but its
* tricky (due to potential race with the clone disappearing) and
* rare, so not worth dealing with.
*/
if (to->pp_recycle != from->pp_recycle)
return false;
if (skb_frags_readable(from) != skb_frags_readable(to))
return false;
if (len <= skb_tailroom(to) && skb_frags_readable(from)) {
if (len)
BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
*delta_truesize = 0;
return true;
}
to_shinfo = skb_shinfo(to);
from_shinfo = skb_shinfo(from);
if (to_shinfo->frag_list || from_shinfo->frag_list)
return false;
if (skb_zcopy(to) || skb_zcopy(from))
return false;
if (skb_headlen(from) != 0) {
struct page *page;
unsigned int offset;
if (to_shinfo->nr_frags +
from_shinfo->nr_frags >= MAX_SKB_FRAGS)
return false;
if (skb_head_is_locked(from))
return false;
delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
skb_fill_page_desc(to, to_shinfo->nr_frags,
page, offset, skb_headlen(from));
*fragstolen = true;
} else {
if (to_shinfo->nr_frags +
from_shinfo->nr_frags > MAX_SKB_FRAGS)
return false;
delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
}
WARN_ON_ONCE(delta < len);
memcpy(to_shinfo->frags + to_shinfo->nr_frags,
from_shinfo->frags,
from_shinfo->nr_frags * sizeof(skb_frag_t));
to_shinfo->nr_frags += from_shinfo->nr_frags;
if (!skb_cloned(from))
from_shinfo->nr_frags = 0;
/* if the skb is not cloned this does nothing
* since we set nr_frags to 0.
*/
if (skb_pp_frag_ref(from)) {
for (i = 0; i < from_shinfo->nr_frags; i++)
__skb_frag_ref(&from_shinfo->frags[i]);
}
to->truesize += delta;
to->len += len;
to->data_len += len;
*delta_truesize = delta;
return true;
}
EXPORT_SYMBOL(skb_try_coalesce);
/**
* skb_scrub_packet - scrub an skb
*
* @skb: buffer to clean
* @xnet: packet is crossing netns
*
* skb_scrub_packet can be used after encapsulating or decapsulating a packet
* into/from a tunnel. Some information have to be cleared during these
* operations.
* skb_scrub_packet can also be used to clean a skb before injecting it in
* another namespace (@xnet == true). We have to clear all information in the
* skb that could impact namespace isolation.
*/
void skb_scrub_packet(struct sk_buff *skb, bool xnet)
{
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
skb_dst_drop(skb);
skb_ext_reset(skb);
nf_reset_ct(skb);
nf_reset_trace(skb);
#ifdef CONFIG_NET_SWITCHDEV
skb->offload_fwd_mark = 0;
skb->offload_l3_fwd_mark = 0;
#endif
ipvs_reset(skb);
if (!xnet)
return;
skb->mark = 0;
skb_clear_tstamp(skb);
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
{
int mac_len, meta_len;
void *meta;
if (skb_cow(skb, skb_headroom(skb)) < 0) {
kfree_skb(skb);
return NULL;
}
mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
mac_len - VLAN_HLEN - ETH_TLEN);
}
meta_len = skb_metadata_len(skb);
if (meta_len) { meta = skb_metadata_end(skb) - meta_len;
memmove(meta + VLAN_HLEN, meta, meta_len);
}
skb->mac_header += VLAN_HLEN;
return skb;
}
struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
{
struct vlan_hdr *vhdr;
u16 vlan_tci;
if (unlikely(skb_vlan_tag_present(skb))) {
/* vlan_tci is already set-up so leave this for another time */
return skb;
}
skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb))
goto err_free;
/* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */
if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short))))
goto err_free;
vhdr = (struct vlan_hdr *)skb->data;
vlan_tci = ntohs(vhdr->h_vlan_TCI);
__vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci);
skb_pull_rcsum(skb, VLAN_HLEN);
vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb);
if (unlikely(!skb))
goto err_free;
skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb);
return skb;
err_free:
kfree_skb(skb);
return NULL;
}
EXPORT_SYMBOL(skb_vlan_untag);
int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
{
if (!pskb_may_pull(skb, write_len))
return -ENOMEM;
if (!skb_frags_readable(skb))
return -EFAULT;
if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
return 0;
return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
}
EXPORT_SYMBOL(skb_ensure_writable);
int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
{
int needed_headroom = dev->needed_headroom;
int needed_tailroom = dev->needed_tailroom;
/* For tail taggers, we need to pad short frames ourselves, to ensure
* that the tail tag does not fail at its role of being at the end of
* the packet, once the conduit interface pads the frame. Account for
* that pad length here, and pad later.
*/
if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
needed_tailroom += ETH_ZLEN - skb->len;
/* skb_headroom() returns unsigned int... */
needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
/* No reallocation needed, yay! */
return 0;
return pskb_expand_head(skb, needed_headroom, needed_tailroom,
GFP_ATOMIC);
}
EXPORT_SYMBOL(skb_ensure_writable_head_tail);
/* remove VLAN header from packet and update csum accordingly.
* expects a non skb_vlan_tag_present skb with a vlan tag payload
*/
int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
{
int offset = skb->data - skb_mac_header(skb);
int err;
if (WARN_ONCE(offset,
"__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n",
offset)) {
return -EINVAL;
}
err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
vlan_remove_tag(skb, vlan_tci);
skb->mac_header += VLAN_HLEN;
if (skb_network_offset(skb) < ETH_HLEN)
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_len(skb);
return err;
}
EXPORT_SYMBOL(__skb_vlan_pop);
/* Pop a vlan tag either from hwaccel or from payload.
* Expects skb->data at mac header.
*/
int skb_vlan_pop(struct sk_buff *skb)
{
u16 vlan_tci;
__be16 vlan_proto;
int err;
if (likely(skb_vlan_tag_present(skb))) {
__vlan_hwaccel_clear_tag(skb);
} else {
if (unlikely(!eth_type_vlan(skb->protocol)))
return 0;
err = __skb_vlan_pop(skb, &vlan_tci);
if (err)
return err;
}
/* move next vlan tag to hw accel tag */
if (likely(!eth_type_vlan(skb->protocol)))
return 0;
vlan_proto = skb->protocol;
err = __skb_vlan_pop(skb, &vlan_tci);
if (unlikely(err))
return err;
__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
return 0;
}
EXPORT_SYMBOL(skb_vlan_pop);
/* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present).
* Expects skb->data at mac header.
*/
int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
{
if (skb_vlan_tag_present(skb)) {
int offset = skb->data - skb_mac_header(skb);
int err;
if (WARN_ONCE(offset,
"skb_vlan_push got skb with skb->data not at mac header (offset %d)\n",
offset)) {
return -EINVAL;
}
err = __vlan_insert_tag(skb, skb->vlan_proto,
skb_vlan_tag_get(skb));
if (err)
return err;
skb->protocol = skb->vlan_proto;
skb->network_header -= VLAN_HLEN;
skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
}
__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
return 0;
}
EXPORT_SYMBOL(skb_vlan_push);
/**
* skb_eth_pop() - Drop the Ethernet header at the head of a packet
*
* @skb: Socket buffer to modify
*
* Drop the Ethernet header of @skb.
*
* Expects that skb->data points to the mac header and that no VLAN tags are
* present.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_eth_pop(struct sk_buff *skb)
{
if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
skb_network_offset(skb) < ETH_HLEN)
return -EPROTO;
skb_pull_rcsum(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
return 0;
}
EXPORT_SYMBOL(skb_eth_pop);
/**
* skb_eth_push() - Add a new Ethernet header at the head of a packet
*
* @skb: Socket buffer to modify
* @dst: Destination MAC address of the new header
* @src: Source MAC address of the new header
*
* Prepend @skb with a new Ethernet header.
*
* Expects that skb->data points to the mac header, which must be empty.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
const unsigned char *src)
{
struct ethhdr *eth;
int err;
if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
return -EPROTO;
err = skb_cow_head(skb, sizeof(*eth));
if (err < 0)
return err;
skb_push(skb, sizeof(*eth));
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
eth = eth_hdr(skb);
ether_addr_copy(eth->h_dest, dst);
ether_addr_copy(eth->h_source, src);
eth->h_proto = skb->protocol;
skb_postpush_rcsum(skb, eth, sizeof(*eth));
return 0;
}
EXPORT_SYMBOL(skb_eth_push);
/* Update the ethertype of hdr and the skb csum value if required. */
static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
__be16 ethertype)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be16 diff[] = { ~hdr->h_proto, ethertype };
skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
}
hdr->h_proto = ethertype;
}
/**
* skb_mpls_push() - push a new MPLS header after mac_len bytes from start of
* the packet
*
* @skb: buffer
* @mpls_lse: MPLS label stack entry to push
* @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
* @mac_len: length of the MAC header
* @ethernet: flag to indicate if the resulting packet after skb_mpls_push is
* ethernet
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
int mac_len, bool ethernet)
{
struct mpls_shim_hdr *lse;
int err;
if (unlikely(!eth_p_mpls(mpls_proto)))
return -EINVAL;
/* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */
if (skb->encapsulation)
return -EINVAL;
err = skb_cow_head(skb, MPLS_HLEN);
if (unlikely(err))
return err;
if (!skb->inner_protocol) {
skb_set_inner_network_header(skb, skb_network_offset(skb));
skb_set_inner_protocol(skb, skb->protocol);
}
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
mac_len);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb_reset_mac_len(skb);
lse = mpls_hdr(skb);
lse->label_stack_entry = mpls_lse;
skb_postpush_rcsum(skb, lse, MPLS_HLEN);
if (ethernet && mac_len >= ETH_HLEN)
skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
skb->protocol = mpls_proto;
return 0;
}
EXPORT_SYMBOL_GPL(skb_mpls_push);
/**
* skb_mpls_pop() - pop the outermost MPLS header
*
* @skb: buffer
* @next_proto: ethertype of header after popped MPLS header
* @mac_len: length of the MAC header
* @ethernet: flag to indicate if the packet is ethernet
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
bool ethernet)
{
int err;
if (unlikely(!eth_p_mpls(skb->protocol)))
return 0;
err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
if (ethernet && mac_len >= ETH_HLEN) {
struct ethhdr *hdr;
/* use mpls_hdr() to get ethertype to account for VLANs. */
hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
skb_mod_eth_type(skb, hdr, next_proto);
}
skb->protocol = next_proto;
return 0;
}
EXPORT_SYMBOL_GPL(skb_mpls_pop);
/**
* skb_mpls_update_lse() - modify outermost MPLS header and update csum
*
* @skb: buffer
* @mpls_lse: new MPLS label stack entry to update to
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse)
{
int err;
if (unlikely(!eth_p_mpls(skb->protocol)))
return -EINVAL;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse };
skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
}
mpls_hdr(skb)->label_stack_entry = mpls_lse;
return 0;
}
EXPORT_SYMBOL_GPL(skb_mpls_update_lse);
/**
* skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header
*
* @skb: buffer
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
int skb_mpls_dec_ttl(struct sk_buff *skb)
{
u32 lse;
u8 ttl;
if (unlikely(!eth_p_mpls(skb->protocol)))
return -EINVAL;
if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
return -ENOMEM;
lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry);
ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
if (!--ttl)
return -EINVAL;
lse &= ~MPLS_LS_TTL_MASK;
lse |= ttl << MPLS_LS_TTL_SHIFT;
return skb_mpls_update_lse(skb, cpu_to_be32(lse));
}
EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
/**
* alloc_skb_with_frags - allocate skb with page frags
*
* @header_len: size of linear part
* @data_len: needed length in frags
* @order: max page order desired.
* @errcode: pointer to error code if any
* @gfp_mask: allocation mask
*
* This can be used to allocate a paged skb, given a maximal order for frags.
*/
struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
unsigned long data_len,
int order,
int *errcode,
gfp_t gfp_mask)
{
unsigned long chunk;
struct sk_buff *skb;
struct page *page;
int nr_frags = 0;
*errcode = -EMSGSIZE;
if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order)))
return NULL;
*errcode = -ENOBUFS;
skb = alloc_skb(header_len, gfp_mask);
if (!skb)
return NULL;
while (data_len) { if (nr_frags == MAX_SKB_FRAGS - 1)
goto failure;
while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order))
order--;
if (order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
__GFP_NOWARN,
order);
if (!page) {
order--;
continue;
}
} else {
page = alloc_page(gfp_mask);
if (!page)
goto failure;
}
chunk = min_t(unsigned long, data_len,
PAGE_SIZE << order);
skb_fill_page_desc(skb, nr_frags, page, 0, chunk);
nr_frags++;
skb->truesize += (PAGE_SIZE << order);
data_len -= chunk;
}
return skb;
failure:
kfree_skb(skb);
return NULL;
}
EXPORT_SYMBOL(alloc_skb_with_frags);
/* carve out the first off bytes from skb when off < headlen */
static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off,
const int headlen, gfp_t gfp_mask)
{
int i;
unsigned int size = skb_end_offset(skb);
int new_hlen = headlen - off;
u8 *data;
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
return -ENOMEM;
size = SKB_WITH_OVERHEAD(size);
/* Copy real data, and all frags */
skb_copy_from_linear_data_offset(skb, off, data, new_hlen);
skb->len -= off;
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb),
offsetof(struct skb_shared_info,
frags[skb_shinfo(skb)->nr_frags]));
if (skb_cloned(skb)) {
/* drop the old head gracefully */
if (skb_orphan_frags(skb, gfp_mask)) {
skb_kfree_head(data, size);
return -ENOMEM;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
skb_frag_ref(skb, i);
if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
skb_release_data(skb, SKB_CONSUMED);
} else {
/* we can reuse existing recount- all we did was
* relocate values
*/
skb_free_head(skb);
}
skb->head = data;
skb->data = data;
skb->head_frag = 0;
skb_set_end_offset(skb, size);
skb_set_tail_pointer(skb, skb_headlen(skb));
skb_headers_offset_update(skb, 0);
skb->cloned = 0;
skb->hdr_len = 0;
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
return 0;
}
static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp);
/* carve out the first eat bytes from skb's frag_list. May recurse into
* pskb_carve()
*/
static int pskb_carve_frag_list(struct sk_buff *skb,
struct skb_shared_info *shinfo, int eat,
gfp_t gfp_mask)
{
struct sk_buff *list = shinfo->frag_list;
struct sk_buff *clone = NULL;
struct sk_buff *insp = NULL;
do {
if (!list) {
pr_err("Not enough bytes to eat. Want %d\n", eat);
return -EFAULT;
}
if (list->len <= eat) {
/* Eaten as whole. */
eat -= list->len;
list = list->next;
insp = list;
} else {
/* Eaten partially. */
if (skb_shared(list)) {
clone = skb_clone(list, gfp_mask);
if (!clone)
return -ENOMEM;
insp = list->next;
list = clone;
} else {
/* This may be pulled without problems. */
insp = list;
}
if (pskb_carve(list, eat, gfp_mask) < 0) {
kfree_skb(clone);
return -ENOMEM;
}
break;
}
} while (eat);
/* Free pulled out fragments. */
while ((list = shinfo->frag_list) != insp) {
shinfo->frag_list = list->next;
consume_skb(list);
}
/* And insert new clone at head. */
if (clone) {
clone->next = list;
shinfo->frag_list = clone;
}
return 0;
}
/* carve off first len bytes from skb. Split line (off) is in the
* non-linear part of skb
*/
static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
int pos, gfp_t gfp_mask)
{
int i, k = 0;
unsigned int size = skb_end_offset(skb);
u8 *data;
const int nfrags = skb_shinfo(skb)->nr_frags;
struct skb_shared_info *shinfo;
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
return -ENOMEM;
size = SKB_WITH_OVERHEAD(size);
memcpy((struct skb_shared_info *)(data + size),
skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0]));
if (skb_orphan_frags(skb, gfp_mask)) {
skb_kfree_head(data, size);
return -ENOMEM;
}
shinfo = (struct skb_shared_info *)(data + size);
for (i = 0; i < nfrags; i++) {
int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (pos + fsize > off) {
shinfo->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < off) {
/* Split frag.
* We have two variants in this case:
* 1. Move all the frag to the second
* part, if it is possible. F.e.
* this approach is mandatory for TUX,
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
skb_frag_off_add(&shinfo->frags[0], off - pos);
skb_frag_size_sub(&shinfo->frags[0], off - pos);
}
skb_frag_ref(skb, i);
k++;
}
pos += fsize;
}
shinfo->nr_frags = k;
if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
/* split line is in frag list */
if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) {
/* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */
if (skb_has_frag_list(skb))
kfree_skb_list(skb_shinfo(skb)->frag_list);
skb_kfree_head(data, size);
return -ENOMEM;
}
skb_release_data(skb, SKB_CONSUMED);
skb->head = data;
skb->head_frag = 0;
skb->data = data;
skb_set_end_offset(skb, size);
skb_reset_tail_pointer(skb);
skb_headers_offset_update(skb, 0);
skb->cloned = 0;
skb->hdr_len = 0;
skb->nohdr = 0;
skb->len -= off;
skb->data_len = skb->len;
atomic_set(&skb_shinfo(skb)->dataref, 1);
return 0;
}
/* remove len bytes from the beginning of the skb */
static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp)
{
int headlen = skb_headlen(skb);
if (len < headlen)
return pskb_carve_inside_header(skb, len, headlen, gfp);
else
return pskb_carve_inside_nonlinear(skb, len, headlen, gfp);
}
/* Extract to_copy bytes starting at off from skb, and return this in
* a new skb
*/
struct sk_buff *pskb_extract(struct sk_buff *skb, int off,
int to_copy, gfp_t gfp)
{
struct sk_buff *clone = skb_clone(skb, gfp);
if (!clone)
return NULL;
if (pskb_carve(clone, off, gfp) < 0 ||
pskb_trim(clone, to_copy)) {
kfree_skb(clone);
return NULL;
}
return clone;
}
EXPORT_SYMBOL(pskb_extract);
/**
* skb_condense - try to get rid of fragments/frag_list if possible
* @skb: buffer
*
* Can be used to save memory before skb is added to a busy queue.
* If packet has bytes in frags and enough tail room in skb->head,
* pull all of them, so that we can free the frags right now and adjust
* truesize.
* Notes:
* We do not reallocate skb->head thus can not fail.
* Caller must re-evaluate skb->truesize if needed.
*/
void skb_condense(struct sk_buff *skb)
{
if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb) || !skb_frags_readable(skb))
return;
/* Nice, we can free page frag(s) right now */
__pskb_pull_tail(skb, skb->data_len);
}
/* At this point, skb->truesize might be over estimated,
* because skb had a fragment, and fragments do not tell
* their truesize.
* When we pulled its content into skb->head, fragment
* was freed, but __pskb_pull_tail() could not possibly
* adjust skb->truesize, not knowing the frag truesize.
*/
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
}
EXPORT_SYMBOL(skb_condense);
#ifdef CONFIG_SKB_EXTENSIONS
static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
{
return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
}
/**
* __skb_ext_alloc - allocate a new skb extensions storage
*
* @flags: See kmalloc().
*
* Returns the newly allocated pointer. The pointer can later attached to a
* skb via __skb_ext_set().
* Note: caller must handle the skb_ext as an opaque data.
*/
struct skb_ext *__skb_ext_alloc(gfp_t flags)
{
struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags);
if (new) {
memset(new->offset, 0, sizeof(new->offset));
refcount_set(&new->refcnt, 1);
}
return new;
}
static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
unsigned int old_active)
{
struct skb_ext *new;
if (refcount_read(&old->refcnt) == 1)
return old;
new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
if (!new)
return NULL;
memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE);
refcount_set(&new->refcnt, 1);
#ifdef CONFIG_XFRM
if (old_active & (1 << SKB_EXT_SEC_PATH)) {
struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH);
unsigned int i;
for (i = 0; i < sp->len; i++)
xfrm_state_hold(sp->xvec[i]);
}
#endif
#ifdef CONFIG_MCTP_FLOWS
if (old_active & (1 << SKB_EXT_MCTP)) {
struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP);
if (flow->key)
refcount_inc(&flow->key->refs);
}
#endif
__skb_ext_put(old);
return new;
}
/**
* __skb_ext_set - attach the specified extension storage to this skb
* @skb: buffer
* @id: extension id
* @ext: extension storage previously allocated via __skb_ext_alloc()
*
* Existing extensions, if any, are cleared.
*
* Returns the pointer to the extension.
*/
void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
struct skb_ext *ext)
{
unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext);
skb_ext_put(skb);
newlen = newoff + skb_ext_type_len[id];
ext->chunks = newlen;
ext->offset[id] = newoff;
skb->extensions = ext;
skb->active_extensions = 1 << id;
return skb_ext_get_ptr(ext, id);
}
/**
* skb_ext_add - allocate space for given extension, COW if needed
* @skb: buffer
* @id: extension to allocate space for
*
* Allocates enough space for the given extension.
* If the extension is already present, a pointer to that extension
* is returned.
*
* If the skb was cloned, COW applies and the returned memory can be
* modified without changing the extension space of clones buffers.
*
* Returns pointer to the extension or NULL on allocation failure.
*/
void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
{
struct skb_ext *new, *old = NULL;
unsigned int newlen, newoff;
if (skb->active_extensions) {
old = skb->extensions;
new = skb_ext_maybe_cow(old, skb->active_extensions);
if (!new)
return NULL;
if (__skb_ext_exist(new, id))
goto set_active;
newoff = new->chunks;
} else {
newoff = SKB_EXT_CHUNKSIZEOF(*new);
new = __skb_ext_alloc(GFP_ATOMIC);
if (!new)
return NULL;
}
newlen = newoff + skb_ext_type_len[id];
new->chunks = newlen;
new->offset[id] = newoff;
set_active:
skb->slow_gro = 1;
skb->extensions = new;
skb->active_extensions |= 1 << id;
return skb_ext_get_ptr(new, id);
}
EXPORT_SYMBOL(skb_ext_add);
#ifdef CONFIG_XFRM
static void skb_ext_put_sp(struct sec_path *sp)
{
unsigned int i;
for (i = 0; i < sp->len; i++)
xfrm_state_put(sp->xvec[i]);
}
#endif
#ifdef CONFIG_MCTP_FLOWS
static void skb_ext_put_mctp(struct mctp_flow *flow)
{
if (flow->key)
mctp_key_unref(flow->key);
}
#endif
void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
{
struct skb_ext *ext = skb->extensions;
skb->active_extensions &= ~(1 << id);
if (skb->active_extensions == 0) {
skb->extensions = NULL;
__skb_ext_put(ext);
#ifdef CONFIG_XFRM
} else if (id == SKB_EXT_SEC_PATH &&
refcount_read(&ext->refcnt) == 1) {
struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH);
skb_ext_put_sp(sp);
sp->len = 0;
#endif
}
}
EXPORT_SYMBOL(__skb_ext_del);
void __skb_ext_put(struct skb_ext *ext)
{
/* If this is last clone, nothing can increment
* it after check passes. Avoids one atomic op.
*/
if (refcount_read(&ext->refcnt) == 1)
goto free_now;
if (!refcount_dec_and_test(&ext->refcnt))
return;
free_now:
#ifdef CONFIG_XFRM
if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
#endif
#ifdef CONFIG_MCTP_FLOWS
if (__skb_ext_exist(ext, SKB_EXT_MCTP))
skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP));
#endif
kmem_cache_free(skbuff_ext_cache, ext);
}
EXPORT_SYMBOL(__skb_ext_put);
#endif /* CONFIG_SKB_EXTENSIONS */
static void kfree_skb_napi_cache(struct sk_buff *skb)
{
/* if SKB is a clone, don't handle this case */
if (skb->fclone != SKB_FCLONE_UNAVAILABLE) {
__kfree_skb(skb);
return;
}
local_bh_disable();
__napi_kfree_skb(skb, SKB_CONSUMED);
local_bh_enable();
}
/**
* skb_attempt_defer_free - queue skb for remote freeing
* @skb: buffer
*
* Put @skb in a per-cpu list, using the cpu which
* allocated the skb/pages to reduce false sharing
* and memory zone spinlock contention.
*/
void skb_attempt_defer_free(struct sk_buff *skb)
{
int cpu = skb->alloc_cpu;
struct softnet_data *sd;
unsigned int defer_max;
bool kick;
if (cpu == raw_smp_processor_id() ||
WARN_ON_ONCE(cpu >= nr_cpu_ids) ||
!cpu_online(cpu)) {
nodefer: kfree_skb_napi_cache(skb);
return;
}
DEBUG_NET_WARN_ON_ONCE(skb_dst(skb));
DEBUG_NET_WARN_ON_ONCE(skb->destructor);
sd = &per_cpu(softnet_data, cpu);
defer_max = READ_ONCE(net_hotdata.sysctl_skb_defer_max);
if (READ_ONCE(sd->defer_count) >= defer_max)
goto nodefer;
spin_lock_bh(&sd->defer_lock);
/* Send an IPI every time queue reaches half capacity. */
kick = sd->defer_count == (defer_max >> 1);
/* Paired with the READ_ONCE() few lines above */
WRITE_ONCE(sd->defer_count, sd->defer_count + 1);
skb->next = sd->defer_list;
/* Paired with READ_ONCE() in skb_defer_free_flush() */
WRITE_ONCE(sd->defer_list, skb);
spin_unlock_bh(&sd->defer_lock);
/* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU
* if we are unlucky enough (this seems very unlikely).
*/
if (unlikely(kick))
kick_defer_list_purge(sd, cpu);
}
static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
size_t offset, size_t len)
{
const char *kaddr;
__wsum csum;
kaddr = kmap_local_page(page);
csum = csum_partial(kaddr + offset, len, 0);
kunmap_local(kaddr);
skb->csum = csum_block_add(skb->csum, csum, skb->len);
}
/**
* skb_splice_from_iter - Splice (or copy) pages to skbuff
* @skb: The buffer to add pages to
* @iter: Iterator representing the pages to be added
* @maxsize: Maximum amount of pages to be added
* @gfp: Allocation flags
*
* This is a common helper function for supporting MSG_SPLICE_PAGES. It
* extracts pages from an iterator and adds them to the socket buffer if
* possible, copying them to fragments if not possible (such as if they're slab
* pages).
*
* Returns the amount of data spliced/copied or -EMSGSIZE if there's
* insufficient space in the buffer to transfer anything.
*/
ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
ssize_t maxsize, gfp_t gfp)
{
size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags);
struct page *pages[8], **ppages = pages;
ssize_t spliced = 0, ret = 0;
unsigned int i;
while (iter->count > 0) {
ssize_t space, nr, len;
size_t off;
ret = -EMSGSIZE;
space = frag_limit - skb_shinfo(skb)->nr_frags;
if (space < 0)
break;
/* We might be able to coalesce without increasing nr_frags */
nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages));
len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off);
if (len <= 0) {
ret = len ?: -EIO;
break;
}
i = 0;
do {
struct page *page = pages[i++];
size_t part = min_t(size_t, PAGE_SIZE - off, len);
ret = -EIO;
if (WARN_ON_ONCE(!sendpage_ok(page)))
goto out;
ret = skb_append_pagefrags(skb, page, off, part,
frag_limit);
if (ret < 0) {
iov_iter_revert(iter, len);
goto out;
}
if (skb->ip_summed == CHECKSUM_NONE)
skb_splice_csum_page(skb, page, off, part);
off = 0;
spliced += part;
maxsize -= part;
len -= part;
} while (len > 0);
if (maxsize <= 0)
break;
}
out:
skb_len_add(skb, spliced);
return spliced ?: ret;
}
EXPORT_SYMBOL(skb_splice_from_iter);
static __always_inline
size_t memcpy_from_iter_csum(void *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
__wsum *csum = priv2;
__wsum next = csum_partial_copy_nocheck(iter_from, to + progress, len);
*csum = csum_block_add(*csum, next, progress);
return 0;
}
static __always_inline
size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
__wsum next, *csum = priv2;
next = csum_and_copy_from_user(iter_from, to + progress, len);
*csum = csum_block_add(*csum, next, progress);
return next ? 0 : len;
}
bool csum_and_copy_from_iter_full(void *addr, size_t bytes,
__wsum *csum, struct iov_iter *i)
{
size_t copied;
if (WARN_ON_ONCE(!i->data_source))
return false;
copied = iterate_and_advance2(i, bytes, addr, csum,
copy_from_user_iter_csum,
memcpy_from_iter_csum);
if (likely(copied == bytes))
return true;
iov_iter_revert(i, copied);
return false;
}
EXPORT_SYMBOL(csum_and_copy_from_iter_full);
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/file_table.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*/
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/cdev.h>
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/task_work.h>
#include <linux/swap.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include "internal.h"
/* sysctl tunables... */
static struct files_stat_struct files_stat = {
.max_files = NR_FILE
};
/* SLAB cache for file structures */
static struct kmem_cache *filp_cachep __ro_after_init;
static struct kmem_cache *bfilp_cachep __ro_after_init;
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
/* Container for backing file with optional user path */
struct backing_file {
struct file file;
union {
struct path user_path;
freeptr_t bf_freeptr;
};
};
static inline struct backing_file *backing_file(struct file *f)
{
return container_of(f, struct backing_file, file);
}
struct path *backing_file_user_path(struct file *f)
{
return &backing_file(f)->user_path;
}
EXPORT_SYMBOL_GPL(backing_file_user_path);
static inline void file_free(struct file *f)
{
security_file_free(f);
if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { path_put(backing_file_user_path(f));
kmem_cache_free(bfilp_cachep, backing_file(f));
} else {
kmem_cache_free(filp_cachep, f);
}
}
/*
* Return the total number of open files in the system
*/
static long get_nr_files(void)
{
return percpu_counter_read_positive(&nr_files);
}
/*
* Return the maximum number of open files in the system
*/
unsigned long get_max_files(void)
{
return files_stat.max_files;
}
EXPORT_SYMBOL_GPL(get_max_files);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
/*
* Handle nr_files sysctl
*/
static int proc_nr_files(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static const struct ctl_table fs_stat_sysctls[] = {
{
.procname = "file-nr",
.data = &files_stat,
.maxlen = sizeof(files_stat),
.mode = 0444,
.proc_handler = proc_nr_files,
},
{
.procname = "file-max",
.data = &files_stat.max_files,
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
.extra1 = SYSCTL_LONG_ZERO,
.extra2 = SYSCTL_LONG_MAX,
},
{
.procname = "nr_open",
.data = &sysctl_nr_open,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_douintvec_minmax,
.extra1 = &sysctl_nr_open_min,
.extra2 = &sysctl_nr_open_max,
},
};
static int __init init_fs_stat_sysctls(void)
{
register_sysctl_init("fs", fs_stat_sysctls);
if (IS_ENABLED(CONFIG_BINFMT_MISC)) {
struct ctl_table_header *hdr;
hdr = register_sysctl_mount_point("fs/binfmt_misc");
kmemleak_not_leak(hdr);
}
return 0;
}
fs_initcall(init_fs_stat_sysctls);
#endif
static int init_file(struct file *f, int flags, const struct cred *cred)
{
int error;
f->f_cred = get_cred(cred);
error = security_file_alloc(f);
if (unlikely(error)) {
put_cred(f->f_cred);
return error;
}
spin_lock_init(&f->f_lock);
/*
* Note that f_pos_lock is only used for files raising
* FMODE_ATOMIC_POS and directories. Other files such as pipes
* don't need it and since f_pos_lock is in a union may reuse
* the space for other purposes. They are expected to initialize
* the respective member when opening the file.
*/
mutex_init(&f->f_pos_lock);
memset(&f->f_path, 0, sizeof(f->f_path));
memset(&f->f_ra, 0, sizeof(f->f_ra));
f->f_flags = flags;
f->f_mode = OPEN_FMODE(flags);
f->f_op = NULL;
f->f_mapping = NULL;
f->private_data = NULL;
f->f_inode = NULL;
f->f_owner = NULL;
#ifdef CONFIG_EPOLL
f->f_ep = NULL;
#endif
f->f_iocb_flags = 0;
f->f_pos = 0;
f->f_wb_err = 0;
f->f_sb_err = 0;
/*
* We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While
* fget-rcu pattern users need to be able to handle spurious
* refcount bumps we should reinitialize the reused file first.
*/
file_ref_init(&f->f_ref, 1);
/*
* Disable permission and pre-content events for all files by default.
* They may be enabled later by file_set_fsnotify_mode_from_watchers().
*/
file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
return 0;
}
/* Find an unused file structure and return a pointer to it.
* Returns an error pointer if some error happend e.g. we over file
* structures limit, run out of memory or operation is not permitted.
*
* Be very careful using this. You are responsible for
* getting write access to any mount that you might assign
* to this filp, if it is opened for write. If this is not
* done, you will imbalance int the mount's writer count
* and a warning at __fput() time.
*/
struct file *alloc_empty_file(int flags, const struct cred *cred)
{
static long old_max;
struct file *f;
int error;
/*
* Privileged users can go above max_files
*/
if (unlikely(get_nr_files() >= files_stat.max_files) &&
!capable(CAP_SYS_ADMIN)) {
/*
* percpu_counters are inaccurate. Do an expensive check before
* we go and fail.
*/
if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
goto over;
}
f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
error = init_file(f, flags, cred);
if (unlikely(error)) {
kmem_cache_free(filp_cachep, f);
return ERR_PTR(error);
}
percpu_counter_inc(&nr_files);
return f;
over:
/* Ran out of filps - report that */
if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files());
old_max = get_nr_files();
}
return ERR_PTR(-ENFILE);
}
/*
* Variant of alloc_empty_file() that doesn't check and modify nr_files.
*
* This is only for kernel internal use, and the allocate file must not be
* installed into file tables or such.
*/
struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
{
struct file *f;
int error;
f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
error = init_file(f, flags, cred);
if (unlikely(error)) {
kmem_cache_free(filp_cachep, f);
return ERR_PTR(error);
}
f->f_mode |= FMODE_NOACCOUNT;
return f;
}
/*
* Variant of alloc_empty_file() that allocates a backing_file container
* and doesn't check and modify nr_files.
*
* This is only for kernel internal use, and the allocate file must not be
* installed into file tables or such.
*/
struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
{
struct backing_file *ff;
int error;
ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL);
if (unlikely(!ff))
return ERR_PTR(-ENOMEM);
error = init_file(&ff->file, flags, cred);
if (unlikely(error)) {
kmem_cache_free(bfilp_cachep, ff);
return ERR_PTR(error);
}
ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
return &ff->file;
}
/**
* file_init_path - initialize a 'struct file' based on path
*
* @file: the file to set up
* @path: the (dentry, vfsmount) pair for the new file
* @fop: the 'struct file_operations' for the new file
*/
static void file_init_path(struct file *file, const struct path *path,
const struct file_operations *fop)
{
file->f_path = *path;
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
file->f_sb_err = file_sample_sb_err(file);
if (fop->llseek) file->f_mode |= FMODE_LSEEK; if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter))
file->f_mode |= FMODE_CAN_READ;
if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter))
file->f_mode |= FMODE_CAN_WRITE;
file->f_iocb_flags = iocb_flags(file);
file->f_mode |= FMODE_OPENED;
file->f_op = fop;
if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode);
}
/**
* alloc_file - allocate and initialize a 'struct file'
*
* @path: the (dentry, vfsmount) pair for the new file
* @flags: O_... flags with which the new file will be opened
* @fop: the 'struct file_operations' for the new file
*/
static struct file *alloc_file(const struct path *path, int flags,
const struct file_operations *fop)
{
struct file *file;
file = alloc_empty_file(flags, current_cred());
if (!IS_ERR(file))
file_init_path(file, path, fop);
return file;
}
static inline int alloc_path_pseudo(const char *name, struct inode *inode,
struct vfsmount *mnt, struct path *path)
{
path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name));
if (!path->dentry)
return -ENOMEM;
path->mnt = mntget(mnt);
d_instantiate(path->dentry, inode);
return 0;
}
struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
const char *name, int flags,
const struct file_operations *fops)
{
int ret;
struct path path;
struct file *file;
ret = alloc_path_pseudo(name, inode, mnt, &path);
if (ret)
return ERR_PTR(ret);
file = alloc_file(&path, flags, fops);
if (IS_ERR(file)) {
ihold(inode);
path_put(&path);
return file;
}
/*
* Disable all fsnotify events for pseudo files by default.
* They may be enabled by caller with file_set_fsnotify_mode().
*/
file_set_fsnotify_mode(file, FMODE_NONOTIFY);
return file;
}
EXPORT_SYMBOL(alloc_file_pseudo);
struct file *alloc_file_pseudo_noaccount(struct inode *inode,
struct vfsmount *mnt, const char *name,
int flags,
const struct file_operations *fops)
{
int ret;
struct path path;
struct file *file;
ret = alloc_path_pseudo(name, inode, mnt, &path);
if (ret)
return ERR_PTR(ret);
file = alloc_empty_file_noaccount(flags, current_cred());
if (IS_ERR(file)) {
ihold(inode);
path_put(&path);
return file;
}
file_init_path(file, &path, fops);
/*
* Disable all fsnotify events for pseudo files by default.
* They may be enabled by caller with file_set_fsnotify_mode().
*/
file_set_fsnotify_mode(file, FMODE_NONOTIFY);
return file;
}
EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
struct file *alloc_file_clone(struct file *base, int flags,
const struct file_operations *fops)
{
struct file *f;
f = alloc_file(&base->f_path, flags, fops);
if (!IS_ERR(f)) {
path_get(&f->f_path);
f->f_mapping = base->f_mapping;
}
return f;
}
/* the real guts of fput() - releasing the last reference to file
*/
static void __fput(struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
struct vfsmount *mnt = file->f_path.mnt;
struct inode *inode = file->f_inode;
fmode_t mode = file->f_mode;
if (unlikely(!(file->f_mode & FMODE_OPENED)))
goto out;
might_sleep();
fsnotify_close(file);
/*
* The function eventpoll_release() should be the first called
* in the file cleanup chain.
*/
eventpoll_release(file);
locks_remove_file(file);
security_file_release(file);
if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0);
}
if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
!(mode & FMODE_PATH))) {
cdev_put(inode->i_cdev);
}
fops_put(file->f_op);
file_f_owner_release(file);
put_file_access(file);
dput(dentry);
if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt);
mntput(mnt);
out:
file_free(file);
}
static LLIST_HEAD(delayed_fput_list);
static void delayed_fput(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&delayed_fput_list);
struct file *f, *t;
llist_for_each_entry_safe(f, t, node, f_llist)
__fput(f);
}
static void ____fput(struct callback_head *work)
{
__fput(container_of(work, struct file, f_task_work));
}
static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
/*
* If kernel thread really needs to have the final fput() it has done
* to complete, call this. The only user right now is the boot - we
* *do* need to make sure our writes to binaries on initramfs has
* not left us with opened struct file waiting for __fput() - execve()
* won't work without that. Please, don't add more callers without
* very good reasons; in particular, never call that with locks
* held and never call that from a thread that might need to do
* some work on any kind of umount.
*/
void flush_delayed_fput(void)
{
delayed_fput(NULL);
flush_delayed_work(&delayed_fput_work);
}
EXPORT_SYMBOL_GPL(flush_delayed_fput);
static void __fput_deferred(struct file *file)
{
struct task_struct *task = current;
if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
file_free(file);
return;
}
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
init_task_work(&file->f_task_work, ____fput);
if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
return;
/*
* After this task has run exit_task_work(),
* task_work_add() will fail. Fall through to delayed
* fput to avoid leaking *file.
*/
}
if (llist_add(&file->f_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1);
}
void fput(struct file *file)
{ if (unlikely(file_ref_put(&file->f_ref))) __fput_deferred(file);
}
EXPORT_SYMBOL(fput);
/*
* synchronous analog of fput(); for kernel threads that might be needed
* in some umount() (and thus can't use flush_delayed_fput() without
* risking deadlocks), need to wait for completion of __fput() and know
* for this specific struct file it won't involve anything that would
* need them. Use only if you really need it - at the very least,
* don't blindly convert fput() by kernel thread to that.
*/
void __fput_sync(struct file *file)
{
if (file_ref_put(&file->f_ref))
__fput(file);
}
EXPORT_SYMBOL(__fput_sync);
/*
* Equivalent to __fput_sync(), but optimized for being called with the last
* reference.
*
* See file_ref_put_close() for details.
*/
void fput_close_sync(struct file *file)
{ if (likely(file_ref_put_close(&file->f_ref)))
__fput(file);
}
/*
* Equivalent to fput(), but optimized for being called with the last
* reference.
*
* See file_ref_put_close() for details.
*/
void fput_close(struct file *file)
{ if (file_ref_put_close(&file->f_ref))
__fput_deferred(file);
}
void __init files_init(void)
{
struct kmem_cache_args args = {
.use_freeptr_offset = true,
.freeptr_offset = offsetof(struct file, f_freeptr),
};
filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args,
SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
args.freeptr_offset = offsetof(struct backing_file, bf_freeptr);
bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file),
&args, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
percpu_counter_init(&nr_files, 0, GFP_KERNEL);
}
/*
* One file with associated inode and dcache is very roughly 1K. Per default
* do not use more than 10% of our memory for files.
*/
void __init files_maxfiles_init(void)
{
unsigned long n;
unsigned long nr_pages = totalram_pages();
unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2;
memreserve = min(memreserve, nr_pages - 1);
n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
files_stat.max_files = max_t(unsigned long, n, NR_FILE);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
/*
* Linux wait queue related types and methods
*/
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/current.h>
typedef struct wait_queue_entry wait_queue_entry_t;
typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
/* wait_queue_entry::flags */
#define WQ_FLAG_EXCLUSIVE 0x01
#define WQ_FLAG_WOKEN 0x02
#define WQ_FLAG_CUSTOM 0x04
#define WQ_FLAG_DONE 0x08
#define WQ_FLAG_PRIORITY 0x10
/*
* A single wait-queue entry structure:
*/
struct wait_queue_entry {
unsigned int flags;
void *private;
wait_queue_func_t func;
struct list_head entry;
};
struct wait_queue_head {
spinlock_t lock;
struct list_head head;
};
typedef struct wait_queue_head wait_queue_head_t;
struct task_struct;
/*
* Macros for declaration and initialisaton of the datatypes
*/
#define __WAITQUEUE_INITIALIZER(name, tsk) { \
.private = tsk, \
.func = default_wake_function, \
.entry = { NULL, NULL } }
#define DECLARE_WAITQUEUE(name, tsk) \
struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk)
#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.head = LIST_HEAD_INIT(name.head) }
#define DECLARE_WAIT_QUEUE_HEAD(name) \
struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *);
#define init_waitqueue_head(wq_head) \
do { \
static struct lock_class_key __key; \
\
__init_waitqueue_head((wq_head), #wq_head, &__key); \
} while (0)
#ifdef CONFIG_LOCKDEP
# define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
({ init_waitqueue_head(&name); name; })
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
#else
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name)
#endif
static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p)
{
wq_entry->flags = 0;
wq_entry->private = p;
wq_entry->func = default_wake_function;
}
static inline void
init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func)
{
wq_entry->flags = 0;
wq_entry->private = NULL;
wq_entry->func = func;
}
/**
* waitqueue_active -- locklessly test for waiters on the queue
* @wq_head: the waitqueue to test for waiters
*
* returns true if the wait list is not empty
*
* NOTE: this function is lockless and requires care, incorrect usage _will_
* lead to sporadic and non-obvious failure.
*
* Use either while holding wait_queue_head::lock or when used for wakeups
* with an extra smp_mb() like::
*
* CPU0 - waker CPU1 - waiter
*
* for (;;) {
* @cond = true; prepare_to_wait(&wq_head, &wait, state);
* smp_mb(); // smp_mb() from set_current_state()
* if (waitqueue_active(wq_head)) if (@cond)
* wake_up(wq_head); break;
* schedule();
* }
* finish_wait(&wq_head, &wait);
*
* Because without the explicit smp_mb() it's possible for the
* waitqueue_active() load to get hoisted over the @cond store such that we'll
* observe an empty wait list while the waiter might not observe @cond.
*
* Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
* which (when the lock is uncontended) are of roughly equal cost.
*/
static inline int waitqueue_active(struct wait_queue_head *wq_head)
{
return !list_empty(&wq_head->head);
}
/**
* wq_has_single_sleeper - check if there is only one sleeper
* @wq_head: wait queue head
*
* Returns true of wq_head has only one sleeper on the list.
*
* Please refer to the comment for waitqueue_active.
*/
static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head)
{
return list_is_singular(&wq_head->head);
}
/**
* wq_has_sleeper - check if there are any waiting processes
* @wq_head: wait queue head
*
* Returns true if wq_head has waiting processes
*
* Please refer to the comment for waitqueue_active.
*/
static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
{
/*
* We need to be sure we are in sync with the
* add_wait_queue modifications to the wait queue.
*
* This memory barrier should be paired with one on the
* waiting side.
*/
smp_mb();
return waitqueue_active(wq_head);
}
extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
struct list_head *head = &wq_head->head;
struct wait_queue_entry *wq;
list_for_each_entry(wq, &wq_head->head, entry) {
if (!(wq->flags & WQ_FLAG_PRIORITY))
break;
head = &wq->entry;
}
list_add(&wq_entry->entry, head);
}
/*
* Used for wake-one threads:
*/
static inline void
__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq_head, wq_entry);
}
static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
list_add_tail(&wq_entry->entry, &wq_head->head);
}
static inline void
__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_entry_tail(wq_head, wq_entry);
}
static inline void
__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
{
list_del(&wq_entry->entry);
}
int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
void __wake_up_pollfree(struct wait_queue_head *wq_head);
#define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL)
#define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL)
#define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL)
#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1)
#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0)
#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL)
#define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
#define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL)
#define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE)
/*
* Wakeup macros to be used to report events to the targets.
*/
#define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m))
#define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m))
#define wake_up_poll(x, m) \
__wake_up(x, TASK_NORMAL, 1, poll_to_key(m))
#define wake_up_poll_on_current_cpu(x, m) \
__wake_up_on_current_cpu(x, TASK_NORMAL, poll_to_key(m))
#define wake_up_locked_poll(x, m) \
__wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m))
#define wake_up_interruptible_poll(x, m) \
__wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m))
#define wake_up_interruptible_sync_poll(x, m) \
__wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
#define wake_up_interruptible_sync_poll_locked(x, m) \
__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
/**
* wake_up_pollfree - signal that a polled waitqueue is going away
* @wq_head: the wait queue head
*
* In the very rare cases where a ->poll() implementation uses a waitqueue whose
* lifetime is tied to a task rather than to the 'struct file' being polled,
* this function must be called before the waitqueue is freed so that
* non-blocking polls (e.g. epoll) are notified that the queue is going away.
*
* The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via
* an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU.
*/
static inline void wake_up_pollfree(struct wait_queue_head *wq_head)
{
/*
* For performance reasons, we don't always take the queue lock here.
* Therefore, we might race with someone removing the last entry from
* the queue, and proceed while they still hold the queue lock.
* However, rcu_read_lock() is required to be held in such cases, so we
* can safely proceed with an RCU-delayed free.
*/
if (waitqueue_active(wq_head))
__wake_up_pollfree(wq_head);
}
#define ___wait_cond_timeout(condition) \
({ \
bool __cond = (condition); \
if (__cond && !__ret) \
__ret = 1; \
__cond || !__ret; \
})
#define ___wait_is_interruptible(state) \
(!__builtin_constant_p(state) || \
(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags);
/*
* The below macro ___wait_event() has an explicit shadow of the __ret
* variable when used from the wait_event_*() macros.
*
* This is so that both can use the ___wait_cond_timeout() construct
* to wrap the condition.
*
* The type inconsistency of the wait_event_*() __ret variable is also
* on purpose; we use long where we can return timeout values and int
* otherwise.
*/
#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \
({ \
__label__ __out; \
struct wait_queue_entry __wq_entry; \
long __ret = ret; /* explicit shadow */ \
\
init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \
for (;;) { \
long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\
\
if (condition) \
break; \
\
if (___wait_is_interruptible(state) && __int) { \
__ret = __int; \
goto __out; \
} \
\
cmd; \
\
if (condition) \
break; \
} \
finish_wait(&wq_head, &__wq_entry); \
__out: __ret; \
})
#define __wait_event(wq_head, condition) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
schedule())
/**
* wait_event - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event(wq_head, condition) \
do { \
might_sleep(); \
if (condition) \
break; \
__wait_event(wq_head, condition); \
} while (0)
#define __io_wait_event(wq_head, condition) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
io_schedule())
/*
* io_wait_event() -- like wait_event() but with io_schedule()
*/
#define io_wait_event(wq_head, condition) \
do { \
might_sleep(); \
if (condition) \
break; \
__io_wait_event(wq_head, condition); \
} while (0)
#define __wait_event_freezable(wq_head, condition) \
___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \
0, 0, schedule())
/**
* wait_event_freezable - sleep (or freeze) until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
* to system load) until the @condition evaluates to true. The
* @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event_freezable(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_freezable(wq_head, condition); \
__ret; \
})
#define __wait_event_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_UNINTERRUPTIBLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_freezable_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
(TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \
__ret = schedule_timeout(__ret))
/*
* like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
* increasing load and is freezable.
*/
#define wait_event_freezable_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \
cmd1; schedule(); cmd2)
/*
* Just like wait_event_cmd(), except it sets exclusive flag
*/
#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \
do { \
if (condition) \
break; \
__wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \
} while (0)
#define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
cmd1; schedule(); cmd2)
/**
* wait_event_cmd - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @cmd1: the command will be executed before sleep
* @cmd2: the command will be executed after sleep
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*/
#define wait_event_cmd(wq_head, condition, cmd1, cmd2) \
do { \
if (condition) \
break; \
__wait_event_cmd(wq_head, condition, cmd1, cmd2); \
} while (0)
#define __wait_event_interruptible(wq_head, condition) \
___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \
schedule())
/**
* wait_event_interruptible - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_interruptible(wq_head, condition); \
__ret; \
})
#define __wait_event_interruptible_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_INTERRUPTIBLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
* interrupted by a signal.
*/
#define wait_event_interruptible_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_interruptible_timeout(wq_head, \
condition, timeout); \
__ret; \
})
#define __wait_event_hrtimeout(wq_head, condition, timeout, state) \
({ \
int __ret = 0; \
struct hrtimer_sleeper __t; \
\
hrtimer_setup_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \
HRTIMER_MODE_REL); \
if ((timeout) != KTIME_MAX) { \
hrtimer_set_expires_range_ns(&__t.timer, timeout, \
current->timer_slack_ns); \
hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \
} \
\
__ret = ___wait_event(wq_head, condition, state, 0, 0, \
if (!__t.task) { \
__ret = -ETIME; \
break; \
} \
schedule()); \
\
hrtimer_cancel(&__t.timer); \
destroy_hrtimer_on_stack(&__t.timer); \
__ret; \
})
/**
* wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, as a ktime_t
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function returns 0 if @condition became true, or -ETIME if the timeout
* elapsed.
*/
#define wait_event_hrtimeout(wq_head, condition, timeout) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_hrtimeout(wq_head, condition, timeout, \
TASK_UNINTERRUPTIBLE); \
__ret; \
})
/**
* wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, as a ktime_t
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function returns 0 if @condition became true, -ERESTARTSYS if it was
* interrupted by a signal, or -ETIME if the timeout elapsed.
*/
#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \
({ \
long __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_hrtimeout(wq, condition, timeout, \
TASK_INTERRUPTIBLE); \
__ret; \
})
#define __wait_event_interruptible_exclusive(wq, condition) \
___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \
schedule())
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_interruptible_exclusive(wq, condition); \
__ret; \
})
#define __wait_event_killable_exclusive(wq, condition) \
___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \
schedule())
#define wait_event_killable_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_killable_exclusive(wq, condition); \
__ret; \
})
#define __wait_event_freezable_exclusive(wq, condition) \
___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\
schedule())
#define wait_event_freezable_exclusive(wq, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_freezable_exclusive(wq, condition); \
__ret; \
})
/**
* wait_event_idle - wait for a condition without contributing to system load
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
*/
#define wait_event_idle(wq_head, condition) \
do { \
might_sleep(); \
if (!(condition)) \
___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \
} while (0)
/**
* wait_event_idle_exclusive - wait for a condition with contributing to system load
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus if other processes wait on the same list, when this
* process is woken further processes are not considered.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
*/
#define wait_event_idle_exclusive(wq_head, condition) \
do { \
might_sleep(); \
if (!(condition)) \
___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \
} while (0)
#define __wait_event_idle_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_IDLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_idle_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_idle_timeout(wq_head, condition, timeout); \
__ret; \
})
#define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_IDLE, 1, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_IDLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus if other processes wait on the same list, when this
* process is woken further processes are not considered.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* or the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed.
*/
#define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\
__ret; \
})
extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *);
extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
({ \
int __ret; \
DEFINE_WAIT(__wait); \
if (exclusive) \
__wait.flags |= WQ_FLAG_EXCLUSIVE; \
do { \
__ret = fn(&(wq), &__wait); \
if (__ret) \
break; \
} while (!(condition)); \
__remove_wait_queue(&(wq), &__wait); \
__set_current_state(TASK_RUNNING); \
__ret; \
})
/**
* wait_event_interruptible_locked - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock()/spin_unlock()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_locked(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
/**
* wait_event_interruptible_locked_irq - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_locked_irq(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
/**
* wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock()/spin_unlock()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus when other process waits process on the list if this
* process is awaken further processes are not considered.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_exclusive_locked(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
/**
* wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
* @wq: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq is woken up.
*
* It must be called with wq.lock being held. This spinlock is
* unlocked while sleeping but @condition testing is done while lock
* is held and when this macro exits the lock is held.
*
* The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
* functions which must match the way they are locked/unlocked outside
* of this macro.
*
* The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
* set thus when other process waits process on the list if this
* process is awaken further processes are not considered.
*
* wake_up_locked() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \
((condition) \
? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
#define __wait_event_killable(wq, condition) \
___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
/**
* wait_event_killable - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
*
* The process is put to sleep (TASK_KILLABLE) until the
* @condition evaluates to true or a signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a
* signal and 0 if @condition evaluated to true.
*/
#define wait_event_killable(wq_head, condition) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_killable(wq_head, condition); \
__ret; \
})
#define __wait_event_state(wq, condition, state) \
___wait_event(wq, condition, state, 0, 0, schedule())
/**
* wait_event_state - sleep until a condition gets true
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @state: state to sleep in
*
* The process is put to sleep (@state) until the @condition evaluates to true
* or a signal is received (when allowed by @state). The @condition is checked
* each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* The function will return -ERESTARTSYS if it was interrupted by a signal
* (when allowed by @state) and 0 if @condition evaluated to true.
*/
#define wait_event_state(wq_head, condition, state) \
({ \
int __ret = 0; \
might_sleep(); \
if (!(condition)) \
__ret = __wait_event_state(wq_head, condition, state); \
__ret; \
})
#define __wait_event_killable_timeout(wq_head, condition, timeout) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
TASK_KILLABLE, 0, timeout, \
__ret = schedule_timeout(__ret))
/**
* wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_KILLABLE) until the
* @condition evaluates to true or a kill signal is received.
* The @condition is checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* Returns:
* 0 if the @condition evaluated to %false after the @timeout elapsed,
* 1 if the @condition evaluated to %true after the @timeout elapsed,
* the remaining jiffies (at least 1) if the @condition evaluated
* to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
* interrupted by a kill signal.
*
* Only kill signals interrupt this process.
*/
#define wait_event_killable_timeout(wq_head, condition, timeout) \
({ \
long __ret = timeout; \
might_sleep(); \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_killable_timeout(wq_head, \
condition, timeout); \
__ret; \
})
#define __wait_event_lock_irq(wq_head, condition, lock, cmd) \
(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \
spin_unlock_irq(&lock); \
cmd; \
schedule(); \
spin_lock_irq(&lock))
/**
* wait_event_lock_irq_cmd - sleep until a condition gets true. The
* condition is checked under the lock. This
* is expected to be called with the lock
* taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before cmd
* and schedule() and reacquired afterwards.
* @cmd: a command which is invoked outside the critical section before
* sleep
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before invoking the cmd and going to sleep and is reacquired
* afterwards.
*/
#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \
do { \
if (condition) \
break; \
__wait_event_lock_irq(wq_head, condition, lock, cmd); \
} while (0)
/**
* wait_event_lock_irq - sleep until a condition gets true. The
* condition is checked under the lock. This
* is expected to be called with the lock
* taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
*
* The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
* @condition evaluates to true. The @condition is checked each time
* the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*/
#define wait_event_lock_irq(wq_head, condition, lock) \
do { \
if (condition) \
break; \
__wait_event_lock_irq(wq_head, condition, lock, ); \
} while (0)
#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \
___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \
spin_unlock_irq(&lock); \
cmd; \
schedule(); \
spin_lock_irq(&lock))
/**
* wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
* The condition is checked under the lock. This is expected to
* be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before cmd and
* schedule() and reacquired afterwards.
* @cmd: a command which is invoked outside the critical section before
* sleep
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or a signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before invoking the cmd and going to sleep and is reacquired
* afterwards.
*
* The macro will return -ERESTARTSYS if it was interrupted by a signal
* and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \
({ \
int __ret = 0; \
if (!(condition)) \
__ret = __wait_event_interruptible_lock_irq(wq_head, \
condition, lock, cmd); \
__ret; \
})
/**
* wait_event_interruptible_lock_irq - sleep until a condition gets true.
* The condition is checked under the lock. This is expected
* to be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*
* The macro will return -ERESTARTSYS if it was interrupted by a signal
* and 0 if @condition evaluated to true.
*/
#define wait_event_interruptible_lock_irq(wq_head, condition, lock) \
({ \
int __ret = 0; \
if (!(condition)) \
__ret = __wait_event_interruptible_lock_irq(wq_head, \
condition, lock,); \
__ret; \
})
#define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \
___wait_event(wq_head, ___wait_cond_timeout(condition), \
state, 0, timeout, \
spin_unlock_irq(&lock); \
__ret = schedule_timeout(__ret); \
spin_lock_irq(&lock));
/**
* wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
* true or a timeout elapses. The condition is checked under
* the lock. This is expected to be called with the lock taken.
* @wq_head: the waitqueue to wait on
* @condition: a C expression for the event to wait for
* @lock: a locked spinlock_t, which will be released before schedule()
* and reacquired afterwards.
* @timeout: timeout, in jiffies
*
* The process is put to sleep (TASK_INTERRUPTIBLE) until the
* @condition evaluates to true or signal is received. The @condition is
* checked each time the waitqueue @wq_head is woken up.
*
* wake_up() has to be called after changing any variable that could
* change the result of the wait condition.
*
* This is supposed to be called while holding the lock. The lock is
* dropped before going to sleep and is reacquired afterwards.
*
* The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it
* was interrupted by a signal, and the remaining jiffies otherwise
* if the condition evaluated to true before the timeout elapsed.
*/
#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \
timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_lock_irq_timeout( \
wq_head, condition, lock, timeout, \
TASK_INTERRUPTIBLE); \
__ret; \
})
#define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \
({ \
long __ret = timeout; \
if (!___wait_cond_timeout(condition)) \
__ret = __wait_event_lock_irq_timeout( \
wq_head, condition, lock, timeout, \
TASK_UNINTERRUPTIBLE); \
__ret; \
})
/*
* Waitqueues which are removed from the waitqueue_head at wakeup time
*/
void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);
int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
#define DEFINE_WAIT_FUNC(name, function) \
struct wait_queue_entry name = { \
.private = current, \
.func = function, \
.entry = LIST_HEAD_INIT((name).entry), \
}
#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)
#define init_wait_func(wait, function) \
do { \
(wait)->private = current; \
(wait)->func = function; \
INIT_LIST_HEAD(&(wait)->entry); \
(wait)->flags = 0; \
} while (0)
#define init_wait(wait) init_wait_func(wait, autoremove_wake_function)
typedef int (*task_call_f)(struct task_struct *p, void *arg);
extern int task_call_func(struct task_struct *p, task_call_f func, void *arg);
#endif /* _LINUX_WAIT_H */
// SPDX-License-Identifier: GPL-2.0
/*
* device.h - generic, centralized driver model
*
* Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org>
* Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2008-2009 Novell Inc.
*
* See Documentation/driver-api/driver-model/ for more information.
*/
#ifndef _DEVICE_H_
#define _DEVICE_H_
#include <linux/dev_printk.h>
#include <linux/energy_model.h>
#include <linux/ioport.h>
#include <linux/kobject.h>
#include <linux/klist.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/compiler.h>
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/pm.h>
#include <linux/atomic.h>
#include <linux/uidgid.h>
#include <linux/gfp.h>
#include <linux/device/bus.h>
#include <linux/device/class.h>
#include <linux/device/devres.h>
#include <linux/device/driver.h>
#include <linux/cleanup.h>
#include <asm/device.h>
struct device;
struct device_private;
struct device_driver;
struct driver_private;
struct module;
struct class;
struct subsys_private;
struct device_node;
struct fwnode_handle;
struct iommu_group;
struct dev_pin_info;
struct dev_iommu;
struct msi_device_data;
/**
* struct subsys_interface - interfaces to device functions
* @name: name of the device function
* @subsys: subsystem of the devices to attach to
* @node: the list of functions registered at the subsystem
* @add_dev: device hookup to device function handler
* @remove_dev: device hookup to device function handler
*
* Simple interfaces attached to a subsystem. Multiple interfaces can
* attach to a subsystem and its devices. Unlike drivers, they do not
* exclusively claim or control devices. Interfaces usually represent
* a specific functionality of a subsystem/class of devices.
*/
struct subsys_interface {
const char *name;
const struct bus_type *subsys;
struct list_head node;
int (*add_dev)(struct device *dev, struct subsys_interface *sif);
void (*remove_dev)(struct device *dev, struct subsys_interface *sif);
};
int subsys_interface_register(struct subsys_interface *sif);
void subsys_interface_unregister(struct subsys_interface *sif);
int subsys_system_register(const struct bus_type *subsys,
const struct attribute_group **groups);
int subsys_virtual_register(const struct bus_type *subsys,
const struct attribute_group **groups);
/*
* The type of device, "struct device" is embedded in. A class
* or bus can contain devices of different types
* like "partitions" and "disks", "mouse" and "event".
* This identifies the device type and carries type-specific
* information, equivalent to the kobj_type of a kobject.
* If "name" is specified, the uevent will contain it in
* the DEVTYPE variable.
*/
struct device_type {
const char *name;
const struct attribute_group **groups;
int (*uevent)(const struct device *dev, struct kobj_uevent_env *env);
char *(*devnode)(const struct device *dev, umode_t *mode,
kuid_t *uid, kgid_t *gid);
void (*release)(struct device *dev);
const struct dev_pm_ops *pm;
};
/**
* struct device_attribute - Interface for exporting device attributes.
* @attr: sysfs attribute definition.
* @show: Show handler.
* @store: Store handler.
*/
struct device_attribute {
struct attribute attr;
ssize_t (*show)(struct device *dev, struct device_attribute *attr,
char *buf);
ssize_t (*store)(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count);
};
/**
* struct dev_ext_attribute - Exported device attribute with extra context.
* @attr: Exported device attribute.
* @var: Pointer to context.
*/
struct dev_ext_attribute {
struct device_attribute attr;
void *var;
};
ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr,
char *buf);
ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count);
ssize_t device_show_int(struct device *dev, struct device_attribute *attr,
char *buf);
ssize_t device_store_int(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count);
ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
char *buf);
ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count);
ssize_t device_show_string(struct device *dev, struct device_attribute *attr,
char *buf);
/**
* DEVICE_ATTR - Define a device attribute.
* @_name: Attribute name.
* @_mode: File mode.
* @_show: Show handler. Optional, but mandatory if attribute is readable.
* @_store: Store handler. Optional, but mandatory if attribute is writable.
*
* Convenience macro for defining a struct device_attribute.
*
* For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to:
*
* .. code-block:: c
*
* struct device_attribute dev_attr_foo = {
* .attr = { .name = "foo", .mode = 0644 },
* .show = foo_show,
* .store = foo_store,
* };
*/
#define DEVICE_ATTR(_name, _mode, _show, _store) \
struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
/**
* DEVICE_ATTR_PREALLOC - Define a preallocated device attribute.
* @_name: Attribute name.
* @_mode: File mode.
* @_show: Show handler. Optional, but mandatory if attribute is readable.
* @_store: Store handler. Optional, but mandatory if attribute is writable.
*
* Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode.
*/
#define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \
struct device_attribute dev_attr_##_name = \
__ATTR_PREALLOC(_name, _mode, _show, _store)
/**
* DEVICE_ATTR_RW - Define a read-write device attribute.
* @_name: Attribute name.
*
* Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show,
* and @_store is <_name>_store.
*/
#define DEVICE_ATTR_RW(_name) \
struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
/**
* DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute.
* @_name: Attribute name.
*
* Like DEVICE_ATTR_RW(), but @_mode is 0600.
*/
#define DEVICE_ATTR_ADMIN_RW(_name) \
struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600)
/**
* DEVICE_ATTR_RO - Define a readable device attribute.
* @_name: Attribute name.
*
* Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show.
*/
#define DEVICE_ATTR_RO(_name) \
struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
/**
* DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute.
* @_name: Attribute name.
*
* Like DEVICE_ATTR_RO(), but @_mode is 0400.
*/
#define DEVICE_ATTR_ADMIN_RO(_name) \
struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400)
/**
* DEVICE_ATTR_WO - Define an admin-only writable device attribute.
* @_name: Attribute name.
*
* Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store.
*/
#define DEVICE_ATTR_WO(_name) \
struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
/**
* DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long.
* @_name: Attribute name.
* @_mode: File mode.
* @_var: Identifier of unsigned long.
*
* Like DEVICE_ATTR(), but @_show and @_store are automatically provided
* such that reads and writes to the attribute from userspace affect @_var.
*/
#define DEVICE_ULONG_ATTR(_name, _mode, _var) \
struct dev_ext_attribute dev_attr_##_name = \
{ __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) }
/**
* DEVICE_INT_ATTR - Define a device attribute backed by an int.
* @_name: Attribute name.
* @_mode: File mode.
* @_var: Identifier of int.
*
* Like DEVICE_ULONG_ATTR(), but @_var is an int.
*/
#define DEVICE_INT_ATTR(_name, _mode, _var) \
struct dev_ext_attribute dev_attr_##_name = \
{ __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) }
/**
* DEVICE_BOOL_ATTR - Define a device attribute backed by a bool.
* @_name: Attribute name.
* @_mode: File mode.
* @_var: Identifier of bool.
*
* Like DEVICE_ULONG_ATTR(), but @_var is a bool.
*/
#define DEVICE_BOOL_ATTR(_name, _mode, _var) \
struct dev_ext_attribute dev_attr_##_name = \
{ __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) }
/**
* DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string.
* @_name: Attribute name.
* @_mode: File mode.
* @_var: Identifier of string.
*
* Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the
* string allocation is unknown, the attribute must be read-only.
*/
#define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \
struct dev_ext_attribute dev_attr_##_name = \
{ __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) }
#define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
struct device_attribute dev_attr_##_name = \
__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
int device_create_file(struct device *device,
const struct device_attribute *entry);
void device_remove_file(struct device *dev,
const struct device_attribute *attr);
bool device_remove_file_self(struct device *dev,
const struct device_attribute *attr);
int __must_check device_create_bin_file(struct device *dev,
const struct bin_attribute *attr);
void device_remove_bin_file(struct device *dev,
const struct bin_attribute *attr);
/* allows to add/remove a custom action to devres stack */
int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data);
/**
* devm_remove_action() - removes previously added custom action
* @dev: Device that owns the action
* @action: Function implementing the action
* @data: Pointer to data passed to @action implementation
*
* Removes instance of @action previously added by devm_add_action().
* Both action and data should match one of the existing entries.
*/
static inline
void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
{
WARN_ON(devm_remove_action_nowarn(dev, action, data));
}
void devm_release_action(struct device *dev, void (*action)(void *), void *data);
int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name);
#define devm_add_action(dev, action, data) \
__devm_add_action(dev, action, data, #action)
static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *),
void *data, const char *name)
{
int ret;
ret = __devm_add_action(dev, action, data, name);
if (ret)
action(data);
return ret;
}
#define devm_add_action_or_reset(dev, action, data) \
__devm_add_action_or_reset(dev, action, data, #action)
/**
* devm_alloc_percpu - Resource-managed alloc_percpu
* @dev: Device to allocate per-cpu memory for
* @type: Type to allocate per-cpu memory for
*
* Managed alloc_percpu. Per-cpu memory allocated with this function is
* automatically freed on driver detach.
*
* RETURNS:
* Pointer to allocated memory on success, NULL on failure.
*/
#define devm_alloc_percpu(dev, type) \
((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \
__alignof__(type)))
void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
size_t align);
void devm_free_percpu(struct device *dev, void __percpu *pdata);
struct device_dma_parameters {
/*
* a low level driver may set these to teach IOMMU code about
* sg limitations.
*/
unsigned int max_segment_size;
unsigned int min_align_mask;
unsigned long segment_boundary_mask;
};
/**
* enum device_link_state - Device link states.
* @DL_STATE_NONE: The presence of the drivers is not being tracked.
* @DL_STATE_DORMANT: None of the supplier/consumer drivers is present.
* @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not.
* @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present).
* @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present.
* @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding.
*/
enum device_link_state {
DL_STATE_NONE = -1,
DL_STATE_DORMANT = 0,
DL_STATE_AVAILABLE,
DL_STATE_CONSUMER_PROBE,
DL_STATE_ACTIVE,
DL_STATE_SUPPLIER_UNBIND,
};
/*
* Device link flags.
*
* STATELESS: The core will not remove this link automatically.
* AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind.
* PM_RUNTIME: If set, the runtime PM framework will use this link.
* RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
* AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind.
* AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds.
* MANAGED: The core tracks presence of supplier/consumer drivers (internal).
* SYNC_STATE_ONLY: Link only affects sync_state() behavior.
* INFERRED: Inferred from data (eg: firmware) and not from driver actions.
*/
#define DL_FLAG_STATELESS BIT(0)
#define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1)
#define DL_FLAG_PM_RUNTIME BIT(2)
#define DL_FLAG_RPM_ACTIVE BIT(3)
#define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4)
#define DL_FLAG_AUTOPROBE_CONSUMER BIT(5)
#define DL_FLAG_MANAGED BIT(6)
#define DL_FLAG_SYNC_STATE_ONLY BIT(7)
#define DL_FLAG_INFERRED BIT(8)
#define DL_FLAG_CYCLE BIT(9)
/**
* enum dl_dev_state - Device driver presence tracking information.
* @DL_DEV_NO_DRIVER: There is no driver attached to the device.
* @DL_DEV_PROBING: A driver is probing.
* @DL_DEV_DRIVER_BOUND: The driver has been bound to the device.
* @DL_DEV_UNBINDING: The driver is unbinding from the device.
*/
enum dl_dev_state {
DL_DEV_NO_DRIVER = 0,
DL_DEV_PROBING,
DL_DEV_DRIVER_BOUND,
DL_DEV_UNBINDING,
};
/**
* enum device_removable - Whether the device is removable. The criteria for a
* device to be classified as removable is determined by its subsystem or bus.
* @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this
* device (default).
* @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown.
* @DEVICE_FIXED: Device is not removable by the user.
* @DEVICE_REMOVABLE: Device is removable by the user.
*/
enum device_removable {
DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */
DEVICE_REMOVABLE_UNKNOWN,
DEVICE_FIXED,
DEVICE_REMOVABLE,
};
/**
* struct dev_links_info - Device data related to device links.
* @suppliers: List of links to supplier devices.
* @consumers: List of links to consumer devices.
* @defer_sync: Hook to global list of devices that have deferred sync_state.
* @status: Driver status information.
*/
struct dev_links_info {
struct list_head suppliers;
struct list_head consumers;
struct list_head defer_sync;
enum dl_dev_state status;
};
/**
* struct dev_msi_info - Device data related to MSI
* @domain: The MSI interrupt domain associated to the device
* @data: Pointer to MSI device data
*/
struct dev_msi_info {
#ifdef CONFIG_GENERIC_MSI_IRQ
struct irq_domain *domain;
struct msi_device_data *data;
#endif
};
/**
* enum device_physical_location_panel - Describes which panel surface of the
* system's housing the device connection point resides on.
* @DEVICE_PANEL_TOP: Device connection point is on the top panel.
* @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel.
* @DEVICE_PANEL_LEFT: Device connection point is on the left panel.
* @DEVICE_PANEL_RIGHT: Device connection point is on the right panel.
* @DEVICE_PANEL_FRONT: Device connection point is on the front panel.
* @DEVICE_PANEL_BACK: Device connection point is on the back panel.
* @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown.
*/
enum device_physical_location_panel {
DEVICE_PANEL_TOP,
DEVICE_PANEL_BOTTOM,
DEVICE_PANEL_LEFT,
DEVICE_PANEL_RIGHT,
DEVICE_PANEL_FRONT,
DEVICE_PANEL_BACK,
DEVICE_PANEL_UNKNOWN,
};
/**
* enum device_physical_location_vertical_position - Describes vertical
* position of the device connection point on the panel surface.
* @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel.
* @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel.
* @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel.
*/
enum device_physical_location_vertical_position {
DEVICE_VERT_POS_UPPER,
DEVICE_VERT_POS_CENTER,
DEVICE_VERT_POS_LOWER,
};
/**
* enum device_physical_location_horizontal_position - Describes horizontal
* position of the device connection point on the panel surface.
* @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel.
* @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel.
* @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel.
*/
enum device_physical_location_horizontal_position {
DEVICE_HORI_POS_LEFT,
DEVICE_HORI_POS_CENTER,
DEVICE_HORI_POS_RIGHT,
};
/**
* struct device_physical_location - Device data related to physical location
* of the device connection point.
* @panel: Panel surface of the system's housing that the device connection
* point resides on.
* @vertical_position: Vertical position of the device connection point within
* the panel.
* @horizontal_position: Horizontal position of the device connection point
* within the panel.
* @dock: Set if the device connection point resides in a docking station or
* port replicator.
* @lid: Set if this device connection point resides on the lid of laptop
* system.
*/
struct device_physical_location {
enum device_physical_location_panel panel;
enum device_physical_location_vertical_position vertical_position;
enum device_physical_location_horizontal_position horizontal_position;
bool dock;
bool lid;
};
/**
* struct device - The basic device structure
* @parent: The device's "parent" device, the device to which it is attached.
* In most cases, a parent device is some sort of bus or host
* controller. If parent is NULL, the device, is a top-level device,
* which is not usually what you want.
* @p: Holds the private data of the driver core portions of the device.
* See the comment of the struct device_private for detail.
* @kobj: A top-level, abstract class from which other classes are derived.
* @init_name: Initial name of the device.
* @type: The type of device.
* This identifies the device type and carries type-specific
* information.
* @mutex: Mutex to synchronize calls to its driver.
* @bus: Type of bus device is on.
* @driver: Which driver has allocated this
* @platform_data: Platform data specific to the device.
* Example: For devices on custom boards, as typical of embedded
* and SOC based hardware, Linux often uses platform_data to point
* to board-specific structures describing devices and how they
* are wired. That can include what ports are available, chip
* variants, which GPIO pins act in what additional roles, and so
* on. This shrinks the "Board Support Packages" (BSPs) and
* minimizes board-specific #ifdefs in drivers.
* @driver_data: Private pointer for driver specific info.
* @links: Links to suppliers and consumers of this device.
* @power: For device power management.
* See Documentation/driver-api/pm/devices.rst for details.
* @pm_domain: Provide callbacks that are executed during system suspend,
* hibernation, system resume and during runtime PM transitions
* along with subsystem-level and driver-level callbacks.
* @em_pd: device's energy model performance domain
* @pins: For device pin management.
* See Documentation/driver-api/pin-control.rst for details.
* @msi: MSI related data
* @numa_node: NUMA node this device is close to.
* @dma_ops: DMA mapping operations for this device.
* @dma_mask: Dma mask (if dma'ble device).
* @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
* hardware supports 64-bit addresses for consistent allocations
* such descriptors.
* @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
* DMA limit than the device itself supports.
* @dma_range_map: map for DMA memory ranges relative to that of RAM
* @dma_parms: A low level driver may set these to teach IOMMU code about
* segment limitations.
* @dma_pools: Dma pools (if dma'ble device).
* @dma_mem: Internal for coherent mem override.
* @cma_area: Contiguous memory area for dma allocations
* @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use.
* @dma_io_tlb_pools: List of transient swiotlb memory pools.
* @dma_io_tlb_lock: Protects changes to the list of active pools.
* @dma_uses_io_tlb: %true if device has used the software IO TLB.
* @archdata: For arch-specific additions.
* @of_node: Associated device tree node.
* @fwnode: Associated device node supplied by platform firmware.
* @devt: For creating the sysfs "dev".
* @id: device instance
* @devres_lock: Spinlock to protect the resource of the device.
* @devres_head: The resources list of the device.
* @class: The class of the device.
* @groups: Optional attribute groups.
* @release: Callback to free the device after all references have
* gone away. This should be set by the allocator of the
* device (i.e. the bus driver that discovered the device).
* @iommu_group: IOMMU group the device belongs to.
* @iommu: Per device generic IOMMU runtime data
* @physical_location: Describes physical location of the device connection
* point in the system housing.
* @removable: Whether the device can be removed from the system. This
* should be set by the subsystem / bus driver that discovered
* the device.
*
* @offline_disabled: If set, the device is permanently online.
* @offline: Set after successful invocation of bus type's .offline().
* @of_node_reused: Set if the device-tree node is shared with an ancestor
* device.
* @state_synced: The hardware state of this device has been synced to match
* the software state of this device by calling the driver/bus
* sync_state() callback.
* @can_match: The device has matched with a driver at least once or it is in
* a bus (like AMBA) which can't check for matching drivers until
* other devices probe successfully.
* @dma_coherent: this particular device is dma coherent, even if the
* architecture supports non-coherent devices.
* @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the
* streaming DMA operations (->map_* / ->unmap_* / ->sync_*),
* and optionall (if the coherent mask is large enough) also
* for dma allocations. This flag is managed by the dma ops
* instance from ->dma_supported.
* @dma_skip_sync: DMA sync operations can be skipped for coherent buffers.
* @dma_iommu: Device is using default IOMMU implementation for DMA and
* doesn't rely on dma_ops structure.
*
* At the lowest level, every device in a Linux system is represented by an
* instance of struct device. The device structure contains the information
* that the device model core needs to model the system. Most subsystems,
* however, track additional information about the devices they host. As a
* result, it is rare for devices to be represented by bare device structures;
* instead, that structure, like kobject structures, is usually embedded within
* a higher-level representation of the device.
*/
struct device {
struct kobject kobj;
struct device *parent;
struct device_private *p;
const char *init_name; /* initial name of the device */
const struct device_type *type;
const struct bus_type *bus; /* type of bus device is on */
struct device_driver *driver; /* which driver has allocated this
device */
void *platform_data; /* Platform specific data, device
core doesn't touch it */
void *driver_data; /* Driver data, set and get with
dev_set_drvdata/dev_get_drvdata */
struct mutex mutex; /* mutex to synchronize calls to
* its driver.
*/
struct dev_links_info links;
struct dev_pm_info power;
struct dev_pm_domain *pm_domain;
#ifdef CONFIG_ENERGY_MODEL
struct em_perf_domain *em_pd;
#endif
#ifdef CONFIG_PINCTRL
struct dev_pin_info *pins;
#endif
struct dev_msi_info msi;
#ifdef CONFIG_ARCH_HAS_DMA_OPS
const struct dma_map_ops *dma_ops;
#endif
u64 *dma_mask; /* dma mask (if dma'able device) */
u64 coherent_dma_mask;/* Like dma_mask, but for
alloc_coherent mappings as
not all hardware supports
64 bit addresses for consistent
allocations such descriptors. */
u64 bus_dma_limit; /* upstream dma constraint */
const struct bus_dma_region *dma_range_map;
struct device_dma_parameters *dma_parms;
struct list_head dma_pools; /* dma pools (if dma'ble) */
#ifdef CONFIG_DMA_DECLARE_COHERENT
struct dma_coherent_mem *dma_mem; /* internal for coherent mem
override */
#endif
#ifdef CONFIG_DMA_CMA
struct cma *cma_area; /* contiguous memory area for dma
allocations */
#endif
#ifdef CONFIG_SWIOTLB
struct io_tlb_mem *dma_io_tlb_mem;
#endif
#ifdef CONFIG_SWIOTLB_DYNAMIC
struct list_head dma_io_tlb_pools;
spinlock_t dma_io_tlb_lock;
bool dma_uses_io_tlb;
#endif
/* arch specific additions */
struct dev_archdata archdata;
struct device_node *of_node; /* associated device tree node */
struct fwnode_handle *fwnode; /* firmware device node */
#ifdef CONFIG_NUMA
int numa_node; /* NUMA node this device is close to */
#endif
dev_t devt; /* dev_t, creates the sysfs "dev" */
u32 id; /* device instance */
spinlock_t devres_lock;
struct list_head devres_head;
const struct class *class;
const struct attribute_group **groups; /* optional groups */
void (*release)(struct device *dev);
struct iommu_group *iommu_group;
struct dev_iommu *iommu;
struct device_physical_location *physical_location;
enum device_removable removable;
bool offline_disabled:1;
bool offline:1;
bool of_node_reused:1;
bool state_synced:1;
bool can_match:1;
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
bool dma_coherent:1;
#endif
#ifdef CONFIG_DMA_OPS_BYPASS
bool dma_ops_bypass : 1;
#endif
#ifdef CONFIG_DMA_NEED_SYNC
bool dma_skip_sync:1;
#endif
#ifdef CONFIG_IOMMU_DMA
bool dma_iommu:1;
#endif
};
/**
* struct device_link - Device link representation.
* @supplier: The device on the supplier end of the link.
* @s_node: Hook to the supplier device's list of links to consumers.
* @consumer: The device on the consumer end of the link.
* @c_node: Hook to the consumer device's list of links to suppliers.
* @link_dev: device used to expose link details in sysfs
* @status: The state of the link (with respect to the presence of drivers).
* @flags: Link flags.
* @rpm_active: Whether or not the consumer device is runtime-PM-active.
* @kref: Count repeated addition of the same link.
* @rm_work: Work structure used for removing the link.
* @supplier_preactivated: Supplier has been made active before consumer probe.
*/
struct device_link {
struct device *supplier;
struct list_head s_node;
struct device *consumer;
struct list_head c_node;
struct device link_dev;
enum device_link_state status;
u32 flags;
refcount_t rpm_active;
struct kref kref;
struct work_struct rm_work;
bool supplier_preactivated; /* Owned by consumer probe. */
};
#define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj)
/**
* device_iommu_mapped - Returns true when the device DMA is translated
* by an IOMMU
* @dev: Device to perform the check on
*/
static inline bool device_iommu_mapped(struct device *dev)
{
return (dev->iommu_group != NULL);
}
/* Get the wakeup routines, which depend on struct device */
#include <linux/pm_wakeup.h>
/**
* dev_name - Return a device's name.
* @dev: Device with name to get.
* Return: The kobject name of the device, or its initial name if unavailable.
*/
static inline const char *dev_name(const struct device *dev)
{
/* Use the init name until the kobject becomes available */
if (dev->init_name)
return dev->init_name;
return kobject_name(&dev->kobj);
}
/**
* dev_bus_name - Return a device's bus/class name, if at all possible
* @dev: struct device to get the bus/class name of
*
* Will return the name of the bus/class the device is attached to. If it is
* not attached to a bus/class, an empty string will be returned.
*/
static inline const char *dev_bus_name(const struct device *dev)
{
return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : "");
}
__printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...);
#ifdef CONFIG_NUMA
static inline int dev_to_node(struct device *dev)
{
return dev->numa_node;
}
static inline void set_dev_node(struct device *dev, int node)
{
dev->numa_node = node;
}
#else
static inline int dev_to_node(struct device *dev)
{
return NUMA_NO_NODE;
}
static inline void set_dev_node(struct device *dev, int node)
{
}
#endif
static inline struct irq_domain *dev_get_msi_domain(const struct device *dev)
{
#ifdef CONFIG_GENERIC_MSI_IRQ
return dev->msi.domain;
#else
return NULL;
#endif
}
static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d)
{
#ifdef CONFIG_GENERIC_MSI_IRQ
dev->msi.domain = d;
#endif
}
static inline void *dev_get_drvdata(const struct device *dev)
{
return dev->driver_data;
}
static inline void dev_set_drvdata(struct device *dev, void *data)
{
dev->driver_data = data;
}
static inline struct pm_subsys_data *dev_to_psd(struct device *dev)
{
return dev ? dev->power.subsys_data : NULL;
}
static inline unsigned int dev_get_uevent_suppress(const struct device *dev)
{
return dev->kobj.uevent_suppress;
}
static inline void dev_set_uevent_suppress(struct device *dev, int val)
{
dev->kobj.uevent_suppress = val;
}
static inline int device_is_registered(struct device *dev)
{
return dev->kobj.state_in_sysfs;
}
static inline void device_enable_async_suspend(struct device *dev)
{
if (!dev->power.is_prepared)
dev->power.async_suspend = true;
}
static inline void device_disable_async_suspend(struct device *dev)
{
if (!dev->power.is_prepared)
dev->power.async_suspend = false;
}
static inline bool device_async_suspend_enabled(struct device *dev)
{
return !!dev->power.async_suspend;
}
static inline bool device_pm_not_required(struct device *dev)
{
return dev->power.no_pm;
}
static inline void device_set_pm_not_required(struct device *dev)
{
dev->power.no_pm = true;
}
static inline void dev_pm_syscore_device(struct device *dev, bool val)
{
#ifdef CONFIG_PM_SLEEP
dev->power.syscore = val;
#endif
}
static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags)
{
dev->power.driver_flags = flags;
}
static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags)
{
return !!(dev->power.driver_flags & flags);
}
static inline bool dev_pm_smart_suspend(struct device *dev)
{
#ifdef CONFIG_PM_SLEEP
return dev->power.smart_suspend;
#else
return false;
#endif
}
static inline void device_lock(struct device *dev)
{
mutex_lock(&dev->mutex);
}
static inline int device_lock_interruptible(struct device *dev)
{
return mutex_lock_interruptible(&dev->mutex);
}
static inline int device_trylock(struct device *dev)
{
return mutex_trylock(&dev->mutex);
}
static inline void device_unlock(struct device *dev)
{
mutex_unlock(&dev->mutex);
}
DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
static inline void device_lock_assert(struct device *dev)
{
lockdep_assert_held(&dev->mutex);
}
static inline bool dev_has_sync_state(struct device *dev)
{
if (!dev)
return false;
if (dev->driver && dev->driver->sync_state)
return true;
if (dev->bus && dev->bus->sync_state)
return true;
return false;
}
static inline void dev_set_removable(struct device *dev,
enum device_removable removable)
{
dev->removable = removable;
}
static inline bool dev_is_removable(struct device *dev)
{
return dev->removable == DEVICE_REMOVABLE;
}
static inline bool dev_removable_is_valid(struct device *dev)
{
return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED;
}
/*
* High level routines for use by the bus drivers
*/
int __must_check device_register(struct device *dev);
void device_unregister(struct device *dev);
void device_initialize(struct device *dev);
int __must_check device_add(struct device *dev);
void device_del(struct device *dev);
DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T))
int device_for_each_child(struct device *parent, void *data,
device_iter_t fn);
int device_for_each_child_reverse(struct device *parent, void *data,
device_iter_t fn);
int device_for_each_child_reverse_from(struct device *parent,
struct device *from, void *data,
device_iter_t fn);
struct device *device_find_child(struct device *parent, const void *data,
device_match_t match);
/**
* device_find_child_by_name - device iterator for locating a child device.
* @parent: parent struct device
* @name: name of the child device
*
* This is similar to the device_find_child() function above, but it
* returns a reference to a device that has the name @name.
*
* NOTE: you will need to drop the reference with put_device() after use.
*/
static inline struct device *device_find_child_by_name(struct device *parent,
const char *name)
{
return device_find_child(parent, name, device_match_name);
}
/**
* device_find_any_child - device iterator for locating a child device, if any.
* @parent: parent struct device
*
* This is similar to the device_find_child() function above, but it
* returns a reference to a child device, if any.
*
* NOTE: you will need to drop the reference with put_device() after use.
*/
static inline struct device *device_find_any_child(struct device *parent)
{
return device_find_child(parent, NULL, device_match_any);
}
int device_rename(struct device *dev, const char *new_name);
int device_move(struct device *dev, struct device *new_parent,
enum dpm_order dpm_order);
int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
static inline bool device_supports_offline(struct device *dev)
{
return dev->bus && dev->bus->offline && dev->bus->online;
}
#define __device_lock_set_class(dev, name, key) \
do { \
struct device *__d2 __maybe_unused = dev; \
lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \
} while (0)
/**
* device_lock_set_class - Specify a temporary lock class while a device
* is attached to a driver
* @dev: device to modify
* @key: lock class key data
*
* This must be called with the device_lock() already held, for example
* from driver ->probe(). Take care to only override the default
* lockdep_no_validate class.
*/
#ifdef CONFIG_LOCKDEP
#define device_lock_set_class(dev, key) \
do { \
struct device *__d = dev; \
dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \
&__lockdep_no_validate__), \
"overriding existing custom lock class\n"); \
__device_lock_set_class(__d, #key, key); \
} while (0)
#else
#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key)
#endif
/**
* device_lock_reset_class - Return a device to the default lockdep novalidate state
* @dev: device to modify
*
* This must be called with the device_lock() already held, for example
* from driver ->remove().
*/
#define device_lock_reset_class(dev) \
do { \
struct device *__d __maybe_unused = dev; \
lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \
_THIS_IP_); \
} while (0)
void lock_device_hotplug(void);
void unlock_device_hotplug(void);
int lock_device_hotplug_sysfs(void);
int device_offline(struct device *dev);
int device_online(struct device *dev);
void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
void device_set_node(struct device *dev, struct fwnode_handle *fwnode);
int device_add_of_node(struct device *dev, struct device_node *of_node);
void device_remove_of_node(struct device *dev);
void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
static inline struct device_node *dev_of_node(struct device *dev)
{
if (!IS_ENABLED(CONFIG_OF) || !dev)
return NULL;
return dev->of_node;
}
static inline int dev_num_vf(struct device *dev)
{
if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev);
return 0;
}
/*
* Root device objects for grouping under /sys/devices
*/
struct device *__root_device_register(const char *name, struct module *owner);
/* This is a macro to avoid include problems with THIS_MODULE */
#define root_device_register(name) \
__root_device_register(name, THIS_MODULE)
void root_device_unregister(struct device *root);
static inline void *dev_get_platdata(const struct device *dev)
{
return dev->platform_data;
}
/*
* Manual binding of a device to driver. See drivers/base/bus.c
* for information on use.
*/
int __must_check device_driver_attach(const struct device_driver *drv,
struct device *dev);
int __must_check device_bind_driver(struct device *dev);
void device_release_driver(struct device *dev);
int __must_check device_attach(struct device *dev);
int __must_check driver_attach(const struct device_driver *drv);
void device_initial_probe(struct device *dev);
int __must_check device_reprobe(struct device *dev);
bool device_is_bound(struct device *dev);
/*
* Easy functions for dynamically creating devices on the fly
*/
__printf(5, 6) struct device *
device_create(const struct class *cls, struct device *parent, dev_t devt,
void *drvdata, const char *fmt, ...);
__printf(6, 7) struct device *
device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt,
void *drvdata, const struct attribute_group **groups,
const char *fmt, ...);
void device_destroy(const struct class *cls, dev_t devt);
int __must_check device_add_groups(struct device *dev,
const struct attribute_group **groups);
void device_remove_groups(struct device *dev,
const struct attribute_group **groups);
static inline int __must_check device_add_group(struct device *dev,
const struct attribute_group *grp)
{
const struct attribute_group *groups[] = { grp, NULL };
return device_add_groups(dev, groups);
}
static inline void device_remove_group(struct device *dev,
const struct attribute_group *grp)
{
const struct attribute_group *groups[] = { grp, NULL };
device_remove_groups(dev, groups);
}
int __must_check devm_device_add_group(struct device *dev,
const struct attribute_group *grp);
/*
* get_device - atomically increment the reference count for the device.
*
*/
struct device *get_device(struct device *dev);
void put_device(struct device *dev);
DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T))
bool kill_device(struct device *dev);
#ifdef CONFIG_DEVTMPFS
int devtmpfs_mount(void);
#else
static inline int devtmpfs_mount(void) { return 0; }
#endif
/* drivers/base/power/shutdown.c */
void device_shutdown(void);
/* debugging and troubleshooting/diagnostic helpers. */
const char *dev_driver_string(const struct device *dev);
/* Device links interface. */
struct device_link *device_link_add(struct device *consumer,
struct device *supplier, u32 flags);
void device_link_del(struct device_link *link);
void device_link_remove(void *consumer, struct device *supplier);
void device_links_supplier_sync_state_pause(void);
void device_links_supplier_sync_state_resume(void);
void device_link_wait_removal(void);
/* Create alias, so I can be autoloaded. */
#define MODULE_ALIAS_CHARDEV(major,minor) \
MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_CHARDEV_MAJOR(major) \
MODULE_ALIAS("char-major-" __stringify(major) "-*")
#endif /* _DEVICE_H_ */
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/percpu-vm.c - vmalloc area based chunk allocation
*
* Copyright (C) 2010 SUSE Linux Products GmbH
* Copyright (C) 2010 Tejun Heo <tj@kernel.org>
*
* Chunks are mapped into vmalloc areas and populated page by page.
* This is the default chunk allocator.
*/
#include "internal.h"
static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
unsigned int cpu, int page_idx)
{
/* must not be used on pre-mapped chunk */
WARN_ON(chunk->immutable);
return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));
}
/**
* pcpu_get_pages - get temp pages array
*
* Returns pointer to array of pointers to struct page which can be indexed
* with pcpu_page_idx(). Note that there is only one array and accesses
* should be serialized by pcpu_alloc_mutex.
*
* RETURNS:
* Pointer to temp pages array on success.
*/
static struct page **pcpu_get_pages(void)
{
static struct page **pages;
size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
lockdep_assert_held(&pcpu_alloc_mutex);
if (!pages)
pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL);
return pages;
}
/**
* pcpu_free_pages - free pages which were allocated for @chunk
* @chunk: chunk pages were allocated for
* @pages: array of pages to be freed, indexed by pcpu_page_idx()
* @page_start: page index of the first page to be freed
* @page_end: page index of the last page to be freed + 1
*
* Free pages [@page_start and @page_end) in @pages for all units.
* The pages were allocated for @chunk.
*/
static void pcpu_free_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu;
int i;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page *page = pages[pcpu_page_idx(cpu, i)];
if (page)
__free_page(page);
}
}
}
/**
* pcpu_alloc_pages - allocates pages for @chunk
* @chunk: target chunk
* @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
* @page_start: page index of the first page to be allocated
* @page_end: page index of the last page to be allocated + 1
* @gfp: allocation flags passed to the underlying allocator
*
* Allocate pages [@page_start,@page_end) into @pages for all units.
* The allocation is for @chunk. Percpu core doesn't care about the
* content of @pages and will pass it verbatim to pcpu_map_pages().
*/
static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end,
gfp_t gfp)
{
unsigned int cpu, tcpu;
int i;
gfp |= __GFP_HIGHMEM;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
if (!*pagep)
goto err;
}
}
return 0;
err:
while (--i >= page_start)
__free_page(pages[pcpu_page_idx(cpu, i)]);
for_each_possible_cpu(tcpu) {
if (tcpu == cpu)
break;
for (i = page_start; i < page_end; i++)
__free_page(pages[pcpu_page_idx(tcpu, i)]);
}
return -ENOMEM;
}
/**
* pcpu_pre_unmap_flush - flush cache prior to unmapping
* @chunk: chunk the regions to be flushed belongs to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages in [@page_start,@page_end) of @chunk are about to be
* unmapped. Flush cache. As each flushing trial can be very
* expensive, issue flush on the whole region at once rather than
* doing it for each cpu. This could be an overkill but is more
* scalable.
*/
static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vunmap(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
{
vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT));
}
/**
* pcpu_unmap_pages - unmap pages out of a pcpu_chunk
* @chunk: chunk of interest
* @pages: pages array which can be used to pass information to free
* @page_start: page index of the first page to unmap
* @page_end: page index of the last page to unmap + 1
*
* For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
* Corresponding elements in @pages were cleared by the caller and can
* be used to carry information to pcpu_free_pages() which will be
* called after all unmaps are finished. The caller should call
* proper pre/post flush functions.
*/
static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu;
int i;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page *page;
page = pcpu_chunk_page(chunk, cpu, i);
WARN_ON(!page);
pages[pcpu_page_idx(cpu, i)] = page;
}
__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
page_end - page_start);
}
}
/**
* pcpu_post_unmap_tlb_flush - flush TLB after unmapping
* @chunk: pcpu_chunk the regions to be flushed belong to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages [@page_start,@page_end) of @chunk have been unmapped. Flush
* TLB for the regions. This can be skipped if the area is to be
* returned to vmalloc as vmalloc will handle TLB flushing lazily.
*
* As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
* for the whole region.
*/
static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_tlb_kernel_range(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static int __pcpu_map_pages(unsigned long addr, struct page **pages,
int nr_pages)
{
return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT),
PAGE_KERNEL, pages, PAGE_SHIFT);
}
/**
* pcpu_map_pages - map pages into a pcpu_chunk
* @chunk: chunk of interest
* @pages: pages array containing pages to be mapped
* @page_start: page index of the first page to map
* @page_end: page index of the last page to map + 1
*
* For each cpu, map pages [@page_start,@page_end) into @chunk. The
* caller is responsible for calling pcpu_post_map_flush() after all
* mappings are complete.
*
* This function is responsible for setting up whatever is necessary for
* reverse lookup (addr -> chunk).
*/
static int pcpu_map_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu, tcpu;
int i, err;
for_each_possible_cpu(cpu) {
err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
&pages[pcpu_page_idx(cpu, page_start)],
page_end - page_start);
if (err < 0)
goto err;
for (i = page_start; i < page_end; i++)
pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
chunk);
}
return 0;
err:
for_each_possible_cpu(tcpu) {
__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
page_end - page_start);
if (tcpu == cpu)
break;
}
pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
return err;
}
/**
* pcpu_post_map_flush - flush cache after mapping
* @chunk: pcpu_chunk the regions to be flushed belong to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages [@page_start,@page_end) of @chunk have been mapped. Flush
* cache.
*
* As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
* for the whole region.
*/
static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vmap(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
/**
* pcpu_populate_chunk - populate and map an area of a pcpu_chunk
* @chunk: chunk of interest
* @page_start: the start page
* @page_end: the end page
* @gfp: allocation flags passed to the underlying memory allocator
*
* For each cpu, populate and map pages [@page_start,@page_end) into
* @chunk.
*
* CONTEXT:
* pcpu_alloc_mutex, does GFP_KERNEL allocation.
*/
static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end, gfp_t gfp)
{
struct page **pages;
pages = pcpu_get_pages();
if (!pages)
return -ENOMEM;
if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp))
return -ENOMEM;
if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
pcpu_free_pages(chunk, pages, page_start, page_end);
return -ENOMEM;
}
pcpu_post_map_flush(chunk, page_start, page_end);
return 0;
}
/**
* pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
* @chunk: chunk to depopulate
* @page_start: the start page
* @page_end: the end page
*
* For each cpu, depopulate and unmap pages [@page_start,@page_end)
* from @chunk.
*
* Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the
* region back to vmalloc() which will lazily flush the tlb.
*
* CONTEXT:
* pcpu_alloc_mutex.
*/
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
struct page **pages;
/*
* If control reaches here, there must have been at least one
* successful population attempt so the temp pages array must
* be available now.
*/
pages = pcpu_get_pages();
BUG_ON(!pages);
/* unmap and free */
pcpu_pre_unmap_flush(chunk, page_start, page_end);
pcpu_unmap_pages(chunk, pages, page_start, page_end);
pcpu_free_pages(chunk, pages, page_start, page_end);
}
static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
{
struct pcpu_chunk *chunk;
struct vm_struct **vms;
chunk = pcpu_alloc_chunk(gfp);
if (!chunk)
return NULL;
vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
pcpu_nr_groups, pcpu_atom_size);
if (!vms) {
pcpu_free_chunk(chunk);
return NULL;
}
chunk->data = vms;
chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
pcpu_stats_chunk_alloc();
trace_percpu_create_chunk(chunk->base_addr);
return chunk;
}
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
{
if (!chunk)
return;
pcpu_stats_chunk_dealloc();
trace_percpu_destroy_chunk(chunk->base_addr);
if (chunk->data)
pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
pcpu_free_chunk(chunk);
}
static struct page *pcpu_addr_to_page(void *addr)
{
return vmalloc_to_page(addr);
}
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
{
/* no extra restriction */
return 0;
}
/**
* pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim
* @chunk: chunk of interest
*
* This is the entry point for percpu reclaim. If a chunk qualifies, it is then
* isolated and managed in separate lists at the back of pcpu_slot: sidelined
* and to_depopulate respectively. The to_depopulate list holds chunks slated
* for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once
* they are on this list. Once depopulated, they are moved onto the sidelined
* list which enables them to be pulled back in for allocation if no other chunk
* can suffice the allocation.
*/
static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
{
/* do not reclaim either the first chunk or reserved chunk */
if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk)
return false;
/*
* If it is isolated, it may be on the sidelined list so move it back to
* the to_depopulate list. If we hit at least 1/4 pages empty pages AND
* there is no system-wide shortage of empty pages aside from this
* chunk, move it to the to_depopulate list.
*/
return ((chunk->isolated && chunk->nr_empty_pop_pages) ||
(pcpu_nr_empty_pop_pages >
(PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) &&
chunk->nr_empty_pop_pages >= chunk->nr_pages / 4));
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Statically sized hash table implementation
* (C) 2012 Sasha Levin <levinsasha928@gmail.com>
*/
#ifndef _LINUX_HASHTABLE_H
#define _LINUX_HASHTABLE_H
#include <linux/list.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/hash.h>
#include <linux/rculist.h>
#define DEFINE_HASHTABLE(name, bits) \
struct hlist_head name[1 << (bits)] = \
{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
#define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \
struct hlist_head name[1 << (bits)] __read_mostly = \
{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
#define DECLARE_HASHTABLE(name, bits) \
struct hlist_head name[1 << (bits)]
#define HASH_SIZE(name) (ARRAY_SIZE(name))
#define HASH_BITS(name) ilog2(HASH_SIZE(name))
/* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */
#define hash_min(val, bits) \
(sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits))
static inline void __hash_init(struct hlist_head *ht, unsigned int sz)
{
unsigned int i;
for (i = 0; i < sz; i++)
INIT_HLIST_HEAD(&ht[i]);
}
/**
* hash_init - initialize a hash table
* @hashtable: hashtable to be initialized
*
* Calculates the size of the hashtable from the given parameter, otherwise
* same as hash_init_size.
*
* This has to be a macro since HASH_BITS() will not work on pointers since
* it calculates the size during preprocessing.
*/
#define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable))
/**
* hash_add - add an object to a hashtable
* @hashtable: hashtable to add to
* @node: the &struct hlist_node of the object to be added
* @key: the key of the object to be added
*/
#define hash_add(hashtable, node, key) \
hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
/**
* hash_add_rcu - add an object to a rcu enabled hashtable
* @hashtable: hashtable to add to
* @node: the &struct hlist_node of the object to be added
* @key: the key of the object to be added
*/
#define hash_add_rcu(hashtable, node, key) \
hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
/**
* hash_hashed - check whether an object is in any hashtable
* @node: the &struct hlist_node of the object to be checked
*/
static inline bool hash_hashed(struct hlist_node *node)
{
return !hlist_unhashed(node);
}
static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz)
{
unsigned int i;
for (i = 0; i < sz; i++)
if (!hlist_empty(&ht[i]))
return false;
return true;
}
/**
* hash_empty - check whether a hashtable is empty
* @hashtable: hashtable to check
*
* This has to be a macro since HASH_BITS() will not work on pointers since
* it calculates the size during preprocessing.
*/
#define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable))
/**
* hash_del - remove an object from a hashtable
* @node: &struct hlist_node of the object to remove
*/
static inline void hash_del(struct hlist_node *node)
{
hlist_del_init(node);
}
/**
* hash_del_rcu - remove an object from a rcu enabled hashtable
* @node: &struct hlist_node of the object to remove
*/
static inline void hash_del_rcu(struct hlist_node *node)
{
hlist_del_init_rcu(node);
}
/**
* hash_for_each - iterate over a hashtable
* @name: hashtable to iterate
* @bkt: integer to use as bucket loop cursor
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
*/
#define hash_for_each(name, bkt, obj, member) \
for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
(bkt)++)\
hlist_for_each_entry(obj, &name[bkt], member)
/**
* hash_for_each_rcu - iterate over a rcu enabled hashtable
* @name: hashtable to iterate
* @bkt: integer to use as bucket loop cursor
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
*/
#define hash_for_each_rcu(name, bkt, obj, member) \
for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
(bkt)++)\
hlist_for_each_entry_rcu(obj, &name[bkt], member)
/**
* hash_for_each_safe - iterate over a hashtable safe against removal of
* hash entry
* @name: hashtable to iterate
* @bkt: integer to use as bucket loop cursor
* @tmp: a &struct hlist_node used for temporary storage
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
*/
#define hash_for_each_safe(name, bkt, tmp, obj, member) \
for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
(bkt)++)\
hlist_for_each_entry_safe(obj, tmp, &name[bkt], member)
/**
* hash_for_each_possible - iterate over all possible objects hashing to the
* same bucket
* @name: hashtable to iterate
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
* @key: the key of the objects to iterate over
*/
#define hash_for_each_possible(name, obj, member, key) \
hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member)
/**
* hash_for_each_possible_rcu - iterate over all possible objects hashing to the
* same bucket in an rcu enabled hashtable
* @name: hashtable to iterate
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
* @key: the key of the objects to iterate over
*/
#define hash_for_each_possible_rcu(name, obj, member, key, cond...) \
hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\
member, ## cond)
/**
* hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing
* to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable
* @name: hashtable to iterate
* @obj: the type * to use as a loop cursor for each entry
* @member: the name of the hlist_node within the struct
* @key: the key of the objects to iterate over
*
* This is the same as hash_for_each_possible_rcu() except that it does
* not do any RCU debugging or tracing.
*/
#define hash_for_each_possible_rcu_notrace(name, obj, member, key) \
hlist_for_each_entry_rcu_notrace(obj, \
&name[hash_min(key, HASH_BITS(name))], member)
/**
* hash_for_each_possible_safe - iterate over all possible objects hashing to the
* same bucket safe against removals
* @name: hashtable to iterate
* @obj: the type * to use as a loop cursor for each entry
* @tmp: a &struct hlist_node used for temporary storage
* @member: the name of the hlist_node within the struct
* @key: the key of the objects to iterate over
*/
#define hash_for_each_possible_safe(name, obj, tmp, member, key) \
hlist_for_each_entry_safe(obj, tmp,\
&name[hash_min(key, HASH_BITS(name))], member)
#endif
// SPDX-License-Identifier: GPL-2.0
#include <linux/irq_work.h>
#include <linux/spinlock.h>
#include <linux/task_work.h>
#include <linux/resume_user_mode.h>
static struct callback_head work_exited; /* all we need is ->next == NULL */
#ifdef CONFIG_IRQ_WORK
static void task_work_set_notify_irq(struct irq_work *entry)
{
test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
}
static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) =
IRQ_WORK_INIT_HARD(task_work_set_notify_irq);
#endif
/**
* task_work_add - ask the @task to execute @work->func()
* @task: the task which should run the callback
* @work: the callback to run
* @notify: how to notify the targeted task
*
* Queue @work for task_work_run() below and notify the @task if @notify
* is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT.
*
* @TWA_SIGNAL works like signals, in that the it will interrupt the targeted
* task and run the task_work, regardless of whether the task is currently
* running in the kernel or userspace.
* @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a
* reschedule IPI to force the targeted task to reschedule and run task_work.
* This can be advantageous if there's no strict requirement that the
* task_work be run as soon as possible, just whenever the task enters the
* kernel anyway.
* @TWA_RESUME work is run only when the task exits the kernel and returns to
* user mode, or before entering guest mode.
* @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the
* current @task and if the current context is NMI.
*
* Fails if the @task is exiting/exited and thus it can't process this @work.
* Otherwise @work->func() will be called when the @task goes through one of
* the aforementioned transitions, or exits.
*
* If the targeted task is exiting, then an error is returned and the work item
* is not queued. It's up to the caller to arrange for an alternative mechanism
* in that case.
*
* Note: there is no ordering guarantee on works queued here. The task_work
* list is LIFO.
*
* RETURNS:
* 0 if succeeds or -ESRCH.
*/
int task_work_add(struct task_struct *task, struct callback_head *work,
enum task_work_notify_mode notify)
{
struct callback_head *head;
if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current))
return -EINVAL;
if (!IS_ENABLED(CONFIG_IRQ_WORK))
return -EINVAL;
} else {
kasan_record_aux_stack(work);
}
head = READ_ONCE(task->task_works);
do {
if (unlikely(head == &work_exited))
return -ESRCH;
work->next = head;
} while (!try_cmpxchg(&task->task_works, &head, work)); switch (notify) {
case TWA_NONE:
break;
case TWA_RESUME:
set_notify_resume(task);
break;
case TWA_SIGNAL:
set_notify_signal(task);
break;
case TWA_SIGNAL_NO_IPI:
__set_notify_signal(task);
break;
#ifdef CONFIG_IRQ_WORK
case TWA_NMI_CURRENT:
irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume));
break;
#endif
default:
WARN_ON_ONCE(1);
break;
}
return 0;
}
/**
* task_work_cancel_match - cancel a pending work added by task_work_add()
* @task: the task which should execute the work
* @match: match function to call
* @data: data to be passed in to match function
*
* RETURNS:
* The found work or NULL if not found.
*/
struct callback_head *
task_work_cancel_match(struct task_struct *task,
bool (*match)(struct callback_head *, void *data),
void *data)
{
struct callback_head **pprev = &task->task_works;
struct callback_head *work;
unsigned long flags;
if (likely(!task_work_pending(task)))
return NULL;
/*
* If cmpxchg() fails we continue without updating pprev.
* Either we raced with task_work_add() which added the
* new entry before this work, we will find it again. Or
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
work = READ_ONCE(*pprev);
while (work) {
if (!match(work, data)) {
pprev = &work->next;
work = READ_ONCE(*pprev);
} else if (try_cmpxchg(pprev, &work, work->next))
break;
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return work;
}
static bool task_work_func_match(struct callback_head *cb, void *data)
{
return cb->func == data;
}
/**
* task_work_cancel_func - cancel a pending work matching a function added by task_work_add()
* @task: the task which should execute the func's work
* @func: identifies the func to match with a work to remove
*
* Find the last queued pending work with ->func == @func and remove
* it from queue.
*
* RETURNS:
* The found work or NULL if not found.
*/
struct callback_head *
task_work_cancel_func(struct task_struct *task, task_work_func_t func)
{
return task_work_cancel_match(task, task_work_func_match, func);
}
static bool task_work_match(struct callback_head *cb, void *data)
{
return cb == data;
}
/**
* task_work_cancel - cancel a pending work added by task_work_add()
* @task: the task which should execute the work
* @cb: the callback to remove if queued
*
* Remove a callback from a task's queue if queued.
*
* RETURNS:
* True if the callback was queued and got cancelled, false otherwise.
*/
bool task_work_cancel(struct task_struct *task, struct callback_head *cb)
{
struct callback_head *ret;
ret = task_work_cancel_match(task, task_work_match, cb);
return ret == cb;
}
/**
* task_work_run - execute the works added by task_work_add()
*
* Flush the pending works. Should be used by the core kernel code.
* Called before the task returns to the user-mode or stops, or when
* it exits. In the latter case task_work_add() can no longer add the
* new work after task_work_run() returns.
*/
void task_work_run(void)
{
struct task_struct *task = current;
struct callback_head *work, *head, *next;
for (;;) {
/*
* work->func() can do task_work_add(), do not set
* work_exited unless the list is empty.
*/
work = READ_ONCE(task->task_works);
do {
head = NULL;
if (!work) { if (task->flags & PF_EXITING)
head = &work_exited;
else
break;
}
} while (!try_cmpxchg(&task->task_works, &work, head));
if (!work)
break;
/*
* Synchronize with task_work_cancel_match(). It can not remove
* the first entry == work, cmpxchg(task_works) must fail.
* But it can remove another entry from the ->next list.
*/
raw_spin_lock_irq(&task->pi_lock);
raw_spin_unlock_irq(&task->pi_lock);
do {
next = work->next;
work->func(work);
work = next;
cond_resched();
} while (work);
}
}
// SPDX-License-Identifier: GPL-2.0-or-later
/* Copyright Amazon.com Inc. or its affiliates. */
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/notifier.h>
#include <linux/rtnetlink.h>
#include <net/net_namespace.h>
#include <net/netdev_lock.h>
#include <net/netns/generic.h>
int netdev_debug_event(struct notifier_block *nb, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
enum netdev_cmd cmd = event;
/* Keep enum and don't add default to trigger -Werror=switch */
switch (cmd) {
case NETDEV_REGISTER:
case NETDEV_UP:
case NETDEV_CHANGE:
netdev_ops_assert_locked(dev);
fallthrough;
case NETDEV_DOWN:
case NETDEV_REBOOT:
case NETDEV_UNREGISTER:
case NETDEV_CHANGEMTU:
case NETDEV_CHANGEADDR:
case NETDEV_PRE_CHANGEADDR:
case NETDEV_GOING_DOWN:
case NETDEV_FEAT_CHANGE:
case NETDEV_BONDING_FAILOVER:
case NETDEV_PRE_UP:
case NETDEV_PRE_TYPE_CHANGE:
case NETDEV_POST_TYPE_CHANGE:
case NETDEV_POST_INIT:
case NETDEV_PRE_UNINIT:
case NETDEV_RELEASE:
case NETDEV_NOTIFY_PEERS:
case NETDEV_JOIN:
case NETDEV_CHANGEUPPER:
case NETDEV_RESEND_IGMP:
case NETDEV_PRECHANGEMTU:
case NETDEV_CHANGEINFODATA:
case NETDEV_BONDING_INFO:
case NETDEV_PRECHANGEUPPER:
case NETDEV_CHANGELOWERSTATE:
case NETDEV_UDP_TUNNEL_PUSH_INFO:
case NETDEV_UDP_TUNNEL_DROP_INFO:
case NETDEV_CHANGE_TX_QUEUE_LEN:
case NETDEV_CVLAN_FILTER_PUSH_INFO:
case NETDEV_CVLAN_FILTER_DROP_INFO:
case NETDEV_SVLAN_FILTER_PUSH_INFO:
case NETDEV_SVLAN_FILTER_DROP_INFO:
case NETDEV_OFFLOAD_XSTATS_ENABLE:
case NETDEV_OFFLOAD_XSTATS_DISABLE:
case NETDEV_OFFLOAD_XSTATS_REPORT_USED:
case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA:
case NETDEV_XDP_FEAT_CHANGE:
ASSERT_RTNL();
break;
case NETDEV_CHANGENAME:
ASSERT_RTNL_NET(net);
break;
}
return NOTIFY_DONE;
}
EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL");
static int rtnl_net_debug_net_id;
static int __net_init rtnl_net_debug_net_init(struct net *net)
{
struct notifier_block *nb;
nb = net_generic(net, rtnl_net_debug_net_id);
nb->notifier_call = netdev_debug_event;
return register_netdevice_notifier_net(net, nb);
}
static void __net_exit rtnl_net_debug_net_exit(struct net *net)
{
struct notifier_block *nb;
nb = net_generic(net, rtnl_net_debug_net_id);
unregister_netdevice_notifier_net(net, nb);
}
static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = {
.init = rtnl_net_debug_net_init,
.exit = rtnl_net_debug_net_exit,
.id = &rtnl_net_debug_net_id,
.size = sizeof(struct notifier_block),
};
static struct notifier_block rtnl_net_debug_block = {
.notifier_call = netdev_debug_event,
};
static int __init rtnl_net_debug_init(void)
{
int ret;
ret = register_pernet_subsys(&rtnl_net_debug_net_ops);
if (ret)
return ret;
ret = register_netdevice_notifier(&rtnl_net_debug_block);
if (ret)
unregister_pernet_subsys(&rtnl_net_debug_net_ops);
return ret;
}
subsys_initcall(rtnl_net_debug_init);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RCULIST_BL_H
#define _LINUX_RCULIST_BL_H
/*
* RCU-protected bl list version. See include/linux/list_bl.h.
*/
#include <linux/list_bl.h>
#include <linux/rcupdate.h>
static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h,
struct hlist_bl_node *n)
{
LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) !=
LIST_BL_LOCKMASK);
rcu_assign_pointer(h->first,
(struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK));
}
static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)
{
return (struct hlist_bl_node *)
((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK);
}
/**
* hlist_bl_del_rcu - deletes entry from hash list without re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_bl_unhashed() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the hash list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_bl_add_head_rcu()
* or hlist_bl_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_bl_for_each_entry().
*/
static inline void hlist_bl_del_rcu(struct hlist_bl_node *n)
{
__hlist_bl_del(n);
n->pprev = LIST_POISON2;
}
/**
* hlist_bl_add_head_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_bl,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_bl_add_head_rcu()
* or hlist_bl_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n,
struct hlist_bl_head *h)
{
struct hlist_bl_node *first;
/* don't need hlist_bl_first_rcu because we're under lock */
first = hlist_bl_first(h);
n->next = first;
if (first) first->pprev = &n->next;
n->pprev = &h->first;
/* need _rcu because we can have concurrent lock free readers */
hlist_bl_set_first_rcu(h, n);
}
/**
* hlist_bl_for_each_entry_rcu - iterate over rcu list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_bl_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_bl_node within the struct.
*
*/
#define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \
for (pos = hlist_bl_first_rcu(head); \
pos && \
({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(pos->next))
#endif
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/irqflags.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/bug.h>
#include "printk_ringbuffer.h"
#include "internal.h"
/**
* DOC: printk_ringbuffer overview
*
* Data Structure
* --------------
* The printk_ringbuffer is made up of 3 internal ringbuffers:
*
* desc_ring
* A ring of descriptors and their meta data (such as sequence number,
* timestamp, loglevel, etc.) as well as internal state information about
* the record and logical positions specifying where in the other
* ringbuffer the text strings are located.
*
* text_data_ring
* A ring of data blocks. A data block consists of an unsigned long
* integer (ID) that maps to a desc_ring index followed by the text
* string of the record.
*
* The internal state information of a descriptor is the key element to allow
* readers and writers to locklessly synchronize access to the data.
*
* Implementation
* --------------
*
* Descriptor Ring
* ~~~~~~~~~~~~~~~
* The descriptor ring is an array of descriptors. A descriptor contains
* essential meta data to track the data of a printk record using
* blk_lpos structs pointing to associated text data blocks (see
* "Data Rings" below). Each descriptor is assigned an ID that maps
* directly to index values of the descriptor array and has a state. The ID
* and the state are bitwise combined into a single descriptor field named
* @state_var, allowing ID and state to be synchronously and atomically
* updated.
*
* Descriptors have four states:
*
* reserved
* A writer is modifying the record.
*
* committed
* The record and all its data are written. A writer can reopen the
* descriptor (transitioning it back to reserved), but in the committed
* state the data is consistent.
*
* finalized
* The record and all its data are complete and available for reading. A
* writer cannot reopen the descriptor.
*
* reusable
* The record exists, but its text and/or meta data may no longer be
* available.
*
* Querying the @state_var of a record requires providing the ID of the
* descriptor to query. This can yield a possible fifth (pseudo) state:
*
* miss
* The descriptor being queried has an unexpected ID.
*
* The descriptor ring has a @tail_id that contains the ID of the oldest
* descriptor and @head_id that contains the ID of the newest descriptor.
*
* When a new descriptor should be created (and the ring is full), the tail
* descriptor is invalidated by first transitioning to the reusable state and
* then invalidating all tail data blocks up to and including the data blocks
* associated with the tail descriptor (for the text ring). Then
* @tail_id is advanced, followed by advancing @head_id. And finally the
* @state_var of the new descriptor is initialized to the new ID and reserved
* state.
*
* The @tail_id can only be advanced if the new @tail_id would be in the
* committed or reusable queried state. This makes it possible that a valid
* sequence number of the tail is always available.
*
* Descriptor Finalization
* ~~~~~~~~~~~~~~~~~~~~~~~
* When a writer calls the commit function prb_commit(), record data is
* fully stored and is consistent within the ringbuffer. However, a writer can
* reopen that record, claiming exclusive access (as with prb_reserve()), and
* modify that record. When finished, the writer must again commit the record.
*
* In order for a record to be made available to readers (and also become
* recyclable for writers), it must be finalized. A finalized record cannot be
* reopened and can never become "unfinalized". Record finalization can occur
* in three different scenarios:
*
* 1) A writer can simultaneously commit and finalize its record by calling
* prb_final_commit() instead of prb_commit().
*
* 2) When a new record is reserved and the previous record has been
* committed via prb_commit(), that previous record is automatically
* finalized.
*
* 3) When a record is committed via prb_commit() and a newer record
* already exists, the record being committed is automatically finalized.
*
* Data Ring
* ~~~~~~~~~
* The text data ring is a byte array composed of data blocks. Data blocks are
* referenced by blk_lpos structs that point to the logical position of the
* beginning of a data block and the beginning of the next adjacent data
* block. Logical positions are mapped directly to index values of the byte
* array ringbuffer.
*
* Each data block consists of an ID followed by the writer data. The ID is
* the identifier of a descriptor that is associated with the data block. A
* given data block is considered valid if all of the following conditions
* are met:
*
* 1) The descriptor associated with the data block is in the committed
* or finalized queried state.
*
* 2) The blk_lpos struct within the descriptor associated with the data
* block references back to the same data block.
*
* 3) The data block is within the head/tail logical position range.
*
* If the writer data of a data block would extend beyond the end of the
* byte array, only the ID of the data block is stored at the logical
* position and the full data block (ID and writer data) is stored at the
* beginning of the byte array. The referencing blk_lpos will point to the
* ID before the wrap and the next data block will be at the logical
* position adjacent the full data block after the wrap.
*
* Data rings have a @tail_lpos that points to the beginning of the oldest
* data block and a @head_lpos that points to the logical position of the
* next (not yet existing) data block.
*
* When a new data block should be created (and the ring is full), tail data
* blocks will first be invalidated by putting their associated descriptors
* into the reusable state and then pushing the @tail_lpos forward beyond
* them. Then the @head_lpos is pushed forward and is associated with a new
* descriptor. If a data block is not valid, the @tail_lpos cannot be
* advanced beyond it.
*
* Info Array
* ~~~~~~~~~~
* The general meta data of printk records are stored in printk_info structs,
* stored in an array with the same number of elements as the descriptor ring.
* Each info corresponds to the descriptor of the same index in the
* descriptor ring. Info validity is confirmed by evaluating the corresponding
* descriptor before and after loading the info.
*
* Usage
* -----
* Here are some simple examples demonstrating writers and readers. For the
* examples a global ringbuffer (test_rb) is available (which is not the
* actual ringbuffer used by printk)::
*
* DEFINE_PRINTKRB(test_rb, 15, 5);
*
* This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of
* 1 MiB (2 ^ (15 + 5)) for text data.
*
* Sample writer code::
*
* const char *textstr = "message text";
* struct prb_reserved_entry e;
* struct printk_record r;
*
* // specify how much to allocate
* prb_rec_init_wr(&r, strlen(textstr) + 1);
*
* if (prb_reserve(&e, &test_rb, &r)) {
* snprintf(r.text_buf, r.text_buf_size, "%s", textstr);
*
* r.info->text_len = strlen(textstr);
* r.info->ts_nsec = local_clock();
* r.info->caller_id = printk_caller_id();
*
* // commit and finalize the record
* prb_final_commit(&e);
* }
*
* Note that additional writer functions are available to extend a record
* after it has been committed but not yet finalized. This can be done as
* long as no new records have been reserved and the caller is the same.
*
* Sample writer code (record extending)::
*
* // alternate rest of previous example
*
* r.info->text_len = strlen(textstr);
* r.info->ts_nsec = local_clock();
* r.info->caller_id = printk_caller_id();
*
* // commit the record (but do not finalize yet)
* prb_commit(&e);
* }
*
* ...
*
* // specify additional 5 bytes text space to extend
* prb_rec_init_wr(&r, 5);
*
* // try to extend, but only if it does not exceed 32 bytes
* if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) {
* snprintf(&r.text_buf[r.info->text_len],
* r.text_buf_size - r.info->text_len, "hello");
*
* r.info->text_len += 5;
*
* // commit and finalize the record
* prb_final_commit(&e);
* }
*
* Sample reader code::
*
* struct printk_info info;
* struct printk_record r;
* char text_buf[32];
* u64 seq;
*
* prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf));
*
* prb_for_each_record(0, &test_rb, &seq, &r) {
* if (info.seq != seq)
* pr_warn("lost %llu records\n", info.seq - seq);
*
* if (info.text_len > r.text_buf_size) {
* pr_warn("record %llu text truncated\n", info.seq);
* text_buf[r.text_buf_size - 1] = 0;
* }
*
* pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec,
* &text_buf[0]);
* }
*
* Note that additional less convenient reader functions are available to
* allow complex record access.
*
* ABA Issues
* ~~~~~~~~~~
* To help avoid ABA issues, descriptors are referenced by IDs (array index
* values combined with tagged bits counting array wraps) and data blocks are
* referenced by logical positions (array index values combined with tagged
* bits counting array wraps). However, on 32-bit systems the number of
* tagged bits is relatively small such that an ABA incident is (at least
* theoretically) possible. For example, if 4 million maximally sized (1KiB)
* printk messages were to occur in NMI context on a 32-bit system, the
* interrupted context would not be able to recognize that the 32-bit integer
* completely wrapped and thus represents a different data block than the one
* the interrupted context expects.
*
* To help combat this possibility, additional state checking is performed
* (such as using cmpxchg() even though set() would suffice). These extra
* checks are commented as such and will hopefully catch any ABA issue that
* a 32-bit system might experience.
*
* Memory Barriers
* ~~~~~~~~~~~~~~~
* Multiple memory barriers are used. To simplify proving correctness and
* generating litmus tests, lines of code related to memory barriers
* (loads, stores, and the associated memory barriers) are labeled::
*
* LMM(function:letter)
*
* Comments reference the labels using only the "function:letter" part.
*
* The memory barrier pairs and their ordering are:
*
* desc_reserve:D / desc_reserve:B
* push descriptor tail (id), then push descriptor head (id)
*
* desc_reserve:D / data_push_tail:B
* push data tail (lpos), then set new descriptor reserved (state)
*
* desc_reserve:D / desc_push_tail:C
* push descriptor tail (id), then set new descriptor reserved (state)
*
* desc_reserve:D / prb_first_seq:C
* push descriptor tail (id), then set new descriptor reserved (state)
*
* desc_reserve:F / desc_read:D
* set new descriptor id and reserved (state), then allow writer changes
*
* data_alloc:A (or data_realloc:A) / desc_read:D
* set old descriptor reusable (state), then modify new data block area
*
* data_alloc:A (or data_realloc:A) / data_push_tail:B
* push data tail (lpos), then modify new data block area
*
* _prb_commit:B / desc_read:B
* store writer changes, then set new descriptor committed (state)
*
* desc_reopen_last:A / _prb_commit:B
* set descriptor reserved (state), then read descriptor data
*
* _prb_commit:B / desc_reserve:D
* set new descriptor committed (state), then check descriptor head (id)
*
* data_push_tail:D / data_push_tail:A
* set descriptor reusable (state), then push data tail (lpos)
*
* desc_push_tail:B / desc_reserve:D
* set descriptor reusable (state), then push descriptor tail (id)
*
* desc_update_last_finalized:A / desc_last_finalized_seq:A
* store finalized record, then set new highest finalized sequence number
*/
#define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits)
#define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1)
#define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits)
#define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1)
/* Determine the data array index from a logical position. */
#define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring))
/* Determine the desc array index from an ID or sequence number. */
#define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring))
/* Determine how many times the data array has wrapped. */
#define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits)
/* Determine if a logical position refers to a data-less block. */
#define LPOS_DATALESS(lpos) ((lpos) & 1UL)
#define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \
LPOS_DATALESS((blk)->next))
/* Get the logical position at index 0 of the current wrap. */
#define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \
((lpos) & ~DATA_SIZE_MASK(data_ring))
/* Get the ID for the same index of the previous wrap as the given ID. */
#define DESC_ID_PREV_WRAP(desc_ring, id) \
DESC_ID((id) - DESCS_COUNT(desc_ring))
/*
* A data block: mapped directly to the beginning of the data block area
* specified as a logical position within the data ring.
*
* @id: the ID of the associated descriptor
* @data: the writer data
*
* Note that the size of a data block is only known by its associated
* descriptor.
*/
struct prb_data_block {
unsigned long id;
char data[];
};
/*
* Return the descriptor associated with @n. @n can be either a
* descriptor ID or a sequence number.
*/
static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n)
{
return &desc_ring->descs[DESC_INDEX(desc_ring, n)];
}
/*
* Return the printk_info associated with @n. @n can be either a
* descriptor ID or a sequence number.
*/
static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n)
{
return &desc_ring->infos[DESC_INDEX(desc_ring, n)];
}
static struct prb_data_block *to_block(struct prb_data_ring *data_ring,
unsigned long begin_lpos)
{
return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)];
}
/*
* Increase the data size to account for data block meta data plus any
* padding so that the adjacent data block is aligned on the ID size.
*/
static unsigned int to_blk_size(unsigned int size)
{
struct prb_data_block *db = NULL;
size += sizeof(*db);
size = ALIGN(size, sizeof(db->id));
return size;
}
/*
* Sanity checker for reserve size. The ringbuffer code assumes that a data
* block does not exceed the maximum possible size that could fit within the
* ringbuffer. This function provides that basic size check so that the
* assumption is safe.
*/
static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size)
{
struct prb_data_block *db = NULL;
if (size == 0)
return true;
/*
* Ensure the alignment padded size could possibly fit in the data
* array. The largest possible data block must still leave room for
* at least the ID of the next block.
*/
size = to_blk_size(size);
if (size > DATA_SIZE(data_ring) - sizeof(db->id))
return false;
return true;
}
/* Query the state of a descriptor. */
static enum desc_state get_desc_state(unsigned long id,
unsigned long state_val)
{
if (id != DESC_ID(state_val))
return desc_miss;
return DESC_STATE(state_val);
}
/*
* Get a copy of a specified descriptor and return its queried state. If the
* descriptor is in an inconsistent state (miss or reserved), the caller can
* only expect the descriptor's @state_var field to be valid.
*
* The sequence number and caller_id can be optionally retrieved. Like all
* non-state_var data, they are only valid if the descriptor is in a
* consistent state.
*/
static enum desc_state desc_read(struct prb_desc_ring *desc_ring,
unsigned long id, struct prb_desc *desc_out,
u64 *seq_out, u32 *caller_id_out)
{
struct printk_info *info = to_info(desc_ring, id);
struct prb_desc *desc = to_desc(desc_ring, id);
atomic_long_t *state_var = &desc->state_var;
enum desc_state d_state;
unsigned long state_val;
/* Check the descriptor state. */
state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */
d_state = get_desc_state(id, state_val);
if (d_state == desc_miss || d_state == desc_reserved) {
/*
* The descriptor is in an inconsistent state. Set at least
* @state_var so that the caller can see the details of
* the inconsistent state.
*/
goto out;
}
/*
* Guarantee the state is loaded before copying the descriptor
* content. This avoids copying obsolete descriptor content that might
* not apply to the descriptor state. This pairs with _prb_commit:B.
*
* Memory barrier involvement:
*
* If desc_read:A reads from _prb_commit:B, then desc_read:C reads
* from _prb_commit:A.
*
* Relies on:
*
* WMB from _prb_commit:A to _prb_commit:B
* matching
* RMB from desc_read:A to desc_read:C
*/
smp_rmb(); /* LMM(desc_read:B) */
/*
* Copy the descriptor data. The data is not valid until the
* state has been re-checked. A memcpy() for all of @desc
* cannot be used because of the atomic_t @state_var field.
*/
if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos,
sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */
}
if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */
/*
* 1. Guarantee the descriptor content is loaded before re-checking
* the state. This avoids reading an obsolete descriptor state
* that may not apply to the copied content. This pairs with
* desc_reserve:F.
*
* Memory barrier involvement:
*
* If desc_read:C reads from desc_reserve:G, then desc_read:E
* reads from desc_reserve:F.
*
* Relies on:
*
* WMB from desc_reserve:F to desc_reserve:G
* matching
* RMB from desc_read:C to desc_read:E
*
* 2. Guarantee the record data is loaded before re-checking the
* state. This avoids reading an obsolete descriptor state that may
* not apply to the copied data. This pairs with data_alloc:A and
* data_realloc:A.
*
* Memory barrier involvement:
*
* If copy_data:A reads from data_alloc:B, then desc_read:E
* reads from desc_make_reusable:A.
*
* Relies on:
*
* MB from desc_make_reusable:A to data_alloc:B
* matching
* RMB from desc_read:C to desc_read:E
*
* Note: desc_make_reusable:A and data_alloc:B can be different
* CPUs. However, the data_alloc:B CPU (which performs the
* full memory barrier) must have previously seen
* desc_make_reusable:A.
*/
smp_rmb(); /* LMM(desc_read:D) */
/*
* The data has been copied. Return the current descriptor state,
* which may have changed since the load above.
*/
state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */
d_state = get_desc_state(id, state_val);
out:
if (desc_out) atomic_long_set(&desc_out->state_var, state_val);
return d_state;
}
/*
* Take a specified descriptor out of the finalized state by attempting
* the transition from finalized to reusable. Either this context or some
* other context will have been successful.
*/
static void desc_make_reusable(struct prb_desc_ring *desc_ring,
unsigned long id)
{
unsigned long val_finalized = DESC_SV(id, desc_finalized);
unsigned long val_reusable = DESC_SV(id, desc_reusable);
struct prb_desc *desc = to_desc(desc_ring, id);
atomic_long_t *state_var = &desc->state_var;
atomic_long_cmpxchg_relaxed(state_var, val_finalized,
val_reusable); /* LMM(desc_make_reusable:A) */
}
/*
* Given the text data ring, put the associated descriptor of each
* data block from @lpos_begin until @lpos_end into the reusable state.
*
* If there is any problem making the associated descriptor reusable, either
* the descriptor has not yet been finalized or another writer context has
* already pushed the tail lpos past the problematic data block. Regardless,
* on error the caller can re-load the tail lpos to determine the situation.
*/
static bool data_make_reusable(struct printk_ringbuffer *rb,
unsigned long lpos_begin,
unsigned long lpos_end,
unsigned long *lpos_out)
{
struct prb_data_ring *data_ring = &rb->text_data_ring;
struct prb_desc_ring *desc_ring = &rb->desc_ring;
struct prb_data_block *blk;
enum desc_state d_state;
struct prb_desc desc;
struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos;
unsigned long id;
/* Loop until @lpos_begin has advanced to or beyond @lpos_end. */
while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) {
blk = to_block(data_ring, lpos_begin);
/*
* Load the block ID from the data block. This is a data race
* against a writer that may have newly reserved this data
* area. If the loaded value matches a valid descriptor ID,
* the blk_lpos of that descriptor will be checked to make
* sure it points back to this data block. If the check fails,
* the data area has been recycled by another writer.
*/
id = blk->id; /* LMM(data_make_reusable:A) */
d_state = desc_read(desc_ring, id, &desc,
NULL, NULL); /* LMM(data_make_reusable:B) */
switch (d_state) {
case desc_miss:
case desc_reserved:
case desc_committed:
return false;
case desc_finalized:
/*
* This data block is invalid if the descriptor
* does not point back to it.
*/
if (blk_lpos->begin != lpos_begin)
return false;
desc_make_reusable(desc_ring, id);
break;
case desc_reusable:
/*
* This data block is invalid if the descriptor
* does not point back to it.
*/
if (blk_lpos->begin != lpos_begin)
return false;
break;
}
/* Advance @lpos_begin to the next data block. */
lpos_begin = blk_lpos->next;
}
*lpos_out = lpos_begin;
return true;
}
/*
* Advance the data ring tail to at least @lpos. This function puts
* descriptors into the reusable state if the tail is pushed beyond
* their associated data block.
*/
static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos)
{
struct prb_data_ring *data_ring = &rb->text_data_ring;
unsigned long tail_lpos_new;
unsigned long tail_lpos;
unsigned long next_lpos;
/* If @lpos is from a data-less block, there is nothing to do. */
if (LPOS_DATALESS(lpos))
return true;
/*
* Any descriptor states that have transitioned to reusable due to the
* data tail being pushed to this loaded value will be visible to this
* CPU. This pairs with data_push_tail:D.
*
* Memory barrier involvement:
*
* If data_push_tail:A reads from data_push_tail:D, then this CPU can
* see desc_make_reusable:A.
*
* Relies on:
*
* MB from desc_make_reusable:A to data_push_tail:D
* matches
* READFROM from data_push_tail:D to data_push_tail:A
* thus
* READFROM from desc_make_reusable:A to this CPU
*/
tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */
/*
* Loop until the tail lpos is at or beyond @lpos. This condition
* may already be satisfied, resulting in no full memory barrier
* from data_push_tail:D being performed. However, since this CPU
* sees the new tail lpos, any descriptor states that transitioned to
* the reusable state must already be visible.
*/
while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) {
/*
* Make all descriptors reusable that are associated with
* data blocks before @lpos.
*/
if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) {
/*
* 1. Guarantee the block ID loaded in
* data_make_reusable() is performed before
* reloading the tail lpos. The failed
* data_make_reusable() may be due to a newly
* recycled data area causing the tail lpos to
* have been previously pushed. This pairs with
* data_alloc:A and data_realloc:A.
*
* Memory barrier involvement:
*
* If data_make_reusable:A reads from data_alloc:B,
* then data_push_tail:C reads from
* data_push_tail:D.
*
* Relies on:
*
* MB from data_push_tail:D to data_alloc:B
* matching
* RMB from data_make_reusable:A to
* data_push_tail:C
*
* Note: data_push_tail:D and data_alloc:B can be
* different CPUs. However, the data_alloc:B
* CPU (which performs the full memory
* barrier) must have previously seen
* data_push_tail:D.
*
* 2. Guarantee the descriptor state loaded in
* data_make_reusable() is performed before
* reloading the tail lpos. The failed
* data_make_reusable() may be due to a newly
* recycled descriptor causing the tail lpos to
* have been previously pushed. This pairs with
* desc_reserve:D.
*
* Memory barrier involvement:
*
* If data_make_reusable:B reads from
* desc_reserve:F, then data_push_tail:C reads
* from data_push_tail:D.
*
* Relies on:
*
* MB from data_push_tail:D to desc_reserve:F
* matching
* RMB from data_make_reusable:B to
* data_push_tail:C
*
* Note: data_push_tail:D and desc_reserve:F can
* be different CPUs. However, the
* desc_reserve:F CPU (which performs the
* full memory barrier) must have previously
* seen data_push_tail:D.
*/
smp_rmb(); /* LMM(data_push_tail:B) */
tail_lpos_new = atomic_long_read(&data_ring->tail_lpos
); /* LMM(data_push_tail:C) */
if (tail_lpos_new == tail_lpos)
return false;
/* Another CPU pushed the tail. Try again. */
tail_lpos = tail_lpos_new;
continue;
}
/*
* Guarantee any descriptor states that have transitioned to
* reusable are stored before pushing the tail lpos. A full
* memory barrier is needed since other CPUs may have made
* the descriptor states reusable. This pairs with
* data_push_tail:A.
*/
if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos,
next_lpos)) { /* LMM(data_push_tail:D) */
break;
}
}
return true;
}
/*
* Advance the desc ring tail. This function advances the tail by one
* descriptor, thus invalidating the oldest descriptor. Before advancing
* the tail, the tail descriptor is made reusable and all data blocks up to
* and including the descriptor's data block are invalidated (i.e. the data
* ring tail is pushed past the data block of the descriptor being made
* reusable).
*/
static bool desc_push_tail(struct printk_ringbuffer *rb,
unsigned long tail_id)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
enum desc_state d_state;
struct prb_desc desc;
d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL);
switch (d_state) {
case desc_miss:
/*
* If the ID is exactly 1 wrap behind the expected, it is
* in the process of being reserved by another writer and
* must be considered reserved.
*/
if (DESC_ID(atomic_long_read(&desc.state_var)) ==
DESC_ID_PREV_WRAP(desc_ring, tail_id)) {
return false;
}
/*
* The ID has changed. Another writer must have pushed the
* tail and recycled the descriptor already. Success is
* returned because the caller is only interested in the
* specified tail being pushed, which it was.
*/
return true;
case desc_reserved:
case desc_committed:
return false;
case desc_finalized:
desc_make_reusable(desc_ring, tail_id);
break;
case desc_reusable:
break;
}
/*
* Data blocks must be invalidated before their associated
* descriptor can be made available for recycling. Invalidating
* them later is not possible because there is no way to trust
* data blocks once their associated descriptor is gone.
*/
if (!data_push_tail(rb, desc.text_blk_lpos.next))
return false;
/*
* Check the next descriptor after @tail_id before pushing the tail
* to it because the tail must always be in a finalized or reusable
* state. The implementation of prb_first_seq() relies on this.
*
* A successful read implies that the next descriptor is less than or
* equal to @head_id so there is no risk of pushing the tail past the
* head.
*/
d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc,
NULL, NULL); /* LMM(desc_push_tail:A) */
if (d_state == desc_finalized || d_state == desc_reusable) {
/*
* Guarantee any descriptor states that have transitioned to
* reusable are stored before pushing the tail ID. This allows
* verifying the recycled descriptor state. A full memory
* barrier is needed since other CPUs may have made the
* descriptor states reusable. This pairs with desc_reserve:D.
*/
atomic_long_cmpxchg(&desc_ring->tail_id, tail_id,
DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */
} else {
/*
* Guarantee the last state load from desc_read() is before
* reloading @tail_id in order to see a new tail ID in the
* case that the descriptor has been recycled. This pairs
* with desc_reserve:D.
*
* Memory barrier involvement:
*
* If desc_push_tail:A reads from desc_reserve:F, then
* desc_push_tail:D reads from desc_push_tail:B.
*
* Relies on:
*
* MB from desc_push_tail:B to desc_reserve:F
* matching
* RMB from desc_push_tail:A to desc_push_tail:D
*
* Note: desc_push_tail:B and desc_reserve:F can be different
* CPUs. However, the desc_reserve:F CPU (which performs
* the full memory barrier) must have previously seen
* desc_push_tail:B.
*/
smp_rmb(); /* LMM(desc_push_tail:C) */
/*
* Re-check the tail ID. The descriptor following @tail_id is
* not in an allowed tail state. But if the tail has since
* been moved by another CPU, then it does not matter.
*/
if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */
return false;
}
return true;
}
/* Reserve a new descriptor, invalidating the oldest if necessary. */
static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
unsigned long prev_state_val;
unsigned long id_prev_wrap;
struct prb_desc *desc;
unsigned long head_id;
unsigned long id;
head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */
do {
id = DESC_ID(head_id + 1);
id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id);
/*
* Guarantee the head ID is read before reading the tail ID.
* Since the tail ID is updated before the head ID, this
* guarantees that @id_prev_wrap is never ahead of the tail
* ID. This pairs with desc_reserve:D.
*
* Memory barrier involvement:
*
* If desc_reserve:A reads from desc_reserve:D, then
* desc_reserve:C reads from desc_push_tail:B.
*
* Relies on:
*
* MB from desc_push_tail:B to desc_reserve:D
* matching
* RMB from desc_reserve:A to desc_reserve:C
*
* Note: desc_push_tail:B and desc_reserve:D can be different
* CPUs. However, the desc_reserve:D CPU (which performs
* the full memory barrier) must have previously seen
* desc_push_tail:B.
*/
smp_rmb(); /* LMM(desc_reserve:B) */
if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id
)) { /* LMM(desc_reserve:C) */
/*
* Make space for the new descriptor by
* advancing the tail.
*/
if (!desc_push_tail(rb, id_prev_wrap))
return false;
}
/*
* 1. Guarantee the tail ID is read before validating the
* recycled descriptor state. A read memory barrier is
* sufficient for this. This pairs with desc_push_tail:B.
*
* Memory barrier involvement:
*
* If desc_reserve:C reads from desc_push_tail:B, then
* desc_reserve:E reads from desc_make_reusable:A.
*
* Relies on:
*
* MB from desc_make_reusable:A to desc_push_tail:B
* matching
* RMB from desc_reserve:C to desc_reserve:E
*
* Note: desc_make_reusable:A and desc_push_tail:B can be
* different CPUs. However, the desc_push_tail:B CPU
* (which performs the full memory barrier) must have
* previously seen desc_make_reusable:A.
*
* 2. Guarantee the tail ID is stored before storing the head
* ID. This pairs with desc_reserve:B.
*
* 3. Guarantee any data ring tail changes are stored before
* recycling the descriptor. Data ring tail changes can
* happen via desc_push_tail()->data_push_tail(). A full
* memory barrier is needed since another CPU may have
* pushed the data ring tails. This pairs with
* data_push_tail:B.
*
* 4. Guarantee a new tail ID is stored before recycling the
* descriptor. A full memory barrier is needed since
* another CPU may have pushed the tail ID. This pairs
* with desc_push_tail:C and this also pairs with
* prb_first_seq:C.
*
* 5. Guarantee the head ID is stored before trying to
* finalize the previous descriptor. This pairs with
* _prb_commit:B.
*/
} while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id,
id)); /* LMM(desc_reserve:D) */
desc = to_desc(desc_ring, id);
/*
* If the descriptor has been recycled, verify the old state val.
* See "ABA Issues" about why this verification is performed.
*/
prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */
if (prev_state_val &&
get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) {
WARN_ON_ONCE(1);
return false;
}
/*
* Assign the descriptor a new ID and set its state to reserved.
* See "ABA Issues" about why cmpxchg() instead of set() is used.
*
* Guarantee the new descriptor ID and state is stored before making
* any other changes. A write memory barrier is sufficient for this.
* This pairs with desc_read:D.
*/
if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val,
DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */
WARN_ON_ONCE(1);
return false;
}
/* Now data in @desc can be modified: LMM(desc_reserve:G) */
*id_out = id;
return true;
}
/* Determine the end of a data block. */
static unsigned long get_next_lpos(struct prb_data_ring *data_ring,
unsigned long lpos, unsigned int size)
{
unsigned long begin_lpos;
unsigned long next_lpos;
begin_lpos = lpos;
next_lpos = lpos + size;
/* First check if the data block does not wrap. */
if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos))
return next_lpos;
/* Wrapping data blocks store their data at the beginning. */
return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size);
}
/*
* Allocate a new data block, invalidating the oldest data block(s)
* if necessary. This function also associates the data block with
* a specified descriptor.
*/
static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size,
struct prb_data_blk_lpos *blk_lpos, unsigned long id)
{
struct prb_data_ring *data_ring = &rb->text_data_ring;
struct prb_data_block *blk;
unsigned long begin_lpos;
unsigned long next_lpos;
if (size == 0) {
/*
* Data blocks are not created for empty lines. Instead, the
* reader will recognize these special lpos values and handle
* it appropriately.
*/
blk_lpos->begin = EMPTY_LINE_LPOS;
blk_lpos->next = EMPTY_LINE_LPOS;
return NULL;
}
size = to_blk_size(size);
begin_lpos = atomic_long_read(&data_ring->head_lpos);
do {
next_lpos = get_next_lpos(data_ring, begin_lpos, size);
if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) {
/* Failed to allocate, specify a data-less block. */
blk_lpos->begin = FAILED_LPOS;
blk_lpos->next = FAILED_LPOS;
return NULL;
}
/*
* 1. Guarantee any descriptor states that have transitioned
* to reusable are stored before modifying the newly
* allocated data area. A full memory barrier is needed
* since other CPUs may have made the descriptor states
* reusable. See data_push_tail:A about why the reusable
* states are visible. This pairs with desc_read:D.
*
* 2. Guarantee any updated tail lpos is stored before
* modifying the newly allocated data area. Another CPU may
* be in data_make_reusable() and is reading a block ID
* from this area. data_make_reusable() can handle reading
* a garbage block ID value, but then it must be able to
* load a new tail lpos. A full memory barrier is needed
* since other CPUs may have updated the tail lpos. This
* pairs with data_push_tail:B.
*/
} while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos,
next_lpos)); /* LMM(data_alloc:A) */
blk = to_block(data_ring, begin_lpos);
blk->id = id; /* LMM(data_alloc:B) */
if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) {
/* Wrapping data blocks store their data at the beginning. */
blk = to_block(data_ring, 0);
/*
* Store the ID on the wrapped block for consistency.
* The printk_ringbuffer does not actually use it.
*/
blk->id = id;
}
blk_lpos->begin = begin_lpos;
blk_lpos->next = next_lpos;
return &blk->data[0];
}
/*
* Try to resize an existing data block associated with the descriptor
* specified by @id. If the resized data block should become wrapped, it
* copies the old data to the new data block. If @size yields a data block
* with the same or less size, the data block is left as is.
*
* Fail if this is not the last allocated data block or if there is not
* enough space or it is not possible make enough space.
*
* Return a pointer to the beginning of the entire data buffer or NULL on
* failure.
*/
static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size,
struct prb_data_blk_lpos *blk_lpos, unsigned long id)
{
struct prb_data_ring *data_ring = &rb->text_data_ring;
struct prb_data_block *blk;
unsigned long head_lpos;
unsigned long next_lpos;
bool wrapped;
/* Reallocation only works if @blk_lpos is the newest data block. */
head_lpos = atomic_long_read(&data_ring->head_lpos);
if (head_lpos != blk_lpos->next)
return NULL;
/* Keep track if @blk_lpos was a wrapping data block. */
wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next));
size = to_blk_size(size);
next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size);
/* If the data block does not increase, there is nothing to do. */
if (head_lpos - next_lpos < DATA_SIZE(data_ring)) {
if (wrapped)
blk = to_block(data_ring, 0);
else
blk = to_block(data_ring, blk_lpos->begin);
return &blk->data[0];
}
if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring)))
return NULL;
/* The memory barrier involvement is the same as data_alloc:A. */
if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos,
next_lpos)) { /* LMM(data_realloc:A) */
return NULL;
}
blk = to_block(data_ring, blk_lpos->begin);
if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) {
struct prb_data_block *old_blk = blk;
/* Wrapping data blocks store their data at the beginning. */
blk = to_block(data_ring, 0);
/*
* Store the ID on the wrapped block for consistency.
* The printk_ringbuffer does not actually use it.
*/
blk->id = id;
if (!wrapped) {
/*
* Since the allocated space is now in the newly
* created wrapping data block, copy the content
* from the old data block.
*/
memcpy(&blk->data[0], &old_blk->data[0],
(blk_lpos->next - blk_lpos->begin) - sizeof(blk->id));
}
}
blk_lpos->next = next_lpos;
return &blk->data[0];
}
/* Return the number of bytes used by a data block. */
static unsigned int space_used(struct prb_data_ring *data_ring,
struct prb_data_blk_lpos *blk_lpos)
{
/* Data-less blocks take no space. */
if (BLK_DATALESS(blk_lpos))
return 0;
if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) {
/* Data block does not wrap. */
return (DATA_INDEX(data_ring, blk_lpos->next) -
DATA_INDEX(data_ring, blk_lpos->begin));
}
/*
* For wrapping data blocks, the trailing (wasted) space is
* also counted.
*/
return (DATA_INDEX(data_ring, blk_lpos->next) +
DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin));
}
/*
* Given @blk_lpos, return a pointer to the writer data from the data block
* and calculate the size of the data part. A NULL pointer is returned if
* @blk_lpos specifies values that could never be legal.
*
* This function (used by readers) performs strict validation on the lpos
* values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is
* triggered if an internal error is detected.
*/
static const char *get_data(struct prb_data_ring *data_ring,
struct prb_data_blk_lpos *blk_lpos,
unsigned int *data_size)
{
struct prb_data_block *db;
/* Data-less data block description. */
if (BLK_DATALESS(blk_lpos)) {
/*
* Records that are just empty lines are also valid, even
* though they do not have a data block. For such records
* explicitly return empty string data to signify success.
*/
if (blk_lpos->begin == EMPTY_LINE_LPOS &&
blk_lpos->next == EMPTY_LINE_LPOS) {
*data_size = 0;
return "";
}
/* Data lost, invalid, or otherwise unavailable. */
return NULL;
}
/* Regular data block: @begin less than @next and in same wrap. */
if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) &&
blk_lpos->begin < blk_lpos->next) {
db = to_block(data_ring, blk_lpos->begin);
*data_size = blk_lpos->next - blk_lpos->begin;
/* Wrapping data block: @begin is one wrap behind @next. */
} else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) ==
DATA_WRAPS(data_ring, blk_lpos->next)) {
db = to_block(data_ring, 0);
*data_size = DATA_INDEX(data_ring, blk_lpos->next);
/* Illegal block description. */
} else {
WARN_ON_ONCE(1);
return NULL;
}
/* A valid data block will always be aligned to the ID size. */
if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) {
return NULL;
}
/* A valid data block will always have at least an ID. */
if (WARN_ON_ONCE(*data_size < sizeof(db->id)))
return NULL;
/* Subtract block ID space from size to reflect data size. */
*data_size -= sizeof(db->id);
return &db->data[0];
}
/*
* Attempt to transition the newest descriptor from committed back to reserved
* so that the record can be modified by a writer again. This is only possible
* if the descriptor is not yet finalized and the provided @caller_id matches.
*/
static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring,
u32 caller_id, unsigned long *id_out)
{
unsigned long prev_state_val;
enum desc_state d_state;
struct prb_desc desc;
struct prb_desc *d;
unsigned long id;
u32 cid;
id = atomic_long_read(&desc_ring->head_id);
/*
* To reduce unnecessarily reopening, first check if the descriptor
* state and caller ID are correct.
*/
d_state = desc_read(desc_ring, id, &desc, NULL, &cid);
if (d_state != desc_committed || cid != caller_id)
return NULL;
d = to_desc(desc_ring, id);
prev_state_val = DESC_SV(id, desc_committed);
/*
* Guarantee the reserved state is stored before reading any
* record data. A full memory barrier is needed because @state_var
* modification is followed by reading. This pairs with _prb_commit:B.
*
* Memory barrier involvement:
*
* If desc_reopen_last:A reads from _prb_commit:B, then
* prb_reserve_in_last:A reads from _prb_commit:A.
*
* Relies on:
*
* WMB from _prb_commit:A to _prb_commit:B
* matching
* MB If desc_reopen_last:A to prb_reserve_in_last:A
*/
if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val,
DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */
return NULL;
}
*id_out = id;
return d;
}
/**
* prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer
* used by the newest record.
*
* @e: The entry structure to setup.
* @rb: The ringbuffer to re-reserve and extend data in.
* @r: The record structure to allocate buffers for.
* @caller_id: The caller ID of the caller (reserving writer).
* @max_size: Fail if the extended size would be greater than this.
*
* This is the public function available to writers to re-reserve and extend
* data.
*
* The writer specifies the text size to extend (not the new total size) by
* setting the @text_buf_size field of @r. To ensure proper initialization
* of @r, prb_rec_init_wr() should be used.
*
* This function will fail if @caller_id does not match the caller ID of the
* newest record. In that case the caller must reserve new data using
* prb_reserve().
*
* Context: Any context. Disables local interrupts on success.
* Return: true if text data could be extended, otherwise false.
*
* On success:
*
* - @r->text_buf points to the beginning of the entire text buffer.
*
* - @r->text_buf_size is set to the new total size of the buffer.
*
* - @r->info is not touched so that @r->info->text_len could be used
* to append the text.
*
* - prb_record_text_space() can be used on @e to query the new
* actually used space.
*
* Important: All @r->info fields will already be set with the current values
* for the record. I.e. @r->info->text_len will be less than
* @text_buf_size. Writers can use @r->info->text_len to know
* where concatenation begins and writers should update
* @r->info->text_len after concatenating.
*/
bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb,
struct printk_record *r, u32 caller_id, unsigned int max_size)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
struct printk_info *info;
unsigned int data_size;
struct prb_desc *d;
unsigned long id;
local_irq_save(e->irqflags);
/* Transition the newest descriptor back to the reserved state. */
d = desc_reopen_last(desc_ring, caller_id, &id);
if (!d) {
local_irq_restore(e->irqflags);
goto fail_reopen;
}
/* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */
info = to_info(desc_ring, id);
/*
* Set the @e fields here so that prb_commit() can be used if
* anything fails from now on.
*/
e->rb = rb;
e->id = id;
/*
* desc_reopen_last() checked the caller_id, but there was no
* exclusive access at that point. The descriptor may have
* changed since then.
*/
if (caller_id != info->caller_id)
goto fail;
if (BLK_DATALESS(&d->text_blk_lpos)) {
if (WARN_ON_ONCE(info->text_len != 0)) {
pr_warn_once("wrong text_len value (%hu, expecting 0)\n",
info->text_len);
info->text_len = 0;
}
if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
goto fail;
if (r->text_buf_size > max_size)
goto fail;
r->text_buf = data_alloc(rb, r->text_buf_size,
&d->text_blk_lpos, id);
} else {
if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size))
goto fail;
/*
* Increase the buffer size to include the original size. If
* the meta data (@text_len) is not sane, use the full data
* block size.
*/
if (WARN_ON_ONCE(info->text_len > data_size)) {
pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n",
info->text_len, data_size);
info->text_len = data_size;
}
r->text_buf_size += info->text_len;
if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
goto fail;
if (r->text_buf_size > max_size)
goto fail;
r->text_buf = data_realloc(rb, r->text_buf_size,
&d->text_blk_lpos, id);
}
if (r->text_buf_size && !r->text_buf)
goto fail;
r->info = info;
e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);
return true;
fail:
prb_commit(e);
/* prb_commit() re-enabled interrupts. */
fail_reopen:
/* Make it clear to the caller that the re-reserve failed. */
memset(r, 0, sizeof(*r));
return false;
}
/*
* @last_finalized_seq value guarantees that all records up to and including
* this sequence number are finalized and can be read. The only exception are
* too old records which have already been overwritten.
*
* It is also guaranteed that @last_finalized_seq only increases.
*
* Be aware that finalized records following non-finalized records are not
* reported because they are not yet available to the reader. For example,
* a new record stored via printk() will not be available to a printer if
* it follows a record that has not been finalized yet. However, once that
* non-finalized record becomes finalized, @last_finalized_seq will be
* appropriately updated and the full set of finalized records will be
* available to the printer. And since each printk() caller will either
* directly print or trigger deferred printing of all available unprinted
* records, all printk() messages will get printed.
*/
static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
unsigned long ulseq;
/*
* Guarantee the sequence number is loaded before loading the
* associated record in order to guarantee that the record can be
* seen by this CPU. This pairs with desc_update_last_finalized:A.
*/
ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq
); /* LMM(desc_last_finalized_seq:A) */
return __ulseq_to_u64seq(rb, ulseq);
}
static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
struct printk_record *r, unsigned int *line_count);
/*
* Check if there are records directly following @last_finalized_seq that are
* finalized. If so, update @last_finalized_seq to the latest of these
* records. It is not allowed to skip over records that are not yet finalized.
*/
static void desc_update_last_finalized(struct printk_ringbuffer *rb)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
u64 old_seq = desc_last_finalized_seq(rb);
unsigned long oldval;
unsigned long newval;
u64 finalized_seq;
u64 try_seq;
try_again:
finalized_seq = old_seq;
try_seq = finalized_seq + 1;
/* Try to find later finalized records. */
while (_prb_read_valid(rb, &try_seq, NULL, NULL)) {
finalized_seq = try_seq;
try_seq++;
}
/* No update needed if no later finalized record was found. */
if (finalized_seq == old_seq)
return;
oldval = __u64seq_to_ulseq(old_seq);
newval = __u64seq_to_ulseq(finalized_seq);
/*
* Set the sequence number of a later finalized record that has been
* seen.
*
* Guarantee the record data is visible to other CPUs before storing
* its sequence number. This pairs with desc_last_finalized_seq:A.
*
* Memory barrier involvement:
*
* If desc_last_finalized_seq:A reads from
* desc_update_last_finalized:A, then desc_read:A reads from
* _prb_commit:B.
*
* Relies on:
*
* RELEASE from _prb_commit:B to desc_update_last_finalized:A
* matching
* ACQUIRE from desc_last_finalized_seq:A to desc_read:A
*
* Note: _prb_commit:B and desc_update_last_finalized:A can be
* different CPUs. However, the desc_update_last_finalized:A
* CPU (which performs the release) must have previously seen
* _prb_commit:B.
*/
if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq,
&oldval, newval)) { /* LMM(desc_update_last_finalized:A) */
old_seq = __ulseq_to_u64seq(rb, oldval);
goto try_again;
}
}
/*
* Attempt to finalize a specified descriptor. If this fails, the descriptor
* is either already final or it will finalize itself when the writer commits.
*/
static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
unsigned long prev_state_val = DESC_SV(id, desc_committed);
struct prb_desc *d = to_desc(desc_ring, id);
if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val,
DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */
desc_update_last_finalized(rb);
}
}
/**
* prb_reserve() - Reserve space in the ringbuffer.
*
* @e: The entry structure to setup.
* @rb: The ringbuffer to reserve data in.
* @r: The record structure to allocate buffers for.
*
* This is the public function available to writers to reserve data.
*
* The writer specifies the text size to reserve by setting the
* @text_buf_size field of @r. To ensure proper initialization of @r,
* prb_rec_init_wr() should be used.
*
* Context: Any context. Disables local interrupts on success.
* Return: true if at least text data could be allocated, otherwise false.
*
* On success, the fields @info and @text_buf of @r will be set by this
* function and should be filled in by the writer before committing. Also
* on success, prb_record_text_space() can be used on @e to query the actual
* space used for the text data block.
*
* Important: @info->text_len needs to be set correctly by the writer in
* order for data to be readable and/or extended. Its value
* is initialized to 0.
*/
bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb,
struct printk_record *r)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
struct printk_info *info;
struct prb_desc *d;
unsigned long id;
u64 seq;
if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
goto fail;
/*
* Descriptors in the reserved state act as blockers to all further
* reservations once the desc_ring has fully wrapped. Disable
* interrupts during the reserve/commit window in order to minimize
* the likelihood of this happening.
*/
local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) {
/* Descriptor reservation failures are tracked. */
atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags);
goto fail;
}
d = to_desc(desc_ring, id);
info = to_info(desc_ring, id);
/*
* All @info fields (except @seq) are cleared and must be filled in
* by the writer. Save @seq before clearing because it is used to
* determine the new sequence number.
*/
seq = info->seq;
memset(info, 0, sizeof(*info));
/*
* Set the @e fields here so that prb_commit() can be used if
* text data allocation fails.
*/
e->rb = rb;
e->id = id;
/*
* Initialize the sequence number if it has "never been set".
* Otherwise just increment it by a full wrap.
*
* @seq is considered "never been set" if it has a value of 0,
* _except_ for @infos[0], which was specially setup by the ringbuffer
* initializer and therefore is always considered as set.
*
* See the "Bootstrap" comment block in printk_ringbuffer.h for
* details about how the initializer bootstraps the descriptors.
*/
if (seq == 0 && DESC_INDEX(desc_ring, id) != 0)
info->seq = DESC_INDEX(desc_ring, id);
else
info->seq = seq + DESCS_COUNT(desc_ring);
/*
* New data is about to be reserved. Once that happens, previous
* descriptors are no longer able to be extended. Finalize the
* previous descriptor now so that it can be made available to
* readers. (For seq==0 there is no previous descriptor.)
*/
if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1));
r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id);
/* If text data allocation fails, a data-less record is committed. */
if (r->text_buf_size && !r->text_buf) {
prb_commit(e);
/* prb_commit() re-enabled interrupts. */
goto fail;
}
r->info = info;
/* Record full text space used by record. */
e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);
return true;
fail:
/* Make it clear to the caller that the reserve failed. */
memset(r, 0, sizeof(*r));
return false;
}
/* Commit the data (possibly finalizing it) and restore interrupts. */
static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val)
{
struct prb_desc_ring *desc_ring = &e->rb->desc_ring;
struct prb_desc *d = to_desc(desc_ring, e->id);
unsigned long prev_state_val = DESC_SV(e->id, desc_reserved);
/* Now the writer has finished all writing: LMM(_prb_commit:A) */
/*
* Set the descriptor as committed. See "ABA Issues" about why
* cmpxchg() instead of set() is used.
*
* 1 Guarantee all record data is stored before the descriptor state
* is stored as committed. A write memory barrier is sufficient
* for this. This pairs with desc_read:B and desc_reopen_last:A.
*
* 2. Guarantee the descriptor state is stored as committed before
* re-checking the head ID in order to possibly finalize this
* descriptor. This pairs with desc_reserve:D.
*
* Memory barrier involvement:
*
* If prb_commit:A reads from desc_reserve:D, then
* desc_make_final:A reads from _prb_commit:B.
*
* Relies on:
*
* MB _prb_commit:B to prb_commit:A
* matching
* MB desc_reserve:D to desc_make_final:A
*/
if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val,
DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */
WARN_ON_ONCE(1);
}
/* Restore interrupts, the reserve/commit window is finished. */
local_irq_restore(e->irqflags);
}
/**
* prb_commit() - Commit (previously reserved) data to the ringbuffer.
*
* @e: The entry containing the reserved data information.
*
* This is the public function available to writers to commit data.
*
* Note that the data is not yet available to readers until it is finalized.
* Finalizing happens automatically when space for the next record is
* reserved.
*
* See prb_final_commit() for a version of this function that finalizes
* immediately.
*
* Context: Any context. Enables local interrupts.
*/
void prb_commit(struct prb_reserved_entry *e)
{
struct prb_desc_ring *desc_ring = &e->rb->desc_ring;
unsigned long head_id;
_prb_commit(e, desc_committed);
/*
* If this descriptor is no longer the head (i.e. a new record has
* been allocated), extending the data for this record is no longer
* allowed and therefore it must be finalized.
*/
head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */
if (head_id != e->id)
desc_make_final(e->rb, e->id);
}
/**
* prb_final_commit() - Commit and finalize (previously reserved) data to
* the ringbuffer.
*
* @e: The entry containing the reserved data information.
*
* This is the public function available to writers to commit+finalize data.
*
* By finalizing, the data is made immediately available to readers.
*
* This function should only be used if there are no intentions of extending
* this data using prb_reserve_in_last().
*
* Context: Any context. Enables local interrupts.
*/
void prb_final_commit(struct prb_reserved_entry *e)
{
_prb_commit(e, desc_finalized);
desc_update_last_finalized(e->rb);
}
/*
* Count the number of lines in provided text. All text has at least 1 line
* (even if @text_size is 0). Each '\n' processed is counted as an additional
* line.
*/
static unsigned int count_lines(const char *text, unsigned int text_size)
{
unsigned int next_size = text_size;
unsigned int line_count = 1;
const char *next = text;
while (next_size) {
next = memchr(next, '\n', next_size);
if (!next)
break;
line_count++;
next++;
next_size = text_size - (next - text);
}
return line_count;
}
/*
* Given @blk_lpos, copy an expected @len of data into the provided buffer.
* If @line_count is provided, count the number of lines in the data.
*
* This function (used by readers) performs strict validation on the data
* size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is
* triggered if an internal error is detected.
*/
static bool copy_data(struct prb_data_ring *data_ring,
struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf,
unsigned int buf_size, unsigned int *line_count)
{
unsigned int data_size;
const char *data;
/* Caller might not want any data. */
if ((!buf || !buf_size) && !line_count)
return true;
data = get_data(data_ring, blk_lpos, &data_size);
if (!data)
return false;
/*
* Actual cannot be less than expected. It can be more than expected
* because of the trailing alignment padding.
*
* Note that invalid @len values can occur because the caller loads
* the value during an allowed data race.
*/
if (data_size < (unsigned int)len)
return false;
/* Caller interested in the line count? */
if (line_count) *line_count = count_lines(data, len);
/* Caller interested in the data content? */
if (!buf || !buf_size)
return true;
data_size = min_t(unsigned int, buf_size, len);
memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */
return true;
}
/*
* This is an extended version of desc_read(). It gets a copy of a specified
* descriptor. However, it also verifies that the record is finalized and has
* the sequence number @seq. On success, 0 is returned.
*
* Error return values:
* -EINVAL: A finalized record with sequence number @seq does not exist.
* -ENOENT: A finalized record with sequence number @seq exists, but its data
* is not available. This is a valid record, so readers should
* continue with the next record.
*/
static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring,
unsigned long id, u64 seq,
struct prb_desc *desc_out)
{
struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos;
enum desc_state d_state;
u64 s;
d_state = desc_read(desc_ring, id, desc_out, &s, NULL);
/*
* An unexpected @id (desc_miss) or @seq mismatch means the record
* does not exist. A descriptor in the reserved or committed state
* means the record does not yet exist for the reader.
*/
if (d_state == desc_miss ||
d_state == desc_reserved ||
d_state == desc_committed ||
s != seq) {
return -EINVAL;
}
/*
* A descriptor in the reusable state may no longer have its data
* available; report it as existing but with lost data. Or the record
* may actually be a record with lost data.
*/
if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) {
return -ENOENT;
}
return 0;
}
/*
* Copy the ringbuffer data from the record with @seq to the provided
* @r buffer. On success, 0 is returned.
*
* See desc_read_finalized_seq() for error return values.
*/
static int prb_read(struct printk_ringbuffer *rb, u64 seq,
struct printk_record *r, unsigned int *line_count)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
struct printk_info *info = to_info(desc_ring, seq);
struct prb_desc *rdesc = to_desc(desc_ring, seq);
atomic_long_t *state_var = &rdesc->state_var;
struct prb_desc desc;
unsigned long id;
int err;
/* Extract the ID, used to specify the descriptor to read. */
id = DESC_ID(atomic_long_read(state_var));
/* Get a local copy of the correct descriptor (if available). */
err = desc_read_finalized_seq(desc_ring, id, seq, &desc);
/*
* If @r is NULL, the caller is only interested in the availability
* of the record.
*/
if (err || !r)
return err;
/* If requested, copy meta data. */
if (r->info) memcpy(r->info, info, sizeof(*(r->info)));
/* Copy text data. If it fails, this is a data-less record. */
if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len,
r->text_buf, r->text_buf_size, line_count)) {
return -ENOENT;
}
/* Ensure the record is still finalized and has the same @seq. */
return desc_read_finalized_seq(desc_ring, id, seq, &desc);
}
/* Get the sequence number of the tail descriptor. */
u64 prb_first_seq(struct printk_ringbuffer *rb)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
enum desc_state d_state;
struct prb_desc desc;
unsigned long id;
u64 seq;
for (;;) {
id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */
d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */
/*
* This loop will not be infinite because the tail is
* _always_ in the finalized or reusable state.
*/
if (d_state == desc_finalized || d_state == desc_reusable)
break;
/*
* Guarantee the last state load from desc_read() is before
* reloading @tail_id in order to see a new tail in the case
* that the descriptor has been recycled. This pairs with
* desc_reserve:D.
*
* Memory barrier involvement:
*
* If prb_first_seq:B reads from desc_reserve:F, then
* prb_first_seq:A reads from desc_push_tail:B.
*
* Relies on:
*
* MB from desc_push_tail:B to desc_reserve:F
* matching
* RMB prb_first_seq:B to prb_first_seq:A
*/
smp_rmb(); /* LMM(prb_first_seq:C) */
}
return seq;
}
/**
* prb_next_reserve_seq() - Get the sequence number after the most recently
* reserved record.
*
* @rb: The ringbuffer to get the sequence number from.
*
* This is the public function available to readers to see what sequence
* number will be assigned to the next reserved record.
*
* Note that depending on the situation, this value can be equal to or
* higher than the sequence number returned by prb_next_seq().
*
* Context: Any context.
* Return: The sequence number that will be assigned to the next record
* reserved.
*/
u64 prb_next_reserve_seq(struct printk_ringbuffer *rb)
{
struct prb_desc_ring *desc_ring = &rb->desc_ring;
unsigned long last_finalized_id;
atomic_long_t *state_var;
u64 last_finalized_seq;
unsigned long head_id;
struct prb_desc desc;
unsigned long diff;
struct prb_desc *d;
int err;
/*
* It may not be possible to read a sequence number for @head_id.
* So the ID of @last_finailzed_seq is used to calculate what the
* sequence number of @head_id will be.
*/
try_again:
last_finalized_seq = desc_last_finalized_seq(rb);
/*
* @head_id is loaded after @last_finalized_seq to ensure that
* it points to the record with @last_finalized_seq or newer.
*
* Memory barrier involvement:
*
* If desc_last_finalized_seq:A reads from
* desc_update_last_finalized:A, then
* prb_next_reserve_seq:A reads from desc_reserve:D.
*
* Relies on:
*
* RELEASE from desc_reserve:D to desc_update_last_finalized:A
* matching
* ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A
*
* Note: desc_reserve:D and desc_update_last_finalized:A can be
* different CPUs. However, the desc_update_last_finalized:A CPU
* (which performs the release) must have previously seen
* desc_read:C, which implies desc_reserve:D can be seen.
*/
head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */
d = to_desc(desc_ring, last_finalized_seq);
state_var = &d->state_var;
/* Extract the ID, used to specify the descriptor to read. */
last_finalized_id = DESC_ID(atomic_long_read(state_var));
/* Ensure @last_finalized_id is correct. */
err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc);
if (err == -EINVAL) {
if (last_finalized_seq == 0) {
/*
* No record has been finalized or even reserved yet.
*
* The @head_id is initialized such that the first
* increment will yield the first record (seq=0).
* Handle it separately to avoid a negative @diff
* below.
*/
if (head_id == DESC0_ID(desc_ring->count_bits))
return 0;
/*
* One or more descriptors are already reserved. Use
* the descriptor ID of the first one (@seq=0) for
* the @diff below.
*/
last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1;
} else {
/* Record must have been overwritten. Try again. */
goto try_again;
}
}
/* Diff of known descriptor IDs to compute related sequence numbers. */
diff = head_id - last_finalized_id;
/*
* @head_id points to the most recently reserved record, but this
* function returns the sequence number that will be assigned to the
* next (not yet reserved) record. Thus +1 is needed.
*/
return (last_finalized_seq + diff + 1);
}
/*
* Non-blocking read of a record.
*
* On success @seq is updated to the record that was read and (if provided)
* @r and @line_count will contain the read/calculated data.
*
* On failure @seq is updated to a record that is not yet available to the
* reader, but it will be the next record available to the reader.
*
* Note: When the current CPU is in panic, this function will skip over any
* non-existent/non-finalized records in order to allow the panic CPU
* to print any and all records that have been finalized.
*/
static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
struct printk_record *r, unsigned int *line_count)
{
u64 tail_seq;
int err;
while ((err = prb_read(rb, *seq, r, line_count))) {
tail_seq = prb_first_seq(rb);
if (*seq < tail_seq) {
/*
* Behind the tail. Catch up and try again. This
* can happen for -ENOENT and -EINVAL cases.
*/
*seq = tail_seq;
} else if (err == -ENOENT) {
/* Record exists, but the data was lost. Skip. */
(*seq)++;
} else {
/*
* Non-existent/non-finalized record. Must stop.
*
* For panic situations it cannot be expected that
* non-finalized records will become finalized. But
* there may be other finalized records beyond that
* need to be printed for a panic situation. If this
* is the panic CPU, skip this
* non-existent/non-finalized record unless non-panic
* CPUs are still running and their debugging is
* explicitly enabled.
*
* Note that new messages printed on panic CPU are
* finalized when we are here. The only exception
* might be the last message without trailing newline.
* But it would have the sequence number returned
* by "prb_next_reserve_seq() - 1".
*/
if (this_cpu_in_panic() && (!debug_non_panic_cpus || legacy_allow_panic_sync) &&
((*seq + 1) < prb_next_reserve_seq(rb))) {
(*seq)++;
} else {
return false;
}
}
}
return true;
}
/**
* prb_read_valid() - Non-blocking read of a requested record or (if gone)
* the next available record.
*
* @rb: The ringbuffer to read from.
* @seq: The sequence number of the record to read.
* @r: A record data buffer to store the read record to.
*
* This is the public function available to readers to read a record.
*
* The reader provides the @info and @text_buf buffers of @r to be
* filled in. Any of the buffer pointers can be set to NULL if the reader
* is not interested in that data. To ensure proper initialization of @r,
* prb_rec_init_rd() should be used.
*
* Context: Any context.
* Return: true if a record was read, otherwise false.
*
* On success, the reader must check r->info.seq to see which record was
* actually read. This allows the reader to detect dropped records.
*
* Failure means @seq refers to a record not yet available to the reader.
*/
bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq,
struct printk_record *r)
{
return _prb_read_valid(rb, &seq, r, NULL);
}
/**
* prb_read_valid_info() - Non-blocking read of meta data for a requested
* record or (if gone) the next available record.
*
* @rb: The ringbuffer to read from.
* @seq: The sequence number of the record to read.
* @info: A buffer to store the read record meta data to.
* @line_count: A buffer to store the number of lines in the record text.
*
* This is the public function available to readers to read only the
* meta data of a record.
*
* The reader provides the @info, @line_count buffers to be filled in.
* Either of the buffer pointers can be set to NULL if the reader is not
* interested in that data.
*
* Context: Any context.
* Return: true if a record's meta data was read, otherwise false.
*
* On success, the reader must check info->seq to see which record meta data
* was actually read. This allows the reader to detect dropped records.
*
* Failure means @seq refers to a record not yet available to the reader.
*/
bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq,
struct printk_info *info, unsigned int *line_count)
{
struct printk_record r;
prb_rec_init_rd(&r, info, NULL, 0);
return _prb_read_valid(rb, &seq, &r, line_count);
}
/**
* prb_first_valid_seq() - Get the sequence number of the oldest available
* record.
*
* @rb: The ringbuffer to get the sequence number from.
*
* This is the public function available to readers to see what the
* first/oldest valid sequence number is.
*
* This provides readers a starting point to begin iterating the ringbuffer.
*
* Context: Any context.
* Return: The sequence number of the first/oldest record or, if the
* ringbuffer is empty, 0 is returned.
*/
u64 prb_first_valid_seq(struct printk_ringbuffer *rb)
{
u64 seq = 0;
if (!_prb_read_valid(rb, &seq, NULL, NULL))
return 0;
return seq;
}
/**
* prb_next_seq() - Get the sequence number after the last available record.
*
* @rb: The ringbuffer to get the sequence number from.
*
* This is the public function available to readers to see what the next
* newest sequence number available to readers will be.
*
* This provides readers a sequence number to jump to if all currently
* available records should be skipped. It is guaranteed that all records
* previous to the returned value have been finalized and are (or were)
* available to the reader.
*
* Context: Any context.
* Return: The sequence number of the next newest (not yet available) record
* for readers.
*/
u64 prb_next_seq(struct printk_ringbuffer *rb)
{
u64 seq;
seq = desc_last_finalized_seq(rb);
/*
* Begin searching after the last finalized record.
*
* On 0, the search must begin at 0 because of hack#2
* of the bootstrapping phase it is not known if a
* record at index 0 exists.
*/
if (seq != 0)
seq++;
/*
* The information about the last finalized @seq might be inaccurate.
* Search forward to find the current one.
*/
while (_prb_read_valid(rb, &seq, NULL, NULL))
seq++;
return seq;
}
/**
* prb_init() - Initialize a ringbuffer to use provided external buffers.
*
* @rb: The ringbuffer to initialize.
* @text_buf: The data buffer for text data.
* @textbits: The size of @text_buf as a power-of-2 value.
* @descs: The descriptor buffer for ringbuffer records.
* @descbits: The count of @descs items as a power-of-2 value.
* @infos: The printk_info buffer for ringbuffer records.
*
* This is the public function available to writers to setup a ringbuffer
* during runtime using provided buffers.
*
* This must match the initialization of DEFINE_PRINTKRB().
*
* Context: Any context.
*/
void prb_init(struct printk_ringbuffer *rb,
char *text_buf, unsigned int textbits,
struct prb_desc *descs, unsigned int descbits,
struct printk_info *infos)
{
memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0]));
memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0]));
rb->desc_ring.count_bits = descbits;
rb->desc_ring.descs = descs;
rb->desc_ring.infos = infos;
atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits));
atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits));
atomic_long_set(&rb->desc_ring.last_finalized_seq, 0);
rb->text_data_ring.size_bits = textbits;
rb->text_data_ring.data = text_buf;
atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits));
atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits));
atomic_long_set(&rb->fail, 0);
atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits));
descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS;
descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS;
infos[0].seq = -(u64)_DESCS_COUNT(descbits);
infos[_DESCS_COUNT(descbits) - 1].seq = 0;
}
/**
* prb_record_text_space() - Query the full actual used ringbuffer space for
* the text data of a reserved entry.
*
* @e: The successfully reserved entry to query.
*
* This is the public function available to writers to see how much actual
* space is used in the ringbuffer to store the text data of the specified
* entry.
*
* This function is only valid if @e has been successfully reserved using
* prb_reserve().
*
* Context: Any context.
* Return: The size in bytes used by the text data of the associated record.
*/
unsigned int prb_record_text_space(struct prb_reserved_entry *e)
{
return e->text_space;
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_FS_H
#define _LINUX_FS_H
#include <linux/vfsdebug.h>
#include <linux/linkage.h>
#include <linux/wait_bit.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/list_lru.h>
#include <linux/llist.h>
#include <linux/radix-tree.h>
#include <linux/xarray.h>
#include <linux/rbtree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fcntl.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
#include <linux/delayed_call.h>
#include <linux/uuid.h>
#include <linux/errseq.h>
#include <linux/ioprio.h>
#include <linux/fs_types.h>
#include <linux/build_bug.h>
#include <linux/stddef.h>
#include <linux/mount.h>
#include <linux/cred.h>
#include <linux/mnt_idmapping.h>
#include <linux/slab.h>
#include <linux/maple_tree.h>
#include <linux/rw_hint.h>
#include <linux/file_ref.h>
#include <linux/unicode.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
struct backing_dev_info;
struct bdi_writeback;
struct bio;
struct io_comp_batch;
struct export_operations;
struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
struct fscrypt_inode_info;
struct fscrypt_operations;
struct fsverity_info;
struct fsverity_operations;
struct fsnotify_mark_connector;
struct fsnotify_sb_info;
struct fs_context;
struct fs_parameter_spec;
struct fileattr;
struct iomap_ops;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);
extern unsigned long get_max_files(void);
extern unsigned int sysctl_nr_open;
typedef __kernel_rwf_t rwf_t;
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
#define MAY_READ 0x00000004
#define MAY_APPEND 0x00000008
#define MAY_ACCESS 0x00000010
#define MAY_OPEN 0x00000020
#define MAY_CHDIR 0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK 0x00000080
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
* to O_WRONLY and O_RDWR via the strange trick in do_dentry_open()
*/
/* file is open for reading */
#define FMODE_READ ((__force fmode_t)(1 << 0))
/* file is open for writing */
#define FMODE_WRITE ((__force fmode_t)(1 << 1))
/* file is seekable */
#define FMODE_LSEEK ((__force fmode_t)(1 << 2))
/* file can be accessed using pread */
#define FMODE_PREAD ((__force fmode_t)(1 << 3))
/* file can be accessed using pwrite */
#define FMODE_PWRITE ((__force fmode_t)(1 << 4))
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC ((__force fmode_t)(1 << 5))
/* File writes are restricted (block device specific) */
#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6))
/* File supports atomic writes */
#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7))
/* FMODE_* bit 8 */
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH ((__force fmode_t)(1 << 9))
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH ((__force fmode_t)(1 << 10))
/*
* Don't update ctime and mtime.
*
* Currently a special hack for the XFS open_by_handle ioctl, but we'll
* hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
*/
#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11))
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)(1 << 12))
/* FMODE_* bit 13 */
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH ((__force fmode_t)(1 << 14))
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15))
/* Write access to underlying fs */
#define FMODE_WRITER ((__force fmode_t)(1 << 16))
/* Has read method(s) */
#define FMODE_CAN_READ ((__force fmode_t)(1 << 17))
/* Has write method(s) */
#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18))
#define FMODE_OPENED ((__force fmode_t)(1 << 19))
#define FMODE_CREATED ((__force fmode_t)(1 << 20))
/* File is stream-like */
#define FMODE_STREAM ((__force fmode_t)(1 << 21))
/* File supports DIRECT IO */
#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22))
#define FMODE_NOREUSE ((__force fmode_t)(1 << 23))
/* File is embedded in backing_file object */
#define FMODE_BACKING ((__force fmode_t)(1 << 24))
/*
* Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be
* generated (see below)
*/
#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25))
/*
* Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be
* generated (see below)
*/
#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26))
/* File is capable of returning -EAGAIN if I/O will block */
#define FMODE_NOWAIT ((__force fmode_t)(1 << 27))
/* File represents mount that needs unmounting */
#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28))
/* File does not contribute to nr_files count */
#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29))
/*
* The two FMODE_NONOTIFY* define which fsnotify events should not be generated
* for a file. These are the possible values of (f->f_mode &
* FMODE_FSNOTIFY_MASK) and their meaning:
*
* FMODE_NONOTIFY - suppress all (incl. non-permission) events.
* FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events.
* FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events.
*/
#define FMODE_FSNOTIFY_MASK \
(FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)
#define FMODE_FSNOTIFY_NONE(mode) \
((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY)
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
#define FMODE_FSNOTIFY_PERM(mode) \
((mode & FMODE_FSNOTIFY_MASK) == 0 || \
(mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM))
#define FMODE_FSNOTIFY_HSM(mode) \
((mode & FMODE_FSNOTIFY_MASK) == 0)
#else
#define FMODE_FSNOTIFY_PERM(mode) 0
#define FMODE_FSNOTIFY_HSM(mode) 0
#endif
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
*/
#define ATTR_MODE (1 << 0)
#define ATTR_UID (1 << 1)
#define ATTR_GID (1 << 2)
#define ATTR_SIZE (1 << 3)
#define ATTR_ATIME (1 << 4)
#define ATTR_MTIME (1 << 5)
#define ATTR_CTIME (1 << 6)
#define ATTR_ATIME_SET (1 << 7)
#define ATTR_MTIME_SET (1 << 8)
#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
#define ATTR_KILL_SUID (1 << 11)
#define ATTR_KILL_SGID (1 << 12)
#define ATTR_FILE (1 << 13)
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
#define ATTR_TOUCH (1 << 17)
#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */
/*
* Whiteout is represented by a char device. The following constants define the
* mode and device number to use.
*/
#define WHITEOUT_MODE 0
#define WHITEOUT_DEV 0
/*
* This is the Inode Attributes structure, used for notify_change(). It
* uses the above definitions as flags, to know which values have changed.
* Also, in this manner, a Filesystem can look at only the values it cares
* about. Basically, these are the attributes that the VFS layer can
* request to change from the FS layer.
*
* Derek Atkins <warlord@MIT.EDU> 94-10-20
*/
struct iattr {
unsigned int ia_valid;
umode_t ia_mode;
/*
* The two anonymous unions wrap structures with the same member.
*
* Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which
* are a dedicated type requiring the filesystem to use the dedicated
* helpers. Other filesystem can continue to use ia_{g,u}id until they
* have been ported.
*
* They always contain the same value. In other words FS_ALLOW_IDMAP
* pass down the same value on idmapped mounts as they would on regular
* mounts.
*/
union {
kuid_t ia_uid;
vfsuid_t ia_vfsuid;
};
union {
kgid_t ia_gid;
vfsgid_t ia_vfsgid;
};
loff_t ia_size;
struct timespec64 ia_atime;
struct timespec64 ia_mtime;
struct timespec64 ia_ctime;
/*
* Not an attribute, but an auxiliary info for filesystems wanting to
* implement an ftruncate() like method. NOTE: filesystem should
* check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
*/
struct file *ia_file;
};
/*
* Includes for diskquotas.
*/
#include <linux/quota.h>
/*
* Maximum number of layers of fs stack. Needs to be limited to
* prevent kernel stack overflow
*/
#define FILESYSTEM_MAX_STACK_DEPTH 2
/**
* enum positive_aop_returns - aop return codes with specific semantics
*
* @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
* completed, that the page is still locked, and
* should be considered active. The VM uses this hint
* to return the page to the active list -- it won't
* be a candidate for writeback again in the near
* future. Other callers must be careful to unlock
* the page if they get this return. Returned by
* writepage();
*
* @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
* unlocked it and the page might have been truncated.
* The caller should back up to acquiring a new page and
* trying again. The aop will be taking reasonable
* precautions not to livelock. If the caller held a page
* reference, it should drop it before retrying. Returned
* by read_folio().
*
* address_space_operation functions return these large constants to indicate
* special semantics to the caller. These are much larger than the bytes in a
* page to allow for functions that return the number of bytes operated on in a
* given page.
*/
enum positive_aop_returns {
AOP_WRITEPAGE_ACTIVATE = 0x80000,
AOP_TRUNCATED_PAGE = 0x80001,
};
/*
* oh the beauties of C type declarations.
*/
struct page;
struct address_space;
struct writeback_control;
struct readahead_control;
/* Match RWF_* bits to IOCB bits */
#define IOCB_HIPRI (__force int) RWF_HIPRI
#define IOCB_DSYNC (__force int) RWF_DSYNC
#define IOCB_SYNC (__force int) RWF_SYNC
#define IOCB_NOWAIT (__force int) RWF_NOWAIT
#define IOCB_APPEND (__force int) RWF_APPEND
#define IOCB_ATOMIC (__force int) RWF_ATOMIC
#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE
/* non-RWF related bits - start at 16 */
#define IOCB_EVENTFD (1 << 16)
#define IOCB_DIRECT (1 << 17)
#define IOCB_WRITE (1 << 18)
/* iocb->ki_waitq is valid */
#define IOCB_WAITQ (1 << 19)
#define IOCB_NOIO (1 << 20)
/* can use bio alloc cache */
#define IOCB_ALLOC_CACHE (1 << 21)
/*
* IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the
* iocb completion can be passed back to the owner for execution from a safe
* context rather than needing to be punted through a workqueue. If this
* flag is set, the bio completion handling may set iocb->dio_complete to a
* handler function and iocb->private to context information for that handler.
* The issuer should call the handler with that context information from task
* context to complete the processing of the iocb. Note that while this
* provides a task context for the dio_complete() callback, it should only be
* used on the completion side for non-IO generating completions. It's fine to
* call blocking functions from this callback, but they should not wait for
* unrelated IO (like cache flushing, new IO generation, etc).
*/
#define IOCB_DIO_CALLER_COMP (1 << 22)
/* kiocb is a read or write operation submitted by fs/aio.c. */
#define IOCB_AIO_RW (1 << 23)
#define IOCB_HAS_METADATA (1 << 24)
/* for use in trace events */
#define TRACE_IOCB_STRINGS \
{ IOCB_HIPRI, "HIPRI" }, \
{ IOCB_DSYNC, "DSYNC" }, \
{ IOCB_SYNC, "SYNC" }, \
{ IOCB_NOWAIT, "NOWAIT" }, \
{ IOCB_APPEND, "APPEND" }, \
{ IOCB_ATOMIC, "ATOMIC" }, \
{ IOCB_DONTCACHE, "DONTCACHE" }, \
{ IOCB_EVENTFD, "EVENTFD"}, \
{ IOCB_DIRECT, "DIRECT" }, \
{ IOCB_WRITE, "WRITE" }, \
{ IOCB_WAITQ, "WAITQ" }, \
{ IOCB_NOIO, "NOIO" }, \
{ IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \
{ IOCB_DIO_CALLER_COMP, "CALLER_COMP" }
struct kiocb {
struct file *ki_filp;
loff_t ki_pos;
void (*ki_complete)(struct kiocb *iocb, long ret);
void *private;
int ki_flags;
u16 ki_ioprio; /* See linux/ioprio.h */
union {
/*
* Only used for async buffered reads, where it denotes the
* page waitqueue associated with completing the read. Valid
* IFF IOCB_WAITQ is set.
*/
struct wait_page_queue *ki_waitq;
/*
* Can be used for O_DIRECT IO, where the completion handling
* is punted back to the issuer of the IO. May only be set
* if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer
* must then check for presence of this handler when ki_complete
* is invoked. The data passed in to this handler must be
* assigned to ->private when dio_complete is assigned.
*/
ssize_t (*dio_complete)(void *data);
};
};
static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
return kiocb->ki_complete == NULL;
}
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*read_folio)(struct file *, struct folio *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
/* Mark a folio dirty. Return true if this dirtied it */
bool (*dirty_folio)(struct address_space *, struct folio *);
void (*readahead)(struct readahead_control *);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata);
int (*write_end)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata);
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
sector_t (*bmap)(struct address_space *, sector_t);
void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
bool (*release_folio)(struct folio *, gfp_t);
void (*free_folio)(struct folio *folio);
ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
/*
* migrate the contents of a folio to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
*/
int (*migrate_folio)(struct address_space *, struct folio *dst,
struct folio *src, enum migrate_mode);
int (*launder_folio)(struct folio *);
bool (*is_partially_uptodate) (struct folio *, size_t from,
size_t count);
void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
int (*error_remove_folio)(struct address_space *, struct folio *);
/* swapfile support */
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
sector_t *span);
void (*swap_deactivate)(struct file *file);
int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
};
extern const struct address_space_operations empty_aops;
/**
* struct address_space - Contents of a cacheable, mappable object.
* @host: Owner, either the inode or the block_device.
* @i_pages: Cached pages.
* @invalidate_lock: Guards coherency between page cache contents and
* file offset->disk block mappings in the filesystem during invalidates.
* It is also used to block modification of page cache contents through
* memory mappings.
* @gfp_mask: Memory allocation flags to use for allocating pages.
* @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings.
* @nr_thps: Number of THPs in the pagecache (non-shmem only).
* @i_mmap: Tree of private and shared mappings.
* @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
* @nrpages: Number of page entries, protected by the i_pages lock.
* @writeback_index: Writeback starts here.
* @a_ops: Methods.
* @flags: Error bits and flags (AS_*).
* @wb_err: The most recent error which has occurred.
* @i_private_lock: For use by the owner of the address_space.
* @i_private_list: For use by the owner of the address_space.
* @i_private_data: For use by the owner of the address_space.
*/
struct address_space {
struct inode *host;
struct xarray i_pages;
struct rw_semaphore invalidate_lock;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
/* number of thp, only for non-shmem files */
atomic_t nr_thps;
#endif
struct rb_root_cached i_mmap;
unsigned long nrpages;
pgoff_t writeback_index;
const struct address_space_operations *a_ops;
unsigned long flags;
errseq_t wb_err;
spinlock_t i_private_lock;
struct list_head i_private_list;
struct rw_semaphore i_mmap_rwsem;
void * i_private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
* On most architectures that alignment is already the case; but
* must be enforced here for CRIS, to let the least significant bit
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
*/
/* XArray tags, for tagging dirty and writeback pages in the pagecache. */
#define PAGECACHE_TAG_DIRTY XA_MARK_0
#define PAGECACHE_TAG_WRITEBACK XA_MARK_1
#define PAGECACHE_TAG_TOWRITE XA_MARK_2
/*
* Returns true if any of the pages in the mapping are marked with the tag.
*/
static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
{
return xa_marked(&mapping->i_pages, tag);
}
static inline void i_mmap_lock_write(struct address_space *mapping)
{
down_write(&mapping->i_mmap_rwsem);
}
static inline int i_mmap_trylock_write(struct address_space *mapping)
{
return down_write_trylock(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_unlock_write(struct address_space *mapping)
{
up_write(&mapping->i_mmap_rwsem);
}
static inline int i_mmap_trylock_read(struct address_space *mapping)
{
return down_read_trylock(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_lock_read(struct address_space *mapping)
{
down_read(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_unlock_read(struct address_space *mapping)
{
up_read(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_assert_locked(struct address_space *mapping)
{
lockdep_assert_held(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_assert_write_locked(struct address_space *mapping)
{
lockdep_assert_held_write(&mapping->i_mmap_rwsem);
}
/*
* Might pages of this file be mapped into userspace?
*/
static inline int mapping_mapped(struct address_space *mapping)
{
return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
}
/*
* Might pages of this file have been modified in userspace?
* Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap
* marks vma as VM_SHARED if it is shared, and the file was opened for
* writing i.e. vma may be mprotected writable even if now readonly.
*
* If i_mmap_writable is negative, no new writable mappings are allowed. You
* can only deny writable mappings, if none exists right now.
*/
static inline int mapping_writably_mapped(struct address_space *mapping)
{
return atomic_read(&mapping->i_mmap_writable) > 0;
}
static inline int mapping_map_writable(struct address_space *mapping)
{
return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
0 : -EPERM;
}
static inline void mapping_unmap_writable(struct address_space *mapping)
{
atomic_dec(&mapping->i_mmap_writable);
}
static inline int mapping_deny_writable(struct address_space *mapping)
{
return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
0 : -EBUSY;
}
static inline void mapping_allow_writable(struct address_space *mapping)
{
atomic_inc(&mapping->i_mmap_writable);
}
/*
* Use sequence counter to get consistent i_size on 32-bit processors.
*/
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
/*
* ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
* cache the ACL. This also means that ->get_inode_acl() can be called in RCU
* mode with the LOOKUP_RCU flag.
*/
#define ACL_DONT_CACHE ((void *)(-3))
static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
{
return (void *)task + 1;
}
static inline bool
is_uncached_acl(struct posix_acl *acl)
{
return (long)acl & 1;
}
#define IOP_FASTPERM 0x0001
#define IOP_LOOKUP 0x0002
#define IOP_NOFOLLOW 0x0004
#define IOP_XATTR 0x0008
#define IOP_DEFAULT_READLINK 0x0010
#define IOP_MGTIME 0x0020
#define IOP_CACHED_LINK 0x0040
/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
*/
struct inode {
umode_t i_mode;
unsigned short i_opflags;
kuid_t i_uid;
kgid_t i_gid;
unsigned int i_flags;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
/* Stat data, not accessed from path walking */
unsigned long i_ino;
/*
* Filesystems may only read i_nlink directly. They shall use the
* following functions for modification:
*
* (set|clear|inc|drop)_nlink
* inode_(inc|dec)_link_count
*/
union {
const unsigned int i_nlink;
unsigned int __i_nlink;
};
dev_t i_rdev;
loff_t i_size;
time64_t i_atime_sec;
time64_t i_mtime_sec;
time64_t i_ctime_sec;
u32 i_atime_nsec;
u32 i_mtime_nsec;
u32 i_ctime_nsec;
u32 i_generation;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
enum rw_hint i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
/* Misc */
u32 i_state;
/* 32-bit hole */
struct rw_semaphore i_rwsem;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_io_list; /* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *i_wb; /* the associated cgroup wb */
/* foreign inode detection, see wbc_detach_inode() */
int i_wb_frn_winner;
u16 i_wb_frn_avg_time;
u16 i_wb_frn_history;
#endif
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
struct list_head i_wb_list; /* backing dev writeback list */
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
};
atomic64_t i_version;
atomic64_t i_sequence; /* see futex */
atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
atomic_t i_readcount; /* struct files open RO */
#endif
union {
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
void (*free_inode)(struct inode *);
};
struct file_lock_context *i_flctx;
struct address_space i_data;
union {
struct list_head i_devices;
int i_linklen;
};
union {
struct pipe_inode_info *i_pipe;
struct cdev *i_cdev;
char *i_link;
unsigned i_dir_seq;
};
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
/* 32-bit hole reserved for expanding i_fsnotify_mask */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_inode_info *i_crypt_info;
#endif
#ifdef CONFIG_FS_VERITY
struct fsverity_info *i_verity_info;
#endif
void *i_private; /* fs or device private pointer */
} __randomize_layout;
static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
{
VFS_WARN_ON_INODE(strlen(link) != linklen, inode);
VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode);
inode->i_link = link;
inode->i_linklen = linklen;
inode->i_opflags |= IOP_CACHED_LINK;
}
/*
* Get bit address from inode->i_state to use with wait_var_event()
* infrastructre.
*/
#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit))
struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe,
struct inode *inode, u32 bit);
static inline void inode_wake_up_bit(struct inode *inode, u32 bit)
{
/* Caller is responsible for correct memory barriers. */
wake_up_var(inode_state_wait_address(inode, bit));
}
struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode);
static inline unsigned int i_blocksize(const struct inode *node)
{
return (1 << node->i_blkbits);
}
static inline int inode_unhashed(struct inode *inode)
{
return hlist_unhashed(&inode->i_hash);
}
/*
* __mark_inode_dirty expects inodes to be hashed. Since we don't
* want special inodes in the fileset inode space, we make them
* appear hashed, but do not put on any lists. hlist_del()
* will work fine and require no locking.
*/
static inline void inode_fake_hash(struct inode *inode)
{
hlist_add_fake(&inode->i_hash);
}
/*
* inode->i_mutex nesting subclasses for the lock validator:
*
* 0: the object of the current VFS operation
* 1: parent
* 2: child/target
* 3: xattr
* 4: second non-directory
* 5: second parent (when locking independent directories in rename)
*
* I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
* non-directories at once.
*
* The locking order between these classes is
* parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
*/
enum inode_i_mutex_lock_class
{
I_MUTEX_NORMAL,
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
I_MUTEX_NONDIR2,
I_MUTEX_PARENT2,
};
static inline void inode_lock(struct inode *inode)
{
down_write(&inode->i_rwsem);
}
static inline void inode_unlock(struct inode *inode)
{
up_write(&inode->i_rwsem);
}
static inline void inode_lock_shared(struct inode *inode)
{
down_read(&inode->i_rwsem);
}
static inline void inode_unlock_shared(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
static inline int inode_trylock(struct inode *inode)
{
return down_write_trylock(&inode->i_rwsem);
}
static inline int inode_trylock_shared(struct inode *inode)
{
return down_read_trylock(&inode->i_rwsem);
}
static inline int inode_is_locked(struct inode *inode)
{
return rwsem_is_locked(&inode->i_rwsem);
}
static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
down_write_nested(&inode->i_rwsem, subclass);
}
static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass)
{
down_read_nested(&inode->i_rwsem, subclass);
}
static inline void filemap_invalidate_lock(struct address_space *mapping)
{
down_write(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_unlock(struct address_space *mapping)
{
up_write(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
{
down_read(&mapping->invalidate_lock);
}
static inline int filemap_invalidate_trylock_shared(
struct address_space *mapping)
{
return down_read_trylock(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_unlock_shared(
struct address_space *mapping)
{
up_read(&mapping->invalidate_lock);
}
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
void filemap_invalidate_lock_two(struct address_space *mapping1,
struct address_space *mapping2);
void filemap_invalidate_unlock_two(struct address_space *mapping1,
struct address_space *mapping2);
/*
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
* with respect to the local cpu (unlike with preempt disabled),
* but they don't need to be atomic with respect to other cpus like in
* true SMP (so they need either to either locally disable irq around
* the read or for example on x86 they can be still implemented as a
* cmpxchg8b without the need of the lock prefix). For SMP compiles
* and 64bit archs it makes no difference if preempt is enabled or not.
*/
static inline loff_t i_size_read(const struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
loff_t i_size;
unsigned int seq;
do {
seq = read_seqcount_begin(&inode->i_size_seqcount);
i_size = inode->i_size;
} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
loff_t i_size;
preempt_disable();
i_size = inode->i_size;
preempt_enable();
return i_size;
#else
/* Pairs with smp_store_release() in i_size_write() */
return smp_load_acquire(&inode->i_size);
#endif
}
/*
* NOTE: unlike i_size_read(), i_size_write() does need locking around it
* (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
* can be lost, resulting in subsequent i_size_read() calls spinning forever.
*/
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
preempt_disable();
write_seqcount_begin(&inode->i_size_seqcount);
inode->i_size = i_size;
write_seqcount_end(&inode->i_size_seqcount);
preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
preempt_disable();
inode->i_size = i_size;
preempt_enable();
#else
/*
* Pairs with smp_load_acquire() in i_size_read() to ensure
* changes related to inode size (such as page contents) are
* visible before we see the changed inode size.
*/
smp_store_release(&inode->i_size, i_size);
#endif
}
static inline unsigned iminor(const struct inode *inode)
{
return MINOR(inode->i_rdev);
}
static inline unsigned imajor(const struct inode *inode)
{
return MAJOR(inode->i_rdev);
}
struct fown_struct {
struct file *file; /* backpointer for security modules */
rwlock_t lock; /* protects pid, uid, euid fields */
struct pid *pid; /* pid or -pgrp where SIGIO should be sent */
enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */
kuid_t uid, euid; /* uid/euid of process setting the owner */
int signum; /* posix.1b rt signal to be delivered on IO */
};
/**
* struct file_ra_state - Track a file's readahead state.
* @start: Where the most recent readahead started.
* @size: Number of pages read in the most recent readahead.
* @async_size: Numer of pages that were/are not needed immediately
* and so were/are genuinely "ahead". Start next readahead when
* the first of these pages is accessed.
* @ra_pages: Maximum size of a readahead request, copied from the bdi.
* @mmap_miss: How many mmap accesses missed in the page cache.
* @prev_pos: The last byte in the most recent read request.
*
* When this structure is passed to ->readahead(), the "most recent"
* readahead means the current readahead.
*/
struct file_ra_state {
pgoff_t start;
unsigned int size;
unsigned int async_size;
unsigned int ra_pages;
unsigned int mmap_miss;
loff_t prev_pos;
};
/*
* Check if @index falls in the readahead windows.
*/
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
return (index >= ra->start &&
index < ra->start + ra->size);
}
/**
* struct file - Represents a file
* @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context.
* @f_mode: FMODE_* flags often used in hotpaths
* @f_op: file operations
* @f_mapping: Contents of a cacheable, mappable object.
* @private_data: filesystem or driver specific data
* @f_inode: cached inode
* @f_flags: file flags
* @f_iocb_flags: iocb flags
* @f_cred: stashed credentials of creator/opener
* @f_owner: file owner
* @f_path: path of the file
* @f_pos_lock: lock protecting file position
* @f_pipe: specific to pipes
* @f_pos: file position
* @f_security: LSM security context of this file
* @f_wb_err: writeback error
* @f_sb_err: per sb writeback errors
* @f_ep: link of all epoll hooks for this file
* @f_task_work: task work entry point
* @f_llist: work queue entrypoint
* @f_ra: file's readahead state
* @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.)
* @f_ref: reference count
*/
struct file {
spinlock_t f_lock;
fmode_t f_mode;
const struct file_operations *f_op;
struct address_space *f_mapping;
void *private_data;
struct inode *f_inode;
unsigned int f_flags;
unsigned int f_iocb_flags;
const struct cred *f_cred;
struct fown_struct *f_owner;
/* --- cacheline 1 boundary (64 bytes) --- */
struct path f_path;
union {
/* regular files (with FMODE_ATOMIC_POS) and directories */
struct mutex f_pos_lock;
/* pipes */
u64 f_pipe;
};
loff_t f_pos;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* --- cacheline 2 boundary (128 bytes) --- */
errseq_t f_wb_err;
errseq_t f_sb_err;
#ifdef CONFIG_EPOLL
struct hlist_head *f_ep;
#endif
union {
struct callback_head f_task_work;
struct llist_node f_llist;
struct file_ra_state f_ra;
freeptr_t f_freeptr;
};
file_ref_t f_ref;
/* --- cacheline 3 boundary (192 bytes) --- */
} __randomize_layout
__attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
__u32 handle_bytes;
int handle_type;
/* file identifier */
unsigned char f_handle[] __counted_by(handle_bytes);
};
static inline struct file *get_file(struct file *f)
{ file_ref_inc(&f->f_ref);
return f;
}
struct file *get_file_rcu(struct file __rcu **f);
struct file *get_file_active(struct file **f);
#define file_count(f) file_ref_read(&(f)->f_ref)
#define MAX_NON_LFS ((1UL<<31) - 1)
/* Page cache limit. The filesystems should put that into their s_maxbytes
limits, otherwise bad things can happen in VM. */
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT)
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX)
#endif
/* legacy typedef, should eventually be removed */
typedef void *fl_owner_t;
struct file_lock;
struct file_lease;
/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define OFFSET_MAX type_max(loff_t)
#define OFFT_OFFSET_MAX type_max(off_t)
#endif
int file_f_owner_allocate(struct file *file);
static inline struct fown_struct *file_f_owner(const struct file *file)
{
return READ_ONCE(file->f_owner);
}
extern void send_sigio(struct fown_struct *fown, int fd, int band);
static inline struct inode *file_inode(const struct file *f)
{
return f->f_inode;
}
/*
* file_dentry() is a relic from the days that overlayfs was using files with a
* "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs.
* In those days, file_dentry() was needed to get the underlying fs dentry that
* matches f_inode.
* Files with "fake" path should not exist nowadays, so use an assertion to make
* sure that file_dentry() was not papering over filesystem bugs.
*/
static inline struct dentry *file_dentry(const struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
WARN_ON_ONCE(d_inode(dentry) != file_inode(file));
return dentry;
}
struct fasync_struct {
rwlock_t fa_lock;
int magic;
int fa_fd;
struct fasync_struct *fa_next; /* singly linked list */
struct file *fa_file;
struct rcu_head fa_rcu;
};
#define FASYNC_MAGIC 0x4601
/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern int f_setown(struct file *filp, int who, int force);
extern void f_delown(struct file *filp);
extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct file *file);
/*
* sb->s_flags. Note that these mirror the equivalent MS_* flags where
* represented in both.
*/
#define SB_RDONLY BIT(0) /* Mount read-only */
#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */
#define SB_NODEV BIT(2) /* Disallow access to device special files */
#define SB_NOEXEC BIT(3) /* Disallow program execution */
#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */
#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */
#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */
#define SB_NOATIME BIT(10) /* Do not update access times. */
#define SB_NODIRATIME BIT(11) /* Do not update directory access times */
#define SB_SILENT BIT(15)
#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */
#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */
#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */
#define SB_I_VERSION BIT(23) /* Update inode I_version field */
#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */
/* These sb flags are internal to the kernel */
#define SB_DEAD BIT(21)
#define SB_DYING BIT(24)
#define SB_SUBMOUNT BIT(26)
#define SB_FORCE BIT(27)
#define SB_NOSEC BIT(28)
#define SB_BORN BIT(29)
#define SB_ACTIVE BIT(30)
#define SB_NOUSER BIT(31)
/* These flags relate to encoding and casefolding */
#define SB_ENC_STRICT_MODE_FL (1 << 0)
#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1)
#define sb_has_strict_encoding(sb) \
(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
#if IS_ENABLED(CONFIG_UNICODE)
#define sb_no_casefold_compat_fallback(sb) \
(sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL)
#else
#define sb_no_casefold_compat_fallback(sb) (1)
#endif
/*
* Umount options
*/
#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */
#define MNT_DETACH 0x00000002 /* Just detach from the tree */
#define MNT_EXPIRE 0x00000004 /* Mark for expiry */
#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */
#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */
/* sb->s_iflags */
#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */
#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */
#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */
#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */
/* sb->s_iflags to limit user namespace mounts */
#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */
#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020
#define SB_I_UNTRUSTED_MOUNTER 0x00000040
#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080
#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */
#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */
#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */
#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */
#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */
#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */
/* Possible states of 'frozen' field */
enum {
SB_UNFROZEN = 0, /* FS is unfrozen */
SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */
SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */
SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop
* internal threads if needed) */
SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */
};
#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
struct sb_writers {
unsigned short frozen; /* Is sb frozen? */
int freeze_kcount; /* How many kernel freeze requests? */
int freeze_ucount; /* How many userspace freeze requests? */
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
};
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
unsigned char s_blocksize_bits;
unsigned long s_blocksize;
loff_t s_maxbytes; /* Max file size */
struct file_system_type *s_type;
const struct super_operations *s_op;
const struct dquot_operations *dq_op;
const struct quotactl_ops *s_qcop;
const struct export_operations *s_export_op;
unsigned long s_flags;
unsigned long s_iflags; /* internal SB_I_* flags */
unsigned long s_magic;
struct dentry *s_root;
struct rw_semaphore s_umount;
int s_count;
atomic_t s_active;
#ifdef CONFIG_SECURITY
void *s_security;
#endif
const struct xattr_handler * const *s_xattr;
#ifdef CONFIG_FS_ENCRYPTION
const struct fscrypt_operations *s_cop;
struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */
#endif
#ifdef CONFIG_FS_VERITY
const struct fsverity_operations *s_vop;
#endif
#if IS_ENABLED(CONFIG_UNICODE)
struct unicode_map *s_encoding;
__u16 s_encoding_flags;
#endif
struct hlist_bl_head s_roots; /* alternate root dentries for NFS */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */
struct file *s_bdev_file;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct hlist_node s_instances;
unsigned int s_quota_types; /* Bitmask of supported quota types */
struct quota_info s_dquot; /* Diskquota specific options */
struct sb_writers s_writers;
/*
* Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
* s_fsnotify_info together for cache efficiency. They are frequently
* accessed and rarely modified.
*/
void *s_fs_info; /* Filesystem private info */
/* Granularity of c/m/atime in ns (cannot be worse than a second) */
u32 s_time_gran;
/* Time limits for c/m/atime in seconds */
time64_t s_time_min;
time64_t s_time_max;
#ifdef CONFIG_FSNOTIFY
u32 s_fsnotify_mask;
struct fsnotify_sb_info *s_fsnotify_info;
#endif
/*
* q: why are s_id and s_sysfs_name not the same? both are human
* readable strings that identify the filesystem
* a: s_id is allowed to change at runtime; it's used in log messages,
* and we want to when a device starts out as single device (s_id is dev
* name) but then a device is hot added and we have to switch to
* identifying it by UUID
* but s_sysfs_name is a handle for programmatic access, and can't
* change at runtime
*/
char s_id[32]; /* Informational name */
uuid_t s_uuid; /* UUID */
u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */
/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
char s_sysfs_name[UUID_STRING_LEN + 1];
unsigned int s_max_links;
/*
* The next field is for VFS *only*. No filesystems have any business
* even looking at it. You had been warned.
*/
struct mutex s_vfs_rename_mutex; /* Kludge */
/*
* Filesystem subtype. If non-empty the filesystem type field
* in /proc/mounts will be "type.subtype"
*/
const char *s_subtype;
const struct dentry_operations *s_d_op; /* default d_op for dentries */
struct shrinker *s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
/* Read-only state of the superblock is being changed */
int s_readonly_remount;
/* per-sb errseq_t for reporting writeback errors via syncfs */
errseq_t s_wb_err;
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
/*
* Owning user namespace and default context in which to
* interpret filesystem uids, gids, quotas, device nodes,
* xattrs and security labels.
*/
struct user_namespace *s_user_ns;
/*
* The list_lru structure is essentially just a pointer to a table
* of per-node lru lists, each of which has its own spinlock.
* There is no need to put them into separate cachelines.
*/
struct list_lru s_dentry_lru;
struct list_lru s_inode_lru;
struct rcu_head rcu;
struct work_struct destroy_work;
struct mutex s_sync_lock; /* sync serialisation lock */
/*
* Indicates how deep in a filesystem stack this SB is
*/
int s_stack_depth;
/* s_inode_list_lock protects s_inodes */
spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
struct list_head s_inodes; /* all inodes */
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
} __randomize_layout;
static inline struct user_namespace *i_user_ns(const struct inode *inode)
{
return inode->i_sb->s_user_ns;
}
/* Helper functions so that in most cases filesystems will
* not need to deal directly with kuid_t and kgid_t and can
* instead deal with the raw numeric values that are stored
* in the filesystem.
*/
static inline uid_t i_uid_read(const struct inode *inode)
{
return from_kuid(i_user_ns(inode), inode->i_uid);
}
static inline gid_t i_gid_read(const struct inode *inode)
{
return from_kgid(i_user_ns(inode), inode->i_gid);
}
static inline void i_uid_write(struct inode *inode, uid_t uid)
{
inode->i_uid = make_kuid(i_user_ns(inode), uid);
}
static inline void i_gid_write(struct inode *inode, gid_t gid)
{
inode->i_gid = make_kgid(i_user_ns(inode), gid);
}
/**
* i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping
* @idmap: idmap of the mount the inode was found from
* @inode: inode to map
*
* Return: whe inode's i_uid mapped down according to @idmap.
* If the inode's i_uid has no mapping INVALID_VFSUID is returned.
*/
static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap,
const struct inode *inode)
{
return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid);
}
/**
* i_uid_needs_update - check whether inode's i_uid needs to be updated
* @idmap: idmap of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Check whether the $inode's i_uid field needs to be updated taking idmapped
* mounts into account if the filesystem supports it.
*
* Return: true if @inode's i_uid field needs to be updated, false if not.
*/
static inline bool i_uid_needs_update(struct mnt_idmap *idmap,
const struct iattr *attr,
const struct inode *inode)
{
return ((attr->ia_valid & ATTR_UID) &&
!vfsuid_eq(attr->ia_vfsuid,
i_uid_into_vfsuid(idmap, inode)));
}
/**
* i_uid_update - update @inode's i_uid field
* @idmap: idmap of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Safely update @inode's i_uid field translating the vfsuid of any idmapped
* mount into the filesystem kuid.
*/
static inline void i_uid_update(struct mnt_idmap *idmap,
const struct iattr *attr,
struct inode *inode)
{
if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode),
attr->ia_vfsuid);
}
/**
* i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping
* @idmap: idmap of the mount the inode was found from
* @inode: inode to map
*
* Return: the inode's i_gid mapped down according to @idmap.
* If the inode's i_gid has no mapping INVALID_VFSGID is returned.
*/
static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap,
const struct inode *inode)
{
return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid);
}
/**
* i_gid_needs_update - check whether inode's i_gid needs to be updated
* @idmap: idmap of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Check whether the $inode's i_gid field needs to be updated taking idmapped
* mounts into account if the filesystem supports it.
*
* Return: true if @inode's i_gid field needs to be updated, false if not.
*/
static inline bool i_gid_needs_update(struct mnt_idmap *idmap,
const struct iattr *attr,
const struct inode *inode)
{
return ((attr->ia_valid & ATTR_GID) &&
!vfsgid_eq(attr->ia_vfsgid,
i_gid_into_vfsgid(idmap, inode)));
}
/**
* i_gid_update - update @inode's i_gid field
* @idmap: idmap of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Safely update @inode's i_gid field translating the vfsgid of any idmapped
* mount into the filesystem kgid.
*/
static inline void i_gid_update(struct mnt_idmap *idmap,
const struct iattr *attr,
struct inode *inode)
{
if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode),
attr->ia_vfsgid);
}
/**
* inode_fsuid_set - initialize inode's i_uid field with callers fsuid
* @inode: inode to initialize
* @idmap: idmap of the mount the inode was found from
*
* Initialize the i_uid field of @inode. If the inode was found/created via
* an idmapped mount map the caller's fsuid according to @idmap.
*/
static inline void inode_fsuid_set(struct inode *inode,
struct mnt_idmap *idmap)
{
inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode));
}
/**
* inode_fsgid_set - initialize inode's i_gid field with callers fsgid
* @inode: inode to initialize
* @idmap: idmap of the mount the inode was found from
*
* Initialize the i_gid field of @inode. If the inode was found/created via
* an idmapped mount map the caller's fsgid according to @idmap.
*/
static inline void inode_fsgid_set(struct inode *inode,
struct mnt_idmap *idmap)
{
inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode));
}
/**
* fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped
* @sb: the superblock we want a mapping in
* @idmap: idmap of the relevant mount
*
* Check whether the caller's fsuid and fsgid have a valid mapping in the
* s_user_ns of the superblock @sb. If the caller is on an idmapped mount map
* the caller's fsuid and fsgid according to the @idmap first.
*
* Return: true if fsuid and fsgid is mapped, false if not.
*/
static inline bool fsuidgid_has_mapping(struct super_block *sb,
struct mnt_idmap *idmap)
{
struct user_namespace *fs_userns = sb->s_user_ns;
kuid_t kuid;
kgid_t kgid;
kuid = mapped_fsuid(idmap, fs_userns);
if (!uid_valid(kuid))
return false;
kgid = mapped_fsgid(idmap, fs_userns);
if (!gid_valid(kgid))
return false;
return kuid_has_mapping(fs_userns, kuid) &&
kgid_has_mapping(fs_userns, kgid);
}
struct timespec64 current_time(struct inode *inode);
struct timespec64 inode_set_ctime_current(struct inode *inode);
struct timespec64 inode_set_ctime_deleg(struct inode *inode,
struct timespec64 update);
static inline time64_t inode_get_atime_sec(const struct inode *inode)
{
return inode->i_atime_sec;
}
static inline long inode_get_atime_nsec(const struct inode *inode)
{
return inode->i_atime_nsec;
}
static inline struct timespec64 inode_get_atime(const struct inode *inode)
{
struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode),
.tv_nsec = inode_get_atime_nsec(inode) };
return ts;
}
static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode,
struct timespec64 ts)
{
inode->i_atime_sec = ts.tv_sec;
inode->i_atime_nsec = ts.tv_nsec;
return ts;
}
static inline struct timespec64 inode_set_atime(struct inode *inode,
time64_t sec, long nsec)
{
struct timespec64 ts = { .tv_sec = sec,
.tv_nsec = nsec };
return inode_set_atime_to_ts(inode, ts);
}
static inline time64_t inode_get_mtime_sec(const struct inode *inode)
{
return inode->i_mtime_sec;
}
static inline long inode_get_mtime_nsec(const struct inode *inode)
{
return inode->i_mtime_nsec;
}
static inline struct timespec64 inode_get_mtime(const struct inode *inode)
{
struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode),
.tv_nsec = inode_get_mtime_nsec(inode) };
return ts;
}
static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode,
struct timespec64 ts)
{
inode->i_mtime_sec = ts.tv_sec;
inode->i_mtime_nsec = ts.tv_nsec;
return ts;
}
static inline struct timespec64 inode_set_mtime(struct inode *inode,
time64_t sec, long nsec)
{
struct timespec64 ts = { .tv_sec = sec,
.tv_nsec = nsec };
return inode_set_mtime_to_ts(inode, ts);
}
/*
* Multigrain timestamps
*
* Conditionally use fine-grained ctime and mtime timestamps when there
* are users actively observing them via getattr. The primary use-case
* for this is NFS clients that use the ctime to distinguish between
* different states of the file, and that are often fooled by multiple
* operations that occur in the same coarse-grained timer tick.
*/
#define I_CTIME_QUERIED ((u32)BIT(31))
static inline time64_t inode_get_ctime_sec(const struct inode *inode)
{
return inode->i_ctime_sec;
}
static inline long inode_get_ctime_nsec(const struct inode *inode)
{
return inode->i_ctime_nsec & ~I_CTIME_QUERIED;
}
static inline struct timespec64 inode_get_ctime(const struct inode *inode)
{
struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) };
return ts;
}
struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts);
/**
* inode_set_ctime - set the ctime in the inode
* @inode: inode in which to set the ctime
* @sec: tv_sec value to set
* @nsec: tv_nsec value to set
*
* Set the ctime in @inode to { @sec, @nsec }
*/
static inline struct timespec64 inode_set_ctime(struct inode *inode,
time64_t sec, long nsec)
{
struct timespec64 ts = { .tv_sec = sec,
.tv_nsec = nsec };
return inode_set_ctime_to_ts(inode, ts);
}
struct timespec64 simple_inode_init_ts(struct inode *inode);
/*
* Snapshotting support.
*/
/*
* These are internal functions, please use sb_start_{write,pagefault,intwrite}
* instead.
*/
static inline void __sb_end_write(struct super_block *sb, int level)
{
percpu_up_read(sb->s_writers.rw_sem + level-1);
}
static inline void __sb_start_write(struct super_block *sb, int level)
{
percpu_down_read(sb->s_writers.rw_sem + level - 1);
}
static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
{
return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
}
#define __sb_writers_acquired(sb, lev) \
percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
#define __sb_writers_release(sb, lev) \
percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_)
/**
* __sb_write_started - check if sb freeze level is held
* @sb: the super we write to
* @level: the freeze level
*
* * > 0 - sb freeze level is held
* * 0 - sb freeze level is not held
* * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
*/
static inline int __sb_write_started(const struct super_block *sb, int level)
{
return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
}
/**
* sb_write_started - check if SB_FREEZE_WRITE is held
* @sb: the super we write to
*
* May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
*/
static inline bool sb_write_started(const struct super_block *sb)
{
return __sb_write_started(sb, SB_FREEZE_WRITE);
}
/**
* sb_write_not_started - check if SB_FREEZE_WRITE is not held
* @sb: the super we write to
*
* May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
*/
static inline bool sb_write_not_started(const struct super_block *sb)
{
return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
}
/**
* file_write_started - check if SB_FREEZE_WRITE is held
* @file: the file we write to
*
* May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
* May be false positive with !S_ISREG, because file_start_write() has
* no effect on !S_ISREG.
*/
static inline bool file_write_started(const struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return sb_write_started(file_inode(file)->i_sb);
}
/**
* file_write_not_started - check if SB_FREEZE_WRITE is not held
* @file: the file we write to
*
* May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
* May be false positive with !S_ISREG, because file_start_write() has
* no effect on !S_ISREG.
*/
static inline bool file_write_not_started(const struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return sb_write_not_started(file_inode(file)->i_sb);
}
/**
* sb_end_write - drop write access to a superblock
* @sb: the super we wrote to
*
* Decrement number of writers to the filesystem. Wake up possible waiters
* wanting to freeze the filesystem.
*/
static inline void sb_end_write(struct super_block *sb)
{ __sb_end_write(sb, SB_FREEZE_WRITE);
}
/**
* sb_end_pagefault - drop write access to a superblock from a page fault
* @sb: the super we wrote to
*
* Decrement number of processes handling write page fault to the filesystem.
* Wake up possible waiters wanting to freeze the filesystem.
*/
static inline void sb_end_pagefault(struct super_block *sb)
{
__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}
/**
* sb_end_intwrite - drop write access to a superblock for internal fs purposes
* @sb: the super we wrote to
*
* Decrement fs-internal number of writers to the filesystem. Wake up possible
* waiters wanting to freeze the filesystem.
*/
static inline void sb_end_intwrite(struct super_block *sb)
{
__sb_end_write(sb, SB_FREEZE_FS);
}
/**
* sb_start_write - get write access to a superblock
* @sb: the super we write to
*
* When a process wants to write data or metadata to a file system (i.e. dirty
* a page or an inode), it should embed the operation in a sb_start_write() -
* sb_end_write() pair to get exclusion against file system freezing. This
* function increments number of writers preventing freezing. If the file
* system is already frozen, the function waits until the file system is
* thawed.
*
* Since freeze protection behaves as a lock, users have to preserve
* ordering of freeze protection and other filesystem locks. Generally,
* freeze protection should be the outermost lock. In particular, we have:
*
* sb_start_write
* -> i_mutex (write path, truncate, directory ops, ...)
* -> s_umount (freeze_super, thaw_super)
*/
static inline void sb_start_write(struct super_block *sb)
{ __sb_start_write(sb, SB_FREEZE_WRITE);
}
static inline bool sb_start_write_trylock(struct super_block *sb)
{
return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
}
/**
* sb_start_pagefault - get write access to a superblock from a page fault
* @sb: the super we write to
*
* When a process starts handling write page fault, it should embed the
* operation into sb_start_pagefault() - sb_end_pagefault() pair to get
* exclusion against file system freezing. This is needed since the page fault
* is going to dirty a page. This function increments number of running page
* faults preventing freezing. If the file system is already frozen, the
* function waits until the file system is thawed.
*
* Since page fault freeze protection behaves as a lock, users have to preserve
* ordering of freeze protection and other filesystem locks. It is advised to
* put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
* handling code implies lock dependency:
*
* mmap_lock
* -> sb_start_pagefault
*/
static inline void sb_start_pagefault(struct super_block *sb)
{
__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
}
/**
* sb_start_intwrite - get write access to a superblock for internal fs purposes
* @sb: the super we write to
*
* This is the third level of protection against filesystem freezing. It is
* free for use by a filesystem. The only requirement is that it must rank
* below sb_start_pagefault.
*
* For example filesystem can call sb_start_intwrite() when starting a
* transaction which somewhat eases handling of freezing for internal sources
* of filesystem changes (internal fs threads, discarding preallocation on file
* close, etc.).
*/
static inline void sb_start_intwrite(struct super_block *sb)
{
__sb_start_write(sb, SB_FREEZE_FS);
}
static inline bool sb_start_intwrite_trylock(struct super_block *sb)
{
return __sb_start_write_trylock(sb, SB_FREEZE_FS);
}
bool inode_owner_or_capable(struct mnt_idmap *idmap,
const struct inode *inode);
/*
* VFS helper functions..
*/
int vfs_create(struct mnt_idmap *, struct inode *,
struct dentry *, umode_t, bool);
struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *,
struct dentry *, umode_t);
int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
umode_t, dev_t);
int vfs_symlink(struct mnt_idmap *, struct inode *,
struct dentry *, const char *);
int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *,
struct dentry *, struct inode **);
int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *);
int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
struct inode **);
/**
* struct renamedata - contains all information required for renaming
* @old_mnt_idmap: idmap of the old mount the inode was found from
* @old_dir: parent of source
* @old_dentry: source
* @new_mnt_idmap: idmap of the new mount the inode was found from
* @new_dir: parent of destination
* @new_dentry: destination
* @delegated_inode: returns an inode needing a delegation break
* @flags: rename flags
*/
struct renamedata {
struct mnt_idmap *old_mnt_idmap;
struct inode *old_dir;
struct dentry *old_dentry;
struct mnt_idmap *new_mnt_idmap;
struct inode *new_dir;
struct dentry *new_dentry;
struct inode **delegated_inode;
unsigned int flags;
} __randomize_layout;
int vfs_rename(struct renamedata *);
static inline int vfs_whiteout(struct mnt_idmap *idmap,
struct inode *dir, struct dentry *dentry)
{
return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE,
WHITEOUT_DEV);
}
struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,
const struct path *parentpath,
umode_t mode, int open_flag,
const struct cred *cred);
struct file *kernel_file_open(const struct path *path, int flags,
const struct cred *cred);
int vfs_mkobj(struct dentry *, umode_t,
int (*f)(struct dentry *, umode_t, void *),
void *);
int vfs_fchown(struct file *file, uid_t user, gid_t group);
int vfs_fchmod(struct file *file, umode_t mode);
int vfs_utimes(const struct path *path, struct timespec64 *times);
int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
#else
#define compat_ptr_ioctl NULL
#endif
/*
* VFS file helper functions.
*/
void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
const struct inode *dir, umode_t mode);
extern bool may_open_dev(const struct path *path);
umode_t mode_strip_sgid(struct mnt_idmap *idmap,
const struct inode *dir, umode_t mode);
bool in_group_or_capable(struct mnt_idmap *idmap,
const struct inode *inode, vfsgid_t vfsgid);
/*
* This is the "filldir" function type, used by readdir() to let
* the kernel specify what kind of dirent layout it wants to have.
* This allows the kernel to read directories into kernel space or
* to have different dirent layouts depending on the binary type.
* Return 'true' to keep going and 'false' if there are no more entries.
*/
struct dir_context;
typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
unsigned);
struct dir_context {
filldir_t actor;
loff_t pos;
};
/*
* These flags let !MMU mmap() govern direct device mapping vs immediate
* copying more easily for MAP_PRIVATE, especially for ROM filesystems.
*
* NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE)
* NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED)
* NOMMU_MAP_READ: Can be mapped for reading
* NOMMU_MAP_WRITE: Can be mapped for writing
* NOMMU_MAP_EXEC: Can be mapped for execution
*/
#define NOMMU_MAP_COPY 0x00000001
#define NOMMU_MAP_DIRECT 0x00000008
#define NOMMU_MAP_READ VM_MAYREAD
#define NOMMU_MAP_WRITE VM_MAYWRITE
#define NOMMU_MAP_EXEC VM_MAYEXEC
#define NOMMU_VMFLAGS \
(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
/*
* These flags control the behavior of the remap_file_range function pointer.
* If it is called with len == 0 that means "remap to end of source file".
* See Documentation/filesystems/vfs.rst for more details about this call.
*
* REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
* REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request
*/
#define REMAP_FILE_DEDUP (1 << 0)
#define REMAP_FILE_CAN_SHORTEN (1 << 1)
/*
* These flags signal that the caller is ok with altering various aspects of
* the behavior of the remap operation. The changes must be made by the
* implementation; the vfs remap helper functions can take advantage of them.
* Flags in this category exist to preserve the quirky behavior of the hoisted
* btrfs clone/dedupe ioctls.
*/
#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN)
/*
* These flags control the behavior of vfs_copy_file_range().
* They are not available to the user via syscall.
*
* COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops
*/
#define COPY_FILE_SPLICE (1 << 0)
struct iov_iter;
struct io_uring_cmd;
struct offset_ctx;
typedef unsigned int __bitwise fop_flags_t;
struct file_operations {
struct module *owner;
fop_flags_t fop_flags;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
unsigned int flags);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
int (*flock) (struct file *, int, struct file_lock *);
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
void (*splice_eof)(struct file *file);
int (*setlease)(struct file *, int, struct file_lease **, void **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
void (*show_fdinfo)(struct seq_file *m, struct file *f);
#ifndef CONFIG_MMU
unsigned (*mmap_capabilities)(struct file *);
#endif
ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
loff_t, size_t, unsigned int);
loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
int (*fadvise)(struct file *, loff_t, loff_t, int);
int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *,
unsigned int poll_flags);
} __randomize_layout;
/* Supports async buffered reads */
#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0))
/* Supports async buffered writes */
#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1))
/* Supports synchronous page faults for mappings */
#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2))
/* Supports non-exclusive O_DIRECT writes from multiple threads */
#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3))
/* Contains huge pages */
#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4))
/* Treat loff_t as unsigned (e.g., /dev/mem) */
#define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5))
/* Supports asynchronous lock callbacks */
#define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6))
/* File system supports uncached read/write buffered IO */
#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7))
/* Wrap a directory iterator that needs exclusive inode access */
int wrap_directory_iterator(struct file *, struct dir_context *,
int (*) (struct file *, struct dir_context *));
#define WRAP_DIR_ITER(x) \
static int shared_##x(struct file *file , struct dir_context *ctx) \
{ return wrap_directory_iterator(file, ctx, x); }
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
int (*permission) (struct mnt_idmap *, struct inode *, int);
struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
int (*readlink) (struct dentry *, char __user *,int);
int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,
umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,
const char *);
struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,
struct dentry *, umode_t);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,
umode_t,dev_t);
int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
int (*getattr) (struct mnt_idmap *, const struct path *,
struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
umode_t create_mode);
int (*tmpfile) (struct mnt_idmap *, struct inode *,
struct file *, umode_t);
struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *,
int);
int (*set_acl)(struct mnt_idmap *, struct dentry *,
struct posix_acl *, int);
int (*fileattr_set)(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa);
int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
} ____cacheline_aligned;
static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
{
return file->f_op->mmap(file, vma);
}
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write);
int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
const struct iomap_ops *dax_read_ops);
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *count, unsigned int remap_flags);
extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
extern int vfs_dedupe_file_range(struct file *file,
struct file_dedupe_range *same);
extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
struct file *dst_file, loff_t dst_pos,
loff_t len, unsigned int remap_flags);
/**
* enum freeze_holder - holder of the freeze
* @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
* @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
* @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
*
* Indicate who the owner of the freeze or thaw request is and whether
* the freeze needs to be exclusive or can nest.
* Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
* same holder aren't allowed. It is however allowed to hold a single
* @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
* the same time. This is relied upon by some filesystems during online
* repair or similar.
*/
enum freeze_holder {
FREEZE_HOLDER_KERNEL = (1U << 0),
FREEZE_HOLDER_USERSPACE = (1U << 1),
FREEZE_MAY_NEST = (1U << 2),
};
struct super_operations {
struct inode *(*alloc_inode)(struct super_block *sb);
void (*destroy_inode)(struct inode *);
void (*free_inode)(struct inode *);
void (*dirty_inode) (struct inode *, int flags);
int (*write_inode) (struct inode *, struct writeback_control *wbc);
int (*drop_inode) (struct inode *);
void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
int (*sync_fs)(struct super_block *sb, int wait);
int (*freeze_super) (struct super_block *, enum freeze_holder who);
int (*freeze_fs) (struct super_block *);
int (*thaw_super) (struct super_block *, enum freeze_holder who);
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct dentry *);
int (*show_devname)(struct seq_file *, struct dentry *);
int (*show_path)(struct seq_file *, struct dentry *);
int (*show_stats)(struct seq_file *, struct dentry *);
#ifdef CONFIG_QUOTA
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
struct dquot __rcu **(*get_dquots)(struct inode *);
#endif
long (*nr_cached_objects)(struct super_block *,
struct shrink_control *);
long (*free_cached_objects)(struct super_block *,
struct shrink_control *);
void (*shutdown)(struct super_block *sb);
};
/*
* Inode flags - they have no relation to superblock flags now
*/
#define S_SYNC (1 << 0) /* Writes are synced at once */
#define S_NOATIME (1 << 1) /* Do not update access times */
#define S_APPEND (1 << 2) /* Append-only file */
#define S_IMMUTABLE (1 << 3) /* Immutable file */
#define S_DEAD (1 << 4) /* removed, but still open directory */
#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */
#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */
#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */
#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE (1 << 9) /* Inode is fs-internal */
#define S_IMA (1 << 10) /* Inode has an associated IMA struct */
#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */
#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */
#ifdef CONFIG_FS_DAX
#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */
#else
#define S_DAX 0 /* Make all the DAX code disappear */
#endif
#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */
#define S_CASEFOLD (1 << 15) /* Casefolded file */
#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */
#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
* flags just means all the inodes inherit those flags by default. It might be
* possible to override it selectively if you really wanted to with some
* ioctl() that is not currently implemented.
*
* Exception: SB_RDONLY is always applied to the entire file system.
*
* Unfortunately, it is possible to change a filesystems flags with it mounted
* with files in use. This means that all of the inodes will not have their
* i_flags updated. Hence, i_flags no longer inherit the superblock mount
* flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
*/
#define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg))
static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb)
#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \
((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK)
#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME)
#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE)
#ifdef CONFIG_FS_POSIX_ACL
#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL)
#else
#define IS_POSIXACL(inode) 0
#endif
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
#ifdef CONFIG_SWAP
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#else
#define IS_SWAPFILE(inode) ((void)(inode), 0U)
#endif
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
#define IS_DAX(inode) ((inode)->i_flags & S_DAX)
#define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED)
#define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD)
#define IS_VERITY(inode) ((inode)->i_flags & S_VERITY)
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap,
struct inode *inode)
{ return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode));
}
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
*kiocb = (struct kiocb) {
.ki_filp = filp,
.ki_flags = filp->f_iocb_flags,
.ki_ioprio = get_current_ioprio(),
};
}
static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
struct file *filp)
{
*kiocb = (struct kiocb) {
.ki_filp = filp,
.ki_flags = kiocb_src->ki_flags,
.ki_ioprio = kiocb_src->ki_ioprio,
.ki_pos = kiocb_src->ki_pos,
};
}
/*
* Inode state bits. Protected by inode->i_lock
*
* Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
* I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
*
* Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
* until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
* various stages of removing an inode.
*
* Two bits are used for locking and completion notification, I_NEW and I_SYNC.
*
* I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
* fdatasync() (unless I_DIRTY_DATASYNC is also set).
* Timestamp updates are the usual cause.
* I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
* these changes separately from I_DIRTY_SYNC so that we
* don't have to write inode on fdatasync() when only
* e.g. the timestamps have changed.
* I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
* I_DIRTY_TIME The inode itself has dirty timestamps, and the
* lazytime mount option is enabled. We keep track of this
* separately from I_DIRTY_SYNC in order to implement
* lazytime. This gets cleared if I_DIRTY_INODE
* (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
* I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
* in place because writeback might already be in progress
* and we don't want to lose the time update
* I_NEW Serves as both a mutex and completion notification.
* New inodes set I_NEW. If two processes both create
* the same inode, one of them will release its inode and
* wait for I_NEW to be released before returning.
* Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
* also cause waiting on I_NEW, without I_NEW actually
* being set. find_inode() uses this to prevent returning
* nearly-dead inodes.
* I_WILL_FREE Must be set when calling write_inode_now() if i_count
* is zero. I_FREEING must be set when I_WILL_FREE is
* cleared.
* I_FREEING Set when inode is about to be freed but still has dirty
* pages or buffers attached or the inode itself is still
* dirty.
* I_CLEAR Added by clear_inode(). In this state the inode is
* clean and can be destroyed. Inode keeps I_FREEING.
*
* Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
* prohibited for many purposes. iget() must wait for
* the inode to be completely released, then create it
* anew. Other functions will just ignore such inodes,
* if appropriate. I_NEW is used for waiting.
*
* I_SYNC Writeback of inode is running. The bit is set during
* data writeback, and cleared with a wakeup on the bit
* address once it is done. The bit is also used to pin
* the inode in memory for flusher thread.
*
* I_REFERENCED Marks the inode as recently references on the LRU list.
*
* I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
* synchronize competing switching instances and to tell
* wb stat updates to grab the i_pages lock. See
* inode_switch_wbs_work_fn() for details.
*
* I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
* and work dirs among overlayfs mounts.
*
* I_CREATING New object's inode in the middle of setting up.
*
* I_DONTCACHE Evict inode as soon as it is not used anymore.
*
* I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists.
* Used to detect that mark_inode_dirty() should not move
* inode between dirty lists.
*
* I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
*
* I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding
* i_count.
*
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*
* __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait
* upon. There's one free address left.
*/
#define __I_NEW 0
#define I_NEW (1 << __I_NEW)
#define __I_SYNC 1
#define I_SYNC (1 << __I_SYNC)
#define __I_LRU_ISOLATING 2
#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)
#define I_DIRTY_SYNC (1 << 3)
#define I_DIRTY_DATASYNC (1 << 4)
#define I_DIRTY_PAGES (1 << 5)
#define I_WILL_FREE (1 << 6)
#define I_FREEING (1 << 7)
#define I_CLEAR (1 << 8)
#define I_REFERENCED (1 << 9)
#define I_LINKABLE (1 << 10)
#define I_DIRTY_TIME (1 << 11)
#define I_WB_SWITCH (1 << 12)
#define I_OVL_INUSE (1 << 13)
#define I_CREATING (1 << 14)
#define I_DONTCACHE (1 << 15)
#define I_SYNC_QUEUED (1 << 16)
#define I_PINNING_NETFS_WB (1 << 17)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
__mark_inode_dirty(inode, I_DIRTY);
}
static inline void mark_inode_dirty_sync(struct inode *inode)
{
__mark_inode_dirty(inode, I_DIRTY_SYNC);
}
/*
* Returns true if the given inode itself only has dirty timestamps (its pages
* may still be dirty) and isn't currently being allocated or freed.
* Filesystems should call this if when writing an inode when lazytime is
* enabled, they want to opportunistically write the timestamps of other inodes
* located very nearby on-disk, e.g. in the same inode block. This returns true
* if the given inode is in need of such an opportunistic update. Requires
* i_lock, or at least later re-checking under i_lock.
*/
static inline bool inode_is_dirtytime_only(struct inode *inode)
{
return (inode->i_state & (I_DIRTY_TIME | I_NEW |
I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
}
extern void inc_nlink(struct inode *inode);
extern void drop_nlink(struct inode *inode);
extern void clear_nlink(struct inode *inode);
extern void set_nlink(struct inode *inode, unsigned int nlink);
static inline void inode_inc_link_count(struct inode *inode)
{
inc_nlink(inode);
mark_inode_dirty(inode);
}
static inline void inode_dec_link_count(struct inode *inode)
{
drop_nlink(inode);
mark_inode_dirty(inode);
}
enum file_time_flags {
S_ATIME = 1,
S_MTIME = 2,
S_CTIME = 4,
S_VERSION = 8,
};
extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
int inode_update_time(struct inode *inode, int flags);
static inline void file_accessed(struct file *file)
{
if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path);
}
extern int file_modified(struct file *file);
int kiocb_modified(struct kiocb *iocb);
int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
const char *name;
int fs_flags;
#define FS_REQUIRES_DEV 1
#define FS_BINARY_MOUNTDATA 2
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */
#define FS_MGTIME 64 /* FS uses multigrain timestamps */
#define FS_LBS 128 /* FS supports LBS */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_spec *parameters;
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
struct hlist_head fs_supers;
struct lock_class_key s_lock_key;
struct lock_class_key s_umount_key;
struct lock_class_key s_vfs_rename_key;
struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
struct lock_class_key invalidate_lock_key;
struct lock_class_key i_mutex_dir_key;
};
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
/**
* is_mgtime: is this inode using multigrain timestamps
* @inode: inode to test for multigrain timestamps
*
* Return true if the inode uses multigrain timestamps, false otherwise.
*/
static inline bool is_mgtime(const struct inode *inode)
{
return inode->i_opflags & IOP_MGTIME;
}
extern struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
void retire_super(struct super_block *sb);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
int set_anon_super_fc(struct super_block *s, struct fs_context *fc);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
struct super_block *sget_fc(struct fs_context *fc,
int (*test)(struct super_block *, struct fs_context *),
int (*set)(struct super_block *, struct fs_context *));
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags, void *data);
struct super_block *sget_dev(struct fs_context *fc, dev_t dev);
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) ({ \
const struct file_operations *_fops = (fops); \
(((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \
})
#define fops_put(fops) ({ \
const struct file_operations *_fops = (fops); \
if (_fops) \
module_put((_fops)->owner); \
})
/*
* This one is to be used *ONLY* from ->open() instances.
* fops must be non-NULL, pinned down *and* module dependencies
* should be sufficient to pin the caller down as well.
*/
#define replace_fops(f, fops) \
do { \
struct file *__file = (f); \
fops_put(__file->f_op); \
BUG_ON(!(__file->f_op = (fops))); \
} while(0)
extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern int vfs_statfs(const struct path *, struct kstatfs *);
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
int freeze_super(struct super_block *super, enum freeze_holder who);
int thaw_super(struct super_block *super, enum freeze_holder who);
extern __printf(2, 3)
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
extern int super_setup_bdi(struct super_block *sb);
static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len)
{
if (WARN_ON(len > sizeof(sb->s_uuid)))
len = sizeof(sb->s_uuid);
sb->s_uuid_len = len;
memcpy(&sb->s_uuid, uuid, len);
}
/* set sb sysfs name based on sb->s_bdev */
static inline void super_set_sysfs_name_bdev(struct super_block *sb)
{
snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
}
/* set sb sysfs name based on sb->s_uuid */
static inline void super_set_sysfs_name_uuid(struct super_block *sb)
{
WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
}
/* set sb sysfs name based on sb->s_id */
static inline void super_set_sysfs_name_id(struct super_block *sb)
{
strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
}
/* try to use something standard before you use this */
__printf(2, 3)
static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
va_end(args);
}
extern int current_umask(void);
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
int inode_update_timestamps(struct inode *inode, int flags);
int generic_update_time(struct inode *, int);
/* /sys/fs */
extern struct kobject *fs_kobj;
#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
/* fs/open.c */
struct audit_names;
struct filename {
const char *name; /* pointer to actual string */
const __user char *uptr; /* original userland pointer */
atomic_t refcnt;
struct audit_names *aname;
const char iname[];
};
static_assert(offsetof(struct filename, iname) % sizeof(long) == 0);
static inline struct mnt_idmap *file_mnt_idmap(const struct file *file)
{
return mnt_idmap(file->f_path.mnt);
}
/**
* is_idmapped_mnt - check whether a mount is mapped
* @mnt: the mount to check
*
* If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped.
*
* Return: true if mount is mapped, false if not.
*/
static inline bool is_idmapped_mnt(const struct vfsmount *mnt)
{
return mnt_idmap(mnt) != &nop_mnt_idmap;
}
int vfs_truncate(const struct path *, loff_t);
int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start,
unsigned int time_attrs, struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
int do_sys_open(int dfd, const char __user *filename, int flags,
umode_t mode);
extern struct file *file_open_name(struct filename *, int, umode_t);
extern struct file *filp_open(const char *, int, umode_t);
extern struct file *file_open_root(const struct path *,
const char *, int, umode_t);
static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
const char *name, int flags, umode_t mode)
{
return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
name, flags, mode);
}
struct file *dentry_open(const struct path *path, int flags,
const struct cred *creds);
struct file *dentry_open_nonotify(const struct path *path, int flags,
const struct cred *cred);
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
const struct cred *cred);
struct path *backing_file_user_path(struct file *f);
/*
* When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
* stored in ->vm_file is a backing file whose f_inode is on the underlying
* filesystem. When the mapped file path and inode number are displayed to
* user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
* path and inode number to display to the user, which is the path of the fd
* that user has requested to map and the inode number that would be returned
* by fstat() on that same fd.
*/
/* Get the path to display in /proc/<pid>/maps */
static inline const struct path *file_user_path(struct file *f)
{
if (unlikely(f->f_mode & FMODE_BACKING))
return backing_file_user_path(f);
return &f->f_path;
}
/* Get the inode whose inode number to display in /proc/<pid>/maps */
static inline const struct inode *file_user_inode(struct file *f)
{
if (unlikely(f->f_mode & FMODE_BACKING))
return d_inode(backing_file_user_path(f)->dentry);
return file_inode(f);
}
static inline struct file *file_clone_open(struct file *file)
{
return dentry_open(&file->f_path, file->f_flags, file->f_cred);
}
extern int filp_close(struct file *, fl_owner_t id);
extern struct filename *getname_flags(const char __user *, int);
extern struct filename *getname_uflags(const char __user *, int);
static inline struct filename *getname(const char __user *name)
{
return getname_flags(name, 0);
}
extern struct filename *getname_kernel(const char *);
extern struct filename *__getname_maybe_null(const char __user *);
static inline struct filename *getname_maybe_null(const char __user *name, int flags)
{
if (!(flags & AT_EMPTY_PATH))
return getname(name);
if (!name)
return NULL;
return __getname_maybe_null(name);
}
extern void putname(struct filename *name);
DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T))
static inline struct filename *refname(struct filename *name)
{
atomic_inc(&name->refcnt);
return name;
}
extern int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *));
extern int finish_no_open(struct file *file, struct dentry *dentry);
/* Helper for the simple case when original dentry is used */
static inline int finish_open_simple(struct file *file, int error)
{
if (error)
return error;
return finish_open(file, file->f_path.dentry, NULL);
}
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(void);
extern struct kmem_cache *names_cachep;
#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
extern struct super_block *blockdev_superblock;
static inline bool sb_is_blkdev_sb(struct super_block *sb)
{
return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
}
void emergency_thaw_all(void);
extern int sync_filesystem(struct super_block *);
extern const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;
/* fs/char_dev.c */
#define CHRDEV_MAJOR_MAX 512
/* Marks the bottom of the first segment of free char majors */
#define CHRDEV_MAJOR_DYN_END 234
/* Marks the top and bottom of the second segment of free char majors */
#define CHRDEV_MAJOR_DYN_EXT_START 511
#define CHRDEV_MAJOR_DYN_EXT_END 384
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name,
const struct file_operations *fops);
extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name);
extern void unregister_chrdev_region(dev_t, unsigned);
extern void chrdev_show(struct seq_file *,off_t);
static inline int register_chrdev(unsigned int major, const char *name,
const struct file_operations *fops)
{
return __register_chrdev(major, 0, 256, name, fops);
}
static inline void unregister_chrdev(unsigned int major, const char *name)
{
__unregister_chrdev(major, 0, 256, name);
}
extern void init_special_inode(struct inode *, umode_t, dev_t);
/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern bool is_bad_inode(struct inode *);
extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
loff_t lend);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
loff_t start, loff_t end);
int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
loff_t end);
static inline int file_write_and_wait(struct file *file)
{
return file_write_and_wait_range(file, 0, LLONG_MAX);
}
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
unsigned int flags);
static inline bool iocb_is_dsync(const struct kiocb *iocb)
{
return (iocb->ki_flags & IOCB_DSYNC) ||
IS_SYNC(iocb->ki_filp->f_mapping->host);
}
/*
* Sync the bytes written if this was a synchronous write. Expect ki_pos
* to already be updated for the write, and will return either the amount
* of bytes passed in, or an error if syncing the file failed.
*/
static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
{
if (iocb_is_dsync(iocb)) {
int ret = vfs_fsync_range(iocb->ki_filp,
iocb->ki_pos - count, iocb->ki_pos - 1,
(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
if (ret)
return ret;
} else if (iocb->ki_flags & IOCB_DONTCACHE) {
struct address_space *mapping = iocb->ki_filp->f_mapping;
filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
iocb->ki_pos - 1);
}
return count;
}
extern void emergency_sync(void);
extern void emergency_remount(void);
#ifdef CONFIG_BLOCK
extern int bmap(struct inode *inode, sector_t *block);
#else
static inline int bmap(struct inode *inode, sector_t *block)
{
return -EINVAL;
}
#endif
int notify_change(struct mnt_idmap *, struct dentry *,
struct iattr *, struct inode **);
int inode_permission(struct mnt_idmap *, struct inode *, int);
int generic_permission(struct mnt_idmap *, struct inode *, int);
static inline int file_permission(struct file *file, int mask)
{
return inode_permission(file_mnt_idmap(file),
file_inode(file), mask);
}
static inline int path_permission(const struct path *path, int mask)
{
return inode_permission(mnt_idmap(path->mnt),
d_inode(path->dentry), mask);
}
int __check_sticky(struct mnt_idmap *idmap, struct inode *dir,
struct inode *inode);
static inline bool execute_ok(struct inode *inode)
{
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}
static inline bool inode_wrong_type(const struct inode *inode, umode_t mode)
{
return (inode->i_mode ^ mode) & S_IFMT;
}
/**
* file_start_write - get write access to a superblock for regular file io
* @file: the file we want to write to
*
* This is a variant of sb_start_write() which is a noop on non-regualr file.
* Should be matched with a call to file_end_write().
*/
static inline void file_start_write(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
sb_start_write(file_inode(file)->i_sb);
}
static inline bool file_start_write_trylock(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return sb_start_write_trylock(file_inode(file)->i_sb);
}
/**
* file_end_write - drop write access to a superblock of a regular file
* @file: the file we wrote to
*
* Should be matched with a call to file_start_write().
*/
static inline void file_end_write(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
sb_end_write(file_inode(file)->i_sb);
}
/**
* kiocb_start_write - get write access to a superblock for async file io
* @iocb: the io context we want to submit the write with
*
* This is a variant of sb_start_write() for async io submission.
* Should be matched with a call to kiocb_end_write().
*/
static inline void kiocb_start_write(struct kiocb *iocb)
{
struct inode *inode = file_inode(iocb->ki_filp);
sb_start_write(inode->i_sb);
/*
* Fool lockdep by telling it the lock got released so that it
* doesn't complain about the held lock when we return to userspace.
*/
__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
}
/**
* kiocb_end_write - drop write access to a superblock after async file io
* @iocb: the io context we sumbitted the write with
*
* Should be matched with a call to kiocb_start_write().
*/
static inline void kiocb_end_write(struct kiocb *iocb)
{
struct inode *inode = file_inode(iocb->ki_filp);
/*
* Tell lockdep we inherited freeze protection from submission thread.
*/
__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
sb_end_write(inode->i_sb);
}
/*
* This is used for regular files where some users -- especially the
* currently executed binary in a process, previously handled via
* VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap
* read-write shared) accesses.
*
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
* deny_write_access() denies write access to a file.
* allow_write_access() re-enables write access to a file.
*
* The i_writecount field of an inode can have the following values:
* 0: no write access, no denied write access
* < 0: (-i_writecount) users that denied write access to the file.
* > 0: (i_writecount) users that have write access to the file.
*
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
* except for the cases where we don't hold i_writecount yet. Then we need to
* use {get,deny}_write_access() - these functions check the sign and refuse
* to do the change if sign is wrong.
*/
static inline int get_write_access(struct inode *inode)
{
return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline int deny_write_access(struct file *file)
{
struct inode *inode = file_inode(file);
return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline void put_write_access(struct inode * inode)
{
atomic_dec(&inode->i_writecount);
}
static inline void allow_write_access(struct file *file)
{
if (file)
atomic_inc(&file_inode(file)->i_writecount);
}
/*
* Do not prevent write to executable file when watched by pre-content events.
*
* Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at
* the time of file open and remains constant for entire lifetime of the file,
* so if pre-content watches are added post execution or removed before the end
* of the execution, it will not cause i_writecount reference leak.
*/
static inline int exe_file_deny_write_access(struct file *exe_file)
{
if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
return 0;
return deny_write_access(exe_file);
}
static inline void exe_file_allow_write_access(struct file *exe_file)
{
if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
return;
allow_write_access(exe_file);
}
static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode)
{
file->f_mode &= ~FMODE_FSNOTIFY_MASK; file->f_mode |= mode;
}
static inline bool inode_is_open_for_write(const struct inode *inode)
{
return atomic_read(&inode->i_writecount) > 0;
}
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
static inline void i_readcount_dec(struct inode *inode)
{
BUG_ON(atomic_dec_return(&inode->i_readcount) < 0);
}
static inline void i_readcount_inc(struct inode *inode)
{
atomic_inc(&inode->i_readcount);
}
#else
static inline void i_readcount_dec(struct inode *inode)
{
return;
}
static inline void i_readcount_inc(struct inode *inode)
{
return;
}
#endif
extern int do_pipe_flags(int *, int);
extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
extern struct file * open_exec(const char *);
/* fs/dcache.c -- generic fs support functions */
extern bool is_subdir(struct dentry *, struct dentry *);
extern bool path_is_under(const struct path *, const struct path *);
extern char *file_path(struct file *, char *, int);
/**
* is_dot_dotdot - returns true only if @name is "." or ".."
* @name: file name to check
* @len: length of file name, in bytes
*/
static inline bool is_dot_dotdot(const char *name, size_t len)
{
return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.'));
}
#include <linux/err.h>
/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t);
static inline int inode_init_always(struct super_block *sb, struct inode *inode)
{
return inode_init_always_gfp(sb, inode, GFP_NOFS);
}
extern void inode_init_once(struct inode *);
extern void address_space_init_once(struct address_space *mapping);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern int generic_delete_inode(struct inode *inode);
static inline int generic_drop_inode(struct inode *inode)
{
return !inode->i_nlink || inode_unhashed(inode);
}
extern void d_mark_dontcache(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
void *data);
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *),
void *data);
struct inode *iget5_locked(struct super_block *, unsigned long,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *);
struct inode *iget5_locked_rcu(struct super_block *, unsigned long,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern struct inode *find_inode_nowait(struct super_block *,
unsigned long,
int (*match)(struct inode *,
unsigned long, void *),
void *data);
extern struct inode *find_inode_rcu(struct super_block *, unsigned long,
int (*)(struct inode *, void *), void *);
extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
#else
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
#endif
extern void unlock_new_inode(struct inode *);
extern void discard_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern void evict_inodes(struct super_block *sb);
void dump_mapping(const struct address_space *);
/*
* Userspace may rely on the inode number being non-zero. For example, glibc
* simply ignores files with zero i_ino in unlink() and other places.
*
* As an additional complication, if userspace was compiled with
* _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the
* lower 32 bits, so we need to check that those aren't zero explicitly. With
* _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but
* better safe than sorry.
*/
static inline bool is_zero_ino(ino_t ino)
{
return (u32)ino == 0;
}
/*
* inode->i_lock must be held
*/
static inline void __iget(struct inode *inode)
{
atomic_inc(&inode->i_count);
}
extern void iget_failed(struct inode *);
extern void clear_inode(struct inode *);
extern void __destroy_inode(struct inode *);
struct inode *alloc_inode(struct super_block *sb);
static inline struct inode *new_inode_pseudo(struct super_block *sb)
{
return alloc_inode(sb);
}
extern struct inode *new_inode(struct super_block *sb);
extern void free_inode_nonrcu(struct inode *inode);
extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
extern int file_remove_privs_flags(struct file *file, unsigned int flags);
extern int file_remove_privs(struct file *);
int setattr_should_drop_sgid(struct mnt_idmap *idmap,
const struct inode *inode);
/*
* This must be used for allocating filesystems specific inodes to set
* up the inode reclaim context correctly.
*/
#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp)
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
static inline void insert_inode_hash(struct inode *inode)
{
__insert_inode_hash(inode, inode->i_ino);
}
extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode);
}
extern void inode_sb_list_add(struct inode *inode);
extern void inode_add_lru(struct inode *inode);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
int generic_write_checks_count(struct kiocb *iocb, loff_t *count);
extern int generic_write_check_limits(struct file *file, loff_t pos,
loff_t *count);
extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to,
ssize_t already_read);
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
ssize_t generic_perform_write(struct kiocb *, struct iov_iter *);
ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
ssize_t direct_written, ssize_t buffered_written);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags);
ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
struct iov_iter *iter);
ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
struct iov_iter *iter);
/* fs/splice.c */
ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
ssize_t copy_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
int whence, loff_t maxsize, loff_t eof);
loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence,
u64 *cookie);
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
int whence, loff_t size);
extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
int rw_verify_area(int, struct file *, const loff_t *, size_t);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
extern int stream_open(struct inode * inode, struct file * filp);
#ifdef CONFIG_BLOCK
typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
loff_t file_offset);
enum {
/* need locking between buffered and direct access */
DIO_LOCKING = 0x01,
/* filesystem does not support filling holes */
DIO_SKIP_HOLES = 0x02,
};
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
get_block_t get_block,
dio_iodone_t end_io,
int flags);
static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
struct inode *inode,
struct iov_iter *iter,
get_block_t get_block)
{
return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
}
#endif
bool inode_dio_finished(const struct inode *inode);
void inode_dio_wait(struct inode *inode);
void inode_dio_wait_interruptible(struct inode *inode);
/**
* inode_dio_begin - signal start of a direct I/O requests
* @inode: inode the direct I/O happens on
*
* This is called once we've finished processing a direct I/O request,
* and is used to wake up callers waiting for direct I/O to be quiesced.
*/
static inline void inode_dio_begin(struct inode *inode)
{
atomic_inc(&inode->i_dio_count);
}
/**
* inode_dio_end - signal finish of a direct I/O requests
* @inode: inode the direct I/O happens on
*
* This is called once we've finished processing a direct I/O request,
* and is used to wake up callers waiting for direct I/O to be quiesced.
*/
static inline void inode_dio_end(struct inode *inode)
{
if (atomic_dec_and_test(&inode->i_dio_count))
wake_up_var(&inode->i_dio_count);
}
extern void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask);
extern const struct file_operations generic_ro_fops;
#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
extern int readlink_copy(char __user *, int, const char *, int);
extern int page_readlink(struct dentry *, char __user *, int);
extern const char *page_get_link_raw(struct dentry *, struct inode *,
struct delayed_call *);
extern const char *page_get_link(struct dentry *, struct inode *,
struct delayed_call *);
extern void page_put_link(void *);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
extern void kfree_link(void *);
void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode);
void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
void generic_fill_statx_atomic_writes(struct kstat *stat,
unsigned int unit_min,
unsigned int unit_max);
extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
static inline loff_t __inode_get_bytes(struct inode *inode)
{
return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
}
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
const char *simple_get_link(struct dentry *, struct inode *,
struct delayed_call *);
extern const struct inode_operations simple_symlink_inode_operations;
extern int iterate_dir(struct file *, struct dir_context *);
int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
int flags);
int vfs_fstat(int fd, struct kstat *stat);
static inline int vfs_stat(const char __user *filename, struct kstat *stat)
{
return vfs_fstatat(AT_FDCWD, filename, stat, 0);
}
static inline int vfs_lstat(const char __user *name, struct kstat *stat)
{
return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}
extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
extern int vfs_readlink(struct dentry *, char __user *, int);
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern void drop_super(struct super_block *sb);
extern void drop_super_exclusive(struct super_block *sb);
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
extern void iterate_supers_type(struct file_system_type *,
void (*)(struct super_block *, void *), void *);
extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, struct dir_context *);
extern int simple_setattr(struct mnt_idmap *, struct dentry *,
struct iattr *);
extern int simple_getattr(struct mnt_idmap *, const struct path *,
struct kstat *, u32, unsigned int);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_open(struct inode *inode, struct file *file);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry);
extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry);
extern int simple_rename(struct mnt_idmap *, struct inode *,
struct dentry *, struct inode *, struct dentry *,
unsigned int);
extern void simple_recursive_removal(struct dentry *,
void (*callback)(struct dentry *));
extern int noop_fsync(struct file *, loff_t, loff_t, int);
extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
extern int simple_empty(struct dentry *);
extern int simple_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata);
extern const struct address_space_operations ram_aops;
extern int always_delete_dentry(const struct dentry *);
extern struct inode *alloc_anon_inode(struct super_block *);
extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
extern const struct dentry_operations simple_dentry_operations;
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
extern const struct inode_operations simple_dir_inode_operations;
extern void make_empty_dir_inode(struct inode *inode);
extern bool is_empty_dir_inode(struct inode *inode);
struct tree_descr { const char *name; const struct file_operations *ops; int mode; };
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, unsigned long,
const struct tree_descr *);
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
loff_t *ppos, const void *from, size_t available);
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
struct offset_ctx {
struct maple_tree mt;
unsigned long next_offset;
};
void simple_offset_init(struct offset_ctx *octx);
int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry);
int simple_offset_rename_exchange(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry);
void simple_offset_destroy(struct offset_ctx *octx);
extern const struct file_operations simple_offset_dir_operations;
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_check_addressable(unsigned, u64);
extern void generic_set_sb_d_ops(struct super_block *sb);
extern int generic_ci_match(const struct inode *parent,
const struct qstr *name,
const struct qstr *folded_name,
const u8 *de_name, u32 de_name_len);
#if IS_ENABLED(CONFIG_UNICODE)
int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name);
/**
* generic_ci_validate_strict_name - Check if a given name is suitable
* for a directory
*
* This functions checks if the proposed filename is valid for the
* parent directory. That means that only valid UTF-8 filenames will be
* accepted for casefold directories from filesystems created with the
* strict encoding flag. That also means that any name will be
* accepted for directories that doesn't have casefold enabled, or
* aren't being strict with the encoding.
*
* @dir: inode of the directory where the new file will be created
* @name: name of the new file
*
* Return:
* * True: if the filename is suitable for this directory. It can be
* true if a given name is not suitable for a strict encoding
* directory, but the directory being used isn't strict
* * False if the filename isn't suitable for this directory. This only
* happens when a directory is casefolded and the filesystem is strict
* about its encoding.
*/
static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name)
{
if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb))
return true;
/*
* A casefold dir must have a encoding set, unless the filesystem
* is corrupted
*/
if (WARN_ON_ONCE(!dir->i_sb->s_encoding))
return true;
return !utf8_validate(dir->i_sb->s_encoding, name);
}
#else
static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name)
{
return true;
}
#endif
static inline bool sb_has_encoding(const struct super_block *sb)
{
#if IS_ENABLED(CONFIG_UNICODE)
return !!sb->s_encoding;
#else
return false;
#endif
}
int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
unsigned int ia_valid);
int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
void setattr_copy(struct mnt_idmap *, struct inode *inode,
const struct iattr *attr);
extern int file_update_time(struct file *file);
static inline bool vma_is_dax(const struct vm_area_struct *vma)
{
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
static inline bool vma_is_fsdax(struct vm_area_struct *vma)
{
struct inode *inode;
if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file)
return false;
if (!vma_is_dax(vma))
return false;
inode = file_inode(vma->vm_file);
if (S_ISCHR(inode->i_mode))
return false; /* device-dax */
return true;
}
static inline int iocb_flags(struct file *file)
{
int res = 0;
if (file->f_flags & O_APPEND)
res |= IOCB_APPEND;
if (file->f_flags & O_DIRECT)
res |= IOCB_DIRECT;
if (file->f_flags & O_DSYNC)
res |= IOCB_DSYNC;
if (file->f_flags & __O_SYNC)
res |= IOCB_SYNC;
return res;
}
static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
int rw_type)
{
int kiocb_flags = 0;
/* make sure there's no overlap between RWF and private IOCB flags */
BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD);
if (!flags)
return 0;
if (unlikely(flags & ~RWF_SUPPORTED))
return -EOPNOTSUPP;
if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
return -EINVAL;
if (flags & RWF_NOWAIT) {
if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
return -EOPNOTSUPP;
}
if (flags & RWF_ATOMIC) {
if (rw_type != WRITE)
return -EOPNOTSUPP;
if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
return -EOPNOTSUPP;
}
if (flags & RWF_DONTCACHE) {
/* file system must support it */
if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE))
return -EOPNOTSUPP;
/* DAX mappings not supported */
if (IS_DAX(ki->ki_filp->f_mapping->host))
return -EOPNOTSUPP;
}
kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
if (flags & RWF_SYNC)
kiocb_flags |= IOCB_DSYNC;
if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
if (IS_APPEND(file_inode(ki->ki_filp)))
return -EPERM;
ki->ki_flags &= ~IOCB_APPEND;
}
ki->ki_flags |= kiocb_flags;
return 0;
}
/* Transaction based IO helpers */
/*
* An argresp is stored in an allocated page and holds the
* size of the argument or response, along with its content
*/
struct simple_transaction_argresp {
ssize_t size;
char data[];
};
#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
char *simple_transaction_get(struct file *file, const char __user *buf,
size_t size);
ssize_t simple_transaction_read(struct file *file, char __user *buf,
size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);
void simple_transaction_set(struct file *file, size_t n);
/*
* simple attribute files
*
* These attributes behave similar to those in sysfs:
*
* Writing to an attribute immediately sets a value, an open file can be
* written to multiple times.
*
* Reading from an attribute creates a buffer from the value that might get
* read with multiple read calls. When the attribute has been read
* completely, no further read calls are possible until the file is opened
* again.
*
* All attributes contain a text representation of a numeric value
* that are accessed with the get() and set() functions.
*/
#define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \
static int __fops ## _open(struct inode *inode, struct file *file) \
{ \
__simple_attr_check_format(__fmt, 0ull); \
return simple_attr_open(inode, file, __get, __set, __fmt); \
} \
static const struct file_operations __fops = { \
.owner = THIS_MODULE, \
.open = __fops ## _open, \
.release = simple_attr_release, \
.read = simple_attr_read, \
.write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \
.llseek = generic_file_llseek, \
}
#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \
DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false)
#define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \
DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true)
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
{
/* don't do anything, just let the compiler check the arguments; */
}
int simple_attr_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt);
int simple_attr_release(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos);
ssize_t simple_attr_write_signed(struct file *file, const char __user *buf,
size_t len, loff_t *ppos);
struct ctl_table;
int __init list_bdev_fs_names(char *buf, size_t size);
#define __FMODE_EXEC ((__force int) FMODE_EXEC)
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE))
static inline bool is_sxid(umode_t mode)
{
return mode & (S_ISUID | S_ISGID);
}
static inline int check_sticky(struct mnt_idmap *idmap,
struct inode *dir, struct inode *inode)
{
if (!(dir->i_mode & S_ISVTX))
return 0;
return __check_sticky(idmap, dir, inode);
}
static inline void inode_has_no_xattr(struct inode *inode)
{
if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC;
}
static inline bool is_root_inode(struct inode *inode)
{
return inode == inode->i_sb->s_root->d_inode;
}
static inline bool dir_emit(struct dir_context *ctx,
const char *name, int namelen,
u64 ino, unsigned type)
{
return ctx->actor(ctx, name, namelen, ctx->pos, ino, type);
}
static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
{
return ctx->actor(ctx, ".", 1, ctx->pos,
file->f_path.dentry->d_inode->i_ino, DT_DIR);
}
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
{
return ctx->actor(ctx, "..", 2, ctx->pos,
d_parent_ino(file->f_path.dentry), DT_DIR);
}
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
{
if (ctx->pos == 0) {
if (!dir_emit_dot(file, ctx))
return false;
ctx->pos = 1;
}
if (ctx->pos == 1) {
if (!dir_emit_dotdot(file, ctx))
return false;
ctx->pos = 2;
}
return true;
}
static inline bool dir_relax(struct inode *inode)
{
inode_unlock(inode);
inode_lock(inode);
return !IS_DEADDIR(inode);
}
static inline bool dir_relax_shared(struct inode *inode)
{
inode_unlock_shared(inode);
inode_lock_shared(inode);
return !IS_DEADDIR(inode);
}
extern bool path_noexec(const struct path *path);
extern void inode_nohighmem(struct inode *inode);
/* mm/fadvise.c */
extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
int advice);
extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
int advice);
static inline bool vfs_empty_path(int dfd, const char __user *path)
{
char c;
if (dfd < 0)
return false;
/* We now allow NULL to be used for empty path. */
if (!path)
return true;
if (unlikely(get_user(c, path)))
return false;
return !c;
}
int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter);
#endif /* _LINUX_FS_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_BACKING_DEV_DEFS_H
#define __LINUX_BACKING_DEV_DEFS_H
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/percpu_counter.h>
#include <linux/percpu-refcount.h>
#include <linux/flex_proportions.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/kref.h>
#include <linux/refcount.h>
struct page;
struct device;
struct dentry;
/*
* Bits in bdi_writeback.state
*/
enum wb_state {
WB_registered, /* bdi_register() was done */
WB_writeback_running, /* Writeback is in progress */
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
WB_start_all, /* nr_pages == 0 (all) work pending */
};
enum wb_stat_item {
WB_RECLAIMABLE,
WB_WRITEBACK,
WB_DIRTIED,
WB_WRITTEN,
NR_WB_STAT_ITEMS
};
#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
/*
* why some writeback work was initiated
*/
enum wb_reason {
WB_REASON_BACKGROUND,
WB_REASON_VMSCAN,
WB_REASON_SYNC,
WB_REASON_PERIODIC,
WB_REASON_LAPTOP_TIMER,
WB_REASON_FS_FREE_SPACE,
/*
* There is no bdi forker thread any more and works are done
* by emergency worker, however, this is TPs userland visible
* and we'll be exposing exactly the same information,
* so it has a mismatch name.
*/
WB_REASON_FORKER_THREAD,
WB_REASON_FOREIGN_FLUSH,
WB_REASON_MAX,
};
struct wb_completion {
atomic_t cnt;
wait_queue_head_t *waitq;
};
#define __WB_COMPLETION_INIT(_waitq) \
(struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) }
/*
* If one wants to wait for one or more wb_writeback_works, each work's
* ->done should be set to a wb_completion defined using the following
* macro. Once all work items are issued with wb_queue_work(), the caller
* can wait for the completion of all using wb_wait_for_completion(). Work
* items which are waited upon aren't freed automatically on completion.
*/
#define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq)
#define DEFINE_WB_COMPLETION(cmpl, bdi) \
struct wb_completion cmpl = WB_COMPLETION_INIT(bdi)
/*
* Each wb (bdi_writeback) can perform writeback operations, is measured
* and throttled, independently. Without cgroup writeback, each bdi
* (bdi_writeback) is served by its embedded bdi->wb.
*
* On the default hierarchy, blkcg implicitly enables memcg. This allows
* using memcg's page ownership for attributing writeback IOs, and every
* memcg - blkcg combination can be served by its own wb by assigning a
* dedicated wb to each memcg, which enables isolation across different
* cgroups and propagation of IO back pressure down from the IO layer upto
* the tasks which are generating the dirty pages to be written back.
*
* A cgroup wb is indexed on its bdi by the ID of the associated memcg,
* refcounted with the number of inodes attached to it, and pins the memcg
* and the corresponding blkcg. As the corresponding blkcg for a memcg may
* change as blkcg is disabled and enabled higher up in the hierarchy, a wb
* is tested for blkcg after lookup and removed from index on mismatch so
* that a new wb for the combination can be created.
*
* Each bdi_writeback that is not embedded into the backing_dev_info must hold
* a reference to the parent backing_dev_info. See cgwb_create() for details.
*/
struct bdi_writeback {
struct backing_dev_info *bdi; /* our parent bdi */
unsigned long state; /* Always use atomic bitops on this */
unsigned long last_old_flush; /* last old data flush */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
struct list_head b_dirty_time; /* time stamps are dirty */
spinlock_t list_lock; /* protects the b_* lists */
atomic_t writeback_inodes; /* number of inodes under writeback */
struct percpu_counter stat[NR_WB_STAT_ITEMS];
unsigned long bw_time_stamp; /* last time write bw is updated */
unsigned long dirtied_stamp;
unsigned long written_stamp; /* pages written at bw_time_stamp */
unsigned long write_bandwidth; /* the estimated write bandwidth */
unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */
/*
* The base dirty throttle rate, re-calculated on every 200ms.
* All the bdi tasks' dirty rate will be curbed under it.
* @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
* in small steps and is much more smooth/stable than the latter.
*/
unsigned long dirty_ratelimit;
unsigned long balanced_dirty_ratelimit;
struct fprop_local_percpu completions;
int dirty_exceeded;
enum wb_reason start_all_reason;
spinlock_t work_lock; /* protects work_list & dwork scheduling */
struct list_head work_list;
struct delayed_work dwork; /* work item used for writeback */
struct delayed_work bw_dwork; /* work item used for bandwidth estimate */
struct list_head bdi_node; /* anchored at bdi->wb_list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct percpu_ref refcnt; /* used only for !root wb's */
struct fprop_local_percpu memcg_completions;
struct cgroup_subsys_state *memcg_css; /* the associated memcg */
struct cgroup_subsys_state *blkcg_css; /* and blkcg */
struct list_head memcg_node; /* anchored at memcg->cgwb_list */
struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */
struct list_head b_attached; /* attached inodes, protected by list_lock */
struct list_head offline_node; /* anchored at offline_cgwbs */
union {
struct work_struct release_work;
struct rcu_head rcu;
};
#endif
};
struct backing_dev_info {
u64 id;
struct rb_node rb_node; /* keyed by ->id */
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
unsigned long io_pages; /* max allowed IO size */
struct kref refcnt; /* Reference counter for the structure */
unsigned int capabilities; /* Device capabilities */
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
/*
* Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are
* any dirty wbs, which is depended upon by bdi_has_dirty().
*/
atomic_long_t tot_write_bandwidth;
/*
* Jiffies when last process was dirty throttled on this bdi. Used by
* blk-wbt.
*/
unsigned long last_bdp_sleep;
struct bdi_writeback wb; /* the root writeback info for this bdi */
struct list_head wb_list; /* list of all wbs */
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
#endif
wait_queue_head_t wb_waitq;
struct device *dev;
char dev_name[64];
struct device *owner;
struct timer_list laptop_mode_wb_timer;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
#endif
};
struct wb_lock_cookie {
bool locked;
unsigned long flags;
};
#ifdef CONFIG_CGROUP_WRITEBACK
/**
* wb_tryget - try to increment a wb's refcount
* @wb: bdi_writeback to get
*/
static inline bool wb_tryget(struct bdi_writeback *wb)
{
if (wb != &wb->bdi->wb)
return percpu_ref_tryget(&wb->refcnt);
return true;
}
/**
* wb_get - increment a wb's refcount
* @wb: bdi_writeback to get
*/
static inline void wb_get(struct bdi_writeback *wb)
{ if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt);
}
/**
* wb_put - decrement a wb's refcount
* @wb: bdi_writeback to put
* @nr: number of references to put
*/
static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr)
{
if (WARN_ON_ONCE(!wb->bdi)) {
/*
* A driver bug might cause a file to be removed before bdi was
* initialized.
*/
return;
}
if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr);
}
/**
* wb_put - decrement a wb's refcount
* @wb: bdi_writeback to put
*/
static inline void wb_put(struct bdi_writeback *wb)
{
wb_put_many(wb, 1);
}
/**
* wb_dying - is a wb dying?
* @wb: bdi_writeback of interest
*
* Returns whether @wb is unlinked and being drained.
*/
static inline bool wb_dying(struct bdi_writeback *wb)
{
return percpu_ref_is_dying(&wb->refcnt);
}
#else /* CONFIG_CGROUP_WRITEBACK */
static inline bool wb_tryget(struct bdi_writeback *wb)
{
return true;
}
static inline void wb_get(struct bdi_writeback *wb)
{
}
static inline void wb_put(struct bdi_writeback *wb)
{
}
static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr)
{
}
static inline bool wb_dying(struct bdi_writeback *wb)
{
return false;
}
#endif /* CONFIG_CGROUP_WRITEBACK */
#endif /* __LINUX_BACKING_DEV_DEFS_H */
/* CPU control.
* (C) 2001, 2002, 2003, 2004 Rusty Russell
*
* This code is licenced under the GPL.
*/
#include <linux/sched/mm.h>
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/isolation.h>
#include <linux/sched/task.h>
#include <linux/sched/smt.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/bug.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
#include <linux/lockdep.h>
#include <linux/tick.h>
#include <linux/irq.h>
#include <linux/nmi.h>
#include <linux/smpboot.h>
#include <linux/relay.h>
#include <linux/slab.h>
#include <linux/scs.h>
#include <linux/percpu-rwsem.h>
#include <linux/cpuset.h>
#include <linux/random.h>
#include <linux/cc_platform.h>
#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>
#include "smpboot.h"
/**
* struct cpuhp_cpu_state - Per cpu hotplug state storage
* @state: The current cpu state
* @target: The target state
* @fail: Current CPU hotplug callback state
* @thread: Pointer to the hotplug thread
* @should_run: Thread should execute
* @rollback: Perform a rollback
* @single: Single callback invocation
* @bringup: Single callback bringup or teardown selector
* @node: Remote CPU node; for multi-instance, do a
* single entry callback for install/remove
* @last: For multi-instance rollback, remember how far we got
* @cb_state: The state for a single callback (install/uninstall)
* @result: Result of the operation
* @ap_sync_state: State for AP synchronization
* @done_up: Signal completion to the issuer of the task for cpu-up
* @done_down: Signal completion to the issuer of the task for cpu-down
*/
struct cpuhp_cpu_state {
enum cpuhp_state state;
enum cpuhp_state target;
enum cpuhp_state fail;
#ifdef CONFIG_SMP
struct task_struct *thread;
bool should_run;
bool rollback;
bool single;
bool bringup;
struct hlist_node *node;
struct hlist_node *last;
enum cpuhp_state cb_state;
int result;
atomic_t ap_sync_state;
struct completion done_up;
struct completion done_down;
#endif
};
static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
.fail = CPUHP_INVALID,
};
#ifdef CONFIG_SMP
cpumask_t cpus_booted_once_mask;
#endif
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
static struct lockdep_map cpuhp_state_up_map =
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
static struct lockdep_map cpuhp_state_down_map =
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
static inline void cpuhp_lock_acquire(bool bringup)
{
lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
static inline void cpuhp_lock_release(bool bringup)
{
lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
#else
static inline void cpuhp_lock_acquire(bool bringup) { }
static inline void cpuhp_lock_release(bool bringup) { }
#endif
/**
* struct cpuhp_step - Hotplug state machine step
* @name: Name of the step
* @startup: Startup function of the step
* @teardown: Teardown function of the step
* @cant_stop: Bringup/teardown can't be stopped at this step
* @multi_instance: State has multiple instances which get added afterwards
*/
struct cpuhp_step {
const char *name;
union {
int (*single)(unsigned int cpu);
int (*multi)(unsigned int cpu,
struct hlist_node *node);
} startup;
union {
int (*single)(unsigned int cpu);
int (*multi)(unsigned int cpu,
struct hlist_node *node);
} teardown;
/* private: */
struct hlist_head list;
/* public: */
bool cant_stop;
bool multi_instance;
};
static DEFINE_MUTEX(cpuhp_state_mutex);
static struct cpuhp_step cpuhp_hp_states[];
static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
{
return cpuhp_hp_states + state;
}
static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step)
{
return bringup ? !step->startup.single : !step->teardown.single;
}
/**
* cpuhp_invoke_callback - Invoke the callbacks for a given state
* @cpu: The cpu for which the callback should be invoked
* @state: The state to do callbacks for
* @bringup: True if the bringup callback should be invoked
* @node: For multi-instance, do a single entry callback for install/remove
* @lastp: For multi-instance rollback, remember how far we got
*
* Called from cpu hotplug and from the state register machinery.
*
* Return: %0 on success or a negative errno code
*/
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
bool bringup, struct hlist_node *node,
struct hlist_node **lastp)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
struct cpuhp_step *step = cpuhp_get_step(state);
int (*cbm)(unsigned int cpu, struct hlist_node *node);
int (*cb)(unsigned int cpu);
int ret, cnt;
if (st->fail == state) {
st->fail = CPUHP_INVALID;
return -EAGAIN;
}
if (cpuhp_step_empty(bringup, step)) {
WARN_ON_ONCE(1);
return 0;
}
if (!step->multi_instance) {
WARN_ON_ONCE(lastp && *lastp);
cb = bringup ? step->startup.single : step->teardown.single;
trace_cpuhp_enter(cpu, st->target, state, cb);
ret = cb(cpu);
trace_cpuhp_exit(cpu, st->state, state, ret);
return ret;
}
cbm = bringup ? step->startup.multi : step->teardown.multi;
/* Single invocation for instance add/remove */
if (node) {
WARN_ON_ONCE(lastp && *lastp);
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
return ret;
}
/* State transition. Invoke on all instances */
cnt = 0;
hlist_for_each(node, &step->list) {
if (lastp && node == *lastp)
break;
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
if (ret) {
if (!lastp)
goto err;
*lastp = node;
return ret;
}
cnt++;
}
if (lastp)
*lastp = NULL;
return 0;
err:
/* Rollback the instances if one failed */
cbm = !bringup ? step->startup.multi : step->teardown.multi;
if (!cbm)
return ret;
hlist_for_each(node, &step->list) {
if (!cnt--)
break;
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
/*
* Rollback must not fail,
*/
WARN_ON_ONCE(ret);
}
return ret;
}
#ifdef CONFIG_SMP
static bool cpuhp_is_ap_state(enum cpuhp_state state)
{
/*
* The extra check for CPUHP_TEARDOWN_CPU is only for documentation
* purposes as that state is handled explicitly in cpu_down.
*/
return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
}
static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
struct completion *done = bringup ? &st->done_up : &st->done_down;
wait_for_completion(done);
}
static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
struct completion *done = bringup ? &st->done_up : &st->done_down;
complete(done);
}
/*
* The former STARTING/DYING states, ran with IRQs disabled and must not fail.
*/
static bool cpuhp_is_atomic_state(enum cpuhp_state state)
{
return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
}
/* Synchronization state management */
enum cpuhp_sync_state {
SYNC_STATE_DEAD,
SYNC_STATE_KICKED,
SYNC_STATE_SHOULD_DIE,
SYNC_STATE_ALIVE,
SYNC_STATE_SHOULD_ONLINE,
SYNC_STATE_ONLINE,
};
#ifdef CONFIG_HOTPLUG_CORE_SYNC
/**
* cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown
* @state: The synchronization state to set
*
* No synchronization point. Just update of the synchronization state, but implies
* a full barrier so that the AP changes are visible before the control CPU proceeds.
*/
static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state)
{
atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state);
(void)atomic_xchg(st, state);
}
void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); }
static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state,
enum cpuhp_sync_state next_state)
{
atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
ktime_t now, end, start = ktime_get();
int sync;
end = start + 10ULL * NSEC_PER_SEC;
sync = atomic_read(st);
while (1) {
if (sync == state) {
if (!atomic_try_cmpxchg(st, &sync, next_state))
continue;
return true;
}
now = ktime_get();
if (now > end) {
/* Timeout. Leave the state unchanged */
return false;
} else if (now - start < NSEC_PER_MSEC) {
/* Poll for one millisecond */
arch_cpuhp_sync_state_poll();
} else {
usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC);
}
sync = atomic_read(st);
}
return true;
}
#else /* CONFIG_HOTPLUG_CORE_SYNC */
static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { }
#endif /* !CONFIG_HOTPLUG_CORE_SYNC */
#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD
/**
* cpuhp_ap_report_dead - Update synchronization state to DEAD
*
* No synchronization point. Just update of the synchronization state.
*/
void cpuhp_ap_report_dead(void)
{
cpuhp_ap_update_sync_state(SYNC_STATE_DEAD);
}
void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { }
/*
* Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down
* because the AP cannot issue complete() at this stage.
*/
static void cpuhp_bp_sync_dead(unsigned int cpu)
{
atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
int sync = atomic_read(st);
do {
/* CPU can have reported dead already. Don't overwrite that! */
if (sync == SYNC_STATE_DEAD)
break;
} while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE));
if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) {
/* CPU reached dead state. Invoke the cleanup function */
arch_cpuhp_cleanup_dead_cpu(cpu);
return;
}
/* No further action possible. Emit message and give up. */
pr_err("CPU%u failed to report dead state\n", cpu);
}
#else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */
static inline void cpuhp_bp_sync_dead(unsigned int cpu) { }
#endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */
#ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL
/**
* cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive
*
* Updates the AP synchronization state to SYNC_STATE_ALIVE and waits
* for the BP to release it.
*/
void cpuhp_ap_sync_alive(void)
{
atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state);
cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE);
/* Wait for the control CPU to release it. */
while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE)
cpu_relax();
}
static bool cpuhp_can_boot_ap(unsigned int cpu)
{
atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu);
int sync = atomic_read(st);
again:
switch (sync) {
case SYNC_STATE_DEAD:
/* CPU is properly dead */
break;
case SYNC_STATE_KICKED:
/* CPU did not come up in previous attempt */
break;
case SYNC_STATE_ALIVE:
/* CPU is stuck cpuhp_ap_sync_alive(). */
break;
default:
/* CPU failed to report online or dead and is in limbo state. */
return false;
}
/* Prepare for booting */
if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED))
goto again;
return true;
}
void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { }
/*
* Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up
* because the AP cannot issue complete() so early in the bringup.
*/
static int cpuhp_bp_sync_alive(unsigned int cpu)
{
int ret = 0;
if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL))
return 0;
if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) {
pr_err("CPU%u failed to report alive state\n", cpu);
ret = -EIO;
}
/* Let the architecture cleanup the kick alive mechanics. */
arch_cpuhp_cleanup_kick_cpu(cpu);
return ret;
}
#else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */
static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; }
static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; }
#endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
bool cpuhp_tasks_frozen;
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
/*
* The following two APIs (cpu_maps_update_begin/done) must be used when
* attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
/*
* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
* Should always be manipulated under cpu_add_remove_lock
*/
static int cpu_hotplug_disabled;
#ifdef CONFIG_HOTPLUG_CPU
DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
static bool cpu_hotplug_offline_disabled __ro_after_init;
void cpus_read_lock(void)
{ percpu_down_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_lock);
int cpus_read_trylock(void)
{
return percpu_down_read_trylock(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_trylock);
void cpus_read_unlock(void)
{ percpu_up_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_unlock);
void cpus_write_lock(void)
{
percpu_down_write(&cpu_hotplug_lock);
}
void cpus_write_unlock(void)
{
percpu_up_write(&cpu_hotplug_lock);
}
void lockdep_assert_cpus_held(void)
{
/*
* We can't have hotplug operations before userspace starts running,
* and some init codepaths will knowingly not take the hotplug lock.
* This is all valid, so mute lockdep until it makes sense to report
* unheld locks.
*/
if (system_state < SYSTEM_RUNNING)
return;
percpu_rwsem_assert_held(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(lockdep_assert_cpus_held);
#ifdef CONFIG_LOCKDEP
int lockdep_is_cpus_held(void)
{
return percpu_rwsem_is_held(&cpu_hotplug_lock);
}
#endif
static void lockdep_acquire_cpus_lock(void)
{
rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_);
}
static void lockdep_release_cpus_lock(void)
{
rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_);
}
/* Declare CPU offlining not supported */
void cpu_hotplug_disable_offlining(void)
{
cpu_maps_update_begin();
cpu_hotplug_offline_disabled = true;
cpu_maps_update_done();
}
/*
* Wait for currently running CPU hotplug operations to complete (if any) and
* disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
* the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
* hotplug path before performing hotplug operations. So acquiring that lock
* guarantees mutual exclusion from any currently running hotplug operations.
*/
void cpu_hotplug_disable(void)
{
cpu_maps_update_begin();
cpu_hotplug_disabled++;
cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
static void __cpu_hotplug_enable(void)
{
if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
return;
cpu_hotplug_disabled--;
}
void cpu_hotplug_enable(void)
{
cpu_maps_update_begin();
__cpu_hotplug_enable();
cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#else
static void lockdep_acquire_cpus_lock(void)
{
}
static void lockdep_release_cpus_lock(void)
{
}
#endif /* CONFIG_HOTPLUG_CPU */
/*
* Architectures that need SMT-specific errata handling during SMT hotplug
* should override this.
*/
void __weak arch_smt_update(void) { }
#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
static unsigned int cpu_smt_max_threads __ro_after_init;
unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX;
void __init cpu_smt_disable(bool force)
{
if (!cpu_smt_possible())
return;
if (force) {
pr_info("SMT: Force disabled\n");
cpu_smt_control = CPU_SMT_FORCE_DISABLED;
} else {
pr_info("SMT: disabled\n");
cpu_smt_control = CPU_SMT_DISABLED;
}
cpu_smt_num_threads = 1;
}
/*
* The decision whether SMT is supported can only be done after the full
* CPU identification. Called from architecture code.
*/
void __init cpu_smt_set_num_threads(unsigned int num_threads,
unsigned int max_threads)
{
WARN_ON(!num_threads || (num_threads > max_threads));
if (max_threads == 1)
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
cpu_smt_max_threads = max_threads;
/*
* If SMT has been disabled via the kernel command line or SMT is
* not supported, set cpu_smt_num_threads to 1 for consistency.
* If enabled, take the architecture requested number of threads
* to bring up into account.
*/
if (cpu_smt_control != CPU_SMT_ENABLED)
cpu_smt_num_threads = 1;
else if (num_threads < cpu_smt_num_threads)
cpu_smt_num_threads = num_threads;
}
static int __init smt_cmdline_disable(char *str)
{
cpu_smt_disable(str && !strcmp(str, "force"));
return 0;
}
early_param("nosmt", smt_cmdline_disable);
/*
* For Archicture supporting partial SMT states check if the thread is allowed.
* Otherwise this has already been checked through cpu_smt_max_threads when
* setting the SMT level.
*/
static inline bool cpu_smt_thread_allowed(unsigned int cpu)
{
#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC
return topology_smt_thread_allowed(cpu);
#else
return true;
#endif
}
static inline bool cpu_bootable(unsigned int cpu)
{
if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
return true;
/* All CPUs are bootable if controls are not configured */
if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED)
return true;
/* All CPUs are bootable if CPU is not SMT capable */
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
return true;
if (topology_is_primary_thread(cpu))
return true;
/*
* On x86 it's required to boot all logical CPUs at least once so
* that the init code can get a chance to set CR4.MCE on each
* CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any
* core will shutdown the machine.
*/
return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
}
/* Returns true if SMT is supported and not forcefully (irreversibly) disabled */
bool cpu_smt_possible(void)
{
return cpu_smt_control != CPU_SMT_FORCE_DISABLED &&
cpu_smt_control != CPU_SMT_NOT_SUPPORTED;
}
EXPORT_SYMBOL_GPL(cpu_smt_possible);
#else
static inline bool cpu_bootable(unsigned int cpu) { return true; }
#endif
static inline enum cpuhp_state
cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
bool bringup = st->state < target;
st->rollback = false;
st->last = NULL;
st->target = target;
st->single = false;
st->bringup = bringup;
if (cpu_dying(cpu) != !bringup)
set_cpu_dying(cpu, !bringup);
return prev_state;
}
static inline void
cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st,
enum cpuhp_state prev_state)
{
bool bringup = !st->bringup;
st->target = prev_state;
/*
* Already rolling back. No need invert the bringup value or to change
* the current state.
*/
if (st->rollback)
return;
st->rollback = true;
/*
* If we have st->last we need to undo partial multi_instance of this
* state first. Otherwise start undo at the previous state.
*/
if (!st->last) {
if (st->bringup)
st->state--;
else
st->state++;
}
st->bringup = bringup;
if (cpu_dying(cpu) != !bringup)
set_cpu_dying(cpu, !bringup);
}
/* Regular hotplug invocation of the AP hotplug thread */
static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
{
if (!st->single && st->state == st->target)
return;
st->result = 0;
/*
* Make sure the above stores are visible before should_run becomes
* true. Paired with the mb() above in cpuhp_thread_fun()
*/
smp_mb();
st->should_run = true;
wake_up_process(st->thread);
wait_for_ap_thread(st, st->bringup);
}
static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
enum cpuhp_state prev_state;
int ret;
prev_state = cpuhp_set_state(cpu, st, target);
__cpuhp_kick_ap(st);
if ((ret = st->result)) {
cpuhp_reset_state(cpu, st, prev_state);
__cpuhp_kick_ap(st);
}
return ret;
}
static int bringup_wait_for_ap_online(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
wait_for_ap_thread(st, true);
if (WARN_ON_ONCE((!cpu_online(cpu))))
return -ECANCELED;
/* Unpark the hotplug thread of the target cpu */
kthread_unpark(st->thread);
/*
* SMT soft disabling on X86 requires to bring the CPU out of the
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
* CPU marked itself as booted_once in notify_cpu_starting() so the
* cpu_bootable() check will now return false if this is not the
* primary sibling.
*/
if (!cpu_bootable(cpu))
return -ECANCELED;
return 0;
}
#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP
static int cpuhp_kick_ap_alive(unsigned int cpu)
{
if (!cpuhp_can_boot_ap(cpu))
return -EAGAIN;
return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu));
}
static int cpuhp_bringup_ap(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int ret;
/*
* Some architectures have to walk the irq descriptors to
* setup the vector space for the cpu which comes online.
* Prevent irq alloc/free across the bringup.
*/
irq_lock_sparse();
ret = cpuhp_bp_sync_alive(cpu);
if (ret)
goto out_unlock;
ret = bringup_wait_for_ap_online(cpu);
if (ret)
goto out_unlock;
irq_unlock_sparse();
if (st->target <= CPUHP_AP_ONLINE_IDLE)
return 0;
return cpuhp_kick_ap(cpu, st, st->target);
out_unlock:
irq_unlock_sparse();
return ret;
}
#else
static int bringup_cpu(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
struct task_struct *idle = idle_thread_get(cpu);
int ret;
if (!cpuhp_can_boot_ap(cpu))
return -EAGAIN;
/*
* Some architectures have to walk the irq descriptors to
* setup the vector space for the cpu which comes online.
*
* Prevent irq alloc/free across the bringup by acquiring the
* sparse irq lock. Hold it until the upcoming CPU completes the
* startup in cpuhp_online_idle() which allows to avoid
* intermediate synchronization points in the architecture code.
*/
irq_lock_sparse();
ret = __cpu_up(cpu, idle);
if (ret)
goto out_unlock;
ret = cpuhp_bp_sync_alive(cpu);
if (ret)
goto out_unlock;
ret = bringup_wait_for_ap_online(cpu);
if (ret)
goto out_unlock;
irq_unlock_sparse();
if (st->target <= CPUHP_AP_ONLINE_IDLE)
return 0;
return cpuhp_kick_ap(cpu, st, st->target);
out_unlock:
irq_unlock_sparse();
return ret;
}
#endif
static int finish_cpu(unsigned int cpu)
{
struct task_struct *idle = idle_thread_get(cpu);
struct mm_struct *mm = idle->active_mm;
/*
* sched_force_init_mm() ensured the use of &init_mm,
* drop that refcount now that the CPU has stopped.
*/
WARN_ON(mm != &init_mm);
idle->active_mm = NULL;
mmdrop_lazy_tlb(mm);
return 0;
}
/*
* Hotplug state machine related functions
*/
/*
* Get the next state to run. Empty ones will be skipped. Returns true if a
* state must be run.
*
* st->state will be modified ahead of time, to match state_to_run, as if it
* has already ran.
*/
static bool cpuhp_next_state(bool bringup,
enum cpuhp_state *state_to_run,
struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
do {
if (bringup) {
if (st->state >= target)
return false;
*state_to_run = ++st->state;
} else {
if (st->state <= target)
return false;
*state_to_run = st->state--;
}
if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run)))
break;
} while (true);
return true;
}
static int __cpuhp_invoke_callback_range(bool bringup,
unsigned int cpu,
struct cpuhp_cpu_state *st,
enum cpuhp_state target,
bool nofail)
{
enum cpuhp_state state;
int ret = 0;
while (cpuhp_next_state(bringup, &state, st, target)) {
int err;
err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL);
if (!err)
continue;
if (nofail) {
pr_warn("CPU %u %s state %s (%d) failed (%d)\n",
cpu, bringup ? "UP" : "DOWN",
cpuhp_get_step(st->state)->name,
st->state, err);
ret = -1;
} else {
ret = err;
break;
}
}
return ret;
}
static inline int cpuhp_invoke_callback_range(bool bringup,
unsigned int cpu,
struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false);
}
static inline void cpuhp_invoke_callback_range_nofail(bool bringup,
unsigned int cpu,
struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
__cpuhp_invoke_callback_range(bringup, cpu, st, target, true);
}
static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
{
if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
return true;
/*
* When CPU hotplug is disabled, then taking the CPU down is not
* possible because takedown_cpu() and the architecture and
* subsystem specific mechanisms are not available. So the CPU
* which would be completely unplugged again needs to stay around
* in the current state.
*/
return st->state <= CPUHP_BRINGUP_CPU;
}
static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
int ret = 0;
ret = cpuhp_invoke_callback_range(true, cpu, st, target);
if (ret) {
pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n",
ret, cpu, cpuhp_get_step(st->state)->name,
st->state);
cpuhp_reset_state(cpu, st, prev_state);
if (can_rollback_cpu(st))
WARN_ON(cpuhp_invoke_callback_range(false, cpu, st,
prev_state));
}
return ret;
}
/*
* The cpu hotplug threads manage the bringup and teardown of the cpus
*/
static int cpuhp_should_run(unsigned int cpu)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
return st->should_run;
}
/*
* Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
* callbacks when a state gets [un]installed at runtime.
*
* Each invocation of this function by the smpboot thread does a single AP
* state callback.
*
* It has 3 modes of operation:
* - single: runs st->cb_state
* - up: runs ++st->state, while st->state < st->target
* - down: runs st->state--, while st->state > st->target
*
* When complete or on error, should_run is cleared and the completion is fired.
*/
static void cpuhp_thread_fun(unsigned int cpu)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
bool bringup = st->bringup;
enum cpuhp_state state;
if (WARN_ON_ONCE(!st->should_run))
return;
/*
* ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
* that if we see ->should_run we also see the rest of the state.
*/
smp_mb();
/*
* The BP holds the hotplug lock, but we're now running on the AP,
* ensure that anybody asserting the lock is held, will actually find
* it so.
*/
lockdep_acquire_cpus_lock();
cpuhp_lock_acquire(bringup);
if (st->single) {
state = st->cb_state;
st->should_run = false;
} else {
st->should_run = cpuhp_next_state(bringup, &state, st, st->target);
if (!st->should_run)
goto end;
}
WARN_ON_ONCE(!cpuhp_is_ap_state(state));
if (cpuhp_is_atomic_state(state)) {
local_irq_disable();
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
local_irq_enable();
/*
* STARTING/DYING must not fail!
*/
WARN_ON_ONCE(st->result);
} else {
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
}
if (st->result) {
/*
* If we fail on a rollback, we're up a creek without no
* paddle, no way forward, no way back. We loose, thanks for
* playing.
*/
WARN_ON_ONCE(st->rollback);
st->should_run = false;
}
end:
cpuhp_lock_release(bringup);
lockdep_release_cpus_lock();
if (!st->should_run)
complete_ap_thread(st, bringup);
}
/* Invoke a single callback on a remote cpu */
static int
cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
struct hlist_node *node)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int ret;
if (!cpu_online(cpu))
return 0;
cpuhp_lock_acquire(false);
cpuhp_lock_release(false);
cpuhp_lock_acquire(true);
cpuhp_lock_release(true);
/*
* If we are up and running, use the hotplug thread. For early calls
* we invoke the thread function directly.
*/
if (!st->thread)
return cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
st->rollback = false;
st->last = NULL;
st->node = node;
st->bringup = bringup;
st->cb_state = state;
st->single = true;
__cpuhp_kick_ap(st);
/*
* If we failed and did a partial, do a rollback.
*/
if ((ret = st->result) && st->last) {
st->rollback = true;
st->bringup = !bringup;
__cpuhp_kick_ap(st);
}
/*
* Clean up the leftovers so the next hotplug operation wont use stale
* data.
*/
st->node = st->last = NULL;
return ret;
}
static int cpuhp_kick_ap_work(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state prev_state = st->state;
int ret;
cpuhp_lock_acquire(false);
cpuhp_lock_release(false);
cpuhp_lock_acquire(true);
cpuhp_lock_release(true);
trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
ret = cpuhp_kick_ap(cpu, st, st->target);
trace_cpuhp_exit(cpu, st->state, prev_state, ret);
return ret;
}
static struct smp_hotplug_thread cpuhp_threads = {
.store = &cpuhp_state.thread,
.thread_should_run = cpuhp_should_run,
.thread_fn = cpuhp_thread_fun,
.thread_comm = "cpuhp/%u",
.selfparking = true,
};
static __init void cpuhp_init_state(void)
{
struct cpuhp_cpu_state *st;
int cpu;
for_each_possible_cpu(cpu) {
st = per_cpu_ptr(&cpuhp_state, cpu);
init_completion(&st->done_up);
init_completion(&st->done_down);
}
}
void __init cpuhp_threads_init(void)
{
cpuhp_init_state();
BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
kthread_unpark(this_cpu_read(cpuhp_state.thread));
}
#ifdef CONFIG_HOTPLUG_CPU
#ifndef arch_clear_mm_cpumask_cpu
#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
#endif
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
*
* This function walks all processes, finds a valid mm struct for each one and
* then clears a corresponding bit in mm's cpumask. While this all sounds
* trivial, there are various non-obvious corner cases, which this function
* tries to solve in a safe manner.
*
* Also note that the function uses a somewhat relaxed locking scheme, so it may
* be called only for an already offlined CPU.
*/
void clear_tasks_mm_cpumask(int cpu)
{
struct task_struct *p;
/*
* This function is called after the cpu is taken down and marked
* offline, so its not like new tasks will ever get this cpu set in
* their mm mask. -- Peter Zijlstra
* Thus, we may use rcu_read_lock() here, instead of grabbing
* full-fledged tasklist_lock.
*/
WARN_ON(cpu_online(cpu));
rcu_read_lock();
for_each_process(p) {
struct task_struct *t;
/*
* Main thread might exit, but other threads may still have
* a valid mm. Find one.
*/
t = find_lock_task_mm(p);
if (!t)
continue;
arch_clear_mm_cpumask_cpu(cpu, t->mm);
task_unlock(t);
}
rcu_read_unlock();
}
/* Take this CPU down. */
static int take_cpu_down(void *_param)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
int err, cpu = smp_processor_id();
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
if (err < 0)
return err;
/*
* Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going
* down, that the current state is CPUHP_TEARDOWN_CPU - 1.
*/
WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1));
/*
* Invoke the former CPU_DYING callbacks. DYING must not fail!
*/
cpuhp_invoke_callback_range_nofail(false, cpu, st, target);
/* Park the stopper thread */
stop_machine_park(cpu);
return 0;
}
static int takedown_cpu(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int err;
/* Park the smpboot threads */
kthread_park(st->thread);
/*
* Prevent irq alloc/free while the dying cpu reorganizes the
* interrupt affinities.
*/
irq_lock_sparse();
/*
* So now all preempt/rcu users must observe !cpu_active().
*/
err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
if (err) {
/* CPU refused to die */
irq_unlock_sparse();
/* Unpark the hotplug thread so we can rollback there */
kthread_unpark(st->thread);
return err;
}
BUG_ON(cpu_online(cpu));
/*
* The teardown callback for CPUHP_AP_SCHED_STARTING will have removed
* all runnable tasks from the CPU, there's only the idle task left now
* that the migration thread is done doing the stop_machine thing.
*
* Wait for the stop thread to go away.
*/
wait_for_ap_thread(st, false);
BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
/* Interrupts are moved away from the dying cpu, reenable alloc/free */
irq_unlock_sparse();
hotplug_cpu__broadcast_tick_pull(cpu);
/* This actually kills the CPU. */
__cpu_die(cpu);
cpuhp_bp_sync_dead(cpu);
lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu));
/*
* Callbacks must be re-integrated right away to the RCU state machine.
* Otherwise an RCU callback could block a further teardown function
* waiting for its completion.
*/
rcutree_migrate_callbacks(cpu);
return 0;
}
static void cpuhp_complete_idle_dead(void *arg)
{
struct cpuhp_cpu_state *st = arg;
complete_ap_thread(st, false);
}
void cpuhp_report_idle_dead(void)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
BUG_ON(st->state != CPUHP_AP_OFFLINE);
tick_assert_timekeeping_handover();
rcutree_report_cpu_dead();
st->state = CPUHP_AP_IDLE_DEAD;
/*
* We cannot call complete after rcutree_report_cpu_dead() so we delegate it
* to an online cpu.
*/
smp_call_function_single(cpumask_first(cpu_online_mask),
cpuhp_complete_idle_dead, st, 0);
}
static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
int ret = 0;
ret = cpuhp_invoke_callback_range(false, cpu, st, target);
if (ret) {
pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n",
ret, cpu, cpuhp_get_step(st->state)->name,
st->state);
cpuhp_reset_state(cpu, st, prev_state);
if (st->state < prev_state)
WARN_ON(cpuhp_invoke_callback_range(true, cpu, st,
prev_state));
}
return ret;
}
/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
enum cpuhp_state target)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int prev_state, ret = 0;
if (num_online_cpus() == 1)
return -EBUSY;
if (!cpu_present(cpu))
return -EINVAL;
cpus_write_lock();
cpuhp_tasks_frozen = tasks_frozen;
prev_state = cpuhp_set_state(cpu, st, target);
/*
* If the current CPU state is in the range of the AP hotplug thread,
* then we need to kick the thread.
*/
if (st->state > CPUHP_TEARDOWN_CPU) {
st->target = max((int)target, CPUHP_TEARDOWN_CPU);
ret = cpuhp_kick_ap_work(cpu);
/*
* The AP side has done the error rollback already. Just
* return the error code..
*/
if (ret)
goto out;
/*
* We might have stopped still in the range of the AP hotplug
* thread. Nothing to do anymore.
*/
if (st->state > CPUHP_TEARDOWN_CPU)
goto out;
st->target = target;
}
/*
* The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
* to do the further cleanups.
*/
ret = cpuhp_down_callbacks(cpu, st, target);
if (ret && st->state < prev_state) {
if (st->state == CPUHP_TEARDOWN_CPU) {
cpuhp_reset_state(cpu, st, prev_state);
__cpuhp_kick_ap(st);
} else {
WARN(1, "DEAD callback error for CPU%d", cpu);
}
}
out:
cpus_write_unlock();
arch_smt_update();
return ret;
}
struct cpu_down_work {
unsigned int cpu;
enum cpuhp_state target;
};
static long __cpu_down_maps_locked(void *arg)
{
struct cpu_down_work *work = arg;
return _cpu_down(work->cpu, 0, work->target);
}
static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
{
struct cpu_down_work work = { .cpu = cpu, .target = target, };
/*
* If the platform does not support hotplug, report it explicitly to
* differentiate it from a transient offlining failure.
*/
if (cpu_hotplug_offline_disabled)
return -EOPNOTSUPP;
if (cpu_hotplug_disabled)
return -EBUSY;
/*
* Ensure that the control task does not run on the to be offlined
* CPU to prevent a deadlock against cfs_b->period_timer.
* Also keep at least one housekeeping cpu onlined to avoid generating
* an empty sched_domain span.
*/
for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) {
if (cpu != work.cpu)
return work_on_cpu(cpu, __cpu_down_maps_locked, &work);
}
return -EBUSY;
}
static int cpu_down(unsigned int cpu, enum cpuhp_state target)
{
int err;
cpu_maps_update_begin();
err = cpu_down_maps_locked(cpu, target);
cpu_maps_update_done();
return err;
}
/**
* cpu_device_down - Bring down a cpu device
* @dev: Pointer to the cpu device to offline
*
* This function is meant to be used by device core cpu subsystem only.
*
* Other subsystems should use remove_cpu() instead.
*
* Return: %0 on success or a negative errno code
*/
int cpu_device_down(struct device *dev)
{
return cpu_down(dev->id, CPUHP_OFFLINE);
}
int remove_cpu(unsigned int cpu)
{
int ret;
lock_device_hotplug();
ret = device_offline(get_cpu_device(cpu));
unlock_device_hotplug();
return ret;
}
EXPORT_SYMBOL_GPL(remove_cpu);
void smp_shutdown_nonboot_cpus(unsigned int primary_cpu)
{
unsigned int cpu;
int error;
cpu_maps_update_begin();
/*
* Make certain the cpu I'm about to reboot on is online.
*
* This is inline to what migrate_to_reboot_cpu() already do.
*/
if (!cpu_online(primary_cpu))
primary_cpu = cpumask_first(cpu_online_mask);
for_each_online_cpu(cpu) {
if (cpu == primary_cpu)
continue;
error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
if (error) {
pr_err("Failed to offline CPU%d - error=%d",
cpu, error);
break;
}
}
/*
* Ensure all but the reboot CPU are offline.
*/
BUG_ON(num_online_cpus() > 1);
/*
* Make sure the CPUs won't be enabled by someone else after this
* point. Kexec will reboot to a new kernel shortly resetting
* everything along the way.
*/
cpu_hotplug_disabled++;
cpu_maps_update_done();
}
#else
#define takedown_cpu NULL
#endif /*CONFIG_HOTPLUG_CPU*/
/**
* notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
* @cpu: cpu that just started
*
* It must be called by the arch code on the new cpu, before the new cpu
* enables interrupts and before the "boot" cpu returns from __cpu_up().
*/
void notify_cpu_starting(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
cpumask_set_cpu(cpu, &cpus_booted_once_mask);
/*
* STARTING must not fail!
*/
cpuhp_invoke_callback_range_nofail(true, cpu, st, target);
}
/*
* Called from the idle task. Wake up the controlling task which brings the
* hotplug thread of the upcoming CPU up and then delegates the rest of the
* online bringup to the hotplug thread.
*/
void cpuhp_online_idle(enum cpuhp_state state)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
/* Happens for the boot cpu */
if (state != CPUHP_AP_ONLINE_IDLE)
return;
cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE);
/*
* Unpark the stopper thread before we start the idle loop (and start
* scheduling); this ensures the stopper task is always available.
*/
stop_machine_unpark(smp_processor_id());
st->state = CPUHP_AP_ONLINE_IDLE;
complete_ap_thread(st, true);
}
/* Requires cpu_add_remove_lock to be held */
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
struct task_struct *idle;
int ret = 0;
cpus_write_lock();
if (!cpu_present(cpu)) {
ret = -EINVAL;
goto out;
}
/*
* The caller of cpu_up() might have raced with another
* caller. Nothing to do.
*/
if (st->state >= target)
goto out;
if (st->state == CPUHP_OFFLINE) {
/* Let it fail before we try to bring the cpu up */
idle = idle_thread_get(cpu);
if (IS_ERR(idle)) {
ret = PTR_ERR(idle);
goto out;
}
/*
* Reset stale stack state from the last time this CPU was online.
*/
scs_task_reset(idle);
kasan_unpoison_task_stack(idle);
}
cpuhp_tasks_frozen = tasks_frozen;
cpuhp_set_state(cpu, st, target);
/*
* If the current CPU state is in the range of the AP hotplug thread,
* then we need to kick the thread once more.
*/
if (st->state > CPUHP_BRINGUP_CPU) {
ret = cpuhp_kick_ap_work(cpu);
/*
* The AP side has done the error rollback already. Just
* return the error code..
*/
if (ret)
goto out;
}
/*
* Try to reach the target state. We max out on the BP at
* CPUHP_BRINGUP_CPU. After that the AP hotplug thread is
* responsible for bringing it up to the target state.
*/
target = min((int)target, CPUHP_BRINGUP_CPU);
ret = cpuhp_up_callbacks(cpu, st, target);
out:
cpus_write_unlock();
arch_smt_update();
return ret;
}
static int cpu_up(unsigned int cpu, enum cpuhp_state target)
{
int err = 0;
if (!cpu_possible(cpu)) {
pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
cpu);
return -EINVAL;
}
err = try_online_node(cpu_to_node(cpu));
if (err)
return err;
cpu_maps_update_begin();
if (cpu_hotplug_disabled) {
err = -EBUSY;
goto out;
}
if (!cpu_bootable(cpu)) {
err = -EPERM;
goto out;
}
err = _cpu_up(cpu, 0, target);
out:
cpu_maps_update_done();
return err;
}
/**
* cpu_device_up - Bring up a cpu device
* @dev: Pointer to the cpu device to online
*
* This function is meant to be used by device core cpu subsystem only.
*
* Other subsystems should use add_cpu() instead.
*
* Return: %0 on success or a negative errno code
*/
int cpu_device_up(struct device *dev)
{
return cpu_up(dev->id, CPUHP_ONLINE);
}
int add_cpu(unsigned int cpu)
{
int ret;
lock_device_hotplug();
ret = device_online(get_cpu_device(cpu));
unlock_device_hotplug();
return ret;
}
EXPORT_SYMBOL_GPL(add_cpu);
/**
* bringup_hibernate_cpu - Bring up the CPU that we hibernated on
* @sleep_cpu: The cpu we hibernated on and should be brought up.
*
* On some architectures like arm64, we can hibernate on any CPU, but on
* wake up the CPU we hibernated on might be offline as a side effect of
* using maxcpus= for example.
*
* Return: %0 on success or a negative errno code
*/
int bringup_hibernate_cpu(unsigned int sleep_cpu)
{
int ret;
if (!cpu_online(sleep_cpu)) {
pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
ret = cpu_up(sleep_cpu, CPUHP_ONLINE);
if (ret) {
pr_err("Failed to bring hibernate-CPU up!\n");
return ret;
}
}
return 0;
}
static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus,
enum cpuhp_state target)
{
unsigned int cpu;
for_each_cpu(cpu, mask) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
if (cpu_up(cpu, target) && can_rollback_cpu(st)) {
/*
* If this failed then cpu_up() might have only
* rolled back to CPUHP_BP_KICK_AP for the final
* online. Clean it up. NOOP if already rolled back.
*/
WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE));
}
if (!--ncpus)
break;
}
}
#ifdef CONFIG_HOTPLUG_PARALLEL
static bool __cpuhp_parallel_bringup __ro_after_init = true;
static int __init parallel_bringup_parse_param(char *arg)
{
return kstrtobool(arg, &__cpuhp_parallel_bringup);
}
early_param("cpuhp.parallel", parallel_bringup_parse_param);
#ifdef CONFIG_HOTPLUG_SMT
static inline bool cpuhp_smt_aware(void)
{
return cpu_smt_max_threads > 1;
}
static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
{
return cpu_primary_thread_mask;
}
#else
static inline bool cpuhp_smt_aware(void)
{
return false;
}
static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
{
return cpu_none_mask;
}
#endif
bool __weak arch_cpuhp_init_parallel_bringup(void)
{
return true;
}
/*
* On architectures which have enabled parallel bringup this invokes all BP
* prepare states for each of the to be onlined APs first. The last state
* sends the startup IPI to the APs. The APs proceed through the low level
* bringup code in parallel and then wait for the control CPU to release
* them one by one for the final onlining procedure.
*
* This avoids waiting for each AP to respond to the startup IPI in
* CPUHP_BRINGUP_CPU.
*/
static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus)
{
const struct cpumask *mask = cpu_present_mask;
if (__cpuhp_parallel_bringup)
__cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup();
if (!__cpuhp_parallel_bringup)
return false;
if (cpuhp_smt_aware()) {
const struct cpumask *pmask = cpuhp_get_primary_thread_mask();
static struct cpumask tmp_mask __initdata;
/*
* X86 requires to prevent that SMT siblings stopped while
* the primary thread does a microcode update for various
* reasons. Bring the primary threads up first.
*/
cpumask_and(&tmp_mask, mask, pmask);
cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP);
cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE);
/* Account for the online CPUs */
ncpus -= num_online_cpus();
if (!ncpus)
return true;
/* Create the mask for secondary CPUs */
cpumask_andnot(&tmp_mask, mask, pmask);
mask = &tmp_mask;
}
/* Bring the not-yet started CPUs up */
cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP);
cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE);
return true;
}
#else
static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; }
#endif /* CONFIG_HOTPLUG_PARALLEL */
void __init bringup_nonboot_cpus(unsigned int max_cpus)
{
if (!max_cpus)
return;
/* Try parallel bringup optimization if enabled */
if (cpuhp_bringup_cpus_parallel(max_cpus))
return;
/* Full per CPU serialized bringup */
cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE);
}
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
int freeze_secondary_cpus(int primary)
{
int cpu, error = 0;
cpu_maps_update_begin();
if (primary == -1) {
primary = cpumask_first(cpu_online_mask);
if (!housekeeping_cpu(primary, HK_TYPE_TIMER))
primary = housekeeping_any_cpu(HK_TYPE_TIMER);
} else {
if (!cpu_online(primary))
primary = cpumask_first(cpu_online_mask);
}
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
*/
cpumask_clear(frozen_cpus);
pr_info("Disabling non-boot CPUs ...\n");
for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) {
if (!cpu_online(cpu) || cpu == primary)
continue;
if (pm_wakeup_pending()) {
pr_info("Wakeup pending. Abort CPU freeze\n");
error = -EBUSY;
break;
}
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
if (!error)
cpumask_set_cpu(cpu, frozen_cpus);
else {
pr_err("Error taking CPU%d down: %d\n", cpu, error);
break;
}
}
if (!error)
BUG_ON(num_online_cpus() > 1);
else
pr_err("Non-boot CPUs are not disabled\n");
/*
* Make sure the CPUs won't be enabled by someone else. We need to do
* this even in case of failure as all freeze_secondary_cpus() users are
* supposed to do thaw_secondary_cpus() on the failure path.
*/
cpu_hotplug_disabled++;
cpu_maps_update_done();
return error;
}
void __weak arch_thaw_secondary_cpus_begin(void)
{
}
void __weak arch_thaw_secondary_cpus_end(void)
{
}
void thaw_secondary_cpus(void)
{
int cpu, error;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
__cpu_hotplug_enable();
if (cpumask_empty(frozen_cpus))
goto out;
pr_info("Enabling non-boot CPUs ...\n");
arch_thaw_secondary_cpus_begin();
for_each_cpu(cpu, frozen_cpus) {
trace_suspend_resume(TPS("CPU_ON"), cpu, true);
error = _cpu_up(cpu, 1, CPUHP_ONLINE);
trace_suspend_resume(TPS("CPU_ON"), cpu, false);
if (!error) {
pr_info("CPU%d is up\n", cpu);
continue;
}
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
}
arch_thaw_secondary_cpus_end();
cpumask_clear(frozen_cpus);
out:
cpu_maps_update_done();
}
static int __init alloc_frozen_cpus(void)
{
if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
return -ENOMEM;
return 0;
}
core_initcall(alloc_frozen_cpus);
/*
* When callbacks for CPU hotplug notifications are being executed, we must
* ensure that the state of the system with respect to the tasks being frozen
* or not, as reported by the notification, remains unchanged *throughout the
* duration* of the execution of the callbacks.
* Hence we need to prevent the freezer from racing with regular CPU hotplug.
*
* This synchronization is implemented by mutually excluding regular CPU
* hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
* Hibernate notifications.
*/
static int
cpu_hotplug_pm_callback(struct notifier_block *nb,
unsigned long action, void *ptr)
{
switch (action) {
case PM_SUSPEND_PREPARE:
case PM_HIBERNATION_PREPARE:
cpu_hotplug_disable();
break;
case PM_POST_SUSPEND:
case PM_POST_HIBERNATION:
cpu_hotplug_enable();
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
static int __init cpu_hotplug_pm_sync_init(void)
{
/*
* cpu_hotplug_pm_callback has higher priority than x86
* bsp_pm_callback which depends on cpu_hotplug_pm_callback
* to disable cpu hotplug to avoid cpu hotplug race.
*/
pm_notifier(cpu_hotplug_pm_callback, 0);
return 0;
}
core_initcall(cpu_hotplug_pm_sync_init);
#endif /* CONFIG_PM_SLEEP_SMP */
int __boot_cpu_id;
#endif /* CONFIG_SMP */
/* Boot processor state steps */
static struct cpuhp_step cpuhp_hp_states[] = {
[CPUHP_OFFLINE] = {
.name = "offline",
.startup.single = NULL,
.teardown.single = NULL,
},
#ifdef CONFIG_SMP
[CPUHP_CREATE_THREADS]= {
.name = "threads:prepare",
.startup.single = smpboot_create_threads,
.teardown.single = NULL,
.cant_stop = true,
},
[CPUHP_PERF_PREPARE] = {
.name = "perf:prepare",
.startup.single = perf_event_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
[CPUHP_RANDOM_PREPARE] = {
.name = "random:prepare",
.startup.single = random_prepare_cpu,
.teardown.single = NULL,
},
[CPUHP_WORKQUEUE_PREP] = {
.name = "workqueue:prepare",
.startup.single = workqueue_prepare_cpu,
.teardown.single = NULL,
},
[CPUHP_HRTIMERS_PREPARE] = {
.name = "hrtimers:prepare",
.startup.single = hrtimers_prepare_cpu,
.teardown.single = NULL,
},
[CPUHP_SMPCFD_PREPARE] = {
.name = "smpcfd:prepare",
.startup.single = smpcfd_prepare_cpu,
.teardown.single = smpcfd_dead_cpu,
},
[CPUHP_RELAY_PREPARE] = {
.name = "relay:prepare",
.startup.single = relay_prepare_cpu,
.teardown.single = NULL,
},
[CPUHP_RCUTREE_PREP] = {
.name = "RCU/tree:prepare",
.startup.single = rcutree_prepare_cpu,
.teardown.single = rcutree_dead_cpu,
},
/*
* On the tear-down path, timers_dead_cpu() must be invoked
* before blk_mq_queue_reinit_notify() from notify_dead(),
* otherwise a RCU stall occurs.
*/
[CPUHP_TIMERS_PREPARE] = {
.name = "timers:prepare",
.startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP
/*
* Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until
* the next step will release it.
*/
[CPUHP_BP_KICK_AP] = {
.name = "cpu:kick_ap",
.startup.single = cpuhp_kick_ap_alive,
},
/*
* Waits for the AP to reach cpuhp_ap_sync_alive() and then
* releases it for the complete bringup.
*/
[CPUHP_BRINGUP_CPU] = {
.name = "cpu:bringup",
.startup.single = cpuhp_bringup_ap,
.teardown.single = finish_cpu,
.cant_stop = true,
},
#else
/*
* All-in-one CPU bringup state which includes the kick alive.
*/
[CPUHP_BRINGUP_CPU] = {
.name = "cpu:bringup",
.startup.single = bringup_cpu,
.teardown.single = finish_cpu,
.cant_stop = true,
},
#endif
/* Final state before CPU kills itself */
[CPUHP_AP_IDLE_DEAD] = {
.name = "idle:dead",
},
/*
* Last state before CPU enters the idle loop to die. Transient state
* for synchronization.
*/
[CPUHP_AP_OFFLINE] = {
.name = "ap:offline",
.cant_stop = true,
},
/* First state is scheduler control. Interrupts are disabled */
[CPUHP_AP_SCHED_STARTING] = {
.name = "sched:starting",
.startup.single = sched_cpu_starting,
.teardown.single = sched_cpu_dying,
},
[CPUHP_AP_RCUTREE_DYING] = {
.name = "RCU/tree:dying",
.startup.single = NULL,
.teardown.single = rcutree_dying_cpu,
},
[CPUHP_AP_SMPCFD_DYING] = {
.name = "smpcfd:dying",
.startup.single = NULL,
.teardown.single = smpcfd_dying_cpu,
},
[CPUHP_AP_HRTIMERS_DYING] = {
.name = "hrtimers:dying",
.startup.single = hrtimers_cpu_starting,
.teardown.single = hrtimers_cpu_dying,
},
[CPUHP_AP_TICK_DYING] = {
.name = "tick:dying",
.startup.single = NULL,
.teardown.single = tick_cpu_dying,
},
/* Entry state on starting. Interrupts enabled from here on. Transient
* state for synchronsization */
[CPUHP_AP_ONLINE] = {
.name = "ap:online",
},
/*
* Handled on control processor until the plugged processor manages
* this itself.
*/
[CPUHP_TEARDOWN_CPU] = {
.name = "cpu:teardown",
.startup.single = NULL,
.teardown.single = takedown_cpu,
.cant_stop = true,
},
[CPUHP_AP_SCHED_WAIT_EMPTY] = {
.name = "sched:waitempty",
.startup.single = NULL,
.teardown.single = sched_cpu_wait_empty,
},
/* Handle smpboot threads park/unpark */
[CPUHP_AP_SMPBOOT_THREADS] = {
.name = "smpboot/threads:online",
.startup.single = smpboot_unpark_threads,
.teardown.single = smpboot_park_threads,
},
[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
.name = "irq/affinity:online",
.startup.single = irq_affinity_online_cpu,
.teardown.single = NULL,
},
[CPUHP_AP_PERF_ONLINE] = {
.name = "perf:online",
.startup.single = perf_event_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
[CPUHP_AP_WATCHDOG_ONLINE] = {
.name = "lockup_detector:online",
.startup.single = lockup_detector_online_cpu,
.teardown.single = lockup_detector_offline_cpu,
},
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
.startup.single = workqueue_online_cpu,
.teardown.single = workqueue_offline_cpu,
},
[CPUHP_AP_RANDOM_ONLINE] = {
.name = "random:online",
.startup.single = random_online_cpu,
.teardown.single = NULL,
},
[CPUHP_AP_RCUTREE_ONLINE] = {
.name = "RCU/tree:online",
.startup.single = rcutree_online_cpu,
.teardown.single = rcutree_offline_cpu,
},
#endif
/*
* The dynamically registered state space is here
*/
#ifdef CONFIG_SMP
/* Last state is scheduler control setting the cpu active */
[CPUHP_AP_ACTIVE] = {
.name = "sched:active",
.startup.single = sched_cpu_activate,
.teardown.single = sched_cpu_deactivate,
},
#endif
/* CPU is fully up and running. */
[CPUHP_ONLINE] = {
.name = "online",
.startup.single = NULL,
.teardown.single = NULL,
},
};
/* Sanity check for callbacks */
static int cpuhp_cb_check(enum cpuhp_state state)
{
if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
return -EINVAL;
return 0;
}
/*
* Returns a free for dynamic slot assignment of the Online state. The states
* are protected by the cpuhp_slot_states mutex and an empty slot is identified
* by having no name assigned.
*/
static int cpuhp_reserve_state(enum cpuhp_state state)
{
enum cpuhp_state i, end;
struct cpuhp_step *step;
switch (state) {
case CPUHP_AP_ONLINE_DYN:
step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN;
end = CPUHP_AP_ONLINE_DYN_END;
break;
case CPUHP_BP_PREPARE_DYN:
step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN;
end = CPUHP_BP_PREPARE_DYN_END;
break;
default:
return -EINVAL;
}
for (i = state; i <= end; i++, step++) {
if (!step->name)
return i;
}
WARN(1, "No more dynamic states available for CPU hotplug\n");
return -ENOSPC;
}
static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
int (*startup)(unsigned int cpu),
int (*teardown)(unsigned int cpu),
bool multi_instance)
{
/* (Un)Install the callbacks for further cpu hotplug operations */
struct cpuhp_step *sp;
int ret = 0;
/*
* If name is NULL, then the state gets removed.
*
* CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on
* the first allocation from these dynamic ranges, so the removal
* would trigger a new allocation and clear the wrong (already
* empty) state, leaving the callbacks of the to be cleared state
* dangling, which causes wreckage on the next hotplug operation.
*/
if (name && (state == CPUHP_AP_ONLINE_DYN ||
state == CPUHP_BP_PREPARE_DYN)) {
ret = cpuhp_reserve_state(state);
if (ret < 0)
return ret;
state = ret;
}
sp = cpuhp_get_step(state);
if (name && sp->name)
return -EBUSY;
sp->startup.single = startup;
sp->teardown.single = teardown;
sp->name = name;
sp->multi_instance = multi_instance;
INIT_HLIST_HEAD(&sp->list);
return ret;
}
static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
{
return cpuhp_get_step(state)->teardown.single;
}
/*
* Call the startup/teardown function for a step either on the AP or
* on the current CPU.
*/
static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
struct hlist_node *node)
{
struct cpuhp_step *sp = cpuhp_get_step(state);
int ret;
/*
* If there's nothing to do, we done.
* Relies on the union for multi_instance.
*/
if (cpuhp_step_empty(bringup, sp))
return 0;
/*
* The non AP bound callbacks can fail on bringup. On teardown
* e.g. module removal we crash for now.
*/
#ifdef CONFIG_SMP
if (cpuhp_is_ap_state(state))
ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
else
ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#else
ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#endif
BUG_ON(ret && !bringup);
return ret;
}
/*
* Called from __cpuhp_setup_state on a recoverable failure.
*
* Note: The teardown callbacks for rollback are not allowed to fail!
*/
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
struct hlist_node *node)
{
int cpu;
/* Roll back the already executed steps on the other cpus */
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int cpustate = st->state;
if (cpu >= failedcpu)
break;
/* Did we invoke the startup call on that cpu ? */
if (cpustate >= state)
cpuhp_issue_call(cpu, state, false, node);
}
}
int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
struct hlist_node *node,
bool invoke)
{
struct cpuhp_step *sp;
int cpu;
int ret;
lockdep_assert_cpus_held();
sp = cpuhp_get_step(state);
if (sp->multi_instance == false)
return -EINVAL;
mutex_lock(&cpuhp_state_mutex);
if (!invoke || !sp->startup.multi)
goto add_node;
/*
* Try to call the startup callback for each present cpu
* depending on the hotplug state of the cpu.
*/
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int cpustate = st->state;
if (cpustate < state)
continue;
ret = cpuhp_issue_call(cpu, state, true, node);
if (ret) {
if (sp->teardown.multi)
cpuhp_rollback_install(cpu, state, node);
goto unlock;
}
}
add_node:
ret = 0;
hlist_add_head(node, &sp->list);
unlock:
mutex_unlock(&cpuhp_state_mutex);
return ret;
}
int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
bool invoke)
{
int ret;
cpus_read_lock();
ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
cpus_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
/**
* __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state
* @state: The state to setup
* @name: Name of the step
* @invoke: If true, the startup function is invoked for cpus where
* cpu state >= @state
* @startup: startup callback function
* @teardown: teardown callback function
* @multi_instance: State is set up for multiple instances which get
* added afterwards.
*
* The caller needs to hold cpus read locked while calling this function.
* Return:
* On success:
* Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN;
* 0 for all other states
* On failure: proper (negative) error code
*/
int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
const char *name, bool invoke,
int (*startup)(unsigned int cpu),
int (*teardown)(unsigned int cpu),
bool multi_instance)
{
int cpu, ret = 0;
bool dynstate;
lockdep_assert_cpus_held();
if (cpuhp_cb_check(state) || !name)
return -EINVAL;
mutex_lock(&cpuhp_state_mutex);
ret = cpuhp_store_callbacks(state, name, startup, teardown,
multi_instance);
dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN;
if (ret > 0 && dynstate) {
state = ret;
ret = 0;
}
if (ret || !invoke || !startup)
goto out;
/*
* Try to call the startup callback for each present cpu
* depending on the hotplug state of the cpu.
*/
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int cpustate = st->state;
if (cpustate < state)
continue;
ret = cpuhp_issue_call(cpu, state, true, NULL);
if (ret) {
if (teardown)
cpuhp_rollback_install(cpu, state, NULL);
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
goto out;
}
}
out:
mutex_unlock(&cpuhp_state_mutex);
/*
* If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN,
* return the dynamically allocated state in case of success.
*/
if (!ret && dynstate)
return state;
return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);
int __cpuhp_setup_state(enum cpuhp_state state,
const char *name, bool invoke,
int (*startup)(unsigned int cpu),
int (*teardown)(unsigned int cpu),
bool multi_instance)
{
int ret;
cpus_read_lock();
ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
teardown, multi_instance);
cpus_read_unlock();
return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state);
int __cpuhp_state_remove_instance(enum cpuhp_state state,
struct hlist_node *node, bool invoke)
{
struct cpuhp_step *sp = cpuhp_get_step(state);
int cpu;
BUG_ON(cpuhp_cb_check(state));
if (!sp->multi_instance)
return -EINVAL;
cpus_read_lock();
mutex_lock(&cpuhp_state_mutex);
if (!invoke || !cpuhp_get_teardown_cb(state))
goto remove;
/*
* Call the teardown callback for each present cpu depending
* on the hotplug state of the cpu. This function is not
* allowed to fail currently!
*/
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int cpustate = st->state;
if (cpustate >= state)
cpuhp_issue_call(cpu, state, false, node);
}
remove:
hlist_del(node);
mutex_unlock(&cpuhp_state_mutex);
cpus_read_unlock();
return 0;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
/**
* __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state
* @state: The state to remove
* @invoke: If true, the teardown function is invoked for cpus where
* cpu state >= @state
*
* The caller needs to hold cpus read locked while calling this function.
* The teardown callback is currently not allowed to fail. Think
* about module removal!
*/
void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
{
struct cpuhp_step *sp = cpuhp_get_step(state);
int cpu;
BUG_ON(cpuhp_cb_check(state));
lockdep_assert_cpus_held();
mutex_lock(&cpuhp_state_mutex);
if (sp->multi_instance) {
WARN(!hlist_empty(&sp->list),
"Error: Removing state %d which has instances left.\n",
state);
goto remove;
}
if (!invoke || !cpuhp_get_teardown_cb(state))
goto remove;
/*
* Call the teardown callback for each present cpu depending
* on the hotplug state of the cpu. This function is not
* allowed to fail currently!
*/
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int cpustate = st->state;
if (cpustate >= state)
cpuhp_issue_call(cpu, state, false, NULL);
}
remove:
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
mutex_unlock(&cpuhp_state_mutex);
}
EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
{
cpus_read_lock();
__cpuhp_remove_state_cpuslocked(state, invoke);
cpus_read_unlock();
}
EXPORT_SYMBOL(__cpuhp_remove_state);
#ifdef CONFIG_HOTPLUG_SMT
static void cpuhp_offline_cpu_device(unsigned int cpu)
{
struct device *dev = get_cpu_device(cpu);
dev->offline = true;
/* Tell user space about the state change */
kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
}
static void cpuhp_online_cpu_device(unsigned int cpu)
{
struct device *dev = get_cpu_device(cpu);
dev->offline = false;
/* Tell user space about the state change */
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
}
int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
{
int cpu, ret = 0;
cpu_maps_update_begin();
for_each_online_cpu(cpu) {
if (topology_is_primary_thread(cpu))
continue;
/*
* Disable can be called with CPU_SMT_ENABLED when changing
* from a higher to lower number of SMT threads per core.
*/
if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
continue;
ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
if (ret)
break;
/*
* As this needs to hold the cpu maps lock it's impossible
* to call device_offline() because that ends up calling
* cpu_down() which takes cpu maps lock. cpu maps lock
* needs to be held as this might race against in kernel
* abusers of the hotplug machinery (thermal management).
*
* So nothing would update device:offline state. That would
* leave the sysfs entry stale and prevent onlining after
* smt control has been changed to 'off' again. This is
* called under the sysfs hotplug lock, so it is properly
* serialized against the regular offline usage.
*/
cpuhp_offline_cpu_device(cpu);
}
if (!ret)
cpu_smt_control = ctrlval;
cpu_maps_update_done();
return ret;
}
/* Check if the core a CPU belongs to is online */
#if !defined(topology_is_core_online)
static inline bool topology_is_core_online(unsigned int cpu)
{
return true;
}
#endif
int cpuhp_smt_enable(void)
{
int cpu, ret = 0;
cpu_maps_update_begin();
cpu_smt_control = CPU_SMT_ENABLED;
for_each_present_cpu(cpu) {
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
continue;
if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu))
continue;
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
if (ret)
break;
/* See comment in cpuhp_smt_disable() */
cpuhp_online_cpu_device(cpu);
}
cpu_maps_update_done();
return ret;
}
#endif
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t state_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
return sprintf(buf, "%d\n", st->state);
}
static DEVICE_ATTR_RO(state);
static ssize_t target_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
struct cpuhp_step *sp;
int target, ret;
ret = kstrtoint(buf, 10, &target);
if (ret)
return ret;
#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
return -EINVAL;
#else
if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
return -EINVAL;
#endif
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
mutex_lock(&cpuhp_state_mutex);
sp = cpuhp_get_step(target);
ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
mutex_unlock(&cpuhp_state_mutex);
if (ret)
goto out;
if (st->state < target)
ret = cpu_up(dev->id, target);
else if (st->state > target)
ret = cpu_down(dev->id, target);
else if (WARN_ON(st->target != target))
st->target = target;
out:
unlock_device_hotplug();
return ret ? ret : count;
}
static ssize_t target_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
return sprintf(buf, "%d\n", st->target);
}
static DEVICE_ATTR_RW(target);
static ssize_t fail_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
struct cpuhp_step *sp;
int fail, ret;
ret = kstrtoint(buf, 10, &fail);
if (ret)
return ret;
if (fail == CPUHP_INVALID) {
st->fail = fail;
return count;
}
if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
return -EINVAL;
/*
* Cannot fail STARTING/DYING callbacks.
*/
if (cpuhp_is_atomic_state(fail))
return -EINVAL;
/*
* DEAD callbacks cannot fail...
* ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter
* triggering STARTING callbacks, a failure in this state would
* hinder rollback.
*/
if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU)
return -EINVAL;
/*
* Cannot fail anything that doesn't have callbacks.
*/
mutex_lock(&cpuhp_state_mutex);
sp = cpuhp_get_step(fail);
if (!sp->startup.single && !sp->teardown.single)
ret = -EINVAL;
mutex_unlock(&cpuhp_state_mutex);
if (ret)
return ret;
st->fail = fail;
return count;
}
static ssize_t fail_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
return sprintf(buf, "%d\n", st->fail);
}
static DEVICE_ATTR_RW(fail);
static struct attribute *cpuhp_cpu_attrs[] = {
&dev_attr_state.attr,
&dev_attr_target.attr,
&dev_attr_fail.attr,
NULL
};
static const struct attribute_group cpuhp_cpu_attr_group = {
.attrs = cpuhp_cpu_attrs,
.name = "hotplug",
};
static ssize_t states_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
ssize_t cur, res = 0;
int i;
mutex_lock(&cpuhp_state_mutex);
for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
struct cpuhp_step *sp = cpuhp_get_step(i);
if (sp->name) {
cur = sprintf(buf, "%3d: %s\n", i, sp->name);
buf += cur;
res += cur;
}
}
mutex_unlock(&cpuhp_state_mutex);
return res;
}
static DEVICE_ATTR_RO(states);
static struct attribute *cpuhp_cpu_root_attrs[] = {
&dev_attr_states.attr,
NULL
};
static const struct attribute_group cpuhp_cpu_root_attr_group = {
.attrs = cpuhp_cpu_root_attrs,
.name = "hotplug",
};
#ifdef CONFIG_HOTPLUG_SMT
static bool cpu_smt_num_threads_valid(unsigned int threads)
{
if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC))
return threads >= 1 && threads <= cpu_smt_max_threads;
return threads == 1 || threads == cpu_smt_max_threads;
}
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int ctrlval, ret, num_threads, orig_threads;
bool force_off;
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
return -EPERM;
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
return -ENODEV;
if (sysfs_streq(buf, "on")) {
ctrlval = CPU_SMT_ENABLED;
num_threads = cpu_smt_max_threads;
} else if (sysfs_streq(buf, "off")) {
ctrlval = CPU_SMT_DISABLED;
num_threads = 1;
} else if (sysfs_streq(buf, "forceoff")) {
ctrlval = CPU_SMT_FORCE_DISABLED;
num_threads = 1;
} else if (kstrtoint(buf, 10, &num_threads) == 0) {
if (num_threads == 1)
ctrlval = CPU_SMT_DISABLED;
else if (cpu_smt_num_threads_valid(num_threads))
ctrlval = CPU_SMT_ENABLED;
else
return -EINVAL;
} else {
return -EINVAL;
}
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
orig_threads = cpu_smt_num_threads;
cpu_smt_num_threads = num_threads;
force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED;
if (num_threads > orig_threads)
ret = cpuhp_smt_enable();
else if (num_threads < orig_threads || force_off)
ret = cpuhp_smt_disable(ctrlval);
unlock_device_hotplug();
return ret ? ret : count;
}
#else /* !CONFIG_HOTPLUG_SMT */
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
return -ENODEV;
}
#endif /* CONFIG_HOTPLUG_SMT */
static const char *smt_states[] = {
[CPU_SMT_ENABLED] = "on",
[CPU_SMT_DISABLED] = "off",
[CPU_SMT_FORCE_DISABLED] = "forceoff",
[CPU_SMT_NOT_SUPPORTED] = "notsupported",
[CPU_SMT_NOT_IMPLEMENTED] = "notimplemented",
};
static ssize_t control_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
const char *state = smt_states[cpu_smt_control];
#ifdef CONFIG_HOTPLUG_SMT
/*
* If SMT is enabled but not all threads are enabled then show the
* number of threads. If all threads are enabled show "on". Otherwise
* show the state name.
*/
if (cpu_smt_control == CPU_SMT_ENABLED &&
cpu_smt_num_threads != cpu_smt_max_threads)
return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
#endif
return sysfs_emit(buf, "%s\n", state);
}
static ssize_t control_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
return __store_smt_control(dev, attr, buf, count);
}
static DEVICE_ATTR_RW(control);
static ssize_t active_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%d\n", sched_smt_active());
}
static DEVICE_ATTR_RO(active);
static struct attribute *cpuhp_smt_attrs[] = {
&dev_attr_control.attr,
&dev_attr_active.attr,
NULL
};
static const struct attribute_group cpuhp_smt_attr_group = {
.attrs = cpuhp_smt_attrs,
.name = "smt",
};
static int __init cpu_smt_sysfs_init(void)
{
struct device *dev_root;
int ret = -ENODEV;
dev_root = bus_get_dev_root(&cpu_subsys);
if (dev_root) {
ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group);
put_device(dev_root);
}
return ret;
}
static int __init cpuhp_sysfs_init(void)
{
struct device *dev_root;
int cpu, ret;
ret = cpu_smt_sysfs_init();
if (ret)
return ret;
dev_root = bus_get_dev_root(&cpu_subsys);
if (dev_root) {
ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group);
put_device(dev_root);
if (ret)
return ret;
}
for_each_possible_cpu(cpu) {
struct device *dev = get_cpu_device(cpu);
if (!dev)
continue;
ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
if (ret)
return ret;
}
return 0;
}
device_initcall(cpuhp_sysfs_init);
#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
/*
* cpu_bit_bitmap[] is a special, "compressed" data structure that
* represents all NR_CPUS bits binary values of 1<<nr.
*
* It is used by cpumask_of() to get a constant address to a CPU
* mask value that has a single bit set only.
*/
/* cpu_bit_bitmap[0] is empty - so we can back into it */
#define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x))
#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
MASK_DECLARE_8(0), MASK_DECLARE_8(8),
MASK_DECLARE_8(16), MASK_DECLARE_8(24),
#if BITS_PER_LONG > 32
MASK_DECLARE_8(32), MASK_DECLARE_8(40),
MASK_DECLARE_8(48), MASK_DECLARE_8(56),
#endif
};
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);
#ifdef CONFIG_INIT_ALL_POSSIBLE
struct cpumask __cpu_possible_mask __ro_after_init
= {CPU_BITS_ALL};
#else
struct cpumask __cpu_possible_mask __ro_after_init;
#endif
EXPORT_SYMBOL(__cpu_possible_mask);
struct cpumask __cpu_online_mask __read_mostly;
EXPORT_SYMBOL(__cpu_online_mask);
struct cpumask __cpu_enabled_mask __read_mostly;
EXPORT_SYMBOL(__cpu_enabled_mask);
struct cpumask __cpu_present_mask __read_mostly;
EXPORT_SYMBOL(__cpu_present_mask);
struct cpumask __cpu_active_mask __read_mostly;
EXPORT_SYMBOL(__cpu_active_mask);
struct cpumask __cpu_dying_mask __read_mostly;
EXPORT_SYMBOL(__cpu_dying_mask);
atomic_t __num_online_cpus __read_mostly;
EXPORT_SYMBOL(__num_online_cpus);
void init_cpu_present(const struct cpumask *src)
{
cpumask_copy(&__cpu_present_mask, src);
}
void init_cpu_possible(const struct cpumask *src)
{
cpumask_copy(&__cpu_possible_mask, src);
}
void set_cpu_online(unsigned int cpu, bool online)
{
/*
* atomic_inc/dec() is required to handle the horrid abuse of this
* function by the reboot and kexec code which invoke it from
* IPI/NMI broadcasts when shutting down CPUs. Invocation from
* regular CPU hotplug is properly serialized.
*
* Note, that the fact that __num_online_cpus is of type atomic_t
* does not protect readers which are not serialized against
* concurrent hotplug operations.
*/
if (online) {
if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask))
atomic_inc(&__num_online_cpus);
} else {
if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask))
atomic_dec(&__num_online_cpus);
}
}
/*
* Activate the first processor.
*/
void __init boot_cpu_init(void)
{
int cpu = smp_processor_id();
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
set_cpu_online(cpu, true);
set_cpu_active(cpu, true);
set_cpu_present(cpu, true);
set_cpu_possible(cpu, true);
#ifdef CONFIG_SMP
__boot_cpu_id = cpu;
#endif
}
/*
* Must be called _AFTER_ setting up the per_cpu areas
*/
void __init boot_cpu_hotplug_init(void)
{
#ifdef CONFIG_SMP
cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask);
atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE);
#endif
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
}
#ifdef CONFIG_CPU_MITIGATIONS
/*
* These are used for a global "mitigations=" cmdline option for toggling
* optional CPU mitigations.
*/
enum cpu_mitigations {
CPU_MITIGATIONS_OFF,
CPU_MITIGATIONS_AUTO,
CPU_MITIGATIONS_AUTO_NOSMT,
};
static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
if (!strcmp(arg, "off"))
cpu_mitigations = CPU_MITIGATIONS_OFF;
else if (!strcmp(arg, "auto"))
cpu_mitigations = CPU_MITIGATIONS_AUTO;
else if (!strcmp(arg, "auto,nosmt"))
cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
else
pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
arg);
return 0;
}
/* mitigations=off */
bool cpu_mitigations_off(void)
{
return cpu_mitigations == CPU_MITIGATIONS_OFF;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_off);
/* mitigations=auto,nosmt */
bool cpu_mitigations_auto_nosmt(void)
{
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
#else
static int __init mitigations_parse_cmdline(char *arg)
{
pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n");
return 0;
}
#endif
early_param("mitigations", mitigations_parse_cmdline);
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/context_tracking.h>
#include <linux/errno.h>
#include <linux/nospec.h>
#include <linux/ptrace.h>
#include <linux/randomize_kstack.h>
#include <linux/syscalls.h>
#include <asm/debug-monitors.h>
#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
#include <asm/unistd.h>
#include <asm/unistd_compat_32.h>
long compat_arm_syscall(struct pt_regs *regs, int scno);
long sys_ni_syscall(void);
static long do_ni_syscall(struct pt_regs *regs, int scno)
{
if (is_compat_task()) {
long ret = compat_arm_syscall(regs, scno);
if (ret != -ENOSYS)
return ret;
}
return sys_ni_syscall();
}
static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
{
return syscall_fn(regs);
}
static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
unsigned int sc_nr,
const syscall_fn_t syscall_table[])
{
long ret;
add_random_kstack_offset();
if (scno < sc_nr) {
syscall_fn_t syscall_fn;
syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
ret = __invoke_syscall(regs, syscall_fn);
} else {
ret = do_ni_syscall(regs, scno);
}
syscall_set_return_value(current, regs, 0, ret);
/*
* This value will get limited by KSTACK_OFFSET_MAX(), which is 10
* bits. The actual entropy will be further reduced by the compiler
* when applying stack alignment constraints: the AAPCS mandates a
* 16-byte aligned SP at function boundaries, which will remove the
* 4 low bits from any entropy chosen here.
*
* The resulting 6 bits of entropy is seen in SP[9:4].
*/
choose_random_kstack_offset(get_random_u16());
}
static inline bool has_syscall_work(unsigned long flags)
{
return unlikely(flags & _TIF_SYSCALL_WORK);
}
static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
const syscall_fn_t syscall_table[])
{
unsigned long flags = read_thread_flags();
regs->orig_x0 = regs->regs[0];
regs->syscallno = scno;
/*
* BTI note:
* The architecture does not guarantee that SPSR.BTYPE is zero
* on taking an SVC, so we could return to userspace with a
* non-zero BTYPE after the syscall.
*
* This shouldn't matter except when userspace is explicitly
* doing something stupid, such as setting PROT_BTI on a page
* that lacks conforming BTI/PACIxSP instructions, falling
* through from one executable page to another with differing
* PROT_BTI, or messing with BTYPE via ptrace: in such cases,
* userspace should not be surprised if a SIGILL occurs on
* syscall return.
*
* So, don't touch regs->pstate & PSR_BTYPE_MASK here.
* (Similarly for HVC and SMC elsewhere.)
*/
if (flags & _TIF_MTE_ASYNC_FAULT) {
/*
* Process the asynchronous tag check fault before the actual
* syscall. do_notify_resume() will send a signal to userspace
* before the syscall is restarted.
*/
syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0);
return;
}
if (has_syscall_work(flags)) {
/*
* The de-facto standard way to skip a system call using ptrace
* is to set the system call to -1 (NO_SYSCALL) and set x0 to a
* suitable error code for consumption by userspace. However,
* this cannot be distinguished from a user-issued syscall(-1)
* and so we must set x0 to -ENOSYS here in case the tracer doesn't
* issue the skip and we fall into trace_exit with x0 preserved.
*
* This is slightly odd because it also means that if a tracer
* sets the system call number to -1 but does not initialise x0,
* then x0 will be preserved for all system calls apart from a
* user-issued syscall(-1). However, requesting a skip and not
* setting the return value is unlikely to do anything sensible
* anyway.
*/
if (scno == NO_SYSCALL) syscall_set_return_value(current, regs, -ENOSYS, 0);
scno = syscall_trace_enter(regs);
if (scno == NO_SYSCALL)
goto trace_exit;
}
invoke_syscall(regs, scno, sc_nr, syscall_table);
/*
* The tracing status may have changed under our feet, so we have to
* check again. However, if we were tracing entry, then we always trace
* exit regardless, as the old entry assembly did.
*/
if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
flags = read_thread_flags();
if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
return;
}
trace_exit:
syscall_trace_exit(regs);
}
void do_el0_svc(struct pt_regs *regs)
{
el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
}
#ifdef CONFIG_COMPAT
void do_el0_svc_compat(struct pt_regs *regs)
{
el0_svc_common(regs, regs->regs[7], __NR_compat32_syscalls,
compat_sys_call_table);
}
#endif
// SPDX-License-Identifier: GPL-2.0+
/*
* ext4_jbd2.h
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1999
*
* Copyright 1998--1999 Red Hat corp --- All Rights Reserved
*
* Ext4-specific journaling extensions.
*/
#ifndef _EXT4_JBD2_H
#define _EXT4_JBD2_H
#include <linux/fs.h>
#include <linux/jbd2.h>
#include "ext4.h"
#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal)
/* Define the number of blocks we need to account to a transaction to
* modify one block of data.
*
* We may have to touch one inode, one bitmap buffer, up to three
* indirection blocks, the group and superblock summaries, and the data
* block to complete the transaction.
*
* For extents-enabled fs we may have to allocate and modify up to
* 5 levels of tree, data block (for each of these we need bitmap + group
* summaries), root which is stored in the inode, sb
*/
#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \
(ext4_has_feature_extents(sb) ? 20U : 8U)
/* Extended attribute operations touch at most two data buffers,
* two bitmap buffers, and two group summaries, in addition to the inode
* and the superblock, which are already accounted for. */
#define EXT4_XATTR_TRANS_BLOCKS 6U
/* Define the minimum size for a transaction which modifies data. This
* needs to take into account the fact that we may end up modifying two
* quota files too (one for the group, one for the user quota). The
* superblock only gets updated once, of course, so don't bother
* counting that again for the quota updates. */
#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
EXT4_XATTR_TRANS_BLOCKS - 2 + \
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
/*
* Define the number of metadata blocks we need to account to modify data.
*
* This include super block, inode block, quota blocks and xattr blocks
*/
#define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
/* Define an arbitrary limit for the amount of data we will anticipate
* writing to any given transaction. For unbounded transactions such as
* write(2) and truncate(2) we can write more than this, but we always
* start off at the maximum transaction size and grow the transaction
* optimistically as we go. */
#define EXT4_MAX_TRANS_DATA 64U
/* We break up a large truncate or write transaction once the handle's
* buffer credits gets this low, we need either to extend the
* transaction or to start a new one. Reserve enough space here for
* inode, bitmap, superblock, group and indirection updates for at least
* one block, plus two quota updates. Quota allocations are not
* needed. */
#define EXT4_RESERVE_TRANS_BLOCKS 12U
/*
* Number of credits needed if we need to insert an entry into a
* directory. For each new index block, we need 4 blocks (old index
* block, new index block, bitmap block, bg summary). For normal
* htree directories there are 2 levels; if the largedir feature
* enabled it's 3 levels.
*/
#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U
#ifdef CONFIG_QUOTA
/* Amount of blocks needed for quota update - we know that the structure was
* allocated so we need to update only data block */
#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0)
/* Amount of blocks needed for quota insert/delete - we do some block writes
* but inode, sb and group updates are done only once */
#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+3+DQUOT_INIT_REWRITE) : 0)
#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+3+DQUOT_DEL_REWRITE) : 0)
#else
#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
#endif
#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
/*
* Ext4 handle operation types -- for logging purposes
*/
#define EXT4_HT_MISC 0
#define EXT4_HT_INODE 1
#define EXT4_HT_WRITE_PAGE 2
#define EXT4_HT_MAP_BLOCKS 3
#define EXT4_HT_DIR 4
#define EXT4_HT_TRUNCATE 5
#define EXT4_HT_QUOTA 6
#define EXT4_HT_RESIZE 7
#define EXT4_HT_MIGRATE 8
#define EXT4_HT_MOVE_EXTENTS 9
#define EXT4_HT_XATTR 10
#define EXT4_HT_EXT_CONVERT 11
#define EXT4_HT_MAX 12
int
ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc);
/*
* On success, We end up with an outstanding reference count against
* iloc->bh. This _must_ be cleaned up later.
*/
int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc);
#define ext4_mark_inode_dirty(__h, __i) \
__ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__)
int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
const char *func, unsigned int line);
int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc *iloc);
/*
* Wrapper functions with which ext4 calls into JBD.
*/
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct super_block *sb,
struct buffer_head *bh,
enum ext4_journal_trigger_type trigger_type);
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr);
int __ext4_journal_get_create_access(const char *where, unsigned int line,
handle_t *handle, struct super_block *sb,
struct buffer_head *bh,
enum ext4_journal_trigger_type trigger_type);
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh);
#define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \
(bh), (trigger_type))
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
(bh), (block_nr))
#define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \
__ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \
(bh), (trigger_type))
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
(bh))
handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb,
unsigned int line, int type, int blocks,
int rsv_blocks, int revoke_creds);
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
/* Note: Do not use this for NULL handles. This is only to determine if
* a properly allocated handle is using a journal or not. */
static inline int ext4_handle_valid(handle_t *handle)
{
if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
return 0;
return 1;
}
static inline void ext4_handle_sync(handle_t *handle)
{
if (ext4_handle_valid(handle))
handle->h_sync = 1;
}
static inline int ext4_handle_is_aborted(handle_t *handle)
{
if (ext4_handle_valid(handle))
return is_handle_aborted(handle);
return 0;
}
static inline int ext4_free_metadata_revoke_credits(struct super_block *sb,
int blocks)
{
/* Freeing each metadata block can result in freeing one cluster */
return blocks * EXT4_SB(sb)->s_cluster_ratio;
}
static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
{
return ext4_free_metadata_revoke_credits(sb, 8);
}
#define ext4_journal_start_sb(sb, type, nblocks) \
__ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\
ext4_trans_default_revoke_credits(sb))
#define ext4_journal_start(inode, type, nblocks) \
__ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \
ext4_trans_default_revoke_credits((inode)->i_sb))
#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\
__ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\
ext4_trans_default_revoke_credits((inode)->i_sb))
#define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \
__ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \
(revoke_creds))
static inline handle_t *__ext4_journal_start(struct inode *inode,
unsigned int line, int type,
int blocks, int rsv_blocks,
int revoke_creds)
{
return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks,
rsv_blocks, revoke_creds);
}
#define ext4_journal_stop(handle) \
__ext4_journal_stop(__func__, __LINE__, (handle))
#define ext4_journal_start_reserved(handle, type) \
__ext4_journal_start_reserved((handle), __LINE__, (type))
handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
int type);
static inline handle_t *ext4_journal_current_handle(void)
{
return journal_current_handle();
}
static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke)
{
if (ext4_handle_valid(handle))
return jbd2_journal_extend(handle, nblocks, revoke);
return 0;
}
static inline int ext4_journal_restart(handle_t *handle, int nblocks,
int revoke)
{
if (ext4_handle_valid(handle))
return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS);
return 0;
}
int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
int extend_cred, int revoke_cred);
/*
* Ensure @handle has at least @check_creds credits available. If not,
* transaction will be extended or restarted to contain at least @extend_cred
* credits. Before restarting transaction @fn is executed to allow for cleanup
* before the transaction is restarted.
*
* The return value is < 0 in case of error, 0 in case the handle has enough
* credits or transaction extension succeeded, 1 in case transaction had to be
* restarted.
*/
#define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \
revoke_cred, fn) \
({ \
__label__ __ensure_end; \
int err = __ext4_journal_ensure_credits((handle), (check_cred), \
(extend_cred), (revoke_cred)); \
\
if (err <= 0) \
goto __ensure_end; \
err = (fn); \
if (err < 0) \
goto __ensure_end; \
err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \
if (err == 0) \
err = 1; \
__ensure_end: \
err; \
})
/*
* Ensure given handle has at least requested amount of credits available,
* possibly restarting transaction if needed. We also make sure the transaction
* has space for at least ext4_trans_default_revoke_credits(sb) revoke records
* as freeing one or two blocks is very common pattern and requesting this is
* very cheap.
*/
static inline int ext4_journal_ensure_credits(handle_t *handle, int credits,
int revoke_creds)
{
return ext4_journal_ensure_credits_fn(handle, credits, credits,
revoke_creds, 0);
}
static inline int ext4_journal_blocks_per_page(struct inode *inode)
{
if (EXT4_JOURNAL(inode) != NULL)
return jbd2_journal_blocks_per_page(inode);
return 0;
}
static inline int ext4_journal_force_commit(journal_t *journal)
{
if (journal)
return jbd2_journal_force_commit(journal);
return 0;
}
static inline int ext4_jbd2_inode_add_write(handle_t *handle,
struct inode *inode, loff_t start_byte, loff_t length)
{
if (ext4_handle_valid(handle))
return jbd2_journal_inode_ranged_write(handle,
EXT4_I(inode)->jinode, start_byte, length);
return 0;
}
static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
struct inode *inode, loff_t start_byte, loff_t length)
{
if (ext4_handle_valid(handle))
return jbd2_journal_inode_ranged_wait(handle,
EXT4_I(inode)->jinode, start_byte, length);
return 0;
}
static inline void ext4_update_inode_fsync_trans(handle_t *handle,
struct inode *inode,
int datasync)
{
struct ext4_inode_info *ei = EXT4_I(inode);
if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) {
ei->i_sync_tid = handle->h_transaction->t_tid;
if (datasync)
ei->i_datasync_tid = handle->h_transaction->t_tid;
}
}
/* super.c */
int ext4_force_commit(struct super_block *sb);
/*
* Ext4 inode journal modes
*/
#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */
#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
int ext4_inode_journal_mode(struct inode *inode);
static inline int ext4_should_journal_data(struct inode *inode)
{
return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
}
static inline int ext4_should_order_data(struct inode *inode)
{
return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
}
static inline int ext4_should_writeback_data(struct inode *inode)
{
return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
}
static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
{
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
return 0;
if (!ext4_should_journal_data(inode))
return 0;
/*
* Data blocks in one extent are contiguous, just account for partial
* clusters at extent boundaries
*/
return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1);
}
/*
* This function controls whether or not we should try to go down the
* dioread_nolock code paths, which makes it safe to avoid taking
* i_rwsem for direct I/O reads. This only works for extent-based
* files, and it doesn't work if data journaling is enabled, since the
* dioread_nolock code uses b_private to pass information back to the
* I/O completion handler, and this conflicts with the jbd's use of
* b_private.
*/
static inline int ext4_should_dioread_nolock(struct inode *inode)
{
if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return 0;
if (ext4_should_journal_data(inode))
return 0;
/* temporary fix to prevent generic/422 test failures */
if (!test_opt(inode->i_sb, DELALLOC))
return 0;
return 1;
}
/*
* Pass journal explicitly as it may not be cached in the sbi->s_journal in some
* cases
*/
static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal)
{
int err = 0;
/*
* At this point only two things can be operating on the journal.
* JBD2 thread performing transaction commit and s_sb_upd_work
* issuing sb update through the journal. Once we set
* EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not
* queue s_sb_upd_work and ext4_force_commit() makes sure any
* ext4_handle_error() calls from the running transaction commit are
* finished. Hence no new s_sb_upd_work can be queued after we
* flush it here.
*/
ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY);
ext4_force_commit(sbi->s_sb);
flush_work(&sbi->s_sb_upd_work);
err = jbd2_journal_destroy(journal);
sbi->s_journal = NULL;
return err;
}
#endif /* _EXT4_JBD2_H */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/mlock.c
*
* (C) Copyright 1995 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*/
#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/sched/user.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/pagewalk.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/secretmem.h>
#include "internal.h"
struct mlock_fbatch {
local_lock_t lock;
struct folio_batch fbatch;
};
static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = {
.lock = INIT_LOCAL_LOCK(lock),
};
bool can_do_mlock(void)
{ if (rlimit(RLIMIT_MEMLOCK) != 0)
return true;
if (capable(CAP_IPC_LOCK))
return true;
return false;
}
EXPORT_SYMBOL(can_do_mlock);
/*
* Mlocked folios are marked with the PG_mlocked flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
* statistics.
*
* An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it
* will be ostensibly placed on the LRU "unevictable" list (actually no such
* list exists), rather than the [in]active lists. PG_unevictable is set to
* indicate the unevictable state.
*/
static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec)
{
/* There is nothing more we can do while it's off LRU */
if (!folio_test_clear_lru(folio))
return lruvec;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (unlikely(folio_evictable(folio))) {
/*
* This is a little surprising, but quite possible: PG_mlocked
* must have got cleared already by another CPU. Could this
* folio be unevictable? I'm not sure, but move it now if so.
*/
if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGRESCUED,
folio_nr_pages(folio));
}
goto out;
}
if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++;
goto out;
}
lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio));
out:
folio_set_lru(folio);
return lruvec;
}
static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec)
{
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
lruvec = folio_lruvec_relock_irq(folio, lruvec);
/* As above, this is a little surprising, but possible */
if (unlikely(folio_evictable(folio)))
goto out;
folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio));
out:
lruvec_add_folio(lruvec, folio); folio_set_lru(folio);
return lruvec;
}
static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec)
{
int nr_pages = folio_nr_pages(folio);
bool isolated = false;
if (!folio_test_clear_lru(folio))
goto munlock;
isolated = true;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (folio_test_unevictable(folio)) {
/* Then mlock_count is maintained, but might undercount */
if (folio->mlock_count)
folio->mlock_count--;
if (folio->mlock_count)
goto out;
}
/* else assume that was the last mlock: reclaim will fix it if not */
munlock:
if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio))
__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
else
__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
}
/* folio_evictable() has to be checked *after* clearing Mlocked */
if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
}
out:
if (isolated)
folio_set_lru(folio);
return lruvec;
}
/*
* Flags held in the low bits of a struct folio pointer on the mlock_fbatch.
*/
#define LRU_FOLIO 0x1
#define NEW_FOLIO 0x2
static inline struct folio *mlock_lru(struct folio *folio)
{
return (struct folio *)((unsigned long)folio + LRU_FOLIO);
}
static inline struct folio *mlock_new(struct folio *folio)
{
return (struct folio *)((unsigned long)folio + NEW_FOLIO);
}
/*
* mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can
* make use of such folio pointer flags in future, but for now just keep it for
* mlock. We could use three separate folio batches instead, but one feels
* better (munlocking a full folio batch does not need to drain mlocking folio
* batches first).
*/
static void mlock_folio_batch(struct folio_batch *fbatch)
{
struct lruvec *lruvec = NULL;
unsigned long mlock;
struct folio *folio;
int i;
for (i = 0; i < folio_batch_count(fbatch); i++) {
folio = fbatch->folios[i];
mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO);
folio = (struct folio *)((unsigned long)folio - mlock);
fbatch->folios[i] = folio;
if (mlock & LRU_FOLIO)
lruvec = __mlock_folio(folio, lruvec);
else if (mlock & NEW_FOLIO)
lruvec = __mlock_new_folio(folio, lruvec);
else
lruvec = __munlock_folio(folio, lruvec);
}
if (lruvec) unlock_page_lruvec_irq(lruvec);
folios_put(fbatch);
}
void mlock_drain_local(void)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock);
}
void mlock_drain_remote(int cpu)
{
struct folio_batch *fbatch;
WARN_ON_ONCE(cpu_online(cpu));
fbatch = &per_cpu(mlock_fbatch.fbatch, cpu);
if (folio_batch_count(fbatch))
mlock_folio_batch(fbatch);
}
bool need_mlock_drain(int cpu)
{
return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu));
}
/**
* mlock_folio - mlock a folio already on (or temporarily off) LRU
* @folio: folio to be mlocked.
*/
void mlock_folio(struct folio *folio)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages);
__count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
}
folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
/**
* mlock_new_folio - mlock a newly allocated folio not yet on LRU
* @folio: folio to be mlocked, either normal or a THP head.
*/
void mlock_new_folio(struct folio *folio)
{
struct folio_batch *fbatch;
int nr_pages = folio_nr_pages(folio);
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages);
__count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
/**
* munlock_folio - munlock a folio
* @folio: folio to be munlocked, either normal or a THP head.
*/
void munlock_folio(struct folio *folio)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
/*
* folio_test_clear_mlocked(folio) must be left to __munlock_folio(),
* which will check whether the folio is multiply mlocked.
*/
folio_get(folio); if (!folio_batch_add(fbatch, folio) || folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
static inline unsigned int folio_mlock_step(struct folio *folio,
pte_t *pte, unsigned long addr, unsigned long end)
{
const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
unsigned int count = (end - addr) >> PAGE_SHIFT;
pte_t ptent = ptep_get(pte);
if (!folio_test_large(folio))
return 1;
return folio_pte_batch(folio, addr, pte, ptent, count, fpb_flags, NULL,
NULL, NULL);
}
static inline bool allow_mlock_munlock(struct folio *folio,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, unsigned int step)
{
/*
* For unlock, allow munlock large folio which is partially
* mapped to VMA. As it's possible that large folio is
* mlocked and VMA is split later.
*
* During memory pressure, such kind of large folio can
* be split. And the pages are not in VM_LOCKed VMA
* can be reclaimed.
*/
if (!(vma->vm_flags & VM_LOCKED))
return true;
/* folio_within_range() cannot take KSM, but any small folio is OK */
if (!folio_test_large(folio))
return true;
/* folio not in range [start, end), skip mlock */
if (!folio_within_range(folio, vma, start, end))
return false;
/* folio is not fully mapped, skip mlock */
if (step != folio_nr_pages(folio))
return false;
return true;
}
static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
pte_t *start_pte, *pte;
pte_t ptent;
struct folio *folio;
unsigned int step = 1;
unsigned long start = addr;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
if (!pmd_present(*pmd))
goto out;
if (is_huge_zero_pmd(*pmd))
goto out;
folio = pmd_folio(*pmd);
if (folio_is_zone_device(folio))
goto out;
if (vma->vm_flags & VM_LOCKED)
mlock_folio(folio);
else
munlock_folio(folio);
goto out;
}
start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (!start_pte) {
walk->action = ACTION_AGAIN;
return 0;
}
for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
ptent = ptep_get(pte);
if (!pte_present(ptent))
continue;
folio = vm_normal_folio(vma, addr, ptent);
if (!folio || folio_is_zone_device(folio))
continue;
step = folio_mlock_step(folio, pte, addr, end);
if (!allow_mlock_munlock(folio, vma, start, end, step))
goto next_entry;
if (vma->vm_flags & VM_LOCKED)
mlock_folio(folio);
else
munlock_folio(folio);
next_entry:
pte += step - 1;
addr += (step - 1) << PAGE_SHIFT;
}
pte_unmap(start_pte);
out:
spin_unlock(ptl);
cond_resched();
return 0;
}
/*
* mlock_vma_pages_range() - mlock any pages already in the range,
* or munlock all pages in the range.
* @vma - vma containing range to be mlock()ed or munlock()ed
* @start - start address in @vma of the range
* @end - end of range in @vma
* @newflags - the new set of flags for @vma.
*
* Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED;
* called for munlock() and munlockall(), to clear VM_LOCKED from @vma.
*/
static void mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, vm_flags_t newflags)
{
static const struct mm_walk_ops mlock_walk_ops = {
.pmd_entry = mlock_pte_range,
.walk_lock = PGWALK_WRLOCK_VERIFY,
};
/*
* There is a slight chance that concurrent page migration,
* or page reclaim finding a page of this now-VM_LOCKED vma,
* will call mlock_vma_folio() and raise page's mlock_count:
* double counting, leaving the page unevictable indefinitely.
* Communicate this danger to mlock_vma_folio() with VM_IO,
* which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas.
* mmap_lock is held in write mode here, so this weird
* combination should not be visible to other mmap_lock users;
* but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED.
*/
if (newflags & VM_LOCKED)
newflags |= VM_IO;
vma_start_write(vma);
vm_flags_reset_once(vma, newflags);
lru_add_drain();
walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL);
lru_add_drain();
if (newflags & VM_IO) {
newflags &= ~VM_IO;
vm_flags_reset_once(vma, newflags);
}
}
/*
* mlock_fixup - handle mlock[all]/munlock[all] requests.
*
* Filters out "special" vmas -- VM_LOCKED never gets set for these, and
* munlock is a no-op. However, for some special vmas, we go ahead and
* populate the ptes.
*
* For vmas that pass the filters, merge/split as appropriate.
*/
static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
unsigned long end, vm_flags_t newflags)
{
struct mm_struct *mm = vma->vm_mm;
int nr_pages;
int ret = 0;
vm_flags_t oldflags = vma->vm_flags;
if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
goto out;
vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto out;
}
/*
* Keep track of amount of locked VM.
*/
nr_pages = (end - start) >> PAGE_SHIFT;
if (!(newflags & VM_LOCKED))
nr_pages = -nr_pages;
else if (oldflags & VM_LOCKED)
nr_pages = 0;
mm->locked_vm += nr_pages;
/*
* vm_flags is protected by the mmap_lock held in write mode.
* It's okay if try_to_unmap_one unmaps a page just after we
* set VM_LOCKED, populate_vma_page_range will bring it back.
*/
if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) {
/* No work to do, and mlocking twice would be wrong */
vma_start_write(vma);
vm_flags_reset(vma, newflags);
} else {
mlock_vma_pages_range(vma, start, end, newflags);
}
out:
*prev = vma;
return ret;
}
static int apply_vma_lock_flags(unsigned long start, size_t len,
vm_flags_t flags)
{
unsigned long nstart, end, tmp;
struct vm_area_struct *vma, *prev;
VMA_ITERATOR(vmi, current->mm, start);
VM_BUG_ON(offset_in_page(start));
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
vma = vma_iter_load(&vmi);
if (!vma)
return -ENOMEM;
prev = vma_prev(&vmi);
if (start > vma->vm_start)
prev = vma;
nstart = start;
tmp = vma->vm_start;
for_each_vma_range(vmi, vma, end) {
int error;
vm_flags_t newflags;
if (vma->vm_start != tmp)
return -ENOMEM;
newflags = vma->vm_flags & ~VM_LOCKED_MASK;
newflags |= flags;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
tmp = vma->vm_end;
if (tmp > end)
tmp = end;
error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags);
if (error)
return error;
tmp = vma_iter_end(&vmi);
nstart = tmp;
}
if (tmp < end)
return -ENOMEM;
return 0;
}
/*
* Go through vma areas and sum size of mlocked
* vma pages, as return value.
* Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT)
* is also counted.
* Return value: previously mlocked page counts
*/
static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
unsigned long start, size_t len)
{
struct vm_area_struct *vma;
unsigned long count = 0;
unsigned long end;
VMA_ITERATOR(vmi, mm, start);
/* Don't overflow past ULONG_MAX */
if (unlikely(ULONG_MAX - len < start))
end = ULONG_MAX;
else
end = start + len;
for_each_vma_range(vmi, vma, end) {
if (vma->vm_flags & VM_LOCKED) {
if (start > vma->vm_start)
count -= (start - vma->vm_start);
if (end < vma->vm_end) {
count += end - vma->vm_start;
break;
}
count += vma->vm_end - vma->vm_start;
}
}
return count >> PAGE_SHIFT;
}
/*
* convert get_user_pages() return value to posix mlock() error
*/
static int __mlock_posix_error_return(long retval)
{
if (retval == -EFAULT)
retval = -ENOMEM;
else if (retval == -ENOMEM)
retval = -EAGAIN;
return retval;
}
static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
{
unsigned long locked;
unsigned long lock_limit;
int error = -ENOMEM;
start = untagged_addr(start);
if (!can_do_mlock())
return -EPERM;
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = len >> PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
locked += current->mm->locked_vm;
if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) {
/*
* It is possible that the regions requested intersect with
* previously mlocked areas, that part area in "mm->locked_vm"
* should not be counted to new mlock increment count. So check
* and adjust locked count if necessary.
*/
locked -= count_mm_mlocked_page_nr(current->mm,
start, len);
}
/* check against resource limits */
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
error = apply_vma_lock_flags(start, len, flags);
mmap_write_unlock(current->mm);
if (error)
return error;
error = __mm_populate(start, len, 0);
if (error)
return __mlock_posix_error_return(error);
return 0;
}
SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
return do_mlock(start, len, VM_LOCKED);
}
SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
vm_flags_t vm_flags = VM_LOCKED;
if (flags & ~MLOCK_ONFAULT)
return -EINVAL;
if (flags & MLOCK_ONFAULT)
vm_flags |= VM_LOCKONFAULT;
return do_mlock(start, len, vm_flags);
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
start = untagged_addr(start);
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_vma_lock_flags(start, len, 0);
mmap_write_unlock(current->mm);
return ret;
}
/*
* Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
* and translate into the appropriate modifications to mm->def_flags and/or the
* flags for all current VMAs.
*
* There are a couple of subtleties with this. If mlockall() is called multiple
* times with different flags, the values do not necessarily stack. If mlockall
* is called once including the MCL_FUTURE flag and then a second time without
* it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
*/
static int apply_mlockall_flags(int flags)
{
VMA_ITERATOR(vmi, current->mm, 0);
struct vm_area_struct *vma, *prev = NULL;
vm_flags_t to_add = 0;
current->mm->def_flags &= ~VM_LOCKED_MASK;
if (flags & MCL_FUTURE) {
current->mm->def_flags |= VM_LOCKED;
if (flags & MCL_ONFAULT)
current->mm->def_flags |= VM_LOCKONFAULT;
if (!(flags & MCL_CURRENT))
goto out;
}
if (flags & MCL_CURRENT) {
to_add |= VM_LOCKED;
if (flags & MCL_ONFAULT)
to_add |= VM_LOCKONFAULT;
}
for_each_vma(vmi, vma) {
int error;
vm_flags_t newflags;
newflags = vma->vm_flags & ~VM_LOCKED_MASK;
newflags |= to_add;
error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end,
newflags);
/* Ignore errors, but prev needs fixing up. */
if (error)
prev = vma;
cond_resched();
}
out:
return 0;
}
SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret;
if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
flags == MCL_ONFAULT)
return -EINVAL;
if (!can_do_mlock())
return -EPERM;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = -ENOMEM;
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
capable(CAP_IPC_LOCK))
ret = apply_mlockall_flags(flags);
mmap_write_unlock(current->mm);
if (!ret && (flags & MCL_CURRENT))
mm_populate(0, TASK_SIZE);
return ret;
}
SYSCALL_DEFINE0(munlockall)
{
int ret;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_mlockall_flags(0);
mmap_write_unlock(current->mm);
return ret;
}
/*
* Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
* shm segments) get accounted against the user_struct instead.
*/
static DEFINE_SPINLOCK(shmlock_user_lock);
int user_shm_lock(size_t size, struct ucounts *ucounts)
{
unsigned long lock_limit, locked;
long memlock;
int allowed = 0;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
lock_limit = rlimit(RLIMIT_MEMLOCK);
if (lock_limit != RLIM_INFINITY)
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
goto out;
}
if (!get_ucounts(ucounts)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
allowed = 0;
goto out;
}
allowed = 1;
out:
spin_unlock(&shmlock_user_lock);
return allowed;
}
void user_shm_unlock(size_t size, struct ucounts *ucounts)
{
spin_lock(&shmlock_user_lock);
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT);
spin_unlock(&shmlock_user_lock);
put_ucounts(ucounts);
}
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
#define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
#include <linux/bits.h>
#include <asm/barrier.h>
#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
#endif
/*
* Generic definitions for bit operations, should not be used in regular code
* directly.
*/
/**
* generic___set_bit - Set a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
*
* Unlike set_bit(), this function is non-atomic and may be reordered.
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
static __always_inline void
generic___set_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
*p |= mask;
}
static __always_inline void
generic___clear_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
*p &= ~mask;
}
/**
* generic___change_bit - Toggle a bit in memory
* @nr: the bit to change
* @addr: the address to start counting from
*
* Unlike change_bit(), this function is non-atomic and may be reordered.
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
static __always_inline void
generic___change_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
*p ^= mask;
}
/**
* generic___test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is non-atomic and can be reordered.
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
*/
static __always_inline bool
generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old = *p;
*p = old | mask;
return (old & mask) != 0;
}
/**
* generic___test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*
* This operation is non-atomic and can be reordered.
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
*/
static __always_inline bool
generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old = *p;
*p = old & ~mask;
return (old & mask) != 0;
}
/* WARNING: non atomic and it can be reordered! */
static __always_inline bool
generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old = *p;
*p = old ^ mask;
return (old & mask) != 0;
}
/**
* generic_test_bit - Determine whether a bit is set
* @nr: bit number to test
* @addr: Address to start counting from
*/
static __always_inline bool
generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
{
/*
* Unlike the bitops with the '__' prefix above, this one *is* atomic,
* so `volatile` must always stay here with no cast-aways. See
* `Documentation/atomic_bitops.txt` for the details.
*/
return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
}
/**
* generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
* @nr: bit number to test
* @addr: Address to start counting from
*/
static __always_inline bool
generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
{
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
}
/*
* const_*() definitions provide good compile-time optimizations when
* the passed arguments can be resolved at compile time.
*/
#define const___set_bit generic___set_bit
#define const___clear_bit generic___clear_bit
#define const___change_bit generic___change_bit
#define const___test_and_set_bit generic___test_and_set_bit
#define const___test_and_clear_bit generic___test_and_clear_bit
#define const___test_and_change_bit generic___test_and_change_bit
#define const_test_bit_acquire generic_test_bit_acquire
/**
* const_test_bit - Determine whether a bit is set
* @nr: bit number to test
* @addr: Address to start counting from
*
* A version of generic_test_bit() which discards the `volatile` qualifier to
* allow a compiler to optimize code harder. Non-atomic and to be called only
* for testing compile-time constants, e.g. by the corresponding macros, not
* directly from "regular" code.
*/
static __always_inline bool
const_test_bit(unsigned long nr, const volatile unsigned long *addr)
{
const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr);
unsigned long mask = BIT_MASK(nr);
unsigned long val = *p;
return !!(val & mask);
}
#endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*
* For policy-specific per-blkcg data:
* Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
* Arianna Avanzini <avanzini.arianna@gmail.com>
*/
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/ctype.h>
#include <linux/resume_user_mode.h>
#include <linux/psi.h>
#include <linux/part_stat.h>
#include "blk.h"
#include "blk-cgroup.h"
#include "blk-ioprio.h"
#include "blk-throttle.h"
static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu);
/*
* blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
* blkcg_pol_register_mutex nests outside of it and synchronizes entire
* policy [un]register operations including cgroup file additions /
* removals. Putting cgroup file registration outside blkcg_pol_mutex
* allows grabbing it from cgroup callbacks.
*/
static DEFINE_MUTEX(blkcg_pol_register_mutex);
static DEFINE_MUTEX(blkcg_pol_mutex);
struct blkcg blkcg_root;
EXPORT_SYMBOL_GPL(blkcg_root);
struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
EXPORT_SYMBOL_GPL(blkcg_root_css);
static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */
bool blkcg_debug_stats = false;
static DEFINE_RAW_SPINLOCK(blkg_stat_lock);
#define BLKG_DESTROY_BATCH_SIZE 64
/*
* Lockless lists for tracking IO stats update
*
* New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg).
* There are multiple blkg's (one for each block device) attached to each
* blkcg. The rstat code keeps track of which cpu has IO stats updated,
* but it doesn't know which blkg has the updated stats. If there are many
* block devices in a system, the cost of iterating all the blkg's to flush
* out the IO stats can be high. To reduce such overhead, a set of percpu
* lockless lists (lhead) per blkcg are used to track the set of recently
* updated iostat_cpu's since the last flush. An iostat_cpu will be put
* onto the lockless list on the update side [blk_cgroup_bio_start()] if
* not there yet and then removed when being flushed [blkcg_rstat_flush()].
* References to blkg are gotten and then put back in the process to
* protect against blkg removal.
*
* Return: 0 if successful or -ENOMEM if allocation fails.
*/
static int init_blkcg_llists(struct blkcg *blkcg)
{
int cpu;
blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL);
if (!blkcg->lhead)
return -ENOMEM;
for_each_possible_cpu(cpu)
init_llist_head(per_cpu_ptr(blkcg->lhead, cpu));
return 0;
}
/**
* blkcg_css - find the current css
*
* Find the css associated with either the kthread or the current task.
* This may return a dying css, so it is up to the caller to use tryget logic
* to confirm it is alive and well.
*/
static struct cgroup_subsys_state *blkcg_css(void)
{
struct cgroup_subsys_state *css;
css = kthread_blkcg();
if (css)
return css;
return task_css(current, io_cgrp_id);
}
static bool blkcg_policy_enabled(struct request_queue *q,
const struct blkcg_policy *pol)
{
return pol && test_bit(pol->plid, q->blkcg_pols);
}
static void blkg_free_workfn(struct work_struct *work)
{
struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
free_work);
struct request_queue *q = blkg->q;
int i;
/*
* pd_free_fn() can also be called from blkcg_deactivate_policy(),
* in order to make sure pd_free_fn() is called in order, the deletion
* of the list blkg->q_node is delayed to here from blkg_destroy(), and
* blkcg_mutex is used to synchronize blkg_free_workfn() and
* blkcg_deactivate_policy().
*/
mutex_lock(&q->blkcg_mutex);
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (blkg->pd[i])
blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
if (blkg->parent)
blkg_put(blkg->parent);
spin_lock_irq(&q->queue_lock);
list_del_init(&blkg->q_node);
spin_unlock_irq(&q->queue_lock);
mutex_unlock(&q->blkcg_mutex);
blk_put_queue(q);
free_percpu(blkg->iostat_cpu);
percpu_ref_exit(&blkg->refcnt);
kfree(blkg);
}
/**
* blkg_free - free a blkg
* @blkg: blkg to free
*
* Free @blkg which may be partially allocated.
*/
static void blkg_free(struct blkcg_gq *blkg)
{
if (!blkg)
return;
/*
* Both ->pd_free_fn() and request queue's release handler may
* sleep, so free us by scheduling one work func
*/
INIT_WORK(&blkg->free_work, blkg_free_workfn);
schedule_work(&blkg->free_work);
}
static void __blkg_release(struct rcu_head *rcu)
{
struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
struct blkcg *blkcg = blkg->blkcg;
int cpu;
#ifdef CONFIG_BLK_CGROUP_PUNT_BIO
WARN_ON(!bio_list_empty(&blkg->async_bios));
#endif
/*
* Flush all the non-empty percpu lockless lists before releasing
* us, given these stat belongs to us.
*
* blkg_stat_lock is for serializing blkg stat update
*/
for_each_possible_cpu(cpu)
__blkcg_rstat_flush(blkcg, cpu);
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
blkg_free(blkg);
}
/*
* A group is RCU protected, but having an rcu lock does not mean that one
* can access all the fields of blkg and assume these are valid. For
* example, don't try to follow throtl_data and request queue links.
*
* Having a reference to blkg under an rcu allows accesses to only values
* local to groups like group stats and group rate limits.
*/
static void blkg_release(struct percpu_ref *ref)
{
struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt);
call_rcu(&blkg->rcu_head, __blkg_release);
}
#ifdef CONFIG_BLK_CGROUP_PUNT_BIO
static struct workqueue_struct *blkcg_punt_bio_wq;
static void blkg_async_bio_workfn(struct work_struct *work)
{
struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
async_bio_work);
struct bio_list bios = BIO_EMPTY_LIST;
struct bio *bio;
struct blk_plug plug;
bool need_plug = false;
/* as long as there are pending bios, @blkg can't go away */
spin_lock(&blkg->async_bio_lock);
bio_list_merge_init(&bios, &blkg->async_bios);
spin_unlock(&blkg->async_bio_lock);
/* start plug only when bio_list contains at least 2 bios */
if (bios.head && bios.head->bi_next) {
need_plug = true;
blk_start_plug(&plug);
}
while ((bio = bio_list_pop(&bios)))
submit_bio(bio);
if (need_plug)
blk_finish_plug(&plug);
}
/*
* When a shared kthread issues a bio for a cgroup, doing so synchronously can
* lead to priority inversions as the kthread can be trapped waiting for that
* cgroup. Use this helper instead of submit_bio to punt the actual issuing to
* a dedicated per-blkcg work item to avoid such priority inversions.
*/
void blkcg_punt_bio_submit(struct bio *bio)
{
struct blkcg_gq *blkg = bio->bi_blkg;
if (blkg->parent) {
spin_lock(&blkg->async_bio_lock);
bio_list_add(&blkg->async_bios, bio);
spin_unlock(&blkg->async_bio_lock);
queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work);
} else {
/* never bounce for the root cgroup */
submit_bio(bio);
}
}
EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit);
static int __init blkcg_punt_bio_init(void)
{
blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
WQ_MEM_RECLAIM | WQ_FREEZABLE |
WQ_UNBOUND | WQ_SYSFS, 0);
if (!blkcg_punt_bio_wq)
return -ENOMEM;
return 0;
}
subsys_initcall(blkcg_punt_bio_init);
#endif /* CONFIG_BLK_CGROUP_PUNT_BIO */
/**
* bio_blkcg_css - return the blkcg CSS associated with a bio
* @bio: target bio
*
* This returns the CSS for the blkcg associated with a bio, or %NULL if not
* associated. Callers are expected to either handle %NULL or know association
* has been done prior to calling this.
*/
struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio)
{
if (!bio || !bio->bi_blkg)
return NULL;
return &bio->bi_blkg->blkcg->css;
}
EXPORT_SYMBOL_GPL(bio_blkcg_css);
/**
* blkcg_parent - get the parent of a blkcg
* @blkcg: blkcg of interest
*
* Return the parent blkcg of @blkcg. Can be called anytime.
*/
static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
{
return css_to_blkcg(blkcg->css.parent);
}
/**
* blkg_alloc - allocate a blkg
* @blkcg: block cgroup the new blkg is associated with
* @disk: gendisk the new blkg is associated with
* @gfp_mask: allocation mask to use
*
* Allocate a new blkg associating @blkcg and @disk.
*/
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
gfp_t gfp_mask)
{
struct blkcg_gq *blkg;
int i, cpu;
/* alloc and init base part */
blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node);
if (!blkg)
return NULL;
if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask))
goto out_free_blkg;
blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
if (!blkg->iostat_cpu)
goto out_exit_refcnt;
if (!blk_get_queue(disk->queue))
goto out_free_iostat;
blkg->q = disk->queue;
INIT_LIST_HEAD(&blkg->q_node);
blkg->blkcg = blkcg;
blkg->iostat.blkg = blkg;
#ifdef CONFIG_BLK_CGROUP_PUNT_BIO
spin_lock_init(&blkg->async_bio_lock);
bio_list_init(&blkg->async_bios);
INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
#endif
u64_stats_init(&blkg->iostat.sync);
for_each_possible_cpu(cpu) {
u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync);
per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg;
}
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkg_policy_data *pd;
if (!blkcg_policy_enabled(disk->queue, pol))
continue;
/* alloc per-policy data and attach it to blkg */
pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask);
if (!pd)
goto out_free_pds;
blkg->pd[i] = pd;
pd->blkg = blkg;
pd->plid = i;
pd->online = false;
}
return blkg;
out_free_pds:
while (--i >= 0)
if (blkg->pd[i])
blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
blk_put_queue(disk->queue);
out_free_iostat:
free_percpu(blkg->iostat_cpu);
out_exit_refcnt:
percpu_ref_exit(&blkg->refcnt);
out_free_blkg:
kfree(blkg);
return NULL;
}
/*
* If @new_blkg is %NULL, this function tries to allocate a new one as
* necessary using %GFP_NOWAIT. @new_blkg is always consumed on return.
*/
static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
struct blkcg_gq *new_blkg)
{
struct blkcg_gq *blkg;
int i, ret;
lockdep_assert_held(&disk->queue->queue_lock);
/* request_queue is dying, do not create/recreate a blkg */
if (blk_queue_dying(disk->queue)) {
ret = -ENODEV;
goto err_free_blkg;
}
/* blkg holds a reference to blkcg */
if (!css_tryget_online(&blkcg->css)) {
ret = -ENODEV;
goto err_free_blkg;
}
/* allocate */
if (!new_blkg) {
new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN);
if (unlikely(!new_blkg)) {
ret = -ENOMEM;
goto err_put_css;
}
}
blkg = new_blkg;
/* link parent */
if (blkcg_parent(blkcg)) {
blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue);
if (WARN_ON_ONCE(!blkg->parent)) {
ret = -ENODEV;
goto err_put_css;
}
blkg_get(blkg->parent);
}
/* invoke per-policy init */
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_init_fn)
pol->pd_init_fn(blkg->pd[i]);
}
/* insert */
spin_lock(&blkcg->lock);
ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg);
if (likely(!ret)) {
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
list_add(&blkg->q_node, &disk->queue->blkg_list);
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i]) {
if (pol->pd_online_fn)
pol->pd_online_fn(blkg->pd[i]);
blkg->pd[i]->online = true;
}
}
}
blkg->online = true;
spin_unlock(&blkcg->lock);
if (!ret)
return blkg;
/* @blkg failed fully initialized, use the usual release path */
blkg_put(blkg);
return ERR_PTR(ret);
err_put_css:
css_put(&blkcg->css);
err_free_blkg:
if (new_blkg)
blkg_free(new_blkg);
return ERR_PTR(ret);
}
/**
* blkg_lookup_create - lookup blkg, try to create one if not there
* @blkcg: blkcg of interest
* @disk: gendisk of interest
*
* Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to
* create one. blkg creation is performed recursively from blkcg_root such
* that all non-root blkg's have access to the parent blkg. This function
* should be called under RCU read lock and takes @disk->queue->queue_lock.
*
* Returns the blkg or the closest blkg if blkg_create() fails as it walks
* down from root.
*/
static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
struct gendisk *disk)
{
struct request_queue *q = disk->queue;
struct blkcg_gq *blkg;
unsigned long flags;
WARN_ON_ONCE(!rcu_read_lock_held());
blkg = blkg_lookup(blkcg, q);
if (blkg)
return blkg;
spin_lock_irqsave(&q->queue_lock, flags);
blkg = blkg_lookup(blkcg, q);
if (blkg) {
if (blkcg != &blkcg_root &&
blkg != rcu_dereference(blkcg->blkg_hint))
rcu_assign_pointer(blkcg->blkg_hint, blkg);
goto found;
}
/*
* Create blkgs walking down from blkcg_root to @blkcg, so that all
* non-root blkgs have access to their parents. Returns the closest
* blkg to the intended blkg should blkg_create() fail.
*/
while (true) {
struct blkcg *pos = blkcg;
struct blkcg *parent = blkcg_parent(blkcg);
struct blkcg_gq *ret_blkg = q->root_blkg;
while (parent) {
blkg = blkg_lookup(parent, q);
if (blkg) {
/* remember closest blkg */
ret_blkg = blkg;
break;
}
pos = parent;
parent = blkcg_parent(parent);
}
blkg = blkg_create(pos, disk, NULL);
if (IS_ERR(blkg)) {
blkg = ret_blkg;
break;
}
if (pos == blkcg)
break;
}
found:
spin_unlock_irqrestore(&q->queue_lock, flags);
return blkg;
}
static void blkg_destroy(struct blkcg_gq *blkg)
{
struct blkcg *blkcg = blkg->blkcg;
int i;
lockdep_assert_held(&blkg->q->queue_lock);
lockdep_assert_held(&blkcg->lock);
/*
* blkg stays on the queue list until blkg_free_workfn(), see details in
* blkg_free_workfn(), hence this function can be called from
* blkcg_destroy_blkgs() first and again from blkg_destroy_all() before
* blkg_free_workfn().
*/
if (hlist_unhashed(&blkg->blkcg_node))
return;
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && blkg->pd[i]->online) {
blkg->pd[i]->online = false;
if (pol->pd_offline_fn)
pol->pd_offline_fn(blkg->pd[i]);
}
}
blkg->online = false;
radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
hlist_del_init_rcu(&blkg->blkcg_node);
/*
* Both setting lookup hint to and clearing it from @blkg are done
* under queue_lock. If it's not pointing to @blkg now, it never
* will. Hint assignment itself can race safely.
*/
if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
rcu_assign_pointer(blkcg->blkg_hint, NULL);
/*
* Put the reference taken at the time of creation so that when all
* queues are gone, group can be destroyed.
*/
percpu_ref_kill(&blkg->refcnt);
}
static void blkg_destroy_all(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
struct blkcg_gq *blkg;
int count = BLKG_DESTROY_BATCH_SIZE;
int i;
restart:
spin_lock_irq(&q->queue_lock);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
struct blkcg *blkcg = blkg->blkcg;
if (hlist_unhashed(&blkg->blkcg_node))
continue;
spin_lock(&blkcg->lock);
blkg_destroy(blkg);
spin_unlock(&blkcg->lock);
/*
* in order to avoid holding the spin lock for too long, release
* it when a batch of blkgs are destroyed.
*/
if (!(--count)) {
count = BLKG_DESTROY_BATCH_SIZE;
spin_unlock_irq(&q->queue_lock);
cond_resched();
goto restart;
}
}
/*
* Mark policy deactivated since policy offline has been done, and
* the free is scheduled, so future blkcg_deactivate_policy() can
* be bypassed
*/
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (pol)
__clear_bit(pol->plid, q->blkcg_pols);
}
q->root_blkg = NULL;
spin_unlock_irq(&q->queue_lock);
}
static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
{
int i;
for (i = 0; i < BLKG_IOSTAT_NR; i++) {
dst->bytes[i] = src->bytes[i];
dst->ios[i] = src->ios[i];
}
}
static void __blkg_clear_stat(struct blkg_iostat_set *bis)
{
struct blkg_iostat cur = {0};
unsigned long flags;
flags = u64_stats_update_begin_irqsave(&bis->sync);
blkg_iostat_set(&bis->cur, &cur);
blkg_iostat_set(&bis->last, &cur);
u64_stats_update_end_irqrestore(&bis->sync, flags);
}
static void blkg_clear_stat(struct blkcg_gq *blkg)
{
int cpu;
for_each_possible_cpu(cpu) {
struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu);
__blkg_clear_stat(s);
}
__blkg_clear_stat(&blkg->iostat);
}
static int blkcg_reset_stats(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 val)
{
struct blkcg *blkcg = css_to_blkcg(css);
struct blkcg_gq *blkg;
int i;
pr_info_once("blkio.%s is deprecated\n", cftype->name);
mutex_lock(&blkcg_pol_mutex);
spin_lock_irq(&blkcg->lock);
/*
* Note that stat reset is racy - it doesn't synchronize against
* stat updates. This is a debug feature which shouldn't exist
* anyway. If you get hit by a race, retry.
*/
hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
blkg_clear_stat(blkg);
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_reset_stats_fn)
pol->pd_reset_stats_fn(blkg->pd[i]);
}
}
spin_unlock_irq(&blkcg->lock);
mutex_unlock(&blkcg_pol_mutex);
return 0;
}
const char *blkg_dev_name(struct blkcg_gq *blkg)
{
if (!blkg->q->disk)
return NULL;
return bdi_dev_name(blkg->q->disk->bdi);
}
/**
* blkcg_print_blkgs - helper for printing per-blkg data
* @sf: seq_file to print to
* @blkcg: blkcg of interest
* @prfill: fill function to print out a blkg
* @pol: policy in question
* @data: data to be passed to @prfill
* @show_total: to print out sum of prfill return values or not
*
* This function invokes @prfill on each blkg of @blkcg if pd for the
* policy specified by @pol exists. @prfill is invoked with @sf, the
* policy data and @data and the matching queue lock held. If @show_total
* is %true, the sum of the return values from @prfill is printed with
* "Total" label at the end.
*
* This is to be used to construct print functions for
* cftype->read_seq_string method.
*/
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
u64 (*prfill)(struct seq_file *,
struct blkg_policy_data *, int),
const struct blkcg_policy *pol, int data,
bool show_total)
{
struct blkcg_gq *blkg;
u64 total = 0;
rcu_read_lock();
hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
spin_lock_irq(&blkg->q->queue_lock);
if (blkcg_policy_enabled(blkg->q, pol))
total += prfill(sf, blkg->pd[pol->plid], data);
spin_unlock_irq(&blkg->q->queue_lock);
}
rcu_read_unlock();
if (show_total)
seq_printf(sf, "Total %llu\n", (unsigned long long)total);
}
EXPORT_SYMBOL_GPL(blkcg_print_blkgs);
/**
* __blkg_prfill_u64 - prfill helper for a single u64 value
* @sf: seq_file to print to
* @pd: policy private data of interest
* @v: value to print
*
* Print @v to @sf for the device associated with @pd.
*/
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
{
const char *dname = blkg_dev_name(pd->blkg);
if (!dname)
return 0;
seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
/**
* blkg_conf_init - initialize a blkg_conf_ctx
* @ctx: blkg_conf_ctx to initialize
* @input: input string
*
* Initialize @ctx which can be used to parse blkg config input string @input.
* Once initialized, @ctx can be used with blkg_conf_open_bdev() and
* blkg_conf_prep(), and must be cleaned up with blkg_conf_exit().
*/
void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input)
{
*ctx = (struct blkg_conf_ctx){ .input = input };
}
EXPORT_SYMBOL_GPL(blkg_conf_init);
/**
* blkg_conf_open_bdev - parse and open bdev for per-blkg config update
* @ctx: blkg_conf_ctx initialized with blkg_conf_init()
*
* Parse the device node prefix part, MAJ:MIN, of per-blkg config update from
* @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is
* set to point past the device node prefix.
*
* This function may be called multiple times on @ctx and the extra calls become
* NOOPs. blkg_conf_prep() implicitly calls this function. Use this function
* explicitly if bdev access is needed without resolving the blkcg / policy part
* of @ctx->input. Returns -errno on error.
*/
int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
{
char *input = ctx->input;
unsigned int major, minor;
struct block_device *bdev;
int key_len;
if (ctx->bdev)
return 0;
if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
return -EINVAL;
input += key_len;
if (!isspace(*input))
return -EINVAL;
input = skip_spaces(input);
bdev = blkdev_get_no_open(MKDEV(major, minor), false);
if (!bdev)
return -ENODEV;
if (bdev_is_partition(bdev)) {
blkdev_put_no_open(bdev);
return -ENODEV;
}
mutex_lock(&bdev->bd_queue->rq_qos_mutex);
if (!disk_live(bdev->bd_disk)) {
blkdev_put_no_open(bdev);
mutex_unlock(&bdev->bd_queue->rq_qos_mutex);
return -ENODEV;
}
ctx->body = input;
ctx->bdev = bdev;
return 0;
}
/*
* Similar to blkg_conf_open_bdev, but additionally freezes the queue,
* acquires q->elevator_lock, and ensures the correct locking order
* between q->elevator_lock and q->rq_qos_mutex.
*
* This function returns negative error on failure. On success it returns
* memflags which must be saved and later passed to blkg_conf_exit_frozen
* for restoring the memalloc scope.
*/
unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx)
{
int ret;
unsigned long memflags;
if (ctx->bdev)
return -EINVAL;
ret = blkg_conf_open_bdev(ctx);
if (ret < 0)
return ret;
/*
* At this point, we haven’t started protecting anything related to QoS,
* so we release q->rq_qos_mutex here, which was first acquired in blkg_
* conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing
* the queue and acquiring q->elevator_lock to maintain the correct
* locking order.
*/
mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex);
memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue);
mutex_lock(&ctx->bdev->bd_queue->elevator_lock);
mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex);
return memflags;
}
/**
* blkg_conf_prep - parse and prepare for per-blkg config update
* @blkcg: target block cgroup
* @pol: target policy
* @ctx: blkg_conf_ctx initialized with blkg_conf_init()
*
* Parse per-blkg config update from @ctx->input and initialize @ctx
* accordingly. On success, @ctx->body points to the part of @ctx->input
* following MAJ:MIN, @ctx->bdev points to the target block device and
* @ctx->blkg to the blkg being configured.
*
* blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this
* function returns with queue lock held and must be followed by
* blkg_conf_exit().
*/
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
struct blkg_conf_ctx *ctx)
__acquires(&bdev->bd_queue->queue_lock)
{
struct gendisk *disk;
struct request_queue *q;
struct blkcg_gq *blkg;
int ret;
ret = blkg_conf_open_bdev(ctx);
if (ret)
return ret;
disk = ctx->bdev->bd_disk;
q = disk->queue;
/*
* blkcg_deactivate_policy() requires queue to be frozen, we can grab
* q_usage_counter to prevent concurrent with blkcg_deactivate_policy().
*/
ret = blk_queue_enter(q, 0);
if (ret)
goto fail;
spin_lock_irq(&q->queue_lock);
if (!blkcg_policy_enabled(q, pol)) {
ret = -EOPNOTSUPP;
goto fail_unlock;
}
blkg = blkg_lookup(blkcg, q);
if (blkg)
goto success;
/*
* Create blkgs walking down from blkcg_root to @blkcg, so that all
* non-root blkgs have access to their parents.
*/
while (true) {
struct blkcg *pos = blkcg;
struct blkcg *parent;
struct blkcg_gq *new_blkg;
parent = blkcg_parent(blkcg);
while (parent && !blkg_lookup(parent, q)) {
pos = parent;
parent = blkcg_parent(parent);
}
/* Drop locks to do new blkg allocation with GFP_KERNEL. */
spin_unlock_irq(&q->queue_lock);
new_blkg = blkg_alloc(pos, disk, GFP_KERNEL);
if (unlikely(!new_blkg)) {
ret = -ENOMEM;
goto fail_exit_queue;
}
if (radix_tree_preload(GFP_KERNEL)) {
blkg_free(new_blkg);
ret = -ENOMEM;
goto fail_exit_queue;
}
spin_lock_irq(&q->queue_lock);
if (!blkcg_policy_enabled(q, pol)) {
blkg_free(new_blkg);
ret = -EOPNOTSUPP;
goto fail_preloaded;
}
blkg = blkg_lookup(pos, q);
if (blkg) {
blkg_free(new_blkg);
} else {
blkg = blkg_create(pos, disk, new_blkg);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
goto fail_preloaded;
}
}
radix_tree_preload_end();
if (pos == blkcg)
goto success;
}
success:
blk_queue_exit(q);
ctx->blkg = blkg;
return 0;
fail_preloaded:
radix_tree_preload_end();
fail_unlock:
spin_unlock_irq(&q->queue_lock);
fail_exit_queue:
blk_queue_exit(q);
fail:
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
* can be bypassing for some time and it's always nice to
* avoid busy looping.
*/
if (ret == -EBUSY) {
msleep(10);
ret = restart_syscall();
}
return ret;
}
EXPORT_SYMBOL_GPL(blkg_conf_prep);
/**
* blkg_conf_exit - clean up per-blkg config update
* @ctx: blkg_conf_ctx initialized with blkg_conf_init()
*
* Clean up after per-blkg config update. This function must be called on all
* blkg_conf_ctx's initialized with blkg_conf_init().
*/
void blkg_conf_exit(struct blkg_conf_ctx *ctx)
__releases(&ctx->bdev->bd_queue->queue_lock)
__releases(&ctx->bdev->bd_queue->rq_qos_mutex)
{
if (ctx->blkg) {
spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
ctx->blkg = NULL;
}
if (ctx->bdev) {
mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex);
blkdev_put_no_open(ctx->bdev);
ctx->body = NULL;
ctx->bdev = NULL;
}
}
EXPORT_SYMBOL_GPL(blkg_conf_exit);
/*
* Similar to blkg_conf_exit, but also unfreezes the queue and releases
* q->elevator_lock. Should be used when blkg_conf_open_bdev_frozen
* is used to open the bdev.
*/
void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags)
{
if (ctx->bdev) {
struct request_queue *q = ctx->bdev->bd_queue;
blkg_conf_exit(ctx);
mutex_unlock(&q->elevator_lock);
blk_mq_unfreeze_queue(q, memflags);
}
}
static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
{
int i;
for (i = 0; i < BLKG_IOSTAT_NR; i++) {
dst->bytes[i] += src->bytes[i];
dst->ios[i] += src->ios[i];
}
}
static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
{
int i;
for (i = 0; i < BLKG_IOSTAT_NR; i++) {
dst->bytes[i] -= src->bytes[i];
dst->ios[i] -= src->ios[i];
}
}
static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur,
struct blkg_iostat *last)
{
struct blkg_iostat delta;
unsigned long flags;
/* propagate percpu delta to global */
flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
blkg_iostat_set(&delta, cur);
blkg_iostat_sub(&delta, last);
blkg_iostat_add(&blkg->iostat.cur, &delta);
blkg_iostat_add(last, &delta);
u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
}
static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
{
struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu);
struct llist_node *lnode;
struct blkg_iostat_set *bisc, *next_bisc;
unsigned long flags;
rcu_read_lock();
lnode = llist_del_all(lhead);
if (!lnode)
goto out;
/*
* For covering concurrent parent blkg update from blkg_release().
*
* When flushing from cgroup, cgroup_rstat_lock is always held, so
* this lock won't cause contention most of time.
*/
raw_spin_lock_irqsave(&blkg_stat_lock, flags);
/*
* Iterate only the iostat_cpu's queued in the lockless list.
*/
llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) {
struct blkcg_gq *blkg = bisc->blkg;
struct blkcg_gq *parent = blkg->parent;
struct blkg_iostat cur;
unsigned int seq;
/*
* Order assignment of `next_bisc` from `bisc->lnode.next` in
* llist_for_each_entry_safe and clearing `bisc->lqueued` for
* avoiding to assign `next_bisc` with new next pointer added
* in blk_cgroup_bio_start() in case of re-ordering.
*
* The pair barrier is implied in llist_add() in blk_cgroup_bio_start().
*/
smp_mb();
WRITE_ONCE(bisc->lqueued, false);
if (bisc == &blkg->iostat)
goto propagate_up; /* propagate up to parent only */
/* fetch the current per-cpu values */
do {
seq = u64_stats_fetch_begin(&bisc->sync);
blkg_iostat_set(&cur, &bisc->cur);
} while (u64_stats_fetch_retry(&bisc->sync, seq));
blkcg_iostat_update(blkg, &cur, &bisc->last);
propagate_up:
/* propagate global delta to parent (unless that's root) */
if (parent && parent->parent) {
blkcg_iostat_update(parent, &blkg->iostat.cur,
&blkg->iostat.last);
/*
* Queue parent->iostat to its blkcg's lockless
* list to propagate up to the grandparent if the
* iostat hasn't been queued yet.
*/
if (!parent->iostat.lqueued) {
struct llist_head *plhead;
plhead = per_cpu_ptr(parent->blkcg->lhead, cpu);
llist_add(&parent->iostat.lnode, plhead);
parent->iostat.lqueued = true;
}
}
}
raw_spin_unlock_irqrestore(&blkg_stat_lock, flags);
out:
rcu_read_unlock();
}
static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
{
/* Root-level stats are sourced from system-wide IO stats */
if (cgroup_parent(css->cgroup))
__blkcg_rstat_flush(css_to_blkcg(css), cpu);
}
/*
* We source root cgroup stats from the system-wide stats to avoid
* tracking the same information twice and incurring overhead when no
* cgroups are defined. For that reason, cgroup_rstat_flush in
* blkcg_print_stat does not actually fill out the iostat in the root
* cgroup's blkcg_gq.
*
* However, we would like to re-use the printing code between the root and
* non-root cgroups to the extent possible. For that reason, we simulate
* flushing the root cgroup's stats by explicitly filling in the iostat
* with disk level statistics.
*/
static void blkcg_fill_root_iostats(void)
{
struct class_dev_iter iter;
struct device *dev;
class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
while ((dev = class_dev_iter_next(&iter))) {
struct block_device *bdev = dev_to_bdev(dev);
struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg;
struct blkg_iostat tmp;
int cpu;
unsigned long flags;
memset(&tmp, 0, sizeof(tmp));
for_each_possible_cpu(cpu) {
struct disk_stats *cpu_dkstats;
cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
tmp.ios[BLKG_IOSTAT_READ] +=
cpu_dkstats->ios[STAT_READ];
tmp.ios[BLKG_IOSTAT_WRITE] +=
cpu_dkstats->ios[STAT_WRITE];
tmp.ios[BLKG_IOSTAT_DISCARD] +=
cpu_dkstats->ios[STAT_DISCARD];
// convert sectors to bytes
tmp.bytes[BLKG_IOSTAT_READ] +=
cpu_dkstats->sectors[STAT_READ] << 9;
tmp.bytes[BLKG_IOSTAT_WRITE] +=
cpu_dkstats->sectors[STAT_WRITE] << 9;
tmp.bytes[BLKG_IOSTAT_DISCARD] +=
cpu_dkstats->sectors[STAT_DISCARD] << 9;
}
flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
blkg_iostat_set(&blkg->iostat.cur, &tmp);
u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
}
class_dev_iter_exit(&iter);
}
static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
{
struct blkg_iostat_set *bis = &blkg->iostat;
u64 rbytes, wbytes, rios, wios, dbytes, dios;
const char *dname;
unsigned seq;
int i;
if (!blkg->online)
return;
dname = blkg_dev_name(blkg);
if (!dname)
return;
seq_printf(s, "%s ", dname);
do {
seq = u64_stats_fetch_begin(&bis->sync);
rbytes = bis->cur.bytes[BLKG_IOSTAT_READ];
wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE];
dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD];
rios = bis->cur.ios[BLKG_IOSTAT_READ];
wios = bis->cur.ios[BLKG_IOSTAT_WRITE];
dios = bis->cur.ios[BLKG_IOSTAT_DISCARD];
} while (u64_stats_fetch_retry(&bis->sync, seq));
if (rbytes || wbytes || rios || wios) {
seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
rbytes, wbytes, rios, wios,
dbytes, dios);
}
if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) {
seq_printf(s, " use_delay=%d delay_nsec=%llu",
atomic_read(&blkg->use_delay),
atomic64_read(&blkg->delay_nsec));
}
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (!blkg->pd[i] || !pol->pd_stat_fn)
continue;
pol->pd_stat_fn(blkg->pd[i], s);
}
seq_puts(s, "\n");
}
static int blkcg_print_stat(struct seq_file *sf, void *v)
{
struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
struct blkcg_gq *blkg;
if (!seq_css(sf)->parent)
blkcg_fill_root_iostats();
else
cgroup_rstat_flush(blkcg->css.cgroup);
rcu_read_lock();
hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
spin_lock_irq(&blkg->q->queue_lock);
blkcg_print_one_stat(blkg, sf);
spin_unlock_irq(&blkg->q->queue_lock);
}
rcu_read_unlock();
return 0;
}
static struct cftype blkcg_files[] = {
{
.name = "stat",
.seq_show = blkcg_print_stat,
},
{ } /* terminate */
};
static struct cftype blkcg_legacy_files[] = {
{
.name = "reset_stats",
.write_u64 = blkcg_reset_stats,
},
{ } /* terminate */
};
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css)
{
return &css_to_blkcg(css)->cgwb_list;
}
#endif
/*
* blkcg destruction is a three-stage process.
*
* 1. Destruction starts. The blkcg_css_offline() callback is invoked
* which offlines writeback. Here we tie the next stage of blkg destruction
* to the completion of writeback associated with the blkcg. This lets us
* avoid punting potentially large amounts of outstanding writeback to root
* while maintaining any ongoing policies. The next stage is triggered when
* the nr_cgwbs count goes to zero.
*
* 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called
* and handles the destruction of blkgs. Here the css reference held by
* the blkg is put back eventually allowing blkcg_css_free() to be called.
* This work may occur in cgwb_release_workfn() on the cgwb_release
* workqueue. Any submitted ios that fail to get the blkg ref will be
* punted to the root_blkg.
*
* 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called.
* This finally frees the blkcg.
*/
/**
* blkcg_destroy_blkgs - responsible for shooting down blkgs
* @blkcg: blkcg of interest
*
* blkgs should be removed while holding both q and blkcg locks. As blkcg lock
* is nested inside q lock, this function performs reverse double lock dancing.
* Destroying the blkgs releases the reference held on the blkcg's css allowing
* blkcg_css_free to eventually be called.
*
* This is the blkcg counterpart of ioc_release_fn().
*/
static void blkcg_destroy_blkgs(struct blkcg *blkcg)
{
might_sleep();
spin_lock_irq(&blkcg->lock);
while (!hlist_empty(&blkcg->blkg_list)) {
struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
struct blkcg_gq, blkcg_node);
struct request_queue *q = blkg->q;
if (need_resched() || !spin_trylock(&q->queue_lock)) {
/*
* Given that the system can accumulate a huge number
* of blkgs in pathological cases, check to see if we
* need to rescheduling to avoid softlockup.
*/
spin_unlock_irq(&blkcg->lock);
cond_resched();
spin_lock_irq(&blkcg->lock);
continue;
}
blkg_destroy(blkg);
spin_unlock(&q->queue_lock);
}
spin_unlock_irq(&blkcg->lock);
}
/**
* blkcg_pin_online - pin online state
* @blkcg_css: blkcg of interest
*
* While pinned, a blkcg is kept online. This is primarily used to
* impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline
* while an associated cgwb is still active.
*/
void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css)
{
refcount_inc(&css_to_blkcg(blkcg_css)->online_pin);
}
/**
* blkcg_unpin_online - unpin online state
* @blkcg_css: blkcg of interest
*
* This is primarily used to impedance-match blkg and cgwb lifetimes so
* that blkg doesn't go offline while an associated cgwb is still active.
* When this count goes to zero, all active cgwbs have finished so the
* blkcg can continue destruction by calling blkcg_destroy_blkgs().
*/
void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
{
struct blkcg *blkcg = css_to_blkcg(blkcg_css);
do {
struct blkcg *parent;
if (!refcount_dec_and_test(&blkcg->online_pin))
break;
parent = blkcg_parent(blkcg);
blkcg_destroy_blkgs(blkcg);
blkcg = parent;
} while (blkcg);
}
/**
* blkcg_css_offline - cgroup css_offline callback
* @css: css of interest
*
* This function is called when @css is about to go away. Here the cgwbs are
* offlined first and only once writeback associated with the blkcg has
* finished do we start step 2 (see above).
*/
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
/* this prevents anyone from attaching or migrating to this blkcg */
wb_blkcg_offline(css);
/* put the base online pin allowing step 2 to be triggered */
blkcg_unpin_online(css);
}
static void blkcg_css_free(struct cgroup_subsys_state *css)
{
struct blkcg *blkcg = css_to_blkcg(css);
int i;
mutex_lock(&blkcg_pol_mutex);
list_del(&blkcg->all_blkcgs_node);
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (blkcg->cpd[i])
blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);
mutex_unlock(&blkcg_pol_mutex);
free_percpu(blkcg->lhead);
kfree(blkcg);
}
static struct cgroup_subsys_state *
blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct blkcg *blkcg;
int i;
mutex_lock(&blkcg_pol_mutex);
if (!parent_css) {
blkcg = &blkcg_root;
} else {
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
if (!blkcg)
goto unlock;
}
if (init_blkcg_llists(blkcg))
goto free_blkcg;
for (i = 0; i < BLKCG_MAX_POLS ; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkcg_policy_data *cpd;
/*
* If the policy hasn't been attached yet, wait for it
* to be attached before doing anything else. Otherwise,
* check if the policy requires any specific per-cgroup
* data: if it does, allocate and initialize it.
*/
if (!pol || !pol->cpd_alloc_fn)
continue;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd)
goto free_pd_blkcg;
blkcg->cpd[i] = cpd;
cpd->blkcg = blkcg;
cpd->plid = i;
}
spin_lock_init(&blkcg->lock);
refcount_set(&blkcg->online_pin, 1);
INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN);
INIT_HLIST_HEAD(&blkcg->blkg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&blkcg->cgwb_list);
#endif
list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
mutex_unlock(&blkcg_pol_mutex);
return &blkcg->css;
free_pd_blkcg:
for (i--; i >= 0; i--)
if (blkcg->cpd[i])
blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);
free_percpu(blkcg->lhead);
free_blkcg:
if (blkcg != &blkcg_root)
kfree(blkcg);
unlock:
mutex_unlock(&blkcg_pol_mutex);
return ERR_PTR(-ENOMEM);
}
static int blkcg_css_online(struct cgroup_subsys_state *css)
{
struct blkcg *parent = blkcg_parent(css_to_blkcg(css));
/*
* blkcg_pin_online() is used to delay blkcg offline so that blkgs
* don't go offline while cgwbs are still active on them. Pin the
* parent so that offline always happens towards the root.
*/
if (parent)
blkcg_pin_online(&parent->css);
return 0;
}
void blkg_init_queue(struct request_queue *q)
{
INIT_LIST_HEAD(&q->blkg_list);
mutex_init(&q->blkcg_mutex);
}
int blkcg_init_disk(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
struct blkcg_gq *new_blkg, *blkg;
bool preloaded;
new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
if (!new_blkg)
return -ENOMEM;
preloaded = !radix_tree_preload(GFP_KERNEL);
/* Make sure the root blkg exists. */
/* spin_lock_irq can serve as RCU read-side critical section. */
spin_lock_irq(&q->queue_lock);
blkg = blkg_create(&blkcg_root, disk, new_blkg);
if (IS_ERR(blkg))
goto err_unlock;
q->root_blkg = blkg;
spin_unlock_irq(&q->queue_lock);
if (preloaded)
radix_tree_preload_end();
return 0;
err_unlock:
spin_unlock_irq(&q->queue_lock);
if (preloaded)
radix_tree_preload_end();
return PTR_ERR(blkg);
}
void blkcg_exit_disk(struct gendisk *disk)
{
blkg_destroy_all(disk);
blk_throtl_exit(disk);
}
static void blkcg_exit(struct task_struct *tsk)
{
if (tsk->throttle_disk)
put_disk(tsk->throttle_disk);
tsk->throttle_disk = NULL;
}
struct cgroup_subsys io_cgrp_subsys = {
.css_alloc = blkcg_css_alloc,
.css_online = blkcg_css_online,
.css_offline = blkcg_css_offline,
.css_free = blkcg_css_free,
.css_rstat_flush = blkcg_rstat_flush,
.dfl_cftypes = blkcg_files,
.legacy_cftypes = blkcg_legacy_files,
.legacy_name = "blkio",
.exit = blkcg_exit,
#ifdef CONFIG_MEMCG
/*
* This ensures that, if available, memcg is automatically enabled
* together on the default hierarchy so that the owner cgroup can
* be retrieved from writeback pages.
*/
.depends_on = 1 << memory_cgrp_id,
#endif
};
EXPORT_SYMBOL_GPL(io_cgrp_subsys);
/**
* blkcg_activate_policy - activate a blkcg policy on a gendisk
* @disk: gendisk of interest
* @pol: blkcg policy to activate
*
* Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through
* bypass mode to populate its blkgs with policy_data for @pol.
*
* Activation happens with @disk bypassed, so nobody would be accessing blkgs
* from IO path. Update of each blkg is protected by both queue and blkcg
* locks so that holding either lock and testing blkcg_policy_enabled() is
* always enough for dereferencing policy data.
*
* The caller is responsible for synchronizing [de]activations and policy
* [un]registerations. Returns 0 on success, -errno on failure.
*/
int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
{
struct request_queue *q = disk->queue;
struct blkg_policy_data *pd_prealloc = NULL;
struct blkcg_gq *blkg, *pinned_blkg = NULL;
unsigned int memflags;
int ret;
if (blkcg_policy_enabled(q, pol))
return 0;
/*
* Policy is allowed to be registered without pd_alloc_fn/pd_free_fn,
* for example, ioprio. Such policy will work on blkcg level, not disk
* level, and don't need to be activated.
*/
if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn))
return -EINVAL;
if (queue_is_mq(q))
memflags = blk_mq_freeze_queue(q);
retry:
spin_lock_irq(&q->queue_lock);
/* blkg_list is pushed at the head, reverse walk to initialize parents first */
list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
struct blkg_policy_data *pd;
if (blkg->pd[pol->plid])
continue;
/* If prealloc matches, use it; otherwise try GFP_NOWAIT */
if (blkg == pinned_blkg) {
pd = pd_prealloc;
pd_prealloc = NULL;
} else {
pd = pol->pd_alloc_fn(disk, blkg->blkcg,
GFP_NOWAIT | __GFP_NOWARN);
}
if (!pd) {
/*
* GFP_NOWAIT failed. Free the existing one and
* prealloc for @blkg w/ GFP_KERNEL.
*/
if (pinned_blkg)
blkg_put(pinned_blkg);
blkg_get(blkg);
pinned_blkg = blkg;
spin_unlock_irq(&q->queue_lock);
if (pd_prealloc)
pol->pd_free_fn(pd_prealloc);
pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg,
GFP_KERNEL);
if (pd_prealloc)
goto retry;
else
goto enomem;
}
spin_lock(&blkg->blkcg->lock);
pd->blkg = blkg;
pd->plid = pol->plid;
blkg->pd[pol->plid] = pd;
if (pol->pd_init_fn)
pol->pd_init_fn(pd);
if (pol->pd_online_fn)
pol->pd_online_fn(pd);
pd->online = true;
spin_unlock(&blkg->blkcg->lock);
}
__set_bit(pol->plid, q->blkcg_pols);
ret = 0;
spin_unlock_irq(&q->queue_lock);
out:
if (queue_is_mq(q))
blk_mq_unfreeze_queue(q, memflags);
if (pinned_blkg)
blkg_put(pinned_blkg);
if (pd_prealloc)
pol->pd_free_fn(pd_prealloc);
return ret;
enomem:
/* alloc failed, take down everything */
spin_lock_irq(&q->queue_lock);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
struct blkcg *blkcg = blkg->blkcg;
struct blkg_policy_data *pd;
spin_lock(&blkcg->lock);
pd = blkg->pd[pol->plid];
if (pd) {
if (pd->online && pol->pd_offline_fn)
pol->pd_offline_fn(pd);
pd->online = false;
pol->pd_free_fn(pd);
blkg->pd[pol->plid] = NULL;
}
spin_unlock(&blkcg->lock);
}
spin_unlock_irq(&q->queue_lock);
ret = -ENOMEM;
goto out;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);
/**
* blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk
* @disk: gendisk of interest
* @pol: blkcg policy to deactivate
*
* Deactivate @pol on @disk. Follows the same synchronization rules as
* blkcg_activate_policy().
*/
void blkcg_deactivate_policy(struct gendisk *disk,
const struct blkcg_policy *pol)
{
struct request_queue *q = disk->queue;
struct blkcg_gq *blkg;
unsigned int memflags;
if (!blkcg_policy_enabled(q, pol))
return;
if (queue_is_mq(q))
memflags = blk_mq_freeze_queue(q);
mutex_lock(&q->blkcg_mutex);
spin_lock_irq(&q->queue_lock);
__clear_bit(pol->plid, q->blkcg_pols);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
struct blkcg *blkcg = blkg->blkcg;
spin_lock(&blkcg->lock);
if (blkg->pd[pol->plid]) {
if (blkg->pd[pol->plid]->online && pol->pd_offline_fn)
pol->pd_offline_fn(blkg->pd[pol->plid]);
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
spin_unlock(&blkcg->lock);
}
spin_unlock_irq(&q->queue_lock);
mutex_unlock(&q->blkcg_mutex);
if (queue_is_mq(q))
blk_mq_unfreeze_queue(q, memflags);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
static void blkcg_free_all_cpd(struct blkcg_policy *pol)
{
struct blkcg *blkcg;
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
if (blkcg->cpd[pol->plid]) {
pol->cpd_free_fn(blkcg->cpd[pol->plid]);
blkcg->cpd[pol->plid] = NULL;
}
}
}
/**
* blkcg_policy_register - register a blkcg policy
* @pol: blkcg policy to register
*
* Register @pol with blkcg core. Might sleep and @pol may be modified on
* successful registration. Returns 0 on success and -errno on failure.
*/
int blkcg_policy_register(struct blkcg_policy *pol)
{
struct blkcg *blkcg;
int i, ret;
/*
* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy
* without pd_alloc_fn/pd_free_fn can't be activated.
*/
if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
(!pol->pd_alloc_fn ^ !pol->pd_free_fn))
return -EINVAL;
mutex_lock(&blkcg_pol_register_mutex);
mutex_lock(&blkcg_pol_mutex);
/* find an empty slot */
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (!blkcg_policy[i])
break;
if (i >= BLKCG_MAX_POLS) {
pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n");
ret = -ENOSPC;
goto err_unlock;
}
/* register @pol */
pol->plid = i;
blkcg_policy[pol->plid] = pol;
/* allocate and install cpd's */
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
struct blkcg_policy_data *cpd;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd) {
ret = -ENOMEM;
goto err_free_cpds;
}
blkcg->cpd[pol->plid] = cpd;
cpd->blkcg = blkcg;
cpd->plid = pol->plid;
}
}
mutex_unlock(&blkcg_pol_mutex);
/* everything is in place, add intf files for the new policy */
if (pol->dfl_cftypes == pol->legacy_cftypes) {
WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys,
pol->dfl_cftypes));
} else {
WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
pol->dfl_cftypes));
WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
pol->legacy_cftypes));
}
mutex_unlock(&blkcg_pol_register_mutex);
return 0;
err_free_cpds:
if (pol->cpd_free_fn)
blkcg_free_all_cpd(pol);
blkcg_policy[pol->plid] = NULL;
err_unlock:
mutex_unlock(&blkcg_pol_mutex);
mutex_unlock(&blkcg_pol_register_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_policy_register);
/**
* blkcg_policy_unregister - unregister a blkcg policy
* @pol: blkcg policy to unregister
*
* Undo blkcg_policy_register(@pol). Might sleep.
*/
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
mutex_lock(&blkcg_pol_register_mutex);
if (WARN_ON(blkcg_policy[pol->plid] != pol))
goto out_unlock;
/* kill the intf files first */
if (pol->dfl_cftypes)
cgroup_rm_cftypes(pol->dfl_cftypes);
if (pol->legacy_cftypes)
cgroup_rm_cftypes(pol->legacy_cftypes);
/* remove cpds and unregister */
mutex_lock(&blkcg_pol_mutex);
if (pol->cpd_free_fn)
blkcg_free_all_cpd(pol);
blkcg_policy[pol->plid] = NULL;
mutex_unlock(&blkcg_pol_mutex);
out_unlock:
mutex_unlock(&blkcg_pol_register_mutex);
}
EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
/*
* Scale the accumulated delay based on how long it has been since we updated
* the delay. We only call this when we are adding delay, in case it's been a
* while since we added delay, and when we are checking to see if we need to
* delay a task, to account for any delays that may have occurred.
*/
static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
{
u64 old = atomic64_read(&blkg->delay_start);
/* negative use_delay means no scaling, see blkcg_set_delay() */
if (atomic_read(&blkg->use_delay) < 0)
return;
/*
* We only want to scale down every second. The idea here is that we
* want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
* time window. We only want to throttle tasks for recent delay that
* has occurred, in 1 second time windows since that's the maximum
* things can be throttled. We save the current delay window in
* blkg->last_delay so we know what amount is still left to be charged
* to the blkg from this point onward. blkg->last_use keeps track of
* the use_delay counter. The idea is if we're unthrottling the blkg we
* are ok with whatever is happening now, and we can take away more of
* the accumulated delay as we've already throttled enough that
* everybody is happy with their IO latencies.
*/
if (time_before64(old + NSEC_PER_SEC, now) &&
atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) {
u64 cur = atomic64_read(&blkg->delay_nsec);
u64 sub = min_t(u64, blkg->last_delay, now - old);
int cur_use = atomic_read(&blkg->use_delay);
/*
* We've been unthrottled, subtract a larger chunk of our
* accumulated delay.
*/
if (cur_use < blkg->last_use)
sub = max_t(u64, sub, blkg->last_delay >> 1);
/*
* This shouldn't happen, but handle it anyway. Our delay_nsec
* should only ever be growing except here where we subtract out
* min(last_delay, 1 second), but lord knows bugs happen and I'd
* rather not end up with negative numbers.
*/
if (unlikely(cur < sub)) {
atomic64_set(&blkg->delay_nsec, 0);
blkg->last_delay = 0;
} else {
atomic64_sub(sub, &blkg->delay_nsec);
blkg->last_delay = cur - sub;
}
blkg->last_use = cur_use;
}
}
/*
* This is called when we want to actually walk up the hierarchy and check to
* see if we need to throttle, and then actually throttle if there is some
* accumulated delay. This should only be called upon return to user space so
* we're not holding some lock that would induce a priority inversion.
*/
static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
{
unsigned long pflags;
bool clamp;
u64 now = blk_time_get_ns();
u64 exp;
u64 delay_nsec = 0;
int tok;
while (blkg->parent) {
int use_delay = atomic_read(&blkg->use_delay);
if (use_delay) {
u64 this_delay;
blkcg_scale_delay(blkg, now);
this_delay = atomic64_read(&blkg->delay_nsec);
if (this_delay > delay_nsec) {
delay_nsec = this_delay;
clamp = use_delay > 0;
}
}
blkg = blkg->parent;
}
if (!delay_nsec)
return;
/*
* Let's not sleep for all eternity if we've amassed a huge delay.
* Swapping or metadata IO can accumulate 10's of seconds worth of
* delay, and we want userspace to be able to do _something_ so cap the
* delays at 0.25s. If there's 10's of seconds worth of delay then the
* tasks will be delayed for 0.25 second for every syscall. If
* blkcg_set_delay() was used as indicated by negative use_delay, the
* caller is responsible for regulating the range.
*/
if (clamp)
delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
if (use_memdelay)
psi_memstall_enter(&pflags);
exp = ktime_add_ns(now, delay_nsec);
tok = io_schedule_prepare();
do {
__set_current_state(TASK_KILLABLE);
if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS))
break;
} while (!fatal_signal_pending(current));
io_schedule_finish(tok);
if (use_memdelay)
psi_memstall_leave(&pflags);
}
/**
* blkcg_maybe_throttle_current - throttle the current task if it has been marked
*
* This is only called if we've been marked with set_notify_resume(). Obviously
* we can be set_notify_resume() for reasons other than blkcg throttling, so we
* check to see if current->throttle_disk is set and if not this doesn't do
* anything. This should only ever be called by the resume code, it's not meant
* to be called by people willy-nilly as it will actually do the work to
* throttle the task if it is setup for throttling.
*/
void blkcg_maybe_throttle_current(void)
{
struct gendisk *disk = current->throttle_disk;
struct blkcg *blkcg;
struct blkcg_gq *blkg;
bool use_memdelay = current->use_memdelay;
if (!disk)
return;
current->throttle_disk = NULL;
current->use_memdelay = false;
rcu_read_lock();
blkcg = css_to_blkcg(blkcg_css());
if (!blkcg)
goto out;
blkg = blkg_lookup(blkcg, disk->queue); if (!blkg)
goto out;
if (!blkg_tryget(blkg))
goto out;
rcu_read_unlock();
blkcg_maybe_throttle_blkg(blkg, use_memdelay);
blkg_put(blkg);
put_disk(disk);
return;
out:
rcu_read_unlock();
}
/**
* blkcg_schedule_throttle - this task needs to check for throttling
* @disk: disk to throttle
* @use_memdelay: do we charge this to memory delay for PSI
*
* This is called by the IO controller when we know there's delay accumulated
* for the blkg for this task. We do not pass the blkg because there are places
* we call this that may not have that information, the swapping code for
* instance will only have a block_device at that point. This set's the
* notify_resume for the task to check and see if it requires throttling before
* returning to user space.
*
* We will only schedule once per syscall. You can call this over and over
* again and it will only do the check once upon return to user space, and only
* throttle once. If the task needs to be throttled again it'll need to be
* re-set at the next time we see the task.
*/
void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay)
{
if (unlikely(current->flags & PF_KTHREAD))
return;
if (current->throttle_disk != disk) {
if (test_bit(GD_DEAD, &disk->state))
return;
get_device(disk_to_dev(disk));
if (current->throttle_disk)
put_disk(current->throttle_disk);
current->throttle_disk = disk;
}
if (use_memdelay)
current->use_memdelay = use_memdelay;
set_notify_resume(current);
}
/**
* blkcg_add_delay - add delay to this blkg
* @blkg: blkg of interest
* @now: the current time in nanoseconds
* @delta: how many nanoseconds of delay to add
*
* Charge @delta to the blkg's current delay accumulation. This is used to
* throttle tasks if an IO controller thinks we need more throttling.
*/
void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
{
if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
return;
blkcg_scale_delay(blkg, now);
atomic64_add(delta, &blkg->delay_nsec);
}
/**
* blkg_tryget_closest - try and get a blkg ref on the closet blkg
* @bio: target bio
* @css: target css
*
* As the failure mode here is to walk up the blkg tree, this ensure that the
* blkg->parent pointers are always valid. This returns the blkg that it ended
* up taking a reference on or %NULL if no reference was taken.
*/
static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
struct cgroup_subsys_state *css)
{
struct blkcg_gq *blkg, *ret_blkg = NULL;
rcu_read_lock();
blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk);
while (blkg) {
if (blkg_tryget(blkg)) {
ret_blkg = blkg;
break;
}
blkg = blkg->parent;
}
rcu_read_unlock();
return ret_blkg;
}
/**
* bio_associate_blkg_from_css - associate a bio with a specified css
* @bio: target bio
* @css: target css
*
* Associate @bio with the blkg found by combining the css's blkg and the
* request_queue of the @bio. An association failure is handled by walking up
* the blkg tree. Therefore, the blkg associated can be anything between @blkg
* and q->root_blkg. This situation only happens when a cgroup is dying and
* then the remaining bios will spill to the closest alive blkg.
*
* A reference will be taken on the blkg and will be released when @bio is
* freed.
*/
void bio_associate_blkg_from_css(struct bio *bio,
struct cgroup_subsys_state *css)
{
if (bio->bi_blkg)
blkg_put(bio->bi_blkg);
if (css && css->parent) {
bio->bi_blkg = blkg_tryget_closest(bio, css);
} else {
blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg);
bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg;
}
}
EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
/**
* bio_associate_blkg - associate a bio with a blkg
* @bio: target bio
*
* Associate @bio with the blkg found from the bio's css and request_queue.
* If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is
* already associated, the css is reused and association redone as the
* request_queue may have changed.
*/
void bio_associate_blkg(struct bio *bio)
{
struct cgroup_subsys_state *css;
if (blk_op_is_passthrough(bio->bi_opf))
return;
rcu_read_lock();
if (bio->bi_blkg)
css = bio_blkcg_css(bio);
else
css = blkcg_css();
bio_associate_blkg_from_css(bio, css);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(bio_associate_blkg);
/**
* bio_clone_blkg_association - clone blkg association from src to dst bio
* @dst: destination bio
* @src: source bio
*/
void bio_clone_blkg_association(struct bio *dst, struct bio *src)
{
if (src->bi_blkg)
bio_associate_blkg_from_css(dst, bio_blkcg_css(src));
}
EXPORT_SYMBOL_GPL(bio_clone_blkg_association);
static int blk_cgroup_io_type(struct bio *bio)
{
if (op_is_discard(bio->bi_opf))
return BLKG_IOSTAT_DISCARD;
if (op_is_write(bio->bi_opf))
return BLKG_IOSTAT_WRITE;
return BLKG_IOSTAT_READ;
}
void blk_cgroup_bio_start(struct bio *bio)
{
struct blkcg *blkcg = bio->bi_blkg->blkcg;
int rwd = blk_cgroup_io_type(bio), cpu;
struct blkg_iostat_set *bis;
unsigned long flags;
if (!cgroup_subsys_on_dfl(io_cgrp_subsys))
return;
/* Root-level stats are sourced from system-wide IO stats */
if (!cgroup_parent(blkcg->css.cgroup))
return;
cpu = get_cpu();
bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu);
flags = u64_stats_update_begin_irqsave(&bis->sync);
/*
* If the bio is flagged with BIO_CGROUP_ACCT it means this is a split
* bio and we would have already accounted for the size of the bio.
*/
if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
bio_set_flag(bio, BIO_CGROUP_ACCT);
bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
}
bis->cur.ios[rwd]++;
/*
* If the iostat_cpu isn't in a lockless list, put it into the
* list to indicate that a stat update is pending.
*/
if (!READ_ONCE(bis->lqueued)) {
struct llist_head *lhead = this_cpu_ptr(blkcg->lhead);
llist_add(&bis->lnode, lhead);
WRITE_ONCE(bis->lqueued, true);
}
u64_stats_update_end_irqrestore(&bis->sync, flags);
cgroup_rstat_updated(blkcg->css.cgroup, cpu);
put_cpu();
}
bool blk_cgroup_congested(void)
{
struct blkcg *blkcg;
bool ret = false;
rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg;
blkcg = blkcg_parent(blkcg)) {
if (atomic_read(&blkcg->congestion_count)) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
module_param(blkcg_debug_stats, bool, 0644);
MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
#define _ASM_GENERIC_BITOPS_LOCK_H_
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <asm/barrier.h>
/**
* arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and provides acquire barrier semantics if
* the returned value is 0.
* It can be used to implement bit locks.
*/
static __always_inline int
arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p)
{
long old;
unsigned long mask = BIT_MASK(nr);
p += BIT_WORD(nr);
if (READ_ONCE(*p) & mask)
return 1;
old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
return !!(old & mask);
}
/**
* arch_clear_bit_unlock - Clear a bit in memory, for unlock
* @nr: the bit to set
* @addr: the address to start counting from
*
* This operation is atomic and provides release barrier semantics.
*/
static __always_inline void
arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
}
/**
* arch___clear_bit_unlock - Clear a bit in memory, for unlock
* @nr: the bit to set
* @addr: the address to start counting from
*
* A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
* the bits in the word are protected by this lock some archs can use weaker
* ops to safely unlock.
*
* See for example x86's implementation.
*/
static inline void
arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
{
unsigned long old;
p += BIT_WORD(nr);
old = READ_ONCE(*p);
old &= ~BIT_MASK(nr);
raw_atomic_long_set_release((atomic_long_t *)p, old);
}
#ifndef arch_xor_unlock_is_negative_byte
static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
volatile unsigned long *p)
{
long old;
old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p);
return !!(old & BIT(7));
}
#endif
#include <asm-generic/bitops/instrumented-lock.h>
#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
// SPDX-License-Identifier: GPL-2.0
/*
* Workingset detection
*
* Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
*/
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/shmem_fs.h>
#include <linux/pagemap.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "internal.h"
/*
* Double CLOCK lists
*
* Per node, two clock lists are maintained for file pages: the
* inactive and the active list. Freshly faulted pages start out at
* the head of the inactive list and page reclaim scans pages from the
* tail. Pages that are accessed multiple times on the inactive list
* are promoted to the active list, to protect them from reclaim,
* whereas active pages are demoted to the inactive list when the
* active list grows too big.
*
* fault ------------------------+
* |
* +--------------+ | +-------------+
* reclaim <- | inactive | <-+-- demotion | active | <--+
* +--------------+ +-------------+ |
* | |
* +-------------- promotion ------------------+
*
*
* Access frequency and refault distance
*
* A workload is thrashing when its pages are frequently used but they
* are evicted from the inactive list every time before another access
* would have promoted them to the active list.
*
* In cases where the average access distance between thrashing pages
* is bigger than the size of memory there is nothing that can be
* done - the thrashing set could never fit into memory under any
* circumstance.
*
* However, the average access distance could be bigger than the
* inactive list, yet smaller than the size of memory. In this case,
* the set could fit into memory if it weren't for the currently
* active pages - which may be used more, hopefully less frequently:
*
* +-memory available to cache-+
* | |
* +-inactive------+-active----+
* a b | c d e f g h i | J K L M N |
* +---------------+-----------+
*
* It is prohibitively expensive to accurately track access frequency
* of pages. But a reasonable approximation can be made to measure
* thrashing on the inactive list, after which refaulting pages can be
* activated optimistically to compete with the existing active pages.
*
* Approximating inactive page access frequency - Observations:
*
* 1. When a page is accessed for the first time, it is added to the
* head of the inactive list, slides every existing inactive page
* towards the tail by one slot, and pushes the current tail page
* out of memory.
*
* 2. When a page is accessed for the second time, it is promoted to
* the active list, shrinking the inactive list by one slot. This
* also slides all inactive pages that were faulted into the cache
* more recently than the activated page towards the tail of the
* inactive list.
*
* Thus:
*
* 1. The sum of evictions and activations between any two points in
* time indicate the minimum number of inactive pages accessed in
* between.
*
* 2. Moving one inactive page N page slots towards the tail of the
* list requires at least N inactive page accesses.
*
* Combining these:
*
* 1. When a page is finally evicted from memory, the number of
* inactive pages accessed while the page was in cache is at least
* the number of page slots on the inactive list.
*
* 2. In addition, measuring the sum of evictions and activations (E)
* at the time of a page's eviction, and comparing it to another
* reading (R) at the time the page faults back into memory tells
* the minimum number of accesses while the page was not cached.
* This is called the refault distance.
*
* Because the first access of the page was the fault and the second
* access the refault, we combine the in-cache distance with the
* out-of-cache distance to get the complete minimum access distance
* of this page:
*
* NR_inactive + (R - E)
*
* And knowing the minimum access distance of a page, we can easily
* tell if the page would be able to stay in cache assuming all page
* slots in the cache were available:
*
* NR_inactive + (R - E) <= NR_inactive + NR_active
*
* If we have swap we should consider about NR_inactive_anon and
* NR_active_anon, so for page cache and anonymous respectively:
*
* NR_inactive_file + (R - E) <= NR_inactive_file + NR_active_file
* + NR_inactive_anon + NR_active_anon
*
* NR_inactive_anon + (R - E) <= NR_inactive_anon + NR_active_anon
* + NR_inactive_file + NR_active_file
*
* Which can be further simplified to:
*
* (R - E) <= NR_active_file + NR_inactive_anon + NR_active_anon
*
* (R - E) <= NR_active_anon + NR_inactive_file + NR_active_file
*
* Put into words, the refault distance (out-of-cache) can be seen as
* a deficit in inactive list space (in-cache). If the inactive list
* had (R - E) more page slots, the page would not have been evicted
* in between accesses, but activated instead. And on a full system,
* the only thing eating into inactive list space is active pages.
*
*
* Refaulting inactive pages
*
* All that is known about the active list is that the pages have been
* accessed more than once in the past. This means that at any given
* time there is actually a good chance that pages on the active list
* are no longer in active use.
*
* So when a refault distance of (R - E) is observed and there are at
* least (R - E) pages in the userspace workingset, the refaulting page
* is activated optimistically in the hope that (R - E) pages are actually
* used less frequently than the refaulting page - or even not used at
* all anymore.
*
* That means if inactive cache is refaulting with a suitable refault
* distance, we assume the cache workingset is transitioning and put
* pressure on the current workingset.
*
* If this is wrong and demotion kicks in, the pages which are truly
* used more frequently will be reactivated while the less frequently
* used once will be evicted from memory.
*
* But if this is right, the stale pages will be pushed out of memory
* and the used pages get to stay in cache.
*
* Refaulting active pages
*
* If on the other hand the refaulting pages have recently been
* deactivated, it means that the active list is no longer protecting
* actively used cache from reclaim. The cache is NOT transitioning to
* a different workingset; the existing workingset is thrashing in the
* space allocated to the page cache.
*
*
* Implementation
*
* For each node's LRU lists, a counter for inactive evictions and
* activations is maintained (node->nonresident_age).
*
* On eviction, a snapshot of this counter (along with some bits to
* identify the node) is stored in the now empty page cache
* slot of the evicted page. This is called a shadow entry.
*
* On cache misses for which there are shadow entries, an eligible
* refault distance will immediately activate the refaulting page.
*/
#define WORKINGSET_SHIFT 1
#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \
WORKINGSET_SHIFT + NODES_SHIFT + \
MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
/*
* Eviction timestamps need to be able to cover the full range of
* actionable refaults. However, bits are tight in the xarray
* entry, and after storing the identifier for the lruvec there might
* not be enough left to represent every single actionable refault. In
* that case, we have to sacrifice granularity for distance, and group
* evictions into coarser buckets by shaving off lower timestamp bits.
*/
static unsigned int bucket_order __read_mostly;
static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
bool workingset)
{
eviction &= EVICTION_MASK;
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
eviction = (eviction << WORKINGSET_SHIFT) | workingset;
return xa_mk_value(eviction);
}
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
unsigned long *evictionp, bool *workingsetp)
{
unsigned long entry = xa_to_value(shadow);
int memcgid, nid;
bool workingset;
workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1);
entry >>= WORKINGSET_SHIFT;
nid = entry & ((1UL << NODES_SHIFT) - 1);
entry >>= NODES_SHIFT;
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
entry >>= MEM_CGROUP_ID_SHIFT;
*memcgidp = memcgid;
*pgdat = NODE_DATA(nid);
*evictionp = entry;
*workingsetp = workingset;
}
#ifdef CONFIG_LRU_GEN
static void *lru_gen_eviction(struct folio *folio)
{
int hist;
unsigned long token;
unsigned long min_seq;
struct lruvec *lruvec;
struct lru_gen_folio *lrugen;
int type = folio_is_file_lru(folio);
int delta = folio_nr_pages(folio);
int refs = folio_lru_refs(folio);
bool workingset = folio_test_workingset(folio);
int tier = lru_tier_from_refs(refs, workingset);
struct mem_cgroup *memcg = folio_memcg(folio);
struct pglist_data *pgdat = folio_pgdat(folio);
BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
lrugen = &lruvec->lrugen;
min_seq = READ_ONCE(lrugen->min_seq[type]);
token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0);
hist = lru_hist_from_seq(min_seq);
atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);
return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset);
}
/*
* Tests if the shadow entry is for a folio that was recently evicted.
* Fills in @lruvec, @token, @workingset with the values unpacked from shadow.
*/
static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec,
unsigned long *token, bool *workingset)
{
int memcg_id;
unsigned long max_seq;
struct mem_cgroup *memcg;
struct pglist_data *pgdat;
unpack_shadow(shadow, &memcg_id, &pgdat, token, workingset);
memcg = mem_cgroup_from_id(memcg_id);
*lruvec = mem_cgroup_lruvec(memcg, pgdat);
max_seq = READ_ONCE((*lruvec)->lrugen.max_seq);
max_seq &= EVICTION_MASK >> LRU_REFS_WIDTH;
return abs_diff(max_seq, *token >> LRU_REFS_WIDTH) < MAX_NR_GENS;
}
static void lru_gen_refault(struct folio *folio, void *shadow)
{
bool recent;
int hist, tier, refs;
bool workingset;
unsigned long token;
struct lruvec *lruvec;
struct lru_gen_folio *lrugen;
int type = folio_is_file_lru(folio);
int delta = folio_nr_pages(folio);
rcu_read_lock();
recent = lru_gen_test_recent(shadow, &lruvec, &token, &workingset);
if (lruvec != folio_lruvec(folio))
goto unlock;
mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);
if (!recent)
goto unlock;
lrugen = &lruvec->lrugen;
hist = lru_hist_from_seq(READ_ONCE(lrugen->min_seq[type]));
refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + 1;
tier = lru_tier_from_refs(refs, workingset);
atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
/* see folio_add_lru() where folio_set_active() will be called */
if (lru_gen_in_fault())
mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
if (workingset) {
folio_set_workingset(folio);
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
} else
set_mask_bits(&folio->flags, LRU_REFS_MASK, (refs - 1UL) << LRU_REFS_PGOFF);
unlock:
rcu_read_unlock();
}
#else /* !CONFIG_LRU_GEN */
static void *lru_gen_eviction(struct folio *folio)
{
return NULL;
}
static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec,
unsigned long *token, bool *workingset)
{
return false;
}
static void lru_gen_refault(struct folio *folio, void *shadow)
{
}
#endif /* CONFIG_LRU_GEN */
/**
* workingset_age_nonresident - age non-resident entries as LRU ages
* @lruvec: the lruvec that was aged
* @nr_pages: the number of pages to count
*
* As in-memory pages are aged, non-resident pages need to be aged as
* well, in order for the refault distances later on to be comparable
* to the in-memory dimensions. This function allows reclaim and LRU
* operations to drive the non-resident aging along in parallel.
*/
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
{
/*
* Reclaiming a cgroup means reclaiming all its children in a
* round-robin fashion. That means that each cgroup has an LRU
* order that is composed of the LRU orders of its child
* cgroups; and every page has an LRU position not just in the
* cgroup that owns it, but in all of that group's ancestors.
*
* So when the physical inactive list of a leaf cgroup ages,
* the virtual inactive lists of all its parents, including
* the root cgroup's, age as well.
*/
do {
atomic_long_add(nr_pages, &lruvec->nonresident_age);
} while ((lruvec = parent_lruvec(lruvec)));
}
/**
* workingset_eviction - note the eviction of a folio from memory
* @target_memcg: the cgroup that is causing the reclaim
* @folio: the folio being evicted
*
* Return: a shadow entry to be stored in @folio->mapping->i_pages in place
* of the evicted @folio so that a later refault can be detected.
*/
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
{
struct pglist_data *pgdat = folio_pgdat(folio);
unsigned long eviction;
struct lruvec *lruvec;
int memcgid;
/* Folio is fully exclusive and pins folio's memory cgroup pointer */
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (lru_gen_enabled())
return lru_gen_eviction(folio);
lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
/* XXX: target_memcg can be NULL, go through lruvec */
memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
eviction = atomic_long_read(&lruvec->nonresident_age);
eviction >>= bucket_order;
workingset_age_nonresident(lruvec, folio_nr_pages(folio));
return pack_shadow(memcgid, pgdat, eviction,
folio_test_workingset(folio));
}
/**
* workingset_test_recent - tests if the shadow entry is for a folio that was
* recently evicted. Also fills in @workingset with the value unpacked from
* shadow.
* @shadow: the shadow entry to be tested.
* @file: whether the corresponding folio is from the file lru.
* @workingset: where the workingset value unpacked from shadow should
* be stored.
* @flush: whether to flush cgroup rstat.
*
* Return: true if the shadow is for a recently evicted folio; false otherwise.
*/
bool workingset_test_recent(void *shadow, bool file, bool *workingset,
bool flush)
{
struct mem_cgroup *eviction_memcg;
struct lruvec *eviction_lruvec;
unsigned long refault_distance;
unsigned long workingset_size;
unsigned long refault;
int memcgid;
struct pglist_data *pgdat;
unsigned long eviction;
if (lru_gen_enabled()) {
bool recent;
rcu_read_lock();
recent = lru_gen_test_recent(shadow, &eviction_lruvec, &eviction, workingset);
rcu_read_unlock();
return recent;
}
rcu_read_lock();
unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset);
eviction <<= bucket_order;
/*
* Look up the memcg associated with the stored ID. It might
* have been deleted since the folio's eviction.
*
* Note that in rare events the ID could have been recycled
* for a new cgroup that refaults a shared folio. This is
* impossible to tell from the available data. However, this
* should be a rare and limited disturbance, and activations
* are always speculative anyway. Ultimately, it's the aging
* algorithm's job to shake out the minimum access frequency
* for the active cache.
*
* XXX: On !CONFIG_MEMCG, this will always return NULL; it
* would be better if the root_mem_cgroup existed in all
* configurations instead.
*/
eviction_memcg = mem_cgroup_from_id(memcgid);
if (!mem_cgroup_tryget(eviction_memcg))
eviction_memcg = NULL;
rcu_read_unlock();
if (!mem_cgroup_disabled() && !eviction_memcg)
return false;
/*
* Flush stats (and potentially sleep) outside the RCU read section.
*
* Note that workingset_test_recent() itself might be called in RCU read
* section (for e.g, in cachestat) - these callers need to skip flushing
* stats (via the flush argument).
*
* XXX: With per-memcg flushing and thresholding, is ratelimiting
* still needed here?
*/
if (flush)
mem_cgroup_flush_stats_ratelimited(eviction_memcg);
eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
refault = atomic_long_read(&eviction_lruvec->nonresident_age);
/*
* Calculate the refault distance
*
* The unsigned subtraction here gives an accurate distance
* across nonresident_age overflows in most cases. There is a
* special case: usually, shadow entries have a short lifetime
* and are either refaulted or reclaimed along with the inode
* before they get too old. But it is not impossible for the
* nonresident_age to lap a shadow entry in the field, which
* can then result in a false small refault distance, leading
* to a false activation should this old entry actually
* refault again. However, earlier kernels used to deactivate
* unconditionally with *every* reclaim invocation for the
* longest time, so the occasional inappropriate activation
* leading to pressure on the active list is not a problem.
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
/*
* Compare the distance to the existing workingset size. We
* don't activate pages that couldn't stay resident even if
* all the memory was available to the workingset. Whether
* workingset competition needs to consider anon or not depends
* on having free swap space.
*/
workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
if (!file) {
workingset_size += lruvec_page_state(eviction_lruvec,
NR_INACTIVE_FILE);
}
if (mem_cgroup_get_nr_swap_pages(eviction_memcg) > 0) {
workingset_size += lruvec_page_state(eviction_lruvec,
NR_ACTIVE_ANON);
if (file) {
workingset_size += lruvec_page_state(eviction_lruvec,
NR_INACTIVE_ANON);
}
}
mem_cgroup_put(eviction_memcg);
return refault_distance <= workingset_size;
}
/**
* workingset_refault - Evaluate the refault of a previously evicted folio.
* @folio: The freshly allocated replacement folio.
* @shadow: Shadow entry of the evicted folio.
*
* Calculates and evaluates the refault distance of the previously
* evicted folio in the context of the node and the memcg whose memory
* pressure caused the eviction.
*/
void workingset_refault(struct folio *folio, void *shadow)
{
bool file = folio_is_file_lru(folio);
struct pglist_data *pgdat;
struct mem_cgroup *memcg;
struct lruvec *lruvec;
bool workingset;
long nr;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (lru_gen_enabled()) {
lru_gen_refault(folio, shadow);
return;
}
/*
* The activation decision for this folio is made at the level
* where the eviction occurred, as that is where the LRU order
* during folio reclaim is being determined.
*
* However, the cgroup that will own the folio is the one that
* is actually experiencing the refault event. Make sure the folio is
* locked to guarantee folio_memcg() stability throughout.
*/
nr = folio_nr_pages(folio);
memcg = folio_memcg(folio);
pgdat = folio_pgdat(folio);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
if (!workingset_test_recent(shadow, file, &workingset, true))
return;
folio_set_active(folio);
workingset_age_nonresident(lruvec, nr);
mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr);
/* Folio was active prior to eviction */
if (workingset) {
folio_set_workingset(folio);
/*
* XXX: Move to folio_add_lru() when it supports new vs
* putback
*/
lru_note_cost_refault(folio);
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
}
}
/**
* workingset_activation - note a page activation
* @folio: Folio that is being activated.
*/
void workingset_activation(struct folio *folio)
{
/*
* Filter non-memcg pages here, e.g. unmap can call
* mark_page_accessed() on VDSO pages.
*/
if (mem_cgroup_disabled() || folio_memcg_charged(folio))
workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio));
}
/*
* Shadow entries reflect the share of the working set that does not
* fit into memory, so their number depends on the access pattern of
* the workload. In most cases, they will refault or get reclaimed
* along with the inode, but a (malicious) workload that streams
* through files with a total size several times that of available
* memory, while preventing the inodes from being reclaimed, can
* create excessive amounts of shadow nodes. To keep a lid on this,
* track shadow nodes and reclaim them when they grow way past the
* point where they would still be useful.
*/
struct list_lru shadow_nodes;
void workingset_update_node(struct xa_node *node)
{
struct address_space *mapping;
struct page *page = virt_to_page(node);
/*
* Track non-empty nodes that contain only shadow entries;
* unlink those that contain pages or are being freed.
*
* Avoid acquiring the list_lru lock when the nodes are
* already where they should be. The list_empty() test is safe
* as node->private_list is protected by the i_pages lock.
*/
mapping = container_of(node->array, struct address_space, i_pages);
lockdep_assert_held(&mapping->i_pages.xa_lock); if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add_obj(&shadow_nodes, &node->private_list);
__inc_node_page_state(page, WORKINGSET_NODES);
}
} else {
if (!list_empty(&node->private_list)) { list_lru_del_obj(&shadow_nodes, &node->private_list);
__dec_node_page_state(page, WORKINGSET_NODES);
}
}
}
static unsigned long count_shadow_nodes(struct shrinker *shrinker,
struct shrink_control *sc)
{
unsigned long max_nodes;
unsigned long nodes;
unsigned long pages;
nodes = list_lru_shrink_count(&shadow_nodes, sc);
if (!nodes)
return SHRINK_EMPTY;
/*
* Approximate a reasonable limit for the nodes
* containing shadow entries. We don't need to keep more
* shadow entries than possible pages on the active list,
* since refault distances bigger than that are dismissed.
*
* The size of the active list converges toward 100% of
* overall page cache as memory grows, with only a tiny
* inactive list. Assume the total cache size for that.
*
* Nodes might be sparsely populated, with only one shadow
* entry in the extreme case. Obviously, we cannot keep one
* node for every eligible shadow entry, so compromise on a
* worst-case density of 1/8th. Below that, not all eligible
* refaults can be detected anymore.
*
* On 64-bit with 7 xa_nodes per page and 64 slots
* each, this will reclaim shadow entries when they consume
* ~1.8% of available memory:
*
* PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
*/
#ifdef CONFIG_MEMCG
if (sc->memcg) {
struct lruvec *lruvec;
int i;
mem_cgroup_flush_stats_ratelimited(sc->memcg);
lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
pages += lruvec_page_state_local(lruvec,
NR_LRU_BASE + i);
pages += lruvec_page_state_local(
lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
pages += lruvec_page_state_local(
lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
} else
#endif
pages = node_present_pages(sc->nid);
max_nodes = pages >> (XA_CHUNK_SHIFT - 3);
if (nodes <= max_nodes)
return 0;
return nodes - max_nodes;
}
static enum lru_status shadow_lru_isolate(struct list_head *item,
struct list_lru_one *lru,
void *arg) __must_hold(lru->lock)
{
struct xa_node *node = container_of(item, struct xa_node, private_list);
struct address_space *mapping;
int ret;
/*
* Page cache insertions and deletions synchronously maintain
* the shadow node LRU under the i_pages lock and the
* &lru->lock. Because the page cache tree is emptied before
* the inode can be destroyed, holding the &lru->lock pins any
* address_space that has nodes on the LRU.
*
* We can then safely transition to the i_pages lock to
* pin only the address_space of the particular node we want
* to reclaim, take the node off-LRU, and drop the &lru->lock.
*/
mapping = container_of(node->array, struct address_space, i_pages);
/* Coming from the list, invert the lock order */
if (!xa_trylock(&mapping->i_pages)) {
spin_unlock_irq(&lru->lock);
ret = LRU_RETRY;
goto out;
}
/* For page cache we need to hold i_lock */
if (mapping->host != NULL) {
if (!spin_trylock(&mapping->host->i_lock)) {
xa_unlock(&mapping->i_pages);
spin_unlock_irq(&lru->lock);
ret = LRU_RETRY;
goto out;
}
}
list_lru_isolate(lru, item);
__dec_node_page_state(virt_to_page(node), WORKINGSET_NODES);
spin_unlock(&lru->lock);
/*
* The nodes should only contain one or more shadow entries,
* no pages, so we expect to be able to remove them all and
* delete and free the empty node afterwards.
*/
if (WARN_ON_ONCE(!node->nr_values))
goto out_invalid;
if (WARN_ON_ONCE(node->count != node->nr_values))
goto out_invalid;
xa_delete_node(node, workingset_update_node);
__inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM);
out_invalid:
xa_unlock_irq(&mapping->i_pages);
if (mapping->host != NULL) {
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
}
ret = LRU_REMOVED_RETRY;
out:
cond_resched();
return ret;
}
static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
struct shrink_control *sc)
{
/* list_lru lock nests inside the IRQ-safe i_pages lock */
return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate,
NULL);
}
/*
* Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
* i_pages lock.
*/
static struct lock_class_key shadow_nodes_key;
static int __init workingset_init(void)
{
struct shrinker *workingset_shadow_shrinker;
unsigned int timestamp_bits;
unsigned int max_order;
int ret = -ENOMEM;
BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT);
/*
* Calculate the eviction bucket size to cover the longest
* actionable refault distance, which is currently half of
* memory (totalram_pages/2). However, memory hotplug may add
* some more pages at runtime, so keep working with up to
* double the initial memory by using totalram_pages as-is.
*/
timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
max_order = fls_long(totalram_pages() - 1);
if (max_order > timestamp_bits)
bucket_order = max_order - timestamp_bits;
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
timestamp_bits, max_order, bucket_order);
workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE |
SHRINKER_MEMCG_AWARE,
"mm-shadow");
if (!workingset_shadow_shrinker)
goto err;
ret = list_lru_init_memcg_key(&shadow_nodes, workingset_shadow_shrinker,
&shadow_nodes_key);
if (ret)
goto err_list_lru;
workingset_shadow_shrinker->count_objects = count_shadow_nodes;
workingset_shadow_shrinker->scan_objects = scan_shadow_nodes;
/* ->count reports only fully expendable nodes */
workingset_shadow_shrinker->seeks = 0;
shrinker_register(workingset_shadow_shrinker);
return 0;
err_list_lru:
shrinker_free(workingset_shadow_shrinker);
err:
return ret;
}
module_init(workingset_init);
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/mmu_context.h
*
* Copyright (C) 1996 Russell King.
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_MMU_CONTEXT_H
#define __ASM_MMU_CONTEXT_H
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
#include <linux/sched.h>
#include <linux/sched/hotplug.h>
#include <linux/mm_types.h>
#include <linux/pgtable.h>
#include <linux/pkeys.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
#include <asm/gcs.h>
#include <asm/proc-fns.h>
#include <asm/cputype.h>
#include <asm/sysreg.h>
#include <asm/tlbflush.h>
extern bool rodata_full;
static inline void contextidr_thread_switch(struct task_struct *next)
{
if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
return;
write_sysreg(task_pid_nr(next), contextidr_el1);
isb();
}
/*
* Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0.
*/
static inline void cpu_set_reserved_ttbr0_nosync(void)
{
unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
write_sysreg(ttbr, ttbr0_el1);
}
static inline void cpu_set_reserved_ttbr0(void)
{
cpu_set_reserved_ttbr0_nosync();
isb();
}
void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
{
BUG_ON(pgd == swapper_pg_dir);
cpu_do_switch_mm(virt_to_phys(pgd),mm);
}
/*
* TCR.T0SZ value to use when the ID map is active.
*/
#define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS)
/*
* Ensure TCR.T0SZ is set to the provided value.
*/
static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
{
unsigned long tcr = read_sysreg(tcr_el1);
if ((tcr & TCR_T0SZ_MASK) == t0sz)
return;
tcr &= ~TCR_T0SZ_MASK;
tcr |= t0sz;
write_sysreg(tcr, tcr_el1);
isb();
}
#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual))
#define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz)
/*
* Remove the idmap from TTBR0_EL1 and install the pgd of the active mm.
*
* The idmap lives in the same VA range as userspace, but uses global entries
* and may use a different TCR_EL1.T0SZ. To avoid issues resulting from
* speculative TLB fetches, we must temporarily install the reserved page
* tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ.
*
* If current is a not a user task, the mm covers the TTBR1_EL1 page tables,
* which should not be installed in TTBR0_EL1. In this case we can leave the
* reserved page tables in place.
*/
static inline void cpu_uninstall_idmap(void)
{
struct mm_struct *mm = current->active_mm;
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
cpu_set_default_tcr_t0sz();
if (mm != &init_mm && !system_uses_ttbr0_pan())
cpu_switch_mm(mm->pgd, mm);
}
static inline void cpu_install_idmap(void)
{
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
cpu_set_idmap_tcr_t0sz();
cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
}
/*
* Load our new page tables. A strict BBM approach requires that we ensure that
* TLBs are free of any entries that may overlap with the global mappings we are
* about to install.
*
* For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero
* page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime
* services), while for a userspace-driven test_resume cycle it points to
* userspace page tables (and we must point it at a zero page ourselves).
*
* We change T0SZ as part of installing the idmap. This is undone by
* cpu_uninstall_idmap() in __cpu_suspend_exit().
*/
static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
{
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
__cpu_set_tcr_t0sz(t0sz);
/* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */
write_sysreg(ttbr0, ttbr0_el1);
isb();
}
void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp);
static inline void cpu_enable_swapper_cnp(void)
{
__cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true);
}
static inline void cpu_replace_ttbr1(pgd_t *pgdp)
{
/*
* Only for early TTBR1 replacement before cpucaps are finalized and
* before we've decided whether to use CNP.
*/
WARN_ON(system_capabilities_finalized());
__cpu_replace_ttbr1(pgdp, false);
}
/*
* It would be nice to return ASIDs back to the allocator, but unfortunately
* that introduces a race with a generation rollover where we could erroneously
* free an ASID allocated in a future generation. We could workaround this by
* freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap),
* but we'd then need to make sure that we didn't dirty any TLBs afterwards.
* Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you
* take CPU migration into account.
*/
void check_and_switch_context(struct mm_struct *mm);
#define init_new_context(tsk, mm) init_new_context(tsk, mm)
static inline int
init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
atomic64_set(&mm->context.id, 0);
refcount_set(&mm->context.pinned, 0);
/* pkey 0 is the default, so always reserve it. */
mm->context.pkey_allocation_map = BIT(0);
return 0;
}
static inline void arch_dup_pkeys(struct mm_struct *oldmm,
struct mm_struct *mm)
{
/* Duplicate the oldmm pkey state in mm: */
mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
}
static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
arch_dup_pkeys(oldmm, mm);
return 0;
}
static inline void arch_exit_mmap(struct mm_struct *mm)
{
}
static inline void arch_unmap(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
}
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
static inline void update_saved_ttbr0(struct task_struct *tsk,
struct mm_struct *mm)
{
u64 ttbr;
if (!system_uses_ttbr0_pan())
return;
if (mm == &init_mm)
ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
else
ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48;
WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
}
#else
static inline void update_saved_ttbr0(struct task_struct *tsk,
struct mm_struct *mm)
{
}
#endif
#define enter_lazy_tlb enter_lazy_tlb
static inline void
enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
/*
* We don't actually care about the ttbr0 mapping, so point it at the
* zero page.
*/
update_saved_ttbr0(tsk, &init_mm);
}
static inline void __switch_mm(struct mm_struct *next)
{
/*
* init_mm.pgd does not contain any user mappings and it is always
* active for kernel addresses in TTBR1. Just set the reserved TTBR0.
*/
if (next == &init_mm) {
cpu_set_reserved_ttbr0();
return;
}
check_and_switch_context(next);
}
static inline void
switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
if (prev != next)
__switch_mm(next);
/*
* Update the saved TTBR0_EL1 of the scheduled-in task as the previous
* value may have not been initialised yet (activate_mm caller) or the
* ASID has changed since the last run (following the context switch
* of another thread of the same process).
*/
update_saved_ttbr0(tsk, next);
}
static inline const struct cpumask *
__task_cpu_possible_mask(struct task_struct *p, const struct cpumask *mask)
{
if (!static_branch_unlikely(&arm64_mismatched_32bit_el0))
return mask;
if (!is_compat_thread(task_thread_info(p)))
return mask;
return system_32bit_el0_cpumask();
}
static inline const struct cpumask *
task_cpu_possible_mask(struct task_struct *p)
{
return __task_cpu_possible_mask(p, cpu_possible_mask);
}
#define task_cpu_possible_mask task_cpu_possible_mask
const struct cpumask *task_cpu_fallback_mask(struct task_struct *p);
void verify_cpu_asid_bits(void);
void post_ttbr_update_workaround(void);
unsigned long arm64_mm_context_get(struct mm_struct *mm);
void arm64_mm_context_put(struct mm_struct *mm);
#define mm_untag_mask mm_untag_mask
static inline unsigned long mm_untag_mask(struct mm_struct *mm)
{
return -1UL >> 8;
}
/*
* Only enforce protection keys on the current process, because there is no
* user context to access POR_EL0 for another address space.
*/
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
bool write, bool execute, bool foreign)
{
if (!system_supports_poe())
return true;
/* allow access if the VMA is not one from this process */
if (foreign || vma_is_foreign(vma))
return true;
return por_el0_allows_pkey(vma_pkey(vma), write, execute);
}
#define deactivate_mm deactivate_mm
static inline void deactivate_mm(struct task_struct *tsk,
struct mm_struct *mm)
{
gcs_free(tsk);
}
#include <asm-generic/mmu_context.h>
#endif /* !__ASSEMBLY__ */
#endif /* !__ASM_MMU_CONTEXT_H */
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/cacheflush.h
*
* Copyright (C) 1999-2002 Russell King.
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_CACHEFLUSH_H
#define __ASM_CACHEFLUSH_H
#include <linux/kgdb.h>
#include <linux/mm.h>
/*
* This flag is used to indicate that the page pointed to by a pte is clean
* and does not require cleaning before returning it to the user.
*/
#define PG_dcache_clean PG_arch_1
/*
* MM Cache Management
* ===================
*
* The arch/arm64/mm/cache.S implements these methods.
*
* Start addresses are inclusive and end addresses are exclusive; start
* addresses should be rounded down, end addresses up.
*
* See Documentation/core-api/cachetlb.rst for more information. Please note that
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
* VIPT I-cache.
*
* All functions below apply to the interval [start, end)
* - start - virtual start address (inclusive)
* - end - virtual end address (exclusive)
*
* caches_clean_inval_pou(start, end)
*
* Ensure coherency between the I-cache and the D-cache region to
* the Point of Unification.
*
* caches_clean_inval_user_pou(start, end)
*
* Ensure coherency between the I-cache and the D-cache region to
* the Point of Unification.
* Use only if the region might access user memory.
*
* icache_inval_pou(start, end)
*
* Invalidate I-cache region to the Point of Unification.
*
* dcache_clean_inval_poc(start, end)
*
* Clean and invalidate D-cache region to the Point of Coherency.
*
* dcache_inval_poc(start, end)
*
* Invalidate D-cache region to the Point of Coherency.
*
* dcache_clean_poc(start, end)
*
* Clean D-cache region to the Point of Coherency.
*
* dcache_clean_pop(start, end)
*
* Clean D-cache region to the Point of Persistence.
*
* dcache_clean_pou(start, end)
*
* Clean D-cache region to the Point of Unification.
*/
extern void caches_clean_inval_pou(unsigned long start, unsigned long end);
extern void icache_inval_pou(unsigned long start, unsigned long end);
extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
extern void dcache_inval_poc(unsigned long start, unsigned long end);
extern void dcache_clean_poc(unsigned long start, unsigned long end);
extern void dcache_clean_pop(unsigned long start, unsigned long end);
extern void dcache_clean_pou(unsigned long start, unsigned long end);
extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end);
extern void sync_icache_aliases(unsigned long start, unsigned long end);
static inline void flush_icache_range(unsigned long start, unsigned long end)
{
caches_clean_inval_pou(start, end);
/*
* IPI all online CPUs so that they undergo a context synchronization
* event and are forced to refetch the new instructions.
*/
/*
* KGDB performs cache maintenance with interrupts disabled, so we
* will deadlock trying to IPI the secondary CPUs. In theory, we can
* set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that
* just means that KGDB will elide the maintenance altogether! As it
* turns out, KGDB uses IPIs to round-up the secondary CPUs during
* the patching operation, so we don't need extra IPIs here anyway.
* In which case, add a KGDB-specific bodge and return early.
*/
if (in_dbg_master())
return;
kick_all_cpus_sync();
}
#define flush_icache_range flush_icache_range
/*
* Copy user data from/to a page which is mapped into a different
* processes address space. Really, we want to allow our "user
* space" model to handle this.
*/
extern void copy_to_user_page(struct vm_area_struct *, struct page *,
unsigned long, void *, const void *, unsigned long);
#define copy_to_user_page copy_to_user_page
/*
* flush_dcache_folio is used when the kernel has written to the page
* cache page at virtual address page->virtual.
*
* If this page isn't mapped (ie, folio_mapping == NULL), or it might
* have userspace mappings, then we _must_ always clean + invalidate
* the dcache entries associated with the kernel mapping.
*
* Otherwise we can defer the operation, and clean the cache when we are
* about to change to user space. This is the same method as used on SPARC64.
* See update_mmu_cache for the user space part.
*/
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
void flush_dcache_folio(struct folio *);
#define flush_dcache_folio flush_dcache_folio
static __always_inline void icache_inval_all_pou(void)
{
if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC))
return;
asm("ic ialluis");
dsb(ish);
}
#include <asm-generic/cacheflush.h>
#endif /* __ASM_CACHEFLUSH_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_IVERSION_H
#define _LINUX_IVERSION_H
#include <linux/fs.h>
/*
* The inode->i_version field:
* ---------------------------
* The change attribute (i_version) is mandated by NFSv4 and is mostly for
* knfsd, but is also used for other purposes (e.g. IMA). The i_version must
* appear larger to observers if there was an explicit change to the inode's
* data or metadata since it was last queried.
*
* An explicit change is one that would ordinarily result in a change to the
* inode status change time (aka ctime). i_version must appear to change, even
* if the ctime does not (since the whole point is to avoid missing updates due
* to timestamp granularity). If POSIX or other relevant spec mandates that the
* ctime must change due to an operation, then the i_version counter must be
* incremented as well.
*
* Making the i_version update completely atomic with the operation itself would
* be prohibitively expensive. Traditionally the kernel has updated the times on
* directories after an operation that changes its contents. For regular files,
* the ctime is usually updated before the data is copied into the cache for a
* write. This means that there is a window of time when an observer can
* associate a new timestamp with old file contents. Since the purpose of the
* i_version is to allow for better cache coherency, the i_version must always
* be updated after the results of the operation are visible. Updating it before
* and after a change is also permitted. (Note that no filesystems currently do
* this. Fixing that is a work-in-progress).
*
* Observers see the i_version as a 64-bit number that never decreases. If it
* remains the same since it was last checked, then nothing has changed in the
* inode. If it's different then something has changed. Observers cannot infer
* anything about the nature or magnitude of the changes from the value, only
* that the inode has changed in some fashion.
*
* Not all filesystems properly implement the i_version counter. Subsystems that
* want to use i_version field on an inode should first check whether the
* filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro).
*
* Those that set SB_I_VERSION will automatically have their i_version counter
* incremented on writes to normal files. If the SB_I_VERSION is not set, then
* the VFS will not touch it on writes, and the filesystem can use it how it
* wishes. Note that the filesystem is always responsible for updating the
* i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.).
* We consider these sorts of filesystems to have a kernel-managed i_version.
*
* It may be impractical for filesystems to keep i_version updates atomic with
* respect to the changes that cause them. They should, however, guarantee
* that i_version updates are never visible before the changes that caused
* them. Also, i_version updates should never be delayed longer than it takes
* the original change to reach disk.
*
* This implementation uses the low bit in the i_version field as a flag to
* track when the value has been queried. If it has not been queried since it
* was last incremented, we can skip the increment in most cases.
*
* In the event that we're updating the ctime, we will usually go ahead and
* bump the i_version anyway. Since that has to go to stable storage in some
* fashion, we might as well increment it as well.
*
* With this implementation, the value should always appear to observers to
* increase over time if the file has changed. It's recommended to use
* inode_eq_iversion() helper to compare values.
*
* Note that some filesystems (e.g. NFS and AFS) just use the field to store
* a server-provided value (for the most part). For that reason, those
* filesystems do not set SB_I_VERSION. These filesystems are considered to
* have a self-managed i_version.
*
* Persistently storing the i_version
* ----------------------------------
* Queries of the i_version field are not gated on them hitting the backing
* store. It's always possible that the host could crash after allowing
* a query of the value but before it has made it to disk.
*
* To mitigate this problem, filesystems should always use
* inode_set_iversion_queried when loading an existing inode from disk. This
* ensures that the next attempted inode increment will result in the value
* changing.
*
* Storing the value to disk therefore does not count as a query, so those
* filesystems should use inode_peek_iversion to grab the value to be stored.
* There is no need to flag the value as having been queried in that case.
*/
/*
* We borrow the lowest bit in the i_version to use as a flag to tell whether
* it has been queried since we last incremented it. If it has, then we must
* increment it on the next change. After that, we can clear the flag and
* avoid incrementing it again until it has again been queried.
*/
#define I_VERSION_QUERIED_SHIFT (1)
#define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1))
#define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT)
/**
* inode_set_iversion_raw - set i_version to the specified raw value
* @inode: inode to set
* @val: new i_version value to set
*
* Set @inode's i_version field to @val. This function is for use by
* filesystems that self-manage the i_version.
*
* For example, the NFS client stores its NFSv4 change attribute in this way,
* and the AFS client stores the data_version from the server here.
*/
static inline void
inode_set_iversion_raw(struct inode *inode, u64 val)
{
atomic64_set(&inode->i_version, val);
}
/**
* inode_peek_iversion_raw - grab a "raw" iversion value
* @inode: inode from which i_version should be read
*
* Grab a "raw" inode->i_version value and return it. The i_version is not
* flagged or converted in any way. This is mostly used to access a self-managed
* i_version.
*
* With those filesystems, we want to treat the i_version as an entirely
* opaque value.
*/
static inline u64
inode_peek_iversion_raw(const struct inode *inode)
{
return atomic64_read(&inode->i_version);
}
/**
* inode_set_max_iversion_raw - update i_version new value is larger
* @inode: inode to set
* @val: new i_version to set
*
* Some self-managed filesystems (e.g Ceph) will only update the i_version
* value if the new value is larger than the one we already have.
*/
static inline void
inode_set_max_iversion_raw(struct inode *inode, u64 val)
{
u64 cur = inode_peek_iversion_raw(inode);
do {
if (cur > val)
break;
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val));
}
/**
* inode_set_iversion - set i_version to a particular value
* @inode: inode to set
* @val: new i_version value to set
*
* Set @inode's i_version field to @val. This function is for filesystems with
* a kernel-managed i_version, for initializing a newly-created inode from
* scratch.
*
* In this case, we do not set the QUERIED flag since we know that this value
* has never been queried.
*/
static inline void
inode_set_iversion(struct inode *inode, u64 val)
{
inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT);
}
/**
* inode_set_iversion_queried - set i_version to a particular value as quereied
* @inode: inode to set
* @val: new i_version value to set
*
* Set @inode's i_version field to @val, and flag it for increment on the next
* change.
*
* Filesystems that persistently store the i_version on disk should use this
* when loading an existing inode from disk.
*
* When loading in an i_version value from a backing store, we can't be certain
* that it wasn't previously viewed before being stored. Thus, we must assume
* that it was, to ensure that we don't end up handing out the same value for
* different versions of the same inode.
*/
static inline void
inode_set_iversion_queried(struct inode *inode, u64 val)
{
inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) |
I_VERSION_QUERIED);
}
bool inode_maybe_inc_iversion(struct inode *inode, bool force);
/**
* inode_inc_iversion - forcibly increment i_version
* @inode: inode that needs to be updated
*
* Forcbily increment the i_version field. This always results in a change to
* the observable value.
*/
static inline void
inode_inc_iversion(struct inode *inode)
{
inode_maybe_inc_iversion(inode, true);
}
/**
* inode_iversion_need_inc - is the i_version in need of being incremented?
* @inode: inode to check
*
* Returns whether the inode->i_version counter needs incrementing on the next
* change. Just fetch the value and check the QUERIED flag.
*/
static inline bool
inode_iversion_need_inc(struct inode *inode)
{
return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED;
}
/**
* inode_inc_iversion_raw - forcibly increment raw i_version
* @inode: inode that needs to be updated
*
* Forcbily increment the raw i_version field. This always results in a change
* to the raw value.
*
* NFS will use the i_version field to store the value from the server. It
* mostly treats it as opaque, but in the case where it holds a write
* delegation, it must increment the value itself. This function does that.
*/
static inline void
inode_inc_iversion_raw(struct inode *inode)
{
atomic64_inc(&inode->i_version);
}
/**
* inode_peek_iversion - read i_version without flagging it to be incremented
* @inode: inode from which i_version should be read
*
* Read the inode i_version counter for an inode without registering it as a
* query.
*
* This is typically used by local filesystems that need to store an i_version
* on disk. In that situation, it's not necessary to flag it as having been
* viewed, as the result won't be used to gauge changes from that point.
*/
static inline u64
inode_peek_iversion(const struct inode *inode)
{
return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT;
}
/*
* For filesystems without any sort of change attribute, the best we can
* do is fake one up from the ctime:
*/
static inline u64 time_to_chattr(const struct timespec64 *t)
{
u64 chattr = t->tv_sec;
chattr <<= 32;
chattr += t->tv_nsec;
return chattr;
}
u64 inode_query_iversion(struct inode *inode);
/**
* inode_eq_iversion_raw - check whether the raw i_version counter has changed
* @inode: inode to check
* @old: old value to check against its i_version
*
* Compare the current raw i_version counter with a previous one. Returns true
* if they are the same or false if they are different.
*/
static inline bool
inode_eq_iversion_raw(const struct inode *inode, u64 old)
{
return inode_peek_iversion_raw(inode) == old;
}
/**
* inode_eq_iversion - check whether the i_version counter has changed
* @inode: inode to check
* @old: old value to check against its i_version
*
* Compare an i_version counter with a previous one. Returns true if they are
* the same, and false if they are different.
*
* Note that we don't need to set the QUERIED flag in this case, as the value
* in the inode is not being recorded for later use.
*/
static inline bool
inode_eq_iversion(const struct inode *inode, u64 old)
{
return inode_peek_iversion(inode) == old;
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* VFIO core
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#include <linux/vfio.h>
#include <linux/iommufd.h>
#include <linux/anon_inodes.h>
#include "vfio.h"
static struct vfio {
struct class *class;
struct list_head group_list;
struct mutex group_lock; /* locks group_list */
struct ida group_ida;
dev_t group_devt;
} vfio;
static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
char *buf)
{
struct vfio_device *it, *device = ERR_PTR(-ENODEV);
mutex_lock(&group->device_lock);
list_for_each_entry(it, &group->device_list, group_next) {
int ret;
if (it->ops->match) {
ret = it->ops->match(it, buf);
if (ret < 0) {
device = ERR_PTR(ret);
break;
}
} else {
ret = !strcmp(dev_name(it->dev), buf);
}
if (ret && vfio_device_try_get_registration(it)) {
device = it;
break;
}
}
mutex_unlock(&group->device_lock);
return device;
}
/*
* VFIO Group fd, /dev/vfio/$GROUP
*/
static bool vfio_group_has_iommu(struct vfio_group *group)
{
lockdep_assert_held(&group->group_lock);
/*
* There can only be users if there is a container, and if there is a
* container there must be users.
*/
WARN_ON(!group->container != !group->container_users);
return group->container || group->iommufd;
}
/*
* VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
* if there was no container to unset. Since the ioctl is called on
* the group, we know that still exists, therefore the only valid
* transition here is 1->0.
*/
static int vfio_group_ioctl_unset_container(struct vfio_group *group)
{
int ret = 0;
mutex_lock(&group->group_lock);
if (!vfio_group_has_iommu(group)) {
ret = -EINVAL;
goto out_unlock;
}
if (group->container) {
if (group->container_users != 1) {
ret = -EBUSY;
goto out_unlock;
}
vfio_group_detach_container(group);
}
if (group->iommufd) {
iommufd_ctx_put(group->iommufd);
group->iommufd = NULL;
}
out_unlock:
mutex_unlock(&group->group_lock);
return ret;
}
static int vfio_group_ioctl_set_container(struct vfio_group *group,
int __user *arg)
{
struct vfio_container *container;
struct iommufd_ctx *iommufd;
int ret;
int fd;
if (get_user(fd, arg))
return -EFAULT;
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
mutex_lock(&group->group_lock);
if (vfio_group_has_iommu(group)) {
ret = -EINVAL;
goto out_unlock;
}
if (!group->iommu_group) {
ret = -ENODEV;
goto out_unlock;
}
container = vfio_container_from_file(fd_file(f));
if (container) {
ret = vfio_container_attach_group(container, group);
goto out_unlock;
}
iommufd = iommufd_ctx_from_file(fd_file(f));
if (!IS_ERR(iommufd)) {
if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) &&
group->type == VFIO_NO_IOMMU)
ret = iommufd_vfio_compat_set_no_iommu(iommufd);
else
ret = iommufd_vfio_compat_ioas_create(iommufd);
if (ret) {
iommufd_ctx_put(iommufd);
goto out_unlock;
}
group->iommufd = iommufd;
goto out_unlock;
}
/* The FD passed is not recognized. */
ret = -EBADFD;
out_unlock:
mutex_unlock(&group->group_lock);
return ret;
}
static void vfio_device_group_get_kvm_safe(struct vfio_device *device)
{
spin_lock(&device->group->kvm_ref_lock);
vfio_device_get_kvm_safe(device, device->group->kvm);
spin_unlock(&device->group->kvm_ref_lock);
}
static int vfio_df_group_open(struct vfio_device_file *df)
{
struct vfio_device *device = df->device;
int ret;
mutex_lock(&device->group->group_lock);
if (!vfio_group_has_iommu(device->group)) {
ret = -EINVAL;
goto out_unlock;
}
mutex_lock(&device->dev_set->lock);
/*
* Before the first device open, get the KVM pointer currently
* associated with the group (if there is one) and obtain a reference
* now that will be held until the open_count reaches 0 again. Save
* the pointer in the device for use by drivers.
*/
if (device->open_count == 0)
vfio_device_group_get_kvm_safe(device);
df->iommufd = device->group->iommufd;
if (df->iommufd && vfio_device_is_noiommu(device) && device->open_count == 0) {
/*
* Require no compat ioas to be assigned to proceed. The basic
* statement is that the user cannot have done something that
* implies they expected translation to exist
*/
if (!capable(CAP_SYS_RAWIO) ||
vfio_iommufd_device_has_compat_ioas(device, df->iommufd))
ret = -EPERM;
else
ret = 0;
goto out_put_kvm;
}
ret = vfio_df_open(df);
if (ret)
goto out_put_kvm;
if (df->iommufd && device->open_count == 1) {
ret = vfio_iommufd_compat_attach_ioas(device, df->iommufd);
if (ret)
goto out_close_device;
}
/*
* Paired with smp_load_acquire() in vfio_device_fops::ioctl/
* read/write/mmap and vfio_file_has_device_access()
*/
smp_store_release(&df->access_granted, true);
mutex_unlock(&device->dev_set->lock);
mutex_unlock(&device->group->group_lock);
return 0;
out_close_device:
vfio_df_close(df);
out_put_kvm:
df->iommufd = NULL;
if (device->open_count == 0)
vfio_device_put_kvm(device);
mutex_unlock(&device->dev_set->lock);
out_unlock:
mutex_unlock(&device->group->group_lock);
return ret;
}
void vfio_df_group_close(struct vfio_device_file *df)
{
struct vfio_device *device = df->device;
mutex_lock(&device->group->group_lock);
mutex_lock(&device->dev_set->lock);
vfio_df_close(df);
df->iommufd = NULL;
if (device->open_count == 0)
vfio_device_put_kvm(device);
mutex_unlock(&device->dev_set->lock);
mutex_unlock(&device->group->group_lock);
}
static struct file *vfio_device_open_file(struct vfio_device *device)
{
struct vfio_device_file *df;
struct file *filep;
int ret;
df = vfio_allocate_device_file(device);
if (IS_ERR(df)) {
ret = PTR_ERR(df);
goto err_out;
}
df->group = device->group;
ret = vfio_df_group_open(df);
if (ret)
goto err_free;
filep = anon_inode_getfile_fmode("[vfio-device]", &vfio_device_fops,
df, O_RDWR, FMODE_PREAD | FMODE_PWRITE);
if (IS_ERR(filep)) {
ret = PTR_ERR(filep);
goto err_close_device;
}
/*
* Use the pseudo fs inode on the device to link all mmaps
* to the same address space, allowing us to unmap all vmas
* associated to this device using unmap_mapping_range().
*/
filep->f_mapping = device->inode->i_mapping;
if (device->group->type == VFIO_NO_IOMMU)
dev_warn(device->dev, "vfio-noiommu device opened by user "
"(%s:%d)\n", current->comm, task_pid_nr(current));
/*
* On success the ref of device is moved to the file and
* put in vfio_device_fops_release()
*/
return filep;
err_close_device:
vfio_df_group_close(df);
err_free:
kfree(df);
err_out:
return ERR_PTR(ret);
}
static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
char __user *arg)
{
struct vfio_device *device;
struct file *filep;
char *buf;
int fdno;
int ret;
buf = strndup_user(arg, PAGE_SIZE);
if (IS_ERR(buf))
return PTR_ERR(buf);
device = vfio_device_get_from_name(group, buf);
kfree(buf);
if (IS_ERR(device))
return PTR_ERR(device);
fdno = get_unused_fd_flags(O_CLOEXEC);
if (fdno < 0) {
ret = fdno;
goto err_put_device;
}
filep = vfio_device_open_file(device);
if (IS_ERR(filep)) {
ret = PTR_ERR(filep);
goto err_put_fdno;
}
fd_install(fdno, filep);
return fdno;
err_put_fdno:
put_unused_fd(fdno);
err_put_device:
vfio_device_put_registration(device);
return ret;
}
static int vfio_group_ioctl_get_status(struct vfio_group *group,
struct vfio_group_status __user *arg)
{
unsigned long minsz = offsetofend(struct vfio_group_status, flags);
struct vfio_group_status status;
if (copy_from_user(&status, arg, minsz))
return -EFAULT;
if (status.argsz < minsz)
return -EINVAL;
status.flags = 0;
mutex_lock(&group->group_lock);
if (!group->iommu_group) {
mutex_unlock(&group->group_lock);
return -ENODEV;
}
/*
* With the container FD the iommu_group_claim_dma_owner() is done
* during SET_CONTAINER but for IOMMFD this is done during
* VFIO_GROUP_GET_DEVICE_FD. Meaning that with iommufd
* VFIO_GROUP_FLAGS_VIABLE could be set but GET_DEVICE_FD will fail due
* to viability.
*/
if (vfio_group_has_iommu(group))
status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
VFIO_GROUP_FLAGS_VIABLE;
else if (!iommu_group_dma_owner_claimed(group->iommu_group))
status.flags |= VFIO_GROUP_FLAGS_VIABLE;
mutex_unlock(&group->group_lock);
if (copy_to_user(arg, &status, minsz))
return -EFAULT;
return 0;
}
static long vfio_group_fops_unl_ioctl(struct file *filep,
unsigned int cmd, unsigned long arg)
{
struct vfio_group *group = filep->private_data;
void __user *uarg = (void __user *)arg;
switch (cmd) {
case VFIO_GROUP_GET_DEVICE_FD:
return vfio_group_ioctl_get_device_fd(group, uarg);
case VFIO_GROUP_GET_STATUS:
return vfio_group_ioctl_get_status(group, uarg);
case VFIO_GROUP_SET_CONTAINER:
return vfio_group_ioctl_set_container(group, uarg);
case VFIO_GROUP_UNSET_CONTAINER:
return vfio_group_ioctl_unset_container(group);
default:
return -ENOTTY;
}
}
int vfio_device_block_group(struct vfio_device *device)
{
struct vfio_group *group = device->group;
int ret = 0;
mutex_lock(&group->group_lock);
if (group->opened_file) {
ret = -EBUSY;
goto out_unlock;
}
group->cdev_device_open_cnt++;
out_unlock:
mutex_unlock(&group->group_lock);
return ret;
}
void vfio_device_unblock_group(struct vfio_device *device)
{
struct vfio_group *group = device->group;
mutex_lock(&group->group_lock);
group->cdev_device_open_cnt--;
mutex_unlock(&group->group_lock);
}
static int vfio_group_fops_open(struct inode *inode, struct file *filep)
{
struct vfio_group *group =
container_of(inode->i_cdev, struct vfio_group, cdev);
int ret;
mutex_lock(&group->group_lock);
/*
* drivers can be zero if this races with vfio_device_remove_group(), it
* will be stable at 0 under the group rwsem
*/
if (refcount_read(&group->drivers) == 0) {
ret = -ENODEV;
goto out_unlock;
}
if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
ret = -EPERM;
goto out_unlock;
}
if (group->cdev_device_open_cnt) {
ret = -EBUSY;
goto out_unlock;
}
/*
* Do we need multiple instances of the group open? Seems not.
*/
if (group->opened_file) {
ret = -EBUSY;
goto out_unlock;
}
group->opened_file = filep;
filep->private_data = group;
ret = 0;
out_unlock:
mutex_unlock(&group->group_lock);
return ret;
}
static int vfio_group_fops_release(struct inode *inode, struct file *filep)
{
struct vfio_group *group = filep->private_data;
filep->private_data = NULL;
mutex_lock(&group->group_lock);
/*
* Device FDs hold a group file reference, therefore the group release
* is only called when there are no open devices.
*/
WARN_ON(group->notifier.head);
if (group->container)
vfio_group_detach_container(group);
if (group->iommufd) {
iommufd_ctx_put(group->iommufd);
group->iommufd = NULL;
}
group->opened_file = NULL;
mutex_unlock(&group->group_lock);
return 0;
}
static const struct file_operations vfio_group_fops = {
.owner = THIS_MODULE,
.unlocked_ioctl = vfio_group_fops_unl_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.open = vfio_group_fops_open,
.release = vfio_group_fops_release,
};
/*
* Group objects - create, release, get, put, search
*/
static struct vfio_group *
vfio_group_find_from_iommu(struct iommu_group *iommu_group)
{
struct vfio_group *group;
lockdep_assert_held(&vfio.group_lock);
/*
* group->iommu_group from the vfio.group_list cannot be NULL
* under the vfio.group_lock.
*/
list_for_each_entry(group, &vfio.group_list, vfio_next) {
if (group->iommu_group == iommu_group)
return group;
}
return NULL;
}
static void vfio_group_release(struct device *dev)
{
struct vfio_group *group = container_of(dev, struct vfio_group, dev);
mutex_destroy(&group->device_lock);
mutex_destroy(&group->group_lock);
WARN_ON(group->iommu_group);
WARN_ON(group->cdev_device_open_cnt);
ida_free(&vfio.group_ida, MINOR(group->dev.devt));
kfree(group);
}
static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
enum vfio_group_type type)
{
struct vfio_group *group;
int minor;
group = kzalloc(sizeof(*group), GFP_KERNEL);
if (!group)
return ERR_PTR(-ENOMEM);
minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
if (minor < 0) {
kfree(group);
return ERR_PTR(minor);
}
device_initialize(&group->dev);
group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
group->dev.class = vfio.class;
group->dev.release = vfio_group_release;
cdev_init(&group->cdev, &vfio_group_fops);
group->cdev.owner = THIS_MODULE;
refcount_set(&group->drivers, 1);
mutex_init(&group->group_lock);
spin_lock_init(&group->kvm_ref_lock);
INIT_LIST_HEAD(&group->device_list);
mutex_init(&group->device_lock);
group->iommu_group = iommu_group;
/* put in vfio_group_release() */
iommu_group_ref_get(iommu_group);
group->type = type;
BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
return group;
}
static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
enum vfio_group_type type)
{
struct vfio_group *group;
struct vfio_group *ret;
int err;
lockdep_assert_held(&vfio.group_lock);
group = vfio_group_alloc(iommu_group, type);
if (IS_ERR(group))
return group;
err = dev_set_name(&group->dev, "%s%d",
group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
iommu_group_id(iommu_group));
if (err) {
ret = ERR_PTR(err);
goto err_put;
}
err = cdev_device_add(&group->cdev, &group->dev);
if (err) {
ret = ERR_PTR(err);
goto err_put;
}
list_add(&group->vfio_next, &vfio.group_list);
return group;
err_put:
put_device(&group->dev);
return ret;
}
static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
enum vfio_group_type type)
{
struct iommu_group *iommu_group;
struct vfio_group *group;
int ret;
iommu_group = iommu_group_alloc();
if (IS_ERR(iommu_group))
return ERR_CAST(iommu_group);
ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
if (ret)
goto out_put_group;
ret = iommu_group_add_device(iommu_group, dev);
if (ret)
goto out_put_group;
mutex_lock(&vfio.group_lock);
group = vfio_create_group(iommu_group, type);
mutex_unlock(&vfio.group_lock);
if (IS_ERR(group)) {
ret = PTR_ERR(group);
goto out_remove_device;
}
iommu_group_put(iommu_group);
return group;
out_remove_device:
iommu_group_remove_device(dev);
out_put_group:
iommu_group_put(iommu_group);
return ERR_PTR(ret);
}
static bool vfio_group_has_device(struct vfio_group *group, struct device *dev)
{
struct vfio_device *device;
mutex_lock(&group->device_lock);
list_for_each_entry(device, &group->device_list, group_next) {
if (device->dev == dev) {
mutex_unlock(&group->device_lock);
return true;
}
}
mutex_unlock(&group->device_lock);
return false;
}
static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
{
struct iommu_group *iommu_group;
struct vfio_group *group;
iommu_group = iommu_group_get(dev);
if (!iommu_group && vfio_noiommu) {
/*
* With noiommu enabled, create an IOMMU group for devices that
* don't already have one, implying no IOMMU hardware/driver
* exists. Taint the kernel because we're about to give a DMA
* capable device to a user without IOMMU protection.
*/
group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
if (!IS_ERR(group)) {
add_taint(TAINT_USER, LOCKDEP_STILL_OK);
dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
}
return group;
}
if (!iommu_group)
return ERR_PTR(-EINVAL);
mutex_lock(&vfio.group_lock);
group = vfio_group_find_from_iommu(iommu_group);
if (group) {
if (WARN_ON(vfio_group_has_device(group, dev)))
group = ERR_PTR(-EINVAL);
else
refcount_inc(&group->drivers);
} else {
group = vfio_create_group(iommu_group, VFIO_IOMMU);
}
mutex_unlock(&vfio.group_lock);
/* The vfio_group holds a reference to the iommu_group */
iommu_group_put(iommu_group);
return group;
}
int vfio_device_set_group(struct vfio_device *device,
enum vfio_group_type type)
{
struct vfio_group *group;
if (type == VFIO_IOMMU)
group = vfio_group_find_or_alloc(device->dev);
else
group = vfio_noiommu_group_alloc(device->dev, type);
if (IS_ERR(group))
return PTR_ERR(group);
/* Our reference on group is moved to the device */
device->group = group;
return 0;
}
void vfio_device_remove_group(struct vfio_device *device)
{
struct vfio_group *group = device->group;
struct iommu_group *iommu_group;
if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
iommu_group_remove_device(device->dev);
/* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
return;
list_del(&group->vfio_next);
/*
* We could concurrently probe another driver in the group that might
* race vfio_device_remove_group() with vfio_get_group(), so we have to
* ensure that the sysfs is all cleaned up under lock otherwise the
* cdev_device_add() will fail due to the name aready existing.
*/
cdev_device_del(&group->cdev, &group->dev);
mutex_lock(&group->group_lock);
/*
* These data structures all have paired operations that can only be
* undone when the caller holds a live reference on the device. Since
* all pairs must be undone these WARN_ON's indicate some caller did not
* properly hold the group reference.
*/
WARN_ON(!list_empty(&group->device_list));
WARN_ON(group->notifier.head);
/*
* Revoke all users of group->iommu_group. At this point we know there
* are no devices active because we are unplugging the last one. Setting
* iommu_group to NULL blocks all new users.
*/
if (group->container)
vfio_group_detach_container(group);
iommu_group = group->iommu_group;
group->iommu_group = NULL;
mutex_unlock(&group->group_lock);
mutex_unlock(&vfio.group_lock);
iommu_group_put(iommu_group);
put_device(&group->dev);
}
void vfio_device_group_register(struct vfio_device *device)
{
mutex_lock(&device->group->device_lock);
list_add(&device->group_next, &device->group->device_list);
mutex_unlock(&device->group->device_lock);
}
void vfio_device_group_unregister(struct vfio_device *device)
{
mutex_lock(&device->group->device_lock);
list_del(&device->group_next);
mutex_unlock(&device->group->device_lock);
}
int vfio_device_group_use_iommu(struct vfio_device *device)
{
struct vfio_group *group = device->group;
int ret = 0;
lockdep_assert_held(&group->group_lock);
if (WARN_ON(!group->container))
return -EINVAL;
ret = vfio_group_use_container(group);
if (ret)
return ret;
vfio_device_container_register(device);
return 0;
}
void vfio_device_group_unuse_iommu(struct vfio_device *device)
{
struct vfio_group *group = device->group;
lockdep_assert_held(&group->group_lock);
if (WARN_ON(!group->container))
return;
vfio_device_container_unregister(device);
vfio_group_unuse_container(group);
}
bool vfio_device_has_container(struct vfio_device *device)
{
return device->group->container;
}
struct vfio_group *vfio_group_from_file(struct file *file)
{ struct vfio_group *group = file->private_data; if (file->f_op != &vfio_group_fops)
return NULL;
return group;
}
/**
* vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
* @file: VFIO group file
*
* The returned iommu_group is valid as long as a ref is held on the file. This
* returns a reference on the group. This function is deprecated, only the SPAPR
* path in kvm should call it.
*/
struct iommu_group *vfio_file_iommu_group(struct file *file)
{
struct vfio_group *group = vfio_group_from_file(file);
struct iommu_group *iommu_group = NULL;
if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
return NULL;
if (!group)
return NULL;
mutex_lock(&group->group_lock);
if (group->iommu_group) {
iommu_group = group->iommu_group;
iommu_group_ref_get(iommu_group);
}
mutex_unlock(&group->group_lock);
return iommu_group;
}
EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
/**
* vfio_file_is_group - True if the file is a vfio group file
* @file: VFIO group file
*/
bool vfio_file_is_group(struct file *file)
{
return vfio_group_from_file(file);
}
EXPORT_SYMBOL_GPL(vfio_file_is_group);
bool vfio_group_enforced_coherent(struct vfio_group *group)
{
struct vfio_device *device;
bool ret = true;
/*
* If the device does not have IOMMU_CAP_ENFORCE_CACHE_COHERENCY then
* any domain later attached to it will also not support it. If the cap
* is set then the iommu_domain eventually attached to the device/group
* must use a domain with enforce_cache_coherency().
*/
mutex_lock(&group->device_lock);
list_for_each_entry(device, &group->device_list, group_next) {
if (!device_iommu_capable(device->dev,
IOMMU_CAP_ENFORCE_CACHE_COHERENCY)) {
ret = false;
break;
}
}
mutex_unlock(&group->device_lock);
return ret;
}
void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
{
spin_lock(&group->kvm_ref_lock);
group->kvm = kvm;
spin_unlock(&group->kvm_ref_lock);
}
/**
* vfio_file_has_dev - True if the VFIO file is a handle for device
* @file: VFIO file to check
* @device: Device that must be part of the file
*
* Returns true if given file has permission to manipulate the given device.
*/
bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
{
struct vfio_group *group = vfio_group_from_file(file);
if (!group)
return false;
return group == device->group;
}
EXPORT_SYMBOL_GPL(vfio_file_has_dev);
static char *vfio_devnode(const struct device *dev, umode_t *mode)
{
return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
}
int __init vfio_group_init(void)
{
int ret;
ida_init(&vfio.group_ida);
mutex_init(&vfio.group_lock);
INIT_LIST_HEAD(&vfio.group_list);
ret = vfio_container_init();
if (ret)
return ret;
/* /dev/vfio/$GROUP */
vfio.class = class_create("vfio");
if (IS_ERR(vfio.class)) {
ret = PTR_ERR(vfio.class);
goto err_group_class;
}
vfio.class->devnode = vfio_devnode;
ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
if (ret)
goto err_alloc_chrdev;
return 0;
err_alloc_chrdev:
class_destroy(vfio.class);
vfio.class = NULL;
err_group_class:
vfio_container_cleanup();
return ret;
}
void vfio_group_cleanup(void)
{
WARN_ON(!list_empty(&vfio.group_list));
ida_destroy(&vfio.group_ida);
unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
class_destroy(vfio.class);
vfio.class = NULL;
vfio_container_cleanup();
}
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2015, 2016 ARM Ltd.
*/
#ifndef __KVM_ARM_VGIC_H
#define __KVM_ARM_VGIC_H
#include <linux/bits.h>
#include <linux/kvm.h>
#include <linux/irqreturn.h>
#include <linux/kref.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/static_key.h>
#include <linux/types.h>
#include <linux/xarray.h>
#include <kvm/iodev.h>
#include <linux/list.h>
#include <linux/jump_label.h>
#include <linux/irqchip/arm-gic-v4.h>
#define VGIC_V3_MAX_CPUS 512
#define VGIC_V2_MAX_CPUS 8
#define VGIC_NR_IRQS_LEGACY 256
#define VGIC_NR_SGIS 16
#define VGIC_NR_PPIS 16
#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
#define VGIC_MAX_SPI 1019
#define VGIC_MAX_RESERVED 1023
#define VGIC_MIN_LPI 8192
#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
#define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS)
#define irq_is_spi(irq) ((irq) >= VGIC_NR_PRIVATE_IRQS && \
(irq) <= VGIC_MAX_SPI)
enum vgic_type {
VGIC_V2, /* Good ol' GICv2 */
VGIC_V3, /* New fancy GICv3 */
};
/* same for all guests, as depending only on the _host's_ GIC model */
struct vgic_global {
/* type of the host GIC */
enum vgic_type type;
/* Physical address of vgic virtual cpu interface */
phys_addr_t vcpu_base;
/* GICV mapping, kernel VA */
void __iomem *vcpu_base_va;
/* GICV mapping, HYP VA */
void __iomem *vcpu_hyp_va;
/* virtual control interface mapping, kernel VA */
void __iomem *vctrl_base;
/* virtual control interface mapping, HYP VA */
void __iomem *vctrl_hyp;
/* Number of implemented list registers */
int nr_lr;
/* Maintenance IRQ number */
unsigned int maint_irq;
/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
int max_gic_vcpus;
/* Only needed for the legacy KVM_CREATE_IRQCHIP */
bool can_emulate_gicv2;
/* Hardware has GICv4? */
bool has_gicv4;
bool has_gicv4_1;
/* Pseudo GICv3 from outer space */
bool no_hw_deactivation;
/* GIC system register CPU interface */
struct static_key_false gicv3_cpuif;
u32 ich_vtr_el2;
};
extern struct vgic_global kvm_vgic_global_state;
#define VGIC_V2_MAX_LRS (1 << 6)
#define VGIC_V3_MAX_LRS 16
#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
enum vgic_irq_config {
VGIC_CONFIG_EDGE = 0,
VGIC_CONFIG_LEVEL
};
/*
* Per-irq ops overriding some common behavious.
*
* Always called in non-preemptible section and the functions can use
* kvm_arm_get_running_vcpu() to get the vcpu pointer for private IRQs.
*/
struct irq_ops {
/* Per interrupt flags for special-cased interrupts */
unsigned long flags;
#define VGIC_IRQ_SW_RESAMPLE BIT(0) /* Clear the active state for resampling */
/*
* Callback function pointer to in-kernel devices that can tell us the
* state of the input level of mapped level-triggered IRQ faster than
* peaking into the physical GIC.
*/
bool (*get_input_level)(int vintid);
};
struct vgic_irq {
raw_spinlock_t irq_lock; /* Protects the content of the struct */
struct rcu_head rcu;
struct list_head ap_list;
struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU
* SPIs and LPIs: The VCPU whose ap_list
* this is queued on.
*/
struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should
* be sent to, as a result of the
* targets reg (v2) or the
* affinity reg (v3).
*/
u32 intid; /* Guest visible INTID */
bool line_level; /* Level only */
bool pending_latch; /* The pending latch state used to calculate
* the pending state for both level
* and edge triggered IRQs. */
bool active; /* not used for LPIs */
bool enabled;
bool hw; /* Tied to HW IRQ */
struct kref refcount; /* Used for LPIs */
u32 hwintid; /* HW INTID number */
unsigned int host_irq; /* linux irq corresponding to hwintid */
union {
u8 targets; /* GICv2 target VCPUs mask */
u32 mpidr; /* GICv3 target VCPU */
};
u8 source; /* GICv2 SGIs only */
u8 active_source; /* GICv2 SGIs only */
u8 priority;
u8 group; /* 0 == group 0, 1 == group 1 */
enum vgic_irq_config config; /* Level or edge */
struct irq_ops *ops;
void *owner; /* Opaque pointer to reserve an interrupt
for in-kernel devices. */
};
static inline bool vgic_irq_needs_resampling(struct vgic_irq *irq)
{
return irq->ops && (irq->ops->flags & VGIC_IRQ_SW_RESAMPLE);
}
struct vgic_register_region;
struct vgic_its;
enum iodev_type {
IODEV_CPUIF,
IODEV_DIST,
IODEV_REDIST,
IODEV_ITS
};
struct vgic_io_device {
gpa_t base_addr;
union {
struct kvm_vcpu *redist_vcpu;
struct vgic_its *its;
};
const struct vgic_register_region *regions;
enum iodev_type iodev_type;
int nr_regions;
struct kvm_io_device dev;
};
struct vgic_its {
/* The base address of the ITS control register frame */
gpa_t vgic_its_base;
bool enabled;
struct vgic_io_device iodev;
struct kvm_device *dev;
/* These registers correspond to GITS_BASER{0,1} */
u64 baser_device_table;
u64 baser_coll_table;
/* Protects the command queue */
struct mutex cmd_lock;
u64 cbaser;
u32 creadr;
u32 cwriter;
/* migration ABI revision in use */
u32 abi_rev;
/* Protects the device and collection lists */
struct mutex its_lock;
struct list_head device_list;
struct list_head collection_list;
/*
* Caches the (device_id, event_id) -> vgic_irq translation for
* LPIs that are mapped and enabled.
*/
struct xarray translation_cache;
};
struct vgic_state_iter;
struct vgic_redist_region {
u32 index;
gpa_t base;
u32 count; /* number of redistributors or 0 if single region */
u32 free_index; /* index of the next free redistributor */
struct list_head list;
};
struct vgic_dist {
bool in_kernel;
bool ready;
bool initialized;
/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
u32 vgic_model;
/* Implementation revision as reported in the GICD_IIDR */
u32 implementation_rev;
#define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */
#define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */
#define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3
/* Userspace can write to GICv2 IGROUPR */
bool v2_groups_user_writable;
/* Do injected MSIs require an additional device ID? */
bool msis_require_devid;
int nr_spis;
/* The GIC maintenance IRQ for nested hypervisors. */
u32 mi_intid;
/* base addresses in guest physical address space: */
gpa_t vgic_dist_base; /* distributor */
union {
/* either a GICv2 CPU interface */
gpa_t vgic_cpu_base;
/* or a number of GICv3 redistributor regions */
struct list_head rd_regions;
};
/* distributor enabled */
bool enabled;
/* Wants SGIs without active state */
bool nassgireq;
struct vgic_irq *spis;
struct vgic_io_device dist_iodev;
bool has_its;
bool table_write_in_progress;
/*
* Contains the attributes and gpa of the LPI configuration table.
* Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
* one address across all redistributors.
* GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables"
*/
u64 propbaser;
#define LPI_XA_MARK_DEBUG_ITER XA_MARK_0
struct xarray lpi_xa;
/* used by vgic-debug */
struct vgic_state_iter *iter;
/*
* GICv4 ITS per-VM data, containing the IRQ domain, the VPE
* array, the property table pointer as well as allocation
* data. This essentially ties the Linux IRQ core and ITS
* together, and avoids leaking KVM's data structures anywhere
* else.
*/
struct its_vm its_vm;
};
struct vgic_v2_cpu_if {
u32 vgic_hcr;
u32 vgic_vmcr;
u32 vgic_apr;
u32 vgic_lr[VGIC_V2_MAX_LRS];
unsigned int used_lrs;
};
struct vgic_v3_cpu_if {
u32 vgic_hcr;
u32 vgic_vmcr;
u32 vgic_sre; /* Restored only, change ignored */
u32 vgic_ap0r[4];
u32 vgic_ap1r[4];
u64 vgic_lr[VGIC_V3_MAX_LRS];
/*
* GICv4 ITS per-VPE data, containing the doorbell IRQ, the
* pending table pointer, the its_vm pointer and a few other
* HW specific things. As for the its_vm structure, this is
* linking the Linux IRQ subsystem and the ITS together.
*/
struct its_vpe its_vpe;
unsigned int used_lrs;
};
struct vgic_cpu {
/* CPU vif control registers for world switch */
union {
struct vgic_v2_cpu_if vgic_v2;
struct vgic_v3_cpu_if vgic_v3;
};
struct vgic_irq *private_irqs;
raw_spinlock_t ap_list_lock; /* Protects the ap_list */
/*
* List of IRQs that this VCPU should consider because they are either
* Active or Pending (hence the name; AP list), or because they recently
* were one of the two and need to be migrated off this list to another
* VCPU.
*/
struct list_head ap_list_head;
/*
* Members below are used with GICv3 emulation only and represent
* parts of the redistributor.
*/
struct vgic_io_device rd_iodev;
struct vgic_redist_region *rdreg;
u32 rdreg_index;
atomic_t syncr_busy;
/* Contains the attributes and gpa of the LPI pending tables. */
u64 pendbaser;
/* GICR_CTLR.{ENABLE_LPIS,RWP} */
atomic_t ctlr;
/* Cache guest priority bits */
u32 num_pri_bits;
/* Cache guest interrupt ID bits */
u32 num_id_bits;
};
extern struct static_key_false vgic_v2_cpuif_trap;
extern struct static_key_false vgic_v3_cpuif_trap;
int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr);
void kvm_vgic_early_init(struct kvm *kvm);
int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu);
int kvm_vgic_create(struct kvm *kvm, u32 type);
void kvm_vgic_destroy(struct kvm *kvm);
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
void kvm_vgic_init_cpu_hardware(void);
int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
unsigned int intid, bool level, void *owner);
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
u32 vintid, struct irq_ops *ops);
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid);
int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid);
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
void kvm_vgic_load(struct kvm_vcpu *vcpu);
void kvm_vgic_put(struct kvm_vcpu *vcpu);
u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu);
u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu);
u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) ((k)->arch.vgic.initialized)
#define vgic_ready(k) ((k)->arch.vgic.ready)
#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid);
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1);
/**
* kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
*
* The host's GIC naturally limits the maximum amount of VCPUs a guest
* can use.
*/
static inline int kvm_vgic_get_max_vcpus(void)
{
return kvm_vgic_global_state.max_gic_vcpus;
}
/**
* kvm_vgic_setup_default_irq_routing:
* Setup a default flat gsi routing table mapping all SPIs
*/
int kvm_vgic_setup_default_irq_routing(struct kvm *kvm);
int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner);
struct kvm_kernel_irq_routing_entry;
int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
struct kvm_kernel_irq_routing_entry *irq_entry);
int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
struct kvm_kernel_irq_routing_entry *irq_entry);
int vgic_v4_load(struct kvm_vcpu *vcpu);
void vgic_v4_commit(struct kvm_vcpu *vcpu);
int vgic_v4_put(struct kvm_vcpu *vcpu);
bool vgic_state_is_nested(struct kvm_vcpu *vcpu);
/* CPU HP callbacks */
void kvm_vgic_cpu_up(void);
void kvm_vgic_cpu_down(void);
#endif /* __KVM_ARM_VGIC_H */
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/memory.h
*
* Copyright (C) 2000-2002 Russell King
* Copyright (C) 2012 ARM Ltd.
*
* Note: this file should not be included by non-asm/.h files
*/
#ifndef __ASM_MEMORY_H
#define __ASM_MEMORY_H
#include <linux/const.h>
#include <linux/sizes.h>
#include <asm/page-def.h>
/*
* Size of the PCI I/O space. This must remain a power of two so that
* IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses.
*/
#define PCI_IO_SIZE SZ_16M
/*
* VMEMMAP_SIZE - allows the whole linear region to be covered by
* a struct page array
*
* If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE
* needs to cover the memory region from the beginning of the 52-bit
* PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to
* keep a constant PAGE_OFFSET and "fallback" to using the higher end
* of the VMEMMAP where 52-bit support is not available in hardware.
*/
#define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET)
#define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page))
/*
* PAGE_OFFSET - the virtual address of the start of the linear map, at the
* start of the TTBR1 address space.
* PAGE_END - the end of the linear map, where all other kernel mappings begin.
* KIMAGE_VADDR - the virtual address of the start of the kernel image.
* VA_BITS - the maximum number of bits for virtual addresses.
*/
#define VA_BITS (CONFIG_ARM64_VA_BITS)
#define _PAGE_OFFSET(va) (-(UL(1) << (va)))
#define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS))
#define KIMAGE_VADDR (MODULES_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define MODULES_VADDR (_PAGE_END(VA_BITS_MIN))
#define MODULES_VSIZE (SZ_2G)
#define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE)
#define VMEMMAP_END (-UL(SZ_1G))
#define PCI_IO_START (VMEMMAP_END + SZ_8M)
#define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE)
#define FIXADDR_TOP (-UL(SZ_8M))
#if VA_BITS > 48
#ifdef CONFIG_ARM64_16K_PAGES
#define VA_BITS_MIN (47)
#else
#define VA_BITS_MIN (48)
#endif
#else
#define VA_BITS_MIN (VA_BITS)
#endif
#define _PAGE_END(va) (-(UL(1) << ((va) - 1)))
#define KERNEL_START _text
#define KERNEL_END _end
/*
* Generic and Software Tag-Based KASAN modes require 1/8th and 1/16th of the
* kernel virtual address space for storing the shadow memory respectively.
*
* The mapping between a virtual memory address and its corresponding shadow
* memory address is defined based on the formula:
*
* shadow_addr = (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
*
* where KASAN_SHADOW_SCALE_SHIFT is the order of the number of bits that map
* to a single shadow byte and KASAN_SHADOW_OFFSET is a constant that offsets
* the mapping. Note that KASAN_SHADOW_OFFSET does not point to the start of
* the shadow memory region.
*
* Based on this mapping, we define two constants:
*
* KASAN_SHADOW_START: the start of the shadow memory region;
* KASAN_SHADOW_END: the end of the shadow memory region.
*
* KASAN_SHADOW_END is defined first as the shadow address that corresponds to
* the upper bound of possible virtual kernel memory addresses UL(1) << 64
* according to the mapping formula.
*
* KASAN_SHADOW_START is defined second based on KASAN_SHADOW_END. The shadow
* memory start must map to the lowest possible kernel virtual memory address
* and thus it depends on the actual bitness of the address space.
*
* As KASAN inserts redzones between stack variables, this increases the stack
* memory usage significantly. Thus, we double the (minimum) stack size.
*/
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
#define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) + KASAN_SHADOW_OFFSET)
#define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (UL(1) << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
#define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual)
#define PAGE_END KASAN_SHADOW_START
#define KASAN_THREAD_SHIFT 1
#else
#define KASAN_THREAD_SHIFT 0
#define PAGE_END (_PAGE_END(VA_BITS_MIN))
#endif /* CONFIG_KASAN */
#define DIRECT_MAP_PHYSMEM_END __pa(PAGE_END - 1)
#define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT)
/*
* VMAP'd stacks are allocated at page granularity, so we must ensure that such
* stacks are a multiple of page size.
*/
#if defined(CONFIG_VMAP_STACK) && (MIN_THREAD_SHIFT < PAGE_SHIFT)
#define THREAD_SHIFT PAGE_SHIFT
#else
#define THREAD_SHIFT MIN_THREAD_SHIFT
#endif
#if THREAD_SHIFT >= PAGE_SHIFT
#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
#endif
#define THREAD_SIZE (UL(1) << THREAD_SHIFT)
/*
* By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
* checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
* assembly.
*/
#ifdef CONFIG_VMAP_STACK
#define THREAD_ALIGN (2 * THREAD_SIZE)
#else
#define THREAD_ALIGN THREAD_SIZE
#endif
#define IRQ_STACK_SIZE THREAD_SIZE
#define OVERFLOW_STACK_SIZE SZ_4K
#define NVHE_STACK_SHIFT PAGE_SHIFT
#define NVHE_STACK_SIZE (UL(1) << NVHE_STACK_SHIFT)
/*
* With the minimum frame size of [x29, x30], exactly half the combined
* sizes of the hyp and overflow stacks is the maximum size needed to
* save the unwinded stacktrace; plus an additional entry to delimit the
* end.
*/
#define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + NVHE_STACK_SIZE) / 2 + sizeof(long))
/*
* Alignment of kernel segments (e.g. .text, .data).
*
* 4 KB granule: 16 level 3 entries, with contiguous bit
* 16 KB granule: 4 level 3 entries, without contiguous bit
* 64 KB granule: 1 level 3 entry
*/
#define SEGMENT_ALIGN SZ_64K
/*
* Memory types available.
*
* IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
* the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
* that protection_map[] only contains MT_NORMAL attributes.
*/
#define MT_NORMAL 0
#define MT_NORMAL_TAGGED 1
#define MT_NORMAL_NC 2
#define MT_DEVICE_nGnRnE 3
#define MT_DEVICE_nGnRE 4
/*
* Memory types for Stage-2 translation
*/
#define MT_S2_NORMAL 0xf
#define MT_S2_NORMAL_NC 0x5
#define MT_S2_DEVICE_nGnRE 0x1
/*
* Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001
* Stage-2 enforces Normal-WB and Device-nGnRE
*/
#define MT_S2_FWB_NORMAL 6
#define MT_S2_FWB_NORMAL_NC 5
#define MT_S2_FWB_DEVICE_nGnRE 1
#ifdef CONFIG_ARM64_4K_PAGES
#define IOREMAP_MAX_ORDER (PUD_SHIFT)
#else
#define IOREMAP_MAX_ORDER (PMD_SHIFT)
#endif
/*
* Open-coded (swapper_pg_dir - reserved_pg_dir) as this cannot be calculated
* until link time.
*/
#define RESERVED_SWAPPER_OFFSET (PAGE_SIZE)
/*
* Open-coded (swapper_pg_dir - tramp_pg_dir) as this cannot be calculated
* until link time.
*/
#define TRAMP_SWAPPER_OFFSET (2 * PAGE_SIZE)
#ifndef __ASSEMBLY__
#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/mmdebug.h>
#include <linux/types.h>
#include <asm/boot.h>
#include <asm/bug.h>
#include <asm/sections.h>
#include <asm/sysreg.h>
static inline u64 __pure read_tcr(void)
{
u64 tcr;
// read_sysreg() uses asm volatile, so avoid it here
asm("mrs %0, tcr_el1" : "=r"(tcr));
return tcr;
}
#if VA_BITS > 48
// For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here
#define vabits_actual (64 - ((read_tcr() >> 16) & 63))
#else
#define vabits_actual ((u64)VA_BITS)
#endif
extern s64 memstart_addr;
/* PHYS_OFFSET - the physical address of the start of memory. */
#define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
/* the offset between the kernel virtual and physical mappings */
extern u64 kimage_voffset;
static inline unsigned long kaslr_offset(void)
{
return (u64)&_text - KIMAGE_VADDR;
}
#ifdef CONFIG_RANDOMIZE_BASE
void kaslr_init(void);
static inline bool kaslr_enabled(void)
{
extern bool __kaslr_is_enabled;
return __kaslr_is_enabled;
}
#else
static inline void kaslr_init(void) { }
static inline bool kaslr_enabled(void) { return false; }
#endif
/*
* Allow all memory at the discovery stage. We will clip it later.
*/
#define MIN_MEMBLOCK_ADDR 0
#define MAX_MEMBLOCK_ADDR U64_MAX
/*
* PFNs are used to describe any physical page; this means
* PFN 0 == physical address 0.
*
* This is the PFN of the first RAM page in the kernel
* direct-mapped view. We assume this is the first page
* of RAM in the mem_map as well.
*/
#define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT)
/*
* When dealing with data aborts, watchpoints, or instruction traps we may end
* up with a tagged userland pointer. Clear the tag to get a sane pointer to
* pass on to access_ok(), for instance.
*/
#define __untagged_addr(addr) \
((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
#define untagged_addr(addr) ({ \
u64 __addr = (__force u64)(addr); \
__addr &= __untagged_addr(__addr); \
(__force __typeof__(addr))__addr; \
})
#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
#define __tag_shifted(tag) ((u64)(tag) << 56)
#define __tag_reset(addr) __untagged_addr(addr)
#define __tag_get(addr) (__u8)((u64)(addr) >> 56)
#else
#define __tag_shifted(tag) 0UL
#define __tag_reset(addr) (addr)
#define __tag_get(addr) 0
#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
static inline const void *__tag_set(const void *addr, u8 tag)
{
u64 __addr = (u64)addr & ~__tag_shifted(0xff);
return (const void *)(__addr | __tag_shifted(tag));
}
#ifdef CONFIG_KASAN_HW_TAGS
#define arch_enable_tag_checks_sync() mte_enable_kernel_sync()
#define arch_enable_tag_checks_async() mte_enable_kernel_async()
#define arch_enable_tag_checks_asymm() mte_enable_kernel_asymm()
#define arch_suppress_tag_checks_start() mte_enable_tco()
#define arch_suppress_tag_checks_stop() mte_disable_tco()
#define arch_force_async_tag_fault() mte_check_tfsr_exit()
#define arch_get_random_tag() mte_get_random_tag()
#define arch_get_mem_tag(addr) mte_get_mem_tag(addr)
#define arch_set_mem_tag_range(addr, size, tag, init) \
mte_set_mem_tag_range((addr), (size), (tag), (init))
#endif /* CONFIG_KASAN_HW_TAGS */
/*
* Physical vs virtual RAM address space conversion. These are
* private definitions which should NOT be used outside memory.h
* files. Use virt_to_phys/phys_to_virt/__pa/__va instead.
*/
/*
* Check whether an arbitrary address is within the linear map, which
* lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
* kernel's TTBR1 address range.
*/
#define __is_lm_address(addr) (((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
#define __lm_to_phys(addr) (((addr) - PAGE_OFFSET) + PHYS_OFFSET)
#define __kimg_to_phys(addr) ((addr) - kimage_voffset)
#define __virt_to_phys_nodebug(x) ({ \
phys_addr_t __x = (phys_addr_t)(__tag_reset(x)); \
__is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x); \
})
#define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x))
#ifdef CONFIG_DEBUG_VIRTUAL
extern phys_addr_t __virt_to_phys(unsigned long x);
extern phys_addr_t __phys_addr_symbol(unsigned long x);
#else
#define __virt_to_phys(x) __virt_to_phys_nodebug(x)
#define __phys_addr_symbol(x) __pa_symbol_nodebug(x)
#endif /* CONFIG_DEBUG_VIRTUAL */
#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
#define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset))
/*
* Note: Drivers should NOT use these. They are the wrong
* translation for translating DMA addresses. Use the driver
* DMA support - see dma-mapping.h.
*/
#define virt_to_phys virt_to_phys
static inline phys_addr_t virt_to_phys(const volatile void *x)
{
return __virt_to_phys((unsigned long)(x));
}
#define phys_to_virt phys_to_virt
static inline void *phys_to_virt(phys_addr_t x)
{
return (void *)(__phys_to_virt(x));
}
/* Needed already here for resolving __phys_to_pfn() in virt_to_pfn() */
#include <asm-generic/memory_model.h>
static inline unsigned long virt_to_pfn(const void *kaddr)
{
return __phys_to_pfn(virt_to_phys(kaddr));
}
/*
* Drivers should NOT use these either.
*/
#define __pa(x) __virt_to_phys((unsigned long)(x))
#define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
#define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x))
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x))
/*
* virt_to_page(x) convert a _valid_ virtual address to struct page *
* virt_addr_valid(x) indicates whether a virtual address is valid
*/
#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET)
#if defined(CONFIG_DEBUG_VIRTUAL)
#define page_to_virt(x) ({ \
__typeof__(x) __page = x; \
void *__addr = __va(page_to_phys(__page)); \
(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
})
#define virt_to_page(x) pfn_to_page(virt_to_pfn(x))
#else
#define page_to_virt(x) ({ \
__typeof__(x) __page = x; \
u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\
u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE); \
(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
})
#define virt_to_page(x) ({ \
u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE; \
u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \
(struct page *)__addr; \
})
#endif /* CONFIG_DEBUG_VIRTUAL */
#define virt_addr_valid(addr) ({ \
__typeof__(addr) __addr = __tag_reset(addr); \
__is_lm_address(__addr) && pfn_is_map_memory(virt_to_pfn(__addr)); \
})
void dump_mem_limit(void);
#endif /* !ASSEMBLY */
/*
* Given that the GIC architecture permits ITS implementations that can only be
* configured with a LPI table address once, GICv3 systems with many CPUs may
* end up reserving a lot of different regions after a kexec for their LPI
* tables (one per CPU), as we are forced to reuse the same memory after kexec
* (and thus reserve it persistently with EFI beforehand)
*/
#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS)
# define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1)
#endif
/*
* memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory
* of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into
* multiple parts. As a result, the number of memory regions is large.
*/
#ifdef CONFIG_EFI
#define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8)
#endif
#endif /* __ASM_MEMORY_H */
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the Interfaces handler.
*
* Version: @(#)dev.h 1.0.10 08/12/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Bjorn Ekwall. <bj0rn@blox.se>
* Pekka Riikonen <priikone@poseidon.pspt.fi>
*
* Moved to /usr/include/linux for NET3
*/
#ifndef _LINUX_NETDEVICE_H
#define _LINUX_NETDEVICE_H
#include <linux/timer.h>
#include <linux/bug.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/prefetch.h>
#include <asm/cache.h>
#include <asm/byteorder.h>
#include <asm/local.h>
#include <linux/percpu.h>
#include <linux/rculist.h>
#include <linux/workqueue.h>
#include <linux/dynamic_queue_limits.h>
#include <net/net_namespace.h>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
#include <net/netprio_cgroup.h>
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
#include <linux/netdevice_xmit.h>
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
#include <uapi/linux/pkt_cls.h>
#include <uapi/linux/netdev.h>
#include <linux/hashtable.h>
#include <linux/rbtree.h>
#include <net/net_trackers.h>
#include <net/net_debug.h>
#include <net/dropreason-core.h>
#include <net/neighbour_tables.h>
struct netpoll_info;
struct device;
struct ethtool_ops;
struct kernel_hwtstamp_config;
struct phy_device;
struct dsa_port;
struct ip_tunnel_parm_kern;
struct macsec_context;
struct macsec_ops;
struct netdev_config;
struct netdev_name_node;
struct sd_flow_limit;
struct sfp_bus;
/* 802.11 specific */
struct wireless_dev;
/* 802.15.4 specific */
struct wpan_dev;
struct mpls_dev;
/* UDP Tunnel offloads */
struct udp_tunnel_info;
struct udp_tunnel_nic_info;
struct udp_tunnel_nic;
struct bpf_prog;
struct xdp_buff;
struct xdp_frame;
struct xdp_metadata_ops;
struct xdp_md;
struct ethtool_netdev_state;
struct phy_link_topology;
struct hwtstamp_provider;
typedef u32 xdp_features_t;
void synchronize_net(void);
void netdev_set_default_ethtool_ops(struct net_device *dev,
const struct ethtool_ops *ops);
void netdev_sw_irq_coalesce_default_on(struct net_device *dev);
/* Backlog congestion levels */
#define NET_RX_SUCCESS 0 /* keep 'em coming, baby */
#define NET_RX_DROP 1 /* packet dropped */
#define MAX_NEST_DEV 8
/*
* Transmit return codes: transmit return codes originate from three different
* namespaces:
*
* - qdisc return codes
* - driver transmit return codes
* - errno values
*
* Drivers are allowed to return any one of those in their hard_start_xmit()
* function. Real network devices commonly used with qdiscs should only return
* the driver transmit return codes though - when qdiscs are used, the actual
* transmission happens asynchronously, so the value is not propagated to
* higher layers. Virtual network devices transmit synchronously; in this case
* the driver transmit return codes are consumed by dev_queue_xmit(), and all
* others are propagated to higher layers.
*/
/* qdisc ->enqueue() return codes. */
#define NET_XMIT_SUCCESS 0x00
#define NET_XMIT_DROP 0x01 /* skb dropped */
#define NET_XMIT_CN 0x02 /* congestion notification */
#define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */
/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
* indicates that the device will soon be dropping packets, or already drops
* some packets of the same priority; prompting us to send less aggressively. */
#define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e))
#define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0)
/* Driver transmit return codes */
#define NETDEV_TX_MASK 0xf0
enum netdev_tx {
__NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */
NETDEV_TX_OK = 0x00, /* driver took care of packet */
NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/
};
typedef enum netdev_tx netdev_tx_t;
/*
* Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant;
* hard_start_xmit() return < NET_XMIT_MASK means skb was consumed.
*/
static inline bool dev_xmit_complete(int rc)
{
/*
* Positive cases with an skb consumed by a driver:
* - successful transmission (rc == NETDEV_TX_OK)
* - error while transmitting (rc < 0)
* - error while queueing to a different device (rc & NET_XMIT_MASK)
*/
if (likely(rc < NET_XMIT_MASK))
return true;
return false;
}
/*
* Compute the worst-case header length according to the protocols
* used.
*/
#if defined(CONFIG_HYPERV_NET)
# define LL_MAX_HEADER 128
#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
# if defined(CONFIG_MAC80211_MESH)
# define LL_MAX_HEADER 128
# else
# define LL_MAX_HEADER 96
# endif
#else
# define LL_MAX_HEADER 32
#endif
#if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \
!IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL)
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif
/*
* Old network device statistics. Fields are native words
* (unsigned long) so they can be read and written atomically.
*/
#define NET_DEV_STAT(FIELD) \
union { \
unsigned long FIELD; \
atomic_long_t __##FIELD; \
}
struct net_device_stats {
NET_DEV_STAT(rx_packets);
NET_DEV_STAT(tx_packets);
NET_DEV_STAT(rx_bytes);
NET_DEV_STAT(tx_bytes);
NET_DEV_STAT(rx_errors);
NET_DEV_STAT(tx_errors);
NET_DEV_STAT(rx_dropped);
NET_DEV_STAT(tx_dropped);
NET_DEV_STAT(multicast);
NET_DEV_STAT(collisions);
NET_DEV_STAT(rx_length_errors);
NET_DEV_STAT(rx_over_errors);
NET_DEV_STAT(rx_crc_errors);
NET_DEV_STAT(rx_frame_errors);
NET_DEV_STAT(rx_fifo_errors);
NET_DEV_STAT(rx_missed_errors);
NET_DEV_STAT(tx_aborted_errors);
NET_DEV_STAT(tx_carrier_errors);
NET_DEV_STAT(tx_fifo_errors);
NET_DEV_STAT(tx_heartbeat_errors);
NET_DEV_STAT(tx_window_errors);
NET_DEV_STAT(rx_compressed);
NET_DEV_STAT(tx_compressed);
};
#undef NET_DEV_STAT
/* per-cpu stats, allocated on demand.
* Try to fit them in a single cache line, for dev_get_stats() sake.
*/
struct net_device_core_stats {
unsigned long rx_dropped;
unsigned long tx_dropped;
unsigned long rx_nohandler;
unsigned long rx_otherhost_dropped;
} __aligned(4 * sizeof(unsigned long));
#include <linux/cache.h>
#include <linux/skbuff.h>
struct neighbour;
struct neigh_parms;
struct sk_buff;
struct netdev_hw_addr {
struct list_head list;
struct rb_node node;
unsigned char addr[MAX_ADDR_LEN];
unsigned char type;
#define NETDEV_HW_ADDR_T_LAN 1
#define NETDEV_HW_ADDR_T_SAN 2
#define NETDEV_HW_ADDR_T_UNICAST 3
#define NETDEV_HW_ADDR_T_MULTICAST 4
bool global_use;
int sync_cnt;
int refcount;
int synced;
struct rcu_head rcu_head;
};
struct netdev_hw_addr_list {
struct list_head list;
int count;
/* Auxiliary tree for faster lookup on addition and deletion */
struct rb_root tree;
};
#define netdev_hw_addr_list_count(l) ((l)->count)
#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0)
#define netdev_hw_addr_list_for_each(ha, l) \
list_for_each_entry(ha, &(l)->list, list)
#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc)
#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc)
#define netdev_for_each_uc_addr(ha, dev) \
netdev_hw_addr_list_for_each(ha, &(dev)->uc)
#define netdev_for_each_synced_uc_addr(_ha, _dev) \
netdev_for_each_uc_addr((_ha), (_dev)) \
if ((_ha)->sync_cnt)
#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
#define netdev_for_each_mc_addr(ha, dev) \
netdev_hw_addr_list_for_each(ha, &(dev)->mc)
#define netdev_for_each_synced_mc_addr(_ha, _dev) \
netdev_for_each_mc_addr((_ha), (_dev)) \
if ((_ha)->sync_cnt)
struct hh_cache {
unsigned int hh_len;
seqlock_t hh_lock;
/* cached hardware header; allow for machine alignment needs. */
#define HH_DATA_MOD 16
#define HH_DATA_OFF(__len) \
(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
#define HH_DATA_ALIGN(__len) \
(((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1))
unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)];
};
/* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much.
* Alternative is:
* dev->hard_header_len ? (dev->hard_header_len +
* (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0
*
* We could use other alignment values, but we must maintain the
* relationship HH alignment <= LL alignment.
*/
#define LL_RESERVED_SPACE(dev) \
((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \
& ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \
& ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
struct header_ops {
int (*create) (struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr,
const void *saddr, unsigned int len);
int (*parse)(const struct sk_buff *skb, unsigned char *haddr);
int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
void (*cache_update)(struct hh_cache *hh,
const struct net_device *dev,
const unsigned char *haddr);
bool (*validate)(const char *ll_header, unsigned int len);
__be16 (*parse_protocol)(const struct sk_buff *skb);
};
/* These flag bits are private to the generic network queueing
* layer; they may not be explicitly referenced by any other
* code.
*/
enum netdev_state_t {
__LINK_STATE_START,
__LINK_STATE_PRESENT,
__LINK_STATE_NOCARRIER,
__LINK_STATE_LINKWATCH_PENDING,
__LINK_STATE_DORMANT,
__LINK_STATE_TESTING,
};
struct gro_list {
struct list_head list;
int count;
};
/*
* size of gro hash buckets, must be <= the number of bits in
* gro_node::bitmask
*/
#define GRO_HASH_BUCKETS 8
/**
* struct gro_node - structure to support Generic Receive Offload
* @bitmask: bitmask to indicate used buckets in @hash
* @hash: hashtable of pending aggregated skbs, separated by flows
* @rx_list: list of pending ``GRO_NORMAL`` skbs
* @rx_count: cached current length of @rx_list
* @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone
*/
struct gro_node {
unsigned long bitmask;
struct gro_list hash[GRO_HASH_BUCKETS];
struct list_head rx_list;
u32 rx_count;
u32 cached_napi_id;
};
/*
* Structure for per-NAPI config
*/
struct napi_config {
u64 gro_flush_timeout;
u64 irq_suspend_timeout;
u32 defer_hard_irqs;
cpumask_t affinity_mask;
unsigned int napi_id;
};
/*
* Structure for NAPI scheduling similar to tasklet but with weighting
*/
struct napi_struct {
/* The poll_list must only be managed by the entity which
* changes the state of the NAPI_STATE_SCHED bit. This means
* whoever atomically sets that bit can add this napi_struct
* to the per-CPU poll_list, and whoever clears that bit
* can remove from the list right before clearing the bit.
*/
struct list_head poll_list;
unsigned long state;
int weight;
u32 defer_hard_irqs_count;
int (*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
/* CPU actively polling if netpoll is configured */
int poll_owner;
#endif
/* CPU on which NAPI has been scheduled for processing */
int list_owner;
struct net_device *dev;
struct sk_buff *skb;
struct gro_node gro;
struct hrtimer timer;
/* all fields past this point are write-protected by netdev_lock */
struct task_struct *thread;
unsigned long gro_flush_timeout;
unsigned long irq_suspend_timeout;
u32 defer_hard_irqs;
/* control-path-only fields follow */
u32 napi_id;
struct list_head dev_list;
struct hlist_node napi_hash_node;
int irq;
struct irq_affinity_notify notify;
int napi_rmap_idx;
int index;
struct napi_config *config;
};
enum {
NAPI_STATE_SCHED, /* Poll is scheduled */
NAPI_STATE_MISSED, /* reschedule a napi */
NAPI_STATE_DISABLE, /* Disable pending */
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
NAPI_STATE_LISTED, /* NAPI added to system lists */
NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */
NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */
NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/
NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/
NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */
NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */
};
enum {
NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED),
NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED),
NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE),
NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC),
NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED),
NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL),
NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED),
NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER),
};
enum gro_result {
GRO_MERGED,
GRO_MERGED_FREE,
GRO_HELD,
GRO_NORMAL,
GRO_CONSUMED,
};
typedef enum gro_result gro_result_t;
/*
* enum rx_handler_result - Possible return values for rx_handlers.
* @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it
* further.
* @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in
* case skb->dev was changed by rx_handler.
* @RX_HANDLER_EXACT: Force exact delivery, no wildcard.
* @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called.
*
* rx_handlers are functions called from inside __netif_receive_skb(), to do
* special processing of the skb, prior to delivery to protocol handlers.
*
* Currently, a net_device can only have a single rx_handler registered. Trying
* to register a second rx_handler will return -EBUSY.
*
* To register a rx_handler on a net_device, use netdev_rx_handler_register().
* To unregister a rx_handler on a net_device, use
* netdev_rx_handler_unregister().
*
* Upon return, rx_handler is expected to tell __netif_receive_skb() what to
* do with the skb.
*
* If the rx_handler consumed the skb in some way, it should return
* RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for
* the skb to be delivered in some other way.
*
* If the rx_handler changed skb->dev, to divert the skb to another
* net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the
* new device will be called if it exists.
*
* If the rx_handler decides the skb should be ignored, it should return
* RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
* are registered on exact device (ptype->dev == skb->dev).
*
* If the rx_handler didn't change skb->dev, but wants the skb to be normally
* delivered, it should return RX_HANDLER_PASS.
*
* A device without a registered rx_handler will behave as if rx_handler
* returned RX_HANDLER_PASS.
*/
enum rx_handler_result {
RX_HANDLER_CONSUMED,
RX_HANDLER_ANOTHER,
RX_HANDLER_EXACT,
RX_HANDLER_PASS,
};
typedef enum rx_handler_result rx_handler_result_t;
typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
void __napi_schedule(struct napi_struct *n);
void __napi_schedule_irqoff(struct napi_struct *n);
static inline bool napi_disable_pending(struct napi_struct *n)
{
return test_bit(NAPI_STATE_DISABLE, &n->state);
}
static inline bool napi_prefer_busy_poll(struct napi_struct *n)
{
return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
}
/**
* napi_is_scheduled - test if NAPI is scheduled
* @n: NAPI context
*
* This check is "best-effort". With no locking implemented,
* a NAPI can be scheduled or terminate right after this check
* and produce not precise results.
*
* NAPI_STATE_SCHED is an internal state, napi_is_scheduled
* should not be used normally and napi_schedule should be
* used instead.
*
* Use only if the driver really needs to check if a NAPI
* is scheduled for example in the context of delayed timer
* that can be skipped if a NAPI is already scheduled.
*
* Return: True if NAPI is scheduled, False otherwise.
*/
static inline bool napi_is_scheduled(struct napi_struct *n)
{
return test_bit(NAPI_STATE_SCHED, &n->state);
}
bool napi_schedule_prep(struct napi_struct *n);
/**
* napi_schedule - schedule NAPI poll
* @n: NAPI context
*
* Schedule NAPI poll routine to be called if it is not already
* running.
* Return: true if we schedule a NAPI or false if not.
* Refer to napi_schedule_prep() for additional reason on why
* a NAPI might not be scheduled.
*/
static inline bool napi_schedule(struct napi_struct *n)
{
if (napi_schedule_prep(n)) { __napi_schedule(n);
return true;
}
return false;
}
/**
* napi_schedule_irqoff - schedule NAPI poll
* @n: NAPI context
*
* Variant of napi_schedule(), assuming hard irqs are masked.
*/
static inline void napi_schedule_irqoff(struct napi_struct *n)
{
if (napi_schedule_prep(n))
__napi_schedule_irqoff(n);
}
/**
* napi_complete_done - NAPI processing complete
* @n: NAPI context
* @work_done: number of packets processed
*
* Mark NAPI processing as complete. Should only be called if poll budget
* has not been completely consumed.
* Prefer over napi_complete().
* Return: false if device should avoid rearming interrupts.
*/
bool napi_complete_done(struct napi_struct *n, int work_done);
static inline bool napi_complete(struct napi_struct *n)
{
return napi_complete_done(n, 0);
}
int dev_set_threaded(struct net_device *dev, bool threaded);
void napi_disable(struct napi_struct *n);
void napi_disable_locked(struct napi_struct *n);
void napi_enable(struct napi_struct *n);
void napi_enable_locked(struct napi_struct *n);
/**
* napi_synchronize - wait until NAPI is not running
* @n: NAPI context
*
* Wait until NAPI is done being scheduled on this context.
* Waits till any outstanding processing completes but
* does not disable future activations.
*/
static inline void napi_synchronize(const struct napi_struct *n)
{
if (IS_ENABLED(CONFIG_SMP))
while (test_bit(NAPI_STATE_SCHED, &n->state))
msleep(1);
else
barrier();
}
/**
* napi_if_scheduled_mark_missed - if napi is running, set the
* NAPIF_STATE_MISSED
* @n: NAPI context
*
* If napi is running, set the NAPIF_STATE_MISSED, and return true if
* NAPI is scheduled.
**/
static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n)
{
unsigned long val, new;
val = READ_ONCE(n->state);
do {
if (val & NAPIF_STATE_DISABLE)
return true;
if (!(val & NAPIF_STATE_SCHED))
return false;
new = val | NAPIF_STATE_MISSED;
} while (!try_cmpxchg(&n->state, &val, new));
return true;
}
enum netdev_queue_state_t {
__QUEUE_STATE_DRV_XOFF,
__QUEUE_STATE_STACK_XOFF,
__QUEUE_STATE_FROZEN,
};
#define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF)
#define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN)
#define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
QUEUE_STATE_FROZEN)
#define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \
QUEUE_STATE_FROZEN)
/*
* __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The
* netif_tx_* functions below are used to manipulate this flag. The
* __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit
* queue independently. The netif_xmit_*stopped functions below are called
* to check if the queue has been stopped by the driver or stack (either
* of the XOFF bits are set in the state). Drivers should not need to call
* netif_xmit*stopped functions, they should only be using netif_tx_*.
*/
struct netdev_queue {
/*
* read-mostly part
*/
struct net_device *dev;
netdevice_tracker dev_tracker;
struct Qdisc __rcu *qdisc;
struct Qdisc __rcu *qdisc_sleeping;
#ifdef CONFIG_SYSFS
struct kobject kobj;
const struct attribute_group **groups;
#endif
unsigned long tx_maxrate;
/*
* Number of TX timeouts for this queue
* (/sys/class/net/DEV/Q/trans_timeout)
*/
atomic_long_t trans_timeout;
/* Subordinate device that the queue has been assigned to */
struct net_device *sb_dev;
#ifdef CONFIG_XDP_SOCKETS
struct xsk_buff_pool *pool;
#endif
/*
* write-mostly part
*/
#ifdef CONFIG_BQL
struct dql dql;
#endif
spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
int xmit_lock_owner;
/*
* Time (in jiffies) of last Tx
*/
unsigned long trans_start;
unsigned long state;
/*
* slow- / control-path part
*/
/* NAPI instance for the queue
* "ops protected", see comment about net_device::lock
*/
struct napi_struct *napi;
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
int numa_node;
#endif
} ____cacheline_aligned_in_smp;
extern int sysctl_fb_tunnels_only_for_init_net;
extern int sysctl_devconf_inherit_init_net;
/*
* sysctl_fb_tunnels_only_for_init_net == 0 : For all netns
* == 1 : For initns only
* == 2 : For none.
*/
static inline bool net_has_fallback_tunnels(const struct net *net)
{
#if IS_ENABLED(CONFIG_SYSCTL)
int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
return !fb_tunnels_only_for_init_net ||
(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
#else
return true;
#endif
}
static inline int net_inherit_devconf(void)
{
#if IS_ENABLED(CONFIG_SYSCTL)
return READ_ONCE(sysctl_devconf_inherit_init_net);
#else
return 0;
#endif
}
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
{
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
return q->numa_node;
#else
return NUMA_NO_NODE;
#endif
}
static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node)
{
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
q->numa_node = node;
#endif
}
#ifdef CONFIG_RFS_ACCEL
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
u16 filter_id);
#endif
/* XPS map type and offset of the xps map within net_device->xps_maps[]. */
enum xps_map_type {
XPS_CPUS = 0,
XPS_RXQS,
XPS_MAPS_MAX,
};
#ifdef CONFIG_XPS
/*
* This structure holds an XPS map which can be of variable length. The
* map is an array of queues.
*/
struct xps_map {
unsigned int len;
unsigned int alloc_len;
struct rcu_head rcu;
u16 queues[];
};
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \
- sizeof(struct xps_map)) / sizeof(u16))
/*
* This structure holds all XPS maps for device. Maps are indexed by CPU.
*
* We keep track of the number of cpus/rxqs used when the struct is allocated,
* in nr_ids. This will help not accessing out-of-bound memory.
*
* We keep track of the number of traffic classes used when the struct is
* allocated, in num_tc. This will be used to navigate the maps, to ensure we're
* not crossing its upper bound, as the original dev->num_tc can be updated in
* the meantime.
*/
struct xps_dev_maps {
struct rcu_head rcu;
unsigned int nr_ids;
s16 num_tc;
struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */
};
#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
(nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\
(_rxqs * (_tcs) * sizeof(struct xps_map *)))
#endif /* CONFIG_XPS */
#define TC_MAX_QUEUE 16
#define TC_BITMASK 15
/* HW offloaded queuing disciplines txq count and offset maps */
struct netdev_tc_txq {
u16 count;
u16 offset;
};
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
/*
* This structure is to hold information about the device
* configured to run FCoE protocol stack.
*/
struct netdev_fcoe_hbainfo {
char manufacturer[64];
char serial_number[64];
char hardware_version[64];
char driver_version[64];
char optionrom_version[64];
char firmware_version[64];
char model[256];
char model_description[256];
};
#endif
#define MAX_PHYS_ITEM_ID_LEN 32
/* This structure holds a unique identifier to identify some
* physical item (port for example) used by a netdevice.
*/
struct netdev_phys_item_id {
unsigned char id[MAX_PHYS_ITEM_ID_LEN];
unsigned char id_len;
};
static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
struct netdev_phys_item_id *b)
{
return a->id_len == b->id_len &&
memcmp(a->id, b->id, a->id_len) == 0;
}
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
enum net_device_path_type {
DEV_PATH_ETHERNET = 0,
DEV_PATH_VLAN,
DEV_PATH_BRIDGE,
DEV_PATH_PPPOE,
DEV_PATH_DSA,
DEV_PATH_MTK_WDMA,
};
struct net_device_path {
enum net_device_path_type type;
const struct net_device *dev;
union {
struct {
u16 id;
__be16 proto;
u8 h_dest[ETH_ALEN];
} encap;
struct {
enum {
DEV_PATH_BR_VLAN_KEEP,
DEV_PATH_BR_VLAN_TAG,
DEV_PATH_BR_VLAN_UNTAG,
DEV_PATH_BR_VLAN_UNTAG_HW,
} vlan_mode;
u16 vlan_id;
__be16 vlan_proto;
} bridge;
struct {
int port;
u16 proto;
} dsa;
struct {
u8 wdma_idx;
u8 queue;
u16 wcid;
u8 bss;
u8 amsdu;
} mtk_wdma;
};
};
#define NET_DEVICE_PATH_STACK_MAX 5
#define NET_DEVICE_PATH_VLAN_MAX 2
struct net_device_path_stack {
int num_paths;
struct net_device_path path[NET_DEVICE_PATH_STACK_MAX];
};
struct net_device_path_ctx {
const struct net_device *dev;
u8 daddr[ETH_ALEN];
int num_vlans;
struct {
u16 id;
__be16 proto;
} vlan[NET_DEVICE_PATH_VLAN_MAX];
};
enum tc_setup_type {
TC_QUERY_CAPS,
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
TC_SETUP_CLSFLOWER,
TC_SETUP_CLSMATCHALL,
TC_SETUP_CLSBPF,
TC_SETUP_BLOCK,
TC_SETUP_QDISC_CBS,
TC_SETUP_QDISC_RED,
TC_SETUP_QDISC_PRIO,
TC_SETUP_QDISC_MQ,
TC_SETUP_QDISC_ETF,
TC_SETUP_ROOT_QDISC,
TC_SETUP_QDISC_GRED,
TC_SETUP_QDISC_TAPRIO,
TC_SETUP_FT,
TC_SETUP_QDISC_ETS,
TC_SETUP_QDISC_TBF,
TC_SETUP_QDISC_FIFO,
TC_SETUP_QDISC_HTB,
TC_SETUP_ACT,
};
/* These structures hold the attributes of bpf state that are being passed
* to the netdevice through the bpf op.
*/
enum bpf_netdev_command {
/* Set or clear a bpf program used in the earliest stages of packet
* rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee
* is responsible for calling bpf_prog_put on any old progs that are
* stored. In case of error, the callee need not release the new prog
* reference, but on success it takes ownership and must bpf_prog_put
* when it is no longer used.
*/
XDP_SETUP_PROG,
XDP_SETUP_PROG_HW,
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_MAP_ALLOC,
BPF_OFFLOAD_MAP_FREE,
XDP_SETUP_XSK_POOL,
};
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
struct xdp_dev_bulk_queue;
struct bpf_xdp_link;
enum bpf_xdp_mode {
XDP_MODE_SKB = 0,
XDP_MODE_DRV = 1,
XDP_MODE_HW = 2,
__MAX_XDP_MODE
};
struct bpf_xdp_entity {
struct bpf_prog *prog;
struct bpf_xdp_link *link;
};
struct netdev_bpf {
enum bpf_netdev_command command;
union {
/* XDP_SETUP_PROG */
struct {
u32 flags;
struct bpf_prog *prog;
struct netlink_ext_ack *extack;
};
/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
struct {
struct bpf_offloaded_map *offmap;
};
/* XDP_SETUP_XSK_POOL */
struct {
struct xsk_buff_pool *pool;
u16 queue_id;
} xsk;
};
};
/* Flags for ndo_xsk_wakeup. */
#define XDP_WAKEUP_RX (1 << 0)
#define XDP_WAKEUP_TX (1 << 1)
#ifdef CONFIG_XFRM_OFFLOAD
struct xfrmdev_ops {
int (*xdo_dev_state_add) (struct xfrm_state *x, struct netlink_ext_ack *extack);
void (*xdo_dev_state_delete) (struct xfrm_state *x);
void (*xdo_dev_state_free) (struct xfrm_state *x);
bool (*xdo_dev_offload_ok) (struct sk_buff *skb,
struct xfrm_state *x);
void (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
void (*xdo_dev_state_update_stats) (struct xfrm_state *x);
int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack);
void (*xdo_dev_policy_delete) (struct xfrm_policy *x);
void (*xdo_dev_policy_free) (struct xfrm_policy *x);
};
#endif
struct dev_ifalias {
struct rcu_head rcuhead;
char ifalias[];
};
struct devlink;
struct tlsdev_ops;
struct netdev_net_notifier {
struct list_head list;
struct notifier_block *nb;
};
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
* optional and can be filled with a null pointer.
*
* int (*ndo_init)(struct net_device *dev);
* This function is called once when a network device is registered.
* The network device can use this for any late stage initialization
* or semantic validation. It can fail with an error code which will
* be propagated back to register_netdev.
*
* void (*ndo_uninit)(struct net_device *dev);
* This function is called when device is unregistered or when registration
* fails. It is not called if init fails.
*
* int (*ndo_open)(struct net_device *dev);
* This function is called when a network device transitions to the up
* state.
*
* int (*ndo_stop)(struct net_device *dev);
* This function is called when a network device transitions to the down
* state.
*
* netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
* struct net_device *dev);
* Called when a packet needs to be transmitted.
* Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop
* the queue before that can happen; it's for obsolete devices and weird
* corner cases, but the stack really does a non-trivial amount
* of useless work if you return NETDEV_TX_BUSY.
* Required; cannot be NULL.
*
* netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
* struct net_device *dev
* netdev_features_t features);
* Called by core transmit path to determine if device is capable of
* performing offload operations on a given packet. This is to give
* the device an opportunity to implement any restrictions that cannot
* be otherwise expressed by feature flags. The check is called with
* the set of features that the stack has calculated and it returns
* those the driver believes to be appropriate.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
* struct net_device *sb_dev);
* Called to decide which queue to use when device supports multiple
* transmit queues.
*
* void (*ndo_change_rx_flags)(struct net_device *dev, int flags);
* This function is called to allow device receiver to make
* changes to configuration when multicast or promiscuous is enabled.
*
* void (*ndo_set_rx_mode)(struct net_device *dev);
* This function is called device changes address list filtering.
* If driver handles unicast address filtering, it should set
* IFF_UNICAST_FLT in its priv_flags.
*
* int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
* This function is called when the Media Access Control address
* needs to be changed. If this interface is not defined, the
* MAC address can not be changed.
*
* int (*ndo_validate_addr)(struct net_device *dev);
* Test if Media Access Control address is valid for the device.
*
* int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
* Old-style ioctl entry point. This is used internally by the
* ieee802154 subsystem but is no longer called by the device
* ioctl handler.
*
* int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd);
* Used by the bonding driver for its device specific ioctls:
* SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE,
* SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY
*
* * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
* Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG,
* SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP.
*
* int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);
* Used to set network devices bus interface parameters. This interface
* is retained for legacy reasons; new devices should use the bus
* interface (PCI) for low level management.
*
* int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);
* Called when a user wants to change the Maximum Transfer Unit
* of a device.
*
* void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue);
* Callback used when the transmitter has not made any progress
* for dev->watchdog ticks.
*
* void (*ndo_get_stats64)(struct net_device *dev,
* struct rtnl_link_stats64 *storage);
* struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
* Called when a user wants to get the network device usage
* statistics. Drivers must do one of the following:
* 1. Define @ndo_get_stats64 to fill in a zero-initialised
* rtnl_link_stats64 structure passed by the caller.
* 2. Define @ndo_get_stats to update a net_device_stats structure
* (which should normally be dev->stats) and return a pointer to
* it. The structure may be changed asynchronously only if each
* field is written atomically.
* 3. Update dev->stats asynchronously and atomically, and define
* neither operation.
*
* bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id)
* Return true if this device supports offload stats of this attr_id.
*
* int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev,
* void *attr_data)
* Get statistics for offload operations by attr_id. Write it into the
* attr_data pointer.
*
* int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports VLAN filtering this function is called when a
* VLAN id is registered.
*
* int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports VLAN filtering this function is called when a
* VLAN id is unregistered.
*
* void (*ndo_poll_controller)(struct net_device *dev);
*
* SR-IOV management functions.
* int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);
* int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan,
* u8 qos, __be16 proto);
* int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
* int max_tx_rate);
* int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
* int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_config)(struct net_device *dev,
* int vf, struct ifla_vf_info *ivf);
* int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
* int (*ndo_set_vf_port)(struct net_device *dev, int vf,
* struct nlattr *port[]);
*
* Enable or disable the VF ability to query its RSS Redirection Table and
* Hash Key. This is needed since on some devices VF share this information
* with PF and querying it may introduce a theoretical security risk.
* int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
* int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type,
* void *type_data);
* Called to setup any 'tc' scheduler, classifier or action on @dev.
* This is always called from the stack with the rtnl lock held and netif
* tx queues stopped. This allows the netdevice to perform queue
* management safely.
*
* Fiber Channel over Ethernet (FCoE) offload functions.
* int (*ndo_fcoe_enable)(struct net_device *dev);
* Called when the FCoE protocol stack wants to start using LLD for FCoE
* so the underlying device can perform whatever needed configuration or
* initialization to support acceleration of FCoE traffic.
*
* int (*ndo_fcoe_disable)(struct net_device *dev);
* Called when the FCoE protocol stack wants to stop using LLD for FCoE
* so the underlying device can perform whatever needed clean-ups to
* stop supporting acceleration of FCoE traffic.
*
* int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,
* struct scatterlist *sgl, unsigned int sgc);
* Called when the FCoE Initiator wants to initialize an I/O that
* is a possible candidate for Direct Data Placement (DDP). The LLD can
* perform necessary setup and returns 1 to indicate the device is set up
* successfully to perform DDP on this I/O, otherwise this returns 0.
*
* int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid);
* Called when the FCoE Initiator/Target is done with the DDPed I/O as
* indicated by the FC exchange id 'xid', so the underlying device can
* clean up and reuse resources for later DDP requests.
*
* int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,
* struct scatterlist *sgl, unsigned int sgc);
* Called when the FCoE Target wants to initialize an I/O that
* is a possible candidate for Direct Data Placement (DDP). The LLD can
* perform necessary setup and returns 1 to indicate the device is set up
* successfully to perform DDP on this I/O, otherwise this returns 0.
*
* int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
* struct netdev_fcoe_hbainfo *hbainfo);
* Called when the FCoE Protocol stack wants information on the underlying
* device. This information is utilized by the FCoE protocol stack to
* register attributes with Fiber Channel management service as per the
* FC-GS Fabric Device Management Information(FDMI) specification.
*
* int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);
* Called when the underlying device wants to override default World Wide
* Name (WWN) generation mechanism in FCoE protocol stack to pass its own
* World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE
* protocol stack to use.
*
* RFS acceleration.
* int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
* u16 rxq_index, u32 flow_id);
* Set hardware filter for RFS. rxq_index is the target queue index;
* flow_id is a flow ID to be passed to rps_may_expire_flow() later.
* Return the filter ID on success, or a negative error code.
*
* Slave management functions (for bridge, bonding, etc).
* int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to make another netdev an underling.
*
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to release previously enslaved netdev.
*
* struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev,
* struct sk_buff *skb,
* bool all_slaves);
* Get the xmit slave of master device. If all_slaves is true, function
* assume all the slaves can transmit.
*
* Feature/offload setting functions.
* netdev_features_t (*ndo_fix_features)(struct net_device *dev,
* netdev_features_t features);
* Adjusts the requested feature flags according to device-specific
* constraints, and returns the resulting flags. Must not modify
* the device state.
*
* int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
* Called to update device configuration to new features. Passed
* feature set might be less than what was returned by ndo_fix_features()).
* Must return >0 or -errno if it changed dev->features itself.
*
* int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],
* struct net_device *dev,
* const unsigned char *addr, u16 vid, u16 flags,
* bool *notified, struct netlink_ext_ack *extack);
* Adds an FDB entry to dev for addr.
* Callee shall set *notified to true if it sent any appropriate
* notification(s). Otherwise core will send a generic one.
* int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
* struct net_device *dev,
* const unsigned char *addr, u16 vid
* bool *notified, struct netlink_ext_ack *extack);
* Deletes the FDB entry from dev corresponding to addr.
* Callee shall set *notified to true if it sent any appropriate
* notification(s). Otherwise core will send a generic one.
* int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev,
* struct netlink_ext_ack *extack);
* int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
* struct net_device *dev, struct net_device *filter_dev,
* int *idx)
* Used to add FDB entries to dump requests. Implementers should add
* entries to skb and update idx with the number of entries.
*
* int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[],
* u16 nlmsg_flags, struct netlink_ext_ack *extack);
* Adds an MDB entry to dev.
* int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[],
* struct netlink_ext_ack *extack);
* Deletes the MDB entry from dev.
* int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[],
* struct netlink_ext_ack *extack);
* Bulk deletes MDB entries from dev.
* int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb,
* struct netlink_callback *cb);
* Dumps MDB entries from dev. The first argument (marker) in the netlink
* callback is used by core rtnetlink code.
*
* int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags, struct netlink_ext_ack *extack)
* int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
* struct net_device *dev, u32 filter_mask,
* int nlflags)
* int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags);
*
* int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
* Called to change device carrier. Soft-devices (like dummy, team, etc)
* which do not represent real hardware may define this to allow their
* userspace components to manage their virtual carrier state. Devices
* that determine carrier state from physical hardware properties (eg
* network cables) or protocol-dependent mechanisms (eg
* USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
*
* int (*ndo_get_phys_port_id)(struct net_device *dev,
* struct netdev_phys_item_id *ppid);
* Called to get ID of physical port of this device. If driver does
* not implement this, it is assumed that the hw is not able to have
* multiple net devices on single physical port.
*
* int (*ndo_get_port_parent_id)(struct net_device *dev,
* struct netdev_phys_item_id *ppid)
* Called to get the parent ID of the physical port of this device.
*
* void* (*ndo_dfwd_add_station)(struct net_device *pdev,
* struct net_device *dev)
* Called by upper layer devices to accelerate switching or other
* station functionality into hardware. 'pdev is the lowerdev
* to use for the offload and 'dev' is the net device that will
* back the offload. Returns a pointer to the private structure
* the upper layer will maintain.
* void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv)
* Called by upper layer device to delete the station created
* by 'ndo_dfwd_add_station'. 'pdev' is the net device backing
* the station and priv is the structure returned by the add
* operation.
* int (*ndo_set_tx_maxrate)(struct net_device *dev,
* int queue_index, u32 maxrate);
* Called when a user wants to set a max-rate limitation of specific
* TX queue.
* int (*ndo_get_iflink)(const struct net_device *dev);
* Called to get the iflink value of this device.
* int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb);
* This function is used to get egress tunnel information for given skb.
* This is useful for retrieving outer tunnel header parameters while
* sampling packet.
* void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
* This function is used to specify the headroom that the skb must
* consider when allocation skb during packet reception. Setting
* appropriate rx headroom value allows avoiding skb head copy on
* forward. Setting a negative value resets the rx headroom to the
* default value.
* int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf);
* This function is used to set or query state related to XDP on the
* netdevice and manage BPF offload. See definition of
* enum bpf_netdev_command for details.
* int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp,
* u32 flags);
* This function is used to submit @n XDP packets for transmit on a
* netdevice. Returns number of frames successfully transmitted, frames
* that got dropped are freed/returned via xdp_return_frame().
* Returns negative number, means general error invoking ndo, meaning
* no frames were xmit'ed and core-caller will free all frames.
* struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev,
* struct xdp_buff *xdp);
* Get the xmit slave of master device based on the xdp_buff.
* int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags);
* This function is used to wake up the softirq, ksoftirqd or kthread
* responsible for sending and/or receiving packets on a specific
* queue id bound to an AF_XDP socket. The flags field specifies if
* only RX, only Tx, or both should be woken up using the flags
* XDP_WAKEUP_RX and XDP_WAKEUP_TX.
* int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
* int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
* Get the forwarding path to reach the real device from the HW destination address
* ktime_t (*ndo_get_tstamp)(struct net_device *dev,
* const struct skb_shared_hwtstamps *hwtstamps,
* bool cycles);
* Get hardware timestamp based on normal/adjustable time or free running
* cycle counter. This function is required if physical clock supports a
* free running cycle counter.
*
* int (*ndo_hwtstamp_get)(struct net_device *dev,
* struct kernel_hwtstamp_config *kernel_config);
* Get the currently configured hardware timestamping parameters for the
* NIC device.
*
* int (*ndo_hwtstamp_set)(struct net_device *dev,
* struct kernel_hwtstamp_config *kernel_config,
* struct netlink_ext_ack *extack);
* Change the hardware timestamping parameters for NIC device.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
void (*ndo_uninit)(struct net_device *dev);
int (*ndo_open)(struct net_device *dev);
int (*ndo_stop)(struct net_device *dev);
netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
struct net_device *dev);
netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
void (*ndo_change_rx_flags)(struct net_device *dev,
int flags);
void (*ndo_set_rx_mode)(struct net_device *dev);
int (*ndo_set_mac_address)(struct net_device *dev,
void *addr);
int (*ndo_validate_addr)(struct net_device *dev);
int (*ndo_do_ioctl)(struct net_device *dev,
struct ifreq *ifr, int cmd);
int (*ndo_eth_ioctl)(struct net_device *dev,
struct ifreq *ifr, int cmd);
int (*ndo_siocbond)(struct net_device *dev,
struct ifreq *ifr, int cmd);
int (*ndo_siocwandev)(struct net_device *dev,
struct if_settings *ifs);
int (*ndo_siocdevprivate)(struct net_device *dev,
struct ifreq *ifr,
void __user *data, int cmd);
int (*ndo_set_config)(struct net_device *dev,
struct ifmap *map);
int (*ndo_change_mtu)(struct net_device *dev,
int new_mtu);
int (*ndo_neigh_setup)(struct net_device *dev,
struct neigh_parms *);
void (*ndo_tx_timeout) (struct net_device *dev,
unsigned int txqueue);
void (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage);
bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id);
int (*ndo_get_offload_stats)(int attr_id,
const struct net_device *dev,
void *attr_data);
struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
int (*ndo_vlan_rx_add_vid)(struct net_device *dev,
__be16 proto, u16 vid);
int (*ndo_vlan_rx_kill_vid)(struct net_device *dev,
__be16 proto, u16 vid);
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_netpoll_setup)(struct net_device *dev);
void (*ndo_netpoll_cleanup)(struct net_device *dev);
#endif
int (*ndo_set_vf_mac)(struct net_device *dev,
int queue, u8 *mac);
int (*ndo_set_vf_vlan)(struct net_device *dev,
int queue, u16 vlan,
u8 qos, __be16 proto);
int (*ndo_set_vf_rate)(struct net_device *dev,
int vf, int min_tx_rate,
int max_tx_rate);
int (*ndo_set_vf_spoofchk)(struct net_device *dev,
int vf, bool setting);
int (*ndo_set_vf_trust)(struct net_device *dev,
int vf, bool setting);
int (*ndo_get_vf_config)(struct net_device *dev,
int vf,
struct ifla_vf_info *ivf);
int (*ndo_set_vf_link_state)(struct net_device *dev,
int vf, int link_state);
int (*ndo_get_vf_stats)(struct net_device *dev,
int vf,
struct ifla_vf_stats
*vf_stats);
int (*ndo_set_vf_port)(struct net_device *dev,
int vf,
struct nlattr *port[]);
int (*ndo_get_vf_port)(struct net_device *dev,
int vf, struct sk_buff *skb);
int (*ndo_get_vf_guid)(struct net_device *dev,
int vf,
struct ifla_vf_guid *node_guid,
struct ifla_vf_guid *port_guid);
int (*ndo_set_vf_guid)(struct net_device *dev,
int vf, u64 guid,
int guid_type);
int (*ndo_set_vf_rss_query_en)(
struct net_device *dev,
int vf, bool setting);
int (*ndo_setup_tc)(struct net_device *dev,
enum tc_setup_type type,
void *type_data);
#if IS_ENABLED(CONFIG_FCOE)
int (*ndo_fcoe_enable)(struct net_device *dev);
int (*ndo_fcoe_disable)(struct net_device *dev);
int (*ndo_fcoe_ddp_setup)(struct net_device *dev,
u16 xid,
struct scatterlist *sgl,
unsigned int sgc);
int (*ndo_fcoe_ddp_done)(struct net_device *dev,
u16 xid);
int (*ndo_fcoe_ddp_target)(struct net_device *dev,
u16 xid,
struct scatterlist *sgl,
unsigned int sgc);
int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
struct netdev_fcoe_hbainfo *hbainfo);
#endif
#if IS_ENABLED(CONFIG_LIBFCOE)
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
u64 *wwn, int type);
#endif
#ifdef CONFIG_RFS_ACCEL
int (*ndo_rx_flow_steer)(struct net_device *dev,
const struct sk_buff *skb,
u16 rxq_index,
u32 flow_id);
#endif
int (*ndo_add_slave)(struct net_device *dev,
struct net_device *slave_dev,
struct netlink_ext_ack *extack);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev,
struct sk_buff *skb,
bool all_slaves);
struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev,
struct sock *sk);
netdev_features_t (*ndo_fix_features)(struct net_device *dev,
netdev_features_t features);
int (*ndo_set_features)(struct net_device *dev,
netdev_features_t features);
int (*ndo_neigh_construct)(struct net_device *dev,
struct neighbour *n);
void (*ndo_neigh_destroy)(struct net_device *dev,
struct neighbour *n);
int (*ndo_fdb_add)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid,
u16 flags,
bool *notified,
struct netlink_ext_ack *extack);
int (*ndo_fdb_del)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid,
bool *notified,
struct netlink_ext_ack *extack);
int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh,
struct net_device *dev,
struct netlink_ext_ack *extack);
int (*ndo_fdb_dump)(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
int *idx);
int (*ndo_fdb_get)(struct sk_buff *skb,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid, u32 portid, u32 seq,
struct netlink_ext_ack *extack);
int (*ndo_mdb_add)(struct net_device *dev,
struct nlattr *tb[],
u16 nlmsg_flags,
struct netlink_ext_ack *extack);
int (*ndo_mdb_del)(struct net_device *dev,
struct nlattr *tb[],
struct netlink_ext_ack *extack);
int (*ndo_mdb_del_bulk)(struct net_device *dev,
struct nlattr *tb[],
struct netlink_ext_ack *extack);
int (*ndo_mdb_dump)(struct net_device *dev,
struct sk_buff *skb,
struct netlink_callback *cb);
int (*ndo_mdb_get)(struct net_device *dev,
struct nlattr *tb[], u32 portid,
u32 seq,
struct netlink_ext_ack *extack);
int (*ndo_bridge_setlink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags,
struct netlink_ext_ack *extack);
int (*ndo_bridge_getlink)(struct sk_buff *skb,
u32 pid, u32 seq,
struct net_device *dev,
u32 filter_mask,
int nlflags);
int (*ndo_bridge_dellink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags);
int (*ndo_change_carrier)(struct net_device *dev,
bool new_carrier);
int (*ndo_get_phys_port_id)(struct net_device *dev,
struct netdev_phys_item_id *ppid);
int (*ndo_get_port_parent_id)(struct net_device *dev,
struct netdev_phys_item_id *ppid);
int (*ndo_get_phys_port_name)(struct net_device *dev,
char *name, size_t len);
void* (*ndo_dfwd_add_station)(struct net_device *pdev,
struct net_device *dev);
void (*ndo_dfwd_del_station)(struct net_device *pdev,
void *priv);
int (*ndo_set_tx_maxrate)(struct net_device *dev,
int queue_index,
u32 maxrate);
int (*ndo_get_iflink)(const struct net_device *dev);
int (*ndo_fill_metadata_dst)(struct net_device *dev,
struct sk_buff *skb);
void (*ndo_set_rx_headroom)(struct net_device *dev,
int needed_headroom);
int (*ndo_bpf)(struct net_device *dev,
struct netdev_bpf *bpf);
int (*ndo_xdp_xmit)(struct net_device *dev, int n,
struct xdp_frame **xdp,
u32 flags);
struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev,
struct xdp_buff *xdp);
int (*ndo_xsk_wakeup)(struct net_device *dev,
u32 queue_id, u32 flags);
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm_kern *p,
int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
struct net_device_path *path);
ktime_t (*ndo_get_tstamp)(struct net_device *dev,
const struct skb_shared_hwtstamps *hwtstamps,
bool cycles);
int (*ndo_hwtstamp_get)(struct net_device *dev,
struct kernel_hwtstamp_config *kernel_config);
int (*ndo_hwtstamp_set)(struct net_device *dev,
struct kernel_hwtstamp_config *kernel_config,
struct netlink_ext_ack *extack);
#if IS_ENABLED(CONFIG_NET_SHAPER)
/**
* @net_shaper_ops: Device shaping offload operations
* see include/net/net_shapers.h
*/
const struct net_shaper_ops *net_shaper_ops;
#endif
};
/**
* enum netdev_priv_flags - &struct net_device priv_flags
*
* These are the &struct net_device, they are only set internally
* by drivers and used in the kernel. These flags are invisible to
* userspace; this means that the order of these flags can change
* during any kernel release.
*
* You should add bitfield booleans after either net_device::priv_flags
* (hotpath) or ::threaded (slowpath) instead of extending these flags.
*
* @IFF_802_1Q_VLAN: 802.1Q VLAN device
* @IFF_EBRIDGE: Ethernet bridging device
* @IFF_BONDING: bonding master or slave
* @IFF_ISATAP: ISATAP interface (RFC4214)
* @IFF_WAN_HDLC: WAN HDLC device
* @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
* release skb->dst
* @IFF_DONT_BRIDGE: disallow bridging this ether dev
* @IFF_DISABLE_NETPOLL: disable netpoll at run-time
* @IFF_MACVLAN_PORT: device used as macvlan port
* @IFF_BRIDGE_PORT: device used as bridge port
* @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
* @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
* @IFF_UNICAST_FLT: Supports unicast filtering
* @IFF_TEAM_PORT: device used as team port
* @IFF_SUPP_NOFCS: device supports sending custom FCS
* @IFF_LIVE_ADDR_CHANGE: device supports hardware address
* change when it's running
* @IFF_MACVLAN: Macvlan device
* @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account
* underlying stacked devices
* @IFF_L3MDEV_MASTER: device is an L3 master device
* @IFF_NO_QUEUE: device can run without qdisc attached
* @IFF_OPENVSWITCH: device is a Open vSwitch master
* @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
* @IFF_TEAM: device is a team device
* @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
* @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
* entity (i.e. the master device for bridged veth)
* @IFF_MACSEC: device is a MACsec device
* @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
* @IFF_FAILOVER: device is a failover master device
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
* @IFF_NO_ADDRCONF: prevent ipv6 addrconf
* @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
* skb_headlen(skb) == 0 (data starts from frag0)
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_EBRIDGE = 1<<1,
IFF_BONDING = 1<<2,
IFF_ISATAP = 1<<3,
IFF_WAN_HDLC = 1<<4,
IFF_XMIT_DST_RELEASE = 1<<5,
IFF_DONT_BRIDGE = 1<<6,
IFF_DISABLE_NETPOLL = 1<<7,
IFF_MACVLAN_PORT = 1<<8,
IFF_BRIDGE_PORT = 1<<9,
IFF_OVS_DATAPATH = 1<<10,
IFF_TX_SKB_SHARING = 1<<11,
IFF_UNICAST_FLT = 1<<12,
IFF_TEAM_PORT = 1<<13,
IFF_SUPP_NOFCS = 1<<14,
IFF_LIVE_ADDR_CHANGE = 1<<15,
IFF_MACVLAN = 1<<16,
IFF_XMIT_DST_RELEASE_PERM = 1<<17,
IFF_L3MDEV_MASTER = 1<<18,
IFF_NO_QUEUE = 1<<19,
IFF_OPENVSWITCH = 1<<20,
IFF_L3MDEV_SLAVE = 1<<21,
IFF_TEAM = 1<<22,
IFF_RXFH_CONFIGURED = 1<<23,
IFF_PHONY_HEADROOM = 1<<24,
IFF_MACSEC = 1<<25,
IFF_NO_RX_HANDLER = 1<<26,
IFF_FAILOVER = 1<<27,
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
IFF_NO_ADDRCONF = BIT_ULL(30),
IFF_TX_SKB_NO_LINEAR = BIT_ULL(31),
};
/* Specifies the type of the struct net_device::ml_priv pointer */
enum netdev_ml_priv_type {
ML_PRIV_NONE,
ML_PRIV_CAN,
};
enum netdev_stat_type {
NETDEV_PCPU_STAT_NONE,
NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */
NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */
NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */
};
enum netdev_reg_state {
NETREG_UNINITIALIZED = 0,
NETREG_REGISTERED, /* completed register_netdevice */
NETREG_UNREGISTERING, /* called unregister_netdevice */
NETREG_UNREGISTERED, /* completed unregister todo */
NETREG_RELEASED, /* called free_netdev */
NETREG_DUMMY, /* dummy device for NAPI poll */
};
/**
* struct net_device - The DEVICE structure.
*
* Actually, this whole structure is a big mistake. It mixes I/O
* data with strictly "high-level" data, and it has to know about
* almost every data structure used in the INET module.
*
* @priv_flags: flags invisible to userspace defined as bits, see
* enum netdev_priv_flags for the definitions
* @lltx: device supports lockless Tx. Deprecated for real HW
* drivers. Mainly used by logical interfaces, such as
* bonding and tunnels
*
* @name: This is the first field of the "visible" part of this structure
* (i.e. as seen by users in the "Space.c" file). It is the name
* of the interface.
*
* @name_node: Name hashlist node
* @ifalias: SNMP alias
* @mem_end: Shared memory end
* @mem_start: Shared memory start
* @base_addr: Device I/O address
* @irq: Device IRQ number
*
* @state: Generic network queuing layer state, see netdev_state_t
* @dev_list: The global list of network devices
* @napi_list: List entry used for polling NAPI devices
* @unreg_list: List entry when we are unregistering the
* device; see the function unregister_netdev
* @close_list: List entry used when we are closing the device
* @ptype_all: Device-specific packet handlers for all protocols
* @ptype_specific: Device-specific, protocol-specific packet handlers
*
* @adj_list: Directly linked devices, like slaves for bonding
* @features: Currently active device features
* @hw_features: User-changeable features
*
* @wanted_features: User-requested features
* @vlan_features: Mask of features inheritable by VLAN devices
*
* @hw_enc_features: Mask of features inherited by encapsulating devices
* This field indicates what encapsulation
* offloads the hardware is capable of doing,
* and drivers will need to set them appropriately.
*
* @mpls_features: Mask of features inheritable by MPLS
* @gso_partial_features: value(s) from NETIF_F_GSO\*
*
* @ifindex: interface index
* @group: The group the device belongs to
*
* @stats: Statistics struct, which was left as a legacy, use
* rtnl_link_stats64 instead
*
* @core_stats: core networking counters,
* do not use this in drivers
* @carrier_up_count: Number of times the carrier has been up
* @carrier_down_count: Number of times the carrier has been down
*
* @wireless_handlers: List of functions to handle Wireless Extensions,
* instead of ioctl,
* see <net/iw_handler.h> for details.
*
* @netdev_ops: Includes several pointers to callbacks,
* if one wants to override the ndo_*() functions
* @xdp_metadata_ops: Includes pointers to XDP metadata callbacks.
* @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks.
* @ethtool_ops: Management operations
* @l3mdev_ops: Layer 3 master device operations
* @ndisc_ops: Includes callbacks for different IPv6 neighbour
* discovery handling. Necessary for e.g. 6LoWPAN.
* @xfrmdev_ops: Transformation offload operations
* @tlsdev_ops: Transport Layer Security offload operations
* @header_ops: Includes callbacks for creating,parsing,caching,etc
* of Layer 2 headers.
*
* @flags: Interface flags (a la BSD)
* @xdp_features: XDP capability supported by the device
* @gflags: Global flags ( kept as legacy )
* @priv_len: Size of the ->priv flexible array
* @priv: Flexible array containing private data
* @operstate: RFC2863 operstate
* @link_mode: Mapping policy to operstate
* @if_port: Selectable AUI, TP, ...
* @dma: DMA channel
* @mtu: Interface MTU value
* @min_mtu: Interface Minimum MTU value
* @max_mtu: Interface Maximum MTU value
* @type: Interface hardware type
* @hard_header_len: Maximum hardware header length.
* @min_header_len: Minimum hardware header length
*
* @needed_headroom: Extra headroom the hardware may need, but not in all
* cases can this be guaranteed
* @needed_tailroom: Extra tailroom the hardware may need, but not in all
* cases can this be guaranteed. Some cases also use
* LL_MAX_HEADER instead to allocate the skb
*
* interface address info:
*
* @perm_addr: Permanent hw address
* @addr_assign_type: Hw address assignment type
* @addr_len: Hardware address length
* @upper_level: Maximum depth level of upper devices.
* @lower_level: Maximum depth level of lower devices.
* @neigh_priv_len: Used in neigh_alloc()
* @dev_id: Used to differentiate devices that share
* the same link layer address
* @dev_port: Used to differentiate devices that share
* the same function
* @addr_list_lock: XXX: need comments on this one
* @name_assign_type: network interface name assignment type
* @uc_promisc: Counter that indicates promiscuous mode
* has been enabled due to the need to listen to
* additional unicast addresses in a device that
* does not implement ndo_set_rx_mode()
* @uc: unicast mac addresses
* @mc: multicast mac addresses
* @dev_addrs: list of device hw addresses
* @queues_kset: Group of all Kobjects in the Tx and RX queues
* @promiscuity: Number of times the NIC is told to work in
* promiscuous mode; if it becomes 0 the NIC will
* exit promiscuous mode
* @allmulti: Counter, enables or disables allmulticast mode
*
* @vlan_info: VLAN info
* @dsa_ptr: dsa specific data
* @tipc_ptr: TIPC specific data
* @atalk_ptr: AppleTalk link
* @ip_ptr: IPv4 specific data
* @ip6_ptr: IPv6 specific data
* @ax25_ptr: AX.25 specific data
* @ieee80211_ptr: IEEE 802.11 specific data, assign before registering
* @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network
* device struct
* @mpls_ptr: mpls_dev struct pointer
* @mctp_ptr: MCTP specific data
*
* @dev_addr: Hw address (before bcast,
* because most packets are unicast)
*
* @_rx: Array of RX queues
* @num_rx_queues: Number of RX queues
* allocated at register_netdev() time
* @real_num_rx_queues: Number of RX queues currently active in device
* @xdp_prog: XDP sockets filter program pointer
*
* @rx_handler: handler for received packets
* @rx_handler_data: XXX: need comments on this one
* @tcx_ingress: BPF & clsact qdisc specific data for ingress processing
* @ingress_queue: XXX: need comments on this one
* @nf_hooks_ingress: netfilter hooks executed for ingress packets
* @broadcast: hw bcast address
*
* @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts,
* indexed by RX queue number. Assigned by driver.
* This must only be set if the ndo_rx_flow_steer
* operation is defined
* @index_hlist: Device index hash chain
*
* @_tx: Array of TX queues
* @num_tx_queues: Number of TX queues allocated at alloc_netdev_mq() time
* @real_num_tx_queues: Number of TX queues currently active in device
* @qdisc: Root qdisc from userspace point of view
* @tx_queue_len: Max frames per queue allowed
* @tx_global_lock: XXX: need comments on this one
* @xdp_bulkq: XDP device bulk queue
* @xps_maps: all CPUs/RXQs maps for XPS device
*
* @xps_maps: XXX: need comments on this one
* @tcx_egress: BPF & clsact qdisc specific data for egress processing
* @nf_hooks_egress: netfilter hooks executed for egress packets
* @qdisc_hash: qdisc hash table
* @watchdog_timeo: Represents the timeout that is used by
* the watchdog (see dev_watchdog())
* @watchdog_timer: List of timers
*
* @proto_down_reason: reason a netdev interface is held down
* @pcpu_refcnt: Number of references to this device
* @dev_refcnt: Number of references to this device
* @refcnt_tracker: Tracker directory for tracked references to this device
* @todo_list: Delayed register/unregister
* @link_watch_list: XXX: need comments on this one
*
* @reg_state: Register/unregister state machine
* @dismantle: Device is going to be freed
* @rtnl_link_state: This enum represents the phases of creating
* a new link
*
* @needs_free_netdev: Should unregister perform free_netdev?
* @priv_destructor: Called from unregister
* @npinfo: XXX: need comments on this one
* @nd_net: Network namespace this network device is inside
*
* @ml_priv: Mid-layer private
* @ml_priv_type: Mid-layer private type
*
* @pcpu_stat_type: Type of device statistics which the core should
* allocate/free: none, lstats, tstats, dstats. none
* means the driver is handling statistics allocation/
* freeing internally.
* @lstats: Loopback statistics: packets, bytes
* @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes
* @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes
*
* @garp_port: GARP
* @mrp_port: MRP
*
* @dm_private: Drop monitor private
*
* @dev: Class/net/name entry
* @sysfs_groups: Space for optional device, statistics and wireless
* sysfs groups
*
* @sysfs_rx_queue_group: Space for optional per-rx queue attributes
* @rtnl_link_ops: Rtnl_link_ops
* @stat_ops: Optional ops for queue-aware statistics
* @queue_mgmt_ops: Optional ops for queue management
*
* @gso_max_size: Maximum size of generic segmentation offload
* @tso_max_size: Device (as in HW) limit on the max TSO request size
* @gso_max_segs: Maximum number of segments that can be passed to the
* NIC for GSO
* @tso_max_segs: Device (as in HW) limit on the max TSO segment count
* @gso_ipv4_max_size: Maximum size of generic segmentation offload,
* for IPv4.
*
* @dcbnl_ops: Data Center Bridging netlink ops
* @num_tc: Number of traffic classes in the net device
* @tc_to_txq: XXX: need comments on this one
* @prio_tc_map: XXX: need comments on this one
*
* @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp
*
* @priomap: XXX: need comments on this one
* @link_topo: Physical link topology tracking attached PHYs
* @phydev: Physical device may attach itself
* for hardware timestamping
* @sfp_bus: attached &struct sfp_bus structure.
*
* @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
*
* @proto_down: protocol port state information can be sent to the
* switch driver and used to set the phys state of the
* switch port.
*
* @threaded: napi threaded mode is enabled
*
* @irq_affinity_auto: driver wants the core to store and re-assign the IRQ
* affinity. Set by netif_enable_irq_affinity(), then
* the driver must create a persistent napi by
* netif_napi_add_config() and finally bind the napi to
* IRQ (via netif_napi_set_irq()).
*
* @rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap.
* Set by calling netif_enable_cpu_rmap().
*
* @see_all_hwtstamp_requests: device wants to see calls to
* ndo_hwtstamp_set() for all timestamp requests
* regardless of source, even if those aren't
* HWTSTAMP_SOURCE_NETDEV
* @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
* @netns_immutable: interface can't change network namespaces
* @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes
*
* @net_notifier_list: List of per-net netdev notifier block
* that follow this device when it is moved
* to another network namespace.
*
* @macsec_ops: MACsec offloading ops
*
* @udp_tunnel_nic_info: static structure describing the UDP tunnel
* offload capabilities of the device
* @udp_tunnel_nic: UDP tunnel offload state
* @ethtool: ethtool related state
* @xdp_state: stores info on attached XDP BPF programs
*
* @nested_level: Used as a parameter of spin_lock_nested() of
* dev->addr_list_lock.
* @unlink_list: As netif_addr_lock() can be called recursively,
* keep a list of interfaces to be deleted.
* @gro_max_size: Maximum size of aggregated packet in generic
* receive offload (GRO)
* @gro_ipv4_max_size: Maximum size of aggregated packet in generic
* receive offload (GRO), for IPv4.
* @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP
* zero copy driver
*
* @dev_addr_shadow: Copy of @dev_addr to catch direct writes.
* @linkwatch_dev_tracker: refcount tracker used by linkwatch.
* @watchdog_dev_tracker: refcount tracker used by watchdog.
* @dev_registered_tracker: tracker for reference held while
* registered
* @offload_xstats_l3: L3 HW stats for this netdevice.
*
* @devlink_port: Pointer to related devlink port structure.
* Assigned by a driver before netdev registration using
* SET_NETDEV_DEVLINK_PORT macro. This pointer is static
* during the time netdevice is registered.
*
* @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
* where the clock is recovered.
*
* @max_pacing_offload_horizon: max EDT offload horizon in nsec.
* @napi_config: An array of napi_config structures containing per-NAPI
* settings.
* @gro_flush_timeout: timeout for GRO layer in NAPI
* @napi_defer_hard_irqs: If not zero, provides a counter that would
* allow to avoid NIC hard IRQ, on busy queues.
*
* @neighbours: List heads pointing to this device's neighbours'
* dev_list, one per address-family.
* @hwprov: Tracks which PTP performs hardware packet time stamping.
*
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
struct net_device {
/* Cacheline organization can be found documented in
* Documentation/networking/net_cachelines/net_device.rst.
* Please update the document when adding new fields.
*/
/* TX read-mostly hotpath */
__cacheline_group_begin(net_device_read_tx);
struct_group(priv_flags_fast,
unsigned long priv_flags:32;
unsigned long lltx:1;
);
const struct net_device_ops *netdev_ops;
const struct header_ops *header_ops;
struct netdev_queue *_tx;
netdev_features_t gso_partial_features;
unsigned int real_num_tx_queues;
unsigned int gso_max_size;
unsigned int gso_ipv4_max_size;
u16 gso_max_segs;
s16 num_tc;
/* Note : dev->mtu is often read without holding a lock.
* Writers usually hold RTNL.
* It is recommended to use READ_ONCE() to annotate the reads,
* and to use WRITE_ONCE() to annotate the writes.
*/
unsigned int mtu;
unsigned short needed_headroom;
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
#ifdef CONFIG_XPS
struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
#endif
#ifdef CONFIG_NETFILTER_EGRESS
struct nf_hook_entries __rcu *nf_hooks_egress;
#endif
#ifdef CONFIG_NET_XGRESS
struct bpf_mprog_entry __rcu *tcx_egress;
#endif
__cacheline_group_end(net_device_read_tx);
/* TXRX read-mostly hotpath */
__cacheline_group_begin(net_device_read_txrx);
union {
struct pcpu_lstats __percpu *lstats;
struct pcpu_sw_netstats __percpu *tstats;
struct pcpu_dstats __percpu *dstats;
};
unsigned long state;
unsigned int flags;
unsigned short hard_header_len;
netdev_features_t features;
struct inet6_dev __rcu *ip6_ptr;
__cacheline_group_end(net_device_read_txrx);
/* RX read-mostly hotpath */
__cacheline_group_begin(net_device_read_rx);
struct bpf_prog __rcu *xdp_prog;
struct list_head ptype_specific;
int ifindex;
unsigned int real_num_rx_queues;
struct netdev_rx_queue *_rx;
unsigned int gro_max_size;
unsigned int gro_ipv4_max_size;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
possible_net_t nd_net;
#ifdef CONFIG_NETPOLL
struct netpoll_info __rcu *npinfo;
#endif
#ifdef CONFIG_NET_XGRESS
struct bpf_mprog_entry __rcu *tcx_ingress;
#endif
__cacheline_group_end(net_device_read_rx);
char name[IFNAMSIZ];
struct netdev_name_node *name_node;
struct dev_ifalias __rcu *ifalias;
/*
* I/O specific fields
* FIXME: Merge these and struct ifmap into one
*/
unsigned long mem_end;
unsigned long mem_start;
unsigned long base_addr;
/*
* Some hardware also needs these fields (state,dev_list,
* napi_list,unreg_list,close_list) but they are not
* part of the usual set specified in Space.c.
*/
struct list_head dev_list;
struct list_head napi_list;
struct list_head unreg_list;
struct list_head close_list;
struct list_head ptype_all;
struct {
struct list_head upper;
struct list_head lower;
} adj_list;
/* Read-mostly cache-line for fast-path access */
xdp_features_t xdp_features;
const struct xdp_metadata_ops *xdp_metadata_ops;
const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
unsigned short gflags;
unsigned short needed_tailroom;
netdev_features_t hw_features;
netdev_features_t wanted_features;
netdev_features_t vlan_features;
netdev_features_t hw_enc_features;
netdev_features_t mpls_features;
unsigned int min_mtu;
unsigned int max_mtu;
unsigned short type;
unsigned char min_header_len;
unsigned char name_assign_type;
int group;
struct net_device_stats stats; /* not used by modern drivers */
struct net_device_core_stats __percpu *core_stats;
/* Stats to monitor link on/off, flapping */
atomic_t carrier_up_count;
atomic_t carrier_down_count;
#ifdef CONFIG_WIRELESS_EXT
const struct iw_handler_def *wireless_handlers;
#endif
const struct ethtool_ops *ethtool_ops;
#ifdef CONFIG_NET_L3_MASTER_DEV
const struct l3mdev_ops *l3mdev_ops;
#endif
#if IS_ENABLED(CONFIG_IPV6)
const struct ndisc_ops *ndisc_ops;
#endif
#ifdef CONFIG_XFRM_OFFLOAD
const struct xfrmdev_ops *xfrmdev_ops;
#endif
#if IS_ENABLED(CONFIG_TLS_DEVICE)
const struct tlsdev_ops *tlsdev_ops;
#endif
unsigned int operstate;
unsigned char link_mode;
unsigned char if_port;
unsigned char dma;
/* Interface address info. */
unsigned char perm_addr[MAX_ADDR_LEN];
unsigned char addr_assign_type;
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
int irq;
u32 priv_len;
spinlock_t addr_list_lock;
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
#ifdef CONFIG_SYSFS
struct kset *queues_kset;
#endif
#ifdef CONFIG_LOCKDEP
struct list_head unlink_list;
#endif
unsigned int promiscuity;
unsigned int allmulti;
bool uc_promisc;
#ifdef CONFIG_LOCKDEP
unsigned char nested_level;
#endif
/* Protocol-specific pointers */
struct in_device __rcu *ip_ptr;
/** @fib_nh_head: nexthops associated with this netdev */
struct hlist_head fib_nh_head;
#if IS_ENABLED(CONFIG_VLAN_8021Q)
struct vlan_info __rcu *vlan_info;
#endif
#if IS_ENABLED(CONFIG_NET_DSA)
struct dsa_port *dsa_ptr;
#endif
#if IS_ENABLED(CONFIG_TIPC)
struct tipc_bearer __rcu *tipc_ptr;
#endif
#if IS_ENABLED(CONFIG_ATALK)
void *atalk_ptr;
#endif
#if IS_ENABLED(CONFIG_AX25)
struct ax25_dev __rcu *ax25_ptr;
#endif
#if IS_ENABLED(CONFIG_CFG80211)
struct wireless_dev *ieee80211_ptr;
#endif
#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN)
struct wpan_dev *ieee802154_ptr;
#endif
#if IS_ENABLED(CONFIG_MPLS_ROUTING)
struct mpls_dev __rcu *mpls_ptr;
#endif
#if IS_ENABLED(CONFIG_MCTP)
struct mctp_dev __rcu *mctp_ptr;
#endif
/*
* Cache lines mostly used on receive path (including eth_type_trans())
*/
/* Interface address info used in eth_type_trans() */
const unsigned char *dev_addr;
unsigned int num_rx_queues;
#define GRO_LEGACY_MAX_SIZE 65536u
/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
* and shinfo->gso_segs is a 16bit field.
*/
#define GRO_MAX_SIZE (8 * 65535u)
unsigned int xdp_zc_max_segs;
struct netdev_queue __rcu *ingress_queue;
#ifdef CONFIG_NETFILTER_INGRESS
struct nf_hook_entries __rcu *nf_hooks_ingress;
#endif
unsigned char broadcast[MAX_ADDR_LEN];
#ifdef CONFIG_RFS_ACCEL
struct cpu_rmap *rx_cpu_rmap;
#endif
struct hlist_node index_hlist;
/*
* Cache lines mostly used on transmit path
*/
unsigned int num_tx_queues;
struct Qdisc __rcu *qdisc;
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_NET_SCHED
DECLARE_HASHTABLE (qdisc_hash, 4);
#endif
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
int watchdog_timeo;
u32 proto_down_reason;
struct list_head todo_list;
#ifdef CONFIG_PCPU_DEV_REFCNT
int __percpu *pcpu_refcnt;
#else
refcount_t dev_refcnt;
#endif
struct ref_tracker_dir refcnt_tracker;
struct list_head link_watch_list;
u8 reg_state;
bool dismantle;
enum {
RTNL_LINK_INITIALIZED,
RTNL_LINK_INITIALIZING,
} rtnl_link_state:16;
bool needs_free_netdev;
void (*priv_destructor)(struct net_device *dev);
/* mid-layer private */
void *ml_priv;
enum netdev_ml_priv_type ml_priv_type;
enum netdev_stat_type pcpu_stat_type:8;
#if IS_ENABLED(CONFIG_GARP)
struct garp_port __rcu *garp_port;
#endif
#if IS_ENABLED(CONFIG_MRP)
struct mrp_port __rcu *mrp_port;
#endif
#if IS_ENABLED(CONFIG_NET_DROP_MONITOR)
struct dm_hw_stat_delta __rcu *dm_private;
#endif
struct device dev;
const struct attribute_group *sysfs_groups[4];
const struct attribute_group *sysfs_rx_queue_group;
const struct rtnl_link_ops *rtnl_link_ops;
const struct netdev_stat_ops *stat_ops;
const struct netdev_queue_mgmt_ops *queue_mgmt_ops;
/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SEGS 65535u
#define GSO_LEGACY_MAX_SIZE 65536u
/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
* and shinfo->gso_segs is a 16bit field.
*/
#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS)
#define TSO_LEGACY_MAX_SIZE 65536
#define TSO_MAX_SIZE UINT_MAX
unsigned int tso_max_size;
#define TSO_MAX_SEGS U16_MAX
u16 tso_max_segs;
#ifdef CONFIG_DCB
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif
u8 prio_tc_map[TC_BITMASK + 1];
#if IS_ENABLED(CONFIG_FCOE)
unsigned int fcoe_ddp_xid;
#endif
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
struct netprio_map __rcu *priomap;
#endif
struct phy_link_topology *link_topo;
struct phy_device *phydev;
struct sfp_bus *sfp_bus;
struct lock_class_key *qdisc_tx_busylock;
bool proto_down;
bool threaded;
bool irq_affinity_auto;
bool rx_cpu_rmap_auto;
/* priv_flags_slow, ungrouped to save space */
unsigned long see_all_hwtstamp_requests:1;
unsigned long change_proto_down:1;
unsigned long netns_immutable:1;
unsigned long fcoe_mtu:1;
struct list_head net_notifier_list;
#if IS_ENABLED(CONFIG_MACSEC)
/* MACsec management functions */
const struct macsec_ops *macsec_ops;
#endif
const struct udp_tunnel_nic_info *udp_tunnel_nic_info;
struct udp_tunnel_nic *udp_tunnel_nic;
/** @cfg: net_device queue-related configuration */
struct netdev_config *cfg;
/**
* @cfg_pending: same as @cfg but when device is being actively
* reconfigured includes any changes to the configuration
* requested by the user, but which may or may not be rejected.
*/
struct netdev_config *cfg_pending;
struct ethtool_netdev_state *ethtool;
/* protected by rtnl_lock */
struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE];
u8 dev_addr_shadow[MAX_ADDR_LEN];
netdevice_tracker linkwatch_dev_tracker;
netdevice_tracker watchdog_dev_tracker;
netdevice_tracker dev_registered_tracker;
struct rtnl_hw_stats64 *offload_xstats_l3;
struct devlink_port *devlink_port;
#if IS_ENABLED(CONFIG_DPLL)
struct dpll_pin __rcu *dpll_pin;
#endif
#if IS_ENABLED(CONFIG_PAGE_POOL)
/** @page_pools: page pools created for this netdevice */
struct hlist_head page_pools;
#endif
/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
struct dim_irq_moder *irq_moder;
u64 max_pacing_offload_horizon;
struct napi_config *napi_config;
unsigned long gro_flush_timeout;
u32 napi_defer_hard_irqs;
/**
* @up: copy of @state's IFF_UP, but safe to read with just @lock.
* May report false negatives while the device is being opened
* or closed (@lock does not protect .ndo_open, or .ndo_close).
*/
bool up;
/**
* @request_ops_lock: request the core to run all @netdev_ops and
* @ethtool_ops under the @lock.
*/
bool request_ops_lock;
/**
* @lock: netdev-scope lock, protects a small selection of fields.
* Should always be taken using netdev_lock() / netdev_unlock() helpers.
* Drivers are free to use it for other protection.
*
* For the drivers that implement shaper or queue API, the scope
* of this lock is expanded to cover most ndo/queue/ethtool/sysfs
* operations. Drivers may opt-in to this behavior by setting
* @request_ops_lock.
*
* @lock protection mixes with rtnl_lock in multiple ways, fields are
* either:
*
* - simply protected by the instance @lock;
*
* - double protected - writers hold both locks, readers hold either;
*
* - ops protected - protected by the lock held around the NDOs
* and other callbacks, that is the instance lock on devices for
* which netdev_need_ops_lock() returns true, otherwise by rtnl_lock;
*
* - double ops protected - always protected by rtnl_lock but for
* devices for which netdev_need_ops_lock() returns true - also
* the instance lock.
*
* Simply protects:
* @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list,
* @net_shaper_hierarchy, @reg_state, @threaded
*
* Double protects:
* @up
*
* Double ops protects:
* @real_num_rx_queues, @real_num_tx_queues
*
* Also protects some fields in:
* struct napi_struct, struct netdev_queue, struct netdev_rx_queue
*
* Ordering: take after rtnl_lock.
*/
struct mutex lock;
#if IS_ENABLED(CONFIG_NET_SHAPER)
/**
* @net_shaper_hierarchy: data tracking the current shaper status
* see include/net/net_shapers.h
*/
struct net_shaper_hierarchy *net_shaper_hierarchy;
#endif
struct hlist_head neighbours[NEIGH_NR_TABLES];
struct hwtstamp_provider __rcu *hwprov;
u8 priv[] ____cacheline_aligned
__counted_by(priv_len);
} ____cacheline_aligned;
#define to_net_dev(d) container_of(d, struct net_device, dev)
/*
* Driver should use this to assign devlink port instance to a netdevice
* before it registers the netdevice. Therefore devlink_port is static
* during the netdev lifetime after it is registered.
*/
#define SET_NETDEV_DEVLINK_PORT(dev, port) \
({ \
WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \
((dev)->devlink_port = (port)); \
})
static inline bool netif_elide_gro(const struct net_device *dev)
{
if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog)
return true;
return false;
}
#define NETDEV_ALIGN 32
static inline
int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
{
return dev->prio_tc_map[prio & TC_BITMASK];
}
static inline
int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
{
if (tc >= dev->num_tc)
return -EINVAL;
dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK;
return 0;
}
int netdev_txq_to_tc(struct net_device *dev, unsigned int txq);
void netdev_reset_tc(struct net_device *dev);
int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset);
int netdev_set_num_tc(struct net_device *dev, u8 num_tc);
static inline
int netdev_get_num_tc(struct net_device *dev)
{
return dev->num_tc;
}
static inline void net_prefetch(void *p)
{
prefetch(p);
#if L1_CACHE_BYTES < 128
prefetch((u8 *)p + L1_CACHE_BYTES);
#endif
}
static inline void net_prefetchw(void *p)
{
prefetchw(p);
#if L1_CACHE_BYTES < 128
prefetchw((u8 *)p + L1_CACHE_BYTES);
#endif
}
void netdev_unbind_sb_channel(struct net_device *dev,
struct net_device *sb_dev);
int netdev_bind_sb_channel_queue(struct net_device *dev,
struct net_device *sb_dev,
u8 tc, u16 count, u16 offset);
int netdev_set_sb_channel(struct net_device *dev, u16 channel);
static inline int netdev_get_sb_channel(struct net_device *dev)
{
return max_t(int, -dev->num_tc, 0);
}
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
unsigned int index)
{
DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues);
return &dev->_tx[index];
}
static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev,
const struct sk_buff *skb)
{
return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
}
static inline void netdev_for_each_tx_queue(struct net_device *dev,
void (*f)(struct net_device *,
struct netdev_queue *,
void *),
void *arg)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++)
f(dev, &dev->_tx[i], arg);
}
u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
/* returns the headroom that the master device needs to take in account
* when forwarding to this dev
*/
static inline unsigned netdev_get_fwd_headroom(struct net_device *dev)
{
return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom;
}
static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr)
{
if (dev->netdev_ops->ndo_set_rx_headroom)
dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr);
}
/* set the device rx headroom to the dev's default */
static inline void netdev_reset_rx_headroom(struct net_device *dev)
{
netdev_set_rx_headroom(dev, -1);
}
static inline void *netdev_get_ml_priv(struct net_device *dev,
enum netdev_ml_priv_type type)
{
if (dev->ml_priv_type != type)
return NULL;
return dev->ml_priv;
}
static inline void netdev_set_ml_priv(struct net_device *dev,
void *ml_priv,
enum netdev_ml_priv_type type)
{
WARN(dev->ml_priv_type && dev->ml_priv_type != type,
"Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n",
dev->ml_priv_type, type);
WARN(!dev->ml_priv_type && dev->ml_priv,
"Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n");
dev->ml_priv = ml_priv;
dev->ml_priv_type = type;
}
/*
* Net namespace inlines
*/
static inline
struct net *dev_net(const struct net_device *dev)
{
return read_pnet(&dev->nd_net);
}
static inline
struct net *dev_net_rcu(const struct net_device *dev)
{
return read_pnet_rcu(&dev->nd_net);
}
static inline
void dev_net_set(struct net_device *dev, struct net *net)
{
write_pnet(&dev->nd_net, net);
}
/**
* netdev_priv - access network device private data
* @dev: network device
*
* Get network device private data
*/
static inline void *netdev_priv(const struct net_device *dev)
{
return (void *)dev->priv;
}
/* Set the sysfs physical device reference for the network logical device
* if set prior to registration will cause a symlink during initialization.
*/
#define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev))
/* Set the sysfs device type for the network logical device to allow
* fine-grained identification of different network device types. For
* example Ethernet, Wireless LAN, Bluetooth, WiMAX etc.
*/
#define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype))
void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
enum netdev_queue_type type,
struct napi_struct *napi);
static inline void netdev_lock(struct net_device *dev)
{
mutex_lock(&dev->lock);
}
static inline void netdev_unlock(struct net_device *dev)
{
mutex_unlock(&dev->lock);
}
/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */
void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
{
netdev_lock(napi->dev);
netif_napi_set_irq_locked(napi, irq);
netdev_unlock(napi->dev);
}
/* Default NAPI poll() weight
* Device drivers are strongly advised to not use bigger value
*/
#define NAPI_POLL_WEIGHT 64
void netif_napi_add_weight_locked(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int),
int weight);
static inline void
netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
netdev_lock(dev);
netif_napi_add_weight_locked(dev, napi, poll, weight);
netdev_unlock(dev);
}
/**
* netif_napi_add() - initialize a NAPI context
* @dev: network device
* @napi: NAPI context
* @poll: polling function
*
* netif_napi_add() must be used to initialize a NAPI context prior to calling
* *any* of the other NAPI-related functions.
*/
static inline void
netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int))
{
netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
}
static inline void
netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int))
{
netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT);
}
static inline void
netif_napi_add_tx_weight(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int),
int weight)
{
set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
netif_napi_add_weight(dev, napi, poll, weight);
}
static inline void
netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int index)
{
napi->index = index;
napi->config = &dev->napi_config[index];
netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT);
}
/**
* netif_napi_add_config - initialize a NAPI context with persistent config
* @dev: network device
* @napi: NAPI context
* @poll: polling function
* @index: the NAPI index
*/
static inline void
netif_napi_add_config(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int index)
{
netdev_lock(dev);
netif_napi_add_config_locked(dev, napi, poll, index);
netdev_unlock(dev);
}
/**
* netif_napi_add_tx() - initialize a NAPI context to be used for Tx only
* @dev: network device
* @napi: NAPI context
* @poll: polling function
*
* This variant of netif_napi_add() should be used from drivers using NAPI
* to exclusively poll a TX queue.
* This will avoid we add it into napi_hash[], thus polluting this hash table.
*/
static inline void netif_napi_add_tx(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int))
{
netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
}
void __netif_napi_del_locked(struct napi_struct *napi);
/**
* __netif_napi_del - remove a NAPI context
* @napi: NAPI context
*
* Warning: caller must observe RCU grace period before freeing memory
* containing @napi. Drivers might want to call this helper to combine
* all the needed RCU grace periods into a single one.
*/
static inline void __netif_napi_del(struct napi_struct *napi)
{
netdev_lock(napi->dev);
__netif_napi_del_locked(napi);
netdev_unlock(napi->dev);
}
static inline void netif_napi_del_locked(struct napi_struct *napi)
{
__netif_napi_del_locked(napi);
synchronize_net();
}
/**
* netif_napi_del - remove a NAPI context
* @napi: NAPI context
*
* netif_napi_del() removes a NAPI context from the network device NAPI list
*/
static inline void netif_napi_del(struct napi_struct *napi)
{
__netif_napi_del(napi);
synchronize_net();
}
int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
void netif_set_affinity_auto(struct net_device *dev);
struct packet_type {
__be16 type; /* This is really htons(ether_type). */
bool ignore_outgoing;
struct net_device *dev; /* NULL is wildcarded here */
netdevice_tracker dev_tracker;
int (*func) (struct sk_buff *,
struct net_device *,
struct packet_type *,
struct net_device *);
void (*list_func) (struct list_head *,
struct packet_type *,
struct net_device *);
bool (*id_match)(struct packet_type *ptype,
struct sock *sk);
struct net *af_packet_net;
void *af_packet_priv;
struct list_head list;
};
struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
struct sk_buff *(*gro_receive)(struct list_head *head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
};
struct packet_offload {
__be16 type; /* This is really htons(ether_type). */
u16 priority;
struct offload_callbacks callbacks;
struct list_head list;
};
/* often modified stats are per-CPU, other are shared (netdev->stats) */
struct pcpu_sw_netstats {
u64_stats_t rx_packets;
u64_stats_t rx_bytes;
u64_stats_t tx_packets;
u64_stats_t tx_bytes;
struct u64_stats_sync syncp;
} __aligned(4 * sizeof(u64));
struct pcpu_dstats {
u64_stats_t rx_packets;
u64_stats_t rx_bytes;
u64_stats_t tx_packets;
u64_stats_t tx_bytes;
u64_stats_t rx_drops;
u64_stats_t tx_drops;
struct u64_stats_sync syncp;
} __aligned(8 * sizeof(u64));
struct pcpu_lstats {
u64_stats_t packets;
u64_stats_t bytes;
struct u64_stats_sync syncp;
} __aligned(2 * sizeof(u64));
void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
{
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
u64_stats_add(&tstats->rx_bytes, len); u64_stats_inc(&tstats->rx_packets);
u64_stats_update_end(&tstats->syncp);
}
static inline void dev_sw_netstats_tx_add(struct net_device *dev,
unsigned int packets,
unsigned int len)
{
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&tstats->syncp);
u64_stats_add(&tstats->tx_bytes, len);
u64_stats_add(&tstats->tx_packets, packets);
u64_stats_update_end(&tstats->syncp);
}
static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
{
struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
u64_stats_update_begin(&lstats->syncp);
u64_stats_add(&lstats->bytes, len);
u64_stats_inc(&lstats->packets);
u64_stats_update_end(&lstats->syncp);
}
static inline void dev_dstats_rx_add(struct net_device *dev,
unsigned int len)
{
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
u64_stats_inc(&dstats->rx_packets);
u64_stats_add(&dstats->rx_bytes, len);
u64_stats_update_end(&dstats->syncp);
}
static inline void dev_dstats_rx_dropped(struct net_device *dev)
{
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
u64_stats_inc(&dstats->rx_drops);
u64_stats_update_end(&dstats->syncp);
}
static inline void dev_dstats_tx_add(struct net_device *dev,
unsigned int len)
{
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
u64_stats_inc(&dstats->tx_packets);
u64_stats_add(&dstats->tx_bytes, len);
u64_stats_update_end(&dstats->syncp);
}
static inline void dev_dstats_tx_dropped(struct net_device *dev)
{
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
u64_stats_inc(&dstats->tx_drops);
u64_stats_update_end(&dstats->syncp);
}
#define __netdev_alloc_pcpu_stats(type, gfp) \
({ \
typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\
if (pcpu_stats) { \
int __cpu; \
for_each_possible_cpu(__cpu) { \
typeof(type) *stat; \
stat = per_cpu_ptr(pcpu_stats, __cpu); \
u64_stats_init(&stat->syncp); \
} \
} \
pcpu_stats; \
})
#define netdev_alloc_pcpu_stats(type) \
__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
#define devm_netdev_alloc_pcpu_stats(dev, type) \
({ \
typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\
if (pcpu_stats) { \
int __cpu; \
for_each_possible_cpu(__cpu) { \
typeof(type) *stat; \
stat = per_cpu_ptr(pcpu_stats, __cpu); \
u64_stats_init(&stat->syncp); \
} \
} \
pcpu_stats; \
})
enum netdev_lag_tx_type {
NETDEV_LAG_TX_TYPE_UNKNOWN,
NETDEV_LAG_TX_TYPE_RANDOM,
NETDEV_LAG_TX_TYPE_BROADCAST,
NETDEV_LAG_TX_TYPE_ROUNDROBIN,
NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
NETDEV_LAG_TX_TYPE_HASH,
};
enum netdev_lag_hash {
NETDEV_LAG_HASH_NONE,
NETDEV_LAG_HASH_L2,
NETDEV_LAG_HASH_L34,
NETDEV_LAG_HASH_L23,
NETDEV_LAG_HASH_E23,
NETDEV_LAG_HASH_E34,
NETDEV_LAG_HASH_VLAN_SRCMAC,
NETDEV_LAG_HASH_UNKNOWN,
};
struct netdev_lag_upper_info {
enum netdev_lag_tx_type tx_type;
enum netdev_lag_hash hash_type;
};
struct netdev_lag_lower_state_info {
u8 link_up : 1,
tx_enabled : 1;
};
#include <linux/notifier.h>
/* netdevice notifier chain. Please remember to update netdev_cmd_to_name()
* and the rtnetlink notification exclusion list in rtnetlink_event() when
* adding new types.
*/
enum netdev_cmd {
NETDEV_UP = 1, /* For now you can't veto a device up/down */
NETDEV_DOWN,
NETDEV_REBOOT, /* Tell a protocol stack a network interface
detected a hardware crash and restarted
- we can use this eg to kick tcp sessions
once done */
NETDEV_CHANGE, /* Notify device state change */
NETDEV_REGISTER,
NETDEV_UNREGISTER,
NETDEV_CHANGEMTU, /* notify after mtu change happened */
NETDEV_CHANGEADDR, /* notify after the address change */
NETDEV_PRE_CHANGEADDR, /* notify before the address change */
NETDEV_GOING_DOWN,
NETDEV_CHANGENAME,
NETDEV_FEAT_CHANGE,
NETDEV_BONDING_FAILOVER,
NETDEV_PRE_UP,
NETDEV_PRE_TYPE_CHANGE,
NETDEV_POST_TYPE_CHANGE,
NETDEV_POST_INIT,
NETDEV_PRE_UNINIT,
NETDEV_RELEASE,
NETDEV_NOTIFY_PEERS,
NETDEV_JOIN,
NETDEV_CHANGEUPPER,
NETDEV_RESEND_IGMP,
NETDEV_PRECHANGEMTU, /* notify before mtu change happened */
NETDEV_CHANGEINFODATA,
NETDEV_BONDING_INFO,
NETDEV_PRECHANGEUPPER,
NETDEV_CHANGELOWERSTATE,
NETDEV_UDP_TUNNEL_PUSH_INFO,
NETDEV_UDP_TUNNEL_DROP_INFO,
NETDEV_CHANGE_TX_QUEUE_LEN,
NETDEV_CVLAN_FILTER_PUSH_INFO,
NETDEV_CVLAN_FILTER_DROP_INFO,
NETDEV_SVLAN_FILTER_PUSH_INFO,
NETDEV_SVLAN_FILTER_DROP_INFO,
NETDEV_OFFLOAD_XSTATS_ENABLE,
NETDEV_OFFLOAD_XSTATS_DISABLE,
NETDEV_OFFLOAD_XSTATS_REPORT_USED,
NETDEV_OFFLOAD_XSTATS_REPORT_DELTA,
NETDEV_XDP_FEAT_CHANGE,
};
const char *netdev_cmd_to_name(enum netdev_cmd cmd);
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
int unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb);
int register_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn);
int unregister_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn);
struct netdev_notifier_info {
struct net_device *dev;
struct netlink_ext_ack *extack;
};
struct netdev_notifier_info_ext {
struct netdev_notifier_info info; /* must be first */
union {
u32 mtu;
} ext;
};
struct netdev_notifier_change_info {
struct netdev_notifier_info info; /* must be first */
unsigned int flags_changed;
};
struct netdev_notifier_changeupper_info {
struct netdev_notifier_info info; /* must be first */
struct net_device *upper_dev; /* new upper dev */
bool master; /* is upper dev master */
bool linking; /* is the notification for link or unlink */
void *upper_info; /* upper dev info */
};
struct netdev_notifier_changelowerstate_info {
struct netdev_notifier_info info; /* must be first */
void *lower_state_info; /* is lower dev state */
};
struct netdev_notifier_pre_changeaddr_info {
struct netdev_notifier_info info; /* must be first */
const unsigned char *dev_addr;
};
enum netdev_offload_xstats_type {
NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1,
};
struct netdev_notifier_offload_xstats_info {
struct netdev_notifier_info info; /* must be first */
enum netdev_offload_xstats_type type;
union {
/* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */
struct netdev_notifier_offload_xstats_rd *report_delta;
/* NETDEV_OFFLOAD_XSTATS_REPORT_USED */
struct netdev_notifier_offload_xstats_ru *report_used;
};
};
int netdev_offload_xstats_enable(struct net_device *dev,
enum netdev_offload_xstats_type type,
struct netlink_ext_ack *extack);
int netdev_offload_xstats_disable(struct net_device *dev,
enum netdev_offload_xstats_type type);
bool netdev_offload_xstats_enabled(const struct net_device *dev,
enum netdev_offload_xstats_type type);
int netdev_offload_xstats_get(struct net_device *dev,
enum netdev_offload_xstats_type type,
struct rtnl_hw_stats64 *stats, bool *used,
struct netlink_ext_ack *extack);
void
netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd,
const struct rtnl_hw_stats64 *stats);
void
netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru);
void netdev_offload_xstats_push_delta(struct net_device *dev,
enum netdev_offload_xstats_type type,
const struct rtnl_hw_stats64 *stats);
static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
struct net_device *dev)
{
info->dev = dev;
info->extack = NULL;
}
static inline struct net_device *
netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
{
return info->dev;
}
static inline struct netlink_ext_ack *
netdev_notifier_info_to_extack(const struct netdev_notifier_info *info)
{
return info->extack;
}
int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info);
#define for_each_netdev(net, d) \
list_for_each_entry(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_reverse(net, d) \
list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_rcu(net, d) \
list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_safe(net, d, n) \
list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list)
#define for_each_netdev_continue(net, d) \
list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_continue_reverse(net, d) \
list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \
dev_list)
#define for_each_netdev_continue_rcu(net, d) \
list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_in_bond_rcu(bond, slave) \
for_each_netdev_rcu(&init_net, slave) \
if (netdev_master_upper_dev_get_rcu(slave) == (bond))
#define net_device_entry(lh) list_entry(lh, struct net_device, dev_list)
#define for_each_netdev_dump(net, d, ifindex) \
for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \
ULONG_MAX, XA_PRESENT)); ifindex++)
static inline struct net_device *next_net_device(struct net_device *dev)
{
struct list_head *lh;
struct net *net;
net = dev_net(dev);
lh = dev->dev_list.next;
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}
static inline struct net_device *next_net_device_rcu(struct net_device *dev)
{
struct list_head *lh;
struct net *net;
net = dev_net(dev);
lh = rcu_dereference(list_next_rcu(&dev->dev_list));
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}
static inline struct net_device *first_net_device(struct net *net)
{
return list_empty(&net->dev_base_head) ? NULL :
net_device_entry(net->dev_base_head.next);
}
static inline struct net_device *first_net_device_rcu(struct net *net)
{
struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));
return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}
int netdev_boot_setup_check(struct net_device *dev);
struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
const char *hwaddr);
struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
const char *hwaddr);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
void dev_add_pack(struct packet_type *pt);
void dev_remove_pack(struct packet_type *pt);
void __dev_remove_pack(struct packet_type *pt);
void dev_add_offload(struct packet_offload *po);
void dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
struct net_device_path_stack *stack);
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
struct net_device *__dev_get_by_name(struct net *net, const char *name);
bool netdev_name_in_use(struct net *net, const char *name);
int dev_alloc_name(struct net_device *dev, const char *name);
int netif_open(struct net_device *dev, struct netlink_ext_ack *extack);
int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
void netif_close(struct net_device *dev);
void dev_close(struct net_device *dev);
void dev_close_many(struct list_head *head, bool unlink);
void netif_disable_lro(struct net_device *dev);
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
static inline int dev_queue_xmit(struct sk_buff *skb)
{
return __dev_queue_xmit(skb, NULL);
}
static inline int dev_queue_xmit_accel(struct sk_buff *skb,
struct net_device *sb_dev)
{
return __dev_queue_xmit(skb, sb_dev);
}
static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
int ret;
ret = __dev_direct_xmit(skb, queue_id);
if (!dev_xmit_complete(ret))
kfree_skb(skb);
return ret;
}
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
static inline void unregister_netdevice(struct net_device *dev)
{
unregister_netdevice_queue(dev, NULL);
}
int netdev_refcnt_read(const struct net_device *dev);
void free_netdev(struct net_device *dev);
struct net_device *netdev_get_xmit_slave(struct net_device *dev,
struct sk_buff *skb,
bool all_slaves);
struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev,
struct sock *sk);
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *netdev_get_by_index(struct net *net, int ifindex,
netdevice_tracker *tracker, gfp_t gfp);
struct net_device *netdev_get_by_name(struct net *net, const char *name,
netdevice_tracker *tracker, gfp_t gfp);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
void netdev_copy_name(struct net_device *dev, char *name);
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr,
unsigned int len)
{
if (!dev->header_ops || !dev->header_ops->create)
return 0;
return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
}
static inline int dev_parse_header(const struct sk_buff *skb,
unsigned char *haddr)
{
const struct net_device *dev = skb->dev;
if (!dev->header_ops || !dev->header_ops->parse)
return 0;
return dev->header_ops->parse(skb, haddr);
}
static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb)
{
const struct net_device *dev = skb->dev;
if (!dev->header_ops || !dev->header_ops->parse_protocol)
return 0;
return dev->header_ops->parse_protocol(skb);
}
/* ll_header must have at least hard_header_len allocated */
static inline bool dev_validate_header(const struct net_device *dev,
char *ll_header, int len)
{
if (likely(len >= dev->hard_header_len))
return true;
if (len < dev->min_header_len)
return false;
if (capable(CAP_SYS_RAWIO)) {
memset(ll_header + len, 0, dev->hard_header_len - len);
return true;
}
if (dev->header_ops && dev->header_ops->validate)
return dev->header_ops->validate(ll_header, len);
return false;
}
static inline bool dev_has_header(const struct net_device *dev)
{
return dev->header_ops && dev->header_ops->create;
}
/*
* Incoming packets are placed on per-CPU queues
*/
struct softnet_data {
struct list_head poll_list;
struct sk_buff_head process_queue;
local_lock_t process_queue_bh_lock;
/* stats */
unsigned int processed;
unsigned int time_squeeze;
#ifdef CONFIG_RPS
struct softnet_data *rps_ipi_list;
#endif
unsigned int received_rps;
bool in_net_rx_action;
bool in_napi_threaded_poll;
#ifdef CONFIG_NET_FLOW_LIMIT
struct sd_flow_limit __rcu *flow_limit;
#endif
struct Qdisc *output_queue;
struct Qdisc **output_queue_tailp;
struct sk_buff *completion_queue;
#ifdef CONFIG_XFRM_OFFLOAD
struct sk_buff_head xfrm_backlog;
#endif
/* written and read only by owning cpu: */
struct netdev_xmit xmit;
#ifdef CONFIG_RPS
/* input_queue_head should be written by cpu owning this struct,
* and only read by other cpus. Worth using a cache line.
*/
unsigned int input_queue_head ____cacheline_aligned_in_smp;
/* Elements below can be accessed between CPUs for RPS/RFS */
call_single_data_t csd ____cacheline_aligned_in_smp;
struct softnet_data *rps_ipi_next;
unsigned int cpu;
unsigned int input_queue_tail;
#endif
struct sk_buff_head input_pkt_queue;
struct napi_struct backlog;
atomic_t dropped ____cacheline_aligned_in_smp;
/* Another possibly contended cache line */
spinlock_t defer_lock ____cacheline_aligned_in_smp;
int defer_count;
int defer_ipi_scheduled;
struct sk_buff *defer_list;
call_single_data_t defer_csd;
};
DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
DECLARE_PER_CPU(struct page_pool *, system_page_pool);
#ifndef CONFIG_PREEMPT_RT
static inline int dev_recursion_level(void)
{
return this_cpu_read(softnet_data.xmit.recursion);
}
#else
static inline int dev_recursion_level(void)
{
return current->net_xmit.recursion;
}
#endif
void __netif_schedule(struct Qdisc *q);
void netif_schedule_queue(struct netdev_queue *txq);
static inline void netif_tx_schedule_all(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++)
netif_schedule_queue(netdev_get_tx_queue(dev, i));
}
static __always_inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
* netif_start_queue - allow transmit
* @dev: network device
*
* Allow upper layers to call the device hard_start_xmit routine.
*/
static inline void netif_start_queue(struct net_device *dev)
{
netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
}
static inline void netif_tx_start_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_start_queue(txq);
}
}
void netif_tx_wake_queue(struct netdev_queue *dev_queue);
/**
* netif_wake_queue - restart transmit
* @dev: network device
*
* Allow upper layers to call the device hard_start_xmit routine.
* Used for flow control when transmit resources are available.
*/
static inline void netif_wake_queue(struct net_device *dev)
{
netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
}
static inline void netif_tx_wake_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_wake_queue(txq);
}
}
static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
/* Paired with READ_ONCE() from dev_watchdog() */
WRITE_ONCE(dev_queue->trans_start, jiffies);
/* This barrier is paired with smp_mb() from dev_watchdog() */
smp_mb__before_atomic();
/* Must be an atomic op see netif_txq_try_stop() */
set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
* netif_stop_queue - stop transmitted packets
* @dev: network device
*
* Stop upper layers calling the device hard_start_xmit routine.
* Used for flow control when transmit resources are unavailable.
*/
static inline void netif_stop_queue(struct net_device *dev)
{
netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
}
void netif_tx_stop_all_queues(struct net_device *dev);
static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
* netif_queue_stopped - test if transmit queue is flowblocked
* @dev: network device
*
* Test if transmit queue on device is currently unable to send.
*/
static inline bool netif_queue_stopped(const struct net_device *dev)
{
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
}
static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_ANY_XOFF;
}
static inline bool
netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
}
static inline bool
netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
}
/**
* netdev_queue_set_dql_min_limit - set dql minimum limit
* @dev_queue: pointer to transmit queue
* @min_limit: dql minimum limit
*
* Forces xmit_more() to return true until the minimum threshold
* defined by @min_limit is reached (or until the tx queue is
* empty). Warning: to be use with care, misuse will impact the
* latency.
*/
static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue,
unsigned int min_limit)
{
#ifdef CONFIG_BQL
dev_queue->dql.min_limit = min_limit;
#endif
}
static inline int netdev_queue_dql_avail(const struct netdev_queue *txq)
{
#ifdef CONFIG_BQL
/* Non-BQL migrated drivers will return 0, too. */
return dql_avail(&txq->dql);
#else
return 0;
#endif
}
/**
* netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
*
* BQL enabled drivers might use this helper in their ndo_start_xmit(),
* to give appropriate hint to the CPU.
*/
static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
prefetchw(&dev_queue->dql.num_queued);
#endif
}
/**
* netdev_txq_bql_complete_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
*
* BQL enabled drivers might use this helper in their TX completion path,
* to give appropriate hint to the CPU.
*/
static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
prefetchw(&dev_queue->dql.limit);
#endif
}
/**
* netdev_tx_sent_queue - report the number of bytes queued to a given tx queue
* @dev_queue: network device queue
* @bytes: number of bytes queued to the device queue
*
* Report the number of bytes queued for sending/completion to the network
* device hardware queue. @bytes should be a good approximation and should
* exactly match netdev_completed_queue() @bytes.
* This is typically called once per packet, from ndo_start_xmit().
*/
static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
unsigned int bytes)
{
#ifdef CONFIG_BQL
dql_queued(&dev_queue->dql, bytes);
if (likely(dql_avail(&dev_queue->dql) >= 0))
return;
/* Paired with READ_ONCE() from dev_watchdog() */
WRITE_ONCE(dev_queue->trans_start, jiffies);
/* This barrier is paired with smp_mb() from dev_watchdog() */
smp_mb__before_atomic();
set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
/*
* The XOFF flag must be set before checking the dql_avail below,
* because in netdev_tx_completed_queue we update the dql_completed
* before checking the XOFF flag.
*/
smp_mb__after_atomic();
/* check again in case another CPU has just made room avail */
if (unlikely(dql_avail(&dev_queue->dql) >= 0))
clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
#endif
}
/* Variant of netdev_tx_sent_queue() for drivers that are aware
* that they should not test BQL status themselves.
* We do want to change __QUEUE_STATE_STACK_XOFF only for the last
* skb of a batch.
* Returns true if the doorbell must be used to kick the NIC.
*/
static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue,
unsigned int bytes,
bool xmit_more)
{
if (xmit_more) {
#ifdef CONFIG_BQL
dql_queued(&dev_queue->dql, bytes);
#endif
return netif_tx_queue_stopped(dev_queue);
}
netdev_tx_sent_queue(dev_queue, bytes);
return true;
}
/**
* netdev_sent_queue - report the number of bytes queued to hardware
* @dev: network device
* @bytes: number of bytes queued to the hardware device queue
*
* Report the number of bytes queued for sending/completion to the network
* device hardware queue#0. @bytes should be a good approximation and should
* exactly match netdev_completed_queue() @bytes.
* This is typically called once per packet, from ndo_start_xmit().
*/
static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
{
netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
}
static inline bool __netdev_sent_queue(struct net_device *dev,
unsigned int bytes,
bool xmit_more)
{
return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes,
xmit_more);
}
/**
* netdev_tx_completed_queue - report number of packets/bytes at TX completion.
* @dev_queue: network device queue
* @pkts: number of packets (currently ignored)
* @bytes: number of bytes dequeued from the device queue
*
* Must be called at most once per TX completion round (and not per
* individual packet), so that BQL can adjust its limits appropriately.
*/
static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
unsigned int pkts, unsigned int bytes)
{
#ifdef CONFIG_BQL
if (unlikely(!bytes))
return;
dql_completed(&dev_queue->dql, bytes);
/*
* Without the memory barrier there is a small possibility that
* netdev_tx_sent_queue will miss the update and cause the queue to
* be stopped forever
*/
smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */
if (unlikely(dql_avail(&dev_queue->dql) < 0))
return;
if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state))
netif_schedule_queue(dev_queue);
#endif
}
/**
* netdev_completed_queue - report bytes and packets completed by device
* @dev: network device
* @pkts: actual number of packets sent over the medium
* @bytes: actual number of bytes sent over the medium
*
* Report the number of bytes and packets transmitted by the network device
* hardware queue over the physical medium, @bytes must exactly match the
* @bytes amount passed to netdev_sent_queue()
*/
static inline void netdev_completed_queue(struct net_device *dev,
unsigned int pkts, unsigned int bytes)
{
netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
}
static inline void netdev_tx_reset_queue(struct netdev_queue *q)
{
#ifdef CONFIG_BQL
clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state);
dql_reset(&q->dql);
#endif
}
/**
* netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue
* @dev: network device
* @qid: stack index of the queue to reset
*/
static inline void netdev_tx_reset_subqueue(const struct net_device *dev,
u32 qid)
{
netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid));
}
/**
* netdev_reset_queue - reset the packets and bytes count of a network device
* @dev_queue: network device
*
* Reset the bytes and packet count of a network device and clear the
* software flow control OFF bit for this network device
*/
static inline void netdev_reset_queue(struct net_device *dev_queue)
{
netdev_tx_reset_subqueue(dev_queue, 0);
}
/**
* netdev_cap_txqueue - check if selected tx queue exceeds device queues
* @dev: network device
* @queue_index: given tx queue index
*
* Returns 0 if given tx queue index >= number of device tx queues,
* otherwise returns the originally passed tx queue index.
*/
static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
dev->name, queue_index,
dev->real_num_tx_queues);
return 0;
}
return queue_index;
}
/**
* netif_running - test if up
* @dev: network device
*
* Test if the device has been brought up.
*/
static inline bool netif_running(const struct net_device *dev)
{
return test_bit(__LINK_STATE_START, &dev->state);
}
/*
* Routines to manage the subqueues on a device. We only need start,
* stop, and a check if it's stopped. All other device management is
* done at the overall netdevice level.
* Also test the device if we're multiqueue.
*/
/**
* netif_start_subqueue - allow sending packets on subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Start individual transmit queue of a device with multiple transmit queues.
*/
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
netif_tx_start_queue(txq);
}
/**
* netif_stop_subqueue - stop sending packets on subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Stop individual transmit queue of a device with multiple transmit queues.
*/
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
netif_tx_stop_queue(txq);
}
/**
* __netif_subqueue_stopped - test status of subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Check individual transmit queue of a device with multiple transmit queues.
*/
static inline bool __netif_subqueue_stopped(const struct net_device *dev,
u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
return netif_tx_queue_stopped(txq);
}
/**
* netif_subqueue_stopped - test status of subqueue
* @dev: network device
* @skb: sub queue buffer pointer
*
* Check individual transmit queue of a device with multiple transmit queues.
*/
static inline bool netif_subqueue_stopped(const struct net_device *dev,
struct sk_buff *skb)
{
return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
}
/**
* netif_wake_subqueue - allow sending packets on subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Resume individual transmit queue of a device with multiple transmit queues.
*/
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
netif_tx_wake_queue(txq);
}
#ifdef CONFIG_XPS
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index);
int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
u16 index, enum xps_map_type type);
/**
* netif_attr_test_mask - Test a CPU or Rx queue set in a mask
* @j: CPU/Rx queue index
* @mask: bitmask of all cpus/rx queues
* @nr_bits: number of bits in the bitmask
*
* Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues.
*/
static inline bool netif_attr_test_mask(unsigned long j,
const unsigned long *mask,
unsigned int nr_bits)
{
cpu_max_bits_warn(j, nr_bits);
return test_bit(j, mask);
}
/**
* netif_attr_test_online - Test for online CPU/Rx queue
* @j: CPU/Rx queue index
* @online_mask: bitmask for CPUs/Rx queues that are online
* @nr_bits: number of bits in the bitmask
*
* Returns: true if a CPU/Rx queue is online.
*/
static inline bool netif_attr_test_online(unsigned long j,
const unsigned long *online_mask,
unsigned int nr_bits)
{
cpu_max_bits_warn(j, nr_bits);
if (online_mask)
return test_bit(j, online_mask);
return (j < nr_bits);
}
/**
* netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask
* @n: CPU/Rx queue index
* @srcp: the cpumask/Rx queue mask pointer
* @nr_bits: number of bits in the bitmask
*
* Returns: next (after n) CPU/Rx queue index in the mask;
* >= nr_bits if no further CPUs/Rx queues set.
*/
static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
unsigned int nr_bits)
{
/* -1 is a legal arg here. */
if (n != -1)
cpu_max_bits_warn(n, nr_bits);
if (srcp)
return find_next_bit(srcp, nr_bits, n + 1);
return n + 1;
}
/**
* netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p
* @n: CPU/Rx queue index
* @src1p: the first CPUs/Rx queues mask pointer
* @src2p: the second CPUs/Rx queues mask pointer
* @nr_bits: number of bits in the bitmask
*
* Returns: next (after n) CPU/Rx queue index set in both masks;
* >= nr_bits if no further CPUs/Rx queues set in both.
*/
static inline int netif_attrmask_next_and(int n, const unsigned long *src1p,
const unsigned long *src2p,
unsigned int nr_bits)
{
/* -1 is a legal arg here. */
if (n != -1)
cpu_max_bits_warn(n, nr_bits);
if (src1p && src2p)
return find_next_and_bit(src1p, src2p, nr_bits, n + 1);
else if (src1p)
return find_next_bit(src1p, nr_bits, n + 1);
else if (src2p)
return find_next_bit(src2p, nr_bits, n + 1);
return n + 1;
}
#else
static inline int netif_set_xps_queue(struct net_device *dev,
const struct cpumask *mask,
u16 index)
{
return 0;
}
static inline int __netif_set_xps_queue(struct net_device *dev,
const unsigned long *mask,
u16 index, enum xps_map_type type)
{
return 0;
}
#endif
/**
* netif_is_multiqueue - test if device has multiple transmit queues
* @dev: network device
*
* Check if device has multiple transmit queues
*/
static inline bool netif_is_multiqueue(const struct net_device *dev)
{
return dev->num_tx_queues > 1;
}
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
int netif_set_real_num_queues(struct net_device *dev,
unsigned int txq, unsigned int rxq);
int netif_get_num_default_rss_queues(void);
void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason);
void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason);
/*
* It is not allowed to call kfree_skb() or consume_skb() from hardware
* interrupt context or with hardware interrupts being disabled.
* (in_hardirq() || irqs_disabled())
*
* We provide four helpers that can be used in following contexts :
*
* dev_kfree_skb_irq(skb) when caller drops a packet from irq context,
* replacing kfree_skb(skb)
*
* dev_consume_skb_irq(skb) when caller consumes a packet from irq context.
* Typically used in place of consume_skb(skb) in TX completion path
*
* dev_kfree_skb_any(skb) when caller doesn't know its current irq context,
* replacing kfree_skb(skb)
*
* dev_consume_skb_any(skb) when caller doesn't know its current irq context,
* and consumed a packet. Used in place of consume_skb(skb)
*/
static inline void dev_kfree_skb_irq(struct sk_buff *skb)
{
dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
}
static inline void dev_consume_skb_irq(struct sk_buff *skb)
{
dev_kfree_skb_irq_reason(skb, SKB_CONSUMED);
}
static inline void dev_kfree_skb_any(struct sk_buff *skb)
{
dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
}
static inline void dev_consume_skb_any(struct sk_buff *skb)
{
dev_kfree_skb_any_reason(skb, SKB_CONSUMED);
}
u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
const struct bpf_prog *xdp_prog);
void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog);
int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb);
int netif_rx(struct sk_buff *skb);
int __netif_rx(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
int netif_receive_skb_core(struct sk_buff *skb);
void netif_receive_skb_list_internal(struct list_head *head);
void netif_receive_skb_list(struct list_head *head);
gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb);
static inline gro_result_t napi_gro_receive(struct napi_struct *napi,
struct sk_buff *skb)
{
return gro_receive_skb(&napi->gro, skb);
}
struct sk_buff *napi_get_frags(struct napi_struct *napi);
gro_result_t napi_gro_frags(struct napi_struct *napi);
static inline void napi_free_frags(struct napi_struct *napi)
{
kfree_skb(napi->skb);
napi->skb = NULL;
}
bool netdev_is_rx_handler_busy(struct net_device *dev);
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data);
void netdev_rx_handler_unregister(struct net_device *dev);
bool dev_valid_name(const char *name);
static inline bool is_socket_ioctl_cmd(unsigned int cmd)
{
return _IOC_TYPE(cmd) == SOCK_IOC_TYPE;
}
int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg);
int put_user_ifreq(struct ifreq *ifr, void __user *arg);
int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
void __user *data, bool *need_copyout);
int dev_ifconf(struct net *net, struct ifconf __user *ifc);
int dev_eth_ioctl(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd);
int generic_hwtstamp_get_lower(struct net_device *dev,
struct kernel_hwtstamp_config *kernel_cfg);
int generic_hwtstamp_set_lower(struct net_device *dev,
struct kernel_hwtstamp_config *kernel_cfg,
struct netlink_ext_ack *extack);
int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
unsigned int dev_get_flags(const struct net_device *);
int __dev_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack);
int netif_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack);
int dev_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack);
int netif_set_alias(struct net_device *dev, const char *alias, size_t len);
int dev_set_alias(struct net_device *, const char *, size_t);
int dev_get_alias(const struct net_device *, char *, size_t);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex,
struct netlink_ext_ack *extack);
int dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat);
int __dev_set_mtu(struct net_device *, int);
int netif_set_mtu(struct net_device *dev, int new_mtu);
int dev_set_mtu(struct net_device *, int);
int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
struct netlink_ext_ack *extack);
int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack);
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack);
int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack);
int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
int dev_get_port_parent_id(struct net_device *dev,
struct netdev_phys_item_id *ppid, bool recurse);
bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
u8 dev_xdp_prog_count(struct net_device *dev);
int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
u8 dev_xdp_sb_prog_count(struct net_device *dev);
u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
u32 dev_get_min_mp_channel_count(const struct net_device *dev);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
bool is_skb_forwardable(const struct net_device *dev,
const struct sk_buff *skb);
static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
const struct sk_buff *skb,
const bool check_mtu)
{
const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
unsigned int len;
if (!(dev->flags & IFF_UP))
return false;
if (!check_mtu)
return true;
len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
if (skb->len <= len)
return true;
/* if TSO is enabled, we don't care about the length as the packet
* could be forwarded without being segmented before
*/
if (skb_is_gso(skb))
return true;
return false;
}
void netdev_core_stats_inc(struct net_device *dev, u32 offset);
#define DEV_CORE_STATS_INC(FIELD) \
static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \
{ \
netdev_core_stats_inc(dev, \
offsetof(struct net_device_core_stats, FIELD)); \
}
DEV_CORE_STATS_INC(rx_dropped)
DEV_CORE_STATS_INC(tx_dropped)
DEV_CORE_STATS_INC(rx_nohandler)
DEV_CORE_STATS_INC(rx_otherhost_dropped)
#undef DEV_CORE_STATS_INC
static __always_inline int ____dev_forward_skb(struct net_device *dev,
struct sk_buff *skb,
const bool check_mtu)
{
if (skb_orphan_frags(skb, GFP_ATOMIC) ||
unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
dev_core_stats_rx_dropped_inc(dev);
kfree_skb(skb);
return NET_RX_DROP;
}
skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev)));
skb->priority = 0;
return 0;
}
bool dev_nit_active_rcu(const struct net_device *dev);
static inline bool dev_nit_active(const struct net_device *dev)
{
bool ret;
rcu_read_lock();
ret = dev_nit_active_rcu(dev);
rcu_read_unlock();
return ret;
}
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
static inline void __dev_put(struct net_device *dev)
{
if (dev) {
#ifdef CONFIG_PCPU_DEV_REFCNT
this_cpu_dec(*dev->pcpu_refcnt);
#else
refcount_dec(&dev->dev_refcnt);
#endif
}
}
static inline void __dev_hold(struct net_device *dev)
{
if (dev) {
#ifdef CONFIG_PCPU_DEV_REFCNT
this_cpu_inc(*dev->pcpu_refcnt);
#else
refcount_inc(&dev->dev_refcnt);
#endif
}
}
static inline void __netdev_tracker_alloc(struct net_device *dev,
netdevice_tracker *tracker,
gfp_t gfp)
{
#ifdef CONFIG_NET_DEV_REFCNT_TRACKER
ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp);
#endif
}
/* netdev_tracker_alloc() can upgrade a prior untracked reference
* taken by dev_get_by_name()/dev_get_by_index() to a tracked one.
*/
static inline void netdev_tracker_alloc(struct net_device *dev,
netdevice_tracker *tracker, gfp_t gfp)
{
#ifdef CONFIG_NET_DEV_REFCNT_TRACKER
refcount_dec(&dev->refcnt_tracker.no_tracker);
__netdev_tracker_alloc(dev, tracker, gfp);
#endif
}
static inline void netdev_tracker_free(struct net_device *dev,
netdevice_tracker *tracker)
{
#ifdef CONFIG_NET_DEV_REFCNT_TRACKER
ref_tracker_free(&dev->refcnt_tracker, tracker);
#endif
}
static inline void netdev_hold(struct net_device *dev,
netdevice_tracker *tracker, gfp_t gfp)
{
if (dev) { __dev_hold(dev);
__netdev_tracker_alloc(dev, tracker, gfp);
}
}
static inline void netdev_put(struct net_device *dev,
netdevice_tracker *tracker)
{
if (dev) {
netdev_tracker_free(dev, tracker);
__dev_put(dev);
}
}
/**
* dev_hold - get reference to device
* @dev: network device
*
* Hold reference to device to keep it from being freed.
* Try using netdev_hold() instead.
*/
static inline void dev_hold(struct net_device *dev)
{
netdev_hold(dev, NULL, GFP_ATOMIC);
}
/**
* dev_put - release reference to device
* @dev: network device
*
* Release reference to device to allow it to be freed.
* Try using netdev_put() instead.
*/
static inline void dev_put(struct net_device *dev)
{
netdev_put(dev, NULL);
}
DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T))
static inline void netdev_ref_replace(struct net_device *odev,
struct net_device *ndev,
netdevice_tracker *tracker,
gfp_t gfp)
{
if (odev)
netdev_tracker_free(odev, tracker);
__dev_hold(ndev);
__dev_put(odev);
if (ndev)
__netdev_tracker_alloc(ndev, tracker, gfp);
}
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
* and _off may be called from IRQ context, but it is caller
* who is responsible for serialization of these calls.
*
* The name carrier is inappropriate, these functions should really be
* called netif_lowerlayer_*() because they represent the state of any
* kind of lower layer not just hardware media.
*/
void linkwatch_fire_event(struct net_device *dev);
/**
* linkwatch_sync_dev - sync linkwatch for the given device
* @dev: network device to sync linkwatch for
*
* Sync linkwatch for the given device, removing it from the
* pending work list (if queued).
*/
void linkwatch_sync_dev(struct net_device *dev);
void __linkwatch_sync_dev(struct net_device *dev);
/**
* netif_carrier_ok - test if carrier present
* @dev: network device
*
* Check if carrier is present on device
*/
static inline bool netif_carrier_ok(const struct net_device *dev)
{
return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}
unsigned long dev_trans_start(struct net_device *dev);
void netdev_watchdog_up(struct net_device *dev);
void netif_carrier_on(struct net_device *dev);
void netif_carrier_off(struct net_device *dev);
void netif_carrier_event(struct net_device *dev);
/**
* netif_dormant_on - mark device as dormant.
* @dev: network device
*
* Mark device as dormant (as per RFC2863).
*
* The dormant state indicates that the relevant interface is not
* actually in a condition to pass packets (i.e., it is not 'up') but is
* in a "pending" state, waiting for some external event. For "on-
* demand" interfaces, this new state identifies the situation where the
* interface is waiting for events to place it in the up state.
*/
static inline void netif_dormant_on(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_dormant_off - set device as not dormant.
* @dev: network device
*
* Device is not in dormant state.
*/
static inline void netif_dormant_off(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_dormant - test if device is dormant
* @dev: network device
*
* Check if device is dormant.
*/
static inline bool netif_dormant(const struct net_device *dev)
{
return test_bit(__LINK_STATE_DORMANT, &dev->state);
}
/**
* netif_testing_on - mark device as under test.
* @dev: network device
*
* Mark device as under test (as per RFC2863).
*
* The testing state indicates that some test(s) must be performed on
* the interface. After completion, of the test, the interface state
* will change to up, dormant, or down, as appropriate.
*/
static inline void netif_testing_on(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_testing_off - set device as not under test.
* @dev: network device
*
* Device is not in testing state.
*/
static inline void netif_testing_off(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_testing - test if device is under test
* @dev: network device
*
* Check if device is under test
*/
static inline bool netif_testing(const struct net_device *dev)
{
return test_bit(__LINK_STATE_TESTING, &dev->state);
}
/**
* netif_oper_up - test if device is operational
* @dev: network device
*
* Check if carrier is operational
*/
static inline bool netif_oper_up(const struct net_device *dev)
{
unsigned int operstate = READ_ONCE(dev->operstate);
return operstate == IF_OPER_UP ||
operstate == IF_OPER_UNKNOWN /* backward compat */;
}
/**
* netif_device_present - is device available or removed
* @dev: network device
*
* Check if device has not been removed from system.
*/
static inline bool netif_device_present(const struct net_device *dev)
{
return test_bit(__LINK_STATE_PRESENT, &dev->state);
}
void netif_device_detach(struct net_device *dev);
void netif_device_attach(struct net_device *dev);
/*
* Network interface message level settings
*/
enum {
NETIF_MSG_DRV_BIT,
NETIF_MSG_PROBE_BIT,
NETIF_MSG_LINK_BIT,
NETIF_MSG_TIMER_BIT,
NETIF_MSG_IFDOWN_BIT,
NETIF_MSG_IFUP_BIT,
NETIF_MSG_RX_ERR_BIT,
NETIF_MSG_TX_ERR_BIT,
NETIF_MSG_TX_QUEUED_BIT,
NETIF_MSG_INTR_BIT,
NETIF_MSG_TX_DONE_BIT,
NETIF_MSG_RX_STATUS_BIT,
NETIF_MSG_PKTDATA_BIT,
NETIF_MSG_HW_BIT,
NETIF_MSG_WOL_BIT,
/* When you add a new bit above, update netif_msg_class_names array
* in net/ethtool/common.c
*/
NETIF_MSG_CLASS_COUNT,
};
/* Both ethtool_ops interface and internal driver implementation use u32 */
static_assert(NETIF_MSG_CLASS_COUNT <= 32);
#define __NETIF_MSG_BIT(bit) ((u32)1 << (bit))
#define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT)
#define NETIF_MSG_DRV __NETIF_MSG(DRV)
#define NETIF_MSG_PROBE __NETIF_MSG(PROBE)
#define NETIF_MSG_LINK __NETIF_MSG(LINK)
#define NETIF_MSG_TIMER __NETIF_MSG(TIMER)
#define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN)
#define NETIF_MSG_IFUP __NETIF_MSG(IFUP)
#define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR)
#define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR)
#define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED)
#define NETIF_MSG_INTR __NETIF_MSG(INTR)
#define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE)
#define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS)
#define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA)
#define NETIF_MSG_HW __NETIF_MSG(HW)
#define NETIF_MSG_WOL __NETIF_MSG(WOL)
#define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV)
#define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE)
#define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK)
#define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER)
#define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN)
#define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP)
#define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR)
#define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR)
#define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED)
#define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR)
#define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE)
#define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS)
#define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA)
#define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW)
#define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL)
static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
{
/* use default */
if (debug_value < 0 || debug_value >= (sizeof(u32) * 8))
return default_msg_enable_bits;
if (debug_value == 0) /* no output */
return 0;
/* set low N bits */
return (1U << debug_value) - 1;
}
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
{
spin_lock(&txq->_xmit_lock);
/* Pairs with READ_ONCE() in __dev_queue_xmit() */
WRITE_ONCE(txq->xmit_lock_owner, cpu);
}
static inline bool __netif_tx_acquire(struct netdev_queue *txq)
{
__acquire(&txq->_xmit_lock);
return true;
}
static inline void __netif_tx_release(struct netdev_queue *txq)
{
__release(&txq->_xmit_lock);
}
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
spin_lock_bh(&txq->_xmit_lock);
/* Pairs with READ_ONCE() in __dev_queue_xmit() */
WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
}
static inline bool __netif_tx_trylock(struct netdev_queue *txq)
{
bool ok = spin_trylock(&txq->_xmit_lock);
if (likely(ok)) {
/* Pairs with READ_ONCE() in __dev_queue_xmit() */
WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
}
return ok;
}
static inline void __netif_tx_unlock(struct netdev_queue *txq)
{
/* Pairs with READ_ONCE() in __dev_queue_xmit() */
WRITE_ONCE(txq->xmit_lock_owner, -1);
spin_unlock(&txq->_xmit_lock);
}
static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
{
/* Pairs with READ_ONCE() in __dev_queue_xmit() */
WRITE_ONCE(txq->xmit_lock_owner, -1);
spin_unlock_bh(&txq->_xmit_lock);
}
/*
* txq->trans_start can be read locklessly from dev_watchdog()
*/
static inline void txq_trans_update(struct netdev_queue *txq)
{
if (txq->xmit_lock_owner != -1)
WRITE_ONCE(txq->trans_start, jiffies);
}
static inline void txq_trans_cond_update(struct netdev_queue *txq)
{
unsigned long now = jiffies;
if (READ_ONCE(txq->trans_start) != now)
WRITE_ONCE(txq->trans_start, now);
}
/* legacy drivers only, netdev_start_xmit() sets txq->trans_start */
static inline void netif_trans_update(struct net_device *dev)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
txq_trans_cond_update(txq);
}
/**
* netif_tx_lock - grab network device transmit lock
* @dev: network device
*
* Get network device transmit lock
*/
void netif_tx_lock(struct net_device *dev);
static inline void netif_tx_lock_bh(struct net_device *dev)
{
local_bh_disable();
netif_tx_lock(dev);
}
void netif_tx_unlock(struct net_device *dev);
static inline void netif_tx_unlock_bh(struct net_device *dev)
{
netif_tx_unlock(dev);
local_bh_enable();
}
#define HARD_TX_LOCK(dev, txq, cpu) { \
if (!(dev)->lltx) { \
__netif_tx_lock(txq, cpu); \
} else { \
__netif_tx_acquire(txq); \
} \
}
#define HARD_TX_TRYLOCK(dev, txq) \
(!(dev)->lltx ? \
__netif_tx_trylock(txq) : \
__netif_tx_acquire(txq))
#define HARD_TX_UNLOCK(dev, txq) { \
if (!(dev)->lltx) { \
__netif_tx_unlock(txq); \
} else { \
__netif_tx_release(txq); \
} \
}
static inline void netif_tx_disable(struct net_device *dev)
{
unsigned int i;
int cpu;
local_bh_disable();
cpu = smp_processor_id();
spin_lock(&dev->tx_global_lock);
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
__netif_tx_lock(txq, cpu);
netif_tx_stop_queue(txq);
__netif_tx_unlock(txq);
}
spin_unlock(&dev->tx_global_lock);
local_bh_enable();
}
static inline void netif_addr_lock(struct net_device *dev)
{
unsigned char nest_level = 0;
#ifdef CONFIG_LOCKDEP
nest_level = dev->nested_level;
#endif
spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_lock_bh(struct net_device *dev)
{
unsigned char nest_level = 0;
#ifdef CONFIG_LOCKDEP
nest_level = dev->nested_level;
#endif
local_bh_disable();
spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_unlock(struct net_device *dev)
{
spin_unlock(&dev->addr_list_lock);
}
static inline void netif_addr_unlock_bh(struct net_device *dev)
{
spin_unlock_bh(&dev->addr_list_lock);
}
/*
* dev_addrs walker. Should be used only for read access. Call with
* rcu_read_lock held.
*/
#define for_each_dev_addr(dev, ha) \
list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
/* These functions live elsewhere (drivers/net/net_init.c, but related) */
void ether_setup(struct net_device *dev);
/* Allocate dummy net_device */
struct net_device *alloc_netdev_dummy(int sizeof_priv);
/* Support for loadable net-drivers */
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
unsigned char name_assign_type,
void (*setup)(struct net_device *),
unsigned int txqs, unsigned int rxqs);
#define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
#define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \
alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \
count)
int register_netdev(struct net_device *dev);
void unregister_netdev(struct net_device *dev);
int devm_register_netdev(struct device *dev, struct net_device *ndev);
/* General hardware address lists handling functions */
int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list, int addr_len);
int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list,
int addr_len);
void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list, int addr_len);
int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*sync)(struct net_device *, const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *));
int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*sync)(struct net_device *,
const unsigned char *, int),
int (*unsync)(struct net_device *,
const unsigned char *, int));
void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *, int));
void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *));
void __hw_addr_init(struct netdev_hw_addr_list *list);
/* Functions used for device addresses handling */
void dev_addr_mod(struct net_device *dev, unsigned int offset,
const void *addr, size_t len);
static inline void
__dev_addr_set(struct net_device *dev, const void *addr, size_t len)
{
dev_addr_mod(dev, 0, addr, len);
}
static inline void dev_addr_set(struct net_device *dev, const u8 *addr)
{
__dev_addr_set(dev, addr, dev->addr_len);
}
int dev_addr_add(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
int dev_addr_del(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
/* Functions used for unicast addresses handling */
int dev_uc_add(struct net_device *dev, const unsigned char *addr);
int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_uc_del(struct net_device *dev, const unsigned char *addr);
int dev_uc_sync(struct net_device *to, struct net_device *from);
int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_uc_unsync(struct net_device *to, struct net_device *from);
void dev_uc_flush(struct net_device *dev);
void dev_uc_init(struct net_device *dev);
/**
* __dev_uc_sync - Synchronize device's unicast list
* @dev: device to sync
* @sync: function to call if address should be added
* @unsync: function to call if address should be removed
*
* Add newly added addresses to the interface, and release
* addresses that have been deleted.
*/
static inline int __dev_uc_sync(struct net_device *dev,
int (*sync)(struct net_device *,
const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *))
{
return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync);
}
/**
* __dev_uc_unsync - Remove synchronized addresses from device
* @dev: device to sync
* @unsync: function to call if address should be removed
*
* Remove all addresses that were added to the device by dev_uc_sync().
*/
static inline void __dev_uc_unsync(struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *))
{
__hw_addr_unsync_dev(&dev->uc, dev, unsync);
}
/* Functions used for multicast addresses handling */
int dev_mc_add(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_mc_del(struct net_device *dev, const unsigned char *addr);
int dev_mc_del_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_sync(struct net_device *to, struct net_device *from);
int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_mc_unsync(struct net_device *to, struct net_device *from);
void dev_mc_flush(struct net_device *dev);
void dev_mc_init(struct net_device *dev);
/**
* __dev_mc_sync - Synchronize device's multicast list
* @dev: device to sync
* @sync: function to call if address should be added
* @unsync: function to call if address should be removed
*
* Add newly added addresses to the interface, and release
* addresses that have been deleted.
*/
static inline int __dev_mc_sync(struct net_device *dev,
int (*sync)(struct net_device *,
const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *))
{
return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync);
}
/**
* __dev_mc_unsync - Remove synchronized addresses from device
* @dev: device to sync
* @unsync: function to call if address should be removed
*
* Remove all addresses that were added to the device by dev_mc_sync().
*/
static inline void __dev_mc_unsync(struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *))
{
__hw_addr_unsync_dev(&dev->mc, dev, unsync);
}
/* Functions used for secondary unicast and multicast support */
void dev_set_rx_mode(struct net_device *dev);
int dev_set_promiscuity(struct net_device *dev, int inc);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
int dev_set_allmulti(struct net_device *dev, int inc);
void netif_state_change(struct net_device *dev);
void netdev_state_change(struct net_device *dev);
void __netdev_notify_peers(struct net_device *dev);
void netdev_notify_peers(struct net_device *dev);
void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
void dev_load(struct net *net, const char *name);
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
struct rtnl_link_stats64 *storage);
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats);
void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
const struct pcpu_sw_netstats __percpu *netstats);
void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
enum {
NESTED_SYNC_IMM_BIT,
NESTED_SYNC_TODO_BIT,
};
#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit))
#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT)
#define NESTED_SYNC_IMM __NESTED_SYNC(IMM)
#define NESTED_SYNC_TODO __NESTED_SYNC(TODO)
struct netdev_nested_priv {
unsigned char flags;
void *data;
};
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->adj_list.upper, \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
updev; \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *upper_dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev);
bool netdev_has_any_upper_dev(struct net_device *dev);
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter);
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
struct list_head **iter);
#define netdev_for_each_lower_private(dev, priv, iter) \
for (iter = (dev)->adj_list.lower.next, \
priv = netdev_lower_get_next_private(dev, &(iter)); \
priv; \
priv = netdev_lower_get_next_private(dev, &(iter)))
#define netdev_for_each_lower_private_rcu(dev, priv, iter) \
for (iter = &(dev)->adj_list.lower, \
priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \
priv; \
priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
void *netdev_lower_get_next(struct net_device *dev,
struct list_head **iter);
#define netdev_for_each_lower_dev(dev, ldev, iter) \
for (iter = (dev)->adj_list.lower.next, \
ldev = netdev_lower_get_next(dev, &(iter)); \
ldev; \
ldev = netdev_lower_get_next(dev, &(iter)))
struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter);
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv);
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv);
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev,
struct netlink_ext_ack *extack);
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
void *upper_priv, void *upper_info,
struct netlink_ext_ack *extack);
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev);
int netdev_adjacent_change_prepare(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev,
struct netlink_ext_ack *extack);
void netdev_adjacent_change_commit(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev);
void netdev_adjacent_change_abort(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev);
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev);
void netdev_lower_state_changed(struct net_device *lower_dev,
void *lower_state_info);
/* RSS keys are 40 or 52 bytes long */
#define NETDEV_RSS_KEY_LEN 52
extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len);
int skb_checksum_help(struct sk_buff *skb);
int skb_crc32c_csum_help(struct sk_buff *skb);
int skb_csum_hwoffload_help(struct sk_buff *skb,
const netdev_features_t features);
struct netdev_bonding_info {
ifslave slave;
ifbond master;
};
struct netdev_notifier_bonding_info {
struct netdev_notifier_info info; /* must be first */
struct netdev_bonding_info bonding_info;
};
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info);
#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK)
void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data);
#else
static inline void ethtool_notify(struct net_device *dev, unsigned int cmd,
const void *data)
{
}
#endif
__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
static inline bool can_checksum_protocol(netdev_features_t features,
__be16 protocol)
{
if (protocol == htons(ETH_P_FCOE))
return !!(features & NETIF_F_FCOE_CRC);
/* Assume this is an IP checksum (not SCTP CRC) */
if (features & NETIF_F_HW_CSUM) {
/* Can checksum everything */
return true;
}
switch (protocol) {
case htons(ETH_P_IP):
return !!(features & NETIF_F_IP_CSUM);
case htons(ETH_P_IPV6):
return !!(features & NETIF_F_IPV6_CSUM);
default:
return false;
}
}
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb);
#else
static inline void netdev_rx_csum_fault(struct net_device *dev,
struct sk_buff *skb)
{
}
#endif
/* rx skb timestamps */
void net_enable_timestamp(void);
void net_disable_timestamp(void);
static inline ktime_t netdev_get_tstamp(struct net_device *dev,
const struct skb_shared_hwtstamps *hwtstamps,
bool cycles)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_get_tstamp)
return ops->ndo_get_tstamp(dev, hwtstamps, cycles);
return hwtstamps->hwtstamp;
}
#ifndef CONFIG_PREEMPT_RT
static inline void netdev_xmit_set_more(bool more)
{
__this_cpu_write(softnet_data.xmit.more, more);
}
static inline bool netdev_xmit_more(void)
{
return __this_cpu_read(softnet_data.xmit.more);
}
#else
static inline void netdev_xmit_set_more(bool more)
{
current->net_xmit.more = more;
}
static inline bool netdev_xmit_more(void)
{
return current->net_xmit.more;
}
#endif
static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
struct sk_buff *skb, struct net_device *dev,
bool more)
{
netdev_xmit_set_more(more);
return ops->ndo_start_xmit(skb, dev);
}
static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, bool more)
{
const struct net_device_ops *ops = dev->netdev_ops;
netdev_tx_t rc;
rc = __netdev_start_xmit(ops, skb, dev, more);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
int netdev_class_create_file_ns(const struct class_attribute *class_attr,
const void *ns);
void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
const void *ns);
extern const struct kobj_ns_type_operations net_ns_type_operations;
const char *netdev_drivername(const struct net_device *dev);
static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
netdev_features_t f2)
{
if ((f1 ^ f2) & NETIF_F_HW_CSUM) {
if (f1 & NETIF_F_HW_CSUM)
f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
else
f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
return f1 & f2;
}
static inline netdev_features_t netdev_get_wanted_features(
struct net_device *dev)
{
return (dev->features & ~dev->hw_features) | dev->wanted_features;
}
netdev_features_t netdev_increment_features(netdev_features_t all,
netdev_features_t one, netdev_features_t mask);
/* Allow TSO being used on stacked device :
* Performing the GSO segmentation before last device
* is a performance improvement.
*/
static inline netdev_features_t netdev_add_tso_features(netdev_features_t features,
netdev_features_t mask)
{
return netdev_increment_features(features, NETIF_F_ALL_TSO, mask);
}
int __netdev_update_features(struct net_device *dev);
void netdev_update_features(struct net_device *dev);
void netdev_change_features(struct net_device *dev);
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
netdev_features_t passthru_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
netdev_features_t netif_skb_features(struct sk_buff *skb);
void skb_warn_bad_offload(const struct sk_buff *skb);
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
{
netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT;
/* check flags correspondence */
BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCP_ACCECN !=
(NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT));
return (features & feature) == feature;
}
static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
{
return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
(!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
}
static inline bool netif_needs_gso(struct sk_buff *skb,
netdev_features_t features)
{
return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
(skb->ip_summed != CHECKSUM_UNNECESSARY)));
}
void netif_set_tso_max_size(struct net_device *dev, unsigned int size);
void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
void netif_inherit_tso_max(struct net_device *to,
const struct net_device *from);
static inline unsigned int
netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb)
{
/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */
return skb->protocol == htons(ETH_P_IPV6) ?
READ_ONCE(dev->gro_max_size) :
READ_ONCE(dev->gro_ipv4_max_size);
}
static inline unsigned int
netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb)
{
/* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
return skb->protocol == htons(ETH_P_IPV6) ?
READ_ONCE(dev->gso_max_size) :
READ_ONCE(dev->gso_ipv4_max_size);
}
static inline bool netif_is_macsec(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACSEC;
}
static inline bool netif_is_macvlan(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN;
}
static inline bool netif_is_macvlan_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN_PORT;
}
static inline bool netif_is_bond_master(const struct net_device *dev)
{
return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
}
static inline bool netif_is_bond_slave(const struct net_device *dev)
{
return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
}
static inline bool netif_supports_nofcs(struct net_device *dev)
{
return dev->priv_flags & IFF_SUPP_NOFCS;
}
static inline bool netif_has_l3_rx_handler(const struct net_device *dev)
{
return dev->priv_flags & IFF_L3MDEV_RX_HANDLER;
}
static inline bool netif_is_l3_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_L3MDEV_MASTER;
}
static inline bool netif_is_l3_slave(const struct net_device *dev)
{
return dev->priv_flags & IFF_L3MDEV_SLAVE;
}
static inline int dev_sdif(const struct net_device *dev)
{
#ifdef CONFIG_NET_L3_MASTER_DEV
if (netif_is_l3_slave(dev))
return dev->ifindex;
#endif
return 0;
}
static inline bool netif_is_bridge_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_EBRIDGE;
}
static inline bool netif_is_bridge_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_BRIDGE_PORT;
}
static inline bool netif_is_ovs_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_OPENVSWITCH;
}
static inline bool netif_is_ovs_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_OVS_DATAPATH;
}
static inline bool netif_is_any_bridge_master(const struct net_device *dev)
{
return netif_is_bridge_master(dev) || netif_is_ovs_master(dev);
}
static inline bool netif_is_any_bridge_port(const struct net_device *dev)
{
return netif_is_bridge_port(dev) || netif_is_ovs_port(dev);
}
static inline bool netif_is_team_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_TEAM;
}
static inline bool netif_is_team_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_TEAM_PORT;
}
static inline bool netif_is_lag_master(const struct net_device *dev)
{
return netif_is_bond_master(dev) || netif_is_team_master(dev);
}
static inline bool netif_is_lag_port(const struct net_device *dev)
{
return netif_is_bond_slave(dev) || netif_is_team_port(dev);
}
static inline bool netif_is_rxfh_configured(const struct net_device *dev)
{
return dev->priv_flags & IFF_RXFH_CONFIGURED;
}
static inline bool netif_is_failover(const struct net_device *dev)
{
return dev->priv_flags & IFF_FAILOVER;
}
static inline bool netif_is_failover_slave(const struct net_device *dev)
{
return dev->priv_flags & IFF_FAILOVER_SLAVE;
}
/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
static inline void netif_keep_dst(struct net_device *dev)
{
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
}
/* return true if dev can't cope with mtu frames that need vlan tag insertion */
static inline bool netif_reduces_vlan_mtu(struct net_device *dev)
{
/* TODO: reserve and use an additional IFF bit, if we get more users */
return netif_is_macsec(dev);
}
extern struct pernet_operations __net_initdata loopback_net_ops;
/* Logging, debugging and troubleshooting/diagnostic helpers. */
/* netdev_printk helpers, similar to dev_printk */
static inline const char *netdev_name(const struct net_device *dev)
{
if (!dev->name[0] || strchr(dev->name, '%'))
return "(unnamed net_device)";
return dev->name;
}
static inline const char *netdev_reg_state(const struct net_device *dev)
{
u8 reg_state = READ_ONCE(dev->reg_state);
switch (reg_state) {
case NETREG_UNINITIALIZED: return " (uninitialized)";
case NETREG_REGISTERED: return "";
case NETREG_UNREGISTERING: return " (unregistering)";
case NETREG_UNREGISTERED: return " (unregistered)";
case NETREG_RELEASED: return " (released)";
case NETREG_DUMMY: return " (dummy)";
}
WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state);
return " (unknown)";
}
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
/*
* netdev_WARN() acts like dev_printk(), but with the key difference
* of using a WARN/WARN_ON to get the message out, including the
* file/line information and a backtrace.
*/
#define netdev_WARN(dev, format, args...) \
WARN(1, "netdevice: %s%s: " format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
#define netdev_WARN_ONCE(dev, format, args...) \
WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
*
* Why 16. Because with 16 the only overlap we get on a hash of the
* low nibble of the protocol value is RARP/SNAP/X.25.
*
* 0800 IP
* 0001 802.3
* 0002 AX.25
* 0004 802.2
* 8035 RARP
* 0005 SNAP
* 0805 X.25
* 0806 ARP
* 8137 IPX
* 0009 Localtalk
* 86DD IPv6
*/
#define PTYPE_HASH_SIZE (16)
#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
extern struct net_device *blackhole_netdev;
/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */
#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD)
#define DEV_STATS_ADD(DEV, FIELD, VAL) \
atomic_long_add((VAL), &(DEV)->stats.__##FIELD)
#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD)
#endif /* _LINUX_NETDEVICE_H */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/super.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* super.c contains code to handle: - mount structures
* - super-block tables
* - filesystem drivers list
* - mount system call
* - umount system call
* - ustat system call
*
* GK 2/5/95 - Changed to support mounting the root fs via NFS
*
* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
* Added options to /proc/mounts:
* Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/writeback.h> /* for the emergency remount stuff */
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
#include <linux/fscrypt.h>
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
#include <uapi/linux/mount.h>
#include "internal.h"
static int thaw_super_locked(struct super_block *sb, enum freeze_holder who);
static LIST_HEAD(super_blocks);
static DEFINE_SPINLOCK(sb_lock);
static char *sb_writers_name[SB_FREEZE_LEVELS] = {
"sb_writers",
"sb_pagefaults",
"sb_internal",
};
static inline void __super_lock(struct super_block *sb, bool excl)
{
if (excl)
down_write(&sb->s_umount);
else
down_read(&sb->s_umount);
}
static inline void super_unlock(struct super_block *sb, bool excl)
{
if (excl)
up_write(&sb->s_umount);
else
up_read(&sb->s_umount);
}
static inline void __super_lock_excl(struct super_block *sb)
{
__super_lock(sb, true);
}
static inline void super_unlock_excl(struct super_block *sb)
{
super_unlock(sb, true);
}
static inline void super_unlock_shared(struct super_block *sb)
{
super_unlock(sb, false);
}
static bool super_flags(const struct super_block *sb, unsigned int flags)
{
/*
* Pairs with smp_store_release() in super_wake() and ensures
* that we see @flags after we're woken.
*/
return smp_load_acquire(&sb->s_flags) & flags;
}
/**
* super_lock - wait for superblock to become ready and lock it
* @sb: superblock to wait for
* @excl: whether exclusive access is required
*
* If the superblock has neither passed through vfs_get_tree() or
* generic_shutdown_super() yet wait for it to happen. Either superblock
* creation will succeed and SB_BORN is set by vfs_get_tree() or we're
* woken and we'll see SB_DYING.
*
* The caller must have acquired a temporary reference on @sb->s_count.
*
* Return: The function returns true if SB_BORN was set and with
* s_umount held. The function returns false if SB_DYING was
* set and without s_umount held.
*/
static __must_check bool super_lock(struct super_block *sb, bool excl)
{ lockdep_assert_not_held(&sb->s_umount);
/* wait until the superblock is ready or dying */
wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING));
/* Don't pointlessly acquire s_umount. */
if (super_flags(sb, SB_DYING))
return false;
__super_lock(sb, excl);
/*
* Has gone through generic_shutdown_super() in the meantime.
* @sb->s_root is NULL and @sb->s_active is 0. No one needs to
* grab a reference to this. Tell them so.
*/
if (sb->s_flags & SB_DYING) { super_unlock(sb, excl);
return false;
}
WARN_ON_ONCE(!(sb->s_flags & SB_BORN));
return true;
}
/* wait and try to acquire read-side of @sb->s_umount */
static inline bool super_lock_shared(struct super_block *sb)
{
return super_lock(sb, false);
}
/* wait and try to acquire write-side of @sb->s_umount */
static inline bool super_lock_excl(struct super_block *sb)
{
return super_lock(sb, true);
}
/* wake waiters */
#define SUPER_WAKE_FLAGS (SB_BORN | SB_DYING | SB_DEAD)
static void super_wake(struct super_block *sb, unsigned int flag)
{
WARN_ON_ONCE((flag & ~SUPER_WAKE_FLAGS));
WARN_ON_ONCE(hweight32(flag & SUPER_WAKE_FLAGS) > 1);
/*
* Pairs with smp_load_acquire() in super_lock() to make sure
* all initializations in the superblock are seen by the user
* seeing SB_BORN sent.
*/
smp_store_release(&sb->s_flags, sb->s_flags | flag);
/*
* Pairs with the barrier in prepare_to_wait_event() to make sure
* ___wait_var_event() either sees SB_BORN set or
* waitqueue_active() check in wake_up_var() sees the waiter.
*/
smp_mb();
wake_up_var(&sb->s_flags);
}
/*
* One thing we have to be careful of with a per-sb shrinker is that we don't
* drop the last active reference to the superblock from within the shrinker.
* If that happens we could trigger unregistering the shrinker from within the
* shrinker path and that leads to deadlock on the shrinker_mutex. Hence we
* take a passive reference to the superblock to avoid this from occurring.
*/
static unsigned long super_cache_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct super_block *sb;
long fs_objects = 0;
long total_objects;
long freed = 0;
long dentries;
long inodes;
sb = shrink->private_data;
/*
* Deadlock avoidance. We may hold various FS locks, and we don't want
* to recurse into the FS that called us in clear_inode() and friends..
*/
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
if (!super_trylock_shared(sb))
return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb, sc);
inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
total_objects = dentries + inodes + fs_objects + 1;
if (!total_objects)
total_objects = 1;
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
/*
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*
* Ensure that we always scan at least one object - memcg kmem
* accounting uses this to fully empty the caches.
*/
sc->nr_to_scan = dentries + 1;
freed = prune_dcache_sb(sb, sc);
sc->nr_to_scan = inodes + 1;
freed += prune_icache_sb(sb, sc);
if (fs_objects) {
sc->nr_to_scan = fs_objects + 1;
freed += sb->s_op->free_cached_objects(sb, sc);
}
super_unlock_shared(sb);
return freed;
}
static unsigned long super_cache_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct super_block *sb;
long total_objects = 0;
sb = shrink->private_data;
/*
* We don't call super_trylock_shared() here as it is a scalability
* bottleneck, so we're exposed to partial setup state. The shrinker
* rwsem does not protect filesystem operations backing
* list_lru_shrink_count() or s_op->nr_cached_objects(). Counts can
* change between super_cache_count and super_cache_scan, so we really
* don't need locks here.
*
* However, if we are currently mounting the superblock, the underlying
* filesystem might be in a state of partial construction and hence it
* is dangerous to access it. super_trylock_shared() uses a SB_BORN check
* to avoid this situation, so do the same here. The memory barrier is
* matched with the one in mount_fs() as we don't hold locks here.
*/
if (!(sb->s_flags & SB_BORN))
return 0;
smp_rmb();
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb, sc);
total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
if (!total_objects)
return SHRINK_EMPTY;
total_objects = vfs_pressure_ratio(total_objects);
return total_objects;
}
static void destroy_super_work(struct work_struct *work)
{
struct super_block *s = container_of(work, struct super_block,
destroy_work);
fsnotify_sb_free(s);
security_sb_free(s);
put_user_ns(s->s_user_ns);
kfree(s->s_subtype);
for (int i = 0; i < SB_FREEZE_LEVELS; i++)
percpu_free_rwsem(&s->s_writers.rw_sem[i]);
kfree(s);
}
static void destroy_super_rcu(struct rcu_head *head)
{
struct super_block *s = container_of(head, struct super_block, rcu);
INIT_WORK(&s->destroy_work, destroy_super_work);
schedule_work(&s->destroy_work);
}
/* Free a superblock that has never been seen by anyone */
static void destroy_unused_super(struct super_block *s)
{
if (!s)
return;
super_unlock_excl(s);
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
shrinker_free(s->s_shrink);
/* no delays needed */
destroy_super_work(&s->destroy_work);
}
/**
* alloc_super - create new superblock
* @type: filesystem type superblock should belong to
* @flags: the mount flags
* @user_ns: User namespace for the super_block
*
* Allocates and initializes a new &struct super_block. alloc_super()
* returns a pointer new superblock or %NULL if allocation had failed.
*/
static struct super_block *alloc_super(struct file_system_type *type, int flags,
struct user_namespace *user_ns)
{
struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL);
static const struct super_operations default_op;
int i;
if (!s)
return NULL;
INIT_LIST_HEAD(&s->s_mounts);
s->s_user_ns = get_user_ns(user_ns);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
/*
* sget() can have s_umount recursion.
*
* When it cannot find a suitable sb, it allocates a new
* one (this one), and tries again to find a suitable old
* one.
*
* In case that succeeds, it will acquire the s_umount
* lock of the old one. Since these are clearly distrinct
* locks, and this object isn't exposed yet, there's no
* risk of deadlocks.
*
* Annotate this by putting this lock in a different
* subclass.
*/
down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
if (security_sb_alloc(s))
goto fail;
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
sb_writers_name[i],
&type->s_writers_key[i]))
goto fail;
}
s->s_bdi = &noop_backing_dev_info;
s->s_flags = flags;
if (s->s_user_ns != &init_user_ns)
s->s_iflags |= SB_I_NODEV;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_roots);
mutex_init(&s->s_sync_lock);
INIT_LIST_HEAD(&s->s_inodes);
spin_lock_init(&s->s_inode_list_lock);
INIT_LIST_HEAD(&s->s_inodes_wb);
spin_lock_init(&s->s_inode_wblist_lock);
s->s_count = 1;
atomic_set(&s->s_active, 1);
mutex_init(&s->s_vfs_rename_mutex);
lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
init_rwsem(&s->s_dquot.dqio_sem);
s->s_maxbytes = MAX_NON_LFS;
s->s_op = &default_op;
s->s_time_gran = 1000000000;
s->s_time_min = TIME64_MIN;
s->s_time_max = TIME64_MAX;
s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
"sb-%s", type->name);
if (!s->s_shrink)
goto fail;
s->s_shrink->scan_objects = super_cache_scan;
s->s_shrink->count_objects = super_cache_count;
s->s_shrink->batch = 1024;
s->s_shrink->private_data = s;
if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink))
goto fail;
if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink))
goto fail;
return s;
fail:
destroy_unused_super(s);
return NULL;
}
/* Superblock refcounting */
/*
* Drop a superblock's refcount. The caller must hold sb_lock.
*/
static void __put_super(struct super_block *s)
{
if (!--s->s_count) {
list_del_init(&s->s_list);
WARN_ON(s->s_dentry_lru.node);
WARN_ON(s->s_inode_lru.node);
WARN_ON(!list_empty(&s->s_mounts));
call_rcu(&s->rcu, destroy_super_rcu);
}
}
/**
* put_super - drop a temporary reference to superblock
* @sb: superblock in question
*
* Drops a temporary reference, frees superblock if there's no
* references left.
*/
void put_super(struct super_block *sb)
{
spin_lock(&sb_lock);
__put_super(sb);
spin_unlock(&sb_lock);
}
static void kill_super_notify(struct super_block *sb)
{
lockdep_assert_not_held(&sb->s_umount);
/* already notified earlier */
if (sb->s_flags & SB_DEAD)
return;
/*
* Remove it from @fs_supers so it isn't found by new
* sget{_fc}() walkers anymore. Any concurrent mounter still
* managing to grab a temporary reference is guaranteed to
* already see SB_DYING and will wait until we notify them about
* SB_DEAD.
*/
spin_lock(&sb_lock);
hlist_del_init(&sb->s_instances);
spin_unlock(&sb_lock);
/*
* Let concurrent mounts know that this thing is really dead.
* We don't need @sb->s_umount here as every concurrent caller
* will see SB_DYING and either discard the superblock or wait
* for SB_DEAD.
*/
super_wake(sb, SB_DEAD);
}
/**
* deactivate_locked_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Drops an active reference to superblock, converting it into a temporary
* one if there is no other active references left. In that case we
* tell fs driver to shut it down and drop the temporary reference we
* had just acquired.
*
* Caller holds exclusive lock on superblock; that lock is released.
*/
void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
shrinker_free(s->s_shrink);
fs->kill_sb(s);
kill_super_notify(s);
/*
* Since list_lru_destroy() may sleep, we cannot call it from
* put_super(), where we hold the sb_lock. Therefore we destroy
* the lru lists right now.
*/
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
put_filesystem(fs);
put_super(s);
} else {
super_unlock_excl(s);
}
}
EXPORT_SYMBOL(deactivate_locked_super);
/**
* deactivate_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Variant of deactivate_locked_super(), except that superblock is *not*
* locked by caller. If we are going to drop the final active reference,
* lock will be acquired prior to that.
*/
void deactivate_super(struct super_block *s)
{
if (!atomic_add_unless(&s->s_active, -1, 1)) {
__super_lock_excl(s);
deactivate_locked_super(s);
}
}
EXPORT_SYMBOL(deactivate_super);
/**
* grab_super - acquire an active reference to a superblock
* @sb: superblock to acquire
*
* Acquire a temporary reference on a superblock and try to trade it for
* an active reference. This is used in sget{_fc}() to wait for a
* superblock to either become SB_BORN or for it to pass through
* sb->kill() and be marked as SB_DEAD.
*
* Return: This returns true if an active reference could be acquired,
* false if not.
*/
static bool grab_super(struct super_block *sb)
{
bool locked;
sb->s_count++;
spin_unlock(&sb_lock);
locked = super_lock_excl(sb);
if (locked) {
if (atomic_inc_not_zero(&sb->s_active)) {
put_super(sb);
return true;
}
super_unlock_excl(sb);
}
wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD));
put_super(sb);
return false;
}
/*
* super_trylock_shared - try to grab ->s_umount shared
* @sb: reference we are trying to grab
*
* Try to prevent fs shutdown. This is used in places where we
* cannot take an active reference but we need to ensure that the
* filesystem is not shut down while we are working on it. It returns
* false if we cannot acquire s_umount or if we lose the race and
* filesystem already got into shutdown, and returns true with the s_umount
* lock held in read mode in case of success. On successful return,
* the caller must drop the s_umount lock when done.
*
* Note that unlike get_super() et.al. this one does *not* bump ->s_count.
* The reason why it's safe is that we are OK with doing trylock instead
* of down_read(). There's a couple of places that are OK with that, but
* it's very much not a general-purpose interface.
*/
bool super_trylock_shared(struct super_block *sb)
{
if (down_read_trylock(&sb->s_umount)) {
if (!(sb->s_flags & SB_DYING) && sb->s_root &&
(sb->s_flags & SB_BORN))
return true;
super_unlock_shared(sb);
}
return false;
}
/**
* retire_super - prevents superblock from being reused
* @sb: superblock to retire
*
* The function marks superblock to be ignored in superblock test, which
* prevents it from being reused for any new mounts. If the superblock has
* a private bdi, it also unregisters it, but doesn't reduce the refcount
* of the superblock to prevent potential races. The refcount is reduced
* by generic_shutdown_super(). The function can not be called
* concurrently with generic_shutdown_super(). It is safe to call the
* function multiple times, subsequent calls have no effect.
*
* The marker will affect the re-use only for block-device-based
* superblocks. Other superblocks will still get marked if this function
* is used, but that will not affect their reusability.
*/
void retire_super(struct super_block *sb)
{
WARN_ON(!sb->s_bdev);
__super_lock_excl(sb);
if (sb->s_iflags & SB_I_PERSB_BDI) {
bdi_unregister(sb->s_bdi);
sb->s_iflags &= ~SB_I_PERSB_BDI;
}
sb->s_iflags |= SB_I_RETIRED;
super_unlock_excl(sb);
}
EXPORT_SYMBOL(retire_super);
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
*
* generic_shutdown_super() does all fs-independent work on superblock
* shutdown. Typical ->kill_sb() should pick all fs-specific objects
* that need destruction out of superblock, call generic_shutdown_super()
* and release aforementioned objects. Note: dentries and inodes _are_
* taken care of and do not need specific handling.
*
* Upon calling this function, the filesystem may no longer alter or
* rearrange the set of dentries belonging to this super_block, nor may it
* change the attachments of dentries to inodes.
*/
void generic_shutdown_super(struct super_block *sb)
{
const struct super_operations *sop = sb->s_op;
if (sb->s_root) {
shrink_dcache_for_umount(sb);
sync_filesystem(sb);
sb->s_flags &= ~SB_ACTIVE;
cgroup_writeback_umount(sb);
/* Evict all inodes with zero refcount. */
evict_inodes(sb);
/*
* Clean up and evict any inodes that still have references due
* to fsnotify or the security policy.
*/
fsnotify_sb_delete(sb);
security_sb_delete(sb);
if (sb->s_dio_done_wq) {
destroy_workqueue(sb->s_dio_done_wq);
sb->s_dio_done_wq = NULL;
}
if (sop->put_super)
sop->put_super(sb);
/*
* Now that all potentially-encrypted inodes have been evicted,
* the fscrypt keyring can be destroyed.
*/
fscrypt_destroy_keyring(sb);
if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL,
"VFS: Busy inodes after unmount of %s (%s)",
sb->s_id, sb->s_type->name)) {
/*
* Adding a proper bailout path here would be hard, but
* we can at least make it more likely that a later
* iput_final() or such crashes cleanly.
*/
struct inode *inode;
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
inode->i_op = VFS_PTR_POISON;
inode->i_sb = VFS_PTR_POISON;
inode->i_mapping = VFS_PTR_POISON;
}
spin_unlock(&sb->s_inode_list_lock);
}
}
/*
* Broadcast to everyone that grabbed a temporary reference to this
* superblock before we removed it from @fs_supers that the superblock
* is dying. Every walker of @fs_supers outside of sget{_fc}() will now
* discard this superblock and treat it as dead.
*
* We leave the superblock on @fs_supers so it can be found by
* sget{_fc}() until we passed sb->kill_sb().
*/
super_wake(sb, SB_DYING);
super_unlock_excl(sb);
if (sb->s_bdi != &noop_backing_dev_info) {
if (sb->s_iflags & SB_I_PERSB_BDI)
bdi_unregister(sb->s_bdi);
bdi_put(sb->s_bdi);
sb->s_bdi = &noop_backing_dev_info;
}
}
EXPORT_SYMBOL(generic_shutdown_super);
bool mount_capable(struct fs_context *fc)
{
if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT))
return capable(CAP_SYS_ADMIN);
else
return ns_capable(fc->user_ns, CAP_SYS_ADMIN);
}
/**
* sget_fc - Find or create a superblock
* @fc: Filesystem context.
* @test: Comparison callback
* @set: Setup callback
*
* Create a new superblock or find an existing one.
*
* The @test callback is used to find a matching existing superblock.
* Whether or not the requested parameters in @fc are taken into account
* is specific to the @test callback that is used. They may even be
* completely ignored.
*
* If an extant superblock is matched, it will be returned unless:
*
* (1) the namespace the filesystem context @fc and the extant
* superblock's namespace differ
*
* (2) the filesystem context @fc has requested that reusing an extant
* superblock is not allowed
*
* In both cases EBUSY will be returned.
*
* If no match is made, a new superblock will be allocated and basic
* initialisation will be performed (s_type, s_fs_info and s_id will be
* set and the @set callback will be invoked), the superblock will be
* published and it will be returned in a partially constructed state
* with SB_BORN and SB_ACTIVE as yet unset.
*
* Return: On success, an extant or newly created superblock is
* returned. On failure an error pointer is returned.
*/
struct super_block *sget_fc(struct fs_context *fc,
int (*test)(struct super_block *, struct fs_context *),
int (*set)(struct super_block *, struct fs_context *))
{
struct super_block *s = NULL;
struct super_block *old;
struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns;
int err;
/*
* Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is
* not set, as the filesystem is likely unprepared to handle it.
* This can happen when fsconfig() is called from init_user_ns with
* an fs_fd opened in another user namespace.
*/
if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) {
errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed");
return ERR_PTR(-EPERM);
}
retry:
spin_lock(&sb_lock);
if (test) {
hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) {
if (test(old, fc))
goto share_extant_sb;
}
}
if (!s) {
spin_unlock(&sb_lock);
s = alloc_super(fc->fs_type, fc->sb_flags, user_ns);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
}
s->s_fs_info = fc->s_fs_info;
err = set(s, fc);
if (err) {
s->s_fs_info = NULL;
spin_unlock(&sb_lock);
destroy_unused_super(s);
return ERR_PTR(err);
}
fc->s_fs_info = NULL;
s->s_type = fc->fs_type;
s->s_iflags |= fc->s_iflags;
strscpy(s->s_id, s->s_type->name, sizeof(s->s_id));
/*
* Make the superblock visible on @super_blocks and @fs_supers.
* It's in a nascent state and users should wait on SB_BORN or
* SB_DYING to be set.
*/
list_add_tail(&s->s_list, &super_blocks);
hlist_add_head(&s->s_instances, &s->s_type->fs_supers);
spin_unlock(&sb_lock);
get_filesystem(s->s_type);
shrinker_register(s->s_shrink);
return s;
share_extant_sb:
if (user_ns != old->s_user_ns || fc->exclusive) {
spin_unlock(&sb_lock);
destroy_unused_super(s);
if (fc->exclusive)
warnfc(fc, "reusing existing filesystem not allowed");
else
warnfc(fc, "reusing existing filesystem in another namespace not allowed");
return ERR_PTR(-EBUSY);
}
if (!grab_super(old))
goto retry;
destroy_unused_super(s);
return old;
}
EXPORT_SYMBOL(sget_fc);
/**
* sget - find or create a superblock
* @type: filesystem type superblock should belong to
* @test: comparison callback
* @set: setup callback
* @flags: mount flags
* @data: argument to each of them
*/
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags,
void *data)
{
struct user_namespace *user_ns = current_user_ns();
struct super_block *s = NULL;
struct super_block *old;
int err;
/* We don't yet pass the user namespace of the parent
* mount through to here so always use &init_user_ns
* until that changes.
*/
if (flags & SB_SUBMOUNT)
user_ns = &init_user_ns;
retry:
spin_lock(&sb_lock);
if (test) {
hlist_for_each_entry(old, &type->fs_supers, s_instances) {
if (!test(old, data))
continue;
if (user_ns != old->s_user_ns) {
spin_unlock(&sb_lock);
destroy_unused_super(s);
return ERR_PTR(-EBUSY);
}
if (!grab_super(old))
goto retry;
destroy_unused_super(s);
return old;
}
}
if (!s) {
spin_unlock(&sb_lock);
s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
}
err = set(s, data);
if (err) {
spin_unlock(&sb_lock);
destroy_unused_super(s);
return ERR_PTR(err);
}
s->s_type = type;
strscpy(s->s_id, type->name, sizeof(s->s_id));
list_add_tail(&s->s_list, &super_blocks);
hlist_add_head(&s->s_instances, &type->fs_supers);
spin_unlock(&sb_lock);
get_filesystem(type);
shrinker_register(s->s_shrink);
return s;
}
EXPORT_SYMBOL(sget);
void drop_super(struct super_block *sb)
{
super_unlock_shared(sb);
put_super(sb);
}
EXPORT_SYMBOL(drop_super);
void drop_super_exclusive(struct super_block *sb)
{
super_unlock_excl(sb);
put_super(sb);
}
EXPORT_SYMBOL(drop_super_exclusive);
static void __iterate_supers(void (*f)(struct super_block *))
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (super_flags(sb, SB_DYING))
continue;
sb->s_count++;
spin_unlock(&sb_lock);
f(sb);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
/**
* iterate_supers - call function for all active superblocks
* @f: function to call
* @arg: argument to pass to it
*
* Scans the superblock list and calls given function, passing it
* locked superblock and given argument.
*/
void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
bool locked;
sb->s_count++;
spin_unlock(&sb_lock);
locked = super_lock_shared(sb);
if (locked) {
if (sb->s_root)
f(sb, arg);
super_unlock_shared(sb);
}
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
/**
* iterate_supers_type - call function for superblocks of given type
* @type: fs type
* @f: function to call
* @arg: argument to pass to it
*
* Scans the superblock list and calls given function, passing it
* locked superblock and given argument.
*/
void iterate_supers_type(struct file_system_type *type,
void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
bool locked;
sb->s_count++;
spin_unlock(&sb_lock);
locked = super_lock_shared(sb);
if (locked) {
if (sb->s_root)
f(sb, arg);
super_unlock_shared(sb);
}
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
EXPORT_SYMBOL(iterate_supers_type);
struct super_block *user_get_super(dev_t dev, bool excl)
{
struct super_block *sb;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (sb->s_dev == dev) {
bool locked;
sb->s_count++;
spin_unlock(&sb_lock);
/* still alive? */
locked = super_lock(sb, excl);
if (locked) {
if (sb->s_root)
return sb;
super_unlock(sb, excl);
}
/* nope, got unmounted */
spin_lock(&sb_lock);
__put_super(sb);
break;
}
}
spin_unlock(&sb_lock);
return NULL;
}
/**
* reconfigure_super - asks filesystem to change superblock parameters
* @fc: The superblock and configuration
*
* Alters the configuration parameters of a live superblock.
*/
int reconfigure_super(struct fs_context *fc)
{
struct super_block *sb = fc->root->d_sb;
int retval;
bool remount_ro = false;
bool remount_rw = false;
bool force = fc->sb_flags & SB_FORCE;
if (fc->sb_flags_mask & ~MS_RMT_MASK)
return -EINVAL;
if (sb->s_writers.frozen != SB_UNFROZEN)
return -EBUSY;
retval = security_sb_remount(sb, fc->security);
if (retval)
return retval;
if (fc->sb_flags_mask & SB_RDONLY) {
#ifdef CONFIG_BLOCK
if (!(fc->sb_flags & SB_RDONLY) && sb->s_bdev &&
bdev_read_only(sb->s_bdev))
return -EACCES;
#endif
remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb);
remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb);
}
if (remount_ro) {
if (!hlist_empty(&sb->s_pins)) {
super_unlock_excl(sb);
group_pin_kill(&sb->s_pins);
__super_lock_excl(sb);
if (!sb->s_root)
return 0;
if (sb->s_writers.frozen != SB_UNFROZEN)
return -EBUSY;
remount_ro = !sb_rdonly(sb);
}
}
shrink_dcache_sb(sb);
/* If we are reconfiguring to RDONLY and current sb is read/write,
* make sure there are no files open for writing.
*/
if (remount_ro) {
if (force) {
sb_start_ro_state_change(sb);
} else {
retval = sb_prepare_remount_readonly(sb);
if (retval)
return retval;
}
} else if (remount_rw) {
/*
* Protect filesystem's reconfigure code from writes from
* userspace until reconfigure finishes.
*/
sb_start_ro_state_change(sb);
}
if (fc->ops->reconfigure) {
retval = fc->ops->reconfigure(fc);
if (retval) {
if (!force)
goto cancel_readonly;
/* If forced remount, go ahead despite any errors */
WARN(1, "forced remount of a %s fs returned %i\n",
sb->s_type->name, retval);
}
}
WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) |
(fc->sb_flags & fc->sb_flags_mask)));
sb_end_ro_state_change(sb);
/*
* Some filesystems modify their metadata via some other path than the
* bdev buffer cache (eg. use a private mapping, or directories in
* pagecache, etc). Also file data modifications go via their own
* mappings. So If we try to mount readonly then copy the filesystem
* from bdev, we could get stale data, so invalidate it to give a best
* effort at coherency.
*/
if (remount_ro && sb->s_bdev)
invalidate_bdev(sb->s_bdev);
return 0;
cancel_readonly:
sb_end_ro_state_change(sb);
return retval;
}
static void do_emergency_remount_callback(struct super_block *sb)
{
bool locked = super_lock_excl(sb);
if (locked && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) {
struct fs_context *fc;
fc = fs_context_for_reconfigure(sb->s_root,
SB_RDONLY | SB_FORCE, SB_RDONLY);
if (!IS_ERR(fc)) {
if (parse_monolithic_mount_data(fc, NULL) == 0)
(void)reconfigure_super(fc);
put_fs_context(fc);
}
}
if (locked)
super_unlock_excl(sb);
}
static void do_emergency_remount(struct work_struct *work)
{
__iterate_supers(do_emergency_remount_callback);
kfree(work);
printk("Emergency Remount complete\n");
}
void emergency_remount(void)
{
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_emergency_remount);
schedule_work(work);
}
}
static void do_thaw_all_callback(struct super_block *sb)
{
bool locked = super_lock_excl(sb);
if (locked && sb->s_root) {
if (IS_ENABLED(CONFIG_BLOCK))
while (sb->s_bdev && !bdev_thaw(sb->s_bdev))
pr_warn("Emergency Thaw on %pg\n", sb->s_bdev);
thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE);
return;
}
if (locked)
super_unlock_excl(sb);
}
static void do_thaw_all(struct work_struct *work)
{
__iterate_supers(do_thaw_all_callback);
kfree(work);
printk(KERN_WARNING "Emergency Thaw complete\n");
}
/**
* emergency_thaw_all -- forcibly thaw every frozen filesystem
*
* Used for emergency unfreeze of all filesystems via SysRq
*/
void emergency_thaw_all(void)
{
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_thaw_all);
schedule_work(work);
}
}
static DEFINE_IDA(unnamed_dev_ida);
/**
* get_anon_bdev - Allocate a block device for filesystems which don't have one.
* @p: Pointer to a dev_t.
*
* Filesystems which don't use real block devices can call this function
* to allocate a virtual block device.
*
* Context: Any context. Frequently called while holding sb_lock.
* Return: 0 on success, -EMFILE if there are no anonymous bdevs left
* or -ENOMEM if memory allocation failed.
*/
int get_anon_bdev(dev_t *p)
{
int dev;
/*
* Many userspace utilities consider an FSID of 0 invalid.
* Always return at least 1 from get_anon_bdev.
*/
dev = ida_alloc_range(&unnamed_dev_ida, 1, (1 << MINORBITS) - 1,
GFP_ATOMIC);
if (dev == -ENOSPC)
dev = -EMFILE;
if (dev < 0)
return dev;
*p = MKDEV(0, dev);
return 0;
}
EXPORT_SYMBOL(get_anon_bdev);
void free_anon_bdev(dev_t dev)
{
ida_free(&unnamed_dev_ida, MINOR(dev));
}
EXPORT_SYMBOL(free_anon_bdev);
int set_anon_super(struct super_block *s, void *data)
{
return get_anon_bdev(&s->s_dev);
}
EXPORT_SYMBOL(set_anon_super);
void kill_anon_super(struct super_block *sb)
{
dev_t dev = sb->s_dev;
generic_shutdown_super(sb);
kill_super_notify(sb);
free_anon_bdev(dev);
}
EXPORT_SYMBOL(kill_anon_super);
void kill_litter_super(struct super_block *sb)
{
if (sb->s_root)
d_genocide(sb->s_root);
kill_anon_super(sb);
}
EXPORT_SYMBOL(kill_litter_super);
int set_anon_super_fc(struct super_block *sb, struct fs_context *fc)
{
return set_anon_super(sb, NULL);
}
EXPORT_SYMBOL(set_anon_super_fc);
static int test_keyed_super(struct super_block *sb, struct fs_context *fc)
{
return sb->s_fs_info == fc->s_fs_info;
}
static int test_single_super(struct super_block *s, struct fs_context *fc)
{
return 1;
}
static int vfs_get_super(struct fs_context *fc,
int (*test)(struct super_block *, struct fs_context *),
int (*fill_super)(struct super_block *sb,
struct fs_context *fc))
{
struct super_block *sb;
int err;
sb = sget_fc(fc, test, set_anon_super_fc);
if (IS_ERR(sb))
return PTR_ERR(sb);
if (!sb->s_root) {
err = fill_super(sb, fc);
if (err)
goto error;
sb->s_flags |= SB_ACTIVE;
}
fc->root = dget(sb->s_root);
return 0;
error:
deactivate_locked_super(sb);
return err;
}
int get_tree_nodev(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc))
{
return vfs_get_super(fc, NULL, fill_super);
}
EXPORT_SYMBOL(get_tree_nodev);
int get_tree_single(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc))
{
return vfs_get_super(fc, test_single_super, fill_super);
}
EXPORT_SYMBOL(get_tree_single);
int get_tree_keyed(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc),
void *key)
{
fc->s_fs_info = key;
return vfs_get_super(fc, test_keyed_super, fill_super);
}
EXPORT_SYMBOL(get_tree_keyed);
static int set_bdev_super(struct super_block *s, void *data)
{
s->s_dev = *(dev_t *)data;
return 0;
}
static int super_s_dev_set(struct super_block *s, struct fs_context *fc)
{
return set_bdev_super(s, fc->sget_key);
}
static int super_s_dev_test(struct super_block *s, struct fs_context *fc)
{
return !(s->s_iflags & SB_I_RETIRED) &&
s->s_dev == *(dev_t *)fc->sget_key;
}
/**
* sget_dev - Find or create a superblock by device number
* @fc: Filesystem context.
* @dev: device number
*
* Find or create a superblock using the provided device number that
* will be stored in fc->sget_key.
*
* If an extant superblock is matched, then that will be returned with
* an elevated reference count that the caller must transfer or discard.
*
* If no match is made, a new superblock will be allocated and basic
* initialisation will be performed (s_type, s_fs_info, s_id, s_dev will
* be set). The superblock will be published and it will be returned in
* a partially constructed state with SB_BORN and SB_ACTIVE as yet
* unset.
*
* Return: an existing or newly created superblock on success, an error
* pointer on failure.
*/
struct super_block *sget_dev(struct fs_context *fc, dev_t dev)
{
fc->sget_key = &dev;
return sget_fc(fc, super_s_dev_test, super_s_dev_set);
}
EXPORT_SYMBOL(sget_dev);
#ifdef CONFIG_BLOCK
/*
* Lock the superblock that is holder of the bdev. Returns the superblock
* pointer if we successfully locked the superblock and it is alive. Otherwise
* we return NULL and just unlock bdev->bd_holder_lock.
*
* The function must be called with bdev->bd_holder_lock and releases it.
*/
static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl)
__releases(&bdev->bd_holder_lock)
{
struct super_block *sb = bdev->bd_holder;
bool locked;
lockdep_assert_held(&bdev->bd_holder_lock);
lockdep_assert_not_held(&sb->s_umount);
lockdep_assert_not_held(&bdev->bd_disk->open_mutex);
/* Make sure sb doesn't go away from under us */
spin_lock(&sb_lock);
sb->s_count++;
spin_unlock(&sb_lock);
mutex_unlock(&bdev->bd_holder_lock);
locked = super_lock(sb, excl);
/*
* If the superblock wasn't already SB_DYING then we hold
* s_umount and can safely drop our temporary reference.
*/
put_super(sb);
if (!locked)
return NULL;
if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
super_unlock(sb, excl);
return NULL;
}
return sb;
}
static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
{
struct super_block *sb;
sb = bdev_super_lock(bdev, false);
if (!sb)
return;
if (!surprise)
sync_filesystem(sb);
shrink_dcache_sb(sb);
evict_inodes(sb);
if (sb->s_op->shutdown)
sb->s_op->shutdown(sb);
super_unlock_shared(sb);
}
static void fs_bdev_sync(struct block_device *bdev)
{
struct super_block *sb;
sb = bdev_super_lock(bdev, false);
if (!sb)
return;
sync_filesystem(sb);
super_unlock_shared(sb);
}
static struct super_block *get_bdev_super(struct block_device *bdev)
{
bool active = false;
struct super_block *sb;
sb = bdev_super_lock(bdev, true);
if (sb) {
active = atomic_inc_not_zero(&sb->s_active);
super_unlock_excl(sb);
}
if (!active)
return NULL;
return sb;
}
/**
* fs_bdev_freeze - freeze owning filesystem of block device
* @bdev: block device
*
* Freeze the filesystem that owns this block device if it is still
* active.
*
* A filesystem that owns multiple block devices may be frozen from each
* block device and won't be unfrozen until all block devices are
* unfrozen. Each block device can only freeze the filesystem once as we
* nest freezes for block devices in the block layer.
*
* Return: If the freeze was successful zero is returned. If the freeze
* failed a negative error code is returned.
*/
static int fs_bdev_freeze(struct block_device *bdev)
{
struct super_block *sb;
int error = 0;
lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
sb = get_bdev_super(bdev);
if (!sb)
return -EINVAL;
if (sb->s_op->freeze_super)
error = sb->s_op->freeze_super(sb,
FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
else
error = freeze_super(sb,
FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
if (!error)
error = sync_blockdev(bdev);
deactivate_super(sb);
return error;
}
/**
* fs_bdev_thaw - thaw owning filesystem of block device
* @bdev: block device
*
* Thaw the filesystem that owns this block device.
*
* A filesystem that owns multiple block devices may be frozen from each
* block device and won't be unfrozen until all block devices are
* unfrozen. Each block device can only freeze the filesystem once as we
* nest freezes for block devices in the block layer.
*
* Return: If the thaw was successful zero is returned. If the thaw
* failed a negative error code is returned. If this function
* returns zero it doesn't mean that the filesystem is unfrozen
* as it may have been frozen multiple times (kernel may hold a
* freeze or might be frozen from other block devices).
*/
static int fs_bdev_thaw(struct block_device *bdev)
{
struct super_block *sb;
int error;
lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
/*
* The block device may have been frozen before it was claimed by a
* filesystem. Concurrently another process might try to mount that
* frozen block device and has temporarily claimed the block device for
* that purpose causing a concurrent fs_bdev_thaw() to end up here. The
* mounter is already about to abort mounting because they still saw an
* elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
* NULL in that case.
*/
sb = get_bdev_super(bdev);
if (!sb)
return -EINVAL;
if (sb->s_op->thaw_super)
error = sb->s_op->thaw_super(sb,
FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
else
error = thaw_super(sb,
FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
deactivate_super(sb);
return error;
}
const struct blk_holder_ops fs_holder_ops = {
.mark_dead = fs_bdev_mark_dead,
.sync = fs_bdev_sync,
.freeze = fs_bdev_freeze,
.thaw = fs_bdev_thaw,
};
EXPORT_SYMBOL_GPL(fs_holder_ops);
int setup_bdev_super(struct super_block *sb, int sb_flags,
struct fs_context *fc)
{
blk_mode_t mode = sb_open_mode(sb_flags);
struct file *bdev_file;
struct block_device *bdev;
bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
if (IS_ERR(bdev_file)) {
if (fc)
errorf(fc, "%s: Can't open blockdev", fc->source);
return PTR_ERR(bdev_file);
}
bdev = file_bdev(bdev_file);
/*
* This really should be in blkdev_get_by_dev, but right now can't due
* to legacy issues that require us to allow opening a block device node
* writable from userspace even for a read-only block device.
*/
if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
bdev_fput(bdev_file);
return -EACCES;
}
/*
* It is enough to check bdev was not frozen before we set
* s_bdev as freezing will wait until SB_BORN is set.
*/
if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
if (fc)
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
bdev_fput(bdev_file);
return -EBUSY;
}
spin_lock(&sb_lock);
sb->s_bdev_file = bdev_file;
sb->s_bdev = bdev;
sb->s_bdi = bdi_get(bdev->bd_disk->bdi);
if (bdev_stable_writes(bdev))
sb->s_iflags |= SB_I_STABLE_WRITES;
spin_unlock(&sb_lock);
snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name,
sb->s_id);
sb_set_blocksize(sb, block_size(bdev));
return 0;
}
EXPORT_SYMBOL_GPL(setup_bdev_super);
/**
* get_tree_bdev_flags - Get a superblock based on a single block device
* @fc: The filesystem context holding the parameters
* @fill_super: Helper to initialise a new superblock
* @flags: GET_TREE_BDEV_* flags
*/
int get_tree_bdev_flags(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc), unsigned int flags)
{
struct super_block *s;
int error = 0;
dev_t dev;
if (!fc->source)
return invalf(fc, "No source specified");
error = lookup_bdev(fc->source, &dev);
if (error) {
if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP))
errorf(fc, "%s: Can't lookup blockdev", fc->source);
return error;
}
fc->sb_flags |= SB_NOSEC;
s = sget_dev(fc, dev);
if (IS_ERR(s))
return PTR_ERR(s);
if (s->s_root) {
/* Don't summarily change the RO/RW state. */
if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
warnf(fc, "%pg: Can't mount, would change RO state", s->s_bdev);
deactivate_locked_super(s);
return -EBUSY;
}
} else {
error = setup_bdev_super(s, fc->sb_flags, fc);
if (!error)
error = fill_super(s, fc);
if (error) {
deactivate_locked_super(s);
return error;
}
s->s_flags |= SB_ACTIVE;
}
BUG_ON(fc->root);
fc->root = dget(s->s_root);
return 0;
}
EXPORT_SYMBOL_GPL(get_tree_bdev_flags);
/**
* get_tree_bdev - Get a superblock based on a single block device
* @fc: The filesystem context holding the parameters
* @fill_super: Helper to initialise a new superblock
*/
int get_tree_bdev(struct fs_context *fc,
int (*fill_super)(struct super_block *,
struct fs_context *))
{
return get_tree_bdev_flags(fc, fill_super, 0);
}
EXPORT_SYMBOL(get_tree_bdev);
static int test_bdev_super(struct super_block *s, void *data)
{
return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data;
}
struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
struct super_block *s;
int error;
dev_t dev;
error = lookup_bdev(dev_name, &dev);
if (error)
return ERR_PTR(error);
flags |= SB_NOSEC;
s = sget(fs_type, test_bdev_super, set_bdev_super, flags, &dev);
if (IS_ERR(s))
return ERR_CAST(s);
if (s->s_root) {
if ((flags ^ s->s_flags) & SB_RDONLY) {
deactivate_locked_super(s);
return ERR_PTR(-EBUSY);
}
} else {
error = setup_bdev_super(s, flags, NULL);
if (!error)
error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= SB_ACTIVE;
}
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_bdev);
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
generic_shutdown_super(sb);
if (bdev) {
sync_blockdev(bdev);
bdev_fput(sb->s_bdev_file);
}
}
EXPORT_SYMBOL(kill_block_super);
#endif
struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
int error;
struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= SB_ACTIVE;
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_nodev);
/**
* vfs_get_tree - Get the mountable root
* @fc: The superblock configuration context.
*
* The filesystem is invoked to get or create a superblock which can then later
* be used for mounting. The filesystem places a pointer to the root to be
* used for mounting in @fc->root.
*/
int vfs_get_tree(struct fs_context *fc)
{
struct super_block *sb;
int error;
if (fc->root)
return -EBUSY;
/* Get the mountable root in fc->root, with a ref on the root and a ref
* on the superblock.
*/
error = fc->ops->get_tree(fc);
if (error < 0)
return error;
if (!fc->root) {
pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n",
fc->fs_type->name, error);
/* We don't know what the locking state of the superblock is -
* if there is a superblock.
*/
BUG();
}
sb = fc->root->d_sb;
WARN_ON(!sb->s_bdi);
/*
* super_wake() contains a memory barrier which also care of
* ordering for super_cache_count(). We place it before setting
* SB_BORN as the data dependency between the two functions is
* the superblock structure contents that we just set up, not
* the SB_BORN flag.
*/
super_wake(sb, SB_BORN);
error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL);
if (unlikely(error)) {
fc_drop_locked(fc);
return error;
}
/*
* filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
* but s_maxbytes was an unsigned long long for many releases. Throw
* this warning for a little while to try and catch filesystems that
* violate this rule.
*/
WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
"negative value (%lld)\n", fc->fs_type->name, sb->s_maxbytes);
return 0;
}
EXPORT_SYMBOL(vfs_get_tree);
/*
* Setup private BDI for given superblock. It gets automatically cleaned up
* in generic_shutdown_super().
*/
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
{
struct backing_dev_info *bdi;
int err;
va_list args;
bdi = bdi_alloc(NUMA_NO_NODE);
if (!bdi)
return -ENOMEM;
va_start(args, fmt);
err = bdi_register_va(bdi, fmt, args);
va_end(args);
if (err) {
bdi_put(bdi);
return err;
}
WARN_ON(sb->s_bdi != &noop_backing_dev_info);
sb->s_bdi = bdi;
sb->s_iflags |= SB_I_PERSB_BDI;
return 0;
}
EXPORT_SYMBOL(super_setup_bdi_name);
/*
* Setup private BDI for given superblock. I gets automatically cleaned up
* in generic_shutdown_super().
*/
int super_setup_bdi(struct super_block *sb)
{
static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
atomic_long_inc_return(&bdi_seq));
}
EXPORT_SYMBOL(super_setup_bdi);
/**
* sb_wait_write - wait until all writers to given file system finish
* @sb: the super for which we wait
* @level: type of writers we wait for (normal vs page fault)
*
* This function waits until there are no writers of given type to given file
* system.
*/
static void sb_wait_write(struct super_block *sb, int level)
{
percpu_down_write(sb->s_writers.rw_sem + level-1);
}
/*
* We are going to return to userspace and forget about these locks, the
* ownership goes to the caller of thaw_super() which does unlock().
*/
static void lockdep_sb_freeze_release(struct super_block *sb)
{
int level;
for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_);
}
/*
* Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb).
*/
static void lockdep_sb_freeze_acquire(struct super_block *sb)
{
int level;
for (level = 0; level < SB_FREEZE_LEVELS; ++level)
percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
}
static void sb_freeze_unlock(struct super_block *sb, int level)
{
for (level--; level >= 0; level--)
percpu_up_write(sb->s_writers.rw_sem + level);
}
static int wait_for_partially_frozen(struct super_block *sb)
{
int ret = 0;
do {
unsigned short old = sb->s_writers.frozen;
up_write(&sb->s_umount);
ret = wait_var_event_killable(&sb->s_writers.frozen,
sb->s_writers.frozen != old);
down_write(&sb->s_umount);
} while (ret == 0 &&
sb->s_writers.frozen != SB_UNFROZEN &&
sb->s_writers.frozen != SB_FREEZE_COMPLETE);
return ret;
}
#define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE)
#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST)
static inline int freeze_inc(struct super_block *sb, enum freeze_holder who)
{
WARN_ON_ONCE((who & ~FREEZE_FLAGS));
WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
if (who & FREEZE_HOLDER_KERNEL)
++sb->s_writers.freeze_kcount;
if (who & FREEZE_HOLDER_USERSPACE)
++sb->s_writers.freeze_ucount;
return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
}
static inline int freeze_dec(struct super_block *sb, enum freeze_holder who)
{
WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount) --sb->s_writers.freeze_kcount; if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount) --sb->s_writers.freeze_ucount;
return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
}
static inline bool may_freeze(struct super_block *sb, enum freeze_holder who)
{
WARN_ON_ONCE((who & ~FREEZE_FLAGS));
WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
if (who & FREEZE_HOLDER_KERNEL)
return (who & FREEZE_MAY_NEST) ||
sb->s_writers.freeze_kcount == 0;
if (who & FREEZE_HOLDER_USERSPACE)
return (who & FREEZE_MAY_NEST) ||
sb->s_writers.freeze_ucount == 0;
return false;
}
/**
* freeze_super - lock the filesystem and force it into a consistent state
* @sb: the super to lock
* @who: context that wants to freeze
*
* Syncs the super to make sure the filesystem is consistent and calls the fs's
* freeze_fs. Subsequent calls to this without first thawing the fs may return
* -EBUSY.
*
* @who should be:
* * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs;
* * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs.
* * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed.
*
* The @who argument distinguishes between the kernel and userspace trying to
* freeze the filesystem. Although there cannot be multiple kernel freezes or
* multiple userspace freezes in effect at any given time, the kernel and
* userspace can both hold a filesystem frozen. The filesystem remains frozen
* until there are no kernel or userspace freezes in effect.
*
* A filesystem may hold multiple devices and thus a filesystems may be
* frozen through the block layer via multiple block devices. In this
* case the request is marked as being allowed to nest by passing
* FREEZE_MAY_NEST. The filesystem remains frozen until all block
* devices are unfrozen. If multiple freezes are attempted without
* FREEZE_MAY_NEST -EBUSY will be returned.
*
* During this function, sb->s_writers.frozen goes through these values:
*
* SB_UNFROZEN: File system is normal, all writes progress as usual.
*
* SB_FREEZE_WRITE: The file system is in the process of being frozen. New
* writes should be blocked, though page faults are still allowed. We wait for
* all writes to complete and then proceed to the next stage.
*
* SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked
* but internal fs threads can still modify the filesystem (although they
* should not dirty new pages or inodes), writeback can run etc. After waiting
* for all running page faults we sync the filesystem which will clean all
* dirty pages and inodes (no new dirty pages or inodes can be created when
* sync is running).
*
* SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs
* modification are blocked (e.g. XFS preallocation truncation on inode
* reclaim). This is usually implemented by blocking new transactions for
* filesystems that have them and need this additional guard. After all
* internal writers are finished we call ->freeze_fs() to finish filesystem
* freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is
* mostly auxiliary for filesystems to verify they do not modify frozen fs.
*
* sb->s_writers.frozen is protected by sb->s_umount.
*
* Return: If the freeze was successful zero is returned. If the freeze
* failed a negative error code is returned.
*/
int freeze_super(struct super_block *sb, enum freeze_holder who)
{
int ret;
if (!super_lock_excl(sb)) {
WARN_ON_ONCE("Dying superblock while freezing!");
return -EINVAL;
}
atomic_inc(&sb->s_active);
retry:
if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) {
if (may_freeze(sb, who))
ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1);
else
ret = -EBUSY;
/* All freezers share a single active reference. */
deactivate_locked_super(sb);
return ret;
}
if (sb->s_writers.frozen != SB_UNFROZEN) {
ret = wait_for_partially_frozen(sb);
if (ret) {
deactivate_locked_super(sb);
return ret;
}
goto retry;
}
if (sb_rdonly(sb)) {
/* Nothing to do really... */
WARN_ON_ONCE(freeze_inc(sb, who) > 1);
sb->s_writers.frozen = SB_FREEZE_COMPLETE;
wake_up_var(&sb->s_writers.frozen);
super_unlock_excl(sb);
return 0;
}
sb->s_writers.frozen = SB_FREEZE_WRITE;
/* Release s_umount to preserve sb_start_write -> s_umount ordering */
super_unlock_excl(sb);
sb_wait_write(sb, SB_FREEZE_WRITE);
__super_lock_excl(sb);
/* Now we go and block page faults... */
sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
/* All writers are done so after syncing there won't be dirty data */
ret = sync_filesystem(sb);
if (ret) {
sb->s_writers.frozen = SB_UNFROZEN;
sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT);
wake_up_var(&sb->s_writers.frozen);
deactivate_locked_super(sb);
return ret;
}
/* Now wait for internal filesystem counter */
sb->s_writers.frozen = SB_FREEZE_FS;
sb_wait_write(sb, SB_FREEZE_FS);
if (sb->s_op->freeze_fs) {
ret = sb->s_op->freeze_fs(sb);
if (ret) {
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_writers.frozen = SB_UNFROZEN;
sb_freeze_unlock(sb, SB_FREEZE_FS);
wake_up_var(&sb->s_writers.frozen);
deactivate_locked_super(sb);
return ret;
}
}
/*
* For debugging purposes so that fs can warn if it sees write activity
* when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
*/
WARN_ON_ONCE(freeze_inc(sb, who) > 1);
sb->s_writers.frozen = SB_FREEZE_COMPLETE;
wake_up_var(&sb->s_writers.frozen);
lockdep_sb_freeze_release(sb);
super_unlock_excl(sb);
return 0;
}
EXPORT_SYMBOL(freeze_super);
/*
* Undoes the effect of a freeze_super_locked call. If the filesystem is
* frozen both by userspace and the kernel, a thaw call from either source
* removes that state without releasing the other state or unlocking the
* filesystem.
*/
static int thaw_super_locked(struct super_block *sb, enum freeze_holder who)
{
int error = -EINVAL;
if (sb->s_writers.frozen != SB_FREEZE_COMPLETE)
goto out_unlock;
/*
* All freezers share a single active reference.
* So just unlock in case there are any left.
*/
if (freeze_dec(sb, who))
goto out_unlock;
if (sb_rdonly(sb)) {
sb->s_writers.frozen = SB_UNFROZEN;
wake_up_var(&sb->s_writers.frozen);
goto out_deactivate;
}
lockdep_sb_freeze_acquire(sb);
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
if (error) { pr_err("VFS: Filesystem thaw failed\n");
freeze_inc(sb, who);
lockdep_sb_freeze_release(sb);
goto out_unlock;
}
}
sb->s_writers.frozen = SB_UNFROZEN;
wake_up_var(&sb->s_writers.frozen);
sb_freeze_unlock(sb, SB_FREEZE_FS);
out_deactivate:
deactivate_locked_super(sb);
return 0;
out_unlock:
super_unlock_excl(sb);
return error;
}
/**
* thaw_super -- unlock filesystem
* @sb: the super to thaw
* @who: context that wants to freeze
*
* Unlocks the filesystem and marks it writeable again after freeze_super()
* if there are no remaining freezes on the filesystem.
*
* @who should be:
* * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs;
* * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs.
* * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed
*
* A filesystem may hold multiple devices and thus a filesystems may
* have been frozen through the block layer via multiple block devices.
* The filesystem remains frozen until all block devices are unfrozen.
*/
int thaw_super(struct super_block *sb, enum freeze_holder who)
{
if (!super_lock_excl(sb)) {
WARN_ON_ONCE("Dying superblock while thawing!");
return -EINVAL;
}
return thaw_super_locked(sb, who);
}
EXPORT_SYMBOL(thaw_super);
/*
* Create workqueue for deferred direct IO completions. We allocate the
* workqueue when it's first needed. This avoids creating workqueue for
* filesystems that don't need it and also allows us to create the workqueue
* late enough so the we can include s_id in the name of the workqueue.
*/
int sb_init_dio_done_wq(struct super_block *sb)
{
struct workqueue_struct *old;
struct workqueue_struct *wq = alloc_workqueue("dio/%s",
WQ_MEM_RECLAIM, 0,
sb->s_id);
if (!wq)
return -ENOMEM;
/*
* This has to be atomic as more DIOs can race to create the workqueue
*/
old = cmpxchg(&sb->s_dio_done_wq, NULL, wq);
/* Someone created workqueue before us? Free ours... */
if (old)
destroy_workqueue(wq);
return 0;
}
EXPORT_SYMBOL_GPL(sb_init_dio_done_wq);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <linux/arm-smccc.h>
#include <linux/preempt.h>
#include <linux/kvm_host.h>
#include <linux/uaccess.h>
#include <linux/wait.h>
#include <asm/cputype.h>
#include <asm/kvm_emulate.h>
#include <kvm/arm_psci.h>
#include <kvm/arm_hypercalls.h>
/*
* This is an implementation of the Power State Coordination Interface
* as described in ARM document number ARM DEN 0022A.
*/
#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
static unsigned long psci_affinity_mask(unsigned long affinity_level)
{
if (affinity_level <= 3)
return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
return 0;
}
static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
{
/*
* NOTE: For simplicity, we make VCPU suspend emulation to be
* same-as WFI (Wait-for-interrupt) emulation.
*
* This means for KVM the wakeup events are interrupts and
* this is consistent with intended use of StateID as described
* in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
*
* Further, we also treat power-down request to be same as
* stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
* specification (ARM DEN 0022A). This means all suspend states
* for KVM will preserve the register state.
*/
kvm_vcpu_wfi(vcpu);
return PSCI_RET_SUCCESS;
}
static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
unsigned long affinity)
{
return !(affinity & ~MPIDR_HWID_BITMASK);
}
static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
{
struct vcpu_reset_state *reset_state;
struct kvm *kvm = source_vcpu->kvm;
struct kvm_vcpu *vcpu = NULL;
int ret = PSCI_RET_SUCCESS;
unsigned long cpu_id;
cpu_id = smccc_get_arg1(source_vcpu);
if (!kvm_psci_valid_affinity(source_vcpu, cpu_id))
return PSCI_RET_INVALID_PARAMS;
vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
/*
* Make sure the caller requested a valid CPU and that the CPU is
* turned off.
*/
if (!vcpu)
return PSCI_RET_INVALID_PARAMS;
spin_lock(&vcpu->arch.mp_state_lock);
if (!kvm_arm_vcpu_stopped(vcpu)) {
if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
ret = PSCI_RET_ALREADY_ON;
else
ret = PSCI_RET_INVALID_PARAMS;
goto out_unlock;
}
reset_state = &vcpu->arch.reset_state;
reset_state->pc = smccc_get_arg2(source_vcpu);
/* Propagate caller endianness */
reset_state->be = kvm_vcpu_is_be(source_vcpu);
/*
* NOTE: We always update r0 (or x0) because for PSCI v0.1
* the general purpose registers are undefined upon CPU_ON.
*/
reset_state->r0 = smccc_get_arg3(source_vcpu);
reset_state->reset = true;
kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
/*
* Make sure the reset request is observed if the RUNNABLE mp_state is
* observed.
*/
smp_wmb();
WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE);
kvm_vcpu_wake_up(vcpu);
out_unlock:
spin_unlock(&vcpu->arch.mp_state_lock);
return ret;
}
static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
{
int matching_cpus = 0;
unsigned long i, mpidr;
unsigned long target_affinity;
unsigned long target_affinity_mask;
unsigned long lowest_affinity_level;
struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tmp;
target_affinity = smccc_get_arg1(vcpu);
lowest_affinity_level = smccc_get_arg2(vcpu);
if (!kvm_psci_valid_affinity(vcpu, target_affinity))
return PSCI_RET_INVALID_PARAMS;
/* Determine target affinity mask */
target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
if (!target_affinity_mask)
return PSCI_RET_INVALID_PARAMS;
/* Ignore other bits of target affinity */
target_affinity &= target_affinity_mask;
/*
* If one or more VCPU matching target affinity are running
* then ON else OFF
*/
kvm_for_each_vcpu(i, tmp, kvm) { mpidr = kvm_vcpu_get_mpidr_aff(tmp); if ((mpidr & target_affinity_mask) == target_affinity) {
matching_cpus++;
if (!kvm_arm_vcpu_stopped(tmp))
return PSCI_0_2_AFFINITY_LEVEL_ON;
}
}
if (!matching_cpus)
return PSCI_RET_INVALID_PARAMS;
return PSCI_0_2_AFFINITY_LEVEL_OFF;
}
static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
{
unsigned long i;
struct kvm_vcpu *tmp;
/*
* The KVM ABI specifies that a system event exit may call KVM_RUN
* again and may perform shutdown/reboot at a later time that when the
* actual request is made. Since we are implementing PSCI and a
* caller of PSCI reboot and shutdown expects that the system shuts
* down or reboots immediately, let's make sure that VCPUs are not run
* after this call is handled and before the VCPUs have been
* re-initialized.
*/
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
spin_lock(&tmp->arch.mp_state_lock);
WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
spin_unlock(&tmp->arch.mp_state_lock);
}
kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
vcpu->run->system_event.type = type;
vcpu->run->system_event.ndata = 1;
vcpu->run->system_event.data[0] = flags;
vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
}
static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
{
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0);
}
static void kvm_psci_system_off2(struct kvm_vcpu *vcpu)
{
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN,
KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2);
}
static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
{
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0);
}
static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu)
{
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET,
KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2);
}
static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
memset(&run->system_event, 0, sizeof(vcpu->run->system_event));
run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND;
run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
}
static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
{
int i;
/*
* Zero the input registers' upper 32 bits. They will be fully
* zeroed on exit, so we're fine changing them in place.
*/
for (i = 1; i < 4; i++)
vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i)));
}
static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn)
{
/*
* Prevent 32 bit guests from calling 64 bit PSCI functions.
*/
if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu))
return PSCI_RET_NOT_SUPPORTED;
return 0;
}
static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
{
u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
int ret = 1;
switch (psci_fn) {
case PSCI_0_2_FN_PSCI_VERSION:
/*
* Bits[31:16] = Major Version = 0
* Bits[15:0] = Minor Version = 2
*/
val = KVM_ARM_PSCI_0_2;
break;
case PSCI_0_2_FN_CPU_SUSPEND:
case PSCI_0_2_FN64_CPU_SUSPEND:
val = kvm_psci_vcpu_suspend(vcpu);
break;
case PSCI_0_2_FN_CPU_OFF:
kvm_arm_vcpu_power_off(vcpu);
val = PSCI_RET_SUCCESS;
break;
case PSCI_0_2_FN_CPU_ON:
kvm_psci_narrow_to_32bit(vcpu);
fallthrough;
case PSCI_0_2_FN64_CPU_ON:
val = kvm_psci_vcpu_on(vcpu);
break;
case PSCI_0_2_FN_AFFINITY_INFO:
kvm_psci_narrow_to_32bit(vcpu);
fallthrough;
case PSCI_0_2_FN64_AFFINITY_INFO:
val = kvm_psci_vcpu_affinity_info(vcpu);
break;
case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
/*
* Trusted OS is MP hence does not require migration
* or
* Trusted OS is not present
*/
val = PSCI_0_2_TOS_MP;
break;
case PSCI_0_2_FN_SYSTEM_OFF:
kvm_psci_system_off(vcpu);
/*
* We shouldn't be going back to guest VCPU after
* receiving SYSTEM_OFF request.
*
* If user space accidentally/deliberately resumes
* guest VCPU after SYSTEM_OFF request then guest
* VCPU should see internal failure from PSCI return
* value. To achieve this, we preload r0 (or x0) with
* PSCI return value INTERNAL_FAILURE.
*/
val = PSCI_RET_INTERNAL_FAILURE;
ret = 0;
break;
case PSCI_0_2_FN_SYSTEM_RESET:
kvm_psci_system_reset(vcpu);
/*
* Same reason as SYSTEM_OFF for preloading r0 (or x0)
* with PSCI return value INTERNAL_FAILURE.
*/
val = PSCI_RET_INTERNAL_FAILURE;
ret = 0;
break;
default:
val = PSCI_RET_NOT_SUPPORTED;
break;
}
smccc_set_retval(vcpu, val, 0, 0, 0);
return ret;
}
static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
{
unsigned long val = PSCI_RET_NOT_SUPPORTED;
u32 psci_fn = smccc_get_function(vcpu);
struct kvm *kvm = vcpu->kvm;
u32 arg;
int ret = 1;
switch(psci_fn) {
case PSCI_0_2_FN_PSCI_VERSION:
val = PSCI_VERSION(1, minor);
break;
case PSCI_1_0_FN_PSCI_FEATURES:
arg = smccc_get_arg1(vcpu);
val = kvm_psci_check_allowed_function(vcpu, arg);
if (val)
break;
val = PSCI_RET_NOT_SUPPORTED;
switch(arg) {
case PSCI_0_2_FN_PSCI_VERSION:
case PSCI_0_2_FN_CPU_SUSPEND:
case PSCI_0_2_FN64_CPU_SUSPEND:
case PSCI_0_2_FN_CPU_OFF:
case PSCI_0_2_FN_CPU_ON:
case PSCI_0_2_FN64_CPU_ON:
case PSCI_0_2_FN_AFFINITY_INFO:
case PSCI_0_2_FN64_AFFINITY_INFO:
case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
case PSCI_0_2_FN_SYSTEM_OFF:
case PSCI_0_2_FN_SYSTEM_RESET:
case PSCI_1_0_FN_PSCI_FEATURES:
case ARM_SMCCC_VERSION_FUNC_ID:
val = 0;
break;
case PSCI_1_0_FN_SYSTEM_SUSPEND:
case PSCI_1_0_FN64_SYSTEM_SUSPEND:
if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags))
val = 0;
break;
case PSCI_1_1_FN_SYSTEM_RESET2:
case PSCI_1_1_FN64_SYSTEM_RESET2:
if (minor >= 1)
val = 0;
break;
case PSCI_1_3_FN_SYSTEM_OFF2:
case PSCI_1_3_FN64_SYSTEM_OFF2:
if (minor >= 3)
val = PSCI_1_3_OFF_TYPE_HIBERNATE_OFF;
break;
}
break;
case PSCI_1_0_FN_SYSTEM_SUSPEND:
kvm_psci_narrow_to_32bit(vcpu);
fallthrough;
case PSCI_1_0_FN64_SYSTEM_SUSPEND:
/*
* Return directly to userspace without changing the vCPU's
* registers. Userspace depends on reading the SMCCC parameters
* to implement SYSTEM_SUSPEND.
*/
if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) { kvm_psci_system_suspend(vcpu);
return 0;
}
break;
case PSCI_1_1_FN_SYSTEM_RESET2:
kvm_psci_narrow_to_32bit(vcpu);
fallthrough;
case PSCI_1_1_FN64_SYSTEM_RESET2:
if (minor >= 1) {
arg = smccc_get_arg1(vcpu);
if (arg <= PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET ||
arg >= PSCI_1_1_RESET_TYPE_VENDOR_START) {
kvm_psci_system_reset2(vcpu);
vcpu_set_reg(vcpu, 0, PSCI_RET_INTERNAL_FAILURE);
return 0;
}
val = PSCI_RET_INVALID_PARAMS;
break;
}
break;
case PSCI_1_3_FN_SYSTEM_OFF2:
kvm_psci_narrow_to_32bit(vcpu);
fallthrough;
case PSCI_1_3_FN64_SYSTEM_OFF2:
if (minor < 3)
break;
arg = smccc_get_arg1(vcpu);
/*
* SYSTEM_OFF2 defaults to HIBERNATE_OFF if arg1 is zero. arg2
* must be zero.
*/
if ((arg && arg != PSCI_1_3_OFF_TYPE_HIBERNATE_OFF) ||
smccc_get_arg2(vcpu) != 0) {
val = PSCI_RET_INVALID_PARAMS;
break;
}
kvm_psci_system_off2(vcpu);
/*
* We shouldn't be going back to the guest after receiving a
* SYSTEM_OFF2 request. Preload a return value of
* INTERNAL_FAILURE should userspace ignore the exit and resume
* the vCPU.
*/
val = PSCI_RET_INTERNAL_FAILURE;
ret = 0;
break;
default:
return kvm_psci_0_2_call(vcpu);
}
smccc_set_retval(vcpu, val, 0, 0, 0);
return ret;
}
static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
{
u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
switch (psci_fn) {
case KVM_PSCI_FN_CPU_OFF:
kvm_arm_vcpu_power_off(vcpu);
val = PSCI_RET_SUCCESS;
break;
case KVM_PSCI_FN_CPU_ON:
val = kvm_psci_vcpu_on(vcpu);
break;
default:
val = PSCI_RET_NOT_SUPPORTED;
break;
}
smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
/**
* kvm_psci_call - handle PSCI call if r0 value is in range
* @vcpu: Pointer to the VCPU struct
*
* Handle PSCI calls from guests through traps from HVC instructions.
* The calling convention is similar to SMC calls to the secure world
* where the function number is placed in r0.
*
* This function returns: > 0 (success), 0 (success but exit to user
* space), and < 0 (errors)
*
* Errors:
* -EINVAL: Unrecognized PSCI function
*/
int kvm_psci_call(struct kvm_vcpu *vcpu)
{
u32 psci_fn = smccc_get_function(vcpu);
int version = kvm_psci_version(vcpu);
unsigned long val;
val = kvm_psci_check_allowed_function(vcpu, psci_fn);
if (val) {
smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
switch (version) {
case KVM_ARM_PSCI_1_3:
return kvm_psci_1_x_call(vcpu, 3);
case KVM_ARM_PSCI_1_2:
return kvm_psci_1_x_call(vcpu, 2);
case KVM_ARM_PSCI_1_1:
return kvm_psci_1_x_call(vcpu, 1);
case KVM_ARM_PSCI_1_0:
return kvm_psci_1_x_call(vcpu, 0);
case KVM_ARM_PSCI_0_2:
return kvm_psci_0_2_call(vcpu);
case KVM_ARM_PSCI_0_1:
return kvm_psci_0_1_call(vcpu);
default:
WARN_ONCE(1, "Unknown PSCI version %d", version);
smccc_set_retval(vcpu, SMCCC_RET_NOT_SUPPORTED, 0, 0, 0);
return 1;
}
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* FP/SIMD context switching and fault handling
*
* Copyright (C) 2012 ARM Ltd.
* Author: Catalin Marinas <catalin.marinas@arm.com>
*/
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bottom_half.h>
#include <linux/bug.h>
#include <linux/cache.h>
#include <linux/compat.h>
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/ctype.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/prctl.h>
#include <linux/preempt.h>
#include <linux/ptrace.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/sysctl.h>
#include <linux/swab.h>
#include <asm/esr.h>
#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/neon.h>
#include <asm/processor.h>
#include <asm/simd.h>
#include <asm/sigcontext.h>
#include <asm/sysreg.h>
#include <asm/traps.h>
#include <asm/virt.h>
#define FPEXC_IOF (1 << 0)
#define FPEXC_DZF (1 << 1)
#define FPEXC_OFF (1 << 2)
#define FPEXC_UFF (1 << 3)
#define FPEXC_IXF (1 << 4)
#define FPEXC_IDF (1 << 7)
/*
* (Note: in this discussion, statements about FPSIMD apply equally to SVE.)
*
* In order to reduce the number of times the FPSIMD state is needlessly saved
* and restored, we need to keep track of two things:
* (a) for each task, we need to remember which CPU was the last one to have
* the task's FPSIMD state loaded into its FPSIMD registers;
* (b) for each CPU, we need to remember which task's userland FPSIMD state has
* been loaded into its FPSIMD registers most recently, or whether it has
* been used to perform kernel mode NEON in the meantime.
*
* For (a), we add a fpsimd_cpu field to thread_struct, which gets updated to
* the id of the current CPU every time the state is loaded onto a CPU. For (b),
* we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
* address of the userland FPSIMD state of the task that was loaded onto the CPU
* the most recently, or NULL if kernel mode NEON has been performed after that.
*
* With this in place, we no longer have to restore the next FPSIMD state right
* when switching between tasks. Instead, we can defer this check to userland
* resume, at which time we verify whether the CPU's fpsimd_last_state and the
* task's fpsimd_cpu are still mutually in sync. If this is the case, we
* can omit the FPSIMD restore.
*
* As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
* indicate whether or not the userland FPSIMD state of the current task is
* present in the registers. The flag is set unless the FPSIMD registers of this
* CPU currently contain the most recent userland FPSIMD state of the current
* task. If the task is behaving as a VMM, then this is will be managed by
* KVM which will clear it to indicate that the vcpu FPSIMD state is currently
* loaded on the CPU, allowing the state to be saved if a FPSIMD-aware
* softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and
* flag the register state as invalid.
*
* In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be
* called from softirq context, which will save the task's FPSIMD context back
* to task_struct. To prevent this from racing with the manipulation of the
* task's FPSIMD state from task context and thereby corrupting the state, it
* is necessary to protect any manipulation of a task's fpsimd_state or
* TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend
* softirq servicing entirely until put_cpu_fpsimd_context() is called.
*
* For a certain task, the sequence may look something like this:
* - the task gets scheduled in; if both the task's fpsimd_cpu field
* contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
* variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
* cleared, otherwise it is set;
*
* - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
* userland FPSIMD state is copied from memory to the registers, the task's
* fpsimd_cpu field is set to the id of the current CPU, the current
* CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
* TIF_FOREIGN_FPSTATE flag is cleared;
*
* - the task executes an ordinary syscall; upon return to userland, the
* TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
* restored;
*
* - the task executes a syscall which executes some NEON instructions; this is
* preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
* register contents to memory, clears the fpsimd_last_state per-cpu variable
* and sets the TIF_FOREIGN_FPSTATE flag;
*
* - the task gets preempted after kernel_neon_end() is called; as we have not
* returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
* whatever is in the FPSIMD registers is not saved to memory, but discarded.
*/
static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
__ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
#ifdef CONFIG_ARM64_SVE
[ARM64_VEC_SVE] = {
.type = ARM64_VEC_SVE,
.name = "SVE",
.min_vl = SVE_VL_MIN,
.max_vl = SVE_VL_MIN,
.max_virtualisable_vl = SVE_VL_MIN,
},
#endif
#ifdef CONFIG_ARM64_SME
[ARM64_VEC_SME] = {
.type = ARM64_VEC_SME,
.name = "SME",
},
#endif
};
static unsigned int vec_vl_inherit_flag(enum vec_type type)
{
switch (type) {
case ARM64_VEC_SVE:
return TIF_SVE_VL_INHERIT;
case ARM64_VEC_SME:
return TIF_SME_VL_INHERIT;
default:
WARN_ON_ONCE(1);
return 0;
}
}
struct vl_config {
int __default_vl; /* Default VL for tasks */
};
static struct vl_config vl_config[ARM64_VEC_MAX];
static inline int get_default_vl(enum vec_type type)
{
return READ_ONCE(vl_config[type].__default_vl);
}
#ifdef CONFIG_ARM64_SVE
static inline int get_sve_default_vl(void)
{
return get_default_vl(ARM64_VEC_SVE);
}
static inline void set_default_vl(enum vec_type type, int val)
{
WRITE_ONCE(vl_config[type].__default_vl, val);
}
static inline void set_sve_default_vl(int val)
{
set_default_vl(ARM64_VEC_SVE, val);
}
static void __percpu *efi_sve_state;
#else /* ! CONFIG_ARM64_SVE */
/* Dummy declaration for code that will be optimised out: */
extern void __percpu *efi_sve_state;
#endif /* ! CONFIG_ARM64_SVE */
#ifdef CONFIG_ARM64_SME
static int get_sme_default_vl(void)
{
return get_default_vl(ARM64_VEC_SME);
}
static void set_sme_default_vl(int val)
{
set_default_vl(ARM64_VEC_SME, val);
}
static void sme_free(struct task_struct *);
#else
static inline void sme_free(struct task_struct *t) { }
#endif
static void fpsimd_bind_task_to_cpu(void);
/*
* Claim ownership of the CPU FPSIMD context for use by the calling context.
*
* The caller may freely manipulate the FPSIMD context metadata until
* put_cpu_fpsimd_context() is called.
*
* On RT kernels local_bh_disable() is not sufficient because it only
* serializes soft interrupt related sections via a local lock, but stays
* preemptible. Disabling preemption is the right choice here as bottom
* half processing is always in thread context on RT kernels so it
* implicitly prevents bottom half processing as well.
*/
static void get_cpu_fpsimd_context(void)
{
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
local_bh_disable();
else
preempt_disable();
}
/*
* Release the CPU FPSIMD context.
*
* Must be called from a context in which get_cpu_fpsimd_context() was
* previously called, with no call to put_cpu_fpsimd_context() in the
* meantime.
*/
static void put_cpu_fpsimd_context(void)
{
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
local_bh_enable();
else
preempt_enable();
}
unsigned int task_get_vl(const struct task_struct *task, enum vec_type type)
{ return task->thread.vl[type];
}
void task_set_vl(struct task_struct *task, enum vec_type type,
unsigned long vl)
{
task->thread.vl[type] = vl;
}
unsigned int task_get_vl_onexec(const struct task_struct *task,
enum vec_type type)
{
return task->thread.vl_onexec[type];
}
void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
unsigned long vl)
{
task->thread.vl_onexec[type] = vl;
}
/*
* TIF_SME controls whether a task can use SME without trapping while
* in userspace, when TIF_SME is set then we must have storage
* allocated in sve_state and sme_state to store the contents of both ZA
* and the SVE registers for both streaming and non-streaming modes.
*
* If both SVCR.ZA and SVCR.SM are disabled then at any point we
* may disable TIF_SME and reenable traps.
*/
/*
* TIF_SVE controls whether a task can use SVE without trapping while
* in userspace, and also (together with TIF_SME) the way a task's
* FPSIMD/SVE state is stored in thread_struct.
*
* The kernel uses this flag to track whether a user task is actively
* using SVE, and therefore whether full SVE register state needs to
* be tracked. If not, the cheaper FPSIMD context handling code can
* be used instead of the more costly SVE equivalents.
*
* * TIF_SVE or SVCR.SM set:
*
* The task can execute SVE instructions while in userspace without
* trapping to the kernel.
*
* During any syscall, the kernel may optionally clear TIF_SVE and
* discard the vector state except for the FPSIMD subset.
*
* * TIF_SVE clear:
*
* An attempt by the user task to execute an SVE instruction causes
* do_sve_acc() to be called, which does some preparation and then
* sets TIF_SVE.
*
* During any syscall, the kernel may optionally clear TIF_SVE and
* discard the vector state except for the FPSIMD subset.
*
* The data will be stored in one of two formats:
*
* * FPSIMD only - FP_STATE_FPSIMD:
*
* When the FPSIMD only state stored task->thread.fp_type is set to
* FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in
* task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are
* logically zero but not stored anywhere; P0-P15 and FFR are not
* stored and have unspecified values from userspace's point of
* view. For hygiene purposes, the kernel zeroes them on next use,
* but userspace is discouraged from relying on this.
*
* task->thread.sve_state does not need to be non-NULL, valid or any
* particular size: it must not be dereferenced and any data stored
* there should be considered stale and not referenced.
*
* * SVE state - FP_STATE_SVE:
*
* When the full SVE state is stored task->thread.fp_type is set to
* FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the
* corresponding Zn), P0-P15 and FFR are encoded in in
* task->thread.sve_state, formatted appropriately for vector
* length task->thread.sve_vl or, if SVCR.SM is set,
* task->thread.sme_vl. The storage for the vector registers in
* task->thread.uw.fpsimd_state should be ignored.
*
* task->thread.sve_state must point to a valid buffer at least
* sve_state_size(task) bytes in size. The data stored in
* task->thread.uw.fpsimd_state.vregs should be considered stale
* and not referenced.
*
* * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state
* irrespective of whether TIF_SVE is clear or set, since these are
* not vector length dependent.
*/
/*
* Update current's FPSIMD/SVE registers from thread_struct.
*
* This function should be called only when the FPSIMD/SVE state in
* thread_struct is known to be up to date, when preparing to enter
* userspace.
*/
static void task_fpsimd_load(void)
{
bool restore_sve_regs = false;
bool restore_ffr;
WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); if (system_supports_fpmr()) write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
if (test_and_clear_thread_flag(TIF_SVE)) sve_user_disable();
break;
case FP_STATE_SVE:
if (!thread_sm_enabled(¤t->thread) &&
!WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE))) sve_user_enable(); if (test_thread_flag(TIF_SVE)) sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
restore_sve_regs = true;
restore_ffr = true;
break;
default:
/*
* This indicates either a bug in
* fpsimd_save_user_state() or memory corruption, we
* should always record an explicit format
* when we save. We always at least have the
* memory allocated for FPSIMD registers so
* try that and hope for the best.
*/
WARN_ON_ONCE(1);
clear_thread_flag(TIF_SVE);
break;
}
}
/* Restore SME, override SVE register configuration if needed */
if (system_supports_sme()) {
unsigned long sme_vl = task_get_sme_vl(current);
/* Ensure VL is set up for restoring data */
if (test_thread_flag(TIF_SME))
sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
write_sysreg_s(current->thread.svcr, SYS_SVCR);
if (thread_za_enabled(¤t->thread))
sme_load_state(current->thread.sme_state,
system_supports_sme2());
if (thread_sm_enabled(¤t->thread))
restore_ffr = system_supports_fa64();
}
if (restore_sve_regs) {
WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
sve_load_state(sve_pffr(¤t->thread),
¤t->thread.uw.fpsimd_state.fpsr,
restore_ffr);
} else {
WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD);
fpsimd_load_state(¤t->thread.uw.fpsimd_state);
}
}
/*
* Ensure FPSIMD/SVE storage in memory for the loaded context is up to
* date with respect to the CPU registers. Note carefully that the
* current context is the context last bound to the CPU stored in
* last, if KVM is involved this may be the guest VM context rather
* than the host thread for the VM pointed to by current. This means
* that we must always reference the state storage via last rather
* than via current, if we are saving KVM state then it will have
* ensured that the type of registers to save is set in last->to_save.
*/
static void fpsimd_save_user_state(void)
{
struct cpu_fp_state const *last =
this_cpu_ptr(&fpsimd_last_state);
/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
bool save_sve_regs = false;
bool save_ffr;
unsigned int vl;
WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); if (test_thread_flag(TIF_FOREIGN_FPSTATE))
return;
if (system_supports_fpmr()) *(last->fpmr) = read_sysreg_s(SYS_FPMR);
/*
* If a task is in a syscall the ABI allows us to only
* preserve the state shared with FPSIMD so don't bother
* saving the full SVE state in that case.
*/
if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) && !in_syscall(current_pt_regs())) ||
last->to_save == FP_STATE_SVE) {
save_sve_regs = true;
save_ffr = true;
vl = last->sve_vl;
}
if (system_supports_sme()) {
u64 *svcr = last->svcr;
*svcr = read_sysreg_s(SYS_SVCR);
if (*svcr & SVCR_ZA_MASK)
sme_save_state(last->sme_state,
system_supports_sme2());
/* If we are in streaming mode override regular SVE. */
if (*svcr & SVCR_SM_MASK) {
save_sve_regs = true;
save_ffr = system_supports_fa64();
vl = last->sme_vl;
}
}
if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
/* Get the configured VL from RDVL, will account for SM */
if (WARN_ON(sve_get_vl() != vl)) {
/*
* Can't save the user regs, so current would
* re-enter user with corrupt state.
* There's no way to recover, so kill it:
*/
force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
return;
}
sve_save_state((char *)last->sve_state +
sve_ffr_offset(vl),
&last->st->fpsr, save_ffr);
*last->fp_type = FP_STATE_SVE;
} else {
fpsimd_save_state(last->st);
*last->fp_type = FP_STATE_FPSIMD;
}
}
/*
* All vector length selection from userspace comes through here.
* We're on a slow path, so some sanity-checks are included.
* If things go wrong there's a bug somewhere, but try to fall back to a
* safe choice.
*/
static unsigned int find_supported_vector_length(enum vec_type type,
unsigned int vl)
{
struct vl_info *info = &vl_info[type];
int bit;
int max_vl = info->max_vl;
if (WARN_ON(!sve_vl_valid(vl)))
vl = info->min_vl;
if (WARN_ON(!sve_vl_valid(max_vl)))
max_vl = info->min_vl;
if (vl > max_vl)
vl = max_vl;
if (vl < info->min_vl)
vl = info->min_vl;
bit = find_next_bit(info->vq_map, SVE_VQ_MAX,
__vq_to_bit(sve_vq_from_vl(vl)));
return sve_vl_from_vq(__bit_to_vq(bit));
}
#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
static int vec_proc_do_default_vl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct vl_info *info = table->extra1;
enum vec_type type = info->type;
int ret;
int vl = get_default_vl(type);
struct ctl_table tmp_table = {
.data = &vl,
.maxlen = sizeof(vl),
};
ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
/* Writing -1 has the special meaning "set to max": */
if (vl == -1)
vl = info->max_vl;
if (!sve_vl_valid(vl))
return -EINVAL;
set_default_vl(type, find_supported_vector_length(type, vl));
return 0;
}
static const struct ctl_table sve_default_vl_table[] = {
{
.procname = "sve_default_vector_length",
.mode = 0644,
.proc_handler = vec_proc_do_default_vl,
.extra1 = &vl_info[ARM64_VEC_SVE],
},
};
static int __init sve_sysctl_init(void)
{
if (system_supports_sve())
if (!register_sysctl("abi", sve_default_vl_table))
return -EINVAL;
return 0;
}
#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
static int __init sve_sysctl_init(void) { return 0; }
#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
static const struct ctl_table sme_default_vl_table[] = {
{
.procname = "sme_default_vector_length",
.mode = 0644,
.proc_handler = vec_proc_do_default_vl,
.extra1 = &vl_info[ARM64_VEC_SME],
},
};
static int __init sme_sysctl_init(void)
{
if (system_supports_sme())
if (!register_sysctl("abi", sme_default_vl_table))
return -EINVAL;
return 0;
}
#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
static int __init sme_sysctl_init(void) { return 0; }
#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
#define ZREG(sve_state, vq, n) ((char *)(sve_state) + \
(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
#ifdef CONFIG_CPU_BIG_ENDIAN
static __uint128_t arm64_cpu_to_le128(__uint128_t x)
{
u64 a = swab64(x);
u64 b = swab64(x >> 64);
return ((__uint128_t)a << 64) | b;
}
#else
static __uint128_t arm64_cpu_to_le128(__uint128_t x)
{
return x;
}
#endif
#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
unsigned int vq)
{
unsigned int i;
__uint128_t *p;
for (i = 0; i < SVE_NUM_ZREGS; ++i) {
p = (__uint128_t *)ZREG(sst, vq, i);
*p = arm64_cpu_to_le128(fst->vregs[i]);
}
}
/*
* Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
* task->thread.sve_state.
*
* Task can be a non-runnable task, or current. In the latter case,
* the caller must have ownership of the cpu FPSIMD context before calling
* this function.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
* task->thread.uw.fpsimd_state must be up to date before calling this
* function.
*/
static void fpsimd_to_sve(struct task_struct *task)
{
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
if (!system_supports_sve() && !system_supports_sme())
return;
vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
__fpsimd_to_sve(sst, fst, vq);
}
/*
* Transfer the SVE state in task->thread.sve_state to
* task->thread.uw.fpsimd_state.
*
* Task can be a non-runnable task, or current. In the latter case,
* the caller must have ownership of the cpu FPSIMD context before calling
* this function.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
* task->thread.sve_state must be up to date before calling this function.
*/
static void sve_to_fpsimd(struct task_struct *task)
{
unsigned int vq, vl;
void const *sst = task->thread.sve_state;
struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
unsigned int i;
__uint128_t const *p;
if (!system_supports_sve() && !system_supports_sme())
return;
vl = thread_get_cur_vl(&task->thread);
vq = sve_vq_from_vl(vl);
for (i = 0; i < SVE_NUM_ZREGS; ++i) {
p = (__uint128_t const *)ZREG(sst, vq, i);
fst->vregs[i] = arm64_le128_to_cpu(*p);
}
}
void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
{
write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
SYS_SCTLR_EL1);
}
#ifdef CONFIG_ARM64_SVE
/*
* Call __sve_free() directly only if you know task can't be scheduled
* or preempted.
*/
static void __sve_free(struct task_struct *task)
{
kfree(task->thread.sve_state);
task->thread.sve_state = NULL;
}
static void sve_free(struct task_struct *task)
{
WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
__sve_free(task);
}
/*
* Return how many bytes of memory are required to store the full SVE
* state for task, given task's currently configured vector length.
*/
size_t sve_state_size(struct task_struct const *task)
{
unsigned int vl = 0;
if (system_supports_sve())
vl = task_get_sve_vl(task);
if (system_supports_sme())
vl = max(vl, task_get_sme_vl(task));
return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
}
/*
* Ensure that task->thread.sve_state is allocated and sufficiently large.
*
* This function should be used only in preparation for replacing
* task->thread.sve_state with new data. The memory is always zeroed
* here to prevent stale data from showing through: this is done in
* the interest of testability and predictability: except in the
* do_sve_acc() case, there is no ABI requirement to hide stale data
* written previously be task.
*/
void sve_alloc(struct task_struct *task, bool flush)
{
if (task->thread.sve_state) {
if (flush)
memset(task->thread.sve_state, 0,
sve_state_size(task));
return;
}
/* This is a small allocation (maximum ~8KB) and Should Not Fail. */
task->thread.sve_state =
kzalloc(sve_state_size(task), GFP_KERNEL);
}
/*
* Force the FPSIMD state shared with SVE to be updated in the SVE state
* even if the SVE state is the current active state.
*
* This should only be called by ptrace. task must be non-runnable.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
*/
void fpsimd_force_sync_to_sve(struct task_struct *task)
{
fpsimd_to_sve(task);
}
/*
* Ensure that task->thread.sve_state is up to date with respect to
* the user task, irrespective of when SVE is in use or not.
*
* This should only be called by ptrace. task must be non-runnable.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
*/
void fpsimd_sync_to_sve(struct task_struct *task)
{
if (!test_tsk_thread_flag(task, TIF_SVE) &&
!thread_sm_enabled(&task->thread))
fpsimd_to_sve(task);
}
/*
* Ensure that task->thread.uw.fpsimd_state is up to date with respect to
* the user task, irrespective of whether SVE is in use or not.
*
* This should only be called by ptrace. task must be non-runnable.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
*/
void sve_sync_to_fpsimd(struct task_struct *task)
{
if (task->thread.fp_type == FP_STATE_SVE)
sve_to_fpsimd(task);
}
/*
* Ensure that task->thread.sve_state is up to date with respect to
* the task->thread.uw.fpsimd_state.
*
* This should only be called by ptrace to merge new FPSIMD register
* values into a task for which SVE is currently active.
* task must be non-runnable.
* task->thread.sve_state must point to at least sve_state_size(task)
* bytes of allocated kernel memory.
* task->thread.uw.fpsimd_state must already have been initialised with
* the new FPSIMD register values to be merged in.
*/
void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
{
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
if (!test_tsk_thread_flag(task, TIF_SVE) &&
!thread_sm_enabled(&task->thread))
return;
vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
__fpsimd_to_sve(sst, fst, vq);
}
int vec_set_vector_length(struct task_struct *task, enum vec_type type,
unsigned long vl, unsigned long flags)
{
bool free_sme = false;
if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
PR_SVE_SET_VL_ONEXEC))
return -EINVAL;
if (!sve_vl_valid(vl))
return -EINVAL;
/*
* Clamp to the maximum vector length that VL-agnostic code
* can work with. A flag may be assigned in the future to
* allow setting of larger vector lengths without confusing
* older software.
*/
if (vl > VL_ARCH_MAX)
vl = VL_ARCH_MAX;
vl = find_supported_vector_length(type, vl);
if (flags & (PR_SVE_VL_INHERIT |
PR_SVE_SET_VL_ONEXEC))
task_set_vl_onexec(task, type, vl);
else
/* Reset VL to system default on next exec: */
task_set_vl_onexec(task, type, 0);
/* Only actually set the VL if not deferred: */
if (flags & PR_SVE_SET_VL_ONEXEC)
goto out;
if (vl == task_get_vl(task, type))
goto out;
/*
* To ensure the FPSIMD bits of the SVE vector registers are preserved,
* write any live register state back to task_struct, and convert to a
* regular FPSIMD thread.
*/
if (task == current) {
get_cpu_fpsimd_context();
fpsimd_save_user_state();
}
fpsimd_flush_task_state(task);
if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
thread_sm_enabled(&task->thread)) {
sve_to_fpsimd(task);
task->thread.fp_type = FP_STATE_FPSIMD;
}
if (system_supports_sme()) {
if (type == ARM64_VEC_SME ||
!(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) {
/*
* We are changing the SME VL or weren't using
* SME anyway, discard the state and force a
* reallocation.
*/
task->thread.svcr &= ~(SVCR_SM_MASK |
SVCR_ZA_MASK);
clear_tsk_thread_flag(task, TIF_SME);
free_sme = true;
}
}
if (task == current)
put_cpu_fpsimd_context();
task_set_vl(task, type, vl);
/*
* Free the changed states if they are not in use, SME will be
* reallocated to the correct size on next use and we just
* allocate SVE now in case it is needed for use in streaming
* mode.
*/
sve_free(task);
sve_alloc(task, true);
if (free_sme)
sme_free(task);
out:
update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
flags & PR_SVE_VL_INHERIT);
return 0;
}
/*
* Encode the current vector length and flags for return.
* This is only required for prctl(): ptrace has separate fields.
* SVE and SME use the same bits for _ONEXEC and _INHERIT.
*
* flags are as for vec_set_vector_length().
*/
static int vec_prctl_status(enum vec_type type, unsigned long flags)
{
int ret;
if (flags & PR_SVE_SET_VL_ONEXEC)
ret = task_get_vl_onexec(current, type);
else
ret = task_get_vl(current, type);
if (test_thread_flag(vec_vl_inherit_flag(type)))
ret |= PR_SVE_VL_INHERIT;
return ret;
}
/* PR_SVE_SET_VL */
int sve_set_current_vl(unsigned long arg)
{
unsigned long vl, flags;
int ret;
vl = arg & PR_SVE_VL_LEN_MASK;
flags = arg & ~vl;
if (!system_supports_sve() || is_compat_task())
return -EINVAL;
ret = vec_set_vector_length(current, ARM64_VEC_SVE, vl, flags);
if (ret)
return ret;
return vec_prctl_status(ARM64_VEC_SVE, flags);
}
/* PR_SVE_GET_VL */
int sve_get_current_vl(void)
{
if (!system_supports_sve() || is_compat_task())
return -EINVAL;
return vec_prctl_status(ARM64_VEC_SVE, 0);
}
#ifdef CONFIG_ARM64_SME
/* PR_SME_SET_VL */
int sme_set_current_vl(unsigned long arg)
{
unsigned long vl, flags;
int ret;
vl = arg & PR_SME_VL_LEN_MASK;
flags = arg & ~vl;
if (!system_supports_sme() || is_compat_task())
return -EINVAL;
ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags);
if (ret)
return ret;
return vec_prctl_status(ARM64_VEC_SME, flags);
}
/* PR_SME_GET_VL */
int sme_get_current_vl(void)
{
if (!system_supports_sme() || is_compat_task())
return -EINVAL;
return vec_prctl_status(ARM64_VEC_SME, 0);
}
#endif /* CONFIG_ARM64_SME */
static void vec_probe_vqs(struct vl_info *info,
DECLARE_BITMAP(map, SVE_VQ_MAX))
{
unsigned int vq, vl;
bitmap_zero(map, SVE_VQ_MAX);
for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
write_vl(info->type, vq - 1); /* self-syncing */
switch (info->type) {
case ARM64_VEC_SVE:
vl = sve_get_vl();
break;
case ARM64_VEC_SME:
vl = sme_get_vl();
break;
default:
vl = 0;
break;
}
/* Minimum VL identified? */
if (sve_vq_from_vl(vl) > vq)
break;
vq = sve_vq_from_vl(vl); /* skip intervening lengths */
set_bit(__vq_to_bit(vq), map);
}
}
/*
* Initialise the set of known supported VQs for the boot CPU.
* This is called during kernel boot, before secondary CPUs are brought up.
*/
void __init vec_init_vq_map(enum vec_type type)
{
struct vl_info *info = &vl_info[type];
vec_probe_vqs(info, info->vq_map);
bitmap_copy(info->vq_partial_map, info->vq_map, SVE_VQ_MAX);
}
/*
* If we haven't committed to the set of supported VQs yet, filter out
* those not supported by the current CPU.
* This function is called during the bring-up of early secondary CPUs only.
*/
void vec_update_vq_map(enum vec_type type)
{
struct vl_info *info = &vl_info[type];
DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
vec_probe_vqs(info, tmp_map);
bitmap_and(info->vq_map, info->vq_map, tmp_map, SVE_VQ_MAX);
bitmap_or(info->vq_partial_map, info->vq_partial_map, tmp_map,
SVE_VQ_MAX);
}
/*
* Check whether the current CPU supports all VQs in the committed set.
* This function is called during the bring-up of late secondary CPUs only.
*/
int vec_verify_vq_map(enum vec_type type)
{
struct vl_info *info = &vl_info[type];
DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
unsigned long b;
vec_probe_vqs(info, tmp_map);
bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
if (bitmap_intersects(tmp_map, info->vq_map, SVE_VQ_MAX)) {
pr_warn("%s: cpu%d: Required vector length(s) missing\n",
info->name, smp_processor_id());
return -EINVAL;
}
if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
return 0;
/*
* For KVM, it is necessary to ensure that this CPU doesn't
* support any vector length that guests may have probed as
* unsupported.
*/
/* Recover the set of supported VQs: */
bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
/* Find VQs supported that are not globally supported: */
bitmap_andnot(tmp_map, tmp_map, info->vq_map, SVE_VQ_MAX);
/* Find the lowest such VQ, if any: */
b = find_last_bit(tmp_map, SVE_VQ_MAX);
if (b >= SVE_VQ_MAX)
return 0; /* no mismatches */
/*
* Mismatches above sve_max_virtualisable_vl are fine, since
* no guest is allowed to configure ZCR_EL2.LEN to exceed this:
*/
if (sve_vl_from_vq(__bit_to_vq(b)) <= info->max_virtualisable_vl) {
pr_warn("%s: cpu%d: Unsupported vector length(s) present\n",
info->name, smp_processor_id());
return -EINVAL;
}
return 0;
}
static void __init sve_efi_setup(void)
{
int max_vl = 0;
int i;
if (!IS_ENABLED(CONFIG_EFI))
return;
for (i = 0; i < ARRAY_SIZE(vl_info); i++)
max_vl = max(vl_info[i].max_vl, max_vl);
/*
* alloc_percpu() warns and prints a backtrace if this goes wrong.
* This is evidence of a crippled system and we are returning void,
* so no attempt is made to handle this situation here.
*/
if (!sve_vl_valid(max_vl))
goto fail;
efi_sve_state = __alloc_percpu(
SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
if (!efi_sve_state)
goto fail;
return;
fail:
panic("Cannot allocate percpu memory for EFI SVE save/restore");
}
void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p)
{
write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1);
isb();
write_sysreg_s(0, SYS_ZCR_EL1);
}
void __init sve_setup(void)
{
struct vl_info *info = &vl_info[ARM64_VEC_SVE];
DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
unsigned long b;
int max_bit;
if (!system_supports_sve())
return;
/*
* The SVE architecture mandates support for 128-bit vectors,
* so sve_vq_map must have at least SVE_VQ_MIN set.
* If something went wrong, at least try to patch it up:
*/
if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map)))
set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map);
max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX);
info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit));
/*
* For the default VL, pick the maximum supported value <= 64.
* VL == 64 is guaranteed not to grow the signal frame.
*/
set_sve_default_vl(find_supported_vector_length(ARM64_VEC_SVE, 64));
bitmap_andnot(tmp_map, info->vq_partial_map, info->vq_map,
SVE_VQ_MAX);
b = find_last_bit(tmp_map, SVE_VQ_MAX);
if (b >= SVE_VQ_MAX)
/* No non-virtualisable VLs found */
info->max_virtualisable_vl = SVE_VQ_MAX;
else if (WARN_ON(b == SVE_VQ_MAX - 1))
/* No virtualisable VLs? This is architecturally forbidden. */
info->max_virtualisable_vl = SVE_VQ_MIN;
else /* b + 1 < SVE_VQ_MAX */
info->max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));
if (info->max_virtualisable_vl > info->max_vl)
info->max_virtualisable_vl = info->max_vl;
pr_info("%s: maximum available vector length %u bytes per vector\n",
info->name, info->max_vl);
pr_info("%s: default vector length %u bytes per vector\n",
info->name, get_sve_default_vl());
/* KVM decides whether to support mismatched systems. Just warn here: */
if (sve_max_virtualisable_vl() < sve_max_vl())
pr_warn("%s: unvirtualisable vector lengths present\n",
info->name);
sve_efi_setup();
}
/*
* Called from the put_task_struct() path, which cannot get here
* unless dead_task is really dead and not schedulable.
*/
void fpsimd_release_task(struct task_struct *dead_task)
{
__sve_free(dead_task);
sme_free(dead_task);
}
#endif /* CONFIG_ARM64_SVE */
#ifdef CONFIG_ARM64_SME
/*
* Ensure that task->thread.sme_state is allocated and sufficiently large.
*
* This function should be used only in preparation for replacing
* task->thread.sme_state with new data. The memory is always zeroed
* here to prevent stale data from showing through: this is done in
* the interest of testability and predictability, the architecture
* guarantees that when ZA is enabled it will be zeroed.
*/
void sme_alloc(struct task_struct *task, bool flush)
{
if (task->thread.sme_state) {
if (flush)
memset(task->thread.sme_state, 0,
sme_state_size(task));
return;
}
/* This could potentially be up to 64K. */
task->thread.sme_state =
kzalloc(sme_state_size(task), GFP_KERNEL);
}
static void sme_free(struct task_struct *task)
{
kfree(task->thread.sme_state);
task->thread.sme_state = NULL;
}
void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p)
{
/* Set priority for all PEs to architecturally defined minimum */
write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK,
SYS_SMPRI_EL1);
/* Allow SME in kernel */
write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
isb();
/* Ensure all bits in SMCR are set to known values */
write_sysreg_s(0, SYS_SMCR_EL1);
/* Allow EL0 to access TPIDR2 */
write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
isb();
}
void cpu_enable_sme2(const struct arm64_cpu_capabilities *__always_unused p)
{
/* This must be enabled after SME */
BUILD_BUG_ON(ARM64_SME2 <= ARM64_SME);
/* Allow use of ZT0 */
write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
SYS_SMCR_EL1);
}
void cpu_enable_fa64(const struct arm64_cpu_capabilities *__always_unused p)
{
/* This must be enabled after SME */
BUILD_BUG_ON(ARM64_SME_FA64 <= ARM64_SME);
/* Allow use of FA64 */
write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK,
SYS_SMCR_EL1);
}
void __init sme_setup(void)
{
struct vl_info *info = &vl_info[ARM64_VEC_SME];
int min_bit, max_bit;
if (!system_supports_sme())
return;
/*
* SME doesn't require any particular vector length be
* supported but it does require at least one. We should have
* disabled the feature entirely while bringing up CPUs but
* let's double check here. The bitmap is SVE_VQ_MAP sized for
* sharing with SVE.
*/
WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX));
min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX);
info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit));
max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX);
info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit));
WARN_ON(info->min_vl > info->max_vl);
/*
* For the default VL, pick the maximum supported value <= 32
* (256 bits) if there is one since this is guaranteed not to
* grow the signal frame when in streaming mode, otherwise the
* minimum available VL will be used.
*/
set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32));
pr_info("SME: minimum available vector length %u bytes per vector\n",
info->min_vl);
pr_info("SME: maximum available vector length %u bytes per vector\n",
info->max_vl);
pr_info("SME: default vector length %u bytes per vector\n",
get_sme_default_vl());
}
void sme_suspend_exit(void)
{
u64 smcr = 0;
if (!system_supports_sme())
return;
if (system_supports_fa64())
smcr |= SMCR_ELx_FA64;
if (system_supports_sme2())
smcr |= SMCR_ELx_EZT0;
write_sysreg_s(smcr, SYS_SMCR_EL1);
write_sysreg_s(0, SYS_SMPRI_EL1);
}
#endif /* CONFIG_ARM64_SME */
static void sve_init_regs(void)
{
/*
* Convert the FPSIMD state to SVE, zeroing all the state that
* is not shared with FPSIMD. If (as is likely) the current
* state is live in the registers then do this there and
* update our metadata for the current task including
* disabling the trap, otherwise update our in-memory copy.
* We are guaranteed to not be in streaming mode, we can only
* take a SVE trap when not in streaming mode and we can't be
* in streaming mode when taking a SME trap.
*/
if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
unsigned long vq_minus_one =
sve_vq_from_vl(task_get_sve_vl(current)) - 1;
sve_set_vq(vq_minus_one);
sve_flush_live(true, vq_minus_one);
fpsimd_bind_task_to_cpu();
} else {
fpsimd_to_sve(current);
current->thread.fp_type = FP_STATE_SVE;
fpsimd_flush_task_state(current);
}
}
/*
* Trapped SVE access
*
* Storage is allocated for the full SVE state, the current FPSIMD
* register contents are migrated across, and the access trap is
* disabled.
*
* TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state()
* would have disabled the SVE access trap for userspace during
* ret_to_user, making an SVE access trap impossible in that case.
*/
void do_sve_acc(unsigned long esr, struct pt_regs *regs)
{
/* Even if we chose not to use SVE, the hardware could still trap: */
if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) {
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
return;
}
sve_alloc(current, true);
if (!current->thread.sve_state) {
force_sig(SIGKILL);
return;
}
get_cpu_fpsimd_context();
if (test_and_set_thread_flag(TIF_SVE))
WARN_ON(1); /* SVE access shouldn't have trapped */
/*
* Even if the task can have used streaming mode we can only
* generate SVE access traps in normal SVE mode and
* transitioning out of streaming mode may discard any
* streaming mode state. Always clear the high bits to avoid
* any potential errors tracking what is properly initialised.
*/
sve_init_regs();
put_cpu_fpsimd_context();
}
/*
* Trapped SME access
*
* Storage is allocated for the full SVE and SME state, the current
* FPSIMD register contents are migrated to SVE if SVE is not already
* active, and the access trap is disabled.
*
* TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state()
* would have disabled the SME access trap for userspace during
* ret_to_user, making an SME access trap impossible in that case.
*/
void do_sme_acc(unsigned long esr, struct pt_regs *regs)
{
/* Even if we chose not to use SME, the hardware could still trap: */
if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) {
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
return;
}
/*
* If this not a trap due to SME being disabled then something
* is being used in the wrong mode, report as SIGILL.
*/
if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
return;
}
sve_alloc(current, false);
sme_alloc(current, true);
if (!current->thread.sve_state || !current->thread.sme_state) {
force_sig(SIGKILL);
return;
}
get_cpu_fpsimd_context();
/* With TIF_SME userspace shouldn't generate any traps */
if (test_and_set_thread_flag(TIF_SME))
WARN_ON(1);
if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
unsigned long vq_minus_one =
sve_vq_from_vl(task_get_sme_vl(current)) - 1;
sme_set_vq(vq_minus_one);
fpsimd_bind_task_to_cpu();
}
put_cpu_fpsimd_context();
}
/*
* Trapped FP/ASIMD access.
*/
void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs)
{
/* Even if we chose not to use FPSIMD, the hardware could still trap: */
if (!system_supports_fpsimd()) {
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
return;
}
/*
* When FPSIMD is enabled, we should never take a trap unless something
* has gone very wrong.
*/
BUG();
}
/*
* Raise a SIGFPE for the current process.
*/
void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs)
{
unsigned int si_code = FPE_FLTUNK;
if (esr & ESR_ELx_FP_EXC_TFV) {
if (esr & FPEXC_IOF)
si_code = FPE_FLTINV;
else if (esr & FPEXC_DZF)
si_code = FPE_FLTDIV;
else if (esr & FPEXC_OFF)
si_code = FPE_FLTOVF;
else if (esr & FPEXC_UFF)
si_code = FPE_FLTUND;
else if (esr & FPEXC_IXF)
si_code = FPE_FLTRES;
}
send_sig_fault(SIGFPE, si_code,
(void __user *)instruction_pointer(regs),
current);
}
static void fpsimd_load_kernel_state(struct task_struct *task)
{
struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
/*
* Elide the load if this CPU holds the most recent kernel mode
* FPSIMD context of the current task.
*/
if (last->st == &task->thread.kernel_fpsimd_state &&
task->thread.kernel_fpsimd_cpu == smp_processor_id())
return;
fpsimd_load_state(&task->thread.kernel_fpsimd_state);
}
static void fpsimd_save_kernel_state(struct task_struct *task)
{
struct cpu_fp_state cpu_fp_state = {
.st = &task->thread.kernel_fpsimd_state,
.to_save = FP_STATE_FPSIMD,
};
fpsimd_save_state(&task->thread.kernel_fpsimd_state);
fpsimd_bind_state_to_cpu(&cpu_fp_state);
task->thread.kernel_fpsimd_cpu = smp_processor_id();
}
/*
* Invalidate any task's FPSIMD state that is present on this cpu.
* The FPSIMD context should be acquired with get_cpu_fpsimd_context()
* before calling this function.
*/
static void fpsimd_flush_cpu_state(void)
{
WARN_ON(!system_supports_fpsimd());
__this_cpu_write(fpsimd_last_state.st, NULL);
/*
* Leaving streaming mode enabled will cause issues for any kernel
* NEON and leaving streaming mode or ZA enabled may increase power
* consumption.
*/
if (system_supports_sme())
sme_smstop();
set_thread_flag(TIF_FOREIGN_FPSTATE);
}
void fpsimd_thread_switch(struct task_struct *next)
{
bool wrong_task, wrong_cpu;
if (!system_supports_fpsimd())
return;
WARN_ON_ONCE(!irqs_disabled());
/* Save unsaved fpsimd state, if any: */
if (test_thread_flag(TIF_KERNEL_FPSTATE))
fpsimd_save_kernel_state(current);
else
fpsimd_save_user_state();
if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
fpsimd_load_kernel_state(next);
fpsimd_flush_cpu_state();
} else {
/*
* Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
* state. For kernel threads, FPSIMD registers are never
* loaded with user mode FPSIMD state and so wrong_task and
* wrong_cpu will always be true.
*/
wrong_task = __this_cpu_read(fpsimd_last_state.st) !=
&next->thread.uw.fpsimd_state;
wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id();
update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
wrong_task || wrong_cpu);
}
}
static void fpsimd_flush_thread_vl(enum vec_type type)
{
int vl, supported_vl;
/*
* Reset the task vector length as required. This is where we
* ensure that all user tasks have a valid vector length
* configured: no kernel task can become a user task without
* an exec and hence a call to this function. By the time the
* first call to this function is made, all early hardware
* probing is complete, so __sve_default_vl should be valid.
* If a bug causes this to go wrong, we make some noise and
* try to fudge thread.sve_vl to a safe value here.
*/
vl = task_get_vl_onexec(current, type);
if (!vl)
vl = get_default_vl(type);
if (WARN_ON(!sve_vl_valid(vl)))
vl = vl_info[type].min_vl;
supported_vl = find_supported_vector_length(type, vl);
if (WARN_ON(supported_vl != vl))
vl = supported_vl;
task_set_vl(current, type, vl);
/*
* If the task is not set to inherit, ensure that the vector
* length will be reset by a subsequent exec:
*/
if (!test_thread_flag(vec_vl_inherit_flag(type)))
task_set_vl_onexec(current, type, 0);
}
void fpsimd_flush_thread(void)
{
void *sve_state = NULL;
void *sme_state = NULL;
if (!system_supports_fpsimd())
return;
get_cpu_fpsimd_context();
fpsimd_flush_task_state(current);
memset(¤t->thread.uw.fpsimd_state, 0,
sizeof(current->thread.uw.fpsimd_state));
if (system_supports_sve()) {
clear_thread_flag(TIF_SVE);
/* Defer kfree() while in atomic context */
sve_state = current->thread.sve_state;
current->thread.sve_state = NULL;
fpsimd_flush_thread_vl(ARM64_VEC_SVE);
}
if (system_supports_sme()) {
clear_thread_flag(TIF_SME);
/* Defer kfree() while in atomic context */
sme_state = current->thread.sme_state;
current->thread.sme_state = NULL;
fpsimd_flush_thread_vl(ARM64_VEC_SME);
current->thread.svcr = 0;
}
current->thread.fp_type = FP_STATE_FPSIMD;
put_cpu_fpsimd_context();
kfree(sve_state);
kfree(sme_state);
}
/*
* Save the userland FPSIMD state of 'current' to memory, but only if the state
* currently held in the registers does in fact belong to 'current'
*/
void fpsimd_preserve_current_state(void)
{
if (!system_supports_fpsimd())
return;
get_cpu_fpsimd_context();
fpsimd_save_user_state();
put_cpu_fpsimd_context();
}
/*
* Like fpsimd_preserve_current_state(), but ensure that
* current->thread.uw.fpsimd_state is updated so that it can be copied to
* the signal frame.
*/
void fpsimd_signal_preserve_current_state(void)
{ fpsimd_preserve_current_state(); if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current);
}
/*
* Associate current's FPSIMD context with this cpu
* The caller must have ownership of the cpu FPSIMD context before calling
* this function.
*/
static void fpsimd_bind_task_to_cpu(void)
{
struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
WARN_ON(!system_supports_fpsimd());
last->st = ¤t->thread.uw.fpsimd_state;
last->sve_state = current->thread.sve_state;
last->sme_state = current->thread.sme_state;
last->sve_vl = task_get_sve_vl(current);
last->sme_vl = task_get_sme_vl(current);
last->svcr = ¤t->thread.svcr;
last->fpmr = ¤t->thread.uw.fpmr;
last->fp_type = ¤t->thread.fp_type;
last->to_save = FP_STATE_CURRENT;
current->thread.fpsimd_cpu = smp_processor_id();
/*
* Toggle SVE and SME trapping for userspace if needed, these
* are serialsied by ret_to_user().
*/
if (system_supports_sme()) {
if (test_thread_flag(TIF_SME))
sme_user_enable();
else
sme_user_disable();
}
if (system_supports_sve()) {
if (test_thread_flag(TIF_SVE))
sve_user_enable();
else
sve_user_disable();
}
}
void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state)
{
struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
WARN_ON(!system_supports_fpsimd());
WARN_ON(!in_softirq() && !irqs_disabled());
*last = *state;
}
/*
* Load the userland FPSIMD state of 'current' from memory, but only if the
* FPSIMD state already held in the registers is /not/ the most recent FPSIMD
* state of 'current'. This is called when we are preparing to return to
* userspace to ensure that userspace sees a good register state.
*/
void fpsimd_restore_current_state(void)
{
/*
* TIF_FOREIGN_FPSTATE is set on the init task and copied by
* arch_dup_task_struct() regardless of whether FP/SIMD is detected.
* Thus user threads can have this set even when FP/SIMD hasn't been
* detected.
*
* When FP/SIMD is detected, begin_new_exec() will set
* TIF_FOREIGN_FPSTATE via flush_thread() -> fpsimd_flush_thread(),
* and fpsimd_thread_switch() will set TIF_FOREIGN_FPSTATE when
* switching tasks. We detect FP/SIMD before we exec the first user
* process, ensuring this has TIF_FOREIGN_FPSTATE set and
* do_notify_resume() will call fpsimd_restore_current_state() to
* install the user FP/SIMD context.
*
* When FP/SIMD is not detected, nothing else will clear or set
* TIF_FOREIGN_FPSTATE prior to the first return to userspace, and
* we must clear TIF_FOREIGN_FPSTATE to avoid do_notify_resume()
* looping forever calling fpsimd_restore_current_state().
*/
if (!system_supports_fpsimd()) {
clear_thread_flag(TIF_FOREIGN_FPSTATE);
return;
}
get_cpu_fpsimd_context();
if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { task_fpsimd_load();
fpsimd_bind_task_to_cpu();
}
put_cpu_fpsimd_context();
}
/*
* Load an updated userland FPSIMD state for 'current' from memory and set the
* flag that indicates that the FPSIMD register contents are the most recent
* FPSIMD state of 'current'. This is used by the signal code to restore the
* register state when returning from a signal handler in FPSIMD only cases,
* any SVE context will be discarded.
*/
void fpsimd_update_current_state(struct user_fpsimd_state const *state)
{
if (WARN_ON(!system_supports_fpsimd()))
return;
get_cpu_fpsimd_context();
current->thread.uw.fpsimd_state = *state;
if (test_thread_flag(TIF_SVE))
fpsimd_to_sve(current);
task_fpsimd_load();
fpsimd_bind_task_to_cpu();
clear_thread_flag(TIF_FOREIGN_FPSTATE);
put_cpu_fpsimd_context();
}
/*
* Invalidate live CPU copies of task t's FPSIMD state
*
* This function may be called with preemption enabled. The barrier()
* ensures that the assignment to fpsimd_cpu is visible to any
* preemption/softirq that could race with set_tsk_thread_flag(), so
* that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared.
*
* The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any
* subsequent code.
*/
void fpsimd_flush_task_state(struct task_struct *t)
{
t->thread.fpsimd_cpu = NR_CPUS;
/*
* If we don't support fpsimd, bail out after we have
* reset the fpsimd_cpu for this task and clear the
* FPSTATE.
*/
if (!system_supports_fpsimd())
return;
barrier();
set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
barrier();
}
/*
* Save the FPSIMD state to memory and invalidate cpu view.
* This function must be called with preemption disabled.
*/
void fpsimd_save_and_flush_cpu_state(void)
{
unsigned long flags;
if (!system_supports_fpsimd())
return;
WARN_ON(preemptible()); local_irq_save(flags);
fpsimd_save_user_state();
fpsimd_flush_cpu_state(); local_irq_restore(flags);
}
#ifdef CONFIG_KERNEL_MODE_NEON
/*
* Kernel-side NEON support functions
*/
/*
* kernel_neon_begin(): obtain the CPU FPSIMD registers for use by the calling
* context
*
* Must not be called unless may_use_simd() returns true.
* Task context in the FPSIMD registers is saved back to memory as necessary.
*
* A matching call to kernel_neon_end() must be made before returning from the
* calling context.
*
* The caller may freely use the FPSIMD registers until kernel_neon_end() is
* called.
*/
void kernel_neon_begin(void)
{
if (WARN_ON(!system_supports_fpsimd()))
return;
BUG_ON(!may_use_simd());
get_cpu_fpsimd_context();
/* Save unsaved fpsimd state, if any: */
if (test_thread_flag(TIF_KERNEL_FPSTATE)) {
BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq());
fpsimd_save_kernel_state(current);
} else {
fpsimd_save_user_state();
/*
* Set the thread flag so that the kernel mode FPSIMD state
* will be context switched along with the rest of the task
* state.
*
* On non-PREEMPT_RT, softirqs may interrupt task level kernel
* mode FPSIMD, but the task will not be preemptible so setting
* TIF_KERNEL_FPSTATE for those would be both wrong (as it
* would mark the task context FPSIMD state as requiring a
* context switch) and unnecessary.
*
* On PREEMPT_RT, softirqs are serviced from a separate thread,
* which is scheduled as usual, and this guarantees that these
* softirqs are not interrupting use of the FPSIMD in kernel
* mode in task context. So in this case, setting the flag here
* is always appropriate.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq())
set_thread_flag(TIF_KERNEL_FPSTATE);
}
/* Invalidate any task state remaining in the fpsimd regs: */
fpsimd_flush_cpu_state();
put_cpu_fpsimd_context();
}
EXPORT_SYMBOL_GPL(kernel_neon_begin);
/*
* kernel_neon_end(): give the CPU FPSIMD registers back to the current task
*
* Must be called from a context in which kernel_neon_begin() was previously
* called, with no call to kernel_neon_end() in the meantime.
*
* The caller must not use the FPSIMD registers after this function is called,
* unless kernel_neon_begin() is called again in the meantime.
*/
void kernel_neon_end(void)
{
if (!system_supports_fpsimd())
return;
/*
* If we are returning from a nested use of kernel mode FPSIMD, restore
* the task context kernel mode FPSIMD state. This can only happen when
* running in softirq context on non-PREEMPT_RT.
*/
if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() &&
test_thread_flag(TIF_KERNEL_FPSTATE))
fpsimd_load_kernel_state(current);
else
clear_thread_flag(TIF_KERNEL_FPSTATE);
}
EXPORT_SYMBOL_GPL(kernel_neon_end);
#ifdef CONFIG_EFI
static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
static DEFINE_PER_CPU(bool, efi_sve_state_used);
static DEFINE_PER_CPU(bool, efi_sm_state);
/*
* EFI runtime services support functions
*
* The ABI for EFI runtime services allows EFI to use FPSIMD during the call.
* This means that for EFI (and only for EFI), we have to assume that FPSIMD
* is always used rather than being an optional accelerator.
*
* These functions provide the necessary support for ensuring FPSIMD
* save/restore in the contexts from which EFI is used.
*
* Do not use them for any other purpose -- if tempted to do so, you are
* either doing something wrong or you need to propose some refactoring.
*/
/*
* __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call
*/
void __efi_fpsimd_begin(void)
{
if (!system_supports_fpsimd())
return;
WARN_ON(preemptible());
if (may_use_simd()) {
kernel_neon_begin();
} else {
/*
* If !efi_sve_state, SVE can't be in use yet and doesn't need
* preserving:
*/
if (system_supports_sve() && likely(efi_sve_state)) {
char *sve_state = this_cpu_ptr(efi_sve_state);
bool ffr = true;
u64 svcr;
__this_cpu_write(efi_sve_state_used, true);
if (system_supports_sme()) {
svcr = read_sysreg_s(SYS_SVCR);
__this_cpu_write(efi_sm_state,
svcr & SVCR_SM_MASK);
/*
* Unless we have FA64 FFR does not
* exist in streaming mode.
*/
if (!system_supports_fa64())
ffr = !(svcr & SVCR_SM_MASK);
}
sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
&this_cpu_ptr(&efi_fpsimd_state)->fpsr,
ffr);
if (system_supports_sme())
sysreg_clear_set_s(SYS_SVCR,
SVCR_SM_MASK, 0);
} else {
fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
}
__this_cpu_write(efi_fpsimd_state_used, true);
}
}
/*
* __efi_fpsimd_end(): clean up FPSIMD after an EFI runtime services call
*/
void __efi_fpsimd_end(void)
{
if (!system_supports_fpsimd())
return;
if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
kernel_neon_end();
} else {
if (system_supports_sve() &&
likely(__this_cpu_read(efi_sve_state_used))) {
char const *sve_state = this_cpu_ptr(efi_sve_state);
bool ffr = true;
/*
* Restore streaming mode; EFI calls are
* normal function calls so should not return in
* streaming mode.
*/
if (system_supports_sme()) {
if (__this_cpu_read(efi_sm_state)) {
sysreg_clear_set_s(SYS_SVCR,
0,
SVCR_SM_MASK);
/*
* Unless we have FA64 FFR does not
* exist in streaming mode.
*/
if (!system_supports_fa64())
ffr = false;
}
}
sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
&this_cpu_ptr(&efi_fpsimd_state)->fpsr,
ffr);
__this_cpu_write(efi_sve_state_used, false);
} else {
fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
}
}
}
#endif /* CONFIG_EFI */
#endif /* CONFIG_KERNEL_MODE_NEON */
#ifdef CONFIG_CPU_PM
static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd, void *v)
{
switch (cmd) {
case CPU_PM_ENTER:
fpsimd_save_and_flush_cpu_state();
break;
case CPU_PM_EXIT:
break;
case CPU_PM_ENTER_FAILED:
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
static struct notifier_block fpsimd_cpu_pm_notifier_block = {
.notifier_call = fpsimd_cpu_pm_notifier,
};
static void __init fpsimd_pm_init(void)
{
cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
}
#else
static inline void fpsimd_pm_init(void) { }
#endif /* CONFIG_CPU_PM */
#ifdef CONFIG_HOTPLUG_CPU
static int fpsimd_cpu_dead(unsigned int cpu)
{
per_cpu(fpsimd_last_state.st, cpu) = NULL;
return 0;
}
static inline void fpsimd_hotplug_init(void)
{
cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead",
NULL, fpsimd_cpu_dead);
}
#else
static inline void fpsimd_hotplug_init(void) { }
#endif
void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__always_unused p)
{
unsigned long enable = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN;
write_sysreg(read_sysreg(CPACR_EL1) | enable, CPACR_EL1);
isb();
}
/*
* FP/SIMD support code initialisation.
*/
static int __init fpsimd_init(void)
{
if (cpu_have_named_feature(FP)) {
fpsimd_pm_init();
fpsimd_hotplug_init();
} else {
pr_notice("Floating-point is not implemented\n");
}
if (!cpu_have_named_feature(ASIMD))
pr_notice("Advanced SIMD is not implemented\n");
sve_sysctl_init();
sme_sysctl_init();
return 0;
}
core_initcall(fpsimd_init);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_MQ_H
#define BLK_MQ_H
#include <linux/blkdev.h>
#include <linux/sbitmap.h>
#include <linux/lockdep.h>
#include <linux/scatterlist.h>
#include <linux/prefetch.h>
#include <linux/srcu.h>
#include <linux/rw_hint.h>
struct blk_mq_tags;
struct blk_flush_queue;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_DEFAULT_RQ 128
enum rq_end_io_ret {
RQ_END_IO_NONE,
RQ_END_IO_FREE,
};
typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
/*
* request flags */
typedef __u32 __bitwise req_flags_t;
/* Keep rqf_name[] in sync with the definitions below */
enum rqf_flags {
/* drive already may have started this one */
__RQF_STARTED,
/* request for flush sequence */
__RQF_FLUSH_SEQ,
/* merge of different types, fail separately */
__RQF_MIXED_MERGE,
/* don't call prep for this one */
__RQF_DONTPREP,
/* use hctx->sched_tags */
__RQF_SCHED_TAGS,
/* use an I/O scheduler for this request */
__RQF_USE_SCHED,
/* vaguely specified driver internal error. Ignored by block layer */
__RQF_FAILED,
/* don't warn about errors */
__RQF_QUIET,
/* account into disk and partition IO statistics */
__RQF_IO_STAT,
/* runtime pm request */
__RQF_PM,
/* on IO scheduler merge hash */
__RQF_HASHED,
/* track IO completion time */
__RQF_STATS,
/* Look at ->special_vec for the actual data payload instead of the
bio chain. */
__RQF_SPECIAL_PAYLOAD,
/* request completion needs to be signaled to zone write plugging. */
__RQF_ZONE_WRITE_PLUGGING,
/* ->timeout has been called, don't expire again */
__RQF_TIMED_OUT,
__RQF_RESV,
__RQF_BITS
};
#define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED))
#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ))
#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE))
#define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP))
#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS))
#define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED))
#define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED))
#define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET))
#define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT))
#define RQF_PM ((__force req_flags_t)(1 << __RQF_PM))
#define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED))
#define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS))
#define RQF_SPECIAL_PAYLOAD \
((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD))
#define RQF_ZONE_WRITE_PLUGGING \
((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING))
#define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT))
#define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV))
/* flags that prevent us from merging requests: */
#define RQF_NOMERGE_FLAGS \
(RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
enum mq_rq_state {
MQ_RQ_IDLE = 0,
MQ_RQ_IN_FLIGHT = 1,
MQ_RQ_COMPLETE = 2,
};
/*
* Try to put the fields that are referenced together in the same cacheline.
*
* If you modify this structure, make sure to update blk_rq_init() and
* especially blk_mq_rq_ctx_init() to take care of the added fields.
*/
struct request {
struct request_queue *q;
struct blk_mq_ctx *mq_ctx;
struct blk_mq_hw_ctx *mq_hctx;
blk_opf_t cmd_flags; /* op and common flags */
req_flags_t rq_flags;
int tag;
int internal_tag;
unsigned int timeout;
/* the following two fields are internal, NEVER access directly */
unsigned int __data_len; /* total data len */
sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
union {
struct list_head queuelist;
struct request *rq_next;
};
struct block_device *part;
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
/* Time that the first bio started allocating this request. */
u64 alloc_time_ns;
#endif
/* Time that this request was allocated for this IO. */
u64 start_time_ns;
/* Time that I/O was submitted to the device. */
u64 io_start_time_ns;
#ifdef CONFIG_BLK_WBT
unsigned short wbt_flags;
#endif
/*
* rq sectors used for blk stats. It has the same value
* with blk_rq_sectors(rq), except that it never be zeroed
* by completion.
*/
unsigned short stats_sectors;
/*
* Number of scatter-gather DMA addr+len pairs after
* physical address coalescing is performed.
*/
unsigned short nr_phys_segments;
unsigned short nr_integrity_segments;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
struct bio_crypt_ctx *crypt_ctx;
struct blk_crypto_keyslot *crypt_keyslot;
#endif
enum mq_rq_state state;
atomic_t ref;
unsigned long deadline;
/*
* The hash is used inside the scheduler, and killed once the
* request reaches the dispatch list. The ipi_list is only used
* to queue the request for softirq completion, which is long
* after the request has been unhashed (and even removed from
* the dispatch list).
*/
union {
struct hlist_node hash; /* merge hash */
struct llist_node ipi_list;
};
/*
* The rb_node is only used inside the io scheduler, requests
* are pruned when moved to the dispatch queue. special_vec must
* only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be
* insert into an IO scheduler.
*/
union {
struct rb_node rb_node; /* sort/lookup */
struct bio_vec special_vec;
};
/*
* Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it.
*/
struct {
struct io_cq *icq;
void *priv[2];
} elv;
struct {
unsigned int seq;
rq_end_io_fn *saved_end_io;
} flush;
u64 fifo_time;
/*
* completion callback.
*/
rq_end_io_fn *end_io;
void *end_io_data;
};
static inline enum req_op req_op(const struct request *req)
{
return req->cmd_flags & REQ_OP_MASK;
}
static inline bool blk_rq_is_passthrough(struct request *rq)
{
return blk_op_is_passthrough(rq->cmd_flags);
}
static inline unsigned short req_get_ioprio(struct request *req)
{
if (req->bio)
return req->bio->bi_ioprio;
return 0;
}
#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ)
#define rq_dma_dir(rq) \
(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
static inline int rq_list_empty(const struct rq_list *rl)
{
return rl->head == NULL;
}
static inline void rq_list_init(struct rq_list *rl)
{
rl->head = NULL;
rl->tail = NULL;
}
static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq)
{
rq->rq_next = NULL;
if (rl->tail) rl->tail->rq_next = rq;
else
rl->head = rq;
rl->tail = rq;
}
static inline void rq_list_add_head(struct rq_list *rl, struct request *rq)
{
rq->rq_next = rl->head;
rl->head = rq;
if (!rl->tail)
rl->tail = rq;
}
static inline struct request *rq_list_pop(struct rq_list *rl)
{
struct request *rq = rl->head;
if (rq) {
rl->head = rl->head->rq_next;
if (!rl->head) rl->tail = NULL;
rq->rq_next = NULL;
}
return rq;
}
static inline struct request *rq_list_peek(struct rq_list *rl)
{
return rl->head;
}
#define rq_list_for_each(rl, pos) \
for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next)
#define rq_list_for_each_safe(rl, pos, nxt) \
for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \
pos; pos = nxt, nxt = pos ? pos->rq_next : NULL)
/**
* enum blk_eh_timer_return - How the timeout handler should proceed
* @BLK_EH_DONE: The block driver completed the command or will complete it at
* a later time.
* @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the
* request to complete.
*/
enum blk_eh_timer_return {
BLK_EH_DONE,
BLK_EH_RESET_TIMER,
};
/**
* struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
* block device
*/
struct blk_mq_hw_ctx {
struct {
/** @lock: Protects the dispatch list. */
spinlock_t lock;
/**
* @dispatch: Used for requests that are ready to be
* dispatched to the hardware but for some reason (e.g. lack of
* resources) could not be sent to the hardware. As soon as the
* driver can send new requests, requests at this list will
* be sent first for a fairer dispatch.
*/
struct list_head dispatch;
/**
* @state: BLK_MQ_S_* flags. Defines the state of the hw
* queue (active, scheduled to restart, stopped).
*/
unsigned long state;
} ____cacheline_aligned_in_smp;
/**
* @run_work: Used for scheduling a hardware queue run at a later time.
*/
struct delayed_work run_work;
/** @cpumask: Map of available CPUs where this hctx can run. */
cpumask_var_t cpumask;
/**
* @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU
* selection from @cpumask.
*/
int next_cpu;
/**
* @next_cpu_batch: Counter of how many works left in the batch before
* changing to the next CPU.
*/
int next_cpu_batch;
/** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */
unsigned long flags;
/**
* @sched_data: Pointer owned by the IO scheduler attached to a request
* queue. It's up to the IO scheduler how to use this pointer.
*/
void *sched_data;
/**
* @queue: Pointer to the request queue that owns this hardware context.
*/
struct request_queue *queue;
/** @fq: Queue of requests that need to perform a flush operation. */
struct blk_flush_queue *fq;
/**
* @driver_data: Pointer to data owned by the block driver that created
* this hctx
*/
void *driver_data;
/**
* @ctx_map: Bitmap for each software queue. If bit is on, there is a
* pending request in that software queue.
*/
struct sbitmap ctx_map;
/**
* @dispatch_from: Software queue to be used when no scheduler was
* selected.
*/
struct blk_mq_ctx *dispatch_from;
/**
* @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to
* decide if the hw_queue is busy using Exponential Weighted Moving
* Average algorithm.
*/
unsigned int dispatch_busy;
/** @type: HCTX_TYPE_* flags. Type of hardware queue. */
unsigned short type;
/** @nr_ctx: Number of software queues. */
unsigned short nr_ctx;
/** @ctxs: Array of software queues. */
struct blk_mq_ctx **ctxs;
/** @dispatch_wait_lock: Lock for dispatch_wait queue. */
spinlock_t dispatch_wait_lock;
/**
* @dispatch_wait: Waitqueue to put requests when there is no tag
* available at the moment, to wait for another try in the future.
*/
wait_queue_entry_t dispatch_wait;
/**
* @wait_index: Index of next available dispatch_wait queue to insert
* requests.
*/
atomic_t wait_index;
/**
* @tags: Tags owned by the block driver. A tag at this set is only
* assigned when a request is dispatched from a hardware queue.
*/
struct blk_mq_tags *tags;
/**
* @sched_tags: Tags owned by I/O scheduler. If there is an I/O
* scheduler associated with a request queue, a tag is assigned when
* that request is allocated. Else, this member is not used.
*/
struct blk_mq_tags *sched_tags;
/** @numa_node: NUMA node the storage adapter has been connected to. */
unsigned int numa_node;
/** @queue_num: Index of this hardware queue. */
unsigned int queue_num;
/**
* @nr_active: Number of active requests. Only used when a tag set is
* shared across request queues.
*/
atomic_t nr_active;
/** @cpuhp_online: List to store request if CPU is going to die */
struct hlist_node cpuhp_online;
/** @cpuhp_dead: List to store request if some CPU die. */
struct hlist_node cpuhp_dead;
/** @kobj: Kernel object for sysfs. */
struct kobject kobj;
#ifdef CONFIG_BLK_DEBUG_FS
/**
* @debugfs_dir: debugfs directory for this hardware queue. Named
* as cpu<cpu_number>.
*/
struct dentry *debugfs_dir;
/** @sched_debugfs_dir: debugfs directory for the scheduler. */
struct dentry *sched_debugfs_dir;
#endif
/**
* @hctx_list: if this hctx is not in use, this is an entry in
* q->unused_hctx_list.
*/
struct list_head hctx_list;
};
/**
* struct blk_mq_queue_map - Map software queues to hardware queues
* @mq_map: CPU ID to hardware queue index map. This is an array
* with nr_cpu_ids elements. Each element has a value in the range
* [@queue_offset, @queue_offset + @nr_queues).
* @nr_queues: Number of hardware queues to map CPU IDs onto.
* @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe
* driver to map each hardware queue type (enum hctx_type) onto a distinct
* set of hardware queues.
*/
struct blk_mq_queue_map {
unsigned int *mq_map;
unsigned int nr_queues;
unsigned int queue_offset;
};
/**
* enum hctx_type - Type of hardware queue
* @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for.
* @HCTX_TYPE_READ: Just for READ I/O.
* @HCTX_TYPE_POLL: Polled I/O of any kind.
* @HCTX_MAX_TYPES: Number of types of hctx.
*/
enum hctx_type {
HCTX_TYPE_DEFAULT,
HCTX_TYPE_READ,
HCTX_TYPE_POLL,
HCTX_MAX_TYPES,
};
/**
* struct blk_mq_tag_set - tag set that can be shared between request queues
* @ops: Pointers to functions that implement block driver behavior.
* @map: One or more ctx -> hctx mappings. One map exists for each
* hardware queue type (enum hctx_type) that the driver wishes
* to support. There are no restrictions on maps being of the
* same size, and it's perfectly legal to share maps between
* types.
* @nr_maps: Number of elements in the @map array. A number in the range
* [1, HCTX_MAX_TYPES].
* @nr_hw_queues: Number of hardware queues supported by the block driver that
* owns this data structure.
* @queue_depth: Number of tags per hardware queue, reserved tags included.
* @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag
* allocations.
* @cmd_size: Number of additional bytes to allocate per request. The block
* driver owns these additional bytes.
* @numa_node: NUMA node the storage adapter has been connected to.
* @timeout: Request processing timeout in jiffies.
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
* @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues
* elements.
* @shared_tags:
* Shared set of tags. Has @nr_hw_queues elements. If set,
* shared by all @tags.
* @tag_list_lock: Serializes tag_list accesses.
* @tag_list: List of the request queues that use this tag set. See also
* request_queue.tag_set_list.
* @srcu: Use as lock when type of the request queue is blocking
* (BLK_MQ_F_BLOCKING).
*/
struct blk_mq_tag_set {
const struct blk_mq_ops *ops;
struct blk_mq_queue_map map[HCTX_MAX_TYPES];
unsigned int nr_maps;
unsigned int nr_hw_queues;
unsigned int queue_depth;
unsigned int reserved_tags;
unsigned int cmd_size;
int numa_node;
unsigned int timeout;
unsigned int flags;
void *driver_data;
struct blk_mq_tags **tags;
struct blk_mq_tags *shared_tags;
struct mutex tag_list_lock;
struct list_head tag_list;
struct srcu_struct *srcu;
};
/**
* struct blk_mq_queue_data - Data about a request inserted in a queue
*
* @rq: Request pointer.
* @last: If it is the last request in the queue.
*/
struct blk_mq_queue_data {
struct request *rq;
bool last;
};
typedef bool (busy_tag_iter_fn)(struct request *, void *);
/**
* struct blk_mq_ops - Callback functions that implements block driver
* behaviour.
*/
struct blk_mq_ops {
/**
* @queue_rq: Queue a new request from block IO.
*/
blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *,
const struct blk_mq_queue_data *);
/**
* @commit_rqs: If a driver uses bd->last to judge when to submit
* requests to hardware, it must define this function. In case of errors
* that make us stop issuing further requests, this hook serves the
* purpose of kicking the hardware (which the last request otherwise
* would have done).
*/
void (*commit_rqs)(struct blk_mq_hw_ctx *);
/**
* @queue_rqs: Queue a list of new requests. Driver is guaranteed
* that each request belongs to the same queue. If the driver doesn't
* empty the @rqlist completely, then the rest will be queued
* individually by the block layer upon return.
*/
void (*queue_rqs)(struct rq_list *rqlist);
/**
* @get_budget: Reserve budget before queue request, once .queue_rq is
* run, it is driver's responsibility to release the
* reserved budget. Also we have to handle failure case
* of .get_budget for avoiding I/O deadlock.
*/
int (*get_budget)(struct request_queue *);
/**
* @put_budget: Release the reserved budget.
*/
void (*put_budget)(struct request_queue *, int);
/**
* @set_rq_budget_token: store rq's budget token
*/
void (*set_rq_budget_token)(struct request *, int);
/**
* @get_rq_budget_token: retrieve rq's budget token
*/
int (*get_rq_budget_token)(struct request *);
/**
* @timeout: Called on request timeout.
*/
enum blk_eh_timer_return (*timeout)(struct request *);
/**
* @poll: Called to poll for completion of a specific tag.
*/
int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *);
/**
* @complete: Mark the request as complete.
*/
void (*complete)(struct request *);
/**
* @init_hctx: Called when the block layer side of a hardware queue has
* been set up, allowing the driver to allocate/init matching
* structures.
*/
int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int);
/**
* @exit_hctx: Ditto for exit/teardown.
*/
void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
/**
* @init_request: Called for every command allocated by the block layer
* to allow the driver to set up driver specific data.
*
* Tag greater than or equal to queue_depth is for setting up
* flush request.
*/
int (*init_request)(struct blk_mq_tag_set *set, struct request *,
unsigned int, unsigned int);
/**
* @exit_request: Ditto for exit/teardown.
*/
void (*exit_request)(struct blk_mq_tag_set *set, struct request *,
unsigned int);
/**
* @cleanup_rq: Called before freeing one request which isn't completed
* yet, and usually for freeing the driver private data.
*/
void (*cleanup_rq)(struct request *);
/**
* @busy: If set, returns whether or not this queue currently is busy.
*/
bool (*busy)(struct request_queue *);
/**
* @map_queues: This allows drivers specify their own queue mapping by
* overriding the setup-time function that builds the mq_map.
*/
void (*map_queues)(struct blk_mq_tag_set *set);
#ifdef CONFIG_BLK_DEBUG_FS
/**
* @show_rq: Used by the debugfs implementation to show driver-specific
* information about a request.
*/
void (*show_rq)(struct seq_file *m, struct request *rq);
#endif
};
/* Keep hctx_flag_name[] in sync with the definitions below */
enum {
BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
/*
* Set when this device requires underlying blk-mq device for
* completing IO:
*/
BLK_MQ_F_STACKING = 1 << 2,
BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
BLK_MQ_F_BLOCKING = 1 << 4,
/*
* Alloc tags on a round-robin base instead of the first available one.
*/
BLK_MQ_F_TAG_RR = 1 << 5,
/*
* Select 'none' during queue registration in case of a single hwq
* or shared hwqs instead of 'mq-deadline'.
*/
BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6,
BLK_MQ_F_MAX = 1 << 7,
};
#define BLK_MQ_MAX_DEPTH (10240)
#define BLK_MQ_NO_HCTX_IDX (-1U)
enum {
/* Keep hctx_state_name[] in sync with the definitions below */
BLK_MQ_S_STOPPED,
BLK_MQ_S_TAG_ACTIVE,
BLK_MQ_S_SCHED_RESTART,
/* hw queue is inactive after all its CPUs become offline */
BLK_MQ_S_INACTIVE,
BLK_MQ_S_MAX
};
struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
struct queue_limits *lim, void *queuedata,
struct lock_class_key *lkclass);
#define blk_mq_alloc_disk(set, lim, queuedata) \
({ \
static struct lock_class_key __key; \
\
__blk_mq_alloc_disk(set, lim, queuedata, &__key); \
})
struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
struct lock_class_key *lkclass);
struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
struct queue_limits *lim, void *queuedata);
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q);
void blk_mq_destroy_queue(struct request_queue *);
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops, unsigned int queue_depth,
unsigned int set_flags);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
void blk_mq_free_request(struct request *rq);
int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,
unsigned int poll_flags);
bool blk_mq_queue_inflight(struct request_queue *q);
enum {
/* return when out of requests */
BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0),
/* allocate from reserved pool */
BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1),
/* set RQF_PM */
BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2),
};
struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
blk_mq_req_flags_t flags);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
blk_opf_t opf, blk_mq_req_flags_t flags,
unsigned int hctx_idx);
/*
* Tag address space map.
*/
struct blk_mq_tags {
unsigned int nr_tags;
unsigned int nr_reserved_tags;
unsigned int active_queues;
struct sbitmap_queue bitmap_tags;
struct sbitmap_queue breserved_tags;
struct request **rqs;
struct request **static_rqs;
struct list_head page_list;
/*
* used to clear request reference in rqs[] before freeing one
* request pool
*/
spinlock_t lock;
};
static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags,
unsigned int tag)
{
if (tag < tags->nr_tags) {
prefetch(tags->rqs[tag]);
return tags->rqs[tag];
}
return NULL;
}
enum {
BLK_MQ_UNIQUE_TAG_BITS = 16,
BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1,
};
u32 blk_mq_unique_tag(struct request *rq);
static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag)
{
return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS;
}
static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
{
return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
}
/**
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
* @rq: target request.
*/
static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
{
return READ_ONCE(rq->state);
}
static inline int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
}
static inline int blk_mq_request_completed(struct request *rq)
{
return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
}
/*
*
* Set the state to complete when completing a request from inside ->queue_rq.
* This is used by drivers that want to ensure special complete actions that
* need access to the request are called on failure, e.g. by nvme for
* multipathing.
*/
static inline void blk_mq_set_request_complete(struct request *rq)
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
}
/*
* Complete the request directly instead of deferring it to softirq or
* completing it another CPU. Useful in preemptible instead of an interrupt.
*/
static inline void blk_mq_complete_request_direct(struct request *rq,
void (*complete)(struct request *rq))
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
complete(rq);
}
void blk_mq_start_request(struct request *rq);
void blk_mq_end_request(struct request *rq, blk_status_t error);
void __blk_mq_end_request(struct request *rq, blk_status_t error);
void blk_mq_end_request_batch(struct io_comp_batch *ib);
/*
* Only need start/end time stamping if we have iostat or
* blk stats enabled, or using an IO scheduler.
*/
static inline bool blk_mq_need_time_stamp(struct request *rq)
{
return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
}
static inline bool blk_mq_is_reserved_rq(struct request *rq)
{
return rq->rq_flags & RQF_RESV;
}
/**
* blk_mq_add_to_batch() - add a request to the completion batch
* @req: The request to add to batch
* @iob: The batch to add the request
* @is_error: Specify true if the request failed with an error
* @complete: The completaion handler for the request
*
* Batched completions only work when there is no I/O error and no special
* ->end_io handler.
*
* Return: true when the request was added to the batch, otherwise false
*/
static inline bool blk_mq_add_to_batch(struct request *req,
struct io_comp_batch *iob, bool is_error,
void (*complete)(struct io_comp_batch *))
{
/*
* Check various conditions that exclude batch processing:
* 1) No batch container
* 2) Has scheduler data attached
* 3) Not a passthrough request and end_io set
* 4) Not a passthrough request and failed with an error
*/
if (!iob)
return false;
if (req->rq_flags & RQF_SCHED_TAGS)
return false;
if (!blk_rq_is_passthrough(req)) {
if (req->end_io)
return false;
if (is_error)
return false;
}
if (!iob->complete)
iob->complete = complete;
else if (iob->complete != complete)
return false;
iob->need_ts |= blk_mq_need_time_stamp(req);
rq_list_add_tail(&iob->req_list, req);
return true;
}
void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
void blk_mq_complete_request(struct request *rq);
bool blk_mq_complete_request_remote(struct request *rq);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_stop_hw_queues(struct request_queue *q);
void blk_mq_start_hw_queues(struct request_queue *q);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
void blk_mq_quiesce_queue(struct request_queue *q);
void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set);
void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set);
void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set);
void blk_mq_unquiesce_queue(struct request_queue *q);
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv);
void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
void blk_mq_freeze_queue_nomemsave(struct request_queue *q);
void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q);
static inline unsigned int __must_check
blk_mq_freeze_queue(struct request_queue *q)
{
unsigned int memflags = memalloc_noio_save();
blk_mq_freeze_queue_nomemsave(q);
return memflags;
}
static inline void
blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags)
{
blk_mq_unfreeze_queue_nomemrestore(q);
memalloc_noio_restore(memflags);
}
void blk_freeze_queue_start(struct request_queue *q);
void blk_mq_freeze_queue_wait(struct request_queue *q);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout);
void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
void blk_freeze_queue_start_non_owner(struct request_queue *q);
void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
struct device *dev, unsigned int offset);
void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
void blk_mq_quiesce_queue_nowait(struct request_queue *q);
unsigned int blk_mq_rq_cpu(struct request *rq);
bool __blk_should_fake_timeout(struct request_queue *q);
static inline bool blk_should_fake_timeout(struct request_queue *q)
{
if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) &&
test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
return __blk_should_fake_timeout(q);
return false;
}
/**
* blk_mq_rq_from_pdu - cast a PDU to a request
* @pdu: the PDU (Protocol Data Unit) to be casted
*
* Return: request
*
* Driver command data is immediately after the request. So subtract request
* size to get back to the original request.
*/
static inline struct request *blk_mq_rq_from_pdu(void *pdu)
{
return pdu - sizeof(struct request);
}
/**
* blk_mq_rq_to_pdu - cast a request to a PDU
* @rq: the request to be casted
*
* Return: pointer to the PDU
*
* Driver command data is immediately after the request. So add request to get
* the PDU.
*/
static inline void *blk_mq_rq_to_pdu(struct request *rq)
{
return rq + 1;
}
#define queue_for_each_hw_ctx(q, hctx, i) \
xa_for_each(&(q)->hctx_table, (i), (hctx))
#define hctx_for_each_ctx(hctx, ctx, i) \
for ((i) = 0; (i) < (hctx)->nr_ctx && \
({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
static inline void blk_mq_cleanup_rq(struct request *rq)
{
if (rq->q->mq_ops->cleanup_rq)
rq->q->mq_ops->cleanup_rq(rq);
}
void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
struct lock_class_key *key);
static inline bool rq_is_sync(struct request *rq)
{
return op_is_sync(rq->cmd_flags);
}
void blk_rq_init(struct request_queue *q, struct request *rq);
int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio_set *bs, gfp_t gfp_mask,
int (*bio_ctr)(struct bio *, struct bio *, void *), void *data);
void blk_rq_unprep_clone(struct request *rq);
blk_status_t blk_insert_cloned_request(struct request *rq);
struct rq_map_data {
struct page **pages;
unsigned long offset;
unsigned short page_order;
unsigned short nr_entries;
bool null_mapped;
bool from_user;
};
int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long, gfp_t);
int blk_rq_map_user_io(struct request *, struct rq_map_data *,
void __user *, unsigned long, gfp_t, bool, int, bool, int);
int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, const struct iov_iter *, gfp_t);
int blk_rq_unmap_user(struct bio *);
int blk_rq_map_kern(struct request_queue *, struct request *, void *,
unsigned int, gfp_t);
int blk_rq_append_bio(struct request *rq, struct bio *bio);
void blk_execute_rq_nowait(struct request *rq, bool at_head);
blk_status_t blk_execute_rq(struct request *rq, bool at_head);
bool blk_rq_is_poll(struct request *rq);
struct req_iterator {
struct bvec_iter iter;
struct bio *bio;
};
#define __rq_for_each_bio(_bio, rq) \
if ((rq->bio)) \
for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
#define rq_for_each_segment(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bio_for_each_segment(bvl, _iter.bio, _iter.iter)
#define rq_for_each_bvec(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
#define rq_iter_last(bvec, _iter) \
(_iter.bio->bi_next == NULL && \
bio_iter_last(bvec, _iter.iter))
/*
* blk_rq_pos() : the current sector
* blk_rq_bytes() : bytes left in the entire request
* blk_rq_cur_bytes() : bytes left in the current segment
* blk_rq_sectors() : sectors left in the entire request
* blk_rq_cur_sectors() : sectors left in the current segment
* blk_rq_stats_sectors() : sectors of the entire request used for stats
*/
static inline sector_t blk_rq_pos(const struct request *rq)
{
return rq->__sector;
}
static inline unsigned int blk_rq_bytes(const struct request *rq)
{
return rq->__data_len;
}
static inline int blk_rq_cur_bytes(const struct request *rq)
{
if (!rq->bio)
return 0;
if (!bio_has_data(rq->bio)) /* dataless requests such as discard */
return rq->bio->bi_iter.bi_size;
return bio_iovec(rq->bio).bv_len;
}
static inline unsigned int blk_rq_sectors(const struct request *rq)
{
return blk_rq_bytes(rq) >> SECTOR_SHIFT;
}
static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
{
return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
}
static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
{
return rq->stats_sectors;
}
/*
* Some commands like WRITE SAME have a payload or data transfer size which
* is different from the size of the request. Any driver that supports such
* commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
* calculate the data transfer size.
*/
static inline unsigned int blk_rq_payload_bytes(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return rq->special_vec.bv_len;
return blk_rq_bytes(rq);
}
/*
* Return the first full biovec in the request. The caller needs to check that
* there are any bvecs before calling this helper.
*/
static inline struct bio_vec req_bvec(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return rq->special_vec;
return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
}
static inline unsigned int blk_rq_count_bios(struct request *rq)
{
unsigned int nr_bios = 0;
struct bio *bio;
__rq_for_each_bio(bio, rq)
nr_bios++;
return nr_bios;
}
void blk_steal_bios(struct bio_list *list, struct request *rq);
/*
* Request completion related functions.
*
* blk_update_request() completes given number of bytes and updates
* the request without completing it.
*/
bool blk_update_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes);
void blk_abort_request(struct request *);
/*
* Number of physical segments as sent to the device.
*
* Normally this is the number of discontiguous data segments sent by the
* submitter. But for data-less command like discard we might have no
* actual data segments submitted, but the driver might have to add it's
* own special payload. In that case we still return 1 here so that this
* special payload will be mapped.
*/
static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
{
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
return 1;
return rq->nr_phys_segments;
}
/*
* Number of discard segments (or ranges) the driver needs to fill in.
* Each discard bio merged into a request is counted as one segment.
*/
static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
{
return max_t(unsigned short, rq->nr_phys_segments, 1);
}
int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist,
struct scatterlist **last_sg);
static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
{
struct scatterlist *last_sg = NULL;
return __blk_rq_map_sg(rq, sglist, &last_sg);
}
void blk_dump_rq_flags(struct request *, char *);
#endif /* BLK_MQ_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/exec.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* #!-checking implemented by tytso.
*/
/*
* Demand-loading implemented 01.12.91 - no need to read anything but
* the header into memory. The inode of the executable is put into
* "current->executable", and page faults do the actual loading. Clean.
*
* Once more I can proudly say that linux stood up to being changed: it
* was less than 2 hours work to get demand-loading completely implemented.
*
* Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
* current->executable is only used by the procfs. This allows a dispatch
* table to check for several different types of binary formats. We keep
* trying until we recognize the file or we run out of supported binary
* formats.
*/
#include <linux/kernel_read_file.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/signal.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/task.h>
#include <linux/pagemap.h>
#include <linux/perf_event.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
#include <linux/kmod.h>
#include <linux/fsnotify.h>
#include <linux/fs_struct.h>
#include <linux/oom.h>
#include <linux/compat.h>
#include <linux/vmalloc.h>
#include <linux/io_uring.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/coredump.h>
#include <linux/time_namespace.h>
#include <linux/user_events.h>
#include <linux/rseq.h>
#include <linux/ksm.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
#include <trace/events/task.h>
#include "internal.h"
#include <trace/events/sched.h>
static int bprm_creds_from_file(struct linux_binprm *bprm);
int suid_dumpable = 0;
static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);
void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
write_lock(&binfmt_lock);
insert ? list_add(&fmt->lh, &formats) :
list_add_tail(&fmt->lh, &formats);
write_unlock(&binfmt_lock);
}
EXPORT_SYMBOL(__register_binfmt);
void unregister_binfmt(struct linux_binfmt * fmt)
{
write_lock(&binfmt_lock);
list_del(&fmt->lh);
write_unlock(&binfmt_lock);
}
EXPORT_SYMBOL(unregister_binfmt);
static inline void put_binfmt(struct linux_binfmt * fmt)
{
module_put(fmt->module);
}
bool path_noexec(const struct path *path)
{ return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
}
#ifdef CONFIG_USELIB
/*
* Note that a shared library must be both readable and executable due to
* security reasons.
*
* Also note that we take the address to load from the file itself.
*/
SYSCALL_DEFINE1(uselib, const char __user *, library)
{
struct linux_binfmt *fmt;
struct file *file;
struct filename *tmp = getname(library);
int error = PTR_ERR(tmp);
static const struct open_flags uselib_flags = {
.open_flag = O_LARGEFILE | O_RDONLY,
.acc_mode = MAY_READ | MAY_EXEC,
.intent = LOOKUP_OPEN,
.lookup_flags = LOOKUP_FOLLOW,
};
if (IS_ERR(tmp))
goto out;
file = do_filp_open(AT_FDCWD, tmp, &uselib_flags);
putname(tmp);
error = PTR_ERR(file);
if (IS_ERR(file))
goto out;
/*
* Check do_open_execat() for an explanation.
*/
error = -EACCES;
if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
path_noexec(&file->f_path))
goto exit;
error = -ENOEXEC;
read_lock(&binfmt_lock);
list_for_each_entry(fmt, &formats, lh) {
if (!fmt->load_shlib)
continue;
if (!try_module_get(fmt->module))
continue;
read_unlock(&binfmt_lock);
error = fmt->load_shlib(file);
read_lock(&binfmt_lock);
put_binfmt(fmt);
if (error != -ENOEXEC)
break;
}
read_unlock(&binfmt_lock);
exit:
fput(file);
out:
return error;
}
#endif /* #ifdef CONFIG_USELIB */
#ifdef CONFIG_MMU
/*
* The nascent bprm->mm is not visible until exec_mmap() but it can
* use a lot of memory, account these pages in current->mm temporary
* for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we
* change the counter back via acct_arg_size(0).
*/
static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
struct mm_struct *mm = current->mm;
long diff = (long)(pages - bprm->vma_pages);
if (!mm || !diff)
return;
bprm->vma_pages = pages;
add_mm_counter(mm, MM_ANONPAGES, diff);
}
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
int write)
{
struct page *page;
struct vm_area_struct *vma = bprm->vma;
struct mm_struct *mm = bprm->mm;
int ret;
/*
* Avoid relying on expanding the stack down in GUP (which
* does not work for STACK_GROWSUP anyway), and just do it
* ahead of time.
*/
if (!mmap_read_lock_maybe_expand(mm, vma, pos, write))
return NULL;
/*
* We are doing an exec(). 'current' is the process
* doing the exec and 'mm' is the new process's mm.
*/
ret = get_user_pages_remote(mm, pos, 1,
write ? FOLL_WRITE : 0,
&page, NULL);
mmap_read_unlock(mm);
if (ret <= 0)
return NULL;
if (write)
acct_arg_size(bprm, vma_pages(vma));
return page;
}
static void put_arg_page(struct page *page)
{
put_page(page);
}
static void free_arg_pages(struct linux_binprm *bprm)
{
}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
struct page *page)
{
flush_cache_page(bprm->vma, pos, page_to_pfn(page));
}
static int __bprm_mm_init(struct linux_binprm *bprm)
{
int err;
struct vm_area_struct *vma = NULL;
struct mm_struct *mm = bprm->mm;
bprm->vma = vma = vm_area_alloc(mm);
if (!vma)
return -ENOMEM;
vma_set_anonymous(vma);
if (mmap_write_lock_killable(mm)) {
err = -EINTR;
goto err_free;
}
/*
* Need to be called with mmap write lock
* held, to avoid race with ksmd.
*/
err = ksm_execve(mm);
if (err)
goto err_ksm;
/*
* Place the stack at the largest stack address the architecture
* supports. Later, we'll move this to an appropriate place. We don't
* use STACK_TOP because that can depend on attributes which aren't
* configured yet.
*/
BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
vma->vm_end = STACK_TOP_MAX;
vma->vm_start = vma->vm_end - PAGE_SIZE;
vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP);
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
err = insert_vm_struct(mm, vma);
if (err)
goto err;
mm->stack_vm = mm->total_vm = 1;
mmap_write_unlock(mm);
bprm->p = vma->vm_end - sizeof(void *);
return 0;
err:
ksm_exit(mm);
err_ksm:
mmap_write_unlock(mm);
err_free:
bprm->vma = NULL;
vm_area_free(vma);
return err;
}
static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
return len <= MAX_ARG_STRLEN;
}
#else
static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
}
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
int write)
{
struct page *page;
page = bprm->page[pos / PAGE_SIZE];
if (!page && write) {
page = alloc_page(GFP_HIGHUSER|__GFP_ZERO);
if (!page)
return NULL;
bprm->page[pos / PAGE_SIZE] = page;
}
return page;
}
static void put_arg_page(struct page *page)
{
}
static void free_arg_page(struct linux_binprm *bprm, int i)
{
if (bprm->page[i]) {
__free_page(bprm->page[i]);
bprm->page[i] = NULL;
}
}
static void free_arg_pages(struct linux_binprm *bprm)
{
int i;
for (i = 0; i < MAX_ARG_PAGES; i++)
free_arg_page(bprm, i);
}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
struct page *page)
{
}
static int __bprm_mm_init(struct linux_binprm *bprm)
{
bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
return 0;
}
static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
return len <= bprm->p;
}
#endif /* CONFIG_MMU */
/*
* Create a new mm_struct and populate it with a temporary stack
* vm_area_struct. We don't have enough context at this point to set the stack
* flags, permissions, and offset, so we use temporary values. We'll update
* them later in setup_arg_pages().
*/
static int bprm_mm_init(struct linux_binprm *bprm)
{
int err;
struct mm_struct *mm = NULL;
bprm->mm = mm = mm_alloc();
err = -ENOMEM;
if (!mm)
goto err;
/* Save current stack limit for all calculations made during exec. */
task_lock(current->group_leader);
bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK];
task_unlock(current->group_leader);
err = __bprm_mm_init(bprm);
if (err)
goto err;
return 0;
err:
if (mm) {
bprm->mm = NULL;
mmdrop(mm);
}
return err;
}
struct user_arg_ptr {
#ifdef CONFIG_COMPAT
bool is_compat;
#endif
union {
const char __user *const __user *native;
#ifdef CONFIG_COMPAT
const compat_uptr_t __user *compat;
#endif
} ptr;
};
static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr)
{
const char __user *native;
#ifdef CONFIG_COMPAT
if (unlikely(argv.is_compat)) {
compat_uptr_t compat;
if (get_user(compat, argv.ptr.compat + nr))
return ERR_PTR(-EFAULT);
return compat_ptr(compat);
}
#endif
if (get_user(native, argv.ptr.native + nr))
return ERR_PTR(-EFAULT);
return native;
}
/*
* count() counts the number of strings in array ARGV.
*/
static int count(struct user_arg_ptr argv, int max)
{
int i = 0;
if (argv.ptr.native != NULL) {
for (;;) {
const char __user *p = get_user_arg_ptr(argv, i);
if (!p)
break;
if (IS_ERR(p))
return -EFAULT;
if (i >= max)
return -E2BIG;
++i;
if (fatal_signal_pending(current))
return -ERESTARTNOHAND;
cond_resched();
}
}
return i;
}
static int count_strings_kernel(const char *const *argv)
{
int i;
if (!argv)
return 0;
for (i = 0; argv[i]; ++i) {
if (i >= MAX_ARG_STRINGS)
return -E2BIG;
if (fatal_signal_pending(current))
return -ERESTARTNOHAND;
cond_resched();
}
return i;
}
static inline int bprm_set_stack_limit(struct linux_binprm *bprm,
unsigned long limit)
{
#ifdef CONFIG_MMU
/* Avoid a pathological bprm->p. */
if (bprm->p < limit)
return -E2BIG;
bprm->argmin = bprm->p - limit;
#endif
return 0;
}
static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm)
{
#ifdef CONFIG_MMU
return bprm->p < bprm->argmin;
#else
return false;
#endif
}
/*
* Calculate bprm->argmin from:
* - _STK_LIM
* - ARG_MAX
* - bprm->rlim_stack.rlim_cur
* - bprm->argc
* - bprm->envc
* - bprm->p
*/
static int bprm_stack_limits(struct linux_binprm *bprm)
{
unsigned long limit, ptr_size;
/*
* Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
* (whichever is smaller) for the argv+env strings.
* This ensures that:
* - the remaining binfmt code will not run out of stack space,
* - the program will have a reasonable amount of stack left
* to work from.
*/
limit = _STK_LIM / 4 * 3;
limit = min(limit, bprm->rlim_stack.rlim_cur / 4);
/*
* We've historically supported up to 32 pages (ARG_MAX)
* of argument strings even with small stacks
*/
limit = max_t(unsigned long, limit, ARG_MAX);
/* Reject totally pathological counts. */
if (bprm->argc < 0 || bprm->envc < 0)
return -E2BIG;
/*
* We must account for the size of all the argv and envp pointers to
* the argv and envp strings, since they will also take up space in
* the stack. They aren't stored until much later when we can't
* signal to the parent that the child has run out of stack space.
* Instead, calculate it here so it's possible to fail gracefully.
*
* In the case of argc = 0, make sure there is space for adding a
* empty string (which will bump argc to 1), to ensure confused
* userspace programs don't start processing from argv[1], thinking
* argc can never be 0, to keep them from walking envp by accident.
* See do_execveat_common().
*/
if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) ||
check_mul_overflow(ptr_size, sizeof(void *), &ptr_size))
return -E2BIG;
if (limit <= ptr_size)
return -E2BIG;
limit -= ptr_size;
return bprm_set_stack_limit(bprm, limit);
}
/*
* 'copy_strings()' copies argument/environment strings from the old
* processes's memory to the new process's stack. The call to get_user_pages()
* ensures the destination page is created and not swapped out.
*/
static int copy_strings(int argc, struct user_arg_ptr argv,
struct linux_binprm *bprm)
{
struct page *kmapped_page = NULL;
char *kaddr = NULL;
unsigned long kpos = 0;
int ret;
while (argc-- > 0) {
const char __user *str;
int len;
unsigned long pos;
ret = -EFAULT;
str = get_user_arg_ptr(argv, argc);
if (IS_ERR(str))
goto out;
len = strnlen_user(str, MAX_ARG_STRLEN);
if (!len)
goto out;
ret = -E2BIG;
if (!valid_arg_len(bprm, len))
goto out;
/* We're going to work our way backwards. */
pos = bprm->p;
str += len;
bprm->p -= len;
if (bprm_hit_stack_limit(bprm))
goto out;
while (len > 0) {
int offset, bytes_to_copy;
if (fatal_signal_pending(current)) {
ret = -ERESTARTNOHAND;
goto out;
}
cond_resched();
offset = pos % PAGE_SIZE;
if (offset == 0)
offset = PAGE_SIZE;
bytes_to_copy = offset;
if (bytes_to_copy > len)
bytes_to_copy = len;
offset -= bytes_to_copy;
pos -= bytes_to_copy;
str -= bytes_to_copy;
len -= bytes_to_copy;
if (!kmapped_page || kpos != (pos & PAGE_MASK)) {
struct page *page;
page = get_arg_page(bprm, pos, 1);
if (!page) {
ret = -E2BIG;
goto out;
}
if (kmapped_page) {
flush_dcache_page(kmapped_page);
kunmap_local(kaddr);
put_arg_page(kmapped_page);
}
kmapped_page = page;
kaddr = kmap_local_page(kmapped_page);
kpos = pos & PAGE_MASK;
flush_arg_page(bprm, kpos, kmapped_page);
}
if (copy_from_user(kaddr+offset, str, bytes_to_copy)) {
ret = -EFAULT;
goto out;
}
}
}
ret = 0;
out:
if (kmapped_page) {
flush_dcache_page(kmapped_page);
kunmap_local(kaddr);
put_arg_page(kmapped_page);
}
return ret;
}
/*
* Copy and argument/environment string from the kernel to the processes stack.
*/
int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
{
int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */;
unsigned long pos = bprm->p;
if (len == 0)
return -EFAULT;
if (!valid_arg_len(bprm, len))
return -E2BIG;
/* We're going to work our way backwards. */
arg += len;
bprm->p -= len;
if (bprm_hit_stack_limit(bprm))
return -E2BIG;
while (len > 0) {
unsigned int bytes_to_copy = min_t(unsigned int, len,
min_not_zero(offset_in_page(pos), PAGE_SIZE));
struct page *page;
pos -= bytes_to_copy;
arg -= bytes_to_copy;
len -= bytes_to_copy;
page = get_arg_page(bprm, pos, 1);
if (!page)
return -E2BIG;
flush_arg_page(bprm, pos & PAGE_MASK, page);
memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy);
put_arg_page(page);
}
return 0;
}
EXPORT_SYMBOL(copy_string_kernel);
static int copy_strings_kernel(int argc, const char *const *argv,
struct linux_binprm *bprm)
{
while (argc-- > 0) {
int ret = copy_string_kernel(argv[argc], bprm);
if (ret < 0)
return ret;
if (fatal_signal_pending(current))
return -ERESTARTNOHAND;
cond_resched();
}
return 0;
}
#ifdef CONFIG_MMU
/*
* Finalizes the stack vm_area_struct. The flags and permissions are updated,
* the stack is optionally relocated, and some extra space is added.
*/
int setup_arg_pages(struct linux_binprm *bprm,
unsigned long stack_top,
int executable_stack)
{
unsigned long ret;
unsigned long stack_shift;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = bprm->vma;
struct vm_area_struct *prev = NULL;
unsigned long vm_flags;
unsigned long stack_base;
unsigned long stack_size;
unsigned long stack_expand;
unsigned long rlim_stack;
struct mmu_gather tlb;
struct vma_iterator vmi;
#ifdef CONFIG_STACK_GROWSUP
/* Limit stack size */
stack_base = bprm->rlim_stack.rlim_max;
stack_base = calc_max_stack_size(stack_base);
/* Add space for stack randomization. */
if (current->flags & PF_RANDOMIZE)
stack_base += (STACK_RND_MASK << PAGE_SHIFT);
/* Make sure we didn't let the argument array grow too large. */
if (vma->vm_end - vma->vm_start > stack_base)
return -ENOMEM;
stack_base = PAGE_ALIGN(stack_top - stack_base);
stack_shift = vma->vm_start - stack_base;
mm->arg_start = bprm->p - stack_shift;
bprm->p = vma->vm_end - stack_shift;
#else
stack_top = arch_align_stack(stack_top);
stack_top = PAGE_ALIGN(stack_top);
if (unlikely(stack_top < mmap_min_addr) ||
unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr))
return -ENOMEM;
stack_shift = vma->vm_end - stack_top;
bprm->p -= stack_shift;
mm->arg_start = bprm->p;
#endif
bprm->exec -= stack_shift;
if (mmap_write_lock_killable(mm))
return -EINTR;
vm_flags = VM_STACK_FLAGS;
/*
* Adjust stack execute permissions; explicitly enable for
* EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone
* (arch default) otherwise.
*/
if (unlikely(executable_stack == EXSTACK_ENABLE_X))
vm_flags |= VM_EXEC;
else if (executable_stack == EXSTACK_DISABLE_X)
vm_flags &= ~VM_EXEC;
vm_flags |= mm->def_flags;
vm_flags |= VM_STACK_INCOMPLETE_SETUP;
vma_iter_init(&vmi, mm, vma->vm_start);
tlb_gather_mmu(&tlb, mm);
ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end,
vm_flags);
tlb_finish_mmu(&tlb);
if (ret)
goto out_unlock;
BUG_ON(prev != vma);
if (unlikely(vm_flags & VM_EXEC)) {
pr_warn_once("process '%pD4' started with executable stack\n",
bprm->file);
}
/* Move stack pages down in memory. */
if (stack_shift) {
/*
* During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once
* the binfmt code determines where the new stack should reside, we shift it to
* its final location.
*/
ret = relocate_vma_down(vma, stack_shift);
if (ret)
goto out_unlock;
}
/* mprotect_fixup is overkill to remove the temporary stack flags */
vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP);
stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
stack_size = vma->vm_end - vma->vm_start;
/*
* Align this down to a page boundary as expand_stack
* will align it up.
*/
rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK;
stack_expand = min(rlim_stack, stack_size + stack_expand);
#ifdef CONFIG_STACK_GROWSUP
stack_base = vma->vm_start + stack_expand;
#else
stack_base = vma->vm_end - stack_expand;
#endif
current->mm->start_stack = bprm->p;
ret = expand_stack_locked(vma, stack_base);
if (ret)
ret = -EFAULT;
out_unlock:
mmap_write_unlock(mm);
return ret;
}
EXPORT_SYMBOL(setup_arg_pages);
#else
/*
* Transfer the program arguments and environment from the holding pages
* onto the stack. The provided stack pointer is adjusted accordingly.
*/
int transfer_args_to_stack(struct linux_binprm *bprm,
unsigned long *sp_location)
{
unsigned long index, stop, sp;
int ret = 0;
stop = bprm->p >> PAGE_SHIFT;
sp = *sp_location;
for (index = MAX_ARG_PAGES - 1; index >= stop; index--) {
unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0;
char *src = kmap_local_page(bprm->page[index]) + offset;
sp -= PAGE_SIZE - offset;
if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0)
ret = -EFAULT;
kunmap_local(src);
if (ret)
goto out;
}
bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE;
*sp_location = sp;
out:
return ret;
}
EXPORT_SYMBOL(transfer_args_to_stack);
#endif /* CONFIG_MMU */
/*
* On success, caller must call do_close_execat() on the returned
* struct file to close it.
*/
static struct file *do_open_execat(int fd, struct filename *name, int flags)
{
int err;
struct file *file __free(fput) = NULL;
struct open_flags open_exec_flags = {
.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
.acc_mode = MAY_EXEC,
.intent = LOOKUP_OPEN,
.lookup_flags = LOOKUP_FOLLOW,
};
if ((flags &
~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0)
return ERR_PTR(-EINVAL);
if (flags & AT_SYMLINK_NOFOLLOW)
open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
if (flags & AT_EMPTY_PATH)
open_exec_flags.lookup_flags |= LOOKUP_EMPTY;
file = do_filp_open(fd, name, &open_exec_flags);
if (IS_ERR(file))
return file;
/*
* In the past the regular type check was here. It moved to may_open() in
* 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is
* an invariant that all non-regular files error out before we get here.
*/
if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
path_noexec(&file->f_path))
return ERR_PTR(-EACCES);
err = exe_file_deny_write_access(file);
if (err)
return ERR_PTR(err);
return no_free_ptr(file);
}
/**
* open_exec - Open a path name for execution
*
* @name: path name to open with the intent of executing it.
*
* Returns ERR_PTR on failure or allocated struct file on success.
*
* As this is a wrapper for the internal do_open_execat(), callers
* must call exe_file_allow_write_access() before fput() on release. Also see
* do_close_execat().
*/
struct file *open_exec(const char *name)
{
struct filename *filename = getname_kernel(name);
struct file *f = ERR_CAST(filename);
if (!IS_ERR(filename)) {
f = do_open_execat(AT_FDCWD, filename, 0);
putname(filename);
}
return f;
}
EXPORT_SYMBOL(open_exec);
#if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC)
ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
{
ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
if (res > 0)
flush_icache_user_range(addr, addr + len);
return res;
}
EXPORT_SYMBOL(read_code);
#endif
/*
* Maps the mm_struct mm into the current task struct.
* On success, this function returns with exec_update_lock
* held for writing.
*/
static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
struct mm_struct *old_mm, *active_mm;
int ret;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
exec_mm_release(tsk, old_mm);
ret = down_write_killable(&tsk->signal->exec_update_lock);
if (ret)
return ret;
if (old_mm) {
/*
* If there is a pending fatal signal perhaps a signal
* whose default action is to create a coredump get
* out and die instead of going through with the exec.
*/
ret = mmap_read_lock_killable(old_mm);
if (ret) {
up_write(&tsk->signal->exec_update_lock);
return ret;
}
}
task_lock(tsk);
membarrier_exec_mmap(mm);
local_irq_disable();
active_mm = tsk->active_mm;
tsk->active_mm = mm;
tsk->mm = mm;
mm_init_cid(mm, tsk);
/*
* This prevents preemption while active_mm is being loaded and
* it and mm are being updated, which could cause problems for
* lazy tlb mm refcounting when these are updated by context
* switches. Not all architectures can handle irqs off over
* activate_mm yet.
*/
if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
activate_mm(active_mm, mm);
if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
lru_gen_add_mm(mm);
task_unlock(tsk);
lru_gen_use_mm(mm);
if (old_mm) {
mmap_read_unlock(old_mm);
BUG_ON(active_mm != old_mm);
setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
mm_update_next_owner(old_mm);
mmput(old_mm);
return 0;
}
mmdrop_lazy_tlb(active_mm);
return 0;
}
static int de_thread(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
struct sighand_struct *oldsighand = tsk->sighand;
spinlock_t *lock = &oldsighand->siglock;
if (thread_group_empty(tsk))
goto no_thread_group;
/*
* Kill all other threads in the thread group.
*/
spin_lock_irq(lock);
if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) {
/*
* Another group action in progress, just
* return so that the signal is processed.
*/
spin_unlock_irq(lock);
return -EAGAIN;
}
sig->group_exec_task = tsk;
sig->notify_count = zap_other_threads(tsk);
if (!thread_group_leader(tsk))
sig->notify_count--;
while (sig->notify_count) {
__set_current_state(TASK_KILLABLE);
spin_unlock_irq(lock);
schedule();
if (__fatal_signal_pending(tsk))
goto killed;
spin_lock_irq(lock);
}
spin_unlock_irq(lock);
/*
* At this point all other threads have exited, all we have to
* do is to wait for the thread group leader to become inactive,
* and to assume its PID:
*/
if (!thread_group_leader(tsk)) {
struct task_struct *leader = tsk->group_leader;
for (;;) {
cgroup_threadgroup_change_begin(tsk);
write_lock_irq(&tasklist_lock);
/*
* Do this under tasklist_lock to ensure that
* exit_notify() can't miss ->group_exec_task
*/
sig->notify_count = -1;
if (likely(leader->exit_state))
break;
__set_current_state(TASK_KILLABLE);
write_unlock_irq(&tasklist_lock);
cgroup_threadgroup_change_end(tsk);
schedule();
if (__fatal_signal_pending(tsk))
goto killed;
}
/*
* The only record we have of the real-time age of a
* process, regardless of execs it's done, is start_time.
* All the past CPU time is accumulated in signal_struct
* from sister threads now dead. But in this non-leader
* exec, nothing survives from the original leader thread,
* whose birth marks the true age of this process now.
* When we take on its identity by switching to its PID, we
* also take its birthdate (always earlier than our own).
*/
tsk->start_time = leader->start_time;
tsk->start_boottime = leader->start_boottime;
BUG_ON(!same_thread_group(leader, tsk));
/*
* An exec() starts a new thread group with the
* TGID of the previous thread group. Rehash the
* two threads with a switched PID, and release
* the former thread group leader:
*/
/* Become a process group leader with the old leader's pid.
* The old leader becomes a thread of the this thread group.
*/
exchange_tids(tsk, leader);
transfer_pid(leader, tsk, PIDTYPE_TGID);
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks);
list_replace_init(&leader->sibling, &tsk->sibling);
tsk->group_leader = tsk;
leader->group_leader = tsk;
tsk->exit_signal = SIGCHLD;
leader->exit_signal = -1;
BUG_ON(leader->exit_state != EXIT_ZOMBIE);
leader->exit_state = EXIT_DEAD;
/*
* We are going to release_task()->ptrace_unlink() silently,
* the tracer can sleep in do_wait(). EXIT_DEAD guarantees
* the tracer won't block again waiting for this thread.
*/
if (unlikely(leader->ptrace))
__wake_up_parent(leader, leader->parent);
write_unlock_irq(&tasklist_lock);
cgroup_threadgroup_change_end(tsk);
release_task(leader);
}
sig->group_exec_task = NULL;
sig->notify_count = 0;
no_thread_group:
/* we have changed execution domain */
tsk->exit_signal = SIGCHLD;
BUG_ON(!thread_group_leader(tsk));
return 0;
killed:
/* protects against exit_notify() and __exit_signal() */
read_lock(&tasklist_lock);
sig->group_exec_task = NULL;
sig->notify_count = 0;
read_unlock(&tasklist_lock);
return -EAGAIN;
}
/*
* This function makes sure the current process has its own signal table,
* so that flush_signal_handlers can later reset the handlers without
* disturbing other processes. (Other processes might share the signal
* table via the CLONE_SIGHAND option to clone().)
*/
static int unshare_sighand(struct task_struct *me)
{
struct sighand_struct *oldsighand = me->sighand;
if (refcount_read(&oldsighand->count) != 1) {
struct sighand_struct *newsighand;
/*
* This ->sighand is shared with the CLONE_SIGHAND
* but not CLONE_THREAD task, switch to the new one.
*/
newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
if (!newsighand)
return -ENOMEM;
refcount_set(&newsighand->count, 1);
write_lock_irq(&tasklist_lock);
spin_lock(&oldsighand->siglock);
memcpy(newsighand->action, oldsighand->action,
sizeof(newsighand->action));
rcu_assign_pointer(me->sighand, newsighand);
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
__cleanup_sighand(oldsighand);
}
return 0;
}
/*
* This is unlocked -- the string will always be NUL-terminated, but
* may show overlapping contents if racing concurrent reads.
*/
void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
{
size_t len = min(strlen(buf), sizeof(tsk->comm) - 1);
trace_task_rename(tsk, buf);
memcpy(tsk->comm, buf, len);
memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len);
perf_event_comm(tsk, exec);
}
/*
* Calling this is the point of no return. None of the failures will be
* seen by userspace since either the process is already taking a fatal
* signal (via de_thread() or coredump), or will have SEGV raised
* (after exec_mmap()) by search_binary_handler (see below).
*/
int begin_new_exec(struct linux_binprm * bprm)
{
struct task_struct *me = current;
int retval;
/* Once we are committed compute the creds */
retval = bprm_creds_from_file(bprm);
if (retval)
return retval;
/*
* This tracepoint marks the point before flushing the old exec where
* the current task is still unchanged, but errors are fatal (point of
* no return). The later "sched_process_exec" tracepoint is called after
* the current task has successfully switched to the new exec.
*/
trace_sched_prepare_exec(current, bprm);
/*
* Ensure all future errors are fatal.
*/
bprm->point_of_no_return = true;
/* Make this the only thread in the thread group */
retval = de_thread(me);
if (retval)
goto out;
/* see the comment in check_unsafe_exec() */
current->fs->in_exec = 0;
/*
* Cancel any io_uring activity across execve
*/
io_uring_task_cancel();
/* Ensure the files table is not shared. */
retval = unshare_files();
if (retval)
goto out;
/*
* Must be called _before_ exec_mmap() as bprm->mm is
* not visible until then. Doing it here also ensures
* we don't race against replace_mm_exe_file().
*/
retval = set_mm_exe_file(bprm->mm, bprm->file);
if (retval)
goto out;
/* If the binary is not readable then enforce mm->dumpable=0 */
would_dump(bprm, bprm->file);
if (bprm->have_execfd)
would_dump(bprm, bprm->executable);
/*
* Release all of the old mmap stuff
*/
acct_arg_size(bprm, 0);
retval = exec_mmap(bprm->mm);
if (retval)
goto out;
bprm->mm = NULL;
retval = exec_task_namespaces();
if (retval)
goto out_unlock;
#ifdef CONFIG_POSIX_TIMERS
spin_lock_irq(&me->sighand->siglock);
posix_cpu_timers_exit(me);
spin_unlock_irq(&me->sighand->siglock);
exit_itimers(me);
flush_itimer_signals();
#endif
/*
* Make the signal table private.
*/
retval = unshare_sighand(me);
if (retval)
goto out_unlock;
me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC |
PF_NOFREEZE | PF_NO_SETAFFINITY);
flush_thread();
me->personality &= ~bprm->per_clear;
clear_syscall_work_syscall_user_dispatch(me);
/*
* We have to apply CLOEXEC before we change whether the process is
* dumpable (in setup_new_exec) to avoid a race with a process in userspace
* trying to access the should-be-closed file descriptors of a process
* undergoing exec(2).
*/
do_close_on_exec(me->files);
if (bprm->secureexec) {
/* Make sure parent cannot signal privileged process. */
me->pdeath_signal = 0;
/*
* For secureexec, reset the stack limit to sane default to
* avoid bad behavior from the prior rlimits. This has to
* happen before arch_pick_mmap_layout(), which examines
* RLIMIT_STACK, but after the point of no return to avoid
* needing to clean up the change on failure.
*/
if (bprm->rlim_stack.rlim_cur > _STK_LIM)
bprm->rlim_stack.rlim_cur = _STK_LIM;
}
me->sas_ss_sp = me->sas_ss_size = 0;
/*
* Figure out dumpability. Note that this checking only of current
* is wrong, but userspace depends on it. This should be testing
* bprm->secureexec instead.
*/
if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
!(uid_eq(current_euid(), current_uid()) &&
gid_eq(current_egid(), current_gid())))
set_dumpable(current->mm, suid_dumpable);
else
set_dumpable(current->mm, SUID_DUMP_USER);
perf_event_exec();
/*
* If the original filename was empty, alloc_bprm() made up a path
* that will probably not be useful to admins running ps or similar.
* Let's fix it up to be something reasonable.
*/
if (bprm->comm_from_dentry) {
/*
* Hold RCU lock to keep the name from being freed behind our back.
* Use acquire semantics to make sure the terminating NUL from
* __d_alloc() is seen.
*
* Note, we're deliberately sloppy here. We don't need to care about
* detecting a concurrent rename and just want a terminated name.
*/
rcu_read_lock();
__set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name),
true);
rcu_read_unlock();
} else {
__set_task_comm(me, kbasename(bprm->filename), true);
}
/* An exec changes our domain. We are no longer part of the thread
group */
WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1);
flush_signal_handlers(me, 0);
retval = set_cred_ucounts(bprm->cred);
if (retval < 0)
goto out_unlock;
/*
* install the new credentials for this executable
*/
security_bprm_committing_creds(bprm);
commit_creds(bprm->cred);
bprm->cred = NULL;
/*
* Disable monitoring for regular users
* when executing setuid binaries. Must
* wait until new credentials are committed
* by commit_creds() above
*/
if (get_dumpable(me->mm) != SUID_DUMP_USER)
perf_event_exit_task(me);
/*
* cred_guard_mutex must be held at least to this point to prevent
* ptrace_attach() from altering our determination of the task's
* credentials; any time after this it may be unlocked.
*/
security_bprm_committed_creds(bprm);
/* Pass the opened binary to the interpreter. */
if (bprm->have_execfd) {
retval = get_unused_fd_flags(0);
if (retval < 0)
goto out_unlock;
fd_install(retval, bprm->executable);
bprm->executable = NULL;
bprm->execfd = retval;
}
return 0;
out_unlock:
up_write(&me->signal->exec_update_lock);
if (!bprm->cred)
mutex_unlock(&me->signal->cred_guard_mutex);
out:
return retval;
}
EXPORT_SYMBOL(begin_new_exec);
void would_dump(struct linux_binprm *bprm, struct file *file)
{
struct inode *inode = file_inode(file);
struct mnt_idmap *idmap = file_mnt_idmap(file);
if (inode_permission(idmap, inode, MAY_READ) < 0) {
struct user_namespace *old, *user_ns;
bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
/* Ensure mm->user_ns contains the executable */
user_ns = old = bprm->mm->user_ns;
while ((user_ns != &init_user_ns) &&
!privileged_wrt_inode_uidgid(user_ns, idmap, inode))
user_ns = user_ns->parent;
if (old != user_ns) {
bprm->mm->user_ns = get_user_ns(user_ns);
put_user_ns(old);
}
}
}
EXPORT_SYMBOL(would_dump);
void setup_new_exec(struct linux_binprm * bprm)
{
/* Setup things that can depend upon the personality */
struct task_struct *me = current;
arch_pick_mmap_layout(me->mm, &bprm->rlim_stack);
arch_setup_new_exec();
/* Set the new mm task size. We have to do that late because it may
* depend on TIF_32BIT which is only updated in flush_thread() on
* some architectures like powerpc
*/
me->mm->task_size = TASK_SIZE;
up_write(&me->signal->exec_update_lock);
mutex_unlock(&me->signal->cred_guard_mutex);
}
EXPORT_SYMBOL(setup_new_exec);
/* Runs immediately before start_thread() takes over. */
void finalize_exec(struct linux_binprm *bprm)
{
/* Store any stack rlimit changes before starting thread. */
task_lock(current->group_leader);
current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack;
task_unlock(current->group_leader);
}
EXPORT_SYMBOL(finalize_exec);
/*
* Prepare credentials and lock ->cred_guard_mutex.
* setup_new_exec() commits the new creds and drops the lock.
* Or, if exec fails before, free_bprm() should release ->cred
* and unlock.
*/
static int prepare_bprm_creds(struct linux_binprm *bprm)
{
if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex))
return -ERESTARTNOINTR;
bprm->cred = prepare_exec_creds();
if (likely(bprm->cred))
return 0;
mutex_unlock(¤t->signal->cred_guard_mutex);
return -ENOMEM;
}
/* Matches do_open_execat() */
static void do_close_execat(struct file *file)
{
if (!file)
return;
exe_file_allow_write_access(file);
fput(file);
}
static void free_bprm(struct linux_binprm *bprm)
{
if (bprm->mm) {
acct_arg_size(bprm, 0);
mmput(bprm->mm);
}
free_arg_pages(bprm);
if (bprm->cred) {
/* in case exec fails before de_thread() succeeds */
current->fs->in_exec = 0;
mutex_unlock(¤t->signal->cred_guard_mutex);
abort_creds(bprm->cred);
}
do_close_execat(bprm->file);
if (bprm->executable)
fput(bprm->executable);
/* If a binfmt changed the interp, free it. */
if (bprm->interp != bprm->filename)
kfree(bprm->interp);
kfree(bprm->fdpath);
kfree(bprm);
}
static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags)
{
struct linux_binprm *bprm;
struct file *file;
int retval = -ENOMEM;
file = do_open_execat(fd, filename, flags);
if (IS_ERR(file))
return ERR_CAST(file);
bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
if (!bprm) {
do_close_execat(file);
return ERR_PTR(-ENOMEM);
}
bprm->file = file;
if (fd == AT_FDCWD || filename->name[0] == '/') {
bprm->filename = filename->name;
} else {
if (filename->name[0] == '\0') {
bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd);
bprm->comm_from_dentry = 1;
} else {
bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s",
fd, filename->name);
}
if (!bprm->fdpath)
goto out_free;
/*
* Record that a name derived from an O_CLOEXEC fd will be
* inaccessible after exec. This allows the code in exec to
* choose to fail when the executable is not mmaped into the
* interpreter and an open file descriptor is not passed to
* the interpreter. This makes for a better user experience
* than having the interpreter start and then immediately fail
* when it finds the executable is inaccessible.
*/
if (get_close_on_exec(fd))
bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
bprm->filename = bprm->fdpath;
}
bprm->interp = bprm->filename;
/*
* At this point, security_file_open() has already been called (with
* __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will
* stop just after the security_bprm_creds_for_exec() call in
* bprm_execve(). Indeed, the kernel should not try to parse the
* content of the file with exec_binprm() nor change the calling
* thread, which means that the following security functions will not
* be called:
* - security_bprm_check()
* - security_bprm_creds_from_file()
* - security_bprm_committing_creds()
* - security_bprm_committed_creds()
*/
bprm->is_check = !!(flags & AT_EXECVE_CHECK);
retval = bprm_mm_init(bprm);
if (!retval)
return bprm;
out_free:
free_bprm(bprm);
return ERR_PTR(retval);
}
int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
{
/* If a binfmt changed the interp, free it first. */
if (bprm->interp != bprm->filename)
kfree(bprm->interp);
bprm->interp = kstrdup(interp, GFP_KERNEL);
if (!bprm->interp)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(bprm_change_interp);
/*
* determine how safe it is to execute the proposed program
* - the caller must hold ->cred_guard_mutex to protect against
* PTRACE_ATTACH or seccomp thread-sync
*/
static void check_unsafe_exec(struct linux_binprm *bprm)
{
struct task_struct *p = current, *t;
unsigned n_fs;
if (p->ptrace)
bprm->unsafe |= LSM_UNSAFE_PTRACE;
/*
* This isn't strictly necessary, but it makes it harder for LSMs to
* mess up.
*/
if (task_no_new_privs(current))
bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
/*
* If another task is sharing our fs, we cannot safely
* suid exec because the differently privileged task
* will be able to manipulate the current directory, etc.
* It would be nice to force an unshare instead...
*
* Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS)
* from another sub-thread until de_thread() succeeds, this
* state is protected by cred_guard_mutex we hold.
*/
n_fs = 1;
spin_lock(&p->fs->lock);
rcu_read_lock();
for_other_threads(p, t) {
if (t->fs == p->fs)
n_fs++;
}
rcu_read_unlock();
/* "users" and "in_exec" locked for copy_fs() */
if (p->fs->users > n_fs)
bprm->unsafe |= LSM_UNSAFE_SHARE;
else
p->fs->in_exec = 1;
spin_unlock(&p->fs->lock);
}
static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
{
/* Handle suid and sgid on files */
struct mnt_idmap *idmap;
struct inode *inode = file_inode(file);
unsigned int mode;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
int err;
if (!mnt_may_suid(file->f_path.mnt))
return;
if (task_no_new_privs(current))
return;
mode = READ_ONCE(inode->i_mode);
if (!(mode & (S_ISUID|S_ISGID)))
return;
idmap = file_mnt_idmap(file);
/* Be careful if suid/sgid is set */
inode_lock(inode);
/* Atomically reload and check mode/uid/gid now that lock held. */
mode = inode->i_mode;
vfsuid = i_uid_into_vfsuid(idmap, inode);
vfsgid = i_gid_into_vfsgid(idmap, inode);
err = inode_permission(idmap, inode, MAY_EXEC);
inode_unlock(inode);
/* Did the exec bit vanish out from under us? Give up. */
if (err)
return;
/* We ignore suid/sgid if there are no mappings for them in the ns */
if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) ||
!vfsgid_has_mapping(bprm->cred->user_ns, vfsgid))
return;
if (mode & S_ISUID) {
bprm->per_clear |= PER_CLEAR_ON_SETID;
bprm->cred->euid = vfsuid_into_kuid(vfsuid);
}
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
bprm->per_clear |= PER_CLEAR_ON_SETID;
bprm->cred->egid = vfsgid_into_kgid(vfsgid);
}
}
/*
* Compute brpm->cred based upon the final binary.
*/
static int bprm_creds_from_file(struct linux_binprm *bprm)
{
/* Compute creds based on which file? */
struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file;
bprm_fill_uid(bprm, file);
return security_bprm_creds_from_file(bprm, file);
}
/*
* Fill the binprm structure from the inode.
* Read the first BINPRM_BUF_SIZE bytes
*
* This may be called multiple times for binary chains (scripts for example).
*/
static int prepare_binprm(struct linux_binprm *bprm)
{
loff_t pos = 0;
memset(bprm->buf, 0, BINPRM_BUF_SIZE);
return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos);
}
/*
* Arguments are '\0' separated strings found at the location bprm->p
* points to; chop off the first by relocating brpm->p to right after
* the first '\0' encountered.
*/
int remove_arg_zero(struct linux_binprm *bprm)
{
unsigned long offset;
char *kaddr;
struct page *page;
if (!bprm->argc)
return 0;
do {
offset = bprm->p & ~PAGE_MASK;
page = get_arg_page(bprm, bprm->p, 0);
if (!page)
return -EFAULT;
kaddr = kmap_local_page(page);
for (; offset < PAGE_SIZE && kaddr[offset];
offset++, bprm->p++)
;
kunmap_local(kaddr);
put_arg_page(page);
} while (offset == PAGE_SIZE);
bprm->p++;
bprm->argc--;
return 0;
}
EXPORT_SYMBOL(remove_arg_zero);
/*
* cycle the list of binary formats handler, until one recognizes the image
*/
static int search_binary_handler(struct linux_binprm *bprm)
{
struct linux_binfmt *fmt;
int retval;
retval = prepare_binprm(bprm);
if (retval < 0)
return retval;
retval = security_bprm_check(bprm);
if (retval)
return retval;
read_lock(&binfmt_lock);
list_for_each_entry(fmt, &formats, lh) {
if (!try_module_get(fmt->module))
continue;
read_unlock(&binfmt_lock);
retval = fmt->load_binary(bprm);
read_lock(&binfmt_lock);
put_binfmt(fmt);
if (bprm->point_of_no_return || (retval != -ENOEXEC)) {
read_unlock(&binfmt_lock);
return retval;
}
}
read_unlock(&binfmt_lock);
return -ENOEXEC;
}
/* binfmt handlers will call back into begin_new_exec() on success. */
static int exec_binprm(struct linux_binprm *bprm)
{
pid_t old_pid, old_vpid;
int ret, depth;
/* Need to fetch pid before load_binary changes it */
old_pid = current->pid;
rcu_read_lock();
old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
rcu_read_unlock();
/* This allows 4 levels of binfmt rewrites before failing hard. */
for (depth = 0;; depth++) {
struct file *exec;
if (depth > 5)
return -ELOOP;
ret = search_binary_handler(bprm);
if (ret < 0)
return ret;
if (!bprm->interpreter)
break;
exec = bprm->file;
bprm->file = bprm->interpreter;
bprm->interpreter = NULL;
exe_file_allow_write_access(exec);
if (unlikely(bprm->have_execfd)) {
if (bprm->executable) {
fput(exec);
return -ENOEXEC;
}
bprm->executable = exec;
} else
fput(exec);
}
audit_bprm(bprm);
trace_sched_process_exec(current, old_pid, bprm);
ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
proc_exec_connector(current);
return 0;
}
static int bprm_execve(struct linux_binprm *bprm)
{
int retval;
retval = prepare_bprm_creds(bprm);
if (retval)
return retval;
/*
* Check for unsafe execution states before exec_binprm(), which
* will call back into begin_new_exec(), into bprm_creds_from_file(),
* where setuid-ness is evaluated.
*/
check_unsafe_exec(bprm);
current->in_execve = 1;
sched_mm_cid_before_execve(current);
sched_exec();
/* Set the unchanging part of bprm->cred */
retval = security_bprm_creds_for_exec(bprm);
if (retval || bprm->is_check)
goto out;
retval = exec_binprm(bprm);
if (retval < 0)
goto out;
sched_mm_cid_after_execve(current);
rseq_execve(current);
/* execve succeeded */
current->in_execve = 0;
user_events_execve(current);
acct_update_integrals(current);
task_numa_free(current, false);
return retval;
out:
/*
* If past the point of no return ensure the code never
* returns to the userspace process. Use an existing fatal
* signal if present otherwise terminate the process with
* SIGSEGV.
*/
if (bprm->point_of_no_return && !fatal_signal_pending(current))
force_fatal_sig(SIGSEGV);
sched_mm_cid_after_execve(current);
rseq_set_notify_resume(current);
current->in_execve = 0;
return retval;
}
static int do_execveat_common(int fd, struct filename *filename,
struct user_arg_ptr argv,
struct user_arg_ptr envp,
int flags)
{
struct linux_binprm *bprm;
int retval;
if (IS_ERR(filename))
return PTR_ERR(filename);
/*
* We move the actual failure in case of RLIMIT_NPROC excess from
* set*uid() to execve() because too many poorly written programs
* don't check setuid() return code. Here we additionally recheck
* whether NPROC limit is still exceeded.
*/
if ((current->flags & PF_NPROC_EXCEEDED) &&
is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
retval = -EAGAIN;
goto out_ret;
}
/* We're below the limit (still or again), so we don't want to make
* further execve() calls fail. */
current->flags &= ~PF_NPROC_EXCEEDED;
bprm = alloc_bprm(fd, filename, flags);
if (IS_ERR(bprm)) {
retval = PTR_ERR(bprm);
goto out_ret;
}
retval = count(argv, MAX_ARG_STRINGS);
if (retval < 0)
goto out_free;
bprm->argc = retval;
retval = count(envp, MAX_ARG_STRINGS);
if (retval < 0)
goto out_free;
bprm->envc = retval;
retval = bprm_stack_limits(bprm);
if (retval < 0)
goto out_free;
retval = copy_string_kernel(bprm->filename, bprm);
if (retval < 0)
goto out_free;
bprm->exec = bprm->p;
retval = copy_strings(bprm->envc, envp, bprm);
if (retval < 0)
goto out_free;
retval = copy_strings(bprm->argc, argv, bprm);
if (retval < 0)
goto out_free;
/*
* When argv is empty, add an empty string ("") as argv[0] to
* ensure confused userspace programs that start processing
* from argv[1] won't end up walking envp. See also
* bprm_stack_limits().
*/
if (bprm->argc == 0) {
retval = copy_string_kernel("", bprm);
if (retval < 0)
goto out_free;
bprm->argc = 1;
pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n",
current->comm, bprm->filename);
}
retval = bprm_execve(bprm);
out_free:
free_bprm(bprm);
out_ret:
putname(filename);
return retval;
}
int kernel_execve(const char *kernel_filename,
const char *const *argv, const char *const *envp)
{
struct filename *filename;
struct linux_binprm *bprm;
int fd = AT_FDCWD;
int retval;
/* It is non-sense for kernel threads to call execve */
if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
return -EINVAL;
filename = getname_kernel(kernel_filename);
if (IS_ERR(filename))
return PTR_ERR(filename);
bprm = alloc_bprm(fd, filename, 0);
if (IS_ERR(bprm)) {
retval = PTR_ERR(bprm);
goto out_ret;
}
retval = count_strings_kernel(argv);
if (WARN_ON_ONCE(retval == 0))
retval = -EINVAL;
if (retval < 0)
goto out_free;
bprm->argc = retval;
retval = count_strings_kernel(envp);
if (retval < 0)
goto out_free;
bprm->envc = retval;
retval = bprm_stack_limits(bprm);
if (retval < 0)
goto out_free;
retval = copy_string_kernel(bprm->filename, bprm);
if (retval < 0)
goto out_free;
bprm->exec = bprm->p;
retval = copy_strings_kernel(bprm->envc, envp, bprm);
if (retval < 0)
goto out_free;
retval = copy_strings_kernel(bprm->argc, argv, bprm);
if (retval < 0)
goto out_free;
retval = bprm_execve(bprm);
out_free:
free_bprm(bprm);
out_ret:
putname(filename);
return retval;
}
static int do_execve(struct filename *filename,
const char __user *const __user *__argv,
const char __user *const __user *__envp)
{
struct user_arg_ptr argv = { .ptr.native = __argv };
struct user_arg_ptr envp = { .ptr.native = __envp };
return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
}
static int do_execveat(int fd, struct filename *filename,
const char __user *const __user *__argv,
const char __user *const __user *__envp,
int flags)
{
struct user_arg_ptr argv = { .ptr.native = __argv };
struct user_arg_ptr envp = { .ptr.native = __envp };
return do_execveat_common(fd, filename, argv, envp, flags);
}
#ifdef CONFIG_COMPAT
static int compat_do_execve(struct filename *filename,
const compat_uptr_t __user *__argv,
const compat_uptr_t __user *__envp)
{
struct user_arg_ptr argv = {
.is_compat = true,
.ptr.compat = __argv,
};
struct user_arg_ptr envp = {
.is_compat = true,
.ptr.compat = __envp,
};
return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
}
static int compat_do_execveat(int fd, struct filename *filename,
const compat_uptr_t __user *__argv,
const compat_uptr_t __user *__envp,
int flags)
{
struct user_arg_ptr argv = {
.is_compat = true,
.ptr.compat = __argv,
};
struct user_arg_ptr envp = {
.is_compat = true,
.ptr.compat = __envp,
};
return do_execveat_common(fd, filename, argv, envp, flags);
}
#endif
void set_binfmt(struct linux_binfmt *new)
{
struct mm_struct *mm = current->mm;
if (mm->binfmt)
module_put(mm->binfmt->module);
mm->binfmt = new;
if (new)
__module_get(new->module);
}
EXPORT_SYMBOL(set_binfmt);
/*
* set_dumpable stores three-value SUID_DUMP_* into mm->flags.
*/
void set_dumpable(struct mm_struct *mm, int value)
{
if (WARN_ON((unsigned)value > SUID_DUMP_ROOT))
return;
set_mask_bits(&mm->flags, MMF_DUMPABLE_MASK, value);
}
SYSCALL_DEFINE3(execve,
const char __user *, filename,
const char __user *const __user *, argv,
const char __user *const __user *, envp)
{
return do_execve(getname(filename), argv, envp);
}
SYSCALL_DEFINE5(execveat,
int, fd, const char __user *, filename,
const char __user *const __user *, argv,
const char __user *const __user *, envp,
int, flags)
{
return do_execveat(fd,
getname_uflags(filename, flags),
argv, envp, flags);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
const compat_uptr_t __user *, argv,
const compat_uptr_t __user *, envp)
{
return compat_do_execve(getname(filename), argv, envp);
}
COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
const char __user *, filename,
const compat_uptr_t __user *, argv,
const compat_uptr_t __user *, envp,
int, flags)
{
return compat_do_execveat(fd,
getname_uflags(filename, flags),
argv, envp, flags);
}
#endif
#ifdef CONFIG_SYSCTL
static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!error)
validate_coredump_safety();
return error;
}
static const struct ctl_table fs_exec_sysctls[] = {
{
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax_coredump,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
};
static int __init init_fs_exec_sysctls(void)
{
register_sysctl_init("fs", fs_exec_sysctls);
return 0;
}
fs_initcall(init_fs_exec_sysctls);
#endif /* CONFIG_SYSCTL */
#ifdef CONFIG_EXEC_KUNIT_TEST
#include "tests/exec_kunit.c"
#endif
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _LINUX_RCUREF_H
#define _LINUX_RCUREF_H
#include <linux/atomic.h>
#include <linux/bug.h>
#include <linux/limits.h>
#include <linux/lockdep.h>
#include <linux/preempt.h>
#include <linux/rcupdate.h>
#define RCUREF_ONEREF 0x00000000U
#define RCUREF_MAXREF 0x7FFFFFFFU
#define RCUREF_SATURATED 0xA0000000U
#define RCUREF_RELEASED 0xC0000000U
#define RCUREF_DEAD 0xE0000000U
#define RCUREF_NOREF 0xFFFFFFFFU
/**
* rcuref_init - Initialize a rcuref reference count with the given reference count
* @ref: Pointer to the reference count
* @cnt: The initial reference count typically '1'
*/
static inline void rcuref_init(rcuref_t *ref, unsigned int cnt)
{
atomic_set(&ref->refcnt, cnt - 1);
}
/**
* rcuref_read - Read the number of held reference counts of a rcuref
* @ref: Pointer to the reference count
*
* Return: The number of held references (0 ... N)
*/
static inline unsigned int rcuref_read(rcuref_t *ref)
{
unsigned int c = atomic_read(&ref->refcnt);
/* Return 0 if within the DEAD zone. */
return c >= RCUREF_RELEASED ? 0 : c + 1;
}
extern __must_check bool rcuref_get_slowpath(rcuref_t *ref);
/**
* rcuref_get - Acquire one reference on a rcuref reference count
* @ref: Pointer to the reference count
*
* Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* and thereby orders future stores. See documentation in lib/rcuref.c
*
* Return:
* False if the attempt to acquire a reference failed. This happens
* when the last reference has been put already
*
* True if a reference was successfully acquired
*/
static inline __must_check bool rcuref_get(rcuref_t *ref)
{
/*
* Unconditionally increase the reference count. The saturation and
* dead zones provide enough tolerance for this.
*/
if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt)))
return true;
/* Handle the cases inside the saturation and dead zones */
return rcuref_get_slowpath(ref);
}
extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt);
/*
* Internal helper. Do not invoke directly.
*/
static __always_inline __must_check bool __rcuref_put(rcuref_t *ref)
{
int cnt;
RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(),
"suspicious rcuref_put_rcusafe() usage");
/*
* Unconditionally decrease the reference count. The saturation and
* dead zones provide enough tolerance for this.
*/
cnt = atomic_sub_return_release(1, &ref->refcnt); if (likely(cnt >= 0))
return false;
/*
* Handle the last reference drop and cases inside the saturation
* and dead zones.
*/
return rcuref_put_slowpath(ref, cnt);
}
/**
* rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe
* @ref: Pointer to the reference count
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides an acquire ordering on success such that free()
* must come after.
*
* Can be invoked from contexts, which guarantee that no grace period can
* happen which would free the object concurrently if the decrement drops
* the last reference and the slowpath races against a concurrent get() and
* put() pair. rcu_read_lock()'ed and atomic contexts qualify.
*
* Return:
* True if this was the last reference with no future references
* possible. This signals the caller that it can safely release the
* object which is protected by the reference counter.
*
* False if there are still active references or the put() raced
* with a concurrent get()/put() pair. Caller is not allowed to
* release the protected object.
*/
static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref)
{
return __rcuref_put(ref);
}
/**
* rcuref_put -- Release one reference for a rcuref reference count
* @ref: Pointer to the reference count
*
* Can be invoked from any context.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides an acquire ordering on success such that free()
* must come after.
*
* Return:
*
* True if this was the last reference with no future references
* possible. This signals the caller that it can safely schedule the
* object, which is protected by the reference counter, for
* deconstruction.
*
* False if there are still active references or the put() raced
* with a concurrent get()/put() pair. Caller is not allowed to
* deconstruct the protected object.
*/
static inline __must_check bool rcuref_put(rcuref_t *ref)
{
bool released;
preempt_disable();
released = __rcuref_put(ref); preempt_enable();
return released;
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
File: fs/xattr.c
Extended attribute handling.
Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com>
Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*/
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl_xattr.h>
#include <linux/uaccess.h>
#include "internal.h"
static const char *
strcmp_prefix(const char *a, const char *a_prefix)
{
while (*a_prefix && *a == *a_prefix) {
a++;
a_prefix++;
}
return *a_prefix ? NULL : a;
}
/*
* In order to implement different sets of xattr operations for each xattr
* prefix, a filesystem should create a null-terminated array of struct
* xattr_handler (one for each prefix) and hang a pointer to it off of the
* s_xattr field of the superblock.
*/
#define for_each_xattr_handler(handlers, handler) \
if (handlers) \
for ((handler) = *(handlers)++; \
(handler) != NULL; \
(handler) = *(handlers)++)
/*
* Find the xattr_handler with the matching prefix.
*/
static const struct xattr_handler *
xattr_resolve_name(struct inode *inode, const char **name)
{
const struct xattr_handler * const *handlers = inode->i_sb->s_xattr;
const struct xattr_handler *handler;
if (!(inode->i_opflags & IOP_XATTR)) {
if (unlikely(is_bad_inode(inode)))
return ERR_PTR(-EIO);
return ERR_PTR(-EOPNOTSUPP);
}
for_each_xattr_handler(handlers, handler) {
const char *n;
n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) {
if (!handler->prefix ^ !*n) {
if (*n)
continue;
return ERR_PTR(-EINVAL);
}
*name = n;
return handler;
}
}
return ERR_PTR(-EOPNOTSUPP);
}
/**
* may_write_xattr - check whether inode allows writing xattr
* @idmap: idmap of the mount the inode was found from
* @inode: the inode on which to set an xattr
*
* Check whether the inode allows writing xattrs. Specifically, we can never
* set or remove an extended attribute on a read-only filesystem or on an
* immutable / append-only inode.
*
* We also need to ensure that the inode has a mapping in the mount to
* not risk writing back invalid i_{g,u}id values.
*
* Return: On success zero is returned. On error a negative errno is returned.
*/
int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode)
{
if (IS_IMMUTABLE(inode))
return -EPERM;
if (IS_APPEND(inode))
return -EPERM;
if (HAS_UNMAPPED_ID(idmap, inode))
return -EPERM;
return 0;
}
/*
* Check permissions for extended attribute access. This is a bit complicated
* because different namespaces have very different rules.
*/
static int
xattr_permission(struct mnt_idmap *idmap, struct inode *inode,
const char *name, int mask)
{
if (mask & MAY_WRITE) {
int ret;
ret = may_write_xattr(idmap, inode);
if (ret)
return ret;
}
/*
* No restriction for security.* and system.* from the VFS. Decision
* on these is left to the underlying filesystem / security module.
*/
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return 0;
/*
* The trusted.* namespace can only be accessed by privileged users.
*/
if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
if (!capable(CAP_SYS_ADMIN))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
return 0;
}
/*
* In the user.* namespace, only regular files and directories can have
* extended attributes. For sticky directories, only the owner and
* privileged users can write attributes.
*/
if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
(mask & MAY_WRITE) &&
!inode_owner_or_capable(idmap, inode))
return -EPERM;
}
return inode_permission(idmap, inode, mask);
}
/*
* Look for any handler that deals with the specified namespace.
*/
int
xattr_supports_user_prefix(struct inode *inode)
{
const struct xattr_handler * const *handlers = inode->i_sb->s_xattr;
const struct xattr_handler *handler;
if (!(inode->i_opflags & IOP_XATTR)) {
if (unlikely(is_bad_inode(inode)))
return -EIO;
return -EOPNOTSUPP;
}
for_each_xattr_handler(handlers, handler) {
if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX,
XATTR_USER_PREFIX_LEN))
return 0;
}
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(xattr_supports_user_prefix);
int
__vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct inode *inode, const char *name, const void *value,
size_t size, int flags)
{
const struct xattr_handler *handler;
if (is_posix_acl_xattr(name))
return -EOPNOTSUPP;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->set)
return -EOPNOTSUPP;
if (size == 0)
value = ""; /* empty EA, do not remove */
return handler->set(handler, idmap, dentry, inode, name, value,
size, flags);
}
EXPORT_SYMBOL(__vfs_setxattr);
/**
* __vfs_setxattr_noperm - perform setxattr operation without performing
* permission checks.
*
* @idmap: idmap of the mount the inode was found from
* @dentry: object to perform setxattr on
* @name: xattr name to set
* @value: value to set @name to
* @size: size of @value
* @flags: flags to pass into filesystem operations
*
* returns the result of the internal setxattr or setsecurity operations.
*
* This function requires the caller to lock the inode's i_mutex before it
* is executed. It also assumes that the caller will make the appropriate
* permission checks.
*/
int __vfs_setxattr_noperm(struct mnt_idmap *idmap,
struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
int error = -EAGAIN;
int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
if (issec)
inode->i_flags &= ~S_NOSEC;
if (inode->i_opflags & IOP_XATTR) {
error = __vfs_setxattr(idmap, dentry, inode, name, value,
size, flags);
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_setxattr(dentry, name, value,
size, flags);
}
} else {
if (unlikely(is_bad_inode(inode)))
return -EIO;
}
if (error == -EAGAIN) {
error = -EOPNOTSUPP;
if (issec) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
error = security_inode_setsecurity(inode, suffix, value,
size, flags);
if (!error)
fsnotify_xattr(dentry);
}
}
return error;
}
/**
* __vfs_setxattr_locked - set an extended attribute while holding the inode
* lock
*
* @idmap: idmap of the mount of the target inode
* @dentry: object to perform setxattr on
* @name: xattr name to set
* @value: value to set @name to
* @size: size of @value
* @flags: flags to pass into filesystem operations
* @delegated_inode: on return, will contain an inode pointer that
* a delegation was broken on, NULL if none.
*/
int
__vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name, const void *value, size_t size,
int flags, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(idmap, inode, name, MAY_WRITE);
if (error)
return error;
error = security_inode_setxattr(idmap, dentry, name, value, size,
flags);
if (error)
goto out;
error = try_break_deleg(inode, delegated_inode);
if (error)
goto out;
error = __vfs_setxattr_noperm(idmap, dentry, name, value,
size, flags);
out:
return error;
}
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
int
vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name, const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
const void *orig_value = value;
int error;
if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
error = cap_convert_nscap(idmap, dentry, &value, size);
if (error < 0)
return error;
size = error;
}
retry_deleg:
inode_lock(inode);
error = __vfs_setxattr_locked(idmap, dentry, name, value, size,
flags, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
if (value != orig_value)
kfree(value);
return error;
}
EXPORT_SYMBOL_GPL(vfs_setxattr);
static ssize_t
xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode,
const char *name, void *value, size_t size)
{
void *buffer = NULL;
ssize_t len;
if (!value || !size) {
len = security_inode_getsecurity(idmap, inode, name,
&buffer, false);
goto out_noalloc;
}
len = security_inode_getsecurity(idmap, inode, name, &buffer,
true);
if (len < 0)
return len;
if (size < len) {
len = -ERANGE;
goto out;
}
memcpy(value, buffer, len);
out:
kfree(buffer);
out_noalloc:
return len;
}
/*
* vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
*
* Allocate memory, if not already allocated, or re-allocate correct size,
* before retrieving the extended attribute. The xattr value buffer should
* always be freed by the caller, even on error.
*
* Returns the result of alloc, if failed, or the getxattr operation.
*/
int
vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name, char **xattr_value, size_t xattr_size,
gfp_t flags)
{
const struct xattr_handler *handler;
struct inode *inode = dentry->d_inode;
char *value = *xattr_value;
int error;
error = xattr_permission(idmap, inode, name, MAY_READ);
if (error)
return error;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->get)
return -EOPNOTSUPP;
error = handler->get(handler, dentry, inode, name, NULL, 0);
if (error < 0)
return error;
if (!value || (error > xattr_size)) {
value = krealloc(*xattr_value, error + 1, flags);
if (!value)
return -ENOMEM;
memset(value, 0, error + 1);
}
error = handler->get(handler, dentry, inode, name, value, error);
*xattr_value = value;
return error;
}
ssize_t
__vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
void *value, size_t size)
{
const struct xattr_handler *handler;
if (is_posix_acl_xattr(name))
return -EOPNOTSUPP;
handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->get)
return -EOPNOTSUPP;
return handler->get(handler, dentry, inode, name, value, size);
}
EXPORT_SYMBOL(__vfs_getxattr);
ssize_t
vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name, void *value, size_t size)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(idmap, inode, name, MAY_READ);
if (error)
return error;
error = security_inode_getxattr(dentry, name);
if (error)
return error;
if (!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
int ret = xattr_getsecurity(idmap, inode, suffix, value,
size);
/*
* Only overwrite the return value if a security module
* is actually active.
*/
if (ret == -EOPNOTSUPP)
goto nolsm;
return ret;
}
nolsm:
return __vfs_getxattr(dentry, inode, name, value, size);
}
EXPORT_SYMBOL_GPL(vfs_getxattr);
/**
* vfs_listxattr - retrieve \0 separated list of xattr names
* @dentry: the dentry from whose inode the xattr names are retrieved
* @list: buffer to store xattr names into
* @size: size of the buffer
*
* This function returns the names of all xattrs associated with the
* inode of @dentry.
*
* Note, for legacy reasons the vfs_listxattr() function lists POSIX
* ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the
* vfs_listxattr() function doesn't check for this flag since a
* filesystem could implement POSIX ACLs without implementing any other
* xattrs.
*
* However, since all codepaths that remove IOP_XATTR also assign of
* inode operations that either don't implement or implement a stub
* ->listxattr() operation.
*
* Return: On success, the size of the buffer that was used. On error a
* negative error code.
*/
ssize_t
vfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct inode *inode = d_inode(dentry);
ssize_t error;
error = security_inode_listxattr(dentry);
if (error)
return error;
if (inode->i_op->listxattr) {
error = inode->i_op->listxattr(dentry, list, size);
} else {
error = security_inode_listsecurity(inode, list, size);
if (size && error > size)
error = -ERANGE;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_listxattr);
int
__vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name)
{
struct inode *inode = d_inode(dentry);
const struct xattr_handler *handler;
if (is_posix_acl_xattr(name))
return -EOPNOTSUPP;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->set)
return -EOPNOTSUPP;
return handler->set(handler, idmap, dentry, inode, name, NULL, 0,
XATTR_REPLACE);
}
EXPORT_SYMBOL(__vfs_removexattr);
/**
* __vfs_removexattr_locked - set an extended attribute while holding the inode
* lock
*
* @idmap: idmap of the mount of the target inode
* @dentry: object to perform setxattr on
* @name: name of xattr to remove
* @delegated_inode: on return, will contain an inode pointer that
* a delegation was broken on, NULL if none.
*/
int
__vfs_removexattr_locked(struct mnt_idmap *idmap,
struct dentry *dentry, const char *name,
struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(idmap, inode, name, MAY_WRITE);
if (error)
return error;
error = security_inode_removexattr(idmap, dentry, name);
if (error)
goto out;
error = try_break_deleg(inode, delegated_inode);
if (error)
goto out;
error = __vfs_removexattr(idmap, dentry, name);
if (error)
return error;
fsnotify_xattr(dentry);
security_inode_post_removexattr(dentry, name);
out:
return error;
}
EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
int
vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
const char *name)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
retry_deleg:
inode_lock(inode);
error = __vfs_removexattr_locked(idmap, dentry,
name, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_removexattr);
int import_xattr_name(struct xattr_name *kname, const char __user *name)
{
int error = strncpy_from_user(kname->name, name,
sizeof(kname->name));
if (error == 0 || error == sizeof(kname->name))
return -ERANGE;
if (error < 0)
return error;
return 0;
}
/*
* Extended attribute SET operations
*/
int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx)
{
int error;
if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
return -EINVAL;
error = import_xattr_name(ctx->kname, name);
if (error)
return error;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
return -E2BIG;
ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size);
if (IS_ERR(ctx->kvalue)) {
error = PTR_ERR(ctx->kvalue);
ctx->kvalue = NULL;
}
}
return error;
}
static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct kernel_xattr_ctx *ctx)
{
if (is_posix_acl_xattr(ctx->kname->name))
return do_set_acl(idmap, dentry, ctx->kname->name,
ctx->kvalue, ctx->size);
return vfs_setxattr(idmap, dentry, ctx->kname->name,
ctx->kvalue, ctx->size, ctx->flags);
}
int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx)
{
int error = mnt_want_write_file(f);
if (!error) {
audit_file(f);
error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
mnt_drop_write_file(f);
}
return error;
}
/* unconditionally consumes filename */
int filename_setxattr(int dfd, struct filename *filename,
unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
{
struct path path;
int error;
retry:
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (!error) {
error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
putname(filename);
return error;
}
static int path_setxattrat(int dfd, const char __user *pathname,
unsigned int at_flags, const char __user *name,
const void __user *value, size_t size, int flags)
{
struct xattr_name kname;
struct kernel_xattr_ctx ctx = {
.cvalue = value,
.kvalue = NULL,
.size = size,
.kname = &kname,
.flags = flags,
};
struct filename *filename;
unsigned int lookup_flags = 0;
int error;
if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
if (!(at_flags & AT_SYMLINK_NOFOLLOW))
lookup_flags = LOOKUP_FOLLOW;
error = setxattr_copy(name, &ctx);
if (error)
return error;
filename = getname_maybe_null(pathname, at_flags);
if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
error = -EBADF;
else
error = file_setxattr(fd_file(f), &ctx);
} else {
error = filename_setxattr(dfd, filename, lookup_flags, &ctx);
}
kvfree(ctx.kvalue);
return error;
}
SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
const char __user *, name, const struct xattr_args __user *, uargs,
size_t, usize)
{
struct xattr_args args = {};
int error;
BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);
if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
return -EINVAL;
if (usize > PAGE_SIZE)
return -E2BIG;
error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
if (error)
return error;
return path_setxattrat(dfd, pathname, at_flags, name,
u64_to_user_ptr(args.value), args.size,
args.flags);
}
SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags);
}
SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
value, size, flags);
}
SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
const void __user *,value, size_t, size, int, flags)
{
return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name,
value, size, flags);
}
/*
* Extended attribute GET operations
*/
static ssize_t
do_getxattr(struct mnt_idmap *idmap, struct dentry *d,
struct kernel_xattr_ctx *ctx)
{
ssize_t error;
char *kname = ctx->kname->name;
void *kvalue = NULL;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
ctx->size = XATTR_SIZE_MAX;
kvalue = kvzalloc(ctx->size, GFP_KERNEL);
if (!kvalue)
return -ENOMEM;
}
if (is_posix_acl_xattr(kname))
error = do_get_acl(idmap, d, kname, kvalue, ctx->size);
else
error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size);
if (error > 0) {
if (ctx->size && copy_to_user(ctx->value, kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
/* The file system tried to returned a value bigger
than XATTR_SIZE_MAX bytes. Not possible. */
error = -E2BIG;
}
kvfree(kvalue);
return error;
}
ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx)
{
audit_file(f);
return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
}
/* unconditionally consumes filename */
ssize_t filename_getxattr(int dfd, struct filename *filename,
unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
{
struct path path;
ssize_t error;
retry:
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
goto out;
error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
putname(filename);
return error;
}
static ssize_t path_getxattrat(int dfd, const char __user *pathname,
unsigned int at_flags, const char __user *name,
void __user *value, size_t size)
{
struct xattr_name kname;
struct kernel_xattr_ctx ctx = {
.value = value,
.size = size,
.kname = &kname,
.flags = 0,
};
struct filename *filename;
ssize_t error;
if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
error = import_xattr_name(&kname, name);
if (error)
return error;
filename = getname_maybe_null(pathname, at_flags);
if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
return -EBADF;
return file_getxattr(fd_file(f), &ctx);
} else {
int lookup_flags = 0;
if (!(at_flags & AT_SYMLINK_NOFOLLOW))
lookup_flags = LOOKUP_FOLLOW;
return filename_getxattr(dfd, filename, lookup_flags, &ctx);
}
}
SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
const char __user *, name, struct xattr_args __user *, uargs, size_t, usize)
{
struct xattr_args args = {};
int error;
BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);
if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
return -EINVAL;
if (usize > PAGE_SIZE)
return -E2BIG;
error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
if (error)
return error;
if (args.flags != 0)
return -EINVAL;
return path_getxattrat(dfd, pathname, at_flags, name,
u64_to_user_ptr(args.value), args.size);
}
SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size);
}
SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
value, size);
}
SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
void __user *, value, size_t, size)
{
return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size);
}
/*
* Extended attribute LIST operations
*/
static ssize_t
listxattr(struct dentry *d, char __user *list, size_t size)
{
ssize_t error;
char *klist = NULL;
if (size) {
if (size > XATTR_LIST_MAX)
size = XATTR_LIST_MAX;
klist = kvmalloc(size, GFP_KERNEL);
if (!klist)
return -ENOMEM;
}
error = vfs_listxattr(d, klist, size);
if (error > 0) {
if (size && copy_to_user(list, klist, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
/* The file system tried to returned a list bigger
than XATTR_LIST_MAX bytes. Not possible. */
error = -E2BIG;
}
kvfree(klist);
return error;
}
static
ssize_t file_listxattr(struct file *f, char __user *list, size_t size)
{
audit_file(f);
return listxattr(f->f_path.dentry, list, size);
}
/* unconditionally consumes filename */
static
ssize_t filename_listxattr(int dfd, struct filename *filename,
unsigned int lookup_flags,
char __user *list, size_t size)
{
struct path path;
ssize_t error;
retry:
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
goto out;
error = listxattr(path.dentry, list, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
putname(filename);
return error;
}
static ssize_t path_listxattrat(int dfd, const char __user *pathname,
unsigned int at_flags, char __user *list,
size_t size)
{
struct filename *filename;
int lookup_flags;
if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
filename = getname_maybe_null(pathname, at_flags);
if (!filename) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
return -EBADF;
return file_listxattr(fd_file(f), list, size);
}
lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
return filename_listxattr(dfd, filename, lookup_flags, list, size);
}
SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname,
unsigned int, at_flags,
char __user *, list, size_t, size)
{
return path_listxattrat(dfd, pathname, at_flags, list, size);
}
SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattrat(AT_FDCWD, pathname, 0, list, size);
}
SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size);
}
SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size);
}
/*
* Extended attribute REMOVE operations
*/
static long
removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
{
if (is_posix_acl_xattr(name))
return vfs_remove_acl(idmap, d, name);
return vfs_removexattr(idmap, d, name);
}
static int file_removexattr(struct file *f, struct xattr_name *kname)
{
int error = mnt_want_write_file(f);
if (!error) {
audit_file(f);
error = removexattr(file_mnt_idmap(f),
f->f_path.dentry, kname->name);
mnt_drop_write_file(f);
}
return error;
}
/* unconditionally consumes filename */
static int filename_removexattr(int dfd, struct filename *filename,
unsigned int lookup_flags, struct xattr_name *kname)
{
struct path path;
int error;
retry:
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (!error) {
error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
putname(filename);
return error;
}
static int path_removexattrat(int dfd, const char __user *pathname,
unsigned int at_flags, const char __user *name)
{
struct xattr_name kname;
struct filename *filename;
unsigned int lookup_flags;
int error;
if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
error = import_xattr_name(&kname, name);
if (error)
return error;
filename = getname_maybe_null(pathname, at_flags);
if (!filename) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
return -EBADF;
return file_removexattr(fd_file(f), &kname);
}
lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
return filename_removexattr(dfd, filename, lookup_flags, &kname);
}
SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname,
unsigned int, at_flags, const char __user *, name)
{
return path_removexattrat(dfd, pathname, at_flags, name);
}
SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattrat(AT_FDCWD, pathname, 0, name);
}
SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name);
}
SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name);
}
int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name)
{
size_t len;
len = strlen(name) + 1;
if (*buffer) {
if (*remaining_size < len)
return -ERANGE;
memcpy(*buffer, name, len);
*buffer += len;
}
*remaining_size -= len;
return 0;
}
/**
* generic_listxattr - run through a dentry's xattr list() operations
* @dentry: dentry to list the xattrs
* @buffer: result buffer
* @buffer_size: size of @buffer
*
* Combine the results of the list() operation from every xattr_handler in the
* xattr_handler stack.
*
* Note that this will not include the entries for POSIX ACLs.
*/
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr;
ssize_t remaining_size = buffer_size;
for_each_xattr_handler(handlers, handler) {
int err;
if (!handler->name || (handler->list && !handler->list(dentry)))
continue;
err = xattr_list_one(&buffer, &remaining_size, handler->name);
if (err)
return err;
}
return buffer_size - remaining_size;
}
EXPORT_SYMBOL(generic_listxattr);
/**
* xattr_full_name - Compute full attribute name from suffix
*
* @handler: handler of the xattr_handler operation
* @name: name passed to the xattr_handler operation
*
* The get and set xattr handler operations are called with the remainder of
* the attribute name after skipping the handler's prefix: for example, "foo"
* is passed to the get operation of a handler with prefix "user." to get
* attribute "user.foo". The full name is still "there" in the name though.
*
* Note: the list xattr handler operation when called from the vfs is passed a
* NULL name; some file systems use this operation internally, with varying
* semantics.
*/
const char *xattr_full_name(const struct xattr_handler *handler,
const char *name)
{ size_t prefix_len = strlen(xattr_prefix(handler));
return name - prefix_len;
}
EXPORT_SYMBOL(xattr_full_name);
/**
* simple_xattr_space - estimate the memory used by a simple xattr
* @name: the full name of the xattr
* @size: the size of its value
*
* This takes no account of how much larger the two slab objects actually are:
* that would depend on the slab implementation, when what is required is a
* deterministic number, which grows with name length and size and quantity.
*
* Return: The approximate number of bytes of memory used by such an xattr.
*/
size_t simple_xattr_space(const char *name, size_t size)
{
/*
* Use "40" instead of sizeof(struct simple_xattr), to return the
* same result on 32-bit and 64-bit, and even if simple_xattr grows.
*/
return 40 + size + strlen(name);
}
/**
* simple_xattr_free - free an xattr object
* @xattr: the xattr object
*
* Free the xattr object. Can handle @xattr being NULL.
*/
void simple_xattr_free(struct simple_xattr *xattr)
{
if (xattr)
kfree(xattr->name);
kvfree(xattr);
}
/**
* simple_xattr_alloc - allocate new xattr object
* @value: value of the xattr object
* @size: size of @value
*
* Allocate a new xattr object and initialize respective members. The caller is
* responsible for handling the name of the xattr.
*
* Return: On success a new xattr object is returned. On failure NULL is
* returned.
*/
struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
{
struct simple_xattr *new_xattr;
size_t len;
/* wrap around? */
len = sizeof(*new_xattr) + size;
if (len < sizeof(*new_xattr))
return NULL;
new_xattr = kvmalloc(len, GFP_KERNEL_ACCOUNT);
if (!new_xattr)
return NULL;
new_xattr->size = size;
memcpy(new_xattr->value, value, size);
return new_xattr;
}
/**
* rbtree_simple_xattr_cmp - compare xattr name with current rbtree xattr entry
* @key: xattr name
* @node: current node
*
* Compare the xattr name with the xattr name attached to @node in the rbtree.
*
* Return: Negative value if continuing left, positive if continuing right, 0
* if the xattr attached to @node matches @key.
*/
static int rbtree_simple_xattr_cmp(const void *key, const struct rb_node *node)
{
const char *xattr_name = key;
const struct simple_xattr *xattr;
xattr = rb_entry(node, struct simple_xattr, rb_node);
return strcmp(xattr->name, xattr_name);
}
/**
* rbtree_simple_xattr_node_cmp - compare two xattr rbtree nodes
* @new_node: new node
* @node: current node
*
* Compare the xattr attached to @new_node with the xattr attached to @node.
*
* Return: Negative value if continuing left, positive if continuing right, 0
* if the xattr attached to @new_node matches the xattr attached to @node.
*/
static int rbtree_simple_xattr_node_cmp(struct rb_node *new_node,
const struct rb_node *node)
{
struct simple_xattr *xattr;
xattr = rb_entry(new_node, struct simple_xattr, rb_node);
return rbtree_simple_xattr_cmp(xattr->name, node);
}
/**
* simple_xattr_get - get an xattr object
* @xattrs: the header of the xattr object
* @name: the name of the xattr to retrieve
* @buffer: the buffer to store the value into
* @size: the size of @buffer
*
* Try to find and retrieve the xattr object associated with @name.
* If @buffer is provided store the value of @xattr in @buffer
* otherwise just return the length. The size of @buffer is limited
* to XATTR_SIZE_MAX which currently is 65536.
*
* Return: On success the length of the xattr value is returned. On error a
* negative error code is returned.
*/
int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
void *buffer, size_t size)
{
struct simple_xattr *xattr = NULL;
struct rb_node *rbp;
int ret = -ENODATA;
read_lock(&xattrs->lock);
rbp = rb_find(name, &xattrs->rb_root, rbtree_simple_xattr_cmp);
if (rbp) {
xattr = rb_entry(rbp, struct simple_xattr, rb_node);
ret = xattr->size;
if (buffer) { if (size < xattr->size)
ret = -ERANGE;
else
memcpy(buffer, xattr->value, xattr->size);
}
}
read_unlock(&xattrs->lock);
return ret;
}
/**
* simple_xattr_set - set an xattr object
* @xattrs: the header of the xattr object
* @name: the name of the xattr to retrieve
* @value: the value to store along the xattr
* @size: the size of @value
* @flags: the flags determining how to set the xattr
*
* Set a new xattr object.
* If @value is passed a new xattr object will be allocated. If XATTR_REPLACE
* is specified in @flags a matching xattr object for @name must already exist.
* If it does it will be replaced with the new xattr object. If it doesn't we
* fail. If XATTR_CREATE is specified and a matching xattr does already exist
* we fail. If it doesn't we create a new xattr. If @flags is zero we simply
* insert the new xattr replacing any existing one.
*
* If @value is empty and a matching xattr object is found we delete it if
* XATTR_REPLACE is specified in @flags or @flags is zero.
*
* If @value is empty and no matching xattr object for @name is found we do
* nothing if XATTR_CREATE is specified in @flags or @flags is zero. For
* XATTR_REPLACE we fail as mentioned above.
*
* Return: On success, the removed or replaced xattr is returned, to be freed
* by the caller; or NULL if none. On failure a negative error code is returned.
*/
struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs,
const char *name, const void *value,
size_t size, int flags)
{
struct simple_xattr *old_xattr = NULL, *new_xattr = NULL;
struct rb_node *parent = NULL, **rbp;
int err = 0, ret;
/* value == NULL means remove */
if (value) {
new_xattr = simple_xattr_alloc(value, size);
if (!new_xattr)
return ERR_PTR(-ENOMEM);
new_xattr->name = kstrdup(name, GFP_KERNEL_ACCOUNT);
if (!new_xattr->name) {
simple_xattr_free(new_xattr);
return ERR_PTR(-ENOMEM);
}
}
write_lock(&xattrs->lock);
rbp = &xattrs->rb_root.rb_node;
while (*rbp) {
parent = *rbp;
ret = rbtree_simple_xattr_cmp(name, *rbp);
if (ret < 0)
rbp = &(*rbp)->rb_left;
else if (ret > 0)
rbp = &(*rbp)->rb_right;
else
old_xattr = rb_entry(*rbp, struct simple_xattr, rb_node);
if (old_xattr)
break;
}
if (old_xattr) {
/* Fail if XATTR_CREATE is requested and the xattr exists. */
if (flags & XATTR_CREATE) {
err = -EEXIST;
goto out_unlock;
}
if (new_xattr)
rb_replace_node(&old_xattr->rb_node,
&new_xattr->rb_node, &xattrs->rb_root);
else
rb_erase(&old_xattr->rb_node, &xattrs->rb_root);
} else {
/* Fail if XATTR_REPLACE is requested but no xattr is found. */
if (flags & XATTR_REPLACE) {
err = -ENODATA;
goto out_unlock;
}
/*
* If XATTR_CREATE or no flags are specified together with a
* new value simply insert it.
*/
if (new_xattr) {
rb_link_node(&new_xattr->rb_node, parent, rbp);
rb_insert_color(&new_xattr->rb_node, &xattrs->rb_root);
}
/*
* If XATTR_CREATE or no flags are specified and neither an
* old or new xattr exist then we don't need to do anything.
*/
}
out_unlock:
write_unlock(&xattrs->lock);
if (!err)
return old_xattr;
simple_xattr_free(new_xattr);
return ERR_PTR(err);
}
static bool xattr_is_trusted(const char *name)
{
return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
/**
* simple_xattr_list - list all xattr objects
* @inode: inode from which to get the xattrs
* @xattrs: the header of the xattr object
* @buffer: the buffer to store all xattrs into
* @size: the size of @buffer
*
* List all xattrs associated with @inode. If @buffer is NULL we returned
* the required size of the buffer. If @buffer is provided we store the
* xattrs value into it provided it is big enough.
*
* Note, the number of xattr names that can be listed with listxattr(2) is
* limited to XATTR_LIST_MAX aka 65536 bytes. If a larger buffer is passed
* then vfs_listxattr() caps it to XATTR_LIST_MAX and if more xattr names
* are found it will return -E2BIG.
*
* Return: On success the required size or the size of the copied xattrs is
* returned. On error a negative error code is returned.
*/
ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
char *buffer, size_t size)
{
bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN);
struct simple_xattr *xattr;
struct rb_node *rbp;
ssize_t remaining_size = size;
int err = 0;
err = posix_acl_listxattr(inode, &buffer, &remaining_size);
if (err)
return err;
read_lock(&xattrs->lock);
for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
xattr = rb_entry(rbp, struct simple_xattr, rb_node);
/* skip "trusted." attributes for unprivileged callers */
if (!trusted && xattr_is_trusted(xattr->name))
continue;
err = xattr_list_one(&buffer, &remaining_size, xattr->name);
if (err)
break;
}
read_unlock(&xattrs->lock);
return err ? err : size - remaining_size;
}
/**
* rbtree_simple_xattr_less - compare two xattr rbtree nodes
* @new_node: new node
* @node: current node
*
* Compare the xattr attached to @new_node with the xattr attached to @node.
* Note that this function technically tolerates duplicate entries.
*
* Return: True if insertion point in the rbtree is found.
*/
static bool rbtree_simple_xattr_less(struct rb_node *new_node,
const struct rb_node *node)
{
return rbtree_simple_xattr_node_cmp(new_node, node) < 0;
}
/**
* simple_xattr_add - add xattr objects
* @xattrs: the header of the xattr object
* @new_xattr: the xattr object to add
*
* Add an xattr object to @xattrs. This assumes no replacement or removal
* of matching xattrs is wanted. Should only be called during inode
* initialization when a few distinct initial xattrs are supposed to be set.
*/
void simple_xattr_add(struct simple_xattrs *xattrs,
struct simple_xattr *new_xattr)
{
write_lock(&xattrs->lock);
rb_add(&new_xattr->rb_node, &xattrs->rb_root, rbtree_simple_xattr_less);
write_unlock(&xattrs->lock);
}
/**
* simple_xattrs_init - initialize new xattr header
* @xattrs: header to initialize
*
* Initialize relevant fields of a an xattr header.
*/
void simple_xattrs_init(struct simple_xattrs *xattrs)
{
xattrs->rb_root = RB_ROOT;
rwlock_init(&xattrs->lock);
}
/**
* simple_xattrs_free - free xattrs
* @xattrs: xattr header whose xattrs to destroy
* @freed_space: approximate number of bytes of memory freed from @xattrs
*
* Destroy all xattrs in @xattr. When this is called no one can hold a
* reference to any of the xattrs anymore.
*/
void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space)
{
struct rb_node *rbp;
if (freed_space) *freed_space = 0;
rbp = rb_first(&xattrs->rb_root);
while (rbp) {
struct simple_xattr *xattr;
struct rb_node *rbp_next;
rbp_next = rb_next(rbp);
xattr = rb_entry(rbp, struct simple_xattr, rb_node);
rb_erase(&xattr->rb_node, &xattrs->rb_root);
if (freed_space)
*freed_space += simple_xattr_space(xattr->name,
xattr->size);
simple_xattr_free(xattr);
rbp = rbp_next;
}
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
*
* (C) SGI 2006, Christoph Lameter
* Cleaned up and restructured to ease the addition of alternative
* implementations of SLAB allocators.
* (C) Linux Foundation 2008-2013
* Unified interface for all slab allocators
*/
#ifndef _LINUX_SLAB_H
#define _LINUX_SLAB_H
#include <linux/cache.h>
#include <linux/gfp.h>
#include <linux/overflow.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/percpu-refcount.h>
#include <linux/cleanup.h>
#include <linux/hash.h>
enum _slab_flag_bits {
_SLAB_CONSISTENCY_CHECKS,
_SLAB_RED_ZONE,
_SLAB_POISON,
_SLAB_KMALLOC,
_SLAB_HWCACHE_ALIGN,
_SLAB_CACHE_DMA,
_SLAB_CACHE_DMA32,
_SLAB_STORE_USER,
_SLAB_PANIC,
_SLAB_TYPESAFE_BY_RCU,
_SLAB_TRACE,
#ifdef CONFIG_DEBUG_OBJECTS
_SLAB_DEBUG_OBJECTS,
#endif
_SLAB_NOLEAKTRACE,
_SLAB_NO_MERGE,
#ifdef CONFIG_FAILSLAB
_SLAB_FAILSLAB,
#endif
#ifdef CONFIG_MEMCG
_SLAB_ACCOUNT,
#endif
#ifdef CONFIG_KASAN_GENERIC
_SLAB_KASAN,
#endif
_SLAB_NO_USER_FLAGS,
#ifdef CONFIG_KFENCE
_SLAB_SKIP_KFENCE,
#endif
#ifndef CONFIG_SLUB_TINY
_SLAB_RECLAIM_ACCOUNT,
#endif
_SLAB_OBJECT_POISON,
_SLAB_CMPXCHG_DOUBLE,
#ifdef CONFIG_SLAB_OBJ_EXT
_SLAB_NO_OBJ_EXT,
#endif
_SLAB_FLAGS_LAST_BIT
};
#define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr)))
#define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U))
/*
* Flags to pass to kmem_cache_create().
* The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op
*/
/* DEBUG: Perform (expensive) checks on alloc/free */
#define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS)
/* DEBUG: Red zone objs in a cache */
#define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE)
/* DEBUG: Poison objects */
#define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON)
/* Indicate a kmalloc slab */
#define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC)
/**
* define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries.
*
* Sufficiently large objects are aligned on cache line boundary. For object
* size smaller than a half of cache line size, the alignment is on the half of
* cache line size. In general, if object size is smaller than 1/2^n of cache
* line size, the alignment is adjusted to 1/2^n.
*
* If explicit alignment is also requested by the respective
* &struct kmem_cache_args field, the greater of both is alignments is applied.
*/
#define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN)
/* Use GFP_DMA memory */
#define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA)
/* Use GFP_DMA32 memory */
#define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32)
/* DEBUG: Store the last owner for bug hunting */
#define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER)
/* Panic if kmem_cache_create() fails */
#define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC)
/**
* define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
*
* This delays freeing the SLAB page by a grace period, it does _NOT_
* delay object freeing. This means that if you do kmem_cache_free()
* that memory location is free to be reused at any time. Thus it may
* be possible to see another object there in the same RCU grace period.
*
* This feature only ensures the memory location backing the object
* stays valid, the trick to using this is relying on an independent
* object validation pass. Something like:
*
* ::
*
* begin:
* rcu_read_lock();
* obj = lockless_lookup(key);
* if (obj) {
* if (!try_get_ref(obj)) // might fail for free objects
* rcu_read_unlock();
* goto begin;
*
* if (obj->key != key) { // not the object we expected
* put_ref(obj);
* rcu_read_unlock();
* goto begin;
* }
* }
* rcu_read_unlock();
*
* This is useful if we need to approach a kernel structure obliquely,
* from its address obtained without the usual locking. We can lock
* the structure to stabilize it and check it's still at the given address,
* only if we can be sure that the memory has not been meanwhile reused
* for some other kind of object (which our subsystem's lock might corrupt).
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
*
* Note that object identity check has to be done *after* acquiring a
* reference, therefore user has to ensure proper ordering for loads.
* Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU,
* the newly allocated object has to be fully initialized *before* its
* refcount gets initialized and proper ordering for stores is required.
* refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are
* designed with the proper fences required for reference counting objects
* allocated with SLAB_TYPESAFE_BY_RCU.
*
* Note that it is not possible to acquire a lock within a structure
* allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference
* as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages
* are not zeroed before being given to the slab, which means that any
* locks must be initialized after each and every kmem_struct_alloc().
* Alternatively, make the ctor passed to kmem_cache_create() initialize
* the locks at page-allocation time, as is done in __i915_request_ctor(),
* sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers
* to safely acquire those ctor-initialized locks under rcu_read_lock()
* protection.
*
* Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
*/
#define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU)
/* Trace allocations and frees */
#define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE)
/* Flag to prevent checks on free */
#ifdef CONFIG_DEBUG_OBJECTS
# define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS)
#else
# define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED
#endif
/* Avoid kmemleak tracing */
#define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE)
/*
* Prevent merging with compatible kmem caches. This flag should be used
* cautiously. Valid use cases:
*
* - caches created for self-tests (e.g. kunit)
* - general caches created and used by a subsystem, only when a
* (subsystem-specific) debug option is enabled
* - performance critical caches, should be very rare and consulted with slab
* maintainers, and not used together with CONFIG_SLUB_TINY
*/
#define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE)
/* Fault injection mark */
#ifdef CONFIG_FAILSLAB
# define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB)
#else
# define SLAB_FAILSLAB __SLAB_FLAG_UNUSED
#endif
/**
* define SLAB_ACCOUNT - Account allocations to memcg.
*
* All object allocations from this cache will be memcg accounted, regardless of
* __GFP_ACCOUNT being or not being passed to individual allocations.
*/
#ifdef CONFIG_MEMCG
# define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT)
#else
# define SLAB_ACCOUNT __SLAB_FLAG_UNUSED
#endif
#ifdef CONFIG_KASAN_GENERIC
#define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN)
#else
#define SLAB_KASAN __SLAB_FLAG_UNUSED
#endif
/*
* Ignore user specified debugging flags.
* Intended for caches created for self-tests so they have only flags
* specified in the code and other flags are ignored.
*/
#define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS)
#ifdef CONFIG_KFENCE
#define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE)
#else
#define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED
#endif
/* The following flags affect the page allocator grouping pages by mobility */
/**
* define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable.
*
* Use this flag for caches that have an associated shrinker. As a result, slab
* pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by
* mobility, and are accounted in SReclaimable counter in /proc/meminfo
*/
#ifndef CONFIG_SLUB_TINY
#define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT)
#else
#define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED
#endif
#define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */
/* Slab created using create_boot_cache */
#ifdef CONFIG_SLAB_OBJ_EXT
#define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT)
#else
#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED
#endif
/*
* ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
*
* Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault.
*
* ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can.
* Both make kfree a no-op.
*/
#define ZERO_SIZE_PTR ((void *)16)
#define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
(unsigned long)ZERO_SIZE_PTR)
#include <linux/kasan.h>
struct list_lru;
struct mem_cgroup;
/*
* struct kmem_cache related prototypes
*/
bool slab_is_available(void);
/**
* struct kmem_cache_args - Less common arguments for kmem_cache_create()
*
* Any uninitialized fields of the structure are interpreted as unused. The
* exception is @freeptr_offset where %0 is a valid value, so
* @use_freeptr_offset must be also set to %true in order to interpret the field
* as used. For @useroffset %0 is also valid, but only with non-%0
* @usersize.
*
* When %NULL args is passed to kmem_cache_create(), it is equivalent to all
* fields unused.
*/
struct kmem_cache_args {
/**
* @align: The required alignment for the objects.
*
* %0 means no specific alignment is requested.
*/
unsigned int align;
/**
* @useroffset: Usercopy region offset.
*
* %0 is a valid offset, when @usersize is non-%0
*/
unsigned int useroffset;
/**
* @usersize: Usercopy region size.
*
* %0 means no usercopy region is specified.
*/
unsigned int usersize;
/**
* @freeptr_offset: Custom offset for the free pointer
* in &SLAB_TYPESAFE_BY_RCU caches
*
* By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer
* outside of the object. This might cause the object to grow in size.
* Cache creators that have a reason to avoid this can specify a custom
* free pointer offset in their struct where the free pointer will be
* placed.
*
* Note that placing the free pointer inside the object requires the
* caller to ensure that no fields are invalidated that are required to
* guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for
* details).
*
* Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset
* is specified, %use_freeptr_offset must be set %true.
*
* Note that @ctor currently isn't supported with custom free pointers
* as a @ctor requires an external free pointer.
*/
unsigned int freeptr_offset;
/**
* @use_freeptr_offset: Whether a @freeptr_offset is used.
*/
bool use_freeptr_offset;
/**
* @ctor: A constructor for the objects.
*
* The constructor is invoked for each object in a newly allocated slab
* page. It is the cache user's responsibility to free object in the
* same state as after calling the constructor, or deal appropriately
* with any differences between a freshly constructed and a reallocated
* object.
*
* %NULL means no constructor.
*/
void (*ctor)(void *);
};
struct kmem_cache *__kmem_cache_create_args(const char *name,
unsigned int object_size,
struct kmem_cache_args *args,
slab_flags_t flags);
static inline struct kmem_cache *
__kmem_cache_create(const char *name, unsigned int size, unsigned int align,
slab_flags_t flags, void (*ctor)(void *))
{
struct kmem_cache_args kmem_args = {
.align = align,
.ctor = ctor,
};
return __kmem_cache_create_args(name, size, &kmem_args, flags);
}
/**
* kmem_cache_create_usercopy - Create a kmem cache with a region suitable
* for copying to userspace.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
* @flags: SLAB flags
* @useroffset: Usercopy region offset
* @usersize: Usercopy region size
* @ctor: A constructor for the objects, or %NULL.
*
* This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY()
* if whitelisting a single field is sufficient, or kmem_cache_create() with
* the necessary parameters passed via the args parameter (see
* &struct kmem_cache_args)
*
* Return: a pointer to the cache on success, NULL on failure.
*/
static inline struct kmem_cache *
kmem_cache_create_usercopy(const char *name, unsigned int size,
unsigned int align, slab_flags_t flags,
unsigned int useroffset, unsigned int usersize,
void (*ctor)(void *))
{
struct kmem_cache_args kmem_args = {
.align = align,
.ctor = ctor,
.useroffset = useroffset,
.usersize = usersize,
};
return __kmem_cache_create_args(name, size, &kmem_args, flags);
}
/* If NULL is passed for @args, use this variant with default arguments. */
static inline struct kmem_cache *
__kmem_cache_default_args(const char *name, unsigned int size,
struct kmem_cache_args *args,
slab_flags_t flags)
{
struct kmem_cache_args kmem_default_args = {};
/* Make sure we don't get passed garbage. */
if (WARN_ON_ONCE(args))
return ERR_PTR(-EINVAL);
return __kmem_cache_create_args(name, size, &kmem_default_args, flags);
}
/**
* kmem_cache_create - Create a kmem cache.
* @__name: A string which is used in /proc/slabinfo to identify this cache.
* @__object_size: The size of objects to be created in this cache.
* @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL
* means defaults will be used for all the arguments.
*
* This is currently implemented as a macro using ``_Generic()`` to call
* either the new variant of the function, or a legacy one.
*
* The new variant has 4 parameters:
* ``kmem_cache_create(name, object_size, args, flags)``
*
* See __kmem_cache_create_args() which implements this.
*
* The legacy variant has 5 parameters:
* ``kmem_cache_create(name, object_size, align, flags, ctor)``
*
* The align and ctor parameters map to the respective fields of
* &struct kmem_cache_args
*
* Context: Cannot be called within a interrupt, but can be interrupted.
*
* Return: a pointer to the cache on success, NULL on failure.
*/
#define kmem_cache_create(__name, __object_size, __args, ...) \
_Generic((__args), \
struct kmem_cache_args *: __kmem_cache_create_args, \
void *: __kmem_cache_default_args, \
default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__)
void kmem_cache_destroy(struct kmem_cache *s);
int kmem_cache_shrink(struct kmem_cache *s);
/*
* Please use this macro to create slab caches. Simply specify the
* name of the structure and maybe some flags that are listed above.
*
* The alignment of the struct determines object alignment. If you
* f.e. add ____cacheline_aligned_in_smp to the struct declaration
* then the objects will be properly aligned in SMP configurations.
*/
#define KMEM_CACHE(__struct, __flags) \
__kmem_cache_create_args(#__struct, sizeof(struct __struct), \
&(struct kmem_cache_args) { \
.align = __alignof__(struct __struct), \
}, (__flags))
/*
* To whitelist a single field for copying to/from usercopy, use this
* macro instead for KMEM_CACHE() above.
*/
#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \
__kmem_cache_create_args(#__struct, sizeof(struct __struct), \
&(struct kmem_cache_args) { \
.align = __alignof__(struct __struct), \
.useroffset = offsetof(struct __struct, __field), \
.usersize = sizeof_field(struct __struct, __field), \
}, (__flags))
/*
* Common kmalloc functions provided by all allocators
*/
void * __must_check krealloc_noprof(const void *objp, size_t new_size,
gfp_t flags) __realloc_size(2);
#define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__))
void kfree(const void *objp);
void kfree_sensitive(const void *objp);
size_t __ksize(const void *objp);
DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T))
DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T))
/**
* ksize - Report actual allocation size of associated object
*
* @objp: Pointer returned from a prior kmalloc()-family allocation.
*
* This should not be used for writing beyond the originally requested
* allocation size. Either use krealloc() or round up the allocation size
* with kmalloc_size_roundup() prior to allocation. If this is used to
* access beyond the originally requested allocation size, UBSAN_BOUNDS
* and/or FORTIFY_SOURCE may trip, since they only know about the
* originally allocated size via the __alloc_size attribute.
*/
size_t ksize(const void *objp);
#ifdef CONFIG_PRINTK
bool kmem_dump_obj(void *object);
#else
static inline bool kmem_dump_obj(void *object) { return false; }
#endif
/*
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
* alignment larger than the alignment of a 64-bit integer.
* Setting ARCH_DMA_MINALIGN in arch headers allows that.
*/
#ifdef ARCH_HAS_DMA_MINALIGN
#if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN)
#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
#endif
#endif
#ifndef ARCH_KMALLOC_MINALIGN
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
#elif ARCH_KMALLOC_MINALIGN > 8
#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN
#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
#endif
/*
* Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
* Intended for arches that get misalignment faults even for 64 bit integer
* aligned buffers.
*/
#ifndef ARCH_SLAB_MINALIGN
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
/*
* Arches can define this function if they want to decide the minimum slab
* alignment at runtime. The value returned by the function must be a power
* of two and >= ARCH_SLAB_MINALIGN.
*/
#ifndef arch_slab_minalign
static inline unsigned int arch_slab_minalign(void)
{
return ARCH_SLAB_MINALIGN;
}
#endif
/*
* kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN.
* kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN
* and ARCH_SLAB_MINALIGN, but here we only assume the former alignment.
*/
#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN)
#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN)
#define __assume_page_alignment __assume_aligned(PAGE_SIZE)
/*
* Kmalloc array related definitions
*/
/*
* SLUB directly allocates requests fitting in to an order-1 page
* (PAGE_SIZE*2). Larger requests are passed to the page allocator.
*/
#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1)
#define KMALLOC_SHIFT_MAX (MAX_PAGE_ORDER + PAGE_SHIFT)
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 3
#endif
/* Maximum allocatable size */
#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX)
/* Maximum size for which we actually use a slab cache */
#define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH)
/* Maximum order allocatable via the slab allocator */
#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT)
/*
* Kmalloc subsystem.
*/
#ifndef KMALLOC_MIN_SIZE
#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
#endif
/*
* This restriction comes from byte sized index implementation.
* Page size is normally 2^12 bytes and, in this case, if we want to use
* byte sized index which can represent 2^8 entries, the size of the object
* should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
* If minimum size of kmalloc is less than 16, we use it as minimum object
* size and give up to use byte sized index.
*/
#define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \
(KMALLOC_MIN_SIZE) : 16)
#ifdef CONFIG_RANDOM_KMALLOC_CACHES
#define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies
#else
#define RANDOM_KMALLOC_CACHES_NR 0
#endif
/*
* Whenever changing this, take care of that kmalloc_type() and
* create_kmalloc_caches() still work as intended.
*
* KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP
* is for accounted but unreclaimable and non-dma objects. All the other
* kmem caches can have both accounted and unaccounted objects.
*/
enum kmalloc_cache_type {
KMALLOC_NORMAL = 0,
#ifndef CONFIG_ZONE_DMA
KMALLOC_DMA = KMALLOC_NORMAL,
#endif
#ifndef CONFIG_MEMCG
KMALLOC_CGROUP = KMALLOC_NORMAL,
#endif
KMALLOC_RANDOM_START = KMALLOC_NORMAL,
KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR,
#ifdef CONFIG_SLUB_TINY
KMALLOC_RECLAIM = KMALLOC_NORMAL,
#else
KMALLOC_RECLAIM,
#endif
#ifdef CONFIG_ZONE_DMA
KMALLOC_DMA,
#endif
#ifdef CONFIG_MEMCG
KMALLOC_CGROUP,
#endif
NR_KMALLOC_TYPES
};
typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1];
extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES];
/*
* Define gfp bits that should not be set for KMALLOC_NORMAL.
*/
#define KMALLOC_NOT_NORMAL_BITS \
(__GFP_RECLAIMABLE | \
(IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \
(IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0))
extern unsigned long random_kmalloc_seed;
static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller)
{
/*
* The most common case is KMALLOC_NORMAL, so test for it
* with a single branch for all the relevant flags.
*/
if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0))
#ifdef CONFIG_RANDOM_KMALLOC_CACHES
/* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */
return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed,
ilog2(RANDOM_KMALLOC_CACHES_NR + 1));
#else
return KMALLOC_NORMAL;
#endif
/*
* At least one of the flags has to be set. Their priorities in
* decreasing order are:
* 1) __GFP_DMA
* 2) __GFP_RECLAIMABLE
* 3) __GFP_ACCOUNT
*/
if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA))
return KMALLOC_DMA;
if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE))
return KMALLOC_RECLAIM;
else
return KMALLOC_CGROUP;
}
/*
* Figure out which kmalloc slab an allocation of a certain size
* belongs to.
* 0 = zero alloc
* 1 = 65 .. 96 bytes
* 2 = 129 .. 192 bytes
* n = 2^(n-1)+1 .. 2^n
*
* Note: __kmalloc_index() is compile-time optimized, and not runtime optimized;
* typical usage is via kmalloc_index() and therefore evaluated at compile-time.
* Callers where !size_is_constant should only be test modules, where runtime
* overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab().
*/
static __always_inline unsigned int __kmalloc_index(size_t size,
bool size_is_constant)
{
if (!size)
return 0;
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
return 1;
if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
return 2;
if (size <= 8) return 3;
if (size <= 16) return 4;
if (size <= 32) return 5;
if (size <= 64) return 6;
if (size <= 128) return 7;
if (size <= 256) return 8;
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
if (size <= 4 * 1024) return 12;
if (size <= 8 * 1024) return 13;
if (size <= 16 * 1024) return 14;
if (size <= 32 * 1024) return 15;
if (size <= 64 * 1024) return 16;
if (size <= 128 * 1024) return 17;
if (size <= 256 * 1024) return 18;
if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
if (size <= 2 * 1024 * 1024) return 21;
if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant)
BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()");
else
BUG();
/* Will never be reached. Needed because the compiler may complain */
return -1;
}
static_assert(PAGE_SHIFT <= 20);
#define kmalloc_index(s) __kmalloc_index(s, true)
#include <linux/alloc_tag.h>
/**
* kmem_cache_alloc - Allocate an object
* @cachep: The cache to allocate from.
* @flags: See kmalloc().
*
* Allocate an object from this cache.
* See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags.
*
* Return: pointer to the new object or %NULL in case of error
*/
void *kmem_cache_alloc_noprof(struct kmem_cache *cachep,
gfp_t flags) __assume_slab_alignment __malloc;
#define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__))
void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru,
gfp_t gfpflags) __assume_slab_alignment __malloc;
#define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__))
/**
* kmem_cache_charge - memcg charge an already allocated slab memory
* @objp: address of the slab object to memcg charge
* @gfpflags: describe the allocation context
*
* kmem_cache_charge allows charging a slab object to the current memcg,
* primarily in cases where charging at allocation time might not be possible
* because the target memcg is not known (i.e. softirq context)
*
* The objp should be pointer returned by the slab allocator functions like
* kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge
* behavior can be controlled through gfpflags parameter, which affects how the
* necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes
* that overcharging is requested instead of failure, but is not applied for the
* internal metadata allocation.
*
* There are several cases where it will return true even if the charging was
* not done:
* More specifically:
*
* 1. For !CONFIG_MEMCG or cgroup_disable=memory systems.
* 2. Already charged slab objects.
* 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc()
* without __GFP_ACCOUNT
* 4. Allocating internal metadata has failed
*
* Return: true if charge was successful otherwise false.
*/
bool kmem_cache_charge(void *objp, gfp_t gfpflags);
void kmem_cache_free(struct kmem_cache *s, void *objp);
kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags,
unsigned int useroffset, unsigned int usersize,
void (*ctor)(void *));
/*
* Bulk allocation and freeing operations. These are accelerated in an
* allocator specific way to avoid taking locks repeatedly or building
* metadata structures unnecessarily.
*
* Note that interrupts must be enabled when calling these functions.
*/
void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p);
int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p);
#define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__))
static __always_inline void kfree_bulk(size_t size, void **p)
{
kmem_cache_free_bulk(NULL, size, p);
}
void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags,
int node) __assume_slab_alignment __malloc;
#define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__))
/*
* These macros allow declaring a kmem_buckets * parameter alongside size, which
* can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call
* sites don't have to pass NULL.
*/
#ifdef CONFIG_SLAB_BUCKETS
#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b)
#define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b)
#define PASS_BUCKET_PARAM(_b) (_b)
#else
#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size)
#define PASS_BUCKET_PARAMS(_size, _b) (_size)
#define PASS_BUCKET_PARAM(_b) NULL
#endif
/*
* The following functions are not to be used directly and are intended only
* for internal use from kmalloc() and kmalloc_node()
* with the exception of kunit tests
*/
void *__kmalloc_noprof(size_t size, gfp_t flags)
__assume_kmalloc_alignment __alloc_size(1);
void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node)
__assume_kmalloc_alignment __alloc_size(1);
void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size)
__assume_kmalloc_alignment __alloc_size(3);
void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags,
int node, size_t size)
__assume_kmalloc_alignment __alloc_size(4);
void *__kmalloc_large_noprof(size_t size, gfp_t flags)
__assume_page_alignment __alloc_size(1);
void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node)
__assume_page_alignment __alloc_size(1);
/**
* kmalloc - allocate kernel memory
* @size: how many bytes of memory are required.
* @flags: describe the allocation context
*
* kmalloc is the normal method of allocating memory
* for objects smaller than page size in the kernel.
*
* The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN
* bytes. For @size of power of two bytes, the alignment is also guaranteed
* to be at least to the size. For other sizes, the alignment is guaranteed to
* be at least the largest power-of-two divisor of @size.
*
* The @flags argument may be one of the GFP flags defined at
* include/linux/gfp_types.h and described at
* :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>`
*
* The recommended usage of the @flags is described at
* :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>`
*
* Below is a brief outline of the most useful GFP flags
*
* %GFP_KERNEL
* Allocate normal kernel ram. May sleep.
*
* %GFP_NOWAIT
* Allocation will not sleep.
*
* %GFP_ATOMIC
* Allocation will not sleep. May use emergency pools.
*
* Also it is possible to set different flags by OR'ing
* in one or more of the following additional @flags:
*
* %__GFP_ZERO
* Zero the allocated memory before returning. Also see kzalloc().
*
* %__GFP_HIGH
* This allocation has high priority and may use emergency pools.
*
* %__GFP_NOFAIL
* Indicate that this allocation is in no way allowed to fail
* (think twice before using).
*
* %__GFP_NORETRY
* If memory is not immediately available,
* then give up at once.
*
* %__GFP_NOWARN
* If allocation fails, don't issue any warnings.
*
* %__GFP_RETRY_MAYFAIL
* Try really hard to succeed the allocation but fail
* eventually.
*/
static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags)
{
if (__builtin_constant_p(size) && size) {
unsigned int index;
if (size > KMALLOC_MAX_CACHE_SIZE)
return __kmalloc_large_noprof(size, flags);
index = kmalloc_index(size);
return __kmalloc_cache_noprof(
kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
flags, size);
}
return __kmalloc_noprof(size, flags);
}
#define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__))
#define kmem_buckets_alloc(_b, _size, _flags) \
alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE))
#define kmem_buckets_alloc_track_caller(_b, _size, _flags) \
alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_))
static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node)
{
if (__builtin_constant_p(size) && size) {
unsigned int index;
if (size > KMALLOC_MAX_CACHE_SIZE)
return __kmalloc_large_node_noprof(size, flags, node);
index = kmalloc_index(size);
return __kmalloc_cache_node_noprof(
kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
flags, node, size);
}
return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node);
}
#define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__))
/**
* kmalloc_array - allocate memory for an array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags)
{
size_t bytes;
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
return kmalloc_noprof(bytes, flags);
}
#define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__))
/**
* krealloc_array - reallocate memory for an array.
* @p: pointer to the memory chunk to reallocate
* @new_n: new number of elements to alloc
* @new_size: new size of a single member of the array
* @flags: the type of memory to allocate (see kmalloc)
*
* If __GFP_ZERO logic is requested, callers must ensure that, starting with the
* initial memory allocation, every subsequent call to this API for the same
* memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
* __GFP_ZERO is not fully honored by this API.
*
* See krealloc_noprof() for further details.
*
* In any case, the contents of the object pointed to are preserved up to the
* lesser of the new and old sizes.
*/
static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p,
size_t new_n,
size_t new_size,
gfp_t flags)
{
size_t bytes;
if (unlikely(check_mul_overflow(new_n, new_size, &bytes)))
return NULL;
return krealloc_noprof(p, bytes, flags);
}
#define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__))
/**
* kcalloc - allocate memory for an array. The memory is set to zero.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
#define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO)
void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node,
unsigned long caller) __alloc_size(1);
#define kmalloc_node_track_caller_noprof(size, flags, node, caller) \
__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller)
#define kmalloc_node_track_caller(...) \
alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_))
/*
* kmalloc_track_caller is a special version of kmalloc that records the
* calling function of the routine calling it for slab leak tracking instead
* of just the calling function (confusing, eh?).
* It's useful when the call to kmalloc comes from a widely-used standard
* allocator where we care about the real place the memory allocation
* request comes from.
*/
#define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE)
#define kmalloc_track_caller_noprof(...) \
kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_)
static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags,
int node)
{
size_t bytes;
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
if (__builtin_constant_p(n) && __builtin_constant_p(size))
return kmalloc_node_noprof(bytes, flags, node);
return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node);
}
#define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__))
#define kcalloc_node(_n, _size, _flags, _node) \
kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node)
/*
* Shortcuts
*/
#define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO)
/**
* kzalloc - allocate memory. The memory is set to zero.
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags)
{
return kmalloc_noprof(size, flags | __GFP_ZERO);
}
#define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__))
#define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node)
void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1);
#define kvmalloc_node_noprof(size, flags, node) \
__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node)
#define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__))
#define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE)
#define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE)
#define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO)
#define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node)
#define kmem_buckets_valloc(_b, _size, _flags) \
alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE))
static inline __alloc_size(1, 2) void *
kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node)
{
size_t bytes;
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
return kvmalloc_node_noprof(bytes, flags, node);
}
#define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE)
#define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node)
#define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE)
#define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__))
#define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__))
#define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__))
void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags)
__realloc_size(2);
#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__))
extern void kvfree(const void *addr);
DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T))
extern void kvfree_sensitive(const void *addr, size_t len);
unsigned int kmem_cache_size(struct kmem_cache *s);
#ifndef CONFIG_KVFREE_RCU_BATCHED
static inline void kvfree_rcu_barrier(void)
{
rcu_barrier();
}
static inline void kfree_rcu_scheduler_running(void) { }
#else
void kvfree_rcu_barrier(void);
void kfree_rcu_scheduler_running(void);
#endif
/**
* kmalloc_size_roundup - Report allocation bucket size for the given size
*
* @size: Number of bytes to round up from.
*
* This returns the number of bytes that would be available in a kmalloc()
* allocation of @size bytes. For example, a 126 byte request would be
* rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly
* for the general-purpose kmalloc()-based allocations, and is not for the
* pre-sized kmem_cache_alloc()-based allocations.)
*
* Use this to kmalloc() the full bucket size ahead of time instead of using
* ksize() to query the size after an allocation.
*/
size_t kmalloc_size_roundup(size_t size);
void __init kmem_cache_init_late(void);
void __init kvfree_rcu_init(void);
#endif /* _LINUX_SLAB_H */
/* SPDX-License-Identifier: GPL-2.0 */
/* rwsem.h: R/W semaphores, public interface
*
* Written by David Howells (dhowells@redhat.com).
* Derived from asm-i386/semaphore.h
*/
#ifndef _LINUX_RWSEM_H
#define _LINUX_RWSEM_H
#include <linux/linkage.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/err.h>
#include <linux/cleanup.h>
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __RWSEM_DEP_MAP_INIT(lockname) \
.dep_map = { \
.name = #lockname, \
.wait_type_inner = LD_WAIT_SLEEP, \
},
#else
# define __RWSEM_DEP_MAP_INIT(lockname)
#endif
#ifndef CONFIG_PREEMPT_RT
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
#include <linux/osq_lock.h>
#endif
/*
* For an uncontended rwsem, count and owner are the only fields a task
* needs to touch when acquiring the rwsem. So they are put next to each
* other to increase the chance that they will share the same cacheline.
*
* In a contended rwsem, the owner is likely the most frequently accessed
* field in the structure as the optimistic waiter that holds the osq lock
* will spin on owner. For an embedded rwsem, other hot fields in the
* containing structure should be moved further away from the rwsem to
* reduce the chance that they will share the same cacheline causing
* cacheline bouncing problem.
*/
struct rw_semaphore {
atomic_long_t count;
/*
* Write owner or one of the read owners as well flags regarding
* the current state of the rwsem. Can be used as a speculative
* check to see if the write owner is running on the cpu.
*/
atomic_long_t owner;
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
struct optimistic_spin_queue osq; /* spinner MCS lock */
#endif
raw_spinlock_t wait_lock;
struct list_head wait_list;
#ifdef CONFIG_DEBUG_RWSEMS
void *magic;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
#define RWSEM_UNLOCKED_VALUE 0UL
#define RWSEM_WRITER_LOCKED (1UL << 0)
#define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
static inline int rwsem_is_locked(struct rw_semaphore *sem)
{
return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE;
}
static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem)
{
WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE);
}
static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem)
{
WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED));
}
/* Common initializer macros and functions */
#ifdef CONFIG_DEBUG_RWSEMS
# define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname,
#else
# define __RWSEM_DEBUG_INIT(lockname)
#endif
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
#define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED,
#else
#define __RWSEM_OPT_INIT(lockname)
#endif
#define __RWSEM_INITIALIZER(name) \
{ __RWSEM_COUNT_INIT(name), \
.owner = ATOMIC_LONG_INIT(0), \
__RWSEM_OPT_INIT(name) \
.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\
.wait_list = LIST_HEAD_INIT((name).wait_list), \
__RWSEM_DEBUG_INIT(name) \
__RWSEM_DEP_MAP_INIT(name) }
#define DECLARE_RWSEM(name) \
struct rw_semaphore name = __RWSEM_INITIALIZER(name)
extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
struct lock_class_key *key);
#define init_rwsem(sem) \
do { \
static struct lock_class_key __key; \
\
__init_rwsem((sem), #sem, &__key); \
} while (0)
/*
* This is the same regardless of which rwsem implementation that is being used.
* It is just a heuristic meant to be called by somebody already holding the
* rwsem to see if somebody from an incompatible type is wanting access to the
* lock.
*/
static inline int rwsem_is_contended(struct rw_semaphore *sem)
{
return !list_empty(&sem->wait_list);
}
#else /* !CONFIG_PREEMPT_RT */
#include <linux/rwbase_rt.h>
struct rw_semaphore {
struct rwbase_rt rwbase;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
#define __RWSEM_INITIALIZER(name) \
{ \
.rwbase = __RWBASE_INITIALIZER(name), \
__RWSEM_DEP_MAP_INIT(name) \
}
#define DECLARE_RWSEM(lockname) \
struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name,
struct lock_class_key *key);
#define init_rwsem(sem) \
do { \
static struct lock_class_key __key; \
\
__init_rwsem((sem), #sem, &__key); \
} while (0)
static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem)
{
return rw_base_is_locked(&sem->rwbase);
}
static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem)
{
WARN_ON(!rwsem_is_locked(sem));
}
static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem)
{
WARN_ON(!rw_base_is_write_locked(&sem->rwbase));
}
static __always_inline int rwsem_is_contended(struct rw_semaphore *sem)
{
return rw_base_is_contended(&sem->rwbase);
}
#endif /* CONFIG_PREEMPT_RT */
/*
* The functions below are the same for all rwsem implementations including
* the RT specific variant.
*/
static inline void rwsem_assert_held(const struct rw_semaphore *sem)
{
if (IS_ENABLED(CONFIG_LOCKDEP))
lockdep_assert_held(sem);
else
rwsem_assert_held_nolockdep(sem);
}
static inline void rwsem_assert_held_write(const struct rw_semaphore *sem)
{
if (IS_ENABLED(CONFIG_LOCKDEP))
lockdep_assert_held_write(sem);
else
rwsem_assert_held_write_nolockdep(sem);
}
/*
* lock for reading
*/
extern void down_read(struct rw_semaphore *sem);
extern int __must_check down_read_interruptible(struct rw_semaphore *sem);
extern int __must_check down_read_killable(struct rw_semaphore *sem);
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
extern int down_read_trylock(struct rw_semaphore *sem);
/*
* lock for writing
*/
extern void down_write(struct rw_semaphore *sem);
extern int __must_check down_write_killable(struct rw_semaphore *sem);
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
extern int down_write_trylock(struct rw_semaphore *sem);
/*
* release a read lock
*/
extern void up_read(struct rw_semaphore *sem);
/*
* release a write lock
*/
extern void up_write(struct rw_semaphore *sem);
DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T))
DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T))
DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0)
DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
/*
* downgrade write lock to read lock
*/
extern void downgrade_write(struct rw_semaphore *sem);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* nested locking. NOTE: rwsems are not allowed to recurse
* (which occurs if the same task tries to acquire the same
* lock instance multiple times), but multiple locks of the
* same lock class might be taken, if the order of the locks
* is always the same. This ordering rule can be expressed
* to lockdep via the _nested() APIs, but enumerating the
* subclasses that are used. (If the nesting relationship is
* static then another method for expressing nested locking is
* the explicit definition of lock class keys and the use of
* lockdep_set_class() at lock initialization time.
* See Documentation/locking/lockdep-design.rst for more details.)
*/
extern void down_read_nested(struct rw_semaphore *sem, int subclass);
extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass);
extern void down_write_nested(struct rw_semaphore *sem, int subclass);
extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass);
extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
# define down_write_nest_lock(sem, nest_lock) \
do { \
typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
_down_write_nest_lock(sem, &(nest_lock)->dep_map); \
} while (0)
/*
* Take/release a lock when not the owner will release it.
*
* [ This API should be avoided as much as possible - the
* proper abstraction for this case is completions. ]
*/
extern void down_read_non_owner(struct rw_semaphore *sem);
extern void up_read_non_owner(struct rw_semaphore *sem);
#else
# define down_read_nested(sem, subclass) down_read(sem)
# define down_read_killable_nested(sem, subclass) down_read_killable(sem)
# define down_write_nest_lock(sem, nest_lock) down_write(sem)
# define down_write_nested(sem, subclass) down_write(sem)
# define down_write_killable_nested(sem, subclass) down_write_killable(sem)
# define down_read_non_owner(sem) down_read(sem)
# define up_read_non_owner(sem) up_read(sem)
#endif
#endif /* _LINUX_RWSEM_H */
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c.
*
* Copyright (C) 2004 Paul Mackerras, IBM Corp.
*/
#include <linux/bsearch.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sort.h>
#include <linux/uaccess.h>
#include <linux/extable.h>
#ifndef ARCH_HAS_RELATIVE_EXTABLE
#define ex_to_insn(x) ((x)->insn)
#else
static inline unsigned long ex_to_insn(const struct exception_table_entry *x)
{
return (unsigned long)&x->insn + x->insn;
}
#endif
#ifndef ARCH_HAS_RELATIVE_EXTABLE
#define swap_ex NULL
#else
static void swap_ex(void *a, void *b, int size)
{
struct exception_table_entry *x = a, *y = b, tmp;
int delta = b - a;
tmp = *x;
x->insn = y->insn + delta;
y->insn = tmp.insn - delta;
#ifdef swap_ex_entry_fixup
swap_ex_entry_fixup(x, y, tmp, delta);
#else
x->fixup = y->fixup + delta;
y->fixup = tmp.fixup - delta;
#endif
}
#endif /* ARCH_HAS_RELATIVE_EXTABLE */
/*
* The exception table needs to be sorted so that the binary
* search that we use to find entries in it works properly.
* This is used both for the kernel exception table and for
* the exception tables of modules that get loaded.
*/
static int cmp_ex_sort(const void *a, const void *b)
{
const struct exception_table_entry *x = a, *y = b;
/* avoid overflow */
if (ex_to_insn(x) > ex_to_insn(y))
return 1;
if (ex_to_insn(x) < ex_to_insn(y))
return -1;
return 0;
}
void sort_extable(struct exception_table_entry *start,
struct exception_table_entry *finish)
{
sort(start, finish - start, sizeof(struct exception_table_entry),
cmp_ex_sort, swap_ex);
}
#ifdef CONFIG_MODULES
/*
* If the exception table is sorted, any referring to the module init
* will be at the beginning or the end.
*/
void trim_init_extable(struct module *m)
{
/*trim the beginning*/
while (m->num_exentries &&
within_module_init(ex_to_insn(&m->extable[0]), m)) {
m->extable++;
m->num_exentries--;
}
/*trim the end*/
while (m->num_exentries &&
within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]),
m))
m->num_exentries--;
}
#endif /* CONFIG_MODULES */
static int cmp_ex_search(const void *key, const void *elt)
{
const struct exception_table_entry *_elt = elt;
unsigned long _key = *(unsigned long *)key;
/* avoid overflow */
if (_key > ex_to_insn(_elt))
return 1;
if (_key < ex_to_insn(_elt))
return -1;
return 0;
}
/*
* Search one exception table for an entry corresponding to the
* given instruction address, and return the address of the entry,
* or NULL if none is found.
* We use a binary search, and thus we assume that the table is
* already sorted.
*/
const struct exception_table_entry *
search_extable(const struct exception_table_entry *base,
const size_t num,
unsigned long value)
{
return bsearch(&value, base, num,
sizeof(struct exception_table_entry), cmp_ex_search);
}
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET3 Protocol independent device support routines.
*
* Derived from the non IP parts of dev.c 1.0.19
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
* Additional Authors:
* Florian la Roche <rzsfl@rz.uni-sb.de>
* Alan Cox <gw4pts@gw4pts.ampr.org>
* David Hinds <dahinds@users.sourceforge.net>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
* Adam Sulmicki <adam@cfar.umd.edu>
* Pekka Riikonen <priikone@poesidon.pspt.fi>
*
* Changes:
* D.J. Barrow : Fixed bug where dev->refcnt gets set
* to 2 if register_netdev gets called
* before net_dev_init & also removed a
* few lines of code in the process.
* Alan Cox : device private ioctl copies fields back.
* Alan Cox : Transmit queue code does relevant
* stunts to keep the queue safe.
* Alan Cox : Fixed double lock.
* Alan Cox : Fixed promisc NULL pointer trap
* ???????? : Support the full private ioctl range
* Alan Cox : Moved ioctl permission check into
* drivers
* Tim Kordas : SIOCADDMULTI/SIOCDELMULTI
* Alan Cox : 100 backlog just doesn't cut it when
* you start doing multicast video 8)
* Alan Cox : Rewrote net_bh and list manager.
* Alan Cox : Fix ETH_P_ALL echoback lengths.
* Alan Cox : Took out transmit every packet pass
* Saved a few bytes in the ioctl handler
* Alan Cox : Network driver sets packet type before
* calling netif_rx. Saves a function
* call a packet.
* Alan Cox : Hashed net_bh()
* Richard Kooijman: Timestamp fixes.
* Alan Cox : Wrong field in SIOCGIFDSTADDR
* Alan Cox : Device lock protection.
* Alan Cox : Fixed nasty side effect of device close
* changes.
* Rudi Cilibrasi : Pass the right thing to
* set_mac_address()
* Dave Miller : 32bit quantity for the device lock to
* make it work out on a Sparc.
* Bjorn Ekwall : Added KERNELD hack.
* Alan Cox : Cleaned up the backlog initialise.
* Craig Metz : SIOCGIFCONF fix if space for under
* 1 device.
* Thomas Bogendoerfer : Return ENODEV for dev_open, if there
* is no device open function.
* Andi Kleen : Fix error reporting for SIOCGIFCONF
* Michael Chastain : Fix signed/unsigned for SIOCGIFCONF
* Cyrus Durgin : Cleaned for KMOD
* Adam Sulmicki : Bug Fix : Network Device Unload
* A network device unload needs to purge
* the backlog queue.
* Paul Rusty Russell : SIOCSIFNAME
* Pekka Riikonen : Netdev boot-time settings code
* Andrew Morton : Make unregister_netdevice wait
* indefinitely on dev->refcnt
* J Hadi Salim : - Backlog queue sampling
* - netif_rx() feedback
*/
#include <linux/uaccess.h>
#include <linux/bitmap.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/hash.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/isolation.h>
#include <linux/sched/mm.h>
#include <linux/smpboot.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/ethtool_netlink.h>
#include <linux/skbuff.h>
#include <linux/kthread.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/busy_poll.h>
#include <linux/rtnetlink.h>
#include <linux/stat.h>
#include <net/dsa.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/gro.h>
#include <net/netdev_queues.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <net/tcx.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/ctype.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/mpls.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
#include <trace/events/qdisc.h>
#include <trace/events/xdp.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
#include <linux/hashtable.h>
#include <linux/vmalloc.h>
#include <linux/if_macvlan.h>
#include <linux/errqueue.h>
#include <linux/hrtimer.h>
#include <linux/netfilter_netdev.h>
#include <linux/crash_dump.h>
#include <linux/sctp.h>
#include <net/udp_tunnel.h>
#include <linux/net_namespace.h>
#include <linux/indirect_call_wrapper.h>
#include <net/devlink.h>
#include <linux/pm_runtime.h>
#include <linux/prandom.h>
#include <linux/once_lite.h>
#include <net/netdev_lock.h>
#include <net/netdev_rx_queue.h>
#include <net/page_pool/types.h>
#include <net/page_pool/helpers.h>
#include <net/page_pool/memory_provider.h>
#include <net/rps.h>
#include <linux/phy_link_topology.h>
#include "dev.h"
#include "devmem.h"
#include "net-sysfs.h"
static DEFINE_SPINLOCK(ptype_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_extack(unsigned long val,
struct net_device *dev,
struct netlink_ext_ack *extack);
static DEFINE_MUTEX(ifalias_mutex);
/* protects napi_hash addition/deletion and napi_gen_id */
static DEFINE_SPINLOCK(napi_hash_lock);
static unsigned int napi_gen_id = NR_CPUS;
static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
static inline void dev_base_seq_inc(struct net *net)
{
unsigned int val = net->dev_base_seq + 1;
WRITE_ONCE(net->dev_base_seq, val ?: 1);
}
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ));
return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
}
static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
{
return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
}
#ifndef CONFIG_PREEMPT_RT
static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key);
static int __init setup_backlog_napi_threads(char *arg)
{
static_branch_enable(&use_backlog_threads_key);
return 0;
}
early_param("thread_backlog_napi", setup_backlog_napi_threads);
static bool use_backlog_threads(void)
{
return static_branch_unlikely(&use_backlog_threads_key);
}
#else
static bool use_backlog_threads(void)
{
return true;
}
#endif
static inline void backlog_lock_irq_save(struct softnet_data *sd,
unsigned long *flags)
{
if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
else
local_irq_save(*flags);
}
static inline void backlog_lock_irq_disable(struct softnet_data *sd)
{
if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
spin_lock_irq(&sd->input_pkt_queue.lock);
else
local_irq_disable();
}
static inline void backlog_unlock_irq_restore(struct softnet_data *sd,
unsigned long *flags)
{
if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
else
local_irq_restore(*flags);
}
static inline void backlog_unlock_irq_enable(struct softnet_data *sd)
{
if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
spin_unlock_irq(&sd->input_pkt_queue.lock);
else
local_irq_enable();
}
static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,
const char *name)
{
struct netdev_name_node *name_node;
name_node = kmalloc(sizeof(*name_node), GFP_KERNEL);
if (!name_node)
return NULL;
INIT_HLIST_NODE(&name_node->hlist);
name_node->dev = dev;
name_node->name = name;
return name_node;
}
static struct netdev_name_node *
netdev_name_node_head_alloc(struct net_device *dev)
{
struct netdev_name_node *name_node;
name_node = netdev_name_node_alloc(dev, dev->name);
if (!name_node)
return NULL;
INIT_LIST_HEAD(&name_node->list);
return name_node;
}
static void netdev_name_node_free(struct netdev_name_node *name_node)
{
kfree(name_node);
}
static void netdev_name_node_add(struct net *net,
struct netdev_name_node *name_node)
{
hlist_add_head_rcu(&name_node->hlist,
dev_name_hash(net, name_node->name));
}
static void netdev_name_node_del(struct netdev_name_node *name_node)
{
hlist_del_rcu(&name_node->hlist);
}
static struct netdev_name_node *netdev_name_node_lookup(struct net *net,
const char *name)
{
struct hlist_head *head = dev_name_hash(net, name);
struct netdev_name_node *name_node;
hlist_for_each_entry(name_node, head, hlist)
if (!strcmp(name_node->name, name))
return name_node;
return NULL;
}
static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net,
const char *name)
{
struct hlist_head *head = dev_name_hash(net, name);
struct netdev_name_node *name_node;
hlist_for_each_entry_rcu(name_node, head, hlist)
if (!strcmp(name_node->name, name))
return name_node;
return NULL;
}
bool netdev_name_in_use(struct net *net, const char *name)
{
return netdev_name_node_lookup(net, name);
}
EXPORT_SYMBOL(netdev_name_in_use);
int netdev_name_node_alt_create(struct net_device *dev, const char *name)
{
struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
name_node = netdev_name_node_lookup(net, name);
if (name_node)
return -EEXIST;
name_node = netdev_name_node_alloc(dev, name);
if (!name_node)
return -ENOMEM;
netdev_name_node_add(net, name_node);
/* The node that holds dev->name acts as a head of per-device list. */
list_add_tail_rcu(&name_node->list, &dev->name_node->list);
return 0;
}
static void netdev_name_node_alt_free(struct rcu_head *head)
{
struct netdev_name_node *name_node =
container_of(head, struct netdev_name_node, rcu);
kfree(name_node->name);
netdev_name_node_free(name_node);
}
static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
{
netdev_name_node_del(name_node);
list_del(&name_node->list);
call_rcu(&name_node->rcu, netdev_name_node_alt_free);
}
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
{
struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
name_node = netdev_name_node_lookup(net, name);
if (!name_node)
return -ENOENT;
/* lookup might have found our primary name or a name belonging
* to another device.
*/
if (name_node == dev->name_node || name_node->dev != dev)
return -EINVAL;
__netdev_name_node_alt_destroy(name_node);
return 0;
}
static void netdev_name_node_alt_flush(struct net_device *dev)
{
struct netdev_name_node *name_node, *tmp;
list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) {
list_del(&name_node->list);
netdev_name_node_alt_free(&name_node->rcu);
}
}
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
netdev_for_each_altname(dev, name_node)
netdev_name_node_add(net, name_node);
/* We reserved the ifindex, this can't fail */
WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL));
dev_base_seq_inc(net);
}
/* Device list removal
* caller must respect a RCU grace period before freeing/reusing dev
*/
static void unlist_netdevice(struct net_device *dev)
{
struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
xa_erase(&net->dev_by_index, dev->ifindex);
netdev_for_each_altname(dev, name_node)
netdev_name_node_del(name_node);
/* Unlink dev from the device chain */
list_del_rcu(&dev->dev_list);
netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
dev_base_seq_inc(dev_net(dev));
}
/*
* Our notifier list
*/
static RAW_NOTIFIER_HEAD(netdev_chain);
/*
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = {
.process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock),
};
EXPORT_PER_CPU_SYMBOL(softnet_data);
/* Page_pool has a lockless array/stack to alloc/recycle pages.
* PP consumers must pay attention to run APIs in the appropriate context
* (e.g. NAPI context).
*/
DEFINE_PER_CPU(struct page_pool *, system_page_pool);
#ifdef CONFIG_LOCKDEP
/*
* register_netdevice() inits txq->_xmit_lock and sets lockdep class
* according to dev->type
*/
static const unsigned short netdev_lock_type[] = {
ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
static const char *const netdev_lock_name[] = {
"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
static inline unsigned short netdev_lock_pos(unsigned short dev_type)
{
int i;
for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
if (netdev_lock_type[i] == dev_type)
return i;
/* the last key is used by default */
return ARRAY_SIZE(netdev_lock_type) - 1;
}
static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
unsigned short dev_type)
{
int i;
i = netdev_lock_pos(dev_type);
lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
netdev_lock_name[i]);
}
static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
int i;
i = netdev_lock_pos(dev->type);
lockdep_set_class_and_name(&dev->addr_list_lock,
&netdev_addr_lock_key[i],
netdev_lock_name[i]);
}
#else
static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
unsigned short dev_type)
{
}
static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
}
#endif
/*******************************************************************************
*
* Protocol management and registration routines
*
*******************************************************************************/
/*
* Add a protocol ID to the list. Now that the input handler is
* smarter we can dispense with all the messy stuff that used to be
* here.
*
* BEWARE!!! Protocol handlers, mangling input packets,
* MUST BE last in hash buckets and checking protocol handlers
* MUST start from promiscuous ptype_all chain in net_bh.
* It is true now, do not change it.
* Explanation follows: if protocol handler, mangling packet, will
* be the first on list, it is not able to sense, that packet
* is cloned and should be copied-on-write, so that it will
* change it and subsequent readers will get broken packet.
* --ANK (980803)
*/
static inline struct list_head *ptype_head(const struct packet_type *pt)
{
if (pt->type == htons(ETH_P_ALL)) {
if (!pt->af_packet_net && !pt->dev)
return NULL;
return pt->dev ? &pt->dev->ptype_all :
&pt->af_packet_net->ptype_all;
}
if (pt->dev)
return &pt->dev->ptype_specific;
return pt->af_packet_net ? &pt->af_packet_net->ptype_specific :
&ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
}
/**
* dev_add_pack - add packet handler
* @pt: packet type declaration
*
* Add a protocol handler to the networking stack. The passed &packet_type
* is linked into kernel lists and may not be freed until it has been
* removed from the kernel lists.
*
* This call does not sleep therefore it can not
* guarantee all CPU's that are in middle of receiving packets
* will see the new packet type (until the next received packet).
*/
void dev_add_pack(struct packet_type *pt)
{
struct list_head *head = ptype_head(pt);
if (WARN_ON_ONCE(!head))
return;
spin_lock(&ptype_lock);
list_add_rcu(&pt->list, head);
spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(dev_add_pack);
/**
* __dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* The packet type might still be in use by receivers
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
void __dev_remove_pack(struct packet_type *pt)
{
struct list_head *head = ptype_head(pt);
struct packet_type *pt1;
if (!head)
return;
spin_lock(&ptype_lock);
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
list_del_rcu(&pt->list);
goto out;
}
}
pr_warn("dev_remove_pack: %p not found\n", pt);
out:
spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(__dev_remove_pack);
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* This call sleeps to guarantee that no CPU is looking at the packet
* type after return.
*/
void dev_remove_pack(struct packet_type *pt)
{
__dev_remove_pack(pt);
synchronize_net();
}
EXPORT_SYMBOL(dev_remove_pack);
/*******************************************************************************
*
* Device Interface Subroutines
*
*******************************************************************************/
/**
* dev_get_iflink - get 'iflink' value of a interface
* @dev: targeted interface
*
* Indicates the ifindex the interface is linked to.
* Physical interfaces have the same 'ifindex' and 'iflink' values.
*/
int dev_get_iflink(const struct net_device *dev)
{ if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev);
return READ_ONCE(dev->ifindex);
}
EXPORT_SYMBOL(dev_get_iflink);
/**
* dev_fill_metadata_dst - Retrieve tunnel egress information.
* @dev: targeted interface
* @skb: The packet.
*
* For better visibility of tunnel traffic OVS needs to retrieve
* egress tunnel information for a packet. Following API allows
* user to get this info.
*/
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct ip_tunnel_info *info;
if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst)
return -EINVAL;
info = skb_tunnel_info_unclone(skb);
if (!info)
return -ENOMEM;
if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX)))
return -EINVAL;
return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb);
}
EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack)
{
int k = stack->num_paths++;
if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX))
return NULL;
return &stack->path[k];
}
int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
struct net_device_path_stack *stack)
{
const struct net_device *last_dev;
struct net_device_path_ctx ctx = {
.dev = dev,
};
struct net_device_path *path;
int ret = 0;
memcpy(ctx.daddr, daddr, sizeof(ctx.daddr));
stack->num_paths = 0;
while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
last_dev = ctx.dev;
path = dev_fwd_path(stack);
if (!path)
return -1;
memset(path, 0, sizeof(struct net_device_path));
ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path);
if (ret < 0)
return -1;
if (WARN_ON_ONCE(last_dev == ctx.dev))
return -1;
}
if (!ctx.dev)
return ret;
path = dev_fwd_path(stack);
if (!path)
return -1;
path->type = DEV_PATH_ETHERNET;
path->dev = ctx.dev;
return ret;
}
EXPORT_SYMBOL_GPL(dev_fill_forward_path);
/* must be called under rcu_read_lock(), as we dont take a reference */
static struct napi_struct *napi_by_id(unsigned int napi_id)
{
unsigned int hash = napi_id % HASH_SIZE(napi_hash);
struct napi_struct *napi;
hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node)
if (napi->napi_id == napi_id)
return napi;
return NULL;
}
/* must be called under rcu_read_lock(), as we dont take a reference */
static struct napi_struct *
netdev_napi_by_id(struct net *net, unsigned int napi_id)
{
struct napi_struct *napi;
napi = napi_by_id(napi_id);
if (!napi)
return NULL;
if (WARN_ON_ONCE(!napi->dev))
return NULL;
if (!net_eq(net, dev_net(napi->dev)))
return NULL;
return napi;
}
/**
* netdev_napi_by_id_lock() - find a device by NAPI ID and lock it
* @net: the applicable net namespace
* @napi_id: ID of a NAPI of a target device
*
* Find a NAPI instance with @napi_id. Lock its device.
* The device must be in %NETREG_REGISTERED state for lookup to succeed.
* netdev_unlock() must be called to release it.
*
* Return: pointer to NAPI, its device with lock held, NULL if not found.
*/
struct napi_struct *
netdev_napi_by_id_lock(struct net *net, unsigned int napi_id)
{
struct napi_struct *napi;
struct net_device *dev;
rcu_read_lock();
napi = netdev_napi_by_id(net, napi_id);
if (!napi || READ_ONCE(napi->dev->reg_state) != NETREG_REGISTERED) {
rcu_read_unlock();
return NULL;
}
dev = napi->dev;
dev_hold(dev);
rcu_read_unlock();
dev = __netdev_put_lock(dev);
if (!dev)
return NULL;
rcu_read_lock();
napi = netdev_napi_by_id(net, napi_id);
if (napi && napi->dev != dev)
napi = NULL;
rcu_read_unlock();
if (!napi)
netdev_unlock(dev);
return napi;
}
/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name. Must be called under RTNL semaphore.
* If the name is found a pointer to the device is returned.
* If the name is not found then %NULL is returned. The
* reference counters are not incremented so the caller must be
* careful with locks.
*/
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
struct netdev_name_node *node_name;
node_name = netdev_name_node_lookup(net, name);
return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
/**
* dev_get_by_name_rcu - find a device by its name
* @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name.
* If the name is found a pointer to the device is returned.
* If the name is not found then %NULL is returned.
* The reference counters are not incremented so the caller must be
* careful with locks. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
struct netdev_name_node *node_name;
node_name = netdev_name_node_lookup_rcu(net, name);
return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
/* Deprecated for new users, call netdev_get_by_name() instead */
struct net_device *dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, name);
dev_hold(dev);
rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_name);
/**
* netdev_get_by_name() - find a device by its name
* @net: the applicable net namespace
* @name: name to find
* @tracker: tracking object for the acquired reference
* @gfp: allocation flags for the tracker
*
* Find an interface by name. This can be called from any
* context and does its own locking. The returned handle has
* the usage count incremented and the caller must use netdev_put() to
* release it when it is no longer needed. %NULL is returned if no
* matching device is found.
*/
struct net_device *netdev_get_by_name(struct net *net, const char *name,
netdevice_tracker *tracker, gfp_t gfp)
{
struct net_device *dev;
dev = dev_get_by_name(net, name);
if (dev)
netdev_tracker_alloc(dev, tracker, gfp);
return dev;
}
EXPORT_SYMBOL(netdev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
* about locking. The caller must hold the RTNL semaphore.
*/
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
return NULL;
}
EXPORT_SYMBOL(__dev_get_by_index);
/**
* dev_get_by_index_rcu - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
* about locking. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
{
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry_rcu(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_get_by_index_rcu);
/* Deprecated for new users, call netdev_get_by_index() instead */
struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
dev_hold(dev);
rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_index);
/**
* netdev_get_by_index() - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
* @tracker: tracking object for the acquired reference
* @gfp: allocation flags for the tracker
*
* Search for an interface by index. Returns NULL if the device
* is not found or a pointer to the device. The device returned has
* had a reference added and the pointer is safe until the user calls
* netdev_put() to indicate they have finished with it.
*/
struct net_device *netdev_get_by_index(struct net *net, int ifindex,
netdevice_tracker *tracker, gfp_t gfp)
{
struct net_device *dev;
dev = dev_get_by_index(net, ifindex);
if (dev)
netdev_tracker_alloc(dev, tracker, gfp);
return dev;
}
EXPORT_SYMBOL(netdev_get_by_index);
/**
* dev_get_by_napi_id - find a device by napi_id
* @napi_id: ID of the NAPI struct
*
* Search for an interface by NAPI ID. Returns %NULL if the device
* is not found or a pointer to the device. The device has not had
* its reference counter increased so the caller must be careful
* about locking. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_napi_id(unsigned int napi_id)
{
struct napi_struct *napi;
WARN_ON_ONCE(!rcu_read_lock_held());
if (!napi_id_valid(napi_id))
return NULL;
napi = napi_by_id(napi_id);
return napi ? napi->dev : NULL;
}
/* Release the held reference on the net_device, and if the net_device
* is still registered try to lock the instance lock. If device is being
* unregistered NULL will be returned (but the reference has been released,
* either way!)
*
* This helper is intended for locking net_device after it has been looked up
* using a lockless lookup helper. Lock prevents the instance from going away.
*/
struct net_device *__netdev_put_lock(struct net_device *dev)
{
netdev_lock(dev);
if (dev->reg_state > NETREG_REGISTERED) {
netdev_unlock(dev);
dev_put(dev);
return NULL;
}
dev_put(dev);
return dev;
}
/**
* netdev_get_by_index_lock() - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. If a valid device
* with @ifindex is found it will be returned with netdev->lock held.
* netdev_unlock() must be called to release it.
*
* Return: pointer to a device with lock held, NULL if not found.
*/
struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex)
{
struct net_device *dev;
dev = dev_get_by_index(net, ifindex);
if (!dev)
return NULL;
return __netdev_put_lock(dev);
}
struct net_device *
netdev_xa_find_lock(struct net *net, struct net_device *dev,
unsigned long *index)
{
if (dev)
netdev_unlock(dev);
do {
rcu_read_lock();
dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT);
if (!dev) {
rcu_read_unlock();
return NULL;
}
dev_hold(dev);
rcu_read_unlock();
dev = __netdev_put_lock(dev);
if (dev)
return dev;
(*index)++;
} while (true);
}
static DEFINE_SEQLOCK(netdev_rename_lock);
void netdev_copy_name(struct net_device *dev, char *name)
{
unsigned int seq;
do {
seq = read_seqbegin(&netdev_rename_lock); strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq));}
/**
* netdev_get_name - get a netdevice name, knowing its ifindex.
* @net: network namespace
* @name: a pointer to the buffer where the name will be stored.
* @ifindex: the ifindex of the interface to get the name from.
*/
int netdev_get_name(struct net *net, char *name, int ifindex)
{
struct net_device *dev;
int ret;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (!dev) {
ret = -ENODEV;
goto out;
}
netdev_copy_name(dev, name);
ret = 0;
out:
rcu_read_unlock();
return ret;
}
static bool dev_addr_cmp(struct net_device *dev, unsigned short type,
const char *ha)
{
return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len);
}
/**
* dev_getbyhwaddr_rcu - find a device by its hardware address
* @net: the applicable net namespace
* @type: media type of device
* @ha: hardware address
*
* Search for an interface by MAC address. Returns NULL if the device
* is not found or a pointer to the device.
* The caller must hold RCU.
* The returned device has not had its ref count increased
* and the caller must therefore be careful about locking
*
*/
struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
const char *ha)
{
struct net_device *dev;
for_each_netdev_rcu(net, dev)
if (dev_addr_cmp(dev, type, ha))
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
/**
* dev_getbyhwaddr() - find a device by its hardware address
* @net: the applicable net namespace
* @type: media type of device
* @ha: hardware address
*
* Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold
* rtnl_lock.
*
* Context: rtnl_lock() must be held.
* Return: pointer to the net_device, or NULL if not found
*/
struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
const char *ha)
{
struct net_device *dev;
ASSERT_RTNL();
for_each_netdev(net, dev)
if (dev_addr_cmp(dev, type, ha))
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_getbyhwaddr);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev, *ret = NULL;
rcu_read_lock();
for_each_netdev_rcu(net, dev)
if (dev->type == type) {
dev_hold(dev);
ret = dev;
break;
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
* __dev_get_by_flags - find any device with given flags
* @net: the applicable net namespace
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* Search for any interface with the given flags. Returns NULL if a device
* is not found or a pointer to the device. Must be called inside
* rtnl_lock(), and result refcount is unchanged.
*/
struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
unsigned short mask)
{
struct net_device *dev, *ret;
ASSERT_RTNL();
ret = NULL;
for_each_netdev(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
ret = dev;
break;
}
}
return ret;
}
EXPORT_SYMBOL(__dev_get_by_flags);
/**
* dev_valid_name - check if name is okay for network device
* @name: name string
*
* Network device names need to be valid file names to
* allow sysfs to work. We also disallow any kind of
* whitespace.
*/
bool dev_valid_name(const char *name)
{
if (*name == '\0')
return false;
if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
return false;
if (!strcmp(name, ".") || !strcmp(name, ".."))
return false;
while (*name) {
if (*name == '/' || *name == ':' || isspace(*name))
return false;
name++;
}
return true;
}
EXPORT_SYMBOL(dev_valid_name);
/**
* __dev_alloc_name - allocate a name for a device
* @net: network namespace to allocate the device name in
* @name: name format string
* @res: result name string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. It scans list of devices to build up a free map, then chooses
* the first empty slot. The caller must hold the dev_base or rtnl lock
* while allocating the name and adding the device in order to avoid
* duplicates.
* Limited to bits_per_byte * page size devices (ie 32K on most platforms).
* Returns the number of the unit assigned or a negative errno code.
*/
static int __dev_alloc_name(struct net *net, const char *name, char *res)
{
int i = 0;
const char *p;
const int max_netdevices = 8*PAGE_SIZE;
unsigned long *inuse;
struct net_device *d;
char buf[IFNAMSIZ];
/* Verify the string as this thing may have come from the user.
* There must be one "%d" and no other "%" characters.
*/
p = strchr(name, '%');
if (!p || p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
/* Use one page as a bit array of possible slots */
inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC);
if (!inuse)
return -ENOMEM;
for_each_netdev(net, d) {
struct netdev_name_node *name_node;
netdev_for_each_altname(d, name_node) {
if (!sscanf(name_node->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
continue;
/* avoid cases where sscanf is not exact inverse of printf */
snprintf(buf, IFNAMSIZ, name, i);
if (!strncmp(buf, name_node->name, IFNAMSIZ))
__set_bit(i, inuse);
}
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
continue;
/* avoid cases where sscanf is not exact inverse of printf */
snprintf(buf, IFNAMSIZ, name, i);
if (!strncmp(buf, d->name, IFNAMSIZ))
__set_bit(i, inuse);
}
i = find_first_zero_bit(inuse, max_netdevices);
bitmap_free(inuse);
if (i == max_netdevices)
return -ENFILE;
/* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
strscpy(buf, name, IFNAMSIZ);
snprintf(res, IFNAMSIZ, buf, i);
return i;
}
/* Returns negative errno or allocated unit id (see __dev_alloc_name()) */
static int dev_prep_valid_name(struct net *net, struct net_device *dev,
const char *want_name, char *out_name,
int dup_errno)
{
if (!dev_valid_name(want_name))
return -EINVAL;
if (strchr(want_name, '%'))
return __dev_alloc_name(net, want_name, out_name);
if (netdev_name_in_use(net, want_name))
return -dup_errno;
if (out_name != want_name)
strscpy(out_name, want_name, IFNAMSIZ);
return 0;
}
/**
* dev_alloc_name - allocate a name for a device
* @dev: device
* @name: name format string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. It scans list of devices to build up a free map, then chooses
* the first empty slot. The caller must hold the dev_base or rtnl lock
* while allocating the name and adding the device in order to avoid
* duplicates.
* Limited to bits_per_byte * page size devices (ie 32K on most platforms).
* Returns the number of the unit assigned or a negative errno code.
*/
int dev_alloc_name(struct net_device *dev, const char *name)
{
return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE);
}
EXPORT_SYMBOL(dev_alloc_name);
static int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name)
{
int ret;
ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST);
return ret < 0 ? ret : 0;
}
int netif_change_name(struct net_device *dev, const char *newname)
{
struct net *net = dev_net(dev);
unsigned char old_assign_type;
char oldname[IFNAMSIZ];
int err = 0;
int ret;
ASSERT_RTNL_NET(net);
if (!strncmp(newname, dev->name, IFNAMSIZ))
return 0;
memcpy(oldname, dev->name, IFNAMSIZ);
write_seqlock_bh(&netdev_rename_lock);
err = dev_get_valid_name(net, dev, newname);
write_sequnlock_bh(&netdev_rename_lock);
if (err < 0)
return err;
if (oldname[0] && !strchr(oldname, '%'))
netdev_info(dev, "renamed from %s%s\n", oldname,
dev->flags & IFF_UP ? " (while UP)" : "");
old_assign_type = dev->name_assign_type;
WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED);
rollback:
ret = device_rename(&dev->dev, dev->name);
if (ret) {
write_seqlock_bh(&netdev_rename_lock);
memcpy(dev->name, oldname, IFNAMSIZ);
write_sequnlock_bh(&netdev_rename_lock);
WRITE_ONCE(dev->name_assign_type, old_assign_type);
return ret;
}
netdev_adjacent_rename_links(dev, oldname);
netdev_name_node_del(dev->name_node);
synchronize_net();
netdev_name_node_add(net, dev->name_node);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
ret = notifier_to_errno(ret);
if (ret) {
/* err >= 0 after dev_alloc_name() or stores the first errno */
if (err >= 0) {
err = ret;
write_seqlock_bh(&netdev_rename_lock);
memcpy(dev->name, oldname, IFNAMSIZ);
write_sequnlock_bh(&netdev_rename_lock);
memcpy(oldname, newname, IFNAMSIZ);
WRITE_ONCE(dev->name_assign_type, old_assign_type);
old_assign_type = NET_NAME_RENAMED;
goto rollback;
} else {
netdev_err(dev, "name change rollback failed: %d\n",
ret);
}
}
return err;
}
int netif_set_alias(struct net_device *dev, const char *alias, size_t len)
{
struct dev_ifalias *new_alias = NULL;
if (len >= IFALIASZ)
return -EINVAL;
if (len) {
new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
if (!new_alias)
return -ENOMEM;
memcpy(new_alias->ifalias, alias, len);
new_alias->ifalias[len] = 0;
}
mutex_lock(&ifalias_mutex);
new_alias = rcu_replace_pointer(dev->ifalias, new_alias,
mutex_is_locked(&ifalias_mutex));
mutex_unlock(&ifalias_mutex);
if (new_alias)
kfree_rcu(new_alias, rcuhead);
return len;
}
/**
* dev_get_alias - get ifalias of a device
* @dev: device
* @name: buffer to store name of ifalias
* @len: size of buffer
*
* get ifalias for a device. Caller must make sure dev cannot go
* away, e.g. rcu read lock or own a reference count to device.
*/
int dev_get_alias(const struct net_device *dev, char *name, size_t len)
{
const struct dev_ifalias *alias;
int ret = 0;
rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock();
return ret;
}
/**
* netdev_features_change - device changes features
* @dev: device to cause notification
*
* Called to indicate a device has changed features.
*/
void netdev_features_change(struct net_device *dev)
{
call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);
void netif_state_change(struct net_device *dev)
{ netdev_ops_assert_locked_or_invisible(dev); if (dev->flags & IFF_UP) {
struct netdev_notifier_change_info change_info = {
.info.dev = dev,
};
call_netdevice_notifiers_info(NETDEV_CHANGE,
&change_info.info);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL);
}
}
/**
* __netdev_notify_peers - notify network peers about existence of @dev,
* to be called when rtnl lock is already held.
* @dev: network device
*
* Generate traffic such that interested network peers are aware of
* @dev, such as by generating a gratuitous ARP. This may be used when
* a device wants to inform the rest of the network about some sort of
* reconfiguration such as a failover event or virtual machine
* migration.
*/
void __netdev_notify_peers(struct net_device *dev)
{
ASSERT_RTNL();
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
}
EXPORT_SYMBOL(__netdev_notify_peers);
/**
* netdev_notify_peers - notify network peers about existence of @dev
* @dev: network device
*
* Generate traffic such that interested network peers are aware of
* @dev, such as by generating a gratuitous ARP. This may be used when
* a device wants to inform the rest of the network about some sort of
* reconfiguration such as a failover event or virtual machine
* migration.
*/
void netdev_notify_peers(struct net_device *dev)
{
rtnl_lock();
__netdev_notify_peers(dev);
rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);
static int napi_threaded_poll(void *data);
static int napi_kthread_create(struct napi_struct *n)
{
int err = 0;
/* Create and wake up the kthread once to put it in
* TASK_INTERRUPTIBLE mode to avoid the blocked task
* warning and work with loadavg.
*/
n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
n->dev->name, n->napi_id);
if (IS_ERR(n->thread)) {
err = PTR_ERR(n->thread);
pr_err("kthread_run failed with err %d\n", err);
n->thread = NULL;
}
return err;
}
static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
const struct net_device_ops *ops = dev->netdev_ops;
int ret;
ASSERT_RTNL();
dev_addr_check(dev);
if (!netif_device_present(dev)) {
/* may be detached because parent is runtime-suspended */
if (dev->dev.parent)
pm_runtime_resume(dev->dev.parent);
if (!netif_device_present(dev))
return -ENODEV;
}
/* Block netpoll from trying to do any rx path servicing.
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
netpoll_poll_disable(dev);
ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack);
ret = notifier_to_errno(ret);
if (ret)
return ret;
set_bit(__LINK_STATE_START, &dev->state);
netdev_ops_assert_locked(dev);
if (ops->ndo_validate_addr)
ret = ops->ndo_validate_addr(dev);
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
netpoll_poll_enable(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
else {
netif_set_up(dev, true);
dev_set_rx_mode(dev);
dev_activate(dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
}
int netif_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
int ret;
if (dev->flags & IFF_UP)
return 0;
ret = __dev_open(dev, extack);
if (ret < 0)
return ret;
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL);
call_netdevice_notifiers(NETDEV_UP, dev);
return ret;
}
static void __dev_close_many(struct list_head *head)
{
struct net_device *dev;
ASSERT_RTNL();
might_sleep();
list_for_each_entry(dev, head, close_list) {
/* Temporarily disable netpoll until the interface is down */
netpoll_poll_disable(dev);
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
/* Synchronize to scheduled poll. We cannot touch poll list, it
* can be even on different cpu. So just clear netif_running().
*
* dev->stop() will invoke napi_disable() on all of it's
* napi_struct instances on this device.
*/
smp_mb__after_atomic(); /* Commit netif_running(). */
}
dev_deactivate_many(head);
list_for_each_entry(dev, head, close_list) {
const struct net_device_ops *ops = dev->netdev_ops;
/*
* Call the device specific close. This cannot fail.
* Only if device is UP
*
* We allow it to be called even after a DETACH hot-plug
* event.
*/
netdev_ops_assert_locked(dev);
if (ops->ndo_stop)
ops->ndo_stop(dev);
netif_set_up(dev, false);
netpoll_poll_enable(dev);
}
}
static void __dev_close(struct net_device *dev)
{
LIST_HEAD(single);
list_add(&dev->close_list, &single);
__dev_close_many(&single);
list_del(&single);
}
void dev_close_many(struct list_head *head, bool unlink)
{
struct net_device *dev, *tmp;
/* Remove the devices that don't need to be closed */
list_for_each_entry_safe(dev, tmp, head, close_list)
if (!(dev->flags & IFF_UP))
list_del_init(&dev->close_list);
__dev_close_many(head);
list_for_each_entry_safe(dev, tmp, head, close_list) {
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL);
call_netdevice_notifiers(NETDEV_DOWN, dev);
if (unlink)
list_del_init(&dev->close_list);
}
}
EXPORT_SYMBOL(dev_close_many);
void netif_close(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
list_add(&dev->close_list, &single);
dev_close_many(&single, true);
list_del(&single);
}
}
EXPORT_SYMBOL(netif_close);
void netif_disable_lro(struct net_device *dev)
{
struct net_device *lower_dev;
struct list_head *iter;
dev->wanted_features &= ~NETIF_F_LRO;
netdev_update_features(dev);
if (unlikely(dev->features & NETIF_F_LRO))
netdev_WARN(dev, "failed to disable LRO!\n");
netdev_for_each_lower_dev(dev, lower_dev, iter) {
netdev_lock_ops(lower_dev);
netif_disable_lro(lower_dev);
netdev_unlock_ops(lower_dev);
}
}
EXPORT_IPV6_MOD(netif_disable_lro);
/**
* dev_disable_gro_hw - disable HW Generic Receive Offload on a device
* @dev: device
*
* Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be
* called under RTNL. This is needed if Generic XDP is installed on
* the device.
*/
static void dev_disable_gro_hw(struct net_device *dev)
{
dev->wanted_features &= ~NETIF_F_GRO_HW;
netdev_update_features(dev);
if (unlikely(dev->features & NETIF_F_GRO_HW))
netdev_WARN(dev, "failed to disable GRO_HW!\n");
}
const char *netdev_cmd_to_name(enum netdev_cmd cmd)
{
#define N(val) \
case NETDEV_##val: \
return "NETDEV_" __stringify(val);
switch (cmd) {
N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER)
N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE)
N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE)
N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN)
N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA)
N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE)
N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE)
N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA)
N(XDP_FEAT_CHANGE)
}
#undef N
return "UNKNOWN_NETDEV_EVENT";
}
EXPORT_SYMBOL_GPL(netdev_cmd_to_name);
static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
struct net_device *dev)
{
struct netdev_notifier_info info = {
.dev = dev,
};
return nb->notifier_call(nb, val, &info);
}
static int call_netdevice_register_notifiers(struct notifier_block *nb,
struct net_device *dev)
{
int err;
err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
err = notifier_to_errno(err);
if (err)
return err;
if (!(dev->flags & IFF_UP))
return 0;
call_netdevice_notifier(nb, NETDEV_UP, dev);
return 0;
}
static void call_netdevice_unregister_notifiers(struct notifier_block *nb,
struct net_device *dev)
{
if (dev->flags & IFF_UP) {
call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
dev);
call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
struct net *net)
{
struct net_device *dev;
int err;
for_each_netdev(net, dev) {
netdev_lock_ops(dev);
err = call_netdevice_register_notifiers(nb, dev);
netdev_unlock_ops(dev);
if (err)
goto rollback;
}
return 0;
rollback:
for_each_netdev_continue_reverse(net, dev)
call_netdevice_unregister_notifiers(nb, dev);
return err;
}
static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb,
struct net *net)
{
struct net_device *dev;
for_each_netdev(net, dev)
call_netdevice_unregister_notifiers(nb, dev);
}
static int dev_boot_phase = 1;
/**
* register_netdevice_notifier - register a network notifier block
* @nb: notifier
*
* Register a notifier to be called when network device events occur.
* The notifier passed is linked into the kernel structures and must
* not be reused until it has been unregistered. A negative errno code
* is returned on a failure.
*
* When registered all registration and up events are replayed
* to the new notifier to allow device to have a race free
* view of the network device list.
*/
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net *net;
int err;
/* Close race with setup_net() and cleanup_net() */
down_write(&pernet_ops_rwsem);
/* When RTNL is removed, we need protection for netdev_chain. */
rtnl_lock();
err = raw_notifier_chain_register(&netdev_chain, nb);
if (err)
goto unlock;
if (dev_boot_phase)
goto unlock;
for_each_net(net) {
__rtnl_net_lock(net);
err = call_netdevice_register_net_notifiers(nb, net);
__rtnl_net_unlock(net);
if (err)
goto rollback;
}
unlock:
rtnl_unlock();
up_write(&pernet_ops_rwsem);
return err;
rollback:
for_each_net_continue_reverse(net) {
__rtnl_net_lock(net);
call_netdevice_unregister_net_notifiers(nb, net);
__rtnl_net_unlock(net);
}
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
EXPORT_SYMBOL(register_netdevice_notifier);
/**
* unregister_netdevice_notifier - unregister a network notifier block
* @nb: notifier
*
* Unregister a notifier previously registered by
* register_netdevice_notifier(). The notifier is unlinked into the
* kernel structures and may then be reused. A negative errno code
* is returned on a failure.
*
* After unregistering unregister and down device events are synthesized
* for all devices on the device list to the removed notifier to remove
* the need for special case cleanup code.
*/
int unregister_netdevice_notifier(struct notifier_block *nb)
{
struct net *net;
int err;
/* Close race with setup_net() and cleanup_net() */
down_write(&pernet_ops_rwsem);
rtnl_lock();
err = raw_notifier_chain_unregister(&netdev_chain, nb);
if (err)
goto unlock;
for_each_net(net) {
__rtnl_net_lock(net);
call_netdevice_unregister_net_notifiers(nb, net);
__rtnl_net_unlock(net);
}
unlock:
rtnl_unlock();
up_write(&pernet_ops_rwsem);
return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
static int __register_netdevice_notifier_net(struct net *net,
struct notifier_block *nb,
bool ignore_call_fail)
{
int err;
err = raw_notifier_chain_register(&net->netdev_chain, nb);
if (err)
return err;
if (dev_boot_phase)
return 0;
err = call_netdevice_register_net_notifiers(nb, net);
if (err && !ignore_call_fail)
goto chain_unregister;
return 0;
chain_unregister:
raw_notifier_chain_unregister(&net->netdev_chain, nb);
return err;
}
static int __unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb)
{
int err;
err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
if (err)
return err;
call_netdevice_unregister_net_notifiers(nb, net);
return 0;
}
/**
* register_netdevice_notifier_net - register a per-netns network notifier block
* @net: network namespace
* @nb: notifier
*
* Register a notifier to be called when network device events occur.
* The notifier passed is linked into the kernel structures and must
* not be reused until it has been unregistered. A negative errno code
* is returned on a failure.
*
* When registered all registration and up events are replayed
* to the new notifier to allow device to have a race free
* view of the network device list.
*/
int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
{
int err;
rtnl_net_lock(net);
err = __register_netdevice_notifier_net(net, nb, false);
rtnl_net_unlock(net);
return err;
}
EXPORT_SYMBOL(register_netdevice_notifier_net);
/**
* unregister_netdevice_notifier_net - unregister a per-netns
* network notifier block
* @net: network namespace
* @nb: notifier
*
* Unregister a notifier previously registered by
* register_netdevice_notifier_net(). The notifier is unlinked from the
* kernel structures and may then be reused. A negative errno code
* is returned on a failure.
*
* After unregistering unregister and down device events are synthesized
* for all devices on the device list to the removed notifier to remove
* the need for special case cleanup code.
*/
int unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb)
{
int err;
rtnl_net_lock(net);
err = __unregister_netdevice_notifier_net(net, nb);
rtnl_net_unlock(net);
return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier_net);
static void __move_netdevice_notifier_net(struct net *src_net,
struct net *dst_net,
struct notifier_block *nb)
{
__unregister_netdevice_notifier_net(src_net, nb);
__register_netdevice_notifier_net(dst_net, nb, true);
}
static void rtnl_net_dev_lock(struct net_device *dev)
{
bool again;
do {
struct net *net;
again = false;
/* netns might be being dismantled. */
rcu_read_lock();
net = dev_net_rcu(dev);
net_passive_inc(net);
rcu_read_unlock();
rtnl_net_lock(net);
#ifdef CONFIG_NET_NS
/* dev might have been moved to another netns. */
if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) {
rtnl_net_unlock(net);
net_passive_dec(net);
again = true;
}
#endif
} while (again);
}
static void rtnl_net_dev_unlock(struct net_device *dev)
{
struct net *net = dev_net(dev);
rtnl_net_unlock(net);
net_passive_dec(net);
}
int register_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn)
{
int err;
rtnl_net_dev_lock(dev);
err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
if (!err) {
nn->nb = nb;
list_add(&nn->list, &dev->net_notifier_list);
}
rtnl_net_dev_unlock(dev);
return err;
}
EXPORT_SYMBOL(register_netdevice_notifier_dev_net);
int unregister_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn)
{
int err;
rtnl_net_dev_lock(dev);
list_del(&nn->list);
err = __unregister_netdevice_notifier_net(dev_net(dev), nb);
rtnl_net_dev_unlock(dev);
return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net);
static void move_netdevice_notifiers_dev_net(struct net_device *dev,
struct net *net)
{
struct netdev_net_notifier *nn;
list_for_each_entry(nn, &dev->net_notifier_list, list)
__move_netdevice_notifier_net(dev_net(dev), net, nn->nb);
}
/**
* call_netdevice_notifiers_info - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @info: notifier information data
*
* Call all network notifier blocks. Parameters and return value
* are as for raw_notifier_call_chain().
*/
int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info)
{
struct net *net = dev_net(info->dev);
int ret;
ASSERT_RTNL();
/* Run per-netns notifier block chain first, then run the global one.
* Hopefully, one day, the global one is going to be removed after
* all notifier block registrators get converted to be per-netns.
*/
ret = raw_notifier_call_chain(&net->netdev_chain, val, info);
if (ret & NOTIFY_STOP_MASK)
return ret;
return raw_notifier_call_chain(&netdev_chain, val, info);
}
/**
* call_netdevice_notifiers_info_robust - call per-netns notifier blocks
* for and rollback on error
* @val_up: value passed unmodified to notifier function
* @val_down: value passed unmodified to the notifier function when
* recovering from an error on @val_up
* @info: notifier information data
*
* Call all per-netns network notifier blocks, but not notifier blocks on
* the global notifier chain. Parameters and return value are as for
* raw_notifier_call_chain_robust().
*/
static int
call_netdevice_notifiers_info_robust(unsigned long val_up,
unsigned long val_down,
struct netdev_notifier_info *info)
{
struct net *net = dev_net(info->dev);
ASSERT_RTNL();
return raw_notifier_call_chain_robust(&net->netdev_chain,
val_up, val_down, info);
}
static int call_netdevice_notifiers_extack(unsigned long val,
struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_info info = {
.dev = dev,
.extack = extack,
};
return call_netdevice_notifiers_info(val, &info);
}
/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @dev: net_device pointer passed unmodified to notifier function
*
* Call all network notifier blocks. Parameters and return value
* are as for raw_notifier_call_chain().
*/
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
return call_netdevice_notifiers_extack(val, dev, NULL);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
/**
* call_netdevice_notifiers_mtu - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @dev: net_device pointer passed unmodified to notifier function
* @arg: additional u32 argument passed to the notifier function
*
* Call all network notifier blocks. Parameters and return value
* are as for raw_notifier_call_chain().
*/
static int call_netdevice_notifiers_mtu(unsigned long val,
struct net_device *dev, u32 arg)
{
struct netdev_notifier_info_ext info = {
.info.dev = dev,
.ext.mtu = arg,
};
BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0);
return call_netdevice_notifiers_info(val, &info.info);
}
#ifdef CONFIG_NET_INGRESS
static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);
void net_inc_ingress_queue(void)
{
static_branch_inc(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
void net_dec_ingress_queue(void)
{
static_branch_dec(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
#endif
#ifdef CONFIG_NET_EGRESS
static DEFINE_STATIC_KEY_FALSE(egress_needed_key);
void net_inc_egress_queue(void)
{
static_branch_inc(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_egress_queue);
void net_dec_egress_queue(void)
{
static_branch_dec(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_egress_queue);
#endif
#ifdef CONFIG_NET_CLS_ACT
DEFINE_STATIC_KEY_FALSE(tcf_sw_enabled_key);
EXPORT_SYMBOL(tcf_sw_enabled_key);
#endif
DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
EXPORT_SYMBOL(netstamp_needed_key);
#ifdef CONFIG_JUMP_LABEL
static atomic_t netstamp_needed_deferred;
static atomic_t netstamp_wanted;
static void netstamp_clear(struct work_struct *work)
{
int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
int wanted;
wanted = atomic_add_return(deferred, &netstamp_wanted);
if (wanted > 0)
static_branch_enable(&netstamp_needed_key);
else
static_branch_disable(&netstamp_needed_key);
}
static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif
void net_enable_timestamp(void)
{
#ifdef CONFIG_JUMP_LABEL
int wanted = atomic_read(&netstamp_wanted);
while (wanted > 0) {
if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1))
return;
}
atomic_inc(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
static_branch_inc(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
#ifdef CONFIG_JUMP_LABEL
int wanted = atomic_read(&netstamp_wanted);
while (wanted > 1) {
if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1))
return;
}
atomic_dec(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
static_branch_dec(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp_set(struct sk_buff *skb)
{
skb->tstamp = 0;
skb->tstamp_type = SKB_CLOCK_REALTIME;
if (static_branch_unlikely(&netstamp_needed_key))
skb->tstamp = ktime_get_real();
}
#define net_timestamp_check(COND, SKB) \
if (static_branch_unlikely(&netstamp_needed_key)) { \
if ((COND) && !(SKB)->tstamp) \
(SKB)->tstamp = ktime_get_real(); \
} \
bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
{
return __is_skb_forwardable(dev, skb, true);
}
EXPORT_SYMBOL_GPL(is_skb_forwardable);
static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
bool check_mtu)
{
int ret = ____dev_forward_skb(dev, skb, check_mtu);
if (likely(!ret)) {
skb->protocol = eth_type_trans(skb, dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
return ret;
}
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
return __dev_forward_skb2(dev, skb, true);
}
EXPORT_SYMBOL_GPL(__dev_forward_skb);
/**
* dev_forward_skb - loopback an skb to another netif
*
* @dev: destination network device
* @skb: buffer to forward
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_DROP (packet was dropped, but freed)
*
* dev_forward_skb can be used for injecting an skb from the
* start_xmit function of one device into the receive queue
* of another device.
*
* The receiving device may be in another namespace, so
* we have to clear all information in the skb that could
* impact namespace isolation.
*/
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb)
{
return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb);
}
static inline int deliver_skb(struct sk_buff *skb,
struct packet_type *pt_prev,
struct net_device *orig_dev)
{
if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
return -ENOMEM;
refcount_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
static inline void deliver_ptype_list_skb(struct sk_buff *skb,
struct packet_type **pt,
struct net_device *orig_dev,
__be16 type,
struct list_head *ptype_list)
{
struct packet_type *ptype, *pt_prev = *pt;
list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type)
continue;
if (pt_prev) deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
*pt = pt_prev;
}
static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
{
if (!ptype->af_packet_priv || !skb->sk)
return false;
if (ptype->id_match)
return ptype->id_match(ptype, skb->sk);
else if ((struct sock *)ptype->af_packet_priv == skb->sk)
return true;
return false;
}
/**
* dev_nit_active_rcu - return true if any network interface taps are in use
*
* The caller must hold the RCU lock
*
* @dev: network device to check for the presence of taps
*/
bool dev_nit_active_rcu(const struct net_device *dev)
{
/* Callers may hold either RCU or RCU BH lock */
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
return !list_empty(&dev_net(dev)->ptype_all) ||
!list_empty(&dev->ptype_all);
}
EXPORT_SYMBOL_GPL(dev_nit_active_rcu);
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
*/
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
struct packet_type *ptype, *pt_prev = NULL;
struct list_head *ptype_list;
struct sk_buff *skb2 = NULL;
rcu_read_lock();
ptype_list = &dev_net_rcu(dev)->ptype_all;
again:
list_for_each_entry_rcu(ptype, ptype_list, list) {
if (READ_ONCE(ptype->ignore_outgoing))
continue;
/* Never send packets back to the socket
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if (skb_loop_sk(ptype, skb))
continue;
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
continue;
}
/* need to clone skb, done only once */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
goto out_unlock;
net_timestamp_set(skb2);
/* skb->nh should be correctly
* set by sender, so that the second statement is
* just protection against buggy protocols.
*/
skb_reset_mac_header(skb2);
if (skb_network_header(skb2) < skb2->data ||
skb_network_header(skb2) > skb_tail_pointer(skb2)) {
net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
ntohs(skb2->protocol),
dev->name);
skb_reset_network_header(skb2);
}
skb2->transport_header = skb2->network_header;
skb2->pkt_type = PACKET_OUTGOING;
pt_prev = ptype;
}
if (ptype_list != &dev->ptype_all) {
ptype_list = &dev->ptype_all;
goto again;
}
out_unlock:
if (pt_prev) {
if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC))
pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
else
kfree_skb(skb2);
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(dev_queue_xmit_nit);
/**
* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
* @dev: Network device
* @txq: number of queues available
*
* If real_num_tx_queues is changed the tc mappings may no longer be
* valid. To resolve this verify the tc mapping remains valid and if
* not NULL the mapping. With no priorities mapping to this
* offset/count pair it will no longer be used. In the worst case TC0
* is invalid nothing can be done so disable priority mappings. If is
* expected that drivers will fix this mapping if they can before
* calling netif_set_real_num_tx_queues.
*/
static void netif_setup_tc(struct net_device *dev, unsigned int txq)
{
int i;
struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
/* If TC0 is invalidated disable TC mapping */
if (tc->offset + tc->count > txq) {
netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n");
dev->num_tc = 0;
return;
}
/* Invalidated prio to tc mappings set to TC0 */
for (i = 1; i < TC_BITMASK + 1; i++) {
int q = netdev_get_prio_tc_map(dev, i);
tc = &dev->tc_to_txq[q];
if (tc->offset + tc->count > txq) {
netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n",
i, q);
netdev_set_prio_tc_map(dev, i, 0);
}
}
}
int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
{
if (dev->num_tc) {
struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
int i;
/* walk through the TCs and see if it falls into any of them */
for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
if ((txq - tc->offset) < tc->count)
return i;
}
/* didn't find it, just return -1 to indicate no match */
return -1;
}
return 0;
}
EXPORT_SYMBOL(netdev_txq_to_tc);
#ifdef CONFIG_XPS
static struct static_key xps_needed __read_mostly;
static struct static_key xps_rxqs_needed __read_mostly;
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
struct xps_dev_maps *old_maps, int tci, u16 index)
{
struct xps_map *map = NULL;
int pos;
map = xmap_dereference(dev_maps->attr_map[tci]);
if (!map)
return false;
for (pos = map->len; pos--;) {
if (map->queues[pos] != index)
continue;
if (map->len > 1) {
map->queues[pos] = map->queues[--map->len];
break;
}
if (old_maps)
RCU_INIT_POINTER(old_maps->attr_map[tci], NULL);
RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
kfree_rcu(map, rcu);
return false;
}
return true;
}
static bool remove_xps_queue_cpu(struct net_device *dev,
struct xps_dev_maps *dev_maps,
int cpu, u16 offset, u16 count)
{
int num_tc = dev_maps->num_tc;
bool active = false;
int tci;
for (tci = cpu * num_tc; num_tc--; tci++) {
int i, j;
for (i = count, j = offset; i--; j++) {
if (!remove_xps_queue(dev_maps, NULL, tci, j))
break;
}
active |= i < 0;
}
return active;
}
static void reset_xps_maps(struct net_device *dev,
struct xps_dev_maps *dev_maps,
enum xps_map_type type)
{
static_key_slow_dec_cpuslocked(&xps_needed);
if (type == XPS_RXQS)
static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
RCU_INIT_POINTER(dev->xps_maps[type], NULL);
kfree_rcu(dev_maps, rcu);
}
static void clean_xps_maps(struct net_device *dev, enum xps_map_type type,
u16 offset, u16 count)
{
struct xps_dev_maps *dev_maps;
bool active = false;
int i, j;
dev_maps = xmap_dereference(dev->xps_maps[type]);
if (!dev_maps)
return;
for (j = 0; j < dev_maps->nr_ids; j++)
active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count);
if (!active)
reset_xps_maps(dev, dev_maps, type);
if (type == XPS_CPUS) {
for (i = offset + (count - 1); count--; i--)
netdev_queue_numa_node_write(
netdev_get_tx_queue(dev, i), NUMA_NO_NODE);
}
}
static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
u16 count)
{
if (!static_key_false(&xps_needed))
return;
cpus_read_lock();
mutex_lock(&xps_map_mutex);
if (static_key_false(&xps_rxqs_needed))
clean_xps_maps(dev, XPS_RXQS, offset, count);
clean_xps_maps(dev, XPS_CPUS, offset, count);
mutex_unlock(&xps_map_mutex);
cpus_read_unlock();
}
static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
{
netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
}
static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
u16 index, bool is_rxqs_map)
{
struct xps_map *new_map;
int alloc_len = XPS_MIN_MAP_ALLOC;
int i, pos;
for (pos = 0; map && pos < map->len; pos++) {
if (map->queues[pos] != index)
continue;
return map;
}
/* Need to add tx-queue to this CPU's/rx-queue's existing map */
if (map) {
if (pos < map->alloc_len)
return map;
alloc_len = map->alloc_len * 2;
}
/* Need to allocate new map to store tx-queue on this CPU's/rx-queue's
* map
*/
if (is_rxqs_map)
new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL);
else
new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
cpu_to_node(attr_index));
if (!new_map)
return NULL;
for (i = 0; i < pos; i++)
new_map->queues[i] = map->queues[i];
new_map->alloc_len = alloc_len;
new_map->len = pos;
return new_map;
}
/* Copy xps maps at a given index */
static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps,
struct xps_dev_maps *new_dev_maps, int index,
int tc, bool skip_tc)
{
int i, tci = index * dev_maps->num_tc;
struct xps_map *map;
/* copy maps belonging to foreign traffic classes */
for (i = 0; i < dev_maps->num_tc; i++, tci++) {
if (i == tc && skip_tc)
continue;
/* fill in the new device map from the old device map */
map = xmap_dereference(dev_maps->attr_map[tci]);
RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
}
/* Must be called under cpus_read_lock */
int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
u16 index, enum xps_map_type type)
{
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL;
const unsigned long *online_mask = NULL;
bool active = false, copy = false;
int i, j, tci, numa_node_id = -2;
int maps_sz, num_tc = 1, tc = 0;
struct xps_map *map, *new_map;
unsigned int nr_ids;
WARN_ON_ONCE(index >= dev->num_tx_queues);
if (dev->num_tc) {
/* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
if (num_tc < 0)
return -EINVAL;
/* If queue belongs to subordinate dev use its map */
dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
tc = netdev_txq_to_tc(dev, index);
if (tc < 0)
return -EINVAL;
}
mutex_lock(&xps_map_mutex);
dev_maps = xmap_dereference(dev->xps_maps[type]);
if (type == XPS_RXQS) {
maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
nr_ids = dev->num_rx_queues;
} else {
maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
if (num_possible_cpus() > 1)
online_mask = cpumask_bits(cpu_online_mask);
nr_ids = nr_cpu_ids;
}
if (maps_sz < L1_CACHE_BYTES)
maps_sz = L1_CACHE_BYTES;
/* The old dev_maps could be larger or smaller than the one we're
* setting up now, as dev->num_tc or nr_ids could have been updated in
* between. We could try to be smart, but let's be safe instead and only
* copy foreign traffic classes if the two map sizes match.
*/
if (dev_maps &&
dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids)
copy = true;
/* allocate memory for queue storage */
for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids),
j < nr_ids;) {
if (!new_dev_maps) {
new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
if (!new_dev_maps) {
mutex_unlock(&xps_map_mutex);
return -ENOMEM;
}
new_dev_maps->nr_ids = nr_ids;
new_dev_maps->num_tc = num_tc;
}
tci = j * num_tc + tc;
map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL;
map = expand_xps_map(map, j, index, type == XPS_RXQS);
if (!map)
goto error;
RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
if (!new_dev_maps)
goto out_no_new_maps;
if (!dev_maps) {
/* Increment static keys at most once per type */
static_key_slow_inc_cpuslocked(&xps_needed);
if (type == XPS_RXQS)
static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
}
for (j = 0; j < nr_ids; j++) {
bool skip_tc = false;
tci = j * num_tc + tc;
if (netif_attr_test_mask(j, mask, nr_ids) &&
netif_attr_test_online(j, online_mask, nr_ids)) {
/* add tx-queue to CPU/rx-queue maps */
int pos = 0;
skip_tc = true;
map = xmap_dereference(new_dev_maps->attr_map[tci]);
while ((pos < map->len) && (map->queues[pos] != index))
pos++;
if (pos == map->len)
map->queues[map->len++] = index;
#ifdef CONFIG_NUMA
if (type == XPS_CPUS) {
if (numa_node_id == -2)
numa_node_id = cpu_to_node(j);
else if (numa_node_id != cpu_to_node(j))
numa_node_id = -1;
}
#endif
}
if (copy)
xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc,
skip_tc);
}
rcu_assign_pointer(dev->xps_maps[type], new_dev_maps);
/* Cleanup old maps */
if (!dev_maps)
goto out_no_old_maps;
for (j = 0; j < dev_maps->nr_ids; j++) {
for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) {
map = xmap_dereference(dev_maps->attr_map[tci]);
if (!map)
continue;
if (copy) {
new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
if (map == new_map)
continue;
}
RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
kfree_rcu(map, rcu);
}
}
old_dev_maps = dev_maps;
out_no_old_maps:
dev_maps = new_dev_maps;
active = true;
out_no_new_maps:
if (type == XPS_CPUS)
/* update Tx queue numa node */
netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
(numa_node_id >= 0) ?
numa_node_id : NUMA_NO_NODE);
if (!dev_maps)
goto out_no_maps;
/* removes tx-queue from unused CPUs/rx-queues */
for (j = 0; j < dev_maps->nr_ids; j++) {
tci = j * dev_maps->num_tc;
for (i = 0; i < dev_maps->num_tc; i++, tci++) {
if (i == tc &&
netif_attr_test_mask(j, mask, dev_maps->nr_ids) &&
netif_attr_test_online(j, online_mask, dev_maps->nr_ids))
continue;
active |= remove_xps_queue(dev_maps,
copy ? old_dev_maps : NULL,
tci, index);
}
}
if (old_dev_maps)
kfree_rcu(old_dev_maps, rcu);
/* free map if not active */
if (!active)
reset_xps_maps(dev, dev_maps, type);
out_no_maps:
mutex_unlock(&xps_map_mutex);
return 0;
error:
/* remove any maps that we added */
for (j = 0; j < nr_ids; j++) {
for (i = num_tc, tci = j * num_tc; i--; tci++) {
new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
map = copy ?
xmap_dereference(dev_maps->attr_map[tci]) :
NULL;
if (new_map && new_map != map)
kfree(new_map);
}
}
mutex_unlock(&xps_map_mutex);
kfree(new_dev_maps);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__netif_set_xps_queue);
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index)
{
int ret;
cpus_read_lock();
ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS);
cpus_read_unlock();
return ret;
}
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
static void netdev_unbind_all_sb_channels(struct net_device *dev)
{
struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
/* Unbind any subordinate channels */
while (txq-- != &dev->_tx[0]) {
if (txq->sb_dev)
netdev_unbind_sb_channel(dev, txq->sb_dev);
}
}
void netdev_reset_tc(struct net_device *dev)
{
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
netdev_unbind_all_sb_channels(dev);
/* Reset TC configuration of device */
dev->num_tc = 0;
memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
}
EXPORT_SYMBOL(netdev_reset_tc);
int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
{
if (tc >= dev->num_tc)
return -EINVAL;
#ifdef CONFIG_XPS
netif_reset_xps_queues(dev, offset, count);
#endif
dev->tc_to_txq[tc].count = count;
dev->tc_to_txq[tc].offset = offset;
return 0;
}
EXPORT_SYMBOL(netdev_set_tc_queue);
int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
{
if (num_tc > TC_MAX_QUEUE)
return -EINVAL;
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, 0);
#endif
netdev_unbind_all_sb_channels(dev);
dev->num_tc = num_tc;
return 0;
}
EXPORT_SYMBOL(netdev_set_num_tc);
void netdev_unbind_sb_channel(struct net_device *dev,
struct net_device *sb_dev)
{
struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(sb_dev, 0);
#endif
memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
while (txq-- != &dev->_tx[0]) {
if (txq->sb_dev == sb_dev)
txq->sb_dev = NULL;
}
}
EXPORT_SYMBOL(netdev_unbind_sb_channel);
int netdev_bind_sb_channel_queue(struct net_device *dev,
struct net_device *sb_dev,
u8 tc, u16 count, u16 offset)
{
/* Make certain the sb_dev and dev are already configured */
if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
return -EINVAL;
/* We cannot hand out queues we don't have */
if ((offset + count) > dev->real_num_tx_queues)
return -EINVAL;
/* Record the mapping */
sb_dev->tc_to_txq[tc].count = count;
sb_dev->tc_to_txq[tc].offset = offset;
/* Provide a way for Tx queue to find the tc_to_txq map or
* XPS map for itself.
*/
while (count--)
netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;
return 0;
}
EXPORT_SYMBOL(netdev_bind_sb_channel_queue);
int netdev_set_sb_channel(struct net_device *dev, u16 channel)
{
/* Do not use a multiqueue device to represent a subordinate channel */
if (netif_is_multiqueue(dev))
return -ENODEV;
/* We allow channels 1 - 32767 to be used for subordinate channels.
* Channel 0 is meant to be "native" mode and used only to represent
* the main root device. We allow writing 0 to reset the device back
* to normal mode after being used as a subordinate channel.
*/
if (channel > S16_MAX)
return -EINVAL;
dev->num_tc = -channel;
return 0;
}
EXPORT_SYMBOL(netdev_set_sb_channel);
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater than real_num_tx_queues stale skbs on the qdisc must be flushed.
*/
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
{
bool disabling;
int rc;
disabling = txq < dev->real_num_tx_queues;
if (txq < 1 || txq > dev->num_tx_queues)
return -EINVAL;
if (dev->reg_state == NETREG_REGISTERED ||
dev->reg_state == NETREG_UNREGISTERING) {
ASSERT_RTNL();
netdev_ops_assert_locked(dev);
rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues,
txq);
if (rc)
return rc;
if (dev->num_tc)
netif_setup_tc(dev, txq);
net_shaper_set_real_num_tx_queues(dev, txq);
dev_qdisc_change_real_num_tx(dev, txq);
dev->real_num_tx_queues = txq;
if (disabling) {
synchronize_net();
qdisc_reset_all_tx_gt(dev, txq);
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, txq);
#endif
}
} else {
dev->real_num_tx_queues = txq;
}
return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
/**
* netif_set_real_num_rx_queues - set actual number of RX queues used
* @dev: Network device
* @rxq: Actual number of RX queues
*
* This must be called either with the rtnl_lock held or before
* registration of the net device. Returns 0 on success, or a
* negative error code. If called before registration, it always
* succeeds.
*/
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
{
int rc;
if (rxq < 1 || rxq > dev->num_rx_queues)
return -EINVAL;
if (dev->reg_state == NETREG_REGISTERED) {
ASSERT_RTNL();
netdev_ops_assert_locked(dev);
rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
rxq);
if (rc)
return rc;
}
dev->real_num_rx_queues = rxq;
return 0;
}
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
/**
* netif_set_real_num_queues - set actual number of RX and TX queues used
* @dev: Network device
* @txq: Actual number of TX queues
* @rxq: Actual number of RX queues
*
* Set the real number of both TX and RX queues.
* Does nothing if the number of queues is already correct.
*/
int netif_set_real_num_queues(struct net_device *dev,
unsigned int txq, unsigned int rxq)
{
unsigned int old_rxq = dev->real_num_rx_queues;
int err;
if (txq < 1 || txq > dev->num_tx_queues ||
rxq < 1 || rxq > dev->num_rx_queues)
return -EINVAL;
/* Start from increases, so the error path only does decreases -
* decreases can't fail.
*/
if (rxq > dev->real_num_rx_queues) {
err = netif_set_real_num_rx_queues(dev, rxq);
if (err)
return err;
}
if (txq > dev->real_num_tx_queues) {
err = netif_set_real_num_tx_queues(dev, txq);
if (err)
goto undo_rx;
}
if (rxq < dev->real_num_rx_queues)
WARN_ON(netif_set_real_num_rx_queues(dev, rxq));
if (txq < dev->real_num_tx_queues)
WARN_ON(netif_set_real_num_tx_queues(dev, txq));
return 0;
undo_rx:
WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq));
return err;
}
EXPORT_SYMBOL(netif_set_real_num_queues);
/**
* netif_set_tso_max_size() - set the max size of TSO frames supported
* @dev: netdev to update
* @size: max skb->len of a TSO frame
*
* Set the limit on the size of TSO super-frames the device can handle.
* Unless explicitly set the stack will assume the value of
* %GSO_LEGACY_MAX_SIZE.
*/
void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
{
dev->tso_max_size = min(GSO_MAX_SIZE, size);
if (size < READ_ONCE(dev->gso_max_size))
netif_set_gso_max_size(dev, size);
if (size < READ_ONCE(dev->gso_ipv4_max_size))
netif_set_gso_ipv4_max_size(dev, size);
}
EXPORT_SYMBOL(netif_set_tso_max_size);
/**
* netif_set_tso_max_segs() - set the max number of segs supported for TSO
* @dev: netdev to update
* @segs: max number of TCP segments
*
* Set the limit on the number of TCP segments the device can generate from
* a single TSO super-frame.
* Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS.
*/
void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs)
{
dev->tso_max_segs = segs;
if (segs < READ_ONCE(dev->gso_max_segs))
netif_set_gso_max_segs(dev, segs);
}
EXPORT_SYMBOL(netif_set_tso_max_segs);
/**
* netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper
* @to: netdev to update
* @from: netdev from which to copy the limits
*/
void netif_inherit_tso_max(struct net_device *to, const struct net_device *from)
{
netif_set_tso_max_size(to, from->tso_max_size);
netif_set_tso_max_segs(to, from->tso_max_segs);
}
EXPORT_SYMBOL(netif_inherit_tso_max);
/**
* netif_get_num_default_rss_queues - default number of RSS queues
*
* Default value is the number of physical cores if there are only 1 or 2, or
* divided by 2 if there are more.
*/
int netif_get_num_default_rss_queues(void)
{
cpumask_var_t cpus;
int cpu, count = 0;
if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL)))
return 1;
cpumask_copy(cpus, cpu_online_mask);
for_each_cpu(cpu, cpus) {
++count;
cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
}
free_cpumask_var(cpus);
return count > 2 ? DIV_ROUND_UP(count, 2) : count;
}
EXPORT_SYMBOL(netif_get_num_default_rss_queues);
static void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
unsigned long flags;
local_irq_save(flags);
sd = this_cpu_ptr(&softnet_data);
q->next_sched = NULL;
*sd->output_queue_tailp = q;
sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
void __netif_schedule(struct Qdisc *q)
{
if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
__netif_reschedule(q);
}
EXPORT_SYMBOL(__netif_schedule);
struct dev_kfree_skb_cb {
enum skb_drop_reason reason;
};
static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
{
return (struct dev_kfree_skb_cb *)skb->cb;
}
void netif_schedule_queue(struct netdev_queue *txq)
{
rcu_read_lock();
if (!netif_xmit_stopped(txq)) {
struct Qdisc *q = rcu_dereference(txq->qdisc);
__netif_schedule(q);
}
rcu_read_unlock();
}
EXPORT_SYMBOL(netif_schedule_queue);
void netif_tx_wake_queue(struct netdev_queue *dev_queue)
{
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
struct Qdisc *q;
rcu_read_lock();
q = rcu_dereference(dev_queue->qdisc);
__netif_schedule(q);
rcu_read_unlock();
}
}
EXPORT_SYMBOL(netif_tx_wake_queue);
void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason)
{
unsigned long flags;
if (unlikely(!skb))
return;
if (likely(refcount_read(&skb->users) == 1)) {
smp_rmb();
refcount_set(&skb->users, 0);
} else if (likely(!refcount_dec_and_test(&skb->users))) {
return;
}
get_kfree_skb_cb(skb)->reason = reason;
local_irq_save(flags);
skb->next = __this_cpu_read(softnet_data.completion_queue);
__this_cpu_write(softnet_data.completion_queue, skb);
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(dev_kfree_skb_irq_reason);
void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason)
{
if (in_hardirq() || irqs_disabled())
dev_kfree_skb_irq_reason(skb, reason);
else
kfree_skb_reason(skb, reason);
}
EXPORT_SYMBOL(dev_kfree_skb_any_reason);
/**
* netif_device_detach - mark device as removed
* @dev: network device
*
* Mark device as removed from system and therefore no longer available.
*/
void netif_device_detach(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
netif_tx_stop_all_queues(dev);
}
}
EXPORT_SYMBOL(netif_device_detach);
/**
* netif_device_attach - mark device as attached
* @dev: network device
*
* Mark device as attached from system and restart if needed.
*/
void netif_device_attach(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
netif_tx_wake_all_queues(dev);
netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_device_attach);
/*
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
* to be used as a distribution range.
*/
static u16 skb_tx_hash(const struct net_device *dev,
const struct net_device *sb_dev,
struct sk_buff *skb)
{
u32 hash;
u16 qoffset = 0;
u16 qcount = dev->real_num_tx_queues;
if (dev->num_tc) {
u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
qoffset = sb_dev->tc_to_txq[tc].offset;
qcount = sb_dev->tc_to_txq[tc].count;
if (unlikely(!qcount)) {
net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n",
sb_dev->name, qoffset, tc);
qoffset = 0;
qcount = dev->real_num_tx_queues;
}
}
if (skb_rx_queue_recorded(skb)) {
DEBUG_NET_WARN_ON_ONCE(qcount == 0);
hash = skb_get_rx_queue(skb);
if (hash >= qoffset)
hash -= qoffset;
while (unlikely(hash >= qcount))
hash -= qcount;
return hash + qoffset;
}
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
void skb_warn_bad_offload(const struct sk_buff *skb)
{
static const netdev_features_t null_features;
struct net_device *dev = skb->dev;
const char *name = "";
if (!net_ratelimit())
return;
if (dev) {
if (dev->dev.parent)
name = dev_driver_string(dev->dev.parent);
else
name = netdev_name(dev);
}
skb_dump(KERN_WARNING, skb, false);
WARN(1, "%s: caps=(%pNF, %pNF)\n",
name, dev ? &dev->features : &null_features,
skb->sk ? &skb->sk->sk_route_caps : &null_features);
}
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
*/
int skb_checksum_help(struct sk_buff *skb)
{
__wsum csum;
int ret = 0, offset;
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
if (unlikely(skb_is_gso(skb))) {
skb_warn_bad_offload(skb);
return -EINVAL;
}
if (!skb_frags_readable(skb)) {
return -EFAULT;
}
/* Before computing a checksum, we should make sure no frag could
* be modified by an external entity : checksum could be wrong.
*/
if (skb_has_shared_frag(skb)) {
ret = __skb_linearize(skb);
if (ret)
goto out;
}
offset = skb_checksum_start_offset(skb);
ret = -EINVAL;
if (unlikely(offset >= skb_headlen(skb))) {
DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n",
offset, skb_headlen(skb));
goto out;
}
csum = skb_checksum(skb, offset, skb->len - offset, 0);
offset += skb->csum_offset;
if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) {
DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n",
offset + sizeof(__sum16), skb_headlen(skb));
goto out;
}
ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
if (ret)
goto out;
*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
return ret;
}
EXPORT_SYMBOL(skb_checksum_help);
int skb_crc32c_csum_help(struct sk_buff *skb)
{
__le32 crc32c_csum;
int ret = 0, offset, start;
if (skb->ip_summed != CHECKSUM_PARTIAL)
goto out;
if (unlikely(skb_is_gso(skb)))
goto out;
/* Before computing a checksum, we should make sure no frag could
* be modified by an external entity : checksum could be wrong.
*/
if (unlikely(skb_has_shared_frag(skb))) {
ret = __skb_linearize(skb);
if (ret)
goto out;
}
start = skb_checksum_start_offset(skb);
offset = start + offsetof(struct sctphdr, checksum);
if (WARN_ON_ONCE(offset >= skb_headlen(skb))) {
ret = -EINVAL;
goto out;
}
ret = skb_ensure_writable(skb, offset + sizeof(__le32));
if (ret)
goto out;
crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
skb->len - start, ~(__u32)0,
crc32c_csum_stub));
*(__le32 *)(skb->data + offset) = crc32c_csum;
skb_reset_csum_not_inet(skb);
out:
return ret;
}
EXPORT_SYMBOL(skb_crc32c_csum_help);
__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
/* Tunnel gso handlers can set protocol to ethernet. */
if (type == htons(ETH_P_TEB)) {
struct ethhdr *eth;
if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
return 0;
eth = (struct ethhdr *)skb->data;
type = eth->h_proto;
}
return vlan_get_protocol_and_depth(skb, type, depth);
}
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
{
netdev_err(dev, "hw csum failure\n");
skb_dump(KERN_ERR, skb, true);
dump_stack();
}
void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
{
DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb);
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif
/* XXX: check that highmem exists at all on the given machine. */
static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
if (!(dev->features & NETIF_F_HIGHDMA)) {
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
struct page *page = skb_frag_page(frag);
if (page && PageHighMem(page))
return 1;
}
}
#endif
return 0;
}
/* If MPLS offload request, verify we are testing hardware MPLS features
* instead of standard features for the netdev.
*/
#if IS_ENABLED(CONFIG_NET_MPLS_GSO)
static netdev_features_t net_mpls_features(struct sk_buff *skb,
netdev_features_t features,
__be16 type)
{
if (eth_p_mpls(type))
features &= skb->dev->mpls_features;
return features;
}
#else
static netdev_features_t net_mpls_features(struct sk_buff *skb,
netdev_features_t features,
__be16 type)
{
return features;
}
#endif
static netdev_features_t harmonize_features(struct sk_buff *skb,
netdev_features_t features)
{
__be16 type;
type = skb_network_protocol(skb, NULL);
features = net_mpls_features(skb, features, type);
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, type)) {
features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
if (illegal_highdma(skb->dev, skb))
features &= ~NETIF_F_SG;
return features;
}
netdev_features_t passthru_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
return features;
}
EXPORT_SYMBOL(passthru_features_check);
static netdev_features_t dflt_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
return vlan_features_check(skb, features);
}
static netdev_features_t gso_features_check(const struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
u16 gso_segs = skb_shinfo(skb)->gso_segs;
if (gso_segs > READ_ONCE(dev->gso_max_segs))
return features & ~NETIF_F_GSO_MASK;
if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb)))
return features & ~NETIF_F_GSO_MASK;
if (!skb_shinfo(skb)->gso_type) {
skb_warn_bad_offload(skb);
return features & ~NETIF_F_GSO_MASK;
}
/* Support for GSO partial features requires software
* intervention before we can actually process the packets
* so we need to strip support for any partial features now
* and we can pull them back in after we have partially
* segmented the frame.
*/
if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
features &= ~dev->gso_partial_features;
/* Make sure to clear the IPv4 ID mangling feature if the
* IPv4 header has the potential to be fragmented.
*/
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
struct iphdr *iph = skb->encapsulation ?
inner_ip_hdr(skb) : ip_hdr(skb);
if (!(iph->frag_off & htons(IP_DF)))
features &= ~NETIF_F_TSO_MANGLEID;
}
return features;
}
netdev_features_t netif_skb_features(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
netdev_features_t features = dev->features;
if (skb_is_gso(skb))
features = gso_features_check(skb, dev, features);
/* If encapsulation offload request, verify we are testing
* hardware encapsulation features instead of standard
* features for the netdev
*/
if (skb->encapsulation)
features &= dev->hw_enc_features;
if (skb_vlan_tagged(skb))
features = netdev_intersect_features(features,
dev->vlan_features |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (dev->netdev_ops->ndo_features_check)
features &= dev->netdev_ops->ndo_features_check(skb, dev,
features);
else
features &= dflt_features_check(skb, dev, features);
return harmonize_features(skb, features);
}
EXPORT_SYMBOL(netif_skb_features);
static int xmit_one(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, bool more)
{
unsigned int len;
int rc;
if (dev_nit_active_rcu(dev))
dev_queue_xmit_nit(skb, dev);
len = skb->len;
trace_net_dev_start_xmit(skb, dev);
rc = netdev_start_xmit(skb, dev, txq, more);
trace_net_dev_xmit(skb, rc, dev, len);
return rc;
}
struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev,
struct netdev_queue *txq, int *ret)
{
struct sk_buff *skb = first;
int rc = NETDEV_TX_OK;
while (skb) {
struct sk_buff *next = skb->next;
skb_mark_not_on_list(skb);
rc = xmit_one(skb, dev, txq, next != NULL);
if (unlikely(!dev_xmit_complete(rc))) {
skb->next = next;
goto out;
}
skb = next;
if (netif_tx_queue_stopped(txq) && skb) {
rc = NETDEV_TX_BUSY;
break;
}
}
out:
*ret = rc;
return skb;
}
static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tag_present(skb) &&
!vlan_hw_offload_capable(features, skb->vlan_proto))
skb = __vlan_hwaccel_push_inside(skb);
return skb;
}
int skb_csum_hwoffload_help(struct sk_buff *skb,
const netdev_features_t features)
{
if (unlikely(skb_csum_is_sctp(skb)))
return !!(features & NETIF_F_SCTP_CRC) ? 0 :
skb_crc32c_csum_help(skb);
if (features & NETIF_F_HW_CSUM)
return 0;
if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) {
if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) &&
skb_network_header_len(skb) != sizeof(struct ipv6hdr) &&
!ipv6_has_hopopt_jumbo(skb))
goto sw_checksum;
switch (skb->csum_offset) {
case offsetof(struct tcphdr, check):
case offsetof(struct udphdr, check):
return 0;
}
}
sw_checksum:
return skb_checksum_help(skb);
}
EXPORT_SYMBOL(skb_csum_hwoffload_help);
static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
{
netdev_features_t features;
if (!skb_frags_readable(skb))
goto out_kfree_skb;
features = netif_skb_features(skb);
skb = validate_xmit_vlan(skb, features);
if (unlikely(!skb))
goto out_null;
skb = sk_validate_xmit_skb(skb, dev);
if (unlikely(!skb))
goto out_null;
if (netif_needs_gso(skb, features)) {
struct sk_buff *segs;
segs = skb_gso_segment(skb, features);
if (IS_ERR(segs)) {
goto out_kfree_skb;
} else if (segs) {
consume_skb(skb);
skb = segs;
}
} else {
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not
* support checksumming for this protocol, complete
* checksumming here.
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (skb->encapsulation)
skb_set_inner_transport_header(skb,
skb_checksum_start_offset(skb));
else
skb_set_transport_header(skb,
skb_checksum_start_offset(skb));
if (skb_csum_hwoffload_help(skb, features))
goto out_kfree_skb;
}
}
skb = validate_xmit_xfrm(skb, features, again);
return skb;
out_kfree_skb:
kfree_skb(skb);
out_null:
dev_core_stats_tx_dropped_inc(dev);
return NULL;
}
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again)
{
struct sk_buff *next, *head = NULL, *tail;
for (; skb != NULL; skb = next) {
next = skb->next;
skb_mark_not_on_list(skb);
/* in case skb won't be segmented, point to itself */
skb->prev = skb;
skb = validate_xmit_skb(skb, dev, again);
if (!skb)
continue;
if (!head)
head = skb;
else
tail->next = skb;
/* If skb was segmented, skb->prev points to
* the last segment. If not, it still contains skb.
*/
tail = skb->prev;
}
return head;
}
EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
static void qdisc_pkt_len_init(struct sk_buff *skb)
{
const struct skb_shared_info *shinfo = skb_shinfo(skb);
qdisc_skb_cb(skb)->pkt_len = skb->len;
/* To get more precise estimation of bytes sent on wire,
* we add to pkt_len the headers size of all segments
*/
if (shinfo->gso_size && skb_transport_header_was_set(skb)) {
u16 gso_segs = shinfo->gso_segs;
unsigned int hdr_len;
/* mac layer + network layer */
hdr_len = skb_transport_offset(skb);
/* + transport layer */
if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
const struct tcphdr *th;
struct tcphdr _tcphdr;
th = skb_header_pointer(skb, hdr_len,
sizeof(_tcphdr), &_tcphdr);
if (likely(th))
hdr_len += __tcp_hdrlen(th);
} else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
struct udphdr _udphdr;
if (skb_header_pointer(skb, hdr_len,
sizeof(_udphdr), &_udphdr))
hdr_len += sizeof(struct udphdr);
}
if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) {
int payload = skb->len - hdr_len;
/* Malicious packet. */
if (payload <= 0)
return;
gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size);
}
qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
}
}
static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
struct sk_buff **to_free,
struct netdev_queue *txq)
{
int rc;
rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
if (rc == NET_XMIT_SUCCESS)
trace_qdisc_enqueue(q, txq, skb);
return rc;
}
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
{
spinlock_t *root_lock = qdisc_lock(q);
struct sk_buff *to_free = NULL;
bool contended;
int rc;
qdisc_calculate_pkt_len(skb, q);
tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP);
if (q->flags & TCQ_F_NOLOCK) {
if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
qdisc_run_begin(q)) {
/* Retest nolock_qdisc_is_empty() within the protection
* of q->seqlock to protect from racing with requeuing.
*/
if (unlikely(!nolock_qdisc_is_empty(q))) {
rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
__qdisc_run(q);
qdisc_run_end(q);
goto no_lock_out;
}
qdisc_bstats_cpu_update(q, skb);
if (sch_direct_xmit(skb, q, dev, txq, NULL, true) &&
!nolock_qdisc_is_empty(q))
__qdisc_run(q);
qdisc_run_end(q);
return NET_XMIT_SUCCESS;
}
rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
qdisc_run(q);
no_lock_out:
if (unlikely(to_free))
kfree_skb_list_reason(to_free,
tcf_get_drop_reason(to_free));
return rc;
}
if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) {
kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP);
return NET_XMIT_DROP;
}
/*
* Heuristic to force contended enqueues to serialize on a
* separate lock before trying to get qdisc main lock.
* This permits qdisc->running owner to get the lock more
* often and dequeue packets faster.
* On PREEMPT_RT it is possible to preempt the qdisc owner during xmit
* and then other tasks will only enqueue packets. The packets will be
* sent after the qdisc owner is scheduled again. To prevent this
* scenario the task always serialize on the lock.
*/
contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT);
if (unlikely(contended))
spin_lock(&q->busylock);
spin_lock(root_lock);
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
__qdisc_drop(skb, &to_free);
rc = NET_XMIT_DROP;
} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
qdisc_run_begin(q)) {
/*
* This is a work-conserving queue; there are no old skbs
* waiting to be sent out; and the qdisc is not running -
* xmit the skb directly.
*/
qdisc_bstats_update(q, skb);
if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
}
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
WRITE_ONCE(q->owner, smp_processor_id());
rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
WRITE_ONCE(q->owner, -1);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
qdisc_run_end(q);
}
}
spin_unlock(root_lock);
if (unlikely(to_free))
kfree_skb_list_reason(to_free,
tcf_get_drop_reason(to_free));
if (unlikely(contended))
spin_unlock(&q->busylock);
return rc;
}
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
static void skb_update_prio(struct sk_buff *skb)
{
const struct netprio_map *map;
const struct sock *sk;
unsigned int prioidx;
if (skb->priority)
return;
map = rcu_dereference_bh(skb->dev->priomap);
if (!map)
return;
sk = skb_to_full_sk(skb);
if (!sk)
return;
prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data);
if (prioidx < map->priomap_len)
skb->priority = map->priomap[prioidx];
}
#else
#define skb_update_prio(skb)
#endif
/**
* dev_loopback_xmit - loop back @skb
* @net: network namespace this loopback is happening in
* @sk: sk needed to be a netfilter okfn
* @skb: buffer to transmit
*/
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
skb->pkt_type = PACKET_LOOPBACK;
if (skb->ip_summed == CHECKSUM_NONE)
skb->ip_summed = CHECKSUM_UNNECESSARY;
DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb));
skb_dst_force(skb);
netif_rx(skb);
return 0;
}
EXPORT_SYMBOL(dev_loopback_xmit);
#ifdef CONFIG_NET_EGRESS
static struct netdev_queue *
netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
{
int qm = skb_get_queue_mapping(skb);
return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
}
#ifndef CONFIG_PREEMPT_RT
static bool netdev_xmit_txqueue_skipped(void)
{
return __this_cpu_read(softnet_data.xmit.skip_txqueue);
}
void netdev_xmit_skip_txqueue(bool skip)
{
__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
}
EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
#else
static bool netdev_xmit_txqueue_skipped(void)
{
return current->net_xmit.skip_txqueue;
}
void netdev_xmit_skip_txqueue(bool skip)
{
current->net_xmit.skip_txqueue = skip;
}
EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
#endif
#endif /* CONFIG_NET_EGRESS */
#ifdef CONFIG_NET_XGRESS
static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
enum skb_drop_reason *drop_reason)
{
int ret = TC_ACT_UNSPEC;
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq);
struct tcf_result res;
if (!miniq)
return ret;
/* Global bypass */
if (!static_branch_likely(&tcf_sw_enabled_key))
return ret;
/* Block-wise bypass */
if (tcf_block_bypass_sw(miniq->block))
return ret;
tc_skb_cb(skb)->mru = 0;
tc_skb_cb(skb)->post_ct = false;
tcf_set_drop_reason(skb, *drop_reason);
mini_qdisc_bstats_cpu_update(miniq, skb);
ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
/* Only tcf related quirks below. */
switch (ret) {
case TC_ACT_SHOT:
*drop_reason = tcf_get_drop_reason(skb);
mini_qdisc_qstats_cpu_drop(miniq);
break;
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(res.classid);
break;
}
#endif /* CONFIG_NET_CLS_ACT */
return ret;
}
static DEFINE_STATIC_KEY_FALSE(tcx_needed_key);
void tcx_inc(void)
{
static_branch_inc(&tcx_needed_key);
}
void tcx_dec(void)
{
static_branch_dec(&tcx_needed_key);
}
static __always_inline enum tcx_action_base
tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb,
const bool needs_mac)
{
const struct bpf_mprog_fp *fp;
const struct bpf_prog *prog;
int ret = TCX_NEXT;
if (needs_mac)
__skb_push(skb, skb->mac_len);
bpf_mprog_foreach_prog(entry, fp, prog) {
bpf_compute_data_pointers(skb);
ret = bpf_prog_run(prog, skb); if (ret != TCX_NEXT)
break;
}
if (needs_mac)
__skb_pull(skb, skb->mac_len); return tcx_action_code(skb, ret);
}
static __always_inline struct sk_buff *
sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev, bool *another)
{
struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress);
enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS;
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
int sch_ret;
if (!entry)
return skb;
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
qdisc_skb_cb(skb)->pkt_len = skb->len;
tcx_set_ingress(skb, true);
if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, true);
if (sch_ret != TC_ACT_UNSPEC)
goto ingress_verdict;
}
sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason);
ingress_verdict:
switch (sch_ret) {
case TC_ACT_REDIRECT:
/* skb_mac_header check was done by BPF, so we can safely
* push the L2 header back before redirecting to another
* netdev.
*/
__skb_push(skb, skb->mac_len);
if (skb_do_redirect(skb) == -EAGAIN) {
__skb_pull(skb, skb->mac_len);
*another = true;
break;
}
*ret = NET_RX_SUCCESS;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
case TC_ACT_SHOT:
kfree_skb_reason(skb, drop_reason);
*ret = NET_RX_DROP;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
/* used by tc_run */
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
case TC_ACT_TRAP:
consume_skb(skb);
fallthrough;
case TC_ACT_CONSUMED:
*ret = NET_RX_SUCCESS;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
}
bpf_net_ctx_clear(bpf_net_ctx);
return skb;
}
static __always_inline struct sk_buff *
sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
{
struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress);
enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS;
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
int sch_ret;
if (!entry)
return skb;
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
/* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was
* already set by the caller.
*/
if (static_branch_unlikely(&tcx_needed_key)) {
sch_ret = tcx_run(entry, skb, false);
if (sch_ret != TC_ACT_UNSPEC)
goto egress_verdict;
}
sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason);
egress_verdict:
switch (sch_ret) {
case TC_ACT_REDIRECT:
/* No need to push/pop skb's mac_header here on egress! */
skb_do_redirect(skb);
*ret = NET_XMIT_SUCCESS;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
case TC_ACT_SHOT:
kfree_skb_reason(skb, drop_reason);
*ret = NET_XMIT_DROP;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
/* used by tc_run */
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
case TC_ACT_TRAP:
consume_skb(skb);
fallthrough;
case TC_ACT_CONSUMED:
*ret = NET_XMIT_SUCCESS;
bpf_net_ctx_clear(bpf_net_ctx);
return NULL;
}
bpf_net_ctx_clear(bpf_net_ctx);
return skb;
}
#else
static __always_inline struct sk_buff *
sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev, bool *another)
{
return skb;
}
static __always_inline struct sk_buff *
sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
{
return skb;
}
#endif /* CONFIG_NET_XGRESS */
#ifdef CONFIG_XPS
static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
struct xps_dev_maps *dev_maps, unsigned int tci)
{
int tc = netdev_get_prio_tc_map(dev, skb->priority);
struct xps_map *map;
int queue_index = -1;
if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids)
return queue_index;
tci *= dev_maps->num_tc;
tci += tc;
map = rcu_dereference(dev_maps->attr_map[tci]);
if (map) {
if (map->len == 1)
queue_index = map->queues[0];
else
queue_index = map->queues[reciprocal_scale(
skb_get_hash(skb), map->len)];
if (unlikely(queue_index >= dev->real_num_tx_queues))
queue_index = -1;
}
return queue_index;
}
#endif
static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev,
struct sk_buff *skb)
{
#ifdef CONFIG_XPS
struct xps_dev_maps *dev_maps;
struct sock *sk = skb->sk;
int queue_index = -1;
if (!static_key_false(&xps_needed))
return -1;
rcu_read_lock();
if (!static_key_false(&xps_rxqs_needed))
goto get_cpus_map;
dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]);
if (dev_maps) {
int tci = sk_rx_queue_get(sk);
if (tci >= 0)
queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
tci);
}
get_cpus_map:
if (queue_index < 0) {
dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]);
if (dev_maps) {
unsigned int tci = skb->sender_cpu - 1;
queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
tci);
}
}
rcu_read_unlock();
return queue_index;
#else
return -1;
#endif
}
u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
return 0;
}
EXPORT_SYMBOL(dev_pick_tx_zero);
u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
struct sock *sk = skb->sk;
int queue_index = sk_tx_queue_get(sk);
sb_dev = sb_dev ? : dev;
if (queue_index < 0 || skb->ooo_okay ||
queue_index >= dev->real_num_tx_queues) {
int new_index = get_xps_queue(dev, sb_dev, skb);
if (new_index < 0)
new_index = skb_tx_hash(dev, sb_dev, skb);
if (queue_index != new_index && sk &&
sk_fullsock(sk) &&
rcu_access_pointer(sk->sk_dst_cache))
sk_tx_queue_set(sk, new_index);
queue_index = new_index;
}
return queue_index;
}
EXPORT_SYMBOL(netdev_pick_tx);
struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev)
{
int queue_index = 0;
#ifdef CONFIG_XPS
u32 sender_cpu = skb->sender_cpu - 1;
if (sender_cpu >= (u32)NR_CPUS)
skb->sender_cpu = raw_smp_processor_id() + 1;
#endif
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
queue_index = ops->ndo_select_queue(dev, skb, sb_dev);
else
queue_index = netdev_pick_tx(dev, skb, sb_dev);
queue_index = netdev_cap_txqueue(dev, queue_index);
}
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
}
/**
* __dev_queue_xmit() - transmit a buffer
* @skb: buffer to transmit
* @sb_dev: suboordinate device used for L2 forwarding offload
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
* this function. The function can be called from an interrupt.
*
* When calling this method, interrupts MUST be enabled. This is because
* the BH enable code must have IRQs enabled so that it will not deadlock.
*
* Regardless of the return value, the skb is consumed, so it is currently
* difficult to retry a send to this method. (You can bump the ref count
* before sending to hold a reference for retry if you are careful.)
*
* Return:
* * 0 - buffer successfully transmitted
* * positive qdisc return code - NET_XMIT_DROP etc.
* * negative errno - other errors
*/
int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq = NULL;
struct Qdisc *q;
int rc = -ENOMEM;
bool again = false;
skb_reset_mac_header(skb);
skb_assert_len(skb);
if (unlikely(skb_shinfo(skb)->tx_flags &
(SKBTX_SCHED_TSTAMP | SKBTX_BPF)))
__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
rcu_read_lock_bh();
skb_update_prio(skb);
qdisc_pkt_len_init(skb);
tcx_set_ingress(skb, false);
#ifdef CONFIG_NET_EGRESS
if (static_branch_unlikely(&egress_needed_key)) {
if (nf_hook_egress_active()) {
skb = nf_hook_egress(skb, &rc, dev);
if (!skb)
goto out;
}
netdev_xmit_skip_txqueue(false);
nf_skip_egress(skb, true);
skb = sch_handle_egress(skb, &rc, dev);
if (!skb)
goto out;
nf_skip_egress(skb, false);
if (netdev_xmit_txqueue_skipped())
txq = netdev_tx_queue_mapping(dev, skb);
}
#endif
/* If device/qdisc don't need skb->dst, release it right now while
* its hot in this cpu cache.
*/
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(skb);
else
skb_dst_force(skb);
if (!txq)
txq = netdev_core_pick_tx(dev, skb, sb_dev);
q = rcu_dereference_bh(txq->qdisc);
trace_net_dev_queue(skb);
if (q->enqueue) {
rc = __dev_xmit_skb(skb, q, dev, txq);
goto out;
}
/* The device has no queue. Common case for software devices:
* loopback, all the sorts of tunnels...
* Really, it is unlikely that netif_tx_lock protection is necessary
* here. (f.e. loopback and IP tunnels are clean ignoring statistics
* counters.)
* However, it is possible, that they rely on protection
* made by us here.
* Check this and shot the lock. It is not prone from deadlocks.
*Either shot noqueue qdisc, it is even simpler 8)
*/
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
/* Other cpus might concurrently change txq->xmit_lock_owner
* to -1 or to their cpu id, but not to our id.
*/
if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
if (dev_xmit_recursion())
goto recursion_alert;
skb = validate_xmit_skb(skb, dev, &again);
if (!skb)
goto out;
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_stopped(txq)) {
dev_xmit_recursion_inc();
skb = dev_hard_start_xmit(skb, dev, txq, &rc);
dev_xmit_recursion_dec();
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
}
}
HARD_TX_UNLOCK(dev, txq);
net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
dev->name);
} else {
/* Recursion is detected! It is possible,
* unfortunately
*/
recursion_alert:
net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
dev->name);
}
}
rc = -ENETDOWN;
rcu_read_unlock_bh();
dev_core_stats_tx_dropped_inc(dev);
kfree_skb_list(skb);
return rc;
out:
rcu_read_unlock_bh();
return rc;
}
EXPORT_SYMBOL(__dev_queue_xmit);
int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
struct net_device *dev = skb->dev;
struct sk_buff *orig_skb = skb;
struct netdev_queue *txq;
int ret = NETDEV_TX_BUSY;
bool again = false;
if (unlikely(!netif_running(dev) ||
!netif_carrier_ok(dev)))
goto drop;
skb = validate_xmit_skb_list(skb, dev, &again);
if (skb != orig_skb)
goto drop;
skb_set_queue_mapping(skb, queue_id);
txq = skb_get_tx_queue(dev, skb);
local_bh_disable();
dev_xmit_recursion_inc();
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_drv_stopped(txq))
ret = netdev_start_xmit(skb, dev, txq, false);
HARD_TX_UNLOCK(dev, txq);
dev_xmit_recursion_dec();
local_bh_enable();
return ret;
drop:
dev_core_stats_tx_dropped_inc(dev);
kfree_skb_list(skb);
return NET_XMIT_DROP;
}
EXPORT_SYMBOL(__dev_direct_xmit);
/*************************************************************************
* Receiver routines
*************************************************************************/
static DEFINE_PER_CPU(struct task_struct *, backlog_napi);
int weight_p __read_mostly = 64; /* old backlog weight */
int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */
int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */
/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
struct napi_struct *napi)
{
struct task_struct *thread;
lockdep_assert_irqs_disabled();
if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
/* Paired with smp_mb__before_atomic() in
* napi_enable()/dev_set_threaded().
* Use READ_ONCE() to guarantee a complete
* read on napi->thread. Only call
* wake_up_process() when it's not NULL.
*/
thread = READ_ONCE(napi->thread);
if (thread) {
if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi))
goto use_local_napi;
set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
wake_up_process(thread);
return;
}
}
use_local_napi:
list_add_tail(&napi->poll_list, &sd->poll_list);
WRITE_ONCE(napi->list_owner, smp_processor_id());
/* If not called from net_rx_action()
* we have to raise NET_RX_SOFTIRQ.
*/
if (!sd->in_net_rx_action)
raise_softirq_irqoff(NET_RX_SOFTIRQ);
}
#ifdef CONFIG_RPS
struct static_key_false rps_needed __read_mostly;
EXPORT_SYMBOL(rps_needed);
struct static_key_false rfs_needed __read_mostly;
EXPORT_SYMBOL(rfs_needed);
static u32 rfs_slot(u32 hash, const struct rps_dev_flow_table *flow_table)
{
return hash_32(hash, flow_table->log);
}
static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
if (next_cpu < nr_cpu_ids) {
u32 head;
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
struct rps_dev_flow *old_rflow;
u16 rxq_index;
u32 flow_id;
int rc;
/* Should we steer this flow to a different hardware queue? */
if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap ||
!(dev->features & NETIF_F_NTUPLE))
goto out;
rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu);
if (rxq_index == skb_get_rx_queue(skb))
goto out;
rxqueue = dev->_rx + rxq_index;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (!flow_table)
goto out;
flow_id = rfs_slot(skb_get_hash(skb), flow_table);
rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
rxq_index, flow_id);
if (rc < 0)
goto out;
old_rflow = rflow;
rflow = &flow_table->flows[flow_id];
WRITE_ONCE(rflow->filter, rc);
if (old_rflow->filter == rc)
WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER);
out:
#endif
head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head);
rps_input_queue_tail_save(&rflow->last_qtail, head);
}
WRITE_ONCE(rflow->cpu, next_cpu);
return rflow;
}
/*
* get_rps_cpu is called from netif_receive_skb and returns the target
* CPU from the RPS map of the receiving queue for a given skb.
* rcu_read_lock must be held on entry.
*/
static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow **rflowp)
{
const struct rps_sock_flow_table *sock_flow_table;
struct netdev_rx_queue *rxqueue = dev->_rx;
struct rps_dev_flow_table *flow_table;
struct rps_map *map;
int cpu = -1;
u32 tcpu;
u32 hash;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
if (unlikely(index >= dev->real_num_rx_queues)) {
WARN_ONCE(dev->real_num_rx_queues > 1,
"%s received packet on queue %u, but number "
"of RX queues is %u\n",
dev->name, index, dev->real_num_rx_queues);
goto done;
}
rxqueue += index;
}
/* Avoid computing hash if RFS/RPS is not active for this rxqueue */
flow_table = rcu_dereference(rxqueue->rps_flow_table);
map = rcu_dereference(rxqueue->rps_map);
if (!flow_table && !map)
goto done;
skb_reset_network_header(skb);
hash = skb_get_hash(skb);
if (!hash)
goto done;
sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table);
if (flow_table && sock_flow_table) {
struct rps_dev_flow *rflow;
u32 next_cpu;
u32 ident;
/* First check into global flow table if there is a match.
* This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow().
*/
ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]);
if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask)
goto try_rps;
next_cpu = ident & net_hotdata.rps_cpu_mask;
/* OK, now we know there is a match,
* we can look at the local (per receive queue) flow table
*/
rflow = &flow_table->flows[rfs_slot(hash, flow_table)];
tcpu = rflow->cpu;
/*
* If the desired CPU (where last recvmsg was done) is
* different from current CPU (one in the rx-queue flow
* table entry), switch if one of the following holds:
* - Current CPU is unset (>= nr_cpu_ids).
* - Current CPU is offline.
* - The current CPU's queue tail has advanced beyond the
* last packet that was enqueued using this table entry.
* This guarantees that all previous packets for the flow
* have been dequeued, thus preserving in order delivery.
*/
if (unlikely(tcpu != next_cpu) &&
(tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) -
rflow->last_qtail)) >= 0)) {
tcpu = next_cpu;
rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
}
if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
*rflowp = rflow;
cpu = tcpu;
goto done;
}
}
try_rps:
if (map) {
tcpu = map->cpus[reciprocal_scale(hash, map->len)];
if (cpu_online(tcpu)) {
cpu = tcpu;
goto done;
}
}
done:
return cpu;
}
#ifdef CONFIG_RFS_ACCEL
/**
* rps_may_expire_flow - check whether an RFS hardware filter may be removed
* @dev: Device on which the filter was set
* @rxq_index: RX queue index
* @flow_id: Flow ID passed to ndo_rx_flow_steer()
* @filter_id: Filter ID returned by ndo_rx_flow_steer()
*
* Drivers that implement ndo_rx_flow_steer() should periodically call
* this function for each installed filter and remove the filters for
* which it returns %true.
*/
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
u32 flow_id, u16 filter_id)
{
struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index;
struct rps_dev_flow_table *flow_table;
struct rps_dev_flow *rflow;
bool expire = true;
unsigned int cpu;
rcu_read_lock();
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (flow_table && flow_id < (1UL << flow_table->log)) {
rflow = &flow_table->flows[flow_id];
cpu = READ_ONCE(rflow->cpu);
if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids &&
((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) -
READ_ONCE(rflow->last_qtail)) <
(int)(10 << flow_table->log)))
expire = false;
}
rcu_read_unlock();
return expire;
}
EXPORT_SYMBOL(rps_may_expire_flow);
#endif /* CONFIG_RFS_ACCEL */
/* Called from hardirq (IPI) context */
static void rps_trigger_softirq(void *data)
{
struct softnet_data *sd = data;
____napi_schedule(sd, &sd->backlog);
sd->received_rps++;
}
#endif /* CONFIG_RPS */
/* Called from hardirq (IPI) context */
static void trigger_rx_softirq(void *data)
{
struct softnet_data *sd = data;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
smp_store_release(&sd->defer_ipi_scheduled, 0);
}
/*
* After we queued a packet into sd->input_pkt_queue,
* we need to make sure this queue is serviced soon.
*
* - If this is another cpu queue, link it to our rps_ipi_list,
* and make sure we will process rps_ipi_list from net_rx_action().
*
* - If this is our own queue, NAPI schedule our backlog.
* Note that this also raises NET_RX_SOFTIRQ.
*/
static void napi_schedule_rps(struct softnet_data *sd)
{
struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
#ifdef CONFIG_RPS
if (sd != mysd) {
if (use_backlog_threads()) {
__napi_schedule_irqoff(&sd->backlog);
return;
}
sd->rps_ipi_next = mysd->rps_ipi_list;
mysd->rps_ipi_list = sd;
/* If not called from net_rx_action() or napi_threaded_poll()
* we have to raise NET_RX_SOFTIRQ.
*/
if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll)
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
return;
}
#endif /* CONFIG_RPS */
__napi_schedule_irqoff(&mysd->backlog);
}
void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu)
{
unsigned long flags;
if (use_backlog_threads()) {
backlog_lock_irq_save(sd, &flags);
if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state))
__napi_schedule_irqoff(&sd->backlog);
backlog_unlock_irq_restore(sd, &flags);
} else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) {
smp_call_function_single_async(cpu, &sd->defer_csd);
}
}
#ifdef CONFIG_NET_FLOW_LIMIT
int netdev_flow_limit_table_len __read_mostly = (1 << 12);
#endif
static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
{
#ifdef CONFIG_NET_FLOW_LIMIT
struct sd_flow_limit *fl;
struct softnet_data *sd;
unsigned int old_flow, new_flow;
if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1))
return false;
sd = this_cpu_ptr(&softnet_data);
rcu_read_lock();
fl = rcu_dereference(sd->flow_limit);
if (fl) {
new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
old_flow = fl->history[fl->history_head];
fl->history[fl->history_head] = new_flow;
fl->history_head++;
fl->history_head &= FLOW_LIMIT_HISTORY - 1;
if (likely(fl->buckets[old_flow]))
fl->buckets[old_flow]--;
if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
fl->count++;
rcu_read_unlock();
return true;
}
}
rcu_read_unlock();
#endif
return false;
}
/*
* enqueue_to_backlog is called to queue an skb to a per CPU backlog
* queue (may be a remote CPU queue).
*/
static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
unsigned int *qtail)
{
enum skb_drop_reason reason;
struct softnet_data *sd;
unsigned long flags;
unsigned int qlen;
int max_backlog;
u32 tail;
reason = SKB_DROP_REASON_DEV_READY;
if (!netif_running(skb->dev))
goto bad_dev;
reason = SKB_DROP_REASON_CPU_BACKLOG;
sd = &per_cpu(softnet_data, cpu);
qlen = skb_queue_len_lockless(&sd->input_pkt_queue);
max_backlog = READ_ONCE(net_hotdata.max_backlog);
if (unlikely(qlen > max_backlog))
goto cpu_backlog_drop;
backlog_lock_irq_save(sd, &flags);
qlen = skb_queue_len(&sd->input_pkt_queue);
if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) {
if (!qlen) {
/* Schedule NAPI for backlog device. We can use
* non atomic operation as we own the queue lock.
*/
if (!__test_and_set_bit(NAPI_STATE_SCHED,
&sd->backlog.state))
napi_schedule_rps(sd);
}
__skb_queue_tail(&sd->input_pkt_queue, skb);
tail = rps_input_queue_tail_incr(sd);
backlog_unlock_irq_restore(sd, &flags);
/* save the tail outside of the critical section */
rps_input_queue_tail_save(qtail, tail);
return NET_RX_SUCCESS;
}
backlog_unlock_irq_restore(sd, &flags);
cpu_backlog_drop:
atomic_inc(&sd->dropped);
bad_dev:
dev_core_stats_rx_dropped_inc(skb->dev);
kfree_skb_reason(skb, reason);
return NET_RX_DROP;
}
static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct netdev_rx_queue *rxqueue;
rxqueue = dev->_rx;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
if (unlikely(index >= dev->real_num_rx_queues)) {
WARN_ONCE(dev->real_num_rx_queues > 1,
"%s received packet on queue %u, but number "
"of RX queues is %u\n",
dev->name, index, dev->real_num_rx_queues);
return rxqueue; /* Return first rxqueue */
}
rxqueue += index;
}
return rxqueue;
}
u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
const struct bpf_prog *xdp_prog)
{
void *orig_data, *orig_data_end, *hard_start;
struct netdev_rx_queue *rxqueue;
bool orig_bcast, orig_host;
u32 mac_len, frame_sz;
__be16 orig_eth_type;
struct ethhdr *eth;
u32 metalen, act;
int off;
/* The XDP program wants to see the packet starting at the MAC
* header.
*/
mac_len = skb->data - skb_mac_header(skb);
hard_start = skb->data - skb_headroom(skb);
/* SKB "head" area always have tailroom for skb_shared_info */
frame_sz = (void *)skb_end_pointer(skb) - hard_start;
frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
rxqueue = netif_get_rxqueue(skb);
xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq);
xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len,
skb_headlen(skb) + mac_len, true);
if (skb_is_nonlinear(skb)) {
skb_shinfo(skb)->xdp_frags_size = skb->data_len;
xdp_buff_set_frags_flag(xdp);
} else {
xdp_buff_clear_frags_flag(xdp);
}
orig_data_end = xdp->data_end;
orig_data = xdp->data;
eth = (struct ethhdr *)xdp->data;
orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr);
orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest);
orig_eth_type = eth->h_proto;
act = bpf_prog_run_xdp(xdp_prog, xdp);
/* check if bpf_xdp_adjust_head was used */
off = xdp->data - orig_data;
if (off) {
if (off > 0)
__skb_pull(skb, off);
else if (off < 0)
__skb_push(skb, -off);
skb->mac_header += off;
skb_reset_network_header(skb);
}
/* check if bpf_xdp_adjust_tail was used */
off = xdp->data_end - orig_data_end;
if (off != 0) {
skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
skb->len += off; /* positive on grow, negative on shrink */
}
/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
* (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
*/
if (xdp_buff_has_frags(xdp))
skb->data_len = skb_shinfo(skb)->xdp_frags_size;
else
skb->data_len = 0;
/* check if XDP changed eth hdr such SKB needs update */
eth = (struct ethhdr *)xdp->data;
if ((orig_eth_type != eth->h_proto) ||
(orig_host != ether_addr_equal_64bits(eth->h_dest,
skb->dev->dev_addr)) ||
(orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) {
__skb_push(skb, ETH_HLEN);
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, skb->dev);
}
/* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull
* before calling us again on redirect path. We do not call do_redirect
* as we leave that up to the caller.
*
* Caller is responsible for managing lifetime of skb (i.e. calling
* kfree_skb in response to actions it cannot handle/XDP_DROP).
*/
switch (act) {
case XDP_REDIRECT:
case XDP_TX:
__skb_push(skb, mac_len);
break;
case XDP_PASS:
metalen = xdp->data - xdp->data_meta;
if (metalen)
skb_metadata_set(skb, metalen);
break;
}
return act;
}
static int
netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog)
{
struct sk_buff *skb = *pskb;
int err, hroom, troom;
if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog))
return 0;
/* In case we have to go down the path and also linearize,
* then lets do the pskb_expand_head() work just once here.
*/
hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
troom = skb->tail + skb->data_len - skb->end;
err = pskb_expand_head(skb,
hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
troom > 0 ? troom + 128 : 0, GFP_ATOMIC);
if (err)
return err;
return skb_linearize(skb);
}
static u32 netif_receive_generic_xdp(struct sk_buff **pskb,
struct xdp_buff *xdp,
const struct bpf_prog *xdp_prog)
{
struct sk_buff *skb = *pskb;
u32 mac_len, act = XDP_DROP;
/* Reinjected packets coming from act_mirred or similar should
* not get XDP generic processing.
*/
if (skb_is_redirected(skb))
return XDP_PASS;
/* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM
* bytes. This is the guarantee that also native XDP provides,
* thus we need to do it here as well.
*/
mac_len = skb->data - skb_mac_header(skb);
__skb_push(skb, mac_len);
if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
skb_headroom(skb) < XDP_PACKET_HEADROOM) {
if (netif_skb_check_for_xdp(pskb, xdp_prog))
goto do_drop;
}
__skb_pull(*pskb, mac_len);
act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog);
switch (act) {
case XDP_REDIRECT:
case XDP_TX:
case XDP_PASS:
break;
default:
bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception((*pskb)->dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
do_drop:
kfree_skb(*pskb);
break;
}
return act;
}
/* When doing generic XDP we have to bypass the qdisc layer and the
* network taps in order to match in-driver-XDP behavior. This also means
* that XDP packets are able to starve other packets going through a qdisc,
* and DDOS attacks will be more effective. In-driver-XDP use dedicated TX
* queues, so they do not have this starvation issue.
*/
void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
bool free_skb = true;
int cpu, rc;
txq = netdev_core_pick_tx(dev, skb, NULL);
cpu = smp_processor_id();
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_frozen_or_drv_stopped(txq)) {
rc = netdev_start_xmit(skb, dev, txq, 0);
if (dev_xmit_complete(rc))
free_skb = false;
}
HARD_TX_UNLOCK(dev, txq);
if (free_skb) {
trace_xdp_exception(dev, xdp_prog, XDP_TX);
dev_core_stats_tx_dropped_inc(dev);
kfree_skb(skb);
}
}
static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb)
{
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
if (xdp_prog) {
struct xdp_buff xdp;
u32 act;
int err;
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog);
if (act != XDP_PASS) {
switch (act) {
case XDP_REDIRECT:
err = xdp_do_generic_redirect((*pskb)->dev, *pskb,
&xdp, xdp_prog);
if (err)
goto out_redir;
break;
case XDP_TX:
generic_xdp_tx(*pskb, xdp_prog);
break;
}
bpf_net_ctx_clear(bpf_net_ctx);
return XDP_DROP;
}
bpf_net_ctx_clear(bpf_net_ctx);
}
return XDP_PASS;
out_redir:
bpf_net_ctx_clear(bpf_net_ctx);
kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP);
return XDP_DROP;
}
EXPORT_SYMBOL_GPL(do_xdp_generic);
static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb);
trace_netif_rx(skb);
#ifdef CONFIG_RPS
if (static_branch_unlikely(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
rcu_read_lock();
cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu < 0)
cpu = smp_processor_id();
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
} else
#endif
{
unsigned int qtail;
ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail);
}
return ret;
}
/**
* __netif_rx - Slightly optimized version of netif_rx
* @skb: buffer to post
*
* This behaves as netif_rx except that it does not disable bottom halves.
* As a result this function may only be invoked from the interrupt context
* (either hard or soft interrupt).
*/
int __netif_rx(struct sk_buff *skb)
{
int ret;
lockdep_assert_once(hardirq_count() | softirq_count());
trace_netif_rx_entry(skb);
ret = netif_rx_internal(skb);
trace_netif_rx_exit(ret);
return ret;
}
EXPORT_SYMBOL(__netif_rx);
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
*
* This function receives a packet from a device driver and queues it for
* the upper (protocol) levels to process via the backlog NAPI device. It
* always succeeds. The buffer may be dropped during processing for
* congestion control or by the protocol layers.
* The network buffer is passed via the backlog NAPI device. Modern NIC
* driver should use NAPI and GRO.
* This function can used from interrupt and from process context. The
* caller from process context must not disable interrupts before invoking
* this function.
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_DROP (packet was dropped)
*
*/
int netif_rx(struct sk_buff *skb)
{
bool need_bh_off = !(hardirq_count() | softirq_count());
int ret;
if (need_bh_off)
local_bh_disable();
trace_netif_rx_entry(skb);
ret = netif_rx_internal(skb);
trace_netif_rx_exit(ret);
if (need_bh_off)
local_bh_enable();
return ret;
}
EXPORT_SYMBOL(netif_rx);
static __latent_entropy void net_tx_action(void)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
if (sd->completion_queue) {
struct sk_buff *clist;
local_irq_disable();
clist = sd->completion_queue;
sd->completion_queue = NULL;
local_irq_enable();
while (clist) {
struct sk_buff *skb = clist;
clist = clist->next;
WARN_ON(refcount_read(&skb->users));
if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED))
trace_consume_skb(skb, net_tx_action);
else
trace_kfree_skb(skb, net_tx_action,
get_kfree_skb_cb(skb)->reason, NULL);
if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
__kfree_skb(skb);
else
__napi_kfree_skb(skb,
get_kfree_skb_cb(skb)->reason);
}
}
if (sd->output_queue) {
struct Qdisc *head;
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
rcu_read_lock();
while (head) {
struct Qdisc *q = head;
spinlock_t *root_lock = NULL;
head = head->next_sched;
/* We need to make sure head->next_sched is read
* before clearing __QDISC_STATE_SCHED
*/
smp_mb__before_atomic();
if (!(q->flags & TCQ_F_NOLOCK)) {
root_lock = qdisc_lock(q);
spin_lock(root_lock);
} else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
&q->state))) {
/* There is a synchronize_net() between
* STATE_DEACTIVATED flag being set and
* qdisc_reset()/some_qdisc_is_busy() in
* dev_deactivate(), so we can safely bail out
* early here to avoid data race between
* qdisc_deactivate() and some_qdisc_is_busy()
* for lockless qdisc.
*/
clear_bit(__QDISC_STATE_SCHED, &q->state);
continue;
}
clear_bit(__QDISC_STATE_SCHED, &q->state);
qdisc_run(q);
if (root_lock)
spin_unlock(root_lock);
}
rcu_read_unlock();
}
xfrm_dev_backlog(sd);
}
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE)
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
/**
* netdev_is_rx_handler_busy - check if receive handler is registered
* @dev: device to check
*
* Check if a receive handler is already registered for a given device.
* Return true if there one.
*
* The caller must hold the rtnl_mutex.
*/
bool netdev_is_rx_handler_busy(struct net_device *dev)
{
ASSERT_RTNL();
return dev && rtnl_dereference(dev->rx_handler);
}
EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
* @rx_handler: receive handler to register
* @rx_handler_data: data pointer that is used by rx handler
*
* Register a receive handler for a device. This handler will then be
* called from __netif_receive_skb. A negative errno code is returned
* on a failure.
*
* The caller must hold the rtnl_mutex.
*
* For a general description of rx_handler, see enum rx_handler_result.
*/
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data)
{
if (netdev_is_rx_handler_busy(dev))
return -EBUSY;
if (dev->priv_flags & IFF_NO_RX_HANDLER)
return -EINVAL;
/* Note: rx_handler_data must be set before rx_handler */
rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
rcu_assign_pointer(dev->rx_handler, rx_handler);
return 0;
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
/**
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
* Unregister a receive handler from a device.
*
* The caller must hold the rtnl_mutex.
*/
void netdev_rx_handler_unregister(struct net_device *dev)
{
ASSERT_RTNL();
RCU_INIT_POINTER(dev->rx_handler, NULL);
/* a reader seeing a non NULL rx_handler in a rcu_read_lock()
* section has a guarantee to see a non NULL rx_handler_data
* as well.
*/
synchronize_net();
RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
/*
* Limit the use of PFMEMALLOC reserves to those protocols that implement
* the special handling of PFMEMALLOC skbs.
*/
static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
{
switch (skb->protocol) {
case htons(ETH_P_ARP):
case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
return true;
default:
return false;
}
}
static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
int *ret, struct net_device *orig_dev)
{
if (nf_hook_ingress_active(skb)) {
int ingress_retval;
if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock();
return ingress_retval;
}
return 0;
}
static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
struct packet_type **ppt_prev)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
struct sk_buff *skb = *pskb;
struct net_device *orig_dev;
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb);
orig_dev = skb->dev;
skb_reset_network_header(skb);
#if !defined(CONFIG_DEBUG_NET)
/* We plan to no longer reset the transport header here.
* Give some time to fuzzers and dev build to catch bugs
* in network stacks.
*/
if (!skb_transport_header_was_set(skb))
skb_reset_transport_header(skb);
#endif
skb_reset_mac_len(skb);
pt_prev = NULL;
another_round:
skb->skb_iif = skb->dev->ifindex;
__this_cpu_inc(softnet_data.processed);
if (static_branch_unlikely(&generic_xdp_needed_key)) {
int ret2;
migrate_disable();
ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog),
&skb);
migrate_enable();
if (ret2 != XDP_PASS) {
ret = NET_RX_DROP;
goto out;
}
}
if (eth_type_vlan(skb->protocol)) {
skb = skb_vlan_untag(skb);
if (unlikely(!skb))
goto out;
}
if (skb_skip_tc_classify(skb))
goto skip_classify;
if (pfmemalloc)
goto skip_taps;
list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all,
list) {
if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
skip_taps:
#ifdef CONFIG_NET_INGRESS
if (static_branch_unlikely(&ingress_needed_key)) {
bool another = false;
nf_skip_egress(skb, true);
skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
&another);
if (another)
goto another_round;
if (!skb)
goto out;
nf_skip_egress(skb, false);
if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
goto out;
}
#endif
skb_reset_redirect(skb);
skip_classify:
if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL;
}
if (vlan_do_receive(&skb))
goto another_round;
else if (unlikely(!skb))
goto out;
}
rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL;
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
ret = NET_RX_SUCCESS;
goto out;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
deliver_exact = true;
break;
case RX_HANDLER_PASS:
break;
default:
BUG();
}
}
if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) {
check_vlan_id:
if (skb_vlan_tag_get_id(skb)) {
/* Vlan id is non 0 and vlan_do_receive() above couldn't
* find vlan device.
*/
skb->pkt_type = PACKET_OTHERHOST;
} else if (eth_type_vlan(skb->protocol)) {
/* Outer header is 802.1P with vlan 0, inner header is
* 802.1Q or 802.1AD and vlan_do_receive() above could
* not find vlan dev for vlan id 0.
*/
__vlan_hwaccel_clear_tag(skb);
skb = skb_vlan_untag(skb);
if (unlikely(!skb))
goto out;
if (vlan_do_receive(&skb))
/* After stripping off 802.1P header with vlan 0
* vlan dev is found for inner header.
*/
goto another_round;
else if (unlikely(!skb))
goto out;
else
/* We have stripped outer 802.1P vlan 0 header.
* But could not find vlan dev.
* check again for vlan id to set OTHERHOST.
*/
goto check_vlan_id;
}
/* Note: we might in the future use prio bits
* and set skb->priority like in vlan_do_receive()
* For the time being, just ignore Priority Code Point
*/
__vlan_hwaccel_clear_tag(skb);
}
type = skb->protocol;
/* deliver only exact match when indicated */
if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
&ptype_base[ntohs(type) &
PTYPE_HASH_MASK]);
/* orig_dev and skb->dev could belong to different netns;
* Even in such case we need to traverse only the list
* coming from skb->dev, as the ptype owner (packet socket)
* will use dev_net(skb->dev) to do namespace filtering.
*/
deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &dev_net_rcu(skb->dev)->ptype_specific);
}
deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
&orig_dev->ptype_specific);
if (unlikely(skb->dev != orig_dev)) {
deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
&skb->dev->ptype_specific);
}
if (pt_prev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
goto drop;
*ppt_prev = pt_prev;
} else {
drop:
if (!deliver_exact)
dev_core_stats_rx_dropped_inc(skb->dev);
else
dev_core_stats_rx_nohandler_inc(skb->dev);
kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
*/
ret = NET_RX_DROP;
}
out:
/* The invariant here is that if *ppt_prev is not NULL
* then skb should also be non-NULL.
*
* Apparently *ppt_prev assignment above holds this invariant due to
* skb dereferencing near it.
*/
*pskb = skb;
return ret;
}
static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
{
struct net_device *orig_dev = skb->dev;
struct packet_type *pt_prev = NULL;
int ret;
ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
skb->dev, pt_prev, orig_dev);
return ret;
}
/**
* netif_receive_skb_core - special purpose version of netif_receive_skb
* @skb: buffer to process
*
* More direct receive version of netif_receive_skb(). It should
* only be used by callers that have a need to skip RPS and Generic XDP.
* Caller must also take care of handling if ``(page_is_)pfmemalloc``.
*
* This function may only be called from softirq context and interrupts
* should be enabled.
*
* Return values (usually ignored):
* NET_RX_SUCCESS: no congestion
* NET_RX_DROP: packet was dropped
*/
int netif_receive_skb_core(struct sk_buff *skb)
{
int ret;
rcu_read_lock();
ret = __netif_receive_skb_one_core(skb, false);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(netif_receive_skb_core);
static inline void __netif_receive_skb_list_ptype(struct list_head *head,
struct packet_type *pt_prev,
struct net_device *orig_dev)
{
struct sk_buff *skb, *next;
if (!pt_prev)
return;
if (list_empty(head))
return;
if (pt_prev->list_func != NULL)
INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv,
ip_list_rcv, head, pt_prev, orig_dev);
else
list_for_each_entry_safe(skb, next, head, list) {
skb_list_del_init(skb);
pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
}
static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
{
/* Fast-path assumptions:
* - There is no RX handler.
* - Only one packet_type matches.
* If either of these fails, we will end up doing some per-packet
* processing in-line, then handling the 'last ptype' for the whole
* sublist. This can't cause out-of-order delivery to any single ptype,
* because the 'last ptype' must be constant across the sublist, and all
* other ptypes are handled per-packet.
*/
/* Current (common) ptype of sublist */
struct packet_type *pt_curr = NULL;
/* Current (common) orig_dev of sublist */
struct net_device *od_curr = NULL;
struct sk_buff *skb, *next;
LIST_HEAD(sublist);
list_for_each_entry_safe(skb, next, head, list) {
struct net_device *orig_dev = skb->dev;
struct packet_type *pt_prev = NULL;
skb_list_del_init(skb);
__netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (!pt_prev)
continue;
if (pt_curr != pt_prev || od_curr != orig_dev) {
/* dispatch old sublist */
__netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
/* start new sublist */
INIT_LIST_HEAD(&sublist);
pt_curr = pt_prev;
od_curr = orig_dev;
}
list_add_tail(&skb->list, &sublist);
}
/* dispatch final sublist */
__netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
}
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
if (sk_memalloc_socks() && skb_pfmemalloc(skb)) {
unsigned int noreclaim_flag;
/*
* PFMEMALLOC skbs are special, they should
* - be delivered to SOCK_MEMALLOC sockets only
* - stay away from userspace
* - have bounded memory usage
*
* Use PF_MEMALLOC as this saves us from propagating the allocation
* context down to all allocation sites.
*/
noreclaim_flag = memalloc_noreclaim_save();
ret = __netif_receive_skb_one_core(skb, true);
memalloc_noreclaim_restore(noreclaim_flag);
} else
ret = __netif_receive_skb_one_core(skb, false);
return ret;
}
static void __netif_receive_skb_list(struct list_head *head)
{
unsigned long noreclaim_flag = 0;
struct sk_buff *skb, *next;
bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */
list_for_each_entry_safe(skb, next, head, list) {
if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) {
struct list_head sublist;
/* Handle the previous sublist */
list_cut_before(&sublist, head, &skb->list);
if (!list_empty(&sublist))
__netif_receive_skb_list_core(&sublist, pfmemalloc);
pfmemalloc = !pfmemalloc;
/* See comments in __netif_receive_skb */
if (pfmemalloc)
noreclaim_flag = memalloc_noreclaim_save();
else
memalloc_noreclaim_restore(noreclaim_flag);
}
}
/* Handle the remaining sublist */
if (!list_empty(head))
__netif_receive_skb_list_core(head, pfmemalloc);
/* Restore pflags */
if (pfmemalloc)
memalloc_noreclaim_restore(noreclaim_flag);
}
static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
{
struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
struct bpf_prog *new = xdp->prog;
int ret = 0;
switch (xdp->command) {
case XDP_SETUP_PROG:
rcu_assign_pointer(dev->xdp_prog, new);
if (old)
bpf_prog_put(old);
if (old && !new) {
static_branch_dec(&generic_xdp_needed_key);
} else if (new && !old) {
static_branch_inc(&generic_xdp_needed_key);
netif_disable_lro(dev);
dev_disable_gro_hw(dev);
}
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
static int netif_receive_skb_internal(struct sk_buff *skb)
{
int ret;
net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
rcu_read_lock();
#ifdef CONFIG_RPS
if (static_branch_unlikely(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
return ret;
}
}
#endif
ret = __netif_receive_skb(skb);
rcu_read_unlock();
return ret;
}
void netif_receive_skb_list_internal(struct list_head *head)
{
struct sk_buff *skb, *next;
LIST_HEAD(sublist);
list_for_each_entry_safe(skb, next, head, list) {
net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue),
skb);
skb_list_del_init(skb);
if (!skb_defer_rx_timestamp(skb))
list_add_tail(&skb->list, &sublist);
}
list_splice_init(&sublist, head);
rcu_read_lock();
#ifdef CONFIG_RPS
if (static_branch_unlikely(&rps_needed)) {
list_for_each_entry_safe(skb, next, head, list) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
/* Will be handled, remove from list */
skb_list_del_init(skb);
enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
}
}
}
#endif
__netif_receive_skb_list(head);
rcu_read_unlock();
}
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
*
* netif_receive_skb() is the main receive data processing function.
* It always succeeds. The buffer may be dropped during processing
* for congestion control or by the protocol layers.
*
* This function may only be called from softirq context and interrupts
* should be enabled.
*
* Return values (usually ignored):
* NET_RX_SUCCESS: no congestion
* NET_RX_DROP: packet was dropped
*/
int netif_receive_skb(struct sk_buff *skb)
{
int ret;
trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret);
return ret;
}
EXPORT_SYMBOL(netif_receive_skb);
/**
* netif_receive_skb_list - process many receive buffers from network
* @head: list of skbs to process.
*
* Since return value of netif_receive_skb() is normally ignored, and
* wouldn't be meaningful for a list, this function returns void.
*
* This function may only be called from softirq context and interrupts
* should be enabled.
*/
void netif_receive_skb_list(struct list_head *head)
{
struct sk_buff *skb;
if (list_empty(head))
return;
if (trace_netif_receive_skb_list_entry_enabled()) {
list_for_each_entry(skb, head, list)
trace_netif_receive_skb_list_entry(skb);
}
netif_receive_skb_list_internal(head);
trace_netif_receive_skb_list_exit(0);
}
EXPORT_SYMBOL(netif_receive_skb_list);
/* Network device is going away, flush any packets still pending */
static void flush_backlog(struct work_struct *work)
{
struct sk_buff *skb, *tmp;
struct sk_buff_head list;
struct softnet_data *sd;
__skb_queue_head_init(&list);
local_bh_disable();
sd = this_cpu_ptr(&softnet_data);
backlog_lock_irq_disable(sd);
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->input_pkt_queue);
__skb_queue_tail(&list, skb);
rps_input_queue_head_incr(sd);
}
}
backlog_unlock_irq_enable(sd);
local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->process_queue);
__skb_queue_tail(&list, skb);
rps_input_queue_head_incr(sd);
}
}
local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
local_bh_enable();
__skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY);
}
static bool flush_required(int cpu)
{
#if IS_ENABLED(CONFIG_RPS)
struct softnet_data *sd = &per_cpu(softnet_data, cpu);
bool do_flush;
backlog_lock_irq_disable(sd);
/* as insertion into process_queue happens with the rps lock held,
* process_queue access may race only with dequeue
*/
do_flush = !skb_queue_empty(&sd->input_pkt_queue) ||
!skb_queue_empty_lockless(&sd->process_queue);
backlog_unlock_irq_enable(sd);
return do_flush;
#endif
/* without RPS we can't safely check input_pkt_queue: during a
* concurrent remote skb_queue_splice() we can detect as empty both
* input_pkt_queue and process_queue even if the latter could end-up
* containing a lot of packets.
*/
return true;
}
struct flush_backlogs {
cpumask_t flush_cpus;
struct work_struct w[];
};
static struct flush_backlogs *flush_backlogs_alloc(void)
{
return kmalloc(struct_size_t(struct flush_backlogs, w, nr_cpu_ids),
GFP_KERNEL);
}
static struct flush_backlogs *flush_backlogs_fallback;
static DEFINE_MUTEX(flush_backlogs_mutex);
static void flush_all_backlogs(void)
{
struct flush_backlogs *ptr = flush_backlogs_alloc();
unsigned int cpu;
if (!ptr) {
mutex_lock(&flush_backlogs_mutex);
ptr = flush_backlogs_fallback;
}
cpumask_clear(&ptr->flush_cpus);
cpus_read_lock();
for_each_online_cpu(cpu) {
if (flush_required(cpu)) {
INIT_WORK(&ptr->w[cpu], flush_backlog);
queue_work_on(cpu, system_highpri_wq, &ptr->w[cpu]);
__cpumask_set_cpu(cpu, &ptr->flush_cpus);
}
}
/* we can have in flight packet[s] on the cpus we are not flushing,
* synchronize_net() in unregister_netdevice_many() will take care of
* them.
*/
for_each_cpu(cpu, &ptr->flush_cpus)
flush_work(&ptr->w[cpu]);
cpus_read_unlock();
if (ptr != flush_backlogs_fallback)
kfree(ptr);
else
mutex_unlock(&flush_backlogs_mutex);
}
static void net_rps_send_ipi(struct softnet_data *remsd)
{
#ifdef CONFIG_RPS
while (remsd) {
struct softnet_data *next = remsd->rps_ipi_next;
if (cpu_online(remsd->cpu))
smp_call_function_single_async(remsd->cpu, &remsd->csd);
remsd = next;
}
#endif
}
/*
* net_rps_action_and_irq_enable sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
*/
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
struct softnet_data *remsd = sd->rps_ipi_list;
if (!use_backlog_threads() && remsd) {
sd->rps_ipi_list = NULL;
local_irq_enable();
/* Send pending IPI's to kick RPS processing on remote cpus. */
net_rps_send_ipi(remsd);
} else
#endif
local_irq_enable();
}
static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
return !use_backlog_threads() && sd->rps_ipi_list;
#else
return false;
#endif
}
static int process_backlog(struct napi_struct *napi, int quota)
{
struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
bool again = true;
int work = 0;
/* Check if we have pending ipi, its better to send them now,
* not waiting net_rx_action() end.
*/
if (sd_has_rps_ipi_waiting(sd)) {
local_irq_disable();
net_rps_action_and_irq_enable(sd);
}
napi->weight = READ_ONCE(net_hotdata.dev_rx_weight);
while (again) {
struct sk_buff *skb;
local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
while ((skb = __skb_dequeue(&sd->process_queue))) {
local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
rcu_read_lock();
__netif_receive_skb(skb);
rcu_read_unlock();
if (++work >= quota) {
rps_input_queue_head_add(sd, work);
return work;
}
local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
}
local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
backlog_lock_irq_disable(sd);
if (skb_queue_empty(&sd->input_pkt_queue)) {
/*
* Inline a custom version of __napi_complete().
* only current cpu owns and manipulates this napi,
* and NAPI_STATE_SCHED is the only possible flag set
* on backlog.
* We can use a plain write instead of clear_bit(),
* and we dont need an smp_mb() memory barrier.
*/
napi->state &= NAPIF_STATE_THREADED;
again = false;
} else {
local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
skb_queue_splice_tail_init(&sd->input_pkt_queue,
&sd->process_queue);
local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
}
backlog_unlock_irq_enable(sd);
}
if (work)
rps_input_queue_head_add(sd, work);
return work;
}
/**
* __napi_schedule - schedule for receive
* @n: entry to schedule
*
* The entry's receive function will be scheduled to run.
* Consider using __napi_schedule_irqoff() if hard irqs are masked.
*/
void __napi_schedule(struct napi_struct *n)
{
unsigned long flags;
local_irq_save(flags);
____napi_schedule(this_cpu_ptr(&softnet_data), n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);
/**
* napi_schedule_prep - check if napi can be scheduled
* @n: napi context
*
* Test if NAPI routine is already running, and if not mark
* it as running. This is used as a condition variable to
* insure only one NAPI poll instance runs. We also make
* sure there is no pending NAPI disable.
*/
bool napi_schedule_prep(struct napi_struct *n)
{
unsigned long new, val = READ_ONCE(n->state);
do {
if (unlikely(val & NAPIF_STATE_DISABLE))
return false;
new = val | NAPIF_STATE_SCHED;
/* Sets STATE_MISSED bit if STATE_SCHED was already set
* This was suggested by Alexander Duyck, as compiler
* emits better code than :
* if (val & NAPIF_STATE_SCHED)
* new |= NAPIF_STATE_MISSED;
*/
new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED *
NAPIF_STATE_MISSED;
} while (!try_cmpxchg(&n->state, &val, new));
return !(val & NAPIF_STATE_SCHED);
}
EXPORT_SYMBOL(napi_schedule_prep);
/**
* __napi_schedule_irqoff - schedule for receive
* @n: entry to schedule
*
* Variant of __napi_schedule() assuming hard irqs are masked.
*
* On PREEMPT_RT enabled kernels this maps to __napi_schedule()
* because the interrupt disabled assumption might not be true
* due to force-threaded interrupts and spinlock substitution.
*/
void __napi_schedule_irqoff(struct napi_struct *n)
{
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
____napi_schedule(this_cpu_ptr(&softnet_data), n);
else
__napi_schedule(n);
}
EXPORT_SYMBOL(__napi_schedule_irqoff);
bool napi_complete_done(struct napi_struct *n, int work_done)
{
unsigned long flags, val, new, timeout = 0;
bool ret = true;
/*
* 1) Don't let napi dequeue from the cpu poll list
* just in case its running on a different cpu.
* 2) If we are busy polling, do nothing here, we have
* the guarantee we will be called later.
*/
if (unlikely(n->state & (NAPIF_STATE_NPSVC |
NAPIF_STATE_IN_BUSY_POLL)))
return false;
if (work_done) {
if (n->gro.bitmask)
timeout = napi_get_gro_flush_timeout(n);
n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
}
if (n->defer_hard_irqs_count > 0) {
n->defer_hard_irqs_count--;
timeout = napi_get_gro_flush_timeout(n);
if (timeout)
ret = false;
}
/*
* When the NAPI instance uses a timeout and keeps postponing
* it, we need to bound somehow the time packets are kept in
* the GRO layer.
*/
gro_flush(&n->gro, !!timeout);
gro_normal_list(&n->gro);
if (unlikely(!list_empty(&n->poll_list))) {
/* If n->poll_list is not empty, we need to mask irqs */
local_irq_save(flags);
list_del_init(&n->poll_list);
local_irq_restore(flags);
}
WRITE_ONCE(n->list_owner, -1);
val = READ_ONCE(n->state);
do {
WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
NAPIF_STATE_SCHED_THREADED |
NAPIF_STATE_PREFER_BUSY_POLL);
/* If STATE_MISSED was set, leave STATE_SCHED set,
* because we will call napi->poll() one more time.
* This C code was suggested by Alexander Duyck to help gcc.
*/
new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
NAPIF_STATE_SCHED;
} while (!try_cmpxchg(&n->state, &val, new));
if (unlikely(val & NAPIF_STATE_MISSED)) {
__napi_schedule(n);
return false;
}
if (timeout)
hrtimer_start(&n->timer, ns_to_ktime(timeout),
HRTIMER_MODE_REL_PINNED);
return ret;
}
EXPORT_SYMBOL(napi_complete_done);
static void skb_defer_free_flush(struct softnet_data *sd)
{
struct sk_buff *skb, *next;
/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
if (!READ_ONCE(sd->defer_list))
return;
spin_lock(&sd->defer_lock);
skb = sd->defer_list;
sd->defer_list = NULL;
sd->defer_count = 0;
spin_unlock(&sd->defer_lock);
while (skb != NULL) {
next = skb->next;
napi_consume_skb(skb, 1);
skb = next;
}
}
#if defined(CONFIG_NET_RX_BUSY_POLL)
static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
{
if (!skip_schedule) {
gro_normal_list(&napi->gro);
__napi_schedule(napi);
return;
}
/* Flush too old packets. If HZ < 1000, flush all packets */
gro_flush(&napi->gro, HZ >= 1000);
gro_normal_list(&napi->gro);
clear_bit(NAPI_STATE_SCHED, &napi->state);
}
enum {
NAPI_F_PREFER_BUSY_POLL = 1,
NAPI_F_END_ON_RESCHED = 2,
};
static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
unsigned flags, u16 budget)
{
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
bool skip_schedule = false;
unsigned long timeout;
int rc;
/* Busy polling means there is a high chance device driver hard irq
* could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was
* set in napi_schedule_prep().
* Since we are about to call napi->poll() once more, we can safely
* clear NAPI_STATE_MISSED.
*
* Note: x86 could use a single "lock and ..." instruction
* to perform these two clear_bit()
*/
clear_bit(NAPI_STATE_MISSED, &napi->state);
clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
local_bh_disable();
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
if (flags & NAPI_F_PREFER_BUSY_POLL) {
napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
timeout = napi_get_gro_flush_timeout(napi);
if (napi->defer_hard_irqs_count && timeout) {
hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
skip_schedule = true;
}
}
/* All we really want here is to re-enable device interrupts.
* Ideally, a new ndo_busy_poll_stop() could avoid another round.
*/
rc = napi->poll(napi, budget);
/* We can't gro_normal_list() here, because napi->poll() might have
* rearmed the napi (napi_complete_done()) in which case it could
* already be running on another CPU.
*/
trace_napi_poll(napi, rc, budget);
netpoll_poll_unlock(have_poll_lock);
if (rc == budget)
__busy_poll_stop(napi, skip_schedule);
bpf_net_ctx_clear(bpf_net_ctx);
local_bh_enable();
}
static void __napi_busy_loop(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
void *loop_end_arg, unsigned flags, u16 budget)
{
unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
void *have_poll_lock = NULL;
struct napi_struct *napi;
WARN_ON_ONCE(!rcu_read_lock_held());
restart:
napi_poll = NULL;
napi = napi_by_id(napi_id);
if (!napi)
return;
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_disable();
for (;;) {
int work = 0;
local_bh_disable();
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
if (!napi_poll) {
unsigned long val = READ_ONCE(napi->state);
/* If multiple threads are competing for this napi,
* we avoid dirtying napi->state as much as we can.
*/
if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
NAPIF_STATE_IN_BUSY_POLL)) {
if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
if (cmpxchg(&napi->state, val,
val | NAPIF_STATE_IN_BUSY_POLL |
NAPIF_STATE_SCHED) != val) {
if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
have_poll_lock = netpoll_poll_lock(napi);
napi_poll = napi->poll;
}
work = napi_poll(napi, budget);
trace_napi_poll(napi, work, budget);
gro_normal_list(&napi->gro);
count:
if (work > 0)
__NET_ADD_STATS(dev_net(napi->dev),
LINUX_MIB_BUSYPOLLRXPACKETS, work);
skb_defer_free_flush(this_cpu_ptr(&softnet_data));
bpf_net_ctx_clear(bpf_net_ctx);
local_bh_enable();
if (!loop_end || loop_end(loop_end_arg, start_time))
break;
if (unlikely(need_resched())) {
if (flags & NAPI_F_END_ON_RESCHED)
break;
if (napi_poll)
busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
rcu_read_unlock();
cond_resched();
rcu_read_lock();
if (loop_end(loop_end_arg, start_time))
return;
goto restart;
}
cpu_relax();
}
if (napi_poll)
busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
}
void napi_busy_loop_rcu(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
void *loop_end_arg, bool prefer_busy_poll, u16 budget)
{
unsigned flags = NAPI_F_END_ON_RESCHED;
if (prefer_busy_poll)
flags |= NAPI_F_PREFER_BUSY_POLL;
__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
}
void napi_busy_loop(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
void *loop_end_arg, bool prefer_busy_poll, u16 budget)
{
unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
rcu_read_lock();
__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
rcu_read_unlock();
}
EXPORT_SYMBOL(napi_busy_loop);
void napi_suspend_irqs(unsigned int napi_id)
{
struct napi_struct *napi;
rcu_read_lock();
napi = napi_by_id(napi_id);
if (napi) {
unsigned long timeout = napi_get_irq_suspend_timeout(napi);
if (timeout)
hrtimer_start(&napi->timer, ns_to_ktime(timeout),
HRTIMER_MODE_REL_PINNED);
}
rcu_read_unlock();
}
void napi_resume_irqs(unsigned int napi_id)
{
struct napi_struct *napi;
rcu_read_lock();
napi = napi_by_id(napi_id);
if (napi) {
/* If irq_suspend_timeout is set to 0 between the call to
* napi_suspend_irqs and now, the original value still
* determines the safety timeout as intended and napi_watchdog
* will resume irq processing.
*/
if (napi_get_irq_suspend_timeout(napi)) {
local_bh_disable();
napi_schedule(napi);
local_bh_enable();
}
}
rcu_read_unlock();
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
static void __napi_hash_add_with_id(struct napi_struct *napi,
unsigned int napi_id)
{
napi->gro.cached_napi_id = napi_id;
WRITE_ONCE(napi->napi_id, napi_id);
hlist_add_head_rcu(&napi->napi_hash_node,
&napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
}
static void napi_hash_add_with_id(struct napi_struct *napi,
unsigned int napi_id)
{
unsigned long flags;
spin_lock_irqsave(&napi_hash_lock, flags);
WARN_ON_ONCE(napi_by_id(napi_id));
__napi_hash_add_with_id(napi, napi_id);
spin_unlock_irqrestore(&napi_hash_lock, flags);
}
static void napi_hash_add(struct napi_struct *napi)
{
unsigned long flags;
if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state))
return;
spin_lock_irqsave(&napi_hash_lock, flags);
/* 0..NR_CPUS range is reserved for sender_cpu use */
do {
if (unlikely(!napi_id_valid(++napi_gen_id)))
napi_gen_id = MIN_NAPI_ID;
} while (napi_by_id(napi_gen_id));
__napi_hash_add_with_id(napi, napi_gen_id);
spin_unlock_irqrestore(&napi_hash_lock, flags);
}
/* Warning : caller is responsible to make sure rcu grace period
* is respected before freeing memory containing @napi
*/
static void napi_hash_del(struct napi_struct *napi)
{
unsigned long flags;
spin_lock_irqsave(&napi_hash_lock, flags);
hlist_del_init_rcu(&napi->napi_hash_node);
spin_unlock_irqrestore(&napi_hash_lock, flags);
}
static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
{
struct napi_struct *napi;
napi = container_of(timer, struct napi_struct, timer);
/* Note : we use a relaxed variant of napi_schedule_prep() not setting
* NAPI_STATE_MISSED, since we do not react to a device IRQ.
*/
if (!napi_disable_pending(napi) &&
!test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
__napi_schedule_irqoff(napi);
}
return HRTIMER_NORESTART;
}
int dev_set_threaded(struct net_device *dev, bool threaded)
{
struct napi_struct *napi;
int err = 0;
netdev_assert_locked_or_invisible(dev);
if (dev->threaded == threaded)
return 0;
if (threaded) {
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (!napi->thread) {
err = napi_kthread_create(napi);
if (err) {
threaded = false;
break;
}
}
}
}
WRITE_ONCE(dev->threaded, threaded);
/* Make sure kthread is created before THREADED bit
* is set.
*/
smp_mb__before_atomic();
/* Setting/unsetting threaded mode on a napi might not immediately
* take effect, if the current napi instance is actively being
* polled. In this case, the switch between threaded mode and
* softirq mode will happen in the next round of napi_schedule().
* This should not cause hiccups/stalls to the live traffic.
*/
list_for_each_entry(napi, &dev->napi_list, dev_list)
assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
return err;
}
EXPORT_SYMBOL(dev_set_threaded);
/**
* netif_queue_set_napi - Associate queue with the napi
* @dev: device to which NAPI and queue belong
* @queue_index: Index of queue
* @type: queue type as RX or TX
* @napi: NAPI context, pass NULL to clear previously set NAPI
*
* Set queue with its corresponding napi context. This should be done after
* registering the NAPI handler for the queue-vector and the queues have been
* mapped to the corresponding interrupt vector.
*/
void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
enum netdev_queue_type type, struct napi_struct *napi)
{
struct netdev_rx_queue *rxq;
struct netdev_queue *txq;
if (WARN_ON_ONCE(napi && !napi->dev))
return;
netdev_ops_assert_locked_or_invisible(dev);
switch (type) {
case NETDEV_QUEUE_TYPE_RX:
rxq = __netif_get_rx_queue(dev, queue_index);
rxq->napi = napi;
return;
case NETDEV_QUEUE_TYPE_TX:
txq = netdev_get_tx_queue(dev, queue_index);
txq->napi = napi;
return;
default:
return;
}
}
EXPORT_SYMBOL(netif_queue_set_napi);
static void
netif_napi_irq_notify(struct irq_affinity_notify *notify,
const cpumask_t *mask)
{
struct napi_struct *napi =
container_of(notify, struct napi_struct, notify);
#ifdef CONFIG_RFS_ACCEL
struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
int err;
#endif
if (napi->config && napi->dev->irq_affinity_auto)
cpumask_copy(&napi->config->affinity_mask, mask);
#ifdef CONFIG_RFS_ACCEL
if (napi->dev->rx_cpu_rmap_auto) {
err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask);
if (err)
netdev_warn(napi->dev, "RMAP update failed (%d)\n",
err);
}
#endif
}
#ifdef CONFIG_RFS_ACCEL
static void netif_napi_affinity_release(struct kref *ref)
{
struct napi_struct *napi =
container_of(ref, struct napi_struct, notify.kref);
struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
netdev_assert_locked(napi->dev);
WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER,
&napi->state));
if (!napi->dev->rx_cpu_rmap_auto)
return;
rmap->obj[napi->napi_rmap_idx] = NULL;
napi->napi_rmap_idx = -1;
cpu_rmap_put(rmap);
}
int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
{
if (dev->rx_cpu_rmap_auto)
return 0;
dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs);
if (!dev->rx_cpu_rmap)
return -ENOMEM;
dev->rx_cpu_rmap_auto = true;
return 0;
}
EXPORT_SYMBOL(netif_enable_cpu_rmap);
static void netif_del_cpu_rmap(struct net_device *dev)
{
struct cpu_rmap *rmap = dev->rx_cpu_rmap;
if (!dev->rx_cpu_rmap_auto)
return;
/* Free the rmap */
cpu_rmap_put(rmap);
dev->rx_cpu_rmap = NULL;
dev->rx_cpu_rmap_auto = false;
}
#else
static void netif_napi_affinity_release(struct kref *ref)
{
}
int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
{
return 0;
}
EXPORT_SYMBOL(netif_enable_cpu_rmap);
static void netif_del_cpu_rmap(struct net_device *dev)
{
}
#endif
void netif_set_affinity_auto(struct net_device *dev)
{
unsigned int i, maxqs, numa;
maxqs = max(dev->num_tx_queues, dev->num_rx_queues);
numa = dev_to_node(&dev->dev);
for (i = 0; i < maxqs; i++)
cpumask_set_cpu(cpumask_local_spread(i, numa),
&dev->napi_config[i].affinity_mask);
dev->irq_affinity_auto = true;
}
EXPORT_SYMBOL(netif_set_affinity_auto);
void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
{
int rc;
netdev_assert_locked_or_invisible(napi->dev);
if (napi->irq == irq)
return;
/* Remove existing resources */
if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
irq_set_affinity_notifier(napi->irq, NULL);
napi->irq = irq;
if (irq < 0 ||
(!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto))
return;
/* Abort for buggy drivers */
if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config))
return;
#ifdef CONFIG_RFS_ACCEL
if (napi->dev->rx_cpu_rmap_auto) {
rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi);
if (rc < 0)
return;
cpu_rmap_get(napi->dev->rx_cpu_rmap);
napi->napi_rmap_idx = rc;
}
#endif
/* Use core IRQ notifier */
napi->notify.notify = netif_napi_irq_notify;
napi->notify.release = netif_napi_affinity_release;
rc = irq_set_affinity_notifier(irq, &napi->notify);
if (rc) {
netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n",
rc);
goto put_rmap;
}
set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state);
return;
put_rmap:
#ifdef CONFIG_RFS_ACCEL
if (napi->dev->rx_cpu_rmap_auto) {
napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL;
cpu_rmap_put(napi->dev->rx_cpu_rmap);
napi->napi_rmap_idx = -1;
}
#endif
napi->notify.notify = NULL;
napi->notify.release = NULL;
}
EXPORT_SYMBOL(netif_napi_set_irq_locked);
static void napi_restore_config(struct napi_struct *n)
{
n->defer_hard_irqs = n->config->defer_hard_irqs;
n->gro_flush_timeout = n->config->gro_flush_timeout;
n->irq_suspend_timeout = n->config->irq_suspend_timeout;
if (n->dev->irq_affinity_auto &&
test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state))
irq_set_affinity(n->irq, &n->config->affinity_mask);
/* a NAPI ID might be stored in the config, if so use it. if not, use
* napi_hash_add to generate one for us.
*/
if (n->config->napi_id) {
napi_hash_add_with_id(n, n->config->napi_id);
} else {
napi_hash_add(n);
n->config->napi_id = n->napi_id;
}
}
static void napi_save_config(struct napi_struct *n)
{
n->config->defer_hard_irqs = n->defer_hard_irqs;
n->config->gro_flush_timeout = n->gro_flush_timeout;
n->config->irq_suspend_timeout = n->irq_suspend_timeout;
napi_hash_del(n);
}
/* Netlink wants the NAPI list to be sorted by ID, if adding a NAPI which will
* inherit an existing ID try to insert it at the right position.
*/
static void
netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi)
{
unsigned int new_id, pos_id;
struct list_head *higher;
struct napi_struct *pos;
new_id = UINT_MAX;
if (napi->config && napi->config->napi_id)
new_id = napi->config->napi_id;
higher = &dev->napi_list;
list_for_each_entry(pos, &dev->napi_list, dev_list) {
if (napi_id_valid(pos->napi_id))
pos_id = pos->napi_id;
else if (pos->config)
pos_id = pos->config->napi_id;
else
pos_id = UINT_MAX;
if (pos_id <= new_id)
break;
higher = &pos->dev_list;
}
list_add_rcu(&napi->dev_list, higher); /* adds after higher */
}
/* Double check that napi_get_frags() allocates skbs with
* skb->head being backed by slab, not a page fragment.
* This is to make sure bug fixed in 3226b158e67c
* ("net: avoid 32 x truesize under-estimation for tiny skbs")
* does not accidentally come back.
*/
static void napi_get_frags_check(struct napi_struct *napi)
{
struct sk_buff *skb;
local_bh_disable();
skb = napi_get_frags(napi);
WARN_ON_ONCE(skb && skb->head_frag);
napi_free_frags(napi);
local_bh_enable();
}
void netif_napi_add_weight_locked(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int),
int weight)
{
netdev_assert_locked(dev);
if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
return;
INIT_LIST_HEAD(&napi->poll_list);
INIT_HLIST_NODE(&napi->napi_hash_node);
hrtimer_setup(&napi->timer, napi_watchdog, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
gro_init(&napi->gro);
napi->skb = NULL;
napi->poll = poll;
if (weight > NAPI_POLL_WEIGHT)
netdev_err_once(dev, "%s() called with weight %d\n", __func__,
weight);
napi->weight = weight;
napi->dev = dev;
#ifdef CONFIG_NETPOLL
napi->poll_owner = -1;
#endif
napi->list_owner = -1;
set_bit(NAPI_STATE_SCHED, &napi->state);
set_bit(NAPI_STATE_NPSVC, &napi->state);
netif_napi_dev_list_add(dev, napi);
/* default settings from sysfs are applied to all NAPIs. any per-NAPI
* configuration will be loaded in napi_enable
*/
napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs));
napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout));
napi_get_frags_check(napi);
/* Create kthread for this napi if dev->threaded is set.
* Clear dev->threaded if kthread creation failed so that
* threaded mode will not be enabled in napi_enable().
*/
if (dev->threaded && napi_kthread_create(napi))
dev->threaded = false;
netif_napi_set_irq_locked(napi, -1);
}
EXPORT_SYMBOL(netif_napi_add_weight_locked);
void napi_disable_locked(struct napi_struct *n)
{
unsigned long val, new;
might_sleep();
netdev_assert_locked(n->dev);
set_bit(NAPI_STATE_DISABLE, &n->state);
val = READ_ONCE(n->state);
do {
while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) {
usleep_range(20, 200);
val = READ_ONCE(n->state);
}
new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC;
new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL);
} while (!try_cmpxchg(&n->state, &val, new));
hrtimer_cancel(&n->timer);
if (n->config)
napi_save_config(n);
else
napi_hash_del(n);
clear_bit(NAPI_STATE_DISABLE, &n->state);
}
EXPORT_SYMBOL(napi_disable_locked);
/**
* napi_disable() - prevent NAPI from scheduling
* @n: NAPI context
*
* Stop NAPI from being scheduled on this context.
* Waits till any outstanding processing completes.
* Takes netdev_lock() for associated net_device.
*/
void napi_disable(struct napi_struct *n)
{
netdev_lock(n->dev);
napi_disable_locked(n);
netdev_unlock(n->dev);
}
EXPORT_SYMBOL(napi_disable);
void napi_enable_locked(struct napi_struct *n)
{
unsigned long new, val = READ_ONCE(n->state);
if (n->config)
napi_restore_config(n);
else
napi_hash_add(n);
do {
BUG_ON(!test_bit(NAPI_STATE_SCHED, &val));
new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC);
if (n->dev->threaded && n->thread)
new |= NAPIF_STATE_THREADED;
} while (!try_cmpxchg(&n->state, &val, new));
}
EXPORT_SYMBOL(napi_enable_locked);
/**
* napi_enable() - enable NAPI scheduling
* @n: NAPI context
*
* Enable scheduling of a NAPI instance.
* Must be paired with napi_disable().
* Takes netdev_lock() for associated net_device.
*/
void napi_enable(struct napi_struct *n)
{
netdev_lock(n->dev);
napi_enable_locked(n);
netdev_unlock(n->dev);
}
EXPORT_SYMBOL(napi_enable);
/* Must be called in process context */
void __netif_napi_del_locked(struct napi_struct *napi)
{
netdev_assert_locked(napi->dev);
if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
return;
/* Make sure NAPI is disabled (or was never enabled). */
WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
irq_set_affinity_notifier(napi->irq, NULL);
if (napi->config) {
napi->index = -1;
napi->config = NULL;
}
list_del_rcu(&napi->dev_list);
napi_free_frags(napi);
gro_cleanup(&napi->gro);
if (napi->thread) {
kthread_stop(napi->thread);
napi->thread = NULL;
}
}
EXPORT_SYMBOL(__netif_napi_del_locked);
static int __napi_poll(struct napi_struct *n, bool *repoll)
{
int work, weight;
weight = n->weight;
/* This NAPI_STATE_SCHED test is for avoiding a race
* with netpoll's poll_napi(). Only the entity which
* obtains the lock and sees NAPI_STATE_SCHED set will
* actually make the ->poll() call. Therefore we avoid
* accidentally calling ->poll() when NAPI is not scheduled.
*/
work = 0;
if (napi_is_scheduled(n)) {
work = n->poll(n, weight);
trace_napi_poll(n, work, weight);
xdp_do_check_flushed(n);
}
if (unlikely(work > weight))
netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n",
n->poll, work, weight);
if (likely(work < weight))
return work;
/* Drivers must not modify the NAPI state if they
* consume the entire weight. In such cases this code
* still "owns" the NAPI instance and therefore can
* move the instance around on the list at-will.
*/
if (unlikely(napi_disable_pending(n))) {
napi_complete(n);
return work;
}
/* The NAPI context has more processing work, but busy-polling
* is preferred. Exit early.
*/
if (napi_prefer_busy_poll(n)) {
if (napi_complete_done(n, work)) {
/* If timeout is not set, we need to make sure
* that the NAPI is re-scheduled.
*/
napi_schedule(n);
}
return work;
}
/* Flush too old packets. If HZ < 1000, flush all packets */
gro_flush(&n->gro, HZ >= 1000);
gro_normal_list(&n->gro);
/* Some drivers may have called napi_schedule
* prior to exhausting their budget.
*/
if (unlikely(!list_empty(&n->poll_list))) {
pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
n->dev ? n->dev->name : "backlog");
return work;
}
*repoll = true;
return work;
}
static int napi_poll(struct napi_struct *n, struct list_head *repoll)
{
bool do_repoll = false;
void *have;
int work;
list_del_init(&n->poll_list);
have = netpoll_poll_lock(n);
work = __napi_poll(n, &do_repoll);
if (do_repoll)
list_add_tail(&n->poll_list, repoll);
netpoll_poll_unlock(have);
return work;
}
static int napi_thread_wait(struct napi_struct *napi)
{
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
/* Testing SCHED_THREADED bit here to make sure the current
* kthread owns this napi and could poll on this napi.
* Testing SCHED bit is not enough because SCHED bit might be
* set by some other busy poll thread or by napi_disable().
*/
if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) {
WARN_ON(!list_empty(&napi->poll_list));
__set_current_state(TASK_RUNNING);
return 0;
}
schedule();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return -1;
}
static void napi_threaded_poll_loop(struct napi_struct *napi)
{
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
struct softnet_data *sd;
unsigned long last_qs = jiffies;
for (;;) {
bool repoll = false;
void *have;
local_bh_disable();
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
sd = this_cpu_ptr(&softnet_data);
sd->in_napi_threaded_poll = true;
have = netpoll_poll_lock(napi);
__napi_poll(napi, &repoll);
netpoll_poll_unlock(have);
sd->in_napi_threaded_poll = false;
barrier();
if (sd_has_rps_ipi_waiting(sd)) {
local_irq_disable();
net_rps_action_and_irq_enable(sd);
}
skb_defer_free_flush(sd);
bpf_net_ctx_clear(bpf_net_ctx);
local_bh_enable();
if (!repoll)
break;
rcu_softirq_qs_periodic(last_qs);
cond_resched();
}
}
static int napi_threaded_poll(void *data)
{
struct napi_struct *napi = data;
while (!napi_thread_wait(napi))
napi_threaded_poll_loop(napi);
return 0;
}
static __latent_entropy void net_rx_action(void)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs));
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
int budget = READ_ONCE(net_hotdata.netdev_budget);
LIST_HEAD(list);
LIST_HEAD(repoll);
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
start:
sd->in_net_rx_action = true;
local_irq_disable();
list_splice_init(&sd->poll_list, &list);
local_irq_enable();
for (;;) {
struct napi_struct *n;
skb_defer_free_flush(sd);
if (list_empty(&list)) {
if (list_empty(&repoll)) {
sd->in_net_rx_action = false;
barrier();
/* We need to check if ____napi_schedule()
* had refilled poll_list while
* sd->in_net_rx_action was true.
*/
if (!list_empty(&sd->poll_list))
goto start;
if (!sd_has_rps_ipi_waiting(sd))
goto end;
}
break;
}
n = list_first_entry(&list, struct napi_struct, poll_list);
budget -= napi_poll(n, &repoll);
/* If softirq window is exhausted then punt.
* Allow this to run for 2 jiffies since which will allow
* an average latency of 1.5/HZ.
*/
if (unlikely(budget <= 0 ||
time_after_eq(jiffies, time_limit))) {
sd->time_squeeze++;
break;
}
}
local_irq_disable();
list_splice_tail_init(&sd->poll_list, &list);
list_splice_tail(&repoll, &list);
list_splice(&list, &sd->poll_list);
if (!list_empty(&sd->poll_list))
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
else
sd->in_net_rx_action = false;
net_rps_action_and_irq_enable(sd);
end:
bpf_net_ctx_clear(bpf_net_ctx);
}
struct netdev_adjacent {
struct net_device *dev;
netdevice_tracker dev_tracker;
/* upper master flag, there can only be one master device per list */
bool master;
/* lookup ignore flag */
bool ignore;
/* counter for the number of times this device was added to us */
u16 ref_nr;
/* private field for the users */
void *private;
struct list_head list;
struct rcu_head rcu;
};
static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
struct list_head *adj_list)
{
struct netdev_adjacent *adj;
list_for_each_entry(adj, adj_list, list) {
if (adj->dev == adj_dev)
return adj;
}
return NULL;
}
static int ____netdev_has_upper_dev(struct net_device *upper_dev,
struct netdev_nested_priv *priv)
{
struct net_device *dev = (struct net_device *)priv->data;
return upper_dev == dev;
}
/**
* netdev_has_upper_dev - Check if device is linked to an upper device
* @dev: device
* @upper_dev: upper device to check
*
* Find out if a device is linked to specified upper device and return true
* in case it is. Note that this checks only immediate upper device,
* not through a complete stack of devices. The caller must hold the RTNL lock.
*/
bool netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_nested_priv priv = {
.data = (void *)upper_dev,
};
ASSERT_RTNL();
return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
&priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
* netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
* @dev: device
* @upper_dev: upper device to check
*
* Find out if a device is linked to specified upper device and return true
* in case it is. Note that this checks the entire upper device chain.
* The caller must hold rcu lock.
*/
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_nested_priv priv = {
.data = (void *)upper_dev,
};
return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
&priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
/**
* netdev_has_any_upper_dev - Check if device is linked to some device
* @dev: device
*
* Find out if a device is linked to an upper device and return true in case
* it is. The caller must hold the RTNL lock.
*/
bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
return !list_empty(&dev->adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_any_upper_dev);
/**
* netdev_master_upper_dev_get - Get master upper device
* @dev: device
*
* Find a master upper device and return pointer to it or NULL in case
* it's not there. The caller must hold the RTNL lock.
*/
struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
{
struct netdev_adjacent *upper;
ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper))
return NULL;
upper = list_first_entry(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (likely(upper->master))
return upper->dev;
return NULL;
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
{
struct netdev_adjacent *upper;
ASSERT_RTNL();
if (list_empty(&dev->adj_list.upper))
return NULL;
upper = list_first_entry(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (likely(upper->master) && !upper->ignore)
return upper->dev;
return NULL;
}
/**
* netdev_has_any_lower_dev - Check if device is linked to some device
* @dev: device
*
* Find out if a device is linked to a lower device and return true in case
* it is. The caller must hold the RTNL lock.
*/
static bool netdev_has_any_lower_dev(struct net_device *dev)
{
ASSERT_RTNL();
return !list_empty(&dev->adj_list.lower);
}
void *netdev_adjacent_get_private(struct list_head *adj_list)
{
struct netdev_adjacent *adj;
adj = list_entry(adj_list, struct netdev_adjacent, list);
return adj->private;
}
EXPORT_SYMBOL(netdev_adjacent_get_private);
/**
* netdev_upper_get_next_dev_rcu - Get the next dev from upper list
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next device from the dev's upper list, starting from iter
* position. The caller must hold RCU read lock.
*/
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *upper;
WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
if (&upper->list == &dev->adj_list.upper)
return NULL;
*iter = &upper->list;
return upper->dev;
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
struct list_head **iter,
bool *ignore)
{
struct netdev_adjacent *upper;
upper = list_entry((*iter)->next, struct netdev_adjacent, list);
if (&upper->list == &dev->adj_list.upper)
return NULL;
*iter = &upper->list;
*ignore = upper->ignore;
return upper->dev;
}
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *upper;
WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
if (&upper->list == &dev->adj_list.upper)
return NULL;
*iter = &upper->list;
return upper->dev;
}
static int __netdev_walk_all_upper_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int ret, cur = 0;
bool ignore;
now = dev;
iter = &dev->adj_list.upper;
while (1) {
if (now != dev) {
ret = fn(now, priv);
if (ret)
return ret;
}
next = NULL;
while (1) {
udev = __netdev_next_upper_dev(now, &iter, &ignore);
if (!udev)
break;
if (ignore)
continue;
next = udev;
niter = &udev->adj_list.upper;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
break;
}
if (!next) {
if (!cur)
return 0;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return 0;
}
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int ret, cur = 0;
now = dev;
iter = &dev->adj_list.upper;
while (1) {
if (now != dev) {
ret = fn(now, priv);
if (ret)
return ret;
}
next = NULL;
while (1) {
udev = netdev_next_upper_dev_rcu(now, &iter);
if (!udev)
break;
next = udev;
niter = &udev->adj_list.upper;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
break;
}
if (!next) {
if (!cur)
return 0;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
static bool __netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_nested_priv priv = {
.flags = 0,
.data = (void *)upper_dev,
};
ASSERT_RTNL();
return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
&priv);
}
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next netdev_adjacent->private from the dev's lower neighbour
* list, starting from iter position. The caller must hold either hold the
* RTNL lock or its own locking that guarantees that the neighbour lower
* list will remain unchanged.
*/
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *lower;
lower = list_entry(*iter, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = lower->list.next;
return lower->private;
}
EXPORT_SYMBOL(netdev_lower_get_next_private);
/**
* netdev_lower_get_next_private_rcu - Get the next ->private from the
* lower neighbour list, RCU
* variant
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next netdev_adjacent->private from the dev's lower neighbour
* list, starting from iter position. The caller must hold RCU read lock.
*/
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *lower;
WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = &lower->list;
return lower->private;
}
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
* netdev_lower_get_next - Get the next device from the lower neighbour
* list
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next netdev_adjacent from the dev's lower neighbour
* list, starting from iter position. The caller must hold RTNL lock or
* its own locking that guarantees that the neighbour lower
* list will remain unchanged.
*/
void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
{
struct netdev_adjacent *lower;
lower = list_entry(*iter, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = lower->list.next;
return lower->dev;
}
EXPORT_SYMBOL(netdev_lower_get_next);
static struct net_device *netdev_next_lower_dev(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *lower;
lower = list_entry((*iter)->next, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = &lower->list;
return lower->dev;
}
static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
struct list_head **iter,
bool *ignore)
{
struct netdev_adjacent *lower;
lower = list_entry((*iter)->next, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = &lower->list;
*ignore = lower->ignore;
return lower->dev;
}
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int ret, cur = 0;
now = dev;
iter = &dev->adj_list.lower;
while (1) {
if (now != dev) {
ret = fn(now, priv);
if (ret)
return ret;
}
next = NULL;
while (1) {
ldev = netdev_next_lower_dev(now, &iter);
if (!ldev)
break;
next = ldev;
niter = &ldev->adj_list.lower;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
break;
}
if (!next) {
if (!cur)
return 0;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
static int __netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int ret, cur = 0;
bool ignore;
now = dev;
iter = &dev->adj_list.lower;
while (1) {
if (now != dev) {
ret = fn(now, priv);
if (ret)
return ret;
}
next = NULL;
while (1) {
ldev = __netdev_next_lower_dev(now, &iter, &ignore);
if (!ldev)
break;
if (ignore)
continue;
next = ldev;
niter = &ldev->adj_list.lower;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
break;
}
if (!next) {
if (!cur)
return 0;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return 0;
}
struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
struct netdev_adjacent *lower;
lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
if (&lower->list == &dev->adj_list.lower)
return NULL;
*iter = &lower->list;
return lower->dev;
}
EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
static u8 __netdev_upper_depth(struct net_device *dev)
{
struct net_device *udev;
struct list_head *iter;
u8 max_depth = 0;
bool ignore;
for (iter = &dev->adj_list.upper,
udev = __netdev_next_upper_dev(dev, &iter, &ignore);
udev;
udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
if (ignore)
continue;
if (max_depth < udev->upper_level)
max_depth = udev->upper_level;
}
return max_depth;
}
static u8 __netdev_lower_depth(struct net_device *dev)
{
struct net_device *ldev;
struct list_head *iter;
u8 max_depth = 0;
bool ignore;
for (iter = &dev->adj_list.lower,
ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
ldev;
ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
if (ignore)
continue;
if (max_depth < ldev->lower_level)
max_depth = ldev->lower_level;
}
return max_depth;
}
static int __netdev_update_upper_level(struct net_device *dev,
struct netdev_nested_priv *__unused)
{
dev->upper_level = __netdev_upper_depth(dev) + 1;
return 0;
}
#ifdef CONFIG_LOCKDEP
static LIST_HEAD(net_unlink_list);
static void net_unlink_todo(struct net_device *dev)
{
if (list_empty(&dev->unlink_list))
list_add_tail(&dev->unlink_list, &net_unlink_list);
}
#endif
static int __netdev_update_lower_level(struct net_device *dev,
struct netdev_nested_priv *priv)
{
dev->lower_level = __netdev_lower_depth(dev) + 1;
#ifdef CONFIG_LOCKDEP
if (!priv)
return 0;
if (priv->flags & NESTED_SYNC_IMM)
dev->nested_level = dev->lower_level - 1;
if (priv->flags & NESTED_SYNC_TODO)
net_unlink_todo(dev);
#endif
return 0;
}
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
struct netdev_nested_priv *priv),
struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int ret, cur = 0;
now = dev;
iter = &dev->adj_list.lower;
while (1) {
if (now != dev) {
ret = fn(now, priv);
if (ret)
return ret;
}
next = NULL;
while (1) {
ldev = netdev_next_lower_dev_rcu(now, &iter);
if (!ldev)
break;
next = ldev;
niter = &ldev->adj_list.lower;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
break;
}
if (!next) {
if (!cur)
return 0;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu);
/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
* variant
* @dev: device
*
* Gets the first netdev_adjacent->private from the dev's lower neighbour
* list. The caller must hold RCU read lock.
*/
void *netdev_lower_get_first_private_rcu(struct net_device *dev)
{
struct netdev_adjacent *lower;
lower = list_first_or_null_rcu(&dev->adj_list.lower,
struct netdev_adjacent, list);
if (lower)
return lower->private;
return NULL;
}
EXPORT_SYMBOL(netdev_lower_get_first_private_rcu);
/**
* netdev_master_upper_dev_get_rcu - Get master upper device
* @dev: device
*
* Find a master upper device and return pointer to it or NULL in case
* it's not there. The caller must hold the RCU read lock.
*/
struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
{
struct netdev_adjacent *upper;
upper = list_first_or_null_rcu(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (upper && likely(upper->master)) return upper->dev;
return NULL;
}
EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
static int netdev_adjacent_sysfs_add(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list)
{
char linkname[IFNAMSIZ+7];
sprintf(linkname, dev_list == &dev->adj_list.upper ?
"upper_%s" : "lower_%s", adj_dev->name);
return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
linkname);
}
static void netdev_adjacent_sysfs_del(struct net_device *dev,
char *name,
struct list_head *dev_list)
{
char linkname[IFNAMSIZ+7];
sprintf(linkname, dev_list == &dev->adj_list.upper ?
"upper_%s" : "lower_%s", name);
sysfs_remove_link(&(dev->dev.kobj), linkname);
}
static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list)
{
return (dev_list == &dev->adj_list.upper ||
dev_list == &dev->adj_list.lower) &&
net_eq(dev_net(dev), dev_net(adj_dev));
}
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list,
void *private, bool master)
{
struct netdev_adjacent *adj;
int ret;
adj = __netdev_find_adj(adj_dev, dev_list);
if (adj) {
adj->ref_nr += 1;
pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n",
dev->name, adj_dev->name, adj->ref_nr);
return 0;
}
adj = kmalloc(sizeof(*adj), GFP_KERNEL);
if (!adj)
return -ENOMEM;
adj->dev = adj_dev;
adj->master = master;
adj->ref_nr = 1;
adj->private = private;
adj->ignore = false;
netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL);
pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
dev->name, adj_dev->name, adj->ref_nr, adj_dev->name);
if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) {
ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
if (ret)
goto free_adj;
}
/* Ensure that master link is always the first item in list. */
if (master) {
ret = sysfs_create_link(&(dev->dev.kobj),
&(adj_dev->dev.kobj), "master");
if (ret)
goto remove_symlinks;
list_add_rcu(&adj->list, dev_list);
} else {
list_add_tail_rcu(&adj->list, dev_list);
}
return 0;
remove_symlinks:
if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list))
netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
free_adj:
netdev_put(adj_dev, &adj->dev_tracker);
kfree(adj);
return ret;
}
static void __netdev_adjacent_dev_remove(struct net_device *dev,
struct net_device *adj_dev,
u16 ref_nr,
struct list_head *dev_list)
{
struct netdev_adjacent *adj;
pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n",
dev->name, adj_dev->name, ref_nr);
adj = __netdev_find_adj(adj_dev, dev_list);
if (!adj) {
pr_err("Adjacency does not exist for device %s from %s\n",
dev->name, adj_dev->name);
WARN_ON(1);
return;
}
if (adj->ref_nr > ref_nr) {
pr_debug("adjacency: %s to %s ref_nr - %d = %d\n",
dev->name, adj_dev->name, ref_nr,
adj->ref_nr - ref_nr);
adj->ref_nr -= ref_nr;
return;
}
if (adj->master)
sysfs_remove_link(&(dev->dev.kobj), "master");
if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list))
netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
list_del_rcu(&adj->list);
pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n",
adj_dev->name, dev->name, adj_dev->name);
netdev_put(adj_dev, &adj->dev_tracker);
kfree_rcu(adj, rcu);
}
static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
struct net_device *upper_dev,
struct list_head *up_list,
struct list_head *down_list,
void *private, bool master)
{
int ret;
ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list,
private, master);
if (ret)
return ret;
ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list,
private, false);
if (ret) {
__netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list);
return ret;
}
return 0;
}
static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
struct net_device *upper_dev,
u16 ref_nr,
struct list_head *up_list,
struct list_head *down_list)
{
__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
}
static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
struct net_device *upper_dev,
void *private, bool master)
{
return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->adj_list.upper,
&upper_dev->adj_list.lower,
private, master);
}
static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
&dev->adj_list.upper,
&upper_dev->adj_list.lower);
}
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
void *upper_priv, void *upper_info,
struct netdev_nested_priv *priv,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_changeupper_info changeupper_info = {
.info = {
.dev = dev,
.extack = extack,
},
.upper_dev = upper_dev,
.master = master,
.linking = true,
.upper_info = upper_info,
};
struct net_device *master_dev;
int ret = 0;
ASSERT_RTNL();
if (dev == upper_dev)
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
if (__netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
return -EMLINK;
if (!master) {
if (__netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
} else {
master_dev = __netdev_master_upper_dev_get(dev);
if (master_dev)
return master_dev == upper_dev ? -EEXIST : -EBUSY;
}
ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
return ret;
ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv,
master);
if (ret)
return ret;
ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
goto rollback;
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
__netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
priv);
return 0;
rollback:
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
}
/**
* netdev_upper_dev_link - Add a link to the upper device
* @dev: device
* @upper_dev: new upper device
* @extack: netlink extended ack
*
* Adds a link to device which is upper to this one. The caller must hold
* the RTNL lock. On a failure a negative errno code is returned.
* On success the reference counts are adjusted and the function
* returns zero.
*/
int netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
struct netlink_ext_ack *extack)
{
struct netdev_nested_priv priv = {
.flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
.data = NULL,
};
return __netdev_upper_dev_link(dev, upper_dev, false,
NULL, NULL, &priv, extack);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
/**
* netdev_master_upper_dev_link - Add a master link to the upper device
* @dev: device
* @upper_dev: new upper device
* @upper_priv: upper device private
* @upper_info: upper info to be passed down via notifier
* @extack: netlink extended ack
*
* Adds a link to device which is upper to this one. In this case, only
* one master upper device can be linked, although other non-master devices
* might be linked as well. The caller must hold the RTNL lock.
* On a failure a negative errno code is returned. On success the reference
* counts are adjusted and the function returns zero.
*/
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev,
void *upper_priv, void *upper_info,
struct netlink_ext_ack *extack)
{
struct netdev_nested_priv priv = {
.flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
.data = NULL,
};
return __netdev_upper_dev_link(dev, upper_dev, true,
upper_priv, upper_info, &priv, extack);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
static void __netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev,
struct netdev_nested_priv *priv)
{
struct netdev_notifier_changeupper_info changeupper_info = {
.info = {
.dev = dev,
},
.upper_dev = upper_dev,
.linking = false,
};
ASSERT_RTNL();
changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER,
&changeupper_info.info);
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
__netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
priv);
}
/**
* netdev_upper_dev_unlink - Removes a link to upper device
* @dev: device
* @upper_dev: new upper device
*
* Removes a link to device which is upper to this one. The caller must hold
* the RTNL lock.
*/
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_nested_priv priv = {
.flags = NESTED_SYNC_TODO,
.data = NULL,
};
__netdev_upper_dev_unlink(dev, upper_dev, &priv);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
struct net_device *lower_dev,
bool val)
{
struct netdev_adjacent *adj;
adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
if (adj)
adj->ignore = val;
adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
if (adj)
adj->ignore = val;
}
static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
struct net_device *lower_dev)
{
__netdev_adjacent_dev_set(upper_dev, lower_dev, true);
}
static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
struct net_device *lower_dev)
{
__netdev_adjacent_dev_set(upper_dev, lower_dev, false);
}
int netdev_adjacent_change_prepare(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct netdev_nested_priv priv = {
.flags = 0,
.data = NULL,
};
int err;
if (!new_dev)
return 0;
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_disable(dev, old_dev);
err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv,
extack);
if (err) {
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
return err;
}
return 0;
}
EXPORT_SYMBOL(netdev_adjacent_change_prepare);
void netdev_adjacent_change_commit(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev)
{
struct netdev_nested_priv priv = {
.flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
.data = NULL,
};
if (!new_dev || !old_dev)
return;
if (new_dev == old_dev)
return;
netdev_adjacent_dev_enable(dev, old_dev);
__netdev_upper_dev_unlink(old_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_commit);
void netdev_adjacent_change_abort(struct net_device *old_dev,
struct net_device *new_dev,
struct net_device *dev)
{
struct netdev_nested_priv priv = {
.flags = 0,
.data = NULL,
};
if (!new_dev)
return;
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
__netdev_upper_dev_unlink(new_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_abort);
/**
* netdev_bonding_info_change - Dispatch event about slave change
* @dev: device
* @bonding_info: info to dispatch
*
* Send NETDEV_BONDING_INFO to netdev notifiers with info.
* The caller must hold the RTNL lock.
*/
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info)
{
struct netdev_notifier_bonding_info info = {
.info.dev = dev,
};
memcpy(&info.bonding_info, bonding_info,
sizeof(struct netdev_bonding_info));
call_netdevice_notifiers_info(NETDEV_BONDING_INFO,
&info.info);
}
EXPORT_SYMBOL(netdev_bonding_info_change);
static int netdev_offload_xstats_enable_l3(struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_offload_xstats_info info = {
.info.dev = dev,
.info.extack = extack,
.type = NETDEV_OFFLOAD_XSTATS_TYPE_L3,
};
int err;
int rc;
dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3),
GFP_KERNEL);
if (!dev->offload_xstats_l3)
return -ENOMEM;
rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE,
NETDEV_OFFLOAD_XSTATS_DISABLE,
&info.info);
err = notifier_to_errno(rc);
if (err)
goto free_stats;
return 0;
free_stats:
kfree(dev->offload_xstats_l3);
dev->offload_xstats_l3 = NULL;
return err;
}
int netdev_offload_xstats_enable(struct net_device *dev,
enum netdev_offload_xstats_type type,
struct netlink_ext_ack *extack)
{
ASSERT_RTNL();
if (netdev_offload_xstats_enabled(dev, type))
return -EALREADY;
switch (type) {
case NETDEV_OFFLOAD_XSTATS_TYPE_L3:
return netdev_offload_xstats_enable_l3(dev, extack);
}
WARN_ON(1);
return -EINVAL;
}
EXPORT_SYMBOL(netdev_offload_xstats_enable);
static void netdev_offload_xstats_disable_l3(struct net_device *dev)
{
struct netdev_notifier_offload_xstats_info info = {
.info.dev = dev,
.type = NETDEV_OFFLOAD_XSTATS_TYPE_L3,
};
call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE,
&info.info);
kfree(dev->offload_xstats_l3);
dev->offload_xstats_l3 = NULL;
}
int netdev_offload_xstats_disable(struct net_device *dev,
enum netdev_offload_xstats_type type)
{
ASSERT_RTNL();
if (!netdev_offload_xstats_enabled(dev, type))
return -EALREADY;
switch (type) {
case NETDEV_OFFLOAD_XSTATS_TYPE_L3:
netdev_offload_xstats_disable_l3(dev);
return 0;
}
WARN_ON(1);
return -EINVAL;
}
EXPORT_SYMBOL(netdev_offload_xstats_disable);
static void netdev_offload_xstats_disable_all(struct net_device *dev)
{
netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3);
}
static struct rtnl_hw_stats64 *
netdev_offload_xstats_get_ptr(const struct net_device *dev,
enum netdev_offload_xstats_type type)
{
switch (type) {
case NETDEV_OFFLOAD_XSTATS_TYPE_L3:
return dev->offload_xstats_l3;
}
WARN_ON(1);
return NULL;
}
bool netdev_offload_xstats_enabled(const struct net_device *dev,
enum netdev_offload_xstats_type type)
{
ASSERT_RTNL();
return netdev_offload_xstats_get_ptr(dev, type);
}
EXPORT_SYMBOL(netdev_offload_xstats_enabled);
struct netdev_notifier_offload_xstats_ru {
bool used;
};
struct netdev_notifier_offload_xstats_rd {
struct rtnl_hw_stats64 stats;
bool used;
};
static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest,
const struct rtnl_hw_stats64 *src)
{
dest->rx_packets += src->rx_packets;
dest->tx_packets += src->tx_packets;
dest->rx_bytes += src->rx_bytes;
dest->tx_bytes += src->tx_bytes;
dest->rx_errors += src->rx_errors;
dest->tx_errors += src->tx_errors;
dest->rx_dropped += src->rx_dropped;
dest->tx_dropped += src->tx_dropped;
dest->multicast += src->multicast;
}
static int netdev_offload_xstats_get_used(struct net_device *dev,
enum netdev_offload_xstats_type type,
bool *p_used,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_offload_xstats_ru report_used = {};
struct netdev_notifier_offload_xstats_info info = {
.info.dev = dev,
.info.extack = extack,
.type = type,
.report_used = &report_used,
};
int rc;
WARN_ON(!netdev_offload_xstats_enabled(dev, type));
rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED,
&info.info);
*p_used = report_used.used;
return notifier_to_errno(rc);
}
static int netdev_offload_xstats_get_stats(struct net_device *dev,
enum netdev_offload_xstats_type type,
struct rtnl_hw_stats64 *p_stats,
bool *p_used,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_offload_xstats_rd report_delta = {};
struct netdev_notifier_offload_xstats_info info = {
.info.dev = dev,
.info.extack = extack,
.type = type,
.report_delta = &report_delta,
};
struct rtnl_hw_stats64 *stats;
int rc;
stats = netdev_offload_xstats_get_ptr(dev, type);
if (WARN_ON(!stats))
return -EINVAL;
rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA,
&info.info);
/* Cache whatever we got, even if there was an error, otherwise the
* successful stats retrievals would get lost.
*/
netdev_hw_stats64_add(stats, &report_delta.stats);
if (p_stats)
*p_stats = *stats;
*p_used = report_delta.used;
return notifier_to_errno(rc);
}
int netdev_offload_xstats_get(struct net_device *dev,
enum netdev_offload_xstats_type type,
struct rtnl_hw_stats64 *p_stats, bool *p_used,
struct netlink_ext_ack *extack)
{
ASSERT_RTNL();
if (p_stats)
return netdev_offload_xstats_get_stats(dev, type, p_stats,
p_used, extack);
else
return netdev_offload_xstats_get_used(dev, type, p_used,
extack);
}
EXPORT_SYMBOL(netdev_offload_xstats_get);
void
netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta,
const struct rtnl_hw_stats64 *stats)
{
report_delta->used = true;
netdev_hw_stats64_add(&report_delta->stats, stats);
}
EXPORT_SYMBOL(netdev_offload_xstats_report_delta);
void
netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used)
{
report_used->used = true;
}
EXPORT_SYMBOL(netdev_offload_xstats_report_used);
void netdev_offload_xstats_push_delta(struct net_device *dev,
enum netdev_offload_xstats_type type,
const struct rtnl_hw_stats64 *p_stats)
{
struct rtnl_hw_stats64 *stats;
ASSERT_RTNL();
stats = netdev_offload_xstats_get_ptr(dev, type);
if (WARN_ON(!stats))
return;
netdev_hw_stats64_add(stats, p_stats);
}
EXPORT_SYMBOL(netdev_offload_xstats_push_delta);
/**
* netdev_get_xmit_slave - Get the xmit slave of master device
* @dev: device
* @skb: The packet
* @all_slaves: assume all the slaves are active
*
* The reference counters are not incremented so the caller must be
* careful with locks. The caller must hold RCU lock.
* %NULL is returned if no slave is found.
*/
struct net_device *netdev_get_xmit_slave(struct net_device *dev,
struct sk_buff *skb,
bool all_slaves)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (!ops->ndo_get_xmit_slave)
return NULL;
return ops->ndo_get_xmit_slave(dev, skb, all_slaves);
}
EXPORT_SYMBOL(netdev_get_xmit_slave);
static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev,
struct sock *sk)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (!ops->ndo_sk_get_lower_dev)
return NULL;
return ops->ndo_sk_get_lower_dev(dev, sk);
}
/**
* netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket
* @dev: device
* @sk: the socket
*
* %NULL is returned if no lower device is found.
*/
struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev,
struct sock *sk)
{
struct net_device *lower;
lower = netdev_sk_get_lower_dev(dev, sk);
while (lower) {
dev = lower;
lower = netdev_sk_get_lower_dev(dev, sk);
}
return dev;
}
EXPORT_SYMBOL(netdev_sk_get_lowest_dev);
static void netdev_adjacent_add_links(struct net_device *dev)
{
struct netdev_adjacent *iter;
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.lower);
netdev_adjacent_sysfs_add(dev, iter->dev,
&dev->adj_list.upper);
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.upper);
netdev_adjacent_sysfs_add(dev, iter->dev,
&dev->adj_list.lower);
}
}
static void netdev_adjacent_del_links(struct net_device *dev)
{
struct netdev_adjacent *iter;
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, dev->name,
&iter->dev->adj_list.lower);
netdev_adjacent_sysfs_del(dev, iter->dev->name,
&dev->adj_list.upper);
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, dev->name,
&iter->dev->adj_list.upper);
netdev_adjacent_sysfs_del(dev, iter->dev->name,
&dev->adj_list.lower);
}
}
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
{
struct netdev_adjacent *iter;
struct net *net = dev_net(dev);
list_for_each_entry(iter, &dev->adj_list.upper, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, oldname,
&iter->dev->adj_list.lower);
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.lower);
}
list_for_each_entry(iter, &dev->adj_list.lower, list) {
if (!net_eq(net, dev_net(iter->dev)))
continue;
netdev_adjacent_sysfs_del(iter->dev, oldname,
&iter->dev->adj_list.upper);
netdev_adjacent_sysfs_add(iter->dev, dev,
&iter->dev->adj_list.upper);
}
}
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev)
{
struct netdev_adjacent *lower;
if (!lower_dev)
return NULL;
lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower);
if (!lower)
return NULL;
return lower->private;
}
EXPORT_SYMBOL(netdev_lower_dev_get_private);
/**
* netdev_lower_state_changed - Dispatch event about lower device state change
* @lower_dev: device
* @lower_state_info: state to dispatch
*
* Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info.
* The caller must hold the RTNL lock.
*/
void netdev_lower_state_changed(struct net_device *lower_dev,
void *lower_state_info)
{
struct netdev_notifier_changelowerstate_info changelowerstate_info = {
.info.dev = lower_dev,
};
ASSERT_RTNL();
changelowerstate_info.lower_state_info = lower_state_info;
call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE,
&changelowerstate_info.info);
}
EXPORT_SYMBOL(netdev_lower_state_changed);
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
{
unsigned int old_flags = dev->flags;
unsigned int promiscuity, flags;
kuid_t uid;
kgid_t gid;
ASSERT_RTNL();
promiscuity = dev->promiscuity + inc;
if (promiscuity == 0) {
/*
* Avoid overflow.
* If inc causes overflow, untouch promisc and return error.
*/
if (unlikely(inc > 0)) {
netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n");
return -EOVERFLOW;
}
flags = old_flags & ~IFF_PROMISC;
} else {
flags = old_flags | IFF_PROMISC;
}
WRITE_ONCE(dev->promiscuity, promiscuity);
if (flags != old_flags) {
WRITE_ONCE(dev->flags, flags);
netdev_info(dev, "%s promiscuous mode\n",
dev->flags & IFF_PROMISC ? "entered" : "left");
if (audit_enabled) {
current_uid_gid(&uid, &gid);
audit_log(audit_context(), GFP_ATOMIC,
AUDIT_ANOM_PROMISCUOUS,
"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
dev->name, (dev->flags & IFF_PROMISC),
(old_flags & IFF_PROMISC),
from_kuid(&init_user_ns, audit_get_loginuid(current)),
from_kuid(&init_user_ns, uid),
from_kgid(&init_user_ns, gid),
audit_get_sessionid(current));
}
dev_change_rx_flags(dev, IFF_PROMISC);
}
if (notify)
__dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL);
return 0;
}
/**
* dev_set_promiscuity - update promiscuity count on a device
* @dev: device
* @inc: modifier
*
* Add or remove promiscuity from a device. While the count in the device
* remains above zero the interface remains promiscuous. Once it hits zero
* the device reverts back to normal filtering operation. A negative inc
* value is used to drop promiscuity on the device.
* Return 0 if successful or a negative errno code on error.
*/
int dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned int old_flags = dev->flags;
int err;
err = __dev_set_promiscuity(dev, inc, true);
if (err < 0)
return err;
if (dev->flags != old_flags)
dev_set_rx_mode(dev);
return err;
}
EXPORT_SYMBOL(dev_set_promiscuity);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
{
unsigned int old_flags = dev->flags, old_gflags = dev->gflags;
unsigned int allmulti, flags;
ASSERT_RTNL();
allmulti = dev->allmulti + inc;
if (allmulti == 0) {
/*
* Avoid overflow.
* If inc causes overflow, untouch allmulti and return error.
*/
if (unlikely(inc > 0)) {
netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n");
return -EOVERFLOW;
}
flags = old_flags & ~IFF_ALLMULTI;
} else {
flags = old_flags | IFF_ALLMULTI;
}
WRITE_ONCE(dev->allmulti, allmulti);
if (flags != old_flags) {
WRITE_ONCE(dev->flags, flags);
netdev_info(dev, "%s allmulticast mode\n",
dev->flags & IFF_ALLMULTI ? "entered" : "left");
dev_change_rx_flags(dev, IFF_ALLMULTI);
dev_set_rx_mode(dev);
if (notify)
__dev_notify_flags(dev, old_flags,
dev->gflags ^ old_gflags, 0, NULL);
}
return 0;
}
/*
* Upload unicast and multicast address lists to device and
* configure RX filtering. When the device doesn't support unicast
* filtering it is put in promiscuous mode while unicast addresses
* are present.
*/
void __dev_set_rx_mode(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
/* dev_open will call this function so the list will stay sane. */
if (!(dev->flags&IFF_UP))
return;
if (!netif_device_present(dev))
return;
if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
*/
if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
__dev_set_promiscuity(dev, 1, false);
dev->uc_promisc = true;
} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
__dev_set_promiscuity(dev, -1, false);
dev->uc_promisc = false;
}
}
if (ops->ndo_set_rx_mode)
ops->ndo_set_rx_mode(dev);
}
void dev_set_rx_mode(struct net_device *dev)
{
netif_addr_lock_bh(dev);
__dev_set_rx_mode(dev);
netif_addr_unlock_bh(dev);
}
/**
* dev_get_flags - get flags reported to userspace
* @dev: device
*
* Get the combination of flag bits exported through APIs to userspace.
*/
unsigned int dev_get_flags(const struct net_device *dev)
{
unsigned int flags;
flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC |
IFF_ALLMULTI |
IFF_RUNNING |
IFF_LOWER_UP |
IFF_DORMANT)) |
(READ_ONCE(dev->gflags) & (IFF_PROMISC |
IFF_ALLMULTI));
if (netif_running(dev)) { if (netif_oper_up(dev))
flags |= IFF_RUNNING;
if (netif_carrier_ok(dev))
flags |= IFF_LOWER_UP;
if (netif_dormant(dev))
flags |= IFF_DORMANT;
}
return flags;
}
EXPORT_SYMBOL(dev_get_flags);
int __dev_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack)
{
unsigned int old_flags = dev->flags;
int ret;
ASSERT_RTNL();
/*
* Set the flags on our device.
*/
dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
IFF_AUTOMEDIA)) |
(dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
IFF_ALLMULTI));
/*
* Load in the correct multicast list now the flags have changed.
*/
if ((old_flags ^ flags) & IFF_MULTICAST)
dev_change_rx_flags(dev, IFF_MULTICAST);
dev_set_rx_mode(dev);
/*
* Have we downed the interface. We handle IFF_UP ourselves
* according to user attempts to set it, rather than blindly
* setting it.
*/
ret = 0;
if ((old_flags ^ flags) & IFF_UP) {
if (old_flags & IFF_UP)
__dev_close(dev);
else
ret = __dev_open(dev, extack);
}
if ((flags ^ dev->gflags) & IFF_PROMISC) {
int inc = (flags & IFF_PROMISC) ? 1 : -1;
old_flags = dev->flags;
dev->gflags ^= IFF_PROMISC;
if (__dev_set_promiscuity(dev, inc, false) >= 0)
if (dev->flags != old_flags)
dev_set_rx_mode(dev);
}
/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
* is important. Some (broken) drivers set IFF_PROMISC, when
* IFF_ALLMULTI is requested not asking us and not reporting.
*/
if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
dev->gflags ^= IFF_ALLMULTI;
netif_set_allmulti(dev, inc, false);
}
return ret;
}
void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
unsigned int gchanges, u32 portid,
const struct nlmsghdr *nlh)
{
unsigned int changes = dev->flags ^ old_flags;
if (gchanges)
rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh);
if (changes & IFF_UP) {
if (dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_UP, dev);
else
call_netdevice_notifiers(NETDEV_DOWN, dev);
}
if (dev->flags & IFF_UP &&
(changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
struct netdev_notifier_change_info change_info = {
.info = {
.dev = dev,
},
.flags_changed = changes,
};
call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info);
}
}
int netif_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack)
{
int ret;
unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
ret = __dev_change_flags(dev, flags, extack);
if (ret < 0)
return ret;
changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags);
__dev_notify_flags(dev, old_flags, changes, 0, NULL);
return ret;
}
int __dev_set_mtu(struct net_device *dev, int new_mtu)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_change_mtu)
return ops->ndo_change_mtu(dev, new_mtu);
/* Pairs with all the lockless reads of dev->mtu in the stack */
WRITE_ONCE(dev->mtu, new_mtu);
return 0;
}
EXPORT_SYMBOL(__dev_set_mtu);
int dev_validate_mtu(struct net_device *dev, int new_mtu,
struct netlink_ext_ack *extack)
{
/* MTU must be positive, and in range */
if (new_mtu < 0 || new_mtu < dev->min_mtu) {
NL_SET_ERR_MSG(extack, "mtu less than device minimum");
return -EINVAL;
}
if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
return -EINVAL;
}
return 0;
}
/**
* netif_set_mtu_ext - Change maximum transfer unit
* @dev: device
* @new_mtu: new transfer unit
* @extack: netlink extended ack
*
* Change the maximum transfer size of the network device.
*/
int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
struct netlink_ext_ack *extack)
{
int err, orig_mtu;
if (new_mtu == dev->mtu)
return 0;
err = dev_validate_mtu(dev, new_mtu, extack);
if (err)
return err;
if (!netif_device_present(dev))
return -ENODEV;
err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev);
err = notifier_to_errno(err);
if (err)
return err;
orig_mtu = dev->mtu;
err = __dev_set_mtu(dev, new_mtu);
if (!err) {
err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
orig_mtu);
err = notifier_to_errno(err);
if (err) {
/* setting mtu back and notifying everyone again,
* so that they have a chance to revert changes.
*/
__dev_set_mtu(dev, orig_mtu);
call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
new_mtu);
}
}
return err;
}
int netif_set_mtu(struct net_device *dev, int new_mtu)
{
struct netlink_ext_ack extack;
int err;
memset(&extack, 0, sizeof(extack));
err = netif_set_mtu_ext(dev, new_mtu, &extack);
if (err && extack._msg)
net_err_ratelimited("%s: %s\n", dev->name, extack._msg);
return err;
}
EXPORT_SYMBOL(netif_set_mtu);
int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
{
unsigned int orig_len = dev->tx_queue_len;
int res;
if (new_len != (unsigned int)new_len)
return -ERANGE;
if (new_len != orig_len) {
WRITE_ONCE(dev->tx_queue_len, new_len);
res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
res = notifier_to_errno(res);
if (res)
goto err_rollback;
res = dev_qdisc_change_tx_queue_len(dev);
if (res)
goto err_rollback;
}
return 0;
err_rollback:
netdev_err(dev, "refused to change device tx_queue_len\n");
WRITE_ONCE(dev->tx_queue_len, orig_len);
return res;
}
void netif_set_group(struct net_device *dev, int new_group)
{
dev->group = new_group;
}
/**
* dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
* @dev: device
* @addr: new address
* @extack: netlink extended ack
*/
int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_pre_changeaddr_info info = {
.info.dev = dev,
.info.extack = extack,
.dev_addr = addr,
};
int rc;
rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
return notifier_to_errno(rc);
}
EXPORT_SYMBOL(dev_pre_changeaddr_notify);
int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (!ops->ndo_set_mac_address)
return -EOPNOTSUPP;
if (sa->sa_family != dev->type)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
if (err)
return err;
if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) {
err = ops->ndo_set_mac_address(dev, sa);
if (err)
return err;
}
dev->addr_assign_type = NET_ADDR_SET;
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
return 0;
}
DECLARE_RWSEM(dev_addr_sem);
int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
{
size_t size = sizeof(sa->sa_data_min);
struct net_device *dev;
int ret = 0;
down_read(&dev_addr_sem);
rcu_read_lock();
dev = dev_get_by_name_rcu(net, dev_name);
if (!dev) {
ret = -ENODEV;
goto unlock;
}
if (!dev->addr_len)
memset(sa->sa_data, 0, size);
else
memcpy(sa->sa_data, dev->dev_addr,
min_t(size_t, size, dev->addr_len));
sa->sa_family = dev->type;
unlock:
rcu_read_unlock();
up_read(&dev_addr_sem);
return ret;
}
EXPORT_SYMBOL(dev_get_mac_address);
int netif_change_carrier(struct net_device *dev, bool new_carrier)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (!ops->ndo_change_carrier)
return -EOPNOTSUPP;
if (!netif_device_present(dev))
return -ENODEV;
return ops->ndo_change_carrier(dev, new_carrier);
}
/**
* dev_get_phys_port_id - Get device physical port ID
* @dev: device
* @ppid: port ID
*
* Get device physical port ID
*/
int dev_get_phys_port_id(struct net_device *dev,
struct netdev_phys_item_id *ppid)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (!ops->ndo_get_phys_port_id)
return -EOPNOTSUPP;
return ops->ndo_get_phys_port_id(dev, ppid);
}
/**
* dev_get_phys_port_name - Get device physical port name
* @dev: device
* @name: port name
* @len: limit of bytes to copy to name
*
* Get device physical port name
*/
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (ops->ndo_get_phys_port_name) {
err = ops->ndo_get_phys_port_name(dev, name, len);
if (err != -EOPNOTSUPP)
return err;
}
return devlink_compat_phys_port_name_get(dev, name, len);
}
/**
* dev_get_port_parent_id - Get the device's port parent identifier
* @dev: network device
* @ppid: pointer to a storage for the port's parent identifier
* @recurse: allow/disallow recursion to lower devices
*
* Get the devices's port parent identifier
*/
int dev_get_port_parent_id(struct net_device *dev,
struct netdev_phys_item_id *ppid,
bool recurse)
{
const struct net_device_ops *ops = dev->netdev_ops;
struct netdev_phys_item_id first = { };
struct net_device *lower_dev;
struct list_head *iter;
int err;
if (ops->ndo_get_port_parent_id) {
err = ops->ndo_get_port_parent_id(dev, ppid);
if (err != -EOPNOTSUPP)
return err;
}
err = devlink_compat_switch_id_get(dev, ppid);
if (!recurse || err != -EOPNOTSUPP)
return err;
netdev_for_each_lower_dev(dev, lower_dev, iter) {
err = dev_get_port_parent_id(lower_dev, ppid, true);
if (err)
break;
if (!first.id_len)
first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid)))
return -EOPNOTSUPP;
}
return err;
}
EXPORT_SYMBOL(dev_get_port_parent_id);
/**
* netdev_port_same_parent_id - Indicate if two network devices have
* the same port parent identifier
* @a: first network device
* @b: second network device
*/
bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
{
struct netdev_phys_item_id a_id = { };
struct netdev_phys_item_id b_id = { };
if (dev_get_port_parent_id(a, &a_id, true) ||
dev_get_port_parent_id(b, &b_id, true))
return false;
return netdev_phys_item_id_same(&a_id, &b_id);
}
EXPORT_SYMBOL(netdev_port_same_parent_id);
int netif_change_proto_down(struct net_device *dev, bool proto_down)
{
if (!dev->change_proto_down)
return -EOPNOTSUPP;
if (!netif_device_present(dev))
return -ENODEV;
if (proto_down)
netif_carrier_off(dev);
else
netif_carrier_on(dev);
WRITE_ONCE(dev->proto_down, proto_down);
return 0;
}
/**
* netdev_change_proto_down_reason_locked - proto down reason
*
* @dev: device
* @mask: proto down mask
* @value: proto down value
*/
void netdev_change_proto_down_reason_locked(struct net_device *dev,
unsigned long mask, u32 value)
{
u32 proto_down_reason;
int b;
if (!mask) {
proto_down_reason = value;
} else {
proto_down_reason = dev->proto_down_reason;
for_each_set_bit(b, &mask, 32) {
if (value & (1 << b))
proto_down_reason |= BIT(b);
else
proto_down_reason &= ~BIT(b);
}
}
WRITE_ONCE(dev->proto_down_reason, proto_down_reason);
}
struct bpf_xdp_link {
struct bpf_link link;
struct net_device *dev; /* protected by rtnl_lock, no refcnt held */
int flags;
};
static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags)
{
if (flags & XDP_FLAGS_HW_MODE)
return XDP_MODE_HW;
if (flags & XDP_FLAGS_DRV_MODE)
return XDP_MODE_DRV;
if (flags & XDP_FLAGS_SKB_MODE)
return XDP_MODE_SKB;
return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB;
}
static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
{
switch (mode) {
case XDP_MODE_SKB:
return generic_xdp_install;
case XDP_MODE_DRV:
case XDP_MODE_HW:
return dev->netdev_ops->ndo_bpf;
default:
return NULL;
}
}
static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
enum bpf_xdp_mode mode)
{
return dev->xdp_state[mode].link;
}
static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
enum bpf_xdp_mode mode)
{
struct bpf_xdp_link *link = dev_xdp_link(dev, mode);
if (link)
return link->link.prog;
return dev->xdp_state[mode].prog;
}
u8 dev_xdp_prog_count(struct net_device *dev)
{
u8 count = 0;
int i;
for (i = 0; i < __MAX_XDP_MODE; i++)
if (dev->xdp_state[i].prog || dev->xdp_state[i].link)
count++;
return count;
}
EXPORT_SYMBOL_GPL(dev_xdp_prog_count);
u8 dev_xdp_sb_prog_count(struct net_device *dev)
{
u8 count = 0;
int i;
for (i = 0; i < __MAX_XDP_MODE; i++)
if (dev->xdp_state[i].prog &&
!dev->xdp_state[i].prog->aux->xdp_has_frags)
count++;
return count;
}
int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
{
if (!dev->netdev_ops->ndo_bpf)
return -EOPNOTSUPP;
if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
bpf->command == XDP_SETUP_PROG &&
bpf->prog && !bpf->prog->aux->xdp_has_frags) {
NL_SET_ERR_MSG(bpf->extack,
"unable to propagate XDP to device using tcp-data-split");
return -EBUSY;
}
if (dev_get_min_mp_channel_count(dev)) {
NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider");
return -EBUSY;
}
return dev->netdev_ops->ndo_bpf(dev, bpf);
}
u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
{
struct bpf_prog *prog = dev_xdp_prog(dev, mode);
return prog ? prog->aux->id : 0;
}
static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode,
struct bpf_xdp_link *link)
{
dev->xdp_state[mode].link = link;
dev->xdp_state[mode].prog = NULL;
}
static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
struct bpf_prog *prog)
{
dev->xdp_state[mode].link = NULL;
dev->xdp_state[mode].prog = prog;
}
static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
bpf_op_t bpf_op, struct netlink_ext_ack *extack,
u32 flags, struct bpf_prog *prog)
{
struct netdev_bpf xdp;
int err;
netdev_ops_assert_locked(dev);
if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
prog && !prog->aux->xdp_has_frags) {
NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split");
return -EBUSY;
}
if (dev_get_min_mp_channel_count(dev)) {
NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider");
return -EBUSY;
}
memset(&xdp, 0, sizeof(xdp));
xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG;
xdp.extack = extack;
xdp.flags = flags;
xdp.prog = prog;
/* Drivers assume refcnt is already incremented (i.e, prog pointer is
* "moved" into driver), so they don't increment it on their own, but
* they do decrement refcnt when program is detached or replaced.
* Given net_device also owns link/prog, we need to bump refcnt here
* to prevent drivers from underflowing it.
*/
if (prog)
bpf_prog_inc(prog);
err = bpf_op(dev, &xdp);
if (err) {
if (prog)
bpf_prog_put(prog);
return err;
}
if (mode != XDP_MODE_HW)
bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog);
return 0;
}
static void dev_xdp_uninstall(struct net_device *dev)
{
struct bpf_xdp_link *link;
struct bpf_prog *prog;
enum bpf_xdp_mode mode;
bpf_op_t bpf_op;
ASSERT_RTNL();
for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) {
prog = dev_xdp_prog(dev, mode);
if (!prog)
continue;
bpf_op = dev_xdp_bpf_op(dev, mode);
if (!bpf_op)
continue;
WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
/* auto-detach link from net device */
link = dev_xdp_link(dev, mode);
if (link)
link->dev = NULL;
else
bpf_prog_put(prog);
dev_xdp_set_link(dev, mode, NULL);
}
}
static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack,
struct bpf_xdp_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog, u32 flags)
{
unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES);
struct bpf_prog *cur_prog;
struct net_device *upper;
struct list_head *iter;
enum bpf_xdp_mode mode;
bpf_op_t bpf_op;
int err;
ASSERT_RTNL();
/* either link or prog attachment, never both */
if (link && (new_prog || old_prog))
return -EINVAL;
/* link supports only XDP mode flags */
if (link && (flags & ~XDP_FLAGS_MODES)) {
NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment");
return -EINVAL;
}
/* just one XDP mode bit should be set, zero defaults to drv/skb mode */
if (num_modes > 1) {
NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
return -EINVAL;
}
/* avoid ambiguity if offload + drv/skb mode progs are both loaded */
if (!num_modes && dev_xdp_prog_count(dev) > 1) {
NL_SET_ERR_MSG(extack,
"More than one program loaded, unset mode is ambiguous");
return -EINVAL;
}
/* old_prog != NULL implies XDP_FLAGS_REPLACE is set */
if (old_prog && !(flags & XDP_FLAGS_REPLACE)) {
NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified");
return -EINVAL;
}
mode = dev_xdp_mode(dev, flags);
/* can't replace attached link */
if (dev_xdp_link(dev, mode)) {
NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
return -EBUSY;
}
/* don't allow if an upper device already has a program */
netdev_for_each_upper_dev_rcu(dev, upper, iter) {
if (dev_xdp_prog_count(upper) > 0) {
NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program");
return -EEXIST;
}
}
cur_prog = dev_xdp_prog(dev, mode);
/* can't replace attached prog with link */
if (link && cur_prog) {
NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link");
return -EBUSY;
}
if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) {
NL_SET_ERR_MSG(extack, "Active program does not match expected");
return -EEXIST;
}
/* put effective new program into new_prog */
if (link)
new_prog = link->link.prog;
if (new_prog) {
bool offload = mode == XDP_MODE_HW;
enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
? XDP_MODE_DRV : XDP_MODE_SKB;
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
NL_SET_ERR_MSG(extack, "XDP program already attached");
return -EBUSY;
}
if (!offload && dev_xdp_prog(dev, other_mode)) {
NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
return -EEXIST;
}
if (!offload && bpf_prog_is_offloaded(new_prog->aux)) {
NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported");
return -EINVAL;
}
if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) {
NL_SET_ERR_MSG(extack, "Program bound to different device");
return -EINVAL;
}
if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) {
NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode");
return -EINVAL;
}
if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) {
NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
return -EINVAL;
}
if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) {
NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device");
return -EINVAL;
}
}
/* don't call drivers if the effective program didn't change */
if (new_prog != cur_prog) {
bpf_op = dev_xdp_bpf_op(dev, mode);
if (!bpf_op) {
NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode");
return -EOPNOTSUPP;
}
err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog);
if (err)
return err;
}
if (link)
dev_xdp_set_link(dev, mode, link);
else
dev_xdp_set_prog(dev, mode, new_prog);
if (cur_prog)
bpf_prog_put(cur_prog);
return 0;
}
static int dev_xdp_attach_link(struct net_device *dev,
struct netlink_ext_ack *extack,
struct bpf_xdp_link *link)
{
return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags);
}
static int dev_xdp_detach_link(struct net_device *dev,
struct netlink_ext_ack *extack,
struct bpf_xdp_link *link)
{
enum bpf_xdp_mode mode;
bpf_op_t bpf_op;
ASSERT_RTNL();
mode = dev_xdp_mode(dev, link->flags);
if (dev_xdp_link(dev, mode) != link)
return -EINVAL;
bpf_op = dev_xdp_bpf_op(dev, mode);
WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
dev_xdp_set_link(dev, mode, NULL);
return 0;
}
static void bpf_xdp_link_release(struct bpf_link *link)
{
struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
rtnl_lock();
/* if racing with net_device's tear down, xdp_link->dev might be
* already NULL, in which case link was already auto-detached
*/
if (xdp_link->dev) {
netdev_lock_ops(xdp_link->dev);
WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
netdev_unlock_ops(xdp_link->dev);
xdp_link->dev = NULL;
}
rtnl_unlock();
}
static int bpf_xdp_link_detach(struct bpf_link *link)
{
bpf_xdp_link_release(link);
return 0;
}
static void bpf_xdp_link_dealloc(struct bpf_link *link)
{
struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
kfree(xdp_link);
}
static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link,
struct seq_file *seq)
{
struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
u32 ifindex = 0;
rtnl_lock();
if (xdp_link->dev)
ifindex = xdp_link->dev->ifindex;
rtnl_unlock();
seq_printf(seq, "ifindex:\t%u\n", ifindex);
}
static int bpf_xdp_link_fill_link_info(const struct bpf_link *link,
struct bpf_link_info *info)
{
struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
u32 ifindex = 0;
rtnl_lock();
if (xdp_link->dev)
ifindex = xdp_link->dev->ifindex;
rtnl_unlock();
info->xdp.ifindex = ifindex;
return 0;
}
static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog)
{
struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
enum bpf_xdp_mode mode;
bpf_op_t bpf_op;
int err = 0;
rtnl_lock();
/* link might have been auto-released already, so fail */
if (!xdp_link->dev) {
err = -ENOLINK;
goto out_unlock;
}
if (old_prog && link->prog != old_prog) {
err = -EPERM;
goto out_unlock;
}
old_prog = link->prog;
if (old_prog->type != new_prog->type ||
old_prog->expected_attach_type != new_prog->expected_attach_type) {
err = -EINVAL;
goto out_unlock;
}
if (old_prog == new_prog) {
/* no-op, don't disturb drivers */
bpf_prog_put(new_prog);
goto out_unlock;
}
netdev_lock_ops(xdp_link->dev);
mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags);
bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode);
err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL,
xdp_link->flags, new_prog);
netdev_unlock_ops(xdp_link->dev);
if (err)
goto out_unlock;
old_prog = xchg(&link->prog, new_prog);
bpf_prog_put(old_prog);
out_unlock:
rtnl_unlock();
return err;
}
static const struct bpf_link_ops bpf_xdp_link_lops = {
.release = bpf_xdp_link_release,
.dealloc = bpf_xdp_link_dealloc,
.detach = bpf_xdp_link_detach,
.show_fdinfo = bpf_xdp_link_show_fdinfo,
.fill_link_info = bpf_xdp_link_fill_link_info,
.update_prog = bpf_xdp_link_update,
};
int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct net *net = current->nsproxy->net_ns;
struct bpf_link_primer link_primer;
struct netlink_ext_ack extack = {};
struct bpf_xdp_link *link;
struct net_device *dev;
int err, fd;
rtnl_lock();
dev = dev_get_by_index(net, attr->link_create.target_ifindex);
if (!dev) {
rtnl_unlock();
return -EINVAL;
}
link = kzalloc(sizeof(*link), GFP_USER);
if (!link) {
err = -ENOMEM;
goto unlock;
}
bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
link->dev = dev;
link->flags = attr->link_create.flags;
err = bpf_link_prime(&link->link, &link_primer);
if (err) {
kfree(link);
goto unlock;
}
netdev_lock_ops(dev);
err = dev_xdp_attach_link(dev, &extack, link);
netdev_unlock_ops(dev);
rtnl_unlock();
if (err) {
link->dev = NULL;
bpf_link_cleanup(&link_primer);
trace_bpf_xdp_link_attach_failed(extack._msg);
goto out_put_dev;
}
fd = bpf_link_settle(&link_primer);
/* link itself doesn't hold dev's refcnt to not complicate shutdown */
dev_put(dev);
return fd;
unlock:
rtnl_unlock();
out_put_dev:
dev_put(dev);
return err;
}
/**
* dev_change_xdp_fd - set or clear a bpf program for a device rx path
* @dev: device
* @extack: netlink extended ack
* @fd: new program fd or negative value to clear
* @expected_fd: old program fd that userspace expects to replace or clear
* @flags: xdp-related flags
*
* Set or clear a bpf program for a device
*/
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, int expected_fd, u32 flags)
{
enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags);
struct bpf_prog *new_prog = NULL, *old_prog = NULL;
int err;
ASSERT_RTNL();
if (fd >= 0) {
new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
mode != XDP_MODE_SKB);
if (IS_ERR(new_prog))
return PTR_ERR(new_prog);
}
if (expected_fd >= 0) {
old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP,
mode != XDP_MODE_SKB);
if (IS_ERR(old_prog)) {
err = PTR_ERR(old_prog);
old_prog = NULL;
goto err_out;
}
}
err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags);
err_out:
if (err && new_prog)
bpf_prog_put(new_prog);
if (old_prog)
bpf_prog_put(old_prog);
return err;
}
u32 dev_get_min_mp_channel_count(const struct net_device *dev)
{
int i;
netdev_ops_assert_locked(dev);
for (i = dev->real_num_rx_queues - 1; i >= 0; i--)
if (dev->_rx[i].mp_params.mp_priv)
/* The channel count is the idx plus 1. */
return i + 1;
return 0;
}
/**
* dev_index_reserve() - allocate an ifindex in a namespace
* @net: the applicable net namespace
* @ifindex: requested ifindex, pass %0 to get one allocated
*
* Allocate a ifindex for a new device. Caller must either use the ifindex
* to store the device (via list_netdevice()) or call dev_index_release()
* to give the index up.
*
* Return: a suitable unique value for a new device interface number or -errno.
*/
static int dev_index_reserve(struct net *net, u32 ifindex)
{
int err;
if (ifindex > INT_MAX) {
DEBUG_NET_WARN_ON_ONCE(1);
return -EINVAL;
}
if (!ifindex)
err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL,
xa_limit_31b, &net->ifindex, GFP_KERNEL);
else
err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL);
if (err < 0)
return err;
return ifindex;
}
static void dev_index_release(struct net *net, int ifindex)
{
/* Expect only unused indexes, unlist_netdevice() removes the used */
WARN_ON(xa_erase(&net->dev_by_index, ifindex));
}
static bool from_cleanup_net(void)
{
#ifdef CONFIG_NET_NS
return current == cleanup_net_task;
#else
return false;
#endif
}
/* Delayed registration/unregisteration */
LIST_HEAD(net_todo_list);
DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
atomic_t dev_unreg_count = ATOMIC_INIT(0);
static void net_set_todo(struct net_device *dev)
{
list_add_tail(&dev->todo_list, &net_todo_list);
}
static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
struct net_device *upper, netdev_features_t features)
{
netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES;
netdev_features_t feature;
int feature_bit;
for_each_netdev_feature(upper_disables, feature_bit) {
feature = __NETIF_F_BIT(feature_bit);
if (!(upper->wanted_features & feature)
&& (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n",
&feature, upper->name);
features &= ~feature;
}
}
return features;
}
static void netdev_sync_lower_features(struct net_device *upper,
struct net_device *lower, netdev_features_t features)
{
netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES;
netdev_features_t feature;
int feature_bit;
for_each_netdev_feature(upper_disables, feature_bit) {
feature = __NETIF_F_BIT(feature_bit);
if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
&feature, lower->name);
lower->wanted_features &= ~feature;
__netdev_update_features(lower);
if (unlikely(lower->features & feature))
netdev_WARN(upper, "failed to disable %pNF on %s!\n",
&feature, lower->name);
else
netdev_features_change(lower);
}
}
}
static bool netdev_has_ip_or_hw_csum(netdev_features_t features)
{
netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
bool ip_csum = (features & ip_csum_mask) == ip_csum_mask;
bool hw_csum = features & NETIF_F_HW_CSUM;
return ip_csum || hw_csum;
}
static netdev_features_t netdev_fix_features(struct net_device *dev,
netdev_features_t features)
{
/* Fix illegal checksum combinations */
if ((features & NETIF_F_HW_CSUM) &&
(features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
netdev_warn(dev, "mixed HW and IP checksum settings.\n");
features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
/* TSO requires that SG is present as well. */
if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n");
features &= ~NETIF_F_ALL_TSO;
}
if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) &&
!(features & NETIF_F_IP_CSUM)) {
netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n");
features &= ~NETIF_F_TSO;
features &= ~NETIF_F_TSO_ECN;
}
if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) &&
!(features & NETIF_F_IPV6_CSUM)) {
netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n");
features &= ~NETIF_F_TSO6;
}
/* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */
if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO))
features &= ~NETIF_F_TSO_MANGLEID;
/* TSO ECN requires that TSO is present as well. */
if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
features &= ~NETIF_F_TSO_ECN;
/* Software GSO depends on SG. */
if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
features &= ~NETIF_F_GSO;
}
/* GSO partial features require GSO partial be set */
if ((features & dev->gso_partial_features) &&
!(features & NETIF_F_GSO_PARTIAL)) {
netdev_dbg(dev,
"Dropping partially supported GSO features since no GSO partial.\n");
features &= ~dev->gso_partial_features;
}
if (!(features & NETIF_F_RXCSUM)) {
/* NETIF_F_GRO_HW implies doing RXCSUM since every packet
* successfully merged by hardware must also have the
* checksum verified by hardware. If the user does not
* want to enable RXCSUM, logically, we should disable GRO_HW.
*/
if (features & NETIF_F_GRO_HW) {
netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n");
features &= ~NETIF_F_GRO_HW;
}
}
/* LRO/HW-GRO features cannot be combined with RX-FCS */
if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n");
features &= ~NETIF_F_LRO;
}
if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n");
features &= ~NETIF_F_GRO_HW;
}
}
if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n");
features &= ~NETIF_F_LRO;
}
if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
features &= ~NETIF_F_HW_TLS_TX;
}
if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n");
features &= ~NETIF_F_HW_TLS_RX;
}
if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n");
features &= ~NETIF_F_GSO_UDP_L4;
}
return features;
}
int __netdev_update_features(struct net_device *dev)
{
struct net_device *upper, *lower;
netdev_features_t features;
struct list_head *iter;
int err = -1;
ASSERT_RTNL(); netdev_ops_assert_locked(dev);
features = netdev_get_wanted_features(dev);
if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features);
/* driver might be less strict about feature dependencies */
features = netdev_fix_features(dev, features);
/* some features can't be enabled if they're off on an upper device */
netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features)
goto sync_lower;
netdev_dbg(dev, "Features changed: %pNF -> %pNF\n",
&dev->features, &features);
if (dev->netdev_ops->ndo_set_features)
err = dev->netdev_ops->ndo_set_features(dev, features);
else
err = 0;
if (unlikely(err < 0)) { netdev_err(dev,
"set_features() failed (%d); wanted %pNF, left %pNF\n",
err, &features, &dev->features);
/* return non-0 since some features might have changed and
* it's better to fire a spurious notification than miss it
*/
return -1;
}
sync_lower:
/* some features must be disabled on lower devices when disabled
* on an upper device (think: bonding master or bridge)
*/
netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) {
netdev_features_t diff = features ^ dev->features;
if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) {
/* udp_tunnel_{get,drop}_rx_info both need
* NETIF_F_RX_UDP_TUNNEL_PORT enabled on the
* device, or they won't do anything.
* Thus we need to update dev->features
* *before* calling udp_tunnel_get_rx_info,
* but *after* calling udp_tunnel_drop_rx_info.
*/
if (features & NETIF_F_RX_UDP_TUNNEL_PORT) {
dev->features = features;
udp_tunnel_get_rx_info(dev);
} else {
udp_tunnel_drop_rx_info(dev);
}
}
if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) {
if (features & NETIF_F_HW_VLAN_CTAG_FILTER) {
dev->features = features;
err |= vlan_get_rx_ctag_filter_info(dev);
} else {
vlan_drop_rx_ctag_filter_info(dev);
}
}
if (diff & NETIF_F_HW_VLAN_STAG_FILTER) {
if (features & NETIF_F_HW_VLAN_STAG_FILTER) {
dev->features = features;
err |= vlan_get_rx_stag_filter_info(dev);
} else {
vlan_drop_rx_stag_filter_info(dev);
}
}
dev->features = features;
}
return err < 0 ? 0 : 1;
}
/**
* netdev_update_features - recalculate device features
* @dev: the device to check
*
* Recalculate dev->features set and send notifications if it
* has changed. Should be called after driver or hardware dependent
* conditions might have changed that influence the features.
*/
void netdev_update_features(struct net_device *dev)
{ if (__netdev_update_features(dev)) netdev_features_change(dev);
}
EXPORT_SYMBOL(netdev_update_features);
/**
* netdev_change_features - recalculate device features
* @dev: the device to check
*
* Recalculate dev->features set and send notifications even
* if they have not changed. Should be called instead of
* netdev_update_features() if also dev->vlan_features might
* have changed to allow the changes to be propagated to stacked
* VLAN devices.
*/
void netdev_change_features(struct net_device *dev)
{
__netdev_update_features(dev);
netdev_features_change(dev);
}
EXPORT_SYMBOL(netdev_change_features);
/**
* netif_stacked_transfer_operstate - transfer operstate
* @rootdev: the root or lower level device to transfer state from
* @dev: the device to transfer operstate to
*
* Transfer operational state from root to device. This is normally
* called when a stacking relationship exists between the root
* device and the device(a leaf device).
*/
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev)
{
if (rootdev->operstate == IF_OPER_DORMANT)
netif_dormant_on(dev);
else
netif_dormant_off(dev);
if (rootdev->operstate == IF_OPER_TESTING)
netif_testing_on(dev);
else
netif_testing_off(dev);
if (netif_carrier_ok(rootdev))
netif_carrier_on(dev);
else
netif_carrier_off(dev);
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
static int netif_alloc_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
struct netdev_rx_queue *rx;
size_t sz = count * sizeof(*rx);
int err = 0;
BUG_ON(count < 1);
rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
if (!rx)
return -ENOMEM;
dev->_rx = rx;
for (i = 0; i < count; i++) {
rx[i].dev = dev;
/* XDP RX-queue setup */
err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
if (err < 0)
goto err_rxq_info;
}
return 0;
err_rxq_info:
/* Rollback successful reg's and free other resources */
while (i--)
xdp_rxq_info_unreg(&rx[i].xdp_rxq);
kvfree(dev->_rx);
dev->_rx = NULL;
return err;
}
static void netif_free_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
/* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */
if (!dev->_rx)
return;
for (i = 0; i < count; i++)
xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq);
kvfree(dev->_rx);
}
static void netdev_init_one_queue(struct net_device *dev,
struct netdev_queue *queue, void *_unused)
{
/* Initialize queue lock */
spin_lock_init(&queue->_xmit_lock);
netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
queue->xmit_lock_owner = -1;
netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
queue->dev = dev;
#ifdef CONFIG_BQL
dql_init(&queue->dql, HZ);
#endif
}
static void netif_free_tx_queues(struct net_device *dev)
{
kvfree(dev->_tx);
}
static int netif_alloc_netdev_queues(struct net_device *dev)
{
unsigned int count = dev->num_tx_queues;
struct netdev_queue *tx;
size_t sz = count * sizeof(*tx);
if (count < 1 || count > 0xffff)
return -EINVAL;
tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
if (!tx)
return -ENOMEM;
dev->_tx = tx;
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
spin_lock_init(&dev->tx_global_lock);
return 0;
}
void netif_tx_stop_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_stop_queue(txq);
}
}
EXPORT_SYMBOL(netif_tx_stop_all_queues);
static int netdev_do_alloc_pcpu_stats(struct net_device *dev)
{
void __percpu *v;
/* Drivers implementing ndo_get_peer_dev must support tstat
* accounting, so that skb_do_redirect() can bump the dev's
* RX stats upon network namespace switch.
*/
if (dev->netdev_ops->ndo_get_peer_dev &&
dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS)
return -EOPNOTSUPP;
switch (dev->pcpu_stat_type) {
case NETDEV_PCPU_STAT_NONE:
return 0;
case NETDEV_PCPU_STAT_LSTATS:
v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
break;
case NETDEV_PCPU_STAT_TSTATS:
v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
break;
case NETDEV_PCPU_STAT_DSTATS:
v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
break;
default:
return -EINVAL;
}
return v ? 0 : -ENOMEM;
}
static void netdev_do_free_pcpu_stats(struct net_device *dev)
{
switch (dev->pcpu_stat_type) {
case NETDEV_PCPU_STAT_NONE:
return;
case NETDEV_PCPU_STAT_LSTATS:
free_percpu(dev->lstats);
break;
case NETDEV_PCPU_STAT_TSTATS:
free_percpu(dev->tstats);
break;
case NETDEV_PCPU_STAT_DSTATS:
free_percpu(dev->dstats);
break;
}
}
static void netdev_free_phy_link_topology(struct net_device *dev)
{
struct phy_link_topology *topo = dev->link_topo;
if (IS_ENABLED(CONFIG_PHYLIB) && topo) {
xa_destroy(&topo->phys);
kfree(topo);
dev->link_topo = NULL;
}
}
/**
* register_netdevice() - register a network device
* @dev: device to register
*
* Take a prepared network device structure and make it externally accessible.
* A %NETDEV_REGISTER message is sent to the netdev notifier chain.
* Callers must hold the rtnl lock - you may want register_netdev()
* instead of this.
*/
int register_netdevice(struct net_device *dev)
{
int ret;
struct net *net = dev_net(dev);
BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE <
NETDEV_FEATURE_COUNT);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
might_sleep();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
BUG_ON(!net);
ret = ethtool_check_ops(dev->ethtool_ops);
if (ret)
return ret;
/* rss ctx ID 0 is reserved for the default context, start from 1 */
xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1);
mutex_init(&dev->ethtool->rss_lock);
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
ret = dev_get_valid_name(net, dev, dev->name);
if (ret < 0)
goto out;
ret = -ENOMEM;
dev->name_node = netdev_name_node_head_alloc(dev);
if (!dev->name_node)
goto out;
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
goto err_free_name;
}
}
if (((dev->hw_features | dev->features) &
NETIF_F_HW_VLAN_CTAG_FILTER) &&
(!dev->netdev_ops->ndo_vlan_rx_add_vid ||
!dev->netdev_ops->ndo_vlan_rx_kill_vid)) {
netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n");
ret = -EINVAL;
goto err_uninit;
}
ret = netdev_do_alloc_pcpu_stats(dev);
if (ret)
goto err_uninit;
ret = dev_index_reserve(net, dev->ifindex);
if (ret < 0)
goto err_free_pcpu;
dev->ifindex = ret;
/* Transfer changeable features to wanted_features and enable
* software offloads (GSO and GRO).
*/
dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF);
dev->features |= NETIF_F_SOFT_FEATURES;
if (dev->udp_tunnel_nic_info) {
dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT;
dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT;
}
dev->wanted_features = dev->features & dev->hw_features;
if (!(dev->flags & IFF_LOOPBACK))
dev->hw_features |= NETIF_F_NOCACHE_COPY;
/* If IPv4 TCP segmentation offload is supported we should also
* allow the device to enable segmenting the frame with the option
* of ignoring a static IP ID value. This doesn't enable the
* feature itself but allows the user to enable it later.
*/
if (dev->hw_features & NETIF_F_TSO)
dev->hw_features |= NETIF_F_TSO_MANGLEID;
if (dev->vlan_features & NETIF_F_TSO)
dev->vlan_features |= NETIF_F_TSO_MANGLEID;
if (dev->mpls_features & NETIF_F_TSO)
dev->mpls_features |= NETIF_F_TSO_MANGLEID;
if (dev->hw_enc_features & NETIF_F_TSO)
dev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
*/
dev->vlan_features |= NETIF_F_HIGHDMA;
/* Make NETIF_F_SG inheritable to tunnel devices.
*/
dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL;
/* Make NETIF_F_SG inheritable to MPLS.
*/
dev->mpls_features |= NETIF_F_SG;
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
goto err_ifindex_release;
ret = netdev_register_kobject(dev);
netdev_lock(dev);
WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED);
netdev_unlock(dev);
if (ret)
goto err_uninit_notify;
netdev_lock_ops(dev);
__netdev_update_features(dev);
netdev_unlock_ops(dev);
/*
* Default initial state at registry is that the
* device is present.
*/
set_bit(__LINK_STATE_PRESENT, &dev->state);
linkwatch_init_dev(dev);
dev_init_scheduler(dev);
netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL);
list_netdevice(dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
/* If the device has permanent device address, driver should
* set dev_addr and also addr_assign_type should be set to
* NET_ADDR_PERM (default value).
*/
if (dev->addr_assign_type == NET_ADDR_PERM)
memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
/* Notify protocols, that a new device appeared. */
netdev_lock_ops(dev);
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
netdev_unlock_ops(dev);
ret = notifier_to_errno(ret);
if (ret) {
/* Expect explicit free_netdev() on failure */
dev->needs_free_netdev = false;
unregister_netdevice_queue(dev, NULL);
goto out;
}
/*
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
out:
return ret;
err_uninit_notify:
call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
err_ifindex_release:
dev_index_release(net, dev->ifindex);
err_free_pcpu:
netdev_do_free_pcpu_stats(dev);
err_uninit:
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
if (dev->priv_destructor)
dev->priv_destructor(dev);
err_free_name:
netdev_name_node_free(dev->name_node);
goto out;
}
EXPORT_SYMBOL(register_netdevice);
/* Initialize the core of a dummy net device.
* The setup steps dummy netdevs need which normal netdevs get by going
* through register_netdevice().
*/
static void init_dummy_netdev(struct net_device *dev)
{
/* make sure we BUG if trying to hit standard
* register/unregister code path
*/
dev->reg_state = NETREG_DUMMY;
/* a dummy interface is started by default */
set_bit(__LINK_STATE_PRESENT, &dev->state);
set_bit(__LINK_STATE_START, &dev->state);
/* Note : We dont allocate pcpu_refcnt for dummy devices,
* because users of this 'device' dont need to change
* its refcount.
*/
}
/**
* register_netdev - register a network device
* @dev: device to register
*
* Take a completed network device structure and add it to the kernel
* interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
* chain. 0 is returned on success. A negative errno code is returned
* on a failure to set up the device, or if the name is a duplicate.
*
* This is a wrapper around register_netdevice that takes the rtnl semaphore
* and expands the device name if you passed a format string to
* alloc_netdev.
*/
int register_netdev(struct net_device *dev)
{
struct net *net = dev_net(dev);
int err;
if (rtnl_net_lock_killable(net))
return -EINTR;
err = register_netdevice(dev);
rtnl_net_unlock(net);
return err;
}
EXPORT_SYMBOL(register_netdev);
int netdev_refcnt_read(const struct net_device *dev)
{
#ifdef CONFIG_PCPU_DEV_REFCNT
int i, refcnt = 0;
for_each_possible_cpu(i)
refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i);
return refcnt;
#else
return refcount_read(&dev->dev_refcnt);
#endif
}
EXPORT_SYMBOL(netdev_refcnt_read);
int netdev_unregister_timeout_secs __read_mostly = 10;
#define WAIT_REFS_MIN_MSECS 1
#define WAIT_REFS_MAX_MSECS 250
/**
* netdev_wait_allrefs_any - wait until all references are gone.
* @list: list of net_devices to wait on
*
* This is called when unregistering network devices.
*
* Any protocol or device that holds a reference should register
* for netdevice notification, and cleanup and put back the
* reference if they receive an UNREGISTER event.
* We can get stuck here if buggy protocols don't correctly
* call dev_put.
*/
static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
{
unsigned long rebroadcast_time, warning_time;
struct net_device *dev;
int wait = 0;
rebroadcast_time = warning_time = jiffies;
list_for_each_entry(dev, list, todo_list)
if (netdev_refcnt_read(dev) == 1)
return dev;
while (true) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
rtnl_lock();
/* Rebroadcast unregister notification */
list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
__rtnl_unlock();
rcu_barrier();
rtnl_lock();
list_for_each_entry(dev, list, todo_list)
if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
&dev->state)) {
/* We must not have linkwatch events
* pending on unregister. If this
* happens, we simply run the queue
* unscheduled, resulting in a noop
* for this device.
*/
linkwatch_run_queue();
break;
}
__rtnl_unlock();
rebroadcast_time = jiffies;
}
rcu_barrier();
if (!wait) {
wait = WAIT_REFS_MIN_MSECS;
} else {
msleep(wait);
wait = min(wait << 1, WAIT_REFS_MAX_MSECS);
}
list_for_each_entry(dev, list, todo_list)
if (netdev_refcnt_read(dev) == 1)
return dev;
if (time_after(jiffies, warning_time +
READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
list_for_each_entry(dev, list, todo_list) {
pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
dev->name, netdev_refcnt_read(dev));
ref_tracker_dir_print(&dev->refcnt_tracker, 10);
}
warning_time = jiffies;
}
}
}
/* The sequence is:
*
* rtnl_lock();
* ...
* register_netdevice(x1);
* register_netdevice(x2);
* ...
* unregister_netdevice(y1);
* unregister_netdevice(y2);
* ...
* rtnl_unlock();
* free_netdev(y1);
* free_netdev(y2);
*
* We are invoked by rtnl_unlock().
* This allows us to deal with problems:
* 1) We can delete sysfs objects which invoke hotplug
* without deadlocking with linkwatch via keventd.
* 2) Since we run with the RTNL semaphore not held, we can sleep
* safely in order to wait for the netdev refcnt to drop to zero.
*
* We must not return until all unregister events added during
* the interval the lock was held have been completed.
*/
void netdev_run_todo(void)
{
struct net_device *dev, *tmp;
struct list_head list;
int cnt;
#ifdef CONFIG_LOCKDEP
struct list_head unlink_list;
list_replace_init(&net_unlink_list, &unlink_list);
while (!list_empty(&unlink_list)) {
dev = list_first_entry(&unlink_list, struct net_device,
unlink_list);
list_del_init(&dev->unlink_list);
dev->nested_level = dev->lower_level - 1;
}
#endif
/* Snapshot list, allow later requests */
list_replace_init(&net_todo_list, &list);
__rtnl_unlock();
/* Wait for rcu callbacks to finish before next phase */
if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) {
if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list);
continue;
}
netdev_lock(dev);
WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED);
netdev_unlock(dev);
linkwatch_sync_dev(dev);
}
cnt = 0;
while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list);
/* paranoia */
BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev);
cnt++;
/* Free network device */
kobject_put(&dev->dev.kobj);
}
if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) wake_up(&netdev_unregistering_wq);
}
/* Collate per-cpu network dstats statistics
*
* Read per-cpu network statistics from dev->dstats and populate the related
* fields in @s.
*/
static void dev_fetch_dstats(struct rtnl_link_stats64 *s,
const struct pcpu_dstats __percpu *dstats)
{
int cpu;
for_each_possible_cpu(cpu) {
u64 rx_packets, rx_bytes, rx_drops;
u64 tx_packets, tx_bytes, tx_drops;
const struct pcpu_dstats *stats;
unsigned int start;
stats = per_cpu_ptr(dstats, cpu);
do {
start = u64_stats_fetch_begin(&stats->syncp);
rx_packets = u64_stats_read(&stats->rx_packets);
rx_bytes = u64_stats_read(&stats->rx_bytes);
rx_drops = u64_stats_read(&stats->rx_drops);
tx_packets = u64_stats_read(&stats->tx_packets);
tx_bytes = u64_stats_read(&stats->tx_bytes);
tx_drops = u64_stats_read(&stats->tx_drops);
} while (u64_stats_fetch_retry(&stats->syncp, start));
s->rx_packets += rx_packets;
s->rx_bytes += rx_bytes;
s->rx_dropped += rx_drops;
s->tx_packets += tx_packets;
s->tx_bytes += tx_bytes;
s->tx_dropped += tx_drops;
}
}
/* ndo_get_stats64 implementation for dtstats-based accounting.
*
* Populate @s from dev->stats and dev->dstats. This is used internally by the
* core for NETDEV_PCPU_STAT_DSTAT-type stats collection.
*/
static void dev_get_dstats64(const struct net_device *dev,
struct rtnl_link_stats64 *s)
{
netdev_stats_to_stats64(s, &dev->stats);
dev_fetch_dstats(s, dev->dstats);
}
/* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has
* all the same fields in the same order as net_device_stats, with only
* the type differing, but rtnl_link_stats64 may have additional fields
* at the end for newer counters.
*/
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats)
{
size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t);
const atomic_long_t *src = (atomic_long_t *)netdev_stats;
u64 *dst = (u64 *)stats64;
BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
dst[i] = (unsigned long)atomic_long_read(&src[i]);
/* zero out counters that only exist in rtnl_link_stats64 */
memset((char *)stats64 + n * sizeof(u64), 0,
sizeof(*stats64) - n * sizeof(u64));
}
EXPORT_SYMBOL(netdev_stats_to_stats64);
static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc(
struct net_device *dev)
{
struct net_device_core_stats __percpu *p;
p = alloc_percpu_gfp(struct net_device_core_stats,
GFP_ATOMIC | __GFP_NOWARN);
if (p && cmpxchg(&dev->core_stats, NULL, p))
free_percpu(p);
/* This READ_ONCE() pairs with the cmpxchg() above */
return READ_ONCE(dev->core_stats);
}
noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset)
{
/* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */
struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats);
unsigned long __percpu *field;
if (unlikely(!p)) {
p = netdev_core_stats_alloc(dev);
if (!p)
return;
}
field = (unsigned long __percpu *)((void __percpu *)p + offset);
this_cpu_inc(*field);
}
EXPORT_SYMBOL_GPL(netdev_core_stats_inc);
/**
* dev_get_stats - get network device statistics
* @dev: device to get statistics from
* @storage: place to store stats
*
* Get network statistics from device. Return @storage.
* The device driver may provide its own method by setting
* dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats;
* otherwise the internal statistics structure is used.
*/
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
struct rtnl_link_stats64 *storage)
{
const struct net_device_ops *ops = dev->netdev_ops;
const struct net_device_core_stats __percpu *p;
/*
* IPv{4,6} and udp tunnels share common stat helpers and use
* different stat type (NETDEV_PCPU_STAT_TSTATS vs
* NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent.
*/
BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) !=
offsetof(struct pcpu_dstats, rx_bytes));
BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) !=
offsetof(struct pcpu_dstats, rx_packets));
BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) !=
offsetof(struct pcpu_dstats, tx_bytes));
BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) !=
offsetof(struct pcpu_dstats, tx_packets));
if (ops->ndo_get_stats64) {
memset(storage, 0, sizeof(*storage));
ops->ndo_get_stats64(dev, storage);
} else if (ops->ndo_get_stats) {
netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage);
} else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) {
dev_get_dstats64(dev, storage);
} else {
netdev_stats_to_stats64(storage, &dev->stats);
}
/* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */
p = READ_ONCE(dev->core_stats);
if (p) {
const struct net_device_core_stats *core_stats;
int i;
for_each_possible_cpu(i) {
core_stats = per_cpu_ptr(p, i);
storage->rx_dropped += READ_ONCE(core_stats->rx_dropped);
storage->tx_dropped += READ_ONCE(core_stats->tx_dropped);
storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler);
storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped);
}
}
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
/**
* dev_fetch_sw_netstats - get per-cpu network device statistics
* @s: place to store stats
* @netstats: per-cpu network stats to read from
*
* Read per-cpu network statistics and populate the related fields in @s.
*/
void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
const struct pcpu_sw_netstats __percpu *netstats)
{
int cpu;
for_each_possible_cpu(cpu) {
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
const struct pcpu_sw_netstats *stats;
unsigned int start;
stats = per_cpu_ptr(netstats, cpu);
do {
start = u64_stats_fetch_begin(&stats->syncp);
rx_packets = u64_stats_read(&stats->rx_packets);
rx_bytes = u64_stats_read(&stats->rx_bytes);
tx_packets = u64_stats_read(&stats->tx_packets);
tx_bytes = u64_stats_read(&stats->tx_bytes);
} while (u64_stats_fetch_retry(&stats->syncp, start));
s->rx_packets += rx_packets;
s->rx_bytes += rx_bytes;
s->tx_packets += tx_packets;
s->tx_bytes += tx_bytes;
}
}
EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
/**
* dev_get_tstats64 - ndo_get_stats64 implementation
* @dev: device to get statistics from
* @s: place to store stats
*
* Populate @s from dev->stats and dev->tstats. Can be used as
* ndo_get_stats64() callback.
*/
void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
{
netdev_stats_to_stats64(s, &dev->stats);
dev_fetch_sw_netstats(s, dev->tstats);
}
EXPORT_SYMBOL_GPL(dev_get_tstats64);
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
struct netdev_queue *queue = dev_ingress_queue(dev);
#ifdef CONFIG_NET_CLS_ACT
if (queue)
return queue;
queue = kzalloc(sizeof(*queue), GFP_KERNEL);
if (!queue)
return NULL;
netdev_init_one_queue(dev, queue, NULL);
RCU_INIT_POINTER(queue->qdisc, &noop_qdisc);
RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc);
rcu_assign_pointer(dev->ingress_queue, queue);
#endif
return queue;
}
static const struct ethtool_ops default_ethtool_ops;
void netdev_set_default_ethtool_ops(struct net_device *dev,
const struct ethtool_ops *ops)
{
if (dev->ethtool_ops == &default_ethtool_ops)
dev->ethtool_ops = ops;
}
EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
/**
* netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default
* @dev: netdev to enable the IRQ coalescing on
*
* Sets a conservative default for SW IRQ coalescing. Users can use
* sysfs attributes to override the default values.
*/
void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
{
WARN_ON(dev->reg_state == NETREG_REGISTERED);
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
netdev_set_gro_flush_timeout(dev, 20000);
netdev_set_defer_hard_irqs(dev, 1);
}
}
EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on);
/**
* alloc_netdev_mqs - allocate network device
* @sizeof_priv: size of private data to allocate space for
* @name: device name format string
* @name_assign_type: origin of device name
* @setup: callback to initialize device
* @txqs: the number of TX subqueues to allocate
* @rxqs: the number of RX subqueues to allocate
*
* Allocates a struct net_device with private data area for driver use
* and performs basic initialization. Also allocates subqueue structs
* for each queue on the device.
*/
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
unsigned char name_assign_type,
void (*setup)(struct net_device *),
unsigned int txqs, unsigned int rxqs)
{
struct net_device *dev;
size_t napi_config_sz;
unsigned int maxqs;
BUG_ON(strlen(name) >= sizeof(dev->name));
if (txqs < 1) {
pr_err("alloc_netdev: Unable to allocate device with zero queues\n");
return NULL;
}
if (rxqs < 1) {
pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
return NULL;
}
maxqs = max(txqs, rxqs);
dev = kvzalloc(struct_size(dev, priv, sizeof_priv),
GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
if (!dev)
return NULL;
dev->priv_len = sizeof_priv;
ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
#ifdef CONFIG_PCPU_DEV_REFCNT
dev->pcpu_refcnt = alloc_percpu(int);
if (!dev->pcpu_refcnt)
goto free_dev;
__dev_hold(dev);
#else
refcount_set(&dev->dev_refcnt, 1);
#endif
if (dev_addr_init(dev))
goto free_pcpu;
dev_mc_init(dev);
dev_uc_init(dev);
dev_net_set(dev, &init_net);
dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
dev->xdp_zc_max_segs = 1;
dev->gso_max_segs = GSO_MAX_SEGS;
dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE;
dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE;
dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
dev->tso_max_segs = TSO_MAX_SEGS;
dev->upper_level = 1;
dev->lower_level = 1;
#ifdef CONFIG_LOCKDEP
dev->nested_level = 0;
INIT_LIST_HEAD(&dev->unlink_list);
#endif
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
INIT_LIST_HEAD(&dev->close_list);
INIT_LIST_HEAD(&dev->link_watch_list);
INIT_LIST_HEAD(&dev->adj_list.upper);
INIT_LIST_HEAD(&dev->adj_list.lower);
INIT_LIST_HEAD(&dev->ptype_all);
INIT_LIST_HEAD(&dev->ptype_specific);
INIT_LIST_HEAD(&dev->net_notifier_list);
#ifdef CONFIG_NET_SCHED
hash_init(dev->qdisc_hash);
#endif
mutex_init(&dev->lock);
dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
setup(dev);
if (!dev->tx_queue_len) {
dev->priv_flags |= IFF_NO_QUEUE;
dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
}
dev->num_tx_queues = txqs;
dev->real_num_tx_queues = txqs;
if (netif_alloc_netdev_queues(dev))
goto free_all;
dev->num_rx_queues = rxqs;
dev->real_num_rx_queues = rxqs;
if (netif_alloc_rx_queues(dev))
goto free_all;
dev->ethtool = kzalloc(sizeof(*dev->ethtool), GFP_KERNEL_ACCOUNT);
if (!dev->ethtool)
goto free_all;
dev->cfg = kzalloc(sizeof(*dev->cfg), GFP_KERNEL_ACCOUNT);
if (!dev->cfg)
goto free_all;
dev->cfg_pending = dev->cfg;
napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config));
dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT);
if (!dev->napi_config)
goto free_all;
strscpy(dev->name, name);
dev->name_assign_type = name_assign_type;
dev->group = INIT_NETDEV_GROUP;
if (!dev->ethtool_ops)
dev->ethtool_ops = &default_ethtool_ops;
nf_hook_netdev_init(dev);
return dev;
free_all:
free_netdev(dev);
return NULL;
free_pcpu:
#ifdef CONFIG_PCPU_DEV_REFCNT
free_percpu(dev->pcpu_refcnt);
free_dev:
#endif
kvfree(dev);
return NULL;
}
EXPORT_SYMBOL(alloc_netdev_mqs);
static void netdev_napi_exit(struct net_device *dev)
{
if (!list_empty(&dev->napi_list)) {
struct napi_struct *p, *n;
netdev_lock(dev);
list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
__netif_napi_del_locked(p);
netdev_unlock(dev);
synchronize_net();
}
kvfree(dev->napi_config);
}
/**
* free_netdev - free network device
* @dev: device
*
* This function does the last stage of destroying an allocated device
* interface. The reference to the device object is released. If this
* is the last reference then it will be freed.Must be called in process
* context.
*/
void free_netdev(struct net_device *dev)
{
might_sleep();
/* When called immediately after register_netdevice() failed the unwind
* handling may still be dismantling the device. Handle that case by
* deferring the free.
*/
if (dev->reg_state == NETREG_UNREGISTERING) {
ASSERT_RTNL();
dev->needs_free_netdev = true;
return;
}
WARN_ON(dev->cfg != dev->cfg_pending);
kfree(dev->cfg);
kfree(dev->ethtool);
netif_free_tx_queues(dev);
netif_free_rx_queues(dev);
kfree(rcu_dereference_protected(dev->ingress_queue, 1));
/* Flush device addresses */
dev_addr_flush(dev);
netdev_napi_exit(dev);
netif_del_cpu_rmap(dev);
ref_tracker_dir_exit(&dev->refcnt_tracker);
#ifdef CONFIG_PCPU_DEV_REFCNT
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
#endif
free_percpu(dev->core_stats);
dev->core_stats = NULL;
free_percpu(dev->xdp_bulkq);
dev->xdp_bulkq = NULL;
netdev_free_phy_link_topology(dev);
mutex_destroy(&dev->lock);
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED ||
dev->reg_state == NETREG_DUMMY) {
kvfree(dev);
return;
}
BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
WRITE_ONCE(dev->reg_state, NETREG_RELEASED);
/* will free via device release */
put_device(&dev->dev);
}
EXPORT_SYMBOL(free_netdev);
/**
* alloc_netdev_dummy - Allocate and initialize a dummy net device.
* @sizeof_priv: size of private data to allocate space for
*
* Return: the allocated net_device on success, NULL otherwise
*/
struct net_device *alloc_netdev_dummy(int sizeof_priv)
{
return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN,
init_dummy_netdev);
}
EXPORT_SYMBOL_GPL(alloc_netdev_dummy);
/**
* synchronize_net - Synchronize with packet receive processing
*
* Wait for packets currently being received to be done.
* Does not block later packets from starting.
*/
void synchronize_net(void)
{
might_sleep();
if (from_cleanup_net() || rtnl_is_locked())
synchronize_rcu_expedited();
else
synchronize_rcu();
}
EXPORT_SYMBOL(synchronize_net);
static void netdev_rss_contexts_free(struct net_device *dev)
{
struct ethtool_rxfh_context *ctx;
unsigned long context;
mutex_lock(&dev->ethtool->rss_lock);
xa_for_each(&dev->ethtool->rss_ctx, context, ctx) {
struct ethtool_rxfh_param rxfh;
rxfh.indir = ethtool_rxfh_context_indir(ctx);
rxfh.key = ethtool_rxfh_context_key(ctx);
rxfh.hfunc = ctx->hfunc;
rxfh.input_xfrm = ctx->input_xfrm;
rxfh.rss_context = context;
rxfh.rss_delete = true;
xa_erase(&dev->ethtool->rss_ctx, context);
if (dev->ethtool_ops->create_rxfh_context)
dev->ethtool_ops->remove_rxfh_context(dev, ctx,
context, NULL);
else
dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
kfree(ctx);
}
xa_destroy(&dev->ethtool->rss_ctx);
mutex_unlock(&dev->ethtool->rss_lock);
}
/**
* unregister_netdevice_queue - remove device from the kernel
* @dev: device
* @head: list
*
* This function shuts down a device interface and removes it
* from the kernel tables.
* If head not NULL, device is queued to be unregistered later.
*
* Callers must hold the rtnl semaphore. You may want
* unregister_netdev() instead of this.
*/
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
{
ASSERT_RTNL();
if (head) {
list_move_tail(&dev->unreg_list, head);
} else {
LIST_HEAD(single);
list_add(&dev->unreg_list, &single);
unregister_netdevice_many(&single);
}
}
EXPORT_SYMBOL(unregister_netdevice_queue);
static void dev_memory_provider_uninstall(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->real_num_rx_queues; i++) {
struct netdev_rx_queue *rxq = &dev->_rx[i];
struct pp_memory_provider_params *p = &rxq->mp_params;
if (p->mp_ops && p->mp_ops->uninstall)
p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq);
}
}
void unregister_netdevice_many_notify(struct list_head *head,
u32 portid, const struct nlmsghdr *nlh)
{
struct net_device *dev, *tmp;
LIST_HEAD(close_head);
int cnt = 0;
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
if (list_empty(head))
return;
list_for_each_entry_safe(dev, tmp, head, unreg_list) {
/* Some devices call without registering
* for initialization unwind. Remove those
* devices and proceed with the remaining.
*/
if (dev->reg_state == NETREG_UNINITIALIZED) {
pr_debug("unregister_netdevice: device %s/%p never was registered\n",
dev->name, dev);
WARN_ON(1);
list_del(&dev->unreg_list);
continue;
}
dev->dismantle = true;
BUG_ON(dev->reg_state != NETREG_REGISTERED);
}
/* If device is running, close it first. Start with ops locked... */
list_for_each_entry(dev, head, unreg_list) {
if (netdev_need_ops_lock(dev)) {
list_add_tail(&dev->close_list, &close_head);
netdev_lock(dev);
}
}
dev_close_many(&close_head, true);
/* ... now unlock them and go over the rest. */
list_for_each_entry(dev, head, unreg_list) {
if (netdev_need_ops_lock(dev))
netdev_unlock(dev);
else
list_add_tail(&dev->close_list, &close_head);
}
dev_close_many(&close_head, true);
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
unlist_netdevice(dev);
netdev_lock(dev);
WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING);
netdev_unlock(dev);
}
flush_all_backlogs();
synchronize_net();
list_for_each_entry(dev, head, unreg_list) {
struct sk_buff *skb = NULL;
/* Shutdown queueing discipline. */
dev_shutdown(dev);
dev_tcx_uninstall(dev);
netdev_lock_ops(dev);
dev_xdp_uninstall(dev);
dev_memory_provider_uninstall(dev);
netdev_unlock_ops(dev);
bpf_dev_bound_netdev_unregister(dev);
netdev_offload_xstats_disable_all(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
GFP_KERNEL, NULL, 0,
portid, nlh);
/*
* Flush the unicast and multicast chains
*/
dev_uc_flush(dev);
dev_mc_flush(dev);
netdev_name_node_alt_flush(dev);
netdev_name_node_free(dev->name_node);
netdev_rss_contexts_free(dev);
call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
mutex_destroy(&dev->ethtool->rss_lock);
net_shaper_flush_netdev(dev);
if (skb)
rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh);
/* Notifier chain MUST detach us all upper devices. */
WARN_ON(netdev_has_any_upper_dev(dev));
WARN_ON(netdev_has_any_lower_dev(dev));
/* Remove entries from kobject tree */
netdev_unregister_kobject(dev);
#ifdef CONFIG_XPS
/* Remove XPS queueing entries */
netif_reset_xps_queues_gt(dev, 0);
#endif
}
synchronize_net();
list_for_each_entry(dev, head, unreg_list) {
netdev_put(dev, &dev->dev_registered_tracker);
net_set_todo(dev);
cnt++;
}
atomic_add(cnt, &dev_unreg_count);
list_del(head);
}
/**
* unregister_netdevice_many - unregister many devices
* @head: list of devices
*
* Note: As most callers use a stack allocated list_head,
* we force a list_del() to make sure stack won't be corrupted later.
*/
void unregister_netdevice_many(struct list_head *head)
{
unregister_netdevice_many_notify(head, 0, NULL);
}
EXPORT_SYMBOL(unregister_netdevice_many);
/**
* unregister_netdev - remove device from the kernel
* @dev: device
*
* This function shuts down a device interface and removes it
* from the kernel tables.
*
* This is just a wrapper for unregister_netdevice that takes
* the rtnl semaphore. In general you want to use this and not
* unregister_netdevice.
*/
void unregister_netdev(struct net_device *dev)
{
rtnl_net_dev_lock(dev);
unregister_netdevice(dev);
rtnl_net_dev_unlock(dev);
}
EXPORT_SYMBOL(unregister_netdev);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex,
struct netlink_ext_ack *extack)
{
struct netdev_name_node *name_node;
struct net *net_old = dev_net(dev);
char new_name[IFNAMSIZ] = {};
int err, new_nsid;
ASSERT_RTNL();
/* Don't allow namespace local devices to be moved. */
err = -EINVAL;
if (dev->netns_immutable) {
NL_SET_ERR_MSG(extack, "The interface netns is immutable");
goto out;
}
/* Ensure the device has been registered */
if (dev->reg_state != NETREG_REGISTERED) {
NL_SET_ERR_MSG(extack, "The interface isn't registered");
goto out;
}
/* Get out if there is nothing todo */
err = 0;
if (net_eq(net_old, net))
goto out;
/* Pick the destination device name, and ensure
* we can use it in the destination network namespace.
*/
err = -EEXIST;
if (netdev_name_in_use(net, dev->name)) {
/* We get here if we can't use the current device name */
if (!pat) {
NL_SET_ERR_MSG(extack,
"An interface with the same name exists in the target netns");
goto out;
}
err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST);
if (err < 0) {
NL_SET_ERR_MSG_FMT(extack,
"Unable to use '%s' for the new interface name in the target netns",
pat);
goto out;
}
}
/* Check that none of the altnames conflicts. */
err = -EEXIST;
netdev_for_each_altname(dev, name_node) {
if (netdev_name_in_use(net, name_node->name)) {
NL_SET_ERR_MSG_FMT(extack,
"An interface with the altname %s exists in the target netns",
name_node->name);
goto out;
}
}
/* Check that new_ifindex isn't used yet. */
if (new_ifindex) {
err = dev_index_reserve(net, new_ifindex);
if (err < 0) {
NL_SET_ERR_MSG_FMT(extack,
"The ifindex %d is not available in the target netns",
new_ifindex);
goto out;
}
} else {
/* If there is an ifindex conflict assign a new one */
err = dev_index_reserve(net, dev->ifindex);
if (err == -EBUSY)
err = dev_index_reserve(net, 0);
if (err < 0) {
NL_SET_ERR_MSG(extack,
"Unable to allocate a new ifindex in the target netns");
goto out;
}
new_ifindex = err;
}
/*
* And now a mini version of register_netdevice unregister_netdevice.
*/
netdev_lock_ops(dev);
/* If device is running close it first. */
netif_close(dev);
/* And unlink it from device chain */
unlist_netdevice(dev);
netdev_unlock_ops(dev);
synchronize_net();
/* Shutdown queueing discipline. */
dev_shutdown(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
*
* Note that dev->reg_state stays at NETREG_REGISTERED.
* This is wanted because this way 8021q and macvlan know
* the device is just moving and can keep their slaves up.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid,
new_ifindex);
/*
* Flush the unicast and multicast chains
*/
dev_uc_flush(dev);
dev_mc_flush(dev);
/* Send a netdev-removed uevent to the old namespace */
kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE);
netdev_adjacent_del_links(dev);
/* Move per-net netdevice notifiers that are following the netdevice */
move_netdevice_notifiers_dev_net(dev, net);
/* Actually switch the network namespace */
dev_net_set(dev, net);
dev->ifindex = new_ifindex;
if (new_name[0]) {
/* Rename the netdev to prepared name */
write_seqlock_bh(&netdev_rename_lock);
strscpy(dev->name, new_name, IFNAMSIZ);
write_sequnlock_bh(&netdev_rename_lock);
}
/* Fixup kobjects */
dev_set_uevent_suppress(&dev->dev, 1);
err = device_rename(&dev->dev, dev->name);
dev_set_uevent_suppress(&dev->dev, 0);
WARN_ON(err);
/* Send a netdev-add uevent to the new namespace */
kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
netdev_adjacent_add_links(dev);
/* Adapt owner in case owning user namespace of target network
* namespace is different from the original one.
*/
err = netdev_change_owner(dev, net_old, net);
WARN_ON(err);
netdev_lock_ops(dev);
/* Add the device back in the hashes */
list_netdevice(dev);
/* Notify protocols, that a new device appeared. */
call_netdevice_notifiers(NETDEV_REGISTER, dev);
netdev_unlock_ops(dev);
/*
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
synchronize_net();
err = 0;
out:
return err;
}
static int dev_cpu_dead(unsigned int oldcpu)
{
struct sk_buff **list_skb;
struct sk_buff *skb;
unsigned int cpu;
struct softnet_data *sd, *oldsd, *remsd = NULL;
local_irq_disable();
cpu = smp_processor_id();
sd = &per_cpu(softnet_data, cpu);
oldsd = &per_cpu(softnet_data, oldcpu);
/* Find end of our completion_queue. */
list_skb = &sd->completion_queue;
while (*list_skb)
list_skb = &(*list_skb)->next;
/* Append completion queue from offline CPU. */
*list_skb = oldsd->completion_queue;
oldsd->completion_queue = NULL;
/* Append output queue from offline CPU. */
if (oldsd->output_queue) {
*sd->output_queue_tailp = oldsd->output_queue;
sd->output_queue_tailp = oldsd->output_queue_tailp;
oldsd->output_queue = NULL;
oldsd->output_queue_tailp = &oldsd->output_queue;
}
/* Append NAPI poll list from offline CPU, with one exception :
* process_backlog() must be called by cpu owning percpu backlog.
* We properly handle process_queue & input_pkt_queue later.
*/
while (!list_empty(&oldsd->poll_list)) {
struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
struct napi_struct,
poll_list);
list_del_init(&napi->poll_list);
if (napi->poll == process_backlog)
napi->state &= NAPIF_STATE_THREADED;
else
____napi_schedule(sd, napi);
}
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_enable();
if (!use_backlog_threads()) {
#ifdef CONFIG_RPS
remsd = oldsd->rps_ipi_list;
oldsd->rps_ipi_list = NULL;
#endif
/* send out pending IPI's on offline CPU */
net_rps_send_ipi(remsd);
}
/* Process offline CPU's input_pkt_queue */
while ((skb = __skb_dequeue(&oldsd->process_queue))) {
netif_rx(skb);
rps_input_queue_head_incr(oldsd);
}
while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
rps_input_queue_head_incr(oldsd);
}
return 0;
}
/**
* netdev_increment_features - increment feature set by one
* @all: current feature set
* @one: new feature set
* @mask: mask feature set
*
* Computes a new feature set after adding a device with feature set
* @one to the master device with current feature set @all. Will not
* enable anything that is off in @mask. Returns the new feature set.
*/
netdev_features_t netdev_increment_features(netdev_features_t all,
netdev_features_t one, netdev_features_t mask)
{
if (mask & NETIF_F_HW_CSUM)
mask |= NETIF_F_CSUM_MASK;
mask |= NETIF_F_VLAN_CHALLENGED;
all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask;
all &= one | ~NETIF_F_ALL_FOR_ALL;
/* If one device supports hw checksumming, set for all. */
if (all & NETIF_F_HW_CSUM)
all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM);
return all;
}
EXPORT_SYMBOL(netdev_increment_features);
static struct hlist_head * __net_init netdev_create_hash(void)
{
int i;
struct hlist_head *hash;
hash = kmalloc_array(NETDEV_HASHENTRIES, sizeof(*hash), GFP_KERNEL);
if (hash != NULL)
for (i = 0; i < NETDEV_HASHENTRIES; i++)
INIT_HLIST_HEAD(&hash[i]);
return hash;
}
/* Initialize per network namespace state */
static int __net_init netdev_init(struct net *net)
{
BUILD_BUG_ON(GRO_HASH_BUCKETS >
BITS_PER_BYTE * sizeof_field(struct gro_node, bitmask));
INIT_LIST_HEAD(&net->dev_base_head);
net->dev_name_head = netdev_create_hash();
if (net->dev_name_head == NULL)
goto err_name;
net->dev_index_head = netdev_create_hash();
if (net->dev_index_head == NULL)
goto err_idx;
xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1);
RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
return 0;
err_idx:
kfree(net->dev_name_head);
err_name:
return -ENOMEM;
}
/**
* netdev_drivername - network driver for the device
* @dev: network device
*
* Determine network driver for device.
*/
const char *netdev_drivername(const struct net_device *dev)
{
const struct device_driver *driver;
const struct device *parent;
const char *empty = "";
parent = dev->dev.parent;
if (!parent)
return empty;
driver = parent->driver;
if (driver && driver->name)
return driver->name;
return empty;
}
static void __netdev_printk(const char *level, const struct net_device *dev,
struct va_format *vaf)
{
if (dev && dev->dev.parent) {
dev_printk_emit(level[1] - '0',
dev->dev.parent,
"%s %s %s%s: %pV",
dev_driver_string(dev->dev.parent),
dev_name(dev->dev.parent),
netdev_name(dev), netdev_reg_state(dev),
vaf);
} else if (dev) {
printk("%s%s%s: %pV",
level, netdev_name(dev), netdev_reg_state(dev), vaf);
} else {
printk("%s(NULL net_device): %pV", level, vaf);
}
}
void netdev_printk(const char *level, const struct net_device *dev,
const char *format, ...)
{
struct va_format vaf;
va_list args;
va_start(args, format);
vaf.fmt = format;
vaf.va = &args;
__netdev_printk(level, dev, &vaf);
va_end(args);
}
EXPORT_SYMBOL(netdev_printk);
#define define_netdev_printk_level(func, level) \
void func(const struct net_device *dev, const char *fmt, ...) \
{ \
struct va_format vaf; \
va_list args; \
\
va_start(args, fmt); \
\
vaf.fmt = fmt; \
vaf.va = &args; \
\
__netdev_printk(level, dev, &vaf); \
\
va_end(args); \
} \
EXPORT_SYMBOL(func);
define_netdev_printk_level(netdev_emerg, KERN_EMERG);
define_netdev_printk_level(netdev_alert, KERN_ALERT);
define_netdev_printk_level(netdev_crit, KERN_CRIT);
define_netdev_printk_level(netdev_err, KERN_ERR);
define_netdev_printk_level(netdev_warn, KERN_WARNING);
define_netdev_printk_level(netdev_notice, KERN_NOTICE);
define_netdev_printk_level(netdev_info, KERN_INFO);
static void __net_exit netdev_exit(struct net *net)
{
kfree(net->dev_name_head);
kfree(net->dev_index_head);
xa_destroy(&net->dev_by_index);
if (net != &init_net)
WARN_ON_ONCE(!list_empty(&net->dev_base_head));
}
static struct pernet_operations __net_initdata netdev_net_ops = {
.init = netdev_init,
.exit = netdev_exit,
};
static void __net_exit default_device_exit_net(struct net *net)
{
struct netdev_name_node *name_node, *tmp;
struct net_device *dev, *aux;
/*
* Push all migratable network devices back to the
* initial network namespace
*/
ASSERT_RTNL();
for_each_netdev_safe(net, dev, aux) {
int err;
char fb_name[IFNAMSIZ];
/* Ignore unmoveable devices (i.e. loopback) */
if (dev->netns_immutable)
continue;
/* Leave virtual devices for the generic cleanup */
if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
continue;
/* Push remaining network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
if (netdev_name_in_use(&init_net, fb_name))
snprintf(fb_name, IFNAMSIZ, "dev%%d");
netdev_for_each_altname_safe(dev, name_node, tmp)
if (netdev_name_in_use(&init_net, name_node->name))
__netdev_name_node_alt_destroy(name_node);
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
pr_emerg("%s: failed to move %s to init_net: %d\n",
__func__, dev->name, err);
BUG();
}
}
}
static void __net_exit default_device_exit_batch(struct list_head *net_list)
{
/* At exit all network devices most be removed from a network
* namespace. Do this in the reverse order of registration.
* Do this across as many network namespaces as possible to
* improve batching efficiency.
*/
struct net_device *dev;
struct net *net;
LIST_HEAD(dev_kill_list);
rtnl_lock();
list_for_each_entry(net, net_list, exit_list) {
default_device_exit_net(net);
cond_resched();
}
list_for_each_entry(net, net_list, exit_list) {
for_each_netdev_reverse(net, dev) {
if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink)
dev->rtnl_link_ops->dellink(dev, &dev_kill_list);
else
unregister_netdevice_queue(dev, &dev_kill_list);
}
}
unregister_netdevice_many(&dev_kill_list);
rtnl_unlock();
}
static struct pernet_operations __net_initdata default_device_ops = {
.exit_batch = default_device_exit_batch,
};
static void __init net_dev_struct_check(void)
{
/* TX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq);
#ifdef CONFIG_XPS
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps);
#endif
#ifdef CONFIG_NETFILTER_EGRESS
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress);
#endif
#ifdef CONFIG_NET_XGRESS
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress);
#endif
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
/* TXRX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46);
/* RX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net);
#ifdef CONFIG_NETPOLL
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo);
#endif
#ifdef CONFIG_NET_XGRESS
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
#endif
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 92);
}
/*
* Initialize the DEV module. At boot time this walks the device list and
* unhooks any devices that fail to initialise (normally hardware not
* present) and leaves us with a valid list of present and active devices.
*
*/
/* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */
#define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE)
static int net_page_pool_create(int cpuid)
{
#if IS_ENABLED(CONFIG_PAGE_POOL)
struct page_pool_params page_pool_params = {
.pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE,
.flags = PP_FLAG_SYSTEM_POOL,
.nid = cpu_to_mem(cpuid),
};
struct page_pool *pp_ptr;
int err;
pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid);
if (IS_ERR(pp_ptr))
return -ENOMEM;
err = xdp_reg_page_pool(pp_ptr);
if (err) {
page_pool_destroy(pp_ptr);
return err;
}
per_cpu(system_page_pool, cpuid) = pp_ptr;
#endif
return 0;
}
static int backlog_napi_should_run(unsigned int cpu)
{
struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
struct napi_struct *napi = &sd->backlog;
return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
}
static void run_backlog_napi(unsigned int cpu)
{
struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
napi_threaded_poll_loop(&sd->backlog);
}
static void backlog_napi_setup(unsigned int cpu)
{
struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
struct napi_struct *napi = &sd->backlog;
napi->thread = this_cpu_read(backlog_napi);
set_bit(NAPI_STATE_THREADED, &napi->state);
}
static struct smp_hotplug_thread backlog_threads = {
.store = &backlog_napi,
.thread_should_run = backlog_napi_should_run,
.thread_fn = run_backlog_napi,
.thread_comm = "backlog_napi/%u",
.setup = backlog_napi_setup,
};
/*
* This is called single threaded during boot, so no need
* to take the rtnl semaphore.
*/
static int __init net_dev_init(void)
{
int i, rc = -ENOMEM;
BUG_ON(!dev_boot_phase);
net_dev_struct_check();
if (dev_proc_init())
goto out;
if (netdev_kobject_init())
goto out;
for (i = 0; i < PTYPE_HASH_SIZE; i++)
INIT_LIST_HEAD(&ptype_base[i]);
if (register_pernet_subsys(&netdev_net_ops))
goto out;
/*
* Initialise the packet receive queues.
*/
flush_backlogs_fallback = flush_backlogs_alloc();
if (!flush_backlogs_fallback)
goto out;
for_each_possible_cpu(i) {
struct softnet_data *sd = &per_cpu(softnet_data, i);
skb_queue_head_init(&sd->input_pkt_queue);
skb_queue_head_init(&sd->process_queue);
#ifdef CONFIG_XFRM_OFFLOAD
skb_queue_head_init(&sd->xfrm_backlog);
#endif
INIT_LIST_HEAD(&sd->poll_list);
sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
sd->cpu = i;
#endif
INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
spin_lock_init(&sd->defer_lock);
gro_init(&sd->backlog.gro);
sd->backlog.poll = process_backlog;
sd->backlog.weight = weight_p;
INIT_LIST_HEAD(&sd->backlog.poll_list);
if (net_page_pool_create(i))
goto out;
}
if (use_backlog_threads())
smpboot_register_percpu_thread(&backlog_threads);
dev_boot_phase = 0;
/* The loopback device is special if any other network devices
* is present in a network namespace the loopback device must
* be present. Since we now dynamically allocate and free the
* loopback device ensure this invariant is maintained by
* keeping the loopback device as the first device on the
* list of network devices. Ensuring the loopback devices
* is the first device that appears and the last network device
* that disappears.
*/
if (register_pernet_device(&loopback_net_ops))
goto out;
if (register_pernet_device(&default_device_ops))
goto out;
open_softirq(NET_TX_SOFTIRQ, net_tx_action);
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead",
NULL, dev_cpu_dead);
WARN_ON(rc < 0);
rc = 0;
/* avoid static key IPIs to isolated CPUs */
if (housekeeping_enabled(HK_TYPE_MISC))
net_enable_timestamp();
out:
if (rc < 0) {
for_each_possible_cpu(i) {
struct page_pool *pp_ptr;
pp_ptr = per_cpu(system_page_pool, i);
if (!pp_ptr)
continue;
xdp_unreg_page_pool(pp_ptr);
page_pool_destroy(pp_ptr);
per_cpu(system_page_pool, i) = NULL;
}
}
return rc;
}
subsys_initcall(net_dev_init);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Routines to manage notifier chains for passing status changes to any
* interested routines. We need this instead of hard coded call lists so
* that modules can poke their nose into the innards. The network devices
* needed them so here they are for the rest of you.
*
* Alan Cox <Alan.Cox@linux.org>
*/
#ifndef _LINUX_NOTIFIER_H
#define _LINUX_NOTIFIER_H
#include <linux/errno.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/srcu.h>
/*
* Notifier chains are of four types:
*
* Atomic notifier chains: Chain callbacks run in interrupt/atomic
* context. Callouts are not allowed to block.
* Blocking notifier chains: Chain callbacks run in process context.
* Callouts are allowed to block.
* Raw notifier chains: There are no restrictions on callbacks,
* registration, or unregistration. All locking and protection
* must be provided by the caller.
* SRCU notifier chains: A variant of blocking notifier chains, with
* the same restrictions.
*
* atomic_notifier_chain_register() may be called from an atomic context,
* but blocking_notifier_chain_register() and srcu_notifier_chain_register()
* must be called from a process context. Ditto for the corresponding
* _unregister() routines.
*
* atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(),
* and srcu_notifier_chain_unregister() _must not_ be called from within
* the call chain.
*
* SRCU notifier chains are an alternative form of blocking notifier chains.
* They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for
* protection of the chain links. This means there is _very_ low overhead
* in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
* As compensation, srcu_notifier_chain_unregister() is rather expensive.
* SRCU notifier chains should be used when the chain will be called very
* often but notifier_blocks will seldom be removed.
*/
struct notifier_block;
typedef int (*notifier_fn_t)(struct notifier_block *nb,
unsigned long action, void *data);
struct notifier_block {
notifier_fn_t notifier_call;
struct notifier_block __rcu *next;
int priority;
};
struct atomic_notifier_head {
spinlock_t lock;
struct notifier_block __rcu *head;
};
struct blocking_notifier_head {
struct rw_semaphore rwsem;
struct notifier_block __rcu *head;
};
struct raw_notifier_head {
struct notifier_block __rcu *head;
};
struct srcu_notifier_head {
struct mutex mutex;
struct srcu_usage srcuu;
struct srcu_struct srcu;
struct notifier_block __rcu *head;
};
#define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \
spin_lock_init(&(name)->lock); \
(name)->head = NULL; \
} while (0)
#define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \
init_rwsem(&(name)->rwsem); \
(name)->head = NULL; \
} while (0)
#define RAW_INIT_NOTIFIER_HEAD(name) do { \
(name)->head = NULL; \
} while (0)
/* srcu_notifier_heads must be cleaned up dynamically */
extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
#define srcu_cleanup_notifier_head(name) \
cleanup_srcu_struct(&(name)->srcu);
#define ATOMIC_NOTIFIER_INIT(name) { \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.head = NULL }
#define BLOCKING_NOTIFIER_INIT(name) { \
.rwsem = __RWSEM_INITIALIZER((name).rwsem), \
.head = NULL }
#define RAW_NOTIFIER_INIT(name) { \
.head = NULL }
#define SRCU_NOTIFIER_INIT(name, pcpu) \
{ \
.mutex = __MUTEX_INITIALIZER(name.mutex), \
.head = NULL, \
.srcuu = __SRCU_USAGE_INIT(name.srcuu), \
.srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \
}
#define ATOMIC_NOTIFIER_HEAD(name) \
struct atomic_notifier_head name = \
ATOMIC_NOTIFIER_INIT(name)
#define BLOCKING_NOTIFIER_HEAD(name) \
struct blocking_notifier_head name = \
BLOCKING_NOTIFIER_INIT(name)
#define RAW_NOTIFIER_HEAD(name) \
struct raw_notifier_head name = \
RAW_NOTIFIER_INIT(name)
#ifdef CONFIG_TREE_SRCU
#define _SRCU_NOTIFIER_HEAD(name, mod) \
static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \
mod struct srcu_notifier_head name = \
SRCU_NOTIFIER_INIT(name, name##_head_srcu_data)
#else
#define _SRCU_NOTIFIER_HEAD(name, mod) \
mod struct srcu_notifier_head name = \
SRCU_NOTIFIER_INIT(name, name)
#endif
#define SRCU_NOTIFIER_HEAD(name) \
_SRCU_NOTIFIER_HEAD(name, /* not static */)
#define SRCU_NOTIFIER_HEAD_STATIC(name) \
_SRCU_NOTIFIER_HEAD(name, static)
#ifdef __KERNEL__
extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
struct notifier_block *nb);
extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
struct notifier_block *nb);
extern int raw_notifier_chain_register(struct raw_notifier_head *nh,
struct notifier_block *nb);
extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
struct notifier_block *nb);
extern int atomic_notifier_chain_register_unique_prio(
struct atomic_notifier_head *nh, struct notifier_block *nb);
extern int blocking_notifier_chain_register_unique_prio(
struct blocking_notifier_head *nh, struct notifier_block *nb);
extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
struct notifier_block *nb);
extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
struct notifier_block *nb);
extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
struct notifier_block *nb);
extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
struct notifier_block *nb);
extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
unsigned long val, void *v);
extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
unsigned long val, void *v);
extern int raw_notifier_call_chain(struct raw_notifier_head *nh,
unsigned long val, void *v);
extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
unsigned long val, void *v);
extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v);
extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v);
extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh);
#define NOTIFY_DONE 0x0000 /* Don't care */
#define NOTIFY_OK 0x0001 /* Suits me */
#define NOTIFY_STOP_MASK 0x8000 /* Don't call further */
#define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002)
/* Bad/Veto action */
/*
* Clean way to return from the notifier and stop further calls.
*/
#define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK)
/* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */
static inline int notifier_from_errno(int err)
{
if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err);
return NOTIFY_OK;
}
/* Restore (negative) errno value from notify return value. */
static inline int notifier_to_errno(int ret)
{
ret &= ~NOTIFY_STOP_MASK;
return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0;
}
/*
* Declared notifiers so far. I can imagine quite a few more chains
* over time (eg laptop power reset chains, reboot chain (to clean
* device units up), device [un]mount chain, module load/unload chain,
* low memory chain, screenblank chain (for plug in modular screenblankers)
* VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
*/
/* CPU notfiers are defined in include/linux/cpu.h. */
/* netdevice notifiers are defined in include/linux/netdevice.h */
/* reboot notifiers are defined in include/linux/reboot.h. */
/* Hibernation and suspend events are defined in include/linux/suspend.h. */
/* Virtual Terminal events are defined in include/linux/vt.h. */
#define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */
/* Console keyboard events.
* Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and
* KBD_KEYSYM. */
#define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */
#define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */
#define KBD_UNICODE 0x0003 /* Keyboard unicode */
#define KBD_KEYSYM 0x0004 /* Keyboard keysym */
#define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */
#endif /* __KERNEL__ */
#endif /* _LINUX_NOTIFIER_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Kernel internal timers
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better.
*
* 1997-09-10 Updated NTP code according to technical memorandum Jan '96
* "A Kernel Model for Precision Timekeeping" by Dave Mills
* 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
* serialize accesses to xtime/lost_ticks).
* Copyright (C) 1998 Andrea Arcangeli
* 1999-03-10 Improved NTP compatibility by Ulrich Windl
* 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love
* 2000-10-05 Implemented scalable SMP per-CPU timer handling.
* Copyright (C) 2000, 2001, 2002 Ingo Molnar
* Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
*/
#include <linux/kernel_stat.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/pid_namespace.h>
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/delay.h>
#include <linux/tick.h>
#include <linux/kallsyms.h>
#include <linux/irq_work.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/nohz.h>
#include <linux/sched/debug.h>
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/random.h>
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>
#include "tick-internal.h"
#include "timer_migration.h"
#define CREATE_TRACE_POINTS
#include <trace/events/timer.h>
__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
/*
* The timer wheel has LVL_DEPTH array levels. Each level provides an array of
* LVL_SIZE buckets. Each level is driven by its own clock and therefore each
* level has a different granularity.
*
* The level granularity is: LVL_CLK_DIV ^ level
* The level clock frequency is: HZ / (LVL_CLK_DIV ^ level)
*
* The array level of a newly armed timer depends on the relative expiry
* time. The farther the expiry time is away the higher the array level and
* therefore the granularity becomes.
*
* Contrary to the original timer wheel implementation, which aims for 'exact'
* expiry of the timers, this implementation removes the need for recascading
* the timers into the lower array levels. The previous 'classic' timer wheel
* implementation of the kernel already violated the 'exact' expiry by adding
* slack to the expiry time to provide batched expiration. The granularity
* levels provide implicit batching.
*
* This is an optimization of the original timer wheel implementation for the
* majority of the timer wheel use cases: timeouts. The vast majority of
* timeout timers (networking, disk I/O ...) are canceled before expiry. If
* the timeout expires it indicates that normal operation is disturbed, so it
* does not matter much whether the timeout comes with a slight delay.
*
* The only exception to this are networking timers with a small expiry
* time. They rely on the granularity. Those fit into the first wheel level,
* which has HZ granularity.
*
* We don't have cascading anymore. timers with a expiry time above the
* capacity of the last wheel level are force expired at the maximum timeout
* value of the last wheel level. From data sampling we know that the maximum
* value observed is 5 days (network connection tracking), so this should not
* be an issue.
*
* The currently chosen array constants values are a good compromise between
* array size and granularity.
*
* This results in the following granularity and range levels:
*
* HZ 1000 steps
* Level Offset Granularity Range
* 0 0 1 ms 0 ms - 63 ms
* 1 64 8 ms 64 ms - 511 ms
* 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s)
* 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s)
* 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m)
* 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m)
* 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h)
* 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d)
* 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d)
*
* HZ 300
* Level Offset Granularity Range
* 0 0 3 ms 0 ms - 210 ms
* 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s)
* 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s)
* 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m)
* 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m)
* 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h)
* 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h)
* 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d)
* 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d)
*
* HZ 250
* Level Offset Granularity Range
* 0 0 4 ms 0 ms - 255 ms
* 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s)
* 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s)
* 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m)
* 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m)
* 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h)
* 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h)
* 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d)
* 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d)
*
* HZ 100
* Level Offset Granularity Range
* 0 0 10 ms 0 ms - 630 ms
* 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s)
* 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s)
* 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m)
* 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m)
* 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h)
* 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d)
* 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d)
*/
/* Clock divisor for the next level */
#define LVL_CLK_SHIFT 3
#define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT)
#define LVL_CLK_MASK (LVL_CLK_DIV - 1)
#define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT)
#define LVL_GRAN(n) (1UL << LVL_SHIFT(n))
/*
* The time start value for each level to select the bucket at enqueue
* time. We start from the last possible delta of the previous level
* so that we can later add an extra LVL_GRAN(n) to n (see calc_index()).
*/
#define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT))
/* Size of each clock level */
#define LVL_BITS 6
#define LVL_SIZE (1UL << LVL_BITS)
#define LVL_MASK (LVL_SIZE - 1)
#define LVL_OFFS(n) ((n) * LVL_SIZE)
/* Level depth */
#if HZ > 100
# define LVL_DEPTH 9
# else
# define LVL_DEPTH 8
#endif
/* The cutoff (max. capacity of the wheel) */
#define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH))
#define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1))
/*
* The resulting wheel size. If NOHZ is configured we allocate two
* wheels so we have a separate storage for the deferrable timers.
*/
#define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH)
#ifdef CONFIG_NO_HZ_COMMON
/*
* If multiple bases need to be locked, use the base ordering for lock
* nesting, i.e. lowest number first.
*/
# define NR_BASES 3
# define BASE_LOCAL 0
# define BASE_GLOBAL 1
# define BASE_DEF 2
#else
# define NR_BASES 1
# define BASE_LOCAL 0
# define BASE_GLOBAL 0
# define BASE_DEF 0
#endif
/**
* struct timer_base - Per CPU timer base (number of base depends on config)
* @lock: Lock protecting the timer_base
* @running_timer: When expiring timers, the lock is dropped. To make
* sure not to race against deleting/modifying a
* currently running timer, the pointer is set to the
* timer, which expires at the moment. If no timer is
* running, the pointer is NULL.
* @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around
* timer expiry callback execution and when trying to
* delete a running timer and it wasn't successful in
* the first glance. It prevents priority inversion
* when callback was preempted on a remote CPU and a
* caller tries to delete the running timer. It also
* prevents a life lock, when the task which tries to
* delete a timer preempted the softirq thread which
* is running the timer callback function.
* @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter
* waiting for the end of the timer callback function
* execution.
* @clk: clock of the timer base; is updated before enqueue
* of a timer; during expiry, it is 1 offset ahead of
* jiffies to avoid endless requeuing to current
* jiffies
* @next_expiry: expiry value of the first timer; it is updated when
* finding the next timer and during enqueue; the
* value is not valid, when next_expiry_recalc is set
* @cpu: Number of CPU the timer base belongs to
* @next_expiry_recalc: States, whether a recalculation of next_expiry is
* required. Value is set true, when a timer was
* deleted.
* @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ
* code. This state is only used in standard
* base. Deferrable timers, which are enqueued remotely
* never wake up an idle CPU. So no matter of supporting it
* for this base.
* @timers_pending: Is set, when a timer is pending in the base. It is only
* reliable when next_expiry_recalc is not set.
* @pending_map: bitmap of the timer wheel; each bit reflects a
* bucket of the wheel. When a bit is set, at least a
* single timer is enqueued in the related bucket.
* @vectors: Array of lists; Each array member reflects a bucket
* of the timer wheel. The list contains all timers
* which are enqueued into a specific bucket.
*/
struct timer_base {
raw_spinlock_t lock;
struct timer_list *running_timer;
#ifdef CONFIG_PREEMPT_RT
spinlock_t expiry_lock;
atomic_t timer_waiters;
#endif
unsigned long clk;
unsigned long next_expiry;
unsigned int cpu;
bool next_expiry_recalc;
bool is_idle;
bool timers_pending;
DECLARE_BITMAP(pending_map, WHEEL_SIZE);
struct hlist_head vectors[WHEEL_SIZE];
} ____cacheline_aligned;
static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
#ifdef CONFIG_NO_HZ_COMMON
static DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
static DEFINE_MUTEX(timer_keys_mutex);
static void timer_update_keys(struct work_struct *work);
static DECLARE_WORK(timer_update_work, timer_update_keys);
#ifdef CONFIG_SMP
static unsigned int sysctl_timer_migration = 1;
DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
static void timers_update_migration(void)
{
if (sysctl_timer_migration && tick_nohz_active)
static_branch_enable(&timers_migration_enabled);
else
static_branch_disable(&timers_migration_enabled);
}
#ifdef CONFIG_SYSCTL
static int timer_migration_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
mutex_lock(&timer_keys_mutex);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write)
timers_update_migration();
mutex_unlock(&timer_keys_mutex);
return ret;
}
static const struct ctl_table timer_sysctl[] = {
{
.procname = "timer_migration",
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = timer_migration_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
};
static int __init timer_sysctl_init(void)
{
register_sysctl("kernel", timer_sysctl);
return 0;
}
device_initcall(timer_sysctl_init);
#endif /* CONFIG_SYSCTL */
#else /* CONFIG_SMP */
static inline void timers_update_migration(void) { }
#endif /* !CONFIG_SMP */
static void timer_update_keys(struct work_struct *work)
{
mutex_lock(&timer_keys_mutex);
timers_update_migration();
static_branch_enable(&timers_nohz_active);
mutex_unlock(&timer_keys_mutex);
}
void timers_update_nohz(void)
{
schedule_work(&timer_update_work);
}
static inline bool is_timers_nohz_active(void)
{
return static_branch_unlikely(&timers_nohz_active);
}
#else
static inline bool is_timers_nohz_active(void) { return false; }
#endif /* NO_HZ_COMMON */
static unsigned long round_jiffies_common(unsigned long j, int cpu,
bool force_up)
{
int rem;
unsigned long original = j;
/*
* We don't want all cpus firing their timers at once hitting the
* same lock or cachelines, so we skew each extra cpu with an extra
* 3 jiffies. This 3 jiffies came originally from the mm/ code which
* already did this.
* The skew is done by adding 3*cpunr, then round, then subtract this
* extra offset again.
*/
j += cpu * 3;
rem = j % HZ;
/*
* If the target jiffy is just after a whole second (which can happen
* due to delays of the timer irq, long irq off times etc etc) then
* we should round down to the whole second, not up. Use 1/4th second
* as cutoff for this rounding as an extreme upper bound for this.
* But never round down if @force_up is set.
*/
if (rem < HZ/4 && !force_up) /* round down */
j = j - rem;
else /* round up */
j = j - rem + HZ;
/* now that we have rounded, subtract the extra skew again */
j -= cpu * 3;
/*
* Make sure j is still in the future. Otherwise return the
* unmodified value.
*/
return time_is_after_jiffies(j) ? j : original;
}
/**
* __round_jiffies - function to round jiffies to a full second
* @j: the time in (absolute) jiffies that should be rounded
* @cpu: the processor number on which the timeout will happen
*
* __round_jiffies() rounds an absolute time in the future (in jiffies)
* up or down to (approximately) full seconds. This is useful for timers
* for which the exact time they fire does not matter too much, as long as
* they fire approximately every X seconds.
*
* By rounding these timers to whole seconds, all such timers will fire
* at the same time, rather than at various times spread out. The goal
* of this is to have the CPU wake up less, which saves power.
*
* The exact rounding is skewed for each processor to avoid all
* processors firing at the exact same time, which could lead
* to lock contention or spurious cache line bouncing.
*
* The return value is the rounded version of the @j parameter.
*/
unsigned long __round_jiffies(unsigned long j, int cpu)
{
return round_jiffies_common(j, cpu, false);
}
EXPORT_SYMBOL_GPL(__round_jiffies);
/**
* __round_jiffies_relative - function to round jiffies to a full second
* @j: the time in (relative) jiffies that should be rounded
* @cpu: the processor number on which the timeout will happen
*
* __round_jiffies_relative() rounds a time delta in the future (in jiffies)
* up or down to (approximately) full seconds. This is useful for timers
* for which the exact time they fire does not matter too much, as long as
* they fire approximately every X seconds.
*
* By rounding these timers to whole seconds, all such timers will fire
* at the same time, rather than at various times spread out. The goal
* of this is to have the CPU wake up less, which saves power.
*
* The exact rounding is skewed for each processor to avoid all
* processors firing at the exact same time, which could lead
* to lock contention or spurious cache line bouncing.
*
* The return value is the rounded version of the @j parameter.
*/
unsigned long __round_jiffies_relative(unsigned long j, int cpu)
{
unsigned long j0 = jiffies;
/* Use j0 because jiffies might change while we run */
return round_jiffies_common(j + j0, cpu, false) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_relative);
/**
* round_jiffies - function to round jiffies to a full second
* @j: the time in (absolute) jiffies that should be rounded
*
* round_jiffies() rounds an absolute time in the future (in jiffies)
* up or down to (approximately) full seconds. This is useful for timers
* for which the exact time they fire does not matter too much, as long as
* they fire approximately every X seconds.
*
* By rounding these timers to whole seconds, all such timers will fire
* at the same time, rather than at various times spread out. The goal
* of this is to have the CPU wake up less, which saves power.
*
* The return value is the rounded version of the @j parameter.
*/
unsigned long round_jiffies(unsigned long j)
{
return round_jiffies_common(j, raw_smp_processor_id(), false);
}
EXPORT_SYMBOL_GPL(round_jiffies);
/**
* round_jiffies_relative - function to round jiffies to a full second
* @j: the time in (relative) jiffies that should be rounded
*
* round_jiffies_relative() rounds a time delta in the future (in jiffies)
* up or down to (approximately) full seconds. This is useful for timers
* for which the exact time they fire does not matter too much, as long as
* they fire approximately every X seconds.
*
* By rounding these timers to whole seconds, all such timers will fire
* at the same time, rather than at various times spread out. The goal
* of this is to have the CPU wake up less, which saves power.
*
* The return value is the rounded version of the @j parameter.
*/
unsigned long round_jiffies_relative(unsigned long j)
{
return __round_jiffies_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_relative);
/**
* __round_jiffies_up - function to round jiffies up to a full second
* @j: the time in (absolute) jiffies that should be rounded
* @cpu: the processor number on which the timeout will happen
*
* This is the same as __round_jiffies() except that it will never
* round down. This is useful for timeouts for which the exact time
* of firing does not matter too much, as long as they don't fire too
* early.
*/
unsigned long __round_jiffies_up(unsigned long j, int cpu)
{
return round_jiffies_common(j, cpu, true);
}
EXPORT_SYMBOL_GPL(__round_jiffies_up);
/**
* __round_jiffies_up_relative - function to round jiffies up to a full second
* @j: the time in (relative) jiffies that should be rounded
* @cpu: the processor number on which the timeout will happen
*
* This is the same as __round_jiffies_relative() except that it will never
* round down. This is useful for timeouts for which the exact time
* of firing does not matter too much, as long as they don't fire too
* early.
*/
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
{
unsigned long j0 = jiffies;
/* Use j0 because jiffies might change while we run */
return round_jiffies_common(j + j0, cpu, true) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
/**
* round_jiffies_up - function to round jiffies up to a full second
* @j: the time in (absolute) jiffies that should be rounded
*
* This is the same as round_jiffies() except that it will never
* round down. This is useful for timeouts for which the exact time
* of firing does not matter too much, as long as they don't fire too
* early.
*/
unsigned long round_jiffies_up(unsigned long j)
{
return round_jiffies_common(j, raw_smp_processor_id(), true);
}
EXPORT_SYMBOL_GPL(round_jiffies_up);
/**
* round_jiffies_up_relative - function to round jiffies up to a full second
* @j: the time in (relative) jiffies that should be rounded
*
* This is the same as round_jiffies_relative() except that it will never
* round down. This is useful for timeouts for which the exact time
* of firing does not matter too much, as long as they don't fire too
* early.
*/
unsigned long round_jiffies_up_relative(unsigned long j)
{
return __round_jiffies_up_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
static inline unsigned int timer_get_idx(struct timer_list *timer)
{
return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT;
}
static inline void timer_set_idx(struct timer_list *timer, unsigned int idx)
{
timer->flags = (timer->flags & ~TIMER_ARRAYMASK) |
idx << TIMER_ARRAYSHIFT;
}
/*
* Helper function to calculate the array index for a given expiry
* time.
*/
static inline unsigned calc_index(unsigned long expires, unsigned lvl,
unsigned long *bucket_expiry)
{
/*
* The timer wheel has to guarantee that a timer does not fire
* early. Early expiry can happen due to:
* - Timer is armed at the edge of a tick
* - Truncation of the expiry time in the outer wheel levels
*
* Round up with level granularity to prevent this.
*/
expires = (expires >> LVL_SHIFT(lvl)) + 1;
*bucket_expiry = expires << LVL_SHIFT(lvl);
return LVL_OFFS(lvl) + (expires & LVL_MASK);
}
static int calc_wheel_index(unsigned long expires, unsigned long clk,
unsigned long *bucket_expiry)
{
unsigned long delta = expires - clk;
unsigned int idx;
if (delta < LVL_START(1)) {
idx = calc_index(expires, 0, bucket_expiry);
} else if (delta < LVL_START(2)) {
idx = calc_index(expires, 1, bucket_expiry);
} else if (delta < LVL_START(3)) {
idx = calc_index(expires, 2, bucket_expiry);
} else if (delta < LVL_START(4)) {
idx = calc_index(expires, 3, bucket_expiry);
} else if (delta < LVL_START(5)) {
idx = calc_index(expires, 4, bucket_expiry);
} else if (delta < LVL_START(6)) {
idx = calc_index(expires, 5, bucket_expiry);
} else if (delta < LVL_START(7)) {
idx = calc_index(expires, 6, bucket_expiry);
} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
idx = calc_index(expires, 7, bucket_expiry);
} else if ((long) delta < 0) {
idx = clk & LVL_MASK;
*bucket_expiry = clk;
} else {
/*
* Force expire obscene large timeouts to expire at the
* capacity limit of the wheel.
*/
if (delta >= WHEEL_TIMEOUT_CUTOFF)
expires = clk + WHEEL_TIMEOUT_MAX;
idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry);
}
return idx;
}
static void
trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
{
/*
* Deferrable timers do not prevent the CPU from entering dynticks and
* are not taken into account on the idle/nohz_full path. An IPI when a
* new deferrable timer is enqueued will wake up the remote CPU but
* nothing will be done with the deferrable timer base. Therefore skip
* the remote IPI for deferrable timers completely.
*/
if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE)
return;
/*
* We might have to IPI the remote CPU if the base is idle and the
* timer is pinned. If it is a non pinned timer, it is only queued
* on the remote CPU, when timer was running during queueing. Then
* everything is handled by remote CPU anyway. If the other CPU is
* on the way to idle then it can't set base->is_idle as we hold
* the base lock:
*/
if (base->is_idle) { WARN_ON_ONCE(!(timer->flags & TIMER_PINNED ||
tick_nohz_full_cpu(base->cpu)));
wake_up_nohz_cpu(base->cpu);
}
}
/*
* Enqueue the timer into the hash bucket, mark it pending in
* the bitmap, store the index in the timer flags then wake up
* the target CPU if needed.
*/
static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
unsigned int idx, unsigned long bucket_expiry)
{ hlist_add_head(&timer->entry, base->vectors + idx);
__set_bit(idx, base->pending_map);
timer_set_idx(timer, idx);
trace_timer_start(timer, bucket_expiry);
/*
* Check whether this is the new first expiring timer. The
* effective expiry time of the timer is required here
* (bucket_expiry) instead of timer->expires.
*/
if (time_before(bucket_expiry, base->next_expiry)) {
/*
* Set the next expiry time and kick the CPU so it
* can reevaluate the wheel:
*/
WRITE_ONCE(base->next_expiry, bucket_expiry);
base->timers_pending = true;
base->next_expiry_recalc = false;
trigger_dyntick_cpu(base, timer);
}
}
static void internal_add_timer(struct timer_base *base, struct timer_list *timer)
{
unsigned long bucket_expiry;
unsigned int idx;
idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry);
enqueue_timer(base, timer, idx, bucket_expiry);
}
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static const struct debug_obj_descr timer_debug_descr;
struct timer_hint {
void (*function)(struct timer_list *t);
long offset;
};
#define TIMER_HINT(fn, container, timr, hintfn) \
{ \
.function = fn, \
.offset = offsetof(container, hintfn) - \
offsetof(container, timr) \
}
static const struct timer_hint timer_hints[] = {
TIMER_HINT(delayed_work_timer_fn,
struct delayed_work, timer, work.func),
TIMER_HINT(kthread_delayed_work_timer_fn,
struct kthread_delayed_work, timer, work.func),
};
static void *timer_debug_hint(void *addr)
{
struct timer_list *timer = addr;
int i;
for (i = 0; i < ARRAY_SIZE(timer_hints); i++) {
if (timer_hints[i].function == timer->function) {
void (**fn)(void) = addr + timer_hints[i].offset;
return *fn;
}
}
return timer->function;
}
static bool timer_is_static_object(void *addr)
{
struct timer_list *timer = addr;
return (timer->entry.pprev == NULL &&
timer->entry.next == TIMER_ENTRY_STATIC);
}
/*
* timer_fixup_init is called when:
* - an active object is initialized
*/
static bool timer_fixup_init(void *addr, enum debug_obj_state state)
{
struct timer_list *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
timer_delete_sync(timer);
debug_object_init(timer, &timer_debug_descr);
return true;
default:
return false;
}
}
/* Stub timer callback for improperly used timers. */
static void stub_timer(struct timer_list *unused)
{
WARN_ON(1);
}
/*
* timer_fixup_activate is called when:
* - an active object is activated
* - an unknown non-static object is activated
*/
static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
{
struct timer_list *timer = addr;
switch (state) {
case ODEBUG_STATE_NOTAVAILABLE:
timer_setup(timer, stub_timer, 0);
return true;
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
fallthrough;
default:
return false;
}
}
/*
* timer_fixup_free is called when:
* - an active object is freed
*/
static bool timer_fixup_free(void *addr, enum debug_obj_state state)
{
struct timer_list *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
timer_delete_sync(timer);
debug_object_free(timer, &timer_debug_descr);
return true;
default:
return false;
}
}
/*
* timer_fixup_assert_init is called when:
* - an untracked/uninit-ed object is found
*/
static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
{
struct timer_list *timer = addr;
switch (state) {
case ODEBUG_STATE_NOTAVAILABLE:
timer_setup(timer, stub_timer, 0);
return true;
default:
return false;
}
}
static const struct debug_obj_descr timer_debug_descr = {
.name = "timer_list",
.debug_hint = timer_debug_hint,
.is_static_object = timer_is_static_object,
.fixup_init = timer_fixup_init,
.fixup_activate = timer_fixup_activate,
.fixup_free = timer_fixup_free,
.fixup_assert_init = timer_fixup_assert_init,
};
static inline void debug_timer_init(struct timer_list *timer)
{
debug_object_init(timer, &timer_debug_descr);
}
static inline void debug_timer_activate(struct timer_list *timer)
{
debug_object_activate(timer, &timer_debug_descr);
}
static inline void debug_timer_deactivate(struct timer_list *timer)
{
debug_object_deactivate(timer, &timer_debug_descr);
}
static inline void debug_timer_assert_init(struct timer_list *timer)
{
debug_object_assert_init(timer, &timer_debug_descr);
}
static void do_init_timer(struct timer_list *timer,
void (*func)(struct timer_list *),
unsigned int flags,
const char *name, struct lock_class_key *key);
void init_timer_on_stack_key(struct timer_list *timer,
void (*func)(struct timer_list *),
unsigned int flags,
const char *name, struct lock_class_key *key)
{
debug_object_init_on_stack(timer, &timer_debug_descr);
do_init_timer(timer, func, flags, name, key);
}
EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
void destroy_timer_on_stack(struct timer_list *timer)
{
debug_object_free(timer, &timer_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_timer_on_stack);
#else
static inline void debug_timer_init(struct timer_list *timer) { }
static inline void debug_timer_activate(struct timer_list *timer) { }
static inline void debug_timer_deactivate(struct timer_list *timer) { }
static inline void debug_timer_assert_init(struct timer_list *timer) { }
#endif
static inline void debug_init(struct timer_list *timer)
{
debug_timer_init(timer);
trace_timer_init(timer);
}
static inline void debug_deactivate(struct timer_list *timer)
{
debug_timer_deactivate(timer);
trace_timer_cancel(timer);
}
static inline void debug_assert_init(struct timer_list *timer)
{
debug_timer_assert_init(timer);
}
static void do_init_timer(struct timer_list *timer,
void (*func)(struct timer_list *),
unsigned int flags,
const char *name, struct lock_class_key *key)
{
timer->entry.pprev = NULL;
timer->function = func;
if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS))
flags &= TIMER_INIT_FLAGS;
timer->flags = flags | raw_smp_processor_id();
lockdep_init_map(&timer->lockdep_map, name, key, 0);
}
/**
* init_timer_key - initialize a timer
* @timer: the timer to be initialized
* @func: timer callback function
* @flags: timer flags
* @name: name of the timer
* @key: lockdep class key of the fake lock used for tracking timer
* sync lock dependencies
*
* init_timer_key() must be done to a timer prior to calling *any* of the
* other timer functions.
*/
void init_timer_key(struct timer_list *timer,
void (*func)(struct timer_list *), unsigned int flags,
const char *name, struct lock_class_key *key)
{ debug_init(timer); do_init_timer(timer, func, flags, name, key);
}
EXPORT_SYMBOL(init_timer_key);
static inline void detach_timer(struct timer_list *timer, bool clear_pending)
{
struct hlist_node *entry = &timer->entry;
debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL;
entry->next = LIST_POISON2;
}
static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
bool clear_pending)
{
unsigned idx = timer_get_idx(timer);
if (!timer_pending(timer))
return 0;
if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map);
base->next_expiry_recalc = true;
}
detach_timer(timer, clear_pending);
return 1;
}
static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
{
int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
/*
* If the timer is deferrable and NO_HZ_COMMON is set then we need
* to use the deferrable base.
*/
if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
index = BASE_DEF;
return per_cpu_ptr(&timer_bases[index], cpu);
}
static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
{
int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
/*
* If the timer is deferrable and NO_HZ_COMMON is set then we need
* to use the deferrable base.
*/
if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
index = BASE_DEF;
return this_cpu_ptr(&timer_bases[index]);
}
static inline struct timer_base *get_timer_base(u32 tflags)
{
return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
}
static inline void __forward_timer_base(struct timer_base *base,
unsigned long basej)
{
/*
* Check whether we can forward the base. We can only do that when
* @basej is past base->clk otherwise we might rewind base->clk.
*/
if (time_before_eq(basej, base->clk))
return;
/*
* If the next expiry value is > jiffies, then we fast forward to
* jiffies otherwise we forward to the next expiry value.
*/
if (time_after(base->next_expiry, basej)) {
base->clk = basej;
} else {
if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
return;
base->clk = base->next_expiry;
}
}
static inline void forward_timer_base(struct timer_base *base)
{
__forward_timer_base(base, READ_ONCE(jiffies));
}
/*
* We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
* that all timers which are tied to this base are locked, and the base itself
* is locked too.
*
* So __run_timers/migrate_timers can safely modify all timers which could
* be found in the base->vectors array.
*
* When a timer is migrating then the TIMER_MIGRATING flag is set and we need
* to wait until the migration is done.
*/
static struct timer_base *lock_timer_base(struct timer_list *timer,
unsigned long *flags)
__acquires(timer->base->lock)
{
for (;;) {
struct timer_base *base;
u32 tf;
/*
* We need to use READ_ONCE() here, otherwise the compiler
* might re-read @tf between the check for TIMER_MIGRATING
* and spin_lock().
*/
tf = READ_ONCE(timer->flags);
if (!(tf & TIMER_MIGRATING)) {
base = get_timer_base(tf);
raw_spin_lock_irqsave(&base->lock, *flags);
if (timer->flags == tf)
return base;
raw_spin_unlock_irqrestore(&base->lock, *flags);
}
cpu_relax();
}
}
#define MOD_TIMER_PENDING_ONLY 0x01
#define MOD_TIMER_REDUCE 0x02
#define MOD_TIMER_NOTPENDING 0x04
static inline int
__mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options)
{
unsigned long clk = 0, flags, bucket_expiry;
struct timer_base *base, *new_base;
unsigned int idx = UINT_MAX;
int ret = 0;
debug_assert_init(timer);
/*
* This is a common optimization triggered by the networking code - if
* the timer is re-modified to have the same timeout or ends up in the
* same array bucket then just return:
*/
if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) {
/*
* The downside of this optimization is that it can result in
* larger granularity than you would get from adding a new
* timer with this expiry.
*/
long diff = timer->expires - expires;
if (!diff)
return 1;
if (options & MOD_TIMER_REDUCE && diff <= 0)
return 1;
/*
* We lock timer base and calculate the bucket index right
* here. If the timer ends up in the same bucket, then we
* just update the expiry time and avoid the whole
* dequeue/enqueue dance.
*/
base = lock_timer_base(timer, &flags);
/*
* Has @timer been shutdown? This needs to be evaluated
* while holding base lock to prevent a race against the
* shutdown code.
*/
if (!timer->function)
goto out_unlock;
forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) &&
time_before_eq(timer->expires, expires)) {
ret = 1;
goto out_unlock;
}
clk = base->clk;
idx = calc_wheel_index(expires, clk, &bucket_expiry);
/*
* Retrieve and compare the array index of the pending
* timer. If it matches set the expiry to the new value so a
* subsequent call will exit in the expires check above.
*/
if (idx == timer_get_idx(timer)) {
if (!(options & MOD_TIMER_REDUCE))
timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires;
ret = 1;
goto out_unlock;
}
} else {
base = lock_timer_base(timer, &flags);
/*
* Has @timer been shutdown? This needs to be evaluated
* while holding base lock to prevent a race against the
* shutdown code.
*/
if (!timer->function)
goto out_unlock;
forward_timer_base(base);
}
ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY))
goto out_unlock;
new_base = get_timer_this_cpu_base(timer->flags);
if (base != new_base) {
/*
* We are trying to schedule the timer on the new base.
* However we can't change timer's base while it is running,
* otherwise timer_delete_sync() can't detect that the timer's
* handler yet has not finished. This also guarantees that the
* timer is serialized wrt itself.
*/
if (likely(base->running_timer != timer)) {
/* See the comment in lock_timer_base() */
timer->flags |= TIMER_MIGRATING;
raw_spin_unlock(&base->lock);
base = new_base;
raw_spin_lock(&base->lock);
WRITE_ONCE(timer->flags,
(timer->flags & ~TIMER_BASEMASK) | base->cpu);
forward_timer_base(base);
}
}
debug_timer_activate(timer);
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
* between calculating 'idx' and possibly switching the base, only
* enqueue_timer() is required. Otherwise we need to (re)calculate
* the wheel index via internal_add_timer().
*/
if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry);
else
internal_add_timer(base, timer);
out_unlock:
raw_spin_unlock_irqrestore(&base->lock, flags);
return ret;
}
/**
* mod_timer_pending - Modify a pending timer's timeout
* @timer: The pending timer to be modified
* @expires: New absolute timeout in jiffies
*
* mod_timer_pending() is the same for pending timers as mod_timer(), but
* will not activate inactive timers.
*
* If @timer->function == NULL then the start operation is silently
* discarded.
*
* Return:
* * %0 - The timer was inactive and not modified or was in
* shutdown state and the operation was discarded
* * %1 - The timer was active and requeued to expire at @expires
*/
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
{
return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY);
}
EXPORT_SYMBOL(mod_timer_pending);
/**
* mod_timer - Modify a timer's timeout
* @timer: The timer to be modified
* @expires: New absolute timeout in jiffies
*
* mod_timer(timer, expires) is equivalent to:
*
* timer_delete(timer); timer->expires = expires; add_timer(timer);
*
* mod_timer() is more efficient than the above open coded sequence. In
* case that the timer is inactive, the timer_delete() part is a NOP. The
* timer is in any case activated with the new expiry time @expires.
*
* Note that if there are multiple unserialized concurrent users of the
* same timer, then mod_timer() is the only safe way to modify the timeout,
* since add_timer() cannot modify an already running timer.
*
* If @timer->function == NULL then the start operation is silently
* discarded. In this case the return value is 0 and meaningless.
*
* Return:
* * %0 - The timer was inactive and started or was in shutdown
* state and the operation was discarded
* * %1 - The timer was active and requeued to expire at @expires or
* the timer was active and not modified because @expires did
* not change the effective expiry time
*/
int mod_timer(struct timer_list *timer, unsigned long expires)
{
return __mod_timer(timer, expires, 0);
}
EXPORT_SYMBOL(mod_timer);
/**
* timer_reduce - Modify a timer's timeout if it would reduce the timeout
* @timer: The timer to be modified
* @expires: New absolute timeout in jiffies
*
* timer_reduce() is very similar to mod_timer(), except that it will only
* modify an enqueued timer if that would reduce the expiration time. If
* @timer is not enqueued it starts the timer.
*
* If @timer->function == NULL then the start operation is silently
* discarded.
*
* Return:
* * %0 - The timer was inactive and started or was in shutdown
* state and the operation was discarded
* * %1 - The timer was active and requeued to expire at @expires or
* the timer was active and not modified because @expires
* did not change the effective expiry time such that the
* timer would expire earlier than already scheduled
*/
int timer_reduce(struct timer_list *timer, unsigned long expires)
{
return __mod_timer(timer, expires, MOD_TIMER_REDUCE);
}
EXPORT_SYMBOL(timer_reduce);
/**
* add_timer - Start a timer
* @timer: The timer to be started
*
* Start @timer to expire at @timer->expires in the future. @timer->expires
* is the absolute expiry time measured in 'jiffies'. When the timer expires
* timer->function(timer) will be invoked from soft interrupt context.
*
* The @timer->expires and @timer->function fields must be set prior
* to calling this function.
*
* If @timer->function == NULL then the start operation is silently
* discarded.
*
* If @timer->expires is already in the past @timer will be queued to
* expire at the next timer tick.
*
* This can only operate on an inactive timer. Attempts to invoke this on
* an active timer are rejected with a warning.
*/
void add_timer(struct timer_list *timer)
{
if (WARN_ON_ONCE(timer_pending(timer)))
return;
__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
}
EXPORT_SYMBOL(add_timer);
/**
* add_timer_local() - Start a timer on the local CPU
* @timer: The timer to be started
*
* Same as add_timer() except that the timer flag TIMER_PINNED is set.
*
* See add_timer() for further details.
*/
void add_timer_local(struct timer_list *timer)
{
if (WARN_ON_ONCE(timer_pending(timer)))
return;
timer->flags |= TIMER_PINNED;
__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
}
EXPORT_SYMBOL(add_timer_local);
/**
* add_timer_global() - Start a timer without TIMER_PINNED flag set
* @timer: The timer to be started
*
* Same as add_timer() except that the timer flag TIMER_PINNED is unset.
*
* See add_timer() for further details.
*/
void add_timer_global(struct timer_list *timer)
{ if (WARN_ON_ONCE(timer_pending(timer)))
return;
timer->flags &= ~TIMER_PINNED;
__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
}
EXPORT_SYMBOL(add_timer_global);
/**
* add_timer_on - Start a timer on a particular CPU
* @timer: The timer to be started
* @cpu: The CPU to start it on
*
* Same as add_timer() except that it starts the timer on the given CPU and
* the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in
* the next round, add_timer_global() should be used instead as it unsets
* the TIMER_PINNED flag.
*
* See add_timer() for further details.
*/
void add_timer_on(struct timer_list *timer, int cpu)
{
struct timer_base *new_base, *base;
unsigned long flags;
debug_assert_init(timer);
if (WARN_ON_ONCE(timer_pending(timer)))
return;
/* Make sure timer flags have TIMER_PINNED flag set */
timer->flags |= TIMER_PINNED;
new_base = get_timer_cpu_base(timer->flags, cpu);
/*
* If @timer was on a different CPU, it should be migrated with the
* old base locked to prevent other operations proceeding with the
* wrong base locked. See lock_timer_base().
*/
base = lock_timer_base(timer, &flags);
/*
* Has @timer been shutdown? This needs to be evaluated while
* holding base lock to prevent a race against the shutdown code.
*/
if (!timer->function)
goto out_unlock;
if (base != new_base) {
timer->flags |= TIMER_MIGRATING;
raw_spin_unlock(&base->lock);
base = new_base;
raw_spin_lock(&base->lock);
WRITE_ONCE(timer->flags,
(timer->flags & ~TIMER_BASEMASK) | cpu);
}
forward_timer_base(base);
debug_timer_activate(timer);
internal_add_timer(base, timer);
out_unlock:
raw_spin_unlock_irqrestore(&base->lock, flags);
}
EXPORT_SYMBOL_GPL(add_timer_on);
/**
* __timer_delete - Internal function: Deactivate a timer
* @timer: The timer to be deactivated
* @shutdown: If true, this indicates that the timer is about to be
* shutdown permanently.
*
* If @shutdown is true then @timer->function is set to NULL under the
* timer base lock which prevents further rearming of the time. In that
* case any attempt to rearm @timer after this function returns will be
* silently ignored.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
*/
static int __timer_delete(struct timer_list *timer, bool shutdown)
{
struct timer_base *base;
unsigned long flags;
int ret = 0;
debug_assert_init(timer);
/*
* If @shutdown is set then the lock has to be taken whether the
* timer is pending or not to protect against a concurrent rearm
* which might hit between the lockless pending check and the lock
* acquisition. By taking the lock it is ensured that such a newly
* enqueued timer is dequeued and cannot end up with
* timer->function == NULL in the expiry code.
*
* If timer->function is currently executed, then this makes sure
* that the callback cannot requeue the timer.
*/
if (timer_pending(timer) || shutdown) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL;
raw_spin_unlock_irqrestore(&base->lock, flags);
}
return ret;
}
/**
* timer_delete - Deactivate a timer
* @timer: The timer to be deactivated
*
* The function only deactivates a pending timer, but contrary to
* timer_delete_sync() it does not take into account whether the timer's
* callback function is concurrently executed on a different CPU or not.
* It neither prevents rearming of the timer. If @timer can be rearmed
* concurrently then the return value of this function is meaningless.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
*/
int timer_delete(struct timer_list *timer)
{
return __timer_delete(timer, false);
}
EXPORT_SYMBOL(timer_delete);
/**
* timer_shutdown - Deactivate a timer and prevent rearming
* @timer: The timer to be deactivated
*
* The function does not wait for an eventually running timer callback on a
* different CPU but it prevents rearming of the timer. Any attempt to arm
* @timer after this function returns will be silently ignored.
*
* This function is useful for teardown code and should only be used when
* timer_shutdown_sync() cannot be invoked due to locking or context constraints.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending
*/
int timer_shutdown(struct timer_list *timer)
{
return __timer_delete(timer, true);
}
EXPORT_SYMBOL_GPL(timer_shutdown);
/**
* __try_to_del_timer_sync - Internal function: Try to deactivate a timer
* @timer: Timer to deactivate
* @shutdown: If true, this indicates that the timer is about to be
* shutdown permanently.
*
* If @shutdown is true then @timer->function is set to NULL under the
* timer base lock which prevents further rearming of the timer. Any
* attempt to rearm @timer after this function returns will be silently
* ignored.
*
* This function cannot guarantee that the timer cannot be rearmed
* right after dropping the base lock if @shutdown is false. That
* needs to be prevented by the calling code if necessary.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
* * %-1 - The timer callback function is running on a different CPU
*/
static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown)
{
struct timer_base *base;
unsigned long flags;
int ret = -1;
debug_assert_init(timer);
base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL;
raw_spin_unlock_irqrestore(&base->lock, flags);
return ret;
}
/**
* try_to_del_timer_sync - Try to deactivate a timer
* @timer: Timer to deactivate
*
* This function tries to deactivate a timer. On success the timer is not
* queued and the timer callback function is not running on any CPU.
*
* This function does not guarantee that the timer cannot be rearmed right
* after dropping the base lock. That needs to be prevented by the calling
* code if necessary.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
* * %-1 - The timer callback function is running on a different CPU
*/
int try_to_del_timer_sync(struct timer_list *timer)
{
return __try_to_del_timer_sync(timer, false);
}
EXPORT_SYMBOL(try_to_del_timer_sync);
#ifdef CONFIG_PREEMPT_RT
static __init void timer_base_init_expiry_lock(struct timer_base *base)
{
spin_lock_init(&base->expiry_lock);
}
static inline void timer_base_lock_expiry(struct timer_base *base)
{
spin_lock(&base->expiry_lock);
}
static inline void timer_base_unlock_expiry(struct timer_base *base)
{
spin_unlock(&base->expiry_lock);
}
/*
* The counterpart to del_timer_wait_running().
*
* If there is a waiter for base->expiry_lock, then it was waiting for the
* timer callback to finish. Drop expiry_lock and reacquire it. That allows
* the waiter to acquire the lock and make progress.
*/
static void timer_sync_wait_running(struct timer_base *base)
__releases(&base->lock) __releases(&base->expiry_lock)
__acquires(&base->expiry_lock) __acquires(&base->lock)
{
if (atomic_read(&base->timer_waiters)) {
raw_spin_unlock_irq(&base->lock);
spin_unlock(&base->expiry_lock);
spin_lock(&base->expiry_lock);
raw_spin_lock_irq(&base->lock);
}
}
/*
* This function is called on PREEMPT_RT kernels when the fast path
* deletion of a timer failed because the timer callback function was
* running.
*
* This prevents priority inversion, if the softirq thread on a remote CPU
* got preempted, and it prevents a life lock when the task which tries to
* delete a timer preempted the softirq thread running the timer callback
* function.
*/
static void del_timer_wait_running(struct timer_list *timer)
{
u32 tf;
tf = READ_ONCE(timer->flags);
if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) {
struct timer_base *base = get_timer_base(tf);
/*
* Mark the base as contended and grab the expiry lock,
* which is held by the softirq across the timer
* callback. Drop the lock immediately so the softirq can
* expire the next timer. In theory the timer could already
* be running again, but that's more than unlikely and just
* causes another wait loop.
*/
atomic_inc(&base->timer_waiters);
spin_lock_bh(&base->expiry_lock);
atomic_dec(&base->timer_waiters);
spin_unlock_bh(&base->expiry_lock);
}
}
#else
static inline void timer_base_init_expiry_lock(struct timer_base *base) { }
static inline void timer_base_lock_expiry(struct timer_base *base) { }
static inline void timer_base_unlock_expiry(struct timer_base *base) { }
static inline void timer_sync_wait_running(struct timer_base *base) { }
static inline void del_timer_wait_running(struct timer_list *timer) { }
#endif
/**
* __timer_delete_sync - Internal function: Deactivate a timer and wait
* for the handler to finish.
* @timer: The timer to be deactivated
* @shutdown: If true, @timer->function will be set to NULL under the
* timer base lock which prevents rearming of @timer
*
* If @shutdown is not set the timer can be rearmed later. If the timer can
* be rearmed concurrently, i.e. after dropping the base lock then the
* return value is meaningless.
*
* If @shutdown is set then @timer->function is set to NULL under timer
* base lock which prevents rearming of the timer. Any attempt to rearm
* a shutdown timer is silently ignored.
*
* If the timer should be reused after shutdown it has to be initialized
* again.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
*/
static int __timer_delete_sync(struct timer_list *timer, bool shutdown)
{
int ret;
#ifdef CONFIG_LOCKDEP
unsigned long flags;
/*
* If lockdep gives a backtrace here, please reference
* the synchronization rules above.
*/
local_irq_save(flags);
lock_map_acquire(&timer->lockdep_map);
lock_map_release(&timer->lockdep_map);
local_irq_restore(flags);
#endif
/*
* don't use it in hardirq context, because it
* could lead to deadlock.
*/
WARN_ON(in_hardirq() && !(timer->flags & TIMER_IRQSAFE));
/*
* Must be able to sleep on PREEMPT_RT because of the slowpath in
* del_timer_wait_running().
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(timer->flags & TIMER_IRQSAFE))
lockdep_assert_preemption_enabled();
do {
ret = __try_to_del_timer_sync(timer, shutdown);
if (unlikely(ret < 0)) {
del_timer_wait_running(timer);
cpu_relax();
}
} while (ret < 0);
return ret;
}
/**
* timer_delete_sync - Deactivate a timer and wait for the handler to finish.
* @timer: The timer to be deactivated
*
* Synchronization rules: Callers must prevent restarting of the timer,
* otherwise this function is meaningless. It must not be called from
* interrupt contexts unless the timer is an irqsafe one. The caller must
* not hold locks which would prevent completion of the timer's callback
* function. The timer's handler must not call add_timer_on(). Upon exit
* the timer is not queued and the handler is not running on any CPU.
*
* For !irqsafe timers, the caller must not hold locks that are held in
* interrupt context. Even if the lock has nothing to do with the timer in
* question. Here's why::
*
* CPU0 CPU1
* ---- ----
* <SOFTIRQ>
* call_timer_fn();
* base->running_timer = mytimer;
* spin_lock_irq(somelock);
* <IRQ>
* spin_lock(somelock);
* timer_delete_sync(mytimer);
* while (base->running_timer == mytimer);
*
* Now timer_delete_sync() will never return and never release somelock.
* The interrupt on the other CPU is waiting to grab somelock but it has
* interrupted the softirq that CPU0 is waiting to finish.
*
* This function cannot guarantee that the timer is not rearmed again by
* some concurrent or preempting code, right after it dropped the base
* lock. If there is the possibility of a concurrent rearm then the return
* value of the function is meaningless.
*
* If such a guarantee is needed, e.g. for teardown situations then use
* timer_shutdown_sync() instead.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending and deactivated
*/
int timer_delete_sync(struct timer_list *timer)
{
return __timer_delete_sync(timer, false);
}
EXPORT_SYMBOL(timer_delete_sync);
/**
* timer_shutdown_sync - Shutdown a timer and prevent rearming
* @timer: The timer to be shutdown
*
* When the function returns it is guaranteed that:
* - @timer is not queued
* - The callback function of @timer is not running
* - @timer cannot be enqueued again. Any attempt to rearm
* @timer is silently ignored.
*
* See timer_delete_sync() for synchronization rules.
*
* This function is useful for final teardown of an infrastructure where
* the timer is subject to a circular dependency problem.
*
* A common pattern for this is a timer and a workqueue where the timer can
* schedule work and work can arm the timer. On shutdown the workqueue must
* be destroyed and the timer must be prevented from rearming. Unless the
* code has conditionals like 'if (mything->in_shutdown)' to prevent that
* there is no way to get this correct with timer_delete_sync().
*
* timer_shutdown_sync() is solving the problem. The correct ordering of
* calls in this case is:
*
* timer_shutdown_sync(&mything->timer);
* workqueue_destroy(&mything->workqueue);
*
* After this 'mything' can be safely freed.
*
* This obviously implies that the timer is not required to be functional
* for the rest of the shutdown operation.
*
* Return:
* * %0 - The timer was not pending
* * %1 - The timer was pending
*/
int timer_shutdown_sync(struct timer_list *timer)
{
return __timer_delete_sync(timer, true);
}
EXPORT_SYMBOL_GPL(timer_shutdown_sync);
static void call_timer_fn(struct timer_list *timer,
void (*fn)(struct timer_list *),
unsigned long baseclk)
{
int count = preempt_count();
#ifdef CONFIG_LOCKDEP
/*
* It is permissible to free the timer from inside the
* function that is called from it, this we need to take into
* account for lockdep too. To avoid bogus "held lock freed"
* warnings as well as problems when looking into
* timer->lockdep_map, make a copy and use that here.
*/
struct lockdep_map lockdep_map;
lockdep_copy_map(&lockdep_map, &timer->lockdep_map);
#endif
/*
* Couple the lock chain with the lock chain at
* timer_delete_sync() by acquiring the lock_map around the fn()
* call here and in timer_delete_sync().
*/
lock_map_acquire(&lockdep_map);
trace_timer_expire_entry(timer, baseclk);
fn(timer);
trace_timer_expire_exit(timer);
lock_map_release(&lockdep_map);
if (count != preempt_count()) {
WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n",
fn, count, preempt_count());
/*
* Restore the preempt count. That gives us a decent
* chance to survive and extract information. If the
* callback kept a lock held, bad luck, but not worse
* than the BUG() we had.
*/
preempt_count_set(count);
}
}
static void expire_timers(struct timer_base *base, struct hlist_head *head)
{
/*
* This value is required only for tracing. base->clk was
* incremented directly before expire_timers was called. But expiry
* is related to the old base->clk value.
*/
unsigned long baseclk = base->clk - 1;
while (!hlist_empty(head)) {
struct timer_list *timer;
void (*fn)(struct timer_list *);
timer = hlist_entry(head->first, struct timer_list, entry);
base->running_timer = timer;
detach_timer(timer, true);
fn = timer->function;
if (WARN_ON_ONCE(!fn)) {
/* Should never happen. Emphasis on should! */
base->running_timer = NULL;
continue;
}
if (timer->flags & TIMER_IRQSAFE) {
raw_spin_unlock(&base->lock);
call_timer_fn(timer, fn, baseclk);
raw_spin_lock(&base->lock);
base->running_timer = NULL;
} else {
raw_spin_unlock_irq(&base->lock);
call_timer_fn(timer, fn, baseclk);
raw_spin_lock_irq(&base->lock);
base->running_timer = NULL;
timer_sync_wait_running(base);
}
}
}
static int collect_expired_timers(struct timer_base *base,
struct hlist_head *heads)
{
unsigned long clk = base->clk = base->next_expiry;
struct hlist_head *vec;
int i, levels = 0;
unsigned int idx;
for (i = 0; i < LVL_DEPTH; i++) {
idx = (clk & LVL_MASK) + i * LVL_SIZE;
if (__test_and_clear_bit(idx, base->pending_map)) {
vec = base->vectors + idx;
hlist_move_list(vec, heads++);
levels++;
}
/* Is it time to look at the next level? */
if (clk & LVL_CLK_MASK)
break;
/* Shift clock for the next level granularity */
clk >>= LVL_CLK_SHIFT;
}
return levels;
}
/*
* Find the next pending bucket of a level. Search from level start (@offset)
* + @clk upwards and if nothing there, search from start of the level
* (@offset) up to @offset + clk.
*/
static int next_pending_bucket(struct timer_base *base, unsigned offset,
unsigned clk)
{
unsigned pos, start = offset + clk;
unsigned end = offset + LVL_SIZE;
pos = find_next_bit(base->pending_map, end, start);
if (pos < end)
return pos - start;
pos = find_next_bit(base->pending_map, start, offset);
return pos < start ? pos + LVL_SIZE - start : -1;
}
/*
* Search the first expiring timer in the various clock levels. Caller must
* hold base->lock.
*
* Store next expiry time in base->next_expiry.
*/
static void timer_recalc_next_expiry(struct timer_base *base)
{
unsigned long clk, next, adj;
unsigned lvl, offset = 0;
next = base->clk + NEXT_TIMER_MAX_DELTA;
clk = base->clk;
for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
int pos = next_pending_bucket(base, offset, clk & LVL_MASK);
unsigned long lvl_clk = clk & LVL_CLK_MASK;
if (pos >= 0) {
unsigned long tmp = clk + (unsigned long) pos;
tmp <<= LVL_SHIFT(lvl);
if (time_before(tmp, next))
next = tmp;
/*
* If the next expiration happens before we reach
* the next level, no need to check further.
*/
if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK))
break;
}
/*
* Clock for the next level. If the current level clock lower
* bits are zero, we look at the next level as is. If not we
* need to advance it by one because that's going to be the
* next expiring bucket in that level. base->clk is the next
* expiring jiffy. So in case of:
*
* LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
* 0 0 0 0 0 0
*
* we have to look at all levels @index 0. With
*
* LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
* 0 0 0 0 0 2
*
* LVL0 has the next expiring bucket @index 2. The upper
* levels have the next expiring bucket @index 1.
*
* In case that the propagation wraps the next level the same
* rules apply:
*
* LVL5 LVL4 LVL3 LVL2 LVL1 LVL0
* 0 0 0 0 F 2
*
* So after looking at LVL0 we get:
*
* LVL5 LVL4 LVL3 LVL2 LVL1
* 0 0 0 1 0
*
* So no propagation from LVL1 to LVL2 because that happened
* with the add already, but then we need to propagate further
* from LVL2 to LVL3.
*
* So the simple check whether the lower bits of the current
* level are 0 or not is sufficient for all cases.
*/
adj = lvl_clk ? 1 : 0;
clk >>= LVL_CLK_SHIFT;
clk += adj;
}
WRITE_ONCE(base->next_expiry, next);
base->next_expiry_recalc = false;
base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
}
#ifdef CONFIG_NO_HZ_COMMON
/*
* Check, if the next hrtimer event is before the next timer wheel
* event:
*/
static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
{
u64 nextevt = hrtimer_get_next_event();
/*
* If high resolution timers are enabled
* hrtimer_get_next_event() returns KTIME_MAX.
*/
if (expires <= nextevt)
return expires;
/*
* If the next timer is already expired, return the tick base
* time so the tick is fired immediately.
*/
if (nextevt <= basem)
return basem;
/*
* Round up to the next jiffy. High resolution timers are
* off, so the hrtimers are expired in the tick and we need to
* make sure that this tick really expires the timer to avoid
* a ping pong of the nohz stop code.
*
* Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
*/
return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
}
static unsigned long next_timer_interrupt(struct timer_base *base,
unsigned long basej)
{
if (base->next_expiry_recalc)
timer_recalc_next_expiry(base);
/*
* Move next_expiry for the empty base into the future to prevent an
* unnecessary raise of the timer softirq when the next_expiry value
* will be reached even if there is no timer pending.
*
* This update is also required to make timer_base::next_expiry values
* easy comparable to find out which base holds the first pending timer.
*/
if (!base->timers_pending)
WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA);
return base->next_expiry;
}
static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem,
struct timer_base *base_local,
struct timer_base *base_global,
struct timer_events *tevt)
{
unsigned long nextevt, nextevt_local, nextevt_global;
bool local_first;
nextevt_local = next_timer_interrupt(base_local, basej);
nextevt_global = next_timer_interrupt(base_global, basej);
local_first = time_before_eq(nextevt_local, nextevt_global);
nextevt = local_first ? nextevt_local : nextevt_global;
/*
* If the @nextevt is at max. one tick away, use @nextevt and store
* it in the local expiry value. The next global event is irrelevant in
* this case and can be left as KTIME_MAX.
*/
if (time_before_eq(nextevt, basej + 1)) {
/* If we missed a tick already, force 0 delta */
if (time_before(nextevt, basej))
nextevt = basej;
tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
* This is required for the remote check only but it doesn't
* hurt, when it is done for both call sites:
*
* * The remote callers will only take care of the global timers
* as local timers will be handled by CPU itself. When not
* updating tevt->global with the already missed first global
* timer, it is possible that it will be missed completely.
*
* * The local callers will ignore the tevt->global anyway, when
* nextevt is max. one tick away.
*/
if (!local_first)
tevt->global = tevt->local;
return nextevt;
}
/*
* Update tevt.* values:
*
* If the local queue expires first, then the global event can be
* ignored. If the global queue is empty, nothing to do either.
*/
if (!local_first && base_global->timers_pending)
tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC;
if (base_local->timers_pending)
tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC;
return nextevt;
}
# ifdef CONFIG_SMP
/**
* fetch_next_timer_interrupt_remote() - Store next timers into @tevt
* @basej: base time jiffies
* @basem: base time clock monotonic
* @tevt: Pointer to the storage for the expiry values
* @cpu: Remote CPU
*
* Stores the next pending local and global timer expiry values in the
* struct pointed to by @tevt. If a queue is empty the corresponding
* field is set to KTIME_MAX. If local event expires before global
* event, global event is set to KTIME_MAX as well.
*
* Caller needs to make sure timer base locks are held (use
* timer_lock_remote_bases() for this purpose).
*/
void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem,
struct timer_events *tevt,
unsigned int cpu)
{
struct timer_base *base_local, *base_global;
/* Preset local / global events */
tevt->local = tevt->global = KTIME_MAX;
base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
lockdep_assert_held(&base_local->lock);
lockdep_assert_held(&base_global->lock);
fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt);
}
/**
* timer_unlock_remote_bases - unlock timer bases of cpu
* @cpu: Remote CPU
*
* Unlocks the remote timer bases.
*/
void timer_unlock_remote_bases(unsigned int cpu)
__releases(timer_bases[BASE_LOCAL]->lock)
__releases(timer_bases[BASE_GLOBAL]->lock)
{
struct timer_base *base_local, *base_global;
base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
raw_spin_unlock(&base_global->lock);
raw_spin_unlock(&base_local->lock);
}
/**
* timer_lock_remote_bases - lock timer bases of cpu
* @cpu: Remote CPU
*
* Locks the remote timer bases.
*/
void timer_lock_remote_bases(unsigned int cpu)
__acquires(timer_bases[BASE_LOCAL]->lock)
__acquires(timer_bases[BASE_GLOBAL]->lock)
{
struct timer_base *base_local, *base_global;
base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
lockdep_assert_irqs_disabled();
raw_spin_lock(&base_local->lock);
raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
}
/**
* timer_base_is_idle() - Return whether timer base is set idle
*
* Returns value of local timer base is_idle value.
*/
bool timer_base_is_idle(void)
{
return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle);
}
static void __run_timer_base(struct timer_base *base);
/**
* timer_expire_remote() - expire global timers of cpu
* @cpu: Remote CPU
*
* Expire timers of global base of remote CPU.
*/
void timer_expire_remote(unsigned int cpu)
{
struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
__run_timer_base(base);
}
static void timer_use_tmigr(unsigned long basej, u64 basem,
unsigned long *nextevt, bool *tick_stop_path,
bool timer_base_idle, struct timer_events *tevt)
{
u64 next_tmigr;
if (timer_base_idle)
next_tmigr = tmigr_cpu_new_timer(tevt->global);
else if (tick_stop_path)
next_tmigr = tmigr_cpu_deactivate(tevt->global);
else
next_tmigr = tmigr_quick_check(tevt->global);
/*
* If the CPU is the last going idle in timer migration hierarchy, make
* sure the CPU will wake up in time to handle remote timers.
* next_tmigr == KTIME_MAX if other CPUs are still active.
*/
if (next_tmigr < tevt->local) {
u64 tmp;
/* If we missed a tick already, force 0 delta */
if (next_tmigr < basem)
next_tmigr = basem;
tmp = div_u64(next_tmigr - basem, TICK_NSEC);
*nextevt = basej + (unsigned long)tmp;
tevt->local = next_tmigr;
}
}
# else
static void timer_use_tmigr(unsigned long basej, u64 basem,
unsigned long *nextevt, bool *tick_stop_path,
bool timer_base_idle, struct timer_events *tevt)
{
/*
* Make sure first event is written into tevt->local to not miss a
* timer on !SMP systems.
*/
tevt->local = min_t(u64, tevt->local, tevt->global);
}
# endif /* CONFIG_SMP */
static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
bool *idle)
{
struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX };
struct timer_base *base_local, *base_global;
unsigned long nextevt;
bool idle_is_possible;
/*
* When the CPU is offline, the tick is cancelled and nothing is supposed
* to try to stop it.
*/
if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) {
if (idle)
*idle = true;
return tevt.local;
}
base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]);
raw_spin_lock(&base_local->lock);
raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
nextevt = fetch_next_timer_interrupt(basej, basem, base_local,
base_global, &tevt);
/*
* If the next event is only one jiffy ahead there is no need to call
* timer migration hierarchy related functions. The value for the next
* global timer in @tevt struct equals then KTIME_MAX. This is also
* true, when the timer base is idle.
*
* The proper timer migration hierarchy function depends on the callsite
* and whether timer base is idle or not. @nextevt will be updated when
* this CPU needs to handle the first timer migration hierarchy
* event. See timer_use_tmigr() for detailed information.
*/
idle_is_possible = time_after(nextevt, basej + 1);
if (idle_is_possible)
timer_use_tmigr(basej, basem, &nextevt, idle,
base_local->is_idle, &tevt);
/*
* We have a fresh next event. Check whether we can forward the
* base.
*/
__forward_timer_base(base_local, basej);
__forward_timer_base(base_global, basej);
/*
* Set base->is_idle only when caller is timer_base_try_to_set_idle()
*/
if (idle) {
/*
* Bases are idle if the next event is more than a tick
* away. Caution: @nextevt could have changed by enqueueing a
* global timer into timer migration hierarchy. Therefore a new
* check is required here.
*
* If the base is marked idle then any timer add operation must
* forward the base clk itself to keep granularity small. This
* idle logic is only maintained for the BASE_LOCAL and
* BASE_GLOBAL base, deferrable timers may still see large
* granularity skew (by design).
*/
if (!base_local->is_idle && time_after(nextevt, basej + 1)) {
base_local->is_idle = true;
/*
* Global timers queued locally while running in a task
* in nohz_full mode need a self-IPI to kick reprogramming
* in IRQ tail.
*/
if (tick_nohz_full_cpu(base_local->cpu))
base_global->is_idle = true;
trace_timer_base_idle(true, base_local->cpu);
}
*idle = base_local->is_idle;
/*
* When timer base is not set idle, undo the effect of
* tmigr_cpu_deactivate() to prevent inconsistent states - active
* timer base but inactive timer migration hierarchy.
*
* When timer base was already marked idle, nothing will be
* changed here.
*/
if (!base_local->is_idle && idle_is_possible)
tmigr_cpu_activate();
}
raw_spin_unlock(&base_global->lock);
raw_spin_unlock(&base_local->lock);
return cmp_next_hrtimer_event(basem, tevt.local);
}
/**
* get_next_timer_interrupt() - return the time (clock mono) of the next timer
* @basej: base time jiffies
* @basem: base time clock monotonic
*
* Returns the tick aligned clock monotonic time of the next pending timer or
* KTIME_MAX if no timer is pending. If timer of global base was queued into
* timer migration hierarchy, first global timer is not taken into account. If
* it was the last CPU of timer migration hierarchy going idle, first global
* event is taken into account.
*/
u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
{
return __get_next_timer_interrupt(basej, basem, NULL);
}
/**
* timer_base_try_to_set_idle() - Try to set the idle state of the timer bases
* @basej: base time jiffies
* @basem: base time clock monotonic
* @idle: pointer to store the value of timer_base->is_idle on return;
* *idle contains the information whether tick was already stopped
*
* Returns the tick aligned clock monotonic time of the next pending timer or
* KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is
* returned as well.
*/
u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle)
{
if (*idle)
return KTIME_MAX;
return __get_next_timer_interrupt(basej, basem, idle);
}
/**
* timer_clear_idle - Clear the idle state of the timer base
*
* Called with interrupts disabled
*/
void timer_clear_idle(void)
{
/*
* We do this unlocked. The worst outcome is a remote pinned timer
* enqueue sending a pointless IPI, but taking the lock would just
* make the window for sending the IPI a few instructions smaller
* for the cost of taking the lock in the exit from idle
* path. Required for BASE_LOCAL only.
*/
__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);
if (tick_nohz_full_cpu(smp_processor_id()))
__this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false);
trace_timer_base_idle(false, smp_processor_id());
/* Activate without holding the timer_base->lock */
tmigr_cpu_activate();
}
#endif
/**
* __run_timers - run all expired timers (if any) on this CPU.
* @base: the timer vector to be processed.
*/
static inline void __run_timers(struct timer_base *base)
{
struct hlist_head heads[LVL_DEPTH];
int levels;
lockdep_assert_held(&base->lock);
if (base->running_timer)
return;
while (time_after_eq(jiffies, base->clk) &&
time_after_eq(jiffies, base->next_expiry)) {
levels = collect_expired_timers(base, heads);
/*
* The two possible reasons for not finding any expired
* timer at this clk are that all matching timers have been
* dequeued or no timer has been queued since
* base::next_expiry was set to base::clk +
* NEXT_TIMER_MAX_DELTA.
*/
WARN_ON_ONCE(!levels && !base->next_expiry_recalc
&& base->timers_pending);
/*
* While executing timers, base->clk is set 1 offset ahead of
* jiffies to avoid endless requeuing to current jiffies.
*/
base->clk++;
timer_recalc_next_expiry(base);
while (levels--)
expire_timers(base, heads + levels);
}
}
static void __run_timer_base(struct timer_base *base)
{
/* Can race against a remote CPU updating next_expiry under the lock */
if (time_before(jiffies, READ_ONCE(base->next_expiry)))
return;
timer_base_lock_expiry(base);
raw_spin_lock_irq(&base->lock);
__run_timers(base);
raw_spin_unlock_irq(&base->lock);
timer_base_unlock_expiry(base);
}
static void run_timer_base(int index)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[index]);
__run_timer_base(base);
}
/*
* This function runs timers and the timer-tq in bottom half context.
*/
static __latent_entropy void run_timer_softirq(void)
{
run_timer_base(BASE_LOCAL);
if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) {
run_timer_base(BASE_GLOBAL);
run_timer_base(BASE_DEF);
if (is_timers_nohz_active())
tmigr_handle_remote();
}
}
/*
* Called by the local, per-CPU timer interrupt on SMP.
*/
static void run_local_timers(void)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
hrtimer_run_queues();
for (int i = 0; i < NR_BASES; i++, base++) {
/*
* Raise the softirq only if required.
*
* timer_base::next_expiry can be written by a remote CPU while
* holding the lock. If this write happens at the same time than
* the lockless local read, sanity checker could complain about
* data corruption.
*
* There are two possible situations where
* timer_base::next_expiry is written by a remote CPU:
*
* 1. Remote CPU expires global timers of this CPU and updates
* timer_base::next_expiry of BASE_GLOBAL afterwards in
* next_timer_interrupt() or timer_recalc_next_expiry(). The
* worst outcome is a superfluous raise of the timer softirq
* when the not yet updated value is read.
*
* 2. A new first pinned timer is enqueued by a remote CPU
* and therefore timer_base::next_expiry of BASE_LOCAL is
* updated. When this update is missed, this isn't a
* problem, as an IPI is executed nevertheless when the CPU
* was idle before. When the CPU wasn't idle but the update
* is missed, then the timer would expire one jiffy late -
* bad luck.
*
* Those unlikely corner cases where the worst outcome is only a
* one jiffy delay or a superfluous raise of the softirq are
* not that expensive as doing the check always while holding
* the lock.
*
* Possible remote writers are using WRITE_ONCE(). Local reader
* uses therefore READ_ONCE().
*/
if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) ||
(i == BASE_DEF && tmigr_requires_handle_remote())) {
raise_timer_softirq(TIMER_SOFTIRQ);
return;
}
}
}
/*
* Called from the timer interrupt handler to charge one tick to the current
* process. user_tick is 1 if the tick is user time, 0 for system.
*/
void update_process_times(int user_tick)
{
struct task_struct *p = current;
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
rcu_sched_clock_irq(user_tick);
#ifdef CONFIG_IRQ_WORK
if (in_irq())
irq_work_tick();
#endif
sched_tick();
if (IS_ENABLED(CONFIG_POSIX_TIMERS))
run_posix_cpu_timers();
}
#ifdef CONFIG_HOTPLUG_CPU
static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head)
{
struct timer_list *timer;
int cpu = new_base->cpu;
while (!hlist_empty(head)) {
timer = hlist_entry(head->first, struct timer_list, entry);
detach_timer(timer, false);
timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
internal_add_timer(new_base, timer);
}
}
int timers_prepare_cpu(unsigned int cpu)
{
struct timer_base *base;
int b;
for (b = 0; b < NR_BASES; b++) {
base = per_cpu_ptr(&timer_bases[b], cpu);
base->clk = jiffies;
base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
base->next_expiry_recalc = false;
base->timers_pending = false;
base->is_idle = false;
}
return 0;
}
int timers_dead_cpu(unsigned int cpu)
{
struct timer_base *old_base;
struct timer_base *new_base;
int b, i;
for (b = 0; b < NR_BASES; b++) {
old_base = per_cpu_ptr(&timer_bases[b], cpu);
new_base = get_cpu_ptr(&timer_bases[b]);
/*
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
*/
raw_spin_lock_irq(&new_base->lock);
raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
/*
* The current CPUs base clock might be stale. Update it
* before moving the timers over.
*/
forward_timer_base(new_base);
WARN_ON_ONCE(old_base->running_timer);
old_base->running_timer = NULL;
for (i = 0; i < WHEEL_SIZE; i++)
migrate_timer_list(new_base, old_base->vectors + i);
raw_spin_unlock(&old_base->lock);
raw_spin_unlock_irq(&new_base->lock);
put_cpu_ptr(&timer_bases);
}
return 0;
}
#endif /* CONFIG_HOTPLUG_CPU */
static void __init init_timer_cpu(int cpu)
{
struct timer_base *base;
int i;
for (i = 0; i < NR_BASES; i++) {
base = per_cpu_ptr(&timer_bases[i], cpu);
base->cpu = cpu;
raw_spin_lock_init(&base->lock);
base->clk = jiffies;
base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
timer_base_init_expiry_lock(base);
}
}
static void __init init_timer_cpus(void)
{
int cpu;
for_each_possible_cpu(cpu)
init_timer_cpu(cpu);
}
void __init init_timers(void)
{
init_timer_cpus();
posix_cputimers_init_work();
open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
}
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* High-resolution kernel timers
*
* In contrast to the low-resolution timeout API, aka timer wheel,
* hrtimers provide finer resolution and accuracy depending on system
* configuration and capabilities.
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* Credits:
* Based on the original timer wheel code
*
* Help, testing, suggestions, bugfixes, improvements were
* provided by:
*
* George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
* et. al.
*/
#include <linux/cpu.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/interrupt.h>
#include <linux/tick.h>
#include <linux/err.h>
#include <linux/debugobjects.h>
#include <linux/sched/signal.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/sched/deadline.h>
#include <linux/sched/nohz.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
#include <linux/timer.h>
#include <linux/freezer.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <trace/events/timer.h>
#include "tick-internal.h"
/*
* Masks for selecting the soft and hard context timers from
* cpu_base->active
*/
#define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT)
#define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1)
#define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT)
#define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
static void retrigger_next_event(void *arg);
/*
* The timer bases:
*
* There are more clockids than hrtimer bases. Thus, we index
* into the timer bases by the hrtimer_base_type enum. When trying
* to reach a base using a clockid, hrtimer_clockid_to_base()
* is used to convert from clockid to the proper hrtimer_base_type.
*/
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
.clock_base =
{
{
.index = HRTIMER_BASE_MONOTONIC,
.clockid = CLOCK_MONOTONIC,
.get_time = &ktime_get,
},
{
.index = HRTIMER_BASE_REALTIME,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
{
.index = HRTIMER_BASE_BOOTTIME,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
},
{
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
},
{
.index = HRTIMER_BASE_MONOTONIC_SOFT,
.clockid = CLOCK_MONOTONIC,
.get_time = &ktime_get,
},
{
.index = HRTIMER_BASE_REALTIME_SOFT,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
{
.index = HRTIMER_BASE_BOOTTIME_SOFT,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
},
{
.index = HRTIMER_BASE_TAI_SOFT,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
},
},
.csd = CSD_INIT(retrigger_next_event, NULL)
};
static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
{
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return true;
else
return likely(base->online);
}
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
*/
#ifdef CONFIG_SMP
/*
* We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
* such that hrtimer_callback_running() can unconditionally dereference
* timer->base->cpu_base
*/
static struct hrtimer_cpu_base migration_cpu_base = {
.clock_base = { {
.cpu_base = &migration_cpu_base,
.seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq,
&migration_cpu_base.lock),
}, },
};
#define migration_base migration_cpu_base.clock_base[0]
/*
* We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
* means that all timers which are tied to this base via timer->base are
* locked, and the base itself is locked too.
*
* So __run_timers/migrate_timers can safely modify all timers which could
* be found on the lists/queues.
*
* When the timer's base is locked, and the timer removed from list, it is
* possible to set timer->base = &migration_base and drop the lock: the timer
* remains locked.
*/
static
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
unsigned long *flags)
__acquires(&timer->base->lock)
{
struct hrtimer_clock_base *base;
for (;;) {
base = READ_ONCE(timer->base);
if (likely(base != &migration_base)) {
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
/* The timer has migrated to another CPU: */
raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
}
cpu_relax();
}
}
/*
* Check if the elected target is suitable considering its next
* event and the hotplug state of the current CPU.
*
* If the elected target is remote and its next event is after the timer
* to queue, then a remote reprogram is necessary. However there is no
* guarantee the IPI handling the operation would arrive in time to meet
* the high resolution deadline. In this case the local CPU becomes a
* preferred target, unless it is offline.
*
* High and low resolution modes are handled the same way for simplicity.
*
* Called with cpu_base->lock of target cpu held.
*/
static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base,
struct hrtimer_cpu_base *new_cpu_base,
struct hrtimer_cpu_base *this_cpu_base)
{
ktime_t expires;
/*
* The local CPU clockevent can be reprogrammed. Also get_target_base()
* guarantees it is online.
*/
if (new_cpu_base == this_cpu_base)
return true;
/*
* The offline local CPU can't be the default target if the
* next remote target event is after this timer. Keep the
* elected new base. An IPI will we issued to reprogram
* it as a last resort.
*/
if (!hrtimer_base_is_online(this_cpu_base))
return true;
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
return expires >= new_base->cpu_base->expires_next;
}
static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned)
{
if (!hrtimer_base_is_online(base)) {
int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER));
return &per_cpu(hrtimer_bases, cpu);
}
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target());
#endif
return base;
}
/*
* We switch the timer base to a power-optimized selected CPU target,
* if:
* - NO_HZ_COMMON is enabled
* - timer migration is enabled
* - the timer callback is not running
* - the timer is not the first expiring timer on the new target
*
* If one of the above requirements is not fulfilled we move the timer
* to the current CPU or leave it on the previously assigned CPU if
* the timer callback is currently running.
*/
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
int pinned)
{
struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base;
struct hrtimer_clock_base *new_base;
int basenum = base->index;
this_cpu_base = this_cpu_ptr(&hrtimer_bases);
new_cpu_base = get_target_base(this_cpu_base, pinned);
again:
new_base = &new_cpu_base->clock_base[basenum];
if (base != new_base) {
/*
* We are trying to move timer to new_base.
* However we can't change timer's base while it is running,
* so we keep it on the same CPU. No hassle vs. reprogramming
* the event source in the high resolution case. The softirq
* code will take care of this when the timer function has
* completed. There is no conflict as we hold the lock until
* the timer is enqueued.
*/
if (unlikely(hrtimer_callback_running(timer)))
return base;
/* See the comment in lock_hrtimer_base() */
WRITE_ONCE(timer->base, &migration_base);
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
if (!hrtimer_suitable_target(timer, new_base, new_cpu_base,
this_cpu_base)) {
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
new_cpu_base = this_cpu_base;
WRITE_ONCE(timer->base, base);
goto again;
}
WRITE_ONCE(timer->base, new_base);
} else {
if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) {
new_cpu_base = this_cpu_base;
goto again;
}
}
return new_base;
}
#else /* CONFIG_SMP */
static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
__acquires(&timer->base->cpu_base->lock)
{
struct hrtimer_clock_base *base = timer->base;
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
return base;
}
# define switch_hrtimer_base(t, b, p) (b)
#endif /* !CONFIG_SMP */
/*
* Functions for the union type storage format of ktime_t which are
* too large for inlining:
*/
#if BITS_PER_LONG < 64
/*
* Divide a ktime value by a nanosecond value
*/
s64 __ktime_divns(const ktime_t kt, s64 div)
{
int sft = 0;
s64 dclc;
u64 tmp;
dclc = ktime_to_ns(kt);
tmp = dclc < 0 ? -dclc : dclc;
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
div >>= 1;
}
tmp >>= sft;
do_div(tmp, (u32) div);
return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
#endif /* BITS_PER_LONG >= 64 */
/*
* Add two ktime values and do a safety check for overflow:
*/
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
ktime_t res = ktime_add_unsafe(lhs, rhs);
/*
* We use KTIME_SEC_MAX here, the maximum timeout which we can
* return to user space in a timespec:
*/
if (res < 0 || res < lhs || res < rhs)
res = ktime_set(KTIME_SEC_MAX, 0);
return res;
}
EXPORT_SYMBOL_GPL(ktime_add_safe);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static const struct debug_obj_descr hrtimer_debug_descr;
static void *hrtimer_debug_hint(void *addr)
{
return ACCESS_PRIVATE((struct hrtimer *)addr, function);
}
/*
* fixup_init is called when:
* - an active object is initialized
*/
static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state)
{
struct hrtimer *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
hrtimer_cancel(timer);
debug_object_init(timer, &hrtimer_debug_descr);
return true;
default:
return false;
}
}
/*
* fixup_activate is called when:
* - an active object is activated
* - an unknown non-static object is activated
*/
static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
{
switch (state) {
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
fallthrough;
default:
return false;
}
}
/*
* fixup_free is called when:
* - an active object is freed
*/
static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state)
{
struct hrtimer *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
hrtimer_cancel(timer);
debug_object_free(timer, &hrtimer_debug_descr);
return true;
default:
return false;
}
}
static const struct debug_obj_descr hrtimer_debug_descr = {
.name = "hrtimer",
.debug_hint = hrtimer_debug_hint,
.fixup_init = hrtimer_fixup_init,
.fixup_activate = hrtimer_fixup_activate,
.fixup_free = hrtimer_fixup_free,
};
static inline void debug_hrtimer_init(struct hrtimer *timer)
{
debug_object_init(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer)
{
debug_object_init_on_stack(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_activate(struct hrtimer *timer,
enum hrtimer_mode mode)
{
debug_object_activate(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
{
debug_object_deactivate(timer, &hrtimer_debug_descr);
}
void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { }
static inline void debug_hrtimer_activate(struct hrtimer *timer,
enum hrtimer_mode mode) { }
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif
static inline void debug_setup(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode)
{
debug_hrtimer_init(timer);
trace_hrtimer_setup(timer, clockid, mode);
}
static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid,
enum hrtimer_mode mode)
{
debug_hrtimer_init_on_stack(timer);
trace_hrtimer_setup(timer, clockid, mode);
}
static inline void debug_activate(struct hrtimer *timer,
enum hrtimer_mode mode)
{
debug_hrtimer_activate(timer, mode);
trace_hrtimer_start(timer, mode);
}
static inline void debug_deactivate(struct hrtimer *timer)
{
debug_hrtimer_deactivate(timer);
trace_hrtimer_cancel(timer);
}
static struct hrtimer_clock_base *
__next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active)
{
unsigned int idx;
if (!*active)
return NULL;
idx = __ffs(*active);
*active &= ~(1U << idx);
return &cpu_base->clock_base[idx];
}
#define for_each_active_base(base, cpu_base, active) \
while ((base = __next_base((cpu_base), &(active))))
static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
const struct hrtimer *exclude,
unsigned int active,
ktime_t expires_next)
{
struct hrtimer_clock_base *base;
ktime_t expires;
for_each_active_base(base, cpu_base, active) {
struct timerqueue_node *next;
struct hrtimer *timer;
next = timerqueue_getnext(&base->active);
timer = container_of(next, struct hrtimer, node);
if (timer == exclude) {
/* Get to the next timer in the queue. */
next = timerqueue_iterate_next(next);
if (!next)
continue;
timer = container_of(next, struct hrtimer, node);
}
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
if (expires < expires_next) {
expires_next = expires;
/* Skip cpu_base update if a timer is being excluded. */
if (exclude)
continue;
if (timer->is_soft)
cpu_base->softirq_next_timer = timer;
else
cpu_base->next_timer = timer;
}
}
/*
* clock_was_set() might have changed base->offset of any of
* the clock bases so the result might be negative. Fix it up
* to prevent a false positive in clockevents_program_event().
*/
if (expires_next < 0)
expires_next = 0;
return expires_next;
}
/*
* Recomputes cpu_base::*next_timer and returns the earliest expires_next
* but does not set cpu_base::*expires_next, that is done by
* hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating
* cpu_base::*expires_next right away, reprogramming logic would no longer
* work.
*
* When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases,
* those timers will get run whenever the softirq gets handled, at the end of
* hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases.
*
* Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases.
* The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual
* softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD.
*
* @active_mask must be one of:
* - HRTIMER_ACTIVE_ALL,
* - HRTIMER_ACTIVE_SOFT, or
* - HRTIMER_ACTIVE_HARD.
*/
static ktime_t
__hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask)
{
unsigned int active;
struct hrtimer *next_timer = NULL;
ktime_t expires_next = KTIME_MAX;
if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) {
active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
cpu_base->softirq_next_timer = NULL;
expires_next = __hrtimer_next_event_base(cpu_base, NULL,
active, KTIME_MAX);
next_timer = cpu_base->softirq_next_timer;
}
if (active_mask & HRTIMER_ACTIVE_HARD) {
active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
cpu_base->next_timer = next_timer;
expires_next = __hrtimer_next_event_base(cpu_base, NULL, active,
expires_next);
}
return expires_next;
}
static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base)
{
ktime_t expires_next, soft = KTIME_MAX;
/*
* If the soft interrupt has already been activated, ignore the
* soft bases. They will be handled in the already raised soft
* interrupt.
*/
if (!cpu_base->softirq_activated) {
soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
/*
* Update the soft expiry time. clock_settime() might have
* affected it.
*/
cpu_base->softirq_expires_next = soft;
}
expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD);
/*
* If a softirq timer is expiring first, update cpu_base->next_timer
* and program the hardware with the soft expiry time.
*/
if (expires_next > soft) {
cpu_base->next_timer = cpu_base->softirq_next_timer;
expires_next = soft;
}
return expires_next;
}
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
offs_real, offs_boot, offs_tai);
base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
return now;
}
/*
* Is the high resolution mode active ?
*/
static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
{
return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
cpu_base->hres_active : 0;
}
static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base,
struct hrtimer *next_timer,
ktime_t expires_next)
{
cpu_base->expires_next = expires_next;
/*
* If hres is not active, hardware does not have to be
* reprogrammed yet.
*
* If a hang was detected in the last timer interrupt then we
* leave the hang delay active in the hardware. We want the
* system to make progress. That also prevents the following
* scenario:
* T1 expires 50ms from now
* T2 expires 5s from now
*
* T1 is removed, so this code is called and would reprogram
* the hardware to 5s from now. Any hrtimer_start after that
* will not reprogram the hardware due to hang_detected being
* set. So we'd effectively block all timers until the T2 event
* fires.
*/
if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
return;
tick_program_event(expires_next, 1);
}
/*
* Reprogram the event source with checking both queues for the
* next event
* Called with interrupts disabled and base->lock held
*/
static void
hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
ktime_t expires_next;
expires_next = hrtimer_update_next_event(cpu_base);
if (skip_equal && expires_next == cpu_base->expires_next)
return;
__hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next);
}
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
/*
* High resolution timer enabled ?
*/
static bool hrtimer_hres_enabled __read_mostly = true;
unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
EXPORT_SYMBOL_GPL(hrtimer_resolution);
/*
* Enable / Disable high resolution mode
*/
static int __init setup_hrtimer_hres(char *str)
{
return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
}
__setup("highres=", setup_hrtimer_hres);
/*
* hrtimer_high_res_enabled - query, if the highres mode is enabled
*/
static inline int hrtimer_is_hres_enabled(void)
{
return hrtimer_hres_enabled;
}
/*
* Switch to high resolution mode
*/
static void hrtimer_switch_to_hres(void)
{
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
if (tick_init_highres()) {
pr_warn("Could not switch to high resolution mode on CPU %u\n",
base->cpu);
return;
}
base->hres_active = 1;
hrtimer_resolution = HIGH_RES_NSEC;
tick_setup_sched_timer(true);
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
}
#else
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline void hrtimer_switch_to_hres(void) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
/*
* Retrigger next event is called after clock was set with interrupts
* disabled through an SMP function call or directly from low level
* resume code.
*
* This is only invoked when:
* - CONFIG_HIGH_RES_TIMERS is enabled.
* - CONFIG_NOHZ_COMMON is enabled
*
* For the other cases this function is empty and because the call sites
* are optimized out it vanishes as well, i.e. no need for lots of
* #ifdeffery.
*/
static void retrigger_next_event(void *arg)
{
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
/*
* When high resolution mode or nohz is active, then the offsets of
* CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the
* next tick will take care of that.
*
* If high resolution mode is active then the next expiring timer
* must be reevaluated and the clock event device reprogrammed if
* necessary.
*
* In the NOHZ case the update of the offset and the reevaluation
* of the next expiring timer is enough. The return from the SMP
* function call will take care of the reprogramming in case the
* CPU was in a NOHZ idle sleep.
*/
if (!hrtimer_hres_active(base) && !tick_nohz_active)
return;
raw_spin_lock(&base->lock);
hrtimer_update_base(base);
if (hrtimer_hres_active(base))
hrtimer_force_reprogram(base, 0);
else
hrtimer_update_next_event(base);
raw_spin_unlock(&base->lock);
}
/*
* When a timer is enqueued and expires earlier than the already enqueued
* timers, we have to check, whether it expires earlier than the timer for
* which the clock event device was armed.
*
* Called with interrupts disabled and base->cpu_base.lock held
*/
static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
struct hrtimer_clock_base *base = timer->base;
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
/*
* CLOCK_REALTIME timer might be requested with an absolute
* expiry time which is less than base->offset. Set it to 0.
*/
if (expires < 0)
expires = 0;
if (timer->is_soft) {
/*
* soft hrtimer could be started on a remote CPU. In this
* case softirq_expires_next needs to be updated on the
* remote CPU. The soft hrtimer will not expire before the
* first hard hrtimer on the remote CPU -
* hrtimer_check_target() prevents this case.
*/
struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base;
if (timer_cpu_base->softirq_activated)
return;
if (!ktime_before(expires, timer_cpu_base->softirq_expires_next))
return;
timer_cpu_base->softirq_next_timer = timer;
timer_cpu_base->softirq_expires_next = expires;
if (!ktime_before(expires, timer_cpu_base->expires_next) ||
!reprogram)
return;
}
/*
* If the timer is not on the current cpu, we cannot reprogram
* the other cpus clock event device.
*/
if (base->cpu_base != cpu_base)
return;
if (expires >= cpu_base->expires_next)
return;
/*
* If the hrtimer interrupt is running, then it will reevaluate the
* clock bases and reprogram the clock event device.
*/
if (cpu_base->in_hrtirq)
return;
cpu_base->next_timer = timer;
__hrtimer_reprogram(cpu_base, timer, expires);
}
static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base,
unsigned int active)
{
struct hrtimer_clock_base *base;
unsigned int seq;
ktime_t expires;
/*
* Update the base offsets unconditionally so the following
* checks whether the SMP function call is required works.
*
* The update is safe even when the remote CPU is in the hrtimer
* interrupt or the hrtimer soft interrupt and expiring affected
* bases. Either it will see the update before handling a base or
* it will see it when it finishes the processing and reevaluates
* the next expiring timer.
*/
seq = cpu_base->clock_was_set_seq;
hrtimer_update_base(cpu_base);
/*
* If the sequence did not change over the update then the
* remote CPU already handled it.
*/
if (seq == cpu_base->clock_was_set_seq)
return false;
/*
* If the remote CPU is currently handling an hrtimer interrupt, it
* will reevaluate the first expiring timer of all clock bases
* before reprogramming. Nothing to do here.
*/
if (cpu_base->in_hrtirq)
return false;
/*
* Walk the affected clock bases and check whether the first expiring
* timer in a clock base is moving ahead of the first expiring timer of
* @cpu_base. If so, the IPI must be invoked because per CPU clock
* event devices cannot be remotely reprogrammed.
*/
active &= cpu_base->active_bases;
for_each_active_base(base, cpu_base, active) {
struct timerqueue_node *next;
next = timerqueue_getnext(&base->active);
expires = ktime_sub(next->expires, base->offset);
if (expires < cpu_base->expires_next)
return true;
/* Extra check for softirq clock bases */
if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT)
continue;
if (cpu_base->softirq_activated)
continue;
if (expires < cpu_base->softirq_expires_next)
return true;
}
return false;
}
/*
* Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and
* CLOCK_BOOTTIME (for late sleep time injection).
*
* This requires to update the offsets for these clocks
* vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this
* also requires to eventually reprogram the per CPU clock event devices
* when the change moves an affected timer ahead of the first expiring
* timer on that CPU. Obviously remote per CPU clock event devices cannot
* be reprogrammed. The other reason why an IPI has to be sent is when the
* system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets
* in the tick, which obviously might be stopped, so this has to bring out
* the remote CPU which might sleep in idle to get this sorted.
*/
void clock_was_set(unsigned int bases)
{
struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases);
cpumask_var_t mask;
int cpu;
if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active)
goto out_timerfd;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
on_each_cpu(retrigger_next_event, NULL, 1);
goto out_timerfd;
}
/* Avoid interrupting CPUs if possible */
cpus_read_lock();
for_each_online_cpu(cpu) {
unsigned long flags;
cpu_base = &per_cpu(hrtimer_bases, cpu);
raw_spin_lock_irqsave(&cpu_base->lock, flags);
if (update_needs_ipi(cpu_base, bases))
cpumask_set_cpu(cpu, mask);
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
}
preempt_disable();
smp_call_function_many(mask, retrigger_next_event, NULL, 1);
preempt_enable();
cpus_read_unlock();
free_cpumask_var(mask);
out_timerfd:
timerfd_clock_was_set();
}
static void clock_was_set_work(struct work_struct *work)
{
clock_was_set(CLOCK_SET_WALL);
}
static DECLARE_WORK(hrtimer_work, clock_was_set_work);
/*
* Called from timekeeping code to reprogram the hrtimer interrupt device
* on all cpus and to notify timerfd.
*/
void clock_was_set_delayed(void)
{
schedule_work(&hrtimer_work);
}
/*
* Called during resume either directly from via timekeeping_resume()
* or in the case of s2idle from tick_unfreeze() to ensure that the
* hrtimers are up to date.
*/
void hrtimers_resume_local(void)
{
lockdep_assert_irqs_disabled();
/* Retrigger on the local CPU */
retrigger_next_event(NULL);
}
/*
* Counterpart to lock_hrtimer_base above:
*/
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
__releases(&timer->base->cpu_base->lock)
{
raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}
/**
* hrtimer_forward() - forward the timer expiry
* @timer: hrtimer to forward
* @now: forward past this time
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire in the future.
*
* .. note::
* This only updates the timer expiry value and does not requeue the timer.
*
* There is also a variant of the function hrtimer_forward_now().
*
* Context: Can be safely called from the callback function of @timer. If called
* from other contexts @timer must neither be enqueued nor running the
* callback and the caller needs to take care of serialization.
*
* Return: The number of overruns are returned.
*/
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
u64 orun = 1;
ktime_t delta;
delta = ktime_sub(now, hrtimer_get_expires(timer));
if (delta < 0)
return 0;
if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
return 0;
if (interval < hrtimer_resolution)
interval = hrtimer_resolution;
if (unlikely(delta >= interval)) {
s64 incr = ktime_to_ns(interval);
orun = ktime_divns(delta, incr);
hrtimer_add_expires_ns(timer, incr * orun);
if (hrtimer_get_expires_tv64(timer) > now)
return orun;
/*
* This (and the ktime_add() below) is the
* correction for exact:
*/
orun++;
}
hrtimer_add_expires(timer, interval);
return orun;
}
EXPORT_SYMBOL_GPL(hrtimer_forward);
/*
* enqueue_hrtimer - internal function to (re)start a timer
*
* The timer is inserted in expiry order. Insertion into the
* red black tree is O(log(n)). Must hold the base lock.
*
* Returns true when the new timer is the leftmost timer in the tree.
*/
static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base,
enum hrtimer_mode mode)
{ debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online);
base->cpu_base->active_bases |= 1 << base->index;
/* Pairs with the lockless read in hrtimer_is_queued() */
WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED);
return timerqueue_add(&base->active, &timer->node);
}
/*
* __remove_hrtimer - internal function to remove a timer
*
* Caller must hold the base lock.
*
* High resolution timer mode reprograms the clock event device when the
* timer is the one which expires next. The caller can disable this by setting
* reprogram to zero. This is useful, when the context does a reprogramming
* anyway (e.g. timer interrupt)
*/
static void __remove_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base,
u8 newstate, int reprogram)
{
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
u8 state = timer->state;
/* Pairs with the lockless read in hrtimer_is_queued() */
WRITE_ONCE(timer->state, newstate);
if (!(state & HRTIMER_STATE_ENQUEUED))
return;
if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index);
/*
* Note: If reprogram is false we do not update
* cpu_base->next_timer. This happens when we remove the first
* timer on a remote cpu. No harm as we never dereference
* cpu_base->next_timer. So the worst thing what can happen is
* an superfluous call to hrtimer_force_reprogram() on the
* remote cpu later on if the same timer gets enqueued again.
*/
if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1);
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base,
bool restart, bool keep_local)
{
u8 state = timer->state;
if (state & HRTIMER_STATE_ENQUEUED) {
bool reprogram;
/*
* Remove the timer and force reprogramming when high
* resolution mode is active and the timer is on the current
* CPU. If we remove a timer on another CPU, reprogramming is
* skipped. The interrupt event on this CPU is fired and
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
debug_deactivate(timer);
reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
/*
* If the timer is not restarted then reprogramming is
* required if the timer is local. If it is local and about
* to be restarted, avoid programming it twice (on removal
* and a moment later when it's requeued).
*/
if (!restart)
state = HRTIMER_STATE_INACTIVE;
else
reprogram &= !keep_local;
__remove_hrtimer(timer, base, state, reprogram);
return 1;
}
return 0;
}
static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode)
{
#ifdef CONFIG_TIME_LOW_RES
/*
* CONFIG_TIME_LOW_RES indicates that the system has no way to return
* granular time values. For relative timers we add hrtimer_resolution
* (i.e. one jiffy) to prevent short timeouts.
*/
timer->is_rel = mode & HRTIMER_MODE_REL;
if (timer->is_rel)
tim = ktime_add_safe(tim, hrtimer_resolution);
#endif
return tim;
}
static void
hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram)
{
ktime_t expires;
/*
* Find the next SOFT expiration.
*/
expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
/*
* reprogramming needs to be triggered, even if the next soft
* hrtimer expires at the same time than the next hard
* hrtimer. cpu_base->softirq_expires_next needs to be updated!
*/
if (expires == KTIME_MAX)
return;
/*
* cpu_base->*next_timer is recomputed by __hrtimer_get_next_event()
* cpu_base->*expires_next is only set by hrtimer_reprogram()
*/
hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram);
}
static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
u64 delta_ns, const enum hrtimer_mode mode,
struct hrtimer_clock_base *base)
{
struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases);
struct hrtimer_clock_base *new_base;
bool force_local, first;
/*
* If the timer is on the local cpu base and is the first expiring
* timer then this might end up reprogramming the hardware twice
* (on removal and on enqueue). To avoid that by prevent the
* reprogram on removal, keep the timer local to the current CPU
* and enforce reprogramming after it is queued no matter whether
* it is the new first expiring timer again or not.
*/
force_local = base->cpu_base == this_cpu_base;
force_local &= base->cpu_base->next_timer == timer;
/*
* Don't force local queuing if this enqueue happens on a unplugged
* CPU after hrtimer_cpu_dying() has been invoked.
*/
force_local &= this_cpu_base->online;
/*
* Remove an active timer from the queue. In case it is not queued
* on the current CPU, make sure that remove_hrtimer() updates the
* remote data correctly.
*
* If it's on the current CPU and the first expiring timer, then
* skip reprogramming, keep the timer local and enforce
* reprogramming later if it was the first expiring timer. This
* avoids programming the underlying clock event twice (once at
* removal and once after enqueue).
*/
remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time());
tim = hrtimer_update_lowres(timer, tim, mode);
hrtimer_set_expires_range_ns(timer, tim, delta_ns);
/* Switch the timer base, if necessary: */
if (!force_local) {
new_base = switch_hrtimer_base(timer, base,
mode & HRTIMER_MODE_PINNED);
} else {
new_base = base;
}
first = enqueue_hrtimer(timer, new_base, mode);
if (!force_local) {
/*
* If the current CPU base is online, then the timer is
* never queued on a remote CPU if it would be the first
* expiring timer there.
*/
if (hrtimer_base_is_online(this_cpu_base))
return first;
/*
* Timer was enqueued remote because the current base is
* already offline. If the timer is the first to expire,
* kick the remote CPU to reprogram the clock event.
*/
if (first) { struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base;
smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd);
}
return 0;
}
/*
* Timer was forced to stay on the current CPU to avoid
* reprogramming on removal and enqueue. Force reprogram the
* hardware by evaluating the new first expiring timer.
*/
hrtimer_force_reprogram(new_base->cpu_base, 1);
return 0;
}
/**
* hrtimer_start_range_ns - (re)start an hrtimer
* @timer: the timer to be added
* @tim: expiry time
* @delta_ns: "slack" range for the timer
* @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
* relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
* softirq based mode is considered for debug purpose only!
*/
void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
u64 delta_ns, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base;
unsigned long flags;
/*
* Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
* match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard
* expiry mode because unmarked timers are moved to softirq expiry.
*/
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
else
WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard);
base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true);
unlock_hrtimer_base(timer, &flags);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
/**
* hrtimer_try_to_cancel - try to deactivate a timer
* @timer: hrtimer to stop
*
* Returns:
*
* * 0 when the timer was not active
* * 1 when the timer was active
* * -1 when the timer is currently executing the callback function and
* cannot be stopped
*/
int hrtimer_try_to_cancel(struct hrtimer *timer)
{
struct hrtimer_clock_base *base;
unsigned long flags;
int ret = -1;
/*
* Check lockless first. If the timer is not active (neither
* enqueued nor running the callback, nothing to do here. The
* base lock does not serialize against a concurrent enqueue,
* so we can avoid taking it.
*/
if (!hrtimer_active(timer))
return 0;
base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false);
unlock_hrtimer_base(timer, &flags);
return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);
#ifdef CONFIG_PREEMPT_RT
static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base)
{
spin_lock_init(&base->softirq_expiry_lock);
}
static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base)
__acquires(&base->softirq_expiry_lock)
{
spin_lock(&base->softirq_expiry_lock);
}
static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base)
__releases(&base->softirq_expiry_lock)
{
spin_unlock(&base->softirq_expiry_lock);
}
/*
* The counterpart to hrtimer_cancel_wait_running().
*
* If there is a waiter for cpu_base->expiry_lock, then it was waiting for
* the timer callback to finish. Drop expiry_lock and reacquire it. That
* allows the waiter to acquire the lock and make progress.
*/
static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
unsigned long flags)
{
if (atomic_read(&cpu_base->timer_waiters)) {
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
spin_unlock(&cpu_base->softirq_expiry_lock);
spin_lock(&cpu_base->softirq_expiry_lock);
raw_spin_lock_irq(&cpu_base->lock);
}
}
#ifdef CONFIG_SMP
static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
{
return base == &migration_base;
}
#else
static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
{
return false;
}
#endif
/*
* This function is called on PREEMPT_RT kernels when the fast path
* deletion of a timer failed because the timer callback function was
* running.
*
* This prevents priority inversion: if the soft irq thread is preempted
* in the middle of a timer callback, then calling hrtimer_cancel() can
* lead to two issues:
*
* - If the caller is on a remote CPU then it has to spin wait for the timer
* handler to complete. This can result in unbound priority inversion.
*
* - If the caller originates from the task which preempted the timer
* handler on the same CPU, then spin waiting for the timer handler to
* complete is never going to end.
*/
void hrtimer_cancel_wait_running(const struct hrtimer *timer)
{
/* Lockless read. Prevent the compiler from reloading it below */
struct hrtimer_clock_base *base = READ_ONCE(timer->base);
/*
* Just relax if the timer expires in hard interrupt context or if
* it is currently on the migration base.
*/
if (!timer->is_soft || is_migration_base(base)) {
cpu_relax();
return;
}
/*
* Mark the base as contended and grab the expiry lock, which is
* held by the softirq across the timer callback. Drop the lock
* immediately so the softirq can expire the next timer. In theory
* the timer could already be running again, but that's more than
* unlikely and just causes another wait loop.
*/
atomic_inc(&base->cpu_base->timer_waiters);
spin_lock_bh(&base->cpu_base->softirq_expiry_lock);
atomic_dec(&base->cpu_base->timer_waiters);
spin_unlock_bh(&base->cpu_base->softirq_expiry_lock);
}
#else
static inline void
hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { }
static inline void
hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { }
static inline void
hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { }
static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base,
unsigned long flags) { }
#endif
/**
* hrtimer_cancel - cancel a timer and wait for the handler to finish.
* @timer: the timer to be cancelled
*
* Returns:
* 0 when the timer was not active
* 1 when the timer was active
*/
int hrtimer_cancel(struct hrtimer *timer)
{
int ret;
do {
ret = hrtimer_try_to_cancel(timer);
if (ret < 0)
hrtimer_cancel_wait_running(timer);
} while (ret < 0);
return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_cancel);
/**
* __hrtimer_get_remaining - get remaining time for the timer
* @timer: the timer to read
* @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y
*/
ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust)
{
unsigned long flags;
ktime_t rem;
lock_hrtimer_base(timer, &flags);
if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust)
rem = hrtimer_expires_remaining_adjusted(timer);
else
rem = hrtimer_expires_remaining(timer);
unlock_hrtimer_base(timer, &flags);
return rem;
}
EXPORT_SYMBOL_GPL(__hrtimer_get_remaining);
#ifdef CONFIG_NO_HZ_COMMON
/**
* hrtimer_get_next_event - get the time until next expiry event
*
* Returns the next expiry time or KTIME_MAX if no timer is pending.
*/
u64 hrtimer_get_next_event(void)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
u64 expires = KTIME_MAX;
unsigned long flags;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
if (!hrtimer_hres_active(cpu_base))
expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
return expires;
}
/**
* hrtimer_next_event_without - time until next expiry event w/o one timer
* @exclude: timer to exclude
*
* Returns the next expiry time over all timers except for the @exclude one or
* KTIME_MAX if none of them is pending.
*/
u64 hrtimer_next_event_without(const struct hrtimer *exclude)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
u64 expires = KTIME_MAX;
unsigned long flags;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
if (hrtimer_hres_active(cpu_base)) {
unsigned int active;
if (!cpu_base->softirq_activated) {
active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
expires = __hrtimer_next_event_base(cpu_base, exclude,
active, KTIME_MAX);
}
active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
expires = __hrtimer_next_event_base(cpu_base, exclude, active,
expires);
}
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
return expires;
}
#endif
static inline int hrtimer_clockid_to_base(clockid_t clock_id)
{
switch (clock_id) {
case CLOCK_REALTIME:
return HRTIMER_BASE_REALTIME;
case CLOCK_MONOTONIC:
return HRTIMER_BASE_MONOTONIC;
case CLOCK_BOOTTIME:
return HRTIMER_BASE_BOOTTIME;
case CLOCK_TAI:
return HRTIMER_BASE_TAI;
default:
WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
return HRTIMER_BASE_MONOTONIC;
}
}
static void __hrtimer_setup(struct hrtimer *timer,
enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t clock_id, enum hrtimer_mode mode)
{
bool softtimer = !!(mode & HRTIMER_MODE_SOFT);
struct hrtimer_cpu_base *cpu_base;
int base;
/*
* On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context for latency reasons and because the callbacks
* can invoke functions which might sleep on RT, e.g. spin_lock().
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD))
softtimer = true;
memset(timer, 0, sizeof(struct hrtimer));
cpu_base = raw_cpu_ptr(&hrtimer_bases);
/*
* POSIX magic: Relative CLOCK_REALTIME timers are not affected by
* clock modifications, so they needs to become CLOCK_MONOTONIC to
* ensure POSIX compliance.
*/
if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL)
clock_id = CLOCK_MONOTONIC;
base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
base += hrtimer_clockid_to_base(clock_id);
timer->is_soft = softtimer;
timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
timer->base = &cpu_base->clock_base[base];
timerqueue_init(&timer->node);
if (WARN_ON_ONCE(!function))
ACCESS_PRIVATE(timer, function) = hrtimer_dummy_timeout;
else
ACCESS_PRIVATE(timer, function) = function;
}
/**
* hrtimer_setup - initialize a timer to the given clock
* @timer: the timer to be initialized
* @function: the callback function
* @clock_id: the clock to be used
* @mode: The modes which are relevant for initialization:
* HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
* HRTIMER_MODE_REL_SOFT
*
* The PINNED variants of the above can be handed in,
* but the PINNED bit is ignored as pinning happens
* when the hrtimer is started
*/
void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t clock_id, enum hrtimer_mode mode)
{
debug_setup(timer, clock_id, mode);
__hrtimer_setup(timer, function, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_setup);
/**
* hrtimer_setup_on_stack - initialize a timer on stack memory
* @timer: The timer to be initialized
* @function: the callback function
* @clock_id: The clock to be used
* @mode: The timer mode
*
* Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack
* memory.
*/
void hrtimer_setup_on_stack(struct hrtimer *timer,
enum hrtimer_restart (*function)(struct hrtimer *),
clockid_t clock_id, enum hrtimer_mode mode)
{
debug_setup_on_stack(timer, clock_id, mode);
__hrtimer_setup(timer, function, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack);
/*
* A timer is active, when it is enqueued into the rbtree or the
* callback function is running or it's in the state of being migrated
* to another cpu.
*
* It is important for this function to not return a false negative.
*/
bool hrtimer_active(const struct hrtimer *timer)
{
struct hrtimer_clock_base *base;
unsigned int seq;
do {
base = READ_ONCE(timer->base);
seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE ||
base->running == timer)
return true;
} while (read_seqcount_retry(&base->seq, seq) ||
base != READ_ONCE(timer->base));
return false;
}
EXPORT_SYMBOL_GPL(hrtimer_active);
/*
* The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
* distinct sections:
*
* - queued: the timer is queued
* - callback: the timer is being ran
* - post: the timer is inactive or (re)queued
*
* On the read side we ensure we observe timer->state and cpu_base->running
* from the same section, if anything changed while we looked at it, we retry.
* This includes timer->base changing because sequence numbers alone are
* insufficient for that.
*
* The sequence numbers are required because otherwise we could still observe
* a false negative if the read side got smeared over multiple consecutive
* __run_hrtimer() invocations.
*/
static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
struct hrtimer_clock_base *base,
struct hrtimer *timer, ktime_t *now,
unsigned long flags) __must_hold(&cpu_base->lock)
{
enum hrtimer_restart (*fn)(struct hrtimer *);
bool expires_in_hardirq;
int restart;
lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
base->running = timer;
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe base->running == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&base->seq);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
fn = ACCESS_PRIVATE(timer, function);
/*
* Clear the 'is relative' flag for the TIME_LOW_RES case. If the
* timer is restarted with a period then it becomes an absolute
* timer. If its not restarted it does not matter.
*/
if (IS_ENABLED(CONFIG_TIME_LOW_RES))
timer->is_rel = false;
/*
* The timer is marked as running in the CPU base, so it is
* protected against migration to a different CPU even if the lock
* is dropped.
*/
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
trace_hrtimer_expire_entry(timer, now);
expires_in_hardirq = lockdep_hrtimer_enter(timer);
restart = fn(timer);
lockdep_hrtimer_exit(expires_in_hardirq);
trace_hrtimer_expire_exit(timer);
raw_spin_lock_irq(&cpu_base->lock);
/*
* Note: We clear the running state after enqueue_hrtimer and
* we do not reprogram the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
*
* Note: Because we dropped the cpu_base->lock above,
* hrtimer_start_range_ns() can have popped in and enqueued the timer
* for us already.
*/
if (restart != HRTIMER_NORESTART &&
!(timer->state & HRTIMER_STATE_ENQUEUED))
enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS);
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe base->running.timer == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&base->seq);
WARN_ON_ONCE(base->running != timer);
base->running = NULL;
}
static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
unsigned long flags, unsigned int active_mask)
{
struct hrtimer_clock_base *base;
unsigned int active = cpu_base->active_bases & active_mask;
for_each_active_base(base, cpu_base, active) {
struct timerqueue_node *node;
ktime_t basenow;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
timer = container_of(node, struct hrtimer, node);
/*
* The immediate goal for using the softexpires is
* minimizing wakeups, not running timers at the
* earliest interrupt after their soft expiration.
* This allows us to avoid using a Priority Search
* Tree, which can answer a stabbing query for
* overlapping intervals and instead use the simple
* BST we already have.
* We don't add extra wakeups by delaying timers that
* are right-of a not yet expired timer, because that
* timer will have to trigger a wakeup anyway.
*/
if (basenow < hrtimer_get_softexpires_tv64(timer))
break;
__run_hrtimer(cpu_base, base, timer, &basenow, flags);
if (active_mask == HRTIMER_ACTIVE_SOFT)
hrtimer_sync_wait_running(cpu_base, flags);
}
}
}
static __latent_entropy void hrtimer_run_softirq(void)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
unsigned long flags;
ktime_t now;
hrtimer_cpu_base_lock_expiry(cpu_base);
raw_spin_lock_irqsave(&cpu_base->lock, flags);
now = hrtimer_update_base(cpu_base);
__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT);
cpu_base->softirq_activated = 0;
hrtimer_update_softirq_timer(cpu_base, true);
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
hrtimer_cpu_base_unlock_expiry(cpu_base);
}
#ifdef CONFIG_HIGH_RES_TIMERS
/*
* High resolution timer interrupt
* Called with interrupts disabled
*/
void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
unsigned long flags;
int retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event = KTIME_MAX;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
entry_time = now = hrtimer_update_base(cpu_base);
retry:
cpu_base->in_hrtirq = 1;
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
* the migration code. This does not affect enqueueing of
* timers which run their callback and need to be requeued on
* this CPU.
*/
cpu_base->expires_next = KTIME_MAX;
if (!ktime_before(now, cpu_base->softirq_expires_next)) {
cpu_base->softirq_expires_next = KTIME_MAX;
cpu_base->softirq_activated = 1;
raise_timer_softirq(HRTIMER_SOFTIRQ);
}
__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
/* Reevaluate the clock bases for the [soft] next expiry */
expires_next = hrtimer_update_next_event(cpu_base);
/*
* Store the new expiry value so the migration code can verify
* against it.
*/
cpu_base->expires_next = expires_next;
cpu_base->in_hrtirq = 0;
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
/* Reprogramming necessary ? */
if (!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
/*
* The next timer was already expired due to:
* - tracing
* - long lasting callbacks
* - being scheduled away when running in a VM
*
* We need to prevent that we loop forever in the hrtimer
* interrupt routine. We give it 3 attempts to avoid
* overreacting on some spurious event.
*
* Acquire base lock for updating the offsets and retrieving
* the current time.
*/
raw_spin_lock_irqsave(&cpu_base->lock, flags);
now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
/*
* Give the system a chance to do something else than looping
* here. We stored the entry time, so we know exactly how long
* we spent here. We schedule the next event this amount of
* time away.
*/
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
delta = ktime_sub(now, entry_time);
if ((unsigned int)delta > cpu_base->max_hang_time)
cpu_base->max_hang_time = (unsigned int) delta;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
*/
if (delta > 100 * NSEC_PER_MSEC)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
}
#endif /* !CONFIG_HIGH_RES_TIMERS */
/*
* Called from run_local_timers in hardirq context every jiffy
*/
void hrtimer_run_queues(void)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
unsigned long flags;
ktime_t now;
if (hrtimer_hres_active(cpu_base))
return;
/*
* This _is_ ugly: We have to check periodically, whether we
* can switch to highres and / or nohz mode. The clocksource
* switch happens with xtime_lock held. Notification from
* there only sets the check bit in the tick_oneshot code,
* otherwise we might deadlock vs. xtime_lock.
*/
if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
hrtimer_switch_to_hres();
return;
}
raw_spin_lock_irqsave(&cpu_base->lock, flags);
now = hrtimer_update_base(cpu_base);
if (!ktime_before(now, cpu_base->softirq_expires_next)) {
cpu_base->softirq_expires_next = KTIME_MAX;
cpu_base->softirq_activated = 1;
raise_timer_softirq(HRTIMER_SOFTIRQ);
}
__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
}
/*
* Sleep related functions:
*/
static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
{
struct hrtimer_sleeper *t =
container_of(timer, struct hrtimer_sleeper, timer);
struct task_struct *task = t->task;
t->task = NULL;
if (task)
wake_up_process(task);
return HRTIMER_NORESTART;
}
/**
* hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer
* @sl: sleeper to be started
* @mode: timer mode abs/rel
*
* Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers
* to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context)
*/
void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
enum hrtimer_mode mode)
{
/*
* Make the enqueue delivery mode check work on RT. If the sleeper
* was initialized for hard interrupt delivery, force the mode bit.
* This is a special case for hrtimer_sleepers because
* __hrtimer_setup_sleeper() determines the delivery mode on RT so the
* fiddling with this decision is avoided at the call sites.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard)
mode |= HRTIMER_MODE_HARD;
hrtimer_start_expires(&sl->timer, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires);
static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl,
clockid_t clock_id, enum hrtimer_mode mode)
{
/*
* On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context either for latency reasons or because the
* hrtimer callback takes regular spinlocks or invokes other
* functions which are not suitable for hard interrupt context on
* PREEMPT_RT.
*
* The hrtimer_sleeper callback is RT compatible in hard interrupt
* context, but there is a latency concern: Untrusted userspace can
* spawn many threads which arm timers for the same expiry time on
* the same CPU. That causes a latency spike due to the wakeup of
* a gazillion threads.
*
* OTOH, privileged real-time user space applications rely on the
* low latency of hard interrupt wakeups. If the current task is in
* a real-time scheduling class, mark the mode for hard interrupt
* expiry.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT))
mode |= HRTIMER_MODE_HARD;
}
__hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode);
sl->task = current;
}
/**
* hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory
* @sl: sleeper to be initialized
* @clock_id: the clock to be used
* @mode: timer mode abs/rel
*/
void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl,
clockid_t clock_id, enum hrtimer_mode mode)
{
debug_setup_on_stack(&sl->timer, clock_id, mode);
__hrtimer_setup_sleeper(sl, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack);
int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
{
switch(restart->nanosleep.type) {
#ifdef CONFIG_COMPAT_32BIT_TIME
case TT_COMPAT:
if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp))
return -EFAULT;
break;
#endif
case TT_NATIVE:
if (put_timespec64(ts, restart->nanosleep.rmtp))
return -EFAULT;
break;
default:
BUG();
}
return -ERESTART_RESTARTBLOCK;
}
static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
{
struct restart_block *restart;
do {
set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
hrtimer_sleeper_start_expires(t, mode);
if (likely(t->task))
schedule();
hrtimer_cancel(&t->timer);
mode = HRTIMER_MODE_ABS;
} while (t->task && !signal_pending(current));
__set_current_state(TASK_RUNNING);
if (!t->task)
return 0;
restart = ¤t->restart_block;
if (restart->nanosleep.type != TT_NONE) {
ktime_t rem = hrtimer_expires_remaining(&t->timer);
struct timespec64 rmt;
if (rem <= 0)
return 0;
rmt = ktime_to_timespec64(rem);
return nanosleep_copyout(restart, &rmt);
}
return -ERESTART_RESTARTBLOCK;
}
static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
{
struct hrtimer_sleeper t;
int ret;
hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS);
hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
ret = do_nanosleep(&t, HRTIMER_MODE_ABS);
destroy_hrtimer_on_stack(&t.timer);
return ret;
}
long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
const clockid_t clockid)
{
struct restart_block *restart;
struct hrtimer_sleeper t;
int ret = 0;
hrtimer_setup_sleeper_on_stack(&t, clockid, mode);
hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns);
ret = do_nanosleep(&t, mode);
if (ret != -ERESTART_RESTARTBLOCK)
goto out;
/* Absolute timers do not update the rmtp value and restart: */
if (mode == HRTIMER_MODE_ABS) {
ret = -ERESTARTNOHAND;
goto out;
}
restart = ¤t->restart_block;
restart->nanosleep.clockid = t.timer.base->clockid;
restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
set_restart_fn(restart, hrtimer_nanosleep_restart);
out:
destroy_hrtimer_on_stack(&t.timer);
return ret;
}
#ifdef CONFIG_64BIT
SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
struct __kernel_timespec __user *, rmtp)
{
struct timespec64 tu;
if (get_timespec64(&tu, rqtp))
return -EFAULT;
if (!timespec64_valid(&tu))
return -EINVAL;
current->restart_block.fn = do_no_restart_syscall;
current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
current->restart_block.nanosleep.rmtp = rmtp;
return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
CLOCK_MONOTONIC);
}
#endif
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp,
struct old_timespec32 __user *, rmtp)
{
struct timespec64 tu;
if (get_old_timespec32(&tu, rqtp))
return -EFAULT;
if (!timespec64_valid(&tu))
return -EINVAL;
current->restart_block.fn = do_no_restart_syscall;
current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
current->restart_block.nanosleep.compat_rmtp = rmtp;
return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL,
CLOCK_MONOTONIC);
}
#endif
/*
* Functions related to boot-time initialization:
*/
int hrtimers_prepare_cpu(unsigned int cpu)
{
struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i];
clock_b->cpu_base = cpu_base;
seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock);
timerqueue_init_head(&clock_b->active);
}
cpu_base->cpu = cpu;
hrtimer_cpu_base_init_expiry_lock(cpu_base);
return 0;
}
int hrtimers_cpu_starting(unsigned int cpu)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
/* Clear out any left over state from a CPU down operation */
cpu_base->active_bases = 0;
cpu_base->hres_active = 0;
cpu_base->hang_detected = 0;
cpu_base->next_timer = NULL;
cpu_base->softirq_next_timer = NULL;
cpu_base->expires_next = KTIME_MAX;
cpu_base->softirq_expires_next = KTIME_MAX;
cpu_base->online = 1;
return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
struct hrtimer_clock_base *new_base)
{
struct hrtimer *timer;
struct timerqueue_node *node;
while ((node = timerqueue_getnext(&old_base->active))) {
timer = container_of(node, struct hrtimer, node);
BUG_ON(hrtimer_callback_running(timer));
debug_deactivate(timer);
/*
* Mark it as ENQUEUED not INACTIVE otherwise the
* timer could be seen as !active and just vanish away
* under us on another CPU
*/
__remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
timer->base = new_base;
/*
* Enqueue the timers on the new cpu. This does not
* reprogram the event device in case the timer
* expires before the earliest on this CPU, but we run
* hrtimer_interrupt after we migrated everything to
* sort out already expired timers and reprogram the
* event device.
*/
enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS);
}
}
int hrtimers_cpu_dying(unsigned int dying_cpu)
{
int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER));
struct hrtimer_cpu_base *old_base, *new_base;
old_base = this_cpu_ptr(&hrtimer_bases);
new_base = &per_cpu(hrtimer_bases, ncpu);
/*
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
*/
raw_spin_lock(&old_base->lock);
raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
migrate_hrtimer_list(&old_base->clock_base[i],
&new_base->clock_base[i]);
}
/*
* The migration might have changed the first expiring softirq
* timer on this CPU. Update it.
*/
__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
/* Tell the other CPU to retrigger the next event */
smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
raw_spin_unlock(&new_base->lock);
old_base->online = 0;
raw_spin_unlock(&old_base->lock);
return 0;
}
#endif /* CONFIG_HOTPLUG_CPU */
void __init hrtimers_init(void)
{
hrtimers_prepare_cpu(smp_processor_id());
hrtimers_cpu_starting(smp_processor_id());
open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_TASK_H
#define _LINUX_SCHED_TASK_H
/*
* Interface between the scheduler and various task lifetime (fork()/exit())
* functionality:
*/
#include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
struct task_struct;
struct rusage;
union thread_union;
struct css_set;
/* All the bits taken by the old clone syscall. */
#define CLONE_LEGACY_FLAGS 0xffffffffULL
struct kernel_clone_args {
u64 flags;
int __user *pidfd;
int __user *child_tid;
int __user *parent_tid;
const char *name;
int exit_signal;
u32 kthread:1;
u32 io_thread:1;
u32 user_worker:1;
u32 no_files:1;
unsigned long stack;
unsigned long stack_size;
unsigned long tls;
pid_t *set_tid;
/* Number of elements in *set_tid */
size_t set_tid_size;
int cgroup;
int idle;
int (*fn)(void *);
void *fn_arg;
struct cgroup *cgrp;
struct css_set *cset;
unsigned int kill_seq;
};
/*
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
* _adding_ to the beginning of the run-queue has
* a separate lock).
*/
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;
extern union thread_union init_thread_union;
extern struct task_struct init_task;
extern int lockdep_tasklist_lock_is_held(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
extern void sched_cancel_fork(struct task_struct *p);
extern void sched_post_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);
void __noreturn do_task_dead(void);
void __noreturn make_task_dead(int signr);
extern void mm_cache_init(void);
extern void proc_caches_init(void);
extern void fork_init(void);
extern void release_task(struct task_struct * p);
extern int copy_thread(struct task_struct *, const struct kernel_clone_args *);
extern void flush_thread(void);
#ifdef CONFIG_HAVE_EXIT_THREAD
extern void exit_thread(struct task_struct *tsk);
#else
static inline void exit_thread(struct task_struct *tsk)
{
}
#endif
extern __noreturn void do_group_exit(int);
extern void exit_files(struct task_struct *);
extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *copy_process(struct pid *pid, int trace, int node,
struct kernel_clone_args *args);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
struct task_struct *fork_idle(int);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name,
unsigned long flags);
extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
int kernel_wait(pid_t pid, int *stat);
extern void free_task(struct task_struct *tsk);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec() {}
#endif
static inline struct task_struct *get_task_struct(struct task_struct *t)
{
refcount_inc(&t->usage);
return t;
}
static inline struct task_struct *tryget_task_struct(struct task_struct *t)
{
return refcount_inc_not_zero(&t->usage) ? t : NULL;
}
extern void __put_task_struct(struct task_struct *t);
extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);
static inline void put_task_struct(struct task_struct *t)
{
if (!refcount_dec_and_test(&t->usage))
return;
/*
* In !RT, it is always safe to call __put_task_struct().
* Under RT, we can only call it in preemptible context.
*/
if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
lock_map_acquire_try(&put_task_map);
__put_task_struct(t);
lock_map_release(&put_task_map);
return;
}
/*
* under PREEMPT_RT, we can't call put_task_struct
* in atomic context because it will indirectly
* acquire sleeping locks.
*
* call_rcu() will schedule delayed_put_task_struct_rcu()
* to be called in process context.
*
* __put_task_struct() is called when
* refcount_dec_and_test(&t->usage) succeeds.
*
* This means that it can't "conflict" with
* put_task_struct_rcu_user() which abuses ->rcu the same
* way; rcu_users has a reference so task->usage can't be
* zero after rcu_users 1 -> 0 transition.
*
* delayed_free_task() also uses ->rcu, but it is only called
* when it fails to fork a process. Therefore, there is no
* way it can conflict with put_task_struct().
*/
call_rcu(&t->rcu, __put_task_struct_rcu_cb);
}
DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T))
static inline void put_task_struct_many(struct task_struct *t, int nr)
{
if (refcount_sub_and_test(nr, &t->usage))
__put_task_struct(t);
}
void put_task_struct_rcu_user(struct task_struct *task);
/* Free all architecture-specific resources held by a thread. */
void release_thread(struct task_struct *dead_task);
#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
extern int arch_task_struct_size __read_mostly;
#else
# define arch_task_struct_size (sizeof(struct task_struct))
#endif
#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
/*
* If an architecture has not declared a thread_struct whitelist we
* must assume something there may need to be copied to userspace.
*/
static inline void arch_thread_struct_whitelist(unsigned long *offset,
unsigned long *size)
{
*offset = 0;
/* Handle dynamically sized thread_struct. */
*size = arch_task_struct_size - offsetof(struct task_struct, thread);
}
#endif
#ifdef CONFIG_VMAP_STACK
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
{
return t->stack_vm_area;
}
#else
static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
{
return NULL;
}
#endif
/*
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
* pins the final release of task.io_context. Also protects ->cpuset and
* ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
* neither inside nor outside.
*/
static inline void task_lock(struct task_struct *p)
{
spin_lock(&p->alloc_lock);
}
static inline void task_unlock(struct task_struct *p)
{
spin_unlock(&p->alloc_lock);
}
DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))
#endif /* _LINUX_SCHED_TASK_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_NETLINK_H
#define __NET_NETLINK_H
#include <linux/types.h>
#include <linux/netlink.h>
#include <linux/jiffies.h>
#include <linux/in6.h>
/* ========================================================================
* Netlink Messages and Attributes Interface (As Seen On TV)
* ------------------------------------------------------------------------
* Messages Interface
* ------------------------------------------------------------------------
*
* Message Format:
* <--- nlmsg_total_size(payload) --->
* <-- nlmsg_msg_size(payload) ->
* +----------+- - -+-------------+- - -+-------- - -
* | nlmsghdr | Pad | Payload | Pad | nlmsghdr
* +----------+- - -+-------------+- - -+-------- - -
* nlmsg_data(nlh)---^ ^
* nlmsg_next(nlh)-----------------------+
*
* Payload Format:
* <---------------------- nlmsg_len(nlh) --------------------->
* <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) ->
* +----------------------+- - -+--------------------------------+
* | Family Header | Pad | Attributes |
* +----------------------+- - -+--------------------------------+
* nlmsg_attrdata(nlh, hdrlen)---^
*
* Data Structures:
* struct nlmsghdr netlink message header
*
* Message Construction:
* nlmsg_new() create a new netlink message
* nlmsg_put() add a netlink message to an skb
* nlmsg_put_answer() callback based nlmsg_put()
* nlmsg_end() finalize netlink message
* nlmsg_get_pos() return current position in message
* nlmsg_trim() trim part of message
* nlmsg_cancel() cancel message construction
* nlmsg_consume() free a netlink message (expected)
* nlmsg_free() free a netlink message (drop)
*
* Message Sending:
* nlmsg_multicast() multicast message to several groups
* nlmsg_unicast() unicast a message to a single socket
* nlmsg_notify() send notification message
*
* Message Length Calculations:
* nlmsg_msg_size(payload) length of message w/o padding
* nlmsg_total_size(payload) length of message w/ padding
* nlmsg_padlen(payload) length of padding at tail
*
* Message Payload Access:
* nlmsg_data(nlh) head of message payload
* nlmsg_len(nlh) length of message payload
* nlmsg_attrdata(nlh, hdrlen) head of attributes data
* nlmsg_attrlen(nlh, hdrlen) length of attributes data
*
* Message Parsing:
* nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes?
* nlmsg_next(nlh, remaining) get next netlink message
* nlmsg_parse() parse attributes of a message
* nlmsg_find_attr() find an attribute in a message
* nlmsg_for_each_msg() loop over all messages
* nlmsg_validate() validate netlink message incl. attrs
* nlmsg_for_each_attr() loop over all attributes
*
* Misc:
* nlmsg_report() report back to application?
*
* ------------------------------------------------------------------------
* Attributes Interface
* ------------------------------------------------------------------------
*
* Attribute Format:
* <------- nla_total_size(payload) ------->
* <---- nla_attr_size(payload) ----->
* +----------+- - -+- - - - - - - - - +- - -+-------- - -
* | Header | Pad | Payload | Pad | Header
* +----------+- - -+- - - - - - - - - +- - -+-------- - -
* <- nla_len(nla) -> ^
* nla_data(nla)----^ |
* nla_next(nla)-----------------------------'
*
* Data Structures:
* struct nlattr netlink attribute header
*
* Attribute Construction:
* nla_reserve(skb, type, len) reserve room for an attribute
* nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr
* nla_put(skb, type, len, data) add attribute to skb
* nla_put_nohdr(skb, len, data) add attribute w/o hdr
* nla_append(skb, len, data) append data to skb
*
* Attribute Construction for Basic Types:
* nla_put_u8(skb, type, value) add u8 attribute to skb
* nla_put_u16(skb, type, value) add u16 attribute to skb
* nla_put_u32(skb, type, value) add u32 attribute to skb
* nla_put_u64_64bit(skb, type,
* value, padattr) add u64 attribute to skb
* nla_put_s8(skb, type, value) add s8 attribute to skb
* nla_put_s16(skb, type, value) add s16 attribute to skb
* nla_put_s32(skb, type, value) add s32 attribute to skb
* nla_put_s64(skb, type, value,
* padattr) add s64 attribute to skb
* nla_put_string(skb, type, str) add string attribute to skb
* nla_put_flag(skb, type) add flag attribute to skb
* nla_put_msecs(skb, type, jiffies,
* padattr) add msecs attribute to skb
* nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb
* nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb
*
* Nested Attributes Construction:
* nla_nest_start(skb, type) start a nested attribute
* nla_nest_end(skb, nla) finalize a nested attribute
* nla_nest_cancel(skb, nla) cancel nested attribute construction
* nla_put_empty_nest(skb, type) create an empty nest
*
* Attribute Length Calculations:
* nla_attr_size(payload) length of attribute w/o padding
* nla_total_size(payload) length of attribute w/ padding
* nla_padlen(payload) length of padding
*
* Attribute Payload Access:
* nla_data(nla) head of attribute payload
* nla_len(nla) length of attribute payload
*
* Attribute Payload Access for Basic Types:
* nla_get_uint(nla) get payload for a uint attribute
* nla_get_sint(nla) get payload for a sint attribute
* nla_get_u8(nla) get payload for a u8 attribute
* nla_get_u16(nla) get payload for a u16 attribute
* nla_get_u32(nla) get payload for a u32 attribute
* nla_get_u64(nla) get payload for a u64 attribute
* nla_get_s8(nla) get payload for a s8 attribute
* nla_get_s16(nla) get payload for a s16 attribute
* nla_get_s32(nla) get payload for a s32 attribute
* nla_get_s64(nla) get payload for a s64 attribute
* nla_get_flag(nla) return 1 if flag is true
* nla_get_msecs(nla) get payload for a msecs attribute
*
* The same functions also exist with _default().
*
* Attribute Misc:
* nla_memcpy(dest, nla, count) copy attribute into memory
* nla_memcmp(nla, data, size) compare attribute with memory area
* nla_strscpy(dst, nla, size) copy attribute to a sized string
* nla_strcmp(nla, str) compare attribute with string
*
* Attribute Parsing:
* nla_ok(nla, remaining) does nla fit into remaining bytes?
* nla_next(nla, remaining) get next netlink attribute
* nla_validate() validate a stream of attributes
* nla_validate_nested() validate a stream of nested attributes
* nla_find() find attribute in stream of attributes
* nla_find_nested() find attribute in nested attributes
* nla_parse() parse and validate stream of attrs
* nla_parse_nested() parse nested attributes
* nla_for_each_attr() loop over all attributes
* nla_for_each_attr_type() loop over all attributes with the
* given type
* nla_for_each_nested() loop over the nested attributes
* nla_for_each_nested_type() loop over the nested attributes with
* the given type
*=========================================================================
*/
/**
* Standard attribute types to specify validation policy
*/
enum {
NLA_UNSPEC,
NLA_U8,
NLA_U16,
NLA_U32,
NLA_U64,
NLA_STRING,
NLA_FLAG,
NLA_MSECS,
NLA_NESTED,
NLA_NESTED_ARRAY,
NLA_NUL_STRING,
NLA_BINARY,
NLA_S8,
NLA_S16,
NLA_S32,
NLA_S64,
NLA_BITFIELD32,
NLA_REJECT,
NLA_BE16,
NLA_BE32,
NLA_SINT,
NLA_UINT,
__NLA_TYPE_MAX,
};
#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
struct netlink_range_validation {
u64 min, max;
};
struct netlink_range_validation_signed {
s64 min, max;
};
enum nla_policy_validation {
NLA_VALIDATE_NONE,
NLA_VALIDATE_RANGE,
NLA_VALIDATE_RANGE_WARN_TOO_LONG,
NLA_VALIDATE_MIN,
NLA_VALIDATE_MAX,
NLA_VALIDATE_MASK,
NLA_VALIDATE_RANGE_PTR,
NLA_VALIDATE_FUNCTION,
};
/**
* struct nla_policy - attribute validation policy
* @type: Type of attribute or NLA_UNSPEC
* @validation_type: type of attribute validation done in addition to
* type-specific validation (e.g. range, function call), see
* &enum nla_policy_validation
* @len: Type specific length of payload
*
* Policies are defined as arrays of this struct, the array must be
* accessible by attribute type up to the highest identifier to be expected.
*
* Meaning of `len' field:
* NLA_STRING Maximum length of string
* NLA_NUL_STRING Maximum length of string (excluding NUL)
* NLA_FLAG Unused
* NLA_BINARY Maximum length of attribute payload
* (but see also below with the validation type)
* NLA_NESTED,
* NLA_NESTED_ARRAY Length verification is done by checking len of
* nested header (or empty); len field is used if
* nested_policy is also used, for the max attr
* number in the nested policy.
* NLA_SINT, NLA_UINT,
* NLA_U8, NLA_U16,
* NLA_U32, NLA_U64,
* NLA_S8, NLA_S16,
* NLA_S32, NLA_S64,
* NLA_BE16, NLA_BE32,
* NLA_MSECS Leaving the length field zero will verify the
* given type fits, using it verifies minimum length
* just like "All other"
* NLA_BITFIELD32 Unused
* NLA_REJECT Unused
* All other Minimum length of attribute payload
*
* Meaning of validation union:
* NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and
* `bitfield32_valid' is the u32 value of valid flags
* NLA_REJECT This attribute is always rejected and `reject_message'
* may point to a string to report as the error instead
* of the generic one in extended ACK.
* NLA_NESTED `nested_policy' to a nested policy to validate, must
* also set `len' to the max attribute number. Use the
* provided NLA_POLICY_NESTED() macro.
* Note that nla_parse() will validate, but of course not
* parse, the nested sub-policies.
* NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate,
* must also set `len' to the max attribute number. Use
* the provided NLA_POLICY_NESTED_ARRAY() macro.
* The difference to NLA_NESTED is the structure:
* NLA_NESTED has the nested attributes directly inside
* while an array has the nested attributes at another
* level down and the attribute types directly in the
* nesting don't matter.
* NLA_UINT,
* NLA_U8,
* NLA_U16,
* NLA_U32,
* NLA_U64,
* NLA_BE16,
* NLA_BE32,
* NLA_SINT,
* NLA_S8,
* NLA_S16,
* NLA_S32,
* NLA_S64 The `min' and `max' fields are used depending on the
* validation_type field, if that is min/max/range then
* the min, max or both are used (respectively) to check
* the value of the integer attribute.
* Note that in the interest of code simplicity and
* struct size both limits are s16, so you cannot
* enforce a range that doesn't fall within the range
* of s16 - do that using the NLA_POLICY_FULL_RANGE()
* or NLA_POLICY_FULL_RANGE_SIGNED() macros instead.
* Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and
* NLA_POLICY_RANGE() macros.
* NLA_UINT,
* NLA_U8,
* NLA_U16,
* NLA_U32,
* NLA_U64 If the validation_type field instead is set to
* NLA_VALIDATE_RANGE_PTR, `range' must be a pointer
* to a struct netlink_range_validation that indicates
* the min/max values.
* Use NLA_POLICY_FULL_RANGE().
* NLA_SINT,
* NLA_S8,
* NLA_S16,
* NLA_S32,
* NLA_S64 If the validation_type field instead is set to
* NLA_VALIDATE_RANGE_PTR, `range_signed' must be a
* pointer to a struct netlink_range_validation_signed
* that indicates the min/max values.
* Use NLA_POLICY_FULL_RANGE_SIGNED().
*
* NLA_BINARY If the validation type is like the ones for integers
* above, then the min/max length (not value like for
* integers) of the attribute is enforced.
*
* All other Unused - but note that it's a union
*
* Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN:
* NLA_BINARY Validation function called for the attribute.
* All other Unused - but note that it's a union
*
* Example:
*
* static const u32 myvalidflags = 0xff231023;
*
* static const struct nla_policy my_policy[ATTR_MAX+1] = {
* [ATTR_FOO] = { .type = NLA_U16 },
* [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ },
* [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)),
* [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags),
* };
*/
struct nla_policy {
u8 type;
u8 validation_type;
u16 len;
union {
/**
* @strict_start_type: first attribute to validate strictly
*
* This entry is special, and used for the attribute at index 0
* only, and specifies special data about the policy, namely it
* specifies the "boundary type" where strict length validation
* starts for any attribute types >= this value, also, strict
* nesting validation starts here.
*
* Additionally, it means that NLA_UNSPEC is actually NLA_REJECT
* for any types >= this, so need to use NLA_POLICY_MIN_LEN() to
* get the previous pure { .len = xyz } behaviour. The advantage
* of this is that types not specified in the policy will be
* rejected.
*
* For completely new families it should be set to 1 so that the
* validation is enforced for all attributes. For existing ones
* it should be set at least when new attributes are added to
* the enum used by the policy, and be set to the new value that
* was added to enforce strict validation from thereon.
*/
u16 strict_start_type;
/* private: use NLA_POLICY_*() to set */
const u32 bitfield32_valid;
const u32 mask;
const char *reject_message;
const struct nla_policy *nested_policy;
const struct netlink_range_validation *range;
const struct netlink_range_validation_signed *range_signed;
struct {
s16 min, max;
};
int (*validate)(const struct nlattr *attr,
struct netlink_ext_ack *extack);
};
};
#define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN)
#define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN)
#define _NLA_POLICY_NESTED(maxattr, policy) \
{ .type = NLA_NESTED, .nested_policy = policy, .len = maxattr }
#define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \
{ .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr }
#define NLA_POLICY_NESTED(policy) \
_NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy)
#define NLA_POLICY_NESTED_ARRAY(policy) \
_NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy)
#define NLA_POLICY_BITFIELD32(valid) \
{ .type = NLA_BITFIELD32, .bitfield32_valid = valid }
#define __NLA_IS_UINT_TYPE(tp) \
(tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \
tp == NLA_U64 || tp == NLA_UINT || \
tp == NLA_BE16 || tp == NLA_BE32)
#define __NLA_IS_SINT_TYPE(tp) \
(tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \
tp == NLA_SINT)
#define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
#define NLA_ENSURE_UINT_TYPE(tp) \
(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp)
#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \
(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \
tp == NLA_MSECS || \
tp == NLA_BINARY) + tp)
#define NLA_ENSURE_SINT_TYPE(tp) \
(__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp)
#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \
(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \
__NLA_IS_SINT_TYPE(tp) || \
tp == NLA_MSECS || \
tp == NLA_BINARY) + tp)
#define NLA_ENSURE_NO_VALIDATION_PTR(tp) \
(__NLA_ENSURE(tp != NLA_BITFIELD32 && \
tp != NLA_REJECT && \
tp != NLA_NESTED && \
tp != NLA_NESTED_ARRAY) + tp)
#define NLA_POLICY_RANGE(tp, _min, _max) { \
.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_RANGE, \
.min = _min, \
.max = _max \
}
#define NLA_POLICY_FULL_RANGE(tp, _range) { \
.type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_RANGE_PTR, \
.range = _range, \
}
#define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \
.type = NLA_ENSURE_SINT_TYPE(tp), \
.validation_type = NLA_VALIDATE_RANGE_PTR, \
.range_signed = _range, \
}
#define NLA_POLICY_MIN(tp, _min) { \
.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_MIN, \
.min = _min, \
}
#define NLA_POLICY_MAX(tp, _max) { \
.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_MAX, \
.max = _max, \
}
#define NLA_POLICY_MASK(tp, _mask) { \
.type = NLA_ENSURE_UINT_TYPE(tp), \
.validation_type = NLA_VALIDATE_MASK, \
.mask = _mask, \
}
#define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \
.type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \
.validation_type = NLA_VALIDATE_FUNCTION, \
.validate = fn, \
.len = __VA_ARGS__ + 0, \
}
#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len)
#define NLA_POLICY_EXACT_LEN_WARN(_len) { \
.type = NLA_BINARY, \
.validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \
.min = _len, \
.max = _len \
}
#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len)
#define NLA_POLICY_MAX_LEN(_len) NLA_POLICY_MAX(NLA_BINARY, _len)
/**
* struct nl_info - netlink source information
* @nlh: Netlink message header of original request
* @nl_net: Network namespace
* @portid: Netlink PORTID of requesting application
* @skip_notify: Skip netlink notifications to user space
* @skip_notify_kernel: Skip selected in-kernel notifications
*/
struct nl_info {
struct nlmsghdr *nlh;
struct net *nl_net;
u32 portid;
u8 skip_notify:1,
skip_notify_kernel:1;
};
/**
* enum netlink_validation - netlink message/attribute validation levels
* @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about
* extra data at the end of the message, attributes being longer than
* they should be, or unknown attributes being present.
* @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing.
* @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING
* this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict().
* @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy.
* This can safely be set by the kernel when the given policy has no
* NLA_UNSPEC anymore, and can thus be used to ensure policy entries
* are enforced going forward.
* @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g.
* U8, U16, U32 must have exact size, etc.)
* @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY)
* and unset for other policies.
*/
enum netlink_validation {
NL_VALIDATE_LIBERAL = 0,
NL_VALIDATE_TRAILING = BIT(0),
NL_VALIDATE_MAXTYPE = BIT(1),
NL_VALIDATE_UNSPEC = BIT(2),
NL_VALIDATE_STRICT_ATTRS = BIT(3),
NL_VALIDATE_NESTED = BIT(4),
};
#define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\
NL_VALIDATE_MAXTYPE)
#define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\
NL_VALIDATE_MAXTYPE |\
NL_VALIDATE_UNSPEC |\
NL_VALIDATE_STRICT_ATTRS |\
NL_VALIDATE_NESTED)
int netlink_rcv_skb(struct sk_buff *skb,
int (*cb)(struct sk_buff *, struct nlmsghdr *,
struct netlink_ext_ack *));
int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
unsigned int group, int report, gfp_t flags);
int __nla_validate(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack);
int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
int len, const struct nla_policy *policy, unsigned int validate,
struct netlink_ext_ack *extack);
int nla_policy_len(const struct nla_policy *, int);
struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize);
char *nla_strdup(const struct nlattr *nla, gfp_t flags);
int nla_memcpy(void *dest, const struct nlattr *src, int count);
int nla_memcmp(const struct nlattr *nla, const void *data, size_t size);
int nla_strcmp(const struct nlattr *nla, const char *str);
struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen);
struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype,
int attrlen, int padattr);
void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen);
struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype,
int attrlen, int padattr);
void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
void __nla_put(struct sk_buff *skb, int attrtype, int attrlen,
const void *data);
void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen,
const void *data, int padattr);
void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data);
int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data);
int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen,
const void *data, int padattr);
int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data);
int nla_append(struct sk_buff *skb, int attrlen, const void *data);
/**************************************************************************
* Netlink Messages
**************************************************************************/
/**
* nlmsg_msg_size - length of netlink message not including padding
* @payload: length of message payload
*/
static inline int nlmsg_msg_size(int payload)
{
return NLMSG_HDRLEN + payload;
}
/**
* nlmsg_total_size - length of netlink message including padding
* @payload: length of message payload
*/
static inline int nlmsg_total_size(int payload)
{
return NLMSG_ALIGN(nlmsg_msg_size(payload));
}
/**
* nlmsg_padlen - length of padding at the message's tail
* @payload: length of message payload
*/
static inline int nlmsg_padlen(int payload)
{
return nlmsg_total_size(payload) - nlmsg_msg_size(payload);
}
/**
* nlmsg_data - head of message payload
* @nlh: netlink message header
*/
static inline void *nlmsg_data(const struct nlmsghdr *nlh)
{
return (unsigned char *) nlh + NLMSG_HDRLEN;
}
/**
* nlmsg_len - length of message payload
* @nlh: netlink message header
*/
static inline int nlmsg_len(const struct nlmsghdr *nlh)
{
return nlh->nlmsg_len - NLMSG_HDRLEN;
}
/**
* nlmsg_attrdata - head of attributes data
* @nlh: netlink message header
* @hdrlen: length of family specific header
*/
static inline struct nlattr *nlmsg_attrdata(const struct nlmsghdr *nlh,
int hdrlen)
{
unsigned char *data = nlmsg_data(nlh);
return (struct nlattr *) (data + NLMSG_ALIGN(hdrlen));
}
/**
* nlmsg_attrlen - length of attributes data
* @nlh: netlink message header
* @hdrlen: length of family specific header
*/
static inline int nlmsg_attrlen(const struct nlmsghdr *nlh, int hdrlen)
{
return nlmsg_len(nlh) - NLMSG_ALIGN(hdrlen);
}
/**
* nlmsg_ok - check if the netlink message fits into the remaining bytes
* @nlh: netlink message header
* @remaining: number of bytes remaining in message stream
*/
static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining)
{
return (remaining >= (int) sizeof(struct nlmsghdr) &&
nlh->nlmsg_len >= sizeof(struct nlmsghdr) &&
nlh->nlmsg_len <= remaining);
}
/**
* nlmsg_next - next netlink message in message stream
* @nlh: netlink message header
* @remaining: number of bytes remaining in message stream
*
* Returns: the next netlink message in the message stream and
* decrements remaining by the size of the current message.
*/
static inline struct nlmsghdr *
nlmsg_next(const struct nlmsghdr *nlh, int *remaining)
{
int totlen = NLMSG_ALIGN(nlh->nlmsg_len);
*remaining -= totlen;
return (struct nlmsghdr *) ((unsigned char *) nlh + totlen);
}
/**
* nla_parse - Parse a stream of attributes into a tb buffer
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @head: head of attribute stream
* @len: length of attribute stream
* @policy: validation policy
* @extack: extended ACK pointer
*
* Parses a stream of attributes and stores a pointer to each attribute in
* the tb array accessible via the attribute type. Attributes with a type
* exceeding maxtype will be rejected, policy must be specified, attributes
* will be validated in the strictest way possible.
*
* Returns: 0 on success or a negative error code.
*/
static inline int nla_parse(struct nlattr **tb, int maxtype,
const struct nlattr *head, int len,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_parse(tb, maxtype, head, len, policy,
NL_VALIDATE_STRICT, extack);
}
/**
* nla_parse_deprecated - Parse a stream of attributes into a tb buffer
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @head: head of attribute stream
* @len: length of attribute stream
* @policy: validation policy
* @extack: extended ACK pointer
*
* Parses a stream of attributes and stores a pointer to each attribute in
* the tb array accessible via the attribute type. Attributes with a type
* exceeding maxtype will be ignored and attributes from the policy are not
* always strictly validated (only for new attributes).
*
* Returns: 0 on success or a negative error code.
*/
static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype,
const struct nlattr *head, int len,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_parse(tb, maxtype, head, len, policy,
NL_VALIDATE_LIBERAL, extack);
}
/**
* nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @head: head of attribute stream
* @len: length of attribute stream
* @policy: validation policy
* @extack: extended ACK pointer
*
* Parses a stream of attributes and stores a pointer to each attribute in
* the tb array accessible via the attribute type. Attributes with a type
* exceeding maxtype will be rejected as well as trailing data, but the
* policy is not completely strictly validated (only for new attributes).
*
* Returns: 0 on success or a negative error code.
*/
static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype,
const struct nlattr *head,
int len,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_parse(tb, maxtype, head, len, policy,
NL_VALIDATE_DEPRECATED_STRICT, extack);
}
/**
* __nlmsg_parse - parse attributes of a netlink message
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @validate: validation strictness
* @extack: extended ACK report struct
*
* See nla_parse()
*/
static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
struct nlattr *tb[], int maxtype,
const struct nla_policy *policy,
unsigned int validate,
struct netlink_ext_ack *extack)
{
if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) {
NL_SET_ERR_MSG(extack, "Invalid header length");
return -EINVAL;
}
return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
nlmsg_attrlen(nlh, hdrlen), policy, validate,
extack);
}
/**
* nlmsg_parse - parse attributes of a netlink message
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*
* See nla_parse()
*/
static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
struct nlattr *tb[], int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
NL_VALIDATE_STRICT, extack);
}
/**
* nlmsg_parse_deprecated - parse attributes of a netlink message
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*
* See nla_parse_deprecated()
*/
static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen,
struct nlattr *tb[], int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
NL_VALIDATE_LIBERAL, extack);
}
/**
* nlmsg_parse_deprecated_strict - parse attributes of a netlink message
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*
* See nla_parse_deprecated_strict()
*/
static inline int
nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen,
struct nlattr *tb[], int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
NL_VALIDATE_DEPRECATED_STRICT, extack);
}
/**
* nlmsg_find_attr - find a specific attribute in a netlink message
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @attrtype: type of attribute to look for
*
* Returns: the first attribute which matches the specified type.
*/
static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
int hdrlen, int attrtype)
{
return nla_find(nlmsg_attrdata(nlh, hdrlen),
nlmsg_attrlen(nlh, hdrlen), attrtype);
}
/**
* nla_validate_deprecated - Validate a stream of attributes
* @head: head of attribute stream
* @len: length of attribute stream
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*
* Validates all attributes in the specified attribute stream against the
* specified policy. Validation is done in liberal mode.
* See documentation of struct nla_policy for more details.
*
* Returns: 0 on success or a negative error code.
*/
static inline int nla_validate_deprecated(const struct nlattr *head, int len,
int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL,
extack);
}
/**
* nla_validate - Validate a stream of attributes
* @head: head of attribute stream
* @len: length of attribute stream
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*
* Validates all attributes in the specified attribute stream against the
* specified policy. Validation is done in strict mode.
* See documentation of struct nla_policy for more details.
*
* Returns: 0 on success or a negative error code.
*/
static inline int nla_validate(const struct nlattr *head, int len, int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT,
extack);
}
/**
* nlmsg_validate_deprecated - validate a netlink message including attributes
* @nlh: netlinket message header
* @hdrlen: length of family specific header
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @extack: extended ACK report struct
*/
static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh,
int hdrlen, int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
return -EINVAL;
return __nla_validate(nlmsg_attrdata(nlh, hdrlen),
nlmsg_attrlen(nlh, hdrlen), maxtype,
policy, NL_VALIDATE_LIBERAL, extack);
}
/**
* nlmsg_report - need to report back to application?
* @nlh: netlink message header
*
* Returns: 1 if a report back to the application is requested.
*/
static inline int nlmsg_report(const struct nlmsghdr *nlh)
{
return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0;
}
/**
* nlmsg_seq - return the seq number of netlink message
* @nlh: netlink message header
*
* Returns: 0 if netlink message is NULL
*/
static inline u32 nlmsg_seq(const struct nlmsghdr *nlh)
{
return nlh ? nlh->nlmsg_seq : 0;
}
/**
* nlmsg_for_each_attr - iterate over a stream of attributes
* @pos: loop counter, set to current attribute
* @nlh: netlink message header
* @hdrlen: length of family specific header
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \
nla_for_each_attr(pos, nlmsg_attrdata(nlh, hdrlen), \
nlmsg_attrlen(nlh, hdrlen), rem)
/**
* nlmsg_put - Add a new netlink message to an skb
* @skb: socket buffer to store message in
* @portid: netlink PORTID of requesting application
* @seq: sequence number of message
* @type: message type
* @payload: length of message payload
* @flags: message flags
*
* Returns: NULL if the tailroom of the skb is insufficient to store
* the message header and payload.
*/
static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
int type, int payload, int flags)
{
if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload)))
return NULL;
return __nlmsg_put(skb, portid, seq, type, payload, flags);
}
/**
* nlmsg_append - Add more data to a nlmsg in a skb
* @skb: socket buffer to store message in
* @size: length of message payload
*
* Append data to an existing nlmsg, used when constructing a message
* with multiple fixed-format headers (which is rare).
* Returns: NULL if the tailroom of the skb is insufficient to store
* the extra payload.
*/
static inline void *nlmsg_append(struct sk_buff *skb, u32 size)
{
if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size)))
return NULL;
if (NLMSG_ALIGN(size) - size)
memset(skb_tail_pointer(skb) + size, 0,
NLMSG_ALIGN(size) - size);
return __skb_put(skb, NLMSG_ALIGN(size));
}
/**
* nlmsg_put_answer - Add a new callback based netlink message to an skb
* @skb: socket buffer to store message in
* @cb: netlink callback
* @type: message type
* @payload: length of message payload
* @flags: message flags
*
* Returns: NULL if the tailroom of the skb is insufficient to store
* the message header and payload.
*/
static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb,
struct netlink_callback *cb,
int type, int payload,
int flags)
{
return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
type, payload, flags);
}
/**
* nlmsg_new - Allocate a new netlink message
* @payload: size of the message payload
* @flags: the type of memory to allocate.
*
* Use NLMSG_DEFAULT_SIZE if the size of the payload isn't known
* and a good default is needed.
*/
static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags)
{
return alloc_skb(nlmsg_total_size(payload), flags);
}
/**
* nlmsg_new_large - Allocate a new netlink message with non-contiguous
* physical memory
* @payload: size of the message payload
*
* The allocated skb is unable to have frag page for shinfo->frags*,
* as the NULL setting for skb->head in netlink_skb_destructor() will
* bypass most of the handling in skb_release_data()
*/
static inline struct sk_buff *nlmsg_new_large(size_t payload)
{
return netlink_alloc_large_skb(nlmsg_total_size(payload), 0);
}
/**
* nlmsg_end - Finalize a netlink message
* @skb: socket buffer the message is stored in
* @nlh: netlink message header
*
* Corrects the netlink message header to include the appended
* attributes. Only necessary if attributes have been added to
* the message.
*/
static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh)
{
nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh;
}
/**
* nlmsg_get_pos - return current position in netlink message
* @skb: socket buffer the message is stored in
*
* Returns: a pointer to the current tail of the message.
*/
static inline void *nlmsg_get_pos(struct sk_buff *skb)
{
return skb_tail_pointer(skb);
}
/**
* nlmsg_trim - Trim message to a mark
* @skb: socket buffer the message is stored in
* @mark: mark to trim to
*
* Trims the message to the provided mark.
*/
static inline void nlmsg_trim(struct sk_buff *skb, const void *mark)
{
if (mark) {
WARN_ON((unsigned char *) mark < skb->data);
skb_trim(skb, (unsigned char *) mark - skb->data);
}
}
/**
* nlmsg_cancel - Cancel construction of a netlink message
* @skb: socket buffer the message is stored in
* @nlh: netlink message header
*
* Removes the complete netlink message including all
* attributes from the socket buffer again.
*/
static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh)
{
nlmsg_trim(skb, nlh);
}
/**
* nlmsg_free - drop a netlink message
* @skb: socket buffer of netlink message
*/
static inline void nlmsg_free(struct sk_buff *skb)
{
kfree_skb(skb);
}
/**
* nlmsg_consume - free a netlink message
* @skb: socket buffer of netlink message
*/
static inline void nlmsg_consume(struct sk_buff *skb)
{
consume_skb(skb);
}
/**
* nlmsg_multicast_filtered - multicast a netlink message with filter function
* @sk: netlink socket to spread messages to
* @skb: netlink message as socket buffer
* @portid: own netlink portid to avoid sending to yourself
* @group: multicast group id
* @flags: allocation flags
* @filter: filter function
* @filter_data: filter function private data
*
* Return: 0 on success, negative error code for failure.
*/
static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb,
u32 portid, unsigned int group,
gfp_t flags,
netlink_filter_fn filter,
void *filter_data)
{
int err;
NETLINK_CB(skb).dst_group = group;
err = netlink_broadcast_filtered(sk, skb, portid, group, flags,
filter, filter_data);
if (err > 0)
err = 0;
return err;
}
/**
* nlmsg_multicast - multicast a netlink message
* @sk: netlink socket to spread messages to
* @skb: netlink message as socket buffer
* @portid: own netlink portid to avoid sending to yourself
* @group: multicast group id
* @flags: allocation flags
*/
static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
u32 portid, unsigned int group, gfp_t flags)
{
return nlmsg_multicast_filtered(sk, skb, portid, group, flags,
NULL, NULL);
}
/**
* nlmsg_unicast - unicast a netlink message
* @sk: netlink socket to spread message to
* @skb: netlink message as socket buffer
* @portid: netlink portid of the destination socket
*/
static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid)
{
int err;
err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT);
if (err > 0)
err = 0;
return err;
}
/**
* nlmsg_for_each_msg - iterate over a stream of messages
* @pos: loop counter, set to current message
* @head: head of message stream
* @len: length of message stream
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nlmsg_for_each_msg(pos, head, len, rem) \
for (pos = head, rem = len; \
nlmsg_ok(pos, rem); \
pos = nlmsg_next(pos, &(rem)))
/**
* nl_dump_check_consistent - check if sequence is consistent and advertise if not
* @cb: netlink callback structure that stores the sequence number
* @nlh: netlink message header to write the flag to
*
* This function checks if the sequence (generation) number changed during dump
* and if it did, advertises it in the netlink message header.
*
* The correct way to use it is to set cb->seq to the generation counter when
* all locks for dumping have been acquired, and then call this function for
* each message that is generated.
*
* Note that due to initialisation concerns, 0 is an invalid sequence number
* and must not be used by code that uses this functionality.
*/
static inline void
nl_dump_check_consistent(struct netlink_callback *cb,
struct nlmsghdr *nlh)
{
if (cb->prev_seq && cb->seq != cb->prev_seq)
nlh->nlmsg_flags |= NLM_F_DUMP_INTR;
cb->prev_seq = cb->seq;
}
/**************************************************************************
* Netlink Attributes
**************************************************************************/
/**
* nla_attr_size - length of attribute not including padding
* @payload: length of payload
*/
static inline int nla_attr_size(int payload)
{
return NLA_HDRLEN + payload;
}
/**
* nla_total_size - total length of attribute including padding
* @payload: length of payload
*/
static inline int nla_total_size(int payload)
{
return NLA_ALIGN(nla_attr_size(payload));
}
/**
* nla_padlen - length of padding at the tail of attribute
* @payload: length of payload
*/
static inline int nla_padlen(int payload)
{
return nla_total_size(payload) - nla_attr_size(payload);
}
/**
* nla_type - attribute type
* @nla: netlink attribute
*/
static inline int nla_type(const struct nlattr *nla)
{
return nla->nla_type & NLA_TYPE_MASK;
}
/**
* nla_data - head of payload
* @nla: netlink attribute
*/
static inline void *nla_data(const struct nlattr *nla)
{
return (char *) nla + NLA_HDRLEN;
}
/**
* nla_len - length of payload
* @nla: netlink attribute
*/
static inline u16 nla_len(const struct nlattr *nla)
{
return nla->nla_len - NLA_HDRLEN;
}
/**
* nla_ok - check if the netlink attribute fits into the remaining bytes
* @nla: netlink attribute
* @remaining: number of bytes remaining in attribute stream
*/
static inline int nla_ok(const struct nlattr *nla, int remaining)
{
return remaining >= (int) sizeof(*nla) &&
nla->nla_len >= sizeof(*nla) &&
nla->nla_len <= remaining;
}
/**
* nla_next - next netlink attribute in attribute stream
* @nla: netlink attribute
* @remaining: number of bytes remaining in attribute stream
*
* Returns: the next netlink attribute in the attribute stream and
* decrements remaining by the size of the current attribute.
*/
static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
{
unsigned int totlen = NLA_ALIGN(nla->nla_len);
*remaining -= totlen;
return (struct nlattr *) ((char *) nla + totlen);
}
/**
* nla_find_nested - find attribute in a set of nested attributes
* @nla: attribute containing the nested attributes
* @attrtype: type of attribute to look for
*
* Returns: the first attribute which matches the specified type.
*/
static inline struct nlattr *
nla_find_nested(const struct nlattr *nla, int attrtype)
{
return nla_find(nla_data(nla), nla_len(nla), attrtype);
}
/**
* nla_parse_nested - parse nested attributes
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @nla: attribute containing the nested attributes
* @policy: validation policy
* @extack: extended ACK report struct
*
* See nla_parse()
*/
static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
const struct nlattr *nla,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
if (!(nla->nla_type & NLA_F_NESTED)) {
NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing");
return -EINVAL;
}
return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
NL_VALIDATE_STRICT, extack);
}
/**
* nla_parse_nested_deprecated - parse nested attributes
* @tb: destination array with maxtype+1 elements
* @maxtype: maximum attribute type to be expected
* @nla: attribute containing the nested attributes
* @policy: validation policy
* @extack: extended ACK report struct
*
* See nla_parse_deprecated()
*/
static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype,
const struct nlattr *nla,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
NL_VALIDATE_LIBERAL, extack);
}
/**
* nla_put_u8 - Add a u8 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value)
{
/* temporary variables to work around GCC PR81715 with asan-stack=1 */
u8 tmp = value;
return nla_put(skb, attrtype, sizeof(u8), &tmp);
}
/**
* nla_put_u16 - Add a u16 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value)
{
u16 tmp = value;
return nla_put(skb, attrtype, sizeof(u16), &tmp);
}
/**
* nla_put_be16 - Add a __be16 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value)
{
__be16 tmp = value;
return nla_put(skb, attrtype, sizeof(__be16), &tmp);
}
/**
* nla_put_net16 - Add 16-bit network byte order netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value)
{
__be16 tmp = value;
return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
}
/**
* nla_put_le16 - Add a __le16 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value)
{
__le16 tmp = value;
return nla_put(skb, attrtype, sizeof(__le16), &tmp);
}
/**
* nla_put_u32 - Add a u32 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value)
{
u32 tmp = value;
return nla_put(skb, attrtype, sizeof(u32), &tmp);
}
/**
* nla_put_uint - Add a variable-size unsigned int to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value)
{
u64 tmp64 = value;
u32 tmp32 = value;
if (tmp64 == tmp32)
return nla_put_u32(skb, attrtype, tmp32);
return nla_put(skb, attrtype, sizeof(u64), &tmp64);
}
/**
* nla_put_be32 - Add a __be32 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value)
{
__be32 tmp = value;
return nla_put(skb, attrtype, sizeof(__be32), &tmp);
}
/**
* nla_put_net32 - Add 32-bit network byte order netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value)
{
__be32 tmp = value;
return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp);
}
/**
* nla_put_le32 - Add a __le32 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value)
{
__le32 tmp = value;
return nla_put(skb, attrtype, sizeof(__le32), &tmp);
}
/**
* nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
* @padattr: attribute type for the padding
*/
static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype,
u64 value, int padattr)
{
u64 tmp = value;
return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr);
}
/**
* nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
* @padattr: attribute type for the padding
*/
static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value,
int padattr)
{
__be64 tmp = value;
return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr);
}
/**
* nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
* @padattr: attribute type for the padding
*/
static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value,
int padattr)
{
__be64 tmp = value;
return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp,
padattr);
}
/**
* nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
* @padattr: attribute type for the padding
*/
static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value,
int padattr)
{
__le64 tmp = value;
return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr);
}
/**
* nla_put_s8 - Add a s8 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value)
{
s8 tmp = value;
return nla_put(skb, attrtype, sizeof(s8), &tmp);
}
/**
* nla_put_s16 - Add a s16 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value)
{
s16 tmp = value;
return nla_put(skb, attrtype, sizeof(s16), &tmp);
}
/**
* nla_put_s32 - Add a s32 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value)
{
s32 tmp = value;
return nla_put(skb, attrtype, sizeof(s32), &tmp);
}
/**
* nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
* @padattr: attribute type for the padding
*/
static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value,
int padattr)
{
s64 tmp = value;
return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr);
}
/**
* nla_put_sint - Add a variable-size signed int to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: numeric value
*/
static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value)
{
s64 tmp64 = value;
s32 tmp32 = value;
if (tmp64 == tmp32)
return nla_put_s32(skb, attrtype, tmp32);
return nla_put(skb, attrtype, sizeof(s64), &tmp64);
}
/**
* nla_put_string - Add a string netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @str: NUL terminated string
*/
static inline int nla_put_string(struct sk_buff *skb, int attrtype,
const char *str)
{ return nla_put(skb, attrtype, strlen(str) + 1, str);
}
/**
* nla_put_flag - Add a flag netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
*/
static inline int nla_put_flag(struct sk_buff *skb, int attrtype)
{
return nla_put(skb, attrtype, 0, NULL);
}
/**
* nla_put_msecs - Add a msecs netlink attribute to a skb and align it
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @njiffies: number of jiffies to convert to msecs
* @padattr: attribute type for the padding
*/
static inline int nla_put_msecs(struct sk_buff *skb, int attrtype,
unsigned long njiffies, int padattr)
{
u64 tmp = jiffies_to_msecs(njiffies);
return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr);
}
/**
* nla_put_in_addr - Add an IPv4 address netlink attribute to a socket
* buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @addr: IPv4 address
*/
static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype,
__be32 addr)
{
__be32 tmp = addr;
return nla_put_be32(skb, attrtype, tmp);
}
/**
* nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket
* buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @addr: IPv6 address
*/
static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype,
const struct in6_addr *addr)
{
return nla_put(skb, attrtype, sizeof(*addr), addr);
}
/**
* nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer
* @skb: socket buffer to add attribute to
* @attrtype: attribute type
* @value: value carrying bits
* @selector: selector of valid bits
*/
static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype,
__u32 value, __u32 selector)
{
struct nla_bitfield32 tmp = { value, selector, };
return nla_put(skb, attrtype, sizeof(tmp), &tmp);
}
/**
* nla_get_u32 - return payload of u32 attribute
* @nla: u32 netlink attribute
*/
static inline u32 nla_get_u32(const struct nlattr *nla)
{
return *(u32 *) nla_data(nla);
}
/**
* nla_get_u32_default - return payload of u32 attribute or default
* @nla: u32 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline u32 nla_get_u32_default(const struct nlattr *nla, u32 defvalue)
{
if (!nla)
return defvalue;
return nla_get_u32(nla);
}
/**
* nla_get_be32 - return payload of __be32 attribute
* @nla: __be32 netlink attribute
*/
static inline __be32 nla_get_be32(const struct nlattr *nla)
{
return *(__be32 *) nla_data(nla);
}
/**
* nla_get_be32_default - return payload of be32 attribute or default
* @nla: __be32 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __be32 nla_get_be32_default(const struct nlattr *nla,
__be32 defvalue)
{
if (!nla)
return defvalue;
return nla_get_be32(nla);
}
/**
* nla_get_le32 - return payload of __le32 attribute
* @nla: __le32 netlink attribute
*/
static inline __le32 nla_get_le32(const struct nlattr *nla)
{
return *(__le32 *) nla_data(nla);
}
/**
* nla_get_le32_default - return payload of le32 attribute or default
* @nla: __le32 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __le32 nla_get_le32_default(const struct nlattr *nla,
__le32 defvalue)
{
if (!nla)
return defvalue;
return nla_get_le32(nla);
}
/**
* nla_get_u16 - return payload of u16 attribute
* @nla: u16 netlink attribute
*/
static inline u16 nla_get_u16(const struct nlattr *nla)
{
return *(u16 *) nla_data(nla);
}
/**
* nla_get_u16_default - return payload of u16 attribute or default
* @nla: u16 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline u16 nla_get_u16_default(const struct nlattr *nla, u16 defvalue)
{
if (!nla)
return defvalue;
return nla_get_u16(nla);
}
/**
* nla_get_be16 - return payload of __be16 attribute
* @nla: __be16 netlink attribute
*/
static inline __be16 nla_get_be16(const struct nlattr *nla)
{
return *(__be16 *) nla_data(nla);
}
/**
* nla_get_be16_default - return payload of be16 attribute or default
* @nla: __be16 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __be16 nla_get_be16_default(const struct nlattr *nla,
__be16 defvalue)
{
if (!nla)
return defvalue;
return nla_get_be16(nla);
}
/**
* nla_get_le16 - return payload of __le16 attribute
* @nla: __le16 netlink attribute
*/
static inline __le16 nla_get_le16(const struct nlattr *nla)
{
return *(__le16 *) nla_data(nla);
}
/**
* nla_get_le16_default - return payload of le16 attribute or default
* @nla: __le16 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __le16 nla_get_le16_default(const struct nlattr *nla,
__le16 defvalue)
{
if (!nla)
return defvalue;
return nla_get_le16(nla);
}
/**
* nla_get_u8 - return payload of u8 attribute
* @nla: u8 netlink attribute
*/
static inline u8 nla_get_u8(const struct nlattr *nla)
{
return *(u8 *) nla_data(nla);
}
/**
* nla_get_u8_default - return payload of u8 attribute or default
* @nla: u8 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline u8 nla_get_u8_default(const struct nlattr *nla, u8 defvalue)
{
if (!nla)
return defvalue;
return nla_get_u8(nla);
}
/**
* nla_get_u64 - return payload of u64 attribute
* @nla: u64 netlink attribute
*/
static inline u64 nla_get_u64(const struct nlattr *nla)
{
u64 tmp;
nla_memcpy(&tmp, nla, sizeof(tmp));
return tmp;
}
/**
* nla_get_u64_default - return payload of u64 attribute or default
* @nla: u64 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline u64 nla_get_u64_default(const struct nlattr *nla, u64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_u64(nla);
}
/**
* nla_get_uint - return payload of uint attribute
* @nla: uint netlink attribute
*/
static inline u64 nla_get_uint(const struct nlattr *nla)
{
if (nla_len(nla) == sizeof(u32))
return nla_get_u32(nla);
return nla_get_u64(nla);
}
/**
* nla_get_uint_default - return payload of uint attribute or default
* @nla: uint netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline u64 nla_get_uint_default(const struct nlattr *nla, u64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_uint(nla);
}
/**
* nla_get_be64 - return payload of __be64 attribute
* @nla: __be64 netlink attribute
*/
static inline __be64 nla_get_be64(const struct nlattr *nla)
{
__be64 tmp;
nla_memcpy(&tmp, nla, sizeof(tmp));
return tmp;
}
/**
* nla_get_be64_default - return payload of be64 attribute or default
* @nla: __be64 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __be64 nla_get_be64_default(const struct nlattr *nla,
__be64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_be64(nla);
}
/**
* nla_get_le64 - return payload of __le64 attribute
* @nla: __le64 netlink attribute
*/
static inline __le64 nla_get_le64(const struct nlattr *nla)
{
return *(__le64 *) nla_data(nla);
}
/**
* nla_get_le64_default - return payload of le64 attribute or default
* @nla: __le64 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __le64 nla_get_le64_default(const struct nlattr *nla,
__le64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_le64(nla);
}
/**
* nla_get_s32 - return payload of s32 attribute
* @nla: s32 netlink attribute
*/
static inline s32 nla_get_s32(const struct nlattr *nla)
{
return *(s32 *) nla_data(nla);
}
/**
* nla_get_s32_default - return payload of s32 attribute or default
* @nla: s32 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline s32 nla_get_s32_default(const struct nlattr *nla, s32 defvalue)
{
if (!nla)
return defvalue;
return nla_get_s32(nla);
}
/**
* nla_get_s16 - return payload of s16 attribute
* @nla: s16 netlink attribute
*/
static inline s16 nla_get_s16(const struct nlattr *nla)
{
return *(s16 *) nla_data(nla);
}
/**
* nla_get_s16_default - return payload of s16 attribute or default
* @nla: s16 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline s16 nla_get_s16_default(const struct nlattr *nla, s16 defvalue)
{
if (!nla)
return defvalue;
return nla_get_s16(nla);
}
/**
* nla_get_s8 - return payload of s8 attribute
* @nla: s8 netlink attribute
*/
static inline s8 nla_get_s8(const struct nlattr *nla)
{
return *(s8 *) nla_data(nla);
}
/**
* nla_get_s8_default - return payload of s8 attribute or default
* @nla: s8 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline s8 nla_get_s8_default(const struct nlattr *nla, s8 defvalue)
{
if (!nla)
return defvalue;
return nla_get_s8(nla);
}
/**
* nla_get_s64 - return payload of s64 attribute
* @nla: s64 netlink attribute
*/
static inline s64 nla_get_s64(const struct nlattr *nla)
{
s64 tmp;
nla_memcpy(&tmp, nla, sizeof(tmp));
return tmp;
}
/**
* nla_get_s64_default - return payload of s64 attribute or default
* @nla: s64 netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline s64 nla_get_s64_default(const struct nlattr *nla, s64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_s64(nla);
}
/**
* nla_get_sint - return payload of uint attribute
* @nla: uint netlink attribute
*/
static inline s64 nla_get_sint(const struct nlattr *nla)
{
if (nla_len(nla) == sizeof(s32))
return nla_get_s32(nla);
return nla_get_s64(nla);
}
/**
* nla_get_sint_default - return payload of sint attribute or default
* @nla: sint netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline s64 nla_get_sint_default(const struct nlattr *nla, s64 defvalue)
{
if (!nla)
return defvalue;
return nla_get_sint(nla);
}
/**
* nla_get_flag - return payload of flag attribute
* @nla: flag netlink attribute
*/
static inline int nla_get_flag(const struct nlattr *nla)
{
return !!nla;
}
/**
* nla_get_msecs - return payload of msecs attribute
* @nla: msecs netlink attribute
*
* Returns: the number of milliseconds in jiffies.
*/
static inline unsigned long nla_get_msecs(const struct nlattr *nla)
{
u64 msecs = nla_get_u64(nla);
return msecs_to_jiffies((unsigned long) msecs);
}
/**
* nla_get_msecs_default - return payload of msecs attribute or default
* @nla: msecs netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline unsigned long nla_get_msecs_default(const struct nlattr *nla,
unsigned long defvalue)
{
if (!nla)
return defvalue;
return nla_get_msecs(nla);
}
/**
* nla_get_in_addr - return payload of IPv4 address attribute
* @nla: IPv4 address netlink attribute
*/
static inline __be32 nla_get_in_addr(const struct nlattr *nla)
{
return *(__be32 *) nla_data(nla);
}
/**
* nla_get_in_addr_default - return payload of be32 attribute or default
* @nla: IPv4 address netlink attribute, may be %NULL
* @defvalue: default value to use if @nla is %NULL
*
* Return: the value of the attribute, or the default value if not present
*/
static inline __be32 nla_get_in_addr_default(const struct nlattr *nla,
__be32 defvalue)
{
if (!nla)
return defvalue;
return nla_get_in_addr(nla);
}
/**
* nla_get_in6_addr - return payload of IPv6 address attribute
* @nla: IPv6 address netlink attribute
*/
static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla)
{
struct in6_addr tmp;
nla_memcpy(&tmp, nla, sizeof(tmp));
return tmp;
}
/**
* nla_get_bitfield32 - return payload of 32 bitfield attribute
* @nla: nla_bitfield32 attribute
*/
static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla)
{
struct nla_bitfield32 tmp;
nla_memcpy(&tmp, nla, sizeof(tmp));
return tmp;
}
/**
* nla_memdup - duplicate attribute memory (kmemdup)
* @src: netlink attribute to duplicate from
* @gfp: GFP mask
*/
static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp)
{
return kmemdup_noprof(nla_data(src), nla_len(src), gfp);
}
#define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__))
/**
* nla_nest_start_noflag - Start a new level of nested attributes
* @skb: socket buffer to add attributes to
* @attrtype: attribute type of container
*
* This function exists for backward compatibility to use in APIs which never
* marked their nest attributes with NLA_F_NESTED flag. New APIs should use
* nla_nest_start() which sets the flag.
*
* Returns: the container attribute or NULL on error
*/
static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb,
int attrtype)
{
struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb);
if (nla_put(skb, attrtype, 0, NULL) < 0)
return NULL;
return start;
}
/**
* nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED
* @skb: socket buffer to add attributes to
* @attrtype: attribute type of container
*
* Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED
* flag. This is the preferred function to use in new code.
*
* Returns: the container attribute or NULL on error
*/
static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
{
return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED);
}
/**
* nla_nest_end - Finalize nesting of attributes
* @skb: socket buffer the attributes are stored in
* @start: container attribute
*
* Corrects the container attribute header to include the all
* appended attributes.
*
* Returns: the total data length of the skb.
*/
static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start)
{
start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start;
return skb->len;
}
/**
* nla_nest_cancel - Cancel nesting of attributes
* @skb: socket buffer the message is stored in
* @start: container attribute
*
* Removes the container attribute and including all nested
* attributes. Returns -EMSGSIZE
*/
static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
{
nlmsg_trim(skb, start);
}
/**
* nla_put_empty_nest - Create an empty nest
* @skb: socket buffer the message is stored in
* @attrtype: attribute type of the container
*
* This function is a helper for creating empty nests.
*
* Returns: 0 when successful or -EMSGSIZE on failure.
*/
static inline int nla_put_empty_nest(struct sk_buff *skb, int attrtype)
{
return nla_nest_start(skb, attrtype) ? 0 : -EMSGSIZE;
}
/**
* __nla_validate_nested - Validate a stream of nested attributes
* @start: container attribute
* @maxtype: maximum attribute type to be expected
* @policy: validation policy
* @validate: validation strictness
* @extack: extended ACK report struct
*
* Validates all attributes in the nested attribute stream against the
* specified policy. Attributes with a type exceeding maxtype will be
* ignored. See documentation of struct nla_policy for more details.
*
* Returns: 0 on success or a negative error code.
*/
static inline int __nla_validate_nested(const struct nlattr *start, int maxtype,
const struct nla_policy *policy,
unsigned int validate,
struct netlink_ext_ack *extack)
{
return __nla_validate(nla_data(start), nla_len(start), maxtype, policy,
validate, extack);
}
static inline int
nla_validate_nested(const struct nlattr *start, int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_validate_nested(start, maxtype, policy,
NL_VALIDATE_STRICT, extack);
}
static inline int
nla_validate_nested_deprecated(const struct nlattr *start, int maxtype,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
return __nla_validate_nested(start, maxtype, policy,
NL_VALIDATE_LIBERAL, extack);
}
/**
* nla_need_padding_for_64bit - test 64-bit alignment of the next attribute
* @skb: socket buffer the message is stored in
*
* Return: true if padding is needed to align the next attribute (nla_data()) to
* a 64-bit aligned area.
*/
static inline bool nla_need_padding_for_64bit(struct sk_buff *skb)
{
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
/* The nlattr header is 4 bytes in size, that's why we test
* if the skb->data _is_ aligned. A NOP attribute, plus
* nlattr header for next attribute, will make nla_data()
* 8-byte aligned.
*/
if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8))
return true;
#endif
return false;
}
/**
* nla_align_64bit - 64-bit align the nla_data() of next attribute
* @skb: socket buffer the message is stored in
* @padattr: attribute type for the padding
*
* Conditionally emit a padding netlink attribute in order to make
* the next attribute we emit have a 64-bit aligned nla_data() area.
* This will only be done in architectures which do not have
* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined.
*
* Returns: zero on success or a negative error code.
*/
static inline int nla_align_64bit(struct sk_buff *skb, int padattr)
{
if (nla_need_padding_for_64bit(skb) &&
!nla_reserve(skb, padattr, 0))
return -EMSGSIZE;
return 0;
}
/**
* nla_total_size_64bit - total length of attribute including padding
* @payload: length of payload
*/
static inline int nla_total_size_64bit(int payload)
{
return NLA_ALIGN(nla_attr_size(payload))
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ NLA_ALIGN(nla_attr_size(0))
#endif
;
}
/**
* nla_for_each_attr - iterate over a stream of attributes
* @pos: loop counter, set to current attribute
* @head: head of attribute stream
* @len: length of attribute stream
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nla_for_each_attr(pos, head, len, rem) \
for (pos = head, rem = len; \
nla_ok(pos, rem); \
pos = nla_next(pos, &(rem)))
/**
* nla_for_each_attr_type - iterate over a stream of attributes
* @pos: loop counter, set to current attribute
* @type: required attribute type for @pos
* @head: head of attribute stream
* @len: length of attribute stream
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nla_for_each_attr_type(pos, type, head, len, rem) \
nla_for_each_attr(pos, head, len, rem) \
if (nla_type(pos) == type)
/**
* nla_for_each_nested - iterate over nested attributes
* @pos: loop counter, set to current attribute
* @nla: attribute containing the nested attributes
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nla_for_each_nested(pos, nla, rem) \
nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem)
/**
* nla_for_each_nested_type - iterate over nested attributes
* @pos: loop counter, set to current attribute
* @type: required attribute type for @pos
* @nla: attribute containing the nested attributes
* @rem: initialized to len, holds bytes currently remaining in stream
*/
#define nla_for_each_nested_type(pos, type, nla, rem) \
nla_for_each_nested(pos, nla, rem) \
if (nla_type(pos) == type)
/**
* nla_is_last - Test if attribute is last in stream
* @nla: attribute to test
* @rem: bytes remaining in stream
*/
static inline bool nla_is_last(const struct nlattr *nla, int rem)
{
return nla->nla_len == rem;
}
void nla_get_range_unsigned(const struct nla_policy *pt,
struct netlink_range_validation *range);
void nla_get_range_signed(const struct nla_policy *pt,
struct netlink_range_validation_signed *range);
struct netlink_policy_dump_state;
int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
const struct nla_policy *policy,
unsigned int maxtype);
int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
const struct nla_policy *policy,
unsigned int maxtype);
bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
int netlink_policy_dump_write(struct sk_buff *skb,
struct netlink_policy_dump_state *state);
int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt);
int netlink_policy_dump_write_attr(struct sk_buff *skb,
const struct nla_policy *pt,
int nestattr);
void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_SIGNAL_H
#define _LINUX_SCHED_SIGNAL_H
#include <linux/rculist.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/sched/jobctl.h>
#include <linux/sched/task.h>
#include <linux/cred.h>
#include <linux/refcount.h>
#include <linux/pid.h>
#include <linux/posix-timers.h>
#include <linux/mm_types.h>
#include <asm/ptrace.h>
/*
* Types defining task->signal and task->sighand and APIs using them:
*/
struct sighand_struct {
spinlock_t siglock;
refcount_t count;
wait_queue_head_t signalfd_wqh;
struct k_sigaction action[_NSIG];
};
/*
* Per-process accounting stats:
*/
struct pacct_struct {
int ac_flag;
long ac_exitcode;
unsigned long ac_mem;
u64 ac_utime, ac_stime;
unsigned long ac_minflt, ac_majflt;
};
struct cpu_itimer {
u64 expires;
u64 incr;
};
/*
* This is the atomic variant of task_cputime, which can be used for
* storing and updating task_cputime statistics without locking.
*/
struct task_cputime_atomic {
atomic64_t utime;
atomic64_t stime;
atomic64_t sum_exec_runtime;
};
#define INIT_CPUTIME_ATOMIC \
(struct task_cputime_atomic) { \
.utime = ATOMIC64_INIT(0), \
.stime = ATOMIC64_INIT(0), \
.sum_exec_runtime = ATOMIC64_INIT(0), \
}
/**
* struct thread_group_cputimer - thread group interval timer counts
* @cputime_atomic: atomic thread group interval timers.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
*/
struct thread_group_cputimer {
struct task_cputime_atomic cputime_atomic;
};
struct multiprocess_signals {
sigset_t signal;
struct hlist_node node;
};
struct core_thread {
struct task_struct *task;
struct core_thread *next;
};
struct core_state {
atomic_t nr_threads;
struct core_thread dumper;
struct completion startup;
};
/*
* NOTE! "signal_struct" does not have its own
* locking, because a shared signal_struct always
* implies a shared sighand_struct, so locking
* sighand_struct is always a proper superset of
* the locking of signal_struct.
*/
struct signal_struct {
refcount_t sigcnt;
atomic_t live;
int nr_threads;
int quick_threads;
struct list_head thread_head;
wait_queue_head_t wait_chldexit; /* for wait4() */
/* current thread group signal load-balancing target: */
struct task_struct *curr_target;
/* shared signal handling: */
struct sigpending shared_pending;
/* For collecting multiprocess signals during fork */
struct hlist_head multiprocess;
/* thread group exit support */
int group_exit_code;
/* notify group_exec_task when notify_count is less or equal to 0 */
int notify_count;
struct task_struct *group_exec_task;
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
unsigned int flags; /* see SIGNAL_* flags below */
struct core_state *core_state; /* coredumping support */
/*
* PR_SET_CHILD_SUBREAPER marks a process, like a service
* manager, to re-parent orphan (double-forking) child processes
* to this process instead of 'init'. The service manager is
* able to receive SIGCHLD signals and is able to investigate
* the process until it calls wait(). All children of this
* process will inherit a flag if they should look for a
* child_subreaper process at exit.
*/
unsigned int is_child_subreaper:1;
unsigned int has_child_subreaper:1;
#ifdef CONFIG_POSIX_TIMERS
/* POSIX.1b Interval Timers */
unsigned int timer_create_restore_ids:1;
atomic_t next_posix_timer_id;
struct hlist_head posix_timers;
struct hlist_head ignored_posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
ktime_t it_real_incr;
/*
* ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
* CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
* values are defined to 0 and 1 respectively
*/
struct cpu_itimer it[2];
/*
* Thread group totals for process CPU timers.
* See thread_group_cputimer(), et al, for details.
*/
struct thread_group_cputimer cputimer;
#endif
/* Empty if CONFIG_POSIX_TIMERS=n */
struct posix_cputimers posix_cputimers;
/* PID/PID hash table linkage. */
struct pid *pids[PIDTYPE_MAX];
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
struct pid *tty_old_pgrp;
/* boolean value for session group leader */
int leader;
struct tty_struct *tty; /* NULL if no tty */
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup *autogroup;
#endif
/*
* Cumulative resource counters for dead threads in the group,
* and for reaped dead child processes forked by this group.
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
*/
seqlock_t stats_lock;
u64 utime, stime, cutime, cstime;
u64 gtime;
u64 cgtime;
struct prev_cputime prev_cputime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
unsigned long maxrss, cmaxrss;
struct task_io_accounting ioac;
/*
* Cumulative ns of schedule CPU time fo dead threads in the
* group, not including a zombie group leader, (This only differs
* from jiffies_to_ns(utime + stime) if sched_clock uses something
* other than jiffies.)
*/
unsigned long long sum_sched_runtime;
/*
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
* to get both rlim_cur and rlim_max atomically, and either one
* alone is a single word that can safely be read normally.
* getrlimit/setrlimit use task_lock(current->group_leader) to
* protect this instead of the siglock, because they really
* have no need to disable irqs.
*/
struct rlimit rlim[RLIM_NLIMITS];
#ifdef CONFIG_BSD_PROCESS_ACCT
struct pacct_struct pacct; /* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
struct taskstats *stats;
#endif
#ifdef CONFIG_AUDIT
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
/*
* Thread is the potential origin of an oom condition; kill first on
* oom
*/
bool oom_flag_origin;
short oom_score_adj; /* OOM kill score adjustment */
short oom_score_adj_min; /* OOM kill score adjustment min value.
* Only settable by CAP_SYS_RESOURCE. */
struct mm_struct *oom_mm; /* recorded mm when the thread group got
* killed by the oom killer */
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
* (notably. ptrace)
* Deprecated do not use in new code.
* Use exec_update_lock instead.
*/
struct rw_semaphore exec_update_lock; /* Held while task_struct is
* being updated during exec,
* and may have inconsistent
* permissions.
*/
} __randomize_layout;
/*
* Bits in flags field of signal_struct.
*/
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */
/*
* Pending notifications to parent.
*/
#define SIGNAL_CLD_STOPPED 0x00000010
#define SIGNAL_CLD_CONTINUED 0x00000020
#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */
#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
SIGNAL_STOP_CONTINUED)
static inline void signal_set_stop_flags(struct signal_struct *sig,
unsigned int flags)
{
WARN_ON(sig->flags & SIGNAL_GROUP_EXIT);
sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
}
extern void flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type);
static inline int kernel_dequeue_signal(void)
{
struct task_struct *task = current;
kernel_siginfo_t __info;
enum pid_type __type;
int ret;
spin_lock_irq(&task->sighand->siglock);
ret = dequeue_signal(&task->blocked, &__info, &__type);
spin_unlock_irq(&task->sighand->siglock);
return ret;
}
static inline void kernel_signal_stop(void)
{
spin_lock_irq(¤t->sighand->siglock);
if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
current->jobctl |= JOBCTL_STOPPED;
set_special_state(TASK_STOPPED);
}
spin_unlock_irq(¤t->sighand->siglock);
schedule();
}
int force_sig_fault_to_task(int sig, int code, void __user *addr,
struct task_struct *t);
int force_sig_fault(int sig, int code, void __user *addr);
int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t);
int force_sig_mceerr(int code, void __user *, short);
int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper);
int force_sig_pkuerr(void __user *addr, u32 pkey);
int send_sig_perf(void __user *addr, u32 type, u64 sig_data);
int force_sig_ptrace_errno_trap(int errno, void __user *addr);
int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno);
int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno,
struct task_struct *t);
int force_sig_seccomp(int syscall, int reason, bool force_coredump);
extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *);
extern void force_sigsegv(int sig);
extern int force_sig_info(struct kernel_siginfo *);
extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid);
extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *,
const struct cred *);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern __must_check bool do_notify_parent(struct task_struct *, int);
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int);
extern void force_fatal_sig(int);
extern void force_exit_sig(int);
extern int send_sig(int, struct task_struct *, int);
extern int zap_other_threads(struct task_struct *p);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
static inline void clear_notify_signal(void)
{
clear_thread_flag(TIF_NOTIFY_SIGNAL);
smp_mb__after_atomic();
}
/*
* Returns 'true' if kick_process() is needed to force a transition from
* user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work.
*/
static inline bool __set_notify_signal(struct task_struct *task)
{
return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE);
}
/*
* Called to break out of interruptible wait loops, and enter the
* exit_to_user_mode_loop().
*/
static inline void set_notify_signal(struct task_struct *task)
{
if (__set_notify_signal(task)) kick_process(task);
}
static inline int restart_syscall(void)
{
set_tsk_thread_flag(current, TIF_SIGPENDING);
return -ERESTARTNOINTR;
}
static inline int task_sigpending(struct task_struct *p)
{
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
static inline int signal_pending(struct task_struct *p)
{
/*
* TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
* behavior in terms of ensuring that we break out of wait loops
* so that notify signal callbacks can be processed.
*/
if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
return 1;
return task_sigpending(p);
}
static inline int __fatal_signal_pending(struct task_struct *p)
{
return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
static inline int fatal_signal_pending(struct task_struct *p)
{
return task_sigpending(p) && __fatal_signal_pending(p);
}
static inline int signal_pending_state(unsigned int state, struct task_struct *p)
{
if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
return 0;
if (!signal_pending(p))
return 0;
return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
}
/*
* This should only be used in fault handlers to decide whether we
* should stop the current fault routine to handle the signals
* instead, especially with the case where we've got interrupted with
* a VM_FAULT_RETRY.
*/
static inline bool fault_signal_pending(vm_fault_t fault_flags,
struct pt_regs *regs)
{ return unlikely((fault_flags & VM_FAULT_RETRY) &&
(fatal_signal_pending(current) ||
(user_mode(regs) && signal_pending(current))));
}
/*
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
* This is required every time the blocked sigset_t changes.
* callers must hold sighand->siglock.
*/
extern void recalc_sigpending(void);
extern void calculate_sigpending(void);
extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
static inline void signal_wake_up(struct task_struct *t, bool fatal)
{
unsigned int state = 0;
if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
state = TASK_WAKEKILL | __TASK_TRACED;
}
signal_wake_up_state(t, state);
}
static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
{
unsigned int state = 0;
if (resume) {
t->jobctl &= ~JOBCTL_TRACED;
state = __TASK_TRACED;
}
signal_wake_up_state(t, state);
}
void task_join_group_stop(struct task_struct *task);
#ifdef TIF_RESTORE_SIGMASK
/*
* Legacy restore_sigmask accessors. These are inefficient on
* SMP architectures because they require atomic operations.
*/
/**
* set_restore_sigmask() - make sure saved_sigmask processing gets done
*
* This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
* will run before returning to user mode, to process the flag. For
* all callers, TIF_SIGPENDING is already set or it's no harm to set
* it. TIF_RESTORE_SIGMASK need not be in the set of bits that the
* arch code will notice on return to user mode, in case those bits
* are scarce. We set TIF_SIGPENDING here to ensure that the arch
* signal code always gets run when TIF_RESTORE_SIGMASK is set.
*/
static inline void set_restore_sigmask(void)
{
set_thread_flag(TIF_RESTORE_SIGMASK);
}
static inline void clear_tsk_restore_sigmask(struct task_struct *task)
{
clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK);
}
static inline void clear_restore_sigmask(void)
{
clear_thread_flag(TIF_RESTORE_SIGMASK);
}
static inline bool test_tsk_restore_sigmask(struct task_struct *task)
{
return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK);
}
static inline bool test_restore_sigmask(void)
{
return test_thread_flag(TIF_RESTORE_SIGMASK);
}
static inline bool test_and_clear_restore_sigmask(void)
{
return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
}
#else /* TIF_RESTORE_SIGMASK */
/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
static inline void set_restore_sigmask(void)
{
current->restore_sigmask = true;
}
static inline void clear_tsk_restore_sigmask(struct task_struct *task)
{
task->restore_sigmask = false;
}
static inline void clear_restore_sigmask(void)
{
current->restore_sigmask = false;
}
static inline bool test_restore_sigmask(void)
{
return current->restore_sigmask;
}
static inline bool test_tsk_restore_sigmask(struct task_struct *task)
{
return task->restore_sigmask;
}
static inline bool test_and_clear_restore_sigmask(void)
{
if (!current->restore_sigmask)
return false;
current->restore_sigmask = false;
return true;
}
#endif
static inline void restore_saved_sigmask(void)
{
if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask);
}
extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
static inline void restore_saved_sigmask_unless(bool interrupted)
{
if (interrupted)
WARN_ON(!signal_pending(current));
else
restore_saved_sigmask();
}
static inline sigset_t *sigmask_to_save(void)
{
sigset_t *res = ¤t->blocked;
if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask;
return res;
}
static inline int kill_cad_pid(int sig, int priv)
{
return kill_pid(cad_pid, sig, priv);
}
/* These can be the second arg to send_sig_info/send_group_sig_info. */
#define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0)
#define SEND_SIG_PRIV ((struct kernel_siginfo *) 1)
static inline int __on_sig_stack(unsigned long sp)
{
#ifdef CONFIG_STACK_GROWSUP
return sp >= current->sas_ss_sp &&
sp - current->sas_ss_sp < current->sas_ss_size;
#else
return sp > current->sas_ss_sp &&
sp - current->sas_ss_sp <= current->sas_ss_size;
#endif
}
/*
* True if we are on the alternate signal stack.
*/
static inline int on_sig_stack(unsigned long sp)
{
/*
* If the signal stack is SS_AUTODISARM then, by construction, we
* can't be on the signal stack unless user code deliberately set
* SS_AUTODISARM when we were already on it.
*
* This improves reliability: if user state gets corrupted such that
* the stack pointer points very close to the end of the signal stack,
* then this check will enable the signal to be handled anyway.
*/
if (current->sas_ss_flags & SS_AUTODISARM)
return 0;
return __on_sig_stack(sp);
}
static inline int sas_ss_flags(unsigned long sp)
{
if (!current->sas_ss_size)
return SS_DISABLE;
return on_sig_stack(sp) ? SS_ONSTACK : 0;
}
static inline void sas_ss_reset(struct task_struct *p)
{
p->sas_ss_sp = 0;
p->sas_ss_size = 0;
p->sas_ss_flags = SS_DISABLE;
}
static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
{
if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
#ifdef CONFIG_STACK_GROWSUP
return current->sas_ss_sp;
#else
return current->sas_ss_sp + current->sas_ss_size;
#endif
return sp;
}
extern void __cleanup_sighand(struct sighand_struct *);
extern void flush_itimer_signals(void);
#define tasklist_empty() \
list_empty(&init_task.tasks)
#define next_task(p) \
list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
extern bool current_is_single_threaded(void);
/*
* Without tasklist/siglock it is only rcu-safe if g can't exit/exec,
* otherwise next_thread(t) will never reach g after list_del_rcu(g).
*/
#define while_each_thread(g, t) \
while ((t = next_thread(t)) != g)
#define for_other_threads(p, t) \
for (t = p; (t = next_thread(t)) != p; )
#define __for_each_thread(signal, t) \
list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \
lockdep_is_held(&tasklist_lock))
#define for_each_thread(p, t) \
__for_each_thread((p)->signal, t)
/* Careful: this is a double loop, 'break' won't work as expected. */
#define for_each_process_thread(p, t) \
for_each_process(p) for_each_thread(p, t)
typedef int (*proc_visitor)(struct task_struct *p, void *data);
void walk_process_tree(struct task_struct *top, proc_visitor, void *);
static inline
struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
if (type == PIDTYPE_PID)
pid = task_pid(task);
else
pid = task->signal->pids[type];
return pid;
}
static inline struct pid *task_tgid(struct task_struct *task)
{
return task->signal->pids[PIDTYPE_TGID];
}
/*
* Without tasklist or RCU lock it is not safe to dereference
* the result of task_pgrp/task_session even if task == current,
* we can race with another thread doing sys_setsid/sys_setpgid.
*/
static inline struct pid *task_pgrp(struct task_struct *task)
{
return task->signal->pids[PIDTYPE_PGID];
}
static inline struct pid *task_session(struct task_struct *task)
{
return task->signal->pids[PIDTYPE_SID];
}
static inline int get_nr_threads(struct task_struct *task)
{
return task->signal->nr_threads;
}
static inline bool thread_group_leader(struct task_struct *p)
{
return p->exit_signal >= 0;
}
static inline
bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
return p1->signal == p2->signal;
}
/*
* returns NULL if p is the last thread in the thread group
*/
static inline struct task_struct *__next_thread(struct task_struct *p)
{
return list_next_or_null_rcu(&p->signal->thread_head,
&p->thread_node,
struct task_struct,
thread_node);
}
static inline struct task_struct *next_thread(struct task_struct *p)
{
return __next_thread(p) ?: p->group_leader;
}
static inline int thread_group_empty(struct task_struct *p)
{
return thread_group_leader(p) &&
list_is_last(&p->thread_node, &p->signal->thread_head);
}
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
unsigned long *flags);
static inline struct sighand_struct *lock_task_sighand(struct task_struct *task,
unsigned long *flags)
{
struct sighand_struct *ret;
ret = __lock_task_sighand(task, flags);
(void)__cond_lock(&task->sighand->siglock, ret);
return ret;
}
static inline void unlock_task_sighand(struct task_struct *task,
unsigned long *flags)
{
spin_unlock_irqrestore(&task->sighand->siglock, *flags);
}
#ifdef CONFIG_LOCKDEP
extern void lockdep_assert_task_sighand_held(struct task_struct *task);
#else
static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { }
#endif
static inline unsigned long task_rlimit(const struct task_struct *task,
unsigned int limit)
{
return READ_ONCE(task->signal->rlim[limit].rlim_cur);
}
static inline unsigned long task_rlimit_max(const struct task_struct *task,
unsigned int limit)
{
return READ_ONCE(task->signal->rlim[limit].rlim_max);
}
static inline unsigned long rlimit(unsigned int limit)
{
return task_rlimit(current, limit);
}
static inline unsigned long rlimit_max(unsigned int limit)
{
return task_rlimit_max(current, limit);
}
#endif /* _LINUX_SCHED_SIGNAL_H */
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
* Copyright (C) 2005-2006, Thomas Gleixner, Russell King
*
* This file contains the interrupt descriptor management code. Detailed
* information is available in Documentation/core-api/genericirq.rst
*
*/
#include <linux/irq.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/maple_tree.h>
#include <linux/irqdomain.h>
#include <linux/sysfs.h>
#include <linux/string_choices.h>
#include "internals.h"
/*
* lockdep: we want to handle all irq_desc locks as a single lock-class:
*/
static struct lock_class_key irq_desc_lock_class;
#if defined(CONFIG_SMP)
static int __init irq_affinity_setup(char *str)
{
alloc_bootmem_cpumask_var(&irq_default_affinity);
cpulist_parse(str, irq_default_affinity);
/*
* Set at least the boot cpu. We don't want to end up with
* bugreports caused by random commandline masks
*/
cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
return 1;
}
__setup("irqaffinity=", irq_affinity_setup);
static void __init init_irq_default_affinity(void)
{
if (!cpumask_available(irq_default_affinity))
zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
if (cpumask_empty(irq_default_affinity))
cpumask_setall(irq_default_affinity);
}
#else
static void __init init_irq_default_affinity(void)
{
}
#endif
#ifdef CONFIG_SMP
static int alloc_masks(struct irq_desc *desc, int node)
{
if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity,
GFP_KERNEL, node))
return -ENOMEM;
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity,
GFP_KERNEL, node)) {
free_cpumask_var(desc->irq_common_data.affinity);
return -ENOMEM;
}
#endif
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) {
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
free_cpumask_var(desc->irq_common_data.effective_affinity);
#endif
free_cpumask_var(desc->irq_common_data.affinity);
return -ENOMEM;
}
#endif
return 0;
}
static void desc_smp_init(struct irq_desc *desc, int node,
const struct cpumask *affinity)
{
if (!affinity)
affinity = irq_default_affinity;
cpumask_copy(desc->irq_common_data.affinity, affinity);
#ifdef CONFIG_GENERIC_PENDING_IRQ
cpumask_clear(desc->pending_mask);
#endif
#ifdef CONFIG_NUMA
desc->irq_common_data.node = node;
#endif
}
static void free_masks(struct irq_desc *desc)
{
#ifdef CONFIG_GENERIC_PENDING_IRQ
free_cpumask_var(desc->pending_mask);
#endif
free_cpumask_var(desc->irq_common_data.affinity);
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
free_cpumask_var(desc->irq_common_data.effective_affinity);
#endif
}
#else
static inline int
alloc_masks(struct irq_desc *desc, int node) { return 0; }
static inline void
desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
static inline void free_masks(struct irq_desc *desc) { }
#endif
static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
const struct cpumask *affinity, struct module *owner)
{
int cpu;
desc->irq_common_data.handler_data = NULL;
desc->irq_common_data.msi_desc = NULL;
desc->irq_data.common = &desc->irq_common_data;
desc->irq_data.irq = irq;
desc->irq_data.chip = &no_irq_chip;
desc->irq_data.chip_data = NULL;
irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED);
irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
desc->handle_irq = handle_bad_irq;
desc->depth = 1;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
desc->tot_count = 0;
desc->name = NULL;
desc->owner = owner;
for_each_possible_cpu(cpu)
*per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { };
desc_smp_init(desc, node, affinity);
}
static unsigned int nr_irqs = NR_IRQS;
/**
* irq_get_nr_irqs() - Number of interrupts supported by the system.
*/
unsigned int irq_get_nr_irqs(void)
{
return nr_irqs;
}
EXPORT_SYMBOL_GPL(irq_get_nr_irqs);
/**
* irq_set_nr_irqs() - Set the number of interrupts supported by the system.
* @nr: New number of interrupts.
*
* Return: @nr.
*/
unsigned int irq_set_nr_irqs(unsigned int nr)
{
nr_irqs = nr;
return nr;
}
EXPORT_SYMBOL_GPL(irq_set_nr_irqs);
static DEFINE_MUTEX(sparse_irq_lock);
static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs,
MT_FLAGS_ALLOC_RANGE |
MT_FLAGS_LOCK_EXTERN |
MT_FLAGS_USE_RCU,
sparse_irq_lock);
static int irq_find_free_area(unsigned int from, unsigned int cnt)
{
MA_STATE(mas, &sparse_irqs, 0, 0);
if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt))
return -ENOSPC;
return mas.index;
}
static unsigned int irq_find_at_or_after(unsigned int offset)
{
unsigned long index = offset;
struct irq_desc *desc;
guard(rcu)();
desc = mt_find(&sparse_irqs, &index, nr_irqs);
return desc ? irq_desc_get_irq(desc) : nr_irqs;
}
static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
{
MA_STATE(mas, &sparse_irqs, irq, irq);
WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0);
}
static void delete_irq_desc(unsigned int irq)
{
MA_STATE(mas, &sparse_irqs, irq, irq);
mas_erase(&mas);
}
#ifdef CONFIG_SPARSE_IRQ
static const struct kobj_type irq_kobj_type;
#endif
static int init_desc(struct irq_desc *desc, int irq, int node,
unsigned int flags,
const struct cpumask *affinity,
struct module *owner)
{
desc->kstat_irqs = alloc_percpu(struct irqstat);
if (!desc->kstat_irqs)
return -ENOMEM;
if (alloc_masks(desc, node)) {
free_percpu(desc->kstat_irqs);
return -ENOMEM;
}
raw_spin_lock_init(&desc->lock);
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
mutex_init(&desc->request_mutex);
init_waitqueue_head(&desc->wait_for_threads);
desc_set_defaults(irq, desc, node, affinity, owner);
irqd_set(&desc->irq_data, flags);
irq_resend_init(desc);
#ifdef CONFIG_SPARSE_IRQ
kobject_init(&desc->kobj, &irq_kobj_type);
init_rcu_head(&desc->rcu);
#endif
return 0;
}
#ifdef CONFIG_SPARSE_IRQ
static void irq_kobj_release(struct kobject *kobj);
#ifdef CONFIG_SYSFS
static struct kobject *irq_kobj_base;
#define IRQ_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
static ssize_t per_cpu_count_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
char *p = "";
int cpu;
for_each_possible_cpu(cpu) {
unsigned int c = irq_desc_kstat_cpu(desc, cpu);
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
p = ",";
}
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
return ret;
}
IRQ_ATTR_RO(per_cpu_count);
static ssize_t chip_name_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
raw_spin_lock_irq(&desc->lock);
if (desc->irq_data.chip && desc->irq_data.chip->name) {
ret = scnprintf(buf, PAGE_SIZE, "%s\n",
desc->irq_data.chip->name);
}
raw_spin_unlock_irq(&desc->lock);
return ret;
}
IRQ_ATTR_RO(chip_name);
static ssize_t hwirq_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
raw_spin_lock_irq(&desc->lock);
if (desc->irq_data.domain)
ret = sprintf(buf, "%lu\n", desc->irq_data.hwirq);
raw_spin_unlock_irq(&desc->lock);
return ret;
}
IRQ_ATTR_RO(hwirq);
static ssize_t type_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
raw_spin_lock_irq(&desc->lock);
ret = sprintf(buf, "%s\n",
irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
raw_spin_unlock_irq(&desc->lock);
return ret;
}
IRQ_ATTR_RO(type);
static ssize_t wakeup_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
raw_spin_lock_irq(&desc->lock);
ret = sprintf(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data)));
raw_spin_unlock_irq(&desc->lock);
return ret;
}
IRQ_ATTR_RO(wakeup);
static ssize_t name_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
ssize_t ret = 0;
raw_spin_lock_irq(&desc->lock);
if (desc->name)
ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name);
raw_spin_unlock_irq(&desc->lock);
return ret;
}
IRQ_ATTR_RO(name);
static ssize_t actions_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
struct irqaction *action;
ssize_t ret = 0;
char *p = "";
raw_spin_lock_irq(&desc->lock);
for_each_action_of_desc(desc, action) {
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
p, action->name);
p = ",";
}
raw_spin_unlock_irq(&desc->lock);
if (ret)
ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
return ret;
}
IRQ_ATTR_RO(actions);
static struct attribute *irq_attrs[] = {
&per_cpu_count_attr.attr,
&chip_name_attr.attr,
&hwirq_attr.attr,
&type_attr.attr,
&wakeup_attr.attr,
&name_attr.attr,
&actions_attr.attr,
NULL
};
ATTRIBUTE_GROUPS(irq);
static const struct kobj_type irq_kobj_type = {
.release = irq_kobj_release,
.sysfs_ops = &kobj_sysfs_ops,
.default_groups = irq_groups,
};
static void irq_sysfs_add(int irq, struct irq_desc *desc)
{
if (irq_kobj_base) {
/*
* Continue even in case of failure as this is nothing
* crucial and failures in the late irq_sysfs_init()
* cannot be rolled back.
*/
if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq))
pr_warn("Failed to add kobject for irq %d\n", irq);
else
desc->istate |= IRQS_SYSFS;
}
}
static void irq_sysfs_del(struct irq_desc *desc)
{
/*
* Only invoke kobject_del() when kobject_add() was successfully
* invoked for the descriptor. This covers both early boot, where
* sysfs is not initialized yet, and the case of a failed
* kobject_add() invocation.
*/
if (desc->istate & IRQS_SYSFS)
kobject_del(&desc->kobj);
}
static int __init irq_sysfs_init(void)
{
struct irq_desc *desc;
int irq;
/* Prevent concurrent irq alloc/free */
irq_lock_sparse();
irq_kobj_base = kobject_create_and_add("irq", kernel_kobj);
if (!irq_kobj_base) {
irq_unlock_sparse();
return -ENOMEM;
}
/* Add the already allocated interrupts */
for_each_irq_desc(irq, desc)
irq_sysfs_add(irq, desc);
irq_unlock_sparse();
return 0;
}
postcore_initcall(irq_sysfs_init);
#else /* !CONFIG_SYSFS */
static const struct kobj_type irq_kobj_type = {
.release = irq_kobj_release,
};
static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
static void irq_sysfs_del(struct irq_desc *desc) {}
#endif /* CONFIG_SYSFS */
struct irq_desc *irq_to_desc(unsigned int irq)
{
return mtree_load(&sparse_irqs, irq);
}
#ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE
EXPORT_SYMBOL_GPL(irq_to_desc);
#endif
void irq_lock_sparse(void)
{
mutex_lock(&sparse_irq_lock);
}
void irq_unlock_sparse(void)
{
mutex_unlock(&sparse_irq_lock);
}
static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
const struct cpumask *affinity,
struct module *owner)
{
struct irq_desc *desc;
int ret;
desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node);
if (!desc)
return NULL;
ret = init_desc(desc, irq, node, flags, affinity, owner);
if (unlikely(ret)) {
kfree(desc);
return NULL;
}
return desc;
}
static void irq_kobj_release(struct kobject *kobj)
{
struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
free_masks(desc);
free_percpu(desc->kstat_irqs);
kfree(desc);
}
static void delayed_free_desc(struct rcu_head *rhp)
{
struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
kobject_put(&desc->kobj);
}
static void free_desc(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
irq_remove_debugfs_entry(desc);
unregister_irq_proc(irq, desc);
/*
* sparse_irq_lock protects also show_interrupts() and
* kstat_irq_usr(). Once we deleted the descriptor from the
* sparse tree we can free it. Access in proc will fail to
* lookup the descriptor.
*
* The sysfs entry must be serialized against a concurrent
* irq_sysfs_init() as well.
*/
irq_sysfs_del(desc);
delete_irq_desc(irq);
/*
* We free the descriptor, masks and stat fields via RCU. That
* allows demultiplex interrupts to do rcu based management of
* the child interrupts.
* This also allows us to use rcu in kstat_irqs_usr().
*/
call_rcu(&desc->rcu, delayed_free_desc);
}
static int alloc_descs(unsigned int start, unsigned int cnt, int node,
const struct irq_affinity_desc *affinity,
struct module *owner)
{
struct irq_desc *desc;
int i;
/* Validate affinity mask(s) */
if (affinity) {
for (i = 0; i < cnt; i++) {
if (cpumask_empty(&affinity[i].mask))
return -EINVAL;
}
}
for (i = 0; i < cnt; i++) {
const struct cpumask *mask = NULL;
unsigned int flags = 0;
if (affinity) {
if (affinity->is_managed) {
flags = IRQD_AFFINITY_MANAGED |
IRQD_MANAGED_SHUTDOWN;
}
flags |= IRQD_AFFINITY_SET;
mask = &affinity->mask;
node = cpu_to_node(cpumask_first(mask));
affinity++;
}
desc = alloc_desc(start + i, node, flags, mask, owner);
if (!desc)
goto err;
irq_insert_desc(start + i, desc);
irq_sysfs_add(start + i, desc);
irq_add_debugfs_entry(start + i, desc);
}
return start;
err:
for (i--; i >= 0; i--)
free_desc(start + i);
return -ENOMEM;
}
static int irq_expand_nr_irqs(unsigned int nr)
{
if (nr > MAX_SPARSE_IRQS)
return -ENOMEM;
nr_irqs = nr;
return 0;
}
int __init early_irq_init(void)
{
int i, initcnt, node = first_online_node;
struct irq_desc *desc;
init_irq_default_affinity();
/* Let arch update nr_irqs and return the nr of preallocated irqs */
initcnt = arch_probe_nr_irqs();
printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n",
NR_IRQS, nr_irqs, initcnt);
if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS))
nr_irqs = MAX_SPARSE_IRQS;
if (WARN_ON(initcnt > MAX_SPARSE_IRQS))
initcnt = MAX_SPARSE_IRQS;
if (initcnt > nr_irqs)
nr_irqs = initcnt;
for (i = 0; i < initcnt; i++) {
desc = alloc_desc(i, node, 0, NULL, NULL);
irq_insert_desc(i, desc);
}
return arch_early_irq_init();
}
#else /* !CONFIG_SPARSE_IRQ */
struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
[0 ... NR_IRQS-1] = {
.handle_irq = handle_bad_irq,
.depth = 1,
.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
}
};
int __init early_irq_init(void)
{
int count, i, node = first_online_node;
int ret;
init_irq_default_affinity();
printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS);
count = ARRAY_SIZE(irq_desc);
for (i = 0; i < count; i++) {
ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL);
if (unlikely(ret))
goto __free_desc_res;
}
return arch_early_irq_init();
__free_desc_res:
while (--i >= 0) {
free_masks(irq_desc + i);
free_percpu(irq_desc[i].kstat_irqs);
}
return ret;
}
struct irq_desc *irq_to_desc(unsigned int irq)
{
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}
EXPORT_SYMBOL(irq_to_desc);
static void free_desc(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
raw_spin_lock_irqsave(&desc->lock, flags);
desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
raw_spin_unlock_irqrestore(&desc->lock, flags);
delete_irq_desc(irq);
}
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
const struct irq_affinity_desc *affinity,
struct module *owner)
{
u32 i;
for (i = 0; i < cnt; i++) {
struct irq_desc *desc = irq_to_desc(start + i);
desc->owner = owner;
irq_insert_desc(start + i, desc);
}
return start;
}
static int irq_expand_nr_irqs(unsigned int nr)
{
return -ENOMEM;
}
void irq_mark_irq(unsigned int irq)
{
mutex_lock(&sparse_irq_lock);
irq_insert_desc(irq, irq_desc + irq);
mutex_unlock(&sparse_irq_lock);
}
#ifdef CONFIG_GENERIC_IRQ_LEGACY
void irq_init_desc(unsigned int irq)
{
free_desc(irq);
}
#endif
#endif /* !CONFIG_SPARSE_IRQ */
int handle_irq_desc(struct irq_desc *desc)
{
struct irq_data *data;
if (!desc)
return -EINVAL;
data = irq_desc_get_irq_data(desc);
if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data)))
return -EPERM;
generic_handle_irq_desc(desc);
return 0;
}
/**
* generic_handle_irq - Invoke the handler for a particular irq
* @irq: The irq number to handle
*
* Returns: 0 on success, or -EINVAL if conversion has failed
*
* This function must be called from an IRQ context with irq regs
* initialized.
*/
int generic_handle_irq(unsigned int irq)
{
return handle_irq_desc(irq_to_desc(irq));
}
EXPORT_SYMBOL_GPL(generic_handle_irq);
/**
* generic_handle_irq_safe - Invoke the handler for a particular irq from any
* context.
* @irq: The irq number to handle
*
* Returns: 0 on success, a negative value on error.
*
* This function can be called from any context (IRQ or process context). It
* will report an error if not invoked from IRQ context and the irq has been
* marked to enforce IRQ-context only.
*/
int generic_handle_irq_safe(unsigned int irq)
{
unsigned long flags;
int ret;
local_irq_save(flags);
ret = handle_irq_desc(irq_to_desc(irq));
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL_GPL(generic_handle_irq_safe);
#ifdef CONFIG_IRQ_DOMAIN
/**
* generic_handle_domain_irq - Invoke the handler for a HW irq belonging
* to a domain.
* @domain: The domain where to perform the lookup
* @hwirq: The HW irq number to convert to a logical one
*
* Returns: 0 on success, or -EINVAL if conversion has failed
*
* This function must be called from an IRQ context with irq regs
* initialized.
*/
int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq)
{
return handle_irq_desc(irq_resolve_mapping(domain, hwirq));
}
EXPORT_SYMBOL_GPL(generic_handle_domain_irq);
/**
* generic_handle_irq_safe - Invoke the handler for a HW irq belonging
* to a domain from any context.
* @domain: The domain where to perform the lookup
* @hwirq: The HW irq number to convert to a logical one
*
* Returns: 0 on success, a negative value on error.
*
* This function can be called from any context (IRQ or process
* context). If the interrupt is marked as 'enforce IRQ-context only' then
* the function must be invoked from hard interrupt context.
*/
int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq)
{
unsigned long flags;
int ret;
local_irq_save(flags);
ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq));
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe);
/**
* generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging
* to a domain.
* @domain: The domain where to perform the lookup
* @hwirq: The HW irq number to convert to a logical one
*
* Returns: 0 on success, or -EINVAL if conversion has failed
*
* This function must be called from an NMI context with irq regs
* initialized.
**/
int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq)
{
WARN_ON_ONCE(!in_nmi());
return handle_irq_desc(irq_resolve_mapping(domain, hwirq));
}
#endif
/* Dynamic interrupt handling */
/**
* irq_free_descs - free irq descriptors
* @from: Start of descriptor range
* @cnt: Number of consecutive irqs to free
*/
void irq_free_descs(unsigned int from, unsigned int cnt)
{
int i;
if (from >= nr_irqs || (from + cnt) > nr_irqs)
return;
mutex_lock(&sparse_irq_lock);
for (i = 0; i < cnt; i++)
free_desc(from + i);
mutex_unlock(&sparse_irq_lock);
}
EXPORT_SYMBOL_GPL(irq_free_descs);
/**
* __irq_alloc_descs - allocate and initialize a range of irq descriptors
* @irq: Allocate for specific irq number if irq >= 0
* @from: Start the search from this irq number
* @cnt: Number of consecutive irqs to allocate.
* @node: Preferred node on which the irq descriptor should be allocated
* @owner: Owning module (can be NULL)
* @affinity: Optional pointer to an affinity mask array of size @cnt which
* hints where the irq descriptors should be allocated and which
* default affinities to use
*
* Returns the first irq number or error code
*/
int __ref
__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
struct module *owner, const struct irq_affinity_desc *affinity)
{
int start, ret;
if (!cnt)
return -EINVAL;
if (irq >= 0) {
if (from > irq)
return -EINVAL;
from = irq;
} else {
/*
* For interrupts which are freely allocated the
* architecture can force a lower bound to the @from
* argument. x86 uses this to exclude the GSI space.
*/
from = arch_dynirq_lower_bound(from);
}
mutex_lock(&sparse_irq_lock);
start = irq_find_free_area(from, cnt);
ret = -EEXIST;
if (irq >=0 && start != irq)
goto unlock;
if (start + cnt > nr_irqs) {
ret = irq_expand_nr_irqs(start + cnt);
if (ret)
goto unlock;
}
ret = alloc_descs(start, cnt, node, affinity, owner);
unlock:
mutex_unlock(&sparse_irq_lock);
return ret;
}
EXPORT_SYMBOL_GPL(__irq_alloc_descs);
/**
* irq_get_next_irq - get next allocated irq number
* @offset: where to start the search
*
* Returns next irq number after offset or nr_irqs if none is found.
*/
unsigned int irq_get_next_irq(unsigned int offset)
{
return irq_find_at_or_after(offset);
}
struct irq_desc *
__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
unsigned int check)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc) { if (check & _IRQ_DESC_CHECK) { if ((check & _IRQ_DESC_PERCPU) &&
!irq_settings_is_per_cpu_devid(desc))
return NULL;
if (!(check & _IRQ_DESC_PERCPU) &&
irq_settings_is_per_cpu_devid(desc))
return NULL;
}
if (bus) chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, *flags);
}
return desc;
}
void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
__releases(&desc->lock)
{
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (bus) chip_bus_sync_unlock(desc);
}
int irq_set_percpu_devid_partition(unsigned int irq,
const struct cpumask *affinity)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || desc->percpu_enabled)
return -EINVAL;
desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL);
if (!desc->percpu_enabled)
return -ENOMEM;
desc->percpu_affinity = affinity ? : cpu_possible_mask;
irq_set_percpu_devid_flags(irq);
return 0;
}
int irq_set_percpu_devid(unsigned int irq)
{
return irq_set_percpu_devid_partition(irq, NULL);
}
int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !desc->percpu_enabled)
return -EINVAL;
if (affinity)
cpumask_copy(affinity, desc->percpu_affinity);
return 0;
}
EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition);
void kstat_incr_irq_this_cpu(unsigned int irq)
{
kstat_incr_irqs_this_cpu(irq_to_desc(irq));
}
/**
* kstat_irqs_cpu - Get the statistics for an interrupt on a cpu
* @irq: The interrupt number
* @cpu: The cpu number
*
* Returns the sum of interrupt counts on @cpu since boot for
* @irq. The caller must ensure that the interrupt is not removed
* concurrently.
*/
unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
{
struct irq_desc *desc = irq_to_desc(irq);
return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
}
static unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask)
{
unsigned int sum = 0;
int cpu;
if (!irq_settings_is_per_cpu_devid(desc) &&
!irq_settings_is_per_cpu(desc) &&
!irq_is_nmi(desc))
return data_race(desc->tot_count);
for_each_cpu(cpu, cpumask)
sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu));
return sum;
}
static unsigned int kstat_irqs(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !desc->kstat_irqs)
return 0;
return kstat_irqs_desc(desc, cpu_possible_mask);
}
#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
void kstat_snapshot_irqs(void)
{
struct irq_desc *desc;
unsigned int irq;
for_each_irq_desc(irq, desc) {
if (!desc->kstat_irqs)
continue;
this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt));
}
}
unsigned int kstat_get_irq_since_snapshot(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !desc->kstat_irqs)
return 0;
return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref);
}
#endif
/**
* kstat_irqs_usr - Get the statistics for an interrupt from thread context
* @irq: The interrupt number
*
* Returns the sum of interrupt counts on all cpus since boot for @irq.
*
* It uses rcu to protect the access since a concurrent removal of an
* interrupt descriptor is observing an rcu grace period before
* delayed_free_desc()/irq_kobj_release().
*/
unsigned int kstat_irqs_usr(unsigned int irq)
{
unsigned int sum;
rcu_read_lock();
sum = kstat_irqs(irq);
rcu_read_unlock();
return sum;
}
#ifdef CONFIG_LOCKDEP
void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
struct lock_class_key *request_class)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc) {
lockdep_set_class(&desc->lock, lock_class);
lockdep_set_class(&desc->request_mutex, request_class);
}
}
EXPORT_SYMBOL_GPL(__irq_set_lockdep_class);
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2023 ARM Ltd.
*/
#include <linux/mm.h>
#include <linux/efi.h>
#include <linux/export.h>
#include <asm/tlbflush.h>
static inline bool mm_is_user(struct mm_struct *mm)
{
/*
* Don't attempt to apply the contig bit to kernel mappings, because
* dynamically adding/removing the contig bit can cause page faults.
* These racing faults are ok for user space, since they get serialized
* on the PTL. But kernel mappings can't tolerate faults.
*/
if (unlikely(mm_is_efi(mm)))
return false;
return mm != &init_mm;
}
static inline pte_t *contpte_align_down(pte_t *ptep)
{
return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES);
}
static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr)
{
/*
* Unfold any partially covered contpte block at the beginning and end
* of the range.
*/
if (ptep != contpte_align_down(ptep) || nr < CONT_PTES)
contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
if (ptep + nr != contpte_align_down(ptep + nr)) {
unsigned long last_addr = addr + PAGE_SIZE * (nr - 1);
pte_t *last_ptep = ptep + nr - 1;
contpte_try_unfold(mm, last_addr, last_ptep,
__ptep_get(last_ptep));
}
}
static void contpte_convert(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
unsigned long start_addr;
pte_t *start_ptep;
int i;
start_ptep = ptep = contpte_align_down(ptep);
start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
pte = pfn_pte(ALIGN_DOWN(pte_pfn(pte), CONT_PTES), pte_pgprot(pte));
for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) {
pte_t ptent = __ptep_get_and_clear(mm, addr, ptep);
if (pte_dirty(ptent))
pte = pte_mkdirty(pte);
if (pte_young(ptent))
pte = pte_mkyoung(pte);
}
__flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3);
__set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
}
void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
/*
* We have already checked that the virtual and pysical addresses are
* correctly aligned for a contpte mapping in contpte_try_fold() so the
* remaining checks are to ensure that the contpte range is fully
* covered by a single folio, and ensure that all the ptes are valid
* with contiguous PFNs and matching prots. We ignore the state of the
* access and dirty bits for the purpose of deciding if its a contiguous
* range; the folding process will generate a single contpte entry which
* has a single access and dirty bit. Those 2 bits are the logical OR of
* their respective bits in the constituent pte entries. In order to
* ensure the contpte range is covered by a single folio, we must
* recover the folio from the pfn, but special mappings don't have a
* folio backing them. Fortunately contpte_try_fold() already checked
* that the pte is not special - we never try to fold special mappings.
* Note we can't use vm_normal_page() for this since we don't have the
* vma.
*/
unsigned long folio_start, folio_end;
unsigned long cont_start, cont_end;
pte_t expected_pte, subpte;
struct folio *folio;
struct page *page;
unsigned long pfn;
pte_t *orig_ptep;
pgprot_t prot;
int i;
if (!mm_is_user(mm))
return;
page = pte_page(pte);
folio = page_folio(page);
folio_start = addr - (page - &folio->page) * PAGE_SIZE;
folio_end = folio_start + folio_nr_pages(folio) * PAGE_SIZE;
cont_start = ALIGN_DOWN(addr, CONT_PTE_SIZE);
cont_end = cont_start + CONT_PTE_SIZE;
if (folio_start > cont_start || folio_end < cont_end)
return;
pfn = ALIGN_DOWN(pte_pfn(pte), CONT_PTES);
prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
expected_pte = pfn_pte(pfn, prot);
orig_ptep = ptep;
ptep = contpte_align_down(ptep);
for (i = 0; i < CONT_PTES; i++) {
subpte = pte_mkold(pte_mkclean(__ptep_get(ptep)));
if (!pte_same(subpte, expected_pte))
return;
expected_pte = pte_advance_pfn(expected_pte, 1);
ptep++;
}
pte = pte_mkcont(pte);
contpte_convert(mm, addr, orig_ptep, pte);
}
EXPORT_SYMBOL_GPL(__contpte_try_fold);
void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
/*
* We have already checked that the ptes are contiguous in
* contpte_try_unfold(), so just check that the mm is user space.
*/
if (!mm_is_user(mm))
return;
pte = pte_mknoncont(pte);
contpte_convert(mm, addr, ptep, pte);
}
EXPORT_SYMBOL_GPL(__contpte_try_unfold);
pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
{
/*
* Gather access/dirty bits, which may be populated in any of the ptes
* of the contig range. We are guaranteed to be holding the PTL, so any
* contiguous range cannot be unfolded or otherwise modified under our
* feet.
*/
pte_t pte;
int i;
ptep = contpte_align_down(ptep);
for (i = 0; i < CONT_PTES; i++, ptep++) {
pte = __ptep_get(ptep);
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
if (pte_young(pte))
orig_pte = pte_mkyoung(orig_pte);
}
return orig_pte;
}
EXPORT_SYMBOL_GPL(contpte_ptep_get);
pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
{
/*
* The ptep_get_lockless() API requires us to read and return *orig_ptep
* so that it is self-consistent, without the PTL held, so we may be
* racing with other threads modifying the pte. Usually a READ_ONCE()
* would suffice, but for the contpte case, we also need to gather the
* access and dirty bits from across all ptes in the contiguous block,
* and we can't read all of those neighbouring ptes atomically, so any
* contiguous range may be unfolded/modified/refolded under our feet.
* Therefore we ensure we read a _consistent_ contpte range by checking
* that all ptes in the range are valid and have CONT_PTE set, that all
* pfns are contiguous and that all pgprots are the same (ignoring
* access/dirty). If we find a pte that is not consistent, then we must
* be racing with an update so start again. If the target pte does not
* have CONT_PTE set then that is considered consistent on its own
* because it is not part of a contpte range.
*/
pgprot_t orig_prot;
unsigned long pfn;
pte_t orig_pte;
pgprot_t prot;
pte_t *ptep;
pte_t pte;
int i;
retry:
orig_pte = __ptep_get(orig_ptep);
if (!pte_valid_cont(orig_pte))
return orig_pte;
orig_prot = pte_pgprot(pte_mkold(pte_mkclean(orig_pte)));
ptep = contpte_align_down(orig_ptep);
pfn = pte_pfn(orig_pte) - (orig_ptep - ptep);
for (i = 0; i < CONT_PTES; i++, ptep++, pfn++) {
pte = __ptep_get(ptep);
prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
if (!pte_valid_cont(pte) ||
pte_pfn(pte) != pfn ||
pgprot_val(prot) != pgprot_val(orig_prot))
goto retry;
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
if (pte_young(pte))
orig_pte = pte_mkyoung(orig_pte);
}
return orig_pte;
}
EXPORT_SYMBOL_GPL(contpte_ptep_get_lockless);
void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, unsigned int nr)
{
unsigned long next;
unsigned long end;
unsigned long pfn;
pgprot_t prot;
/*
* The set_ptes() spec guarantees that when nr > 1, the initial state of
* all ptes is not-present. Therefore we never need to unfold or
* otherwise invalidate a range before we set the new ptes.
* contpte_set_ptes() should never be called for nr < 2.
*/
VM_WARN_ON(nr == 1);
if (!mm_is_user(mm))
return __set_ptes(mm, addr, ptep, pte, nr);
end = addr + (nr << PAGE_SHIFT);
pfn = pte_pfn(pte);
prot = pte_pgprot(pte);
do {
next = pte_cont_addr_end(addr, end);
nr = (next - addr) >> PAGE_SHIFT;
pte = pfn_pte(pfn, prot);
if (((addr | next | (pfn << PAGE_SHIFT)) & ~CONT_PTE_MASK) == 0)
pte = pte_mkcont(pte);
else
pte = pte_mknoncont(pte);
__set_ptes(mm, addr, ptep, pte, nr);
addr = next;
ptep += nr;
pfn += nr;
} while (addr != end);
}
EXPORT_SYMBOL_GPL(contpte_set_ptes);
void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr, int full)
{
contpte_try_unfold_partial(mm, addr, ptep, nr);
__clear_full_ptes(mm, addr, ptep, nr, full);
}
EXPORT_SYMBOL_GPL(contpte_clear_full_ptes);
pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
unsigned long addr, pte_t *ptep,
unsigned int nr, int full)
{
contpte_try_unfold_partial(mm, addr, ptep, nr);
return __get_and_clear_full_ptes(mm, addr, ptep, nr, full);
}
EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes);
int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
/*
* ptep_clear_flush_young() technically requires us to clear the access
* flag for a _single_ pte. However, the core-mm code actually tracks
* access/dirty per folio, not per page. And since we only create a
* contig range when the range is covered by a single folio, we can get
* away with clearing young for the whole contig range here, so we avoid
* having to unfold.
*/
int young = 0;
int i;
ptep = contpte_align_down(ptep);
addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
young |= __ptep_test_and_clear_young(vma, addr, ptep);
return young;
}
EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young);
int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
int young;
young = contpte_ptep_test_and_clear_young(vma, addr, ptep);
if (young) {
/*
* See comment in __ptep_clear_flush_young(); same rationale for
* eliding the trailing DSB applies here.
*/
addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
__flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
PAGE_SIZE, true, 3);
}
return young;
}
EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young);
void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr)
{
/*
* If wrprotecting an entire contig range, we can avoid unfolding. Just
* set wrprotect and wait for the later mmu_gather flush to invalidate
* the tlb. Until the flush, the page may or may not be wrprotected.
* After the flush, it is guaranteed wrprotected. If it's a partial
* range though, we must unfold, because we can't have a case where
* CONT_PTE is set but wrprotect applies to a subset of the PTEs; this
* would cause it to continue to be unpredictable after the flush.
*/
contpte_try_unfold_partial(mm, addr, ptep, nr);
__wrprotect_ptes(mm, addr, ptep, nr);
}
EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes);
void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
unsigned int nr, cydp_t flags)
{
/*
* We can safely clear access/dirty without needing to unfold from
* the architectures perspective, even when contpte is set. If the
* range starts or ends midway through a contpte block, we can just
* expand to include the full contpte block. While this is not
* exactly what the core-mm asked for, it tracks access/dirty per
* folio, not per page. And since we only create a contpte block
* when it is covered by a single folio, we can get away with
* clearing access/dirty for the whole block.
*/
unsigned long start = addr;
unsigned long end = start + nr * PAGE_SIZE;
if (pte_cont(__ptep_get(ptep + nr - 1)))
end = ALIGN(end, CONT_PTE_SIZE);
if (pte_cont(__ptep_get(ptep))) {
start = ALIGN_DOWN(start, CONT_PTE_SIZE);
ptep = contpte_align_down(ptep);
}
__clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags);
}
EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t entry, int dirty)
{
unsigned long start_addr;
pte_t orig_pte;
int i;
/*
* Gather the access/dirty bits for the contiguous range. If nothing has
* changed, its a noop.
*/
orig_pte = pte_mknoncont(ptep_get(ptep));
if (pte_val(orig_pte) == pte_val(entry))
return 0;
/*
* We can fix up access/dirty bits without having to unfold the contig
* range. But if the write bit is changing, we must unfold.
*/
if (pte_write(orig_pte) == pte_write(entry)) {
/*
* For HW access management, we technically only need to update
* the flag on a single pte in the range. But for SW access
* management, we need to update all the ptes to prevent extra
* faults. Avoid per-page tlb flush in __ptep_set_access_flags()
* and instead flush the whole range at the end.
*/
ptep = contpte_align_down(ptep);
start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
/*
* We are not advancing entry because __ptep_set_access_flags()
* only consumes access flags from entry. And since we have checked
* for the whole contpte block and returned early, pte_same()
* within __ptep_set_access_flags() is likely false.
*/
for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
__ptep_set_access_flags(vma, addr, ptep, entry, 0);
if (dirty)
__flush_tlb_range(vma, start_addr, addr,
PAGE_SIZE, true, 3);
} else {
__contpte_try_unfold(vma->vm_mm, addr, ptep, orig_pte);
__ptep_set_access_flags(vma, addr, ptep, entry, dirty);
}
return 1;
}
EXPORT_SYMBOL_GPL(contpte_ptep_set_access_flags);
// SPDX-License-Identifier: GPL-2.0
/*
* bus.c - bus driver management
*
* Copyright (c) 2002-3 Patrick Mochel
* Copyright (c) 2002-3 Open Source Development Labs
* Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2007 Novell Inc.
* Copyright (c) 2023 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
*/
#include <linux/async.h>
#include <linux/device/bus.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/mutex.h>
#include <linux/sysfs.h>
#include "base.h"
#include "power/power.h"
/* /sys/devices/system */
static struct kset *system_kset;
/* /sys/bus */
static struct kset *bus_kset;
#define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr)
/*
* sysfs bindings for drivers
*/
#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr)
#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
struct driver_attribute driver_attr_##_name = \
__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data);
/**
* bus_to_subsys - Turn a struct bus_type into a struct subsys_private
*
* @bus: pointer to the struct bus_type to look up
*
* The driver core internals needs to work on the subsys_private structure, not
* the external struct bus_type pointer. This function walks the list of
* registered busses in the system and finds the matching one and returns the
* internal struct subsys_private that relates to that bus.
*
* Note, the reference count of the return value is INCREMENTED if it is not
* NULL. A call to subsys_put() must be done when finished with the pointer in
* order for it to be properly freed.
*/
struct subsys_private *bus_to_subsys(const struct bus_type *bus)
{
struct subsys_private *sp = NULL;
struct kobject *kobj;
if (!bus || !bus_kset)
return NULL;
spin_lock(&bus_kset->list_lock);
if (list_empty(&bus_kset->list))
goto done;
list_for_each_entry(kobj, &bus_kset->list, entry) {
struct kset *kset = container_of(kobj, struct kset, kobj);
sp = container_of_const(kset, struct subsys_private, subsys);
if (sp->bus == bus)
goto done;
}
sp = NULL;
done:
sp = subsys_get(sp);
spin_unlock(&bus_kset->list_lock);
return sp;
}
static const struct bus_type *bus_get(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
if (sp)
return bus;
return NULL;
}
static void bus_put(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
/* two puts are required as the call to bus_to_subsys incremented it again */
subsys_put(sp);
subsys_put(sp);
}
static ssize_t drv_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct driver_attribute *drv_attr = to_drv_attr(attr);
struct driver_private *drv_priv = to_driver(kobj);
ssize_t ret = -EIO;
if (drv_attr->show)
ret = drv_attr->show(drv_priv->driver, buf);
return ret;
}
static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct driver_attribute *drv_attr = to_drv_attr(attr);
struct driver_private *drv_priv = to_driver(kobj);
ssize_t ret = -EIO;
if (drv_attr->store)
ret = drv_attr->store(drv_priv->driver, buf, count);
return ret;
}
static const struct sysfs_ops driver_sysfs_ops = {
.show = drv_attr_show,
.store = drv_attr_store,
};
static void driver_release(struct kobject *kobj)
{
struct driver_private *drv_priv = to_driver(kobj);
pr_debug("driver: '%s': %s\n", kobject_name(kobj), __func__);
kfree(drv_priv);
}
static const struct kobj_type driver_ktype = {
.sysfs_ops = &driver_sysfs_ops,
.release = driver_release,
};
/*
* sysfs bindings for buses
*/
static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct bus_attribute *bus_attr = to_bus_attr(attr);
struct subsys_private *subsys_priv = to_subsys_private(kobj);
/* return -EIO for reading a bus attribute without show() */
ssize_t ret = -EIO;
if (bus_attr->show)
ret = bus_attr->show(subsys_priv->bus, buf);
return ret;
}
static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct bus_attribute *bus_attr = to_bus_attr(attr);
struct subsys_private *subsys_priv = to_subsys_private(kobj);
/* return -EIO for writing a bus attribute without store() */
ssize_t ret = -EIO;
if (bus_attr->store)
ret = bus_attr->store(subsys_priv->bus, buf, count);
return ret;
}
static const struct sysfs_ops bus_sysfs_ops = {
.show = bus_attr_show,
.store = bus_attr_store,
};
int bus_create_file(const struct bus_type *bus, struct bus_attribute *attr)
{
struct subsys_private *sp = bus_to_subsys(bus);
int error;
if (!sp)
return -EINVAL;
error = sysfs_create_file(&sp->subsys.kobj, &attr->attr);
subsys_put(sp);
return error;
}
EXPORT_SYMBOL_GPL(bus_create_file);
void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr)
{
struct subsys_private *sp = bus_to_subsys(bus);
if (!sp)
return;
sysfs_remove_file(&sp->subsys.kobj, &attr->attr);
subsys_put(sp);
}
EXPORT_SYMBOL_GPL(bus_remove_file);
static void bus_release(struct kobject *kobj)
{
struct subsys_private *priv = to_subsys_private(kobj);
lockdep_unregister_key(&priv->lock_key);
kfree(priv);
}
static const struct kobj_type bus_ktype = {
.sysfs_ops = &bus_sysfs_ops,
.release = bus_release,
};
static int bus_uevent_filter(const struct kobject *kobj)
{
const struct kobj_type *ktype = get_ktype(kobj);
if (ktype == &bus_ktype)
return 1;
return 0;
}
static const struct kset_uevent_ops bus_uevent_ops = {
.filter = bus_uevent_filter,
};
/* Manually detach a device from its associated driver. */
static ssize_t unbind_store(struct device_driver *drv, const char *buf,
size_t count)
{
const struct bus_type *bus = bus_get(drv->bus);
struct device *dev;
int err = -ENODEV;
dev = bus_find_device_by_name(bus, NULL, buf);
if (dev && dev->driver == drv) {
device_driver_detach(dev);
err = count;
}
put_device(dev);
bus_put(bus);
return err;
}
static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store);
/*
* Manually attach a device to a driver.
* Note: the driver must want to bind to the device,
* it is not possible to override the driver's id table.
*/
static ssize_t bind_store(struct device_driver *drv, const char *buf,
size_t count)
{
const struct bus_type *bus = bus_get(drv->bus);
struct device *dev;
int err = -ENODEV;
dev = bus_find_device_by_name(bus, NULL, buf);
if (dev && driver_match_device(drv, dev)) {
err = device_driver_attach(drv, dev);
if (!err) {
/* success */
err = count;
}
}
put_device(dev);
bus_put(bus);
return err;
}
static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store);
static ssize_t drivers_autoprobe_show(const struct bus_type *bus, char *buf)
{
struct subsys_private *sp = bus_to_subsys(bus);
int ret;
if (!sp)
return -EINVAL;
ret = sysfs_emit(buf, "%d\n", sp->drivers_autoprobe);
subsys_put(sp);
return ret;
}
static ssize_t drivers_autoprobe_store(const struct bus_type *bus,
const char *buf, size_t count)
{
struct subsys_private *sp = bus_to_subsys(bus);
if (!sp)
return -EINVAL;
if (buf[0] == '0')
sp->drivers_autoprobe = 0;
else
sp->drivers_autoprobe = 1;
subsys_put(sp);
return count;
}
static ssize_t drivers_probe_store(const struct bus_type *bus,
const char *buf, size_t count)
{
struct device *dev;
int err = -EINVAL;
dev = bus_find_device_by_name(bus, NULL, buf);
if (!dev)
return -ENODEV;
if (bus_rescan_devices_helper(dev, NULL) == 0)
err = count;
put_device(dev);
return err;
}
static struct device *next_device(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct device *dev = NULL;
struct device_private *dev_prv;
if (n) {
dev_prv = to_device_private_bus(n);
dev = dev_prv->device;
}
return dev;
}
/**
* bus_for_each_dev - device iterator.
* @bus: bus type.
* @start: device to start iterating from.
* @data: data for the callback.
* @fn: function to be called for each device.
*
* Iterate over @bus's list of devices, and call @fn for each,
* passing it @data. If @start is not NULL, we use that device to
* begin iterating from.
*
* We check the return of @fn each time. If it returns anything
* other than 0, we break out and return that value.
*
* NOTE: The device that returns a non-zero value is not retained
* in any way, nor is its refcount incremented. If the caller needs
* to retain this data, it should do so, and increment the reference
* count in the supplied callback.
*/
int bus_for_each_dev(const struct bus_type *bus, struct device *start,
void *data, device_iter_t fn)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct klist_iter i;
struct device *dev;
int error = 0;
if (!sp)
return -EINVAL;
klist_iter_init_node(&sp->klist_devices, &i,
(start ? &start->p->knode_bus : NULL));
while (!error && (dev = next_device(&i)))
error = fn(dev, data);
klist_iter_exit(&i);
subsys_put(sp);
return error;
}
EXPORT_SYMBOL_GPL(bus_for_each_dev);
/**
* bus_find_device - device iterator for locating a particular device.
* @bus: bus type
* @start: Device to begin with
* @data: Data to pass to match function
* @match: Callback function to check device
*
* This is similar to the bus_for_each_dev() function above, but it
* returns a reference to a device that is 'found' for later use, as
* determined by the @match callback.
*
* The callback should return 0 if the device doesn't match and non-zero
* if it does. If the callback returns non-zero, this function will
* return to the caller and not iterate over any more devices.
*/
struct device *bus_find_device(const struct bus_type *bus,
struct device *start, const void *data,
device_match_t match)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct klist_iter i;
struct device *dev;
if (!sp)
return NULL;
klist_iter_init_node(&sp->klist_devices, &i,
(start ? &start->p->knode_bus : NULL));
while ((dev = next_device(&i))) {
if (match(dev, data)) {
get_device(dev);
break;
}
}
klist_iter_exit(&i);
subsys_put(sp);
return dev;
}
EXPORT_SYMBOL_GPL(bus_find_device);
static struct device_driver *next_driver(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct driver_private *drv_priv;
if (n) {
drv_priv = container_of(n, struct driver_private, knode_bus);
return drv_priv->driver;
}
return NULL;
}
/**
* bus_for_each_drv - driver iterator
* @bus: bus we're dealing with.
* @start: driver to start iterating on.
* @data: data to pass to the callback.
* @fn: function to call for each driver.
*
* This is nearly identical to the device iterator above.
* We iterate over each driver that belongs to @bus, and call
* @fn for each. If @fn returns anything but 0, we break out
* and return it. If @start is not NULL, we use it as the head
* of the list.
*
* NOTE: we don't return the driver that returns a non-zero
* value, nor do we leave the reference count incremented for that
* driver. If the caller needs to know that info, it must set it
* in the callback. It must also be sure to increment the refcount
* so it doesn't disappear before returning to the caller.
*/
int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
void *data, int (*fn)(struct device_driver *, void *))
{
struct subsys_private *sp = bus_to_subsys(bus);
struct klist_iter i;
struct device_driver *drv;
int error = 0;
if (!sp)
return -EINVAL;
klist_iter_init_node(&sp->klist_drivers, &i,
start ? &start->p->knode_bus : NULL);
while ((drv = next_driver(&i)) && !error)
error = fn(drv, data);
klist_iter_exit(&i);
subsys_put(sp);
return error;
}
EXPORT_SYMBOL_GPL(bus_for_each_drv);
/**
* bus_add_device - add device to bus
* @dev: device being added
*
* - Add device's bus attributes.
* - Create links to device's bus.
* - Add the device to its bus's list of devices.
*/
int bus_add_device(struct device *dev)
{
struct subsys_private *sp = bus_to_subsys(dev->bus);
int error;
if (!sp) {
/*
* This is a normal operation for many devices that do not
* have a bus assigned to them, just say that all went
* well.
*/
return 0;
}
/*
* Reference in sp is now incremented and will be dropped when
* the device is removed from the bus
*/
pr_debug("bus: '%s': add device %s\n", sp->bus->name, dev_name(dev));
error = device_add_groups(dev, sp->bus->dev_groups);
if (error)
goto out_put;
error = sysfs_create_link(&sp->devices_kset->kobj, &dev->kobj, dev_name(dev));
if (error)
goto out_groups;
error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem");
if (error)
goto out_subsys;
klist_add_tail(&dev->p->knode_bus, &sp->klist_devices);
return 0;
out_subsys:
sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev));
out_groups:
device_remove_groups(dev, sp->bus->dev_groups);
out_put:
subsys_put(sp);
return error;
}
/**
* bus_probe_device - probe drivers for a new device
* @dev: device to probe
*
* - Automatically probe for a driver if the bus allows it.
*/
void bus_probe_device(struct device *dev)
{
struct subsys_private *sp = bus_to_subsys(dev->bus);
struct subsys_interface *sif;
if (!sp)
return;
if (sp->drivers_autoprobe)
device_initial_probe(dev);
mutex_lock(&sp->mutex);
list_for_each_entry(sif, &sp->interfaces, node)
if (sif->add_dev)
sif->add_dev(dev, sif);
mutex_unlock(&sp->mutex);
subsys_put(sp);
}
/**
* bus_remove_device - remove device from bus
* @dev: device to be removed
*
* - Remove device from all interfaces.
* - Remove symlink from bus' directory.
* - Delete device from bus's list.
* - Detach from its driver.
* - Drop reference taken in bus_add_device().
*/
void bus_remove_device(struct device *dev)
{
struct subsys_private *sp = bus_to_subsys(dev->bus);
struct subsys_interface *sif;
if (!sp)
return;
mutex_lock(&sp->mutex);
list_for_each_entry(sif, &sp->interfaces, node)
if (sif->remove_dev)
sif->remove_dev(dev, sif);
mutex_unlock(&sp->mutex);
sysfs_remove_link(&dev->kobj, "subsystem");
sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev));
device_remove_groups(dev, dev->bus->dev_groups);
if (klist_node_attached(&dev->p->knode_bus))
klist_del(&dev->p->knode_bus);
pr_debug("bus: '%s': remove device %s\n",
dev->bus->name, dev_name(dev));
device_release_driver(dev);
/*
* Decrement the reference count twice, once for the bus_to_subsys()
* call in the start of this function, and the second one from the
* reference increment in bus_add_device()
*/
subsys_put(sp);
subsys_put(sp);
}
static int __must_check add_bind_files(struct device_driver *drv)
{
int ret;
ret = driver_create_file(drv, &driver_attr_unbind);
if (ret == 0) {
ret = driver_create_file(drv, &driver_attr_bind);
if (ret)
driver_remove_file(drv, &driver_attr_unbind);
}
return ret;
}
static void remove_bind_files(struct device_driver *drv)
{
driver_remove_file(drv, &driver_attr_bind);
driver_remove_file(drv, &driver_attr_unbind);
}
static BUS_ATTR_WO(drivers_probe);
static BUS_ATTR_RW(drivers_autoprobe);
static int add_probe_files(const struct bus_type *bus)
{
int retval;
retval = bus_create_file(bus, &bus_attr_drivers_probe);
if (retval)
goto out;
retval = bus_create_file(bus, &bus_attr_drivers_autoprobe);
if (retval)
bus_remove_file(bus, &bus_attr_drivers_probe);
out:
return retval;
}
static void remove_probe_files(const struct bus_type *bus)
{
bus_remove_file(bus, &bus_attr_drivers_autoprobe);
bus_remove_file(bus, &bus_attr_drivers_probe);
}
static ssize_t uevent_store(struct device_driver *drv, const char *buf,
size_t count)
{
int rc;
rc = kobject_synth_uevent(&drv->p->kobj, buf, count);
return rc ? rc : count;
}
static DRIVER_ATTR_WO(uevent);
/**
* bus_add_driver - Add a driver to the bus.
* @drv: driver.
*/
int bus_add_driver(struct device_driver *drv)
{
struct subsys_private *sp = bus_to_subsys(drv->bus);
struct driver_private *priv;
int error = 0;
if (!sp)
return -EINVAL;
/*
* Reference in sp is now incremented and will be dropped when
* the driver is removed from the bus
*/
pr_debug("bus: '%s': add driver %s\n", sp->bus->name, drv->name);
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv) {
error = -ENOMEM;
goto out_put_bus;
}
klist_init(&priv->klist_devices, NULL, NULL);
priv->driver = drv;
drv->p = priv;
priv->kobj.kset = sp->drivers_kset;
error = kobject_init_and_add(&priv->kobj, &driver_ktype, NULL,
"%s", drv->name);
if (error)
goto out_unregister;
klist_add_tail(&priv->knode_bus, &sp->klist_drivers);
if (sp->drivers_autoprobe) {
error = driver_attach(drv);
if (error)
goto out_del_list;
}
error = module_add_driver(drv->owner, drv);
if (error) {
printk(KERN_ERR "%s: failed to create module links for %s\n",
__func__, drv->name);
goto out_detach;
}
error = driver_create_file(drv, &driver_attr_uevent);
if (error) {
printk(KERN_ERR "%s: uevent attr (%s) failed\n",
__func__, drv->name);
}
error = driver_add_groups(drv, sp->bus->drv_groups);
if (error) {
/* How the hell do we get out of this pickle? Give up */
printk(KERN_ERR "%s: driver_add_groups(%s) failed\n",
__func__, drv->name);
}
if (!drv->suppress_bind_attrs) {
error = add_bind_files(drv);
if (error) {
/* Ditto */
printk(KERN_ERR "%s: add_bind_files(%s) failed\n",
__func__, drv->name);
}
}
return 0;
out_detach:
driver_detach(drv);
out_del_list:
klist_del(&priv->knode_bus);
out_unregister:
kobject_put(&priv->kobj);
/* drv->p is freed in driver_release() */
drv->p = NULL;
out_put_bus:
subsys_put(sp);
return error;
}
/**
* bus_remove_driver - delete driver from bus's knowledge.
* @drv: driver.
*
* Detach the driver from the devices it controls, and remove
* it from its bus's list of drivers. Finally, we drop the reference
* to the bus we took in bus_add_driver().
*/
void bus_remove_driver(struct device_driver *drv)
{
struct subsys_private *sp = bus_to_subsys(drv->bus);
if (!sp)
return;
pr_debug("bus: '%s': remove driver %s\n", sp->bus->name, drv->name);
if (!drv->suppress_bind_attrs)
remove_bind_files(drv);
driver_remove_groups(drv, sp->bus->drv_groups);
driver_remove_file(drv, &driver_attr_uevent);
klist_remove(&drv->p->knode_bus);
driver_detach(drv);
module_remove_driver(drv);
kobject_put(&drv->p->kobj);
/*
* Decrement the reference count twice, once for the bus_to_subsys()
* call in the start of this function, and the second one from the
* reference increment in bus_add_driver()
*/
subsys_put(sp);
subsys_put(sp);
}
/* Helper for bus_rescan_devices's iter */
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data)
{
int ret = 0;
if (!dev->driver) {
if (dev->parent && dev->bus->need_parent_lock)
device_lock(dev->parent);
ret = device_attach(dev);
if (dev->parent && dev->bus->need_parent_lock)
device_unlock(dev->parent);
}
return ret < 0 ? ret : 0;
}
/**
* bus_rescan_devices - rescan devices on the bus for possible drivers
* @bus: the bus to scan.
*
* This function will look for devices on the bus with no driver
* attached and rescan it against existing drivers to see if it matches
* any by calling device_attach() for the unbound devices.
*/
int bus_rescan_devices(const struct bus_type *bus)
{
return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper);
}
EXPORT_SYMBOL_GPL(bus_rescan_devices);
/**
* device_reprobe - remove driver for a device and probe for a new driver
* @dev: the device to reprobe
*
* This function detaches the attached driver (if any) for the given
* device and restarts the driver probing process. It is intended
* to use if probing criteria changed during a devices lifetime and
* driver attachment should change accordingly.
*/
int device_reprobe(struct device *dev)
{
if (dev->driver)
device_driver_detach(dev);
return bus_rescan_devices_helper(dev, NULL);
}
EXPORT_SYMBOL_GPL(device_reprobe);
static void klist_devices_get(struct klist_node *n)
{
struct device_private *dev_prv = to_device_private_bus(n);
struct device *dev = dev_prv->device;
get_device(dev);
}
static void klist_devices_put(struct klist_node *n)
{
struct device_private *dev_prv = to_device_private_bus(n);
struct device *dev = dev_prv->device;
put_device(dev);
}
static ssize_t bus_uevent_store(const struct bus_type *bus,
const char *buf, size_t count)
{
struct subsys_private *sp = bus_to_subsys(bus);
int ret;
if (!sp)
return -EINVAL;
ret = kobject_synth_uevent(&sp->subsys.kobj, buf, count);
subsys_put(sp);
if (ret)
return ret;
return count;
}
/*
* "open code" the old BUS_ATTR() macro here. We want to use BUS_ATTR_WO()
* here, but can not use it as earlier in the file we have
* DEVICE_ATTR_WO(uevent), which would cause a clash with the with the store
* function name.
*/
static struct bus_attribute bus_attr_uevent = __ATTR(uevent, 0200, NULL,
bus_uevent_store);
/**
* bus_register - register a driver-core subsystem
* @bus: bus to register
*
* Once we have that, we register the bus with the kobject
* infrastructure, then register the children subsystems it has:
* the devices and drivers that belong to the subsystem.
*/
int bus_register(const struct bus_type *bus)
{
int retval;
struct subsys_private *priv;
struct kobject *bus_kobj;
struct lock_class_key *key;
priv = kzalloc(sizeof(struct subsys_private), GFP_KERNEL);
if (!priv)
return -ENOMEM;
priv->bus = bus;
BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier);
bus_kobj = &priv->subsys.kobj;
retval = kobject_set_name(bus_kobj, "%s", bus->name);
if (retval)
goto out;
bus_kobj->kset = bus_kset;
bus_kobj->ktype = &bus_ktype;
priv->drivers_autoprobe = 1;
retval = kset_register(&priv->subsys);
if (retval)
goto out;
retval = bus_create_file(bus, &bus_attr_uevent);
if (retval)
goto bus_uevent_fail;
priv->devices_kset = kset_create_and_add("devices", NULL, bus_kobj);
if (!priv->devices_kset) {
retval = -ENOMEM;
goto bus_devices_fail;
}
priv->drivers_kset = kset_create_and_add("drivers", NULL, bus_kobj);
if (!priv->drivers_kset) {
retval = -ENOMEM;
goto bus_drivers_fail;
}
INIT_LIST_HEAD(&priv->interfaces);
key = &priv->lock_key;
lockdep_register_key(key);
__mutex_init(&priv->mutex, "subsys mutex", key);
klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put);
klist_init(&priv->klist_drivers, NULL, NULL);
retval = add_probe_files(bus);
if (retval)
goto bus_probe_files_fail;
retval = sysfs_create_groups(bus_kobj, bus->bus_groups);
if (retval)
goto bus_groups_fail;
pr_debug("bus: '%s': registered\n", bus->name);
return 0;
bus_groups_fail:
remove_probe_files(bus);
bus_probe_files_fail:
kset_unregister(priv->drivers_kset);
bus_drivers_fail:
kset_unregister(priv->devices_kset);
bus_devices_fail:
bus_remove_file(bus, &bus_attr_uevent);
bus_uevent_fail:
kset_unregister(&priv->subsys);
/* Above kset_unregister() will kfree @priv */
priv = NULL;
out:
kfree(priv);
return retval;
}
EXPORT_SYMBOL_GPL(bus_register);
/**
* bus_unregister - remove a bus from the system
* @bus: bus.
*
* Unregister the child subsystems and the bus itself.
* Finally, we call bus_put() to release the refcount
*/
void bus_unregister(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct kobject *bus_kobj;
if (!sp)
return;
pr_debug("bus: '%s': unregistering\n", bus->name);
if (sp->dev_root)
device_unregister(sp->dev_root);
bus_kobj = &sp->subsys.kobj;
sysfs_remove_groups(bus_kobj, bus->bus_groups);
remove_probe_files(bus);
bus_remove_file(bus, &bus_attr_uevent);
kset_unregister(sp->drivers_kset);
kset_unregister(sp->devices_kset);
kset_unregister(&sp->subsys);
subsys_put(sp);
}
EXPORT_SYMBOL_GPL(bus_unregister);
int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb)
{
struct subsys_private *sp = bus_to_subsys(bus);
int retval;
if (!sp)
return -EINVAL;
retval = blocking_notifier_chain_register(&sp->bus_notifier, nb);
subsys_put(sp);
return retval;
}
EXPORT_SYMBOL_GPL(bus_register_notifier);
int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb)
{
struct subsys_private *sp = bus_to_subsys(bus);
int retval;
if (!sp)
return -EINVAL;
retval = blocking_notifier_chain_unregister(&sp->bus_notifier, nb);
subsys_put(sp);
return retval;
}
EXPORT_SYMBOL_GPL(bus_unregister_notifier);
void bus_notify(struct device *dev, enum bus_notifier_event value)
{
struct subsys_private *sp = bus_to_subsys(dev->bus);
if (!sp)
return;
blocking_notifier_call_chain(&sp->bus_notifier, value, dev);
subsys_put(sp);
}
struct kset *bus_get_kset(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct kset *kset;
if (!sp)
return NULL;
kset = &sp->subsys;
subsys_put(sp);
return kset;
}
EXPORT_SYMBOL_GPL(bus_get_kset);
/*
* Yes, this forcibly breaks the klist abstraction temporarily. It
* just wants to sort the klist, not change reference counts and
* take/drop locks rapidly in the process. It does all this while
* holding the lock for the list, so objects can't otherwise be
* added/removed while we're swizzling.
*/
static void device_insertion_sort_klist(struct device *a, struct list_head *list,
int (*compare)(const struct device *a,
const struct device *b))
{
struct klist_node *n;
struct device_private *dev_prv;
struct device *b;
list_for_each_entry(n, list, n_node) {
dev_prv = to_device_private_bus(n);
b = dev_prv->device;
if (compare(a, b) <= 0) {
list_move_tail(&a->p->knode_bus.n_node,
&b->p->knode_bus.n_node);
return;
}
}
list_move_tail(&a->p->knode_bus.n_node, list);
}
void bus_sort_breadthfirst(const struct bus_type *bus,
int (*compare)(const struct device *a,
const struct device *b))
{
struct subsys_private *sp = bus_to_subsys(bus);
LIST_HEAD(sorted_devices);
struct klist_node *n, *tmp;
struct device_private *dev_prv;
struct device *dev;
struct klist *device_klist;
if (!sp)
return;
device_klist = &sp->klist_devices;
spin_lock(&device_klist->k_lock);
list_for_each_entry_safe(n, tmp, &device_klist->k_list, n_node) {
dev_prv = to_device_private_bus(n);
dev = dev_prv->device;
device_insertion_sort_klist(dev, &sorted_devices, compare);
}
list_splice(&sorted_devices, &device_klist->k_list);
spin_unlock(&device_klist->k_lock);
subsys_put(sp);
}
EXPORT_SYMBOL_GPL(bus_sort_breadthfirst);
struct subsys_dev_iter {
struct klist_iter ki;
const struct device_type *type;
};
/**
* subsys_dev_iter_init - initialize subsys device iterator
* @iter: subsys iterator to initialize
* @sp: the subsys private (i.e. bus) we wanna iterate over
* @start: the device to start iterating from, if any
* @type: device_type of the devices to iterate over, NULL for all
*
* Initialize subsys iterator @iter such that it iterates over devices
* of @subsys. If @start is set, the list iteration will start there,
* otherwise if it is NULL, the iteration starts at the beginning of
* the list.
*/
static void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct subsys_private *sp,
struct device *start, const struct device_type *type)
{
struct klist_node *start_knode = NULL;
if (start)
start_knode = &start->p->knode_bus;
klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode);
iter->type = type;
}
/**
* subsys_dev_iter_next - iterate to the next device
* @iter: subsys iterator to proceed
*
* Proceed @iter to the next device and return it. Returns NULL if
* iteration is complete.
*
* The returned device is referenced and won't be released till
* iterator is proceed to the next device or exited. The caller is
* free to do whatever it wants to do with the device including
* calling back into subsys code.
*/
static struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter)
{
struct klist_node *knode;
struct device *dev;
for (;;) {
knode = klist_next(&iter->ki);
if (!knode)
return NULL;
dev = to_device_private_bus(knode)->device;
if (!iter->type || iter->type == dev->type)
return dev;
}
}
/**
* subsys_dev_iter_exit - finish iteration
* @iter: subsys iterator to finish
*
* Finish an iteration. Always call this function after iteration is
* complete whether the iteration ran till the end or not.
*/
static void subsys_dev_iter_exit(struct subsys_dev_iter *iter)
{
klist_iter_exit(&iter->ki);
}
int subsys_interface_register(struct subsys_interface *sif)
{
struct subsys_private *sp;
struct subsys_dev_iter iter;
struct device *dev;
if (!sif || !sif->subsys)
return -ENODEV;
sp = bus_to_subsys(sif->subsys);
if (!sp)
return -EINVAL;
/*
* Reference in sp is now incremented and will be dropped when
* the interface is removed from the bus
*/
mutex_lock(&sp->mutex);
list_add_tail(&sif->node, &sp->interfaces);
if (sif->add_dev) {
subsys_dev_iter_init(&iter, sp, NULL, NULL);
while ((dev = subsys_dev_iter_next(&iter)))
sif->add_dev(dev, sif);
subsys_dev_iter_exit(&iter);
}
mutex_unlock(&sp->mutex);
return 0;
}
EXPORT_SYMBOL_GPL(subsys_interface_register);
void subsys_interface_unregister(struct subsys_interface *sif)
{
struct subsys_private *sp;
struct subsys_dev_iter iter;
struct device *dev;
if (!sif || !sif->subsys)
return;
sp = bus_to_subsys(sif->subsys);
if (!sp)
return;
mutex_lock(&sp->mutex);
list_del_init(&sif->node);
if (sif->remove_dev) {
subsys_dev_iter_init(&iter, sp, NULL, NULL);
while ((dev = subsys_dev_iter_next(&iter)))
sif->remove_dev(dev, sif);
subsys_dev_iter_exit(&iter);
}
mutex_unlock(&sp->mutex);
/*
* Decrement the reference count twice, once for the bus_to_subsys()
* call in the start of this function, and the second one from the
* reference increment in subsys_interface_register()
*/
subsys_put(sp);
subsys_put(sp);
}
EXPORT_SYMBOL_GPL(subsys_interface_unregister);
static void system_root_device_release(struct device *dev)
{
kfree(dev);
}
static int subsys_register(const struct bus_type *subsys,
const struct attribute_group **groups,
struct kobject *parent_of_root)
{
struct subsys_private *sp;
struct device *dev;
int err;
err = bus_register(subsys);
if (err < 0)
return err;
sp = bus_to_subsys(subsys);
if (!sp) {
err = -EINVAL;
goto err_sp;
}
dev = kzalloc(sizeof(struct device), GFP_KERNEL);
if (!dev) {
err = -ENOMEM;
goto err_dev;
}
err = dev_set_name(dev, "%s", subsys->name);
if (err < 0)
goto err_name;
dev->kobj.parent = parent_of_root;
dev->groups = groups;
dev->release = system_root_device_release;
err = device_register(dev);
if (err < 0)
goto err_dev_reg;
sp->dev_root = dev;
subsys_put(sp);
return 0;
err_dev_reg:
put_device(dev);
dev = NULL;
err_name:
kfree(dev);
err_dev:
subsys_put(sp);
err_sp:
bus_unregister(subsys);
return err;
}
/**
* subsys_system_register - register a subsystem at /sys/devices/system/
* @subsys: system subsystem
* @groups: default attributes for the root device
*
* All 'system' subsystems have a /sys/devices/system/<name> root device
* with the name of the subsystem. The root device can carry subsystem-
* wide attributes. All registered devices are below this single root
* device and are named after the subsystem with a simple enumeration
* number appended. The registered devices are not explicitly named;
* only 'id' in the device needs to be set.
*
* Do not use this interface for anything new, it exists for compatibility
* with bad ideas only. New subsystems should use plain subsystems; and
* add the subsystem-wide attributes should be added to the subsystem
* directory itself and not some create fake root-device placed in
* /sys/devices/system/<name>.
*/
int subsys_system_register(const struct bus_type *subsys,
const struct attribute_group **groups)
{
return subsys_register(subsys, groups, &system_kset->kobj);
}
EXPORT_SYMBOL_GPL(subsys_system_register);
/**
* subsys_virtual_register - register a subsystem at /sys/devices/virtual/
* @subsys: virtual subsystem
* @groups: default attributes for the root device
*
* All 'virtual' subsystems have a /sys/devices/system/<name> root device
* with the name of the subsystem. The root device can carry subsystem-wide
* attributes. All registered devices are below this single root device.
* There's no restriction on device naming. This is for kernel software
* constructs which need sysfs interface.
*/
int subsys_virtual_register(const struct bus_type *subsys,
const struct attribute_group **groups)
{
struct kobject *virtual_dir;
virtual_dir = virtual_device_parent();
if (!virtual_dir)
return -ENOMEM;
return subsys_register(subsys, groups, virtual_dir);
}
EXPORT_SYMBOL_GPL(subsys_virtual_register);
/**
* driver_find - locate driver on a bus by its name.
* @name: name of the driver.
* @bus: bus to scan for the driver.
*
* Call kset_find_obj() to iterate over list of drivers on
* a bus to find driver by name. Return driver if found.
*
* This routine provides no locking to prevent the driver it returns
* from being unregistered or unloaded while the caller is using it.
* The caller is responsible for preventing this.
*/
struct device_driver *driver_find(const char *name, const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct kobject *k;
struct driver_private *priv;
if (!sp)
return NULL;
k = kset_find_obj(sp->drivers_kset, name);
subsys_put(sp);
if (!k)
return NULL;
priv = to_driver(k);
/* Drop reference added by kset_find_obj() */
kobject_put(k);
return priv->driver;
}
EXPORT_SYMBOL_GPL(driver_find);
/*
* Warning, the value could go to "removed" instantly after calling this function, so be very
* careful when calling it...
*/
bool bus_is_registered(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
bool is_initialized = false;
if (sp) {
is_initialized = true;
subsys_put(sp);
}
return is_initialized;
}
/**
* bus_get_dev_root - return a pointer to the "device root" of a bus
* @bus: bus to return the device root of.
*
* If a bus has a "device root" structure, return it, WITH THE REFERENCE
* COUNT INCREMENTED.
*
* Note, when finished with the device, a call to put_device() is required.
*
* If the device root is not present (or bus is not a valid pointer), NULL
* will be returned.
*/
struct device *bus_get_dev_root(const struct bus_type *bus)
{
struct subsys_private *sp = bus_to_subsys(bus);
struct device *dev_root;
if (!sp)
return NULL;
dev_root = get_device(sp->dev_root);
subsys_put(sp);
return dev_root;
}
EXPORT_SYMBOL_GPL(bus_get_dev_root);
int __init buses_init(void)
{
bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL);
if (!bus_kset)
return -ENOMEM;
system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj);
if (!system_kset) {
/* Do error handling here as devices_init() do */
kset_unregister(bus_kset);
bus_kset = NULL;
pr_err("%s: failed to create and add kset 'bus'\n", __func__);
return -ENOMEM;
}
return 0;
}
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/char_dev.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/major.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/kobject.h>
#include <linux/kobj_map.h>
#include <linux/cdev.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/tty.h>
#include "internal.h"
static struct kobj_map *cdev_map __ro_after_init;
static DEFINE_MUTEX(chrdevs_lock);
#define CHRDEV_MAJOR_HASH_SIZE 255
static struct char_device_struct {
struct char_device_struct *next;
unsigned int major;
unsigned int baseminor;
int minorct;
char name[64];
struct cdev *cdev; /* will die */
} *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
/* index in the above */
static inline int major_to_index(unsigned major)
{
return major % CHRDEV_MAJOR_HASH_SIZE;
}
#ifdef CONFIG_PROC_FS
void chrdev_show(struct seq_file *f, off_t offset)
{
struct char_device_struct *cd;
mutex_lock(&chrdevs_lock);
for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) {
if (cd->major == offset)
seq_printf(f, "%3d %s\n", cd->major, cd->name);
}
mutex_unlock(&chrdevs_lock);
}
#endif /* CONFIG_PROC_FS */
static int find_dynamic_major(void)
{
int i;
struct char_device_struct *cd;
for (i = ARRAY_SIZE(chrdevs)-1; i >= CHRDEV_MAJOR_DYN_END; i--) {
if (chrdevs[i] == NULL)
return i;
}
for (i = CHRDEV_MAJOR_DYN_EXT_START;
i >= CHRDEV_MAJOR_DYN_EXT_END; i--) {
for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next)
if (cd->major == i)
break;
if (cd == NULL)
return i;
}
return -EBUSY;
}
/*
* Register a single major with a specified minor range.
*
* If major == 0 this function will dynamically allocate an unused major.
* If major > 0 this function will attempt to reserve the range of minors
* with given major.
*
*/
static struct char_device_struct *
__register_chrdev_region(unsigned int major, unsigned int baseminor,
int minorct, const char *name)
{
struct char_device_struct *cd, *curr, *prev = NULL;
int ret;
int i;
if (major >= CHRDEV_MAJOR_MAX) {
pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n",
name, major, CHRDEV_MAJOR_MAX-1);
return ERR_PTR(-EINVAL);
}
if (minorct > MINORMASK + 1 - baseminor) {
pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n",
name, baseminor, baseminor + minorct - 1, 0, MINORMASK);
return ERR_PTR(-EINVAL);
}
cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL);
if (cd == NULL)
return ERR_PTR(-ENOMEM);
mutex_lock(&chrdevs_lock);
if (major == 0) {
ret = find_dynamic_major();
if (ret < 0) {
pr_err("CHRDEV \"%s\" dynamic allocation region is full\n",
name);
goto out;
}
major = ret;
}
ret = -EBUSY;
i = major_to_index(major);
for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) {
if (curr->major < major)
continue;
if (curr->major > major)
break;
if (curr->baseminor + curr->minorct <= baseminor)
continue;
if (curr->baseminor >= baseminor + minorct)
break;
goto out;
}
cd->major = major;
cd->baseminor = baseminor;
cd->minorct = minorct;
strscpy(cd->name, name, sizeof(cd->name));
if (!prev) {
cd->next = curr;
chrdevs[i] = cd;
} else {
cd->next = prev->next;
prev->next = cd;
}
mutex_unlock(&chrdevs_lock);
return cd;
out:
mutex_unlock(&chrdevs_lock);
kfree(cd);
return ERR_PTR(ret);
}
static struct char_device_struct *
__unregister_chrdev_region(unsigned major, unsigned baseminor, int minorct)
{
struct char_device_struct *cd = NULL, **cp;
int i = major_to_index(major);
mutex_lock(&chrdevs_lock);
for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next)
if ((*cp)->major == major &&
(*cp)->baseminor == baseminor &&
(*cp)->minorct == minorct)
break;
if (*cp) {
cd = *cp;
*cp = cd->next;
}
mutex_unlock(&chrdevs_lock);
return cd;
}
/**
* register_chrdev_region() - register a range of device numbers
* @from: the first in the desired range of device numbers; must include
* the major number.
* @count: the number of consecutive device numbers required
* @name: the name of the device or driver.
*
* Return value is zero on success, a negative error code on failure.
*/
int register_chrdev_region(dev_t from, unsigned count, const char *name)
{
struct char_device_struct *cd;
dev_t to = from + count;
dev_t n, next;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
if (next > to)
next = to;
cd = __register_chrdev_region(MAJOR(n), MINOR(n),
next - n, name);
if (IS_ERR(cd))
goto fail;
}
return 0;
fail:
to = n;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
}
return PTR_ERR(cd);
}
/**
* alloc_chrdev_region() - register a range of char device numbers
* @dev: output parameter for first assigned number
* @baseminor: first of the requested range of minor numbers
* @count: the number of minor numbers required
* @name: the name of the associated device or driver
*
* Allocates a range of char device numbers. The major number will be
* chosen dynamically, and returned (along with the first minor number)
* in @dev. Returns zero or a negative error code.
*/
int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count,
const char *name)
{
struct char_device_struct *cd;
cd = __register_chrdev_region(0, baseminor, count, name);
if (IS_ERR(cd))
return PTR_ERR(cd);
*dev = MKDEV(cd->major, cd->baseminor);
return 0;
}
/**
* __register_chrdev() - create and register a cdev occupying a range of minors
* @major: major device number or 0 for dynamic allocation
* @baseminor: first of the requested range of minor numbers
* @count: the number of minor numbers required
* @name: name of this range of devices
* @fops: file operations associated with this devices
*
* If @major == 0 this functions will dynamically allocate a major and return
* its number.
*
* If @major > 0 this function will attempt to reserve a device with the given
* major number and will return zero on success.
*
* Returns a -ve errno on failure.
*
* The name of this device has nothing to do with the name of the device in
* /dev. It only helps to keep track of the different owners of devices. If
* your module name has only one type of devices it's ok to use e.g. the name
* of the module here.
*/
int __register_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name,
const struct file_operations *fops)
{
struct char_device_struct *cd;
struct cdev *cdev;
int err = -ENOMEM;
cd = __register_chrdev_region(major, baseminor, count, name);
if (IS_ERR(cd))
return PTR_ERR(cd);
cdev = cdev_alloc();
if (!cdev)
goto out2;
cdev->owner = fops->owner;
cdev->ops = fops;
kobject_set_name(&cdev->kobj, "%s", name);
err = cdev_add(cdev, MKDEV(cd->major, baseminor), count);
if (err)
goto out;
cd->cdev = cdev;
return major ? 0 : cd->major;
out:
kobject_put(&cdev->kobj);
out2:
kfree(__unregister_chrdev_region(cd->major, baseminor, count));
return err;
}
/**
* unregister_chrdev_region() - unregister a range of device numbers
* @from: the first in the range of numbers to unregister
* @count: the number of device numbers to unregister
*
* This function will unregister a range of @count device numbers,
* starting with @from. The caller should normally be the one who
* allocated those numbers in the first place...
*/
void unregister_chrdev_region(dev_t from, unsigned count)
{
dev_t to = from + count;
dev_t n, next;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
if (next > to)
next = to;
kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
}
}
/**
* __unregister_chrdev - unregister and destroy a cdev
* @major: major device number
* @baseminor: first of the range of minor numbers
* @count: the number of minor numbers this cdev is occupying
* @name: name of this range of devices
*
* Unregister and destroy the cdev occupying the region described by
* @major, @baseminor and @count. This function undoes what
* __register_chrdev() did.
*/
void __unregister_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name)
{
struct char_device_struct *cd;
cd = __unregister_chrdev_region(major, baseminor, count);
if (cd && cd->cdev)
cdev_del(cd->cdev);
kfree(cd);
}
static DEFINE_SPINLOCK(cdev_lock);
static struct kobject *cdev_get(struct cdev *p)
{
struct module *owner = p->owner;
struct kobject *kobj;
if (!try_module_get(owner))
return NULL;
kobj = kobject_get_unless_zero(&p->kobj);
if (!kobj) module_put(owner);
return kobj;
}
void cdev_put(struct cdev *p)
{ if (p) { struct module *owner = p->owner;
kobject_put(&p->kobj);
module_put(owner);
}
}
/*
* Called every time a character special file is opened
*/
static int chrdev_open(struct inode *inode, struct file *filp)
{
const struct file_operations *fops;
struct cdev *p;
struct cdev *new = NULL;
int ret = 0;
spin_lock(&cdev_lock);
p = inode->i_cdev;
if (!p) {
struct kobject *kobj;
int idx;
spin_unlock(&cdev_lock);
kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
if (!kobj)
return -ENXIO;
new = container_of(kobj, struct cdev, kobj);
spin_lock(&cdev_lock);
/* Check i_cdev again in case somebody beat us to it while
we dropped the lock. */
p = inode->i_cdev;
if (!p) {
inode->i_cdev = p = new;
list_add(&inode->i_devices, &p->list);
new = NULL;
} else if (!cdev_get(p))
ret = -ENXIO;
} else if (!cdev_get(p))
ret = -ENXIO;
spin_unlock(&cdev_lock);
cdev_put(new);
if (ret)
return ret;
ret = -ENXIO;
fops = fops_get(p->ops);
if (!fops)
goto out_cdev_put;
replace_fops(filp, fops); if (filp->f_op->open) {
ret = filp->f_op->open(inode, filp);
if (ret)
goto out_cdev_put;
}
return 0;
out_cdev_put:
cdev_put(p);
return ret;
}
void cd_forget(struct inode *inode)
{
spin_lock(&cdev_lock);
list_del_init(&inode->i_devices);
inode->i_cdev = NULL;
inode->i_mapping = &inode->i_data;
spin_unlock(&cdev_lock);
}
static void cdev_purge(struct cdev *cdev)
{
spin_lock(&cdev_lock);
while (!list_empty(&cdev->list)) {
struct inode *inode;
inode = container_of(cdev->list.next, struct inode, i_devices);
list_del_init(&inode->i_devices);
inode->i_cdev = NULL;
}
spin_unlock(&cdev_lock);
}
/*
* Dummy default file-operations: the only thing this does
* is contain the open that then fills in the correct operations
* depending on the special file...
*/
const struct file_operations def_chr_fops = {
.open = chrdev_open,
.llseek = noop_llseek,
};
static struct kobject *exact_match(dev_t dev, int *part, void *data)
{
struct cdev *p = data;
return &p->kobj;
}
static int exact_lock(dev_t dev, void *data)
{
struct cdev *p = data;
return cdev_get(p) ? 0 : -1;
}
/**
* cdev_add() - add a char device to the system
* @p: the cdev structure for the device
* @dev: the first device number for which this device is responsible
* @count: the number of consecutive minor numbers corresponding to this
* device
*
* cdev_add() adds the device represented by @p to the system, making it
* live immediately. A negative error code is returned on failure.
*/
int cdev_add(struct cdev *p, dev_t dev, unsigned count)
{
int error;
p->dev = dev;
p->count = count;
if (WARN_ON(dev == WHITEOUT_DEV)) {
error = -EBUSY;
goto err;
}
error = kobj_map(cdev_map, dev, count, NULL,
exact_match, exact_lock, p);
if (error)
goto err;
kobject_get(p->kobj.parent);
return 0;
err:
kfree_const(p->kobj.name);
p->kobj.name = NULL;
return error;
}
/**
* cdev_set_parent() - set the parent kobject for a char device
* @p: the cdev structure
* @kobj: the kobject to take a reference to
*
* cdev_set_parent() sets a parent kobject which will be referenced
* appropriately so the parent is not freed before the cdev. This
* should be called before cdev_add.
*/
void cdev_set_parent(struct cdev *p, struct kobject *kobj)
{
WARN_ON(!kobj->state_initialized);
p->kobj.parent = kobj;
}
/**
* cdev_device_add() - add a char device and it's corresponding
* struct device, linkink
* @dev: the device structure
* @cdev: the cdev structure
*
* cdev_device_add() adds the char device represented by @cdev to the system,
* just as cdev_add does. It then adds @dev to the system using device_add
* The dev_t for the char device will be taken from the struct device which
* needs to be initialized first. This helper function correctly takes a
* reference to the parent device so the parent will not get released until
* all references to the cdev are released.
*
* This helper uses dev->devt for the device number. If it is not set
* it will not add the cdev and it will be equivalent to device_add.
*
* This function should be used whenever the struct cdev and the
* struct device are members of the same structure whose lifetime is
* managed by the struct device.
*
* NOTE: Callers must assume that userspace was able to open the cdev and
* can call cdev fops callbacks at any time, even if this function fails.
*/
int cdev_device_add(struct cdev *cdev, struct device *dev)
{
int rc = 0;
if (dev->devt) {
cdev_set_parent(cdev, &dev->kobj);
rc = cdev_add(cdev, dev->devt, 1);
if (rc)
return rc;
}
rc = device_add(dev);
if (rc && dev->devt)
cdev_del(cdev);
return rc;
}
/**
* cdev_device_del() - inverse of cdev_device_add
* @cdev: the cdev structure
* @dev: the device structure
*
* cdev_device_del() is a helper function to call cdev_del and device_del.
* It should be used whenever cdev_device_add is used.
*
* If dev->devt is not set it will not remove the cdev and will be equivalent
* to device_del.
*
* NOTE: This guarantees that associated sysfs callbacks are not running
* or runnable, however any cdevs already open will remain and their fops
* will still be callable even after this function returns.
*/
void cdev_device_del(struct cdev *cdev, struct device *dev)
{
device_del(dev);
if (dev->devt)
cdev_del(cdev);
}
static void cdev_unmap(dev_t dev, unsigned count)
{
kobj_unmap(cdev_map, dev, count);
}
/**
* cdev_del() - remove a cdev from the system
* @p: the cdev structure to be removed
*
* cdev_del() removes @p from the system, possibly freeing the structure
* itself.
*
* NOTE: This guarantees that cdev device will no longer be able to be
* opened, however any cdevs already open will remain and their fops will
* still be callable even after cdev_del returns.
*/
void cdev_del(struct cdev *p)
{
cdev_unmap(p->dev, p->count);
kobject_put(&p->kobj);
}
static void cdev_default_release(struct kobject *kobj)
{
struct cdev *p = container_of(kobj, struct cdev, kobj);
struct kobject *parent = kobj->parent;
cdev_purge(p);
kobject_put(parent);
}
static void cdev_dynamic_release(struct kobject *kobj)
{
struct cdev *p = container_of(kobj, struct cdev, kobj);
struct kobject *parent = kobj->parent;
cdev_purge(p);
kfree(p);
kobject_put(parent);
}
static struct kobj_type ktype_cdev_default = {
.release = cdev_default_release,
};
static struct kobj_type ktype_cdev_dynamic = {
.release = cdev_dynamic_release,
};
/**
* cdev_alloc() - allocate a cdev structure
*
* Allocates and returns a cdev structure, or NULL on failure.
*/
struct cdev *cdev_alloc(void)
{
struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL);
if (p) {
INIT_LIST_HEAD(&p->list);
kobject_init(&p->kobj, &ktype_cdev_dynamic);
}
return p;
}
/**
* cdev_init() - initialize a cdev structure
* @cdev: the structure to initialize
* @fops: the file_operations for this device
*
* Initializes @cdev, remembering @fops, making it ready to add to the
* system with cdev_add().
*/
void cdev_init(struct cdev *cdev, const struct file_operations *fops)
{
memset(cdev, 0, sizeof *cdev);
INIT_LIST_HEAD(&cdev->list);
kobject_init(&cdev->kobj, &ktype_cdev_default);
cdev->ops = fops;
}
static struct kobject *base_probe(dev_t dev, int *part, void *data)
{
if (request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
/* Make old-style 2.4 aliases work */
request_module("char-major-%d", MAJOR(dev));
return NULL;
}
void __init chrdev_init(void)
{
cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
}
/* Let modules do char dev stuff */
EXPORT_SYMBOL(register_chrdev_region);
EXPORT_SYMBOL(unregister_chrdev_region);
EXPORT_SYMBOL(alloc_chrdev_region);
EXPORT_SYMBOL(cdev_init);
EXPORT_SYMBOL(cdev_alloc);
EXPORT_SYMBOL(cdev_del);
EXPORT_SYMBOL(cdev_add);
EXPORT_SYMBOL(cdev_set_parent);
EXPORT_SYMBOL(cdev_device_add);
EXPORT_SYMBOL(cdev_device_del);
EXPORT_SYMBOL(__register_chrdev);
EXPORT_SYMBOL(__unregister_chrdev);
/*
* include/linux/topology.h
*
* Written by: Matthew Dobson, IBM Corporation
*
* Copyright (C) 2002, IBM Corp.
*
* All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*
* Send feedback to <colpatch@us.ibm.com>
*/
#ifndef _LINUX_TOPOLOGY_H
#define _LINUX_TOPOLOGY_H
#include <linux/arch_topology.h>
#include <linux/cpumask.h>
#include <linux/bitops.h>
#include <linux/mmzone.h>
#include <linux/smp.h>
#include <linux/percpu.h>
#include <asm/topology.h>
#ifndef nr_cpus_node
#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
#endif
#define for_each_node_with_cpus(node) \
for_each_online_node(node) \
if (nr_cpus_node(node))
int arch_update_cpu_topology(void);
/* Conform to ACPI 2.0 SLIT distance definitions */
#define LOCAL_DISTANCE 10
#define REMOTE_DISTANCE 20
#define DISTANCE_BITS 8
#ifndef node_distance
#define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE)
#endif
#ifndef RECLAIM_DISTANCE
/*
* If the distance between nodes in a system is larger than RECLAIM_DISTANCE
* (in whatever arch specific measurement units returned by node_distance())
* and node_reclaim_mode is enabled then the VM will only call node_reclaim()
* on nodes within this distance.
*/
#define RECLAIM_DISTANCE 30
#endif
/*
* The following tunable allows platforms to override the default node
* reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are
* sufficiently fast that the default value actually hurts
* performance.
*
* AMD EPYC machines use this because even though the 2-hop distance
* is 32 (3.2x slower than a local memory access) performance actually
* *improves* if allowed to reclaim memory and load balance tasks
* between NUMA nodes 2-hops apart.
*/
extern int __read_mostly node_reclaim_distance;
#ifndef PENALTY_FOR_NODE_WITH_CPUS
#define PENALTY_FOR_NODE_WITH_CPUS (1)
#endif
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DECLARE_PER_CPU(int, numa_node);
#ifndef numa_node_id
/* Returns the number of the current Node. */
static inline int numa_node_id(void)
{
return raw_cpu_read(numa_node);
}
#endif
#ifndef cpu_to_node
static inline int cpu_to_node(int cpu)
{
return per_cpu(numa_node, cpu);
}
#endif
#ifndef set_numa_node
static inline void set_numa_node(int node)
{
this_cpu_write(numa_node, node);
}
#endif
#ifndef set_cpu_numa_node
static inline void set_cpu_numa_node(int cpu, int node)
{
per_cpu(numa_node, cpu) = node;
}
#endif
#else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */
/* Returns the number of the current Node. */
#ifndef numa_node_id
static inline int numa_node_id(void)
{
return cpu_to_node(raw_smp_processor_id());
}
#endif
#endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
*/
DECLARE_PER_CPU(int, _numa_mem_);
#ifndef set_numa_mem
static inline void set_numa_mem(int node)
{
this_cpu_write(_numa_mem_, node);
}
#endif
#ifndef numa_mem_id
/* Returns the number of the nearest Node with memory */
static inline int numa_mem_id(void)
{
return raw_cpu_read(_numa_mem_);
}
#endif
#ifndef cpu_to_mem
static inline int cpu_to_mem(int cpu)
{
return per_cpu(_numa_mem_, cpu);
}
#endif
#ifndef set_cpu_numa_mem
static inline void set_cpu_numa_mem(int cpu, int node)
{
per_cpu(_numa_mem_, cpu) = node;
}
#endif
#else /* !CONFIG_HAVE_MEMORYLESS_NODES */
#ifndef numa_mem_id
/* Returns the number of the nearest Node with memory */
static inline int numa_mem_id(void)
{
return numa_node_id();
}
#endif
#ifndef cpu_to_mem
static inline int cpu_to_mem(int cpu)
{
return cpu_to_node(cpu);
}
#endif
#endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */
#if defined(topology_die_id) && defined(topology_die_cpumask)
#define TOPOLOGY_DIE_SYSFS
#endif
#if defined(topology_cluster_id) && defined(topology_cluster_cpumask)
#define TOPOLOGY_CLUSTER_SYSFS
#endif
#if defined(topology_book_id) && defined(topology_book_cpumask)
#define TOPOLOGY_BOOK_SYSFS
#endif
#if defined(topology_drawer_id) && defined(topology_drawer_cpumask)
#define TOPOLOGY_DRAWER_SYSFS
#endif
#ifndef topology_physical_package_id
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_die_id
#define topology_die_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_cluster_id
#define topology_cluster_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_core_id
#define topology_core_id(cpu) ((void)(cpu), 0)
#endif
#ifndef topology_book_id
#define topology_book_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_drawer_id
#define topology_drawer_id(cpu) ((void)(cpu), -1)
#endif
#ifndef topology_ppin
#define topology_ppin(cpu) ((void)(cpu), 0ull)
#endif
#ifndef topology_sibling_cpumask
#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_core_cpumask
#define topology_core_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_cluster_cpumask
#define topology_cluster_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_die_cpumask
#define topology_die_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_book_cpumask
#define topology_book_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_drawer_cpumask
#define topology_drawer_cpumask(cpu) cpumask_of(cpu)
#endif
#if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask)
static inline const struct cpumask *cpu_smt_mask(int cpu)
{
return topology_sibling_cpumask(cpu);
}
#endif
#ifndef topology_is_primary_thread
static inline bool topology_is_primary_thread(unsigned int cpu)
{
/*
* When disabling SMT, the primary thread of the SMT will remain
* enabled/active. Architectures that have a special primary thread
* (e.g. x86) need to override this function. Otherwise the first
* thread in the SMT can be made the primary thread.
*
* The sibling cpumask of an offline CPU always contains the CPU
* itself on architectures using the implementation of
* CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology.
* Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for
* building their topology have to check whether to use this default
* implementation or to override it.
*/
return cpu == cpumask_first(topology_sibling_cpumask(cpu));
}
#define topology_is_primary_thread topology_is_primary_thread
#endif
static inline const struct cpumask *cpu_cpu_mask(int cpu)
{
return cpumask_of_node(cpu_to_node(cpu));
}
#ifdef CONFIG_NUMA
int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node);
extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops);
#else
static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
{
return cpumask_nth_and(cpu, cpus, cpu_online_mask);
}
static inline const struct cpumask *
sched_numa_hop_mask(unsigned int node, unsigned int hops)
{
return ERR_PTR(-EOPNOTSUPP);
}
#endif /* CONFIG_NUMA */
/**
* for_each_node_numadist() - iterate over nodes in increasing distance
* order, starting from a given node
* @node: the iteration variable and the starting node.
* @unvisited: a nodemask to keep track of the unvisited nodes.
*
* This macro iterates over NUMA node IDs in increasing distance from the
* starting @node and yields MAX_NUMNODES when all the nodes have been
* visited.
*
* Note that by the time the loop completes, the @unvisited nodemask will
* be fully cleared, unless the loop exits early.
*
* The difference between for_each_node() and for_each_node_numadist() is
* that the former allows to iterate over nodes in numerical order, whereas
* the latter iterates over nodes in increasing order of distance.
*
* This complexity of this iterator is O(N^2), where N represents the
* number of nodes, as each iteration involves scanning all nodes to
* find the one with the shortest distance.
*
* Requires rcu_lock to be held.
*/
#define for_each_node_numadist(node, unvisited) \
for (int __start = (node), \
(node) = nearest_node_nodemask((__start), &(unvisited)); \
(node) < MAX_NUMNODES; \
node_clear((node), (unvisited)), \
(node) = nearest_node_nodemask((__start), &(unvisited)))
/**
* for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance
* from a given node.
* @mask: the iteration variable.
* @node: the NUMA node to start the search from.
*
* Requires rcu_lock to be held.
*
* Yields cpu_online_mask for @node == NUMA_NO_NODE.
*/
#define for_each_numa_hop_mask(mask, node) \
for (unsigned int __hops = 0; \
mask = (node != NUMA_NO_NODE || __hops) ? \
sched_numa_hop_mask(node, __hops) : \
cpu_online_mask, \
!IS_ERR_OR_NULL(mask); \
__hops++)
#endif /* _LINUX_TOPOLOGY_H */
// SPDX-License-Identifier: GPL-2.0
// Generated by scripts/atomic/gen-atomic-instrumented.sh
// DO NOT MODIFY THIS FILE DIRECTLY
/*
* This file provoides atomic operations with explicit instrumentation (e.g.
* KASAN, KCSAN), which should be used unless it is necessary to avoid
* instrumentation. Where it is necessary to aovid instrumenation, the
* raw_atomic*() operations should be used.
*/
#ifndef _LINUX_ATOMIC_INSTRUMENTED_H
#define _LINUX_ATOMIC_INSTRUMENTED_H
#include <linux/build_bug.h>
#include <linux/compiler.h>
#include <linux/instrumented.h>
/**
* atomic_read() - atomic load with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically loads the value of @v with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_read() there.
*
* Return: The value loaded from @v.
*/
static __always_inline int
atomic_read(const atomic_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic_read(v);
}
/**
* atomic_read_acquire() - atomic load with acquire ordering
* @v: pointer to atomic_t
*
* Atomically loads the value of @v with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_read_acquire() there.
*
* Return: The value loaded from @v.
*/
static __always_inline int
atomic_read_acquire(const atomic_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic_read_acquire(v);
}
/**
* atomic_set() - atomic set with relaxed ordering
* @v: pointer to atomic_t
* @i: int value to assign
*
* Atomically sets @v to @i with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_set() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_set(atomic_t *v, int i)
{
instrument_atomic_write(v, sizeof(*v));
raw_atomic_set(v, i);
}
/**
* atomic_set_release() - atomic set with release ordering
* @v: pointer to atomic_t
* @i: int value to assign
*
* Atomically sets @v to @i with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_set_release() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_set_release(atomic_t *v, int i)
{
kcsan_release();
instrument_atomic_write(v, sizeof(*v));
raw_atomic_set_release(v, i);
}
/**
* atomic_add() - atomic add with relaxed ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_add(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_add(i, v);
}
/**
* atomic_add_return() - atomic add with full ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_add_return(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_return(i, v);
}
/**
* atomic_add_return_acquire() - atomic add with acquire ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_add_return_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_return_acquire(i, v);
}
/**
* atomic_add_return_release() - atomic add with release ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_add_return_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_return_release(i, v);
}
/**
* atomic_add_return_relaxed() - atomic add with relaxed ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_add_return_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_return_relaxed(i, v);
}
/**
* atomic_fetch_add() - atomic add with full ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_add() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_add(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_add(i, v);
}
/**
* atomic_fetch_add_acquire() - atomic add with acquire ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_add_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_add_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_add_acquire(i, v);
}
/**
* atomic_fetch_add_release() - atomic add with release ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_add_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_add_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_add_release(i, v);
}
/**
* atomic_fetch_add_relaxed() - atomic add with relaxed ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_add_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_add_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_add_relaxed(i, v);
}
/**
* atomic_sub() - atomic subtract with relaxed ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_sub(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_sub(i, v);
}
/**
* atomic_sub_return() - atomic subtract with full ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_sub_return(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_sub_return(i, v);
}
/**
* atomic_sub_return_acquire() - atomic subtract with acquire ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_sub_return_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_sub_return_acquire(i, v);
}
/**
* atomic_sub_return_release() - atomic subtract with release ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_sub_return_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_sub_return_release(i, v);
}
/**
* atomic_sub_return_relaxed() - atomic subtract with relaxed ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_sub_return_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_sub_return_relaxed(i, v);
}
/**
* atomic_fetch_sub() - atomic subtract with full ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_sub() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_sub(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_sub(i, v);
}
/**
* atomic_fetch_sub_acquire() - atomic subtract with acquire ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_sub_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_sub_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_sub_acquire(i, v);
}
/**
* atomic_fetch_sub_release() - atomic subtract with release ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_sub_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_sub_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_sub_release(i, v);
}
/**
* atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_sub_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_sub_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_sub_relaxed(i, v);
}
/**
* atomic_inc() - atomic increment with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_inc(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_inc(v);
}
/**
* atomic_inc_return() - atomic increment with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_inc_return(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_return(v);
}
/**
* atomic_inc_return_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_inc_return_acquire(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_return_acquire(v);
}
/**
* atomic_inc_return_release() - atomic increment with release ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_inc_return_release(atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_return_release(v);
}
/**
* atomic_inc_return_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_inc_return_relaxed(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_return_relaxed(v);
}
/**
* atomic_fetch_inc() - atomic increment with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_inc() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_inc(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_inc(v);
}
/**
* atomic_fetch_inc_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_inc_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_inc_acquire(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_inc_acquire(v);
}
/**
* atomic_fetch_inc_release() - atomic increment with release ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_inc_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_inc_release(atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_inc_release(v);
}
/**
* atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_inc_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_inc_relaxed(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_inc_relaxed(v);
}
/**
* atomic_dec() - atomic decrement with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_dec(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_dec(v);
}
/**
* atomic_dec_return() - atomic decrement with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_dec_return(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_return(v);
}
/**
* atomic_dec_return_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_dec_return_acquire(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_return_acquire(v);
}
/**
* atomic_dec_return_release() - atomic decrement with release ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_dec_return_release(atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_return_release(v);
}
/**
* atomic_dec_return_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline int
atomic_dec_return_relaxed(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_return_relaxed(v);
}
/**
* atomic_fetch_dec() - atomic decrement with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_dec() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_dec(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_dec(v);
}
/**
* atomic_fetch_dec_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_dec_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_dec_acquire(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_dec_acquire(v);
}
/**
* atomic_fetch_dec_release() - atomic decrement with release ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_dec_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_dec_release(atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_dec_release(v);
}
/**
* atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_dec_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_dec_relaxed(atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_dec_relaxed(v);
}
/**
* atomic_and() - atomic bitwise AND with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_and() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_and(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_and(i, v);
}
/**
* atomic_fetch_and() - atomic bitwise AND with full ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_and() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_and(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_and(i, v);
}
/**
* atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_and_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_and_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_and_acquire(i, v);
}
/**
* atomic_fetch_and_release() - atomic bitwise AND with release ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_and_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_and_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_and_release(i, v);
}
/**
* atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_and_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_and_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_and_relaxed(i, v);
}
/**
* atomic_andnot() - atomic bitwise AND NOT with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_andnot() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_andnot(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_andnot(i, v);
}
/**
* atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & ~@i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_andnot() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_andnot(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_andnot(i, v);
}
/**
* atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & ~@i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_andnot_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_andnot_acquire(i, v);
}
/**
* atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & ~@i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_andnot_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_andnot_release(i, v);
}
/**
* atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_andnot_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_andnot_relaxed(i, v);
}
/**
* atomic_or() - atomic bitwise OR with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_or() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_or(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_or(i, v);
}
/**
* atomic_fetch_or() - atomic bitwise OR with full ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v | @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_or() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_or(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_or(i, v);
}
/**
* atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v | @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_or_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_or_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_or_acquire(i, v);
}
/**
* atomic_fetch_or_release() - atomic bitwise OR with release ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v | @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_or_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_or_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_or_release(i, v);
}
/**
* atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_or_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_or_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_or_relaxed(i, v);
}
/**
* atomic_xor() - atomic bitwise XOR with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_xor() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_xor(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_xor(i, v);
}
/**
* atomic_fetch_xor() - atomic bitwise XOR with full ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v ^ @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_xor() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_xor(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_xor(i, v);
}
/**
* atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v ^ @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_xor_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_xor_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_xor_acquire(i, v);
}
/**
* atomic_fetch_xor_release() - atomic bitwise XOR with release ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v ^ @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_xor_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_xor_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_xor_release(i, v);
}
/**
* atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
* @i: int value
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_xor_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_xor_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_xor_relaxed(i, v);
}
/**
* atomic_xchg() - atomic exchange with full ordering
* @v: pointer to atomic_t
* @new: int value to assign
*
* Atomically updates @v to @new with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_xchg() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_xchg(atomic_t *v, int new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_xchg(v, new);
}
/**
* atomic_xchg_acquire() - atomic exchange with acquire ordering
* @v: pointer to atomic_t
* @new: int value to assign
*
* Atomically updates @v to @new with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_xchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_xchg_acquire(atomic_t *v, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_xchg_acquire(v, new);
}
/**
* atomic_xchg_release() - atomic exchange with release ordering
* @v: pointer to atomic_t
* @new: int value to assign
*
* Atomically updates @v to @new with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_xchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_xchg_release(atomic_t *v, int new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_xchg_release(v, new);
}
/**
* atomic_xchg_relaxed() - atomic exchange with relaxed ordering
* @v: pointer to atomic_t
* @new: int value to assign
*
* Atomically updates @v to @new with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_xchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_xchg_relaxed(atomic_t *v, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_xchg_relaxed(v, new);
}
/**
* atomic_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_t
* @old: int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_cmpxchg(atomic_t *v, int old, int new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_cmpxchg(v, old, new);
}
/**
* atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_t
* @old: int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_cmpxchg_acquire(v, old, new);
}
/**
* atomic_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_t
* @old: int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_cmpxchg_release(atomic_t *v, int old, int new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_cmpxchg_release(v, old, new);
}
/**
* atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_t
* @old: int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_cmpxchg_relaxed(v, old, new);
}
/**
* atomic_try_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_t
* @old: pointer to int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_try_cmpxchg(atomic_t *v, int *old, int new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_try_cmpxchg(v, old, new);
}
/**
* atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_t
* @old: pointer to int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_try_cmpxchg_acquire(v, old, new);
}
/**
* atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_t
* @old: pointer to int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_try_cmpxchg_release(v, old, new);
}
/**
* atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_t
* @old: pointer to int value to compare with
* @new: int value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_try_cmpxchg_relaxed(v, old, new);
}
/**
* atomic_sub_and_test() - atomic subtract and test if zero with full ordering
* @i: int value to subtract
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_sub_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_sub_and_test(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_sub_and_test(i, v);
}
/**
* atomic_dec_and_test() - atomic decrement and test if zero with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_dec_and_test(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_and_test(v);
}
/**
* atomic_inc_and_test() - atomic increment and test if zero with full ordering
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_inc_and_test(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_and_test(v);
}
/**
* atomic_add_negative() - atomic add and test if negative with full ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_negative() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_add_negative(int i, atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_negative(i, v);
}
/**
* atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_negative_acquire() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_add_negative_acquire(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_negative_acquire(i, v);
}
/**
* atomic_add_negative_release() - atomic add and test if negative with release ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_negative_release() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_add_negative_release(int i, atomic_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_negative_release(i, v);
}
/**
* atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
* @i: int value to add
* @v: pointer to atomic_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_add_negative_relaxed() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_add_negative_relaxed(int i, atomic_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_negative_relaxed(i, v);
}
/**
* atomic_fetch_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_t
* @a: int value to add
* @u: int value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there.
*
* Return: The original value of @v.
*/
static __always_inline int
atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_fetch_add_unless(v, a, u);
}
/**
* atomic_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_t
* @a: int value to add
* @u: int value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_add_unless() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_add_unless(atomic_t *v, int a, int u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_add_unless(v, a, u);
}
/**
* atomic_inc_not_zero() - atomic increment unless zero with full ordering
* @v: pointer to atomic_t
*
* If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_inc_not_zero(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_not_zero(v);
}
/**
* atomic_inc_unless_negative() - atomic increment unless negative with full ordering
* @v: pointer to atomic_t
*
* If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_inc_unless_negative(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_inc_unless_negative(v);
}
/**
* atomic_dec_unless_positive() - atomic decrement unless positive with full ordering
* @v: pointer to atomic_t
*
* If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_dec_unless_positive(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_unless_positive(v);
}
/**
* atomic_dec_if_positive() - atomic decrement if positive with full ordering
* @v: pointer to atomic_t
*
* If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there.
*
* Return: The old value of (@v - 1), regardless of whether @v was updated.
*/
static __always_inline int
atomic_dec_if_positive(atomic_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_dec_if_positive(v);
}
/**
* atomic64_read() - atomic load with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically loads the value of @v with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_read() there.
*
* Return: The value loaded from @v.
*/
static __always_inline s64
atomic64_read(const atomic64_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic64_read(v);
}
/**
* atomic64_read_acquire() - atomic load with acquire ordering
* @v: pointer to atomic64_t
*
* Atomically loads the value of @v with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_read_acquire() there.
*
* Return: The value loaded from @v.
*/
static __always_inline s64
atomic64_read_acquire(const atomic64_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic64_read_acquire(v);
}
/**
* atomic64_set() - atomic set with relaxed ordering
* @v: pointer to atomic64_t
* @i: s64 value to assign
*
* Atomically sets @v to @i with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_set() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_set(atomic64_t *v, s64 i)
{
instrument_atomic_write(v, sizeof(*v));
raw_atomic64_set(v, i);
}
/**
* atomic64_set_release() - atomic set with release ordering
* @v: pointer to atomic64_t
* @i: s64 value to assign
*
* Atomically sets @v to @i with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_set_release() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_set_release(atomic64_t *v, s64 i)
{
kcsan_release();
instrument_atomic_write(v, sizeof(*v));
raw_atomic64_set_release(v, i);
}
/**
* atomic64_add() - atomic add with relaxed ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_add(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_add(i, v);
}
/**
* atomic64_add_return() - atomic add with full ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_add_return(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_return(i, v);
}
/**
* atomic64_add_return_acquire() - atomic add with acquire ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_add_return_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_return_acquire(i, v);
}
/**
* atomic64_add_return_release() - atomic add with release ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_add_return_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_return_release(i, v);
}
/**
* atomic64_add_return_relaxed() - atomic add with relaxed ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_add_return_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_return_relaxed(i, v);
}
/**
* atomic64_fetch_add() - atomic add with full ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_add() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_add(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_add(i, v);
}
/**
* atomic64_fetch_add_acquire() - atomic add with acquire ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_add_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_add_acquire(i, v);
}
/**
* atomic64_fetch_add_release() - atomic add with release ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_add_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_add_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_add_release(i, v);
}
/**
* atomic64_fetch_add_relaxed() - atomic add with relaxed ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_add_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_add_relaxed(i, v);
}
/**
* atomic64_sub() - atomic subtract with relaxed ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_sub(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_sub(i, v);
}
/**
* atomic64_sub_return() - atomic subtract with full ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_sub_return(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_sub_return(i, v);
}
/**
* atomic64_sub_return_acquire() - atomic subtract with acquire ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_sub_return_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_sub_return_acquire(i, v);
}
/**
* atomic64_sub_return_release() - atomic subtract with release ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_sub_return_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_sub_return_release(i, v);
}
/**
* atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_sub_return_relaxed(i, v);
}
/**
* atomic64_fetch_sub() - atomic subtract with full ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_sub() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_sub(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_sub(i, v);
}
/**
* atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_sub_acquire(i, v);
}
/**
* atomic64_fetch_sub_release() - atomic subtract with release ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_sub_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_sub_release(i, v);
}
/**
* atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_sub_relaxed(i, v);
}
/**
* atomic64_inc() - atomic increment with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_inc(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_inc(v);
}
/**
* atomic64_inc_return() - atomic increment with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_inc_return(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_return(v);
}
/**
* atomic64_inc_return_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_inc_return_acquire(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_return_acquire(v);
}
/**
* atomic64_inc_return_release() - atomic increment with release ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_inc_return_release(atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_return_release(v);
}
/**
* atomic64_inc_return_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_inc_return_relaxed(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_return_relaxed(v);
}
/**
* atomic64_fetch_inc() - atomic increment with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_inc() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_inc(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_inc(v);
}
/**
* atomic64_fetch_inc_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_inc_acquire(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_inc_acquire(v);
}
/**
* atomic64_fetch_inc_release() - atomic increment with release ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_inc_release(atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_inc_release(v);
}
/**
* atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_inc_relaxed(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_inc_relaxed(v);
}
/**
* atomic64_dec() - atomic decrement with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_dec(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_dec(v);
}
/**
* atomic64_dec_return() - atomic decrement with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_dec_return(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_return(v);
}
/**
* atomic64_dec_return_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_dec_return_acquire(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_return_acquire(v);
}
/**
* atomic64_dec_return_release() - atomic decrement with release ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_dec_return_release(atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_return_release(v);
}
/**
* atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline s64
atomic64_dec_return_relaxed(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_return_relaxed(v);
}
/**
* atomic64_fetch_dec() - atomic decrement with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_dec() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_dec(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_dec(v);
}
/**
* atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_dec_acquire(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_dec_acquire(v);
}
/**
* atomic64_fetch_dec_release() - atomic decrement with release ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_dec_release(atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_dec_release(v);
}
/**
* atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_dec_relaxed(atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_dec_relaxed(v);
}
/**
* atomic64_and() - atomic bitwise AND with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_and() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_and(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_and(i, v);
}
/**
* atomic64_fetch_and() - atomic bitwise AND with full ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_and() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_and(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_and(i, v);
}
/**
* atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_and_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_and_acquire(i, v);
}
/**
* atomic64_fetch_and_release() - atomic bitwise AND with release ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_and_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_and_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_and_release(i, v);
}
/**
* atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_and_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_and_relaxed(i, v);
}
/**
* atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_andnot() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_andnot(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_andnot(i, v);
}
/**
* atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & ~@i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_andnot(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_andnot(i, v);
}
/**
* atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & ~@i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_andnot_acquire(i, v);
}
/**
* atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & ~@i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_andnot_release(i, v);
}
/**
* atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_andnot_relaxed(i, v);
}
/**
* atomic64_or() - atomic bitwise OR with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_or() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_or(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_or(i, v);
}
/**
* atomic64_fetch_or() - atomic bitwise OR with full ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v | @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_or() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_or(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_or(i, v);
}
/**
* atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v | @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_or_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_or_acquire(i, v);
}
/**
* atomic64_fetch_or_release() - atomic bitwise OR with release ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v | @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_or_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_or_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_or_release(i, v);
}
/**
* atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_or_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_or_relaxed(i, v);
}
/**
* atomic64_xor() - atomic bitwise XOR with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_xor() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic64_xor(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic64_xor(i, v);
}
/**
* atomic64_fetch_xor() - atomic bitwise XOR with full ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v ^ @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_xor() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_xor(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_xor(i, v);
}
/**
* atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v ^ @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_xor_acquire(i, v);
}
/**
* atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v ^ @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_xor_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_xor_release(i, v);
}
/**
* atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
* @i: s64 value
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_xor_relaxed(i, v);
}
/**
* atomic64_xchg() - atomic exchange with full ordering
* @v: pointer to atomic64_t
* @new: s64 value to assign
*
* Atomically updates @v to @new with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_xchg() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_xchg(atomic64_t *v, s64 new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_xchg(v, new);
}
/**
* atomic64_xchg_acquire() - atomic exchange with acquire ordering
* @v: pointer to atomic64_t
* @new: s64 value to assign
*
* Atomically updates @v to @new with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_xchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_xchg_acquire(atomic64_t *v, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_xchg_acquire(v, new);
}
/**
* atomic64_xchg_release() - atomic exchange with release ordering
* @v: pointer to atomic64_t
* @new: s64 value to assign
*
* Atomically updates @v to @new with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_xchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_xchg_release(atomic64_t *v, s64 new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_xchg_release(v, new);
}
/**
* atomic64_xchg_relaxed() - atomic exchange with relaxed ordering
* @v: pointer to atomic64_t
* @new: s64 value to assign
*
* Atomically updates @v to @new with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_xchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_xchg_relaxed(atomic64_t *v, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_xchg_relaxed(v, new);
}
/**
* atomic64_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic64_t
* @old: s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_cmpxchg(v, old, new);
}
/**
* atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic64_t
* @old: s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_cmpxchg_acquire(v, old, new);
}
/**
* atomic64_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic64_t
* @old: s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_cmpxchg_release(v, old, new);
}
/**
* atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic64_t
* @old: s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_cmpxchg_relaxed(v, old, new);
}
/**
* atomic64_try_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic64_t
* @old: pointer to s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic64_try_cmpxchg(v, old, new);
}
/**
* atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic64_t
* @old: pointer to s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic64_try_cmpxchg_acquire(v, old, new);
}
/**
* atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic64_t
* @old: pointer to s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic64_try_cmpxchg_release(v, old, new);
}
/**
* atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic64_t
* @old: pointer to s64 value to compare with
* @new: s64 value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic64_try_cmpxchg_relaxed(v, old, new);
}
/**
* atomic64_sub_and_test() - atomic subtract and test if zero with full ordering
* @i: s64 value to subtract
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_sub_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic64_sub_and_test(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_sub_and_test(i, v);
}
/**
* atomic64_dec_and_test() - atomic decrement and test if zero with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic64_dec_and_test(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_and_test(v);
}
/**
* atomic64_inc_and_test() - atomic increment and test if zero with full ordering
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic64_inc_and_test(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_and_test(v);
}
/**
* atomic64_add_negative() - atomic add and test if negative with full ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_negative() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic64_add_negative(s64 i, atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_negative(i, v);
}
/**
* atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_negative_acquire() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic64_add_negative_acquire(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_negative_acquire(i, v);
}
/**
* atomic64_add_negative_release() - atomic add and test if negative with release ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_negative_release() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic64_add_negative_release(s64 i, atomic64_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_negative_release(i, v);
}
/**
* atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
* @i: s64 value to add
* @v: pointer to atomic64_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_negative_relaxed() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_negative_relaxed(i, v);
}
/**
* atomic64_fetch_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic64_t
* @a: s64 value to add
* @u: s64 value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there.
*
* Return: The original value of @v.
*/
static __always_inline s64
atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_fetch_add_unless(v, a, u);
}
/**
* atomic64_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic64_t
* @a: s64 value to add
* @u: s64 value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_add_unless() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_add_unless(v, a, u);
}
/**
* atomic64_inc_not_zero() - atomic increment unless zero with full ordering
* @v: pointer to atomic64_t
*
* If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic64_inc_not_zero(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_not_zero(v);
}
/**
* atomic64_inc_unless_negative() - atomic increment unless negative with full ordering
* @v: pointer to atomic64_t
*
* If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic64_inc_unless_negative(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_inc_unless_negative(v);
}
/**
* atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering
* @v: pointer to atomic64_t
*
* If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic64_dec_unless_positive(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_unless_positive(v);
}
/**
* atomic64_dec_if_positive() - atomic decrement if positive with full ordering
* @v: pointer to atomic64_t
*
* If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there.
*
* Return: The old value of (@v - 1), regardless of whether @v was updated.
*/
static __always_inline s64
atomic64_dec_if_positive(atomic64_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic64_dec_if_positive(v);
}
/**
* atomic_long_read() - atomic load with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically loads the value of @v with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_read() there.
*
* Return: The value loaded from @v.
*/
static __always_inline long
atomic_long_read(const atomic_long_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic_long_read(v);
}
/**
* atomic_long_read_acquire() - atomic load with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically loads the value of @v with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_read_acquire() there.
*
* Return: The value loaded from @v.
*/
static __always_inline long
atomic_long_read_acquire(const atomic_long_t *v)
{
instrument_atomic_read(v, sizeof(*v));
return raw_atomic_long_read_acquire(v);
}
/**
* atomic_long_set() - atomic set with relaxed ordering
* @v: pointer to atomic_long_t
* @i: long value to assign
*
* Atomically sets @v to @i with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_set() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_set(atomic_long_t *v, long i)
{
instrument_atomic_write(v, sizeof(*v));
raw_atomic_long_set(v, i);
}
/**
* atomic_long_set_release() - atomic set with release ordering
* @v: pointer to atomic_long_t
* @i: long value to assign
*
* Atomically sets @v to @i with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_set_release() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_set_release(atomic_long_t *v, long i)
{
kcsan_release();
instrument_atomic_write(v, sizeof(*v));
raw_atomic_long_set_release(v, i);
}
/**
* atomic_long_add() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_add(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_add(i, v);
}
/**
* atomic_long_add_return() - atomic add with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_add_return(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_return(i, v);
}
/**
* atomic_long_add_return_acquire() - atomic add with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_add_return_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_return_acquire(i, v);
}
/**
* atomic_long_add_return_release() - atomic add with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_add_return_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_return_release(i, v);
}
/**
* atomic_long_add_return_relaxed() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_add_return_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_return_relaxed(i, v);
}
/**
* atomic_long_fetch_add() - atomic add with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_add() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_add(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_add(i, v);
}
/**
* atomic_long_fetch_add_acquire() - atomic add with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_add_acquire(i, v);
}
/**
* atomic_long_fetch_add_release() - atomic add with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_add_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_add_release(i, v);
}
/**
* atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_add_relaxed(i, v);
}
/**
* atomic_long_sub() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_sub(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_sub(i, v);
}
/**
* atomic_long_sub_return() - atomic subtract with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_sub_return(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_sub_return(i, v);
}
/**
* atomic_long_sub_return_acquire() - atomic subtract with acquire ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_sub_return_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_sub_return_acquire(i, v);
}
/**
* atomic_long_sub_return_release() - atomic subtract with release ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_sub_return_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_sub_return_release(i, v);
}
/**
* atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_sub_return_relaxed(i, v);
}
/**
* atomic_long_fetch_sub() - atomic subtract with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_sub(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_sub(i, v);
}
/**
* atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_sub_acquire(i, v);
}
/**
* atomic_long_fetch_sub_release() - atomic subtract with release ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_sub_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_sub_release(i, v);
}
/**
* atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_sub_relaxed(i, v);
}
/**
* atomic_long_inc() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_inc(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_inc(v);
}
/**
* atomic_long_inc_return() - atomic increment with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_inc_return(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_return(v);
}
/**
* atomic_long_inc_return_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_inc_return_acquire(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_return_acquire(v);
}
/**
* atomic_long_inc_return_release() - atomic increment with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_inc_return_release(atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_return_release(v);
}
/**
* atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_inc_return_relaxed(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_return_relaxed(v);
}
/**
* atomic_long_fetch_inc() - atomic increment with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_inc(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_inc(v);
}
/**
* atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_inc_acquire(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_inc_acquire(v);
}
/**
* atomic_long_fetch_inc_release() - atomic increment with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_inc_release(atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_inc_release(v);
}
/**
* atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_inc_relaxed(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_inc_relaxed(v);
}
/**
* atomic_long_dec() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_dec(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_dec(v);
}
/**
* atomic_long_dec_return() - atomic decrement with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_return() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_dec_return(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_return(v);
}
/**
* atomic_long_dec_return_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_return_acquire() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_dec_return_acquire(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_return_acquire(v);
}
/**
* atomic_long_dec_return_release() - atomic decrement with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_return_release() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_dec_return_release(atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_return_release(v);
}
/**
* atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_return_relaxed() there.
*
* Return: The updated value of @v.
*/
static __always_inline long
atomic_long_dec_return_relaxed(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_return_relaxed(v);
}
/**
* atomic_long_fetch_dec() - atomic decrement with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_dec(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_dec(v);
}
/**
* atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_dec_acquire(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_dec_acquire(v);
}
/**
* atomic_long_fetch_dec_release() - atomic decrement with release ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_dec_release(atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_dec_release(v);
}
/**
* atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_dec_relaxed(atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_dec_relaxed(v);
}
/**
* atomic_long_and() - atomic bitwise AND with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_and() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_and(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_and(i, v);
}
/**
* atomic_long_fetch_and() - atomic bitwise AND with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_and() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_and(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_and(i, v);
}
/**
* atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_and_acquire(i, v);
}
/**
* atomic_long_fetch_and_release() - atomic bitwise AND with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_and_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_and_release(i, v);
}
/**
* atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_and_relaxed(i, v);
}
/**
* atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_andnot() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_andnot(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_andnot(i, v);
}
/**
* atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_andnot(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_andnot(i, v);
}
/**
* atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_andnot_acquire(i, v);
}
/**
* atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_andnot_release(i, v);
}
/**
* atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v & ~@i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_andnot_relaxed(i, v);
}
/**
* atomic_long_or() - atomic bitwise OR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_or() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_or(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_or(i, v);
}
/**
* atomic_long_fetch_or() - atomic bitwise OR with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_or() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_or(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_or(i, v);
}
/**
* atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_or_acquire(i, v);
}
/**
* atomic_long_fetch_or_release() - atomic bitwise OR with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_or_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_or_release(i, v);
}
/**
* atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v | @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_or_relaxed(i, v);
}
/**
* atomic_long_xor() - atomic bitwise XOR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_xor() there.
*
* Return: Nothing.
*/
static __always_inline void
atomic_long_xor(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
raw_atomic_long_xor(i, v);
}
/**
* atomic_long_fetch_xor() - atomic bitwise XOR with full ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_xor(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_xor(i, v);
}
/**
* atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_xor_acquire(i, v);
}
/**
* atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_xor_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_xor_release(i, v);
}
/**
* atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
* @i: long value
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v ^ @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_xor_relaxed(i, v);
}
/**
* atomic_long_xchg() - atomic exchange with full ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_xchg() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_xchg(atomic_long_t *v, long new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_xchg(v, new);
}
/**
* atomic_long_xchg_acquire() - atomic exchange with acquire ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_xchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_xchg_acquire(atomic_long_t *v, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_xchg_acquire(v, new);
}
/**
* atomic_long_xchg_release() - atomic exchange with release ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_xchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_xchg_release(atomic_long_t *v, long new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_xchg_release(v, new);
}
/**
* atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @new: long value to assign
*
* Atomically updates @v to @new with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_xchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_xchg_relaxed(atomic_long_t *v, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_xchg_relaxed(v, new);
}
/**
* atomic_long_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_cmpxchg(v, old, new);
}
/**
* atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_cmpxchg_acquire(v, old, new);
}
/**
* atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_cmpxchg_release(v, old, new);
}
/**
* atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @old: long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_cmpxchg_relaxed(v, old, new);
}
/**
* atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with full ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_long_try_cmpxchg(v, old, new);
}
/**
* atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with acquire ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_long_try_cmpxchg_acquire(v, old, new);
}
/**
* atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with release ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_long_try_cmpxchg_release(v, old, new);
}
/**
* atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
* @v: pointer to atomic_long_t
* @old: pointer to long value to compare with
* @new: long value to assign
*
* If (@v == @old), atomically updates @v to @new with relaxed ordering.
* Otherwise, @v is not modified, @old is updated to the current value of @v,
* and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there.
*
* Return: @true if the exchange occured, @false otherwise.
*/
static __always_inline bool
atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
{
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return raw_atomic_long_try_cmpxchg_relaxed(v, old, new);
}
/**
* atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering
* @i: long value to subtract
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_sub_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_long_sub_and_test(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_sub_and_test(i, v);
}
/**
* atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v - 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_long_dec_and_test(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_and_test(v);
}
/**
* atomic_long_inc_and_test() - atomic increment and test if zero with full ordering
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + 1) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_and_test() there.
*
* Return: @true if the resulting value of @v is zero, @false otherwise.
*/
static __always_inline bool
atomic_long_inc_and_test(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_and_test(v);
}
/**
* atomic_long_add_negative() - atomic add and test if negative with full ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with full ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_negative() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_long_add_negative(long i, atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_negative(i, v);
}
/**
* atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with acquire ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_negative_acquire() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_long_add_negative_acquire(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_negative_acquire(i, v);
}
/**
* atomic_long_add_negative_release() - atomic add and test if negative with release ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with release ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_negative_release() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_long_add_negative_release(long i, atomic_long_t *v)
{
kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_negative_release(i, v);
}
/**
* atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
* @i: long value to add
* @v: pointer to atomic_long_t
*
* Atomically updates @v to (@v + @i) with relaxed ordering.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_negative_relaxed() there.
*
* Return: @true if the resulting value of @v is negative, @false otherwise.
*/
static __always_inline bool
atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
{
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_negative_relaxed(i, v);
}
/**
* atomic_long_fetch_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_long_t
* @a: long value to add
* @u: long value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there.
*
* Return: The original value of @v.
*/
static __always_inline long
atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_fetch_add_unless(v, a, u);
}
/**
* atomic_long_add_unless() - atomic add unless value with full ordering
* @v: pointer to atomic_long_t
* @a: long value to add
* @u: long value to compare with
*
* If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_long_add_unless(atomic_long_t *v, long a, long u)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_add_unless(v, a, u);
}
/**
* atomic_long_inc_not_zero() - atomic increment unless zero with full ordering
* @v: pointer to atomic_long_t
*
* If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_long_inc_not_zero(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_not_zero(v);
}
/**
* atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering
* @v: pointer to atomic_long_t
*
* If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_long_inc_unless_negative(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_inc_unless_negative(v);
}
/**
* atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering
* @v: pointer to atomic_long_t
*
* If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there.
*
* Return: @true if @v was updated, @false otherwise.
*/
static __always_inline bool
atomic_long_dec_unless_positive(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_unless_positive(v);
}
/**
* atomic_long_dec_if_positive() - atomic decrement if positive with full ordering
* @v: pointer to atomic_long_t
*
* If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
* Otherwise, @v is not modified and relaxed ordering is provided.
*
* Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there.
*
* Return: The old value of (@v - 1), regardless of whether @v was updated.
*/
static __always_inline long
atomic_long_dec_if_positive(atomic_long_t *v)
{
kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return raw_atomic_long_dec_if_positive(v);
}
#define xchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_xchg(__ai_ptr, __VA_ARGS__); \
})
#define xchg_acquire(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_xchg_acquire(__ai_ptr, __VA_ARGS__); \
})
#define xchg_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_xchg_release(__ai_ptr, __VA_ARGS__); \
})
#define xchg_relaxed(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_xchg_relaxed(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg_acquire(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg_relaxed(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg64(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg64(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg64_acquire(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg64_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg64_relaxed(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg128(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg128(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg128_acquire(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg128_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg128_relaxed(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \
})
#define try_cmpxchg(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg_acquire(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg_release(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg_relaxed(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg64(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg64_acquire(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg64_release(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg64_relaxed(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg128(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg128_acquire(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg128_release(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
kcsan_release(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg128_relaxed(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define cmpxchg_local(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg_local(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg64_local(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
})
#define cmpxchg128_local(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \
})
#define sync_cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
#define try_cmpxchg_local(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg64_local(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define try_cmpxchg128_local(ptr, oldp, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
})
#define sync_try_cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
// 8829b337928e9508259079d32581775ececd415b
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/filemap.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* This file handles the generic file mmap semantics used by
* most "normal" filesystems (but you don't /have/ to use this:
* the NFS filesystem used to do this differently, for example)
*/
#include <linux/export.h>
#include <linux/compiler.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/syscalls.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/error-injection.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/security.h>
#include <linux/cpuset.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
#include <linux/delayacct.h>
#include <linux/psi.h>
#include <linux/ramfs.h>
#include <linux/page_idle.h>
#include <linux/migrate.h>
#include <linux/pipe_fs_i.h>
#include <linux/splice.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched/mm.h>
#include <linux/sysctl.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/filemap.h>
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
#include <linux/buffer_head.h> /* for try_to_free_buffers */
#include <asm/mman.h>
#include "swap.h"
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
* though.
*
* Shared mappings now work. 15.8.1995 Bruno.
*
* finished 'unifying' the page and buffer cache and SMP-threaded the
* page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
*
* SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
*/
/*
* Lock ordering:
*
* ->i_mmap_rwsem (truncate_pagecache)
* ->private_lock (__free_pte->block_dirty_folio)
* ->swap_lock (exclusive_swap_page, others)
* ->i_pages lock
*
* ->i_rwsem
* ->invalidate_lock (acquired by fs in truncate path)
* ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
* ->mmap_lock
* ->i_mmap_rwsem
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_lock
* ->invalidate_lock (filemap_fault)
* ->lock_page (filemap_fault, access_process_vm)
*
* ->i_rwsem (generic_perform_write)
* ->mmap_lock (fault_in_readable->do_page_fault)
*
* bdi->wb.list_lock
* sb_lock (fs/fs-writeback.c)
* ->i_pages lock (__sync_single_inode)
*
* ->i_mmap_rwsem
* ->anon_vma.lock (vma_merge)
*
* ->anon_vma.lock
* ->page_table_lock or pte_lock (anon_vma_prepare and various)
*
* ->page_table_lock or pte_lock
* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->i_pages lock (try_to_unmap_one)
* ->lruvec->lru_lock (follow_page_mask->mark_page_accessed)
* ->lruvec->lru_lock (check_pte_range->folio_isolate_lru)
* ->private_lock (folio_remove_rmap_pte->set_page_dirty)
* ->i_pages lock (folio_remove_rmap_pte->set_page_dirty)
* bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty)
* ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty)
* bdi.wb->list_lock (zap_pte_range->set_page_dirty)
* ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->block_dirty_folio)
*/
static void page_cache_delete(struct address_space *mapping,
struct folio *folio, void *shadow)
{
XA_STATE(xas, &mapping->i_pages, folio->index);
long nr = 1;
mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow);
xas_init_marks(&xas);
folio->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
mapping->nrpages -= nr;
}
static void filemap_unaccount_folio(struct address_space *mapping,
struct folio *folio)
{
long nr;
VM_BUG_ON_FOLIO(folio_mapped(folio), folio);
if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) {
pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n",
current->comm, folio_pfn(folio));
dump_page(&folio->page, "still mapped when deleted");
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
if (mapping_exiting(mapping) && !folio_test_large(folio)) {
int mapcount = folio_mapcount(folio);
if (folio_ref_count(folio) >= mapcount + 2) {
/*
* All vmas have already been torn down, so it's
* a good bet that actually the page is unmapped
* and we'd rather not leak it: if we're wrong,
* another bad page check should catch it later.
*/
atomic_set(&folio->_mapcount, -1);
folio_ref_sub(folio, mapcount);
}
}
}
/* hugetlb folios do not participate in page cache accounting. */
if (folio_test_hugetlb(folio))
return;
nr = folio_nr_pages(folio);
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
if (folio_test_swapbacked(folio)) {
__lruvec_stat_mod_folio(folio, NR_SHMEM, -nr);
if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) {
__lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr);
filemap_nr_thps_dec(mapping);
}
/*
* At this point folio must be either written or cleaned by
* truncate. Dirty folio here signals a bug and loss of
* unwritten data - on ordinary filesystems.
*
* But it's harmless on in-memory filesystems like tmpfs; and can
* occur when a driver which did get_user_pages() sets page dirty
* before putting it, while the inode is being finally evicted.
*
* Below fixes dirty accounting after removing the folio entirely
* but leaves the dirty flag set: it has no effect for truncated
* folio and anyway will be cleared before returning folio to
* buddy allocator.
*/
if (WARN_ON_ONCE(folio_test_dirty(folio) &&
mapping_can_writeback(mapping)))
folio_account_cleaned(folio, inode_to_wb(mapping->host));
}
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the i_pages lock.
*/
void __filemap_remove_folio(struct folio *folio, void *shadow)
{
struct address_space *mapping = folio->mapping;
trace_mm_filemap_delete_from_page_cache(folio);
filemap_unaccount_folio(mapping, folio);
page_cache_delete(mapping, folio, shadow);
}
void filemap_free_folio(struct address_space *mapping, struct folio *folio)
{
void (*free_folio)(struct folio *);
free_folio = mapping->a_ops->free_folio;
if (free_folio) free_folio(folio); folio_put_refs(folio, folio_nr_pages(folio));
}
/**
* filemap_remove_folio - Remove folio from page cache.
* @folio: The folio.
*
* This must be called only on folios that are locked and have been
* verified to be in the page cache. It will never put the folio into
* the free list because the caller has a reference on the page.
*/
void filemap_remove_folio(struct folio *folio)
{
struct address_space *mapping = folio->mapping;
BUG_ON(!folio_test_locked(folio));
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
__filemap_remove_folio(folio, NULL);
xa_unlock_irq(&mapping->i_pages);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
filemap_free_folio(mapping, folio);
}
/*
* page_cache_delete_batch - delete several folios from page cache
* @mapping: the mapping to which folios belong
* @fbatch: batch of folios to delete
*
* The function walks over mapping->i_pages and removes folios passed in
* @fbatch from the mapping. The function expects @fbatch to be sorted
* by page index and is optimised for it to be dense.
* It tolerates holes in @fbatch (mapping entries at those indices are not
* modified).
*
* The function expects the i_pages lock to be held.
*/
static void page_cache_delete_batch(struct address_space *mapping,
struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index);
long total_pages = 0;
int i = 0;
struct folio *folio;
mapping_set_update(&xas, mapping);
xas_for_each(&xas, folio, ULONG_MAX) {
if (i >= folio_batch_count(fbatch))
break;
/* A swap/dax/shadow entry got inserted? Skip it. */
if (xa_is_value(folio))
continue;
/*
* A page got inserted in our range? Skip it. We have our
* pages locked so they are protected from being removed.
* If we see a page whose index is higher than ours, it
* means our page has been removed, which shouldn't be
* possible because we're holding the PageLock.
*/
if (folio != fbatch->folios[i]) {
VM_BUG_ON_FOLIO(folio->index >
fbatch->folios[i]->index, folio);
continue;
}
WARN_ON_ONCE(!folio_test_locked(folio));
folio->mapping = NULL;
/* Leave folio->index set: truncation lookup relies on it */
i++;
xas_store(&xas, NULL);
total_pages += folio_nr_pages(folio);
}
mapping->nrpages -= total_pages;
}
void delete_from_page_cache_batch(struct address_space *mapping,
struct folio_batch *fbatch)
{
int i;
if (!folio_batch_count(fbatch))
return;
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
for (i = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
trace_mm_filemap_delete_from_page_cache(folio);
filemap_unaccount_folio(mapping, folio);
}
page_cache_delete_batch(mapping, fbatch);
xa_unlock_irq(&mapping->i_pages);
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
for (i = 0; i < folio_batch_count(fbatch); i++)
filemap_free_folio(mapping, fbatch->folios[i]);
}
int filemap_check_errors(struct address_space *mapping)
{
int ret = 0;
/* Check for outstanding write errors */
if (test_bit(AS_ENOSPC, &mapping->flags) &&
test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
if (test_bit(AS_EIO, &mapping->flags) &&
test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(filemap_check_errors);
static int filemap_check_and_keep_errors(struct address_space *mapping)
{
/* Check for outstanding write errors */
if (test_bit(AS_EIO, &mapping->flags))
return -EIO;
if (test_bit(AS_ENOSPC, &mapping->flags))
return -ENOSPC;
return 0;
}
/**
* filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @wbc: the writeback_control controlling the writeout
*
* Call writepages on the mapping using the provided wbc to control the
* writeout.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_fdatawrite_wbc(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret;
if (!mapping_can_writeback(mapping) ||
!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
wbc_attach_fdatawrite_inode(wbc, mapping->host);
ret = do_writepages(mapping, wbc);
wbc_detach_inode(wbc);
return ret;
}
EXPORT_SYMBOL(filemap_fdatawrite_wbc);
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
* @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* Start writeback against all of a mapping's dirty pages that lie
* within the byte offsets <start, end> inclusive.
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
*
* Return: %0 on success, negative error code otherwise.
*/
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
return filemap_fdatawrite_wbc(mapping, &wbc);
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
int sync_mode)
{
return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}
int filemap_fdatawrite(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);
int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);
/**
* filemap_fdatawrite_range_kick - start writeback on a range
* @mapping: target address_space
* @start: index to start writeback on
* @end: last (inclusive) index for writeback
*
* This is a non-integrity writeback helper, to start writing back folios
* for the indicated range.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
}
EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
/**
* filemap_flush - mostly a non-blocking flush
* @mapping: target address_space
*
* This is a mostly non-blocking flush. Not suitable for data-integrity
* purposes - I/O may not be started against all dirty pages.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);
/**
* filemap_range_has_page - check if a page exists in range.
* @mapping: address space within which to check
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Find at least one page in the range supplied, usually used to check if
* direct writing in this range will trigger a writeback.
*
* Return: %true if at least one page exists in the specified range,
* %false otherwise.
*/
bool filemap_range_has_page(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
struct folio *folio;
XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
pgoff_t max = end_byte >> PAGE_SHIFT;
if (end_byte < start_byte)
return false;
rcu_read_lock();
for (;;) {
folio = xas_find(&xas, max);
if (xas_retry(&xas, folio))
continue;
/* Shadow entries don't count */
if (xa_is_value(folio))
continue;
/*
* We don't need to try to pin this page; we're about to
* release the RCU lock anyway. It is enough to know that
* there was a page here recently.
*/
break;
}
rcu_read_unlock();
return folio != NULL;
}
EXPORT_SYMBOL(filemap_range_has_page);
static void __filemap_fdatawait_range(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
pgoff_t index = start_byte >> PAGE_SHIFT;
pgoff_t end = end_byte >> PAGE_SHIFT;
struct folio_batch fbatch;
unsigned nr_folios;
folio_batch_init(&fbatch);
while (index <= end) {
unsigned i;
nr_folios = filemap_get_folios_tag(mapping, &index, end,
PAGECACHE_TAG_WRITEBACK, &fbatch);
if (!nr_folios)
break;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
folio_wait_writeback(folio);
}
folio_batch_release(&fbatch);
cond_resched();
}
}
/**
* filemap_fdatawait_range - wait for writeback to complete
* @mapping: address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the given address space
* in the given range and wait for all of them. Check error status of
* the address space and return it.
*
* Since the error status of the address space is cleared by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space.
*/
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range);
/**
* filemap_fdatawait_range_keep_errors - wait for writeback to complete
* @mapping: address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the given address space in the
* given range and wait for all of them. Unlike filemap_fdatawait_range(),
* this function does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*/
int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
/**
* file_fdatawait_range - wait for writeback to complete
* @file: file pointing to address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the address space that file
* refers to, in the given range and wait for all of them. Check error
* status of the address space vs. the file->f_wb_err cursor and return it.
*
* Since the error status of the file is advanced by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space vs. the file->f_wb_err cursor.
*/
int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
{
struct address_space *mapping = file->f_mapping;
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return file_check_and_advance_wb_err(file);
}
EXPORT_SYMBOL(file_fdatawait_range);
/**
* filemap_fdatawait_keep_errors - wait for writeback without clearing errors
* @mapping: address space structure to wait for
*
* Walk the list of under-writeback pages of the given address space
* and wait for all of them. Unlike filemap_fdatawait(), this function
* does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*
* Return: error status of the address space.
*/
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
__filemap_fdatawait_range(mapping, 0, LLONG_MAX);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
/* Returns true if writeback might be needed or already in progress. */
static bool mapping_needs_writeback(struct address_space *mapping)
{
return mapping->nrpages;
}
bool filemap_range_has_writeback(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
pgoff_t max = end_byte >> PAGE_SHIFT;
struct folio *folio;
if (end_byte < start_byte)
return false;
rcu_read_lock();
xas_for_each(&xas, folio, max) {
if (xas_retry(&xas, folio))
continue;
if (xa_is_value(folio))
continue;
if (folio_test_dirty(folio) || folio_test_locked(folio) ||
folio_test_writeback(folio))
break;
}
rcu_read_unlock();
return folio != NULL;
}
EXPORT_SYMBOL_GPL(filemap_range_has_writeback);
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that @lend is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*
* Return: error status of the address space.
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
int err = 0, err2;
if (lend < lstart)
return 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/*
* Even if the above returned error, the pages may be
* written partially (e.g. -ENOSPC), so we wait for it.
* But the -EIO is special case, it may indicate the worst
* thing (e.g. bug) happened, so we avoid waiting for it.
*/
if (err != -EIO)
__filemap_fdatawait_range(mapping, lstart, lend);
}
err2 = filemap_check_errors(mapping);
if (!err)
err = err2;
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait_range);
void __filemap_set_wb_err(struct address_space *mapping, int err)
{
errseq_t eseq = errseq_set(&mapping->wb_err, err);
trace_filemap_set_wb_err(mapping, eseq);
}
EXPORT_SYMBOL(__filemap_set_wb_err);
/**
* file_check_and_advance_wb_err - report wb error (if any) that was previously
* and advance wb_err to current one
* @file: struct file on which the error is being reported
*
* When userland calls fsync (or something like nfsd does the equivalent), we
* want to report any writeback errors that occurred since the last fsync (or
* since the file was opened if there haven't been any).
*
* Grab the wb_err from the mapping. If it matches what we have in the file,
* then just quickly return 0. The file is all caught up.
*
* If it doesn't match, then take the mapping value, set the "seen" flag in
* it and try to swap it into place. If it works, or another task beat us
* to it with the new value, then update the f_wb_err and return the error
* portion. The error at this point must be reported via proper channels
* (a'la fsync, or NFS COMMIT operation, etc.).
*
* While we handle mapping->wb_err with atomic operations, the f_wb_err
* value is protected by the f_lock since we must ensure that it reflects
* the latest value swapped in for this file descriptor.
*
* Return: %0 on success, negative error code otherwise.
*/
int file_check_and_advance_wb_err(struct file *file)
{
int err = 0;
errseq_t old = READ_ONCE(file->f_wb_err);
struct address_space *mapping = file->f_mapping;
/* Locklessly handle the common case where nothing has changed */
if (errseq_check(&mapping->wb_err, old)) {
/* Something changed, must use slow path */
spin_lock(&file->f_lock);
old = file->f_wb_err;
err = errseq_check_and_advance(&mapping->wb_err,
&file->f_wb_err);
trace_file_check_and_advance_wb_err(file, old);
spin_unlock(&file->f_lock);
}
/*
* We're mostly using this function as a drop in replacement for
* filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
* that the legacy code would have had on these flags.
*/
clear_bit(AS_EIO, &mapping->flags);
clear_bit(AS_ENOSPC, &mapping->flags);
return err;
}
EXPORT_SYMBOL(file_check_and_advance_wb_err);
/**
* file_write_and_wait_range - write out & wait on a file range
* @file: file pointing to address_space with pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that @lend is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*
* After writing out and waiting on the data, we check and advance the
* f_wb_err cursor to the latest value, and return any errors detected there.
*
* Return: %0 on success, negative error code otherwise.
*/
int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
{
int err = 0, err2;
struct address_space *mapping = file->f_mapping;
if (lend < lstart)
return 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO)
__filemap_fdatawait_range(mapping, lstart, lend);
}
err2 = file_check_and_advance_wb_err(file);
if (!err)
err = err2;
return err;
}
EXPORT_SYMBOL(file_write_and_wait_range);
/**
* replace_page_cache_folio - replace a pagecache folio with a new one
* @old: folio to be replaced
* @new: folio to replace with
*
* This function replaces a folio in the pagecache with a new one. On
* success it acquires the pagecache reference for the new folio and
* drops it for the old folio. Both the old and new folios must be
* locked. This function does not add the new folio to the LRU, the
* caller must do that.
*
* The remove + add is atomic. This function cannot fail.
*/
void replace_page_cache_folio(struct folio *old, struct folio *new)
{
struct address_space *mapping = old->mapping;
void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
pgoff_t offset = old->index;
XA_STATE(xas, &mapping->i_pages, offset);
VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
VM_BUG_ON_FOLIO(new->mapping, new);
folio_get(new);
new->mapping = mapping;
new->index = offset;
mem_cgroup_replace_folio(old, new);
xas_lock_irq(&xas);
xas_store(&xas, new);
old->mapping = NULL;
/* hugetlb pages do not participate in page cache accounting. */
if (!folio_test_hugetlb(old))
__lruvec_stat_sub_folio(old, NR_FILE_PAGES);
if (!folio_test_hugetlb(new))
__lruvec_stat_add_folio(new, NR_FILE_PAGES);
if (folio_test_swapbacked(old))
__lruvec_stat_sub_folio(old, NR_SHMEM);
if (folio_test_swapbacked(new))
__lruvec_stat_add_folio(new, NR_SHMEM);
xas_unlock_irq(&xas);
if (free_folio)
free_folio(old);
folio_put(old);
}
EXPORT_SYMBOL_GPL(replace_page_cache_folio);
noinline int __filemap_add_folio(struct address_space *mapping,
struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
{ XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio));
bool huge;
long nr;
unsigned int forder = folio_order(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping),
folio);
mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
huge = folio_test_hugetlb(folio);
nr = folio_nr_pages(folio);
gfp &= GFP_RECLAIM_MASK;
folio_ref_add(folio, nr);
folio->mapping = mapping;
folio->index = xas.xa_index;
for (;;) {
int order = -1;
void *entry, *old = NULL;
xas_lock_irq(&xas);
xas_for_each_conflict(&xas, entry) {
old = entry;
if (!xa_is_value(entry)) {
xas_set_err(&xas, -EEXIST);
goto unlock;
}
/*
* If a larger entry exists,
* it will be the first and only entry iterated.
*/
if (order == -1) order = xas_get_order(&xas);
}
if (old) {
if (order > 0 && order > forder) {
unsigned int split_order = max(forder,
xas_try_split_min_order(order));
/* How to handle large swap entries? */
BUG_ON(shmem_mapping(mapping)); while (order > forder) {
xas_set_order(&xas, index, split_order);
xas_try_split(&xas, old, order);
if (xas_error(&xas))
goto unlock;
order = split_order;
split_order =
max(xas_try_split_min_order(
split_order),
forder);
}
xas_reset(&xas);
}
if (shadowp) *shadowp = old;
}
xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
mapping->nrpages += nr;
/* hugetlb pages do not participate in page cache accounting */
if (!huge) {
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio,
NR_FILE_THPS, nr);
}
unlock:
xas_unlock_irq(&xas);
if (!xas_nomem(&xas, gfp))
break;
}
if (xas_error(&xas))
goto error;
trace_mm_filemap_add_to_page_cache(folio);
return 0;
error:
folio->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
folio_put_refs(folio, nr);
return xas_error(&xas);
}
ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
int filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp)
{
void *shadow = NULL;
int ret;
ret = mem_cgroup_charge(folio, NULL, gfp); if (ret)
return ret;
__folio_set_locked(folio);
ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
if (unlikely(ret)) {
mem_cgroup_uncharge(folio); __folio_clear_locked(folio);
} else {
/*
* The folio might have been evicted from cache only
* recently, in which case it should be activated like
* any other repeatedly accessed folio.
* The exception is folios getting rewritten; evicting other
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow);
folio_add_lru(folio);
}
return ret;
}
EXPORT_SYMBOL_GPL(filemap_add_folio);
#ifdef CONFIG_NUMA
struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
{
int n;
struct folio *folio;
if (cpuset_do_page_mem_spread()) {
unsigned int cpuset_mems_cookie;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
n = cpuset_mem_spread_node();
folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie));
return folio;
}
return folio_alloc_noprof(gfp, order);
}
EXPORT_SYMBOL(filemap_alloc_folio_noprof);
#endif
/*
* filemap_invalidate_lock_two - lock invalidate_lock for two mappings
*
* Lock exclusively invalidate_lock of any passed mapping that is not NULL.
*
* @mapping1: the first mapping to lock
* @mapping2: the second mapping to lock
*/
void filemap_invalidate_lock_two(struct address_space *mapping1,
struct address_space *mapping2)
{
if (mapping1 > mapping2)
swap(mapping1, mapping2);
if (mapping1)
down_write(&mapping1->invalidate_lock);
if (mapping2 && mapping1 != mapping2)
down_write_nested(&mapping2->invalidate_lock, 1);
}
EXPORT_SYMBOL(filemap_invalidate_lock_two);
/*
* filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings
*
* Unlock exclusive invalidate_lock of any passed mapping that is not NULL.
*
* @mapping1: the first mapping to unlock
* @mapping2: the second mapping to unlock
*/
void filemap_invalidate_unlock_two(struct address_space *mapping1,
struct address_space *mapping2)
{
if (mapping1)
up_write(&mapping1->invalidate_lock);
if (mapping2 && mapping1 != mapping2)
up_write(&mapping2->invalidate_lock);
}
EXPORT_SYMBOL(filemap_invalidate_unlock_two);
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
* waitqueues where the bucket discipline is to maintain all
* waiters on the same queue and wake all when any of the pages
* become available, and for the woken contexts to check to be
* sure the appropriate page became available, this saves space
* at a cost of "thundering herd" phenomena during rare hash
* collisions.
*/
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
static wait_queue_head_t *folio_waitqueue(struct folio *folio)
{
return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)];
}
/* How many times do we accept lock stealing from under a waiter? */
static int sysctl_page_lock_unfairness = 5;
static const struct ctl_table filemap_sysctl_table[] = {
{
.procname = "page_lock_unfairness",
.data = &sysctl_page_lock_unfairness,
.maxlen = sizeof(sysctl_page_lock_unfairness),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
}
};
void __init pagecache_init(void)
{
int i;
for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
init_waitqueue_head(&folio_wait_table[i]);
page_writeback_init();
register_sysctl_init("vm", filemap_sysctl_table);
}
/*
* The page wait code treats the "wait->flags" somewhat unusually, because
* we have multiple different kinds of waits, not just the usual "exclusive"
* one.
*
* We have:
*
* (a) no special bits set:
*
* We're just waiting for the bit to be released, and when a waker
* calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
* and remove it from the wait queue.
*
* Simple and straightforward.
*
* (b) WQ_FLAG_EXCLUSIVE:
*
* The waiter is waiting to get the lock, and only one waiter should
* be woken up to avoid any thundering herd behavior. We'll set the
* WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
*
* This is the traditional exclusive wait.
*
* (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
*
* The waiter is waiting to get the bit, and additionally wants the
* lock to be transferred to it for fair lock behavior. If the lock
* cannot be taken, we stop walking the wait queue without waking
* the waiter.
*
* This is the "fair lock handoff" case, and in addition to setting
* WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
* that it now has the lock.
*/
static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
{
unsigned int flags;
struct wait_page_key *key = arg;
struct wait_page_queue *wait_page
= container_of(wait, struct wait_page_queue, wait);
if (!wake_page_match(wait_page, key))
return 0;
/*
* If it's a lock handoff wait, we get the bit for it, and
* stop walking (and do not wake it up) if we can't.
*/
flags = wait->flags;
if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags))
return -1;
if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags))
return -1;
flags |= WQ_FLAG_DONE;
}
}
/*
* We are holding the wait-queue lock, but the waiter that
* is waiting for this will be checking the flags without
* any locking.
*
* So update the flags atomically, and wake up the waiter
* afterwards to avoid any races. This store-release pairs
* with the load-acquire in folio_wait_bit_common().
*/
smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
wake_up_state(wait->private, mode);
/*
* Ok, we have successfully done what we're waiting for,
* and we can unconditionally remove the wait entry.
*
* Note that this pairs with the "finish_wait()" in the
* waiter, and has to be the absolute last thing we do.
* After this list_del_init(&wait->entry) the wait entry
* might be de-allocated and the process might even have
* exited.
*/
list_del_init_careful(&wait->entry);
return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
static void folio_wake_bit(struct folio *folio, int bit_nr)
{
wait_queue_head_t *q = folio_waitqueue(folio);
struct wait_page_key key;
unsigned long flags;
key.folio = folio;
key.bit_nr = bit_nr;
key.page_match = 0;
spin_lock_irqsave(&q->lock, flags);
__wake_up_locked_key(q, TASK_NORMAL, &key);
/*
* It's possible to miss clearing waiters here, when we woke our page
* waiters, but the hashed waitqueue has waiters for other pages on it.
* That's okay, it's a rare case. The next waker will clear it.
*
* Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE,
* other), the flag may be cleared in the course of freeing the page;
* but that is not required for correctness.
*/
if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio);
spin_unlock_irqrestore(&q->lock, flags);
}
/*
* A choice of three behaviors for folio_wait_bit_common():
*/
enum behavior {
EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
* __folio_lock() waiting on then setting PG_locked.
*/
SHARED, /* Hold ref to page and check the bit when woken, like
* folio_wait_writeback() waiting on PG_writeback.
*/
DROP, /* Drop ref to page before wait, no check when woken,
* like folio_put_wait_locked() on PG_locked.
*/
};
/*
* Attempt to check (or get) the folio flag, and mark us done
* if successful.
*/
static inline bool folio_trylock_flag(struct folio *folio, int bit_nr,
struct wait_queue_entry *wait)
{
if (wait->flags & WQ_FLAG_EXCLUSIVE) {
if (test_and_set_bit(bit_nr, &folio->flags))
return false;
} else if (test_bit(bit_nr, &folio->flags))
return false;
wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
return true;
}
static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
int state, enum behavior behavior)
{
wait_queue_head_t *q = folio_waitqueue(folio);
int unfairness = sysctl_page_lock_unfairness;
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
bool thrashing = false;
unsigned long pflags;
bool in_thrashing;
if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
delayacct_thrashing_start(&in_thrashing);
psi_memstall_enter(&pflags);
thrashing = true;
}
init_wait(wait);
wait->func = wake_page_function;
wait_page.folio = folio;
wait_page.bit_nr = bit_nr;
repeat:
wait->flags = 0;
if (behavior == EXCLUSIVE) {
wait->flags = WQ_FLAG_EXCLUSIVE;
if (--unfairness < 0)
wait->flags |= WQ_FLAG_CUSTOM;
}
/*
* Do one last check whether we can get the
* page bit synchronously.
*
* Do the folio_set_waiters() marking before that
* to let any waker we _just_ missed know they
* need to wake us up (otherwise they'll never
* even go to the slow case that looks at the
* page queue), and add ourselves to the wait
* queue if we need to sleep.
*
* This part needs to be done under the queue
* lock to avoid races.
*/
spin_lock_irq(&q->lock);
folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
/*
* From now on, all the logic will be based on
* the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
* see whether the page bit testing has already
* been done by the wake function.
*
* We can drop our reference to the folio.
*/
if (behavior == DROP) folio_put(folio);
/*
* Note that until the "finish_wait()", or until
* we see the WQ_FLAG_WOKEN flag, we need to
* be very careful with the 'wait->flags', because
* we may race with a waker that sets them.
*/
for (;;) {
unsigned int flags;
set_current_state(state);
/* Loop until we've been woken or interrupted */
flags = smp_load_acquire(&wait->flags);
if (!(flags & WQ_FLAG_WOKEN)) {
if (signal_pending_state(state, current))
break;
io_schedule();
continue;
}
/* If we were non-exclusive, we're done */
if (behavior != EXCLUSIVE)
break;
/* If the waker got the lock for us, we're done */
if (flags & WQ_FLAG_DONE)
break;
/*
* Otherwise, if we're getting the lock, we need to
* try to get it ourselves.
*
* And if that fails, we'll have to retry this all.
*/
if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0))))
goto repeat;
wait->flags |= WQ_FLAG_DONE;
break;
}
/*
* If a signal happened, this 'finish_wait()' may remove the last
* waiter from the wait-queues, but the folio waiters bit will remain
* set. That's ok. The next wakeup will take care of it, and trying
* to do it here would be difficult and prone to races.
*/
finish_wait(q, wait);
if (thrashing) {
delayacct_thrashing_end(&in_thrashing);
psi_memstall_leave(&pflags);
}
/*
* NOTE! The wait->flags weren't stable until we've done the
* 'finish_wait()', and we could have exited the loop above due
* to a signal, and had a wakeup event happen after the signal
* test but before the 'finish_wait()'.
*
* So only after the finish_wait() can we reliably determine
* if we got woken up or not, so we can now figure out the final
* return value based on that state without races.
*
* Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
* waiter, but an exclusive one requires WQ_FLAG_DONE.
*/
if (behavior == EXCLUSIVE)
return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
#ifdef CONFIG_MIGRATION
/**
* migration_entry_wait_on_locked - Wait for a migration entry to be removed
* @entry: migration swap entry.
* @ptl: already locked ptl. This function will drop the lock.
*
* Wait for a migration entry referencing the given page to be removed. This is
* equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except
* this can be called without taking a reference on the page. Instead this
* should be called while holding the ptl for the migration entry referencing
* the page.
*
* Returns after unlocking the ptl.
*
* This follows the same logic as folio_wait_bit_common() so see the comments
* there.
*/
void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl)
__releases(ptl)
{
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
bool thrashing = false;
unsigned long pflags;
bool in_thrashing;
wait_queue_head_t *q;
struct folio *folio = pfn_swap_entry_folio(entry);
q = folio_waitqueue(folio);
if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
delayacct_thrashing_start(&in_thrashing);
psi_memstall_enter(&pflags);
thrashing = true;
}
init_wait(wait);
wait->func = wake_page_function;
wait_page.folio = folio;
wait_page.bit_nr = PG_locked;
wait->flags = 0;
spin_lock_irq(&q->lock);
folio_set_waiters(folio);
if (!folio_trylock_flag(folio, PG_locked, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
/*
* If a migration entry exists for the page the migration path must hold
* a valid reference to the page, and it must take the ptl to remove the
* migration entry. So the page is valid until the ptl is dropped.
*/
spin_unlock(ptl);
for (;;) {
unsigned int flags;
set_current_state(TASK_UNINTERRUPTIBLE);
/* Loop until we've been woken or interrupted */
flags = smp_load_acquire(&wait->flags);
if (!(flags & WQ_FLAG_WOKEN)) {
if (signal_pending_state(TASK_UNINTERRUPTIBLE, current))
break;
io_schedule();
continue;
}
break;
}
finish_wait(q, wait);
if (thrashing) {
delayacct_thrashing_end(&in_thrashing);
psi_memstall_leave(&pflags);
}
}
#endif
void folio_wait_bit(struct folio *folio, int bit_nr)
{
folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
EXPORT_SYMBOL(folio_wait_bit);
int folio_wait_bit_killable(struct folio *folio, int bit_nr)
{
return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED);
}
EXPORT_SYMBOL(folio_wait_bit_killable);
/**
* folio_put_wait_locked - Drop a reference and wait for it to be unlocked
* @folio: The folio to wait for.
* @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc).
*
* The caller should hold a reference on @folio. They expect the page to
* become unlocked relatively soon, but do not wish to hold up migration
* (for example) by holding the reference while waiting for the folio to
* come unlocked. After this function returns, the caller should not
* dereference @folio.
*
* Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal.
*/
static int folio_put_wait_locked(struct folio *folio, int state)
{
return folio_wait_bit_common(folio, PG_locked, state, DROP);
}
/**
* folio_unlock - Unlock a locked folio.
* @folio: The folio.
*
* Unlocks the folio and wakes up any thread sleeping on the page lock.
*
* Context: May be called from interrupt or process context. May not be
* called from NMI context.
*/
void folio_unlock(struct folio *folio)
{
/* Bit 7 allows x86 to check the byte's sign bit */
BUILD_BUG_ON(PG_waiters != 7);
BUILD_BUG_ON(PG_locked > 7);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked);
}
EXPORT_SYMBOL(folio_unlock);
/**
* folio_end_read - End read on a folio.
* @folio: The folio.
* @success: True if all reads completed successfully.
*
* When all reads against a folio have completed, filesystems should
* call this function to let the pagecache know that no more reads
* are outstanding. This will unlock the folio and wake up any thread
* sleeping on the lock. The folio will also be marked uptodate if all
* reads succeeded.
*
* Context: May be called from interrupt or process context. May not be
* called from NMI context.
*/
void folio_end_read(struct folio *folio, bool success)
{
unsigned long mask = 1 << PG_locked;
/* Must be in bottom byte for x86 to work */
BUILD_BUG_ON(PG_uptodate > 7);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio);
if (likely(success))
mask |= 1 << PG_uptodate;
if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked);
}
EXPORT_SYMBOL(folio_end_read);
/**
* folio_end_private_2 - Clear PG_private_2 and wake any waiters.
* @folio: The folio.
*
* Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for
* it. The folio reference held for PG_private_2 being set is released.
*
* This is, for example, used when a netfs folio is being written to a local
* disk cache, thereby allowing writes to the cache for the same folio to be
* serialised.
*/
void folio_end_private_2(struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio);
clear_bit_unlock(PG_private_2, folio_flags(folio, 0));
folio_wake_bit(folio, PG_private_2);
folio_put(folio);
}
EXPORT_SYMBOL(folio_end_private_2);
/**
* folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
* @folio: The folio to wait on.
*
* Wait for PG_private_2 to be cleared on a folio.
*/
void folio_wait_private_2(struct folio *folio)
{
while (folio_test_private_2(folio))
folio_wait_bit(folio, PG_private_2);
}
EXPORT_SYMBOL(folio_wait_private_2);
/**
* folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
* @folio: The folio to wait on.
*
* Wait for PG_private_2 to be cleared on a folio or until a fatal signal is
* received by the calling task.
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
int folio_wait_private_2_killable(struct folio *folio)
{
int ret = 0;
while (folio_test_private_2(folio)) {
ret = folio_wait_bit_killable(folio, PG_private_2);
if (ret < 0)
break;
}
return ret;
}
EXPORT_SYMBOL(folio_wait_private_2_killable);
/*
* If folio was marked as dropbehind, then pages should be dropped when writeback
* completes. Do that now. If we fail, it's likely because of a big folio -
* just reset dropbehind for that case and latter completions should invalidate.
*/
static void folio_end_dropbehind_write(struct folio *folio)
{
/*
* Hitting !in_task() should not happen off RWF_DONTCACHE writeback,
* but can happen if normal writeback just happens to find dirty folios
* that were created as part of uncached writeback, and that writeback
* would otherwise not need non-IRQ handling. Just skip the
* invalidation in that case.
*/
if (in_task() && folio_trylock(folio)) {
if (folio->mapping)
folio_unmap_invalidate(folio->mapping, folio, 0);
folio_unlock(folio);
}
}
/**
* folio_end_writeback - End writeback against a folio.
* @folio: The folio.
*
* The folio must actually be under writeback.
*
* Context: May be called from process or interrupt context.
*/
void folio_end_writeback(struct folio *folio)
{
bool folio_dropbehind = false;
VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
/*
* folio_test_clear_reclaim() could be used here but it is an
* atomic operation and overkill in this particular case. Failing
* to shuffle a folio marked for immediate reclaim is too mild
* a gain to justify taking an atomic operation penalty at the
* end of every folio writeback.
*/
if (folio_test_reclaim(folio)) {
folio_clear_reclaim(folio);
folio_rotate_reclaimable(folio);
}
/*
* Writeback does not hold a folio reference of its own, relying
* on truncation to wait for the clearing of PG_writeback.
* But here we must make sure that the folio is not freed and
* reused before the folio_wake_bit().
*/
folio_get(folio);
if (!folio_test_dirty(folio))
folio_dropbehind = folio_test_clear_dropbehind(folio);
if (__folio_end_writeback(folio))
folio_wake_bit(folio, PG_writeback);
acct_reclaim_writeback(folio);
if (folio_dropbehind)
folio_end_dropbehind_write(folio);
folio_put(folio);
}
EXPORT_SYMBOL(folio_end_writeback);
/**
* __folio_lock - Get a lock on the folio, assuming we need to sleep to get it.
* @folio: The folio to lock
*/
void __folio_lock(struct folio *folio)
{ folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE,
EXCLUSIVE);
}
EXPORT_SYMBOL(__folio_lock);
int __folio_lock_killable(struct folio *folio)
{
return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE,
EXCLUSIVE);
}
EXPORT_SYMBOL_GPL(__folio_lock_killable);
static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
{
struct wait_queue_head *q = folio_waitqueue(folio);
int ret;
wait->folio = folio;
wait->bit_nr = PG_locked;
spin_lock_irq(&q->lock);
__add_wait_queue_entry_tail(q, &wait->wait);
folio_set_waiters(folio);
ret = !folio_trylock(folio);
/*
* If we were successful now, we know we're still on the
* waitqueue as we're still under the lock. This means it's
* safe to remove and return success, we know the callback
* isn't going to trigger.
*/
if (!ret)
__remove_wait_queue(q, &wait->wait);
else
ret = -EIOCBQUEUED;
spin_unlock_irq(&q->lock);
return ret;
}
/*
* Return values:
* 0 - folio is locked.
* non-zero - folio is not locked.
* mmap_lock or per-VMA lock has been released (mmap_read_unlock() or
* vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and
* FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held.
*
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 0
* with the folio locked and the mmap_lock/per-VMA lock is left unperturbed.
*/
vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf)
{
unsigned int flags = vmf->flags;
if (fault_flag_allow_retry_first(flags)) {
/*
* CAUTION! In this case, mmap_lock/per-VMA lock is not
* released even though returning VM_FAULT_RETRY.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
return VM_FAULT_RETRY;
release_fault_lock(vmf);
if (flags & FAULT_FLAG_KILLABLE)
folio_wait_locked_killable(folio);
else
folio_wait_locked(folio);
return VM_FAULT_RETRY;
}
if (flags & FAULT_FLAG_KILLABLE) {
bool ret;
ret = __folio_lock_killable(folio);
if (ret) {
release_fault_lock(vmf);
return VM_FAULT_RETRY;
}
} else {
__folio_lock(folio);
}
return 0;
}
/**
* page_cache_next_miss() - Find the next gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
*
* Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
* gap with the lowest index.
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 5, then subsequently a gap is
* created at index 10, page_cache_next_miss covering both indices may
* return 10 if called under the rcu_read_lock.
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'return - index >= max_scan' will be true).
* In the rare case of index wrap-around, 0 will be returned.
*/
pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
while (max_scan--) {
void *entry = xas_next(&xas);
if (!entry || xa_is_value(entry))
return xas.xa_index;
if (xas.xa_index == 0)
return 0;
}
return index + max_scan;
}
EXPORT_SYMBOL(page_cache_next_miss);
/**
* page_cache_prev_miss() - Find the previous gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
*
* Search the range [max(index - max_scan + 1, 0), index] for the
* gap with the highest index.
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 10, then subsequently a gap is
* created at index 5, page_cache_prev_miss() covering both indices may
* return 5 if called under the rcu_read_lock.
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'index - return >= max_scan' will be true).
* In the rare case of wrap-around, ULONG_MAX will be returned.
*/
pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
while (max_scan--) {
void *entry = xas_prev(&xas);
if (!entry || xa_is_value(entry))
break;
if (xas.xa_index == ULONG_MAX)
break;
}
return xas.xa_index;
}
EXPORT_SYMBOL(page_cache_prev_miss);
/*
* Lockless page cache protocol:
* On the lookup side:
* 1. Load the folio from i_pages
* 2. Increment the refcount if it's not zero
* 3. If the folio is not found by xas_reload(), put the refcount and retry
*
* On the removal side:
* A. Freeze the page (by zeroing the refcount if nobody else has a reference)
* B. Remove the page from i_pages
* C. Return the page to the page allocator
*
* This means that any page may have its reference count temporarily
* increased by a speculative page cache (or GUP-fast) lookup as it can
* be allocated by another user before the RCU grace period expires.
* Because the refcount temporarily acquired here may end up being the
* last refcount on the page, any page allocation must be freeable by
* folio_put().
*/
/*
* filemap_get_entry - Get a page cache entry.
* @mapping: the address_space to search
* @index: The page cache index.
*
* Looks up the page cache entry at @mapping & @index. If it is a folio,
* it is returned with an increased refcount. If it is a shadow entry
* of a previously evicted folio, or a swap entry from shmem/tmpfs,
* it is returned without further action.
*
* Return: The folio, swap or shadow entry, %NULL if nothing is found.
*/
void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
{
XA_STATE(xas, &mapping->i_pages, index);
struct folio *folio;
rcu_read_lock();
repeat:
xas_reset(&xas);
folio = xas_load(&xas);
if (xas_retry(&xas, folio))
goto repeat;
/*
* A shadow entry of a recently evicted page, or a swap entry from
* shmem/tmpfs. Return it without attempting to raise page count.
*/
if (!folio || xa_is_value(folio))
goto out;
if (!folio_try_get(folio))
goto repeat;
if (unlikely(folio != xas_reload(&xas))) { folio_put(folio);
goto repeat;
}
out:
rcu_read_unlock();
return folio;
}
/**
* __filemap_get_folio - Find and get a reference to a folio.
* @mapping: The address_space to search.
* @index: The page index.
* @fgp_flags: %FGP flags modify how the folio is returned.
* @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
*
* Looks up the page cache entry at @mapping & @index.
*
* If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
* if the %GFP flags specified for %FGP_CREAT are atomic.
*
* If this function returns a folio, it is returned with an increased refcount.
*
* Return: The found folio or an ERR_PTR() otherwise.
*/
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
fgf_t fgp_flags, gfp_t gfp)
{
struct folio *folio;
repeat:
folio = filemap_get_entry(mapping, index);
if (xa_is_value(folio))
folio = NULL;
if (!folio)
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
if (!folio_trylock(folio)) { folio_put(folio);
return ERR_PTR(-EAGAIN);
}
} else {
folio_lock(folio);
}
/* Has the page been truncated? */
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
folio_put(folio);
goto repeat;
}
VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
}
if (fgp_flags & FGP_ACCESSED)
folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) {
/* Clear idle flag for buffer write */
if (folio_test_idle(folio)) folio_clear_idle(folio);
}
if (fgp_flags & FGP_STABLE) folio_wait_stable(folio);
no_page:
if (!folio && (fgp_flags & FGP_CREAT)) {
unsigned int min_order = mapping_min_folio_order(mapping);
unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
int err;
index = mapping_align_index(mapping, index);
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp &= ~__GFP_FS;
if (fgp_flags & FGP_NOWAIT) {
gfp &= ~GFP_KERNEL;
gfp |= GFP_NOWAIT | __GFP_NOWARN;
}
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
fgp_flags |= FGP_LOCK;
if (order > mapping_max_folio_order(mapping))
order = mapping_max_folio_order(mapping);
/* If we're not aligned, allocate a smaller folio */
if (index & ((1UL << order) - 1))
order = __ffs(index);
do {
gfp_t alloc_gfp = gfp;
err = -ENOMEM;
if (order > min_order)
alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
folio = filemap_alloc_folio(alloc_gfp, order);
if (!folio)
continue;
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); if (fgp_flags & FGP_DONTCACHE) __folio_set_dropbehind(folio);
err = filemap_add_folio(mapping, folio, index, gfp);
if (!err)
break;
folio_put(folio);
folio = NULL;
} while (order-- > min_order); if (err == -EEXIST)
goto repeat;
if (err) {
/*
* When NOWAIT I/O fails to allocate folios this could
* be due to a nonblocking memory allocation and not
* because the system actually is out of memory.
* Return -EAGAIN so that there caller retries in a
* blocking fashion instead of propagating -ENOMEM
* to the application.
*/
if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM)
err = -EAGAIN;
return ERR_PTR(err);
}
/*
* filemap_add_folio locks the page, and for mmap
* we expect an unlocked page.
*/
if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio);
}
if (!folio)
return ERR_PTR(-ENOENT);
/* not an uncached lookup, clear uncached if set */
if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) folio_clear_dropbehind(folio);
return folio;
}
EXPORT_SYMBOL(__filemap_get_folio);
static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
xa_mark_t mark)
{
struct folio *folio;
retry:
if (mark == XA_PRESENT)
folio = xas_find(xas, max);
else
folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio))
goto retry;
/*
* A shadow entry of a recently evicted page, a swap
* entry from shmem/tmpfs or a DAX entry. Return it
* without attempting to raise page count.
*/
if (!folio || xa_is_value(folio))
return folio;
if (!folio_try_get(folio))
goto reset;
if (unlikely(folio != xas_reload(xas))) { folio_put(folio);
goto reset;
}
return folio;
reset:
xas_reset(xas);
goto retry;
}
/**
* find_get_entries - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page cache index
* @end: The final page index (inclusive).
* @fbatch: Where the resulting entries are placed.
* @indices: The cache indices corresponding to the entries in @entries
*
* find_get_entries() will search for and return a batch of entries in
* the mapping. The entries are placed in @fbatch. find_get_entries()
* takes a reference on any actual folios it returns.
*
* The entries have ascending indexes. The indices may not be consecutive
* due to not-present entries or large folios.
*
* Any shadow entries of evicted folios, or swap entries from
* shmem/tmpfs, are included in the returned array.
*
* Return: The number of entries which were found.
*/
unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
indices[fbatch->nr] = xas.xa_index;
if (!folio_batch_add(fbatch, folio))
break;
}
if (folio_batch_count(fbatch)) {
unsigned long nr;
int idx = folio_batch_count(fbatch) - 1;
folio = fbatch->folios[idx];
if (!xa_is_value(folio))
nr = folio_nr_pages(folio);
else
nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]);
*start = round_down(indices[idx] + nr, nr);
}
rcu_read_unlock();
return folio_batch_count(fbatch);
}
/**
* find_lock_entries - Find a batch of pagecache entries.
* @mapping: The address_space to search.
* @start: The starting page cache index.
* @end: The final page index (inclusive).
* @fbatch: Where the resulting entries are placed.
* @indices: The cache indices of the entries in @fbatch.
*
* find_lock_entries() will return a batch of entries from @mapping.
* Swap, shadow and DAX entries are included. Folios are returned
* locked and with an incremented refcount. Folios which are locked
* by somebody else or under writeback are skipped. Folios which are
* partially outside the range are not returned.
*
* The entries have ascending indexes. The indices may not be consecutive
* due to not-present entries, large folios, folios which could not be
* locked or folios under writeback.
*
* Return: The number of entries which were found.
*/
unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
unsigned long base;
unsigned long nr;
if (!xa_is_value(folio)) {
nr = folio_nr_pages(folio);
base = folio->index;
/* Omit large folio which begins before the start */
if (base < *start)
goto put;
/* Omit large folio which extends beyond the end */
if (base + nr - 1 > end)
goto put;
if (!folio_trylock(folio))
goto put;
if (folio->mapping != mapping || folio_test_writeback(folio))
goto unlock;
VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index),
folio);
} else {
nr = 1 << xas_get_order(&xas);
base = xas.xa_index & ~(nr - 1);
/* Omit order>0 value which begins before the start */
if (base < *start)
continue;
/* Omit order>0 value which extends beyond the end */
if (base + nr - 1 > end)
break;
}
/* Update start now so that last update is correct on return */
*start = base + nr;
indices[fbatch->nr] = xas.xa_index;
if (!folio_batch_add(fbatch, folio))
break;
continue;
unlock:
folio_unlock(folio);
put:
folio_put(folio);
}
rcu_read_unlock();
return folio_batch_count(fbatch);
}
/**
* filemap_get_folios - Get a batch of folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @fbatch: The batch to fill.
*
* Search for and return a batch of folios in the mapping starting at
* index @start and up to index @end (inclusive). The folios are returned
* in @fbatch with an elevated reference count.
*
* Return: The number of folios which were found.
* We also update @start to index the next folio for the traversal.
*/
unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch)
{
return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch);
}
EXPORT_SYMBOL(filemap_get_folios);
/**
* filemap_get_folios_contig - Get a batch of contiguous folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @fbatch: The batch to fill
*
* filemap_get_folios_contig() works exactly like filemap_get_folios(),
* except the returned folios are guaranteed to be contiguous. This may
* not return all contiguous folios if the batch gets filled up.
*
* Return: The number of folios found.
* Also update @start to be positioned for traversal of the next folio.
*/
unsigned filemap_get_folios_contig(struct address_space *mapping,
pgoff_t *start, pgoff_t end, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
unsigned long nr;
struct folio *folio;
rcu_read_lock();
for (folio = xas_load(&xas); folio && xas.xa_index <= end;
folio = xas_next(&xas)) {
if (xas_retry(&xas, folio))
continue;
/*
* If the entry has been swapped out, we can stop looking.
* No current caller is looking for DAX entries.
*/
if (xa_is_value(folio))
goto update_start;
/* If we landed in the middle of a THP, continue at its end. */
if (xa_is_sibling(folio))
goto update_start;
if (!folio_try_get(folio))
goto retry;
if (unlikely(folio != xas_reload(&xas)))
goto put_folio;
if (!folio_batch_add(fbatch, folio)) {
nr = folio_nr_pages(folio);
*start = folio->index + nr;
goto out;
}
xas_advance(&xas, folio_next_index(folio) - 1);
continue;
put_folio:
folio_put(folio);
retry:
xas_reset(&xas);
}
update_start:
nr = folio_batch_count(fbatch);
if (nr) {
folio = fbatch->folios[nr - 1];
*start = folio_next_index(folio);
}
out:
rcu_read_unlock();
return folio_batch_count(fbatch);
}
EXPORT_SYMBOL(filemap_get_folios_contig);
/**
* filemap_get_folios_tag - Get a batch of folios matching @tag
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @tag: The tag index
* @fbatch: The batch to fill
*
* The first folio may start before @start; if it does, it will contain
* @start. The final folio may extend beyond @end; if it does, it will
* contain @end. The folios have ascending indices. There may be gaps
* between the folios if there are indices which have no folio in the
* page cache. If folios are added to or removed from the page cache
* while this is running, they may or may not be found by this call.
* Only returns folios that are tagged with @tag.
*
* Return: The number of folios found.
* Also update @start to index the next folio for traversal.
*/
unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) {
/*
* Shadow entries should never be tagged, but this iteration
* is lockless so there is a window for page reclaim to evict
* a page we saw tagged. Skip over it.
*/
if (xa_is_value(folio))
continue;
if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio);
*start = folio->index + nr;
goto out;
}
}
/*
* We come here when there is no page beyond @end. We take care to not
* overflow the index @start as it confuses some of the callers. This
* breaks the iteration when there is a page at index -1 but that is
* already broke anyway.
*/
if (end == (pgoff_t)-1)
*start = (pgoff_t)-1;
else
*start = end + 1;
out:
rcu_read_unlock();
return folio_batch_count(fbatch);
}
EXPORT_SYMBOL(filemap_get_folios_tag);
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
* a _large_ part of the i/o request. Imagine the worst scenario:
*
* ---R__________________________________________B__________
* ^ reading here ^ bad block(assume 4k)
*
* read(R) => miss => readahead(R...B) => media error => frustrating retries
* => failing the whole request => read(R) => read(R+1) =>
* readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
* readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
* readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
*
* It is going insane. Fix it by quickly scaling down the readahead size.
*/
static void shrink_readahead_size_eio(struct file_ra_state *ra)
{
ra->ra_pages /= 4;
}
/*
* filemap_get_read_batch - Get a batch of folios for read
*
* Get a batch of folios which represent a contiguous range of bytes in
* the file. No exceptional entries will be returned. If @index is in
* the middle of a folio, the entire folio will be returned. The last
* folio in the batch may have the readahead flag set or the uptodate flag
* clear so that the caller can take the appropriate action.
*/
static void filemap_get_read_batch(struct address_space *mapping,
pgoff_t index, pgoff_t max, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, index);
struct folio *folio;
rcu_read_lock();
for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) {
if (xas_retry(&xas, folio))
continue;
if (xas.xa_index > max || xa_is_value(folio))
break;
if (xa_is_sibling(folio))
break;
if (!folio_try_get(folio))
goto retry;
if (unlikely(folio != xas_reload(&xas)))
goto put_folio;
if (!folio_batch_add(fbatch, folio))
break;
if (!folio_test_uptodate(folio))
break;
if (folio_test_readahead(folio))
break;
xas_advance(&xas, folio_next_index(folio) - 1);
continue;
put_folio:
folio_put(folio);
retry:
xas_reset(&xas);
}
rcu_read_unlock();
}
static int filemap_read_folio(struct file *file, filler_t filler,
struct folio *folio)
{
bool workingset = folio_test_workingset(folio);
unsigned long pflags;
int error;
/* Start the actual read. The read will unlock the page. */
if (unlikely(workingset))
psi_memstall_enter(&pflags);
error = filler(file, folio);
if (unlikely(workingset))
psi_memstall_leave(&pflags);
if (error)
return error;
error = folio_wait_locked_killable(folio);
if (error)
return error;
if (folio_test_uptodate(folio))
return 0;
if (file)
shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
static bool filemap_range_uptodate(struct address_space *mapping,
loff_t pos, size_t count, struct folio *folio,
bool need_uptodate)
{
if (folio_test_uptodate(folio))
return true;
/* pipes can't handle partially uptodate pages */
if (need_uptodate)
return false;
if (!mapping->a_ops->is_partially_uptodate)
return false;
if (mapping->host->i_blkbits >= folio_shift(folio))
return false;
if (folio_pos(folio) > pos) {
count -= folio_pos(folio) - pos;
pos = 0;
} else {
pos -= folio_pos(folio);
}
return mapping->a_ops->is_partially_uptodate(folio, pos, count);
}
static int filemap_update_page(struct kiocb *iocb,
struct address_space *mapping, size_t count,
struct folio *folio, bool need_uptodate)
{
int error;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!filemap_invalidate_trylock_shared(mapping))
return -EAGAIN;
} else {
filemap_invalidate_lock_shared(mapping);
}
if (!folio_trylock(folio)) {
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
goto unlock_mapping;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
filemap_invalidate_unlock_shared(mapping);
/*
* This is where we usually end up waiting for a
* previously submitted readahead to finish.
*/
folio_put_wait_locked(folio, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
error = __folio_lock_async(folio, iocb->ki_waitq);
if (error)
goto unlock_mapping;
}
error = AOP_TRUNCATED_PAGE;
if (!folio->mapping)
goto unlock;
error = 0;
if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio,
need_uptodate))
goto unlock;
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
folio);
goto unlock_mapping;
unlock:
folio_unlock(folio);
unlock_mapping:
filemap_invalidate_unlock_shared(mapping);
if (error == AOP_TRUNCATED_PAGE)
folio_put(folio);
return error;
}
static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct folio *folio;
int error;
unsigned int min_order = mapping_min_folio_order(mapping);
pgoff_t index;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
return -EAGAIN;
folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
if (!folio)
return -ENOMEM;
if (iocb->ki_flags & IOCB_DONTCACHE)
__folio_set_dropbehind(folio);
/*
* Protect against truncate / hole punch. Grabbing invalidate_lock
* here assures we cannot instantiate and bring uptodate new
* pagecache folios after evicting page cache during truncate
* and before actually freeing blocks. Note that we could
* release invalidate_lock after inserting the folio into
* the page cache as the locked folio would then be enough to
* synchronize with hole punching. But there are code paths
* such as filemap_update_page() filling in partially uptodate
* pages or ->readahead() that need to hold invalidate_lock
* while mapping blocks for IO so let's hold the lock here as
* well to keep locking rules simple.
*/
filemap_invalidate_lock_shared(mapping);
index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order;
error = filemap_add_folio(mapping, folio, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error == -EEXIST)
error = AOP_TRUNCATED_PAGE;
if (error)
goto error;
error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
folio);
if (error)
goto error;
filemap_invalidate_unlock_shared(mapping);
folio_batch_add(fbatch, folio);
return 0;
error:
filemap_invalidate_unlock_shared(mapping);
folio_put(folio);
return error;
}
static int filemap_readahead(struct kiocb *iocb, struct file *file,
struct address_space *mapping, struct folio *folio,
pgoff_t last_index)
{
DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index);
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
if (iocb->ki_flags & IOCB_DONTCACHE)
ractl.dropbehind = 1;
page_cache_async_ra(&ractl, folio, last_index - folio->index);
return 0;
}
static int filemap_get_pages(struct kiocb *iocb, size_t count,
struct folio_batch *fbatch, bool need_uptodate)
{
struct file *filp = iocb->ki_filp;
struct address_space *mapping = filp->f_mapping;
pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
pgoff_t last_index;
struct folio *folio;
unsigned int flags;
int err = 0;
/* "last_index" is the index of the page beyond the end of the read */
last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE);
retry:
if (fatal_signal_pending(current))
return -EINTR;
filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
if (!folio_batch_count(fbatch)) {
DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index);
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
if (iocb->ki_flags & IOCB_NOWAIT)
flags = memalloc_noio_save();
if (iocb->ki_flags & IOCB_DONTCACHE)
ractl.dropbehind = 1;
page_cache_sync_ra(&ractl, last_index - index);
if (iocb->ki_flags & IOCB_NOWAIT)
memalloc_noio_restore(flags);
filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
}
if (!folio_batch_count(fbatch)) {
err = filemap_create_folio(iocb, fbatch);
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
folio = fbatch->folios[folio_batch_count(fbatch) - 1];
if (folio_test_readahead(folio)) {
err = filemap_readahead(iocb, filp, mapping, folio, last_index);
if (err)
goto err;
}
if (!folio_test_uptodate(folio)) {
if ((iocb->ki_flags & IOCB_WAITQ) &&
folio_batch_count(fbatch) > 1)
iocb->ki_flags |= IOCB_NOWAIT;
err = filemap_update_page(iocb, mapping, count, folio,
need_uptodate);
if (err)
goto err;
}
trace_mm_filemap_get_pages(mapping, index, last_index - 1);
return 0;
err:
if (err < 0)
folio_put(folio);
if (likely(--fbatch->nr))
return 0;
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio)
{
unsigned int shift = folio_shift(folio);
return (pos1 >> shift == pos2 >> shift);
}
static void filemap_end_dropbehind_read(struct address_space *mapping,
struct folio *folio)
{
if (!folio_test_dropbehind(folio))
return;
if (folio_test_writeback(folio) || folio_test_dirty(folio))
return;
if (folio_trylock(folio)) {
if (folio_test_clear_dropbehind(folio))
folio_unmap_invalidate(mapping, folio, 0);
folio_unlock(folio);
}
}
/**
* filemap_read - Read data from the page cache.
* @iocb: The iocb to read.
* @iter: Destination for the data.
* @already_read: Number of bytes already read by the caller.
*
* Copies data from the page cache. If the data is not currently present,
* uses the readahead and read_folio address_space operations to fetch it.
*
* Return: Total number of bytes copied, including those already read by
* the caller. If an error happens before any bytes are copied, returns
* a negative error number.
*/
ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
ssize_t already_read)
{
struct file *filp = iocb->ki_filp;
struct file_ra_state *ra = &filp->f_ra;
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct folio_batch fbatch;
int i, error = 0;
bool writably_mapped;
loff_t isize, end_offset;
loff_t last_pos = ra->prev_pos;
if (unlikely(iocb->ki_pos < 0))
return -EINVAL;
if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes))
return 0;
if (unlikely(!iov_iter_count(iter)))
return 0;
iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos);
folio_batch_init(&fbatch);
do {
cond_resched();
/*
* If we've already successfully copied some data, then we
* can no longer safely return -EIOCBQUEUED. Hence mark
* an async read NOWAIT at that point.
*/
if ((iocb->ki_flags & IOCB_WAITQ) && already_read)
iocb->ki_flags |= IOCB_NOWAIT;
if (unlikely(iocb->ki_pos >= i_size_read(inode)))
break;
error = filemap_get_pages(iocb, iter->count, &fbatch, false);
if (error < 0)
break;
/*
* i_size must be checked after we know the pages are Uptodate.
*
* Checking i_size after the check allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(inode);
if (unlikely(iocb->ki_pos >= isize))
goto put_folios;
end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
/*
* Once we start copying data, we don't want to be touching any
* cachelines that might be contended:
*/
writably_mapped = mapping_writably_mapped(mapping);
/*
* When a read accesses the same folio several times, only
* mark it as accessed the first time.
*/
if (!pos_same_folio(iocb->ki_pos, last_pos - 1,
fbatch.folios[0]))
folio_mark_accessed(fbatch.folios[0]);
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
size_t fsize = folio_size(folio);
size_t offset = iocb->ki_pos & (fsize - 1);
size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos,
fsize - offset);
size_t copied;
if (end_offset < folio_pos(folio))
break;
if (i > 0)
folio_mark_accessed(folio);
/*
* If users can be writing to this folio using arbitrary
* virtual addresses, take care of potential aliasing
* before reading the folio on the kernel side.
*/
if (writably_mapped)
flush_dcache_folio(folio);
copied = copy_folio_to_iter(folio, offset, bytes, iter);
already_read += copied;
iocb->ki_pos += copied;
last_pos = iocb->ki_pos;
if (copied < bytes) {
error = -EFAULT;
break;
}
}
put_folios:
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
filemap_end_dropbehind_read(mapping, folio);
folio_put(folio);
}
folio_batch_init(&fbatch);
} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
file_accessed(filp);
ra->prev_pos = last_pos;
return already_read ? already_read : error;
}
EXPORT_SYMBOL_GPL(filemap_read);
int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
loff_t pos = iocb->ki_pos;
loff_t end = pos + count - 1;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (filemap_range_needs_writeback(mapping, pos, end))
return -EAGAIN;
return 0;
}
return filemap_write_and_wait_range(mapping, pos, end);
}
EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
int filemap_invalidate_pages(struct address_space *mapping,
loff_t pos, loff_t end, bool nowait)
{
int ret;
if (nowait) {
/* we could block if there are any pages in the range */
if (filemap_range_has_page(mapping, pos, end))
return -EAGAIN;
} else {
ret = filemap_write_and_wait_range(mapping, pos, end);
if (ret)
return ret;
}
/*
* After a write we want buffered reads to be sure to go to disk to get
* the new data. We invalidate clean cached page from the region we're
* about to write. We do this *before* the write so that we can return
* without clobbering -EIOCBQUEUED from ->direct_IO().
*/
return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
return filemap_invalidate_pages(mapping, iocb->ki_pos,
iocb->ki_pos + count - 1,
iocb->ki_flags & IOCB_NOWAIT);
}
EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
/**
* generic_file_read_iter - generic filesystem read routine
* @iocb: kernel I/O control block
* @iter: destination for the data read
*
* This is the "read_iter()" routine for all filesystems
* that can use the page cache directly.
*
* The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
* be returned when no data can be read without waiting for I/O requests
* to complete; it doesn't prevent readahead.
*
* The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
* requests shall be made for the read or for readahead. When no data
* can be read, -EAGAIN shall be returned. When readahead would be
* triggered, a partial, possibly empty read shall be returned.
*
* Return:
* * number of bytes copied, even for partial reads
* * negative error code (or 0 if IOCB_NOIO) if nothing was read
*/
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
size_t count = iov_iter_count(iter);
ssize_t retval = 0;
if (!count)
return 0; /* skip atime */
if (iocb->ki_flags & IOCB_DIRECT) {
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
retval = kiocb_write_and_wait(iocb, count);
if (retval < 0)
return retval;
file_accessed(file);
retval = mapping->a_ops->direct_IO(iocb, iter);
if (retval >= 0) {
iocb->ki_pos += retval;
count -= retval;
}
if (retval != -EIOCBQUEUED)
iov_iter_revert(iter, count - iov_iter_count(iter));
/*
* Btrfs can have a short DIO read if we encounter
* compressed extents, so if there was an error, or if
* we've already read everything we wanted to, or if
* there was a short read because we hit EOF, go ahead
* and return. Otherwise fallthrough to buffered io for
* the rest of the read. Buffered reads will not work for
* DAX files, so don't bother trying.
*/
if (retval < 0 || !count || IS_DAX(inode))
return retval;
if (iocb->ki_pos >= i_size_read(inode))
return retval;
}
return filemap_read(iocb, iter, retval);
}
EXPORT_SYMBOL(generic_file_read_iter);
/*
* Splice subpages from a folio into a pipe.
*/
size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
struct folio *folio, loff_t fpos, size_t size)
{
struct page *page;
size_t spliced = 0, offset = offset_in_folio(folio, fpos);
page = folio_page(folio, offset / PAGE_SIZE);
size = min(size, folio_size(folio) - offset);
offset %= PAGE_SIZE;
while (spliced < size && !pipe_is_full(pipe)) {
struct pipe_buffer *buf = pipe_head_buf(pipe);
size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced);
*buf = (struct pipe_buffer) {
.ops = &page_cache_pipe_buf_ops,
.page = page,
.offset = offset,
.len = part,
};
folio_get(folio);
pipe->head++;
page++;
spliced += part;
offset = 0;
}
return spliced;
}
/**
* filemap_splice_read - Splice data from a file's pagecache into a pipe
* @in: The file to read from
* @ppos: Pointer to the file position to read from
* @pipe: The pipe to splice into
* @len: The amount to splice
* @flags: The SPLICE_F_* flags
*
* This function gets folios from a file's pagecache and splices them into the
* pipe. Readahead will be called as necessary to fill more folios. This may
* be used for blockdevs also.
*
* Return: On success, the number of bytes read will be returned and *@ppos
* will be updated if appropriate; 0 will be returned if there is no more data
* to be read; -EAGAIN will be returned if the pipe had no space, and some
* other negative error code will be returned on error. A short read may occur
* if the pipe has insufficient space, we reach the end of the data or we hit a
* hole.
*/
ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
{
struct folio_batch fbatch;
struct kiocb iocb;
size_t total_spliced = 0, used, npages;
loff_t isize, end_offset;
bool writably_mapped;
int i, error = 0;
if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes))
return 0;
init_sync_kiocb(&iocb, in);
iocb.ki_pos = *ppos;
/* Work out how much data we can actually add into the pipe */
used = pipe_buf_usage(pipe);
npages = max_t(ssize_t, pipe->max_usage - used, 0);
len = min_t(size_t, len, npages * PAGE_SIZE);
folio_batch_init(&fbatch);
do {
cond_resched();
if (*ppos >= i_size_read(in->f_mapping->host))
break;
iocb.ki_pos = *ppos;
error = filemap_get_pages(&iocb, len, &fbatch, true);
if (error < 0)
break;
/*
* i_size must be checked after we know the pages are Uptodate.
*
* Checking i_size after the check allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(in->f_mapping->host);
if (unlikely(*ppos >= isize))
break;
end_offset = min_t(loff_t, isize, *ppos + len);
/*
* Once we start copying data, we don't want to be touching any
* cachelines that might be contended:
*/
writably_mapped = mapping_writably_mapped(in->f_mapping);
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
size_t n;
if (folio_pos(folio) >= end_offset)
goto out;
folio_mark_accessed(folio);
/*
* If users can be writing to this folio using arbitrary
* virtual addresses, take care of potential aliasing
* before reading the folio on the kernel side.
*/
if (writably_mapped)
flush_dcache_folio(folio);
n = min_t(loff_t, len, isize - *ppos);
n = splice_folio_into_pipe(pipe, folio, *ppos, n);
if (!n)
goto out;
len -= n;
total_spliced += n;
*ppos += n;
in->f_ra.prev_pos = *ppos;
if (pipe_is_full(pipe))
goto out;
}
folio_batch_release(&fbatch);
} while (len);
out:
folio_batch_release(&fbatch);
file_accessed(in);
return total_spliced ? total_spliced : error;
}
EXPORT_SYMBOL(filemap_splice_read);
static inline loff_t folio_seek_hole_data(struct xa_state *xas,
struct address_space *mapping, struct folio *folio,
loff_t start, loff_t end, bool seek_data)
{
const struct address_space_operations *ops = mapping->a_ops;
size_t offset, bsz = i_blocksize(mapping->host);
if (xa_is_value(folio) || folio_test_uptodate(folio))
return seek_data ? start : end;
if (!ops->is_partially_uptodate)
return seek_data ? end : start;
xas_pause(xas);
rcu_read_unlock();
folio_lock(folio);
if (unlikely(folio->mapping != mapping))
goto unlock;
offset = offset_in_folio(folio, start) & ~(bsz - 1);
do {
if (ops->is_partially_uptodate(folio, offset, bsz) ==
seek_data)
break;
start = (start + bsz) & ~((u64)bsz - 1);
offset += bsz;
} while (offset < folio_size(folio));
unlock:
folio_unlock(folio);
rcu_read_lock();
return start;
}
static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio)
{
if (xa_is_value(folio))
return PAGE_SIZE << xas_get_order(xas);
return folio_size(folio);
}
/**
* mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache.
* @mapping: Address space to search.
* @start: First byte to consider.
* @end: Limit of search (exclusive).
* @whence: Either SEEK_HOLE or SEEK_DATA.
*
* If the page cache knows which blocks contain holes and which blocks
* contain data, your filesystem can use this function to implement
* SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are
* entirely memory-based such as tmpfs, and filesystems which support
* unwritten extents.
*
* Return: The requested offset on success, or -ENXIO if @whence specifies
* SEEK_DATA and there is no data after @start. There is an implicit hole
* after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start
* and @end contain data.
*/
loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
loff_t end, int whence)
{
XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
pgoff_t max = (end - 1) >> PAGE_SHIFT;
bool seek_data = (whence == SEEK_DATA);
struct folio *folio;
if (end <= start)
return -ENXIO;
rcu_read_lock();
while ((folio = find_get_entry(&xas, max, XA_PRESENT))) {
loff_t pos = (u64)xas.xa_index << PAGE_SHIFT;
size_t seek_size;
if (start < pos) {
if (!seek_data)
goto unlock;
start = pos;
}
seek_size = seek_folio_size(&xas, folio);
pos = round_up((u64)pos + 1, seek_size);
start = folio_seek_hole_data(&xas, mapping, folio, start, pos,
seek_data);
if (start < pos)
goto unlock;
if (start >= end)
break;
if (seek_size > PAGE_SIZE)
xas_set(&xas, pos >> PAGE_SHIFT);
if (!xa_is_value(folio))
folio_put(folio);
}
if (seek_data)
start = -ENXIO;
unlock:
rcu_read_unlock();
if (folio && !xa_is_value(folio))
folio_put(folio);
if (start > end)
return end;
return start;
}
#ifdef CONFIG_MMU
#define MMAP_LOTSAMISS (100)
/*
* lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
* @vmf - the vm_fault for this fault.
* @folio - the folio to lock.
* @fpin - the pointer to the file we may pin (or is already pinned).
*
* This works similar to lock_folio_or_retry in that it can drop the
* mmap_lock. It differs in that it actually returns the folio locked
* if it returns 1 and 0 if it couldn't lock the folio. If we did have
* to drop the mmap_lock then fpin will point to the pinned file and
* needs to be fput()'ed at a later point.
*/
static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio,
struct file **fpin)
{
if (folio_trylock(folio))
return 1;
/*
* NOTE! This will make us return with VM_FAULT_RETRY, but with
* the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT
* is supposed to work. We have way too many special cases..
*/
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
if (__folio_lock_killable(folio)) {
/*
* We didn't have the right flags to drop the
* fault lock, but all fault_handlers only check
* for fatal signals if we return VM_FAULT_RETRY,
* so we need to drop the fault lock here and
* return 0 if we don't have a fpin.
*/
if (*fpin == NULL) release_fault_lock(vmf);
return 0;
}
} else
__folio_lock(folio);
return 1;
}
/*
* Synchronous readahead happens when we don't even find a page in the page
* cache at all. We don't want to perform IO under the mmap sem, so if we have
* to drop the mmap sem we return the file that was pinned in order for us to do
* that. If we didn't pin a file then we return NULL. The file that is
* returned needs to be fput()'ed when we're done with it.
*/
static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
struct file *fpin = NULL;
unsigned long vm_flags = vmf->vma->vm_flags;
unsigned int mmap_miss;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* Use the readahead code, even if readahead is disabled */
if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
ra->size = HPAGE_PMD_NR;
/*
* Fetch two PMD folios, so we get the chance to actually
* readahead, unless we've been told not to.
*/
if (!(vm_flags & VM_RAND_READ))
ra->size *= 2;
ra->async_size = HPAGE_PMD_NR;
page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER);
return fpin;
}
#endif
/* If we don't want any read-ahead, don't bother */
if (vm_flags & VM_RAND_READ)
return fpin;
if (!ra->ra_pages)
return fpin;
if (vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_sync_ra(&ractl, ra->ra_pages);
return fpin;
}
/* Avoid banging the cache line if not needed */
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss < MMAP_LOTSAMISS * 10)
WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
if (mmap_miss > MMAP_LOTSAMISS)
return fpin;
/*
* mmap read-around
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
ractl._index = ra->start;
page_cache_ra_order(&ractl, ra, 0);
return fpin;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
* so we want to possibly extend the readahead further. We return the file that
* was pinned if we have to drop the mmap_lock in order to do IO.
*/
static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct folio *folio)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff);
struct file *fpin = NULL;
unsigned int mmap_miss;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
return fpin;
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_async_ra(&ractl, folio, ra->ra_pages);
}
return fpin;
}
static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret = 0;
pte_t *ptep;
/*
* We might have COW'ed a pagecache folio and might now have an mlocked
* anon folio mapped. The original pagecache folio is not mlocked and
* might have been evicted. During a read+clear/modify/write update of
* the PTE, such as done in do_numa_page()/change_pte_range(), we
* temporarily clear the PTE under PT lock and might detect it here as
* "none" when not holding the PT lock.
*
* Not rechecking the PTE under PT lock could result in an unexpected
* major fault in an mlock'ed region. Recheck only for this special
* scenario while holding the PT lock, to not degrade non-mlocked
* scenarios. Recheck the PTE without PT lock firstly, thereby reducing
* the number of times we hold PT lock.
*/
if (!(vma->vm_flags & VM_LOCKED))
return 0;
if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID))
return 0;
ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (unlikely(!ptep))
return VM_FAULT_NOPAGE;
if (unlikely(!pte_none(ptep_get_lockless(ptep)))) {
ret = VM_FAULT_NOPAGE;
} else {
spin_lock(vmf->ptl);
if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE;
spin_unlock(vmf->ptl);
}
pte_unmap(ptep);
return ret;
}
/**
* filemap_fault - read in file data for page fault handling
* @vmf: struct vm_fault containing details of the fault
*
* filemap_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*
* vma->vm_mm->mmap_lock must be held on entry.
*
* If our return value has VM_FAULT_RETRY set, it's because the mmap_lock
* may be dropped before doing I/O or by lock_folio_maybe_drop_mmap().
*
* If our return value does not have VM_FAULT_RETRY set, the mmap_lock
* has not been released.
*
* We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
*
* Return: bitwise-OR of %VM_FAULT_ codes.
*/
vm_fault_t filemap_fault(struct vm_fault *vmf)
{
int error;
struct file *file = vmf->vma->vm_file;
struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
pgoff_t max_idx, index = vmf->pgoff;
struct folio *folio;
vm_fault_t ret = 0;
bool mapping_locked = false;
max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(index >= max_idx))
return VM_FAULT_SIGBUS;
trace_mm_filemap_fault(mapping, index);
/*
* Do we have something in the page cache already?
*/
folio = filemap_get_folio(mapping, index);
if (likely(!IS_ERR(folio))) {
/*
* We found the page, so try async readahead before waiting for
* the lock.
*/
if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping);
mapping_locked = true;
}
} else {
ret = filemap_fault_recheck_pte_none(vmf);
if (unlikely(ret))
return ret;
/* No page in the page cache at all */
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
fpin = do_sync_mmap_readahead(vmf);
retry_find:
/*
* See comment in filemap_create_folio() why we need
* invalidate_lock
*/
if (!mapping_locked) { filemap_invalidate_lock_shared(mapping);
mapping_locked = true;
}
folio = __filemap_get_folio(mapping, index,
FGP_CREAT|FGP_FOR_MMAP,
vmf->gfp_mask);
if (IS_ERR(folio)) { if (fpin)
goto out_retry;
filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_OOM;
}
}
if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin))
goto out_retry;
/* Did it get truncated? */
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
folio_put(folio);
goto retry_find;
}
VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
/*
* We have a locked folio in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error,
* or because readahead was otherwise unable to retrieve it.
*/
if (unlikely(!folio_test_uptodate(folio))) {
/*
* If the invalidate lock is not held, the folio was in cache
* and uptodate and now it is not. Strange but possible since we
* didn't hold the page lock all the time. Let's drop
* everything, get the invalidate lock and try again.
*/
if (!mapping_locked) {
folio_unlock(folio);
folio_put(folio);
goto retry_find;
}
/*
* OK, the folio is really not uptodate. This can be because the
* VMA has the VM_RAND_READ flag set, or because an error
* arose. Let's read it in directly.
*/
goto page_not_uptodate;
}
/*
* We've made it this far and we had to drop our mmap_lock, now is the
* time to return to the upper layer and have it re-find the vma and
* redo the fault.
*/
if (fpin) {
folio_unlock(folio);
goto out_retry;
}
if (mapping_locked) filemap_invalidate_unlock_shared(mapping);
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(index >= max_idx)) {
folio_unlock(folio);
folio_put(folio);
return VM_FAULT_SIGBUS;
}
vmf->page = folio_file_page(folio, index);
return ret | VM_FAULT_LOCKED;
page_not_uptodate:
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
* because there really aren't any performance issues here
* and we need to check for errors.
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (fpin)
goto out_retry;
folio_put(folio);
if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_SIGBUS;
out_retry:
/*
* We dropped the mmap_lock, we need to return to the fault handler to
* re-find the vma and come back and find our hopefully still populated
* page.
*/
if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin);
return ret | VM_FAULT_RETRY;
}
EXPORT_SYMBOL(filemap_fault);
static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
pgoff_t start)
{
struct mm_struct *mm = vmf->vma->vm_mm;
/* Huge page is mapped? No need to proceed. */
if (pmd_trans_huge(*vmf->pmd)) {
folio_unlock(folio);
folio_put(folio);
return true;
}
if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start);
vm_fault_t ret = do_set_pmd(vmf, page);
if (!ret) {
/* The page is mapped successfully, reference consumed. */
folio_unlock(folio);
return true;
}
}
if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
return false;
}
static struct folio *next_uptodate_folio(struct xa_state *xas,
struct address_space *mapping, pgoff_t end_pgoff)
{
struct folio *folio = xas_next_entry(xas, end_pgoff);
unsigned long max_idx;
do {
if (!folio)
return NULL;
if (xas_retry(xas, folio))
continue;
if (xa_is_value(folio))
continue;
if (!folio_try_get(folio))
continue;
if (folio_test_locked(folio))
goto skip;
/* Has the page moved or been split? */
if (unlikely(folio != xas_reload(xas)))
goto skip;
if (!folio_test_uptodate(folio) || folio_test_readahead(folio))
goto skip;
if (!folio_trylock(folio))
goto skip;
if (folio->mapping != mapping)
goto unlock;
if (!folio_test_uptodate(folio))
goto unlock;
max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
if (xas->xa_index >= max_idx)
goto unlock;
return folio;
unlock:
folio_unlock(folio);
skip:
folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL);
return NULL;
}
/*
* Map page range [start_page, start_page + nr_pages) of folio.
* start_page is gotten from start by folio_page(folio, start)
*/
static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
struct folio *folio, unsigned long start,
unsigned long addr, unsigned int nr_pages,
unsigned long *rss, unsigned int *mmap_miss)
{
vm_fault_t ret = 0;
struct page *page = folio_page(folio, start);
unsigned int count = 0;
pte_t *old_ptep = vmf->pte;
do {
if (PageHWPoison(page + count))
goto skip;
/*
* If there are too many folios that are recently evicted
* in a file, they will probably continue to be evicted.
* In such situation, read-ahead is only a waste of IO.
* Don't decrease mmap_miss in this scenario to make sure
* we can stop read-ahead.
*/
if (!folio_test_workingset(folio))
(*mmap_miss)++;
/*
* NOTE: If there're PTE markers, we'll leave them to be
* handled in the specific fault path, and it'll prohibit the
* fault-around logic.
*/
if (!pte_none(ptep_get(&vmf->pte[count])))
goto skip;
count++;
continue;
skip:
if (count) {
set_pte_range(vmf, folio, page, count, addr);
*rss += count;
folio_ref_add(folio, count);
if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
count++;
page += count;
vmf->pte += count;
addr += count * PAGE_SIZE;
count = 0;
} while (--nr_pages > 0); if (count) {
set_pte_range(vmf, folio, page, count, addr);
*rss += count;
folio_ref_add(folio, count);
if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
vmf->pte = old_ptep;
return ret;
}
static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
struct folio *folio, unsigned long addr,
unsigned long *rss, unsigned int *mmap_miss)
{
vm_fault_t ret = 0;
struct page *page = &folio->page;
if (PageHWPoison(page))
return ret;
/* See comment of filemap_map_folio_range() */
if (!folio_test_workingset(folio))
(*mmap_miss)++;
/*
* NOTE: If there're PTE markers, we'll leave them to be
* handled in the specific fault path, and it'll prohibit
* the fault-around logic.
*/
if (!pte_none(ptep_get(vmf->pte)))
return ret;
if (vmf->address == addr)
ret = VM_FAULT_NOPAGE;
set_pte_range(vmf, folio, page, 1, addr);
(*rss)++;
folio_ref_inc(folio);
return ret;
}
vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff)
{
struct vm_area_struct *vma = vmf->vma;
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
pgoff_t file_end, last_pgoff = start_pgoff;
unsigned long addr;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct folio *folio;
vm_fault_t ret = 0;
unsigned long rss = 0;
unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type;
rcu_read_lock();
folio = next_uptodate_folio(&xas, mapping, end_pgoff);
if (!folio)
goto out;
if (filemap_map_pmd(vmf, folio, start_pgoff)) {
ret = VM_FAULT_NOPAGE;
goto out;
}
addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
if (!vmf->pte) {
folio_unlock(folio);
folio_put(folio);
goto out;
}
file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
if (end_pgoff > file_end)
end_pgoff = file_end;
folio_type = mm_counter_file(folio);
do {
unsigned long end;
addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
vmf->pte += xas.xa_index - last_pgoff;
last_pgoff = xas.xa_index;
end = folio_next_index(folio) - 1;
nr_pages = min(end, end_pgoff) - xas.xa_index + 1;
if (!folio_test_large(folio))
ret |= filemap_map_order0_folio(vmf,
folio, addr, &rss, &mmap_miss);
else
ret |= filemap_map_folio_range(vmf, folio,
xas.xa_index - folio->index, addr,
nr_pages, &rss, &mmap_miss);
folio_unlock(folio);
folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
add_mm_counter(vma->vm_mm, folio_type, rss);
pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff);
out:
rcu_read_unlock();
mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss);
if (mmap_miss >= mmap_miss_saved)
WRITE_ONCE(file->f_ra.mmap_miss, 0);
else
WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss);
return ret;
}
EXPORT_SYMBOL(filemap_map_pages);
vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
struct folio *folio = page_folio(vmf->page);
vm_fault_t ret = VM_FAULT_LOCKED;
sb_start_pagefault(mapping->host->i_sb);
file_update_time(vmf->vma->vm_file);
folio_lock(folio);
if (folio->mapping != mapping) {
folio_unlock(folio);
ret = VM_FAULT_NOPAGE;
goto out;
}
/*
* We mark the folio dirty already here so that when freeze is in
* progress, we are guaranteed that writeback during freezing will
* see the dirty folio and writeprotect it again.
*/
folio_mark_dirty(folio);
folio_wait_stable(folio);
out:
sb_end_pagefault(mapping->host->i_sb);
return ret;
}
const struct vm_operations_struct generic_file_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = filemap_page_mkwrite,
};
/* This is used for a general mmap of a disk file */
int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct address_space *mapping = file->f_mapping;
if (!mapping->a_ops->read_folio)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &generic_file_vm_ops;
return 0;
}
/*
* This is for filesystems which do not implement ->writepage.
*/
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
if (vma_is_shared_maywrite(vma))
return -EINVAL;
return generic_file_mmap(file, vma);
}
#else
vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
}
int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
#endif /* CONFIG_MMU */
EXPORT_SYMBOL(filemap_page_mkwrite);
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
static struct folio *do_read_cache_folio(struct address_space *mapping,
pgoff_t index, filler_t filler, struct file *file, gfp_t gfp)
{
struct folio *folio;
int err;
if (!filler)
filler = mapping->a_ops->read_folio;
repeat:
folio = filemap_get_folio(mapping, index);
if (IS_ERR(folio)) {
folio = filemap_alloc_folio(gfp,
mapping_min_folio_order(mapping));
if (!folio)
return ERR_PTR(-ENOMEM);
index = mapping_align_index(mapping, index);
err = filemap_add_folio(mapping, folio, index, gfp);
if (unlikely(err)) {
folio_put(folio);
if (err == -EEXIST)
goto repeat;
/* Presumably ENOMEM for xarray node */
return ERR_PTR(err);
}
goto filler;
}
if (folio_test_uptodate(folio))
goto out;
if (!folio_trylock(folio)) {
folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE);
goto repeat;
}
/* Folio was truncated from mapping */
if (!folio->mapping) {
folio_unlock(folio);
folio_put(folio);
goto repeat;
}
/* Someone else locked and filled the page in a very small window */
if (folio_test_uptodate(folio)) {
folio_unlock(folio);
goto out;
}
filler:
err = filemap_read_folio(file, filler, folio);
if (err) {
folio_put(folio);
if (err == AOP_TRUNCATED_PAGE)
goto repeat;
return ERR_PTR(err);
}
out:
folio_mark_accessed(folio);
return folio;
}
/**
* read_cache_folio - Read into page cache, fill it if needed.
* @mapping: The address_space to read from.
* @index: The index to read.
* @filler: Function to perform the read, or NULL to use aops->read_folio().
* @file: Passed to filler function, may be NULL if not required.
*
* Read one page into the page cache. If it succeeds, the folio returned
* will contain @index, but it may not be the first page of the folio.
*
* If the filler function returns an error, it will be returned to the
* caller.
*
* Context: May sleep. Expects mapping->invalidate_lock to be held.
* Return: An uptodate folio on success, ERR_PTR() on failure.
*/
struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index,
filler_t filler, struct file *file)
{
return do_read_cache_folio(mapping, index, filler, file,
mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_folio);
/**
* mapping_read_folio_gfp - Read into page cache, using specified allocation flags.
* @mapping: The address_space for the folio.
* @index: The index that the allocated folio will contain.
* @gfp: The page allocator flags to use if allocating.
*
* This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with
* any new memory allocations done using the specified allocation flags.
*
* The most likely error from this function is EIO, but ENOMEM is
* possible and so is EINTR. If ->read_folio returns another error,
* that will be returned to the caller.
*
* The function expects mapping->invalidate_lock to be already held.
*
* Return: Uptodate folio on success, ERR_PTR() on failure.
*/
struct folio *mapping_read_folio_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp)
{
return do_read_cache_folio(mapping, index, NULL, NULL, gfp);
}
EXPORT_SYMBOL(mapping_read_folio_gfp);
static struct page *do_read_cache_page(struct address_space *mapping,
pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp)
{
struct folio *folio;
folio = do_read_cache_folio(mapping, index, filler, file, gfp);
if (IS_ERR(folio))
return &folio->page;
return folio_file_page(folio, index);
}
struct page *read_cache_page(struct address_space *mapping,
pgoff_t index, filler_t *filler, struct file *file)
{
return do_read_cache_page(mapping, index, filler, file,
mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_page);
/**
* read_cache_page_gfp - read into page cache, using specified page allocation flags.
* @mapping: the page's address_space
* @index: the page index
* @gfp: the page allocator flags to use if allocating
*
* This is the same as "read_mapping_page(mapping, index, NULL)", but with
* any new page allocations done using the specified allocation flags.
*
* If the page does not get brought uptodate, return -EIO.
*
* The function expects mapping->invalidate_lock to be already held.
*
* Return: up to date page on success, ERR_PTR() on failure.
*/
struct page *read_cache_page_gfp(struct address_space *mapping,
pgoff_t index,
gfp_t gfp)
{
return do_read_cache_page(mapping, index, NULL, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);
/*
* Warn about a page cache invalidation failure during a direct I/O write.
*/
static void dio_warn_stale_pagecache(struct file *filp)
{
static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
char pathname[128];
char *path;
errseq_set(&filp->f_mapping->wb_err, -EIO);
if (__ratelimit(&_rs)) {
path = file_path(filp, pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
current->comm);
}
}
void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
if (mapping->nrpages &&
invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT,
(iocb->ki_pos + count - 1) >> PAGE_SHIFT))
dio_warn_stale_pagecache(iocb->ki_filp);
}
ssize_t
generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
size_t write_len = iov_iter_count(from);
ssize_t written;
/*
* If a page can not be invalidated, return 0 to fall back
* to buffered write.
*/
written = kiocb_invalidate_pages(iocb, write_len);
if (written) {
if (written == -EBUSY)
return 0;
return written;
}
written = mapping->a_ops->direct_IO(iocb, from);
/*
* Finally, try again to invalidate clean pages which might have been
* cached by non-direct readahead, or faulted in by get_user_pages()
* if the source of the write was an mmap'ed region of the file
* we're writing. Either one is a pretty crazy thing to do,
* so we don't support it 100%. If this invalidation
* fails, tough, the write still worked...
*
* Most of the time we do not need this since dio_complete() will do
* the invalidation for us. However there are some file systems that
* do not end up with dio_complete() being called, so let's not break
* them by removing it completely.
*
* Noticeable example is a blkdev_direct_IO().
*
* Skip invalidation for async writes or if mapping has no pages.
*/
if (written > 0) {
struct inode *inode = mapping->host;
loff_t pos = iocb->ki_pos;
kiocb_invalidate_post_direct_write(iocb, written);
pos += written;
write_len -= written;
if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
iocb->ki_pos = pos;
}
if (written != -EIOCBQUEUED)
iov_iter_revert(from, write_len - iov_iter_count(from));
return written;
}
EXPORT_SYMBOL(generic_file_direct_write);
ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
{
struct file *file = iocb->ki_filp;
loff_t pos = iocb->ki_pos;
struct address_space *mapping = file->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
size_t chunk = mapping_max_folio_size(mapping);
long status = 0;
ssize_t written = 0;
do {
struct folio *folio;
size_t offset; /* Offset into folio */
size_t bytes; /* Bytes to write to folio */
size_t copied; /* Bytes copied from user */
void *fsdata = NULL;
bytes = iov_iter_count(i);
retry:
offset = pos & (chunk - 1);
bytes = min(chunk - offset, bytes);
balance_dirty_pages_ratelimited(mapping);
if (fatal_signal_pending(current)) {
status = -EINTR;
break;
}
status = a_ops->write_begin(file, mapping, pos, bytes,
&folio, &fsdata);
if (unlikely(status < 0))
break;
offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio);
/*
* Faults here on mmap()s can recurse into arbitrary
* filesystem code. Lots of locks are held that can
* deadlock. Use an atomic copy to avoid deadlocking
* in page fault handling.
*/
copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
flush_dcache_folio(folio);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
folio, fsdata);
if (unlikely(status != copied)) {
iov_iter_revert(i, copied - max(status, 0L));
if (unlikely(status < 0))
break;
}
cond_resched();
if (unlikely(status == 0)) {
/*
* A short copy made ->write_end() reject the
* thing entirely. Might be memory poisoning
* halfway through, might be a race with munmap,
* might be severe memory pressure.
*/
if (chunk > PAGE_SIZE)
chunk /= 2;
if (copied) {
bytes = copied;
goto retry;
}
/*
* 'folio' is now unlocked and faults on it can be
* handled. Ensure forward progress by trying to
* fault it in now.
*/
if (fault_in_iov_iter_readable(i, bytes) == bytes) {
status = -EFAULT;
break;
}
} else {
pos += status;
written += status;
}
} while (iov_iter_count(i)); if (!written)
return status;
iocb->ki_pos += written;
return written;
}
EXPORT_SYMBOL(generic_perform_write);
/**
* __generic_file_write_iter - write data to a file
* @iocb: IO state structure (file, offset, etc.)
* @from: iov_iter with data to write
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
* modification times and calls proper subroutines depending on whether we
* do direct IO or a standard buffered write.
*
* It expects i_rwsem to be grabbed unless we work on a block device or similar
* object which does not need locking at all.
*
* This function does *not* take care of syncing data in case of O_SYNC write.
* A caller has to handle it. This is mainly due to the fact that we want to
* avoid syncing under i_rwsem.
*
* Return:
* * number of bytes written, even for truncated writes
* * negative error code if no data has been written at all
*/
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
ret = file_remove_privs(file);
if (ret)
return ret;
ret = file_update_time(file);
if (ret)
return ret;
if (iocb->ki_flags & IOCB_DIRECT) {
ret = generic_file_direct_write(iocb, from);
/*
* If the write stopped short of completing, fall back to
* buffered writes. Some filesystems do this for writes to
* holes, for example. For DAX files, a buffered write will
* not succeed (even if it did, DAX does not handle dirty
* page-cache pages correctly).
*/
if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode))
return ret;
return direct_write_fallback(iocb, from, ret,
generic_perform_write(iocb, from));
}
return generic_perform_write(iocb, from);
}
EXPORT_SYMBOL(__generic_file_write_iter);
/**
* generic_file_write_iter - write data to a file
* @iocb: IO state structure
* @from: iov_iter with data to write
*
* This is a wrapper around __generic_file_write_iter() to be used by most
* filesystems. It takes care of syncing the file in case of O_SYNC file
* and acquires i_rwsem as needed.
* Return:
* * negative error code if no data has been written at all of
* vfs_fsync_range() failed for a synchronous write
* * number of bytes written, even for truncated writes
*/
ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
inode_lock(inode);
ret = generic_write_checks(iocb, from);
if (ret > 0)
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
}
EXPORT_SYMBOL(generic_file_write_iter);
/**
* filemap_release_folio() - Release fs-specific metadata on a folio.
* @folio: The folio which the kernel is trying to free.
* @gfp: Memory allocation flags (and I/O mode).
*
* The address_space is trying to release any data attached to a folio
* (presumably at folio->private).
*
* This will also be called if the private_2 flag is set on a page,
* indicating that the folio has other metadata associated with it.
*
* The @gfp argument specifies whether I/O may be performed to release
* this page (__GFP_IO), and whether the call may block
* (__GFP_RECLAIM & __GFP_FS).
*
* Return: %true if the release was successful, otherwise %false.
*/
bool filemap_release_folio(struct folio *folio, gfp_t gfp)
{
struct address_space * const mapping = folio->mapping;
BUG_ON(!folio_test_locked(folio));
if (!folio_needs_release(folio))
return true;
if (folio_test_writeback(folio))
return false;
if (mapping && mapping->a_ops->release_folio)
return mapping->a_ops->release_folio(folio, gfp);
return try_to_free_buffers(folio);
}
EXPORT_SYMBOL(filemap_release_folio);
/**
* filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache
* @inode: The inode to flush
* @flush: Set to write back rather than simply invalidate.
* @start: First byte to in range.
* @end: Last byte in range (inclusive), or LLONG_MAX for everything from start
* onwards.
*
* Invalidate all the folios on an inode that contribute to the specified
* range, possibly writing them back first. Whilst the operation is
* undertaken, the invalidate lock is held to prevent new folios from being
* installed.
*/
int filemap_invalidate_inode(struct inode *inode, bool flush,
loff_t start, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t first = start >> PAGE_SHIFT;
pgoff_t last = end >> PAGE_SHIFT;
pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1;
if (!mapping || !mapping->nrpages || end < start)
goto out;
/* Prevent new folios from being added to the inode. */
filemap_invalidate_lock(mapping);
if (!mapping->nrpages)
goto unlock;
unmap_mapping_pages(mapping, first, nr, false);
/* Write back the data if we're asked to. */
if (flush) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
filemap_fdatawrite_wbc(mapping, &wbc);
}
/* Wait for writeback to complete on all folios and discard. */
invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE);
unlock:
filemap_invalidate_unlock(mapping);
out:
return filemap_check_errors(mapping);
}
EXPORT_SYMBOL_GPL(filemap_invalidate_inode);
#ifdef CONFIG_CACHESTAT_SYSCALL
/**
* filemap_cachestat() - compute the page cache statistics of a mapping
* @mapping: The mapping to compute the statistics for.
* @first_index: The starting page cache index.
* @last_index: The final page index (inclusive).
* @cs: the cachestat struct to write the result to.
*
* This will query the page cache statistics of a mapping in the
* page range of [first_index, last_index] (inclusive). The statistics
* queried include: number of dirty pages, number of pages marked for
* writeback, and the number of (recently) evicted pages.
*/
static void filemap_cachestat(struct address_space *mapping,
pgoff_t first_index, pgoff_t last_index, struct cachestat *cs)
{
XA_STATE(xas, &mapping->i_pages, first_index);
struct folio *folio;
/* Flush stats (and potentially sleep) outside the RCU read section. */
mem_cgroup_flush_stats_ratelimited(NULL);
rcu_read_lock();
xas_for_each(&xas, folio, last_index) {
int order;
unsigned long nr_pages;
pgoff_t folio_first_index, folio_last_index;
/*
* Don't deref the folio. It is not pinned, and might
* get freed (and reused) underneath us.
*
* We *could* pin it, but that would be expensive for
* what should be a fast and lightweight syscall.
*
* Instead, derive all information of interest from
* the rcu-protected xarray.
*/
if (xas_retry(&xas, folio))
continue;
order = xas_get_order(&xas);
nr_pages = 1 << order;
folio_first_index = round_down(xas.xa_index, 1 << order);
folio_last_index = folio_first_index + nr_pages - 1;
/* Folios might straddle the range boundaries, only count covered pages */
if (folio_first_index < first_index)
nr_pages -= first_index - folio_first_index;
if (folio_last_index > last_index)
nr_pages -= folio_last_index - last_index;
if (xa_is_value(folio)) {
/* page is evicted */
void *shadow = (void *)folio;
bool workingset; /* not used */
cs->nr_evicted += nr_pages;
#ifdef CONFIG_SWAP /* implies CONFIG_MMU */
if (shmem_mapping(mapping)) {
/* shmem file - in swap cache */
swp_entry_t swp = radix_to_swp_entry(folio);
/* swapin error results in poisoned entry */
if (non_swap_entry(swp))
goto resched;
/*
* Getting a swap entry from the shmem
* inode means we beat
* shmem_unuse(). rcu_read_lock()
* ensures swapoff waits for us before
* freeing the swapper space. However,
* we can race with swapping and
* invalidation, so there might not be
* a shadow in the swapcache (yet).
*/
shadow = get_shadow_from_swap_cache(swp);
if (!shadow)
goto resched;
}
#endif
if (workingset_test_recent(shadow, true, &workingset, false))
cs->nr_recently_evicted += nr_pages;
goto resched;
}
/* page is in cache */
cs->nr_cache += nr_pages;
if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY))
cs->nr_dirty += nr_pages;
if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK))
cs->nr_writeback += nr_pages;
resched:
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
}
/*
* See mincore: reveal pagecache information only for files
* that the calling process has write access to, or could (if
* tried) open for writing.
*/
static inline bool can_do_cachestat(struct file *f)
{
if (f->f_mode & FMODE_WRITE)
return true;
if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f)))
return true;
return file_permission(f, MAY_WRITE) == 0;
}
/*
* The cachestat(2) system call.
*
* cachestat() returns the page cache statistics of a file in the
* bytes range specified by `off` and `len`: number of cached pages,
* number of dirty pages, number of pages marked for writeback,
* number of evicted pages, and number of recently evicted pages.
*
* An evicted page is a page that is previously in the page cache
* but has been evicted since. A page is recently evicted if its last
* eviction was recent enough that its reentry to the cache would
* indicate that it is actively being used by the system, and that
* there is memory pressure on the system.
*
* `off` and `len` must be non-negative integers. If `len` > 0,
* the queried range is [`off`, `off` + `len`]. If `len` == 0,
* we will query in the range from `off` to the end of the file.
*
* The `flags` argument is unused for now, but is included for future
* extensibility. User should pass 0 (i.e no flag specified).
*
* Currently, hugetlbfs is not supported.
*
* Because the status of a page can change after cachestat() checks it
* but before it returns to the application, the returned values may
* contain stale information.
*
* return values:
* zero - success
* -EFAULT - cstat or cstat_range points to an illegal address
* -EINVAL - invalid flags
* -EBADF - invalid file descriptor
* -EOPNOTSUPP - file descriptor is of a hugetlbfs file
*/
SYSCALL_DEFINE4(cachestat, unsigned int, fd,
struct cachestat_range __user *, cstat_range,
struct cachestat __user *, cstat, unsigned int, flags)
{
CLASS(fd, f)(fd);
struct address_space *mapping;
struct cachestat_range csr;
struct cachestat cs;
pgoff_t first_index, last_index;
if (fd_empty(f))
return -EBADF;
if (copy_from_user(&csr, cstat_range,
sizeof(struct cachestat_range)))
return -EFAULT;
/* hugetlbfs is not supported */
if (is_file_hugepages(fd_file(f)))
return -EOPNOTSUPP;
if (!can_do_cachestat(fd_file(f)))
return -EPERM;
if (flags != 0)
return -EINVAL;
first_index = csr.off >> PAGE_SHIFT;
last_index =
csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT;
memset(&cs, 0, sizeof(struct cachestat));
mapping = fd_file(f)->f_mapping;
filemap_cachestat(mapping, first_index, last_index, &cs);
if (copy_to_user(cstat, &cs, sizeof(struct cachestat)))
return -EFAULT;
return 0;
}
#endif /* CONFIG_CACHESTAT_SYSCALL */
// SPDX-License-Identifier: GPL-1.0+
/*
* originally based on the dummy device.
*
* Copyright 1999, Thomas Davis, tadavis@lbl.gov.
* Based on dummy.c, and eql.c devices.
*
* bonding.c: an Ethernet Bonding driver
*
* This is useful to talk to a Cisco EtherChannel compatible equipment:
* Cisco 5500
* Sun Trunking (Solaris)
* Alteon AceDirector Trunks
* Linux Bonding
* and probably many L2 switches ...
*
* How it works:
* ifconfig bond0 ipaddress netmask up
* will setup a network device, with an ip address. No mac address
* will be assigned at this time. The hw mac address will come from
* the first slave bonded to the channel. All slaves will then use
* this hw mac address.
*
* ifconfig bond0 down
* will release all slaves, marking them as down.
*
* ifenslave bond0 eth0
* will attach eth0 to bond0 as a slave. eth0 hw mac address will either
* a: be used as initial mac address
* b: if a hw mac address already is there, eth0's hw mac address
* will then be set from bond0.
*
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/filter.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <net/ip.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <asm/dma.h>
#include <linux/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include <linux/phy.h>
#include <linux/jiffies.h>
#include <linux/preempt.h>
#include <net/route.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/pkt_sched.h>
#include <linux/rculist.h>
#include <net/flow_dissector.h>
#include <net/xfrm.h>
#include <net/bonding.h>
#include <net/bond_3ad.h>
#include <net/bond_alb.h>
#if IS_ENABLED(CONFIG_TLS_DEVICE)
#include <net/tls.h>
#endif
#include <net/ip6_route.h>
#include <net/netdev_lock.h>
#include <net/xdp.h>
#include "bonding_priv.h"
/*---------------------------- Module parameters ----------------------------*/
/* monitor all links that often (in milliseconds). <=0 disables monitoring */
static int max_bonds = BOND_DEFAULT_MAX_BONDS;
static int tx_queues = BOND_DEFAULT_TX_QUEUES;
static int num_peer_notif = 1;
static int miimon;
static int updelay;
static int downdelay;
static int use_carrier = 1;
static char *mode;
static char *primary;
static char *primary_reselect;
static char *lacp_rate;
static int min_links;
static char *ad_select;
static char *xmit_hash_policy;
static int arp_interval;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
static char *arp_validate;
static char *arp_all_targets;
static char *fail_over_mac;
static int all_slaves_active;
static struct bond_params bonding_defaults;
static int resend_igmp = BOND_DEFAULT_RESEND_IGMP;
static int packets_per_slave = 1;
static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(tx_queues, int, 0);
MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
module_param_named(num_grat_arp, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on "
"failover event (alias of num_unsol_na)");
module_param_named(num_unsol_na, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on "
"failover event (alias of num_grat_arp)");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds");
module_param(downdelay, int, 0);
MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
"in milliseconds");
module_param(use_carrier, int, 0);
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
"0 for off, 1 for on (default)");
module_param(mode, charp, 0);
MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, "
"1 for active-backup, 2 for balance-xor, "
"3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
"6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(primary_reselect, charp, 0);
MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
"once it comes up; "
"0 for always (default), "
"1 for only if speed of primary is "
"better, "
"2 for only on active slave "
"failure");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; "
"0 for slow, 1 for fast");
module_param(ad_select, charp, 0);
MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; "
"0 for stable (default), 1 for bandwidth, "
"2 for count");
module_param(min_links, int, 0);
MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier");
module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; "
"0 for layer 2 (default), 1 for layer 3+4, "
"2 for layer 2+3, 3 for encap layer 2+3, "
"4 for encap layer 3+4, 5 for vlan+srcmac");
module_param(arp_interval, int, 0);
MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
module_param_array(arp_ip_target, charp, NULL, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
module_param(arp_validate, charp, 0);
MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; "
"0 for none (default), 1 for active, "
"2 for backup, 3 for all");
module_param(arp_all_targets, charp, 0);
MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all");
module_param(fail_over_mac, charp, 0);
MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to "
"the same MAC; 0 for none (default), "
"1 for active, 2 for follow");
module_param(all_slaves_active, int, 0);
MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface "
"by setting active flag for all slaves; "
"0 for never (default), 1 for always.");
module_param(resend_igmp, int, 0);
MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on "
"link failure");
module_param(packets_per_slave, int, 0);
MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr "
"mode; 0 for a random slave, 1 packet per "
"slave (default), >1 packets per slave.");
module_param(lp_interval, uint, 0);
MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where "
"the bonding driver sends learning packets to "
"each slaves peer switch. The default is 1.");
/*----------------------------- Global variables ----------------------------*/
#ifdef CONFIG_NET_POLL_CONTROLLER
atomic_t netpoll_block_tx = ATOMIC_INIT(0);
#endif
unsigned int bond_net_id __read_mostly;
static const struct flow_dissector_key flow_keys_bonding_keys[] = {
{
.key_id = FLOW_DISSECTOR_KEY_CONTROL,
.offset = offsetof(struct flow_keys, control),
},
{
.key_id = FLOW_DISSECTOR_KEY_BASIC,
.offset = offsetof(struct flow_keys, basic),
},
{
.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
.offset = offsetof(struct flow_keys, addrs.v4addrs),
},
{
.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
.offset = offsetof(struct flow_keys, addrs.v6addrs),
},
{
.key_id = FLOW_DISSECTOR_KEY_TIPC,
.offset = offsetof(struct flow_keys, addrs.tipckey),
},
{
.key_id = FLOW_DISSECTOR_KEY_PORTS,
.offset = offsetof(struct flow_keys, ports),
},
{
.key_id = FLOW_DISSECTOR_KEY_ICMP,
.offset = offsetof(struct flow_keys, icmp),
},
{
.key_id = FLOW_DISSECTOR_KEY_VLAN,
.offset = offsetof(struct flow_keys, vlan),
},
{
.key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL,
.offset = offsetof(struct flow_keys, tags),
},
{
.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
.offset = offsetof(struct flow_keys, keyid),
},
};
static struct flow_dissector flow_keys_bonding __read_mostly;
/*-------------------------- Forward declarations ---------------------------*/
static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);
static void bond_get_stats(struct net_device *bond_dev,
struct rtnl_link_stats64 *stats);
static void bond_slave_arr_handler(struct work_struct *work);
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod);
static void bond_netdev_notify_work(struct work_struct *work);
/*---------------------------- General routines -----------------------------*/
const char *bond_mode_name(int mode)
{
static const char *names[] = {
[BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)",
[BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)",
[BOND_MODE_XOR] = "load balancing (xor)",
[BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)",
[BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation",
[BOND_MODE_TLB] = "transmit load balancing",
[BOND_MODE_ALB] = "adaptive load balancing",
};
if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB)
return "unknown";
return names[mode];
}
/**
* bond_dev_queue_xmit - Prepare skb for xmit.
*
* @bond: bond device that got this skb for tx.
* @skb: hw accel VLAN tagged skb to transmit
* @slave_dev: slave that is supposed to xmit this skbuff
*/
netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
struct net_device *slave_dev)
{
skb->dev = slave_dev;
BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping));
skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
if (unlikely(netpoll_tx_running(bond->dev)))
return bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
return dev_queue_xmit(skb);
}
static bool bond_sk_check(struct bonding *bond)
{
switch (BOND_MODE(bond)) {
case BOND_MODE_8023AD:
case BOND_MODE_XOR:
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
return true;
fallthrough;
default:
return false;
}
}
bool bond_xdp_check(struct bonding *bond, int mode)
{
switch (mode) {
case BOND_MODE_ROUNDROBIN:
case BOND_MODE_ACTIVEBACKUP:
return true;
case BOND_MODE_8023AD:
case BOND_MODE_XOR:
/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
* payload is not in the packet due to hardware offload.
*/
if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
return true;
fallthrough;
default:
return false;
}
}
/*---------------------------------- VLAN -----------------------------------*/
/* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
* We don't protect the slave list iteration with a lock because:
* a. This operation is performed in IOCTL context,
* b. The operation is protected by the RTNL semaphore in the 8021q code,
* c. Holding a lock with BH disabled while directly calling a base driver
* entry point is generally a BAD idea.
*
* The design of synchronization/protection for this operation in the 8021q
* module is good for one or more VLAN devices over a single physical device
* and cannot be extended for a teaming solution like bonding, so there is a
* potential race condition here where a net device from the vlan group might
* be referenced (either by a base driver or the 8021q code) while it is being
* removed from the system. However, it turns out we're not making matters
* worse, and if it works for regular VLAN usage it will work here too.
*/
/**
* bond_vlan_rx_add_vid - Propagates adding an id to slaves
* @bond_dev: bonding net device that got called
* @proto: network protocol ID
* @vid: vlan id being added
*/
static int bond_vlan_rx_add_vid(struct net_device *bond_dev,
__be16 proto, u16 vid)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *rollback_slave;
struct list_head *iter;
int res;
bond_for_each_slave(bond, slave, iter) {
res = vlan_vid_add(slave->dev, proto, vid);
if (res)
goto unwind;
}
return 0;
unwind:
/* unwind to the slave that failed */
bond_for_each_slave(bond, rollback_slave, iter) {
if (rollback_slave == slave)
break;
vlan_vid_del(rollback_slave->dev, proto, vid);
}
return res;
}
/**
* bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
* @bond_dev: bonding net device that got called
* @proto: network protocol ID
* @vid: vlan id being removed
*/
static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
__be16 proto, u16 vid)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
bond_for_each_slave(bond, slave, iter)
vlan_vid_del(slave->dev, proto, vid);
if (bond_is_lb(bond))
bond_alb_clear_vlan(bond, vid);
return 0;
}
/*---------------------------------- XFRM -----------------------------------*/
#ifdef CONFIG_XFRM_OFFLOAD
/**
* bond_ipsec_dev - Get active device for IPsec offload
* @xs: pointer to transformer state struct
*
* Context: caller must hold rcu_read_lock.
*
* Return: the device for ipsec offload, or NULL if not exist.
**/
static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
struct bonding *bond;
struct slave *slave;
bond = netdev_priv(bond_dev);
if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
return NULL;
slave = rcu_dereference(bond->curr_active_slave);
if (!slave)
return NULL;
if (!xs->xso.real_dev)
return NULL;
if (xs->xso.real_dev != slave->dev)
pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n",
bond_dev->name, slave->dev->name, xs->xso.real_dev->name);
return slave->dev;
}
/**
* bond_ipsec_add_sa - program device with a security association
* @xs: pointer to transformer state struct
* @extack: extack point to fill failure reason
**/
static int bond_ipsec_add_sa(struct xfrm_state *xs,
struct netlink_ext_ack *extack)
{
struct net_device *bond_dev = xs->xso.dev;
struct net_device *real_dev;
netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
int err;
if (!bond_dev)
return -EINVAL;
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
real_dev = slave ? slave->dev : NULL;
netdev_hold(real_dev, &tracker, GFP_ATOMIC);
rcu_read_unlock();
if (!real_dev) {
err = -ENODEV;
goto out;
}
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_add ||
netif_is_bond_master(real_dev)) {
NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
err = -EINVAL;
goto out;
}
ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
if (!ipsec) {
err = -ENOMEM;
goto out;
}
xs->xso.real_dev = real_dev;
err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
if (!err) {
ipsec->xs = xs;
INIT_LIST_HEAD(&ipsec->list);
mutex_lock(&bond->ipsec_lock);
list_add(&ipsec->list, &bond->ipsec_list);
mutex_unlock(&bond->ipsec_lock);
} else {
kfree(ipsec);
}
out:
netdev_put(real_dev, &tracker);
return err;
}
static void bond_ipsec_add_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
slave = rtnl_dereference(bond->curr_active_slave);
real_dev = slave ? slave->dev : NULL;
if (!real_dev)
return;
mutex_lock(&bond->ipsec_lock);
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_add ||
netif_is_bond_master(real_dev)) {
if (!list_empty(&bond->ipsec_list))
slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_add\n",
__func__);
goto out;
}
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
/* If new state is added before ipsec_lock acquired */
if (ipsec->xs->xso.real_dev == real_dev)
continue;
ipsec->xs->xso.real_dev = real_dev;
if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
ipsec->xs->xso.real_dev = NULL;
}
}
out:
mutex_unlock(&bond->ipsec_lock);
}
/**
* bond_ipsec_del_sa - clear out this specific SA
* @xs: pointer to transformer state struct
**/
static void bond_ipsec_del_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
struct net_device *real_dev;
netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
if (!bond_dev)
return;
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
real_dev = slave ? slave->dev : NULL;
netdev_hold(real_dev, &tracker, GFP_ATOMIC);
rcu_read_unlock();
if (!slave)
goto out;
if (!xs->xso.real_dev)
goto out;
WARN_ON(xs->xso.real_dev != real_dev);
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_delete ||
netif_is_bond_master(real_dev)) {
slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
goto out;
}
real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
out:
netdev_put(real_dev, &tracker);
mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (ipsec->xs == xs) {
list_del(&ipsec->list);
kfree(ipsec);
break;
}
}
mutex_unlock(&bond->ipsec_lock);
}
static void bond_ipsec_del_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
slave = rtnl_dereference(bond->curr_active_slave);
real_dev = slave ? slave->dev : NULL;
if (!real_dev)
return;
mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (!ipsec->xs->xso.real_dev)
continue;
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_delete ||
netif_is_bond_master(real_dev)) {
slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_delete\n",
__func__);
} else {
real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
if (real_dev->xfrmdev_ops->xdo_dev_state_free)
real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
}
}
mutex_unlock(&bond->ipsec_lock);
}
static void bond_ipsec_free_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
struct net_device *real_dev;
netdevice_tracker tracker;
struct bonding *bond;
struct slave *slave;
if (!bond_dev)
return;
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
real_dev = slave ? slave->dev : NULL;
netdev_hold(real_dev, &tracker, GFP_ATOMIC);
rcu_read_unlock();
if (!slave)
goto out;
if (!xs->xso.real_dev)
goto out;
WARN_ON(xs->xso.real_dev != real_dev);
if (real_dev && real_dev->xfrmdev_ops &&
real_dev->xfrmdev_ops->xdo_dev_state_free)
real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
out:
netdev_put(real_dev, &tracker);
}
/**
* bond_ipsec_offload_ok - can this packet use the xfrm hw offload
* @skb: current data packet
* @xs: pointer to transformer state struct
**/
static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
struct net_device *real_dev;
rcu_read_lock();
real_dev = bond_ipsec_dev(xs);
if (!real_dev || netif_is_bond_master(real_dev)) {
rcu_read_unlock();
return false;
}
rcu_read_unlock();
return true;
}
/**
* bond_advance_esn_state - ESN support for IPSec HW offload
* @xs: pointer to transformer state struct
**/
static void bond_advance_esn_state(struct xfrm_state *xs)
{
struct net_device *real_dev;
rcu_read_lock();
real_dev = bond_ipsec_dev(xs);
if (!real_dev)
goto out;
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name);
goto out;
}
real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs);
out:
rcu_read_unlock();
}
/**
* bond_xfrm_update_stats - Update xfrm state
* @xs: pointer to transformer state struct
**/
static void bond_xfrm_update_stats(struct xfrm_state *xs)
{
struct net_device *real_dev;
rcu_read_lock();
real_dev = bond_ipsec_dev(xs);
if (!real_dev)
goto out;
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_state_update_stats) {
pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name);
goto out;
}
real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs);
out:
rcu_read_unlock();
}
static const struct xfrmdev_ops bond_xfrmdev_ops = {
.xdo_dev_state_add = bond_ipsec_add_sa,
.xdo_dev_state_delete = bond_ipsec_del_sa,
.xdo_dev_state_free = bond_ipsec_free_sa,
.xdo_dev_offload_ok = bond_ipsec_offload_ok,
.xdo_dev_state_advance_esn = bond_advance_esn_state,
.xdo_dev_state_update_stats = bond_xfrm_update_stats,
};
#endif /* CONFIG_XFRM_OFFLOAD */
/*------------------------------- Link status -------------------------------*/
/* Set the carrier state for the master according to the state of its
* slaves. If any slaves are up, the master is up. In 802.3ad mode,
* do special 802.3ad magic.
*
* Returns zero if carrier state does not change, nonzero if it does.
*/
int bond_set_carrier(struct bonding *bond)
{
struct list_head *iter;
struct slave *slave;
if (!bond_has_slaves(bond))
goto down;
if (BOND_MODE(bond) == BOND_MODE_8023AD)
return bond_3ad_set_carrier(bond);
bond_for_each_slave(bond, slave, iter) {
if (slave->link == BOND_LINK_UP) {
if (!netif_carrier_ok(bond->dev)) {
netif_carrier_on(bond->dev);
return 1;
}
return 0;
}
}
down:
if (netif_carrier_ok(bond->dev)) {
netif_carrier_off(bond->dev);
return 1;
}
return 0;
}
/* Get link speed and duplex from the slave's base driver
* using ethtool. If for some reason the call fails or the
* values are invalid, set speed and duplex to -1,
* and return. Return 1 if speed or duplex settings are
* UNKNOWN; 0 otherwise.
*/
static int bond_update_speed_duplex(struct slave *slave)
{
struct net_device *slave_dev = slave->dev;
struct ethtool_link_ksettings ecmd;
int res;
slave->speed = SPEED_UNKNOWN;
slave->duplex = DUPLEX_UNKNOWN;
res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
if (res < 0)
return 1;
if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
return 1;
switch (ecmd.base.duplex) {
case DUPLEX_FULL:
case DUPLEX_HALF:
break;
default:
return 1;
}
slave->speed = ecmd.base.speed;
slave->duplex = ecmd.base.duplex;
return 0;
}
const char *bond_slave_link_status(s8 link)
{
switch (link) {
case BOND_LINK_UP:
return "up";
case BOND_LINK_FAIL:
return "going down";
case BOND_LINK_DOWN:
return "down";
case BOND_LINK_BACK:
return "going back";
default:
return "unknown";
}
}
/* if <dev> supports MII link status reporting, check its link status.
*
* We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
* depending upon the setting of the use_carrier parameter.
*
* Return either BMSR_LSTATUS, meaning that the link is up (or we
* can't tell and just pretend it is), or 0, meaning that the link is
* down.
*
* If reporting is non-zero, instead of faking link up, return -1 if
* both ETHTOOL and MII ioctls fail (meaning the device does not
* support them). If use_carrier is set, return whatever it says.
* It'd be nice if there was a good way to tell if a driver supports
* netif_carrier, but there really isn't.
*/
static int bond_check_dev_link(struct bonding *bond,
struct net_device *slave_dev, int reporting)
{
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct mii_ioctl_data *mii;
struct ifreq ifr;
int ret;
if (!reporting && !netif_running(slave_dev))
return 0;
if (bond->params.use_carrier)
return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
/* Try to get link status using Ethtool first. */
if (slave_dev->ethtool_ops->get_link) {
netdev_lock_ops(slave_dev);
ret = slave_dev->ethtool_ops->get_link(slave_dev);
netdev_unlock_ops(slave_dev);
return ret ? BMSR_LSTATUS : 0;
}
/* Ethtool can't be used, fallback to MII ioctls. */
if (slave_ops->ndo_eth_ioctl) {
/* TODO: set pointer to correct ioctl on a per team member
* bases to make this more efficient. that is, once
* we determine the correct ioctl, we will always
* call it and not the others for that team
* member.
*/
/* We cannot assume that SIOCGMIIPHY will also read a
* register; not all network drivers (e.g., e100)
* support that.
*/
/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
mii = if_mii(&ifr);
if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
mii->reg_num = MII_BMSR;
if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
return mii->val_out & BMSR_LSTATUS;
}
}
/* If reporting, report that either there's no ndo_eth_ioctl,
* or both SIOCGMIIREG and get_link failed (meaning that we
* cannot report link status). If not reporting, pretend
* we're ok.
*/
return reporting ? -1 : BMSR_LSTATUS;
}
/*----------------------------- Multicast list ------------------------------*/
/* Push the promiscuity flag down to appropriate slaves */
static int bond_set_promiscuity(struct bonding *bond, int inc)
{
struct list_head *iter;
int err = 0;
if (bond_uses_primary(bond)) {
struct slave *curr_active = rtnl_dereference(bond->curr_active_slave);
if (curr_active)
err = dev_set_promiscuity(curr_active->dev, inc);
} else {
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
err = dev_set_promiscuity(slave->dev, inc);
if (err)
return err;
}
}
return err;
}
/* Push the allmulti flag down to all slaves */
static int bond_set_allmulti(struct bonding *bond, int inc)
{
struct list_head *iter;
int err = 0;
if (bond_uses_primary(bond)) {
struct slave *curr_active = rtnl_dereference(bond->curr_active_slave);
if (curr_active)
err = dev_set_allmulti(curr_active->dev, inc);
} else {
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
err = dev_set_allmulti(slave->dev, inc);
if (err)
return err;
}
}
return err;
}
/* Retrieve the list of registered multicast addresses for the bonding
* device and retransmit an IGMP JOIN request to the current active
* slave.
*/
static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
mcast_work.work);
if (!rtnl_trylock()) {
queue_delayed_work(bond->wq, &bond->mcast_work, 1);
return;
}
call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev);
if (bond->igmp_retrans > 1) {
bond->igmp_retrans--;
queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
}
rtnl_unlock();
}
/* Flush bond's hardware addresses from slave */
static void bond_hw_addr_flush(struct net_device *bond_dev,
struct net_device *slave_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
dev_uc_unsync(slave_dev, bond_dev);
dev_mc_unsync(slave_dev, bond_dev);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
dev_mc_del(slave_dev, lacpdu_mcast_addr);
}
/*--------------------------- Active slave change ---------------------------*/
/* Update the hardware address list and promisc/allmulti for the new and
* old active slaves (if any). Modes that are not using primary keep all
* slaves up date at all times; only the modes that use primary need to call
* this function to swap these settings during a failover.
*/
static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
struct slave *old_active)
{
if (old_active) {
if (bond->dev->flags & IFF_PROMISC)
dev_set_promiscuity(old_active->dev, -1);
if (bond->dev->flags & IFF_ALLMULTI)
dev_set_allmulti(old_active->dev, -1);
if (bond->dev->flags & IFF_UP)
bond_hw_addr_flush(bond->dev, old_active->dev);
bond_slave_ns_maddrs_add(bond, old_active);
}
if (new_active) {
/* FIXME: Signal errors upstream. */
if (bond->dev->flags & IFF_PROMISC)
dev_set_promiscuity(new_active->dev, 1);
if (bond->dev->flags & IFF_ALLMULTI)
dev_set_allmulti(new_active->dev, 1);
if (bond->dev->flags & IFF_UP) {
netif_addr_lock_bh(bond->dev);
dev_uc_sync(new_active->dev, bond->dev);
dev_mc_sync(new_active->dev, bond->dev);
netif_addr_unlock_bh(bond->dev);
}
bond_slave_ns_maddrs_del(bond, new_active);
}
}
/**
* bond_set_dev_addr - clone slave's address to bond
* @bond_dev: bond net device
* @slave_dev: slave net device
*
* Should be called with RTNL held.
*/
static int bond_set_dev_addr(struct net_device *bond_dev,
struct net_device *slave_dev)
{
int err;
slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
bond_dev, slave_dev, slave_dev->addr_len);
err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
if (err)
return err;
__dev_addr_set(bond_dev, slave_dev->dev_addr, slave_dev->addr_len);
bond_dev->addr_assign_type = NET_ADDR_STOLEN;
call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
return 0;
}
static struct slave *bond_get_old_active(struct bonding *bond,
struct slave *new_active)
{
struct slave *slave;
struct list_head *iter;
bond_for_each_slave(bond, slave, iter) {
if (slave == new_active)
continue;
if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
return slave;
}
return NULL;
}
/* bond_do_fail_over_mac
*
* Perform special MAC address swapping for fail_over_mac settings
*
* Called with RTNL
*/
static void bond_do_fail_over_mac(struct bonding *bond,
struct slave *new_active,
struct slave *old_active)
{
u8 tmp_mac[MAX_ADDR_LEN];
struct sockaddr_storage ss;
int rv;
switch (bond->params.fail_over_mac) {
case BOND_FOM_ACTIVE:
if (new_active) {
rv = bond_set_dev_addr(bond->dev, new_active->dev);
if (rv)
slave_err(bond->dev, new_active->dev, "Error %d setting bond MAC from slave\n",
-rv);
}
break;
case BOND_FOM_FOLLOW:
/* if new_active && old_active, swap them
* if just old_active, do nothing (going to no active slave)
* if just new_active, set new_active to bond's MAC
*/
if (!new_active)
return;
if (!old_active)
old_active = bond_get_old_active(bond, new_active);
if (old_active) {
bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
new_active->dev->addr_len);
bond_hw_addr_copy(ss.__data,
old_active->dev->dev_addr,
old_active->dev->addr_len);
ss.ss_family = new_active->dev->type;
} else {
bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
bond->dev->addr_len);
ss.ss_family = bond->dev->type;
}
rv = dev_set_mac_address(new_active->dev,
(struct sockaddr *)&ss, NULL);
if (rv) {
slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n",
-rv);
goto out;
}
if (!old_active)
goto out;
bond_hw_addr_copy(ss.__data, tmp_mac,
new_active->dev->addr_len);
ss.ss_family = old_active->dev->type;
rv = dev_set_mac_address(old_active->dev,
(struct sockaddr *)&ss, NULL);
if (rv)
slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n",
-rv);
out:
break;
default:
netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n",
bond->params.fail_over_mac);
break;
}
}
/**
* bond_choose_primary_or_current - select the primary or high priority slave
* @bond: our bonding struct
*
* - Check if there is a primary link. If the primary link was set and is up,
* go on and do link reselection.
*
* - If primary link is not set or down, find the highest priority link.
* If the highest priority link is not current slave, set it as primary
* link and do link reselection.
*/
static struct slave *bond_choose_primary_or_current(struct bonding *bond)
{
struct slave *prim = rtnl_dereference(bond->primary_slave);
struct slave *curr = rtnl_dereference(bond->curr_active_slave);
struct slave *slave, *hprio = NULL;
struct list_head *iter;
if (!prim || prim->link != BOND_LINK_UP) {
bond_for_each_slave(bond, slave, iter) {
if (slave->link == BOND_LINK_UP) {
hprio = hprio ?: slave;
if (slave->prio > hprio->prio)
hprio = slave;
}
}
if (hprio && hprio != curr) {
prim = hprio;
goto link_reselect;
}
if (!curr || curr->link != BOND_LINK_UP)
return NULL;
return curr;
}
if (bond->force_primary) {
bond->force_primary = false;
return prim;
}
link_reselect:
if (!curr || curr->link != BOND_LINK_UP)
return prim;
/* At this point, prim and curr are both up */
switch (bond->params.primary_reselect) {
case BOND_PRI_RESELECT_ALWAYS:
return prim;
case BOND_PRI_RESELECT_BETTER:
if (prim->speed < curr->speed)
return curr;
if (prim->speed == curr->speed && prim->duplex <= curr->duplex)
return curr;
return prim;
case BOND_PRI_RESELECT_FAILURE:
return curr;
default:
netdev_err(bond->dev, "impossible primary_reselect %d\n",
bond->params.primary_reselect);
return curr;
}
}
/**
* bond_find_best_slave - select the best available slave to be the active one
* @bond: our bonding struct
*/
static struct slave *bond_find_best_slave(struct bonding *bond)
{
struct slave *slave, *bestslave = NULL;
struct list_head *iter;
int mintime = bond->params.updelay;
slave = bond_choose_primary_or_current(bond);
if (slave)
return slave;
bond_for_each_slave(bond, slave, iter) {
if (slave->link == BOND_LINK_UP)
return slave;
if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) &&
slave->delay < mintime) {
mintime = slave->delay;
bestslave = slave;
}
}
return bestslave;
}
/* must be called in RCU critical section or with RTNL held */
static bool bond_should_notify_peers(struct bonding *bond)
{
struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
if (!slave || !bond->send_peer_notif ||
bond->send_peer_notif %
max(1, bond->params.peer_notif_delay) != 0 ||
!netif_carrier_ok(bond->dev) ||
test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
return false;
netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n",
slave ? slave->dev->name : "NULL");
return true;
}
/**
* bond_change_active_slave - change the active slave into the specified one
* @bond: our bonding struct
* @new_active: the new slave to make the active one
*
* Set the new slave to the bond's settings and unset them on the old
* curr_active_slave.
* Setting include flags, mc-list, promiscuity, allmulti, etc.
*
* If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP,
* because it is apparently the best available slave we have, even though its
* updelay hasn't timed out yet.
*
* Caller must hold RTNL.
*/
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
struct slave *old_active;
ASSERT_RTNL();
old_active = rtnl_dereference(bond->curr_active_slave);
if (old_active == new_active)
return;
#ifdef CONFIG_XFRM_OFFLOAD
bond_ipsec_del_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
if (new_active) {
new_active->last_link_up = jiffies;
if (new_active->link == BOND_LINK_BACK) {
if (bond_uses_primary(bond)) {
slave_info(bond->dev, new_active->dev, "making interface the new active one %d ms earlier\n",
(bond->params.updelay - new_active->delay) * bond->params.miimon);
}
new_active->delay = 0;
bond_set_slave_link_state(new_active, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
if (bond_is_lb(bond))
bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
} else {
if (bond_uses_primary(bond))
slave_info(bond->dev, new_active->dev, "making interface the new active one\n");
}
}
if (bond_uses_primary(bond))
bond_hw_addr_swap(bond, new_active, old_active);
if (bond_is_lb(bond)) {
bond_alb_handle_active_change(bond, new_active);
if (old_active)
bond_set_slave_inactive_flags(old_active,
BOND_SLAVE_NOTIFY_NOW);
if (new_active)
bond_set_slave_active_flags(new_active,
BOND_SLAVE_NOTIFY_NOW);
} else {
rcu_assign_pointer(bond->curr_active_slave, new_active);
}
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) {
if (old_active)
bond_set_slave_inactive_flags(old_active,
BOND_SLAVE_NOTIFY_NOW);
if (new_active) {
bool should_notify_peers = false;
bond_set_slave_active_flags(new_active,
BOND_SLAVE_NOTIFY_NOW);
if (bond->params.fail_over_mac)
bond_do_fail_over_mac(bond, new_active,
old_active);
if (netif_running(bond->dev)) {
bond->send_peer_notif =
bond->params.num_peer_notif *
max(1, bond->params.peer_notif_delay);
should_notify_peers =
bond_should_notify_peers(bond);
}
call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
if (should_notify_peers) {
bond->send_peer_notif--;
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
}
}
}
#ifdef CONFIG_XFRM_OFFLOAD
bond_ipsec_add_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
/* resend IGMP joins since active slave has changed or
* all were sent on curr_active_slave.
* resend only if bond is brought up with the affected
* bonding modes and the retransmission is enabled
*/
if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) &&
((bond_uses_primary(bond) && new_active) ||
BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) {
bond->igmp_retrans = bond->params.resend_igmp;
queue_delayed_work(bond->wq, &bond->mcast_work, 1);
}
}
/**
* bond_select_active_slave - select a new active slave, if needed
* @bond: our bonding struct
*
* This functions should be called when one of the following occurs:
* - The old curr_active_slave has been released or lost its link.
* - The primary_slave has got its link back.
* - A slave has got its link back and there's no old curr_active_slave.
*
* Caller must hold RTNL.
*/
void bond_select_active_slave(struct bonding *bond)
{
struct slave *best_slave;
int rv;
ASSERT_RTNL();
best_slave = bond_find_best_slave(bond);
if (best_slave != rtnl_dereference(bond->curr_active_slave)) {
bond_change_active_slave(bond, best_slave);
rv = bond_set_carrier(bond);
if (!rv)
return;
if (netif_carrier_ok(bond->dev))
netdev_info(bond->dev, "active interface up!\n");
else
netdev_info(bond->dev, "now running without any active interface!\n");
}
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static inline int slave_enable_netpoll(struct slave *slave)
{
struct netpoll *np;
int err = 0;
np = kzalloc(sizeof(*np), GFP_KERNEL);
err = -ENOMEM;
if (!np)
goto out;
err = __netpoll_setup(np, slave->dev);
if (err) {
kfree(np);
goto out;
}
slave->np = np;
out:
return err;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
struct netpoll *np = slave->np;
if (!np)
return;
slave->np = NULL;
__netpoll_free(np);
}
static void bond_poll_controller(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave = NULL;
struct list_head *iter;
struct ad_info ad_info;
if (BOND_MODE(bond) == BOND_MODE_8023AD)
if (bond_3ad_get_active_agg_info(bond, &ad_info))
return;
bond_for_each_slave_rcu(bond, slave, iter) {
if (!bond_slave_is_up(slave))
continue;
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct aggregator *agg =
SLAVE_AD_INFO(slave)->port.aggregator;
if (agg &&
agg->aggregator_identifier != ad_info.aggregator_id)
continue;
}
netpoll_poll_dev(slave->dev);
}
}
static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
bond_for_each_slave(bond, slave, iter)
if (bond_slave_is_up(slave))
slave_disable_netpoll(slave);
}
static int bond_netpoll_setup(struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
struct list_head *iter;
struct slave *slave;
int err = 0;
bond_for_each_slave(bond, slave, iter) {
err = slave_enable_netpoll(slave);
if (err) {
bond_netpoll_cleanup(dev);
break;
}
}
return err;
}
#else
static inline int slave_enable_netpoll(struct slave *slave)
{
return 0;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
}
static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
}
#endif
/*---------------------------------- IOCTL ----------------------------------*/
static netdev_features_t bond_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct bonding *bond = netdev_priv(dev);
struct list_head *iter;
netdev_features_t mask;
struct slave *slave;
mask = features;
features = netdev_base_features(features);
bond_for_each_slave(bond, slave, iter) {
features = netdev_increment_features(features,
slave->dev->features,
mask);
}
features = netdev_add_tso_features(features, mask);
return features;
}
#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
NETIF_F_GSO_ENCAP_ALL | \
NETIF_F_HIGHDMA | NETIF_F_LRO)
#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \
NETIF_F_GSO_PARTIAL)
#define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_GSO_SOFTWARE)
#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP)
static void bond_compute_features(struct bonding *bond)
{
netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES;
unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
IFF_XMIT_DST_RELEASE_PERM;
netdev_features_t vlan_features = BOND_VLAN_FEATURES;
netdev_features_t enc_features = BOND_ENC_FEATURES;
#ifdef CONFIG_XFRM_OFFLOAD
netdev_features_t xfrm_features = BOND_XFRM_FEATURES;
#endif /* CONFIG_XFRM_OFFLOAD */
netdev_features_t mpls_features = BOND_MPLS_FEATURES;
struct net_device *bond_dev = bond->dev;
struct list_head *iter;
struct slave *slave;
unsigned short max_hard_header_len = ETH_HLEN;
unsigned int tso_max_size = TSO_MAX_SIZE;
u16 tso_max_segs = TSO_MAX_SEGS;
if (!bond_has_slaves(bond))
goto done;
vlan_features = netdev_base_features(vlan_features);
mpls_features = netdev_base_features(mpls_features);
bond_for_each_slave(bond, slave, iter) {
vlan_features = netdev_increment_features(vlan_features,
slave->dev->vlan_features, BOND_VLAN_FEATURES);
enc_features = netdev_increment_features(enc_features,
slave->dev->hw_enc_features,
BOND_ENC_FEATURES);
#ifdef CONFIG_XFRM_OFFLOAD
xfrm_features = netdev_increment_features(xfrm_features,
slave->dev->hw_enc_features,
BOND_XFRM_FEATURES);
#endif /* CONFIG_XFRM_OFFLOAD */
gso_partial_features = netdev_increment_features(gso_partial_features,
slave->dev->gso_partial_features,
BOND_GSO_PARTIAL_FEATURES);
mpls_features = netdev_increment_features(mpls_features,
slave->dev->mpls_features,
BOND_MPLS_FEATURES);
dst_release_flag &= slave->dev->priv_flags;
if (slave->dev->hard_header_len > max_hard_header_len)
max_hard_header_len = slave->dev->hard_header_len;
tso_max_size = min(tso_max_size, slave->dev->tso_max_size);
tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs);
}
bond_dev->hard_header_len = max_hard_header_len;
done:
bond_dev->gso_partial_features = gso_partial_features;
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
#ifdef CONFIG_XFRM_OFFLOAD
bond_dev->hw_enc_features |= xfrm_features;
#endif /* CONFIG_XFRM_OFFLOAD */
bond_dev->mpls_features = mpls_features;
netif_set_tso_max_segs(bond_dev, tso_max_segs);
netif_set_tso_max_size(bond_dev, tso_max_size);
bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE;
netdev_change_features(bond_dev);
}
static void bond_setup_by_slave(struct net_device *bond_dev,
struct net_device *slave_dev)
{
bool was_up = !!(bond_dev->flags & IFF_UP);
dev_close(bond_dev);
bond_dev->header_ops = slave_dev->header_ops;
bond_dev->type = slave_dev->type;
bond_dev->hard_header_len = slave_dev->hard_header_len;
bond_dev->needed_headroom = slave_dev->needed_headroom;
bond_dev->addr_len = slave_dev->addr_len;
memcpy(bond_dev->broadcast, slave_dev->broadcast,
slave_dev->addr_len);
if (slave_dev->flags & IFF_POINTOPOINT) {
bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP);
}
if (was_up)
dev_open(bond_dev, NULL);
}
/* On bonding slaves other than the currently active slave, suppress
* duplicates except for alb non-mcast/bcast.
*/
static bool bond_should_deliver_exact_match(struct sk_buff *skb,
struct slave *slave,
struct bonding *bond)
{
if (bond_is_slave_inactive(slave)) {
if (BOND_MODE(bond) == BOND_MODE_ALB &&
skb->pkt_type != PACKET_BROADCAST &&
skb->pkt_type != PACKET_MULTICAST)
return false;
return true;
}
return false;
}
static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
struct slave *slave;
struct bonding *bond;
int (*recv_probe)(const struct sk_buff *, struct bonding *,
struct slave *);
int ret = RX_HANDLER_ANOTHER;
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return RX_HANDLER_CONSUMED;
*pskb = skb;
slave = bond_slave_get_rcu(skb->dev);
bond = slave->bond;
recv_probe = READ_ONCE(bond->recv_probe);
if (recv_probe) {
ret = recv_probe(skb, bond, slave);
if (ret == RX_HANDLER_CONSUMED) {
consume_skb(skb);
return ret;
}
}
/*
* For packets determined by bond_should_deliver_exact_match() call to
* be suppressed we want to make an exception for link-local packets.
* This is necessary for e.g. LLDP daemons to be able to monitor
* inactive slave links without being forced to bind to them
* explicitly.
*
* At the same time, packets that are passed to the bonding master
* (including link-local ones) can have their originating interface
* determined via PACKET_ORIGDEV socket option.
*/
if (bond_should_deliver_exact_match(skb, slave, bond)) {
if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
return RX_HANDLER_PASS;
return RX_HANDLER_EXACT;
}
skb->dev = bond->dev;
if (BOND_MODE(bond) == BOND_MODE_ALB &&
netif_is_bridge_port(bond->dev) &&
skb->pkt_type == PACKET_HOST) {
if (unlikely(skb_cow_head(skb,
skb->data - skb_mac_header(skb)))) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
bond->dev->addr_len);
}
return ret;
}
static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
{
switch (BOND_MODE(bond)) {
case BOND_MODE_ROUNDROBIN:
return NETDEV_LAG_TX_TYPE_ROUNDROBIN;
case BOND_MODE_ACTIVEBACKUP:
return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP;
case BOND_MODE_BROADCAST:
return NETDEV_LAG_TX_TYPE_BROADCAST;
case BOND_MODE_XOR:
case BOND_MODE_8023AD:
return NETDEV_LAG_TX_TYPE_HASH;
default:
return NETDEV_LAG_TX_TYPE_UNKNOWN;
}
}
static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond,
enum netdev_lag_tx_type type)
{
if (type != NETDEV_LAG_TX_TYPE_HASH)
return NETDEV_LAG_HASH_NONE;
switch (bond->params.xmit_policy) {
case BOND_XMIT_POLICY_LAYER2:
return NETDEV_LAG_HASH_L2;
case BOND_XMIT_POLICY_LAYER34:
return NETDEV_LAG_HASH_L34;
case BOND_XMIT_POLICY_LAYER23:
return NETDEV_LAG_HASH_L23;
case BOND_XMIT_POLICY_ENCAP23:
return NETDEV_LAG_HASH_E23;
case BOND_XMIT_POLICY_ENCAP34:
return NETDEV_LAG_HASH_E34;
case BOND_XMIT_POLICY_VLAN_SRCMAC:
return NETDEV_LAG_HASH_VLAN_SRCMAC;
default:
return NETDEV_LAG_HASH_UNKNOWN;
}
}
static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave,
struct netlink_ext_ack *extack)
{
struct netdev_lag_upper_info lag_upper_info;
enum netdev_lag_tx_type type;
int err;
type = bond_lag_tx_type(bond);
lag_upper_info.tx_type = type;
lag_upper_info.hash_type = bond_lag_hash_type(bond, type);
err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
&lag_upper_info, extack);
if (err)
return err;
slave->dev->flags |= IFF_SLAVE;
return 0;
}
static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave)
{
netdev_upper_dev_unlink(slave->dev, bond->dev);
slave->dev->flags &= ~IFF_SLAVE;
}
static void slave_kobj_release(struct kobject *kobj)
{
struct slave *slave = to_slave(kobj);
struct bonding *bond = bond_get_bond_by_slave(slave);
cancel_delayed_work_sync(&slave->notify_work);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
kfree(SLAVE_AD_INFO(slave));
kfree(slave);
}
static struct kobj_type slave_ktype = {
.release = slave_kobj_release,
#ifdef CONFIG_SYSFS
.sysfs_ops = &slave_sysfs_ops,
#endif
};
static int bond_kobj_init(struct slave *slave)
{
int err;
err = kobject_init_and_add(&slave->kobj, &slave_ktype,
&(slave->dev->dev.kobj), "bonding_slave");
if (err)
kobject_put(&slave->kobj);
return err;
}
static struct slave *bond_alloc_slave(struct bonding *bond,
struct net_device *slave_dev)
{
struct slave *slave = NULL;
slave = kzalloc(sizeof(*slave), GFP_KERNEL);
if (!slave)
return NULL;
slave->bond = bond;
slave->dev = slave_dev;
INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work);
if (bond_kobj_init(slave))
return NULL;
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info),
GFP_KERNEL);
if (!SLAVE_AD_INFO(slave)) {
kobject_put(&slave->kobj);
return NULL;
}
}
return slave;
}
static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info)
{
info->bond_mode = BOND_MODE(bond);
info->miimon = bond->params.miimon;
info->num_slaves = bond->slave_cnt;
}
static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
{
strcpy(info->slave_name, slave->dev->name);
info->link = slave->link;
info->state = bond_slave_state(slave);
info->link_failure_count = slave->link_failure_count;
}
static void bond_netdev_notify_work(struct work_struct *_work)
{
struct slave *slave = container_of(_work, struct slave,
notify_work.work);
if (rtnl_trylock()) {
struct netdev_bonding_info binfo;
bond_fill_ifslave(slave, &binfo.slave);
bond_fill_ifbond(slave->bond, &binfo.master);
netdev_bonding_info_change(slave->dev, &binfo);
rtnl_unlock();
} else {
queue_delayed_work(slave->bond->wq, &slave->notify_work, 1);
}
}
void bond_queue_slave_event(struct slave *slave)
{
queue_delayed_work(slave->bond->wq, &slave->notify_work, 0);
}
void bond_lower_state_changed(struct slave *slave)
{
struct netdev_lag_lower_state_info info;
info.link_up = slave->link == BOND_LINK_UP ||
slave->link == BOND_LINK_FAIL;
info.tx_enabled = bond_is_active_slave(slave);
netdev_lower_state_changed(slave->dev, &info);
}
#define BOND_NL_ERR(bond_dev, extack, errmsg) do { \
if (extack) \
NL_SET_ERR_MSG(extack, errmsg); \
else \
netdev_err(bond_dev, "Error: %s\n", errmsg); \
} while (0)
#define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do { \
if (extack) \
NL_SET_ERR_MSG(extack, errmsg); \
else \
slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \
} while (0)
/* The bonding driver uses ether_setup() to convert a master bond device
* to ARPHRD_ETHER, that resets the target netdevice's flags so we always
* have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP
* if they were set
*/
static void bond_ether_setup(struct net_device *bond_dev)
{
unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP);
ether_setup(bond_dev);
bond_dev->flags |= IFF_MASTER | flags;
bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
}
void bond_xdp_set_features(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
xdp_features_t val = NETDEV_XDP_ACT_MASK;
struct list_head *iter;
struct slave *slave;
ASSERT_RTNL();
if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) {
xdp_clear_features_flag(bond_dev);
return;
}
bond_for_each_slave(bond, slave, iter)
val &= slave->dev->xdp_features;
val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY;
xdp_set_features_flag(bond_dev, val);
}
/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
struct netlink_ext_ack *extack)
{
struct bonding *bond = netdev_priv(bond_dev);
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct slave *new_slave = NULL, *prev_slave;
struct sockaddr_storage ss;
int link_reporting;
int res = 0, i;
if (slave_dev->flags & IFF_MASTER &&
!netif_is_bond_master(slave_dev)) {
BOND_NL_ERR(bond_dev, extack,
"Device type (master device) cannot be enslaved");
return -EPERM;
}
if (!bond->params.use_carrier &&
slave_dev->ethtool_ops->get_link == NULL &&
slave_ops->ndo_eth_ioctl == NULL) {
slave_warn(bond_dev, slave_dev, "no link monitoring support\n");
}
/* already in-use? */
if (netdev_is_rx_handler_busy(slave_dev)) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Device is in use and cannot be enslaved");
return -EBUSY;
}
if (bond_dev == slave_dev) {
BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself.");
return -EPERM;
}
/* vlan challenged mutual exclusion */
/* no need to lock since we're protected by rtnl_lock */
if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n");
if (vlan_uses_dev(bond_dev)) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Can not enslave VLAN challenged device to VLAN enabled bond");
return -EPERM;
} else {
slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n");
}
} else {
slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n");
}
if (slave_dev->features & NETIF_F_HW_ESP)
slave_dbg(bond_dev, slave_dev, "is esp-hw-offload capable\n");
/* Old ifenslave binaries are no longer supported. These can
* be identified with moderate accuracy by the state of the slave:
* the current ifenslave will set the interface down prior to
* enslaving it; the old ifenslave will not.
*/
if (slave_dev->flags & IFF_UP) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Device can not be enslaved while up");
return -EPERM;
}
/* set bonding device ether type by slave - bonding netdevices are
* created with ether_setup, so when the slave type is not ARPHRD_ETHER
* there is a need to override some of the type dependent attribs/funcs.
*
* bond ether type mutual exclusion - don't allow slaves of dissimilar
* ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
*/
if (!bond_has_slaves(bond)) {
if (bond_dev->type != slave_dev->type) {
slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n",
bond_dev->type, slave_dev->type);
res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE,
bond_dev);
res = notifier_to_errno(res);
if (res) {
slave_err(bond_dev, slave_dev, "refused to change device type\n");
return -EBUSY;
}
/* Flush unicast and multicast addresses */
dev_uc_flush(bond_dev);
dev_mc_flush(bond_dev);
if (slave_dev->type != ARPHRD_ETHER)
bond_setup_by_slave(bond_dev, slave_dev);
else
bond_ether_setup(bond_dev);
call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,
bond_dev);
}
} else if (bond_dev->type != slave_dev->type) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Device type is different from other slaves");
return -EINVAL;
}
if (slave_dev->type == ARPHRD_INFINIBAND &&
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Only active-backup mode is supported for infiniband slaves");
res = -EOPNOTSUPP;
goto err_undo_flags;
}
if (!slave_ops->ndo_set_mac_address ||
slave_dev->type == ARPHRD_INFINIBAND) {
slave_warn(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address\n");
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
if (!bond_has_slaves(bond)) {
bond->params.fail_over_mac = BOND_FOM_ACTIVE;
slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n");
} else {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Slave device does not support setting the MAC address, but fail_over_mac is not set to active");
res = -EOPNOTSUPP;
goto err_undo_flags;
}
}
}
call_netdevice_notifiers(NETDEV_JOIN, slave_dev);
/* If this is the first slave, then we need to set the master's hardware
* address to be the same as the slave's.
*/
if (!bond_has_slaves(bond) &&
bond->dev->addr_assign_type == NET_ADDR_RANDOM) {
res = bond_set_dev_addr(bond->dev, slave_dev);
if (res)
goto err_undo_flags;
}
new_slave = bond_alloc_slave(bond, slave_dev);
if (!new_slave) {
res = -ENOMEM;
goto err_undo_flags;
}
/* Set the new_slave's queue_id to be zero. Queue ID mapping
* is set via sysfs or module option if desired.
*/
new_slave->queue_id = 0;
/* Save slave's original mtu and then set it to match the bond */
new_slave->original_mtu = slave_dev->mtu;
res = dev_set_mtu(slave_dev, bond->dev->mtu);
if (res) {
slave_err(bond_dev, slave_dev, "Error %d calling dev_set_mtu\n", res);
goto err_free;
}
/* Save slave's original ("permanent") mac address for modes
* that need it, and for restoring it upon release, and then
* set it to the master's address
*/
bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
slave_dev->addr_len);
if (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* Set slave to master's mac address. The application already
* set the master's mac address to that of the first slave
*/
memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
ss.ss_family = slave_dev->type;
res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
extack);
if (res) {
slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
goto err_restore_mtu;
}
}
/* set no_addrconf flag before open to prevent IPv6 addrconf */
slave_dev->priv_flags |= IFF_NO_ADDRCONF;
/* open the slave since the application closed it */
res = dev_open(slave_dev, extack);
if (res) {
slave_err(bond_dev, slave_dev, "Opening slave failed\n");
goto err_restore_mac;
}
slave_dev->priv_flags |= IFF_BONDING;
/* initialize slave stats */
dev_get_stats(new_slave->dev, &new_slave->slave_stats);
if (bond_is_lb(bond)) {
/* bond_alb_init_slave() must be called before all other stages since
* it might fail and we do not want to have to undo everything
*/
res = bond_alb_init_slave(bond, new_slave);
if (res)
goto err_close;
}
res = vlan_vids_add_by_dev(slave_dev, bond_dev);
if (res) {
slave_err(bond_dev, slave_dev, "Couldn't add bond vlan ids\n");
goto err_close;
}
prev_slave = bond_last_slave(bond);
new_slave->delay = 0;
new_slave->link_failure_count = 0;
if (bond_update_speed_duplex(new_slave) &&
bond_needs_speed_duplex(bond))
new_slave->link = BOND_LINK_DOWN;
new_slave->last_rx = jiffies -
(msecs_to_jiffies(bond->params.arp_interval) + 1);
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
new_slave->target_last_arp_rx[i] = new_slave->last_rx;
new_slave->last_tx = new_slave->last_rx;
if (bond->params.miimon && !bond->params.use_carrier) {
link_reporting = bond_check_dev_link(bond, slave_dev, 1);
if ((link_reporting == -1) && !bond->params.arp_interval) {
/* miimon is set but a bonded network driver
* does not support ETHTOOL/MII and
* arp_interval is not set. Note: if
* use_carrier is enabled, we will never go
* here (because netif_carrier is always
* supported); thus, we don't need to change
* the messages for netif_carrier.
*/
slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n");
} else if (link_reporting == -1) {
/* unable get link status using mii/ethtool */
slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n");
}
}
/* check for initial state */
new_slave->link = BOND_LINK_NOCHANGE;
if (bond->params.miimon) {
if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
if (bond->params.updelay) {
bond_set_slave_link_state(new_slave,
BOND_LINK_BACK,
BOND_SLAVE_NOTIFY_NOW);
new_slave->delay = bond->params.updelay;
} else {
bond_set_slave_link_state(new_slave,
BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
}
} else {
bond_set_slave_link_state(new_slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_NOW);
}
} else if (bond->params.arp_interval) {
bond_set_slave_link_state(new_slave,
(netif_carrier_ok(slave_dev) ?
BOND_LINK_UP : BOND_LINK_DOWN),
BOND_SLAVE_NOTIFY_NOW);
} else {
bond_set_slave_link_state(new_slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
}
if (new_slave->link != BOND_LINK_DOWN)
new_slave->last_link_up = jiffies;
slave_dbg(bond_dev, slave_dev, "Initial state of slave is BOND_LINK_%s\n",
new_slave->link == BOND_LINK_DOWN ? "DOWN" :
(new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));
if (bond_uses_primary(bond) && bond->params.primary[0]) {
/* if there is a primary slave, remember it */
if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
rcu_assign_pointer(bond->primary_slave, new_slave);
bond->force_primary = true;
}
}
switch (BOND_MODE(bond)) {
case BOND_MODE_ACTIVEBACKUP:
bond_set_slave_inactive_flags(new_slave,
BOND_SLAVE_NOTIFY_NOW);
break;
case BOND_MODE_8023AD:
/* in 802.3ad mode, the internal mechanism
* will activate the slaves in the selected
* aggregator
*/
bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
/* if this is the first slave */
if (!prev_slave) {
SLAVE_AD_INFO(new_slave)->id = 1;
/* Initialize AD with the number of times that the AD timer is called in 1 second
* can be called only after the mac address of the bond is set
*/
bond_3ad_initialize(bond);
} else {
SLAVE_AD_INFO(new_slave)->id =
SLAVE_AD_INFO(prev_slave)->id + 1;
}
bond_3ad_bind_slave(new_slave);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
bond_set_active_slave(new_slave);
bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
break;
default:
slave_dbg(bond_dev, slave_dev, "This slave is always active in trunk mode\n");
/* always active in trunk mode */
bond_set_active_slave(new_slave);
/* In trunking mode there is little meaning to curr_active_slave
* anyway (it holds no special properties of the bond device),
* so we can change it without calling change_active_interface()
*/
if (!rcu_access_pointer(bond->curr_active_slave) &&
new_slave->link == BOND_LINK_UP)
rcu_assign_pointer(bond->curr_active_slave, new_slave);
break;
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
slave_info(bond_dev, slave_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
goto err_detach;
}
}
#endif
if (!(bond_dev->features & NETIF_F_LRO))
dev_disable_lro(slave_dev);
res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
new_slave);
if (res) {
slave_dbg(bond_dev, slave_dev, "Error %d calling netdev_rx_handler_register\n", res);
goto err_detach;
}
res = bond_master_upper_dev_link(bond, new_slave, extack);
if (res) {
slave_dbg(bond_dev, slave_dev, "Error %d calling bond_master_upper_dev_link\n", res);
goto err_unregister;
}
bond_lower_state_changed(new_slave);
res = bond_sysfs_slave_add(new_slave);
if (res) {
slave_dbg(bond_dev, slave_dev, "Error %d calling bond_sysfs_slave_add\n", res);
goto err_upper_unlink;
}
/* If the mode uses primary, then the following is handled by
* bond_change_active_slave().
*/
if (!bond_uses_primary(bond)) {
/* set promiscuity level to new slave */
if (bond_dev->flags & IFF_PROMISC) {
res = dev_set_promiscuity(slave_dev, 1);
if (res)
goto err_sysfs_del;
}
/* set allmulti level to new slave */
if (bond_dev->flags & IFF_ALLMULTI) {
res = dev_set_allmulti(slave_dev, 1);
if (res) {
if (bond_dev->flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
goto err_sysfs_del;
}
}
if (bond_dev->flags & IFF_UP) {
netif_addr_lock_bh(bond_dev);
dev_mc_sync_multiple(slave_dev, bond_dev);
dev_uc_sync_multiple(slave_dev, bond_dev);
netif_addr_unlock_bh(bond_dev);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
dev_mc_add(slave_dev, lacpdu_mcast_addr);
}
}
bond->slave_cnt++;
bond_compute_features(bond);
bond_set_carrier(bond);
/* Needs to be called before bond_select_active_slave(), which will
* remove the maddrs if the slave is selected as active slave.
*/
bond_slave_ns_maddrs_add(bond, new_slave);
if (bond_uses_primary(bond)) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
if (!slave_dev->netdev_ops->ndo_bpf ||
!slave_dev->netdev_ops->ndo_xdp_xmit) {
if (bond->xdp_prog) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Slave does not support XDP");
res = -EOPNOTSUPP;
goto err_sysfs_del;
}
} else if (bond->xdp_prog) {
struct netdev_bpf xdp = {
.command = XDP_SETUP_PROG,
.flags = 0,
.prog = bond->xdp_prog,
.extack = extack,
};
if (dev_xdp_prog_count(slave_dev) > 0) {
SLAVE_NL_ERR(bond_dev, slave_dev, extack,
"Slave has XDP program loaded, please unload before enslaving");
res = -EOPNOTSUPP;
goto err_sysfs_del;
}
res = dev_xdp_propagate(slave_dev, &xdp);
if (res < 0) {
/* ndo_bpf() sets extack error message */
slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
goto err_sysfs_del;
}
if (bond->xdp_prog)
bpf_prog_inc(bond->xdp_prog);
}
bond_xdp_set_features(bond_dev);
slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n",
bond_is_active_slave(new_slave) ? "an active" : "a backup",
new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
/* enslave is successful */
bond_queue_slave_event(new_slave);
return 0;
/* Undo stages on error */
err_sysfs_del:
bond_sysfs_slave_del(new_slave);
err_upper_unlink:
bond_upper_dev_unlink(bond, new_slave);
err_unregister:
netdev_rx_handler_unregister(slave_dev);
err_detach:
vlan_vids_del_by_dev(slave_dev, bond_dev);
if (rcu_access_pointer(bond->primary_slave) == new_slave)
RCU_INIT_POINTER(bond->primary_slave, NULL);
if (rcu_access_pointer(bond->curr_active_slave) == new_slave) {
block_netpoll_tx();
bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
/* either primary_slave or curr_active_slave might've changed */
synchronize_rcu();
slave_disable_netpoll(new_slave);
err_close:
if (!netif_is_bond_master(slave_dev))
slave_dev->priv_flags &= ~IFF_BONDING;
dev_close(slave_dev);
err_restore_mac:
slave_dev->priv_flags &= ~IFF_NO_ADDRCONF;
if (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* XXX TODO - fom follow mode needs to change master's
* MAC if this slave's MAC is in use by the bond, or at
* least print a warning.
*/
bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
new_slave->dev->addr_len);
ss.ss_family = slave_dev->type;
dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
}
err_restore_mtu:
dev_set_mtu(slave_dev, new_slave->original_mtu);
err_free:
kobject_put(&new_slave->kobj);
err_undo_flags:
/* Enslave of first slave has failed and we need to fix master's mac */
if (!bond_has_slaves(bond)) {
if (ether_addr_equal_64bits(bond_dev->dev_addr,
slave_dev->dev_addr))
eth_hw_addr_random(bond_dev);
if (bond_dev->type != ARPHRD_ETHER) {
dev_close(bond_dev);
bond_ether_setup(bond_dev);
}
}
return res;
}
/* Try to release the slave device <slave> from the bond device <master>
* It is legal to access curr_active_slave without a lock because all the function
* is RTNL-locked. If "all" is true it means that the function is being called
* while destroying a bond interface and all slaves are being released.
*
* The rules for slave state should be:
* for Active/Backup:
* Active stays on all backups go down
* for Bonded connections:
* The first up interface should be left on and all others downed.
*/
static int __bond_release_one(struct net_device *bond_dev,
struct net_device *slave_dev,
bool all, bool unregister)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr_storage ss;
int old_flags = bond_dev->flags;
netdev_features_t old_features = bond_dev->features;
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
!netdev_has_upper_dev(slave_dev, bond_dev)) {
slave_dbg(bond_dev, slave_dev, "cannot release slave\n");
return -EINVAL;
}
block_netpoll_tx();
slave = bond_get_slave_by_dev(bond, slave_dev);
if (!slave) {
/* not a slave of this bond */
slave_info(bond_dev, slave_dev, "interface not enslaved\n");
unblock_netpoll_tx();
return -EINVAL;
}
bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);
bond_sysfs_slave_del(slave);
/* recompute stats just before removing the slave */
bond_get_stats(bond->dev, &bond->bond_stats);
if (bond->xdp_prog) {
struct netdev_bpf xdp = {
.command = XDP_SETUP_PROG,
.flags = 0,
.prog = NULL,
.extack = NULL,
};
if (dev_xdp_propagate(slave_dev, &xdp))
slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
}
/* unregister rx_handler early so bond_handle_frame wouldn't be called
* for this slave anymore.
*/
netdev_rx_handler_unregister(slave_dev);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
bond_upper_dev_unlink(bond, slave);
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, slave);
slave_info(bond_dev, slave_dev, "Releasing %s interface\n",
bond_is_active_slave(slave) ? "active" : "backup");
oldcurrent = rcu_access_pointer(bond->curr_active_slave);
RCU_INIT_POINTER(bond->current_arp_slave, NULL);
if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond_has_slaves(bond))
slave_warn(bond_dev, slave_dev, "the permanent HWaddr of slave - %pM - is still in use by bond - set the HWaddr of slave to a different address to avoid conflicts\n",
slave->perm_hwaddr);
}
if (rtnl_dereference(bond->primary_slave) == slave)
RCU_INIT_POINTER(bond->primary_slave, NULL);
if (oldcurrent == slave)
bond_change_active_slave(bond, NULL);
/* Must be called after bond_change_active_slave () as the slave
* might change from an active slave to a backup slave. Then it is
* necessary to clear the maddrs on the backup slave.
*/
bond_slave_ns_maddrs_del(bond, slave);
if (bond_is_lb(bond)) {
/* Must be called only after the slave has been
* detached from the list and the curr_active_slave
* has been cleared (if our_slave == old_current),
* but before a new active slave is selected.
*/
bond_alb_deinit_slave(bond, slave);
}
if (all) {
RCU_INIT_POINTER(bond->curr_active_slave, NULL);
} else if (oldcurrent == slave) {
/* Note that we hold RTNL over this sequence, so there
* is no concern that another slave add/remove event
* will interfere.
*/
bond_select_active_slave(bond);
}
bond_set_carrier(bond);
if (!bond_has_slaves(bond))
eth_hw_addr_random(bond_dev);
unblock_netpoll_tx();
synchronize_rcu();
bond->slave_cnt--;
if (!bond_has_slaves(bond)) {
call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
call_netdevice_notifiers(NETDEV_RELEASE, bond->dev);
}
bond_compute_features(bond);
if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
(old_features & NETIF_F_VLAN_CHALLENGED))
slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n");
vlan_vids_del_by_dev(slave_dev, bond_dev);
/* If the mode uses primary, then this case was handled above by
* bond_change_active_slave(..., NULL)
*/
if (!bond_uses_primary(bond)) {
/* unset promiscuity level from slave
* NOTE: The NETDEV_CHANGEADDR call above may change the value
* of the IFF_PROMISC flag in the bond_dev, but we need the
* value of that flag before that change, as that was the value
* when this slave was attached, so we cache at the start of the
* function and use it here. Same goes for ALLMULTI below
*/
if (old_flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
/* unset allmulti level from slave */
if (old_flags & IFF_ALLMULTI)
dev_set_allmulti(slave_dev, -1);
if (old_flags & IFF_UP)
bond_hw_addr_flush(bond_dev, slave_dev);
}
slave_disable_netpoll(slave);
/* close slave before restoring its mac address */
dev_close(slave_dev);
slave_dev->priv_flags &= ~IFF_NO_ADDRCONF;
if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* restore original ("permanent") mac address */
bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
slave->dev->addr_len);
ss.ss_family = slave_dev->type;
dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
}
if (unregister) {
netdev_lock_ops(slave_dev);
__dev_set_mtu(slave_dev, slave->original_mtu);
netdev_unlock_ops(slave_dev);
} else {
dev_set_mtu(slave_dev, slave->original_mtu);
}
if (!netif_is_bond_master(slave_dev))
slave_dev->priv_flags &= ~IFF_BONDING;
bond_xdp_set_features(bond_dev);
kobject_put(&slave->kobj);
return 0;
}
/* A wrapper used because of ndo_del_link */
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
return __bond_release_one(bond_dev, slave_dev, false, false);
}
/* First release a slave and then destroy the bond if no more slaves are left.
* Must be under rtnl_lock when this function is called.
*/
static int bond_release_and_destroy(struct net_device *bond_dev,
struct net_device *slave_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
int ret;
ret = __bond_release_one(bond_dev, slave_dev, false, true);
if (ret == 0 && !bond_has_slaves(bond) &&
bond_dev->reg_state != NETREG_UNREGISTERING) {
bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
netdev_info(bond_dev, "Destroying bond\n");
bond_remove_proc_entry(bond);
unregister_netdevice(bond_dev);
}
return ret;
}
static void bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
struct bonding *bond = netdev_priv(bond_dev);
bond_fill_ifbond(bond, info);
}
static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
int i = 0, res = -ENODEV;
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
if (i++ == (int)info->slave_id) {
res = 0;
bond_fill_ifslave(slave, info);
break;
}
}
return res;
}
/*-------------------------------- Monitoring -------------------------------*/
/* called with rcu_read_lock() */
static int bond_miimon_inspect(struct bonding *bond)
{
bool ignore_updelay = false;
int link_state, commit = 0;
struct list_head *iter;
struct slave *slave;
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) {
ignore_updelay = !rcu_dereference(bond->curr_active_slave);
} else {
struct bond_up_slave *usable_slaves;
usable_slaves = rcu_dereference(bond->usable_slaves);
if (usable_slaves && usable_slaves->count == 0)
ignore_updelay = true;
}
bond_for_each_slave_rcu(bond, slave, iter) {
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
link_state = bond_check_dev_link(bond, slave->dev, 0);
switch (slave->link) {
case BOND_LINK_UP:
if (link_state)
continue;
bond_propose_link_state(slave, BOND_LINK_FAIL);
commit++;
slave->delay = bond->params.downdelay;
if (slave->delay && net_ratelimit()) {
slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n",
(BOND_MODE(bond) ==
BOND_MODE_ACTIVEBACKUP) ?
(bond_is_active_slave(slave) ?
"active " : "backup ") : "",
bond->params.downdelay * bond->params.miimon);
}
fallthrough;
case BOND_LINK_FAIL:
if (link_state) {
/* recovered before downdelay expired */
bond_propose_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
if (net_ratelimit())
slave_info(bond->dev, slave->dev, "link status up again after %d ms\n",
(bond->params.downdelay - slave->delay) *
bond->params.miimon);
commit++;
continue;
}
if (slave->delay <= 0) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
commit++;
continue;
}
slave->delay--;
break;
case BOND_LINK_DOWN:
if (!link_state)
continue;
bond_propose_link_state(slave, BOND_LINK_BACK);
commit++;
slave->delay = bond->params.updelay;
if (slave->delay && net_ratelimit()) {
slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n",
ignore_updelay ? 0 :
bond->params.updelay *
bond->params.miimon);
}
fallthrough;
case BOND_LINK_BACK:
if (!link_state) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
if (net_ratelimit())
slave_info(bond->dev, slave->dev, "link status down again after %d ms\n",
(bond->params.updelay - slave->delay) *
bond->params.miimon);
commit++;
continue;
}
if (ignore_updelay)
slave->delay = 0;
if (slave->delay <= 0) {
bond_propose_link_state(slave, BOND_LINK_UP);
commit++;
ignore_updelay = false;
continue;
}
slave->delay--;
break;
}
}
return commit;
}
static void bond_miimon_link_change(struct bonding *bond,
struct slave *slave,
char link)
{
switch (BOND_MODE(bond)) {
case BOND_MODE_8023AD:
bond_3ad_handle_link_change(slave, link);
break;
case BOND_MODE_TLB:
case BOND_MODE_ALB:
bond_alb_handle_link_change(bond, slave, link);
break;
case BOND_MODE_XOR:
bond_update_slave_arr(bond, NULL);
break;
}
}
static void bond_miimon_commit(struct bonding *bond)
{
struct slave *slave, *primary, *active;
bool do_failover = false;
struct list_head *iter;
ASSERT_RTNL();
bond_for_each_slave(bond, slave, iter) {
switch (slave->link_new_state) {
case BOND_LINK_NOCHANGE:
/* For 802.3ad mode, check current slave speed and
* duplex again in case its port was disabled after
* invalid speed/duplex reporting but recovered before
* link monitoring could make a decision on the actual
* link status
*/
if (BOND_MODE(bond) == BOND_MODE_8023AD &&
slave->link == BOND_LINK_UP)
bond_3ad_adapter_speed_duplex_changed(slave);
continue;
case BOND_LINK_UP:
if (bond_update_speed_duplex(slave) &&
bond_needs_speed_duplex(bond)) {
slave->link = BOND_LINK_DOWN;
if (net_ratelimit())
slave_warn(bond->dev, slave->dev,
"failed to get link speed/duplex\n");
continue;
}
bond_set_slave_link_state(slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
slave->last_link_up = jiffies;
primary = rtnl_dereference(bond->primary_slave);
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
/* prevent it from being the active one */
bond_set_backup_slave(slave);
} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* make it immediately active */
bond_set_active_slave(slave);
}
slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n",
slave->speed == SPEED_UNKNOWN ? 0 : slave->speed,
slave->duplex ? "full" : "half");
bond_miimon_link_change(bond, slave, BOND_LINK_UP);
active = rtnl_dereference(bond->curr_active_slave);
if (!active || slave == primary || slave->prio > active->prio)
do_failover = true;
continue;
case BOND_LINK_DOWN:
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
bond_set_slave_link_state(slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_NOW);
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
BOND_MODE(bond) == BOND_MODE_8023AD)
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n");
bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);
if (slave == rcu_access_pointer(bond->curr_active_slave))
do_failover = true;
continue;
default:
slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
slave->link_new_state);
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
continue;
}
}
if (do_failover) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
bond_set_carrier(bond);
}
/* bond_mii_monitor
*
* Really a wrapper that splits the mii monitor into two phases: an
* inspection, then (if inspection indicates something needs to be done)
* an acquisition of appropriate locks followed by a commit phase to
* implement whatever link state changes are indicated.
*/
static void bond_mii_monitor(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
mii_work.work);
bool should_notify_peers = false;
bool commit;
unsigned long delay;
struct slave *slave;
struct list_head *iter;
delay = msecs_to_jiffies(bond->params.miimon);
if (!bond_has_slaves(bond))
goto re_arm;
rcu_read_lock();
should_notify_peers = bond_should_notify_peers(bond);
commit = !!bond_miimon_inspect(bond);
if (bond->send_peer_notif) {
rcu_read_unlock();
if (rtnl_trylock()) {
bond->send_peer_notif--;
rtnl_unlock();
}
} else {
rcu_read_unlock();
}
if (commit) {
/* Race avoidance with bond_close cancel of workqueue */
if (!rtnl_trylock()) {
delay = 1;
should_notify_peers = false;
goto re_arm;
}
bond_for_each_slave(bond, slave, iter) {
bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
}
bond_miimon_commit(bond);
rtnl_unlock(); /* might sleep, hold no other locks */
}
re_arm:
if (bond->params.miimon)
queue_delayed_work(bond->wq, &bond->mii_work, delay);
if (should_notify_peers) {
if (!rtnl_trylock())
return;
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
rtnl_unlock();
}
}
static int bond_upper_dev_walk(struct net_device *upper,
struct netdev_nested_priv *priv)
{
__be32 ip = *(__be32 *)priv->data;
return ip == bond_confirm_addr(upper, 0, ip);
}
static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
struct netdev_nested_priv priv = {
.data = (void *)&ip,
};
bool ret = false;
if (ip == bond_confirm_addr(bond->dev, 0, ip))
return true;
rcu_read_lock();
if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv))
ret = true;
rcu_read_unlock();
return ret;
}
#define BOND_VLAN_PROTO_NONE cpu_to_be16(0xffff)
static bool bond_handle_vlan(struct slave *slave, struct bond_vlan_tag *tags,
struct sk_buff *skb)
{
struct net_device *bond_dev = slave->bond->dev;
struct net_device *slave_dev = slave->dev;
struct bond_vlan_tag *outer_tag = tags;
if (!tags || tags->vlan_proto == BOND_VLAN_PROTO_NONE)
return true;
tags++;
/* Go through all the tags backwards and add them to the packet */
while (tags->vlan_proto != BOND_VLAN_PROTO_NONE) {
if (!tags->vlan_id) {
tags++;
continue;
}
slave_dbg(bond_dev, slave_dev, "inner tag: proto %X vid %X\n",
ntohs(outer_tag->vlan_proto), tags->vlan_id);
skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto,
tags->vlan_id);
if (!skb) {
net_err_ratelimited("failed to insert inner VLAN tag\n");
return false;
}
tags++;
}
/* Set the outer tag */
if (outer_tag->vlan_id) {
slave_dbg(bond_dev, slave_dev, "outer tag: proto %X vid %X\n",
ntohs(outer_tag->vlan_proto), outer_tag->vlan_id);
__vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto,
outer_tag->vlan_id);
}
return true;
}
/* We go to the (large) trouble of VLAN tagging ARP frames because
* switches in VLAN mode (especially if ports are configured as
* "native" to a VLAN) might not pass non-tagged frames.
*/
static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip,
__be32 src_ip, struct bond_vlan_tag *tags)
{
struct net_device *bond_dev = slave->bond->dev;
struct net_device *slave_dev = slave->dev;
struct sk_buff *skb;
slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n",
arp_op, &dest_ip, &src_ip);
skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
NULL, slave_dev->dev_addr, NULL);
if (!skb) {
net_err_ratelimited("ARP packet allocation failed\n");
return;
}
if (bond_handle_vlan(slave, tags, skb)) {
slave_update_last_tx(slave);
arp_xmit(skb);
}
return;
}
/* Validate the device path between the @start_dev and the @end_dev.
* The path is valid if the @end_dev is reachable through device
* stacking.
* When the path is validated, collect any vlan information in the
* path.
*/
struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
struct net_device *end_dev,
int level)
{
struct bond_vlan_tag *tags;
struct net_device *upper;
struct list_head *iter;
if (start_dev == end_dev) {
tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC);
if (!tags)
return ERR_PTR(-ENOMEM);
tags[level].vlan_proto = BOND_VLAN_PROTO_NONE;
return tags;
}
netdev_for_each_upper_dev_rcu(start_dev, upper, iter) {
tags = bond_verify_device_path(upper, end_dev, level + 1);
if (IS_ERR_OR_NULL(tags)) {
if (IS_ERR(tags))
return tags;
continue;
}
if (is_vlan_dev(upper)) {
tags[level].vlan_proto = vlan_dev_vlan_proto(upper);
tags[level].vlan_id = vlan_dev_vlan_id(upper);
}
return tags;
}
return NULL;
}
static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
struct rtable *rt;
struct bond_vlan_tag *tags;
__be32 *targets = bond->params.arp_targets, addr;
int i;
for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
slave_dbg(bond->dev, slave->dev, "%s: target %pI4\n",
__func__, &targets[i]);
tags = NULL;
/* Find out through which dev should the packet go */
rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0,
RT_SCOPE_LINK);
if (IS_ERR(rt)) {
/* there's no route to target - try to send arp
* probe to generate any traffic (arp_validate=0)
*/
if (bond->params.arp_validate)
pr_warn_once("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
bond->dev->name,
&targets[i]);
bond_arp_send(slave, ARPOP_REQUEST, targets[i],
0, tags);
continue;
}
/* bond device itself */
if (rt->dst.dev == bond->dev)
goto found;
rcu_read_lock();
tags = bond_verify_device_path(bond->dev, rt->dst.dev, 0);
rcu_read_unlock();
if (!IS_ERR_OR_NULL(tags))
goto found;
/* Not our device - skip */
slave_dbg(bond->dev, slave->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n",
&targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL");
ip_rt_put(rt);
continue;
found:
addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
ip_rt_put(rt);
bond_arp_send(slave, ARPOP_REQUEST, targets[i], addr, tags);
kfree(tags);
}
}
static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
int i;
if (!sip || !bond_has_this_ip(bond, tip)) {
slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 tip %pI4 not found\n",
__func__, &sip, &tip);
return;
}
i = bond_get_targets_ip(bond->params.arp_targets, sip);
if (i == -1) {
slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 not found in targets\n",
__func__, &sip);
return;
}
slave->last_rx = jiffies;
slave->target_last_arp_rx[i] = jiffies;
}
static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
struct slave *slave)
{
struct arphdr *arp = (struct arphdr *)skb->data;
struct slave *curr_active_slave, *curr_arp_slave;
unsigned char *arp_ptr;
__be32 sip, tip;
unsigned int alen;
alen = arp_hdr_len(bond->dev);
if (alen > skb_headlen(skb)) {
arp = kmalloc(alen, GFP_ATOMIC);
if (!arp)
goto out_unlock;
if (skb_copy_bits(skb, 0, arp, alen) < 0)
goto out_unlock;
}
if (arp->ar_hln != bond->dev->addr_len ||
skb->pkt_type == PACKET_OTHERHOST ||
skb->pkt_type == PACKET_LOOPBACK ||
arp->ar_hrd != htons(ARPHRD_ETHER) ||
arp->ar_pro != htons(ETH_P_IP) ||
arp->ar_pln != 4)
goto out_unlock;
arp_ptr = (unsigned char *)(arp + 1);
arp_ptr += bond->dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4 + bond->dev->addr_len;
memcpy(&tip, arp_ptr, 4);
slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI4 tip %pI4\n",
__func__, slave->dev->name, bond_slave_state(slave),
bond->params.arp_validate, slave_do_arp_validate(bond, slave),
&sip, &tip);
curr_active_slave = rcu_dereference(bond->curr_active_slave);
curr_arp_slave = rcu_dereference(bond->current_arp_slave);
/* We 'trust' the received ARP enough to validate it if:
*
* (a) the slave receiving the ARP is active (which includes the
* current ARP slave, if any), or
*
* (b) the receiving slave isn't active, but there is a currently
* active slave and it received valid arp reply(s) after it became
* the currently active slave, or
*
* (c) there is an ARP slave that sent an ARP during the prior ARP
* interval, and we receive an ARP reply on any slave. We accept
* these because switch FDB update delays may deliver the ARP
* reply to a slave other than the sender of the ARP request.
*
* Note: for (b), backup slaves are receiving the broadcast ARP
* request, not a reply. This request passes from the sending
* slave through the L2 switch(es) to the receiving slave. Since
* this is checking the request, sip/tip are swapped for
* validation.
*
* This is done to avoid endless looping when we can't reach the
* arp_ip_target and fool ourselves with our own arp requests.
*/
if (bond_is_active_slave(slave))
bond_validate_arp(bond, slave, sip, tip);
else if (curr_active_slave &&
time_after(slave_last_rx(bond, curr_active_slave),
curr_active_slave->last_link_up))
bond_validate_arp(bond, slave, tip, sip);
else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1))
bond_validate_arp(bond, slave, sip, tip);
out_unlock:
if (arp != (struct arphdr *)skb->data)
kfree(arp);
return RX_HANDLER_ANOTHER;
}
#if IS_ENABLED(CONFIG_IPV6)
static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr,
const struct in6_addr *saddr, struct bond_vlan_tag *tags)
{
struct net_device *bond_dev = slave->bond->dev;
struct net_device *slave_dev = slave->dev;
struct in6_addr mcaddr;
struct sk_buff *skb;
slave_dbg(bond_dev, slave_dev, "NS on slave: dst %pI6c src %pI6c\n",
daddr, saddr);
skb = ndisc_ns_create(slave_dev, daddr, saddr, 0);
if (!skb) {
net_err_ratelimited("NS packet allocation failed\n");
return;
}
addrconf_addr_solict_mult(daddr, &mcaddr);
if (bond_handle_vlan(slave, tags, skb)) {
slave_update_last_tx(slave);
ndisc_send_skb(skb, &mcaddr, saddr);
}
}
static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
{
struct in6_addr *targets = bond->params.ns_targets;
struct bond_vlan_tag *tags;
struct dst_entry *dst;
struct in6_addr saddr;
struct flowi6 fl6;
int i;
for (i = 0; i < BOND_MAX_NS_TARGETS && !ipv6_addr_any(&targets[i]); i++) {
slave_dbg(bond->dev, slave->dev, "%s: target %pI6c\n",
__func__, &targets[i]);
tags = NULL;
/* Find out through which dev should the packet go */
memset(&fl6, 0, sizeof(struct flowi6));
fl6.daddr = targets[i];
fl6.flowi6_oif = bond->dev->ifindex;
dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6);
if (dst->error) {
dst_release(dst);
/* there's no route to target - try to send arp
* probe to generate any traffic (arp_validate=0)
*/
if (bond->params.arp_validate)
pr_warn_once("%s: no route to ns_ip6_target %pI6c and arp_validate is set\n",
bond->dev->name,
&targets[i]);
bond_ns_send(slave, &targets[i], &in6addr_any, tags);
continue;
}
/* bond device itself */
if (dst->dev == bond->dev)
goto found;
rcu_read_lock();
tags = bond_verify_device_path(bond->dev, dst->dev, 0);
rcu_read_unlock();
if (!IS_ERR_OR_NULL(tags))
goto found;
/* Not our device - skip */
slave_dbg(bond->dev, slave->dev, "no path to ns_ip6_target %pI6c via dst->dev %s\n",
&targets[i], dst->dev ? dst->dev->name : "NULL");
dst_release(dst);
continue;
found:
if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr))
bond_ns_send(slave, &targets[i], &saddr, tags);
else
bond_ns_send(slave, &targets[i], &in6addr_any, tags);
dst_release(dst);
kfree(tags);
}
}
static int bond_confirm_addr6(struct net_device *dev,
struct netdev_nested_priv *priv)
{
struct in6_addr *addr = (struct in6_addr *)priv->data;
return ipv6_chk_addr(dev_net(dev), addr, dev, 0);
}
static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr)
{
struct netdev_nested_priv priv = {
.data = addr,
};
int ret = false;
if (bond_confirm_addr6(bond->dev, &priv))
return true;
rcu_read_lock();
if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_confirm_addr6, &priv))
ret = true;
rcu_read_unlock();
return ret;
}
static void bond_validate_na(struct bonding *bond, struct slave *slave,
struct in6_addr *saddr, struct in6_addr *daddr)
{
int i;
/* Ignore NAs that:
* 1. Source address is unspecified address.
* 2. Dest address is neither all-nodes multicast address nor
* exist on bond interface.
*/
if (ipv6_addr_any(saddr) ||
(!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) &&
!bond_has_this_ip6(bond, daddr))) {
slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n",
__func__, saddr, daddr);
return;
}
i = bond_get_targets_ip6(bond->params.ns_targets, saddr);
if (i == -1) {
slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c not found in targets\n",
__func__, saddr);
return;
}
slave->last_rx = jiffies;
slave->target_last_arp_rx[i] = jiffies;
}
static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond,
struct slave *slave)
{
struct slave *curr_active_slave, *curr_arp_slave;
struct in6_addr *saddr, *daddr;
struct {
struct ipv6hdr ip6;
struct icmp6hdr icmp6;
} *combined, _combined;
if (skb->pkt_type == PACKET_OTHERHOST ||
skb->pkt_type == PACKET_LOOPBACK)
goto out;
combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined);
if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP ||
(combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&
combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT))
goto out;
saddr = &combined->ip6.saddr;
daddr = &combined->ip6.daddr;
slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n",
__func__, slave->dev->name, bond_slave_state(slave),
bond->params.arp_validate, slave_do_arp_validate(bond, slave),
saddr, daddr);
curr_active_slave = rcu_dereference(bond->curr_active_slave);
curr_arp_slave = rcu_dereference(bond->current_arp_slave);
/* We 'trust' the received ARP enough to validate it if:
* see bond_arp_rcv().
*/
if (bond_is_active_slave(slave))
bond_validate_na(bond, slave, saddr, daddr);
else if (curr_active_slave &&
time_after(slave_last_rx(bond, curr_active_slave),
curr_active_slave->last_link_up))
bond_validate_na(bond, slave, daddr, saddr);
else if (curr_arp_slave &&
bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1))
bond_validate_na(bond, slave, saddr, daddr);
out:
return RX_HANDLER_ANOTHER;
}
#endif
int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond,
struct slave *slave)
{
#if IS_ENABLED(CONFIG_IPV6)
bool is_ipv6 = skb->protocol == __cpu_to_be16(ETH_P_IPV6);
#endif
bool is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n",
__func__, skb->dev->name);
/* Use arp validate logic for both ARP and NS */
if (!slave_do_arp_validate(bond, slave)) {
if ((slave_do_arp_validate_only(bond) && is_arp) ||
#if IS_ENABLED(CONFIG_IPV6)
(slave_do_arp_validate_only(bond) && is_ipv6) ||
#endif
!slave_do_arp_validate_only(bond))
slave->last_rx = jiffies;
return RX_HANDLER_ANOTHER;
} else if (is_arp) {
return bond_arp_rcv(skb, bond, slave);
#if IS_ENABLED(CONFIG_IPV6)
} else if (is_ipv6) {
return bond_na_rcv(skb, bond, slave);
#endif
} else {
return RX_HANDLER_ANOTHER;
}
}
static void bond_send_validate(struct bonding *bond, struct slave *slave)
{
bond_arp_send_all(bond, slave);
#if IS_ENABLED(CONFIG_IPV6)
bond_ns_send_all(bond, slave);
#endif
}
/* function to verify if we're in the arp_interval timeslice, returns true if
* (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval +
* arp_interval/2) . the arp_interval/2 is needed for really fast networks.
*/
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod)
{
int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
return time_in_range(jiffies,
last_act - delta_in_ticks,
last_act + mod * delta_in_ticks + delta_in_ticks/2);
}
/* This function is called regularly to monitor each slave's link
* ensuring that traffic is being sent and received when arp monitoring
* is used in load-balancing mode. if the adapter has been dormant, then an
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
static void bond_loadbalance_arp_mon(struct bonding *bond)
{
struct slave *slave, *oldcurrent;
struct list_head *iter;
int do_failover = 0, slave_state_changed = 0;
if (!bond_has_slaves(bond))
goto re_arm;
rcu_read_lock();
oldcurrent = rcu_dereference(bond->curr_active_slave);
/* see if any of the previous devices are up now (i.e. they have
* xmt and rcv traffic). the curr_active_slave does not come into
* the picture unless it is null. also, slave->last_link_up is not
* needed here because we send an arp on each slave and give a slave
* as long as it needs to get the tx/rx within the delta.
* TODO: what about up/down delay in arp mode? it wasn't here before
* so it can wait
*/
bond_for_each_slave_rcu(bond, slave, iter) {
unsigned long last_tx = slave_last_tx(slave);
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, last_tx, 1) &&
bond_time_in_interval(bond, slave->last_rx, 1)) {
bond_propose_link_state(slave, BOND_LINK_UP);
slave_state_changed = 1;
/* primary_slave has no meaning in round-robin
* mode. the window of a slave being up and
* curr_active_slave being null after enslaving
* is closed.
*/
if (!oldcurrent) {
slave_info(bond->dev, slave->dev, "link status definitely up\n");
do_failover = 1;
} else {
slave_info(bond->dev, slave->dev, "interface is now up\n");
}
}
} else {
/* slave->link == BOND_LINK_UP */
/* not all switches will respond to an arp request
* when the source ip is 0, so don't take the link down
* if we don't know our ip yet
*/
if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) ||
!bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
slave_state_changed = 1;
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
slave_info(bond->dev, slave->dev, "interface is now down\n");
if (slave == oldcurrent)
do_failover = 1;
}
}
/* note: if switch is in round-robin mode, all links
* must tx arp to ensure all links rx an arp - otherwise
* links may oscillate or not come up at all; if switch is
* in something like xor mode, there is nothing we can
* do - all replies will be rx'ed on same link causing slaves
* to be unstable during low/no traffic periods
*/
if (bond_slave_is_up(slave))
bond_send_validate(bond, slave);
}
rcu_read_unlock();
if (do_failover || slave_state_changed) {
if (!rtnl_trylock())
goto re_arm;
bond_for_each_slave(bond, slave, iter) {
if (slave->link_new_state != BOND_LINK_NOCHANGE)
slave->link = slave->link_new_state;
}
if (slave_state_changed) {
bond_slave_state_change(bond);
if (BOND_MODE(bond) == BOND_MODE_XOR)
bond_update_slave_arr(bond, NULL);
}
if (do_failover) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
rtnl_unlock();
}
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work,
msecs_to_jiffies(bond->params.arp_interval));
}
/* Called to inspect slaves for active-backup mode ARP monitor link state
* changes. Sets proposed link state in slaves to specify what action
* should take place for the slave. Returns 0 if no changes are found, >0
* if changes to link states must be committed.
*
* Called with rcu_read_lock held.
*/
static int bond_ab_arp_inspect(struct bonding *bond)
{
unsigned long last_tx, last_rx;
struct list_head *iter;
struct slave *slave;
int commit = 0;
bond_for_each_slave_rcu(bond, slave, iter) {
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
last_rx = slave_last_rx(bond, slave);
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, last_rx, 1)) {
bond_propose_link_state(slave, BOND_LINK_UP);
commit++;
} else if (slave->link == BOND_LINK_BACK) {
bond_propose_link_state(slave, BOND_LINK_FAIL);
commit++;
}
continue;
}
/* Give slaves 2*delta after being enslaved or made
* active. This avoids bouncing, as the last receive
* times need a full ARP monitor cycle to be updated.
*/
if (bond_time_in_interval(bond, slave->last_link_up, 2))
continue;
/* Backup slave is down if:
* - No current_arp_slave AND
* - more than (missed_max+1)*delta since last receive AND
* - the bond has an IP address
*
* Note: a non-null current_arp_slave indicates
* the curr_active_slave went down and we are
* searching for a new one; under this condition
* we only take the curr_active_slave down - this
* gives each slave a chance to tx/rx traffic
* before being taken out
*/
if (!bond_is_active_slave(slave) &&
!rcu_access_pointer(bond->current_arp_slave) &&
!bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
commit++;
}
/* Active slave is down if:
* - more than missed_max*delta since transmitting OR
* - (more than missed_max*delta since receive AND
* the bond has an IP address)
*/
last_tx = slave_last_tx(slave);
if (bond_is_active_slave(slave) &&
(!bond_time_in_interval(bond, last_tx, bond->params.missed_max) ||
!bond_time_in_interval(bond, last_rx, bond->params.missed_max))) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
commit++;
}
}
return commit;
}
/* Called to commit link state changes noted by inspection step of
* active-backup mode ARP monitor.
*
* Called with RTNL hold.
*/
static void bond_ab_arp_commit(struct bonding *bond)
{
bool do_failover = false;
struct list_head *iter;
unsigned long last_tx;
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
switch (slave->link_new_state) {
case BOND_LINK_NOCHANGE:
continue;
case BOND_LINK_UP:
last_tx = slave_last_tx(slave);
if (rtnl_dereference(bond->curr_active_slave) != slave ||
(!rtnl_dereference(bond->curr_active_slave) &&
bond_time_in_interval(bond, last_tx, 1))) {
struct slave *current_arp_slave;
current_arp_slave = rtnl_dereference(bond->current_arp_slave);
bond_set_slave_link_state(slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
if (current_arp_slave) {
bond_set_slave_inactive_flags(
current_arp_slave,
BOND_SLAVE_NOTIFY_NOW);
RCU_INIT_POINTER(bond->current_arp_slave, NULL);
}
slave_info(bond->dev, slave->dev, "link status definitely up\n");
if (!rtnl_dereference(bond->curr_active_slave) ||
slave == rtnl_dereference(bond->primary_slave) ||
slave->prio > rtnl_dereference(bond->curr_active_slave)->prio)
do_failover = true;
}
continue;
case BOND_LINK_DOWN:
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
bond_set_slave_link_state(slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_NOW);
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n");
if (slave == rtnl_dereference(bond->curr_active_slave)) {
RCU_INIT_POINTER(bond->current_arp_slave, NULL);
do_failover = true;
}
continue;
case BOND_LINK_FAIL:
bond_set_slave_link_state(slave, BOND_LINK_FAIL,
BOND_SLAVE_NOTIFY_NOW);
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
/* A slave has just been enslaved and has become
* the current active slave.
*/
if (rtnl_dereference(bond->curr_active_slave))
RCU_INIT_POINTER(bond->current_arp_slave, NULL);
continue;
default:
slave_err(bond->dev, slave->dev,
"impossible: link_new_state %d on slave\n",
slave->link_new_state);
continue;
}
}
if (do_failover) {
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
}
bond_set_carrier(bond);
}
/* Send ARP probes for active-backup mode ARP monitor.
*
* Called with rcu_read_lock held.
*/
static bool bond_ab_arp_probe(struct bonding *bond)
{
struct slave *slave, *before = NULL, *new_slave = NULL,
*curr_arp_slave = rcu_dereference(bond->current_arp_slave),
*curr_active_slave = rcu_dereference(bond->curr_active_slave);
struct list_head *iter;
bool found = false;
bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
if (curr_arp_slave && curr_active_slave)
netdev_info(bond->dev, "PROBE: c_arp %s && cas %s BAD\n",
curr_arp_slave->dev->name,
curr_active_slave->dev->name);
if (curr_active_slave) {
bond_send_validate(bond, curr_active_slave);
return should_notify_rtnl;
}
/* if we don't have a curr_active_slave, search for the next available
* backup slave from the current_arp_slave and make it the candidate
* for becoming the curr_active_slave
*/
if (!curr_arp_slave) {
curr_arp_slave = bond_first_slave_rcu(bond);
if (!curr_arp_slave)
return should_notify_rtnl;
}
bond_for_each_slave_rcu(bond, slave, iter) {
if (!found && !before && bond_slave_is_up(slave))
before = slave;
if (found && !new_slave && bond_slave_is_up(slave))
new_slave = slave;
/* if the link state is up at this point, we
* mark it down - this can happen if we have
* simultaneous link failures and
* reselect_active_interface doesn't make this
* one the current slave so it is still marked
* up when it is actually down
*/
if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
bond_set_slave_link_state(slave, BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_LATER);
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_LATER);
slave_info(bond->dev, slave->dev, "backup interface is now down\n");
}
if (slave == curr_arp_slave)
found = true;
}
if (!new_slave && before)
new_slave = before;
if (!new_slave)
goto check_state;
bond_set_slave_link_state(new_slave, BOND_LINK_BACK,
BOND_SLAVE_NOTIFY_LATER);
bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
bond_send_validate(bond, new_slave);
new_slave->last_link_up = jiffies;
rcu_assign_pointer(bond->current_arp_slave, new_slave);
check_state:
bond_for_each_slave_rcu(bond, slave, iter) {
if (slave->should_notify || slave->should_notify_link) {
should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
break;
}
}
return should_notify_rtnl;
}
static void bond_activebackup_arp_mon(struct bonding *bond)
{
bool should_notify_peers = false;
bool should_notify_rtnl = false;
int delta_in_ticks;
delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
if (!bond_has_slaves(bond))
goto re_arm;
rcu_read_lock();
should_notify_peers = bond_should_notify_peers(bond);
if (bond_ab_arp_inspect(bond)) {
rcu_read_unlock();
/* Race avoidance with bond_close flush of workqueue */
if (!rtnl_trylock()) {
delta_in_ticks = 1;
should_notify_peers = false;
goto re_arm;
}
bond_ab_arp_commit(bond);
rtnl_unlock();
rcu_read_lock();
}
should_notify_rtnl = bond_ab_arp_probe(bond);
rcu_read_unlock();
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
if (should_notify_peers || should_notify_rtnl) {
if (!rtnl_trylock())
return;
if (should_notify_peers) {
bond->send_peer_notif--;
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
bond->dev);
}
if (should_notify_rtnl) {
bond_slave_state_notify(bond);
bond_slave_link_notify(bond);
}
rtnl_unlock();
}
}
static void bond_arp_monitor(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
bond_activebackup_arp_mon(bond);
else
bond_loadbalance_arp_mon(bond);
}
/*-------------------------- netdev event handling --------------------------*/
/* Change device name */
static int bond_event_changename(struct bonding *bond)
{
bond_remove_proc_entry(bond);
bond_create_proc_entry(bond);
bond_debug_reregister(bond);
return NOTIFY_DONE;
}
static int bond_master_netdev_event(unsigned long event,
struct net_device *bond_dev)
{
struct bonding *event_bond = netdev_priv(bond_dev);
netdev_dbg(bond_dev, "%s called\n", __func__); switch (event) {
case NETDEV_CHANGENAME:
return bond_event_changename(event_bond);
case NETDEV_UNREGISTER:
bond_remove_proc_entry(event_bond);
#ifdef CONFIG_XFRM_OFFLOAD
xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
#endif /* CONFIG_XFRM_OFFLOAD */
break;
case NETDEV_REGISTER:
bond_create_proc_entry(event_bond);
break;
default:
break;
}
return NOTIFY_DONE;
}
static int bond_slave_netdev_event(unsigned long event,
struct net_device *slave_dev)
{
struct slave *slave = bond_slave_get_rtnl(slave_dev), *primary;
struct bonding *bond;
struct net_device *bond_dev;
/* A netdev event can be generated while enslaving a device
* before netdev_rx_handler_register is called in which case
* slave will be NULL
*/
if (!slave) {
netdev_dbg(slave_dev, "%s called on NULL slave\n", __func__);
return NOTIFY_DONE;
}
bond_dev = slave->bond->dev;
bond = slave->bond;
primary = rtnl_dereference(bond->primary_slave); slave_dbg(bond_dev, slave_dev, "%s called\n", __func__); switch (event) {
case NETDEV_UNREGISTER:
if (bond_dev->type != ARPHRD_ETHER)
bond_release_and_destroy(bond_dev, slave_dev);
else
__bond_release_one(bond_dev, slave_dev, false, true);
break;
case NETDEV_UP:
case NETDEV_CHANGE:
/* For 802.3ad mode only:
* Getting invalid Speed/Duplex values here will put slave
* in weird state. Mark it as link-fail if the link was
* previously up or link-down if it hasn't yet come up, and
* let link-monitoring (miimon) set it right when correct
* speeds/duplex are available.
*/
if (bond_update_speed_duplex(slave) &&
BOND_MODE(bond) == BOND_MODE_8023AD) {
if (slave->last_link_up)
slave->link = BOND_LINK_FAIL;
else
slave->link = BOND_LINK_DOWN;
}
if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave);
fallthrough;
case NETDEV_DOWN:
/* Refresh slave-array if applicable!
* If the setup does not use miimon or arpmon (mode-specific!),
* then these events will not cause the slave-array to be
* refreshed. This will cause xmit to use a slave that is not
* usable. Avoid such situation by refeshing the array at these
* events. If these (miimon/arpmon) parameters are configured
* then array gets refreshed twice and that should be fine!
*/
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
break;
case NETDEV_CHANGEMTU:
/* TODO: Should slaves be allowed to
* independently alter their MTU? For
* an active-backup bond, slaves need
* not be the same type of device, so
* MTUs may vary. For other modes,
* slaves arguably should have the
* same MTUs. To do this, we'd need to
* take over the slave's change_mtu
* function for the duration of their
* servitude.
*/
break;
case NETDEV_CHANGENAME:
/* we don't care if we don't have primary set */
if (!bond_uses_primary(bond) ||
!bond->params.primary[0])
break;
if (slave == primary) {
/* slave's name changed - he's no longer primary */
RCU_INIT_POINTER(bond->primary_slave, NULL); } else if (!strcmp(slave_dev->name, bond->params.primary)) {
/* we have a new primary slave */
rcu_assign_pointer(bond->primary_slave, slave);
} else { /* we didn't change primary - exit */
break;
}
netdev_info(bond->dev, "Primary slave changed to %s, reselecting active slave\n",
primary ? slave_dev->name : "none");
block_netpoll_tx();
bond_select_active_slave(bond);
unblock_netpoll_tx();
break;
case NETDEV_FEAT_CHANGE:
if (!bond->notifier_ctx) { bond->notifier_ctx = true;
bond_compute_features(bond);
bond->notifier_ctx = false;
}
break;
case NETDEV_RESEND_IGMP:
/* Propagate to master device */
call_netdevice_notifiers(event, slave->bond->dev);
break;
case NETDEV_XDP_FEAT_CHANGE:
bond_xdp_set_features(bond_dev);
break;
default:
break;
}
return NOTIFY_DONE;
}
/* bond_netdev_event: handle netdev notifier chain events.
*
* This function receives events for the netdev chain. The caller (an
* ioctl handler calling blocking_notifier_call_chain) holds the necessary
* locks for us to safely manipulate the slave devices (RTNL lock,
* dev_probe_lock).
*/
static int bond_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
netdev_dbg(event_dev, "%s received %s\n",
__func__, netdev_cmd_to_name(event));
if (!(event_dev->priv_flags & IFF_BONDING))
return NOTIFY_DONE;
if (event_dev->flags & IFF_MASTER) {
int ret;
ret = bond_master_netdev_event(event, event_dev);
if (ret != NOTIFY_DONE)
return ret;
}
if (event_dev->flags & IFF_SLAVE) return bond_slave_netdev_event(event, event_dev);
return NOTIFY_DONE;
}
static struct notifier_block bond_netdev_notifier = {
.notifier_call = bond_netdev_event,
};
/*---------------------------- Hashing Policies -----------------------------*/
/* Helper to access data in a packet, with or without a backing skb.
* If skb is given the data is linearized if necessary via pskb_may_pull.
*/
static inline const void *bond_pull_data(struct sk_buff *skb,
const void *data, int hlen, int n)
{
if (likely(n <= hlen))
return data;
else if (skb && likely(pskb_may_pull(skb, n)))
return skb->data;
return NULL;
}
/* L2 hash helper */
static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
{
struct ethhdr *ep;
data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
if (!data)
return 0;
ep = (struct ethhdr *)(data + mhoff);
return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto);
}
static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data,
int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34)
{
const struct ipv6hdr *iph6;
const struct iphdr *iph;
if (l2_proto == htons(ETH_P_IP)) {
data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph));
if (!data)
return false;
iph = (const struct iphdr *)(data + *nhoff);
iph_to_flow_copy_v4addrs(fk, iph);
*nhoff += iph->ihl << 2;
if (!ip_is_fragment(iph))
*ip_proto = iph->protocol;
} else if (l2_proto == htons(ETH_P_IPV6)) {
data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6));
if (!data)
return false;
iph6 = (const struct ipv6hdr *)(data + *nhoff);
iph_to_flow_copy_v6addrs(fk, iph6);
*nhoff += sizeof(*iph6);
*ip_proto = iph6->nexthdr;
} else {
return false;
}
if (l34 && *ip_proto >= 0)
fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
return true;
}
static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
{
u32 srcmac_vendor = 0, srcmac_dev = 0;
struct ethhdr *mac_hdr;
u16 vlan = 0;
int i;
data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
if (!data)
return 0;
mac_hdr = (struct ethhdr *)(data + mhoff);
for (i = 0; i < 3; i++)
srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i];
for (i = 3; i < ETH_ALEN; i++)
srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i];
if (skb && skb_vlan_tag_present(skb))
vlan = skb_vlan_tag_get(skb);
return vlan ^ srcmac_vendor ^ srcmac_dev;
}
/* Extract the appropriate headers based on bond's xmit policy */
static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data,
__be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk)
{
bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
int ip_proto = -1;
switch (bond->params.xmit_policy) {
case BOND_XMIT_POLICY_ENCAP23:
case BOND_XMIT_POLICY_ENCAP34:
memset(fk, 0, sizeof(*fk));
return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
fk, data, l2_proto, nhoff, hlen, 0);
default:
break;
}
fk->ports.ports = 0;
memset(&fk->icmp, 0, sizeof(fk->icmp));
if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34))
return false;
/* ICMP error packets contains at least 8 bytes of the header
* of the packet which generated the error. Use this information
* to correlate ICMP error packets within the same flow which
* generated the error.
*/
if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) {
skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen);
if (ip_proto == IPPROTO_ICMP) {
if (!icmp_is_err(fk->icmp.type))
return true;
nhoff += sizeof(struct icmphdr);
} else if (ip_proto == IPPROTO_ICMPV6) {
if (!icmpv6_is_err(fk->icmp.type))
return true;
nhoff += sizeof(struct icmp6hdr);
}
return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34);
}
return true;
}
static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy)
{
hash ^= (__force u32)flow_get_u32_dst(flow) ^
(__force u32)flow_get_u32_src(flow);
hash ^= (hash >> 16);
hash ^= (hash >> 8);
/* discard lowest hash bit to deal with the common even ports pattern */
if (xmit_policy == BOND_XMIT_POLICY_LAYER34 ||
xmit_policy == BOND_XMIT_POLICY_ENCAP34)
return hash >> 1;
return hash;
}
/* Generate hash based on xmit policy. If @skb is given it is used to linearize
* the data as required, but this function can be used without it if the data is
* known to be linear (e.g. with xdp_buff).
*/
static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data,
__be16 l2_proto, int mhoff, int nhoff, int hlen)
{
struct flow_keys flow;
u32 hash;
if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC)
return bond_vlan_srcmac_hash(skb, data, mhoff, hlen);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
!bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow))
return bond_eth_hash(skb, data, mhoff, hlen);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
hash = bond_eth_hash(skb, data, mhoff, hlen);
} else {
if (flow.icmp.id)
memcpy(&hash, &flow.icmp, sizeof(hash));
else
memcpy(&hash, &flow.ports.ports, sizeof(hash));
}
return bond_ip_hash(hash, &flow, bond->params.xmit_policy);
}
/**
* bond_xmit_hash - generate a hash value based on the xmit policy
* @bond: bonding device
* @skb: buffer to use for headers
*
* This function will extract the necessary headers from the skb buffer and use
* them to generate a hash based on the xmit_policy set in the bonding device
*/
u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
{
if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 &&
skb->l4_hash)
return skb->hash;
return __bond_xmit_hash(bond, skb, skb->data, skb->protocol,
0, skb_network_offset(skb),
skb_headlen(skb));
}
/**
* bond_xmit_hash_xdp - generate a hash value based on the xmit policy
* @bond: bonding device
* @xdp: buffer to use for headers
*
* The XDP variant of bond_xmit_hash.
*/
static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp)
{
struct ethhdr *eth;
if (xdp->data + sizeof(struct ethhdr) > xdp->data_end)
return 0;
eth = (struct ethhdr *)xdp->data;
return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0,
sizeof(struct ethhdr), xdp->data_end - xdp->data);
}
/*-------------------------- Device entry points ----------------------------*/
void bond_work_init_all(struct bonding *bond)
{
INIT_DELAYED_WORK(&bond->mcast_work,
bond_resend_igmp_join_requests_delayed);
INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
}
static void bond_work_cancel_all(struct bonding *bond)
{
cancel_delayed_work_sync(&bond->mii_work);
cancel_delayed_work_sync(&bond->arp_work);
cancel_delayed_work_sync(&bond->alb_work);
cancel_delayed_work_sync(&bond->ad_work);
cancel_delayed_work_sync(&bond->mcast_work);
cancel_delayed_work_sync(&bond->slave_arr_work);
}
static int bond_open(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) {
bond->rr_tx_counter = alloc_percpu(u32);
if (!bond->rr_tx_counter)
return -ENOMEM;
}
/* reset slave->backup and slave->inactive */
if (bond_has_slaves(bond)) {
bond_for_each_slave(bond, slave, iter) {
if (bond_uses_primary(bond) &&
slave != rcu_access_pointer(bond->curr_active_slave)) {
bond_set_slave_inactive_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
} else if (BOND_MODE(bond) != BOND_MODE_8023AD) {
bond_set_slave_active_flags(slave,
BOND_SLAVE_NOTIFY_NOW);
}
}
}
if (bond_is_lb(bond)) {
/* bond_alb_initialize must be called before the timer
* is started.
*/
if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB)))
return -ENOMEM;
if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB)
queue_delayed_work(bond->wq, &bond->alb_work, 0);
}
if (bond->params.miimon) /* link check interval, in milliseconds. */
queue_delayed_work(bond->wq, &bond->mii_work, 0);
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
queue_delayed_work(bond->wq, &bond->arp_work, 0);
bond->recv_probe = bond_rcv_validate;
}
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
queue_delayed_work(bond->wq, &bond->ad_work, 0);
/* register to receive LACPDUs */
bond->recv_probe = bond_3ad_lacpdu_recv;
bond_3ad_initiate_agg_selection(bond, 1);
bond_for_each_slave(bond, slave, iter)
dev_mc_add(slave->dev, lacpdu_mcast_addr);
}
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
return 0;
}
static int bond_close(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
bond_work_cancel_all(bond);
bond->send_peer_notif = 0;
if (bond_is_lb(bond))
bond_alb_deinitialize(bond);
bond->recv_probe = NULL;
if (bond_uses_primary(bond)) {
rcu_read_lock();
slave = rcu_dereference(bond->curr_active_slave);
if (slave)
bond_hw_addr_flush(bond_dev, slave->dev);
rcu_read_unlock();
} else {
struct list_head *iter;
bond_for_each_slave(bond, slave, iter)
bond_hw_addr_flush(bond_dev, slave->dev);
}
return 0;
}
/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
* that some drivers can provide 32bit values only.
*/
static void bond_fold_stats(struct rtnl_link_stats64 *_res,
const struct rtnl_link_stats64 *_new,
const struct rtnl_link_stats64 *_old)
{
const u64 *new = (const u64 *)_new;
const u64 *old = (const u64 *)_old;
u64 *res = (u64 *)_res;
int i;
for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
u64 nv = new[i];
u64 ov = old[i];
s64 delta = nv - ov;
/* detects if this particular field is 32bit only */
if (((nv | ov) >> 32) == 0)
delta = (s64)(s32)((u32)nv - (u32)ov);
/* filter anomalies, some drivers reset their stats
* at down/up events.
*/
if (delta > 0)
res[i] += delta;
}
}
#ifdef CONFIG_LOCKDEP
static int bond_get_lowest_level_rcu(struct net_device *dev)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
int cur = 0, max = 0;
now = dev;
iter = &dev->adj_list.lower;
while (1) {
next = NULL;
while (1) {
ldev = netdev_next_lower_dev_rcu(now, &iter);
if (!ldev)
break;
next = ldev;
niter = &ldev->adj_list.lower;
dev_stack[cur] = now;
iter_stack[cur++] = iter;
if (max <= cur)
max = cur;
break;
}
if (!next) {
if (!cur)
return max;
next = dev_stack[--cur];
niter = iter_stack[cur];
}
now = next;
iter = niter;
}
return max;
}
#endif
static void bond_get_stats(struct net_device *bond_dev,
struct rtnl_link_stats64 *stats)
{
struct bonding *bond = netdev_priv(bond_dev);
struct rtnl_link_stats64 temp;
struct list_head *iter;
struct slave *slave;
int nest_level = 0;
rcu_read_lock();
#ifdef CONFIG_LOCKDEP
nest_level = bond_get_lowest_level_rcu(bond_dev);
#endif
spin_lock_nested(&bond->stats_lock, nest_level);
memcpy(stats, &bond->bond_stats, sizeof(*stats));
bond_for_each_slave_rcu(bond, slave, iter) {
const struct rtnl_link_stats64 *new =
dev_get_stats(slave->dev, &temp);
bond_fold_stats(stats, new, &slave->slave_stats);
/* save off the slave stats for the next run */
memcpy(&slave->slave_stats, new, sizeof(*new));
}
memcpy(&bond->bond_stats, stats, sizeof(*stats));
spin_unlock(&bond->stats_lock);
rcu_read_unlock();
}
static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
{
struct bonding *bond = netdev_priv(bond_dev);
struct mii_ioctl_data *mii = NULL;
netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd);
switch (cmd) {
case SIOCGMIIPHY:
mii = if_mii(ifr);
if (!mii)
return -EINVAL;
mii->phy_id = 0;
fallthrough;
case SIOCGMIIREG:
/* We do this again just in case we were called by SIOCGMIIREG
* instead of SIOCGMIIPHY.
*/
mii = if_mii(ifr);
if (!mii)
return -EINVAL;
if (mii->reg_num == 1) {
mii->val_out = 0;
if (netif_carrier_ok(bond->dev))
mii->val_out = BMSR_LSTATUS;
}
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
{
struct bonding *bond = netdev_priv(bond_dev);
struct net_device *slave_dev = NULL;
struct ifbond k_binfo;
struct ifbond __user *u_binfo = NULL;
struct ifslave k_sinfo;
struct ifslave __user *u_sinfo = NULL;
struct bond_opt_value newval;
struct net *net;
int res = 0;
netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd);
switch (cmd) {
case SIOCBONDINFOQUERY:
u_binfo = (struct ifbond __user *)ifr->ifr_data;
if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond)))
return -EFAULT;
bond_info_query(bond_dev, &k_binfo);
if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond)))
return -EFAULT;
return 0;
case SIOCBONDSLAVEINFOQUERY:
u_sinfo = (struct ifslave __user *)ifr->ifr_data;
if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave)))
return -EFAULT;
res = bond_slave_info_query(bond_dev, &k_sinfo);
if (res == 0 &&
copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave)))
return -EFAULT;
return res;
default:
break;
}
net = dev_net(bond_dev);
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
slave_dev = __dev_get_by_name(net, ifr->ifr_slave);
slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev);
if (!slave_dev)
return -ENODEV;
switch (cmd) {
case SIOCBONDENSLAVE:
res = bond_enslave(bond_dev, slave_dev, NULL);
break;
case SIOCBONDRELEASE:
res = bond_release(bond_dev, slave_dev);
break;
case SIOCBONDSETHWADDR:
res = bond_set_dev_addr(bond_dev, slave_dev);
break;
case SIOCBONDCHANGEACTIVE:
bond_opt_initstr(&newval, slave_dev->name);
res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE,
&newval);
break;
default:
res = -EOPNOTSUPP;
}
return res;
}
static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr,
void __user *data, int cmd)
{
struct ifreq ifrdata = { .ifr_data = data };
switch (cmd) {
case BOND_INFO_QUERY_OLD:
return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY);
case BOND_SLAVE_INFO_QUERY_OLD:
return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY);
case BOND_ENSLAVE_OLD:
return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE);
case BOND_RELEASE_OLD:
return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE);
case BOND_SETHWADDR_OLD:
return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR);
case BOND_CHANGE_ACTIVE_OLD:
return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE);
}
return -EOPNOTSUPP;
}
static void bond_change_rx_flags(struct net_device *bond_dev, int change)
{
struct bonding *bond = netdev_priv(bond_dev);
if (change & IFF_PROMISC)
bond_set_promiscuity(bond,
bond_dev->flags & IFF_PROMISC ? 1 : -1);
if (change & IFF_ALLMULTI)
bond_set_allmulti(bond,
bond_dev->flags & IFF_ALLMULTI ? 1 : -1);
}
static void bond_set_rx_mode(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
rcu_read_lock();
if (bond_uses_primary(bond)) {
slave = rcu_dereference(bond->curr_active_slave);
if (slave) {
dev_uc_sync(slave->dev, bond_dev);
dev_mc_sync(slave->dev, bond_dev);
}
} else {
bond_for_each_slave_rcu(bond, slave, iter) {
dev_uc_sync_multiple(slave->dev, bond_dev);
dev_mc_sync_multiple(slave->dev, bond_dev);
}
}
rcu_read_unlock();
}
static int bond_neigh_init(struct neighbour *n)
{
struct bonding *bond = netdev_priv(n->dev);
const struct net_device_ops *slave_ops;
struct neigh_parms parms;
struct slave *slave;
int ret = 0;
rcu_read_lock();
slave = bond_first_slave_rcu(bond);
if (!slave)
goto out;
slave_ops = slave->dev->netdev_ops;
if (!slave_ops->ndo_neigh_setup)
goto out;
/* TODO: find another way [1] to implement this.
* Passing a zeroed structure is fragile,
* but at least we do not pass garbage.
*
* [1] One way would be that ndo_neigh_setup() never touch
* struct neigh_parms, but propagate the new neigh_setup()
* back to ___neigh_create() / neigh_parms_alloc()
*/
memset(&parms, 0, sizeof(parms));
ret = slave_ops->ndo_neigh_setup(slave->dev, &parms);
if (ret)
goto out;
if (parms.neigh_setup)
ret = parms.neigh_setup(n);
out:
rcu_read_unlock();
return ret;
}
/* The bonding ndo_neigh_setup is called at init time beofre any
* slave exists. So we must declare proxy setup function which will
* be used at run time to resolve the actual slave neigh param setup.
*
* It's also called by master devices (such as vlans) to setup their
* underlying devices. In that case - do nothing, we're already set up from
* our init.
*/
static int bond_neigh_setup(struct net_device *dev,
struct neigh_parms *parms)
{
/* modify only our neigh_parms */
if (parms->dev == dev)
parms->neigh_setup = bond_neigh_init;
return 0;
}
/* Change the MTU of all of a master's slaves to match the master */
static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *rollback_slave;
struct list_head *iter;
int res = 0;
netdev_dbg(bond_dev, "bond=%p, new_mtu=%d\n", bond, new_mtu);
bond_for_each_slave(bond, slave, iter) {
slave_dbg(bond_dev, slave->dev, "s %p c_m %p\n",
slave, slave->dev->netdev_ops->ndo_change_mtu);
res = dev_set_mtu(slave->dev, new_mtu);
if (res) {
/* If we failed to set the slave's mtu to the new value
* we must abort the operation even in ACTIVE_BACKUP
* mode, because if we allow the backup slaves to have
* different mtu values than the active slave we'll
* need to change their mtu when doing a failover. That
* means changing their mtu from timer context, which
* is probably not a good idea.
*/
slave_dbg(bond_dev, slave->dev, "err %d setting mtu to %d\n",
res, new_mtu);
goto unwind;
}
}
WRITE_ONCE(bond_dev->mtu, new_mtu);
return 0;
unwind:
/* unwind from head to the slave that failed */
bond_for_each_slave(bond, rollback_slave, iter) {
int tmp_res;
if (rollback_slave == slave)
break;
tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu);
if (tmp_res)
slave_dbg(bond_dev, rollback_slave->dev, "unwind err %d\n",
tmp_res);
}
return res;
}
/* Change HW address
*
* Note that many devices must be down to change the HW address, and
* downing the master releases all slaves. We can make bonds full of
* bonding devices to test this, however.
*/
static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *rollback_slave;
struct sockaddr_storage *ss = addr, tmp_ss;
struct list_head *iter;
int res = 0;
if (BOND_MODE(bond) == BOND_MODE_ALB)
return bond_alb_set_mac_address(bond_dev, addr);
netdev_dbg(bond_dev, "%s: bond=%p\n", __func__, bond);
/* If fail_over_mac is enabled, do nothing and return success.
* Returning an error causes ifenslave to fail.
*/
if (bond->params.fail_over_mac &&
BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
return 0;
if (!is_valid_ether_addr(ss->__data))
return -EADDRNOTAVAIL;
bond_for_each_slave(bond, slave, iter) {
slave_dbg(bond_dev, slave->dev, "%s: slave=%p\n",
__func__, slave);
res = dev_set_mac_address(slave->dev, addr, NULL);
if (res) {
/* TODO: consider downing the slave
* and retry ?
* User should expect communications
* breakage anyway until ARP finish
* updating, so...
*/
slave_dbg(bond_dev, slave->dev, "%s: err %d\n",
__func__, res);
goto unwind;
}
}
/* success */
dev_addr_set(bond_dev, ss->__data);
return 0;
unwind:
memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
tmp_ss.ss_family = bond_dev->type;
/* unwind from head to the slave that failed */
bond_for_each_slave(bond, rollback_slave, iter) {
int tmp_res;
if (rollback_slave == slave)
break;
tmp_res = dev_set_mac_address(rollback_slave->dev,
(struct sockaddr *)&tmp_ss, NULL);
if (tmp_res) {
slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n",
__func__, tmp_res);
}
}
return res;
}
/**
* bond_get_slave_by_id - get xmit slave with slave_id
* @bond: bonding device that is transmitting
* @slave_id: slave id up to slave_cnt-1 through which to transmit
*
* This function tries to get slave with slave_id but in case
* it fails, it tries to find the first available slave for transmission.
*/
static struct slave *bond_get_slave_by_id(struct bonding *bond,
int slave_id)
{
struct list_head *iter;
struct slave *slave;
int i = slave_id;
/* Here we start from the slave with slave_id */
bond_for_each_slave_rcu(bond, slave, iter) {
if (--i < 0) {
if (bond_slave_can_tx(slave))
return slave;
}
}
/* Here we start from the first slave up to slave_id */
i = slave_id;
bond_for_each_slave_rcu(bond, slave, iter) {
if (--i < 0)
break;
if (bond_slave_can_tx(slave))
return slave;
}
/* no slave that can tx has been found */
return NULL;
}
/**
* bond_rr_gen_slave_id - generate slave id based on packets_per_slave
* @bond: bonding device to use
*
* Based on the value of the bonding device's packets_per_slave parameter
* this function generates a slave id, which is usually used as the next
* slave to transmit through.
*/
static u32 bond_rr_gen_slave_id(struct bonding *bond)
{
u32 slave_id;
struct reciprocal_value reciprocal_packets_per_slave;
int packets_per_slave = bond->params.packets_per_slave;
switch (packets_per_slave) {
case 0:
slave_id = get_random_u32();
break;
case 1:
slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
break;
default:
reciprocal_packets_per_slave =
bond->params.reciprocal_packets_per_slave;
slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
slave_id = reciprocal_divide(slave_id,
reciprocal_packets_per_slave);
break;
}
return slave_id;
}
static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond,
struct sk_buff *skb)
{
struct slave *slave;
int slave_cnt;
u32 slave_id;
/* Start with the curr_active_slave that joined the bond as the
* default for sending IGMP traffic. For failover purposes one
* needs to maintain some consistency for the interface that will
* send the join/membership reports. The curr_active_slave found
* will send all of this type of traffic.
*/
if (skb->protocol == htons(ETH_P_IP)) {
int noff = skb_network_offset(skb);
struct iphdr *iph;
if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
goto non_igmp;
iph = ip_hdr(skb);
if (iph->protocol == IPPROTO_IGMP) {
slave = rcu_dereference(bond->curr_active_slave);
if (slave)
return slave;
return bond_get_slave_by_id(bond, 0);
}
}
non_igmp:
slave_cnt = READ_ONCE(bond->slave_cnt);
if (likely(slave_cnt)) {
slave_id = bond_rr_gen_slave_id(bond) % slave_cnt;
return bond_get_slave_by_id(bond, slave_id);
}
return NULL;
}
static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond,
struct xdp_buff *xdp)
{
struct slave *slave;
int slave_cnt;
u32 slave_id;
const struct ethhdr *eth;
void *data = xdp->data;
if (data + sizeof(struct ethhdr) > xdp->data_end)
goto non_igmp;
eth = (struct ethhdr *)data;
data += sizeof(struct ethhdr);
/* See comment on IGMP in bond_xmit_roundrobin_slave_get() */
if (eth->h_proto == htons(ETH_P_IP)) {
const struct iphdr *iph;
if (data + sizeof(struct iphdr) > xdp->data_end)
goto non_igmp;
iph = (struct iphdr *)data;
if (iph->protocol == IPPROTO_IGMP) {
slave = rcu_dereference(bond->curr_active_slave);
if (slave)
return slave;
return bond_get_slave_by_id(bond, 0);
}
}
non_igmp:
slave_cnt = READ_ONCE(bond->slave_cnt);
if (likely(slave_cnt)) {
slave_id = bond_rr_gen_slave_id(bond) % slave_cnt;
return bond_get_slave_by_id(bond, slave_id);
}
return NULL;
}
static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
slave = bond_xmit_roundrobin_slave_get(bond, skb);
if (likely(slave))
return bond_dev_queue_xmit(bond, skb, slave->dev);
return bond_tx_drop(bond_dev, skb);
}
static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond)
{
return rcu_dereference(bond->curr_active_slave);
}
/* In active-backup mode, we know that bond->curr_active_slave is always valid if
* the bond has a usable interface.
*/
static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
slave = bond_xmit_activebackup_slave_get(bond);
if (slave)
return bond_dev_queue_xmit(bond, skb, slave->dev);
return bond_tx_drop(bond_dev, skb);
}
/* Use this to update slave_array when (a) it's not appropriate to update
* slave_array right away (note that update_slave_array() may sleep)
* and / or (b) RTNL is not held.
*/
void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay)
{
queue_delayed_work(bond->wq, &bond->slave_arr_work, delay);
}
/* Slave array work handler. Holds only RTNL */
static void bond_slave_arr_handler(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
slave_arr_work.work);
int ret;
if (!rtnl_trylock())
goto err;
ret = bond_update_slave_arr(bond, NULL);
rtnl_unlock();
if (ret) {
pr_warn_ratelimited("Failed to update slave array from WT\n");
goto err;
}
return;
err:
bond_slave_arr_work_rearm(bond, 1);
}
static void bond_skip_slave(struct bond_up_slave *slaves,
struct slave *skipslave)
{
int idx;
/* Rare situation where caller has asked to skip a specific
* slave but allocation failed (most likely!). BTW this is
* only possible when the call is initiated from
* __bond_release_one(). In this situation; overwrite the
* skipslave entry in the array with the last entry from the
* array to avoid a situation where the xmit path may choose
* this to-be-skipped slave to send a packet out.
*/
for (idx = 0; slaves && idx < slaves->count; idx++) {
if (skipslave == slaves->arr[idx]) {
slaves->arr[idx] =
slaves->arr[slaves->count - 1];
slaves->count--;
break;
}
}
}
static void bond_set_slave_arr(struct bonding *bond,
struct bond_up_slave *usable_slaves,
struct bond_up_slave *all_slaves)
{
struct bond_up_slave *usable, *all;
usable = rtnl_dereference(bond->usable_slaves);
rcu_assign_pointer(bond->usable_slaves, usable_slaves);
kfree_rcu(usable, rcu);
all = rtnl_dereference(bond->all_slaves);
rcu_assign_pointer(bond->all_slaves, all_slaves);
kfree_rcu(all, rcu);
}
static void bond_reset_slave_arr(struct bonding *bond)
{
bond_set_slave_arr(bond, NULL, NULL);
}
/* Build the usable slaves array in control path for modes that use xmit-hash
* to determine the slave interface -
* (a) BOND_MODE_8023AD
* (b) BOND_MODE_XOR
* (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0
*
* The caller is expected to hold RTNL only and NO other lock!
*/
int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
{
struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL;
struct slave *slave;
struct list_head *iter;
int agg_id = 0;
int ret = 0;
might_sleep();
usable_slaves = kzalloc(struct_size(usable_slaves, arr,
bond->slave_cnt), GFP_KERNEL);
all_slaves = kzalloc(struct_size(all_slaves, arr,
bond->slave_cnt), GFP_KERNEL);
if (!usable_slaves || !all_slaves) {
ret = -ENOMEM;
goto out;
}
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct ad_info ad_info;
spin_lock_bh(&bond->mode_lock);
if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
spin_unlock_bh(&bond->mode_lock);
pr_debug("bond_3ad_get_active_agg_info failed\n");
/* No active aggragator means it's not safe to use
* the previous array.
*/
bond_reset_slave_arr(bond);
goto out;
}
spin_unlock_bh(&bond->mode_lock);
agg_id = ad_info.aggregator_id;
}
bond_for_each_slave(bond, slave, iter) {
if (skipslave == slave)
continue;
all_slaves->arr[all_slaves->count++] = slave;
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct aggregator *agg;
agg = SLAVE_AD_INFO(slave)->port.aggregator;
if (!agg || agg->aggregator_identifier != agg_id)
continue;
}
if (!bond_slave_can_tx(slave))
continue;
slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n",
usable_slaves->count);
usable_slaves->arr[usable_slaves->count++] = slave;
}
bond_set_slave_arr(bond, usable_slaves, all_slaves);
return ret;
out:
if (ret != 0 && skipslave) {
bond_skip_slave(rtnl_dereference(bond->all_slaves),
skipslave);
bond_skip_slave(rtnl_dereference(bond->usable_slaves),
skipslave);
}
kfree_rcu(all_slaves, rcu);
kfree_rcu(usable_slaves, rcu);
return ret;
}
static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond,
struct sk_buff *skb,
struct bond_up_slave *slaves)
{
struct slave *slave;
unsigned int count;
u32 hash;
hash = bond_xmit_hash(bond, skb);
count = slaves ? READ_ONCE(slaves->count) : 0;
if (unlikely(!count))
return NULL;
slave = slaves->arr[hash % count];
return slave;
}
static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond,
struct xdp_buff *xdp)
{
struct bond_up_slave *slaves;
unsigned int count;
u32 hash;
hash = bond_xmit_hash_xdp(bond, xdp);
slaves = rcu_dereference(bond->usable_slaves);
count = slaves ? READ_ONCE(slaves->count) : 0;
if (unlikely(!count))
return NULL;
return slaves->arr[hash % count];
}
/* Use this Xmit function for 3AD as well as XOR modes. The current
* usable slave array is formed in the control path. The xmit function
* just calculates hash and sends the packet out.
*/
static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
struct bond_up_slave *slaves;
struct slave *slave;
slaves = rcu_dereference(bond->usable_slaves);
slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves);
if (likely(slave))
return bond_dev_queue_xmit(bond, skb, slave->dev);
return bond_tx_drop(dev, skb);
}
/* in broadcast mode, we send everything to all usable interfaces. */
static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave = NULL;
struct list_head *iter;
bool xmit_suc = false;
bool skb_used = false;
bond_for_each_slave_rcu(bond, slave, iter) {
struct sk_buff *skb2;
if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
continue;
if (bond_is_last_slave(bond, slave)) {
skb2 = skb;
skb_used = true;
} else {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2) {
net_err_ratelimited("%s: Error: %s: skb_clone() failed\n",
bond_dev->name, __func__);
continue;
}
}
if (bond_dev_queue_xmit(bond, skb2, slave->dev) == NETDEV_TX_OK)
xmit_suc = true;
}
if (!skb_used)
dev_kfree_skb_any(skb);
if (xmit_suc)
return NETDEV_TX_OK;
dev_core_stats_tx_dropped_inc(bond_dev);
return NET_XMIT_DROP;
}
/*------------------------- Device initialization ---------------------------*/
/* Lookup the slave that corresponds to a qid */
static inline int bond_slave_override(struct bonding *bond,
struct sk_buff *skb)
{
struct slave *slave = NULL;
struct list_head *iter;
if (!skb_rx_queue_recorded(skb))
return 1;
/* Find out if any slaves have the same mapping as this skb. */
bond_for_each_slave_rcu(bond, slave, iter) {
if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) {
if (bond_slave_is_up(slave) &&
slave->link == BOND_LINK_UP) {
bond_dev_queue_xmit(bond, skb, slave->dev);
return 0;
}
/* If the slave isn't UP, use default transmit policy. */
break;
}
}
return 1;
}
static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
/* This helper function exists to help dev_pick_tx get the correct
* destination queue. Using a helper function skips a call to
* skb_tx_hash and will put the skbs in the queue we expect on their
* way down to the bonding driver.
*/
u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
/* Save the original txq to restore before passing to the driver */
qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb);
if (unlikely(txq >= dev->real_num_tx_queues)) {
do {
txq -= dev->real_num_tx_queues;
} while (txq >= dev->real_num_tx_queues);
}
return txq;
}
static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
struct sk_buff *skb,
bool all_slaves)
{
struct bonding *bond = netdev_priv(master_dev);
struct bond_up_slave *slaves;
struct slave *slave = NULL;
switch (BOND_MODE(bond)) {
case BOND_MODE_ROUNDROBIN:
slave = bond_xmit_roundrobin_slave_get(bond, skb);
break;
case BOND_MODE_ACTIVEBACKUP:
slave = bond_xmit_activebackup_slave_get(bond);
break;
case BOND_MODE_8023AD:
case BOND_MODE_XOR:
if (all_slaves)
slaves = rcu_dereference(bond->all_slaves);
else
slaves = rcu_dereference(bond->usable_slaves);
slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves);
break;
case BOND_MODE_BROADCAST:
break;
case BOND_MODE_ALB:
slave = bond_xmit_alb_slave_get(bond, skb);
break;
case BOND_MODE_TLB:
slave = bond_xmit_tlb_slave_get(bond, skb);
break;
default:
/* Should never happen, mode already checked */
WARN_ONCE(true, "Unknown bonding mode");
break;
}
if (slave)
return slave->dev;
return NULL;
}
static void bond_sk_to_flow(struct sock *sk, struct flow_keys *flow)
{
switch (sk->sk_family) {
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
if (ipv6_only_sock(sk) ||
ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) {
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
flow->addrs.v6addrs.src = inet6_sk(sk)->saddr;
flow->addrs.v6addrs.dst = sk->sk_v6_daddr;
break;
}
fallthrough;
#endif
default: /* AF_INET */
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
flow->addrs.v4addrs.src = inet_sk(sk)->inet_rcv_saddr;
flow->addrs.v4addrs.dst = inet_sk(sk)->inet_daddr;
break;
}
flow->ports.src = inet_sk(sk)->inet_sport;
flow->ports.dst = inet_sk(sk)->inet_dport;
}
/**
* bond_sk_hash_l34 - generate a hash value based on the socket's L3 and L4 fields
* @sk: socket to use for headers
*
* This function will extract the necessary field from the socket and use
* them to generate a hash based on the LAYER34 xmit_policy.
* Assumes that sk is a TCP or UDP socket.
*/
static u32 bond_sk_hash_l34(struct sock *sk)
{
struct flow_keys flow;
u32 hash;
bond_sk_to_flow(sk, &flow);
/* L4 */
memcpy(&hash, &flow.ports.ports, sizeof(hash));
/* L3 */
return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34);
}
static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond,
struct sock *sk)
{
struct bond_up_slave *slaves;
struct slave *slave;
unsigned int count;
u32 hash;
slaves = rcu_dereference(bond->usable_slaves);
count = slaves ? READ_ONCE(slaves->count) : 0;
if (unlikely(!count))
return NULL;
hash = bond_sk_hash_l34(sk);
slave = slaves->arr[hash % count];
return slave->dev;
}
static struct net_device *bond_sk_get_lower_dev(struct net_device *dev,
struct sock *sk)
{
struct bonding *bond = netdev_priv(dev);
struct net_device *lower = NULL;
rcu_read_lock();
if (bond_sk_check(bond))
lower = __bond_sk_get_lower_dev(bond, sk);
rcu_read_unlock();
return lower;
}
#if IS_ENABLED(CONFIG_TLS_DEVICE)
static netdev_tx_t bond_tls_device_xmit(struct bonding *bond, struct sk_buff *skb,
struct net_device *dev)
{
struct net_device *tls_netdev = rcu_dereference(tls_get_ctx(skb->sk)->netdev);
/* tls_netdev might become NULL, even if tls_is_skb_tx_device_offloaded
* was true, if tls_device_down is running in parallel, but it's OK,
* because bond_get_slave_by_dev has a NULL check.
*/
if (likely(bond_get_slave_by_dev(bond, tls_netdev)))
return bond_dev_queue_xmit(bond, skb, tls_netdev);
return bond_tx_drop(dev, skb);
}
#endif
static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
if (bond_should_override_tx_queue(bond) &&
!bond_slave_override(bond, skb))
return NETDEV_TX_OK;
#if IS_ENABLED(CONFIG_TLS_DEVICE)
if (tls_is_skb_tx_device_offloaded(skb))
return bond_tls_device_xmit(bond, skb, dev);
#endif
switch (BOND_MODE(bond)) {
case BOND_MODE_ROUNDROBIN:
return bond_xmit_roundrobin(skb, dev);
case BOND_MODE_ACTIVEBACKUP:
return bond_xmit_activebackup(skb, dev);
case BOND_MODE_8023AD:
case BOND_MODE_XOR:
return bond_3ad_xor_xmit(skb, dev);
case BOND_MODE_BROADCAST:
return bond_xmit_broadcast(skb, dev);
case BOND_MODE_ALB:
return bond_alb_xmit(skb, dev);
case BOND_MODE_TLB:
return bond_tlb_xmit(skb, dev);
default:
/* Should never happen, mode already checked */
netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond));
WARN_ON_ONCE(1);
return bond_tx_drop(dev, skb);
}
}
static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
netdev_tx_t ret = NETDEV_TX_OK;
/* If we risk deadlock from transmitting this in the
* netpoll path, tell netpoll to queue the frame for later tx
*/
if (unlikely(is_netpoll_tx_blocked(dev)))
return NETDEV_TX_BUSY;
rcu_read_lock();
if (bond_has_slaves(bond))
ret = __bond_start_xmit(skb, dev);
else
ret = bond_tx_drop(dev, skb);
rcu_read_unlock();
return ret;
}
static struct net_device *
bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
/* Caller needs to hold rcu_read_lock() */
switch (BOND_MODE(bond)) {
case BOND_MODE_ROUNDROBIN:
slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp);
break;
case BOND_MODE_ACTIVEBACKUP:
slave = bond_xmit_activebackup_slave_get(bond);
break;
case BOND_MODE_8023AD:
case BOND_MODE_XOR:
slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp);
break;
default:
if (net_ratelimit())
netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
BOND_MODE(bond));
return NULL;
}
if (slave)
return slave->dev;
return NULL;
}
static int bond_xdp_xmit(struct net_device *bond_dev,
int n, struct xdp_frame **frames, u32 flags)
{
int nxmit, err = -ENXIO;
rcu_read_lock();
for (nxmit = 0; nxmit < n; nxmit++) {
struct xdp_frame *frame = frames[nxmit];
struct xdp_frame *frames1[] = {frame};
struct net_device *slave_dev;
struct xdp_buff xdp;
xdp_convert_frame_to_buff(frame, &xdp);
slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp);
if (!slave_dev) {
err = -ENXIO;
break;
}
err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags);
if (err < 1)
break;
}
rcu_read_unlock();
/* If error happened on the first frame then we can pass the error up, otherwise
* report the number of frames that were xmitted.
*/
if (err < 0)
return (nxmit == 0 ? err : nxmit);
return nxmit;
}
static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct bonding *bond = netdev_priv(dev);
struct list_head *iter;
struct slave *slave, *rollback_slave;
struct bpf_prog *old_prog;
struct netdev_bpf xdp = {
.command = XDP_SETUP_PROG,
.flags = 0,
.prog = prog,
.extack = extack,
};
int err;
ASSERT_RTNL();
if (!bond_xdp_check(bond, BOND_MODE(bond))) {
BOND_NL_ERR(dev, extack,
"No native XDP support for the current bonding mode");
return -EOPNOTSUPP;
}
old_prog = bond->xdp_prog;
bond->xdp_prog = prog;
bond_for_each_slave(bond, slave, iter) {
struct net_device *slave_dev = slave->dev;
if (!slave_dev->netdev_ops->ndo_bpf ||
!slave_dev->netdev_ops->ndo_xdp_xmit) {
SLAVE_NL_ERR(dev, slave_dev, extack,
"Slave device does not support XDP");
err = -EOPNOTSUPP;
goto err;
}
if (dev_xdp_prog_count(slave_dev) > 0) {
SLAVE_NL_ERR(dev, slave_dev, extack,
"Slave has XDP program loaded, please unload before enslaving");
err = -EOPNOTSUPP;
goto err;
}
err = dev_xdp_propagate(slave_dev, &xdp);
if (err < 0) {
/* ndo_bpf() sets extack error message */
slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
goto err;
}
if (prog)
bpf_prog_inc(prog);
}
if (prog) {
static_branch_inc(&bpf_master_redirect_enabled_key);
} else if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&bpf_master_redirect_enabled_key);
}
return 0;
err:
/* unwind the program changes */
bond->xdp_prog = old_prog;
xdp.prog = old_prog;
xdp.extack = NULL; /* do not overwrite original error */
bond_for_each_slave(bond, rollback_slave, iter) {
struct net_device *slave_dev = rollback_slave->dev;
int err_unwind;
if (slave == rollback_slave)
break;
err_unwind = dev_xdp_propagate(slave_dev, &xdp);
if (err_unwind < 0)
slave_err(dev, slave_dev,
"Error %d when unwinding XDP program change\n", err_unwind);
else if (xdp.prog)
bpf_prog_inc(xdp.prog);
}
return err;
}
static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
return bond_xdp_set(dev, xdp->prog, xdp->extack);
default:
return -EINVAL;
}
}
static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
{
if (speed == 0 || speed == SPEED_UNKNOWN)
speed = slave->speed;
else
speed = min(speed, slave->speed);
return speed;
}
/* Set the BOND_PHC_INDEX flag to notify user space */
static int bond_set_phc_index_flag(struct kernel_hwtstamp_config *kernel_cfg)
{
struct ifreq *ifr = kernel_cfg->ifr;
struct hwtstamp_config cfg;
if (kernel_cfg->copied_to_user) {
/* Lower device has a legacy implementation */
if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
return -EFAULT;
cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX;
if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
return -EFAULT;
} else {
kernel_cfg->flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX;
}
return 0;
}
static int bond_hwtstamp_get(struct net_device *dev,
struct kernel_hwtstamp_config *cfg)
{
struct bonding *bond = netdev_priv(dev);
struct net_device *real_dev;
int err;
real_dev = bond_option_active_slave_get_rcu(bond);
if (!real_dev)
return -EOPNOTSUPP;
err = generic_hwtstamp_get_lower(real_dev, cfg);
if (err)
return err;
return bond_set_phc_index_flag(cfg);
}
static int bond_hwtstamp_set(struct net_device *dev,
struct kernel_hwtstamp_config *cfg,
struct netlink_ext_ack *extack)
{
struct bonding *bond = netdev_priv(dev);
struct net_device *real_dev;
int err;
if (!(cfg->flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX))
return -EOPNOTSUPP;
real_dev = bond_option_active_slave_get_rcu(bond);
if (!real_dev)
return -EOPNOTSUPP;
err = generic_hwtstamp_set_lower(real_dev, cfg, extack);
if (err)
return err;
return bond_set_phc_index_flag(cfg);
}
static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
struct ethtool_link_ksettings *cmd)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
u32 speed = 0;
cmd->base.duplex = DUPLEX_UNKNOWN;
cmd->base.port = PORT_OTHER;
/* Since bond_slave_can_tx returns false for all inactive or down slaves, we
* do not need to check mode. Though link speed might not represent
* the true receive or transmit bandwidth (not all modes are symmetric)
* this is an accurate maximum.
*/
bond_for_each_slave(bond, slave, iter) {
if (bond_slave_can_tx(slave)) {
bond_update_speed_duplex(slave);
if (slave->speed != SPEED_UNKNOWN) {
if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
speed = bond_mode_bcast_speed(slave,
speed);
else
speed += slave->speed;
}
if (cmd->base.duplex == DUPLEX_UNKNOWN &&
slave->duplex != DUPLEX_UNKNOWN)
cmd->base.duplex = slave->duplex;
}
}
cmd->base.speed = speed ? : SPEED_UNKNOWN;
return 0;
}
static void bond_ethtool_get_drvinfo(struct net_device *bond_dev,
struct ethtool_drvinfo *drvinfo)
{
strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d",
BOND_ABI_VERSION);
}
static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
struct kernel_ethtool_ts_info *info)
{
struct bonding *bond = netdev_priv(bond_dev);
struct kernel_ethtool_ts_info ts_info;
struct net_device *real_dev;
bool sw_tx_support = false;
struct list_head *iter;
struct slave *slave;
int ret = 0;
rcu_read_lock();
real_dev = bond_option_active_slave_get_rcu(bond);
dev_hold(real_dev);
rcu_read_unlock();
if (real_dev) {
ret = ethtool_get_ts_info_by_layer(real_dev, info);
} else {
/* Check if all slaves support software tx timestamping */
rcu_read_lock();
bond_for_each_slave_rcu(bond, slave, iter) {
ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info);
if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) {
sw_tx_support = true;
continue;
}
sw_tx_support = false;
break;
}
rcu_read_unlock();
}
if (sw_tx_support)
info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
dev_put(real_dev);
return ret;
}
static const struct ethtool_ops bond_ethtool_ops = {
.get_drvinfo = bond_ethtool_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_link_ksettings = bond_ethtool_get_link_ksettings,
.get_ts_info = bond_ethtool_get_ts_info,
};
static const struct net_device_ops bond_netdev_ops = {
.ndo_init = bond_init,
.ndo_uninit = bond_uninit,
.ndo_open = bond_open,
.ndo_stop = bond_close,
.ndo_start_xmit = bond_start_xmit,
.ndo_select_queue = bond_select_queue,
.ndo_get_stats64 = bond_get_stats,
.ndo_eth_ioctl = bond_eth_ioctl,
.ndo_siocbond = bond_do_ioctl,
.ndo_siocdevprivate = bond_siocdevprivate,
.ndo_change_rx_flags = bond_change_rx_flags,
.ndo_set_rx_mode = bond_set_rx_mode,
.ndo_change_mtu = bond_change_mtu,
.ndo_set_mac_address = bond_set_mac_address,
.ndo_neigh_setup = bond_neigh_setup,
.ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_netpoll_setup = bond_netpoll_setup,
.ndo_netpoll_cleanup = bond_netpoll_cleanup,
.ndo_poll_controller = bond_poll_controller,
#endif
.ndo_add_slave = bond_enslave,
.ndo_del_slave = bond_release,
.ndo_fix_features = bond_fix_features,
.ndo_features_check = passthru_features_check,
.ndo_get_xmit_slave = bond_xmit_get_slave,
.ndo_sk_get_lower_dev = bond_sk_get_lower_dev,
.ndo_bpf = bond_xdp,
.ndo_xdp_xmit = bond_xdp_xmit,
.ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave,
.ndo_hwtstamp_get = bond_hwtstamp_get,
.ndo_hwtstamp_set = bond_hwtstamp_set,
};
static const struct device_type bond_type = {
.name = "bond",
};
static void bond_destructor(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
if (bond->wq)
destroy_workqueue(bond->wq);
free_percpu(bond->rr_tx_counter);
}
void bond_setup(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
spin_lock_init(&bond->mode_lock);
bond->params = bonding_defaults;
/* Initialize pointers */
bond->dev = bond_dev;
/* Initialize the device entry points */
ether_setup(bond_dev);
bond_dev->max_mtu = ETH_MAX_MTU;
bond_dev->netdev_ops = &bond_netdev_ops;
bond_dev->ethtool_ops = &bond_ethtool_ops;
bond_dev->needs_free_netdev = true;
bond_dev->priv_destructor = bond_destructor;
SET_NETDEV_DEVTYPE(bond_dev, &bond_type);
/* Initialize the device options */
bond_dev->flags |= IFF_MASTER;
bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE;
bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
#ifdef CONFIG_XFRM_OFFLOAD
/* set up xfrm device ops (only supported in active-backup right now) */
bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
INIT_LIST_HEAD(&bond->ipsec_list);
mutex_init(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
/* don't acquire bond device's netif_tx_lock when transmitting */
bond_dev->lltx = true;
/* Don't allow bond devices to change network namespaces. */
bond_dev->netns_immutable = true;
/* By default, we declare the bond to be fully
* VLAN hardware accelerated capable. Special
* care is taken in the various xmit functions
* when there are slaves that are not hw accel
* capable
*/
bond_dev->hw_features = BOND_VLAN_FEATURES |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_STAG_RX |
NETIF_F_HW_VLAN_STAG_FILTER;
bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
bond_dev->features |= bond_dev->hw_features;
bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
bond_dev->features |= NETIF_F_GSO_PARTIAL;
#ifdef CONFIG_XFRM_OFFLOAD
bond_dev->hw_features |= BOND_XFRM_FEATURES;
/* Only enable XFRM features if this is an active-backup config */
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
bond_dev->features |= BOND_XFRM_FEATURES;
#endif /* CONFIG_XFRM_OFFLOAD */
}
/* Destroy a bonding device.
* Must be under rtnl_lock when this function is called.
*/
static void bond_uninit(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct list_head *iter;
struct slave *slave;
bond_netpoll_cleanup(bond_dev);
/* Release the bonded slaves */
bond_for_each_slave(bond, slave, iter)
__bond_release_one(bond_dev, slave->dev, true, true);
netdev_info(bond_dev, "Released all slaves\n");
#ifdef CONFIG_XFRM_OFFLOAD
mutex_destroy(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
bond_set_slave_arr(bond, NULL, NULL);
list_del_rcu(&bond->bond_list);
bond_debug_unregister(bond);
}
/*------------------------- Module initialization ---------------------------*/
static int __init bond_check_params(struct bond_params *params)
{
int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
struct bond_opt_value newval;
const struct bond_opt_value *valptr;
int arp_all_targets_value = 0;
u16 ad_actor_sys_prio = 0;
u16 ad_user_port_key = 0;
__be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0 };
int arp_ip_count;
int bond_mode = BOND_MODE_ROUNDROBIN;
int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
int lacp_fast = 0;
int tlb_dynamic_lb;
/* Convert string parameters. */
if (mode) {
bond_opt_initstr(&newval, mode);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval);
if (!valptr) {
pr_err("Error: Invalid bonding mode \"%s\"\n", mode);
return -EINVAL;
}
bond_mode = valptr->value;
}
if (xmit_hash_policy) {
if (bond_mode == BOND_MODE_ROUNDROBIN ||
bond_mode == BOND_MODE_ACTIVEBACKUP ||
bond_mode == BOND_MODE_BROADCAST) {
pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
bond_opt_initstr(&newval, xmit_hash_policy);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH),
&newval);
if (!valptr) {
pr_err("Error: Invalid xmit_hash_policy \"%s\"\n",
xmit_hash_policy);
return -EINVAL;
}
xmit_hashtype = valptr->value;
}
}
if (lacp_rate) {
if (bond_mode != BOND_MODE_8023AD) {
pr_info("lacp_rate param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
bond_opt_initstr(&newval, lacp_rate);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE),
&newval);
if (!valptr) {
pr_err("Error: Invalid lacp rate \"%s\"\n",
lacp_rate);
return -EINVAL;
}
lacp_fast = valptr->value;
}
}
if (ad_select) {
bond_opt_initstr(&newval, ad_select);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT),
&newval);
if (!valptr) {
pr_err("Error: Invalid ad_select \"%s\"\n", ad_select);
return -EINVAL;
}
params->ad_select = valptr->value;
if (bond_mode != BOND_MODE_8023AD)
pr_warn("ad_select param only affects 802.3ad mode\n");
} else {
params->ad_select = BOND_AD_STABLE;
}
if (max_bonds < 0) {
pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS);
max_bonds = BOND_DEFAULT_MAX_BONDS;
}
if (miimon < 0) {
pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n",
miimon, INT_MAX);
miimon = 0;
}
if (updelay < 0) {
pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
updelay, INT_MAX);
updelay = 0;
}
if (downdelay < 0) {
pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
downdelay, INT_MAX);
downdelay = 0;
}
if ((use_carrier != 0) && (use_carrier != 1)) {
pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",
use_carrier);
use_carrier = 1;
}
if (num_peer_notif < 0 || num_peer_notif > 255) {
pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
num_peer_notif);
num_peer_notif = 1;
}
/* reset values for 802.3ad/TLB/ALB */
if (!bond_mode_uses_arp(bond_mode)) {
if (!miimon) {
pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
pr_warn("Forcing miimon to 100msec\n");
miimon = BOND_DEFAULT_MIIMON;
}
}
if (tx_queues < 1 || tx_queues > 255) {
pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n",
tx_queues, BOND_DEFAULT_TX_QUEUES);
tx_queues = BOND_DEFAULT_TX_QUEUES;
}
if ((all_slaves_active != 0) && (all_slaves_active != 1)) {
pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n",
all_slaves_active);
all_slaves_active = 0;
}
if (resend_igmp < 0 || resend_igmp > 255) {
pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n",
resend_igmp, BOND_DEFAULT_RESEND_IGMP);
resend_igmp = BOND_DEFAULT_RESEND_IGMP;
}
bond_opt_initval(&newval, packets_per_slave);
if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) {
pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n",
packets_per_slave, USHRT_MAX);
packets_per_slave = 1;
}
if (bond_mode == BOND_MODE_ALB) {
pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n",
updelay);
}
if (!miimon) {
if (updelay || downdelay) {
/* just warn the user the up/down delay will have
* no effect since miimon is zero...
*/
pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n",
updelay, downdelay);
}
} else {
/* don't allow arp monitoring */
if (arp_interval) {
pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n",
miimon, arp_interval);
arp_interval = 0;
}
if ((updelay % miimon) != 0) {
pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
updelay, miimon, (updelay / miimon) * miimon);
}
updelay /= miimon;
if ((downdelay % miimon) != 0) {
pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n",
downdelay, miimon,
(downdelay / miimon) * miimon);
}
downdelay /= miimon;
}
if (arp_interval < 0) {
pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n",
arp_interval, INT_MAX);
arp_interval = 0;
}
for (arp_ip_count = 0, i = 0;
(arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) {
__be32 ip;
/* not a complete check, but good enough to catch mistakes */
if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) ||
!bond_is_ip_target_ok(ip)) {
pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n",
arp_ip_target[i]);
arp_interval = 0;
} else {
if (bond_get_targets_ip(arp_target, ip) == -1)
arp_target[arp_ip_count++] = ip;
else
pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n",
&ip);
}
}
if (arp_interval && !arp_ip_count) {
/* don't allow arping if no arp_ip_target given... */
pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n",
arp_interval);
arp_interval = 0;
}
if (arp_validate) {
if (!arp_interval) {
pr_err("arp_validate requires arp_interval\n");
return -EINVAL;
}
bond_opt_initstr(&newval, arp_validate);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE),
&newval);
if (!valptr) {
pr_err("Error: invalid arp_validate \"%s\"\n",
arp_validate);
return -EINVAL;
}
arp_validate_value = valptr->value;
} else {
arp_validate_value = 0;
}
if (arp_all_targets) {
bond_opt_initstr(&newval, arp_all_targets);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS),
&newval);
if (!valptr) {
pr_err("Error: invalid arp_all_targets_value \"%s\"\n",
arp_all_targets);
arp_all_targets_value = 0;
} else {
arp_all_targets_value = valptr->value;
}
}
if (miimon) {
pr_info("MII link monitoring set to %d ms\n", miimon);
} else if (arp_interval) {
valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE,
arp_validate_value);
pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):",
arp_interval, valptr->string, arp_ip_count);
for (i = 0; i < arp_ip_count; i++)
pr_cont(" %s", arp_ip_target[i]);
pr_cont("\n");
} else if (max_bonds) {
/* miimon and arp_interval not set, we need one so things
* work as expected, see bonding.txt for details
*/
pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n");
}
if (primary && !bond_mode_uses_primary(bond_mode)) {
/* currently, using a primary only makes sense
* in active backup, TLB or ALB modes
*/
pr_warn("Warning: %s primary device specified but has no effect in %s mode\n",
primary, bond_mode_name(bond_mode));
primary = NULL;
}
if (primary && primary_reselect) {
bond_opt_initstr(&newval, primary_reselect);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT),
&newval);
if (!valptr) {
pr_err("Error: Invalid primary_reselect \"%s\"\n",
primary_reselect);
return -EINVAL;
}
primary_reselect_value = valptr->value;
} else {
primary_reselect_value = BOND_PRI_RESELECT_ALWAYS;
}
if (fail_over_mac) {
bond_opt_initstr(&newval, fail_over_mac);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC),
&newval);
if (!valptr) {
pr_err("Error: invalid fail_over_mac \"%s\"\n",
fail_over_mac);
return -EINVAL;
}
fail_over_mac_value = valptr->value;
if (bond_mode != BOND_MODE_ACTIVEBACKUP)
pr_warn("Warning: fail_over_mac only affects active-backup mode\n");
} else {
fail_over_mac_value = BOND_FOM_NONE;
}
bond_opt_initstr(&newval, "default");
valptr = bond_opt_parse(
bond_opt_get(BOND_OPT_AD_ACTOR_SYS_PRIO),
&newval);
if (!valptr) {
pr_err("Error: No ad_actor_sys_prio default value");
return -EINVAL;
}
ad_actor_sys_prio = valptr->value;
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_USER_PORT_KEY),
&newval);
if (!valptr) {
pr_err("Error: No ad_user_port_key default value");
return -EINVAL;
}
ad_user_port_key = valptr->value;
bond_opt_initstr(&newval, "default");
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval);
if (!valptr) {
pr_err("Error: No tlb_dynamic_lb default value");
return -EINVAL;
}
tlb_dynamic_lb = valptr->value;
if (lp_interval == 0) {
pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
}
/* fill params struct with the proper values */
params->mode = bond_mode;
params->xmit_policy = xmit_hashtype;
params->miimon = miimon;
params->num_peer_notif = num_peer_notif;
params->arp_interval = arp_interval;
params->arp_validate = arp_validate_value;
params->arp_all_targets = arp_all_targets_value;
params->missed_max = 2;
params->updelay = updelay;
params->downdelay = downdelay;
params->peer_notif_delay = 0;
params->use_carrier = use_carrier;
params->lacp_active = 1;
params->lacp_fast = lacp_fast;
params->primary[0] = 0;
params->primary_reselect = primary_reselect_value;
params->fail_over_mac = fail_over_mac_value;
params->tx_queues = tx_queues;
params->all_slaves_active = all_slaves_active;
params->resend_igmp = resend_igmp;
params->min_links = min_links;
params->lp_interval = lp_interval;
params->packets_per_slave = packets_per_slave;
params->tlb_dynamic_lb = tlb_dynamic_lb;
params->ad_actor_sys_prio = ad_actor_sys_prio;
eth_zero_addr(params->ad_actor_system);
params->ad_user_port_key = ad_user_port_key;
params->coupled_control = 1;
if (packets_per_slave > 0) {
params->reciprocal_packets_per_slave =
reciprocal_value(packets_per_slave);
} else {
/* reciprocal_packets_per_slave is unused if
* packets_per_slave is 0 or 1, just initialize it
*/
params->reciprocal_packets_per_slave =
(struct reciprocal_value) { 0 };
}
if (primary)
strscpy_pad(params->primary, primary, sizeof(params->primary));
memcpy(params->arp_targets, arp_target, sizeof(arp_target));
#if IS_ENABLED(CONFIG_IPV6)
memset(params->ns_targets, 0, sizeof(struct in6_addr) * BOND_MAX_NS_TARGETS);
#endif
return 0;
}
/* Called from registration process */
static int bond_init(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
netdev_dbg(bond_dev, "Begin bond_init\n");
bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
bond_dev->name);
if (!bond->wq)
return -ENOMEM;
bond->notifier_ctx = false;
spin_lock_init(&bond->stats_lock);
netdev_lockdep_set_classes(bond_dev);
list_add_tail_rcu(&bond->bond_list, &bn->dev_list);
bond_prepare_sysfs_group(bond);
bond_debug_register(bond);
/* Ensure valid dev_addr */
if (is_zero_ether_addr(bond_dev->dev_addr) &&
bond_dev->addr_assign_type == NET_ADDR_PERM)
eth_hw_addr_random(bond_dev);
return 0;
}
unsigned int bond_get_num_tx_queues(void)
{
return tx_queues;
}
/* Create a new bond based on the specified name and bonding parameters.
* If name is NULL, obtain a suitable "bond%d" name for us.
* Caller must NOT hold rtnl_lock; we need to release it here before we
* set up our sysfs entries.
*/
int bond_create(struct net *net, const char *name)
{
struct net_device *bond_dev;
struct bonding *bond;
int res = -ENOMEM;
rtnl_lock();
bond_dev = alloc_netdev_mq(sizeof(struct bonding),
name ? name : "bond%d", NET_NAME_UNKNOWN,
bond_setup, tx_queues);
if (!bond_dev)
goto out;
bond = netdev_priv(bond_dev);
dev_net_set(bond_dev, net);
bond_dev->rtnl_link_ops = &bond_link_ops;
res = register_netdevice(bond_dev);
if (res < 0) {
free_netdev(bond_dev);
goto out;
}
netif_carrier_off(bond_dev);
bond_work_init_all(bond);
out:
rtnl_unlock();
return res;
}
static int __net_init bond_net_init(struct net *net)
{
struct bond_net *bn = net_generic(net, bond_net_id);
bn->net = net;
INIT_LIST_HEAD(&bn->dev_list);
bond_create_proc_dir(bn);
bond_create_sysfs(bn);
return 0;
}
/* According to commit 69b0216ac255 ("bonding: fix bonding_masters
* race condition in bond unloading") we need to remove sysfs files
* before we remove our devices (done later in bond_net_exit_batch_rtnl())
*/
static void __net_exit bond_net_pre_exit(struct net *net)
{
struct bond_net *bn = net_generic(net, bond_net_id);
bond_destroy_sysfs(bn);
}
static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list,
struct list_head *dev_kill_list)
{
struct bond_net *bn;
struct net *net;
/* Kill off any bonds created after unregistering bond rtnl ops */
list_for_each_entry(net, net_list, exit_list) {
struct bonding *bond, *tmp_bond;
bn = net_generic(net, bond_net_id);
list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
unregister_netdevice_queue(bond->dev, dev_kill_list);
}
}
/* According to commit 23fa5c2caae0 ("bonding: destroy proc directory
* only after all bonds are gone") bond_destroy_proc_dir() is called
* after bond_net_exit_batch_rtnl() has completed.
*/
static void __net_exit bond_net_exit_batch(struct list_head *net_list)
{
struct bond_net *bn;
struct net *net;
list_for_each_entry(net, net_list, exit_list) {
bn = net_generic(net, bond_net_id);
bond_destroy_proc_dir(bn);
}
}
static struct pernet_operations bond_net_ops = {
.init = bond_net_init,
.pre_exit = bond_net_pre_exit,
.exit_batch_rtnl = bond_net_exit_batch_rtnl,
.exit_batch = bond_net_exit_batch,
.id = &bond_net_id,
.size = sizeof(struct bond_net),
};
static int __init bonding_init(void)
{
int i;
int res;
res = bond_check_params(&bonding_defaults);
if (res)
goto out;
bond_create_debugfs();
res = register_pernet_subsys(&bond_net_ops);
if (res)
goto err_net_ops;
res = bond_netlink_init();
if (res)
goto err_link;
for (i = 0; i < max_bonds; i++) {
res = bond_create(&init_net, NULL);
if (res)
goto err;
}
skb_flow_dissector_init(&flow_keys_bonding,
flow_keys_bonding_keys,
ARRAY_SIZE(flow_keys_bonding_keys));
register_netdevice_notifier(&bond_netdev_notifier);
out:
return res;
err:
bond_netlink_fini();
err_link:
unregister_pernet_subsys(&bond_net_ops);
err_net_ops:
bond_destroy_debugfs();
goto out;
}
static void __exit bonding_exit(void)
{
unregister_netdevice_notifier(&bond_netdev_notifier);
bond_netlink_fini();
unregister_pernet_subsys(&bond_net_ops);
bond_destroy_debugfs();
#ifdef CONFIG_NET_POLL_CONTROLLER
/* Make sure we don't have an imbalance on our netpoll blocking */
WARN_ON(atomic_read(&netpoll_block_tx));
#endif
}
module_init(bonding_init);
module_exit(bonding_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION(DRV_DESCRIPTION);
MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PGTABLE_H
#define _LINUX_PGTABLE_H
#include <linux/pfn.h>
#include <asm/pgtable.h>
#define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT)
#define PUD_ORDER (PUD_SHIFT - PAGE_SHIFT)
#ifndef __ASSEMBLY__
#ifdef CONFIG_MMU
#include <linux/mm_types.h>
#include <linux/bug.h>
#include <linux/errno.h>
#include <asm-generic/pgtable_uffd.h>
#include <linux/page_table_check.h>
#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
#endif
/*
* On almost all architectures and configurations, 0 can be used as the
* upper ceiling to free_pgtables(): on many architectures it has the same
* effect as using TASK_SIZE. However, there is one configuration which
* must impose a more careful limit, to avoid freeing kernel pgtables.
*/
#ifndef USER_PGTABLES_CEILING
#define USER_PGTABLES_CEILING 0UL
#endif
/*
* This defines the first usable user address. Platforms
* can override its value with custom FIRST_USER_ADDRESS
* defined in their respective <asm/pgtable.h>.
*/
#ifndef FIRST_USER_ADDRESS
#define FIRST_USER_ADDRESS 0UL
#endif
/*
* This defines the generic helper for accessing PMD page
* table page. Although platforms can still override this
* via their respective <asm/pgtable.h>.
*/
#ifndef pmd_pgtable
#define pmd_pgtable(pmd) pmd_page(pmd)
#endif
#define pmd_folio(pmd) page_folio(pmd_page(pmd))
/*
* A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD]
*
* The pXx_index() functions return the index of the entry in the page
* table page which would control the given virtual address
*
* As these functions may be used by the same code for different levels of
* the page table folding, they are always available, regardless of
* CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0
* because in such cases PTRS_PER_PxD equals 1.
*/
static inline unsigned long pte_index(unsigned long address)
{
return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}
#ifndef pmd_index
static inline unsigned long pmd_index(unsigned long address)
{
return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}
#define pmd_index pmd_index
#endif
#ifndef pud_index
static inline unsigned long pud_index(unsigned long address)
{
return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
#define pud_index pud_index
#endif
#ifndef pgd_index
/* Must be a compile-time constant, so implement it as a macro */
#define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
#endif
#ifndef kernel_pte_init
static inline void kernel_pte_init(void *addr)
{
}
#define kernel_pte_init kernel_pte_init
#endif
#ifndef pmd_init
static inline void pmd_init(void *addr)
{
}
#define pmd_init pmd_init
#endif
#ifndef pud_init
static inline void pud_init(void *addr)
{
}
#define pud_init pud_init
#endif
#ifndef pte_offset_kernel
static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}
#define pte_offset_kernel pte_offset_kernel
#endif
#ifdef CONFIG_HIGHPTE
#define __pte_map(pmd, address) \
((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address)))
#define pte_unmap(pte) do { \
kunmap_local((pte)); \
rcu_read_unlock(); \
} while (0)
#else
static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address)
{
return pte_offset_kernel(pmd, address);
}
static inline void pte_unmap(pte_t *pte)
{ rcu_read_unlock();
}
#endif
void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
/* Find an entry in the second-level page table.. */
#ifndef pmd_offset
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
return pud_pgtable(*pud) + pmd_index(address);
}
#define pmd_offset pmd_offset
#endif
#ifndef pud_offset
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
return p4d_pgtable(*p4d) + pud_index(address);
}
#define pud_offset pud_offset
#endif
static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address)
{
return (pgd + pgd_index(address));
};
/*
* a shortcut to get a pgd_t in a given mm
*/
#ifndef pgd_offset
#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
#endif
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
*/
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
/*
* In many cases it is known that a virtual address is mapped at PMD or PTE
* level, so instead of traversing all the page table levels, we can get a
* pointer to the PMD entry in user or kernel page table or translate a virtual
* address to the pointer in the PTE in the kernel page tables with simple
* helpers.
*/
static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va)
{
return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va);
}
static inline pmd_t *pmd_off_k(unsigned long va)
{
return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va);
}
static inline pte_t *virt_to_kpte(unsigned long vaddr)
{
pmd_t *pmd = pmd_off_k(vaddr);
return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
}
#ifndef pmd_young
static inline int pmd_young(pmd_t pmd)
{
return 0;
}
#endif
#ifndef pmd_dirty
static inline int pmd_dirty(pmd_t pmd)
{
return 0;
}
#endif
/*
* A facility to provide lazy MMU batching. This allows PTE updates and
* page invalidations to be delayed until a call to leave lazy MMU mode
* is issued. Some architectures may benefit from doing this, and it is
* beneficial for both shadow and direct mode hypervisors, which may batch
* the PTE updates which happen during this window. Note that using this
* interface requires that read hazards be removed from the code. A read
* hazard could result in the direct mode hypervisor case, since the actual
* write to the page tables may not yet have taken place, so reads though
* a raw PTE pointer after it has been modified are not guaranteed to be
* up to date.
*
* In the general case, no lock is guaranteed to be held between entry and exit
* of the lazy mode. So the implementation must assume preemption may be enabled
* and cpu migration is possible; it must take steps to be robust against this.
* (In practice, for user PTE updates, the appropriate page table lock(s) are
* held, but for kernel PTE updates, no lock is held). Nesting is not permitted
* and the mode cannot be used in interrupt context.
*/
#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
#define arch_enter_lazy_mmu_mode() do {} while (0)
#define arch_leave_lazy_mmu_mode() do {} while (0)
#define arch_flush_lazy_mmu_mode() do {} while (0)
#endif
#ifndef pte_batch_hint
/**
* pte_batch_hint - Number of pages that can be added to batch without scanning.
* @ptep: Page table pointer for the entry.
* @pte: Page table entry.
*
* Some architectures know that a set of contiguous ptes all map the same
* contiguous memory with the same permissions. In this case, it can provide a
* hint to aid pte batching without the core code needing to scan every pte.
*
* An architecture implementation may ignore the PTE accessed state. Further,
* the dirty state must apply atomically to all the PTEs described by the hint.
*
* May be overridden by the architecture, else pte_batch_hint is always 1.
*/
static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte)
{
return 1;
}
#endif
#ifndef pte_advance_pfn
static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
{
return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT));
}
#endif
#define pte_next_pfn(pte) pte_advance_pfn(pte, 1)
#ifndef set_ptes
/**
* set_ptes - Map consecutive pages to a contiguous range of addresses.
* @mm: Address space to map the pages into.
* @addr: Address to map the first page at.
* @ptep: Page table pointer for the first entry.
* @pte: Page table entry for the first page.
* @nr: Number of pages to map.
*
* When nr==1, initial state of pte may be present or not present, and new state
* may be present or not present. When nr>1, initial state of all ptes must be
* not present, and new state must be present.
*
* May be overridden by the architecture, or the architecture can define
* set_pte() and PFN_PTE_SHIFT.
*
* Context: The caller holds the page table lock. The pages all belong
* to the same folio. The PTEs are all in the same PMD.
*/
static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, unsigned int nr)
{
page_table_check_ptes_set(mm, ptep, pte, nr);
for (;;) {
set_pte(ptep, pte);
if (--nr == 0)
break;
ptep++;
pte = pte_next_pfn(pte);
}
}
#endif
#define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1)
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty);
#endif
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
extern int pudp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
pud_t entry, int dirty);
#else
static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty)
{
BUILD_BUG();
return 0;
}
static inline int pudp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
pud_t entry, int dirty)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef ptep_get
static inline pte_t ptep_get(pte_t *ptep)
{
return READ_ONCE(*ptep);
}
#endif
#ifndef pmdp_get
static inline pmd_t pmdp_get(pmd_t *pmdp)
{
return READ_ONCE(*pmdp);
}
#endif
#ifndef pudp_get
static inline pud_t pudp_get(pud_t *pudp)
{
return READ_ONCE(*pudp);
}
#endif
#ifndef p4dp_get
static inline p4d_t p4dp_get(p4d_t *p4dp)
{
return READ_ONCE(*p4dp);
}
#endif
#ifndef pgdp_get
static inline pgd_t pgdp_get(pgd_t *pgdp)
{
return READ_ONCE(*pgdp);
}
#endif
#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pte_t *ptep)
{
pte_t pte = ptep_get(ptep);
int r = 1;
if (!pte_young(pte))
r = 0;
else
set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
return r;
}
#endif
#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd = *pmdp;
int r = 1;
if (!pmd_young(pmd))
r = 0;
else
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
return r;
}
#else
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep);
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#else
/*
* Despite relevant to THP only, this API is called from generic rmap code
* under PageTransHuge(), hence needs a dummy implementation for !THP
*/
static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
BUILD_BUG();
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef arch_has_hw_nonleaf_pmd_young
/*
* Return whether the accessed bit in non-leaf PMD entries is supported on the
* local CPU.
*/
static inline bool arch_has_hw_nonleaf_pmd_young(void)
{
return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
}
#endif
#ifndef arch_has_hw_pte_young
/*
* Return whether the accessed bit is supported on the local CPU.
*
* This stub assumes accessing through an old PTE triggers a page fault.
* Architectures that automatically set the access bit should overwrite it.
*/
static inline bool arch_has_hw_pte_young(void)
{
return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG);
}
#endif
#ifndef arch_check_zapped_pte
static inline void arch_check_zapped_pte(struct vm_area_struct *vma,
pte_t pte)
{
}
#endif
#ifndef arch_check_zapped_pmd
static inline void arch_check_zapped_pmd(struct vm_area_struct *vma,
pmd_t pmd)
{
}
#endif
#ifndef arch_check_zapped_pud
static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud)
{
}
#endif
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address,
pte_t *ptep)
{
pte_t pte = ptep_get(ptep);
pte_clear(mm, address, ptep);
page_table_check_pte_clear(mm, pte);
return pte;
}
#endif
#ifndef clear_young_dirty_ptes
/**
* clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the
* same folio as old/clean.
* @mm: Address space the pages are mapped into.
* @addr: Address the first page is mapped at.
* @ptep: Page table pointer for the first entry.
* @nr: Number of entries to mark old/clean.
* @flags: Flags to modify the PTE batch semantics.
*
* May be overridden by the architecture; otherwise, implemented by
* get_and_clear/modify/set for each pte in the range.
*
* Note that PTE bits in the PTE range besides the PFN can differ. For example,
* some PTEs might be write-protected.
*
* Context: The caller holds the page table lock. The PTEs map consecutive
* pages that belong to the same folio. The PTEs are all in the same PMD.
*/
static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
unsigned int nr, cydp_t flags)
{
pte_t pte;
for (;;) {
if (flags == CYDP_CLEAR_YOUNG)
ptep_test_and_clear_young(vma, addr, ptep);
else {
pte = ptep_get_and_clear(vma->vm_mm, addr, ptep);
if (flags & CYDP_CLEAR_YOUNG)
pte = pte_mkold(pte);
if (flags & CYDP_CLEAR_DIRTY)
pte = pte_mkclean(pte);
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
if (--nr == 0)
break;
ptep++;
addr += PAGE_SIZE;
}
}
#endif
static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
pte_t pte = ptep_get(ptep);
pte_clear(mm, addr, ptep);
/*
* No need for ptep_get_and_clear(): page table check doesn't care about
* any bits that could have been set by HW concurrently.
*/
page_table_check_pte_clear(mm, pte);
}
#ifdef CONFIG_GUP_GET_PXX_LOW_HIGH
/*
* For walking the pagetables without holding any locks. Some architectures
* (eg x86-32 PAE) cannot load the entries atomically without using expensive
* instructions. We are guaranteed that a PTE will only either go from not
* present to present, or present to not present -- it will not switch to a
* completely different present page without a TLB flush inbetween; which we
* are blocking by holding interrupts off.
*
* Setting ptes from not present to present goes:
*
* ptep->pte_high = h;
* smp_wmb();
* ptep->pte_low = l;
*
* And present to not present goes:
*
* ptep->pte_low = 0;
* smp_wmb();
* ptep->pte_high = 0;
*
* We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
* We load pte_high *after* loading pte_low, which ensures we don't see an older
* value of pte_high. *Then* we recheck pte_low, which ensures that we haven't
* picked up a changed pte high. We might have gotten rubbish values from
* pte_low and pte_high, but we are guaranteed that pte_low will not have the
* present bit set *unless* it is 'l'. Because get_user_pages_fast() only
* operates on present ptes we're safe.
*/
static inline pte_t ptep_get_lockless(pte_t *ptep)
{
pte_t pte;
do {
pte.pte_low = ptep->pte_low;
smp_rmb();
pte.pte_high = ptep->pte_high;
smp_rmb();
} while (unlikely(pte.pte_low != ptep->pte_low));
return pte;
}
#define ptep_get_lockless ptep_get_lockless
#if CONFIG_PGTABLE_LEVELS > 2
static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
{
pmd_t pmd;
do {
pmd.pmd_low = pmdp->pmd_low;
smp_rmb();
pmd.pmd_high = pmdp->pmd_high;
smp_rmb();
} while (unlikely(pmd.pmd_low != pmdp->pmd_low));
return pmd;
}
#define pmdp_get_lockless pmdp_get_lockless
#define pmdp_get_lockless_sync() tlb_remove_table_sync_one()
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */
/*
* We require that the PTE can be read atomically.
*/
#ifndef ptep_get_lockless
static inline pte_t ptep_get_lockless(pte_t *ptep)
{
return ptep_get(ptep);
}
#endif
#ifndef pmdp_get_lockless
static inline pmd_t pmdp_get_lockless(pmd_t *pmdp)
{
return pmdp_get(pmdp);
}
static inline void pmdp_get_lockless_sync(void)
{
}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd = *pmdp;
pmd_clear(pmdp);
page_table_check_pmd_clear(mm, pmd);
return pmd;
}
#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address,
pud_t *pudp)
{
pud_t pud = *pudp;
pud_clear(pudp);
page_table_check_pud_clear(mm, pud);
return pud;
}
#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
int full)
{
return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
}
#endif
#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
int full)
{
return pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long address, pte_t *ptep,
int full)
{
return ptep_get_and_clear(mm, address, ptep);
}
#endif
#ifndef get_and_clear_full_ptes
/**
* get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of
* the same folio, collecting dirty/accessed bits.
* @mm: Address space the pages are mapped into.
* @addr: Address the first page is mapped at.
* @ptep: Page table pointer for the first entry.
* @nr: Number of entries to clear.
* @full: Whether we are clearing a full mm.
*
* May be overridden by the architecture; otherwise, implemented as a simple
* loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the
* returned PTE.
*
* Note that PTE bits in the PTE range besides the PFN can differ. For example,
* some PTEs might be write-protected.
*
* Context: The caller holds the page table lock. The PTEs map consecutive
* pages that belong to the same folio. The PTEs are all in the same PMD.
*/
static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm,
unsigned long addr, pte_t *ptep, unsigned int nr, int full)
{
pte_t pte, tmp_pte;
pte = ptep_get_and_clear_full(mm, addr, ptep, full);
while (--nr) {
ptep++;
addr += PAGE_SIZE;
tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full);
if (pte_dirty(tmp_pte))
pte = pte_mkdirty(pte);
if (pte_young(tmp_pte))
pte = pte_mkyoung(pte);
}
return pte;
}
#endif
#ifndef clear_full_ptes
/**
* clear_full_ptes - Clear present PTEs that map consecutive pages of the same
* folio.
* @mm: Address space the pages are mapped into.
* @addr: Address the first page is mapped at.
* @ptep: Page table pointer for the first entry.
* @nr: Number of entries to clear.
* @full: Whether we are clearing a full mm.
*
* May be overridden by the architecture; otherwise, implemented as a simple
* loop over ptep_get_and_clear_full().
*
* Note that PTE bits in the PTE range besides the PFN can differ. For example,
* some PTEs might be write-protected.
*
* Context: The caller holds the page table lock. The PTEs map consecutive
* pages that belong to the same folio. The PTEs are all in the same PMD.
*/
static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr, int full)
{
for (;;) {
ptep_get_and_clear_full(mm, addr, ptep, full);
if (--nr == 0)
break;
ptep++;
addr += PAGE_SIZE;
}
}
#endif
/*
* If two threads concurrently fault at the same page, the thread that
* won the race updates the PTE and its local TLB/Cache. The other thread
* gives up, simply does nothing, and continues; on architectures where
* software can update TLB, local TLB can be updated here to avoid next page
* fault. This function updates TLB only, do nothing with cache or others.
* It is the difference with function update_mmu_cache.
*/
#ifndef update_mmu_tlb_range
static inline void update_mmu_tlb_range(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, unsigned int nr)
{
}
#endif
static inline void update_mmu_tlb(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
update_mmu_tlb_range(vma, address, ptep, 1);
}
/*
* Some architectures may be able to avoid expensive synchronization
* primitives when modifications are made to PTE's which are already
* not present, or in the process of an address space destruction.
*/
#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
static inline void pte_clear_not_present_full(struct mm_struct *mm,
unsigned long address,
pte_t *ptep,
int full)
{
pte_clear(mm, address, ptep);
}
#endif
#ifndef clear_not_present_full_ptes
/**
* clear_not_present_full_ptes - Clear multiple not present PTEs which are
* consecutive in the pgtable.
* @mm: Address space the ptes represent.
* @addr: Address of the first pte.
* @ptep: Page table pointer for the first entry.
* @nr: Number of entries to clear.
* @full: Whether we are clearing a full mm.
*
* May be overridden by the architecture; otherwise, implemented as a simple
* loop over pte_clear_not_present_full().
*
* Context: The caller holds the page table lock. The PTEs are all not present.
* The PTEs are all in the same PMD.
*/
static inline void clear_not_present_full_ptes(struct mm_struct *mm,
unsigned long addr, pte_t *ptep, unsigned int nr, int full)
{
for (;;) {
pte_clear_not_present_full(mm, addr, ptep, full); if (--nr == 0)
break;
ptep++;
addr += PAGE_SIZE;
}
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pte_t *ptep);
#endif
#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp);
extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
unsigned long address,
pud_t *pudp);
#endif
#ifndef pte_mkwrite
static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
return pte_mkwrite_novma(pte);
}
#endif
#if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite)
static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
return pmd_mkwrite_novma(pmd);
}
#endif
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
struct mm_struct;
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
pte_t old_pte = ptep_get(ptep);
set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
}
#endif
#ifndef wrprotect_ptes
/**
* wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same
* folio.
* @mm: Address space the pages are mapped into.
* @addr: Address the first page is mapped at.
* @ptep: Page table pointer for the first entry.
* @nr: Number of entries to write-protect.
*
* May be overridden by the architecture; otherwise, implemented as a simple
* loop over ptep_set_wrprotect().
*
* Note that PTE bits in the PTE range besides the PFN can differ. For example,
* some PTEs might be write-protected.
*
* Context: The caller holds the page table lock. The PTEs map consecutive
* pages that belong to the same folio. The PTEs are all in the same PMD.
*/
static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr)
{
for (;;) {
ptep_set_wrprotect(mm, addr, ptep);
if (--nr == 0)
break;
ptep++;
addr += PAGE_SIZE;
}
}
#endif
/*
* On some architectures hardware does not set page access bit when accessing
* memory page, it is responsibility of software setting this bit. It brings
* out extra page fault penalty to track page access bit. For optimization page
* access bit can be set during all page fault flow on these arches.
* To be differentiate with macro pte_mkyoung, this macro is used on platforms
* where software maintains page access bit.
*/
#ifndef pte_sw_mkyoung
static inline pte_t pte_sw_mkyoung(pte_t pte)
{
return pte;
}
#define pte_sw_mkyoung pte_sw_mkyoung
#endif
#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
pmd_t old_pmd = *pmdp;
set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
}
#else
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void pudp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pud_t *pudp)
{
pud_t old_pud = *pudp;
set_pud_at(mm, address, pudp, pud_wrprotect(old_pud));
}
#else
static inline void pudp_set_wrprotect(struct mm_struct *mm,
unsigned long address, pud_t *pudp)
{
BUILD_BUG();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#endif
#ifndef pmdp_collapse_flush
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#else
static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
BUILD_BUG();
return *pmdp;
}
#define pmdp_collapse_flush pmdp_collapse_flush
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable);
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#endif
#ifndef arch_needs_pgtable_deposit
#define arch_needs_pgtable_deposit() (false)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* This is an implementation of pmdp_establish() that is only suitable for an
* architecture that doesn't have hardware dirty/accessed bits. In this case we
* can't race with CPU which sets these bits and non-atomic approach is fine.
*/
static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
pmd_t old_pmd = *pmdp;
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
return old_pmd;
}
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
/*
* pmdp_invalidate_ad() invalidates the PMD while changing a transparent
* hugepage mapping in the page tables. This function is similar to
* pmdp_invalidate(), but should only be used if the access and dirty bits would
* not be cleared by the software in the new PMD value. The function ensures
* that hardware changes of the access and dirty bits updates would not be lost.
*
* Doing so can allow in certain architectures to avoid a TLB flush in most
* cases. Yet, another TLB flush might be necessary later if the PMD update
* itself requires such flush (e.g., if protection was set to be stricter). Yet,
* even when a TLB flush is needed because of the update, the caller may be able
* to batch these TLB flushing operations, so fewer TLB flush operations are
* needed.
*/
extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#endif
#ifndef __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
return pte_val(pte_a) == pte_val(pte_b);
}
#endif
#ifndef __HAVE_ARCH_PTE_UNUSED
/*
* Some architectures provide facilities to virtualization guests
* so that they can flag allocated pages as unused. This allows the
* host to transparently reclaim unused pages. This function returns
* whether the pte's page is unused.
*/
static inline int pte_unused(pte_t pte)
{
return 0;
}
#endif
#ifndef pte_access_permitted
#define pte_access_permitted(pte, write) \
(pte_present(pte) && (!(write) || pte_write(pte)))
#endif
#ifndef pmd_access_permitted
#define pmd_access_permitted(pmd, write) \
(pmd_present(pmd) && (!(write) || pmd_write(pmd)))
#endif
#ifndef pud_access_permitted
#define pud_access_permitted(pud, write) \
(pud_present(pud) && (!(write) || pud_write(pud)))
#endif
#ifndef p4d_access_permitted
#define p4d_access_permitted(p4d, write) \
(p4d_present(p4d) && (!(write) || p4d_write(p4d)))
#endif
#ifndef pgd_access_permitted
#define pgd_access_permitted(pgd, write) \
(pgd_present(pgd) && (!(write) || pgd_write(pgd)))
#endif
#ifndef __HAVE_ARCH_PMD_SAME
static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
{
return pmd_val(pmd_a) == pmd_val(pmd_b);
}
#endif
#ifndef pud_same
static inline int pud_same(pud_t pud_a, pud_t pud_b)
{
return pud_val(pud_a) == pud_val(pud_b);
}
#define pud_same pud_same
#endif
#ifndef __HAVE_ARCH_P4D_SAME
static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b)
{
return p4d_val(p4d_a) == p4d_val(p4d_b);
}
#endif
#ifndef __HAVE_ARCH_PGD_SAME
static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b)
{
return pgd_val(pgd_a) == pgd_val(pgd_b);
}
#endif
#ifndef __HAVE_ARCH_DO_SWAP_PAGE
static inline void arch_do_swap_page_nr(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
pte_t pte, pte_t oldpte,
int nr)
{
}
#else
/*
* Some architectures support metadata associated with a page. When a
* page is being swapped out, this metadata must be saved so it can be
* restored when the page is swapped back in. SPARC M7 and newer
* processors support an ADI (Application Data Integrity) tag for the
* page as metadata for the page. arch_do_swap_page() can restore this
* metadata when a page is swapped back in.
*/
static inline void arch_do_swap_page_nr(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
pte_t pte, pte_t oldpte,
int nr)
{
for (int i = 0; i < nr; i++) {
arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE,
pte_advance_pfn(pte, i),
pte_advance_pfn(oldpte, i));
}
}
#endif
#ifndef __HAVE_ARCH_UNMAP_ONE
/*
* Some architectures support metadata associated with a page. When a
* page is being swapped out, this metadata must be saved so it can be
* restored when the page is swapped back in. SPARC M7 and newer
* processors support an ADI (Application Data Integrity) tag for the
* page as metadata for the page. arch_unmap_one() can save this
* metadata on a swap-out of a page.
*/
static inline int arch_unmap_one(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
pte_t orig_pte)
{
return 0;
}
#endif
/*
* Allow architectures to preserve additional metadata associated with
* swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function
* prototypes must be defined in the arch-specific asm/pgtable.h file.
*/
#ifndef __HAVE_ARCH_PREPARE_TO_SWAP
static inline int arch_prepare_to_swap(struct folio *folio)
{
return 0;
}
#endif
#ifndef __HAVE_ARCH_SWAP_INVALIDATE
static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
{
}
static inline void arch_swap_invalidate_area(int type)
{
}
#endif
#ifndef __HAVE_ARCH_SWAP_RESTORE
static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
{
}
#endif
#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr)
#endif
#ifndef __HAVE_ARCH_MOVE_PTE
#define move_pte(pte, old_addr, new_addr) (pte)
#endif
#ifndef pte_accessible
# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address)
#endif
/*
* When walking page tables, get the address of the next boundary,
* or the end address of the range if that comes earlier. Although no
* vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
*/
#define pgd_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#ifndef p4d_addr_end
#define p4d_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
#ifndef pud_addr_end
#define pud_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
#ifndef pmd_addr_end
#define pmd_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
#endif
/*
* When walking page tables, we usually want to skip any p?d_none entries;
* and any p?d_bad entries - reporting the error before resetting to none.
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
*/
void pgd_clear_bad(pgd_t *);
#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *);
#else
#define p4d_clear_bad(p4d) do { } while (0)
#endif
#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *);
#else
#define pud_clear_bad(p4d) do { } while (0)
#endif
void pmd_clear_bad(pmd_t *);
static inline int pgd_none_or_clear_bad(pgd_t *pgd)
{
if (pgd_none(*pgd))
return 1;
if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd);
return 1;
}
return 0;
}
static inline int p4d_none_or_clear_bad(p4d_t *p4d)
{
if (p4d_none(*p4d))
return 1;
if (unlikely(p4d_bad(*p4d))) {
p4d_clear_bad(p4d);
return 1;
}
return 0;
}
static inline int pud_none_or_clear_bad(pud_t *pud)
{
if (pud_none(*pud))
return 1;
if (unlikely(pud_bad(*pud))) {
pud_clear_bad(pud);
return 1;
}
return 0;
}
static inline int pmd_none_or_clear_bad(pmd_t *pmd)
{
if (pmd_none(*pmd))
return 1;
if (unlikely(pmd_bad(*pmd))) {
pmd_clear_bad(pmd);
return 1;
}
return 0;
}
static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
/*
* Get the current pte state, but zero it out to make it
* non-present, preventing the hardware from asynchronously
* updating it.
*/
return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t pte)
{
/*
* The pte is non-present, so there's no hardware state to
* preserve.
*/
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
/*
* Start a pte protection read-modify-write transaction, which
* protects against asynchronous hardware modifications to the pte.
* The intention is not to prevent the hardware from making pte
* updates, but to prevent any updates it may make from being lost.
*
* This does not protect against other software modifications of the
* pte; the appropriate pte lock must be held over the transaction.
*
* Note that this interface is intended to be batchable, meaning that
* ptep_modify_prot_commit may not actually update the pte, but merely
* queue the update to be done at some later time. The update must be
* actually committed before the pte lock is released, however.
*/
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
return __ptep_modify_prot_start(vma, addr, ptep);
}
/*
* Commit an update to a pte, leaving any hardware-controlled bits in
* the PTE unmodified.
*/
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
__ptep_modify_prot_commit(vma, addr, ptep, pte);
}
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
#endif /* CONFIG_MMU */
/*
* No-op macros that just return the current protection value. Defined here
* because these macros can be used even if CONFIG_MMU is not defined.
*/
#ifndef pgprot_nx
#define pgprot_nx(prot) (prot)
#endif
#ifndef pgprot_noncached
#define pgprot_noncached(prot) (prot)
#endif
#ifndef pgprot_writecombine
#define pgprot_writecombine pgprot_noncached
#endif
#ifndef pgprot_writethrough
#define pgprot_writethrough pgprot_noncached
#endif
#ifndef pgprot_device
#define pgprot_device pgprot_noncached
#endif
#ifndef pgprot_mhp
#define pgprot_mhp(prot) (prot)
#endif
#ifdef CONFIG_MMU
#ifndef pgprot_modify
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
newprot = pgprot_noncached(newprot);
if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
newprot = pgprot_writecombine(newprot);
if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
newprot = pgprot_device(newprot);
return newprot;
}
#endif
#endif /* CONFIG_MMU */
#ifndef pgprot_encrypted
#define pgprot_encrypted(prot) (prot)
#endif
#ifndef pgprot_decrypted
#define pgprot_decrypted(prot) (prot)
#endif
/*
* A facility to provide batching of the reload of page tables and
* other process state with the actual context switch code for
* paravirtualized guests. By convention, only one of the batched
* update (lazy) modes (CPU, MMU) should be active at any given time,
* entry should never be nested, and entry and exits should always be
* paired. This is for sanity of maintaining and reasoning about the
* kernel code. In this case, the exit (end of the context switch) is
* in architecture-specific code, and so doesn't need a generic
* definition.
*/
#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
#define arch_start_context_switch(prev) do {} while (0)
#endif
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
#endif
#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */
static inline int pte_soft_dirty(pte_t pte)
{
return 0;
}
static inline int pmd_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
return pte;
}
static inline int pte_swp_soft_dirty(pte_t pte)
{
return 0;
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
return pte;
}
static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
{
return pmd;
}
static inline int pmd_swp_soft_dirty(pmd_t pmd)
{
return 0;
}
static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
{
return pmd;
}
#endif
#ifndef __HAVE_PFNMAP_TRACKING
/*
* Interfaces that can be used by architecture code to keep track of
* memory type of pfn mappings specified by the remap_pfn_range,
* vmf_insert_pfn.
*/
/*
* track_pfn_remap is called when a _new_ pfn mapping is being established
* by remap_pfn_range() for physical range indicated by pfn and size.
*/
static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr,
unsigned long size)
{
return 0;
}
/*
* track_pfn_insert is called when a _new_ single pfn is established
* by vmf_insert_pfn().
*/
static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
pfn_t pfn)
{
}
/*
* track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page
* tables copied during copy_page_range(). Will store the pfn to be
* passed to untrack_pfn_copy() only if there is something to be untracked.
* Callers should initialize the pfn to 0.
*/
static inline int track_pfn_copy(struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, unsigned long *pfn)
{
return 0;
}
/*
* untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during
* copy_page_range(), but after track_pfn_copy() was already called. Can
* be called even if track_pfn_copy() did not actually track anything:
* handled internally.
*/
static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma,
unsigned long pfn)
{
}
/*
* untrack_pfn is called while unmapping a pfnmap for a region.
* untrack can be called for a specific region indicated by pfn and size or
* can be for the entire vma (in which case pfn, size are zero).
*/
static inline void untrack_pfn(struct vm_area_struct *vma,
unsigned long pfn, unsigned long size,
bool mm_wr_locked)
{
}
/*
* untrack_pfn_clear is called in the following cases on a VM_PFNMAP VMA:
*
* 1) During mremap() on the src VMA after the page tables were moved.
* 2) During fork() on the dst VMA, immediately after duplicating the src VMA.
*/
static inline void untrack_pfn_clear(struct vm_area_struct *vma)
{
}
#else
extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr,
unsigned long size);
extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
pfn_t pfn);
extern int track_pfn_copy(struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, unsigned long *pfn);
extern void untrack_pfn_copy(struct vm_area_struct *dst_vma,
unsigned long pfn);
extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size, bool mm_wr_locked);
extern void untrack_pfn_clear(struct vm_area_struct *vma);
#endif
#ifdef CONFIG_MMU
#ifdef __HAVE_COLOR_ZERO_PAGE
static inline int is_zero_pfn(unsigned long pfn)
{
extern unsigned long zero_pfn;
unsigned long offset_from_zero_pfn = pfn - zero_pfn;
return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
}
#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr))
#else
static inline int is_zero_pfn(unsigned long pfn)
{
extern unsigned long zero_pfn;
return pfn == zero_pfn;
}
static inline unsigned long my_zero_pfn(unsigned long addr)
{
extern unsigned long zero_pfn;
return zero_pfn;
}
#endif
#else
static inline int is_zero_pfn(unsigned long pfn)
{
return 0;
}
static inline unsigned long my_zero_pfn(unsigned long addr)
{
return 0;
}
#endif /* CONFIG_MMU */
#ifdef CONFIG_MMU
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_huge(pmd_t pmd)
{
return 0;
}
#ifndef pmd_write
static inline int pmd_write(pmd_t pmd)
{
BUG();
return 0;
}
#endif /* pmd_write */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifndef pud_write
static inline int pud_write(pud_t pud)
{
BUG();
return 0;
}
#endif /* pud_write */
#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline int pmd_devmap(pmd_t pmd)
{
return 0;
}
static inline int pud_devmap(pud_t pud)
{
return 0;
}
static inline int pgd_devmap(pgd_t pgd)
{
return 0;
}
#endif
#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline int pud_trans_huge(pud_t pud)
{
return 0;
}
#endif
static inline int pud_trans_unstable(pud_t *pud)
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
pud_t pudval = READ_ONCE(*pud);
if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
return 1;
if (unlikely(pud_bad(pudval))) {
pud_clear_bad(pud);
return 1;
}
#endif
return 0;
}
#ifndef CONFIG_NUMA_BALANCING
/*
* In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is
* perfectly valid to indicate "no" in that case, which is why our default
* implementation defaults to "always no".
*
* In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE
* page protection due to NUMA hinting. NUMA hinting faults only apply in
* accessible VMAs.
*
* So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault,
* looking at the VMA accessibility is sufficient.
*/
static inline int pte_protnone(pte_t pte)
{
return 0;
}
static inline int pmd_protnone(pmd_t pmd)
{
return 0;
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_MMU */
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
#ifndef __PAGETABLE_P4D_FOLDED
int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
void p4d_clear_huge(p4d_t *p4d);
#else
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline void p4d_clear_huge(p4d_t *p4d) { }
#endif /* !__PAGETABLE_P4D_FOLDED */
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
int pud_free_pmd_page(pud_t *pud, unsigned long addr);
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
static inline void p4d_clear_huge(p4d_t *p4d) { }
static inline int pud_clear_huge(pud_t *pud)
{
return 0;
}
static inline int pmd_clear_huge(pmd_t *pmd)
{
return 0;
}
static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
{
return 0;
}
static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
return 0;
}
static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
return 0;
}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* ARCHes with special requirements for evicting THP backing TLB entries can
* implement this. Otherwise also, it can help optimize normal TLB flush in
* THP regime. Stock flush_tlb_range() typically has optimization to nuke the
* entire TLB if flush span is greater than a threshold, which will
* likely be true for a single huge page. Thus a single THP flush will
* invalidate the entire TLB which is not desirable.
* e.g. see arch/arc: flush_pmd_tlb_range
*/
#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
#else
#define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG()
#define flush_pud_tlb_range(vma, addr, end) BUILD_BUG()
#endif
#endif
struct file;
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot);
#ifndef CONFIG_X86_ESPFIX64
static inline void init_espfix_bsp(void) { }
#endif
extern void __init pgtable_cache_init(void);
#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
{
return true;
}
static inline bool arch_has_pfn_modify_check(void)
{
return false;
}
#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
/*
* Architecture PAGE_KERNEL_* fallbacks
*
* Some architectures don't define certain PAGE_KERNEL_* flags. This is either
* because they really don't support them, or the port needs to be updated to
* reflect the required functionality. Below are a set of relatively safe
* fallbacks, as best effort, which we can count on in lieu of the architectures
* not defining them on their own yet.
*/
#ifndef PAGE_KERNEL_RO
# define PAGE_KERNEL_RO PAGE_KERNEL
#endif
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif
/*
* Page Table Modification bits for pgtbl_mod_mask.
*
* These are used by the p?d_alloc_track*() set of functions an in the generic
* vmalloc/ioremap code to track at which page-table levels entries have been
* modified. Based on that the code can better decide when vmalloc and ioremap
* mapping changes need to be synchronized to other page-tables in the system.
*/
#define __PGTBL_PGD_MODIFIED 0
#define __PGTBL_P4D_MODIFIED 1
#define __PGTBL_PUD_MODIFIED 2
#define __PGTBL_PMD_MODIFIED 3
#define __PGTBL_PTE_MODIFIED 4
#define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED)
#define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED)
#define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED)
#define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED)
#define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED)
/* Page-Table Modification Mask */
typedef unsigned int pgtbl_mod_mask;
#endif /* !__ASSEMBLY__ */
#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
#ifdef CONFIG_PHYS_ADDR_T_64BIT
/*
* ZSMALLOC needs to know the highest PFN on 32-bit architectures
* with physical address space extension, but falls back to
* BITS_PER_LONG otherwise.
*/
#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
#else
#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
#endif
#ifndef has_transparent_hugepage
#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE)
#endif
#ifndef has_transparent_pud_hugepage
#define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
#endif
/*
* On some architectures it depends on the mm if the p4d/pud or pmd
* layer of the page table hierarchy is folded or not.
*/
#ifndef mm_p4d_folded
#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED)
#endif
#ifndef mm_pud_folded
#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED)
#endif
#ifndef mm_pmd_folded
#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED)
#endif
#ifndef p4d_offset_lockless
#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address)
#endif
#ifndef pud_offset_lockless
#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address)
#endif
#ifndef pmd_offset_lockless
#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address)
#endif
/*
* pXd_leaf() is the API to check whether a pgtable entry is a huge page
* mapping. It should work globally across all archs, without any
* dependency on CONFIG_* options. For architectures that do not support
* huge mappings on specific levels, below fallbacks will be used.
*
* A leaf pgtable entry should always imply the following:
*
* - It is a "present" entry. IOW, before using this API, please check it
* with pXd_present() first. NOTE: it may not always mean the "present
* bit" is set. For example, PROT_NONE entries are always "present".
*
* - It should _never_ be a swap entry of any type. Above "present" check
* should have guarded this, but let's be crystal clear on this.
*
* - It should contain a huge PFN, which points to a huge page larger than
* PAGE_SIZE of the platform. The PFN format isn't important here.
*
* - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(),
* pXd_devmap(), or hugetlb mappings).
*/
#ifndef pgd_leaf
#define pgd_leaf(x) false
#endif
#ifndef p4d_leaf
#define p4d_leaf(x) false
#endif
#ifndef pud_leaf
#define pud_leaf(x) false
#endif
#ifndef pmd_leaf
#define pmd_leaf(x) false
#endif
#ifndef pgd_leaf_size
#define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT)
#endif
#ifndef p4d_leaf_size
#define p4d_leaf_size(x) P4D_SIZE
#endif
#ifndef pud_leaf_size
#define pud_leaf_size(x) PUD_SIZE
#endif
#ifndef pmd_leaf_size
#define pmd_leaf_size(x) PMD_SIZE
#endif
#ifndef __pte_leaf_size
#ifndef pte_leaf_size
#define pte_leaf_size(x) PAGE_SIZE
#endif
#define __pte_leaf_size(x,y) pte_leaf_size(y)
#endif
/*
* We always define pmd_pfn for all archs as it's used in lots of generic
* code. Now it happens too for pud_pfn (and can happen for larger
* mappings too in the future; we're not there yet). Instead of defining
* it for all archs (like pmd_pfn), provide a fallback.
*
* Note that returning 0 here means any arch that didn't define this can
* get severely wrong when it hits a real pud leaf. It's arch's
* responsibility to properly define it when a huge pud is possible.
*/
#ifndef pud_pfn
#define pud_pfn(x) 0
#endif
/*
* Some architectures have MMUs that are configurable or selectable at boot
* time. These lead to variable PTRS_PER_x. For statically allocated arrays it
* helps to have a static maximum value.
*/
#ifndef MAX_PTRS_PER_PTE
#define MAX_PTRS_PER_PTE PTRS_PER_PTE
#endif
#ifndef MAX_PTRS_PER_PMD
#define MAX_PTRS_PER_PMD PTRS_PER_PMD
#endif
#ifndef MAX_PTRS_PER_PUD
#define MAX_PTRS_PER_PUD PTRS_PER_PUD
#endif
#ifndef MAX_PTRS_PER_P4D
#define MAX_PTRS_PER_P4D PTRS_PER_P4D
#endif
#ifndef pte_pgprot
#define pte_pgprot(x) ((pgprot_t) {0})
#endif
#ifndef pmd_pgprot
#define pmd_pgprot(x) ((pgprot_t) {0})
#endif
#ifndef pud_pgprot
#define pud_pgprot(x) ((pgprot_t) {0})
#endif
/* description of effects of mapping type and prot in current implementation.
* this is due to the limited x86 page protection hardware. The expected
* behavior is in parens:
*
* map_type prot
* PROT_NONE PROT_READ PROT_WRITE PROT_EXEC
* MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (yes) yes w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
*
* MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
*
* On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
* MAP_PRIVATE (with Enhanced PAN supported):
* r: (no) no
* w: (no) no
* x: (yes) yes
*/
#define DECLARE_VM_GET_PAGE_PROT \
pgprot_t vm_get_page_prot(unsigned long vm_flags) \
{ \
return protection_map[vm_flags & \
(VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \
} \
EXPORT_SYMBOL(vm_get_page_prot);
#endif /* _LINUX_PGTABLE_H */
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/pipe.c
*
* Copyright (C) 1991, 1992, 1999 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/log2.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/magic.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/audit.h>
#include <linux/syscalls.h>
#include <linux/fcntl.h>
#include <linux/memcontrol.h>
#include <linux/watch_queue.h>
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include "internal.h"
/*
* New pipe buffers will be restricted to this size while the user is exceeding
* their pipe buffer quota. The general pipe use case needs at least two
* buffers: one for data yet to be read, and one for new data. If this is less
* than two, then a write to a non-empty pipe may block even if the pipe is not
* full. This can occur with GNU make jobserver or similar uses of pipes as
* semaphores: multiple processes may be waiting to write tokens back to the
* pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/.
*
* Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their
* own risk, namely: pipe writes to non-full pipes may block until the pipe is
* emptied.
*/
#define PIPE_MIN_DEF_BUFFERS 2
/*
* The max size that a non-root user is allowed to grow the pipe. Can
* be set by root in /proc/sys/fs/pipe-max-size
*/
static unsigned int pipe_max_size = 1048576;
/* Maximum allocatable pages per user. Hard limit is unset by default, soft
* matches default values.
*/
static unsigned long pipe_user_pages_hard;
static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
/*
* We use head and tail indices that aren't masked off, except at the point of
* dereference, but rather they're allowed to wrap naturally. This means there
* isn't a dead spot in the buffer, but the ring has to be a power of two and
* <= 2^31.
* -- David Howells 2019-09-23.
*
* Reads with count = 0 should always return 0.
* -- Julian Bradfield 1999-06-07.
*
* FIFOs and Pipes now generate SIGIO for both readers and writers.
* -- Jeremy Elson <jelson@circlemud.org> 2001-08-16
*
* pipe_read & write cleanup
* -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
*/
#define cmp_int(l, r) ((l > r) - (l < r))
#ifdef CONFIG_PROVE_LOCKING
static int pipe_lock_cmp_fn(const struct lockdep_map *a,
const struct lockdep_map *b)
{
return cmp_int((unsigned long) a, (unsigned long) b);
}
#endif
void pipe_lock(struct pipe_inode_info *pipe)
{
if (pipe->files)
mutex_lock(&pipe->mutex);
}
EXPORT_SYMBOL(pipe_lock);
void pipe_unlock(struct pipe_inode_info *pipe)
{
if (pipe->files)
mutex_unlock(&pipe->mutex);
}
EXPORT_SYMBOL(pipe_unlock);
void pipe_double_lock(struct pipe_inode_info *pipe1,
struct pipe_inode_info *pipe2)
{
BUG_ON(pipe1 == pipe2);
if (pipe1 > pipe2)
swap(pipe1, pipe2);
pipe_lock(pipe1);
pipe_lock(pipe2);
}
static struct page *anon_pipe_get_page(struct pipe_inode_info *pipe)
{
for (int i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
if (pipe->tmp_page[i]) {
struct page *page = pipe->tmp_page[i];
pipe->tmp_page[i] = NULL;
return page;
}
}
return alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
}
static void anon_pipe_put_page(struct pipe_inode_info *pipe,
struct page *page)
{ if (page_count(page) == 1) {
for (int i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
if (!pipe->tmp_page[i]) {
pipe->tmp_page[i] = page;
return;
}
}
}
put_page(page);
}
static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
anon_pipe_put_page(pipe, page);
}
static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
if (page_count(page) != 1)
return false;
memcg_kmem_uncharge_page(page, 0);
__SetPageLocked(page);
return true;
}
/**
* generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to attempt to steal
*
* Description:
* This function attempts to steal the &struct page attached to
* @buf. If successful, this function returns 0 and returns with
* the page locked. The caller may then reuse the page for whatever
* he wishes; the typical use is insertion into a different file
* page cache.
*/
bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
/*
* A reference of one is golden, that means that the owner of this
* page is the only one holding a reference to it. lock the page
* and return OK.
*/
if (page_count(page) == 1) {
lock_page(page);
return true;
}
return false;
}
EXPORT_SYMBOL(generic_pipe_buf_try_steal);
/**
* generic_pipe_buf_get - get a reference to a &struct pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to get a reference to
*
* Description:
* This function grabs an extra reference to @buf. It's used in
* the tee() system call, when we duplicate the buffers in one
* pipe into another.
*/
bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
return try_get_page(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_get);
/**
* generic_pipe_buf_release - put a reference to a &struct pipe_buffer
* @pipe: the pipe that the buffer belongs to
* @buf: the buffer to put a reference to
*
* Description:
* This function releases a reference to @buf.
*/
void generic_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
put_page(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_release);
static const struct pipe_buf_operations anon_pipe_buf_ops = {
.release = anon_pipe_buf_release,
.try_steal = anon_pipe_buf_try_steal,
.get = generic_pipe_buf_get,
};
/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
static inline bool pipe_readable(const struct pipe_inode_info *pipe)
{
union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
unsigned int writers = READ_ONCE(pipe->writers);
return !pipe_empty(idx.head, idx.tail) || !writers;
}
static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
struct pipe_buffer *buf,
unsigned int tail)
{
pipe_buf_release(pipe, buf);
/*
* If the pipe has a watch_queue, we need additional protection
* by the spinlock because notifications get posted with only
* this spinlock, no mutex
*/
if (pipe_has_watch_queue(pipe)) {
spin_lock_irq(&pipe->rd_wait.lock);
#ifdef CONFIG_WATCH_QUEUE
if (buf->flags & PIPE_BUF_FLAG_LOSS)
pipe->note_loss = true;
#endif
pipe->tail = ++tail;
spin_unlock_irq(&pipe->rd_wait.lock);
return tail;
}
/*
* Without a watch_queue, we can simply increment the tail
* without the spinlock - the mutex is enough.
*/
pipe->tail = ++tail;
return tail;
}
static ssize_t
anon_pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
size_t total_len = iov_iter_count(to);
struct file *filp = iocb->ki_filp;
struct pipe_inode_info *pipe = filp->private_data;
bool wake_writer = false, wake_next_reader = false;
ssize_t ret;
/* Null read succeeds. */
if (unlikely(total_len == 0))
return 0;
ret = 0;
mutex_lock(&pipe->mutex);
/*
* We only wake up writers if the pipe was full when we started reading
* and it is no longer full after reading to avoid unnecessary wakeups.
*
* But when we do wake up writers, we do so using a sync wakeup
* (WF_SYNC), because we want them to get going and generate more
* data for us.
*/
for (;;) {
/* Read ->head with a barrier vs post_one_notification() */
unsigned int head = smp_load_acquire(&pipe->head);
unsigned int tail = pipe->tail;
#ifdef CONFIG_WATCH_QUEUE
if (pipe->note_loss) {
struct watch_notification n;
if (total_len < 8) {
if (ret == 0)
ret = -ENOBUFS;
break;
}
n.type = WATCH_TYPE_META;
n.subtype = WATCH_META_LOSS_NOTIFICATION;
n.info = watch_sizeof(n);
if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) {
if (ret == 0)
ret = -EFAULT;
break;
}
ret += sizeof(n);
total_len -= sizeof(n);
pipe->note_loss = false;
}
#endif
if (!pipe_empty(head, tail)) {
struct pipe_buffer *buf = pipe_buf(pipe, tail);
size_t chars = buf->len;
size_t written;
int error;
if (chars > total_len) {
if (buf->flags & PIPE_BUF_FLAG_WHOLE) {
if (ret == 0)
ret = -ENOBUFS;
break;
}
chars = total_len;
}
error = pipe_buf_confirm(pipe, buf);
if (error) {
if (!ret)
ret = error;
break;
}
written = copy_page_to_iter(buf->page, buf->offset, chars, to);
if (unlikely(written < chars)) {
if (!ret)
ret = -EFAULT;
break;
}
ret += chars;
buf->offset += chars;
buf->len -= chars;
/* Was it a packet buffer? Clean up and exit */
if (buf->flags & PIPE_BUF_FLAG_PACKET) {
total_len = chars;
buf->len = 0;
}
if (!buf->len) {
wake_writer |= pipe_full(head, tail, pipe->max_usage);
tail = pipe_update_tail(pipe, buf, tail);
}
total_len -= chars;
if (!total_len)
break; /* common path: read succeeded */
if (!pipe_empty(head, tail)) /* More to do? */
continue;
}
if (!pipe->writers)
break;
if (ret)
break;
if ((filp->f_flags & O_NONBLOCK) ||
(iocb->ki_flags & IOCB_NOWAIT)) {
ret = -EAGAIN;
break;
}
mutex_unlock(&pipe->mutex);
/*
* We only get here if we didn't actually read anything.
*
* But because we didn't read anything, at this point we can
* just return directly with -ERESTARTSYS if we're interrupted,
* since we've done any required wakeups and there's no need
* to mark anything accessed. And we've dropped the lock.
*/
if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0)
return -ERESTARTSYS;
wake_next_reader = true;
mutex_lock(&pipe->mutex);
}
if (pipe_is_empty(pipe))
wake_next_reader = false;
mutex_unlock(&pipe->mutex);
if (wake_writer)
wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
if (wake_next_reader)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
return ret;
}
static ssize_t
fifo_pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
int ret = anon_pipe_read(iocb, to);
if (ret > 0)
file_accessed(iocb->ki_filp);
return ret;
}
static inline int is_packetized(struct file *file)
{
return (file->f_flags & O_DIRECT) != 0;
}
/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
static inline bool pipe_writable(const struct pipe_inode_info *pipe)
{
union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
unsigned int max_usage = READ_ONCE(pipe->max_usage);
return !pipe_full(idx.head, idx.tail, max_usage) ||
!READ_ONCE(pipe->readers);
}
static ssize_t
anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *filp = iocb->ki_filp;
struct pipe_inode_info *pipe = filp->private_data;
unsigned int head;
ssize_t ret = 0;
size_t total_len = iov_iter_count(from);
ssize_t chars;
bool was_empty = false;
bool wake_next_writer = false;
/*
* Reject writing to watch queue pipes before the point where we lock
* the pipe.
* Otherwise, lockdep would be unhappy if the caller already has another
* pipe locked.
* If we had to support locking a normal pipe and a notification pipe at
* the same time, we could set up lockdep annotations for that, but
* since we don't actually need that, it's simpler to just bail here.
*/
if (pipe_has_watch_queue(pipe))
return -EXDEV;
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
mutex_lock(&pipe->mutex);
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
goto out;
}
/*
* If it wasn't empty we try to merge new data into
* the last buffer.
*
* That naturally merges small writes, but it also
* page-aligns the rest of the writes for large writes
* spanning multiple pages.
*/
head = pipe->head;
was_empty = pipe_empty(head, pipe->tail);
chars = total_len & (PAGE_SIZE-1);
if (chars && !was_empty) {
struct pipe_buffer *buf = pipe_buf(pipe, head - 1);
int offset = buf->offset + buf->len;
if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) &&
offset + chars <= PAGE_SIZE) {
ret = pipe_buf_confirm(pipe, buf); if (ret)
goto out;
ret = copy_page_from_iter(buf->page, offset, chars, from);
if (unlikely(ret < chars)) {
ret = -EFAULT;
goto out;
}
buf->len += ret;
if (!iov_iter_count(from))
goto out;
}
}
for (;;) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
ret = -EPIPE;
break;
}
head = pipe->head;
if (!pipe_full(head, pipe->tail, pipe->max_usage)) {
struct pipe_buffer *buf;
struct page *page;
int copied;
page = anon_pipe_get_page(pipe); if (unlikely(!page)) { if (!ret)
ret = -ENOMEM;
break;
}
copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { anon_pipe_put_page(pipe, page);
if (!ret)
ret = -EFAULT;
break;
}
pipe->head = head + 1;
/* Insert it into the buffer array */
buf = pipe_buf(pipe, head);
buf->page = page;
buf->ops = &anon_pipe_buf_ops;
buf->offset = 0;
if (is_packetized(filp))
buf->flags = PIPE_BUF_FLAG_PACKET;
else
buf->flags = PIPE_BUF_FLAG_CAN_MERGE;
buf->len = copied;
ret += copied;
if (!iov_iter_count(from))
break;
continue;
}
/* Wait for buffer space to become available. */
if ((filp->f_flags & O_NONBLOCK) ||
(iocb->ki_flags & IOCB_NOWAIT)) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
/*
* We're going to release the pipe lock and wait for more
* space. We wake up any readers if necessary, and then
* after waiting we need to re-check whether the pipe
* become empty while we dropped the lock.
*/
mutex_unlock(&pipe->mutex);
if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
mutex_lock(&pipe->mutex);
was_empty = pipe_is_empty(pipe);
wake_next_writer = true;
}
out:
if (pipe_is_full(pipe))
wake_next_writer = false;
mutex_unlock(&pipe->mutex);
/*
* If we do do a wakeup event, we do a 'sync' wakeup, because we
* want the reader to start processing things asap, rather than
* leave the data pending.
*
* This is particularly important for small writes, because of
* how (for example) the GNU make jobserver uses small writes to
* wake up pending jobs
*
* Epoll nonsensically wants a wakeup whether the pipe
* was already empty or not.
*/
if (was_empty || pipe->poll_usage)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
return ret;
}
static ssize_t
fifo_pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
int ret = anon_pipe_write(iocb, from);
if (ret > 0) {
struct file *filp = iocb->ki_filp;
if (sb_start_write_trylock(file_inode(filp)->i_sb)) {
int err = file_update_time(filp);
if (err)
ret = err;
sb_end_write(file_inode(filp)->i_sb);
}
}
return ret;
}
static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct pipe_inode_info *pipe = filp->private_data;
unsigned int count, head, tail;
switch (cmd) {
case FIONREAD:
mutex_lock(&pipe->mutex);
count = 0;
head = pipe->head;
tail = pipe->tail;
while (!pipe_empty(head, tail)) {
count += pipe_buf(pipe, tail)->len;
tail++;
}
mutex_unlock(&pipe->mutex);
return put_user(count, (int __user *)arg);
#ifdef CONFIG_WATCH_QUEUE
case IOC_WATCH_QUEUE_SET_SIZE: {
int ret;
mutex_lock(&pipe->mutex);
ret = watch_queue_set_size(pipe, arg);
mutex_unlock(&pipe->mutex);
return ret;
}
case IOC_WATCH_QUEUE_SET_FILTER:
return watch_queue_set_filter(
pipe, (struct watch_notification_filter __user *)arg);
#endif
default:
return -ENOIOCTLCMD;
}
}
/* No kernel lock held - fine */
static __poll_t
pipe_poll(struct file *filp, poll_table *wait)
{
__poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
union pipe_index idx;
/* Epoll has some historical nasty semantics, this enables them */
WRITE_ONCE(pipe->poll_usage, true);
/*
* Reading pipe state only -- no need for acquiring the semaphore.
*
* But because this is racy, the code has to add the
* entry to the poll table _first_ ..
*/
if (filp->f_mode & FMODE_READ)
poll_wait(filp, &pipe->rd_wait, wait);
if (filp->f_mode & FMODE_WRITE)
poll_wait(filp, &pipe->wr_wait, wait);
/*
* .. and only then can you do the racy tests. That way,
* if something changes and you got it wrong, the poll
* table entry will wake you up and fix it.
*/
idx.head_tail = READ_ONCE(pipe->head_tail);
mask = 0;
if (filp->f_mode & FMODE_READ) {
if (!pipe_empty(idx.head, idx.tail))
mask |= EPOLLIN | EPOLLRDNORM;
if (!pipe->writers && filp->f_pipe != pipe->w_counter)
mask |= EPOLLHUP;
}
if (filp->f_mode & FMODE_WRITE) {
if (!pipe_full(idx.head, idx.tail, pipe->max_usage))
mask |= EPOLLOUT | EPOLLWRNORM;
/*
* Most Unices do not set EPOLLERR for FIFOs but on Linux they
* behave exactly like pipes for poll().
*/
if (!pipe->readers)
mask |= EPOLLERR;
}
return mask;
}
static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
{
int kill = 0;
spin_lock(&inode->i_lock);
if (!--pipe->files) {
inode->i_pipe = NULL;
kill = 1;
}
spin_unlock(&inode->i_lock);
if (kill)
free_pipe_info(pipe);
}
static int
pipe_release(struct inode *inode, struct file *file)
{
struct pipe_inode_info *pipe = file->private_data;
mutex_lock(&pipe->mutex);
if (file->f_mode & FMODE_READ)
pipe->readers--;
if (file->f_mode & FMODE_WRITE)
pipe->writers--;
/* Was that the last reader or writer, but not the other side? */
if (!pipe->readers != !pipe->writers) {
wake_up_interruptible_all(&pipe->rd_wait);
wake_up_interruptible_all(&pipe->wr_wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
mutex_unlock(&pipe->mutex);
put_pipe_info(inode, pipe);
return 0;
}
static int
pipe_fasync(int fd, struct file *filp, int on)
{
struct pipe_inode_info *pipe = filp->private_data;
int retval = 0;
mutex_lock(&pipe->mutex);
if (filp->f_mode & FMODE_READ)
retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
if (retval < 0 && (filp->f_mode & FMODE_READ))
/* this can happen only if on == T */
fasync_helper(-1, filp, 0, &pipe->fasync_readers);
}
mutex_unlock(&pipe->mutex);
return retval;
}
unsigned long account_pipe_buffers(struct user_struct *user,
unsigned long old, unsigned long new)
{
return atomic_long_add_return(new - old, &user->pipe_bufs);
}
bool too_many_pipe_buffers_soft(unsigned long user_bufs)
{
unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft);
return soft_limit && user_bufs > soft_limit;
}
bool too_many_pipe_buffers_hard(unsigned long user_bufs)
{
unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard);
return hard_limit && user_bufs > hard_limit;
}
bool pipe_is_unprivileged_user(void)
{
return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
}
struct pipe_inode_info *alloc_pipe_info(void)
{
struct pipe_inode_info *pipe;
unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
struct user_struct *user = get_current_user();
unsigned long user_bufs;
unsigned int max_size = READ_ONCE(pipe_max_size);
pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT);
if (pipe == NULL)
goto out_free_uid;
if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE))
pipe_bufs = max_size >> PAGE_SHIFT;
user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS);
pipe_bufs = PIPE_MIN_DEF_BUFFERS;
}
if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())
goto out_revert_acct;
pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer),
GFP_KERNEL_ACCOUNT);
if (pipe->bufs) {
init_waitqueue_head(&pipe->rd_wait);
init_waitqueue_head(&pipe->wr_wait);
pipe->r_counter = pipe->w_counter = 1;
pipe->max_usage = pipe_bufs;
pipe->ring_size = pipe_bufs;
pipe->nr_accounted = pipe_bufs;
pipe->user = user;
mutex_init(&pipe->mutex);
lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL);
return pipe;
}
out_revert_acct:
(void) account_pipe_buffers(user, pipe_bufs, 0);
kfree(pipe);
out_free_uid:
free_uid(user);
return NULL;
}
void free_pipe_info(struct pipe_inode_info *pipe)
{
unsigned int i;
#ifdef CONFIG_WATCH_QUEUE
if (pipe->watch_queue)
watch_queue_clear(pipe->watch_queue);
#endif
(void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0);
free_uid(pipe->user);
for (i = 0; i < pipe->ring_size; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops)
pipe_buf_release(pipe, buf);
}
#ifdef CONFIG_WATCH_QUEUE
if (pipe->watch_queue)
put_watch_queue(pipe->watch_queue);
#endif
for (i = 0; i < ARRAY_SIZE(pipe->tmp_page); i++) {
if (pipe->tmp_page[i])
__free_page(pipe->tmp_page[i]);
}
kfree(pipe->bufs);
kfree(pipe);
}
static struct vfsmount *pipe_mnt __ro_after_init;
/*
* pipefs_dname() is called from d_path().
*/
static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen)
{
return dynamic_dname(buffer, buflen, "pipe:[%lu]",
d_inode(dentry)->i_ino);
}
static const struct dentry_operations pipefs_dentry_operations = {
.d_dname = pipefs_dname,
};
static const struct file_operations pipeanon_fops;
static struct inode * get_pipe_inode(void)
{
struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb);
struct pipe_inode_info *pipe;
if (!inode)
goto fail_inode;
inode->i_ino = get_next_ino();
pipe = alloc_pipe_info();
if (!pipe)
goto fail_iput;
inode->i_pipe = pipe;
pipe->files = 2;
pipe->readers = pipe->writers = 1;
inode->i_fop = &pipeanon_fops;
/*
* Mark the inode dirty from the very beginning,
* that way it will never be moved to the dirty
* list because "mark_inode_dirty()" will think
* that it already _is_ on the dirty list.
*/
inode->i_state = I_DIRTY;
inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
simple_inode_init_ts(inode);
return inode;
fail_iput:
iput(inode);
fail_inode:
return NULL;
}
int create_pipe_files(struct file **res, int flags)
{
struct inode *inode = get_pipe_inode();
struct file *f;
int error;
if (!inode)
return -ENFILE;
if (flags & O_NOTIFICATION_PIPE) {
error = watch_queue_init(inode->i_pipe);
if (error) {
free_pipe_info(inode->i_pipe);
iput(inode);
return error;
}
}
f = alloc_file_pseudo(inode, pipe_mnt, "",
O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
&pipeanon_fops);
if (IS_ERR(f)) {
free_pipe_info(inode->i_pipe);
iput(inode);
return PTR_ERR(f);
}
f->private_data = inode->i_pipe;
f->f_pipe = 0;
res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
&pipeanon_fops);
if (IS_ERR(res[0])) {
put_pipe_info(inode, inode->i_pipe);
fput(f);
return PTR_ERR(res[0]);
}
res[0]->private_data = inode->i_pipe;
res[0]->f_pipe = 0;
res[1] = f;
stream_open(inode, res[0]);
stream_open(inode, res[1]);
/*
* Disable permission and pre-content events, but enable legacy
* inotify events for legacy users.
*/
file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM);
file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM);
return 0;
}
static int __do_pipe_flags(int *fd, struct file **files, int flags)
{
int error;
int fdw, fdr;
if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE))
return -EINVAL;
error = create_pipe_files(files, flags);
if (error)
return error;
error = get_unused_fd_flags(flags);
if (error < 0)
goto err_read_pipe;
fdr = error;
error = get_unused_fd_flags(flags);
if (error < 0)
goto err_fdr;
fdw = error;
audit_fd_pair(fdr, fdw);
fd[0] = fdr;
fd[1] = fdw;
/* pipe groks IOCB_NOWAIT */
files[0]->f_mode |= FMODE_NOWAIT;
files[1]->f_mode |= FMODE_NOWAIT;
return 0;
err_fdr:
put_unused_fd(fdr);
err_read_pipe:
fput(files[0]);
fput(files[1]);
return error;
}
int do_pipe_flags(int *fd, int flags)
{
struct file *files[2];
int error = __do_pipe_flags(fd, files, flags);
if (!error) {
fd_install(fd[0], files[0]);
fd_install(fd[1], files[1]);
}
return error;
}
/*
* sys_pipe() is the normal C calling standard for creating
* a pipe. It's not the way Unix traditionally does this, though.
*/
static int do_pipe2(int __user *fildes, int flags)
{
struct file *files[2];
int fd[2];
int error;
error = __do_pipe_flags(fd, files, flags);
if (!error) {
if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) {
fput(files[0]);
fput(files[1]);
put_unused_fd(fd[0]);
put_unused_fd(fd[1]);
error = -EFAULT;
} else {
fd_install(fd[0], files[0]);
fd_install(fd[1], files[1]);
}
}
return error;
}
SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
{
return do_pipe2(fildes, flags);
}
SYSCALL_DEFINE1(pipe, int __user *, fildes)
{
return do_pipe2(fildes, 0);
}
/*
* This is the stupid "wait for pipe to be readable or writable"
* model.
*
* See pipe_read/write() for the proper kind of exclusive wait,
* but that requires that we wake up any other readers/writers
* if we then do not end up reading everything (ie the whole
* "wake_next_reader/writer" logic in pipe_read/write()).
*/
void pipe_wait_readable(struct pipe_inode_info *pipe)
{
pipe_unlock(pipe);
wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe));
pipe_lock(pipe);
}
void pipe_wait_writable(struct pipe_inode_info *pipe)
{
pipe_unlock(pipe);
wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe));
pipe_lock(pipe);
}
/*
* This depends on both the wait (here) and the wakeup (wake_up_partner)
* holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot
* race with the count check and waitqueue prep.
*
* Normally in order to avoid races, you'd do the prepare_to_wait() first,
* then check the condition you're waiting for, and only then sleep. But
* because of the pipe lock, we can check the condition before being on
* the wait queue.
*
* We use the 'rd_wait' waitqueue for pipe partner waiting.
*/
static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt)
{
DEFINE_WAIT(rdwait);
int cur = *cnt;
while (cur == *cnt) {
prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE);
pipe_unlock(pipe);
schedule();
finish_wait(&pipe->rd_wait, &rdwait);
pipe_lock(pipe);
if (signal_pending(current))
break;
}
return cur == *cnt ? -ERESTARTSYS : 0;
}
static void wake_up_partner(struct pipe_inode_info *pipe)
{
wake_up_interruptible_all(&pipe->rd_wait);
}
static int fifo_open(struct inode *inode, struct file *filp)
{
bool is_pipe = inode->i_fop == &pipeanon_fops;
struct pipe_inode_info *pipe;
int ret;
filp->f_pipe = 0;
spin_lock(&inode->i_lock);
if (inode->i_pipe) {
pipe = inode->i_pipe;
pipe->files++;
spin_unlock(&inode->i_lock);
} else {
spin_unlock(&inode->i_lock);
pipe = alloc_pipe_info();
if (!pipe)
return -ENOMEM;
pipe->files = 1;
spin_lock(&inode->i_lock);
if (unlikely(inode->i_pipe)) {
inode->i_pipe->files++;
spin_unlock(&inode->i_lock);
free_pipe_info(pipe);
pipe = inode->i_pipe;
} else {
inode->i_pipe = pipe;
spin_unlock(&inode->i_lock);
}
}
filp->private_data = pipe;
/* OK, we have a pipe and it's pinned down */
mutex_lock(&pipe->mutex);
/* We can only do regular read/write on fifos */
stream_open(inode, filp);
switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) {
case FMODE_READ:
/*
* O_RDONLY
* POSIX.1 says that O_NONBLOCK means return with the FIFO
* opened, even when there is no process writing the FIFO.
*/
pipe->r_counter++;
if (pipe->readers++ == 0)
wake_up_partner(pipe);
if (!is_pipe && !pipe->writers) {
if ((filp->f_flags & O_NONBLOCK)) {
/* suppress EPOLLHUP until we have
* seen a writer */
filp->f_pipe = pipe->w_counter;
} else {
if (wait_for_partner(pipe, &pipe->w_counter))
goto err_rd;
}
}
break;
case FMODE_WRITE:
/*
* O_WRONLY
* POSIX.1 says that O_NONBLOCK means return -1 with
* errno=ENXIO when there is no process reading the FIFO.
*/
ret = -ENXIO;
if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers)
goto err;
pipe->w_counter++;
if (!pipe->writers++)
wake_up_partner(pipe);
if (!is_pipe && !pipe->readers) {
if (wait_for_partner(pipe, &pipe->r_counter))
goto err_wr;
}
break;
case FMODE_READ | FMODE_WRITE:
/*
* O_RDWR
* POSIX.1 leaves this case "undefined" when O_NONBLOCK is set.
* This implementation will NEVER block on a O_RDWR open, since
* the process can at least talk to itself.
*/
pipe->readers++;
pipe->writers++;
pipe->r_counter++;
pipe->w_counter++;
if (pipe->readers == 1 || pipe->writers == 1)
wake_up_partner(pipe);
break;
default:
ret = -EINVAL;
goto err;
}
/* Ok! */
mutex_unlock(&pipe->mutex);
return 0;
err_rd:
if (!--pipe->readers)
wake_up_interruptible(&pipe->wr_wait);
ret = -ERESTARTSYS;
goto err;
err_wr:
if (!--pipe->writers)
wake_up_interruptible_all(&pipe->rd_wait);
ret = -ERESTARTSYS;
goto err;
err:
mutex_unlock(&pipe->mutex);
put_pipe_info(inode, pipe);
return ret;
}
const struct file_operations pipefifo_fops = {
.open = fifo_open,
.read_iter = fifo_pipe_read,
.write_iter = fifo_pipe_write,
.poll = pipe_poll,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
.splice_write = iter_file_splice_write,
};
static const struct file_operations pipeanon_fops = {
.open = fifo_open,
.read_iter = anon_pipe_read,
.write_iter = anon_pipe_write,
.poll = pipe_poll,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
.splice_write = iter_file_splice_write,
};
/*
* Currently we rely on the pipe array holding a power-of-2 number
* of pages. Returns 0 on error.
*/
unsigned int round_pipe_size(unsigned int size)
{
if (size > (1U << 31))
return 0;
/* Minimum pipe size, as required by POSIX */
if (size < PAGE_SIZE)
return PAGE_SIZE;
return roundup_pow_of_two(size);
}
/*
* Resize the pipe ring to a number of slots.
*
* Note the pipe can be reduced in capacity, but only if the current
* occupancy doesn't exceed nr_slots; if it does, EBUSY will be
* returned instead.
*/
int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
{
struct pipe_buffer *bufs;
unsigned int head, tail, mask, n;
/* nr_slots larger than limits of pipe->{head,tail} */
if (unlikely(nr_slots > (pipe_index_t)-1u))
return -EINVAL;
bufs = kcalloc(nr_slots, sizeof(*bufs),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (unlikely(!bufs))
return -ENOMEM;
spin_lock_irq(&pipe->rd_wait.lock);
mask = pipe->ring_size - 1;
head = pipe->head;
tail = pipe->tail;
n = pipe_occupancy(head, tail);
if (nr_slots < n) {
spin_unlock_irq(&pipe->rd_wait.lock);
kfree(bufs);
return -EBUSY;
}
/*
* The pipe array wraps around, so just start the new one at zero
* and adjust the indices.
*/
if (n > 0) {
unsigned int h = head & mask;
unsigned int t = tail & mask;
if (h > t) {
memcpy(bufs, pipe->bufs + t,
n * sizeof(struct pipe_buffer));
} else {
unsigned int tsize = pipe->ring_size - t;
if (h > 0)
memcpy(bufs + tsize, pipe->bufs,
h * sizeof(struct pipe_buffer));
memcpy(bufs, pipe->bufs + t,
tsize * sizeof(struct pipe_buffer));
}
}
head = n;
tail = 0;
kfree(pipe->bufs);
pipe->bufs = bufs;
pipe->ring_size = nr_slots;
if (pipe->max_usage > nr_slots)
pipe->max_usage = nr_slots;
pipe->tail = tail;
pipe->head = head;
if (!pipe_has_watch_queue(pipe)) {
pipe->max_usage = nr_slots;
pipe->nr_accounted = nr_slots;
}
spin_unlock_irq(&pipe->rd_wait.lock);
/* This might have made more room for writers */
wake_up_interruptible(&pipe->wr_wait);
return 0;
}
/*
* Allocate a new array of pipe buffers and copy the info over. Returns the
* pipe size if successful, or return -ERROR on error.
*/
static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg)
{
unsigned long user_bufs;
unsigned int nr_slots, size;
long ret = 0;
if (pipe_has_watch_queue(pipe))
return -EBUSY;
size = round_pipe_size(arg);
nr_slots = size >> PAGE_SHIFT;
if (!nr_slots)
return -EINVAL;
/*
* If trying to increase the pipe capacity, check that an
* unprivileged user is not trying to exceed various limits
* (soft limit check here, hard limit check just below).
* Decreasing the pipe capacity is always permitted, even
* if the user is currently over a limit.
*/
if (nr_slots > pipe->max_usage &&
size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
return -EPERM;
user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots);
if (nr_slots > pipe->max_usage &&
(too_many_pipe_buffers_hard(user_bufs) ||
too_many_pipe_buffers_soft(user_bufs)) &&
pipe_is_unprivileged_user()) {
ret = -EPERM;
goto out_revert_acct;
}
ret = pipe_resize_ring(pipe, nr_slots);
if (ret < 0)
goto out_revert_acct;
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
(void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted);
return ret;
}
/*
* Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is
* not enough to verify that this is a pipe.
*/
struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice)
{
struct pipe_inode_info *pipe = file->private_data;
if (!pipe)
return NULL;
if (file->f_op != &pipefifo_fops && file->f_op != &pipeanon_fops)
return NULL;
if (for_splice && pipe_has_watch_queue(pipe))
return NULL;
return pipe;
}
long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
{
struct pipe_inode_info *pipe;
long ret;
pipe = get_pipe_info(file, false);
if (!pipe)
return -EBADF;
mutex_lock(&pipe->mutex);
switch (cmd) {
case F_SETPIPE_SZ:
ret = pipe_set_size(pipe, arg);
break;
case F_GETPIPE_SZ:
ret = pipe->max_usage * PAGE_SIZE;
break;
default:
ret = -EINVAL;
break;
}
mutex_unlock(&pipe->mutex);
return ret;
}
static const struct super_operations pipefs_ops = {
.destroy_inode = free_inode_nonrcu,
.statfs = simple_statfs,
};
/*
* pipefs should _never_ be mounted by userland - too much of security hassle,
* no real gain from having the whole file system mounted. So we don't need
* any operations on the root directory. However, we need a non-trivial
* d_name - pipe: will go nicely and kill the special-casing in procfs.
*/
static int pipefs_init_fs_context(struct fs_context *fc)
{
struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC);
if (!ctx)
return -ENOMEM;
ctx->ops = &pipefs_ops;
ctx->dops = &pipefs_dentry_operations;
return 0;
}
static struct file_system_type pipe_fs_type = {
.name = "pipefs",
.init_fs_context = pipefs_init_fs_context,
.kill_sb = kill_anon_super,
};
#ifdef CONFIG_SYSCTL
static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
unsigned int *valp,
int write, void *data)
{
if (write) {
unsigned int val;
val = round_pipe_size(*lvalp);
if (val == 0)
return -EINVAL;
*valp = val;
} else {
unsigned int val = *valp;
*lvalp = (unsigned long) val;
}
return 0;
}
static int proc_dopipe_max_size(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
return do_proc_douintvec(table, write, buffer, lenp, ppos,
do_proc_dopipe_max_size_conv, NULL);
}
static const struct ctl_table fs_pipe_sysctls[] = {
{
.procname = "pipe-max-size",
.data = &pipe_max_size,
.maxlen = sizeof(pipe_max_size),
.mode = 0644,
.proc_handler = proc_dopipe_max_size,
},
{
.procname = "pipe-user-pages-hard",
.data = &pipe_user_pages_hard,
.maxlen = sizeof(pipe_user_pages_hard),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "pipe-user-pages-soft",
.data = &pipe_user_pages_soft,
.maxlen = sizeof(pipe_user_pages_soft),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
};
#endif
static int __init init_pipe_fs(void)
{
int err = register_filesystem(&pipe_fs_type);
if (!err) {
pipe_mnt = kern_mount(&pipe_fs_type);
if (IS_ERR(pipe_mnt)) {
err = PTR_ERR(pipe_mnt);
unregister_filesystem(&pipe_fs_type);
}
}
#ifdef CONFIG_SYSCTL
register_sysctl_init("fs", fs_pipe_sysctls);
#endif
return err;
}
fs_initcall(init_pipe_fs);
/*
* linux/include/linux/console.h
*
* Copyright (C) 1993 Hamish Macdonald
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file COPYING in the main directory of this archive
* for more details.
*
* Changed:
* 10-Mar-94: Arno Griffioen: Conversion for vt100 emulator port from PC LINUX
*/
#ifndef _LINUX_CONSOLE_H_
#define _LINUX_CONSOLE_H_ 1
#include <linux/atomic.h>
#include <linux/bits.h>
#include <linux/irq_work.h>
#include <linux/rculist.h>
#include <linux/rcuwait.h>
#include <linux/types.h>
#include <linux/vesa.h>
struct vc_data;
struct console_font_op;
struct console_font;
struct module;
struct tty_struct;
struct notifier_block;
enum con_scroll {
SM_UP,
SM_DOWN,
};
enum vc_intensity;
/**
* struct consw - callbacks for consoles
*
* @owner: the module to get references of when this console is used
* @con_startup: set up the console and return its name (like VGA, EGA, ...)
* @con_init: initialize the console on @vc. @init is true for the very first
* call on this @vc.
* @con_deinit: deinitialize the console from @vc.
* @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1.
* @con_putc: emit one character with attributes @ca to [@x, @y] on @vc.
* (optional -- @con_putcs would be called instead)
* @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc.
* @con_cursor: enable/disable cursor depending on @enable
* @con_scroll: move lines from @top to @bottom in direction @dir by @lines.
* Return true if no generic handling should be done.
* Invoked by csi_M and printing to the console.
* @con_switch: notifier about the console switch; it is supposed to return
* true if a redraw is needed.
* @con_blank: blank/unblank the console. The target mode is passed in @blank.
* @mode_switch is set if changing from/to text/graphics. The hook
* is supposed to return true if a redraw is needed.
* @con_font_set: set console @vc font to @font with height @vpitch. @flags can
* be %KD_FONT_FLAG_DONT_RECALC. (optional)
* @con_font_get: fetch the current font on @vc of height @vpitch into @font.
* (optional)
* @con_font_default: set default font on @vc. @name can be %NULL or font name
* to search for. @font can be filled back. (optional)
* @con_resize: resize the @vc console to @width x @height. @from_user is true
* when this change comes from the user space.
* @con_set_palette: sets the palette of the console @vc to @table (optional)
* @con_scrolldelta: the contents of the console should be scrolled by @lines.
* Invoked by user. (optional)
* @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not
* provided or returns false, the origin is set to
* @vc->vc_screenbuf. (optional)
* @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g.
* upon entering graphics. (optional)
* @con_build_attr: build attributes based on @color, @intensity and other
* parameters. The result is used for both normal and erase
* characters. (optional)
* @con_invert_region: invert a region of length @count on @vc starting at @p.
* (optional)
* @con_debug_enter: prepare the console for the debugger. This includes, but
* is not limited to, unblanking the console, loading an
* appropriate palette, and allowing debugger generated output.
* (optional)
* @con_debug_leave: restore the console to its pre-debug state as closely as
* possible. (optional)
*/
struct consw {
struct module *owner;
const char *(*con_startup)(void);
void (*con_init)(struct vc_data *vc, bool init);
void (*con_deinit)(struct vc_data *vc);
void (*con_clear)(struct vc_data *vc, unsigned int y,
unsigned int x, unsigned int count);
void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y,
unsigned int x);
void (*con_putcs)(struct vc_data *vc, const u16 *s,
unsigned int count, unsigned int ypos,
unsigned int xpos);
void (*con_cursor)(struct vc_data *vc, bool enable);
bool (*con_scroll)(struct vc_data *vc, unsigned int top,
unsigned int bottom, enum con_scroll dir,
unsigned int lines);
bool (*con_switch)(struct vc_data *vc);
bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank,
bool mode_switch);
int (*con_font_set)(struct vc_data *vc,
const struct console_font *font,
unsigned int vpitch, unsigned int flags);
int (*con_font_get)(struct vc_data *vc, struct console_font *font,
unsigned int vpitch);
int (*con_font_default)(struct vc_data *vc,
struct console_font *font, const char *name);
int (*con_resize)(struct vc_data *vc, unsigned int width,
unsigned int height, bool from_user);
void (*con_set_palette)(struct vc_data *vc,
const unsigned char *table);
void (*con_scrolldelta)(struct vc_data *vc, int lines);
bool (*con_set_origin)(struct vc_data *vc);
void (*con_save_screen)(struct vc_data *vc);
u8 (*con_build_attr)(struct vc_data *vc, u8 color,
enum vc_intensity intensity,
bool blink, bool underline, bool reverse, bool italic);
void (*con_invert_region)(struct vc_data *vc, u16 *p, int count);
void (*con_debug_enter)(struct vc_data *vc);
void (*con_debug_leave)(struct vc_data *vc);
};
extern const struct consw *conswitchp;
extern const struct consw dummy_con; /* dummy console buffer */
extern const struct consw vga_con; /* VGA text console */
extern const struct consw newport_con; /* SGI Newport console */
struct screen_info;
#ifdef CONFIG_VGA_CONSOLE
void vgacon_register_screen(struct screen_info *si);
#else
static inline void vgacon_register_screen(struct screen_info *si) { }
#endif
int con_is_bound(const struct consw *csw);
int do_unregister_con_driver(const struct consw *csw);
int do_take_over_console(const struct consw *sw, int first, int last, int deflt);
void give_up_console(const struct consw *sw);
#ifdef CONFIG_VT
void con_debug_enter(struct vc_data *vc);
void con_debug_leave(void);
#else
static inline void con_debug_enter(struct vc_data *vc) { }
static inline void con_debug_leave(void) { }
#endif
/*
* The interface for a console, or any other device that wants to capture
* console messages (printer driver?)
*/
/**
* enum cons_flags - General console flags
* @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate
* output of messages that were already shown by boot
* consoles or read by userspace via syslog() syscall.
* @CON_CONSDEV: Indicates that the console driver is backing
* /dev/console.
* @CON_ENABLED: Indicates if a console is allowed to print records. If
* false, the console also will not advance to later
* records.
* @CON_BOOT: Marks the console driver as early console driver which
* is used during boot before the real driver becomes
* available. It will be automatically unregistered
* when the real console driver is registered unless
* "keep_bootcon" parameter is used.
* @CON_ANYTIME: A misnomed historical flag which tells the core code
* that the legacy @console::write callback can be invoked
* on a CPU which is marked OFFLINE. That is misleading as
* it suggests that there is no contextual limit for
* invoking the callback. The original motivation was
* readiness of the per-CPU areas.
* @CON_BRL: Indicates a braille device which is exempt from
* receiving the printk spam for obvious reasons.
* @CON_EXTENDED: The console supports the extended output format of
* /dev/kmesg which requires a larger output buffer.
* @CON_SUSPENDED: Indicates if a console is suspended. If true, the
* printing callbacks must not be called.
* @CON_NBCON: Console can operate outside of the legacy style console_lock
* constraints.
*/
enum cons_flags {
CON_PRINTBUFFER = BIT(0),
CON_CONSDEV = BIT(1),
CON_ENABLED = BIT(2),
CON_BOOT = BIT(3),
CON_ANYTIME = BIT(4),
CON_BRL = BIT(5),
CON_EXTENDED = BIT(6),
CON_SUSPENDED = BIT(7),
CON_NBCON = BIT(8),
};
/**
* struct nbcon_state - console state for nbcon consoles
* @atom: Compound of the state fields for atomic operations
*
* @req_prio: The priority of a handover request
* @prio: The priority of the current owner
* @unsafe: Console is busy in a non takeover region
* @unsafe_takeover: A hostile takeover in an unsafe state happened in the
* past. The console cannot be safe until re-initialized.
* @cpu: The CPU on which the owner runs
*
* To be used for reading and preparing of the value stored in the nbcon
* state variable @console::nbcon_state.
*
* The @prio and @req_prio fields are particularly important to allow
* spin-waiting to timeout and give up without the risk of a waiter being
* assigned the lock after giving up.
*/
struct nbcon_state {
union {
unsigned int atom;
struct {
unsigned int prio : 2;
unsigned int req_prio : 2;
unsigned int unsafe : 1;
unsigned int unsafe_takeover : 1;
unsigned int cpu : 24;
};
};
};
/*
* The nbcon_state struct is used to easily create and interpret values that
* are stored in the @console::nbcon_state variable. Ensure this struct stays
* within the size boundaries of the atomic variable's underlying type in
* order to avoid any accidental truncation.
*/
static_assert(sizeof(struct nbcon_state) <= sizeof(int));
/**
* enum nbcon_prio - console owner priority for nbcon consoles
* @NBCON_PRIO_NONE: Unused
* @NBCON_PRIO_NORMAL: Normal (non-emergency) usage
* @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...)
* @NBCON_PRIO_PANIC: Panic output
* @NBCON_PRIO_MAX: The number of priority levels
*
* A higher priority context can takeover the console when it is
* in the safe state. The final attempt to flush consoles in panic()
* can be allowed to do so even in an unsafe state (Hope and pray).
*/
enum nbcon_prio {
NBCON_PRIO_NONE = 0,
NBCON_PRIO_NORMAL,
NBCON_PRIO_EMERGENCY,
NBCON_PRIO_PANIC,
NBCON_PRIO_MAX,
};
struct console;
struct printk_buffers;
/**
* struct nbcon_context - Context for console acquire/release
* @console: The associated console
* @spinwait_max_us: Limit for spin-wait acquire
* @prio: Priority of the context
* @allow_unsafe_takeover: Allow performing takeover even if unsafe. Can
* be used only with NBCON_PRIO_PANIC @prio. It
* might cause a system freeze when the console
* is used later.
* @backlog: Ringbuffer has pending records
* @pbufs: Pointer to the text buffer for this context
* @seq: The sequence number to print for this context
*/
struct nbcon_context {
/* members set by caller */
struct console *console;
unsigned int spinwait_max_us;
enum nbcon_prio prio;
unsigned int allow_unsafe_takeover : 1;
/* members set by emit */
unsigned int backlog : 1;
/* members set by acquire */
struct printk_buffers *pbufs;
u64 seq;
};
/**
* struct nbcon_write_context - Context handed to the nbcon write callbacks
* @ctxt: The core console context
* @outbuf: Pointer to the text buffer for output
* @len: Length to write
* @unsafe_takeover: If a hostile takeover in an unsafe state has occurred
*/
struct nbcon_write_context {
struct nbcon_context __private ctxt;
char *outbuf;
unsigned int len;
bool unsafe_takeover;
};
/**
* struct console - The console descriptor structure
* @name: The name of the console driver
* @write: Legacy write callback to output messages (Optional)
* @read: Read callback for console input (Optional)
* @device: The underlying TTY device driver (Optional)
* @unblank: Callback to unblank the console (Optional)
* @setup: Callback for initializing the console (Optional)
* @exit: Callback for teardown of the console (Optional)
* @match: Callback for matching a console (Optional)
* @flags: Console flags. See enum cons_flags
* @index: Console index, e.g. port number
* @cflag: TTY control mode flags
* @ispeed: TTY input speed
* @ospeed: TTY output speed
* @seq: Sequence number of the next ringbuffer record to print
* @dropped: Number of unreported dropped ringbuffer records
* @data: Driver private data
* @node: hlist node for the console list
*
* @nbcon_state: State for nbcon consoles
* @nbcon_seq: Sequence number of the next record for nbcon to print
* @nbcon_device_ctxt: Context available for non-printing operations
* @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print
* @pbufs: Pointer to nbcon private buffer
* @kthread: Printer kthread for this console
* @rcuwait: RCU-safe wait object for @kthread waking
* @irq_work: Defer @kthread waking to IRQ work context
*/
struct console {
char name[16];
void (*write)(struct console *co, const char *s, unsigned int count);
int (*read)(struct console *co, char *s, unsigned int count);
struct tty_driver *(*device)(struct console *co, int *index);
void (*unblank)(void);
int (*setup)(struct console *co, char *options);
int (*exit)(struct console *co);
int (*match)(struct console *co, char *name, int idx, char *options);
short flags;
short index;
int cflag;
uint ispeed;
uint ospeed;
u64 seq;
unsigned long dropped;
void *data;
struct hlist_node node;
/* nbcon console specific members */
/**
* @write_atomic:
*
* NBCON callback to write out text in any context. (Optional)
*
* This callback is called with the console already acquired. However,
* a higher priority context is allowed to take it over by default.
*
* The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe()
* around any code where the takeover is not safe, for example, when
* manipulating the serial port registers.
*
* nbcon_enter_unsafe() will fail if the context has lost the console
* ownership in the meantime. In this case, the callback is no longer
* allowed to go forward. It must back out immediately and carefully.
* The buffer content is also no longer trusted since it no longer
* belongs to the context.
*
* The callback should allow the takeover whenever it is safe. It
* increases the chance to see messages when the system is in trouble.
* If the driver must reacquire ownership in order to finalize or
* revert hardware changes, nbcon_reacquire_nobuf() can be used.
* However, on reacquire the buffer content is no longer available. A
* reacquire cannot be used to resume printing.
*
* The callback can be called from any context (including NMI).
* Therefore it must avoid usage of any locking and instead rely
* on the console ownership for synchronization.
*/
void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt);
/**
* @write_thread:
*
* NBCON callback to write out text in task context.
*
* This callback must be called only in task context with both
* device_lock() and the nbcon console acquired with
* NBCON_PRIO_NORMAL.
*
* The same rules for console ownership verification and unsafe
* sections handling applies as with write_atomic().
*
* The console ownership handling is necessary for synchronization
* against write_atomic() which is synchronized only via the context.
*
* The device_lock() provides the primary serialization for operations
* on the device. It might be as relaxed (mutex)[*] or as tight
* (disabled preemption and interrupts) as needed. It allows
* the kthread to operate in the least restrictive mode[**].
*
* [*] Standalone nbcon_context_try_acquire() is not safe with
* the preemption enabled, see nbcon_owner_matches(). But it
* can be safe when always called in the preemptive context
* under the device_lock().
*
* [**] The device_lock() makes sure that nbcon_context_try_acquire()
* would never need to spin which is important especially with
* PREEMPT_RT.
*/
void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt);
/**
* @device_lock:
*
* NBCON callback to begin synchronization with driver code.
*
* Console drivers typically must deal with access to the hardware
* via user input/output (such as an interactive login shell) and
* output of kernel messages via printk() calls. This callback is
* called by the printk-subsystem whenever it needs to synchronize
* with hardware access by the driver. It should be implemented to
* use whatever synchronization mechanism the driver is using for
* itself (for example, the port lock for uart serial consoles).
*
* The callback is always called from task context. It may use any
* synchronization method required by the driver.
*
* IMPORTANT: The callback MUST disable migration. The console driver
* may be using a synchronization mechanism that already takes
* care of this (such as spinlocks). Otherwise this function must
* explicitly call migrate_disable().
*
* The flags argument is provided as a convenience to the driver. It
* will be passed again to device_unlock(). It can be ignored if the
* driver does not need it.
*/
void (*device_lock)(struct console *con, unsigned long *flags);
/**
* @device_unlock:
*
* NBCON callback to finish synchronization with driver code.
*
* It is the counterpart to device_lock().
*
* This callback is always called from task context. It must
* appropriately re-enable migration (depending on how device_lock()
* disabled migration).
*
* The flags argument is the value of the same variable that was
* passed to device_lock().
*/
void (*device_unlock)(struct console *con, unsigned long flags);
atomic_t __private nbcon_state;
atomic_long_t __private nbcon_seq;
struct nbcon_context __private nbcon_device_ctxt;
atomic_long_t __private nbcon_prev_seq;
struct printk_buffers *pbufs;
struct task_struct *kthread;
struct rcuwait rcuwait;
struct irq_work irq_work;
};
#ifdef CONFIG_LOCKDEP
extern void lockdep_assert_console_list_lock_held(void);
#else
static inline void lockdep_assert_console_list_lock_held(void)
{
}
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern bool console_srcu_read_lock_is_held(void);
#else
static inline bool console_srcu_read_lock_is_held(void)
{
return 1;
}
#endif
extern int console_srcu_read_lock(void);
extern void console_srcu_read_unlock(int cookie);
extern void console_list_lock(void) __acquires(console_mutex);
extern void console_list_unlock(void) __releases(console_mutex);
extern struct hlist_head console_list;
/**
* console_srcu_read_flags - Locklessly read flags of a possibly registered
* console
* @con: struct console pointer of console to read flags from
*
* Locklessly reading @con->flags provides a consistent read value because
* there is at most one CPU modifying @con->flags and that CPU is using only
* read-modify-write operations to do so.
*
* Requires console_srcu_read_lock to be held, which implies that @con might
* be a registered console. The purpose of holding console_srcu_read_lock is
* to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED)
* and that no exit/cleanup routines will run if the console is currently
* undergoing unregistration.
*
* If the caller is holding the console_list_lock or it is _certain_ that
* @con is not and will not become registered, the caller may read
* @con->flags directly instead.
*
* Context: Any context.
* Return: The current value of the @con->flags field.
*/
static inline short console_srcu_read_flags(const struct console *con)
{
WARN_ON_ONCE(!console_srcu_read_lock_is_held());
/*
* The READ_ONCE() matches the WRITE_ONCE() when @flags are modified
* for registered consoles with console_srcu_write_flags().
*/
return data_race(READ_ONCE(con->flags));
}
/**
* console_srcu_write_flags - Write flags for a registered console
* @con: struct console pointer of console to write flags to
* @flags: new flags value to write
*
* Only use this function to write flags for registered consoles. It
* requires holding the console_list_lock.
*
* Context: Any context.
*/
static inline void console_srcu_write_flags(struct console *con, short flags)
{
lockdep_assert_console_list_lock_held();
/* This matches the READ_ONCE() in console_srcu_read_flags(). */
WRITE_ONCE(con->flags, flags);
}
/* Variant of console_is_registered() when the console_list_lock is held. */
static inline bool console_is_registered_locked(const struct console *con)
{
lockdep_assert_console_list_lock_held();
return !hlist_unhashed(&con->node);
}
/*
* console_is_registered - Check if the console is registered
* @con: struct console pointer of console to check
*
* Context: Process context. May sleep while acquiring console list lock.
* Return: true if the console is in the console list, otherwise false.
*
* If false is returned for a console that was previously registered, it
* can be assumed that the console's unregistration is fully completed,
* including the exit() callback after console list removal.
*/
static inline bool console_is_registered(const struct console *con)
{
bool ret;
console_list_lock();
ret = console_is_registered_locked(con);
console_list_unlock();
return ret;
}
/**
* for_each_console_srcu() - Iterator over registered consoles
* @con: struct console pointer used as loop cursor
*
* Although SRCU guarantees the console list will be consistent, the
* struct console fields may be updated by other CPUs while iterating.
*
* Requires console_srcu_read_lock to be held. Can be invoked from
* any context.
*/
#define for_each_console_srcu(con) \
hlist_for_each_entry_srcu(con, &console_list, node, \
console_srcu_read_lock_is_held())
/**
* for_each_console() - Iterator over registered consoles
* @con: struct console pointer used as loop cursor
*
* The console list and the &console.flags are immutable while iterating.
*
* Requires console_list_lock to be held.
*/
#define for_each_console(con) \
lockdep_assert_console_list_lock_held(); \
hlist_for_each_entry(con, &console_list, node)
#ifdef CONFIG_PRINTK
extern void nbcon_cpu_emergency_enter(void);
extern void nbcon_cpu_emergency_exit(void);
extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt);
extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt);
extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt);
extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt);
#else
static inline void nbcon_cpu_emergency_enter(void) { }
static inline void nbcon_cpu_emergency_exit(void) { }
static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; }
static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; }
static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; }
static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { }
#endif
extern int console_set_on_cmdline;
extern struct console *early_console;
enum con_flush_mode {
CONSOLE_FLUSH_PENDING,
CONSOLE_REPLAY_ALL,
};
extern int add_preferred_console(const char *name, const short idx, char *options);
extern void console_force_preferred_locked(struct console *con);
extern void register_console(struct console *);
extern int unregister_console(struct console *);
extern void console_lock(void);
extern int console_trylock(void);
extern void console_unlock(void);
extern void console_conditional_schedule(void);
extern void console_unblank(void);
extern void console_flush_on_panic(enum con_flush_mode mode);
extern struct tty_driver *console_device(int *);
extern void console_suspend(struct console *);
extern void console_resume(struct console *);
extern int is_console_locked(void);
extern int braille_register_console(struct console *, int index,
char *console_options, char *braille_options);
extern int braille_unregister_console(struct console *);
#ifdef CONFIG_TTY
extern void console_sysfs_notify(void);
#else
static inline void console_sysfs_notify(void)
{ }
#endif
extern bool console_suspend_enabled;
/* Suspend and resume console messages over PM events */
extern void console_suspend_all(void);
extern void console_resume_all(void);
int mda_console_init(void);
void vcs_make_sysfs(int index);
void vcs_remove_sysfs(int index);
/* Some debug stub to catch some of the obvious races in the VT code */
#define WARN_CONSOLE_UNLOCKED() \
WARN_ON(!atomic_read(&ignore_console_lock_warning) && \
!is_console_locked() && !oops_in_progress)
/*
* Increment ignore_console_lock_warning if you need to quiet
* WARN_CONSOLE_UNLOCKED() for debugging purposes.
*/
extern atomic_t ignore_console_lock_warning;
extern void console_init(void);
/* For deferred console takeover */
void dummycon_register_output_notifier(struct notifier_block *nb);
void dummycon_unregister_output_notifier(struct notifier_block *nb);
#endif /* _LINUX_CONSOLE_H */
// SPDX-License-Identifier: GPL-2.0
/*
* mm/pgtable-generic.c
*
* Generic pgtable methods declared in linux/pgtable.h
*
* Copyright (C) 2010 Linus Torvalds
*/
#include <linux/pagemap.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mm_inline.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
/*
* If a p?d_bad entry is found while walking page tables, report
* the error, before resetting entry to p?d_none. Usually (but
* very seldom) called out from the p?d_none_or_clear_bad macros.
*/
void pgd_clear_bad(pgd_t *pgd)
{
pgd_ERROR(*pgd);
pgd_clear(pgd);
}
#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *p4d)
{
p4d_ERROR(*p4d);
p4d_clear(p4d);
}
#endif
#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
pud_clear(pud);
}
#endif
/*
* Note that the pmd variant below can't be stub'ed out just as for p4d/pud
* above. pmd folding is special and typically pmd_* macros refer to upper
* level even when folded
*/
void pmd_clear_bad(pmd_t *pmd)
{
pmd_ERROR(*pmd);
pmd_clear(pmd);
}
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
/*
* Only sets the access flags (dirty, accessed), as well as write
* permission. Furthermore, we know it always gets set to a "more
* permissive" setting, which allows most architectures to optimize
* this. We return whether the PTE actually changed, which in turn
* instructs the caller to do things like update__mmu_cache. This
* used to be done in the caller, but sparc needs minor faults to
* force that call on sun4c so we changed this macro slightly
*/
int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
int changed = !pte_same(ptep_get(ptep), entry);
if (changed) {
set_pte_at(vma->vm_mm, address, ptep, entry);
flush_tlb_fix_spurious_fault(vma, address, ptep);
}
return changed;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
int young;
young = ptep_test_and_clear_young(vma, address, ptep);
if (young)
flush_tlb_page(vma, address);
return young;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
struct mm_struct *mm = (vma)->vm_mm;
pte_t pte;
pte = ptep_get_and_clear(mm, address, ptep); if (pte_accessible(mm, pte)) flush_tlb_page(vma, address);
return pte;
}
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty)
{
int changed = !pmd_same(*pmdp, entry);
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
if (changed) {
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
return changed;
}
#endif
#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
int young;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
young = pmdp_test_and_clear_young(vma, address, pmdp);
if (young)
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return young;
}
#endif
#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
!pmd_devmap(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
pud_t *pudp)
{
pud_t pud;
VM_BUG_ON(address & ~HPAGE_PUD_MASK);
VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
return pud;
}
#endif
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable)
{
assert_spin_locked(pmd_lockptr(mm, pmdp));
/* FIFO */
if (!pmd_huge_pte(mm, pmdp))
INIT_LIST_HEAD(&pgtable->lru);
else
list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
pmd_huge_pte(mm, pmdp) = pgtable;
}
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
/* no "address" argument so destroys page coloring of some arch */
pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
pgtable_t pgtable;
assert_spin_locked(pmd_lockptr(mm, pmdp));
/* FIFO */
pgtable = pmd_huge_pte(mm, pmdp);
pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru,
struct page, lru);
if (pmd_huge_pte(mm, pmdp))
list_del(&pgtable->lru);
return pgtable;
}
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
VM_WARN_ON_ONCE(!pmd_present(*pmdp));
pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return old;
}
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
VM_WARN_ON_ONCE(!pmd_present(*pmdp));
return pmdp_invalidate(vma, address, pmdp);
}
#endif
#ifndef pmdp_collapse_flush
pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
/*
* pmd and hugepage pte format are same. So we could
* use the same function.
*/
pmd_t pmd;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
VM_BUG_ON(pmd_trans_huge(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
/* collapse entails shooting down ptes not pmd */
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
return pmd;
}
#endif
/* arch define pte_free_defer in asm/pgalloc.h for its own implementation */
#ifndef pte_free_defer
static void pte_free_now(struct rcu_head *head)
{
struct page *page;
page = container_of(head, struct page, rcu_head);
pte_free(NULL /* mm not passed and not used */, (pgtable_t)page);
}
void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
{
struct page *page;
page = pgtable;
call_rcu(&page->rcu_head, pte_free_now);
}
#endif /* pte_free_defer */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \
(defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU))
/*
* See the comment above ptep_get_lockless() in include/linux/pgtable.h:
* the barriers in pmdp_get_lockless() cannot guarantee that the value in
* pmd_high actually belongs with the value in pmd_low; but holding interrupts
* off blocks the TLB flush between present updates, which guarantees that a
* successful __pte_offset_map() points to a page from matched halves.
*/
static unsigned long pmdp_get_lockless_start(void)
{
unsigned long irqflags;
local_irq_save(irqflags);
return irqflags;
}
static void pmdp_get_lockless_end(unsigned long irqflags)
{
local_irq_restore(irqflags);
}
#else
static unsigned long pmdp_get_lockless_start(void) { return 0; }
static void pmdp_get_lockless_end(unsigned long irqflags) { }
#endif
pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
{
unsigned long irqflags;
pmd_t pmdval;
rcu_read_lock();
irqflags = pmdp_get_lockless_start();
pmdval = pmdp_get_lockless(pmd);
pmdp_get_lockless_end(irqflags);
if (pmdvalp) *pmdvalp = pmdval; if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
goto nomap;
if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval)))
goto nomap;
if (unlikely(pmd_bad(pmdval))) {
pmd_clear_bad(pmd);
goto nomap;
}
return __pte_map(&pmdval, addr);
nomap:
rcu_read_unlock();
return NULL;
}
pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp)
{
pmd_t pmdval;
pte_t *pte;
pte = __pte_offset_map(pmd, addr, &pmdval);
if (likely(pte))
*ptlp = pte_lockptr(mm, &pmdval);
return pte;
}
pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, pmd_t *pmdvalp,
spinlock_t **ptlp)
{
pte_t *pte;
VM_WARN_ON_ONCE(!pmdvalp);
pte = __pte_offset_map(pmd, addr, pmdvalp);
if (likely(pte)) *ptlp = pte_lockptr(mm, pmdvalp);
return pte;
}
/*
* pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation
* __pte_offset_map_lock() below, is usually called with the pmd pointer for
* addr, reached by walking down the mm's pgd, p4d, pud for addr: either while
* holding mmap_lock or vma lock for read or for write; or in truncate or rmap
* context, while holding file's i_mmap_lock or anon_vma lock for read (or for
* write). In a few cases, it may be used with pmd pointing to a pmd_t already
* copied to or constructed on the stack.
*
* When successful, it returns the pte pointer for addr, with its page table
* kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent
* modification by software, with a pointer to that spinlock in ptlp (in some
* configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's
* struct page). pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards.
*
* But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no
* page table at *pmd: if, for example, the page table has just been removed,
* or replaced by the huge pmd of a THP. (When successful, *pmd is rechecked
* after acquiring the ptlock, and retried internally if it changed: so that a
* page table can be safely removed or replaced by THP while holding its lock.)
*
* pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above,
* just returns the pte pointer for addr, its page table kmapped if necessary;
* or NULL if there is no page table at *pmd. It does not attempt to lock the
* page table, so cannot normally be used when the page table is to be updated,
* or when entries read must be stable. But it does take rcu_read_lock(): so
* that even when page table is racily removed, it remains a valid though empty
* and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s
* afterwards.
*
* pte_offset_map_ro_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map();
* but when successful, it also outputs a pointer to the spinlock in ptlp - as
* pte_offset_map_lock() does, but in this case without locking it. This helps
* the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time
* act on a changed *pmd: pte_offset_map_ro_nolock() provides the correct spinlock
* pointer for the page table that it returns. Even after grabbing the spinlock,
* we might be looking either at a page table that is still mapped or one that
* was unmapped and is about to get freed. But for R/O access this is sufficient.
* So it is only applicable for read-only cases where any modification operations
* to the page table are not allowed even if the corresponding spinlock is held
* afterwards.
*
* pte_offset_map_rw_nolock(mm, pmd, addr, pmdvalp, ptlp), above, is like
* pte_offset_map_ro_nolock(); but when successful, it also outputs the pdmval.
* It is applicable for may-write cases where any modification operations to the
* page table may happen after the corresponding spinlock is held afterwards.
* But the users should make sure the page table is stable like checking pte_same()
* or checking pmd_same() by using the output pmdval before performing the write
* operations.
*
* Note: "RO" / "RW" expresses the intended semantics, not that the *kmap* will
* be read-only/read-write protected.
*
* Note that free_pgtables(), used after unmapping detached vmas, or when
* exiting the whole mm, does not take page table lock before freeing a page
* table, and may not use RCU at all: "outsiders" like khugepaged should avoid
* pte_offset_map() and co once the vma is detached from mm or mm_users is zero.
*/
pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, spinlock_t **ptlp)
{
spinlock_t *ptl;
pmd_t pmdval;
pte_t *pte;
again:
pte = __pte_offset_map(pmd, addr, &pmdval);
if (unlikely(!pte))
return pte;
ptl = pte_lockptr(mm, &pmdval);
spin_lock(ptl);
if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
*ptlp = ptl;
return pte;
}
pte_unmap_unlock(pte, ptl);
goto again;
}
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Directory notifications for Linux.
*
* Copyright (C) 2000,2001,2002 Stephen Rothwell
*
* Copyright (C) 2009 Eric Paris <Red Hat Inc>
* dnotify was largly rewritten to use the new fsnotify infrastructure
*/
#include <linux/fs.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/dnotify.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/fsnotify_backend.h>
static int dir_notify_enable __read_mostly = 1;
#ifdef CONFIG_SYSCTL
static const struct ctl_table dnotify_sysctls[] = {
{
.procname = "dir-notify-enable",
.data = &dir_notify_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
};
static void __init dnotify_sysctl_init(void)
{
register_sysctl_init("fs", dnotify_sysctls);
}
#else
#define dnotify_sysctl_init() do { } while (0)
#endif
static struct kmem_cache *dnotify_struct_cache __ro_after_init;
static struct kmem_cache *dnotify_mark_cache __ro_after_init;
static struct fsnotify_group *dnotify_group __ro_after_init;
/*
* dnotify will attach one of these to each inode (i_fsnotify_marks) which
* is being watched by dnotify. If multiple userspace applications are watching
* the same directory with dnotify their information is chained in dn
*/
struct dnotify_mark {
struct fsnotify_mark fsn_mark;
struct dnotify_struct *dn;
};
/*
* When a process starts or stops watching an inode the set of events which
* dnotify cares about for that inode may change. This function runs the
* list of everything receiving dnotify events about this directory and calculates
* the set of all those events. After it updates what dnotify is interested in
* it calls the fsnotify function so it can update the set of all events relevant
* to this inode.
*/
static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
{
__u32 new_mask = 0;
struct dnotify_struct *dn;
struct dnotify_mark *dn_mark = container_of(fsn_mark,
struct dnotify_mark,
fsn_mark);
assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
if (fsn_mark->mask == new_mask)
return;
fsn_mark->mask = new_mask;
fsnotify_recalc_mask(fsn_mark->connector);
}
/*
* Mains fsnotify call where events are delivered to dnotify.
* Find the dnotify mark on the relevant inode, run the list of dnotify structs
* on that mark and determine which of them has expressed interest in receiving
* events of this type. When found send the correct process and signal and
* destroy the dnotify struct if it was not registered to receive multiple
* events.
*/
static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
struct inode *inode, struct inode *dir,
const struct qstr *name, u32 cookie)
{
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
struct dnotify_struct **prev;
struct fown_struct *fown;
__u32 test_mask = mask & ~FS_EVENT_ON_CHILD;
/* not a dir, dnotify doesn't care */
if (!dir && !(mask & FS_ISDIR))
return 0;
dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark);
spin_lock(&inode_mark->lock);
prev = &dn_mark->dn;
while ((dn = *prev) != NULL) {
if ((dn->dn_mask & test_mask) == 0) {
prev = &dn->dn_next;
continue;
}
fown = file_f_owner(dn->dn_filp);
send_sigio(fown, dn->dn_fd, POLL_MSG);
if (dn->dn_mask & FS_DN_MULTISHOT)
prev = &dn->dn_next;
else {
*prev = dn->dn_next;
kmem_cache_free(dnotify_struct_cache, dn);
dnotify_recalc_inode_mask(inode_mark);
}
}
spin_unlock(&inode_mark->lock);
return 0;
}
static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
{
struct dnotify_mark *dn_mark = container_of(fsn_mark,
struct dnotify_mark,
fsn_mark);
BUG_ON(dn_mark->dn);
kmem_cache_free(dnotify_mark_cache, dn_mark);
}
static const struct fsnotify_ops dnotify_fsnotify_ops = {
.handle_inode_event = dnotify_handle_event,
.free_mark = dnotify_free_mark,
};
/*
* Called every time a file is closed. Looks first for a dnotify mark on the
* inode. If one is found run all of the ->dn structures attached to that
* mark for one relevant to this process closing the file and remove that
* dnotify_struct. If that was the last dnotify_struct also remove the
* fsnotify_mark.
*/
void dnotify_flush(struct file *filp, fl_owner_t id)
{
struct fsnotify_mark *fsn_mark;
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
struct dnotify_struct **prev;
struct inode *inode;
bool free = false;
inode = file_inode(filp);
if (!S_ISDIR(inode->i_mode))
return;
fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
if (!fsn_mark)
return;
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
fsnotify_group_lock(dnotify_group);
spin_lock(&fsn_mark->lock);
prev = &dn_mark->dn;
while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
*prev = dn->dn_next;
kmem_cache_free(dnotify_struct_cache, dn);
dnotify_recalc_inode_mask(fsn_mark);
break;
}
prev = &dn->dn_next;
}
spin_unlock(&fsn_mark->lock);
/* nothing else could have found us thanks to the dnotify_groups
mark_mutex */
if (dn_mark->dn == NULL) {
fsnotify_detach_mark(fsn_mark);
free = true;
}
fsnotify_group_unlock(dnotify_group);
if (free)
fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
}
/* this conversion is done only at watch creation */
static __u32 convert_arg(unsigned int arg)
{
__u32 new_mask = FS_EVENT_ON_CHILD;
if (arg & DN_MULTISHOT)
new_mask |= FS_DN_MULTISHOT;
if (arg & DN_DELETE)
new_mask |= (FS_DELETE | FS_MOVED_FROM);
if (arg & DN_MODIFY)
new_mask |= FS_MODIFY;
if (arg & DN_ACCESS)
new_mask |= FS_ACCESS;
if (arg & DN_ATTRIB)
new_mask |= FS_ATTRIB;
if (arg & DN_RENAME)
new_mask |= FS_RENAME;
if (arg & DN_CREATE)
new_mask |= (FS_CREATE | FS_MOVED_TO);
return new_mask;
}
/*
* If multiple processes watch the same inode with dnotify there is only one
* dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct
* onto that mark. This function either attaches the new dnotify_struct onto
* that list, or it |= the mask onto an existing dnofiy_struct.
*/
static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark,
fl_owner_t id, int fd, struct file *filp, __u32 mask)
{
struct dnotify_struct *odn;
odn = dn_mark->dn;
while (odn != NULL) {
/* adding more events to existing dnofiy_struct? */
if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
odn->dn_fd = fd;
odn->dn_mask |= mask;
return -EEXIST;
}
odn = odn->dn_next;
}
dn->dn_mask = mask;
dn->dn_fd = fd;
dn->dn_filp = filp;
dn->dn_owner = id;
dn->dn_next = dn_mark->dn;
dn_mark->dn = dn;
return 0;
}
/*
* When a process calls fcntl to attach a dnotify watch to a directory it ends
* up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be
* attached to the fsnotify_mark.
*/
int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
{
struct dnotify_mark *new_dn_mark, *dn_mark;
struct fsnotify_mark *new_fsn_mark, *fsn_mark;
struct dnotify_struct *dn;
struct inode *inode;
fl_owner_t id = current->files;
struct file *f = NULL;
int destroy = 0, error = 0;
__u32 mask;
/* we use these to tell if we need to kfree */
new_fsn_mark = NULL;
dn = NULL;
if (!dir_notify_enable) {
error = -EINVAL;
goto out_err;
}
/* a 0 mask means we are explicitly removing the watch */
if ((arg & ~DN_MULTISHOT) == 0) {
dnotify_flush(filp, id);
error = 0;
goto out_err;
}
/* dnotify only works on directories */
inode = file_inode(filp);
if (!S_ISDIR(inode->i_mode)) {
error = -ENOTDIR;
goto out_err;
}
/*
* convert the userspace DN_* "arg" to the internal FS_*
* defined in fsnotify
*/
mask = convert_arg(arg);
error = security_path_notify(&filp->f_path, mask,
FSNOTIFY_OBJ_TYPE_INODE);
if (error)
goto out_err;
/* expect most fcntl to add new rather than augment old */
dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL);
if (!dn) {
error = -ENOMEM;
goto out_err;
}
/* new fsnotify mark, we expect most fcntl calls to add a new mark */
new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL);
if (!new_dn_mark) {
error = -ENOMEM;
goto out_err;
}
error = file_f_owner_allocate(filp);
if (error)
goto out_err;
/* set up the new_fsn_mark and new_dn_mark */
new_fsn_mark = &new_dn_mark->fsn_mark;
fsnotify_init_mark(new_fsn_mark, dnotify_group);
new_fsn_mark->mask = mask;
new_dn_mark->dn = NULL;
/* this is needed to prevent the fcntl/close race described below */
fsnotify_group_lock(dnotify_group);
/* add the new_fsn_mark or find an old one. */
fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
if (fsn_mark) {
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
} else {
error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0);
if (error) {
fsnotify_group_unlock(dnotify_group);
goto out_err;
}
spin_lock(&new_fsn_mark->lock);
fsn_mark = new_fsn_mark;
dn_mark = new_dn_mark;
/* we used new_fsn_mark, so don't free it */
new_fsn_mark = NULL;
}
f = fget_raw(fd);
/* if (f != filp) means that we lost a race and another task/thread
* actually closed the fd we are still playing with before we grabbed
* the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the
* fd is the only time we clean up the marks we need to get our mark
* off the list. */
if (f != filp) {
/* if we added ourselves, shoot ourselves, it's possible that
* the flush actually did shoot this fsn_mark. That's fine too
* since multiple calls to destroy_mark is perfectly safe, if
* we found a dn_mark already attached to the inode, just sod
* off silently as the flush at close time dealt with it.
*/
if (dn_mark == new_dn_mark)
destroy = 1;
error = 0;
goto out;
}
__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
error = attach_dn(dn, dn_mark, id, fd, filp, mask);
/* !error means that we attached the dn to the dn_mark, so don't free it */
if (!error)
dn = NULL;
/* -EEXIST means that we didn't add this new dn and used an old one.
* that isn't an error (and the unused dn should be freed) */
else if (error == -EEXIST)
error = 0;
dnotify_recalc_inode_mask(fsn_mark);
out:
spin_unlock(&fsn_mark->lock);
if (destroy)
fsnotify_detach_mark(fsn_mark);
fsnotify_group_unlock(dnotify_group);
if (destroy)
fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
out_err:
if (new_fsn_mark)
fsnotify_put_mark(new_fsn_mark);
if (dn)
kmem_cache_free(dnotify_struct_cache, dn);
if (f)
fput(f);
return error;
}
static int __init dnotify_init(void)
{
dnotify_struct_cache = KMEM_CACHE(dnotify_struct,
SLAB_PANIC|SLAB_ACCOUNT);
dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0);
if (IS_ERR(dnotify_group))
panic("unable to allocate fsnotify group for dnotify\n");
dnotify_sysctl_init();
return 0;
}
module_init(dnotify_init)
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MIN_HEAP_H
#define _LINUX_MIN_HEAP_H
#include <linux/bug.h>
#include <linux/string.h>
#include <linux/types.h>
/*
* The Min Heap API provides utilities for managing min-heaps, a binary tree
* structure where each node's value is less than or equal to its children's
* values, ensuring the smallest element is at the root.
*
* Users should avoid directly calling functions prefixed with __min_heap_*().
* Instead, use the provided macro wrappers.
*
* For further details and examples, refer to Documentation/core-api/min_heap.rst.
*/
/**
* Data structure to hold a min-heap.
* @nr: Number of elements currently in the heap.
* @size: Maximum number of elements that can be held in current storage.
* @data: Pointer to the start of array holding the heap elements.
* @preallocated: Start of the static preallocated array holding the heap elements.
*/
#define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \
struct _name { \
size_t nr; \
size_t size; \
_type *data; \
_type preallocated[_nr]; \
}
#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0)
typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char;
#define __minheap_cast(_heap) (typeof((_heap)->data[0]) *)
#define __minheap_obj_size(_heap) sizeof((_heap)->data[0])
/**
* struct min_heap_callbacks - Data/functions to customise the min_heap.
* @less: Partial order function for this heap.
* @swp: Swap elements function.
*/
struct min_heap_callbacks {
bool (*less)(const void *lhs, const void *rhs, void *args);
void (*swp)(void *lhs, void *rhs, void *args);
};
/**
* is_aligned - is this pointer & size okay for word-wide copying?
* @base: pointer to data
* @size: size of each element
* @align: required alignment (typically 4 or 8)
*
* Returns true if elements can be copied using word loads and stores.
* The size must be a multiple of the alignment, and the base address must
* be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
*
* For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
* to "if ((a | b) & mask)", so we do that by hand.
*/
__attribute_const__ __always_inline
static bool is_aligned(const void *base, size_t size, unsigned char align)
{
unsigned char lsbits = (unsigned char)size;
(void)base;
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
lsbits |= (unsigned char)(uintptr_t)base;
#endif
return (lsbits & (align - 1)) == 0;
}
/**
* swap_words_32 - swap two elements in 32-bit chunks
* @a: pointer to the first element to swap
* @b: pointer to the second element to swap
* @n: element size (must be a multiple of 4)
*
* Exchange the two objects in memory. This exploits base+index addressing,
* which basically all CPUs have, to minimize loop overhead computations.
*
* For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
* bottom of the loop, even though the zero flag is still valid from the
* subtract (since the intervening mov instructions don't alter the flags).
* Gcc 8.1.0 doesn't have that problem.
*/
static __always_inline
void swap_words_32(void *a, void *b, size_t n)
{
do {
u32 t = *(u32 *)(a + (n -= 4));
*(u32 *)(a + n) = *(u32 *)(b + n);
*(u32 *)(b + n) = t;
} while (n);
}
/**
* swap_words_64 - swap two elements in 64-bit chunks
* @a: pointer to the first element to swap
* @b: pointer to the second element to swap
* @n: element size (must be a multiple of 8)
*
* Exchange the two objects in memory. This exploits base+index
* addressing, which basically all CPUs have, to minimize loop overhead
* computations.
*
* We'd like to use 64-bit loads if possible. If they're not, emulating
* one requires base+index+4 addressing which x86 has but most other
* processors do not. If CONFIG_64BIT, we definitely have 64-bit loads,
* but it's possible to have 64-bit loads without 64-bit pointers (e.g.
* x32 ABI). Are there any cases the kernel needs to worry about?
*/
static __always_inline
void swap_words_64(void *a, void *b, size_t n)
{
do {
#ifdef CONFIG_64BIT
u64 t = *(u64 *)(a + (n -= 8));
*(u64 *)(a + n) = *(u64 *)(b + n);
*(u64 *)(b + n) = t;
#else
/* Use two 32-bit transfers to avoid base+index+4 addressing */
u32 t = *(u32 *)(a + (n -= 4));
*(u32 *)(a + n) = *(u32 *)(b + n);
*(u32 *)(b + n) = t;
t = *(u32 *)(a + (n -= 4));
*(u32 *)(a + n) = *(u32 *)(b + n);
*(u32 *)(b + n) = t;
#endif
} while (n);
}
/**
* swap_bytes - swap two elements a byte at a time
* @a: pointer to the first element to swap
* @b: pointer to the second element to swap
* @n: element size
*
* This is the fallback if alignment doesn't allow using larger chunks.
*/
static __always_inline
void swap_bytes(void *a, void *b, size_t n)
{
do {
char t = ((char *)a)[--n];
((char *)a)[n] = ((char *)b)[n];
((char *)b)[n] = t;
} while (n);
}
/*
* The values are arbitrary as long as they can't be confused with
* a pointer, but small integers make for the smallest compare
* instructions.
*/
#define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0)
#define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1)
#define SWAP_BYTES ((void (*)(void *, void *, void *))2)
/*
* Selects the appropriate swap function based on the element size.
*/
static __always_inline
void *select_swap_func(const void *base, size_t size)
{
if (is_aligned(base, size, 8))
return SWAP_WORDS_64;
else if (is_aligned(base, size, 4))
return SWAP_WORDS_32;
else
return SWAP_BYTES;
}
static __always_inline
void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args),
void *priv)
{
if (swap_func == SWAP_WORDS_64)
swap_words_64(a, b, size);
else if (swap_func == SWAP_WORDS_32)
swap_words_32(a, b, size);
else if (swap_func == SWAP_BYTES)
swap_bytes(a, b, size);
else
swap_func(a, b, priv);
}
/**
* parent - given the offset of the child, find the offset of the parent.
* @i: the offset of the heap element whose parent is sought. Non-zero.
* @lsbit: a precomputed 1-bit mask, equal to "size & -size"
* @size: size of each element
*
* In terms of array indexes, the parent of element j = @i/@size is simply
* (j-1)/2. But when working in byte offsets, we can't use implicit
* truncation of integer divides.
*
* Fortunately, we only need one bit of the quotient, not the full divide.
* @size has a least significant bit. That bit will be clear if @i is
* an even multiple of @size, and set if it's an odd multiple.
*
* Logically, we're doing "if (i & lsbit) i -= size;", but since the
* branch is unpredictable, it's done with a bit of clever branch-free
* code instead.
*/
__attribute_const__ __always_inline
static size_t parent(size_t i, unsigned int lsbit, size_t size)
{
i -= size;
i -= size & -(i & lsbit);
return i / 2;
}
/* Initialize a min-heap. */
static __always_inline
void __min_heap_init_inline(min_heap_char *heap, void *data, size_t size)
{
heap->nr = 0;
heap->size = size;
if (data)
heap->data = data;
else
heap->data = heap->preallocated;
}
#define min_heap_init_inline(_heap, _data, _size) \
__min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
/* Get the minimum element from the heap. */
static __always_inline
void *__min_heap_peek_inline(struct min_heap_char *heap)
{
return heap->nr ? heap->data : NULL;
}
#define min_heap_peek_inline(_heap) \
(__minheap_cast(_heap) \
__min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr)))
/* Check if the heap is full. */
static __always_inline
bool __min_heap_full_inline(min_heap_char *heap)
{
return heap->nr == heap->size;
}
#define min_heap_full_inline(_heap) \
__min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr))
/* Sift the element at pos down the heap. */
static __always_inline
void __min_heap_sift_down_inline(min_heap_char *heap, size_t pos, size_t elem_size,
const struct min_heap_callbacks *func, void *args)
{
const unsigned long lsbit = elem_size & -elem_size;
void *data = heap->data;
void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
/* pre-scale counters for performance */
size_t a = pos * elem_size;
size_t b, c, d;
size_t n = heap->nr * elem_size;
if (!swp)
swp = select_swap_func(data, elem_size);
/* Find the sift-down path all the way to the leaves. */
for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;)
b = func->less(data + c, data + d, args) ? c : d;
/* Special case for the last leaf with no sibling. */
if (d == n)
b = c;
/* Backtrack to the correct location. */
while (b != a && func->less(data + a, data + b, args))
b = parent(b, lsbit, elem_size);
/* Shift the element into its correct place. */
c = b;
while (b != a) {
b = parent(b, lsbit, elem_size);
do_swap(data + b, data + c, elem_size, swp, args);
}
}
#define min_heap_sift_down_inline(_heap, _pos, _func, _args) \
__min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \
__minheap_obj_size(_heap), _func, _args)
/* Sift up ith element from the heap, O(log2(nr)). */
static __always_inline
void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx,
const struct min_heap_callbacks *func, void *args)
{
const unsigned long lsbit = elem_size & -elem_size;
void *data = heap->data;
void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
/* pre-scale counters for performance */
size_t a = idx * elem_size, b;
if (!swp)
swp = select_swap_func(data, elem_size);
while (a) {
b = parent(a, lsbit, elem_size);
if (func->less(data + b, data + a, args))
break;
do_swap(data + a, data + b, elem_size, swp, args);
a = b;
}
}
#define min_heap_sift_up_inline(_heap, _idx, _func, _args) \
__min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _idx, _func, _args)
/* Floyd's approach to heapification that is O(nr). */
static __always_inline
void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size,
const struct min_heap_callbacks *func, void *args)
{
ssize_t i;
for (i = heap->nr / 2 - 1; i >= 0; i--) __min_heap_sift_down_inline(heap, i, elem_size, func, args);
}
#define min_heapify_all_inline(_heap, _func, _args) \
__min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _func, _args)
/* Remove minimum element from the heap, O(log2(nr)). */
static __always_inline
bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size,
const struct min_heap_callbacks *func, void *args)
{
void *data = heap->data;
if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
return false;
/* Place last element at the root (position 0) and then sift down. */
heap->nr--;
memcpy(data, data + (heap->nr * elem_size), elem_size);
__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
return true;
}
#define min_heap_pop_inline(_heap, _func, _args) \
__min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _func, _args)
/*
* Remove the minimum element and then push the given element. The
* implementation performs 1 sift (O(log2(nr))) and is therefore more
* efficient than a pop followed by a push that does 2.
*/
static __always_inline
void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
const struct min_heap_callbacks *func, void *args)
{
memcpy(heap->data, element, elem_size);
__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
}
#define min_heap_pop_push_inline(_heap, _element, _func, _args) \
__min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \
__minheap_obj_size(_heap), _func, _args)
/* Push an element on to the heap, O(log2(nr)). */
static __always_inline
bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
const struct min_heap_callbacks *func, void *args)
{
void *data = heap->data;
size_t pos;
if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap"))
return false;
/* Place at the end of data. */
pos = heap->nr;
memcpy(data + (pos * elem_size), element, elem_size);
heap->nr++;
/* Sift child at pos up. */
__min_heap_sift_up_inline(heap, elem_size, pos, func, args);
return true;
}
#define min_heap_push_inline(_heap, _element, _func, _args) \
__min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \
__minheap_obj_size(_heap), _func, _args)
/* Remove ith element from the heap, O(log2(nr)). */
static __always_inline
bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx,
const struct min_heap_callbacks *func, void *args)
{
void *data = heap->data;
void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
return false;
if (!swp)
swp = select_swap_func(data, elem_size);
/* Place last element at the root (position 0) and then sift down. */
heap->nr--;
if (idx == heap->nr)
return true;
do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args);
__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
__min_heap_sift_down_inline(heap, idx, elem_size, func, args);
return true;
}
#define min_heap_del_inline(_heap, _idx, _func, _args) \
__min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _idx, _func, _args)
void __min_heap_init(min_heap_char *heap, void *data, size_t size);
void *__min_heap_peek(struct min_heap_char *heap);
bool __min_heap_full(min_heap_char *heap);
void __min_heap_sift_down(min_heap_char *heap, size_t pos, size_t elem_size,
const struct min_heap_callbacks *func, void *args);
void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
const struct min_heap_callbacks *func, void *args);
void __min_heapify_all(min_heap_char *heap, size_t elem_size,
const struct min_heap_callbacks *func, void *args);
bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
const struct min_heap_callbacks *func, void *args);
void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size,
const struct min_heap_callbacks *func, void *args);
bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
const struct min_heap_callbacks *func, void *args);
bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
const struct min_heap_callbacks *func, void *args);
#define min_heap_init(_heap, _data, _size) \
__min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
#define min_heap_peek(_heap) \
(__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr)))
#define min_heap_full(_heap) \
__min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr))
#define min_heap_sift_down(_heap, _pos, _func, _args) \
__min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \
__minheap_obj_size(_heap), _func, _args)
#define min_heap_sift_up(_heap, _idx, _func, _args) \
__min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _idx, _func, _args)
#define min_heapify_all(_heap, _func, _args) \
__min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _func, _args)
#define min_heap_pop(_heap, _func, _args) \
__min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _func, _args)
#define min_heap_pop_push(_heap, _element, _func, _args) \
__min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \
__minheap_obj_size(_heap), _func, _args)
#define min_heap_push(_heap, _element, _func, _args) \
__min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \
__minheap_obj_size(_heap), _func, _args)
#define min_heap_del(_heap, _idx, _func, _args) \
__min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr), \
__minheap_obj_size(_heap), _idx, _func, _args)
#endif /* _LINUX_MIN_HEAP_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/locks.c
*
* We implement four types of file locks: BSD locks, posix locks, open
* file description locks, and leases. For details about BSD locks,
* see the flock(2) man page; for details about the other three, see
* fcntl(2).
*
*
* Locking conflicts and dependencies:
* If multiple threads attempt to lock the same byte (or flock the same file)
* only one can be granted the lock, and other must wait their turn.
* The first lock has been "applied" or "granted", the others are "waiting"
* and are "blocked" by the "applied" lock..
*
* Waiting and applied locks are all kept in trees whose properties are:
*
* - the root of a tree may be an applied or waiting lock.
* - every other node in the tree is a waiting lock that
* conflicts with every ancestor of that node.
*
* Every such tree begins life as a waiting singleton which obviously
* satisfies the above properties.
*
* The only ways we modify trees preserve these properties:
*
* 1. We may add a new leaf node, but only after first verifying that it
* conflicts with all of its ancestors.
* 2. We may remove the root of a tree, creating a new singleton
* tree from the root and N new trees rooted in the immediate
* children.
* 3. If the root of a tree is not currently an applied lock, we may
* apply it (if possible).
* 4. We may upgrade the root of the tree (either extend its range,
* or upgrade its entire range from read to write).
*
* When an applied lock is modified in a way that reduces or downgrades any
* part of its range, we remove all its children (2 above). This particularly
* happens when a lock is unlocked.
*
* For each of those child trees we "wake up" the thread which is
* waiting for the lock so it can continue handling as follows: if the
* root of the tree applies, we do so (3). If it doesn't, it must
* conflict with some applied lock. We remove (wake up) all of its children
* (2), and add it is a new leaf to the tree rooted in the applied
* lock (1). We then repeat the process recursively with those
* children.
*
*/
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/filelock.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/time.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/hashtable.h>
#include <linux/percpu.h>
#include <linux/sysctl.h>
#define CREATE_TRACE_POINTS
#include <trace/events/filelock.h>
#include <linux/uaccess.h>
static struct file_lock *file_lock(struct file_lock_core *flc)
{
return container_of(flc, struct file_lock, c);
}
static struct file_lease *file_lease(struct file_lock_core *flc)
{
return container_of(flc, struct file_lease, c);
}
static bool lease_breaking(struct file_lease *fl)
{
return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
}
static int target_leasetype(struct file_lease *fl)
{
if (fl->c.flc_flags & FL_UNLOCK_PENDING)
return F_UNLCK;
if (fl->c.flc_flags & FL_DOWNGRADE_PENDING)
return F_RDLCK;
return fl->c.flc_type;
}
static int leases_enable = 1;
static int lease_break_time = 45;
#ifdef CONFIG_SYSCTL
static const struct ctl_table locks_sysctls[] = {
{
.procname = "leases-enable",
.data = &leases_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_MMU
{
.procname = "lease-break-time",
.data = &lease_break_time,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_MMU */
};
static int __init init_fs_locks_sysctls(void)
{
register_sysctl_init("fs", locks_sysctls);
return 0;
}
early_initcall(init_fs_locks_sysctls);
#endif /* CONFIG_SYSCTL */
/*
* The global file_lock_list is only used for displaying /proc/locks, so we
* keep a list on each CPU, with each list protected by its own spinlock.
* Global serialization is done using file_rwsem.
*
* Note that alterations to the list also require that the relevant flc_lock is
* held.
*/
struct file_lock_list_struct {
spinlock_t lock;
struct hlist_head hlist;
};
static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list);
DEFINE_STATIC_PERCPU_RWSEM(file_rwsem);
/*
* The blocked_hash is used to find POSIX lock loops for deadlock detection.
* It is protected by blocked_lock_lock.
*
* We hash locks by lockowner in order to optimize searching for the lock a
* particular lockowner is waiting on.
*
* FIXME: make this value scale via some heuristic? We generally will want more
* buckets when we have more lockowners holding locks, but that's a little
* difficult to determine without knowing what the workload will look like.
*/
#define BLOCKED_HASH_BITS 7
static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
/*
* This lock protects the blocked_hash. Generally, if you're accessing it, you
* want to be holding this lock.
*
* In addition, it also protects the fl->fl_blocked_requests list, and the
* fl->fl_blocker pointer for file_lock structures that are acting as lock
* requests (in contrast to those that are acting as records of acquired locks).
*
* Note that when we acquire this lock in order to change the above fields,
* we often hold the flc_lock as well. In certain cases, when reading the fields
* protected by this lock, we can skip acquiring it iff we already hold the
* flc_lock.
*/
static DEFINE_SPINLOCK(blocked_lock_lock);
static struct kmem_cache *flctx_cache __ro_after_init;
static struct kmem_cache *filelock_cache __ro_after_init;
static struct kmem_cache *filelease_cache __ro_after_init;
static struct file_lock_context *
locks_get_lock_context(struct inode *inode, int type)
{
struct file_lock_context *ctx;
/* paired with cmpxchg() below */
ctx = locks_inode_context(inode);
if (likely(ctx) || type == F_UNLCK)
goto out;
ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL);
if (!ctx)
goto out;
spin_lock_init(&ctx->flc_lock);
INIT_LIST_HEAD(&ctx->flc_flock);
INIT_LIST_HEAD(&ctx->flc_posix);
INIT_LIST_HEAD(&ctx->flc_lease);
/*
* Assign the pointer if it's not already assigned. If it is, then
* free the context we just allocated.
*/
if (cmpxchg(&inode->i_flctx, NULL, ctx)) {
kmem_cache_free(flctx_cache, ctx);
ctx = locks_inode_context(inode);
}
out:
trace_locks_get_lock_context(inode, type, ctx);
return ctx;
}
static void
locks_dump_ctx_list(struct list_head *list, char *list_type)
{
struct file_lock_core *flc;
list_for_each_entry(flc, list, flc_list)
pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
list_type, flc->flc_owner, flc->flc_flags,
flc->flc_type, flc->flc_pid);
}
static void
locks_check_ctx_lists(struct inode *inode)
{
struct file_lock_context *ctx = inode->i_flctx;
if (unlikely(!list_empty(&ctx->flc_flock) ||
!list_empty(&ctx->flc_posix) ||
!list_empty(&ctx->flc_lease))) {
pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n",
MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
inode->i_ino);
locks_dump_ctx_list(&ctx->flc_flock, "FLOCK");
locks_dump_ctx_list(&ctx->flc_posix, "POSIX");
locks_dump_ctx_list(&ctx->flc_lease, "LEASE");
}
}
static void
locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type)
{
struct file_lock_core *flc;
struct inode *inode = file_inode(filp);
list_for_each_entry(flc, list, flc_list) if (flc->flc_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx "
" fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
list_type, MAJOR(inode->i_sb->s_dev),
MINOR(inode->i_sb->s_dev), inode->i_ino,
flc->flc_owner, flc->flc_flags,
flc->flc_type, flc->flc_pid);
}
void
locks_free_lock_context(struct inode *inode)
{ struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) {
locks_check_ctx_lists(inode);
kmem_cache_free(flctx_cache, ctx);
}
}
static void locks_init_lock_heads(struct file_lock_core *flc)
{
INIT_HLIST_NODE(&flc->flc_link);
INIT_LIST_HEAD(&flc->flc_list);
INIT_LIST_HEAD(&flc->flc_blocked_requests);
INIT_LIST_HEAD(&flc->flc_blocked_member);
init_waitqueue_head(&flc->flc_wait);
}
/* Allocate an empty lock structure. */
struct file_lock *locks_alloc_lock(void)
{
struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL);
if (fl)
locks_init_lock_heads(&fl->c);
return fl;
}
EXPORT_SYMBOL_GPL(locks_alloc_lock);
/* Allocate an empty lock structure. */
struct file_lease *locks_alloc_lease(void)
{
struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL);
if (fl)
locks_init_lock_heads(&fl->c);
return fl;
}
EXPORT_SYMBOL_GPL(locks_alloc_lease);
void locks_release_private(struct file_lock *fl)
{
struct file_lock_core *flc = &fl->c;
BUG_ON(waitqueue_active(&flc->flc_wait));
BUG_ON(!list_empty(&flc->flc_list));
BUG_ON(!list_empty(&flc->flc_blocked_requests));
BUG_ON(!list_empty(&flc->flc_blocked_member));
BUG_ON(!hlist_unhashed(&flc->flc_link));
if (fl->fl_ops) {
if (fl->fl_ops->fl_release_private)
fl->fl_ops->fl_release_private(fl);
fl->fl_ops = NULL;
}
if (fl->fl_lmops) {
if (fl->fl_lmops->lm_put_owner) {
fl->fl_lmops->lm_put_owner(flc->flc_owner);
flc->flc_owner = NULL;
}
fl->fl_lmops = NULL;
}
}
EXPORT_SYMBOL_GPL(locks_release_private);
/**
* locks_owner_has_blockers - Check for blocking lock requests
* @flctx: file lock context
* @owner: lock owner
*
* Return values:
* %true: @owner has at least one blocker
* %false: @owner has no blockers
*/
bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner)
{
struct file_lock_core *flc;
spin_lock(&flctx->flc_lock);
list_for_each_entry(flc, &flctx->flc_posix, flc_list) {
if (flc->flc_owner != owner)
continue;
if (!list_empty(&flc->flc_blocked_requests)) {
spin_unlock(&flctx->flc_lock);
return true;
}
}
spin_unlock(&flctx->flc_lock);
return false;
}
EXPORT_SYMBOL_GPL(locks_owner_has_blockers);
/* Free a lock which is not in use. */
void locks_free_lock(struct file_lock *fl)
{
locks_release_private(fl);
kmem_cache_free(filelock_cache, fl);
}
EXPORT_SYMBOL(locks_free_lock);
/* Free a lease which is not in use. */
void locks_free_lease(struct file_lease *fl)
{
kmem_cache_free(filelease_cache, fl);
}
EXPORT_SYMBOL(locks_free_lease);
static void
locks_dispose_list(struct list_head *dispose)
{
struct file_lock_core *flc;
while (!list_empty(dispose)) {
flc = list_first_entry(dispose, struct file_lock_core, flc_list);
list_del_init(&flc->flc_list);
if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
locks_free_lease(file_lease(flc));
else
locks_free_lock(file_lock(flc));
}
}
void locks_init_lock(struct file_lock *fl)
{
memset(fl, 0, sizeof(struct file_lock));
locks_init_lock_heads(&fl->c);
}
EXPORT_SYMBOL(locks_init_lock);
void locks_init_lease(struct file_lease *fl)
{
memset(fl, 0, sizeof(*fl));
locks_init_lock_heads(&fl->c);
}
EXPORT_SYMBOL(locks_init_lease);
/*
* Initialize a new lock from an existing file_lock structure.
*/
void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
new->c.flc_owner = fl->c.flc_owner;
new->c.flc_pid = fl->c.flc_pid;
new->c.flc_file = NULL;
new->c.flc_flags = fl->c.flc_flags;
new->c.flc_type = fl->c.flc_type;
new->fl_start = fl->fl_start;
new->fl_end = fl->fl_end;
new->fl_lmops = fl->fl_lmops;
new->fl_ops = NULL;
if (fl->fl_lmops) {
if (fl->fl_lmops->lm_get_owner)
fl->fl_lmops->lm_get_owner(fl->c.flc_owner);
}
}
EXPORT_SYMBOL(locks_copy_conflock);
void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
/* "new" must be a freshly-initialized lock */
WARN_ON_ONCE(new->fl_ops);
locks_copy_conflock(new, fl);
new->c.flc_file = fl->c.flc_file;
new->fl_ops = fl->fl_ops;
if (fl->fl_ops) {
if (fl->fl_ops->fl_copy_lock)
fl->fl_ops->fl_copy_lock(new, fl);
}
}
EXPORT_SYMBOL(locks_copy_lock);
static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
{
struct file_lock *f;
/*
* As ctx->flc_lock is held, new requests cannot be added to
* ->flc_blocked_requests, so we don't need a lock to check if it
* is empty.
*/
if (list_empty(&fl->c.flc_blocked_requests))
return;
spin_lock(&blocked_lock_lock);
list_splice_init(&fl->c.flc_blocked_requests,
&new->c.flc_blocked_requests);
list_for_each_entry(f, &new->c.flc_blocked_requests,
c.flc_blocked_member)
f->c.flc_blocker = &new->c;
spin_unlock(&blocked_lock_lock);
}
static inline int flock_translate_cmd(int cmd) {
switch (cmd) {
case LOCK_SH:
return F_RDLCK;
case LOCK_EX:
return F_WRLCK;
case LOCK_UN:
return F_UNLCK;
}
return -EINVAL;
}
/* Fill in a file_lock structure with an appropriate FLOCK lock. */
static void flock_make_lock(struct file *filp, struct file_lock *fl, int type)
{
locks_init_lock(fl);
fl->c.flc_file = filp;
fl->c.flc_owner = filp;
fl->c.flc_pid = current->tgid;
fl->c.flc_flags = FL_FLOCK;
fl->c.flc_type = type;
fl->fl_end = OFFSET_MAX;
}
static int assign_type(struct file_lock_core *flc, int type)
{
switch (type) {
case F_RDLCK:
case F_WRLCK:
case F_UNLCK:
flc->flc_type = type;
break;
default:
return -EINVAL;
}
return 0;
}
static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
struct flock64 *l)
{
switch (l->l_whence) {
case SEEK_SET:
fl->fl_start = 0;
break;
case SEEK_CUR:
fl->fl_start = filp->f_pos;
break;
case SEEK_END:
fl->fl_start = i_size_read(file_inode(filp));
break;
default:
return -EINVAL;
}
if (l->l_start > OFFSET_MAX - fl->fl_start)
return -EOVERFLOW;
fl->fl_start += l->l_start;
if (fl->fl_start < 0)
return -EINVAL;
/* POSIX-1996 leaves the case l->l_len < 0 undefined;
POSIX-2001 defines it. */
if (l->l_len > 0) {
if (l->l_len - 1 > OFFSET_MAX - fl->fl_start)
return -EOVERFLOW;
fl->fl_end = fl->fl_start + (l->l_len - 1);
} else if (l->l_len < 0) {
if (fl->fl_start + l->l_len < 0)
return -EINVAL;
fl->fl_end = fl->fl_start - 1;
fl->fl_start += l->l_len;
} else
fl->fl_end = OFFSET_MAX;
fl->c.flc_owner = current->files;
fl->c.flc_pid = current->tgid;
fl->c.flc_file = filp;
fl->c.flc_flags = FL_POSIX;
fl->fl_ops = NULL;
fl->fl_lmops = NULL;
return assign_type(&fl->c, l->l_type);
}
/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
* style lock.
*/
static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
struct flock *l)
{
struct flock64 ll = {
.l_type = l->l_type,
.l_whence = l->l_whence,
.l_start = l->l_start,
.l_len = l->l_len,
};
return flock64_to_posix_lock(filp, fl, &ll);
}
/* default lease lock manager operations */
static bool
lease_break_callback(struct file_lease *fl)
{
kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
return false;
}
static void
lease_setup(struct file_lease *fl, void **priv)
{
struct file *filp = fl->c.flc_file;
struct fasync_struct *fa = *priv;
/*
* fasync_insert_entry() returns the old entry if any. If there was no
* old entry, then it used "priv" and inserted it into the fasync list.
* Clear the pointer to indicate that it shouldn't be freed.
*/
if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa))
*priv = NULL;
__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
}
static const struct lease_manager_operations lease_manager_ops = {
.lm_break = lease_break_callback,
.lm_change = lease_modify,
.lm_setup = lease_setup,
};
/*
* Initialize a lease, use the default lock manager operations
*/
static int lease_init(struct file *filp, int type, struct file_lease *fl)
{
if (assign_type(&fl->c, type) != 0)
return -EINVAL;
fl->c.flc_owner = filp;
fl->c.flc_pid = current->tgid;
fl->c.flc_file = filp;
fl->c.flc_flags = FL_LEASE;
fl->fl_lmops = &lease_manager_ops;
return 0;
}
/* Allocate a file_lock initialised to this type of lease */
static struct file_lease *lease_alloc(struct file *filp, int type)
{
struct file_lease *fl = locks_alloc_lease();
int error = -ENOMEM;
if (fl == NULL)
return ERR_PTR(error);
error = lease_init(filp, type, fl);
if (error) {
locks_free_lease(fl);
return ERR_PTR(error);
}
return fl;
}
/* Check if two locks overlap each other.
*/
static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
{
return ((fl1->fl_end >= fl2->fl_start) &&
(fl2->fl_end >= fl1->fl_start));
}
/*
* Check whether two locks have the same owner.
*/
static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2)
{
return fl1->flc_owner == fl2->flc_owner;
}
/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock_core *flc)
{
struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);
percpu_rwsem_assert_held(&file_rwsem);
spin_lock(&fll->lock);
flc->flc_link_cpu = smp_processor_id();
hlist_add_head(&flc->flc_link, &fll->hlist);
spin_unlock(&fll->lock);
}
/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock_core *flc)
{
struct file_lock_list_struct *fll;
percpu_rwsem_assert_held(&file_rwsem);
/*
* Avoid taking lock if already unhashed. This is safe since this check
* is done while holding the flc_lock, and new insertions into the list
* also require that it be held.
*/
if (hlist_unhashed(&flc->flc_link))
return;
fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu);
spin_lock(&fll->lock);
hlist_del_init(&flc->flc_link);
spin_unlock(&fll->lock);
}
static unsigned long
posix_owner_key(struct file_lock_core *flc)
{
return (unsigned long) flc->flc_owner;
}
static void locks_insert_global_blocked(struct file_lock_core *waiter)
{
lockdep_assert_held(&blocked_lock_lock);
hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter));
}
static void locks_delete_global_blocked(struct file_lock_core *waiter)
{
lockdep_assert_held(&blocked_lock_lock);
hash_del(&waiter->flc_link);
}
/* Remove waiter from blocker's block list.
* When blocker ends up pointing to itself then the list is empty.
*
* Must be called with blocked_lock_lock held.
*/
static void __locks_unlink_block(struct file_lock_core *waiter)
{
locks_delete_global_blocked(waiter);
list_del_init(&waiter->flc_blocked_member);
}
static void __locks_wake_up_blocks(struct file_lock_core *blocker)
{
while (!list_empty(&blocker->flc_blocked_requests)) {
struct file_lock_core *waiter;
struct file_lock *fl;
waiter = list_first_entry(&blocker->flc_blocked_requests,
struct file_lock_core, flc_blocked_member);
fl = file_lock(waiter);
__locks_unlink_block(waiter);
if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) &&
fl->fl_lmops && fl->fl_lmops->lm_notify)
fl->fl_lmops->lm_notify(fl);
else
locks_wake_up(fl);
/*
* The setting of flc_blocker to NULL marks the "done"
* point in deleting a block. Paired with acquire at the top
* of locks_delete_block().
*/
smp_store_release(&waiter->flc_blocker, NULL);
}
}
static int __locks_delete_block(struct file_lock_core *waiter)
{
int status = -ENOENT;
/*
* If fl_blocker is NULL, it won't be set again as this thread "owns"
* the lock and is the only one that might try to claim the lock.
*
* We use acquire/release to manage fl_blocker so that we can
* optimize away taking the blocked_lock_lock in many cases.
*
* The smp_load_acquire guarantees two things:
*
* 1/ that fl_blocked_requests can be tested locklessly. If something
* was recently added to that list it must have been in a locked region
* *before* the locked region when fl_blocker was set to NULL.
*
* 2/ that no other thread is accessing 'waiter', so it is safe to free
* it. __locks_wake_up_blocks is careful not to touch waiter after
* fl_blocker is released.
*
* If a lockless check of fl_blocker shows it to be NULL, we know that
* no new locks can be inserted into its fl_blocked_requests list, and
* can avoid doing anything further if the list is empty.
*/
if (!smp_load_acquire(&waiter->flc_blocker) &&
list_empty(&waiter->flc_blocked_requests))
return status;
spin_lock(&blocked_lock_lock);
if (waiter->flc_blocker)
status = 0;
__locks_wake_up_blocks(waiter);
__locks_unlink_block(waiter);
/*
* The setting of fl_blocker to NULL marks the "done" point in deleting
* a block. Paired with acquire at the top of this function.
*/
smp_store_release(&waiter->flc_blocker, NULL);
spin_unlock(&blocked_lock_lock);
return status;
}
/**
* locks_delete_block - stop waiting for a file lock
* @waiter: the lock which was waiting
*
* lockd/nfsd need to disconnect the lock while working on it.
*/
int locks_delete_block(struct file_lock *waiter)
{
return __locks_delete_block(&waiter->c);
}
EXPORT_SYMBOL(locks_delete_block);
/* Insert waiter into blocker's block list.
* We use a circular list so that processes can be easily woken up in
* the order they blocked. The documentation doesn't require this but
* it seems like the reasonable thing to do.
*
* Must be called with both the flc_lock and blocked_lock_lock held. The
* fl_blocked_requests list itself is protected by the blocked_lock_lock,
* but by ensuring that the flc_lock is also held on insertions we can avoid
* taking the blocked_lock_lock in some cases when we see that the
* fl_blocked_requests list is empty.
*
* Rather than just adding to the list, we check for conflicts with any existing
* waiters, and add beneath any waiter that blocks the new waiter.
* Thus wakeups don't happen until needed.
*/
static void __locks_insert_block(struct file_lock_core *blocker,
struct file_lock_core *waiter,
bool conflict(struct file_lock_core *,
struct file_lock_core *))
{
struct file_lock_core *flc;
BUG_ON(!list_empty(&waiter->flc_blocked_member));
new_blocker:
list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member)
if (conflict(flc, waiter)) {
blocker = flc;
goto new_blocker;
}
waiter->flc_blocker = blocker;
list_add_tail(&waiter->flc_blocked_member,
&blocker->flc_blocked_requests);
if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX)
locks_insert_global_blocked(waiter);
/* The requests in waiter->flc_blocked are known to conflict with
* waiter, but might not conflict with blocker, or the requests
* and lock which block it. So they all need to be woken.
*/
__locks_wake_up_blocks(waiter);
}
/* Must be called with flc_lock held. */
static void locks_insert_block(struct file_lock_core *blocker,
struct file_lock_core *waiter,
bool conflict(struct file_lock_core *,
struct file_lock_core *))
{
spin_lock(&blocked_lock_lock);
__locks_insert_block(blocker, waiter, conflict);
spin_unlock(&blocked_lock_lock);
}
/*
* Wake up processes blocked waiting for blocker.
*
* Must be called with the inode->flc_lock held!
*/
static void locks_wake_up_blocks(struct file_lock_core *blocker)
{
/*
* Avoid taking global lock if list is empty. This is safe since new
* blocked requests are only added to the list under the flc_lock, and
* the flc_lock is always held here. Note that removal from the
* fl_blocked_requests list does not require the flc_lock, so we must
* recheck list_empty() after acquiring the blocked_lock_lock.
*/
if (list_empty(&blocker->flc_blocked_requests))
return;
spin_lock(&blocked_lock_lock);
__locks_wake_up_blocks(blocker);
spin_unlock(&blocked_lock_lock);
}
static void
locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before)
{
list_add_tail(&fl->flc_list, before);
locks_insert_global_locks(fl);
}
static void
locks_unlink_lock_ctx(struct file_lock_core *fl)
{
locks_delete_global_locks(fl);
list_del_init(&fl->flc_list);
locks_wake_up_blocks(fl);
}
static void
locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose)
{
locks_unlink_lock_ctx(fl);
if (dispose)
list_add(&fl->flc_list, dispose);
else
locks_free_lock(file_lock(fl));
}
/* Determine if lock sys_fl blocks lock caller_fl. Common functionality
* checks for shared/exclusive status of overlapping locks.
*/
static bool locks_conflict(struct file_lock_core *caller_flc,
struct file_lock_core *sys_flc)
{
if (sys_flc->flc_type == F_WRLCK)
return true;
if (caller_flc->flc_type == F_WRLCK)
return true;
return false;
}
/* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
* checking before calling the locks_conflict().
*/
static bool posix_locks_conflict(struct file_lock_core *caller_flc,
struct file_lock_core *sys_flc)
{
struct file_lock *caller_fl = file_lock(caller_flc);
struct file_lock *sys_fl = file_lock(sys_flc);
/* POSIX locks owned by the same process do not conflict with
* each other.
*/
if (posix_same_owner(caller_flc, sys_flc))
return false;
/* Check whether they overlap */
if (!locks_overlap(caller_fl, sys_fl))
return false;
return locks_conflict(caller_flc, sys_flc);
}
/* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK
* path so checks for additional GETLK-specific things like F_UNLCK.
*/
static bool posix_test_locks_conflict(struct file_lock *caller_fl,
struct file_lock *sys_fl)
{
struct file_lock_core *caller = &caller_fl->c;
struct file_lock_core *sys = &sys_fl->c;
/* F_UNLCK checks any locks on the same fd. */
if (lock_is_unlock(caller_fl)) {
if (!posix_same_owner(caller, sys))
return false;
return locks_overlap(caller_fl, sys_fl);
}
return posix_locks_conflict(caller, sys);
}
/* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
* checking before calling the locks_conflict().
*/
static bool flock_locks_conflict(struct file_lock_core *caller_flc,
struct file_lock_core *sys_flc)
{
/* FLOCK locks referring to the same filp do not conflict with
* each other.
*/
if (caller_flc->flc_file == sys_flc->flc_file)
return false;
return locks_conflict(caller_flc, sys_flc);
}
void
posix_test_lock(struct file *filp, struct file_lock *fl)
{
struct file_lock *cfl;
struct file_lock_context *ctx;
struct inode *inode = file_inode(filp);
void *owner;
void (*func)(void);
ctx = locks_inode_context(inode);
if (!ctx || list_empty_careful(&ctx->flc_posix)) {
fl->c.flc_type = F_UNLCK;
return;
}
retry:
spin_lock(&ctx->flc_lock);
list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) {
if (!posix_test_locks_conflict(fl, cfl))
continue;
if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
&& (*cfl->fl_lmops->lm_lock_expirable)(cfl)) {
owner = cfl->fl_lmops->lm_mod_owner;
func = cfl->fl_lmops->lm_expire_lock;
__module_get(owner);
spin_unlock(&ctx->flc_lock);
(*func)();
module_put(owner);
goto retry;
}
locks_copy_conflock(fl, cfl);
goto out;
}
fl->c.flc_type = F_UNLCK;
out:
spin_unlock(&ctx->flc_lock);
return;
}
EXPORT_SYMBOL(posix_test_lock);
/*
* Deadlock detection:
*
* We attempt to detect deadlocks that are due purely to posix file
* locks.
*
* We assume that a task can be waiting for at most one lock at a time.
* So for any acquired lock, the process holding that lock may be
* waiting on at most one other lock. That lock in turns may be held by
* someone waiting for at most one other lock. Given a requested lock
* caller_fl which is about to wait for a conflicting lock block_fl, we
* follow this chain of waiters to ensure we are not about to create a
* cycle.
*
* Since we do this before we ever put a process to sleep on a lock, we
* are ensured that there is never a cycle; that is what guarantees that
* the while() loop in posix_locks_deadlock() eventually completes.
*
* Note: the above assumption may not be true when handling lock
* requests from a broken NFS client. It may also fail in the presence
* of tasks (such as posix threads) sharing the same open file table.
* To handle those cases, we just bail out after a few iterations.
*
* For FL_OFDLCK locks, the owner is the filp, not the files_struct.
* Because the owner is not even nominally tied to a thread of
* execution, the deadlock detection below can't reasonably work well. Just
* skip it for those.
*
* In principle, we could do a more limited deadlock detection on FL_OFDLCK
* locks that just checks for the case where two tasks are attempting to
* upgrade from read to write locks on the same inode.
*/
#define MAX_DEADLK_ITERATIONS 10
/* Find a lock that the owner of the given @blocker is blocking on. */
static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker)
{
struct file_lock_core *flc;
hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) {
if (posix_same_owner(flc, blocker)) {
while (flc->flc_blocker)
flc = flc->flc_blocker;
return flc;
}
}
return NULL;
}
/* Must be called with the blocked_lock_lock held! */
static bool posix_locks_deadlock(struct file_lock *caller_fl,
struct file_lock *block_fl)
{
struct file_lock_core *caller = &caller_fl->c;
struct file_lock_core *blocker = &block_fl->c;
int i = 0;
lockdep_assert_held(&blocked_lock_lock);
/*
* This deadlock detector can't reasonably detect deadlocks with
* FL_OFDLCK locks, since they aren't owned by a process, per-se.
*/
if (caller->flc_flags & FL_OFDLCK)
return false;
while ((blocker = what_owner_is_waiting_for(blocker))) {
if (i++ > MAX_DEADLK_ITERATIONS)
return false;
if (posix_same_owner(caller, blocker))
return true;
}
return false;
}
/* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
* after any leases, but before any posix locks.
*
* Note that if called with an FL_EXISTS argument, the caller may determine
* whether or not a lock was successfully freed by testing the return
* value for -ENOENT.
*/
static int flock_lock_inode(struct inode *inode, struct file_lock *request)
{
struct file_lock *new_fl = NULL;
struct file_lock *fl;
struct file_lock_context *ctx;
int error = 0;
bool found = false;
LIST_HEAD(dispose);
ctx = locks_get_lock_context(inode, request->c.flc_type);
if (!ctx) {
if (request->c.flc_type != F_UNLCK)
return -ENOMEM;
return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0;
}
if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) {
new_fl = locks_alloc_lock();
if (!new_fl)
return -ENOMEM;
}
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
if (request->c.flc_flags & FL_ACCESS)
goto find_conflict;
list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
if (request->c.flc_file != fl->c.flc_file)
continue;
if (request->c.flc_type == fl->c.flc_type)
goto out;
found = true;
locks_delete_lock_ctx(&fl->c, &dispose);
break;
}
if (lock_is_unlock(request)) {
if ((request->c.flc_flags & FL_EXISTS) && !found)
error = -ENOENT;
goto out;
}
find_conflict:
list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
if (!flock_locks_conflict(&request->c, &fl->c))
continue;
error = -EAGAIN;
if (!(request->c.flc_flags & FL_SLEEP))
goto out;
error = FILE_LOCK_DEFERRED;
locks_insert_block(&fl->c, &request->c, flock_locks_conflict);
goto out;
}
if (request->c.flc_flags & FL_ACCESS)
goto out;
locks_copy_lock(new_fl, request);
locks_move_blocks(new_fl, request);
locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock);
new_fl = NULL;
error = 0;
out:
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
if (new_fl)
locks_free_lock(new_fl);
locks_dispose_list(&dispose);
trace_flock_lock_inode(inode, request, error);
return error;
}
static int posix_lock_inode(struct inode *inode, struct file_lock *request,
struct file_lock *conflock)
{
struct file_lock *fl, *tmp;
struct file_lock *new_fl = NULL;
struct file_lock *new_fl2 = NULL;
struct file_lock *left = NULL;
struct file_lock *right = NULL;
struct file_lock_context *ctx;
int error;
bool added = false;
LIST_HEAD(dispose);
void *owner;
void (*func)(void);
ctx = locks_get_lock_context(inode, request->c.flc_type);
if (!ctx)
return lock_is_unlock(request) ? 0 : -ENOMEM;
/*
* We may need two file_lock structures for this operation,
* so we get them in advance to avoid races.
*
* In some cases we can be sure, that no new locks will be needed
*/
if (!(request->c.flc_flags & FL_ACCESS) &&
(request->c.flc_type != F_UNLCK ||
request->fl_start != 0 || request->fl_end != OFFSET_MAX)) {
new_fl = locks_alloc_lock();
new_fl2 = locks_alloc_lock();
}
retry:
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
* there are any, either return error or put the request on the
* blocker's list of waiters and the global blocked_hash.
*/
if (request->c.flc_type != F_UNLCK) {
list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
if (!posix_locks_conflict(&request->c, &fl->c))
continue;
if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
owner = fl->fl_lmops->lm_mod_owner;
func = fl->fl_lmops->lm_expire_lock;
__module_get(owner);
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
(*func)();
module_put(owner);
goto retry;
}
if (conflock)
locks_copy_conflock(conflock, fl);
error = -EAGAIN;
if (!(request->c.flc_flags & FL_SLEEP))
goto out;
/*
* Deadlock detection and insertion into the blocked
* locks list must be done while holding the same lock!
*/
error = -EDEADLK;
spin_lock(&blocked_lock_lock);
/*
* Ensure that we don't find any locks blocked on this
* request during deadlock detection.
*/
__locks_wake_up_blocks(&request->c);
if (likely(!posix_locks_deadlock(request, fl))) {
error = FILE_LOCK_DEFERRED;
__locks_insert_block(&fl->c, &request->c,
posix_locks_conflict);
}
spin_unlock(&blocked_lock_lock);
goto out;
}
}
/* If we're just looking for a conflict, we're done. */
error = 0;
if (request->c.flc_flags & FL_ACCESS)
goto out;
/* Find the first old lock with the same owner as the new lock */
list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
if (posix_same_owner(&request->c, &fl->c))
break;
}
/* Process locks with this owner. */
list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) {
if (!posix_same_owner(&request->c, &fl->c))
break;
/* Detect adjacent or overlapping regions (if same lock type) */
if (request->c.flc_type == fl->c.flc_type) {
/* In all comparisons of start vs end, use
* "start - 1" rather than "end + 1". If end
* is OFFSET_MAX, end + 1 will become negative.
*/
if (fl->fl_end < request->fl_start - 1)
continue;
/* If the next lock in the list has entirely bigger
* addresses than the new one, insert the lock here.
*/
if (fl->fl_start - 1 > request->fl_end)
break;
/* If we come here, the new and old lock are of the
* same type and adjacent or overlapping. Make one
* lock yielding from the lower start address of both
* locks to the higher end address.
*/
if (fl->fl_start > request->fl_start)
fl->fl_start = request->fl_start;
else
request->fl_start = fl->fl_start;
if (fl->fl_end < request->fl_end)
fl->fl_end = request->fl_end;
else
request->fl_end = fl->fl_end;
if (added) {
locks_delete_lock_ctx(&fl->c, &dispose);
continue;
}
request = fl;
added = true;
} else {
/* Processing for different lock types is a bit
* more complex.
*/
if (fl->fl_end < request->fl_start)
continue;
if (fl->fl_start > request->fl_end)
break;
if (lock_is_unlock(request))
added = true;
if (fl->fl_start < request->fl_start)
left = fl;
/* If the next lock in the list has a higher end
* address than the new one, insert the new one here.
*/
if (fl->fl_end > request->fl_end) {
right = fl;
break;
}
if (fl->fl_start >= request->fl_start) {
/* The new lock completely replaces an old
* one (This may happen several times).
*/
if (added) {
locks_delete_lock_ctx(&fl->c, &dispose);
continue;
}
/*
* Replace the old lock with new_fl, and
* remove the old one. It's safe to do the
* insert here since we know that we won't be
* using new_fl later, and that the lock is
* just replacing an existing lock.
*/
error = -ENOLCK;
if (!new_fl)
goto out;
locks_copy_lock(new_fl, request);
locks_move_blocks(new_fl, request);
request = new_fl;
new_fl = NULL;
locks_insert_lock_ctx(&request->c,
&fl->c.flc_list);
locks_delete_lock_ctx(&fl->c, &dispose);
added = true;
}
}
}
/*
* The above code only modifies existing locks in case of merging or
* replacing. If new lock(s) need to be inserted all modifications are
* done below this, so it's safe yet to bail out.
*/
error = -ENOLCK; /* "no luck" */
if (right && left == right && !new_fl2)
goto out;
error = 0;
if (!added) {
if (lock_is_unlock(request)) {
if (request->c.flc_flags & FL_EXISTS)
error = -ENOENT;
goto out;
}
if (!new_fl) {
error = -ENOLCK;
goto out;
}
locks_copy_lock(new_fl, request);
locks_move_blocks(new_fl, request);
locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list);
fl = new_fl;
new_fl = NULL;
}
if (right) {
if (left == right) {
/* The new lock breaks the old one in two pieces,
* so we have to use the second new lock.
*/
left = new_fl2;
new_fl2 = NULL;
locks_copy_lock(left, right);
locks_insert_lock_ctx(&left->c, &fl->c.flc_list);
}
right->fl_start = request->fl_end + 1;
locks_wake_up_blocks(&right->c);
}
if (left) {
left->fl_end = request->fl_start - 1;
locks_wake_up_blocks(&left->c);
}
out:
trace_posix_lock_inode(inode, request, error);
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
/*
* Free any unused locks.
*/
if (new_fl)
locks_free_lock(new_fl);
if (new_fl2)
locks_free_lock(new_fl2);
locks_dispose_list(&dispose);
return error;
}
/**
* posix_lock_file - Apply a POSIX-style lock to a file
* @filp: The file to apply the lock to
* @fl: The lock to be applied
* @conflock: Place to return a copy of the conflicting lock, if found.
*
* Add a POSIX style lock to a file.
* We merge adjacent & overlapping locks whenever possible.
* POSIX locks are sorted by owner task, then by starting address
*
* Note that if called with an FL_EXISTS argument, the caller may determine
* whether or not a lock was successfully freed by testing the return
* value for -ENOENT.
*/
int posix_lock_file(struct file *filp, struct file_lock *fl,
struct file_lock *conflock)
{
return posix_lock_inode(file_inode(filp), fl, conflock);
}
EXPORT_SYMBOL(posix_lock_file);
/**
* posix_lock_inode_wait - Apply a POSIX-style lock to a file
* @inode: inode of file to which lock request should be applied
* @fl: The lock to be applied
*
* Apply a POSIX style lock request to an inode.
*/
static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
int error;
might_sleep ();
for (;;) {
error = posix_lock_inode(inode, fl, NULL);
if (error != FILE_LOCK_DEFERRED)
break;
error = wait_event_interruptible(fl->c.flc_wait,
list_empty(&fl->c.flc_blocked_member));
if (error)
break;
}
locks_delete_block(fl);
return error;
}
static void lease_clear_pending(struct file_lease *fl, int arg)
{
switch (arg) {
case F_UNLCK:
fl->c.flc_flags &= ~FL_UNLOCK_PENDING;
fallthrough;
case F_RDLCK:
fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING;
}
}
/* We already had a lease on this file; just change its type */
int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose)
{
int error = assign_type(&fl->c, arg);
if (error)
return error;
lease_clear_pending(fl, arg);
locks_wake_up_blocks(&fl->c);
if (arg == F_UNLCK) {
struct file *filp = fl->c.flc_file;
f_delown(filp);
file_f_owner(filp)->signum = 0;
fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync);
if (fl->fl_fasync != NULL) {
printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
fl->fl_fasync = NULL;
}
locks_delete_lock_ctx(&fl->c, dispose);
}
return 0;
}
EXPORT_SYMBOL(lease_modify);
static bool past_time(unsigned long then)
{
if (!then)
/* 0 is a special value meaning "this never expires": */
return false;
return time_after(jiffies, then);
}
static void time_out_leases(struct inode *inode, struct list_head *dispose)
{
struct file_lock_context *ctx = inode->i_flctx;
struct file_lease *fl, *tmp;
lockdep_assert_held(&ctx->flc_lock);
list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
trace_time_out_leases(inode, fl);
if (past_time(fl->fl_downgrade_time))
lease_modify(fl, F_RDLCK, dispose);
if (past_time(fl->fl_break_time))
lease_modify(fl, F_UNLCK, dispose);
}
}
static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc)
{
bool rc;
struct file_lease *lease = file_lease(lc);
struct file_lease *breaker = file_lease(bc);
if (lease->fl_lmops->lm_breaker_owns_lease
&& lease->fl_lmops->lm_breaker_owns_lease(lease))
return false;
if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) {
rc = false;
goto trace;
}
if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) {
rc = false;
goto trace;
}
rc = locks_conflict(bc, lc);
trace:
trace_leases_conflict(rc, lease, breaker);
return rc;
}
static bool
any_leases_conflict(struct inode *inode, struct file_lease *breaker)
{
struct file_lock_context *ctx = inode->i_flctx;
struct file_lock_core *flc;
lockdep_assert_held(&ctx->flc_lock);
list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
if (leases_conflict(flc, &breaker->c))
return true;
}
return false;
}
/**
* __break_lease - revoke all outstanding leases on file
* @inode: the inode of the file to return
* @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
* break all leases
* @type: FL_LEASE: break leases and delegations; FL_DELEG: break
* only delegations
*
* break_lease (inlined for speed) has checked there already is at least
* some kind of lock (maybe a lease) on this file. Leases are broken on
* a call to open() or truncate(). This function can sleep unless you
* specified %O_NONBLOCK to your open().
*/
int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
int error = 0;
struct file_lock_context *ctx;
struct file_lease *new_fl, *fl, *tmp;
unsigned long break_time;
int want_write = (mode & O_ACCMODE) != O_RDONLY;
LIST_HEAD(dispose);
new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
if (IS_ERR(new_fl))
return PTR_ERR(new_fl);
new_fl->c.flc_flags = type;
/* typically we will check that ctx is non-NULL before calling */
ctx = locks_inode_context(inode);
if (!ctx) {
WARN_ON_ONCE(1);
goto free_lock;
}
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
if (!any_leases_conflict(inode, new_fl))
goto out;
break_time = 0;
if (lease_break_time > 0) {
break_time = jiffies + lease_break_time * HZ;
if (break_time == 0)
break_time++; /* so that 0 means no break time */
}
list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
if (!leases_conflict(&fl->c, &new_fl->c))
continue;
if (want_write) {
if (fl->c.flc_flags & FL_UNLOCK_PENDING)
continue;
fl->c.flc_flags |= FL_UNLOCK_PENDING;
fl->fl_break_time = break_time;
} else {
if (lease_breaking(fl))
continue;
fl->c.flc_flags |= FL_DOWNGRADE_PENDING;
fl->fl_downgrade_time = break_time;
}
if (fl->fl_lmops->lm_break(fl))
locks_delete_lock_ctx(&fl->c, &dispose);
}
if (list_empty(&ctx->flc_lease))
goto out;
if (mode & O_NONBLOCK) {
trace_break_lease_noblock(inode, new_fl);
error = -EWOULDBLOCK;
goto out;
}
restart:
fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list);
break_time = fl->fl_break_time;
if (break_time != 0)
break_time -= jiffies;
if (break_time == 0)
break_time++;
locks_insert_block(&fl->c, &new_fl->c, leases_conflict);
trace_break_lease_block(inode, new_fl);
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
error = wait_event_interruptible_timeout(new_fl->c.flc_wait,
list_empty(&new_fl->c.flc_blocked_member),
break_time);
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
trace_break_lease_unblock(inode, new_fl);
__locks_delete_block(&new_fl->c);
if (error >= 0) {
/*
* Wait for the next conflicting lease that has not been
* broken yet
*/
if (error == 0)
time_out_leases(inode, &dispose);
if (any_leases_conflict(inode, new_fl))
goto restart;
error = 0;
}
out:
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
free_lock:
locks_free_lease(new_fl);
return error;
}
EXPORT_SYMBOL(__break_lease);
/**
* lease_get_mtime - update modified time of an inode with exclusive lease
* @inode: the inode
* @time: pointer to a timespec which contains the last modified time
*
* This is to force NFS clients to flush their caches for files with
* exclusive leases. The justification is that if someone has an
* exclusive lease, then they could be modifying it.
*/
void lease_get_mtime(struct inode *inode, struct timespec64 *time)
{
bool has_lease = false;
struct file_lock_context *ctx;
struct file_lock_core *flc;
ctx = locks_inode_context(inode);
if (ctx && !list_empty_careful(&ctx->flc_lease)) {
spin_lock(&ctx->flc_lock);
flc = list_first_entry_or_null(&ctx->flc_lease,
struct file_lock_core, flc_list);
if (flc && flc->flc_type == F_WRLCK)
has_lease = true;
spin_unlock(&ctx->flc_lock);
}
if (has_lease)
*time = current_time(inode);
}
EXPORT_SYMBOL(lease_get_mtime);
/**
* fcntl_getlease - Enquire what lease is currently active
* @filp: the file
*
* The value returned by this function will be one of
* (if no lease break is pending):
*
* %F_RDLCK to indicate a shared lease is held.
*
* %F_WRLCK to indicate an exclusive lease is held.
*
* %F_UNLCK to indicate no lease is held.
*
* (if a lease break is pending):
*
* %F_RDLCK to indicate an exclusive lease needs to be
* changed to a shared lease (or removed).
*
* %F_UNLCK to indicate the lease needs to be removed.
*
* XXX: sfr & willy disagree over whether F_INPROGRESS
* should be returned to userspace.
*/
int fcntl_getlease(struct file *filp)
{
struct file_lease *fl;
struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
int type = F_UNLCK;
LIST_HEAD(dispose);
ctx = locks_inode_context(inode);
if (ctx && !list_empty_careful(&ctx->flc_lease)) {
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
if (fl->c.flc_file != filp)
continue;
type = target_leasetype(fl);
break;
}
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
}
return type;
}
/**
* check_conflicting_open - see if the given file points to an inode that has
* an existing open that would conflict with the
* desired lease.
* @filp: file to check
* @arg: type of lease that we're trying to acquire
* @flags: current lock flags
*
* Check to see if there's an existing open fd on this file that would
* conflict with the lease we're trying to set.
*/
static int
check_conflicting_open(struct file *filp, const int arg, int flags)
{
struct inode *inode = file_inode(filp);
int self_wcount = 0, self_rcount = 0;
if (flags & FL_LAYOUT)
return 0;
if (flags & FL_DELEG)
/* We leave these checks to the caller */
return 0;
if (arg == F_RDLCK)
return inode_is_open_for_write(inode) ? -EAGAIN : 0;
else if (arg != F_WRLCK)
return 0;
/*
* Make sure that only read/write count is from lease requestor.
* Note that this will result in denying write leases when i_writecount
* is negative, which is what we want. (We shouldn't grant write leases
* on files open for execution.)
*/
if (filp->f_mode & FMODE_WRITE)
self_wcount = 1;
else if (filp->f_mode & FMODE_READ)
self_rcount = 1;
if (atomic_read(&inode->i_writecount) != self_wcount ||
atomic_read(&inode->i_readcount) != self_rcount)
return -EAGAIN;
return 0;
}
static int
generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv)
{
struct file_lease *fl, *my_fl = NULL, *lease;
struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
bool is_deleg = (*flp)->c.flc_flags & FL_DELEG;
int error;
LIST_HEAD(dispose);
lease = *flp;
trace_generic_add_lease(inode, lease);
error = file_f_owner_allocate(filp);
if (error)
return error;
/* Note that arg is never F_UNLCK here */
ctx = locks_get_lock_context(inode, arg);
if (!ctx)
return -ENOMEM;
/*
* In the delegation case we need mutual exclusion with
* a number of operations that take the i_mutex. We trylock
* because delegations are an optional optimization, and if
* there's some chance of a conflict--we'd rather not
* bother, maybe that's a sign this just isn't a good file to
* hand out a delegation on.
*/
if (is_deleg && !inode_trylock(inode))
return -EAGAIN;
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
error = check_conflicting_open(filp, arg, lease->c.flc_flags);
if (error)
goto out;
/*
* At this point, we know that if there is an exclusive
* lease on this file, then we hold it on this filp
* (otherwise our open of this file would have blocked).
* And if we are trying to acquire an exclusive lease,
* then the file is not open by anyone (including us)
* except for this filp.
*/
error = -EAGAIN;
list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
if (fl->c.flc_file == filp &&
fl->c.flc_owner == lease->c.flc_owner) {
my_fl = fl;
continue;
}
/*
* No exclusive leases if someone else has a lease on
* this file:
*/
if (arg == F_WRLCK)
goto out;
/*
* Modifying our existing lease is OK, but no getting a
* new lease if someone else is opening for write:
*/
if (fl->c.flc_flags & FL_UNLOCK_PENDING)
goto out;
}
if (my_fl != NULL) {
lease = my_fl;
error = lease->fl_lmops->lm_change(lease, arg, &dispose);
if (error)
goto out;
goto out_setup;
}
error = -EINVAL;
if (!leases_enable)
goto out;
locks_insert_lock_ctx(&lease->c, &ctx->flc_lease);
/*
* The check in break_lease() is lockless. It's possible for another
* open to race in after we did the earlier check for a conflicting
* open but before the lease was inserted. Check again for a
* conflicting open and cancel the lease if there is one.
*
* We also add a barrier here to ensure that the insertion of the lock
* precedes these checks.
*/
smp_mb();
error = check_conflicting_open(filp, arg, lease->c.flc_flags);
if (error) {
locks_unlink_lock_ctx(&lease->c);
goto out;
}
out_setup:
if (lease->fl_lmops->lm_setup)
lease->fl_lmops->lm_setup(lease, priv);
out:
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
if (is_deleg)
inode_unlock(inode);
if (!error && !my_fl)
*flp = NULL;
return error;
}
static int generic_delete_lease(struct file *filp, void *owner)
{
int error = -EAGAIN;
struct file_lease *fl, *victim = NULL;
struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
LIST_HEAD(dispose);
ctx = locks_inode_context(inode);
if (!ctx) {
trace_generic_delete_lease(inode, NULL);
return error;
}
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
if (fl->c.flc_file == filp &&
fl->c.flc_owner == owner) {
victim = fl;
break;
}
}
trace_generic_delete_lease(inode, victim);
if (victim)
error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
return error;
}
/**
* generic_setlease - sets a lease on an open file
* @filp: file pointer
* @arg: type of lease to obtain
* @flp: input - file_lock to use, output - file_lock inserted
* @priv: private data for lm_setup (may be NULL if lm_setup
* doesn't require it)
*
* The (input) flp->fl_lmops->lm_break function is required
* by break_lease().
*/
int generic_setlease(struct file *filp, int arg, struct file_lease **flp,
void **priv)
{
switch (arg) {
case F_UNLCK:
return generic_delete_lease(filp, *priv);
case F_RDLCK:
case F_WRLCK:
if (!(*flp)->fl_lmops->lm_break) {
WARN_ON_ONCE(1);
return -ENOLCK;
}
return generic_add_lease(filp, arg, flp, priv);
default:
return -EINVAL;
}
}
EXPORT_SYMBOL(generic_setlease);
/*
* Kernel subsystems can register to be notified on any attempt to set
* a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd
* to close files that it may have cached when there is an attempt to set a
* conflicting lease.
*/
static struct srcu_notifier_head lease_notifier_chain;
static inline void
lease_notifier_chain_init(void)
{
srcu_init_notifier_head(&lease_notifier_chain);
}
static inline void
setlease_notifier(int arg, struct file_lease *lease)
{
if (arg != F_UNLCK)
srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
}
int lease_register_notifier(struct notifier_block *nb)
{
return srcu_notifier_chain_register(&lease_notifier_chain, nb);
}
EXPORT_SYMBOL_GPL(lease_register_notifier);
void lease_unregister_notifier(struct notifier_block *nb)
{
srcu_notifier_chain_unregister(&lease_notifier_chain, nb);
}
EXPORT_SYMBOL_GPL(lease_unregister_notifier);
int
kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
{
if (lease)
setlease_notifier(arg, *lease);
if (filp->f_op->setlease)
return filp->f_op->setlease(filp, arg, lease, priv);
else
return generic_setlease(filp, arg, lease, priv);
}
EXPORT_SYMBOL_GPL(kernel_setlease);
/**
* vfs_setlease - sets a lease on an open file
* @filp: file pointer
* @arg: type of lease to obtain
* @lease: file_lock to use when adding a lease
* @priv: private info for lm_setup when adding a lease (may be
* NULL if lm_setup doesn't require it)
*
* Call this to establish a lease on the file. The "lease" argument is not
* used for F_UNLCK requests and may be NULL. For commands that set or alter
* an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be
* set; if not, this function will return -ENOLCK (and generate a scary-looking
* stack trace).
*
* The "priv" pointer is passed directly to the lm_setup function as-is. It
* may be NULL if the lm_setup operation doesn't require it.
*/
int
vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
{
struct inode *inode = file_inode(filp);
vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
int error;
if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
return -EACCES;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
error = security_file_lock(filp, arg);
if (error)
return error;
return kernel_setlease(filp, arg, lease, priv);
}
EXPORT_SYMBOL_GPL(vfs_setlease);
static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
{
struct file_lease *fl;
struct fasync_struct *new;
int error;
fl = lease_alloc(filp, arg);
if (IS_ERR(fl))
return PTR_ERR(fl);
new = fasync_alloc();
if (!new) {
locks_free_lease(fl);
return -ENOMEM;
}
new->fa_fd = fd;
error = vfs_setlease(filp, arg, &fl, (void **)&new);
if (fl)
locks_free_lease(fl);
if (new)
fasync_free(new);
return error;
}
/**
* fcntl_setlease - sets a lease on an open file
* @fd: open file descriptor
* @filp: file pointer
* @arg: type of lease to obtain
*
* Call this fcntl to establish a lease on the file.
* Note that you also need to call %F_SETSIG to
* receive a signal when the lease is broken.
*/
int fcntl_setlease(unsigned int fd, struct file *filp, int arg)
{
if (arg == F_UNLCK)
return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp);
return do_fcntl_add_lease(fd, filp, arg);
}
/**
* flock_lock_inode_wait - Apply a FLOCK-style lock to a file
* @inode: inode of the file to apply to
* @fl: The lock to be applied
*
* Apply a FLOCK style lock request to an inode.
*/
static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
int error;
might_sleep();
for (;;) {
error = flock_lock_inode(inode, fl);
if (error != FILE_LOCK_DEFERRED)
break;
error = wait_event_interruptible(fl->c.flc_wait,
list_empty(&fl->c.flc_blocked_member));
if (error)
break;
}
locks_delete_block(fl);
return error;
}
/**
* locks_lock_inode_wait - Apply a lock to an inode
* @inode: inode of the file to apply to
* @fl: The lock to be applied
*
* Apply a POSIX or FLOCK style lock request to an inode.
*/
int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
int res = 0;
switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) {
case FL_POSIX:
res = posix_lock_inode_wait(inode, fl);
break;
case FL_FLOCK:
res = flock_lock_inode_wait(inode, fl);
break;
default:
BUG();
}
return res;
}
EXPORT_SYMBOL(locks_lock_inode_wait);
/**
* sys_flock: - flock() system call.
* @fd: the file descriptor to lock.
* @cmd: the type of lock to apply.
*
* Apply a %FL_FLOCK style lock to an open file descriptor.
* The @cmd can be one of:
*
* - %LOCK_SH -- a shared lock.
* - %LOCK_EX -- an exclusive lock.
* - %LOCK_UN -- remove an existing lock.
* - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED)
*
* %LOCK_MAND support has been removed from the kernel.
*/
SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
int can_sleep, error, type;
struct file_lock fl;
/*
* LOCK_MAND locks were broken for a long time in that they never
* conflicted with one another and didn't prevent any sort of open,
* read or write activity.
*
* Just ignore these requests now, to preserve legacy behavior, but
* throw a warning to let people know that they don't actually work.
*/
if (cmd & LOCK_MAND) {
pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid);
return 0;
}
type = flock_translate_cmd(cmd & ~LOCK_NB);
if (type < 0)
return type;
CLASS(fd, f)(fd);
if (fd_empty(f))
return -EBADF;
if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE)))
return -EBADF;
flock_make_lock(fd_file(f), &fl, type);
error = security_file_lock(fd_file(f), fl.c.flc_type);
if (error)
return error;
can_sleep = !(cmd & LOCK_NB);
if (can_sleep)
fl.c.flc_flags |= FL_SLEEP;
if (fd_file(f)->f_op->flock)
error = fd_file(f)->f_op->flock(fd_file(f),
(can_sleep) ? F_SETLKW : F_SETLK,
&fl);
else
error = locks_lock_file_wait(fd_file(f), &fl);
locks_release_private(&fl);
return error;
}
/**
* vfs_test_lock - test file byte range lock
* @filp: The file to test lock for
* @fl: The lock to test; also used to hold result
*
* Returns -ERRNO on failure. Indicates presence of conflicting lock by
* setting conf->fl_type to something other than F_UNLCK.
*/
int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
WARN_ON_ONCE(filp != fl->c.flc_file);
if (filp->f_op->lock)
return filp->f_op->lock(filp, F_GETLK, fl);
posix_test_lock(filp, fl);
return 0;
}
EXPORT_SYMBOL_GPL(vfs_test_lock);
/**
* locks_translate_pid - translate a file_lock's fl_pid number into a namespace
* @fl: The file_lock who's fl_pid should be translated
* @ns: The namespace into which the pid should be translated
*
* Used to translate a fl_pid into a namespace virtual pid number
*/
static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns)
{
pid_t vnr;
struct pid *pid;
if (fl->flc_flags & FL_OFDLCK)
return -1;
/* Remote locks report a negative pid value */
if (fl->flc_pid <= 0)
return fl->flc_pid;
/*
* If the flock owner process is dead and its pid has been already
* freed, the translation below won't work, but we still want to show
* flock owner pid number in init pidns.
*/
if (ns == &init_pid_ns)
return (pid_t) fl->flc_pid;
rcu_read_lock();
pid = find_pid_ns(fl->flc_pid, &init_pid_ns);
vnr = pid_nr_ns(pid, ns);
rcu_read_unlock();
return vnr;
}
static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
{
flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
#if BITS_PER_LONG == 32
/*
* Make sure we can represent the posix lock via
* legacy 32bit flock.
*/
if (fl->fl_start > OFFT_OFFSET_MAX)
return -EOVERFLOW;
if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX)
return -EOVERFLOW;
#endif
flock->l_start = fl->fl_start;
flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
fl->fl_end - fl->fl_start + 1;
flock->l_whence = 0;
flock->l_type = fl->c.flc_type;
return 0;
}
#if BITS_PER_LONG == 32
static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
{
flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
flock->l_start = fl->fl_start;
flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
fl->fl_end - fl->fl_start + 1;
flock->l_whence = 0;
flock->l_type = fl->c.flc_type;
}
#endif
/* Report the first existing lock that would conflict with l.
* This implements the F_GETLK command of fcntl().
*/
int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
{
struct file_lock *fl;
int error;
fl = locks_alloc_lock();
if (fl == NULL)
return -ENOMEM;
error = -EINVAL;
if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK
&& flock->l_type != F_WRLCK)
goto out;
error = flock_to_posix_lock(filp, fl, flock);
if (error)
goto out;
if (cmd == F_OFD_GETLK) {
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
fl->c.flc_flags |= FL_OFDLCK;
fl->c.flc_owner = filp;
}
error = vfs_test_lock(filp, fl);
if (error)
goto out;
flock->l_type = fl->c.flc_type;
if (fl->c.flc_type != F_UNLCK) {
error = posix_lock_to_flock(flock, fl);
if (error)
goto out;
}
out:
locks_free_lock(fl);
return error;
}
/**
* vfs_lock_file - file byte range lock
* @filp: The file to apply the lock to
* @cmd: type of locking operation (F_SETLK, F_GETLK, etc.)
* @fl: The lock to be applied
* @conf: Place to return a copy of the conflicting lock, if found.
*
* A caller that doesn't care about the conflicting lock may pass NULL
* as the final argument.
*
* If the filesystem defines a private ->lock() method, then @conf will
* be left unchanged; so a caller that cares should initialize it to
* some acceptable default.
*
* To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX
* locks, the ->lock() interface may return asynchronously, before the lock has
* been granted or denied by the underlying filesystem, if (and only if)
* lm_grant is set. Additionally EXPORT_OP_ASYNC_LOCK in export_operations
* flags need to be set.
*
* Callers expecting ->lock() to return asynchronously will only use F_SETLK,
* not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a
* blocking lock. When ->lock() does return asynchronously, it must return
* FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes.
* If the request is for non-blocking lock the file system should return
* FILE_LOCK_DEFERRED then try to get the lock and call the callback routine
* with the result. If the request timed out the callback routine will return a
* nonzero return code and the file system should release the lock. The file
* system is also responsible to keep a corresponding posix lock when it
* grants a lock so the VFS can find out which locks are locally held and do
* the correct lock cleanup when required.
* The underlying filesystem must not drop the kernel lock or call
* ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED
* return code.
*/
int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
{
WARN_ON_ONCE(filp != fl->c.flc_file);
if (filp->f_op->lock)
return filp->f_op->lock(filp, cmd, fl);
else
return posix_lock_file(filp, fl, conf);
}
EXPORT_SYMBOL_GPL(vfs_lock_file);
static int do_lock_file_wait(struct file *filp, unsigned int cmd,
struct file_lock *fl)
{
int error;
error = security_file_lock(filp, fl->c.flc_type);
if (error)
return error;
for (;;) {
error = vfs_lock_file(filp, cmd, fl, NULL);
if (error != FILE_LOCK_DEFERRED)
break;
error = wait_event_interruptible(fl->c.flc_wait,
list_empty(&fl->c.flc_blocked_member));
if (error)
break;
}
locks_delete_block(fl);
return error;
}
/* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */
static int
check_fmode_for_setlk(struct file_lock *fl)
{
switch (fl->c.flc_type) {
case F_RDLCK:
if (!(fl->c.flc_file->f_mode & FMODE_READ))
return -EBADF;
break;
case F_WRLCK:
if (!(fl->c.flc_file->f_mode & FMODE_WRITE))
return -EBADF;
}
return 0;
}
/* Apply the lock described by l to an open file descriptor.
* This implements both the F_SETLK and F_SETLKW commands of fcntl().
*/
int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
struct flock *flock)
{
struct file_lock *file_lock = locks_alloc_lock();
struct inode *inode = file_inode(filp);
struct file *f;
int error;
if (file_lock == NULL)
return -ENOLCK;
error = flock_to_posix_lock(filp, file_lock, flock);
if (error)
goto out;
error = check_fmode_for_setlk(file_lock);
if (error)
goto out;
/*
* If the cmd is requesting file-private locks, then set the
* FL_OFDLCK flag and override the owner.
*/
switch (cmd) {
case F_OFD_SETLK:
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
cmd = F_SETLK;
file_lock->c.flc_flags |= FL_OFDLCK;
file_lock->c.flc_owner = filp;
break;
case F_OFD_SETLKW:
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
cmd = F_SETLKW;
file_lock->c.flc_flags |= FL_OFDLCK;
file_lock->c.flc_owner = filp;
fallthrough;
case F_SETLKW:
file_lock->c.flc_flags |= FL_SLEEP;
}
error = do_lock_file_wait(filp, cmd, file_lock);
/*
* Detect close/fcntl races and recover by zapping all POSIX locks
* associated with this file and our files_struct, just like on
* filp_flush(). There is no need to do that when we're
* unlocking though, or for OFD locks.
*/
if (!error && file_lock->c.flc_type != F_UNLCK &&
!(file_lock->c.flc_flags & FL_OFDLCK)) {
struct files_struct *files = current->files;
/*
* We need that spin_lock here - it prevents reordering between
* update of i_flctx->flc_posix and check for it done in
* close(). rcu_read_lock() wouldn't do.
*/
spin_lock(&files->file_lock);
f = files_lookup_fd_locked(files, fd);
spin_unlock(&files->file_lock);
if (f != filp) {
locks_remove_posix(filp, files);
error = -EBADF;
}
}
out:
trace_fcntl_setlk(inode, file_lock, error);
locks_free_lock(file_lock);
return error;
}
#if BITS_PER_LONG == 32
/* Report the first existing lock that would conflict with l.
* This implements the F_GETLK command of fcntl().
*/
int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
{
struct file_lock *fl;
int error;
fl = locks_alloc_lock();
if (fl == NULL)
return -ENOMEM;
error = -EINVAL;
if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK
&& flock->l_type != F_WRLCK)
goto out;
error = flock64_to_posix_lock(filp, fl, flock);
if (error)
goto out;
if (cmd == F_OFD_GETLK) {
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
fl->c.flc_flags |= FL_OFDLCK;
fl->c.flc_owner = filp;
}
error = vfs_test_lock(filp, fl);
if (error)
goto out;
flock->l_type = fl->c.flc_type;
if (fl->c.flc_type != F_UNLCK)
posix_lock_to_flock64(flock, fl);
out:
locks_free_lock(fl);
return error;
}
/* Apply the lock described by l to an open file descriptor.
* This implements both the F_SETLK and F_SETLKW commands of fcntl().
*/
int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
struct flock64 *flock)
{
struct file_lock *file_lock = locks_alloc_lock();
struct file *f;
int error;
if (file_lock == NULL)
return -ENOLCK;
error = flock64_to_posix_lock(filp, file_lock, flock);
if (error)
goto out;
error = check_fmode_for_setlk(file_lock);
if (error)
goto out;
/*
* If the cmd is requesting file-private locks, then set the
* FL_OFDLCK flag and override the owner.
*/
switch (cmd) {
case F_OFD_SETLK:
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
cmd = F_SETLK64;
file_lock->c.flc_flags |= FL_OFDLCK;
file_lock->c.flc_owner = filp;
break;
case F_OFD_SETLKW:
error = -EINVAL;
if (flock->l_pid != 0)
goto out;
cmd = F_SETLKW64;
file_lock->c.flc_flags |= FL_OFDLCK;
file_lock->c.flc_owner = filp;
fallthrough;
case F_SETLKW64:
file_lock->c.flc_flags |= FL_SLEEP;
}
error = do_lock_file_wait(filp, cmd, file_lock);
/*
* Detect close/fcntl races and recover by zapping all POSIX locks
* associated with this file and our files_struct, just like on
* filp_flush(). There is no need to do that when we're
* unlocking though, or for OFD locks.
*/
if (!error && file_lock->c.flc_type != F_UNLCK &&
!(file_lock->c.flc_flags & FL_OFDLCK)) {
struct files_struct *files = current->files;
/*
* We need that spin_lock here - it prevents reordering between
* update of i_flctx->flc_posix and check for it done in
* close(). rcu_read_lock() wouldn't do.
*/
spin_lock(&files->file_lock);
f = files_lookup_fd_locked(files, fd);
spin_unlock(&files->file_lock);
if (f != filp) {
locks_remove_posix(filp, files);
error = -EBADF;
}
}
out:
locks_free_lock(file_lock);
return error;
}
#endif /* BITS_PER_LONG == 32 */
/*
* This function is called when the file is being removed
* from the task's fd array. POSIX locks belonging to this task
* are deleted at this time.
*/
void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
int error;
struct inode *inode = file_inode(filp);
struct file_lock lock;
struct file_lock_context *ctx;
/*
* If there are no locks held on this file, we don't need to call
* posix_lock_file(). Another process could be setting a lock on this
* file at the same time, but we wouldn't remove that lock anyway.
*/
ctx = locks_inode_context(inode);
if (!ctx || list_empty(&ctx->flc_posix))
return;
locks_init_lock(&lock);
lock.c.flc_type = F_UNLCK;
lock.c.flc_flags = FL_POSIX | FL_CLOSE;
lock.fl_start = 0;
lock.fl_end = OFFSET_MAX;
lock.c.flc_owner = owner;
lock.c.flc_pid = current->tgid;
lock.c.flc_file = filp;
lock.fl_ops = NULL;
lock.fl_lmops = NULL;
error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error);
}
EXPORT_SYMBOL(locks_remove_posix);
/* The i_flctx must be valid when calling into here */
static void
locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
{
struct file_lock fl;
struct inode *inode = file_inode(filp);
if (list_empty(&flctx->flc_flock))
return;
flock_make_lock(filp, &fl, F_UNLCK);
fl.c.flc_flags |= FL_CLOSE;
if (filp->f_op->flock)
filp->f_op->flock(filp, F_SETLKW, &fl);
else
flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl);
}
/* The i_flctx must be valid when calling into here */
static void
locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
{
struct file_lease *fl, *tmp;
LIST_HEAD(dispose);
if (list_empty(&ctx->flc_lease))
return;
percpu_down_read(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) if (filp == fl->c.flc_file)
lease_modify(fl, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
percpu_up_read(&file_rwsem);
locks_dispose_list(&dispose);
}
/*
* This function is called on the last close of an open file.
*/
void locks_remove_file(struct file *filp)
{
struct file_lock_context *ctx;
ctx = locks_inode_context(file_inode(filp));
if (!ctx)
return;
/* remove any OFD locks */
locks_remove_posix(filp, filp);
/* remove flock locks */
locks_remove_flock(filp, ctx);
/* remove any leases */
locks_remove_lease(filp, ctx);
spin_lock(&ctx->flc_lock);
locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE");
spin_unlock(&ctx->flc_lock);
}
/**
* vfs_cancel_lock - file byte range unblock lock
* @filp: The file to apply the unblock to
* @fl: The lock to be unblocked
*
* Used by lock managers to cancel blocked requests
*/
int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
WARN_ON_ONCE(filp != fl->c.flc_file);
if (filp->f_op->lock)
return filp->f_op->lock(filp, F_CANCELLK, fl);
return 0;
}
EXPORT_SYMBOL_GPL(vfs_cancel_lock);
/**
* vfs_inode_has_locks - are any file locks held on @inode?
* @inode: inode to check for locks
*
* Return true if there are any FL_POSIX or FL_FLOCK locks currently
* set on @inode.
*/
bool vfs_inode_has_locks(struct inode *inode)
{
struct file_lock_context *ctx;
bool ret;
ctx = locks_inode_context(inode);
if (!ctx)
return false;
spin_lock(&ctx->flc_lock);
ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock);
spin_unlock(&ctx->flc_lock);
return ret;
}
EXPORT_SYMBOL_GPL(vfs_inode_has_locks);
#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
struct locks_iterator {
int li_cpu;
loff_t li_pos;
};
static void lock_get_status(struct seq_file *f, struct file_lock_core *flc,
loff_t id, char *pfx, int repeat)
{
struct inode *inode = NULL;
unsigned int pid;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
int type = flc->flc_type;
struct file_lock *fl = file_lock(flc);
pid = locks_translate_pid(flc, proc_pidns);
/*
* If lock owner is dead (and pid is freed) or not visible in current
* pidns, zero is shown as a pid value. Check lock info from
* init_pid_ns to get saved lock pid value.
*/
if (flc->flc_file != NULL)
inode = file_inode(flc->flc_file);
seq_printf(f, "%lld: ", id);
if (repeat)
seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);
if (flc->flc_flags & FL_POSIX) {
if (flc->flc_flags & FL_ACCESS)
seq_puts(f, "ACCESS");
else if (flc->flc_flags & FL_OFDLCK)
seq_puts(f, "OFDLCK");
else
seq_puts(f, "POSIX ");
seq_printf(f, " %s ",
(inode == NULL) ? "*NOINODE*" : "ADVISORY ");
} else if (flc->flc_flags & FL_FLOCK) {
seq_puts(f, "FLOCK ADVISORY ");
} else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) {
struct file_lease *lease = file_lease(flc);
type = target_leasetype(lease);
if (flc->flc_flags & FL_DELEG)
seq_puts(f, "DELEG ");
else
seq_puts(f, "LEASE ");
if (lease_breaking(lease))
seq_puts(f, "BREAKING ");
else if (flc->flc_file)
seq_puts(f, "ACTIVE ");
else
seq_puts(f, "BREAKER ");
} else {
seq_puts(f, "UNKNOWN UNKNOWN ");
}
seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
(type == F_RDLCK) ? "READ" : "UNLCK");
if (inode) {
/* userspace relies on this representation of dev_t */
seq_printf(f, "%d %02x:%02x:%lu ", pid,
MAJOR(inode->i_sb->s_dev),
MINOR(inode->i_sb->s_dev), inode->i_ino);
} else {
seq_printf(f, "%d <none>:0 ", pid);
}
if (flc->flc_flags & FL_POSIX) {
if (fl->fl_end == OFFSET_MAX)
seq_printf(f, "%Ld EOF\n", fl->fl_start);
else
seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end);
} else {
seq_puts(f, "0 EOF\n");
}
}
static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node)
{
struct file_lock_core *tmp;
/* NULL node or root node */
if (node == NULL || node->flc_blocker == NULL)
return NULL;
/* Next member in the linked list could be itself */
tmp = list_next_entry(node, flc_blocked_member);
if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests,
flc_blocked_member)
|| tmp == node) {
return NULL;
}
return tmp;
}
static int locks_show(struct seq_file *f, void *v)
{
struct locks_iterator *iter = f->private;
struct file_lock_core *cur, *tmp;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
int level = 0;
cur = hlist_entry(v, struct file_lock_core, flc_link);
if (locks_translate_pid(cur, proc_pidns) == 0)
return 0;
/* View this crossed linked list as a binary tree, the first member of flc_blocked_requests
* is the left child of current node, the next silibing in flc_blocked_member is the
* right child, we can alse get the parent of current node from flc_blocker, so this
* question becomes traversal of a binary tree
*/
while (cur != NULL) {
if (level)
lock_get_status(f, cur, iter->li_pos, "-> ", level);
else
lock_get_status(f, cur, iter->li_pos, "", level);
if (!list_empty(&cur->flc_blocked_requests)) {
/* Turn left */
cur = list_first_entry_or_null(&cur->flc_blocked_requests,
struct file_lock_core,
flc_blocked_member);
level++;
} else {
/* Turn right */
tmp = get_next_blocked_member(cur);
/* Fall back to parent node */
while (tmp == NULL && cur->flc_blocker != NULL) {
cur = cur->flc_blocker;
level--;
tmp = get_next_blocked_member(cur);
}
cur = tmp;
}
}
return 0;
}
static void __show_fd_locks(struct seq_file *f,
struct list_head *head, int *id,
struct file *filp, struct files_struct *files)
{
struct file_lock_core *fl;
list_for_each_entry(fl, head, flc_list) {
if (filp != fl->flc_file)
continue;
if (fl->flc_owner != files && fl->flc_owner != filp)
continue;
(*id)++;
seq_puts(f, "lock:\t");
lock_get_status(f, fl, *id, "", 0);
}
}
void show_fd_locks(struct seq_file *f,
struct file *filp, struct files_struct *files)
{
struct inode *inode = file_inode(filp);
struct file_lock_context *ctx;
int id = 0;
ctx = locks_inode_context(inode);
if (!ctx)
return;
spin_lock(&ctx->flc_lock);
__show_fd_locks(f, &ctx->flc_flock, &id, filp, files);
__show_fd_locks(f, &ctx->flc_posix, &id, filp, files);
__show_fd_locks(f, &ctx->flc_lease, &id, filp, files);
spin_unlock(&ctx->flc_lock);
}
static void *locks_start(struct seq_file *f, loff_t *pos)
__acquires(&blocked_lock_lock)
{
struct locks_iterator *iter = f->private;
iter->li_pos = *pos + 1;
percpu_down_write(&file_rwsem);
spin_lock(&blocked_lock_lock);
return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos);
}
static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
{
struct locks_iterator *iter = f->private;
++iter->li_pos;
return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos);
}
static void locks_stop(struct seq_file *f, void *v)
__releases(&blocked_lock_lock)
{
spin_unlock(&blocked_lock_lock);
percpu_up_write(&file_rwsem);
}
static const struct seq_operations locks_seq_operations = {
.start = locks_start,
.next = locks_next,
.stop = locks_stop,
.show = locks_show,
};
static int __init proc_locks_init(void)
{
proc_create_seq_private("locks", 0, NULL, &locks_seq_operations,
sizeof(struct locks_iterator), NULL);
return 0;
}
fs_initcall(proc_locks_init);
#endif
static int __init filelock_init(void)
{
int i;
flctx_cache = kmem_cache_create("file_lock_ctx",
sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);
filelock_cache = kmem_cache_create("file_lock_cache",
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
filelease_cache = kmem_cache_create("file_lease_cache",
sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
for_each_possible_cpu(i) {
struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
spin_lock_init(&fll->lock);
INIT_HLIST_HEAD(&fll->hlist);
}
lease_notifier_chain_init();
return 0;
}
core_initcall(filelock_init);
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/netdevice.h>
#include <net/netdev_lock.h>
#include "dev.h"
/**
* dev_change_name() - change name of a device
* @dev: device
* @newname: name (or format string) must be at least IFNAMSIZ
*
* Change name of a device, can pass format strings "eth%d".
* for wildcarding.
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_name(struct net_device *dev, const char *newname)
{
int ret;
netdev_lock_ops(dev);
ret = netif_change_name(dev, newname);
netdev_unlock_ops(dev);
return ret;
}
/**
* dev_set_alias() - change ifalias of a device
* @dev: device
* @alias: name up to IFALIASZ
* @len: limit of bytes to copy from info
*
* Set ifalias for a device.
*
* Return: 0 on success, -errno on failure.
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
int ret;
netdev_lock_ops(dev);
ret = netif_set_alias(dev, alias, len);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_set_alias);
/**
* dev_change_flags() - change device settings
* @dev: device
* @flags: device state flags
* @extack: netlink extended ack
*
* Change settings on device based state flags. The flags are
* in the userspace exported format.
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack)
{
int ret;
netdev_lock_ops(dev);
ret = netif_change_flags(dev, flags, extack);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_change_flags);
/**
* dev_set_group() - change group this device belongs to
* @dev: device
* @new_group: group this device should belong to
*/
void dev_set_group(struct net_device *dev, int new_group)
{
netdev_lock_ops(dev);
netif_set_group(dev, new_group);
netdev_unlock_ops(dev);
}
int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack)
{
int ret;
down_write(&dev_addr_sem);
netdev_lock_ops(dev);
ret = netif_set_mac_address(dev, sa, extack);
netdev_unlock_ops(dev);
up_write(&dev_addr_sem);
return ret;
}
EXPORT_SYMBOL(dev_set_mac_address_user);
/**
* dev_change_net_namespace() - move device to different nethost namespace
* @dev: device
* @net: network namespace
* @pat: If not NULL name pattern to try if the current device name
* is already taken in the destination network namespace.
*
* This function shuts down a device interface and moves it
* to a new network namespace. On success 0 is returned, on
* a failure a netagive errno code is returned.
*
* Callers must hold the rtnl semaphore.
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat)
{
return __dev_change_net_namespace(dev, net, pat, 0, NULL);
}
EXPORT_SYMBOL_GPL(dev_change_net_namespace);
/**
* dev_change_carrier() - change device carrier
* @dev: device
* @new_carrier: new value
*
* Change device carrier
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_carrier(struct net_device *dev, bool new_carrier)
{
int ret;
netdev_lock_ops(dev);
ret = netif_change_carrier(dev, new_carrier);
netdev_unlock_ops(dev);
return ret;
}
/**
* dev_change_tx_queue_len() - change TX queue length of a netdevice
* @dev: device
* @new_len: new tx queue length
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
{
int ret;
netdev_lock_ops(dev);
ret = netif_change_tx_queue_len(dev, new_len);
netdev_unlock_ops(dev);
return ret;
}
/**
* dev_change_proto_down() - set carrier according to proto_down
* @dev: device
* @proto_down: new value
*
* Return: 0 on success, -errno on failure.
*/
int dev_change_proto_down(struct net_device *dev, bool proto_down)
{
int ret;
netdev_lock_ops(dev);
ret = netif_change_proto_down(dev, proto_down);
netdev_unlock_ops(dev);
return ret;
}
/**
* dev_open() - prepare an interface for use
* @dev: device to open
* @extack: netlink extended ack
*
* Takes a device from down to up state. The device's private open
* function is invoked and then the multicast lists are loaded. Finally
* the device is moved into the up state and a %NETDEV_UP message is
* sent to the netdev notifier chain.
*
* Calling this function on an active interface is a nop. On a failure
* a negative errno code is returned.
*
* Return: 0 on success, -errno on failure.
*/
int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
int ret;
netdev_lock_ops(dev);
ret = netif_open(dev, extack);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_open);
/**
* dev_close() - shutdown an interface
* @dev: device to shutdown
*
* This function moves an active device into down state. A
* %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
* is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
* chain.
*/
void dev_close(struct net_device *dev)
{
netdev_lock_ops(dev);
netif_close(dev);
netdev_unlock_ops(dev);
}
EXPORT_SYMBOL(dev_close);
int dev_eth_ioctl(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
int ret = -ENODEV;
if (!ops->ndo_eth_ioctl)
return -EOPNOTSUPP;
netdev_lock_ops(dev);
if (netif_device_present(dev))
ret = ops->ndo_eth_ioctl(dev, ifr, cmd);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_eth_ioctl);
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
int ret;
netdev_lock_ops(dev);
ret = netif_set_mtu(dev, new_mtu);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_set_mtu);
/**
* dev_disable_lro() - disable Large Receive Offload on a device
* @dev: device
*
* Disable Large Receive Offload (LRO) on a net device. Must be
* called under RTNL. This is needed if received packets may be
* forwarded to another interface.
*/
void dev_disable_lro(struct net_device *dev)
{
netdev_lock_ops(dev);
netif_disable_lro(dev);
netdev_unlock_ops(dev);
}
EXPORT_SYMBOL(dev_disable_lro);
/**
* dev_set_allmulti() - update allmulti count on a device
* @dev: device
* @inc: modifier
*
* Add or remove reception of all multicast frames to a device. While the
* count in the device remains above zero the interface remains listening
* to all interfaces. Once it hits zero the device reverts back to normal
* filtering operation. A negative @inc value is used to drop the counter
* when releasing a resource needing all multicasts.
*
* Return: 0 on success, -errno on failure.
*/
int dev_set_allmulti(struct net_device *dev, int inc)
{
int ret;
netdev_lock_ops(dev);
ret = netif_set_allmulti(dev, inc, true);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_set_allmulti);
/**
* dev_set_mac_address() - change Media Access Control Address
* @dev: device
* @sa: new address
* @extack: netlink extended ack
*
* Change the hardware (MAC) address of the device
*
* Return: 0 on success, -errno on failure.
*/
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack)
{
int ret;
netdev_lock_ops(dev);
ret = netif_set_mac_address(dev, sa, extack);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL(dev_set_mac_address);
int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
{
int ret;
netdev_lock_ops(dev);
ret = netif_xdp_propagate(dev, bpf);
netdev_unlock_ops(dev);
return ret;
}
EXPORT_SYMBOL_GPL(dev_xdp_propagate);
/**
* netdev_state_change() - device changes state
* @dev: device to cause notification
*
* Called to indicate a device has changed state. This function calls
* the notifier chains for netdev_chain and sends a NEWLINK message
* to the routing socket.
*/
void netdev_state_change(struct net_device *dev)
{ netdev_lock_ops(dev);
netif_state_change(dev);
netdev_unlock_ops(dev);
}
EXPORT_SYMBOL(netdev_state_change);
// SPDX-License-Identifier: GPL-2.0
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/cpumask.h>
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/numa.h>
/* These are not inline because of header tangles. */
#ifdef CONFIG_CPUMASK_OFFSTACK
/**
* alloc_cpumask_var_node - allocate a struct cpumask on a given node
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
* @node: memory node from which to allocate or %NUMA_NO_NODE
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>).
*
* Return: TRUE if memory allocation succeeded, FALSE otherwise.
*
* In addition, mask will be NULL if this fails. Note that gcc is
* usually smart enough to know that mask can never be NULL if
* CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case
* too.
*/
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{ *mask = kmalloc_node(cpumask_size(), flags, node);
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
dump_stack();
}
#endif
return *mask != NULL;
}
EXPORT_SYMBOL(alloc_cpumask_var_node);
/**
* alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
* @mask: pointer to cpumask_var_t where the cpumask is returned
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop (in <linux/cpumask.h>).
* Either returns an allocated (zero-filled) cpumask, or causes the
* system to panic.
*/
void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
{
*mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
}
/**
* free_cpumask_var - frees memory allocated for a struct cpumask.
* @mask: cpumask to free
*
* This is safe on a NULL mask.
*/
void free_cpumask_var(cpumask_var_t mask)
{
kfree(mask);
}
EXPORT_SYMBOL(free_cpumask_var);
/**
* free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var
* @mask: cpumask to free
*/
void __init free_bootmem_cpumask_var(cpumask_var_t mask)
{
memblock_free(mask, cpumask_size());
}
#endif
/**
* cpumask_local_spread - select the i'th cpu based on NUMA distances
* @i: index number
* @node: local numa_node
*
* Return: online CPU according to a numa aware policy; local cpus are returned
* first, followed by non-local ones, then it wraps around.
*
* For those who wants to enumerate all CPUs based on their NUMA distances,
* i.e. call this function in a loop, like:
*
* for (i = 0; i < num_online_cpus(); i++) {
* cpu = cpumask_local_spread(i, node);
* do_something(cpu);
* }
*
* There's a better alternative based on for_each()-like iterators:
*
* for_each_numa_hop_mask(mask, node) {
* for_each_cpu_andnot(cpu, mask, prev)
* do_something(cpu);
* prev = mask;
* }
*
* It's simpler and more verbose than above. Complexity of iterator-based
* enumeration is O(sched_domains_numa_levels * nr_cpu_ids), while
* cpumask_local_spread() when called for each cpu is
* O(sched_domains_numa_levels * nr_cpu_ids * log(nr_cpu_ids)).
*/
unsigned int cpumask_local_spread(unsigned int i, int node)
{
unsigned int cpu;
/* Wrap: we always want a cpu. */
i %= num_online_cpus();
cpu = sched_numa_find_nth_cpu(cpu_online_mask, i, node);
WARN_ON(cpu >= nr_cpu_ids);
return cpu;
}
EXPORT_SYMBOL(cpumask_local_spread);
static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
/**
* cpumask_any_and_distribute - Return an arbitrary cpu within src1p & src2p.
* @src1p: first &cpumask for intersection
* @src2p: second &cpumask for intersection
*
* Iterated calls using the same srcp1 and srcp2 will be distributed within
* their intersection.
*
* Return: >= nr_cpu_ids if the intersection is empty.
*/
unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p)
{
unsigned int next, prev;
/* NOTE: our first selection will skip 0. */
prev = __this_cpu_read(distribute_cpu_mask_prev);
next = cpumask_next_and_wrap(prev, src1p, src2p);
if (next < nr_cpu_ids)
__this_cpu_write(distribute_cpu_mask_prev, next);
return next;
}
EXPORT_SYMBOL(cpumask_any_and_distribute);
/**
* cpumask_any_distribute - Return an arbitrary cpu from srcp
* @srcp: &cpumask for selection
*
* Return: >= nr_cpu_ids if the intersection is empty.
*/
unsigned int cpumask_any_distribute(const struct cpumask *srcp)
{
unsigned int next, prev;
/* NOTE: our first selection will skip 0. */
prev = __this_cpu_read(distribute_cpu_mask_prev);
next = cpumask_next_wrap(prev, srcp);
if (next < nr_cpu_ids)
__this_cpu_write(distribute_cpu_mask_prev, next);
return next;
}
EXPORT_SYMBOL(cpumask_any_distribute);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_LIST_H
#define _LINUX_LIST_H
#include <linux/container_of.h>
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/poison.h>
#include <linux/const.h>
#include <asm/barrier.h>
/*
* Circular doubly linked list implementation.
*
* Some of the internal functions ("__xxx") are useful when
* manipulating whole lists rather than single entries, as
* sometimes we already know the next/prev entries and we can
* generate better code by using them directly rather than
* using the generic single-entry routines.
*/
#define LIST_HEAD_INIT(name) { &(name), &(name) }
#define LIST_HEAD(name) \
struct list_head name = LIST_HEAD_INIT(name)
/**
* INIT_LIST_HEAD - Initialize a list_head structure
* @list: list_head structure to be initialized.
*
* Initializes the list_head to point to itself. If it is a list header,
* the result is an empty list.
*/
static inline void INIT_LIST_HEAD(struct list_head *list)
{
WRITE_ONCE(list->next, list);
WRITE_ONCE(list->prev, list);
}
#ifdef CONFIG_LIST_HARDENED
#ifdef CONFIG_DEBUG_LIST
# define __list_valid_slowpath
#else
# define __list_valid_slowpath __cold __preserve_most
#endif
/*
* Performs the full set of list corruption checks before __list_add().
* On list corruption reports a warning, and returns false.
*/
extern bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new,
struct list_head *prev,
struct list_head *next);
/*
* Performs list corruption checks before __list_add(). Returns false if a
* corruption is detected, true otherwise.
*
* With CONFIG_LIST_HARDENED only, performs minimal list integrity checking
* inline to catch non-faulting corruptions, and only if a corruption is
* detected calls the reporting function __list_add_valid_or_report().
*/
static __always_inline bool __list_add_valid(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
bool ret = true;
if (!IS_ENABLED(CONFIG_DEBUG_LIST)) {
/*
* With the hardening version, elide checking if next and prev
* are NULL, since the immediate dereference of them below would
* result in a fault if NULL.
*
* With the reduced set of checks, we can afford to inline the
* checks, which also gives the compiler a chance to elide some
* of them completely if they can be proven at compile-time. If
* one of the pre-conditions does not hold, the slow-path will
* show a report which pre-condition failed.
*/
if (likely(next->prev == prev && prev->next == next && new != prev && new != next))
return true;
ret = false;
}
ret &= __list_add_valid_or_report(new, prev, next);
return ret;
}
/*
* Performs the full set of list corruption checks before __list_del_entry().
* On list corruption reports a warning, and returns false.
*/
extern bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry);
/*
* Performs list corruption checks before __list_del_entry(). Returns false if a
* corruption is detected, true otherwise.
*
* With CONFIG_LIST_HARDENED only, performs minimal list integrity checking
* inline to catch non-faulting corruptions, and only if a corruption is
* detected calls the reporting function __list_del_entry_valid_or_report().
*/
static __always_inline bool __list_del_entry_valid(struct list_head *entry)
{
bool ret = true;
if (!IS_ENABLED(CONFIG_DEBUG_LIST)) {
struct list_head *prev = entry->prev;
struct list_head *next = entry->next;
/*
* With the hardening version, elide checking if next and prev
* are NULL, LIST_POISON1 or LIST_POISON2, since the immediate
* dereference of them below would result in a fault.
*/
if (likely(prev->next == entry && next->prev == entry))
return true;
ret = false;
}
ret &= __list_del_entry_valid_or_report(entry);
return ret;
}
#else
static inline bool __list_add_valid(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
return true;
}
static inline bool __list_del_entry_valid(struct list_head *entry)
{
return true;
}
#endif
/*
* Insert a new entry between two known consecutive entries.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
static inline void __list_add(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
if (!__list_add_valid(new, prev, next))
return;
next->prev = new;
new->next = next;
new->prev = prev;
WRITE_ONCE(prev->next, new);
}
/**
* list_add - add a new entry
* @new: new entry to be added
* @head: list head to add it after
*
* Insert a new entry after the specified head.
* This is good for implementing stacks.
*/
static inline void list_add(struct list_head *new, struct list_head *head)
{
__list_add(new, head, head->next);
}
/**
* list_add_tail - add a new entry
* @new: new entry to be added
* @head: list head to add it before
*
* Insert a new entry before the specified head.
* This is useful for implementing queues.
*/
static inline void list_add_tail(struct list_head *new, struct list_head *head)
{
__list_add(new, head->prev, head);
}
/*
* Delete a list entry by making the prev/next entries
* point to each other.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
static inline void __list_del(struct list_head * prev, struct list_head * next)
{
next->prev = prev;
WRITE_ONCE(prev->next, next);
}
/*
* Delete a list entry and clear the 'prev' pointer.
*
* This is a special-purpose list clearing method used in the networking code
* for lists allocated as per-cpu, where we don't want to incur the extra
* WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this
* needs to check the node 'prev' pointer instead of calling list_empty().
*/
static inline void __list_del_clearprev(struct list_head *entry)
{
__list_del(entry->prev, entry->next);
entry->prev = NULL;
}
static inline void __list_del_entry(struct list_head *entry)
{
if (!__list_del_entry_valid(entry))
return;
__list_del(entry->prev, entry->next);
}
/**
* list_del - deletes entry from list.
* @entry: the element to delete from the list.
* Note: list_empty() on entry does not return true after this, the entry is
* in an undefined state.
*/
static inline void list_del(struct list_head *entry)
{
__list_del_entry(entry);
entry->next = LIST_POISON1;
entry->prev = LIST_POISON2;
}
/**
* list_replace - replace old entry by new one
* @old : the element to be replaced
* @new : the new element to insert
*
* If @old was empty, it will be overwritten.
*/
static inline void list_replace(struct list_head *old,
struct list_head *new)
{
new->next = old->next;
new->next->prev = new;
new->prev = old->prev;
new->prev->next = new;
}
/**
* list_replace_init - replace old entry by new one and initialize the old one
* @old : the element to be replaced
* @new : the new element to insert
*
* If @old was empty, it will be overwritten.
*/
static inline void list_replace_init(struct list_head *old,
struct list_head *new)
{
list_replace(old, new);
INIT_LIST_HEAD(old);
}
/**
* list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position
* @entry1: the location to place entry2
* @entry2: the location to place entry1
*/
static inline void list_swap(struct list_head *entry1,
struct list_head *entry2)
{
struct list_head *pos = entry2->prev;
list_del(entry2);
list_replace(entry1, entry2);
if (pos == entry1)
pos = entry2;
list_add(entry1, pos);
}
/**
* list_del_init - deletes entry from list and reinitialize it.
* @entry: the element to delete from the list.
*/
static inline void list_del_init(struct list_head *entry)
{
__list_del_entry(entry);
INIT_LIST_HEAD(entry);
}
/**
* list_move - delete from one list and add as another's head
* @list: the entry to move
* @head: the head that will precede our entry
*/
static inline void list_move(struct list_head *list, struct list_head *head)
{
__list_del_entry(list); list_add(list, head);
}
/**
* list_move_tail - delete from one list and add as another's tail
* @list: the entry to move
* @head: the head that will follow our entry
*/
static inline void list_move_tail(struct list_head *list,
struct list_head *head)
{
__list_del_entry(list); list_add_tail(list, head);
}
/**
* list_bulk_move_tail - move a subsection of a list to its tail
* @head: the head that will follow our entry
* @first: first entry to move
* @last: last entry to move, can be the same as first
*
* Move all entries between @first and including @last before @head.
* All three entries must belong to the same linked list.
*/
static inline void list_bulk_move_tail(struct list_head *head,
struct list_head *first,
struct list_head *last)
{
first->prev->next = last->next;
last->next->prev = first->prev;
head->prev->next = first;
first->prev = head->prev;
last->next = head;
head->prev = last;
}
/**
* list_is_first -- tests whether @list is the first entry in list @head
* @list: the entry to test
* @head: the head of the list
*/
static inline int list_is_first(const struct list_head *list, const struct list_head *head)
{
return list->prev == head;
}
/**
* list_is_last - tests whether @list is the last entry in list @head
* @list: the entry to test
* @head: the head of the list
*/
static inline int list_is_last(const struct list_head *list, const struct list_head *head)
{
return list->next == head;
}
/**
* list_is_head - tests whether @list is the list @head
* @list: the entry to test
* @head: the head of the list
*/
static inline int list_is_head(const struct list_head *list, const struct list_head *head)
{
return list == head;
}
/**
* list_empty - tests whether a list is empty
* @head: the list to test.
*/
static inline int list_empty(const struct list_head *head)
{
return READ_ONCE(head->next) == head;
}
/**
* list_del_init_careful - deletes entry from list and reinitialize it.
* @entry: the element to delete from the list.
*
* This is the same as list_del_init(), except designed to be used
* together with list_empty_careful() in a way to guarantee ordering
* of other memory operations.
*
* Any memory operations done before a list_del_init_careful() are
* guaranteed to be visible after a list_empty_careful() test.
*/
static inline void list_del_init_careful(struct list_head *entry)
{
__list_del_entry(entry);
WRITE_ONCE(entry->prev, entry);
smp_store_release(&entry->next, entry);
}
/**
* list_empty_careful - tests whether a list is empty and not being modified
* @head: the list to test
*
* Description:
* tests whether a list is empty _and_ checks that no other CPU might be
* in the process of modifying either member (next or prev)
*
* NOTE: using list_empty_careful() without synchronization
* can only be safe if the only activity that can happen
* to the list entry is list_del_init(). Eg. it cannot be used
* if another CPU could re-list_add() it.
*/
static inline int list_empty_careful(const struct list_head *head)
{
struct list_head *next = smp_load_acquire(&head->next);
return list_is_head(next, head) && (next == READ_ONCE(head->prev));
}
/**
* list_rotate_left - rotate the list to the left
* @head: the head of the list
*/
static inline void list_rotate_left(struct list_head *head)
{
struct list_head *first;
if (!list_empty(head)) {
first = head->next;
list_move_tail(first, head);
}
}
/**
* list_rotate_to_front() - Rotate list to specific item.
* @list: The desired new front of the list.
* @head: The head of the list.
*
* Rotates list so that @list becomes the new front of the list.
*/
static inline void list_rotate_to_front(struct list_head *list,
struct list_head *head)
{
/*
* Deletes the list head from the list denoted by @head and
* places it as the tail of @list, this effectively rotates the
* list so that @list is at the front.
*/
list_move_tail(head, list);
}
/**
* list_is_singular - tests whether a list has just one entry.
* @head: the list to test.
*/
static inline int list_is_singular(const struct list_head *head)
{
return !list_empty(head) && (head->next == head->prev);
}
static inline void __list_cut_position(struct list_head *list,
struct list_head *head, struct list_head *entry)
{
struct list_head *new_first = entry->next;
list->next = head->next;
list->next->prev = list;
list->prev = entry;
entry->next = list;
head->next = new_first;
new_first->prev = head;
}
/**
* list_cut_position - cut a list into two
* @list: a new list to add all removed entries
* @head: a list with entries
* @entry: an entry within head, could be the head itself
* and if so we won't cut the list
*
* This helper moves the initial part of @head, up to and
* including @entry, from @head to @list. You should
* pass on @entry an element you know is on @head. @list
* should be an empty list or a list you do not care about
* losing its data.
*
*/
static inline void list_cut_position(struct list_head *list,
struct list_head *head, struct list_head *entry)
{
if (list_empty(head))
return;
if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next))
return;
if (list_is_head(entry, head))
INIT_LIST_HEAD(list);
else
__list_cut_position(list, head, entry);
}
/**
* list_cut_before - cut a list into two, before given entry
* @list: a new list to add all removed entries
* @head: a list with entries
* @entry: an entry within head, could be the head itself
*
* This helper moves the initial part of @head, up to but
* excluding @entry, from @head to @list. You should pass
* in @entry an element you know is on @head. @list should
* be an empty list or a list you do not care about losing
* its data.
* If @entry == @head, all entries on @head are moved to
* @list.
*/
static inline void list_cut_before(struct list_head *list,
struct list_head *head,
struct list_head *entry)
{
if (head->next == entry) {
INIT_LIST_HEAD(list);
return;
}
list->next = head->next;
list->next->prev = list;
list->prev = entry->prev;
list->prev->next = list;
head->next = entry;
entry->prev = head;
}
static inline void __list_splice(const struct list_head *list,
struct list_head *prev,
struct list_head *next)
{
struct list_head *first = list->next;
struct list_head *last = list->prev;
first->prev = prev;
prev->next = first;
last->next = next;
next->prev = last;
}
/**
* list_splice - join two lists, this is designed for stacks
* @list: the new list to add.
* @head: the place to add it in the first list.
*/
static inline void list_splice(const struct list_head *list,
struct list_head *head)
{
if (!list_empty(list)) __list_splice(list, head, head->next);
}
/**
* list_splice_tail - join two lists, each list being a queue
* @list: the new list to add.
* @head: the place to add it in the first list.
*/
static inline void list_splice_tail(struct list_head *list,
struct list_head *head)
{
if (!list_empty(list))
__list_splice(list, head->prev, head);
}
/**
* list_splice_init - join two lists and reinitialise the emptied list.
* @list: the new list to add.
* @head: the place to add it in the first list.
*
* The list at @list is reinitialised
*/
static inline void list_splice_init(struct list_head *list,
struct list_head *head)
{
if (!list_empty(list)) { __list_splice(list, head, head->next);
INIT_LIST_HEAD(list);
}
}
/**
* list_splice_tail_init - join two lists and reinitialise the emptied list
* @list: the new list to add.
* @head: the place to add it in the first list.
*
* Each of the lists is a queue.
* The list at @list is reinitialised
*/
static inline void list_splice_tail_init(struct list_head *list,
struct list_head *head)
{
if (!list_empty(list)) { __list_splice(list, head->prev, head);
INIT_LIST_HEAD(list);
}
}
/**
* list_entry - get the struct for this entry
* @ptr: the &struct list_head pointer.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*/
#define list_entry(ptr, type, member) \
container_of(ptr, type, member)
/**
* list_first_entry - get the first element from a list
* @ptr: the list head to take the element from.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* Note, that list is expected to be not empty.
*/
#define list_first_entry(ptr, type, member) \
list_entry((ptr)->next, type, member)
/**
* list_last_entry - get the last element from a list
* @ptr: the list head to take the element from.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* Note, that list is expected to be not empty.
*/
#define list_last_entry(ptr, type, member) \
list_entry((ptr)->prev, type, member)
/**
* list_first_entry_or_null - get the first element from a list
* @ptr: the list head to take the element from.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_head within the struct.
*
* Note that if the list is empty, it returns NULL.
*/
#define list_first_entry_or_null(ptr, type, member) ({ \
struct list_head *head__ = (ptr); \
struct list_head *pos__ = READ_ONCE(head__->next); \
pos__ != head__ ? list_entry(pos__, type, member) : NULL; \
})
/**
* list_next_entry - get the next element in list
* @pos: the type * to cursor
* @member: the name of the list_head within the struct.
*/
#define list_next_entry(pos, member) \
list_entry((pos)->member.next, typeof(*(pos)), member)
/**
* list_next_entry_circular - get the next element in list
* @pos: the type * to cursor.
* @head: the list head to take the element from.
* @member: the name of the list_head within the struct.
*
* Wraparound if pos is the last element (return the first element).
* Note, that list is expected to be not empty.
*/
#define list_next_entry_circular(pos, head, member) \
(list_is_last(&(pos)->member, head) ? \
list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member))
/**
* list_prev_entry - get the prev element in list
* @pos: the type * to cursor
* @member: the name of the list_head within the struct.
*/
#define list_prev_entry(pos, member) \
list_entry((pos)->member.prev, typeof(*(pos)), member)
/**
* list_prev_entry_circular - get the prev element in list
* @pos: the type * to cursor.
* @head: the list head to take the element from.
* @member: the name of the list_head within the struct.
*
* Wraparound if pos is the first element (return the last element).
* Note, that list is expected to be not empty.
*/
#define list_prev_entry_circular(pos, head, member) \
(list_is_first(&(pos)->member, head) ? \
list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member))
/**
* list_for_each - iterate over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
*/
#define list_for_each(pos, head) \
for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
/**
* list_for_each_rcu - Iterate over a list in an RCU-safe fashion
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
*/
#define list_for_each_rcu(pos, head) \
for (pos = rcu_dereference((head)->next); \
!list_is_head(pos, (head)); \
pos = rcu_dereference(pos->next))
/**
* list_for_each_continue - continue iteration over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
*
* Continue to iterate over a list, continuing after the current position.
*/
#define list_for_each_continue(pos, head) \
for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next)
/**
* list_for_each_prev - iterate over a list backwards
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
*/
#define list_for_each_prev(pos, head) \
for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev)
/**
* list_for_each_safe - iterate over a list safe against removal of list entry
* @pos: the &struct list_head to use as a loop cursor.
* @n: another &struct list_head to use as temporary storage
* @head: the head for your list.
*/
#define list_for_each_safe(pos, n, head) \
for (pos = (head)->next, n = pos->next; \
!list_is_head(pos, (head)); \
pos = n, n = pos->next)
/**
* list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
* @pos: the &struct list_head to use as a loop cursor.
* @n: another &struct list_head to use as temporary storage
* @head: the head for your list.
*/
#define list_for_each_prev_safe(pos, n, head) \
for (pos = (head)->prev, n = pos->prev; \
!list_is_head(pos, (head)); \
pos = n, n = pos->prev)
/**
* list_count_nodes - count nodes in the list
* @head: the head for your list.
*/
static inline size_t list_count_nodes(struct list_head *head)
{
struct list_head *pos;
size_t count = 0;
list_for_each(pos, head)
count++;
return count;
}
/**
* list_entry_is_head - test if the entry points to the head of the list
* @pos: the type * to cursor
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*/
#define list_entry_is_head(pos, head, member) \
list_is_head(&pos->member, (head))
/**
* list_for_each_entry - iterate over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*/
#define list_for_each_entry(pos, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member); \
!list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
* list_for_each_entry_reverse - iterate backwards over list of given type.
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*/
#define list_for_each_entry_reverse(pos, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member); \
!list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
* list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
* @pos: the type * to use as a start point
* @head: the head of the list
* @member: the name of the list_head within the struct.
*
* Prepares a pos entry for use as a start point in list_for_each_entry_continue().
*/
#define list_prepare_entry(pos, head, member) \
((pos) ? : list_entry(head, typeof(*pos), member))
/**
* list_for_each_entry_continue - continue iteration over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Continue to iterate over list of given type, continuing after
* the current position.
*/
#define list_for_each_entry_continue(pos, head, member) \
for (pos = list_next_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
* list_for_each_entry_continue_reverse - iterate backwards from the given point
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Start to iterate over list of given type backwards, continuing after
* the current position.
*/
#define list_for_each_entry_continue_reverse(pos, head, member) \
for (pos = list_prev_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
* list_for_each_entry_from - iterate over list of given type from the current point
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Iterate over list of given type, continuing from current position.
*/
#define list_for_each_entry_from(pos, head, member) \
for (; !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
* list_for_each_entry_from_reverse - iterate backwards over list of given type
* from the current point
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Iterate backwards over list of given type, continuing from current position.
*/
#define list_for_each_entry_from_reverse(pos, head, member) \
for (; !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
* list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
* @pos: the type * to use as a loop cursor.
* @n: another type * to use as temporary storage
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*/
#define list_for_each_entry_safe(pos, n, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member), \
n = list_next_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
* list_for_each_entry_safe_continue - continue list iteration safe against removal
* @pos: the type * to use as a loop cursor.
* @n: another type * to use as temporary storage
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Iterate over list of given type, continuing after current point,
* safe against removal of list entry.
*/
#define list_for_each_entry_safe_continue(pos, n, head, member) \
for (pos = list_next_entry(pos, member), \
n = list_next_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
* list_for_each_entry_safe_from - iterate over list from current point safe against removal
* @pos: the type * to use as a loop cursor.
* @n: another type * to use as temporary storage
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Iterate over list of given type from current point, safe against
* removal of list entry.
*/
#define list_for_each_entry_safe_from(pos, n, head, member) \
for (n = list_next_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
* list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
* @pos: the type * to use as a loop cursor.
* @n: another type * to use as temporary storage
* @head: the head for your list.
* @member: the name of the list_head within the struct.
*
* Iterate backwards over list of given type, safe against removal
* of list entry.
*/
#define list_for_each_entry_safe_reverse(pos, n, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member), \
n = list_prev_entry(pos, member); \
!list_entry_is_head(pos, head, member); \
pos = n, n = list_prev_entry(n, member))
/**
* list_safe_reset_next - reset a stale list_for_each_entry_safe loop
* @pos: the loop cursor used in the list_for_each_entry_safe loop
* @n: temporary storage used in list_for_each_entry_safe
* @member: the name of the list_head within the struct.
*
* list_safe_reset_next is not safe to use in general if the list may be
* modified concurrently (eg. the lock is dropped in the loop body). An
* exception to this is if the cursor element (pos) is pinned in the list,
* and list_safe_reset_next is called after re-taking the lock and before
* completing the current iteration of the loop body.
*/
#define list_safe_reset_next(pos, n, member) \
n = list_next_entry(pos, member)
/*
* Double linked lists with a single pointer list head.
* Mostly useful for hash tables where the two pointer list head is
* too wasteful.
* You lose the ability to access the tail in O(1).
*/
#define HLIST_HEAD_INIT { .first = NULL }
#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL }
#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
static inline void INIT_HLIST_NODE(struct hlist_node *h)
{
h->next = NULL;
h->pprev = NULL;
}
/**
* hlist_unhashed - Has node been removed from list and reinitialized?
* @h: Node to be checked
*
* Not that not all removal functions will leave a node in unhashed
* state. For example, hlist_nulls_del_init_rcu() does leave the
* node in unhashed state, but hlist_nulls_del() does not.
*/
static inline int hlist_unhashed(const struct hlist_node *h)
{
return !h->pprev;
}
/**
* hlist_unhashed_lockless - Version of hlist_unhashed for lockless use
* @h: Node to be checked
*
* This variant of hlist_unhashed() must be used in lockless contexts
* to avoid potential load-tearing. The READ_ONCE() is paired with the
* various WRITE_ONCE() in hlist helpers that are defined below.
*/
static inline int hlist_unhashed_lockless(const struct hlist_node *h)
{
return !READ_ONCE(h->pprev);
}
/**
* hlist_empty - Is the specified hlist_head structure an empty hlist?
* @h: Structure to check.
*/
static inline int hlist_empty(const struct hlist_head *h)
{
return !READ_ONCE(h->first);
}
static inline void __hlist_del(struct hlist_node *n)
{
struct hlist_node *next = n->next;
struct hlist_node **pprev = n->pprev;
WRITE_ONCE(*pprev, next);
if (next) WRITE_ONCE(next->pprev, pprev);
}
/**
* hlist_del - Delete the specified hlist_node from its list
* @n: Node to delete.
*
* Note that this function leaves the node in hashed state. Use
* hlist_del_init() or similar instead to unhash @n.
*/
static inline void hlist_del(struct hlist_node *n)
{
__hlist_del(n); n->next = LIST_POISON1;
n->pprev = LIST_POISON2;
}
/**
* hlist_del_init - Delete the specified hlist_node from its list and initialize
* @n: Node to delete.
*
* Note that this function leaves the node in unhashed state.
*/
static inline void hlist_del_init(struct hlist_node *n)
{
if (!hlist_unhashed(n)) { __hlist_del(n);
INIT_HLIST_NODE(n);
}
}
/**
* hlist_add_head - add a new entry at the beginning of the hlist
* @n: new entry to be added
* @h: hlist head to add it after
*
* Insert a new entry after the specified head.
* This is good for implementing stacks.
*/
static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
{
struct hlist_node *first = h->first;
WRITE_ONCE(n->next, first);
if (first) WRITE_ONCE(first->pprev, &n->next);
WRITE_ONCE(h->first, n);
WRITE_ONCE(n->pprev, &h->first);
}
/**
* hlist_add_before - add a new entry before the one specified
* @n: new entry to be added
* @next: hlist node to add it before, which must be non-NULL
*/
static inline void hlist_add_before(struct hlist_node *n,
struct hlist_node *next)
{
WRITE_ONCE(n->pprev, next->pprev);
WRITE_ONCE(n->next, next);
WRITE_ONCE(next->pprev, &n->next);
WRITE_ONCE(*(n->pprev), n);
}
/**
* hlist_add_behind - add a new entry after the one specified
* @n: new entry to be added
* @prev: hlist node to add it after, which must be non-NULL
*/
static inline void hlist_add_behind(struct hlist_node *n,
struct hlist_node *prev)
{
WRITE_ONCE(n->next, prev->next);
WRITE_ONCE(prev->next, n);
WRITE_ONCE(n->pprev, &prev->next);
if (n->next)
WRITE_ONCE(n->next->pprev, &n->next);
}
/**
* hlist_add_fake - create a fake hlist consisting of a single headless node
* @n: Node to make a fake list out of
*
* This makes @n appear to be its own predecessor on a headless hlist.
* The point of this is to allow things like hlist_del() to work correctly
* in cases where there is no list.
*/
static inline void hlist_add_fake(struct hlist_node *n)
{
n->pprev = &n->next;
}
/**
* hlist_fake: Is this node a fake hlist?
* @h: Node to check for being a self-referential fake hlist.
*/
static inline bool hlist_fake(struct hlist_node *h)
{
return h->pprev == &h->next;
}
/**
* hlist_is_singular_node - is node the only element of the specified hlist?
* @n: Node to check for singularity.
* @h: Header for potentially singular list.
*
* Check whether the node is the only node of the head without
* accessing head, thus avoiding unnecessary cache misses.
*/
static inline bool
hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h)
{
return !n->next && n->pprev == &h->first;
}
/**
* hlist_move_list - Move an hlist
* @old: hlist_head for old list.
* @new: hlist_head for new list.
*
* Move a list from one list head to another. Fixup the pprev
* reference of the first entry if it exists.
*/
static inline void hlist_move_list(struct hlist_head *old,
struct hlist_head *new)
{
new->first = old->first;
if (new->first)
new->first->pprev = &new->first;
old->first = NULL;
}
/**
* hlist_splice_init() - move all entries from one list to another
* @from: hlist_head from which entries will be moved
* @last: last entry on the @from list
* @to: hlist_head to which entries will be moved
*
* @to can be empty, @from must contain at least @last.
*/
static inline void hlist_splice_init(struct hlist_head *from,
struct hlist_node *last,
struct hlist_head *to)
{
if (to->first) to->first->pprev = &last->next;
last->next = to->first;
to->first = from->first;
from->first->pprev = &to->first;
from->first = NULL;
}
#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
#define hlist_for_each(pos, head) \
for (pos = (head)->first; pos ; pos = pos->next)
#define hlist_for_each_safe(pos, n, head) \
for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
pos = n)
#define hlist_entry_safe(ptr, type, member) \
({ typeof(ptr) ____ptr = (ptr); \
____ptr ? hlist_entry(____ptr, type, member) : NULL; \
})
/**
* hlist_for_each_entry - iterate over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry(pos, head, member) \
for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
pos; \
pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
/**
* hlist_for_each_entry_continue - iterate over a hlist continuing after current point
* @pos: the type * to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_continue(pos, member) \
for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\
pos; \
pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
/**
* hlist_for_each_entry_from - iterate over a hlist continuing from current point
* @pos: the type * to use as a loop cursor.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_from(pos, member) \
for (; pos; \
pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
/**
* hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
* @pos: the type * to use as a loop cursor.
* @n: a &struct hlist_node to use as temporary storage
* @head: the head for your list.
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_safe(pos, n, head, member) \
for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\
pos && ({ n = pos->member.next; 1; }); \
pos = hlist_entry_safe(n, typeof(*pos), member))
/**
* hlist_count_nodes - count nodes in the hlist
* @head: the head for your hlist.
*/
static inline size_t hlist_count_nodes(struct hlist_head *head)
{
struct hlist_node *pos;
size_t count = 0;
hlist_for_each(pos, head)
count++;
return count;
}
#endif
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_MMU_H
#define __ASM_MMU_H
#include <asm/cputype.h>
#define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */
#define USER_ASID_BIT 48
#define USER_ASID_FLAG (UL(1) << USER_ASID_BIT)
#define TTBR_ASID_MASK (UL(0xffff) << 48)
#ifndef __ASSEMBLY__
#include <linux/refcount.h>
#include <asm/cpufeature.h>
typedef struct {
atomic64_t id;
#ifdef CONFIG_COMPAT
void *sigpage;
#endif
refcount_t pinned;
void *vdso;
unsigned long flags;
u8 pkey_allocation_map;
} mm_context_t;
/*
* We use atomic64_read() here because the ASID for an 'mm_struct' can
* be reallocated when scheduling one of its threads following a
* rollover event (see new_context() and flush_context()). In this case,
* a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush())
* may use a stale ASID. This is fine in principle as the new ASID is
* guaranteed to be clean in the TLB, but the TLBI routines have to take
* care to handle the following race:
*
* CPU 0 CPU 1 CPU 2
*
* // ptep_clear_flush(mm)
* xchg_relaxed(pte, 0)
* DSB ISHST
* old = ASID(mm)
* | <rollover>
* | new = new_context(mm)
* \-----------------> atomic_set(mm->context.id, new)
* cpu_switch_mm(mm)
* // Hardware walk of pte using new ASID
* TLBI(old)
*
* In this scenario, the barrier on CPU 0 and the dependency on CPU 1
* ensure that the page-table walker on CPU 1 *must* see the invalid PTE
* written by CPU 0.
*/
#define ASID(mm) (atomic64_read(&(mm)->context.id) & 0xffff)
static inline bool arm64_kernel_unmapped_at_el0(void)
{
return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0);
}
extern void arm64_memblock_init(void);
extern void paging_init(void);
extern void bootmem_init(void);
extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot, bool page_mappings_only);
extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot);
extern void mark_linear_text_alias_ro(void);
/*
* This check is triggered during the early boot before the cpufeature
* is initialised. Checking the status on the local CPU allows the boot
* CPU to detect the need for non-global mappings and thus avoiding a
* pagetable re-write after all the CPUs are booted. This check will be
* anyway run on individual CPUs, allowing us to get the consistent
* state once the SMP CPUs are up and thus make the switch to non-global
* mappings if required.
*/
static inline bool kaslr_requires_kpti(void)
{
/*
* E0PD does a similar job to KPTI so can be used instead
* where available.
*/
if (IS_ENABLED(CONFIG_ARM64_E0PD)) {
u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1);
if (cpuid_feature_extract_unsigned_field(mmfr2,
ID_AA64MMFR2_EL1_E0PD_SHIFT))
return false;
}
return true;
}
#endif /* !__ASSEMBLY__ */
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/mmap.c
*
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/io.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <asm/cpufeature.h>
#include <asm/page.h>
static pgprot_t protection_map[16] __ro_after_init = {
[VM_NONE] = PAGE_NONE,
[VM_READ] = PAGE_READONLY,
[VM_WRITE] = PAGE_READONLY,
[VM_WRITE | VM_READ] = PAGE_READONLY,
/* PAGE_EXECONLY if Enhanced PAN */
[VM_EXEC] = PAGE_READONLY_EXEC,
[VM_EXEC | VM_READ] = PAGE_READONLY_EXEC,
[VM_EXEC | VM_WRITE] = PAGE_READONLY_EXEC,
[VM_EXEC | VM_WRITE | VM_READ] = PAGE_READONLY_EXEC,
[VM_SHARED] = PAGE_NONE,
[VM_SHARED | VM_READ] = PAGE_READONLY,
[VM_SHARED | VM_WRITE] = PAGE_SHARED,
[VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED,
/* PAGE_EXECONLY if Enhanced PAN */
[VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC,
[VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC,
[VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC,
[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC
};
/*
* You really shouldn't be using read() or write() on /dev/mem. This might go
* away in the future.
*/
int valid_phys_addr_range(phys_addr_t addr, size_t size)
{
/*
* Check whether addr is covered by a memory region without the
* MEMBLOCK_NOMAP attribute, and whether that region covers the
* entire range. In theory, this could lead to false negatives
* if the range is covered by distinct but adjacent memory regions
* that only differ in other attributes. However, few of such
* attributes have been defined, and it is debatable whether it
* follows that /dev/mem read() calls should be able traverse
* such boundaries.
*/
return memblock_is_region_memory(addr, size) &&
memblock_is_map_memory(addr);
}
/*
* Do not allow /dev/mem mappings beyond the supported physical range.
*/
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK);
}
static int __init adjust_protection_map(void)
{
/*
* With Enhanced PAN we can honour the execute-only permissions as
* there is no PAN override with such mappings.
*/
if (cpus_have_cap(ARM64_HAS_EPAN)) {
protection_map[VM_EXEC] = PAGE_EXECONLY;
protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
}
if (lpa2_is_enabled())
for (int i = 0; i < ARRAY_SIZE(protection_map); i++)
pgprot_val(protection_map[i]) &= ~PTE_SHARED;
return 0;
}
arch_initcall(adjust_protection_map);
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
pteval_t prot;
/* Short circuit GCS to avoid bloating the table. */
if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
prot = _PAGE_GCS_RO;
} else {
prot = pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
}
if (vm_flags & VM_ARM64_BTI)
prot |= PTE_GP;
/*
* There are two conditions required for returning a Normal Tagged
* memory type: (1) the user requested it via PROT_MTE passed to
* mmap() or mprotect() and (2) the corresponding vma supports MTE. We
* register (1) as VM_MTE in the vma->vm_flags and (2) as
* VM_MTE_ALLOWED. Note that the latter can only be set during the
* mmap() call since mprotect() does not accept MAP_* flags.
* Checking for VM_MTE only is sufficient since arch_validate_flags()
* does not permit (VM_MTE & !VM_MTE_ALLOWED).
*/
if (vm_flags & VM_MTE)
prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
#ifdef CONFIG_ARCH_HAS_PKEYS
if (system_supports_poe()) { if (vm_flags & VM_PKEY_BIT0)
prot |= PTE_PO_IDX_0;
if (vm_flags & VM_PKEY_BIT1)
prot |= PTE_PO_IDX_1;
if (vm_flags & VM_PKEY_BIT2)
prot |= PTE_PO_IDX_2;
}
#endif
return __pgprot(prot);
}
EXPORT_SYMBOL(vm_get_page_prot);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* kernel/workqueue_internal.h
*
* Workqueue internal header file. Only to be included by workqueue and
* core kernel subsystems.
*/
#ifndef _KERNEL_WORKQUEUE_INTERNAL_H
#define _KERNEL_WORKQUEUE_INTERNAL_H
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/preempt.h>
struct worker_pool;
/*
* The poor guys doing the actual heavy lifting. All on-duty workers are
* either serving the manager role, on idle list or on busy hash. For
* details on the locking annotation (L, I, X...), refer to workqueue.c.
*
* Only to be used in workqueue and async.
*/
struct worker {
/* on idle list while idle, on busy hash table while busy */
union {
struct list_head entry; /* L: while idle */
struct hlist_node hentry; /* L: while busy */
};
struct work_struct *current_work; /* K: work being processed and its */
work_func_t current_func; /* K: function */
struct pool_workqueue *current_pwq; /* K: pwq */
u64 current_at; /* K: runtime at start or last wakeup */
unsigned int current_color; /* K: color */
int sleeping; /* S: is worker sleeping? */
/* used by the scheduler to determine a worker's last known identity */
work_func_t last_func; /* K: last work's fn */
struct list_head scheduled; /* L: scheduled works */
struct task_struct *task; /* I: worker task */
struct worker_pool *pool; /* A: the associated pool */
/* L: for rescuers */
struct list_head node; /* A: anchored at pool->workers */
/* A: runs through worker->node */
unsigned long last_active; /* K: last active timestamp */
unsigned int flags; /* L: flags */
int id; /* I: worker id */
/*
* Opaque string set with work_set_desc(). Printed out with task
* dump for debugging - WARN, BUG, panic or sysrq.
*/
char desc[WORKER_DESC_LEN];
/* used only by rescuers to point to the target workqueue */
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
};
/**
* current_wq_worker - return struct worker if %current is a workqueue worker
*/
static inline struct worker *current_wq_worker(void)
{
if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current);
return NULL;
}
/*
* Scheduler hooks for concurrency managed workqueue. Only to be used from
* sched/ and workqueue.c.
*/
void wq_worker_running(struct task_struct *task);
void wq_worker_sleeping(struct task_struct *task);
void wq_worker_tick(struct task_struct *task);
work_func_t wq_worker_last_func(struct task_struct *task);
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/kvm_host.h>
#include <linux/irqchip/arm-gic-v3.h>
#include "vgic.h"
/*
* How KVM uses GICv4 (insert rude comments here):
*
* The vgic-v4 layer acts as a bridge between several entities:
* - The GICv4 ITS representation offered by the ITS driver
* - VFIO, which is in charge of the PCI endpoint
* - The virtual ITS, which is the only thing the guest sees
*
* The configuration of VLPIs is triggered by a callback from VFIO,
* instructing KVM that a PCI device has been configured to deliver
* MSIs to a vITS.
*
* kvm_vgic_v4_set_forwarding() is thus called with the routing entry,
* and this is used to find the corresponding vITS data structures
* (ITS instance, device, event and irq) using a process that is
* extremely similar to the injection of an MSI.
*
* At this stage, we can link the guest's view of an LPI (uniquely
* identified by the routing entry) and the host irq, using the GICv4
* driver mapping operation. Should the mapping succeed, we've then
* successfully upgraded the guest's LPI to a VLPI. We can then start
* with updating GICv4's view of the property table and generating an
* INValidation in order to kickstart the delivery of this VLPI to the
* guest directly, without software intervention. Well, almost.
*
* When the PCI endpoint is deconfigured, this operation is reversed
* with VFIO calling kvm_vgic_v4_unset_forwarding().
*
* Once the VLPI has been mapped, it needs to follow any change the
* guest performs on its LPI through the vITS. For that, a number of
* command handlers have hooks to communicate these changes to the HW:
* - Any invalidation triggers a call to its_prop_update_vlpi()
* - The INT command results in a irq_set_irqchip_state(), which
* generates an INT on the corresponding VLPI.
* - The CLEAR command results in a irq_set_irqchip_state(), which
* generates an CLEAR on the corresponding VLPI.
* - DISCARD translates into an unmap, similar to a call to
* kvm_vgic_v4_unset_forwarding().
* - MOVI is translated by an update of the existing mapping, changing
* the target vcpu, resulting in a VMOVI being generated.
* - MOVALL is translated by a string of mapping updates (similar to
* the handling of MOVI). MOVALL is horrible.
*
* Note that a DISCARD/MAPTI sequence emitted from the guest without
* reprogramming the PCI endpoint after MAPTI does not result in a
* VLPI being mapped, as there is no callback from VFIO (the guest
* will get the interrupt via the normal SW injection). Fixing this is
* not trivial, and requires some horrible messing with the VFIO
* internals. Not fun. Don't do that.
*
* Then there is the scheduling. Each time a vcpu is about to run on a
* physical CPU, KVM must tell the corresponding redistributor about
* it. And if we've migrated our vcpu from one CPU to another, we must
* tell the ITS (so that the messages reach the right redistributor).
* This is done in two steps: first issue a irq_set_affinity() on the
* irq corresponding to the vcpu, then call its_make_vpe_resident().
* You must be in a non-preemptible context. On exit, a call to
* its_make_vpe_non_resident() tells the redistributor that we're done
* with the vcpu.
*
* Finally, the doorbell handling: Each vcpu is allocated an interrupt
* which will fire each time a VLPI is made pending whilst the vcpu is
* not running. Each time the vcpu gets blocked, the doorbell
* interrupt gets enabled. When the vcpu is unblocked (for whatever
* reason), the doorbell interrupt is disabled.
*/
#define DB_IRQ_FLAGS (IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY | IRQ_NO_BALANCING)
static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
{
struct kvm_vcpu *vcpu = info;
/* We got the message, no need to fire again */
if (!kvm_vgic_global_state.has_gicv4_1 &&
!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
disable_irq_nosync(irq);
/*
* The v4.1 doorbell can fire concurrently with the vPE being
* made non-resident. Ensure we only update pending_last
* *after* the non-residency sequence has completed.
*/
raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
return IRQ_HANDLED;
}
static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq)
{
vpe->sgi_config[irq->intid].enabled = irq->enabled;
vpe->sgi_config[irq->intid].group = irq->group;
vpe->sgi_config[irq->intid].priority = irq->priority;
}
static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu)
{
struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
int i;
/*
* With GICv4.1, every virtual SGI can be directly injected. So
* let's pretend that they are HW interrupts, tied to a host
* IRQ. The SGI code will do its magic.
*/
for (i = 0; i < VGIC_NR_SGIS; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i);
struct irq_desc *desc;
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw)
goto unlock;
irq->hw = true;
irq->host_irq = irq_find_mapping(vpe->sgi_domain, i);
/* Transfer the full irq state to the vPE */
vgic_v4_sync_sgi_config(vpe, irq);
desc = irq_to_desc(irq->host_irq);
ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc),
false);
if (!WARN_ON(ret)) {
/* Transfer pending state */
ret = irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
irq->pending_latch);
WARN_ON(ret);
irq->pending_latch = false;
}
unlock:
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu)
{
int i;
for (i = 0; i < VGIC_NR_SGIS; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i);
struct irq_desc *desc;
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (!irq->hw)
goto unlock;
irq->hw = false;
ret = irq_get_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
&irq->pending_latch);
WARN_ON(ret);
desc = irq_to_desc(irq->host_irq);
irq_domain_deactivate_irq(irq_desc_get_irq_data(desc));
unlock:
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
void vgic_v4_configure_vsgis(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
unsigned long i;
lockdep_assert_held(&kvm->arch.config_lock);
kvm_arm_halt_guest(kvm);
kvm_for_each_vcpu(i, vcpu, kvm) {
if (dist->nassgireq)
vgic_v4_enable_vsgis(vcpu);
else
vgic_v4_disable_vsgis(vcpu);
}
kvm_arm_resume_guest(kvm);
}
/*
* Must be called with GICv4.1 and the vPE unmapped, which
* indicates the invalidation of any VPT caches associated
* with the vPE, thus we can get the VLPI state by peeking
* at the VPT.
*/
void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val)
{
struct its_vpe *vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
int mask = BIT(irq->intid % BITS_PER_BYTE);
void *va;
u8 *ptr;
va = page_address(vpe->vpt_page);
ptr = va + irq->intid / BITS_PER_BYTE;
*val = !!(*ptr & mask);
}
int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq)
{
return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu);
}
/**
* vgic_v4_init - Initialize the GICv4 data structures
* @kvm: Pointer to the VM being initialized
*
* We may be called each time a vITS is created, or when the
* vgic is initialized. In both cases, the number of vcpus
* should now be fixed.
*/
int vgic_v4_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int nr_vcpus, ret;
unsigned long i;
lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vgic_global_state.has_gicv4)
return 0; /* Nothing to see here... move along. */
if (dist->its_vm.vpes)
return 0;
nr_vcpus = atomic_read(&kvm->online_vcpus);
dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes),
GFP_KERNEL_ACCOUNT);
if (!dist->its_vm.vpes)
return -ENOMEM;
dist->its_vm.nr_vpes = nr_vcpus;
kvm_for_each_vcpu(i, vcpu, kvm)
dist->its_vm.vpes[i] = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
ret = its_alloc_vcpu_irqs(&dist->its_vm);
if (ret < 0) {
kvm_err("VPE IRQ allocation failure\n");
kfree(dist->its_vm.vpes);
dist->its_vm.nr_vpes = 0;
dist->its_vm.vpes = NULL;
return ret;
}
kvm_for_each_vcpu(i, vcpu, kvm) {
int irq = dist->its_vm.vpes[i]->irq;
unsigned long irq_flags = DB_IRQ_FLAGS;
/*
* Don't automatically enable the doorbell, as we're
* flipping it back and forth when the vcpu gets
* blocked. Also disable the lazy disabling, as the
* doorbell could kick us out of the guest too
* early...
*
* On GICv4.1, the doorbell is managed in HW and must
* be left enabled.
*/
if (kvm_vgic_global_state.has_gicv4_1)
irq_flags &= ~IRQ_NOAUTOEN;
irq_set_status_flags(irq, irq_flags);
ret = vgic_v4_request_vpe_irq(vcpu, irq);
if (ret) {
kvm_err("failed to allocate vcpu IRQ%d\n", irq);
/*
* Trick: adjust the number of vpes so we know
* how many to nuke on teardown...
*/
dist->its_vm.nr_vpes = i;
break;
}
}
if (ret)
vgic_v4_teardown(kvm);
return ret;
}
/**
* vgic_v4_teardown - Free the GICv4 data structures
* @kvm: Pointer to the VM being destroyed
*/
void vgic_v4_teardown(struct kvm *kvm)
{
struct its_vm *its_vm = &kvm->arch.vgic.its_vm;
int i;
lockdep_assert_held(&kvm->arch.config_lock);
if (!its_vm->vpes)
return;
for (i = 0; i < its_vm->nr_vpes; i++) {
struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, i);
int irq = its_vm->vpes[i]->irq;
irq_clear_status_flags(irq, DB_IRQ_FLAGS);
free_irq(irq, vcpu);
}
its_free_vcpu_irqs(its_vm);
kfree(its_vm->vpes);
its_vm->nr_vpes = 0;
its_vm->vpes = NULL;
}
static inline bool vgic_v4_want_doorbell(struct kvm_vcpu *vcpu)
{
if (vcpu_get_flag(vcpu, IN_WFI))
return true;
if (likely(!vcpu_has_nv(vcpu)))
return false;
/*
* GICv4 hardware is only ever used for the L1. Mark the vPE (i.e. the
* L1 context) nonresident and request a doorbell to kick us out of the
* L2 when an IRQ becomes pending.
*/
return vcpu_get_flag(vcpu, IN_NESTED_ERET);
}
int vgic_v4_put(struct kvm_vcpu *vcpu)
{
struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
return 0;
return its_make_vpe_non_resident(vpe, vgic_v4_want_doorbell(vcpu));
}
int vgic_v4_load(struct kvm_vcpu *vcpu)
{
struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
int err;
if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
return 0;
if (vcpu_get_flag(vcpu, IN_WFI))
return 0;
/*
* Before making the VPE resident, make sure the redistributor
* corresponding to our current CPU expects us here. See the
* doc in drivers/irqchip/irq-gic-v4.c to understand how this
* turns into a VMOVP command at the ITS level.
*/
err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id()));
if (err)
return err;
err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled);
if (err)
return err;
/*
* Now that the VPE is resident, let's get rid of a potential
* doorbell interrupt that would still be pending. This is a
* GICv4.0 only "feature"...
*/
if (!kvm_vgic_global_state.has_gicv4_1) err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
return err;
}
void vgic_v4_commit(struct kvm_vcpu *vcpu)
{
struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
/*
* No need to wait for the vPE to be ready across a shallow guest
* exit, as only a vcpu_put will invalidate it.
*/
if (!vpe->ready)
its_commit_vpe(vpe);
}
static struct vgic_its *vgic_get_its(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *irq_entry)
{
struct kvm_msi msi = (struct kvm_msi) {
.address_lo = irq_entry->msi.address_lo,
.address_hi = irq_entry->msi.address_hi,
.data = irq_entry->msi.data,
.flags = irq_entry->msi.flags,
.devid = irq_entry->msi.devid,
};
return vgic_msi_to_its(kvm, &msi);
}
int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
struct kvm_kernel_irq_routing_entry *irq_entry)
{
struct vgic_its *its;
struct vgic_irq *irq;
struct its_vlpi_map map;
unsigned long flags;
int ret = 0;
if (!vgic_supports_direct_msis(kvm))
return 0;
/*
* Get the ITS, and escape early on error (not a valid
* doorbell for any of our vITSs).
*/
its = vgic_get_its(kvm, irq_entry);
if (IS_ERR(its))
return 0;
mutex_lock(&its->its_lock);
/*
* Perform the actual DevID/EventID -> LPI translation.
*
* Silently exit if translation fails as the guest (or userspace!) has
* managed to do something stupid. Emulated LPI injection will still
* work if the guest figures itself out at a later time.
*/
if (vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
irq_entry->msi.data, &irq))
goto out;
/* Silently exit if the vLPI is already mapped */
if (irq->hw)
goto out;
/*
* Emit the mapping request. If it fails, the ITS probably
* isn't v4 compatible, so let's silently bail out. Holding
* the ITS lock should ensure that nothing can modify the
* target vcpu.
*/
map = (struct its_vlpi_map) {
.vm = &kvm->arch.vgic.its_vm,
.vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe,
.vintid = irq->intid,
.properties = ((irq->priority & 0xfc) |
(irq->enabled ? LPI_PROP_ENABLED : 0) |
LPI_PROP_GROUP1),
.db_enabled = true,
};
ret = its_map_vlpi(virq, &map);
if (ret)
goto out;
irq->hw = true;
irq->host_irq = virq;
atomic_inc(&map.vpe->vlpi_count);
/* Transfer pending state */
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->pending_latch) {
ret = irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
irq->pending_latch);
WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq);
/*
* Clear pending_latch and communicate this state
* change via vgic_queue_irq_unlock.
*/
irq->pending_latch = false;
vgic_queue_irq_unlock(kvm, irq, flags);
} else {
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
}
out:
mutex_unlock(&its->its_lock);
return ret;
}
int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
struct kvm_kernel_irq_routing_entry *irq_entry)
{
struct vgic_its *its;
struct vgic_irq *irq;
int ret;
if (!vgic_supports_direct_msis(kvm))
return 0;
/*
* Get the ITS, and escape early on error (not a valid
* doorbell for any of our vITSs).
*/
its = vgic_get_its(kvm, irq_entry);
if (IS_ERR(its))
return 0;
mutex_lock(&its->its_lock);
ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
irq_entry->msi.data, &irq);
if (ret)
goto out;
WARN_ON(irq->hw && irq->host_irq != virq);
if (irq->hw) {
atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
irq->hw = false;
ret = its_unmap_vlpi(virq);
}
out:
mutex_unlock(&its->its_lock);
return ret;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Fault injection for both 32 and 64bit guests.
*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Based on arch/arm/kvm/emulate.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_nested.h>
#include <asm/esr.h>
static void pend_sync_exception(struct kvm_vcpu *vcpu)
{
/* If not nesting, EL1 is the only possible exception target */
if (likely(!vcpu_has_nv(vcpu))) { kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
return;
}
/*
* With NV, we need to pick between EL1 and EL2. Note that we
* never deal with a nesting exception here, hence never
* changing context, and the exception itself can be delayed
* until the next entry.
*/
switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) {
case PSR_MODE_EL2h:
case PSR_MODE_EL2t:
kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC);
break;
case PSR_MODE_EL1h:
case PSR_MODE_EL1t:
kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
break;
case PSR_MODE_EL0t:
if (vcpu_el2_tge_is_set(vcpu)) kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC);
else
kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
break;
default:
BUG();
}
}
static bool match_target_el(struct kvm_vcpu *vcpu, unsigned long target)
{
return (vcpu_get_flag(vcpu, EXCEPT_MASK) == target);
}
static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
{
unsigned long cpsr = *vcpu_cpsr(vcpu);
bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
u64 esr = 0;
pend_sync_exception(vcpu);
/*
* Build an {i,d}abort, depending on the level and the
* instruction set. Report an external synchronous abort.
*/
if (kvm_vcpu_trap_il_is32bit(vcpu))
esr |= ESR_ELx_IL;
/*
* Here, the guest runs in AArch64 mode when in EL1. If we get
* an AArch32 fault, it means we managed to trap an EL0 fault.
*/
if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t)
esr |= (ESR_ELx_EC_IABT_LOW << ESR_ELx_EC_SHIFT);
else
esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
if (!is_iabt)
esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
esr |= ESR_ELx_FSC_EXTABT;
if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) {
vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
} else {
vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
}
}
static void inject_undef64(struct kvm_vcpu *vcpu)
{
u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
pend_sync_exception(vcpu);
/*
* Build an unknown exception, depending on the instruction
* set.
*/
if (kvm_vcpu_trap_il_is32bit(vcpu))
esr |= ESR_ELx_IL;
if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC)))
vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
else
vcpu_write_sys_reg(vcpu, esr, ESR_EL2);
}
#define DFSR_FSC_EXTABT_LPAE 0x10
#define DFSR_FSC_EXTABT_nLPAE 0x08
#define DFSR_LPAE BIT(9)
#define TTBCR_EAE BIT(31)
static void inject_undef32(struct kvm_vcpu *vcpu)
{
kvm_pend_exception(vcpu, EXCEPT_AA32_UND);
}
/*
* Modelled after TakeDataAbortException() and TakePrefetchAbortException
* pseudocode.
*/
static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
{
u64 far;
u32 fsr;
/* Give the guest an IMPLEMENTATION DEFINED exception */
if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) {
fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
} else {
/* no need to shuffle FS[4] into DFSR[10] as it's 0 */
fsr = DFSR_FSC_EXTABT_nLPAE;
}
far = vcpu_read_sys_reg(vcpu, FAR_EL1);
if (is_pabt) {
kvm_pend_exception(vcpu, EXCEPT_AA32_IABT);
far &= GENMASK(31, 0);
far |= (u64)addr << 32;
vcpu_write_sys_reg(vcpu, fsr, IFSR32_EL2);
} else { /* !iabt */
kvm_pend_exception(vcpu, EXCEPT_AA32_DABT);
far &= GENMASK(63, 32);
far |= addr;
vcpu_write_sys_reg(vcpu, fsr, ESR_EL1);
}
vcpu_write_sys_reg(vcpu, far, FAR_EL1);
}
/**
* kvm_inject_dabt - inject a data abort into the guest
* @vcpu: The VCPU to receive the data abort
* @addr: The address to report in the DFAR
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
{
if (vcpu_el1_is_32bit(vcpu))
inject_abt32(vcpu, false, addr);
else
inject_abt64(vcpu, false, addr);
}
/**
* kvm_inject_pabt - inject a prefetch abort into the guest
* @vcpu: The VCPU to receive the prefetch abort
* @addr: The address to report in the DFAR
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
{
if (vcpu_el1_is_32bit(vcpu))
inject_abt32(vcpu, true, addr);
else
inject_abt64(vcpu, true, addr);
}
void kvm_inject_size_fault(struct kvm_vcpu *vcpu)
{
unsigned long addr, esr;
addr = kvm_vcpu_get_fault_ipa(vcpu);
addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
if (kvm_vcpu_trap_is_iabt(vcpu))
kvm_inject_pabt(vcpu, addr);
else
kvm_inject_dabt(vcpu, addr);
/*
* If AArch64 or LPAE, set FSC to 0 to indicate an Address
* Size Fault at level 0, as if exceeding PARange.
*
* Non-LPAE guests will only get the external abort, as there
* is no way to describe the ASF.
*/
if (vcpu_el1_is_32bit(vcpu) &&
!(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE))
return;
esr = vcpu_read_sys_reg(vcpu, ESR_EL1);
esr &= ~GENMASK_ULL(5, 0);
vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
}
/**
* kvm_inject_undefined - inject an undefined instruction into the guest
* @vcpu: The vCPU in which to inject the exception
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_undefined(struct kvm_vcpu *vcpu)
{
if (vcpu_el1_is_32bit(vcpu))
inject_undef32(vcpu);
else
inject_undef64(vcpu);
}
void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 esr)
{
vcpu_set_vsesr(vcpu, esr & ESR_ELx_ISS_MASK);
*vcpu_hcr(vcpu) |= HCR_VSE;
}
/**
* kvm_inject_vabt - inject an async abort / SError into the guest
* @vcpu: The VCPU to receive the exception
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*
* Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with
* the remaining ISS all-zeros so that this error is not interpreted as an
* uncategorized RAS error. Without the RAS Extensions we can't specify an ESR
* value, so the CPU generates an imp-def value.
*/
void kvm_inject_vabt(struct kvm_vcpu *vcpu)
{
kvm_set_sei_esr(vcpu, ESR_ELx_ISV);
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012-2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <hyp/adjust_pc.h>
#include <linux/compiler.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#define vtr_to_max_lr_idx(v) ((v) & 0xf)
#define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1)
#define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5))
u64 __gic_v3_get_lr(unsigned int lr)
{
switch (lr & 0xf) {
case 0:
return read_gicreg(ICH_LR0_EL2);
case 1:
return read_gicreg(ICH_LR1_EL2);
case 2:
return read_gicreg(ICH_LR2_EL2);
case 3:
return read_gicreg(ICH_LR3_EL2);
case 4:
return read_gicreg(ICH_LR4_EL2);
case 5:
return read_gicreg(ICH_LR5_EL2);
case 6:
return read_gicreg(ICH_LR6_EL2);
case 7:
return read_gicreg(ICH_LR7_EL2);
case 8:
return read_gicreg(ICH_LR8_EL2);
case 9:
return read_gicreg(ICH_LR9_EL2);
case 10:
return read_gicreg(ICH_LR10_EL2);
case 11:
return read_gicreg(ICH_LR11_EL2);
case 12:
return read_gicreg(ICH_LR12_EL2);
case 13:
return read_gicreg(ICH_LR13_EL2);
case 14:
return read_gicreg(ICH_LR14_EL2);
case 15:
return read_gicreg(ICH_LR15_EL2);
}
unreachable();
}
static void __gic_v3_set_lr(u64 val, int lr)
{
switch (lr & 0xf) {
case 0:
write_gicreg(val, ICH_LR0_EL2);
break;
case 1:
write_gicreg(val, ICH_LR1_EL2);
break;
case 2:
write_gicreg(val, ICH_LR2_EL2);
break;
case 3:
write_gicreg(val, ICH_LR3_EL2);
break;
case 4:
write_gicreg(val, ICH_LR4_EL2);
break;
case 5:
write_gicreg(val, ICH_LR5_EL2);
break;
case 6:
write_gicreg(val, ICH_LR6_EL2);
break;
case 7:
write_gicreg(val, ICH_LR7_EL2);
break;
case 8:
write_gicreg(val, ICH_LR8_EL2);
break;
case 9:
write_gicreg(val, ICH_LR9_EL2);
break;
case 10:
write_gicreg(val, ICH_LR10_EL2);
break;
case 11:
write_gicreg(val, ICH_LR11_EL2);
break;
case 12:
write_gicreg(val, ICH_LR12_EL2);
break;
case 13:
write_gicreg(val, ICH_LR13_EL2);
break;
case 14:
write_gicreg(val, ICH_LR14_EL2);
break;
case 15:
write_gicreg(val, ICH_LR15_EL2);
break;
}
}
static void __vgic_v3_write_ap0rn(u32 val, int n)
{
switch (n) {
case 0:
write_gicreg(val, ICH_AP0R0_EL2);
break;
case 1:
write_gicreg(val, ICH_AP0R1_EL2);
break;
case 2:
write_gicreg(val, ICH_AP0R2_EL2);
break;
case 3:
write_gicreg(val, ICH_AP0R3_EL2);
break;
}
}
static void __vgic_v3_write_ap1rn(u32 val, int n)
{
switch (n) {
case 0:
write_gicreg(val, ICH_AP1R0_EL2);
break;
case 1:
write_gicreg(val, ICH_AP1R1_EL2);
break;
case 2:
write_gicreg(val, ICH_AP1R2_EL2);
break;
case 3:
write_gicreg(val, ICH_AP1R3_EL2);
break;
}
}
static u32 __vgic_v3_read_ap0rn(int n)
{
u32 val;
switch (n) {
case 0:
val = read_gicreg(ICH_AP0R0_EL2);
break;
case 1:
val = read_gicreg(ICH_AP0R1_EL2);
break;
case 2:
val = read_gicreg(ICH_AP0R2_EL2);
break;
case 3:
val = read_gicreg(ICH_AP0R3_EL2);
break;
default:
unreachable();
}
return val;
}
static u32 __vgic_v3_read_ap1rn(int n)
{
u32 val;
switch (n) {
case 0:
val = read_gicreg(ICH_AP1R0_EL2);
break;
case 1:
val = read_gicreg(ICH_AP1R1_EL2);
break;
case 2:
val = read_gicreg(ICH_AP1R2_EL2);
break;
case 3:
val = read_gicreg(ICH_AP1R3_EL2);
break;
default:
unreachable();
}
return val;
}
void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
{
u64 used_lrs = cpu_if->used_lrs;
/*
* Make sure stores to the GIC via the memory mapped interface
* are now visible to the system register interface when reading the
* LRs, and when reading back the VMCR on non-VHE systems.
*/
if (used_lrs || !has_vhe()) {
if (!cpu_if->vgic_sre) { dsb(sy);
isb();
}
}
if (used_lrs || cpu_if->its_vpe.its_vm) {
int i;
u32 elrsr;
elrsr = read_gicreg(ICH_ELRSR_EL2);
write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EL2_En, ICH_HCR_EL2);
for (i = 0; i < used_lrs; i++) {
if (elrsr & (1 << i))
cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
else
cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); __gic_v3_set_lr(0, i);
}
}
}
void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
{
u64 used_lrs = cpu_if->used_lrs;
int i;
if (used_lrs || cpu_if->its_vpe.its_vm) { write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) __gic_v3_set_lr(cpu_if->vgic_lr[i], i);
}
/*
* Ensure that writes to the LRs, and on non-VHE systems ensure that
* the write to the VMCR in __vgic_v3_activate_traps(), will have
* reached the (re)distributors. This ensure the guest will read the
* correct values from the memory-mapped interface.
*/
if (used_lrs || !has_vhe()) {
if (!cpu_if->vgic_sre) { isb();
dsb(sy);
}
}
}
void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
{
/*
* VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
* Group0 interrupt (as generated in GICv2 mode) to be
* delivered as a FIQ to the guest, with potentially fatal
* consequences. So we must make sure that ICC_SRE_EL1 has
* been actually programmed with the value we want before
* starting to mess with the rest of the GIC, and VMCR_EL2 in
* particular. This logic must be called before
* __vgic_v3_restore_state().
*
* However, if the vgic is disabled (ICH_HCR_EL2.EN==0), no GIC is
* provisioned at all. In order to prevent illegal accesses to the
* system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1
* so that the trap bits can take effect. Yes, we *loves* the GIC.
*/
if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) {
write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1);
isb();
} else if (!cpu_if->vgic_sre) { write_gicreg(0, ICC_SRE_EL1);
isb();
write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
if (has_vhe()) {
/*
* Ensure that the write to the VMCR will have reached
* the (re)distributors. This ensure the guest will
* read the correct values from the memory-mapped
* interface.
*/
isb();
dsb(sy);
}
}
/*
* Prevent the guest from touching the ICC_SRE_EL1 system
* register. Note that this may not have any effect, as
* ICC_SRE_EL2.Enable being RAO/WI is a valid implementation.
*/
write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
ICC_SRE_EL2);
/*
* If we need to trap system registers, we must write
* ICH_HCR_EL2 anyway, even if no interrupts are being
* injected. Note that this also applies if we don't expect
* any system register access (no vgic at all).
*/
if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
}
void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
if (!cpu_if->vgic_sre) { cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);
}
val = read_gicreg(ICC_SRE_EL2);
write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
if (!cpu_if->vgic_sre) {
/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
isb();
write_gicreg(1, ICC_SRE_EL1);
}
/*
* If we were trapping system registers, we enabled the VGIC even if
* no interrupts were being injected, and we disable it again here.
*/
if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
write_gicreg(0, ICH_HCR_EL2);
}
static void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
u32 nr_pre_bits;
val = read_gicreg(ICH_VTR_EL2);
nr_pre_bits = vtr_to_nr_pre_bits(val);
switch (nr_pre_bits) {
case 7:
cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
fallthrough;
case 6:
cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
fallthrough;
default:
cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
}
switch (nr_pre_bits) {
case 7:
cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
fallthrough;
case 6:
cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
fallthrough;
default:
cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
}
}
static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
u32 nr_pre_bits;
val = read_gicreg(ICH_VTR_EL2);
nr_pre_bits = vtr_to_nr_pre_bits(val);
switch (nr_pre_bits) {
case 7:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
fallthrough;
case 6:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
fallthrough;
default:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
}
switch (nr_pre_bits) {
case 7:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
fallthrough;
case 6:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
fallthrough;
default:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
}
}
void __vgic_v3_init_lrs(void)
{
int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
int i;
for (i = 0; i <= max_lr_idx; i++)
__gic_v3_set_lr(0, i);
}
/*
* Return the GIC CPU configuration:
* - [31:0] ICH_VTR_EL2
* - [62:32] RES0
* - [63] MMIO (GICv2) capable
*/
u64 __vgic_v3_get_gic_config(void)
{
u64 val, sre = read_gicreg(ICC_SRE_EL1);
unsigned long flags = 0;
/*
* To check whether we have a MMIO-based (GICv2 compatible)
* CPU interface, we need to disable the system register
* view.
*
* Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
* that to be able to set ICC_SRE_EL1.SRE to 0, all the
* interrupt overrides must be set. You've got to love this.
*
* As we always run VHE with HCR_xMO set, no extra xMO
* manipulation is required in that case.
*
* To safely disable SRE, we have to prevent any interrupt
* from firing (which would be deadly). This only makes sense
* on VHE, as interrupts are already masked for nVHE as part
* of the exception entry to EL2.
*/
if (has_vhe()) {
flags = local_daif_save();
} else {
sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO);
isb();
}
write_gicreg(0, ICC_SRE_EL1);
isb();
val = read_gicreg(ICC_SRE_EL1);
write_gicreg(sre, ICC_SRE_EL1);
isb();
if (has_vhe()) {
local_daif_restore(flags);
} else {
sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0);
isb();
}
val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
val |= read_gicreg(ICH_VTR_EL2);
return val;
}
static u64 __vgic_v3_read_vmcr(void)
{
return read_gicreg(ICH_VMCR_EL2);
}
static void __vgic_v3_write_vmcr(u32 vmcr)
{
write_gicreg(vmcr, ICH_VMCR_EL2);
}
void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
{ __vgic_v3_save_aprs(cpu_if); if (cpu_if->vgic_sre) cpu_if->vgic_vmcr = __vgic_v3_read_vmcr();
}
void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
{
/*
* If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
* is dependent on ICC_SRE_EL1.SRE, and we have to perform the
* VMCR_EL2 save/restore in the world switch.
*/
if (cpu_if->vgic_sre) __vgic_v3_write_vmcr(cpu_if->vgic_vmcr); __vgic_v3_restore_aprs(cpu_if);
}
static int __vgic_v3_bpr_min(void)
{
/* See Pseudocode for VPriorityGroup */
return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
}
static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
{
u64 esr = kvm_vcpu_get_esr(vcpu);
u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
return crm != 8;
}
#define GICv3_IDLE_PRIORITY 0xff
static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr,
u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
u8 priority = GICv3_IDLE_PRIORITY;
int i, lr = -1;
for (i = 0; i < used_lrs; i++) {
u64 val = __gic_v3_get_lr(i);
u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;
/* Not pending in the state? */
if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT)
continue;
/* Group-0 interrupt, but Group-0 disabled? */
if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG0_MASK))
continue;
/* Group-1 interrupt, but Group-1 disabled? */
if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG1_MASK))
continue;
/* Not the highest priority? */
if (lr_prio >= priority)
continue;
/* This is a candidate */
priority = lr_prio;
*lr_val = val;
lr = i;
}
if (lr == -1)
*lr_val = ICC_IAR1_EL1_SPURIOUS;
return lr;
}
static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
int i;
for (i = 0; i < used_lrs; i++) {
u64 val = __gic_v3_get_lr(i);
if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid &&
(val & ICH_LR_ACTIVE_BIT)) {
*lr_val = val;
return i;
}
}
*lr_val = ICC_IAR1_EL1_SPURIOUS;
return -1;
}
static int __vgic_v3_get_highest_active_priority(void)
{
u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
u32 hap = 0;
int i;
for (i = 0; i < nr_apr_regs; i++) {
u32 val;
/*
* The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers
* contain the active priority levels for this VCPU
* for the maximum number of supported priority
* levels, and we return the full priority level only
* if the BPR is programmed to its minimum, otherwise
* we return a combination of the priority level and
* subpriority, as determined by the setting of the
* BPR, but without the full subpriority.
*/
val = __vgic_v3_read_ap0rn(i);
val |= __vgic_v3_read_ap1rn(i);
if (!val) {
hap += 32;
continue;
}
return (hap + __ffs(val)) << __vgic_v3_bpr_min();
}
return GICv3_IDLE_PRIORITY;
}
static unsigned int __vgic_v3_get_bpr0(u32 vmcr)
{
return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
}
static unsigned int __vgic_v3_get_bpr1(u32 vmcr)
{
unsigned int bpr;
if (vmcr & ICH_VMCR_CBPR_MASK) {
bpr = __vgic_v3_get_bpr0(vmcr);
if (bpr < 7)
bpr++;
} else {
bpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
}
return bpr;
}
/*
* Convert a priority to a preemption level, taking the relevant BPR
* into account by zeroing the sub-priority bits.
*/
static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
{
unsigned int bpr;
if (!grp)
bpr = __vgic_v3_get_bpr0(vmcr) + 1;
else
bpr = __vgic_v3_get_bpr1(vmcr);
return pri & (GENMASK(7, 0) << bpr);
}
/*
* The priority value is independent of any of the BPR values, so we
* normalize it using the minimal BPR value. This guarantees that no
* matter what the guest does with its BPR, we can always set/get the
* same value of a priority.
*/
static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
{
u8 pre, ap;
u32 val;
int apr;
pre = __vgic_v3_pri_to_pre(pri, vmcr, grp);
ap = pre >> __vgic_v3_bpr_min();
apr = ap / 32;
if (!grp) {
val = __vgic_v3_read_ap0rn(apr);
__vgic_v3_write_ap0rn(val | BIT(ap % 32), apr);
} else {
val = __vgic_v3_read_ap1rn(apr);
__vgic_v3_write_ap1rn(val | BIT(ap % 32), apr);
}
}
static int __vgic_v3_clear_highest_active_priority(void)
{
u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
u32 hap = 0;
int i;
for (i = 0; i < nr_apr_regs; i++) {
u32 ap0, ap1;
int c0, c1;
ap0 = __vgic_v3_read_ap0rn(i);
ap1 = __vgic_v3_read_ap1rn(i);
if (!ap0 && !ap1) {
hap += 32;
continue;
}
c0 = ap0 ? __ffs(ap0) : 32;
c1 = ap1 ? __ffs(ap1) : 32;
/* Always clear the LSB, which is the highest priority */
if (c0 < c1) {
ap0 &= ~BIT(c0);
__vgic_v3_write_ap0rn(ap0, i);
hap += c0;
} else {
ap1 &= ~BIT(c1);
__vgic_v3_write_ap1rn(ap1, i);
hap += c1;
}
/* Rescale to 8 bits of priority */
return hap << __vgic_v3_bpr_min();
}
return GICv3_IDLE_PRIORITY;
}
static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 lr_val;
u8 lr_prio, pmr;
int lr, grp;
grp = __vgic_v3_get_group(vcpu);
lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val);
if (lr < 0)
goto spurious;
if (grp != !!(lr_val & ICH_LR_GROUP))
goto spurious;
pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;
if (pmr <= lr_prio)
goto spurious;
if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp))
goto spurious;
lr_val &= ~ICH_LR_STATE;
lr_val |= ICH_LR_ACTIVE_BIT;
__gic_v3_set_lr(lr_val, lr);
__vgic_v3_set_active_priority(lr_prio, vmcr, grp);
vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
return;
spurious:
vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS);
}
static void __vgic_v3_clear_active_lr(int lr, u64 lr_val)
{
lr_val &= ~ICH_LR_ACTIVE_BIT;
if (lr_val & ICH_LR_HW) {
u32 pid;
pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT;
gic_write_dir(pid);
}
__gic_v3_set_lr(lr_val, lr);
}
static void __vgic_v3_bump_eoicount(void)
{
u32 hcr;
hcr = read_gicreg(ICH_HCR_EL2);
hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT;
write_gicreg(hcr, ICH_HCR_EL2);
}
static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vid = vcpu_get_reg(vcpu, rt);
u64 lr_val;
int lr;
/* EOImode == 0, nothing to be done here */
if (!(vmcr & ICH_VMCR_EOIM_MASK))
return;
/* No deactivate to be performed on an LPI */
if (vid >= VGIC_MIN_LPI)
return;
lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
if (lr == -1) {
__vgic_v3_bump_eoicount();
return;
}
__vgic_v3_clear_active_lr(lr, lr_val);
}
static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vid = vcpu_get_reg(vcpu, rt);
u64 lr_val;
u8 lr_prio, act_prio;
int lr, grp;
grp = __vgic_v3_get_group(vcpu);
/* Drop priority in any case */
act_prio = __vgic_v3_clear_highest_active_priority();
lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
if (lr == -1) {
/* Do not bump EOIcount for LPIs that aren't in the LRs */
if (!(vid >= VGIC_MIN_LPI))
__vgic_v3_bump_eoicount();
return;
}
/* EOImode == 1 and not an LPI, nothing to be done here */
if ((vmcr & ICH_VMCR_EOIM_MASK) && !(vid >= VGIC_MIN_LPI))
return;
lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;
/* If priorities or group do not match, the guest has fscked-up. */
if (grp != !!(lr_val & ICH_LR_GROUP) ||
__vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio)
return;
/* Let's now perform the deactivation */
__vgic_v3_clear_active_lr(lr, lr_val);
}
static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK));
}
static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK));
}
static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
if (val & 1)
vmcr |= ICH_VMCR_ENG0_MASK;
else
vmcr &= ~ICH_VMCR_ENG0_MASK;
__vgic_v3_write_vmcr(vmcr);
}
static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
if (val & 1)
vmcr |= ICH_VMCR_ENG1_MASK;
else
vmcr &= ~ICH_VMCR_ENG1_MASK;
__vgic_v3_write_vmcr(vmcr);
}
static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
}
static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
}
static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
u8 bpr_min = __vgic_v3_bpr_min() - 1;
/* Enforce BPR limiting */
if (val < bpr_min)
val = bpr_min;
val <<= ICH_VMCR_BPR0_SHIFT;
val &= ICH_VMCR_BPR0_MASK;
vmcr &= ~ICH_VMCR_BPR0_MASK;
vmcr |= val;
__vgic_v3_write_vmcr(vmcr);
}
static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
u8 bpr_min = __vgic_v3_bpr_min();
if (vmcr & ICH_VMCR_CBPR_MASK)
return;
/* Enforce BPR limiting */
if (val < bpr_min)
val = bpr_min;
val <<= ICH_VMCR_BPR1_SHIFT;
val &= ICH_VMCR_BPR1_MASK;
vmcr &= ~ICH_VMCR_BPR1_MASK;
vmcr |= val;
__vgic_v3_write_vmcr(vmcr);
}
static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
u32 val;
if (!__vgic_v3_get_group(vcpu))
val = __vgic_v3_read_ap0rn(n);
else
val = __vgic_v3_read_ap1rn(n);
vcpu_set_reg(vcpu, rt, val);
}
static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
u32 val = vcpu_get_reg(vcpu, rt);
if (!__vgic_v3_get_group(vcpu))
__vgic_v3_write_ap0rn(val, n);
else
__vgic_v3_write_ap1rn(val, n);
}
static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 0);
}
static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 1);
}
static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 2);
}
static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 3);
}
static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 0);
}
static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 1);
}
static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 2);
}
static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 3);
}
static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 lr_val;
int lr, lr_grp, grp;
grp = __vgic_v3_get_group(vcpu);
lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val);
if (lr == -1)
goto spurious;
lr_grp = !!(lr_val & ICH_LR_GROUP);
if (lr_grp != grp)
lr_val = ICC_IAR1_EL1_SPURIOUS;
spurious:
vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
}
static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vmcr &= ICH_VMCR_PMR_MASK;
vmcr >>= ICH_VMCR_PMR_SHIFT;
vcpu_set_reg(vcpu, rt, vmcr);
}
static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = vcpu_get_reg(vcpu, rt);
val <<= ICH_VMCR_PMR_SHIFT;
val &= ICH_VMCR_PMR_MASK;
vmcr &= ~ICH_VMCR_PMR_MASK;
vmcr |= val;
write_gicreg(vmcr, ICH_VMCR_EL2);
}
static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = __vgic_v3_get_highest_active_priority();
vcpu_set_reg(vcpu, rt, val);
}
static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vtr, val;
vtr = read_gicreg(ICH_VTR_EL2);
/* PRIbits */
val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT;
/* IDbits */
val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT;
/* A3V */
val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT;
/* EOImode */
val |= ((vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT) << ICC_CTLR_EL1_EOImode_SHIFT;
/* CBPR */
val |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
vcpu_set_reg(vcpu, rt, val);
}
static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = vcpu_get_reg(vcpu, rt);
if (val & ICC_CTLR_EL1_CBPR_MASK)
vmcr |= ICH_VMCR_CBPR_MASK;
else
vmcr &= ~ICH_VMCR_CBPR_MASK;
if (val & ICC_CTLR_EL1_EOImode_MASK)
vmcr |= ICH_VMCR_EOIM_MASK;
else
vmcr &= ~ICH_VMCR_EOIM_MASK;
write_gicreg(vmcr, ICH_VMCR_EL2);
}
static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
u32 sysreg, bool is_read)
{
u64 ich_hcr;
if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
return false;
ich_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
switch (sysreg) {
case SYS_ICC_IGRPEN0_EL1:
if (is_read &&
(__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
return true;
if (!is_read &&
(__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
return true;
fallthrough;
case SYS_ICC_AP0Rn_EL1(0):
case SYS_ICC_AP0Rn_EL1(1):
case SYS_ICC_AP0Rn_EL1(2):
case SYS_ICC_AP0Rn_EL1(3):
case SYS_ICC_BPR0_EL1:
case SYS_ICC_EOIR0_EL1:
case SYS_ICC_HPPIR0_EL1:
case SYS_ICC_IAR0_EL1:
return ich_hcr & ICH_HCR_EL2_TALL0;
case SYS_ICC_IGRPEN1_EL1:
if (is_read &&
(__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
return true;
if (!is_read &&
(__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
return true;
fallthrough;
case SYS_ICC_AP1Rn_EL1(0):
case SYS_ICC_AP1Rn_EL1(1):
case SYS_ICC_AP1Rn_EL1(2):
case SYS_ICC_AP1Rn_EL1(3):
case SYS_ICC_BPR1_EL1:
case SYS_ICC_EOIR1_EL1:
case SYS_ICC_HPPIR1_EL1:
case SYS_ICC_IAR1_EL1:
return ich_hcr & ICH_HCR_EL2_TALL1;
case SYS_ICC_DIR_EL1:
if (ich_hcr & ICH_HCR_EL2_TDIR)
return true;
fallthrough;
case SYS_ICC_RPR_EL1:
case SYS_ICC_CTLR_EL1:
case SYS_ICC_PMR_EL1:
return ich_hcr & ICH_HCR_EL2_TC;
default:
return false;
}
}
int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
{
int rt;
u64 esr;
u32 vmcr;
void (*fn)(struct kvm_vcpu *, u32, int);
bool is_read;
u32 sysreg;
if (kern_hyp_va(vcpu->kvm)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3)
return 0;
esr = kvm_vcpu_get_esr(vcpu);
if (vcpu_mode_is_32bit(vcpu)) {
if (!kvm_condition_valid(vcpu)) {
__kvm_skip_instr(vcpu);
return 1;
}
sysreg = esr_cp15_to_sysreg(esr);
} else {
sysreg = esr_sys64_to_sysreg(esr);
}
is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ;
if (__vgic_v3_check_trap_forwarding(vcpu, sysreg, is_read))
return 0;
switch (sysreg) {
case SYS_ICC_IAR0_EL1:
case SYS_ICC_IAR1_EL1:
if (unlikely(!is_read))
return 0;
fn = __vgic_v3_read_iar;
break;
case SYS_ICC_EOIR0_EL1:
case SYS_ICC_EOIR1_EL1:
if (unlikely(is_read))
return 0;
fn = __vgic_v3_write_eoir;
break;
case SYS_ICC_IGRPEN1_EL1:
if (is_read)
fn = __vgic_v3_read_igrpen1;
else
fn = __vgic_v3_write_igrpen1;
break;
case SYS_ICC_BPR1_EL1:
if (is_read)
fn = __vgic_v3_read_bpr1;
else
fn = __vgic_v3_write_bpr1;
break;
case SYS_ICC_AP0Rn_EL1(0):
case SYS_ICC_AP1Rn_EL1(0):
if (is_read)
fn = __vgic_v3_read_apxr0;
else
fn = __vgic_v3_write_apxr0;
break;
case SYS_ICC_AP0Rn_EL1(1):
case SYS_ICC_AP1Rn_EL1(1):
if (is_read)
fn = __vgic_v3_read_apxr1;
else
fn = __vgic_v3_write_apxr1;
break;
case SYS_ICC_AP0Rn_EL1(2):
case SYS_ICC_AP1Rn_EL1(2):
if (is_read)
fn = __vgic_v3_read_apxr2;
else
fn = __vgic_v3_write_apxr2;
break;
case SYS_ICC_AP0Rn_EL1(3):
case SYS_ICC_AP1Rn_EL1(3):
if (is_read)
fn = __vgic_v3_read_apxr3;
else
fn = __vgic_v3_write_apxr3;
break;
case SYS_ICC_HPPIR0_EL1:
case SYS_ICC_HPPIR1_EL1:
if (unlikely(!is_read))
return 0;
fn = __vgic_v3_read_hppir;
break;
case SYS_ICC_IGRPEN0_EL1:
if (is_read)
fn = __vgic_v3_read_igrpen0;
else
fn = __vgic_v3_write_igrpen0;
break;
case SYS_ICC_BPR0_EL1:
if (is_read)
fn = __vgic_v3_read_bpr0;
else
fn = __vgic_v3_write_bpr0;
break;
case SYS_ICC_DIR_EL1:
if (unlikely(is_read))
return 0;
fn = __vgic_v3_write_dir;
break;
case SYS_ICC_RPR_EL1:
if (unlikely(!is_read))
return 0;
fn = __vgic_v3_read_rpr;
break;
case SYS_ICC_CTLR_EL1:
if (is_read)
fn = __vgic_v3_read_ctlr;
else
fn = __vgic_v3_write_ctlr;
break;
case SYS_ICC_PMR_EL1:
if (is_read)
fn = __vgic_v3_read_pmr;
else
fn = __vgic_v3_write_pmr;
break;
default:
return 0;
}
vmcr = __vgic_v3_read_vmcr();
rt = kvm_vcpu_sys_get_rt(vcpu);
fn(vcpu, vmcr, rt);
__kvm_skip_instr(vcpu);
return 1;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015, 2016 ARM Ltd.
*/
#include <linux/uaccess.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"
/*
* Initialization rules: there are multiple stages to the vgic
* initialization, both for the distributor and the CPU interfaces. The basic
* idea is that even though the VGIC is not functional or not requested from
* user space, the critical path of the run loop can still call VGIC functions
* that just won't do anything, without them having to check additional
* initialization flags to ensure they don't look at uninitialized data
* structures.
*
* Distributor:
*
* - kvm_vgic_early_init(): initialization of static data that doesn't
* depend on any sizing information or emulation type. No allocation
* is allowed there.
*
* - vgic_init(): allocation and initialization of the generic data
* structures that depend on sizing information (number of CPUs,
* number of interrupts). Also initializes the vcpu specific data
* structures. Can be executed lazily for GICv2.
*
* CPU Interface:
*
* - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend
* on any sizing information. Private interrupts are allocated if not
* already allocated at vgic-creation time.
*/
/* EARLY INIT */
/**
* kvm_vgic_early_init() - Initialize static VGIC VCPU data structures
* @kvm: The VM whose VGIC districutor should be initialized
*
* Only do initialization of static structures that don't require any
* allocation or sizing information from userspace. vgic_init() called
* kvm_vgic_dist_init() which takes care of the rest.
*/
void kvm_vgic_early_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
}
/* CREATION */
static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);
/**
* kvm_vgic_create: triggered by the instantiation of the VGIC device by
* user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
* or through the generic KVM_CREATE_DEVICE API ioctl.
* irqchip_in_kernel() tells you if this function succeeded or not.
* @kvm: kvm struct pointer
* @type: KVM_DEV_TYPE_ARM_VGIC_V[23]
*/
int kvm_vgic_create(struct kvm *kvm, u32 type)
{
struct kvm_vcpu *vcpu;
unsigned long i;
int ret;
/*
* This function is also called by the KVM_CREATE_IRQCHIP handler,
* which had no chance yet to check the availability of the GICv2
* emulation. So check this here again. KVM_CREATE_DEVICE does
* the proper checks already.
*/
if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
!kvm_vgic_global_state.can_emulate_gicv2)
return -ENODEV;
/* Must be held to avoid race with vCPU creation */
lockdep_assert_held(&kvm->lock);
ret = -EBUSY;
if (!lock_all_vcpus(kvm))
return ret;
mutex_lock(&kvm->arch.config_lock);
if (irqchip_in_kernel(kvm)) {
ret = -EEXIST;
goto out_unlock;
}
kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_has_run_once(vcpu))
goto out_unlock;
}
ret = 0;
if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
kvm->max_vcpus = VGIC_V2_MAX_CPUS;
else
kvm->max_vcpus = VGIC_V3_MAX_CPUS;
if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) {
ret = -E2BIG;
goto out_unlock;
}
kvm_for_each_vcpu(i, vcpu, kvm) {
ret = vgic_allocate_private_irqs_locked(vcpu, type);
if (ret)
break;
}
if (ret) {
kvm_for_each_vcpu(i, vcpu, kvm) {
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
}
goto out_unlock;
}
kvm->arch.vgic.in_kernel = true;
kvm->arch.vgic.vgic_model = type;
kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
else
INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
out_unlock:
mutex_unlock(&kvm->arch.config_lock);
unlock_all_vcpus(kvm);
return ret;
}
/* INIT/DESTROY */
/**
* kvm_vgic_dist_init: initialize the dist data structures
* @kvm: kvm struct pointer
* @nr_spis: number of spis, frozen by caller
*/
static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
int i;
dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT);
if (!dist->spis)
return -ENOMEM;
/*
* In the following code we do not take the irq struct lock since
* no other action on irq structs can happen while the VGIC is
* not initialized yet:
* If someone wants to inject an interrupt or does a MMIO access, we
* require prior initialization in case of a virtual GICv3 or trigger
* initialization when using a virtual GICv2.
*/
for (i = 0; i < nr_spis; i++) {
struct vgic_irq *irq = &dist->spis[i];
irq->intid = i + VGIC_NR_PRIVATE_IRQS;
INIT_LIST_HEAD(&irq->ap_list);
raw_spin_lock_init(&irq->irq_lock);
irq->vcpu = NULL;
irq->target_vcpu = vcpu0;
kref_init(&irq->refcount);
switch (dist->vgic_model) {
case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->targets = 0;
irq->group = 0;
break;
case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->mpidr = 0;
irq->group = 1;
break;
default:
kfree(dist->spis);
dist->spis = NULL;
return -EINVAL;
}
}
return 0;
}
/* Default GICv3 Maintenance Interrupt INTID, as per SBSA */
#define DEFAULT_MI_INTID 25
int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
{
int ret;
guard(mutex)(&vcpu->kvm->arch.config_lock);
/*
* Matching the tradition established with the timers, provide
* a default PPI for the maintenance interrupt. It makes
* things easier to reason about.
*/
if (vcpu->kvm->arch.vgic.mi_intid == 0)
vcpu->kvm->arch.vgic.mi_intid = DEFAULT_MI_INTID;
ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.mi_intid, vcpu);
return ret;
}
static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int i;
lockdep_assert_held(&vcpu->kvm->arch.config_lock); if (vgic_cpu->private_irqs)
return 0;
vgic_cpu->private_irqs = kcalloc(VGIC_NR_PRIVATE_IRQS,
sizeof(struct vgic_irq),
GFP_KERNEL_ACCOUNT);
if (!vgic_cpu->private_irqs)
return -ENOMEM;
/*
* Enable and configure all SGIs to be edge-triggered and
* configure all PPIs as level-triggered.
*/
for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
INIT_LIST_HEAD(&irq->ap_list);
raw_spin_lock_init(&irq->irq_lock);
irq->intid = i;
irq->vcpu = NULL;
irq->target_vcpu = vcpu;
kref_init(&irq->refcount);
if (vgic_irq_is_sgi(i)) {
/* SGIs */
irq->enabled = 1;
irq->config = VGIC_CONFIG_EDGE;
} else {
/* PPIs */
irq->config = VGIC_CONFIG_LEVEL;
}
switch (type) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->group = 1;
irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
break;
case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->group = 0;
irq->targets = BIT(vcpu->vcpu_id);
break;
}
}
return 0;
}
static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type)
{
int ret;
mutex_lock(&vcpu->kvm->arch.config_lock);
ret = vgic_allocate_private_irqs_locked(vcpu, type);
mutex_unlock(&vcpu->kvm->arch.config_lock);
return ret;
}
/**
* kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
* structures and register VCPU-specific KVM iodevs
*
* @vcpu: pointer to the VCPU being created and initialized
*
* Only do initialization, but do not actually enable the
* VGIC CPU interface
*/
int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int ret = 0;
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
raw_spin_lock_init(&vgic_cpu->ap_list_lock);
atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);
if (!irqchip_in_kernel(vcpu->kvm))
return 0;
ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model);
if (ret)
return ret;
/*
* If we are creating a VCPU with a GICv3 we must also register the
* KVM io device for the redistributor that belongs to this VCPU.
*/
if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { mutex_lock(&vcpu->kvm->slots_lock);
ret = vgic_register_redist_iodev(vcpu);
mutex_unlock(&vcpu->kvm->slots_lock);
}
return ret;
}
static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_enable(vcpu);
else
vgic_v3_enable(vcpu);
}
/*
* vgic_init: allocates and initializes dist and vcpu data structures
* depending on two dimensioning parameters:
* - the number of spis
* - the number of vcpus
* The function is generally called when nr_spis has been explicitly set
* by the guest through the KVM DEVICE API. If not nr_spis is set to 256.
* vgic_initialized() returns true when this function has succeeded.
*/
int vgic_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int ret = 0;
unsigned long idx;
lockdep_assert_held(&kvm->arch.config_lock); if (vgic_initialized(kvm))
return 0;
/* Are we also in the middle of creating a VCPU? */
if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus))
return -EBUSY;
/* freeze the number of spis */
if (!dist->nr_spis) dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; ret = kvm_vgic_dist_init(kvm, dist->nr_spis);
if (ret)
goto out;
/*
* If we have GICv4.1 enabled, unconditionally request enable the
* v4 support so that we get HW-accelerated vSGIs. Otherwise, only
* enable it if we present a virtual ITS to the guest.
*/
if (vgic_supports_direct_msis(kvm)) {
ret = vgic_v4_init(kvm);
if (ret)
goto out;
}
kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu);
ret = kvm_vgic_setup_default_irq_routing(kvm);
if (ret)
goto out;
vgic_debug_init(kvm);
/*
* If userspace didn't set the GIC implementation revision,
* default to the latest and greatest. You know want it.
*/
if (!dist->implementation_rev) dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST;
dist->initialized = true;
out:
return ret;
}
static void kvm_vgic_dist_destroy(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_redist_region *rdreg, *next;
dist->ready = false;
dist->initialized = false;
kfree(dist->spis);
dist->spis = NULL;
dist->nr_spis = 0;
dist->vgic_dist_base = VGIC_ADDR_UNDEF;
if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list)
vgic_v3_free_redist_region(kvm, rdreg);
INIT_LIST_HEAD(&dist->rd_regions);
} else {
dist->vgic_cpu_base = VGIC_ADDR_UNDEF;
}
if (vgic_supports_direct_msis(kvm)) vgic_v4_teardown(kvm);
xa_destroy(&dist->lpi_xa);
}
static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
/*
* Retire all pending LPIs on this vcpu anyway as we're
* going to destroy it.
*/
vgic_flush_pending_lpis(vcpu);
INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
/*
* If this vCPU is being destroyed because of a failed creation
* then unregister the redistributor to avoid leaving behind a
* dangling pointer to the vCPU struct.
*
* vCPUs that have been successfully created (i.e. added to
* kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
* this function gets called while holding kvm->arch.config_lock
* in the VM teardown path and would otherwise introduce a lock
* inversion w.r.t. kvm->srcu.
*
* vCPUs that failed creation are torn down outside of the
* kvm->arch.config_lock and do not get unregistered in
* kvm_vgic_destroy(), meaning it is both safe and necessary to
* do so here.
*/
if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu) vgic_unregister_redist_iodev(vcpu);
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
}
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
mutex_lock(&kvm->slots_lock);
__kvm_vgic_vcpu_destroy(vcpu);
mutex_unlock(&kvm->slots_lock);
}
void kvm_vgic_destroy(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
unsigned long i;
mutex_lock(&kvm->slots_lock);
mutex_lock(&kvm->arch.config_lock);
vgic_debug_destroy(kvm);
kvm_for_each_vcpu(i, vcpu, kvm)
__kvm_vgic_vcpu_destroy(vcpu);
kvm_vgic_dist_destroy(kvm);
mutex_unlock(&kvm->arch.config_lock);
if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) kvm_for_each_vcpu(i, vcpu, kvm)
vgic_unregister_redist_iodev(vcpu);
mutex_unlock(&kvm->slots_lock);
}
/**
* vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
* is a GICv2. A GICv3 must be explicitly initialized by userspace using the
* KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group.
* @kvm: kvm struct pointer
*/
int vgic_lazy_init(struct kvm *kvm)
{
int ret = 0;
if (unlikely(!vgic_initialized(kvm))) {
/*
* We only provide the automatic initialization of the VGIC
* for the legacy case of a GICv2. Any other type must
* be explicitly initialized once setup with the respective
* KVM device call.
*/
if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
return -EBUSY;
mutex_lock(&kvm->arch.config_lock);
ret = vgic_init(kvm);
mutex_unlock(&kvm->arch.config_lock);
}
return ret;
}
/* RESOURCE MAPPING */
/**
* kvm_vgic_map_resources - map the MMIO regions
* @kvm: kvm struct pointer
*
* Map the MMIO regions depending on the VGIC model exposed to the guest
* called on the first VCPU run.
* Also map the virtual CPU interface into the VM.
* v2 calls vgic_init() if not already done.
* v3 and derivatives return an error if the VGIC is not initialized.
* vgic_ready() returns true if this function has succeeded.
*/
int kvm_vgic_map_resources(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
enum vgic_type type;
gpa_t dist_base;
int ret = 0;
if (likely(vgic_ready(kvm)))
return 0;
mutex_lock(&kvm->slots_lock);
mutex_lock(&kvm->arch.config_lock);
if (vgic_ready(kvm))
goto out;
if (!irqchip_in_kernel(kvm))
goto out;
if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
ret = vgic_v2_map_resources(kvm);
type = VGIC_V2;
} else {
ret = vgic_v3_map_resources(kvm);
type = VGIC_V3;
}
if (ret)
goto out;
dist_base = dist->vgic_dist_base;
mutex_unlock(&kvm->arch.config_lock);
ret = vgic_register_dist_iodev(kvm, dist_base, type);
if (ret) {
kvm_err("Unable to register VGIC dist MMIO regions\n");
goto out_slots;
}
/*
* kvm_io_bus_register_dev() guarantees all readers see the new MMIO
* registration before returning through synchronize_srcu(), which also
* implies a full memory barrier. As such, marking the distributor as
* 'ready' here is guaranteed to be ordered after all vCPUs having seen
* a completely configured distributor.
*/
dist->ready = true;
goto out_slots;
out:
mutex_unlock(&kvm->arch.config_lock);
out_slots:
if (ret)
kvm_vm_dead(kvm);
mutex_unlock(&kvm->slots_lock);
return ret;
}
/* GENERIC PROBE */
void kvm_vgic_cpu_up(void)
{
enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
}
void kvm_vgic_cpu_down(void)
{
disable_percpu_irq(kvm_vgic_global_state.maint_irq);
}
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data;
/*
* We cannot rely on the vgic maintenance interrupt to be
* delivered synchronously. This means we can only use it to
* exit the VM, and we perform the handling of EOIed
* interrupts on the exit path (see vgic_fold_lr_state).
*
* Of course, NV throws a wrench in this plan, and needs
* something special.
*/
if (vcpu && vgic_state_is_nested(vcpu))
vgic_v3_handle_nested_maint_irq(vcpu);
return IRQ_HANDLED;
}
static struct gic_kvm_info *gic_kvm_info;
void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
{
BUG_ON(gic_kvm_info != NULL);
gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL);
if (gic_kvm_info)
*gic_kvm_info = *info;
}
/**
* kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
*
* For a specific CPU, initialize the GIC VE hardware.
*/
void kvm_vgic_init_cpu_hardware(void)
{
BUG_ON(preemptible());
/*
* We want to make sure the list registers start out clear so that we
* only have the program the used registers.
*/
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_init_lrs();
else
kvm_call_hyp(__vgic_v3_init_lrs);
}
/**
* kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
* according to the host GIC model. Accordingly calls either
* vgic_v2/v3_probe which registers the KVM_DEVICE that can be
* instantiated by a guest later on .
*/
int kvm_vgic_hyp_init(void)
{
bool has_mask;
int ret;
if (!gic_kvm_info)
return -ENODEV;
has_mask = !gic_kvm_info->no_maint_irq_mask;
if (has_mask && !gic_kvm_info->maint_irq) {
kvm_err("No vgic maintenance irq\n");
return -ENXIO;
}
/*
* If we get one of these oddball non-GICs, taint the kernel,
* as we have no idea of how they *really* behave.
*/
if (gic_kvm_info->no_hw_deactivation) {
kvm_info("Non-architectural vgic, tainting kernel\n");
add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
kvm_vgic_global_state.no_hw_deactivation = true;
}
switch (gic_kvm_info->type) {
case GIC_V2:
ret = vgic_v2_probe(gic_kvm_info);
break;
case GIC_V3:
ret = vgic_v3_probe(gic_kvm_info);
if (!ret) {
static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif);
kvm_info("GIC system register CPU interface enabled\n");
}
break;
default:
ret = -ENODEV;
}
kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;
kfree(gic_kvm_info);
gic_kvm_info = NULL;
if (ret)
return ret;
if (!has_mask && !kvm_vgic_global_state.maint_irq)
return 0;
ret = request_percpu_irq(kvm_vgic_global_state.maint_irq,
vgic_maintenance_handler,
"vgic", kvm_get_running_vcpus());
if (ret) {
kvm_err("Cannot register interrupt %d\n",
kvm_vgic_global_state.maint_irq);
return ret;
}
kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
return 0;
}
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM printk
#if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_PRINTK_H
#include <linux/tracepoint.h>
TRACE_EVENT(console,
TP_PROTO(const char *text, size_t len),
TP_ARGS(text, len),
TP_STRUCT__entry(
__dynamic_array(char, msg, len + 1)
),
TP_fast_assign(
/*
* Each trace entry is printed in a new line.
* If the msg finishes with '\n', cut it off
* to avoid blank lines in the trace.
*/
if ((len > 0) && (text[len-1] == '\n'))
len -= 1;
memcpy(__get_str(msg), text, len);
__get_str(msg)[len] = 0;
),
TP_printk("%s", __get_str(msg))
);
#endif /* _TRACE_PRINTK_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_UDP_TUNNEL_H
#define __NET_UDP_TUNNEL_H
#include <net/ip_tunnels.h>
#include <net/udp.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ipv6_stubs.h>
#endif
struct udp_port_cfg {
u8 family;
/* Used only for kernel-created sockets */
union {
struct in_addr local_ip;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr local_ip6;
#endif
};
union {
struct in_addr peer_ip;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr peer_ip6;
#endif
};
__be16 local_udp_port;
__be16 peer_udp_port;
int bind_ifindex;
unsigned int use_udp_checksums:1,
use_udp6_tx_checksums:1,
use_udp6_rx_checksums:1,
ipv6_v6only:1;
};
int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
struct socket **sockp);
#if IS_ENABLED(CONFIG_IPV6)
int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
struct socket **sockp);
#else
static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
struct socket **sockp)
{
return 0;
}
#endif
static inline int udp_sock_create(struct net *net,
struct udp_port_cfg *cfg,
struct socket **sockp)
{
if (cfg->family == AF_INET)
return udp_sock_create4(net, cfg, sockp);
if (cfg->family == AF_INET6)
return udp_sock_create6(net, cfg, sockp);
return -EPFNOSUPPORT;
}
typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
struct sk_buff *skb);
typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload);
typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
struct list_head *head,
struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
int nhoff);
struct udp_tunnel_sock_cfg {
void *sk_user_data; /* user data used by encap_rcv call back */
/* Used for setting up udp_sock fields, see udp.h for details */
__u8 encap_type;
udp_tunnel_encap_rcv_t encap_rcv;
udp_tunnel_encap_err_lookup_t encap_err_lookup;
udp_tunnel_encap_err_rcv_t encap_err_rcv;
udp_tunnel_encap_destroy_t encap_destroy;
udp_tunnel_gro_receive_t gro_receive;
udp_tunnel_gro_complete_t gro_complete;
};
/* Setup the given (UDP) sock to receive UDP encapsulated packets */
void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
struct udp_tunnel_sock_cfg *sock_cfg);
/* -- List of parsable UDP tunnel types --
*
* Adding to this list will result in serious debate. The main issue is
* that this list is essentially a list of workarounds for either poorly
* designed tunnels, or poorly designed device offloads.
*
* The parsing supported via these types should really be used for Rx
* traffic only as the network stack will have already inserted offsets for
* the location of the headers in the skb. In addition any ports that are
* pushed should be kept within the namespace without leaking to other
* devices such as VFs or other ports on the same device.
*
* It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the
* need to use this for Rx checksum offload. It should not be necessary to
* call this function to perform Tx offloads on outgoing traffic.
*/
enum udp_parsable_tunnel_type {
UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */
UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */
UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */
};
struct udp_tunnel_info {
unsigned short type;
sa_family_t sa_family;
__be16 port;
u8 hw_priv;
};
/* Notify network devices of offloadable types */
void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
unsigned short type);
void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
unsigned short type);
void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);
static inline void udp_tunnel_get_rx_info(struct net_device *dev)
{
ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
return;
call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
}
static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
{
ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
return;
call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev);
}
/* Transmit the skb using UDP encapsulation. */
void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl,
__be16 df, __be16 src_port, __be16 dst_port,
bool xnet, bool nocheck);
int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb,
struct net_device *dev,
const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u8 prio, __u8 ttl, __be32 label,
__be16 src_port, __be16 dst_port, bool nocheck);
void udp_tunnel_sock_release(struct socket *sock);
struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
struct net_device *dev,
struct net *net, int oif,
__be32 *saddr,
const struct ip_tunnel_key *key,
__be16 sport, __be16 dport, u8 tos,
struct dst_cache *dst_cache);
struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
struct net_device *dev,
struct net *net,
struct socket *sock, int oif,
struct in6_addr *saddr,
const struct ip_tunnel_key *key,
__be16 sport, __be16 dport, u8 dsfield,
struct dst_cache *dst_cache);
struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
const unsigned long *flags,
__be64 tunnel_id, int md_size);
#ifdef CONFIG_INET
static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
{
int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
return iptunnel_handle_offloads(skb, type);
}
#endif
static inline void udp_tunnel_encap_enable(struct sock *sk)
{
if (udp_test_and_set_bit(ENCAP_ENABLED, sk))
return;
#if IS_ENABLED(CONFIG_IPV6)
if (READ_ONCE(sk->sk_family) == PF_INET6)
ipv6_stub->udpv6_encap_enable();
#endif
udp_encap_enable();
}
#define UDP_TUNNEL_NIC_MAX_TABLES 4
enum udp_tunnel_nic_info_flags {
/* Device callbacks may sleep */
UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0),
/* Device only supports offloads when it's open, all ports
* will be removed before close and re-added after open.
*/
UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1),
/* Device supports only IPv4 tunnels */
UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2),
/* Device has hard-coded the IANA VXLAN port (4789) as VXLAN.
* This port must not be counted towards n_entries of any table.
* Driver will not receive any callback associated with port 4789.
*/
UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3),
};
struct udp_tunnel_nic;
#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2)
struct udp_tunnel_nic_shared {
struct udp_tunnel_nic *udp_tunnel_nic_info;
struct list_head devices;
};
struct udp_tunnel_nic_shared_node {
struct net_device *dev;
struct list_head list;
};
/**
* struct udp_tunnel_nic_info - driver UDP tunnel offload information
* @set_port: callback for adding a new port
* @unset_port: callback for removing a port
* @sync_table: callback for syncing the entire port table at once
* @shared: reference to device global state (optional)
* @flags: device flags from enum udp_tunnel_nic_info_flags
* @tables: UDP port tables this device has
* @tables.n_entries: number of entries in this table
* @tables.tunnel_types: types of tunnels this table accepts
*
* Drivers are expected to provide either @set_port and @unset_port callbacks
* or the @sync_table callback. Callbacks are invoked with rtnl lock held.
*
* Devices which (misguidedly) share the UDP tunnel port table across multiple
* netdevs should allocate an instance of struct udp_tunnel_nic_shared and
* point @shared at it.
* There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices
* sharing a table.
*
* Known limitations:
* - UDP tunnel port notifications are fundamentally best-effort -
* it is likely the driver will both see skbs which use a UDP tunnel port,
* while not being a tunneled skb, and tunnel skbs from other ports -
* drivers should only use these ports for non-critical RX-side offloads,
* e.g. the checksum offload;
* - none of the devices care about the socket family at present, so we don't
* track it. Please extend this code if you care.
*/
struct udp_tunnel_nic_info {
/* one-by-one */
int (*set_port)(struct net_device *dev,
unsigned int table, unsigned int entry,
struct udp_tunnel_info *ti);
int (*unset_port)(struct net_device *dev,
unsigned int table, unsigned int entry,
struct udp_tunnel_info *ti);
/* all at once */
int (*sync_table)(struct net_device *dev, unsigned int table);
struct udp_tunnel_nic_shared *shared;
unsigned int flags;
struct udp_tunnel_nic_table_info {
unsigned int n_entries;
unsigned int tunnel_types;
} tables[UDP_TUNNEL_NIC_MAX_TABLES];
};
/* UDP tunnel module dependencies
*
* Tunnel drivers are expected to have a hard dependency on the udp_tunnel
* module. NIC drivers are not, they just attach their
* struct udp_tunnel_nic_info to the netdev and wait for callbacks to come.
* Loading a tunnel driver will cause the udp_tunnel module to be loaded
* and only then will all the required state structures be allocated.
* Since we want a weak dependency from the drivers and the core to udp_tunnel
* we call things through the following stubs.
*/
struct udp_tunnel_nic_ops {
void (*get_port)(struct net_device *dev, unsigned int table,
unsigned int idx, struct udp_tunnel_info *ti);
void (*set_port_priv)(struct net_device *dev, unsigned int table,
unsigned int idx, u8 priv);
void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti);
void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti);
void (*reset_ntf)(struct net_device *dev);
size_t (*dump_size)(struct net_device *dev, unsigned int table);
int (*dump_write)(struct net_device *dev, unsigned int table,
struct sk_buff *skb);
};
#ifdef CONFIG_INET
extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
#else
#define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL)
#endif
static inline void
udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
unsigned int idx, struct udp_tunnel_info *ti)
{
/* This helper is used from .sync_table, we indicate empty entries
* by zero'ed @ti. Drivers which need to know the details of a port
* when it gets deleted should use the .set_port / .unset_port
* callbacks.
* Zero out here, otherwise !CONFIG_INET causes uninitilized warnings.
*/
memset(ti, 0, sizeof(*ti));
if (udp_tunnel_nic_ops)
udp_tunnel_nic_ops->get_port(dev, table, idx, ti);
}
static inline void
udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
unsigned int idx, u8 priv)
{
if (udp_tunnel_nic_ops)
udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
}
static inline void
udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
return;
if (udp_tunnel_nic_ops)
udp_tunnel_nic_ops->add_port(dev, ti);
}
static inline void
udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT))
return;
if (udp_tunnel_nic_ops)
udp_tunnel_nic_ops->del_port(dev, ti);
}
/**
* udp_tunnel_nic_reset_ntf() - device-originating reset notification
* @dev: network interface device structure
*
* Called by the driver to inform the core that the entire UDP tunnel port
* state has been lost, usually due to device reset. Core will assume device
* forgot all the ports and issue .set_port and .sync_table callbacks as
* necessary.
*
* This function must be called with rtnl lock held, and will issue all
* the callbacks before returning.
*/
static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
{
if (udp_tunnel_nic_ops)
udp_tunnel_nic_ops->reset_ntf(dev);
}
static inline size_t
udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table)
{
if (!udp_tunnel_nic_ops)
return 0;
return udp_tunnel_nic_ops->dump_size(dev, table);
}
static inline int
udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table,
struct sk_buff *skb)
{
if (!udp_tunnel_nic_ops)
return 0;
return udp_tunnel_nic_ops->dump_write(dev, table, skb);
}
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PID_H
#define _LINUX_PID_H
#include <linux/pid_types.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/sched.h>
#include <linux/wait.h>
/*
* What is struct pid?
*
* A struct pid is the kernel's internal notion of a process identifier.
* It refers to individual tasks, process groups, and sessions. While
* there are processes attached to it the struct pid lives in a hash
* table, so it and then the processes that it refers to can be found
* quickly from the numeric pid value. The attached processes may be
* quickly accessed by following pointers from struct pid.
*
* Storing pid_t values in the kernel and referring to them later has a
* problem. The process originally with that pid may have exited and the
* pid allocator wrapped, and another process could have come along
* and been assigned that pid.
*
* Referring to user space processes by holding a reference to struct
* task_struct has a problem. When the user space process exits
* the now useless task_struct is still kept. A task_struct plus a
* stack consumes around 10K of low kernel memory. More precisely
* this is THREAD_SIZE + sizeof(struct task_struct). By comparison
* a struct pid is about 64 bytes.
*
* Holding a reference to struct pid solves both of these problems.
* It is small so holding a reference does not consume a lot of
* resources, and since a new struct pid is allocated when the numeric pid
* value is reused (when pids wrap around) we don't mistakenly refer to new
* processes.
*/
/*
* struct upid is used to get the id of the struct pid, as it is
* seen in particular namespace. Later the struct pid is found with
* find_pid_ns() using the int nr and struct pid_namespace *ns.
*/
#define RESERVED_PIDS 300
struct upid {
int nr;
struct pid_namespace *ns;
};
struct pid
{
refcount_t count;
unsigned int level;
spinlock_t lock;
struct dentry *stashed;
u64 ino;
struct rb_node pidfs_node;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct hlist_head inodes;
/* wait queue for pidfd notifications */
wait_queue_head_t wait_pidfd;
struct rcu_head rcu;
struct upid numbers[];
};
extern seqcount_spinlock_t pidmap_lock_seq;
extern struct pid init_struct_pid;
struct file;
struct pid *pidfd_pid(const struct file *file);
struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags);
int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret);
void do_notify_pidfd(struct task_struct *task);
static inline struct pid *get_pid(struct pid *pid)
{
if (pid) refcount_inc(&pid->count);
return pid;
}
extern void put_pid(struct pid *pid);
extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
static inline bool pid_has_task(struct pid *pid, enum pid_type type)
{
return !hlist_empty(&pid->tasks[type]);
}
extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type);
extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type);
/*
* these helpers must be called with the tasklist_lock write-held.
*/
extern void attach_pid(struct task_struct *task, enum pid_type);
void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type);
void change_pid(struct pid **pids, struct task_struct *task, enum pid_type,
struct pid *pid);
extern void exchange_tids(struct task_struct *task, struct task_struct *old);
extern void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type);
/*
* look up a PID in the hash table. Must be called with the tasklist_lock
* or rcu_read_lock() held.
*
* find_pid_ns() finds the pid in the namespace specified
* find_vpid() finds the pid by its virtual id, i.e. in the current namespace
*
* see also find_task_by_vpid() set in include/linux/sched.h
*/
extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns);
extern struct pid *find_vpid(int nr);
/*
* Lookup a PID in the hash table, and return with it's count elevated.
*/
extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
size_t set_tid_size);
extern void free_pid(struct pid *pid);
void free_pids(struct pid **pids);
extern void disable_pid_allocation(struct pid_namespace *ns);
/*
* ns_of_pid() returns the pid namespace in which the specified pid was
* allocated.
*
* NOTE:
* ns_of_pid() is expected to be called for a process (task) that has
* an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid
* is expected to be non-NULL. If @pid is NULL, caller should handle
* the resulting NULL pid-ns.
*/
static inline struct pid_namespace *ns_of_pid(struct pid *pid)
{
struct pid_namespace *ns = NULL;
if (pid) ns = pid->numbers[pid->level].ns;
return ns;
}
/*
* is_child_reaper returns true if the pid is the init process
* of the current namespace. As this one could be checked before
* pid_ns->child_reaper is assigned in copy_process, we check
* with the pid number.
*/
static inline bool is_child_reaper(struct pid *pid)
{
return pid->numbers[pid->level].nr == 1;
}
/*
* the helpers to get the pid's id seen from different namespaces
*
* pid_nr() : global id, i.e. the id seen from the init namespace;
* pid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* pid_nr_ns() : id seen from the ns specified.
*
* see also task_xid_nr() etc in include/linux/sched.h
*/
static inline pid_t pid_nr(struct pid *pid)
{
pid_t nr = 0;
if (pid)
nr = pid->numbers[0].nr;
return nr;
}
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns);
pid_t pid_vnr(struct pid *pid);
#define do_each_pid_task(pid, type, task) \
do { \
if ((pid) != NULL) \
hlist_for_each_entry_rcu((task), \
&(pid)->tasks[type], pid_links[type]) {
/*
* Both old and new leaders may be attached to
* the same pid in the middle of de_thread().
*/
#define while_each_pid_task(pid, type, task) \
if (type == PIDTYPE_PID) \
break; \
} \
} while (0)
#define do_each_pid_thread(pid, type, task) \
do_each_pid_task(pid, type, task) { \
struct task_struct *tg___ = task; \
for_each_thread(tg___, task) {
#define while_each_pid_thread(pid, type, task) \
} \
task = tg___; \
} while_each_pid_task(pid, type, task)
static inline struct pid *task_pid(struct task_struct *task)
{
return task->thread_pid;
}
/*
* the helpers to get the task's different pids as they are seen
* from various namespaces
*
* task_xid_nr() : global id, i.e. the id seen from the init namespace;
* task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of
* current.
* task_xid_nr_ns() : id seen from the ns specified;
*
* see also pid_nr() etc in include/linux/pid.h
*/
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
static inline pid_t task_pid_nr(struct task_struct *tsk)
{
return tsk->pid;
}
static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
}
static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
}
static inline pid_t task_tgid_nr(struct task_struct *tsk)
{
return tsk->tgid;
}
/**
* pid_alive - check that a task structure is not stale
* @p: Task structure to be checked.
*
* Test if a process is not yet dead (at most zombie state)
* If pid_alive fails, then pointers within the task structure
* can be stale and must not be dereferenced.
*
* Return: 1 if the process is alive. 0 otherwise.
*/
static inline int pid_alive(const struct task_struct *p)
{
return p->thread_pid != NULL;
}
static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
}
static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
}
static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
}
static inline pid_t task_session_vnr(struct task_struct *tsk)
{
return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
}
static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
}
static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
}
static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
{
pid_t pid = 0;
rcu_read_lock();
if (pid_alive(tsk))
pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
rcu_read_unlock();
return pid;
}
static inline pid_t task_ppid_nr(const struct task_struct *tsk)
{
return task_ppid_nr_ns(tsk, &init_pid_ns);
}
/* Obsolete, do not use: */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
/**
* is_global_init - check if a task structure is init. Since init
* is free to have sub-threads we need to check tgid.
* @tsk: Task structure to be checked.
*
* Check if a task structure is the first user space task the kernel created.
*
* Return: 1 if the task structure is init. 0 otherwise.
*/
static inline int is_global_init(struct task_struct *tsk)
{
return task_tgid_nr(tsk) == 1;
}
#endif /* _LINUX_PID_H */
// SPDX-License-Identifier: GPL-2.0
#include <linux/err.h>
#include <linux/bug.h>
#include <linux/atomic.h>
#include <linux/errseq.h>
#include <linux/log2.h>
/*
* An errseq_t is a way of recording errors in one place, and allowing any
* number of "subscribers" to tell whether it has changed since a previous
* point where it was sampled.
*
* It's implemented as an unsigned 32-bit value. The low order bits are
* designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits
* are used as a counter. This is done with atomics instead of locking so that
* these functions can be called from any context.
*
* The general idea is for consumers to sample an errseq_t value. That value
* can later be used to tell whether any new errors have occurred since that
* sampling was done.
*
* Note that there is a risk of collisions if new errors are being recorded
* frequently, since we have so few bits to use as a counter.
*
* To mitigate this, one bit is used as a flag to tell whether the value has
* been sampled since a new value was recorded. That allows us to avoid bumping
* the counter if no one has sampled it since the last time an error was
* recorded.
*
* A new errseq_t should always be zeroed out. A errseq_t value of all zeroes
* is the special (but common) case where there has never been an error. An all
* zero value thus serves as the "epoch" if one wishes to know whether there
* has ever been an error set since it was first initialized.
*/
/* The low bits are designated for error code (max of MAX_ERRNO) */
#define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1)
/* This bit is used as a flag to indicate whether the value has been seen */
#define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT)
/* The lowest bit of the counter */
#define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1))
/**
* errseq_set - set a errseq_t for later reporting
* @eseq: errseq_t field that should be set
* @err: error to set (must be between -1 and -MAX_ERRNO)
*
* This function sets the error in @eseq, and increments the sequence counter
* if the last sequence was sampled at some point in the past.
*
* Any error set will always overwrite an existing error.
*
* Return: The previous value, primarily for debugging purposes. The
* return value should not be used as a previously sampled value in later
* calls as it will not have the SEEN flag set.
*/
errseq_t errseq_set(errseq_t *eseq, int err)
{
errseq_t cur, old;
/* MAX_ERRNO must be able to serve as a mask */
BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1);
/*
* Ensure the error code actually fits where we want it to go. If it
* doesn't then just throw a warning and don't record anything. We
* also don't accept zero here as that would effectively clear a
* previous error.
*/
old = READ_ONCE(*eseq);
if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO),
"err = %d\n", err))
return old;
for (;;) {
errseq_t new;
/* Clear out error bits and set new error */
new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err;
/* Only increment if someone has looked at it */
if (old & ERRSEQ_SEEN)
new += ERRSEQ_CTR_INC;
/* If there would be no change, then call it done */
if (new == old) {
cur = new;
break;
}
/* Try to swap the new value into place */
cur = cmpxchg(eseq, old, new);
/*
* Call it success if we did the swap or someone else beat us
* to it for the same value.
*/
if (likely(cur == old || cur == new))
break;
/* Raced with an update, try again */
old = cur;
}
return cur;
}
EXPORT_SYMBOL(errseq_set);
/**
* errseq_sample() - Grab current errseq_t value.
* @eseq: Pointer to errseq_t to be sampled.
*
* This function allows callers to initialise their errseq_t variable.
* If the error has been "seen", new callers will not see an old error.
* If there is an unseen error in @eseq, the caller of this function will
* see it the next time it checks for an error.
*
* Context: Any context.
* Return: The current errseq value.
*/
errseq_t errseq_sample(errseq_t *eseq)
{
errseq_t old = READ_ONCE(*eseq);
/* If nobody has seen this error yet, then we can be the first. */
if (!(old & ERRSEQ_SEEN))
old = 0;
return old;
}
EXPORT_SYMBOL(errseq_sample);
/**
* errseq_check() - Has an error occurred since a particular sample point?
* @eseq: Pointer to errseq_t value to be checked.
* @since: Previously-sampled errseq_t from which to check.
*
* Grab the value that eseq points to, and see if it has changed @since
* the given value was sampled. The @since value is not advanced, so there
* is no need to mark the value as seen.
*
* Return: The latest error set in the errseq_t or 0 if it hasn't changed.
*/
int errseq_check(errseq_t *eseq, errseq_t since)
{
errseq_t cur = READ_ONCE(*eseq);
if (likely(cur == since))
return 0;
return -(cur & MAX_ERRNO);
}
EXPORT_SYMBOL(errseq_check);
/**
* errseq_check_and_advance() - Check an errseq_t and advance to current value.
* @eseq: Pointer to value being checked and reported.
* @since: Pointer to previously-sampled errseq_t to check against and advance.
*
* Grab the eseq value, and see whether it matches the value that @since
* points to. If it does, then just return 0.
*
* If it doesn't, then the value has changed. Set the "seen" flag, and try to
* swap it into place as the new eseq value. Then, set that value as the new
* "since" value, and return whatever the error portion is set to.
*
* Note that no locking is provided here for concurrent updates to the "since"
* value. The caller must provide that if necessary. Because of this, callers
* may want to do a lockless errseq_check before taking the lock and calling
* this.
*
* Return: Negative errno if one has been stored, or 0 if no new error has
* occurred.
*/
int errseq_check_and_advance(errseq_t *eseq, errseq_t *since)
{
int err = 0;
errseq_t old, new;
/*
* Most callers will want to use the inline wrapper to check this,
* so that the common case of no error is handled without needing
* to take the lock that protects the "since" value.
*/
old = READ_ONCE(*eseq);
if (old != *since) {
/*
* Set the flag and try to swap it into place if it has
* changed.
*
* We don't care about the outcome of the swap here. If the
* swap doesn't occur, then it has either been updated by a
* writer who is altering the value in some way (updating
* counter or resetting the error), or another reader who is
* just setting the "seen" flag. Either outcome is OK, and we
* can advance "since" and return an error based on what we
* have.
*/
new = old | ERRSEQ_SEEN;
if (new != old)
cmpxchg(eseq, old, new);
*since = new;
err = -(new & MAX_ERRNO);
}
return err;
}
EXPORT_SYMBOL(errseq_check_and_advance);
// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/libfs.c
* Library for filesystems writers.
*/
#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/quotaops.h>
#include <linux/mutex.h>
#include <linux/namei.h>
#include <linux/exportfs.h>
#include <linux/iversion.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h> /* sync_mapping_buffers */
#include <linux/fs_context.h>
#include <linux/pseudo_fs.h>
#include <linux/fsnotify.h>
#include <linux/unicode.h>
#include <linux/fscrypt.h>
#include <linux/pidfs.h>
#include <linux/uaccess.h>
#include "internal.h"
int simple_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask,
unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
return 0;
}
EXPORT_SYMBOL(simple_getattr);
int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
{
u64 id = huge_encode_dev(dentry->d_sb->s_dev);
buf->f_fsid = u64_to_fsid(id);
buf->f_type = dentry->d_sb->s_magic;
buf->f_bsize = PAGE_SIZE;
buf->f_namelen = NAME_MAX;
return 0;
}
EXPORT_SYMBOL(simple_statfs);
/*
* Retaining negative dentries for an in-memory filesystem just wastes
* memory and lookup time: arrange for them to be deleted immediately.
*/
int always_delete_dentry(const struct dentry *dentry)
{
return 1;
}
EXPORT_SYMBOL(always_delete_dentry);
const struct dentry_operations simple_dentry_operations = {
.d_delete = always_delete_dentry,
};
EXPORT_SYMBOL(simple_dentry_operations);
/*
* Lookup the data. This is trivial - if the dentry didn't already
* exist, we know it is negative. Set d_op to delete negative dentries.
*/
struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{ if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
if (!dentry->d_sb->s_d_op) d_set_d_op(dentry, &simple_dentry_operations); if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
return NULL;
d_add(dentry, NULL);
return NULL;
}
EXPORT_SYMBOL(simple_lookup);
int dcache_dir_open(struct inode *inode, struct file *file)
{
file->private_data = d_alloc_cursor(file->f_path.dentry);
return file->private_data ? 0 : -ENOMEM;
}
EXPORT_SYMBOL(dcache_dir_open);
int dcache_dir_close(struct inode *inode, struct file *file)
{
dput(file->private_data);
return 0;
}
EXPORT_SYMBOL(dcache_dir_close);
/* parent is locked at least shared */
/*
* Returns an element of siblings' list.
* We are looking for <count>th positive after <p>; if
* found, dentry is grabbed and returned to caller.
* If no such element exists, NULL is returned.
*/
static struct dentry *scan_positives(struct dentry *cursor,
struct hlist_node **p,
loff_t count,
struct dentry *last)
{
struct dentry *dentry = cursor->d_parent, *found = NULL;
spin_lock(&dentry->d_lock);
while (*p) {
struct dentry *d = hlist_entry(*p, struct dentry, d_sib);
p = &d->d_sib.next;
// we must at least skip cursors, to avoid livelocks
if (d->d_flags & DCACHE_DENTRY_CURSOR)
continue;
if (simple_positive(d) && !--count) {
spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(d))
found = dget_dlock(d);
spin_unlock(&d->d_lock);
if (likely(found))
break;
count = 1;
}
if (need_resched()) {
if (!hlist_unhashed(&cursor->d_sib))
__hlist_del(&cursor->d_sib);
hlist_add_behind(&cursor->d_sib, &d->d_sib);
p = &cursor->d_sib.next;
spin_unlock(&dentry->d_lock);
cond_resched();
spin_lock(&dentry->d_lock);
}
}
spin_unlock(&dentry->d_lock);
dput(last);
return found;
}
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry *dentry = file->f_path.dentry;
switch (whence) {
case 1:
offset += file->f_pos;
fallthrough;
case 0:
if (offset >= 0)
break;
fallthrough;
default:
return -EINVAL;
}
if (offset != file->f_pos) {
struct dentry *cursor = file->private_data;
struct dentry *to = NULL;
inode_lock_shared(dentry->d_inode);
if (offset > 2)
to = scan_positives(cursor, &dentry->d_children.first,
offset - 2, NULL);
spin_lock(&dentry->d_lock);
hlist_del_init(&cursor->d_sib);
if (to)
hlist_add_behind(&cursor->d_sib, &to->d_sib);
spin_unlock(&dentry->d_lock);
dput(to);
file->f_pos = offset;
inode_unlock_shared(dentry->d_inode);
}
return offset;
}
EXPORT_SYMBOL(dcache_dir_lseek);
/*
* Directory is locked and all positive dentries in it are safe, since
* for ramfs-type trees they can't go away without unlink() or rmdir(),
* both impossible due to the lock on directory.
*/
int dcache_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file->f_path.dentry;
struct dentry *cursor = file->private_data;
struct dentry *next = NULL;
struct hlist_node **p;
if (!dir_emit_dots(file, ctx))
return 0;
if (ctx->pos == 2)
p = &dentry->d_children.first;
else
p = &cursor->d_sib.next;
while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
d_inode(next)->i_ino,
fs_umode_to_dtype(d_inode(next)->i_mode)))
break;
ctx->pos++;
p = &next->d_sib.next;
}
spin_lock(&dentry->d_lock);
hlist_del_init(&cursor->d_sib);
if (next)
hlist_add_before(&cursor->d_sib, &next->d_sib);
spin_unlock(&dentry->d_lock);
dput(next);
return 0;
}
EXPORT_SYMBOL(dcache_readdir);
ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos)
{
return -EISDIR;
}
EXPORT_SYMBOL(generic_read_dir);
const struct file_operations simple_dir_operations = {
.open = dcache_dir_open,
.release = dcache_dir_close,
.llseek = dcache_dir_lseek,
.read = generic_read_dir,
.iterate_shared = dcache_readdir,
.fsync = noop_fsync,
};
EXPORT_SYMBOL(simple_dir_operations);
const struct inode_operations simple_dir_inode_operations = {
.lookup = simple_lookup,
};
EXPORT_SYMBOL(simple_dir_inode_operations);
/* simple_offset_add() never assigns these to a dentry */
enum {
DIR_OFFSET_FIRST = 2, /* Find first real entry */
DIR_OFFSET_EOD = S32_MAX,
};
/* simple_offset_add() allocation range */
enum {
DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1,
DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1,
};
static void offset_set(struct dentry *dentry, long offset)
{
dentry->d_fsdata = (void *)offset;
}
static long dentry2offset(struct dentry *dentry)
{
return (long)dentry->d_fsdata;
}
static struct lock_class_key simple_offset_lock_class;
/**
* simple_offset_init - initialize an offset_ctx
* @octx: directory offset map to be initialized
*
*/
void simple_offset_init(struct offset_ctx *octx)
{
mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE);
lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class);
octx->next_offset = DIR_OFFSET_MIN;
}
/**
* simple_offset_add - Add an entry to a directory's offset map
* @octx: directory offset ctx to be updated
* @dentry: new dentry being added
*
* Returns zero on success. @octx and the dentry's offset are updated.
* Otherwise, a negative errno value is returned.
*/
int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
{
unsigned long offset;
int ret;
if (dentry2offset(dentry) != 0)
return -EBUSY;
ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
DIR_OFFSET_MAX, &octx->next_offset,
GFP_KERNEL);
if (unlikely(ret < 0))
return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset);
return 0;
}
static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry,
long offset)
{
int ret;
ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL);
if (ret)
return ret;
offset_set(dentry, offset);
return 0;
}
/**
* simple_offset_remove - Remove an entry to a directory's offset map
* @octx: directory offset ctx to be updated
* @dentry: dentry being removed
*
*/
void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
{
long offset;
offset = dentry2offset(dentry);
if (offset == 0)
return;
mtree_erase(&octx->mt, offset);
offset_set(dentry, 0);
}
/**
* simple_offset_rename - handle directory offsets for rename
* @old_dir: parent directory of source entry
* @old_dentry: dentry of source entry
* @new_dir: parent_directory of destination entry
* @new_dentry: dentry of destination
*
* Caller provides appropriate serialization.
*
* User space expects the directory offset value of the replaced
* (new) directory entry to be unchanged after a rename.
*
* Returns zero on success, a negative errno value on failure.
*/
int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
long new_offset = dentry2offset(new_dentry);
simple_offset_remove(old_ctx, old_dentry);
if (new_offset) {
offset_set(new_dentry, 0);
return simple_offset_replace(new_ctx, old_dentry, new_offset);
}
return simple_offset_add(new_ctx, old_dentry);
}
/**
* simple_offset_rename_exchange - exchange rename with directory offsets
* @old_dir: parent of dentry being moved
* @old_dentry: dentry being moved
* @new_dir: destination parent
* @new_dentry: destination dentry
*
* This API preserves the directory offset values. Caller provides
* appropriate serialization.
*
* Returns zero on success. Otherwise a negative errno is returned and the
* rename is rolled back.
*/
int simple_offset_rename_exchange(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry)
{
struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
long old_index = dentry2offset(old_dentry);
long new_index = dentry2offset(new_dentry);
int ret;
simple_offset_remove(old_ctx, old_dentry);
simple_offset_remove(new_ctx, new_dentry);
ret = simple_offset_replace(new_ctx, old_dentry, new_index);
if (ret)
goto out_restore;
ret = simple_offset_replace(old_ctx, new_dentry, old_index);
if (ret) {
simple_offset_remove(new_ctx, old_dentry);
goto out_restore;
}
ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
if (ret) {
simple_offset_remove(new_ctx, old_dentry);
simple_offset_remove(old_ctx, new_dentry);
goto out_restore;
}
return 0;
out_restore:
(void)simple_offset_replace(old_ctx, old_dentry, old_index);
(void)simple_offset_replace(new_ctx, new_dentry, new_index);
return ret;
}
/**
* simple_offset_destroy - Release offset map
* @octx: directory offset ctx that is about to be destroyed
*
* During fs teardown (eg. umount), a directory's offset map might still
* contain entries. xa_destroy() cleans out anything that remains.
*/
void simple_offset_destroy(struct offset_ctx *octx)
{
mtree_destroy(&octx->mt);
}
/**
* offset_dir_llseek - Advance the read position of a directory descriptor
* @file: an open directory whose position is to be updated
* @offset: a byte offset
* @whence: enumerator describing the starting position for this update
*
* SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories.
*
* Returns the updated read position if successful; otherwise a
* negative errno is returned and the read position remains unchanged.
*/
static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
{
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
fallthrough;
case SEEK_SET:
if (offset >= 0)
break;
fallthrough;
default:
return -EINVAL;
}
return vfs_setpos(file, offset, LONG_MAX);
}
static struct dentry *find_positive_dentry(struct dentry *parent,
struct dentry *dentry,
bool next)
{
struct dentry *found = NULL;
spin_lock(&parent->d_lock);
if (next)
dentry = d_next_sibling(dentry);
else if (!dentry)
dentry = d_first_child(parent);
hlist_for_each_entry_from(dentry, d_sib) {
if (!simple_positive(dentry))
continue;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(dentry))
found = dget_dlock(dentry);
spin_unlock(&dentry->d_lock);
if (likely(found))
break;
}
spin_unlock(&parent->d_lock);
return found;
}
static noinline_for_stack struct dentry *
offset_dir_lookup(struct dentry *parent, loff_t offset)
{
struct inode *inode = d_inode(parent);
struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
struct dentry *child, *found = NULL;
MA_STATE(mas, &octx->mt, offset, offset);
if (offset == DIR_OFFSET_FIRST)
found = find_positive_dentry(parent, NULL, false);
else {
rcu_read_lock();
child = mas_find_rev(&mas, DIR_OFFSET_MIN);
found = find_positive_dentry(parent, child, false);
rcu_read_unlock();
}
return found;
}
static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len,
inode->i_ino, fs_umode_to_dtype(inode->i_mode));
}
static void offset_iterate_dir(struct file *file, struct dir_context *ctx)
{
struct dentry *dir = file->f_path.dentry;
struct dentry *dentry;
dentry = offset_dir_lookup(dir, ctx->pos);
if (!dentry)
goto out_eod;
while (true) {
struct dentry *next;
ctx->pos = dentry2offset(dentry);
if (!offset_dir_emit(ctx, dentry))
break;
next = find_positive_dentry(dir, dentry, true);
dput(dentry);
if (!next)
goto out_eod;
dentry = next;
}
dput(dentry);
return;
out_eod:
ctx->pos = DIR_OFFSET_EOD;
}
/**
* offset_readdir - Emit entries starting at offset @ctx->pos
* @file: an open directory to iterate over
* @ctx: directory iteration context
*
* Caller must hold @file's i_rwsem to prevent insertion or removal of
* entries during this call.
*
* On entry, @ctx->pos contains an offset that represents the first entry
* to be read from the directory.
*
* The operation continues until there are no more entries to read, or
* until the ctx->actor indicates there is no more space in the caller's
* output buffer.
*
* On return, @ctx->pos contains an offset that will read the next entry
* in this directory when offset_readdir() is called again with @ctx.
* Caller places this value in the d_off field of the last entry in the
* user's buffer.
*
* Return values:
* %0 - Complete
*/
static int offset_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dir = file->f_path.dentry;
lockdep_assert_held(&d_inode(dir)->i_rwsem);
if (!dir_emit_dots(file, ctx))
return 0;
if (ctx->pos != DIR_OFFSET_EOD)
offset_iterate_dir(file, ctx);
return 0;
}
const struct file_operations simple_offset_dir_operations = {
.llseek = offset_dir_llseek,
.iterate_shared = offset_readdir,
.read = generic_read_dir,
.fsync = noop_fsync,
};
static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
{
struct dentry *child = NULL, *d;
spin_lock(&parent->d_lock);
d = prev ? d_next_sibling(prev) : d_first_child(parent); hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) {
spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(d)) child = dget_dlock(d);
spin_unlock(&d->d_lock);
if (likely(child))
break;
}
}
spin_unlock(&parent->d_lock);
dput(prev);
return child;
}
void simple_recursive_removal(struct dentry *dentry,
void (*callback)(struct dentry *))
{ struct dentry *this = dget(dentry);
while (true) {
struct dentry *victim = NULL, *child;
struct inode *inode = this->d_inode;
inode_lock(inode);
if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) {
// kill and ascend
// update metadata while it's still locked
inode_set_ctime_current(inode);
clear_nlink(inode);
inode_unlock(inode);
victim = this;
this = this->d_parent;
inode = this->d_inode;
inode_lock(inode);
if (simple_positive(victim)) {
d_invalidate(victim); // avoid lost mounts
if (d_is_dir(victim))
fsnotify_rmdir(inode, victim);
else
fsnotify_unlink(inode, victim); if (callback) callback(victim);
dput(victim); // unpin it
}
if (victim == dentry) {
inode_set_mtime_to_ts(inode,
inode_set_ctime_current(inode));
if (d_is_dir(dentry)) drop_nlink(inode);
inode_unlock(inode);
dput(dentry);
return;
}
}
inode_unlock(inode);
this = child;
}
}
EXPORT_SYMBOL(simple_recursive_removal);
static const struct super_operations simple_super_operations = {
.statfs = simple_statfs,
};
static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc)
{
struct pseudo_fs_context *ctx = fc->fs_private;
struct inode *root;
s->s_maxbytes = MAX_LFS_FILESIZE;
s->s_blocksize = PAGE_SIZE;
s->s_blocksize_bits = PAGE_SHIFT;
s->s_magic = ctx->magic;
s->s_op = ctx->ops ?: &simple_super_operations;
s->s_export_op = ctx->eops;
s->s_xattr = ctx->xattr;
s->s_time_gran = 1;
root = new_inode(s);
if (!root)
return -ENOMEM;
/*
* since this is the first inode, make it number 1. New inodes created
* after this must take care not to collide with it (by passing
* max_reserved of 1 to iunique).
*/
root->i_ino = 1;
root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
simple_inode_init_ts(root);
s->s_root = d_make_root(root);
if (!s->s_root)
return -ENOMEM;
s->s_d_op = ctx->dops;
return 0;
}
static int pseudo_fs_get_tree(struct fs_context *fc)
{
return get_tree_nodev(fc, pseudo_fs_fill_super);
}
static void pseudo_fs_free(struct fs_context *fc)
{
kfree(fc->fs_private);
}
static const struct fs_context_operations pseudo_fs_context_ops = {
.free = pseudo_fs_free,
.get_tree = pseudo_fs_get_tree,
};
/*
* Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
* will never be mountable)
*/
struct pseudo_fs_context *init_pseudo(struct fs_context *fc,
unsigned long magic)
{
struct pseudo_fs_context *ctx;
ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL);
if (likely(ctx)) {
ctx->magic = magic;
fc->fs_private = ctx;
fc->ops = &pseudo_fs_context_ops;
fc->sb_flags |= SB_NOUSER;
fc->global = true;
}
return ctx;
}
EXPORT_SYMBOL(init_pseudo);
int simple_open(struct inode *inode, struct file *file)
{
if (inode->i_private)
file->private_data = inode->i_private;
return 0;
}
EXPORT_SYMBOL(simple_open);
int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(old_dentry);
inode_set_mtime_to_ts(dir,
inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode)));
inc_nlink(inode);
ihold(inode);
dget(dentry);
d_instantiate(dentry, inode);
return 0;
}
EXPORT_SYMBOL(simple_link);
int simple_empty(struct dentry *dentry)
{
struct dentry *child;
int ret = 0;
spin_lock(&dentry->d_lock);
hlist_for_each_entry(child, &dentry->d_children, d_sib) {
spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(child)) {
spin_unlock(&child->d_lock);
goto out;
}
spin_unlock(&child->d_lock);
}
ret = 1;
out:
spin_unlock(&dentry->d_lock);
return ret;
}
EXPORT_SYMBOL(simple_empty);
int simple_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
inode_set_mtime_to_ts(dir,
inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode)));
drop_nlink(inode);
dput(dentry);
return 0;
}
EXPORT_SYMBOL(simple_unlink);
int simple_rmdir(struct inode *dir, struct dentry *dentry)
{
if (!simple_empty(dentry))
return -ENOTEMPTY;
drop_nlink(d_inode(dentry));
simple_unlink(dir, dentry);
drop_nlink(dir);
return 0;
}
EXPORT_SYMBOL(simple_rmdir);
/**
* simple_rename_timestamp - update the various inode timestamps for rename
* @old_dir: old parent directory
* @old_dentry: dentry that is being renamed
* @new_dir: new parent directory
* @new_dentry: target for rename
*
* POSIX mandates that the old and new parent directories have their ctime and
* mtime updated, and that inodes of @old_dentry and @new_dentry (if any), have
* their ctime updated.
*/
void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct inode *newino = d_inode(new_dentry);
inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir));
if (new_dir != old_dir)
inode_set_mtime_to_ts(new_dir,
inode_set_ctime_current(new_dir));
inode_set_ctime_current(d_inode(old_dentry));
if (newino)
inode_set_ctime_current(newino);
}
EXPORT_SYMBOL_GPL(simple_rename_timestamp);
int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
bool old_is_dir = d_is_dir(old_dentry);
bool new_is_dir = d_is_dir(new_dentry);
if (old_dir != new_dir && old_is_dir != new_is_dir) {
if (old_is_dir) {
drop_nlink(old_dir);
inc_nlink(new_dir);
} else {
drop_nlink(new_dir);
inc_nlink(old_dir);
}
}
simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
return 0;
}
EXPORT_SYMBOL_GPL(simple_rename_exchange);
int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir,
struct dentry *old_dentry, struct inode *new_dir,
struct dentry *new_dentry, unsigned int flags)
{
int they_are_dirs = d_is_dir(old_dentry);
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
return -EINVAL;
if (flags & RENAME_EXCHANGE)
return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
if (!simple_empty(new_dentry))
return -ENOTEMPTY;
if (d_really_is_positive(new_dentry)) {
simple_unlink(new_dir, new_dentry);
if (they_are_dirs) {
drop_nlink(d_inode(new_dentry));
drop_nlink(old_dir);
}
} else if (they_are_dirs) {
drop_nlink(old_dir);
inc_nlink(new_dir);
}
simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
return 0;
}
EXPORT_SYMBOL(simple_rename);
/**
* simple_setattr - setattr for simple filesystem
* @idmap: idmap of the target mount
* @dentry: dentry
* @iattr: iattr structure
*
* Returns 0 on success, -error on failure.
*
* simple_setattr is a simple ->setattr implementation without a proper
* implementation of size changes.
*
* It can either be used for in-memory filesystems or special files
* on simple regular filesystems. Anything that needs to change on-disk
* or wire state on size changes needs its own setattr method.
*/
int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int error;
error = setattr_prepare(idmap, dentry, iattr);
if (error)
return error;
if (iattr->ia_valid & ATTR_SIZE)
truncate_setsize(inode, iattr->ia_size);
setattr_copy(idmap, inode, iattr);
mark_inode_dirty(inode);
return 0;
}
EXPORT_SYMBOL(simple_setattr);
static int simple_read_folio(struct file *file, struct folio *folio)
{
folio_zero_range(folio, 0, folio_size(folio));
flush_dcache_folio(folio);
folio_mark_uptodate(folio);
folio_unlock(folio);
return 0;
}
int simple_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata)
{
struct folio *folio;
folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
*foliop = folio;
if (!folio_test_uptodate(folio) && (len != folio_size(folio))) {
size_t from = offset_in_folio(folio, pos);
folio_zero_segments(folio, 0, from,
from + len, folio_size(folio));
}
return 0;
}
EXPORT_SYMBOL(simple_write_begin);
/**
* simple_write_end - .write_end helper for non-block-device FSes
* @file: See .write_end of address_space_operations
* @mapping: "
* @pos: "
* @len: "
* @copied: "
* @folio: "
* @fsdata: "
*
* simple_write_end does the minimum needed for updating a folio after
* writing is done. It has the same API signature as the .write_end of
* address_space_operations vector. So it can just be set onto .write_end for
* FSes that don't need any other processing. i_mutex is assumed to be held.
* Block based filesystems should use generic_write_end().
* NOTE: Even though i_size might get updated by this function, mark_inode_dirty
* is not called, so a filesystem that actually does store data in .write_inode
* should extend on what's done here with a call to mark_inode_dirty() in the
* case that i_size has changed.
*
* Use *ONLY* with simple_read_folio()
*/
static int simple_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
{
struct inode *inode = folio->mapping->host;
loff_t last_pos = pos + copied;
/* zero the stale part of the folio if we did a short copy */
if (!folio_test_uptodate(folio)) {
if (copied < len) {
size_t from = offset_in_folio(folio, pos);
folio_zero_range(folio, from + copied, len - copied);
}
folio_mark_uptodate(folio);
}
/*
* No need to use i_size_read() here, the i_size
* cannot change under us because we hold the i_mutex.
*/
if (last_pos > inode->i_size)
i_size_write(inode, last_pos);
folio_mark_dirty(folio);
folio_unlock(folio);
folio_put(folio);
return copied;
}
/*
* Provides ramfs-style behavior: data in the pagecache, but no writeback.
*/
const struct address_space_operations ram_aops = {
.read_folio = simple_read_folio,
.write_begin = simple_write_begin,
.write_end = simple_write_end,
.dirty_folio = noop_dirty_folio,
};
EXPORT_SYMBOL(ram_aops);
/*
* the inodes created here are not hashed. If you use iunique to generate
* unique inode values later for this filesystem, then you must take care
* to pass it an appropriate max_reserved value to avoid collisions.
*/
int simple_fill_super(struct super_block *s, unsigned long magic,
const struct tree_descr *files)
{
struct inode *inode;
struct dentry *dentry;
int i;
s->s_blocksize = PAGE_SIZE;
s->s_blocksize_bits = PAGE_SHIFT;
s->s_magic = magic;
s->s_op = &simple_super_operations;
s->s_time_gran = 1;
inode = new_inode(s);
if (!inode)
return -ENOMEM;
/*
* because the root inode is 1, the files array must not contain an
* entry at index 1
*/
inode->i_ino = 1;
inode->i_mode = S_IFDIR | 0755;
simple_inode_init_ts(inode);
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
set_nlink(inode, 2);
s->s_root = d_make_root(inode);
if (!s->s_root)
return -ENOMEM;
for (i = 0; !files->name || files->name[0]; i++, files++) {
if (!files->name)
continue;
/* warn if it tries to conflict with the root inode */
if (unlikely(i == 1))
printk(KERN_WARNING "%s: %s passed in a files array"
"with an index of 1!\n", __func__,
s->s_type->name);
dentry = d_alloc_name(s->s_root, files->name);
if (!dentry)
return -ENOMEM;
inode = new_inode(s);
if (!inode) {
dput(dentry);
return -ENOMEM;
}
inode->i_mode = S_IFREG | files->mode;
simple_inode_init_ts(inode);
inode->i_fop = files->ops;
inode->i_ino = i;
d_add(dentry, inode);
}
return 0;
}
EXPORT_SYMBOL(simple_fill_super);
static DEFINE_SPINLOCK(pin_fs_lock);
int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
{
struct vfsmount *mnt = NULL;
spin_lock(&pin_fs_lock);
if (unlikely(!*mount)) {
spin_unlock(&pin_fs_lock);
mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
spin_lock(&pin_fs_lock);
if (!*mount) *mount = mnt;
}
mntget(*mount);
++*count;
spin_unlock(&pin_fs_lock);
mntput(mnt);
return 0;
}
EXPORT_SYMBOL(simple_pin_fs);
void simple_release_fs(struct vfsmount **mount, int *count)
{
struct vfsmount *mnt;
spin_lock(&pin_fs_lock);
mnt = *mount;
if (!--*count) *mount = NULL;
spin_unlock(&pin_fs_lock);
mntput(mnt);
}
EXPORT_SYMBOL(simple_release_fs);
/**
* simple_read_from_buffer - copy data from the buffer to user space
* @to: the user space buffer to read to
* @count: the maximum number of bytes to read
* @ppos: the current position in the buffer
* @from: the buffer to read from
* @available: the size of the buffer
*
* The simple_read_from_buffer() function reads up to @count bytes from the
* buffer @from at offset @ppos into the user space address starting at @to.
*
* On success, the number of bytes read is returned and the offset @ppos is
* advanced by this number, or negative value is returned on error.
**/
ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
const void *from, size_t available)
{
loff_t pos = *ppos;
size_t ret;
if (pos < 0)
return -EINVAL;
if (pos >= available || !count)
return 0;
if (count > available - pos)
count = available - pos;
ret = copy_to_user(to, from + pos, count);
if (ret == count)
return -EFAULT;
count -= ret;
*ppos = pos + count;
return count;
}
EXPORT_SYMBOL(simple_read_from_buffer);
/**
* simple_write_to_buffer - copy data from user space to the buffer
* @to: the buffer to write to
* @available: the size of the buffer
* @ppos: the current position in the buffer
* @from: the user space buffer to read from
* @count: the maximum number of bytes to read
*
* The simple_write_to_buffer() function reads up to @count bytes from the user
* space address starting at @from into the buffer @to at offset @ppos.
*
* On success, the number of bytes written is returned and the offset @ppos is
* advanced by this number, or negative value is returned on error.
**/
ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count)
{
loff_t pos = *ppos;
size_t res;
if (pos < 0)
return -EINVAL;
if (pos >= available || !count)
return 0;
if (count > available - pos)
count = available - pos;
res = copy_from_user(to + pos, from, count);
if (res == count)
return -EFAULT;
count -= res;
*ppos = pos + count;
return count;
}
EXPORT_SYMBOL(simple_write_to_buffer);
/**
* memory_read_from_buffer - copy data from the buffer
* @to: the kernel space buffer to read to
* @count: the maximum number of bytes to read
* @ppos: the current position in the buffer
* @from: the buffer to read from
* @available: the size of the buffer
*
* The memory_read_from_buffer() function reads up to @count bytes from the
* buffer @from at offset @ppos into the kernel space address starting at @to.
*
* On success, the number of bytes read is returned and the offset @ppos is
* advanced by this number, or negative value is returned on error.
**/
ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
const void *from, size_t available)
{
loff_t pos = *ppos;
if (pos < 0)
return -EINVAL;
if (pos >= available)
return 0;
if (count > available - pos)
count = available - pos;
memcpy(to, from + pos, count);
*ppos = pos + count;
return count;
}
EXPORT_SYMBOL(memory_read_from_buffer);
/*
* Transaction based IO.
* The file expects a single write which triggers the transaction, and then
* possibly a read which collects the result - which is stored in a
* file-local buffer.
*/
void simple_transaction_set(struct file *file, size_t n)
{
struct simple_transaction_argresp *ar = file->private_data;
BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
/*
* The barrier ensures that ar->size will really remain zero until
* ar->data is ready for reading.
*/
smp_mb();
ar->size = n;
}
EXPORT_SYMBOL(simple_transaction_set);
char *simple_transaction_get(struct file *file, const char __user *buf, size_t size)
{
struct simple_transaction_argresp *ar;
static DEFINE_SPINLOCK(simple_transaction_lock);
if (size > SIMPLE_TRANSACTION_LIMIT - 1)
return ERR_PTR(-EFBIG);
ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL);
if (!ar)
return ERR_PTR(-ENOMEM);
spin_lock(&simple_transaction_lock);
/* only one write allowed per open */
if (file->private_data) {
spin_unlock(&simple_transaction_lock);
free_page((unsigned long)ar);
return ERR_PTR(-EBUSY);
}
file->private_data = ar;
spin_unlock(&simple_transaction_lock);
if (copy_from_user(ar->data, buf, size))
return ERR_PTR(-EFAULT);
return ar->data;
}
EXPORT_SYMBOL(simple_transaction_get);
ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
{
struct simple_transaction_argresp *ar = file->private_data;
if (!ar)
return 0;
return simple_read_from_buffer(buf, size, pos, ar->data, ar->size);
}
EXPORT_SYMBOL(simple_transaction_read);
int simple_transaction_release(struct inode *inode, struct file *file)
{
free_page((unsigned long)file->private_data);
return 0;
}
EXPORT_SYMBOL(simple_transaction_release);
/* Simple attribute files */
struct simple_attr {
int (*get)(void *, u64 *);
int (*set)(void *, u64);
char get_buf[24]; /* enough to store a u64 and "\n\0" */
char set_buf[24];
void *data;
const char *fmt; /* format for read operation */
struct mutex mutex; /* protects access to these buffers */
};
/* simple_attr_open is called by an actual attribute open file operation
* to set the attribute specific access operations. */
int simple_attr_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt)
{
struct simple_attr *attr;
attr = kzalloc(sizeof(*attr), GFP_KERNEL);
if (!attr)
return -ENOMEM;
attr->get = get;
attr->set = set;
attr->data = inode->i_private;
attr->fmt = fmt;
mutex_init(&attr->mutex);
file->private_data = attr;
return nonseekable_open(inode, file);
}
EXPORT_SYMBOL_GPL(simple_attr_open);
int simple_attr_release(struct inode *inode, struct file *file)
{
kfree(file->private_data);
return 0;
}
EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */
/* read from the buffer that is filled with the get function */
ssize_t simple_attr_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos)
{
struct simple_attr *attr;
size_t size;
ssize_t ret;
attr = file->private_data;
if (!attr->get)
return -EACCES;
ret = mutex_lock_interruptible(&attr->mutex);
if (ret)
return ret;
if (*ppos && attr->get_buf[0]) {
/* continued read */
size = strlen(attr->get_buf);
} else {
/* first read */
u64 val;
ret = attr->get(attr->data, &val);
if (ret)
goto out;
size = scnprintf(attr->get_buf, sizeof(attr->get_buf),
attr->fmt, (unsigned long long)val);
}
ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size);
out:
mutex_unlock(&attr->mutex);
return ret;
}
EXPORT_SYMBOL_GPL(simple_attr_read);
/* interpret the buffer as a number to call the set function with */
static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf,
size_t len, loff_t *ppos, bool is_signed)
{
struct simple_attr *attr;
unsigned long long val;
size_t size;
ssize_t ret;
attr = file->private_data;
if (!attr->set)
return -EACCES;
ret = mutex_lock_interruptible(&attr->mutex);
if (ret)
return ret;
ret = -EFAULT;
size = min(sizeof(attr->set_buf) - 1, len);
if (copy_from_user(attr->set_buf, buf, size))
goto out;
attr->set_buf[size] = '\0';
if (is_signed)
ret = kstrtoll(attr->set_buf, 0, &val);
else
ret = kstrtoull(attr->set_buf, 0, &val);
if (ret)
goto out;
ret = attr->set(attr->data, val);
if (ret == 0)
ret = len; /* on success, claim we got the whole input */
out:
mutex_unlock(&attr->mutex);
return ret;
}
ssize_t simple_attr_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos)
{
return simple_attr_write_xsigned(file, buf, len, ppos, false);
}
EXPORT_SYMBOL_GPL(simple_attr_write);
ssize_t simple_attr_write_signed(struct file *file, const char __user *buf,
size_t len, loff_t *ppos)
{
return simple_attr_write_xsigned(file, buf, len, ppos, true);
}
EXPORT_SYMBOL_GPL(simple_attr_write_signed);
/**
* generic_encode_ino32_fh - generic export_operations->encode_fh function
* @inode: the object to encode
* @fh: where to store the file handle fragment
* @max_len: maximum length to store there (in 4 byte units)
* @parent: parent directory inode, if wanted
*
* This generic encode_fh function assumes that the 32 inode number
* is suitable for locating an inode, and that the generation number
* can be used to check that it is still valid. It places them in the
* filehandle fragment where export_decode_fh expects to find them.
*/
int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len,
struct inode *parent)
{
struct fid *fid = (void *)fh;
int len = *max_len;
int type = FILEID_INO32_GEN;
if (parent && (len < 4)) {
*max_len = 4;
return FILEID_INVALID;
} else if (len < 2) {
*max_len = 2;
return FILEID_INVALID;
}
len = 2;
fid->i32.ino = inode->i_ino;
fid->i32.gen = inode->i_generation;
if (parent) {
fid->i32.parent_ino = parent->i_ino;
fid->i32.parent_gen = parent->i_generation;
len = 4;
type = FILEID_INO32_GEN_PARENT;
}
*max_len = len;
return type;
}
EXPORT_SYMBOL_GPL(generic_encode_ino32_fh);
/**
* generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
* @sb: filesystem to do the file handle conversion on
* @fid: file handle to convert
* @fh_len: length of the file handle in bytes
* @fh_type: type of file handle
* @get_inode: filesystem callback to retrieve inode
*
* This function decodes @fid as long as it has one of the well-known
* Linux filehandle types and calls @get_inode on it to retrieve the
* inode for the object specified in the file handle.
*/
struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type, struct inode *(*get_inode)
(struct super_block *sb, u64 ino, u32 gen))
{
struct inode *inode = NULL;
if (fh_len < 2)
return NULL;
switch (fh_type) {
case FILEID_INO32_GEN:
case FILEID_INO32_GEN_PARENT:
inode = get_inode(sb, fid->i32.ino, fid->i32.gen);
break;
}
return d_obtain_alias(inode);
}
EXPORT_SYMBOL_GPL(generic_fh_to_dentry);
/**
* generic_fh_to_parent - generic helper for the fh_to_parent export operation
* @sb: filesystem to do the file handle conversion on
* @fid: file handle to convert
* @fh_len: length of the file handle in bytes
* @fh_type: type of file handle
* @get_inode: filesystem callback to retrieve inode
*
* This function decodes @fid as long as it has one of the well-known
* Linux filehandle types and calls @get_inode on it to retrieve the
* inode for the _parent_ object specified in the file handle if it
* is specified in the file handle, or NULL otherwise.
*/
struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type, struct inode *(*get_inode)
(struct super_block *sb, u64 ino, u32 gen))
{
struct inode *inode = NULL;
if (fh_len <= 2)
return NULL;
switch (fh_type) {
case FILEID_INO32_GEN_PARENT:
inode = get_inode(sb, fid->i32.parent_ino,
(fh_len > 3 ? fid->i32.parent_gen : 0));
break;
}
return d_obtain_alias(inode);
}
EXPORT_SYMBOL_GPL(generic_fh_to_parent);
/**
* __generic_file_fsync - generic fsync implementation for simple filesystems
*
* @file: file to synchronize
* @start: start offset in bytes
* @end: end offset in bytes (inclusive)
* @datasync: only synchronize essential metadata if true
*
* This is a generic implementation of the fsync method for simple
* filesystems which track all non-inode metadata in the buffers list
* hanging off the address_space structure.
*/
int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
int err;
int ret;
err = file_write_and_wait_range(file, start, end);
if (err)
return err;
inode_lock(inode);
ret = sync_mapping_buffers(inode->i_mapping);
if (!(inode->i_state & I_DIRTY_ALL))
goto out;
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
goto out;
err = sync_inode_metadata(inode, 1);
if (ret == 0)
ret = err;
out:
inode_unlock(inode);
/* check and advance again to catch errors after syncing out buffers */
err = file_check_and_advance_wb_err(file);
if (ret == 0)
ret = err;
return ret;
}
EXPORT_SYMBOL(__generic_file_fsync);
/**
* generic_file_fsync - generic fsync implementation for simple filesystems
* with flush
* @file: file to synchronize
* @start: start offset in bytes
* @end: end offset in bytes (inclusive)
* @datasync: only synchronize essential metadata if true
*
*/
int generic_file_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
int err;
err = __generic_file_fsync(file, start, end, datasync);
if (err)
return err;
return blkdev_issue_flush(inode->i_sb->s_bdev);
}
EXPORT_SYMBOL(generic_file_fsync);
/**
* generic_check_addressable - Check addressability of file system
* @blocksize_bits: log of file system block size
* @num_blocks: number of blocks in file system
*
* Determine whether a file system with @num_blocks blocks (and a
* block size of 2**@blocksize_bits) is addressable by the sector_t
* and page cache of the system. Return 0 if so and -EFBIG otherwise.
*/
int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
{
u64 last_fs_block = num_blocks - 1;
u64 last_fs_page =
last_fs_block >> (PAGE_SHIFT - blocksize_bits);
if (unlikely(num_blocks == 0))
return 0;
if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT))
return -EINVAL;
if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
(last_fs_page > (pgoff_t)(~0ULL))) {
return -EFBIG;
}
return 0;
}
EXPORT_SYMBOL(generic_check_addressable);
/*
* No-op implementation of ->fsync for in-memory filesystems.
*/
int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
return 0;
}
EXPORT_SYMBOL(noop_fsync);
ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
/*
* iomap based filesystems support direct I/O without need for
* this callback. However, it still needs to be set in
* inode->a_ops so that open/fcntl know that direct I/O is
* generally supported.
*/
return -EINVAL;
}
EXPORT_SYMBOL_GPL(noop_direct_IO);
/* Because kfree isn't assignment-compatible with void(void*) ;-/ */
void kfree_link(void *p)
{
kfree(p);
}
EXPORT_SYMBOL(kfree_link);
struct inode *alloc_anon_inode(struct super_block *s)
{
static const struct address_space_operations anon_aops = {
.dirty_folio = noop_dirty_folio,
};
struct inode *inode = new_inode_pseudo(s);
if (!inode)
return ERR_PTR(-ENOMEM);
inode->i_ino = get_next_ino();
inode->i_mapping->a_ops = &anon_aops;
/*
* Mark the inode dirty from the very beginning,
* that way it will never be moved to the dirty
* list because mark_inode_dirty() will think
* that it already _is_ on the dirty list.
*/
inode->i_state = I_DIRTY;
inode->i_mode = S_IRUSR | S_IWUSR;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
inode->i_flags |= S_PRIVATE;
simple_inode_init_ts(inode);
return inode;
}
EXPORT_SYMBOL(alloc_anon_inode);
/**
* simple_nosetlease - generic helper for prohibiting leases
* @filp: file pointer
* @arg: type of lease to obtain
* @flp: new lease supplied for insertion
* @priv: private data for lm_setup operation
*
* Generic helper for filesystems that do not wish to allow leases to be set.
* All arguments are ignored and it just returns -EINVAL.
*/
int
simple_nosetlease(struct file *filp, int arg, struct file_lease **flp,
void **priv)
{
return -EINVAL;
}
EXPORT_SYMBOL(simple_nosetlease);
/**
* simple_get_link - generic helper to get the target of "fast" symlinks
* @dentry: not used here
* @inode: the symlink inode
* @done: not used here
*
* Generic helper for filesystems to use for symlink inodes where a pointer to
* the symlink target is stored in ->i_link. NOTE: this isn't normally called,
* since as an optimization the path lookup code uses any non-NULL ->i_link
* directly, without calling ->get_link(). But ->get_link() still must be set,
* to mark the inode_operations as being for a symlink.
*
* Return: the symlink target
*/
const char *simple_get_link(struct dentry *dentry, struct inode *inode,
struct delayed_call *done)
{
return inode->i_link;
}
EXPORT_SYMBOL(simple_get_link);
const struct inode_operations simple_symlink_inode_operations = {
.get_link = simple_get_link,
};
EXPORT_SYMBOL(simple_symlink_inode_operations);
/*
* Operations for a permanently empty directory.
*/
static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
return ERR_PTR(-ENOENT);
}
static int empty_dir_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *attr)
{
return -EPERM;
}
static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size)
{
return -EOPNOTSUPP;
}
static const struct inode_operations empty_dir_inode_operations = {
.lookup = empty_dir_lookup,
.setattr = empty_dir_setattr,
.listxattr = empty_dir_listxattr,
};
static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence)
{
/* An empty directory has two entries . and .. at offsets 0 and 1 */
return generic_file_llseek_size(file, offset, whence, 2, 2);
}
static int empty_dir_readdir(struct file *file, struct dir_context *ctx)
{
dir_emit_dots(file, ctx);
return 0;
}
static const struct file_operations empty_dir_operations = {
.llseek = empty_dir_llseek,
.read = generic_read_dir,
.iterate_shared = empty_dir_readdir,
.fsync = noop_fsync,
};
void make_empty_dir_inode(struct inode *inode)
{
set_nlink(inode, 2);
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
inode->i_rdev = 0;
inode->i_size = 0;
inode->i_blkbits = PAGE_SHIFT;
inode->i_blocks = 0;
inode->i_op = &empty_dir_inode_operations;
inode->i_opflags &= ~IOP_XATTR;
inode->i_fop = &empty_dir_operations;
}
bool is_empty_dir_inode(struct inode *inode)
{
return (inode->i_fop == &empty_dir_operations) &&
(inode->i_op == &empty_dir_inode_operations);
}
#if IS_ENABLED(CONFIG_UNICODE)
/**
* generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
* @dentry: dentry whose name we are checking against
* @len: len of name of dentry
* @str: str pointer to name of dentry
* @name: Name to compare against
*
* Return: 0 if names match, 1 if mismatch, or -ERRNO
*/
int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name)
{
const struct dentry *parent;
const struct inode *dir;
union shortname_store strbuf;
struct qstr qstr;
/*
* Attempt a case-sensitive match first. It is cheaper and
* should cover most lookups, including all the sane
* applications that expect a case-sensitive filesystem.
*
* This comparison is safe under RCU because the caller
* guarantees the consistency between str and len. See
* __d_lookup_rcu_op_compare() for details.
*/
if (len == name->len && !memcmp(str, name->name, len))
return 0;
parent = READ_ONCE(dentry->d_parent);
dir = READ_ONCE(parent->d_inode);
if (!dir || !IS_CASEFOLDED(dir))
return 1;
qstr.len = len;
qstr.name = str;
/*
* If the dentry name is stored in-line, then it may be concurrently
* modified by a rename. If this happens, the VFS will eventually retry
* the lookup, so it doesn't matter what ->d_compare() returns.
* However, it's unsafe to call utf8_strncasecmp() with an unstable
* string. Therefore, we have to copy the name into a temporary buffer.
* As above, len is guaranteed to match str, so the shortname case
* is exactly when str points to ->d_shortname.
*/
if (qstr.name == dentry->d_shortname.string) {
strbuf = dentry->d_shortname; // NUL is guaranteed to be in there
qstr.name = strbuf.string;
/* prevent compiler from optimizing out the temporary buffer */
barrier();
}
return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
}
EXPORT_SYMBOL(generic_ci_d_compare);
/**
* generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
* @dentry: dentry of the parent directory
* @str: qstr of name whose hash we should fill in
*
* Return: 0 if hash was successful or unchanged, and -EINVAL on error
*/
int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
{
const struct inode *dir = READ_ONCE(dentry->d_inode);
struct super_block *sb = dentry->d_sb;
const struct unicode_map *um = sb->s_encoding;
int ret;
if (!dir || !IS_CASEFOLDED(dir))
return 0;
ret = utf8_casefold_hash(um, dentry, str);
if (ret < 0 && sb_has_strict_encoding(sb))
return -EINVAL;
return 0;
}
EXPORT_SYMBOL(generic_ci_d_hash);
static const struct dentry_operations generic_ci_dentry_ops = {
.d_hash = generic_ci_d_hash,
.d_compare = generic_ci_d_compare,
#ifdef CONFIG_FS_ENCRYPTION
.d_revalidate = fscrypt_d_revalidate,
#endif
};
/**
* generic_ci_match() - Match a name (case-insensitively) with a dirent.
* This is a filesystem helper for comparison with directory entries.
* generic_ci_d_compare should be used in VFS' ->d_compare instead.
*
* @parent: Inode of the parent of the dirent under comparison
* @name: name under lookup.
* @folded_name: Optional pre-folded name under lookup
* @de_name: Dirent name.
* @de_name_len: dirent name length.
*
* Test whether a case-insensitive directory entry matches the filename
* being searched. If @folded_name is provided, it is used instead of
* recalculating the casefold of @name.
*
* Return: > 0 if the directory entry matches, 0 if it doesn't match, or
* < 0 on error.
*/
int generic_ci_match(const struct inode *parent,
const struct qstr *name,
const struct qstr *folded_name,
const u8 *de_name, u32 de_name_len)
{
const struct super_block *sb = parent->i_sb;
const struct unicode_map *um = sb->s_encoding;
struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
struct qstr dirent = QSTR_INIT(de_name, de_name_len);
int res = 0;
if (IS_ENCRYPTED(parent)) {
const struct fscrypt_str encrypted_name =
FSTR_INIT((u8 *) de_name, de_name_len);
if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent)))
return -EINVAL;
decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
if (!decrypted_name.name)
return -ENOMEM;
res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
&decrypted_name);
if (res < 0) {
kfree(decrypted_name.name);
return res;
}
dirent.name = decrypted_name.name;
dirent.len = decrypted_name.len;
}
/*
* Attempt a case-sensitive match first. It is cheaper and
* should cover most lookups, including all the sane
* applications that expect a case-sensitive filesystem.
*/
if (dirent.len == name->len &&
!memcmp(name->name, dirent.name, dirent.len))
goto out;
if (folded_name->name)
res = utf8_strncasecmp_folded(um, folded_name, &dirent);
else
res = utf8_strncasecmp(um, name, &dirent);
out:
kfree(decrypted_name.name);
if (res < 0 && sb_has_strict_encoding(sb)) {
pr_err_ratelimited("Directory contains filename that is invalid UTF-8");
return 0;
}
return !res;
}
EXPORT_SYMBOL(generic_ci_match);
#endif
#ifdef CONFIG_FS_ENCRYPTION
static const struct dentry_operations generic_encrypted_dentry_ops = {
.d_revalidate = fscrypt_d_revalidate,
};
#endif
/**
* generic_set_sb_d_ops - helper for choosing the set of
* filesystem-wide dentry operations for the enabled features
* @sb: superblock to be configured
*
* Filesystems supporting casefolding and/or fscrypt can call this
* helper at mount-time to configure sb->s_d_op to best set of dentry
* operations required for the enabled features. The helper must be
* called after these have been configured, but before the root dentry
* is created.
*/
void generic_set_sb_d_ops(struct super_block *sb)
{
#if IS_ENABLED(CONFIG_UNICODE)
if (sb->s_encoding) {
sb->s_d_op = &generic_ci_dentry_ops;
return;
}
#endif
#ifdef CONFIG_FS_ENCRYPTION
if (sb->s_cop) {
sb->s_d_op = &generic_encrypted_dentry_ops;
return;
}
#endif
}
EXPORT_SYMBOL(generic_set_sb_d_ops);
/**
* inode_maybe_inc_iversion - increments i_version
* @inode: inode with the i_version that should be updated
* @force: increment the counter even if it's not necessary?
*
* Every time the inode is modified, the i_version field must be seen to have
* changed by any observer.
*
* If "force" is set or the QUERIED flag is set, then ensure that we increment
* the value, and clear the queried flag.
*
* In the common case where neither is set, then we can return "false" without
* updating i_version.
*
* If this function returns false, and no other metadata has changed, then we
* can avoid logging the metadata.
*/
bool inode_maybe_inc_iversion(struct inode *inode, bool force)
{
u64 cur, new;
/*
* The i_version field is not strictly ordered with any other inode
* information, but the legacy inode_inc_iversion code used a spinlock
* to serialize increments.
*
* We add a full memory barrier to ensure that any de facto ordering
* with other state is preserved (either implicitly coming from cmpxchg
* or explicitly from smp_mb if we don't know upfront if we will execute
* the former).
*
* These barriers pair with inode_query_iversion().
*/
cur = inode_peek_iversion_raw(inode);
if (!force && !(cur & I_VERSION_QUERIED)) { smp_mb();
cur = inode_peek_iversion_raw(inode);
}
do {
/* If flag is clear then we needn't do anything */
if (!force && !(cur & I_VERSION_QUERIED))
return false;
/* Since lowest bit is flag, add 2 to avoid it */
new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT;
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
return true;
}
EXPORT_SYMBOL(inode_maybe_inc_iversion);
/**
* inode_query_iversion - read i_version for later use
* @inode: inode from which i_version should be read
*
* Read the inode i_version counter. This should be used by callers that wish
* to store the returned i_version for later comparison. This will guarantee
* that a later query of the i_version will result in a different value if
* anything has changed.
*
* In this implementation, we fetch the current value, set the QUERIED flag and
* then try to swap it into place with a cmpxchg, if it wasn't already set. If
* that fails, we try again with the newly fetched value from the cmpxchg.
*/
u64 inode_query_iversion(struct inode *inode)
{
u64 cur, new;
bool fenced = false;
/*
* Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with
* inode_maybe_inc_iversion(), see that routine for more details.
*/
cur = inode_peek_iversion_raw(inode);
do {
/* If flag is already set, then no need to swap */
if (cur & I_VERSION_QUERIED) {
if (!fenced)
smp_mb();
break;
}
fenced = true;
new = cur | I_VERSION_QUERIED;
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
return cur >> I_VERSION_QUERIED_SHIFT;
}
EXPORT_SYMBOL(inode_query_iversion);
ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
ssize_t direct_written, ssize_t buffered_written)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
loff_t pos = iocb->ki_pos - buffered_written;
loff_t end = iocb->ki_pos - 1;
int err;
/*
* If the buffered write fallback returned an error, we want to return
* the number of bytes which were written by direct I/O, or the error
* code if that was zero.
*
* Note that this differs from normal direct-io semantics, which will
* return -EFOO even if some bytes were written.
*/
if (unlikely(buffered_written < 0)) {
if (direct_written)
return direct_written;
return buffered_written;
}
/*
* We need to ensure that the page cache pages are written to disk and
* invalidated to preserve the expected O_DIRECT semantics.
*/
err = filemap_write_and_wait_range(mapping, pos, end);
if (err < 0) {
/*
* We don't know how much we wrote, so just return the number of
* bytes which were direct-written
*/
iocb->ki_pos -= buffered_written;
if (direct_written)
return direct_written;
return err;
}
invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
return direct_written + buffered_written;
}
EXPORT_SYMBOL_GPL(direct_write_fallback);
/**
* simple_inode_init_ts - initialize the timestamps for a new inode
* @inode: inode to be initialized
*
* When a new inode is created, most filesystems set the timestamps to the
* current time. Add a helper to do this.
*/
struct timespec64 simple_inode_init_ts(struct inode *inode)
{
struct timespec64 ts = inode_set_ctime_current(inode);
inode_set_atime_to_ts(inode, ts);
inode_set_mtime_to_ts(inode, ts);
return ts;
}
EXPORT_SYMBOL(simple_inode_init_ts);
struct dentry *stashed_dentry_get(struct dentry **stashed)
{
struct dentry *dentry;
guard(rcu)(); dentry = rcu_dereference(*stashed); if (!dentry)
return NULL;
if (!lockref_get_not_dead(&dentry->d_lockref))
return NULL;
return dentry;
}
static struct dentry *prepare_anon_dentry(struct dentry **stashed,
struct super_block *sb,
void *data)
{
struct dentry *dentry;
struct inode *inode;
const struct stashed_operations *sops = sb->s_fs_info;
int ret;
inode = new_inode_pseudo(sb);
if (!inode) {
sops->put_data(data);
return ERR_PTR(-ENOMEM);
}
inode->i_flags |= S_IMMUTABLE;
inode->i_mode = S_IFREG;
simple_inode_init_ts(inode);
ret = sops->init_inode(inode, data);
if (ret < 0) {
iput(inode);
return ERR_PTR(ret);
}
/* Notice when this is changed. */
WARN_ON_ONCE(!S_ISREG(inode->i_mode)); WARN_ON_ONCE(!IS_IMMUTABLE(inode));
dentry = d_alloc_anon(sb);
if (!dentry) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
/* Store address of location where dentry's supposed to be stashed. */
dentry->d_fsdata = stashed;
/* @data is now owned by the fs */
d_instantiate(dentry, inode);
return dentry;
}
static struct dentry *stash_dentry(struct dentry **stashed,
struct dentry *dentry)
{
guard(rcu)();
for (;;) {
struct dentry *old;
/* Assume any old dentry was cleared out. */
old = cmpxchg(stashed, NULL, dentry); if (likely(!old))
return dentry;
/* Check if somebody else installed a reusable dentry. */
if (lockref_get_not_dead(&old->d_lockref))
return old;
/* There's an old dead dentry there, try to take it over. */
if (likely(try_cmpxchg(stashed, &old, dentry)))
return dentry;
}
}
/**
* path_from_stashed - create path from stashed or new dentry
* @stashed: where to retrieve or stash dentry
* @mnt: mnt of the filesystems to use
* @data: data to store in inode->i_private
* @path: path to create
*
* The function tries to retrieve a stashed dentry from @stashed. If the dentry
* is still valid then it will be reused. If the dentry isn't able the function
* will allocate a new dentry and inode. It will then check again whether it
* can reuse an existing dentry in case one has been added in the meantime or
* update @stashed with the newly added dentry.
*
* Special-purpose helper for nsfs and pidfs.
*
* Return: On success zero and on failure a negative error is returned.
*/
int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
struct path *path)
{
struct dentry *dentry;
const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
/* See if dentry can be reused. */
path->dentry = stashed_dentry_get(stashed);
if (path->dentry) {
sops->put_data(data);
goto out_path;
}
/* Allocate a new dentry. */
dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data); if (IS_ERR(dentry))
return PTR_ERR(dentry);
/* Added a new dentry. @data is now owned by the filesystem. */
path->dentry = stash_dentry(stashed, dentry); if (path->dentry != dentry) dput(dentry);
out_path:
WARN_ON_ONCE(path->dentry->d_fsdata != stashed); WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
path->mnt = mntget(mnt);
return 0;
}
void stashed_dentry_prune(struct dentry *dentry)
{
struct dentry **stashed = dentry->d_fsdata;
struct inode *inode = d_inode(dentry);
if (WARN_ON_ONCE(!stashed))
return;
if (!inode)
return;
/*
* Only replace our own @dentry as someone else might've
* already cleared out @dentry and stashed their own
* dentry in there.
*/
cmpxchg(stashed, dentry, NULL);
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015, 2016 ARM Ltd.
*/
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/list_sort.h>
#include <linux/nospec.h>
#include <asm/kvm_hyp.h>
#include "vgic.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
struct vgic_global kvm_vgic_global_state __ro_after_init = {
.gicv3_cpuif = STATIC_KEY_FALSE_INIT,
};
/*
* Locking order is always:
* kvm->lock (mutex)
* vcpu->mutex (mutex)
* kvm->arch.config_lock (mutex)
* its->cmd_lock (mutex)
* its->its_lock (mutex)
* vgic_cpu->ap_list_lock must be taken with IRQs disabled
* vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled
* vgic_irq->irq_lock must be taken with IRQs disabled
*
* As the ap_list_lock might be taken from the timer interrupt handler,
* we have to disable IRQs before taking this lock and everything lower
* than it.
*
* The config_lock has additional ordering requirements:
* kvm->slots_lock
* kvm->srcu
* kvm->arch.config_lock
*
* If you need to take multiple locks, always take the upper lock first,
* then the lower ones, e.g. first take the its_lock, then the irq_lock.
* If you are already holding a lock and need to take a higher one, you
* have to drop the lower ranking lock first and re-acquire it after having
* taken the upper one.
*
* When taking more than one ap_list_lock at the same time, always take the
* lowest numbered VCPU's ap_list_lock first, so:
* vcpuX->vcpu_id < vcpuY->vcpu_id:
* raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock);
* raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock);
*
* Since the VGIC must support injecting virtual interrupts from ISRs, we have
* to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer
* spinlocks for any lock that may be taken while injecting an interrupt.
*/
/*
* Index the VM's xarray of mapped LPIs and return a reference to the IRQ
* structure. The caller is expected to call vgic_put_irq() later once it's
* finished with the IRQ.
*/
static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = NULL;
rcu_read_lock();
irq = xa_load(&dist->lpi_xa, intid);
if (!vgic_try_get_irq_kref(irq))
irq = NULL;
rcu_read_unlock();
return irq;
}
/*
* This looks up the virtual interrupt ID to get the corresponding
* struct vgic_irq. It also increases the refcount, so any caller is expected
* to call vgic_put_irq() once it's finished with this IRQ.
*/
struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid)
{
/* SPIs */
if (intid >= VGIC_NR_PRIVATE_IRQS &&
intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) {
intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS);
return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
}
/* LPIs */
if (intid >= VGIC_MIN_LPI) return vgic_get_lpi(kvm, intid);
return NULL;
}
struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid)
{ if (WARN_ON(!vcpu))
return NULL;
/* SGIs and PPIs */
if (intid < VGIC_NR_PRIVATE_IRQS) {
intid = array_index_nospec(intid, VGIC_NR_PRIVATE_IRQS);
return &vcpu->arch.vgic_cpu.private_irqs[intid];
}
return vgic_get_irq(vcpu->kvm, intid);
}
/*
* We can't do anything in here, because we lack the kvm pointer to
* lock and remove the item from the lpi_list. So we keep this function
* empty and use the return value of kref_put() to trigger the freeing.
*/
static void vgic_irq_release(struct kref *ref)
{
}
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
unsigned long flags;
if (irq->intid < VGIC_MIN_LPI)
return;
if (!kref_put(&irq->refcount, vgic_irq_release))
return;
xa_lock_irqsave(&dist->lpi_xa, flags);
__xa_erase(&dist->lpi_xa, irq->intid);
xa_unlock_irqrestore(&dist->lpi_xa, flags);
kfree_rcu(irq, rcu);
}
void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq, *tmp;
unsigned long flags;
raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { if (irq->intid >= VGIC_MIN_LPI) {
raw_spin_lock(&irq->irq_lock);
list_del(&irq->ap_list);
irq->vcpu = NULL;
raw_spin_unlock(&irq->irq_lock);
vgic_put_irq(vcpu->kvm, irq);
}
}
raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
}
void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
{
WARN_ON(irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
pending));
}
bool vgic_get_phys_line_level(struct vgic_irq *irq)
{
bool line_level;
BUG_ON(!irq->hw); if (irq->ops && irq->ops->get_input_level)
return irq->ops->get_input_level(irq->intid);
WARN_ON(irq_get_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
&line_level));
return line_level;
}
/* Set/Clear the physical active state */
void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
{ BUG_ON(!irq->hw); WARN_ON(irq_set_irqchip_state(irq->host_irq,
IRQCHIP_STATE_ACTIVE,
active));
}
/**
* vgic_target_oracle - compute the target vcpu for an irq
*
* @irq: The irq to route. Must be already locked.
*
* Based on the current state of the interrupt (enabled, pending,
* active, vcpu and target_vcpu), compute the next vcpu this should be
* given to. Return NULL if this shouldn't be injected at all.
*
* Requires the IRQ lock to be held.
*/
static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq)
{
lockdep_assert_held(&irq->irq_lock);
/* If the interrupt is active, it must stay on the current vcpu */
if (irq->active)
return irq->vcpu ? : irq->target_vcpu;
/*
* If the IRQ is not active but enabled and pending, we should direct
* it to its configured target VCPU.
* If the distributor is disabled, pending interrupts shouldn't be
* forwarded.
*/
if (irq->enabled && irq_is_pending(irq)) { if (unlikely(irq->target_vcpu &&
!irq->target_vcpu->kvm->arch.vgic.enabled))
return NULL;
return irq->target_vcpu;
}
/* If neither active nor pending and enabled, then this IRQ should not
* be queued to any VCPU.
*/
return NULL;
}
/*
* The order of items in the ap_lists defines how we'll pack things in LRs as
* well, the first items in the list being the first things populated in the
* LRs.
*
* A hard rule is that active interrupts can never be pushed out of the LRs
* (and therefore take priority) since we cannot reliably trap on deactivation
* of IRQs and therefore they have to be present in the LRs.
*
* Otherwise things should be sorted by the priority field and the GIC
* hardware support will take care of preemption of priority groups etc.
*
* Return negative if "a" sorts before "b", 0 to preserve order, and positive
* to sort "b" before "a".
*/
static int vgic_irq_cmp(void *priv, const struct list_head *a,
const struct list_head *b)
{
struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list);
struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list);
bool penda, pendb;
int ret;
/*
* list_sort may call this function with the same element when
* the list is fairly long.
*/
if (unlikely(irqa == irqb))
return 0;
raw_spin_lock(&irqa->irq_lock);
raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING);
if (irqa->active || irqb->active) {
ret = (int)irqb->active - (int)irqa->active;
goto out;
}
penda = irqa->enabled && irq_is_pending(irqa);
pendb = irqb->enabled && irq_is_pending(irqb);
if (!penda || !pendb) {
ret = (int)pendb - (int)penda;
goto out;
}
/* Both pending and enabled, sort by priority */
ret = irqa->priority - irqb->priority;
out:
raw_spin_unlock(&irqb->irq_lock);
raw_spin_unlock(&irqa->irq_lock);
return ret;
}
/* Must be called with the ap_list_lock held */
static void vgic_sort_ap_list(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
lockdep_assert_held(&vgic_cpu->ap_list_lock);
list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp);
}
/*
* Only valid injection if changing level for level-triggered IRQs or for a
* rising edge, and in-kernel connected IRQ lines can only be controlled by
* their owner.
*/
static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner)
{
if (irq->owner != owner)
return false;
switch (irq->config) {
case VGIC_CONFIG_LEVEL:
return irq->line_level != level;
case VGIC_CONFIG_EDGE:
return level;
}
return false;
}
/*
* Check whether an IRQ needs to (and can) be queued to a VCPU's ap list.
* Do the queuing if necessary, taking the right locks in the right order.
* Returns true when the IRQ was queued, false otherwise.
*
* Needs to be entered with the IRQ lock already held, but will return
* with all locks dropped.
*/
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
unsigned long flags) __releases(&irq->irq_lock)
{
struct kvm_vcpu *vcpu;
lockdep_assert_held(&irq->irq_lock);
retry:
vcpu = vgic_target_oracle(irq);
if (irq->vcpu || !vcpu) {
/*
* If this IRQ is already on a VCPU's ap_list, then it
* cannot be moved or modified and there is no more work for
* us to do.
*
* Otherwise, if the irq is not pending and enabled, it does
* not need to be inserted into an ap_list and there is also
* no more work for us to do.
*/
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
/*
* We have to kick the VCPU here, because we could be
* queueing an edge-triggered interrupt for which we
* get no EOI maintenance interrupt. In that case,
* while the IRQ is already on the VCPU's AP list, the
* VCPU could have EOI'ed the original interrupt and
* won't see this one until it exits for some other
* reason.
*/
if (vcpu) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
}
return false;
}
/*
* We must unlock the irq lock to take the ap_list_lock where
* we are going to insert this new pending interrupt.
*/
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
/* someone can do stuff here, which we re-check below */
raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags);
raw_spin_lock(&irq->irq_lock);
/*
* Did something change behind our backs?
*
* There are two cases:
* 1) The irq lost its pending state or was disabled behind our
* backs and/or it was queued to another VCPU's ap_list.
* 2) Someone changed the affinity on this irq behind our
* backs and we are now holding the wrong ap_list_lock.
*
* In both cases, drop the locks and retry.
*/
if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) {
raw_spin_unlock(&irq->irq_lock);
raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock,
flags);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
goto retry;
}
/*
* Grab a reference to the irq to reflect the fact that it is
* now in the ap_list. This is safe as the caller must already hold a
* reference on the irq.
*/
vgic_get_irq_kref(irq); list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
irq->vcpu = vcpu;
raw_spin_unlock(&irq->irq_lock);
raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags);
kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
return true;
}
/**
* kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
* @kvm: The VM structure pointer
* @vcpu: The CPU for PPIs or NULL for global interrupts
* @intid: The INTID to inject a new state to.
* @level: Edge-triggered: true: to trigger the interrupt
* false: to ignore the call
* Level-sensitive true: raise the input signal
* false: lower the input signal
* @owner: The opaque pointer to the owner of the IRQ being raised to verify
* that the caller is allowed to inject this IRQ. Userspace
* injections will have owner == NULL.
*
* The VGIC is not concerned with devices being active-LOW or active-HIGH for
* level-sensitive interrupts. You can think of the level parameter as 1
* being HIGH and 0 being LOW and all devices being active-HIGH.
*/
int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
unsigned int intid, bool level, void *owner)
{
struct vgic_irq *irq;
unsigned long flags;
int ret;
ret = vgic_lazy_init(kvm);
if (ret)
return ret;
if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS)
return -EINVAL;
trace_vgic_update_irq_pending(vcpu ? vcpu->vcpu_idx : 0, intid, level);
if (intid < VGIC_NR_PRIVATE_IRQS)
irq = vgic_get_vcpu_irq(vcpu, intid);
else
irq = vgic_get_irq(kvm, intid); if (!irq)
return -EINVAL;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (!vgic_validate_injection(irq, level, owner)) {
/* Nothing to see here, move along... */
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(kvm, irq);
return 0;
}
if (irq->config == VGIC_CONFIG_LEVEL)
irq->line_level = level;
else
irq->pending_latch = true;
vgic_queue_irq_unlock(kvm, irq, flags);
vgic_put_irq(kvm, irq);
return 0;
}
/* @irq->irq_lock must be held */
static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
unsigned int host_irq,
struct irq_ops *ops)
{
struct irq_desc *desc;
struct irq_data *data;
/*
* Find the physical IRQ number corresponding to @host_irq
*/
desc = irq_to_desc(host_irq);
if (!desc) {
kvm_err("%s: no interrupt descriptor\n", __func__);
return -EINVAL;
}
data = irq_desc_get_irq_data(desc);
while (data->parent_data)
data = data->parent_data;
irq->hw = true;
irq->host_irq = host_irq;
irq->hwintid = data->hwirq;
irq->ops = ops;
return 0;
}
/* @irq->irq_lock must be held */
static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq)
{
irq->hw = false;
irq->hwintid = 0;
irq->ops = NULL;
}
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
u32 vintid, struct irq_ops *ops)
{ struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid);
unsigned long flags;
int ret;
BUG_ON(!irq);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
ret = kvm_vgic_map_irq(vcpu, irq, host_irq, ops);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return ret;
}
/**
* kvm_vgic_reset_mapped_irq - Reset a mapped IRQ
* @vcpu: The VCPU pointer
* @vintid: The INTID of the interrupt
*
* Reset the active and pending states of a mapped interrupt. Kernel
* subsystems injecting mapped interrupts should reset their interrupt lines
* when we are doing a reset of the VM.
*/
void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid)
{ struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid);
unsigned long flags;
if (!irq->hw)
goto out;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
irq->active = false;
irq->pending_latch = false;
irq->line_level = false;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
out:
vgic_put_irq(vcpu->kvm, irq);
}
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid)
{
struct vgic_irq *irq;
unsigned long flags;
if (!vgic_initialized(vcpu->kvm))
return -EAGAIN;
irq = vgic_get_vcpu_irq(vcpu, vintid);
BUG_ON(!irq);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
kvm_vgic_unmap_irq(irq);
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return 0;
}
int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid)
{
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid);
unsigned long flags;
int ret = -1;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw)
ret = irq->hwintid;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return ret;
}
/**
* kvm_vgic_set_owner - Set the owner of an interrupt for a VM
*
* @vcpu: Pointer to the VCPU (used for PPIs)
* @intid: The virtual INTID identifying the interrupt (PPI or SPI)
* @owner: Opaque pointer to the owner
*
* Returns 0 if intid is not already used by another in-kernel device and the
* owner is set, otherwise returns an error code.
*/
int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner)
{
struct vgic_irq *irq;
unsigned long flags;
int ret = 0;
if (!vgic_initialized(vcpu->kvm))
return -EAGAIN;
/* SGIs and LPIs cannot be wired up to any device */
if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid))
return -EINVAL;
irq = vgic_get_vcpu_irq(vcpu, intid);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->owner && irq->owner != owner)
ret = -EEXIST;
else
irq->owner = owner;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
return ret;
}
/**
* vgic_prune_ap_list - Remove non-relevant interrupts from the list
*
* @vcpu: The VCPU pointer
*
* Go over the list of "interesting" interrupts, and prune those that we
* won't have to consider in the near future.
*/
static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq, *tmp;
DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
retry:
raw_spin_lock(&vgic_cpu->ap_list_lock);
list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;
bool target_vcpu_needs_kick = false;
raw_spin_lock(&irq->irq_lock);
BUG_ON(vcpu != irq->vcpu); target_vcpu = vgic_target_oracle(irq); if (!target_vcpu) {
/*
* We don't need to process this interrupt any
* further, move it off the list.
*/
list_del(&irq->ap_list);
irq->vcpu = NULL;
raw_spin_unlock(&irq->irq_lock);
/*
* This vgic_put_irq call matches the
* vgic_get_irq_kref in vgic_queue_irq_unlock,
* where we added the LPI to the ap_list. As
* we remove the irq from the list, we drop
* also drop the refcount.
*/
vgic_put_irq(vcpu->kvm, irq);
continue;
}
if (target_vcpu == vcpu) {
/* We're on the right CPU */
raw_spin_unlock(&irq->irq_lock);
continue;
}
/* This interrupt looks like it has to be migrated. */
raw_spin_unlock(&irq->irq_lock);
raw_spin_unlock(&vgic_cpu->ap_list_lock);
/*
* Ensure locking order by always locking the smallest
* ID first.
*/
if (vcpu->vcpu_id < target_vcpu->vcpu_id) {
vcpuA = vcpu;
vcpuB = target_vcpu;
} else {
vcpuA = target_vcpu;
vcpuB = vcpu;
}
raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock);
raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock,
SINGLE_DEPTH_NESTING);
raw_spin_lock(&irq->irq_lock);
/*
* If the affinity has been preserved, move the
* interrupt around. Otherwise, it means things have
* changed while the interrupt was unlocked, and we
* need to replay this.
*
* In all cases, we cannot trust the list not to have
* changed, so we restart from the beginning.
*/
if (target_vcpu == vgic_target_oracle(irq)) {
struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu;
list_del(&irq->ap_list);
irq->vcpu = target_vcpu;
list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
target_vcpu_needs_kick = true;
}
raw_spin_unlock(&irq->irq_lock);
raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock);
if (target_vcpu_needs_kick) {
kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu);
kvm_vcpu_kick(target_vcpu);
}
goto retry;
}
raw_spin_unlock(&vgic_cpu->ap_list_lock);
}
static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_fold_lr_state(vcpu);
else
vgic_v3_fold_lr_state(vcpu);
}
/* Requires the irq_lock to be held. */
static inline void vgic_populate_lr(struct kvm_vcpu *vcpu,
struct vgic_irq *irq, int lr)
{
lockdep_assert_held(&irq->irq_lock);
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_populate_lr(vcpu, irq, lr);
else
vgic_v3_populate_lr(vcpu, irq, lr);
}
static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_clear_lr(vcpu, lr);
else
vgic_v3_clear_lr(vcpu, lr);
}
static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_set_underflow(vcpu);
else
vgic_v3_set_underflow(vcpu);
}
/* Requires the ap_list_lock to be held. */
static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
bool *multi_sgi)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
int count = 0;
*multi_sgi = false;
lockdep_assert_held(&vgic_cpu->ap_list_lock); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
int w;
raw_spin_lock(&irq->irq_lock);
/* GICv2 SGIs can count for more than one... */
w = vgic_irq_get_lr_count(irq);
raw_spin_unlock(&irq->irq_lock);
count += w;
*multi_sgi |= (w > 1);
}
return count;
}
/* Requires the VCPU's ap_list_lock to be held. */
static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
int count;
bool multi_sgi;
u8 prio = 0xff;
int i = 0;
lockdep_assert_held(&vgic_cpu->ap_list_lock); count = compute_ap_list_depth(vcpu, &multi_sgi); if (count > kvm_vgic_global_state.nr_lr || multi_sgi) vgic_sort_ap_list(vcpu);
count = 0;
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
raw_spin_lock(&irq->irq_lock);
/*
* If we have multi-SGIs in the pipeline, we need to
* guarantee that they are all seen before any IRQ of
* lower priority. In that case, we need to filter out
* these interrupts by exiting early. This is easy as
* the AP list has been sorted already.
*/
if (multi_sgi && irq->priority > prio) { _raw_spin_unlock(&irq->irq_lock);
break;
}
if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); if (irq->source) prio = irq->priority;
}
raw_spin_unlock(&irq->irq_lock);
if (count == kvm_vgic_global_state.nr_lr) { if (!list_is_last(&irq->ap_list,
&vgic_cpu->ap_list_head))
vgic_set_underflow(vcpu);
break;
}
}
/* Nuke remaining LRs */
for (i = count ; i < kvm_vgic_global_state.nr_lr; i++) vgic_clear_lr(vcpu, i);
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vcpu->arch.vgic_cpu.vgic_v2.used_lrs = count;
else
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = count;
}
static inline bool can_access_vgic_from_kernel(void)
{
/*
* GICv2 can always be accessed from the kernel because it is
* memory-mapped, and VHE systems can access GICv3 EL2 system
* registers.
*/
return !static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) || has_vhe();
}
static inline void vgic_save_state(struct kvm_vcpu *vcpu)
{
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_save_state(vcpu);
else
__vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
}
/* Sync back the hardware VGIC state into our emulation after a guest's run. */
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
int used_lrs;
/* If nesting, emulate the HW effect from L0 to L1 */
if (vgic_state_is_nested(vcpu)) {
vgic_v3_sync_nested(vcpu);
return;
}
if (vcpu_has_nv(vcpu)) vgic_v3_nested_update_mi(vcpu);
/* An empty ap_list_head implies used_lrs == 0 */
if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
return;
if (can_access_vgic_from_kernel()) vgic_save_state(vcpu); if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs;
else
used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
if (used_lrs) vgic_fold_lr_state(vcpu); vgic_prune_ap_list(vcpu);
}
static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
{
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_restore_state(vcpu);
else
__vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
}
/* Flush our emulation state into the GIC hardware before entering the guest. */
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
/*
* If in a nested state, we must return early. Two possibilities:
*
* - If we have any pending IRQ for the guest and the guest
* expects IRQs to be handled in its virtual EL2 mode (the
* virtual IMO bit is set) and it is not already running in
* virtual EL2 mode, then we have to emulate an IRQ
* exception to virtual EL2.
*
* We do that by placing a request to ourselves which will
* abort the entry procedure and inject the exception at the
* beginning of the run loop.
*
* - Otherwise, do exactly *NOTHING*. The guest state is
* already loaded, and we can carry on with running it.
*
* If we have NV, but are not in a nested state, compute the
* maintenance interrupt state, as it may fire.
*/
if (vgic_state_is_nested(vcpu)) {
if (kvm_vgic_vcpu_pending_irq(vcpu)) kvm_make_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu);
return;
}
if (vcpu_has_nv(vcpu)) vgic_v3_nested_update_mi(vcpu);
/*
* If there are no virtual interrupts active or pending for this
* VCPU, then there is no work to do and we can bail out without
* taking any lock. There is a potential race with someone injecting
* interrupts to the VCPU, but it is a benign race as the VCPU will
* either observe the new interrupt before or after doing this check,
* and introducing additional synchronization mechanism doesn't change
* this.
*
* Note that we still need to go through the whole thing if anything
* can be directly injected (GICv4).
*/
if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) &&
!vgic_supports_direct_msis(vcpu->kvm))
return;
DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
vgic_flush_lr_state(vcpu);
raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
}
if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); if (vgic_supports_direct_msis(vcpu->kvm)) vgic_v4_commit(vcpu);
}
void kvm_vgic_load(struct kvm_vcpu *vcpu)
{ if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
return;
}
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_load(vcpu);
else
vgic_v3_load(vcpu);
}
void kvm_vgic_put(struct kvm_vcpu *vcpu)
{ if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
return;
}
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_put(vcpu);
else
vgic_v3_put(vcpu);
}
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
bool pending = false;
unsigned long flags;
struct vgic_vmcr vmcr;
if (!vcpu->kvm->arch.vgic.enabled)
return false;
if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last)
return true;
vgic_get_vmcr(vcpu, &vmcr);
raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
raw_spin_lock(&irq->irq_lock);
pending = irq_is_pending(irq) && irq->enabled && !irq->active &&
irq->priority < vmcr.pmr;
raw_spin_unlock(&irq->irq_lock);
if (pending)
break;
}
raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
return pending;
}
void vgic_kick_vcpus(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
unsigned long c;
/*
* We've injected an interrupt, time to find out who deserves
* a good kick...
*/
kvm_for_each_vcpu(c, vcpu, kvm) { if (kvm_vgic_vcpu_pending_irq(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
}
}
}
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid)
{
struct vgic_irq *irq;
bool map_is_active;
unsigned long flags;
if (!vgic_initialized(vcpu->kvm))
return false;
irq = vgic_get_vcpu_irq(vcpu, vintid);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
map_is_active = irq->hw && irq->active;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return map_is_active;
}
/*
* Level-triggered mapped IRQs are special because we only observe rising
* edges as input to the VGIC.
*
* If the guest never acked the interrupt we have to sample the physical
* line and set the line level, because the device state could have changed
* or we simply need to process the still pending interrupt later.
*
* We could also have entered the guest with the interrupt active+pending.
* On the next exit, we need to re-evaluate the pending state, as it could
* otherwise result in a spurious interrupt by injecting a now potentially
* stale pending state.
*
* If this causes us to lower the level, we have to also clear the physical
* active state, since we will otherwise never be told when the interrupt
* becomes asserted again.
*
* Another case is when the interrupt requires a helping hand on
* deactivation (no HW deactivation, for example).
*/
void vgic_irq_handle_resampling(struct vgic_irq *irq,
bool lr_deactivated, bool lr_pending)
{ if (vgic_irq_is_mapped_level(irq)) {
bool resample = false;
if (unlikely(vgic_irq_needs_resampling(irq))) { resample = !(irq->active || irq->pending_latch); } else if (lr_pending || (lr_deactivated && irq->line_level)) { irq->line_level = vgic_get_phys_line_level(irq);
resample = !irq->line_level;
}
if (resample) vgic_irq_set_phys_active(irq, false);
}
}
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/syscalls.h>
#include <linux/time_namespace.h>
#include "futex.h"
/*
* Support for robust futexes: the kernel cleans up held futexes at
* thread exit time.
*
* Implementation: user-space maintains a per-thread list of locks it
* is holding. Upon do_exit(), the kernel carefully walks this list,
* and marks all locks that are owned by this thread with the
* FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is
* always manipulated with the lock held, so the list is private and
* per-thread. Userspace also maintains a per-thread 'list_op_pending'
* field, to allow the kernel to clean up if the thread dies after
* acquiring the lock, but just before it could have added itself to
* the list. There can only be one such pending lock.
*/
/**
* sys_set_robust_list() - Set the robust-futex list head of a task
* @head: pointer to the list-head
* @len: length of the list-head, as userspace expects
*/
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
size_t, len)
{
/*
* The kernel knows only one size for now:
*/
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->robust_list = head;
return 0;
}
/**
* sys_get_robust_list() - Get the robust-futex list head of a task
* @pid: pid of the process [zero for current task]
* @head_ptr: pointer to a list-head pointer, the kernel fills it in
* @len_ptr: pointer to a length field, the kernel fills in the header size
*/
SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head __user * __user *, head_ptr,
size_t __user *, len_ptr)
{
struct robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(head, head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
unsigned int flags = futex_to_flags(op);
int cmd = op & FUTEX_CMD_MASK;
if (flags & FLAGS_CLOCKRT) {
if (cmd != FUTEX_WAIT_BITSET &&
cmd != FUTEX_WAIT_REQUEUE_PI &&
cmd != FUTEX_LOCK_PI2)
return -ENOSYS;
}
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAIT_BITSET:
return futex_wait(uaddr, flags, val, timeout, val3);
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAKE_BITSET:
return futex_wake(uaddr, flags, val, val3);
case FUTEX_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0);
case FUTEX_WAKE_OP:
return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
case FUTEX_LOCK_PI:
flags |= FLAGS_CLOCKRT;
fallthrough;
case FUTEX_LOCK_PI2:
return futex_lock_pi(uaddr, flags, timeout, 0);
case FUTEX_UNLOCK_PI:
return futex_unlock_pi(uaddr, flags);
case FUTEX_TRYLOCK_PI:
return futex_lock_pi(uaddr, flags, NULL, 1);
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
uaddr2);
case FUTEX_CMP_REQUEUE_PI:
return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1);
}
return -ENOSYS;
}
static __always_inline bool futex_cmd_has_timeout(u32 cmd)
{
switch (cmd) {
case FUTEX_WAIT:
case FUTEX_LOCK_PI:
case FUTEX_LOCK_PI2:
case FUTEX_WAIT_BITSET:
case FUTEX_WAIT_REQUEUE_PI:
return true;
}
return false;
}
static __always_inline int
futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t)
{
if (!timespec64_valid(ts))
return -EINVAL;
*t = timespec64_to_ktime(*ts);
if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t);
return 0;
}
SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
const struct __kernel_timespec __user *, utime,
u32 __user *, uaddr2, u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
return -EFAULT;
if (get_timespec64(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
/**
* futex_parse_waitv - Parse a waitv array from userspace
* @futexv: Kernel side list of waiters to be filled
* @uwaitv: Userspace list to be parsed
* @nr_futexes: Length of futexv
* @wake: Wake to call when futex is woken
* @wake_data: Data for the wake handler
*
* Return: Error code on failure, 0 on success
*/
int futex_parse_waitv(struct futex_vector *futexv,
struct futex_waitv __user *uwaitv,
unsigned int nr_futexes, futex_wake_fn *wake,
void *wake_data)
{
struct futex_waitv aux;
unsigned int i;
for (i = 0; i < nr_futexes; i++) {
unsigned int flags;
if (copy_from_user(&aux, &uwaitv[i], sizeof(aux)))
return -EFAULT;
if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved)
return -EINVAL;
flags = futex2_to_flags(aux.flags);
if (!futex_flags_valid(flags))
return -EINVAL;
if (!futex_validate_input(flags, aux.val))
return -EINVAL;
futexv[i].w.flags = flags;
futexv[i].w.val = aux.val;
futexv[i].w.uaddr = aux.uaddr;
futexv[i].q = futex_q_init;
futexv[i].q.wake = wake;
futexv[i].q.wake_data = wake_data;
}
return 0;
}
static int futex2_setup_timeout(struct __kernel_timespec __user *timeout,
clockid_t clockid, struct hrtimer_sleeper *to)
{
int flag_clkid = 0, flag_init = 0;
struct timespec64 ts;
ktime_t time;
int ret;
if (!timeout)
return 0;
if (clockid == CLOCK_REALTIME) {
flag_clkid = FLAGS_CLOCKRT;
flag_init = FUTEX_CLOCK_REALTIME;
}
if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC)
return -EINVAL;
if (get_timespec64(&ts, timeout))
return -EFAULT;
/*
* Since there's no opcode for futex_waitv, use
* FUTEX_WAIT_BITSET that uses absolute timeout as well
*/
ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time);
if (ret)
return ret;
futex_setup_timer(&time, to, flag_clkid, 0);
return 0;
}
static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to)
{
hrtimer_cancel(&to->timer);
destroy_hrtimer_on_stack(&to->timer);
}
/**
* sys_futex_waitv - Wait on a list of futexes
* @waiters: List of futexes to wait on
* @nr_futexes: Length of futexv
* @flags: Flag for timeout (monotonic/realtime)
* @timeout: Optional absolute timeout.
* @clockid: Clock to be used for the timeout, realtime or monotonic.
*
* Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes
* if a futex_wake() is performed at any uaddr. The syscall returns immediately
* if any waiter has *uaddr != val. *timeout is an optional timeout value for
* the operation. Each waiter has individual flags. The `flags` argument for
* the syscall should be used solely for specifying the timeout as realtime, if
* needed. Flags for private futexes, sizes, etc. should be used on the
* individual flags of each waiter.
*
* Returns the array index of one of the woken futexes. No further information
* is provided: any number of other futexes may also have been woken by the
* same event, and if more than one futex was woken, the retrned index may
* refer to any one of them. (It is not necessaryily the futex with the
* smallest index, nor the one most recently woken, nor...)
*/
SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
unsigned int, nr_futexes, unsigned int, flags,
struct __kernel_timespec __user *, timeout, clockid_t, clockid)
{
struct hrtimer_sleeper to;
struct futex_vector *futexv;
int ret;
/* This syscall supports no flags for now */
if (flags)
return -EINVAL;
if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
return -EINVAL;
if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
return ret;
futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
if (!futexv) {
ret = -ENOMEM;
goto destroy_timer;
}
ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark,
NULL);
if (!ret)
ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
kfree(futexv);
destroy_timer:
if (timeout)
futex2_destroy_timeout(&to);
return ret;
}
/*
* sys_futex_wake - Wake a number of futexes
* @uaddr: Address of the futex(es) to wake
* @mask: bitmask
* @nr: Number of the futexes to wake
* @flags: FUTEX2 flags
*
* Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
* futex2 family of calls.
*/
SYSCALL_DEFINE4(futex_wake,
void __user *, uaddr,
unsigned long, mask,
int, nr,
unsigned int, flags)
{
if (flags & ~FUTEX2_VALID_MASK)
return -EINVAL;
flags = futex2_to_flags(flags);
if (!futex_flags_valid(flags))
return -EINVAL;
if (!futex_validate_input(flags, mask))
return -EINVAL;
return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask);
}
/*
* sys_futex_wait - Wait on a futex
* @uaddr: Address of the futex to wait on
* @val: Value of @uaddr
* @mask: bitmask
* @flags: FUTEX2 flags
* @timeout: Optional absolute timeout
* @clockid: Clock to be used for the timeout, realtime or monotonic
*
* Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the
* futex2 familiy of calls.
*/
SYSCALL_DEFINE6(futex_wait,
void __user *, uaddr,
unsigned long, val,
unsigned long, mask,
unsigned int, flags,
struct __kernel_timespec __user *, timeout,
clockid_t, clockid)
{
struct hrtimer_sleeper to;
int ret;
if (flags & ~FUTEX2_VALID_MASK)
return -EINVAL;
flags = futex2_to_flags(flags);
if (!futex_flags_valid(flags))
return -EINVAL;
if (!futex_validate_input(flags, val) ||
!futex_validate_input(flags, mask))
return -EINVAL;
if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
return ret;
ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask);
if (timeout)
futex2_destroy_timeout(&to);
return ret;
}
/*
* sys_futex_requeue - Requeue a waiter from one futex to another
* @waiters: array describing the source and destination futex
* @flags: unused
* @nr_wake: number of futexes to wake
* @nr_requeue: number of futexes to requeue
*
* Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the
* futex2 family of calls.
*/
SYSCALL_DEFINE4(futex_requeue,
struct futex_waitv __user *, waiters,
unsigned int, flags,
int, nr_wake,
int, nr_requeue)
{
struct futex_vector futexes[2];
u32 cmpval;
int ret;
if (flags)
return -EINVAL;
if (!waiters)
return -EINVAL;
ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL);
if (ret)
return ret;
cmpval = futexes[0].w.val;
return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags,
nr_wake, nr_requeue, &cmpval, 0);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(set_robust_list,
struct compat_robust_list_head __user *, head,
compat_size_t, len)
{
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->compat_robust_list = head;
return 0;
}
COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
compat_uptr_t __user *, head_ptr,
compat_size_t __user *, len_ptr)
{
struct compat_robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->compat_robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(ptr_to_compat(head), head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) {
if (get_old_timespec32(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
#endif /* CONFIG_COMPAT_32BIT_TIME */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/lib/vsprintf.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */
/*
* Wirzenius wrote this portably, Torvalds fucked it up :-)
*/
/*
* Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com>
* - changed to provide snprintf and vsnprintf functions
* So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de>
* - scnprintf and vscnprintf
*/
#include <linux/stdarg.h>
#include <linux/build_bug.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/errname.h>
#include <linux/module.h> /* for KSYM_SYMBOL_LEN */
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/kernel.h>
#include <linux/kallsyms.h>
#include <linux/math64.h>
#include <linux/uaccess.h>
#include <linux/ioport.h>
#include <linux/dcache.h>
#include <linux/cred.h>
#include <linux/rtc.h>
#include <linux/sprintf.h>
#include <linux/time.h>
#include <linux/uuid.h>
#include <linux/of.h>
#include <net/addrconf.h>
#include <linux/siphash.h>
#include <linux/compiler.h>
#include <linux/property.h>
#include <linux/notifier.h>
#ifdef CONFIG_BLOCK
#include <linux/blkdev.h>
#endif
#include "../mm/internal.h" /* For the trace_print_flags arrays */
#include <asm/page.h> /* for PAGE_SIZE */
#include <asm/byteorder.h> /* cpu_to_le16 */
#include <linux/unaligned.h>
#include <linux/string_helpers.h>
#include "kstrtox.h"
/* Disable pointer hashing if requested */
bool no_hash_pointers __ro_after_init;
EXPORT_SYMBOL_GPL(no_hash_pointers);
noinline
static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars)
{
const char *cp;
unsigned long long result = 0ULL;
size_t prefix_chars;
unsigned int rv;
cp = _parse_integer_fixup_radix(startp, &base);
prefix_chars = cp - startp;
if (prefix_chars < max_chars) {
rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars);
/* FIXME */
cp += (rv & ~KSTRTOX_OVERFLOW);
} else {
/* Field too short for prefix + digit, skip over without converting */
cp = startp + max_chars;
}
if (endp)
*endp = (char *)cp;
return result;
}
/**
* simple_strtoull - convert a string to an unsigned long long
* @cp: The start of the string
* @endp: A pointer to the end of the parsed string will be placed here
* @base: The number base to use
*
* This function has caveats. Please use kstrtoull instead.
*/
noinline
unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
{
return simple_strntoull(cp, endp, base, INT_MAX);
}
EXPORT_SYMBOL(simple_strtoull);
/**
* simple_strtoul - convert a string to an unsigned long
* @cp: The start of the string
* @endp: A pointer to the end of the parsed string will be placed here
* @base: The number base to use
*
* This function has caveats. Please use kstrtoul instead.
*/
unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base)
{
return simple_strtoull(cp, endp, base);
}
EXPORT_SYMBOL(simple_strtoul);
unsigned long simple_strntoul(const char *cp, char **endp, unsigned int base,
size_t max_chars)
{
return simple_strntoull(cp, endp, base, max_chars);
}
EXPORT_SYMBOL(simple_strntoul);
/**
* simple_strtol - convert a string to a signed long
* @cp: The start of the string
* @endp: A pointer to the end of the parsed string will be placed here
* @base: The number base to use
*
* This function has caveats. Please use kstrtol instead.
*/
long simple_strtol(const char *cp, char **endp, unsigned int base)
{
if (*cp == '-')
return -simple_strtoul(cp + 1, endp, base);
return simple_strtoul(cp, endp, base);
}
EXPORT_SYMBOL(simple_strtol);
noinline
static long long simple_strntoll(const char *cp, char **endp, unsigned int base, size_t max_chars)
{
/*
* simple_strntoull() safely handles receiving max_chars==0 in the
* case cp[0] == '-' && max_chars == 1.
* If max_chars == 0 we can drop through and pass it to simple_strntoull()
* and the content of *cp is irrelevant.
*/
if (*cp == '-' && max_chars > 0)
return -simple_strntoull(cp + 1, endp, base, max_chars - 1);
return simple_strntoull(cp, endp, base, max_chars);
}
/**
* simple_strtoll - convert a string to a signed long long
* @cp: The start of the string
* @endp: A pointer to the end of the parsed string will be placed here
* @base: The number base to use
*
* This function has caveats. Please use kstrtoll instead.
*/
long long simple_strtoll(const char *cp, char **endp, unsigned int base)
{
return simple_strntoll(cp, endp, base, INT_MAX);
}
EXPORT_SYMBOL(simple_strtoll);
static inline int skip_atoi(const char **s)
{
int i = 0;
do {
i = i*10 + *((*s)++) - '0';
} while (isdigit(**s));
return i;
}
/*
* Decimal conversion is by far the most typical, and is used for
* /proc and /sys data. This directly impacts e.g. top performance
* with many processes running. We optimize it for speed by emitting
* two characters at a time, using a 200 byte lookup table. This
* roughly halves the number of multiplications compared to computing
* the digits one at a time. Implementation strongly inspired by the
* previous version, which in turn used ideas described at
* <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission
* from the author, Douglas W. Jones).
*
* It turns out there is precisely one 26 bit fixed-point
* approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32
* holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual
* range happens to be somewhat larger (x <= 1073741898), but that's
* irrelevant for our purpose.
*
* For dividing a number in the range [10^4, 10^6-1] by 100, we still
* need a 32x32->64 bit multiply, so we simply use the same constant.
*
* For dividing a number in the range [100, 10^4-1] by 100, there are
* several options. The simplest is (x * 0x147b) >> 19, which is valid
* for all x <= 43698.
*/
static const u16 decpair[100] = {
#define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030)
_( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9),
_(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19),
_(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29),
_(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39),
_(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49),
_(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59),
_(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69),
_(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79),
_(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89),
_(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99),
#undef _
};
/*
* This will print a single '0' even if r == 0, since we would
* immediately jump to out_r where two 0s would be written but only
* one of them accounted for in buf. This is needed by ip4_string
* below. All other callers pass a non-zero value of r.
*/
static noinline_for_stack
char *put_dec_trunc8(char *buf, unsigned r)
{
unsigned q;
/* 1 <= r < 10^8 */
if (r < 100)
goto out_r;
/* 100 <= r < 10^8 */
q = (r * (u64)0x28f5c29) >> 32;
*((u16 *)buf) = decpair[r - 100*q];
buf += 2;
/* 1 <= q < 10^6 */
if (q < 100)
goto out_q;
/* 100 <= q < 10^6 */
r = (q * (u64)0x28f5c29) >> 32;
*((u16 *)buf) = decpair[q - 100*r];
buf += 2;
/* 1 <= r < 10^4 */
if (r < 100)
goto out_r;
/* 100 <= r < 10^4 */
q = (r * 0x147b) >> 19;
*((u16 *)buf) = decpair[r - 100*q];
buf += 2;
out_q:
/* 1 <= q < 100 */
r = q;
out_r:
/* 1 <= r < 100 */
*((u16 *)buf) = decpair[r];
buf += r < 10 ? 1 : 2;
return buf;
}
#if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64
static noinline_for_stack
char *put_dec_full8(char *buf, unsigned r)
{
unsigned q;
/* 0 <= r < 10^8 */
q = (r * (u64)0x28f5c29) >> 32;
*((u16 *)buf) = decpair[r - 100*q];
buf += 2;
/* 0 <= q < 10^6 */
r = (q * (u64)0x28f5c29) >> 32;
*((u16 *)buf) = decpair[q - 100*r];
buf += 2;
/* 0 <= r < 10^4 */
q = (r * 0x147b) >> 19;
*((u16 *)buf) = decpair[r - 100*q];
buf += 2;
/* 0 <= q < 100 */
*((u16 *)buf) = decpair[q];
buf += 2;
return buf;
}
static noinline_for_stack
char *put_dec(char *buf, unsigned long long n)
{ if (n >= 100*1000*1000)
buf = put_dec_full8(buf, do_div(n, 100*1000*1000));
/* 1 <= n <= 1.6e11 */
if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000));
/* 1 <= n < 1e8 */
return put_dec_trunc8(buf, n);
}
#elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64
static void
put_dec_full4(char *buf, unsigned r)
{
unsigned q;
/* 0 <= r < 10^4 */
q = (r * 0x147b) >> 19;
*((u16 *)buf) = decpair[r - 100*q];
buf += 2;
/* 0 <= q < 100 */
*((u16 *)buf) = decpair[q];
}
/*
* Call put_dec_full4 on x % 10000, return x / 10000.
* The approximation x/10000 == (x * 0x346DC5D7) >> 43
* holds for all x < 1,128,869,999. The largest value this
* helper will ever be asked to convert is 1,125,520,955.
* (second call in the put_dec code, assuming n is all-ones).
*/
static noinline_for_stack
unsigned put_dec_helper4(char *buf, unsigned x)
{
uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43;
put_dec_full4(buf, x - q * 10000);
return q;
}
/* Based on code by Douglas W. Jones found at
* <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour>
* (with permission from the author).
* Performs no 64-bit division and hence should be fast on 32-bit machines.
*/
static
char *put_dec(char *buf, unsigned long long n)
{
uint32_t d3, d2, d1, q, h;
if (n < 100*1000*1000)
return put_dec_trunc8(buf, n);
d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */
h = (n >> 32);
d2 = (h ) & 0xffff;
d3 = (h >> 16); /* implicit "& 0xffff" */
/* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0
= 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */
q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff);
q = put_dec_helper4(buf, q);
q += 7671 * d3 + 9496 * d2 + 6 * d1;
q = put_dec_helper4(buf+4, q);
q += 4749 * d3 + 42 * d2;
q = put_dec_helper4(buf+8, q);
q += 281 * d3;
buf += 12;
if (q)
buf = put_dec_trunc8(buf, q);
else while (buf[-1] == '0')
--buf;
return buf;
}
#endif
/*
* Convert passed number to decimal string.
* Returns the length of string. On buffer overflow, returns 0.
*
* If speed is not important, use snprintf(). It's easy to read the code.
*/
int num_to_str(char *buf, int size, unsigned long long num, unsigned int width)
{
/* put_dec requires 2-byte alignment of the buffer. */
char tmp[sizeof(num) * 3] __aligned(2);
int idx, len;
/* put_dec() may work incorrectly for num = 0 (generate "", not "0") */
if (num <= 9) {
tmp[0] = '0' + num;
len = 1;
} else {
len = put_dec(tmp, num) - tmp;
}
if (len > size || width > size)
return 0;
if (width > len) {
width = width - len;
for (idx = 0; idx < width; idx++)
buf[idx] = ' ';
} else {
width = 0;
}
for (idx = 0; idx < len; ++idx)
buf[idx + width] = tmp[len - idx - 1];
return len + width;
}
#define SIGN 1 /* unsigned/signed */
#define LEFT 2 /* left justified */
#define PLUS 4 /* show plus */
#define SPACE 8 /* space if plus */
#define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */
#define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */
#define SPECIAL 64 /* prefix hex with "0x", octal with "0" */
static_assert(ZEROPAD == ('0' - ' '));
static_assert(SMALL == ('a' ^ 'A'));
enum format_state {
FORMAT_STATE_NONE, /* Just a string part */
FORMAT_STATE_NUM,
FORMAT_STATE_WIDTH,
FORMAT_STATE_PRECISION,
FORMAT_STATE_CHAR,
FORMAT_STATE_STR,
FORMAT_STATE_PTR,
FORMAT_STATE_PERCENT_CHAR,
FORMAT_STATE_INVALID,
};
struct printf_spec {
unsigned char flags; /* flags to number() */
unsigned char base; /* number base, 8, 10 or 16 only */
short precision; /* # of digits/chars */
int field_width; /* width of output field */
} __packed;
static_assert(sizeof(struct printf_spec) == 8);
#define FIELD_WIDTH_MAX ((1 << 23) - 1)
#define PRECISION_MAX ((1 << 15) - 1)
static noinline_for_stack
char *number(char *buf, char *end, unsigned long long num,
struct printf_spec spec)
{
/* put_dec requires 2-byte alignment of the buffer. */
char tmp[3 * sizeof(num)] __aligned(2);
char sign;
char locase;
int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10);
int i;
bool is_zero = num == 0LL;
int field_width = spec.field_width;
int precision = spec.precision;
/* locase = 0 or 0x20. ORing digits or letters with 'locase'
* produces same digits or (maybe lowercased) letters */
locase = (spec.flags & SMALL);
if (spec.flags & LEFT)
spec.flags &= ~ZEROPAD;
sign = 0;
if (spec.flags & SIGN) {
if ((signed long long)num < 0) {
sign = '-';
num = -(signed long long)num;
field_width--;
} else if (spec.flags & PLUS) {
sign = '+';
field_width--; } else if (spec.flags & SPACE) {
sign = ' ';
field_width--;
}
}
if (need_pfx) {
if (spec.base == 16)
field_width -= 2; else if (!is_zero)
field_width--;
}
/* generate full string in tmp[], in reverse order */
i = 0;
if (num < spec.base)
tmp[i++] = hex_asc_upper[num] | locase;
else if (spec.base != 10) { /* 8 or 16 */
int mask = spec.base - 1;
int shift = 3;
if (spec.base == 16)
shift = 4;
do {
tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase);
num >>= shift;
} while (num);
} else { /* base 10 */
i = put_dec(tmp, num) - tmp;
}
/* printing 100 using %2d gives "100", not "00" */
if (i > precision)
precision = i;
/* leading space padding */
field_width -= precision;
if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' ';
++buf;
}
}
/* sign */
if (sign) { if (buf < end) *buf = sign;
++buf;
}
/* "0x" / "0" prefix */
if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0';
++buf;
}
if (spec.base == 16) { if (buf < end) *buf = ('X' | locase);
++buf;
}
}
/* zero or space padding */
if (!(spec.flags & LEFT)) {
char c = ' ' + (spec.flags & ZEROPAD);
while (--field_width >= 0) { if (buf < end) *buf = c;
++buf;
}
}
/* hmm even more zero padding? */
while (i <= --precision) { if (buf < end) *buf = '0';
++buf;
}
/* actual digits of result */
while (--i >= 0) { if (buf < end) *buf = tmp[i];
++buf;
}
/* trailing space padding */
while (--field_width >= 0) { if (buf < end) *buf = ' ';
++buf;
}
return buf;
}
static noinline_for_stack
char *special_hex_number(char *buf, char *end, unsigned long long num, int size)
{
struct printf_spec spec;
spec.field_width = 2 + 2 * size; /* 0x + hex */
spec.flags = SPECIAL | SMALL | ZEROPAD;
spec.base = 16;
spec.precision = -1;
return number(buf, end, num, spec);
}
static void move_right(char *buf, char *end, unsigned len, unsigned spaces)
{
size_t size;
if (buf >= end) /* nowhere to put anything */
return;
size = end - buf;
if (size <= spaces) {
memset(buf, ' ', size);
return;
}
if (len) { if (len > size - spaces)
len = size - spaces;
memmove(buf + spaces, buf, len);
}
memset(buf, ' ', spaces);
}
/*
* Handle field width padding for a string.
* @buf: current buffer position
* @n: length of string
* @end: end of output buffer
* @spec: for field width and flags
* Returns: new buffer position after padding.
*/
static noinline_for_stack
char *widen_string(char *buf, int n, char *end, struct printf_spec spec)
{
unsigned spaces;
if (likely(n >= spec.field_width))
return buf;
/* we want to pad the sucker */
spaces = spec.field_width - n;
if (!(spec.flags & LEFT)) {
move_right(buf - n, end, n, spaces);
return buf + spaces;
}
while (spaces--) { if (buf < end) *buf = ' ';
++buf;
}
return buf;
}
/* Handle string from a well known address. */
static char *string_nocheck(char *buf, char *end, const char *s,
struct printf_spec spec)
{
int len = 0;
int lim = spec.precision;
while (lim--) {
char c = *s++;
if (!c)
break;
if (buf < end) *buf = c;
++buf;
++len;
}
return widen_string(buf, len, end, spec);
}
static char *err_ptr(char *buf, char *end, void *ptr,
struct printf_spec spec)
{
int err = PTR_ERR(ptr);
const char *sym = errname(err);
if (sym)
return string_nocheck(buf, end, sym, spec);
/*
* Somebody passed ERR_PTR(-1234) or some other non-existing
* Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to
* printing it as its decimal representation.
*/
spec.flags |= SIGN;
spec.base = 10;
return number(buf, end, err, spec);
}
/* Be careful: error messages must fit into the given buffer. */
static char *error_string(char *buf, char *end, const char *s,
struct printf_spec spec)
{
/*
* Hard limit to avoid a completely insane messages. It actually
* works pretty well because most error messages are in
* the many pointer format modifiers.
*/
if (spec.precision == -1)
spec.precision = 2 * sizeof(void *);
return string_nocheck(buf, end, s, spec);
}
/*
* Do not call any complex external code here. Nested printk()/vsprintf()
* might cause infinite loops. Failures might break printk() and would
* be hard to debug.
*/
static const char *check_pointer_msg(const void *ptr)
{
if (!ptr)
return "(null)";
if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr))
return "(efault)";
return NULL;
}
static int check_pointer(char **buf, char *end, const void *ptr,
struct printf_spec spec)
{
const char *err_msg;
err_msg = check_pointer_msg(ptr);
if (err_msg) {
*buf = error_string(*buf, end, err_msg, spec);
return -EFAULT;
}
return 0;
}
static noinline_for_stack
char *string(char *buf, char *end, const char *s,
struct printf_spec spec)
{ if (check_pointer(&buf, end, s, spec))
return buf;
return string_nocheck(buf, end, s, spec);
}
static char *pointer_string(char *buf, char *end,
const void *ptr,
struct printf_spec spec)
{
spec.base = 16;
spec.flags |= SMALL;
if (spec.field_width == -1) {
spec.field_width = 2 * sizeof(ptr);
spec.flags |= ZEROPAD;
}
return number(buf, end, (unsigned long int)ptr, spec);
}
/* Make pointers available for printing early in the boot sequence. */
static int debug_boot_weak_hash __ro_after_init;
static int __init debug_boot_weak_hash_enable(char *str)
{
debug_boot_weak_hash = 1;
pr_info("debug_boot_weak_hash enabled\n");
return 0;
}
early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable);
static bool filled_random_ptr_key __read_mostly;
static siphash_key_t ptr_key __read_mostly;
static int fill_ptr_key(struct notifier_block *nb, unsigned long action, void *data)
{
get_random_bytes(&ptr_key, sizeof(ptr_key));
/* Pairs with smp_rmb() before reading ptr_key. */
smp_wmb();
WRITE_ONCE(filled_random_ptr_key, true);
return NOTIFY_DONE;
}
static int __init vsprintf_init_hashval(void)
{
static struct notifier_block fill_ptr_key_nb = { .notifier_call = fill_ptr_key };
execute_with_initialized_rng(&fill_ptr_key_nb);
return 0;
}
subsys_initcall(vsprintf_init_hashval)
/* Maps a pointer to a 32 bit unique identifier. */
static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out)
{
unsigned long hashval;
if (!READ_ONCE(filled_random_ptr_key))
return -EBUSY;
/* Pairs with smp_wmb() after writing ptr_key. */
smp_rmb();
#ifdef CONFIG_64BIT
hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key);
/*
* Mask off the first 32 bits, this makes explicit that we have
* modified the address (and 32 bits is plenty for a unique ID).
*/
hashval = hashval & 0xffffffff;
#else
hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key);
#endif
*hashval_out = hashval;
return 0;
}
int ptr_to_hashval(const void *ptr, unsigned long *hashval_out)
{
return __ptr_to_hashval(ptr, hashval_out);
}
static char *ptr_to_id(char *buf, char *end, const void *ptr,
struct printf_spec spec)
{
const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)";
unsigned long hashval;
int ret;
/*
* Print the real pointer value for NULL and error pointers,
* as they are not actual addresses.
*/
if (IS_ERR_OR_NULL(ptr))
return pointer_string(buf, end, ptr, spec);
/* When debugging early boot use non-cryptographically secure hash. */
if (unlikely(debug_boot_weak_hash)) {
hashval = hash_long((unsigned long)ptr, 32);
return pointer_string(buf, end, (const void *)hashval, spec);
}
ret = __ptr_to_hashval(ptr, &hashval);
if (ret) {
spec.field_width = 2 * sizeof(ptr);
/* string length must be less than default_width */
return error_string(buf, end, str, spec);
}
return pointer_string(buf, end, (const void *)hashval, spec);
}
static char *default_pointer(char *buf, char *end, const void *ptr,
struct printf_spec spec)
{
/*
* default is to _not_ leak addresses, so hash before printing,
* unless no_hash_pointers is specified on the command line.
*/
if (unlikely(no_hash_pointers))
return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec);
}
int kptr_restrict __read_mostly;
static noinline_for_stack
char *restricted_pointer(char *buf, char *end, const void *ptr,
struct printf_spec spec)
{
switch (kptr_restrict) {
case 0:
/* Handle as %p, hash and do _not_ leak addresses. */
return default_pointer(buf, end, ptr, spec);
case 1: {
const struct cred *cred;
/*
* kptr_restrict==1 cannot be used in IRQ context
* because its test for CAP_SYSLOG would be meaningless.
*/
if (in_hardirq() || in_serving_softirq() || in_nmi()) {
if (spec.field_width == -1)
spec.field_width = 2 * sizeof(ptr);
return error_string(buf, end, "pK-error", spec);
}
/*
* Only print the real pointer value if the current
* process has CAP_SYSLOG and is running with the
* same credentials it started with. This is because
* access to files is checked at open() time, but %pK
* checks permission at read() time. We don't want to
* leak pointer values if a binary opens a file using
* %pK and then elevates privileges before reading it.
*/
cred = current_cred();
if (!has_capability_noaudit(current, CAP_SYSLOG) ||
!uid_eq(cred->euid, cred->uid) ||
!gid_eq(cred->egid, cred->gid))
ptr = NULL;
break;
}
case 2:
default:
/* Always print 0's for %pK */
ptr = NULL;
break;
}
return pointer_string(buf, end, ptr, spec);
}
static noinline_for_stack
char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec,
const char *fmt)
{
const char *array[4], *s;
const struct dentry *p;
int depth;
int i, n;
switch (fmt[1]) {
case '2': case '3': case '4':
depth = fmt[1] - '0';
break;
default:
depth = 1;
}
rcu_read_lock();
for (i = 0; i < depth; i++, d = p) {
if (check_pointer(&buf, end, d, spec)) {
rcu_read_unlock();
return buf;
}
p = READ_ONCE(d->d_parent);
array[i] = READ_ONCE(d->d_name.name);
if (p == d) {
if (i)
array[i] = "";
i++;
break;
}
}
s = array[--i];
for (n = 0; n != spec.precision; n++, buf++) {
char c = *s++;
if (!c) {
if (!i)
break;
c = '/';
s = array[--i];
}
if (buf < end)
*buf = c;
}
rcu_read_unlock();
return widen_string(buf, n, end, spec);
}
static noinline_for_stack
char *file_dentry_name(char *buf, char *end, const struct file *f,
struct printf_spec spec, const char *fmt)
{
if (check_pointer(&buf, end, f, spec))
return buf;
return dentry_name(buf, end, f->f_path.dentry, spec, fmt);
}
#ifdef CONFIG_BLOCK
static noinline_for_stack
char *bdev_name(char *buf, char *end, struct block_device *bdev,
struct printf_spec spec, const char *fmt)
{
struct gendisk *hd;
if (check_pointer(&buf, end, bdev, spec))
return buf;
hd = bdev->bd_disk;
buf = string(buf, end, hd->disk_name, spec);
if (bdev_is_partition(bdev)) {
if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) {
if (buf < end)
*buf = 'p';
buf++;
}
buf = number(buf, end, bdev_partno(bdev), spec);
}
return buf;
}
#endif
static noinline_for_stack
char *symbol_string(char *buf, char *end, void *ptr,
struct printf_spec spec, const char *fmt)
{
unsigned long value;
#ifdef CONFIG_KALLSYMS
char sym[KSYM_SYMBOL_LEN];
#endif
if (fmt[1] == 'R')
ptr = __builtin_extract_return_addr(ptr);
value = (unsigned long)ptr;
#ifdef CONFIG_KALLSYMS
if (*fmt == 'B' && fmt[1] == 'b')
sprint_backtrace_build_id(sym, value);
else if (*fmt == 'B')
sprint_backtrace(sym, value);
else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b')))
sprint_symbol_build_id(sym, value);
else if (*fmt != 's')
sprint_symbol(sym, value);
else
sprint_symbol_no_offset(sym, value);
return string_nocheck(buf, end, sym, spec);
#else
return special_hex_number(buf, end, value, sizeof(void *));
#endif
}
static const struct printf_spec default_str_spec = {
.field_width = -1,
.precision = -1,
};
static const struct printf_spec default_flag_spec = {
.base = 16,
.precision = -1,
.flags = SPECIAL | SMALL,
};
static const struct printf_spec default_dec_spec = {
.base = 10,
.precision = -1,
};
static const struct printf_spec default_dec02_spec = {
.base = 10,
.field_width = 2,
.precision = -1,
.flags = ZEROPAD,
};
static const struct printf_spec default_dec04_spec = {
.base = 10,
.field_width = 4,
.precision = -1,
.flags = ZEROPAD,
};
static noinline_for_stack
char *hex_range(char *buf, char *end, u64 start_val, u64 end_val,
struct printf_spec spec)
{
buf = number(buf, end, start_val, spec);
if (start_val == end_val)
return buf;
if (buf < end)
*buf = '-';
++buf;
return number(buf, end, end_val, spec);
}
static noinline_for_stack
char *resource_string(char *buf, char *end, struct resource *res,
struct printf_spec spec, const char *fmt)
{
#ifndef IO_RSRC_PRINTK_SIZE
#define IO_RSRC_PRINTK_SIZE 6
#endif
#ifndef MEM_RSRC_PRINTK_SIZE
#define MEM_RSRC_PRINTK_SIZE 10
#endif
static const struct printf_spec io_spec = {
.base = 16,
.field_width = IO_RSRC_PRINTK_SIZE,
.precision = -1,
.flags = SPECIAL | SMALL | ZEROPAD,
};
static const struct printf_spec mem_spec = {
.base = 16,
.field_width = MEM_RSRC_PRINTK_SIZE,
.precision = -1,
.flags = SPECIAL | SMALL | ZEROPAD,
};
static const struct printf_spec bus_spec = {
.base = 16,
.field_width = 2,
.precision = -1,
.flags = SMALL | ZEROPAD,
};
static const struct printf_spec str_spec = {
.field_width = -1,
.precision = 10,
.flags = LEFT,
};
/* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8)
* 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */
#define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4)
#define FLAG_BUF_SIZE (2 * sizeof(res->flags))
#define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]")
#define RAW_BUF_SIZE sizeof("[mem - flags 0x]")
char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE,
2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)];
char *p = sym, *pend = sym + sizeof(sym);
int decode = (fmt[0] == 'R') ? 1 : 0;
const struct printf_spec *specp;
if (check_pointer(&buf, end, res, spec))
return buf;
*p++ = '[';
if (res->flags & IORESOURCE_IO) {
p = string_nocheck(p, pend, "io ", str_spec);
specp = &io_spec;
} else if (res->flags & IORESOURCE_MEM) {
p = string_nocheck(p, pend, "mem ", str_spec);
specp = &mem_spec;
} else if (res->flags & IORESOURCE_IRQ) {
p = string_nocheck(p, pend, "irq ", str_spec);
specp = &default_dec_spec;
} else if (res->flags & IORESOURCE_DMA) {
p = string_nocheck(p, pend, "dma ", str_spec);
specp = &default_dec_spec;
} else if (res->flags & IORESOURCE_BUS) {
p = string_nocheck(p, pend, "bus ", str_spec);
specp = &bus_spec;
} else {
p = string_nocheck(p, pend, "??? ", str_spec);
specp = &mem_spec;
decode = 0;
}
if (decode && res->flags & IORESOURCE_UNSET) {
p = string_nocheck(p, pend, "size ", str_spec);
p = number(p, pend, resource_size(res), *specp);
} else {
p = hex_range(p, pend, res->start, res->end, *specp);
}
if (decode) {
if (res->flags & IORESOURCE_MEM_64)
p = string_nocheck(p, pend, " 64bit", str_spec);
if (res->flags & IORESOURCE_PREFETCH)
p = string_nocheck(p, pend, " pref", str_spec);
if (res->flags & IORESOURCE_WINDOW)
p = string_nocheck(p, pend, " window", str_spec);
if (res->flags & IORESOURCE_DISABLED)
p = string_nocheck(p, pend, " disabled", str_spec);
} else {
p = string_nocheck(p, pend, " flags ", str_spec);
p = number(p, pend, res->flags, default_flag_spec);
}
*p++ = ']';
*p = '\0';
return string_nocheck(buf, end, sym, spec);
}
static noinline_for_stack
char *range_string(char *buf, char *end, const struct range *range,
struct printf_spec spec, const char *fmt)
{
char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")];
char *p = sym, *pend = sym + sizeof(sym);
struct printf_spec range_spec = {
.field_width = 2 + 2 * sizeof(range->start), /* 0x + 2 * 8 */
.flags = SPECIAL | SMALL | ZEROPAD,
.base = 16,
.precision = -1,
};
if (check_pointer(&buf, end, range, spec))
return buf;
p = string_nocheck(p, pend, "[range ", default_str_spec);
p = hex_range(p, pend, range->start, range->end, range_spec);
*p++ = ']';
*p = '\0';
return string_nocheck(buf, end, sym, spec);
}
static noinline_for_stack
char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
const char *fmt)
{
int i, len = 1; /* if we pass '%ph[CDN]', field width remains
negative value, fallback to the default */
char separator;
if (spec.field_width == 0)
/* nothing to print */
return buf;
if (check_pointer(&buf, end, addr, spec))
return buf;
switch (fmt[1]) {
case 'C':
separator = ':';
break;
case 'D':
separator = '-';
break;
case 'N':
separator = 0;
break;
default:
separator = ' ';
break;
}
if (spec.field_width > 0)
len = min_t(int, spec.field_width, 64);
for (i = 0; i < len; ++i) {
if (buf < end)
*buf = hex_asc_hi(addr[i]);
++buf;
if (buf < end)
*buf = hex_asc_lo(addr[i]);
++buf;
if (separator && i != len - 1) {
if (buf < end)
*buf = separator;
++buf;
}
}
return buf;
}
static noinline_for_stack
char *bitmap_string(char *buf, char *end, const unsigned long *bitmap,
struct printf_spec spec, const char *fmt)
{
const int CHUNKSZ = 32;
int nr_bits = max_t(int, spec.field_width, 0);
int i, chunksz;
bool first = true;
if (check_pointer(&buf, end, bitmap, spec))
return buf;
/* reused to print numbers */
spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 };
chunksz = nr_bits & (CHUNKSZ - 1);
if (chunksz == 0)
chunksz = CHUNKSZ;
i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ;
for (; i >= 0; i -= CHUNKSZ) {
u32 chunkmask, val;
int word, bit;
chunkmask = ((1ULL << chunksz) - 1);
word = i / BITS_PER_LONG;
bit = i % BITS_PER_LONG;
val = (bitmap[word] >> bit) & chunkmask;
if (!first) {
if (buf < end)
*buf = ',';
buf++;
}
first = false;
spec.field_width = DIV_ROUND_UP(chunksz, 4);
buf = number(buf, end, val, spec);
chunksz = CHUNKSZ;
}
return buf;
}
static noinline_for_stack
char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap,
struct printf_spec spec, const char *fmt)
{
int nr_bits = max_t(int, spec.field_width, 0);
bool first = true;
int rbot, rtop;
if (check_pointer(&buf, end, bitmap, spec))
return buf;
for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) {
if (!first) {
if (buf < end)
*buf = ',';
buf++;
}
first = false;
buf = number(buf, end, rbot, default_dec_spec);
if (rtop == rbot + 1)
continue;
if (buf < end)
*buf = '-';
buf = number(++buf, end, rtop - 1, default_dec_spec);
}
return buf;
}
static noinline_for_stack
char *mac_address_string(char *buf, char *end, u8 *addr,
struct printf_spec spec, const char *fmt)
{
char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")];
char *p = mac_addr;
int i;
char separator;
bool reversed = false;
if (check_pointer(&buf, end, addr, spec))
return buf;
switch (fmt[1]) {
case 'F':
separator = '-';
break;
case 'R':
reversed = true;
fallthrough;
default:
separator = ':';
break;
}
for (i = 0; i < 6; i++) {
if (reversed)
p = hex_byte_pack(p, addr[5 - i]);
else
p = hex_byte_pack(p, addr[i]);
if (fmt[0] == 'M' && i != 5)
*p++ = separator;
}
*p = '\0';
return string_nocheck(buf, end, mac_addr, spec);
}
static noinline_for_stack
char *ip4_string(char *p, const u8 *addr, const char *fmt)
{
int i;
bool leading_zeros = (fmt[0] == 'i');
int index;
int step;
switch (fmt[2]) {
case 'h':
#ifdef __BIG_ENDIAN
index = 0;
step = 1;
#else
index = 3;
step = -1;
#endif
break;
case 'l':
index = 3;
step = -1;
break;
case 'n':
case 'b':
default:
index = 0;
step = 1;
break;
}
for (i = 0; i < 4; i++) {
char temp[4] __aligned(2); /* hold each IP quad in reverse order */
int digits = put_dec_trunc8(temp, addr[index]) - temp;
if (leading_zeros) {
if (digits < 3)
*p++ = '0';
if (digits < 2)
*p++ = '0';
}
/* reverse the digits in the quad */
while (digits--)
*p++ = temp[digits];
if (i < 3)
*p++ = '.';
index += step;
}
*p = '\0';
return p;
}
static noinline_for_stack
char *ip6_compressed_string(char *p, const char *addr)
{
int i, j, range;
unsigned char zerolength[8];
int longest = 1;
int colonpos = -1;
u16 word;
u8 hi, lo;
bool needcolon = false;
bool useIPv4;
struct in6_addr in6;
memcpy(&in6, addr, sizeof(struct in6_addr));
useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6);
memset(zerolength, 0, sizeof(zerolength));
if (useIPv4)
range = 6;
else
range = 8;
/* find position of longest 0 run */
for (i = 0; i < range; i++) {
for (j = i; j < range; j++) {
if (in6.s6_addr16[j] != 0)
break;
zerolength[i]++;
}
}
for (i = 0; i < range; i++) {
if (zerolength[i] > longest) {
longest = zerolength[i];
colonpos = i;
}
}
if (longest == 1) /* don't compress a single 0 */
colonpos = -1;
/* emit address */
for (i = 0; i < range; i++) {
if (i == colonpos) {
if (needcolon || i == 0)
*p++ = ':';
*p++ = ':';
needcolon = false;
i += longest - 1;
continue;
}
if (needcolon) {
*p++ = ':';
needcolon = false;
}
/* hex u16 without leading 0s */
word = ntohs(in6.s6_addr16[i]);
hi = word >> 8;
lo = word & 0xff;
if (hi) {
if (hi > 0x0f)
p = hex_byte_pack(p, hi);
else
*p++ = hex_asc_lo(hi);
p = hex_byte_pack(p, lo);
}
else if (lo > 0x0f)
p = hex_byte_pack(p, lo);
else
*p++ = hex_asc_lo(lo);
needcolon = true;
}
if (useIPv4) {
if (needcolon)
*p++ = ':';
p = ip4_string(p, &in6.s6_addr[12], "I4");
}
*p = '\0';
return p;
}
static noinline_for_stack
char *ip6_string(char *p, const char *addr, const char *fmt)
{
int i;
for (i = 0; i < 8; i++) {
p = hex_byte_pack(p, *addr++);
p = hex_byte_pack(p, *addr++);
if (fmt[0] == 'I' && i != 7)
*p++ = ':';
}
*p = '\0';
return p;
}
static noinline_for_stack
char *ip6_addr_string(char *buf, char *end, const u8 *addr,
struct printf_spec spec, const char *fmt)
{
char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")];
if (fmt[0] == 'I' && fmt[2] == 'c')
ip6_compressed_string(ip6_addr, addr);
else
ip6_string(ip6_addr, addr, fmt);
return string_nocheck(buf, end, ip6_addr, spec);
}
static noinline_for_stack
char *ip4_addr_string(char *buf, char *end, const u8 *addr,
struct printf_spec spec, const char *fmt)
{
char ip4_addr[sizeof("255.255.255.255")];
ip4_string(ip4_addr, addr, fmt);
return string_nocheck(buf, end, ip4_addr, spec);
}
static noinline_for_stack
char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa,
struct printf_spec spec, const char *fmt)
{
bool have_p = false, have_s = false, have_f = false, have_c = false;
char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") +
sizeof(":12345") + sizeof("/123456789") +
sizeof("%1234567890")];
char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr);
const u8 *addr = (const u8 *) &sa->sin6_addr;
char fmt6[2] = { fmt[0], '6' };
u8 off = 0;
fmt++;
while (isalpha(*++fmt)) {
switch (*fmt) {
case 'p':
have_p = true;
break;
case 'f':
have_f = true;
break;
case 's':
have_s = true;
break;
case 'c':
have_c = true;
break;
}
}
if (have_p || have_s || have_f) {
*p = '[';
off = 1;
}
if (fmt6[0] == 'I' && have_c)
p = ip6_compressed_string(ip6_addr + off, addr);
else
p = ip6_string(ip6_addr + off, addr, fmt6);
if (have_p || have_s || have_f)
*p++ = ']';
if (have_p) {
*p++ = ':';
p = number(p, pend, ntohs(sa->sin6_port), spec);
}
if (have_f) {
*p++ = '/';
p = number(p, pend, ntohl(sa->sin6_flowinfo &
IPV6_FLOWINFO_MASK), spec);
}
if (have_s) {
*p++ = '%';
p = number(p, pend, sa->sin6_scope_id, spec);
}
*p = '\0';
return string_nocheck(buf, end, ip6_addr, spec);
}
static noinline_for_stack
char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa,
struct printf_spec spec, const char *fmt)
{
bool have_p = false;
char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")];
char *pend = ip4_addr + sizeof(ip4_addr);
const u8 *addr = (const u8 *) &sa->sin_addr.s_addr;
char fmt4[3] = { fmt[0], '4', 0 };
fmt++;
while (isalpha(*++fmt)) {
switch (*fmt) {
case 'p':
have_p = true;
break;
case 'h':
case 'l':
case 'n':
case 'b':
fmt4[2] = *fmt;
break;
}
}
p = ip4_string(ip4_addr, addr, fmt4);
if (have_p) {
*p++ = ':';
p = number(p, pend, ntohs(sa->sin_port), spec);
}
*p = '\0';
return string_nocheck(buf, end, ip4_addr, spec);
}
static noinline_for_stack
char *ip_addr_string(char *buf, char *end, const void *ptr,
struct printf_spec spec, const char *fmt)
{
char *err_fmt_msg;
if (check_pointer(&buf, end, ptr, spec))
return buf;
switch (fmt[1]) {
case '6':
return ip6_addr_string(buf, end, ptr, spec, fmt);
case '4':
return ip4_addr_string(buf, end, ptr, spec, fmt);
case 'S': {
const union {
struct sockaddr raw;
struct sockaddr_in v4;
struct sockaddr_in6 v6;
} *sa = ptr;
switch (sa->raw.sa_family) {
case AF_INET:
return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt);
case AF_INET6:
return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt);
default:
return error_string(buf, end, "(einval)", spec);
}}
}
err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)";
return error_string(buf, end, err_fmt_msg, spec);
}
static noinline_for_stack
char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
const char *fmt)
{
bool found = true;
int count = 1;
unsigned int flags = 0;
int len;
if (spec.field_width == 0)
return buf; /* nothing to print */
if (check_pointer(&buf, end, addr, spec))
return buf;
do {
switch (fmt[count++]) {
case 'a':
flags |= ESCAPE_ANY;
break;
case 'c':
flags |= ESCAPE_SPECIAL;
break;
case 'h':
flags |= ESCAPE_HEX;
break;
case 'n':
flags |= ESCAPE_NULL;
break;
case 'o':
flags |= ESCAPE_OCTAL;
break;
case 'p':
flags |= ESCAPE_NP;
break;
case 's':
flags |= ESCAPE_SPACE;
break;
default:
found = false;
break;
}
} while (found);
if (!flags)
flags = ESCAPE_ANY_NP;
len = spec.field_width < 0 ? 1 : spec.field_width;
/*
* string_escape_mem() writes as many characters as it can to
* the given buffer, and returns the total size of the output
* had the buffer been big enough.
*/
buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL);
return buf;
}
#pragma GCC diagnostic push
#ifndef __clang__
#pragma GCC diagnostic ignored "-Wsuggest-attribute=format"
#endif
static char *va_format(char *buf, char *end, struct va_format *va_fmt,
struct printf_spec spec)
{
va_list va;
if (check_pointer(&buf, end, va_fmt, spec))
return buf;
va_copy(va, *va_fmt->va);
buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va);
va_end(va);
return buf;
}
#pragma GCC diagnostic pop
static noinline_for_stack
char *uuid_string(char *buf, char *end, const u8 *addr,
struct printf_spec spec, const char *fmt)
{
char uuid[UUID_STRING_LEN + 1];
char *p = uuid;
int i;
const u8 *index = uuid_index;
bool uc = false;
if (check_pointer(&buf, end, addr, spec))
return buf;
switch (*(++fmt)) {
case 'L':
uc = true;
fallthrough;
case 'l':
index = guid_index;
break;
case 'B':
uc = true;
break;
}
for (i = 0; i < 16; i++) {
if (uc)
p = hex_byte_pack_upper(p, addr[index[i]]);
else
p = hex_byte_pack(p, addr[index[i]]);
switch (i) {
case 3:
case 5:
case 7:
case 9:
*p++ = '-';
break;
}
}
*p = 0;
return string_nocheck(buf, end, uuid, spec);
}
static noinline_for_stack
char *netdev_bits(char *buf, char *end, const void *addr,
struct printf_spec spec, const char *fmt)
{
unsigned long long num;
int size;
if (check_pointer(&buf, end, addr, spec))
return buf;
switch (fmt[1]) {
case 'F':
num = *(const netdev_features_t *)addr;
size = sizeof(netdev_features_t);
break;
default:
return error_string(buf, end, "(%pN?)", spec);
}
return special_hex_number(buf, end, num, size);
}
static noinline_for_stack
char *fourcc_string(char *buf, char *end, const u32 *fourcc,
struct printf_spec spec, const char *fmt)
{
char output[sizeof("0123 little-endian (0x01234567)")];
char *p = output;
unsigned int i;
u32 orig, val;
if (fmt[1] != 'c' || fmt[2] != 'c')
return error_string(buf, end, "(%p4?)", spec);
if (check_pointer(&buf, end, fourcc, spec))
return buf;
orig = get_unaligned(fourcc);
val = orig & ~BIT(31);
for (i = 0; i < sizeof(u32); i++) {
unsigned char c = val >> (i * 8);
/* Print non-control ASCII characters as-is, dot otherwise */
*p++ = isascii(c) && isprint(c) ? c : '.';
}
*p++ = ' ';
strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian");
p += strlen(p);
*p++ = ' ';
*p++ = '(';
p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32));
*p++ = ')';
*p = '\0';
return string(buf, end, output, spec);
}
static noinline_for_stack
char *address_val(char *buf, char *end, const void *addr,
struct printf_spec spec, const char *fmt)
{
unsigned long long num;
int size;
if (check_pointer(&buf, end, addr, spec))
return buf;
switch (fmt[1]) {
case 'd':
num = *(const dma_addr_t *)addr;
size = sizeof(dma_addr_t);
break;
case 'p':
default:
num = *(const phys_addr_t *)addr;
size = sizeof(phys_addr_t);
break;
}
return special_hex_number(buf, end, num, size);
}
static noinline_for_stack
char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r)
{
int year = tm->tm_year + (r ? 0 : 1900);
int mon = tm->tm_mon + (r ? 0 : 1);
buf = number(buf, end, year, default_dec04_spec);
if (buf < end)
*buf = '-';
buf++;
buf = number(buf, end, mon, default_dec02_spec);
if (buf < end)
*buf = '-';
buf++;
return number(buf, end, tm->tm_mday, default_dec02_spec);
}
static noinline_for_stack
char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r)
{
buf = number(buf, end, tm->tm_hour, default_dec02_spec);
if (buf < end)
*buf = ':';
buf++;
buf = number(buf, end, tm->tm_min, default_dec02_spec);
if (buf < end)
*buf = ':';
buf++;
return number(buf, end, tm->tm_sec, default_dec02_spec);
}
static noinline_for_stack
char *rtc_str(char *buf, char *end, const struct rtc_time *tm,
struct printf_spec spec, const char *fmt)
{
bool have_t = true, have_d = true;
bool raw = false, iso8601_separator = true;
bool found = true;
int count = 2;
if (check_pointer(&buf, end, tm, spec))
return buf;
switch (fmt[count]) {
case 'd':
have_t = false;
count++;
break;
case 't':
have_d = false;
count++;
break;
}
do {
switch (fmt[count++]) {
case 'r':
raw = true;
break;
case 's':
iso8601_separator = false;
break;
default:
found = false;
break;
}
} while (found);
if (have_d)
buf = date_str(buf, end, tm, raw);
if (have_d && have_t) {
if (buf < end)
*buf = iso8601_separator ? 'T' : ' ';
buf++;
}
if (have_t)
buf = time_str(buf, end, tm, raw);
return buf;
}
static noinline_for_stack
char *time64_str(char *buf, char *end, const time64_t time,
struct printf_spec spec, const char *fmt)
{
struct rtc_time rtc_time;
struct tm tm;
time64_to_tm(time, 0, &tm);
rtc_time.tm_sec = tm.tm_sec;
rtc_time.tm_min = tm.tm_min;
rtc_time.tm_hour = tm.tm_hour;
rtc_time.tm_mday = tm.tm_mday;
rtc_time.tm_mon = tm.tm_mon;
rtc_time.tm_year = tm.tm_year;
rtc_time.tm_wday = tm.tm_wday;
rtc_time.tm_yday = tm.tm_yday;
rtc_time.tm_isdst = 0;
return rtc_str(buf, end, &rtc_time, spec, fmt);
}
static noinline_for_stack
char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec,
const char *fmt)
{
switch (fmt[1]) {
case 'R':
return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt);
case 'T':
return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt);
default:
return error_string(buf, end, "(%pt?)", spec);
}
}
static noinline_for_stack
char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
const char *fmt)
{
if (!IS_ENABLED(CONFIG_HAVE_CLK))
return error_string(buf, end, "(%pC?)", spec);
if (check_pointer(&buf, end, clk, spec))
return buf;
switch (fmt[1]) {
case 'n':
default:
#ifdef CONFIG_COMMON_CLK
return string(buf, end, __clk_get_name(clk), spec);
#else
return ptr_to_id(buf, end, clk, spec);
#endif
}
}
static
char *format_flags(char *buf, char *end, unsigned long flags,
const struct trace_print_flags *names)
{
unsigned long mask;
for ( ; flags && names->name; names++) {
mask = names->mask;
if ((flags & mask) != mask)
continue;
buf = string(buf, end, names->name, default_str_spec);
flags &= ~mask;
if (flags) {
if (buf < end)
*buf = '|';
buf++;
}
}
if (flags)
buf = number(buf, end, flags, default_flag_spec);
return buf;
}
struct page_flags_fields {
int width;
int shift;
int mask;
const struct printf_spec *spec;
const char *name;
};
static const struct page_flags_fields pff[] = {
{SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK,
&default_dec_spec, "section"},
{NODES_WIDTH, NODES_PGSHIFT, NODES_MASK,
&default_dec_spec, "node"},
{ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK,
&default_dec_spec, "zone"},
{LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK,
&default_flag_spec, "lastcpupid"},
{KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK,
&default_flag_spec, "kasantag"},
};
static
char *format_page_flags(char *buf, char *end, unsigned long flags)
{
unsigned long main_flags = flags & PAGEFLAGS_MASK;
bool append = false;
int i;
buf = number(buf, end, flags, default_flag_spec);
if (buf < end)
*buf = '(';
buf++;
/* Page flags from the main area. */
if (main_flags) {
buf = format_flags(buf, end, main_flags, pageflag_names);
append = true;
}
/* Page flags from the fields area */
for (i = 0; i < ARRAY_SIZE(pff); i++) {
/* Skip undefined fields. */
if (!pff[i].width)
continue;
/* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */
if (append) {
if (buf < end)
*buf = '|';
buf++;
}
buf = string(buf, end, pff[i].name, default_str_spec);
if (buf < end)
*buf = '=';
buf++;
buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask,
*pff[i].spec);
append = true;
}
if (buf < end)
*buf = ')';
buf++;
return buf;
}
static noinline_for_stack
char *flags_string(char *buf, char *end, void *flags_ptr,
struct printf_spec spec, const char *fmt)
{
unsigned long flags;
const struct trace_print_flags *names;
if (check_pointer(&buf, end, flags_ptr, spec))
return buf;
switch (fmt[1]) {
case 'p':
return format_page_flags(buf, end, *(unsigned long *)flags_ptr);
case 'v':
flags = *(unsigned long *)flags_ptr;
names = vmaflag_names;
break;
case 'g':
flags = (__force unsigned long)(*(gfp_t *)flags_ptr);
names = gfpflag_names;
break;
default:
return error_string(buf, end, "(%pG?)", spec);
}
return format_flags(buf, end, flags, names);
}
static noinline_for_stack
char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf,
char *end)
{
int depth;
/* Loop starting from the root node to the current node. */
for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) {
/*
* Only get a reference for other nodes (i.e. parent nodes).
* fwnode refcount may be 0 here.
*/
struct fwnode_handle *__fwnode = depth ?
fwnode_get_nth_parent(fwnode, depth) : fwnode;
buf = string(buf, end, fwnode_get_name_prefix(__fwnode),
default_str_spec);
buf = string(buf, end, fwnode_get_name(__fwnode),
default_str_spec);
if (depth)
fwnode_handle_put(__fwnode);
}
return buf;
}
static noinline_for_stack
char *device_node_string(char *buf, char *end, struct device_node *dn,
struct printf_spec spec, const char *fmt)
{
char tbuf[sizeof("xxxx") + 1];
const char *p;
int ret;
char *buf_start = buf;
struct property *prop;
bool has_mult, pass;
struct printf_spec str_spec = spec;
str_spec.field_width = -1;
if (fmt[0] != 'F')
return error_string(buf, end, "(%pO?)", spec);
if (!IS_ENABLED(CONFIG_OF))
return error_string(buf, end, "(%pOF?)", spec);
if (check_pointer(&buf, end, dn, spec))
return buf;
/* simple case without anything any more format specifiers */
fmt++;
if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0)
fmt = "f";
for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) {
int precision;
if (pass) {
if (buf < end)
*buf = ':';
buf++;
}
switch (*fmt) {
case 'f': /* full_name */
buf = fwnode_full_name_string(of_fwnode_handle(dn), buf,
end);
break;
case 'n': /* name */
p = fwnode_get_name(of_fwnode_handle(dn));
precision = str_spec.precision;
str_spec.precision = strchrnul(p, '@') - p;
buf = string(buf, end, p, str_spec);
str_spec.precision = precision;
break;
case 'p': /* phandle */
buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec);
break;
case 'P': /* path-spec */
p = fwnode_get_name(of_fwnode_handle(dn));
if (!p[1])
p = "/";
buf = string(buf, end, p, str_spec);
break;
case 'F': /* flags */
tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-';
tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-';
tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-';
tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-';
tbuf[4] = 0;
buf = string_nocheck(buf, end, tbuf, str_spec);
break;
case 'c': /* major compatible string */
ret = of_property_read_string(dn, "compatible", &p);
if (!ret)
buf = string(buf, end, p, str_spec);
break;
case 'C': /* full compatible string */
has_mult = false;
of_property_for_each_string(dn, "compatible", prop, p) {
if (has_mult)
buf = string_nocheck(buf, end, ",", str_spec);
buf = string_nocheck(buf, end, "\"", str_spec);
buf = string(buf, end, p, str_spec);
buf = string_nocheck(buf, end, "\"", str_spec);
has_mult = true;
}
break;
default:
break;
}
}
return widen_string(buf, buf - buf_start, end, spec);
}
static noinline_for_stack
char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
struct printf_spec spec, const char *fmt)
{
struct printf_spec str_spec = spec;
char *buf_start = buf;
str_spec.field_width = -1;
if (*fmt != 'w')
return error_string(buf, end, "(%pf?)", spec);
if (check_pointer(&buf, end, fwnode, spec))
return buf;
fmt++;
switch (*fmt) {
case 'P': /* name */
buf = string(buf, end, fwnode_get_name(fwnode), str_spec);
break;
case 'f': /* full_name */
default:
buf = fwnode_full_name_string(fwnode, buf, end);
break;
}
return widen_string(buf, buf - buf_start, end, spec);
}
static noinline_for_stack
char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr,
struct printf_spec spec)
{
if (*fmt == 'r' && fmt[1] == 'a')
return range_string(buf, end, ptr, spec, fmt);
return resource_string(buf, end, ptr, spec, fmt);
}
int __init no_hash_pointers_enable(char *str)
{
if (no_hash_pointers)
return 0;
no_hash_pointers = true;
pr_warn("**********************************************************\n");
pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
pr_warn("** **\n");
pr_warn("** This system shows unhashed kernel memory addresses **\n");
pr_warn("** via the console, logs, and other interfaces. This **\n");
pr_warn("** might reduce the security of your system. **\n");
pr_warn("** **\n");
pr_warn("** If you see this message and you are not debugging **\n");
pr_warn("** the kernel, report this immediately to your system **\n");
pr_warn("** administrator! **\n");
pr_warn("** **\n");
pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
pr_warn("**********************************************************\n");
return 0;
}
early_param("no_hash_pointers", no_hash_pointers_enable);
/*
* Show a '%p' thing. A kernel extension is that the '%p' is followed
* by an extra set of alphanumeric characters that are extended format
* specifiers.
*
* Please update scripts/checkpatch.pl when adding/removing conversion
* characters. (Search for "check for vsprintf extension").
*
* Right now we handle:
*
* - 'S' For symbolic direct pointers (or function descriptors) with offset
* - 's' For symbolic direct pointers (or function descriptors) without offset
* - '[Ss]R' as above with __builtin_extract_return_addr() translation
* - 'S[R]b' as above with module build ID (for use in backtraces)
* - '[Ff]' %pf and %pF were obsoleted and later removed in favor of
* %ps and %pS. Be careful when re-using these specifiers.
* - 'B' For backtraced symbolic direct pointers with offset
* - 'Bb' as above with module build ID (for use in backtraces)
* - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref]
* - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201]
* - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff]
* - 'b[l]' For a bitmap, the number of bits is determined by the field
* width which must be explicitly specified either as part of the
* format string '%32b[l]' or through '%*b[l]', [l] selects
* range-list format instead of hex format
* - 'M' For a 6-byte MAC address, it prints the address in the
* usual colon-separated hex notation
* - 'm' For a 6-byte MAC address, it prints the hex address without colons
* - 'MF' For a 6-byte MAC FDDI address, it prints the address
* with a dash-separated hex notation
* - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth)
* - 'I' [46] for IPv4/IPv6 addresses printed in the usual way
* IPv4 uses dot-separated decimal without leading 0's (1.2.3.4)
* IPv6 uses colon separated network-order 16 bit hex with leading 0's
* [S][pfs]
* Generic IPv4/IPv6 address (struct sockaddr *) that falls back to
* [4] or [6] and is able to print port [p], flowinfo [f], scope [s]
* - 'i' [46] for 'raw' IPv4/IPv6 addresses
* IPv6 omits the colons (01020304...0f)
* IPv4 uses dot-separated decimal with leading 0's (010.123.045.006)
* [S][pfs]
* Generic IPv4/IPv6 address (struct sockaddr *) that falls back to
* [4] or [6] and is able to print port [p], flowinfo [f], scope [s]
* - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order
* - 'I[6S]c' for IPv6 addresses printed as specified by
* https://tools.ietf.org/html/rfc5952
* - 'E[achnops]' For an escaped buffer, where rules are defined by combination
* of the following flags (see string_escape_mem() for the
* details):
* a - ESCAPE_ANY
* c - ESCAPE_SPECIAL
* h - ESCAPE_HEX
* n - ESCAPE_NULL
* o - ESCAPE_OCTAL
* p - ESCAPE_NP
* s - ESCAPE_SPACE
* By default ESCAPE_ANY_NP is used.
* - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form
* "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
* Options for %pU are:
* b big endian lower case hex (default)
* B big endian UPPER case hex
* l little endian lower case hex
* L little endian UPPER case hex
* big endian output byte order is:
* [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15]
* little endian output byte order is:
* [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15]
* - 'V' For a struct va_format which contains a format string * and va_list *,
* call vsnprintf(->format, *->va_list).
* Implements a "recursive vsnprintf".
* Do not use this feature without some mechanism to verify the
* correctness of the format string and va_list arguments.
* - 'K' For a kernel pointer that should be hidden from unprivileged users.
* Use only for procfs, sysfs and similar files, not printk(); please
* read the documentation (path below) first.
* - 'NF' For a netdev_features_t
* - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value.
* - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with
* a certain separator (' ' by default):
* C colon
* D dash
* N no separator
* The maximum supported length is 64 bytes of the input. Consider
* to use print_hex_dump() for the larger input.
* - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives
* (default assumed to be phys_addr_t, passed by reference)
* - 'd[234]' For a dentry name (optionally 2-4 last components)
* - 'D[234]' Same as 'd' but for a struct file
* - 'g' For block_device name (gendisk + partition number)
* - 't[RT][dt][r][s]' For time and date as represented by:
* R struct rtc_time
* T time64_t
* - 'C' For a clock, it prints the name (Common Clock Framework) or address
* (legacy clock framework) of the clock
* - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
* (legacy clock framework) of the clock
* - 'G' For flags to be printed as a collection of symbolic strings that would
* construct the specific value. Supported flags given by option:
* p page flags (see struct page) given as pointer to unsigned long
* g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t
* v vma flags (VM_*) given as pointer to unsigned long
* - 'OF[fnpPcCF]' For a device tree object
* Without any optional arguments prints the full_name
* f device node full_name
* n device node name
* p device node phandle
* P device node path spec (name + @unit)
* F device node flags
* c major compatible string
* C full compatible string
* - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer
* Without an option prints the full name of the node
* f full name
* P node name, including a possible unit address
* - 'x' For printing the address unmodified. Equivalent to "%lx".
* Please read the documentation (path below) before using!
* - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of
* bpf_trace_printk() where [ku] prefix specifies either kernel (k)
* or user (u) memory to probe, and:
* s a string, equivalent to "%s" on direct vsnprintf() use
*
* ** When making changes please also update:
* Documentation/core-api/printk-formats.rst
*
* Note: The default behaviour (unadorned %p) is to hash the address,
* rendering it useful as a unique identifier.
*
* There is also a '%pA' format specifier, but it is only intended to be used
* from Rust code to format core::fmt::Arguments. Do *not* use it from C.
* See rust/kernel/print.rs for details.
*/
static noinline_for_stack
char *pointer(const char *fmt, char *buf, char *end, void *ptr,
struct printf_spec spec)
{ switch (*fmt) {
case 'S':
case 's':
ptr = dereference_symbol_descriptor(ptr);
fallthrough;
case 'B':
return symbol_string(buf, end, ptr, spec, fmt);
case 'R':
case 'r':
return resource_or_range(fmt, buf, end, ptr, spec);
case 'h':
return hex_string(buf, end, ptr, spec, fmt);
case 'b':
switch (fmt[1]) {
case 'l':
return bitmap_list_string(buf, end, ptr, spec, fmt);
default:
return bitmap_string(buf, end, ptr, spec, fmt);
}
case 'M': /* Colon separated: 00:01:02:03:04:05 */
case 'm': /* Contiguous: 000102030405 */
/* [mM]F (FDDI) */
/* [mM]R (Reverse order; Bluetooth) */
return mac_address_string(buf, end, ptr, spec, fmt);
case 'I': /* Formatted IP supported
* 4: 1.2.3.4
* 6: 0001:0203:...:0708
* 6c: 1::708 or 1::1.2.3.4
*/
case 'i': /* Contiguous:
* 4: 001.002.003.004
* 6: 000102...0f
*/
return ip_addr_string(buf, end, ptr, spec, fmt);
case 'E':
return escaped_string(buf, end, ptr, spec, fmt);
case 'U':
return uuid_string(buf, end, ptr, spec, fmt);
case 'V':
return va_format(buf, end, ptr, spec);
case 'K':
return restricted_pointer(buf, end, ptr, spec);
case 'N':
return netdev_bits(buf, end, ptr, spec, fmt);
case '4':
return fourcc_string(buf, end, ptr, spec, fmt);
case 'a':
return address_val(buf, end, ptr, spec, fmt);
case 'd':
return dentry_name(buf, end, ptr, spec, fmt);
case 't':
return time_and_date(buf, end, ptr, spec, fmt);
case 'C':
return clock(buf, end, ptr, spec, fmt);
case 'D':
return file_dentry_name(buf, end, ptr, spec, fmt);
#ifdef CONFIG_BLOCK
case 'g':
return bdev_name(buf, end, ptr, spec, fmt);
#endif
case 'G':
return flags_string(buf, end, ptr, spec, fmt);
case 'O':
return device_node_string(buf, end, ptr, spec, fmt + 1);
case 'f':
return fwnode_string(buf, end, ptr, spec, fmt + 1);
case 'A':
if (!IS_ENABLED(CONFIG_RUST)) {
WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec);
}
return rust_fmt_argument(buf, end, ptr);
case 'x':
return pointer_string(buf, end, ptr, spec);
case 'e':
/* %pe with a non-ERR_PTR gets treated as plain %p */
if (!IS_ERR(ptr))
return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec);
case 'u':
case 'k':
switch (fmt[1]) {
case 's':
return string(buf, end, ptr, spec);
default:
return error_string(buf, end, "(einval)", spec);
}
default:
return default_pointer(buf, end, ptr, spec);
}
}
struct fmt {
const char *str;
unsigned char state; // enum format_state
unsigned char size; // size of numbers
};
#define SPEC_CHAR(x, flag) [(x)-32] = flag
static unsigned char spec_flag(unsigned char c)
{
static const unsigned char spec_flag_array[] = {
SPEC_CHAR(' ', SPACE),
SPEC_CHAR('#', SPECIAL),
SPEC_CHAR('+', PLUS),
SPEC_CHAR('-', LEFT),
SPEC_CHAR('0', ZEROPAD),
};
c -= 32;
return (c < sizeof(spec_flag_array)) ? spec_flag_array[c] : 0;
}
/*
* Helper function to decode printf style format.
* Each call decode a token from the format and return the
* number of characters read (or likely the delta where it wants
* to go on the next call).
* The decoded token is returned through the parameters
*
* 'h', 'l', or 'L' for integer fields
* 'z' support added 23/7/1999 S.H.
* 'z' changed to 'Z' --davidm 1/25/99
* 'Z' changed to 'z' --adobriyan 2017-01-25
* 't' added for ptrdiff_t
*
* @fmt: the format string
* @type of the token returned
* @flags: various flags such as +, -, # tokens..
* @field_width: overwritten width
* @base: base of the number (octal, hex, ...)
* @precision: precision of a number
* @qualifier: qualifier of a number (long, size_t, ...)
*/
static noinline_for_stack
struct fmt format_decode(struct fmt fmt, struct printf_spec *spec)
{
const char *start = fmt.str;
char flag;
/* we finished early by reading the field width */
if (unlikely(fmt.state == FORMAT_STATE_WIDTH)) {
if (spec->field_width < 0) { spec->field_width = -spec->field_width;
spec->flags |= LEFT;
}
fmt.state = FORMAT_STATE_NONE;
goto precision;
}
/* we finished early by reading the precision */
if (unlikely(fmt.state == FORMAT_STATE_PRECISION)) {
if (spec->precision < 0) spec->precision = 0;
fmt.state = FORMAT_STATE_NONE;
goto qualifier;
}
/* By default */
fmt.state = FORMAT_STATE_NONE;
for (; *fmt.str ; fmt.str++) {
if (*fmt.str == '%')
break;
}
/* Return the current non-format string */
if (fmt.str != start || !*fmt.str)
return fmt;
/* Process flags. This also skips the first '%' */
spec->flags = 0;
do {
/* this also skips first '%' */
flag = spec_flag(*++fmt.str);
spec->flags |= flag;
} while (flag);
/* get field width */
spec->field_width = -1;
if (isdigit(*fmt.str))
spec->field_width = skip_atoi(&fmt.str); else if (unlikely(*fmt.str == '*')) {
/* it's the next argument */
fmt.state = FORMAT_STATE_WIDTH;
fmt.str++;
return fmt;
}
precision:
/* get the precision */
spec->precision = -1;
if (unlikely(*fmt.str == '.')) {
fmt.str++;
if (isdigit(*fmt.str)) {
spec->precision = skip_atoi(&fmt.str);
if (spec->precision < 0)
spec->precision = 0;
} else if (*fmt.str == '*') {
/* it's the next argument */
fmt.state = FORMAT_STATE_PRECISION;
fmt.str++;
return fmt;
}
}
qualifier:
/* Set up default numeric format */
spec->base = 10;
fmt.state = FORMAT_STATE_NUM;
fmt.size = sizeof(int);
static const struct format_state {
unsigned char state;
unsigned char size;
unsigned char flags_or_double_size;
unsigned char base;
} lookup_state[256] = {
// Length
['l'] = { 0, sizeof(long), sizeof(long long) },
['L'] = { 0, sizeof(long long) },
['h'] = { 0, sizeof(short), sizeof(char) },
['H'] = { 0, sizeof(char) }, // Questionable historical
['z'] = { 0, sizeof(size_t) },
['t'] = { 0, sizeof(ptrdiff_t) },
// Non-numeric formats
['c'] = { FORMAT_STATE_CHAR },
['s'] = { FORMAT_STATE_STR },
['p'] = { FORMAT_STATE_PTR },
['%'] = { FORMAT_STATE_PERCENT_CHAR },
// Numerics
['o'] = { FORMAT_STATE_NUM, 0, 0, 8 },
['x'] = { FORMAT_STATE_NUM, 0, SMALL, 16 },
['X'] = { FORMAT_STATE_NUM, 0, 0, 16 },
['d'] = { FORMAT_STATE_NUM, 0, SIGN, 10 },
['i'] = { FORMAT_STATE_NUM, 0, SIGN, 10 },
['u'] = { FORMAT_STATE_NUM, 0, 0, 10, },
/*
* Since %n poses a greater security risk than
* utility, treat it as any other invalid or
* unsupported format specifier.
*/
};
const struct format_state *p = lookup_state + (u8)*fmt.str;
if (p->size) {
fmt.size = p->size;
if (p->flags_or_double_size && fmt.str[0] == fmt.str[1]) {
fmt.size = p->flags_or_double_size;
fmt.str++;
}
fmt.str++;
p = lookup_state + *fmt.str;
}
if (p->state) {
if (p->base) spec->base = p->base;
spec->flags |= p->flags_or_double_size;
fmt.state = p->state;
fmt.str++;
return fmt;
}
WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt.str);
fmt.state = FORMAT_STATE_INVALID;
return fmt;
}
static void
set_field_width(struct printf_spec *spec, int width)
{
spec->field_width = width;
if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) {
spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX);
}
}
static void
set_precision(struct printf_spec *spec, int prec)
{
spec->precision = prec;
if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) {
spec->precision = clamp(prec, 0, PRECISION_MAX);
}
}
/*
* Turn a 1/2/4-byte value into a 64-bit one for printing: truncate
* as necessary and deal with signedness.
*
* 'size' is the size of the value in bytes.
*/
static unsigned long long convert_num_spec(unsigned int val, int size, struct printf_spec spec)
{
unsigned int shift = 32 - size*8;
val <<= shift;
if (!(spec.flags & SIGN))
return val >> shift;
return (int)val >> shift;
}
/**
* vsnprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @size: The size of the buffer, including the trailing null space
* @fmt_str: The format string to use
* @args: Arguments for the format string
*
* This function generally follows C99 vsnprintf, but has some
* extensions and a few limitations:
*
* - ``%n`` is unsupported
* - ``%p*`` is handled by pointer()
*
* See pointer() or Documentation/core-api/printk-formats.rst for more
* extensive description.
*
* **Please update the documentation in both places when making changes**
*
* The return value is the number of characters which would
* be generated for the given input, excluding the trailing
* '\0', as per ISO C99. If you want to have the exact
* number of characters written into @buf as return value
* (not including the trailing '\0'), use vscnprintf(). If the
* return is greater than or equal to @size, the resulting
* string is truncated.
*
* If you're not already dealing with a va_list consider using snprintf().
*/
int vsnprintf(char *buf, size_t size, const char *fmt_str, va_list args)
{
char *str, *end;
struct printf_spec spec = {0};
struct fmt fmt = {
.str = fmt_str,
.state = FORMAT_STATE_NONE,
};
/* Reject out-of-range values early. Large positive sizes are
used for unknown buffer sizes. */
if (WARN_ON_ONCE(size > INT_MAX))
return 0;
str = buf;
end = buf + size;
/* Make sure end is always >= buf */
if (end < buf) {
end = ((void *)-1);
size = end - buf;
}
while (*fmt.str) {
const char *old_fmt = fmt.str;
fmt = format_decode(fmt, &spec);
switch (fmt.state) {
case FORMAT_STATE_NONE: {
int read = fmt.str - old_fmt;
if (str < end) {
int copy = read;
if (copy > end - str)
copy = end - str;
memcpy(str, old_fmt, copy);
}
str += read;
continue;
}
case FORMAT_STATE_NUM: {
unsigned long long num;
if (fmt.size <= sizeof(int))
num = convert_num_spec(va_arg(args, int), fmt.size, spec);
else
num = va_arg(args, long long);
str = number(str, end, num, spec);
continue;
}
case FORMAT_STATE_WIDTH:
set_field_width(&spec, va_arg(args, int));
continue;
case FORMAT_STATE_PRECISION:
set_precision(&spec, va_arg(args, int));
continue;
case FORMAT_STATE_CHAR: {
char c;
if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' ';
++str;
}
}
c = (unsigned char) va_arg(args, int); if (str < end)
*str = c;
++str;
while (--spec.field_width > 0) { if (str < end) *str = ' ';
++str;
}
continue;
}
case FORMAT_STATE_STR:
str = string(str, end, va_arg(args, char *), spec);
continue;
case FORMAT_STATE_PTR:
str = pointer(fmt.str, str, end, va_arg(args, void *),
spec);
while (isalnum(*fmt.str))
fmt.str++;
continue;
case FORMAT_STATE_PERCENT_CHAR:
if (str < end) *str = '%';
++str;
continue;
default:
/*
* Presumably the arguments passed gcc's type
* checking, but there is no safe or sane way
* for us to continue parsing the format and
* fetching from the va_list; the remaining
* specifiers and arguments would be out of
* sync.
*/
goto out;
}
}
out:
if (size > 0) {
if (str < end)
*str = '\0';
else
end[-1] = '\0';
}
/* the trailing null byte doesn't count towards the total */
return str-buf;
}
EXPORT_SYMBOL(vsnprintf);
/**
* vscnprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @size: The size of the buffer, including the trailing null space
* @fmt: The format string to use
* @args: Arguments for the format string
*
* The return value is the number of characters which have been written into
* the @buf not including the trailing '\0'. If @size is == 0 the function
* returns 0.
*
* If you're not already dealing with a va_list consider using scnprintf().
*
* See the vsnprintf() documentation for format string extensions over C99.
*/
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
{
int i;
if (unlikely(!size))
return 0;
i = vsnprintf(buf, size, fmt, args);
if (likely(i < size))
return i;
return size - 1;
}
EXPORT_SYMBOL(vscnprintf);
/**
* snprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @size: The size of the buffer, including the trailing null space
* @fmt: The format string to use
* @...: Arguments for the format string
*
* The return value is the number of characters which would be
* generated for the given input, excluding the trailing null,
* as per ISO C99. If the return is greater than or equal to
* @size, the resulting string is truncated.
*
* See the vsnprintf() documentation for format string extensions over C99.
*/
int snprintf(char *buf, size_t size, const char *fmt, ...)
{
va_list args;
int i;
va_start(args, fmt);
i = vsnprintf(buf, size, fmt, args);
va_end(args);
return i;
}
EXPORT_SYMBOL(snprintf);
/**
* scnprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @size: The size of the buffer, including the trailing null space
* @fmt: The format string to use
* @...: Arguments for the format string
*
* The return value is the number of characters written into @buf not including
* the trailing '\0'. If @size is == 0 the function returns 0.
*/
int scnprintf(char *buf, size_t size, const char *fmt, ...)
{
va_list args;
int i;
va_start(args, fmt);
i = vscnprintf(buf, size, fmt, args);
va_end(args);
return i;
}
EXPORT_SYMBOL(scnprintf);
/**
* vsprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @fmt: The format string to use
* @args: Arguments for the format string
*
* The function returns the number of characters written
* into @buf. Use vsnprintf() or vscnprintf() in order to avoid
* buffer overflows.
*
* If you're not already dealing with a va_list consider using sprintf().
*
* See the vsnprintf() documentation for format string extensions over C99.
*/
int vsprintf(char *buf, const char *fmt, va_list args)
{
return vsnprintf(buf, INT_MAX, fmt, args);
}
EXPORT_SYMBOL(vsprintf);
/**
* sprintf - Format a string and place it in a buffer
* @buf: The buffer to place the result into
* @fmt: The format string to use
* @...: Arguments for the format string
*
* The function returns the number of characters written
* into @buf. Use snprintf() or scnprintf() in order to avoid
* buffer overflows.
*
* See the vsnprintf() documentation for format string extensions over C99.
*/
int sprintf(char *buf, const char *fmt, ...)
{
va_list args;
int i;
va_start(args, fmt);
i = vsnprintf(buf, INT_MAX, fmt, args);
va_end(args);
return i;
}
EXPORT_SYMBOL(sprintf);
#ifdef CONFIG_BINARY_PRINTF
/*
* bprintf service:
* vbin_printf() - VA arguments to binary data
* bstr_printf() - Binary data to text string
*/
/**
* vbin_printf - Parse a format string and place args' binary value in a buffer
* @bin_buf: The buffer to place args' binary value
* @size: The size of the buffer(by words(32bits), not characters)
* @fmt_str: The format string to use
* @args: Arguments for the format string
*
* The format follows C99 vsnprintf, except %n is ignored, and its argument
* is skipped.
*
* The return value is the number of words(32bits) which would be generated for
* the given input.
*
* NOTE:
* If the return value is greater than @size, the resulting bin_buf is NOT
* valid for bstr_printf().
*/
int vbin_printf(u32 *bin_buf, size_t size, const char *fmt_str, va_list args)
{
struct fmt fmt = {
.str = fmt_str,
.state = FORMAT_STATE_NONE,
};
struct printf_spec spec = {0};
char *str, *end;
int width;
str = (char *)bin_buf;
end = (char *)(bin_buf + size);
#define save_arg(type) \
({ \
unsigned long long value; \
if (sizeof(type) == 8) { \
unsigned long long val8; \
str = PTR_ALIGN(str, sizeof(u32)); \
val8 = va_arg(args, unsigned long long); \
if (str + sizeof(type) <= end) { \
*(u32 *)str = *(u32 *)&val8; \
*(u32 *)(str + 4) = *((u32 *)&val8 + 1); \
} \
value = val8; \
} else { \
unsigned int val4; \
str = PTR_ALIGN(str, sizeof(type)); \
val4 = va_arg(args, int); \
if (str + sizeof(type) <= end) \
*(typeof(type) *)str = (type)(long)val4; \
value = (unsigned long long)val4; \
} \
str += sizeof(type); \
value; \
})
while (*fmt.str) {
fmt = format_decode(fmt, &spec);
switch (fmt.state) {
case FORMAT_STATE_NONE:
case FORMAT_STATE_PERCENT_CHAR:
break;
case FORMAT_STATE_INVALID:
goto out;
case FORMAT_STATE_WIDTH:
case FORMAT_STATE_PRECISION:
width = (int)save_arg(int);
/* Pointers may require the width */
if (*fmt.str == 'p')
set_field_width(&spec, width);
break;
case FORMAT_STATE_CHAR:
save_arg(char);
break;
case FORMAT_STATE_STR: {
const char *save_str = va_arg(args, char *);
const char *err_msg;
size_t len;
err_msg = check_pointer_msg(save_str);
if (err_msg)
save_str = err_msg;
len = strlen(save_str) + 1;
if (str + len < end)
memcpy(str, save_str, len);
str += len;
break;
}
case FORMAT_STATE_PTR:
/* Dereferenced pointers must be done now */
switch (*fmt.str) {
/* Dereference of functions is still OK */
case 'S':
case 's':
case 'x':
case 'K':
case 'e':
save_arg(void *);
break;
default:
if (!isalnum(*fmt.str)) {
save_arg(void *);
break;
}
str = pointer(fmt.str, str, end, va_arg(args, void *),
spec);
if (str + 1 < end)
*str++ = '\0';
else
end[-1] = '\0'; /* Must be nul terminated */
}
/* skip all alphanumeric pointer suffixes */
while (isalnum(*fmt.str))
fmt.str++;
break;
case FORMAT_STATE_NUM:
if (fmt.size > sizeof(int)) {
save_arg(long long);
} else {
save_arg(int);
}
}
}
out:
return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf;
#undef save_arg
}
EXPORT_SYMBOL_GPL(vbin_printf);
/**
* bstr_printf - Format a string from binary arguments and place it in a buffer
* @buf: The buffer to place the result into
* @size: The size of the buffer, including the trailing null space
* @fmt_str: The format string to use
* @bin_buf: Binary arguments for the format string
*
* This function like C99 vsnprintf, but the difference is that vsnprintf gets
* arguments from stack, and bstr_printf gets arguments from @bin_buf which is
* a binary buffer that generated by vbin_printf.
*
* The format follows C99 vsnprintf, but has some extensions:
* see vsnprintf comment for details.
*
* The return value is the number of characters which would
* be generated for the given input, excluding the trailing
* '\0', as per ISO C99. If you want to have the exact
* number of characters written into @buf as return value
* (not including the trailing '\0'), use vscnprintf(). If the
* return is greater than or equal to @size, the resulting
* string is truncated.
*/
int bstr_printf(char *buf, size_t size, const char *fmt_str, const u32 *bin_buf)
{
struct fmt fmt = {
.str = fmt_str,
.state = FORMAT_STATE_NONE,
};
struct printf_spec spec = {0};
char *str, *end;
const char *args = (const char *)bin_buf;
if (WARN_ON_ONCE(size > INT_MAX))
return 0;
str = buf;
end = buf + size;
#define get_arg(type) \
({ \
typeof(type) value; \
if (sizeof(type) == 8) { \
args = PTR_ALIGN(args, sizeof(u32)); \
*(u32 *)&value = *(u32 *)args; \
*((u32 *)&value + 1) = *(u32 *)(args + 4); \
} else { \
args = PTR_ALIGN(args, sizeof(type)); \
value = *(typeof(type) *)args; \
} \
args += sizeof(type); \
value; \
})
/* Make sure end is always >= buf */
if (end < buf) {
end = ((void *)-1);
size = end - buf;
}
while (*fmt.str) {
const char *old_fmt = fmt.str;
unsigned long long num;
fmt = format_decode(fmt, &spec);
switch (fmt.state) {
case FORMAT_STATE_NONE: {
int read = fmt.str - old_fmt;
if (str < end) {
int copy = read;
if (copy > end - str)
copy = end - str;
memcpy(str, old_fmt, copy);
}
str += read;
continue;
}
case FORMAT_STATE_WIDTH:
set_field_width(&spec, get_arg(int));
continue;
case FORMAT_STATE_PRECISION:
set_precision(&spec, get_arg(int));
continue;
case FORMAT_STATE_CHAR: {
char c;
if (!(spec.flags & LEFT)) {
while (--spec.field_width > 0) {
if (str < end)
*str = ' ';
++str;
}
}
c = (unsigned char) get_arg(char);
if (str < end)
*str = c;
++str;
while (--spec.field_width > 0) {
if (str < end)
*str = ' ';
++str;
}
continue;
}
case FORMAT_STATE_STR: {
const char *str_arg = args;
args += strlen(str_arg) + 1;
str = string(str, end, (char *)str_arg, spec);
continue;
}
case FORMAT_STATE_PTR: {
bool process = false;
int copy, len;
/* Non function dereferences were already done */
switch (*fmt.str) {
case 'S':
case 's':
case 'x':
case 'K':
case 'e':
process = true;
break;
default:
if (!isalnum(*fmt.str)) {
process = true;
break;
}
/* Pointer dereference was already processed */
if (str < end) {
len = copy = strlen(args);
if (copy > end - str)
copy = end - str;
memcpy(str, args, copy);
str += len;
args += len + 1;
}
}
if (process)
str = pointer(fmt.str, str, end, get_arg(void *), spec);
while (isalnum(*fmt.str))
fmt.str++;
continue;
}
case FORMAT_STATE_PERCENT_CHAR:
if (str < end)
*str = '%';
++str;
continue;
case FORMAT_STATE_INVALID:
goto out;
case FORMAT_STATE_NUM:
if (fmt.size > sizeof(int)) {
num = get_arg(long long);
} else {
num = convert_num_spec(get_arg(int), fmt.size, spec);
}
str = number(str, end, num, spec);
continue;
}
} /* while(*fmt.str) */
out:
if (size > 0) {
if (str < end)
*str = '\0';
else
end[-1] = '\0';
}
#undef get_arg
/* the trailing null byte doesn't count towards the total */
return str - buf;
}
EXPORT_SYMBOL_GPL(bstr_printf);
#endif /* CONFIG_BINARY_PRINTF */
/**
* vsscanf - Unformat a buffer into a list of arguments
* @buf: input buffer
* @fmt: format of buffer
* @args: arguments
*/
int vsscanf(const char *buf, const char *fmt, va_list args)
{
const char *str = buf;
char *next;
char digit;
int num = 0;
u8 qualifier;
unsigned int base;
union {
long long s;
unsigned long long u;
} val;
s16 field_width;
bool is_sign;
while (*fmt) {
/* skip any white space in format */
/* white space in format matches any amount of
* white space, including none, in the input.
*/
if (isspace(*fmt)) {
fmt = skip_spaces(++fmt);
str = skip_spaces(str);
}
/* anything that is not a conversion must match exactly */
if (*fmt != '%' && *fmt) {
if (*fmt++ != *str++)
break;
continue;
}
if (!*fmt)
break;
++fmt;
/* skip this conversion.
* advance both strings to next white space
*/
if (*fmt == '*') {
if (!*str)
break;
while (!isspace(*fmt) && *fmt != '%' && *fmt) {
/* '%*[' not yet supported, invalid format */
if (*fmt == '[')
return num;
fmt++;
}
while (!isspace(*str) && *str)
str++;
continue;
}
/* get field width */
field_width = -1;
if (isdigit(*fmt)) {
field_width = skip_atoi(&fmt);
if (field_width <= 0)
break;
}
/* get conversion qualifier */
qualifier = -1;
if (*fmt == 'h' || _tolower(*fmt) == 'l' ||
*fmt == 'z') {
qualifier = *fmt++;
if (unlikely(qualifier == *fmt)) {
if (qualifier == 'h') {
qualifier = 'H';
fmt++;
} else if (qualifier == 'l') {
qualifier = 'L';
fmt++;
}
}
}
if (!*fmt)
break;
if (*fmt == 'n') {
/* return number of characters read so far */
*va_arg(args, int *) = str - buf;
++fmt;
continue;
}
if (!*str)
break;
base = 10;
is_sign = false;
switch (*fmt++) {
case 'c':
{
char *s = (char *)va_arg(args, char*);
if (field_width == -1)
field_width = 1;
do {
*s++ = *str++;
} while (--field_width > 0 && *str);
num++;
}
continue;
case 's':
{
char *s = (char *)va_arg(args, char *);
if (field_width == -1)
field_width = SHRT_MAX;
/* first, skip leading white space in buffer */
str = skip_spaces(str);
/* now copy until next white space */
while (*str && !isspace(*str) && field_width--)
*s++ = *str++;
*s = '\0';
num++;
}
continue;
/*
* Warning: This implementation of the '[' conversion specifier
* deviates from its glibc counterpart in the following ways:
* (1) It does NOT support ranges i.e. '-' is NOT a special
* character
* (2) It cannot match the closing bracket ']' itself
* (3) A field width is required
* (4) '%*[' (discard matching input) is currently not supported
*
* Example usage:
* ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]",
* buf1, buf2, buf3);
* if (ret < 3)
* // etc..
*/
case '[':
{
char *s = (char *)va_arg(args, char *);
DECLARE_BITMAP(set, 256) = {0};
unsigned int len = 0;
bool negate = (*fmt == '^');
/* field width is required */
if (field_width == -1)
return num;
if (negate)
++fmt;
for ( ; *fmt && *fmt != ']'; ++fmt, ++len)
__set_bit((u8)*fmt, set);
/* no ']' or no character set found */
if (!*fmt || !len)
return num;
++fmt;
if (negate) {
bitmap_complement(set, set, 256);
/* exclude null '\0' byte */
__clear_bit(0, set);
}
/* match must be non-empty */
if (!test_bit((u8)*str, set))
return num;
while (test_bit((u8)*str, set) && field_width--)
*s++ = *str++;
*s = '\0';
++num;
}
continue;
case 'o':
base = 8;
break;
case 'x':
case 'X':
base = 16;
break;
case 'i':
base = 0;
fallthrough;
case 'd':
is_sign = true;
fallthrough;
case 'u':
break;
case '%':
/* looking for '%' in str */
if (*str++ != '%')
return num;
continue;
default:
/* invalid format; stop here */
return num;
}
/* have some sort of integer conversion.
* first, skip white space in buffer.
*/
str = skip_spaces(str);
digit = *str;
if (is_sign && digit == '-') {
if (field_width == 1)
break;
digit = *(str + 1);
}
if (!digit
|| (base == 16 && !isxdigit(digit))
|| (base == 10 && !isdigit(digit))
|| (base == 8 && !isodigit(digit))
|| (base == 0 && !isdigit(digit)))
break;
if (is_sign)
val.s = simple_strntoll(str, &next, base,
field_width >= 0 ? field_width : INT_MAX);
else
val.u = simple_strntoull(str, &next, base,
field_width >= 0 ? field_width : INT_MAX);
switch (qualifier) {
case 'H': /* that's 'hh' in format */
if (is_sign)
*va_arg(args, signed char *) = val.s;
else
*va_arg(args, unsigned char *) = val.u;
break;
case 'h':
if (is_sign)
*va_arg(args, short *) = val.s;
else
*va_arg(args, unsigned short *) = val.u;
break;
case 'l':
if (is_sign)
*va_arg(args, long *) = val.s;
else
*va_arg(args, unsigned long *) = val.u;
break;
case 'L':
if (is_sign)
*va_arg(args, long long *) = val.s;
else
*va_arg(args, unsigned long long *) = val.u;
break;
case 'z':
*va_arg(args, size_t *) = val.u;
break;
default:
if (is_sign)
*va_arg(args, int *) = val.s;
else
*va_arg(args, unsigned int *) = val.u;
break;
}
num++;
if (!next)
break;
str = next;
}
return num;
}
EXPORT_SYMBOL(vsscanf);
/**
* sscanf - Unformat a buffer into a list of arguments
* @buf: input buffer
* @fmt: formatting of buffer
* @...: resulting arguments
*/
int sscanf(const char *buf, const char *fmt, ...)
{
va_list args;
int i;
va_start(args, fmt);
i = vsscanf(buf, fmt, args);
va_end(args);
return i;
}
EXPORT_SYMBOL(sscanf);
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion
*
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
*
* Author: Paul McKenney <paulmck@linux.ibm.com>
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU/ *.txt
*
*/
#ifndef _LINUX_SRCU_H
#define _LINUX_SRCU_H
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/rcu_segcblist.h>
struct srcu_struct;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
struct lock_class_key *key);
#define init_srcu_struct(ssp) \
({ \
static struct lock_class_key __srcu_key; \
\
__init_srcu_struct((ssp), #ssp, &__srcu_key); \
})
#define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name },
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
int init_srcu_struct(struct srcu_struct *ssp);
#define __SRCU_DEP_MAP_INIT(srcu_name)
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */
#define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock().
#define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe().
#define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite().
#define SRCU_READ_FLAVOR_FAST 0x8 // srcu_read_lock_fast().
#define SRCU_READ_FLAVOR_ALL (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \
SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST) // All of the above.
#define SRCU_READ_FLAVOR_SLOWGP (SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST)
// Flavors requiring synchronize_rcu()
// instead of smp_mb().
void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
#ifdef CONFIG_TINY_SRCU
#include <linux/srcutiny.h>
#elif defined(CONFIG_TREE_SRCU)
#include <linux/srcutree.h>
#else
#error "Unknown SRCU implementation specified to kernel configuration"
#endif
void call_srcu(struct srcu_struct *ssp, struct rcu_head *head,
void (*func)(struct rcu_head *head));
void cleanup_srcu_struct(struct srcu_struct *ssp);
void synchronize_srcu(struct srcu_struct *ssp);
#define SRCU_GET_STATE_COMPLETED 0x1
/**
* get_completed_synchronize_srcu - Return a pre-completed polled state cookie
*
* Returns a value that poll_state_synchronize_srcu() will always treat
* as a cookie whose grace period has already completed.
*/
static inline unsigned long get_completed_synchronize_srcu(void)
{
return SRCU_GET_STATE_COMPLETED;
}
unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp);
unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp);
bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie);
// Maximum number of unsigned long values corresponding to
// not-yet-completed SRCU grace periods.
#define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2
/**
* same_state_synchronize_srcu - Are two old-state values identical?
* @oldstate1: First old-state value.
* @oldstate2: Second old-state value.
*
* The two old-state values must have been obtained from either
* get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or
* get_completed_synchronize_srcu(). Returns @true if the two values are
* identical and @false otherwise. This allows structures whose lifetimes
* are tracked by old-state values to push these values to a list header,
* allowing those structures to be slightly smaller.
*/
static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2)
{
return oldstate1 == oldstate2;
}
#ifdef CONFIG_NEED_SRCU_NMI_SAFE
int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp);
void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp);
#else
static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp)
{
return __srcu_read_lock(ssp);
}
static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx)
{
__srcu_read_unlock(ssp, idx);
}
#endif /* CONFIG_NEED_SRCU_NMI_SAFE */
void srcu_init(void);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
* srcu_read_lock_held - might we be in SRCU read-side critical section?
* @ssp: The srcu_struct structure to check
*
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an SRCU read-side critical section unless it can
* prove otherwise.
*
* Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
* and while lockdep is disabled.
*
* Note that SRCU is based on its own statemachine and it doesn't
* relies on normal RCU, it can be called from the CPU which
* is in the idle loop from an RCU point of view or offline.
*/
static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
{
if (!debug_lockdep_rcu_enabled())
return 1;
return lock_is_held(&ssp->dep_map);
}
/*
* Annotations provide deadlock detection for SRCU.
*
* Similar to other lockdep annotations, except there is an additional
* srcu_lock_sync(), which is basically an empty *write*-side critical section,
* see lock_sync() for more information.
*/
/* Annotates a srcu_read_lock() */
static inline void srcu_lock_acquire(struct lockdep_map *map)
{ lock_map_acquire_read(map);
}
/* Annotates a srcu_read_lock() */
static inline void srcu_lock_release(struct lockdep_map *map)
{ lock_map_release(map);
}
/* Annotates a synchronize_srcu() */
static inline void srcu_lock_sync(struct lockdep_map *map)
{
lock_map_sync(map);
}
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
{
return 1;
}
#define srcu_lock_acquire(m) do { } while (0)
#define srcu_lock_release(m) do { } while (0)
#define srcu_lock_sync(m) do { } while (0)
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/**
* srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing
* @p: the pointer to fetch and protect for later dereferencing
* @ssp: pointer to the srcu_struct, which is used to check that we
* really are in an SRCU read-side critical section.
* @c: condition to check for update-side use
*
* If PROVE_RCU is enabled, invoking this outside of an RCU read-side
* critical section will result in an RCU-lockdep splat, unless @c evaluates
* to 1. The @c argument will normally be a logical expression containing
* lockdep_is_held() calls.
*/
#define srcu_dereference_check(p, ssp, c) \
__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
(c) || srcu_read_lock_held(ssp), __rcu)
/**
* srcu_dereference - fetch SRCU-protected pointer for later dereferencing
* @p: the pointer to fetch and protect for later dereferencing
* @ssp: pointer to the srcu_struct, which is used to check that we
* really are in an SRCU read-side critical section.
*
* Makes rcu_dereference_check() do the dirty work. If PROVE_RCU
* is enabled, invoking this outside of an RCU read-side critical
* section will result in an RCU-lockdep splat.
*/
#define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0)
/**
* srcu_dereference_notrace - no tracing and no lockdep calls from here
* @p: the pointer to fetch and protect for later dereferencing
* @ssp: pointer to the srcu_struct, which is used to check that we
* really are in an SRCU read-side critical section.
*/
#define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1)
/**
* srcu_read_lock - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter an SRCU read-side critical section. Note that SRCU read-side
* critical sections may be nested. However, it is illegal to
* call anything that waits on an SRCU grace period for the same
* srcu_struct, whether directly or indirectly. Please note that
* one way to indirectly wait on an SRCU grace period is to acquire
* a mutex that is held elsewhere while calling synchronize_srcu() or
* synchronize_srcu_expedited().
*
* The return value from srcu_read_lock() is guaranteed to be
* non-negative. This value must be passed unaltered to the matching
* srcu_read_unlock(). Note that srcu_read_lock() and the matching
* srcu_read_unlock() must occur in the same context, for example, it is
* illegal to invoke srcu_read_unlock() in an irq handler if the matching
* srcu_read_lock() was invoked in process context. Or, for that matter to
* invoke srcu_read_unlock() from one task and the matching srcu_read_lock()
* from another.
*/
static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp)
{
int retval;
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
retval = __srcu_read_lock(ssp);
srcu_lock_acquire(&ssp->dep_map);
return retval;
}
/**
* srcu_read_lock_fast - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter an SRCU read-side critical section, but for a light-weight
* smp_mb()-free reader. See srcu_read_lock() for more information.
*
* If srcu_read_lock_fast() is ever used on an srcu_struct structure,
* then none of the other flavors may be used, whether before, during,
* or after. Note that grace-period auto-expediting is disabled for _fast
* srcu_struct structures because auto-expedited grace periods invoke
* synchronize_rcu_expedited(), IPIs and all.
*
* Note that srcu_read_lock_fast() can be invoked only from those contexts
* where RCU is watching, that is, from contexts where it would be legal
* to invoke rcu_read_lock(). Otherwise, lockdep will complain.
*/
static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *ssp) __acquires(ssp)
{
struct srcu_ctr __percpu *retval;
srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST);
retval = __srcu_read_lock_fast(ssp);
rcu_try_lock_acquire(&ssp->dep_map);
return retval;
}
/**
* srcu_down_read_fast - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter a semaphore-like SRCU read-side critical section, but for
* a light-weight smp_mb()-free reader. See srcu_read_lock_fast() and
* srcu_down_read() for more information.
*
* The same srcu_struct may be used concurrently by srcu_down_read_fast()
* and srcu_read_lock_fast().
*/
static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires(ssp)
{
WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi());
srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST);
return __srcu_read_lock_fast(ssp);
}
/**
* srcu_read_lock_lite - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter an SRCU read-side critical section, but for a light-weight
* smp_mb()-free reader. See srcu_read_lock() for more information.
*
* If srcu_read_lock_lite() is ever used on an srcu_struct structure,
* then none of the other flavors may be used, whether before, during,
* or after. Note that grace-period auto-expediting is disabled for _lite
* srcu_struct structures because auto-expedited grace periods invoke
* synchronize_rcu_expedited(), IPIs and all.
*
* Note that srcu_read_lock_lite() can be invoked only from those contexts
* where RCU is watching, that is, from contexts where it would be legal
* to invoke rcu_read_lock(). Otherwise, lockdep will complain.
*/
static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp)
{
int retval;
srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_LITE);
retval = __srcu_read_lock_lite(ssp);
rcu_try_lock_acquire(&ssp->dep_map);
return retval;
}
/**
* srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter an SRCU read-side critical section, but in an NMI-safe manner.
* See srcu_read_lock() for more information.
*
* If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure,
* then none of the other flavors may be used, whether before, during,
* or after.
*/
static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp)
{
int retval;
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI);
retval = __srcu_read_lock_nmisafe(ssp);
rcu_try_lock_acquire(&ssp->dep_map);
return retval;
}
/* Used by tracing, cannot be traced and cannot invoke lockdep. */
static inline notrace int
srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp)
{
int retval;
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
retval = __srcu_read_lock(ssp);
return retval;
}
/**
* srcu_down_read - register a new reader for an SRCU-protected structure.
* @ssp: srcu_struct in which to register the new reader.
*
* Enter a semaphore-like SRCU read-side critical section. Note that
* SRCU read-side critical sections may be nested. However, it is
* illegal to call anything that waits on an SRCU grace period for the
* same srcu_struct, whether directly or indirectly. Please note that
* one way to indirectly wait on an SRCU grace period is to acquire
* a mutex that is held elsewhere while calling synchronize_srcu() or
* synchronize_srcu_expedited(). But if you want lockdep to help you
* keep this stuff straight, you should instead use srcu_read_lock().
*
* The semaphore-like nature of srcu_down_read() means that the matching
* srcu_up_read() can be invoked from some other context, for example,
* from some other task or from an irq handler. However, neither
* srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler.
*
* Calls to srcu_down_read() may be nested, similar to the manner in
* which calls to down_read() may be nested. The same srcu_struct may be
* used concurrently by srcu_down_read() and srcu_read_lock().
*/
static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp)
{
WARN_ON_ONCE(in_nmi());
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
return __srcu_read_lock(ssp);
}
/**
* srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @idx: return value from corresponding srcu_read_lock().
*
* Exit an SRCU read-side critical section.
*/
static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx)
__releases(ssp)
{ WARN_ON_ONCE(idx & ~0x1);
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
srcu_lock_release(&ssp->dep_map);
__srcu_read_unlock(ssp, idx);
}
/**
* srcu_read_unlock_fast - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @scp: return value from corresponding srcu_read_lock_fast().
*
* Exit a light-weight SRCU read-side critical section.
*/
static inline void srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp)
__releases(ssp)
{
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST);
srcu_lock_release(&ssp->dep_map);
__srcu_read_unlock_fast(ssp, scp);
}
/**
* srcu_up_read_fast - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @scp: return value from corresponding srcu_read_lock_fast().
*
* Exit an SRCU read-side critical section, but not necessarily from
* the same context as the maching srcu_down_read_fast().
*/
static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp)
__releases(ssp)
{
WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi());
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST);
__srcu_read_unlock_fast(ssp, scp);
}
/**
* srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @idx: return value from corresponding srcu_read_lock_lite().
*
* Exit a light-weight SRCU read-side critical section.
*/
static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
__releases(ssp)
{
WARN_ON_ONCE(idx & ~0x1);
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE);
srcu_lock_release(&ssp->dep_map);
__srcu_read_unlock_lite(ssp, idx);
}
/**
* srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @idx: return value from corresponding srcu_read_lock_nmisafe().
*
* Exit an SRCU read-side critical section, but in an NMI-safe manner.
*/
static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx)
__releases(ssp)
{
WARN_ON_ONCE(idx & ~0x1);
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI);
rcu_lock_release(&ssp->dep_map);
__srcu_read_unlock_nmisafe(ssp, idx);
}
/* Used by tracing, cannot be traced and cannot call lockdep. */
static inline notrace void
srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp)
{
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
__srcu_read_unlock(ssp, idx);
}
/**
* srcu_up_read - unregister a old reader from an SRCU-protected structure.
* @ssp: srcu_struct in which to unregister the old reader.
* @idx: return value from corresponding srcu_read_lock().
*
* Exit an SRCU read-side critical section, but not necessarily from
* the same context as the maching srcu_down_read().
*/
static inline void srcu_up_read(struct srcu_struct *ssp, int idx)
__releases(ssp)
{
WARN_ON_ONCE(idx & ~0x1);
WARN_ON_ONCE(in_nmi());
srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
__srcu_read_unlock(ssp, idx);
}
/**
* smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
*
* Converts the preceding srcu_read_unlock into a two-way memory barrier.
*
* Call this after srcu_read_unlock, to guarantee that all memory operations
* that occur after smp_mb__after_srcu_read_unlock will appear to happen after
* the preceding srcu_read_unlock.
*/
static inline void smp_mb__after_srcu_read_unlock(void)
{
/* __srcu_read_unlock has smp_mb() internally so nothing to do here. */
}
/**
* smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock
*
* Converts the preceding srcu_read_lock into a two-way memory barrier.
*
* Call this after srcu_read_lock, to guarantee that all memory operations
* that occur after smp_mb__after_srcu_read_lock will appear to happen after
* the preceding srcu_read_lock.
*/
static inline void smp_mb__after_srcu_read_lock(void)
{
/* __srcu_read_lock has smp_mb() internally so nothing to do here. */
}
DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct,
_T->idx = srcu_read_lock(_T->lock),
srcu_read_unlock(_T->lock, _T->idx),
int idx)
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Network interface table.
*
* Network interfaces (devices) do not have a security field, so we
* maintain a table associating each interface with a SID.
*
* Author: James Morris <jmorris@redhat.com>
*
* Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
* Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
* Paul Moore <paul@paul-moore.com>
*/
#include <linux/init.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include "security.h"
#include "objsec.h"
#include "netif.h"
#define SEL_NETIF_HASH_SIZE 64
#define SEL_NETIF_HASH_MAX 1024
struct sel_netif {
struct list_head list;
struct netif_security_struct nsec;
struct rcu_head rcu_head;
};
static u32 sel_netif_total;
static DEFINE_SPINLOCK(sel_netif_lock);
static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE];
/**
* sel_netif_hashfn - Hashing function for the interface table
* @ns: the network namespace
* @ifindex: the network interface
*
* Description:
* This is the hashing function for the network interface table, it returns the
* bucket number for the given interface.
*
*/
static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex)
{
return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1));
}
/**
* sel_netif_find - Search for an interface record
* @ns: the network namespace
* @ifindex: the network interface
*
* Description:
* Search the network interface table and return the record matching @ifindex.
* If an entry can not be found in the table return NULL.
*
*/
static inline struct sel_netif *sel_netif_find(const struct net *ns,
int ifindex)
{
u32 idx = sel_netif_hashfn(ns, ifindex);
struct sel_netif *netif;
list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list) if (net_eq(netif->nsec.ns, ns) &&
netif->nsec.ifindex == ifindex)
return netif;
return NULL;
}
/**
* sel_netif_insert - Insert a new interface into the table
* @netif: the new interface record
*
* Description:
* Add a new interface record to the network interface hash table. Returns
* zero on success, negative values on failure.
*
*/
static int sel_netif_insert(struct sel_netif *netif)
{
u32 idx;
if (sel_netif_total >= SEL_NETIF_HASH_MAX)
return -ENOSPC;
idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex);
list_add_rcu(&netif->list, &sel_netif_hash[idx]);
sel_netif_total++;
return 0;
}
/**
* sel_netif_destroy - Remove an interface record from the table
* @netif: the existing interface record
*
* Description:
* Remove an existing interface record from the network interface table.
*
*/
static void sel_netif_destroy(struct sel_netif *netif)
{
list_del_rcu(&netif->list);
sel_netif_total--;
kfree_rcu(netif, rcu_head);
}
/**
* sel_netif_sid_slow - Lookup the SID of a network interface using the policy
* @ns: the network namespace
* @ifindex: the network interface
* @sid: interface SID
*
* Description:
* This function determines the SID of a network interface by querying the
* security policy. The result is added to the network interface table to
* speedup future queries. Returns zero on success, negative values on
* failure.
*
*/
static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid)
{
int ret = 0;
struct sel_netif *netif;
struct sel_netif *new;
struct net_device *dev;
/* NOTE: we always use init's network namespace since we don't
* currently support containers */
dev = dev_get_by_index(ns, ifindex);
if (unlikely(dev == NULL)) {
pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n",
__func__, ifindex);
return -ENOENT;
}
spin_lock_bh(&sel_netif_lock);
netif = sel_netif_find(ns, ifindex);
if (netif != NULL) {
*sid = netif->nsec.sid;
goto out;
}
ret = security_netif_sid(dev->name, sid);
if (ret != 0)
goto out;
new = kzalloc(sizeof(*new), GFP_ATOMIC);
if (new) {
new->nsec.ns = ns;
new->nsec.ifindex = ifindex;
new->nsec.sid = *sid;
if (sel_netif_insert(new))
kfree(new);
}
out:
spin_unlock_bh(&sel_netif_lock);
dev_put(dev);
if (unlikely(ret))
pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n",
__func__, ifindex);
return ret;
}
/**
* sel_netif_sid - Lookup the SID of a network interface
* @ns: the network namespace
* @ifindex: the network interface
* @sid: interface SID
*
* Description:
* This function determines the SID of a network interface using the fastest
* method possible. First the interface table is queried, but if an entry
* can't be found then the policy is queried and the result is added to the
* table to speedup future queries. Returns zero on success, negative values
* on failure.
*
*/
int sel_netif_sid(struct net *ns, int ifindex, u32 *sid)
{
struct sel_netif *netif;
rcu_read_lock();
netif = sel_netif_find(ns, ifindex);
if (likely(netif != NULL)) {
*sid = netif->nsec.sid;
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
return sel_netif_sid_slow(ns, ifindex, sid);
}
/**
* sel_netif_kill - Remove an entry from the network interface table
* @ns: the network namespace
* @ifindex: the network interface
*
* Description:
* This function removes the entry matching @ifindex from the network interface
* table if it exists.
*
*/
static void sel_netif_kill(const struct net *ns, int ifindex)
{
struct sel_netif *netif;
rcu_read_lock();
spin_lock_bh(&sel_netif_lock);
netif = sel_netif_find(ns, ifindex); if (netif) sel_netif_destroy(netif);
spin_unlock_bh(&sel_netif_lock);
rcu_read_unlock();
}
/**
* sel_netif_flush - Flush the entire network interface table
*
* Description:
* Remove all entries from the network interface table.
*
*/
void sel_netif_flush(void)
{
int idx;
struct sel_netif *netif;
spin_lock_bh(&sel_netif_lock);
for (idx = 0; idx < SEL_NETIF_HASH_SIZE; idx++)
list_for_each_entry(netif, &sel_netif_hash[idx], list)
sel_netif_destroy(netif);
spin_unlock_bh(&sel_netif_lock);
}
static int sel_netif_netdev_notifier_handler(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
if (event == NETDEV_DOWN) sel_netif_kill(dev_net(dev), dev->ifindex);
return NOTIFY_DONE;
}
static struct notifier_block sel_netif_netdev_notifier = {
.notifier_call = sel_netif_netdev_notifier_handler,
};
static __init int sel_netif_init(void)
{
int i;
if (!selinux_enabled_boot)
return 0;
for (i = 0; i < SEL_NETIF_HASH_SIZE; i++)
INIT_LIST_HEAD(&sel_netif_hash[i]);
register_netdevice_notifier(&sel_netif_netdev_notifier);
return 0;
}
__initcall(sel_netif_init);
// SPDX-License-Identifier: GPL-2.0
/*
* kobject.c - library routines for handling generic kernel objects
*
* Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org>
* Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com>
* Copyright (c) 2006-2007 Novell Inc.
*
* Please see the file Documentation/core-api/kobject.rst for critical information
* about using the kobject interface.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/random.h>
/**
* kobject_namespace() - Return @kobj's namespace tag.
* @kobj: kobject in question
*
* Returns namespace tag of @kobj if its parent has namespace ops enabled
* and thus @kobj should have a namespace tag associated with it. Returns
* %NULL otherwise.
*/
const void *kobject_namespace(const struct kobject *kobj)
{
const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj);
if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE)
return NULL;
return kobj->ktype->namespace(kobj);
}
/**
* kobject_get_ownership() - Get sysfs ownership data for @kobj.
* @kobj: kobject in question
* @uid: kernel user ID for sysfs objects
* @gid: kernel group ID for sysfs objects
*
* Returns initial uid/gid pair that should be used when creating sysfs
* representation of given kobject. Normally used to adjust ownership of
* objects in a container.
*/
void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid)
{
*uid = GLOBAL_ROOT_UID;
*gid = GLOBAL_ROOT_GID;
if (kobj->ktype->get_ownership)
kobj->ktype->get_ownership(kobj, uid, gid);
}
static bool kobj_ns_type_is_valid(enum kobj_ns_type type)
{
if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES))
return false;
return true;
}
static int create_dir(struct kobject *kobj)
{
const struct kobj_type *ktype = get_ktype(kobj);
const struct kobj_ns_type_operations *ops;
int error;
error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj));
if (error)
return error;
if (ktype) {
error = sysfs_create_groups(kobj, ktype->default_groups);
if (error) {
sysfs_remove_dir(kobj);
return error;
}
}
/*
* @kobj->sd may be deleted by an ancestor going away. Hold an
* extra reference so that it stays until @kobj is gone.
*/
sysfs_get(kobj->sd);
/*
* If @kobj has ns_ops, its children need to be filtered based on
* their namespace tags. Enable namespace support on @kobj->sd.
*/
ops = kobj_child_ns_ops(kobj);
if (ops) {
BUG_ON(!kobj_ns_type_is_valid(ops->type));
BUG_ON(!kobj_ns_type_registered(ops->type));
sysfs_enable_ns(kobj->sd);
}
return 0;
}
static int get_kobj_path_length(const struct kobject *kobj)
{
int length = 1;
const struct kobject *parent = kobj;
/* walk up the ancestors until we hit the one pointing to the
* root.
* Add 1 to strlen for leading '/' of each level.
*/
do {
if (kobject_name(parent) == NULL)
return 0;
length += strlen(kobject_name(parent)) + 1;
parent = parent->parent;
} while (parent);
return length;
}
static int fill_kobj_path(const struct kobject *kobj, char *path, int length)
{
const struct kobject *parent;
--length;
for (parent = kobj; parent; parent = parent->parent) {
int cur = strlen(kobject_name(parent));
/* back up enough to print this name with '/' */
length -= cur;
if (length <= 0)
return -EINVAL;
memcpy(path + length, kobject_name(parent), cur);
*(path + --length) = '/';
}
pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj),
kobj, __func__, path);
return 0;
}
/**
* kobject_get_path() - Allocate memory and fill in the path for @kobj.
* @kobj: kobject in question, with which to build the path
* @gfp_mask: the allocation type used to allocate the path
*
* Return: The newly allocated memory, caller must free with kfree().
*/
char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask)
{
char *path;
int len;
retry:
len = get_kobj_path_length(kobj); if (len == 0)
return NULL;
path = kzalloc(len, gfp_mask);
if (!path)
return NULL;
if (fill_kobj_path(kobj, path, len)) { kfree(path);
goto retry;
}
return path;
}
EXPORT_SYMBOL_GPL(kobject_get_path);
/* add the kobject to its kset's list */
static void kobj_kset_join(struct kobject *kobj)
{
if (!kobj->kset)
return;
kset_get(kobj->kset);
spin_lock(&kobj->kset->list_lock);
list_add_tail(&kobj->entry, &kobj->kset->list);
spin_unlock(&kobj->kset->list_lock);
}
/* remove the kobject from its kset's list */
static void kobj_kset_leave(struct kobject *kobj)
{
if (!kobj->kset)
return;
spin_lock(&kobj->kset->list_lock);
list_del_init(&kobj->entry);
spin_unlock(&kobj->kset->list_lock);
kset_put(kobj->kset);
}
static void kobject_init_internal(struct kobject *kobj)
{
if (!kobj)
return;
kref_init(&kobj->kref);
INIT_LIST_HEAD(&kobj->entry);
kobj->state_in_sysfs = 0;
kobj->state_add_uevent_sent = 0;
kobj->state_remove_uevent_sent = 0;
kobj->state_initialized = 1;
}
static int kobject_add_internal(struct kobject *kobj)
{
int error = 0;
struct kobject *parent;
if (!kobj)
return -ENOENT;
if (!kobj->name || !kobj->name[0]) {
WARN(1,
"kobject: (%p): attempted to be registered with empty name!\n",
kobj);
return -EINVAL;
}
parent = kobject_get(kobj->parent);
/* join kset if set, use it as parent if we do not already have one */
if (kobj->kset) {
if (!parent)
parent = kobject_get(&kobj->kset->kobj);
kobj_kset_join(kobj);
kobj->parent = parent;
}
pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n",
kobject_name(kobj), kobj, __func__,
parent ? kobject_name(parent) : "<NULL>",
kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>");
error = create_dir(kobj);
if (error) {
kobj_kset_leave(kobj);
kobject_put(parent);
kobj->parent = NULL;
/* be noisy on error issues */
if (error == -EEXIST)
pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
__func__, kobject_name(kobj));
else
pr_err("%s failed for %s (error: %d parent: %s)\n",
__func__, kobject_name(kobj), error,
parent ? kobject_name(parent) : "'none'");
} else
kobj->state_in_sysfs = 1;
return error;
}
/**
* kobject_set_name_vargs() - Set the name of a kobject.
* @kobj: struct kobject to set the name of
* @fmt: format string used to build the name
* @vargs: vargs to format the string.
*/
int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
va_list vargs)
{
const char *s;
if (kobj->name && !fmt)
return 0;
s = kvasprintf_const(GFP_KERNEL, fmt, vargs);
if (!s)
return -ENOMEM;
/*
* ewww... some of these buggers have '/' in the name ... If
* that's the case, we need to make sure we have an actual
* allocated copy to modify, since kvasprintf_const may have
* returned something from .rodata.
*/
if (strchr(s, '/')) {
char *t;
t = kstrdup(s, GFP_KERNEL);
kfree_const(s);
if (!t)
return -ENOMEM;
s = strreplace(t, '/', '!');
}
kfree_const(kobj->name);
kobj->name = s;
return 0;
}
/**
* kobject_set_name() - Set the name of a kobject.
* @kobj: struct kobject to set the name of
* @fmt: format string used to build the name
*
* This sets the name of the kobject. If you have already added the
* kobject to the system, you must call kobject_rename() in order to
* change the name of the kobject.
*/
int kobject_set_name(struct kobject *kobj, const char *fmt, ...)
{
va_list vargs;
int retval;
va_start(vargs, fmt);
retval = kobject_set_name_vargs(kobj, fmt, vargs);
va_end(vargs);
return retval;
}
EXPORT_SYMBOL(kobject_set_name);
/**
* kobject_init() - Initialize a kobject structure.
* @kobj: pointer to the kobject to initialize
* @ktype: pointer to the ktype for this kobject.
*
* This function will properly initialize a kobject such that it can then
* be passed to the kobject_add() call.
*
* After this function is called, the kobject MUST be cleaned up by a call
* to kobject_put(), not by a call to kfree directly to ensure that all of
* the memory is cleaned up properly.
*/
void kobject_init(struct kobject *kobj, const struct kobj_type *ktype)
{
char *err_str;
if (!kobj) {
err_str = "invalid kobject pointer!";
goto error;
}
if (!ktype) {
err_str = "must have a ktype to be initialized properly!\n";
goto error;
}
if (kobj->state_initialized) {
/* do not error out as sometimes we can recover */
pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n",
kobj);
dump_stack_lvl(KERN_ERR);
}
kobject_init_internal(kobj);
kobj->ktype = ktype;
return;
error:
pr_err("kobject (%p): %s\n", kobj, err_str);
dump_stack_lvl(KERN_ERR);
}
EXPORT_SYMBOL(kobject_init);
static __printf(3, 0) int kobject_add_varg(struct kobject *kobj,
struct kobject *parent,
const char *fmt, va_list vargs)
{
int retval;
retval = kobject_set_name_vargs(kobj, fmt, vargs);
if (retval) {
pr_err("can not set name properly!\n");
return retval;
}
kobj->parent = parent;
return kobject_add_internal(kobj);
}
/**
* kobject_add() - The main kobject add function.
* @kobj: the kobject to add
* @parent: pointer to the parent of the kobject.
* @fmt: format to name the kobject with.
*
* The kobject name is set and added to the kobject hierarchy in this
* function.
*
* If @parent is set, then the parent of the @kobj will be set to it.
* If @parent is NULL, then the parent of the @kobj will be set to the
* kobject associated with the kset assigned to this kobject. If no kset
* is assigned to the kobject, then the kobject will be located in the
* root of the sysfs tree.
*
* Note, no "add" uevent will be created with this call, the caller should set
* up all of the necessary sysfs files for the object and then call
* kobject_uevent() with the UEVENT_ADD parameter to ensure that
* userspace is properly notified of this kobject's creation.
*
* Return: If this function returns an error, kobject_put() must be
* called to properly clean up the memory associated with the
* object. Under no instance should the kobject that is passed
* to this function be directly freed with a call to kfree(),
* that can leak memory.
*
* If this function returns success, kobject_put() must also be called
* in order to properly clean up the memory associated with the object.
*
* In short, once this function is called, kobject_put() MUST be called
* when the use of the object is finished in order to properly free
* everything.
*/
int kobject_add(struct kobject *kobj, struct kobject *parent,
const char *fmt, ...)
{
va_list args;
int retval;
if (!kobj)
return -EINVAL;
if (!kobj->state_initialized) {
pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n",
kobject_name(kobj), kobj);
dump_stack_lvl(KERN_ERR);
return -EINVAL;
}
va_start(args, fmt);
retval = kobject_add_varg(kobj, parent, fmt, args);
va_end(args);
return retval;
}
EXPORT_SYMBOL(kobject_add);
/**
* kobject_init_and_add() - Initialize a kobject structure and add it to
* the kobject hierarchy.
* @kobj: pointer to the kobject to initialize
* @ktype: pointer to the ktype for this kobject.
* @parent: pointer to the parent of this kobject.
* @fmt: the name of the kobject.
*
* This function combines the call to kobject_init() and kobject_add().
*
* If this function returns an error, kobject_put() must be called to
* properly clean up the memory associated with the object. This is the
* same type of error handling after a call to kobject_add() and kobject
* lifetime rules are the same here.
*/
int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype,
struct kobject *parent, const char *fmt, ...)
{
va_list args;
int retval;
kobject_init(kobj, ktype);
va_start(args, fmt);
retval = kobject_add_varg(kobj, parent, fmt, args);
va_end(args);
return retval;
}
EXPORT_SYMBOL_GPL(kobject_init_and_add);
/**
* kobject_rename() - Change the name of an object.
* @kobj: object in question.
* @new_name: object's new name
*
* It is the responsibility of the caller to provide mutual
* exclusion between two different calls of kobject_rename
* on the same kobject and to ensure that new_name is valid and
* won't conflict with other kobjects.
*/
int kobject_rename(struct kobject *kobj, const char *new_name)
{
int error = 0;
const char *devpath = NULL;
const char *dup_name = NULL, *name;
char *devpath_string = NULL;
char *envp[2];
kobj = kobject_get(kobj);
if (!kobj)
return -EINVAL;
if (!kobj->parent) {
kobject_put(kobj);
return -EINVAL;
}
devpath = kobject_get_path(kobj, GFP_KERNEL);
if (!devpath) {
error = -ENOMEM;
goto out;
}
devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL);
if (!devpath_string) {
error = -ENOMEM;
goto out;
}
sprintf(devpath_string, "DEVPATH_OLD=%s", devpath);
envp[0] = devpath_string;
envp[1] = NULL;
name = dup_name = kstrdup_const(new_name, GFP_KERNEL);
if (!name) {
error = -ENOMEM;
goto out;
}
error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj));
if (error)
goto out;
/* Install the new kobject name */
dup_name = kobj->name;
kobj->name = name;
/* This function is mostly/only used for network interface.
* Some hotplug package track interfaces by their name and
* therefore want to know when the name is changed by the user. */
kobject_uevent_env(kobj, KOBJ_MOVE, envp);
out:
kfree_const(dup_name);
kfree(devpath_string);
kfree(devpath);
kobject_put(kobj);
return error;
}
EXPORT_SYMBOL_GPL(kobject_rename);
/**
* kobject_move() - Move object to another parent.
* @kobj: object in question.
* @new_parent: object's new parent (can be NULL)
*/
int kobject_move(struct kobject *kobj, struct kobject *new_parent)
{
int error;
struct kobject *old_parent;
const char *devpath = NULL;
char *devpath_string = NULL;
char *envp[2];
kobj = kobject_get(kobj);
if (!kobj)
return -EINVAL;
new_parent = kobject_get(new_parent);
if (!new_parent) {
if (kobj->kset)
new_parent = kobject_get(&kobj->kset->kobj);
}
/* old object path */
devpath = kobject_get_path(kobj, GFP_KERNEL);
if (!devpath) {
error = -ENOMEM;
goto out;
}
devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL);
if (!devpath_string) {
error = -ENOMEM;
goto out;
}
sprintf(devpath_string, "DEVPATH_OLD=%s", devpath);
envp[0] = devpath_string;
envp[1] = NULL;
error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj));
if (error)
goto out;
old_parent = kobj->parent;
kobj->parent = new_parent;
new_parent = NULL;
kobject_put(old_parent);
kobject_uevent_env(kobj, KOBJ_MOVE, envp);
out:
kobject_put(new_parent);
kobject_put(kobj);
kfree(devpath_string);
kfree(devpath);
return error;
}
EXPORT_SYMBOL_GPL(kobject_move);
static void __kobject_del(struct kobject *kobj)
{
struct kernfs_node *sd;
const struct kobj_type *ktype;
sd = kobj->sd;
ktype = get_ktype(kobj);
if (ktype)
sysfs_remove_groups(kobj, ktype->default_groups);
/* send "remove" if the caller did not do it but sent "add" */
if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
pr_debug("'%s' (%p): auto cleanup 'remove' event\n",
kobject_name(kobj), kobj);
kobject_uevent(kobj, KOBJ_REMOVE);
}
sysfs_remove_dir(kobj);
sysfs_put(sd);
kobj->state_in_sysfs = 0;
kobj_kset_leave(kobj);
kobj->parent = NULL;
}
/**
* kobject_del() - Unlink kobject from hierarchy.
* @kobj: object.
*
* This is the function that should be called to delete an object
* successfully added via kobject_add().
*/
void kobject_del(struct kobject *kobj)
{
struct kobject *parent;
if (!kobj)
return;
parent = kobj->parent;
__kobject_del(kobj);
kobject_put(parent);
}
EXPORT_SYMBOL(kobject_del);
/**
* kobject_get() - Increment refcount for object.
* @kobj: object.
*/
struct kobject *kobject_get(struct kobject *kobj)
{
if (kobj) {
if (!kobj->state_initialized)
WARN(1, KERN_WARNING
"kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n",
kobject_name(kobj), kobj);
kref_get(&kobj->kref);
}
return kobj;
}
EXPORT_SYMBOL(kobject_get);
struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj)
{ if (!kobj)
return NULL;
if (!kref_get_unless_zero(&kobj->kref))
kobj = NULL;
return kobj;
}
EXPORT_SYMBOL(kobject_get_unless_zero);
/*
* kobject_cleanup - free kobject resources.
* @kobj: object to cleanup
*/
static void kobject_cleanup(struct kobject *kobj)
{
struct kobject *parent = kobj->parent;
const struct kobj_type *t = get_ktype(kobj);
const char *name = kobj->name;
pr_debug("'%s' (%p): %s, parent %p\n",
kobject_name(kobj), kobj, __func__, kobj->parent);
if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
kobject_name(kobj), kobj);
/* remove from sysfs if the caller did not do it */
if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n",
kobject_name(kobj), kobj);
__kobject_del(kobj);
} else {
/* avoid dropping the parent reference unnecessarily */
parent = NULL;
}
if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n",
kobject_name(kobj), kobj);
t->release(kobj);
}
/* free name if we allocated it */
if (name) { pr_debug("'%s': free name\n", name);
kfree_const(name);
}
kobject_put(parent);
}
#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
static void kobject_delayed_cleanup(struct work_struct *work)
{
kobject_cleanup(container_of(to_delayed_work(work),
struct kobject, release));
}
#endif
static void kobject_release(struct kref *kref)
{
struct kobject *kobj = container_of(kref, struct kobject, kref);
#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
unsigned long delay = HZ + HZ * get_random_u32_below(4);
pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n",
kobject_name(kobj), kobj, __func__, kobj->parent, delay);
INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup);
schedule_delayed_work(&kobj->release, delay);
#else
kobject_cleanup(kobj);
#endif
}
/**
* kobject_put() - Decrement refcount for object.
* @kobj: object.
*
* Decrement the refcount, and if 0, call kobject_cleanup().
*/
void kobject_put(struct kobject *kobj)
{ if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING
"kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n",
kobject_name(kobj), kobj);
kref_put(&kobj->kref, kobject_release);
}
}
EXPORT_SYMBOL(kobject_put);
static void dynamic_kobj_release(struct kobject *kobj)
{
pr_debug("(%p): %s\n", kobj, __func__);
kfree(kobj);
}
static const struct kobj_type dynamic_kobj_ktype = {
.release = dynamic_kobj_release,
.sysfs_ops = &kobj_sysfs_ops,
};
/**
* kobject_create() - Create a struct kobject dynamically.
*
* This function creates a kobject structure dynamically and sets it up
* to be a "dynamic" kobject with a default release function set up.
*
* If the kobject was not able to be created, NULL will be returned.
* The kobject structure returned from here must be cleaned up with a
* call to kobject_put() and not kfree(), as kobject_init() has
* already been called on this structure.
*/
static struct kobject *kobject_create(void)
{
struct kobject *kobj;
kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
if (!kobj)
return NULL;
kobject_init(kobj, &dynamic_kobj_ktype);
return kobj;
}
/**
* kobject_create_and_add() - Create a struct kobject dynamically and
* register it with sysfs.
* @name: the name for the kobject
* @parent: the parent kobject of this kobject, if any.
*
* This function creates a kobject structure dynamically and registers it
* with sysfs. When you are finished with this structure, call
* kobject_put() and the structure will be dynamically freed when
* it is no longer being used.
*
* If the kobject was not able to be created, NULL will be returned.
*/
struct kobject *kobject_create_and_add(const char *name, struct kobject *parent)
{
struct kobject *kobj;
int retval;
kobj = kobject_create();
if (!kobj)
return NULL;
retval = kobject_add(kobj, parent, "%s", name);
if (retval) {
pr_warn("%s: kobject_add error: %d\n", __func__, retval);
kobject_put(kobj);
kobj = NULL;
}
return kobj;
}
EXPORT_SYMBOL_GPL(kobject_create_and_add);
/**
* kset_init() - Initialize a kset for use.
* @k: kset
*/
void kset_init(struct kset *k)
{
kobject_init_internal(&k->kobj);
INIT_LIST_HEAD(&k->list);
spin_lock_init(&k->list_lock);
}
/* default kobject attribute operations */
static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct kobj_attribute *kattr;
ssize_t ret = -EIO;
kattr = container_of(attr, struct kobj_attribute, attr);
if (kattr->show)
ret = kattr->show(kobj, kattr, buf);
return ret;
}
static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct kobj_attribute *kattr;
ssize_t ret = -EIO;
kattr = container_of(attr, struct kobj_attribute, attr);
if (kattr->store)
ret = kattr->store(kobj, kattr, buf, count);
return ret;
}
const struct sysfs_ops kobj_sysfs_ops = {
.show = kobj_attr_show,
.store = kobj_attr_store,
};
EXPORT_SYMBOL_GPL(kobj_sysfs_ops);
/**
* kset_register() - Initialize and add a kset.
* @k: kset.
*
* NOTE: On error, the kset.kobj.name allocated by() kobj_set_name()
* is freed, it can not be used any more.
*/
int kset_register(struct kset *k)
{
int err;
if (!k)
return -EINVAL;
if (!k->kobj.ktype) {
pr_err("must have a ktype to be initialized properly!\n");
return -EINVAL;
}
kset_init(k);
err = kobject_add_internal(&k->kobj);
if (err) {
kfree_const(k->kobj.name);
/* Set it to NULL to avoid accessing bad pointer in callers. */
k->kobj.name = NULL;
return err;
}
kobject_uevent(&k->kobj, KOBJ_ADD);
return 0;
}
EXPORT_SYMBOL(kset_register);
/**
* kset_unregister() - Remove a kset.
* @k: kset.
*/
void kset_unregister(struct kset *k)
{
if (!k)
return;
kobject_del(&k->kobj);
kobject_put(&k->kobj);
}
EXPORT_SYMBOL(kset_unregister);
/**
* kset_find_obj() - Search for object in kset.
* @kset: kset we're looking in.
* @name: object's name.
*
* Lock kset via @kset->subsys, and iterate over @kset->list,
* looking for a matching kobject. If matching object is found
* take a reference and return the object.
*/
struct kobject *kset_find_obj(struct kset *kset, const char *name)
{
struct kobject *k;
struct kobject *ret = NULL;
spin_lock(&kset->list_lock);
list_for_each_entry(k, &kset->list, entry) {
if (kobject_name(k) && !strcmp(kobject_name(k), name)) {
ret = kobject_get_unless_zero(k);
break;
}
}
spin_unlock(&kset->list_lock);
return ret;
}
EXPORT_SYMBOL_GPL(kset_find_obj);
static void kset_release(struct kobject *kobj)
{
struct kset *kset = container_of(kobj, struct kset, kobj);
pr_debug("'%s' (%p): %s\n",
kobject_name(kobj), kobj, __func__);
kfree(kset);
}
static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid)
{
if (kobj->parent)
kobject_get_ownership(kobj->parent, uid, gid);
}
static const struct kobj_type kset_ktype = {
.sysfs_ops = &kobj_sysfs_ops,
.release = kset_release,
.get_ownership = kset_get_ownership,
};
/**
* kset_create() - Create a struct kset dynamically.
*
* @name: the name for the kset
* @uevent_ops: a struct kset_uevent_ops for the kset
* @parent_kobj: the parent kobject of this kset, if any.
*
* This function creates a kset structure dynamically. This structure can
* then be registered with the system and show up in sysfs with a call to
* kset_register(). When you are finished with this structure, if
* kset_register() has been called, call kset_unregister() and the
* structure will be dynamically freed when it is no longer being used.
*
* If the kset was not able to be created, NULL will be returned.
*/
static struct kset *kset_create(const char *name,
const struct kset_uevent_ops *uevent_ops,
struct kobject *parent_kobj)
{
struct kset *kset;
int retval;
kset = kzalloc(sizeof(*kset), GFP_KERNEL);
if (!kset)
return NULL;
retval = kobject_set_name(&kset->kobj, "%s", name);
if (retval) {
kfree(kset);
return NULL;
}
kset->uevent_ops = uevent_ops;
kset->kobj.parent = parent_kobj;
/*
* The kobject of this kset will have a type of kset_ktype and belong to
* no kset itself. That way we can properly free it when it is
* finished being used.
*/
kset->kobj.ktype = &kset_ktype;
kset->kobj.kset = NULL;
return kset;
}
/**
* kset_create_and_add() - Create a struct kset dynamically and add it to sysfs.
*
* @name: the name for the kset
* @uevent_ops: a struct kset_uevent_ops for the kset
* @parent_kobj: the parent kobject of this kset, if any.
*
* This function creates a kset structure dynamically and registers it
* with sysfs. When you are finished with this structure, call
* kset_unregister() and the structure will be dynamically freed when it
* is no longer being used.
*
* If the kset was not able to be created, NULL will be returned.
*/
struct kset *kset_create_and_add(const char *name,
const struct kset_uevent_ops *uevent_ops,
struct kobject *parent_kobj)
{
struct kset *kset;
int error;
kset = kset_create(name, uevent_ops, parent_kobj);
if (!kset)
return NULL;
error = kset_register(kset);
if (error) {
kfree(kset);
return NULL;
}
return kset;
}
EXPORT_SYMBOL_GPL(kset_create_and_add);
static DEFINE_SPINLOCK(kobj_ns_type_lock);
static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES];
int kobj_ns_type_register(const struct kobj_ns_type_operations *ops)
{
enum kobj_ns_type type = ops->type;
int error;
spin_lock(&kobj_ns_type_lock);
error = -EINVAL;
if (!kobj_ns_type_is_valid(type))
goto out;
error = -EBUSY;
if (kobj_ns_ops_tbl[type])
goto out;
error = 0;
kobj_ns_ops_tbl[type] = ops;
out:
spin_unlock(&kobj_ns_type_lock);
return error;
}
int kobj_ns_type_registered(enum kobj_ns_type type)
{
int registered = 0;
spin_lock(&kobj_ns_type_lock);
if (kobj_ns_type_is_valid(type))
registered = kobj_ns_ops_tbl[type] != NULL;
spin_unlock(&kobj_ns_type_lock);
return registered;
}
const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent)
{
const struct kobj_ns_type_operations *ops = NULL;
if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent);
return ops;
}
const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj)
{ return kobj_child_ns_ops(kobj->parent);
}
bool kobj_ns_current_may_mount(enum kobj_ns_type type)
{
bool may_mount = true;
spin_lock(&kobj_ns_type_lock);
if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type])
may_mount = kobj_ns_ops_tbl[type]->current_may_mount();
spin_unlock(&kobj_ns_type_lock);
return may_mount;
}
void *kobj_ns_grab_current(enum kobj_ns_type type)
{
void *ns = NULL;
spin_lock(&kobj_ns_type_lock);
if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type])
ns = kobj_ns_ops_tbl[type]->grab_current_ns();
spin_unlock(&kobj_ns_type_lock);
return ns;
}
EXPORT_SYMBOL_GPL(kobj_ns_grab_current);
void kobj_ns_drop(enum kobj_ns_type type, void *ns)
{
spin_lock(&kobj_ns_type_lock);
if (kobj_ns_type_is_valid(type) &&
kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns)
kobj_ns_ops_tbl[type]->drop_ns(ns);
spin_unlock(&kobj_ns_type_lock);
}
EXPORT_SYMBOL_GPL(kobj_ns_drop);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KERNEL_PRINTK__
#define __KERNEL_PRINTK__
#include <linux/stdarg.h>
#include <linux/init.h>
#include <linux/kern_levels.h>
#include <linux/linkage.h>
#include <linux/ratelimit_types.h>
#include <linux/once_lite.h>
struct console;
extern const char linux_banner[];
extern const char linux_proc_banner[];
extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */
#define PRINTK_MAX_SINGLE_HEADER_LEN 2
static inline int printk_get_level(const char *buffer)
{
if (buffer[0] == KERN_SOH_ASCII && buffer[1]) {
switch (buffer[1]) {
case '0' ... '7':
case 'c': /* KERN_CONT */
return buffer[1];
}
}
return 0;
}
static inline const char *printk_skip_level(const char *buffer)
{
if (printk_get_level(buffer))
return buffer + 2;
return buffer;
}
static inline const char *printk_skip_headers(const char *buffer)
{
while (printk_get_level(buffer))
buffer = printk_skip_level(buffer);
return buffer;
}
/* printk's without a loglevel use this.. */
#define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT
/* We show everything that is MORE important than this.. */
#define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */
#define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */
#define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */
#define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */
/*
* Default used to be hard-coded at 7, quiet used to be hardcoded at 4,
* we're now allowing both to be set from kernel config.
*/
#define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT
#define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET
int match_devname_and_update_preferred_console(const char *match,
const char *name,
const short idx);
extern int console_printk[];
#define console_loglevel (console_printk[0])
#define default_message_loglevel (console_printk[1])
#define minimum_console_loglevel (console_printk[2])
#define default_console_loglevel (console_printk[3])
extern void console_verbose(void);
/* strlen("ratelimit") + 1 */
#define DEVKMSG_STR_MAX_SIZE 10
extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE];
struct ctl_table;
extern int suppress_printk;
struct va_format {
const char *fmt;
va_list *va;
};
/*
* FW_BUG
* Add this to a message where you are sure the firmware is buggy or behaves
* really stupid or out of spec. Be aware that the responsible BIOS developer
* should be able to fix this issue or at least get a concrete idea of the
* problem by reading your message without the need of looking at the kernel
* code.
*
* Use it for definite and high priority BIOS bugs.
*
* FW_WARN
* Use it for not that clear (e.g. could the kernel messed up things already?)
* and medium priority BIOS bugs.
*
* FW_INFO
* Use this one if you want to tell the user or vendor about something
* suspicious, but generally harmless related to the firmware.
*
* Use it for information or very low priority BIOS bugs.
*/
#define FW_BUG "[Firmware Bug]: "
#define FW_WARN "[Firmware Warn]: "
#define FW_INFO "[Firmware Info]: "
/*
* HW_ERR
* Add this to a message for hardware errors, so that user can report
* it to hardware vendor instead of LKML or software vendor.
*/
#define HW_ERR "[Hardware Error]: "
/*
* DEPRECATED
* Add this to a message whenever you want to warn user space about the use
* of a deprecated aspect of an API so they can stop using it
*/
#define DEPRECATED "[Deprecated]: "
/*
* Dummy printk for disabled debugging statements to use whilst maintaining
* gcc's format checking.
*/
#define no_printk(fmt, ...) \
({ \
if (0) \
_printk(fmt, ##__VA_ARGS__); \
0; \
})
#ifdef CONFIG_EARLY_PRINTK
extern asmlinkage __printf(1, 2)
void early_printk(const char *fmt, ...);
#else
static inline __printf(1, 2) __cold
void early_printk(const char *s, ...) { }
#endif
struct dev_printk_info;
#ifdef CONFIG_PRINTK
asmlinkage __printf(4, 0)
int vprintk_emit(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args);
asmlinkage __printf(1, 0)
int vprintk(const char *fmt, va_list args);
asmlinkage __printf(1, 2) __cold
int _printk(const char *fmt, ...);
/*
* Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
*/
__printf(1, 2) __cold int _printk_deferred(const char *fmt, ...);
extern void __printk_deferred_enter(void);
extern void __printk_deferred_exit(void);
extern void printk_force_console_enter(void);
extern void printk_force_console_exit(void);
/*
* The printk_deferred_enter/exit macros are available only as a hack for
* some code paths that need to defer all printk console printing. Interrupts
* must be disabled for the deferred duration.
*/
#define printk_deferred_enter() __printk_deferred_enter()
#define printk_deferred_exit() __printk_deferred_exit()
/*
* Please don't use printk_ratelimit(), because it shares ratelimiting state
* with all other unrelated printk_ratelimit() callsites. Instead use
* printk_ratelimited() or plain old __ratelimit().
*/
extern int __printk_ratelimit(const char *func);
#define printk_ratelimit() __printk_ratelimit(__func__)
extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec);
extern int printk_delay_msec;
extern int dmesg_restrict;
extern void wake_up_klogd(void);
char *log_buf_addr_get(void);
u32 log_buf_len_get(void);
void log_buf_vmcoreinfo_setup(void);
void __init setup_log_buf(int early);
__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
void dump_stack_print_info(const char *log_lvl);
void show_regs_print_info(const char *log_lvl);
extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
extern asmlinkage void dump_stack(void) __cold;
void printk_trigger_flush(void);
void console_try_replay_all(void);
void printk_legacy_allow_panic_sync(void);
extern bool nbcon_device_try_acquire(struct console *con);
extern void nbcon_device_release(struct console *con);
void nbcon_atomic_flush_unsafe(void);
bool pr_flush(int timeout_ms, bool reset_on_progress);
#else
static inline __printf(1, 0)
int vprintk(const char *s, va_list args)
{
return 0;
}
static inline __printf(1, 2) __cold
int _printk(const char *s, ...)
{
return 0;
}
static inline __printf(1, 2) __cold
int _printk_deferred(const char *s, ...)
{
return 0;
}
static inline void printk_deferred_enter(void)
{
}
static inline void printk_deferred_exit(void)
{
}
static inline void printk_force_console_enter(void)
{
}
static inline void printk_force_console_exit(void)
{
}
static inline int printk_ratelimit(void)
{
return 0;
}
static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec)
{
return false;
}
static inline void wake_up_klogd(void)
{
}
static inline char *log_buf_addr_get(void)
{
return NULL;
}
static inline u32 log_buf_len_get(void)
{
return 0;
}
static inline void log_buf_vmcoreinfo_setup(void)
{
}
static inline void setup_log_buf(int early)
{
}
static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...)
{
}
static inline void dump_stack_print_info(const char *log_lvl)
{
}
static inline void show_regs_print_info(const char *log_lvl)
{
}
static inline void dump_stack_lvl(const char *log_lvl)
{
}
static inline void dump_stack(void)
{
}
static inline void printk_trigger_flush(void)
{
}
static inline void console_try_replay_all(void)
{
}
static inline void printk_legacy_allow_panic_sync(void)
{
}
static inline bool nbcon_device_try_acquire(struct console *con)
{
return false;
}
static inline void nbcon_device_release(struct console *con)
{
}
static inline void nbcon_atomic_flush_unsafe(void)
{
}
static inline bool pr_flush(int timeout_ms, bool reset_on_progress)
{
return true;
}
#endif
bool this_cpu_in_panic(void);
#ifdef CONFIG_SMP
extern int __printk_cpu_sync_try_get(void);
extern void __printk_cpu_sync_wait(void);
extern void __printk_cpu_sync_put(void);
#else
#define __printk_cpu_sync_try_get() true
#define __printk_cpu_sync_wait()
#define __printk_cpu_sync_put()
#endif /* CONFIG_SMP */
/**
* printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk
* cpu-reentrant spinning lock.
* @flags: Stack-allocated storage for saving local interrupt state,
* to be passed to printk_cpu_sync_put_irqrestore().
*
* If the lock is owned by another CPU, spin until it becomes available.
* Interrupts are restored while spinning.
*
* CAUTION: This function must be used carefully. It does not behave like a
* typical lock. Here are important things to watch out for...
*
* * This function is reentrant on the same CPU. Therefore the calling
* code must not assume exclusive access to data if code accessing the
* data can run reentrant or within NMI context on the same CPU.
*
* * If there exists usage of this function from NMI context, it becomes
* unsafe to perform any type of locking or spinning to wait for other
* CPUs after calling this function from any context. This includes
* using spinlocks or any other busy-waiting synchronization methods.
*/
#define printk_cpu_sync_get_irqsave(flags) \
for (;;) { \
local_irq_save(flags); \
if (__printk_cpu_sync_try_get()) \
break; \
local_irq_restore(flags); \
__printk_cpu_sync_wait(); \
}
/**
* printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning
* lock and restore interrupts.
* @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave().
*/
#define printk_cpu_sync_put_irqrestore(flags) \
do { \
__printk_cpu_sync_put(); \
local_irq_restore(flags); \
} while (0)
extern int kptr_restrict;
/**
* pr_fmt - used by the pr_*() macros to generate the printk format string
* @fmt: format string passed from a pr_*() macro
*
* This macro can be used to generate a unified format string for pr_*()
* macros. A common use is to prefix all pr_*() messages in a file with a common
* string. For example, defining this at the top of a source file:
*
* #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
*
* would prefix all pr_info, pr_emerg... messages in the file with the module
* name.
*/
#ifndef pr_fmt
#define pr_fmt(fmt) fmt
#endif
struct module;
#ifdef CONFIG_PRINTK_INDEX
struct pi_entry {
const char *fmt;
const char *func;
const char *file;
unsigned int line;
/*
* While printk and pr_* have the level stored in the string at compile
* time, some subsystems dynamically add it at runtime through the
* format string. For these dynamic cases, we allow the subsystem to
* tell us the level at compile time.
*
* NULL indicates that the level, if any, is stored in fmt.
*/
const char *level;
/*
* The format string used by various subsystem specific printk()
* wrappers to prefix the message.
*
* Note that the static prefix defined by the pr_fmt() macro is stored
* directly in the message format (@fmt), not here.
*/
const char *subsys_fmt_prefix;
} __packed;
#define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \
do { \
if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \
/*
* We check __builtin_constant_p multiple times here
* for the same input because GCC will produce an error
* if we try to assign a static variable to fmt if it
* is not a constant, even with the outer if statement.
*/ \
static const struct pi_entry _entry \
__used = { \
.fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \
.func = __func__, \
.file = __FILE__, \
.line = __LINE__, \
.level = __builtin_constant_p(_level) ? (_level) : NULL, \
.subsys_fmt_prefix = _subsys_fmt_prefix,\
}; \
static const struct pi_entry *_entry_ptr \
__used __section(".printk_index") = &_entry; \
} \
} while (0)
#else /* !CONFIG_PRINTK_INDEX */
#define __printk_index_emit(...) do {} while (0)
#endif /* CONFIG_PRINTK_INDEX */
/*
* Some subsystems have their own custom printk that applies a va_format to a
* generic format, for example, to include a device number or other metadata
* alongside the format supplied by the caller.
*
* In order to store these in the way they would be emitted by the printk
* infrastructure, the subsystem provides us with the start, fixed string, and
* any subsequent text in the format string.
*
* We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed
* as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the
* first one.
*
* subsys_fmt_prefix must be known at compile time, or compilation will fail
* (since this is a mistake). If fmt or level is not known at compile time, no
* index entry will be made (since this can legitimately happen).
*/
#define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \
__printk_index_emit(fmt, level, subsys_fmt_prefix)
#define printk_index_wrap(_p_func, _fmt, ...) \
({ \
__printk_index_emit(_fmt, NULL, NULL); \
_p_func(_fmt, ##__VA_ARGS__); \
})
/**
* printk - print a kernel message
* @fmt: format string
*
* This is printk(). It can be called from any context. We want it to work.
*
* If printk indexing is enabled, _printk() is called from printk_index_wrap.
* Otherwise, printk is simply #defined to _printk.
*
* We try to grab the console_lock. If we succeed, it's easy - we log the
* output and call the console drivers. If we fail to get the semaphore, we
* place the output into the log buffer and return. The current holder of
* the console_sem will notice the new output in console_unlock(); and will
* send it to the consoles before releasing the lock.
*
* One effect of this deferred printing is that code which calls printk() and
* then changes console_loglevel may break. This is because console_loglevel
* is inspected when the actual printing occurs.
*
* See also:
* printf(3)
*
* See the vsnprintf() documentation for format string extensions over C99.
*/
#define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__)
#define printk_deferred(fmt, ...) \
printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__)
/**
* pr_emerg - Print an emergency-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_emerg(fmt, ...) \
printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_alert - Print an alert-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_alert(fmt, ...) \
printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_crit - Print a critical-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_crit(fmt, ...) \
printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_err - Print an error-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_err(fmt, ...) \
printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_warn - Print a warning-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt()
* to generate the format string.
*/
#define pr_warn(fmt, ...) \
printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_notice - Print a notice-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_notice(fmt, ...) \
printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_info - Print an info-level message
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to
* generate the format string.
*/
#define pr_info(fmt, ...) \
printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/**
* pr_cont - Continues a previous log message in the same line.
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_CONT loglevel. It should only be
* used when continuing a log message with no newline ('\n') enclosed. Otherwise
* it defaults back to KERN_DEFAULT loglevel.
*/
#define pr_cont(fmt, ...) \
printk(KERN_CONT fmt, ##__VA_ARGS__)
/**
* pr_devel - Print a debug-level message conditionally
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is
* defined. Otherwise it does nothing.
*
* It uses pr_fmt() to generate the format string.
*/
#ifdef DEBUG
#define pr_devel(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#include <linux/dynamic_debug.h>
/**
* pr_debug - Print a debug-level message conditionally
* @fmt: format string
* @...: arguments for the format string
*
* This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is
* set. Otherwise, if DEBUG is defined, it's equivalent to a printk with
* KERN_DEBUG loglevel. If DEBUG is not defined it does nothing.
*
* It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses
* pr_fmt() internally).
*/
#define pr_debug(fmt, ...) \
dynamic_pr_debug(fmt, ##__VA_ARGS__)
#elif defined(DEBUG)
#define pr_debug(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/*
* Print a one-time message (analogous to WARN_ONCE() et al):
*/
#ifdef CONFIG_PRINTK
#define printk_once(fmt, ...) \
DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__)
#define printk_deferred_once(fmt, ...) \
DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__)
#else
#define printk_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#define printk_deferred_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#endif
#define pr_emerg_once(fmt, ...) \
printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert_once(fmt, ...) \
printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit_once(fmt, ...) \
printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err_once(fmt, ...) \
printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warn_once(fmt, ...) \
printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_notice_once(fmt, ...) \
printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info_once(fmt, ...) \
printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/* no pr_cont_once, don't do that... */
#if defined(DEBUG)
#define pr_devel_once(fmt, ...) \
printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel_once(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(DEBUG)
#define pr_debug_once(fmt, ...) \
printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug_once(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/*
* ratelimited messages with local ratelimit_state,
* no local ratelimit_state used in the !PRINTK case
*/
#ifdef CONFIG_PRINTK
#define printk_ratelimited(fmt, ...) \
({ \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
\
if (__ratelimit(&_rs)) \
printk(fmt, ##__VA_ARGS__); \
})
#else
#define printk_ratelimited(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#endif
#define pr_emerg_ratelimited(fmt, ...) \
printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert_ratelimited(fmt, ...) \
printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit_ratelimited(fmt, ...) \
printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err_ratelimited(fmt, ...) \
printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warn_ratelimited(fmt, ...) \
printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_notice_ratelimited(fmt, ...) \
printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info_ratelimited(fmt, ...) \
printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/* no pr_cont_ratelimited, don't do that... */
#if defined(DEBUG)
#define pr_devel_ratelimited(fmt, ...) \
printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel_ratelimited(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
/* descriptor check is first to prevent flooding with "callbacks suppressed" */
#define pr_debug_ratelimited(fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \
if (DYNAMIC_DEBUG_BRANCH(descriptor) && \
__ratelimit(&_rs)) \
__dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \
} while (0)
#elif defined(DEBUG)
#define pr_debug_ratelimited(fmt, ...) \
printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug_ratelimited(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
extern const struct file_operations kmsg_fops;
enum {
DUMP_PREFIX_NONE,
DUMP_PREFIX_ADDRESS,
DUMP_PREFIX_OFFSET
};
extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
int groupsize, char *linebuf, size_t linebuflen,
bool ascii);
#ifdef CONFIG_PRINTK
extern void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii);
#else
static inline void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
}
static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
const void *buf, size_t len)
{
}
#endif
#if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii) \
dynamic_hex_dump(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii)
#elif defined(DEBUG)
#define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii) \
print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii)
#else
static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type,
int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
}
#endif
/**
* print_hex_dump_bytes - shorthand form of print_hex_dump() with default params
* @prefix_str: string to prefix each line with;
* caller supplies trailing spaces for alignment if desired
* @prefix_type: controls whether prefix of an offset, address, or none
* is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE)
* @buf: data blob to dump
* @len: number of bytes in the @buf
*
* Calls print_hex_dump(), with log level of KERN_DEBUG,
* rowsize of 16, groupsize of 1, and ASCII output included.
*/
#define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \
print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true)
#endif
// SPDX-License-Identifier: GPL-2.0-only
// Copyright (C) 2022 Linutronix GmbH, John Ogness
// Copyright (C) 2022 Intel, Thomas Gleixner
#include <linux/atomic.h>
#include <linux/bug.h>
#include <linux/console.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/irqflags.h>
#include <linux/kthread.h>
#include <linux/minmax.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/string.h>
#include <linux/types.h>
#include "internal.h"
#include "printk_ringbuffer.h"
/*
* Printk console printing implementation for consoles which does not depend
* on the legacy style console_lock mechanism.
*
* The state of the console is maintained in the "nbcon_state" atomic
* variable.
*
* The console is locked when:
*
* - The 'prio' field contains the priority of the context that owns the
* console. Only higher priority contexts are allowed to take over the
* lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked.
*
* - The 'cpu' field denotes on which CPU the console is locked. It is used
* to prevent busy waiting on the same CPU. Also it informs the lock owner
* that it has lost the lock in a more complex scenario when the lock was
* taken over by a higher priority context, released, and taken on another
* CPU with the same priority as the interrupted owner.
*
* The acquire mechanism uses a few more fields:
*
* - The 'req_prio' field is used by the handover approach to make the
* current owner aware that there is a context with a higher priority
* waiting for the friendly handover.
*
* - The 'unsafe' field allows to take over the console in a safe way in the
* middle of emitting a message. The field is set only when accessing some
* shared resources or when the console device is manipulated. It can be
* cleared, for example, after emitting one character when the console
* device is in a consistent state.
*
* - The 'unsafe_takeover' field is set when a hostile takeover took the
* console in an unsafe state. The console will stay in the unsafe state
* until re-initialized.
*
* The acquire mechanism uses three approaches:
*
* 1) Direct acquire when the console is not owned or is owned by a lower
* priority context and is in a safe state.
*
* 2) Friendly handover mechanism uses a request/grant handshake. It is used
* when the current owner has lower priority and the console is in an
* unsafe state.
*
* The requesting context:
*
* a) Sets its priority into the 'req_prio' field.
*
* b) Waits (with a timeout) for the owning context to unlock the
* console.
*
* c) Takes the lock and clears the 'req_prio' field.
*
* The owning context:
*
* a) Observes the 'req_prio' field set on exit from the unsafe
* console state.
*
* b) Gives up console ownership by clearing the 'prio' field.
*
* 3) Unsafe hostile takeover allows to take over the lock even when the
* console is an unsafe state. It is used only in panic() by the final
* attempt to flush consoles in a try and hope mode.
*
* Note that separate record buffers are used in panic(). As a result,
* the messages can be read and formatted without any risk even after
* using the hostile takeover in unsafe state.
*
* The release function simply clears the 'prio' field.
*
* All operations on @console::nbcon_state are atomic cmpxchg based to
* handle concurrency.
*
* The acquire/release functions implement only minimal policies:
*
* - Preference for higher priority contexts.
* - Protection of the panic CPU.
*
* All other policy decisions must be made at the call sites:
*
* - What is marked as an unsafe section.
* - Whether to spin-wait if there is already an owner and the console is
* in an unsafe state.
* - Whether to attempt an unsafe hostile takeover.
*
* The design allows to implement the well known:
*
* acquire()
* output_one_printk_record()
* release()
*
* The output of one printk record might be interrupted with a higher priority
* context. The new owner is supposed to reprint the entire interrupted record
* from scratch.
*/
/**
* nbcon_state_set - Helper function to set the console state
* @con: Console to update
* @new: The new state to write
*
* Only to be used when the console is not yet or no longer visible in the
* system. Otherwise use nbcon_state_try_cmpxchg().
*/
static inline void nbcon_state_set(struct console *con, struct nbcon_state *new)
{
atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom);
}
/**
* nbcon_state_read - Helper function to read the console state
* @con: Console to read
* @state: The state to store the result
*/
static inline void nbcon_state_read(struct console *con, struct nbcon_state *state)
{
state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state));
}
/**
* nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state
* @con: Console to update
* @cur: Old/expected state
* @new: New state
*
* Return: True on success. False on fail and @cur is updated.
*/
static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur,
struct nbcon_state *new)
{
return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom);
}
/**
* nbcon_seq_read - Read the current console sequence
* @con: Console to read the sequence of
*
* Return: Sequence number of the next record to print on @con.
*/
u64 nbcon_seq_read(struct console *con)
{
unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq));
return __ulseq_to_u64seq(prb, nbcon_seq);
}
/**
* nbcon_seq_force - Force console sequence to a specific value
* @con: Console to work on
* @seq: Sequence number value to set
*
* Only to be used during init (before registration) or in extreme situations
* (such as panic with CONSOLE_REPLAY_ALL).
*/
void nbcon_seq_force(struct console *con, u64 seq)
{
/*
* If the specified record no longer exists, the oldest available record
* is chosen. This is especially important on 32bit systems because only
* the lower 32 bits of the sequence number are stored. The upper 32 bits
* are derived from the sequence numbers available in the ringbuffer.
*/
u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb));
atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq));
}
/**
* nbcon_seq_try_update - Try to update the console sequence number
* @ctxt: Pointer to an acquire context that contains
* all information about the acquire mode
* @new_seq: The new sequence number to set
*
* @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to
* the 64bit value). This could be a different value than @new_seq if
* nbcon_seq_force() was used or the current context no longer owns the
* console. In the later case, it will stop printing anyway.
*/
static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq)
{
unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq);
struct console *con = ctxt->console;
if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq,
__u64seq_to_ulseq(new_seq))) {
ctxt->seq = new_seq;
} else {
ctxt->seq = nbcon_seq_read(con);
}
}
/**
* nbcon_context_try_acquire_direct - Try to acquire directly
* @ctxt: The context of the caller
* @cur: The current console state
*
* Acquire the console when it is released. Also acquire the console when
* the current owner has a lower priority and the console is in a safe state.
*
* Return: 0 on success. Otherwise, an error code on failure. Also @cur
* is updated to the latest state when failed to modify it.
*
* Errors:
*
* -EPERM: A panic is in progress and this is not the panic CPU.
* Or the current owner or waiter has the same or higher
* priority. No acquire method can be successful in
* this case.
*
* -EBUSY: The current owner has a lower priority but the console
* in an unsafe state. The caller should try using
* the handover acquire method.
*/
static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,
struct nbcon_state *cur)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state new;
do {
/*
* Panic does not imply that the console is owned. However, it
* is critical that non-panic CPUs during panic are unable to
* acquire ownership in order to satisfy the assumptions of
* nbcon_waiter_matches(). In particular, the assumption that
* lower priorities are ignored during panic.
*/
if (other_cpu_in_panic())
return -EPERM;
if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio)
return -EPERM;
if (cur->unsafe)
return -EBUSY;
/*
* The console should never be safe for a direct acquire
* if an unsafe hostile takeover has ever happened.
*/
WARN_ON_ONCE(cur->unsafe_takeover);
new.atom = cur->atom;
new.prio = ctxt->prio;
new.req_prio = NBCON_PRIO_NONE;
new.unsafe = cur->unsafe_takeover;
new.cpu = cpu;
} while (!nbcon_state_try_cmpxchg(con, cur, &new));
return 0;
}
static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio)
{
/*
* The request context is well defined by the @req_prio because:
*
* - Only a context with a priority higher than the owner can become
* a waiter.
* - Only a context with a priority higher than the waiter can
* directly take over the request.
* - There are only three priorities.
* - Only one CPU is allowed to request PANIC priority.
* - Lower priorities are ignored during panic() until reboot.
*
* As a result, the following scenario is *not* possible:
*
* 1. This context is currently a waiter.
* 2. Another context with a higher priority than this context
* directly takes ownership.
* 3. The higher priority context releases the ownership.
* 4. Another lower priority context takes the ownership.
* 5. Another context with the same priority as this context
* creates a request and starts waiting.
*
* Event #1 implies this context is EMERGENCY.
* Event #2 implies the new context is PANIC.
* Event #3 occurs when panic() has flushed the console.
* Events #4 and #5 are not possible due to the other_cpu_in_panic()
* check in nbcon_context_try_acquire_direct().
*/
return (cur->req_prio == expected_prio);
}
/**
* nbcon_context_try_acquire_requested - Try to acquire after having
* requested a handover
* @ctxt: The context of the caller
* @cur: The current console state
*
* This is a helper function for nbcon_context_try_acquire_handover().
* It is called when the console is in an unsafe state. The current
* owner will release the console on exit from the unsafe region.
*
* Return: 0 on success and @cur is updated to the new console state.
* Otherwise an error code on failure.
*
* Errors:
*
* -EPERM: A panic is in progress and this is not the panic CPU
* or this context is no longer the waiter.
*
* -EBUSY: The console is still locked. The caller should
* continue waiting.
*
* Note: The caller must still remove the request when an error has occurred
* except when this context is no longer the waiter.
*/
static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt,
struct nbcon_state *cur)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state new;
/* Note that the caller must still remove the request! */
if (other_cpu_in_panic())
return -EPERM;
/*
* Note that the waiter will also change if there was an unsafe
* hostile takeover.
*/
if (!nbcon_waiter_matches(cur, ctxt->prio))
return -EPERM;
/* If still locked, caller should continue waiting. */
if (cur->prio != NBCON_PRIO_NONE)
return -EBUSY;
/*
* The previous owner should have never released ownership
* in an unsafe region.
*/
WARN_ON_ONCE(cur->unsafe);
new.atom = cur->atom;
new.prio = ctxt->prio;
new.req_prio = NBCON_PRIO_NONE;
new.unsafe = cur->unsafe_takeover;
new.cpu = cpu;
if (!nbcon_state_try_cmpxchg(con, cur, &new)) {
/*
* The acquire could fail only when it has been taken
* over by a higher priority context.
*/
WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio));
return -EPERM;
}
/* Handover success. This context now owns the console. */
return 0;
}
/**
* nbcon_context_try_acquire_handover - Try to acquire via handover
* @ctxt: The context of the caller
* @cur: The current console state
*
* The function must be called only when the context has higher priority
* than the current owner and the console is in an unsafe state.
* It is the case when nbcon_context_try_acquire_direct() returns -EBUSY.
*
* The function sets "req_prio" field to make the current owner aware of
* the request. Then it waits until the current owner releases the console,
* or an even higher context takes over the request, or timeout expires.
*
* The current owner checks the "req_prio" field on exit from the unsafe
* region and releases the console. It does not touch the "req_prio" field
* so that the console stays reserved for the waiter.
*
* Return: 0 on success. Otherwise, an error code on failure. Also @cur
* is updated to the latest state when failed to modify it.
*
* Errors:
*
* -EPERM: A panic is in progress and this is not the panic CPU.
* Or a higher priority context has taken over the
* console or the handover request.
*
* -EBUSY: The current owner is on the same CPU so that the hand
* shake could not work. Or the current owner is not
* willing to wait (zero timeout). Or the console does
* not enter the safe state before timeout passed. The
* caller might still use the unsafe hostile takeover
* when allowed.
*
* -EAGAIN: @cur has changed when creating the handover request.
* The caller should retry with direct acquire.
*/
static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt,
struct nbcon_state *cur)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state new;
int timeout;
int request_err = -EBUSY;
/*
* Check that the handover is called when the direct acquire failed
* with -EBUSY.
*/
WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
WARN_ON_ONCE(!cur->unsafe);
/* Handover is not possible on the same CPU. */
if (cur->cpu == cpu)
return -EBUSY;
/*
* Console stays unsafe after an unsafe takeover until re-initialized.
* Waiting is not going to help in this case.
*/
if (cur->unsafe_takeover)
return -EBUSY;
/* Is the caller willing to wait? */
if (ctxt->spinwait_max_us == 0)
return -EBUSY;
/*
* Setup a request for the handover. The caller should try to acquire
* the console directly when the current state has been modified.
*/
new.atom = cur->atom;
new.req_prio = ctxt->prio;
if (!nbcon_state_try_cmpxchg(con, cur, &new))
return -EAGAIN;
cur->atom = new.atom;
/* Wait until there is no owner and then acquire the console. */
for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) {
/* On successful acquire, this request is cleared. */
request_err = nbcon_context_try_acquire_requested(ctxt, cur);
if (!request_err)
return 0;
/*
* If the acquire should be aborted, it must be ensured
* that the request is removed before returning to caller.
*/
if (request_err == -EPERM)
break;
udelay(1);
/* Re-read the state because some time has passed. */
nbcon_state_read(con, cur);
}
/* Timed out or aborted. Carefully remove handover request. */
do {
/*
* No need to remove request if there is a new waiter. This
* can only happen if a higher priority context has taken over
* the console or the handover request.
*/
if (!nbcon_waiter_matches(cur, ctxt->prio))
return -EPERM;
/* Unset request for handover. */
new.atom = cur->atom;
new.req_prio = NBCON_PRIO_NONE;
if (nbcon_state_try_cmpxchg(con, cur, &new)) {
/*
* Request successfully unset. Report failure of
* acquiring via handover.
*/
cur->atom = new.atom;
return request_err;
}
/*
* Unable to remove request. Try to acquire in case
* the owner has released the lock.
*/
} while (nbcon_context_try_acquire_requested(ctxt, cur));
/* Lucky timing. The acquire succeeded while removing the request. */
return 0;
}
/**
* nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover
* @ctxt: The context of the caller
* @cur: The current console state
*
* Acquire the console even in the unsafe state.
*
* It can be permitted by setting the 'allow_unsafe_takeover' field only
* by the final attempt to flush messages in panic().
*
* Return: 0 on success. -EPERM when not allowed by the context.
*/
static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt,
struct nbcon_state *cur)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state new;
if (!ctxt->allow_unsafe_takeover)
return -EPERM;
/* Ensure caller is allowed to perform unsafe hostile takeovers. */
if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC))
return -EPERM;
/*
* Check that try_acquire_direct() and try_acquire_handover() returned
* -EBUSY in the right situation.
*/
WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
WARN_ON_ONCE(cur->unsafe != true);
do {
new.atom = cur->atom;
new.cpu = cpu;
new.prio = ctxt->prio;
new.unsafe |= cur->unsafe_takeover;
new.unsafe_takeover |= cur->unsafe;
} while (!nbcon_state_try_cmpxchg(con, cur, &new));
return 0;
}
static struct printk_buffers panic_nbcon_pbufs;
/**
* nbcon_context_try_acquire - Try to acquire nbcon console
* @ctxt: The context of the caller
*
* Context: Under @ctxt->con->device_lock() or local_irq_save().
* Return: True if the console was acquired. False otherwise.
*
* If the caller allowed an unsafe hostile takeover, on success the
* caller should check the current console state to see if it is
* in an unsafe state. Otherwise, on success the caller may assume
* the console is not in an unsafe state.
*/
static bool nbcon_context_try_acquire(struct nbcon_context *ctxt)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state cur;
int err;
nbcon_state_read(con, &cur);
try_again:
err = nbcon_context_try_acquire_direct(ctxt, &cur);
if (err != -EBUSY)
goto out;
err = nbcon_context_try_acquire_handover(ctxt, &cur);
if (err == -EAGAIN)
goto try_again;
if (err != -EBUSY)
goto out;
err = nbcon_context_try_acquire_hostile(ctxt, &cur);
out:
if (err)
return false;
/* Acquire succeeded. */
/* Assign the appropriate buffer for this context. */
if (atomic_read(&panic_cpu) == cpu)
ctxt->pbufs = &panic_nbcon_pbufs;
else
ctxt->pbufs = con->pbufs;
/* Set the record sequence for this context to print. */
ctxt->seq = nbcon_seq_read(ctxt->console);
return true;
}
static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu,
int expected_prio)
{
/*
* A similar function, nbcon_waiter_matches(), only deals with
* EMERGENCY and PANIC priorities. However, this function must also
* deal with the NORMAL priority, which requires additional checks
* and constraints.
*
* For the case where preemption and interrupts are disabled, it is
* enough to also verify that the owning CPU has not changed.
*
* For the case where preemption or interrupts are enabled, an
* external synchronization method *must* be used. In particular,
* the driver-specific locking mechanism used in device_lock()
* (including disabling migration) should be used. It prevents
* scenarios such as:
*
* 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and
* is scheduled out.
* 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY
* and releases it.
* 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X]
* and is scheduled out.
* 4. [Task A] gets running on [CPU X] and sees that the console is
* still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus
* [Task A] thinks it is the owner when it is not.
*/
if (cur->prio != expected_prio)
return false;
if (cur->cpu != expected_cpu)
return false;
return true;
}
/**
* nbcon_context_release - Release the console
* @ctxt: The nbcon context from nbcon_context_try_acquire()
*/
static void nbcon_context_release(struct nbcon_context *ctxt)
{
unsigned int cpu = smp_processor_id();
struct console *con = ctxt->console;
struct nbcon_state cur;
struct nbcon_state new;
nbcon_state_read(con, &cur);
do {
if (!nbcon_owner_matches(&cur, cpu, ctxt->prio))
break;
new.atom = cur.atom;
new.prio = NBCON_PRIO_NONE;
/*
* If @unsafe_takeover is set, it is kept set so that
* the state remains permanently unsafe.
*/
new.unsafe |= cur.unsafe_takeover;
} while (!nbcon_state_try_cmpxchg(con, &cur, &new));
ctxt->pbufs = NULL;
}
/**
* nbcon_context_can_proceed - Check whether ownership can proceed
* @ctxt: The nbcon context from nbcon_context_try_acquire()
* @cur: The current console state
*
* Return: True if this context still owns the console. False if
* ownership was handed over or taken.
*
* Must be invoked when entering the unsafe state to make sure that it still
* owns the lock. Also must be invoked when exiting the unsafe context
* to eventually free the lock for a higher priority context which asked
* for the friendly handover.
*
* It can be called inside an unsafe section when the console is just
* temporary in safe state instead of exiting and entering the unsafe
* state.
*
* Also it can be called in the safe context before doing an expensive
* safe operation. It does not make sense to do the operation when
* a higher priority context took the lock.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context.
*/
static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur)
{
unsigned int cpu = smp_processor_id();
/* Make sure this context still owns the console. */
if (!nbcon_owner_matches(cur, cpu, ctxt->prio))
return false;
/* The console owner can proceed if there is no waiter. */
if (cur->req_prio == NBCON_PRIO_NONE)
return true;
/*
* A console owner within an unsafe region is always allowed to
* proceed, even if there are waiters. It can perform a handover
* when exiting the unsafe region. Otherwise the waiter will
* need to perform an unsafe hostile takeover.
*/
if (cur->unsafe)
return true;
/* Waiters always have higher priorities than owners. */
WARN_ON_ONCE(cur->req_prio <= cur->prio);
/*
* Having a safe point for take over and eventually a few
* duplicated characters or a full line is way better than a
* hostile takeover. Post processing can take care of the garbage.
* Release and hand over.
*/
nbcon_context_release(ctxt);
/*
* It is not clear whether the waiter really took over ownership. The
* outermost callsite must make the final decision whether console
* ownership is needed for it to proceed. If yes, it must reacquire
* ownership (possibly hostile) before carefully proceeding.
*
* The calling context no longer owns the console so go back all the
* way instead of trying to implement reacquire heuristics in tons of
* places.
*/
return false;
}
/**
* nbcon_can_proceed - Check whether ownership can proceed
* @wctxt: The write context that was handed to the write function
*
* Return: True if this context still owns the console. False if
* ownership was handed over or taken.
*
* It is used in nbcon_enter_unsafe() to make sure that it still owns the
* lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock
* for a higher priority context which asked for the friendly handover.
*
* It can be called inside an unsafe section when the console is just
* temporary in safe state instead of exiting and entering the unsafe state.
*
* Also it can be called in the safe context before doing an expensive safe
* operation. It does not make sense to do the operation when a higher
* priority context took the lock.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context.
*/
bool nbcon_can_proceed(struct nbcon_write_context *wctxt)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
struct console *con = ctxt->console;
struct nbcon_state cur;
nbcon_state_read(con, &cur);
return nbcon_context_can_proceed(ctxt, &cur);
}
EXPORT_SYMBOL_GPL(nbcon_can_proceed);
#define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true)
#define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false)
/**
* __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state
* @ctxt: The nbcon context from nbcon_context_try_acquire()
* @unsafe: The new value for the unsafe bit
*
* Return: True if the unsafe state was updated and this context still
* owns the console. Otherwise false if ownership was handed
* over or taken.
*
* This function allows console owners to modify the unsafe status of the
* console.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context.
*
* Internal helper to avoid duplicated code.
*/
static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe)
{
struct console *con = ctxt->console;
struct nbcon_state cur;
struct nbcon_state new;
nbcon_state_read(con, &cur);
do {
/*
* The unsafe bit must not be cleared if an
* unsafe hostile takeover has occurred.
*/
if (!unsafe && cur.unsafe_takeover)
goto out;
if (!nbcon_context_can_proceed(ctxt, &cur))
return false;
new.atom = cur.atom;
new.unsafe = unsafe;
} while (!nbcon_state_try_cmpxchg(con, &cur, &new));
cur.atom = new.atom;
out:
return nbcon_context_can_proceed(ctxt, &cur);
}
static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
char *buf, unsigned int len)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
struct console *con = ctxt->console;
struct nbcon_state cur;
wctxt->outbuf = buf;
wctxt->len = len;
nbcon_state_read(con, &cur);
wctxt->unsafe_takeover = cur.unsafe_takeover;
}
/**
* nbcon_enter_unsafe - Enter an unsafe region in the driver
* @wctxt: The write context that was handed to the write function
*
* Return: True if this context still owns the console. False if
* ownership was handed over or taken.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context.
*/
bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
bool is_owner;
is_owner = nbcon_context_enter_unsafe(ctxt);
if (!is_owner)
nbcon_write_context_set_buf(wctxt, NULL, 0);
return is_owner;
}
EXPORT_SYMBOL_GPL(nbcon_enter_unsafe);
/**
* nbcon_exit_unsafe - Exit an unsafe region in the driver
* @wctxt: The write context that was handed to the write function
*
* Return: True if this context still owns the console. False if
* ownership was handed over or taken.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context.
*/
bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
bool ret;
ret = nbcon_context_exit_unsafe(ctxt);
if (!ret)
nbcon_write_context_set_buf(wctxt, NULL, 0);
return ret;
}
EXPORT_SYMBOL_GPL(nbcon_exit_unsafe);
/**
* nbcon_reacquire_nobuf - Reacquire a console after losing ownership
* while printing
* @wctxt: The write context that was handed to the write callback
*
* Since ownership can be lost at any time due to handover or takeover, a
* printing context _must_ be prepared to back out immediately and
* carefully. However, there are scenarios where the printing context must
* reacquire ownership in order to finalize or revert hardware changes.
*
* This function allows a printing context to reacquire ownership using the
* same priority as its previous ownership.
*
* Note that after a successful reacquire the printing context will have no
* output buffer because that has been lost. This function cannot be used to
* resume printing.
*/
void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
while (!nbcon_context_try_acquire(ctxt))
cpu_relax();
nbcon_write_context_set_buf(wctxt, NULL, 0);
}
EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf);
/**
* nbcon_emit_next_record - Emit a record in the acquired context
* @wctxt: The write context that will be handed to the write function
* @use_atomic: True if the write_atomic() callback is to be used
*
* Return: True if this context still owns the console. False if
* ownership was handed over or taken.
*
* When this function returns false then the calling context no longer owns
* the console and is no longer allowed to go forward. In this case it must
* back out immediately and carefully. The buffer content is also no longer
* trusted since it no longer belongs to the calling context. If the caller
* wants to do more it must reacquire the console first.
*
* When true is returned, @wctxt->ctxt.backlog indicates whether there are
* still records pending in the ringbuffer,
*/
static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
struct console *con = ctxt->console;
bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
struct printk_message pmsg = {
.pbufs = ctxt->pbufs,
};
unsigned long con_dropped;
struct nbcon_state cur;
unsigned long dropped;
unsigned long ulseq;
/*
* This function should never be called for consoles that have not
* implemented the necessary callback for writing: i.e. legacy
* consoles and, when atomic, nbcon consoles with no write_atomic().
* Handle it as if ownership was lost and try to continue.
*
* Note that for nbcon consoles the write_thread() callback is
* mandatory and was already checked in nbcon_alloc().
*/
if (WARN_ON_ONCE((use_atomic && !con->write_atomic) ||
!(console_srcu_read_flags(con) & CON_NBCON))) {
nbcon_context_release(ctxt);
return false;
}
/*
* The printk buffers are filled within an unsafe section. This
* prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from
* clobbering each other.
*/
if (!nbcon_context_enter_unsafe(ctxt))
return false;
ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true);
if (!ctxt->backlog)
return nbcon_context_exit_unsafe(ctxt);
/*
* @con->dropped is not protected in case of an unsafe hostile
* takeover. In that situation the update can be racy so
* annotate it accordingly.
*/
con_dropped = data_race(READ_ONCE(con->dropped));
dropped = con_dropped + pmsg.dropped;
if (dropped && !is_extended)
console_prepend_dropped(&pmsg, dropped);
/*
* If the previous owner was assigned the same record, this context
* has taken over ownership and is replaying the record. Prepend a
* message to let the user know the record is replayed.
*/
ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq));
if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) {
console_prepend_replay(&pmsg);
} else {
/*
* Ensure this context is still the owner before trying to
* update @nbcon_prev_seq. Otherwise the value in @ulseq may
* not be from the previous owner and instead be some later
* value from the context that took over ownership.
*/
nbcon_state_read(con, &cur);
if (!nbcon_context_can_proceed(ctxt, &cur))
return false;
atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq,
__u64seq_to_ulseq(pmsg.seq));
}
if (!nbcon_context_exit_unsafe(ctxt))
return false;
/* For skipped records just update seq/dropped in @con. */
if (pmsg.outbuf_len == 0)
goto update_con;
/* Initialize the write context for driver callbacks. */
nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len);
if (use_atomic)
con->write_atomic(con, wctxt);
else
con->write_thread(con, wctxt);
if (!wctxt->outbuf) {
/*
* Ownership was lost and reacquired by the driver. Handle it
* as if ownership was lost.
*/
nbcon_context_release(ctxt);
return false;
}
/*
* Ownership may have been lost but _not_ reacquired by the driver.
* This case is detected and handled when entering unsafe to update
* dropped/seq values.
*/
/*
* Since any dropped message was successfully output, reset the
* dropped count for the console.
*/
dropped = 0;
update_con:
/*
* The dropped count and the sequence number are updated within an
* unsafe section. This limits update races to the panic context and
* allows the panic context to win.
*/
if (!nbcon_context_enter_unsafe(ctxt))
return false;
if (dropped != con_dropped) {
/* Counterpart to the READ_ONCE() above. */
WRITE_ONCE(con->dropped, dropped);
}
nbcon_seq_try_update(ctxt, pmsg.seq + 1);
return nbcon_context_exit_unsafe(ctxt);
}
/*
* nbcon_emit_one - Print one record for an nbcon console using the
* specified callback
* @wctxt: An initialized write context struct to use for this context
* @use_atomic: True if the write_atomic() callback is to be used
*
* Return: True, when a record has been printed and there are still
* pending records. The caller might want to continue flushing.
*
* False, when there is no pending record, or when the console
* context cannot be acquired, or the ownership has been lost.
* The caller should give up. Either the job is done, cannot be
* done, or will be handled by the owning context.
*
* This is an internal helper to handle the locking of the console before
* calling nbcon_emit_next_record().
*/
static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
struct console *con = ctxt->console;
unsigned long flags;
bool ret = false;
if (!use_atomic) {
con->device_lock(con, &flags);
/*
* Ensure this stays on the CPU to make handover and
* takeover possible.
*/
cant_migrate();
}
if (!nbcon_context_try_acquire(ctxt))
goto out;
/*
* nbcon_emit_next_record() returns false when the console was
* handed over or taken over. In both cases the context is no
* longer valid.
*
* The higher priority printing context takes over responsibility
* to print the pending records.
*/
if (!nbcon_emit_next_record(wctxt, use_atomic))
goto out;
nbcon_context_release(ctxt);
ret = ctxt->backlog;
out:
if (!use_atomic)
con->device_unlock(con, flags);
return ret;
}
/**
* nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup
* @con: Console to operate on
* @ctxt: The nbcon context from nbcon_context_try_acquire()
*
* Return: True if the thread should shutdown or if the console is
* allowed to print and a record is available. False otherwise.
*
* After the thread wakes up, it must first check if it should shutdown before
* attempting any printing.
*/
static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt)
{
bool ret = false;
short flags;
int cookie;
if (kthread_should_stop())
return true;
cookie = console_srcu_read_lock();
flags = console_srcu_read_flags(con);
if (console_is_usable(con, flags, false)) {
/* Bring the sequence in @ctxt up to date */
ctxt->seq = nbcon_seq_read(con);
ret = prb_read_valid(prb, ctxt->seq, NULL);
}
console_srcu_read_unlock(cookie);
return ret;
}
/**
* nbcon_kthread_func - The printer thread function
* @__console: Console to operate on
*
* Return: 0
*/
static int nbcon_kthread_func(void *__console)
{
struct console *con = __console;
struct nbcon_write_context wctxt = {
.ctxt.console = con,
.ctxt.prio = NBCON_PRIO_NORMAL,
};
struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt);
short con_flags;
bool backlog;
int cookie;
wait_for_event:
/*
* Guarantee this task is visible on the rcuwait before
* checking the wake condition.
*
* The full memory barrier within set_current_state() of
* ___rcuwait_wait_event() pairs with the full memory
* barrier within rcuwait_has_sleeper().
*
* This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A.
*/
rcuwait_wait_event(&con->rcuwait,
nbcon_kthread_should_wakeup(con, ctxt),
TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */
do {
if (kthread_should_stop())
return 0;
backlog = false;
/*
* Keep the srcu read lock around the entire operation so that
* synchronize_srcu() can guarantee that the kthread stopped
* or suspended printing.
*/
cookie = console_srcu_read_lock();
con_flags = console_srcu_read_flags(con);
if (console_is_usable(con, con_flags, false))
backlog = nbcon_emit_one(&wctxt, false);
console_srcu_read_unlock(cookie);
cond_resched();
} while (backlog);
goto wait_for_event;
}
/**
* nbcon_irq_work - irq work to wake console printer thread
* @irq_work: The irq work to operate on
*/
static void nbcon_irq_work(struct irq_work *irq_work)
{
struct console *con = container_of(irq_work, struct console, irq_work);
nbcon_kthread_wake(con);
}
static inline bool rcuwait_has_sleeper(struct rcuwait *w)
{
/*
* Guarantee any new records can be seen by tasks preparing to wait
* before this context checks if the rcuwait is empty.
*
* This full memory barrier pairs with the full memory barrier within
* set_current_state() of ___rcuwait_wait_event(), which is called
* after prepare_to_rcuwait() adds the waiter but before it has
* checked the wait condition.
*
* This pairs with nbcon_kthread_func:A.
*/
smp_mb(); /* LMM(rcuwait_has_sleeper:A) */
return rcuwait_active(w);
}
/**
* nbcon_kthreads_wake - Wake up printing threads using irq_work
*/
void nbcon_kthreads_wake(void)
{
struct console *con;
int cookie;
if (!printk_kthreads_running)
return;
cookie = console_srcu_read_lock();
for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON))
continue;
/*
* Only schedule irq_work if the printing thread is
* actively waiting. If not waiting, the thread will
* notice by itself that it has work to do.
*/
if (rcuwait_has_sleeper(&con->rcuwait)) irq_work_queue(&con->irq_work);
}
console_srcu_read_unlock(cookie);
}
/*
* nbcon_kthread_stop - Stop a console printer thread
* @con: Console to operate on
*/
void nbcon_kthread_stop(struct console *con)
{
lockdep_assert_console_list_lock_held();
if (!con->kthread)
return;
kthread_stop(con->kthread);
con->kthread = NULL;
}
/**
* nbcon_kthread_create - Create a console printer thread
* @con: Console to operate on
*
* Return: True if the kthread was started or already exists.
* Otherwise false and @con must not be registered.
*
* This function is called when it will be expected that nbcon consoles are
* flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL
* will be no longer flushed by the legacy loop. This is why failure must
* be fatal for console registration.
*
* If @con was already registered and this function fails, @con must be
* unregistered before the global state variable @printk_kthreads_running
* can be set.
*/
bool nbcon_kthread_create(struct console *con)
{
struct task_struct *kt;
lockdep_assert_console_list_lock_held();
if (con->kthread)
return true;
kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index);
if (WARN_ON(IS_ERR(kt))) {
con_printk(KERN_ERR, con, "failed to start printing thread\n");
return false;
}
con->kthread = kt;
/*
* It is important that console printing threads are scheduled
* shortly after a printk call and with generous runtime budgets.
*/
sched_set_normal(con->kthread, -20);
return true;
}
/* Track the nbcon emergency nesting per CPU. */
static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting);
static unsigned int early_nbcon_pcpu_emergency_nesting __initdata;
/**
* nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer
*
* Context: For reading, any context. For writing, any context which could
* not be migrated to another CPU.
* Return: Either a pointer to the per CPU emergency nesting counter of
* the current CPU or to the init data during early boot.
*
* The function is safe for reading per-CPU variables in any context because
* preemption is disabled if the current CPU is in the emergency state. See
* also nbcon_cpu_emergency_enter().
*/
static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void)
{
/*
* The value of __printk_percpu_data_ready gets set in normal
* context and before SMP initialization. As a result it could
* never change while inside an nbcon emergency section.
*/
if (!printk_percpu_data_ready())
return &early_nbcon_pcpu_emergency_nesting;
return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting);
}
/**
* nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon
* printing on the current CPU
*
* Context: Any context.
* Return: The nbcon_prio to use for acquiring an nbcon console in this
* context for printing.
*
* The function is safe for reading per-CPU data in any context because
* preemption is disabled if the current CPU is in the emergency or panic
* state.
*/
enum nbcon_prio nbcon_get_default_prio(void)
{
unsigned int *cpu_emergency_nesting;
if (this_cpu_in_panic())
return NBCON_PRIO_PANIC;
cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting();
if (*cpu_emergency_nesting)
return NBCON_PRIO_EMERGENCY;
return NBCON_PRIO_NORMAL;
}
/**
* nbcon_legacy_emit_next_record - Print one record for an nbcon console
* in legacy contexts
* @con: The console to print on
* @handover: Will be set to true if a printk waiter has taken over the
* console_lock, in which case the caller is no longer holding
* both the console_lock and the SRCU read lock. Otherwise it
* is set to false.
* @cookie: The cookie from the SRCU read lock.
* @use_atomic: Set true when called in an atomic or unknown context.
* It affects which nbcon callback will be used: write_atomic()
* or write_thread().
*
* When false, the write_thread() callback is used and would be
* called in a preemtible context unless disabled by the
* device_lock. The legacy handover is not allowed in this mode.
*
* Context: Any context except NMI.
* Return: True, when a record has been printed and there are still
* pending records. The caller might want to continue flushing.
*
* False, when there is no pending record, or when the console
* context cannot be acquired, or the ownership has been lost.
* The caller should give up. Either the job is done, cannot be
* done, or will be handled by the owning context.
*
* This function is meant to be called by console_flush_all() to print records
* on nbcon consoles from legacy context (printing via console unlocking).
* Essentially it is the nbcon version of console_emit_next_record().
*/
bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
int cookie, bool use_atomic)
{
struct nbcon_write_context wctxt = { };
struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt);
unsigned long flags;
bool progress;
ctxt->console = con;
ctxt->prio = nbcon_get_default_prio();
if (use_atomic) {
/*
* In an atomic or unknown context, use the same procedure as
* in console_emit_next_record(). It allows to handover.
*/
printk_safe_enter_irqsave(flags);
console_lock_spinning_enable();
stop_critical_timings();
}
progress = nbcon_emit_one(&wctxt, use_atomic);
if (use_atomic) {
start_critical_timings();
*handover = console_lock_spinning_disable_and_check(cookie);
printk_safe_exit_irqrestore(flags);
} else {
/* Non-atomic does not perform legacy spinning handovers. */
*handover = false;
}
return progress;
}
/**
* __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its
* write_atomic() callback
* @con: The nbcon console to flush
* @stop_seq: Flush up until this record
* @allow_unsafe_takeover: True, to allow unsafe hostile takeovers
*
* Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on
* failure.
*
* Errors:
*
* -EPERM: Unable to acquire console ownership.
*
* -EAGAIN: Another context took over ownership while printing.
*
* -ENOENT: A record before @stop_seq is not available.
*
* If flushing up to @stop_seq was not successful, it only makes sense for the
* caller to try again when -EAGAIN was returned. When -EPERM is returned,
* this context is not allowed to acquire the console. When -ENOENT is
* returned, it cannot be expected that the unfinalized record will become
* available.
*/
static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
bool allow_unsafe_takeover)
{
struct nbcon_write_context wctxt = { };
struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt);
int err = 0;
ctxt->console = con;
ctxt->spinwait_max_us = 2000;
ctxt->prio = nbcon_get_default_prio();
ctxt->allow_unsafe_takeover = allow_unsafe_takeover;
if (!nbcon_context_try_acquire(ctxt))
return -EPERM;
while (nbcon_seq_read(con) < stop_seq) {
/*
* nbcon_emit_next_record() returns false when the console was
* handed over or taken over. In both cases the context is no
* longer valid.
*/
if (!nbcon_emit_next_record(&wctxt, true))
return -EAGAIN;
if (!ctxt->backlog) {
/* Are there reserved but not yet finalized records? */
if (nbcon_seq_read(con) < stop_seq)
err = -ENOENT;
break;
}
}
nbcon_context_release(ctxt);
return err;
}
/**
* nbcon_atomic_flush_pending_con - Flush specified nbcon console using its
* write_atomic() callback
* @con: The nbcon console to flush
* @stop_seq: Flush up until this record
* @allow_unsafe_takeover: True, to allow unsafe hostile takeovers
*
* This will stop flushing before @stop_seq if another context has ownership.
* That context is then responsible for the flushing. Likewise, if new records
* are added while this context was flushing and there is no other context
* to handle the printing, this context must also flush those records.
*/
static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
bool allow_unsafe_takeover)
{
struct console_flush_type ft;
unsigned long flags;
int err;
again:
/*
* Atomic flushing does not use console driver synchronization (i.e.
* it does not hold the port lock for uart consoles). Therefore IRQs
* must be disabled to avoid being interrupted and then calling into
* a driver that will deadlock trying to acquire console ownership.
*/
local_irq_save(flags);
err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover);
local_irq_restore(flags);
/*
* If there was a new owner (-EPERM, -EAGAIN), that context is
* responsible for completing.
*
* Do not wait for records not yet finalized (-ENOENT) to avoid a
* possible deadlock. They will either get flushed by the writer or
* eventually skipped on panic CPU.
*/
if (err)
return;
/*
* If flushing was successful but more records are available, this
* context must flush those remaining records if the printer thread
* is not available do it.
*/
printk_get_console_flush_type(&ft);
if (!ft.nbcon_offload &&
prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
stop_seq = prb_next_reserve_seq(prb);
goto again;
}
}
/**
* __nbcon_atomic_flush_pending - Flush all nbcon consoles using their
* write_atomic() callback
* @stop_seq: Flush up until this record
* @allow_unsafe_takeover: True, to allow unsafe hostile takeovers
*/
static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover)
{
struct console *con;
int cookie;
cookie = console_srcu_read_lock();
for_each_console_srcu(con) {
short flags = console_srcu_read_flags(con);
if (!(flags & CON_NBCON))
continue;
if (!console_is_usable(con, flags, true))
continue;
if (nbcon_seq_read(con) >= stop_seq)
continue;
nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover);
}
console_srcu_read_unlock(cookie);
}
/**
* nbcon_atomic_flush_pending - Flush all nbcon consoles using their
* write_atomic() callback
*
* Flush the backlog up through the currently newest record. Any new
* records added while flushing will not be flushed if there is another
* context available to handle the flushing. This is to avoid one CPU
* printing unbounded because other CPUs continue to add records.
*/
void nbcon_atomic_flush_pending(void)
{
__nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false);
}
/**
* nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their
* write_atomic() callback and allowing unsafe hostile takeovers
*
* Flush the backlog up through the currently newest record. Unsafe hostile
* takeovers will be performed, if necessary.
*/
void nbcon_atomic_flush_unsafe(void)
{
__nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true);
}
/**
* nbcon_cpu_emergency_enter - Enter an emergency section where printk()
* messages for that CPU are flushed directly
*
* Context: Any context. Disables preemption.
*
* When within an emergency section, printk() calls will attempt to flush any
* pending messages in the ringbuffer.
*/
void nbcon_cpu_emergency_enter(void)
{
unsigned int *cpu_emergency_nesting;
preempt_disable();
cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting();
(*cpu_emergency_nesting)++;
}
/**
* nbcon_cpu_emergency_exit - Exit an emergency section
*
* Context: Within an emergency section. Enables preemption.
*/
void nbcon_cpu_emergency_exit(void)
{
unsigned int *cpu_emergency_nesting;
cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting();
if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0))
(*cpu_emergency_nesting)--;
preempt_enable();
}
/**
* nbcon_alloc - Allocate and init the nbcon console specific data
* @con: Console to initialize
*
* Return: True if the console was fully allocated and initialized.
* Otherwise @con must not be registered.
*
* When allocation and init was successful, the console must be properly
* freed using nbcon_free() once it is no longer needed.
*/
bool nbcon_alloc(struct console *con)
{
struct nbcon_state state = { };
/* The write_thread() callback is mandatory. */
if (WARN_ON(!con->write_thread))
return false;
rcuwait_init(&con->rcuwait);
init_irq_work(&con->irq_work, nbcon_irq_work);
atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL);
nbcon_state_set(con, &state);
/*
* Initialize @nbcon_seq to the highest possible sequence number so
* that practically speaking it will have nothing to print until a
* desired initial sequence number has been set via nbcon_seq_force().
*/
atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb));
if (con->flags & CON_BOOT) {
/*
* Boot console printing is synchronized with legacy console
* printing, so boot consoles can share the same global printk
* buffers.
*/
con->pbufs = &printk_shared_pbufs;
} else {
con->pbufs = kmalloc(sizeof(*con->pbufs), GFP_KERNEL);
if (!con->pbufs) {
con_printk(KERN_ERR, con, "failed to allocate printing buffer\n");
return false;
}
if (printk_kthreads_running) {
if (!nbcon_kthread_create(con)) {
kfree(con->pbufs);
con->pbufs = NULL;
return false;
}
}
}
return true;
}
/**
* nbcon_free - Free and cleanup the nbcon console specific data
* @con: Console to free/cleanup nbcon data
*/
void nbcon_free(struct console *con)
{
struct nbcon_state state = { };
if (printk_kthreads_running)
nbcon_kthread_stop(con);
nbcon_state_set(con, &state);
/* Boot consoles share global printk buffers. */
if (!(con->flags & CON_BOOT))
kfree(con->pbufs);
con->pbufs = NULL;
}
/**
* nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe
* section
* @con: The nbcon console to acquire
*
* Context: Under the locking mechanism implemented in
* @con->device_lock() including disabling migration.
* Return: True if the console was acquired. False otherwise.
*
* Console drivers will usually use their own internal synchronization
* mechasism to synchronize between console printing and non-printing
* activities (such as setting baud rates). However, nbcon console drivers
* supporting atomic consoles may also want to mark unsafe sections when
* performing non-printing activities in order to synchronize against their
* atomic_write() callback.
*
* This function acquires the nbcon console using priority NBCON_PRIO_NORMAL
* and marks it unsafe for handover/takeover.
*/
bool nbcon_device_try_acquire(struct console *con)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt);
cant_migrate();
memset(ctxt, 0, sizeof(*ctxt));
ctxt->console = con;
ctxt->prio = NBCON_PRIO_NORMAL;
if (!nbcon_context_try_acquire(ctxt))
return false;
if (!nbcon_context_enter_unsafe(ctxt))
return false;
return true;
}
EXPORT_SYMBOL_GPL(nbcon_device_try_acquire);
/**
* nbcon_device_release - Exit unsafe section and release the nbcon console
* @con: The nbcon console acquired in nbcon_device_try_acquire()
*/
void nbcon_device_release(struct console *con)
{
struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt);
struct console_flush_type ft;
int cookie;
if (!nbcon_context_exit_unsafe(ctxt))
return;
nbcon_context_release(ctxt);
/*
* This context must flush any new records added while the console
* was locked if the printer thread is not available to do it. The
* console_srcu_read_lock must be taken to ensure the console is
* usable throughout flushing.
*/
cookie = console_srcu_read_lock();
printk_get_console_flush_type(&ft);
if (console_is_usable(con, console_srcu_read_flags(con), true) &&
!ft.nbcon_offload &&
prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
/*
* If nbcon_atomic flushing is not available, fallback to
* using the legacy loop.
*/
if (ft.nbcon_atomic) {
__nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false);
} else if (ft.legacy_direct) {
if (console_trylock())
console_unlock();
} else if (ft.legacy_offload) {
printk_trigger_flush();
}
}
console_srcu_read_unlock(cookie);
}
EXPORT_SYMBOL_GPL(nbcon_device_release);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* This file provides wrappers with sanitizer instrumentation for bit
* locking operations.
*
* To use this functionality, an arch's bitops.h file needs to define each of
* the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
* arch___set_bit(), etc.).
*/
#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H
#define _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H
#include <linux/instrumented.h>
/**
* clear_bit_unlock - Clear a bit in memory, for unlock
* @nr: the bit to set
* @addr: the address to start counting from
*
* This operation is atomic and provides release barrier semantics.
*/
static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
{
kcsan_release();
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
arch_clear_bit_unlock(nr, addr);
}
/**
* __clear_bit_unlock - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* This is a non-atomic operation but implies a release barrier before the
* memory operation. It can be used for an unlock if no other CPUs can
* concurrently modify other bits in the word.
*/
static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
kcsan_release();
instrument_write(addr + BIT_WORD(nr), sizeof(long));
arch___clear_bit_unlock(nr, addr);
}
/**
* test_and_set_bit_lock - Set a bit and return its old value, for lock
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and provides acquire barrier semantics if
* the returned value is 0.
* It can be used to implement bit locks.
*/
static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
{
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_set_bit_lock(nr, addr);
}
/**
* xor_unlock_is_negative_byte - XOR a single byte in memory and test if
* it is negative, for unlock.
* @mask: Change the bits which are set in this mask.
* @addr: The address of the word containing the byte to change.
*
* Changes some of bits 0-6 in the word pointed to by @addr.
* This operation is atomic and provides release barrier semantics.
* Used to optimise some folio operations which are commonly paired
* with an unlock or end of writeback. Bit 7 is used as PG_waiters to
* indicate whether anybody is waiting for the unlock.
*
* Return: Whether the top bit of the byte is set.
*/
static inline bool xor_unlock_is_negative_byte(unsigned long mask,
volatile unsigned long *addr)
{
kcsan_release();
instrument_atomic_write(addr, sizeof(long));
return arch_xor_unlock_is_negative_byte(mask, addr);
}
#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_KSM_H
#define __LINUX_KSM_H
/*
* Memory merging support.
*
* This code enables dynamic sharing of identical pages found in different
* memory areas, even if they are not shared by fork().
*/
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/sched.h>
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags);
void ksm_add_vma(struct vm_area_struct *vma);
int ksm_enable_merge_any(struct mm_struct *mm);
int ksm_disable_merge_any(struct mm_struct *mm);
int ksm_disable(struct mm_struct *mm);
int __ksm_enter(struct mm_struct *mm);
void __ksm_exit(struct mm_struct *mm);
/*
* To identify zeropages that were mapped by KSM, we reuse the dirty bit
* in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when
* deduplicating memory.
*/
#define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte))
extern atomic_long_t ksm_zero_pages;
static inline void ksm_map_zero_page(struct mm_struct *mm)
{
atomic_long_inc(&ksm_zero_pages);
atomic_long_inc(&mm->ksm_zero_pages);
}
static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
{
if (is_ksm_zero_pte(pte)) { atomic_long_dec(&ksm_zero_pages); atomic_long_dec(&mm->ksm_zero_pages);
}
}
static inline long mm_ksm_zero_pages(struct mm_struct *mm)
{
return atomic_long_read(&mm->ksm_zero_pages);
}
static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
/* Adding mm to ksm is best effort on fork. */
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
__ksm_enter(mm);
}
static inline int ksm_execve(struct mm_struct *mm)
{
if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
return __ksm_enter(mm);
return 0;
}
static inline void ksm_exit(struct mm_struct *mm)
{
if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
__ksm_exit(mm);
}
/*
* When do_swap_page() first faults in from swap what used to be a KSM page,
* no problem, it will be assigned to this vma's anon_vma; but thereafter,
* it might be faulted into a different anon_vma (or perhaps to a different
* offset in the same anon_vma). do_swap_page() cannot do all the locking
* needed to reconstitute a cross-anon_vma KSM page: for now it has to make
* a copy, and leave remerging the pages to a later pass of ksmd.
*
* We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
* but what if the vma was unmerged while the page was swapped out?
*/
struct folio *ksm_might_need_to_copy(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr);
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
void collect_procs_ksm(const struct folio *folio, const struct page *page,
struct list_head *to_kill, int force_early);
long ksm_process_profit(struct mm_struct *);
bool ksm_process_mergeable(struct mm_struct *mm);
#else /* !CONFIG_KSM */
static inline void ksm_add_vma(struct vm_area_struct *vma)
{
}
static inline int ksm_disable(struct mm_struct *mm)
{
return 0;
}
static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
}
static inline int ksm_execve(struct mm_struct *mm)
{
return 0;
}
static inline void ksm_exit(struct mm_struct *mm)
{
}
static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
{
}
static inline void collect_procs_ksm(const struct folio *folio,
const struct page *page, struct list_head *to_kill,
int force_early)
{
}
#ifdef CONFIG_MMU
static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags)
{
return 0;
}
static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr)
{
return folio;
}
static inline void rmap_walk_ksm(struct folio *folio,
struct rmap_walk_control *rwc)
{
}
static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
{
}
#endif /* CONFIG_MMU */
#endif /* !CONFIG_KSM */
#endif /* __LINUX_KSM_H */
// SPDX-License-Identifier: GPL-2.0
/*
* arch/arm64/kvm/fpsimd.c: Guest/host FPSIMD context coordination helpers
*
* Copyright 2018 Arm Limited
* Author: Dave Martin <Dave.Martin@arm.com>
*/
#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/kvm_host.h>
#include <asm/fpsimd.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/sysreg.h>
/*
* Called on entry to KVM_RUN unless this vcpu previously ran at least
* once and the most recent prior KVM_RUN for this vcpu was called from
* the same task as current (highly likely).
*
* This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
* such that on entering hyp the relevant parts of current are already
* mapped.
*/
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
{ struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state;
int ret;
/* pKVM has its own tracking of the host fpsimd state. */
if (is_protected_kvm_enabled())
return 0;
/* Make sure the host task fpsimd state is visible to hyp: */
ret = kvm_share_hyp(fpsimd, fpsimd + 1);
if (ret)
return ret;
return 0;
}
/*
* Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
* The actual loading is done by the FPSIMD access trap taken to hyp.
*
* Here, we just set the correct metadata to indicate that the FPSIMD
* state in the cpu regs (if any) belongs to current on the host.
*/
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
{ BUG_ON(!current->mm); if (!system_supports_fpsimd())
return;
/*
* Ensure that any host FPSIMD/SVE/SME state is saved and unbound such
* that the host kernel is responsible for restoring this state upon
* return to userspace, and the hyp code doesn't need to save anything.
*
* When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures
* that PSTATE.{SM,ZA} == {0,0}.
*/
fpsimd_save_and_flush_cpu_state();
*host_data_ptr(fp_owner) = FP_STATE_FREE;
WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR));
}
/*
* Called just before entering the guest once we are no longer preemptible
* and interrupts are disabled. If we have managed to run anything using
* FP while we were preemptible (such as off the back of an interrupt),
* then neither the host nor the guest own the FP hardware (and it was the
* responsibility of the code that used FP to save the existing state).
*/
void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)
{ if (test_thread_flag(TIF_FOREIGN_FPSTATE)) *host_data_ptr(fp_owner) = FP_STATE_FREE;
}
/*
* Called just after exiting the guest. If the guest FPSIMD state
* was loaded, update the host's context tracking data mark the CPU
* FPSIMD regs as dirty and belonging to vcpu so that they will be
* written back if the kernel clobbers them due to kernel-mode NEON
* before re-entry into the guest.
*/
void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
{
struct cpu_fp_state fp_state;
WARN_ON_ONCE(!irqs_disabled()); if (guest_owns_fp_regs()) {
/*
* Currently we do not support SME guests so SVCR is
* always 0 and we just need a variable to point to.
*/
fp_state.st = &vcpu->arch.ctxt.fp_regs;
fp_state.sve_state = vcpu->arch.sve_state;
fp_state.sve_vl = vcpu->arch.sve_max_vl;
fp_state.sme_state = NULL;
fp_state.svcr = &__vcpu_sys_reg(vcpu, SVCR); fp_state.fpmr = &__vcpu_sys_reg(vcpu, FPMR);
fp_state.fp_type = &vcpu->arch.fp_type;
if (vcpu_has_sve(vcpu))
fp_state.to_save = FP_STATE_SVE;
else
fp_state.to_save = FP_STATE_FPSIMD;
fpsimd_bind_state_to_cpu(&fp_state);
clear_thread_flag(TIF_FOREIGN_FPSTATE);
}
}
/*
* Write back the vcpu FPSIMD regs if they are dirty, and invalidate the
* cpu FPSIMD regs so that they can't be spuriously reused if this vcpu
* disappears and another task or vcpu appears that recycles the same
* struct fpsimd_state.
*/
void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
{
unsigned long flags;
local_irq_save(flags); if (guest_owns_fp_regs()) {
/*
* Flush (save and invalidate) the fpsimd/sve state so that if
* the host tries to use fpsimd/sve, it's not using stale data
* from the guest.
*
* Flushing the state sets the TIF_FOREIGN_FPSTATE bit for the
* context unconditionally, in both nVHE and VHE. This allows
* the kernel to restore the fpsimd/sve state, including ZCR_EL1
* when needed.
*/
fpsimd_save_and_flush_cpu_state();
}
local_irq_restore(flags);
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RMAP_H
#define _LINUX_RMAP_H
/*
* Declarations for Reverse Mapping functions in mm/rmap.c
*/
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/rwsem.h>
#include <linux/memcontrol.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/memremap.h>
#include <linux/bit_spinlock.h>
/*
* The anon_vma heads a list of private "related" vmas, to scan if
* an anonymous page pointing to this anon_vma needs to be unmapped:
* the vmas on the list will be related by forking, or by splitting.
*
* Since vmas come and go as they are split and merged (particularly
* in mprotect), the mapping field of an anonymous page cannot point
* directly to a vma: instead it points to an anon_vma, on whose list
* the related vmas can be easily linked or unlinked.
*
* After unlinking the last vma on the list, we must garbage collect
* the anon_vma object itself: we're guaranteed no page can be
* pointing to this anon_vma once its vma list is empty.
*/
struct anon_vma {
struct anon_vma *root; /* Root of this anon_vma tree */
struct rw_semaphore rwsem; /* W: modification, R: walking the list */
/*
* The refcount is taken on an anon_vma when there is no
* guarantee that the vma of page tables will exist for
* the duration of the operation. A caller that takes
* the reference is responsible for clearing up the
* anon_vma if they are the last user on release
*/
atomic_t refcount;
/*
* Count of child anon_vmas. Equals to the count of all anon_vmas that
* have ->parent pointing to this one, including itself.
*
* This counter is used for making decision about reusing anon_vma
* instead of forking new one. See comments in function anon_vma_clone.
*/
unsigned long num_children;
/* Count of VMAs whose ->anon_vma pointer points to this object. */
unsigned long num_active_vmas;
struct anon_vma *parent; /* Parent of this anon_vma */
/*
* NOTE: the LSB of the rb_root.rb_node is set by
* mm_take_all_locks() _after_ taking the above lock. So the
* rb_root must only be read/written after taking the above lock
* to be sure to see a valid next pointer. The LSB bit itself
* is serialized by a system wide lock only visible to
* mm_take_all_locks() (mm_all_locks_mutex).
*/
/* Interval tree of private "related" vmas */
struct rb_root_cached rb_root;
};
/*
* The copy-on-write semantics of fork mean that an anon_vma
* can become associated with multiple processes. Furthermore,
* each child process will have its own anon_vma, where new
* pages for that process are instantiated.
*
* This structure allows us to find the anon_vmas associated
* with a VMA, or the VMAs associated with an anon_vma.
* The "same_vma" list contains the anon_vma_chains linking
* all the anon_vmas associated with this VMA.
* The "rb" field indexes on an interval tree the anon_vma_chains
* which link all the VMAs associated with this anon_vma.
*/
struct anon_vma_chain {
struct vm_area_struct *vma;
struct anon_vma *anon_vma;
struct list_head same_vma; /* locked by mmap_lock & page_table_lock */
struct rb_node rb; /* locked by anon_vma->rwsem */
unsigned long rb_subtree_last;
#ifdef CONFIG_DEBUG_VM_RB
unsigned long cached_vma_start, cached_vma_last;
#endif
};
enum ttu_flags {
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */
TTU_HWPOISON = 0x20, /* do convert pte to hwpoison entry */
TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible
* and caller guarantees they will
* do a final flush if necessary */
TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock:
* caller holds it */
};
#ifdef CONFIG_MMU
static inline void get_anon_vma(struct anon_vma *anon_vma)
{
atomic_inc(&anon_vma->refcount);
}
void __put_anon_vma(struct anon_vma *anon_vma);
static inline void put_anon_vma(struct anon_vma *anon_vma)
{
if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma);
}
static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
{
down_write(&anon_vma->root->rwsem);
}
static inline int anon_vma_trylock_write(struct anon_vma *anon_vma)
{
return down_write_trylock(&anon_vma->root->rwsem);
}
static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
{
up_write(&anon_vma->root->rwsem);
}
static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
{
down_read(&anon_vma->root->rwsem);
}
static inline int anon_vma_trylock_read(struct anon_vma *anon_vma)
{
return down_read_trylock(&anon_vma->root->rwsem);
}
static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
{
up_read(&anon_vma->root->rwsem);
}
/*
* anon_vma helper functions.
*/
void anon_vma_init(void); /* create anon_vma_cachep */
int __anon_vma_prepare(struct vm_area_struct *);
void unlink_anon_vmas(struct vm_area_struct *);
int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
static inline int anon_vma_prepare(struct vm_area_struct *vma)
{
if (likely(vma->anon_vma))
return 0;
return __anon_vma_prepare(vma);
}
static inline void anon_vma_merge(struct vm_area_struct *vma,
struct vm_area_struct *next)
{
VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma); unlink_anon_vmas(next);
}
struct anon_vma *folio_get_anon_vma(const struct folio *folio);
#ifdef CONFIG_MM_ID
static __always_inline void folio_lock_large_mapcount(struct folio *folio)
{
bit_spin_lock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids);
}
static __always_inline void folio_unlock_large_mapcount(struct folio *folio)
{
__bit_spin_unlock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids);
}
static inline unsigned int folio_mm_id(const struct folio *folio, int idx)
{
VM_WARN_ON_ONCE(idx != 0 && idx != 1);
return folio->_mm_id[idx] & MM_ID_MASK;
}
static inline void folio_set_mm_id(struct folio *folio, int idx, mm_id_t id)
{
VM_WARN_ON_ONCE(idx != 0 && idx != 1);
folio->_mm_id[idx] &= ~MM_ID_MASK;
folio->_mm_id[idx] |= id;
}
static inline void __folio_large_mapcount_sanity_checks(const struct folio *folio,
int diff, mm_id_t mm_id)
{
VM_WARN_ON_ONCE(!folio_test_large(folio) || folio_test_hugetlb(folio));
VM_WARN_ON_ONCE(diff <= 0);
VM_WARN_ON_ONCE(mm_id < MM_ID_MIN || mm_id > MM_ID_MAX);
/*
* Make sure we can detect at least one complete PTE mapping of the
* folio in a single MM as "exclusively mapped". This is primarily
* a check on 32bit, where we currently reduce the size of the per-MM
* mapcount to a short.
*/
VM_WARN_ON_ONCE(diff > folio_large_nr_pages(folio));
VM_WARN_ON_ONCE(folio_large_nr_pages(folio) - 1 > MM_ID_MAPCOUNT_MAX);
VM_WARN_ON_ONCE(folio_mm_id(folio, 0) == MM_ID_DUMMY &&
folio->_mm_id_mapcount[0] != -1);
VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY &&
folio->_mm_id_mapcount[0] < 0);
VM_WARN_ON_ONCE(folio_mm_id(folio, 1) == MM_ID_DUMMY &&
folio->_mm_id_mapcount[1] != -1);
VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY &&
folio->_mm_id_mapcount[1] < 0);
VM_WARN_ON_ONCE(!folio_mapped(folio) &&
folio_test_large_maybe_mapped_shared(folio));
}
static __always_inline void folio_set_large_mapcount(struct folio *folio,
int mapcount, struct vm_area_struct *vma)
{
__folio_large_mapcount_sanity_checks(folio, mapcount, vma->vm_mm->mm_id);
VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY); VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY);
/* Note: mapcounts start at -1. */
atomic_set(&folio->_large_mapcount, mapcount - 1);
folio->_mm_id_mapcount[0] = mapcount - 1;
folio_set_mm_id(folio, 0, vma->vm_mm->mm_id);
}
static __always_inline int folio_add_return_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
const mm_id_t mm_id = vma->vm_mm->mm_id;
int new_mapcount_val;
folio_lock_large_mapcount(folio);
__folio_large_mapcount_sanity_checks(folio, diff, mm_id);
new_mapcount_val = atomic_read(&folio->_large_mapcount) + diff;
atomic_set(&folio->_large_mapcount, new_mapcount_val);
/*
* If a folio is mapped more than once into an MM on 32bit, we
* can in theory overflow the per-MM mapcount (although only for
* fairly large folios), turning it negative. In that case, just
* free up the slot and mark the folio "mapped shared", otherwise
* we might be in trouble when unmapping pages later.
*/
if (folio_mm_id(folio, 0) == mm_id) {
folio->_mm_id_mapcount[0] += diff;
if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[0] < 0)) {
folio->_mm_id_mapcount[0] = -1;
folio_set_mm_id(folio, 0, MM_ID_DUMMY);
folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT;
}
} else if (folio_mm_id(folio, 1) == mm_id) {
folio->_mm_id_mapcount[1] += diff;
if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[1] < 0)) {
folio->_mm_id_mapcount[1] = -1;
folio_set_mm_id(folio, 1, MM_ID_DUMMY);
folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT;
}
} else if (folio_mm_id(folio, 0) == MM_ID_DUMMY) {
folio_set_mm_id(folio, 0, mm_id);
folio->_mm_id_mapcount[0] = diff - 1;
/* We might have other mappings already. */
if (new_mapcount_val != diff - 1) folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; } else if (folio_mm_id(folio, 1) == MM_ID_DUMMY) { folio_set_mm_id(folio, 1, mm_id);
folio->_mm_id_mapcount[1] = diff - 1;
/* Slot 0 certainly has mappings as well. */
folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT;
}
folio_unlock_large_mapcount(folio);
return new_mapcount_val + 1;
}
#define folio_add_large_mapcount folio_add_return_large_mapcount
static __always_inline int folio_sub_return_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
const mm_id_t mm_id = vma->vm_mm->mm_id;
int new_mapcount_val;
folio_lock_large_mapcount(folio);
__folio_large_mapcount_sanity_checks(folio, diff, mm_id);
new_mapcount_val = atomic_read(&folio->_large_mapcount) - diff;
atomic_set(&folio->_large_mapcount, new_mapcount_val);
/*
* There are valid corner cases where we might underflow a per-MM
* mapcount (some mappings added when no slot was free, some mappings
* added once a slot was free), so we always set it to -1 once we go
* negative.
*/
if (folio_mm_id(folio, 0) == mm_id) {
folio->_mm_id_mapcount[0] -= diff;
if (folio->_mm_id_mapcount[0] >= 0)
goto out;
folio->_mm_id_mapcount[0] = -1;
folio_set_mm_id(folio, 0, MM_ID_DUMMY);
} else if (folio_mm_id(folio, 1) == mm_id) {
folio->_mm_id_mapcount[1] -= diff;
if (folio->_mm_id_mapcount[1] >= 0)
goto out;
folio->_mm_id_mapcount[1] = -1;
folio_set_mm_id(folio, 1, MM_ID_DUMMY);
}
/*
* If one MM slot owns all mappings, the folio is mapped exclusively.
* Note that if the folio is now unmapped (new_mapcount_val == -1), both
* slots must be free (mapcount == -1), and we'll also mark it as
* exclusive.
*/
if (folio->_mm_id_mapcount[0] == new_mapcount_val ||
folio->_mm_id_mapcount[1] == new_mapcount_val)
folio->_mm_ids &= ~FOLIO_MM_IDS_SHARED_BIT;
out:
folio_unlock_large_mapcount(folio);
return new_mapcount_val + 1;
}
#define folio_sub_large_mapcount folio_sub_return_large_mapcount
#else /* !CONFIG_MM_ID */
/*
* See __folio_rmap_sanity_checks(), we might map large folios even without
* CONFIG_TRANSPARENT_HUGEPAGE. We'll keep that working for now.
*/
static inline void folio_set_large_mapcount(struct folio *folio, int mapcount,
struct vm_area_struct *vma)
{
/* Note: mapcounts start at -1. */
atomic_set(&folio->_large_mapcount, mapcount - 1);
}
static inline void folio_add_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
atomic_add(diff, &folio->_large_mapcount);
}
static inline int folio_add_return_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
BUILD_BUG();
}
static inline void folio_sub_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
atomic_sub(diff, &folio->_large_mapcount);
}
static inline int folio_sub_return_large_mapcount(struct folio *folio,
int diff, struct vm_area_struct *vma)
{
BUILD_BUG();
}
#endif /* CONFIG_MM_ID */
#define folio_inc_large_mapcount(folio, vma) \
folio_add_large_mapcount(folio, 1, vma)
#define folio_inc_return_large_mapcount(folio, vma) \
folio_add_return_large_mapcount(folio, 1, vma)
#define folio_dec_large_mapcount(folio, vma) \
folio_sub_large_mapcount(folio, 1, vma)
#define folio_dec_return_large_mapcount(folio, vma) \
folio_sub_return_large_mapcount(folio, 1, vma)
/* RMAP flags, currently only relevant for some anon rmap operations. */
typedef int __bitwise rmap_t;
/*
* No special request: A mapped anonymous (sub)page is possibly shared between
* processes.
*/
#define RMAP_NONE ((__force rmap_t)0)
/* The anonymous (sub)page is exclusive to a single process. */
#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0))
/*
* Internally, we're using an enum to specify the granularity. We make the
* compiler emit specialized code for each granularity.
*/
enum rmap_level {
RMAP_LEVEL_PTE = 0,
RMAP_LEVEL_PMD,
RMAP_LEVEL_PUD,
};
static inline void __folio_rmap_sanity_checks(const struct folio *folio,
const struct page *page, int nr_pages, enum rmap_level level)
{
/* hugetlb folios are handled separately. */
VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
/* When (un)mapping zeropages, we should never touch ref+mapcount. */
VM_WARN_ON_FOLIO(is_zero_folio(folio), folio);
/*
* TODO: we get driver-allocated folios that have nothing to do with
* the rmap using vm_insert_page(); therefore, we cannot assume that
* folio_test_large_rmappable() holds for large folios. We should
* handle any desired mapcount+stats accounting for these folios in
* VM_MIXEDMAP VMAs separately, and then sanity-check here that
* we really only get rmappable folios.
*/
VM_WARN_ON_ONCE(nr_pages <= 0); VM_WARN_ON_FOLIO(page_folio(page) != folio, folio); VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio);
switch (level) {
case RMAP_LEVEL_PTE:
break;
case RMAP_LEVEL_PMD:
/*
* We don't support folios larger than a single PMD yet. So
* when RMAP_LEVEL_PMD is set, we assume that we are creating
* a single "entire" mapping of the folio.
*/
VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio);
VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio);
break;
case RMAP_LEVEL_PUD:
/*
* Assume that we are creating a single "entire" mapping of the
* folio.
*/
VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PUD_NR, folio);
VM_WARN_ON_FOLIO(nr_pages != HPAGE_PUD_NR, folio);
break;
default:
VM_WARN_ON_ONCE(true);
}
}
/*
* rmap interfaces called when adding or removing pte of page
*/
void folio_move_anon_rmap(struct folio *, struct vm_area_struct *);
void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages,
struct vm_area_struct *, unsigned long address, rmap_t flags);
#define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \
folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags)
void folio_add_anon_rmap_pmd(struct folio *, struct page *,
struct vm_area_struct *, unsigned long address, rmap_t flags);
void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
unsigned long address, rmap_t flags);
void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
struct vm_area_struct *);
#define folio_add_file_rmap_pte(folio, page, vma) \
folio_add_file_rmap_ptes(folio, page, 1, vma)
void folio_add_file_rmap_pmd(struct folio *, struct page *,
struct vm_area_struct *);
void folio_add_file_rmap_pud(struct folio *, struct page *,
struct vm_area_struct *);
void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
struct vm_area_struct *);
#define folio_remove_rmap_pte(folio, page, vma) \
folio_remove_rmap_ptes(folio, page, 1, vma)
void folio_remove_rmap_pmd(struct folio *, struct page *,
struct vm_area_struct *);
void folio_remove_rmap_pud(struct folio *, struct page *,
struct vm_area_struct *);
void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
unsigned long address, rmap_t flags);
void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
unsigned long address);
/* See folio_try_dup_anon_rmap_*() */
static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
struct vm_area_struct *vma)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
if (PageAnonExclusive(&folio->page)) {
if (unlikely(folio_needs_cow_for_dma(vma, folio)))
return -EBUSY;
ClearPageAnonExclusive(&folio->page);
}
atomic_inc(&folio->_entire_mapcount);
atomic_inc(&folio->_large_mapcount);
return 0;
}
/* See folio_try_share_anon_rmap_*() */
static inline int hugetlb_try_share_anon_rmap(struct folio *folio)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio);
/* Paired with the memory barrier in try_grab_folio(). */
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_mb();
if (unlikely(folio_maybe_dma_pinned(folio)))
return -EBUSY;
ClearPageAnonExclusive(&folio->page);
/*
* This is conceptually a smp_wmb() paired with the smp_rmb() in
* gup_must_unshare().
*/
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_mb__after_atomic();
return 0;
}
static inline void hugetlb_add_file_rmap(struct folio *folio)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount);
}
static inline void hugetlb_remove_rmap(struct folio *folio)
{
VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); atomic_dec(&folio->_large_mapcount);
}
static __always_inline void __folio_dup_file_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *dst_vma,
enum rmap_level level)
{
const int orig_nr_pages = nr_pages;
__folio_rmap_sanity_checks(folio, page, nr_pages, level);
switch (level) {
case RMAP_LEVEL_PTE:
if (!folio_test_large(folio)) {
atomic_inc(&folio->_mapcount);
break;
}
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) {
do {
atomic_inc(&page->_mapcount);
} while (page++, --nr_pages > 0);
}
folio_add_large_mapcount(folio, orig_nr_pages, dst_vma);
break;
case RMAP_LEVEL_PMD:
case RMAP_LEVEL_PUD:
atomic_inc(&folio->_entire_mapcount);
folio_inc_large_mapcount(folio, dst_vma);
break;
}
}
/**
* folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio
* @folio: The folio to duplicate the mappings of
* @page: The first page to duplicate the mappings of
* @nr_pages: The number of pages of which the mapping will be duplicated
* @dst_vma: The destination vm area
*
* The page range of the folio is defined by [page, page + nr_pages)
*
* The caller needs to hold the page table lock.
*/
static inline void folio_dup_file_rmap_ptes(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *dst_vma)
{
__folio_dup_file_rmap(folio, page, nr_pages, dst_vma, RMAP_LEVEL_PTE);
}
static __always_inline void folio_dup_file_rmap_pte(struct folio *folio,
struct page *page, struct vm_area_struct *dst_vma)
{
__folio_dup_file_rmap(folio, page, 1, dst_vma, RMAP_LEVEL_PTE);
}
/**
* folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio
* @folio: The folio to duplicate the mapping of
* @page: The first page to duplicate the mapping of
* @dst_vma: The destination vm area
*
* The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock.
*/
static inline void folio_dup_file_rmap_pmd(struct folio *folio,
struct page *page, struct vm_area_struct *dst_vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
__folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, dst_vma, RMAP_LEVEL_PTE);
#else
WARN_ON_ONCE(true);
#endif
}
static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, enum rmap_level level)
{
const int orig_nr_pages = nr_pages;
bool maybe_pinned;
int i;
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
__folio_rmap_sanity_checks(folio, page, nr_pages, level);
/*
* If this folio may have been pinned by the parent process,
* don't allow to duplicate the mappings but instead require to e.g.,
* copy the subpage immediately for the child so that we'll always
* guarantee the pinned folio won't be randomly replaced in the
* future on write faults.
*/
maybe_pinned = likely(!folio_is_device_private(folio)) &&
unlikely(folio_needs_cow_for_dma(src_vma, folio));
/*
* No need to check+clear for already shared PTEs/PMDs of the
* folio. But if any page is PageAnonExclusive, we must fallback to
* copying if the folio maybe pinned.
*/
switch (level) {
case RMAP_LEVEL_PTE:
if (unlikely(maybe_pinned)) {
for (i = 0; i < nr_pages; i++)
if (PageAnonExclusive(page + i))
return -EBUSY;
}
if (!folio_test_large(folio)) {
if (PageAnonExclusive(page))
ClearPageAnonExclusive(page);
atomic_inc(&folio->_mapcount);
break;
}
do {
if (PageAnonExclusive(page))
ClearPageAnonExclusive(page);
if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
atomic_inc(&page->_mapcount);
} while (page++, --nr_pages > 0);
folio_add_large_mapcount(folio, orig_nr_pages, dst_vma);
break;
case RMAP_LEVEL_PMD:
case RMAP_LEVEL_PUD:
if (PageAnonExclusive(page)) {
if (unlikely(maybe_pinned))
return -EBUSY;
ClearPageAnonExclusive(page);
}
atomic_inc(&folio->_entire_mapcount);
folio_inc_large_mapcount(folio, dst_vma);
break;
}
return 0;
}
/**
* folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range
* of a folio
* @folio: The folio to duplicate the mappings of
* @page: The first page to duplicate the mappings of
* @nr_pages: The number of pages of which the mapping will be duplicated
* @dst_vma: The destination vm area
* @src_vma: The vm area from which the mappings are duplicated
*
* The page range of the folio is defined by [page, page + nr_pages)
*
* The caller needs to hold the page table lock and the
* vma->vma_mm->write_protect_seq.
*
* Duplicating the mappings can only fail if the folio may be pinned; device
* private folios cannot get pinned and consequently this function cannot fail
* for them.
*
* If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in
* the parent and the child. They must *not* be writable after this call
* succeeded.
*
* Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
*/
static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
struct page *page, int nr_pages, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma)
{
return __folio_try_dup_anon_rmap(folio, page, nr_pages, dst_vma,
src_vma, RMAP_LEVEL_PTE);
}
static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio,
struct page *page, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma)
{
return __folio_try_dup_anon_rmap(folio, page, 1, dst_vma, src_vma,
RMAP_LEVEL_PTE);
}
/**
* folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
* of a folio
* @folio: The folio to duplicate the mapping of
* @page: The first page to duplicate the mapping of
* @dst_vma: The destination vm area
* @src_vma: The vm area from which the mapping is duplicated
*
* The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock and the
* vma->vma_mm->write_protect_seq.
*
* Duplicating the mapping can only fail if the folio may be pinned; device
* private folios cannot get pinned and consequently this function cannot fail
* for them.
*
* If duplicating the mapping succeeds, the duplicated PMD has to be R/O in
* the parent and the child. They must *not* be writable after this call
* succeeded.
*
* Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
*/
static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
struct page *page, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, dst_vma,
src_vma, RMAP_LEVEL_PMD);
#else
WARN_ON_ONCE(true);
return -EBUSY;
#endif
}
static __always_inline int __folio_try_share_anon_rmap(struct folio *folio,
struct page *page, int nr_pages, enum rmap_level level)
{
VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio);
__folio_rmap_sanity_checks(folio, page, nr_pages, level);
/* device private folios cannot get pinned via GUP. */
if (unlikely(folio_is_device_private(folio))) {
ClearPageAnonExclusive(page);
return 0;
}
/*
* We have to make sure that when we clear PageAnonExclusive, that
* the page is not pinned and that concurrent GUP-fast won't succeed in
* concurrently pinning the page.
*
* Conceptually, PageAnonExclusive clearing consists of:
* (A1) Clear PTE
* (A2) Check if the page is pinned; back off if so.
* (A3) Clear PageAnonExclusive
* (A4) Restore PTE (optional, but certainly not writable)
*
* When clearing PageAnonExclusive, we cannot possibly map the page
* writable again, because anon pages that may be shared must never
* be writable. So in any case, if the PTE was writable it cannot
* be writable anymore afterwards and there would be a PTE change. Only
* if the PTE wasn't writable, there might not be a PTE change.
*
* Conceptually, GUP-fast pinning of an anon page consists of:
* (B1) Read the PTE
* (B2) FOLL_WRITE: check if the PTE is not writable; back off if so.
* (B3) Pin the mapped page
* (B4) Check if the PTE changed by re-reading it; back off if so.
* (B5) If the original PTE is not writable, check if
* PageAnonExclusive is not set; back off if so.
*
* If the PTE was writable, we only have to make sure that GUP-fast
* observes a PTE change and properly backs off.
*
* If the PTE was not writable, we have to make sure that GUP-fast either
* detects a (temporary) PTE change or that PageAnonExclusive is cleared
* and properly backs off.
*
* Consequently, when clearing PageAnonExclusive(), we have to make
* sure that (A1), (A2)/(A3) and (A4) happen in the right memory
* order. In GUP-fast pinning code, we have to make sure that (B3),(B4)
* and (B5) happen in the right memory order.
*
* We assume that there might not be a memory barrier after
* clearing/invalidating the PTE (A1) and before restoring the PTE (A4),
* so we use explicit ones here.
*/
/* Paired with the memory barrier in try_grab_folio(). */
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_mb();
if (unlikely(folio_maybe_dma_pinned(folio)))
return -EBUSY;
ClearPageAnonExclusive(page);
/*
* This is conceptually a smp_wmb() paired with the smp_rmb() in
* gup_must_unshare().
*/
if (IS_ENABLED(CONFIG_HAVE_GUP_FAST))
smp_mb__after_atomic();
return 0;
}
/**
* folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page
* mapped by a PTE possibly shared to prepare
* for KSM or temporary unmapping
* @folio: The folio to share a mapping of
* @page: The mapped exclusive page
*
* The caller needs to hold the page table lock and has to have the page table
* entries cleared/invalidated.
*
* This is similar to folio_try_dup_anon_rmap_pte(), however, not used during
* fork() to duplicate mappings, but instead to prepare for KSM or temporarily
* unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte().
*
* Marking the mapped page shared can only fail if the folio maybe pinned;
* device private folios cannot get pinned and consequently this function cannot
* fail.
*
* Returns 0 if marking the mapped page possibly shared succeeded. Returns
* -EBUSY otherwise.
*/
static inline int folio_try_share_anon_rmap_pte(struct folio *folio,
struct page *page)
{
return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE);
}
/**
* folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page
* range mapped by a PMD possibly shared to
* prepare for temporary unmapping
* @folio: The folio to share the mapping of
* @page: The first page to share the mapping of
*
* The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
*
* The caller needs to hold the page table lock and has to have the page table
* entries cleared/invalidated.
*
* This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during
* fork() to duplicate a mapping, but instead to prepare for temporarily
* unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd().
*
* Marking the mapped pages shared can only fail if the folio maybe pinned;
* device private folios cannot get pinned and consequently this function cannot
* fail.
*
* Returns 0 if marking the mapped pages possibly shared succeeded. Returns
* -EBUSY otherwise.
*/
static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR,
RMAP_LEVEL_PMD);
#else
WARN_ON_ONCE(true);
return -EBUSY;
#endif
}
/*
* Called from mm/vmscan.c to handle paging out
*/
int folio_referenced(struct folio *, int is_locked,
struct mem_cgroup *memcg, unsigned long *vm_flags);
void try_to_migrate(struct folio *folio, enum ttu_flags flags);
void try_to_unmap(struct folio *, enum ttu_flags flags);
struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
void *owner, struct folio **foliop);
/* Avoid racy checks */
#define PVMW_SYNC (1 << 0)
/* Look for migration entries rather than present PTEs */
#define PVMW_MIGRATION (1 << 1)
struct page_vma_mapped_walk {
unsigned long pfn;
unsigned long nr_pages;
pgoff_t pgoff;
struct vm_area_struct *vma;
unsigned long address;
pmd_t *pmd;
pte_t *pte;
spinlock_t *ptl;
unsigned int flags;
};
#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \
struct page_vma_mapped_walk name = { \
.pfn = folio_pfn(_folio), \
.nr_pages = folio_nr_pages(_folio), \
.pgoff = folio_pgoff(_folio), \
.vma = _vma, \
.address = _address, \
.flags = _flags, \
}
static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
{
/* HugeTLB pte is set to the relevant page table entry without pte_mapped. */
if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma))
pte_unmap(pvmw->pte);
if (pvmw->ptl)
spin_unlock(pvmw->ptl);
}
/**
* page_vma_mapped_walk_restart - Restart the page table walk.
* @pvmw: Pointer to struct page_vma_mapped_walk.
*
* It restarts the page table walk when changes occur in the page
* table, such as splitting a PMD. Ensures that the PTL held during
* the previous walk is released and resets the state to allow for
* a new walk starting at the current address stored in pvmw->address.
*/
static inline void
page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw)
{
WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte);
if (likely(pvmw->ptl))
spin_unlock(pvmw->ptl);
else
WARN_ON_ONCE(1);
pvmw->ptl = NULL;
pvmw->pmd = NULL;
pvmw->pte = NULL;
}
bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);
unsigned long page_address_in_vma(const struct folio *folio,
const struct page *, const struct vm_area_struct *);
/*
* Cleans the PTEs of shared mappings.
* (and since clean PTEs should also be readonly, write protects them too)
*
* returns the number of cleaned PTEs.
*/
int folio_mkclean(struct folio *);
int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff,
unsigned long pfn, unsigned long nr_pages);
int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
struct vm_area_struct *vma);
enum rmp_flags {
RMP_LOCKED = 1 << 0,
RMP_USE_SHARED_ZEROPAGE = 1 << 1,
};
void remove_migration_ptes(struct folio *src, struct folio *dst, int flags);
/*
* rmap_walk_control: To control rmap traversing for specific needs
*
* arg: passed to rmap_one() and invalid_vma()
* try_lock: bail out if the rmap lock is contended
* contended: indicate the rmap traversal bailed out due to lock contention
* rmap_one: executed on each vma where page is mapped
* done: for checking traversing termination condition
* anon_lock: for getting anon_lock by optimized way rather than default
* invalid_vma: for skipping uninterested vma
*/
struct rmap_walk_control {
void *arg;
bool try_lock;
bool contended;
/*
* Return false if page table scanning in rmap_walk should be stopped.
* Otherwise, return true.
*/
bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma,
unsigned long addr, void *arg);
int (*done)(struct folio *folio);
struct anon_vma *(*anon_lock)(const struct folio *folio,
struct rmap_walk_control *rwc);
bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
};
void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc);
void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc);
struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
struct rmap_walk_control *rwc);
#else /* !CONFIG_MMU */
#define anon_vma_init() do {} while (0)
#define anon_vma_prepare(vma) (0)
static inline int folio_referenced(struct folio *folio, int is_locked,
struct mem_cgroup *memcg,
unsigned long *vm_flags)
{
*vm_flags = 0;
return 0;
}
static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
}
static inline int folio_mkclean(struct folio *folio)
{
return 0;
}
#endif /* CONFIG_MMU */
#endif /* _LINUX_RMAP_H */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020 ARM Ltd.
*/
#ifndef __ASM_MTE_H
#define __ASM_MTE_H
#include <asm/compiler.h>
#include <asm/mte-def.h>
#ifndef __ASSEMBLY__
#include <linux/bitfield.h>
#include <linux/kasan-enabled.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <asm/pgtable-types.h>
void mte_clear_page_tags(void *addr);
unsigned long mte_copy_tags_from_user(void *to, const void __user *from,
unsigned long n);
unsigned long mte_copy_tags_to_user(void __user *to, void *from,
unsigned long n);
int mte_save_tags(struct page *page);
void mte_save_page_tags(const void *page_addr, void *tag_storage);
void mte_restore_tags(swp_entry_t entry, struct page *page);
void mte_restore_page_tags(void *page_addr, const void *tag_storage);
void mte_invalidate_tags(int type, pgoff_t offset);
void mte_invalidate_tags_area(int type);
void *mte_allocate_tag_storage(void);
void mte_free_tag_storage(char *storage);
#ifdef CONFIG_ARM64_MTE
/* track which pages have valid allocation tags */
#define PG_mte_tagged PG_arch_2
/* simple lock to avoid multiple threads tagging the same page */
#define PG_mte_lock PG_arch_3
static inline void set_page_mte_tagged(struct page *page)
{
VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page)));
/*
* Ensure that the tags written prior to this function are visible
* before the page flags update.
*/
smp_wmb();
set_bit(PG_mte_tagged, &page->flags);
}
static inline bool page_mte_tagged(struct page *page)
{
bool ret = test_bit(PG_mte_tagged, &page->flags);
VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page)));
/*
* If the page is tagged, ensure ordering with a likely subsequent
* read of the tags.
*/
if (ret)
smp_rmb();
return ret;
}
/*
* Lock the page for tagging and return 'true' if the page can be tagged,
* 'false' if already tagged. PG_mte_tagged is never cleared and therefore the
* locking only happens once for page initialisation.
*
* The page MTE lock state:
*
* Locked: PG_mte_lock && !PG_mte_tagged
* Unlocked: !PG_mte_lock || PG_mte_tagged
*
* Acquire semantics only if the page is tagged (returning 'false').
*/
static inline bool try_page_mte_tagging(struct page *page)
{
VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); if (!test_and_set_bit(PG_mte_lock, &page->flags))
return true;
/*
* The tags are either being initialised or may have been initialised
* already. Check if the PG_mte_tagged flag has been set or wait
* otherwise.
*/
smp_cond_load_acquire(&page->flags, VAL & (1UL << PG_mte_tagged));
return false;
}
void mte_zero_clear_page_tags(void *addr);
void mte_sync_tags(pte_t pte, unsigned int nr_pages);
void mte_copy_page_tags(void *kto, const void *kfrom);
void mte_thread_init_user(void);
void mte_thread_switch(struct task_struct *next);
void mte_cpu_setup(void);
void mte_suspend_enter(void);
void mte_suspend_exit(void);
long set_mte_ctrl(struct task_struct *task, unsigned long arg);
long get_mte_ctrl(struct task_struct *task);
int mte_ptrace_copy_tags(struct task_struct *child, long request,
unsigned long addr, unsigned long data);
size_t mte_probe_user_range(const char __user *uaddr, size_t size);
#else /* CONFIG_ARM64_MTE */
/* unused if !CONFIG_ARM64_MTE, silence the compiler */
#define PG_mte_tagged 0
static inline void set_page_mte_tagged(struct page *page)
{
}
static inline bool page_mte_tagged(struct page *page)
{
return false;
}
static inline bool try_page_mte_tagging(struct page *page)
{
return false;
}
static inline void mte_zero_clear_page_tags(void *addr)
{
}
static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages)
{
}
static inline void mte_copy_page_tags(void *kto, const void *kfrom)
{
}
static inline void mte_thread_init_user(void)
{
}
static inline void mte_thread_switch(struct task_struct *next)
{
}
static inline void mte_suspend_enter(void)
{
}
static inline void mte_suspend_exit(void)
{
}
static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg)
{
return 0;
}
static inline long get_mte_ctrl(struct task_struct *task)
{
return 0;
}
static inline int mte_ptrace_copy_tags(struct task_struct *child,
long request, unsigned long addr,
unsigned long data)
{
return -EIO;
}
#endif /* CONFIG_ARM64_MTE */
#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_ARM64_MTE)
static inline void folio_set_hugetlb_mte_tagged(struct folio *folio)
{
VM_WARN_ON_ONCE(!folio_test_hugetlb(folio));
/*
* Ensure that the tags written prior to this function are visible
* before the folio flags update.
*/
smp_wmb();
set_bit(PG_mte_tagged, &folio->flags);
}
static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio)
{
bool ret = test_bit(PG_mte_tagged, &folio->flags);
VM_WARN_ON_ONCE(!folio_test_hugetlb(folio));
/*
* If the folio is tagged, ensure ordering with a likely subsequent
* read of the tags.
*/
if (ret) smp_rmb();
return ret;
}
static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio)
{
VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); if (!test_and_set_bit(PG_mte_lock, &folio->flags))
return true;
/*
* The tags are either being initialised or may have been initialised
* already. Check if the PG_mte_tagged flag has been set or wait
* otherwise.
*/
smp_cond_load_acquire(&folio->flags, VAL & (1UL << PG_mte_tagged));
return false;
}
#else
static inline void folio_set_hugetlb_mte_tagged(struct folio *folio)
{
}
static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio)
{
return false;
}
static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio)
{
return false;
}
#endif
static inline void mte_disable_tco_entry(struct task_struct *task)
{
if (!system_supports_mte())
return;
/*
* Re-enable tag checking (TCO set on exception entry). This is only
* necessary if MTE is enabled in either the kernel or the userspace
* task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set
* for both). With MTE disabled in the kernel and disabled or
* asynchronous in userspace, tag check faults (including in uaccesses)
* are not reported, therefore there is no need to re-enable checking.
* This is beneficial on microarchitectures where re-enabling TCO is
* expensive.
*/
if (kasan_hw_tags_enabled() ||
(task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT)))
asm volatile(SET_PSTATE_TCO(0));
}
#ifdef CONFIG_KASAN_HW_TAGS
void mte_check_tfsr_el1(void);
static inline void mte_check_tfsr_entry(void)
{
if (!kasan_hw_tags_enabled())
return;
mte_check_tfsr_el1();
}
static inline void mte_check_tfsr_exit(void)
{
if (!kasan_hw_tags_enabled())
return;
/*
* The asynchronous faults are sync'ed automatically with
* TFSR_EL1 on kernel entry but for exit an explicit dsb()
* is required.
*/
dsb(nsh);
isb();
mte_check_tfsr_el1();
}
#else
static inline void mte_check_tfsr_el1(void)
{
}
static inline void mte_check_tfsr_entry(void)
{
}
static inline void mte_check_tfsr_exit(void)
{
}
#endif /* CONFIG_KASAN_HW_TAGS */
#endif /* __ASSEMBLY__ */
#endif /* __ASM_MTE_H */
/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM vmalloc
#if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_VMALLOC_H
#include <linux/tracepoint.h>
/**
* alloc_vmap_area - called when a new vmap allocation occurs
* @addr: an allocated address
* @size: a requested size
* @align: a requested alignment
* @vstart: a requested start range
* @vend: a requested end range
* @failed: an allocation failed or not
*
* This event is used for a debug purpose, it can give an extra
* information for a developer about how often it occurs and which
* parameters are passed for further validation.
*/
TRACE_EVENT(alloc_vmap_area,
TP_PROTO(unsigned long addr, unsigned long size, unsigned long align,
unsigned long vstart, unsigned long vend, int failed),
TP_ARGS(addr, size, align, vstart, vend, failed),
TP_STRUCT__entry(
__field(unsigned long, addr)
__field(unsigned long, size)
__field(unsigned long, align)
__field(unsigned long, vstart)
__field(unsigned long, vend)
__field(int, failed)
),
TP_fast_assign(
__entry->addr = addr;
__entry->size = size;
__entry->align = align;
__entry->vstart = vstart;
__entry->vend = vend;
__entry->failed = failed;
),
TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d",
__entry->addr, __entry->size, __entry->align,
__entry->vstart, __entry->vend, __entry->failed)
);
/**
* purge_vmap_area_lazy - called when vmap areas were lazily freed
* @start: purging start address
* @end: purging end address
* @npurged: numbed of purged vmap areas
*
* This event is used for a debug purpose. It gives some
* indication about start:end range and how many objects
* are released.
*/
TRACE_EVENT(purge_vmap_area_lazy,
TP_PROTO(unsigned long start, unsigned long end,
unsigned int npurged),
TP_ARGS(start, end, npurged),
TP_STRUCT__entry(
__field(unsigned long, start)
__field(unsigned long, end)
__field(unsigned int, npurged)
),
TP_fast_assign(
__entry->start = start;
__entry->end = end;
__entry->npurged = npurged;
),
TP_printk("start=0x%lx end=0x%lx num_purged=%u",
__entry->start, __entry->end, __entry->npurged)
);
/**
* free_vmap_area_noflush - called when a vmap area is freed
* @va_start: a start address of VA
* @nr_lazy: number of current lazy pages
* @nr_lazy_max: number of maximum lazy pages
*
* This event is used for a debug purpose. It gives some
* indication about a VA that is released, number of current
* outstanding areas and a maximum allowed threshold before
* dropping all of them.
*/
TRACE_EVENT(free_vmap_area_noflush,
TP_PROTO(unsigned long va_start, unsigned long nr_lazy,
unsigned long nr_lazy_max),
TP_ARGS(va_start, nr_lazy, nr_lazy_max),
TP_STRUCT__entry(
__field(unsigned long, va_start)
__field(unsigned long, nr_lazy)
__field(unsigned long, nr_lazy_max)
),
TP_fast_assign(
__entry->va_start = va_start;
__entry->nr_lazy = nr_lazy;
__entry->nr_lazy_max = nr_lazy_max;
),
TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu",
__entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max)
);
#endif /* _TRACE_VMALLOC_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* I/O iterator iteration building functions.
*
* Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#ifndef _LINUX_IOV_ITER_H
#define _LINUX_IOV_ITER_H
#include <linux/uio.h>
#include <linux/bvec.h>
#include <linux/folio_queue.h>
typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len,
void *priv, void *priv2);
typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len,
void *priv, void *priv2);
/*
* Handle ITER_UBUF.
*/
static __always_inline
size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_ustep_f step)
{
void __user *base = iter->ubuf;
size_t progress = 0, remain;
remain = step(base + iter->iov_offset, 0, len, priv, priv2);
progress = len - remain;
iter->iov_offset += progress;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_IOVEC.
*/
static __always_inline
size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_ustep_f step)
{
const struct iovec *p = iter->__iov;
size_t progress = 0, skip = iter->iov_offset;
do {
size_t remain, consumed;
size_t part = min(len, p->iov_len - skip);
if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2);
consumed = part - remain;
progress += consumed;
skip += consumed;
len -= consumed;
if (skip < p->iov_len)
break;
}
p++;
skip = 0;
} while (len);
iter->nr_segs -= p - iter->__iov;
iter->__iov = p;
iter->iov_offset = skip;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_KVEC.
*/
static __always_inline
size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_step_f step)
{
const struct kvec *p = iter->kvec;
size_t progress = 0, skip = iter->iov_offset;
do {
size_t remain, consumed;
size_t part = min(len, p->iov_len - skip);
if (likely(part)) {
remain = step(p->iov_base + skip, progress, part, priv, priv2);
consumed = part - remain;
progress += consumed;
skip += consumed;
len -= consumed;
if (skip < p->iov_len)
break;
}
p++;
skip = 0;
} while (len);
iter->nr_segs -= p - iter->kvec;
iter->kvec = p;
iter->iov_offset = skip;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_BVEC.
*/
static __always_inline
size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_step_f step)
{
const struct bio_vec *p = iter->bvec;
size_t progress = 0, skip = iter->iov_offset;
do {
size_t remain, consumed;
size_t offset = p->bv_offset + skip, part;
void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE);
part = min3(len,
(size_t)(p->bv_len - skip),
(size_t)(PAGE_SIZE - offset % PAGE_SIZE));
remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2);
kunmap_local(kaddr);
consumed = part - remain;
len -= consumed;
progress += consumed;
skip += consumed;
if (skip >= p->bv_len) {
skip = 0;
p++;
}
if (remain)
break;
} while (len);
iter->nr_segs -= p - iter->bvec;
iter->bvec = p;
iter->iov_offset = skip;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_FOLIOQ.
*/
static __always_inline
size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_step_f step)
{
const struct folio_queue *folioq = iter->folioq;
unsigned int slot = iter->folioq_slot;
size_t progress = 0, skip = iter->iov_offset;
if (slot == folioq_nr_slots(folioq)) {
/* The iterator may have been extended. */
folioq = folioq->next;
slot = 0;
}
do {
struct folio *folio = folioq_folio(folioq, slot);
size_t part, remain, consumed;
size_t fsize;
void *base;
if (!folio)
break;
fsize = folioq_folio_size(folioq, slot);
base = kmap_local_folio(folio, skip);
part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
remain = step(base, progress, part, priv, priv2);
kunmap_local(base);
consumed = part - remain;
len -= consumed;
progress += consumed;
skip += consumed;
if (skip >= fsize) {
skip = 0;
slot++;
if (slot == folioq_nr_slots(folioq) && folioq->next) {
folioq = folioq->next;
slot = 0;
}
}
if (remain)
break;
} while (len);
iter->folioq_slot = slot;
iter->folioq = folioq;
iter->iov_offset = skip;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_XARRAY.
*/
static __always_inline
size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_step_f step)
{
struct folio *folio;
size_t progress = 0;
loff_t start = iter->xarray_start + iter->iov_offset;
pgoff_t index = start / PAGE_SIZE;
XA_STATE(xas, iter->xarray, index);
rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) {
size_t remain, consumed, offset, part, flen;
if (xas_retry(&xas, folio))
continue;
if (WARN_ON(xa_is_value(folio)))
break;
if (WARN_ON(folio_test_hugetlb(folio)))
break;
offset = offset_in_folio(folio, start + progress);
flen = min(folio_size(folio) - offset, len);
while (flen) {
void *base = kmap_local_folio(folio, offset);
part = min_t(size_t, flen,
PAGE_SIZE - offset_in_page(offset));
remain = step(base, progress, part, priv, priv2);
kunmap_local(base);
consumed = part - remain;
progress += consumed;
len -= consumed;
if (remain || len == 0)
goto out;
flen -= consumed;
offset += consumed;
}
}
out:
rcu_read_unlock();
iter->iov_offset += progress;
iter->count -= progress;
return progress;
}
/*
* Handle ITER_DISCARD.
*/
static __always_inline
size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2,
iov_step_f step)
{
size_t progress = len;
iter->count -= progress;
return progress;
}
/**
* iterate_and_advance2 - Iterate over an iterator
* @iter: The iterator to iterate over.
* @len: The amount to iterate over.
* @priv: Data for the step functions.
* @priv2: More data for the step functions.
* @ustep: Function for UBUF/IOVEC iterators; given __user addresses.
* @step: Function for other iterators; given kernel addresses.
*
* Iterate over the next part of an iterator, up to the specified length. The
* buffer is presented in segments, which for kernel iteration are broken up by
* physical pages and mapped, with the mapped address being presented.
*
* Two step functions, @step and @ustep, must be provided, one for handling
* mapped kernel addresses and the other is given user addresses which have the
* potential to fault since no pinning is performed.
*
* The step functions are passed the address and length of the segment, @priv,
* @priv2 and the amount of data so far iterated over (which can, for example,
* be added to @priv to point to the right part of a second buffer). The step
* functions should return the amount of the segment they didn't process (ie. 0
* indicates complete processsing).
*
* This function returns the amount of data processed (ie. 0 means nothing was
* processed and the value of @len means processes to completion).
*/
static __always_inline
size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv,
void *priv2, iov_ustep_f ustep, iov_step_f step)
{
if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len))
return 0;
if (likely(iter_is_ubuf(iter)))
return iterate_ubuf(iter, len, priv, priv2, ustep);
if (likely(iter_is_iovec(iter)))
return iterate_iovec(iter, len, priv, priv2, ustep);
if (iov_iter_is_bvec(iter))
return iterate_bvec(iter, len, priv, priv2, step);
if (iov_iter_is_kvec(iter))
return iterate_kvec(iter, len, priv, priv2, step);
if (iov_iter_is_folioq(iter))
return iterate_folioq(iter, len, priv, priv2, step);
if (iov_iter_is_xarray(iter))
return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step);
}
/**
* iterate_and_advance - Iterate over an iterator
* @iter: The iterator to iterate over.
* @len: The amount to iterate over.
* @priv: Data for the step functions.
* @ustep: Function for UBUF/IOVEC iterators; given __user addresses.
* @step: Function for other iterators; given kernel addresses.
*
* As iterate_and_advance2(), but priv2 is always NULL.
*/
static __always_inline
size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv,
iov_ustep_f ustep, iov_step_f step)
{
return iterate_and_advance2(iter, len, priv, NULL, ustep, step);
}
/**
* iterate_and_advance_kernel - Iterate over a kernel-internal iterator
* @iter: The iterator to iterate over.
* @len: The amount to iterate over.
* @priv: Data for the step functions.
* @priv2: More data for the step functions.
* @step: Function for other iterators; given kernel addresses.
*
* Iterate over the next part of an iterator, up to the specified length. The
* buffer is presented in segments, which for kernel iteration are broken up by
* physical pages and mapped, with the mapped address being presented.
*
* [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type
* iterators; it will not handle UBUF or IOVEC-type iterators.
*
* A step functions, @step, must be provided, one for handling mapped kernel
* addresses and the other is given user addresses which have the potential to
* fault since no pinning is performed.
*
* The step functions are passed the address and length of the segment, @priv,
* @priv2 and the amount of data so far iterated over (which can, for example,
* be added to @priv to point to the right part of a second buffer). The step
* functions should return the amount of the segment they didn't process (ie. 0
* indicates complete processsing).
*
* This function returns the amount of data processed (ie. 0 means nothing was
* processed and the value of @len means processes to completion).
*/
static __always_inline
size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv,
void *priv2, iov_step_f step)
{
if (unlikely(iter->count < len))
len = iter->count;
if (unlikely(!len))
return 0;
if (iov_iter_is_bvec(iter))
return iterate_bvec(iter, len, priv, priv2, step);
if (iov_iter_is_kvec(iter))
return iterate_kvec(iter, len, priv, priv2, step);
if (iov_iter_is_folioq(iter))
return iterate_folioq(iter, len, priv, priv2, step);
if (iov_iter_is_xarray(iter))
return iterate_xarray(iter, len, priv, priv2, step);
return iterate_discard(iter, len, priv, priv2, step);
}
#endif /* _LINUX_IOV_ITER_H */
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Skb ref helpers.
*
*/
#ifndef _LINUX_SKBUFF_REF_H
#define _LINUX_SKBUFF_REF_H
#include <linux/skbuff.h>
/**
* __skb_frag_ref - take an addition reference on a paged fragment.
* @frag: the paged fragment
*
* Takes an additional reference on the paged fragment @frag.
*/
static inline void __skb_frag_ref(skb_frag_t *frag)
{
get_page(skb_frag_page(frag));
}
/**
* skb_frag_ref - take an addition reference on a paged fragment of an skb.
* @skb: the buffer
* @f: the fragment offset.
*
* Takes an additional reference on the @f'th paged fragment of @skb.
*/
static inline void skb_frag_ref(struct sk_buff *skb, int f)
{
__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
}
bool napi_pp_put_page(netmem_ref netmem);
static inline void skb_page_unref(netmem_ref netmem, bool recycle)
{
#ifdef CONFIG_PAGE_POOL
if (recycle && napi_pp_put_page(netmem))
return;
#endif
put_page(netmem_to_page(netmem));
}
/**
* __skb_frag_unref - release a reference on a paged fragment.
* @frag: the paged fragment
* @recycle: recycle the page if allocated via page_pool
*
* Releases a reference on the paged fragment @frag
* or recycles the page via the page_pool API.
*/
static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
{
skb_page_unref(skb_frag_netmem(frag), recycle);
}
/**
* skb_frag_unref - release a reference on a paged fragment of an skb.
* @skb: the buffer
* @f: the fragment offset
*
* Releases a reference on the @f'th paged fragment of @skb.
*/
static inline void skb_frag_unref(struct sk_buff *skb, int f)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
if (!skb_zcopy_managed(skb)) __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle);
}
#endif /* _LINUX_SKBUFF_REF_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MMU_NOTIFIER_H
#define _LINUX_MMU_NOTIFIER_H
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/mm_types.h>
#include <linux/mmap_lock.h>
#include <linux/srcu.h>
#include <linux/interval_tree.h>
struct mmu_notifier_subscriptions;
struct mmu_notifier;
struct mmu_notifier_range;
struct mmu_interval_notifier;
/**
* enum mmu_notifier_event - reason for the mmu notifier callback
* @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that
* move the range
*
* @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like
* madvise() or replacing a page by another one, ...).
*
* @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range
* ie using the vma access permission (vm_page_prot) to update the whole range
* is enough no need to inspect changes to the CPU page table (mprotect()
* syscall)
*
* @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for
* pages in the range so to mirror those changes the user must inspect the CPU
* page table (from the end callback).
*
* @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same
* access flags). User should soft dirty the page in the end callback to make
* sure that anyone relying on soft dirtiness catch pages that might be written
* through non CPU mappings.
*
* @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
* that the mm refcount is zero and the range is no longer accessible.
*
* @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal
* a device driver to possibly ignore the invalidation if the
* owner field matches the driver's device private pgmap owner.
*
* @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive.
* The owner is initialized to the value provided by the caller of
* make_device_exclusive(), such that this caller can filter out these
* events.
*/
enum mmu_notifier_event {
MMU_NOTIFY_UNMAP = 0,
MMU_NOTIFY_CLEAR,
MMU_NOTIFY_PROTECTION_VMA,
MMU_NOTIFY_PROTECTION_PAGE,
MMU_NOTIFY_SOFT_DIRTY,
MMU_NOTIFY_RELEASE,
MMU_NOTIFY_MIGRATE,
MMU_NOTIFY_EXCLUSIVE,
};
#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
struct mmu_notifier_ops {
/*
* Called either by mmu_notifier_unregister or when the mm is
* being destroyed by exit_mmap, always before all pages are
* freed. This can run concurrently with other mmu notifier
* methods (the ones invoked outside the mm context) and it
* should tear down all secondary mmu mappings and freeze the
* secondary mmu. If this method isn't implemented you've to
* be sure that nothing could possibly write to the pages
* through the secondary mmu by the time the last thread with
* tsk->mm == mm exits.
*
* As side note: the pages freed after ->release returns could
* be immediately reallocated by the gart at an alias physical
* address with a different cache model, so if ->release isn't
* implemented because all _software_ driven memory accesses
* through the secondary mmu are terminated by the time the
* last thread of this mm quits, you've also to be sure that
* speculative _hardware_ operations can't allocate dirty
* cachelines in the cpu that could not be snooped and made
* coherent with the other read and write operations happening
* through the gart alias address, so leading to memory
* corruption.
*/
void (*release)(struct mmu_notifier *subscription,
struct mm_struct *mm);
/*
* clear_flush_young is called after the VM is
* test-and-clearing the young/accessed bitflag in the
* pte. This way the VM will provide proper aging to the
* accesses to the page through the secondary MMUs and not
* only to the ones through the Linux pte.
* Start-end is necessary in case the secondary MMU is mapping the page
* at a smaller granularity than the primary MMU.
*/
int (*clear_flush_young)(struct mmu_notifier *subscription,
struct mm_struct *mm,
unsigned long start,
unsigned long end);
/*
* clear_young is a lightweight version of clear_flush_young. Like the
* latter, it is supposed to test-and-clear the young/accessed bitflag
* in the secondary pte, but it may omit flushing the secondary tlb.
*/
int (*clear_young)(struct mmu_notifier *subscription,
struct mm_struct *mm,
unsigned long start,
unsigned long end);
/*
* test_young is called to check the young/accessed bitflag in
* the secondary pte. This is used to know if the page is
* frequently used without actually clearing the flag or tearing
* down the secondary mapping on the page.
*/
int (*test_young)(struct mmu_notifier *subscription,
struct mm_struct *mm,
unsigned long address);
/*
* invalidate_range_start() and invalidate_range_end() must be
* paired and are called only when the mmap_lock and/or the
* locks protecting the reverse maps are held. If the subsystem
* can't guarantee that no additional references are taken to
* the pages in the range, it has to implement the
* invalidate_range() notifier to remove any references taken
* after invalidate_range_start().
*
* Invalidation of multiple concurrent ranges may be
* optionally permitted by the driver. Either way the
* establishment of sptes is forbidden in the range passed to
* invalidate_range_begin/end for the whole duration of the
* invalidate_range_begin/end critical section.
*
* invalidate_range_start() is called when all pages in the
* range are still mapped and have at least a refcount of one.
*
* invalidate_range_end() is called when all pages in the
* range have been unmapped and the pages have been freed by
* the VM.
*
* The VM will remove the page table entries and potentially
* the page between invalidate_range_start() and
* invalidate_range_end(). If the page must not be freed
* because of pending I/O or other circumstances then the
* invalidate_range_start() callback (or the initial mapping
* by the driver) must make sure that the refcount is kept
* elevated.
*
* If the driver increases the refcount when the pages are
* initially mapped into an address space then either
* invalidate_range_start() or invalidate_range_end() may
* decrease the refcount. If the refcount is decreased on
* invalidate_range_start() then the VM can free pages as page
* table entries are removed. If the refcount is only
* dropped on invalidate_range_end() then the driver itself
* will drop the last refcount but it must take care to flush
* any secondary tlb before doing the final free on the
* page. Pages will no longer be referenced by the linux
* address space but may still be referenced by sptes until
* the last refcount is dropped.
*
* If blockable argument is set to false then the callback cannot
* sleep and has to return with -EAGAIN if sleeping would be required.
* 0 should be returned otherwise. Please note that notifiers that can
* fail invalidate_range_start are not allowed to implement
* invalidate_range_end, as there is no mechanism for informing the
* notifier that its start failed.
*/
int (*invalidate_range_start)(struct mmu_notifier *subscription,
const struct mmu_notifier_range *range);
void (*invalidate_range_end)(struct mmu_notifier *subscription,
const struct mmu_notifier_range *range);
/*
* arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB
* which shares page-tables with the CPU. The
* invalidate_range_start()/end() callbacks should not be implemented as
* invalidate_secondary_tlbs() already catches the points in time when
* an external TLB needs to be flushed.
*
* This requires arch_invalidate_secondary_tlbs() to be called while
* holding the ptl spin-lock and therefore this callback is not allowed
* to sleep.
*
* This is called by architecture code whenever invalidating a TLB
* entry. It is assumed that any secondary TLB has the same rules for
* when invalidations are required. If this is not the case architecture
* code will need to call this explicitly when required for secondary
* TLB invalidation.
*/
void (*arch_invalidate_secondary_tlbs)(
struct mmu_notifier *subscription,
struct mm_struct *mm,
unsigned long start,
unsigned long end);
/*
* These callbacks are used with the get/put interface to manage the
* lifetime of the mmu_notifier memory. alloc_notifier() returns a new
* notifier for use with the mm.
*
* free_notifier() is only called after the mmu_notifier has been
* fully put, calls to any ops callback are prevented and no ops
* callbacks are currently running. It is called from a SRCU callback
* and cannot sleep.
*/
struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm);
void (*free_notifier)(struct mmu_notifier *subscription);
};
/*
* The notifier chains are protected by mmap_lock and/or the reverse map
* semaphores. Notifier chains are only changed when all reverse maps and
* the mmap_lock locks are taken.
*
* Therefore notifier chains can only be traversed when either
*
* 1. mmap_lock is held.
* 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem).
* 3. No other concurrent thread can access the list (release)
*/
struct mmu_notifier {
struct hlist_node hlist;
const struct mmu_notifier_ops *ops;
struct mm_struct *mm;
struct rcu_head rcu;
unsigned int users;
};
/**
* struct mmu_interval_notifier_ops
* @invalidate: Upon return the caller must stop using any SPTEs within this
* range. This function can sleep. Return false only if sleeping
* was required but mmu_notifier_range_blockable(range) is false.
*/
struct mmu_interval_notifier_ops {
bool (*invalidate)(struct mmu_interval_notifier *interval_sub,
const struct mmu_notifier_range *range,
unsigned long cur_seq);
};
struct mmu_interval_notifier {
struct interval_tree_node interval_tree;
const struct mmu_interval_notifier_ops *ops;
struct mm_struct *mm;
struct hlist_node deferred_item;
unsigned long invalidate_seq;
};
#ifdef CONFIG_MMU_NOTIFIER
#ifdef CONFIG_LOCKDEP
extern struct lockdep_map __mmu_notifier_invalidate_range_start_map;
#endif
struct mmu_notifier_range {
struct mm_struct *mm;
unsigned long start;
unsigned long end;
unsigned flags;
enum mmu_notifier_event event;
void *owner;
};
static inline int mm_has_notifiers(struct mm_struct *mm)
{
return unlikely(mm->notifier_subscriptions);
}
struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops,
struct mm_struct *mm);
static inline struct mmu_notifier *
mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm)
{
struct mmu_notifier *ret;
mmap_write_lock(mm);
ret = mmu_notifier_get_locked(ops, mm);
mmap_write_unlock(mm);
return ret;
}
void mmu_notifier_put(struct mmu_notifier *subscription);
void mmu_notifier_synchronize(void);
extern int mmu_notifier_register(struct mmu_notifier *subscription,
struct mm_struct *mm);
extern int __mmu_notifier_register(struct mmu_notifier *subscription,
struct mm_struct *mm);
extern void mmu_notifier_unregister(struct mmu_notifier *subscription,
struct mm_struct *mm);
unsigned long
mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub);
int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
struct mm_struct *mm, unsigned long start,
unsigned long length,
const struct mmu_interval_notifier_ops *ops);
int mmu_interval_notifier_insert_locked(
struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
unsigned long start, unsigned long length,
const struct mmu_interval_notifier_ops *ops);
void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub);
/**
* mmu_interval_set_seq - Save the invalidation sequence
* @interval_sub - The subscription passed to invalidate
* @cur_seq - The cur_seq passed to the invalidate() callback
*
* This must be called unconditionally from the invalidate callback of a
* struct mmu_interval_notifier_ops under the same lock that is used to call
* mmu_interval_read_retry(). It updates the sequence number for later use by
* mmu_interval_read_retry(). The provided cur_seq will always be odd.
*
* If the caller does not call mmu_interval_read_begin() or
* mmu_interval_read_retry() then this call is not required.
*/
static inline void
mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
unsigned long cur_seq)
{
WRITE_ONCE(interval_sub->invalidate_seq, cur_seq);
}
/**
* mmu_interval_read_retry - End a read side critical section against a VA range
* interval_sub: The subscription
* seq: The return of the paired mmu_interval_read_begin()
*
* This MUST be called under a user provided lock that is also held
* unconditionally by op->invalidate() when it calls mmu_interval_set_seq().
*
* Each call should be paired with a single mmu_interval_read_begin() and
* should be used to conclude the read side.
*
* Returns true if an invalidation collided with this critical section, and
* the caller should retry.
*/
static inline bool
mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub,
unsigned long seq)
{
return interval_sub->invalidate_seq != seq;
}
/**
* mmu_interval_check_retry - Test if a collision has occurred
* interval_sub: The subscription
* seq: The return of the matching mmu_interval_read_begin()
*
* This can be used in the critical section between mmu_interval_read_begin()
* and mmu_interval_read_retry(). A return of true indicates an invalidation
* has collided with this critical region and a future
* mmu_interval_read_retry() will return true.
*
* False is not reliable and only suggests a collision may not have
* occurred. It can be called many times and does not have to hold the user
* provided lock.
*
* This call can be used as part of loops and other expensive operations to
* expedite a retry.
*/
static inline bool
mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub,
unsigned long seq)
{
/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
return READ_ONCE(interval_sub->invalidate_seq) != seq;
}
extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm);
extern void __mmu_notifier_release(struct mm_struct *mm);
extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long start,
unsigned long end);
extern int __mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long start,
unsigned long end);
extern int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address);
extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r);
extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r);
extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
unsigned long start, unsigned long end);
extern bool
mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range);
static inline bool
mmu_notifier_range_blockable(const struct mmu_notifier_range *range)
{
return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE);
}
static inline void mmu_notifier_release(struct mm_struct *mm)
{
if (mm_has_notifiers(mm))
__mmu_notifier_release(mm);
}
static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
if (mm_has_notifiers(mm))
return __mmu_notifier_clear_flush_young(mm, start, end);
return 0;
}
static inline int mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
if (mm_has_notifiers(mm))
return __mmu_notifier_clear_young(mm, start, end);
return 0;
}
static inline int mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
if (mm_has_notifiers(mm))
return __mmu_notifier_test_young(mm, address);
return 0;
}
static inline void
mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
{
might_sleep();
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE;
__mmu_notifier_invalidate_range_start(range);
}
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
}
/*
* This version of mmu_notifier_invalidate_range_start() avoids blocking, but it
* can return an error if a notifier can't proceed without blocking, in which
* case you're not allowed to modify PTEs in the specified range.
*
* This is mainly intended for OOM handling.
*/
static inline int __must_check
mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range)
{
int ret = 0;
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
if (mm_has_notifiers(range->mm)) {
range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE;
ret = __mmu_notifier_invalidate_range_start(range);
}
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
return ret;
}
static inline void
mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
{
if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range);
}
static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
if (mm_has_notifiers(mm)) __mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
}
static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
{
mm->notifier_subscriptions = NULL;
}
static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
{
if (mm_has_notifiers(mm))
__mmu_notifier_subscriptions_destroy(mm);
}
static inline void mmu_notifier_range_init(struct mmu_notifier_range *range,
enum mmu_notifier_event event,
unsigned flags,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
range->event = event;
range->mm = mm;
range->start = start;
range->end = end;
range->flags = flags;
}
static inline void mmu_notifier_range_init_owner(
struct mmu_notifier_range *range,
enum mmu_notifier_event event, unsigned int flags,
struct mm_struct *mm, unsigned long start,
unsigned long end, void *owner)
{
mmu_notifier_range_init(range, event, flags, mm, start, end);
range->owner = owner;
}
#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \
({ \
int __young; \
struct vm_area_struct *___vma = __vma; \
unsigned long ___address = __address; \
__young = ptep_clear_flush_young(___vma, ___address, __ptep); \
__young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \
___address, \
___address + \
PAGE_SIZE); \
__young; \
})
#define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \
({ \
int __young; \
struct vm_area_struct *___vma = __vma; \
unsigned long ___address = __address; \
__young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \
__young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \
___address, \
___address + \
PMD_SIZE); \
__young; \
})
#define ptep_clear_young_notify(__vma, __address, __ptep) \
({ \
int __young; \
struct vm_area_struct *___vma = __vma; \
unsigned long ___address = __address; \
__young = ptep_test_and_clear_young(___vma, ___address, __ptep);\
__young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \
___address + PAGE_SIZE); \
__young; \
})
#define pmdp_clear_young_notify(__vma, __address, __pmdp) \
({ \
int __young; \
struct vm_area_struct *___vma = __vma; \
unsigned long ___address = __address; \
__young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\
__young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \
___address + PMD_SIZE); \
__young; \
})
#else /* CONFIG_MMU_NOTIFIER */
struct mmu_notifier_range {
unsigned long start;
unsigned long end;
};
static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range,
unsigned long start,
unsigned long end)
{
range->start = start;
range->end = end;
}
#define mmu_notifier_range_init(range,event,flags,mm,start,end) \
_mmu_notifier_range_init(range, start, end)
#define mmu_notifier_range_init_owner(range, event, flags, mm, start, \
end, owner) \
_mmu_notifier_range_init(range, start, end)
static inline bool
mmu_notifier_range_blockable(const struct mmu_notifier_range *range)
{
return true;
}
static inline int mm_has_notifiers(struct mm_struct *mm)
{
return 0;
}
static inline void mmu_notifier_release(struct mm_struct *mm)
{
}
static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
return 0;
}
static inline int mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
return 0;
}
static inline int mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
return 0;
}
static inline void
mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
{
}
static inline int
mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range)
{
return 0;
}
static inline
void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
{
}
static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
}
static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
{
}
static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
{
}
#define mmu_notifier_range_update_to_read_only(r) false
#define ptep_clear_flush_young_notify ptep_clear_flush_young
#define pmdp_clear_flush_young_notify pmdp_clear_flush_young
#define ptep_clear_young_notify ptep_test_and_clear_young
#define pmdp_clear_young_notify pmdp_test_and_clear_young
#define ptep_clear_flush_notify ptep_clear_flush
#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
#define pudp_huge_clear_flush_notify pudp_huge_clear_flush
static inline void mmu_notifier_synchronize(void)
{
}
#endif /* CONFIG_MMU_NOTIFIER */
#endif /* _LINUX_MMU_NOTIFIER_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H
#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
#include <linux/node.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/atomic.h>
#include <linux/page-flags.h>
#include <uapi/linux/mempolicy.h>
#include <asm/page.h>
struct notifier_block;
struct bio;
struct pagevec;
#define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
#define SWAP_FLAG_PRIO_MASK 0x7fff
#define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */
#define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */
#define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */
#define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
SWAP_FLAG_DISCARD_PAGES)
#define SWAP_BATCH 64
static inline int current_is_kswapd(void)
{
return current->flags & PF_KSWAPD;
}
/*
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
* be swapped to. The swap type and the offset into that swap type are
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
* for the type means that the maximum number of swapcache pages is 27 bits
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
* the type/offset into the pte as 5/27 as well.
*/
#define MAX_SWAPFILES_SHIFT 5
/*
* Use some of the swap files numbers for other purposes. This
* is a convenient way to hook into the VM to trigger special
* actions on faults.
*/
/*
* PTE markers are used to persist information onto PTEs that otherwise
* should be a none pte. As its name "PTE" hints, it should only be
* applied to the leaves of pgtables.
*/
#define SWP_PTE_MARKER_NUM 1
#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
SWP_MIGRATION_NUM + SWP_DEVICE_NUM)
/*
* Unaddressable device memory support. See include/linux/hmm.h and
* Documentation/mm/hmm.rst. Short description is we need struct pages for
* device memory that is unaddressable (inaccessible) by CPU, so that we can
* migrate part of a process memory to device memory.
*
* When a page is migrated from CPU to device, we set the CPU page table entry
* to a special SWP_DEVICE_{READ|WRITE} entry.
*
* When a page is mapped by the device for exclusive access we set the CPU page
* table entries to a special SWP_DEVICE_EXCLUSIVE entry.
*/
#ifdef CONFIG_DEVICE_PRIVATE
#define SWP_DEVICE_NUM 3
#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM)
#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1)
#define SWP_DEVICE_EXCLUSIVE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2)
#else
#define SWP_DEVICE_NUM 0
#endif
/*
* Page migration support.
*
* SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and
* indicates that the referenced (part of) an anonymous page is exclusive to
* a single process. For SWP_MIGRATION_WRITE, that information is implicit:
* (part of) an anonymous page that are mapped writable are exclusive to a
* single process.
*/
#ifdef CONFIG_MIGRATION
#define SWP_MIGRATION_NUM 3
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2)
#else
#define SWP_MIGRATION_NUM 0
#endif
/*
* Handling of hardware poisoned pages with memory corruption.
*/
#ifdef CONFIG_MEMORY_FAILURE
#define SWP_HWPOISON_NUM 1
#define SWP_HWPOISON MAX_SWAPFILES
#else
#define SWP_HWPOISON_NUM 0
#endif
#define MAX_SWAPFILES \
((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \
SWP_PTE_MARKER_NUM)
/*
* Magic header for a swap area. The first part of the union is
* what the swap magic looks like for the old (limited to 128MB)
* swap area format, the second part of the union adds - in the
* old reserved area - some extra information. Note that the first
* kilobyte is reserved for boot loader or disk label stuff...
*
* Having the magic at the end of the PAGE_SIZE makes detecting swap
* areas somewhat tricky on machines that support multiple page sizes.
* For 2.5 we'll probably want to move the magic to just beyond the
* bootbits...
*/
union swap_header {
struct {
char reserved[PAGE_SIZE - 10];
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
} magic;
struct {
char bootbits[1024]; /* Space for disklabel etc. */
__u32 version;
__u32 last_page;
__u32 nr_badpages;
unsigned char sws_uuid[16];
unsigned char sws_volume[16];
__u32 padding[117];
__u32 badpages[1];
} info;
};
/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
*/
struct reclaim_state {
/* pages reclaimed outside of LRU-based reclaim */
unsigned long reclaimed;
#ifdef CONFIG_LRU_GEN
/* per-thread mm walk data */
struct lru_gen_mm_walk *mm_walk;
#endif
};
/*
* mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based
* reclaim
* @pages: number of pages reclaimed
*
* If the current process is undergoing a reclaim operation, increment the
* number of reclaimed pages by @pages.
*/
static inline void mm_account_reclaimed_pages(unsigned long pages)
{
if (current->reclaim_state)
current->reclaim_state->reclaimed += pages;
}
#ifdef __KERNEL__
struct address_space;
struct sysinfo;
struct writeback_control;
struct zone;
/*
* A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
* disk blocks. A rbtree of swap extents maps the entire swapfile (Where the
* term `swapfile' refers to either a blockdevice or an IS_REG file). Apart
* from setup, they're handled identically.
*
* We always assume that blocks are of size PAGE_SIZE.
*/
struct swap_extent {
struct rb_node rb_node;
pgoff_t start_page;
pgoff_t nr_pages;
sector_t start_block;
};
/*
* Max bad pages in the new format..
*/
#define MAX_SWAP_BADPAGES \
((offsetof(union swap_header, magic.magic) - \
offsetof(union swap_header, info.badpages)) / sizeof(int))
enum {
SWP_USED = (1 << 0), /* is slot in swap_info[] used? */
SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */
SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
SWP_BLKDEV = (1 << 6), /* its a block device */
SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */
SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */
SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */
SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */
SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */
SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */
/* add others here before... */
};
#define SWAP_CLUSTER_MAX 32UL
#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10)
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
/* Bit flag in swap_map */
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
#define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */
/* Special value in first swap_map */
#define SWAP_MAP_MAX 0x3e /* Max count */
#define SWAP_MAP_BAD 0x3f /* Note page is bad */
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */
/* Special value in each swap_map continuation */
#define SWAP_CONT_MAX 0x7f /* Max count */
/*
* We use this to track usage of a cluster. A cluster is a block of swap disk
* space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
* free clusters are organized into a list. We fetch an entry from the list to
* get a free cluster.
*
* The flags field determines if a cluster is free. This is
* protected by cluster lock.
*/
struct swap_cluster_info {
spinlock_t lock; /*
* Protect swap_cluster_info fields
* other than list, and swap_info_struct->swap_map
* elements corresponding to the swap cluster.
*/
u16 count;
u8 flags;
u8 order;
struct list_head list;
};
/* All on-list cluster must have a non-zero flag. */
enum swap_cluster_flags {
CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
CLUSTER_FLAG_FREE,
CLUSTER_FLAG_NONFULL,
CLUSTER_FLAG_FRAG,
/* Clusters with flags above are allocatable */
CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
CLUSTER_FLAG_FULL,
CLUSTER_FLAG_DISCARD,
CLUSTER_FLAG_MAX,
};
/*
* The first page in the swap file is the swap header, which is always marked
* bad to prevent it from being allocated as an entry. This also prevents the
* cluster to which it belongs being marked free. Therefore 0 is safe to use as
* a sentinel to indicate an entry is not valid.
*/
#define SWAP_ENTRY_INVALID 0
#ifdef CONFIG_THP_SWAP
#define SWAP_NR_ORDERS (PMD_ORDER + 1)
#else
#define SWAP_NR_ORDERS 1
#endif
/*
* We keep using same cluster for rotational device so IO will be sequential.
* The purpose is to optimize SWAP throughput on these device.
*/
struct swap_sequential_cluster {
unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
};
/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
struct percpu_ref users; /* indicate and keep swap device valid. */
unsigned long flags; /* SWP_USED etc: see above */
signed short prio; /* swap priority of this type */
struct plist_node list; /* entry in swap_active_head */
signed char type; /* strange name for an index */
unsigned int max; /* extent of the swap_map */
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */
struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
struct list_head free_clusters; /* free clusters list */
struct list_head full_clusters; /* full clusters list */
struct list_head nonfull_clusters[SWAP_NR_ORDERS];
/* list of cluster that contains at least one free slot */
struct list_head frag_clusters[SWAP_NR_ORDERS];
/* list of cluster that are fragmented or contented */
atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
unsigned int pages; /* total of usable pages of swap */
atomic_long_t inuse_pages; /* number of those currently in use */
struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */
spinlock_t global_cluster_lock; /* Serialize usage of global cluster */
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
struct completion comp; /* seldom referenced */
spinlock_t lock; /*
* protect map scan related fields like
* swap_map, lowest_bit, highest_bit,
* inuse_pages, cluster_next,
* cluster_nr, lowest_alloc,
* highest_alloc, free/discard cluster
* list. other fields are only changed
* at swapon/swapoff, so are protected
* by swap_lock. changing flags need
* hold this lock and swap_lock. If
* both locks need hold, hold swap_lock
* first.
*/
spinlock_t cont_lock; /*
* protect swap count continuation page
* list.
*/
struct work_struct discard_work; /* discard worker */
struct work_struct reclaim_work; /* reclaim worker */
struct list_head discard_clusters; /* discard clusters list */
struct plist_node avail_lists[]; /*
* entries in swap_avail_heads, one
* entry per node.
* Must be last as the number of the
* array is nr_node_ids, which is not
* a fixed value so have to allocate
* dynamically.
* And it has to be an array so that
* plist_for_each_* can work.
*/
};
static inline swp_entry_t page_swap_entry(struct page *page)
{
struct folio *folio = page_folio(page);
swp_entry_t entry = folio->swap;
entry.val += folio_page_idx(folio, page);
return entry;
}
/* linux/mm/workingset.c */
bool workingset_test_recent(void *shadow, bool file, bool *workingset,
bool flush);
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
void workingset_refault(struct folio *folio, void *shadow);
void workingset_activation(struct folio *folio);
/* linux/mm/page_alloc.c */
extern unsigned long totalreserve_pages;
/* Definition of global_zone_page_state not available yet */
#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
/* linux/mm/swap.c */
void lru_note_cost(struct lruvec *lruvec, bool file,
unsigned int nr_io, unsigned int nr_rotated);
void lru_note_cost_refault(struct folio *);
void folio_add_lru(struct folio *);
void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
void mark_page_accessed(struct page *);
void folio_mark_accessed(struct folio *);
extern atomic_t lru_disable_count;
static inline bool lru_cache_disabled(void)
{
return atomic_read(&lru_disable_count);
}
static inline void lru_cache_enable(void)
{
atomic_dec(&lru_disable_count);
}
extern void lru_cache_disable(void);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_cpu_zone(struct zone *zone);
extern void lru_add_drain_all(void);
void folio_deactivate(struct folio *folio);
void folio_mark_lazyfree(struct folio *folio);
extern void swap_setup(void);
/* linux/mm/vmscan.c */
extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
#define MEMCG_RECLAIM_MAY_SWAP (1 << 1)
#define MEMCG_RECLAIM_PROACTIVE (1 << 2)
#define MIN_SWAPPINESS 0
#define MAX_SWAPPINESS 200
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
unsigned int reclaim_options,
int *swappiness);
extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
long remove_mapping(struct address_space *mapping, struct folio *folio);
#ifdef CONFIG_NUMA
extern int sysctl_min_unmapped_ratio;
extern int sysctl_min_slab_ratio;
#endif
void check_move_unevictable_folios(struct folio_batch *fbatch);
extern void __meminit kswapd_run(int nid);
extern void __meminit kswapd_stop(int nid);
#ifdef CONFIG_SWAP
int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block);
int generic_swapfile_activate(struct swap_info_struct *, struct file *,
sector_t *);
static inline unsigned long total_swapcache_pages(void)
{
return global_node_page_state(NR_SWAPCACHE);
}
void free_swap_cache(struct folio *folio);
void free_page_and_swap_cache(struct page *);
void free_pages_and_swap_cache(struct encoded_page **, int);
/* linux/mm/swapfile.c */
extern atomic_long_t nr_swap_pages;
extern long total_swap_pages;
extern atomic_t nr_rotate_swap;
/* Swap 50% full? Release swapcache more aggressively.. */
static inline bool vm_swap_full(void)
{
return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
}
static inline long get_nr_swap_pages(void)
{
return atomic_long_read(&nr_swap_pages);
}
extern void si_swapinfo(struct sysinfo *);
int folio_alloc_swap(struct folio *folio, gfp_t gfp_mask);
bool folio_free_swap(struct folio *folio);
void put_swap_folio(struct folio *folio, swp_entry_t entry);
extern swp_entry_t get_swap_page_of_type(int);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t, int);
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t entry, int nr);
extern void swap_free_nr(swp_entry_t entry, int nr_pages);
extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
int swap_type_of(dev_t device, sector_t offset);
int find_first_swap(dev_t *device);
extern unsigned int count_swap_pages(int, int);
extern sector_t swapdev_block(int, pgoff_t);
extern int __swap_count(swp_entry_t entry);
extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry);
extern int swp_swapcount(swp_entry_t entry);
struct swap_info_struct *swp_swap_info(swp_entry_t entry);
struct backing_dev_info;
extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
extern void exit_swap_address_space(unsigned int type);
extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
sector_t swap_folio_sector(struct folio *folio);
static inline void put_swap_device(struct swap_info_struct *si)
{
percpu_ref_put(&si->users);
}
#else /* CONFIG_SWAP */
static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
{
return NULL;
}
static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)
{
return NULL;
}
static inline void put_swap_device(struct swap_info_struct *si)
{
}
#define get_nr_swap_pages() 0L
#define total_swap_pages 0L
#define total_swapcache_pages() 0UL
#define vm_swap_full() 0
#define si_swapinfo(val) \
do { (val)->freeswap = (val)->totalswap = 0; } while (0)
/* only sparc can not include linux/pagemap.h in this file
* so leave put_page and release_pages undeclared... */
#define free_page_and_swap_cache(page) \
put_page(page)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr));
static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr)
{
}
static inline void free_swap_cache(struct folio *folio)
{
}
static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
{
return 0;
}
static inline void swap_shmem_alloc(swp_entry_t swp, int nr)
{
}
static inline int swap_duplicate(swp_entry_t swp)
{
return 0;
}
static inline int swapcache_prepare(swp_entry_t swp, int nr)
{
return 0;
}
static inline void swap_free_nr(swp_entry_t entry, int nr_pages)
{
}
static inline void put_swap_folio(struct folio *folio, swp_entry_t swp)
{
}
static inline int __swap_count(swp_entry_t entry)
{
return 0;
}
static inline bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry)
{
return false;
}
static inline int swp_swapcount(swp_entry_t entry)
{
return 0;
}
static inline int folio_alloc_swap(struct folio *folio, gfp_t gfp_mask)
{
return -EINVAL;
}
static inline bool folio_free_swap(struct folio *folio)
{
return false;
}
static inline int add_swap_extent(struct swap_info_struct *sis,
unsigned long start_page,
unsigned long nr_pages, sector_t start_block)
{
return -EINVAL;
}
#endif /* CONFIG_SWAP */
static inline void free_swap_and_cache(swp_entry_t entry)
{
free_swap_and_cache_nr(entry, 1);
}
static inline void swap_free(swp_entry_t entry)
{
swap_free_nr(entry, 1);
}
#ifdef CONFIG_MEMCG
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
/* Cgroup2 doesn't have per-cgroup swappiness */
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return READ_ONCE(vm_swappiness);
/* root ? */
if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
return READ_ONCE(vm_swappiness);
return READ_ONCE(memcg->swappiness);
}
#else
static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
{
return READ_ONCE(vm_swappiness);
}
#endif
#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp);
static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
{
if (mem_cgroup_disabled())
return;
__folio_throttle_swaprate(folio, gfp);
}
#else
static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
{
}
#endif
#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry);
static inline int mem_cgroup_try_charge_swap(struct folio *folio,
swp_entry_t entry)
{
if (mem_cgroup_disabled())
return 0;
return __mem_cgroup_try_charge_swap(folio, entry);
}
extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
{
if (mem_cgroup_disabled())
return;
__mem_cgroup_uncharge_swap(entry, nr_pages);
}
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
extern bool mem_cgroup_swap_full(struct folio *folio);
#else
static inline int mem_cgroup_try_charge_swap(struct folio *folio,
swp_entry_t entry)
{
return 0;
}
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry,
unsigned int nr_pages)
{
}
static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
{
return get_nr_swap_pages();
}
static inline bool mem_cgroup_swap_full(struct folio *folio)
{
return vm_swap_full();
}
#endif
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef IOPRIO_H
#define IOPRIO_H
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/iocontext.h>
#include <uapi/linux/ioprio.h>
/*
* Default IO priority.
*/
#define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0)
/*
* Check that a priority value has a valid class.
*/
static inline bool ioprio_valid(unsigned short ioprio)
{
unsigned short class = IOPRIO_PRIO_CLASS(ioprio);
return class > IOPRIO_CLASS_NONE && class <= IOPRIO_CLASS_IDLE;
}
/*
* if process has set io priority explicitly, use that. if not, convert
* the cpu scheduler nice value to an io priority
*/
static inline int task_nice_ioprio(struct task_struct *task)
{
return (task_nice(task) + 20) / 5;
}
/*
* This is for the case where the task hasn't asked for a specific IO class.
* Check for idle and rt task process, and return appropriate IO class.
*/
static inline int task_nice_ioclass(struct task_struct *task)
{
if (task->policy == SCHED_IDLE)
return IOPRIO_CLASS_IDLE;
else if (rt_or_dl_task_policy(task))
return IOPRIO_CLASS_RT;
else
return IOPRIO_CLASS_BE;
}
#ifdef CONFIG_BLOCK
/*
* If the task has set an I/O priority, use that. Otherwise, return
* the default I/O priority.
*
* Expected to be called for current task or with task_lock() held to keep
* io_context stable.
*/
static inline int __get_task_ioprio(struct task_struct *p)
{
struct io_context *ioc = p->io_context;
int prio;
if (!ioc)
return IOPRIO_DEFAULT;
if (p != current)
lockdep_assert_held(&p->alloc_lock);
prio = ioc->ioprio;
if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
task_nice_ioprio(p));
return prio;
}
#else
static inline int __get_task_ioprio(struct task_struct *p)
{
return IOPRIO_DEFAULT;
}
#endif /* CONFIG_BLOCK */
static inline int get_current_ioprio(void)
{
return __get_task_ioprio(current);
}
extern int set_task_ioprio(struct task_struct *task, int ioprio);
#ifdef CONFIG_BLOCK
extern int ioprio_check_cap(int ioprio);
#else
static inline int ioprio_check_cap(int ioprio)
{
return -ENOTBLK;
}
#endif /* CONFIG_BLOCK */
#endif
/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Read-Copy Update mechanism for mutual exclusion
*
* Copyright IBM Corporation, 2001
*
* Author: Dipankar Sarma <dipankar@in.ibm.com>
*
* Based on the original work by Paul McKenney <paulmck@vnet.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
* Papers:
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
*
* For detailed explanation of Read-Copy Update mechanism see -
* http://lse.sourceforge.net/locking/rcupdate.html
*
*/
#ifndef __LINUX_RCUPDATE_H
#define __LINUX_RCUPDATE_H
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/atomic.h>
#include <linux/irqflags.h>
#include <linux/preempt.h>
#include <linux/bottom_half.h>
#include <linux/lockdep.h>
#include <linux/cleanup.h>
#include <asm/processor.h>
#include <linux/context_tracking_irq.h>
#define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b))
#define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b))
#define RCU_SEQ_CTR_SHIFT 2
#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
/* Exported common interfaces */
void call_rcu(struct rcu_head *head, rcu_callback_t func);
void rcu_barrier_tasks(void);
void synchronize_rcu(void);
struct rcu_gp_oldstate;
unsigned long get_completed_synchronize_rcu(void);
void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
// Maximum number of unsigned long values corresponding to
// not-yet-completed RCU grace periods.
#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2
/**
* same_state_synchronize_rcu - Are two old-state values identical?
* @oldstate1: First old-state value.
* @oldstate2: Second old-state value.
*
* The two old-state values must have been obtained from either
* get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or
* get_completed_synchronize_rcu(). Returns @true if the two values are
* identical and @false otherwise. This allows structures whose lifetimes
* are tracked by old-state values to push these values to a list header,
* allowing those structures to be slightly smaller.
*/
static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2)
{
return oldstate1 == oldstate2;
}
#ifdef CONFIG_PREEMPT_RCU
void __rcu_read_lock(void);
void __rcu_read_unlock(void);
/*
* Defined as a macro as it is a very low level header included from
* areas that don't even know about current. This gives the rcu_read_lock()
* nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
* types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
*/
#define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting)
#else /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TINY_RCU
#define rcu_read_unlock_strict() do { } while (0)
#else
void rcu_read_unlock_strict(void);
#endif
static inline void __rcu_read_lock(void)
{
preempt_disable();
}
static inline void __rcu_read_unlock(void)
{
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
rcu_read_unlock_strict();
preempt_enable();
}
static inline int rcu_preempt_depth(void)
{
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_LAZY
void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func);
#else
static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
{
call_rcu(head, func);
}
#endif
/* Internal to kernel */
void rcu_init(void);
extern int rcu_scheduler_active;
void rcu_sched_clock_irq(int user);
#ifdef CONFIG_RCU_STALL_COMMON
void rcu_sysrq_start(void);
void rcu_sysrq_end(void);
#else /* #ifdef CONFIG_RCU_STALL_COMMON */
static inline void rcu_sysrq_start(void) { }
static inline void rcu_sysrq_end(void) { }
#endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */
#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK))
void rcu_irq_work_resched(void);
#else
static __always_inline void rcu_irq_work_resched(void) { }
#endif
#ifdef CONFIG_RCU_NOCB_CPU
void rcu_init_nohz(void);
int rcu_nocb_cpu_offload(int cpu);
int rcu_nocb_cpu_deoffload(int cpu);
void rcu_nocb_flush_deferred_wakeup(void);
#define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s)
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
static inline void rcu_init_nohz(void) { }
static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; }
static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; }
static inline void rcu_nocb_flush_deferred_wakeup(void) { }
#define RCU_NOCB_LOCKDEP_WARN(c, s)
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
/*
* Note a quasi-voluntary context switch for RCU-tasks's benefit.
* This is a macro rather than an inline function to avoid #include hell.
*/
#ifdef CONFIG_TASKS_RCU_GENERIC
# ifdef CONFIG_TASKS_RCU
# define rcu_tasks_classic_qs(t, preempt) \
do { \
if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \
WRITE_ONCE((t)->rcu_tasks_holdout, false); \
} while (0)
void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
void synchronize_rcu_tasks(void);
void rcu_tasks_torture_stats_print(char *tt, char *tf);
# else
# define rcu_tasks_classic_qs(t, preempt) do { } while (0)
# define call_rcu_tasks call_rcu
# define synchronize_rcu_tasks synchronize_rcu
# endif
# ifdef CONFIG_TASKS_TRACE_RCU
// Bits for ->trc_reader_special.b.need_qs field.
#define TRC_NEED_QS 0x1 // Task needs a quiescent state.
#define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state.
u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new);
void rcu_tasks_trace_qs_blkd(struct task_struct *t);
# define rcu_tasks_trace_qs(t) \
do { \
int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \
\
if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \
likely(!___rttq_nesting)) { \
rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \
} else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \
!READ_ONCE((t)->trc_reader_special.b.blocked)) { \
rcu_tasks_trace_qs_blkd(t); \
} \
} while (0)
void rcu_tasks_trace_torture_stats_print(char *tt, char *tf);
# else
# define rcu_tasks_trace_qs(t) do { } while (0)
# endif
#define rcu_tasks_qs(t, preempt) \
do { \
rcu_tasks_classic_qs((t), (preempt)); \
rcu_tasks_trace_qs(t); \
} while (0)
# ifdef CONFIG_TASKS_RUDE_RCU
void synchronize_rcu_tasks_rude(void);
void rcu_tasks_rude_torture_stats_print(char *tt, char *tf);
# endif
#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
void exit_tasks_rcu_start(void);
void exit_tasks_rcu_finish(void);
#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
#define rcu_tasks_classic_qs(t, preempt) do { } while (0)
#define rcu_tasks_qs(t, preempt) do { } while (0)
#define rcu_note_voluntary_context_switch(t) do { } while (0)
#define call_rcu_tasks call_rcu
#define synchronize_rcu_tasks synchronize_rcu
static inline void exit_tasks_rcu_start(void) { }
static inline void exit_tasks_rcu_finish(void) { }
#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
/**
* rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period?
*
* As an accident of implementation, an RCU Tasks Trace grace period also
* acts as an RCU grace period. However, this could change at any time.
* Code relying on this accident must call this function to verify that
* this accident is still happening.
*
* You have been warned!
*/
static inline bool rcu_trace_implies_rcu_gp(void) { return true; }
/**
* cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
*
* This macro resembles cond_resched(), except that it is defined to
* report potential quiescent states to RCU-tasks even if the cond_resched()
* machinery were to be shut off, as some advocate for PREEMPTION kernels.
*/
#define cond_resched_tasks_rcu_qs() \
do { \
rcu_tasks_qs(current, false); \
cond_resched(); \
} while (0)
/**
* rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states
* @old_ts: jiffies at start of processing.
*
* This helper is for long-running softirq handlers, such as NAPI threads in
* networking. The caller should initialize the variable passed in as @old_ts
* at the beginning of the softirq handler. When invoked frequently, this macro
* will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will
* provide both RCU and RCU-Tasks quiescent states. Note that this macro
* modifies its old_ts argument.
*
* Because regions of code that have disabled softirq act as RCU read-side
* critical sections, this macro should be invoked with softirq (and
* preemption) enabled.
*
* The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would
* have more chance to invoke schedule() calls and provide necessary quiescent
* states. As a contrast, calling cond_resched() only won't achieve the same
* effect because cond_resched() does not provide RCU-Tasks quiescent states.
*/
#define rcu_softirq_qs_periodic(old_ts) \
do { \
if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \
time_after(jiffies, (old_ts) + HZ / 10)) { \
preempt_disable(); \
rcu_softirq_qs(); \
preempt_enable(); \
(old_ts) = jiffies; \
} \
} while (0)
/*
* Infrastructure to implement the synchronize_() primitives in
* TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
*/
#if defined(CONFIG_TREE_RCU)
#include <linux/rcutree.h>
#elif defined(CONFIG_TINY_RCU)
#include <linux/rcutiny.h>
#else
#error "Unknown RCU implementation specified to kernel configuration"
#endif
/*
* The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls
* are needed for dynamic initialization and destruction of rcu_head
* on the stack, and init_rcu_head()/destroy_rcu_head() are needed for
* dynamic initialization and destruction of statically allocated rcu_head
* structures. However, rcu_head structures allocated dynamically in the
* heap don't need any initialization.
*/
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
void init_rcu_head(struct rcu_head *head);
void destroy_rcu_head(struct rcu_head *head);
void init_rcu_head_on_stack(struct rcu_head *head);
void destroy_rcu_head_on_stack(struct rcu_head *head);
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
static inline void init_rcu_head(struct rcu_head *head) { }
static inline void destroy_rcu_head(struct rcu_head *head) { }
static inline void init_rcu_head_on_stack(struct rcu_head *head) { }
static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { }
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
bool rcu_lockdep_current_cpu_online(void);
#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
static inline bool rcu_lockdep_current_cpu_online(void) { return true; }
#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
extern struct lockdep_map rcu_lock_map;
extern struct lockdep_map rcu_bh_lock_map;
extern struct lockdep_map rcu_sched_lock_map;
extern struct lockdep_map rcu_callback_map;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void rcu_lock_acquire(struct lockdep_map *map)
{ lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
}
static inline void rcu_try_lock_acquire(struct lockdep_map *map)
{ lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_);
}
static inline void rcu_lock_release(struct lockdep_map *map)
{ lock_release(map, _THIS_IP_);
}
int debug_lockdep_rcu_enabled(void);
int rcu_read_lock_held(void);
int rcu_read_lock_bh_held(void);
int rcu_read_lock_sched_held(void);
int rcu_read_lock_any_held(void);
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
# define rcu_lock_acquire(a) do { } while (0)
# define rcu_try_lock_acquire(a) do { } while (0)
# define rcu_lock_release(a) do { } while (0)
static inline int rcu_read_lock_held(void)
{
return 1;
}
static inline int rcu_read_lock_bh_held(void)
{
return 1;
}
static inline int rcu_read_lock_sched_held(void)
{
return !preemptible();
}
static inline int rcu_read_lock_any_held(void)
{
return !preemptible();
}
static inline int debug_lockdep_rcu_enabled(void)
{
return 0;
}
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#ifdef CONFIG_PROVE_RCU
/**
* RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met
* @c: condition to check
* @s: informative message
*
* This checks debug_lockdep_rcu_enabled() before checking (c) to
* prevent early boot splats due to lockdep not yet being initialized,
* and rechecks it after checking (c) to prevent false-positive splats
* due to races with lockdep being disabled. See commit 3066820034b5dd
* ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail.
*/
#define RCU_LOCKDEP_WARN(c, s) \
do { \
static bool __section(".data..unlikely") __warned; \
if (debug_lockdep_rcu_enabled() && (c) && \
debug_lockdep_rcu_enabled() && !__warned) { \
__warned = true; \
lockdep_rcu_suspicious(__FILE__, __LINE__, s); \
} \
} while (0)
#ifndef CONFIG_PREEMPT_RCU
static inline void rcu_preempt_sleep_check(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map),
"Illegal context switch in RCU read-side critical section");
}
#else // #ifndef CONFIG_PREEMPT_RCU
static inline void rcu_preempt_sleep_check(void) { }
#endif // #else // #ifndef CONFIG_PREEMPT_RCU
#define rcu_sleep_check() \
do { \
rcu_preempt_sleep_check(); \
if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \
"Illegal context switch in RCU-bh read-side critical section"); \
RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \
"Illegal context switch in RCU-sched read-side critical section"); \
} while (0)
// See RCU_LOCKDEP_WARN() for an explanation of the double call to
// debug_lockdep_rcu_enabled().
static inline bool lockdep_assert_rcu_helper(bool c)
{
return debug_lockdep_rcu_enabled() &&
(c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) &&
debug_lockdep_rcu_enabled();
}
/**
* lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock()
*
* Splats if lockdep is enabled and there is no rcu_read_lock() in effect.
*/
#define lockdep_assert_in_rcu_read_lock() \
WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map)))
/**
* lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh()
*
* Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect.
* Note that local_bh_disable() and friends do not suffice here, instead an
* actual rcu_read_lock_bh() is required.
*/
#define lockdep_assert_in_rcu_read_lock_bh() \
WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map)))
/**
* lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched()
*
* Splats if lockdep is enabled and there is no rcu_read_lock_sched()
* in effect. Note that preempt_disable() and friends do not suffice here,
* instead an actual rcu_read_lock_sched() is required.
*/
#define lockdep_assert_in_rcu_read_lock_sched() \
WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map)))
/**
* lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader
*
* Splats if lockdep is enabled and there is no RCU reader of any
* type in effect. Note that regions of code protected by things like
* preempt_disable, local_bh_disable(), and local_irq_disable() all qualify
* as RCU readers.
*
* Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY
* kernels that are not also built with PREEMPT_COUNT. But if you have
* lockdep enabled, you might as well also enable PREEMPT_COUNT.
*/
#define lockdep_assert_in_rcu_reader() \
WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \
!lock_is_held(&rcu_bh_lock_map) && \
!lock_is_held(&rcu_sched_lock_map) && \
preemptible()))
#else /* #ifdef CONFIG_PROVE_RCU */
#define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c))
#define rcu_sleep_check() do { } while (0)
#define lockdep_assert_in_rcu_read_lock() do { } while (0)
#define lockdep_assert_in_rcu_read_lock_bh() do { } while (0)
#define lockdep_assert_in_rcu_read_lock_sched() do { } while (0)
#define lockdep_assert_in_rcu_reader() do { } while (0)
#endif /* #else #ifdef CONFIG_PROVE_RCU */
/*
* Helper functions for rcu_dereference_check(), rcu_dereference_protected()
* and rcu_assign_pointer(). Some of these could be folded into their
* callers, but they are left separate in order to ease introduction of
* multiple pointers markings to match different RCU implementations
* (e.g., __srcu), should this make sense in the future.
*/
#ifdef __CHECKER__
#define rcu_check_sparse(p, space) \
((void)(((typeof(*p) space *)p) == p))
#else /* #ifdef __CHECKER__ */
#define rcu_check_sparse(p, space)
#endif /* #else #ifdef __CHECKER__ */
#define __unrcu_pointer(p, local) \
({ \
typeof(*p) *local = (typeof(*p) *__force)(p); \
rcu_check_sparse(p, __rcu); \
((typeof(*p) __force __kernel *)(local)); \
})
/**
* unrcu_pointer - mark a pointer as not being RCU protected
* @p: pointer needing to lose its __rcu property
*
* Converts @p from an __rcu pointer to a __kernel pointer.
* This allows an __rcu pointer to be used with xchg() and friends.
*/
#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu))
#define __rcu_access_pointer(p, local, space) \
({ \
typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
rcu_check_sparse(p, space); \
((typeof(*p) __force __kernel *)(local)); \
})
#define __rcu_dereference_check(p, local, c, space) \
({ \
/* Dependency order vs. p above. */ \
typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
rcu_check_sparse(p, space); \
((typeof(*p) __force __kernel *)(local)); \
})
#define __rcu_dereference_protected(p, local, c, space) \
({ \
RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
rcu_check_sparse(p, space); \
((typeof(*p) __force __kernel *)(p)); \
})
#define __rcu_dereference_raw(p, local) \
({ \
/* Dependency order vs. p above. */ \
typeof(p) local = READ_ONCE(p); \
((typeof(*p) __force __kernel *)(local)); \
})
#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu))
/**
* RCU_INITIALIZER() - statically initialize an RCU-protected global variable
* @v: The value to statically initialize with.
*/
#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
/**
* rcu_assign_pointer() - assign to RCU-protected pointer
* @p: pointer to assign to
* @v: value to assign (publish)
*
* Assigns the specified value to the specified RCU-protected
* pointer, ensuring that any concurrent RCU readers will see
* any prior initialization.
*
* Inserts memory barriers on architectures that require them
* (which is most of them), and also prevents the compiler from
* reordering the code that initializes the structure after the pointer
* assignment. More importantly, this call documents which pointers
* will be dereferenced by RCU read-side code.
*
* In some special cases, you may use RCU_INIT_POINTER() instead
* of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due
* to the fact that it does not constrain either the CPU or the compiler.
* That said, using RCU_INIT_POINTER() when you should have used
* rcu_assign_pointer() is a very bad thing that results in
* impossible-to-diagnose memory corruption. So please be careful.
* See the RCU_INIT_POINTER() comment header for details.
*
* Note that rcu_assign_pointer() evaluates each of its arguments only
* once, appearances notwithstanding. One of the "extra" evaluations
* is in typeof() and the other visible only to sparse (__CHECKER__),
* neither of which actually execute the argument. As with most cpp
* macros, this execute-arguments-only-once property is important, so
* please be careful when making changes to rcu_assign_pointer() and the
* other macros that it invokes.
*/
#define rcu_assign_pointer(p, v) \
do { \
uintptr_t _r_a_p__v = (uintptr_t)(v); \
rcu_check_sparse(p, __rcu); \
\
if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \
WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \
else \
smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
} while (0)
/**
* rcu_replace_pointer() - replace an RCU pointer, returning its old value
* @rcu_ptr: RCU pointer, whose old value is returned
* @ptr: regular pointer
* @c: the lockdep conditions under which the dereference will take place
*
* Perform a replacement, where @rcu_ptr is an RCU-annotated
* pointer and @c is the lockdep argument that is passed to the
* rcu_dereference_protected() call used to read that pointer. The old
* value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr.
*/
#define rcu_replace_pointer(rcu_ptr, ptr, c) \
({ \
typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \
rcu_assign_pointer((rcu_ptr), (ptr)); \
__tmp; \
})
/**
* rcu_access_pointer() - fetch RCU pointer with no dereferencing
* @p: The pointer to read
*
* Return the value of the specified RCU-protected pointer, but omit the
* lockdep checks for being in an RCU read-side critical section. This is
* useful when the value of this pointer is accessed, but the pointer is
* not dereferenced, for example, when testing an RCU-protected pointer
* against NULL. Although rcu_access_pointer() may also be used in cases
* where update-side locks prevent the value of the pointer from changing,
* you should instead use rcu_dereference_protected() for this use case.
* Within an RCU read-side critical section, there is little reason to
* use rcu_access_pointer().
*
* It is usually best to test the rcu_access_pointer() return value
* directly in order to avoid accidental dereferences being introduced
* by later inattentive changes. In other words, assigning the
* rcu_access_pointer() return value to a local variable results in an
* accident waiting to happen.
*
* It is also permissible to use rcu_access_pointer() when read-side
* access to the pointer was removed at least one grace period ago, as is
* the case in the context of the RCU callback that is freeing up the data,
* or after a synchronize_rcu() returns. This can be useful when tearing
* down multi-linked structures after a grace period has elapsed. However,
* rcu_dereference_protected() is normally preferred for this use case.
*/
#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
/**
* rcu_dereference_check() - rcu_dereference with debug checking
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* Do an rcu_dereference(), but check that the conditions under which the
* dereference will take place are correct. Typically the conditions
* indicate the various locking conditions that should be held at that
* point. The check should return true if the conditions are satisfied.
* An implicit check for being in an RCU read-side critical section
* (rcu_read_lock()) is included.
*
* For example:
*
* bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
*
* could be used to indicate to lockdep that foo->bar may only be dereferenced
* if either rcu_read_lock() is held, or that the lock required to replace
* the bar struct at foo->bar is held.
*
* Note that the list of conditions may also include indications of when a lock
* need not be held, for example during initialisation or destruction of the
* target struct:
*
* bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
* atomic_read(&foo->usage) == 0);
*
* Inserts memory barriers on architectures that require them
* (currently only the Alpha), prevents the compiler from refetching
* (and from merging fetches), and, more importantly, documents exactly
* which pointers are protected by RCU and checks that the pointer is
* annotated as __rcu.
*/
#define rcu_dereference_check(p, c) \
__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
(c) || rcu_read_lock_held(), __rcu)
/**
* rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* This is the RCU-bh counterpart to rcu_dereference_check(). However,
* please note that starting in v5.0 kernels, vanilla RCU grace periods
* wait for local_bh_disable() regions of code in addition to regions of
* code demarked by rcu_read_lock() and rcu_read_unlock(). This means
* that synchronize_rcu(), call_rcu, and friends all take not only
* rcu_read_lock() but also rcu_read_lock_bh() into account.
*/
#define rcu_dereference_bh_check(p, c) \
__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
(c) || rcu_read_lock_bh_held(), __rcu)
/**
* rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* This is the RCU-sched counterpart to rcu_dereference_check().
* However, please note that starting in v5.0 kernels, vanilla RCU grace
* periods wait for preempt_disable() regions of code in addition to
* regions of code demarked by rcu_read_lock() and rcu_read_unlock().
* This means that synchronize_rcu(), call_rcu, and friends all take not
* only rcu_read_lock() but also rcu_read_lock_sched() into account.
*/
#define rcu_dereference_sched_check(p, c) \
__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
(c) || rcu_read_lock_sched_held(), \
__rcu)
/*
* The tracing infrastructure traces RCU (we want that), but unfortunately
* some of the RCU checks causes tracing to lock up the system.
*
* The no-tracing version of rcu_dereference_raw() must not call
* rcu_read_lock_held().
*/
#define rcu_dereference_raw_check(p) \
__rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu)
/**
* rcu_dereference_protected() - fetch RCU pointer when updates prevented
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* Return the value of the specified RCU-protected pointer, but omit
* the READ_ONCE(). This is useful in cases where update-side locks
* prevent the value of the pointer from changing. Please note that this
* primitive does *not* prevent the compiler from repeating this reference
* or combining it with other references, so it should not be used without
* protection of appropriate locks.
*
* This function is only for update-side use. Using this function
* when protected only by rcu_read_lock() will result in infrequent
* but very ugly failures.
*/
#define rcu_dereference_protected(p, c) \
__rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu)
/**
* rcu_dereference() - fetch RCU-protected pointer for dereferencing
* @p: The pointer to read, prior to dereferencing
*
* This is a simple wrapper around rcu_dereference_check().
*/
#define rcu_dereference(p) rcu_dereference_check(p, 0)
/**
* rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing
* @p: The pointer to read, prior to dereferencing
*
* Makes rcu_dereference_check() do the dirty work.
*/
#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0)
/**
* rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing
* @p: The pointer to read, prior to dereferencing
*
* Makes rcu_dereference_check() do the dirty work.
*/
#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0)
/**
* rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism
* @p: The pointer to hand off
*
* This is simply an identity function, but it documents where a pointer
* is handed off from RCU to some other synchronization mechanism, for
* example, reference counting or locking. In C11, it would map to
* kill_dependency(). It could be used as follows::
*
* rcu_read_lock();
* p = rcu_dereference(gp);
* long_lived = is_long_lived(p);
* if (long_lived) {
* if (!atomic_inc_not_zero(p->refcnt))
* long_lived = false;
* else
* p = rcu_pointer_handoff(p);
* }
* rcu_read_unlock();
*/
#define rcu_pointer_handoff(p) (p)
/**
* rcu_read_lock() - mark the beginning of an RCU read-side critical section
*
* When synchronize_rcu() is invoked on one CPU while other CPUs
* are within RCU read-side critical sections, then the
* synchronize_rcu() is guaranteed to block until after all the other
* CPUs exit their critical sections. Similarly, if call_rcu() is invoked
* on one CPU while other CPUs are within RCU read-side critical
* sections, invocation of the corresponding RCU callback is deferred
* until after the all the other CPUs exit their critical sections.
*
* Both synchronize_rcu() and call_rcu() also wait for regions of code
* with preemption disabled, including regions of code with interrupts or
* softirqs disabled.
*
* Note, however, that RCU callbacks are permitted to run concurrently
* with new RCU read-side critical sections. One way that this can happen
* is via the following sequence of events: (1) CPU 0 enters an RCU
* read-side critical section, (2) CPU 1 invokes call_rcu() to register
* an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
* (4) CPU 2 enters a RCU read-side critical section, (5) the RCU
* callback is invoked. This is legal, because the RCU read-side critical
* section that was running concurrently with the call_rcu() (and which
* therefore might be referencing something that the corresponding RCU
* callback would free up) has completed before the corresponding
* RCU callback is invoked.
*
* RCU read-side critical sections may be nested. Any deferred actions
* will be deferred until the outermost RCU read-side critical section
* completes.
*
* You can avoid reading and understanding the next paragraph by
* following this rule: don't put anything in an rcu_read_lock() RCU
* read-side critical section that would block in a !PREEMPTION kernel.
* But if you want the full story, read on!
*
* In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU),
* it is illegal to block while in an RCU read-side critical section.
* In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION
* kernel builds, RCU read-side critical sections may be preempted,
* but explicit blocking is illegal. Finally, in preemptible RCU
* implementations in real-time (with -rt patchset) kernel builds, RCU
* read-side critical sections may be preempted and they may also block, but
* only when acquiring spinlocks that are subject to priority inheritance.
*/
static __always_inline void rcu_read_lock(void)
{
__rcu_read_lock();
__acquire(RCU);
rcu_lock_acquire(&rcu_lock_map);
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_lock() used illegally while idle");
}
/*
* So where is rcu_write_lock()? It does not exist, as there is no
* way for writers to lock out RCU readers. This is a feature, not
* a bug -- this property is what provides RCU's performance benefits.
* Of course, writers must coordinate with each other. The normal
* spinlock primitives work well for this, but any other technique may be
* used as well. RCU does not care how the writers keep out of each
* others' way, as long as they do so.
*/
/**
* rcu_read_unlock() - marks the end of an RCU read-side critical section.
*
* In almost all situations, rcu_read_unlock() is immune from deadlock.
* This deadlock immunity also extends to the scheduler's runqueue
* and priority-inheritance spinlocks, courtesy of the quiescent-state
* deferral that is carried out when rcu_read_unlock() is invoked with
* interrupts disabled.
*
* See rcu_read_lock() for more information.
*/
static inline void rcu_read_unlock(void)
{ RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_unlock() used illegally while idle");
rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
__release(RCU);
__rcu_read_unlock();
}
/**
* rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
*
* This is equivalent to rcu_read_lock(), but also disables softirqs.
* Note that anything else that disables softirqs can also serve as an RCU
* read-side critical section. However, please note that this equivalence
* applies only to v5.0 and later. Before v5.0, rcu_read_lock() and
* rcu_read_lock_bh() were unrelated.
*
* Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh()
* must occur in the same context, for example, it is illegal to invoke
* rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh()
* was invoked from some other task.
*/
static inline void rcu_read_lock_bh(void)
{
local_bh_disable();
__acquire(RCU_BH);
rcu_lock_acquire(&rcu_bh_lock_map);
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_lock_bh() used illegally while idle");
}
/**
* rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section
*
* See rcu_read_lock_bh() for more information.
*/
static inline void rcu_read_unlock_bh(void)
{
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_unlock_bh() used illegally while idle");
rcu_lock_release(&rcu_bh_lock_map);
__release(RCU_BH);
local_bh_enable();
}
/**
* rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
*
* This is equivalent to rcu_read_lock(), but also disables preemption.
* Read-side critical sections can also be introduced by anything else that
* disables preemption, including local_irq_disable() and friends. However,
* please note that the equivalence to rcu_read_lock() applies only to
* v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched()
* were unrelated.
*
* Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched()
* must occur in the same context, for example, it is illegal to invoke
* rcu_read_unlock_sched() from process context if the matching
* rcu_read_lock_sched() was invoked from an NMI handler.
*/
static inline void rcu_read_lock_sched(void)
{
preempt_disable();
__acquire(RCU_SCHED);
rcu_lock_acquire(&rcu_sched_lock_map);
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_lock_sched() used illegally while idle");
}
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
static inline notrace void rcu_read_lock_sched_notrace(void)
{
preempt_disable_notrace();
__acquire(RCU_SCHED);
}
/**
* rcu_read_unlock_sched() - marks the end of a RCU-classic critical section
*
* See rcu_read_lock_sched() for more information.
*/
static inline void rcu_read_unlock_sched(void)
{
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"rcu_read_unlock_sched() used illegally while idle");
rcu_lock_release(&rcu_sched_lock_map);
__release(RCU_SCHED);
preempt_enable();
}
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
static inline notrace void rcu_read_unlock_sched_notrace(void)
{
__release(RCU_SCHED);
preempt_enable_notrace();
}
/**
* RCU_INIT_POINTER() - initialize an RCU protected pointer
* @p: The pointer to be initialized.
* @v: The value to initialized the pointer to.
*
* Initialize an RCU-protected pointer in special cases where readers
* do not need ordering constraints on the CPU or the compiler. These
* special cases are:
*
* 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or*
* 2. The caller has taken whatever steps are required to prevent
* RCU readers from concurrently accessing this pointer *or*
* 3. The referenced data structure has already been exposed to
* readers either at compile time or via rcu_assign_pointer() *and*
*
* a. You have not made *any* reader-visible changes to
* this structure since then *or*
* b. It is OK for readers accessing this structure from its
* new location to see the old state of the structure. (For
* example, the changes were to statistical counters or to
* other state where exact synchronization is not required.)
*
* Failure to follow these rules governing use of RCU_INIT_POINTER() will
* result in impossible-to-diagnose memory corruption. As in the structures
* will look OK in crash dumps, but any concurrent RCU readers might
* see pre-initialized values of the referenced data structure. So
* please be very careful how you use RCU_INIT_POINTER()!!!
*
* If you are creating an RCU-protected linked structure that is accessed
* by a single external-to-structure RCU-protected pointer, then you may
* use RCU_INIT_POINTER() to initialize the internal RCU-protected
* pointers, but you must use rcu_assign_pointer() to initialize the
* external-to-structure pointer *after* you have completely initialized
* the reader-accessible portions of the linked structure.
*
* Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no
* ordering guarantees for either the CPU or the compiler.
*/
#define RCU_INIT_POINTER(p, v) \
do { \
rcu_check_sparse(p, __rcu); \
WRITE_ONCE(p, RCU_INITIALIZER(v)); \
} while (0)
/**
* RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
* @p: The pointer to be initialized.
* @v: The value to initialized the pointer to.
*
* GCC-style initialization for an RCU-protected pointer in a structure field.
*/
#define RCU_POINTER_INITIALIZER(p, v) \
.p = RCU_INITIALIZER(v)
/**
* kfree_rcu() - kfree an object after a grace period.
* @ptr: pointer to kfree for double-argument invocations.
* @rhf: the name of the struct rcu_head within the type of @ptr.
*
* Many rcu callbacks functions just call kfree() on the base structure.
* These functions are trivial, but their size adds up, and furthermore
* when they are used in a kernel module, that module must invoke the
* high-latency rcu_barrier() function at module-unload time.
*
* The kfree_rcu() function handles this issue. In order to have a universal
* callback function handling different offsets of rcu_head, the callback needs
* to determine the starting address of the freed object, which can be a large
* kmalloc or vmalloc allocation. To allow simply aligning the pointer down to
* page boundary for those, only offsets up to 4095 bytes can be accommodated.
* If the offset is larger than 4095 bytes, a compile-time error will
* be generated in kvfree_rcu_arg_2(). If this error is triggered, you can
* either fall back to use of call_rcu() or rearrange the structure to
* position the rcu_head structure into the first 4096 bytes.
*
* The object to be freed can be allocated either by kmalloc() or
* kmem_cache_alloc().
*
* Note that the allowable offset might decrease in the future.
*
* The BUILD_BUG_ON check must not involve any function calls, hence the
* checks are done in macros here.
*/
#define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf)
#define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf)
/**
* kfree_rcu_mightsleep() - kfree an object after a grace period.
* @ptr: pointer to kfree for single-argument invocations.
*
* When it comes to head-less variant, only one argument
* is passed and that is just a pointer which has to be
* freed after a grace period. Therefore the semantic is
*
* kfree_rcu_mightsleep(ptr);
*
* where @ptr is the pointer to be freed by kvfree().
*
* Please note, head-less way of freeing is permitted to
* use from a context that has to follow might_sleep()
* annotation. Otherwise, please switch and embed the
* rcu_head structure within the type of @ptr.
*/
#define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
#define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
/*
* In mm/slab_common.c, no suitable header to include here.
*/
void kvfree_call_rcu(struct rcu_head *head, void *ptr);
/*
* The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the
* comment of kfree_rcu() for details.
*/
#define kvfree_rcu_arg_2(ptr, rhf) \
do { \
typeof (ptr) ___p = (ptr); \
\
if (___p) { \
BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \
kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \
} \
} while (0)
#define kvfree_rcu_arg_1(ptr) \
do { \
typeof(ptr) ___p = (ptr); \
\
if (___p) \
kvfree_call_rcu(NULL, (void *) (___p)); \
} while (0)
/*
* Place this after a lock-acquisition primitive to guarantee that
* an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies
* if the UNLOCK and LOCK are executed by the same CPU or if the
* UNLOCK and LOCK operate on the same lock variable.
*/
#ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE
#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
#define smp_mb__after_unlock_lock() do { } while (0)
#endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
/* Has the specified rcu_head structure been handed to call_rcu()? */
/**
* rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu()
* @rhp: The rcu_head structure to initialize.
*
* If you intend to invoke rcu_head_after_call_rcu() to test whether a
* given rcu_head structure has already been passed to call_rcu(), then
* you must also invoke this rcu_head_init() function on it just after
* allocating that structure. Calls to this function must not race with
* calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation.
*/
static inline void rcu_head_init(struct rcu_head *rhp)
{
rhp->func = (rcu_callback_t)~0L;
}
/**
* rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()?
* @rhp: The rcu_head structure to test.
* @f: The function passed to call_rcu() along with @rhp.
*
* Returns @true if the @rhp has been passed to call_rcu() with @func,
* and @false otherwise. Emits a warning in any other case, including
* the case where @rhp has already been invoked after a grace period.
* Calls to this function must not race with callback invocation. One way
* to avoid such races is to enclose the call to rcu_head_after_call_rcu()
* in an RCU read-side critical section that includes a read-side fetch
* of the pointer to the structure containing @rhp.
*/
static inline bool
rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
{
rcu_callback_t func = READ_ONCE(rhp->func);
if (func == f)
return true;
WARN_ON_ONCE(func != (rcu_callback_t)~0L);
return false;
}
/* kernel/ksysfs.c definitions */
extern int rcu_expedited;
extern int rcu_normal;
DEFINE_LOCK_GUARD_0(rcu,
do {
rcu_read_lock();
/*
* sparse doesn't call the cleanup function,
* so just release immediately and don't track
* the context. We don't need to anyway, since
* the whole point of the guard is to not need
* the explicit unlock.
*/
__release(RCU);
} while (0),
rcu_read_unlock())
#endif /* __LINUX_RCUPDATE_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* Contains functions related to writing back dirty pages at the
* address_space level.
*
* 10Apr2002 Andrew Morton
* Initial version
*/
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
#include <linux/rmap.h>
#include <linux/percpu.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/pagevec.h>
#include <linux/timer.h>
#include <linux/sched/rt.h>
#include <linux/sched/signal.h>
#include <linux/mm_inline.h>
#include <trace/events/writeback.h>
#include "internal.h"
/*
* Sleep at most 200ms at a time in balance_dirty_pages().
*/
#define MAX_PAUSE max(HZ/5, 1)
/*
* Try to keep balance_dirty_pages() call intervals higher than this many pages
* by raising pause time to max_pause when falls below it.
*/
#define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10))
/*
* Estimate write bandwidth or update dirty limit at 200ms intervals.
*/
#define BANDWIDTH_INTERVAL max(HZ/5, 1)
#define RATELIMIT_CALC_SHIFT 10
/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
static long ratelimit_pages = 32;
/* The following parameters are exported via /proc/sys/vm */
/*
* Start background writeback (via writeback threads) at this percentage
*/
static int dirty_background_ratio = 10;
/*
* dirty_background_bytes starts at 0 (disabled) so that it is a function of
* dirty_background_ratio * the amount of dirtyable memory
*/
static unsigned long dirty_background_bytes;
/*
* free highmem will not be subtracted from the total free memory
* for calculating free ratios if vm_highmem_is_dirtyable is true
*/
static int vm_highmem_is_dirtyable;
/*
* The generator of dirty data starts writeback at this percentage
*/
static int vm_dirty_ratio = 20;
/*
* vm_dirty_bytes starts at 0 (disabled) so that it is a function of
* vm_dirty_ratio * the amount of dirtyable memory
*/
static unsigned long vm_dirty_bytes;
/*
* The interval between `kupdate'-style writebacks
*/
unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
EXPORT_SYMBOL_GPL(dirty_writeback_interval);
/*
* The longest time for which data is allowed to remain dirty
*/
unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */
/*
* Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
* a full sync is triggered after this time elapses without any disk activity.
*/
int laptop_mode;
EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
struct wb_domain global_wb_domain;
/*
* Length of period for aging writeout fractions of bdis. This is an
* arbitrarily chosen number. The longer the period, the slower fractions will
* reflect changes in current writeout rate.
*/
#define VM_COMPLETIONS_PERIOD_LEN (3*HZ)
#ifdef CONFIG_CGROUP_WRITEBACK
#define GDTC_INIT(__wb) .wb = (__wb), \
.dom = &global_wb_domain, \
.wb_completions = &(__wb)->completions
#define GDTC_INIT_NO_WB .dom = &global_wb_domain
#define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \
.dom = mem_cgroup_wb_domain(__wb), \
.wb_completions = &(__wb)->memcg_completions, \
.gdtc = __gdtc
static bool mdtc_valid(struct dirty_throttle_control *dtc)
{
return dtc->dom;
}
static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc)
{
return dtc->dom;
}
static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc)
{
return mdtc->gdtc;
}
static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb)
{
return &wb->memcg_completions;
}
static void wb_min_max_ratio(struct bdi_writeback *wb,
unsigned long *minp, unsigned long *maxp)
{
unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
unsigned long long min = wb->bdi->min_ratio;
unsigned long long max = wb->bdi->max_ratio;
/*
* @wb may already be clean by the time control reaches here and
* the total may not include its bw.
*/
if (this_bw < tot_bw) {
if (min) {
min *= this_bw;
min = div64_ul(min, tot_bw);
}
if (max < 100 * BDI_RATIO_SCALE) {
max *= this_bw;
max = div64_ul(max, tot_bw);
}
}
*minp = min;
*maxp = max;
}
#else /* CONFIG_CGROUP_WRITEBACK */
#define GDTC_INIT(__wb) .wb = (__wb), \
.wb_completions = &(__wb)->completions
#define GDTC_INIT_NO_WB
#define MDTC_INIT(__wb, __gdtc)
static bool mdtc_valid(struct dirty_throttle_control *dtc)
{
return false;
}
static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc)
{
return &global_wb_domain;
}
static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc)
{
return NULL;
}
static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb)
{
return NULL;
}
static void wb_min_max_ratio(struct bdi_writeback *wb,
unsigned long *minp, unsigned long *maxp)
{
*minp = wb->bdi->min_ratio;
*maxp = wb->bdi->max_ratio;
}
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* In a memory zone, there is a certain amount of pages we consider
* available for the page cache, which is essentially the number of
* free and reclaimable pages, minus some zone reserves to protect
* lowmem and the ability to uphold the zone's watermarks without
* requiring writeback.
*
* This number of dirtyable pages is the base value of which the
* user-configurable dirty ratio is the effective number of pages that
* are allowed to be actually dirtied. Per individual zone, or
* globally by using the sum of dirtyable pages over all zones.
*
* Because the user is allowed to specify the dirty limit globally as
* absolute number of bytes, calculating the per-zone dirty limit can
* require translating the configured limit into a percentage of
* global dirtyable memory first.
*/
/**
* node_dirtyable_memory - number of dirtyable pages in a node
* @pgdat: the node
*
* Return: the node's number of pages potentially available for dirty
* page cache. This is the base value for the per-node dirty limits.
*/
static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
{
unsigned long nr_pages = 0;
int z;
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = pgdat->node_zones + z;
if (!populated_zone(zone))
continue;
nr_pages += zone_page_state(zone, NR_FREE_PAGES);
}
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
* clean pages in order to balance the zones.
*/
nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
return nr_pages;
}
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
int node;
unsigned long x = 0;
int i;
for_each_node_state(node, N_HIGH_MEMORY) {
for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
struct zone *z;
unsigned long nr_pages;
if (!is_highmem_idx(i))
continue;
z = &NODE_DATA(node)->node_zones[i];
if (!populated_zone(z))
continue;
nr_pages = zone_page_state(z, NR_FREE_PAGES);
/* watch for underflows */
nr_pages -= min(nr_pages, high_wmark_pages(z));
nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE);
nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE);
x += nr_pages;
}
}
/*
* Make sure that the number of highmem pages is never larger
* than the number of the total dirtyable memory. This can only
* occur in very strange VM situations but we want to make sure
* that this does not occur.
*/
return min(x, total);
#else
return 0;
#endif
}
/**
* global_dirtyable_memory - number of globally dirtyable pages
*
* Return: the global number of pages potentially available for dirty
* page cache. This is the base value for the global dirty limits.
*/
static unsigned long global_dirtyable_memory(void)
{
unsigned long x;
x = global_zone_page_state(NR_FREE_PAGES);
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
* clean pages in order to balance the zones.
*/
x -= min(x, totalreserve_pages);
x += global_node_page_state(NR_INACTIVE_FILE);
x += global_node_page_state(NR_ACTIVE_FILE);
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
return x + 1; /* Ensure that we never return 0 */
}
/**
* domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain
* @dtc: dirty_throttle_control of interest
*
* Calculate @dtc->thresh and ->bg_thresh considering
* vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller
* must ensure that @dtc->avail is set before calling this function. The
* dirty limits will be lifted by 1/4 for real-time tasks.
*/
static void domain_dirty_limits(struct dirty_throttle_control *dtc)
{
const unsigned long available_memory = dtc->avail;
struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
unsigned long bytes = vm_dirty_bytes;
unsigned long bg_bytes = dirty_background_bytes;
/* convert ratios to per-PAGE_SIZE for higher precision */
unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
unsigned long thresh;
unsigned long bg_thresh;
struct task_struct *tsk;
/* gdtc is !NULL iff @dtc is for memcg domain */
if (gdtc) {
unsigned long global_avail = gdtc->avail;
/*
* The byte settings can't be applied directly to memcg
* domains. Convert them to ratios by scaling against
* globally available memory. As the ratios are in
* per-PAGE_SIZE, they can be obtained by dividing bytes by
* number of pages.
*/
if (bytes)
ratio = min(DIV_ROUND_UP(bytes, global_avail),
PAGE_SIZE);
if (bg_bytes)
bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
PAGE_SIZE);
bytes = bg_bytes = 0;
}
if (bytes)
thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
else
thresh = (ratio * available_memory) / PAGE_SIZE;
if (bg_bytes)
bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
else
bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
tsk = current;
if (rt_or_dl_task(tsk)) {
bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
}
/*
* Dirty throttling logic assumes the limits in page units fit into
* 32-bits. This gives 16TB dirty limits max which is hopefully enough.
*/
if (thresh > UINT_MAX)
thresh = UINT_MAX;
/* This makes sure bg_thresh is within 32-bits as well */
if (bg_thresh >= thresh)
bg_thresh = thresh / 2;
dtc->thresh = thresh;
dtc->bg_thresh = bg_thresh;
/* we should eventually report the domain in the TP */
if (!gdtc)
trace_global_dirty_state(bg_thresh, thresh);
}
/**
* global_dirty_limits - background-writeback and dirty-throttling thresholds
* @pbackground: out parameter for bg_thresh
* @pdirty: out parameter for thresh
*
* Calculate bg_thresh and thresh for global_wb_domain. See
* domain_dirty_limits() for details.
*/
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
{
struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB };
gdtc.avail = global_dirtyable_memory();
domain_dirty_limits(&gdtc);
*pbackground = gdtc.bg_thresh;
*pdirty = gdtc.thresh;
}
/**
* node_dirty_limit - maximum number of dirty pages allowed in a node
* @pgdat: the node
*
* Return: the maximum number of dirty pages allowed in a node, based
* on the node's dirtyable memory.
*/
static unsigned long node_dirty_limit(struct pglist_data *pgdat)
{
unsigned long node_memory = node_dirtyable_memory(pgdat);
struct task_struct *tsk = current;
unsigned long dirty;
if (vm_dirty_bytes)
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
node_memory / global_dirtyable_memory();
else
dirty = vm_dirty_ratio * node_memory / 100;
if (rt_or_dl_task(tsk))
dirty += dirty / 4;
/*
* Dirty throttling logic assumes the limits in page units fit into
* 32-bits. This gives 16TB dirty limits max which is hopefully enough.
*/
return min_t(unsigned long, dirty, UINT_MAX);
}
/**
* node_dirty_ok - tells whether a node is within its dirty limits
* @pgdat: the node to check
*
* Return: %true when the dirty pages in @pgdat are within the node's
* dirty limit, %false if the limit is exceeded.
*/
bool node_dirty_ok(struct pglist_data *pgdat)
{
unsigned long limit = node_dirty_limit(pgdat);
unsigned long nr_pages = 0;
nr_pages += node_page_state(pgdat, NR_FILE_DIRTY);
nr_pages += node_page_state(pgdat, NR_WRITEBACK);
return nr_pages <= limit;
}
#ifdef CONFIG_SYSCTL
static int dirty_background_ratio_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
dirty_background_bytes = 0;
return ret;
}
static int dirty_background_bytes_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
unsigned long old_bytes = dirty_background_bytes;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write) {
if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) >
UINT_MAX) {
dirty_background_bytes = old_bytes;
return -ERANGE;
}
dirty_background_ratio = 0;
}
return ret;
}
static int dirty_ratio_handler(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
int old_ratio = vm_dirty_ratio;
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
writeback_set_ratelimit();
vm_dirty_bytes = 0;
}
return ret;
}
static int dirty_bytes_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
unsigned long old_bytes = vm_dirty_bytes;
int ret;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) {
vm_dirty_bytes = old_bytes;
return -ERANGE;
}
writeback_set_ratelimit();
vm_dirty_ratio = 0;
}
return ret;
}
#endif
static unsigned long wp_next_time(unsigned long cur_time)
{
cur_time += VM_COMPLETIONS_PERIOD_LEN;
/* 0 has a special meaning... */
if (!cur_time)
return 1;
return cur_time;
}
static void wb_domain_writeout_add(struct wb_domain *dom,
struct fprop_local_percpu *completions,
unsigned int max_prop_frac, long nr)
{
__fprop_add_percpu_max(&dom->completions, completions,
max_prop_frac, nr);
/* First event after period switching was turned off? */
if (unlikely(!dom->period_time)) {
/*
* We can race with other wb_domain_writeout_add calls here but
* it does not cause any harm since the resulting time when
* timer will fire and what is in writeout_period_time will be
* roughly the same.
*/
dom->period_time = wp_next_time(jiffies);
mod_timer(&dom->period_timer, dom->period_time);
}
}
/*
* Increment @wb's writeout completion count and the global writeout
* completion count. Called from __folio_end_writeback().
*/
static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr)
{
struct wb_domain *cgdom;
wb_stat_mod(wb, WB_WRITTEN, nr);
wb_domain_writeout_add(&global_wb_domain, &wb->completions,
wb->bdi->max_prop_frac, nr);
cgdom = mem_cgroup_wb_domain(wb);
if (cgdom)
wb_domain_writeout_add(cgdom, wb_memcg_completions(wb),
wb->bdi->max_prop_frac, nr);
}
void wb_writeout_inc(struct bdi_writeback *wb)
{
unsigned long flags;
local_irq_save(flags);
__wb_writeout_add(wb, 1);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(wb_writeout_inc);
/*
* On idle system, we can be called long after we scheduled because we use
* deferred timers so count with missed periods.
*/
static void writeout_period(struct timer_list *t)
{
struct wb_domain *dom = from_timer(dom, t, period_timer);
int miss_periods = (jiffies - dom->period_time) /
VM_COMPLETIONS_PERIOD_LEN;
if (fprop_new_period(&dom->completions, miss_periods + 1)) {
dom->period_time = wp_next_time(dom->period_time +
miss_periods * VM_COMPLETIONS_PERIOD_LEN);
mod_timer(&dom->period_timer, dom->period_time);
} else {
/*
* Aging has zeroed all fractions. Stop wasting CPU on period
* updates.
*/
dom->period_time = 0;
}
}
int wb_domain_init(struct wb_domain *dom, gfp_t gfp)
{
memset(dom, 0, sizeof(*dom));
spin_lock_init(&dom->lock);
timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE);
dom->dirty_limit_tstamp = jiffies;
return fprop_global_init(&dom->completions, gfp);
}
#ifdef CONFIG_CGROUP_WRITEBACK
void wb_domain_exit(struct wb_domain *dom)
{
timer_delete_sync(&dom->period_timer);
fprop_global_destroy(&dom->completions);
}
#endif
/*
* bdi_min_ratio keeps the sum of the minimum dirty shares of all
* registered backing devices, which, for obvious reasons, can not
* exceed 100%.
*/
static unsigned int bdi_min_ratio;
static int bdi_check_pages_limit(unsigned long pages)
{
unsigned long max_dirty_pages = global_dirtyable_memory();
if (pages > max_dirty_pages)
return -EINVAL;
return 0;
}
static unsigned long bdi_ratio_from_pages(unsigned long pages)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long ratio;
global_dirty_limits(&background_thresh, &dirty_thresh);
if (!dirty_thresh)
return -EINVAL;
ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh);
return ratio;
}
static u64 bdi_get_bytes(unsigned int ratio)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
u64 bytes;
global_dirty_limits(&background_thresh, &dirty_thresh);
bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100;
return bytes;
}
static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
unsigned int delta;
int ret = 0;
if (min_ratio > 100 * BDI_RATIO_SCALE)
return -EINVAL;
spin_lock_bh(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
if (min_ratio < bdi->min_ratio) {
delta = bdi->min_ratio - min_ratio;
bdi_min_ratio -= delta;
bdi->min_ratio = min_ratio;
} else {
delta = min_ratio - bdi->min_ratio;
if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) {
bdi_min_ratio += delta;
bdi->min_ratio = min_ratio;
} else {
ret = -EINVAL;
}
}
}
spin_unlock_bh(&bdi_lock);
return ret;
}
static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio)
{
int ret = 0;
if (max_ratio > 100 * BDI_RATIO_SCALE)
return -EINVAL;
spin_lock_bh(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) /
(100 * BDI_RATIO_SCALE);
}
spin_unlock_bh(&bdi_lock);
return ret;
}
int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio)
{
return __bdi_set_min_ratio(bdi, min_ratio);
}
int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio)
{
return __bdi_set_max_ratio(bdi, max_ratio);
}
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE);
}
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio)
{
return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE);
}
EXPORT_SYMBOL(bdi_set_max_ratio);
u64 bdi_get_min_bytes(struct backing_dev_info *bdi)
{
return bdi_get_bytes(bdi->min_ratio);
}
int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes)
{
int ret;
unsigned long pages = min_bytes >> PAGE_SHIFT;
long min_ratio;
ret = bdi_check_pages_limit(pages);
if (ret)
return ret;
min_ratio = bdi_ratio_from_pages(pages);
if (min_ratio < 0)
return min_ratio;
return __bdi_set_min_ratio(bdi, min_ratio);
}
u64 bdi_get_max_bytes(struct backing_dev_info *bdi)
{
return bdi_get_bytes(bdi->max_ratio);
}
int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes)
{
int ret;
unsigned long pages = max_bytes >> PAGE_SHIFT;
long max_ratio;
ret = bdi_check_pages_limit(pages);
if (ret)
return ret;
max_ratio = bdi_ratio_from_pages(pages);
if (max_ratio < 0)
return max_ratio;
return __bdi_set_max_ratio(bdi, max_ratio);
}
int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit)
{
if (strict_limit > 1)
return -EINVAL;
spin_lock_bh(&bdi_lock);
if (strict_limit)
bdi->capabilities |= BDI_CAP_STRICTLIMIT;
else
bdi->capabilities &= ~BDI_CAP_STRICTLIMIT;
spin_unlock_bh(&bdi_lock);
return 0;
}
static unsigned long dirty_freerun_ceiling(unsigned long thresh,
unsigned long bg_thresh)
{
return (thresh + bg_thresh) / 2;
}
static unsigned long hard_dirty_limit(struct wb_domain *dom,
unsigned long thresh)
{
return max(thresh, dom->dirty_limit);
}
/*
* Memory which can be further allocated to a memcg domain is capped by
* system-wide clean memory excluding the amount being used in the domain.
*/
static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
unsigned long filepages, unsigned long headroom)
{
struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc);
unsigned long clean = filepages - min(filepages, mdtc->dirty);
unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
unsigned long other_clean = global_clean - min(global_clean, clean);
mdtc->avail = filepages + min(headroom, other_clean);
}
static inline bool dtc_is_global(struct dirty_throttle_control *dtc)
{
return mdtc_gdtc(dtc) == NULL;
}
/*
* Dirty background will ignore pages being written as we're trying to
* decide whether to put more under writeback.
*/
static void domain_dirty_avail(struct dirty_throttle_control *dtc,
bool include_writeback)
{
if (dtc_is_global(dtc)) {
dtc->avail = global_dirtyable_memory();
dtc->dirty = global_node_page_state(NR_FILE_DIRTY);
if (include_writeback)
dtc->dirty += global_node_page_state(NR_WRITEBACK);
} else {
unsigned long filepages = 0, headroom = 0, writeback = 0;
mem_cgroup_wb_stats(dtc->wb, &filepages, &headroom, &dtc->dirty,
&writeback);
if (include_writeback)
dtc->dirty += writeback;
mdtc_calc_avail(dtc, filepages, headroom);
}
}
/**
* __wb_calc_thresh - @wb's share of dirty threshold
* @dtc: dirty_throttle_context of interest
* @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc
*
* Note that balance_dirty_pages() will only seriously take dirty throttling
* threshold as a hard limit when sleeping max_pause per page is not enough
* to keep the dirty pages under control. For example, when the device is
* completely stalled due to some error conditions, or when there are 1000
* dd tasks writing to a slow 10MB/s USB key.
* In the other normal situations, it acts more gently by throttling the tasks
* more (rather than completely block them) when the wb dirty pages go high.
*
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
* - starving fast devices
* - piling up dirty pages (that will take long time to sync) on slow devices
*
* The wb's share of dirty limit will be adapting to its throughput and
* bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
*
* Return: @wb's dirty limit in pages. For dirty throttling limit, the term
* "dirty" in the context of dirty balancing includes all PG_dirty and
* PG_writeback pages.
*/
static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
unsigned long thresh)
{
struct wb_domain *dom = dtc_dom(dtc);
struct bdi_writeback *wb = dtc->wb;
u64 wb_thresh;
u64 wb_max_thresh;
unsigned long numerator, denominator;
unsigned long wb_min_ratio, wb_max_ratio;
/*
* Calculate this wb's share of the thresh ratio.
*/
fprop_fraction_percpu(&dom->completions, dtc->wb_completions,
&numerator, &denominator);
wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE);
wb_thresh *= numerator;
wb_thresh = div64_ul(wb_thresh, denominator);
wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio);
wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE);
/*
* It's very possible that wb_thresh is close to 0 not because the
* device is slow, but that it has remained inactive for long time.
* Honour such devices a reasonable good (hopefully IO efficient)
* threshold, so that the occasional writes won't be blocked and active
* writes can rampup the threshold quickly.
*/
if (thresh > dtc->dirty) {
if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT))
wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100);
else
wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8);
}
wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
if (wb_thresh > wb_max_thresh)
wb_thresh = wb_max_thresh;
return wb_thresh;
}
unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
domain_dirty_avail(&gdtc, true);
return __wb_calc_thresh(&gdtc, thresh);
}
unsigned long cgwb_calc_thresh(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB };
struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) };
domain_dirty_avail(&gdtc, true);
domain_dirty_avail(&mdtc, true);
domain_dirty_limits(&mdtc);
return __wb_calc_thresh(&mdtc, mdtc.thresh);
}
/*
* setpoint - dirty 3
* f(dirty) := 1.0 + (----------------)
* limit - setpoint
*
* it's a 3rd order polynomial that subjects to
*
* (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast
* (2) f(setpoint) = 1.0 => the balance point
* (3) f(limit) = 0 => the hard limit
* (4) df/dx <= 0 => negative feedback control
* (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
* => fast response on large errors; small oscillation near setpoint
*/
static long long pos_ratio_polynom(unsigned long setpoint,
unsigned long dirty,
unsigned long limit)
{
long long pos_ratio;
long x;
x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
(limit - setpoint) | 1);
pos_ratio = x;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
pos_ratio += 1 << RATELIMIT_CALC_SHIFT;
return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT);
}
/*
* Dirty position control.
*
* (o) global/bdi setpoints
*
* We want the dirty pages be balanced around the global/wb setpoints.
* When the number of dirty pages is higher/lower than the setpoint, the
* dirty position control ratio (and hence task dirty ratelimit) will be
* decreased/increased to bring the dirty pages back to the setpoint.
*
* pos_ratio = 1 << RATELIMIT_CALC_SHIFT
*
* if (dirty < setpoint) scale up pos_ratio
* if (dirty > setpoint) scale down pos_ratio
*
* if (wb_dirty < wb_setpoint) scale up pos_ratio
* if (wb_dirty > wb_setpoint) scale down pos_ratio
*
* task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT
*
* (o) global control line
*
* ^ pos_ratio
* |
* | |<===== global dirty control scope ======>|
* 2.0 * * * * * * *
* | .*
* | . *
* | . *
* | . *
* | . *
* | . *
* 1.0 ................................*
* | . . *
* | . . *
* | . . *
* | . . *
* | . . *
* 0 +------------.------------------.----------------------*------------->
* freerun^ setpoint^ limit^ dirty pages
*
* (o) wb control line
*
* ^ pos_ratio
* |
* | *
* | *
* | *
* | *
* | * |<=========== span ============>|
* 1.0 .......................*
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* | . *
* 1/4 ...............................................* * * * * * * * * * * *
* | . .
* | . .
* | . .
* 0 +----------------------.-------------------------------.------------->
* wb_setpoint^ x_intercept^
*
* The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can
* be smoothly throttled down to normal if it starts high in situations like
* - start writing to a slow SD card and a fast disk at the same time. The SD
* card's wb_dirty may rush to many times higher than wb_setpoint.
* - the wb dirty thresh drops quickly due to change of JBOD workload
*/
static void wb_position_ratio(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
unsigned long limit = dtc->limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
unsigned long wb_thresh = dtc->wb_thresh;
unsigned long x_intercept;
unsigned long setpoint; /* dirty pages' target balance point */
unsigned long wb_setpoint;
unsigned long span;
long long pos_ratio; /* for scaling up/down the rate limit */
long x;
dtc->pos_ratio = 0;
if (unlikely(dtc->dirty >= limit))
return;
/*
* global setpoint
*
* See comment for pos_ratio_polynom().
*/
setpoint = (freerun + limit) / 2;
pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit);
/*
* The strictlimit feature is a tool preventing mistrusted filesystems
* from growing a large number of dirty pages before throttling. For
* such filesystems balance_dirty_pages always checks wb counters
* against wb limits. Even if global "nr_dirty" is under "freerun".
* This is especially important for fuse which sets bdi->max_ratio to
* 1% by default. Without strictlimit feature, fuse writeback may
* consume arbitrary amount of RAM because it is accounted in
* NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty".
*
* Here, in wb_position_ratio(), we calculate pos_ratio based on
* two values: wb_dirty and wb_thresh. Let's consider an example:
* total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global
* limits are set by default to 10% and 20% (background and throttle).
* Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages.
* wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is
* about ~6K pages (as the average of background and throttle wb
* limits). The 3rd order polynomial will provide positive feedback if
* wb_dirty is under wb_setpoint and vice versa.
*
* Note, that we cannot use global counters in these calculations
* because we want to throttle process writing to a strictlimit wb
* much earlier than global "freerun" is reached (~23MB vs. ~2.3GB
* in the example above).
*/
if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
long long wb_pos_ratio;
if (dtc->wb_dirty >= wb_thresh)
return;
wb_setpoint = dirty_freerun_ceiling(wb_thresh,
dtc->wb_bg_thresh);
if (wb_setpoint == 0 || wb_setpoint == wb_thresh)
return;
wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty,
wb_thresh);
/*
* Typically, for strictlimit case, wb_setpoint << setpoint
* and pos_ratio >> wb_pos_ratio. In the other words global
* state ("dirty") is not limiting factor and we have to
* make decision based on wb counters. But there is an
* important case when global pos_ratio should get precedence:
* global limits are exceeded (e.g. due to activities on other
* wb's) while given strictlimit wb is below limit.
*
* "pos_ratio * wb_pos_ratio" would work for the case above,
* but it would look too non-natural for the case of all
* activity in the system coming from a single strictlimit wb
* with bdi->max_ratio == 100%.
*
* Note that min() below somewhat changes the dynamics of the
* control system. Normally, pos_ratio value can be well over 3
* (when globally we are at freerun and wb is well below wb
* setpoint). Now the maximum pos_ratio in the same situation
* is 2. We might want to tweak this if we observe the control
* system is too slow to adapt.
*/
dtc->pos_ratio = min(pos_ratio, wb_pos_ratio);
return;
}
/*
* We have computed basic pos_ratio above based on global situation. If
* the wb is over/under its share of dirty pages, we want to scale
* pos_ratio further down/up. That is done by the following mechanism.
*/
/*
* wb setpoint
*
* f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint)
*
* x_intercept - wb_dirty
* := --------------------------
* x_intercept - wb_setpoint
*
* The main wb control line is a linear function that subjects to
*
* (1) f(wb_setpoint) = 1.0
* (2) k = - 1 / (8 * write_bw) (in single wb case)
* or equally: x_intercept = wb_setpoint + 8 * write_bw
*
* For single wb case, the dirty pages are observed to fluctuate
* regularly within range
* [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2]
* for various filesystems, where (2) can yield in a reasonable 12.5%
* fluctuation range for pos_ratio.
*
* For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its
* own size, so move the slope over accordingly and choose a slope that
* yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh.
*/
if (unlikely(wb_thresh > dtc->thresh))
wb_thresh = dtc->thresh;
/*
* scale global setpoint to wb's:
* wb_setpoint = setpoint * wb_thresh / thresh
*/
x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1);
wb_setpoint = setpoint * (u64)x >> 16;
/*
* Use span=(8*write_bw) in single wb case as indicated by
* (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case.
*
* wb_thresh thresh - wb_thresh
* span = --------- * (8 * write_bw) + ------------------ * wb_thresh
* thresh thresh
*/
span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16;
x_intercept = wb_setpoint + span;
if (dtc->wb_dirty < x_intercept - span / 4) {
pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty),
(x_intercept - wb_setpoint) | 1);
} else
pos_ratio /= 4;
/*
* wb reserve area, safeguard against dirty pool underrun and disk idle
* It may push the desired control point of global dirty pages higher
* than setpoint.
*/
x_intercept = wb_thresh / 2;
if (dtc->wb_dirty < x_intercept) {
if (dtc->wb_dirty > x_intercept / 8)
pos_ratio = div_u64(pos_ratio * x_intercept,
dtc->wb_dirty);
else
pos_ratio *= 8;
}
dtc->pos_ratio = pos_ratio;
}
static void wb_update_write_bandwidth(struct bdi_writeback *wb,
unsigned long elapsed,
unsigned long written)
{
const unsigned long period = roundup_pow_of_two(3 * HZ);
unsigned long avg = wb->avg_write_bandwidth;
unsigned long old = wb->write_bandwidth;
u64 bw;
/*
* bw = written * HZ / elapsed
*
* bw * elapsed + write_bandwidth * (period - elapsed)
* write_bandwidth = ---------------------------------------------------
* period
*
* @written may have decreased due to folio_redirty_for_writepage().
* Avoid underflowing @bw calculation.
*/
bw = written - min(written, wb->written_stamp);
bw *= HZ;
if (unlikely(elapsed > period)) {
bw = div64_ul(bw, elapsed);
avg = bw;
goto out;
}
bw += (u64)wb->write_bandwidth * (period - elapsed);
bw >>= ilog2(period);
/*
* one more level of smoothing, for filtering out sudden spikes
*/
if (avg > old && old >= (unsigned long)bw)
avg -= (avg - old) >> 3;
if (avg < old && old <= (unsigned long)bw)
avg += (old - avg) >> 3;
out:
/* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */
avg = max(avg, 1LU);
if (wb_has_dirty_io(wb)) {
long delta = avg - wb->avg_write_bandwidth;
WARN_ON_ONCE(atomic_long_add_return(delta,
&wb->bdi->tot_write_bandwidth) <= 0);
}
wb->write_bandwidth = bw;
WRITE_ONCE(wb->avg_write_bandwidth, avg);
}
static void update_dirty_limit(struct dirty_throttle_control *dtc)
{
struct wb_domain *dom = dtc_dom(dtc);
unsigned long thresh = dtc->thresh;
unsigned long limit = dom->dirty_limit;
/*
* Follow up in one step.
*/
if (limit < thresh) {
limit = thresh;
goto update;
}
/*
* Follow down slowly. Use the higher one as the target, because thresh
* may drop below dirty. This is exactly the reason to introduce
* dom->dirty_limit which is guaranteed to lie above the dirty pages.
*/
thresh = max(thresh, dtc->dirty);
if (limit > thresh) {
limit -= (limit - thresh) >> 5;
goto update;
}
return;
update:
dom->dirty_limit = limit;
}
static void domain_update_dirty_limit(struct dirty_throttle_control *dtc,
unsigned long now)
{
struct wb_domain *dom = dtc_dom(dtc);
/*
* check locklessly first to optimize away locking for the most time
*/
if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL))
return;
spin_lock(&dom->lock);
if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) {
update_dirty_limit(dtc);
dom->dirty_limit_tstamp = now;
}
spin_unlock(&dom->lock);
}
/*
* Maintain wb->dirty_ratelimit, the base dirty throttle rate.
*
* Normal wb tasks will be curbed at or below it in long term.
* Obviously it should be around (write_bw / N) when there are N dd tasks.
*/
static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
unsigned long dirtied,
unsigned long elapsed)
{
struct bdi_writeback *wb = dtc->wb;
unsigned long dirty = dtc->dirty;
unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
unsigned long setpoint = (freerun + limit) / 2;
unsigned long write_bw = wb->avg_write_bandwidth;
unsigned long dirty_ratelimit = wb->dirty_ratelimit;
unsigned long dirty_rate;
unsigned long task_ratelimit;
unsigned long balanced_dirty_ratelimit;
unsigned long step;
unsigned long x;
unsigned long shift;
/*
* The dirty rate will match the writeout rate in long term, except
* when dirty pages are truncated by userspace or re-dirtied by FS.
*/
dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed;
/*
* task_ratelimit reflects each dd's dirty rate for the past 200ms.
*/
task_ratelimit = (u64)dirty_ratelimit *
dtc->pos_ratio >> RATELIMIT_CALC_SHIFT;
task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */
/*
* A linear estimation of the "balanced" throttle rate. The theory is,
* if there are N dd tasks, each throttled at task_ratelimit, the wb's
* dirty_rate will be measured to be (N * task_ratelimit). So the below
* formula will yield the balanced rate limit (write_bw / N).
*
* Note that the expanded form is not a pure rate feedback:
* rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1)
* but also takes pos_ratio into account:
* rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2)
*
* (1) is not realistic because pos_ratio also takes part in balancing
* the dirty rate. Consider the state
* pos_ratio = 0.5 (3)
* rate = 2 * (write_bw / N) (4)
* If (1) is used, it will stuck in that state! Because each dd will
* be throttled at
* task_ratelimit = pos_ratio * rate = (write_bw / N) (5)
* yielding
* dirty_rate = N * task_ratelimit = write_bw (6)
* put (6) into (1) we get
* rate_(i+1) = rate_(i) (7)
*
* So we end up using (2) to always keep
* rate_(i+1) ~= (write_bw / N) (8)
* regardless of the value of pos_ratio. As long as (8) is satisfied,
* pos_ratio is able to drive itself to 1.0, which is not only where
* the dirty count meet the setpoint, but also where the slope of
* pos_ratio is most flat and hence task_ratelimit is least fluctuated.
*/
balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw,
dirty_rate | 1);
/*
* balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw
*/
if (unlikely(balanced_dirty_ratelimit > write_bw))
balanced_dirty_ratelimit = write_bw;
/*
* We could safely do this and return immediately:
*
* wb->dirty_ratelimit = balanced_dirty_ratelimit;
*
* However to get a more stable dirty_ratelimit, the below elaborated
* code makes use of task_ratelimit to filter out singular points and
* limit the step size.
*
* The below code essentially only uses the relative value of
*
* task_ratelimit - dirty_ratelimit
* = (pos_ratio - 1) * dirty_ratelimit
*
* which reflects the direction and size of dirty position error.
*/
/*
* dirty_ratelimit will follow balanced_dirty_ratelimit iff
* task_ratelimit is on the same side of dirty_ratelimit, too.
* For example, when
* - dirty_ratelimit > balanced_dirty_ratelimit
* - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint)
* lowering dirty_ratelimit will help meet both the position and rate
* control targets. Otherwise, don't update dirty_ratelimit if it will
* only help meet the rate target. After all, what the users ultimately
* feel and care are stable dirty rate and small position error.
*
* |task_ratelimit - dirty_ratelimit| is used to limit the step size
* and filter out the singular points of balanced_dirty_ratelimit. Which
* keeps jumping around randomly and can even leap far away at times
* due to the small 200ms estimation period of dirty_rate (we want to
* keep that period small to reduce time lags).
*/
step = 0;
/*
* For strictlimit case, calculations above were based on wb counters
* and limits (starting from pos_ratio = wb_position_ratio() and up to
* balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
* Hence, to calculate "step" properly, we have to use wb_dirty as
* "dirty" and wb_setpoint as "setpoint".
*/
if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
dirty = dtc->wb_dirty;
setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
}
if (dirty < setpoint) {
x = min3(wb->balanced_dirty_ratelimit,
balanced_dirty_ratelimit, task_ratelimit);
if (dirty_ratelimit < x)
step = x - dirty_ratelimit;
} else {
x = max3(wb->balanced_dirty_ratelimit,
balanced_dirty_ratelimit, task_ratelimit);
if (dirty_ratelimit > x)
step = dirty_ratelimit - x;
}
/*
* Don't pursue 100% rate matching. It's impossible since the balanced
* rate itself is constantly fluctuating. So decrease the track speed
* when it gets close to the target. Helps eliminate pointless tremors.
*/
shift = dirty_ratelimit / (2 * step + 1);
if (shift < BITS_PER_LONG)
step = DIV_ROUND_UP(step >> shift, 8);
else
step = 0;
if (dirty_ratelimit < balanced_dirty_ratelimit)
dirty_ratelimit += step;
else
dirty_ratelimit -= step;
WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL));
wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit);
}
static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc,
struct dirty_throttle_control *mdtc,
bool update_ratelimit)
{
struct bdi_writeback *wb = gdtc->wb;
unsigned long now = jiffies;
unsigned long elapsed;
unsigned long dirtied;
unsigned long written;
spin_lock(&wb->list_lock);
/*
* Lockless checks for elapsed time are racy and delayed update after
* IO completion doesn't do it at all (to make sure written pages are
* accounted reasonably quickly). Make sure elapsed >= 1 to avoid
* division errors.
*/
elapsed = max(now - wb->bw_time_stamp, 1UL);
dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
if (update_ratelimit) {
domain_update_dirty_limit(gdtc, now);
wb_update_dirty_ratelimit(gdtc, dirtied, elapsed);
/*
* @mdtc is always NULL if !CGROUP_WRITEBACK but the
* compiler has no way to figure that out. Help it.
*/
if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) {
domain_update_dirty_limit(mdtc, now);
wb_update_dirty_ratelimit(mdtc, dirtied, elapsed);
}
}
wb_update_write_bandwidth(wb, elapsed, written);
wb->dirtied_stamp = dirtied;
wb->written_stamp = written;
WRITE_ONCE(wb->bw_time_stamp, now);
spin_unlock(&wb->list_lock);
}
void wb_update_bandwidth(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
__wb_update_bandwidth(&gdtc, NULL, false);
}
/* Interval after which we consider wb idle and don't estimate bandwidth */
#define WB_BANDWIDTH_IDLE_JIF (HZ)
static void wb_bandwidth_estimate_start(struct bdi_writeback *wb)
{
unsigned long now = jiffies;
unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp);
if (elapsed > WB_BANDWIDTH_IDLE_JIF &&
!atomic_read(&wb->writeback_inodes)) {
spin_lock(&wb->list_lock);
wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED);
wb->written_stamp = wb_stat(wb, WB_WRITTEN);
WRITE_ONCE(wb->bw_time_stamp, now);
spin_unlock(&wb->list_lock);
}
}
/*
* After a task dirtied this many pages, balance_dirty_pages_ratelimited()
* will look to see if it needs to start dirty throttling.
*
* If dirty_poll_interval is too low, big NUMA machines will call the expensive
* global_zone_page_state() too often. So scale it near-sqrt to the safety margin
* (the number of pages we may dirty without exceeding the dirty limits).
*/
static unsigned long dirty_poll_interval(unsigned long dirty,
unsigned long thresh)
{
if (thresh > dirty)
return 1UL << (ilog2(thresh - dirty) >> 1);
return 1;
}
static unsigned long wb_max_pause(struct bdi_writeback *wb,
unsigned long wb_dirty)
{
unsigned long bw = READ_ONCE(wb->avg_write_bandwidth);
unsigned long t;
/*
* Limit pause time for small memory systems. If sleeping for too long
* time, a small pool of dirty/writeback pages may go empty and disk go
* idle.
*
* 8 serves as the safety ratio.
*/
t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
t++;
return min_t(unsigned long, t, MAX_PAUSE);
}
static long wb_min_pause(struct bdi_writeback *wb,
long max_pause,
unsigned long task_ratelimit,
unsigned long dirty_ratelimit,
int *nr_dirtied_pause)
{
long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth));
long lo = ilog2(READ_ONCE(wb->dirty_ratelimit));
long t; /* target pause */
long pause; /* estimated next pause */
int pages; /* target nr_dirtied_pause */
/* target for 10ms pause on 1-dd case */
t = max(1, HZ / 100);
/*
* Scale up pause time for concurrent dirtiers in order to reduce CPU
* overheads.
*
* (N * 10ms) on 2^N concurrent tasks.
*/
if (hi > lo)
t += (hi - lo) * (10 * HZ) / 1024;
/*
* This is a bit convoluted. We try to base the next nr_dirtied_pause
* on the much more stable dirty_ratelimit. However the next pause time
* will be computed based on task_ratelimit and the two rate limits may
* depart considerably at some time. Especially if task_ratelimit goes
* below dirty_ratelimit/2 and the target pause is max_pause, the next
* pause time will be max_pause*2 _trimmed down_ to max_pause. As a
* result task_ratelimit won't be executed faithfully, which could
* eventually bring down dirty_ratelimit.
*
* We apply two rules to fix it up:
* 1) try to estimate the next pause time and if necessary, use a lower
* nr_dirtied_pause so as not to exceed max_pause. When this happens,
* nr_dirtied_pause will be "dancing" with task_ratelimit.
* 2) limit the target pause time to max_pause/2, so that the normal
* small fluctuations of task_ratelimit won't trigger rule (1) and
* nr_dirtied_pause will remain as stable as dirty_ratelimit.
*/
t = min(t, 1 + max_pause / 2);
pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
/*
* Tiny nr_dirtied_pause is found to hurt I/O performance in the test
* case fio-mmap-randwrite-64k, which does 16*{sync read, async write}.
* When the 16 consecutive reads are often interrupted by some dirty
* throttling pause during the async writes, cfq will go into idles
* (deadline is fine). So push nr_dirtied_pause as high as possible
* until reaches DIRTY_POLL_THRESH=32 pages.
*/
if (pages < DIRTY_POLL_THRESH) {
t = max_pause;
pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
if (pages > DIRTY_POLL_THRESH) {
pages = DIRTY_POLL_THRESH;
t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit;
}
}
pause = HZ * pages / (task_ratelimit + 1);
if (pause > max_pause) {
t = max_pause;
pages = task_ratelimit * t / roundup_pow_of_two(HZ);
}
*nr_dirtied_pause = pages;
/*
* The minimal pause time will normally be half the target pause time.
*/
return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
}
static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
unsigned long wb_reclaimable;
/*
* wb_thresh is not treated as some limiting factor as
* dirty_thresh, due to reasons
* - in JBOD setup, wb_thresh can fluctuate a lot
* - in a system with HDD and USB key, the USB key may somehow
* go into state (wb_dirty >> wb_thresh) either because
* wb_dirty starts high, or because wb_thresh drops low.
* In this case we don't want to hard throttle the USB key
* dirtiers for 100 seconds until wb_dirty drops under
* wb_thresh. Instead the auxiliary wb control line in
* wb_position_ratio() will let the dirtier task progress
* at some rate <= (write_bw / 2) for bringing down wb_dirty.
*/
dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh);
dtc->wb_bg_thresh = dtc->thresh ?
div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
/*
* In order to avoid the stacked BDI deadlock we need
* to ensure we accurately count the 'dirty' pages when
* the threshold is low.
*
* Otherwise it would be possible to get thresh+n pages
* reported dirty, even though there are thresh-m pages
* actually dirty; with m+n sitting in the percpu
* deltas.
*/
if (dtc->wb_thresh < 2 * wb_stat_error()) {
wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK);
} else {
wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE);
dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK);
}
}
static unsigned long domain_poll_intv(struct dirty_throttle_control *dtc,
bool strictlimit)
{
unsigned long dirty, thresh;
if (strictlimit) {
dirty = dtc->wb_dirty;
thresh = dtc->wb_thresh;
} else {
dirty = dtc->dirty;
thresh = dtc->thresh;
}
return dirty_poll_interval(dirty, thresh);
}
/*
* Throttle it only when the background writeback cannot catch-up. This avoids
* (excessively) small writeouts when the wb limits are ramping up in case of
* !strictlimit.
*
* In strictlimit case make decision based on the wb counters and limits. Small
* writeouts when the wb limits are ramping up are the price we consciously pay
* for strictlimit-ing.
*/
static void domain_dirty_freerun(struct dirty_throttle_control *dtc,
bool strictlimit)
{
unsigned long dirty, thresh, bg_thresh;
if (unlikely(strictlimit)) {
wb_dirty_limits(dtc);
dirty = dtc->wb_dirty;
thresh = dtc->wb_thresh;
bg_thresh = dtc->wb_bg_thresh;
} else {
dirty = dtc->dirty;
thresh = dtc->thresh;
bg_thresh = dtc->bg_thresh;
}
dtc->freerun = dirty <= dirty_freerun_ceiling(thresh, bg_thresh);
}
static void balance_domain_limits(struct dirty_throttle_control *dtc,
bool strictlimit)
{
domain_dirty_avail(dtc, true);
domain_dirty_limits(dtc);
domain_dirty_freerun(dtc, strictlimit);
}
static void wb_dirty_freerun(struct dirty_throttle_control *dtc,
bool strictlimit)
{
dtc->freerun = false;
/* was already handled in domain_dirty_freerun */
if (strictlimit)
return;
wb_dirty_limits(dtc);
/*
* LOCAL_THROTTLE tasks must not be throttled when below the per-wb
* freerun ceiling.
*/
if (!(current->flags & PF_LOCAL_THROTTLE))
return;
dtc->freerun = dtc->wb_dirty <
dirty_freerun_ceiling(dtc->wb_thresh, dtc->wb_bg_thresh);
}
static inline void wb_dirty_exceeded(struct dirty_throttle_control *dtc,
bool strictlimit)
{
dtc->dirty_exceeded = (dtc->wb_dirty > dtc->wb_thresh) &&
((dtc->dirty > dtc->thresh) || strictlimit);
}
/*
* The limits fields dirty_exceeded and pos_ratio won't be updated if wb is
* in freerun state. Please don't use these invalid fields in freerun case.
*/
static void balance_wb_limits(struct dirty_throttle_control *dtc,
bool strictlimit)
{
wb_dirty_freerun(dtc, strictlimit);
if (dtc->freerun)
return;
wb_dirty_exceeded(dtc, strictlimit);
wb_position_ratio(dtc);
}
/*
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
* the caller to wait once crossing the (background_thresh + dirty_thresh) / 2.
* If we're over `background_thresh' then the writeback threads are woken to
* perform some writeout.
*/
static int balance_dirty_pages(struct bdi_writeback *wb,
unsigned long pages_dirtied, unsigned int flags)
{
struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) };
struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) };
struct dirty_throttle_control * const gdtc = &gdtc_stor;
struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ?
&mdtc_stor : NULL;
struct dirty_throttle_control *sdtc;
unsigned long nr_dirty;
long period;
long pause;
long max_pause;
long min_pause;
int nr_dirtied_pause;
unsigned long task_ratelimit;
unsigned long dirty_ratelimit;
struct backing_dev_info *bdi = wb->bdi;
bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
unsigned long start_time = jiffies;
int ret = 0;
for (;;) {
unsigned long now = jiffies;
nr_dirty = global_node_page_state(NR_FILE_DIRTY);
balance_domain_limits(gdtc, strictlimit);
if (mdtc) {
/*
* If @wb belongs to !root memcg, repeat the same
* basic calculations for the memcg domain.
*/
balance_domain_limits(mdtc, strictlimit);
}
/*
* In laptop mode, we wait until hitting the higher threshold
* before starting background writeout, and then write out all
* the way down to the lower threshold. So slow writers cause
* minimal disk activity.
*
* In normal mode, we start background writeout at the lower
* background_thresh, to keep the amount of dirty memory low.
*/
if (!laptop_mode && nr_dirty > gdtc->bg_thresh &&
!writeback_in_progress(wb))
wb_start_background_writeback(wb);
/*
* If memcg domain is in effect, @dirty should be under
* both global and memcg freerun ceilings.
*/
if (gdtc->freerun && (!mdtc || mdtc->freerun)) {
unsigned long intv;
unsigned long m_intv;
free_running:
intv = domain_poll_intv(gdtc, strictlimit);
m_intv = ULONG_MAX;
current->dirty_paused_when = now;
current->nr_dirtied = 0;
if (mdtc)
m_intv = domain_poll_intv(mdtc, strictlimit);
current->nr_dirtied_pause = min(intv, m_intv);
break;
}
/* Start writeback even when in laptop mode */
if (unlikely(!writeback_in_progress(wb)))
wb_start_background_writeback(wb);
mem_cgroup_flush_foreign(wb);
/*
* Calculate global domain's pos_ratio and select the
* global dtc by default.
*/
balance_wb_limits(gdtc, strictlimit);
if (gdtc->freerun)
goto free_running;
sdtc = gdtc;
if (mdtc) {
/*
* If memcg domain is in effect, calculate its
* pos_ratio. @wb should satisfy constraints from
* both global and memcg domains. Choose the one
* w/ lower pos_ratio.
*/
balance_wb_limits(mdtc, strictlimit);
if (mdtc->freerun)
goto free_running;
if (mdtc->pos_ratio < gdtc->pos_ratio)
sdtc = mdtc;
}
wb->dirty_exceeded = gdtc->dirty_exceeded ||
(mdtc && mdtc->dirty_exceeded);
if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
BANDWIDTH_INTERVAL))
__wb_update_bandwidth(gdtc, mdtc, true);
/* throttle according to the chosen dtc */
dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit);
task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >>
RATELIMIT_CALC_SHIFT;
max_pause = wb_max_pause(wb, sdtc->wb_dirty);
min_pause = wb_min_pause(wb, max_pause,
task_ratelimit, dirty_ratelimit,
&nr_dirtied_pause);
if (unlikely(task_ratelimit == 0)) {
period = max_pause;
pause = max_pause;
goto pause;
}
period = HZ * pages_dirtied / task_ratelimit;
pause = period;
if (current->dirty_paused_when)
pause -= now - current->dirty_paused_when;
/*
* For less than 1s think time (ext3/4 may block the dirtier
* for up to 800ms from time to time on 1-HDD; so does xfs,
* however at much less frequency), try to compensate it in
* future periods by updating the virtual time; otherwise just
* do a reset, as it may be a light dirtier.
*/
if (pause < min_pause) {
trace_balance_dirty_pages(wb,
sdtc,
dirty_ratelimit,
task_ratelimit,
pages_dirtied,
period,
min(pause, 0L),
start_time);
if (pause < -HZ) {
current->dirty_paused_when = now;
current->nr_dirtied = 0;
} else if (period) {
current->dirty_paused_when += period;
current->nr_dirtied = 0;
} else if (current->nr_dirtied_pause <= pages_dirtied)
current->nr_dirtied_pause += pages_dirtied;
break;
}
if (unlikely(pause > max_pause)) {
/* for occasional dropped task_ratelimit */
now += min(pause - max_pause, max_pause);
pause = max_pause;
}
pause:
trace_balance_dirty_pages(wb,
sdtc,
dirty_ratelimit,
task_ratelimit,
pages_dirtied,
period,
pause,
start_time);
if (flags & BDP_ASYNC) {
ret = -EAGAIN;
break;
}
__set_current_state(TASK_KILLABLE);
bdi->last_bdp_sleep = jiffies;
io_schedule_timeout(pause);
current->dirty_paused_when = now + pause;
current->nr_dirtied = 0;
current->nr_dirtied_pause = nr_dirtied_pause;
/*
* This is typically equal to (dirty < thresh) and can also
* keep "1000+ dd on a slow USB stick" under control.
*/
if (task_ratelimit)
break;
/*
* In the case of an unresponsive NFS server and the NFS dirty
* pages exceeds dirty_thresh, give the other good wb's a pipe
* to go through, so that tasks on them still remain responsive.
*
* In theory 1 page is enough to keep the consumer-producer
* pipe going: the flusher cleans 1 page => the task dirties 1
* more page. However wb_dirty has accounting errors. So use
* the larger and more IO friendly wb_stat_error.
*/
if (sdtc->wb_dirty <= wb_stat_error())
break;
if (fatal_signal_pending(current))
break;
}
return ret;
}
static DEFINE_PER_CPU(int, bdp_ratelimits);
/*
* Normal tasks are throttled by
* loop {
* dirty tsk->nr_dirtied_pause pages;
* take a snap in balance_dirty_pages();
* }
* However there is a worst case. If every task exit immediately when dirtied
* (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be
* called to throttle the page dirties. The solution is to save the not yet
* throttled page dirties in dirty_throttle_leaks on task exit and charge them
* randomly into the running tasks. This works well for the above worst case,
* as the new task will pick up and accumulate the old task's leaked dirty
* count and eventually get throttled.
*/
DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
/**
* balance_dirty_pages_ratelimited_flags - Balance dirty memory state.
* @mapping: address_space which was dirtied.
* @flags: BDP flags.
*
* Processes which are dirtying memory should call in here once for each page
* which was newly dirtied. The function will periodically check the system's
* dirty state and will initiate writeback if needed.
*
* See balance_dirty_pages_ratelimited() for details.
*
* Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to
* indicate that memory is out of balance and the caller must wait
* for I/O to complete. Otherwise, it will return 0 to indicate
* that either memory was already in balance, or it was able to sleep
* until the amount of dirty memory returned to balance.
*/
int balance_dirty_pages_ratelimited_flags(struct address_space *mapping,
unsigned int flags)
{
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct bdi_writeback *wb = NULL;
int ratelimit;
int ret = 0;
int *p;
if (!(bdi->capabilities & BDI_CAP_WRITEBACK))
return ret;
if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL);
if (!wb)
wb = &bdi->wb;
ratelimit = current->nr_dirtied_pause;
if (wb->dirty_exceeded)
ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
preempt_disable();
/*
* This prevents one CPU to accumulate too many dirtied pages without
* calling into balance_dirty_pages(), which can happen when there are
* 1000+ tasks, all of them start dirtying pages at exactly the same
* time, hence all honoured too large initial task->nr_dirtied_pause.
*/
p = this_cpu_ptr(&bdp_ratelimits);
if (unlikely(current->nr_dirtied >= ratelimit))
*p = 0;
else if (unlikely(*p >= ratelimit_pages)) {
*p = 0;
ratelimit = 0;
}
/*
* Pick up the dirtied pages by the exited tasks. This avoids lots of
* short-lived tasks (eg. gcc invocations in a kernel build) escaping
* the dirty throttling and livelock other long-run dirtiers.
*/
p = this_cpu_ptr(&dirty_throttle_leaks);
if (*p > 0 && current->nr_dirtied < ratelimit) {
unsigned long nr_pages_dirtied;
nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
*p -= nr_pages_dirtied;
current->nr_dirtied += nr_pages_dirtied;
}
preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb);
return ret;
}
EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags);
/**
* balance_dirty_pages_ratelimited - balance dirty memory state.
* @mapping: address_space which was dirtied.
*
* Processes which are dirtying memory should call in here once for each page
* which was newly dirtied. The function will periodically check the system's
* dirty state and will initiate writeback if needed.
*
* Once we're over the dirty memory limit we decrease the ratelimiting
* by a lot, to prevent individual processes from overshooting the limit
* by (ratelimit_pages) each.
*/
void balance_dirty_pages_ratelimited(struct address_space *mapping)
{
balance_dirty_pages_ratelimited_flags(mapping, 0);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
/*
* Similar to wb_dirty_limits, wb_bg_dirty_limits also calculates dirty
* and thresh, but it's for background writeback.
*/
static void wb_bg_dirty_limits(struct dirty_throttle_control *dtc)
{
struct bdi_writeback *wb = dtc->wb;
dtc->wb_bg_thresh = __wb_calc_thresh(dtc, dtc->bg_thresh);
if (dtc->wb_bg_thresh < 2 * wb_stat_error())
dtc->wb_dirty = wb_stat_sum(wb, WB_RECLAIMABLE);
else
dtc->wb_dirty = wb_stat(wb, WB_RECLAIMABLE);
}
static bool domain_over_bg_thresh(struct dirty_throttle_control *dtc)
{
domain_dirty_avail(dtc, false);
domain_dirty_limits(dtc);
if (dtc->dirty > dtc->bg_thresh)
return true;
wb_bg_dirty_limits(dtc);
if (dtc->wb_dirty > dtc->wb_bg_thresh)
return true;
return false;
}
/**
* wb_over_bg_thresh - does @wb need to be written back?
* @wb: bdi_writeback of interest
*
* Determines whether background writeback should keep writing @wb or it's
* clean enough.
*
* Return: %true if writeback should continue.
*/
bool wb_over_bg_thresh(struct bdi_writeback *wb)
{
struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) };
if (domain_over_bg_thresh(&gdtc))
return true;
if (mdtc_valid(&mdtc))
return domain_over_bg_thresh(&mdtc);
return false;
}
#ifdef CONFIG_SYSCTL
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
unsigned int old_interval = dirty_writeback_interval;
int ret;
ret = proc_dointvec(table, write, buffer, length, ppos);
/*
* Writing 0 to dirty_writeback_interval will disable periodic writeback
* and a different non-zero value will wakeup the writeback threads.
* wb_wakeup_delayed() would be more appropriate, but it's a pain to
* iterate over all bdis and wbs.
* The reason we do this is to make the change take effect immediately.
*/
if (!ret && write && dirty_writeback_interval &&
dirty_writeback_interval != old_interval)
wakeup_flusher_threads(WB_REASON_PERIODIC);
return ret;
}
#endif
void laptop_mode_timer_fn(struct timer_list *t)
{
struct backing_dev_info *backing_dev_info =
from_timer(backing_dev_info, t, laptop_mode_wb_timer);
wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER);
}
/*
* We've spun up the disk and we're in laptop mode: schedule writeback
* of all dirty data a few seconds from now. If the flush is already scheduled
* then push it back - the user is still using the disk.
*/
void laptop_io_completion(struct backing_dev_info *info)
{
mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
}
/*
* We're in laptop mode and we've just synced. The sync's writes will have
* caused another writeback to be scheduled by laptop_io_completion.
* Nothing needs to be written back anymore, so we unschedule the writeback.
*/
void laptop_sync_completion(void)
{
struct backing_dev_info *bdi;
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
timer_delete(&bdi->laptop_mode_wb_timer);
rcu_read_unlock();
}
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
* if a large number of processes all perform writes at the same time.
*
* Here we set ratelimit_pages to a level which ensures that when all CPUs are
* dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
* thresholds.
*/
void writeback_set_ratelimit(void)
{
struct wb_domain *dom = &global_wb_domain;
unsigned long background_thresh;
unsigned long dirty_thresh;
global_dirty_limits(&background_thresh, &dirty_thresh);
dom->dirty_limit = dirty_thresh;
ratelimit_pages = dirty_thresh / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
ratelimit_pages = 16;
}
static int page_writeback_cpu_online(unsigned int cpu)
{
writeback_set_ratelimit();
return 0;
}
#ifdef CONFIG_SYSCTL
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
static const struct ctl_table vm_page_writeback_sysctls[] = {
{
.procname = "dirty_background_ratio",
.data = &dirty_background_ratio,
.maxlen = sizeof(dirty_background_ratio),
.mode = 0644,
.proc_handler = dirty_background_ratio_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE_HUNDRED,
},
{
.procname = "dirty_background_bytes",
.data = &dirty_background_bytes,
.maxlen = sizeof(dirty_background_bytes),
.mode = 0644,
.proc_handler = dirty_background_bytes_handler,
.extra1 = SYSCTL_LONG_ONE,
},
{
.procname = "dirty_ratio",
.data = &vm_dirty_ratio,
.maxlen = sizeof(vm_dirty_ratio),
.mode = 0644,
.proc_handler = dirty_ratio_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE_HUNDRED,
},
{
.procname = "dirty_bytes",
.data = &vm_dirty_bytes,
.maxlen = sizeof(vm_dirty_bytes),
.mode = 0644,
.proc_handler = dirty_bytes_handler,
.extra1 = (void *)&dirty_bytes_min,
},
{
.procname = "dirty_writeback_centisecs",
.data = &dirty_writeback_interval,
.maxlen = sizeof(dirty_writeback_interval),
.mode = 0644,
.proc_handler = dirty_writeback_centisecs_handler,
},
{
.procname = "dirty_expire_centisecs",
.data = &dirty_expire_interval,
.maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#ifdef CONFIG_HIGHMEM
{
.procname = "highmem_is_dirtyable",
.data = &vm_highmem_is_dirtyable,
.maxlen = sizeof(vm_highmem_is_dirtyable),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
#endif
{
.procname = "laptop_mode",
.data = &laptop_mode,
.maxlen = sizeof(laptop_mode),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
};
#endif
/*
* Called early on to tune the page writeback dirty limits.
*
* We used to scale dirty pages according to how total memory
* related to pages that could be allocated for buffers.
*
* However, that was when we used "dirty_ratio" to scale with
* all memory, and we don't do that any more. "dirty_ratio"
* is now applied to total non-HIGHPAGE memory, and as such we can't
* get into the old insane situation any more where we had
* large amounts of dirty pages compared to a small amount of
* non-HIGHMEM memory.
*
* But we might still want to scale the dirty_ratio by how
* much memory the box has..
*/
void __init page_writeback_init(void)
{
BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online",
page_writeback_cpu_online, NULL);
cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL,
page_writeback_cpu_online);
#ifdef CONFIG_SYSCTL
register_sysctl_init("vm", vm_page_writeback_sysctls);
#endif
}
/**
* tag_pages_for_writeback - tag pages to be written by writeback
* @mapping: address space structure to write
* @start: starting page index
* @end: ending page index (inclusive)
*
* This function scans the page range from @start to @end (inclusive) and tags
* all pages that have DIRTY tag set with a special TOWRITE tag. The caller
* can then use the TOWRITE tag to identify pages eligible for writeback.
* This mechanism is used to avoid livelocking of writeback by a process
* steadily creating new dirty pages in the file (thus it is important for this
* function to be quick so that it can tag pages faster than a dirtying process
* can create them).
*/
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
XA_STATE(xas, &mapping->i_pages, start);
unsigned int tagged = 0;
void *page;
xas_lock_irq(&xas);
xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) {
xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE);
if (++tagged % XA_CHECK_SCHED)
continue;
xas_pause(&xas);
xas_unlock_irq(&xas);
cond_resched();
xas_lock_irq(&xas);
}
xas_unlock_irq(&xas);
}
EXPORT_SYMBOL(tag_pages_for_writeback);
static bool folio_prepare_writeback(struct address_space *mapping,
struct writeback_control *wbc, struct folio *folio)
{
/*
* Folio truncated or invalidated. We can freely skip it then,
* even for data integrity operations: the folio has disappeared
* concurrently, so there could be no real expectation of this
* data integrity operation even if there is now a new, dirty
* folio at the same pagecache index.
*/
if (unlikely(folio->mapping != mapping))
return false;
/*
* Did somebody else write it for us?
*/
if (!folio_test_dirty(folio))
return false;
if (folio_test_writeback(folio)) {
if (wbc->sync_mode == WB_SYNC_NONE)
return false;
folio_wait_writeback(folio);
}
BUG_ON(folio_test_writeback(folio));
if (!folio_clear_dirty_for_io(folio))
return false;
return true;
}
static xa_mark_t wbc_to_tag(struct writeback_control *wbc)
{
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
return PAGECACHE_TAG_TOWRITE;
return PAGECACHE_TAG_DIRTY;
}
static pgoff_t wbc_end(struct writeback_control *wbc)
{
if (wbc->range_cyclic)
return -1;
return wbc->range_end >> PAGE_SHIFT;
}
static struct folio *writeback_get_folio(struct address_space *mapping,
struct writeback_control *wbc)
{
struct folio *folio;
retry:
folio = folio_batch_next(&wbc->fbatch);
if (!folio) {
folio_batch_release(&wbc->fbatch);
cond_resched();
filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc),
wbc_to_tag(wbc), &wbc->fbatch);
folio = folio_batch_next(&wbc->fbatch);
if (!folio)
return NULL;
}
folio_lock(folio);
if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) {
folio_unlock(folio);
goto retry;
}
trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
return folio;
}
/**
* writeback_iter - iterate folio of a mapping for writeback
* @mapping: address space structure to write
* @wbc: writeback context
* @folio: previously iterated folio (%NULL to start)
* @error: in-out pointer for writeback errors (see below)
*
* This function returns the next folio for the writeback operation described by
* @wbc on @mapping and should be called in a while loop in the ->writepages
* implementation.
*
* To start the writeback operation, %NULL is passed in the @folio argument, and
* for every subsequent iteration the folio returned previously should be passed
* back in.
*
* If there was an error in the per-folio writeback inside the writeback_iter()
* loop, @error should be set to the error value.
*
* Once the writeback described in @wbc has finished, this function will return
* %NULL and if there was an error in any iteration restore it to @error.
*
* Note: callers should not manually break out of the loop using break or goto
* but must keep calling writeback_iter() until it returns %NULL.
*
* Return: the folio to write or %NULL if the loop is done.
*/
struct folio *writeback_iter(struct address_space *mapping,
struct writeback_control *wbc, struct folio *folio, int *error)
{
if (!folio) {
folio_batch_init(&wbc->fbatch);
wbc->saved_err = *error = 0;
/*
* For range cyclic writeback we remember where we stopped so
* that we can continue where we stopped.
*
* For non-cyclic writeback we always start at the beginning of
* the passed in range.
*/
if (wbc->range_cyclic)
wbc->index = mapping->writeback_index;
else
wbc->index = wbc->range_start >> PAGE_SHIFT;
/*
* To avoid livelocks when other processes dirty new pages, we
* first tag pages which should be written back and only then
* start writing them.
*
* For data-integrity writeback we have to be careful so that we
* do not miss some pages (e.g., because some other process has
* cleared the TOWRITE tag we set). The rule we follow is that
* TOWRITE tag can be cleared only by the process clearing the
* DIRTY tag (and submitting the page for I/O).
*/
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, wbc->index,
wbc_end(wbc));
} else {
wbc->nr_to_write -= folio_nr_pages(folio);
WARN_ON_ONCE(*error > 0);
/*
* For integrity writeback we have to keep going until we have
* written all the folios we tagged for writeback above, even if
* we run past wbc->nr_to_write or encounter errors.
* We stash away the first error we encounter in wbc->saved_err
* so that it can be retrieved when we're done. This is because
* the file system may still have state to clear for each folio.
*
* For background writeback we exit as soon as we run past
* wbc->nr_to_write or encounter the first error.
*/
if (wbc->sync_mode == WB_SYNC_ALL) {
if (*error && !wbc->saved_err)
wbc->saved_err = *error;
} else {
if (*error || wbc->nr_to_write <= 0)
goto done;
}
}
folio = writeback_get_folio(mapping, wbc);
if (!folio) {
/*
* To avoid deadlocks between range_cyclic writeback and callers
* that hold pages in PageWriteback to aggregate I/O until
* the writeback iteration finishes, we do not loop back to the
* start of the file. Doing so causes a page lock/page
* writeback access order inversion - we should only ever lock
* multiple pages in ascending page->index order, and looping
* back to the start of the file violates that rule and causes
* deadlocks.
*/
if (wbc->range_cyclic)
mapping->writeback_index = 0;
/*
* Return the first error we encountered (if there was any) to
* the caller.
*/
*error = wbc->saved_err;
}
return folio;
done:
if (wbc->range_cyclic)
mapping->writeback_index = folio_next_index(folio);
folio_batch_release(&wbc->fbatch);
return NULL;
}
EXPORT_SYMBOL_GPL(writeback_iter);
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* Return: %0 on success, negative error code otherwise
*
* Note: please use writeback_iter() instead.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct folio *folio = NULL;
int error;
while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
error = writepage(folio, wbc, data);
if (error == AOP_WRITEPAGE_ACTIVATE) {
folio_unlock(folio);
error = 0;
}
}
return error;
}
EXPORT_SYMBOL(write_cache_pages);
static int writeback_use_writepage(struct address_space *mapping,
struct writeback_control *wbc)
{
struct folio *folio = NULL;
struct blk_plug plug;
int err;
blk_start_plug(&plug);
while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
err = mapping->a_ops->writepage(&folio->page, wbc);
if (err == AOP_WRITEPAGE_ACTIVATE) {
folio_unlock(folio);
err = 0;
}
mapping_set_error(mapping, err);
}
blk_finish_plug(&plug);
return err;
}
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int ret;
struct bdi_writeback *wb;
if (wbc->nr_to_write <= 0)
return 0;
wb = inode_to_wb_wbc(mapping->host, wbc);
wb_bandwidth_estimate_start(wb);
while (1) {
if (mapping->a_ops->writepages) {
ret = mapping->a_ops->writepages(mapping, wbc);
} else if (mapping->a_ops->writepage) {
ret = writeback_use_writepage(mapping, wbc);
} else {
/* deal with chardevs and other special files */
ret = 0;
}
if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL)
break;
/*
* Lacking an allocation context or the locality or writeback
* state of any of the inode's pages, throttle based on
* writeback activity on the local node. It's as good a
* guess as any.
*/
reclaim_throttle(NODE_DATA(numa_node_id()),
VMSCAN_THROTTLE_WRITEBACK);
}
/*
* Usually few pages are written by now from those we've just submitted
* but if there's constant writeback being submitted, this makes sure
* writeback bandwidth is updated once in a while.
*/
if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
BANDWIDTH_INTERVAL))
wb_update_bandwidth(wb);
return ret;
}
/*
* For address_spaces which do not use buffers nor write back.
*/
bool noop_dirty_folio(struct address_space *mapping, struct folio *folio)
{ if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio);
return false;
}
EXPORT_SYMBOL(noop_dirty_folio);
/*
* Helper function for set_page_dirty family.
*
* NOTE: This relies on being atomic wrt interrupts.
*/
static void folio_account_dirtied(struct folio *folio,
struct address_space *mapping)
{
struct inode *inode = mapping->host;
trace_writeback_dirty_folio(folio, mapping);
if (mapping_can_writeback(mapping)) {
struct bdi_writeback *wb;
long nr = folio_nr_pages(folio);
inode_attach_wb(inode, folio);
wb = inode_to_wb(inode);
__lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr);
__zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
__node_stat_mod_folio(folio, NR_DIRTIED, nr);
wb_stat_mod(wb, WB_RECLAIMABLE, nr);
wb_stat_mod(wb, WB_DIRTIED, nr);
task_io_account_write(nr * PAGE_SIZE);
current->nr_dirtied += nr;
__this_cpu_add(bdp_ratelimits, nr);
mem_cgroup_track_foreign_dirty(folio, wb);
}
}
/*
* Helper function for deaccounting dirty page without writeback.
*
*/
void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
{
long nr = folio_nr_pages(folio);
lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
task_io_account_cancelled_write(nr * PAGE_SIZE);
}
/*
* Mark the folio dirty, and set it dirty in the page cache.
*
* If warn is true, then emit a warning if the folio is not uptodate and has
* not been truncated.
*
* It is the caller's responsibility to prevent the folio from being truncated
* while this function is in progress, although it may have been truncated
* before this function is called. Most callers have the folio locked.
* A few have the folio blocked from truncation through other means (e.g.
* zap_vma_pages() has it mapped and is holding the page table lock).
* When called from mark_buffer_dirty(), the filesystem should hold a
* reference to the buffer_head that is being marked dirty, which causes
* try_to_free_buffers() to fail.
*/
void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
int warn)
{
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
if (folio->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !folio_test_uptodate(folio));
folio_account_dirtied(folio, mapping);
__xa_set_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_DIRTY);
}
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
/**
* filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads.
* @mapping: Address space this folio belongs to.
* @folio: Folio to be marked as dirty.
*
* Filesystems which do not use buffer heads should call this function
* from their dirty_folio address space operation. It ignores the
* contents of folio_get_private(), so if the filesystem marks individual
* blocks as dirty, the filesystem should handle that itself.
*
* This is also sometimes used by filesystems which use buffer_heads when
* a single buffer is being dirtied: we want to set the folio dirty in
* that case, but not all the buffers. This is a "bottom-up" dirtying,
* whereas block_dirty_folio() is a "top-down" dirtying.
*
* The caller must ensure this doesn't race with truncation. Most will
* simply hold the folio lock, but e.g. zap_pte_range() calls with the
* folio mapped and the pte lock held, which also locks out truncation.
*/
bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
{
if (folio_test_set_dirty(folio))
return false;
__folio_mark_dirty(folio, mapping, !folio_test_private(folio));
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return true;
}
EXPORT_SYMBOL(filemap_dirty_folio);
/**
* folio_redirty_for_writepage - Decline to write a dirty folio.
* @wbc: The writeback control.
* @folio: The folio.
*
* When a writepage implementation decides that it doesn't want to write
* @folio for some reason, it should call this function, unlock @folio and
* return 0.
*
* Return: True if we redirtied the folio. False if someone else dirtied
* it first.
*/
bool folio_redirty_for_writepage(struct writeback_control *wbc,
struct folio *folio)
{
struct address_space *mapping = folio->mapping;
long nr = folio_nr_pages(folio);
bool ret;
wbc->pages_skipped += nr;
ret = filemap_dirty_folio(mapping, folio);
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
wb = unlocked_inode_to_wb_begin(inode, &cookie);
current->nr_dirtied -= nr;
node_stat_mod_folio(folio, NR_DIRTIED, -nr);
wb_stat_mod(wb, WB_DIRTIED, -nr);
unlocked_inode_to_wb_end(inode, &cookie);
}
return ret;
}
EXPORT_SYMBOL(folio_redirty_for_writepage);
/**
* folio_mark_dirty - Mark a folio as being modified.
* @folio: The folio.
*
* The folio may not be truncated while this function is running.
* Holding the folio lock is sufficient to prevent truncation, but some
* callers cannot acquire a sleeping lock. These callers instead hold
* the page table lock for a page table which contains at least one page
* in this folio. Truncation will block on the page table lock as it
* unmaps pages before removing the folio from its mapping.
*
* Return: True if the folio was newly dirtied, false if it was already dirty.
*/
bool folio_mark_dirty(struct folio *folio)
{
struct address_space *mapping = folio_mapping(folio);
if (likely(mapping)) {
/*
* readahead/folio_deactivate could remain
* PG_readahead/PG_reclaim due to race with folio_end_writeback
* About readahead, if the folio is written, the flags would be
* reset. So no problem.
* About folio_deactivate, if the folio is redirtied,
* the flag will be reset. So no problem. but if the
* folio is used by readahead it will confuse readahead
* and make it restart the size rampup process. But it's
* a trivial problem.
*/
if (folio_test_reclaim(folio)) folio_clear_reclaim(folio);
return mapping->a_ops->dirty_folio(mapping, folio);
}
return noop_dirty_folio(mapping, folio);
}
EXPORT_SYMBOL(folio_mark_dirty);
/*
* folio_mark_dirty() is racy if the caller has no reference against
* folio->mapping->host, and if the folio is unlocked. This is because another
* CPU could truncate the folio off the mapping and then free the mapping.
*
* Usually, the folio _is_ locked, or the caller is a user-space process which
* holds a reference on the inode by having an open file.
*
* In other cases, the folio should be locked before running folio_mark_dirty().
*/
bool folio_mark_dirty_lock(struct folio *folio)
{
bool ret;
folio_lock(folio);
ret = folio_mark_dirty(folio);
folio_unlock(folio);
return ret;
}
EXPORT_SYMBOL(folio_mark_dirty_lock);
/*
* This cancels just the dirty bit on the kernel page itself, it does NOT
* actually remove dirty bits on any mmap's that may be around. It also
* leaves the page tagged dirty, so any sync activity will still find it on
* the dirty lists, and in particular, clear_page_dirty_for_io() will still
* look at the dirty bits in the VM.
*
* Doing this should *normally* only ever be done when a page is truncated,
* and is not actually mapped anywhere at all. However, fs/buffer.c does
* this when it notices that somebody has cleaned out all the buffers on a
* page without actually doing it through the VM. Can you say "ext3 is
* horribly ugly"? Thought you could.
*/
void __folio_cancel_dirty(struct folio *folio)
{
struct address_space *mapping = folio_mapping(folio);
if (mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie);
} else {
folio_clear_dirty(folio);
}
}
EXPORT_SYMBOL(__folio_cancel_dirty);
/*
* Clear a folio's dirty flag, while caring for dirty memory accounting.
* Returns true if the folio was previously dirty.
*
* This is for preparing to put the folio under writeout. We leave
* the folio tagged as dirty in the xarray so that a concurrent
* write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk.
* The ->writepage implementation will run either folio_start_writeback()
* or folio_mark_dirty(), at which stage we bring the folio's dirty flag
* and xarray dirty tag back into sync.
*
* This incoherency between the folio's dirty flag and xarray tag is
* unfortunate, but it only exists while the folio is locked.
*/
bool folio_clear_dirty_for_io(struct folio *folio)
{
struct address_space *mapping = folio_mapping(folio);
bool ret = false;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole folio dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the folio again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "folio_mark_dirty(folio)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the folio "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
if (folio_mkclean(folio))
folio_mark_dirty(folio);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the folio dirty
* at this point. We do this by having them hold the
* page lock while dirtying the folio, and folios are
* always locked coming in here, so we get the desired
* exclusion.
*/
wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (folio_test_clear_dirty(folio)) {
long nr = folio_nr_pages(folio);
lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
ret = true;
}
unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
return folio_test_clear_dirty(folio);
}
EXPORT_SYMBOL(folio_clear_dirty_for_io);
static void wb_inode_writeback_start(struct bdi_writeback *wb)
{
atomic_inc(&wb->writeback_inodes);
}
static void wb_inode_writeback_end(struct bdi_writeback *wb)
{
unsigned long flags;
atomic_dec(&wb->writeback_inodes);
/*
* Make sure estimate of writeback throughput gets updated after
* writeback completed. We delay the update by BANDWIDTH_INTERVAL
* (which is the interval other bandwidth updates use for batching) so
* that if multiple inodes end writeback at a similar time, they get
* batched into one bandwidth update.
*/
spin_lock_irqsave(&wb->work_lock, flags);
if (test_bit(WB_registered, &wb->state))
queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
spin_unlock_irqrestore(&wb->work_lock, flags);
}
bool __folio_end_writeback(struct folio *folio)
{
long nr = folio_nr_pages(folio);
struct address_space *mapping = folio_mapping(folio);
bool ret;
if (mapping && mapping_use_writeback_tags(mapping)) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
__xa_clear_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_WRITEBACK);
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
wb_stat_mod(wb, WB_WRITEBACK, -nr);
__wb_writeout_add(wb, nr);
if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
wb_inode_writeback_end(wb);
}
if (mapping->host && !mapping_tagged(mapping,
PAGECACHE_TAG_WRITEBACK))
sb_clear_inode_writeback(mapping->host);
xa_unlock_irqrestore(&mapping->i_pages, flags);
} else {
ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
}
lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
node_stat_mod_folio(folio, NR_WRITTEN, nr);
return ret;
}
void __folio_start_writeback(struct folio *folio, bool keep_write)
{
long nr = folio_nr_pages(folio);
struct address_space *mapping = folio_mapping(folio);
int access_ret;
VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (mapping && mapping_use_writeback_tags(mapping)) {
XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
bool on_wblist;
xas_lock_irqsave(&xas, flags);
xas_load(&xas);
folio_test_set_writeback(folio);
on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
wb_stat_mod(wb, WB_WRITEBACK, nr);
if (!on_wblist)
wb_inode_writeback_start(wb);
}
/*
* We can come through here when swapping anonymous
* folios, so we don't necessarily have an inode to
* track for sync.
*/
if (mapping->host && !on_wblist)
sb_mark_inode_writeback(mapping->host);
if (!folio_test_dirty(folio))
xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
if (!keep_write)
xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
xas_unlock_irqrestore(&xas, flags);
} else {
folio_test_set_writeback(folio);
}
lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
access_ret = arch_make_folio_accessible(folio);
/*
* If writeback has been triggered on a page that cannot be made
* accessible, it is too late to recover here.
*/
VM_BUG_ON_FOLIO(access_ret != 0, folio);
}
EXPORT_SYMBOL(__folio_start_writeback);
/**
* folio_wait_writeback - Wait for a folio to finish writeback.
* @folio: The folio to wait for.
*
* If the folio is currently being written back to storage, wait for the
* I/O to complete.
*
* Context: Sleeps. Must be called in process context and with
* no spinlocks held. Caller should hold a reference on the folio.
* If the folio is not locked, writeback may start again after writeback
* has finished.
*/
void folio_wait_writeback(struct folio *folio)
{
while (folio_test_writeback(folio)) {
trace_folio_wait_writeback(folio, folio_mapping(folio));
folio_wait_bit(folio, PG_writeback);
}
}
EXPORT_SYMBOL_GPL(folio_wait_writeback);
/**
* folio_wait_writeback_killable - Wait for a folio to finish writeback.
* @folio: The folio to wait for.
*
* If the folio is currently being written back to storage, wait for the
* I/O to complete or a fatal signal to arrive.
*
* Context: Sleeps. Must be called in process context and with
* no spinlocks held. Caller should hold a reference on the folio.
* If the folio is not locked, writeback may start again after writeback
* has finished.
* Return: 0 on success, -EINTR if we get a fatal signal while waiting.
*/
int folio_wait_writeback_killable(struct folio *folio)
{
while (folio_test_writeback(folio)) {
trace_folio_wait_writeback(folio, folio_mapping(folio));
if (folio_wait_bit_killable(folio, PG_writeback))
return -EINTR;
}
return 0;
}
EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
/**
* folio_wait_stable() - wait for writeback to finish, if necessary.
* @folio: The folio to wait on.
*
* This function determines if the given folio is related to a backing
* device that requires folio contents to be held stable during writeback.
* If so, then it will wait for any pending writeback to complete.
*
* Context: Sleeps. Must be called in process context and with
* no spinlocks held. Caller should hold a reference on the folio.
* If the folio is not locked, writeback may start again after writeback
* has finished.
*/
void folio_wait_stable(struct folio *folio)
{
if (mapping_stable_writes(folio_mapping(folio)))
folio_wait_writeback(folio);
}
EXPORT_SYMBOL_GPL(folio_wait_stable);
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */
#include <linux/cred.h>
#include <linux/fs.h>
#include <linux/mnt_idmapping.h>
#include <linux/slab.h>
#include <linux/user_namespace.h>
#include <linux/seq_file.h>
#include "internal.h"
/*
* Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t,
* never from raw values. These are just internal helpers.
*/
#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val }
#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val }
struct mnt_idmap {
struct uid_gid_map uid_map;
struct uid_gid_map gid_map;
refcount_t count;
};
/*
* Carries the initial idmapping of 0:0:4294967295 which is an identity
* mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is
* mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...].
*/
struct mnt_idmap nop_mnt_idmap = {
.count = REFCOUNT_INIT(1),
};
EXPORT_SYMBOL_GPL(nop_mnt_idmap);
/*
* Carries the invalid idmapping of a full 0-4294967295 {g,u}id range.
* This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID.
*/
struct mnt_idmap invalid_mnt_idmap = {
.count = REFCOUNT_INIT(1),
};
EXPORT_SYMBOL_GPL(invalid_mnt_idmap);
/**
* initial_idmapping - check whether this is the initial mapping
* @ns: idmapping to check
*
* Check whether this is the initial mapping, mapping 0 to 0, 1 to 1,
* [...], 1000 to 1000 [...].
*
* Return: true if this is the initial mapping, false if not.
*/
static inline bool initial_idmapping(const struct user_namespace *ns)
{
return ns == &init_user_ns;
}
/**
* make_vfsuid - map a filesystem kuid according to an idmapping
* @idmap: the mount's idmapping
* @fs_userns: the filesystem's idmapping
* @kuid : kuid to be mapped
*
* Take a @kuid and remap it from @fs_userns into @idmap. Use this
* function when preparing a @kuid to be reported to userspace.
*
* If initial_idmapping() determines that this is not an idmapped mount
* we can simply return @kuid unchanged.
* If initial_idmapping() tells us that the filesystem is not mounted with an
* idmapping we know the value of @kuid won't change when calling
* from_kuid() so we can simply retrieve the value via __kuid_val()
* directly.
*
* Return: @kuid mapped according to @idmap.
* If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is
* returned.
*/
vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
struct user_namespace *fs_userns,
kuid_t kuid)
{
uid_t uid;
if (idmap == &nop_mnt_idmap)
return VFSUIDT_INIT(kuid);
if (idmap == &invalid_mnt_idmap)
return INVALID_VFSUID;
if (initial_idmapping(fs_userns))
uid = __kuid_val(kuid);
else
uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1)
return INVALID_VFSUID;
return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid));
}
EXPORT_SYMBOL_GPL(make_vfsuid);
/**
* make_vfsgid - map a filesystem kgid according to an idmapping
* @idmap: the mount's idmapping
* @fs_userns: the filesystem's idmapping
* @kgid : kgid to be mapped
*
* Take a @kgid and remap it from @fs_userns into @idmap. Use this
* function when preparing a @kgid to be reported to userspace.
*
* If initial_idmapping() determines that this is not an idmapped mount
* we can simply return @kgid unchanged.
* If initial_idmapping() tells us that the filesystem is not mounted with an
* idmapping we know the value of @kgid won't change when calling
* from_kgid() so we can simply retrieve the value via __kgid_val()
* directly.
*
* Return: @kgid mapped according to @idmap.
* If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is
* returned.
*/
vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
struct user_namespace *fs_userns, kgid_t kgid)
{
gid_t gid;
if (idmap == &nop_mnt_idmap)
return VFSGIDT_INIT(kgid);
if (idmap == &invalid_mnt_idmap)
return INVALID_VFSGID;
if (initial_idmapping(fs_userns))
gid = __kgid_val(kgid);
else
gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1)
return INVALID_VFSGID;
return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid));
}
EXPORT_SYMBOL_GPL(make_vfsgid);
/**
* from_vfsuid - map a vfsuid into the filesystem idmapping
* @idmap: the mount's idmapping
* @fs_userns: the filesystem's idmapping
* @vfsuid : vfsuid to be mapped
*
* Map @vfsuid into the filesystem idmapping. This function has to be used in
* order to e.g. write @vfsuid to inode->i_uid.
*
* Return: @vfsuid mapped into the filesystem idmapping
*/
kuid_t from_vfsuid(struct mnt_idmap *idmap,
struct user_namespace *fs_userns, vfsuid_t vfsuid)
{
uid_t uid;
if (idmap == &nop_mnt_idmap)
return AS_KUIDT(vfsuid);
if (idmap == &invalid_mnt_idmap)
return INVALID_UID;
uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid));
if (uid == (uid_t)-1)
return INVALID_UID;
if (initial_idmapping(fs_userns))
return KUIDT_INIT(uid);
return make_kuid(fs_userns, uid);
}
EXPORT_SYMBOL_GPL(from_vfsuid);
/**
* from_vfsgid - map a vfsgid into the filesystem idmapping
* @idmap: the mount's idmapping
* @fs_userns: the filesystem's idmapping
* @vfsgid : vfsgid to be mapped
*
* Map @vfsgid into the filesystem idmapping. This function has to be used in
* order to e.g. write @vfsgid to inode->i_gid.
*
* Return: @vfsgid mapped into the filesystem idmapping
*/
kgid_t from_vfsgid(struct mnt_idmap *idmap,
struct user_namespace *fs_userns, vfsgid_t vfsgid)
{
gid_t gid;
if (idmap == &nop_mnt_idmap)
return AS_KGIDT(vfsgid);
if (idmap == &invalid_mnt_idmap)
return INVALID_GID;
gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid));
if (gid == (gid_t)-1)
return INVALID_GID;
if (initial_idmapping(fs_userns))
return KGIDT_INIT(gid);
return make_kgid(fs_userns, gid);
}
EXPORT_SYMBOL_GPL(from_vfsgid);
#ifdef CONFIG_MULTIUSER
/**
* vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups
* @vfsgid: the mnt gid to match
*
* This function can be used to determine whether @vfsuid matches any of the
* caller's groups.
*
* Return: 1 if vfsuid matches caller's groups, 0 if not.
*/
int vfsgid_in_group_p(vfsgid_t vfsgid)
{
return in_group_p(AS_KGIDT(vfsgid));
}
#else
int vfsgid_in_group_p(vfsgid_t vfsgid)
{
return 1;
}
#endif
EXPORT_SYMBOL_GPL(vfsgid_in_group_p);
static int copy_mnt_idmap(struct uid_gid_map *map_from,
struct uid_gid_map *map_to)
{
struct uid_gid_extent *forward, *reverse;
u32 nr_extents = READ_ONCE(map_from->nr_extents);
/* Pairs with smp_wmb() when writing the idmapping. */
smp_rmb();
/*
* Don't blindly copy @map_to into @map_from if nr_extents is
* smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we
* read @nr_extents someone could have written an idmapping and
* then we might end up with inconsistent data. So just don't do
* anything at all.
*/
if (nr_extents == 0)
return -EINVAL;
/*
* Here we know that nr_extents is greater than zero which means
* a map has been written. Since idmappings can't be changed
* once they have been written we know that we can safely copy
* from @map_to into @map_from.
*/
if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
*map_to = *map_from;
return 0;
}
forward = kmemdup_array(map_from->forward, nr_extents,
sizeof(struct uid_gid_extent),
GFP_KERNEL_ACCOUNT);
if (!forward)
return -ENOMEM;
reverse = kmemdup_array(map_from->reverse, nr_extents,
sizeof(struct uid_gid_extent),
GFP_KERNEL_ACCOUNT);
if (!reverse) {
kfree(forward);
return -ENOMEM;
}
/*
* The idmapping isn't exposed anywhere so we don't need to care
* about ordering between extent pointers and @nr_extents
* initialization.
*/
map_to->forward = forward;
map_to->reverse = reverse;
map_to->nr_extents = nr_extents;
return 0;
}
static void free_mnt_idmap(struct mnt_idmap *idmap)
{
if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(idmap->uid_map.forward);
kfree(idmap->uid_map.reverse);
}
if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(idmap->gid_map.forward);
kfree(idmap->gid_map.reverse);
}
kfree(idmap);
}
struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns)
{
struct mnt_idmap *idmap;
int ret;
idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT);
if (!idmap)
return ERR_PTR(-ENOMEM);
refcount_set(&idmap->count, 1);
ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map);
if (!ret)
ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map);
if (ret) {
free_mnt_idmap(idmap);
idmap = ERR_PTR(ret);
}
return idmap;
}
/**
* mnt_idmap_get - get a reference to an idmapping
* @idmap: the idmap to bump the reference on
*
* If @idmap is not the @nop_mnt_idmap bump the reference count.
*
* Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed.
*/
struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap)
{
if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap)
refcount_inc(&idmap->count);
return idmap;
}
EXPORT_SYMBOL_GPL(mnt_idmap_get);
/**
* mnt_idmap_put - put a reference to an idmapping
* @idmap: the idmap to put the reference on
*
* If this is a non-initial idmapping, put the reference count when a mount is
* released and free it if we're the last user.
*/
void mnt_idmap_put(struct mnt_idmap *idmap)
{
if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap &&
refcount_dec_and_test(&idmap->count))
free_mnt_idmap(idmap);
}
EXPORT_SYMBOL_GPL(mnt_idmap_put);
int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map)
{
struct uid_gid_map *map, *map_up;
u32 idx, nr_mappings;
if (!is_valid_mnt_idmap(idmap))
return 0;
/*
* Idmappings are shown relative to the caller's idmapping.
* This is both the most intuitive and most useful solution.
*/
if (uid_map) {
map = &idmap->uid_map;
map_up = ¤t_user_ns()->uid_map;
} else {
map = &idmap->gid_map;
map_up = ¤t_user_ns()->gid_map;
}
for (idx = 0, nr_mappings = 0; idx < map->nr_extents; idx++) {
uid_t lower;
struct uid_gid_extent *extent;
if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
extent = &map->extent[idx];
else
extent = &map->forward[idx];
/*
* Verify that the whole range of the mapping can be
* resolved in the caller's idmapping. If it cannot be
* resolved skip the mapping.
*/
lower = map_id_range_up(map_up, extent->lower_first, extent->count);
if (lower == (uid_t) -1)
continue;
seq_printf(seq, "%u %u %u", extent->first, lower, extent->count);
seq->count++; /* mappings are separated by \0 */
if (seq_has_overflowed(seq))
return -EAGAIN;
nr_mappings++;
}
return nr_mappings;
}
// SPDX-License-Identifier: GPL-2.0-or-later
/* audit.c -- Auditing support
* Gateway between the kernel (e.g., selinux) and the user-space audit daemon.
* System-call specific features have moved to auditsc.c
*
* Copyright 2003-2007 Red Hat Inc., Durham, North Carolina.
* All Rights Reserved.
*
* Written by Rickard E. (Rik) Faith <faith@redhat.com>
*
* Goals: 1) Integrate fully with Security Modules.
* 2) Minimal run-time overhead:
* a) Minimal when syscall auditing is disabled (audit_enable=0).
* b) Small when syscall auditing is enabled and no audit record
* is generated (defer as much work as possible to record
* generation time):
* i) context is allocated,
* ii) names from getname are stored without a copy, and
* iii) inode information stored from path_lookup.
* 3) Ability to disable syscall auditing at boot time (audit=0).
* 4) Usable by other parts of the kernel (if audit_log* is called,
* then a syscall record will be generated automatically for the
* current syscall).
* 5) Netlink interface to user-space.
* 6) Support low-overhead kernel-based filtering to minimize the
* information that must be passed to user-space.
*
* Audit userspace, documentation, tests, and bug/issue trackers:
* https://github.com/linux-audit
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/file.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/kthread.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/pid.h>
#include <linux/audit.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <linux/skbuff.h>
#include <linux/security.h>
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <net/netns/generic.h>
#include "audit.h"
/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED.
* (Initialization happens after skb_init is called.) */
#define AUDIT_DISABLED -1
#define AUDIT_UNINITIALIZED 0
#define AUDIT_INITIALIZED 1
static int audit_initialized = AUDIT_UNINITIALIZED;
u32 audit_enabled = AUDIT_OFF;
bool audit_ever_enabled = !!AUDIT_OFF;
EXPORT_SYMBOL_GPL(audit_enabled);
/* Default state when kernel boots without any parameters. */
static u32 audit_default = AUDIT_OFF;
/* If auditing cannot proceed, audit_failure selects what happens. */
static u32 audit_failure = AUDIT_FAIL_PRINTK;
/* private audit network namespace index */
static unsigned int audit_net_id;
/**
* struct audit_net - audit private network namespace data
* @sk: communication socket
*/
struct audit_net {
struct sock *sk;
};
/**
* struct auditd_connection - kernel/auditd connection state
* @pid: auditd PID
* @portid: netlink portid
* @net: the associated network namespace
* @rcu: RCU head
*
* Description:
* This struct is RCU protected; you must either hold the RCU lock for reading
* or the associated spinlock for writing.
*/
struct auditd_connection {
struct pid *pid;
u32 portid;
struct net *net;
struct rcu_head rcu;
};
static struct auditd_connection __rcu *auditd_conn;
static DEFINE_SPINLOCK(auditd_conn_lock);
/* If audit_rate_limit is non-zero, limit the rate of sending audit records
* to that number per second. This prevents DoS attacks, but results in
* audit records being dropped. */
static u32 audit_rate_limit;
/* Number of outstanding audit_buffers allowed.
* When set to zero, this means unlimited. */
static u32 audit_backlog_limit = 64;
#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
/* The identity of the user shutting down the audit system. */
static kuid_t audit_sig_uid = INVALID_UID;
static pid_t audit_sig_pid = -1;
static struct lsm_prop audit_sig_lsm;
/* Records can be lost in several ways:
0) [suppressed in audit_alloc]
1) out of memory in audit_log_start [kmalloc of struct audit_buffer]
2) out of memory in audit_log_move [alloc_skb]
3) suppressed due to audit_rate_limit
4) suppressed due to audit_backlog_limit
*/
static atomic_t audit_lost = ATOMIC_INIT(0);
/* Monotonically increasing sum of time the kernel has spent
* waiting while the backlog limit is exceeded.
*/
static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0);
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
static struct kmem_cache *audit_buffer_cache;
/* queue msgs to send via kauditd_task */
static struct sk_buff_head audit_queue;
/* queue msgs due to temporary unicast send problems */
static struct sk_buff_head audit_retry_queue;
/* queue msgs waiting for new auditd connection */
static struct sk_buff_head audit_hold_queue;
/* queue servicing thread */
static struct task_struct *kauditd_task;
static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
/* waitqueue for callers who are blocked on the audit backlog */
static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
.mask = -1,
.features = 0,
.lock = 0,};
static char *audit_feature_names[2] = {
"only_unset_loginuid",
"loginuid_immutable",
};
/**
* struct audit_ctl_mutex - serialize requests from userspace
* @lock: the mutex used for locking
* @owner: the task which owns the lock
*
* Description:
* This is the lock struct used to ensure we only process userspace requests
* in an orderly fashion. We can't simply use a mutex/lock here because we
* need to track lock ownership so we don't end up blocking the lock owner in
* audit_log_start() or similar.
*/
static struct audit_ctl_mutex {
struct mutex lock;
void *owner;
} audit_cmd_mutex;
/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
* audit records. Since printk uses a 1024 byte buffer, this buffer
* should be at least that large. */
#define AUDIT_BUFSIZ 1024
/* The audit_buffer is used when formatting an audit record. The caller
* locks briefly to get the record off the freelist or to allocate the
* buffer, and locks briefly to send the buffer to the netlink layer or
* to place it on a transmit queue. Multiple audit_buffers can be in
* use simultaneously. */
struct audit_buffer {
struct sk_buff *skb; /* formatted skb ready to send */
struct audit_context *ctx; /* NULL or associated context */
gfp_t gfp_mask;
};
struct audit_reply {
__u32 portid;
struct net *net;
struct sk_buff *skb;
};
/**
* auditd_test_task - Check to see if a given task is an audit daemon
* @task: the task to check
*
* Description:
* Return 1 if the task is a registered audit daemon, 0 otherwise.
*/
int auditd_test_task(struct task_struct *task)
{
int rc;
struct auditd_connection *ac;
rcu_read_lock(); ac = rcu_dereference(auditd_conn); rc = (ac && ac->pid == task_tgid(task) ? 1 : 0); rcu_read_unlock();
return rc;
}
/**
* audit_ctl_lock - Take the audit control lock
*/
void audit_ctl_lock(void)
{
mutex_lock(&audit_cmd_mutex.lock);
audit_cmd_mutex.owner = current;
}
/**
* audit_ctl_unlock - Drop the audit control lock
*/
void audit_ctl_unlock(void)
{
audit_cmd_mutex.owner = NULL;
mutex_unlock(&audit_cmd_mutex.lock);
}
/**
* audit_ctl_owner_current - Test to see if the current task owns the lock
*
* Description:
* Return true if the current task owns the audit control lock, false if it
* doesn't own the lock.
*/
static bool audit_ctl_owner_current(void)
{
return (current == audit_cmd_mutex.owner);
}
/**
* auditd_pid_vnr - Return the auditd PID relative to the namespace
*
* Description:
* Returns the PID in relation to the namespace, 0 on failure.
*/
static pid_t auditd_pid_vnr(void)
{
pid_t pid;
const struct auditd_connection *ac;
rcu_read_lock();
ac = rcu_dereference(auditd_conn);
if (!ac || !ac->pid)
pid = 0;
else
pid = pid_vnr(ac->pid);
rcu_read_unlock();
return pid;
}
/**
* audit_get_sk - Return the audit socket for the given network namespace
* @net: the destination network namespace
*
* Description:
* Returns the sock pointer if valid, NULL otherwise. The caller must ensure
* that a reference is held for the network namespace while the sock is in use.
*/
static struct sock *audit_get_sk(const struct net *net)
{
struct audit_net *aunet;
if (!net)
return NULL;
aunet = net_generic(net, audit_net_id);
return aunet->sk;
}
void audit_panic(const char *message)
{
switch (audit_failure) {
case AUDIT_FAIL_SILENT:
break;
case AUDIT_FAIL_PRINTK:
if (printk_ratelimit())
pr_err("%s\n", message);
break;
case AUDIT_FAIL_PANIC:
panic("audit: %s\n", message);
break;
}
}
static inline int audit_rate_check(void)
{
static unsigned long last_check = 0;
static int messages = 0;
static DEFINE_SPINLOCK(lock);
unsigned long flags;
unsigned long now;
int retval = 0;
if (!audit_rate_limit)
return 1;
spin_lock_irqsave(&lock, flags);
if (++messages < audit_rate_limit) {
retval = 1;
} else {
now = jiffies;
if (time_after(now, last_check + HZ)) {
last_check = now;
messages = 0;
retval = 1;
}
}
spin_unlock_irqrestore(&lock, flags);
return retval;
}
/**
* audit_log_lost - conditionally log lost audit message event
* @message: the message stating reason for lost audit message
*
* Emit at least 1 message per second, even if audit_rate_check is
* throttling.
* Always increment the lost messages counter.
*/
void audit_log_lost(const char *message)
{
static unsigned long last_msg = 0;
static DEFINE_SPINLOCK(lock);
unsigned long flags;
unsigned long now;
int print;
atomic_inc(&audit_lost);
print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit);
if (!print) {
spin_lock_irqsave(&lock, flags);
now = jiffies;
if (time_after(now, last_msg + HZ)) {
print = 1;
last_msg = now;
}
spin_unlock_irqrestore(&lock, flags);
}
if (print) {
if (printk_ratelimit())
pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n",
atomic_read(&audit_lost),
audit_rate_limit,
audit_backlog_limit);
audit_panic(message);
}
}
static int audit_log_config_change(char *function_name, u32 new, u32 old,
int allow_changes)
{
struct audit_buffer *ab;
int rc = 0;
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return rc;
audit_log_format(ab, "op=set %s=%u old=%u ", function_name, new, old);
audit_log_session_info(ab);
rc = audit_log_task_context(ab);
if (rc)
allow_changes = 0; /* Something weird, deny request */
audit_log_format(ab, " res=%d", allow_changes);
audit_log_end(ab);
return rc;
}
static int audit_do_config_change(char *function_name, u32 *to_change, u32 new)
{
int allow_changes, rc = 0;
u32 old = *to_change;
/* check if we are locked */
if (audit_enabled == AUDIT_LOCKED)
allow_changes = 0;
else
allow_changes = 1;
if (audit_enabled != AUDIT_OFF) {
rc = audit_log_config_change(function_name, new, old, allow_changes);
if (rc)
allow_changes = 0;
}
/* If we are allowed, make the change */
if (allow_changes == 1)
*to_change = new;
/* Not allowed, update reason */
else if (rc == 0)
rc = -EPERM;
return rc;
}
static int audit_set_rate_limit(u32 limit)
{
return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit);
}
static int audit_set_backlog_limit(u32 limit)
{
return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit);
}
static int audit_set_backlog_wait_time(u32 timeout)
{
return audit_do_config_change("audit_backlog_wait_time",
&audit_backlog_wait_time, timeout);
}
static int audit_set_enabled(u32 state)
{
int rc;
if (state > AUDIT_LOCKED)
return -EINVAL;
rc = audit_do_config_change("audit_enabled", &audit_enabled, state);
if (!rc)
audit_ever_enabled |= !!state;
return rc;
}
static int audit_set_failure(u32 state)
{
if (state != AUDIT_FAIL_SILENT
&& state != AUDIT_FAIL_PRINTK
&& state != AUDIT_FAIL_PANIC)
return -EINVAL;
return audit_do_config_change("audit_failure", &audit_failure, state);
}
/**
* auditd_conn_free - RCU helper to release an auditd connection struct
* @rcu: RCU head
*
* Description:
* Drop any references inside the auditd connection tracking struct and free
* the memory.
*/
static void auditd_conn_free(struct rcu_head *rcu)
{
struct auditd_connection *ac;
ac = container_of(rcu, struct auditd_connection, rcu);
put_pid(ac->pid);
put_net(ac->net);
kfree(ac);
}
/**
* auditd_set - Set/Reset the auditd connection state
* @pid: auditd PID
* @portid: auditd netlink portid
* @net: auditd network namespace pointer
* @skb: the netlink command from the audit daemon
* @ack: netlink ack flag, cleared if ack'd here
*
* Description:
* This function will obtain and drop network namespace references as
* necessary. Returns zero on success, negative values on failure.
*/
static int auditd_set(struct pid *pid, u32 portid, struct net *net,
struct sk_buff *skb, bool *ack)
{
unsigned long flags;
struct auditd_connection *ac_old, *ac_new;
struct nlmsghdr *nlh;
if (!pid || !net)
return -EINVAL;
ac_new = kzalloc(sizeof(*ac_new), GFP_KERNEL);
if (!ac_new)
return -ENOMEM;
ac_new->pid = get_pid(pid);
ac_new->portid = portid;
ac_new->net = get_net(net);
/* send the ack now to avoid a race with the queue backlog */
if (*ack) {
nlh = nlmsg_hdr(skb);
netlink_ack(skb, nlh, 0, NULL);
*ack = false;
}
spin_lock_irqsave(&auditd_conn_lock, flags);
ac_old = rcu_dereference_protected(auditd_conn,
lockdep_is_held(&auditd_conn_lock));
rcu_assign_pointer(auditd_conn, ac_new);
spin_unlock_irqrestore(&auditd_conn_lock, flags);
if (ac_old)
call_rcu(&ac_old->rcu, auditd_conn_free);
return 0;
}
/**
* kauditd_printk_skb - Print the audit record to the ring buffer
* @skb: audit record
*
* Whatever the reason, this packet may not make it to the auditd connection
* so write it via printk so the information isn't completely lost.
*/
static void kauditd_printk_skb(struct sk_buff *skb)
{
struct nlmsghdr *nlh = nlmsg_hdr(skb);
char *data = nlmsg_data(nlh);
if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit())
pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
}
/**
* kauditd_rehold_skb - Handle a audit record send failure in the hold queue
* @skb: audit record
* @error: error code (unused)
*
* Description:
* This should only be used by the kauditd_thread when it fails to flush the
* hold queue.
*/
static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error)
{
/* put the record back in the queue */
skb_queue_tail(&audit_hold_queue, skb);
}
/**
* kauditd_hold_skb - Queue an audit record, waiting for auditd
* @skb: audit record
* @error: error code
*
* Description:
* Queue the audit record, waiting for an instance of auditd. When this
* function is called we haven't given up yet on sending the record, but things
* are not looking good. The first thing we want to do is try to write the
* record via printk and then see if we want to try and hold on to the record
* and queue it, if we have room. If we want to hold on to the record, but we
* don't have room, record a record lost message.
*/
static void kauditd_hold_skb(struct sk_buff *skb, int error)
{
/* at this point it is uncertain if we will ever send this to auditd so
* try to send the message via printk before we go any further */
kauditd_printk_skb(skb);
/* can we just silently drop the message? */
if (!audit_default)
goto drop;
/* the hold queue is only for when the daemon goes away completely,
* not -EAGAIN failures; if we are in a -EAGAIN state requeue the
* record on the retry queue unless it's full, in which case drop it
*/
if (error == -EAGAIN) {
if (!audit_backlog_limit ||
skb_queue_len(&audit_retry_queue) < audit_backlog_limit) {
skb_queue_tail(&audit_retry_queue, skb);
return;
}
audit_log_lost("kauditd retry queue overflow");
goto drop;
}
/* if we have room in the hold queue, queue the message */
if (!audit_backlog_limit ||
skb_queue_len(&audit_hold_queue) < audit_backlog_limit) {
skb_queue_tail(&audit_hold_queue, skb);
return;
}
/* we have no other options - drop the message */
audit_log_lost("kauditd hold queue overflow");
drop:
kfree_skb(skb);
}
/**
* kauditd_retry_skb - Queue an audit record, attempt to send again to auditd
* @skb: audit record
* @error: error code (unused)
*
* Description:
* Not as serious as kauditd_hold_skb() as we still have a connected auditd,
* but for some reason we are having problems sending it audit records so
* queue the given record and attempt to resend.
*/
static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error)
{
if (!audit_backlog_limit ||
skb_queue_len(&audit_retry_queue) < audit_backlog_limit) {
skb_queue_tail(&audit_retry_queue, skb);
return;
}
/* we have to drop the record, send it via printk as a last effort */
kauditd_printk_skb(skb);
audit_log_lost("kauditd retry queue overflow");
kfree_skb(skb);
}
/**
* auditd_reset - Disconnect the auditd connection
* @ac: auditd connection state
*
* Description:
* Break the auditd/kauditd connection and move all the queued records into the
* hold queue in case auditd reconnects. It is important to note that the @ac
* pointer should never be dereferenced inside this function as it may be NULL
* or invalid, you can only compare the memory address! If @ac is NULL then
* the connection will always be reset.
*/
static void auditd_reset(const struct auditd_connection *ac)
{
unsigned long flags;
struct sk_buff *skb;
struct auditd_connection *ac_old;
/* if it isn't already broken, break the connection */
spin_lock_irqsave(&auditd_conn_lock, flags);
ac_old = rcu_dereference_protected(auditd_conn,
lockdep_is_held(&auditd_conn_lock));
if (ac && ac != ac_old) {
/* someone already registered a new auditd connection */
spin_unlock_irqrestore(&auditd_conn_lock, flags);
return;
}
rcu_assign_pointer(auditd_conn, NULL);
spin_unlock_irqrestore(&auditd_conn_lock, flags);
if (ac_old)
call_rcu(&ac_old->rcu, auditd_conn_free);
/* flush the retry queue to the hold queue, but don't touch the main
* queue since we need to process that normally for multicast */
while ((skb = skb_dequeue(&audit_retry_queue)))
kauditd_hold_skb(skb, -ECONNREFUSED);
}
/**
* auditd_send_unicast_skb - Send a record via unicast to auditd
* @skb: audit record
*
* Description:
* Send a skb to the audit daemon, returns positive/zero values on success and
* negative values on failure; in all cases the skb will be consumed by this
* function. If the send results in -ECONNREFUSED the connection with auditd
* will be reset. This function may sleep so callers should not hold any locks
* where this would cause a problem.
*/
static int auditd_send_unicast_skb(struct sk_buff *skb)
{
int rc;
u32 portid;
struct net *net;
struct sock *sk;
struct auditd_connection *ac;
/* NOTE: we can't call netlink_unicast while in the RCU section so
* take a reference to the network namespace and grab local
* copies of the namespace, the sock, and the portid; the
* namespace and sock aren't going to go away while we hold a
* reference and if the portid does become invalid after the RCU
* section netlink_unicast() should safely return an error */
rcu_read_lock();
ac = rcu_dereference(auditd_conn);
if (!ac) {
rcu_read_unlock();
kfree_skb(skb);
rc = -ECONNREFUSED;
goto err;
}
net = get_net(ac->net);
sk = audit_get_sk(net);
portid = ac->portid;
rcu_read_unlock();
rc = netlink_unicast(sk, skb, portid, 0);
put_net(net);
if (rc < 0)
goto err;
return rc;
err:
if (ac && rc == -ECONNREFUSED)
auditd_reset(ac);
return rc;
}
/**
* kauditd_send_queue - Helper for kauditd_thread to flush skb queues
* @sk: the sending sock
* @portid: the netlink destination
* @queue: the skb queue to process
* @retry_limit: limit on number of netlink unicast failures
* @skb_hook: per-skb hook for additional processing
* @err_hook: hook called if the skb fails the netlink unicast send
*
* Description:
* Run through the given queue and attempt to send the audit records to auditd,
* returns zero on success, negative values on failure. It is up to the caller
* to ensure that the @sk is valid for the duration of this function.
*
*/
static int kauditd_send_queue(struct sock *sk, u32 portid,
struct sk_buff_head *queue,
unsigned int retry_limit,
void (*skb_hook)(struct sk_buff *skb),
void (*err_hook)(struct sk_buff *skb, int error))
{
int rc = 0;
struct sk_buff *skb = NULL;
struct sk_buff *skb_tail;
unsigned int failed = 0;
/* NOTE: kauditd_thread takes care of all our locking, we just use
* the netlink info passed to us (e.g. sk and portid) */
skb_tail = skb_peek_tail(queue);
while ((skb != skb_tail) && (skb = skb_dequeue(queue))) {
/* call the skb_hook for each skb we touch */
if (skb_hook)
(*skb_hook)(skb);
/* can we send to anyone via unicast? */
if (!sk) {
if (err_hook)
(*err_hook)(skb, -ECONNREFUSED);
continue;
}
retry:
/* grab an extra skb reference in case of error */
skb_get(skb);
rc = netlink_unicast(sk, skb, portid, 0);
if (rc < 0) {
/* send failed - try a few times unless fatal error */
if (++failed >= retry_limit ||
rc == -ECONNREFUSED || rc == -EPERM) {
sk = NULL;
if (err_hook)
(*err_hook)(skb, rc);
if (rc == -EAGAIN)
rc = 0;
/* continue to drain the queue */
continue;
} else
goto retry;
} else {
/* skb sent - drop the extra reference and continue */
consume_skb(skb);
failed = 0;
}
}
return (rc >= 0 ? 0 : rc);
}
/*
* kauditd_send_multicast_skb - Send a record to any multicast listeners
* @skb: audit record
*
* Description:
* Write a multicast message to anyone listening in the initial network
* namespace. This function doesn't consume an skb as might be expected since
* it has to copy it anyways.
*/
static void kauditd_send_multicast_skb(struct sk_buff *skb)
{
struct sk_buff *copy;
struct sock *sock = audit_get_sk(&init_net);
struct nlmsghdr *nlh;
/* NOTE: we are not taking an additional reference for init_net since
* we don't have to worry about it going away */
if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG))
return;
/*
* The seemingly wasteful skb_copy() rather than bumping the refcount
* using skb_get() is necessary because non-standard mods are made to
* the skb by the original kaudit unicast socket send routine. The
* existing auditd daemon assumes this breakage. Fixing this would
* require co-ordinating a change in the established protocol between
* the kaudit kernel subsystem and the auditd userspace code. There is
* no reason for new multicast clients to continue with this
* non-compliance.
*/
copy = skb_copy(skb, GFP_KERNEL);
if (!copy)
return;
nlh = nlmsg_hdr(copy);
nlh->nlmsg_len = skb->len;
nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL);
}
/**
* kauditd_thread - Worker thread to send audit records to userspace
* @dummy: unused
*/
static int kauditd_thread(void *dummy)
{
int rc;
u32 portid = 0;
struct net *net = NULL;
struct sock *sk = NULL;
struct auditd_connection *ac;
#define UNICAST_RETRIES 5
set_freezable();
while (!kthread_should_stop()) {
/* NOTE: see the lock comments in auditd_send_unicast_skb() */
rcu_read_lock();
ac = rcu_dereference(auditd_conn);
if (!ac) {
rcu_read_unlock();
goto main_queue;
}
net = get_net(ac->net);
sk = audit_get_sk(net);
portid = ac->portid;
rcu_read_unlock();
/* attempt to flush the hold queue */
rc = kauditd_send_queue(sk, portid,
&audit_hold_queue, UNICAST_RETRIES,
NULL, kauditd_rehold_skb);
if (rc < 0) {
sk = NULL;
auditd_reset(ac);
goto main_queue;
}
/* attempt to flush the retry queue */
rc = kauditd_send_queue(sk, portid,
&audit_retry_queue, UNICAST_RETRIES,
NULL, kauditd_hold_skb);
if (rc < 0) {
sk = NULL;
auditd_reset(ac);
goto main_queue;
}
main_queue:
/* process the main queue - do the multicast send and attempt
* unicast, dump failed record sends to the retry queue; if
* sk == NULL due to previous failures we will just do the
* multicast send and move the record to the hold queue */
rc = kauditd_send_queue(sk, portid, &audit_queue, 1,
kauditd_send_multicast_skb,
(sk ?
kauditd_retry_skb : kauditd_hold_skb));
if (ac && rc < 0)
auditd_reset(ac);
sk = NULL;
/* drop our netns reference, no auditd sends past this line */
if (net) {
put_net(net);
net = NULL;
}
/* we have processed all the queues so wake everyone */
wake_up(&audit_backlog_wait);
/* NOTE: we want to wake up if there is anything on the queue,
* regardless of if an auditd is connected, as we need to
* do the multicast send and rotate records from the
* main queue to the retry/hold queues */
wait_event_freezable(kauditd_wait,
(skb_queue_len(&audit_queue) ? 1 : 0));
}
return 0;
}
int audit_send_list_thread(void *_dest)
{
struct audit_netlink_list *dest = _dest;
struct sk_buff *skb;
struct sock *sk = audit_get_sk(dest->net);
/* wait for parent to finish and send an ACK */
audit_ctl_lock();
audit_ctl_unlock();
while ((skb = __skb_dequeue(&dest->q)) != NULL)
netlink_unicast(sk, skb, dest->portid, 0);
put_net(dest->net);
kfree(dest);
return 0;
}
struct sk_buff *audit_make_reply(int seq, int type, int done,
int multi, const void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
void *data;
int flags = multi ? NLM_F_MULTI : 0;
int t = done ? NLMSG_DONE : type;
skb = nlmsg_new(size, GFP_KERNEL);
if (!skb)
return NULL;
nlh = nlmsg_put(skb, 0, seq, t, size, flags);
if (!nlh)
goto out_kfree_skb;
data = nlmsg_data(nlh);
memcpy(data, payload, size);
return skb;
out_kfree_skb:
kfree_skb(skb);
return NULL;
}
static void audit_free_reply(struct audit_reply *reply)
{
if (!reply)
return;
kfree_skb(reply->skb);
if (reply->net)
put_net(reply->net);
kfree(reply);
}
static int audit_send_reply_thread(void *arg)
{
struct audit_reply *reply = (struct audit_reply *)arg;
audit_ctl_lock();
audit_ctl_unlock();
/* Ignore failure. It'll only happen if the sender goes away,
because our timeout is set to infinite. */
netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0);
reply->skb = NULL;
audit_free_reply(reply);
return 0;
}
/**
* audit_send_reply - send an audit reply message via netlink
* @request_skb: skb of request we are replying to (used to target the reply)
* @seq: sequence number
* @type: audit message type
* @done: done (last) flag
* @multi: multi-part message flag
* @payload: payload data
* @size: payload size
*
* Allocates a skb, builds the netlink message, and sends it to the port id.
*/
static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
int multi, const void *payload, int size)
{
struct task_struct *tsk;
struct audit_reply *reply;
reply = kzalloc(sizeof(*reply), GFP_KERNEL);
if (!reply)
return;
reply->skb = audit_make_reply(seq, type, done, multi, payload, size);
if (!reply->skb)
goto err;
reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
reply->portid = NETLINK_CB(request_skb).portid;
tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
if (IS_ERR(tsk))
goto err;
return;
err:
audit_free_reply(reply);
}
/*
* Check for appropriate CAP_AUDIT_ capabilities on incoming audit
* control messages.
*/
static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
{
int err = 0;
/* Only support initial user namespace for now. */
/*
* We return ECONNREFUSED because it tricks userspace into thinking
* that audit was not configured into the kernel. Lots of users
* configure their PAM stack (because that's what the distro does)
* to reject login if unable to send messages to audit. If we return
* ECONNREFUSED the PAM stack thinks the kernel does not have audit
* configured in and will let login proceed. If we return EPERM
* userspace will reject all logins. This should be removed when we
* support non init namespaces!!
*/
if (current_user_ns() != &init_user_ns)
return -ECONNREFUSED;
switch (msg_type) {
case AUDIT_LIST:
case AUDIT_ADD:
case AUDIT_DEL:
return -EOPNOTSUPP;
case AUDIT_GET:
case AUDIT_SET:
case AUDIT_GET_FEATURE:
case AUDIT_SET_FEATURE:
case AUDIT_LIST_RULES:
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
case AUDIT_SIGNAL_INFO:
case AUDIT_TTY_GET:
case AUDIT_TTY_SET:
case AUDIT_TRIM:
case AUDIT_MAKE_EQUIV:
/* Only support auditd and auditctl in initial pid namespace
* for now. */
if (task_active_pid_ns(current) != &init_pid_ns)
return -EPERM;
if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
err = -EPERM;
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
if (!netlink_capable(skb, CAP_AUDIT_WRITE))
err = -EPERM;
break;
default: /* bad msg */
err = -EINVAL;
}
return err;
}
static void audit_log_common_recv_msg(struct audit_context *context,
struct audit_buffer **ab, u16 msg_type)
{
uid_t uid = from_kuid(&init_user_ns, current_uid());
pid_t pid = task_tgid_nr(current);
if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
*ab = NULL;
return;
}
*ab = audit_log_start(context, GFP_KERNEL, msg_type);
if (unlikely(!*ab))
return;
audit_log_format(*ab, "pid=%d uid=%u ", pid, uid);
audit_log_session_info(*ab);
audit_log_task_context(*ab);
}
static inline void audit_log_user_recv_msg(struct audit_buffer **ab,
u16 msg_type)
{
audit_log_common_recv_msg(NULL, ab, msg_type);
}
static int is_audit_feature_set(int i)
{
return af.features & AUDIT_FEATURE_TO_MASK(i);
}
static int audit_get_feature(struct sk_buff *skb)
{
u32 seq;
seq = nlmsg_hdr(skb)->nlmsg_seq;
audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af));
return 0;
}
static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature,
u32 old_lock, u32 new_lock, int res)
{
struct audit_buffer *ab;
if (audit_enabled == AUDIT_OFF)
return;
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE);
if (!ab)
return;
audit_log_task_info(ab);
audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
audit_feature_names[which], !!old_feature, !!new_feature,
!!old_lock, !!new_lock, res);
audit_log_end(ab);
}
static int audit_set_feature(struct audit_features *uaf)
{
int i;
BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names));
/* if there is ever a version 2 we should handle that here */
for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
u32 feature = AUDIT_FEATURE_TO_MASK(i);
u32 old_feature, new_feature, old_lock, new_lock;
/* if we are not changing this feature, move along */
if (!(feature & uaf->mask))
continue;
old_feature = af.features & feature;
new_feature = uaf->features & feature;
new_lock = (uaf->lock | af.lock) & feature;
old_lock = af.lock & feature;
/* are we changing a locked feature? */
if (old_lock && (new_feature != old_feature)) {
audit_log_feature_change(i, old_feature, new_feature,
old_lock, new_lock, 0);
return -EPERM;
}
}
/* nothing invalid, do the changes */
for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
u32 feature = AUDIT_FEATURE_TO_MASK(i);
u32 old_feature, new_feature, old_lock, new_lock;
/* if we are not changing this feature, move along */
if (!(feature & uaf->mask))
continue;
old_feature = af.features & feature;
new_feature = uaf->features & feature;
old_lock = af.lock & feature;
new_lock = (uaf->lock | af.lock) & feature;
if (new_feature != old_feature)
audit_log_feature_change(i, old_feature, new_feature,
old_lock, new_lock, 1);
if (new_feature)
af.features |= feature;
else
af.features &= ~feature;
af.lock |= new_lock;
}
return 0;
}
static int audit_replace(struct pid *pid)
{
pid_t pvnr;
struct sk_buff *skb;
pvnr = pid_vnr(pid);
skb = audit_make_reply(0, AUDIT_REPLACE, 0, 0, &pvnr, sizeof(pvnr));
if (!skb)
return -ENOMEM;
return auditd_send_unicast_skb(skb);
}
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
bool *ack)
{
u32 seq;
void *data;
int data_len;
int err;
struct audit_buffer *ab;
u16 msg_type = nlh->nlmsg_type;
struct audit_sig_info *sig_data;
struct lsm_context lsmctx = { NULL, 0, 0 };
err = audit_netlink_ok(skb, msg_type);
if (err)
return err;
seq = nlh->nlmsg_seq;
data = nlmsg_data(nlh);
data_len = nlmsg_len(nlh);
switch (msg_type) {
case AUDIT_GET: {
struct audit_status s;
memset(&s, 0, sizeof(s));
s.enabled = audit_enabled;
s.failure = audit_failure;
/* NOTE: use pid_vnr() so the PID is relative to the current
* namespace */
s.pid = auditd_pid_vnr();
s.rate_limit = audit_rate_limit;
s.backlog_limit = audit_backlog_limit;
s.lost = atomic_read(&audit_lost);
s.backlog = skb_queue_len(&audit_queue);
s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL;
s.backlog_wait_time = audit_backlog_wait_time;
s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual);
audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_SET: {
struct audit_status s;
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
if (s.mask & AUDIT_STATUS_ENABLED) {
err = audit_set_enabled(s.enabled);
if (err < 0)
return err;
}
if (s.mask & AUDIT_STATUS_FAILURE) {
err = audit_set_failure(s.failure);
if (err < 0)
return err;
}
if (s.mask & AUDIT_STATUS_PID) {
/* NOTE: we are using the vnr PID functions below
* because the s.pid value is relative to the
* namespace of the caller; at present this
* doesn't matter much since you can really only
* run auditd from the initial pid namespace, but
* something to keep in mind if this changes */
pid_t new_pid = s.pid;
pid_t auditd_pid;
struct pid *req_pid = task_tgid(current);
/* Sanity check - PID values must match. Setting
* pid to 0 is how auditd ends auditing. */
if (new_pid && (new_pid != pid_vnr(req_pid)))
return -EINVAL;
/* test the auditd connection */
audit_replace(req_pid);
auditd_pid = auditd_pid_vnr();
if (auditd_pid) {
/* replacing a healthy auditd is not allowed */
if (new_pid) {
audit_log_config_change("audit_pid",
new_pid, auditd_pid, 0);
return -EEXIST;
}
/* only current auditd can unregister itself */
if (pid_vnr(req_pid) != auditd_pid) {
audit_log_config_change("audit_pid",
new_pid, auditd_pid, 0);
return -EACCES;
}
}
if (new_pid) {
/* register a new auditd connection */
err = auditd_set(req_pid,
NETLINK_CB(skb).portid,
sock_net(NETLINK_CB(skb).sk),
skb, ack);
if (audit_enabled != AUDIT_OFF)
audit_log_config_change("audit_pid",
new_pid,
auditd_pid,
err ? 0 : 1);
if (err)
return err;
/* try to process any backlog */
wake_up_interruptible(&kauditd_wait);
} else {
if (audit_enabled != AUDIT_OFF)
audit_log_config_change("audit_pid",
new_pid,
auditd_pid, 1);
/* unregister the auditd connection */
auditd_reset(NULL);
}
}
if (s.mask & AUDIT_STATUS_RATE_LIMIT) {
err = audit_set_rate_limit(s.rate_limit);
if (err < 0)
return err;
}
if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) {
err = audit_set_backlog_limit(s.backlog_limit);
if (err < 0)
return err;
}
if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) {
if (sizeof(s) > (size_t)nlh->nlmsg_len)
return -EINVAL;
if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
return -EINVAL;
err = audit_set_backlog_wait_time(s.backlog_wait_time);
if (err < 0)
return err;
}
if (s.mask == AUDIT_STATUS_LOST) {
u32 lost = atomic_xchg(&audit_lost, 0);
audit_log_config_change("lost", 0, lost, 1);
return lost;
}
if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) {
u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0);
audit_log_config_change("backlog_wait_time_actual", 0, actual, 1);
return actual;
}
break;
}
case AUDIT_GET_FEATURE:
err = audit_get_feature(skb);
if (err)
return err;
break;
case AUDIT_SET_FEATURE:
if (data_len < sizeof(struct audit_features))
return -EINVAL;
err = audit_set_feature(data);
if (err)
return err;
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
if (!audit_enabled && msg_type != AUDIT_USER_AVC)
return 0;
/* exit early if there isn't at least one character to print */
if (data_len < 2)
return -EINVAL;
err = audit_filter(msg_type, AUDIT_FILTER_USER);
if (err == 1) { /* match or error */
char *str = data;
err = 0;
if (msg_type == AUDIT_USER_TTY) {
err = tty_audit_push();
if (err)
break;
}
audit_log_user_recv_msg(&ab, msg_type);
if (msg_type != AUDIT_USER_TTY) {
/* ensure NULL termination */
str[data_len - 1] = '\0';
audit_log_format(ab, " msg='%.*s'",
AUDIT_MESSAGE_TEXT_MAX,
str);
} else {
audit_log_format(ab, " data=");
if (str[data_len - 1] == '\0')
data_len--;
audit_log_n_untrustedstring(ab, str, data_len);
}
audit_log_end(ab);
}
break;
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
if (data_len < sizeof(struct audit_rule_data))
return -EINVAL;
if (audit_enabled == AUDIT_LOCKED) {
audit_log_common_recv_msg(audit_context(), &ab,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=%s audit_enabled=%d res=0",
msg_type == AUDIT_ADD_RULE ?
"add_rule" : "remove_rule",
audit_enabled);
audit_log_end(ab);
return -EPERM;
}
err = audit_rule_change(msg_type, seq, data, data_len);
break;
case AUDIT_LIST_RULES:
err = audit_list_rules_send(skb, seq);
break;
case AUDIT_TRIM:
audit_trim_trees();
audit_log_common_recv_msg(audit_context(), &ab,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=trim res=1");
audit_log_end(ab);
break;
case AUDIT_MAKE_EQUIV: {
void *bufp = data;
u32 sizes[2];
size_t msglen = data_len;
char *old, *new;
err = -EINVAL;
if (msglen < 2 * sizeof(u32))
break;
memcpy(sizes, bufp, 2 * sizeof(u32));
bufp += 2 * sizeof(u32);
msglen -= 2 * sizeof(u32);
old = audit_unpack_string(&bufp, &msglen, sizes[0]);
if (IS_ERR(old)) {
err = PTR_ERR(old);
break;
}
new = audit_unpack_string(&bufp, &msglen, sizes[1]);
if (IS_ERR(new)) {
err = PTR_ERR(new);
kfree(old);
break;
}
/* OK, here comes... */
err = audit_tag_tree(old, new);
audit_log_common_recv_msg(audit_context(), &ab,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=make_equiv old=");
audit_log_untrustedstring(ab, old);
audit_log_format(ab, " new=");
audit_log_untrustedstring(ab, new);
audit_log_format(ab, " res=%d", !err);
audit_log_end(ab);
kfree(old);
kfree(new);
break;
}
case AUDIT_SIGNAL_INFO:
if (lsmprop_is_set(&audit_sig_lsm)) {
err = security_lsmprop_to_secctx(&audit_sig_lsm,
&lsmctx);
if (err < 0)
return err;
}
sig_data = kmalloc(struct_size(sig_data, ctx, lsmctx.len),
GFP_KERNEL);
if (!sig_data) {
if (lsmprop_is_set(&audit_sig_lsm))
security_release_secctx(&lsmctx);
return -ENOMEM;
}
sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid);
sig_data->pid = audit_sig_pid;
if (lsmprop_is_set(&audit_sig_lsm)) {
memcpy(sig_data->ctx, lsmctx.context, lsmctx.len);
security_release_secctx(&lsmctx);
}
audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
sig_data, struct_size(sig_data, ctx,
lsmctx.len));
kfree(sig_data);
break;
case AUDIT_TTY_GET: {
struct audit_tty_status s;
unsigned int t;
t = READ_ONCE(current->signal->audit_tty);
s.enabled = t & AUDIT_TTY_ENABLE;
s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD);
audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
struct audit_tty_status s, old;
struct audit_buffer *ab;
unsigned int t;
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
/* check if new data is valid */
if ((s.enabled != 0 && s.enabled != 1) ||
(s.log_passwd != 0 && s.log_passwd != 1))
err = -EINVAL;
if (err)
t = READ_ONCE(current->signal->audit_tty);
else {
t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD);
t = xchg(¤t->signal->audit_tty, t);
}
old.enabled = t & AUDIT_TTY_ENABLE;
old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD);
audit_log_common_recv_msg(audit_context(), &ab,
AUDIT_CONFIG_CHANGE);
audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d"
" old-log_passwd=%d new-log_passwd=%d res=%d",
old.enabled, s.enabled, old.log_passwd,
s.log_passwd, !err);
audit_log_end(ab);
break;
}
default:
err = -EINVAL;
break;
}
return err < 0 ? err : 0;
}
/**
* audit_receive - receive messages from a netlink control socket
* @skb: the message buffer
*
* Parse the provided skb and deal with any messages that may be present,
* malformed skbs are discarded.
*/
static void audit_receive(struct sk_buff *skb)
{
struct nlmsghdr *nlh;
bool ack;
/*
* len MUST be signed for nlmsg_next to be able to dec it below 0
* if the nlmsg_len was not aligned
*/
int len;
int err;
nlh = nlmsg_hdr(skb);
len = skb->len;
audit_ctl_lock();
while (nlmsg_ok(nlh, len)) {
ack = nlh->nlmsg_flags & NLM_F_ACK;
err = audit_receive_msg(skb, nlh, &ack);
/* send an ack if the user asked for one and audit_receive_msg
* didn't already do it, or if there was an error. */
if (ack || err)
netlink_ack(skb, nlh, err, NULL);
nlh = nlmsg_next(nlh, &len);
}
audit_ctl_unlock();
/* can't block with the ctrl lock, so penalize the sender now */
if (audit_backlog_limit &&
(skb_queue_len(&audit_queue) > audit_backlog_limit)) {
DECLARE_WAITQUEUE(wait, current);
/* wake kauditd to try and flush the queue */
wake_up_interruptible(&kauditd_wait);
add_wait_queue_exclusive(&audit_backlog_wait, &wait);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(audit_backlog_wait_time);
remove_wait_queue(&audit_backlog_wait, &wait);
}
}
/* Log information about who is connecting to the audit multicast socket */
static void audit_log_multicast(int group, const char *op, int err)
{
const struct cred *cred;
struct tty_struct *tty;
char comm[sizeof(current->comm)];
struct audit_buffer *ab;
if (!audit_enabled)
return;
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER);
if (!ab)
return;
cred = current_cred();
tty = audit_get_tty();
audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u",
task_tgid_nr(current),
from_kuid(&init_user_ns, cred->uid),
from_kuid(&init_user_ns, audit_get_loginuid(current)),
tty ? tty_name(tty) : "(none)",
audit_get_sessionid(current));
audit_put_tty(tty);
audit_log_task_context(ab); /* subj= */
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, get_task_comm(comm, current));
audit_log_d_path_exe(ab, current->mm); /* exe= */
audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err);
audit_log_end(ab);
}
/* Run custom bind function on netlink socket group connect or bind requests. */
static int audit_multicast_bind(struct net *net, int group)
{
int err = 0;
if (!capable(CAP_AUDIT_READ))
err = -EPERM;
audit_log_multicast(group, "connect", err);
return err;
}
static void audit_multicast_unbind(struct net *net, int group)
{
audit_log_multicast(group, "disconnect", 0);
}
static int __net_init audit_net_init(struct net *net)
{
struct netlink_kernel_cfg cfg = {
.input = audit_receive,
.bind = audit_multicast_bind,
.unbind = audit_multicast_unbind,
.flags = NL_CFG_F_NONROOT_RECV,
.groups = AUDIT_NLGRP_MAX,
};
struct audit_net *aunet = net_generic(net, audit_net_id);
aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
if (aunet->sk == NULL) {
audit_panic("cannot initialize netlink socket in namespace");
return -ENOMEM;
}
/* limit the timeout in case auditd is blocked/stopped */
aunet->sk->sk_sndtimeo = HZ / 10;
return 0;
}
static void __net_exit audit_net_exit(struct net *net)
{
struct audit_net *aunet = net_generic(net, audit_net_id);
/* NOTE: you would think that we would want to check the auditd
* connection and potentially reset it here if it lives in this
* namespace, but since the auditd connection tracking struct holds a
* reference to this namespace (see auditd_set()) we are only ever
* going to get here after that connection has been released */
netlink_kernel_release(aunet->sk);
}
static struct pernet_operations audit_net_ops __net_initdata = {
.init = audit_net_init,
.exit = audit_net_exit,
.id = &audit_net_id,
.size = sizeof(struct audit_net),
};
/* Initialize audit support at boot time. */
static int __init audit_init(void)
{
int i;
if (audit_initialized == AUDIT_DISABLED)
return 0;
audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC);
skb_queue_head_init(&audit_queue);
skb_queue_head_init(&audit_retry_queue);
skb_queue_head_init(&audit_hold_queue);
for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
INIT_LIST_HEAD(&audit_inode_hash[i]);
mutex_init(&audit_cmd_mutex.lock);
audit_cmd_mutex.owner = NULL;
pr_info("initializing netlink subsys (%s)\n",
str_enabled_disabled(audit_default));
register_pernet_subsys(&audit_net_ops);
audit_initialized = AUDIT_INITIALIZED;
kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
if (IS_ERR(kauditd_task)) {
int err = PTR_ERR(kauditd_task);
panic("audit: failed to start the kauditd thread (%d)\n", err);
}
audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL,
"state=initialized audit_enabled=%u res=1",
audit_enabled);
return 0;
}
postcore_initcall(audit_init);
/*
* Process kernel command-line parameter at boot time.
* audit={0|off} or audit={1|on}.
*/
static int __init audit_enable(char *str)
{
if (!strcasecmp(str, "off") || !strcmp(str, "0"))
audit_default = AUDIT_OFF;
else if (!strcasecmp(str, "on") || !strcmp(str, "1"))
audit_default = AUDIT_ON;
else {
pr_err("audit: invalid 'audit' parameter value (%s)\n", str);
audit_default = AUDIT_ON;
}
if (audit_default == AUDIT_OFF)
audit_initialized = AUDIT_DISABLED;
if (audit_set_enabled(audit_default))
pr_err("audit: error setting audit state (%d)\n",
audit_default);
pr_info("%s\n", audit_default ?
"enabled (after initialization)" : "disabled (until reboot)");
return 1;
}
__setup("audit=", audit_enable);
/* Process kernel command-line parameter at boot time.
* audit_backlog_limit=<n> */
static int __init audit_backlog_limit_set(char *str)
{
u32 audit_backlog_limit_arg;
pr_info("audit_backlog_limit: ");
if (kstrtouint(str, 0, &audit_backlog_limit_arg)) {
pr_cont("using default of %u, unable to parse %s\n",
audit_backlog_limit, str);
return 1;
}
audit_backlog_limit = audit_backlog_limit_arg;
pr_cont("%d\n", audit_backlog_limit);
return 1;
}
__setup("audit_backlog_limit=", audit_backlog_limit_set);
static void audit_buffer_free(struct audit_buffer *ab)
{
if (!ab)
return;
kfree_skb(ab->skb);
kmem_cache_free(audit_buffer_cache, ab);
}
static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx,
gfp_t gfp_mask, int type)
{
struct audit_buffer *ab;
ab = kmem_cache_alloc(audit_buffer_cache, gfp_mask);
if (!ab)
return NULL;
ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask);
if (!ab->skb)
goto err;
if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0))
goto err;
ab->ctx = ctx;
ab->gfp_mask = gfp_mask;
return ab;
err:
audit_buffer_free(ab);
return NULL;
}
/**
* audit_serial - compute a serial number for the audit record
*
* Compute a serial number for the audit record. Audit records are
* written to user-space as soon as they are generated, so a complete
* audit record may be written in several pieces. The timestamp of the
* record and this serial number are used by the user-space tools to
* determine which pieces belong to the same audit record. The
* (timestamp,serial) tuple is unique for each syscall and is live from
* syscall entry to syscall exit.
*
* NOTE: Another possibility is to store the formatted records off the
* audit context (for those records that have a context), and emit them
* all at syscall exit. However, this could delay the reporting of
* significant errors until syscall exit (or never, if the system
* halts).
*/
unsigned int audit_serial(void)
{
static atomic_t serial = ATOMIC_INIT(0);
return atomic_inc_return(&serial);
}
static inline void audit_get_stamp(struct audit_context *ctx,
struct timespec64 *t, unsigned int *serial)
{
if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
ktime_get_coarse_real_ts64(t);
*serial = audit_serial();
}
}
/**
* audit_log_start - obtain an audit buffer
* @ctx: audit_context (may be NULL)
* @gfp_mask: type of allocation
* @type: audit message type
*
* Returns audit_buffer pointer on success or NULL on error.
*
* Obtain an audit buffer. This routine does locking to obtain the
* audit buffer, but then no locking is required for calls to
* audit_log_*format. If the task (ctx) is a task that is currently in a
* syscall, then the syscall is marked as auditable and an audit record
* will be written at syscall exit. If there is no associated task, then
* task context (ctx) should be NULL.
*/
struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
int type)
{
struct audit_buffer *ab;
struct timespec64 t;
unsigned int serial;
if (audit_initialized != AUDIT_INITIALIZED)
return NULL;
if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE)))
return NULL;
/* NOTE: don't ever fail/sleep on these two conditions:
* 1. auditd generated record - since we need auditd to drain the
* queue; also, when we are checking for auditd, compare PIDs using
* task_tgid_vnr() since auditd_pid is set in audit_receive_msg()
* using a PID anchored in the caller's namespace
* 2. generator holding the audit_cmd_mutex - we don't want to block
* while holding the mutex, although we do penalize the sender
* later in audit_receive() when it is safe to block
*/
if (!(auditd_test_task(current) || audit_ctl_owner_current())) {
long stime = audit_backlog_wait_time;
while (audit_backlog_limit &&
(skb_queue_len(&audit_queue) > audit_backlog_limit)) {
/* wake kauditd to try and flush the queue */
wake_up_interruptible(&kauditd_wait);
/* sleep if we are allowed and we haven't exhausted our
* backlog wait limit */
if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) {
long rtime = stime;
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&audit_backlog_wait,
&wait);
set_current_state(TASK_UNINTERRUPTIBLE);
stime = schedule_timeout(rtime);
atomic_add(rtime - stime, &audit_backlog_wait_time_actual);
remove_wait_queue(&audit_backlog_wait, &wait);
} else {
if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n",
skb_queue_len(&audit_queue),
audit_backlog_limit);
audit_log_lost("backlog limit exceeded");
return NULL;
}
}
}
ab = audit_buffer_alloc(ctx, gfp_mask, type);
if (!ab) {
audit_log_lost("out of memory in audit_log_start");
return NULL;
}
audit_get_stamp(ab->ctx, &t, &serial);
/* cancel dummy context to enable supporting records */
if (ctx)
ctx->dummy = 0;
audit_log_format(ab, "audit(%llu.%03lu:%u): ",
(unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial);
return ab;
}
/**
* audit_expand - expand skb in the audit buffer
* @ab: audit_buffer
* @extra: space to add at tail of the skb
*
* Returns 0 (no space) on failed expansion, or available space if
* successful.
*/
static inline int audit_expand(struct audit_buffer *ab, int extra)
{
struct sk_buff *skb = ab->skb;
int oldtail = skb_tailroom(skb);
int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask);
int newtail = skb_tailroom(skb);
if (ret < 0) {
audit_log_lost("out of memory in audit_expand");
return 0;
}
skb->truesize += newtail - oldtail;
return newtail;
}
/*
* Format an audit message into the audit buffer. If there isn't enough
* room in the audit buffer, more room will be allocated and vsnprint
* will be called a second time. Currently, we assume that a printk
* can't format message larger than 1024 bytes, so we don't either.
*/
static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
va_list args)
{
int len, avail;
struct sk_buff *skb;
va_list args2;
if (!ab)
return;
BUG_ON(!ab->skb);
skb = ab->skb;
avail = skb_tailroom(skb); if (avail == 0) { avail = audit_expand(ab, AUDIT_BUFSIZ); if (!avail)
goto out;
}
va_copy(args2, args);
len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args);
if (len >= avail) {
/* The printk buffer is 1024 bytes long, so if we get
* here and AUDIT_BUFSIZ is at least 1024, then we can
* log everything that printk could have logged. */
avail = audit_expand(ab,
max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail));
if (!avail)
goto out_va_end;
len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2);
}
if (len > 0) skb_put(skb, len);
out_va_end:
va_end(args2);
out:
return;
}
/**
* audit_log_format - format a message into the audit buffer.
* @ab: audit_buffer
* @fmt: format string
* @...: optional parameters matching @fmt string
*
* All the work is done in audit_log_vformat.
*/
void audit_log_format(struct audit_buffer *ab, const char *fmt, ...)
{ va_list args; if (!ab)
return;
va_start(args, fmt);
audit_log_vformat(ab, fmt, args);
va_end(args);
}
/**
* audit_log_n_hex - convert a buffer to hex and append it to the audit skb
* @ab: the audit_buffer
* @buf: buffer to convert to hex
* @len: length of @buf to be converted
*
* No return value; failure to expand is silently ignored.
*
* This function will take the passed buf and convert it into a string of
* ascii hex digits. The new string is placed onto the skb.
*/
void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf,
size_t len)
{
int i, avail, new_len;
unsigned char *ptr;
struct sk_buff *skb;
if (!ab)
return;
BUG_ON(!ab->skb);
skb = ab->skb;
avail = skb_tailroom(skb);
new_len = len<<1;
if (new_len >= avail) {
/* Round the buffer request up to the next multiple */
new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); avail = audit_expand(ab, new_len); if (!avail)
return;
}
ptr = skb_tail_pointer(skb);
for (i = 0; i < len; i++)
ptr = hex_byte_pack_upper(ptr, buf[i]);
*ptr = 0;
skb_put(skb, len << 1); /* new string is twice the old string */
}
/*
* Format a string of no more than slen characters into the audit buffer,
* enclosed in quote marks.
*/
void audit_log_n_string(struct audit_buffer *ab, const char *string,
size_t slen)
{
int avail, new_len;
unsigned char *ptr;
struct sk_buff *skb;
if (!ab)
return;
BUG_ON(!ab->skb);
skb = ab->skb;
avail = skb_tailroom(skb);
new_len = slen + 3; /* enclosing quotes + null terminator */
if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail)
return;
}
ptr = skb_tail_pointer(skb);
*ptr++ = '"';
memcpy(ptr, string, slen);
ptr += slen;
*ptr++ = '"';
*ptr = 0;
skb_put(skb, slen + 2); /* don't include null terminator */
}
/**
* audit_string_contains_control - does a string need to be logged in hex
* @string: string to be checked
* @len: max length of the string to check
*/
bool audit_string_contains_control(const char *string, size_t len)
{
const unsigned char *p;
for (p = string; p < (const unsigned char *)string + len; p++) {
if (*p == '"' || *p < 0x21 || *p > 0x7e)
return true;
}
return false;
}
/**
* audit_log_n_untrustedstring - log a string that may contain random characters
* @ab: audit_buffer
* @string: string to be logged
* @len: length of string (not including trailing null)
*
* This code will escape a string that is passed to it if the string
* contains a control character, unprintable character, double quote mark,
* or a space. Unescaped strings will start and end with a double quote mark.
* Strings that are escaped are printed in hex (2 digits per char).
*
* The caller specifies the number of characters in the string to log, which may
* or may not be the entire string.
*/
void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string,
size_t len)
{
if (audit_string_contains_control(string, len)) audit_log_n_hex(ab, string, len);
else
audit_log_n_string(ab, string, len);
}
/**
* audit_log_untrustedstring - log a string that may contain random characters
* @ab: audit_buffer
* @string: string to be logged
*
* Same as audit_log_n_untrustedstring(), except that strlen is used to
* determine string length.
*/
void audit_log_untrustedstring(struct audit_buffer *ab, const char *string)
{ audit_log_n_untrustedstring(ab, string, strlen(string));
}
/* This is a helper-function to print the escaped d_path */
void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
const struct path *path)
{
char *p, *pathname;
if (prefix) audit_log_format(ab, "%s", prefix);
/* We will allow 11 spaces for ' (deleted)' to be appended */
pathname = kmalloc(PATH_MAX+11, ab->gfp_mask);
if (!pathname) {
audit_log_format(ab, "\"<no_memory>\"");
return;
}
p = d_path(path, pathname, PATH_MAX+11);
if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
/* FIXME: can we save some information here? */
audit_log_format(ab, "\"<too_long>\"");
} else
audit_log_untrustedstring(ab, p);
kfree(pathname);
}
void audit_log_session_info(struct audit_buffer *ab)
{
unsigned int sessionid = audit_get_sessionid(current);
uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
audit_log_format(ab, "auid=%u ses=%u", auid, sessionid);
}
void audit_log_key(struct audit_buffer *ab, char *key)
{
audit_log_format(ab, " key=");
if (key)
audit_log_untrustedstring(ab, key);
else
audit_log_format(ab, "(null)");
}
int audit_log_task_context(struct audit_buffer *ab)
{
struct lsm_prop prop;
struct lsm_context ctx;
int error;
security_current_getlsmprop_subj(&prop);
if (!lsmprop_is_set(&prop))
return 0;
error = security_lsmprop_to_secctx(&prop, &ctx);
if (error < 0) {
if (error != -EINVAL)
goto error_path;
return 0;
}
audit_log_format(ab, " subj=%s", ctx.context);
security_release_secctx(&ctx);
return 0;
error_path:
audit_panic("error in audit_log_task_context");
return error;
}
EXPORT_SYMBOL(audit_log_task_context);
void audit_log_d_path_exe(struct audit_buffer *ab,
struct mm_struct *mm)
{
struct file *exe_file;
if (!mm)
goto out_null;
exe_file = get_mm_exe_file(mm);
if (!exe_file)
goto out_null;
audit_log_d_path(ab, " exe=", &exe_file->f_path);
fput(exe_file);
return;
out_null:
audit_log_format(ab, " exe=(null)");
}
struct tty_struct *audit_get_tty(void)
{
struct tty_struct *tty = NULL;
unsigned long flags;
spin_lock_irqsave(¤t->sighand->siglock, flags);
if (current->signal)
tty = tty_kref_get(current->signal->tty);
spin_unlock_irqrestore(¤t->sighand->siglock, flags);
return tty;
}
void audit_put_tty(struct tty_struct *tty)
{
tty_kref_put(tty);
}
void audit_log_task_info(struct audit_buffer *ab)
{
const struct cred *cred;
char comm[sizeof(current->comm)];
struct tty_struct *tty;
if (!ab)
return;
cred = current_cred();
tty = audit_get_tty();
audit_log_format(ab,
" ppid=%d pid=%d auid=%u uid=%u gid=%u"
" euid=%u suid=%u fsuid=%u"
" egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
task_ppid_nr(current),
task_tgid_nr(current),
from_kuid(&init_user_ns, audit_get_loginuid(current)),
from_kuid(&init_user_ns, cred->uid),
from_kgid(&init_user_ns, cred->gid),
from_kuid(&init_user_ns, cred->euid),
from_kuid(&init_user_ns, cred->suid),
from_kuid(&init_user_ns, cred->fsuid),
from_kgid(&init_user_ns, cred->egid),
from_kgid(&init_user_ns, cred->sgid),
from_kgid(&init_user_ns, cred->fsgid),
tty ? tty_name(tty) : "(none)",
audit_get_sessionid(current));
audit_put_tty(tty);
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, get_task_comm(comm, current));
audit_log_d_path_exe(ab, current->mm);
audit_log_task_context(ab);
}
EXPORT_SYMBOL(audit_log_task_info);
/**
* audit_log_path_denied - report a path restriction denial
* @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc)
* @operation: specific operation name
*/
void audit_log_path_denied(int type, const char *operation)
{
struct audit_buffer *ab;
if (!audit_enabled || audit_dummy_context())
return;
/* Generate log with subject, operation, outcome. */
ab = audit_log_start(audit_context(), GFP_KERNEL, type);
if (!ab)
return;
audit_log_format(ab, "op=%s", operation);
audit_log_task_info(ab);
audit_log_format(ab, " res=0");
audit_log_end(ab);
}
/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);
static int audit_set_loginuid_perm(kuid_t loginuid)
{
/* if we are unset, we don't need privs */
if (!audit_loginuid_set(current))
return 0;
/* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
return -EPERM;
/* it is set, you need permission */
if (!capable(CAP_AUDIT_CONTROL))
return -EPERM;
/* reject if this is not an unset and we don't allow that */
if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID)
&& uid_valid(loginuid))
return -EPERM;
return 0;
}
static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
unsigned int oldsessionid,
unsigned int sessionid, int rc)
{
struct audit_buffer *ab;
uid_t uid, oldloginuid, loginuid;
struct tty_struct *tty;
if (!audit_enabled)
return;
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN);
if (!ab)
return;
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid);
tty = audit_get_tty();
audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid);
audit_log_task_context(ab);
audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d",
oldloginuid, loginuid, tty ? tty_name(tty) : "(none)",
oldsessionid, sessionid, !rc);
audit_put_tty(tty);
audit_log_end(ab);
}
/**
* audit_set_loginuid - set current task's loginuid
* @loginuid: loginuid value
*
* Returns 0.
*
* Called (set) from fs/proc/base.c::proc_loginuid_write().
*/
int audit_set_loginuid(kuid_t loginuid)
{
unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET;
kuid_t oldloginuid;
int rc;
oldloginuid = audit_get_loginuid(current);
oldsessionid = audit_get_sessionid(current);
rc = audit_set_loginuid_perm(loginuid);
if (rc)
goto out;
/* are we setting or clearing? */
if (uid_valid(loginuid)) {
sessionid = (unsigned int)atomic_inc_return(&session_id);
if (unlikely(sessionid == AUDIT_SID_UNSET))
sessionid = (unsigned int)atomic_inc_return(&session_id);
}
current->sessionid = sessionid;
current->loginuid = loginuid;
out:
audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
return rc;
}
/**
* audit_signal_info - record signal info for shutting down audit subsystem
* @sig: signal value
* @t: task being signaled
*
* If the audit subsystem is being terminated, record the task (pid)
* and uid that is doing that.
*/
int audit_signal_info(int sig, struct task_struct *t)
{
kuid_t uid = current_uid(), auid;
if (auditd_test_task(t) &&
(sig == SIGTERM || sig == SIGHUP ||
sig == SIGUSR1 || sig == SIGUSR2)) {
audit_sig_pid = task_tgid_nr(current);
auid = audit_get_loginuid(current);
if (uid_valid(auid))
audit_sig_uid = auid;
else
audit_sig_uid = uid;
security_current_getlsmprop_subj(&audit_sig_lsm);
}
return audit_signal_info_syscall(t);
}
/**
* audit_log_end - end one audit record
* @ab: the audit_buffer
*
* We can not do a netlink send inside an irq context because it blocks (last
* arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a
* queue and a kthread is scheduled to remove them from the queue outside the
* irq context. May be called in any context.
*/
void audit_log_end(struct audit_buffer *ab)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
if (!ab)
return;
if (audit_rate_check()) {
skb = ab->skb;
ab->skb = NULL;
/* setup the netlink header, see the comments in
* kauditd_send_multicast_skb() for length quirks */
nlh = nlmsg_hdr(skb);
nlh->nlmsg_len = skb->len - NLMSG_HDRLEN;
/* queue the netlink packet and poke the kauditd thread */
skb_queue_tail(&audit_queue, skb);
wake_up_interruptible(&kauditd_wait);
} else
audit_log_lost("rate limit exceeded");
audit_buffer_free(ab);
}
/**
* audit_log - Log an audit record
* @ctx: audit context
* @gfp_mask: type of allocation
* @type: audit message type
* @fmt: format string to use
* @...: variable parameters matching the format string
*
* This is a convenience function that calls audit_log_start,
* audit_log_vformat, and audit_log_end. It may be called
* in any context.
*/
void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type,
const char *fmt, ...)
{
struct audit_buffer *ab;
va_list args;
ab = audit_log_start(ctx, gfp_mask, type);
if (ab) {
va_start(args, fmt);
audit_log_vformat(ab, fmt, args);
va_end(args);
audit_log_end(ab);
}
}
EXPORT_SYMBOL(audit_log_start);
EXPORT_SYMBOL(audit_log_end);
EXPORT_SYMBOL(audit_log_format);
EXPORT_SYMBOL(audit_log);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_SPINLOCK_H
#define __LINUX_SPINLOCK_H
#define __LINUX_INSIDE_SPINLOCK_H
/*
* include/linux/spinlock.h - generic spinlock/rwlock declarations
*
* here's the role of the various spinlock/rwlock related include files:
*
* on SMP builds:
*
* asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the
* initializers
*
* linux/spinlock_types_raw:
* The raw types and initializers
* linux/spinlock_types.h:
* defines the generic type and initializers
*
* asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel
* implementations, mostly inline assembly code
*
* (also included on UP-debug builds:)
*
* linux/spinlock_api_smp.h:
* contains the prototypes for the _spin_*() APIs.
*
* linux/spinlock.h: builds the final spin_*() APIs.
*
* on UP builds:
*
* linux/spinlock_type_up.h:
* contains the generic, simplified UP spinlock type.
* (which is an empty structure on non-debug builds)
*
* linux/spinlock_types_raw:
* The raw RT types and initializers
* linux/spinlock_types.h:
* defines the generic type and initializers
*
* linux/spinlock_up.h:
* contains the arch_spin_*()/etc. version of UP
* builds. (which are NOPs on non-debug, non-preempt
* builds)
*
* (included on UP-non-debug builds:)
*
* linux/spinlock_api_up.h:
* builds the _spin_*() APIs.
*
* linux/spinlock.h: builds the final spin_*() APIs.
*/
#include <linux/typecheck.h>
#include <linux/preempt.h>
#include <linux/linkage.h>
#include <linux/compiler.h>
#include <linux/irqflags.h>
#include <linux/thread_info.h>
#include <linux/stringify.h>
#include <linux/bottom_half.h>
#include <linux/lockdep.h>
#include <linux/cleanup.h>
#include <asm/barrier.h>
#include <asm/mmiowb.h>
/*
* Must define these before including other files, inline functions need them
*/
#define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME
#define LOCK_SECTION_START(extra) \
".subsection 1\n\t" \
extra \
".ifndef " LOCK_SECTION_NAME "\n\t" \
LOCK_SECTION_NAME ":\n\t" \
".endif\n"
#define LOCK_SECTION_END \
".previous\n\t"
#define __lockfunc __section(".spinlock.text")
/*
* Pull the arch_spinlock_t and arch_rwlock_t definitions:
*/
#include <linux/spinlock_types.h>
/*
* Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them):
*/
#ifdef CONFIG_SMP
# include <asm/spinlock.h>
#else
# include <linux/spinlock_up.h>
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
struct lock_class_key *key, short inner);
# define raw_spin_lock_init(lock) \
do { \
static struct lock_class_key __key; \
\
__raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \
} while (0)
#else
# define raw_spin_lock_init(lock) \
do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0)
#endif
#define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock)
#ifdef arch_spin_is_contended
#define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock)
#else
#define raw_spin_is_contended(lock) (((void)(lock), 0))
#endif /*arch_spin_is_contended*/
/*
* smp_mb__after_spinlock() provides the equivalent of a full memory barrier
* between program-order earlier lock acquisitions and program-order later
* memory accesses.
*
* This guarantees that the following two properties hold:
*
* 1) Given the snippet:
*
* { X = 0; Y = 0; }
*
* CPU0 CPU1
*
* WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1);
* spin_lock(S); smp_mb();
* smp_mb__after_spinlock(); r1 = READ_ONCE(X);
* r0 = READ_ONCE(Y);
* spin_unlock(S);
*
* it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
* and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
* preceding the call to smp_mb__after_spinlock() in __schedule() and in
* try_to_wake_up().
*
* 2) Given the snippet:
*
* { X = 0; Y = 0; }
*
* CPU0 CPU1 CPU2
*
* spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y);
* WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb();
* spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X);
* WRITE_ONCE(Y, 1);
* spin_unlock(S);
*
* it is forbidden that CPU0's critical section executes before CPU1's
* critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
* and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
* preceding the calls to smp_rmb() in try_to_wake_up() for similar
* snippets but "projected" onto two CPUs.
*
* Property (2) upgrades the lock to an RCsc lock.
*
* Since most load-store architectures implement ACQUIRE with an smp_mb() after
* the LL/SC loop, they need no further barriers. Similarly all our TSO
* architectures imply an smp_mb() for each atomic instruction and equally don't
* need more.
*
* Architectures that can implement ACQUIRE better need to take care.
*/
#ifndef smp_mb__after_spinlock
#define smp_mb__after_spinlock() kcsan_mb()
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
extern int do_raw_spin_trylock(raw_spinlock_t *lock);
extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock);
#else
static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
{
__acquire(lock);
arch_spin_lock(&lock->raw_lock);
mmiowb_spin_lock();
}
static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
{
int ret = arch_spin_trylock(&(lock)->raw_lock);
if (ret)
mmiowb_spin_lock();
return ret;
}
static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
{
mmiowb_spin_unlock();
arch_spin_unlock(&lock->raw_lock);
__release(lock);
}
#endif
/*
* Define the various spin_lock methods. Note we define these
* regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The
* various methods are defined as nops in the case they are not
* required.
*/
#define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock))
#define raw_spin_lock(lock) _raw_spin_lock(lock)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define raw_spin_lock_nested(lock, subclass) \
_raw_spin_lock_nested(lock, subclass)
# define raw_spin_lock_nest_lock(lock, nest_lock) \
do { \
typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\
_raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \
} while (0)
#else
/*
* Always evaluate the 'subclass' argument to avoid that the compiler
* warns about set-but-not-used variables when building with
* CONFIG_DEBUG_LOCK_ALLOC=n and with W=1.
*/
# define raw_spin_lock_nested(lock, subclass) \
_raw_spin_lock(((void)(subclass), (lock)))
# define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock)
#endif
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
#define raw_spin_lock_irqsave(lock, flags) \
do { \
typecheck(unsigned long, flags); \
flags = _raw_spin_lock_irqsave(lock); \
} while (0)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#define raw_spin_lock_irqsave_nested(lock, flags, subclass) \
do { \
typecheck(unsigned long, flags); \
flags = _raw_spin_lock_irqsave_nested(lock, subclass); \
} while (0)
#else
#define raw_spin_lock_irqsave_nested(lock, flags, subclass) \
do { \
typecheck(unsigned long, flags); \
flags = _raw_spin_lock_irqsave(lock); \
} while (0)
#endif
#else
#define raw_spin_lock_irqsave(lock, flags) \
do { \
typecheck(unsigned long, flags); \
_raw_spin_lock_irqsave(lock, flags); \
} while (0)
#define raw_spin_lock_irqsave_nested(lock, flags, subclass) \
raw_spin_lock_irqsave(lock, flags)
#endif
#define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock)
#define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock)
#define raw_spin_unlock(lock) _raw_spin_unlock(lock)
#define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock)
#define raw_spin_unlock_irqrestore(lock, flags) \
do { \
typecheck(unsigned long, flags); \
_raw_spin_unlock_irqrestore(lock, flags); \
} while (0)
#define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock)
#define raw_spin_trylock_bh(lock) \
__cond_lock(lock, _raw_spin_trylock_bh(lock))
#define raw_spin_trylock_irq(lock) \
({ \
local_irq_disable(); \
raw_spin_trylock(lock) ? \
1 : ({ local_irq_enable(); 0; }); \
})
#define raw_spin_trylock_irqsave(lock, flags) \
({ \
local_irq_save(flags); \
raw_spin_trylock(lock) ? \
1 : ({ local_irq_restore(flags); 0; }); \
})
#ifndef CONFIG_PREEMPT_RT
/* Include rwlock functions for !RT */
#include <linux/rwlock.h>
#endif
/*
* Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
*/
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
# include <linux/spinlock_api_smp.h>
#else
# include <linux/spinlock_api_up.h>
#endif
/* Non PREEMPT_RT kernel, map to raw spinlocks: */
#ifndef CONFIG_PREEMPT_RT
/*
* Map the spin_lock functions to the raw variants for PREEMPT_RT=n
*/
static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock)
{
return &lock->rlock;
}
#ifdef CONFIG_DEBUG_SPINLOCK
# define spin_lock_init(lock) \
do { \
static struct lock_class_key __key; \
\
__raw_spin_lock_init(spinlock_check(lock), \
#lock, &__key, LD_WAIT_CONFIG); \
} while (0)
#else
# define spin_lock_init(_lock) \
do { \
spinlock_check(_lock); \
*(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \
} while (0)
#endif
static __always_inline void spin_lock(spinlock_t *lock)
{
raw_spin_lock(&lock->rlock);
}
static __always_inline void spin_lock_bh(spinlock_t *lock)
{
raw_spin_lock_bh(&lock->rlock);
}
static __always_inline int spin_trylock(spinlock_t *lock)
{
return raw_spin_trylock(&lock->rlock);
}
#define spin_lock_nested(lock, subclass) \
do { \
raw_spin_lock_nested(spinlock_check(lock), subclass); \
} while (0)
#define spin_lock_nest_lock(lock, nest_lock) \
do { \
raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \
} while (0)
static __always_inline void spin_lock_irq(spinlock_t *lock)
{
raw_spin_lock_irq(&lock->rlock);
}
#define spin_lock_irqsave(lock, flags) \
do { \
raw_spin_lock_irqsave(spinlock_check(lock), flags); \
} while (0)
#define spin_lock_irqsave_nested(lock, flags, subclass) \
do { \
raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \
} while (0)
static __always_inline void spin_unlock(spinlock_t *lock)
{
raw_spin_unlock(&lock->rlock);
}
static __always_inline void spin_unlock_bh(spinlock_t *lock)
{
raw_spin_unlock_bh(&lock->rlock);
}
static __always_inline void spin_unlock_irq(spinlock_t *lock)
{
raw_spin_unlock_irq(&lock->rlock);
}
static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
{
raw_spin_unlock_irqrestore(&lock->rlock, flags);
}
static __always_inline int spin_trylock_bh(spinlock_t *lock)
{
return raw_spin_trylock_bh(&lock->rlock);
}
static __always_inline int spin_trylock_irq(spinlock_t *lock)
{
return raw_spin_trylock_irq(&lock->rlock);
}
#define spin_trylock_irqsave(lock, flags) \
({ \
raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
})
/**
* spin_is_locked() - Check whether a spinlock is locked.
* @lock: Pointer to the spinlock.
*
* This function is NOT required to provide any memory ordering
* guarantees; it could be used for debugging purposes or, when
* additional synchronization is needed, accompanied with other
* constructs (memory barriers) enforcing the synchronization.
*
* Returns: 1 if @lock is locked, 0 otherwise.
*
* Note that the function only tells you that the spinlock is
* seen to be locked, not that it is locked on your CPU.
*
* Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n,
* the return value is always 0 (see include/linux/spinlock_up.h).
* Therefore you should not rely heavily on the return value.
*/
static __always_inline int spin_is_locked(spinlock_t *lock)
{
return raw_spin_is_locked(&lock->rlock);
}
static __always_inline int spin_is_contended(spinlock_t *lock)
{
return raw_spin_is_contended(&lock->rlock);
}
#define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock)
#else /* !CONFIG_PREEMPT_RT */
# include <linux/spinlock_rt.h>
#endif /* CONFIG_PREEMPT_RT */
/*
* Does a critical section need to be broken due to another
* task waiting?: (technically does not depend on CONFIG_PREEMPTION,
* but a general need for low latency)
*/
static inline int spin_needbreak(spinlock_t *lock)
{
if (!preempt_model_preemptible())
return 0;
return spin_is_contended(lock);
}
/*
* Check if a rwlock is contended.
* Returns non-zero if there is another task waiting on the rwlock.
* Returns zero if the lock is not contended or the system / underlying
* rwlock implementation does not support contention detection.
* Technically does not depend on CONFIG_PREEMPTION, but a general need
* for low latency.
*/
static inline int rwlock_needbreak(rwlock_t *lock)
{
if (!preempt_model_preemptible())
return 0;
return rwlock_is_contended(lock);
}
/*
* Pull the atomic_t declaration:
* (asm-mips/atomic.h needs above definitions)
*/
#include <linux/atomic.h>
/**
* atomic_dec_and_lock - lock on reaching reference count zero
* @atomic: the atomic counter
* @lock: the spinlock in question
*
* Decrements @atomic by 1. If the result is 0, returns true and locks
* @lock. Returns false for all other cases.
*/
extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
#define atomic_dec_and_lock(atomic, lock) \
__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
unsigned long *flags);
#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
__cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock);
#define atomic_dec_and_raw_lock(atomic, lock) \
__cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock))
extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
unsigned long *flags);
#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \
__cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags)))
int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
size_t max_size, unsigned int cpu_mult,
gfp_t gfp, const char *name,
struct lock_class_key *key);
#define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \
({ \
static struct lock_class_key key; \
int ret; \
\
ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \
cpu_mult, gfp, #locks, &key); \
ret; \
})
void free_bucket_spinlocks(spinlock_t *locks);
DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t,
raw_spin_lock(_T->lock),
raw_spin_unlock(_T->lock))
DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock))
DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t,
raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING),
raw_spin_unlock(_T->lock))
DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t,
raw_spin_lock_irq(_T->lock),
raw_spin_unlock_irq(_T->lock))
DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock))
DEFINE_LOCK_GUARD_1(raw_spinlock_bh, raw_spinlock_t,
raw_spin_lock_bh(_T->lock),
raw_spin_unlock_bh(_T->lock))
DEFINE_LOCK_GUARD_1_COND(raw_spinlock_bh, _try, raw_spin_trylock_bh(_T->lock))
DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t,
raw_spin_lock_irqsave(_T->lock, _T->flags),
raw_spin_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try,
raw_spin_trylock_irqsave(_T->lock, _T->flags))
DEFINE_LOCK_GUARD_1(spinlock, spinlock_t,
spin_lock(_T->lock),
spin_unlock(_T->lock))
DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock))
DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t,
spin_lock_irq(_T->lock),
spin_unlock_irq(_T->lock))
DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try,
spin_trylock_irq(_T->lock))
DEFINE_LOCK_GUARD_1(spinlock_bh, spinlock_t,
spin_lock_bh(_T->lock),
spin_unlock_bh(_T->lock))
DEFINE_LOCK_GUARD_1_COND(spinlock_bh, _try,
spin_trylock_bh(_T->lock))
DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
spin_lock_irqsave(_T->lock, _T->flags),
spin_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
spin_trylock_irqsave(_T->lock, _T->flags))
DEFINE_LOCK_GUARD_1(read_lock, rwlock_t,
read_lock(_T->lock),
read_unlock(_T->lock))
DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t,
read_lock_irq(_T->lock),
read_unlock_irq(_T->lock))
DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t,
read_lock_irqsave(_T->lock, _T->flags),
read_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
DEFINE_LOCK_GUARD_1(write_lock, rwlock_t,
write_lock(_T->lock),
write_unlock(_T->lock))
DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t,
write_lock_irq(_T->lock),
write_unlock_irq(_T->lock))
DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t,
write_lock_irqsave(_T->lock, _T->flags),
write_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
#undef __LINUX_INSIDE_SPINLOCK_H
#endif /* __LINUX_SPINLOCK_H */
// SPDX-License-Identifier: GPL-2.0
/*
* KVM coalesced MMIO
*
* Copyright (c) 2008 Bull S.A.S.
* Copyright 2009 Red Hat, Inc. and/or its affiliates.
*
* Author: Laurent Vivier <Laurent.Vivier@bull.net>
*
*/
#include <kvm/iodev.h>
#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/kvm.h>
#include "coalesced_mmio.h"
static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
{
return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
}
static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
gpa_t addr, int len)
{
/* is it in a batchable area ?
* (addr,len) is fully included in
* (zone->addr, zone->size)
*/
if (len < 0)
return 0;
if (addr + len < addr)
return 0;
if (addr < dev->zone.addr)
return 0;
if (addr + len > dev->zone.addr + dev->zone.size)
return 0;
return 1;
}
static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
struct kvm_io_device *this, gpa_t addr,
int len, const void *val)
{
struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
__u32 insert;
if (!coalesced_mmio_in_range(dev, addr, len))
return -EOPNOTSUPP;
spin_lock(&dev->kvm->ring_lock);
/*
* last is the index of the entry to fill. Verify userspace hasn't
* set last to be out of range, and that there is room in the ring.
* Leave one entry free in the ring so that userspace can differentiate
* between an empty ring and a full ring.
*/
insert = READ_ONCE(ring->last);
if (insert >= KVM_COALESCED_MMIO_MAX ||
(insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) {
spin_unlock(&dev->kvm->ring_lock);
return -EOPNOTSUPP;
}
/* copy data in first free entry of the ring */
ring->coalesced_mmio[insert].phys_addr = addr;
ring->coalesced_mmio[insert].len = len;
memcpy(ring->coalesced_mmio[insert].data, val, len);
ring->coalesced_mmio[insert].pio = dev->zone.pio;
smp_wmb();
ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX;
spin_unlock(&dev->kvm->ring_lock);
return 0;
}
static void coalesced_mmio_destructor(struct kvm_io_device *this)
{
struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
list_del(&dev->list);
kfree(dev);
}
static const struct kvm_io_device_ops coalesced_mmio_ops = {
.write = coalesced_mmio_write,
.destructor = coalesced_mmio_destructor,
};
int kvm_coalesced_mmio_init(struct kvm *kvm)
{
struct page *page;
page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!page)
return -ENOMEM;
kvm->coalesced_mmio_ring = page_address(page);
/*
* We're using this spinlock to sync access to the coalesced ring.
* The list doesn't need its own lock since device registration and
* unregistration should only happen when kvm->slots_lock is held.
*/
spin_lock_init(&kvm->ring_lock);
INIT_LIST_HEAD(&kvm->coalesced_zones);
return 0;
}
void kvm_coalesced_mmio_free(struct kvm *kvm)
{ if (kvm->coalesced_mmio_ring) free_page((unsigned long)kvm->coalesced_mmio_ring);
}
int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
struct kvm_coalesced_mmio_zone *zone)
{
int ret;
struct kvm_coalesced_mmio_dev *dev;
if (zone->pio != 1 && zone->pio != 0)
return -EINVAL;
dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev),
GFP_KERNEL_ACCOUNT);
if (!dev)
return -ENOMEM;
kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
dev->kvm = kvm;
dev->zone = *zone;
mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm,
zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS,
zone->addr, zone->size, &dev->dev);
if (ret < 0)
goto out_free_dev;
list_add_tail(&dev->list, &kvm->coalesced_zones);
mutex_unlock(&kvm->slots_lock);
return 0;
out_free_dev:
mutex_unlock(&kvm->slots_lock);
kfree(dev);
return ret;
}
int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
struct kvm_coalesced_mmio_zone *zone)
{
struct kvm_coalesced_mmio_dev *dev, *tmp;
int r;
if (zone->pio != 1 && zone->pio != 0)
return -EINVAL;
mutex_lock(&kvm->slots_lock);
list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) { if (zone->pio == dev->zone.pio && coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
r = kvm_io_bus_unregister_dev(kvm,
zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
/*
* On failure, unregister destroys all devices on the
* bus, including the target device. There's no need
* to restart the walk as there aren't any zones left.
*/
if (r)
break;
}
}
mutex_unlock(&kvm->slots_lock);
/*
* Ignore the result of kvm_io_bus_unregister_dev(), from userspace's
* perspective, the coalesced MMIO is most definitely unregistered.
*/
return 0;
}
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_MM_H
#define _LINUX_SCHED_MM_H
#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/gfp.h>
#include <linux/sync_core.h>
#include <linux/sched/coredump.h>
/*
* Routines for handling mm_structs
*/
extern struct mm_struct *mm_alloc(void);
/**
* mmgrab() - Pin a &struct mm_struct.
* @mm: The &struct mm_struct to pin.
*
* Make sure that @mm will not get freed even after the owning task
* exits. This doesn't guarantee that the associated address space
* will still exist later on and mmget_not_zero() has to be used before
* accessing it.
*
* This is a preferred way to pin @mm for a longer/unbounded amount
* of time.
*
* Use mmdrop() to release the reference acquired by mmgrab().
*
* See also <Documentation/mm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmgrab(struct mm_struct *mm)
{
atomic_inc(&mm->mm_count);
}
static inline void smp_mb__after_mmgrab(void)
{
smp_mb__after_atomic();
}
extern void __mmdrop(struct mm_struct *mm);
static inline void mmdrop(struct mm_struct *mm)
{
/*
* The implicit full barrier implied by atomic_dec_and_test() is
* required by the membarrier system call before returning to
* user-space, after storing to rq->curr.
*/
if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm);
}
#ifdef CONFIG_PREEMPT_RT
/*
* RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is
* by far the least expensive way to do that.
*/
static inline void __mmdrop_delayed(struct rcu_head *rhp)
{
struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
__mmdrop(mm);
}
/*
* Invoked from finish_task_switch(). Delegates the heavy lifting on RT
* kernels via RCU.
*/
static inline void mmdrop_sched(struct mm_struct *mm)
{
/* Provides a full memory barrier. See mmdrop() */
if (atomic_dec_and_test(&mm->mm_count))
call_rcu(&mm->delayed_drop, __mmdrop_delayed);
}
#else
static inline void mmdrop_sched(struct mm_struct *mm)
{
mmdrop(mm);
}
#endif
/* Helpers for lazy TLB mm refcounting */
static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
{
if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
mmgrab(mm);
}
static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
{
if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) {
mmdrop(mm);
} else {
/*
* mmdrop_lazy_tlb must provide a full memory barrier, see the
* membarrier comment finish_task_switch which relies on this.
*/
smp_mb();
}
}
static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
{
if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
mmdrop_sched(mm);
else
smp_mb(); /* see mmdrop_lazy_tlb() above */
}
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
*
* Make sure that the address space of the given &struct mm_struct doesn't
* go away. This does not protect against parts of the address space being
* modified or freed, however.
*
* Never use this function to pin this address space for an
* unbounded/indefinite amount of time.
*
* Use mmput() to release the reference acquired by mmget().
*
* See also <Documentation/mm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmget(struct mm_struct *mm)
{
atomic_inc(&mm->mm_users);
}
static inline bool mmget_not_zero(struct mm_struct *mm)
{
return atomic_inc_not_zero(&mm->mm_users);
}
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
#ifdef CONFIG_MMU
/* same as above but performs the slow path from the async context. Can
* be called from the atomic context as well
*/
void mmput_async(struct mm_struct *);
#endif
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/*
* Grab a reference to a task's mm, if it is not already going away
* and ptrace_may_access with the mode parameter passed to it
* succeeds.
*/
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct on exit() */
extern void exit_mm_release(struct task_struct *, struct mm_struct *);
/* Remove the current tasks stale references to the old mm_struct on exec() */
extern void exec_mm_release(struct task_struct *, struct mm_struct *);
#ifdef CONFIG_MEMCG
extern void mm_update_next_owner(struct mm_struct *mm);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}
#endif /* CONFIG_MEMCG */
#ifdef CONFIG_MMU
#ifndef arch_get_mmap_end
#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE)
#endif
#ifndef arch_get_mmap_base
#define arch_get_mmap_base(addr, base) (base)
#endif
extern void arch_pick_mmap_layout(struct mm_struct *mm,
struct rlimit *rlim_stack);
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags);
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t);
unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm,
struct file *filp,
unsigned long addr,
unsigned long len,
unsigned long pgoff,
unsigned long flags,
vm_flags_t vm_flags);
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags);
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm,
struct rlimit *rlim_stack) {}
#endif
static inline bool in_vfork(struct task_struct *tsk)
{
bool ret;
/*
* need RCU to access ->real_parent if CLONE_VM was used along with
* CLONE_PARENT.
*
* We check real_parent->mm == tsk->mm because CLONE_VFORK does not
* imply CLONE_VM
*
* CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
* ->real_parent is not necessarily the task doing vfork(), so in
* theory we can't rely on task_lock() if we want to dereference it.
*
* And in this case we can't trust the real_parent->mm == tsk->mm
* check, it can be false negative. But we do not care, if init or
* another oom-unkillable task does this it should blame itself.
*/
rcu_read_lock();
ret = tsk->vfork_done &&
rcu_dereference(tsk->real_parent)->mm == tsk->mm;
rcu_read_unlock();
return ret;
}
/*
* Applies per-task gfp context to the given allocation flags.
* PF_MEMALLOC_NOIO implies GFP_NOIO
* PF_MEMALLOC_NOFS implies GFP_NOFS
* PF_MEMALLOC_PIN implies !GFP_MOVABLE
*/
static inline gfp_t current_gfp_context(gfp_t flags)
{
unsigned int pflags = READ_ONCE(current->flags);
if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) {
/*
* NOIO implies both NOIO and NOFS and it is a weaker context
* so always make sure it makes precedence
*/
if (pflags & PF_MEMALLOC_NOIO)
flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS)
flags &= ~__GFP_FS;
if (pflags & PF_MEMALLOC_PIN)
flags &= ~__GFP_MOVABLE;
}
return flags;
}
#ifdef CONFIG_LOCKDEP
extern void __fs_reclaim_acquire(unsigned long ip);
extern void __fs_reclaim_release(unsigned long ip);
extern void fs_reclaim_acquire(gfp_t gfp_mask);
extern void fs_reclaim_release(gfp_t gfp_mask);
#else
static inline void __fs_reclaim_acquire(unsigned long ip) { }
static inline void __fs_reclaim_release(unsigned long ip) { }
static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
static inline void fs_reclaim_release(gfp_t gfp_mask) { }
#endif
/* Any memory-allocation retry loop should use
* memalloc_retry_wait(), and pass the flags for the most
* constrained allocation attempt that might have failed.
* This provides useful documentation of where loops are,
* and a central place to fine tune the waiting as the MM
* implementation changes.
*/
static inline void memalloc_retry_wait(gfp_t gfp_flags)
{
/* We use io_schedule_timeout because waiting for memory
* typically included waiting for dirty pages to be
* written out, which requires IO.
*/
__set_current_state(TASK_UNINTERRUPTIBLE);
gfp_flags = current_gfp_context(gfp_flags);
if (gfpflags_allow_blocking(gfp_flags) &&
!(gfp_flags & __GFP_NORETRY))
/* Probably waited already, no need for much more */
io_schedule_timeout(1);
else
/* Probably didn't wait, and has now released a lock,
* so now is a good time to wait
*/
io_schedule_timeout(HZ/50);
}
/**
* might_alloc - Mark possible allocation sites
* @gfp_mask: gfp_t flags that would be used to allocate
*
* Similar to might_sleep() and other annotations, this can be used in functions
* that might allocate, but often don't. Compiles to nothing without
* CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking.
*/
static inline void might_alloc(gfp_t gfp_mask)
{
fs_reclaim_acquire(gfp_mask);
fs_reclaim_release(gfp_mask);
might_sleep_if(gfpflags_allow_blocking(gfp_mask));
}
/**
* memalloc_flags_save - Add a PF_* flag to current->flags, save old value
*
* This allows PF_* flags to be conveniently added, irrespective of current
* value, and then the old version restored with memalloc_flags_restore().
*/
static inline unsigned memalloc_flags_save(unsigned flags)
{
unsigned oldflags = ~current->flags & flags;
current->flags |= flags;
return oldflags;
}
static inline void memalloc_flags_restore(unsigned flags)
{
current->flags &= ~flags;
}
/**
* memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
*
* This functions marks the beginning of the GFP_NOIO allocation scope.
* All further allocations will implicitly drop __GFP_IO flag and so
* they are safe for the IO critical section from the allocation recursion
* point of view. Use memalloc_noio_restore to end the scope with flags
* returned by this function.
*
* Context: This function is safe to be used from any context.
* Return: The saved flags to be passed to memalloc_noio_restore.
*/
static inline unsigned int memalloc_noio_save(void)
{
return memalloc_flags_save(PF_MEMALLOC_NOIO);
}
/**
* memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
* @flags: Flags to restore.
*
* Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
* Always make sure that the given flags is the return value from the
* pairing memalloc_noio_save call.
*/
static inline void memalloc_noio_restore(unsigned int flags)
{
memalloc_flags_restore(flags);
}
/**
* memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
*
* This functions marks the beginning of the GFP_NOFS allocation scope.
* All further allocations will implicitly drop __GFP_FS flag and so
* they are safe for the FS critical section from the allocation recursion
* point of view. Use memalloc_nofs_restore to end the scope with flags
* returned by this function.
*
* Context: This function is safe to be used from any context.
* Return: The saved flags to be passed to memalloc_nofs_restore.
*/
static inline unsigned int memalloc_nofs_save(void)
{
return memalloc_flags_save(PF_MEMALLOC_NOFS);
}
/**
* memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
* @flags: Flags to restore.
*
* Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
* Always make sure that the given flags is the return value from the
* pairing memalloc_nofs_save call.
*/
static inline void memalloc_nofs_restore(unsigned int flags)
{
memalloc_flags_restore(flags);
}
/**
* memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope.
*
* This function marks the beginning of the __GFP_MEMALLOC allocation scope.
* All further allocations will implicitly add the __GFP_MEMALLOC flag, which
* prevents entering reclaim and allows access to all memory reserves. This
* should only be used when the caller guarantees the allocation will allow more
* memory to be freed very shortly, i.e. it needs to allocate some memory in
* the process of freeing memory, and cannot reclaim due to potential recursion.
*
* Users of this scope have to be extremely careful to not deplete the reserves
* completely and implement a throttling mechanism which controls the
* consumption of the reserve based on the amount of freed memory. Usage of a
* pre-allocated pool (e.g. mempool) should be always considered before using
* this scope.
*
* Individual allocations under the scope can opt out using __GFP_NOMEMALLOC
*
* Context: This function should not be used in an interrupt context as that one
* does not give PF_MEMALLOC access to reserves.
* See __gfp_pfmemalloc_flags().
* Return: The saved flags to be passed to memalloc_noreclaim_restore.
*/
static inline unsigned int memalloc_noreclaim_save(void)
{
return memalloc_flags_save(PF_MEMALLOC);
}
/**
* memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope.
* @flags: Flags to restore.
*
* Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save
* function. Always make sure that the given flags is the return value from the
* pairing memalloc_noreclaim_save call.
*/
static inline void memalloc_noreclaim_restore(unsigned int flags)
{
memalloc_flags_restore(flags);
}
/**
* memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope.
*
* This function marks the beginning of the ~__GFP_MOVABLE allocation scope.
* All further allocations will implicitly remove the __GFP_MOVABLE flag, which
* will constraint the allocations to zones that allow long term pinning, i.e.
* not ZONE_MOVABLE zones.
*
* Return: The saved flags to be passed to memalloc_pin_restore.
*/
static inline unsigned int memalloc_pin_save(void)
{
return memalloc_flags_save(PF_MEMALLOC_PIN);
}
/**
* memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope.
* @flags: Flags to restore.
*
* Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function.
* Always make sure that the given flags is the return value from the pairing
* memalloc_pin_save call.
*/
static inline void memalloc_pin_restore(unsigned int flags)
{
memalloc_flags_restore(flags);
}
#ifdef CONFIG_MEMCG
DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
/**
* set_active_memcg - Starts the remote memcg charging scope.
* @memcg: memcg to charge.
*
* This function marks the beginning of the remote memcg charging scope. All the
* __GFP_ACCOUNT allocations till the end of the scope will be charged to the
* given memcg.
*
* Please, make sure that caller has a reference to the passed memcg structure,
* so its lifetime is guaranteed to exceed the scope between two
* set_active_memcg() calls.
*
* NOTE: This function can nest. Users must save the return value and
* reset the previous value after their own charging scope is over.
*/
static inline struct mem_cgroup *
set_active_memcg(struct mem_cgroup *memcg)
{
struct mem_cgroup *old;
if (!in_task()) {
old = this_cpu_read(int_active_memcg);
this_cpu_write(int_active_memcg, memcg);
} else {
old = current->active_memcg;
current->active_memcg = memcg;
}
return old;
}
#else
static inline struct mem_cgroup *
set_active_memcg(struct mem_cgroup *memcg)
{
return NULL;
}
#endif
#ifdef CONFIG_MEMBARRIER
enum {
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0),
MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1),
MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2),
MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7),
};
enum {
MEMBARRIER_FLAG_SYNC_CORE = (1U << 0),
MEMBARRIER_FLAG_RSEQ = (1U << 1),
};
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
#include <asm/membarrier.h>
#endif
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
/*
* The atomic_read() below prevents CSE. The following should
* help the compiler generate more efficient code on architectures
* where sync_core_before_usermode() is a no-op.
*/
if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
return;
if (current->mm != mm)
return;
if (likely(!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
return;
sync_core_before_usermode();
}
extern void membarrier_exec_mmap(struct mm_struct *mm);
extern void membarrier_update_current_mm(struct mm_struct *next_mm);
#else
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
struct mm_struct *next,
struct task_struct *tsk)
{
}
#endif
static inline void membarrier_exec_mmap(struct mm_struct *mm)
{
}
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
}
static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
{
}
#endif
#endif /* _LINUX_SCHED_MM_H */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FUTEX_H
#define _FUTEX_H
#include <linux/futex.h>
#include <linux/rtmutex.h>
#include <linux/sched/wake_q.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#ifdef CONFIG_PREEMPT_RT
#include <linux/rcuwait.h>
#endif
#include <asm/futex.h>
/*
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
#define FLAGS_SIZE_8 0x0000
#define FLAGS_SIZE_16 0x0001
#define FLAGS_SIZE_32 0x0002
#define FLAGS_SIZE_64 0x0003
#define FLAGS_SIZE_MASK 0x0003
#ifdef CONFIG_MMU
# define FLAGS_SHARED 0x0010
#else
/*
* NOMMU does not have per process address space. Let the compiler optimize
* code away.
*/
# define FLAGS_SHARED 0x0000
#endif
#define FLAGS_CLOCKRT 0x0020
#define FLAGS_HAS_TIMEOUT 0x0040
#define FLAGS_NUMA 0x0080
#define FLAGS_STRICT 0x0100
/* FUTEX_ to FLAGS_ */
static inline unsigned int futex_to_flags(unsigned int op)
{
unsigned int flags = FLAGS_SIZE_32;
if (!(op & FUTEX_PRIVATE_FLAG))
flags |= FLAGS_SHARED;
if (op & FUTEX_CLOCK_REALTIME)
flags |= FLAGS_CLOCKRT;
return flags;
}
#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE)
/* FUTEX2_ to FLAGS_ */
static inline unsigned int futex2_to_flags(unsigned int flags2)
{
unsigned int flags = flags2 & FUTEX2_SIZE_MASK;
if (!(flags2 & FUTEX2_PRIVATE))
flags |= FLAGS_SHARED;
if (flags2 & FUTEX2_NUMA)
flags |= FLAGS_NUMA;
return flags;
}
static inline unsigned int futex_size(unsigned int flags)
{
return 1 << (flags & FLAGS_SIZE_MASK);
}
static inline bool futex_flags_valid(unsigned int flags)
{
/* Only 64bit futexes for 64bit code */
if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) {
if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64)
return false;
}
/* Only 32bit futexes are implemented -- for now */
if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
return false;
return true;
}
static inline bool futex_validate_input(unsigned int flags, u64 val)
{
int bits = 8 * futex_size(flags);
if (bits < 64 && (val >> bits))
return false;
return true;
}
#ifdef CONFIG_FAIL_FUTEX
extern bool should_fail_futex(bool fshared);
#else
static inline bool should_fail_futex(bool fshared)
{
return false;
}
#endif
/*
* Hash buckets are shared by all the futex_keys that hash to the same
* location. Each key may have multiple futex_q structures, one for each task
* waiting on a futex.
*/
struct futex_hash_bucket {
atomic_t waiters;
spinlock_t lock;
struct plist_head chain;
} ____cacheline_aligned_in_smp;
/*
* Priority Inheritance state:
*/
struct futex_pi_state {
/*
* list of 'owned' pi_state instances - these have to be
* cleaned up in do_exit() if the task exits prematurely:
*/
struct list_head list;
/*
* The PI object:
*/
struct rt_mutex_base pi_mutex;
struct task_struct *owner;
refcount_t refcount;
union futex_key key;
} __randomize_layout;
struct futex_q;
typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);
/**
* struct futex_q - The hashed futex queue entry, one per waiting task
* @list: priority-sorted list of tasks waiting on this futex
* @task: the task waiting on the futex
* @lock_ptr: the hash bucket lock
* @wake: the wake handler for this queue
* @wake_data: data associated with the wake handler
* @key: the key the futex is hashed on
* @pi_state: optional priority inheritance state
* @rt_waiter: rt_waiter storage for use with requeue_pi
* @requeue_pi_key: the requeue_pi target futex key
* @bitset: bitset for the optional bitmasked wakeup
* @requeue_state: State field for futex_requeue_pi()
* @requeue_wait: RCU wait for futex_requeue_pi() (RT only)
*
* We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
* we can wake only the relevant ones (hashed queues may be shared).
*
* A futex_q has a woken state, just like tasks have TASK_RUNNING.
* It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
* The order of wakeup is always to make the first condition true, then
* the second.
*
* PI futexes are typically woken before they are removed from the hash list via
* the rt_mutex code. See futex_unqueue_pi().
*/
struct futex_q {
struct plist_node list;
struct task_struct *task;
spinlock_t *lock_ptr;
futex_wake_fn *wake;
void *wake_data;
union futex_key key;
struct futex_pi_state *pi_state;
struct rt_mutex_waiter *rt_waiter;
union futex_key *requeue_pi_key;
u32 bitset;
atomic_t requeue_state;
#ifdef CONFIG_PREEMPT_RT
struct rcuwait requeue_wait;
#endif
} __randomize_layout;
extern const struct futex_q futex_q_init;
enum futex_access {
FUTEX_READ,
FUTEX_WRITE
};
extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
enum futex_access rw);
extern struct hrtimer_sleeper *
futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
int flags, u64 range_ns);
extern struct futex_hash_bucket *futex_hash(union futex_key *key);
/**
* futex_match - Check whether two futex keys are equal
* @key1: Pointer to key1
* @key2: Pointer to key2
*
* Return 1 if two futex_keys are equal, 0 otherwise.
*/
static inline int futex_match(union futex_key *key1, union futex_key *key2)
{
return (key1 && key2
&& key1->both.word == key2->both.word
&& key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset);
}
extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb);
extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
struct hrtimer_sleeper *timeout);
extern bool __futex_wake_mark(struct futex_q *q);
extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);
extern int fault_in_user_writeable(u32 __user *uaddr);
extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key);
static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval)
{
int ret;
pagefault_disable();
ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
pagefault_enable();
return ret;
}
/*
* This does a plain atomic user space read, and the user pointer has
* already been verified earlier by get_futex_key() to be both aligned
* and actually in user space, just like futex_atomic_cmpxchg_inatomic().
*
* We still want to avoid any speculation, and while __get_user() is
* the traditional model for this, it's actually slower than doing
* this manually these days.
*
* We could just have a per-architecture special function for it,
* the same way we do futex_atomic_cmpxchg_inatomic(), but rather
* than force everybody to do that, write it out long-hand using
* the low-level user-access infrastructure.
*
* This looks a bit overkill, but generally just results in a couple
* of instructions.
*/
static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from)
{
u32 val;
if (can_do_masked_user_access())
from = masked_user_access_begin(from);
else if (!user_read_access_begin(from, sizeof(*from)))
return -EFAULT;
unsafe_get_user(val, from, Efault);
user_read_access_end();
*dest = val;
return 0;
Efault:
user_read_access_end();
return -EFAULT;
}
static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
{
int ret;
pagefault_disable();
ret = futex_read_inatomic(dest, from);
pagefault_enable();
return ret;
}
extern void __futex_unqueue(struct futex_q *q);
extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
struct task_struct *task);
extern int futex_unqueue(struct futex_q *q);
/**
* futex_queue() - Enqueue the futex_q on the futex_hash_bucket
* @q: The futex_q to enqueue
* @hb: The destination hash bucket
* @task: Task queueing this futex
*
* The hb->lock must be held by the caller, and is released here. A call to
* futex_queue() is typically paired with exactly one call to futex_unqueue(). The
* exceptions involve the PI related operations, which may use futex_unqueue_pi()
* or nothing if the unqueue is done as part of the wake process and the unqueue
* state is implicit in the state of woken task (see futex_wait_requeue_pi() for
* an example).
*
* Note that @task may be NULL, for async usage of futexes.
*/
static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
struct task_struct *task)
__releases(&hb->lock)
{
__futex_queue(q, hb, task);
spin_unlock(&hb->lock);
}
extern void futex_unqueue_pi(struct futex_q *q);
extern void wait_for_owner_exiting(int ret, struct task_struct *exiting);
/*
* Reflects a new waiter being added to the waitqueue.
*/
static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
atomic_inc(&hb->waiters);
/*
* Full barrier (A), see the ordering comment above.
*/
smp_mb__after_atomic();
#endif
}
/*
* Reflects a waiter being removed from the waitqueue by wakeup
* paths.
*/
static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
atomic_dec(&hb->waiters);
#endif
}
static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
/*
* Full barrier (B), see the ordering comment above.
*/
smp_mb();
return atomic_read(&hb->waiters);
#else
return 1;
#endif
}
extern struct futex_hash_bucket *futex_q_lock(struct futex_q *q);
extern void futex_q_unlock(struct futex_hash_bucket *hb);
extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
union futex_key *key,
struct futex_pi_state **ps,
struct task_struct *task,
struct task_struct **exiting,
int set_waiters);
extern int refill_pi_state_cache(void);
extern void get_pi_state(struct futex_pi_state *pi_state);
extern void put_pi_state(struct futex_pi_state *pi_state);
extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked);
/*
* Express the locking dependencies for lockdep:
*/
static inline void
double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
{
if (hb1 > hb2)
swap(hb1, hb2);
spin_lock(&hb1->lock);
if (hb1 != hb2)
spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
}
static inline void
double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
{
spin_unlock(&hb1->lock);
if (hb1 != hb2)
spin_unlock(&hb2->lock);
}
/* syscalls */
extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32
val, ktime_t *abs_time, u32 bitset, u32 __user
*uaddr2);
extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
u32 __user *uaddr2, unsigned int flags2,
int nr_wake, int nr_requeue,
u32 *cmpval, int requeue_pi);
extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
struct hrtimer_sleeper *to, u32 bitset);
extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
ktime_t *abs_time, u32 bitset);
/**
* struct futex_vector - Auxiliary struct for futex_waitv()
* @w: Userspace provided data
* @q: Kernel side data
*
* Struct used to build an array with all data need for futex_waitv()
*/
struct futex_vector {
struct futex_waitv w;
struct futex_q q;
};
extern int futex_parse_waitv(struct futex_vector *futexv,
struct futex_waitv __user *uwaitv,
unsigned int nr_futexes, futex_wake_fn *wake,
void *wake_data);
extern int futex_wait_multiple_setup(struct futex_vector *vs, int count,
int *woken);
extern int futex_unqueue_multiple(struct futex_vector *v, int count);
extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
struct hrtimer_sleeper *to);
extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset);
extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags,
u32 __user *uaddr2, int nr_wake, int nr_wake2, int op);
extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags);
extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock);
#endif /* _FUTEX_H */
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/* Copyright (c) 2002-2007 Volkswagen Group Electronic Research
* Copyright (c) 2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of Volkswagen nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* Alternatively, provided that this notice is retained in full, this
* software may be distributed under the terms of the GNU General
* Public License ("GPL") version 2, in which case the provisions of the
* GPL apply INSTEAD OF those given above.
*
* The provided data structures and external interfaces from this code
* are not restricted to be used by modules with a GPL compatible license.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
* DAMAGE.
*
*/
#ifndef CAN_ML_H
#define CAN_ML_H
#include <linux/can.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
#define CAN_EFF_RCV_HASH_BITS 10
#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS)
enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX };
struct can_dev_rcv_lists {
struct hlist_head rx[RX_MAX];
struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ];
struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ];
int entries;
};
struct can_ml_priv {
struct can_dev_rcv_lists dev_rcv_lists;
#ifdef CAN_J1939
struct j1939_priv *j1939_priv;
#endif
};
static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev)
{
return netdev_get_ml_priv(dev, ML_PRIV_CAN);
}
static inline void can_set_ml_priv(struct net_device *dev,
struct can_ml_priv *ml_priv)
{
netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN);
}
#endif /* CAN_ML_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/mmu_notifier.c
*
* Copyright (C) 2008 Qumranet, Inc.
* Copyright (C) 2008 SGI
* Christoph Lameter <cl@linux.com>
*/
#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/interval_tree.h>
#include <linux/srcu.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>
#include "vma.h"
/* global SRCU for all MMs */
DEFINE_STATIC_SRCU(srcu);
#ifdef CONFIG_LOCKDEP
struct lockdep_map __mmu_notifier_invalidate_range_start_map = {
.name = "mmu_notifier_invalidate_range_start"
};
#endif
/*
* The mmu_notifier_subscriptions structure is allocated and installed in
* mm->notifier_subscriptions inside the mm_take_all_locks() protected
* critical section and it's released only when mm_count reaches zero
* in mmdrop().
*/
struct mmu_notifier_subscriptions {
/* all mmu notifiers registered in this mm are queued in this list */
struct hlist_head list;
bool has_itree;
/* to serialize the list modifications and hlist_unhashed */
spinlock_t lock;
unsigned long invalidate_seq;
unsigned long active_invalidate_ranges;
struct rb_root_cached itree;
wait_queue_head_t wq;
struct hlist_head deferred_list;
};
/*
* This is a collision-retry read-side/write-side 'lock', a lot like a
* seqcount, however this allows multiple write-sides to hold it at
* once. Conceptually the write side is protecting the values of the PTEs in
* this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any
* writer exists.
*
* Note that the core mm creates nested invalidate_range_start()/end() regions
* within the same thread, and runs invalidate_range_start()/end() in parallel
* on multiple CPUs. This is designed to not reduce concurrency or block
* progress on the mm side.
*
* As a secondary function, holding the full write side also serves to prevent
* writers for the itree, this is an optimization to avoid extra locking
* during invalidate_range_start/end notifiers.
*
* The write side has two states, fully excluded:
* - mm->active_invalidate_ranges != 0
* - subscriptions->invalidate_seq & 1 == True (odd)
* - some range on the mm_struct is being invalidated
* - the itree is not allowed to change
*
* And partially excluded:
* - mm->active_invalidate_ranges != 0
* - subscriptions->invalidate_seq & 1 == False (even)
* - some range on the mm_struct is being invalidated
* - the itree is allowed to change
*
* Operations on notifier_subscriptions->invalidate_seq (under spinlock):
* seq |= 1 # Begin writing
* seq++ # Release the writing state
* seq & 1 # True if a writer exists
*
* The later state avoids some expensive work on inv_end in the common case of
* no mmu_interval_notifier monitoring the VA.
*/
static bool
mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions)
{
lockdep_assert_held(&subscriptions->lock);
return subscriptions->invalidate_seq & 1;
}
static struct mmu_interval_notifier *
mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions,
const struct mmu_notifier_range *range,
unsigned long *seq)
{
struct interval_tree_node *node;
struct mmu_interval_notifier *res = NULL;
spin_lock(&subscriptions->lock);
subscriptions->active_invalidate_ranges++;
node = interval_tree_iter_first(&subscriptions->itree, range->start,
range->end - 1);
if (node) {
subscriptions->invalidate_seq |= 1;
res = container_of(node, struct mmu_interval_notifier,
interval_tree);
}
*seq = subscriptions->invalidate_seq;
spin_unlock(&subscriptions->lock);
return res;
}
static struct mmu_interval_notifier *
mn_itree_inv_next(struct mmu_interval_notifier *interval_sub,
const struct mmu_notifier_range *range)
{
struct interval_tree_node *node;
node = interval_tree_iter_next(&interval_sub->interval_tree,
range->start, range->end - 1);
if (!node)
return NULL;
return container_of(node, struct mmu_interval_notifier, interval_tree);
}
static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions)
{
struct mmu_interval_notifier *interval_sub;
struct hlist_node *next;
spin_lock(&subscriptions->lock);
if (--subscriptions->active_invalidate_ranges ||
!mn_itree_is_invalidating(subscriptions)) {
spin_unlock(&subscriptions->lock);
return;
}
/* Make invalidate_seq even */
subscriptions->invalidate_seq++;
/*
* The inv_end incorporates a deferred mechanism like rtnl_unlock().
* Adds and removes are queued until the final inv_end happens then
* they are progressed. This arrangement for tree updates is used to
* avoid using a blocking lock during invalidate_range_start.
*/
hlist_for_each_entry_safe(interval_sub, next,
&subscriptions->deferred_list,
deferred_item) {
if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb))
interval_tree_insert(&interval_sub->interval_tree,
&subscriptions->itree);
else
interval_tree_remove(&interval_sub->interval_tree,
&subscriptions->itree);
hlist_del(&interval_sub->deferred_item);
}
spin_unlock(&subscriptions->lock);
wake_up_all(&subscriptions->wq);
}
/**
* mmu_interval_read_begin - Begin a read side critical section against a VA
* range
* @interval_sub: The interval subscription
*
* mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a
* collision-retry scheme similar to seqcount for the VA range under
* subscription. If the mm invokes invalidation during the critical section
* then mmu_interval_read_retry() will return true.
*
* This is useful to obtain shadow PTEs where teardown or setup of the SPTEs
* require a blocking context. The critical region formed by this can sleep,
* and the required 'user_lock' can also be a sleeping lock.
*
* The caller is required to provide a 'user_lock' to serialize both teardown
* and setup.
*
* The return value should be passed to mmu_interval_read_retry().
*/
unsigned long
mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub)
{
struct mmu_notifier_subscriptions *subscriptions =
interval_sub->mm->notifier_subscriptions;
unsigned long seq;
bool is_invalidating;
/*
* If the subscription has a different seq value under the user_lock
* than we started with then it has collided.
*
* If the subscription currently has the same seq value as the
* subscriptions seq, then it is currently between
* invalidate_start/end and is colliding.
*
* The locking looks broadly like this:
* mn_itree_inv_start(): mmu_interval_read_begin():
* spin_lock
* seq = READ_ONCE(interval_sub->invalidate_seq);
* seq == subs->invalidate_seq
* spin_unlock
* spin_lock
* seq = ++subscriptions->invalidate_seq
* spin_unlock
* op->invalidate():
* user_lock
* mmu_interval_set_seq()
* interval_sub->invalidate_seq = seq
* user_unlock
*
* [Required: mmu_interval_read_retry() == true]
*
* mn_itree_inv_end():
* spin_lock
* seq = ++subscriptions->invalidate_seq
* spin_unlock
*
* user_lock
* mmu_interval_read_retry():
* interval_sub->invalidate_seq != seq
* user_unlock
*
* Barriers are not needed here as any races here are closed by an
* eventual mmu_interval_read_retry(), which provides a barrier via the
* user_lock.
*/
spin_lock(&subscriptions->lock);
/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
seq = READ_ONCE(interval_sub->invalidate_seq);
is_invalidating = seq == subscriptions->invalidate_seq;
spin_unlock(&subscriptions->lock);
/*
* interval_sub->invalidate_seq must always be set to an odd value via
* mmu_interval_set_seq() using the provided cur_seq from
* mn_itree_inv_start_range(). This ensures that if seq does wrap we
* will always clear the below sleep in some reasonable time as
* subscriptions->invalidate_seq is even in the idle state.
*/
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
if (is_invalidating)
wait_event(subscriptions->wq,
READ_ONCE(subscriptions->invalidate_seq) != seq);
/*
* Notice that mmu_interval_read_retry() can already be true at this
* point, avoiding loops here allows the caller to provide a global
* time bound.
*/
return seq;
}
EXPORT_SYMBOL_GPL(mmu_interval_read_begin);
static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions,
struct mm_struct *mm)
{
struct mmu_notifier_range range = {
.flags = MMU_NOTIFIER_RANGE_BLOCKABLE,
.event = MMU_NOTIFY_RELEASE,
.mm = mm,
.start = 0,
.end = ULONG_MAX,
};
struct mmu_interval_notifier *interval_sub;
unsigned long cur_seq;
bool ret;
for (interval_sub =
mn_itree_inv_start_range(subscriptions, &range, &cur_seq);
interval_sub;
interval_sub = mn_itree_inv_next(interval_sub, &range)) {
ret = interval_sub->ops->invalidate(interval_sub, &range,
cur_seq);
WARN_ON(!ret);
}
mn_itree_inv_end(subscriptions);
}
/*
* This function can't run concurrently against mmu_notifier_register
* because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
* runs with mm_users == 0. Other tasks may still invoke mmu notifiers
* in parallel despite there being no task using this mm any more,
* through the vmas outside of the exit_mmap context, such as with
* vmtruncate. This serializes against mmu_notifier_unregister with
* the notifier_subscriptions->lock in addition to SRCU and it serializes
* against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions
* can't go away from under us as exit_mmap holds an mm_count pin
* itself.
*/
static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions,
struct mm_struct *mm)
{
struct mmu_notifier *subscription;
int id;
/*
* SRCU here will block mmu_notifier_unregister until
* ->release returns.
*/
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
srcu_read_lock_held(&srcu))
/*
* If ->release runs before mmu_notifier_unregister it must be
* handled, as it's the only way for the driver to flush all
* existing sptes and stop the driver from establishing any more
* sptes before all the pages in the mm are freed.
*/
if (subscription->ops->release)
subscription->ops->release(subscription, mm);
spin_lock(&subscriptions->lock);
while (unlikely(!hlist_empty(&subscriptions->list))) {
subscription = hlist_entry(subscriptions->list.first,
struct mmu_notifier, hlist);
/*
* We arrived before mmu_notifier_unregister so
* mmu_notifier_unregister will do nothing other than to wait
* for ->release to finish and for mmu_notifier_unregister to
* return.
*/
hlist_del_init_rcu(&subscription->hlist);
}
spin_unlock(&subscriptions->lock);
srcu_read_unlock(&srcu, id);
/*
* synchronize_srcu here prevents mmu_notifier_release from returning to
* exit_mmap (which would proceed with freeing all pages in the mm)
* until the ->release method returns, if it was invoked by
* mmu_notifier_unregister.
*
* The notifier_subscriptions can't go away from under us because
* one mm_count is held by exit_mmap.
*/
synchronize_srcu(&srcu);
}
void __mmu_notifier_release(struct mm_struct *mm)
{
struct mmu_notifier_subscriptions *subscriptions =
mm->notifier_subscriptions;
if (subscriptions->has_itree)
mn_itree_release(subscriptions, mm);
if (!hlist_empty(&subscriptions->list))
mn_hlist_release(subscriptions, mm);
}
/*
* If no young bitflag is supported by the hardware, ->clear_flush_young can
* unmap the address and return 1 or 0 depending if the mapping previously
* existed or not.
*/
int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
struct mmu_notifier *subscription;
int young = 0, id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription,
&mm->notifier_subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->clear_flush_young)
young |= subscription->ops->clear_flush_young(
subscription, mm, start, end);
}
srcu_read_unlock(&srcu, id);
return young;
}
int __mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
struct mmu_notifier *subscription;
int young = 0, id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription,
&mm->notifier_subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->clear_young)
young |= subscription->ops->clear_young(subscription,
mm, start, end);
}
srcu_read_unlock(&srcu, id);
return young;
}
int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
struct mmu_notifier *subscription;
int young = 0, id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription,
&mm->notifier_subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->test_young) {
young = subscription->ops->test_young(subscription, mm,
address);
if (young)
break;
}
}
srcu_read_unlock(&srcu, id);
return young;
}
static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions,
const struct mmu_notifier_range *range)
{
struct mmu_interval_notifier *interval_sub;
unsigned long cur_seq;
for (interval_sub = mn_itree_inv_start_range(subscriptions, range, &cur_seq);
interval_sub;
interval_sub = mn_itree_inv_next(interval_sub, range)) {
bool ret;
ret = interval_sub->ops->invalidate(interval_sub, range,
cur_seq);
if (!ret) { if (WARN_ON(mmu_notifier_range_blockable(range)))
continue;
goto out_would_block;
}
}
return 0;
out_would_block:
/*
* On -EAGAIN the non-blocking caller is not allowed to call
* invalidate_range_end()
*/
mn_itree_inv_end(subscriptions);
return -EAGAIN;
}
static int mn_hlist_invalidate_range_start(
struct mmu_notifier_subscriptions *subscriptions,
struct mmu_notifier_range *range)
{
struct mmu_notifier *subscription;
int ret = 0;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
const struct mmu_notifier_ops *ops = subscription->ops;
if (ops->invalidate_range_start) {
int _ret;
if (!mmu_notifier_range_blockable(range)) non_block_start();
_ret = ops->invalidate_range_start(subscription, range);
if (!mmu_notifier_range_blockable(range)) non_block_end(); if (_ret) {
pr_info("%pS callback failed with %d in %sblockable context.\n",
ops->invalidate_range_start, _ret,
!mmu_notifier_range_blockable(range) ?
"non-" :
"");
WARN_ON(mmu_notifier_range_blockable(range) ||
_ret != -EAGAIN);
/*
* We call all the notifiers on any EAGAIN,
* there is no way for a notifier to know if
* its start method failed, thus a start that
* does EAGAIN can't also do end.
*/
WARN_ON(ops->invalidate_range_end);
ret = _ret;
}
}
}
if (ret) {
/*
* Must be non-blocking to get here. If there are multiple
* notifiers and one or more failed start, any that succeeded
* start are expecting their end to be called. Do so now.
*/
hlist_for_each_entry_rcu(subscription, &subscriptions->list,
hlist, srcu_read_lock_held(&srcu)) {
if (!subscription->ops->invalidate_range_end)
continue;
subscription->ops->invalidate_range_end(subscription,
range);
}
}
srcu_read_unlock(&srcu, id);
return ret;
}
int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
{
struct mmu_notifier_subscriptions *subscriptions =
range->mm->notifier_subscriptions;
int ret;
if (subscriptions->has_itree) { ret = mn_itree_invalidate(subscriptions, range);
if (ret)
return ret;
}
if (!hlist_empty(&subscriptions->list)) return mn_hlist_invalidate_range_start(subscriptions, range);
return 0;
}
static void
mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions,
struct mmu_notifier_range *range)
{
struct mmu_notifier *subscription;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->invalidate_range_end) { if (!mmu_notifier_range_blockable(range)) non_block_start();
subscription->ops->invalidate_range_end(subscription,
range);
if (!mmu_notifier_range_blockable(range)) non_block_end();
}
}
srcu_read_unlock(&srcu, id);
}
void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
{
struct mmu_notifier_subscriptions *subscriptions =
range->mm->notifier_subscriptions;
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
if (subscriptions->has_itree) mn_itree_inv_end(subscriptions); if (!hlist_empty(&subscriptions->list)) mn_hlist_invalidate_end(subscriptions, range);
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
}
void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
struct mmu_notifier *subscription;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(subscription,
&mm->notifier_subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->arch_invalidate_secondary_tlbs) subscription->ops->arch_invalidate_secondary_tlbs(
subscription, mm,
start, end);
}
srcu_read_unlock(&srcu, id);
}
/*
* Same as mmu_notifier_register but here the caller must hold the mmap_lock in
* write mode. A NULL mn signals the notifier is being registered for itree
* mode.
*/
int __mmu_notifier_register(struct mmu_notifier *subscription,
struct mm_struct *mm)
{
struct mmu_notifier_subscriptions *subscriptions = NULL;
int ret;
mmap_assert_write_locked(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0);
/*
* Subsystems should only register for invalidate_secondary_tlbs() or
* invalidate_range_start()/end() callbacks, not both.
*/
if (WARN_ON_ONCE(subscription &&
(subscription->ops->arch_invalidate_secondary_tlbs &&
(subscription->ops->invalidate_range_start ||
subscription->ops->invalidate_range_end))))
return -EINVAL;
if (!mm->notifier_subscriptions) {
/*
* kmalloc cannot be called under mm_take_all_locks(), but we
* know that mm->notifier_subscriptions can't change while we
* hold the write side of the mmap_lock.
*/
subscriptions = kzalloc(
sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL);
if (!subscriptions)
return -ENOMEM;
INIT_HLIST_HEAD(&subscriptions->list);
spin_lock_init(&subscriptions->lock);
subscriptions->invalidate_seq = 2;
subscriptions->itree = RB_ROOT_CACHED;
init_waitqueue_head(&subscriptions->wq);
INIT_HLIST_HEAD(&subscriptions->deferred_list);
}
ret = mm_take_all_locks(mm);
if (unlikely(ret))
goto out_clean;
/*
* Serialize the update against mmu_notifier_unregister. A
* side note: mmu_notifier_release can't run concurrently with
* us because we hold the mm_users pin (either implicitly as
* current->mm or explicitly with get_task_mm() or similar).
* We can't race against any other mmu notifier method either
* thanks to mm_take_all_locks().
*
* release semantics on the initialization of the
* mmu_notifier_subscriptions's contents are provided for unlocked
* readers. acquire can only be used while holding the mmgrab or
* mmget, and is safe because once created the
* mmu_notifier_subscriptions is not freed until the mm is destroyed.
* As above, users holding the mmap_lock or one of the
* mm_take_all_locks() do not need to use acquire semantics.
*/
if (subscriptions)
smp_store_release(&mm->notifier_subscriptions, subscriptions);
if (subscription) {
/* Pairs with the mmdrop in mmu_notifier_unregister_* */
mmgrab(mm);
subscription->mm = mm;
subscription->users = 1;
spin_lock(&mm->notifier_subscriptions->lock);
hlist_add_head_rcu(&subscription->hlist,
&mm->notifier_subscriptions->list);
spin_unlock(&mm->notifier_subscriptions->lock);
} else
mm->notifier_subscriptions->has_itree = true;
mm_drop_all_locks(mm);
BUG_ON(atomic_read(&mm->mm_users) <= 0);
return 0;
out_clean:
kfree(subscriptions);
return ret;
}
EXPORT_SYMBOL_GPL(__mmu_notifier_register);
/**
* mmu_notifier_register - Register a notifier on a mm
* @subscription: The notifier to attach
* @mm: The mm to attach the notifier to
*
* Must not hold mmap_lock nor any other VM related lock when calling
* this registration function. Must also ensure mm_users can't go down
* to zero while this runs to avoid races with mmu_notifier_release,
* so mm has to be current->mm or the mm should be pinned safely such
* as with get_task_mm(). If the mm is not current->mm, the mm_users
* pin should be released by calling mmput after mmu_notifier_register
* returns.
*
* mmu_notifier_unregister() or mmu_notifier_put() must be always called to
* unregister the notifier.
*
* While the caller has a mmu_notifier get the subscription->mm pointer will remain
* valid, and can be converted to an active mm pointer via mmget_not_zero().
*/
int mmu_notifier_register(struct mmu_notifier *subscription,
struct mm_struct *mm)
{
int ret;
mmap_write_lock(mm);
ret = __mmu_notifier_register(subscription, mm);
mmap_write_unlock(mm);
return ret;
}
EXPORT_SYMBOL_GPL(mmu_notifier_register);
static struct mmu_notifier *
find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
{
struct mmu_notifier *subscription;
spin_lock(&mm->notifier_subscriptions->lock);
hlist_for_each_entry_rcu(subscription,
&mm->notifier_subscriptions->list, hlist,
lockdep_is_held(&mm->notifier_subscriptions->lock)) {
if (subscription->ops != ops)
continue;
if (likely(subscription->users != UINT_MAX))
subscription->users++;
else
subscription = ERR_PTR(-EOVERFLOW);
spin_unlock(&mm->notifier_subscriptions->lock);
return subscription;
}
spin_unlock(&mm->notifier_subscriptions->lock);
return NULL;
}
/**
* mmu_notifier_get_locked - Return the single struct mmu_notifier for
* the mm & ops
* @ops: The operations struct being subscribe with
* @mm : The mm to attach notifiers too
*
* This function either allocates a new mmu_notifier via
* ops->alloc_notifier(), or returns an already existing notifier on the
* list. The value of the ops pointer is used to determine when two notifiers
* are the same.
*
* Each call to mmu_notifier_get() must be paired with a call to
* mmu_notifier_put(). The caller must hold the write side of mm->mmap_lock.
*
* While the caller has a mmu_notifier get the mm pointer will remain valid,
* and can be converted to an active mm pointer via mmget_not_zero().
*/
struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops,
struct mm_struct *mm)
{
struct mmu_notifier *subscription;
int ret;
mmap_assert_write_locked(mm);
if (mm->notifier_subscriptions) {
subscription = find_get_mmu_notifier(mm, ops);
if (subscription)
return subscription;
}
subscription = ops->alloc_notifier(mm);
if (IS_ERR(subscription))
return subscription;
subscription->ops = ops;
ret = __mmu_notifier_register(subscription, mm);
if (ret)
goto out_free;
return subscription;
out_free:
subscription->ops->free_notifier(subscription);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(mmu_notifier_get_locked);
/* this is called after the last mmu_notifier_unregister() returned */
void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
{
BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list));
kfree(mm->notifier_subscriptions);
mm->notifier_subscriptions = LIST_POISON1; /* debug */
}
/*
* This releases the mm_count pin automatically and frees the mm
* structure if it was the last user of it. It serializes against
* running mmu notifiers with SRCU and against mmu_notifier_unregister
* with the unregister lock + SRCU. All sptes must be dropped before
* calling mmu_notifier_unregister. ->release or any other notifier
* method may be invoked concurrently with mmu_notifier_unregister,
* and only after mmu_notifier_unregister returned we're guaranteed
* that ->release or any other method can't run anymore.
*/
void mmu_notifier_unregister(struct mmu_notifier *subscription,
struct mm_struct *mm)
{ BUG_ON(atomic_read(&mm->mm_count) <= 0); if (!hlist_unhashed(&subscription->hlist)) {
/*
* SRCU here will force exit_mmap to wait for ->release to
* finish before freeing the pages.
*/
int id;
id = srcu_read_lock(&srcu);
/*
* exit_mmap will block in mmu_notifier_release to guarantee
* that ->release is called before freeing the pages.
*/
if (subscription->ops->release) subscription->ops->release(subscription, mm); srcu_read_unlock(&srcu, id);
spin_lock(&mm->notifier_subscriptions->lock);
/*
* Can not use list_del_rcu() since __mmu_notifier_release
* can delete it before we hold the lock.
*/
hlist_del_init_rcu(&subscription->hlist);
spin_unlock(&mm->notifier_subscriptions->lock);
}
/*
* Wait for any running method to finish, of course including
* ->release if it was run by mmu_notifier_release instead of us.
*/
synchronize_srcu(&srcu);
BUG_ON(atomic_read(&mm->mm_count) <= 0); mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
static void mmu_notifier_free_rcu(struct rcu_head *rcu)
{
struct mmu_notifier *subscription =
container_of(rcu, struct mmu_notifier, rcu);
struct mm_struct *mm = subscription->mm;
subscription->ops->free_notifier(subscription);
/* Pairs with the get in __mmu_notifier_register() */
mmdrop(mm);
}
/**
* mmu_notifier_put - Release the reference on the notifier
* @subscription: The notifier to act on
*
* This function must be paired with each mmu_notifier_get(), it releases the
* reference obtained by the get. If this is the last reference then process
* to free the notifier will be run asynchronously.
*
* Unlike mmu_notifier_unregister() the get/put flow only calls ops->release
* when the mm_struct is destroyed. Instead free_notifier is always called to
* release any resources held by the user.
*
* As ops->release is not guaranteed to be called, the user must ensure that
* all sptes are dropped, and no new sptes can be established before
* mmu_notifier_put() is called.
*
* This function can be called from the ops->release callback, however the
* caller must still ensure it is called pairwise with mmu_notifier_get().
*
* Modules calling this function must call mmu_notifier_synchronize() in
* their __exit functions to ensure the async work is completed.
*/
void mmu_notifier_put(struct mmu_notifier *subscription)
{
struct mm_struct *mm = subscription->mm;
spin_lock(&mm->notifier_subscriptions->lock);
if (WARN_ON(!subscription->users) || --subscription->users)
goto out_unlock;
hlist_del_init_rcu(&subscription->hlist);
spin_unlock(&mm->notifier_subscriptions->lock);
call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu);
return;
out_unlock:
spin_unlock(&mm->notifier_subscriptions->lock);
}
EXPORT_SYMBOL_GPL(mmu_notifier_put);
static int __mmu_interval_notifier_insert(
struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
struct mmu_notifier_subscriptions *subscriptions, unsigned long start,
unsigned long length, const struct mmu_interval_notifier_ops *ops)
{
interval_sub->mm = mm;
interval_sub->ops = ops;
RB_CLEAR_NODE(&interval_sub->interval_tree.rb);
interval_sub->interval_tree.start = start;
/*
* Note that the representation of the intervals in the interval tree
* considers the ending point as contained in the interval.
*/
if (length == 0 ||
check_add_overflow(start, length - 1,
&interval_sub->interval_tree.last))
return -EOVERFLOW;
/* Must call with a mmget() held */
if (WARN_ON(atomic_read(&mm->mm_users) <= 0))
return -EINVAL;
/* pairs with mmdrop in mmu_interval_notifier_remove() */
mmgrab(mm);
/*
* If some invalidate_range_start/end region is going on in parallel
* we don't know what VA ranges are affected, so we must assume this
* new range is included.
*
* If the itree is invalidating then we are not allowed to change
* it. Retrying until invalidation is done is tricky due to the
* possibility for live lock, instead defer the add to
* mn_itree_inv_end() so this algorithm is deterministic.
*
* In all cases the value for the interval_sub->invalidate_seq should be
* odd, see mmu_interval_read_begin()
*/
spin_lock(&subscriptions->lock);
if (subscriptions->active_invalidate_ranges) {
if (mn_itree_is_invalidating(subscriptions))
hlist_add_head(&interval_sub->deferred_item,
&subscriptions->deferred_list);
else {
subscriptions->invalidate_seq |= 1;
interval_tree_insert(&interval_sub->interval_tree,
&subscriptions->itree);
}
interval_sub->invalidate_seq = subscriptions->invalidate_seq;
} else {
WARN_ON(mn_itree_is_invalidating(subscriptions));
/*
* The starting seq for a subscription not under invalidation
* should be odd, not equal to the current invalidate_seq and
* invalidate_seq should not 'wrap' to the new seq any time
* soon.
*/
interval_sub->invalidate_seq =
subscriptions->invalidate_seq - 1;
interval_tree_insert(&interval_sub->interval_tree,
&subscriptions->itree);
}
spin_unlock(&subscriptions->lock);
return 0;
}
/**
* mmu_interval_notifier_insert - Insert an interval notifier
* @interval_sub: Interval subscription to register
* @start: Starting virtual address to monitor
* @length: Length of the range to monitor
* @mm: mm_struct to attach to
* @ops: Interval notifier operations to be called on matching events
*
* This function subscribes the interval notifier for notifications from the
* mm. Upon return the ops related to mmu_interval_notifier will be called
* whenever an event that intersects with the given range occurs.
*
* Upon return the range_notifier may not be present in the interval tree yet.
* The caller must use the normal interval notifier read flow via
* mmu_interval_read_begin() to establish SPTEs for this range.
*/
int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
struct mm_struct *mm, unsigned long start,
unsigned long length,
const struct mmu_interval_notifier_ops *ops)
{
struct mmu_notifier_subscriptions *subscriptions;
int ret;
might_lock(&mm->mmap_lock);
subscriptions = smp_load_acquire(&mm->notifier_subscriptions);
if (!subscriptions || !subscriptions->has_itree) {
ret = mmu_notifier_register(NULL, mm);
if (ret)
return ret;
subscriptions = mm->notifier_subscriptions;
}
return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
start, length, ops);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert);
int mmu_interval_notifier_insert_locked(
struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
unsigned long start, unsigned long length,
const struct mmu_interval_notifier_ops *ops)
{
struct mmu_notifier_subscriptions *subscriptions =
mm->notifier_subscriptions;
int ret;
mmap_assert_write_locked(mm);
if (!subscriptions || !subscriptions->has_itree) {
ret = __mmu_notifier_register(NULL, mm);
if (ret)
return ret;
subscriptions = mm->notifier_subscriptions;
}
return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
start, length, ops);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);
static bool
mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions,
unsigned long seq)
{
bool ret;
spin_lock(&subscriptions->lock);
ret = subscriptions->invalidate_seq != seq;
spin_unlock(&subscriptions->lock);
return ret;
}
/**
* mmu_interval_notifier_remove - Remove a interval notifier
* @interval_sub: Interval subscription to unregister
*
* This function must be paired with mmu_interval_notifier_insert(). It cannot
* be called from any ops callback.
*
* Once this returns ops callbacks are no longer running on other CPUs and
* will not be called in future.
*/
void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub)
{
struct mm_struct *mm = interval_sub->mm;
struct mmu_notifier_subscriptions *subscriptions =
mm->notifier_subscriptions;
unsigned long seq = 0;
might_sleep();
spin_lock(&subscriptions->lock);
if (mn_itree_is_invalidating(subscriptions)) {
/*
* remove is being called after insert put this on the
* deferred list, but before the deferred list was processed.
*/
if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) {
hlist_del(&interval_sub->deferred_item);
} else {
hlist_add_head(&interval_sub->deferred_item,
&subscriptions->deferred_list);
seq = subscriptions->invalidate_seq;
}
} else {
WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb));
interval_tree_remove(&interval_sub->interval_tree,
&subscriptions->itree);
}
spin_unlock(&subscriptions->lock);
/*
* The possible sleep on progress in the invalidation requires the
* caller not hold any locks held by invalidation callbacks.
*/
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
if (seq)
wait_event(subscriptions->wq,
mmu_interval_seq_released(subscriptions, seq));
/* pairs with mmgrab in mmu_interval_notifier_insert() */
mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove);
/**
* mmu_notifier_synchronize - Ensure all mmu_notifiers are freed
*
* This function ensures that all outstanding async SRU work from
* mmu_notifier_put() is completed. After it returns any mmu_notifier_ops
* associated with an unused mmu_notifier will no longer be called.
*
* Before using the caller must ensure that all of its mmu_notifiers have been
* fully released via mmu_notifier_put().
*
* Modules using the mmu_notifier_put() API should call this in their __exit
* function to avoid module unloading races.
*/
void mmu_notifier_synchronize(void)
{
synchronize_srcu(&srcu);
}
EXPORT_SYMBOL_GPL(mmu_notifier_synchronize);
/* SPDX-License-Identifier: GPL-2.0+ */
#ifndef _LINUX_MAPLE_TREE_H
#define _LINUX_MAPLE_TREE_H
/*
* Maple Tree - An RCU-safe adaptive tree for storing ranges
* Copyright (c) 2018-2022 Oracle
* Authors: Liam R. Howlett <Liam.Howlett@Oracle.com>
* Matthew Wilcox <willy@infradead.org>
*/
#include <linux/kernel.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
/* #define CONFIG_MAPLE_RCU_DISABLED */
/*
* Allocated nodes are mutable until they have been inserted into the tree,
* at which time they cannot change their type until they have been removed
* from the tree and an RCU grace period has passed.
*
* Removed nodes have their ->parent set to point to themselves. RCU readers
* check ->parent before relying on the value that they loaded from the
* slots array. This lets us reuse the slots array for the RCU head.
*
* Nodes in the tree point to their parent unless bit 0 is set.
*/
#if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64)
/* 64bit sizes */
#define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */
#define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */
#define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */
#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1)
#else
/* 32bit sizes */
#define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */
#define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */
#define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */
#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2)
#endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */
#define MAPLE_NODE_MASK 255UL
/*
* The node->parent of the root node has bit 0 set and the rest of the pointer
* is a pointer to the tree itself. No more bits are available in this pointer
* (on m68k, the data structure may only be 2-byte aligned).
*
* Internal non-root nodes can only have maple_range_* nodes as parents. The
* parent pointer is 256B aligned like all other tree nodes. When storing a 32
* or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an
* extra bit to store the offset. This extra bit comes from a reuse of the last
* bit in the node type. This is possible by using bit 1 to indicate if bit 2
* is part of the type or the slot.
*
* Once the type is decided, the decision of an allocation range type or a
* range type is done by examining the immutable tree flag for the
* MT_FLAGS_ALLOC_RANGE flag.
*
* Node types:
* 0x??1 = Root
* 0x?00 = 16 bit nodes
* 0x010 = 32 bit nodes
* 0x110 = 64 bit nodes
*
* Slot size and location in the parent pointer:
* type : slot location
* 0x??1 : Root
* 0x?00 : 16 bit values, type in 0-1, slot in 2-6
* 0x010 : 32 bit values, type in 0-2, slot in 3-6
* 0x110 : 64 bit values, type in 0-2, slot in 3-6
*/
/*
* This metadata is used to optimize the gap updating code and in reverse
* searching for gaps or any other code that needs to find the end of the data.
*/
struct maple_metadata {
unsigned char end;
unsigned char gap;
};
/*
* Leaf nodes do not store pointers to nodes, they store user data. Users may
* store almost any bit pattern. As noted above, the optimisation of storing an
* entry at 0 in the root pointer cannot be done for data which have the bottom
* two bits set to '10'. We also reserve values with the bottom two bits set to
* '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs
* return errnos as a negative errno shifted right by two bits and the bottom
* two bits set to '10', and while choosing to store these values in the array
* is not an error, it may lead to confusion if you're testing for an error with
* mas_is_err().
*
* Non-leaf nodes store the type of the node pointed to (enum maple_type in bits
* 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now.
*
* In regular B-Tree terms, pivots are called keys. The term pivot is used to
* indicate that the tree is specifying ranges, Pivots may appear in the
* subtree with an entry attached to the value whereas keys are unique to a
* specific position of a B-tree. Pivot values are inclusive of the slot with
* the same index.
*/
struct maple_range_64 {
struct maple_pnode *parent;
unsigned long pivot[MAPLE_RANGE64_SLOTS - 1];
union {
void __rcu *slot[MAPLE_RANGE64_SLOTS];
struct {
void __rcu *pad[MAPLE_RANGE64_SLOTS - 1];
struct maple_metadata meta;
};
};
};
/*
* At tree creation time, the user can specify that they're willing to trade off
* storing fewer entries in a tree in return for storing more information in
* each node.
*
* The maple tree supports recording the largest range of NULL entries available
* in this node, also called gaps. This optimises the tree for allocating a
* range.
*/
struct maple_arange_64 {
struct maple_pnode *parent;
unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1];
void __rcu *slot[MAPLE_ARANGE64_SLOTS];
unsigned long gap[MAPLE_ARANGE64_SLOTS];
struct maple_metadata meta;
};
struct maple_alloc {
unsigned long total;
unsigned char node_count;
unsigned int request_count;
struct maple_alloc *slot[MAPLE_ALLOC_SLOTS];
};
struct maple_topiary {
struct maple_pnode *parent;
struct maple_enode *next; /* Overlaps the pivot */
};
enum maple_type {
maple_dense,
maple_leaf_64,
maple_range_64,
maple_arange_64,
};
enum store_type {
wr_invalid,
wr_new_root,
wr_store_root,
wr_exact_fit,
wr_spanning_store,
wr_split_store,
wr_rebalance,
wr_append,
wr_node_store,
wr_slot_store,
};
/**
* DOC: Maple tree flags
*
* * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree
* * MT_FLAGS_USE_RCU - Operate in RCU mode
* * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags
* * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value
* * MT_FLAGS_LOCK_MASK - How the mt_lock is used
* * MT_FLAGS_LOCK_IRQ - Acquired irq-safe
* * MT_FLAGS_LOCK_BH - Acquired bh-safe
* * MT_FLAGS_LOCK_EXTERN - mt_lock is not used
*
* MAPLE_HEIGHT_MAX The largest height that can be stored
*/
#define MT_FLAGS_ALLOC_RANGE 0x01
#define MT_FLAGS_USE_RCU 0x02
#define MT_FLAGS_HEIGHT_OFFSET 0x02
#define MT_FLAGS_HEIGHT_MASK 0x7C
#define MT_FLAGS_LOCK_MASK 0x300
#define MT_FLAGS_LOCK_IRQ 0x100
#define MT_FLAGS_LOCK_BH 0x200
#define MT_FLAGS_LOCK_EXTERN 0x300
#define MT_FLAGS_ALLOC_WRAPPED 0x0800
#define MAPLE_HEIGHT_MAX 31
#define MAPLE_NODE_TYPE_MASK 0x0F
#define MAPLE_NODE_TYPE_SHIFT 0x03
#define MAPLE_RESERVED_RANGE 4096
#ifdef CONFIG_LOCKDEP
typedef struct lockdep_map *lockdep_map_p;
#define mt_lock_is_held(mt) \
(!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock))
#define mt_write_lock_is_held(mt) \
(!(mt)->ma_external_lock || \
lock_is_held_type((mt)->ma_external_lock, 0))
#define mt_set_external_lock(mt, lock) \
(mt)->ma_external_lock = &(lock)->dep_map
#define mt_on_stack(mt) (mt).ma_external_lock = NULL
#else
typedef struct { /* nothing */ } lockdep_map_p;
#define mt_lock_is_held(mt) 1
#define mt_write_lock_is_held(mt) 1
#define mt_set_external_lock(mt, lock) do { } while (0)
#define mt_on_stack(mt) do { } while (0)
#endif
/*
* If the tree contains a single entry at index 0, it is usually stored in
* tree->ma_root. To optimise for the page cache, an entry which ends in '00',
* '01' or '11' is stored in the root, but an entry which ends in '10' will be
* stored in a node. Bits 3-6 are used to store enum maple_type.
*
* The flags are used both to store some immutable information about this tree
* (set at tree creation time) and dynamic information set under the spinlock.
*
* Another use of flags are to indicate global states of the tree. This is the
* case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in
* RCU mode. This mode was added to allow the tree to reuse nodes instead of
* re-allocating and RCU freeing nodes when there is a single user.
*/
struct maple_tree {
union {
spinlock_t ma_lock;
lockdep_map_p ma_external_lock;
};
unsigned int ma_flags;
void __rcu *ma_root;
};
/**
* MTREE_INIT() - Initialize a maple tree
* @name: The maple tree name
* @__flags: The maple tree flags
*
*/
#define MTREE_INIT(name, __flags) { \
.ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \
.ma_flags = __flags, \
.ma_root = NULL, \
}
/**
* MTREE_INIT_EXT() - Initialize a maple tree with an external lock.
* @name: The tree name
* @__flags: The maple tree flags
* @__lock: The external lock
*/
#ifdef CONFIG_LOCKDEP
#define MTREE_INIT_EXT(name, __flags, __lock) { \
.ma_external_lock = &(__lock).dep_map, \
.ma_flags = (__flags), \
.ma_root = NULL, \
}
#else
#define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags)
#endif
#define DEFINE_MTREE(name) \
struct maple_tree name = MTREE_INIT(name, 0)
#define mtree_lock(mt) spin_lock((&(mt)->ma_lock))
#define mtree_lock_nested(mas, subclass) \
spin_lock_nested((&(mt)->ma_lock), subclass)
#define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock))
/*
* The Maple Tree squeezes various bits in at various points which aren't
* necessarily obvious. Usually, this is done by observing that pointers are
* N-byte aligned and thus the bottom log_2(N) bits are available for use. We
* don't use the high bits of pointers to store additional information because
* we don't know what bits are unused on any given architecture.
*
* Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8
* low bits for our own purposes. Nodes are currently of 4 types:
* 1. Single pointer (Range is 0-0)
* 2. Non-leaf Allocation Range nodes
* 3. Non-leaf Range nodes
* 4. Leaf Range nodes All nodes consist of a number of node slots,
* pivots, and a parent pointer.
*/
struct maple_node {
union {
struct {
struct maple_pnode *parent;
void __rcu *slot[MAPLE_NODE_SLOTS];
};
struct {
void *pad;
struct rcu_head rcu;
struct maple_enode *piv_parent;
unsigned char parent_slot;
enum maple_type type;
unsigned char slot_len;
unsigned int ma_flags;
};
struct maple_range_64 mr64;
struct maple_arange_64 ma64;
struct maple_alloc alloc;
};
};
/*
* More complicated stores can cause two nodes to become one or three and
* potentially alter the height of the tree. Either half of the tree may need
* to be rebalanced against the other. The ma_topiary struct is used to track
* which nodes have been 'cut' from the tree so that the change can be done
* safely at a later date. This is done to support RCU.
*/
struct ma_topiary {
struct maple_enode *head;
struct maple_enode *tail;
struct maple_tree *mtree;
};
void *mtree_load(struct maple_tree *mt, unsigned long index);
int mtree_insert(struct maple_tree *mt, unsigned long index,
void *entry, gfp_t gfp);
int mtree_insert_range(struct maple_tree *mt, unsigned long first,
unsigned long last, void *entry, gfp_t gfp);
int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp);
int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long range_lo, unsigned long range_hi,
unsigned long *next, gfp_t gfp);
int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp);
int mtree_store_range(struct maple_tree *mt, unsigned long first,
unsigned long last, void *entry, gfp_t gfp);
int mtree_store(struct maple_tree *mt, unsigned long index,
void *entry, gfp_t gfp);
void *mtree_erase(struct maple_tree *mt, unsigned long index);
int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
void mtree_destroy(struct maple_tree *mt);
void __mt_destroy(struct maple_tree *mt);
/**
* mtree_empty() - Determine if a tree has any present entries.
* @mt: Maple Tree.
*
* Context: Any context.
* Return: %true if the tree contains only NULL pointers.
*/
static inline bool mtree_empty(const struct maple_tree *mt)
{
return mt->ma_root == NULL;
}
/* Advanced API */
/*
* Maple State Status
* ma_active means the maple state is pointing to a node and offset and can
* continue operating on the tree.
* ma_start means we have not searched the tree.
* ma_root means we have searched the tree and the entry we found lives in
* the root of the tree (ie it has index 0, length 1 and is the only entry in
* the tree).
* ma_none means we have searched the tree and there is no node in the
* tree for this entry. For example, we searched for index 1 in an empty
* tree. Or we have a tree which points to a full leaf node and we
* searched for an entry which is larger than can be contained in that
* leaf node.
* ma_pause means the data within the maple state may be stale, restart the
* operation
* ma_overflow means the search has reached the upper limit of the search
* ma_underflow means the search has reached the lower limit of the search
* ma_error means there was an error, check the node for the error number.
*/
enum maple_status {
ma_active,
ma_start,
ma_root,
ma_none,
ma_pause,
ma_overflow,
ma_underflow,
ma_error,
};
/*
* The maple state is defined in the struct ma_state and is used to keep track
* of information during operations, and even between operations when using the
* advanced API.
*
* If state->node has bit 0 set then it references a tree location which is not
* a node (eg the root). If bit 1 is set, the rest of the bits are a negative
* errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the
* node type.
*
* state->alloc either has a request number of nodes or an allocated node. If
* stat->alloc has a requested number of nodes, the first bit will be set (0x1)
* and the remaining bits are the value. If state->alloc is a node, then the
* node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for
* storing more allocated nodes, a total number of nodes allocated, and the
* node_count in this node. node_count is the number of allocated nodes in this
* node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further
* nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc
* by removing a node from the state->alloc node until state->alloc->node_count
* is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted
* to state->alloc. Nodes are pushed onto state->alloc by putting the current
* state->alloc into the pushed node's slot[0].
*
* The state also contains the implied min/max of the state->node, the depth of
* this search, and the offset. The implied min/max are either from the parent
* node or are 0-oo for the root node. The depth is incremented or decremented
* every time a node is walked down or up. The offset is the slot/pivot of
* interest in the node - either for reading or writing.
*
* When returning a value the maple state index and last respectively contain
* the start and end of the range for the entry. Ranges are inclusive in the
* Maple Tree.
*
* The status of the state is used to determine how the next action should treat
* the state. For instance, if the status is ma_start then the next action
* should start at the root of the tree and walk down. If the status is
* ma_pause then the node may be stale data and should be discarded. If the
* status is ma_overflow, then the last action hit the upper limit.
*
*/
struct ma_state {
struct maple_tree *tree; /* The tree we're operating in */
unsigned long index; /* The index we're operating on - range start */
unsigned long last; /* The last index we're operating on - range end */
struct maple_enode *node; /* The node containing this entry */
unsigned long min; /* The minimum index of this node - implied pivot min */
unsigned long max; /* The maximum index of this node - implied pivot max */
struct maple_alloc *alloc; /* Allocated nodes for this operation */
enum maple_status status; /* The status of the state (active, start, none, etc) */
unsigned char depth; /* depth of tree descent during write */
unsigned char offset;
unsigned char mas_flags;
unsigned char end; /* The end of the node */
enum store_type store_type; /* The type of store needed for this operation */
};
struct ma_wr_state {
struct ma_state *mas;
struct maple_node *node; /* Decoded mas->node */
unsigned long r_min; /* range min */
unsigned long r_max; /* range max */
enum maple_type type; /* mas->node type */
unsigned char offset_end; /* The offset where the write ends */
unsigned long *pivots; /* mas->node->pivots pointer */
unsigned long end_piv; /* The pivot at the offset end */
void __rcu **slots; /* mas->node->slots pointer */
void *entry; /* The entry to write */
void *content; /* The existing entry that is being overwritten */
};
#define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock))
#define mas_lock_nested(mas, subclass) \
spin_lock_nested(&((mas)->tree->ma_lock), subclass)
#define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock))
/*
* Special values for ma_state.node.
* MA_ERROR represents an errno. After dropping the lock and attempting
* to resolve the error, the walk would have to be restarted from the
* top of the tree as the tree may have been modified.
*/
#define MA_ERROR(err) \
((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
#define MA_STATE(name, mt, first, end) \
struct ma_state name = { \
.tree = mt, \
.index = first, \
.last = end, \
.node = NULL, \
.status = ma_start, \
.min = 0, \
.max = ULONG_MAX, \
.alloc = NULL, \
.mas_flags = 0, \
.store_type = wr_invalid, \
}
#define MA_WR_STATE(name, ma_state, wr_entry) \
struct ma_wr_state name = { \
.mas = ma_state, \
.content = NULL, \
.entry = wr_entry, \
}
#define MA_TOPIARY(name, tree) \
struct ma_topiary name = { \
.head = NULL, \
.tail = NULL, \
.mtree = tree, \
}
void *mas_walk(struct ma_state *mas);
void *mas_store(struct ma_state *mas, void *entry);
void *mas_erase(struct ma_state *mas);
int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp);
void mas_store_prealloc(struct ma_state *mas, void *entry);
void *mas_find(struct ma_state *mas, unsigned long max);
void *mas_find_range(struct ma_state *mas, unsigned long max);
void *mas_find_rev(struct ma_state *mas, unsigned long min);
void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
void *entry, unsigned long range_lo, unsigned long range_hi,
unsigned long *next, gfp_t gfp);
bool mas_nomem(struct ma_state *mas, gfp_t gfp);
void mas_pause(struct ma_state *mas);
void maple_tree_init(void);
void mas_destroy(struct ma_state *mas);
int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries);
void *mas_prev(struct ma_state *mas, unsigned long min);
void *mas_prev_range(struct ma_state *mas, unsigned long max);
void *mas_next(struct ma_state *mas, unsigned long max);
void *mas_next_range(struct ma_state *mas, unsigned long max);
int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max,
unsigned long size);
/*
* This finds an empty area from the highest address to the lowest.
* AKA "Topdown" version,
*/
int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
unsigned long max, unsigned long size);
static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
unsigned long addr)
{
memset(mas, 0, sizeof(struct ma_state));
mas->tree = tree;
mas->index = mas->last = addr;
mas->max = ULONG_MAX;
mas->status = ma_start;
mas->node = NULL;
}
static inline bool mas_is_active(struct ma_state *mas)
{
return mas->status == ma_active;
}
static inline bool mas_is_err(struct ma_state *mas)
{
return mas->status == ma_error;
}
/**
* mas_reset() - Reset a Maple Tree operation state.
* @mas: Maple Tree operation state.
*
* Resets the error or walk state of the @mas so future walks of the
* array will start from the root. Use this if you have dropped the
* lock and want to reuse the ma_state.
*
* Context: Any context.
*/
static __always_inline void mas_reset(struct ma_state *mas)
{
mas->status = ma_start;
mas->node = NULL;
}
/**
* mas_for_each() - Iterate over a range of the maple tree.
* @__mas: Maple Tree operation state (maple_state)
* @__entry: Entry retrieved from the tree
* @__max: maximum index to retrieve from the tree
*
* When returned, mas->index and mas->last will hold the entire range for the
* entry.
*
* Note: may return the zero entry.
*/
#define mas_for_each(__mas, __entry, __max) \
while (((__entry) = mas_find((__mas), (__max))) != NULL)
/**
* mas_for_each_rev() - Iterate over a range of the maple tree in reverse order.
* @__mas: Maple Tree operation state (maple_state)
* @__entry: Entry retrieved from the tree
* @__min: minimum index to retrieve from the tree
*
* When returned, mas->index and mas->last will hold the entire range for the
* entry.
*
* Note: may return the zero entry.
*/
#define mas_for_each_rev(__mas, __entry, __min) \
while (((__entry) = mas_find_rev((__mas), (__min))) != NULL)
#ifdef CONFIG_DEBUG_MAPLE_TREE
enum mt_dump_format {
mt_dump_dec,
mt_dump_hex,
};
extern atomic_t maple_tree_tests_run;
extern atomic_t maple_tree_tests_passed;
void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
void mas_dump(const struct ma_state *mas);
void mas_wr_dump(const struct ma_wr_state *wr_mas);
void mt_validate(struct maple_tree *mt);
void mt_cache_shrink(void);
#define MT_BUG_ON(__tree, __x) do { \
atomic_inc(&maple_tree_tests_run); \
if (__x) { \
pr_info("BUG at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mt_dump(__tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
} while (0)
#define MAS_BUG_ON(__mas, __x) do { \
atomic_inc(&maple_tree_tests_run); \
if (__x) { \
pr_info("BUG at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mas_dump(__mas); \
mt_dump((__mas)->tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
} while (0)
#define MAS_WR_BUG_ON(__wrmas, __x) do { \
atomic_inc(&maple_tree_tests_run); \
if (__x) { \
pr_info("BUG at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mas_wr_dump(__wrmas); \
mas_dump((__wrmas)->mas); \
mt_dump((__wrmas)->mas->tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
} while (0)
#define MT_WARN_ON(__tree, __x) ({ \
int ret = !!(__x); \
atomic_inc(&maple_tree_tests_run); \
if (ret) { \
pr_info("WARN at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mt_dump(__tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
unlikely(ret); \
})
#define MAS_WARN_ON(__mas, __x) ({ \
int ret = !!(__x); \
atomic_inc(&maple_tree_tests_run); \
if (ret) { \
pr_info("WARN at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mas_dump(__mas); \
mt_dump((__mas)->tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
unlikely(ret); \
})
#define MAS_WR_WARN_ON(__wrmas, __x) ({ \
int ret = !!(__x); \
atomic_inc(&maple_tree_tests_run); \
if (ret) { \
pr_info("WARN at %s:%d (%u)\n", \
__func__, __LINE__, __x); \
mas_wr_dump(__wrmas); \
mas_dump((__wrmas)->mas); \
mt_dump((__wrmas)->mas->tree, mt_dump_hex); \
pr_info("Pass: %u Run:%u\n", \
atomic_read(&maple_tree_tests_passed), \
atomic_read(&maple_tree_tests_run)); \
dump_stack(); \
} else { \
atomic_inc(&maple_tree_tests_passed); \
} \
unlikely(ret); \
})
#else
#define MT_BUG_ON(__tree, __x) BUG_ON(__x)
#define MAS_BUG_ON(__mas, __x) BUG_ON(__x)
#define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x)
#define MT_WARN_ON(__tree, __x) WARN_ON(__x)
#define MAS_WARN_ON(__mas, __x) WARN_ON(__x)
#define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x)
#endif /* CONFIG_DEBUG_MAPLE_TREE */
/**
* __mas_set_range() - Set up Maple Tree operation state to a sub-range of the
* current location.
* @mas: Maple Tree operation state.
* @start: New start of range in the Maple Tree.
* @last: New end of range in the Maple Tree.
*
* set the internal maple state values to a sub-range.
* Please use mas_set_range() if you do not know where you are in the tree.
*/
static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
unsigned long last)
{
/* Ensure the range starts within the current slot */
MAS_WARN_ON(mas, mas_is_active(mas) &&
(mas->index > start || mas->last < start));
mas->index = start;
mas->last = last;
}
/**
* mas_set_range() - Set up Maple Tree operation state for a different index.
* @mas: Maple Tree operation state.
* @start: New start of range in the Maple Tree.
* @last: New end of range in the Maple Tree.
*
* Move the operation state to refer to a different range. This will
* have the effect of starting a walk from the top; see mas_next()
* to move to an adjacent index.
*/
static inline
void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last)
{
mas_reset(mas);
__mas_set_range(mas, start, last);
}
/**
* mas_set() - Set up Maple Tree operation state for a different index.
* @mas: Maple Tree operation state.
* @index: New index into the Maple Tree.
*
* Move the operation state to refer to a different index. This will
* have the effect of starting a walk from the top; see mas_next()
* to move to an adjacent index.
*/
static inline void mas_set(struct ma_state *mas, unsigned long index)
{
mas_set_range(mas, index, index);
}
static inline bool mt_external_lock(const struct maple_tree *mt)
{
return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN;
}
/**
* mt_init_flags() - Initialise an empty maple tree with flags.
* @mt: Maple Tree
* @flags: maple tree flags.
*
* If you need to initialise a Maple Tree with special flags (eg, an
* allocation tree), use this function.
*
* Context: Any context.
*/
static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags)
{
mt->ma_flags = flags;
if (!mt_external_lock(mt)) spin_lock_init(&mt->ma_lock);
rcu_assign_pointer(mt->ma_root, NULL);
}
/**
* mt_init() - Initialise an empty maple tree.
* @mt: Maple Tree
*
* An empty Maple Tree.
*
* Context: Any context.
*/
static inline void mt_init(struct maple_tree *mt)
{
mt_init_flags(mt, 0);
}
static inline bool mt_in_rcu(struct maple_tree *mt)
{
#ifdef CONFIG_MAPLE_RCU_DISABLED
return false;
#endif
return mt->ma_flags & MT_FLAGS_USE_RCU;
}
/**
* mt_clear_in_rcu() - Switch the tree to non-RCU mode.
* @mt: The Maple Tree
*/
static inline void mt_clear_in_rcu(struct maple_tree *mt)
{
if (!mt_in_rcu(mt))
return;
if (mt_external_lock(mt)) {
WARN_ON(!mt_lock_is_held(mt));
mt->ma_flags &= ~MT_FLAGS_USE_RCU;
} else {
mtree_lock(mt);
mt->ma_flags &= ~MT_FLAGS_USE_RCU;
mtree_unlock(mt);
}
}
/**
* mt_set_in_rcu() - Switch the tree to RCU safe mode.
* @mt: The Maple Tree
*/
static inline void mt_set_in_rcu(struct maple_tree *mt)
{
if (mt_in_rcu(mt))
return;
if (mt_external_lock(mt)) {
WARN_ON(!mt_lock_is_held(mt));
mt->ma_flags |= MT_FLAGS_USE_RCU;
} else {
mtree_lock(mt);
mt->ma_flags |= MT_FLAGS_USE_RCU;
mtree_unlock(mt);
}
}
static inline unsigned int mt_height(const struct maple_tree *mt)
{
return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET;
}
void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max);
void *mt_find_after(struct maple_tree *mt, unsigned long *index,
unsigned long max);
void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min);
void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max);
/**
* mt_for_each - Iterate over each entry starting at index until max.
* @__tree: The Maple Tree
* @__entry: The current entry
* @__index: The index to start the search from. Subsequently used as iterator.
* @__max: The maximum limit for @index
*
* This iterator skips all entries, which resolve to a NULL pointer,
* e.g. entries which has been reserved with XA_ZERO_ENTRY.
*/
#define mt_for_each(__tree, __entry, __index, __max) \
for (__entry = mt_find(__tree, &(__index), __max); \
__entry; __entry = mt_find_after(__tree, &(__index), __max))
#endif /*_LINUX_MAPLE_TREE_H */
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/user_namespace.h>
#include <linux/proc_ns.h>
#include <linux/highuid.h>
#include <linux/cred.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/keyctl.h>
#include <linux/key-type.h>
#include <keys/user-type.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include <linux/projid.h>
#include <linux/fs_struct.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
static struct kmem_cache *user_ns_cachep __ro_after_init;
static DEFINE_MUTEX(userns_state_mutex);
static bool new_idmap_permitted(const struct file *file,
struct user_namespace *ns, int cap_setid,
struct uid_gid_map *map);
static void free_user_ns(struct work_struct *work);
static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid)
{
return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES);
}
static void dec_user_namespaces(struct ucounts *ucounts)
{
return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES);
}
static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
{
/* Start with the same capabilities as init but useless for doing
* anything as the capabilities are bound to the new user namespace.
*/
cred->securebits = SECUREBITS_DEFAULT;
cred->cap_inheritable = CAP_EMPTY_SET;
cred->cap_permitted = CAP_FULL_SET;
cred->cap_effective = CAP_FULL_SET;
cred->cap_ambient = CAP_EMPTY_SET;
cred->cap_bset = CAP_FULL_SET;
#ifdef CONFIG_KEYS
key_put(cred->request_key_auth);
cred->request_key_auth = NULL;
#endif
/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
cred->user_ns = user_ns;
}
static unsigned long enforced_nproc_rlimit(void)
{
unsigned long limit = RLIM_INFINITY;
/* Is RLIMIT_NPROC currently enforced? */
if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) ||
(current_user_ns() != &init_user_ns))
limit = rlimit(RLIMIT_NPROC);
return limit;
}
/*
* Create a new user namespace, deriving the creator from the user in the
* passed credentials, and replacing that user with the new root user for the
* new namespace.
*
* This is called by copy_creds(), which will finish setting the target task's
* credentials.
*/
int create_user_ns(struct cred *new)
{
struct user_namespace *ns, *parent_ns = new->user_ns;
kuid_t owner = new->euid;
kgid_t group = new->egid;
struct ucounts *ucounts;
int ret, i;
ret = -ENOSPC;
if (parent_ns->level > 32)
goto fail;
ucounts = inc_user_namespaces(parent_ns, owner);
if (!ucounts)
goto fail;
/*
* Verify that we can not violate the policy of which files
* may be accessed that is specified by the root directory,
* by verifying that the root directory is at the root of the
* mount namespace which allows all files to be accessed.
*/
ret = -EPERM;
if (current_chrooted())
goto fail_dec;
/* The creator needs a mapping in the parent user namespace
* or else we won't be able to reasonably tell userspace who
* created a user_namespace.
*/
ret = -EPERM;
if (!kuid_has_mapping(parent_ns, owner) ||
!kgid_has_mapping(parent_ns, group))
goto fail_dec;
ret = security_create_user_ns(new);
if (ret < 0)
goto fail_dec;
ret = -ENOMEM;
ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
if (!ns)
goto fail_dec;
ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
ret = ns_alloc_inum(&ns->ns);
if (ret)
goto fail_free;
ns->ns.ops = &userns_operations;
refcount_set(&ns->ns.count, 1);
/* Leave the new->user_ns reference with the new user namespace. */
ns->parent = parent_ns;
ns->level = parent_ns->level + 1;
ns->owner = owner;
ns->group = group;
INIT_WORK(&ns->work, free_user_ns);
for (i = 0; i < UCOUNT_COUNTS; i++) {
ns->ucount_max[i] = INT_MAX;
}
set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
ns->ucounts = ucounts;
/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
mutex_lock(&userns_state_mutex);
ns->flags = parent_ns->flags;
mutex_unlock(&userns_state_mutex);
#ifdef CONFIG_KEYS
INIT_LIST_HEAD(&ns->keyring_name_list);
init_rwsem(&ns->keyring_sem);
#endif
ret = -ENOMEM;
if (!setup_userns_sysctls(ns))
goto fail_keyring;
set_cred_user_ns(new, ns);
return 0;
fail_keyring:
#ifdef CONFIG_PERSISTENT_KEYRINGS
key_put(ns->persistent_keyring_register);
#endif
ns_free_inum(&ns->ns);
fail_free:
kmem_cache_free(user_ns_cachep, ns);
fail_dec:
dec_user_namespaces(ucounts);
fail:
return ret;
}
int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
{
struct cred *cred;
int err = -ENOMEM;
if (!(unshare_flags & CLONE_NEWUSER))
return 0;
cred = prepare_creds();
if (cred) {
err = create_user_ns(cred);
if (err)
put_cred(cred);
else
*new_cred = cred;
}
return err;
}
static void free_user_ns(struct work_struct *work)
{
struct user_namespace *parent, *ns =
container_of(work, struct user_namespace, work);
do {
struct ucounts *ucounts = ns->ucounts;
parent = ns->parent;
if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(ns->gid_map.forward);
kfree(ns->gid_map.reverse);
}
if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(ns->uid_map.forward);
kfree(ns->uid_map.reverse);
}
if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(ns->projid_map.forward);
kfree(ns->projid_map.reverse);
}
#if IS_ENABLED(CONFIG_BINFMT_MISC)
kfree(ns->binfmt_misc);
#endif
retire_userns_sysctls(ns);
key_free_user_ns(ns);
ns_free_inum(&ns->ns);
kmem_cache_free(user_ns_cachep, ns);
dec_user_namespaces(ucounts);
ns = parent;
} while (refcount_dec_and_test(&parent->ns.count));
}
void __put_user_ns(struct user_namespace *ns)
{
schedule_work(&ns->work);
}
EXPORT_SYMBOL(__put_user_ns);
/*
* struct idmap_key - holds the information necessary to find an idmapping in a
* sorted idmap array. It is passed to cmp_map_id() as first argument.
*/
struct idmap_key {
bool map_up; /* true -> id from kid; false -> kid from id */
u32 id; /* id to find */
u32 count;
};
/*
* cmp_map_id - Function to be passed to bsearch() to find the requested
* idmapping. Expects struct idmap_key to be passed via @k.
*/
static int cmp_map_id(const void *k, const void *e)
{
u32 first, last, id2;
const struct idmap_key *key = k;
const struct uid_gid_extent *el = e;
id2 = key->id + key->count - 1;
/* handle map_id_{down,up}() */
if (key->map_up)
first = el->lower_first;
else
first = el->first;
last = first + el->count - 1;
if (key->id >= first && key->id <= last &&
(id2 >= first && id2 <= last))
return 0;
if (key->id < first || id2 < first)
return -1;
return 1;
}
/*
* map_id_range_down_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static struct uid_gid_extent *
map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count)
{
struct idmap_key key;
key.map_up = false;
key.count = count;
key.id = id;
return bsearch(&key, map->forward, extents,
sizeof(struct uid_gid_extent), cmp_map_id);
}
/*
* map_id_range_down_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static struct uid_gid_extent *
map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count)
{
unsigned idx;
u32 first, last, id2;
id2 = id + count - 1;
/* Find the matching extent */
for (idx = 0; idx < extents; idx++) {
first = map->extent[idx].first;
last = first + map->extent[idx].count - 1;
if (id >= first && id <= last &&
(id2 >= first && id2 <= last))
return &map->extent[idx];
}
return NULL;
}
static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
{
struct uid_gid_extent *extent;
unsigned extents = map->nr_extents;
smp_rmb();
if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
extent = map_id_range_down_base(extents, map, id, count);
else
extent = map_id_range_down_max(extents, map, id, count);
/* Map the id or note failure */
if (extent) id = (id - extent->first) + extent->lower_first;
else
id = (u32) -1;
return id;
}
u32 map_id_down(struct uid_gid_map *map, u32 id)
{
return map_id_range_down(map, id, 1);
}
/*
* map_id_up_base - Find idmap via binary search in static extent array.
* Can only be called if number of mappings is equal or less than
* UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static struct uid_gid_extent *
map_id_range_up_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count)
{
unsigned idx;
u32 first, last, id2;
id2 = id + count - 1;
/* Find the matching extent */
for (idx = 0; idx < extents; idx++) {
first = map->extent[idx].lower_first;
last = first + map->extent[idx].count - 1;
if (id >= first && id <= last &&
(id2 >= first && id2 <= last))
return &map->extent[idx];
}
return NULL;
}
/*
* map_id_up_max - Find idmap via binary search in ordered idmap array.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static struct uid_gid_extent *
map_id_range_up_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count)
{
struct idmap_key key;
key.map_up = true;
key.count = count;
key.id = id;
return bsearch(&key, map->reverse, extents,
sizeof(struct uid_gid_extent), cmp_map_id);
}
u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count)
{
struct uid_gid_extent *extent;
unsigned extents = map->nr_extents;
smp_rmb();
if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
extent = map_id_range_up_base(extents, map, id, count);
else
extent = map_id_range_up_max(extents, map, id, count);
/* Map the id or note failure */
if (extent) id = (id - extent->lower_first) + extent->first;
else
id = (u32) -1;
return id;
}
u32 map_id_up(struct uid_gid_map *map, u32 id)
{
return map_id_range_up(map, id, 1);
}
/**
* make_kuid - Map a user-namespace uid pair into a kuid.
* @ns: User namespace that the uid is in
* @uid: User identifier
*
* Maps a user-namespace uid pair into a kernel internal kuid,
* and returns that kuid.
*
* When there is no mapping defined for the user-namespace uid
* pair INVALID_UID is returned. Callers are expected to test
* for and handle INVALID_UID being returned. INVALID_UID
* may be tested for using uid_valid().
*/
kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
{
/* Map the uid to a global kernel uid */
return KUIDT_INIT(map_id_down(&ns->uid_map, uid));
}
EXPORT_SYMBOL(make_kuid);
/**
* from_kuid - Create a uid from a kuid user-namespace pair.
* @targ: The user namespace we want a uid in.
* @kuid: The kernel internal uid to start with.
*
* Map @kuid into the user-namespace specified by @targ and
* return the resulting uid.
*
* There is always a mapping into the initial user_namespace.
*
* If @kuid has no mapping in @targ (uid_t)-1 is returned.
*/
uid_t from_kuid(struct user_namespace *targ, kuid_t kuid)
{
/* Map the uid from a global kernel uid */
return map_id_up(&targ->uid_map, __kuid_val(kuid));
}
EXPORT_SYMBOL(from_kuid);
/**
* from_kuid_munged - Create a uid from a kuid user-namespace pair.
* @targ: The user namespace we want a uid in.
* @kuid: The kernel internal uid to start with.
*
* Map @kuid into the user-namespace specified by @targ and
* return the resulting uid.
*
* There is always a mapping into the initial user_namespace.
*
* Unlike from_kuid from_kuid_munged never fails and always
* returns a valid uid. This makes from_kuid_munged appropriate
* for use in syscalls like stat and getuid where failing the
* system call and failing to provide a valid uid are not an
* options.
*
* If @kuid has no mapping in @targ overflowuid is returned.
*/
uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid)
{
uid_t uid;
uid = from_kuid(targ, kuid); if (uid == (uid_t) -1)
uid = overflowuid;
return uid;
}
EXPORT_SYMBOL(from_kuid_munged);
/**
* make_kgid - Map a user-namespace gid pair into a kgid.
* @ns: User namespace that the gid is in
* @gid: group identifier
*
* Maps a user-namespace gid pair into a kernel internal kgid,
* and returns that kgid.
*
* When there is no mapping defined for the user-namespace gid
* pair INVALID_GID is returned. Callers are expected to test
* for and handle INVALID_GID being returned. INVALID_GID may be
* tested for using gid_valid().
*/
kgid_t make_kgid(struct user_namespace *ns, gid_t gid)
{
/* Map the gid to a global kernel gid */
return KGIDT_INIT(map_id_down(&ns->gid_map, gid));
}
EXPORT_SYMBOL(make_kgid);
/**
* from_kgid - Create a gid from a kgid user-namespace pair.
* @targ: The user namespace we want a gid in.
* @kgid: The kernel internal gid to start with.
*
* Map @kgid into the user-namespace specified by @targ and
* return the resulting gid.
*
* There is always a mapping into the initial user_namespace.
*
* If @kgid has no mapping in @targ (gid_t)-1 is returned.
*/
gid_t from_kgid(struct user_namespace *targ, kgid_t kgid)
{
/* Map the gid from a global kernel gid */
return map_id_up(&targ->gid_map, __kgid_val(kgid));
}
EXPORT_SYMBOL(from_kgid);
/**
* from_kgid_munged - Create a gid from a kgid user-namespace pair.
* @targ: The user namespace we want a gid in.
* @kgid: The kernel internal gid to start with.
*
* Map @kgid into the user-namespace specified by @targ and
* return the resulting gid.
*
* There is always a mapping into the initial user_namespace.
*
* Unlike from_kgid from_kgid_munged never fails and always
* returns a valid gid. This makes from_kgid_munged appropriate
* for use in syscalls like stat and getgid where failing the
* system call and failing to provide a valid gid are not options.
*
* If @kgid has no mapping in @targ overflowgid is returned.
*/
gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid)
{
gid_t gid;
gid = from_kgid(targ, kgid); if (gid == (gid_t) -1)
gid = overflowgid;
return gid;
}
EXPORT_SYMBOL(from_kgid_munged);
/**
* make_kprojid - Map a user-namespace projid pair into a kprojid.
* @ns: User namespace that the projid is in
* @projid: Project identifier
*
* Maps a user-namespace uid pair into a kernel internal kuid,
* and returns that kuid.
*
* When there is no mapping defined for the user-namespace projid
* pair INVALID_PROJID is returned. Callers are expected to test
* for and handle INVALID_PROJID being returned. INVALID_PROJID
* may be tested for using projid_valid().
*/
kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid)
{
/* Map the uid to a global kernel uid */
return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid));
}
EXPORT_SYMBOL(make_kprojid);
/**
* from_kprojid - Create a projid from a kprojid user-namespace pair.
* @targ: The user namespace we want a projid in.
* @kprojid: The kernel internal project identifier to start with.
*
* Map @kprojid into the user-namespace specified by @targ and
* return the resulting projid.
*
* There is always a mapping into the initial user_namespace.
*
* If @kprojid has no mapping in @targ (projid_t)-1 is returned.
*/
projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid)
{
/* Map the uid from a global kernel uid */
return map_id_up(&targ->projid_map, __kprojid_val(kprojid));
}
EXPORT_SYMBOL(from_kprojid);
/**
* from_kprojid_munged - Create a projiid from a kprojid user-namespace pair.
* @targ: The user namespace we want a projid in.
* @kprojid: The kernel internal projid to start with.
*
* Map @kprojid into the user-namespace specified by @targ and
* return the resulting projid.
*
* There is always a mapping into the initial user_namespace.
*
* Unlike from_kprojid from_kprojid_munged never fails and always
* returns a valid projid. This makes from_kprojid_munged
* appropriate for use in syscalls like stat and where
* failing the system call and failing to provide a valid projid are
* not an options.
*
* If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned.
*/
projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid)
{
projid_t projid;
projid = from_kprojid(targ, kprojid);
if (projid == (projid_t) -1)
projid = OVERFLOW_PROJID;
return projid;
}
EXPORT_SYMBOL(from_kprojid_munged);
static int uid_m_show(struct seq_file *seq, void *v)
{
struct user_namespace *ns = seq->private;
struct uid_gid_extent *extent = v;
struct user_namespace *lower_ns;
uid_t lower;
lower_ns = seq_user_ns(seq);
if ((lower_ns == ns) && lower_ns->parent)
lower_ns = lower_ns->parent;
lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first));
seq_printf(seq, "%10u %10u %10u\n",
extent->first,
lower,
extent->count);
return 0;
}
static int gid_m_show(struct seq_file *seq, void *v)
{
struct user_namespace *ns = seq->private;
struct uid_gid_extent *extent = v;
struct user_namespace *lower_ns;
gid_t lower;
lower_ns = seq_user_ns(seq);
if ((lower_ns == ns) && lower_ns->parent)
lower_ns = lower_ns->parent;
lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first));
seq_printf(seq, "%10u %10u %10u\n",
extent->first,
lower,
extent->count);
return 0;
}
static int projid_m_show(struct seq_file *seq, void *v)
{
struct user_namespace *ns = seq->private;
struct uid_gid_extent *extent = v;
struct user_namespace *lower_ns;
projid_t lower;
lower_ns = seq_user_ns(seq);
if ((lower_ns == ns) && lower_ns->parent)
lower_ns = lower_ns->parent;
lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first));
seq_printf(seq, "%10u %10u %10u\n",
extent->first,
lower,
extent->count);
return 0;
}
static void *m_start(struct seq_file *seq, loff_t *ppos,
struct uid_gid_map *map)
{
loff_t pos = *ppos;
unsigned extents = map->nr_extents;
smp_rmb();
if (pos >= extents)
return NULL;
if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
return &map->extent[pos];
return &map->forward[pos];
}
static void *uid_m_start(struct seq_file *seq, loff_t *ppos)
{
struct user_namespace *ns = seq->private;
return m_start(seq, ppos, &ns->uid_map);
}
static void *gid_m_start(struct seq_file *seq, loff_t *ppos)
{
struct user_namespace *ns = seq->private;
return m_start(seq, ppos, &ns->gid_map);
}
static void *projid_m_start(struct seq_file *seq, loff_t *ppos)
{
struct user_namespace *ns = seq->private;
return m_start(seq, ppos, &ns->projid_map);
}
static void *m_next(struct seq_file *seq, void *v, loff_t *pos)
{
(*pos)++;
return seq->op->start(seq, pos);
}
static void m_stop(struct seq_file *seq, void *v)
{
return;
}
const struct seq_operations proc_uid_seq_operations = {
.start = uid_m_start,
.stop = m_stop,
.next = m_next,
.show = uid_m_show,
};
const struct seq_operations proc_gid_seq_operations = {
.start = gid_m_start,
.stop = m_stop,
.next = m_next,
.show = gid_m_show,
};
const struct seq_operations proc_projid_seq_operations = {
.start = projid_m_start,
.stop = m_stop,
.next = m_next,
.show = projid_m_show,
};
static bool mappings_overlap(struct uid_gid_map *new_map,
struct uid_gid_extent *extent)
{
u32 upper_first, lower_first, upper_last, lower_last;
unsigned idx;
upper_first = extent->first;
lower_first = extent->lower_first;
upper_last = upper_first + extent->count - 1;
lower_last = lower_first + extent->count - 1;
for (idx = 0; idx < new_map->nr_extents; idx++) {
u32 prev_upper_first, prev_lower_first;
u32 prev_upper_last, prev_lower_last;
struct uid_gid_extent *prev;
if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
prev = &new_map->extent[idx];
else
prev = &new_map->forward[idx];
prev_upper_first = prev->first;
prev_lower_first = prev->lower_first;
prev_upper_last = prev_upper_first + prev->count - 1;
prev_lower_last = prev_lower_first + prev->count - 1;
/* Does the upper range intersect a previous extent? */
if ((prev_upper_first <= upper_last) &&
(prev_upper_last >= upper_first))
return true;
/* Does the lower range intersect a previous extent? */
if ((prev_lower_first <= lower_last) &&
(prev_lower_last >= lower_first))
return true;
}
return false;
}
/*
* insert_extent - Safely insert a new idmap extent into struct uid_gid_map.
* Takes care to allocate a 4K block of memory if the number of mappings exceeds
* UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent)
{
struct uid_gid_extent *dest;
if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) {
struct uid_gid_extent *forward;
/* Allocate memory for 340 mappings. */
forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS,
sizeof(struct uid_gid_extent),
GFP_KERNEL);
if (!forward)
return -ENOMEM;
/* Copy over memory. Only set up memory for the forward pointer.
* Defer the memory setup for the reverse pointer.
*/
memcpy(forward, map->extent,
map->nr_extents * sizeof(map->extent[0]));
map->forward = forward;
map->reverse = NULL;
}
if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS)
dest = &map->extent[map->nr_extents];
else
dest = &map->forward[map->nr_extents];
*dest = *extent;
map->nr_extents++;
return 0;
}
/* cmp function to sort() forward mappings */
static int cmp_extents_forward(const void *a, const void *b)
{
const struct uid_gid_extent *e1 = a;
const struct uid_gid_extent *e2 = b;
if (e1->first < e2->first)
return -1;
if (e1->first > e2->first)
return 1;
return 0;
}
/* cmp function to sort() reverse mappings */
static int cmp_extents_reverse(const void *a, const void *b)
{
const struct uid_gid_extent *e1 = a;
const struct uid_gid_extent *e2 = b;
if (e1->lower_first < e2->lower_first)
return -1;
if (e1->lower_first > e2->lower_first)
return 1;
return 0;
}
/*
* sort_idmaps - Sorts an array of idmap entries.
* Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS.
*/
static int sort_idmaps(struct uid_gid_map *map)
{
if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
return 0;
/* Sort forward array. */
sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent),
cmp_extents_forward, NULL);
/* Only copy the memory from forward we actually need. */
map->reverse = kmemdup_array(map->forward, map->nr_extents,
sizeof(struct uid_gid_extent), GFP_KERNEL);
if (!map->reverse)
return -ENOMEM;
/* Sort reverse array. */
sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent),
cmp_extents_reverse, NULL);
return 0;
}
/**
* verify_root_map() - check the uid 0 mapping
* @file: idmapping file
* @map_ns: user namespace of the target process
* @new_map: requested idmap
*
* If a process requests mapping parent uid 0 into the new ns, verify that the
* process writing the map had the CAP_SETFCAP capability as the target process
* will be able to write fscaps that are valid in ancestor user namespaces.
*
* Return: true if the mapping is allowed, false if not.
*/
static bool verify_root_map(const struct file *file,
struct user_namespace *map_ns,
struct uid_gid_map *new_map)
{
int idx;
const struct user_namespace *file_ns = file->f_cred->user_ns;
struct uid_gid_extent *extent0 = NULL;
for (idx = 0; idx < new_map->nr_extents; idx++) {
if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
extent0 = &new_map->extent[idx];
else
extent0 = &new_map->forward[idx];
if (extent0->lower_first == 0)
break;
extent0 = NULL;
}
if (!extent0)
return true;
if (map_ns == file_ns) {
/* The process unshared its ns and is writing to its own
* /proc/self/uid_map. User already has full capabilites in
* the new namespace. Verify that the parent had CAP_SETFCAP
* when it unshared.
* */
if (!file_ns->parent_could_setfcap)
return false;
} else {
/* Process p1 is writing to uid_map of p2, who is in a child
* user namespace to p1's. Verify that the opener of the map
* file has CAP_SETFCAP against the parent of the new map
* namespace */
if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP))
return false;
}
return true;
}
static ssize_t map_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos,
int cap_setid,
struct uid_gid_map *map,
struct uid_gid_map *parent_map)
{
struct seq_file *seq = file->private_data;
struct user_namespace *map_ns = seq->private;
struct uid_gid_map new_map;
unsigned idx;
struct uid_gid_extent extent;
char *kbuf, *pos, *next_line;
ssize_t ret;
/* Only allow < page size writes at the beginning of the file */
if ((*ppos != 0) || (count >= PAGE_SIZE))
return -EINVAL;
/* Slurp in the user data */
kbuf = memdup_user_nul(buf, count);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
/*
* The userns_state_mutex serializes all writes to any given map.
*
* Any map is only ever written once.
*
* An id map fits within 1 cache line on most architectures.
*
* On read nothing needs to be done unless you are on an
* architecture with a crazy cache coherency model like alpha.
*
* There is a one time data dependency between reading the
* count of the extents and the values of the extents. The
* desired behavior is to see the values of the extents that
* were written before the count of the extents.
*
* To achieve this smp_wmb() is used on guarantee the write
* order and smp_rmb() is guaranteed that we don't have crazy
* architectures returning stale data.
*/
mutex_lock(&userns_state_mutex);
memset(&new_map, 0, sizeof(struct uid_gid_map));
ret = -EPERM;
/* Only allow one successful write to the map */
if (map->nr_extents != 0)
goto out;
/*
* Adjusting namespace settings requires capabilities on the target.
*/
if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN))
goto out;
/* Parse the user data */
ret = -EINVAL;
pos = kbuf;
for (; pos; pos = next_line) {
/* Find the end of line and ensure I don't look past it */
next_line = strchr(pos, '\n');
if (next_line) {
*next_line = '\0';
next_line++;
if (*next_line == '\0')
next_line = NULL;
}
pos = skip_spaces(pos);
extent.first = simple_strtoul(pos, &pos, 10);
if (!isspace(*pos))
goto out;
pos = skip_spaces(pos);
extent.lower_first = simple_strtoul(pos, &pos, 10);
if (!isspace(*pos))
goto out;
pos = skip_spaces(pos);
extent.count = simple_strtoul(pos, &pos, 10);
if (*pos && !isspace(*pos))
goto out;
/* Verify there is not trailing junk on the line */
pos = skip_spaces(pos);
if (*pos != '\0')
goto out;
/* Verify we have been given valid starting values */
if ((extent.first == (u32) -1) ||
(extent.lower_first == (u32) -1))
goto out;
/* Verify count is not zero and does not cause the
* extent to wrap
*/
if ((extent.first + extent.count) <= extent.first)
goto out;
if ((extent.lower_first + extent.count) <=
extent.lower_first)
goto out;
/* Do the ranges in extent overlap any previous extents? */
if (mappings_overlap(&new_map, &extent))
goto out;
if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS &&
(next_line != NULL))
goto out;
ret = insert_extent(&new_map, &extent);
if (ret < 0)
goto out;
ret = -EINVAL;
}
/* Be very certain the new map actually exists */
if (new_map.nr_extents == 0)
goto out;
ret = -EPERM;
/* Validate the user is allowed to use user id's mapped to. */
if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
goto out;
ret = -EPERM;
/* Map the lower ids from the parent user namespace to the
* kernel global id space.
*/
for (idx = 0; idx < new_map.nr_extents; idx++) {
struct uid_gid_extent *e;
u32 lower_first;
if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
e = &new_map.extent[idx];
else
e = &new_map.forward[idx];
lower_first = map_id_range_down(parent_map,
e->lower_first,
e->count);
/* Fail if we can not map the specified extent to
* the kernel global id space.
*/
if (lower_first == (u32) -1)
goto out;
e->lower_first = lower_first;
}
/*
* If we want to use binary search for lookup, this clones the extent
* array and sorts both copies.
*/
ret = sort_idmaps(&new_map);
if (ret < 0)
goto out;
/* Install the map */
if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
memcpy(map->extent, new_map.extent,
new_map.nr_extents * sizeof(new_map.extent[0]));
} else {
map->forward = new_map.forward;
map->reverse = new_map.reverse;
}
smp_wmb();
map->nr_extents = new_map.nr_extents;
*ppos = count;
ret = count;
out:
if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
kfree(new_map.forward);
kfree(new_map.reverse);
map->forward = NULL;
map->reverse = NULL;
map->nr_extents = 0;
}
mutex_unlock(&userns_state_mutex);
kfree(kbuf);
return ret;
}
ssize_t proc_uid_map_write(struct file *file, const char __user *buf,
size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
struct user_namespace *seq_ns = seq_user_ns(seq);
if (!ns->parent)
return -EPERM;
if ((seq_ns != ns) && (seq_ns != ns->parent))
return -EPERM;
return map_write(file, buf, size, ppos, CAP_SETUID,
&ns->uid_map, &ns->parent->uid_map);
}
ssize_t proc_gid_map_write(struct file *file, const char __user *buf,
size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
struct user_namespace *seq_ns = seq_user_ns(seq);
if (!ns->parent)
return -EPERM;
if ((seq_ns != ns) && (seq_ns != ns->parent))
return -EPERM;
return map_write(file, buf, size, ppos, CAP_SETGID,
&ns->gid_map, &ns->parent->gid_map);
}
ssize_t proc_projid_map_write(struct file *file, const char __user *buf,
size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
struct user_namespace *seq_ns = seq_user_ns(seq);
if (!ns->parent)
return -EPERM;
if ((seq_ns != ns) && (seq_ns != ns->parent))
return -EPERM;
/* Anyone can set any valid project id no capability needed */
return map_write(file, buf, size, ppos, -1,
&ns->projid_map, &ns->parent->projid_map);
}
static bool new_idmap_permitted(const struct file *file,
struct user_namespace *ns, int cap_setid,
struct uid_gid_map *new_map)
{
const struct cred *cred = file->f_cred;
if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map))
return false;
/* Don't allow mappings that would allow anything that wouldn't
* be allowed without the establishment of unprivileged mappings.
*/
if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
uid_eq(ns->owner, cred->euid)) {
u32 id = new_map->extent[0].lower_first;
if (cap_setid == CAP_SETUID) {
kuid_t uid = make_kuid(ns->parent, id);
if (uid_eq(uid, cred->euid))
return true;
} else if (cap_setid == CAP_SETGID) {
kgid_t gid = make_kgid(ns->parent, id);
if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
gid_eq(gid, cred->egid))
return true;
}
}
/* Allow anyone to set a mapping that doesn't require privilege */
if (!cap_valid(cap_setid))
return true;
/* Allow the specified ids if we have the appropriate capability
* (CAP_SETUID or CAP_SETGID) over the parent user namespace.
* And the opener of the id file also has the appropriate capability.
*/
if (ns_capable(ns->parent, cap_setid) &&
file_ns_capable(file, ns->parent, cap_setid))
return true;
return false;
}
int proc_setgroups_show(struct seq_file *seq, void *v)
{
struct user_namespace *ns = seq->private;
unsigned long userns_flags = READ_ONCE(ns->flags);
seq_printf(seq, "%s\n",
(userns_flags & USERNS_SETGROUPS_ALLOWED) ?
"allow" : "deny");
return 0;
}
ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
char kbuf[8], *pos;
bool setgroups_allowed;
ssize_t ret;
/* Only allow a very narrow range of strings to be written */
ret = -EINVAL;
if ((*ppos != 0) || (count >= sizeof(kbuf)))
goto out;
/* What was written? */
ret = -EFAULT;
if (copy_from_user(kbuf, buf, count))
goto out;
kbuf[count] = '\0';
pos = kbuf;
/* What is being requested? */
ret = -EINVAL;
if (strncmp(pos, "allow", 5) == 0) {
pos += 5;
setgroups_allowed = true;
}
else if (strncmp(pos, "deny", 4) == 0) {
pos += 4;
setgroups_allowed = false;
}
else
goto out;
/* Verify there is not trailing junk on the line */
pos = skip_spaces(pos);
if (*pos != '\0')
goto out;
ret = -EPERM;
mutex_lock(&userns_state_mutex);
if (setgroups_allowed) {
/* Enabling setgroups after setgroups has been disabled
* is not allowed.
*/
if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
goto out_unlock;
} else {
/* Permanently disabling setgroups after setgroups has
* been enabled by writing the gid_map is not allowed.
*/
if (ns->gid_map.nr_extents != 0)
goto out_unlock;
ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
}
mutex_unlock(&userns_state_mutex);
/* Report a successful write */
*ppos = count;
ret = count;
out:
return ret;
out_unlock:
mutex_unlock(&userns_state_mutex);
goto out;
}
bool userns_may_setgroups(const struct user_namespace *ns)
{
bool allowed;
mutex_lock(&userns_state_mutex);
/* It is not safe to use setgroups until a gid mapping in
* the user namespace has been established.
*/
allowed = ns->gid_map.nr_extents != 0;
/* Is setgroups allowed? */
allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
mutex_unlock(&userns_state_mutex);
return allowed;
}
/*
* Returns true if @child is the same namespace or a descendant of
* @ancestor.
*/
bool in_userns(const struct user_namespace *ancestor,
const struct user_namespace *child)
{
const struct user_namespace *ns;
for (ns = child; ns->level > ancestor->level; ns = ns->parent)
;
return (ns == ancestor);
}
bool current_in_userns(const struct user_namespace *target_ns)
{
return in_userns(target_ns, current_user_ns());
}
EXPORT_SYMBOL(current_in_userns);
static inline struct user_namespace *to_user_ns(struct ns_common *ns)
{
return container_of(ns, struct user_namespace, ns);
}
static struct ns_common *userns_get(struct task_struct *task)
{
struct user_namespace *user_ns;
rcu_read_lock();
user_ns = get_user_ns(__task_cred(task)->user_ns);
rcu_read_unlock();
return user_ns ? &user_ns->ns : NULL;
}
static void userns_put(struct ns_common *ns)
{ put_user_ns(to_user_ns(ns));
}
static int userns_install(struct nsset *nsset, struct ns_common *ns)
{
struct user_namespace *user_ns = to_user_ns(ns);
struct cred *cred;
/* Don't allow gaining capabilities by reentering
* the same user namespace.
*/
if (user_ns == current_user_ns())
return -EINVAL;
/* Tasks that share a thread group must share a user namespace */
if (!thread_group_empty(current))
return -EINVAL;
if (current->fs->users != 1)
return -EINVAL;
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
cred = nsset_cred(nsset);
if (!cred)
return -EINVAL;
put_user_ns(cred->user_ns);
set_cred_user_ns(cred, get_user_ns(user_ns));
if (set_cred_ucounts(cred) < 0)
return -EINVAL;
return 0;
}
struct ns_common *ns_get_owner(struct ns_common *ns)
{
struct user_namespace *my_user_ns = current_user_ns();
struct user_namespace *owner, *p;
/* See if the owner is in the current user namespace */
owner = p = ns->ops->owner(ns);
for (;;) {
if (!p)
return ERR_PTR(-EPERM);
if (p == my_user_ns)
break;
p = p->parent;
}
return &get_user_ns(owner)->ns;
}
static struct user_namespace *userns_owner(struct ns_common *ns)
{
return to_user_ns(ns)->parent;
}
const struct proc_ns_operations userns_operations = {
.name = "user",
.type = CLONE_NEWUSER,
.get = userns_get,
.put = userns_put,
.install = userns_install,
.owner = userns_owner,
.get_parent = ns_get_owner,
};
static __init int user_namespaces_init(void)
{
user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT);
return 0;
}
subsys_initcall(user_namespaces_init);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 - Columbia University and Linaro Ltd.
* Author: Jintack Lim <jintack.lim@linaro.org>
*/
#include <linux/bitfield.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/fixmap.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/sysreg.h>
#include "sys_regs.h"
struct vncr_tlb {
/* The guest's VNCR_EL2 */
u64 gva;
struct s1_walk_info wi;
struct s1_walk_result wr;
u64 hpa;
/* -1 when not mapped on a CPU */
int cpu;
/*
* true if the TLB is valid. Can only be changed with the
* mmu_lock held.
*/
bool valid;
};
/*
* Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
* memory usage and potential number of different sets of S2 PTs in
* the guests. Running out of S2 MMUs only affects performance (we
* will invalidate them more often).
*/
#define S2_MMU_PER_VCPU 2
void kvm_init_nested(struct kvm *kvm)
{
kvm->arch.nested_mmus = NULL;
kvm->arch.nested_mmus_size = 0;
atomic_set(&kvm->arch.vncr_map_count, 0);
}
static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
{
/*
* We only initialise the IPA range on the canonical MMU, which
* defines the contract between KVM and userspace on where the
* "hardware" is in the IPA space. This affects the validity of MMIO
* exits forwarded to userspace, for example.
*
* For nested S2s, we use the PARange as exposed to the guest, as it
* is allowed to use it at will to expose whatever memory map it
* wants to its own guests as it would be on real HW.
*/
return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm));
}
int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_s2_mmu *tmp;
int num_mmus, ret = 0;
if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features) &&
!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
return -EINVAL;
if (!vcpu->arch.ctxt.vncr_array)
vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL_ACCOUNT |
__GFP_ZERO);
if (!vcpu->arch.ctxt.vncr_array)
return -ENOMEM;
/*
* Let's treat memory allocation failures as benign: If we fail to
* allocate anything, return an error and keep the allocated array
* alive. Userspace may try to recover by intializing the vcpu
* again, and there is no reason to affect the whole VM for this.
*/
num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;
tmp = kvrealloc(kvm->arch.nested_mmus,
size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus),
GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!tmp)
return -ENOMEM;
swap(kvm->arch.nested_mmus, tmp);
/*
* If we went through a realocation, adjust the MMU back-pointers in
* the previously initialised kvm_pgtable structures.
*/
if (kvm->arch.nested_mmus != tmp)
for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i];
for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]);
if (ret) {
for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]);
free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
vcpu->arch.ctxt.vncr_array = NULL;
return ret;
}
kvm->arch.nested_mmus_size = num_mmus;
return 0;
}
struct s2_walk_info {
int (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
void *data;
u64 baddr;
unsigned int max_oa_bits;
unsigned int pgshift;
unsigned int sl;
unsigned int t0sz;
bool be;
};
static u32 compute_fsc(int level, u32 fsc)
{
return fsc | (level & 0x3);
}
static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
{
u32 esr;
esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
esr |= compute_fsc(level, fsc);
return esr;
}
static int get_ia_size(struct s2_walk_info *wi)
{
return 64 - wi->t0sz;
}
static int check_base_s2_limits(struct s2_walk_info *wi,
int level, int input_size, int stride)
{
int start_size, ia_size;
ia_size = get_ia_size(wi);
/* Check translation limits */
switch (BIT(wi->pgshift)) {
case SZ_64K:
if (level == 0 || (level == 1 && ia_size <= 42))
return -EFAULT;
break;
case SZ_16K:
if (level == 0 || (level == 1 && ia_size <= 40))
return -EFAULT;
break;
case SZ_4K:
if (level < 0 || (level == 0 && ia_size <= 42))
return -EFAULT;
break;
}
/* Check input size limits */
if (input_size > ia_size)
return -EFAULT;
/* Check number of entries in starting level table */
start_size = input_size - ((3 - level) * stride + wi->pgshift);
if (start_size < 1 || start_size > stride + 4)
return -EFAULT;
return 0;
}
/* Check if output is within boundaries */
static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
{
unsigned int output_size = wi->max_oa_bits;
if (output_size != 48 && (output & GENMASK_ULL(47, output_size)))
return -1;
return 0;
}
/*
* This is essentially a C-version of the pseudo code from the ARM ARM
* AArch64.TranslationTableWalk function. I strongly recommend looking at
* that pseudocode in trying to understand this.
*
* Must be called with the kvm->srcu read lock held
*/
static int walk_nested_s2_pgd(phys_addr_t ipa,
struct s2_walk_info *wi, struct kvm_s2_trans *out)
{
int first_block_level, level, stride, input_size, base_lower_bound;
phys_addr_t base_addr;
unsigned int addr_top, addr_bottom;
u64 desc; /* page table entry */
int ret;
phys_addr_t paddr;
switch (BIT(wi->pgshift)) {
default:
case SZ_64K:
case SZ_16K:
level = 3 - wi->sl;
first_block_level = 2;
break;
case SZ_4K:
level = 2 - wi->sl;
first_block_level = 1;
break;
}
stride = wi->pgshift - 3;
input_size = get_ia_size(wi);
if (input_size > 48 || input_size < 25)
return -EFAULT;
ret = check_base_s2_limits(wi, level, input_size, stride);
if (WARN_ON(ret))
return ret;
base_lower_bound = 3 + input_size - ((3 - level) * stride +
wi->pgshift);
base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
if (check_output_size(wi, base_addr)) {
out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
return 1;
}
addr_top = input_size - 1;
while (1) {
phys_addr_t index;
addr_bottom = (3 - level) * stride + wi->pgshift;
index = (ipa & GENMASK_ULL(addr_top, addr_bottom))
>> (addr_bottom - 3);
paddr = base_addr | index;
ret = wi->read_desc(paddr, &desc, wi->data);
if (ret < 0)
return ret;
/*
* Handle reversedescriptors if endianness differs between the
* host and the guest hypervisor.
*/
if (wi->be)
desc = be64_to_cpu((__force __be64)desc);
else
desc = le64_to_cpu((__force __le64)desc);
/* Check for valid descriptor at this point */
if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) {
out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
out->desc = desc;
return 1;
}
/* We're at the final level or block translation level */
if ((desc & 3) == 1 || level == 3)
break;
if (check_output_size(wi, desc)) {
out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
out->desc = desc;
return 1;
}
base_addr = desc & GENMASK_ULL(47, wi->pgshift);
level += 1;
addr_top = addr_bottom - 1;
}
if (level < first_block_level) {
out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
out->desc = desc;
return 1;
}
if (check_output_size(wi, desc)) {
out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
out->desc = desc;
return 1;
}
if (!(desc & BIT(10))) {
out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS);
out->desc = desc;
return 1;
}
addr_bottom += contiguous_bit_shift(desc, wi, level);
/* Calculate and return the result */
paddr = (desc & GENMASK_ULL(47, addr_bottom)) |
(ipa & GENMASK_ULL(addr_bottom - 1, 0));
out->output = paddr;
out->block_size = 1UL << ((3 - level) * stride + wi->pgshift);
out->readable = desc & (0b01 << 6);
out->writable = desc & (0b10 << 6);
out->level = level;
out->desc = desc;
return 0;
}
static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data)
{
struct kvm_vcpu *vcpu = data;
return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc));
}
static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
{
wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK;
switch (vtcr & VTCR_EL2_TG0_MASK) {
case VTCR_EL2_TG0_4K:
wi->pgshift = 12; break;
case VTCR_EL2_TG0_16K:
wi->pgshift = 14; break;
case VTCR_EL2_TG0_64K:
default: /* IMPDEF: treat any other value as 64k */
wi->pgshift = 16; break;
}
wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
/* Global limit for now, should eventually be per-VM */
wi->max_oa_bits = min(get_kvm_ipa_limit(),
ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr)));
}
int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
struct kvm_s2_trans *result)
{
u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
struct s2_walk_info wi;
int ret;
result->esr = 0;
if (!vcpu_has_nv(vcpu))
return 0;
wi.read_desc = read_guest_s2_desc;
wi.data = vcpu;
wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
vtcr_to_walk_info(vtcr, &wi);
wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE;
ret = walk_nested_s2_pgd(gipa, &wi, result);
if (ret)
result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC);
return ret;
}
static unsigned int ttl_to_size(u8 ttl)
{
int level = ttl & 3;
int gran = (ttl >> 2) & 3;
unsigned int max_size = 0;
switch (gran) {
case TLBI_TTL_TG_4K:
switch (level) {
case 0:
break;
case 1:
max_size = SZ_1G;
break;
case 2:
max_size = SZ_2M;
break;
case 3:
max_size = SZ_4K;
break;
}
break;
case TLBI_TTL_TG_16K:
switch (level) {
case 0:
case 1:
break;
case 2:
max_size = SZ_32M;
break;
case 3:
max_size = SZ_16K;
break;
}
break;
case TLBI_TTL_TG_64K:
switch (level) {
case 0:
case 1:
/* No 52bit IPA support */
break;
case 2:
max_size = SZ_512M;
break;
case 3:
max_size = SZ_64K;
break;
}
break;
default: /* No size information */
break;
}
return max_size;
}
static u8 pgshift_level_to_ttl(u16 shift, u8 level)
{
u8 ttl;
switch(shift) {
case 12:
ttl = TLBI_TTL_TG_4K;
break;
case 14:
ttl = TLBI_TTL_TG_16K;
break;
case 16:
ttl = TLBI_TTL_TG_64K;
break;
default:
BUG();
}
ttl <<= 2;
ttl |= level & 3;
return ttl;
}
/*
* Compute the equivalent of the TTL field by parsing the shadow PT. The
* granule size is extracted from the cached VTCR_EL2.TG0 while the level is
* retrieved from first entry carrying the level as a tag.
*/
static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
{
u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr;
kvm_pte_t pte;
u8 ttl, level;
lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock);
switch (vtcr & VTCR_EL2_TG0_MASK) {
case VTCR_EL2_TG0_4K:
ttl = (TLBI_TTL_TG_4K << 2);
break;
case VTCR_EL2_TG0_16K:
ttl = (TLBI_TTL_TG_16K << 2);
break;
case VTCR_EL2_TG0_64K:
default: /* IMPDEF: treat any other value as 64k */
ttl = (TLBI_TTL_TG_64K << 2);
break;
}
tmp = addr;
again:
/* Iteratively compute the block sizes for a particular granule size */
switch (vtcr & VTCR_EL2_TG0_MASK) {
case VTCR_EL2_TG0_4K:
if (sz < SZ_4K) sz = SZ_4K;
else if (sz < SZ_2M) sz = SZ_2M;
else if (sz < SZ_1G) sz = SZ_1G;
else sz = 0;
break;
case VTCR_EL2_TG0_16K:
if (sz < SZ_16K) sz = SZ_16K;
else if (sz < SZ_32M) sz = SZ_32M;
else sz = 0;
break;
case VTCR_EL2_TG0_64K:
default: /* IMPDEF: treat any other value as 64k */
if (sz < SZ_64K) sz = SZ_64K;
else if (sz < SZ_512M) sz = SZ_512M;
else sz = 0;
break;
}
if (sz == 0)
return 0;
tmp &= ~(sz - 1);
if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
goto again;
if (!(pte & PTE_VALID))
goto again;
level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte);
if (!level)
goto again;
ttl |= level;
/*
* We now have found some level information in the shadow S2. Check
* that the resulting range is actually including the original IPA.
*/
sz = ttl_to_size(ttl);
if (addr < (tmp + sz))
return ttl;
return 0;
}
unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
unsigned long max_size;
u8 ttl;
ttl = FIELD_GET(TLBI_TTL_MASK, val);
if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) {
/* No TTL, check the shadow S2 for a hint */
u64 addr = (val & GENMASK_ULL(35, 0)) << 12;
ttl = get_guest_mapping_ttl(mmu, addr);
}
max_size = ttl_to_size(ttl);
if (!max_size) {
/* Compute the maximum extent of the invalidation */
switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
case VTCR_EL2_TG0_4K:
max_size = SZ_1G;
break;
case VTCR_EL2_TG0_16K:
max_size = SZ_32M;
break;
case VTCR_EL2_TG0_64K:
default: /* IMPDEF: treat any other value as 64k */
/*
* No, we do not support 52bit IPA in nested yet. Once
* we do, this should be 4TB.
*/
max_size = SZ_512M;
break;
}
}
WARN_ON(!max_size);
return max_size;
}
/*
* We can have multiple *different* MMU contexts with the same VMID:
*
* - S2 being enabled or not, hence differing by the HCR_EL2.VM bit
*
* - Multiple vcpus using private S2s (huh huh...), hence differing by the
* VBBTR_EL2.BADDR address
*
* - A combination of the above...
*
* We can always identify which MMU context to pick at run-time. However,
* TLB invalidation involving a VMID must take action on all the TLBs using
* this particular VMID. This translates into applying the same invalidation
* operation to all the contexts that are using this VMID. Moar phun!
*/
void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
const union tlbi_info *info,
void (*tlbi_callback)(struct kvm_s2_mmu *,
const union tlbi_info *))
{
write_lock(&kvm->mmu_lock);
for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (!kvm_s2_mmu_valid(mmu))
continue;
if (vmid == get_vmid(mmu->tlb_vttbr))
tlbi_callback(mmu, info);
}
write_unlock(&kvm->mmu_lock);
}
struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
bool nested_stage2_enabled;
u64 vttbr, vtcr, hcr;
lockdep_assert_held_write(&kvm->mmu_lock);
vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
hcr = vcpu_read_sys_reg(vcpu, HCR_EL2);
nested_stage2_enabled = hcr & HCR_VM;
/* Don't consider the CnP bit for the vttbr match */
vttbr &= ~VTTBR_CNP_BIT;
/*
* Two possibilities when looking up a S2 MMU context:
*
* - either S2 is enabled in the guest, and we need a context that is
* S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR,
* which makes it safe from a TLB conflict perspective (a broken
* guest won't be able to generate them),
*
* - or S2 is disabled, and we need a context that is S2-disabled
* and matches the VMID only, as all TLBs are tagged by VMID even
* if S2 translation is disabled.
*/
for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (!kvm_s2_mmu_valid(mmu))
continue;
if (nested_stage2_enabled &&
mmu->nested_stage2_enabled &&
vttbr == mmu->tlb_vttbr &&
vtcr == mmu->tlb_vtcr)
return mmu;
if (!nested_stage2_enabled &&
!mmu->nested_stage2_enabled &&
get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr))
return mmu;
}
return NULL;
}
static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_s2_mmu *s2_mmu;
int i;
lockdep_assert_held_write(&vcpu->kvm->mmu_lock);
s2_mmu = lookup_s2_mmu(vcpu);
if (s2_mmu)
goto out;
/*
* Make sure we don't always search from the same point, or we
* will always reuse a potentially active context, leaving
* free contexts unused.
*/
for (i = kvm->arch.nested_mmus_next;
i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
i++) {
s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
if (atomic_read(&s2_mmu->refcnt) == 0)
break;
}
BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
/* Set the scene for the next search */
kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
/* Make sure we don't forget to do the laundry */
if (kvm_s2_mmu_valid(s2_mmu))
s2_mmu->pending_unmap = true;
/*
* The virtual VMID (modulo CnP) will be used as a key when matching
* an existing kvm_s2_mmu.
*
* We cache VTCR at allocation time, once and for all. It'd be great
* if the guest didn't screw that one up, as this is not very
* forgiving...
*/
s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT;
s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
out:
atomic_inc(&s2_mmu->refcnt);
/*
* Set the vCPU request to perform an unmap, even if the pending unmap
* originates from another vCPU. This guarantees that the MMU has been
* completely unmapped before any vCPU actually uses it, and allows
* multiple vCPUs to lend a hand with completing the unmap.
*/
if (s2_mmu->pending_unmap)
kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
return s2_mmu;
}
void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
{
/* CnP being set denotes an invalid entry */
mmu->tlb_vttbr = VTTBR_CNP_BIT;
mmu->nested_stage2_enabled = false;
atomic_set(&mmu->refcnt, 0);
}
void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
{
/*
* If the vCPU kept its reference on the MMU after the last put,
* keep rolling with it.
*/
if (is_hyp_ctxt(vcpu)) {
if (!vcpu->arch.hw_mmu)
vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
} else {
if (!vcpu->arch.hw_mmu) {
scoped_guard(write_lock, &vcpu->kvm->mmu_lock)
vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
}
if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV)
kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
}
}
void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
{
/* Unconditionally drop the VNCR mapping if we have one */
if (host_data_test_flag(L1_VNCR_MAPPED)) {
BUG_ON(vcpu->arch.vncr_tlb->cpu != smp_processor_id());
BUG_ON(is_hyp_ctxt(vcpu));
clear_fixmap(vncr_fixmap(vcpu->arch.vncr_tlb->cpu));
vcpu->arch.vncr_tlb->cpu = -1;
host_data_clear_flag(L1_VNCR_MAPPED);
atomic_dec(&vcpu->kvm->arch.vncr_map_count);
}
/*
* Keep a reference on the associated stage-2 MMU if the vCPU is
* scheduling out and not in WFI emulation, suggesting it is likely to
* reuse the MMU sometime soon.
*/
if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
return;
if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
atomic_dec(&vcpu->arch.hw_mmu->refcnt);
vcpu->arch.hw_mmu = NULL;
}
/*
* Returns non-zero if permission fault is handled by injecting it to the next
* level hypervisor.
*/
int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
{
bool forward_fault = false;
trans->esr = 0;
if (!kvm_vcpu_trap_is_permission_fault(vcpu))
return 0;
if (kvm_vcpu_trap_is_iabt(vcpu)) {
forward_fault = !kvm_s2_trans_executable(trans);
} else {
bool write_fault = kvm_is_write_fault(vcpu);
forward_fault = ((write_fault && !trans->writable) ||
(!write_fault && !trans->readable));
}
if (forward_fault)
trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM);
return forward_fault;
}
int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
{
vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2);
vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2);
return kvm_inject_nested_sync(vcpu, esr_el2);
}
static void invalidate_vncr(struct vncr_tlb *vt)
{
vt->valid = false;
if (vt->cpu != -1) clear_fixmap(vncr_fixmap(vt->cpu));
}
static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end)
{
struct kvm_vcpu *vcpu;
unsigned long i;
lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
return;
kvm_for_each_vcpu(i, vcpu, kvm) {
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
u64 ipa_start, ipa_end, ipa_size;
/*
* Careful here: We end-up here from an MMU notifier,
* and this can race against a vcpu not being onlined
* yet, without the pseudo-TLB being allocated.
*
* Skip those, as they obviously don't participate in
* the invalidation at this stage.
*/
if (!vt)
continue;
if (!vt->valid)
continue;
ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
vt->wr.level));
ipa_start = vt->wr.pa & (ipa_size - 1);
ipa_end = ipa_start + ipa_size;
if (ipa_end <= start || ipa_start >= end)
continue;
invalidate_vncr(vt);
}
}
struct s1e2_tlbi_scope {
enum {
TLBI_ALL,
TLBI_VA,
TLBI_VAA,
TLBI_ASID,
} type;
u16 asid;
u64 va;
u64 size;
};
static void invalidate_vncr_va(struct kvm *kvm,
struct s1e2_tlbi_scope *scope)
{
struct kvm_vcpu *vcpu;
unsigned long i;
lockdep_assert_held_write(&kvm->mmu_lock);
kvm_for_each_vcpu(i, vcpu, kvm) {
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
u64 va_start, va_end, va_size;
if (!vt->valid)
continue;
va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
vt->wr.level));
va_start = vt->gva & (va_size - 1);
va_end = va_start + va_size;
switch (scope->type) {
case TLBI_ALL:
break;
case TLBI_VA:
if (va_end <= scope->va ||
va_start >= (scope->va + scope->size))
continue;
if (vt->wr.nG && vt->wr.asid != scope->asid)
continue;
break;
case TLBI_VAA:
if (va_end <= scope->va ||
va_start >= (scope->va + scope->size))
continue;
break;
case TLBI_ASID:
if (!vt->wr.nG || vt->wr.asid != scope->asid)
continue;
break;
}
invalidate_vncr(vt);
}
}
static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val,
struct s1e2_tlbi_scope *scope)
{
switch (inst) {
case OP_TLBI_ALLE2:
case OP_TLBI_ALLE2IS:
case OP_TLBI_ALLE2OS:
case OP_TLBI_VMALLE1:
case OP_TLBI_VMALLE1IS:
case OP_TLBI_VMALLE1OS:
case OP_TLBI_ALLE2NXS:
case OP_TLBI_ALLE2ISNXS:
case OP_TLBI_ALLE2OSNXS:
case OP_TLBI_VMALLE1NXS:
case OP_TLBI_VMALLE1ISNXS:
case OP_TLBI_VMALLE1OSNXS:
scope->type = TLBI_ALL;
break;
case OP_TLBI_VAE2:
case OP_TLBI_VAE2IS:
case OP_TLBI_VAE2OS:
case OP_TLBI_VAE1:
case OP_TLBI_VAE1IS:
case OP_TLBI_VAE1OS:
case OP_TLBI_VAE2NXS:
case OP_TLBI_VAE2ISNXS:
case OP_TLBI_VAE2OSNXS:
case OP_TLBI_VAE1NXS:
case OP_TLBI_VAE1ISNXS:
case OP_TLBI_VAE1OSNXS:
case OP_TLBI_VALE2:
case OP_TLBI_VALE2IS:
case OP_TLBI_VALE2OS:
case OP_TLBI_VALE1:
case OP_TLBI_VALE1IS:
case OP_TLBI_VALE1OS:
case OP_TLBI_VALE2NXS:
case OP_TLBI_VALE2ISNXS:
case OP_TLBI_VALE2OSNXS:
case OP_TLBI_VALE1NXS:
case OP_TLBI_VALE1ISNXS:
case OP_TLBI_VALE1OSNXS:
scope->type = TLBI_VA;
scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
if (!scope->size)
scope->size = SZ_1G;
scope->va = (val << 12) & ~(scope->size - 1);
scope->asid = FIELD_GET(TLBIR_ASID_MASK, val);
break;
case OP_TLBI_ASIDE1:
case OP_TLBI_ASIDE1IS:
case OP_TLBI_ASIDE1OS:
case OP_TLBI_ASIDE1NXS:
case OP_TLBI_ASIDE1ISNXS:
case OP_TLBI_ASIDE1OSNXS:
scope->type = TLBI_ASID;
scope->asid = FIELD_GET(TLBIR_ASID_MASK, val);
break;
case OP_TLBI_VAAE1:
case OP_TLBI_VAAE1IS:
case OP_TLBI_VAAE1OS:
case OP_TLBI_VAAE1NXS:
case OP_TLBI_VAAE1ISNXS:
case OP_TLBI_VAAE1OSNXS:
case OP_TLBI_VAALE1:
case OP_TLBI_VAALE1IS:
case OP_TLBI_VAALE1OS:
case OP_TLBI_VAALE1NXS:
case OP_TLBI_VAALE1ISNXS:
case OP_TLBI_VAALE1OSNXS:
scope->type = TLBI_VAA;
scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
if (!scope->size)
scope->size = SZ_1G;
scope->va = (val << 12) & ~(scope->size - 1);
break;
case OP_TLBI_RVAE2:
case OP_TLBI_RVAE2IS:
case OP_TLBI_RVAE2OS:
case OP_TLBI_RVAE1:
case OP_TLBI_RVAE1IS:
case OP_TLBI_RVAE1OS:
case OP_TLBI_RVAE2NXS:
case OP_TLBI_RVAE2ISNXS:
case OP_TLBI_RVAE2OSNXS:
case OP_TLBI_RVAE1NXS:
case OP_TLBI_RVAE1ISNXS:
case OP_TLBI_RVAE1OSNXS:
case OP_TLBI_RVALE2:
case OP_TLBI_RVALE2IS:
case OP_TLBI_RVALE2OS:
case OP_TLBI_RVALE1:
case OP_TLBI_RVALE1IS:
case OP_TLBI_RVALE1OS:
case OP_TLBI_RVALE2NXS:
case OP_TLBI_RVALE2ISNXS:
case OP_TLBI_RVALE2OSNXS:
case OP_TLBI_RVALE1NXS:
case OP_TLBI_RVALE1ISNXS:
case OP_TLBI_RVALE1OSNXS:
scope->type = TLBI_VA;
scope->va = decode_range_tlbi(val, &scope->size, &scope->asid);
break;
case OP_TLBI_RVAAE1:
case OP_TLBI_RVAAE1IS:
case OP_TLBI_RVAAE1OS:
case OP_TLBI_RVAAE1NXS:
case OP_TLBI_RVAAE1ISNXS:
case OP_TLBI_RVAAE1OSNXS:
case OP_TLBI_RVAALE1:
case OP_TLBI_RVAALE1IS:
case OP_TLBI_RVAALE1OS:
case OP_TLBI_RVAALE1NXS:
case OP_TLBI_RVAALE1ISNXS:
case OP_TLBI_RVAALE1OSNXS:
scope->type = TLBI_VAA;
scope->va = decode_range_tlbi(val, &scope->size, NULL);
break;
}
}
void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val)
{
struct s1e2_tlbi_scope scope = {};
compute_s1_tlbi_range(vcpu, inst, val, &scope);
guard(write_lock)(&vcpu->kvm->mmu_lock);
invalidate_vncr_va(vcpu->kvm, &scope);
}
void kvm_nested_s2_wp(struct kvm *kvm)
{
int i;
lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (kvm_s2_mmu_valid(mmu)) kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu));
}
kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits));
}
void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
{
int i;
lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (kvm_s2_mmu_valid(mmu)) kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
}
kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits));
}
void kvm_nested_s2_flush(struct kvm *kvm)
{
int i;
lockdep_assert_held_write(&kvm->mmu_lock);
for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (kvm_s2_mmu_valid(mmu))
kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu));
}
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
int i;
for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu);
}
kvfree(kvm->arch.nested_mmus);
kvm->arch.nested_mmus = NULL;
kvm->arch.nested_mmus_size = 0;
kvm_uninit_stage2_mmu(kvm);
}
/*
* Dealing with VNCR_EL2 exposed by the *guest* is a complicated matter:
*
* - We introduce an internal representation of a vcpu-private TLB,
* representing the mapping between the guest VA contained in VNCR_EL2,
* the IPA the guest's EL2 PTs point to, and the actual PA this lives at.
*
* - On translation fault from a nested VNCR access, we create such a TLB.
* If there is no mapping to describe, the guest inherits the fault.
* Crucially, no actual mapping is done at this stage.
*
* - On vcpu_load() in a non-HYP context with HCR_EL2.NV==1, if the above
* TLB exists, we map it in the fixmap for this CPU, and run with it. We
* have to respect the permissions dictated by the guest, but not the
* memory type (FWB is a must).
*
* - Note that we usually don't do a vcpu_load() on the back of a fault
* (unless we are preempted), so the resolution of a translation fault
* must go via a request that will map the VNCR page in the fixmap.
* vcpu_load() might as well use the same mechanism.
*
* - On vcpu_put() in a non-HYP context with HCR_EL2.NV==1, if the TLB was
* mapped, we unmap it. Yes it is that simple. The TLB still exists
* though, and may be reused at a later load.
*
* - On permission fault, we simply forward the fault to the guest's EL2.
* Get out of my way.
*
* - On any TLBI for the EL2&0 translation regime, we must find any TLB that
* intersects with the TLBI request, invalidate it, and unmap the page
* from the fixmap. Because we need to look at all the vcpu-private TLBs,
* this requires some wide-ranging locking to ensure that nothing races
* against it. This may require some refcounting to avoid the search when
* no such TLB is present.
*
* - On MMU notifiers, we must invalidate our TLB in a similar way, but
* looking at the IPA instead. The funny part is that there may not be a
* stage-2 mapping for this page if L1 hasn't accessed it using LD/ST
* instructions.
*/
int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu)
{
if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
return 0;
vcpu->arch.vncr_tlb = kzalloc(sizeof(*vcpu->arch.vncr_tlb),
GFP_KERNEL_ACCOUNT);
if (!vcpu->arch.vncr_tlb)
return -ENOMEM;
return 0;
}
static u64 read_vncr_el2(struct kvm_vcpu *vcpu)
{
return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48);
}
static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
{
bool write_fault, writable;
unsigned long mmu_seq;
struct vncr_tlb *vt;
struct page *page;
u64 va, pfn, gfn;
int ret;
vt = vcpu->arch.vncr_tlb;
/*
* If we're about to walk the EL2 S1 PTs, we must invalidate the
* current TLB, as it could be sampled from another vcpu doing a
* TLBI *IS. A real CPU wouldn't do that, but we only keep a single
* translation, so not much of a choice.
*
* We also prepare the next walk wilst we're at it.
*/
scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
invalidate_vncr(vt);
vt->wi = (struct s1_walk_info) {
.regime = TR_EL20,
.as_el0 = false,
.pan = false,
};
vt->wr = (struct s1_walk_result){};
}
guard(srcu)(&vcpu->kvm->srcu);
va = read_vncr_el2(vcpu);
ret = __kvm_translate_va(vcpu, &vt->wi, &vt->wr, va);
if (ret)
return ret;
write_fault = kvm_is_write_fault(vcpu);
mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
gfn = vt->wr.pa >> PAGE_SHIFT;
pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writable, &page);
if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
return -EFAULT;
scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
if (mmu_invalidate_retry(vcpu->kvm, mmu_seq))
return -EAGAIN;
vt->gva = va;
vt->hpa = pfn << PAGE_SHIFT;
vt->valid = true;
vt->cpu = -1;
kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw);
}
if (vt->wr.pw)
mark_page_dirty(vcpu->kvm, gfn);
return 0;
}
static void inject_vncr_perm(struct kvm_vcpu *vcpu)
{
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
u64 esr = kvm_vcpu_get_esr(vcpu);
/* Adjust the fault level to reflect that of the guest's */
esr &= ~ESR_ELx_FSC;
esr |= FIELD_PREP(ESR_ELx_FSC,
ESR_ELx_FSC_PERM_L(vt->wr.level));
kvm_inject_nested_sync(vcpu, esr);
}
static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
{
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
lockdep_assert_held_read(&vcpu->kvm->mmu_lock);
if (!vt->valid)
return false;
if (read_vncr_el2(vcpu) != vt->gva)
return false;
if (vt->wr.nG) {
u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
u64 ttbr = ((tcr & TCR_A1) ?
vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
vcpu_read_sys_reg(vcpu, TTBR0_EL2));
u16 asid;
asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
!(tcr & TCR_ASID16))
asid &= GENMASK(7, 0);
return asid != vt->wr.asid;
}
return true;
}
int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
{
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
u64 esr = kvm_vcpu_get_esr(vcpu);
BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT));
if (esr_fsc_is_permission_fault(esr)) {
inject_vncr_perm(vcpu);
} else if (esr_fsc_is_translation_fault(esr)) {
bool valid;
int ret;
scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
valid = kvm_vncr_tlb_lookup(vcpu);
if (!valid)
ret = kvm_translate_vncr(vcpu);
else
ret = -EPERM;
switch (ret) {
case -EAGAIN:
case -ENOMEM:
/* Let's try again... */
break;
case -EFAULT:
case -EINVAL:
case -ENOENT:
case -EACCES:
/*
* Translation failed, inject the corresponding
* exception back to EL2.
*/
BUG_ON(!vt->wr.failed);
esr &= ~ESR_ELx_FSC;
esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst);
kvm_inject_nested_sync(vcpu, esr);
break;
case -EPERM:
/* Hack to deal with POE until we get kernel support */
inject_vncr_perm(vcpu);
break;
case 0:
break;
}
} else {
WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr);
}
return 1;
}
static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
{
struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
pgprot_t prot;
guard(preempt)();
guard(read_lock)(&vcpu->kvm->mmu_lock);
/*
* The request to map VNCR may have raced against some other
* event, such as an interrupt, and may not be valid anymore.
*/
if (is_hyp_ctxt(vcpu))
return;
/*
* Check that the pseudo-TLB is valid and that VNCR_EL2 still
* contains the expected value. If it doesn't, we simply bail out
* without a mapping -- a transformed MSR/MRS will generate the
* fault and allows us to populate the pseudo-TLB.
*/
if (!vt->valid)
return;
if (read_vncr_el2(vcpu) != vt->gva)
return;
if (vt->wr.nG) {
u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
u64 ttbr = ((tcr & TCR_A1) ?
vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
vcpu_read_sys_reg(vcpu, TTBR0_EL2));
u16 asid;
asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
!(tcr & TCR_ASID16))
asid &= GENMASK(7, 0);
if (asid != vt->wr.asid)
return;
}
vt->cpu = smp_processor_id();
if (vt->wr.pw && vt->wr.pr) prot = PAGE_KERNEL; else if (vt->wr.pr) prot = PAGE_KERNEL_RO;
else
prot = PAGE_NONE;
/*
* We can't map write-only (or no permission at all) in the kernel,
* but the guest can do it if using POE, so we'll have to turn a
* translation fault into a permission fault at runtime.
* FIXME: WO doesn't work at all, need POE support in the kernel.
*/
if (pgprot_val(prot) != pgprot_val(PAGE_NONE)) {
__set_fixmap(vncr_fixmap(vt->cpu), vt->hpa, prot); host_data_set_flag(L1_VNCR_MAPPED); atomic_inc(&vcpu->kvm->arch.vncr_map_count);
}
}
/*
* Our emulated CPU doesn't support all the possible features. For the
* sake of simplicity (and probably mental sanity), wipe out a number
* of feature bits we don't intend to support for the time being.
* This list should get updated as new features get added to the NV
* support, and new extension to the architecture.
*/
u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
{
switch (reg) {
case SYS_ID_AA64ISAR0_EL1:
/* Support everything but TME */
val &= ~ID_AA64ISAR0_EL1_TME;
break;
case SYS_ID_AA64ISAR1_EL1:
/* Support everything but LS64 and Spec Invalidation */
val &= ~(ID_AA64ISAR1_EL1_LS64 |
ID_AA64ISAR1_EL1_SPECRES);
break;
case SYS_ID_AA64PFR0_EL1:
/* No RME, AMU, MPAM, S-EL2, or RAS */
val &= ~(ID_AA64PFR0_EL1_RME |
ID_AA64PFR0_EL1_AMU |
ID_AA64PFR0_EL1_MPAM |
ID_AA64PFR0_EL1_SEL2 |
ID_AA64PFR0_EL1_RAS |
ID_AA64PFR0_EL1_EL3 |
ID_AA64PFR0_EL1_EL2 |
ID_AA64PFR0_EL1_EL1 |
ID_AA64PFR0_EL1_EL0);
/* 64bit only at any EL */
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP);
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP);
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP);
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP);
break;
case SYS_ID_AA64PFR1_EL1:
/* Only support BTI, SSBS, CSV2_frac */
val &= (ID_AA64PFR1_EL1_BT |
ID_AA64PFR1_EL1_SSBS |
ID_AA64PFR1_EL1_CSV2_frac);
break;
case SYS_ID_AA64MMFR0_EL1:
/* Hide ExS, Secure Memory */
val &= ~(ID_AA64MMFR0_EL1_EXS |
ID_AA64MMFR0_EL1_TGRAN4_2 |
ID_AA64MMFR0_EL1_TGRAN16_2 |
ID_AA64MMFR0_EL1_TGRAN64_2 |
ID_AA64MMFR0_EL1_SNSMEM);
/* Hide CNTPOFF if present */
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, ECV, IMP);
/* Disallow unsupported S2 page sizes */
switch (PAGE_SIZE) {
case SZ_64K:
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, NI);
fallthrough;
case SZ_16K:
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, NI);
fallthrough;
case SZ_4K:
/* Support everything */
break;
}
/*
* Since we can't support a guest S2 page size smaller
* than the host's own page size (due to KVM only
* populating its own S2 using the kernel's page
* size), advertise the limitation using FEAT_GTG.
*/
switch (PAGE_SIZE) {
case SZ_4K:
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
fallthrough;
case SZ_16K:
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
fallthrough;
case SZ_64K:
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
break;
}
/* Cap PARange to 48bits */
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, PARANGE, 48);
break;
case SYS_ID_AA64MMFR1_EL1:
val &= (ID_AA64MMFR1_EL1_HCX |
ID_AA64MMFR1_EL1_PAN |
ID_AA64MMFR1_EL1_LO |
ID_AA64MMFR1_EL1_HPDS |
ID_AA64MMFR1_EL1_VH |
ID_AA64MMFR1_EL1_VMIDBits);
/* FEAT_E2H0 implies no VHE */
if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features))
val &= ~ID_AA64MMFR1_EL1_VH;
break;
case SYS_ID_AA64MMFR2_EL1:
val &= ~(ID_AA64MMFR2_EL1_BBM |
ID_AA64MMFR2_EL1_TTL |
GENMASK_ULL(47, 44) |
ID_AA64MMFR2_EL1_ST |
ID_AA64MMFR2_EL1_CCIDX |
ID_AA64MMFR2_EL1_VARange);
/* Force TTL support */
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR2_EL1, TTL, IMP);
break;
case SYS_ID_AA64MMFR4_EL1:
/*
* You get EITHER
*
* - FEAT_VHE without FEAT_E2H0
* - FEAT_NV limited to FEAT_NV2
* - HCR_EL2.NV1 being RES0
*
* OR
*
* - FEAT_E2H0 without FEAT_VHE nor FEAT_NV
*
* Life is too short for anything else.
*/
if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) {
val = 0;
} else {
val = SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY);
val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI_NV1);
}
break;
case SYS_ID_AA64DFR0_EL1:
/* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */
val &= (ID_AA64DFR0_EL1_PMUVer |
ID_AA64DFR0_EL1_WRPs |
ID_AA64DFR0_EL1_BRPs |
ID_AA64DFR0_EL1_DebugVer|
ID_AA64DFR0_EL1_HPMN0);
/* Cap Debug to ARMv8.1 */
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, VHE);
break;
}
return val;
}
u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu,
enum vcpu_sysreg sr, u64 v)
{
struct kvm_sysreg_masks *masks;
masks = vcpu->kvm->arch.sysreg_masks;
if (masks) {
sr -= __SANITISED_REG_START__;
v &= ~masks->mask[sr].res0;
v |= masks->mask[sr].res1;
}
return v;
}
static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
{
int i = sr - __SANITISED_REG_START__;
BUILD_BUG_ON(!__builtin_constant_p(sr));
BUILD_BUG_ON(sr < __SANITISED_REG_START__);
BUILD_BUG_ON(sr >= NR_SYS_REGS);
kvm->arch.sysreg_masks->mask[i].res0 = res0;
kvm->arch.sysreg_masks->mask[i].res1 = res1;
}
int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
u64 res0, res1;
lockdep_assert_held(&kvm->arch.config_lock);
if (kvm->arch.sysreg_masks)
goto out;
kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)),
GFP_KERNEL_ACCOUNT);
if (!kvm->arch.sysreg_masks)
return -ENOMEM;
/* VTTBR_EL2 */
res0 = res1 = 0;
if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16))
res0 |= GENMASK(63, 56);
if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, CnP, IMP))
res0 |= VTTBR_CNP_BIT;
set_sysreg_masks(kvm, VTTBR_EL2, res0, res1);
/* VTCR_EL2 */
res0 = GENMASK(63, 32) | GENMASK(30, 20);
res1 = BIT(31);
set_sysreg_masks(kvm, VTCR_EL2, res0, res1);
/* VMPIDR_EL2 */
res0 = GENMASK(63, 40) | GENMASK(30, 24);
res1 = BIT(31);
set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1);
/* HCR_EL2 */
get_reg_fixed_bits(kvm, HCR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HCR_EL2, res0, res1);
/* HCRX_EL2 */
get_reg_fixed_bits(kvm, HCRX_EL2, &res0, &res1);
set_sysreg_masks(kvm, HCRX_EL2, res0, res1);
/* HFG[RW]TR_EL2 */
get_reg_fixed_bits(kvm, HFGRTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGRTR_EL2, res0, res1);
get_reg_fixed_bits(kvm, HFGWTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGWTR_EL2, res0, res1);
/* HDFG[RW]TR_EL2 */
get_reg_fixed_bits(kvm, HDFGRTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HDFGRTR_EL2, res0, res1);
get_reg_fixed_bits(kvm, HDFGWTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HDFGWTR_EL2, res0, res1);
/* HFGITR_EL2 */
get_reg_fixed_bits(kvm, HFGITR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGITR_EL2, res0, res1);
/* HAFGRTR_EL2 - not a lot to see here */
get_reg_fixed_bits(kvm, HAFGRTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);
/* HFG[RW]TR2_EL2 */
get_reg_fixed_bits(kvm, HFGRTR2_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGRTR2_EL2, res0, res1);
get_reg_fixed_bits(kvm, HFGWTR2_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGWTR2_EL2, res0, res1);
/* HDFG[RW]TR2_EL2 */
get_reg_fixed_bits(kvm, HDFGRTR2_EL2, &res0, &res1);
set_sysreg_masks(kvm, HDFGRTR2_EL2, res0, res1);
get_reg_fixed_bits(kvm, HDFGWTR2_EL2, &res0, &res1);
set_sysreg_masks(kvm, HDFGWTR2_EL2, res0, res1);
/* HFGITR2_EL2 */
get_reg_fixed_bits(kvm, HFGITR2_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGITR2_EL2, res0, res1);
/* TCR2_EL2 */
res0 = TCR2_EL2_RES0;
res1 = TCR2_EL2_RES1;
if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP))
res0 |= (TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1 | TCR2_EL2_D128);
if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, MEC, IMP))
res0 |= TCR2_EL2_AMEC1 | TCR2_EL2_AMEC0;
if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, HAFDBS, HAFT))
res0 |= TCR2_EL2_HAFT;
if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
res0 |= TCR2_EL2_PTTWI | TCR2_EL2_PnCH;
if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP))
res0 |= TCR2_EL2_AIE;
if (!kvm_has_s1poe(kvm))
res0 |= TCR2_EL2_POE | TCR2_EL2_E0POE;
if (!kvm_has_s1pie(kvm))
res0 |= TCR2_EL2_PIE;
if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
res0 |= (TCR2_EL2_E0POE | TCR2_EL2_D128 |
TCR2_EL2_AMEC1 | TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1);
set_sysreg_masks(kvm, TCR2_EL2, res0, res1);
/* SCTLR_EL1 */
res0 = SCTLR_EL1_RES0;
res1 = SCTLR_EL1_RES1;
if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN3))
res0 |= SCTLR_EL1_EPAN;
set_sysreg_masks(kvm, SCTLR_EL1, res0, res1);
/* MDCR_EL2 */
res0 = MDCR_EL2_RES0;
res1 = MDCR_EL2_RES1;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
res0 |= (MDCR_EL2_HPMN | MDCR_EL2_TPMCR |
MDCR_EL2_TPM | MDCR_EL2_HPME);
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP))
res0 |= MDCR_EL2_E2PB | MDCR_EL2_TPMS;
if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, SPMU, IMP))
res0 |= MDCR_EL2_EnSPM;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P1))
res0 |= MDCR_EL2_HPMD;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP))
res0 |= MDCR_EL2_TTRF;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
res0 |= MDCR_EL2_HCCD | MDCR_EL2_HLP;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP))
res0 |= MDCR_EL2_E2TB;
if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP))
res0 |= MDCR_EL2_TDCC;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, MTPMU, IMP) ||
kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP))
res0 |= MDCR_EL2_MTPME;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P7))
res0 |= MDCR_EL2_HPMFZO;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSS, IMP))
res0 |= MDCR_EL2_PMSSE;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2))
res0 |= MDCR_EL2_HPMFZS;
if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, EBEP, IMP))
res0 |= MDCR_EL2_PMEE;
if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, V8P9))
res0 |= MDCR_EL2_EBWE;
if (!kvm_has_feat(kvm, ID_AA64DFR2_EL1, STEP, IMP))
res0 |= MDCR_EL2_EnSTEPOP;
set_sysreg_masks(kvm, MDCR_EL2, res0, res1);
/* CNTHCTL_EL2 */
res0 = GENMASK(63, 20);
res1 = 0;
if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP))
res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK;
if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) {
res0 |= CNTHCTL_ECV;
if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP))
res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT |
CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT);
}
if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
res0 |= GENMASK(11, 8);
set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1);
/* ICH_HCR_EL2 */
res0 = ICH_HCR_EL2_RES0;
res1 = ICH_HCR_EL2_RES1;
if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS))
res0 |= ICH_HCR_EL2_TDIR;
/* No GICv4 is presented to the guest */
res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount;
set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1);
/* VNCR_EL2 */
set_sysreg_masks(kvm, VNCR_EL2, VNCR_EL2_RES0, VNCR_EL2_RES1);
out:
for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
(void)__vcpu_sys_reg(vcpu, sr);
return 0;
}
void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
{ if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
write_lock(&vcpu->kvm->mmu_lock);
if (mmu->pending_unmap) { kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
mmu->pending_unmap = false;
}
write_unlock(&vcpu->kvm->mmu_lock);
}
if (kvm_check_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu)) kvm_map_l1_vncr(vcpu);
/* Must be last, as may switch context! */
if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu))
kvm_inject_nested_irq(vcpu);
}
/* SPDX-License-Identifier: GPL-2.0 */
/*
* generic net pointers
*/
#ifndef __NET_GENERIC_H__
#define __NET_GENERIC_H__
#include <linux/bug.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
/*
* Generic net pointers are to be used by modules to put some private
* stuff on the struct net without explicit struct net modification
*
* The rules are simple:
* 1. set pernet_operations->id. After register_pernet_device you
* will have the id of your private pointer.
* 2. set pernet_operations->size to have the code allocate and free
* a private structure pointed to from struct net.
* 3. do not change this pointer while the net is alive;
* 4. do not try to have any private reference on the net_generic object.
*
* After accomplishing all of the above, the private pointer can be
* accessed with the net_generic() call.
*/
struct net_generic {
union {
struct {
unsigned int len;
struct rcu_head rcu;
} s;
DECLARE_FLEX_ARRAY(void *, ptr);
};
};
static inline void *net_generic(const struct net *net, unsigned int id)
{
struct net_generic *ng;
void *ptr;
rcu_read_lock(); ng = rcu_dereference(net->gen);
ptr = ng->ptr[id];
rcu_read_unlock();
return ptr;
}
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_BIT_SPINLOCK_H
#define __LINUX_BIT_SPINLOCK_H
#include <linux/kernel.h>
#include <linux/preempt.h>
#include <linux/atomic.h>
#include <linux/bug.h>
/*
* bit-based spin_lock()
*
* Don't use this unless you really need to: spin_lock() and spin_unlock()
* are significantly faster.
*/
static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr)
{
/*
* Assuming the lock is uncontended, this never enters
* the body of the outer loop. If it is contended, then
* within the inner loop a non-atomic test is used to
* busywait with less bus contention for a good time to
* attempt to acquire the lock bit.
*/
preempt_disable();
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable();
do {
cpu_relax();
} while (test_bit(bitnum, addr)); preempt_disable();
}
#endif
__acquire(bitlock);
}
/*
* Return true if it was acquired
*/
static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr)
{
preempt_disable();
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
if (unlikely(test_and_set_bit_lock(bitnum, addr))) {
preempt_enable();
return 0;
}
#endif
__acquire(bitlock);
return 1;
}
/*
* bit-based spin_unlock()
*/
static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr)
{
#ifdef CONFIG_DEBUG_SPINLOCK
BUG_ON(!test_bit(bitnum, addr));
#endif
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
clear_bit_unlock(bitnum, addr);
#endif
preempt_enable();
__release(bitlock);
}
/*
* bit-based spin_unlock()
* non-atomic version, which can be used eg. if the bit lock itself is
* protecting the rest of the flags in the word.
*/
static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr)
{
#ifdef CONFIG_DEBUG_SPINLOCK
BUG_ON(!test_bit(bitnum, addr));
#endif
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
__clear_bit_unlock(bitnum, addr);
#endif
preempt_enable();
__release(bitlock);
}
/*
* Return true if the lock is held.
*/
static inline int bit_spin_is_locked(int bitnum, unsigned long *addr)
{
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
return test_bit(bitnum, addr);
#elif defined CONFIG_PREEMPT_COUNT
return preempt_count();
#else
return 1;
#endif
}
#endif /* __LINUX_BIT_SPINLOCK_H */
/* SPDX-License-Identifier: GPL-2.0 */
/*
* include/linux/writeback.h
*/
#ifndef WRITEBACK_H
#define WRITEBACK_H
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
#include <linux/flex_proportions.h>
#include <linux/backing-dev-defs.h>
#include <linux/blk_types.h>
#include <linux/pagevec.h>
struct bio;
DECLARE_PER_CPU(int, dirty_throttle_leaks);
/*
* The global dirty threshold is normally equal to the global dirty limit,
* except when the system suddenly allocates a lot of anonymous memory and
* knocks down the global dirty threshold quickly, in which case the global
* dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
*/
#define DIRTY_SCOPE 8
struct backing_dev_info;
/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
WB_SYNC_NONE, /* Don't wait on anything */
WB_SYNC_ALL, /* Wait on every mapping */
};
/*
* A control structure which tells the writeback code what to do. These are
* always on the stack, and hence need no locking. They are always initialised
* in a manner such that unspecified fields are set to zero.
*/
struct writeback_control {
/* public fields that can be set and/or consumed by the caller: */
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
/*
* For a_ops->writepages(): if start or end are non-zero then this is
* a hint that the filesystem need only write out the pages inside that
* byterange. The byte at `end' is included in the writeout request.
*/
loff_t range_start;
loff_t range_end;
enum writeback_sync_modes sync_mode;
unsigned for_kupdate:1; /* A kupdate writeback */
unsigned for_background:1; /* A background writeback */
unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */
/*
* When writeback IOs are bounced through async layers, only the
* initial synchronous phase should be accounted towards inode
* cgroup ownership arbitration to avoid confusion. Later stages
* can set the following flag to disable the accounting.
*/
unsigned no_cgroup_owner:1;
/* To enable batching of swap writes to non-block-device backends,
* "plug" can be set point to a 'struct swap_iocb *'. When all swap
* writes have been submitted, if with swap_iocb is not NULL,
* swap_write_unplug() should be called.
*/
struct swap_iocb **swap_plug;
/* Target list for splitting a large folio */
struct list_head *list;
/* internal fields used by the ->writepages implementation: */
struct folio_batch fbatch;
pgoff_t index;
int saved_err;
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *wb; /* wb this writeback is issued under */
struct inode *inode; /* inode being written out */
/* foreign inode detection, see wbc_detach_inode() */
int wb_id; /* current wb id */
int wb_lcand_id; /* last foreign candidate wb id */
int wb_tcand_id; /* this foreign candidate wb id */
size_t wb_bytes; /* bytes written by current wb */
size_t wb_lcand_bytes; /* bytes written by last candidate */
size_t wb_tcand_bytes; /* bytes written by this candidate */
#endif
};
static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc)
{
blk_opf_t flags = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
flags |= REQ_SYNC;
else if (wbc->for_kupdate || wbc->for_background)
flags |= REQ_BACKGROUND;
return flags;
}
#ifdef CONFIG_CGROUP_WRITEBACK
#define wbc_blkcg_css(wbc) \
((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css)
#else
#define wbc_blkcg_css(wbc) (blkcg_root_css)
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* A wb_domain represents a domain that wb's (bdi_writeback's) belong to
* and are measured against each other in. There always is one global
* domain, global_wb_domain, that every wb in the system is a member of.
* This allows measuring the relative bandwidth of each wb to distribute
* dirtyable memory accordingly.
*/
struct wb_domain {
spinlock_t lock;
/*
* Scale the writeback cache size proportional to the relative
* writeout speed.
*
* We do this by keeping a floating proportion between BDIs, based
* on page writeback completions [end_page_writeback()]. Those
* devices that write out pages fastest will get the larger share,
* while the slower will get a smaller share.
*
* We use page writeout completions because we are interested in
* getting rid of dirty pages. Having them written out is the
* primary goal.
*
* We introduce a concept of time, a period over which we measure
* these events, because demand can/will vary over time. The length
* of this period itself is measured in page writeback completions.
*/
struct fprop_global completions;
struct timer_list period_timer; /* timer for aging of completions */
unsigned long period_time;
/*
* The dirtyable memory and dirty threshold could be suddenly
* knocked down by a large amount (eg. on the startup of KVM in a
* swapless system). This may throw the system into deep dirty
* exceeded state and throttle heavy/light dirtiers alike. To
* retain good responsiveness, maintain global_dirty_limit for
* tracking slowly down to the knocked down dirty threshold.
*
* Both fields are protected by ->lock.
*/
unsigned long dirty_limit_tstamp;
unsigned long dirty_limit;
};
/**
* wb_domain_size_changed - memory available to a wb_domain has changed
* @dom: wb_domain of interest
*
* This function should be called when the amount of memory available to
* @dom has changed. It resets @dom's dirty limit parameters to prevent
* the past values which don't match the current configuration from skewing
* dirty throttling. Without this, when memory size of a wb_domain is
* greatly reduced, the dirty throttling logic may allow too many pages to
* be dirtied leading to consecutive unnecessary OOMs and may get stuck in
* that situation.
*/
static inline void wb_domain_size_changed(struct wb_domain *dom)
{
spin_lock(&dom->lock);
dom->dirty_limit_tstamp = jiffies;
dom->dirty_limit = 0;
spin_unlock(&dom->lock);
}
/*
* fs/fs-writeback.c
*/
struct bdi_writeback;
void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason);
void sync_inodes_sb(struct super_block *);
void wakeup_flusher_threads(enum wb_reason reason);
void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
void inode_io_list_del(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
wait_var_event(inode_state_wait_address(inode, __I_NEW),
!(READ_ONCE(inode->i_state) & I_NEW));
}
#ifdef CONFIG_CGROUP_WRITEBACK
#include <linux/cgroup.h>
#include <linux/bio.h>
void __inode_attach_wb(struct inode *inode, struct folio *folio);
void wbc_detach_inode(struct writeback_control *wbc);
void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
size_t bytes);
int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
enum wb_reason reason, struct wb_completion *done);
void cgroup_writeback_umount(struct super_block *sb);
bool cleanup_offline_cgwb(struct bdi_writeback *wb);
/**
* inode_attach_wb - associate an inode with its wb
* @inode: inode of interest
* @folio: folio being dirtied (may be NULL)
*
* If @inode doesn't have its wb, associate it with the wb matching the
* memcg of @folio or, if @folio is NULL, %current. May be called w/ or w/o
* @inode->i_lock.
*/
static inline void inode_attach_wb(struct inode *inode, struct folio *folio)
{
if (!inode->i_wb) __inode_attach_wb(inode, folio);
}
/**
* inode_detach_wb - disassociate an inode from its wb
* @inode: inode of interest
*
* @inode is being freed. Detach from its wb.
*/
static inline void inode_detach_wb(struct inode *inode)
{
if (inode->i_wb) { WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); wb_put(inode->i_wb);
inode->i_wb = NULL;
}
}
void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode);
/**
* wbc_init_bio - writeback specific initializtion of bio
* @wbc: writeback_control for the writeback in progress
* @bio: bio to be initialized
*
* @bio is a part of the writeback in progress controlled by @wbc. Perform
* writeback specific initialization. This is used to apply the cgroup
* writeback context. Must be called after the bio has been associated with
* a device.
*/
static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
{
/*
* pageout() path doesn't attach @wbc to the inode being written
* out. This is intentional as we don't want the function to block
* behind a slow cgroup. Ultimately, we want pageout() to kick off
* regular writeback instead of writing things out itself.
*/
if (wbc->wb)
bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css);
}
#else /* CONFIG_CGROUP_WRITEBACK */
static inline void inode_attach_wb(struct inode *inode, struct folio *folio)
{
}
static inline void inode_detach_wb(struct inode *inode)
{
}
static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode)
{
}
static inline void wbc_detach_inode(struct writeback_control *wbc)
{
}
static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
{
}
static inline void wbc_account_cgroup_owner(struct writeback_control *wbc,
struct folio *folio, size_t bytes)
{
}
static inline void cgroup_writeback_umount(struct super_block *sb)
{
}
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
* mm/page-writeback.c
*/
/* consolidated parameters for balance_dirty_pages() and its subroutines */
struct dirty_throttle_control {
#ifdef CONFIG_CGROUP_WRITEBACK
struct wb_domain *dom;
struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */
#endif
struct bdi_writeback *wb;
struct fprop_local_percpu *wb_completions;
unsigned long avail; /* dirtyable */
unsigned long dirty; /* file_dirty + write + nfs */
unsigned long thresh; /* dirty threshold */
unsigned long bg_thresh; /* dirty background threshold */
unsigned long limit; /* hard dirty limit */
unsigned long wb_dirty; /* per-wb counterparts */
unsigned long wb_thresh;
unsigned long wb_bg_thresh;
unsigned long pos_ratio;
bool freerun;
bool dirty_exceeded;
};
void laptop_io_completion(struct backing_dev_info *info);
void laptop_sync_completion(void);
void laptop_mode_timer_fn(struct timer_list *t);
bool node_dirty_ok(struct pglist_data *pgdat);
int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
#ifdef CONFIG_CGROUP_WRITEBACK
void wb_domain_exit(struct wb_domain *dom);
#endif
extern struct wb_domain global_wb_domain;
/* These are exported to sysctl. */
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
extern int laptop_mode;
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
unsigned long cgwb_calc_thresh(struct bdi_writeback *wb);
void wb_update_bandwidth(struct bdi_writeback *wb);
/* Invoke balance dirty pages in async mode. */
#define BDP_ASYNC 0x0001
void balance_dirty_pages_ratelimited(struct address_space *mapping);
int balance_dirty_pages_ratelimited_flags(struct address_space *mapping,
unsigned int flags);
bool wb_over_bg_thresh(struct bdi_writeback *wb);
struct folio *writeback_iter(struct address_space *mapping,
struct writeback_control *wbc, struct folio *folio, int *error);
typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc,
void *data);
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio);
bool folio_redirty_for_writepage(struct writeback_control *, struct folio *);
bool redirty_page_for_writepage(struct writeback_control *, struct page *);
void sb_mark_inode_writeback(struct inode *inode);
void sb_clear_inode_writeback(struct inode *inode);
#endif /* WRITEBACK_H */
// SPDX-License-Identifier: GPL-2.0
/*
* security/tomoyo/file.c
*
* Copyright (C) 2005-2011 NTT DATA CORPORATION
*/
#include "common.h"
#include <linux/slab.h>
/*
* Mapping table from "enum tomoyo_path_acl_index" to "enum tomoyo_mac_index".
*/
static const u8 tomoyo_p2mac[TOMOYO_MAX_PATH_OPERATION] = {
[TOMOYO_TYPE_EXECUTE] = TOMOYO_MAC_FILE_EXECUTE,
[TOMOYO_TYPE_READ] = TOMOYO_MAC_FILE_OPEN,
[TOMOYO_TYPE_WRITE] = TOMOYO_MAC_FILE_OPEN,
[TOMOYO_TYPE_APPEND] = TOMOYO_MAC_FILE_OPEN,
[TOMOYO_TYPE_UNLINK] = TOMOYO_MAC_FILE_UNLINK,
[TOMOYO_TYPE_GETATTR] = TOMOYO_MAC_FILE_GETATTR,
[TOMOYO_TYPE_RMDIR] = TOMOYO_MAC_FILE_RMDIR,
[TOMOYO_TYPE_TRUNCATE] = TOMOYO_MAC_FILE_TRUNCATE,
[TOMOYO_TYPE_SYMLINK] = TOMOYO_MAC_FILE_SYMLINK,
[TOMOYO_TYPE_CHROOT] = TOMOYO_MAC_FILE_CHROOT,
[TOMOYO_TYPE_UMOUNT] = TOMOYO_MAC_FILE_UMOUNT,
};
/*
* Mapping table from "enum tomoyo_mkdev_acl_index" to "enum tomoyo_mac_index".
*/
const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION] = {
[TOMOYO_TYPE_MKBLOCK] = TOMOYO_MAC_FILE_MKBLOCK,
[TOMOYO_TYPE_MKCHAR] = TOMOYO_MAC_FILE_MKCHAR,
};
/*
* Mapping table from "enum tomoyo_path2_acl_index" to "enum tomoyo_mac_index".
*/
const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION] = {
[TOMOYO_TYPE_LINK] = TOMOYO_MAC_FILE_LINK,
[TOMOYO_TYPE_RENAME] = TOMOYO_MAC_FILE_RENAME,
[TOMOYO_TYPE_PIVOT_ROOT] = TOMOYO_MAC_FILE_PIVOT_ROOT,
};
/*
* Mapping table from "enum tomoyo_path_number_acl_index" to
* "enum tomoyo_mac_index".
*/
const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION] = {
[TOMOYO_TYPE_CREATE] = TOMOYO_MAC_FILE_CREATE,
[TOMOYO_TYPE_MKDIR] = TOMOYO_MAC_FILE_MKDIR,
[TOMOYO_TYPE_MKFIFO] = TOMOYO_MAC_FILE_MKFIFO,
[TOMOYO_TYPE_MKSOCK] = TOMOYO_MAC_FILE_MKSOCK,
[TOMOYO_TYPE_IOCTL] = TOMOYO_MAC_FILE_IOCTL,
[TOMOYO_TYPE_CHMOD] = TOMOYO_MAC_FILE_CHMOD,
[TOMOYO_TYPE_CHOWN] = TOMOYO_MAC_FILE_CHOWN,
[TOMOYO_TYPE_CHGRP] = TOMOYO_MAC_FILE_CHGRP,
};
/**
* tomoyo_put_name_union - Drop reference on "struct tomoyo_name_union".
*
* @ptr: Pointer to "struct tomoyo_name_union".
*
* Returns nothing.
*/
void tomoyo_put_name_union(struct tomoyo_name_union *ptr)
{
tomoyo_put_group(ptr->group);
tomoyo_put_name(ptr->filename);
}
/**
* tomoyo_compare_name_union - Check whether a name matches "struct tomoyo_name_union" or not.
*
* @name: Pointer to "struct tomoyo_path_info".
* @ptr: Pointer to "struct tomoyo_name_union".
*
* Returns "struct tomoyo_path_info" if @name matches @ptr, NULL otherwise.
*/
const struct tomoyo_path_info *
tomoyo_compare_name_union(const struct tomoyo_path_info *name,
const struct tomoyo_name_union *ptr)
{
if (ptr->group)
return tomoyo_path_matches_group(name, ptr->group); if (tomoyo_path_matches_pattern(name, ptr->filename)) return ptr->filename;
return NULL;
}
/**
* tomoyo_put_number_union - Drop reference on "struct tomoyo_number_union".
*
* @ptr: Pointer to "struct tomoyo_number_union".
*
* Returns nothing.
*/
void tomoyo_put_number_union(struct tomoyo_number_union *ptr)
{
tomoyo_put_group(ptr->group);
}
/**
* tomoyo_compare_number_union - Check whether a value matches "struct tomoyo_number_union" or not.
*
* @value: Number to check.
* @ptr: Pointer to "struct tomoyo_number_union".
*
* Returns true if @value matches @ptr, false otherwise.
*/
bool tomoyo_compare_number_union(const unsigned long value,
const struct tomoyo_number_union *ptr)
{
if (ptr->group)
return tomoyo_number_matches_group(value, value, ptr->group);
return value >= ptr->values[0] && value <= ptr->values[1];
}
/**
* tomoyo_add_slash - Add trailing '/' if needed.
*
* @buf: Pointer to "struct tomoyo_path_info".
*
* Returns nothing.
*
* @buf must be generated by tomoyo_encode() because this function does not
* allocate memory for adding '/'.
*/
static void tomoyo_add_slash(struct tomoyo_path_info *buf)
{
if (buf->is_dir)
return;
/*
* This is OK because tomoyo_encode() reserves space for appending "/".
*/
strcat((char *) buf->name, "/");
tomoyo_fill_path_info(buf);
}
/**
* tomoyo_get_realpath - Get realpath.
*
* @buf: Pointer to "struct tomoyo_path_info".
* @path: Pointer to "struct path".
*
* Returns true on success, false otherwise.
*/
static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path)
{
buf->name = tomoyo_realpath_from_path(path);
if (buf->name) {
tomoyo_fill_path_info(buf);
return true;
}
return false;
}
/**
* tomoyo_audit_path_log - Audit path request log.
*
* @r: Pointer to "struct tomoyo_request_info".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_audit_path_log(struct tomoyo_request_info *r)
{
return tomoyo_supervisor(r, "file %s %s\n", tomoyo_path_keyword
[r->param.path.operation],
r->param.path.filename->name);
}
/**
* tomoyo_audit_path2_log - Audit path/path request log.
*
* @r: Pointer to "struct tomoyo_request_info".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_audit_path2_log(struct tomoyo_request_info *r)
{
return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords
[tomoyo_pp2mac[r->param.path2.operation]],
r->param.path2.filename1->name,
r->param.path2.filename2->name);
}
/**
* tomoyo_audit_mkdev_log - Audit path/number/number/number request log.
*
* @r: Pointer to "struct tomoyo_request_info".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_audit_mkdev_log(struct tomoyo_request_info *r)
{
return tomoyo_supervisor(r, "file %s %s 0%o %u %u\n",
tomoyo_mac_keywords
[tomoyo_pnnn2mac[r->param.mkdev.operation]],
r->param.mkdev.filename->name,
r->param.mkdev.mode, r->param.mkdev.major,
r->param.mkdev.minor);
}
/**
* tomoyo_audit_path_number_log - Audit path/number request log.
*
* @r: Pointer to "struct tomoyo_request_info".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_audit_path_number_log(struct tomoyo_request_info *r)
{
const u8 type = r->param.path_number.operation;
u8 radix;
char buffer[64];
switch (type) {
case TOMOYO_TYPE_CREATE:
case TOMOYO_TYPE_MKDIR:
case TOMOYO_TYPE_MKFIFO:
case TOMOYO_TYPE_MKSOCK:
case TOMOYO_TYPE_CHMOD:
radix = TOMOYO_VALUE_TYPE_OCTAL;
break;
case TOMOYO_TYPE_IOCTL:
radix = TOMOYO_VALUE_TYPE_HEXADECIMAL;
break;
default:
radix = TOMOYO_VALUE_TYPE_DECIMAL;
break;
}
tomoyo_print_ulong(buffer, sizeof(buffer), r->param.path_number.number,
radix);
return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords
[tomoyo_pn2mac[type]],
r->param.path_number.filename->name, buffer);
}
/**
* tomoyo_check_path_acl - Check permission for path operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @ptr: Pointer to "struct tomoyo_acl_info".
*
* Returns true if granted, false otherwise.
*
* To be able to use wildcard for domain transition, this function sets
* matching entry on success. Since the caller holds tomoyo_read_lock(),
* it is safe to set matching entry.
*/
static bool tomoyo_check_path_acl(struct tomoyo_request_info *r,
const struct tomoyo_acl_info *ptr)
{
const struct tomoyo_path_acl *acl = container_of(ptr, typeof(*acl),
head);
if (acl->perm & (1 << r->param.path.operation)) {
r->param.path.matched_path =
tomoyo_compare_name_union(r->param.path.filename,
&acl->name);
return r->param.path.matched_path != NULL;
}
return false;
}
/**
* tomoyo_check_path_number_acl - Check permission for path number operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @ptr: Pointer to "struct tomoyo_acl_info".
*
* Returns true if granted, false otherwise.
*/
static bool tomoyo_check_path_number_acl(struct tomoyo_request_info *r,
const struct tomoyo_acl_info *ptr)
{
const struct tomoyo_path_number_acl *acl =
container_of(ptr, typeof(*acl), head);
return (acl->perm & (1 << r->param.path_number.operation)) && tomoyo_compare_number_union(r->param.path_number.number, &acl->number) && tomoyo_compare_name_union(r->param.path_number.filename,
&acl->name);
}
/**
* tomoyo_check_path2_acl - Check permission for path path operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @ptr: Pointer to "struct tomoyo_acl_info".
*
* Returns true if granted, false otherwise.
*/
static bool tomoyo_check_path2_acl(struct tomoyo_request_info *r,
const struct tomoyo_acl_info *ptr)
{
const struct tomoyo_path2_acl *acl =
container_of(ptr, typeof(*acl), head);
return (acl->perm & (1 << r->param.path2.operation)) &&
tomoyo_compare_name_union(r->param.path2.filename1, &acl->name1)
&& tomoyo_compare_name_union(r->param.path2.filename2,
&acl->name2);
}
/**
* tomoyo_check_mkdev_acl - Check permission for path number number number operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @ptr: Pointer to "struct tomoyo_acl_info".
*
* Returns true if granted, false otherwise.
*/
static bool tomoyo_check_mkdev_acl(struct tomoyo_request_info *r,
const struct tomoyo_acl_info *ptr)
{
const struct tomoyo_mkdev_acl *acl =
container_of(ptr, typeof(*acl), head);
return (acl->perm & (1 << r->param.mkdev.operation)) &&
tomoyo_compare_number_union(r->param.mkdev.mode,
&acl->mode) &&
tomoyo_compare_number_union(r->param.mkdev.major,
&acl->major) &&
tomoyo_compare_number_union(r->param.mkdev.minor,
&acl->minor) &&
tomoyo_compare_name_union(r->param.mkdev.filename,
&acl->name);
}
/**
* tomoyo_same_path_acl - Check for duplicated "struct tomoyo_path_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b except permission bits, false otherwise.
*/
static bool tomoyo_same_path_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_path_acl *p1 = container_of(a, typeof(*p1), head);
const struct tomoyo_path_acl *p2 = container_of(b, typeof(*p2), head);
return tomoyo_same_name_union(&p1->name, &p2->name);
}
/**
* tomoyo_merge_path_acl - Merge duplicated "struct tomoyo_path_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
* @is_delete: True for @a &= ~@b, false for @a |= @b.
*
* Returns true if @a is empty, false otherwise.
*/
static bool tomoyo_merge_path_acl(struct tomoyo_acl_info *a,
struct tomoyo_acl_info *b,
const bool is_delete)
{
u16 * const a_perm = &container_of(a, struct tomoyo_path_acl, head)
->perm;
u16 perm = READ_ONCE(*a_perm);
const u16 b_perm = container_of(b, struct tomoyo_path_acl, head)->perm;
if (is_delete)
perm &= ~b_perm;
else
perm |= b_perm;
WRITE_ONCE(*a_perm, perm);
return !perm;
}
/**
* tomoyo_update_path_acl - Update "struct tomoyo_path_acl" list.
*
* @perm: Permission.
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_update_path_acl(const u16 perm,
struct tomoyo_acl_param *param)
{
struct tomoyo_path_acl e = {
.head.type = TOMOYO_TYPE_PATH_ACL,
.perm = perm
};
int error;
if (!tomoyo_parse_name_union(param, &e.name))
error = -EINVAL;
else
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_path_acl,
tomoyo_merge_path_acl);
tomoyo_put_name_union(&e.name);
return error;
}
/**
* tomoyo_same_mkdev_acl - Check for duplicated "struct tomoyo_mkdev_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b except permission bits, false otherwise.
*/
static bool tomoyo_same_mkdev_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_mkdev_acl *p1 = container_of(a, typeof(*p1), head);
const struct tomoyo_mkdev_acl *p2 = container_of(b, typeof(*p2), head);
return tomoyo_same_name_union(&p1->name, &p2->name) &&
tomoyo_same_number_union(&p1->mode, &p2->mode) &&
tomoyo_same_number_union(&p1->major, &p2->major) &&
tomoyo_same_number_union(&p1->minor, &p2->minor);
}
/**
* tomoyo_merge_mkdev_acl - Merge duplicated "struct tomoyo_mkdev_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
* @is_delete: True for @a &= ~@b, false for @a |= @b.
*
* Returns true if @a is empty, false otherwise.
*/
static bool tomoyo_merge_mkdev_acl(struct tomoyo_acl_info *a,
struct tomoyo_acl_info *b,
const bool is_delete)
{
u8 *const a_perm = &container_of(a, struct tomoyo_mkdev_acl,
head)->perm;
u8 perm = READ_ONCE(*a_perm);
const u8 b_perm = container_of(b, struct tomoyo_mkdev_acl, head)
->perm;
if (is_delete)
perm &= ~b_perm;
else
perm |= b_perm;
WRITE_ONCE(*a_perm, perm);
return !perm;
}
/**
* tomoyo_update_mkdev_acl - Update "struct tomoyo_mkdev_acl" list.
*
* @perm: Permission.
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_update_mkdev_acl(const u8 perm,
struct tomoyo_acl_param *param)
{
struct tomoyo_mkdev_acl e = {
.head.type = TOMOYO_TYPE_MKDEV_ACL,
.perm = perm
};
int error;
if (!tomoyo_parse_name_union(param, &e.name) ||
!tomoyo_parse_number_union(param, &e.mode) ||
!tomoyo_parse_number_union(param, &e.major) ||
!tomoyo_parse_number_union(param, &e.minor))
error = -EINVAL;
else
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_mkdev_acl,
tomoyo_merge_mkdev_acl);
tomoyo_put_name_union(&e.name);
tomoyo_put_number_union(&e.mode);
tomoyo_put_number_union(&e.major);
tomoyo_put_number_union(&e.minor);
return error;
}
/**
* tomoyo_same_path2_acl - Check for duplicated "struct tomoyo_path2_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b except permission bits, false otherwise.
*/
static bool tomoyo_same_path2_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_path2_acl *p1 = container_of(a, typeof(*p1), head);
const struct tomoyo_path2_acl *p2 = container_of(b, typeof(*p2), head);
return tomoyo_same_name_union(&p1->name1, &p2->name1) &&
tomoyo_same_name_union(&p1->name2, &p2->name2);
}
/**
* tomoyo_merge_path2_acl - Merge duplicated "struct tomoyo_path2_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
* @is_delete: True for @a &= ~@b, false for @a |= @b.
*
* Returns true if @a is empty, false otherwise.
*/
static bool tomoyo_merge_path2_acl(struct tomoyo_acl_info *a,
struct tomoyo_acl_info *b,
const bool is_delete)
{
u8 * const a_perm = &container_of(a, struct tomoyo_path2_acl, head)
->perm;
u8 perm = READ_ONCE(*a_perm);
const u8 b_perm = container_of(b, struct tomoyo_path2_acl, head)->perm;
if (is_delete)
perm &= ~b_perm;
else
perm |= b_perm;
WRITE_ONCE(*a_perm, perm);
return !perm;
}
/**
* tomoyo_update_path2_acl - Update "struct tomoyo_path2_acl" list.
*
* @perm: Permission.
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_update_path2_acl(const u8 perm,
struct tomoyo_acl_param *param)
{
struct tomoyo_path2_acl e = {
.head.type = TOMOYO_TYPE_PATH2_ACL,
.perm = perm
};
int error;
if (!tomoyo_parse_name_union(param, &e.name1) ||
!tomoyo_parse_name_union(param, &e.name2))
error = -EINVAL;
else
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_path2_acl,
tomoyo_merge_path2_acl);
tomoyo_put_name_union(&e.name1);
tomoyo_put_name_union(&e.name2);
return error;
}
/**
* tomoyo_path_permission - Check permission for single path operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @operation: Type of operation.
* @filename: Filename to check.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation,
const struct tomoyo_path_info *filename)
{
int error;
r->type = tomoyo_p2mac[operation];
r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type);
if (r->mode == TOMOYO_CONFIG_DISABLED)
return 0;
r->param_type = TOMOYO_TYPE_PATH_ACL;
r->param.path.filename = filename;
r->param.path.operation = operation;
do {
tomoyo_check_acl(r, tomoyo_check_path_acl);
error = tomoyo_audit_path_log(r);
} while (error == TOMOYO_RETRY_REQUEST);
return error;
}
/**
* tomoyo_execute_permission - Check permission for execute operation.
*
* @r: Pointer to "struct tomoyo_request_info".
* @filename: Filename to check.
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
int tomoyo_execute_permission(struct tomoyo_request_info *r,
const struct tomoyo_path_info *filename)
{
/*
* Unlike other permission checks, this check is done regardless of
* profile mode settings in order to check for domain transition
* preference.
*/
r->type = TOMOYO_MAC_FILE_EXECUTE;
r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type);
r->param_type = TOMOYO_TYPE_PATH_ACL;
r->param.path.filename = filename;
r->param.path.operation = TOMOYO_TYPE_EXECUTE;
tomoyo_check_acl(r, tomoyo_check_path_acl);
r->ee->transition = r->matched_acl && r->matched_acl->cond ?
r->matched_acl->cond->transit : NULL;
if (r->mode != TOMOYO_CONFIG_DISABLED)
return tomoyo_audit_path_log(r);
return 0;
}
/**
* tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b except permission bits, false otherwise.
*/
static bool tomoyo_same_path_number_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_path_number_acl *p1 = container_of(a, typeof(*p1),
head);
const struct tomoyo_path_number_acl *p2 = container_of(b, typeof(*p2),
head);
return tomoyo_same_name_union(&p1->name, &p2->name) &&
tomoyo_same_number_union(&p1->number, &p2->number);
}
/**
* tomoyo_merge_path_number_acl - Merge duplicated "struct tomoyo_path_number_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
* @is_delete: True for @a &= ~@b, false for @a |= @b.
*
* Returns true if @a is empty, false otherwise.
*/
static bool tomoyo_merge_path_number_acl(struct tomoyo_acl_info *a,
struct tomoyo_acl_info *b,
const bool is_delete)
{
u8 * const a_perm = &container_of(a, struct tomoyo_path_number_acl,
head)->perm;
u8 perm = READ_ONCE(*a_perm);
const u8 b_perm = container_of(b, struct tomoyo_path_number_acl, head)
->perm;
if (is_delete)
perm &= ~b_perm;
else
perm |= b_perm;
WRITE_ONCE(*a_perm, perm);
return !perm;
}
/**
* tomoyo_update_path_number_acl - Update ioctl/chmod/chown/chgrp ACL.
*
* @perm: Permission.
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*/
static int tomoyo_update_path_number_acl(const u8 perm,
struct tomoyo_acl_param *param)
{
struct tomoyo_path_number_acl e = {
.head.type = TOMOYO_TYPE_PATH_NUMBER_ACL,
.perm = perm
};
int error;
if (!tomoyo_parse_name_union(param, &e.name) ||
!tomoyo_parse_number_union(param, &e.number))
error = -EINVAL;
else
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_path_number_acl,
tomoyo_merge_path_number_acl);
tomoyo_put_name_union(&e.name);
tomoyo_put_number_union(&e.number);
return error;
}
/**
* tomoyo_path_number_perm - Check permission for "create", "mkdir", "mkfifo", "mksock", "ioctl", "chmod", "chown", "chgrp".
*
* @type: Type of operation.
* @path: Pointer to "struct path".
* @number: Number.
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_path_number_perm(const u8 type, const struct path *path,
unsigned long number)
{
struct tomoyo_request_info r;
struct tomoyo_obj_info obj = {
.path1 = { .mnt = path->mnt, .dentry = path->dentry },
};
int error = -ENOMEM;
struct tomoyo_path_info buf;
int idx;
if (tomoyo_init_request_info(&r, NULL, tomoyo_pn2mac[type])
== TOMOYO_CONFIG_DISABLED)
return 0;
idx = tomoyo_read_lock();
if (!tomoyo_get_realpath(&buf, path))
goto out;
r.obj = &obj;
if (type == TOMOYO_TYPE_MKDIR) tomoyo_add_slash(&buf);
r.param_type = TOMOYO_TYPE_PATH_NUMBER_ACL;
r.param.path_number.operation = type;
r.param.path_number.filename = &buf;
r.param.path_number.number = number;
do {
tomoyo_check_acl(&r, tomoyo_check_path_number_acl);
error = tomoyo_audit_path_number_log(&r);
} while (error == TOMOYO_RETRY_REQUEST); kfree(buf.name);
out:
tomoyo_read_unlock(idx);
if (r.mode != TOMOYO_CONFIG_ENFORCING)
error = 0;
return error;
}
/**
* tomoyo_check_open_permission - Check permission for "read" and "write".
*
* @domain: Pointer to "struct tomoyo_domain_info".
* @path: Pointer to "struct path".
* @flag: Flags for open().
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
const struct path *path, const int flag)
{
const u8 acc_mode = ACC_MODE(flag);
int error = 0;
struct tomoyo_path_info buf;
struct tomoyo_request_info r;
struct tomoyo_obj_info obj = {
.path1 = { .mnt = path->mnt, .dentry = path->dentry },
};
int idx;
buf.name = NULL;
r.mode = TOMOYO_CONFIG_DISABLED;
idx = tomoyo_read_lock();
if (acc_mode &&
tomoyo_init_request_info(&r, domain, TOMOYO_MAC_FILE_OPEN)
!= TOMOYO_CONFIG_DISABLED) {
if (!tomoyo_get_realpath(&buf, path)) {
error = -ENOMEM;
goto out;
}
r.obj = &obj;
if (acc_mode & MAY_READ) error = tomoyo_path_permission(&r, TOMOYO_TYPE_READ,
&buf);
if (!error && (acc_mode & MAY_WRITE)) error = tomoyo_path_permission(&r, (flag & O_APPEND) ?
TOMOYO_TYPE_APPEND :
TOMOYO_TYPE_WRITE,
&buf);
}
out:
kfree(buf.name);
tomoyo_read_unlock(idx);
if (r.mode != TOMOYO_CONFIG_ENFORCING)
error = 0;
return error;
}
/**
* tomoyo_path_perm - Check permission for "unlink", "rmdir", "truncate", "symlink", "append", "chroot" and "unmount".
*
* @operation: Type of operation.
* @path: Pointer to "struct path".
* @target: Symlink's target if @operation is TOMOYO_TYPE_SYMLINK,
* NULL otherwise.
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target)
{
struct tomoyo_request_info r;
struct tomoyo_obj_info obj = {
.path1 = { .mnt = path->mnt, .dentry = path->dentry },
};
int error;
struct tomoyo_path_info buf;
bool is_enforce;
struct tomoyo_path_info symlink_target;
int idx;
if (tomoyo_init_request_info(&r, NULL, tomoyo_p2mac[operation])
== TOMOYO_CONFIG_DISABLED)
return 0;
is_enforce = (r.mode == TOMOYO_CONFIG_ENFORCING);
error = -ENOMEM;
buf.name = NULL;
idx = tomoyo_read_lock();
if (!tomoyo_get_realpath(&buf, path))
goto out;
r.obj = &obj;
switch (operation) {
case TOMOYO_TYPE_RMDIR:
case TOMOYO_TYPE_CHROOT:
tomoyo_add_slash(&buf);
break;
case TOMOYO_TYPE_SYMLINK:
symlink_target.name = tomoyo_encode(target);
if (!symlink_target.name)
goto out;
tomoyo_fill_path_info(&symlink_target);
obj.symlink_target = &symlink_target;
break;
}
error = tomoyo_path_permission(&r, operation, &buf); if (operation == TOMOYO_TYPE_SYMLINK) kfree(symlink_target.name);
out:
kfree(buf.name);
tomoyo_read_unlock(idx);
if (!is_enforce)
error = 0;
return error;
}
/**
* tomoyo_mkdev_perm - Check permission for "mkblock" and "mkchar".
*
* @operation: Type of operation. (TOMOYO_TYPE_MKCHAR or TOMOYO_TYPE_MKBLOCK)
* @path: Pointer to "struct path".
* @mode: Create mode.
* @dev: Device number.
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_mkdev_perm(const u8 operation, const struct path *path,
const unsigned int mode, unsigned int dev)
{
struct tomoyo_request_info r;
struct tomoyo_obj_info obj = {
.path1 = { .mnt = path->mnt, .dentry = path->dentry },
};
int error = -ENOMEM;
struct tomoyo_path_info buf;
int idx;
if (tomoyo_init_request_info(&r, NULL, tomoyo_pnnn2mac[operation])
== TOMOYO_CONFIG_DISABLED)
return 0;
idx = tomoyo_read_lock();
error = -ENOMEM;
if (tomoyo_get_realpath(&buf, path)) {
r.obj = &obj;
dev = new_decode_dev(dev);
r.param_type = TOMOYO_TYPE_MKDEV_ACL;
r.param.mkdev.filename = &buf;
r.param.mkdev.operation = operation;
r.param.mkdev.mode = mode;
r.param.mkdev.major = MAJOR(dev);
r.param.mkdev.minor = MINOR(dev);
tomoyo_check_acl(&r, tomoyo_check_mkdev_acl);
error = tomoyo_audit_mkdev_log(&r);
kfree(buf.name);
}
tomoyo_read_unlock(idx);
if (r.mode != TOMOYO_CONFIG_ENFORCING)
error = 0;
return error;
}
/**
* tomoyo_path2_perm - Check permission for "rename", "link" and "pivot_root".
*
* @operation: Type of operation.
* @path1: Pointer to "struct path".
* @path2: Pointer to "struct path".
*
* Returns 0 on success, negative value otherwise.
*/
int tomoyo_path2_perm(const u8 operation, const struct path *path1,
const struct path *path2)
{
int error = -ENOMEM;
struct tomoyo_path_info buf1;
struct tomoyo_path_info buf2;
struct tomoyo_request_info r;
struct tomoyo_obj_info obj = {
.path1 = { .mnt = path1->mnt, .dentry = path1->dentry },
.path2 = { .mnt = path2->mnt, .dentry = path2->dentry }
};
int idx;
if (tomoyo_init_request_info(&r, NULL, tomoyo_pp2mac[operation])
== TOMOYO_CONFIG_DISABLED)
return 0;
buf1.name = NULL;
buf2.name = NULL;
idx = tomoyo_read_lock();
if (!tomoyo_get_realpath(&buf1, path1) ||
!tomoyo_get_realpath(&buf2, path2))
goto out;
switch (operation) {
case TOMOYO_TYPE_RENAME:
case TOMOYO_TYPE_LINK:
if (!d_is_dir(path1->dentry))
break;
fallthrough;
case TOMOYO_TYPE_PIVOT_ROOT:
tomoyo_add_slash(&buf1);
tomoyo_add_slash(&buf2);
break;
}
r.obj = &obj;
r.param_type = TOMOYO_TYPE_PATH2_ACL;
r.param.path2.operation = operation;
r.param.path2.filename1 = &buf1;
r.param.path2.filename2 = &buf2;
do {
tomoyo_check_acl(&r, tomoyo_check_path2_acl);
error = tomoyo_audit_path2_log(&r);
} while (error == TOMOYO_RETRY_REQUEST);
out:
kfree(buf1.name);
kfree(buf2.name);
tomoyo_read_unlock(idx);
if (r.mode != TOMOYO_CONFIG_ENFORCING)
error = 0;
return error;
}
/**
* tomoyo_same_mount_acl - Check for duplicated "struct tomoyo_mount_acl" entry.
*
* @a: Pointer to "struct tomoyo_acl_info".
* @b: Pointer to "struct tomoyo_acl_info".
*
* Returns true if @a == @b, false otherwise.
*/
static bool tomoyo_same_mount_acl(const struct tomoyo_acl_info *a,
const struct tomoyo_acl_info *b)
{
const struct tomoyo_mount_acl *p1 = container_of(a, typeof(*p1), head);
const struct tomoyo_mount_acl *p2 = container_of(b, typeof(*p2), head);
return tomoyo_same_name_union(&p1->dev_name, &p2->dev_name) &&
tomoyo_same_name_union(&p1->dir_name, &p2->dir_name) &&
tomoyo_same_name_union(&p1->fs_type, &p2->fs_type) &&
tomoyo_same_number_union(&p1->flags, &p2->flags);
}
/**
* tomoyo_update_mount_acl - Write "struct tomoyo_mount_acl" list.
*
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
static int tomoyo_update_mount_acl(struct tomoyo_acl_param *param)
{
struct tomoyo_mount_acl e = { .head.type = TOMOYO_TYPE_MOUNT_ACL };
int error;
if (!tomoyo_parse_name_union(param, &e.dev_name) ||
!tomoyo_parse_name_union(param, &e.dir_name) ||
!tomoyo_parse_name_union(param, &e.fs_type) ||
!tomoyo_parse_number_union(param, &e.flags))
error = -EINVAL;
else
error = tomoyo_update_domain(&e.head, sizeof(e), param,
tomoyo_same_mount_acl, NULL);
tomoyo_put_name_union(&e.dev_name);
tomoyo_put_name_union(&e.dir_name);
tomoyo_put_name_union(&e.fs_type);
tomoyo_put_number_union(&e.flags);
return error;
}
/**
* tomoyo_write_file - Update file related list.
*
* @param: Pointer to "struct tomoyo_acl_param".
*
* Returns 0 on success, negative value otherwise.
*
* Caller holds tomoyo_read_lock().
*/
int tomoyo_write_file(struct tomoyo_acl_param *param)
{
u16 perm = 0;
u8 type;
const char *operation = tomoyo_read_token(param);
for (type = 0; type < TOMOYO_MAX_PATH_OPERATION; type++)
if (tomoyo_permstr(operation, tomoyo_path_keyword[type]))
perm |= 1 << type;
if (perm)
return tomoyo_update_path_acl(perm, param);
for (type = 0; type < TOMOYO_MAX_PATH2_OPERATION; type++)
if (tomoyo_permstr(operation,
tomoyo_mac_keywords[tomoyo_pp2mac[type]]))
perm |= 1 << type;
if (perm)
return tomoyo_update_path2_acl(perm, param);
for (type = 0; type < TOMOYO_MAX_PATH_NUMBER_OPERATION; type++)
if (tomoyo_permstr(operation,
tomoyo_mac_keywords[tomoyo_pn2mac[type]]))
perm |= 1 << type;
if (perm)
return tomoyo_update_path_number_acl(perm, param);
for (type = 0; type < TOMOYO_MAX_MKDEV_OPERATION; type++)
if (tomoyo_permstr(operation,
tomoyo_mac_keywords[tomoyo_pnnn2mac[type]]))
perm |= 1 << type;
if (perm)
return tomoyo_update_mkdev_acl(perm, param);
if (tomoyo_permstr(operation,
tomoyo_mac_keywords[TOMOYO_MAC_FILE_MOUNT]))
return tomoyo_update_mount_acl(param);
return -EINVAL;
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
#define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
/**
* __ffs - find first bit in word.
* @word: The word to search
*
* Undefined if no bit exists, so code should check against 0 first.
*/
static __always_inline unsigned int __ffs(unsigned long word)
{
return __builtin_ctzl(word);
}
#endif
// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic hugetlb support.
* (C) Nadia Yvette Chambers, April 2004
*/
#include <linux/list.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/compiler.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/memblock.h>
#include <linux/minmax.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
#include <linux/mmdebug.h>
#include <linux/sched/signal.h>
#include <linux/rmap.h>
#include <linux/string_helpers.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <linux/numa.h>
#include <linux/llist.h>
#include <linux/cma.h>
#include <linux/migrate.h>
#include <linux/nospec.h>
#include <linux/delayacct.h>
#include <linux/memory.h>
#include <linux/mm_inline.h>
#include <linux/padata.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/setup.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/node.h>
#include <linux/page_owner.h>
#include "internal.h"
#include "hugetlb_vmemmap.h"
#include "hugetlb_cma.h"
#include <linux/page-isolation.h>
int hugetlb_max_hstate __read_mostly;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];
__initdata struct list_head huge_boot_pages[MAX_NUMNODES];
static unsigned long hstate_boot_nrinvalid[HUGE_MAX_HSTATE] __initdata;
/*
* Due to ordering constraints across the init code for various
* architectures, hugetlb hstate cmdline parameters can't simply
* be early_param. early_param might call the setup function
* before valid hugetlb page sizes are determined, leading to
* incorrect rejection of valid hugepagesz= options.
*
* So, record the parameters early and consume them whenever the
* init code is ready for them, by calling hugetlb_parse_params().
*/
/* one (hugepagesz=,hugepages=) pair per hstate, one default_hugepagesz */
#define HUGE_MAX_CMDLINE_ARGS (2 * HUGE_MAX_HSTATE + 1)
struct hugetlb_cmdline {
char *val;
int (*setup)(char *val);
};
/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;
static bool __initdata parsed_valid_hugepagesz = true;
static bool __initdata parsed_default_hugepagesz;
static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata;
static unsigned long hugepage_allocation_threads __initdata;
static char hstate_cmdline_buf[COMMAND_LINE_SIZE] __initdata;
static int hstate_cmdline_index __initdata;
static struct hugetlb_cmdline hugetlb_params[HUGE_MAX_CMDLINE_ARGS] __initdata;
static int hugetlb_param_index __initdata;
static __init int hugetlb_add_param(char *s, int (*setup)(char *val));
static __init void hugetlb_parse_params(void);
#define hugetlb_early_param(str, func) \
static __init int func##args(char *s) \
{ \
return hugetlb_add_param(s, func); \
} \
early_param(str, func##args)
/*
* Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
* free_huge_pages, and surplus_huge_pages.
*/
__cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock);
/*
* Serializes faults on the same logical page. This is used to
* prevent spurious OOMs when the hugepage pool is fully utilized.
*/
static int num_fault_mutexes __ro_after_init;
struct mutex *hugetlb_fault_mutex_table __ro_after_init;
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
static struct resv_map *vma_resv_map(struct vm_area_struct *vma);
static void hugetlb_free_folio(struct folio *folio)
{
if (folio_test_hugetlb_cma(folio)) {
hugetlb_cma_free_folio(folio);
return;
}
folio_put(folio);
}
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
if (spool->count)
return false;
if (spool->max_hpages != -1)
return spool->used_hpages == 0;
if (spool->min_hpages != -1)
return spool->rsv_hpages == spool->min_hpages;
return true;
}
static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
unsigned long irq_flags)
{
spin_unlock_irqrestore(&spool->lock, irq_flags);
/* If no pages are used, and no other handles to the subpool
* remain, give up any reservations based on minimum size and
* free the subpool */
if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate,
-spool->min_hpages);
kfree(spool);
}
}
struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
long min_hpages)
{
struct hugepage_subpool *spool;
spool = kzalloc(sizeof(*spool), GFP_KERNEL);
if (!spool)
return NULL;
spin_lock_init(&spool->lock);
spool->count = 1;
spool->max_hpages = max_hpages;
spool->hstate = h;
spool->min_hpages = min_hpages;
if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
kfree(spool);
return NULL;
}
spool->rsv_hpages = min_hpages;
return spool;
}
void hugepage_put_subpool(struct hugepage_subpool *spool)
{
unsigned long flags;
spin_lock_irqsave(&spool->lock, flags);
BUG_ON(!spool->count);
spool->count--;
unlock_or_release_subpool(spool, flags);
}
/*
* Subpool accounting for allocating and reserving pages.
* Return -ENOMEM if there are not enough resources to satisfy the
* request. Otherwise, return the number of pages by which the
* global pools must be adjusted (upward). The returned value may
* only be different than the passed value (delta) in the case where
* a subpool minimum size must be maintained.
*/
static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
long delta)
{
long ret = delta;
if (!spool)
return ret;
spin_lock_irq(&spool->lock);
if (spool->max_hpages != -1) { /* maximum size accounting */
if ((spool->used_hpages + delta) <= spool->max_hpages)
spool->used_hpages += delta;
else {
ret = -ENOMEM;
goto unlock_ret;
}
}
/* minimum size accounting */
if (spool->min_hpages != -1 && spool->rsv_hpages) {
if (delta > spool->rsv_hpages) {
/*
* Asking for more reserves than those already taken on
* behalf of subpool. Return difference.
*/
ret = delta - spool->rsv_hpages;
spool->rsv_hpages = 0;
} else {
ret = 0; /* reserves already accounted for */
spool->rsv_hpages -= delta;
}
}
unlock_ret:
spin_unlock_irq(&spool->lock);
return ret;
}
/*
* Subpool accounting for freeing and unreserving pages.
* Return the number of global page reservations that must be dropped.
* The return value may only be different than the passed value (delta)
* in the case where a subpool minimum size must be maintained.
*/
static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
long delta)
{
long ret = delta;
unsigned long flags;
if (!spool)
return delta;
spin_lock_irqsave(&spool->lock, flags);
if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta;
/* minimum size accounting */
if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages)
ret = 0;
else
ret = spool->rsv_hpages + delta - spool->min_hpages;
spool->rsv_hpages += delta;
if (spool->rsv_hpages > spool->min_hpages)
spool->rsv_hpages = spool->min_hpages;
}
/*
* If hugetlbfs_put_super couldn't free spool due to an outstanding
* quota reference, free it now.
*/
unlock_or_release_subpool(spool, flags);
return ret;
}
static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
{
return HUGETLBFS_SB(inode->i_sb)->spool;
}
static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
{
return subpool_inode(file_inode(vma->vm_file));
}
/*
* hugetlb vma_lock helper routines
*/
void hugetlb_vma_lock_read(struct vm_area_struct *vma)
{ if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma);
down_read(&resv_map->rw_sema);
}
}
void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
{ if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma);
up_read(&resv_map->rw_sema);
}
}
void hugetlb_vma_lock_write(struct vm_area_struct *vma)
{
if (__vma_shareable_lock(vma)) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma);
down_write(&resv_map->rw_sema);
}
}
void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
{
if (__vma_shareable_lock(vma)) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma);
up_write(&resv_map->rw_sema);
}
}
int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
{
if (__vma_shareable_lock(vma)) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
return down_write_trylock(&vma_lock->rw_sema);
} else if (__vma_private_lock(vma)) {
struct resv_map *resv_map = vma_resv_map(vma);
return down_write_trylock(&resv_map->rw_sema);
}
return 1;
}
void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
{ if (__vma_shareable_lock(vma)) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) {
struct resv_map *resv_map = vma_resv_map(vma);
lockdep_assert_held(&resv_map->rw_sema);
}
}
void hugetlb_vma_lock_release(struct kref *kref)
{
struct hugetlb_vma_lock *vma_lock = container_of(kref,
struct hugetlb_vma_lock, refs);
kfree(vma_lock);
}
static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock)
{
struct vm_area_struct *vma = vma_lock->vma;
/*
* vma_lock structure may or not be released as a result of put,
* it certainly will no longer be attached to vma so clear pointer.
* Semaphore synchronizes access to vma_lock->vma field.
*/
vma_lock->vma = NULL;
vma->vm_private_data = NULL;
up_write(&vma_lock->rw_sema);
kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
}
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma)
{
if (__vma_shareable_lock(vma)) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
__hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma);
/* no free for anon vmas, but still need to unlock */
up_write(&resv_map->rw_sema);
}
}
static void hugetlb_vma_lock_free(struct vm_area_struct *vma)
{
/*
* Only present in sharable vmas.
*/
if (!vma || !__vma_shareable_lock(vma))
return;
if (vma->vm_private_data) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
down_write(&vma_lock->rw_sema);
__hugetlb_vma_unlock_write_put(vma_lock);
}
}
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
{
struct hugetlb_vma_lock *vma_lock;
/* Only establish in (flags) sharable vmas */
if (!vma || !(vma->vm_flags & VM_MAYSHARE))
return;
/* Should never get here with non-NULL vm_private_data */
if (vma->vm_private_data)
return;
vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL);
if (!vma_lock) {
/*
* If we can not allocate structure, then vma can not
* participate in pmd sharing. This is only a possible
* performance enhancement and memory saving issue.
* However, the lock is also used to synchronize page
* faults with truncation. If the lock is not present,
* unlikely races could leave pages in a file past i_size
* until the file is removed. Warn in the unlikely case of
* allocation failure.
*/
pr_warn_once("HugeTLB: unable to allocate vma specific lock\n");
return;
}
kref_init(&vma_lock->refs);
init_rwsem(&vma_lock->rw_sema);
vma_lock->vma = vma;
vma->vm_private_data = vma_lock;
}
/* Helper that removes a struct file_region from the resv_map cache and returns
* it for use.
*/
static struct file_region *
get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
{
struct file_region *nrg;
VM_BUG_ON(resv->region_cache_count <= 0);
resv->region_cache_count--;
nrg = list_first_entry(&resv->region_cache, struct file_region, link);
list_del(&nrg->link);
nrg->from = from;
nrg->to = to;
return nrg;
}
static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg,
struct file_region *rg)
{
#ifdef CONFIG_CGROUP_HUGETLB
nrg->reservation_counter = rg->reservation_counter;
nrg->css = rg->css;
if (rg->css) css_get(rg->css);
#endif
}
/* Helper that records hugetlb_cgroup uncharge info. */
static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
struct hstate *h,
struct resv_map *resv,
struct file_region *nrg)
{
#ifdef CONFIG_CGROUP_HUGETLB
if (h_cg) {
nrg->reservation_counter =
&h_cg->rsvd_hugepage[hstate_index(h)];
nrg->css = &h_cg->css;
/*
* The caller will hold exactly one h_cg->css reference for the
* whole contiguous reservation region. But this area might be
* scattered when there are already some file_regions reside in
* it. As a result, many file_regions may share only one css
* reference. In order to ensure that one file_region must hold
* exactly one h_cg->css reference, we should do css_get for
* each file_region and leave the reference held by caller
* untouched.
*/
css_get(&h_cg->css);
if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h);
/* pages_per_hpage should be the same for all entries in
* a resv_map.
*/
VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h));
} else {
nrg->reservation_counter = NULL;
nrg->css = NULL;
}
#endif
}
static void put_uncharge_info(struct file_region *rg)
{
#ifdef CONFIG_CGROUP_HUGETLB
if (rg->css) css_put(rg->css);
#endif
}
static bool has_same_uncharge_info(struct file_region *rg,
struct file_region *org)
{
#ifdef CONFIG_CGROUP_HUGETLB
return rg->reservation_counter == org->reservation_counter &&
rg->css == org->css;
#else
return true;
#endif
}
static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
{
struct file_region *nrg, *prg;
prg = list_prev_entry(rg, link);
if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) {
prg->to = rg->to;
list_del(&rg->link); put_uncharge_info(rg);
kfree(rg);
rg = prg;
}
nrg = list_next_entry(rg, link);
if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) {
nrg->from = rg->from;
list_del(&rg->link); put_uncharge_info(rg);
kfree(rg);
}
}
static inline long
hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from,
long to, struct hstate *h, struct hugetlb_cgroup *cg,
long *regions_needed)
{
struct file_region *nrg;
if (!regions_needed) {
nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg);
} else
*regions_needed += 1;
return to - from;
}
/*
* Must be called with resv->lock held.
*
* Calling this with regions_needed != NULL will count the number of pages
* to be added but will not modify the linked list. And regions_needed will
* indicate the number of file_regions needed in the cache to carry out to add
* the regions for this range.
*/
static long add_reservation_in_range(struct resv_map *resv, long f, long t,
struct hugetlb_cgroup *h_cg,
struct hstate *h, long *regions_needed)
{
long add = 0;
struct list_head *head = &resv->regions;
long last_accounted_offset = f;
struct file_region *iter, *trg = NULL;
struct list_head *rg = NULL;
if (regions_needed) *regions_needed = 0;
/* In this loop, we essentially handle an entry for the range
* [last_accounted_offset, iter->from), at every iteration, with some
* bounds checking.
*/
list_for_each_entry_safe(iter, trg, head, link) {
/* Skip irrelevant regions that start before our range. */
if (iter->from < f) {
/* If this region ends after the last accounted offset,
* then we need to update last_accounted_offset.
*/
if (iter->to > last_accounted_offset)
last_accounted_offset = iter->to;
continue;
}
/* When we find a region that starts beyond our range, we've
* finished.
*/
if (iter->from >= t) {
rg = iter->link.prev;
break;
}
/* Add an entry for last_accounted_offset -> iter->from, and
* update last_accounted_offset.
*/
if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev,
last_accounted_offset,
iter->from, h, h_cg,
regions_needed);
last_accounted_offset = iter->to;
}
/* Handle the case where our range extends beyond
* last_accounted_offset.
*/
if (!rg)
rg = head->prev;
if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
t, h, h_cg, regions_needed);
return add;
}
/* Must be called with resv->lock acquired. Will drop lock to allocate entries.
*/
static int allocate_file_region_entries(struct resv_map *resv,
int regions_needed)
__must_hold(&resv->lock)
{
LIST_HEAD(allocated_regions);
int to_allocate = 0, i = 0;
struct file_region *trg = NULL, *rg = NULL;
VM_BUG_ON(regions_needed < 0);
/*
* Check for sufficient descriptors in the cache to accommodate
* the number of in progress add operations plus regions_needed.
*
* This is a while loop because when we drop the lock, some other call
* to region_add or region_del may have consumed some region_entries,
* so we keep looping here until we finally have enough entries for
* (adds_in_progress + regions_needed).
*/
while (resv->region_cache_count <
(resv->adds_in_progress + regions_needed)) {
to_allocate = resv->adds_in_progress + regions_needed -
resv->region_cache_count;
/* At this point, we should have enough entries in the cache
* for all the existing adds_in_progress. We should only be
* needing to allocate for regions_needed.
*/
VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress);
spin_unlock(&resv->lock);
for (i = 0; i < to_allocate; i++) {
trg = kmalloc(sizeof(*trg), GFP_KERNEL);
if (!trg)
goto out_of_memory;
list_add(&trg->link, &allocated_regions);
}
spin_lock(&resv->lock);
list_splice(&allocated_regions, &resv->region_cache);
resv->region_cache_count += to_allocate;
}
return 0;
out_of_memory:
list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link);
kfree(rg);
}
return -ENOMEM;
}
/*
* Add the huge page range represented by [f, t) to the reserve
* map. Regions will be taken from the cache to fill in this range.
* Sufficient regions should exist in the cache due to the previous
* call to region_chg with the same range, but in some cases the cache will not
* have sufficient entries due to races with other code doing region_add or
* region_del. The extra needed entries will be allocated.
*
* regions_needed is the out value provided by a previous call to region_chg.
*
* Return the number of new huge pages added to the map. This number is greater
* than or equal to zero. If file_region entries needed to be allocated for
* this operation and we were not able to allocate, it returns -ENOMEM.
* region_add of regions of length 1 never allocate file_regions and cannot
* fail; region_chg will always allocate at least 1 entry and a region_add for
* 1 page will only require at most 1 entry.
*/
static long region_add(struct resv_map *resv, long f, long t,
long in_regions_needed, struct hstate *h,
struct hugetlb_cgroup *h_cg)
{
long add = 0, actual_regions_needed = 0;
spin_lock(&resv->lock);
retry:
/* Count how many regions are actually needed to execute this add. */
add_reservation_in_range(resv, f, t, NULL, NULL,
&actual_regions_needed);
/*
* Check for sufficient descriptors in the cache to accommodate
* this add operation. Note that actual_regions_needed may be greater
* than in_regions_needed, as the resv_map may have been modified since
* the region_chg call. In this case, we need to make sure that we
* allocate extra entries, such that we have enough for all the
* existing adds_in_progress, plus the excess needed for this
* operation.
*/
if (actual_regions_needed > in_regions_needed &&
resv->region_cache_count <
resv->adds_in_progress +
(actual_regions_needed - in_regions_needed)) {
/* region_add operation of range 1 should never need to
* allocate file_region entries.
*/
VM_BUG_ON(t - f <= 1);
if (allocate_file_region_entries(
resv, actual_regions_needed - in_regions_needed)) {
return -ENOMEM;
}
goto retry;
}
add = add_reservation_in_range(resv, f, t, h_cg, h, NULL);
resv->adds_in_progress -= in_regions_needed;
spin_unlock(&resv->lock);
return add;
}
/*
* Examine the existing reserve map and determine how many
* huge pages in the specified range [f, t) are NOT currently
* represented. This routine is called before a subsequent
* call to region_add that will actually modify the reserve
* map to add the specified range [f, t). region_chg does
* not change the number of huge pages represented by the
* map. A number of new file_region structures is added to the cache as a
* placeholder, for the subsequent region_add call to use. At least 1
* file_region structure is added.
*
* out_regions_needed is the number of regions added to the
* resv->adds_in_progress. This value needs to be provided to a follow up call
* to region_add or region_abort for proper accounting.
*
* Returns the number of huge pages that need to be added to the existing
* reservation map for the range [f, t). This number is greater or equal to
* zero. -ENOMEM is returned if a new file_region structure or cache entry
* is needed and can not be allocated.
*/
static long region_chg(struct resv_map *resv, long f, long t,
long *out_regions_needed)
{
long chg = 0;
spin_lock(&resv->lock);
/* Count how many hugepages in this range are NOT represented. */
chg = add_reservation_in_range(resv, f, t, NULL, NULL,
out_regions_needed);
if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed))
return -ENOMEM;
resv->adds_in_progress += *out_regions_needed;
spin_unlock(&resv->lock);
return chg;
}
/*
* Abort the in progress add operation. The adds_in_progress field
* of the resv_map keeps track of the operations in progress between
* calls to region_chg and region_add. Operations are sometimes
* aborted after the call to region_chg. In such cases, region_abort
* is called to decrement the adds_in_progress counter. regions_needed
* is the value returned by the region_chg call, it is used to decrement
* the adds_in_progress counter.
*
* NOTE: The range arguments [f, t) are not needed or used in this
* routine. They are kept to make reading the calling code easier as
* arguments will match the associated region_chg call.
*/
static void region_abort(struct resv_map *resv, long f, long t,
long regions_needed)
{
spin_lock(&resv->lock);
VM_BUG_ON(!resv->region_cache_count);
resv->adds_in_progress -= regions_needed;
spin_unlock(&resv->lock);
}
/*
* Delete the specified range [f, t) from the reserve map. If the
* t parameter is LONG_MAX, this indicates that ALL regions after f
* should be deleted. Locate the regions which intersect [f, t)
* and either trim, delete or split the existing regions.
*
* Returns the number of huge pages deleted from the reserve map.
* In the normal case, the return value is zero or more. In the
* case where a region must be split, a new region descriptor must
* be allocated. If the allocation fails, -ENOMEM will be returned.
* NOTE: If the parameter t == LONG_MAX, then we will never split
* a region and possibly return -ENOMEM. Callers specifying
* t == LONG_MAX do not need to check for -ENOMEM error.
*/
static long region_del(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg, *trg;
struct file_region *nrg = NULL;
long del = 0;
retry:
spin_lock(&resv->lock);
list_for_each_entry_safe(rg, trg, head, link) {
/*
* Skip regions before the range to be deleted. file_region
* ranges are normally of the form [from, to). However, there
* may be a "placeholder" entry in the map which is of the form
* (from, to) with from == to. Check for placeholder entries
* at the beginning of the range to be deleted.
*/
if (rg->to <= f && (rg->to != rg->from || rg->to != f))
continue;
if (rg->from >= t)
break;
if (f > rg->from && t < rg->to) { /* Must split region */
/*
* Check for an entry in the cache before dropping
* lock and attempting allocation.
*/
if (!nrg &&
resv->region_cache_count > resv->adds_in_progress) {
nrg = list_first_entry(&resv->region_cache,
struct file_region,
link);
list_del(&nrg->link);
resv->region_cache_count--;
}
if (!nrg) {
spin_unlock(&resv->lock);
nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
if (!nrg)
return -ENOMEM;
goto retry;
}
del += t - f;
hugetlb_cgroup_uncharge_file_region(
resv, rg, t - f, false);
/* New entry for end of split region */
nrg->from = t;
nrg->to = rg->to;
copy_hugetlb_cgroup_uncharge_info(nrg, rg);
INIT_LIST_HEAD(&nrg->link);
/* Original entry is trimmed */
rg->to = f;
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
}
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - rg->from, true);
list_del(&rg->link);
kfree(rg);
continue;
}
if (f <= rg->from) { /* Trim beginning of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from, false);
del += t - rg->from;
rg->from = t;
} else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f, false);
del += rg->to - f;
rg->to = f;
}
}
spin_unlock(&resv->lock);
kfree(nrg);
return del;
}
/*
* A rare out of memory error was encountered which prevented removal of
* the reserve map region for a page. The huge page itself was free'ed
* and removed from the page cache. This routine will adjust the subpool
* usage count, and the global reserve count if needed. By incrementing
* these counts, the reserve map entry which could not be deleted will
* appear as a "reserved" entry instead of simply dangling with incorrect
* counts.
*/
void hugetlb_fix_reserve_counts(struct inode *inode)
{
struct hugepage_subpool *spool = subpool_inode(inode);
long rsv_adjust;
bool reserved = false;
rsv_adjust = hugepage_subpool_get_pages(spool, 1);
if (rsv_adjust > 0) {
struct hstate *h = hstate_inode(inode);
if (!hugetlb_acct_memory(h, 1))
reserved = true;
} else if (!rsv_adjust) {
reserved = true;
}
if (!reserved)
pr_warn("hugetlb: Huge Page Reserved count may go negative.\n");
}
/*
* Count and return the number of huge pages in the reserve map
* that intersect with the range [f, t).
*/
static long region_count(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg;
long chg = 0;
spin_lock(&resv->lock);
/* Locate each segment we overlap with, and count that overlap. */
list_for_each_entry(rg, head, link) {
long seg_from;
long seg_to;
if (rg->to <= f)
continue;
if (rg->from >= t)
break;
seg_from = max(rg->from, f);
seg_to = min(rg->to, t);
chg += seg_to - seg_from;
}
spin_unlock(&resv->lock);
return chg;
}
/*
* Convert the address within this vma to the page offset within
* the mapping, huge page units here.
*/
static pgoff_t vma_hugecache_offset(struct hstate *h,
struct vm_area_struct *vma, unsigned long address)
{
return ((address - vma->vm_start) >> huge_page_shift(h)) +
(vma->vm_pgoff >> huge_page_order(h));
}
/**
* vma_kernel_pagesize - Page size granularity for this VMA.
* @vma: The user mapping.
*
* Folios in this VMA will be aligned to, and at least the size of the
* number of bytes returned by this function.
*
* Return: The default size of the folios allocated when backing a VMA.
*/
unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
if (vma->vm_ops && vma->vm_ops->pagesize)
return vma->vm_ops->pagesize(vma);
return PAGE_SIZE;
}
EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
/*
* Return the page size being used by the MMU to back a VMA. In the majority
* of cases, the page size used by the kernel matches the MMU size. On
* architectures where it differs, an architecture-specific 'strong'
* version of this symbol is required.
*/
__weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
return vma_kernel_pagesize(vma);
}
/*
* Flags for MAP_PRIVATE reservations. These are stored in the bottom
* bits of the reservation map pointer, which are always clear due to
* alignment.
*/
#define HPAGE_RESV_OWNER (1UL << 0)
#define HPAGE_RESV_UNMAPPED (1UL << 1)
#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)
/*
* These helpers are used to track how many pages are reserved for
* faults in a MAP_PRIVATE mapping. Only the process that called mmap()
* is guaranteed to have their future faults succeed.
*
* With the exception of hugetlb_dup_vma_private() which is called at fork(),
* the reserve counters are updated with the hugetlb_lock held. It is safe
* to reset the VMA at fork() time as it is not in use yet and there is no
* chance of the global counters getting corrupted as a result of the values.
*
* The private mapping reservation is represented in a subtly different
* manner to a shared mapping. A shared mapping has a region map associated
* with the underlying file, this region map represents the backing file
* pages which have ever had a reservation assigned which this persists even
* after the page is instantiated. A private mapping has a region map
* associated with the original mmap which is attached to all VMAs which
* reference it, this region map represents those offsets which have consumed
* reservation ie. where pages have been instantiated.
*/
static unsigned long get_vma_private_data(struct vm_area_struct *vma)
{
return (unsigned long)vma->vm_private_data;
}
static void set_vma_private_data(struct vm_area_struct *vma,
unsigned long value)
{
vma->vm_private_data = (void *)value;
}
static void
resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map,
struct hugetlb_cgroup *h_cg,
struct hstate *h)
{
#ifdef CONFIG_CGROUP_HUGETLB
if (!h_cg || !h) {
resv_map->reservation_counter = NULL;
resv_map->pages_per_hpage = 0;
resv_map->css = NULL;
} else {
resv_map->reservation_counter =
&h_cg->rsvd_hugepage[hstate_index(h)];
resv_map->pages_per_hpage = pages_per_huge_page(h);
resv_map->css = &h_cg->css;
}
#endif
}
struct resv_map *resv_map_alloc(void)
{
struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL);
if (!resv_map || !rg) {
kfree(resv_map);
kfree(rg);
return NULL;
}
kref_init(&resv_map->refs);
spin_lock_init(&resv_map->lock);
INIT_LIST_HEAD(&resv_map->regions);
init_rwsem(&resv_map->rw_sema);
resv_map->adds_in_progress = 0;
/*
* Initialize these to 0. On shared mappings, 0's here indicate these
* fields don't do cgroup accounting. On private mappings, these will be
* re-initialized to the proper values, to indicate that hugetlb cgroup
* reservations are to be un-charged from here.
*/
resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL);
INIT_LIST_HEAD(&resv_map->region_cache);
list_add(&rg->link, &resv_map->region_cache);
resv_map->region_cache_count = 1;
return resv_map;
}
void resv_map_release(struct kref *ref)
{
struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
struct list_head *head = &resv_map->region_cache;
struct file_region *rg, *trg;
/* Clear out any active regions before we release the map. */
region_del(resv_map, 0, LONG_MAX);
/* ... and any entries left in the cache */
list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link);
kfree(rg);
}
VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map);
}
static inline struct resv_map *inode_resv_map(struct inode *inode)
{
/*
* At inode evict time, i_mapping may not point to the original
* address space within the inode. This original address space
* contains the pointer to the resv_map. So, always use the
* address space embedded within the inode.
* The VERY common case is inode->mapping == &inode->i_data but,
* this may not be true for device special inodes.
*/
return (struct resv_map *)(&inode->i_data)->i_private_data;
}
static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
if (vma->vm_flags & VM_MAYSHARE) {
struct address_space *mapping = vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
return inode_resv_map(inode);
} else {
return (struct resv_map *)(get_vma_private_data(vma) &
~HPAGE_RESV_MASK);
}
}
static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map);
}
static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}
static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
return (get_vma_private_data(vma) & flag) != 0;
}
bool __vma_private_lock(struct vm_area_struct *vma)
{
return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER);
}
void hugetlb_dup_vma_private(struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
/*
* Clear vm_private_data
* - For shared mappings this is a per-vma semaphore that may be
* allocated in a subsequent call to hugetlb_vm_op_open.
* Before clearing, make sure pointer is not associated with vma
* as this will leak the structure. This is the case when called
* via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already
* been called to allocate a new structure.
* - For MAP_PRIVATE mappings, this is the reserve map which does
* not apply to children. Faults generated by the children are
* not guaranteed to succeed, even if read-only.
*/
if (vma->vm_flags & VM_MAYSHARE) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
if (vma_lock && vma_lock->vma != vma)
vma->vm_private_data = NULL;
} else
vma->vm_private_data = NULL;
}
/*
* Reset and decrement one ref on hugepage private reservation.
* Called with mm->mmap_lock writer semaphore held.
* This function should be only used by move_vma() and operate on
* same sized vma. It should never come here with last ref on the
* reservation.
*/
void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
{
/*
* Clear the old hugetlb private page reservation.
* It has already been transferred to new_vma.
*
* During a mremap() operation of a hugetlb vma we call move_vma()
* which copies vma into new_vma and unmaps vma. After the copy
* operation both new_vma and vma share a reference to the resv_map
* struct, and at that point vma is about to be unmapped. We don't
* want to return the reservation to the pool at unmap of vma because
* the reservation still lives on in new_vma, so simply decrement the
* ref here and remove the resv_map reference from this vma.
*/
struct resv_map *reservations = vma_resv_map(vma);
if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
kref_put(&reservations->refs, resv_map_release);
}
hugetlb_dup_vma_private(vma);
}
static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio)
{
int nid = folio_nid(folio);
lockdep_assert_held(&hugetlb_lock);
VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
list_move(&folio->lru, &h->hugepage_freelists[nid]);
h->free_huge_pages++;
h->free_huge_pages_node[nid]++;
folio_set_hugetlb_freed(folio);
}
static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h,
int nid)
{
struct folio *folio;
bool pin = !!(current->flags & PF_MEMALLOC_PIN);
lockdep_assert_held(&hugetlb_lock);
list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) {
if (pin && !folio_is_longterm_pinnable(folio))
continue;
if (folio_test_hwpoison(folio))
continue;
if (is_migrate_isolate_page(&folio->page))
continue;
list_move(&folio->lru, &h->hugepage_activelist);
folio_ref_unfreeze(folio, 1);
folio_clear_hugetlb_freed(folio);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
return folio;
}
return NULL;
}
static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
unsigned int cpuset_mems_cookie;
struct zonelist *zonelist;
struct zone *zone;
struct zoneref *z;
int node = NUMA_NO_NODE;
/* 'nid' should not be NUMA_NO_NODE. Try to catch any misuse of it and rectifiy. */
if (nid == NUMA_NO_NODE)
nid = numa_node_id();
zonelist = node_zonelist(nid, gfp_mask);
retry_cpuset:
cpuset_mems_cookie = read_mems_allowed_begin();
for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
struct folio *folio;
if (!cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
* no need to ask again on the same node. Pool is node rather than
* zone aware
*/
if (zone_to_nid(zone) == node)
continue;
node = zone_to_nid(zone);
folio = dequeue_hugetlb_folio_node_exact(h, node);
if (folio)
return folio;
}
if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
return NULL;
}
static unsigned long available_huge_pages(struct hstate *h)
{
return h->free_huge_pages - h->resv_huge_pages;
}
static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address, long gbl_chg)
{
struct folio *folio = NULL;
struct mempolicy *mpol;
gfp_t gfp_mask;
nodemask_t *nodemask;
int nid;
/*
* gbl_chg==1 means the allocation requires a new page that was not
* reserved before. Making sure there's at least one free page.
*/
if (gbl_chg && !available_huge_pages(h))
goto err;
gfp_mask = htlb_alloc_mask(h);
nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
if (mpol_is_preferred_many(mpol)) {
folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask,
nid, nodemask);
/* Fallback to all nodes if page==NULL */
nodemask = NULL;
}
if (!folio)
folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask,
nid, nodemask);
mpol_cond_put(mpol);
return folio;
err:
return NULL;
}
/*
* common helper functions for hstate_next_node_to_{alloc|free}.
* We may have allocated or freed a huge page based on a different
* nodes_allowed previously, so h->next_node_to_{alloc|free} might
* be outside of *nodes_allowed. Ensure that we use an allowed
* node for alloc or free.
*/
static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
{
nid = next_node_in(nid, *nodes_allowed);
VM_BUG_ON(nid >= MAX_NUMNODES);
return nid;
}
static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
{
if (!node_isset(nid, *nodes_allowed))
nid = next_node_allowed(nid, nodes_allowed);
return nid;
}
/*
* returns the previously saved node ["this node"] from which to
* allocate a persistent huge page for the pool and advance the
* next node from which to allocate, handling wrap at end of node
* mask.
*/
static int hstate_next_node_to_alloc(int *next_node,
nodemask_t *nodes_allowed)
{
int nid;
VM_BUG_ON(!nodes_allowed);
nid = get_valid_node_allowed(*next_node, nodes_allowed);
*next_node = next_node_allowed(nid, nodes_allowed);
return nid;
}
/*
* helper for remove_pool_hugetlb_folio() - return the previously saved
* node ["this node"] from which to free a huge page. Advance the
* next node id whether or not we find a free huge page to free so
* that the next attempt to free addresses the next node.
*/
static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
{
int nid;
VM_BUG_ON(!nodes_allowed);
nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
return nid;
}
#define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \
for (nr_nodes = nodes_weight(*mask); \
nr_nodes > 0 && \
((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \
nr_nodes--)
#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
for (nr_nodes = nodes_weight(*mask); \
nr_nodes > 0 && \
((node = hstate_next_node_to_free(hs, mask)) || 1); \
nr_nodes--)
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
#ifdef CONFIG_CONTIG_ALLOC
static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask)
{
struct folio *folio;
int order = huge_page_order(h);
bool retried = false;
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
retry:
folio = hugetlb_cma_alloc_folio(h, gfp_mask, nid, nodemask);
if (!folio) {
if (hugetlb_cma_exclusive_alloc())
return NULL;
folio = folio_alloc_gigantic(order, gfp_mask, nid, nodemask);
if (!folio)
return NULL;
}
if (folio_ref_freeze(folio, 1))
return folio;
pr_warn("HugeTLB: unexpected refcount on PFN %lu\n", folio_pfn(folio));
hugetlb_free_folio(folio);
if (!retried) {
retried = true;
goto retry;
}
return NULL;
}
#else /* !CONFIG_CONTIG_ALLOC */
static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask)
{
return NULL;
}
#endif /* CONFIG_CONTIG_ALLOC */
#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask)
{
return NULL;
}
#endif
/*
* Remove hugetlb folio from lists.
* If vmemmap exists for the folio, clear the hugetlb flag so that the
* folio appears as just a compound page. Otherwise, wait until after
* allocating vmemmap to clear the flag.
*
* Must be called with hugetlb lock held.
*/
static void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
bool adjust_surplus)
{
int nid = folio_nid(folio);
VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio);
VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio);
lockdep_assert_held(&hugetlb_lock);
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return;
list_del(&folio->lru);
if (folio_test_hugetlb_freed(folio)) {
folio_clear_hugetlb_freed(folio);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
}
if (adjust_surplus) {
h->surplus_huge_pages--;
h->surplus_huge_pages_node[nid]--;
}
/*
* We can only clear the hugetlb flag after allocating vmemmap
* pages. Otherwise, someone (memory error handling) may try to write
* to tail struct pages.
*/
if (!folio_test_hugetlb_vmemmap_optimized(folio))
__folio_clear_hugetlb(folio);
h->nr_huge_pages--;
h->nr_huge_pages_node[nid]--;
}
static void add_hugetlb_folio(struct hstate *h, struct folio *folio,
bool adjust_surplus)
{
int nid = folio_nid(folio);
VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio);
lockdep_assert_held(&hugetlb_lock);
INIT_LIST_HEAD(&folio->lru);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
if (adjust_surplus) {
h->surplus_huge_pages++;
h->surplus_huge_pages_node[nid]++;
}
__folio_set_hugetlb(folio);
folio_change_private(folio, NULL);
/*
* We have to set hugetlb_vmemmap_optimized again as above
* folio_change_private(folio, NULL) cleared it.
*/
folio_set_hugetlb_vmemmap_optimized(folio);
arch_clear_hugetlb_flags(folio);
enqueue_hugetlb_folio(h, folio);
}
static void __update_and_free_hugetlb_folio(struct hstate *h,
struct folio *folio)
{
bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio);
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return;
/*
* If we don't know which subpages are hwpoisoned, we can't free
* the hugepage, so it's leaked intentionally.
*/
if (folio_test_hugetlb_raw_hwp_unreliable(folio))
return;
/*
* If folio is not vmemmap optimized (!clear_flag), then the folio
* is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio
* can only be passed hugetlb pages and will BUG otherwise.
*/
if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) {
spin_lock_irq(&hugetlb_lock);
/*
* If we cannot allocate vmemmap pages, just refuse to free the
* page and put the page back on the hugetlb free list and treat
* as a surplus page.
*/
add_hugetlb_folio(h, folio, true);
spin_unlock_irq(&hugetlb_lock);
return;
}
/*
* If vmemmap pages were allocated above, then we need to clear the
* hugetlb flag under the hugetlb lock.
*/
if (folio_test_hugetlb(folio)) {
spin_lock_irq(&hugetlb_lock);
__folio_clear_hugetlb(folio);
spin_unlock_irq(&hugetlb_lock);
}
/*
* Move PageHWPoison flag from head page to the raw error pages,
* which makes any healthy subpages reusable.
*/
if (unlikely(folio_test_hwpoison(folio)))
folio_clear_hugetlb_hwpoison(folio);
folio_ref_unfreeze(folio, 1);
hugetlb_free_folio(folio);
}
/*
* As update_and_free_hugetlb_folio() can be called under any context, so we cannot
* use GFP_KERNEL to allocate vmemmap pages. However, we can defer the
* actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate
* the vmemmap pages.
*
* free_hpage_workfn() locklessly retrieves the linked list of pages to be
* freed and frees them one-by-one. As the page->mapping pointer is going
* to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node
* structure of a lockless linked list of huge pages to be freed.
*/
static LLIST_HEAD(hpage_freelist);
static void free_hpage_workfn(struct work_struct *work)
{
struct llist_node *node;
node = llist_del_all(&hpage_freelist);
while (node) {
struct folio *folio;
struct hstate *h;
folio = container_of((struct address_space **)node,
struct folio, mapping);
node = node->next;
folio->mapping = NULL;
/*
* The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in
* folio_hstate() is going to trigger because a previous call to
* remove_hugetlb_folio() will clear the hugetlb bit, so do
* not use folio_hstate() directly.
*/
h = size_to_hstate(folio_size(folio));
__update_and_free_hugetlb_folio(h, folio);
cond_resched();
}
}
static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
static inline void flush_free_hpage_work(struct hstate *h)
{
if (hugetlb_vmemmap_optimizable(h))
flush_work(&free_hpage_work);
}
static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio,
bool atomic)
{
if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) {
__update_and_free_hugetlb_folio(h, folio);
return;
}
/*
* Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages.
*
* Only call schedule_work() if hpage_freelist is previously
* empty. Otherwise, schedule_work() had been called but the workfn
* hasn't retrieved the list yet.
*/
if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist))
schedule_work(&free_hpage_work);
}
static void bulk_vmemmap_restore_error(struct hstate *h,
struct list_head *folio_list,
struct list_head *non_hvo_folios)
{
struct folio *folio, *t_folio;
if (!list_empty(non_hvo_folios)) {
/*
* Free any restored hugetlb pages so that restore of the
* entire list can be retried.
* The idea is that in the common case of ENOMEM errors freeing
* hugetlb pages with vmemmap we will free up memory so that we
* can allocate vmemmap for more hugetlb pages.
*/
list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) {
list_del(&folio->lru);
spin_lock_irq(&hugetlb_lock);
__folio_clear_hugetlb(folio);
spin_unlock_irq(&hugetlb_lock);
update_and_free_hugetlb_folio(h, folio, false);
cond_resched();
}
} else {
/*
* In the case where there are no folios which can be
* immediately freed, we loop through the list trying to restore
* vmemmap individually in the hope that someone elsewhere may
* have done something to cause success (such as freeing some
* memory). If unable to restore a hugetlb page, the hugetlb
* page is made a surplus page and removed from the list.
* If are able to restore vmemmap and free one hugetlb page, we
* quit processing the list to retry the bulk operation.
*/
list_for_each_entry_safe(folio, t_folio, folio_list, lru)
if (hugetlb_vmemmap_restore_folio(h, folio)) {
list_del(&folio->lru);
spin_lock_irq(&hugetlb_lock);
add_hugetlb_folio(h, folio, true);
spin_unlock_irq(&hugetlb_lock);
} else {
list_del(&folio->lru);
spin_lock_irq(&hugetlb_lock);
__folio_clear_hugetlb(folio);
spin_unlock_irq(&hugetlb_lock);
update_and_free_hugetlb_folio(h, folio, false);
cond_resched();
break;
}
}
}
static void update_and_free_pages_bulk(struct hstate *h,
struct list_head *folio_list)
{
long ret;
struct folio *folio, *t_folio;
LIST_HEAD(non_hvo_folios);
/*
* First allocate required vmemmmap (if necessary) for all folios.
* Carefully handle errors and free up any available hugetlb pages
* in an effort to make forward progress.
*/
retry:
ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios);
if (ret < 0) {
bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios);
goto retry;
}
/*
* At this point, list should be empty, ret should be >= 0 and there
* should only be pages on the non_hvo_folios list.
* Do note that the non_hvo_folios list could be empty.
* Without HVO enabled, ret will be 0 and there is no need to call
* __folio_clear_hugetlb as this was done previously.
*/
VM_WARN_ON(!list_empty(folio_list));
VM_WARN_ON(ret < 0);
if (!list_empty(&non_hvo_folios) && ret) {
spin_lock_irq(&hugetlb_lock);
list_for_each_entry(folio, &non_hvo_folios, lru)
__folio_clear_hugetlb(folio);
spin_unlock_irq(&hugetlb_lock);
}
list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) {
update_and_free_hugetlb_folio(h, folio, false);
cond_resched();
}
}
struct hstate *size_to_hstate(unsigned long size)
{
struct hstate *h;
for_each_hstate(h) { if (huge_page_size(h) == size)
return h;
}
return NULL;
}
void free_huge_folio(struct folio *folio)
{
/*
* Can't pass hstate in here because it is called from the
* generic mm code.
*/
struct hstate *h = folio_hstate(folio);
int nid = folio_nid(folio);
struct hugepage_subpool *spool = hugetlb_folio_subpool(folio);
bool restore_reserve;
unsigned long flags;
VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
VM_BUG_ON_FOLIO(folio_mapcount(folio), folio);
hugetlb_set_folio_subpool(folio, NULL);
if (folio_test_anon(folio))
__ClearPageAnonExclusive(&folio->page);
folio->mapping = NULL;
restore_reserve = folio_test_hugetlb_restore_reserve(folio);
folio_clear_hugetlb_restore_reserve(folio);
/*
* If HPageRestoreReserve was set on page, page allocation consumed a
* reservation. If the page was associated with a subpool, there
* would have been a page reserved in the subpool before allocation
* via hugepage_subpool_get_pages(). Since we are 'restoring' the
* reservation, do not call hugepage_subpool_put_pages() as this will
* remove the reserved page from the subpool.
*/
if (!restore_reserve) {
/*
* A return code of zero implies that the subpool will be
* under its minimum size if the reservation is not restored
* after page is free. Therefore, force restore_reserve
* operation.
*/
if (hugepage_subpool_put_pages(spool, 1) == 0)
restore_reserve = true;
}
spin_lock_irqsave(&hugetlb_lock, flags);
folio_clear_hugetlb_migratable(folio);
hugetlb_cgroup_uncharge_folio(hstate_index(h),
pages_per_huge_page(h), folio);
hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
pages_per_huge_page(h), folio);
lruvec_stat_mod_folio(folio, NR_HUGETLB, -pages_per_huge_page(h));
mem_cgroup_uncharge(folio);
if (restore_reserve)
h->resv_huge_pages++;
if (folio_test_hugetlb_temporary(folio)) {
remove_hugetlb_folio(h, folio, false);
spin_unlock_irqrestore(&hugetlb_lock, flags);
update_and_free_hugetlb_folio(h, folio, true);
} else if (h->surplus_huge_pages_node[nid]) {
/* remove the page from active list */
remove_hugetlb_folio(h, folio, true);
spin_unlock_irqrestore(&hugetlb_lock, flags);
update_and_free_hugetlb_folio(h, folio, true);
} else {
arch_clear_hugetlb_flags(folio);
enqueue_hugetlb_folio(h, folio);
spin_unlock_irqrestore(&hugetlb_lock, flags);
}
}
/*
* Must be called with the hugetlb lock held
*/
static void __prep_account_new_huge_page(struct hstate *h, int nid)
{
lockdep_assert_held(&hugetlb_lock);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
}
static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio)
{
__folio_set_hugetlb(folio);
INIT_LIST_HEAD(&folio->lru);
hugetlb_set_folio_subpool(folio, NULL);
set_hugetlb_cgroup(folio, NULL);
set_hugetlb_cgroup_rsvd(folio, NULL);
}
static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio)
{
init_new_hugetlb_folio(h, folio);
hugetlb_vmemmap_optimize_folio(h, folio);
}
static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid)
{
__prep_new_hugetlb_folio(h, folio);
spin_lock_irq(&hugetlb_lock);
__prep_account_new_huge_page(h, nid);
spin_unlock_irq(&hugetlb_lock);
}
/*
* Find and lock address space (mapping) in write mode.
*
* Upon entry, the folio is locked which means that folio_mapping() is
* stable. Due to locking order, we can only trylock_write. If we can
* not get the lock, simply return NULL to caller.
*/
struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio)
{
struct address_space *mapping = folio_mapping(folio);
if (!mapping)
return mapping;
if (i_mmap_trylock_write(mapping))
return mapping;
return NULL;
}
static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask,
nodemask_t *node_alloc_noretry)
{
int order = huge_page_order(h);
struct folio *folio;
bool alloc_try_hard = true;
bool retry = true;
/*
* By default we always try hard to allocate the folio with
* __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in
* a loop (to adjust global huge page counts) and previous allocation
* failed, do not continue to try hard on the same node. Use the
* node_alloc_noretry bitmap to manage this state information.
*/
if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry))
alloc_try_hard = false;
if (alloc_try_hard)
gfp_mask |= __GFP_RETRY_MAYFAIL;
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
retry:
folio = __folio_alloc(gfp_mask, order, nid, nmask);
/* Ensure hugetlb folio won't have large_rmappable flag set. */
if (folio)
folio_clear_large_rmappable(folio);
if (folio && !folio_ref_freeze(folio, 1)) {
folio_put(folio);
if (retry) { /* retry once */
retry = false;
goto retry;
}
/* WOW! twice in a row. */
pr_warn("HugeTLB unexpected inflated folio ref count\n");
folio = NULL;
}
/*
* If we did not specify __GFP_RETRY_MAYFAIL, but still got a
* folio this indicates an overall state change. Clear bit so
* that we resume normal 'try hard' allocations.
*/
if (node_alloc_noretry && folio && !alloc_try_hard)
node_clear(nid, *node_alloc_noretry);
/*
* If we tried hard to get a folio but failed, set bit so that
* subsequent attempts will not try as hard until there is an
* overall state change.
*/
if (node_alloc_noretry && !folio && alloc_try_hard)
node_set(nid, *node_alloc_noretry);
if (!folio) {
__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
return NULL;
}
__count_vm_event(HTLB_BUDDY_PGALLOC);
return folio;
}
static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask,
nodemask_t *node_alloc_noretry)
{
struct folio *folio;
if (hstate_is_gigantic(h))
folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask);
else
folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry);
if (folio)
init_new_hugetlb_folio(h, folio);
return folio;
}
/*
* Common helper to allocate a fresh hugetlb page. All specific allocators
* should use this function to get new hugetlb pages
*
* Note that returned page is 'frozen': ref count of head page and all tail
* pages is zero.
*/
static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask)
{
struct folio *folio;
if (hstate_is_gigantic(h))
folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask);
else
folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, NULL);
if (!folio)
return NULL;
prep_new_hugetlb_folio(h, folio, folio_nid(folio));
return folio;
}
static void prep_and_add_allocated_folios(struct hstate *h,
struct list_head *folio_list)
{
unsigned long flags;
struct folio *folio, *tmp_f;
/* Send list for bulk vmemmap optimization processing */
hugetlb_vmemmap_optimize_folios(h, folio_list);
/* Add all new pool pages to free lists in one lock cycle */
spin_lock_irqsave(&hugetlb_lock, flags);
list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
__prep_account_new_huge_page(h, folio_nid(folio));
enqueue_hugetlb_folio(h, folio);
}
spin_unlock_irqrestore(&hugetlb_lock, flags);
}
/*
* Allocates a fresh hugetlb page in a node interleaved manner. The page
* will later be added to the appropriate hugetlb pool.
*/
static struct folio *alloc_pool_huge_folio(struct hstate *h,
nodemask_t *nodes_allowed,
nodemask_t *node_alloc_noretry,
int *next_node)
{
gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
int nr_nodes, node;
for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) {
struct folio *folio;
folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node,
nodes_allowed, node_alloc_noretry);
if (folio)
return folio;
}
return NULL;
}
/*
* Remove huge page from pool from next node to free. Attempt to keep
* persistent huge pages more or less balanced over allowed nodes.
* This routine only 'removes' the hugetlb page. The caller must make
* an additional call to free the page to low level allocators.
* Called with hugetlb_lock locked.
*/
static struct folio *remove_pool_hugetlb_folio(struct hstate *h,
nodemask_t *nodes_allowed, bool acct_surplus)
{
int nr_nodes, node;
struct folio *folio = NULL;
lockdep_assert_held(&hugetlb_lock);
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
/*
* If we're returning unused surplus pages, only examine
* nodes with surplus pages.
*/
if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
!list_empty(&h->hugepage_freelists[node])) {
folio = list_entry(h->hugepage_freelists[node].next,
struct folio, lru);
remove_hugetlb_folio(h, folio, acct_surplus);
break;
}
}
return folio;
}
/*
* Dissolve a given free hugetlb folio into free buddy pages. This function
* does nothing for in-use hugetlb folios and non-hugetlb folios.
* This function returns values like below:
*
* -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages
* when the system is under memory pressure and the feature of
* freeing unused vmemmap pages associated with each hugetlb page
* is enabled.
* -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
* (allocated or reserved.)
* 0: successfully dissolved free hugepages or the page is not a
* hugepage (considered as already dissolved)
*/
int dissolve_free_hugetlb_folio(struct folio *folio)
{
int rc = -EBUSY;
retry:
/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!folio_test_hugetlb(folio))
return 0;
spin_lock_irq(&hugetlb_lock);
if (!folio_test_hugetlb(folio)) {
rc = 0;
goto out;
}
if (!folio_ref_count(folio)) {
struct hstate *h = folio_hstate(folio);
bool adjust_surplus = false;
if (!available_huge_pages(h))
goto out;
/*
* We should make sure that the page is already on the free list
* when it is dissolved.
*/
if (unlikely(!folio_test_hugetlb_freed(folio))) {
spin_unlock_irq(&hugetlb_lock);
cond_resched();
/*
* Theoretically, we should return -EBUSY when we
* encounter this race. In fact, we have a chance
* to successfully dissolve the page if we do a
* retry. Because the race window is quite small.
* If we seize this opportunity, it is an optimization
* for increasing the success rate of dissolving page.
*/
goto retry;
}
if (h->surplus_huge_pages_node[folio_nid(folio)])
adjust_surplus = true;
remove_hugetlb_folio(h, folio, adjust_surplus);
h->max_huge_pages--;
spin_unlock_irq(&hugetlb_lock);
/*
* Normally update_and_free_hugtlb_folio will allocate required vmemmmap
* before freeing the page. update_and_free_hugtlb_folio will fail to
* free the page if it can not allocate required vmemmap. We
* need to adjust max_huge_pages if the page is not freed.
* Attempt to allocate vmemmmap here so that we can take
* appropriate action on failure.
*
* The folio_test_hugetlb check here is because
* remove_hugetlb_folio will clear hugetlb folio flag for
* non-vmemmap optimized hugetlb folios.
*/
if (folio_test_hugetlb(folio)) {
rc = hugetlb_vmemmap_restore_folio(h, folio);
if (rc) {
spin_lock_irq(&hugetlb_lock);
add_hugetlb_folio(h, folio, adjust_surplus);
h->max_huge_pages++;
goto out;
}
} else
rc = 0;
update_and_free_hugetlb_folio(h, folio, false);
return rc;
}
out:
spin_unlock_irq(&hugetlb_lock);
return rc;
}
/*
* Dissolve free hugepages in a given pfn range. Used by memory hotplug to
* make specified memory blocks removable from the system.
* Note that this will dissolve a free gigantic hugepage completely, if any
* part of it lies within the given range.
* Also note that if dissolve_free_hugetlb_folio() returns with an error, all
* free hugetlb folios that were dissolved before that error are lost.
*/
int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pfn;
struct folio *folio;
int rc = 0;
unsigned int order;
struct hstate *h;
if (!hugepages_supported())
return rc;
order = huge_page_order(&default_hstate);
for_each_hstate(h)
order = min(order, huge_page_order(h));
for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) {
folio = pfn_folio(pfn);
rc = dissolve_free_hugetlb_folio(folio);
if (rc)
break;
}
return rc;
}
/*
* Allocates a fresh surplus page from the page allocator.
*/
static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask)
{
struct folio *folio = NULL;
if (hstate_is_gigantic(h))
return NULL;
spin_lock_irq(&hugetlb_lock);
if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages)
goto out_unlock;
spin_unlock_irq(&hugetlb_lock);
folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL);
if (!folio)
return NULL;
hugetlb_vmemmap_optimize_folio(h, folio);
spin_lock_irq(&hugetlb_lock);
/*
* nr_huge_pages needs to be adjusted within the same lock cycle
* as surplus_pages, otherwise it might confuse
* persistent_huge_pages() momentarily.
*/
__prep_account_new_huge_page(h, folio_nid(folio));
/*
* We could have raced with the pool size change.
* Double check that and simply deallocate the new page
* if we would end up overcommiting the surpluses. Abuse
* temporary page to workaround the nasty free_huge_folio
* codeflow
*/
if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
folio_set_hugetlb_temporary(folio);
spin_unlock_irq(&hugetlb_lock);
free_huge_folio(folio);
return NULL;
}
h->surplus_huge_pages++;
h->surplus_huge_pages_node[folio_nid(folio)]++;
out_unlock:
spin_unlock_irq(&hugetlb_lock);
return folio;
}
static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
struct folio *folio;
if (hstate_is_gigantic(h))
return NULL;
folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask);
if (!folio)
return NULL;
/* fresh huge pages are frozen */
folio_ref_unfreeze(folio, 1);
/*
* We do not account these pages as surplus because they are only
* temporary and will be released properly on the last reference
*/
folio_set_hugetlb_temporary(folio);
return folio;
}
/*
* Use the VMA's mpolicy to allocate a huge page from the buddy.
*/
static
struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
struct folio *folio = NULL;
struct mempolicy *mpol;
gfp_t gfp_mask = htlb_alloc_mask(h);
int nid;
nodemask_t *nodemask;
nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
if (mpol_is_preferred_many(mpol)) {
gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask);
/* Fallback to all nodes if page==NULL */
nodemask = NULL;
}
if (!folio)
folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask);
mpol_cond_put(mpol);
return folio;
}
struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask)
{
struct folio *folio;
spin_lock_irq(&hugetlb_lock);
folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid,
nmask);
if (folio) {
VM_BUG_ON(!h->resv_huge_pages);
h->resv_huge_pages--;
}
spin_unlock_irq(&hugetlb_lock);
return folio;
}
/* folio migration callback function */
struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback)
{
spin_lock_irq(&hugetlb_lock);
if (available_huge_pages(h)) {
struct folio *folio;
folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask,
preferred_nid, nmask);
if (folio) {
spin_unlock_irq(&hugetlb_lock);
return folio;
}
}
spin_unlock_irq(&hugetlb_lock);
/* We cannot fallback to other nodes, as we could break the per-node pool. */
if (!allow_alloc_fallback)
gfp_mask |= __GFP_THISNODE;
return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask);
}
static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
{
#ifdef CONFIG_NUMA
struct mempolicy *mpol = get_task_policy(current);
/*
* Only enforce MPOL_BIND policy which overlaps with cpuset policy
* (from policy_nodemask) specifically for hugetlb case
*/
if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) &&
cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
return &mpol->nodes;
#endif
return NULL;
}
/*
* Increase the hugetlb pool such that it can accommodate a reservation
* of size 'delta'.
*/
static int gather_surplus_pages(struct hstate *h, long delta)
__must_hold(&hugetlb_lock)
{
LIST_HEAD(surplus_list);
struct folio *folio, *tmp;
int ret;
long i;
long needed, allocated;
bool alloc_ok = true;
int node;
nodemask_t *mbind_nodemask, alloc_nodemask;
mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
if (mbind_nodemask)
nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed);
else
alloc_nodemask = cpuset_current_mems_allowed;
lockdep_assert_held(&hugetlb_lock);
needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
if (needed <= 0) {
h->resv_huge_pages += delta;
return 0;
}
allocated = 0;
ret = -ENOMEM;
retry:
spin_unlock_irq(&hugetlb_lock);
for (i = 0; i < needed; i++) {
folio = NULL;
/* Prioritize current node */
if (node_isset(numa_mem_id(), alloc_nodemask)) folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
numa_mem_id(), NULL);
if (!folio) { for_each_node_mask(node, alloc_nodemask) { if (node == numa_mem_id())
continue;
folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
node, NULL);
if (folio)
break;
}
}
if (!folio) {
alloc_ok = false;
break;
}
list_add(&folio->lru, &surplus_list);
cond_resched();
}
allocated += i;
/*
* After retaking hugetlb_lock, we need to recalculate 'needed'
* because either resv_huge_pages or free_huge_pages may have changed.
*/
spin_lock_irq(&hugetlb_lock);
needed = (h->resv_huge_pages + delta) -
(h->free_huge_pages + allocated);
if (needed > 0) {
if (alloc_ok)
goto retry;
/*
* We were not able to allocate enough pages to
* satisfy the entire reservation so we free what
* we've allocated so far.
*/
goto free;
}
/*
* The surplus_list now contains _at_least_ the number of extra pages
* needed to accommodate the reservation. Add the appropriate number
* of pages to the hugetlb pool and free the extras back to the buddy
* allocator. Commit the entire reservation here to prevent another
* process from stealing the pages as they are added to the pool but
* before they are reserved.
*/
needed += allocated;
h->resv_huge_pages += delta;
ret = 0;
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0)
break;
/* Add the page to the hugetlb allocator */
enqueue_hugetlb_folio(h, folio);
}
free:
spin_unlock_irq(&hugetlb_lock);
/*
* Free unnecessary surplus pages to the buddy allocator.
* Pages have no ref count, call free_huge_folio directly.
*/
list_for_each_entry_safe(folio, tmp, &surplus_list, lru)
free_huge_folio(folio);
spin_lock_irq(&hugetlb_lock);
return ret;
}
/*
* This routine has two main purposes:
* 1) Decrement the reservation count (resv_huge_pages) by the value passed
* in unused_resv_pages. This corresponds to the prior adjustments made
* to the associated reservation map.
* 2) Free any unused surplus pages that may have been allocated to satisfy
* the reservation. As many as unused_resv_pages may be freed.
*/
static void return_unused_surplus_pages(struct hstate *h,
unsigned long unused_resv_pages)
{
unsigned long nr_pages;
LIST_HEAD(page_list);
lockdep_assert_held(&hugetlb_lock);
/* Uncommit the reservation */
h->resv_huge_pages -= unused_resv_pages;
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
goto out;
/*
* Part (or even all) of the reservation could have been backed
* by pre-allocated pages. Only free surplus pages.
*/
nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
/*
* We want to release as many surplus pages as possible, spread
* evenly across all nodes with memory. Iterate across these nodes
* until we can no longer free unreserved surplus pages. This occurs
* when the nodes with surplus pages have no free pages.
* remove_pool_hugetlb_folio() will balance the freed pages across the
* on-line nodes with memory and will handle the hstate accounting.
*/
while (nr_pages--) {
struct folio *folio;
folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1);
if (!folio)
goto out;
list_add(&folio->lru, &page_list);
}
out:
spin_unlock_irq(&hugetlb_lock);
update_and_free_pages_bulk(h, &page_list);
spin_lock_irq(&hugetlb_lock);
}
/*
* vma_needs_reservation, vma_commit_reservation and vma_end_reservation
* are used by the huge page allocation routines to manage reservations.
*
* vma_needs_reservation is called to determine if the huge page at addr
* within the vma has an associated reservation. If a reservation is
* needed, the value 1 is returned. The caller is then responsible for
* managing the global reservation and subpool usage counts. After
* the huge page has been allocated, vma_commit_reservation is called
* to add the page to the reservation map. If the page allocation fails,
* the reservation must be ended instead of committed. vma_end_reservation
* is called in such cases.
*
* In the normal case, vma_commit_reservation returns the same value
* as the preceding vma_needs_reservation call. The only time this
* is not the case is if a reserve map was changed between calls. It
* is the responsibility of the caller to notice the difference and
* take appropriate action.
*
* vma_add_reservation is used in error paths where a reservation must
* be restored when a newly allocated huge page must be freed. It is
* to be called after calling vma_needs_reservation to determine if a
* reservation exists.
*
* vma_del_reservation is used in error paths where an entry in the reserve
* map was created during huge page allocation and must be removed. It is to
* be called after calling vma_needs_reservation to determine if a reservation
* exists.
*/
enum vma_resv_mode {
VMA_NEEDS_RESV,
VMA_COMMIT_RESV,
VMA_END_RESV,
VMA_ADD_RESV,
VMA_DEL_RESV,
};
static long __vma_reservation_common(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr,
enum vma_resv_mode mode)
{
struct resv_map *resv;
pgoff_t idx;
long ret;
long dummy_out_regions_needed;
resv = vma_resv_map(vma); if (!resv)
return 1;
idx = vma_hugecache_offset(h, vma, addr);
switch (mode) {
case VMA_NEEDS_RESV:
ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed);
/* We assume that vma_reservation_* routines always operate on
* 1 page, and that adding to resv map a 1 page entry can only
* ever require 1 region.
*/
VM_BUG_ON(dummy_out_regions_needed != 1);
break;
case VMA_COMMIT_RESV:
ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
break;
case VMA_END_RESV:
region_abort(resv, idx, idx + 1, 1);
ret = 0;
break;
case VMA_ADD_RESV:
if (vma->vm_flags & VM_MAYSHARE) {
ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
} else {
region_abort(resv, idx, idx + 1, 1);
ret = region_del(resv, idx, idx + 1);
}
break;
case VMA_DEL_RESV:
if (vma->vm_flags & VM_MAYSHARE) {
region_abort(resv, idx, idx + 1, 1);
ret = region_del(resv, idx, idx + 1);
} else {
ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
/* region_add calls of range 1 should never fail. */
VM_BUG_ON(ret < 0);
}
break;
default:
BUG();
}
if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV)
return ret;
/*
* We know private mapping must have HPAGE_RESV_OWNER set.
*
* In most cases, reserves always exist for private mappings.
* However, a file associated with mapping could have been
* hole punched or truncated after reserves were consumed.
* As subsequent fault on such a range will not use reserves.
* Subtle - The reserve map for private mappings has the
* opposite meaning than that of shared mappings. If NO
* entry is in the reserve map, it means a reservation exists.
* If an entry exists in the reserve map, it means the
* reservation has already been consumed. As a result, the
* return value of this routine is the opposite of the
* value returned from reserve map manipulation routines above.
*/
if (ret > 0)
return 0;
if (ret == 0)
return 1;
return ret;
}
static long vma_needs_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV);
}
static long vma_commit_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV);
}
static void vma_end_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
(void)__vma_reservation_common(h, vma, addr, VMA_END_RESV);
}
static long vma_add_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
}
static long vma_del_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV);
}
/*
* This routine is called to restore reservation information on error paths.
* It should ONLY be called for folios allocated via alloc_hugetlb_folio(),
* and the hugetlb mutex should remain held when calling this routine.
*
* It handles two specific cases:
* 1) A reservation was in place and the folio consumed the reservation.
* hugetlb_restore_reserve is set in the folio.
* 2) No reservation was in place for the page, so hugetlb_restore_reserve is
* not set. However, alloc_hugetlb_folio always updates the reserve map.
*
* In case 1, free_huge_folio later in the error path will increment the
* global reserve count. But, free_huge_folio does not have enough context
* to adjust the reservation map. This case deals primarily with private
* mappings. Adjust the reserve map here to be consistent with global
* reserve count adjustments to be made by free_huge_folio. Make sure the
* reserve map indicates there is a reservation present.
*
* In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio.
*/
void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
unsigned long address, struct folio *folio)
{
long rc = vma_needs_reservation(h, vma, address);
if (folio_test_hugetlb_restore_reserve(folio)) {
if (unlikely(rc < 0))
/*
* Rare out of memory condition in reserve map
* manipulation. Clear hugetlb_restore_reserve so
* that global reserve count will not be incremented
* by free_huge_folio. This will make it appear
* as though the reservation for this folio was
* consumed. This may prevent the task from
* faulting in the folio at a later time. This
* is better than inconsistent global huge page
* accounting of reserve counts.
*/
folio_clear_hugetlb_restore_reserve(folio);
else if (rc)
(void)vma_add_reservation(h, vma, address);
else
vma_end_reservation(h, vma, address);
} else {
if (!rc) {
/*
* This indicates there is an entry in the reserve map
* not added by alloc_hugetlb_folio. We know it was added
* before the alloc_hugetlb_folio call, otherwise
* hugetlb_restore_reserve would be set on the folio.
* Remove the entry so that a subsequent allocation
* does not consume a reservation.
*/
rc = vma_del_reservation(h, vma, address);
if (rc < 0)
/*
* VERY rare out of memory condition. Since
* we can not delete the entry, set
* hugetlb_restore_reserve so that the reserve
* count will be incremented when the folio
* is freed. This reserve will be consumed
* on a subsequent allocation.
*/
folio_set_hugetlb_restore_reserve(folio);
} else if (rc < 0) {
/*
* Rare out of memory condition from
* vma_needs_reservation call. Memory allocation is
* only attempted if a new entry is needed. Therefore,
* this implies there is not an entry in the
* reserve map.
*
* For shared mappings, no entry in the map indicates
* no reservation. We are done.
*/
if (!(vma->vm_flags & VM_MAYSHARE))
/*
* For private mappings, no entry indicates
* a reservation is present. Since we can
* not add an entry, set hugetlb_restore_reserve
* on the folio so reserve count will be
* incremented when freed. This reserve will
* be consumed on a subsequent allocation.
*/
folio_set_hugetlb_restore_reserve(folio);
} else
/*
* No reservation present, do nothing
*/
vma_end_reservation(h, vma, address);
}
}
/*
* alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve
* the old one
* @h: struct hstate old page belongs to
* @old_folio: Old folio to dissolve
* @list: List to isolate the page in case we need to
* Returns 0 on success, otherwise negated error.
*/
static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
struct folio *old_folio, struct list_head *list)
{
gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
int nid = folio_nid(old_folio);
struct folio *new_folio = NULL;
int ret = 0;
retry:
spin_lock_irq(&hugetlb_lock);
if (!folio_test_hugetlb(old_folio)) {
/*
* Freed from under us. Drop new_folio too.
*/
goto free_new;
} else if (folio_ref_count(old_folio)) {
bool isolated;
/*
* Someone has grabbed the folio, try to isolate it here.
* Fail with -EBUSY if not possible.
*/
spin_unlock_irq(&hugetlb_lock);
isolated = folio_isolate_hugetlb(old_folio, list);
ret = isolated ? 0 : -EBUSY;
spin_lock_irq(&hugetlb_lock);
goto free_new;
} else if (!folio_test_hugetlb_freed(old_folio)) {
/*
* Folio's refcount is 0 but it has not been enqueued in the
* freelist yet. Race window is small, so we can succeed here if
* we retry.
*/
spin_unlock_irq(&hugetlb_lock);
cond_resched();
goto retry;
} else {
if (!new_folio) {
spin_unlock_irq(&hugetlb_lock);
new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid,
NULL, NULL);
if (!new_folio)
return -ENOMEM;
__prep_new_hugetlb_folio(h, new_folio);
goto retry;
}
/*
* Ok, old_folio is still a genuine free hugepage. Remove it from
* the freelist and decrease the counters. These will be
* incremented again when calling __prep_account_new_huge_page()
* and enqueue_hugetlb_folio() for new_folio. The counters will
* remain stable since this happens under the lock.
*/
remove_hugetlb_folio(h, old_folio, false);
/*
* Ref count on new_folio is already zero as it was dropped
* earlier. It can be directly added to the pool free list.
*/
__prep_account_new_huge_page(h, nid);
enqueue_hugetlb_folio(h, new_folio);
/*
* Folio has been replaced, we can safely free the old one.
*/
spin_unlock_irq(&hugetlb_lock);
update_and_free_hugetlb_folio(h, old_folio, false);
}
return ret;
free_new:
spin_unlock_irq(&hugetlb_lock);
if (new_folio)
update_and_free_hugetlb_folio(h, new_folio, false);
return ret;
}
int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
{
struct hstate *h;
struct folio *folio = page_folio(page);
int ret = -EBUSY;
/*
* The page might have been dissolved from under our feet, so make sure
* to carefully check the state under the lock.
* Return success when racing as if we dissolved the page ourselves.
*/
spin_lock_irq(&hugetlb_lock);
if (folio_test_hugetlb(folio)) {
h = folio_hstate(folio);
} else {
spin_unlock_irq(&hugetlb_lock);
return 0;
}
spin_unlock_irq(&hugetlb_lock);
/*
* Fence off gigantic pages as there is a cyclic dependency between
* alloc_contig_range and them. Return -ENOMEM as this has the effect
* of bailing out right away without further retrying.
*/
if (hstate_is_gigantic(h))
return -ENOMEM;
if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list))
ret = 0;
else if (!folio_ref_count(folio))
ret = alloc_and_dissolve_hugetlb_folio(h, folio, list);
return ret;
}
/*
* replace_free_hugepage_folios - Replace free hugepage folios in a given pfn
* range with new folios.
* @start_pfn: start pfn of the given pfn range
* @end_pfn: end pfn of the given pfn range
* Returns 0 on success, otherwise negated error.
*/
int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
{
struct hstate *h;
struct folio *folio;
int ret = 0;
LIST_HEAD(isolate_list);
while (start_pfn < end_pfn) {
folio = pfn_folio(start_pfn);
if (folio_test_hugetlb(folio)) {
h = folio_hstate(folio);
} else {
start_pfn++;
continue;
}
if (!folio_ref_count(folio)) {
ret = alloc_and_dissolve_hugetlb_folio(h, folio,
&isolate_list);
if (ret)
break;
putback_movable_pages(&isolate_list);
}
start_pfn++;
}
return ret;
}
void wait_for_freed_hugetlb_folios(void)
{
if (llist_empty(&hpage_freelist))
return;
flush_work(&free_hpage_work);
}
typedef enum {
/*
* For either 0/1: we checked the per-vma resv map, and one resv
* count either can be reused (0), or an extra needed (1).
*/
MAP_CHG_REUSE = 0,
MAP_CHG_NEEDED = 1,
/*
* Cannot use per-vma resv count can be used, hence a new resv
* count is enforced.
*
* NOTE: This is mostly identical to MAP_CHG_NEEDED, except
* that currently vma_needs_reservation() has an unwanted side
* effect to either use end() or commit() to complete the
* transaction. Hence it needs to differenciate from NEEDED.
*/
MAP_CHG_ENFORCED = 2,
} map_chg_state;
/*
* NOTE! "cow_from_owner" represents a very hacky usage only used in CoW
* faults of hugetlb private mappings on top of a non-page-cache folio (in
* which case even if there's a private vma resv map it won't cover such
* allocation). New call sites should (probably) never set it to true!!
* When it's set, the allocation will bypass all vma level reservations.
*/
struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, bool cow_from_owner)
{
struct hugepage_subpool *spool = subpool_vma(vma);
struct hstate *h = hstate_vma(vma);
struct folio *folio;
long retval, gbl_chg;
map_chg_state map_chg;
int ret, idx;
struct hugetlb_cgroup *h_cg = NULL;
gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL;
idx = hstate_index(h);
/* Whether we need a separate per-vma reservation? */
if (cow_from_owner) {
/*
* Special case! Since it's a CoW on top of a reserved
* page, the private resv map doesn't count. So it cannot
* consume the per-vma resv map even if it's reserved.
*/
map_chg = MAP_CHG_ENFORCED;
} else {
/*
* Examine the region/reserve map to determine if the process
* has a reservation for the page to be allocated. A return
* code of zero indicates a reservation exists (no change).
*/
retval = vma_needs_reservation(h, vma, addr);
if (retval < 0)
return ERR_PTR(-ENOMEM);
map_chg = retval ? MAP_CHG_NEEDED : MAP_CHG_REUSE;
}
/*
* Whether we need a separate global reservation?
*
* Processes that did not create the mapping will have no
* reserves as indicated by the region/reserve map. Check
* that the allocation will not exceed the subpool limit.
* Or if it can get one from the pool reservation directly.
*/
if (map_chg) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0)
goto out_end_reservation;
} else {
/*
* If we have the vma reservation ready, no need for extra
* global reservation.
*/
gbl_chg = 0;
}
/*
* If this allocation is not consuming a per-vma reservation,
* charge the hugetlb cgroup now.
*/
if (map_chg) {
ret = hugetlb_cgroup_charge_cgroup_rsvd(
idx, pages_per_huge_page(h), &h_cg);
if (ret)
goto out_subpool_put;
}
ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
if (ret)
goto out_uncharge_cgroup_reservation;
spin_lock_irq(&hugetlb_lock);
/*
* glb_chg is passed to indicate whether or not a page must be taken
* from the global free pool (global change). gbl_chg == 0 indicates
* a reservation exists for the allocation.
*/
folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) {
spin_unlock_irq(&hugetlb_lock);
folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr);
if (!folio)
goto out_uncharge_cgroup;
spin_lock_irq(&hugetlb_lock);
list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1);
/* Fall through */
}
/*
* Either dequeued or buddy-allocated folio needs to add special
* mark to the folio when it consumes a global reservation.
*/
if (!gbl_chg) { folio_set_hugetlb_restore_reserve(folio);
h->resv_huge_pages--;
}
hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio);
/* If allocation is not consuming a reservation, also store the
* hugetlb_cgroup pointer on the page.
*/
if (map_chg) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
h_cg, folio);
}
spin_unlock_irq(&hugetlb_lock);
hugetlb_set_folio_subpool(folio, spool);
if (map_chg != MAP_CHG_ENFORCED) {
/* commit() is only needed if the map_chg is not enforced */
retval = vma_commit_reservation(h, vma, addr);
/*
* Check for possible race conditions. When it happens..
* The page was added to the reservation map between
* vma_needs_reservation and vma_commit_reservation.
* This indicates a race with hugetlb_reserve_pages.
* Adjust for the subpool count incremented above AND
* in hugetlb_reserve_pages for the same page. Also,
* the reservation count added in hugetlb_reserve_pages
* no longer applies.
*/
if (unlikely(map_chg == MAP_CHG_NEEDED && retval == 0)) {
long rsv_adjust;
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
if (map_chg) {
spin_lock_irq(&hugetlb_lock);
hugetlb_cgroup_uncharge_folio_rsvd(
hstate_index(h), pages_per_huge_page(h),
folio);
spin_unlock_irq(&hugetlb_lock);
}
}
}
ret = mem_cgroup_charge_hugetlb(folio, gfp);
/*
* Unconditionally increment NR_HUGETLB here. If it turns out that
* mem_cgroup_charge_hugetlb failed, then immediately free the page and
* decrement NR_HUGETLB.
*/
lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); if (ret == -ENOMEM) { free_huge_folio(folio);
return ERR_PTR(-ENOMEM);
}
return folio;
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
out_uncharge_cgroup_reservation:
if (map_chg) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
h_cg);
out_subpool_put:
if (map_chg)
hugepage_subpool_put_pages(spool, 1);
out_end_reservation:
if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr);
return ERR_PTR(-ENOSPC);
}
static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact)
{
struct huge_bootmem_page *m;
int listnode = nid;
if (hugetlb_early_cma(h))
m = hugetlb_cma_alloc_bootmem(h, &listnode, node_exact);
else {
if (node_exact)
m = memblock_alloc_exact_nid_raw(huge_page_size(h),
huge_page_size(h), 0,
MEMBLOCK_ALLOC_ACCESSIBLE, nid);
else {
m = memblock_alloc_try_nid_raw(huge_page_size(h),
huge_page_size(h), 0,
MEMBLOCK_ALLOC_ACCESSIBLE, nid);
/*
* For pre-HVO to work correctly, pages need to be on
* the list for the node they were actually allocated
* from. That node may be different in the case of
* fallback by memblock_alloc_try_nid_raw. So,
* extract the actual node first.
*/
if (m)
listnode = early_pfn_to_nid(PHYS_PFN(virt_to_phys(m)));
}
if (m) {
m->flags = 0;
m->cma = NULL;
}
}
if (m) {
/*
* Use the beginning of the huge page to store the
* huge_bootmem_page struct (until gather_bootmem
* puts them into the mem_map).
*
* Put them into a private list first because mem_map
* is not up yet.
*/
INIT_LIST_HEAD(&m->list);
list_add(&m->list, &huge_boot_pages[listnode]);
m->hstate = h;
}
return m;
}
int alloc_bootmem_huge_page(struct hstate *h, int nid)
__attribute__ ((weak, alias("__alloc_bootmem_huge_page")));
int __alloc_bootmem_huge_page(struct hstate *h, int nid)
{
struct huge_bootmem_page *m = NULL; /* initialize for clang */
int nr_nodes, node = nid;
/* do node specific alloc */
if (nid != NUMA_NO_NODE) {
m = alloc_bootmem(h, node, true);
if (!m)
return 0;
goto found;
}
/* allocate from next node when distributing huge pages */
for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_ONLINE]) {
m = alloc_bootmem(h, node, false);
if (!m)
return 0;
goto found;
}
found:
/*
* Only initialize the head struct page in memmap_init_reserved_pages,
* rest of the struct pages will be initialized by the HugeTLB
* subsystem itself.
* The head struct page is used to get folio information by the HugeTLB
* subsystem like zone id and node id.
*/
memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE),
huge_page_size(h) - PAGE_SIZE);
return 1;
}
/* Initialize [start_page:end_page_number] tail struct pages of a hugepage */
static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio,
unsigned long start_page_number,
unsigned long end_page_number)
{
enum zone_type zone = zone_idx(folio_zone(folio));
int nid = folio_nid(folio);
unsigned long head_pfn = folio_pfn(folio);
unsigned long pfn, end_pfn = head_pfn + end_page_number;
int ret;
for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) {
struct page *page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid);
prep_compound_tail((struct page *)folio, pfn - head_pfn);
ret = page_ref_freeze(page, 1);
VM_BUG_ON(!ret);
}
}
static void __init hugetlb_folio_init_vmemmap(struct folio *folio,
struct hstate *h,
unsigned long nr_pages)
{
int ret;
/* Prepare folio head */
__folio_clear_reserved(folio);
__folio_set_head(folio);
ret = folio_ref_freeze(folio, 1);
VM_BUG_ON(!ret);
/* Initialize the necessary tail struct pages */
hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages);
prep_compound_head((struct page *)folio, huge_page_order(h));
}
static bool __init hugetlb_bootmem_page_prehvo(struct huge_bootmem_page *m)
{
return m->flags & HUGE_BOOTMEM_HVO;
}
static bool __init hugetlb_bootmem_page_earlycma(struct huge_bootmem_page *m)
{
return m->flags & HUGE_BOOTMEM_CMA;
}
/*
* memblock-allocated pageblocks might not have the migrate type set
* if marked with the 'noinit' flag. Set it to the default (MIGRATE_MOVABLE)
* here, or MIGRATE_CMA if this was a page allocated through an early CMA
* reservation.
*
* In case of vmemmap optimized folios, the tail vmemmap pages are mapped
* read-only, but that's ok - for sparse vmemmap this does not write to
* the page structure.
*/
static void __init hugetlb_bootmem_init_migratetype(struct folio *folio,
struct hstate *h)
{
unsigned long nr_pages = pages_per_huge_page(h), i;
WARN_ON_ONCE(!pageblock_aligned(folio_pfn(folio)));
for (i = 0; i < nr_pages; i += pageblock_nr_pages) {
if (folio_test_hugetlb_cma(folio))
init_cma_pageblock(folio_page(folio, i));
else
set_pageblock_migratetype(folio_page(folio, i),
MIGRATE_MOVABLE);
}
}
static void __init prep_and_add_bootmem_folios(struct hstate *h,
struct list_head *folio_list)
{
unsigned long flags;
struct folio *folio, *tmp_f;
/* Send list for bulk vmemmap optimization processing */
hugetlb_vmemmap_optimize_bootmem_folios(h, folio_list);
list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
/*
* If HVO fails, initialize all tail struct pages
* We do not worry about potential long lock hold
* time as this is early in boot and there should
* be no contention.
*/
hugetlb_folio_init_tail_vmemmap(folio,
HUGETLB_VMEMMAP_RESERVE_PAGES,
pages_per_huge_page(h));
}
hugetlb_bootmem_init_migratetype(folio, h);
/* Subdivide locks to achieve better parallel performance */
spin_lock_irqsave(&hugetlb_lock, flags);
__prep_account_new_huge_page(h, folio_nid(folio));
enqueue_hugetlb_folio(h, folio);
spin_unlock_irqrestore(&hugetlb_lock, flags);
}
}
bool __init hugetlb_bootmem_page_zones_valid(int nid,
struct huge_bootmem_page *m)
{
unsigned long start_pfn;
bool valid;
if (m->flags & HUGE_BOOTMEM_ZONES_VALID) {
/*
* Already validated, skip check.
*/
return true;
}
if (hugetlb_bootmem_page_earlycma(m)) {
valid = cma_validate_zones(m->cma);
goto out;
}
start_pfn = virt_to_phys(m) >> PAGE_SHIFT;
valid = !pfn_range_intersects_zones(nid, start_pfn,
pages_per_huge_page(m->hstate));
out:
if (!valid)
hstate_boot_nrinvalid[hstate_index(m->hstate)]++;
return valid;
}
/*
* Free a bootmem page that was found to be invalid (intersecting with
* multiple zones).
*
* Since it intersects with multiple zones, we can't just do a free
* operation on all pages at once, but instead have to walk all
* pages, freeing them one by one.
*/
static void __init hugetlb_bootmem_free_invalid_page(int nid, struct page *page,
struct hstate *h)
{
unsigned long npages = pages_per_huge_page(h);
unsigned long pfn;
while (npages--) {
pfn = page_to_pfn(page);
__init_page_from_nid(pfn, nid);
free_reserved_page(page);
page++;
}
}
/*
* Put bootmem huge pages into the standard lists after mem_map is up.
* Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages.
*/
static void __init gather_bootmem_prealloc_node(unsigned long nid)
{
LIST_HEAD(folio_list);
struct huge_bootmem_page *m, *tm;
struct hstate *h = NULL, *prev_h = NULL;
list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) {
struct page *page = virt_to_page(m);
struct folio *folio = (void *)page;
h = m->hstate;
if (!hugetlb_bootmem_page_zones_valid(nid, m)) {
/*
* Can't use this page. Initialize the
* page structures if that hasn't already
* been done, and give them to the page
* allocator.
*/
hugetlb_bootmem_free_invalid_page(nid, page, h);
continue;
}
/*
* It is possible to have multiple huge page sizes (hstates)
* in this list. If so, process each size separately.
*/
if (h != prev_h && prev_h != NULL)
prep_and_add_bootmem_folios(prev_h, &folio_list);
prev_h = h;
VM_BUG_ON(!hstate_is_gigantic(h));
WARN_ON(folio_ref_count(folio) != 1);
hugetlb_folio_init_vmemmap(folio, h,
HUGETLB_VMEMMAP_RESERVE_PAGES);
init_new_hugetlb_folio(h, folio);
if (hugetlb_bootmem_page_prehvo(m))
/*
* If pre-HVO was done, just set the
* flag, the HVO code will then skip
* this folio.
*/
folio_set_hugetlb_vmemmap_optimized(folio);
if (hugetlb_bootmem_page_earlycma(m))
folio_set_hugetlb_cma(folio);
list_add(&folio->lru, &folio_list);
/*
* We need to restore the 'stolen' pages to totalram_pages
* in order to fix confusing memory reports from free(1) and
* other side-effects, like CommitLimit going negative.
*
* For CMA pages, this is done in init_cma_pageblock
* (via hugetlb_bootmem_init_migratetype), so skip it here.
*/
if (!folio_test_hugetlb_cma(folio))
adjust_managed_page_count(page, pages_per_huge_page(h));
cond_resched();
}
prep_and_add_bootmem_folios(h, &folio_list);
}
static void __init gather_bootmem_prealloc_parallel(unsigned long start,
unsigned long end, void *arg)
{
int nid;
for (nid = start; nid < end; nid++)
gather_bootmem_prealloc_node(nid);
}
static void __init gather_bootmem_prealloc(void)
{
struct padata_mt_job job = {
.thread_fn = gather_bootmem_prealloc_parallel,
.fn_arg = NULL,
.start = 0,
.size = nr_node_ids,
.align = 1,
.min_chunk = 1,
.max_threads = num_node_state(N_MEMORY),
.numa_aware = true,
};
padata_do_multithreaded(&job);
}
static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
{
unsigned long i;
char buf[32];
LIST_HEAD(folio_list);
for (i = 0; i < h->max_huge_pages_node[nid]; ++i) {
if (hstate_is_gigantic(h)) {
if (!alloc_bootmem_huge_page(h, nid))
break;
} else {
struct folio *folio;
gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid,
&node_states[N_MEMORY], NULL);
if (!folio)
break;
list_add(&folio->lru, &folio_list);
}
cond_resched();
}
if (!list_empty(&folio_list))
prep_and_add_allocated_folios(h, &folio_list);
if (i == h->max_huge_pages_node[nid])
return;
string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n",
h->max_huge_pages_node[nid], buf, nid, i);
h->max_huge_pages -= (h->max_huge_pages_node[nid] - i);
h->max_huge_pages_node[nid] = i;
}
static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h)
{
int i;
bool node_specific_alloc = false;
for_each_online_node(i) {
if (h->max_huge_pages_node[i] > 0) {
hugetlb_hstate_alloc_pages_onenode(h, i);
node_specific_alloc = true;
}
}
return node_specific_alloc;
}
static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h)
{
if (allocated < h->max_huge_pages) {
char buf[32];
string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n",
h->max_huge_pages, buf, allocated);
h->max_huge_pages = allocated;
}
}
static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg)
{
struct hstate *h = (struct hstate *)arg;
int i, num = end - start;
nodemask_t node_alloc_noretry;
LIST_HEAD(folio_list);
int next_node = first_online_node;
/* Bit mask controlling how hard we retry per-node allocations.*/
nodes_clear(node_alloc_noretry);
for (i = 0; i < num; ++i) {
struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
&node_alloc_noretry, &next_node);
if (!folio)
break;
list_move(&folio->lru, &folio_list);
cond_resched();
}
prep_and_add_allocated_folios(h, &folio_list);
}
static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h)
{
unsigned long i;
for (i = 0; i < h->max_huge_pages; ++i) {
if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
break;
cond_resched();
}
return i;
}
static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
{
struct padata_mt_job job = {
.fn_arg = h,
.align = 1,
.numa_aware = true
};
unsigned long jiffies_start;
unsigned long jiffies_end;
job.thread_fn = hugetlb_pages_alloc_boot_node;
job.start = 0;
job.size = h->max_huge_pages;
/*
* job.max_threads is 25% of the available cpu threads by default.
*
* On large servers with terabytes of memory, huge page allocation
* can consume a considerably amount of time.
*
* Tests below show how long it takes to allocate 1 TiB of memory with 2MiB huge pages.
* 2MiB huge pages. Using more threads can significantly improve allocation time.
*
* +-----------------------+-------+-------+-------+-------+-------+
* | threads | 8 | 16 | 32 | 64 | 128 |
* +-----------------------+-------+-------+-------+-------+-------+
* | skylake 144 cpus | 44s | 22s | 16s | 19s | 20s |
* | cascade lake 192 cpus | 39s | 20s | 11s | 10s | 9s |
* +-----------------------+-------+-------+-------+-------+-------+
*/
if (hugepage_allocation_threads == 0) {
hugepage_allocation_threads = num_online_cpus() / 4;
hugepage_allocation_threads = max(hugepage_allocation_threads, 1);
}
job.max_threads = hugepage_allocation_threads;
job.min_chunk = h->max_huge_pages / hugepage_allocation_threads;
jiffies_start = jiffies;
padata_do_multithreaded(&job);
jiffies_end = jiffies;
pr_info("HugeTLB: allocation took %dms with hugepage_allocation_threads=%ld\n",
jiffies_to_msecs(jiffies_end - jiffies_start),
hugepage_allocation_threads);
return h->nr_huge_pages;
}
/*
* NOTE: this routine is called in different contexts for gigantic and
* non-gigantic pages.
* - For gigantic pages, this is called early in the boot process and
* pages are allocated from memblock allocated or something similar.
* Gigantic pages are actually added to pools later with the routine
* gather_bootmem_prealloc.
* - For non-gigantic pages, this is called later in the boot process after
* all of mm is up and functional. Pages are allocated from buddy and
* then added to hugetlb pools.
*/
static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
unsigned long allocated;
/*
* Skip gigantic hugepages allocation if early CMA
* reservations are not available.
*/
if (hstate_is_gigantic(h) && hugetlb_cma_total_size() &&
!hugetlb_early_cma(h)) {
pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
return;
}
/* do node specific alloc */
if (hugetlb_hstate_alloc_pages_specific_nodes(h))
return;
/* below will do all node balanced alloc */
if (hstate_is_gigantic(h))
allocated = hugetlb_gigantic_pages_alloc_boot(h);
else
allocated = hugetlb_pages_alloc_boot(h);
hugetlb_hstate_alloc_pages_errcheck(allocated, h);
}
static void __init hugetlb_init_hstates(void)
{
struct hstate *h, *h2;
for_each_hstate(h) {
/* oversize hugepages were init'ed in early boot */
if (!hstate_is_gigantic(h))
hugetlb_hstate_alloc_pages(h);
/*
* Set demote order for each hstate. Note that
* h->demote_order is initially 0.
* - We can not demote gigantic pages if runtime freeing
* is not supported, so skip this.
* - If CMA allocation is possible, we can not demote
* HUGETLB_PAGE_ORDER or smaller size pages.
*/
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
continue;
if (hugetlb_cma_total_size() && h->order <= HUGETLB_PAGE_ORDER)
continue;
for_each_hstate(h2) {
if (h2 == h)
continue;
if (h2->order < h->order &&
h2->order > h->demote_order)
h->demote_order = h2->order;
}
}
}
static void __init report_hugepages(void)
{
struct hstate *h;
unsigned long nrinvalid;
for_each_hstate(h) {
char buf[32];
nrinvalid = hstate_boot_nrinvalid[hstate_index(h)];
h->max_huge_pages -= nrinvalid;
string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n",
buf, h->free_huge_pages);
if (nrinvalid)
pr_info("HugeTLB: %s page size: %lu invalid page%s discarded\n",
buf, nrinvalid, nrinvalid > 1 ? "s" : "");
pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n",
hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf);
}
}
#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
nodemask_t *nodes_allowed)
{
int i;
LIST_HEAD(page_list);
lockdep_assert_held(&hugetlb_lock);
if (hstate_is_gigantic(h))
return;
/*
* Collect pages to be freed on a list, and free after dropping lock
*/
for_each_node_mask(i, *nodes_allowed) {
struct folio *folio, *next;
struct list_head *freel = &h->hugepage_freelists[i];
list_for_each_entry_safe(folio, next, freel, lru) {
if (count >= h->nr_huge_pages)
goto out;
if (folio_test_highmem(folio))
continue;
remove_hugetlb_folio(h, folio, false);
list_add(&folio->lru, &page_list);
}
}
out:
spin_unlock_irq(&hugetlb_lock);
update_and_free_pages_bulk(h, &page_list);
spin_lock_irq(&hugetlb_lock);
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count,
nodemask_t *nodes_allowed)
{
}
#endif
/*
* Increment or decrement surplus_huge_pages. Keep node-specific counters
* balanced by operating on them in a round-robin fashion.
* Returns 1 if an adjustment was made.
*/
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
int delta)
{
int nr_nodes, node;
lockdep_assert_held(&hugetlb_lock);
VM_BUG_ON(delta != -1 && delta != 1);
if (delta < 0) {
for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) {
if (h->surplus_huge_pages_node[node])
goto found;
}
} else {
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
if (h->surplus_huge_pages_node[node] <
h->nr_huge_pages_node[node])
goto found;
}
}
return 0;
found:
h->surplus_huge_pages += delta;
h->surplus_huge_pages_node[node] += delta;
return 1;
}
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
nodemask_t *nodes_allowed)
{
unsigned long persistent_free_count;
unsigned long min_count;
unsigned long allocated;
struct folio *folio;
LIST_HEAD(page_list);
NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
/*
* Bit mask controlling how hard we retry per-node allocations.
* If we can not allocate the bit mask, do not attempt to allocate
* the requested huge pages.
*/
if (node_alloc_noretry)
nodes_clear(*node_alloc_noretry);
else
return -ENOMEM;
/*
* resize_lock mutex prevents concurrent adjustments to number of
* pages in hstate via the proc/sysfs interfaces.
*/
mutex_lock(&h->resize_lock);
flush_free_hpage_work(h);
spin_lock_irq(&hugetlb_lock);
/*
* Check for a node specific request.
* Changing node specific huge page count may require a corresponding
* change to the global count. In any case, the passed node mask
* (nodes_allowed) will restrict alloc/free to the specified node.
*/
if (nid != NUMA_NO_NODE) {
unsigned long old_count = count;
count += persistent_huge_pages(h) -
(h->nr_huge_pages_node[nid] -
h->surplus_huge_pages_node[nid]);
/*
* User may have specified a large count value which caused the
* above calculation to overflow. In this case, they wanted
* to allocate as many huge pages as possible. Set count to
* largest possible value to align with their intention.
*/
if (count < old_count)
count = ULONG_MAX;
}
/*
* Gigantic pages runtime allocation depend on the capability for large
* page range allocation.
* If the system does not provide this feature, return an error when
* the user tries to allocate gigantic pages but let the user free the
* boottime allocated gigantic pages.
*/
if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
if (count > persistent_huge_pages(h)) {
spin_unlock_irq(&hugetlb_lock);
mutex_unlock(&h->resize_lock);
NODEMASK_FREE(node_alloc_noretry);
return -EINVAL;
}
/* Fall through to decrease pool */
}
/*
* Increase the pool size
* First take pages out of surplus state. Then make up the
* remaining difference by allocating fresh huge pages.
*
* We might race with alloc_surplus_hugetlb_folio() here and be unable
* to convert a surplus huge page to a normal huge page. That is
* not critical, though, it just means the overall size of the
* pool might be one hugepage larger than it needs to be, but
* within all the constraints specified by the sysctls.
*/
while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, -1))
break;
}
allocated = 0;
while (count > (persistent_huge_pages(h) + allocated)) {
/*
* If this allocation races such that we no longer need the
* page, free_huge_folio will handle it by freeing the page
* and reducing the surplus.
*/
spin_unlock_irq(&hugetlb_lock);
/* yield cpu to avoid soft lockup */
cond_resched();
folio = alloc_pool_huge_folio(h, nodes_allowed,
node_alloc_noretry,
&h->next_nid_to_alloc);
if (!folio) {
prep_and_add_allocated_folios(h, &page_list);
spin_lock_irq(&hugetlb_lock);
goto out;
}
list_add(&folio->lru, &page_list);
allocated++;
/* Bail for signals. Probably ctrl-c from user */
if (signal_pending(current)) {
prep_and_add_allocated_folios(h, &page_list);
spin_lock_irq(&hugetlb_lock);
goto out;
}
spin_lock_irq(&hugetlb_lock);
}
/* Add allocated pages to the pool */
if (!list_empty(&page_list)) {
spin_unlock_irq(&hugetlb_lock);
prep_and_add_allocated_folios(h, &page_list);
spin_lock_irq(&hugetlb_lock);
}
/*
* Decrease the pool size
* First return free pages to the buddy allocator (being careful
* to keep enough around to satisfy reservations). Then place
* pages into surplus state as needed so the pool will shrink
* to the desired size as pages become free.
*
* By placing pages into the surplus state independent of the
* overcommit value, we are allowing the surplus pool size to
* exceed overcommit. There are few sane options here. Since
* alloc_surplus_hugetlb_folio() is checking the global counter,
* though, we'll note that we're not allowed to exceed surplus
* and won't grow the pool anywhere else. Not until one of the
* sysctls are changed, or the surplus pages go out of use.
*
* min_count is the expected number of persistent pages, we
* shouldn't calculate min_count by using
* resv_huge_pages + persistent_huge_pages() - free_huge_pages,
* because there may exist free surplus huge pages, and this will
* lead to subtracting twice. Free surplus huge pages come from HVO
* failing to restore vmemmap, see comments in the callers of
* hugetlb_vmemmap_restore_folio(). Thus, we should calculate
* persistent free count first.
*/
persistent_free_count = h->free_huge_pages;
if (h->free_huge_pages > persistent_huge_pages(h)) {
if (h->free_huge_pages > h->surplus_huge_pages)
persistent_free_count -= h->surplus_huge_pages;
else
persistent_free_count = 0;
}
min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count;
min_count = max(count, min_count);
try_to_free_low(h, min_count, nodes_allowed);
/*
* Collect pages to be removed on list without dropping lock
*/
while (min_count < persistent_huge_pages(h)) {
folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0);
if (!folio)
break;
list_add(&folio->lru, &page_list);
}
/* free the pages after dropping lock */
spin_unlock_irq(&hugetlb_lock);
update_and_free_pages_bulk(h, &page_list);
flush_free_hpage_work(h);
spin_lock_irq(&hugetlb_lock);
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
break;
}
out:
h->max_huge_pages = persistent_huge_pages(h);
spin_unlock_irq(&hugetlb_lock);
mutex_unlock(&h->resize_lock);
NODEMASK_FREE(node_alloc_noretry);
return 0;
}
static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
struct list_head *src_list)
{
long rc;
struct folio *folio, *next;
LIST_HEAD(dst_list);
LIST_HEAD(ret_list);
rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list);
list_splice_init(&ret_list, src_list);
/*
* Taking target hstate mutex synchronizes with set_max_huge_pages.
* Without the mutex, pages added to target hstate could be marked
* as surplus.
*
* Note that we already hold src->resize_lock. To prevent deadlock,
* use the convention of always taking larger size hstate mutex first.
*/
mutex_lock(&dst->resize_lock);
list_for_each_entry_safe(folio, next, src_list, lru) {
int i;
if (folio_test_hugetlb_vmemmap_optimized(folio))
continue;
list_del(&folio->lru);
split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst));
for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) {
struct page *page = folio_page(folio, i);
/* Careful: see __split_huge_page_tail() */
struct folio *new_folio = (struct folio *)page;
clear_compound_head(page);
prep_compound_page(page, dst->order);
new_folio->mapping = NULL;
init_new_hugetlb_folio(dst, new_folio);
list_add(&new_folio->lru, &dst_list);
}
}
prep_and_add_allocated_folios(dst, &dst_list);
mutex_unlock(&dst->resize_lock);
return rc;
}
static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed,
unsigned long nr_to_demote)
__must_hold(&hugetlb_lock)
{
int nr_nodes, node;
struct hstate *dst;
long rc = 0;
long nr_demoted = 0;
lockdep_assert_held(&hugetlb_lock);
/* We should never get here if no demote order */
if (!src->demote_order) {
pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n");
return -EINVAL; /* internal error */
}
dst = size_to_hstate(PAGE_SIZE << src->demote_order);
for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) {
LIST_HEAD(list);
struct folio *folio, *next;
list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) {
if (folio_test_hwpoison(folio))
continue;
remove_hugetlb_folio(src, folio, false);
list_add(&folio->lru, &list);
if (++nr_demoted == nr_to_demote)
break;
}
spin_unlock_irq(&hugetlb_lock);
rc = demote_free_hugetlb_folios(src, dst, &list);
spin_lock_irq(&hugetlb_lock);
list_for_each_entry_safe(folio, next, &list, lru) {
list_del(&folio->lru);
add_hugetlb_folio(src, folio, false);
nr_demoted--;
}
if (rc < 0 || nr_demoted == nr_to_demote)
break;
}
/*
* Not absolutely necessary, but for consistency update max_huge_pages
* based on pool changes for the demoted page.
*/
src->max_huge_pages -= nr_demoted;
dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst));
if (rc < 0)
return rc;
if (nr_demoted)
return nr_demoted;
/*
* Only way to get here is if all pages on free lists are poisoned.
* Return -EBUSY so that caller will not retry.
*/
return -EBUSY;
}
#define HSTATE_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define HSTATE_ATTR_WO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_WO(_name)
#define HSTATE_ATTR(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RW(_name)
static struct kobject *hugepages_kobj;
static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);
static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
{
int i;
for (i = 0; i < HUGE_MAX_HSTATE; i++)
if (hstate_kobjs[i] == kobj) {
if (nidp)
*nidp = NUMA_NO_NODE;
return &hstates[i];
}
return kobj_to_node_hstate(kobj, nidp);
}
static ssize_t nr_hugepages_show_common(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h;
unsigned long nr_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
nr_huge_pages = h->nr_huge_pages;
else
nr_huge_pages = h->nr_huge_pages_node[nid];
return sysfs_emit(buf, "%lu\n", nr_huge_pages);
}
static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
struct hstate *h, int nid,
unsigned long count, size_t len)
{
int err;
nodemask_t nodes_allowed, *n_mask;
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return -EINVAL;
if (nid == NUMA_NO_NODE) {
/*
* global hstate attribute
*/
if (!(obey_mempolicy &&
init_nodemask_of_mempolicy(&nodes_allowed)))
n_mask = &node_states[N_MEMORY];
else
n_mask = &nodes_allowed;
} else {
/*
* Node specific request. count adjustment happens in
* set_max_huge_pages() after acquiring hugetlb_lock.
*/
init_nodemask_of_node(&nodes_allowed, nid);
n_mask = &nodes_allowed;
}
err = set_max_huge_pages(h, count, nid, n_mask);
return err ? err : len;
}
static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
struct kobject *kobj, const char *buf,
size_t len)
{
struct hstate *h;
unsigned long count;
int nid;
int err;
err = kstrtoul(buf, 10, &count);
if (err)
return err;
h = kobj_to_hstate(kobj, &nid);
return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len);
}
static ssize_t nr_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return nr_hugepages_show_common(kobj, attr, buf);
}
static ssize_t nr_hugepages_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t len)
{
return nr_hugepages_store_common(false, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages);
#ifdef CONFIG_NUMA
/*
* hstate attribute for optionally mempolicy-based constraint on persistent
* huge page alloc/free.
*/
static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return nr_hugepages_show_common(kobj, attr, buf);
}
static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t len)
{
return nr_hugepages_store_common(true, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages_mempolicy);
#endif
static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h = kobj_to_hstate(kobj, NULL);
return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages);
}
static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
int err;
unsigned long input;
struct hstate *h = kobj_to_hstate(kobj, NULL);
if (hstate_is_gigantic(h))
return -EINVAL;
err = kstrtoul(buf, 10, &input);
if (err)
return err;
spin_lock_irq(&hugetlb_lock);
h->nr_overcommit_huge_pages = input;
spin_unlock_irq(&hugetlb_lock);
return count;
}
HSTATE_ATTR(nr_overcommit_hugepages);
static ssize_t free_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h;
unsigned long free_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
free_huge_pages = h->free_huge_pages;
else
free_huge_pages = h->free_huge_pages_node[nid];
return sysfs_emit(buf, "%lu\n", free_huge_pages);
}
HSTATE_ATTR_RO(free_hugepages);
static ssize_t resv_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h = kobj_to_hstate(kobj, NULL);
return sysfs_emit(buf, "%lu\n", h->resv_huge_pages);
}
HSTATE_ATTR_RO(resv_hugepages);
static ssize_t surplus_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h;
unsigned long surplus_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
surplus_huge_pages = h->surplus_huge_pages;
else
surplus_huge_pages = h->surplus_huge_pages_node[nid];
return sysfs_emit(buf, "%lu\n", surplus_huge_pages);
}
HSTATE_ATTR_RO(surplus_hugepages);
static ssize_t demote_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t len)
{
unsigned long nr_demote;
unsigned long nr_available;
nodemask_t nodes_allowed, *n_mask;
struct hstate *h;
int err;
int nid;
err = kstrtoul(buf, 10, &nr_demote);
if (err)
return err;
h = kobj_to_hstate(kobj, &nid);
if (nid != NUMA_NO_NODE) {
init_nodemask_of_node(&nodes_allowed, nid);
n_mask = &nodes_allowed;
} else {
n_mask = &node_states[N_MEMORY];
}
/* Synchronize with other sysfs operations modifying huge pages */
mutex_lock(&h->resize_lock);
spin_lock_irq(&hugetlb_lock);
while (nr_demote) {
long rc;
/*
* Check for available pages to demote each time thorough the
* loop as demote_pool_huge_page will drop hugetlb_lock.
*/
if (nid != NUMA_NO_NODE)
nr_available = h->free_huge_pages_node[nid];
else
nr_available = h->free_huge_pages;
nr_available -= h->resv_huge_pages;
if (!nr_available)
break;
rc = demote_pool_huge_page(h, n_mask, nr_demote);
if (rc < 0) {
err = rc;
break;
}
nr_demote -= rc;
}
spin_unlock_irq(&hugetlb_lock);
mutex_unlock(&h->resize_lock);
if (err)
return err;
return len;
}
HSTATE_ATTR_WO(demote);
static ssize_t demote_size_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h = kobj_to_hstate(kobj, NULL);
unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K;
return sysfs_emit(buf, "%lukB\n", demote_size);
}
static ssize_t demote_size_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
struct hstate *h, *demote_hstate;
unsigned long demote_size;
unsigned int demote_order;
demote_size = (unsigned long)memparse(buf, NULL);
demote_hstate = size_to_hstate(demote_size);
if (!demote_hstate)
return -EINVAL;
demote_order = demote_hstate->order;
if (demote_order < HUGETLB_PAGE_ORDER)
return -EINVAL;
/* demote order must be smaller than hstate order */
h = kobj_to_hstate(kobj, NULL);
if (demote_order >= h->order)
return -EINVAL;
/* resize_lock synchronizes access to demote size and writes */
mutex_lock(&h->resize_lock);
h->demote_order = demote_order;
mutex_unlock(&h->resize_lock);
return count;
}
HSTATE_ATTR(demote_size);
static struct attribute *hstate_attrs[] = {
&nr_hugepages_attr.attr,
&nr_overcommit_hugepages_attr.attr,
&free_hugepages_attr.attr,
&resv_hugepages_attr.attr,
&surplus_hugepages_attr.attr,
#ifdef CONFIG_NUMA
&nr_hugepages_mempolicy_attr.attr,
#endif
NULL,
};
static const struct attribute_group hstate_attr_group = {
.attrs = hstate_attrs,
};
static struct attribute *hstate_demote_attrs[] = {
&demote_size_attr.attr,
&demote_attr.attr,
NULL,
};
static const struct attribute_group hstate_demote_attr_group = {
.attrs = hstate_demote_attrs,
};
static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
struct kobject **hstate_kobjs,
const struct attribute_group *hstate_attr_group)
{
int retval;
int hi = hstate_index(h);
hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
if (!hstate_kobjs[hi])
return -ENOMEM;
retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
if (retval) {
kobject_put(hstate_kobjs[hi]);
hstate_kobjs[hi] = NULL;
return retval;
}
if (h->demote_order) {
retval = sysfs_create_group(hstate_kobjs[hi],
&hstate_demote_attr_group);
if (retval) {
pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name);
sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group);
kobject_put(hstate_kobjs[hi]);
hstate_kobjs[hi] = NULL;
return retval;
}
}
return 0;
}
#ifdef CONFIG_NUMA
static bool hugetlb_sysfs_initialized __ro_after_init;
/*
* node_hstate/s - associate per node hstate attributes, via their kobjects,
* with node devices in node_devices[] using a parallel array. The array
* index of a node device or _hstate == node id.
* This is here to avoid any static dependency of the node device driver, in
* the base kernel, on the hugetlb module.
*/
struct node_hstate {
struct kobject *hugepages_kobj;
struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
};
static struct node_hstate node_hstates[MAX_NUMNODES];
/*
* A subset of global hstate attributes for node devices
*/
static struct attribute *per_node_hstate_attrs[] = {
&nr_hugepages_attr.attr,
&free_hugepages_attr.attr,
&surplus_hugepages_attr.attr,
NULL,
};
static const struct attribute_group per_node_hstate_attr_group = {
.attrs = per_node_hstate_attrs,
};
/*
* kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
* Returns node id via non-NULL nidp.
*/
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
int nid;
for (nid = 0; nid < nr_node_ids; nid++) {
struct node_hstate *nhs = &node_hstates[nid];
int i;
for (i = 0; i < HUGE_MAX_HSTATE; i++)
if (nhs->hstate_kobjs[i] == kobj) {
if (nidp)
*nidp = nid;
return &hstates[i];
}
}
BUG();
return NULL;
}
/*
* Unregister hstate attributes from a single node device.
* No-op if no hstate attributes attached.
*/
void hugetlb_unregister_node(struct node *node)
{
struct hstate *h;
struct node_hstate *nhs = &node_hstates[node->dev.id];
if (!nhs->hugepages_kobj)
return; /* no hstate attributes */
for_each_hstate(h) {
int idx = hstate_index(h);
struct kobject *hstate_kobj = nhs->hstate_kobjs[idx];
if (!hstate_kobj)
continue;
if (h->demote_order)
sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group);
sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group);
kobject_put(hstate_kobj);
nhs->hstate_kobjs[idx] = NULL;
}
kobject_put(nhs->hugepages_kobj);
nhs->hugepages_kobj = NULL;
}
/*
* Register hstate attributes for a single node device.
* No-op if attributes already registered.
*/
void hugetlb_register_node(struct node *node)
{
struct hstate *h;
struct node_hstate *nhs = &node_hstates[node->dev.id];
int err;
if (!hugetlb_sysfs_initialized)
return;
if (nhs->hugepages_kobj)
return; /* already allocated */
nhs->hugepages_kobj = kobject_create_and_add("hugepages",
&node->dev.kobj);
if (!nhs->hugepages_kobj)
return;
for_each_hstate(h) {
err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
nhs->hstate_kobjs,
&per_node_hstate_attr_group);
if (err) {
pr_err("HugeTLB: Unable to add hstate %s for node %d\n",
h->name, node->dev.id);
hugetlb_unregister_node(node);
break;
}
}
}
/*
* hugetlb init time: register hstate attributes for all registered node
* devices of nodes that have memory. All on-line nodes should have
* registered their associated device by this time.
*/
static void __init hugetlb_register_all_nodes(void)
{
int nid;
for_each_online_node(nid)
hugetlb_register_node(node_devices[nid]);
}
#else /* !CONFIG_NUMA */
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
BUG();
if (nidp)
*nidp = -1;
return NULL;
}
static void hugetlb_register_all_nodes(void) { }
#endif
static void __init hugetlb_sysfs_init(void)
{
struct hstate *h;
int err;
hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
if (!hugepages_kobj)
return;
for_each_hstate(h) {
err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
hstate_kobjs, &hstate_attr_group);
if (err)
pr_err("HugeTLB: Unable to add hstate %s\n", h->name);
}
#ifdef CONFIG_NUMA
hugetlb_sysfs_initialized = true;
#endif
hugetlb_register_all_nodes();
}
#ifdef CONFIG_SYSCTL
static void hugetlb_sysctl_init(void);
#else
static inline void hugetlb_sysctl_init(void) { }
#endif
static int __init hugetlb_init(void)
{
int i;
BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE <
__NR_HPAGEFLAGS);
if (!hugepages_supported()) {
if (hugetlb_max_hstate || default_hstate_max_huge_pages)
pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n");
return 0;
}
/*
* Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some
* architectures depend on setup being done here.
*/
hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
if (!parsed_default_hugepagesz) {
/*
* If we did not parse a default huge page size, set
* default_hstate_idx to HPAGE_SIZE hstate. And, if the
* number of huge pages for this default size was implicitly
* specified, set that here as well.
* Note that the implicit setting will overwrite an explicit
* setting. A warning will be printed in this case.
*/
default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE));
if (default_hstate_max_huge_pages) {
if (default_hstate.max_huge_pages) {
char buf[32];
string_get_size(huge_page_size(&default_hstate),
1, STRING_UNITS_2, buf, 32);
pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n",
default_hstate.max_huge_pages, buf);
pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n",
default_hstate_max_huge_pages);
}
default_hstate.max_huge_pages =
default_hstate_max_huge_pages;
for_each_online_node(i)
default_hstate.max_huge_pages_node[i] =
default_hugepages_in_node[i];
}
}
hugetlb_cma_check();
hugetlb_init_hstates();
gather_bootmem_prealloc();
report_hugepages();
hugetlb_sysfs_init();
hugetlb_cgroup_file_init();
hugetlb_sysctl_init();
#ifdef CONFIG_SMP
num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus());
#else
num_fault_mutexes = 1;
#endif
hugetlb_fault_mutex_table =
kmalloc_array(num_fault_mutexes, sizeof(struct mutex),
GFP_KERNEL);
BUG_ON(!hugetlb_fault_mutex_table);
for (i = 0; i < num_fault_mutexes; i++)
mutex_init(&hugetlb_fault_mutex_table[i]);
return 0;
}
subsys_initcall(hugetlb_init);
/* Overwritten by architectures with more huge page sizes */
bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size)
{
return size == HPAGE_SIZE;
}
void __init hugetlb_add_hstate(unsigned int order)
{
struct hstate *h;
unsigned long i;
if (size_to_hstate(PAGE_SIZE << order)) {
return;
}
BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
BUG_ON(order < order_base_2(__NR_USED_SUBPAGE));
h = &hstates[hugetlb_max_hstate++];
__mutex_init(&h->resize_lock, "resize mutex", &h->resize_key);
h->order = order;
h->mask = ~(huge_page_size(h) - 1);
for (i = 0; i < MAX_NUMNODES; ++i)
INIT_LIST_HEAD(&h->hugepage_freelists[i]);
INIT_LIST_HEAD(&h->hugepage_activelist);
snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
huge_page_size(h)/SZ_1K);
parsed_hstate = h;
}
bool __init __weak hugetlb_node_alloc_supported(void)
{
return true;
}
static void __init hugepages_clear_pages_in_node(void)
{
if (!hugetlb_max_hstate) {
default_hstate_max_huge_pages = 0;
memset(default_hugepages_in_node, 0,
sizeof(default_hugepages_in_node));
} else {
parsed_hstate->max_huge_pages = 0;
memset(parsed_hstate->max_huge_pages_node, 0,
sizeof(parsed_hstate->max_huge_pages_node));
}
}
static __init int hugetlb_add_param(char *s, int (*setup)(char *))
{
size_t len;
char *p;
if (hugetlb_param_index >= HUGE_MAX_CMDLINE_ARGS)
return -EINVAL;
len = strlen(s) + 1;
if (len + hstate_cmdline_index > sizeof(hstate_cmdline_buf))
return -EINVAL;
p = &hstate_cmdline_buf[hstate_cmdline_index];
memcpy(p, s, len);
hstate_cmdline_index += len;
hugetlb_params[hugetlb_param_index].val = p;
hugetlb_params[hugetlb_param_index].setup = setup;
hugetlb_param_index++;
return 0;
}
static __init void hugetlb_parse_params(void)
{
int i;
struct hugetlb_cmdline *hcp;
for (i = 0; i < hugetlb_param_index; i++) {
hcp = &hugetlb_params[i];
hcp->setup(hcp->val);
}
hugetlb_cma_validate_params();
}
/*
* hugepages command line processing
* hugepages normally follows a valid hugepagsz or default_hugepagsz
* specification. If not, ignore the hugepages value. hugepages can also
* be the first huge page command line option in which case it implicitly
* specifies the number of huge pages for the default size.
*/
static int __init hugepages_setup(char *s)
{
unsigned long *mhp;
static unsigned long *last_mhp;
int node = NUMA_NO_NODE;
int count;
unsigned long tmp;
char *p = s;
if (!parsed_valid_hugepagesz) {
pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s);
parsed_valid_hugepagesz = true;
return -EINVAL;
}
/*
* !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter
* yet, so this hugepages= parameter goes to the "default hstate".
* Otherwise, it goes with the previously parsed hugepagesz or
* default_hugepagesz.
*/
else if (!hugetlb_max_hstate)
mhp = &default_hstate_max_huge_pages;
else
mhp = &parsed_hstate->max_huge_pages;
if (mhp == last_mhp) {
pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s);
return 1;
}
while (*p) {
count = 0;
if (sscanf(p, "%lu%n", &tmp, &count) != 1)
goto invalid;
/* Parameter is node format */
if (p[count] == ':') {
if (!hugetlb_node_alloc_supported()) {
pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n");
return 1;
}
if (tmp >= MAX_NUMNODES || !node_online(tmp))
goto invalid;
node = array_index_nospec(tmp, MAX_NUMNODES);
p += count + 1;
/* Parse hugepages */
if (sscanf(p, "%lu%n", &tmp, &count) != 1)
goto invalid;
if (!hugetlb_max_hstate)
default_hugepages_in_node[node] = tmp;
else
parsed_hstate->max_huge_pages_node[node] = tmp;
*mhp += tmp;
/* Go to parse next node*/
if (p[count] == ',')
p += count + 1;
else
break;
} else {
if (p != s)
goto invalid;
*mhp = tmp;
break;
}
}
last_mhp = mhp;
return 0;
invalid:
pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p);
hugepages_clear_pages_in_node();
return -EINVAL;
}
hugetlb_early_param("hugepages", hugepages_setup);
/*
* hugepagesz command line processing
* A specific huge page size can only be specified once with hugepagesz.
* hugepagesz is followed by hugepages on the command line. The global
* variable 'parsed_valid_hugepagesz' is used to determine if prior
* hugepagesz argument was valid.
*/
static int __init hugepagesz_setup(char *s)
{
unsigned long size;
struct hstate *h;
parsed_valid_hugepagesz = false;
size = (unsigned long)memparse(s, NULL);
if (!arch_hugetlb_valid_size(size)) {
pr_err("HugeTLB: unsupported hugepagesz=%s\n", s);
return -EINVAL;
}
h = size_to_hstate(size);
if (h) {
/*
* hstate for this size already exists. This is normally
* an error, but is allowed if the existing hstate is the
* default hstate. More specifically, it is only allowed if
* the number of huge pages for the default hstate was not
* previously specified.
*/
if (!parsed_default_hugepagesz || h != &default_hstate ||
default_hstate.max_huge_pages) {
pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s);
return -EINVAL;
}
/*
* No need to call hugetlb_add_hstate() as hstate already
* exists. But, do set parsed_hstate so that a following
* hugepages= parameter will be applied to this hstate.
*/
parsed_hstate = h;
parsed_valid_hugepagesz = true;
return 0;
}
hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
parsed_valid_hugepagesz = true;
return 0;
}
hugetlb_early_param("hugepagesz", hugepagesz_setup);
/*
* default_hugepagesz command line input
* Only one instance of default_hugepagesz allowed on command line.
*/
static int __init default_hugepagesz_setup(char *s)
{
unsigned long size;
int i;
parsed_valid_hugepagesz = false;
if (parsed_default_hugepagesz) {
pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s);
return -EINVAL;
}
size = (unsigned long)memparse(s, NULL);
if (!arch_hugetlb_valid_size(size)) {
pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s);
return -EINVAL;
}
hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
parsed_valid_hugepagesz = true;
parsed_default_hugepagesz = true;
default_hstate_idx = hstate_index(size_to_hstate(size));
/*
* The number of default huge pages (for this size) could have been
* specified as the first hugetlb parameter: hugepages=X. If so,
* then default_hstate_max_huge_pages is set. If the default huge
* page size is gigantic (> MAX_PAGE_ORDER), then the pages must be
* allocated here from bootmem allocator.
*/
if (default_hstate_max_huge_pages) {
default_hstate.max_huge_pages = default_hstate_max_huge_pages;
/*
* Since this is an early parameter, we can't check
* NUMA node state yet, so loop through MAX_NUMNODES.
*/
for (i = 0; i < MAX_NUMNODES; i++) {
if (default_hugepages_in_node[i] != 0)
default_hstate.max_huge_pages_node[i] =
default_hugepages_in_node[i];
}
default_hstate_max_huge_pages = 0;
}
return 0;
}
hugetlb_early_param("default_hugepagesz", default_hugepagesz_setup);
static bool __hugetlb_bootmem_allocated __initdata;
bool __init hugetlb_bootmem_allocated(void)
{
return __hugetlb_bootmem_allocated;
}
void __init hugetlb_bootmem_alloc(void)
{
struct hstate *h;
int i;
if (__hugetlb_bootmem_allocated)
return;
for (i = 0; i < MAX_NUMNODES; i++)
INIT_LIST_HEAD(&huge_boot_pages[i]);
hugetlb_parse_params();
for_each_hstate(h) {
h->next_nid_to_alloc = first_online_node;
h->next_nid_to_free = first_online_node;
if (hstate_is_gigantic(h))
hugetlb_hstate_alloc_pages(h);
}
__hugetlb_bootmem_allocated = true;
}
/*
* hugepage_alloc_threads command line parsing.
*
* When set, use this specific number of threads for the boot
* allocation of hugepages.
*/
static int __init hugepage_alloc_threads_setup(char *s)
{
unsigned long allocation_threads;
if (kstrtoul(s, 0, &allocation_threads) != 0)
return 1;
if (allocation_threads == 0)
return 1;
hugepage_allocation_threads = allocation_threads;
return 1;
}
__setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup);
static unsigned int allowed_mems_nr(struct hstate *h)
{
int node;
unsigned int nr = 0;
nodemask_t *mbind_nodemask;
unsigned int *array = h->free_huge_pages_node;
gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask))
nr += array[node];
}
return nr;
}
#ifdef CONFIG_SYSCTL
static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write,
void *buffer, size_t *length,
loff_t *ppos, unsigned long *out)
{
struct ctl_table dup_table;
/*
* In order to avoid races with __do_proc_doulongvec_minmax(), we
* can duplicate the @table and alter the duplicate of it.
*/
dup_table = *table;
dup_table.data = out;
return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
}
static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
const struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
struct hstate *h = &default_hstate;
unsigned long tmp = h->max_huge_pages;
int ret;
if (!hugepages_supported())
return -EOPNOTSUPP;
ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
&tmp);
if (ret)
goto out;
if (write)
ret = __nr_hugepages_store_common(obey_mempolicy, h,
NUMA_NO_NODE, tmp, *length);
out:
return ret;
}
static int hugetlb_sysctl_handler(const struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
return hugetlb_sysctl_handler_common(false, table, write,
buffer, length, ppos);
}
#ifdef CONFIG_NUMA
static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
return hugetlb_sysctl_handler_common(true, table, write,
buffer, length, ppos);
}
#endif /* CONFIG_NUMA */
static int hugetlb_overcommit_handler(const struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
struct hstate *h = &default_hstate;
unsigned long tmp;
int ret;
if (!hugepages_supported())
return -EOPNOTSUPP;
tmp = h->nr_overcommit_huge_pages;
if (write && hstate_is_gigantic(h))
return -EINVAL;
ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
&tmp);
if (ret)
goto out;
if (write) {
spin_lock_irq(&hugetlb_lock);
h->nr_overcommit_huge_pages = tmp;
spin_unlock_irq(&hugetlb_lock);
}
out:
return ret;
}
static const struct ctl_table hugetlb_table[] = {
{
.procname = "nr_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = hugetlb_sysctl_handler,
},
#ifdef CONFIG_NUMA
{
.procname = "nr_hugepages_mempolicy",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = &hugetlb_mempolicy_sysctl_handler,
},
#endif
{
.procname = "hugetlb_shm_group",
.data = &sysctl_hugetlb_shm_group,
.maxlen = sizeof(gid_t),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "nr_overcommit_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = hugetlb_overcommit_handler,
},
};
static void __init hugetlb_sysctl_init(void)
{
register_sysctl_init("vm", hugetlb_table);
}
#endif /* CONFIG_SYSCTL */
void hugetlb_report_meminfo(struct seq_file *m)
{
struct hstate *h;
unsigned long total = 0;
if (!hugepages_supported())
return;
for_each_hstate(h) {
unsigned long count = h->nr_huge_pages;
total += huge_page_size(h) * count;
if (h == &default_hstate)
seq_printf(m,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
"HugePages_Rsvd: %5lu\n"
"HugePages_Surp: %5lu\n"
"Hugepagesize: %8lu kB\n",
count,
h->free_huge_pages,
h->resv_huge_pages,
h->surplus_huge_pages,
huge_page_size(h) / SZ_1K);
}
seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K);
}
int hugetlb_report_node_meminfo(char *buf, int len, int nid)
{
struct hstate *h = &default_hstate;
if (!hugepages_supported())
return 0;
return sysfs_emit_at(buf, len,
"Node %d HugePages_Total: %5u\n"
"Node %d HugePages_Free: %5u\n"
"Node %d HugePages_Surp: %5u\n",
nid, h->nr_huge_pages_node[nid],
nid, h->free_huge_pages_node[nid],
nid, h->surplus_huge_pages_node[nid]);
}
void hugetlb_show_meminfo_node(int nid)
{
struct hstate *h;
if (!hugepages_supported())
return;
for_each_hstate(h)
printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
nid,
h->nr_huge_pages_node[nid],
h->free_huge_pages_node[nid],
h->surplus_huge_pages_node[nid],
huge_page_size(h) / SZ_1K);
}
void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
{
seq_printf(m, "HugetlbPages:\t%8lu kB\n",
K(atomic_long_read(&mm->hugetlb_usage)));
}
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
struct hstate *h;
unsigned long nr_total_pages = 0;
for_each_hstate(h)
nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
return nr_total_pages;
}
static int hugetlb_acct_memory(struct hstate *h, long delta)
{
int ret = -ENOMEM;
if (!delta)
return 0;
spin_lock_irq(&hugetlb_lock);
/*
* When cpuset is configured, it breaks the strict hugetlb page
* reservation as the accounting is done on a global variable. Such
* reservation is completely rubbish in the presence of cpuset because
* the reservation is not checked against page availability for the
* current cpuset. Application can still potentially OOM'ed by kernel
* with lack of free htlb page in cpuset that the task is in.
* Attempt to enforce strict accounting with cpuset is almost
* impossible (or too ugly) because cpuset is too fluid that
* task or memory node can be dynamically moved between cpusets.
*
* The change of semantics for shared hugetlb mapping with cpuset is
* undesirable. However, in order to preserve some of the semantics,
* we fall back to check against current free page availability as
* a best attempt and hopefully to minimize the impact of changing
* semantics that cpuset has.
*
* Apart from cpuset, we also have memory policy mechanism that
* also determines from which node the kernel will allocate memory
* in a NUMA system. So similar to cpuset, we also should consider
* the memory policy of the current task. Similar to the description
* above.
*/
if (delta > 0) {
if (gather_surplus_pages(h, delta) < 0)
goto out;
if (delta > allowed_mems_nr(h)) {
return_unused_surplus_pages(h, delta);
goto out;
}
}
ret = 0;
if (delta < 0)
return_unused_surplus_pages(h, (unsigned long) -delta);
out:
spin_unlock_irq(&hugetlb_lock);
return ret;
}
static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
struct resv_map *resv = vma_resv_map(vma);
/*
* HPAGE_RESV_OWNER indicates a private mapping.
* This new VMA should share its siblings reservation map if present.
* The VMA will only ever have a valid reservation map pointer where
* it is being copied for another still existing VMA. As that VMA
* has a reference to the reservation map it cannot disappear until
* after this open call completes. It is therefore safe to take a
* new reference here without additional locking.
*/
if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
resv_map_dup_hugetlb_cgroup_uncharge_info(resv);
kref_get(&resv->refs);
}
/*
* vma_lock structure for sharable mappings is vma specific.
* Clear old pointer (if copied via vm_area_dup) and allocate
* new structure. Before clearing, make sure vma_lock is not
* for this vma.
*/
if (vma->vm_flags & VM_MAYSHARE) {
struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
if (vma_lock) {
if (vma_lock->vma != vma) {
vma->vm_private_data = NULL;
hugetlb_vma_lock_alloc(vma);
} else
pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__);
} else
hugetlb_vma_lock_alloc(vma);
}
}
static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
struct hstate *h = hstate_vma(vma);
struct resv_map *resv;
struct hugepage_subpool *spool = subpool_vma(vma);
unsigned long reserve, start, end;
long gbl_reserve;
hugetlb_vma_lock_free(vma);
resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER))
return;
start = vma_hugecache_offset(h, vma, vma->vm_start);
end = vma_hugecache_offset(h, vma, vma->vm_end);
reserve = (end - start) - region_count(resv, start, end);
hugetlb_cgroup_uncharge_counter(resv, start, end);
if (reserve) {
/*
* Decrement reserve counts. The global reserve count may be
* adjusted if the subpool has a minimum size.
*/
gbl_reserve = hugepage_subpool_put_pages(spool, reserve);
hugetlb_acct_memory(h, -gbl_reserve);
}
kref_put(&resv->refs, resv_map_release);
}
static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
{ if (addr & ~(huge_page_mask(hstate_vma(vma))))
return -EINVAL;
/*
* PMD sharing is only possible for PUD_SIZE-aligned address ranges
* in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
* split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
*/
if (addr & ~PUD_MASK) {
/*
* hugetlb_vm_op_split is called right before we attempt to
* split the VMA. We will need to unshare PMDs in the old and
* new VMAs, so let's unshare before we split.
*/
unsigned long floor = addr & PUD_MASK;
unsigned long ceil = floor + PUD_SIZE;
if (floor >= vma->vm_start && ceil <= vma->vm_end) hugetlb_unshare_pmds(vma, floor, ceil);
}
return 0;
}
static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
{
return huge_page_size(hstate_vma(vma));
}
/*
* We cannot handle pagefaults against hugetlb pages at all. They cause
* handle_mm_fault() to try to instantiate regular-sized pages in the
* hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get
* this far.
*/
static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
{
BUG();
return 0;
}
/*
* When a new function is introduced to vm_operations_struct and added
* to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
* This is because under System V memory model, mappings created via
* shmget/shmat with "huge page" specified are backed by hugetlbfs files,
* their original vm_ops are overwritten with shm_vm_ops.
*/
const struct vm_operations_struct hugetlb_vm_ops = {
.fault = hugetlb_vm_op_fault,
.open = hugetlb_vm_op_open,
.close = hugetlb_vm_op_close,
.may_split = hugetlb_vm_op_split,
.pagesize = hugetlb_vm_op_pagesize,
};
static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
bool try_mkwrite)
{
pte_t entry;
unsigned int shift = huge_page_shift(hstate_vma(vma));
if (try_mkwrite && (vma->vm_flags & VM_WRITE)) {
entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page,
vma->vm_page_prot)));
} else {
entry = huge_pte_wrprotect(mk_huge_pte(page,
vma->vm_page_prot));
}
entry = pte_mkyoung(entry);
entry = arch_make_huge_pte(entry, shift, vma->vm_flags);
return entry;
}
static void set_huge_ptep_writable(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
pte_t entry;
entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(vma->vm_mm, address, ptep)));
if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
update_mmu_cache(vma, address, ptep);
}
static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
if (vma->vm_flags & VM_WRITE)
set_huge_ptep_writable(vma, address, ptep);
}
bool is_hugetlb_entry_migration(pte_t pte)
{
swp_entry_t swp;
if (huge_pte_none(pte) || pte_present(pte))
return false;
swp = pte_to_swp_entry(pte);
if (is_migration_entry(swp))
return true;
else
return false;
}
bool is_hugetlb_entry_hwpoisoned(pte_t pte)
{
swp_entry_t swp;
if (huge_pte_none(pte) || pte_present(pte))
return false;
swp = pte_to_swp_entry(pte);
if (is_hwpoison_entry(swp))
return true;
else
return false;
}
static void
hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
struct folio *new_folio, pte_t old, unsigned long sz)
{
pte_t newpte = make_huge_pte(vma, &new_folio->page, true);
__folio_mark_uptodate(new_folio);
hugetlb_add_new_anon_rmap(new_folio, vma, addr);
if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
newpte = huge_pte_mkuffd_wp(newpte);
set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz);
hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
folio_set_hugetlb_migratable(new_folio);
}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma)
{
pte_t *src_pte, *dst_pte, entry;
struct folio *pte_folio;
unsigned long addr;
bool cow = is_cow_mapping(src_vma->vm_flags);
struct hstate *h = hstate_vma(src_vma);
unsigned long sz = huge_page_size(h);
unsigned long npages = pages_per_huge_page(h);
struct mmu_notifier_range range;
unsigned long last_addr_mask;
int ret = 0;
if (cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src,
src_vma->vm_start,
src_vma->vm_end);
mmu_notifier_invalidate_range_start(&range);
vma_assert_write_locked(src_vma);
raw_write_seqcount_begin(&src->write_protect_seq);
} else {
/*
* For shared mappings the vma lock must be held before
* calling hugetlb_walk() in the src vma. Otherwise, the
* returned ptep could go away if part of a shared pmd and
* another thread calls huge_pmd_unshare.
*/
hugetlb_vma_lock_read(src_vma);
}
last_addr_mask = hugetlb_mask_last_page(h);
for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
spinlock_t *src_ptl, *dst_ptl;
src_pte = hugetlb_walk(src_vma, addr, sz);
if (!src_pte) {
addr |= last_addr_mask;
continue;
}
dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
if (!dst_pte) {
ret = -ENOMEM;
break;
}
/*
* If the pagetables are shared don't copy or take references.
*
* dst_pte == src_pte is the common case of src/dest sharing.
* However, src could have 'unshared' and dst shares with
* another vma. So page_count of ptep page is checked instead
* to reliably determine whether pte is shared.
*/
if (page_count(virt_to_page(dst_pte)) > 1) {
addr |= last_addr_mask;
continue;
}
dst_ptl = huge_pte_lock(h, dst, dst_pte);
src_ptl = huge_pte_lockptr(h, src, src_pte);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte);
again:
if (huge_pte_none(entry)) {
/*
* Skip if src entry none.
*/
;
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
set_huge_pte_at(dst, addr, dst_pte, entry, sz);
} else if (unlikely(is_hugetlb_entry_migration(entry))) {
swp_entry_t swp_entry = pte_to_swp_entry(entry);
bool uffd_wp = pte_swp_uffd_wp(entry);
if (!is_readable_migration_entry(swp_entry) && cow) {
/*
* COW mappings require pages in both
* parent and child to be set to read.
*/
swp_entry = make_readable_migration_entry(
swp_offset(swp_entry));
entry = swp_entry_to_pte(swp_entry);
if (userfaultfd_wp(src_vma) && uffd_wp)
entry = pte_swp_mkuffd_wp(entry);
set_huge_pte_at(src, addr, src_pte, entry, sz);
}
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
set_huge_pte_at(dst, addr, dst_pte, entry, sz);
} else if (unlikely(is_pte_marker(entry))) {
pte_marker marker = copy_pte_marker(
pte_to_swp_entry(entry), dst_vma);
if (marker)
set_huge_pte_at(dst, addr, dst_pte,
make_pte_marker(marker), sz);
} else {
entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte);
pte_folio = page_folio(pte_page(entry));
folio_get(pte_folio);
/*
* Failing to duplicate the anon rmap is a rare case
* where we see pinned hugetlb pages while they're
* prone to COW. We need to do the COW earlier during
* fork.
*
* When pre-allocating the page or copying data, we
* need to be without the pgtable locks since we could
* sleep during the process.
*/
if (!folio_test_anon(pte_folio)) {
hugetlb_add_file_rmap(pte_folio);
} else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) {
pte_t src_pte_old = entry;
struct folio *new_folio;
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
/* Do not use reserve as it's private owned */
new_folio = alloc_hugetlb_folio(dst_vma, addr, false);
if (IS_ERR(new_folio)) {
folio_put(pte_folio);
ret = PTR_ERR(new_folio);
break;
}
ret = copy_user_large_folio(new_folio, pte_folio,
addr, dst_vma);
folio_put(pte_folio);
if (ret) {
folio_put(new_folio);
break;
}
/* Install the new hugetlb folio if src pte stable */
dst_ptl = huge_pte_lock(h, dst, dst_pte);
src_ptl = huge_pte_lockptr(h, src, src_pte);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte);
if (!pte_same(src_pte_old, entry)) {
restore_reserve_on_error(h, dst_vma, addr,
new_folio);
folio_put(new_folio);
/* huge_ptep of dst_pte won't change as in child */
goto again;
}
hugetlb_install_folio(dst_vma, dst_pte, addr,
new_folio, src_pte_old, sz);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
continue;
}
if (cow) {
/*
* No need to notify as we are downgrading page
* table protection not changing it to point
* to a new page.
*
* See Documentation/mm/mmu_notifier.rst
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
entry = huge_pte_wrprotect(entry);
}
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
set_huge_pte_at(dst, addr, dst_pte, entry, sz);
hugetlb_count_add(npages, dst);
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
}
if (cow) {
raw_write_seqcount_end(&src->write_protect_seq);
mmu_notifier_invalidate_range_end(&range);
} else {
hugetlb_vma_unlock_read(src_vma);
}
return ret;
}
static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte,
unsigned long sz)
{
bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma);
struct hstate *h = hstate_vma(vma);
struct mm_struct *mm = vma->vm_mm;
spinlock_t *src_ptl, *dst_ptl;
pte_t pte;
dst_ptl = huge_pte_lock(h, mm, dst_pte);
src_ptl = huge_pte_lockptr(h, mm, src_pte);
/*
* We don't have to worry about the ordering of src and dst ptlocks
* because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
*/
if (src_ptl != dst_ptl)
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz);
if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
huge_pte_clear(mm, new_addr, dst_pte, sz);
else {
if (need_clear_uffd_wp) {
if (pte_present(pte))
pte = huge_pte_clear_uffd_wp(pte);
else if (is_swap_pte(pte))
pte = pte_swp_clear_uffd_wp(pte);
}
set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
}
if (src_ptl != dst_ptl)
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
}
int move_hugetlb_page_tables(struct vm_area_struct *vma,
struct vm_area_struct *new_vma,
unsigned long old_addr, unsigned long new_addr,
unsigned long len)
{
struct hstate *h = hstate_vma(vma);
struct address_space *mapping = vma->vm_file->f_mapping;
unsigned long sz = huge_page_size(h);
struct mm_struct *mm = vma->vm_mm;
unsigned long old_end = old_addr + len;
unsigned long last_addr_mask;
pte_t *src_pte, *dst_pte;
struct mmu_notifier_range range;
bool shared_pmd = false;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr,
old_end);
adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
/*
* In case of shared PMDs, we should cover the maximum possible
* range.
*/
flush_cache_range(vma, range.start, range.end);
mmu_notifier_invalidate_range_start(&range);
last_addr_mask = hugetlb_mask_last_page(h);
/* Prevent race with file truncation */
hugetlb_vma_lock_write(vma);
i_mmap_lock_write(mapping);
for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
src_pte = hugetlb_walk(vma, old_addr, sz);
if (!src_pte) {
old_addr |= last_addr_mask;
new_addr |= last_addr_mask;
continue;
}
if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte)))
continue;
if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) {
shared_pmd = true;
old_addr |= last_addr_mask;
new_addr |= last_addr_mask;
continue;
}
dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz);
if (!dst_pte)
break;
move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz);
}
if (shared_pmd)
flush_hugetlb_tlb_range(vma, range.start, range.end);
else
flush_hugetlb_tlb_range(vma, old_end - len, old_end);
mmu_notifier_invalidate_range_end(&range);
i_mmap_unlock_write(mapping);
hugetlb_vma_unlock_write(vma);
return len + old_addr - old_end;
}
void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page, zap_flags_t zap_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *ptep;
pte_t pte;
spinlock_t *ptl;
struct page *page;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
bool adjust_reservation = false;
unsigned long last_addr_mask;
bool force_flush = false;
WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h));
/*
* This is a hugetlb vma, all the pte entries should point
* to huge page.
*/
tlb_change_page_size(tlb, sz);
tlb_start_vma(tlb, vma);
last_addr_mask = hugetlb_mask_last_page(h);
address = start;
for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz);
if (!ptep) {
address |= last_addr_mask;
continue;
}
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, address, ptep)) {
spin_unlock(ptl);
tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
force_flush = true;
address |= last_addr_mask;
continue;
}
pte = huge_ptep_get(mm, address, ptep);
if (huge_pte_none(pte)) {
spin_unlock(ptl);
continue;
}
/*
* Migrating hugepage or HWPoisoned hugepage is already
* unmapped and its refcount is dropped, so just clear pte here.
*/
if (unlikely(!pte_present(pte))) {
/*
* If the pte was wr-protected by uffd-wp in any of the
* swap forms, meanwhile the caller does not want to
* drop the uffd-wp bit in this zap, then replace the
* pte with a marker.
*/
if (pte_swp_uffd_wp_any(pte) &&
!(zap_flags & ZAP_FLAG_DROP_MARKER))
set_huge_pte_at(mm, address, ptep,
make_pte_marker(PTE_MARKER_UFFD_WP),
sz);
else
huge_pte_clear(mm, address, ptep, sz);
spin_unlock(ptl);
continue;
}
page = pte_page(pte);
/*
* If a reference page is supplied, it is because a specific
* page is being unmapped, not a range. Ensure the page we
* are about to unmap is the actual page of interest.
*/
if (ref_page) {
if (page != ref_page) {
spin_unlock(ptl);
continue;
}
/*
* Mark the VMA as having unmapped its page so that
* future faults in this VMA will fail rather than
* looking like data was lost
*/
set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
}
pte = huge_ptep_get_and_clear(mm, address, ptep, sz);
tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page);
/* Leave a uffd-wp pte marker if needed */
if (huge_pte_uffd_wp(pte) &&
!(zap_flags & ZAP_FLAG_DROP_MARKER))
set_huge_pte_at(mm, address, ptep,
make_pte_marker(PTE_MARKER_UFFD_WP),
sz);
hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(page_folio(page));
/*
* Restore the reservation for anonymous page, otherwise the
* backing page could be stolen by someone.
* If there we are freeing a surplus, do not set the restore
* reservation bit.
*/
if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(page_folio(page))) { folio_set_hugetlb_restore_reserve(page_folio(page));
/* Reservation to be adjusted after the spin lock */
adjust_reservation = true;
}
spin_unlock(ptl);
/*
* Adjust the reservation for the region that will have the
* reserve restored. Keep in mind that vma_needs_reservation() changes
* resv->adds_in_progress if it succeeds. If this is not done,
* do_exit() will not see it, and will keep the reservation
* forever.
*/
if (adjust_reservation) {
int rc = vma_needs_reservation(h, vma, address);
if (rc < 0)
/* Pressumably allocate_file_region_entries failed
* to allocate a file_region struct. Clear
* hugetlb_restore_reserve so that global reserve
* count will not be incremented by free_huge_folio.
* Act as if we consumed the reservation.
*/
folio_clear_hugetlb_restore_reserve(page_folio(page)); else if (rc) vma_add_reservation(h, vma, address);
}
tlb_remove_page_size(tlb, page, huge_page_size(h));
/*
* Bail out after unmapping reference page if supplied
*/
if (ref_page)
break;
}
tlb_end_vma(tlb, vma);
/*
* If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
* could defer the flush until now, since by holding i_mmap_rwsem we
* guaranteed that the last refernece would not be dropped. But we must
* do the flushing before we return, as otherwise i_mmap_rwsem will be
* dropped and the last reference to the shared PMDs page might be
* dropped as well.
*
* In theory we could defer the freeing of the PMD pages as well, but
* huge_pmd_unshare() relies on the exact page_count for the PMD page to
* detect sharing, so we cannot defer the release of the page either.
* Instead, do flush now.
*/
if (force_flush) tlb_flush_mmu_tlbonly(tlb);
}
void __hugetlb_zap_begin(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{ if (!vma->vm_file) /* hugetlbfs_file_mmap error */
return;
adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping);
}
void __hugetlb_zap_end(struct vm_area_struct *vma,
struct zap_details *details)
{
zap_flags_t zap_flags = details ? details->zap_flags : 0;
if (!vma->vm_file) /* hugetlbfs_file_mmap error */
return;
if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */
/*
* Unlock and free the vma lock before releasing i_mmap_rwsem.
* When the vma_lock is freed, this makes the vma ineligible
* for pmd sharing. And, i_mmap_rwsem is required to set up
* pmd sharing. This is important as page tables for this
* unmapped range will be asynchrously deleted. If the page
* tables are shared, there will be issues when accessed by
* someone else.
*/
__hugetlb_vma_unlock_write_free(vma);
} else {
hugetlb_vma_unlock_write(vma);
}
if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping);
}
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page,
zap_flags_t zap_flags)
{
struct mmu_notifier_range range;
struct mmu_gather tlb;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
start, end);
adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
mmu_notifier_invalidate_range_start(&range);
tlb_gather_mmu(&tlb, vma->vm_mm);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
/*
* This is called when the original mapper is failing to COW a MAP_PRIVATE
* mapping it owns the reserve page for. The intention is to unmap the page
* from other VMAs and let the children be SIGKILLed if they are faulting the
* same region.
*/
static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
struct page *page, unsigned long address)
{
struct hstate *h = hstate_vma(vma);
struct vm_area_struct *iter_vma;
struct address_space *mapping;
pgoff_t pgoff;
/*
* vm_pgoff is in PAGE_SIZE units, hence the different calculation
* from page cache lookup which is in HPAGE_SIZE units.
*/
address = address & huge_page_mask(h);
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
vma->vm_pgoff;
mapping = vma->vm_file->f_mapping;
/*
* Take the mapping lock for the duration of the table walk. As
* this mapping should be shared between all the VMAs,
* __unmap_hugepage_range() is called as the lock is already held
*/
i_mmap_lock_write(mapping);
vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) {
/* Do not unmap the current VMA */
if (iter_vma == vma)
continue;
/*
* Shared VMAs have their own reserves and do not affect
* MAP_PRIVATE accounting but it is possible that a shared
* VMA is using the same page so check and skip such VMAs.
*/
if (iter_vma->vm_flags & VM_MAYSHARE)
continue;
/*
* Unmap the page from other VMAs without their own reserves.
* They get marked to be SIGKILLed if they fault in these
* areas. This is because a future no-page fault on this VMA
* could insert a zeroed page instead of the data existing
* from the time of fork. This would look like data corruption
*/
if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
unmap_hugepage_range(iter_vma, address,
address + huge_page_size(h), page, 0);
}
i_mmap_unlock_write(mapping);
}
/*
* hugetlb_wp() should be called with page lock of the original hugepage held.
* Called with hugetlb_fault_mutex_table held and pte_page locked so we
* cannot race with other handlers or page migration.
* Keep the pte_same checks anyway to make transition from the mutex easier.
*/
static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
pte_t pte = huge_ptep_get(mm, vmf->address, vmf->pte);
struct hstate *h = hstate_vma(vma);
struct folio *old_folio;
struct folio *new_folio;
bool cow_from_owner = 0;
vm_fault_t ret = 0;
struct mmu_notifier_range range;
/*
* Never handle CoW for uffd-wp protected pages. It should be only
* handled when the uffd-wp protection is removed.
*
* Note that only the CoW optimization path (in hugetlb_no_page())
* can trigger this, because hugetlb_fault() will always resolve
* uffd-wp bit first.
*/
if (!unshare && huge_pte_uffd_wp(pte))
return 0;
/* Let's take out MAP_SHARED mappings first. */
if (vma->vm_flags & VM_MAYSHARE) {
set_huge_ptep_writable(vma, vmf->address, vmf->pte);
return 0;
}
old_folio = page_folio(pte_page(pte));
delayacct_wpcopy_start();
retry_avoidcopy:
/*
* If no-one else is actually using this page, we're the exclusive
* owner and can reuse this page.
*
* Note that we don't rely on the (safer) folio refcount here, because
* copying the hugetlb folio when there are unexpected (temporary)
* folio references could harm simple fork()+exit() users when
* we run out of free hugetlb folios: we would have to kill processes
* in scenarios that used to work. As a side effect, there can still
* be leaks between processes, for example, with FOLL_GET users.
*/
if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) {
if (!PageAnonExclusive(&old_folio->page)) {
folio_move_anon_rmap(old_folio, vma);
SetPageAnonExclusive(&old_folio->page);
}
if (likely(!unshare))
set_huge_ptep_maybe_writable(vma, vmf->address,
vmf->pte);
delayacct_wpcopy_end();
return 0;
}
VM_BUG_ON_PAGE(folio_test_anon(old_folio) &&
PageAnonExclusive(&old_folio->page), &old_folio->page);
/*
* If the process that created a MAP_PRIVATE mapping is about to
* perform a COW due to a shared page count, attempt to satisfy
* the allocation without using the existing reserves. The pagecache
* page is used to determine if the reserve at this address was
* consumed or not. If reserves were used, a partial faulted mapping
* at the time of fork() could consume its reserves on COW instead
* of the full address range.
*/
if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
old_folio != pagecache_folio)
cow_from_owner = true;
folio_get(old_folio);
/*
* Drop page table lock as buddy allocator may be called. It will
* be acquired again before returning to the caller, as expected.
*/
spin_unlock(vmf->ptl);
new_folio = alloc_hugetlb_folio(vma, vmf->address, cow_from_owner);
if (IS_ERR(new_folio)) {
/*
* If a process owning a MAP_PRIVATE mapping fails to COW,
* it is due to references held by a child and an insufficient
* huge page pool. To guarantee the original mappers
* reliability, unmap the page from child processes. The child
* may get SIGKILLed if it later faults.
*/
if (cow_from_owner) {
struct address_space *mapping = vma->vm_file->f_mapping;
pgoff_t idx;
u32 hash;
folio_put(old_folio);
/*
* Drop hugetlb_fault_mutex and vma_lock before
* unmapping. unmapping needs to hold vma_lock
* in write mode. Dropping vma_lock in read mode
* here is OK as COW mappings do not interact with
* PMD sharing.
*
* Reacquire both after unmap operation.
*/
idx = vma_hugecache_offset(h, vma, vmf->address);
hash = hugetlb_fault_mutex_hash(mapping, idx);
hugetlb_vma_unlock_read(vma);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
unmap_ref_private(mm, vma, &old_folio->page,
vmf->address);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
hugetlb_vma_lock_read(vma);
spin_lock(vmf->ptl);
vmf->pte = hugetlb_walk(vma, vmf->address,
huge_page_size(h));
if (likely(vmf->pte &&
pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte)))
goto retry_avoidcopy;
/*
* race occurs while re-acquiring page table
* lock, and our job is done.
*/
delayacct_wpcopy_end();
return 0;
}
ret = vmf_error(PTR_ERR(new_folio));
goto out_release_old;
}
/*
* When the original hugepage is shared one, it does not have
* anon_vma prepared.
*/
ret = __vmf_anon_prepare(vmf);
if (unlikely(ret))
goto out_release_all;
if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) {
ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h));
goto out_release_all;
}
__folio_mark_uptodate(new_folio);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address,
vmf->address + huge_page_size(h));
mmu_notifier_invalidate_range_start(&range);
/*
* Retake the page table lock to check for racing updates
* before the page tables are altered
*/
spin_lock(vmf->ptl);
vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h));
if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) {
pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare);
/* Break COW or unshare */
huge_ptep_clear_flush(vma, vmf->address, vmf->pte);
hugetlb_remove_rmap(old_folio);
hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address);
if (huge_pte_uffd_wp(pte))
newpte = huge_pte_mkuffd_wp(newpte);
set_huge_pte_at(mm, vmf->address, vmf->pte, newpte,
huge_page_size(h));
folio_set_hugetlb_migratable(new_folio);
/* Make the old page be freed below */
new_folio = old_folio;
}
spin_unlock(vmf->ptl);
mmu_notifier_invalidate_range_end(&range);
out_release_all:
/*
* No restore in case of successful pagetable update (Break COW or
* unshare)
*/
if (new_folio != old_folio)
restore_reserve_on_error(h, vma, vmf->address, new_folio);
folio_put(new_folio);
out_release_old:
folio_put(old_folio);
spin_lock(vmf->ptl); /* Caller expects lock to be held */
delayacct_wpcopy_end();
return ret;
}
/*
* Return whether there is a pagecache page to back given address within VMA.
*/
bool hugetlbfs_pagecache_present(struct hstate *h,
struct vm_area_struct *vma, unsigned long address)
{
struct address_space *mapping = vma->vm_file->f_mapping;
pgoff_t idx = linear_page_index(vma, address);
struct folio *folio;
folio = filemap_get_folio(mapping, idx);
if (IS_ERR(folio))
return false;
folio_put(folio);
return true;
}
int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
pgoff_t idx)
{
struct inode *inode = mapping->host;
struct hstate *h = hstate_inode(inode);
int err;
idx <<= huge_page_order(h);
__folio_set_locked(folio);
err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL);
if (unlikely(err)) {
__folio_clear_locked(folio);
return err;
}
folio_clear_hugetlb_restore_reserve(folio);
/*
* mark folio dirty so that it will not be removed from cache/file
* by non-hugetlbfs specific code paths.
*/
folio_mark_dirty(folio);
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
spin_unlock(&inode->i_lock);
return 0;
}
static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf,
struct address_space *mapping,
unsigned long reason)
{
u32 hash;
/*
* vma_lock and hugetlb_fault_mutex must be dropped before handling
* userfault. Also mmap_lock could be dropped due to handling
* userfault, any vma operation should be careful from here.
*/
hugetlb_vma_unlock_read(vmf->vma);
hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
return handle_userfault(vmf, reason);
}
/*
* Recheck pte with pgtable lock. Returns true if pte didn't change, or
* false if pte changed or is changing.
*/
static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t old_pte)
{
spinlock_t *ptl;
bool same;
ptl = huge_pte_lock(h, mm, ptep);
same = pte_same(huge_ptep_get(mm, addr, ptep), old_pte);
spin_unlock(ptl);
return same;
}
static vm_fault_t hugetlb_no_page(struct address_space *mapping,
struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
struct hstate *h = hstate_vma(vma);
vm_fault_t ret = VM_FAULT_SIGBUS;
int anon_rmap = 0;
unsigned long size;
struct folio *folio;
pte_t new_pte;
bool new_folio, new_pagecache_folio = false;
u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff);
/*
* Currently, we are forced to kill the process in the event the
* original mapper has unmapped pages from the child due to a failed
* COW/unsharing. Warn that such a situation has occurred as it may not
* be obvious.
*/
if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
current->pid);
goto out;
}
/*
* Use page lock to guard against racing truncation
* before we get page_table_lock.
*/
new_folio = false;
folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff);
if (IS_ERR(folio)) {
size = i_size_read(mapping->host) >> huge_page_shift(h);
if (vmf->pgoff >= size)
goto out;
/* Check for page in userfault range */
if (userfaultfd_missing(vma)) {
/*
* Since hugetlb_no_page() was examining pte
* without pgtable lock, we need to re-test under
* lock because the pte may not be stable and could
* have changed from under us. Try to detect
* either changed or during-changing ptes and retry
* properly when needed.
*
* Note that userfaultfd is actually fine with
* false positives (e.g. caused by pte changed),
* but not wrong logical events (e.g. caused by
* reading a pte during changing). The latter can
* confuse the userspace, so the strictness is very
* much preferred. E.g., MISSING event should
* never happen on the page after UFFDIO_COPY has
* correctly installed the page and returned.
*/
if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) {
ret = 0;
goto out;
}
return hugetlb_handle_userfault(vmf, mapping,
VM_UFFD_MISSING);
}
if (!(vma->vm_flags & VM_MAYSHARE)) {
ret = __vmf_anon_prepare(vmf);
if (unlikely(ret))
goto out;
}
folio = alloc_hugetlb_folio(vma, vmf->address, false);
if (IS_ERR(folio)) {
/*
* Returning error will result in faulting task being
* sent SIGBUS. The hugetlb fault mutex prevents two
* tasks from racing to fault in the same page which
* could result in false unable to allocate errors.
* Page migration does not take the fault mutex, but
* does a clear then write of pte's under page table
* lock. Page fault code could race with migration,
* notice the clear pte and try to allocate a page
* here. Before returning error, get ptl and make
* sure there really is no pte entry.
*/
if (hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio));
else
ret = 0;
goto out;
}
folio_zero_user(folio, vmf->real_address);
__folio_mark_uptodate(folio);
new_folio = true;
if (vma->vm_flags & VM_MAYSHARE) {
int err = hugetlb_add_to_page_cache(folio, mapping,
vmf->pgoff);
if (err) {
/*
* err can't be -EEXIST which implies someone
* else consumed the reservation since hugetlb
* fault mutex is held when add a hugetlb page
* to the page cache. So it's safe to call
* restore_reserve_on_error() here.
*/
restore_reserve_on_error(h, vma, vmf->address,
folio);
folio_put(folio);
ret = VM_FAULT_SIGBUS;
goto out;
}
new_pagecache_folio = true;
} else {
folio_lock(folio);
anon_rmap = 1;
}
} else {
/*
* If memory error occurs between mmap() and fault, some process
* don't have hwpoisoned swap entry for errored virtual address.
* So we need to block hugepage fault by PG_hwpoison bit check.
*/
if (unlikely(folio_test_hwpoison(folio))) {
ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto backout_unlocked;
}
/* Check for page in userfault range. */
if (userfaultfd_minor(vma)) {
folio_unlock(folio);
folio_put(folio);
/* See comment in userfaultfd_missing() block above */
if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) {
ret = 0;
goto out;
}
return hugetlb_handle_userfault(vmf, mapping,
VM_UFFD_MINOR);
}
}
/*
* If we are going to COW a private mapping later, we examine the
* pending reservations for this page now. This will ensure that
* any allocations necessary to record that reservation occur outside
* the spinlock.
*/
if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) {
ret = VM_FAULT_OOM;
goto backout_unlocked;
}
/* Just decrements count, does not deallocate */
vma_end_reservation(h, vma, vmf->address);
}
vmf->ptl = huge_pte_lock(h, mm, vmf->pte);
ret = 0;
/* If pte changed from under us, retry */
if (!pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), vmf->orig_pte))
goto backout;
if (anon_rmap)
hugetlb_add_new_anon_rmap(folio, vma, vmf->address);
else
hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, vma->vm_flags & VM_SHARED);
/*
* If this pte was previously wr-protected, keep it wr-protected even
* if populated.
*/
if (unlikely(pte_marker_uffd_wp(vmf->orig_pte)))
new_pte = huge_pte_mkuffd_wp(new_pte);
set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h));
hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
/* Optimization, do the COW without a second fault */
ret = hugetlb_wp(folio, vmf);
}
spin_unlock(vmf->ptl);
/*
* Only set hugetlb_migratable in newly allocated pages. Existing pages
* found in the pagecache may not have hugetlb_migratable if they have
* been isolated for migration.
*/
if (new_folio) folio_set_hugetlb_migratable(folio);
folio_unlock(folio);
out:
hugetlb_vma_unlock_read(vma);
/*
* We must check to release the per-VMA lock. __vmf_anon_prepare() is
* the only way ret can be set to VM_FAULT_RETRY.
*/
if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
return ret;
backout:
spin_unlock(vmf->ptl);
backout_unlocked:
if (new_folio && !new_pagecache_folio) restore_reserve_on_error(h, vma, vmf->address, folio);
folio_unlock(folio);
folio_put(folio);
goto out;
}
#ifdef CONFIG_SMP
u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
{
unsigned long key[2];
u32 hash;
key[0] = (unsigned long) mapping;
key[1] = idx;
hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0);
return hash & (num_fault_mutexes - 1);
}
#else
/*
* For uniprocessor systems we always use a single mutex, so just
* return 0 and avoid the hashing overhead.
*/
u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
{
return 0;
}
#endif
vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
vm_fault_t ret;
u32 hash;
struct folio *folio = NULL;
struct folio *pagecache_folio = NULL;
struct hstate *h = hstate_vma(vma);
struct address_space *mapping;
int need_wait_lock = 0;
struct vm_fault vmf = {
.vma = vma,
.address = address & huge_page_mask(h),
.real_address = address,
.flags = flags,
.pgoff = vma_hugecache_offset(h, vma,
address & huge_page_mask(h)),
/* TODO: Track hugetlb faults using vm_fault */
/*
* Some fields may not be initialized, be careful as it may
* be hard to debug if called functions make assumptions
*/
};
/*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
* the same page in the page cache.
*/
mapping = vma->vm_file->f_mapping;
hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/*
* Acquire vma lock before calling huge_pte_alloc and hold
* until finished with vmf.pte. This prevents huge_pmd_unshare from
* being called elsewhere and making the vmf.pte no longer valid.
*/
hugetlb_vma_lock_read(vma);
vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h));
if (!vmf.pte) {
hugetlb_vma_unlock_read(vma);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
return VM_FAULT_OOM;
}
vmf.orig_pte = huge_ptep_get(mm, vmf.address, vmf.pte);
if (huge_pte_none_mostly(vmf.orig_pte)) {
if (is_pte_marker(vmf.orig_pte)) {
pte_marker marker =
pte_marker_get(pte_to_swp_entry(vmf.orig_pte));
if (marker & PTE_MARKER_POISONED) {
ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto out_mutex;
} else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) {
/* This isn't supported in hugetlb. */
ret = VM_FAULT_SIGSEGV;
goto out_mutex;
}
}
/*
* Other PTE markers should be handled the same way as none PTE.
*
* hugetlb_no_page will drop vma lock and hugetlb fault
* mutex internally, which make us return immediately.
*/
return hugetlb_no_page(mapping, &vmf);
}
ret = 0;
/*
* vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this
* point, so this check prevents the kernel from going below assuming
* that we have an active hugepage in pagecache. This goto expects
* the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned)
* check will properly handle it.
*/
if (!pte_present(vmf.orig_pte)) {
if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) {
/*
* Release the hugetlb fault lock now, but retain
* the vma lock, because it is needed to guard the
* huge_pte_lockptr() later in
* migration_entry_wait_huge(). The vma lock will
* be released there.
*/
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
migration_entry_wait_huge(vma, vmf.address, vmf.pte);
return 0;
} else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte)))
ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto out_mutex;
}
/*
* If we are going to COW/unshare the mapping later, we examine the
* pending reservations for this page now. This will ensure that any
* allocations necessary to record that reservation occur outside the
* spinlock. Also lookup the pagecache page now as it is used to
* determine if a reservation has been consumed.
*/
if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) {
ret = VM_FAULT_OOM;
goto out_mutex;
}
/* Just decrements count, does not deallocate */
vma_end_reservation(h, vma, vmf.address);
pagecache_folio = filemap_lock_hugetlb_folio(h, mapping,
vmf.pgoff);
if (IS_ERR(pagecache_folio))
pagecache_folio = NULL;
}
vmf.ptl = huge_pte_lock(h, mm, vmf.pte);
/* Check for a racing update before calling hugetlb_wp() */
if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(mm, vmf.address, vmf.pte))))
goto out_ptl;
/* Handle userfault-wp first, before trying to lock more pages */
if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(mm, vmf.address, vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) {
if (!userfaultfd_wp_async(vma)) {
spin_unlock(vmf.ptl);
if (pagecache_folio) { folio_unlock(pagecache_folio);
folio_put(pagecache_folio);
}
hugetlb_vma_unlock_read(vma);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
return handle_userfault(&vmf, VM_UFFD_WP);
}
vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte);
set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte,
huge_page_size(hstate_vma(vma)));
/* Fallthrough to CoW */
}
/*
* hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and
* pagecache_folio, so here we need take the former one
* when folio != pagecache_folio or !pagecache_folio.
*/
folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) {
need_wait_lock = 1;
goto out_ptl;
}
folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
if (!huge_pte_write(vmf.orig_pte)) {
ret = hugetlb_wp(pagecache_folio, &vmf);
goto out_put_page;
} else if (likely(flags & FAULT_FLAG_WRITE)) {
vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte);
}
}
vmf.orig_pte = pte_mkyoung(vmf.orig_pte);
if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte,
flags & FAULT_FLAG_WRITE))
update_mmu_cache(vma, vmf.address, vmf.pte);
out_put_page:
if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio);
out_ptl:
spin_unlock(vmf.ptl);
if (pagecache_folio) {
folio_unlock(pagecache_folio);
folio_put(pagecache_folio);
}
out_mutex:
hugetlb_vma_unlock_read(vma);
/*
* We must check to release the per-VMA lock. __vmf_anon_prepare() in
* hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY.
*/
if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
/*
* Generally it's safe to hold refcount during waiting page lock. But
* here we just wait to defer the next page fault to avoid busy loop and
* the page is not used after unlocked before returning from the current
* page fault. So we are safe from accessing freed page, even if we wait
* here without taking refcount.
*/
if (need_wait_lock) folio_wait_locked(folio);
return ret;
}
#ifdef CONFIG_USERFAULTFD
/*
* Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte().
*/
static struct folio *alloc_hugetlb_folio_vma(struct hstate *h,
struct vm_area_struct *vma, unsigned long address)
{
struct mempolicy *mpol;
nodemask_t *nodemask;
struct folio *folio;
gfp_t gfp_mask;
int node;
gfp_mask = htlb_alloc_mask(h);
node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
/*
* This is used to allocate a temporary hugetlb to hold the copied
* content, which will then be copied again to the final hugetlb
* consuming a reservation. Set the alloc_fallback to false to indicate
* that breaking the per-node hugetlb pool is not allowed in this case.
*/
folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false);
mpol_cond_put(mpol);
return folio;
}
/*
* Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte
* with modifications for hugetlb pages.
*/
int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
uffd_flags_t flags,
struct folio **foliop)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE);
bool wp_enabled = (flags & MFILL_ATOMIC_WP);
struct hstate *h = hstate_vma(dst_vma);
struct address_space *mapping = dst_vma->vm_file->f_mapping;
pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
unsigned long size = huge_page_size(h);
int vm_shared = dst_vma->vm_flags & VM_SHARED;
pte_t _dst_pte;
spinlock_t *ptl;
int ret = -ENOMEM;
struct folio *folio;
bool folio_in_pagecache = false;
if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) {
ptl = huge_pte_lock(h, dst_mm, dst_pte);
/* Don't overwrite any existing PTEs (even markers) */
if (!huge_pte_none(huge_ptep_get(dst_mm, dst_addr, dst_pte))) {
spin_unlock(ptl);
return -EEXIST;
}
_dst_pte = make_pte_marker(PTE_MARKER_POISONED);
set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
spin_unlock(ptl);
return 0;
}
if (is_continue) {
ret = -EFAULT;
folio = filemap_lock_hugetlb_folio(h, mapping, idx);
if (IS_ERR(folio))
goto out;
folio_in_pagecache = true;
} else if (!*foliop) {
/* If a folio already exists, then it's UFFDIO_COPY for
* a non-missing case. Return -EEXIST.
*/
if (vm_shared &&
hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
ret = -EEXIST;
goto out;
}
folio = alloc_hugetlb_folio(dst_vma, dst_addr, false);
if (IS_ERR(folio)) {
ret = -ENOMEM;
goto out;
}
ret = copy_folio_from_user(folio, (const void __user *) src_addr,
false);
/* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
ret = -ENOENT;
/* Free the allocated folio which may have
* consumed a reservation.
*/
restore_reserve_on_error(h, dst_vma, dst_addr, folio);
folio_put(folio);
/* Allocate a temporary folio to hold the copied
* contents.
*/
folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr);
if (!folio) {
ret = -ENOMEM;
goto out;
}
*foliop = folio;
/* Set the outparam foliop and return to the caller to
* copy the contents outside the lock. Don't free the
* folio.
*/
goto out;
}
} else {
if (vm_shared &&
hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
folio_put(*foliop);
ret = -EEXIST;
*foliop = NULL;
goto out;
}
folio = alloc_hugetlb_folio(dst_vma, dst_addr, false);
if (IS_ERR(folio)) {
folio_put(*foliop);
ret = -ENOMEM;
*foliop = NULL;
goto out;
}
ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma);
folio_put(*foliop);
*foliop = NULL;
if (ret) {
folio_put(folio);
goto out;
}
}
/*
* If we just allocated a new page, we need a memory barrier to ensure
* that preceding stores to the page become visible before the
* set_pte_at() write. The memory barrier inside __folio_mark_uptodate
* is what we need.
*
* In the case where we have not allocated a new page (is_continue),
* the page must already be uptodate. UFFDIO_CONTINUE already includes
* an earlier smp_wmb() to ensure that prior stores will be visible
* before the set_pte_at() write.
*/
if (!is_continue)
__folio_mark_uptodate(folio);
else
WARN_ON_ONCE(!folio_test_uptodate(folio));
/* Add shared, newly allocated pages to the page cache. */
if (vm_shared && !is_continue) {
ret = -EFAULT;
if (idx >= (i_size_read(mapping->host) >> huge_page_shift(h)))
goto out_release_nounlock;
/*
* Serialization between remove_inode_hugepages() and
* hugetlb_add_to_page_cache() below happens through the
* hugetlb_fault_mutex_table that here must be hold by
* the caller.
*/
ret = hugetlb_add_to_page_cache(folio, mapping, idx);
if (ret)
goto out_release_nounlock;
folio_in_pagecache = true;
}
ptl = huge_pte_lock(h, dst_mm, dst_pte);
ret = -EIO;
if (folio_test_hwpoison(folio))
goto out_release_unlock;
/*
* We allow to overwrite a pte marker: consider when both MISSING|WP
* registered, we firstly wr-protect a none pte which has no page cache
* page backing it, then access the page.
*/
ret = -EEXIST;
if (!huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte)))
goto out_release_unlock;
if (folio_in_pagecache)
hugetlb_add_file_rmap(folio);
else
hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr);
/*
* For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY
* with wp flag set, don't set pte write bit.
*/
_dst_pte = make_huge_pte(dst_vma, &folio->page,
!wp_enabled && !(is_continue && !vm_shared));
/*
* Always mark UFFDIO_COPY page dirty; note that this may not be
* extremely important for hugetlbfs for now since swapping is not
* supported, but we should still be clear in that this page cannot be
* thrown away at will, even if write bit not set.
*/
_dst_pte = huge_pte_mkdirty(_dst_pte);
_dst_pte = pte_mkyoung(_dst_pte);
if (wp_enabled)
_dst_pte = huge_pte_mkuffd_wp(_dst_pte);
set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size);
hugetlb_count_add(pages_per_huge_page(h), dst_mm);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
spin_unlock(ptl);
if (!is_continue)
folio_set_hugetlb_migratable(folio);
if (vm_shared || is_continue)
folio_unlock(folio);
ret = 0;
out:
return ret;
out_release_unlock:
spin_unlock(ptl);
if (vm_shared || is_continue)
folio_unlock(folio);
out_release_nounlock:
if (!folio_in_pagecache)
restore_reserve_on_error(h, dst_vma, dst_addr, folio);
folio_put(folio);
goto out;
}
#endif /* CONFIG_USERFAULTFD */
long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end,
pgprot_t newprot, unsigned long cp_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long start = address;
pte_t *ptep;
pte_t pte;
struct hstate *h = hstate_vma(vma);
long pages = 0, psize = huge_page_size(h);
bool shared_pmd = false;
struct mmu_notifier_range range;
unsigned long last_addr_mask;
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
/*
* In the case of shared PMDs, the area to flush could be beyond
* start/end. Set range.start/range.end to cover the maximum possible
* range if PMD sharing is possible.
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA,
0, mm, start, end);
adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
BUG_ON(address >= end);
flush_cache_range(vma, range.start, range.end);
mmu_notifier_invalidate_range_start(&range);
hugetlb_vma_lock_write(vma);
i_mmap_lock_write(vma->vm_file->f_mapping);
last_addr_mask = hugetlb_mask_last_page(h);
for (; address < end; address += psize) {
spinlock_t *ptl;
ptep = hugetlb_walk(vma, address, psize);
if (!ptep) {
if (!uffd_wp) {
address |= last_addr_mask;
continue;
}
/*
* Userfaultfd wr-protect requires pgtable
* pre-allocations to install pte markers.
*/
ptep = huge_pte_alloc(mm, vma, address, psize);
if (!ptep) {
pages = -ENOMEM;
break;
}
}
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, address, ptep)) {
/*
* When uffd-wp is enabled on the vma, unshare
* shouldn't happen at all. Warn about it if it
* happened due to some reason.
*/
WARN_ON_ONCE(uffd_wp || uffd_wp_resolve);
pages++;
spin_unlock(ptl);
shared_pmd = true;
address |= last_addr_mask;
continue;
}
pte = huge_ptep_get(mm, address, ptep);
if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
/* Nothing to do. */
} else if (unlikely(is_hugetlb_entry_migration(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
struct page *page = pfn_swap_entry_to_page(entry);
pte_t newpte = pte;
if (is_writable_migration_entry(entry)) {
if (PageAnon(page))
entry = make_readable_exclusive_migration_entry(
swp_offset(entry));
else
entry = make_readable_migration_entry(
swp_offset(entry));
newpte = swp_entry_to_pte(entry);
pages++;
}
if (uffd_wp)
newpte = pte_swp_mkuffd_wp(newpte);
else if (uffd_wp_resolve)
newpte = pte_swp_clear_uffd_wp(newpte);
if (!pte_same(pte, newpte))
set_huge_pte_at(mm, address, ptep, newpte, psize);
} else if (unlikely(is_pte_marker(pte))) {
/*
* Do nothing on a poison marker; page is
* corrupted, permissons do not apply. Here
* pte_marker_uffd_wp()==true implies !poison
* because they're mutual exclusive.
*/
if (pte_marker_uffd_wp(pte) && uffd_wp_resolve)
/* Safe to modify directly (non-present->none). */
huge_pte_clear(mm, address, ptep, psize);
} else if (!huge_pte_none(pte)) {
pte_t old_pte;
unsigned int shift = huge_page_shift(hstate_vma(vma));
old_pte = huge_ptep_modify_prot_start(vma, address, ptep);
pte = huge_pte_modify(old_pte, newprot);
pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
if (uffd_wp)
pte = huge_pte_mkuffd_wp(pte);
else if (uffd_wp_resolve)
pte = huge_pte_clear_uffd_wp(pte);
huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte);
pages++;
} else {
/* None pte */
if (unlikely(uffd_wp))
/* Safe to modify directly (none->non-present). */
set_huge_pte_at(mm, address, ptep,
make_pte_marker(PTE_MARKER_UFFD_WP),
psize);
}
spin_unlock(ptl);
}
/*
* Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
* may have cleared our pud entry and done put_page on the page table:
* once we release i_mmap_rwsem, another task can do the final put_page
* and that page table be reused and filled with junk. If we actually
* did unshare a page of pmds, flush the range corresponding to the pud.
*/
if (shared_pmd)
flush_hugetlb_tlb_range(vma, range.start, range.end);
else
flush_hugetlb_tlb_range(vma, start, end);
/*
* No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are
* downgrading page table protection not changing it to point to a new
* page.
*
* See Documentation/mm/mmu_notifier.rst
*/
i_mmap_unlock_write(vma->vm_file->f_mapping);
hugetlb_vma_unlock_write(vma);
mmu_notifier_invalidate_range_end(&range);
return pages > 0 ? (pages << h->order) : pages;
}
/* Return true if reservation was successful, false otherwise. */
bool hugetlb_reserve_pages(struct inode *inode,
long from, long to,
struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
long chg = -1, add = -1;
struct hstate *h = hstate_inode(inode);
struct hugepage_subpool *spool = subpool_inode(inode);
struct resv_map *resv_map;
struct hugetlb_cgroup *h_cg = NULL;
long gbl_reserve, regions_needed = 0;
/* This should never happen */
if (from > to) {
VM_WARN(1, "%s called with a negative range\n", __func__);
return false;
}
/*
* vma specific semaphore used for pmd sharing and fault/truncation
* synchronization
*/
hugetlb_vma_lock_alloc(vma);
/*
* Only apply hugepage reservation if asked. At fault time, an
* attempt will be made for VM_NORESERVE to allocate a page
* without using reserves
*/
if (vm_flags & VM_NORESERVE)
return true;
/*
* Shared mappings base their reservation on the number of pages that
* are already allocated on behalf of the file. Private mappings need
* to reserve the full area even if read-only as mprotect() may be
* called to make the mapping read-write. Assume !vma is a shm mapping
*/
if (!vma || vma->vm_flags & VM_MAYSHARE) {
/*
* resv_map can not be NULL as hugetlb_reserve_pages is only
* called for inodes for which resv_maps were created (see
* hugetlbfs_get_inode).
*/
resv_map = inode_resv_map(inode);
chg = region_chg(resv_map, from, to, ®ions_needed);
} else {
/* Private mapping. */
resv_map = resv_map_alloc();
if (!resv_map)
goto out_err;
chg = to - from;
set_vma_resv_map(vma, resv_map);
set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
}
if (chg < 0)
goto out_err;
if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h),
chg * pages_per_huge_page(h), &h_cg) < 0)
goto out_err;
if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) {
/* For private mappings, the hugetlb_cgroup uncharge info hangs
* of the resv_map.
*/
resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h);
}
/*
* There must be enough pages in the subpool for the mapping. If
* the subpool has a minimum size, there may be some global
* reservations already in place (gbl_reserve).
*/
gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0)
goto out_uncharge_cgroup;
/*
* Check enough hugepages are available for the reservation.
* Hand the pages back to the subpool if there are not
*/
if (hugetlb_acct_memory(h, gbl_reserve) < 0)
goto out_put_pages;
/*
* Account for the reservations made. Shared mappings record regions
* that have reservations as they are shared by multiple VMAs.
* When the last VMA disappears, the region map says how much
* the reservation was and the page cache tells how much of
* the reservation was consumed. Private mappings are per-VMA and
* only the consumed reservations are tracked. When the VMA
* disappears, the original reservation is the VMA size and the
* consumed reservations are stored in the map. Hence, nothing
* else has to be done for private mappings here
*/
if (!vma || vma->vm_flags & VM_MAYSHARE) {
add = region_add(resv_map, from, to, regions_needed, h, h_cg);
if (unlikely(add < 0)) {
hugetlb_acct_memory(h, -gbl_reserve);
goto out_put_pages;
} else if (unlikely(chg > add)) {
/*
* pages in this range were added to the reserve
* map between region_chg and region_add. This
* indicates a race with alloc_hugetlb_folio. Adjust
* the subpool and reserve counts modified above
* based on the difference.
*/
long rsv_adjust;
/*
* hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
* reference to h_cg->css. See comment below for detail.
*/
hugetlb_cgroup_uncharge_cgroup_rsvd(
hstate_index(h),
(chg - add) * pages_per_huge_page(h), h_cg);
rsv_adjust = hugepage_subpool_put_pages(spool,
chg - add);
hugetlb_acct_memory(h, -rsv_adjust);
} else if (h_cg) {
/*
* The file_regions will hold their own reference to
* h_cg->css. So we should release the reference held
* via hugetlb_cgroup_charge_cgroup_rsvd() when we are
* done.
*/
hugetlb_cgroup_put_rsvd_cgroup(h_cg);
}
}
return true;
out_put_pages:
/* put back original number of pages, chg */
(void)hugepage_subpool_put_pages(spool, chg);
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
chg * pages_per_huge_page(h), h_cg);
out_err:
hugetlb_vma_lock_free(vma);
if (!vma || vma->vm_flags & VM_MAYSHARE)
/* Only call region_abort if the region_chg succeeded but the
* region_add failed or didn't run.
*/
if (chg >= 0 && add < 0)
region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL);
}
return false;
}
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed)
{
struct hstate *h = hstate_inode(inode);
struct resv_map *resv_map = inode_resv_map(inode);
long chg = 0;
struct hugepage_subpool *spool = subpool_inode(inode);
long gbl_reserve;
/*
* Since this routine can be called in the evict inode path for all
* hugetlbfs inodes, resv_map could be NULL.
*/
if (resv_map) {
chg = region_del(resv_map, start, end);
/*
* region_del() can fail in the rare case where a region
* must be split and another region descriptor can not be
* allocated. If end == LONG_MAX, it will not fail.
*/
if (chg < 0)
return chg;
}
spin_lock(&inode->i_lock);
inode->i_blocks -= (blocks_per_huge_page(h) * freed);
spin_unlock(&inode->i_lock);
/*
* If the subpool has a minimum size, the number of global
* reservations to be released may be adjusted.
*
* Note that !resv_map implies freed == 0. So (chg - freed)
* won't go negative.
*/
gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed));
hugetlb_acct_memory(h, -gbl_reserve);
return 0;
}
#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
static unsigned long page_table_shareable(struct vm_area_struct *svma,
struct vm_area_struct *vma,
unsigned long addr, pgoff_t idx)
{
unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
svma->vm_start;
unsigned long sbase = saddr & PUD_MASK;
unsigned long s_end = sbase + PUD_SIZE;
/* Allow segments to share if only one is marked locked */
unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK;
unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK;
/*
* match the virtual addresses, permission and the alignment of the
* page table page.
*
* Also, vma_lock (vm_private_data) is required for sharing.
*/
if (pmd_index(addr) != pmd_index(saddr) ||
vm_flags != svm_flags ||
!range_in_vma(svma, sbase, s_end) ||
!svma->vm_private_data)
return 0;
return saddr;
}
bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
{
unsigned long start = addr & PUD_MASK;
unsigned long end = start + PUD_SIZE;
#ifdef CONFIG_USERFAULTFD
if (uffd_disable_huge_pmd_share(vma))
return false;
#endif
/*
* check on proper vm_flags and page table alignment
*/
if (!(vma->vm_flags & VM_MAYSHARE))
return false;
if (!vma->vm_private_data) /* vma lock required for sharing */
return false;
if (!range_in_vma(vma, start, end))
return false;
return true;
}
/*
* Determine if start,end range within vma could be mapped by shared pmd.
* If yes, adjust start and end to cover range associated with possible
* shared pmd mappings.
*/
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE),
v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
/*
* vma needs to span at least one aligned PUD size, and the range
* must be at least partially within in.
*/
if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end))
return;
/* Extend the range to be PUD aligned for a worst case scenario */
if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE);
}
/*
* Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
* and returns the corresponding pte. While this is not necessary for the
* !shared pmd case because we can allocate the pmd later as well, it makes the
* code much cleaner. pmd allocation is essential for the shared case because
* pud has to be populated inside the same i_mmap_rwsem section - otherwise
* racing tasks could either miss the sharing (see huge_pte_offset) or select a
* bad pmd for sharing.
*/
pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pud_t *pud)
{
struct address_space *mapping = vma->vm_file->f_mapping;
pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
vma->vm_pgoff;
struct vm_area_struct *svma;
unsigned long saddr;
pte_t *spte = NULL;
pte_t *pte;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
if (svma == vma)
continue;
saddr = page_table_shareable(svma, vma, addr, idx);
if (saddr) {
spte = hugetlb_walk(svma, saddr,
vma_mmu_pagesize(svma));
if (spte) {
ptdesc_pmd_pts_inc(virt_to_ptdesc(spte));
break;
}
}
}
if (!spte)
goto out;
spin_lock(&mm->page_table_lock);
if (pud_none(*pud)) {
pud_populate(mm, pud,
(pmd_t *)((unsigned long)spte & PAGE_MASK));
mm_inc_nr_pmds(mm);
} else {
ptdesc_pmd_pts_dec(virt_to_ptdesc(spte));
}
spin_unlock(&mm->page_table_lock);
out:
pte = (pte_t *)pmd_alloc(mm, pud, addr);
i_mmap_unlock_read(mapping);
return pte;
}
/*
* unmap huge page backed by shared pte.
*
* Called with page table lock held.
*
* returns: 1 successfully unmapped a shared pte page
* 0 the underlying pte page is not shared, or it is the last user
*/
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
unsigned long sz = huge_page_size(hstate_vma(vma));
pgd_t *pgd = pgd_offset(mm, addr);
p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping);
hugetlb_vma_assert_locked(vma);
if (sz != PMD_SIZE)
return 0;
if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep)))
return 0;
pud_clear(pud); ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm);
return 1;
}
#else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */
pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pud_t *pud)
{
return NULL;
}
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
return 0;
}
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
}
bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
{
return false;
}
#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */
#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return NULL;
pud = pud_alloc(mm, p4d, addr);
if (pud) {
if (sz == PUD_SIZE) {
pte = (pte_t *)pud;
} else {
BUG_ON(sz != PMD_SIZE);
if (want_pmd_share(vma, addr) && pud_none(*pud))
pte = huge_pmd_share(mm, vma, addr, pud);
else
pte = (pte_t *)pmd_alloc(mm, pud, addr);
}
}
if (pte) {
pte_t pteval = ptep_get_lockless(pte);
BUG_ON(pte_present(pteval) && !pte_huge(pteval));
}
return pte;
}
/*
* huge_pte_offset() - Walk the page table to resolve the hugepage
* entry at address @addr
*
* Return: Pointer to page table entry (PUD or PMD) for
* address @addr, or NULL if a !p*d_present() entry is encountered and the
* size @sz doesn't match the hugepage size at this level of the page
* table.
*/
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
return NULL;
p4d = p4d_offset(pgd, addr);
if (!p4d_present(*p4d))
return NULL;
pud = pud_offset(p4d, addr);
if (sz == PUD_SIZE)
/* must be pud huge, non-present or none */
return (pte_t *)pud;
if (!pud_present(*pud))
return NULL;
/* must have a valid entry and size to go further */
pmd = pmd_offset(pud, addr);
/* must be pmd huge, non-present or none */
return (pte_t *)pmd;
}
/*
* Return a mask that can be used to update an address to the last huge
* page in a page table page mapping size. Used to skip non-present
* page table entries when linearly scanning address ranges. Architectures
* with unique huge page to page table relationships can define their own
* version of this routine.
*/
unsigned long hugetlb_mask_last_page(struct hstate *h)
{
unsigned long hp_size = huge_page_size(h);
if (hp_size == PUD_SIZE)
return P4D_SIZE - PUD_SIZE;
else if (hp_size == PMD_SIZE)
return PUD_SIZE - PMD_SIZE;
else
return 0UL;
}
#else
/* See description above. Architectures can provide their own version. */
__weak unsigned long hugetlb_mask_last_page(struct hstate *h)
{
#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
if (huge_page_size(h) == PMD_SIZE)
return PUD_SIZE - PMD_SIZE;
#endif
return 0UL;
}
#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
/**
* folio_isolate_hugetlb - try to isolate an allocated hugetlb folio
* @folio: the folio to isolate
* @list: the list to add the folio to on success
*
* Isolate an allocated (refcount > 0) hugetlb folio, marking it as
* isolated/non-migratable, and moving it from the active list to the
* given list.
*
* Isolation will fail if @folio is not an allocated hugetlb folio, or if
* it is already isolated/non-migratable.
*
* On success, an additional folio reference is taken that must be dropped
* using folio_putback_hugetlb() to undo the isolation.
*
* Return: True if isolation worked, otherwise False.
*/
bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list)
{
bool ret = true;
spin_lock_irq(&hugetlb_lock);
if (!folio_test_hugetlb(folio) ||
!folio_test_hugetlb_migratable(folio) ||
!folio_try_get(folio)) {
ret = false;
goto unlock;
}
folio_clear_hugetlb_migratable(folio);
list_move_tail(&folio->lru, list);
unlock:
spin_unlock_irq(&hugetlb_lock);
return ret;
}
int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison)
{
int ret = 0;
*hugetlb = false;
spin_lock_irq(&hugetlb_lock);
if (folio_test_hugetlb(folio)) {
*hugetlb = true;
if (folio_test_hugetlb_freed(folio))
ret = 0;
else if (folio_test_hugetlb_migratable(folio) || unpoison)
ret = folio_try_get(folio);
else
ret = -EBUSY;
}
spin_unlock_irq(&hugetlb_lock);
return ret;
}
int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared)
{
int ret;
spin_lock_irq(&hugetlb_lock);
ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared);
spin_unlock_irq(&hugetlb_lock);
return ret;
}
/**
* folio_putback_hugetlb - unisolate a hugetlb folio
* @folio: the isolated hugetlb folio
*
* Putback/un-isolate the hugetlb folio that was previous isolated using
* folio_isolate_hugetlb(): marking it non-isolated/migratable and putting it
* back onto the active list.
*
* Will drop the additional folio reference obtained through
* folio_isolate_hugetlb().
*/
void folio_putback_hugetlb(struct folio *folio)
{
spin_lock_irq(&hugetlb_lock);
folio_set_hugetlb_migratable(folio);
list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist);
spin_unlock_irq(&hugetlb_lock);
folio_put(folio);
}
void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason)
{
struct hstate *h = folio_hstate(old_folio);
hugetlb_cgroup_migrate(old_folio, new_folio);
set_page_owner_migrate_reason(&new_folio->page, reason);
/*
* transfer temporary state of the new hugetlb folio. This is
* reverse to other transitions because the newpage is going to
* be final while the old one will be freed so it takes over
* the temporary status.
*
* Also note that we have to transfer the per-node surplus state
* here as well otherwise the global surplus count will not match
* the per-node's.
*/
if (folio_test_hugetlb_temporary(new_folio)) {
int old_nid = folio_nid(old_folio);
int new_nid = folio_nid(new_folio);
folio_set_hugetlb_temporary(old_folio);
folio_clear_hugetlb_temporary(new_folio);
/*
* There is no need to transfer the per-node surplus state
* when we do not cross the node.
*/
if (new_nid == old_nid)
return;
spin_lock_irq(&hugetlb_lock);
if (h->surplus_huge_pages_node[old_nid]) {
h->surplus_huge_pages_node[old_nid]--;
h->surplus_huge_pages_node[new_nid]++;
}
spin_unlock_irq(&hugetlb_lock);
}
/*
* Our old folio is isolated and has "migratable" cleared until it
* is putback. As migration succeeded, set the new folio "migratable"
* and add it to the active list.
*/
spin_lock_irq(&hugetlb_lock);
folio_set_hugetlb_migratable(new_folio);
list_move_tail(&new_folio->lru, &(folio_hstate(new_folio))->hugepage_activelist);
spin_unlock_irq(&hugetlb_lock);
}
static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
unsigned long address;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & VM_MAYSHARE))
return;
if (start >= end)
return;
flush_cache_range(vma, start, end);
/*
* No need to call adjust_range_if_pmd_sharing_possible(), because
* we have already done the PUD_SIZE alignment.
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
start, end);
mmu_notifier_invalidate_range_start(&range);
hugetlb_vma_lock_write(vma);
i_mmap_lock_write(vma->vm_file->f_mapping);
for (address = start; address < end; address += PUD_SIZE) {
ptep = hugetlb_walk(vma, address, sz);
if (!ptep)
continue;
ptl = huge_pte_lock(h, mm, ptep);
huge_pmd_unshare(mm, vma, address, ptep);
spin_unlock(ptl);
}
flush_hugetlb_tlb_range(vma, start, end);
i_mmap_unlock_write(vma->vm_file->f_mapping);
hugetlb_vma_unlock_write(vma);
/*
* No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see
* Documentation/mm/mmu_notifier.rst.
*/
mmu_notifier_invalidate_range_end(&range);
}
/*
* This function will unconditionally remove all the shared pmd pgtable entries
* within the specific vma for a hugetlbfs memory range.
*/
void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
{
hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
ALIGN_DOWN(vma->vm_end, PUD_SIZE));
}
// SPDX-License-Identifier: GPL-2.0
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
/*
* This is an implementation of the notion of "decrement a
* reference count, and return locked if it decremented to zero".
*
* NOTE NOTE NOTE! This is _not_ equivalent to
*
* if (atomic_dec_and_test(&atomic)) {
* spin_lock(&lock);
* return 1;
* }
* return 0;
*
* because the spin-lock and the decrement must be
* "atomic".
*/
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
{
/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
if (atomic_add_unless(atomic, -1, 1))
return 0;
/* Otherwise do it the slow way */
spin_lock(lock);
if (atomic_dec_and_test(atomic))
return 1;
spin_unlock(lock);
return 0;
}
EXPORT_SYMBOL(_atomic_dec_and_lock);
int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
unsigned long *flags)
{
/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
if (atomic_add_unless(atomic, -1, 1))
return 0;
/* Otherwise do it the slow way */
spin_lock_irqsave(lock, *flags);
if (atomic_dec_and_test(atomic))
return 1;
spin_unlock_irqrestore(lock, *flags);
return 0;
}
EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock)
{
/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
if (atomic_add_unless(atomic, -1, 1))
return 0;
/* Otherwise do it the slow way */
raw_spin_lock(lock);
if (atomic_dec_and_test(atomic))
return 1;
raw_spin_unlock(lock);
return 0;
}
EXPORT_SYMBOL(_atomic_dec_and_raw_lock);
int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
unsigned long *flags)
{
/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
if (atomic_add_unless(atomic, -1, 1))
return 0;
/* Otherwise do it the slow way */
raw_spin_lock_irqsave(lock, *flags);
if (atomic_dec_and_test(atomic))
return 1;
raw_spin_unlock_irqrestore(lock, *flags);
return 0;
}
EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave);
/* SPDX-License-Identifier: GPL-2.0 */
/*
* workqueue.h --- work queue handling for Linux.
*/
#ifndef _LINUX_WORKQUEUE_H
#define _LINUX_WORKQUEUE_H
#include <linux/timer.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/lockdep.h>
#include <linux/threads.h>
#include <linux/atomic.h>
#include <linux/cpumask_types.h>
#include <linux/rcupdate.h>
#include <linux/workqueue_types.h>
/*
* The first word is the work queue pointer and the flags rolled into
* one
*/
#define work_data_bits(work) ((unsigned long *)(&(work)->data))
enum work_bits {
WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */
WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */
WORK_STRUCT_PWQ_BIT, /* data points to pwq */
WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */
#endif
WORK_STRUCT_FLAG_BITS,
/* color for workqueue flushing */
WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS,
WORK_STRUCT_COLOR_BITS = 4,
/*
* When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/
* debugobjects turned off. This makes pwqs aligned to 256 bytes (512
* bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors.
*
* MSB
* [ pwq pointer ] [ flush color ] [ STRUCT flags ]
* 4 bits 4 or 5 bits
*/
WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS,
/*
* data contains off-queue information when !WORK_STRUCT_PWQ.
*
* MSB
* [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ]
* 16 bits 1 bit 4 or 5 bits
*/
WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS,
WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT,
WORK_OFFQ_FLAG_END,
WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT,
WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS,
WORK_OFFQ_DISABLE_BITS = 16,
/*
* When a work item is off queue, the high bits encode off-queue flags
* and the last pool it was on. Cap pool ID to 31 bits and use the
* highest number to indicate that no pool is associated.
*/
WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS,
WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
};
enum work_flags {
WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT,
WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT,
WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT,
WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT,
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT,
#else
WORK_STRUCT_STATIC = 0,
#endif
};
enum wq_misc_consts {
WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS),
/* not bound to any CPU, prefer the local CPU */
WORK_CPU_UNBOUND = NR_CPUS,
/* bit mask for work_busy() return values */
WORK_BUSY_PENDING = 1 << 0,
WORK_BUSY_RUNNING = 1 << 1,
/* maximum string length for set_worker_desc() */
WORKER_DESC_LEN = 32,
};
/* Convenience constants - of type 'unsigned long', not 'enum'! */
#define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT)
#define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT)
#define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT)
#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1)
#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT)
#define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1))
#define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
#define WORK_DATA_STATIC_INIT() \
ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC))
struct delayed_work {
struct work_struct work;
struct timer_list timer;
/* target workqueue and CPU ->timer uses to queue ->work */
struct workqueue_struct *wq;
int cpu;
};
struct rcu_work {
struct work_struct work;
struct rcu_head rcu;
/* target workqueue ->rcu uses to queue ->work */
struct workqueue_struct *wq;
};
enum wq_affn_scope {
WQ_AFFN_DFL, /* use system default */
WQ_AFFN_CPU, /* one pod per CPU */
WQ_AFFN_SMT, /* one pod poer SMT */
WQ_AFFN_CACHE, /* one pod per LLC */
WQ_AFFN_NUMA, /* one pod per NUMA node */
WQ_AFFN_SYSTEM, /* one pod across the whole system */
WQ_AFFN_NR_TYPES,
};
/**
* struct workqueue_attrs - A struct for workqueue attributes.
*
* This can be used to change attributes of an unbound workqueue.
*/
struct workqueue_attrs {
/**
* @nice: nice level
*/
int nice;
/**
* @cpumask: allowed CPUs
*
* Work items in this workqueue are affine to these CPUs and not allowed
* to execute on other CPUs. A pool serving a workqueue must have the
* same @cpumask.
*/
cpumask_var_t cpumask;
/**
* @__pod_cpumask: internal attribute used to create per-pod pools
*
* Internal use only.
*
* Per-pod unbound worker pools are used to improve locality. Always a
* subset of ->cpumask. A workqueue can be associated with multiple
* worker pools with disjoint @__pod_cpumask's. Whether the enforcement
* of a pool's @__pod_cpumask is strict depends on @affn_strict.
*/
cpumask_var_t __pod_cpumask;
/**
* @affn_strict: affinity scope is strict
*
* If clear, workqueue will make a best-effort attempt at starting the
* worker inside @__pod_cpumask but the scheduler is free to migrate it
* outside.
*
* If set, workers are only allowed to run inside @__pod_cpumask.
*/
bool affn_strict;
/*
* Below fields aren't properties of a worker_pool. They only modify how
* :c:func:`apply_workqueue_attrs` select pools and thus don't
* participate in pool hash calculations or equality comparisons.
*
* If @affn_strict is set, @cpumask isn't a property of a worker_pool
* either.
*/
/**
* @affn_scope: unbound CPU affinity scope
*
* CPU pods are used to improve execution locality of unbound work
* items. There are multiple pod types, one for each wq_affn_scope, and
* every CPU in the system belongs to one pod in every pod type. CPUs
* that belong to the same pod share the worker pool. For example,
* selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker
* pool for each NUMA node.
*/
enum wq_affn_scope affn_scope;
/**
* @ordered: work items must be executed one by one in queueing order
*/
bool ordered;
};
static inline struct delayed_work *to_delayed_work(struct work_struct *work)
{
return container_of(work, struct delayed_work, work);
}
static inline struct rcu_work *to_rcu_work(struct work_struct *work)
{
return container_of(work, struct rcu_work, work);
}
struct execute_work {
struct work_struct work;
};
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting _key
* here is required, otherwise it could get initialised to the
* copy of the lockdep_map!
*/
#define __WORK_INIT_LOCKDEP_MAP(n, k) \
.lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k),
#else
#define __WORK_INIT_LOCKDEP_MAP(n, k)
#endif
#define __WORK_INITIALIZER(n, f) { \
.data = WORK_DATA_STATIC_INIT(), \
.entry = { &(n).entry, &(n).entry }, \
.func = (f), \
__WORK_INIT_LOCKDEP_MAP(#n, &(n)) \
}
#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \
.work = __WORK_INITIALIZER((n).work, (f)), \
.timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\
(tflags) | TIMER_IRQSAFE), \
}
#define DECLARE_WORK(n, f) \
struct work_struct n = __WORK_INITIALIZER(n, f)
#define DECLARE_DELAYED_WORK(n, f) \
struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0)
#define DECLARE_DEFERRABLE_WORK(n, f) \
struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE)
#ifdef CONFIG_DEBUG_OBJECTS_WORK
extern void __init_work(struct work_struct *work, int onstack);
extern void destroy_work_on_stack(struct work_struct *work);
extern void destroy_delayed_work_on_stack(struct delayed_work *work);
static inline unsigned int work_static(struct work_struct *work)
{
return *work_data_bits(work) & WORK_STRUCT_STATIC;
}
#else
static inline void __init_work(struct work_struct *work, int onstack) { }
static inline void destroy_work_on_stack(struct work_struct *work) { }
static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { }
static inline unsigned int work_static(struct work_struct *work) { return 0; }
#endif
/*
* initialize all of a work item in one go
*
* NOTE! No point in using "atomic_long_set()": using a direct
* assignment of the work data initializer allows the compiler
* to generate better code.
*/
#ifdef CONFIG_LOCKDEP
#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \
do { \
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \
INIT_LIST_HEAD(&(_work)->entry); \
(_work)->func = (_func); \
} while (0)
#else
#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \
do { \
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
INIT_LIST_HEAD(&(_work)->entry); \
(_work)->func = (_func); \
} while (0)
#endif
#define __INIT_WORK(_work, _func, _onstack) \
do { \
static __maybe_unused struct lock_class_key __key; \
\
__INIT_WORK_KEY(_work, _func, _onstack, &__key); \
} while (0)
#define INIT_WORK(_work, _func) \
__INIT_WORK((_work), (_func), 0)
#define INIT_WORK_ONSTACK(_work, _func) \
__INIT_WORK((_work), (_func), 1)
#define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \
__INIT_WORK_KEY((_work), (_func), 1, _key)
#define __INIT_DELAYED_WORK(_work, _func, _tflags) \
do { \
INIT_WORK(&(_work)->work, (_func)); \
__init_timer(&(_work)->timer, \
delayed_work_timer_fn, \
(_tflags) | TIMER_IRQSAFE); \
} while (0)
#define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \
do { \
INIT_WORK_ONSTACK(&(_work)->work, (_func)); \
__init_timer_on_stack(&(_work)->timer, \
delayed_work_timer_fn, \
(_tflags) | TIMER_IRQSAFE); \
} while (0)
#define INIT_DELAYED_WORK(_work, _func) \
__INIT_DELAYED_WORK(_work, _func, 0)
#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \
__INIT_DELAYED_WORK_ONSTACK(_work, _func, 0)
#define INIT_DEFERRABLE_WORK(_work, _func) \
__INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE)
#define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \
__INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE)
#define INIT_RCU_WORK(_work, _func) \
INIT_WORK(&(_work)->work, (_func))
#define INIT_RCU_WORK_ONSTACK(_work, _func) \
INIT_WORK_ONSTACK(&(_work)->work, (_func))
/**
* work_pending - Find out whether a work item is currently pending
* @work: The work item in question
*/
#define work_pending(work) \
test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
/**
* delayed_work_pending - Find out whether a delayable work item is currently
* pending
* @w: The work item in question
*/
#define delayed_work_pending(w) \
work_pending(&(w)->work)
/*
* Workqueue flags and constants. For details, please refer to
* Documentation/core-api/workqueue.rst.
*/
enum wq_flags {
WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */
WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
WQ_FREEZABLE = 1 << 2, /* freeze during suspend */
WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
WQ_HIGHPRI = 1 << 4, /* high priority */
WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */
WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */
/*
* Per-cpu workqueues are generally preferred because they tend to
* show better performance thanks to cache locality. Per-cpu
* workqueues exclude the scheduler from choosing the CPU to
* execute the worker threads, which has an unfortunate side effect
* of increasing power consumption.
*
* The scheduler considers a CPU idle if it doesn't have any task
* to execute and tries to keep idle cores idle to conserve power;
* however, for example, a per-cpu work item scheduled from an
* interrupt handler on an idle CPU will force the scheduler to
* execute the work item on that CPU breaking the idleness, which in
* turn may lead to more scheduling choices which are sub-optimal
* in terms of power consumption.
*
* Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default
* but become unbound if workqueue.power_efficient kernel param is
* specified. Per-cpu workqueues which are identified to
* contribute significantly to power-consumption are identified and
* marked with this flag and enabling the power_efficient mode
* leads to noticeable power saving at the cost of small
* performance disadvantage.
*
* http://thread.gmane.org/gmane.linux.kernel/1480396
*/
WQ_POWER_EFFICIENT = 1 << 7,
__WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */
__WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */
__WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
__WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
/* BH wq only allows the following flags */
__WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI,
};
enum wq_consts {
WQ_MAX_ACTIVE = 2048, /* I like 2048, better ideas? */
WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE,
WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2,
/*
* Per-node default cap on min_active. Unless explicitly set, min_active
* is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see
* workqueue_struct->min_active definition.
*/
WQ_DFL_MIN_ACTIVE = 8,
};
/*
* System-wide workqueues which are always present.
*
* system_wq is the one used by schedule[_delayed]_work[_on]().
* Multi-CPU multi-threaded. There are users which expect relatively
* short queue flush time. Don't queue works which can run for too
* long.
*
* system_highpri_wq is similar to system_wq but for work items which
* require WQ_HIGHPRI.
*
* system_long_wq is similar to system_wq but may host long running
* works. Queue flushing might take relatively long.
*
* system_unbound_wq is unbound workqueue. Workers are not bound to
* any specific CPU, not concurrency managed, and all queued works are
* executed immediately as long as max_active limit is not reached and
* resources are available.
*
* system_freezable_wq is equivalent to system_wq except that it's
* freezable.
*
* *_power_efficient_wq are inclined towards saving power and converted
* into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
* they are same as their non-power-efficient counterparts - e.g.
* system_power_efficient_wq is identical to system_wq if
* 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info.
*
* system_bh[_highpri]_wq are convenience interface to softirq. BH work items
* are executed in the queueing CPU's BH context in the queueing order.
*/
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_highpri_wq;
extern struct workqueue_struct *system_long_wq;
extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *system_freezable_wq;
extern struct workqueue_struct *system_power_efficient_wq;
extern struct workqueue_struct *system_freezable_power_efficient_wq;
extern struct workqueue_struct *system_bh_wq;
extern struct workqueue_struct *system_bh_highpri_wq;
void workqueue_softirq_action(bool highpri);
void workqueue_softirq_dead(unsigned int cpu);
/**
* alloc_workqueue - allocate a workqueue
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags
* @max_active: max in-flight work items, 0 for default
* @...: args for @fmt
*
* For a per-cpu workqueue, @max_active limits the number of in-flight work
* items for each CPU. e.g. @max_active of 1 indicates that each CPU can be
* executing at most one work item for the workqueue.
*
* For unbound workqueues, @max_active limits the number of in-flight work items
* for the whole system. e.g. @max_active of 16 indicates that that there can be
* at most 16 work items executing for the workqueue in the whole system.
*
* As sharing the same active counter for an unbound workqueue across multiple
* NUMA nodes can be expensive, @max_active is distributed to each NUMA node
* according to the proportion of the number of online CPUs and enforced
* independently.
*
* Depending on online CPU distribution, a node may end up with per-node
* max_active which is significantly lower than @max_active, which can lead to
* deadlocks if the per-node concurrency limit is lower than the maximum number
* of interdependent work items for the workqueue.
*
* To guarantee forward progress regardless of online CPU distribution, the
* concurrency limit on every node is guaranteed to be equal to or greater than
* min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means
* that the sum of per-node max_active's may be larger than @max_active.
*
* For detailed information on %WQ_* flags, please refer to
* Documentation/core-api/workqueue.rst.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
__printf(1, 4) struct workqueue_struct *
alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
#ifdef CONFIG_LOCKDEP
/**
* alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags
* @max_active: max in-flight work items, 0 for default
* @lockdep_map: user-defined lockdep_map
* @...: args for @fmt
*
* Same as alloc_workqueue but with the a user-define lockdep_map. Useful for
* workqueues created with the same purpose and to avoid leaking a lockdep_map
* on each workqueue creation.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
__printf(1, 5) struct workqueue_struct *
alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
struct lockdep_map *lockdep_map, ...);
/**
* alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with
* user-defined lockdep_map
*
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
* @lockdep_map: user-defined lockdep_map
* @args: args for @fmt
*
* Same as alloc_ordered_workqueue but with the a user-define lockdep_map.
* Useful for workqueues created with the same purpose and to avoid leaking a
* lockdep_map on each workqueue creation.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
#define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \
alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), \
1, lockdep_map, ##args)
#endif
/**
* alloc_ordered_workqueue - allocate an ordered workqueue
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
* @args: args for @fmt
*
* Allocate an ordered workqueue. An ordered workqueue executes at
* most one work item at any given time in the queued order. They are
* implemented as unbound workqueues with @max_active of one.
*
* RETURNS:
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
#define alloc_ordered_workqueue(fmt, flags, args...) \
alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
#define create_workqueue(name) \
alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
#define create_freezable_workqueue(name) \
alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \
WQ_MEM_RECLAIM, 1, (name))
#define create_singlethread_workqueue(name) \
alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
#define from_work(var, callback_work, work_fieldname) \
container_of(callback_work, typeof(*var), work_fieldname)
extern void destroy_workqueue(struct workqueue_struct *wq);
struct workqueue_attrs *alloc_workqueue_attrs(void);
void free_workqueue_attrs(struct workqueue_attrs *attrs);
int apply_workqueue_attrs(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs);
extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask);
extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work);
extern bool queue_work_node(int node, struct workqueue_struct *wq,
struct work_struct *work);
extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *work, unsigned long delay);
extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay);
extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork);
extern void __flush_workqueue(struct workqueue_struct *wq);
extern void drain_workqueue(struct workqueue_struct *wq);
extern int schedule_on_each_cpu(work_func_t func);
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern bool flush_work(struct work_struct *work);
extern bool cancel_work(struct work_struct *work);
extern bool cancel_work_sync(struct work_struct *work);
extern bool flush_delayed_work(struct delayed_work *dwork);
extern bool cancel_delayed_work(struct delayed_work *dwork);
extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
extern bool disable_work(struct work_struct *work);
extern bool disable_work_sync(struct work_struct *work);
extern bool enable_work(struct work_struct *work);
extern bool disable_delayed_work(struct delayed_work *dwork);
extern bool disable_delayed_work_sync(struct delayed_work *dwork);
extern bool enable_delayed_work(struct delayed_work *dwork);
extern bool flush_rcu_work(struct rcu_work *rwork);
extern void workqueue_set_max_active(struct workqueue_struct *wq,
int max_active);
extern void workqueue_set_min_active(struct workqueue_struct *wq,
int min_active);
extern struct work_struct *current_work(void);
extern bool current_is_workqueue_rescuer(void);
extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
extern unsigned int work_busy(struct work_struct *work);
extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);
extern void print_worker_info(const char *log_lvl, struct task_struct *task);
extern void show_all_workqueues(void);
extern void show_freezable_workqueues(void);
extern void show_one_workqueue(struct workqueue_struct *wq);
extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);
/**
* queue_work - queue work on a workqueue
* @wq: workqueue to use
* @work: work to queue
*
* Returns %false if @work was already on a queue, %true otherwise.
*
* We queue the work to the CPU on which it was submitted, but if the CPU dies
* it can be processed by another CPU.
*
* Memory-ordering properties: If it returns %true, guarantees that all stores
* preceding the call to queue_work() in the program order will be visible from
* the CPU which will execute @work by the time such work executes, e.g.,
*
* { x is initially 0 }
*
* CPU0 CPU1
*
* WRITE_ONCE(x, 1); [ @work is being executed ]
* r0 = queue_work(wq, work); r1 = READ_ONCE(x);
*
* Forbids: r0 == true && r1 == 0
*/
static inline bool queue_work(struct workqueue_struct *wq,
struct work_struct *work)
{
return queue_work_on(WORK_CPU_UNBOUND, wq, work);
}
/**
* queue_delayed_work - queue work on a workqueue after delay
* @wq: workqueue to use
* @dwork: delayable work to queue
* @delay: number of jiffies to wait before queueing
*
* Equivalent to queue_delayed_work_on() but tries to use the local CPU.
*/
static inline bool queue_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
/**
* mod_delayed_work - modify delay of or queue a delayed work
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* mod_delayed_work_on() on local CPU.
*/
static inline bool mod_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork,
unsigned long delay)
{
return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
/**
* schedule_work_on - put work task on a specific cpu
* @cpu: cpu to put the work task on
* @work: job to be done
*
* This puts a job on a specific cpu
*/
static inline bool schedule_work_on(int cpu, struct work_struct *work)
{
return queue_work_on(cpu, system_wq, work);
}
/**
* schedule_work - put work task in global workqueue
* @work: job to be done
*
* Returns %false if @work was already on the kernel-global workqueue and
* %true otherwise.
*
* This puts a job in the kernel-global workqueue if it was not already
* queued and leaves it in the same position on the kernel-global
* workqueue otherwise.
*
* Shares the same memory-ordering properties of queue_work(), cf. the
* DocBook header of queue_work().
*/
static inline bool schedule_work(struct work_struct *work)
{
return queue_work(system_wq, work);
}
/**
* enable_and_queue_work - Enable and queue a work item on a specific workqueue
* @wq: The target workqueue
* @work: The work item to be enabled and queued
*
* This function combines the operations of enable_work() and queue_work(),
* providing a convenient way to enable and queue a work item in a single call.
* It invokes enable_work() on @work and then queues it if the disable depth
* reached 0. Returns %true if the disable depth reached 0 and @work is queued,
* and %false otherwise.
*
* Note that @work is always queued when disable depth reaches zero. If the
* desired behavior is queueing only if certain events took place while @work is
* disabled, the user should implement the necessary state tracking and perform
* explicit conditional queueing after enable_work().
*/
static inline bool enable_and_queue_work(struct workqueue_struct *wq,
struct work_struct *work)
{
if (enable_work(work)) {
queue_work(wq, work);
return true;
}
return false;
}
/*
* Detect attempt to flush system-wide workqueues at compile time when possible.
* Warn attempt to flush system-wide workqueues at runtime.
*
* See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp
* for reasons and steps for converting system-wide workqueues into local workqueues.
*/
extern void __warn_flushing_systemwide_wq(void)
__compiletime_warning("Please avoid flushing system-wide workqueues.");
/* Please stop using this function, for this function will be removed in near future. */
#define flush_scheduled_work() \
({ \
__warn_flushing_systemwide_wq(); \
__flush_workqueue(system_wq); \
})
#define flush_workqueue(wq) \
({ \
struct workqueue_struct *_wq = (wq); \
\
if ((__builtin_constant_p(_wq == system_wq) && \
_wq == system_wq) || \
(__builtin_constant_p(_wq == system_highpri_wq) && \
_wq == system_highpri_wq) || \
(__builtin_constant_p(_wq == system_long_wq) && \
_wq == system_long_wq) || \
(__builtin_constant_p(_wq == system_unbound_wq) && \
_wq == system_unbound_wq) || \
(__builtin_constant_p(_wq == system_freezable_wq) && \
_wq == system_freezable_wq) || \
(__builtin_constant_p(_wq == system_power_efficient_wq) && \
_wq == system_power_efficient_wq) || \
(__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \
_wq == system_freezable_power_efficient_wq)) \
__warn_flushing_systemwide_wq(); \
__flush_workqueue(_wq); \
})
/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
* @delay: number of jiffies to wait
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue on the specified CPU.
*/
static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work_on(cpu, system_wq, dwork, delay);
}
/**
* schedule_delayed_work - put work task in global workqueue after delay
* @dwork: job to be done
* @delay: number of jiffies to wait or 0 for immediate execution
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue.
*/
static inline bool schedule_delayed_work(struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work(system_wq, dwork, delay);
}
#ifndef CONFIG_SMP
static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
{
return fn(arg);
}
static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
{
return fn(arg);
}
#else
long work_on_cpu_key(int cpu, long (*fn)(void *),
void *arg, struct lock_class_key *key);
/*
* A new key is defined for each caller to make sure the work
* associated with the function doesn't share its locking class.
*/
#define work_on_cpu(_cpu, _fn, _arg) \
({ \
static struct lock_class_key __key; \
\
work_on_cpu_key(_cpu, _fn, _arg, &__key); \
})
long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
void *arg, struct lock_class_key *key);
/*
* A new key is defined for each caller to make sure the work
* associated with the function doesn't share its locking class.
*/
#define work_on_cpu_safe(_cpu, _fn, _arg) \
({ \
static struct lock_class_key __key; \
\
work_on_cpu_safe_key(_cpu, _fn, _arg, &__key); \
})
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
extern void freeze_workqueues_begin(void);
extern bool freeze_workqueues_busy(void);
extern void thaw_workqueues(void);
#endif /* CONFIG_FREEZER */
#ifdef CONFIG_SYSFS
int workqueue_sysfs_register(struct workqueue_struct *wq);
#else /* CONFIG_SYSFS */
static inline int workqueue_sysfs_register(struct workqueue_struct *wq)
{ return 0; }
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_WQ_WATCHDOG
void wq_watchdog_touch(int cpu);
#else /* CONFIG_WQ_WATCHDOG */
static inline void wq_watchdog_touch(int cpu) { }
#endif /* CONFIG_WQ_WATCHDOG */
#ifdef CONFIG_SMP
int workqueue_prepare_cpu(unsigned int cpu);
int workqueue_online_cpu(unsigned int cpu);
int workqueue_offline_cpu(unsigned int cpu);
#endif
void __init workqueue_init_early(void);
void __init workqueue_init(void);
void __init workqueue_init_topology(void);
#endif
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_CGROUP_H
#define _LINUX_CGROUP_H
/*
* cgroup interface
*
* Copyright (C) 2003 BULL SA
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
*/
#include <linux/sched.h>
#include <linux/nodemask.h>
#include <linux/list.h>
#include <linux/rculist.h>
#include <linux/cgroupstats.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#include <linux/jump_label.h>
#include <linux/types.h>
#include <linux/ns_common.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
#include <linux/refcount.h>
#include <linux/kernel_stat.h>
#include <linux/cgroup-defs.h>
struct kernel_clone_args;
/*
* All weight knobs on the default hierarchy should use the following min,
* default and max values. The default value is the logarithmic center of
* MIN and MAX and allows 100x to be expressed in both directions.
*/
#define CGROUP_WEIGHT_MIN 1
#define CGROUP_WEIGHT_DFL 100
#define CGROUP_WEIGHT_MAX 10000
#ifdef CONFIG_CGROUPS
enum {
CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */
CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */
CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */
};
/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
struct cgroup_subsys *ss;
unsigned int flags;
struct list_head *cset_pos;
struct list_head *cset_head;
struct list_head *tcset_pos;
struct list_head *tcset_head;
struct list_head *task_pos;
struct list_head *cur_tasks_head;
struct css_set *cur_cset;
struct css_set *cur_dcset;
struct task_struct *cur_task;
struct list_head iters_node; /* css_set->task_iters */
};
extern struct file_system_type cgroup_fs_type;
extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;
extern spinlock_t css_set_lock;
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
#include <linux/cgroup_subsys.h>
#undef SUBSYS
#define SUBSYS(_x) \
extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \
extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key;
#include <linux/cgroup_subsys.h>
#undef SUBSYS
/**
* cgroup_subsys_enabled - fast test on whether a subsys is enabled
* @ss: subsystem in question
*/
#define cgroup_subsys_enabled(ss) \
static_branch_likely(&ss ## _enabled_key)
/**
* cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy
* @ss: subsystem in question
*/
#define cgroup_subsys_on_dfl(ss) \
static_branch_likely(&ss ## _on_dfl_key)
bool css_has_online_children(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
struct cgroup_subsys *ss);
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
struct cgroup_subsys *ss);
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss);
struct cgroup *cgroup_get_from_path(const char *path);
struct cgroup *cgroup_get_from_fd(int fd);
struct cgroup *cgroup_v1v2_get_from_fd(int fd);
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_rm_cftypes(struct cftype *cfts);
void cgroup_file_notify(struct cgroup_file *cfile);
void cgroup_file_show(struct cgroup_file *cfile, bool show);
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk);
void cgroup_fork(struct task_struct *p);
extern int cgroup_can_fork(struct task_struct *p,
struct kernel_clone_args *kargs);
extern void cgroup_cancel_fork(struct task_struct *p,
struct kernel_clone_args *kargs);
extern void cgroup_post_fork(struct task_struct *p,
struct kernel_clone_args *kargs);
void cgroup_exit(struct task_struct *p);
void cgroup_release(struct task_struct *p);
void cgroup_free(struct task_struct *p);
int cgroup_init_early(void);
int cgroup_init(void);
int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v);
/*
* Iteration helpers and macros.
*/
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *parent);
struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos);
struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *css);
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp);
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp);
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
struct css_task_iter *it);
struct task_struct *css_task_iter_next(struct css_task_iter *it);
void css_task_iter_end(struct css_task_iter *it);
/**
* css_for_each_child - iterate through children of a css
* @pos: the css * to use as the loop cursor
* @parent: css whose children to walk
*
* Walk @parent's children. Must be called under rcu_read_lock().
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* It is allowed to temporarily drop RCU read lock during iteration. The
* caller is responsible for ensuring that @pos remains accessible until
* the start of the next iteration by, for example, bumping the css refcnt.
*/
#define css_for_each_child(pos, parent) \
for ((pos) = css_next_child(NULL, (parent)); (pos); \
(pos) = css_next_child((pos), (parent)))
/**
* css_for_each_descendant_pre - pre-order walk of a css's descendants
* @pos: the css * to use as the loop cursor
* @root: css whose descendants to walk
*
* Walk @root's descendants. @root is included in the iteration and the
* first node to be visited. Must be called under rcu_read_lock().
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* For example, the following guarantees that a descendant can't escape
* state updates of its ancestors.
*
* my_online(@css)
* {
* Lock @css's parent and @css;
* Inherit state from the parent;
* Unlock both.
* }
*
* my_update_state(@css)
* {
* css_for_each_descendant_pre(@pos, @css) {
* Lock @pos;
* if (@pos == @css)
* Update @css's state;
* else
* Verify @pos is alive and inherit state from its parent;
* Unlock @pos;
* }
* }
*
* As long as the inheriting step, including checking the parent state, is
* enclosed inside @pos locking, double-locking the parent isn't necessary
* while inheriting. The state update to the parent is guaranteed to be
* visible by walking order and, as long as inheriting operations to the
* same @pos are atomic to each other, multiple updates racing each other
* still result in the correct state. It's guaranateed that at least one
* inheritance happens for any css after the latest update to its parent.
*
* If checking parent's state requires locking the parent, each inheriting
* iteration should lock and unlock both @pos->parent and @pos.
*
* Alternatively, a subsystem may choose to use a single global lock to
* synchronize ->css_online() and ->css_offline() against tree-walking
* operations.
*
* It is allowed to temporarily drop RCU read lock during iteration. The
* caller is responsible for ensuring that @pos remains accessible until
* the start of the next iteration by, for example, bumping the css refcnt.
*/
#define css_for_each_descendant_pre(pos, css) \
for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \
(pos) = css_next_descendant_pre((pos), (css)))
/**
* css_for_each_descendant_post - post-order walk of a css's descendants
* @pos: the css * to use as the loop cursor
* @css: css whose descendants to walk
*
* Similar to css_for_each_descendant_pre() but performs post-order
* traversal instead. @root is included in the iteration and the last
* node to be visited.
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* Note that the walk visibility guarantee example described in pre-order
* walk doesn't apply the same to post-order walks.
*/
#define css_for_each_descendant_post(pos, css) \
for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \
(pos) = css_next_descendant_post((pos), (css)))
/**
* cgroup_taskset_for_each - iterate cgroup_taskset
* @task: the loop cursor
* @dst_css: the destination css
* @tset: taskset to iterate
*
* @tset may contain multiple tasks and they may belong to multiple
* processes.
*
* On the v2 hierarchy, there may be tasks from multiple processes and they
* may not share the source or destination csses.
*
* On traditional hierarchies, when there are multiple tasks in @tset, if a
* task of a process is in @tset, all tasks of the process are in @tset.
* Also, all are guaranteed to share the same source and destination csses.
*
* Iteration is not in any specific order.
*/
#define cgroup_taskset_for_each(task, dst_css, tset) \
for ((task) = cgroup_taskset_first((tset), &(dst_css)); \
(task); \
(task) = cgroup_taskset_next((tset), &(dst_css)))
/**
* cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
* @leader: the loop cursor
* @dst_css: the destination css
* @tset: taskset to iterate
*
* Iterate threadgroup leaders of @tset. For single-task migrations, @tset
* may not contain any.
*/
#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \
for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \
(leader); \
(leader) = cgroup_taskset_next((tset), &(dst_css))) \
if ((leader) != (leader)->group_leader) \
; \
else
/*
* Inline functions.
*/
#ifdef CONFIG_DEBUG_CGROUP_REF
void css_get(struct cgroup_subsys_state *css);
void css_get_many(struct cgroup_subsys_state *css, unsigned int n);
bool css_tryget(struct cgroup_subsys_state *css);
bool css_tryget_online(struct cgroup_subsys_state *css);
void css_put(struct cgroup_subsys_state *css);
void css_put_many(struct cgroup_subsys_state *css, unsigned int n);
#else
#define CGROUP_REF_FN_ATTRS static inline
#define CGROUP_REF_EXPORT(fn)
#include <linux/cgroup_refcnt.h>
#endif
static inline u64 cgroup_id(const struct cgroup *cgrp)
{
return cgrp->kn->id;
}
/**
* css_is_dying - test whether the specified css is dying
* @css: target css
*
* Test whether @css is in the process of offlining or already offline. In
* most cases, ->css_online() and ->css_offline() callbacks should be
* enough; however, the actual offline operations are RCU delayed and this
* test returns %true also when @css is scheduled to be offlined.
*
* This is useful, for example, when the use case requires synchronous
* behavior with respect to cgroup removal. cgroup removal schedules css
* offlining but the css can seem alive while the operation is being
* delayed. If the delay affects user visible semantics, this test can be
* used to resolve the situation.
*/
static inline bool css_is_dying(struct cgroup_subsys_state *css)
{
return css->flags & CSS_DYING;
}
static inline void cgroup_get(struct cgroup *cgrp)
{
css_get(&cgrp->self);
}
static inline bool cgroup_tryget(struct cgroup *cgrp)
{
return css_tryget(&cgrp->self);
}
static inline void cgroup_put(struct cgroup *cgrp)
{
css_put(&cgrp->self);
}
extern struct mutex cgroup_mutex;
static inline void cgroup_lock(void)
{
mutex_lock(&cgroup_mutex);
}
static inline void cgroup_unlock(void)
{
mutex_unlock(&cgroup_mutex);
}
/**
* task_css_set_check - obtain a task's css_set with extra access conditions
* @task: the task to obtain css_set for
* @__c: extra condition expression to be passed to rcu_dereference_check()
*
* A task's css_set is RCU protected, initialized and exited while holding
* task_lock(), and can only be modified while holding both cgroup_mutex
* and task_lock() while the task is alive. This macro verifies that the
* caller is inside proper critical section and returns @task's css_set.
*
* The caller can also specify additional allowed conditions via @__c, such
* as locks used during the cgroup_subsys::attach() methods.
*/
#ifdef CONFIG_PROVE_RCU
#define task_css_set_check(task, __c) \
rcu_dereference_check((task)->cgroups, \
rcu_read_lock_sched_held() || \
lockdep_is_held(&cgroup_mutex) || \
lockdep_is_held(&css_set_lock) || \
((task)->flags & PF_EXITING) || (__c))
#else
#define task_css_set_check(task, __c) \
rcu_dereference((task)->cgroups)
#endif
/**
* task_css_check - obtain css for (task, subsys) w/ extra access conds
* @task: the target task
* @subsys_id: the target subsystem ID
* @__c: extra condition expression to be passed to rcu_dereference_check()
*
* Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The
* synchronization rules are the same as task_css_set_check().
*/
#define task_css_check(task, subsys_id, __c) \
task_css_set_check((task), (__c))->subsys[(subsys_id)]
/**
* task_css_set - obtain a task's css_set
* @task: the task to obtain css_set for
*
* See task_css_set_check().
*/
static inline struct css_set *task_css_set(struct task_struct *task)
{
return task_css_set_check(task, false);
}
/**
* task_css - obtain css for (task, subsys)
* @task: the target task
* @subsys_id: the target subsystem ID
*
* See task_css_check().
*/
static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
int subsys_id)
{
return task_css_check(task, subsys_id, false);
}
/**
* task_get_css - find and get the css for (task, subsys)
* @task: the target task
* @subsys_id: the target subsystem ID
*
* Find the css for the (@task, @subsys_id) combination, increment a
* reference on and return it. This function is guaranteed to return a
* valid css. The returned css may already have been offlined.
*/
static inline struct cgroup_subsys_state *
task_get_css(struct task_struct *task, int subsys_id)
{
struct cgroup_subsys_state *css;
rcu_read_lock();
while (true) {
css = task_css(task, subsys_id);
/*
* Can't use css_tryget_online() here. A task which has
* PF_EXITING set may stay associated with an offline css.
* If such task calls this function, css_tryget_online()
* will keep failing.
*/
if (likely(css_tryget(css)))
break;
cpu_relax();
}
rcu_read_unlock();
return css;
}
/**
* task_css_is_root - test whether a task belongs to the root css
* @task: the target task
* @subsys_id: the target subsystem ID
*
* Test whether @task belongs to the root css on the specified subsystem.
* May be invoked in any context.
*/
static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
{
return task_css_check(task, subsys_id, true) ==
init_css_set.subsys[subsys_id];
}
static inline struct cgroup *task_cgroup(struct task_struct *task,
int subsys_id)
{
return task_css(task, subsys_id)->cgroup;
}
static inline struct cgroup *task_dfl_cgroup(struct task_struct *task)
{
return task_css_set(task)->dfl_cgrp;
}
static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
struct cgroup_subsys_state *parent_css = cgrp->self.parent;
if (parent_css)
return container_of(parent_css, struct cgroup, self);
return NULL;
}
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
* @ancestor: possible ancestor of @cgrp
*
* Test whether @cgrp is a descendant of @ancestor. It also returns %true
* if @cgrp == @ancestor. This function is safe to call as long as @cgrp
* and @ancestor are accessible.
*/
static inline bool cgroup_is_descendant(struct cgroup *cgrp,
struct cgroup *ancestor)
{
if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
return false;
return cgrp->ancestors[ancestor->level] == ancestor;
}
/**
* cgroup_ancestor - find ancestor of cgroup
* @cgrp: cgroup to find ancestor of
* @ancestor_level: level of ancestor to find starting from root
*
* Find ancestor of cgroup at specified level starting from root if it exists
* and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
* @ancestor_level.
*
* This function is safe to call as long as @cgrp is accessible.
*/
static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
int ancestor_level)
{
if (ancestor_level < 0 || ancestor_level > cgrp->level)
return NULL;
return cgrp->ancestors[ancestor_level];
}
/**
* task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
* @task: the task to be tested
* @ancestor: possible ancestor of @task's cgroup
*
* Tests whether @task's default cgroup hierarchy is a descendant of @ancestor.
* It follows all the same rules as cgroup_is_descendant, and only applies
* to the default hierarchy.
*/
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
{
struct css_set *cset = task_css_set(task);
return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
}
/* no synchronization, the result can only be used as a hint */
static inline bool cgroup_is_populated(struct cgroup *cgrp)
{
return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
cgrp->nr_populated_threaded_children;
}
/* returns ino associated with a cgroup */
static inline ino_t cgroup_ino(struct cgroup *cgrp)
{
return kernfs_ino(cgrp->kn);
}
/* cft/css accessors for cftype->write() operation */
static inline struct cftype *of_cft(struct kernfs_open_file *of)
{
return of->kn->priv;
}
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
/* cft/css accessors for cftype->seq_*() operations */
static inline struct cftype *seq_cft(struct seq_file *seq)
{
return of_cft(seq->private);
}
static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
{
return of_css(seq->private);
}
/*
* Name / path handling functions. All are thin wrappers around the kernfs
* counterparts and can be called under any context.
*/
static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_name(cgrp->kn, buf, buflen);
}
static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_path(cgrp->kn, buf, buflen);
}
static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
{
pr_cont_kernfs_name(cgrp->kn);
}
static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
{
pr_cont_kernfs_path(cgrp->kn);
}
bool cgroup_psi_enabled(void);
static inline void cgroup_init_kthreadd(void)
{
/*
* kthreadd is inherited by all kthreads, keep it in the root so
* that the new kthreads are guaranteed to stay in the root until
* initialization is finished.
*/
current->no_cgroup_migration = 1;
}
static inline void cgroup_kthread_ready(void)
{
/*
* This kthread finished initialization. The creator should have
* set PF_NO_SETAFFINITY if this kthread should stay in the root.
*/
current->no_cgroup_migration = 0;
}
void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen);
struct cgroup *cgroup_get_from_id(u64 id);
#else /* !CONFIG_CGROUPS */
struct cgroup_subsys_state;
struct cgroup;
static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; }
static inline void css_get(struct cgroup_subsys_state *css) {}
static inline void css_put(struct cgroup_subsys_state *css) {}
static inline void cgroup_lock(void) {}
static inline void cgroup_unlock(void) {}
static inline int cgroup_attach_task_all(struct task_struct *from,
struct task_struct *t) { return 0; }
static inline int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry) { return -EINVAL; }
static inline void cgroup_fork(struct task_struct *p) {}
static inline int cgroup_can_fork(struct task_struct *p,
struct kernel_clone_args *kargs) { return 0; }
static inline void cgroup_cancel_fork(struct task_struct *p,
struct kernel_clone_args *kargs) {}
static inline void cgroup_post_fork(struct task_struct *p,
struct kernel_clone_args *kargs) {}
static inline void cgroup_exit(struct task_struct *p) {}
static inline void cgroup_release(struct task_struct *p) {}
static inline void cgroup_free(struct task_struct *p) {}
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
static inline void cgroup_init_kthreadd(void) {}
static inline void cgroup_kthread_ready(void) {}
static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
return NULL;
}
static inline bool cgroup_psi_enabled(void)
{
return false;
}
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
{
return true;
}
static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
{}
#endif /* !CONFIG_CGROUPS */
#ifdef CONFIG_CGROUPS
/*
* cgroup scalable recursive statistics.
*/
void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
void cgroup_rstat_flush(struct cgroup *cgrp);
/*
* Basic resource stats.
*/
#ifdef CONFIG_CGROUP_CPUACCT
void cpuacct_charge(struct task_struct *tsk, u64 cputime);
void cpuacct_account_field(struct task_struct *tsk, int index, u64 val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
static inline void cpuacct_account_field(struct task_struct *tsk, int index,
u64 val) {}
#endif
void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec);
void __cgroup_account_cputime_field(struct cgroup *cgrp,
enum cpu_usage_stat index, u64 delta_exec);
static inline void cgroup_account_cputime(struct task_struct *task,
u64 delta_exec)
{
struct cgroup *cgrp;
cpuacct_charge(task, delta_exec);
cgrp = task_dfl_cgroup(task);
if (cgroup_parent(cgrp))
__cgroup_account_cputime(cgrp, delta_exec);
}
static inline void cgroup_account_cputime_field(struct task_struct *task,
enum cpu_usage_stat index,
u64 delta_exec)
{
struct cgroup *cgrp;
cpuacct_account_field(task, index, delta_exec);
cgrp = task_dfl_cgroup(task);
if (cgroup_parent(cgrp))
__cgroup_account_cputime_field(cgrp, index, delta_exec);
}
#else /* CONFIG_CGROUPS */
static inline void cgroup_account_cputime(struct task_struct *task,
u64 delta_exec) {}
static inline void cgroup_account_cputime_field(struct task_struct *task,
enum cpu_usage_stat index,
u64 delta_exec) {}
#endif /* CONFIG_CGROUPS */
/*
* sock->sk_cgrp_data handling. For more info, see sock_cgroup_data
* definition in cgroup-defs.h.
*/
#ifdef CONFIG_SOCK_CGROUP_DATA
void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
void cgroup_sk_clone(struct sock_cgroup_data *skcd);
void cgroup_sk_free(struct sock_cgroup_data *skcd);
static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
{
return skcd->cgroup;
}
#else /* CONFIG_CGROUP_DATA */
static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
#endif /* CONFIG_CGROUP_DATA */
struct cgroup_namespace {
struct ns_common ns;
struct user_namespace *user_ns;
struct ucounts *ucounts;
struct css_set *root_cset;
};
extern struct cgroup_namespace init_cgroup_ns;
#ifdef CONFIG_CGROUPS
void free_cgroup_ns(struct cgroup_namespace *ns);
struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
struct user_namespace *user_ns,
struct cgroup_namespace *old_ns);
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
struct cgroup_namespace *ns);
#else /* !CONFIG_CGROUPS */
static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
static inline struct cgroup_namespace *
copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
struct cgroup_namespace *old_ns)
{
return old_ns;
}
#endif /* !CONFIG_CGROUPS */
static inline void get_cgroup_ns(struct cgroup_namespace *ns)
{
if (ns)
refcount_inc(&ns->ns.count);
}
static inline void put_cgroup_ns(struct cgroup_namespace *ns)
{
if (ns && refcount_dec_and_test(&ns->ns.count))
free_cgroup_ns(ns);
}
#ifdef CONFIG_CGROUPS
void cgroup_enter_frozen(void);
void cgroup_leave_frozen(bool always_leave);
void cgroup_update_frozen(struct cgroup *cgrp);
void cgroup_freeze(struct cgroup *cgrp, bool freeze);
void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src,
struct cgroup *dst);
static inline bool cgroup_task_frozen(struct task_struct *task)
{
return task->frozen;
}
#else /* !CONFIG_CGROUPS */
static inline void cgroup_enter_frozen(void) { }
static inline void cgroup_leave_frozen(bool always_leave) { }
static inline bool cgroup_task_frozen(struct task_struct *task)
{
return false;
}
#endif /* !CONFIG_CGROUPS */
#ifdef CONFIG_CGROUP_BPF
static inline void cgroup_bpf_get(struct cgroup *cgrp)
{
percpu_ref_get(&cgrp->bpf.refcnt);
}
static inline void cgroup_bpf_put(struct cgroup *cgrp)
{
percpu_ref_put(&cgrp->bpf.refcnt);
}
#else /* CONFIG_CGROUP_BPF */
static inline void cgroup_bpf_get(struct cgroup *cgrp) {}
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
#endif /* CONFIG_CGROUP_BPF */
struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id);
struct cgroup_of_peak *of_peak(struct kernfs_open_file *of);
#endif /* _LINUX_CGROUP_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* mm/percpu.c - percpu memory allocator
*
* Copyright (C) 2009 SUSE Linux Products GmbH
* Copyright (C) 2009 Tejun Heo <tj@kernel.org>
*
* Copyright (C) 2017 Facebook Inc.
* Copyright (C) 2017 Dennis Zhou <dennis@kernel.org>
*
* The percpu allocator handles both static and dynamic areas. Percpu
* areas are allocated in chunks which are divided into units. There is
* a 1-to-1 mapping for units to possible cpus. These units are grouped
* based on NUMA properties of the machine.
*
* c0 c1 c2
* ------------------- ------------------- ------------
* | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u
* ------------------- ...... ------------------- .... ------------
*
* Allocation is done by offsets into a unit's address space. Ie., an
* area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0,
* c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear
* and even sparse. Access is handled by configuring percpu base
* registers according to the cpu to unit mappings and offsetting the
* base address using pcpu_unit_size.
*
* There is special consideration for the first chunk which must handle
* the static percpu variables in the kernel image as allocation services
* are not online yet. In short, the first chunk is structured like so:
*
* <Static | [Reserved] | Dynamic>
*
* The static data is copied from the original section managed by the
* linker. The reserved section, if non-zero, primarily manages static
* percpu variables from kernel modules. Finally, the dynamic section
* takes care of normal allocations.
*
* The allocator organizes chunks into lists according to free size and
* memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT
* flag should be passed. All memcg-aware allocations are sharing one set
* of chunks and all unaccounted allocations and allocations performed
* by processes belonging to the root memory cgroup are using the second set.
*
* The allocator tries to allocate from the fullest chunk first. Each chunk
* is managed by a bitmap with metadata blocks. The allocation map is updated
* on every allocation and free to reflect the current state while the boundary
* map is only updated on allocation. Each metadata block contains
* information to help mitigate the need to iterate over large portions
* of the bitmap. The reverse mapping from page to chunk is stored in
* the page's index. Lastly, units are lazily backed and grow in unison.
*
* There is a unique conversion that goes on here between bytes and bits.
* Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk
* tracks the number of pages it is responsible for in nr_pages. Helper
* functions are used to convert from between the bytes, bits, and blocks.
* All hints are managed in bits unless explicitly stated.
*
* To use this allocator, arch code should do the following:
*
* - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
* regular address to percpu pointer and back if they need to be
* different from the default
*
* - use pcpu_setup_first_chunk() during percpu area initialization to
* setup the first chunk containing the kernel static percpu area
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/bitmap.h>
#include <linux/cpumask.h>
#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/list.h>
#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/pfn.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <linux/kmemleak.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/memcontrol.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#define CREATE_TRACE_POINTS
#include <trace/events/percpu.h>
#include "percpu-internal.h"
/*
* The slots are sorted by the size of the biggest continuous free area.
* 1-31 bytes share the same slot.
*/
#define PCPU_SLOT_BASE_SHIFT 5
/* chunks in slots below this are subject to being sidelined on failed alloc */
#define PCPU_SLOT_FAIL_THRESHOLD 3
#define PCPU_EMPTY_POP_PAGES_LOW 2
#define PCPU_EMPTY_POP_PAGES_HIGH 4
#ifdef CONFIG_SMP
/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
#ifndef __addr_to_pcpu_ptr
#define __addr_to_pcpu_ptr(addr) \
(void __percpu *)((unsigned long)(addr) - \
(unsigned long)pcpu_base_addr + \
(unsigned long)__per_cpu_start)
#endif
#ifndef __pcpu_ptr_to_addr
#define __pcpu_ptr_to_addr(ptr) \
(void __force *)((unsigned long)(ptr) + \
(unsigned long)pcpu_base_addr - \
(unsigned long)__per_cpu_start)
#endif
#else /* CONFIG_SMP */
/* on UP, it's always identity mapped */
#define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr)
#define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr)
#endif /* CONFIG_SMP */
static int pcpu_unit_pages __ro_after_init;
static int pcpu_unit_size __ro_after_init;
static int pcpu_nr_units __ro_after_init;
static int pcpu_atom_size __ro_after_init;
int pcpu_nr_slots __ro_after_init;
static int pcpu_free_slot __ro_after_init;
int pcpu_sidelined_slot __ro_after_init;
int pcpu_to_depopulate_slot __ro_after_init;
static size_t pcpu_chunk_struct_size __ro_after_init;
/* cpus with the lowest and highest unit addresses */
static unsigned int pcpu_low_unit_cpu __ro_after_init;
static unsigned int pcpu_high_unit_cpu __ro_after_init;
/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __ro_after_init;
static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */
const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */
/* group information, used for vm allocation */
static int pcpu_nr_groups __ro_after_init;
static const unsigned long *pcpu_group_offsets __ro_after_init;
static const size_t *pcpu_group_sizes __ro_after_init;
/*
* The first chunk which always exists. Note that unlike other
* chunks, this one can be allocated and mapped in several different
* ways and thus often doesn't live in the vmalloc area.
*/
struct pcpu_chunk *pcpu_first_chunk __ro_after_init;
/*
* Optional reserved chunk. This chunk reserves part of the first
* chunk and serves it for reserved allocations. When the reserved
* region doesn't exist, the following variable is NULL.
*/
struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init;
DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */
static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */
struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
/*
* The number of empty populated pages, protected by pcpu_lock.
* The reserved chunk doesn't contribute to the count.
*/
int pcpu_nr_empty_pop_pages;
/*
* The number of populated pages in use by the allocator, protected by
* pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets
* allocated/deallocated, it is allocated/deallocated in all units of a chunk
* and increments/decrements this count by 1).
*/
static unsigned long pcpu_nr_populated;
/*
* Balance work is used to populate or destroy chunks asynchronously. We
* try to keep the number of populated free pages between
* PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
* empty chunk.
*/
static void pcpu_balance_workfn(struct work_struct *work);
static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn);
static bool pcpu_async_enabled __read_mostly;
static bool pcpu_atomic_alloc_failed;
static void pcpu_schedule_balance_work(void)
{
if (pcpu_async_enabled) schedule_work(&pcpu_balance_work);
}
/**
* pcpu_addr_in_chunk - check if the address is served from this chunk
* @chunk: chunk of interest
* @addr: percpu address
*
* RETURNS:
* True if the address is served from this chunk.
*/
static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr)
{
void *start_addr, *end_addr;
if (!chunk)
return false;
start_addr = chunk->base_addr + chunk->start_offset;
end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE -
chunk->end_offset;
return addr >= start_addr && addr < end_addr;
}
static int __pcpu_size_to_slot(int size)
{
int highbit = fls(size); /* size is in bytes */
return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
}
static int pcpu_size_to_slot(int size)
{
if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size);
}
static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
{
const struct pcpu_block_md *chunk_md = &chunk->chunk_md;
if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE ||
chunk_md->contig_hint == 0)
return 0;
return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE);
}
/* set the pointer to a chunk in a page struct */
static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
{
page->private = (unsigned long)pcpu;
}
/* obtain pointer to a chunk from a page struct */
static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
{
return (struct pcpu_chunk *)page->private;
}
static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx)
{
return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
}
static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx)
{
return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT);
}
static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
unsigned int cpu, int page_idx)
{
return (unsigned long)chunk->base_addr +
pcpu_unit_page_offset(cpu, page_idx);
}
/*
* The following are helper functions to help access bitmaps and convert
* between bitmap offsets to address offsets.
*/
static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index)
{
return chunk->alloc_map +
(index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG);
}
static unsigned long pcpu_off_to_block_index(int off)
{
return off / PCPU_BITMAP_BLOCK_BITS;
}
static unsigned long pcpu_off_to_block_off(int off)
{
return off & (PCPU_BITMAP_BLOCK_BITS - 1);
}
static unsigned long pcpu_block_off_to_off(int index, int off)
{
return index * PCPU_BITMAP_BLOCK_BITS + off;
}
/**
* pcpu_check_block_hint - check against the contig hint
* @block: block of interest
* @bits: size of allocation
* @align: alignment of area (max PAGE_SIZE)
*
* Check to see if the allocation can fit in the block's contig hint.
* Note, a chunk uses the same hints as a block so this can also check against
* the chunk's contig hint.
*/
static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits,
size_t align)
{
int bit_off = ALIGN(block->contig_hint_start, align) -
block->contig_hint_start;
return bit_off + bits <= block->contig_hint;
}
/*
* pcpu_next_hint - determine which hint to use
* @block: block of interest
* @alloc_bits: size of allocation
*
* This determines if we should scan based on the scan_hint or first_free.
* In general, we want to scan from first_free to fulfill allocations by
* first fit. However, if we know a scan_hint at position scan_hint_start
* cannot fulfill an allocation, we can begin scanning from there knowing
* the contig_hint will be our fallback.
*/
static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits)
{
/*
* The three conditions below determine if we can skip past the
* scan_hint. First, does the scan hint exist. Second, is the
* contig_hint after the scan_hint (possibly not true iff
* contig_hint == scan_hint). Third, is the allocation request
* larger than the scan_hint.
*/
if (block->scan_hint && block->contig_hint_start > block->scan_hint_start &&
alloc_bits > block->scan_hint)
return block->scan_hint_start + block->scan_hint;
return block->first_free;
}
/**
* pcpu_next_md_free_region - finds the next hint free area
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of free area
*
* Helper function for pcpu_for_each_md_free_region. It checks
* block->contig_hint and performs aggregation across blocks to find the
* next hint. It modifies bit_off and bits in-place to be consumed in the
* loop.
*/
static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
int *bits)
{
int i = pcpu_off_to_block_index(*bit_off);
int block_off = pcpu_off_to_block_off(*bit_off);
struct pcpu_block_md *block;
*bits = 0;
for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
block++, i++) {
/* handles contig area across blocks */
if (*bits) {
*bits += block->left_free;
if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
continue;
return;
}
/*
* This checks three things. First is there a contig_hint to
* check. Second, have we checked this hint before by
* comparing the block_off. Third, is this the same as the
* right contig hint. In the last case, it spills over into
* the next block and should be handled by the contig area
* across blocks code.
*/
*bits = block->contig_hint;
if (*bits && block->contig_hint_start >= block_off &&
*bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) {
*bit_off = pcpu_block_off_to_off(i,
block->contig_hint_start);
return;
}
/* reset to satisfy the second predicate above */
block_off = 0;
*bits = block->right_free;
*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
}
}
/**
* pcpu_next_fit_region - finds fit areas for a given allocation request
* @chunk: chunk of interest
* @alloc_bits: size of allocation
* @align: alignment of area (max PAGE_SIZE)
* @bit_off: chunk offset
* @bits: size of free area
*
* Finds the next free region that is viable for use with a given size and
* alignment. This only returns if there is a valid area to be used for this
* allocation. block->first_free is returned if the allocation request fits
* within the block to see if the request can be fulfilled prior to the contig
* hint.
*/
static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
int align, int *bit_off, int *bits)
{
int i = pcpu_off_to_block_index(*bit_off);
int block_off = pcpu_off_to_block_off(*bit_off);
struct pcpu_block_md *block;
*bits = 0;
for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
block++, i++) {
/* handles contig area across blocks */
if (*bits) {
*bits += block->left_free;
if (*bits >= alloc_bits)
return;
if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
continue;
}
/* check block->contig_hint */
*bits = ALIGN(block->contig_hint_start, align) -
block->contig_hint_start;
/*
* This uses the block offset to determine if this has been
* checked in the prior iteration.
*/
if (block->contig_hint && block->contig_hint_start >= block_off &&
block->contig_hint >= *bits + alloc_bits) {
int start = pcpu_next_hint(block, alloc_bits);
*bits += alloc_bits + block->contig_hint_start -
start;
*bit_off = pcpu_block_off_to_off(i, start);
return;
}
/* reset to satisfy the second predicate above */
block_off = 0;
*bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free,
align);
*bits = PCPU_BITMAP_BLOCK_BITS - *bit_off;
*bit_off = pcpu_block_off_to_off(i, *bit_off);
if (*bits >= alloc_bits)
return;
}
/* no valid offsets were found - fail condition */
*bit_off = pcpu_chunk_map_bits(chunk);
}
/*
* Metadata free area iterators. These perform aggregation of free areas
* based on the metadata blocks and return the offset @bit_off and size in
* bits of the free area @bits. pcpu_for_each_fit_region only returns when
* a fit is found for the allocation request.
*/
#define pcpu_for_each_md_free_region(chunk, bit_off, bits) \
for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \
(bit_off) < pcpu_chunk_map_bits((chunk)); \
(bit_off) += (bits) + 1, \
pcpu_next_md_free_region((chunk), &(bit_off), &(bits)))
#define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \
for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \
&(bits)); \
(bit_off) < pcpu_chunk_map_bits((chunk)); \
(bit_off) += (bits), \
pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \
&(bits)))
/**
* pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
* @gfp: allocation flags
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
* kzalloc() is used; otherwise, the equivalent of vzalloc() is used.
* This is to facilitate passing through whitelisted flags. The
* returned memory is always zeroed.
*
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
{
if (WARN_ON_ONCE(!slab_is_available()))
return NULL;
if (size <= PAGE_SIZE)
return kzalloc(size, gfp);
else
return __vmalloc(size, gfp | __GFP_ZERO);
}
/**
* pcpu_mem_free - free memory
* @ptr: memory to free
*
* Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc().
*/
static void pcpu_mem_free(void *ptr)
{
kvfree(ptr);
}
static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot,
bool move_front)
{
if (chunk != pcpu_reserved_chunk) {
if (move_front)
list_move(&chunk->list, &pcpu_chunk_lists[slot]);
else
list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]);
}
}
static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot)
{
__pcpu_chunk_move(chunk, slot, true);
}
/**
* pcpu_chunk_relocate - put chunk in the appropriate chunk slot
* @chunk: chunk of interest
* @oslot: the previous slot it was on
*
* This function is called after an allocation or free changed @chunk.
* New slot according to the changed state is determined and @chunk is
* moved to the slot. Note that the reserved chunk is never put on
* chunk slots.
*
* CONTEXT:
* pcpu_lock.
*/
static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
{ int nslot = pcpu_chunk_slot(chunk);
/* leave isolated chunks in-place */
if (chunk->isolated)
return;
if (oslot != nslot)
__pcpu_chunk_move(chunk, nslot, oslot < nslot);
}
static void pcpu_isolate_chunk(struct pcpu_chunk *chunk)
{
lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true;
pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages;
}
list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]);
}
static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk)
{
lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false;
pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(chunk, -1);
}
}
/*
* pcpu_update_empty_pages - update empty page counters
* @chunk: chunk of interest
* @nr: nr of empty pages
*
* This is used to keep track of the empty pages now based on the premise
* a md_block covers a page. The hint update functions recognize if a block
* is made full or broken to calculate deltas for keeping track of free pages.
*/
static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
{
chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr;
}
/*
* pcpu_region_overlap - determines if two regions overlap
* @a: start of first region, inclusive
* @b: end of first region, exclusive
* @x: start of second region, inclusive
* @y: end of second region, exclusive
*
* This is used to determine if the hint region [a, b) overlaps with the
* allocated region [x, y).
*/
static inline bool pcpu_region_overlap(int a, int b, int x, int y)
{
return (a < y) && (x < b);
}
/**
* pcpu_block_update - updates a block given a free area
* @block: block of interest
* @start: start offset in block
* @end: end offset in block
*
* Updates a block given a known free area. The region [start, end) is
* expected to be the entirety of the free area within a block. Chooses
* the best starting offset if the contig hints are equal.
*/
static void pcpu_block_update(struct pcpu_block_md *block, int start, int end)
{
int contig = end - start;
block->first_free = min(block->first_free, start);
if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig;
if (contig > block->contig_hint) {
/* promote the old contig_hint to be the new scan_hint */
if (start > block->contig_hint_start) {
if (block->contig_hint > block->scan_hint) {
block->scan_hint_start =
block->contig_hint_start;
block->scan_hint = block->contig_hint;
} else if (start < block->scan_hint_start) {
/*
* The old contig_hint == scan_hint. But, the
* new contig is larger so hold the invariant
* scan_hint_start < contig_hint_start.
*/
block->scan_hint = 0;
}
} else {
block->scan_hint = 0;
}
block->contig_hint_start = start;
block->contig_hint = contig;
} else if (contig == block->contig_hint) {
if (block->contig_hint_start && (!start ||
__ffs(start) > __ffs(block->contig_hint_start))) {
/* start has a better alignment so use it */
block->contig_hint_start = start;
if (start < block->scan_hint_start &&
block->contig_hint > block->scan_hint)
block->scan_hint = 0; } else if (start > block->scan_hint_start ||
block->contig_hint > block->scan_hint) {
/*
* Knowing contig == contig_hint, update the scan_hint
* if it is farther than or larger than the current
* scan_hint.
*/
block->scan_hint_start = start;
block->scan_hint = contig;
}
} else {
/*
* The region is smaller than the contig_hint. So only update
* the scan_hint if it is larger than or equal and farther than
* the current scan_hint.
*/
if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint &&
start > block->scan_hint_start)))) {
block->scan_hint_start = start;
block->scan_hint = contig;
}
}
}
/*
* pcpu_block_update_scan - update a block given a free area from a scan
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of free area
*
* Finding the final allocation spot first goes through pcpu_find_block_fit()
* to find a block that can hold the allocation and then pcpu_alloc_area()
* where a scan is used. When allocations require specific alignments,
* we can inadvertently create holes which will not be seen in the alloc
* or free paths.
*
* This takes a given free area hole and updates a block as it may change the
* scan_hint. We need to scan backwards to ensure we don't miss free bits
* from alignment.
*/
static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
int s_off = pcpu_off_to_block_off(bit_off);
int e_off = s_off + bits;
int s_index, l_bit;
struct pcpu_block_md *block;
if (e_off > PCPU_BITMAP_BLOCK_BITS)
return;
s_index = pcpu_off_to_block_index(bit_off);
block = chunk->md_blocks + s_index;
/* scan backwards in case of alignment skipping free bits */
l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off);
s_off = (s_off == l_bit) ? 0 : l_bit + 1;
pcpu_block_update(block, s_off, e_off);
}
/**
* pcpu_chunk_refresh_hint - updates metadata about a chunk
* @chunk: chunk of interest
* @full_scan: if we should scan from the beginning
*
* Iterates over the metadata blocks to find the largest contig area.
* A full scan can be avoided on the allocation path as this is triggered
* if we broke the contig_hint. In doing so, the scan_hint will be before
* the contig_hint or after if the scan_hint == contig_hint. This cannot
* be prevented on freeing as we want to find the largest area possibly
* spanning blocks.
*/
static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan)
{
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
int bit_off, bits;
/* promote scan_hint to contig_hint */
if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint;
chunk_md->contig_hint_start = chunk_md->scan_hint_start;
chunk_md->contig_hint = chunk_md->scan_hint;
chunk_md->scan_hint = 0;
} else {
bit_off = chunk_md->first_free;
chunk_md->contig_hint = 0;
}
bits = 0;
pcpu_for_each_md_free_region(chunk, bit_off, bits)
pcpu_block_update(chunk_md, bit_off, bit_off + bits);
}
/**
* pcpu_block_refresh_hint
* @chunk: chunk of interest
* @index: index of the metadata block
*
* Scans over the block beginning at first_free and updates the block
* metadata accordingly.
*/
static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index)
{
struct pcpu_block_md *block = chunk->md_blocks + index;
unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index);
unsigned int start, end; /* region start, region end */
/* promote scan_hint to contig_hint */
if (block->scan_hint) {
start = block->scan_hint_start + block->scan_hint;
block->contig_hint_start = block->scan_hint_start;
block->contig_hint = block->scan_hint;
block->scan_hint = 0;
} else {
start = block->first_free;
block->contig_hint = 0;
}
block->right_free = 0;
/* iterate over free areas and update the contig hints */
for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS)
pcpu_block_update(block, start, end);
}
/**
* pcpu_block_update_hint_alloc - update hint on allocation path
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of request
*
* Updates metadata for the allocation path. The metadata only has to be
* refreshed by a full scan iff the chunk's contig hint is broken. Block level
* scans are required if the block's contig hint is broken.
*/
static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */
/*
* Calculate per block offsets.
* The calculation uses an inclusive range, but the resulting offsets
* are [start, end). e_index always points to the last block in the
* range.
*/
s_index = pcpu_off_to_block_index(bit_off);
e_index = pcpu_off_to_block_index(bit_off + bits - 1);
s_off = pcpu_off_to_block_off(bit_off);
e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1;
s_block = chunk->md_blocks + s_index;
e_block = chunk->md_blocks + e_index;
/*
* Update s_block.
*/
if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
/*
* block->first_free must be updated if the allocation takes its place.
* If the allocation breaks the contig_hint, a scan is required to
* restore this hint.
*/
if (s_off == s_block->first_free)
s_block->first_free = find_next_zero_bit(
pcpu_index_alloc_map(chunk, s_index),
PCPU_BITMAP_BLOCK_BITS,
s_off + bits);
if (pcpu_region_overlap(s_block->scan_hint_start,
s_block->scan_hint_start + s_block->scan_hint,
s_off,
s_off + bits)) s_block->scan_hint = 0;
if (pcpu_region_overlap(s_block->contig_hint_start,
s_block->contig_hint_start +
s_block->contig_hint,
s_off,
s_off + bits)) {
/* block contig hint is broken - scan to fix it */
if (!s_off) s_block->left_free = 0;
pcpu_block_refresh_hint(chunk, s_index);
} else {
/* update left and right contig manually */
s_block->left_free = min(s_block->left_free, s_off);
if (s_index == e_index)
s_block->right_free = min_t(int, s_block->right_free,
PCPU_BITMAP_BLOCK_BITS - e_off);
else
s_block->right_free = 0;
}
/*
* Update e_block.
*/
if (s_index != e_index) {
if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
/*
* When the allocation is across blocks, the end is along
* the left part of the e_block.
*/
e_block->first_free = find_next_zero_bit(
pcpu_index_alloc_map(chunk, e_index),
PCPU_BITMAP_BLOCK_BITS, e_off);
if (e_off == PCPU_BITMAP_BLOCK_BITS) {
/* reset the block */
e_block++;
} else {
if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0;
e_block->left_free = 0;
if (e_off > e_block->contig_hint_start) {
/* contig hint is broken - scan to fix it */
pcpu_block_refresh_hint(chunk, e_index);
} else {
e_block->right_free =
min_t(int, e_block->right_free,
PCPU_BITMAP_BLOCK_BITS - e_off);
}
}
/* update in-between md_blocks */
nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) {
block->scan_hint = 0;
block->contig_hint = 0;
block->left_free = 0;
block->right_free = 0;
}
}
/*
* If the allocation is not atomic, some blocks may not be
* populated with pages, while we account it here. The number
* of pages will be added back with pcpu_chunk_populated()
* when populating pages.
*/
if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start,
chunk_md->scan_hint_start +
chunk_md->scan_hint,
bit_off,
bit_off + bits))
chunk_md->scan_hint = 0;
/*
* The only time a full chunk scan is required is if the chunk
* contig hint is broken. Otherwise, it means a smaller space
* was used and therefore the chunk contig hint is still correct.
*/
if (pcpu_region_overlap(chunk_md->contig_hint_start,
chunk_md->contig_hint_start +
chunk_md->contig_hint,
bit_off,
bit_off + bits))
pcpu_chunk_refresh_hint(chunk, false);
}
/**
* pcpu_block_update_hint_free - updates the block hints on the free path
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of request
*
* Updates metadata for the allocation path. This avoids a blind block
* refresh by making use of the block contig hints. If this fails, it scans
* forward and backward to determine the extent of the free area. This is
* capped at the boundary of blocks.
*
* A chunk update is triggered if a page becomes free, a block becomes free,
* or the free spans across blocks. This tradeoff is to minimize iterating
* over the block metadata to update chunk_md->contig_hint.
* chunk_md->contig_hint may be off by up to a page, but it will never be more
* than the available space. If the contig hint is contained in one block, it
* will be accurate.
*/
static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
int bits)
{
int nr_empty_pages = 0;
struct pcpu_block_md *s_block, *e_block, *block;
int s_index, e_index; /* block indexes of the freed allocation */
int s_off, e_off; /* block offsets of the freed allocation */
int start, end; /* start and end of the whole free area */
/*
* Calculate per block offsets.
* The calculation uses an inclusive range, but the resulting offsets
* are [start, end). e_index always points to the last block in the
* range.
*/
s_index = pcpu_off_to_block_index(bit_off);
e_index = pcpu_off_to_block_index(bit_off + bits - 1);
s_off = pcpu_off_to_block_off(bit_off);
e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1;
s_block = chunk->md_blocks + s_index;
e_block = chunk->md_blocks + e_index;
/*
* Check if the freed area aligns with the block->contig_hint.
* If it does, then the scan to find the beginning/end of the
* larger free area can be avoided.
*
* start and end refer to beginning and end of the free area
* within each their respective blocks. This is not necessarily
* the entire free area as it may span blocks past the beginning
* or end of the block.
*/
start = s_off;
if (s_off == s_block->contig_hint + s_block->contig_hint_start) {
start = s_block->contig_hint_start;
} else {
/*
* Scan backwards to find the extent of the free area.
* find_last_bit returns the starting bit, so if the start bit
* is returned, that means there was no last bit and the
* remainder of the chunk is free.
*/
int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index),
start);
start = (start == l_bit) ? 0 : l_bit + 1;
}
end = e_off;
if (e_off == e_block->contig_hint_start)
end = e_block->contig_hint_start + e_block->contig_hint;
else
end = find_next_bit(pcpu_index_alloc_map(chunk, e_index),
PCPU_BITMAP_BLOCK_BITS, end);
/* update s_block */
e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS;
if (!start && e_off == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
pcpu_block_update(s_block, start, e_off);
/* freeing in the same block */
if (s_index != e_index) {
/* update e_block */
if (end == PCPU_BITMAP_BLOCK_BITS)
nr_empty_pages++;
pcpu_block_update(e_block, 0, end);
/* reset md_blocks in the middle */
nr_empty_pages += (e_index - s_index - 1);
for (block = s_block + 1; block < e_block; block++) {
block->first_free = 0;
block->scan_hint = 0;
block->contig_hint_start = 0;
block->contig_hint = PCPU_BITMAP_BLOCK_BITS;
block->left_free = PCPU_BITMAP_BLOCK_BITS;
block->right_free = PCPU_BITMAP_BLOCK_BITS;
}
}
if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages);
/*
* Refresh chunk metadata when the free makes a block free or spans
* across blocks. The contig_hint may be off by up to a page, but if
* the contig_hint is contained in a block, it will be accurate with
* the else condition below.
*/
if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index)
pcpu_chunk_refresh_hint(chunk, true);
else
pcpu_block_update(&chunk->chunk_md,
pcpu_block_off_to_off(s_index, start),
end);
}
/**
* pcpu_is_populated - determines if the region is populated
* @chunk: chunk of interest
* @bit_off: chunk offset
* @bits: size of area
* @next_off: return value for the next offset to start searching
*
* For atomic allocations, check if the backing pages are populated.
*
* RETURNS:
* Bool if the backing pages are populated.
* next_index is to skip over unpopulated blocks in pcpu_find_block_fit.
*/
static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits,
int *next_off)
{
unsigned int start, end;
start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE);
end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);
start = find_next_zero_bit(chunk->populated, end, start);
if (start >= end)
return true;
end = find_next_bit(chunk->populated, end, start + 1);
*next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
return false;
}
/**
* pcpu_find_block_fit - finds the block index to start searching
* @chunk: chunk of interest
* @alloc_bits: size of request in allocation units
* @align: alignment of area (max PAGE_SIZE bytes)
* @pop_only: use populated regions only
*
* Given a chunk and an allocation spec, find the offset to begin searching
* for a free region. This iterates over the bitmap metadata blocks to
* find an offset that will be guaranteed to fit the requirements. It is
* not quite first fit as if the allocation does not fit in the contig hint
* of a block or chunk, it is skipped. This errs on the side of caution
* to prevent excess iteration. Poor alignment can cause the allocator to
* skip over blocks and chunks that have valid free areas.
*
* RETURNS:
* The offset in the bitmap to begin searching.
* -1 if no offset is found.
*/
static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits,
size_t align, bool pop_only)
{
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
int bit_off, bits, next_off;
/*
* This is an optimization to prevent scanning by assuming if the
* allocation cannot fit in the global hint, there is memory pressure
* and creating a new chunk would happen soon.
*/
if (!pcpu_check_block_hint(chunk_md, alloc_bits, align))
return -1;
bit_off = pcpu_next_hint(chunk_md, alloc_bits);
bits = 0;
pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits,
&next_off))
break;
bit_off = next_off;
bits = 0;
}
if (bit_off == pcpu_chunk_map_bits(chunk))
return -1;
return bit_off;
}
/*
* pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off()
* @map: the address to base the search on
* @size: the bitmap size in bits
* @start: the bitnumber to start searching at
* @nr: the number of zeroed bits we're looking for
* @align_mask: alignment mask for zero area
* @largest_off: offset of the largest area skipped
* @largest_bits: size of the largest area skipped
*
* The @align_mask should be one less than a power of 2.
*
* This is a modified version of bitmap_find_next_zero_area_off() to remember
* the largest area that was skipped. This is imperfect, but in general is
* good enough. The largest remembered region is the largest failed region
* seen. This does not include anything we possibly skipped due to alignment.
* pcpu_block_update_scan() does scan backwards to try and recover what was
* lost to alignment. While this can cause scanning to miss earlier possible
* free areas, smaller allocations will eventually fill those holes.
*/
static unsigned long pcpu_find_zero_area(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned long nr,
unsigned long align_mask,
unsigned long *largest_off,
unsigned long *largest_bits)
{
unsigned long index, end, i, area_off, area_bits;
again:
index = find_next_zero_bit(map, size, start);
/* Align allocation */
index = __ALIGN_MASK(index, align_mask);
area_off = index;
end = index + nr;
if (end > size)
return end;
i = find_next_bit(map, end, index);
if (i < end) {
area_bits = i - area_off;
/* remember largest unused area with best alignment */
if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) {
*largest_off = area_off;
*largest_bits = area_bits;
}
start = i + 1;
goto again;
}
return index;
}
/**
* pcpu_alloc_area - allocates an area from a pcpu_chunk
* @chunk: chunk of interest
* @alloc_bits: size of request in allocation units
* @align: alignment of area (max PAGE_SIZE)
* @start: bit_off to start searching
*
* This function takes in a @start offset to begin searching to fit an
* allocation of @alloc_bits with alignment @align. It needs to scan
* the allocation map because if it fits within the block's contig hint,
* @start will be block->first_free. This is an attempt to fill the
* allocation prior to breaking the contig hint. The allocation and
* boundary maps are updated accordingly if it confirms a valid
* free area.
*
* RETURNS:
* Allocated addr offset in @chunk on success.
* -1 if no matching area is found.
*/
static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
size_t align, int start)
{
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
size_t align_mask = (align) ? (align - 1) : 0;
unsigned long area_off = 0, area_bits = 0;
int bit_off, end, oslot;
lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk);
/*
* Search to find a fit.
*/
end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS,
pcpu_chunk_map_bits(chunk));
bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits,
align_mask, &area_off, &area_bits);
if (bit_off >= end)
return -1;
if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits);
/* update alloc map */
bitmap_set(chunk->alloc_map, bit_off, alloc_bits);
/* update boundary map */
set_bit(bit_off, chunk->bound_map);
bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1);
set_bit(bit_off + alloc_bits, chunk->bound_map);
chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE;
/* update first free bit */
if (bit_off == chunk_md->first_free)
chunk_md->first_free = find_next_zero_bit(
chunk->alloc_map,
pcpu_chunk_map_bits(chunk),
bit_off + alloc_bits);
pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits);
pcpu_chunk_relocate(chunk, oslot);
return bit_off * PCPU_MIN_ALLOC_SIZE;
}
/**
* pcpu_free_area - frees the corresponding offset
* @chunk: chunk of interest
* @off: addr offset into chunk
*
* This function determines the size of an allocation to free using
* the boundary bitmap and clears the allocation map.
*
* RETURNS:
* Number of freed bytes.
*/
static int pcpu_free_area(struct pcpu_chunk *chunk, int off)
{
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
int bit_off, bits, end, oslot, freed;
lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk);
bit_off = off / PCPU_MIN_ALLOC_SIZE;
/* find end index */
end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk),
bit_off + 1);
bits = end - bit_off;
bitmap_clear(chunk->alloc_map, bit_off, bits);
freed = bits * PCPU_MIN_ALLOC_SIZE;
/* update metadata */
chunk->free_bytes += freed;
/* update first free bit */
chunk_md->first_free = min(chunk_md->first_free, bit_off);
pcpu_block_update_hint_free(chunk, bit_off, bits);
pcpu_chunk_relocate(chunk, oslot);
return freed;
}
static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits)
{
block->scan_hint = 0;
block->contig_hint = nr_bits;
block->left_free = nr_bits;
block->right_free = nr_bits;
block->first_free = 0;
block->nr_bits = nr_bits;
}
static void pcpu_init_md_blocks(struct pcpu_chunk *chunk)
{
struct pcpu_block_md *md_block;
/* init the chunk's block */
pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk));
for (md_block = chunk->md_blocks;
md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk);
md_block++)
pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS);
}
/**
* pcpu_alloc_first_chunk - creates chunks that serve the first chunk
* @tmp_addr: the start of the region served
* @map_size: size of the region served
*
* This is responsible for creating the chunks that serve the first chunk. The
* base_addr is page aligned down of @tmp_addr while the region end is page
* aligned up. Offsets are kept track of to determine the region served. All
* this is done to appease the bitmap allocator in avoiding partial blocks.
*
* RETURNS:
* Chunk serving the region at @tmp_addr of @map_size.
*/
static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
int map_size)
{
struct pcpu_chunk *chunk;
unsigned long aligned_addr;
int start_offset, offset_bits, region_size, region_bits;
size_t alloc_size;
/* region calculations */
aligned_addr = tmp_addr & PAGE_MASK;
start_offset = tmp_addr - aligned_addr;
region_size = ALIGN(start_offset + map_size, PAGE_SIZE);
/* allocate chunk */
alloc_size = struct_size(chunk, populated,
BITS_TO_LONGS(region_size >> PAGE_SHIFT));
chunk = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
INIT_LIST_HEAD(&chunk->list);
chunk->base_addr = (void *)aligned_addr;
chunk->start_offset = start_offset;
chunk->end_offset = region_size - chunk->start_offset - map_size;
chunk->nr_pages = region_size >> PAGE_SHIFT;
region_bits = pcpu_chunk_map_bits(chunk);
alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]);
chunk->alloc_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
alloc_size =
BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]);
chunk->bound_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]);
chunk->md_blocks = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
#ifdef NEED_PCPUOBJ_EXT
/* first chunk is free to use */
chunk->obj_exts = NULL;
#endif
pcpu_init_md_blocks(chunk);
/* manage populated page bitmap */
chunk->immutable = true;
bitmap_fill(chunk->populated, chunk->nr_pages);
chunk->nr_populated = chunk->nr_pages;
chunk->nr_empty_pop_pages = chunk->nr_pages;
chunk->free_bytes = map_size;
if (chunk->start_offset) {
/* hide the beginning of the bitmap */
offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
bitmap_set(chunk->alloc_map, 0, offset_bits);
set_bit(0, chunk->bound_map);
set_bit(offset_bits, chunk->bound_map);
chunk->chunk_md.first_free = offset_bits;
pcpu_block_update_hint_alloc(chunk, 0, offset_bits);
}
if (chunk->end_offset) {
/* hide the end of the bitmap */
offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE;
bitmap_set(chunk->alloc_map,
pcpu_chunk_map_bits(chunk) - offset_bits,
offset_bits);
set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE,
chunk->bound_map);
set_bit(region_bits, chunk->bound_map);
pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk)
- offset_bits, offset_bits);
}
return chunk;
}
static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
{
struct pcpu_chunk *chunk;
int region_bits;
chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp);
if (!chunk)
return NULL;
INIT_LIST_HEAD(&chunk->list);
chunk->nr_pages = pcpu_unit_pages;
region_bits = pcpu_chunk_map_bits(chunk);
chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
sizeof(chunk->alloc_map[0]), gfp);
if (!chunk->alloc_map)
goto alloc_map_fail;
chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
sizeof(chunk->bound_map[0]), gfp);
if (!chunk->bound_map)
goto bound_map_fail;
chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
sizeof(chunk->md_blocks[0]), gfp);
if (!chunk->md_blocks)
goto md_blocks_fail;
#ifdef NEED_PCPUOBJ_EXT
if (need_pcpuobj_ext()) {
chunk->obj_exts =
pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) *
sizeof(struct pcpuobj_ext), gfp);
if (!chunk->obj_exts)
goto objcg_fail;
}
#endif
pcpu_init_md_blocks(chunk);
/* init metadata */
chunk->free_bytes = chunk->nr_pages * PAGE_SIZE;
return chunk;
#ifdef NEED_PCPUOBJ_EXT
objcg_fail:
pcpu_mem_free(chunk->md_blocks);
#endif
md_blocks_fail:
pcpu_mem_free(chunk->bound_map);
bound_map_fail:
pcpu_mem_free(chunk->alloc_map);
alloc_map_fail:
pcpu_mem_free(chunk);
return NULL;
}
static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
if (!chunk)
return;
#ifdef NEED_PCPUOBJ_EXT
pcpu_mem_free(chunk->obj_exts);
#endif
pcpu_mem_free(chunk->md_blocks);
pcpu_mem_free(chunk->bound_map);
pcpu_mem_free(chunk->alloc_map);
pcpu_mem_free(chunk);
}
/**
* pcpu_chunk_populated - post-population bookkeeping
* @chunk: pcpu_chunk which got populated
* @page_start: the start page
* @page_end: the end page
*
* Pages in [@page_start,@page_end) have been populated to @chunk. Update
* the bookkeeping information accordingly. Must be called after each
* successful population.
*/
static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start,
int page_end)
{
int nr = page_end - page_start;
lockdep_assert_held(&pcpu_lock);
bitmap_set(chunk->populated, page_start, nr);
chunk->nr_populated += nr;
pcpu_nr_populated += nr;
pcpu_update_empty_pages(chunk, nr);
}
/**
* pcpu_chunk_depopulated - post-depopulation bookkeeping
* @chunk: pcpu_chunk which got depopulated
* @page_start: the start page
* @page_end: the end page
*
* Pages in [@page_start,@page_end) have been depopulated from @chunk.
* Update the bookkeeping information accordingly. Must be called after
* each successful depopulation.
*/
static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
int nr = page_end - page_start;
lockdep_assert_held(&pcpu_lock);
bitmap_clear(chunk->populated, page_start, nr);
chunk->nr_populated -= nr;
pcpu_nr_populated -= nr;
pcpu_update_empty_pages(chunk, -nr);
}
/*
* Chunk management implementation.
*
* To allow different implementations, chunk alloc/free and
* [de]population are implemented in a separate file which is pulled
* into this file and compiled together. The following functions
* should be implemented.
*
* pcpu_populate_chunk - populate the specified range of a chunk
* pcpu_depopulate_chunk - depopulate the specified range of a chunk
* pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk
* pcpu_create_chunk - create a new chunk
* pcpu_destroy_chunk - destroy a chunk, always preceded by full depop
* pcpu_addr_to_page - translate address to physical address
* pcpu_verify_alloc_info - check alloc_info is acceptable during init
*/
static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end, gfp_t gfp);
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end);
static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
int page_start, int page_end);
static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
static struct page *pcpu_addr_to_page(void *addr);
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
#ifdef CONFIG_NEED_PER_CPU_KM
#include "percpu-km.c"
#else
#include "percpu-vm.c"
#endif
/**
* pcpu_chunk_addr_search - determine chunk containing specified address
* @addr: address for which the chunk needs to be determined.
*
* This is an internal function that handles all but static allocations.
* Static percpu address values should never be passed into the allocator.
*
* RETURNS:
* The address of the found chunk.
*/
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
/* is it in the dynamic region (first chunk)? */
if (pcpu_addr_in_chunk(pcpu_first_chunk, addr))
return pcpu_first_chunk;
/* is it in the reserved region? */
if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr))
return pcpu_reserved_chunk;
/*
* The address is relative to unit0 which might be unused and
* thus unmapped. Offset the address to the unit space of the
* current processor before looking it up in the vmalloc
* space. Note that any possible cpu id can be used here, so
* there's no need to worry about preemption or cpu hotplug.
*/
addr += pcpu_unit_offsets[raw_smp_processor_id()];
return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
}
#ifdef CONFIG_MEMCG
static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
struct obj_cgroup **objcgp)
{
struct obj_cgroup *objcg;
if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT))
return true;
objcg = current_obj_cgroup();
if (!objcg)
return true;
if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size)))
return false;
*objcgp = objcg;
return true;
}
static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
struct pcpu_chunk *chunk, int off,
size_t size)
{ if (!objcg)
return;
if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg);
chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg;
rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
pcpu_obj_full_size(size));
rcu_read_unlock();
} else {
obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
}
}
static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
{
struct obj_cgroup *objcg;
if (unlikely(!chunk->obj_exts))
return;
objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup;
if (!objcg)
return;
chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL;
obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
-pcpu_obj_full_size(size));
rcu_read_unlock(); obj_cgroup_put(objcg);
}
#else /* CONFIG_MEMCG */
static bool
pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp)
{
return true;
}
static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
struct pcpu_chunk *chunk, int off,
size_t size)
{
}
static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
{
}
#endif /* CONFIG_MEMCG */
#ifdef CONFIG_MEM_ALLOC_PROFILING
static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off,
size_t size)
{
if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) {
alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag,
current->alloc_tag, size);
}
}
static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
{
if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts))
alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size);
}
#else
static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off,
size_t size)
{
}
static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
{
}
#endif
/**
* pcpu_alloc - the percpu allocator
* @size: size of area to allocate in bytes
* @align: alignment of area (max PAGE_SIZE)
* @reserved: allocate from the reserved chunk if available
* @gfp: allocation flags
*
* Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't
* contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN
* then no warning will be triggered on invalid or failed allocation
* requests.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
*/
void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
gfp_t gfp)
{
gfp_t pcpu_gfp;
bool is_atomic;
bool do_warn;
struct obj_cgroup *objcg = NULL;
static int warn_limit = 10;
struct pcpu_chunk *chunk, *next;
const char *err;
int slot, off, cpu, ret;
unsigned long flags;
void __percpu *ptr;
size_t bits, bit_align;
gfp = current_gfp_context(gfp);
/* whitelisted flags that can be passed to the backing allocators */
pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
is_atomic = !gfpflags_allow_blocking(gfp);
do_warn = !(gfp & __GFP_NOWARN);
/*
* There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
* therefore alignment must be a minimum of that many bytes.
* An allocation may have internal fragmentation from rounding up
* of up to PCPU_MIN_ALLOC_SIZE - 1 bytes.
*/
if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE;
size = ALIGN(size, PCPU_MIN_ALLOC_SIZE);
bits = size >> PCPU_MIN_ALLOC_SHIFT;
bit_align = align >> PCPU_MIN_ALLOC_SHIFT;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE ||
!is_power_of_2(align))) {
WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n",
size, align);
return NULL;
}
if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg)))
return NULL;
if (!is_atomic) {
/*
* pcpu_balance_workfn() allocates memory under this mutex,
* and it may wait for memory reclaim. Allow current task
* to become OOM victim, in case of memory pressure.
*/
if (gfp & __GFP_NOFAIL) {
mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
return NULL;
}
}
spin_lock_irqsave(&pcpu_lock, flags);
/* serve reserved allocations from the reserved chunk if available */
if (reserved && pcpu_reserved_chunk) {
chunk = pcpu_reserved_chunk;
off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic);
if (off < 0) {
err = "alloc from reserved chunk failed";
goto fail_unlock;
}
off = pcpu_alloc_area(chunk, bits, bit_align, off);
if (off >= 0)
goto area_found;
err = "alloc from reserved chunk failed";
goto fail_unlock;
}
restart:
/* search through normal chunks */
for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot],
list) {
off = pcpu_find_block_fit(chunk, bits, bit_align,
is_atomic);
if (off < 0) {
if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0);
continue;
}
off = pcpu_alloc_area(chunk, bits, bit_align, off);
if (off >= 0) { pcpu_reintegrate_chunk(chunk);
goto area_found;
}
}
}
spin_unlock_irqrestore(&pcpu_lock, flags);
if (is_atomic) {
err = "atomic alloc failed, no space left";
goto fail;
}
/* No space left. Create a new chunk. */
if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) {
chunk = pcpu_create_chunk(pcpu_gfp);
if (!chunk) {
err = "failed to allocate new chunk";
goto fail;
}
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_chunk_relocate(chunk, -1);
} else {
spin_lock_irqsave(&pcpu_lock, flags);
}
goto restart;
area_found:
pcpu_stats_area_alloc(chunk, size); if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work();
spin_unlock_irqrestore(&pcpu_lock, flags);
/* populate if not all pages are already there */
if (!is_atomic) {
unsigned int page_end, rs, re;
rs = PFN_DOWN(off);
page_end = PFN_UP(off + size);
for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) {
WARN_ON(chunk->immutable);
ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
spin_lock_irqsave(&pcpu_lock, flags);
if (ret) {
pcpu_free_area(chunk, off);
err = "failed to populate";
goto fail_unlock;
}
pcpu_chunk_populated(chunk, rs, re);
spin_unlock_irqrestore(&pcpu_lock, flags);
}
mutex_unlock(&pcpu_alloc_mutex);
}
/* clear the areas and return address relative to base address */
for_each_possible_cpu(cpu)
memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
kmemleak_alloc_percpu(ptr, size, gfp);
trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align,
chunk->base_addr, off, ptr,
pcpu_obj_full_size(size), gfp);
pcpu_memcg_post_alloc_hook(objcg, chunk, off, size);
pcpu_alloc_tag_alloc_hook(chunk, off, size);
return ptr;
fail_unlock:
spin_unlock_irqrestore(&pcpu_lock, flags);
fail:
trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn && warn_limit) {
pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
size, align, is_atomic, err);
if (!is_atomic) dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n");
}
if (is_atomic) {
/* see the flag handling in pcpu_balance_workfn() */
pcpu_atomic_alloc_failed = true;
pcpu_schedule_balance_work();
} else {
mutex_unlock(&pcpu_alloc_mutex);
}
pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size);
return NULL;
}
EXPORT_SYMBOL_GPL(pcpu_alloc_noprof);
/**
* pcpu_balance_free - manage the amount of free chunks
* @empty_only: free chunks only if there are no populated pages
*
* If empty_only is %false, reclaim all fully free chunks regardless of the
* number of populated pages. Otherwise, only reclaim chunks that have no
* populated pages.
*
* CONTEXT:
* pcpu_lock (can be dropped temporarily)
*/
static void pcpu_balance_free(bool empty_only)
{
LIST_HEAD(to_free);
struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot];
struct pcpu_chunk *chunk, *next;
lockdep_assert_held(&pcpu_lock);
/*
* There's no reason to keep around multiple unused chunks and VM
* areas can be scarce. Destroy all free chunks except for one.
*/
list_for_each_entry_safe(chunk, next, free_head, list) {
WARN_ON(chunk->immutable);
/* spare the first one */
if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
continue;
if (!empty_only || chunk->nr_empty_pop_pages == 0)
list_move(&chunk->list, &to_free);
}
if (list_empty(&to_free))
return;
spin_unlock_irq(&pcpu_lock);
list_for_each_entry_safe(chunk, next, &to_free, list) {
unsigned int rs, re;
for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) {
pcpu_depopulate_chunk(chunk, rs, re);
spin_lock_irq(&pcpu_lock);
pcpu_chunk_depopulated(chunk, rs, re);
spin_unlock_irq(&pcpu_lock);
}
pcpu_destroy_chunk(chunk);
cond_resched();
}
spin_lock_irq(&pcpu_lock);
}
/**
* pcpu_balance_populated - manage the amount of populated pages
*
* Maintain a certain amount of populated pages to satisfy atomic allocations.
* It is possible that this is called when physical memory is scarce causing
* OOM killer to be triggered. We should avoid doing so until an actual
* allocation causes the failure as it is possible that requests can be
* serviced from already backed regions.
*
* CONTEXT:
* pcpu_lock (can be dropped temporarily)
*/
static void pcpu_balance_populated(void)
{
/* gfp flags passed to underlying allocators */
const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
struct pcpu_chunk *chunk;
int slot, nr_to_pop, ret;
lockdep_assert_held(&pcpu_lock);
/*
* Ensure there are certain number of free populated pages for
* atomic allocs. Fill up from the most packed so that atomic
* allocs don't increase fragmentation. If atomic allocation
* failed previously, always populate the maximum amount. This
* should prevent atomic allocs larger than PAGE_SIZE from keeping
* failing indefinitely; however, large atomic allocs are not
* something we support properly and can be highly unreliable and
* inefficient.
*/
retry_pop:
if (pcpu_atomic_alloc_failed) {
nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
/* best effort anyway, don't worry about synchronization */
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
pcpu_nr_empty_pop_pages,
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) {
unsigned int nr_unpop = 0, rs, re;
if (!nr_to_pop)
break;
list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) {
nr_unpop = chunk->nr_pages - chunk->nr_populated;
if (nr_unpop)
break;
}
if (!nr_unpop)
continue;
/* @chunk can't go away while pcpu_alloc_mutex is held */
for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) {
int nr = min_t(int, re - rs, nr_to_pop);
spin_unlock_irq(&pcpu_lock);
ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
cond_resched();
spin_lock_irq(&pcpu_lock);
if (!ret) {
nr_to_pop -= nr;
pcpu_chunk_populated(chunk, rs, rs + nr);
} else {
nr_to_pop = 0;
}
if (!nr_to_pop)
break;
}
}
if (nr_to_pop) {
/* ran out of chunks to populate, create a new one and retry */
spin_unlock_irq(&pcpu_lock);
chunk = pcpu_create_chunk(gfp);
cond_resched();
spin_lock_irq(&pcpu_lock);
if (chunk) {
pcpu_chunk_relocate(chunk, -1);
goto retry_pop;
}
}
}
/**
* pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages
*
* Scan over chunks in the depopulate list and try to release unused populated
* pages back to the system. Depopulated chunks are sidelined to prevent
* repopulating these pages unless required. Fully free chunks are reintegrated
* and freed accordingly (1 is kept around). If we drop below the empty
* populated pages threshold, reintegrate the chunk if it has empty free pages.
* Each chunk is scanned in the reverse order to keep populated pages close to
* the beginning of the chunk.
*
* CONTEXT:
* pcpu_lock (can be dropped temporarily)
*
*/
static void pcpu_reclaim_populated(void)
{
struct pcpu_chunk *chunk;
struct pcpu_block_md *block;
int freed_page_start, freed_page_end;
int i, end;
bool reintegrate;
lockdep_assert_held(&pcpu_lock);
/*
* Once a chunk is isolated to the to_depopulate list, the chunk is no
* longer discoverable to allocations whom may populate pages. The only
* other accessor is the free path which only returns area back to the
* allocator not touching the populated bitmap.
*/
while ((chunk = list_first_entry_or_null(
&pcpu_chunk_lists[pcpu_to_depopulate_slot],
struct pcpu_chunk, list))) {
WARN_ON(chunk->immutable);
/*
* Scan chunk's pages in the reverse order to keep populated
* pages close to the beginning of the chunk.
*/
freed_page_start = chunk->nr_pages;
freed_page_end = 0;
reintegrate = false;
for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) {
/* no more work to do */
if (chunk->nr_empty_pop_pages == 0)
break;
/* reintegrate chunk to prevent atomic alloc failures */
if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) {
reintegrate = true;
break;
}
/*
* If the page is empty and populated, start or
* extend the (i, end) range. If i == 0, decrease
* i and perform the depopulation to cover the last
* (first) page in the chunk.
*/
block = chunk->md_blocks + i;
if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS &&
test_bit(i, chunk->populated)) {
if (end == -1)
end = i;
if (i > 0)
continue;
i--;
}
/* depopulate if there is an active range */
if (end == -1)
continue;
spin_unlock_irq(&pcpu_lock);
pcpu_depopulate_chunk(chunk, i + 1, end + 1);
cond_resched();
spin_lock_irq(&pcpu_lock);
pcpu_chunk_depopulated(chunk, i + 1, end + 1);
freed_page_start = min(freed_page_start, i + 1);
freed_page_end = max(freed_page_end, end + 1);
/* reset the range and continue */
end = -1;
}
/* batch tlb flush per chunk to amortize cost */
if (freed_page_start < freed_page_end) {
spin_unlock_irq(&pcpu_lock);
pcpu_post_unmap_tlb_flush(chunk,
freed_page_start,
freed_page_end);
cond_resched();
spin_lock_irq(&pcpu_lock);
}
if (reintegrate || chunk->free_bytes == pcpu_unit_size)
pcpu_reintegrate_chunk(chunk);
else
list_move_tail(&chunk->list,
&pcpu_chunk_lists[pcpu_sidelined_slot]);
}
}
/**
* pcpu_balance_workfn - manage the amount of free chunks and populated pages
* @work: unused
*
* For each chunk type, manage the number of fully free chunks and the number of
* populated pages. An important thing to consider is when pages are freed and
* how they contribute to the global counts.
*/
static void pcpu_balance_workfn(struct work_struct *work)
{
/*
* pcpu_balance_free() is called twice because the first time we may
* trim pages in the active pcpu_nr_empty_pop_pages which may cause us
* to grow other chunks. This then gives pcpu_reclaim_populated() time
* to move fully free chunks to the active list to be freed if
* appropriate.
*
* Enforce GFP_NOIO allocations because we have pcpu_alloc users
* constrained to GFP_NOIO/NOFS contexts and they could form lock
* dependency through pcpu_alloc_mutex
*/
unsigned int flags = memalloc_noio_save();
mutex_lock(&pcpu_alloc_mutex);
spin_lock_irq(&pcpu_lock);
pcpu_balance_free(false);
pcpu_reclaim_populated();
pcpu_balance_populated();
pcpu_balance_free(true);
spin_unlock_irq(&pcpu_lock);
mutex_unlock(&pcpu_alloc_mutex);
memalloc_noio_restore(flags);
}
/**
* free_percpu - free percpu area
* @ptr: pointer to area to free
*
* Free percpu area @ptr.
*
* CONTEXT:
* Can be called from atomic context.
*/
void free_percpu(void __percpu *ptr)
{
void *addr;
struct pcpu_chunk *chunk;
unsigned long flags;
int size, off;
bool need_balance = false;
if (!ptr)
return;
kmemleak_free_percpu(ptr);
addr = __pcpu_ptr_to_addr(ptr);
chunk = pcpu_chunk_addr_search(addr);
off = addr - chunk->base_addr;
spin_lock_irqsave(&pcpu_lock, flags);
size = pcpu_free_area(chunk, off);
pcpu_alloc_tag_free_hook(chunk, off, size);
pcpu_memcg_free_hook(chunk, off, size);
/*
* If there are more than one fully free chunks, wake up grim reaper.
* If the chunk is isolated, it may be in the process of being
* reclaimed. Let reclaim manage cleaning up of that chunk.
*/
if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) {
struct pcpu_chunk *pos;
list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) {
need_balance = true;
break;
}
} else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk);
need_balance = true;
}
trace_percpu_free_percpu(chunk->base_addr, off, ptr);
spin_unlock_irqrestore(&pcpu_lock, flags);
if (need_balance)
pcpu_schedule_balance_work();
}
EXPORT_SYMBOL_GPL(free_percpu);
bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr)
{
#ifdef CONFIG_SMP
const size_t static_size = __per_cpu_end - __per_cpu_start;
void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
unsigned int cpu;
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(base, cpu);
void *va = (void *)addr;
if (va >= start && va < start + static_size) {
if (can_addr) { *can_addr = (unsigned long) (va - start);
*can_addr += (unsigned long)
per_cpu_ptr(base, get_boot_cpu_id());
}
return true;
}
}
#endif
/* on UP, can't distinguish from other static vars, always false */
return false;
}
/**
* is_kernel_percpu_address - test whether address is from static percpu area
* @addr: address to test
*
* Test whether @addr belongs to in-kernel static percpu area. Module
* static percpu areas are not considered. For those, use
* is_module_percpu_address().
*
* RETURNS:
* %true if @addr is from in-kernel static percpu area, %false otherwise.
*/
bool is_kernel_percpu_address(unsigned long addr)
{
return __is_kernel_percpu_address(addr, NULL);
}
/**
* per_cpu_ptr_to_phys - convert translated percpu address to physical address
* @addr: the address to be converted to physical address
*
* Given @addr which is dereferenceable address obtained via one of
* percpu access macros, this function translates it into its physical
* address. The caller is responsible for ensuring @addr stays valid
* until this function finishes.
*
* percpu allocator has special setup for the first chunk, which currently
* supports either embedding in linear address space or vmalloc mapping,
* and, from the second one, the backing allocator (currently either vm or
* km) provides translation.
*
* The addr can be translated simply without checking if it falls into the
* first chunk. But the current code reflects better how percpu allocator
* actually works, and the verification can discover both bugs in percpu
* allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
* code.
*
* RETURNS:
* The physical address for @addr.
*/
phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
bool in_first_chunk = false;
unsigned long first_low, first_high;
unsigned int cpu;
/*
* The following test on unit_low/high isn't strictly
* necessary but will speed up lookups of addresses which
* aren't in the first chunk.
*
* The address check is against full chunk sizes. pcpu_base_addr
* points to the beginning of the first chunk including the
* static region. Assumes good intent as the first chunk may
* not be full (ie. < pcpu_unit_pages in size).
*/
first_low = (unsigned long)pcpu_base_addr +
pcpu_unit_page_offset(pcpu_low_unit_cpu, 0);
first_high = (unsigned long)pcpu_base_addr +
pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages);
if ((unsigned long)addr >= first_low &&
(unsigned long)addr < first_high) {
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(base, cpu);
if (addr >= start && addr < start + pcpu_unit_size) {
in_first_chunk = true;
break;
}
}
}
if (in_first_chunk) {
if (!is_vmalloc_addr(addr))
return __pa(addr);
else
return page_to_phys(vmalloc_to_page(addr)) +
offset_in_page(addr);
} else
return page_to_phys(pcpu_addr_to_page(addr)) +
offset_in_page(addr);
}
/**
* pcpu_alloc_alloc_info - allocate percpu allocation info
* @nr_groups: the number of groups
* @nr_units: the number of units
*
* Allocate ai which is large enough for @nr_groups groups containing
* @nr_units units. The returned ai's groups[0].cpu_map points to the
* cpu_map array which is long enough for @nr_units and filled with
* NR_CPUS. It's the caller's responsibility to initialize cpu_map
* pointer of other groups.
*
* RETURNS:
* Pointer to the allocated pcpu_alloc_info on success, NULL on
* failure.
*/
struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
int nr_units)
{
struct pcpu_alloc_info *ai;
size_t base_size, ai_size;
void *ptr;
int unit;
base_size = ALIGN(struct_size(ai, groups, nr_groups),
__alignof__(ai->groups[0].cpu_map[0]));
ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);
ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE);
if (!ptr)
return NULL;
ai = ptr;
ptr += base_size;
ai->groups[0].cpu_map = ptr;
for (unit = 0; unit < nr_units; unit++)
ai->groups[0].cpu_map[unit] = NR_CPUS;
ai->nr_groups = nr_groups;
ai->__ai_size = PFN_ALIGN(ai_size);
return ai;
}
/**
* pcpu_free_alloc_info - free percpu allocation info
* @ai: pcpu_alloc_info to free
*
* Free @ai which was allocated by pcpu_alloc_alloc_info().
*/
void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
{
memblock_free(ai, ai->__ai_size);
}
/**
* pcpu_dump_alloc_info - print out information about pcpu_alloc_info
* @lvl: loglevel
* @ai: allocation info to dump
*
* Print out information about @ai using loglevel @lvl.
*/
static void pcpu_dump_alloc_info(const char *lvl,
const struct pcpu_alloc_info *ai)
{
int group_width = 1, cpu_width = 1, width;
char empty_str[] = "--------";
int alloc = 0, alloc_end = 0;
int group, v;
int upa, apl; /* units per alloc, allocs per line */
v = ai->nr_groups;
while (v /= 10)
group_width++;
v = num_possible_cpus();
while (v /= 10)
cpu_width++;
empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';
upa = ai->alloc_size / ai->unit_size;
width = upa * (cpu_width + 1) + group_width + 3;
apl = rounddown_pow_of_two(max(60 / width, 1));
printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);
for (group = 0; group < ai->nr_groups; group++) {
const struct pcpu_group_info *gi = &ai->groups[group];
int unit = 0, unit_end = 0;
BUG_ON(gi->nr_units % upa);
for (alloc_end += gi->nr_units / upa;
alloc < alloc_end; alloc++) {
if (!(alloc % apl)) {
pr_cont("\n");
printk("%spcpu-alloc: ", lvl);
}
pr_cont("[%0*d] ", group_width, group);
for (unit_end += upa; unit < unit_end; unit++)
if (gi->cpu_map[unit] != NR_CPUS)
pr_cont("%0*d ",
cpu_width, gi->cpu_map[unit]);
else
pr_cont("%s ", empty_str);
}
}
pr_cont("\n");
}
/**
* pcpu_setup_first_chunk - initialize the first percpu chunk
* @ai: pcpu_alloc_info describing how to percpu area is shaped
* @base_addr: mapped address
*
* Initialize the first percpu chunk which contains the kernel static
* percpu area. This function is to be called from arch percpu area
* setup path.
*
* @ai contains all information necessary to initialize the first
* chunk and prime the dynamic percpu allocator.
*
* @ai->static_size is the size of static percpu area.
*
* @ai->reserved_size, if non-zero, specifies the amount of bytes to
* reserve after the static area in the first chunk. This reserves
* the first chunk such that it's available only through reserved
* percpu allocation. This is primarily used to serve module percpu
* static areas on architectures where the addressing model has
* limited offset range for symbol relocations to guarantee module
* percpu symbols fall inside the relocatable range.
*
* @ai->dyn_size determines the number of bytes available for dynamic
* allocation in the first chunk. The area between @ai->static_size +
* @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
*
* @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
* and equal to or larger than @ai->static_size + @ai->reserved_size +
* @ai->dyn_size.
*
* @ai->atom_size is the allocation atom size and used as alignment
* for vm areas.
*
* @ai->alloc_size is the allocation size and always multiple of
* @ai->atom_size. This is larger than @ai->atom_size if
* @ai->unit_size is larger than @ai->atom_size.
*
* @ai->nr_groups and @ai->groups describe virtual memory layout of
* percpu areas. Units which should be colocated are put into the
* same group. Dynamic VM areas will be allocated according to these
* groupings. If @ai->nr_groups is zero, a single group containing
* all units is assumed.
*
* The caller should have mapped the first chunk at @base_addr and
* copied static data to each unit.
*
* The first chunk will always contain a static and a dynamic region.
* However, the static region is not managed by any chunk. If the first
* chunk also contains a reserved region, it is served by two chunks -
* one for the reserved region and one for the dynamic region. They
* share the same vm, but use offset regions in the area allocation map.
* The chunk serving the dynamic region is circulated in the chunk slots
* and available for dynamic allocation like any other chunk.
*/
void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
void *base_addr)
{
size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
size_t static_size, dyn_size;
unsigned long *group_offsets;
size_t *group_sizes;
unsigned long *unit_off;
unsigned int cpu;
int *unit_map;
int group, unit, i;
unsigned long tmp_addr;
size_t alloc_size;
#define PCPU_SETUP_BUG_ON(cond) do { \
if (unlikely(cond)) { \
pr_emerg("failed to initialize, %s\n", #cond); \
pr_emerg("cpu_possible_mask=%*pb\n", \
cpumask_pr_args(cpu_possible_mask)); \
pcpu_dump_alloc_info(KERN_EMERG, ai); \
BUG(); \
} \
} while (0)
/* sanity checks */
PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
#ifdef CONFIG_SMP
PCPU_SETUP_BUG_ON(!ai->static_size);
PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start));
#endif
PCPU_SETUP_BUG_ON(!base_addr);
PCPU_SETUP_BUG_ON(offset_in_page(base_addr));
PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size));
PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE));
PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE));
PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) ||
IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE)));
PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
/* process group information and build config tables accordingly */
alloc_size = ai->nr_groups * sizeof(group_offsets[0]);
group_offsets = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
alloc_size = ai->nr_groups * sizeof(group_sizes[0]);
group_sizes = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
alloc_size = nr_cpu_ids * sizeof(unit_map[0]);
unit_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
alloc_size = nr_cpu_ids * sizeof(unit_off[0]);
unit_off = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
unit_map[cpu] = UINT_MAX;
pcpu_low_unit_cpu = NR_CPUS;
pcpu_high_unit_cpu = NR_CPUS;
for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
const struct pcpu_group_info *gi = &ai->groups[group];
group_offsets[group] = gi->base_offset;
group_sizes[group] = gi->nr_units * ai->unit_size;
for (i = 0; i < gi->nr_units; i++) {
cpu = gi->cpu_map[i];
if (cpu == NR_CPUS)
continue;
PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids);
PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);
unit_map[cpu] = unit + i;
unit_off[cpu] = gi->base_offset + i * ai->unit_size;
/* determine low/high unit_cpu */
if (pcpu_low_unit_cpu == NR_CPUS ||
unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
pcpu_low_unit_cpu = cpu;
if (pcpu_high_unit_cpu == NR_CPUS ||
unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
pcpu_high_unit_cpu = cpu;
}
}
pcpu_nr_units = unit;
for_each_possible_cpu(cpu)
PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
/* we're done parsing the input, undefine BUG macro and dump config */
#undef PCPU_SETUP_BUG_ON
pcpu_dump_alloc_info(KERN_DEBUG, ai);
pcpu_nr_groups = ai->nr_groups;
pcpu_group_offsets = group_offsets;
pcpu_group_sizes = group_sizes;
pcpu_unit_map = unit_map;
pcpu_unit_offsets = unit_off;
/* determine basic parameters */
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_atom_size = ai->atom_size;
pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated,
BITS_TO_LONGS(pcpu_unit_pages));
pcpu_stats_save_ai(ai);
/*
* Allocate chunk slots. The slots after the active slots are:
* sidelined_slot - isolated, depopulated chunks
* free_slot - fully free chunks
* to_depopulate_slot - isolated, chunks to depopulate
*/
pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1;
pcpu_free_slot = pcpu_sidelined_slot + 1;
pcpu_to_depopulate_slot = pcpu_free_slot + 1;
pcpu_nr_slots = pcpu_to_depopulate_slot + 1;
pcpu_chunk_lists = memblock_alloc_or_panic(pcpu_nr_slots *
sizeof(pcpu_chunk_lists[0]),
SMP_CACHE_BYTES);
for (i = 0; i < pcpu_nr_slots; i++)
INIT_LIST_HEAD(&pcpu_chunk_lists[i]);
/*
* The end of the static region needs to be aligned with the
* minimum allocation size as this offsets the reserved and
* dynamic region. The first chunk ends page aligned by
* expanding the dynamic region, therefore the dynamic region
* can be shrunk to compensate while still staying above the
* configured sizes.
*/
static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE);
dyn_size = ai->dyn_size - (static_size - ai->static_size);
/*
* Initialize first chunk:
* This chunk is broken up into 3 parts:
* < static | [reserved] | dynamic >
* - static - there is no backing chunk because these allocations can
* never be freed.
* - reserved (pcpu_reserved_chunk) - exists primarily to serve
* allocations from module load.
* - dynamic (pcpu_first_chunk) - serves the dynamic part of the first
* chunk.
*/
tmp_addr = (unsigned long)base_addr + static_size;
if (ai->reserved_size)
pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr,
ai->reserved_size);
tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size;
pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size);
pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* include all regions of the first chunk */
pcpu_nr_populated += PFN_DOWN(size_sum);
pcpu_stats_chunk_alloc();
trace_percpu_create_chunk(base_addr);
/* we're done */
pcpu_base_addr = base_addr;
}
#ifdef CONFIG_SMP
const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = {
[PCPU_FC_AUTO] = "auto",
[PCPU_FC_EMBED] = "embed",
[PCPU_FC_PAGE] = "page",
};
enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
static int __init percpu_alloc_setup(char *str)
{
if (!str)
return -EINVAL;
if (0)
/* nada */;
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
else if (!strcmp(str, "embed"))
pcpu_chosen_fc = PCPU_FC_EMBED;
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
else if (!strcmp(str, "page"))
pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
else
pr_warn("unknown allocator %s specified\n", str);
return 0;
}
early_param("percpu_alloc", percpu_alloc_setup);
/*
* pcpu_embed_first_chunk() is used by the generic percpu setup.
* Build it if needed by the arch config or the generic setup is going
* to be used.
*/
#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
#define BUILD_EMBED_FIRST_CHUNK
#endif
/* build pcpu_page_first_chunk() iff needed by the arch config */
#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
#define BUILD_PAGE_FIRST_CHUNK
#endif
/* pcpu_build_alloc_info() is used by both embed and page first chunk */
#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
/**
* pcpu_build_alloc_info - build alloc_info considering distances between CPUs
* @reserved_size: the size of reserved percpu area in bytes
* @dyn_size: minimum free size for dynamic allocation in bytes
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
*
* This function determines grouping of units, their mappings to cpus
* and other parameters considering needed percpu size, allocation
* atom size and distances between CPUs.
*
* Groups are always multiples of atom size and CPUs which are of
* LOCAL_DISTANCE both ways are grouped together and share space for
* units in the same group. The returned configuration is guaranteed
* to have CPUs on different nodes on different groups and >=75% usage
* of allocated virtual address space.
*
* RETURNS:
* On success, pointer to the new allocation_info is returned. On
* failure, ERR_PTR value is returned.
*/
static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
size_t reserved_size, size_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
{
static int group_map[NR_CPUS] __initdata;
static int group_cnt[NR_CPUS] __initdata;
static struct cpumask mask __initdata;
const size_t static_size = __per_cpu_end - __per_cpu_start;
int nr_groups = 1, nr_units = 0;
size_t size_sum, min_unit_size, alloc_size;
int upa, max_upa, best_upa; /* units_per_alloc */
int last_allocs, group, unit;
unsigned int cpu, tcpu;
struct pcpu_alloc_info *ai;
unsigned int *cpu_map;
/* this function may be called multiple times */
memset(group_map, 0, sizeof(group_map));
memset(group_cnt, 0, sizeof(group_cnt));
cpumask_clear(&mask);
/* calculate size_sum and ensure dyn_size is enough for early alloc */
size_sum = PFN_ALIGN(static_size + reserved_size +
max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
dyn_size = size_sum - static_size - reserved_size;
/*
* Determine min_unit_size, alloc_size and max_upa such that
* alloc_size is multiple of atom_size and is the smallest
* which can accommodate 4k aligned segments which are equal to
* or larger than min_unit_size.
*/
min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
/* determine the maximum # of units that can fit in an allocation */
alloc_size = roundup(min_unit_size, atom_size);
upa = alloc_size / min_unit_size;
while (alloc_size % upa || (offset_in_page(alloc_size / upa)))
upa--;
max_upa = upa;
cpumask_copy(&mask, cpu_possible_mask);
/* group cpus according to their proximity */
for (group = 0; !cpumask_empty(&mask); group++) {
/* pop the group's first cpu */
cpu = cpumask_first(&mask);
group_map[cpu] = group;
group_cnt[group]++;
cpumask_clear_cpu(cpu, &mask);
for_each_cpu(tcpu, &mask) {
if (!cpu_distance_fn ||
(cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE &&
cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) {
group_map[tcpu] = group;
group_cnt[group]++;
cpumask_clear_cpu(tcpu, &mask);
}
}
}
nr_groups = group;
/*
* Wasted space is caused by a ratio imbalance of upa to group_cnt.
* Expand the unit_size until we use >= 75% of the units allocated.
* Related to atom_size, which could be much larger than the unit_size.
*/
last_allocs = INT_MAX;
best_upa = 0;
for (upa = max_upa; upa; upa--) {
int allocs = 0, wasted = 0;
if (alloc_size % upa || (offset_in_page(alloc_size / upa)))
continue;
for (group = 0; group < nr_groups; group++) {
int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
allocs += this_allocs;
wasted += this_allocs * upa - group_cnt[group];
}
/*
* Don't accept if wastage is over 1/3. The
* greater-than comparison ensures upa==1 always
* passes the following check.
*/
if (wasted > num_possible_cpus() / 3)
continue;
/* and then don't consume more memory */
if (allocs > last_allocs)
break;
last_allocs = allocs;
best_upa = upa;
}
BUG_ON(!best_upa);
upa = best_upa;
/* allocate and fill alloc_info */
for (group = 0; group < nr_groups; group++)
nr_units += roundup(group_cnt[group], upa);
ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
if (!ai)
return ERR_PTR(-ENOMEM);
cpu_map = ai->groups[0].cpu_map;
for (group = 0; group < nr_groups; group++) {
ai->groups[group].cpu_map = cpu_map;
cpu_map += roundup(group_cnt[group], upa);
}
ai->static_size = static_size;
ai->reserved_size = reserved_size;
ai->dyn_size = dyn_size;
ai->unit_size = alloc_size / upa;
ai->atom_size = atom_size;
ai->alloc_size = alloc_size;
for (group = 0, unit = 0; group < nr_groups; group++) {
struct pcpu_group_info *gi = &ai->groups[group];
/*
* Initialize base_offset as if all groups are located
* back-to-back. The caller should update this to
* reflect actual allocation.
*/
gi->base_offset = unit * ai->unit_size;
for_each_possible_cpu(cpu)
if (group_map[cpu] == group)
gi->cpu_map[gi->nr_units++] = cpu;
gi->nr_units = roundup(gi->nr_units, upa);
unit += gi->nr_units;
}
BUG_ON(unit != nr_units);
return ai;
}
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align,
pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
const unsigned long goal = __pa(MAX_DMA_ADDRESS);
#ifdef CONFIG_NUMA
int node = NUMA_NO_NODE;
void *ptr;
if (cpu_to_nd_fn)
node = cpu_to_nd_fn(cpu);
if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) {
ptr = memblock_alloc_from(size, align, goal);
pr_info("cpu %d has no node %d or node-local memory\n",
cpu, node);
pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n",
cpu, size, (u64)__pa(ptr));
} else {
ptr = memblock_alloc_try_nid(size, align, goal,
MEMBLOCK_ALLOC_ACCESSIBLE,
node);
pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n",
cpu, size, node, (u64)__pa(ptr));
}
return ptr;
#else
return memblock_alloc_from(size, align, goal);
#endif
}
static void __init pcpu_fc_free(void *ptr, size_t size)
{
memblock_free(ptr, size);
}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
#if defined(BUILD_EMBED_FIRST_CHUNK)
/**
* pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
* @reserved_size: the size of reserved percpu area in bytes
* @dyn_size: minimum free size for dynamic allocation in bytes
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
* @cpu_to_nd_fn: callback to convert cpu to it's node, optional
*
* This is a helper to ease setting up embedded first percpu chunk and
* can be called where pcpu_setup_first_chunk() is expected.
*
* If this function is used to setup the first chunk, it is allocated
* by calling pcpu_fc_alloc and used as-is without being mapped into
* vmalloc area. Allocations are always whole multiples of @atom_size
* aligned to @atom_size.
*
* This enables the first chunk to piggy back on the linear physical
* mapping which often uses larger page size. Please note that this
* can result in very sparse cpu->unit mapping on NUMA machines thus
* requiring large vmalloc address space. Don't use this allocator if
* vmalloc space is not orders of magnitude larger than distances
* between node memory addresses (ie. 32bit NUMA machines).
*
* @dyn_size specifies the minimum dynamic area size.
*
* If the needed size is smaller than the minimum or specified unit
* size, the leftover is returned using pcpu_fc_free.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
void *base = (void *)ULONG_MAX;
void **areas = NULL;
struct pcpu_alloc_info *ai;
size_t size_sum, areas_size;
unsigned long max_distance;
int group, i, highest_group, rc = 0;
ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
cpu_distance_fn);
if (IS_ERR(ai))
return PTR_ERR(ai);
size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
areas = memblock_alloc(areas_size, SMP_CACHE_BYTES);
if (!areas) {
rc = -ENOMEM;
goto out_free;
}
/* allocate, copy and determine base address & max_distance */
highest_group = 0;
for (group = 0; group < ai->nr_groups; group++) {
struct pcpu_group_info *gi = &ai->groups[group];
unsigned int cpu = NR_CPUS;
void *ptr;
for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
cpu = gi->cpu_map[i];
BUG_ON(cpu == NR_CPUS);
/* allocate space for the whole group */
ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn);
if (!ptr) {
rc = -ENOMEM;
goto out_free_areas;
}
/* kmemleak tracks the percpu allocations separately */
kmemleak_ignore_phys(__pa(ptr));
areas[group] = ptr;
base = min(ptr, base);
if (ptr > areas[highest_group])
highest_group = group;
}
max_distance = areas[highest_group] - base;
max_distance += ai->unit_size * ai->groups[highest_group].nr_units;
/* warn if maximum distance is further than 75% of vmalloc space */
if (max_distance > VMALLOC_TOTAL * 3 / 4) {
pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n",
max_distance, VMALLOC_TOTAL);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
/* and fail if we have fallback */
rc = -EINVAL;
goto out_free_areas;
#endif
}
/*
* Copy data and free unused parts. This should happen after all
* allocations are complete; otherwise, we may end up with
* overlapping groups.
*/
for (group = 0; group < ai->nr_groups; group++) {
struct pcpu_group_info *gi = &ai->groups[group];
void *ptr = areas[group];
for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
if (gi->cpu_map[i] == NR_CPUS) {
/* unused unit, free whole */
pcpu_fc_free(ptr, ai->unit_size);
continue;
}
/* copy and return the unused part */
memcpy(ptr, __per_cpu_start, ai->static_size);
pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
}
}
/* base address is now known, determine group base offsets */
for (group = 0; group < ai->nr_groups; group++) {
ai->groups[group].base_offset = areas[group] - base;
}
pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n",
PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
pcpu_setup_first_chunk(ai, base);
goto out_free;
out_free_areas:
for (group = 0; group < ai->nr_groups; group++)
if (areas[group])
pcpu_fc_free(areas[group],
ai->groups[group].nr_units * ai->unit_size);
out_free:
pcpu_free_alloc_info(ai);
if (areas)
memblock_free(areas, areas_size);
return rc;
}
#endif /* BUILD_EMBED_FIRST_CHUNK */
#ifdef BUILD_PAGE_FIRST_CHUNK
#include <asm/pgalloc.h>
#ifndef P4D_TABLE_SIZE
#define P4D_TABLE_SIZE PAGE_SIZE
#endif
#ifndef PUD_TABLE_SIZE
#define PUD_TABLE_SIZE PAGE_SIZE
#endif
#ifndef PMD_TABLE_SIZE
#define PMD_TABLE_SIZE PAGE_SIZE
#endif
#ifndef PTE_TABLE_SIZE
#define PTE_TABLE_SIZE PAGE_SIZE
#endif
void __init __weak pcpu_populate_pte(unsigned long addr)
{
pgd_t *pgd = pgd_offset_k(addr);
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
if (pgd_none(*pgd)) {
p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
pgd_populate(&init_mm, pgd, p4d);
}
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d)) {
pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
p4d_populate(&init_mm, p4d, pud);
}
pud = pud_offset(p4d, addr);
if (pud_none(*pud)) {
pmd = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
pud_populate(&init_mm, pud, pmd);
}
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd)) {
pte_t *new;
new = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
pmd_populate_kernel(&init_mm, pmd, new);
}
return;
}
/**
* pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
* @reserved_size: the size of reserved percpu area in bytes
* @cpu_to_nd_fn: callback to convert cpu to it's node, optional
*
* This is a helper to ease setting up page-remapped first percpu
* chunk and can be called where pcpu_setup_first_chunk() is expected.
*
* This is the basic allocator. Static percpu area is allocated
* page-by-page into vmalloc area.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
static struct vm_struct vm;
struct pcpu_alloc_info *ai;
char psize_str[16];
int unit_pages;
size_t pages_size;
struct page **pages;
int unit, i, j, rc = 0;
int upa;
int nr_g0_units;
snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);
ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL);
if (IS_ERR(ai))
return PTR_ERR(ai);
BUG_ON(ai->nr_groups != 1);
upa = ai->alloc_size/ai->unit_size;
nr_g0_units = roundup(num_possible_cpus(), upa);
if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) {
pcpu_free_alloc_info(ai);
return -EINVAL;
}
unit_pages = ai->unit_size >> PAGE_SHIFT;
/* unaligned allocations can't be freed, round up to page size */
pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
sizeof(pages[0]));
pages = memblock_alloc_or_panic(pages_size, SMP_CACHE_BYTES);
/* allocate pages */
j = 0;
for (unit = 0; unit < num_possible_cpus(); unit++) {
unsigned int cpu = ai->groups[0].cpu_map[unit];
for (i = 0; i < unit_pages; i++) {
void *ptr;
ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn);
if (!ptr) {
pr_warn("failed to allocate %s page for cpu%u\n",
psize_str, cpu);
goto enomem;
}
/* kmemleak tracks the percpu allocations separately */
kmemleak_ignore_phys(__pa(ptr));
pages[j++] = virt_to_page(ptr);
}
}
/* allocate vm area, map the pages and copy static data */
vm.flags = VM_ALLOC;
vm.size = num_possible_cpus() * ai->unit_size;
vm_area_register_early(&vm, PAGE_SIZE);
for (unit = 0; unit < num_possible_cpus(); unit++) {
unsigned long unit_addr =
(unsigned long)vm.addr + unit * ai->unit_size;
for (i = 0; i < unit_pages; i++)
pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT));
/* pte already populated, the following shouldn't fail */
rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages],
unit_pages);
if (rc < 0)
panic("failed to map percpu area, err=%d\n", rc);
flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
/* copy static data */
memcpy((void *)unit_addr, __per_cpu_start, ai->static_size);
}
/* we're ready, commit */
pr_info("%d %s pages/cpu s%zu r%zu d%zu\n",
unit_pages, psize_str, ai->static_size,
ai->reserved_size, ai->dyn_size);
pcpu_setup_first_chunk(ai, vm.addr);
goto out_free_ar;
enomem:
while (--j >= 0)
pcpu_fc_free(page_address(pages[j]), PAGE_SIZE);
rc = -ENOMEM;
out_free_ar:
memblock_free(pages, pages_size);
pcpu_free_alloc_info(ai);
return rc;
}
#endif /* BUILD_PAGE_FIRST_CHUNK */
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
/*
* Generic SMP percpu area setup.
*
* The embedding helper is used because its behavior closely resembles
* the original non-dynamic generic percpu area setup. This is
* important because many archs have addressing restrictions and might
* fail if the percpu area is located far away from the previous
* location. As an added bonus, in non-NUMA cases, embedding is
* generally a good idea TLB-wise because percpu area can piggy back
* on the physical linear memory mapping which uses large page
* mappings on applicable archs.
*/
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
unsigned int cpu;
int rc;
/*
* Always reserve area for module percpu variables. That's
* what the legacy allocator did.
*/
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE,
PAGE_SIZE, NULL, NULL);
if (rc < 0)
panic("Failed to initialize percpu areas.");
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu)
__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
}
#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
#else /* CONFIG_SMP */
/*
* UP percpu area setup.
*
* UP always uses km-based percpu allocator with identity mapping.
* Static percpu variables are indistinguishable from the usual static
* variables and don't require any special preparation.
*/
void __init setup_per_cpu_areas(void)
{
const size_t unit_size =
roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
PERCPU_DYNAMIC_RESERVE));
struct pcpu_alloc_info *ai;
void *fc;
ai = pcpu_alloc_alloc_info(1, 1);
fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
if (!ai || !fc)
panic("Failed to allocate memory for percpu areas.");
/* kmemleak tracks the percpu allocations separately */
kmemleak_ignore_phys(__pa(fc));
ai->dyn_size = unit_size;
ai->unit_size = unit_size;
ai->atom_size = unit_size;
ai->alloc_size = unit_size;
ai->groups[0].nr_units = 1;
ai->groups[0].cpu_map[0] = 0;
pcpu_setup_first_chunk(ai, fc);
pcpu_free_alloc_info(ai);
}
#endif /* CONFIG_SMP */
/*
* pcpu_nr_pages - calculate total number of populated backing pages
*
* This reflects the number of pages populated to back chunks. Metadata is
* excluded in the number exposed in meminfo as the number of backing pages
* scales with the number of cpus and can quickly outweigh the memory used for
* metadata. It also keeps this calculation nice and simple.
*
* RETURNS:
* Total number of populated backing pages in use by the allocator.
*/
unsigned long pcpu_nr_pages(void)
{
return pcpu_nr_populated * pcpu_nr_units;
}
/*
* Percpu allocator is initialized early during boot when neither slab or
* workqueue is available. Plug async management until everything is up
* and running.
*/
static int __init percpu_enable_async(void)
{
pcpu_async_enabled = true;
return 0;
}
subsys_initcall(percpu_enable_async);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Fixmap manipulation code
*/
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/libfdt.h>
#include <linux/memory.h>
#include <linux/mm.h>
#include <linux/sizes.h>
#include <asm/fixmap.h>
#include <asm/kernel-pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
/* ensure that the fixmap region does not grow down into the PCI I/O region */
static_assert(FIXADDR_TOT_START > PCI_IO_END);
#define NR_BM_PTE_TABLES \
SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT)
#define NR_BM_PMD_TABLES \
SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT)
static_assert(NR_BM_PMD_TABLES == 1);
#define __BM_TABLE_IDX(addr, shift) \
(((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift)))
#define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT)
static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss;
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
static inline pte_t *fixmap_pte(unsigned long addr)
{
return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)];
}
static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr)
{
pmd_t pmd = READ_ONCE(*pmdp);
pte_t *ptep;
if (pmd_none(pmd)) {
ptep = bm_pte[BM_PTE_TABLE_IDX(addr)];
__pmd_populate(pmdp, __pa_symbol(ptep),
PMD_TYPE_TABLE | PMD_TABLE_AF);
}
}
static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr,
unsigned long end)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
pmd_t *pmdp;
if (pud_none(pud))
__pud_populate(pudp, __pa_symbol(bm_pmd),
PUD_TYPE_TABLE | PUD_TABLE_AF);
pmdp = pmd_offset_kimg(pudp, addr);
do {
next = pmd_addr_end(addr, end);
early_fixmap_init_pte(pmdp, addr);
} while (pmdp++, addr = next, addr != end);
}
static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr,
unsigned long end)
{
p4d_t p4d = READ_ONCE(*p4dp);
pud_t *pudp;
if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) &&
p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) {
/*
* We only end up here if the kernel mapping and the fixmap
* share the top level pgd entry, which should only happen on
* 16k/4 levels configurations.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
}
if (p4d_none(p4d))
__p4d_populate(p4dp, __pa_symbol(bm_pud),
P4D_TYPE_TABLE | P4D_TABLE_AF);
pudp = pud_offset_kimg(p4dp, addr);
early_fixmap_init_pmd(pudp, addr, end);
}
/*
* The p*d_populate functions call virt_to_phys implicitly so they can't be used
* directly on kernel symbols (bm_p*d). This function is called too early to use
* lm_alias so __p*d_populate functions must be used to populate with the
* physical address from __pa_symbol.
*/
void __init early_fixmap_init(void)
{
unsigned long addr = FIXADDR_TOT_START;
unsigned long end = FIXADDR_TOP;
pgd_t *pgdp = pgd_offset_k(addr);
p4d_t *p4dp = p4d_offset_kimg(pgdp, addr);
early_fixmap_init_pud(p4dp, addr, end);
}
/*
* Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we
* ever need to use IPIs for TLB broadcasting, then we're in trouble here.
*/
void __set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags)
{
unsigned long addr = __fix_to_virt(idx);
pte_t *ptep;
BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
ptep = fixmap_pte(addr);
if (pgprot_val(flags)) {
__set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
} else {
__pte_clear(&init_mm, addr, ptep);
flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
}
}
void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
{
const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
phys_addr_t dt_phys_base;
int offset;
void *dt_virt;
/*
* Check whether the physical FDT address is set and meets the minimum
* alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
* at least 8 bytes so that we can always access the magic and size
* fields of the FDT header after mapping the first chunk, double check
* here if that is indeed the case.
*/
BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
return NULL;
dt_phys_base = round_down(dt_phys, PAGE_SIZE);
offset = dt_phys % PAGE_SIZE;
dt_virt = (void *)dt_virt_base + offset;
/* map the first chunk so we can read the size from the header */
create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot);
if (fdt_magic(dt_virt) != FDT_MAGIC)
return NULL;
*size = fdt_totalsize(dt_virt);
if (*size > MAX_FDT_SIZE)
return NULL;
if (offset + *size > PAGE_SIZE) {
create_mapping_noalloc(dt_phys_base, dt_virt_base,
offset + *size, prot);
}
return dt_virt;
}
// SPDX-License-Identifier: GPL-2.0
/*
* Block multiqueue core code
*
* Copyright (C) 2013-2014 Jens Axboe
* Copyright (C) 2013-2014 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/llist.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/topology.h>
#include <linux/sched/signal.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>
#include <linux/blk-crypto.h>
#include <linux/part_stat.h>
#include <linux/sched/isolation.h>
#include <trace/events/block.h>
#include <linux/t10-pi.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-pm.h"
#include "blk-stat.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
static DEFINE_MUTEX(blk_mq_cpuhp_lock);
static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
static void blk_mq_request_bypass_insert(struct request *rq,
blk_insert_t flags);
static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
struct io_comp_batch *iob, unsigned int flags);
/*
* Check if any of the ctx, dispatch list or elevator
* have pending work in this hardware queue.
*/
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
return !list_empty_careful(&hctx->dispatch) ||
sbitmap_any_bit_set(&hctx->ctx_map) ||
blk_mq_sched_has_work(hctx);
}
/*
* Mark this ctx as having pending work in this hardware queue
*/
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
const int bit = ctx->index_hw[hctx->type];
if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit);
}
static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
const int bit = ctx->index_hw[hctx->type];
sbitmap_clear_bit(&hctx->ctx_map, bit);
}
struct mq_inflight {
struct block_device *part;
unsigned int inflight[2];
};
static bool blk_mq_check_inflight(struct request *rq, void *priv)
{
struct mq_inflight *mi = priv;
if (rq->rq_flags & RQF_IO_STAT &&
(!bdev_is_partition(mi->part) || rq->part == mi->part) &&
blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
mi->inflight[rq_data_dir(rq)]++;
return true;
}
unsigned int blk_mq_in_flight(struct request_queue *q,
struct block_device *part)
{
struct mq_inflight mi = { .part = part };
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
return mi.inflight[0] + mi.inflight[1];
}
void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
unsigned int inflight[2])
{
struct mq_inflight mi = { .part = part };
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
inflight[0] = mi.inflight[0];
inflight[1] = mi.inflight[1];
}
#ifdef CONFIG_LOCKDEP
static bool blk_freeze_set_owner(struct request_queue *q,
struct task_struct *owner)
{
if (!owner)
return false;
if (!q->mq_freeze_depth) {
q->mq_freeze_owner = owner;
q->mq_freeze_owner_depth = 1;
q->mq_freeze_disk_dead = !q->disk ||
test_bit(GD_DEAD, &q->disk->state) ||
!blk_queue_registered(q);
q->mq_freeze_queue_dying = blk_queue_dying(q);
return true;
}
if (owner == q->mq_freeze_owner)
q->mq_freeze_owner_depth += 1;
return false;
}
/* verify the last unfreeze in owner context */
static bool blk_unfreeze_check_owner(struct request_queue *q)
{
if (q->mq_freeze_owner != current)
return false;
if (--q->mq_freeze_owner_depth == 0) {
q->mq_freeze_owner = NULL;
return true;
}
return false;
}
#else
static bool blk_freeze_set_owner(struct request_queue *q,
struct task_struct *owner)
{
return false;
}
static bool blk_unfreeze_check_owner(struct request_queue *q)
{
return false;
}
#endif
bool __blk_freeze_queue_start(struct request_queue *q,
struct task_struct *owner)
{
bool freeze;
mutex_lock(&q->mq_freeze_lock);
freeze = blk_freeze_set_owner(q, owner);
if (++q->mq_freeze_depth == 1) {
percpu_ref_kill(&q->q_usage_counter);
mutex_unlock(&q->mq_freeze_lock);
if (queue_is_mq(q))
blk_mq_run_hw_queues(q, false);
} else {
mutex_unlock(&q->mq_freeze_lock);
}
return freeze;
}
void blk_freeze_queue_start(struct request_queue *q)
{
if (__blk_freeze_queue_start(q, current))
blk_freeze_acquire_lock(q);
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
void blk_mq_freeze_queue_wait(struct request_queue *q)
{
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout)
{
return wait_event_timeout(q->mq_freeze_wq,
percpu_ref_is_zero(&q->q_usage_counter),
timeout);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
void blk_mq_freeze_queue_nomemsave(struct request_queue *q)
{
blk_freeze_queue_start(q);
blk_mq_freeze_queue_wait(q);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave);
bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
{
bool unfreeze;
mutex_lock(&q->mq_freeze_lock);
if (force_atomic)
q->q_usage_counter.data->force_atomic = true;
q->mq_freeze_depth--;
WARN_ON_ONCE(q->mq_freeze_depth < 0);
if (!q->mq_freeze_depth) {
percpu_ref_resurrect(&q->q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
unfreeze = blk_unfreeze_check_owner(q);
mutex_unlock(&q->mq_freeze_lock);
return unfreeze;
}
void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q)
{
if (__blk_mq_unfreeze_queue(q, false))
blk_unfreeze_release_lock(q);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore);
/*
* non_owner variant of blk_freeze_queue_start
*
* Unlike blk_freeze_queue_start, the queue doesn't need to be unfrozen
* by the same task. This is fragile and should not be used if at all
* possible.
*/
void blk_freeze_queue_start_non_owner(struct request_queue *q)
{
__blk_freeze_queue_start(q, NULL);
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start_non_owner);
/* non_owner variant of blk_mq_unfreeze_queue */
void blk_mq_unfreeze_queue_non_owner(struct request_queue *q)
{
__blk_mq_unfreeze_queue(q, false);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_non_owner);
/*
* FIXME: replace the scsi_internal_device_*block_nowait() calls in the
* mpt3sas driver such that this function can be removed.
*/
void blk_mq_quiesce_queue_nowait(struct request_queue *q)
{
unsigned long flags;
spin_lock_irqsave(&q->queue_lock, flags);
if (!q->quiesce_depth++)
blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
spin_unlock_irqrestore(&q->queue_lock, flags);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
/**
* blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done
* @set: tag_set to wait on
*
* Note: it is driver's responsibility for making sure that quiesce has
* been started on or more of the request_queues of the tag_set. This
* function only waits for the quiesce on those request_queues that had
* the quiesce flag set using blk_mq_quiesce_queue_nowait.
*/
void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set)
{
if (set->flags & BLK_MQ_F_BLOCKING)
synchronize_srcu(set->srcu);
else
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done);
/**
* blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
* @q: request queue.
*
* Note: this function does not prevent that the struct request end_io()
* callback function is invoked. Once this function is returned, we make
* sure no dispatch can happen until the queue is unquiesced via
* blk_mq_unquiesce_queue().
*/
void blk_mq_quiesce_queue(struct request_queue *q)
{
blk_mq_quiesce_queue_nowait(q);
/* nothing to wait for non-mq queues */
if (queue_is_mq(q))
blk_mq_wait_quiesce_done(q->tag_set);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
/*
* blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
* @q: request queue.
*
* This function recovers queue into the state before quiescing
* which is done by blk_mq_quiesce_queue.
*/
void blk_mq_unquiesce_queue(struct request_queue *q)
{
unsigned long flags;
bool run_queue = false;
spin_lock_irqsave(&q->queue_lock, flags);
if (WARN_ON_ONCE(q->quiesce_depth <= 0)) {
;
} else if (!--q->quiesce_depth) {
blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
run_queue = true;
}
spin_unlock_irqrestore(&q->queue_lock, flags);
/* dispatch requests which are inserted during quiescing */
if (run_queue)
blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
{
struct request_queue *q;
mutex_lock(&set->tag_list_lock);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
if (!blk_queue_skip_tagset_quiesce(q))
blk_mq_quiesce_queue_nowait(q);
}
mutex_unlock(&set->tag_list_lock);
blk_mq_wait_quiesce_done(set);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset);
void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set)
{
struct request_queue *q;
mutex_lock(&set->tag_list_lock);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
if (!blk_queue_skip_tagset_quiesce(q))
blk_mq_unquiesce_queue(q);
}
mutex_unlock(&set->tag_list_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset);
void blk_mq_wake_waiters(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i)
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_wakeup_all(hctx->tags, true);
}
void blk_rq_init(struct request_queue *q, struct request *rq)
{
memset(rq, 0, sizeof(*rq));
INIT_LIST_HEAD(&rq->queuelist);
rq->q = q;
rq->__sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->tag = BLK_MQ_NO_TAG;
rq->internal_tag = BLK_MQ_NO_TAG;
rq->start_time_ns = blk_time_get_ns();
blk_crypto_rq_set_defaults(rq);
}
EXPORT_SYMBOL(blk_rq_init);
/* Set start and alloc time when the allocated request is actually used */
static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
{
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
if (blk_queue_rq_alloc_time(rq->q))
rq->alloc_time_ns = alloc_time_ns;
else
rq->alloc_time_ns = 0;
#endif
}
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
struct blk_mq_tags *tags, unsigned int tag)
{
struct blk_mq_ctx *ctx = data->ctx;
struct blk_mq_hw_ctx *hctx = data->hctx;
struct request_queue *q = data->q;
struct request *rq = tags->static_rqs[tag];
rq->q = q;
rq->mq_ctx = ctx;
rq->mq_hctx = hctx;
rq->cmd_flags = data->cmd_flags;
if (data->flags & BLK_MQ_REQ_PM)
data->rq_flags |= RQF_PM;
rq->rq_flags = data->rq_flags;
if (data->rq_flags & RQF_SCHED_TAGS) {
rq->tag = BLK_MQ_NO_TAG;
rq->internal_tag = tag;
} else {
rq->tag = tag;
rq->internal_tag = BLK_MQ_NO_TAG;
}
rq->timeout = 0;
rq->part = NULL;
rq->io_start_time_ns = 0;
rq->stats_sectors = 0;
rq->nr_phys_segments = 0;
rq->nr_integrity_segments = 0;
rq->end_io = NULL;
rq->end_io_data = NULL;
blk_crypto_rq_set_defaults(rq);
INIT_LIST_HEAD(&rq->queuelist);
/* tag was already set */
WRITE_ONCE(rq->deadline, 0);
req_ref_set(rq, 1);
if (rq->rq_flags & RQF_USE_SCHED) {
struct elevator_queue *e = data->q->elevator;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
if (e->type->ops.prepare_request)
e->type->ops.prepare_request(rq);
}
return rq;
}
static inline struct request *
__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
{
unsigned int tag, tag_offset;
struct blk_mq_tags *tags;
struct request *rq;
unsigned long tag_mask;
int i, nr = 0;
tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
if (unlikely(!tag_mask))
return NULL;
tags = blk_mq_tags_from_data(data);
for (i = 0; tag_mask; i++) {
if (!(tag_mask & (1UL << i)))
continue;
tag = tag_offset + i;
prefetch(tags->static_rqs[tag]);
tag_mask &= ~(1UL << i);
rq = blk_mq_rq_ctx_init(data, tags, tag);
rq_list_add_head(data->cached_rqs, rq);
nr++;
}
if (!(data->rq_flags & RQF_SCHED_TAGS))
blk_mq_add_active_requests(data->hctx, nr);
/* caller already holds a reference, add for remainder */
percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
data->nr_tags -= nr;
return rq_list_pop(data->cached_rqs);
}
static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
{
struct request_queue *q = data->q;
u64 alloc_time_ns = 0;
struct request *rq;
unsigned int tag;
/* alloc_time includes depth and tag waits */
if (blk_queue_rq_alloc_time(q))
alloc_time_ns = blk_time_get_ns();
if (data->cmd_flags & REQ_NOWAIT)
data->flags |= BLK_MQ_REQ_NOWAIT;
retry:
data->ctx = blk_mq_get_ctx(q);
data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx);
if (q->elevator) {
/*
* All requests use scheduler tags when an I/O scheduler is
* enabled for the queue.
*/
data->rq_flags |= RQF_SCHED_TAGS;
/*
* Flush/passthrough requests are special and go directly to the
* dispatch list.
*/
if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH &&
!blk_op_is_passthrough(data->cmd_flags)) {
struct elevator_mq_ops *ops = &q->elevator->type->ops;
WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED);
data->rq_flags |= RQF_USE_SCHED;
if (ops->limit_depth)
ops->limit_depth(data->cmd_flags, data);
}
} else {
blk_mq_tag_busy(data->hctx);
}
if (data->flags & BLK_MQ_REQ_RESERVED)
data->rq_flags |= RQF_RESV;
/*
* Try batched alloc if we want more than 1 tag.
*/
if (data->nr_tags > 1) {
rq = __blk_mq_alloc_requests_batch(data);
if (rq) {
blk_mq_rq_time_init(rq, alloc_time_ns);
return rq;
}
data->nr_tags = 1;
}
/*
* Waiting allocations only fail because of an inactive hctx. In that
* case just retry the hctx assignment and tag allocation as CPU hotplug
* should have migrated us to an online CPU by now.
*/
tag = blk_mq_get_tag(data);
if (tag == BLK_MQ_NO_TAG) {
if (data->flags & BLK_MQ_REQ_NOWAIT)
return NULL;
/*
* Give up the CPU and sleep for a random short time to
* ensure that thread using a realtime scheduling class
* are migrated off the CPU, and thus off the hctx that
* is going away.
*/
msleep(3);
goto retry;
}
if (!(data->rq_flags & RQF_SCHED_TAGS))
blk_mq_inc_active_requests(data->hctx);
rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
blk_mq_rq_time_init(rq, alloc_time_ns);
return rq;
}
static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
struct blk_plug *plug,
blk_opf_t opf,
blk_mq_req_flags_t flags)
{
struct blk_mq_alloc_data data = {
.q = q,
.flags = flags,
.cmd_flags = opf,
.nr_tags = plug->nr_ios,
.cached_rqs = &plug->cached_rqs,
};
struct request *rq;
if (blk_queue_enter(q, flags))
return NULL;
plug->nr_ios = 1;
rq = __blk_mq_alloc_requests(&data);
if (unlikely(!rq))
blk_queue_exit(q);
return rq;
}
static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
blk_opf_t opf,
blk_mq_req_flags_t flags)
{
struct blk_plug *plug = current->plug;
struct request *rq;
if (!plug)
return NULL;
if (rq_list_empty(&plug->cached_rqs)) {
if (plug->nr_ios == 1)
return NULL;
rq = blk_mq_rq_cache_fill(q, plug, opf, flags);
if (!rq)
return NULL;
} else {
rq = rq_list_peek(&plug->cached_rqs);
if (!rq || rq->q != q)
return NULL;
if (blk_mq_get_hctx_type(opf) != rq->mq_hctx->type)
return NULL;
if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
return NULL;
rq_list_pop(&plug->cached_rqs);
blk_mq_rq_time_init(rq, blk_time_get_ns());
}
rq->cmd_flags = opf;
INIT_LIST_HEAD(&rq->queuelist);
return rq;
}
struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
blk_mq_req_flags_t flags)
{
struct request *rq;
rq = blk_mq_alloc_cached_request(q, opf, flags);
if (!rq) {
struct blk_mq_alloc_data data = {
.q = q,
.flags = flags,
.cmd_flags = opf,
.nr_tags = 1,
};
int ret;
ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
rq = __blk_mq_alloc_requests(&data);
if (!rq)
goto out_queue_exit;
}
rq->__data_len = 0;
rq->__sector = (sector_t) -1;
rq->bio = rq->biotail = NULL;
return rq;
out_queue_exit:
blk_queue_exit(q);
return ERR_PTR(-EWOULDBLOCK);
}
EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx)
{
struct blk_mq_alloc_data data = {
.q = q,
.flags = flags,
.cmd_flags = opf,
.nr_tags = 1,
};
u64 alloc_time_ns = 0;
struct request *rq;
unsigned int cpu;
unsigned int tag;
int ret;
/* alloc_time includes depth and tag waits */
if (blk_queue_rq_alloc_time(q))
alloc_time_ns = blk_time_get_ns();
/*
* If the tag allocator sleeps we could get an allocation for a
* different hardware context. No need to complicate the low level
* allocator for this for the rare use case of a command tied to
* a specific queue.
*/
if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) ||
WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED)))
return ERR_PTR(-EINVAL);
if (hctx_idx >= q->nr_hw_queues)
return ERR_PTR(-EIO);
ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
/*
* Check if the hardware context is actually mapped to anything.
* If not tell the caller that it should skip this queue.
*/
ret = -EXDEV;
data.hctx = xa_load(&q->hctx_table, hctx_idx);
if (!blk_mq_hw_queue_mapped(data.hctx))
goto out_queue_exit;
cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
if (cpu >= nr_cpu_ids)
goto out_queue_exit;
data.ctx = __blk_mq_get_ctx(q, cpu);
if (q->elevator)
data.rq_flags |= RQF_SCHED_TAGS;
else
blk_mq_tag_busy(data.hctx);
if (flags & BLK_MQ_REQ_RESERVED)
data.rq_flags |= RQF_RESV;
ret = -EWOULDBLOCK;
tag = blk_mq_get_tag(&data);
if (tag == BLK_MQ_NO_TAG)
goto out_queue_exit;
if (!(data.rq_flags & RQF_SCHED_TAGS))
blk_mq_inc_active_requests(data.hctx);
rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
blk_mq_rq_time_init(rq, alloc_time_ns);
rq->__data_len = 0;
rq->__sector = (sector_t) -1;
rq->bio = rq->biotail = NULL;
return rq;
out_queue_exit:
blk_queue_exit(q);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
static void blk_mq_finish_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_zone_finish_request(rq);
if (rq->rq_flags & RQF_USE_SCHED) {
q->elevator->type->ops.finish_request(rq);
/*
* For postflush request that may need to be
* completed twice, we should clear this flag
* to avoid double finish_request() on the rq.
*/
rq->rq_flags &= ~RQF_USE_SCHED;
}
}
static void __blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
const int sched_tag = rq->internal_tag;
blk_crypto_free_request(rq);
blk_pm_mark_last_busy(rq);
rq->mq_hctx = NULL;
if (rq->tag != BLK_MQ_NO_TAG) {
blk_mq_dec_active_requests(hctx);
blk_mq_put_tag(hctx->tags, ctx, rq->tag);
}
if (sched_tag != BLK_MQ_NO_TAG)
blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
void blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_mq_finish_request(rq);
if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
laptop_io_completion(q->disk->bdi);
rq_qos_done(q, rq);
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
if (req_ref_put_and_test(rq))
__blk_mq_free_request(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
void blk_mq_free_plug_rqs(struct blk_plug *plug)
{
struct request *rq;
while ((rq = rq_list_pop(&plug->cached_rqs)) != NULL)
blk_mq_free_request(rq);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
{
printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
rq->q->disk ? rq->q->disk->disk_name : "?",
(__force unsigned long long) rq->cmd_flags);
printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n",
(unsigned long long)blk_rq_pos(rq),
blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
printk(KERN_INFO " bio %p, biotail %p, len %u\n",
rq->bio, rq->biotail, blk_rq_bytes(rq));
}
EXPORT_SYMBOL(blk_dump_rq_flags);
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (req->rq_flags & RQF_IO_STAT) {
const int sgrp = op_stat_group(req_op(req));
part_stat_lock();
part_stat_add(req->part, sectors[sgrp], bytes >> 9);
part_stat_unlock();
}
}
static void blk_print_req_error(struct request *req, blk_status_t status)
{
printk_ratelimited(KERN_ERR
"%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
"phys_seg %u prio class %u\n",
blk_status_to_str(status),
req->q->disk ? req->q->disk->disk_name : "?",
blk_rq_pos(req), (__force u32)req_op(req),
blk_op_str(req_op(req)),
(__force u32)(req->cmd_flags & ~REQ_OP_MASK),
req->nr_phys_segments,
IOPRIO_PRIO_CLASS(req_get_ioprio(req)));
}
/*
* Fully end IO on a request. Does not support partial completions, or
* errors.
*/
static void blk_complete_request(struct request *req)
{
const bool is_flush = (req->rq_flags & RQF_FLUSH_SEQ) != 0;
int total_bytes = blk_rq_bytes(req);
struct bio *bio = req->bio;
trace_block_rq_complete(req, BLK_STS_OK, total_bytes);
if (!bio)
return;
if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ)
blk_integrity_complete(req, total_bytes);
/*
* Upper layers may call blk_crypto_evict_key() anytime after the last
* bio_endio(). Therefore, the keyslot must be released before that.
*/
blk_crypto_rq_put_keyslot(req);
blk_account_io_completion(req, total_bytes);
do {
struct bio *next = bio->bi_next;
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
blk_zone_update_request_bio(req, bio);
if (!is_flush)
bio_endio(bio);
bio = next;
} while (bio);
/*
* Reset counters so that the request stacking driver
* can find how many bytes remain in the request
* later.
*/
if (!req->end_io) {
req->bio = NULL;
req->__data_len = 0;
}
}
/**
* blk_update_request - Complete multiple bytes without completing the request
* @req: the request being processed
* @error: block status code
* @nr_bytes: number of bytes to complete for @req
*
* Description:
* Ends I/O on a number of bytes attached to @req, but doesn't complete
* the request structure even if @req doesn't have leftover.
* If @req has leftover, sets it up for the next range of segments.
*
* Passing the result of blk_rq_bytes() as @nr_bytes guarantees
* %false return from this function.
*
* Note:
* The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function
* except in the consistency check at the end of this function.
*
* Return:
* %false - this request doesn't have any more data
* %true - this request has more data
**/
bool blk_update_request(struct request *req, blk_status_t error,
unsigned int nr_bytes)
{
bool is_flush = req->rq_flags & RQF_FLUSH_SEQ;
bool quiet = req->rq_flags & RQF_QUIET;
int total_bytes;
trace_block_rq_complete(req, error, nr_bytes);
if (!req->bio)
return false;
if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
error == BLK_STS_OK)
blk_integrity_complete(req, nr_bytes);
/*
* Upper layers may call blk_crypto_evict_key() anytime after the last
* bio_endio(). Therefore, the keyslot must be released before that.
*/
if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
__blk_crypto_rq_put_keyslot(req);
if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) &&
!test_bit(GD_DEAD, &req->q->disk->state)) {
blk_print_req_error(req, error);
trace_block_rq_error(req, error, nr_bytes);
}
blk_account_io_completion(req, nr_bytes);
total_bytes = 0;
while (req->bio) {
struct bio *bio = req->bio;
unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
if (unlikely(error))
bio->bi_status = error;
if (bio_bytes == bio->bi_iter.bi_size) {
req->bio = bio->bi_next;
} else if (bio_is_zone_append(bio) && error == BLK_STS_OK) {
/*
* Partial zone append completions cannot be supported
* as the BIO fragments may end up not being written
* sequentially.
*/
bio->bi_status = BLK_STS_IOERR;
}
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
if (unlikely(quiet))
bio_set_flag(bio, BIO_QUIET);
bio_advance(bio, bio_bytes);
/* Don't actually finish bio if it's part of flush sequence */
if (!bio->bi_iter.bi_size) {
blk_zone_update_request_bio(req, bio);
if (!is_flush)
bio_endio(bio);
}
total_bytes += bio_bytes;
nr_bytes -= bio_bytes;
if (!nr_bytes)
break;
}
/*
* completely done
*/
if (!req->bio) {
/*
* Reset counters so that the request stacking driver
* can find how many bytes remain in the request
* later.
*/
req->__data_len = 0;
return false;
}
req->__data_len -= total_bytes;
/* update sector only for requests with clear definition of sector */
if (!blk_rq_is_passthrough(req))
req->__sector += total_bytes >> 9;
/* mixed attributes always follow the first bio */
if (req->rq_flags & RQF_MIXED_MERGE) {
req->cmd_flags &= ~REQ_FAILFAST_MASK;
req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
}
if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
}
/* recalculate the number of segments */
req->nr_phys_segments = blk_recalc_rq_segments(req);
}
return true;
}
EXPORT_SYMBOL_GPL(blk_update_request);
static inline void blk_account_io_done(struct request *req, u64 now)
{
trace_block_io_done(req);
/*
* Account IO completion. flush_rq isn't accounted as a
* normal IO on queueing nor completion. Accounting the
* containing request is enough.
*/
if ((req->rq_flags & (RQF_IO_STAT|RQF_FLUSH_SEQ)) == RQF_IO_STAT) {
const int sgrp = op_stat_group(req_op(req));
part_stat_lock();
update_io_ticks(req->part, jiffies, true);
part_stat_inc(req->part, ios[sgrp]);
part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
part_stat_local_dec(req->part,
in_flight[op_is_write(req_op(req))]);
part_stat_unlock();
}
}
static inline bool blk_rq_passthrough_stats(struct request *req)
{
struct bio *bio = req->bio;
if (!blk_queue_passthrough_stat(req->q))
return false;
/* Requests without a bio do not transfer data. */
if (!bio)
return false;
/*
* Stats are accumulated in the bdev, so must have one attached to a
* bio to track stats. Most drivers do not set the bdev for passthrough
* requests, but nvme is one that will set it.
*/
if (!bio->bi_bdev)
return false;
/*
* We don't know what a passthrough command does, but we know the
* payload size and data direction. Ensuring the size is aligned to the
* block size filters out most commands with payloads that don't
* represent sector access.
*/
if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1))
return false;
return true;
}
static inline void blk_account_io_start(struct request *req)
{
trace_block_io_start(req);
if (!blk_queue_io_stat(req->q))
return;
if (blk_rq_is_passthrough(req) && !blk_rq_passthrough_stats(req))
return;
req->rq_flags |= RQF_IO_STAT;
req->start_time_ns = blk_time_get_ns();
/*
* All non-passthrough requests are created from a bio with one
* exception: when a flush command that is part of a flush sequence
* generated by the state machine in blk-flush.c is cloned onto the
* lower device by dm-multipath we can get here without a bio.
*/
if (req->bio)
req->part = req->bio->bi_bdev;
else
req->part = req->q->disk->part0;
part_stat_lock();
update_io_ticks(req->part, jiffies, false);
part_stat_local_inc(req->part, in_flight[op_is_write(req_op(req))]);
part_stat_unlock();
}
static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
{
if (rq->rq_flags & RQF_STATS)
blk_stat_add(rq, now);
blk_mq_sched_completed_request(rq, now);
blk_account_io_done(rq, now);
}
inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
if (blk_mq_need_time_stamp(rq))
__blk_mq_end_request_acct(rq, blk_time_get_ns());
blk_mq_finish_request(rq);
if (rq->end_io) {
rq_qos_done(rq->q, rq);
if (rq->end_io(rq, error) == RQ_END_IO_FREE)
blk_mq_free_request(rq);
} else {
blk_mq_free_request(rq);
}
}
EXPORT_SYMBOL(__blk_mq_end_request);
void blk_mq_end_request(struct request *rq, blk_status_t error)
{
if (blk_update_request(rq, error, blk_rq_bytes(rq)))
BUG();
__blk_mq_end_request(rq, error);
}
EXPORT_SYMBOL(blk_mq_end_request);
#define TAG_COMP_BATCH 32
static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
int *tag_array, int nr_tags)
{
struct request_queue *q = hctx->queue;
blk_mq_sub_active_requests(hctx, nr_tags);
blk_mq_put_tags(hctx->tags, tag_array, nr_tags);
percpu_ref_put_many(&q->q_usage_counter, nr_tags);
}
void blk_mq_end_request_batch(struct io_comp_batch *iob)
{
int tags[TAG_COMP_BATCH], nr_tags = 0;
struct blk_mq_hw_ctx *cur_hctx = NULL;
struct request *rq;
u64 now = 0;
if (iob->need_ts)
now = blk_time_get_ns();
while ((rq = rq_list_pop(&iob->req_list)) != NULL) {
prefetch(rq->bio);
prefetch(rq->rq_next);
blk_complete_request(rq);
if (iob->need_ts)
__blk_mq_end_request_acct(rq, now);
blk_mq_finish_request(rq);
rq_qos_done(rq->q, rq);
/*
* If end_io handler returns NONE, then it still has
* ownership of the request.
*/
if (rq->end_io && rq->end_io(rq, 0) == RQ_END_IO_NONE)
continue;
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
if (!req_ref_put_and_test(rq))
continue;
blk_crypto_free_request(rq);
blk_pm_mark_last_busy(rq);
if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) {
if (cur_hctx)
blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
nr_tags = 0;
cur_hctx = rq->mq_hctx;
}
tags[nr_tags++] = rq->tag;
}
if (nr_tags)
blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
}
EXPORT_SYMBOL_GPL(blk_mq_end_request_batch);
static void blk_complete_reqs(struct llist_head *list)
{
struct llist_node *entry = llist_reverse_order(llist_del_all(list));
struct request *rq, *next;
llist_for_each_entry_safe(rq, next, entry, ipi_list)
rq->q->mq_ops->complete(rq);
}
static __latent_entropy void blk_done_softirq(void)
{
blk_complete_reqs(this_cpu_ptr(&blk_cpu_done));
}
static int blk_softirq_cpu_dead(unsigned int cpu)
{
blk_complete_reqs(&per_cpu(blk_cpu_done, cpu));
return 0;
}
static void __blk_mq_complete_request_remote(void *data)
{
__raise_softirq_irqoff(BLOCK_SOFTIRQ);
}
static inline bool blk_mq_complete_need_ipi(struct request *rq)
{
int cpu = raw_smp_processor_id();
if (!IS_ENABLED(CONFIG_SMP) ||
!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
return false;
/*
* With force threaded interrupts enabled, raising softirq from an SMP
* function call will always result in waking the ksoftirqd thread.
* This is probably worse than completing the request on a different
* cache domain.
*/
if (force_irqthreads())
return false;
/* same CPU or cache domain and capacity? Complete locally */
if (cpu == rq->mq_ctx->cpu ||
(!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
cpus_share_cache(cpu, rq->mq_ctx->cpu) &&
cpus_equal_capacity(cpu, rq->mq_ctx->cpu)))
return false;
/* don't try to IPI to an offline CPU */
return cpu_online(rq->mq_ctx->cpu);
}
static void blk_mq_complete_send_ipi(struct request *rq)
{
unsigned int cpu;
cpu = rq->mq_ctx->cpu;
if (llist_add(&rq->ipi_list, &per_cpu(blk_cpu_done, cpu)))
smp_call_function_single_async(cpu, &per_cpu(blk_cpu_csd, cpu));
}
static void blk_mq_raise_softirq(struct request *rq)
{
struct llist_head *list;
preempt_disable();
list = this_cpu_ptr(&blk_cpu_done);
if (llist_add(&rq->ipi_list, list))
raise_softirq(BLOCK_SOFTIRQ);
preempt_enable();
}
bool blk_mq_complete_request_remote(struct request *rq)
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
/*
* For request which hctx has only one ctx mapping,
* or a polled request, always complete locally,
* it's pointless to redirect the completion.
*/
if ((rq->mq_hctx->nr_ctx == 1 &&
rq->mq_ctx->cpu == raw_smp_processor_id()) ||
rq->cmd_flags & REQ_POLLED)
return false;
if (blk_mq_complete_need_ipi(rq)) {
blk_mq_complete_send_ipi(rq);
return true;
}
if (rq->q->nr_hw_queues == 1) {
blk_mq_raise_softirq(rq);
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote);
/**
* blk_mq_complete_request - end I/O on a request
* @rq: the request being processed
*
* Description:
* Complete a request by scheduling the ->complete_rq operation.
**/
void blk_mq_complete_request(struct request *rq)
{
if (!blk_mq_complete_request_remote(rq))
rq->q->mq_ops->complete(rq);
}
EXPORT_SYMBOL(blk_mq_complete_request);
/**
* blk_mq_start_request - Start processing a request
* @rq: Pointer to request to be started
*
* Function used by device drivers to notify the block layer that a request
* is going to be processed now, so blk layer can do proper initializations
* such as starting the timeout timer.
*/
void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
trace_block_rq_issue(rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
!blk_rq_is_passthrough(rq)) {
rq->io_start_time_ns = blk_time_get_ns();
rq->stats_sectors = blk_rq_sectors(rq);
rq->rq_flags |= RQF_STATS;
rq_qos_issue(q, rq);
}
WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
blk_add_timer(rq);
WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
rq->mq_hctx->tags->rqs[rq->tag] = rq;
if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
blk_integrity_prepare(rq);
if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num);
}
EXPORT_SYMBOL(blk_mq_start_request);
/*
* Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
* queues. This is important for md arrays to benefit from merging
* requests.
*/
static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
{
if (plug->multiple_queues)
return BLK_MAX_REQUEST_COUNT * 2;
return BLK_MAX_REQUEST_COUNT;
}
static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
{
struct request *last = rq_list_peek(&plug->mq_list);
if (!plug->rq_count) {
trace_block_plug(rq->q);
} else if (plug->rq_count >= blk_plug_max_rq_count(plug) ||
(!blk_queue_nomerges(rq->q) &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_mq_flush_plug_list(plug, false);
last = NULL;
trace_block_plug(rq->q);
}
if (!plug->multiple_queues && last && last->q != rq->q)
plug->multiple_queues = true;
/*
* Any request allocated from sched tags can't be issued to
* ->queue_rqs() directly
*/
if (!plug->has_elevator && (rq->rq_flags & RQF_SCHED_TAGS))
plug->has_elevator = true;
rq_list_add_tail(&plug->mq_list, rq);
plug->rq_count++;
}
/**
* blk_execute_rq_nowait - insert a request to I/O scheduler for execution
* @rq: request to insert
* @at_head: insert request at head or tail of queue
*
* Description:
* Insert a fully prepared request at the back of the I/O scheduler queue
* for execution. Don't wait for completion.
*
* Note:
* This function will invoke @done directly if the queue is dead.
*/
void blk_execute_rq_nowait(struct request *rq, bool at_head)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
WARN_ON(irqs_disabled());
WARN_ON(!blk_rq_is_passthrough(rq));
blk_account_io_start(rq);
if (current->plug && !at_head) {
blk_add_rq_to_plug(current->plug, rq);
return;
}
blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING);
}
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
struct blk_rq_wait {
struct completion done;
blk_status_t ret;
};
static enum rq_end_io_ret blk_end_sync_rq(struct request *rq, blk_status_t ret)
{
struct blk_rq_wait *wait = rq->end_io_data;
wait->ret = ret;
complete(&wait->done);
return RQ_END_IO_NONE;
}
bool blk_rq_is_poll(struct request *rq)
{
if (!rq->mq_hctx)
return false;
if (rq->mq_hctx->type != HCTX_TYPE_POLL)
return false;
return true;
}
EXPORT_SYMBOL_GPL(blk_rq_is_poll);
static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
{
do {
blk_hctx_poll(rq->q, rq->mq_hctx, NULL, 0);
cond_resched();
} while (!completion_done(wait));
}
/**
* blk_execute_rq - insert a request into queue for execution
* @rq: request to insert
* @at_head: insert request at head or tail of queue
*
* Description:
* Insert a fully prepared request at the back of the I/O scheduler queue
* for execution and wait for completion.
* Return: The blk_status_t result provided to blk_mq_end_request().
*/
blk_status_t blk_execute_rq(struct request *rq, bool at_head)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
struct blk_rq_wait wait = {
.done = COMPLETION_INITIALIZER_ONSTACK(wait.done),
};
WARN_ON(irqs_disabled());
WARN_ON(!blk_rq_is_passthrough(rq));
rq->end_io_data = &wait;
rq->end_io = blk_end_sync_rq;
blk_account_io_start(rq);
blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
blk_mq_run_hw_queue(hctx, false);
if (blk_rq_is_poll(rq))
blk_rq_poll_completion(rq, &wait.done);
else
blk_wait_io(&wait.done);
return wait.ret;
}
EXPORT_SYMBOL(blk_execute_rq);
static void __blk_mq_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_mq_put_driver_tag(rq);
trace_block_rq_requeue(rq);
rq_qos_requeue(q, rq);
if (blk_mq_request_started(rq)) {
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
rq->rq_flags &= ~RQF_TIMED_OUT;
}
}
void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
{
struct request_queue *q = rq->q;
unsigned long flags;
__blk_mq_requeue_request(rq);
/* this request will be re-inserted to io scheduler queue */
blk_mq_sched_requeue_request(rq);
spin_lock_irqsave(&q->requeue_lock, flags);
list_add_tail(&rq->queuelist, &q->requeue_list);
spin_unlock_irqrestore(&q->requeue_lock, flags);
if (kick_requeue_list)
blk_mq_kick_requeue_list(q);
}
EXPORT_SYMBOL(blk_mq_requeue_request);
static void blk_mq_requeue_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, requeue_work.work);
LIST_HEAD(rq_list);
LIST_HEAD(flush_list);
struct request *rq;
spin_lock_irq(&q->requeue_lock);
list_splice_init(&q->requeue_list, &rq_list);
list_splice_init(&q->flush_list, &flush_list);
spin_unlock_irq(&q->requeue_lock);
while (!list_empty(&rq_list)) {
rq = list_entry(rq_list.next, struct request, queuelist);
list_del_init(&rq->queuelist);
/*
* If RQF_DONTPREP is set, the request has been started by the
* driver already and might have driver-specific data allocated
* already. Insert it into the hctx dispatch list to avoid
* block layer merges for the request.
*/
if (rq->rq_flags & RQF_DONTPREP)
blk_mq_request_bypass_insert(rq, 0);
else
blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
}
while (!list_empty(&flush_list)) {
rq = list_entry(flush_list.next, struct request, queuelist);
list_del_init(&rq->queuelist);
blk_mq_insert_request(rq, 0);
}
blk_mq_run_hw_queues(q, false);
}
void blk_mq_kick_requeue_list(struct request_queue *q)
{
kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
}
EXPORT_SYMBOL(blk_mq_kick_requeue_list);
void blk_mq_delay_kick_requeue_list(struct request_queue *q,
unsigned long msecs)
{
kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work,
msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
static bool blk_is_flush_data_rq(struct request *rq)
{
return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq);
}
static bool blk_mq_rq_inflight(struct request *rq, void *priv)
{
/*
* If we find a request that isn't idle we know the queue is busy
* as it's checked in the iter.
* Return false to stop the iteration.
*
* In case of queue quiesce, if one flush data request is completed,
* don't count it as inflight given the flush sequence is suspended,
* and the original flush data request is invisible to driver, just
* like other pending requests because of quiesce
*/
if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) &&
blk_is_flush_data_rq(rq) &&
blk_mq_request_completed(rq))) {
bool *busy = priv;
*busy = true;
return false;
}
return true;
}
bool blk_mq_queue_inflight(struct request_queue *q)
{
bool busy = false;
blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy);
return busy;
}
EXPORT_SYMBOL_GPL(blk_mq_queue_inflight);
static void blk_mq_rq_timed_out(struct request *req)
{
req->rq_flags |= RQF_TIMED_OUT;
if (req->q->mq_ops->timeout) {
enum blk_eh_timer_return ret;
ret = req->q->mq_ops->timeout(req);
if (ret == BLK_EH_DONE)
return;
WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
}
blk_add_timer(req);
}
struct blk_expired_data {
bool has_timedout_rq;
unsigned long next;
unsigned long timeout_start;
};
static bool blk_mq_req_expired(struct request *rq, struct blk_expired_data *expired)
{
unsigned long deadline;
if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
return false;
if (rq->rq_flags & RQF_TIMED_OUT)
return false;
deadline = READ_ONCE(rq->deadline);
if (time_after_eq(expired->timeout_start, deadline))
return true;
if (expired->next == 0)
expired->next = deadline;
else if (time_after(expired->next, deadline))
expired->next = deadline;
return false;
}
void blk_mq_put_rq_ref(struct request *rq)
{
if (is_flush_rq(rq)) {
if (rq->end_io(rq, 0) == RQ_END_IO_FREE)
blk_mq_free_request(rq);
} else if (req_ref_put_and_test(rq)) {
__blk_mq_free_request(rq);
}
}
static bool blk_mq_check_expired(struct request *rq, void *priv)
{
struct blk_expired_data *expired = priv;
/*
* blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
* be reallocated underneath the timeout handler's processing, then
* the expire check is reliable. If the request is not expired, then
* it was completed and reallocated as a new request after returning
* from blk_mq_check_expired().
*/
if (blk_mq_req_expired(rq, expired)) {
expired->has_timedout_rq = true;
return false;
}
return true;
}
static bool blk_mq_handle_expired(struct request *rq, void *priv)
{
struct blk_expired_data *expired = priv;
if (blk_mq_req_expired(rq, expired))
blk_mq_rq_timed_out(rq);
return true;
}
static void blk_mq_timeout_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, timeout_work);
struct blk_expired_data expired = {
.timeout_start = jiffies,
};
struct blk_mq_hw_ctx *hctx;
unsigned long i;
/* A deadlock might occur if a request is stuck requiring a
* timeout at the same time a queue freeze is waiting
* completion, since the timeout code would not be able to
* acquire the queue reference here.
*
* That's why we don't use blk_queue_enter here; instead, we use
* percpu_ref_tryget directly, because we need to be able to
* obtain a reference even in the short window between the queue
* starting to freeze, by dropping the first reference in
* blk_freeze_queue_start, and the moment the last request is
* consumed, marked by the instant q_usage_counter reaches
* zero.
*/
if (!percpu_ref_tryget(&q->q_usage_counter))
return;
/* check if there is any timed-out request */
blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &expired);
if (expired.has_timedout_rq) {
/*
* Before walking tags, we must ensure any submit started
* before the current time has finished. Since the submit
* uses srcu or rcu, wait for a synchronization point to
* ensure all running submits have finished
*/
blk_mq_wait_quiesce_done(q->tag_set);
expired.next = 0;
blk_mq_queue_tag_busy_iter(q, blk_mq_handle_expired, &expired);
}
if (expired.next != 0) {
mod_timer(&q->timeout, expired.next);
} else {
/*
* Request timeouts are handled as a forward rolling timer. If
* we end up here it means that no requests are pending and
* also that no request has been pending for a while. Mark
* each hctx as idle.
*/
queue_for_each_hw_ctx(q, hctx, i) {
/* the hctx may be unmapped, so check it here */
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_idle(hctx);
}
}
blk_queue_exit(q);
}
struct flush_busy_ctx_data {
struct blk_mq_hw_ctx *hctx;
struct list_head *list;
};
static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
{
struct flush_busy_ctx_data *flush_data = data;
struct blk_mq_hw_ctx *hctx = flush_data->hctx;
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
enum hctx_type type = hctx->type;
spin_lock(&ctx->lock);
list_splice_tail_init(&ctx->rq_lists[type], flush_data->list);
sbitmap_clear_bit(sb, bitnr);
spin_unlock(&ctx->lock);
return true;
}
/*
* Process software queues that have been marked busy, splicing them
* to the for-dispatch
*/
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
struct flush_busy_ctx_data data = {
.hctx = hctx,
.list = list,
};
sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
}
struct dispatch_rq_data {
struct blk_mq_hw_ctx *hctx;
struct request *rq;
};
static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
void *data)
{
struct dispatch_rq_data *dispatch_data = data;
struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
enum hctx_type type = hctx->type;
spin_lock(&ctx->lock);
if (!list_empty(&ctx->rq_lists[type])) {
dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next);
list_del_init(&dispatch_data->rq->queuelist);
if (list_empty(&ctx->rq_lists[type]))
sbitmap_clear_bit(sb, bitnr);
}
spin_unlock(&ctx->lock);
return !dispatch_data->rq;
}
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *start)
{
unsigned off = start ? start->index_hw[hctx->type] : 0;
struct dispatch_rq_data data = {
.hctx = hctx,
.rq = NULL,
};
__sbitmap_for_each_set(&hctx->ctx_map, off,
dispatch_rq_from_ctx, &data);
return data.rq;
}
bool __blk_mq_alloc_driver_tag(struct request *rq)
{
struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
int tag;
blk_mq_tag_busy(rq->mq_hctx);
if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
bt = &rq->mq_hctx->tags->breserved_tags;
tag_offset = 0;
} else {
if (!hctx_may_queue(rq->mq_hctx, bt))
return false;
}
tag = __sbitmap_queue_get(bt);
if (tag == BLK_MQ_NO_TAG)
return false;
rq->tag = tag + tag_offset;
blk_mq_inc_active_requests(rq->mq_hctx);
return true;
}
static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
int flags, void *key)
{
struct blk_mq_hw_ctx *hctx;
hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
spin_lock(&hctx->dispatch_wait_lock);
if (!list_empty(&wait->entry)) {
struct sbitmap_queue *sbq;
list_del_init(&wait->entry);
sbq = &hctx->tags->bitmap_tags;
atomic_dec(&sbq->ws_active);
}
spin_unlock(&hctx->dispatch_wait_lock);
blk_mq_run_hw_queue(hctx, true);
return 1;
}
/*
* Mark us waiting for a tag. For shared tags, this involves hooking us into
* the tag wakeups. For non-shared tags, we can simply mark us needing a
* restart. For both cases, take care to check the condition again after
* marking us as waiting.
*/
static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
struct sbitmap_queue *sbq;
struct wait_queue_head *wq;
wait_queue_entry_t *wait;
bool ret;
if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
!(blk_mq_is_shared_tags(hctx->flags))) {
blk_mq_sched_mark_restart_hctx(hctx);
/*
* It's possible that a tag was freed in the window between the
* allocation failure and adding the hardware queue to the wait
* queue.
*
* Don't clear RESTART here, someone else could have set it.
* At most this will cost an extra queue run.
*/
return blk_mq_get_driver_tag(rq);
}
wait = &hctx->dispatch_wait;
if (!list_empty_careful(&wait->entry))
return false;
if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag))
sbq = &hctx->tags->breserved_tags;
else
sbq = &hctx->tags->bitmap_tags;
wq = &bt_wait_ptr(sbq, hctx)->wait;
spin_lock_irq(&wq->lock);
spin_lock(&hctx->dispatch_wait_lock);
if (!list_empty(&wait->entry)) {
spin_unlock(&hctx->dispatch_wait_lock);
spin_unlock_irq(&wq->lock);
return false;
}
atomic_inc(&sbq->ws_active);
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
__add_wait_queue(wq, wait);
/*
* Add one explicit barrier since blk_mq_get_driver_tag() may
* not imply barrier in case of failure.
*
* Order adding us to wait queue and allocating driver tag.
*
* The pair is the one implied in sbitmap_queue_wake_up() which
* orders clearing sbitmap tag bits and waitqueue_active() in
* __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
*
* Otherwise, re-order of adding wait queue and getting driver tag
* may cause __sbitmap_queue_wake_up() to wake up nothing because
* the waitqueue_active() may not observe us in wait queue.
*/
smp_mb();
/*
* It's possible that a tag was freed in the window between the
* allocation failure and adding the hardware queue to the wait
* queue.
*/
ret = blk_mq_get_driver_tag(rq);
if (!ret) {
spin_unlock(&hctx->dispatch_wait_lock);
spin_unlock_irq(&wq->lock);
return false;
}
/*
* We got a tag, remove ourselves from the wait queue to ensure
* someone else gets the wakeup.
*/
list_del_init(&wait->entry);
atomic_dec(&sbq->ws_active);
spin_unlock(&hctx->dispatch_wait_lock);
spin_unlock_irq(&wq->lock);
return true;
}
#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8
#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4
/*
* Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
* - EWMA is one simple way to compute running average value
* - weight(7/8 and 1/8) is applied so that it can decrease exponentially
* - take 4 as factor for avoiding to get too small(0) result, and this
* factor doesn't matter because EWMA decreases exponentially
*/
static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
{
unsigned int ewma;
ewma = hctx->dispatch_busy;
if (!ewma && !busy)
return;
ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
if (busy)
ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;
hctx->dispatch_busy = ewma;
}
#define BLK_MQ_RESOURCE_DELAY 3 /* ms units */
static void blk_mq_handle_dev_resource(struct request *rq,
struct list_head *list)
{
list_add(&rq->queuelist, list);
__blk_mq_requeue_request(rq);
}
enum prep_dispatch {
PREP_DISPATCH_OK,
PREP_DISPATCH_NO_TAG,
PREP_DISPATCH_NO_BUDGET,
};
static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq,
bool need_budget)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
int budget_token = -1;
if (need_budget) {
budget_token = blk_mq_get_dispatch_budget(rq->q);
if (budget_token < 0) {
blk_mq_put_driver_tag(rq);
return PREP_DISPATCH_NO_BUDGET;
}
blk_mq_set_rq_budget_token(rq, budget_token);
}
if (!blk_mq_get_driver_tag(rq)) {
/*
* The initial allocation attempt failed, so we need to
* rerun the hardware queue when a tag is freed. The
* waitqueue takes care of that. If the queue is run
* before we add this entry back on the dispatch list,
* we'll re-run it below.
*/
if (!blk_mq_mark_tag_wait(hctx, rq)) {
/*
* All budgets not got from this function will be put
* together during handling partial dispatch
*/
if (need_budget)
blk_mq_put_dispatch_budget(rq->q, budget_token);
return PREP_DISPATCH_NO_TAG;
}
}
return PREP_DISPATCH_OK;
}
/* release all allocated budgets before calling to blk_mq_dispatch_rq_list */
static void blk_mq_release_budgets(struct request_queue *q,
struct list_head *list)
{
struct request *rq;
list_for_each_entry(rq, list, queuelist) {
int budget_token = blk_mq_get_rq_budget_token(rq);
if (budget_token >= 0)
blk_mq_put_dispatch_budget(q, budget_token);
}
}
/*
* blk_mq_commit_rqs will notify driver using bd->last that there is no
* more requests. (See comment in struct blk_mq_ops for commit_rqs for
* details)
* Attention, we should explicitly call this in unusual cases:
* 1) did not queue everything initially scheduled to queue
* 2) the last attempt to queue a request failed
*/
static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued,
bool from_schedule)
{
if (hctx->queue->mq_ops->commit_rqs && queued) {
trace_block_unplug(hctx->queue, queued, !from_schedule);
hctx->queue->mq_ops->commit_rqs(hctx);
}
}
/*
* Returns true if we did some work AND can potentially do more.
*/
bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
unsigned int nr_budgets)
{
enum prep_dispatch prep;
struct request_queue *q = hctx->queue;
struct request *rq;
int queued;
blk_status_t ret = BLK_STS_OK;
bool needs_resource = false;
if (list_empty(list))
return false;
/*
* Now process all the entries, sending them to the driver.
*/
queued = 0;
do {
struct blk_mq_queue_data bd;
rq = list_first_entry(list, struct request, queuelist);
WARN_ON_ONCE(hctx != rq->mq_hctx);
prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets);
if (prep != PREP_DISPATCH_OK)
break;
list_del_init(&rq->queuelist);
bd.rq = rq;
bd.last = list_empty(list);
/*
* once the request is queued to lld, no need to cover the
* budget any more
*/
if (nr_budgets)
nr_budgets--;
ret = q->mq_ops->queue_rq(hctx, &bd);
switch (ret) {
case BLK_STS_OK:
queued++;
break;
case BLK_STS_RESOURCE:
needs_resource = true;
fallthrough;
case BLK_STS_DEV_RESOURCE:
blk_mq_handle_dev_resource(rq, list);
goto out;
default:
blk_mq_end_request(rq, ret);
}
} while (!list_empty(list));
out:
/* If we didn't flush the entire list, we could have told the driver
* there was more coming, but that turned out to be a lie.
*/
if (!list_empty(list) || ret != BLK_STS_OK)
blk_mq_commit_rqs(hctx, queued, false);
/*
* Any items that need requeuing? Stuff them into hctx->dispatch,
* that is where we will continue on next queue run.
*/
if (!list_empty(list)) {
bool needs_restart;
/* For non-shared tags, the RESTART check will suffice */
bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) ||
blk_mq_is_shared_tags(hctx->flags));
if (nr_budgets)
blk_mq_release_budgets(q, list);
spin_lock(&hctx->lock);
list_splice_tail_init(list, &hctx->dispatch);
spin_unlock(&hctx->lock);
/*
* Order adding requests to hctx->dispatch and checking
* SCHED_RESTART flag. The pair of this smp_mb() is the one
* in blk_mq_sched_restart(). Avoid restart code path to
* miss the new added requests to hctx->dispatch, meantime
* SCHED_RESTART is observed here.
*/
smp_mb();
/*
* If SCHED_RESTART was set by the caller of this function and
* it is no longer set that means that it was cleared by another
* thread and hence that a queue rerun is needed.
*
* If 'no_tag' is set, that means that we failed getting
* a driver tag with an I/O scheduler attached. If our dispatch
* waitqueue is no longer active, ensure that we run the queue
* AFTER adding our entries back to the list.
*
* If no I/O scheduler has been configured it is possible that
* the hardware queue got stopped and restarted before requests
* were pushed back onto the dispatch list. Rerun the queue to
* avoid starvation. Notes:
* - blk_mq_run_hw_queue() checks whether or not a queue has
* been stopped before rerunning a queue.
* - Some but not all block drivers stop a queue before
* returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
* and dm-rq.
*
* If driver returns BLK_STS_RESOURCE and SCHED_RESTART
* bit is set, run queue after a delay to avoid IO stalls
* that could otherwise occur if the queue is idle. We'll do
* similar if we couldn't get budget or couldn't lock a zone
* and SCHED_RESTART is set.
*/
needs_restart = blk_mq_sched_needs_restart(hctx);
if (prep == PREP_DISPATCH_NO_BUDGET)
needs_resource = true;
if (!needs_restart ||
(no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
blk_mq_run_hw_queue(hctx, true);
else if (needs_resource)
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
return false;
}
blk_mq_update_dispatch_busy(hctx, false);
return true;
}
static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
{
int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
if (cpu >= nr_cpu_ids)
cpu = cpumask_first(hctx->cpumask);
return cpu;
}
/*
* ->next_cpu is always calculated from hctx->cpumask, so simply use
* it for speeding up the check
*/
static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
{
return hctx->next_cpu >= nr_cpu_ids;
}
/*
* It'd be great if the workqueue API had a way to pass
* in a mask and had some smarts for more clever placement.
* For now we just round-robin here, switching for every
* BLK_MQ_CPU_WORK_BATCH queued items.
*/
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
{
bool tried = false;
int next_cpu = hctx->next_cpu;
/* Switch to unbound if no allowable CPUs in this hctx */
if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
return WORK_CPU_UNBOUND;
if (--hctx->next_cpu_batch <= 0) {
select_cpu:
next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
next_cpu = blk_mq_first_mapped_cpu(hctx);
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
}
/*
* Do unbound schedule if we can't find a online CPU for this hctx,
* and it should only happen in the path of handling CPU DEAD.
*/
if (!cpu_online(next_cpu)) {
if (!tried) {
tried = true;
goto select_cpu;
}
/*
* Make sure to re-select CPU next time once after CPUs
* in hctx->cpumask become online again.
*/
hctx->next_cpu = next_cpu;
hctx->next_cpu_batch = 1;
return WORK_CPU_UNBOUND;
}
hctx->next_cpu = next_cpu;
return next_cpu;
}
/**
* blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
* @hctx: Pointer to the hardware queue to run.
* @msecs: Milliseconds of delay to wait before running the queue.
*
* Run a hardware queue asynchronously with a delay of @msecs.
*/
void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
{
bool need_run;
/*
* When queue is quiesced, we may be switching io scheduler, or
* updating nr_hw_queues, or other things, and we can't run queue
* any more, even blk_mq_hctx_has_pending() can't be called safely.
*
* And queue will be rerun in blk_mq_unquiesce_queue() if it is
* quiesced.
*/
__blk_mq_run_dispatch_ops(hctx->queue, false,
need_run = !blk_queue_quiesced(hctx->queue) &&
blk_mq_hctx_has_pending(hctx));
return need_run;
}
/**
* blk_mq_run_hw_queue - Start to run a hardware queue.
* @hctx: Pointer to the hardware queue to run.
* @async: If we want to run the queue asynchronously.
*
* Check if the request queue is not in a quiesced state and if there are
* pending requests to be sent. If this is true, run the queue to send requests
* to hardware.
*/
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
bool need_run;
/*
* We can't run the queue inline with interrupts disabled.
*/
WARN_ON_ONCE(!async && in_interrupt());
might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
need_run = blk_mq_hw_queue_need_run(hctx);
if (!need_run) {
unsigned long flags;
/*
* Synchronize with blk_mq_unquiesce_queue(), because we check
* if hw queue is quiesced locklessly above, we need the use
* ->queue_lock to make sure we see the up-to-date status to
* not miss rerunning the hw queue.
*/
spin_lock_irqsave(&hctx->queue->queue_lock, flags);
need_run = blk_mq_hw_queue_need_run(hctx);
spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
if (!need_run)
return;
}
if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
blk_mq_delay_run_hw_queue(hctx, 0);
return;
}
blk_mq_run_dispatch_ops(hctx->queue,
blk_mq_sched_dispatch_requests(hctx));
}
EXPORT_SYMBOL(blk_mq_run_hw_queue);
/*
* Return prefered queue to dispatch from (if any) for non-mq aware IO
* scheduler.
*/
static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
{
struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
/*
* If the IO scheduler does not respect hardware queues when
* dispatching, we just don't bother with multiple HW queues and
* dispatch from hctx for the current CPU since running multiple queues
* just causes lock contention inside the scheduler and pointless cache
* bouncing.
*/
struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT];
if (!blk_mq_hctx_stopped(hctx))
return hctx;
return NULL;
}
/**
* blk_mq_run_hw_queues - Run all hardware queues in a request queue.
* @q: Pointer to the request queue to run.
* @async: If we want to run the queue asynchronously.
*/
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
struct blk_mq_hw_ctx *hctx, *sq_hctx;
unsigned long i;
sq_hctx = NULL;
if (blk_queue_sq_sched(q))
sq_hctx = blk_mq_get_sq_hctx(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_hctx_stopped(hctx))
continue;
/*
* Dispatch from this hctx either if there's no hctx preferred
* by IO scheduler or if it has requests that bypass the
* scheduler.
*/
if (!sq_hctx || sq_hctx == hctx ||
!list_empty_careful(&hctx->dispatch))
blk_mq_run_hw_queue(hctx, async);
}
}
EXPORT_SYMBOL(blk_mq_run_hw_queues);
/**
* blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
* @q: Pointer to the request queue to run.
* @msecs: Milliseconds of delay to wait before running the queues.
*/
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
{
struct blk_mq_hw_ctx *hctx, *sq_hctx;
unsigned long i;
sq_hctx = NULL;
if (blk_queue_sq_sched(q))
sq_hctx = blk_mq_get_sq_hctx(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_hctx_stopped(hctx))
continue;
/*
* If there is already a run_work pending, leave the
* pending delay untouched. Otherwise, a hctx can stall
* if another hctx is re-delaying the other's work
* before the work executes.
*/
if (delayed_work_pending(&hctx->run_work))
continue;
/*
* Dispatch from this hctx either if there's no hctx preferred
* by IO scheduler or if it has requests that bypass the
* scheduler.
*/
if (!sq_hctx || sq_hctx == hctx ||
!list_empty_careful(&hctx->dispatch))
blk_mq_delay_run_hw_queue(hctx, msecs);
}
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
/*
* This function is often used for pausing .queue_rq() by driver when
* there isn't enough resource or some conditions aren't satisfied, and
* BLK_STS_RESOURCE is usually returned.
*
* We do not guarantee that dispatch can be drained or blocked
* after blk_mq_stop_hw_queue() returns. Please use
* blk_mq_quiesce_queue() for that requirement.
*/
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
cancel_delayed_work(&hctx->run_work);
set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
/*
* This function is often used for pausing .queue_rq() by driver when
* there isn't enough resource or some conditions aren't satisfied, and
* BLK_STS_RESOURCE is usually returned.
*
* We do not guarantee that dispatch can be drained or blocked
* after blk_mq_stop_hw_queues() returns. Please use
* blk_mq_quiesce_queue() for that requirement.
*/
void blk_mq_stop_hw_queues(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_stop_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queues);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
{
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING);
}
EXPORT_SYMBOL(blk_mq_start_hw_queue);
void blk_mq_start_hw_queues(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_start_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_start_hw_queues);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
{
if (!blk_mq_hctx_stopped(hctx))
return;
clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
/*
* Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the
* clearing of BLK_MQ_S_STOPPED above and the checking of dispatch
* list in the subsequent routine.
*/
smp_mb__after_atomic();
blk_mq_run_hw_queue(hctx, async);
}
EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_start_stopped_hw_queue(hctx, async ||
(hctx->flags & BLK_MQ_F_BLOCKING));
}
EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
static void blk_mq_run_work_fn(struct work_struct *work)
{
struct blk_mq_hw_ctx *hctx =
container_of(work, struct blk_mq_hw_ctx, run_work.work);
blk_mq_run_dispatch_ops(hctx->queue,
blk_mq_sched_dispatch_requests(hctx));
}
/**
* blk_mq_request_bypass_insert - Insert a request at dispatch list.
* @rq: Pointer to request to be inserted.
* @flags: BLK_MQ_INSERT_*
*
* Should only be used carefully, when the caller knows we want to
* bypass a potential IO scheduler on the target device.
*/
static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
spin_lock(&hctx->lock);
if (flags & BLK_MQ_INSERT_AT_HEAD)
list_add(&rq->queuelist, &hctx->dispatch);
else
list_add_tail(&rq->queuelist, &hctx->dispatch);
spin_unlock(&hctx->lock);
}
static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx, struct list_head *list,
bool run_queue_async)
{
struct request *rq;
enum hctx_type type = hctx->type;
/*
* Try to issue requests directly if the hw queue isn't busy to save an
* extra enqueue & dequeue to the sw queue.
*/
if (!hctx->dispatch_busy && !run_queue_async) { blk_mq_run_dispatch_ops(hctx->queue,
blk_mq_try_issue_list_directly(hctx, list));
if (list_empty(list))
goto out;
}
/*
* preemption doesn't flush plug list, so it's possible ctx->cpu is
* offline now
*/
list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx);
trace_block_rq_insert(rq);
if (rq->cmd_flags & REQ_NOWAIT)
run_queue_async = true;
}
spin_lock(&ctx->lock);
list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
out:
blk_mq_run_hw_queue(hctx, run_queue_async);
}
static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
{
struct request_queue *q = rq->q;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (blk_rq_is_passthrough(rq)) {
/*
* Passthrough request have to be added to hctx->dispatch
* directly. The device may be in a situation where it can't
* handle FS request, and always returns BLK_STS_RESOURCE for
* them, which gets them added to hctx->dispatch.
*
* If a passthrough request is required to unblock the queues,
* and it is added to the scheduler queue, there is no chance to
* dispatch it given we prioritize requests in hctx->dispatch.
*/
blk_mq_request_bypass_insert(rq, flags);
} else if (req_op(rq) == REQ_OP_FLUSH) {
/*
* Firstly normal IO request is inserted to scheduler queue or
* sw queue, meantime we add flush request to dispatch queue(
* hctx->dispatch) directly and there is at most one in-flight
* flush request for each hw queue, so it doesn't matter to add
* flush request to tail or front of the dispatch queue.
*
* Secondly in case of NCQ, flush request belongs to non-NCQ
* command, and queueing it will fail when there is any
* in-flight normal IO request(NCQ command). When adding flush
* rq to the front of hctx->dispatch, it is easier to introduce
* extra time to flush rq's latency because of S_SCHED_RESTART
* compared with adding to the tail of dispatch queue, then
* chance of flush merge is increased, and less flush requests
* will be issued to controller. It is observed that ~10% time
* is saved in blktests block/004 on disk attached to AHCI/NCQ
* drive when adding flush rq to the front of hctx->dispatch.
*
* Simply queue flush rq to the front of hctx->dispatch so that
* intensive flush workloads can benefit in case of NCQ HW.
*/
blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD);
} else if (q->elevator) {
LIST_HEAD(list);
WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG);
list_add(&rq->queuelist, &list);
q->elevator->type->ops.insert_requests(hctx, &list, flags);
} else {
trace_block_rq_insert(rq);
spin_lock(&ctx->lock);
if (flags & BLK_MQ_INSERT_AT_HEAD)
list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]);
else
list_add_tail(&rq->queuelist,
&ctx->rq_lists[hctx->type]);
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
}
}
static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
unsigned int nr_segs)
{
int err;
if (bio->bi_opf & REQ_RAHEAD)
rq->cmd_flags |= REQ_FAILFAST_MASK;
rq->bio = rq->biotail = bio;
rq->__sector = bio->bi_iter.bi_sector;
rq->__data_len = bio->bi_iter.bi_size;
rq->nr_phys_segments = nr_segs;
if (bio_integrity(bio))
rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q,
bio);
/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
WARN_ON_ONCE(err);
blk_account_io_start(rq);
}
static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq, bool last)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
.last = last,
};
blk_status_t ret;
/*
* For OK queue, we are done. For error, caller may kill it.
* Any other error (busy), just add it to our list as we
* previously would have done.
*/
ret = q->mq_ops->queue_rq(hctx, &bd);
switch (ret) {
case BLK_STS_OK:
blk_mq_update_dispatch_busy(hctx, false);
break;
case BLK_STS_RESOURCE:
case BLK_STS_DEV_RESOURCE:
blk_mq_update_dispatch_busy(hctx, true);
__blk_mq_requeue_request(rq);
break;
default:
blk_mq_update_dispatch_busy(hctx, false);
break;
}
return ret;
}
static bool blk_mq_get_budget_and_tag(struct request *rq)
{
int budget_token;
budget_token = blk_mq_get_dispatch_budget(rq->q);
if (budget_token < 0)
return false;
blk_mq_set_rq_budget_token(rq, budget_token);
if (!blk_mq_get_driver_tag(rq)) {
blk_mq_put_dispatch_budget(rq->q, budget_token);
return false;
}
return true;
}
/**
* blk_mq_try_issue_directly - Try to send a request directly to device driver.
* @hctx: Pointer of the associated hardware queue.
* @rq: Pointer to request to be sent.
*
* If the device has enough resources to accept a new request now, send the
* request directly to device driver. Else, insert at hctx->dispatch queue, so
* we can try send it another time in the future. Requests inserted at this
* queue have higher priority.
*/
static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
blk_status_t ret;
if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
blk_mq_insert_request(rq, 0);
blk_mq_run_hw_queue(hctx, false);
return;
}
if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) {
blk_mq_insert_request(rq, 0);
blk_mq_run_hw_queue(hctx, rq->cmd_flags & REQ_NOWAIT);
return;
}
ret = __blk_mq_issue_directly(hctx, rq, true);
switch (ret) {
case BLK_STS_OK:
break;
case BLK_STS_RESOURCE:
case BLK_STS_DEV_RESOURCE:
blk_mq_request_bypass_insert(rq, 0);
blk_mq_run_hw_queue(hctx, false);
break;
default:
blk_mq_end_request(rq, ret);
break;
}
}
static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
blk_mq_insert_request(rq, 0);
blk_mq_run_hw_queue(hctx, false);
return BLK_STS_OK;
}
if (!blk_mq_get_budget_and_tag(rq))
return BLK_STS_RESOURCE;
return __blk_mq_issue_directly(hctx, rq, last);
}
static void blk_mq_plug_issue_direct(struct blk_plug *plug)
{
struct blk_mq_hw_ctx *hctx = NULL;
struct request *rq;
int queued = 0;
blk_status_t ret = BLK_STS_OK;
while ((rq = rq_list_pop(&plug->mq_list))) {
bool last = rq_list_empty(&plug->mq_list);
if (hctx != rq->mq_hctx) {
if (hctx) {
blk_mq_commit_rqs(hctx, queued, false);
queued = 0;
}
hctx = rq->mq_hctx;
}
ret = blk_mq_request_issue_directly(rq, last);
switch (ret) {
case BLK_STS_OK:
queued++;
break;
case BLK_STS_RESOURCE:
case BLK_STS_DEV_RESOURCE:
blk_mq_request_bypass_insert(rq, 0);
blk_mq_run_hw_queue(hctx, false);
goto out;
default:
blk_mq_end_request(rq, ret);
break;
}
}
out:
if (ret != BLK_STS_OK)
blk_mq_commit_rqs(hctx, queued, false);
}
static void __blk_mq_flush_plug_list(struct request_queue *q,
struct blk_plug *plug)
{
if (blk_queue_quiesced(q))
return;
q->mq_ops->queue_rqs(&plug->mq_list);
}
static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
{
struct blk_mq_hw_ctx *this_hctx = NULL;
struct blk_mq_ctx *this_ctx = NULL;
struct rq_list requeue_list = {};
unsigned int depth = 0;
bool is_passthrough = false;
LIST_HEAD(list);
do {
struct request *rq = rq_list_pop(&plug->mq_list);
if (!this_hctx) {
this_hctx = rq->mq_hctx;
this_ctx = rq->mq_ctx;
is_passthrough = blk_rq_is_passthrough(rq);
} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx ||
is_passthrough != blk_rq_is_passthrough(rq)) {
rq_list_add_tail(&requeue_list, rq);
continue;
}
list_add_tail(&rq->queuelist, &list);
depth++;
} while (!rq_list_empty(&plug->mq_list));
plug->mq_list = requeue_list;
trace_block_unplug(this_hctx->queue, depth, !from_sched);
percpu_ref_get(&this_hctx->queue->q_usage_counter);
/* passthrough requests should never be issued to the I/O scheduler */
if (is_passthrough) {
spin_lock(&this_hctx->lock);
list_splice_tail_init(&list, &this_hctx->dispatch);
spin_unlock(&this_hctx->lock);
blk_mq_run_hw_queue(this_hctx, from_sched);
} else if (this_hctx->queue->elevator) {
this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
&list, 0);
blk_mq_run_hw_queue(this_hctx, from_sched);
} else {
blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched);
}
percpu_ref_put(&this_hctx->queue->q_usage_counter);
}
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request *rq;
unsigned int depth;
/*
* We may have been called recursively midway through handling
* plug->mq_list via a schedule() in the driver's queue_rq() callback.
* To avoid mq_list changing under our feet, clear rq_count early and
* bail out specifically if rq_count is 0 rather than checking
* whether the mq_list is empty.
*/
if (plug->rq_count == 0)
return;
depth = plug->rq_count;
plug->rq_count = 0;
if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
struct request_queue *q;
rq = rq_list_peek(&plug->mq_list);
q = rq->q;
trace_block_unplug(q, depth, true);
/*
* Peek first request and see if we have a ->queue_rqs() hook.
* If we do, we can dispatch the whole plug list in one go. We
* already know at this point that all requests belong to the
* same queue, caller must ensure that's the case.
*/
if (q->mq_ops->queue_rqs) { blk_mq_run_dispatch_ops(q,
__blk_mq_flush_plug_list(q, plug));
if (rq_list_empty(&plug->mq_list))
return;
}
blk_mq_run_dispatch_ops(q,
blk_mq_plug_issue_direct(plug));
if (rq_list_empty(&plug->mq_list))
return;
}
do {
blk_mq_dispatch_plug_list(plug, from_schedule); } while (!rq_list_empty(&plug->mq_list));
}
static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list)
{
int queued = 0;
blk_status_t ret = BLK_STS_OK;
while (!list_empty(list)) {
struct request *rq = list_first_entry(list, struct request,
queuelist);
list_del_init(&rq->queuelist);
ret = blk_mq_request_issue_directly(rq, list_empty(list));
switch (ret) {
case BLK_STS_OK:
queued++;
break;
case BLK_STS_RESOURCE:
case BLK_STS_DEV_RESOURCE:
blk_mq_request_bypass_insert(rq, 0);
if (list_empty(list))
blk_mq_run_hw_queue(hctx, false);
goto out;
default:
blk_mq_end_request(rq, ret);
break;
}
}
out:
if (ret != BLK_STS_OK)
blk_mq_commit_rqs(hctx, queued, false);
}
static bool blk_mq_attempt_bio_merge(struct request_queue *q,
struct bio *bio, unsigned int nr_segs)
{
if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
if (blk_attempt_plug_merge(q, bio, nr_segs))
return true;
if (blk_mq_sched_bio_merge(q, bio, nr_segs))
return true;
}
return false;
}
static struct request *blk_mq_get_new_requests(struct request_queue *q,
struct blk_plug *plug,
struct bio *bio)
{
struct blk_mq_alloc_data data = {
.q = q,
.nr_tags = 1,
.cmd_flags = bio->bi_opf,
};
struct request *rq;
rq_qos_throttle(q, bio);
if (plug) {
data.nr_tags = plug->nr_ios;
plug->nr_ios = 1;
data.cached_rqs = &plug->cached_rqs;
}
rq = __blk_mq_alloc_requests(&data);
if (unlikely(!rq))
rq_qos_cleanup(q, bio);
return rq;
}
/*
* Check if there is a suitable cached request and return it.
*/
static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
struct request_queue *q, blk_opf_t opf)
{
enum hctx_type type = blk_mq_get_hctx_type(opf);
struct request *rq;
if (!plug)
return NULL;
rq = rq_list_peek(&plug->cached_rqs);
if (!rq || rq->q != q)
return NULL;
if (type != rq->mq_hctx->type &&
(type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT))
return NULL;
if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
return NULL;
return rq;
}
static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
struct bio *bio)
{
if (rq_list_pop(&plug->cached_rqs) != rq)
WARN_ON_ONCE(1);
/*
* If any qos ->throttle() end up blocking, we will have flushed the
* plug and hence killed the cached_rq list as well. Pop this entry
* before we throttle.
*/
rq_qos_throttle(rq->q, bio);
blk_mq_rq_time_init(rq, blk_time_get_ns());
rq->cmd_flags = bio->bi_opf;
INIT_LIST_HEAD(&rq->queuelist);
}
static bool bio_unaligned(const struct bio *bio, struct request_queue *q)
{
unsigned int bs_mask = queue_logical_block_size(q) - 1;
/* .bi_sector of any zero sized bio need to be initialized */
if ((bio->bi_iter.bi_size & bs_mask) ||
((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask))
return true;
return false;
}
/**
* blk_mq_submit_bio - Create and send a request to block device.
* @bio: Bio pointer.
*
* Builds up a request structure from @q and @bio and send to the device. The
* request may not be queued directly to hardware if:
* * This request can be merged with another one
* * We want to place request at plug queue for possible future merging
* * There is an IO scheduler active at this queue
*
* It will not queue the request if there is an error with the bio, or at the
* request creation.
*/
void blk_mq_submit_bio(struct bio *bio)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
struct blk_plug *plug = current->plug;
const int is_sync = op_is_sync(bio->bi_opf);
struct blk_mq_hw_ctx *hctx;
unsigned int nr_segs;
struct request *rq;
blk_status_t ret;
/*
* If the plug has a cached request for this queue, try to use it.
*/
rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
/*
* A BIO that was released from a zone write plug has already been
* through the preparation in this function, already holds a reference
* on the queue usage counter, and is the only write BIO in-flight for
* the target zone. Go straight to preparing a request for it.
*/
if (bio_zone_write_plugging(bio)) {
nr_segs = bio->__bi_nr_segments;
if (rq)
blk_queue_exit(q);
goto new_request;
}
bio = blk_queue_bounce(bio, q);
/*
* The cached request already holds a q_usage_counter reference and we
* don't have to acquire a new one if we use it.
*/
if (!rq) {
if (unlikely(bio_queue_enter(bio)))
return;
}
/*
* Device reconfiguration may change logical block size or reduce the
* number of poll queues, so the checks for alignment and poll support
* have to be done with queue usage counter held.
*/
if (unlikely(bio_unaligned(bio, q))) {
bio_io_error(bio);
goto queue_exit;
}
if ((bio->bi_opf & REQ_POLLED) && !blk_mq_can_poll(q)) {
bio->bi_status = BLK_STS_NOTSUPP;
bio_endio(bio);
goto queue_exit;
}
bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
if (!bio)
goto queue_exit;
if (!bio_integrity_prep(bio))
goto queue_exit;
if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
goto queue_exit;
if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs))
goto queue_exit;
new_request:
if (rq) {
blk_mq_use_cached_rq(rq, plug, bio);
} else {
rq = blk_mq_get_new_requests(q, plug, bio);
if (unlikely(!rq)) {
if (bio->bi_opf & REQ_NOWAIT)
bio_wouldblock_error(bio);
goto queue_exit;
}
}
trace_block_getrq(bio);
rq_qos_track(q, rq, bio);
blk_mq_bio_to_request(rq, bio, nr_segs);
ret = blk_crypto_rq_get_keyslot(rq);
if (ret != BLK_STS_OK) {
bio->bi_status = ret;
bio_endio(bio);
blk_mq_free_request(rq);
return;
}
if (bio_zone_write_plugging(bio))
blk_zone_write_plug_init_request(rq);
if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
return;
if (plug) {
blk_add_rq_to_plug(plug, rq);
return;
}
hctx = rq->mq_hctx;
if ((rq->rq_flags & RQF_USE_SCHED) ||
(hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
blk_mq_insert_request(rq, 0);
blk_mq_run_hw_queue(hctx, true);
} else {
blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
}
return;
queue_exit:
/*
* Don't drop the queue reference if we were trying to use a cached
* request and thus didn't acquire one.
*/
if (!rq)
blk_queue_exit(q);
}
#ifdef CONFIG_BLK_MQ_STACKING
/**
* blk_insert_cloned_request - Helper for stacking drivers to submit a request
* @rq: the request being queued
*/
blk_status_t blk_insert_cloned_request(struct request *rq)
{
struct request_queue *q = rq->q;
unsigned int max_sectors = blk_queue_get_max_sectors(rq);
unsigned int max_segments = blk_rq_get_max_segments(rq);
blk_status_t ret;
if (blk_rq_sectors(rq) > max_sectors) {
/*
* SCSI device does not have a good way to return if
* Write Same/Zero is actually supported. If a device rejects
* a non-read/write command (discard, write same,etc.) the
* low-level device driver will set the relevant queue limit to
* 0 to prevent blk-lib from issuing more of the offending
* operations. Commands queued prior to the queue limit being
* reset need to be completed with BLK_STS_NOTSUPP to avoid I/O
* errors being propagated to upper layers.
*/
if (max_sectors == 0)
return BLK_STS_NOTSUPP;
printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
__func__, blk_rq_sectors(rq), max_sectors);
return BLK_STS_IOERR;
}
/*
* The queue settings related to segment counting may differ from the
* original queue.
*/
rq->nr_phys_segments = blk_recalc_rq_segments(rq);
if (rq->nr_phys_segments > max_segments) {
printk(KERN_ERR "%s: over max segments limit. (%u > %u)\n",
__func__, rq->nr_phys_segments, max_segments);
return BLK_STS_IOERR;
}
if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq)))
return BLK_STS_IOERR;
ret = blk_crypto_rq_get_keyslot(rq);
if (ret != BLK_STS_OK)
return ret;
blk_account_io_start(rq);
/*
* Since we have a scheduler attached on the top device,
* bypass a potential scheduler on the bottom device for
* insert.
*/
blk_mq_run_dispatch_ops(q,
ret = blk_mq_request_issue_directly(rq, true));
if (ret)
blk_account_io_done(rq, blk_time_get_ns());
return ret;
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
/**
* blk_rq_unprep_clone - Helper function to free all bios in a cloned request
* @rq: the clone request to be cleaned up
*
* Description:
* Free all bios in @rq for a cloned request.
*/
void blk_rq_unprep_clone(struct request *rq)
{
struct bio *bio;
while ((bio = rq->bio) != NULL) {
rq->bio = bio->bi_next;
bio_put(bio);
}
}
EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
/**
* blk_rq_prep_clone - Helper function to setup clone request
* @rq: the request to be setup
* @rq_src: original request to be cloned
* @bs: bio_set that bios for clone are allocated from
* @gfp_mask: memory allocation mask for bio
* @bio_ctr: setup function to be called for each clone bio.
* Returns %0 for success, non %0 for failure.
* @data: private data to be passed to @bio_ctr
*
* Description:
* Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
* Also, pages which the original bios are pointing to are not copied
* and the cloned bios just point same pages.
* So cloned bios must be completed before original bios, which means
* the caller must complete @rq before @rq_src.
*/
int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio_set *bs, gfp_t gfp_mask,
int (*bio_ctr)(struct bio *, struct bio *, void *),
void *data)
{
struct bio *bio_src;
if (!bs)
bs = &fs_bio_set;
__rq_for_each_bio(bio_src, rq_src) {
struct bio *bio = bio_alloc_clone(rq->q->disk->part0, bio_src,
gfp_mask, bs);
if (!bio)
goto free_and_out;
if (bio_ctr && bio_ctr(bio, bio_src, data)) {
bio_put(bio);
goto free_and_out;
}
if (rq->bio) {
rq->biotail->bi_next = bio;
rq->biotail = bio;
} else {
rq->bio = rq->biotail = bio;
}
}
/* Copy attributes of the original request to the clone request. */
rq->__sector = blk_rq_pos(rq_src);
rq->__data_len = blk_rq_bytes(rq_src);
if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) {
rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
rq->special_vec = rq_src->special_vec;
}
rq->nr_phys_segments = rq_src->nr_phys_segments;
rq->nr_integrity_segments = rq_src->nr_integrity_segments;
if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
goto free_and_out;
return 0;
free_and_out:
blk_rq_unprep_clone(rq);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
#endif /* CONFIG_BLK_MQ_STACKING */
/*
* Steal bios from a request and add them to a bio list.
* The request must not have been partially completed before.
*/
void blk_steal_bios(struct bio_list *list, struct request *rq)
{
if (rq->bio) {
if (list->tail)
list->tail->bi_next = rq->bio;
else
list->head = rq->bio;
list->tail = rq->biotail;
rq->bio = NULL;
rq->biotail = NULL;
}
rq->__data_len = 0;
}
EXPORT_SYMBOL_GPL(blk_steal_bios);
static size_t order_to_size(unsigned int order)
{
return (size_t)PAGE_SIZE << order;
}
/* called before freeing request pool in @tags */
static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
struct blk_mq_tags *tags)
{
struct page *page;
unsigned long flags;
/*
* There is no need to clear mapping if driver tags is not initialized
* or the mapping belongs to the driver tags.
*/
if (!drv_tags || drv_tags == tags)
return;
list_for_each_entry(page, &tags->page_list, lru) {
unsigned long start = (unsigned long)page_address(page);
unsigned long end = start + order_to_size(page->private);
int i;
for (i = 0; i < drv_tags->nr_tags; i++) {
struct request *rq = drv_tags->rqs[i];
unsigned long rq_addr = (unsigned long)rq;
if (rq_addr >= start && rq_addr < end) {
WARN_ON_ONCE(req_ref_read(rq) != 0);
cmpxchg(&drv_tags->rqs[i], rq, NULL);
}
}
}
/*
* Wait until all pending iteration is done.
*
* Request reference is cleared and it is guaranteed to be observed
* after the ->lock is released.
*/
spin_lock_irqsave(&drv_tags->lock, flags);
spin_unlock_irqrestore(&drv_tags->lock, flags);
}
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx)
{
struct blk_mq_tags *drv_tags;
struct page *page;
if (list_empty(&tags->page_list))
return;
if (blk_mq_is_shared_tags(set->flags))
drv_tags = set->shared_tags;
else
drv_tags = set->tags[hctx_idx];
if (tags->static_rqs && set->ops->exit_request) {
int i;
for (i = 0; i < tags->nr_tags; i++) {
struct request *rq = tags->static_rqs[i];
if (!rq)
continue;
set->ops->exit_request(set, rq, hctx_idx);
tags->static_rqs[i] = NULL;
}
}
blk_mq_clear_rq_mapping(drv_tags, tags);
while (!list_empty(&tags->page_list)) {
page = list_first_entry(&tags->page_list, struct page, lru);
list_del_init(&page->lru);
/*
* Remove kmemleak object previously allocated in
* blk_mq_alloc_rqs().
*/
kmemleak_free(page_address(page));
__free_pages(page, page->private);
}
}
void blk_mq_free_rq_map(struct blk_mq_tags *tags)
{
kfree(tags->rqs);
tags->rqs = NULL;
kfree(tags->static_rqs);
tags->static_rqs = NULL;
blk_mq_free_tags(tags);
}
static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set,
unsigned int hctx_idx)
{
int i;
for (i = 0; i < set->nr_maps; i++) {
unsigned int start = set->map[i].queue_offset;
unsigned int end = start + set->map[i].nr_queues;
if (hctx_idx >= start && hctx_idx < end)
break;
}
if (i >= set->nr_maps)
i = HCTX_TYPE_DEFAULT;
return i;
}
static int blk_mq_get_hctx_node(struct blk_mq_tag_set *set,
unsigned int hctx_idx)
{
enum hctx_type type = hctx_idx_to_type(set, hctx_idx);
return blk_mq_hw_queue_to_node(&set->map[type], hctx_idx);
}
static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
unsigned int hctx_idx,
unsigned int nr_tags,
unsigned int reserved_tags)
{
int node = blk_mq_get_hctx_node(set, hctx_idx);
struct blk_mq_tags *tags;
if (node == NUMA_NO_NODE)
node = set->numa_node;
tags = blk_mq_init_tags(nr_tags, reserved_tags, set->flags, node);
if (!tags)
return NULL;
tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *),
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
node);
if (!tags->rqs)
goto err_free_tags;
tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *),
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
node);
if (!tags->static_rqs)
goto err_free_rqs;
return tags;
err_free_rqs:
kfree(tags->rqs);
err_free_tags:
blk_mq_free_tags(tags);
return NULL;
}
static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
unsigned int hctx_idx, int node)
{
int ret;
if (set->ops->init_request) {
ret = set->ops->init_request(set, rq, hctx_idx, node);
if (ret)
return ret;
}
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
return 0;
}
static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set,
struct blk_mq_tags *tags,
unsigned int hctx_idx, unsigned int depth)
{
unsigned int i, j, entries_per_page, max_order = 4;
int node = blk_mq_get_hctx_node(set, hctx_idx);
size_t rq_size, left;
if (node == NUMA_NO_NODE)
node = set->numa_node;
INIT_LIST_HEAD(&tags->page_list);
/*
* rq_size is the size of the request plus driver payload, rounded
* to the cacheline size
*/
rq_size = round_up(sizeof(struct request) + set->cmd_size,
cache_line_size());
left = rq_size * depth;
for (i = 0; i < depth; ) {
int this_order = max_order;
struct page *page;
int to_do;
void *p;
while (this_order && left < order_to_size(this_order - 1))
this_order--;
do {
page = alloc_pages_node(node,
GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
this_order);
if (page)
break;
if (!this_order--)
break;
if (order_to_size(this_order) < rq_size)
break;
} while (1);
if (!page)
goto fail;
page->private = this_order;
list_add_tail(&page->lru, &tags->page_list);
p = page_address(page);
/*
* Allow kmemleak to scan these pages as they contain pointers
* to additional allocations like via ops->init_request().
*/
kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
entries_per_page = order_to_size(this_order) / rq_size;
to_do = min(entries_per_page, depth - i);
left -= to_do * rq_size;
for (j = 0; j < to_do; j++) {
struct request *rq = p;
tags->static_rqs[i] = rq;
if (blk_mq_init_request(set, rq, hctx_idx, node)) {
tags->static_rqs[i] = NULL;
goto fail;
}
p += rq_size;
i++;
}
}
return 0;
fail:
blk_mq_free_rqs(set, tags, hctx_idx);
return -ENOMEM;
}
struct rq_iter_data {
struct blk_mq_hw_ctx *hctx;
bool has_rq;
};
static bool blk_mq_has_request(struct request *rq, void *data)
{
struct rq_iter_data *iter_data = data;
if (rq->mq_hctx != iter_data->hctx)
return true;
iter_data->has_rq = true;
return false;
}
static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
{
struct blk_mq_tags *tags = hctx->sched_tags ?
hctx->sched_tags : hctx->tags;
struct rq_iter_data data = {
.hctx = hctx,
};
blk_mq_all_tag_iter(tags, blk_mq_has_request, &data);
return data.has_rq;
}
static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
unsigned int this_cpu)
{
enum hctx_type type = hctx->type;
int cpu;
/*
* hctx->cpumask has to rule out isolated CPUs, but userspace still
* might submit IOs on these isolated CPUs, so use the queue map to
* check if all CPUs mapped to this hctx are offline
*/
for_each_online_cpu(cpu) {
struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
type, cpu);
if (h != hctx)
continue;
/* this hctx has at least one online CPU */
if (this_cpu != cpu)
return true;
}
return false;
}
static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
{
struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
struct blk_mq_hw_ctx, cpuhp_online);
if (blk_mq_hctx_has_online_cpu(hctx, cpu))
return 0;
/*
* Prevent new request from being allocated on the current hctx.
*
* The smp_mb__after_atomic() Pairs with the implied barrier in
* test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is
* seen once we return from the tag allocator.
*/
set_bit(BLK_MQ_S_INACTIVE, &hctx->state);
smp_mb__after_atomic();
/*
* Try to grab a reference to the queue and wait for any outstanding
* requests. If we could not grab a reference the queue has been
* frozen and there are no requests.
*/
if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) {
while (blk_mq_hctx_has_requests(hctx))
msleep(5);
percpu_ref_put(&hctx->queue->q_usage_counter);
}
return 0;
}
/*
* Check if one CPU is mapped to the specified hctx
*
* Isolated CPUs have been ruled out from hctx->cpumask, which is supposed
* to be used for scheduling kworker only. For other usage, please call this
* helper for checking if one CPU belongs to the specified hctx
*/
static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu,
const struct blk_mq_hw_ctx *hctx)
{
struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue,
hctx->type, cpu);
return mapped_hctx == hctx;
}
static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
{
struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
struct blk_mq_hw_ctx, cpuhp_online);
if (blk_mq_cpu_mapped_to_hctx(cpu, hctx))
clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
return 0;
}
/*
* 'cpu' is going away. splice any existing rq_list entries from this
* software queue to the hw queue dispatch list, and ensure that it
* gets run.
*/
static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
{
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
enum hctx_type type;
hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx))
return 0;
ctx = __blk_mq_get_ctx(hctx->queue, cpu);
type = hctx->type;
spin_lock(&ctx->lock);
if (!list_empty(&ctx->rq_lists[type])) {
list_splice_init(&ctx->rq_lists[type], &tmp);
blk_mq_hctx_clear_pending(hctx, ctx);
}
spin_unlock(&ctx->lock);
if (list_empty(&tmp))
return 0;
spin_lock(&hctx->lock);
list_splice_tail_init(&tmp, &hctx->dispatch);
spin_unlock(&hctx->lock);
blk_mq_run_hw_queue(hctx, true);
return 0;
}
static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
{
lockdep_assert_held(&blk_mq_cpuhp_lock);
if (!(hctx->flags & BLK_MQ_F_STACKING) &&
!hlist_unhashed(&hctx->cpuhp_online)) {
cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
&hctx->cpuhp_online);
INIT_HLIST_NODE(&hctx->cpuhp_online);
}
if (!hlist_unhashed(&hctx->cpuhp_dead)) {
cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
&hctx->cpuhp_dead);
INIT_HLIST_NODE(&hctx->cpuhp_dead);
}
}
static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
{
mutex_lock(&blk_mq_cpuhp_lock);
__blk_mq_remove_cpuhp(hctx);
mutex_unlock(&blk_mq_cpuhp_lock);
}
static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx)
{
lockdep_assert_held(&blk_mq_cpuhp_lock);
if (!(hctx->flags & BLK_MQ_F_STACKING) &&
hlist_unhashed(&hctx->cpuhp_online))
cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
&hctx->cpuhp_online);
if (hlist_unhashed(&hctx->cpuhp_dead))
cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD,
&hctx->cpuhp_dead);
}
static void __blk_mq_remove_cpuhp_list(struct list_head *head)
{
struct blk_mq_hw_ctx *hctx;
lockdep_assert_held(&blk_mq_cpuhp_lock);
list_for_each_entry(hctx, head, hctx_list)
__blk_mq_remove_cpuhp(hctx);
}
/*
* Unregister cpuhp callbacks from exited hw queues
*
* Safe to call if this `request_queue` is live
*/
static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q)
{
LIST_HEAD(hctx_list);
spin_lock(&q->unused_hctx_lock);
list_splice_init(&q->unused_hctx_list, &hctx_list);
spin_unlock(&q->unused_hctx_lock);
mutex_lock(&blk_mq_cpuhp_lock);
__blk_mq_remove_cpuhp_list(&hctx_list);
mutex_unlock(&blk_mq_cpuhp_lock);
spin_lock(&q->unused_hctx_lock);
list_splice(&hctx_list, &q->unused_hctx_list);
spin_unlock(&q->unused_hctx_lock);
}
/*
* Register cpuhp callbacks from all hw queues
*
* Safe to call if this `request_queue` is live
*/
static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
mutex_lock(&blk_mq_cpuhp_lock);
queue_for_each_hw_ctx(q, hctx, i)
__blk_mq_add_cpuhp(hctx);
mutex_unlock(&blk_mq_cpuhp_lock);
}
/*
* Before freeing hw queue, clearing the flush request reference in
* tags->rqs[] for avoiding potential UAF.
*/
static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
unsigned int queue_depth, struct request *flush_rq)
{
int i;
unsigned long flags;
/* The hw queue may not be mapped yet */
if (!tags)
return;
WARN_ON_ONCE(req_ref_read(flush_rq) != 0);
for (i = 0; i < queue_depth; i++)
cmpxchg(&tags->rqs[i], flush_rq, NULL);
/*
* Wait until all pending iteration is done.
*
* Request reference is cleared and it is guaranteed to be observed
* after the ->lock is released.
*/
spin_lock_irqsave(&tags->lock, flags);
spin_unlock_irqrestore(&tags->lock, flags);
}
/* hctx->ctxs will be freed in queue's release handler */
static void blk_mq_exit_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
struct request *flush_rq = hctx->fq->flush_rq;
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_idle(hctx);
if (blk_queue_init_done(q))
blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
set->queue_depth, flush_rq);
if (set->ops->exit_request)
set->ops->exit_request(set, flush_rq, hctx_idx);
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
xa_erase(&q->hctx_table, hctx_idx);
spin_lock(&q->unused_hctx_lock);
list_add(&hctx->hctx_list, &q->unused_hctx_list);
spin_unlock(&q->unused_hctx_lock);
}
static void blk_mq_exit_hw_queues(struct request_queue *q,
struct blk_mq_tag_set *set, int nr_queue)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i) {
if (i == nr_queue)
break;
blk_mq_remove_cpuhp(hctx);
blk_mq_exit_hctx(q, set, hctx, i);
}
}
static int blk_mq_init_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
{
hctx->queue_num = hctx_idx;
hctx->tags = set->tags[hctx_idx];
if (set->ops->init_hctx &&
set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
goto fail;
if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
hctx->numa_node))
goto exit_hctx;
if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL))
goto exit_flush_rq;
return 0;
exit_flush_rq:
if (set->ops->exit_request)
set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
exit_hctx:
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
fail:
return -1;
}
static struct blk_mq_hw_ctx *
blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
int node)
{
struct blk_mq_hw_ctx *hctx;
gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node);
if (!hctx)
goto fail_alloc_hctx;
if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node))
goto free_hctx;
atomic_set(&hctx->nr_active, 0);
if (node == NUMA_NO_NODE)
node = set->numa_node;
hctx->numa_node = node;
INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
INIT_HLIST_NODE(&hctx->cpuhp_dead);
INIT_HLIST_NODE(&hctx->cpuhp_online);
hctx->queue = q;
hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
INIT_LIST_HEAD(&hctx->hctx_list);
/*
* Allocate space for all possible cpus to avoid allocation at
* runtime
*/
hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
gfp, node);
if (!hctx->ctxs)
goto free_cpumask;
if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
gfp, node, false, false))
goto free_ctxs;
hctx->nr_ctx = 0;
spin_lock_init(&hctx->dispatch_wait_lock);
init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
if (!hctx->fq)
goto free_bitmap;
blk_mq_hctx_kobj_init(hctx);
return hctx;
free_bitmap:
sbitmap_free(&hctx->ctx_map);
free_ctxs:
kfree(hctx->ctxs);
free_cpumask:
free_cpumask_var(hctx->cpumask);
free_hctx:
kfree(hctx);
fail_alloc_hctx:
return NULL;
}
static void blk_mq_init_cpu_queues(struct request_queue *q,
unsigned int nr_hw_queues)
{
struct blk_mq_tag_set *set = q->tag_set;
unsigned int i, j;
for_each_possible_cpu(i) {
struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
struct blk_mq_hw_ctx *hctx;
int k;
__ctx->cpu = i;
spin_lock_init(&__ctx->lock);
for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++)
INIT_LIST_HEAD(&__ctx->rq_lists[k]);
__ctx->queue = q;
/*
* Set local node, IFF we have more than one hw queue. If
* not, we remain on the home node of the device
*/
for (j = 0; j < set->nr_maps; j++) {
hctx = blk_mq_map_queue_type(q, j, i);
if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
hctx->numa_node = cpu_to_node(i);
}
}
}
struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
unsigned int hctx_idx,
unsigned int depth)
{
struct blk_mq_tags *tags;
int ret;
tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags);
if (!tags)
return NULL;
ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth);
if (ret) {
blk_mq_free_rq_map(tags);
return NULL;
}
return tags;
}
static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
int hctx_idx)
{
if (blk_mq_is_shared_tags(set->flags)) {
set->tags[hctx_idx] = set->shared_tags;
return true;
}
set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx,
set->queue_depth);
return set->tags[hctx_idx];
}
void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
struct blk_mq_tags *tags,
unsigned int hctx_idx)
{
if (tags) {
blk_mq_free_rqs(set, tags, hctx_idx);
blk_mq_free_rq_map(tags);
}
}
static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
unsigned int hctx_idx)
{
if (!blk_mq_is_shared_tags(set->flags))
blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx);
set->tags[hctx_idx] = NULL;
}
static void blk_mq_map_swqueue(struct request_queue *q)
{
unsigned int j, hctx_idx;
unsigned long i;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
mutex_lock(&q->elevator_lock);
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
hctx->dispatch_from = NULL;
}
/*
* Map software to hardware queues.
*
* If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
ctx = per_cpu_ptr(q->queue_ctx, i);
for (j = 0; j < set->nr_maps; j++) {
if (!set->map[j].nr_queues) {
ctx->hctxs[j] = blk_mq_map_queue_type(q,
HCTX_TYPE_DEFAULT, i);
continue;
}
hctx_idx = set->map[j].mq_map[i];
/* unmapped hw queue can be remapped after CPU topo changed */
if (!set->tags[hctx_idx] &&
!__blk_mq_alloc_map_and_rqs(set, hctx_idx)) {
/*
* If tags initialization fail for some hctx,
* that hctx won't be brought online. In this
* case, remap the current ctx to hctx[0] which
* is guaranteed to always have tags allocated
*/
set->map[j].mq_map[i] = 0;
}
hctx = blk_mq_map_queue_type(q, j, i);
ctx->hctxs[j] = hctx;
/*
* If the CPU is already set in the mask, then we've
* mapped this one already. This can happen if
* devices share queues across queue maps.
*/
if (cpumask_test_cpu(i, hctx->cpumask))
continue;
cpumask_set_cpu(i, hctx->cpumask);
hctx->type = j;
ctx->index_hw[hctx->type] = hctx->nr_ctx;
hctx->ctxs[hctx->nr_ctx++] = ctx;
/*
* If the nr_ctx type overflows, we have exceeded the
* amount of sw queues we can support.
*/
BUG_ON(!hctx->nr_ctx);
}
for (; j < HCTX_MAX_TYPES; j++)
ctx->hctxs[j] = blk_mq_map_queue_type(q,
HCTX_TYPE_DEFAULT, i);
}
queue_for_each_hw_ctx(q, hctx, i) {
int cpu;
/*
* If no software queues are mapped to this hardware queue,
* disable it and free the request entries.
*/
if (!hctx->nr_ctx) {
/* Never unmap queue 0. We need it as a
* fallback in case of a new remap fails
* allocation
*/
if (i)
__blk_mq_free_map_and_rqs(set, i);
hctx->tags = NULL;
continue;
}
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
/*
* Set the map size to the number of mapped software queues.
* This is more accurate and more efficient than looping
* over all possibly mapped software queues.
*/
sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
/*
* Rule out isolated CPUs from hctx->cpumask to avoid
* running block kworker on isolated CPUs
*/
for_each_cpu(cpu, hctx->cpumask) {
if (cpu_is_isolated(cpu))
cpumask_clear_cpu(cpu, hctx->cpumask);
}
/*
* Initialize batch roundrobin counts
*/
hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
}
mutex_unlock(&q->elevator_lock);
}
/*
* Caller needs to ensure that we're either frozen/quiesced, or that
* the queue isn't live yet.
*/
static void queue_set_hctx_shared(struct request_queue *q, bool shared)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i) {
if (shared) {
hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
} else {
blk_mq_tag_idle(hctx);
hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
}
}
}
static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
bool shared)
{
struct request_queue *q;
unsigned int memflags;
lockdep_assert_held(&set->tag_list_lock);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
memflags = blk_mq_freeze_queue(q);
queue_set_hctx_shared(q, shared);
blk_mq_unfreeze_queue(q, memflags);
}
}
static void blk_mq_del_queue_tag_set(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
mutex_lock(&set->tag_list_lock);
list_del(&q->tag_set_list);
if (list_is_singular(&set->tag_list)) {
/* just transitioned to unshared */
set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
/* update existing queue */
blk_mq_update_tag_set_shared(set, false);
}
mutex_unlock(&set->tag_list_lock);
INIT_LIST_HEAD(&q->tag_set_list);
}
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
struct request_queue *q)
{
mutex_lock(&set->tag_list_lock);
/*
* Check to see if we're transitioning to shared (from 1 to 2 queues).
*/
if (!list_empty(&set->tag_list) &&
!(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
/* update existing queue */
blk_mq_update_tag_set_shared(set, true);
}
if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
queue_set_hctx_shared(q, true);
list_add_tail(&q->tag_set_list, &set->tag_list);
mutex_unlock(&set->tag_list_lock);
}
/* All allocations will be freed in release handler of q->mq_kobj */
static int blk_mq_alloc_ctxs(struct request_queue *q)
{
struct blk_mq_ctxs *ctxs;
int cpu;
ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL);
if (!ctxs)
return -ENOMEM;
ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx);
if (!ctxs->queue_ctx)
goto fail;
for_each_possible_cpu(cpu) {
struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu);
ctx->ctxs = ctxs;
}
q->mq_kobj = &ctxs->kobj;
q->queue_ctx = ctxs->queue_ctx;
return 0;
fail:
kfree(ctxs);
return -ENOMEM;
}
/*
* It is the actual release handler for mq, but we do it from
* request queue's release handler for avoiding use-after-free
* and headache because q->mq_kobj shouldn't have been introduced,
* but we can't group ctx/kctx kobj without it.
*/
void blk_mq_release(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx, *next;
unsigned long i;
queue_for_each_hw_ctx(q, hctx, i)
WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
/* all hctx are in .unused_hctx_list now */
list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) {
list_del_init(&hctx->hctx_list);
kobject_put(&hctx->kobj);
}
xa_destroy(&q->hctx_table);
/*
* release .mq_kobj and sw queue's kobject now because
* both share lifetime with request queue.
*/
blk_mq_sysfs_deinit(q);
}
struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
struct queue_limits *lim, void *queuedata)
{
struct queue_limits default_lim = { };
struct request_queue *q;
int ret;
if (!lim)
lim = &default_lim;
lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
if (set->nr_maps > HCTX_TYPE_POLL)
lim->features |= BLK_FEAT_POLL;
q = blk_alloc_queue(lim, set->numa_node);
if (IS_ERR(q))
return q;
q->queuedata = queuedata;
ret = blk_mq_init_allocated_queue(set, q);
if (ret) {
blk_put_queue(q);
return ERR_PTR(ret);
}
return q;
}
EXPORT_SYMBOL(blk_mq_alloc_queue);
/**
* blk_mq_destroy_queue - shutdown a request queue
* @q: request queue to shutdown
*
* This shuts down a request queue allocated by blk_mq_alloc_queue(). All future
* requests will be failed with -ENODEV. The caller is responsible for dropping
* the reference from blk_mq_alloc_queue() by calling blk_put_queue().
*
* Context: can sleep
*/
void blk_mq_destroy_queue(struct request_queue *q)
{
WARN_ON_ONCE(!queue_is_mq(q));
WARN_ON_ONCE(blk_queue_registered(q));
might_sleep();
blk_queue_flag_set(QUEUE_FLAG_DYING, q);
blk_queue_start_drain(q);
blk_mq_freeze_queue_wait(q);
blk_sync_queue(q);
blk_mq_cancel_work_sync(q);
blk_mq_exit_queue(q);
}
EXPORT_SYMBOL(blk_mq_destroy_queue);
struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
struct queue_limits *lim, void *queuedata,
struct lock_class_key *lkclass)
{
struct request_queue *q;
struct gendisk *disk;
q = blk_mq_alloc_queue(set, lim, queuedata);
if (IS_ERR(q))
return ERR_CAST(q);
disk = __alloc_disk_node(q, set->numa_node, lkclass);
if (!disk) {
blk_mq_destroy_queue(q);
blk_put_queue(q);
return ERR_PTR(-ENOMEM);
}
set_bit(GD_OWNS_QUEUE, &disk->state);
return disk;
}
EXPORT_SYMBOL(__blk_mq_alloc_disk);
struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
struct lock_class_key *lkclass)
{
struct gendisk *disk;
if (!blk_get_queue(q))
return NULL;
disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass);
if (!disk)
blk_put_queue(q);
return disk;
}
EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue);
/*
* Only hctx removed from cpuhp list can be reused
*/
static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx)
{
return hlist_unhashed(&hctx->cpuhp_online) &&
hlist_unhashed(&hctx->cpuhp_dead);
}
static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
struct blk_mq_tag_set *set, struct request_queue *q,
int hctx_idx, int node)
{
struct blk_mq_hw_ctx *hctx = NULL, *tmp;
/* reuse dead hctx first */
spin_lock(&q->unused_hctx_lock);
list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) {
if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) {
hctx = tmp;
break;
}
}
if (hctx)
list_del_init(&hctx->hctx_list);
spin_unlock(&q->unused_hctx_lock);
if (!hctx)
hctx = blk_mq_alloc_hctx(q, set, node);
if (!hctx)
goto fail;
if (blk_mq_init_hctx(q, set, hctx, hctx_idx))
goto free_hctx;
return hctx;
free_hctx:
kobject_put(&hctx->kobj);
fail:
return NULL;
}
static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i, j;
for (i = 0; i < set->nr_hw_queues; i++) {
int old_node;
int node = blk_mq_get_hctx_node(set, i);
struct blk_mq_hw_ctx *old_hctx = xa_load(&q->hctx_table, i);
if (old_hctx) {
old_node = old_hctx->numa_node;
blk_mq_exit_hctx(q, set, old_hctx, i);
}
if (!blk_mq_alloc_and_init_hctx(set, q, i, node)) {
if (!old_hctx)
break;
pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n",
node, old_node);
hctx = blk_mq_alloc_and_init_hctx(set, q, i, old_node);
WARN_ON_ONCE(!hctx);
}
}
/*
* Increasing nr_hw_queues fails. Free the newly allocated
* hctxs and keep the previous q->nr_hw_queues.
*/
if (i != set->nr_hw_queues) {
j = q->nr_hw_queues;
} else {
j = i;
q->nr_hw_queues = set->nr_hw_queues;
}
xa_for_each_start(&q->hctx_table, j, hctx, j)
blk_mq_exit_hctx(q, set, hctx, j);
}
static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct request_queue *q, bool lock)
{
if (lock) {
/* protect against switching io scheduler */
mutex_lock(&q->elevator_lock);
__blk_mq_realloc_hw_ctxs(set, q);
mutex_unlock(&q->elevator_lock);
} else {
__blk_mq_realloc_hw_ctxs(set, q);
}
/* unregister cpuhp callbacks for exited hctxs */
blk_mq_remove_hw_queues_cpuhp(q);
/* register cpuhp for new initialized hctxs */
blk_mq_add_hw_queues_cpuhp(q);
}
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q)
{
/* mark the queue as mq asap */
q->mq_ops = set->ops;
/*
* ->tag_set has to be setup before initialize hctx, which cpuphp
* handler needs it for checking queue mapping
*/
q->tag_set = set;
if (blk_mq_alloc_ctxs(q))
goto err_exit;
/* init q->mq_kobj and sw queues' kobjects */
blk_mq_sysfs_init(q);
INIT_LIST_HEAD(&q->unused_hctx_list);
spin_lock_init(&q->unused_hctx_lock);
xa_init(&q->hctx_table);
blk_mq_realloc_hw_ctxs(set, q, false);
if (!q->nr_hw_queues)
goto err_hctxs;
INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
INIT_LIST_HEAD(&q->flush_list);
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
q->nr_requests = set->queue_depth;
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q);
return 0;
err_hctxs:
blk_mq_release(q);
err_exit:
q->mq_ops = NULL;
return -ENOMEM;
}
EXPORT_SYMBOL(blk_mq_init_allocated_queue);
/* tags can _not_ be used after returning from blk_mq_exit_queue */
void blk_mq_exit_queue(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
/* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
/* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */
blk_mq_del_queue_tag_set(q);
}
static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
int i;
if (blk_mq_is_shared_tags(set->flags)) {
set->shared_tags = blk_mq_alloc_map_and_rqs(set,
BLK_MQ_NO_HCTX_IDX,
set->queue_depth);
if (!set->shared_tags)
return -ENOMEM;
}
for (i = 0; i < set->nr_hw_queues; i++) {
if (!__blk_mq_alloc_map_and_rqs(set, i))
goto out_unwind;
cond_resched();
}
return 0;
out_unwind:
while (--i >= 0)
__blk_mq_free_map_and_rqs(set, i);
if (blk_mq_is_shared_tags(set->flags)) {
blk_mq_free_map_and_rqs(set, set->shared_tags,
BLK_MQ_NO_HCTX_IDX);
}
return -ENOMEM;
}
/*
* Allocate the request maps associated with this tag_set. Note that this
* may reduce the depth asked for, if memory is tight. set->queue_depth
* will be updated to reflect the allocated depth.
*/
static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set)
{
unsigned int depth;
int err;
depth = set->queue_depth;
do {
err = __blk_mq_alloc_rq_maps(set);
if (!err)
break;
set->queue_depth >>= 1;
if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) {
err = -ENOMEM;
break;
}
} while (set->queue_depth);
if (!set->queue_depth || err) {
pr_err("blk-mq: failed to allocate request map\n");
return -ENOMEM;
}
if (depth != set->queue_depth)
pr_info("blk-mq: reduced tag depth (%u -> %u)\n",
depth, set->queue_depth);
return 0;
}
static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
{
/*
* blk_mq_map_queues() and multiple .map_queues() implementations
* expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the
* number of hardware queues.
*/
if (set->nr_maps == 1)
set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
if (set->ops->map_queues) {
int i;
/*
* transport .map_queues is usually done in the following
* way:
*
* for (queue = 0; queue < set->nr_hw_queues; queue++) {
* mask = get_cpu_mask(queue)
* for_each_cpu(cpu, mask)
* set->map[x].mq_map[cpu] = queue;
* }
*
* When we need to remap, the table has to be cleared for
* killing stale mapping since one CPU may not be mapped
* to any hw queue.
*/
for (i = 0; i < set->nr_maps; i++)
blk_mq_clear_mq_map(&set->map[i]);
set->ops->map_queues(set);
} else {
BUG_ON(set->nr_maps > 1);
blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
}
}
static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
int new_nr_hw_queues)
{
struct blk_mq_tags **new_tags;
int i;
if (set->nr_hw_queues >= new_nr_hw_queues)
goto done;
new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
GFP_KERNEL, set->numa_node);
if (!new_tags)
return -ENOMEM;
if (set->tags)
memcpy(new_tags, set->tags, set->nr_hw_queues *
sizeof(*set->tags));
kfree(set->tags);
set->tags = new_tags;
for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) {
if (!__blk_mq_alloc_map_and_rqs(set, i)) {
while (--i >= set->nr_hw_queues)
__blk_mq_free_map_and_rqs(set, i);
return -ENOMEM;
}
cond_resched();
}
done:
set->nr_hw_queues = new_nr_hw_queues;
return 0;
}
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
* requested depth down, if it's too large. In that case, the set
* value will be stored in set->queue_depth.
*/
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
int i, ret;
BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
if (!set->nr_hw_queues)
return -EINVAL;
if (!set->queue_depth)
return -EINVAL;
if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
return -EINVAL;
if (!set->ops->queue_rq)
return -EINVAL;
if (!set->ops->get_budget ^ !set->ops->put_budget)
return -EINVAL;
if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
pr_info("blk-mq: reduced tag depth to %u\n",
BLK_MQ_MAX_DEPTH);
set->queue_depth = BLK_MQ_MAX_DEPTH;
}
if (!set->nr_maps)
set->nr_maps = 1;
else if (set->nr_maps > HCTX_MAX_TYPES)
return -EINVAL;
/*
* If a crashdump is active, then we are potentially in a very
* memory constrained environment. Limit us to 64 tags to prevent
* using too much memory.
*/
if (is_kdump_kernel())
set->queue_depth = min(64U, set->queue_depth);
/*
* There is no use for more h/w queues than cpus if we just have
* a single map
*/
if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
set->nr_hw_queues = nr_cpu_ids;
if (set->flags & BLK_MQ_F_BLOCKING) {
set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL);
if (!set->srcu)
return -ENOMEM;
ret = init_srcu_struct(set->srcu);
if (ret)
goto out_free_srcu;
}
ret = -ENOMEM;
set->tags = kcalloc_node(set->nr_hw_queues,
sizeof(struct blk_mq_tags *), GFP_KERNEL,
set->numa_node);
if (!set->tags)
goto out_cleanup_srcu;
for (i = 0; i < set->nr_maps; i++) {
set->map[i].mq_map = kcalloc_node(nr_cpu_ids,
sizeof(set->map[i].mq_map[0]),
GFP_KERNEL, set->numa_node);
if (!set->map[i].mq_map)
goto out_free_mq_map;
set->map[i].nr_queues = set->nr_hw_queues;
}
blk_mq_update_queue_map(set);
ret = blk_mq_alloc_set_map_and_rqs(set);
if (ret)
goto out_free_mq_map;
mutex_init(&set->tag_list_lock);
INIT_LIST_HEAD(&set->tag_list);
return 0;
out_free_mq_map:
for (i = 0; i < set->nr_maps; i++) {
kfree(set->map[i].mq_map);
set->map[i].mq_map = NULL;
}
kfree(set->tags);
set->tags = NULL;
out_cleanup_srcu:
if (set->flags & BLK_MQ_F_BLOCKING)
cleanup_srcu_struct(set->srcu);
out_free_srcu:
if (set->flags & BLK_MQ_F_BLOCKING)
kfree(set->srcu);
return ret;
}
EXPORT_SYMBOL(blk_mq_alloc_tag_set);
/* allocate and initialize a tagset for a simple single-queue device */
int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops, unsigned int queue_depth,
unsigned int set_flags)
{
memset(set, 0, sizeof(*set));
set->ops = ops;
set->nr_hw_queues = 1;
set->nr_maps = 1;
set->queue_depth = queue_depth;
set->numa_node = NUMA_NO_NODE;
set->flags = set_flags;
return blk_mq_alloc_tag_set(set);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
{
int i, j;
for (i = 0; i < set->nr_hw_queues; i++)
__blk_mq_free_map_and_rqs(set, i);
if (blk_mq_is_shared_tags(set->flags)) {
blk_mq_free_map_and_rqs(set, set->shared_tags,
BLK_MQ_NO_HCTX_IDX);
}
for (j = 0; j < set->nr_maps; j++) {
kfree(set->map[j].mq_map);
set->map[j].mq_map = NULL;
}
kfree(set->tags);
set->tags = NULL;
if (set->flags & BLK_MQ_F_BLOCKING) {
cleanup_srcu_struct(set->srcu);
kfree(set->srcu);
}
}
EXPORT_SYMBOL(blk_mq_free_tag_set);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
{
struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
int ret;
unsigned long i;
if (WARN_ON_ONCE(!q->mq_freeze_depth))
return -EINVAL;
if (!set)
return -EINVAL;
if (q->nr_requests == nr)
return 0;
blk_mq_quiesce_queue(q);
ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx->tags)
continue;
/*
* If we're using an MQ scheduler, just update the scheduler
* queue depth. This is similar to what the old code would do.
*/
if (hctx->sched_tags) {
ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
nr, true);
} else {
ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
false);
}
if (ret)
break;
if (q->elevator && q->elevator->type->ops.depth_updated)
q->elevator->type->ops.depth_updated(hctx);
}
if (!ret) {
q->nr_requests = nr;
if (blk_mq_is_shared_tags(set->flags)) {
if (q->elevator)
blk_mq_tag_update_sched_shared_tags(q);
else
blk_mq_tag_resize_shared_tags(set, nr);
}
}
blk_mq_unquiesce_queue(q);
return ret;
}
/*
* request_queue and elevator_type pair.
* It is just used by __blk_mq_update_nr_hw_queues to cache
* the elevator_type associated with a request_queue.
*/
struct blk_mq_qe_pair {
struct list_head node;
struct request_queue *q;
struct elevator_type *type;
};
/*
* Cache the elevator_type in qe pair list and switch the
* io scheduler to 'none'
*/
static bool blk_mq_elv_switch_none(struct list_head *head,
struct request_queue *q)
{
struct blk_mq_qe_pair *qe;
qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
if (!qe)
return false;
/* Accessing q->elevator needs protection from ->elevator_lock. */
mutex_lock(&q->elevator_lock);
if (!q->elevator) {
kfree(qe);
goto unlock;
}
INIT_LIST_HEAD(&qe->node);
qe->q = q;
qe->type = q->elevator->type;
/* keep a reference to the elevator module as we'll switch back */
__elevator_get(qe->type);
list_add(&qe->node, head);
elevator_disable(q);
unlock:
mutex_unlock(&q->elevator_lock);
return true;
}
static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head,
struct request_queue *q)
{
struct blk_mq_qe_pair *qe;
list_for_each_entry(qe, head, node)
if (qe->q == q)
return qe;
return NULL;
}
static void blk_mq_elv_switch_back(struct list_head *head,
struct request_queue *q)
{
struct blk_mq_qe_pair *qe;
struct elevator_type *t;
qe = blk_lookup_qe_pair(head, q);
if (!qe)
return;
t = qe->type;
list_del(&qe->node);
kfree(qe);
mutex_lock(&q->elevator_lock);
elevator_switch(q, t);
/* drop the reference acquired in blk_mq_elv_switch_none */
elevator_put(t);
mutex_unlock(&q->elevator_lock);
}
static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
int nr_hw_queues)
{
struct request_queue *q;
LIST_HEAD(head);
int prev_nr_hw_queues = set->nr_hw_queues;
unsigned int memflags;
int i;
lockdep_assert_held(&set->tag_list_lock);
if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids)
nr_hw_queues = nr_cpu_ids;
if (nr_hw_queues < 1)
return;
if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
return;
memflags = memalloc_noio_save();
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_freeze_queue_nomemsave(q);
/*
* Switch IO scheduler to 'none', cleaning up the data associated
* with the previous scheduler. We will switch back once we are done
* updating the new sw to hw queue mappings.
*/
list_for_each_entry(q, &set->tag_list, tag_set_list)
if (!blk_mq_elv_switch_none(&head, q))
goto switch_back;
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_debugfs_unregister_hctxs(q);
blk_mq_sysfs_unregister_hctxs(q);
}
if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
goto reregister;
fallback:
blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q, true);
if (q->nr_hw_queues != set->nr_hw_queues) {
int i = prev_nr_hw_queues;
pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n",
nr_hw_queues, prev_nr_hw_queues);
for (; i < set->nr_hw_queues; i++)
__blk_mq_free_map_and_rqs(set, i);
set->nr_hw_queues = prev_nr_hw_queues;
goto fallback;
}
blk_mq_map_swqueue(q);
}
reregister:
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_sysfs_register_hctxs(q);
blk_mq_debugfs_register_hctxs(q);
}
switch_back:
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_elv_switch_back(&head, q);
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue_nomemrestore(q);
memalloc_noio_restore(memflags);
/* Free the excess tags when nr_hw_queues shrink. */
for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)
__blk_mq_free_map_and_rqs(set, i);
}
void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
{
mutex_lock(&set->tag_list_lock);
__blk_mq_update_nr_hw_queues(set, nr_hw_queues);
mutex_unlock(&set->tag_list_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
struct io_comp_batch *iob, unsigned int flags)
{
long state = get_current_state();
int ret;
do {
ret = q->mq_ops->poll(hctx, iob);
if (ret > 0) {
__set_current_state(TASK_RUNNING);
return ret;
}
if (signal_pending_state(state, current))
__set_current_state(TASK_RUNNING);
if (task_is_running(current))
return 1;
if (ret < 0 || (flags & BLK_POLL_ONESHOT))
break;
cpu_relax();
} while (!need_resched());
__set_current_state(TASK_RUNNING);
return 0;
}
int blk_mq_poll(struct request_queue *q, blk_qc_t cookie,
struct io_comp_batch *iob, unsigned int flags)
{
if (!blk_mq_can_poll(q))
return 0;
return blk_hctx_poll(q, xa_load(&q->hctx_table, cookie), iob, flags);
}
int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,
unsigned int poll_flags)
{
struct request_queue *q = rq->q;
int ret;
if (!blk_rq_is_poll(rq))
return 0;
if (!percpu_ref_tryget(&q->q_usage_counter))
return 0;
ret = blk_hctx_poll(q, rq->mq_hctx, iob, poll_flags);
blk_queue_exit(q);
return ret;
}
EXPORT_SYMBOL_GPL(blk_rq_poll);
unsigned int blk_mq_rq_cpu(struct request *rq)
{
return rq->mq_ctx->cpu;
}
EXPORT_SYMBOL(blk_mq_rq_cpu);
void blk_mq_cancel_work_sync(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned long i;
cancel_delayed_work_sync(&q->requeue_work);
queue_for_each_hw_ctx(q, hctx, i)
cancel_delayed_work_sync(&hctx->run_work);
}
static int __init blk_mq_init(void)
{
int i;
for_each_possible_cpu(i)
init_llist_head(&per_cpu(blk_cpu_done, i));
for_each_possible_cpu(i)
INIT_CSD(&per_cpu(blk_cpu_csd, i),
__blk_mq_complete_request_remote, NULL);
open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
"block/softirq:dead", NULL,
blk_softirq_cpu_dead);
cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
blk_mq_hctx_notify_dead);
cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online",
blk_mq_hctx_notify_online,
blk_mq_hctx_notify_offline);
return 0;
}
subsys_initcall(blk_mq_init);
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_FORTIFY_STRING_H_
#define _LINUX_FORTIFY_STRING_H_
#include <linux/bitfield.h>
#include <linux/bug.h>
#include <linux/const.h>
#include <linux/limits.h>
#define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable
#define __RENAME(x) __asm__(#x)
#define FORTIFY_REASON_DIR(r) FIELD_GET(BIT(0), r)
#define FORTIFY_REASON_FUNC(r) FIELD_GET(GENMASK(7, 1), r)
#define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \
FIELD_PREP(GENMASK(7, 1), func))
/* Overridden by KUnit tests. */
#ifndef fortify_panic
# define fortify_panic(func, write, avail, size, retfail) \
__fortify_panic(FORTIFY_REASON(func, write), avail, size)
#endif
#ifndef fortify_warn_once
# define fortify_warn_once(x...) WARN_ONCE(x)
#endif
#define FORTIFY_READ 0
#define FORTIFY_WRITE 1
#define EACH_FORTIFY_FUNC(macro) \
macro(strncpy), \
macro(strnlen), \
macro(strlen), \
macro(strscpy), \
macro(strlcat), \
macro(strcat), \
macro(strncat), \
macro(memset), \
macro(memcpy), \
macro(memmove), \
macro(memscan), \
macro(memcmp), \
macro(memchr), \
macro(memchr_inv), \
macro(kmemdup), \
macro(strcpy), \
macro(UNKNOWN),
#define MAKE_FORTIFY_FUNC(func) FORTIFY_FUNC_##func
enum fortify_func {
EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC)
};
void __fortify_report(const u8 reason, const size_t avail, const size_t size);
void __fortify_panic(const u8 reason, const size_t avail, const size_t size) __cold __noreturn;
void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)");
void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)");
void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?");
void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)");
void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?");
#define __compiletime_strlen(p) \
({ \
char *__p = (char *)(p); \
size_t __ret = SIZE_MAX; \
const size_t __p_size = __member_size(p); \
if (__p_size != SIZE_MAX && \
__builtin_constant_p(*__p)) { \
size_t __p_len = __p_size - 1; \
if (__builtin_constant_p(__p[__p_len]) && \
__p[__p_len] == '\0') \
__ret = __builtin_strlen(__p); \
} \
__ret; \
})
#if defined(__SANITIZE_ADDRESS__)
#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY)
extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
#elif defined(CONFIG_KASAN_GENERIC)
extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset);
extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove);
extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy);
#else /* CONFIG_KASAN_SW_TAGS */
extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset);
extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove);
extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy);
#endif
extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
#else
#if defined(__SANITIZE_MEMORY__)
/*
* For KMSAN builds all memcpy/memset/memmove calls should be replaced by the
* corresponding __msan_XXX functions.
*/
#include <linux/kmsan_string.h>
#define __underlying_memcpy __msan_memcpy
#define __underlying_memmove __msan_memmove
#define __underlying_memset __msan_memset
#else
#define __underlying_memcpy __builtin_memcpy
#define __underlying_memmove __builtin_memmove
#define __underlying_memset __builtin_memset
#endif
#define __underlying_memchr __builtin_memchr
#define __underlying_memcmp __builtin_memcmp
#define __underlying_strcat __builtin_strcat
#define __underlying_strcpy __builtin_strcpy
#define __underlying_strlen __builtin_strlen
#define __underlying_strncat __builtin_strncat
#define __underlying_strncpy __builtin_strncpy
#endif
/**
* unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking
*
* @dst: Destination memory address to write to
* @src: Source memory address to read from
* @bytes: How many bytes to write to @dst from @src
* @justification: Free-form text or comment describing why the use is needed
*
* This should be used for corner cases where the compiler cannot do the
* right thing, or during transitions between APIs, etc. It should be used
* very rarely, and includes a place for justification detailing where bounds
* checking has happened, and why existing solutions cannot be employed.
*/
#define unsafe_memcpy(dst, src, bytes, justification) \
__underlying_memcpy(dst, src, bytes)
/*
* Clang's use of __builtin_*object_size() within inlines needs hinting via
* __pass_*object_size(). The preference is to only ever use type 1 (member
* size, rather than struct size), but there remain some stragglers using
* type 0 that will be converted in the future.
*/
#if __has_builtin(__builtin_dynamic_object_size)
#define POS __pass_dynamic_object_size(1)
#define POS0 __pass_dynamic_object_size(0)
#else
#define POS __pass_object_size(1)
#define POS0 __pass_object_size(0)
#endif
#define __compiletime_lessthan(bounds, length) ( \
__builtin_constant_p((bounds) < (length)) && \
(bounds) < (length) \
)
/**
* strncpy - Copy a string to memory with non-guaranteed NUL padding
*
* @p: pointer to destination of copy
* @q: pointer to NUL-terminated source string to copy
* @size: bytes to write at @p
*
* If strlen(@q) >= @size, the copy of @q will stop after @size bytes,
* and @p will NOT be NUL-terminated
*
* If strlen(@q) < @size, following the copy of @q, trailing NUL bytes
* will be written to @p until @size total bytes have been written.
*
* Do not use this function. While FORTIFY_SOURCE tries to avoid
* over-reads of @q, it cannot defend against writing unterminated
* results to @p. Using strncpy() remains ambiguous and fragile.
* Instead, please choose an alternative, so that the expectation
* of @p's contents is unambiguous:
*
* +--------------------+--------------------+------------+
* | **p** needs to be: | padded to **size** | not padded |
* +====================+====================+============+
* | NUL-terminated | strscpy_pad() | strscpy() |
* +--------------------+--------------------+------------+
* | not NUL-terminated | strtomem_pad() | strtomem() |
* +--------------------+--------------------+------------+
*
* Note strscpy*()'s differing return values for detecting truncation,
* and strtomem*()'s expectation that the destination is marked with
* __nonstring when it is a character array.
*
*/
__FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3)
char *strncpy(char * const POS p, const char *q, __kernel_size_t size)
{
const size_t p_size = __member_size(p);
if (__compiletime_lessthan(p_size, size))
__write_overflow();
if (p_size < size)
fortify_panic(FORTIFY_FUNC_strncpy, FORTIFY_WRITE, p_size, size, p);
return __underlying_strncpy(p, q, size);
}
extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
/**
* strnlen - Return bounded count of characters in a NUL-terminated string
*
* @p: pointer to NUL-terminated string to count.
* @maxlen: maximum number of characters to count.
*
* Returns number of characters in @p (NOT including the final NUL), or
* @maxlen, if no NUL has been found up to there.
*
*/
__FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen)
{
const size_t p_size = __member_size(p);
const size_t p_len = __compiletime_strlen(p);
size_t ret;
/* We can take compile-time actions when maxlen is const. */
if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) {
/* If p is const, we can use its compile-time-known len. */
if (maxlen >= p_size)
return p_len;
}
/* Do not check characters beyond the end of p. */
ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size);
if (p_size <= ret && maxlen != ret)
fortify_panic(FORTIFY_FUNC_strnlen, FORTIFY_READ, p_size, ret + 1, ret);
return ret;
}
/*
* Defined after fortified strnlen to reuse it. However, it must still be
* possible for strlen() to be used on compile-time strings for use in
* static initializers (i.e. as a constant expression).
*/
/**
* strlen - Return count of characters in a NUL-terminated string
*
* @p: pointer to NUL-terminated string to count.
*
* Do not use this function unless the string length is known at
* compile-time. When @p is unterminated, this function may crash
* or return unexpected counts that could lead to memory content
* exposures. Prefer strnlen().
*
* Returns number of characters in @p (NOT including the final NUL).
*
*/
#define strlen(p) \
__builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \
__builtin_strlen(p), __fortify_strlen(p))
__FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1)
__kernel_size_t __fortify_strlen(const char * const POS p)
{
const size_t p_size = __member_size(p);
__kernel_size_t ret;
/* Give up if we don't know how large p is. */
if (p_size == SIZE_MAX)
return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(FORTIFY_FUNC_strlen, FORTIFY_READ, p_size, ret + 1, ret);
return ret;
}
/* Defined after fortified strnlen() to reuse it. */
extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy);
__FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size)
{
/* Use string size rather than possible enclosing struct size. */
const size_t p_size = __member_size(p);
const size_t q_size = __member_size(q);
size_t len;
/* If we cannot get size of p and q default to call strscpy. */
if (p_size == SIZE_MAX && q_size == SIZE_MAX)
return __real_strscpy(p, q, size);
/*
* If size can be known at compile time and is greater than
* p_size, generate a compile time write overflow error.
*/
if (__compiletime_lessthan(p_size, size))
__write_overflow();
/* Short-circuit for compile-time known-safe lengths. */
if (__compiletime_lessthan(p_size, SIZE_MAX)) {
len = __compiletime_strlen(q);
if (len < SIZE_MAX && __compiletime_lessthan(len, size)) {
__underlying_memcpy(p, q, len + 1);
return len;
}
}
/*
* This call protects from read overflow, because len will default to q
* length if it smaller than size.
*/
len = strnlen(q, size);
/*
* If len equals size, we will copy only size bytes which leads to
* -E2BIG being returned.
* Otherwise we will copy len + 1 because of the final '\O'.
*/
len = len == size ? size : len + 1;
/*
* Generate a runtime write overflow error if len is greater than
* p_size.
*/
if (p_size < len)
fortify_panic(FORTIFY_FUNC_strscpy, FORTIFY_WRITE, p_size, len, -E2BIG);
/*
* We can now safely call vanilla strscpy because we are protected from:
* 1. Read overflow thanks to call to strnlen().
* 2. Write overflow thanks to above ifs.
*/
return __real_strscpy(p, q, len);
}
/* Defined after fortified strlen() to reuse it. */
extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat);
/**
* strlcat - Append a string to an existing string
*
* @p: pointer to %NUL-terminated string to append to
* @q: pointer to %NUL-terminated string to append from
* @avail: Maximum bytes available in @p
*
* Appends %NUL-terminated string @q after the %NUL-terminated
* string at @p, but will not write beyond @avail bytes total,
* potentially truncating the copy from @q. @p will stay
* %NUL-terminated only if a %NUL already existed within
* the @avail bytes of @p. If so, the resulting number of
* bytes copied from @q will be at most "@avail - strlen(@p) - 1".
*
* Do not use this function. While FORTIFY_SOURCE tries to avoid
* read and write overflows, this is only possible when the sizes
* of @p and @q are known to the compiler. Prefer building the
* string with formatting, via scnprintf(), seq_buf, or similar.
*
* Returns total bytes that _would_ have been contained by @p
* regardless of truncation, similar to snprintf(). If return
* value is >= @avail, the string has been truncated.
*
*/
__FORTIFY_INLINE
size_t strlcat(char * const POS p, const char * const POS q, size_t avail)
{
const size_t p_size = __member_size(p);
const size_t q_size = __member_size(q);
size_t p_len, copy_len;
size_t actual, wanted;
/* Give up immediately if both buffer sizes are unknown. */
if (p_size == SIZE_MAX && q_size == SIZE_MAX)
return __real_strlcat(p, q, avail);
p_len = strnlen(p, avail);
copy_len = strlen(q);
wanted = actual = p_len + copy_len;
/* Cannot append any more: report truncation. */
if (avail <= p_len)
return wanted;
/* Give up if string is already overflowed. */
if (p_size <= p_len)
fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_READ, p_size, p_len + 1, wanted);
if (actual >= avail) {
copy_len = avail - p_len - 1;
actual = p_len + copy_len;
}
/* Give up if copy will overflow. */
if (p_size <= actual)
fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_WRITE, p_size, actual + 1, wanted);
__underlying_memcpy(p + p_len, q, copy_len);
p[actual] = '\0';
return wanted;
}
/* Defined after fortified strlcat() to reuse it. */
/**
* strcat - Append a string to an existing string
*
* @p: pointer to NUL-terminated string to append to
* @q: pointer to NUL-terminated source string to append from
*
* Do not use this function. While FORTIFY_SOURCE tries to avoid
* read and write overflows, this is only possible when the
* destination buffer size is known to the compiler. Prefer
* building the string with formatting, via scnprintf() or similar.
* At the very least, use strncat().
*
* Returns @p.
*
*/
__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2)
char *strcat(char * const POS p, const char *q)
{
const size_t p_size = __member_size(p);
const size_t wanted = strlcat(p, q, p_size); if (p_size <= wanted) fortify_panic(FORTIFY_FUNC_strcat, FORTIFY_WRITE, p_size, wanted + 1, p);
return p;
}
/**
* strncat - Append a string to an existing string
*
* @p: pointer to NUL-terminated string to append to
* @q: pointer to source string to append from
* @count: Maximum bytes to read from @q
*
* Appends at most @count bytes from @q (stopping at the first
* NUL byte) after the NUL-terminated string at @p. @p will be
* NUL-terminated.
*
* Do not use this function. While FORTIFY_SOURCE tries to avoid
* read and write overflows, this is only possible when the sizes
* of @p and @q are known to the compiler. Prefer building the
* string with formatting, via scnprintf() or similar.
*
* Returns @p.
*
*/
/* Defined after fortified strlen() and strnlen() to reuse them. */
__FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3)
char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count)
{
const size_t p_size = __member_size(p);
const size_t q_size = __member_size(q);
size_t p_len, copy_len, total;
if (p_size == SIZE_MAX && q_size == SIZE_MAX)
return __underlying_strncat(p, q, count);
p_len = strlen(p);
copy_len = strnlen(q, count);
total = p_len + copy_len + 1;
if (p_size < total)
fortify_panic(FORTIFY_FUNC_strncat, FORTIFY_WRITE, p_size, total, p);
__underlying_memcpy(p + p_len, q, copy_len);
p[p_len + copy_len] = '\0';
return p;
}
__FORTIFY_INLINE bool fortify_memset_chk(__kernel_size_t size,
const size_t p_size,
const size_t p_size_field)
{
if (__builtin_constant_p(size)) {
/*
* Length argument is a constant expression, so we
* can perform compile-time bounds checking where
* buffer sizes are also known at compile time.
*/
/* Error when size is larger than enclosing struct. */
if (__compiletime_lessthan(p_size_field, p_size) &&
__compiletime_lessthan(p_size, size))
__write_overflow();
/* Warn when write size is larger than dest field. */
if (__compiletime_lessthan(p_size_field, size))
__write_overflow_field(p_size_field, size);
}
/*
* At this point, length argument may not be a constant expression,
* so run-time bounds checking can be done where buffer sizes are
* known. (This is not an "else" because the above checks may only
* be compile-time warnings, and we want to still warn for run-time
* overflows.)
*/
/*
* Always stop accesses beyond the struct that contains the
* field, when the buffer's remaining size is known.
* (The SIZE_MAX test is to optimize away checks where the buffer
* lengths are unknown.)
*/
if (p_size != SIZE_MAX && p_size < size)
fortify_panic(FORTIFY_FUNC_memset, FORTIFY_WRITE, p_size, size, true);
return false;
}
#define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \
size_t __fortify_size = (size_t)(size); \
fortify_memset_chk(__fortify_size, p_size, p_size_field), \
__underlying_memset(p, c, __fortify_size); \
})
/*
* __struct_size() vs __member_size() must be captured here to avoid
* evaluating argument side-effects further into the macro layers.
*/
#ifndef CONFIG_KMSAN
#define memset(p, c, s) __fortify_memset_chk(p, c, s, \
__struct_size(p), __member_size(p))
#endif
/*
* To make sure the compiler can enforce protection against buffer overflows,
* memcpy(), memmove(), and memset() must not be used beyond individual
* struct members. If you need to copy across multiple members, please use
* struct_group() to create a named mirror of an anonymous struct union.
* (e.g. see struct sk_buff.) Read overflow checking is currently only
* done when a write overflow is also present, or when building with W=1.
*
* Mitigation coverage matrix
* Bounds checking at:
* +-------+-------+-------+-------+
* | Compile time | Run time |
* memcpy() argument sizes: | write | read | write | read |
* dest source length +-------+-------+-------+-------+
* memcpy(known, known, constant) | y | y | n/a | n/a |
* memcpy(known, unknown, constant) | y | n | n/a | V |
* memcpy(known, known, dynamic) | n | n | B | B |
* memcpy(known, unknown, dynamic) | n | n | B | V |
* memcpy(unknown, known, constant) | n | y | V | n/a |
* memcpy(unknown, unknown, constant) | n | n | V | V |
* memcpy(unknown, known, dynamic) | n | n | V | B |
* memcpy(unknown, unknown, dynamic) | n | n | V | V |
* +-------+-------+-------+-------+
*
* y = perform deterministic compile-time bounds checking
* n = cannot perform deterministic compile-time bounds checking
* n/a = no run-time bounds checking needed since compile-time deterministic
* B = can perform run-time bounds checking (currently unimplemented)
* V = vulnerable to run-time overflow (will need refactoring to solve)
*
*/
__FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
const size_t p_size,
const size_t q_size,
const size_t p_size_field,
const size_t q_size_field,
const u8 func)
{
if (__builtin_constant_p(size)) {
/*
* Length argument is a constant expression, so we
* can perform compile-time bounds checking where
* buffer sizes are also known at compile time.
*/
/* Error when size is larger than enclosing struct. */
if (__compiletime_lessthan(p_size_field, p_size) &&
__compiletime_lessthan(p_size, size))
__write_overflow();
if (__compiletime_lessthan(q_size_field, q_size) &&
__compiletime_lessthan(q_size, size))
__read_overflow2();
/* Warn when write size argument larger than dest field. */
if (__compiletime_lessthan(p_size_field, size))
__write_overflow_field(p_size_field, size);
/*
* Warn for source field over-read when building with W=1
* or when an over-write happened, so both can be fixed at
* the same time.
*/
if ((IS_ENABLED(KBUILD_EXTRA_WARN1) ||
__compiletime_lessthan(p_size_field, size)) &&
__compiletime_lessthan(q_size_field, size))
__read_overflow2_field(q_size_field, size);
}
/*
* At this point, length argument may not be a constant expression,
* so run-time bounds checking can be done where buffer sizes are
* known. (This is not an "else" because the above checks may only
* be compile-time warnings, and we want to still warn for run-time
* overflows.)
*/
/*
* Always stop accesses beyond the struct that contains the
* field, when the buffer's remaining size is known.
* (The SIZE_MAX test is to optimize away checks where the buffer
* lengths are unknown.)
*/
if (p_size != SIZE_MAX && p_size < size)
fortify_panic(func, FORTIFY_WRITE, p_size, size, true); else if (q_size != SIZE_MAX && q_size < size) fortify_panic(func, FORTIFY_READ, p_size, size, true);
/*
* Warn when writing beyond destination field size.
*
* Note the implementation of __builtin_*object_size() behaves
* like sizeof() when not directly referencing a flexible
* array member, which means there will be many bounds checks
* that will appear at run-time, without a way for them to be
* detected at compile-time (as can be done when the destination
* is specifically the flexible array member).
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832
*/
if (p_size_field != SIZE_MAX &&
p_size != p_size_field && p_size_field < size)
return true;
return false;
}
/*
* To work around what seems to be an optimizer bug, the macro arguments
* need to have const copies or the values end up changed by the time they
* reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture
* __bos() results in const temp vars") for more details.
*/
#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \
p_size_field, q_size_field, op) ({ \
const size_t __fortify_size = (size_t)(size); \
const size_t __p_size = (p_size); \
const size_t __q_size = (q_size); \
const size_t __p_size_field = (p_size_field); \
const size_t __q_size_field = (q_size_field); \
/* Keep a mutable version of the size for the final copy. */ \
size_t __copy_size = __fortify_size; \
fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \
__q_size, __p_size_field, \
__q_size_field, FORTIFY_FUNC_ ##op), \
#op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \
__fortify_size, \
"field \"" #p "\" at " FILE_LINE, \
__p_size_field); \
/* Hide only the run-time size from value range tracking to */ \
/* silence compile-time false positive bounds warnings. */ \
if (!__builtin_constant_p(__copy_size)) \
OPTIMIZER_HIDE_VAR(__copy_size); \
__underlying_##op(p, q, __copy_size); \
})
/*
* Notes about compile-time buffer size detection:
*
* With these types...
*
* struct middle {
* u16 a;
* u8 middle_buf[16];
* int b;
* };
* struct end {
* u16 a;
* u8 end_buf[16];
* };
* struct flex {
* int a;
* u8 flex_buf[];
* };
*
* void func(TYPE *ptr) { ... }
*
* Cases where destination size cannot be currently detected:
* - the size of ptr's object (seemingly by design, gcc & clang fail):
* __builtin_object_size(ptr, 1) == SIZE_MAX
* - the size of flexible arrays in ptr's obj (by design, dynamic size):
* __builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX
* - the size of ANY array at the end of ptr's obj (gcc and clang bug):
* __builtin_object_size(ptr->end_buf, 1) == SIZE_MAX
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836
*
* Cases where destination size is currently detected:
* - the size of non-array members within ptr's object:
* __builtin_object_size(ptr->a, 1) == 2
* - the size of non-flexible-array in the middle of ptr's obj:
* __builtin_object_size(ptr->middle_buf, 1) == 16
*
*/
/*
* __struct_size() vs __member_size() must be captured here to avoid
* evaluating argument side-effects further into the macro layers.
*/
#define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \
__struct_size(p), __struct_size(q), \
__member_size(p), __member_size(q), \
memcpy)
#define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \
__struct_size(p), __struct_size(q), \
__member_size(p), __member_size(q), \
memmove)
extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
__FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size)
{
const size_t p_size = __struct_size(p);
if (__compiletime_lessthan(p_size, size))
__read_overflow();
if (p_size < size)
fortify_panic(FORTIFY_FUNC_memscan, FORTIFY_READ, p_size, size, NULL);
return __real_memscan(p, c, size);
}
__FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3)
int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size)
{
const size_t p_size = __struct_size(p);
const size_t q_size = __struct_size(q);
if (__builtin_constant_p(size)) {
if (__compiletime_lessthan(p_size, size))
__read_overflow();
if (__compiletime_lessthan(q_size, size))
__read_overflow2();
}
if (p_size < size)
fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, p_size, size, INT_MIN);
else if (q_size < size)
fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, q_size, size, INT_MIN);
return __underlying_memcmp(p, q, size);
}
__FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3)
void *memchr(const void * const POS0 p, int c, __kernel_size_t size)
{
const size_t p_size = __struct_size(p);
if (__compiletime_lessthan(p_size, size))
__read_overflow();
if (p_size < size)
fortify_panic(FORTIFY_FUNC_memchr, FORTIFY_READ, p_size, size, NULL);
return __underlying_memchr(p, c, size);
}
void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
__FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size)
{
const size_t p_size = __struct_size(p);
if (__compiletime_lessthan(p_size, size))
__read_overflow();
if (p_size < size)
fortify_panic(FORTIFY_FUNC_memchr_inv, FORTIFY_READ, p_size, size, NULL);
return __real_memchr_inv(p, c, size);
}
extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof)
__realloc_size(2);
__FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp)
{
const size_t p_size = __struct_size(p);
if (__compiletime_lessthan(p_size, size))
__read_overflow();
if (p_size < size)
fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size,
__real_kmemdup(p, 0, gfp));
return __real_kmemdup(p, size, gfp);
}
#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__))
/**
* strcpy - Copy a string into another string buffer
*
* @p: pointer to destination of copy
* @q: pointer to NUL-terminated source string to copy
*
* Do not use this function. While FORTIFY_SOURCE tries to avoid
* overflows, this is only possible when the sizes of @q and @p are
* known to the compiler. Prefer strscpy(), though note its different
* return values for detecting truncation.
*
* Returns @p.
*
*/
/* Defined after fortified strlen to reuse it. */
__FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2)
char *strcpy(char * const POS p, const char * const POS q)
{
const size_t p_size = __member_size(p);
const size_t q_size = __member_size(q);
size_t size;
/* If neither buffer size is known, immediately give up. */
if (__builtin_constant_p(p_size) &&
__builtin_constant_p(q_size) &&
p_size == SIZE_MAX && q_size == SIZE_MAX)
return __underlying_strcpy(p, q);
size = strlen(q) + 1;
/* Compile-time check for const size overflow. */
if (__compiletime_lessthan(p_size, size))
__write_overflow();
/* Run-time check for dynamic size overflow. */
if (p_size < size)
fortify_panic(FORTIFY_FUNC_strcpy, FORTIFY_WRITE, p_size, size, p);
__underlying_memcpy(p, q, size);
return p;
}
/* Don't use these outside the FORITFY_SOURCE implementation */
#undef __underlying_memchr
#undef __underlying_memcmp
#undef __underlying_strcat
#undef __underlying_strcpy
#undef __underlying_strlen
#undef __underlying_strncat
#undef __underlying_strncpy
#undef POS
#undef POS0
#endif /* _LINUX_FORTIFY_STRING_H_ */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Fault injection for both 32 and 64bit guests.
*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Based on arch/arm/kvm/emulate.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <hyp/adjust_pc.h>
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__)
#error Hypervisor code only!
#endif
static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
{
u64 val;
if (unlikely(vcpu_has_nv(vcpu))) return vcpu_read_sys_reg(vcpu, reg);
else if (__vcpu_read_sys_reg_from_cpu(reg, &val))
return val;
return __vcpu_sys_reg(vcpu, reg);
}
static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
{
if (unlikely(vcpu_has_nv(vcpu))) vcpu_write_sys_reg(vcpu, val, reg);
else if (!__vcpu_write_sys_reg_to_cpu(val, reg))
__vcpu_sys_reg(vcpu, reg) = val;
}
static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
u64 val)
{
if (unlikely(vcpu_has_nv(vcpu))) {
if (target_mode == PSR_MODE_EL1h)
vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
else
vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
} else if (has_vhe()) {
write_sysreg_el1(val, SYS_SPSR);
} else {
__vcpu_sys_reg(vcpu, SPSR_EL1) = val;
}
}
static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
{
if (has_vhe())
write_sysreg(val, spsr_abt);
else
vcpu->arch.ctxt.spsr_abt = val;
}
static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val)
{
if (has_vhe())
write_sysreg(val, spsr_und);
else
vcpu->arch.ctxt.spsr_und = val;
}
/*
* This performs the exception entry at a given EL (@target_mode), stashing PC
* and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE.
* The EL passed to this function *must* be a non-secure, privileged mode with
* bit 0 being set (PSTATE.SP == 1).
*
* When an exception is taken, most PSTATE fields are left unchanged in the
* handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
* of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
* layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
*
* For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
* For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
*
* Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
* MSB to LSB.
*/
static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
enum exception_type type)
{
unsigned long sctlr, vbar, old, new, mode;
u64 exc_offset;
mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
if (mode == target_mode)
exc_offset = CURRENT_EL_SP_ELx_VECTOR;
else if ((mode | PSR_MODE_THREAD_BIT) == target_mode)
exc_offset = CURRENT_EL_SP_EL0_VECTOR;
else if (!(mode & PSR_MODE32_BIT))
exc_offset = LOWER_EL_AArch64_VECTOR;
else
exc_offset = LOWER_EL_AArch32_VECTOR;
switch (target_mode) {
case PSR_MODE_EL1h:
vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL1); sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
break;
case PSR_MODE_EL2h:
vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL2); sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL2); __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2);
break;
default:
/* Don't do that */
BUG();
}
*vcpu_pc(vcpu) = vbar + exc_offset + type;
old = *vcpu_cpsr(vcpu);
new = 0;
new |= (old & PSR_N_BIT);
new |= (old & PSR_Z_BIT);
new |= (old & PSR_C_BIT);
new |= (old & PSR_V_BIT);
if (kvm_has_mte(kern_hyp_va(vcpu->kvm)))
new |= PSR_TCO_BIT;
new |= (old & PSR_DIT_BIT);
// PSTATE.UAO is set to zero upon any exception to AArch64
// See ARM DDI 0487E.a, page D5-2579.
// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
// See ARM DDI 0487E.a, page D5-2578.
new |= (old & PSR_PAN_BIT);
if (!(sctlr & SCTLR_EL1_SPAN))
new |= PSR_PAN_BIT;
// PSTATE.SS is set to zero upon any exception to AArch64
// See ARM DDI 0487E.a, page D2-2452.
// PSTATE.IL is set to zero upon any exception to AArch64
// See ARM DDI 0487E.a, page D1-2306.
// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
// See ARM DDI 0487E.a, page D13-3258
if (sctlr & SCTLR_ELx_DSSBS)
new |= PSR_SSBS_BIT;
// PSTATE.BTYPE is set to zero upon any exception to AArch64
// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
new |= PSR_D_BIT;
new |= PSR_A_BIT;
new |= PSR_I_BIT;
new |= PSR_F_BIT;
new |= target_mode;
*vcpu_cpsr(vcpu) = new;
__vcpu_write_spsr(vcpu, target_mode, old);
}
/*
* When an exception is taken, most CPSR fields are left unchanged in the
* handler. However, some are explicitly overridden (e.g. M[4:0]).
*
* The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
* either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
* obsoleted by the ARMv7 virtualization extensions and is RES0.
*
* For the SPSR layout seen from AArch32, see:
* - ARM DDI 0406C.d, page B1-1148
* - ARM DDI 0487E.a, page G8-6264
*
* For the SPSR_ELx layout for AArch32 seen from AArch64, see:
* - ARM DDI 0487E.a, page C5-426
*
* Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
* MSB to LSB.
*/
static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
{
u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
unsigned long old, new;
old = *vcpu_cpsr(vcpu);
new = 0;
new |= (old & PSR_AA32_N_BIT);
new |= (old & PSR_AA32_Z_BIT);
new |= (old & PSR_AA32_C_BIT);
new |= (old & PSR_AA32_V_BIT);
new |= (old & PSR_AA32_Q_BIT);
// CPSR.IT[7:0] are set to zero upon any exception
// See ARM DDI 0487E.a, section G1.12.3
// See ARM DDI 0406C.d, section B1.8.3
new |= (old & PSR_AA32_DIT_BIT);
// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
// See ARM DDI 0487E.a, page G8-6244
if (sctlr & BIT(31))
new |= PSR_AA32_SSBS_BIT;
// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
// See ARM DDI 0487E.a, page G8-6246
new |= (old & PSR_AA32_PAN_BIT);
if (!(sctlr & BIT(23)))
new |= PSR_AA32_PAN_BIT;
// SS does not exist in AArch32, so ignore
// CPSR.IL is set to zero upon any exception
// See ARM DDI 0487E.a, page G1-5527
new |= (old & PSR_AA32_GE_MASK);
// CPSR.IT[7:0] are set to zero upon any exception
// See prior comment above
// CPSR.E is set to SCTLR.EE upon any exception
// See ARM DDI 0487E.a, page G8-6245
// See ARM DDI 0406C.d, page B4-1701
if (sctlr & BIT(25))
new |= PSR_AA32_E_BIT;
// CPSR.A is unchanged upon an exception to Undefined, Supervisor
// CPSR.A is set upon an exception to other modes
// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
// See ARM DDI 0406C.d, page B1-1182
new |= (old & PSR_AA32_A_BIT);
if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
new |= PSR_AA32_A_BIT;
// CPSR.I is set upon any exception
// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
// See ARM DDI 0406C.d, page B1-1182
new |= PSR_AA32_I_BIT;
// CPSR.F is set upon an exception to FIQ
// CPSR.F is unchanged upon an exception to other modes
// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
// See ARM DDI 0406C.d, page B1-1182
new |= (old & PSR_AA32_F_BIT);
if (mode == PSR_AA32_MODE_FIQ)
new |= PSR_AA32_F_BIT;
// CPSR.T is set to SCTLR.TE upon any exception
// See ARM DDI 0487E.a, page G8-5514
// See ARM DDI 0406C.d, page B1-1181
if (sctlr & BIT(30))
new |= PSR_AA32_T_BIT;
new |= mode;
return new;
}
/*
* Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
*/
static const u8 return_offsets[8][2] = {
[0] = { 0, 0 }, /* Reset, unused */
[1] = { 4, 2 }, /* Undefined */
[2] = { 0, 0 }, /* SVC, unused */
[3] = { 4, 4 }, /* Prefetch abort */
[4] = { 8, 8 }, /* Data abort */
[5] = { 0, 0 }, /* HVC, unused */
[6] = { 4, 4 }, /* IRQ, unused */
[7] = { 4, 4 }, /* FIQ, unused */
};
static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
{
unsigned long spsr = *vcpu_cpsr(vcpu);
bool is_thumb = (spsr & PSR_AA32_T_BIT);
u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
u32 return_address;
*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
return_address = *vcpu_pc(vcpu);
return_address += return_offsets[vect_offset >> 2][is_thumb];
/* KVM only enters the ABT and UND modes, so only deal with those */
switch(mode) {
case PSR_AA32_MODE_ABT:
__vcpu_write_spsr_abt(vcpu, host_spsr_to_spsr32(spsr));
vcpu_gp_regs(vcpu)->compat_lr_abt = return_address;
break;
case PSR_AA32_MODE_UND:
__vcpu_write_spsr_und(vcpu, host_spsr_to_spsr32(spsr));
vcpu_gp_regs(vcpu)->compat_lr_und = return_address;
break;
}
/* Branch to exception vector */
if (sctlr & (1 << 13))
vect_offset += 0xffff0000;
else /* always have security exceptions */
vect_offset += __vcpu_read_sys_reg(vcpu, VBAR_EL1);
*vcpu_pc(vcpu) = vect_offset;
}
static void kvm_inject_exception(struct kvm_vcpu *vcpu)
{
if (vcpu_el1_is_32bit(vcpu)) {
switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) {
case unpack_vcpu_flag(EXCEPT_AA32_UND):
enter_exception32(vcpu, PSR_AA32_MODE_UND, 4);
break;
case unpack_vcpu_flag(EXCEPT_AA32_IABT):
enter_exception32(vcpu, PSR_AA32_MODE_ABT, 12);
break;
case unpack_vcpu_flag(EXCEPT_AA32_DABT):
enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16);
break;
default:
/* Err... */
break;
}
} else {
switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) {
case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC):
enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
break;
case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC):
enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync);
break;
case unpack_vcpu_flag(EXCEPT_AA64_EL2_IRQ):
enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq);
break;
default:
/*
* Only EL1_SYNC and EL2_{SYNC,IRQ} makes
* sense so far. Everything else gets silently
* ignored.
*/
break;
}
}
}
/*
* Adjust the guest PC (and potentially exception state) depending on
* flags provided by the emulation code.
*/
void __kvm_adjust_pc(struct kvm_vcpu *vcpu)
{
if (vcpu_get_flag(vcpu, PENDING_EXCEPTION)) {
kvm_inject_exception(vcpu); vcpu_clear_flag(vcpu, PENDING_EXCEPTION); vcpu_clear_flag(vcpu, EXCEPT_MASK); } else if (vcpu_get_flag(vcpu, INCREMENT_PC)) { kvm_skip_instr(vcpu); vcpu_clear_flag(vcpu, INCREMENT_PC);
}
}
// SPDX-License-Identifier: GPL-2.0-or-later
/* auditfilter.c -- filtering of audit events
*
* Copyright 2003-2004 Red Hat, Inc.
* Copyright 2005 Hewlett-Packard Development Company, L.P.
* Copyright 2005 IBM Corporation
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include "audit.h"
/*
* Locking model:
*
* audit_filter_mutex:
* Synchronizes writes and blocking reads of audit's filterlist
* data. Rcu is used to traverse the filterlist and access
* contents of structs audit_entry, audit_watch and opaque
* LSM rules during filtering. If modified, these structures
* must be copied and replace their counterparts in the filterlist.
* An audit_parent struct is not accessed during filtering, so may
* be written directly provided audit_filter_mutex is held.
*/
/* Audit filter lists, defined in <linux/audit.h> */
struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
LIST_HEAD_INIT(audit_filter_list[0]),
LIST_HEAD_INIT(audit_filter_list[1]),
LIST_HEAD_INIT(audit_filter_list[2]),
LIST_HEAD_INIT(audit_filter_list[3]),
LIST_HEAD_INIT(audit_filter_list[4]),
LIST_HEAD_INIT(audit_filter_list[5]),
LIST_HEAD_INIT(audit_filter_list[6]),
LIST_HEAD_INIT(audit_filter_list[7]),
#if AUDIT_NR_FILTERS != 8
#error Fix audit_filter_list initialiser
#endif
};
static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
LIST_HEAD_INIT(audit_rules_list[0]),
LIST_HEAD_INIT(audit_rules_list[1]),
LIST_HEAD_INIT(audit_rules_list[2]),
LIST_HEAD_INIT(audit_rules_list[3]),
LIST_HEAD_INIT(audit_rules_list[4]),
LIST_HEAD_INIT(audit_rules_list[5]),
LIST_HEAD_INIT(audit_rules_list[6]),
LIST_HEAD_INIT(audit_rules_list[7]),
};
DEFINE_MUTEX(audit_filter_mutex);
static void audit_free_lsm_field(struct audit_field *f)
{
switch (f->type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
kfree(f->lsm_str);
security_audit_rule_free(f->lsm_rule);
}
}
static inline void audit_free_rule(struct audit_entry *e)
{
int i;
struct audit_krule *erule = &e->rule;
/* some rules don't have associated watches */
if (erule->watch)
audit_put_watch(erule->watch);
if (erule->fields)
for (i = 0; i < erule->field_count; i++)
audit_free_lsm_field(&erule->fields[i]);
kfree(erule->fields);
kfree(erule->filterkey);
kfree(e);
}
void audit_free_rule_rcu(struct rcu_head *head)
{
struct audit_entry *e = container_of(head, struct audit_entry, rcu);
audit_free_rule(e);
}
/* Initialize an audit filterlist entry. */
static inline struct audit_entry *audit_init_entry(u32 field_count)
{
struct audit_entry *entry;
struct audit_field *fields;
entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (unlikely(!entry))
return NULL;
fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL);
if (unlikely(!fields)) {
kfree(entry);
return NULL;
}
entry->rule.fields = fields;
return entry;
}
/* Unpack a filter field's string representation from user-space
* buffer. */
char *audit_unpack_string(void **bufp, size_t *remain, size_t len)
{
char *str;
if (!*bufp || (len == 0) || (len > *remain))
return ERR_PTR(-EINVAL);
/* Of the currently implemented string fields, PATH_MAX
* defines the longest valid length.
*/
if (len > PATH_MAX)
return ERR_PTR(-ENAMETOOLONG);
str = kmalloc(len + 1, GFP_KERNEL);
if (unlikely(!str))
return ERR_PTR(-ENOMEM);
memcpy(str, *bufp, len);
str[len] = 0;
*bufp += len;
*remain -= len;
return str;
}
/* Translate an inode field to kernel representation. */
static inline int audit_to_inode(struct audit_krule *krule,
struct audit_field *f)
{
if ((krule->listnr != AUDIT_FILTER_EXIT &&
krule->listnr != AUDIT_FILTER_URING_EXIT) ||
krule->inode_f || krule->watch || krule->tree ||
(f->op != Audit_equal && f->op != Audit_not_equal))
return -EINVAL;
krule->inode_f = f;
return 0;
}
static __u32 *classes[AUDIT_SYSCALL_CLASSES];
int __init audit_register_class(int class, unsigned *list)
{
__u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL);
if (!p)
return -ENOMEM;
while (*list != ~0U) {
unsigned n = *list++;
if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) {
kfree(p);
return -EINVAL;
}
p[AUDIT_WORD(n)] |= AUDIT_BIT(n);
}
if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) {
kfree(p);
return -EINVAL;
}
classes[class] = p;
return 0;
}
int audit_match_class(int class, unsigned syscall)
{
if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32))
return 0;
if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class]))
return 0;
return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall);
}
#ifdef CONFIG_AUDITSYSCALL
static inline int audit_match_class_bits(int class, u32 *mask)
{
int i;
if (classes[class]) {
for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
if (mask[i] & classes[class][i])
return 0;
}
return 1;
}
static int audit_match_signal(struct audit_entry *entry)
{
struct audit_field *arch = entry->rule.arch_f;
if (!arch) {
/* When arch is unspecified, we must check both masks on biarch
* as syscall number alone is ambiguous. */
return (audit_match_class_bits(AUDIT_CLASS_SIGNAL,
entry->rule.mask) &&
audit_match_class_bits(AUDIT_CLASS_SIGNAL_32,
entry->rule.mask));
}
switch (audit_classify_arch(arch->val)) {
case 0: /* native */
return (audit_match_class_bits(AUDIT_CLASS_SIGNAL,
entry->rule.mask));
case 1: /* 32bit on biarch */
return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32,
entry->rule.mask));
default:
return 1;
}
}
#endif
/* Common user-space to kernel rule translation. */
static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule)
{
unsigned listnr;
struct audit_entry *entry;
int i, err;
err = -EINVAL;
listnr = rule->flags & ~AUDIT_FILTER_PREPEND;
switch (listnr) {
default:
goto exit_err;
#ifdef CONFIG_AUDITSYSCALL
case AUDIT_FILTER_ENTRY:
pr_err("AUDIT_FILTER_ENTRY is deprecated\n");
goto exit_err;
case AUDIT_FILTER_EXIT:
case AUDIT_FILTER_URING_EXIT:
case AUDIT_FILTER_TASK:
#endif
case AUDIT_FILTER_USER:
case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
;
}
if (unlikely(rule->action == AUDIT_POSSIBLE)) {
pr_err("AUDIT_POSSIBLE is deprecated\n");
goto exit_err;
}
if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS)
goto exit_err;
if (rule->field_count > AUDIT_MAX_FIELDS)
goto exit_err;
err = -ENOMEM;
entry = audit_init_entry(rule->field_count);
if (!entry)
goto exit_err;
entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND;
entry->rule.listnr = listnr;
entry->rule.action = rule->action;
entry->rule.field_count = rule->field_count;
for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
entry->rule.mask[i] = rule->mask[i];
for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) {
int bit = AUDIT_BITMASK_SIZE * 32 - i - 1;
__u32 *p = &entry->rule.mask[AUDIT_WORD(bit)];
__u32 *class;
if (!(*p & AUDIT_BIT(bit)))
continue;
*p &= ~AUDIT_BIT(bit);
class = classes[i];
if (class) {
int j;
for (j = 0; j < AUDIT_BITMASK_SIZE; j++)
entry->rule.mask[j] |= class[j];
}
}
return entry;
exit_err:
return ERR_PTR(err);
}
static u32 audit_ops[] =
{
[Audit_equal] = AUDIT_EQUAL,
[Audit_not_equal] = AUDIT_NOT_EQUAL,
[Audit_bitmask] = AUDIT_BIT_MASK,
[Audit_bittest] = AUDIT_BIT_TEST,
[Audit_lt] = AUDIT_LESS_THAN,
[Audit_gt] = AUDIT_GREATER_THAN,
[Audit_le] = AUDIT_LESS_THAN_OR_EQUAL,
[Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL,
};
static u32 audit_to_op(u32 op)
{
u32 n;
for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++)
;
return n;
}
/* check if an audit field is valid */
static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
{
switch (f->type) {
case AUDIT_MSGTYPE:
if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE &&
entry->rule.listnr != AUDIT_FILTER_USER)
return -EINVAL;
break;
case AUDIT_FSTYPE:
if (entry->rule.listnr != AUDIT_FILTER_FS)
return -EINVAL;
break;
case AUDIT_PERM:
if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT)
return -EINVAL;
break;
}
switch (entry->rule.listnr) {
case AUDIT_FILTER_FS:
switch (f->type) {
case AUDIT_FSTYPE:
case AUDIT_FILTERKEY:
break;
default:
return -EINVAL;
}
}
/* Check for valid field type and op */
switch (f->type) {
case AUDIT_ARG0:
case AUDIT_ARG1:
case AUDIT_ARG2:
case AUDIT_ARG3:
case AUDIT_PERS: /* <uapi/linux/personality.h> */
case AUDIT_DEVMINOR:
/* all ops are valid */
break;
case AUDIT_UID:
case AUDIT_EUID:
case AUDIT_SUID:
case AUDIT_FSUID:
case AUDIT_LOGINUID:
case AUDIT_OBJ_UID:
case AUDIT_GID:
case AUDIT_EGID:
case AUDIT_SGID:
case AUDIT_FSGID:
case AUDIT_OBJ_GID:
case AUDIT_PID:
case AUDIT_MSGTYPE:
case AUDIT_PPID:
case AUDIT_DEVMAJOR:
case AUDIT_EXIT:
case AUDIT_SUCCESS:
case AUDIT_INODE:
case AUDIT_SESSIONID:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
case AUDIT_SADDR_FAM:
/* bit ops are only useful on syscall args */
if (f->op == Audit_bitmask || f->op == Audit_bittest)
return -EINVAL;
break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_WATCH:
case AUDIT_DIR:
case AUDIT_FILTERKEY:
case AUDIT_LOGINUID_SET:
case AUDIT_ARCH:
case AUDIT_FSTYPE:
case AUDIT_PERM:
case AUDIT_FILETYPE:
case AUDIT_FIELD_COMPARE:
case AUDIT_EXE:
/* only equal and not equal valid ops */
if (f->op != Audit_not_equal && f->op != Audit_equal)
return -EINVAL;
break;
default:
/* field not recognized */
return -EINVAL;
}
/* Check for select valid field values */
switch (f->type) {
case AUDIT_LOGINUID_SET:
if ((f->val != 0) && (f->val != 1))
return -EINVAL;
break;
case AUDIT_PERM:
if (f->val & ~15)
return -EINVAL;
break;
case AUDIT_FILETYPE:
if (f->val & ~S_IFMT)
return -EINVAL;
break;
case AUDIT_FIELD_COMPARE:
if (f->val > AUDIT_MAX_FIELD_COMPARE)
return -EINVAL;
break;
case AUDIT_SADDR_FAM:
if (f->val >= AF_MAX)
return -EINVAL;
break;
default:
break;
}
return 0;
}
/* Translate struct audit_rule_data to kernel's rule representation. */
static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
size_t datasz)
{
int err = 0;
struct audit_entry *entry;
void *bufp;
size_t remain = datasz - sizeof(struct audit_rule_data);
int i;
char *str;
struct audit_fsnotify_mark *audit_mark;
entry = audit_to_entry_common(data);
if (IS_ERR(entry))
goto exit_nofree;
bufp = data->buf;
for (i = 0; i < data->field_count; i++) {
struct audit_field *f = &entry->rule.fields[i];
u32 f_val;
err = -EINVAL;
f->op = audit_to_op(data->fieldflags[i]);
if (f->op == Audit_bad)
goto exit_free;
f->type = data->fields[i];
f_val = data->values[i];
/* Support legacy tests for a valid loginuid */
if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) {
f->type = AUDIT_LOGINUID_SET;
f_val = 0;
entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
}
err = audit_field_valid(entry, f);
if (err)
goto exit_free;
err = -EINVAL;
switch (f->type) {
case AUDIT_LOGINUID:
case AUDIT_UID:
case AUDIT_EUID:
case AUDIT_SUID:
case AUDIT_FSUID:
case AUDIT_OBJ_UID:
f->uid = make_kuid(current_user_ns(), f_val);
if (!uid_valid(f->uid))
goto exit_free;
break;
case AUDIT_GID:
case AUDIT_EGID:
case AUDIT_SGID:
case AUDIT_FSGID:
case AUDIT_OBJ_GID:
f->gid = make_kgid(current_user_ns(), f_val);
if (!gid_valid(f->gid))
goto exit_free;
break;
case AUDIT_ARCH:
f->val = f_val;
entry->rule.arch_f = f;
break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
entry->rule.buflen += f_val;
f->lsm_str = str;
err = security_audit_rule_init(f->type, f->op, str,
(void **)&f->lsm_rule,
GFP_KERNEL);
/* Keep currently invalid fields around in case they
* become valid after a policy reload. */
if (err == -EINVAL) {
pr_warn("audit rule for LSM \'%s\' is invalid\n",
str);
err = 0;
} else if (err)
goto exit_free;
break;
case AUDIT_WATCH:
str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
err = audit_to_watch(&entry->rule, str, f_val, f->op);
if (err) {
kfree(str);
goto exit_free;
}
entry->rule.buflen += f_val;
break;
case AUDIT_DIR:
str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
err = audit_make_tree(&entry->rule, str, f->op);
kfree(str);
if (err)
goto exit_free;
entry->rule.buflen += f_val;
break;
case AUDIT_INODE:
f->val = f_val;
err = audit_to_inode(&entry->rule, f);
if (err)
goto exit_free;
break;
case AUDIT_FILTERKEY:
if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN)
goto exit_free;
str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
entry->rule.buflen += f_val;
entry->rule.filterkey = str;
break;
case AUDIT_EXE:
if (entry->rule.exe || f_val > PATH_MAX)
goto exit_free;
str = audit_unpack_string(&bufp, &remain, f_val);
if (IS_ERR(str)) {
err = PTR_ERR(str);
goto exit_free;
}
audit_mark = audit_alloc_mark(&entry->rule, str, f_val);
if (IS_ERR(audit_mark)) {
kfree(str);
err = PTR_ERR(audit_mark);
goto exit_free;
}
entry->rule.buflen += f_val;
entry->rule.exe = audit_mark;
break;
default:
f->val = f_val;
break;
}
}
if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
entry->rule.inode_f = NULL;
exit_nofree:
return entry;
exit_free:
if (entry->rule.tree)
audit_put_tree(entry->rule.tree); /* that's the temporary one */
if (entry->rule.exe)
audit_remove_mark(entry->rule.exe); /* that's the template one */
audit_free_rule(entry);
return ERR_PTR(err);
}
/* Pack a filter field's string representation into data block. */
static inline size_t audit_pack_string(void **bufp, const char *str)
{
size_t len = strlen(str);
memcpy(*bufp, str, len);
*bufp += len;
return len;
}
/* Translate kernel rule representation to struct audit_rule_data. */
static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
{
struct audit_rule_data *data;
void *bufp;
int i;
data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL);
if (unlikely(!data))
return NULL;
memset(data, 0, sizeof(*data));
data->flags = krule->flags | krule->listnr;
data->action = krule->action;
data->field_count = krule->field_count;
bufp = data->buf;
for (i = 0; i < data->field_count; i++) {
struct audit_field *f = &krule->fields[i];
data->fields[i] = f->type;
data->fieldflags[i] = audit_ops[f->op];
switch (f->type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
data->buflen += data->values[i] =
audit_pack_string(&bufp, f->lsm_str);
break;
case AUDIT_WATCH:
data->buflen += data->values[i] =
audit_pack_string(&bufp,
audit_watch_path(krule->watch));
break;
case AUDIT_DIR:
data->buflen += data->values[i] =
audit_pack_string(&bufp,
audit_tree_path(krule->tree));
break;
case AUDIT_FILTERKEY:
data->buflen += data->values[i] =
audit_pack_string(&bufp, krule->filterkey);
break;
case AUDIT_EXE:
data->buflen += data->values[i] =
audit_pack_string(&bufp, audit_mark_path(krule->exe));
break;
case AUDIT_LOGINUID_SET:
if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
data->fields[i] = AUDIT_LOGINUID;
data->values[i] = AUDIT_UID_UNSET;
break;
}
fallthrough; /* if set */
default:
data->values[i] = f->val;
}
}
for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
data->mask[i] = krule->mask[i];
return data;
}
/* Compare two rules in kernel format. Considered success if rules
* don't match. */
static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
{
int i;
if (a->flags != b->flags ||
a->pflags != b->pflags ||
a->listnr != b->listnr ||
a->action != b->action ||
a->field_count != b->field_count)
return 1;
for (i = 0; i < a->field_count; i++) {
if (a->fields[i].type != b->fields[i].type ||
a->fields[i].op != b->fields[i].op)
return 1;
switch (a->fields[i].type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str))
return 1;
break;
case AUDIT_WATCH:
if (strcmp(audit_watch_path(a->watch),
audit_watch_path(b->watch)))
return 1;
break;
case AUDIT_DIR:
if (strcmp(audit_tree_path(a->tree),
audit_tree_path(b->tree)))
return 1;
break;
case AUDIT_FILTERKEY:
/* both filterkeys exist based on above type compare */
if (strcmp(a->filterkey, b->filterkey))
return 1;
break;
case AUDIT_EXE:
/* both paths exist based on above type compare */
if (strcmp(audit_mark_path(a->exe),
audit_mark_path(b->exe)))
return 1;
break;
case AUDIT_UID:
case AUDIT_EUID:
case AUDIT_SUID:
case AUDIT_FSUID:
case AUDIT_LOGINUID:
case AUDIT_OBJ_UID:
if (!uid_eq(a->fields[i].uid, b->fields[i].uid))
return 1;
break;
case AUDIT_GID:
case AUDIT_EGID:
case AUDIT_SGID:
case AUDIT_FSGID:
case AUDIT_OBJ_GID:
if (!gid_eq(a->fields[i].gid, b->fields[i].gid))
return 1;
break;
default:
if (a->fields[i].val != b->fields[i].val)
return 1;
}
}
for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
if (a->mask[i] != b->mask[i])
return 1;
return 0;
}
/* Duplicate LSM field information. The lsm_rule is opaque, so must be
* re-initialized. */
static inline int audit_dupe_lsm_field(struct audit_field *df,
struct audit_field *sf)
{
int ret;
char *lsm_str;
/* our own copy of lsm_str */
lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL);
if (unlikely(!lsm_str))
return -ENOMEM;
df->lsm_str = lsm_str;
/* our own (refreshed) copy of lsm_rule */
ret = security_audit_rule_init(df->type, df->op, df->lsm_str,
(void **)&df->lsm_rule, GFP_KERNEL);
/* Keep currently invalid fields around in case they
* become valid after a policy reload. */
if (ret == -EINVAL) {
pr_warn("audit rule for LSM \'%s\' is invalid\n",
df->lsm_str);
ret = 0;
}
return ret;
}
/* Duplicate an audit rule. This will be a deep copy with the exception
* of the watch - that pointer is carried over. The LSM specific fields
* will be updated in the copy. The point is to be able to replace the old
* rule with the new rule in the filterlist, then free the old rule.
* The rlist element is undefined; list manipulations are handled apart from
* the initial copy. */
struct audit_entry *audit_dupe_rule(struct audit_krule *old)
{
u32 fcount = old->field_count;
struct audit_entry *entry;
struct audit_krule *new;
char *fk;
int i, err = 0;
entry = audit_init_entry(fcount);
if (unlikely(!entry))
return ERR_PTR(-ENOMEM);
new = &entry->rule;
new->flags = old->flags;
new->pflags = old->pflags;
new->listnr = old->listnr;
new->action = old->action;
for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
new->mask[i] = old->mask[i];
new->prio = old->prio;
new->buflen = old->buflen;
new->inode_f = old->inode_f;
new->field_count = old->field_count;
/*
* note that we are OK with not refcounting here; audit_match_tree()
* never dereferences tree and we can't get false positives there
* since we'd have to have rule gone from the list *and* removed
* before the chunks found by lookup had been allocated, i.e. before
* the beginning of list scan.
*/
new->tree = old->tree;
memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount);
/* deep copy this information, updating the lsm_rule fields, because
* the originals will all be freed when the old rule is freed. */
for (i = 0; i < fcount; i++) {
switch (new->fields[i].type) {
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
case AUDIT_OBJ_USER:
case AUDIT_OBJ_ROLE:
case AUDIT_OBJ_TYPE:
case AUDIT_OBJ_LEV_LOW:
case AUDIT_OBJ_LEV_HIGH:
err = audit_dupe_lsm_field(&new->fields[i],
&old->fields[i]);
break;
case AUDIT_FILTERKEY:
fk = kstrdup(old->filterkey, GFP_KERNEL);
if (unlikely(!fk))
err = -ENOMEM;
else
new->filterkey = fk;
break;
case AUDIT_EXE:
err = audit_dupe_exe(new, old);
break;
}
if (err) {
if (new->exe)
audit_remove_mark(new->exe);
audit_free_rule(entry);
return ERR_PTR(err);
}
}
if (old->watch) {
audit_get_watch(old->watch);
new->watch = old->watch;
}
return entry;
}
/* Find an existing audit rule.
* Caller must hold audit_filter_mutex to prevent stale rule data. */
static struct audit_entry *audit_find_rule(struct audit_entry *entry,
struct list_head **p)
{
struct audit_entry *e, *found = NULL;
struct list_head *list;
int h;
if (entry->rule.inode_f) {
h = audit_hash_ino(entry->rule.inode_f->val);
*p = list = &audit_inode_hash[h];
} else if (entry->rule.watch) {
/* we don't know the inode number, so must walk entire hash */
for (h = 0; h < AUDIT_INODE_BUCKETS; h++) {
list = &audit_inode_hash[h];
list_for_each_entry(e, list, list)
if (!audit_compare_rule(&entry->rule, &e->rule)) {
found = e;
goto out;
}
}
goto out;
} else {
*p = list = &audit_filter_list[entry->rule.listnr];
}
list_for_each_entry(e, list, list)
if (!audit_compare_rule(&entry->rule, &e->rule)) {
found = e;
goto out;
}
out:
return found;
}
static u64 prio_low = ~0ULL/2;
static u64 prio_high = ~0ULL/2 - 1;
/* Add rule to given filterlist if not a duplicate. */
static inline int audit_add_rule(struct audit_entry *entry)
{
struct audit_entry *e;
struct audit_watch *watch = entry->rule.watch;
struct audit_tree *tree = entry->rule.tree;
struct list_head *list;
int err = 0;
#ifdef CONFIG_AUDITSYSCALL
int dont_count = 0;
/* If any of these, don't count towards total */
switch (entry->rule.listnr) {
case AUDIT_FILTER_USER:
case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
dont_count = 1;
}
#endif
mutex_lock(&audit_filter_mutex);
e = audit_find_rule(entry, &list);
if (e) {
mutex_unlock(&audit_filter_mutex);
err = -EEXIST;
/* normally audit_add_tree_rule() will free it on failure */
if (tree)
audit_put_tree(tree);
return err;
}
if (watch) {
/* audit_filter_mutex is dropped and re-taken during this call */
err = audit_add_watch(&entry->rule, &list);
if (err) {
mutex_unlock(&audit_filter_mutex);
/*
* normally audit_add_tree_rule() will free it
* on failure
*/
if (tree)
audit_put_tree(tree);
return err;
}
}
if (tree) {
err = audit_add_tree_rule(&entry->rule);
if (err) {
mutex_unlock(&audit_filter_mutex);
return err;
}
}
entry->rule.prio = ~0ULL;
if (entry->rule.listnr == AUDIT_FILTER_EXIT ||
entry->rule.listnr == AUDIT_FILTER_URING_EXIT) {
if (entry->rule.flags & AUDIT_FILTER_PREPEND)
entry->rule.prio = ++prio_high;
else
entry->rule.prio = --prio_low;
}
if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
list_add(&entry->rule.list,
&audit_rules_list[entry->rule.listnr]);
list_add_rcu(&entry->list, list);
entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
} else {
list_add_tail(&entry->rule.list,
&audit_rules_list[entry->rule.listnr]);
list_add_tail_rcu(&entry->list, list);
}
#ifdef CONFIG_AUDITSYSCALL
if (!dont_count)
audit_n_rules++;
if (!audit_match_signal(entry))
audit_signals++;
#endif
mutex_unlock(&audit_filter_mutex);
return err;
}
/* Remove an existing rule from filterlist. */
int audit_del_rule(struct audit_entry *entry)
{
struct audit_entry *e;
struct audit_tree *tree = entry->rule.tree;
struct list_head *list;
int ret = 0;
#ifdef CONFIG_AUDITSYSCALL
int dont_count = 0;
/* If any of these, don't count towards total */
switch (entry->rule.listnr) {
case AUDIT_FILTER_USER:
case AUDIT_FILTER_EXCLUDE:
case AUDIT_FILTER_FS:
dont_count = 1;
}
#endif
mutex_lock(&audit_filter_mutex);
e = audit_find_rule(entry, &list);
if (!e) {
ret = -ENOENT;
goto out;
}
if (e->rule.watch)
audit_remove_watch_rule(&e->rule);
if (e->rule.tree)
audit_remove_tree_rule(&e->rule);
if (e->rule.exe)
audit_remove_mark_rule(&e->rule);
#ifdef CONFIG_AUDITSYSCALL
if (!dont_count)
audit_n_rules--;
if (!audit_match_signal(entry))
audit_signals--;
#endif
list_del_rcu(&e->list);
list_del(&e->rule.list);
call_rcu(&e->rcu, audit_free_rule_rcu);
out:
mutex_unlock(&audit_filter_mutex);
if (tree)
audit_put_tree(tree); /* that's the temporary one */
return ret;
}
/* List rules using struct audit_rule_data. */
static void audit_list_rules(int seq, struct sk_buff_head *q)
{
struct sk_buff *skb;
struct audit_krule *r;
int i;
/* This is a blocking read, so use audit_filter_mutex instead of rcu
* iterator to sync with list writers. */
for (i = 0; i < AUDIT_NR_FILTERS; i++) {
list_for_each_entry(r, &audit_rules_list[i], list) {
struct audit_rule_data *data;
data = audit_krule_to_data(r);
if (unlikely(!data))
break;
skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1,
data,
struct_size(data, buf, data->buflen));
if (skb)
skb_queue_tail(q, skb);
kfree(data);
}
}
skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0);
if (skb)
skb_queue_tail(q, skb);
}
/* Log rule additions and removals */
static void audit_log_rule_change(char *action, struct audit_krule *rule, int res)
{
struct audit_buffer *ab;
if (!audit_enabled)
return;
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (!ab)
return;
audit_log_session_info(ab);
audit_log_task_context(ab);
audit_log_format(ab, " op=%s", action);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=%d", rule->listnr, res);
audit_log_end(ab);
}
/**
* audit_rule_change - apply all rules to the specified message type
* @type: audit message type
* @seq: netlink audit message sequence (serial) number
* @data: payload data
* @datasz: size of payload data
*/
int audit_rule_change(int type, int seq, void *data, size_t datasz)
{
int err = 0;
struct audit_entry *entry;
switch (type) {
case AUDIT_ADD_RULE:
entry = audit_data_to_entry(data, datasz);
if (IS_ERR(entry))
return PTR_ERR(entry);
err = audit_add_rule(entry);
audit_log_rule_change("add_rule", &entry->rule, !err);
break;
case AUDIT_DEL_RULE:
entry = audit_data_to_entry(data, datasz);
if (IS_ERR(entry))
return PTR_ERR(entry);
err = audit_del_rule(entry);
audit_log_rule_change("remove_rule", &entry->rule, !err);
break;
default:
WARN_ON(1);
return -EINVAL;
}
if (err || type == AUDIT_DEL_RULE) {
if (entry->rule.exe)
audit_remove_mark(entry->rule.exe);
audit_free_rule(entry);
}
return err;
}
/**
* audit_list_rules_send - list the audit rules
* @request_skb: skb of request we are replying to (used to target the reply)
* @seq: netlink audit message sequence (serial) number
*/
int audit_list_rules_send(struct sk_buff *request_skb, int seq)
{
struct task_struct *tsk;
struct audit_netlink_list *dest;
/* We can't just spew out the rules here because we might fill
* the available socket buffer space and deadlock waiting for
* auditctl to read from it... which isn't ever going to
* happen if we're actually running in the context of auditctl
* trying to _send_ the stuff */
dest = kmalloc(sizeof(*dest), GFP_KERNEL);
if (!dest)
return -ENOMEM;
dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
dest->portid = NETLINK_CB(request_skb).portid;
skb_queue_head_init(&dest->q);
mutex_lock(&audit_filter_mutex);
audit_list_rules(seq, &dest->q);
mutex_unlock(&audit_filter_mutex);
tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list");
if (IS_ERR(tsk)) {
skb_queue_purge(&dest->q);
put_net(dest->net);
kfree(dest);
return PTR_ERR(tsk);
}
return 0;
}
int audit_comparator(u32 left, u32 op, u32 right)
{
switch (op) {
case Audit_equal:
return (left == right);
case Audit_not_equal:
return (left != right);
case Audit_lt:
return (left < right);
case Audit_le:
return (left <= right);
case Audit_gt:
return (left > right);
case Audit_ge:
return (left >= right);
case Audit_bitmask:
return (left & right);
case Audit_bittest:
return ((left & right) == right);
default:
return 0;
}
}
int audit_uid_comparator(kuid_t left, u32 op, kuid_t right)
{
switch (op) {
case Audit_equal:
return uid_eq(left, right);
case Audit_not_equal:
return !uid_eq(left, right);
case Audit_lt:
return uid_lt(left, right);
case Audit_le:
return uid_lte(left, right);
case Audit_gt:
return uid_gt(left, right);
case Audit_ge:
return uid_gte(left, right);
case Audit_bitmask:
case Audit_bittest:
default:
return 0;
}
}
int audit_gid_comparator(kgid_t left, u32 op, kgid_t right)
{
switch (op) {
case Audit_equal:
return gid_eq(left, right);
case Audit_not_equal:
return !gid_eq(left, right);
case Audit_lt:
return gid_lt(left, right);
case Audit_le:
return gid_lte(left, right);
case Audit_gt:
return gid_gt(left, right);
case Audit_ge:
return gid_gte(left, right);
case Audit_bitmask:
case Audit_bittest:
default:
return 0;
}
}
/**
* parent_len - find the length of the parent portion of a pathname
* @path: pathname of which to determine length
*/
int parent_len(const char *path)
{
int plen;
const char *p;
plen = strlen(path);
if (plen == 0)
return plen;
/* disregard trailing slashes */
p = path + plen - 1;
while ((*p == '/') && (p > path))
p--;
/* walk backward until we find the next slash or hit beginning */
while ((*p != '/') && (p > path))
p--;
/* did we find a slash? Then increment to include it in path */
if (*p == '/')
p++;
return p - path;
}
/**
* audit_compare_dname_path - compare given dentry name with last component in
* given path. Return of 0 indicates a match.
* @dname: dentry name that we're comparing
* @path: full pathname that we're comparing
* @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL
* here indicates that we must compute this value.
*/
int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen)
{
int dlen, pathlen;
const char *p;
dlen = dname->len;
pathlen = strlen(path);
if (pathlen < dlen)
return 1;
if (parentlen == AUDIT_NAME_FULL)
parentlen = parent_len(path);
p = path + parentlen;
/* handle trailing slashes */
pathlen -= parentlen;
while (p[pathlen - 1] == '/')
pathlen--;
if (pathlen != dlen)
return 1;
return memcmp(p, dname->name, dlen);
}
int audit_filter(int msgtype, unsigned int listtype)
{
struct audit_entry *e;
int ret = 1; /* Audit by default */
rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) {
int i, result = 0;
for (i = 0; i < e->rule.field_count; i++) {
struct audit_field *f = &e->rule.fields[i];
struct lsm_prop prop = { };
pid_t pid;
switch (f->type) {
case AUDIT_PID:
pid = task_tgid_nr(current);
result = audit_comparator(pid, f->op, f->val);
break;
case AUDIT_UID:
result = audit_uid_comparator(current_uid(), f->op, f->uid);
break;
case AUDIT_GID:
result = audit_gid_comparator(current_gid(), f->op, f->gid);
break;
case AUDIT_LOGINUID:
result = audit_uid_comparator(audit_get_loginuid(current),
f->op, f->uid);
break;
case AUDIT_LOGINUID_SET:
result = audit_comparator(audit_loginuid_set(current),
f->op, f->val);
break;
case AUDIT_MSGTYPE:
result = audit_comparator(msgtype, f->op, f->val);
break;
case AUDIT_SUBJ_USER:
case AUDIT_SUBJ_ROLE:
case AUDIT_SUBJ_TYPE:
case AUDIT_SUBJ_SEN:
case AUDIT_SUBJ_CLR:
if (f->lsm_rule) { security_current_getlsmprop_subj(&prop);
result = security_audit_rule_match(
&prop, f->type, f->op,
f->lsm_rule);
}
break;
case AUDIT_EXE:
result = audit_exe_compare(current, e->rule.exe);
if (f->op == Audit_not_equal) result = !result;
break;
default:
goto unlock_and_return;
}
if (result < 0) /* error */
goto unlock_and_return;
if (!result)
break;
}
if (result > 0) {
if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE)
ret = 0;
break;
}
}
unlock_and_return:
rcu_read_unlock();
return ret;
}
static int update_lsm_rule(struct audit_krule *r)
{
struct audit_entry *entry = container_of(r, struct audit_entry, rule);
struct audit_entry *nentry;
int err = 0;
if (!security_audit_rule_known(r))
return 0;
nentry = audit_dupe_rule(r);
if (entry->rule.exe)
audit_remove_mark(entry->rule.exe);
if (IS_ERR(nentry)) {
/* save the first error encountered for the
* return value */
err = PTR_ERR(nentry);
audit_panic("error updating LSM filters");
if (r->watch)
list_del(&r->rlist);
list_del_rcu(&entry->list);
list_del(&r->list);
} else {
if (r->watch || r->tree)
list_replace_init(&r->rlist, &nentry->rule.rlist);
list_replace_rcu(&entry->list, &nentry->list);
list_replace(&r->list, &nentry->rule.list);
}
call_rcu(&entry->rcu, audit_free_rule_rcu);
return err;
}
/* This function will re-initialize the lsm_rule field of all applicable rules.
* It will traverse the filter lists serarching for rules that contain LSM
* specific filter fields. When such a rule is found, it is copied, the
* LSM field is re-initialized, and the old rule is replaced with the
* updated rule. */
int audit_update_lsm_rules(void)
{
struct audit_krule *r, *n;
int i, err = 0;
/* audit_filter_mutex synchronizes the writers */
mutex_lock(&audit_filter_mutex);
for (i = 0; i < AUDIT_NR_FILTERS; i++) {
list_for_each_entry_safe(r, n, &audit_rules_list[i], list) {
int res = update_lsm_rule(r);
if (!err)
err = res;
}
}
mutex_unlock(&audit_filter_mutex);
return err;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/printk.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Modified to make sys_syslog() more flexible: added commands to
* return the last 4k of kernel messages, regardless of whether
* they've been read or not. Added option to suppress kernel printk's
* to the console. Added hook for sending the console messages
* elsewhere, in preparation for a serial line console (someday).
* Ted Ts'o, 2/11/93.
* Modified for sysctl support, 1/8/97, Chris Horn.
* Fixed SMP synchronization, 08/08/99, Manfred Spraul
* manfred@colorfullife.com
* Rewrote bits to get rid of console_lock
* 01Mar01 Andrew Morton
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/tty.h>
#include <linux/tty_driver.h>
#include <linux/console.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/security.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
#include <linux/syscore_ops.h>
#include <linux/vmcore_info.h>
#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
#include <linux/syslog.h>
#include <linux/cpu.h>
#include <linux/rculist.h>
#include <linux/poll.h>
#include <linux/irq_work.h>
#include <linux/ctype.h>
#include <linux/uio.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/uaccess.h>
#include <asm/sections.h>
#include <trace/events/initcall.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
#include "printk_ringbuffer.h"
#include "console_cmdline.h"
#include "braille.h"
#include "internal.h"
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */
CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */
CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */
};
EXPORT_SYMBOL_GPL(console_printk);
atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0);
EXPORT_SYMBOL(ignore_console_lock_warning);
EXPORT_TRACEPOINT_SYMBOL_GPL(console);
/*
* Low level drivers may need that to know if they can schedule in
* their unblank() callback or not. So let's export it.
*/
int oops_in_progress;
EXPORT_SYMBOL(oops_in_progress);
/*
* console_mutex protects console_list updates and console->flags updates.
* The flags are synchronized only for consoles that are registered, i.e.
* accessible via the console list.
*/
static DEFINE_MUTEX(console_mutex);
/*
* console_sem protects updates to console->seq
* and also provides serialization for console printing.
*/
static DEFINE_SEMAPHORE(console_sem, 1);
HLIST_HEAD(console_list);
EXPORT_SYMBOL_GPL(console_list);
DEFINE_STATIC_SRCU(console_srcu);
/*
* System may need to suppress printk message under certain
* circumstances, like after kernel panic happens.
*/
int __read_mostly suppress_printk;
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_lock_dep_map = {
.name = "console_lock"
};
void lockdep_assert_console_list_lock_held(void)
{
lockdep_assert_held(&console_mutex);
}
EXPORT_SYMBOL(lockdep_assert_console_list_lock_held);
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
bool console_srcu_read_lock_is_held(void)
{ return srcu_read_lock_held(&console_srcu);
}
EXPORT_SYMBOL(console_srcu_read_lock_is_held);
#endif
enum devkmsg_log_bits {
__DEVKMSG_LOG_BIT_ON = 0,
__DEVKMSG_LOG_BIT_OFF,
__DEVKMSG_LOG_BIT_LOCK,
};
enum devkmsg_log_masks {
DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON),
DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF),
DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK),
};
/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */
#define DEVKMSG_LOG_MASK_DEFAULT 0
static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
static int __control_devkmsg(char *str)
{
size_t len;
if (!str)
return -EINVAL;
len = str_has_prefix(str, "on");
if (len) {
devkmsg_log = DEVKMSG_LOG_MASK_ON;
return len;
}
len = str_has_prefix(str, "off");
if (len) {
devkmsg_log = DEVKMSG_LOG_MASK_OFF;
return len;
}
len = str_has_prefix(str, "ratelimit");
if (len) {
devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
return len;
}
return -EINVAL;
}
static int __init control_devkmsg(char *str)
{
if (__control_devkmsg(str) < 0) {
pr_warn("printk.devkmsg: bad option string '%s'\n", str);
return 1;
}
/*
* Set sysctl string accordingly:
*/
if (devkmsg_log == DEVKMSG_LOG_MASK_ON)
strscpy(devkmsg_log_str, "on");
else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF)
strscpy(devkmsg_log_str, "off");
/* else "ratelimit" which is set by default. */
/*
* Sysctl cannot change it anymore. The kernel command line setting of
* this parameter is to force the setting to be permanent throughout the
* runtime of the system. This is a precation measure against userspace
* trying to be a smarta** and attempting to change it up on us.
*/
devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
return 1;
}
__setup("printk.devkmsg=", control_devkmsg);
char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
char old_str[DEVKMSG_STR_MAX_SIZE];
unsigned int old;
int err;
if (write) {
if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK)
return -EINVAL;
old = devkmsg_log;
strscpy(old_str, devkmsg_log_str);
}
err = proc_dostring(table, write, buffer, lenp, ppos);
if (err)
return err;
if (write) {
err = __control_devkmsg(devkmsg_log_str);
/*
* Do not accept an unknown string OR a known string with
* trailing crap...
*/
if (err < 0 || (err + 1 != *lenp)) {
/* ... and restore old setting. */
devkmsg_log = old;
strscpy(devkmsg_log_str, old_str);
return -EINVAL;
}
}
return 0;
}
#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */
/**
* console_list_lock - Lock the console list
*
* For console list or console->flags updates
*/
void console_list_lock(void)
{
/*
* In unregister_console() and console_force_preferred_locked(),
* synchronize_srcu() is called with the console_list_lock held.
* Therefore it is not allowed that the console_list_lock is taken
* with the srcu_lock held.
*
* Detecting if this context is really in the read-side critical
* section is only possible if the appropriate debug options are
* enabled.
*/
WARN_ON_ONCE(debug_lockdep_rcu_enabled() &&
srcu_read_lock_held(&console_srcu));
mutex_lock(&console_mutex);
}
EXPORT_SYMBOL(console_list_lock);
/**
* console_list_unlock - Unlock the console list
*
* Counterpart to console_list_lock()
*/
void console_list_unlock(void)
{
mutex_unlock(&console_mutex);
}
EXPORT_SYMBOL(console_list_unlock);
/**
* console_srcu_read_lock - Register a new reader for the
* SRCU-protected console list
*
* Use for_each_console_srcu() to iterate the console list
*
* Context: Any context.
* Return: A cookie to pass to console_srcu_read_unlock().
*/
int console_srcu_read_lock(void)
__acquires(&console_srcu)
{
return srcu_read_lock_nmisafe(&console_srcu);
}
EXPORT_SYMBOL(console_srcu_read_lock);
/**
* console_srcu_read_unlock - Unregister an old reader from
* the SRCU-protected console list
* @cookie: cookie returned from console_srcu_read_lock()
*
* Counterpart to console_srcu_read_lock()
*/
void console_srcu_read_unlock(int cookie)
__releases(&console_srcu)
{ srcu_read_unlock_nmisafe(&console_srcu, cookie);
}
EXPORT_SYMBOL(console_srcu_read_unlock);
/*
* Helper macros to handle lockdep when locking/unlocking console_sem. We use
* macros instead of functions so that _RET_IP_ contains useful information.
*/
#define down_console_sem() do { \
down(&console_sem);\
mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\
} while (0)
static int __down_trylock_console_sem(unsigned long ip)
{
int lock_failed;
unsigned long flags;
/*
* Here and in __up_console_sem() we need to be in safe mode,
* because spindump/WARN/etc from under console ->lock will
* deadlock in printk()->down_trylock_console_sem() otherwise.
*/
printk_safe_enter_irqsave(flags);
lock_failed = down_trylock(&console_sem);
printk_safe_exit_irqrestore(flags); if (lock_failed)
return 1;
mutex_acquire(&console_lock_dep_map, 0, 1, ip);
return 0;
}
#define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_)
static void __up_console_sem(unsigned long ip)
{
unsigned long flags;
mutex_release(&console_lock_dep_map, ip);
printk_safe_enter_irqsave(flags);
up(&console_sem);
printk_safe_exit_irqrestore(flags);
}
#define up_console_sem() __up_console_sem(_RET_IP_)
static bool panic_in_progress(void)
{
return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
}
/* Return true if a panic is in progress on the current CPU. */
bool this_cpu_in_panic(void)
{
/*
* We can use raw_smp_processor_id() here because it is impossible for
* the task to be migrated to the panic_cpu, or away from it. If
* panic_cpu has already been set, and we're not currently executing on
* that CPU, then we never will be.
*/
return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id());
}
/*
* Return true if a panic is in progress on a remote CPU.
*
* On true, the local CPU should immediately release any printing resources
* that may be needed by the panic CPU.
*/
bool other_cpu_in_panic(void)
{
return (panic_in_progress() && !this_cpu_in_panic());
}
/*
* This is used for debugging the mess that is the VT code by
* keeping track if we have the console semaphore held. It's
* definitely not the perfect debug tool (we don't know if _WE_
* hold it and are racing, but it helps tracking those weird code
* paths in the console code where we end up in places I want
* locked without the console semaphore held).
*/
static int console_locked;
/*
* Array of consoles built from command line options (console=)
*/
#define MAX_CMDLINECONSOLES 8
static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
static int preferred_console = -1;
int console_set_on_cmdline;
EXPORT_SYMBOL(console_set_on_cmdline);
/* Flag: console code may call schedule() */
static int console_may_schedule;
enum con_msg_format_flags {
MSG_FORMAT_DEFAULT = 0,
MSG_FORMAT_SYSLOG = (1 << 0),
};
static int console_msg_format = MSG_FORMAT_DEFAULT;
/*
* The printk log buffer consists of a sequenced collection of records, each
* containing variable length message text. Every record also contains its
* own meta-data (@info).
*
* Every record meta-data carries the timestamp in microseconds, as well as
* the standard userspace syslog level and syslog facility. The usual kernel
* messages use LOG_KERN; userspace-injected messages always carry a matching
* syslog facility, by default LOG_USER. The origin of every message can be
* reliably determined that way.
*
* The human readable log message of a record is available in @text, the
* length of the message text in @text_len. The stored message is not
* terminated.
*
* Optionally, a record can carry a dictionary of properties (key/value
* pairs), to provide userspace with a machine-readable message context.
*
* Examples for well-defined, commonly used property names are:
* DEVICE=b12:8 device identifier
* b12:8 block dev_t
* c127:3 char dev_t
* n8 netdev ifindex
* +sound:card0 subsystem:devname
* SUBSYSTEM=pci driver-core subsystem name
*
* Valid characters in property names are [a-zA-Z0-9.-_]. Property names
* and values are terminated by a '\0' character.
*
* Example of record values:
* record.text_buf = "it's a line" (unterminated)
* record.info.seq = 56
* record.info.ts_nsec = 36863
* record.info.text_len = 11
* record.info.facility = 0 (LOG_KERN)
* record.info.flags = 0
* record.info.level = 3 (LOG_ERR)
* record.info.caller_id = 299 (task 299)
* record.info.dev_info.subsystem = "pci" (terminated)
* record.info.dev_info.device = "+pci:0000:00:01.0" (terminated)
*
* The 'struct printk_info' buffer must never be directly exported to
* userspace, it is a kernel-private implementation detail that might
* need to be changed in the future, when the requirements change.
*
* /dev/kmsg exports the structured data in the following line format:
* "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n"
*
* Users of the export format should ignore possible additional values
* separated by ',', and find the message after the ';' character.
*
* The optional key/value pairs are attached as continuation lines starting
* with a space character and terminated by a newline. All possible
* non-prinatable characters are escaped in the "\xff" notation.
*/
/* syslog_lock protects syslog_* variables and write access to clear_seq. */
static DEFINE_MUTEX(syslog_lock);
/*
* Specifies if a legacy console is registered. If legacy consoles are
* present, it is necessary to perform the console lock/unlock dance
* whenever console flushing should occur.
*/
bool have_legacy_console;
/*
* Specifies if an nbcon console is registered. If nbcon consoles are present,
* synchronous printing of legacy consoles will not occur during panic until
* the backtrace has been stored to the ringbuffer.
*/
bool have_nbcon_console;
/*
* Specifies if a boot console is registered. If boot consoles are present,
* nbcon consoles cannot print simultaneously and must be synchronized by
* the console lock. This is because boot consoles and nbcon consoles may
* have mapped the same hardware.
*/
bool have_boot_console;
/* See printk_legacy_allow_panic_sync() for details. */
bool legacy_allow_panic_sync;
#ifdef CONFIG_PRINTK
DECLARE_WAIT_QUEUE_HEAD(log_wait);
static DECLARE_WAIT_QUEUE_HEAD(legacy_wait);
/* All 3 protected by @syslog_lock. */
/* the next printk record to read by syslog(READ) or /proc/kmsg */
static u64 syslog_seq;
static size_t syslog_partial;
static bool syslog_time;
/* True when _all_ printer threads are available for printing. */
bool printk_kthreads_running;
struct latched_seq {
seqcount_latch_t latch;
u64 val[2];
};
/*
* The next printk record to read after the last 'clear' command. There are
* two copies (updated with seqcount_latch) so that reads can locklessly
* access a valid value. Writers are synchronized by @syslog_lock.
*/
static struct latched_seq clear_seq = {
.latch = SEQCNT_LATCH_ZERO(clear_seq.latch),
.val[0] = 0,
.val[1] = 0,
};
#define LOG_LEVEL(v) ((v) & 0x07)
#define LOG_FACILITY(v) ((v) >> 3 & 0xff)
/* record buffer */
#define LOG_ALIGN __alignof__(unsigned long)
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
#define LOG_BUF_LEN_MAX ((u32)1 << 31)
static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
static char *log_buf = __log_buf;
static u32 log_buf_len = __LOG_BUF_LEN;
/*
* Define the average message size. This only affects the number of
* descriptors that will be available. Underestimating is better than
* overestimating (too many available descriptors is better than not enough).
*/
#define PRB_AVGBITS 5 /* 32 character average length */
#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS
#error CONFIG_LOG_BUF_SHIFT value too small.
#endif
_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
PRB_AVGBITS, &__log_buf[0]);
static struct printk_ringbuffer printk_rb_dynamic;
struct printk_ringbuffer *prb = &printk_rb_static;
/*
* We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
* per_cpu_areas are initialised. This variable is set to true when
* it's safe to access per-CPU data.
*/
static bool __printk_percpu_data_ready __ro_after_init;
bool printk_percpu_data_ready(void)
{
return __printk_percpu_data_ready;
}
/* Must be called under syslog_lock. */
static void latched_seq_write(struct latched_seq *ls, u64 val)
{
write_seqcount_latch_begin(&ls->latch);
ls->val[0] = val;
write_seqcount_latch(&ls->latch);
ls->val[1] = val;
write_seqcount_latch_end(&ls->latch);
}
/* Can be called from any context. */
static u64 latched_seq_read_nolock(struct latched_seq *ls)
{
unsigned int seq;
unsigned int idx;
u64 val;
do {
seq = read_seqcount_latch(&ls->latch);
idx = seq & 0x1;
val = ls->val[idx];
} while (read_seqcount_latch_retry(&ls->latch, seq));
return val;
}
/* Return log buffer address */
char *log_buf_addr_get(void)
{
return log_buf;
}
/* Return log buffer size */
u32 log_buf_len_get(void)
{
return log_buf_len;
}
/*
* Define how much of the log buffer we could take at maximum. The value
* must be greater than two. Note that only half of the buffer is available
* when the index points to the middle.
*/
#define MAX_LOG_TAKE_PART 4
static const char trunc_msg[] = "<truncated>";
static void truncate_msg(u16 *text_len, u16 *trunc_msg_len)
{
/*
* The message should not take the whole buffer. Otherwise, it might
* get removed too soon.
*/
u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART;
if (*text_len > max_text_len)
*text_len = max_text_len;
/* enable the warning message (if there is room) */
*trunc_msg_len = strlen(trunc_msg);
if (*text_len >= *trunc_msg_len)
*text_len -= *trunc_msg_len;
else
*trunc_msg_len = 0;
}
int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT);
static int syslog_action_restricted(int type)
{
if (dmesg_restrict)
return 1;
/*
* Unless restricted, we allow "read all" and "get buffer size"
* for everybody.
*/
return type != SYSLOG_ACTION_READ_ALL &&
type != SYSLOG_ACTION_SIZE_BUFFER;
}
static int check_syslog_permissions(int type, int source)
{
/*
* If this is from /proc/kmsg and we've already opened it, then we've
* already done the capabilities checks at open time.
*/
if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN)
goto ok;
if (syslog_action_restricted(type)) {
if (capable(CAP_SYSLOG))
goto ok;
return -EPERM;
}
ok:
return security_syslog(type);
}
static void append_char(char **pp, char *e, char c)
{
if (*pp < e) *(*pp)++ = c;
}
static ssize_t info_print_ext_header(char *buf, size_t size,
struct printk_info *info)
{
u64 ts_usec = info->ts_nsec;
char caller[20];
#ifdef CONFIG_PRINTK_CALLER
u32 id = info->caller_id;
snprintf(caller, sizeof(caller), ",caller=%c%u",
id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
#else
caller[0] = '\0';
#endif
do_div(ts_usec, 1000);
return scnprintf(buf, size, "%u,%llu,%llu,%c%s;",
(info->facility << 3) | info->level, info->seq,
ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller);
}
static ssize_t msg_add_ext_text(char *buf, size_t size,
const char *text, size_t text_len,
unsigned char endc)
{
char *p = buf, *e = buf + size;
size_t i;
/* escape non-printable characters */
for (i = 0; i < text_len; i++) {
unsigned char c = text[i];
if (c < ' ' || c >= 127 || c == '\\')
p += scnprintf(p, e - p, "\\x%02x", c);
else
append_char(&p, e, c);
}
append_char(&p, e, endc);
return p - buf;
}
static ssize_t msg_add_dict_text(char *buf, size_t size,
const char *key, const char *val)
{
size_t val_len = strlen(val);
ssize_t len;
if (!val_len)
return 0;
len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */
len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '=');
len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n');
return len;
}
static ssize_t msg_print_ext_body(char *buf, size_t size,
char *text, size_t text_len,
struct dev_printk_info *dev_info)
{
ssize_t len;
len = msg_add_ext_text(buf, size, text, text_len, '\n');
if (!dev_info)
goto out;
len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM",
dev_info->subsystem);
len += msg_add_dict_text(buf + len, size - len, "DEVICE",
dev_info->device);
out:
return len;
}
/* /dev/kmsg - userspace message inject/listen interface */
struct devkmsg_user {
atomic64_t seq;
struct ratelimit_state rs;
struct mutex lock;
struct printk_buffers pbufs;
};
static __printf(3, 4) __cold
int devkmsg_emit(int facility, int level, const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = vprintk_emit(facility, level, NULL, fmt, args);
va_end(args);
return r;
}
static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
{
char *buf, *line;
int level = default_message_loglevel;
int facility = 1; /* LOG_USER */
struct file *file = iocb->ki_filp;
struct devkmsg_user *user = file->private_data;
size_t len = iov_iter_count(from);
ssize_t ret = len;
if (len > PRINTKRB_RECORD_MAX)
return -EINVAL;
/* Ignore when user logging is disabled. */
if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
return len;
/* Ratelimit when not explicitly enabled. */
if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) {
if (!___ratelimit(&user->rs, current->comm))
return ret;
}
buf = kmalloc(len+1, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
buf[len] = '\0';
if (!copy_from_iter_full(buf, len, from)) {
kfree(buf);
return -EFAULT;
}
/*
* Extract and skip the syslog prefix <[0-9]*>. Coming from userspace
* the decimal value represents 32bit, the lower 3 bit are the log
* level, the rest are the log facility.
*
* If no prefix or no userspace facility is specified, we
* enforce LOG_USER, to be able to reliably distinguish
* kernel-generated messages from userspace-injected ones.
*/
line = buf;
if (line[0] == '<') {
char *endp = NULL;
unsigned int u;
u = simple_strtoul(line + 1, &endp, 10);
if (endp && endp[0] == '>') {
level = LOG_LEVEL(u);
if (LOG_FACILITY(u) != 0)
facility = LOG_FACILITY(u);
endp++;
line = endp;
}
}
devkmsg_emit(facility, level, "%s", line);
kfree(buf);
return ret;
}
static ssize_t devkmsg_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct devkmsg_user *user = file->private_data;
char *outbuf = &user->pbufs.outbuf[0];
struct printk_message pmsg = {
.pbufs = &user->pbufs,
};
ssize_t ret;
ret = mutex_lock_interruptible(&user->lock);
if (ret)
return ret;
if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
goto out;
}
/*
* Guarantee this task is visible on the waitqueue before
* checking the wake condition.
*
* The full memory barrier within set_current_state() of
* prepare_to_wait_event() pairs with the full memory barrier
* within wq_has_sleeper().
*
* This pairs with __wake_up_klogd:A.
*/
ret = wait_event_interruptible(log_wait,
printk_get_next_message(&pmsg, atomic64_read(&user->seq), true,
false)); /* LMM(devkmsg_read:A) */
if (ret)
goto out;
}
if (pmsg.dropped) {
/* our last seen message is gone, return error and reset */
atomic64_set(&user->seq, pmsg.seq);
ret = -EPIPE;
goto out;
}
atomic64_set(&user->seq, pmsg.seq + 1);
if (pmsg.outbuf_len > count) {
ret = -EINVAL;
goto out;
}
if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) {
ret = -EFAULT;
goto out;
}
ret = pmsg.outbuf_len;
out:
mutex_unlock(&user->lock);
return ret;
}
/*
* Be careful when modifying this function!!!
*
* Only few operations are supported because the device works only with the
* entire variable length messages (records). Non-standard values are
* returned in the other cases and has been this way for quite some time.
* User space applications might depend on this behavior.
*/
static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
{
struct devkmsg_user *user = file->private_data;
loff_t ret = 0;
if (offset)
return -ESPIPE;
switch (whence) {
case SEEK_SET:
/* the first record */
atomic64_set(&user->seq, prb_first_valid_seq(prb));
break;
case SEEK_DATA:
/*
* The first record after the last SYSLOG_ACTION_CLEAR,
* like issued by 'dmesg -c'. Reading /dev/kmsg itself
* changes no global state, and does not clear anything.
*/
atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq));
break;
case SEEK_END:
/* after the last record */
atomic64_set(&user->seq, prb_next_seq(prb));
break;
default:
ret = -EINVAL;
}
return ret;
}
static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
{
struct devkmsg_user *user = file->private_data;
struct printk_info info;
__poll_t ret = 0;
poll_wait(file, &log_wait, wait);
if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
/* return error when data has vanished underneath us */
if (info.seq != atomic64_read(&user->seq))
ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
else
ret = EPOLLIN|EPOLLRDNORM;
}
return ret;
}
static int devkmsg_open(struct inode *inode, struct file *file)
{
struct devkmsg_user *user;
int err;
if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
return -EPERM;
/* write-only does not need any file context */
if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
SYSLOG_FROM_READER);
if (err)
return err;
}
user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
if (!user)
return -ENOMEM;
ratelimit_default_init(&user->rs);
ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);
mutex_init(&user->lock);
atomic64_set(&user->seq, prb_first_valid_seq(prb));
file->private_data = user;
return 0;
}
static int devkmsg_release(struct inode *inode, struct file *file)
{
struct devkmsg_user *user = file->private_data;
ratelimit_state_exit(&user->rs);
mutex_destroy(&user->lock);
kvfree(user);
return 0;
}
const struct file_operations kmsg_fops = {
.open = devkmsg_open,
.read = devkmsg_read,
.write_iter = devkmsg_write,
.llseek = devkmsg_llseek,
.poll = devkmsg_poll,
.release = devkmsg_release,
};
#ifdef CONFIG_VMCORE_INFO
/*
* This appends the listed symbols to /proc/vmcore
*
* /proc/vmcore is used by various utilities, like crash and makedumpfile to
* obtain access to symbols that are otherwise very difficult to locate. These
* symbols are specifically used so that utilities can access and extract the
* dmesg log from a vmcore file after a crash.
*/
void log_buf_vmcoreinfo_setup(void)
{
struct dev_printk_info *dev_info = NULL;
VMCOREINFO_SYMBOL(prb);
VMCOREINFO_SYMBOL(printk_rb_static);
VMCOREINFO_SYMBOL(clear_seq);
/*
* Export struct size and field offsets. User space tools can
* parse it and detect any changes to structure down the line.
*/
VMCOREINFO_STRUCT_SIZE(printk_ringbuffer);
VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring);
VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring);
VMCOREINFO_OFFSET(printk_ringbuffer, fail);
VMCOREINFO_STRUCT_SIZE(prb_desc_ring);
VMCOREINFO_OFFSET(prb_desc_ring, count_bits);
VMCOREINFO_OFFSET(prb_desc_ring, descs);
VMCOREINFO_OFFSET(prb_desc_ring, infos);
VMCOREINFO_OFFSET(prb_desc_ring, head_id);
VMCOREINFO_OFFSET(prb_desc_ring, tail_id);
VMCOREINFO_STRUCT_SIZE(prb_desc);
VMCOREINFO_OFFSET(prb_desc, state_var);
VMCOREINFO_OFFSET(prb_desc, text_blk_lpos);
VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos);
VMCOREINFO_OFFSET(prb_data_blk_lpos, begin);
VMCOREINFO_OFFSET(prb_data_blk_lpos, next);
VMCOREINFO_STRUCT_SIZE(printk_info);
VMCOREINFO_OFFSET(printk_info, seq);
VMCOREINFO_OFFSET(printk_info, ts_nsec);
VMCOREINFO_OFFSET(printk_info, text_len);
VMCOREINFO_OFFSET(printk_info, caller_id);
VMCOREINFO_OFFSET(printk_info, dev_info);
VMCOREINFO_STRUCT_SIZE(dev_printk_info);
VMCOREINFO_OFFSET(dev_printk_info, subsystem);
VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem));
VMCOREINFO_OFFSET(dev_printk_info, device);
VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device));
VMCOREINFO_STRUCT_SIZE(prb_data_ring);
VMCOREINFO_OFFSET(prb_data_ring, size_bits);
VMCOREINFO_OFFSET(prb_data_ring, data);
VMCOREINFO_OFFSET(prb_data_ring, head_lpos);
VMCOREINFO_OFFSET(prb_data_ring, tail_lpos);
VMCOREINFO_SIZE(atomic_long_t);
VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter);
VMCOREINFO_STRUCT_SIZE(latched_seq);
VMCOREINFO_OFFSET(latched_seq, val);
}
#endif
/* requested log_buf_len from kernel cmdline */
static unsigned long __initdata new_log_buf_len;
/* we practice scaling the ring buffer by powers of 2 */
static void __init log_buf_len_update(u64 size)
{
if (size > (u64)LOG_BUF_LEN_MAX) {
size = (u64)LOG_BUF_LEN_MAX;
pr_err("log_buf over 2G is not supported.\n");
}
if (size)
size = roundup_pow_of_two(size);
if (size > log_buf_len)
new_log_buf_len = (unsigned long)size;
}
/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
u64 size;
if (!str)
return -EINVAL;
size = memparse(str, &str);
log_buf_len_update(size);
return 0;
}
early_param("log_buf_len", log_buf_len_setup);
#ifdef CONFIG_SMP
#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)
static void __init log_buf_add_cpu(void)
{
unsigned int cpu_extra;
/*
* archs should set up cpu_possible_bits properly with
* set_cpu_possible() after setup_arch() but just in
* case lets ensure this is valid.
*/
if (num_possible_cpus() == 1)
return;
cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN;
/* by default this will only continue through for large > 64 CPUs */
if (cpu_extra <= __LOG_BUF_LEN / 2)
return;
pr_info("log_buf_len individual max cpu contribution: %d bytes\n",
__LOG_CPU_MAX_BUF_LEN);
pr_info("log_buf_len total cpu_extra contributions: %d bytes\n",
cpu_extra);
pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN);
log_buf_len_update(cpu_extra + __LOG_BUF_LEN);
}
#else /* !CONFIG_SMP */
static inline void log_buf_add_cpu(void) {}
#endif /* CONFIG_SMP */
static void __init set_percpu_data_ready(void)
{
__printk_percpu_data_ready = true;
}
static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
struct printk_record *r)
{
struct prb_reserved_entry e;
struct printk_record dest_r;
prb_rec_init_wr(&dest_r, r->info->text_len);
if (!prb_reserve(&e, rb, &dest_r))
return 0;
memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len);
dest_r.info->text_len = r->info->text_len;
dest_r.info->facility = r->info->facility;
dest_r.info->level = r->info->level;
dest_r.info->flags = r->info->flags;
dest_r.info->ts_nsec = r->info->ts_nsec;
dest_r.info->caller_id = r->info->caller_id;
memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info));
prb_final_commit(&e);
return prb_record_text_space(&e);
}
static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata;
static void print_log_buf_usage_stats(void)
{
unsigned int descs_count = log_buf_len >> PRB_AVGBITS;
size_t meta_data_size;
meta_data_size = descs_count * (sizeof(struct prb_desc) + sizeof(struct printk_info));
pr_info("log buffer data + meta data: %u + %zu = %zu bytes\n",
log_buf_len, meta_data_size, log_buf_len + meta_data_size);
}
void __init setup_log_buf(int early)
{
struct printk_info *new_infos;
unsigned int new_descs_count;
struct prb_desc *new_descs;
struct printk_info info;
struct printk_record r;
unsigned int text_size;
size_t new_descs_size;
size_t new_infos_size;
unsigned long flags;
char *new_log_buf;
unsigned int free;
u64 seq;
/*
* Some archs call setup_log_buf() multiple times - first is very
* early, e.g. from setup_arch(), and second - when percpu_areas
* are initialised.
*/
if (!early)
set_percpu_data_ready();
if (log_buf != __log_buf)
return;
if (!early && !new_log_buf_len)
log_buf_add_cpu();
if (!new_log_buf_len) {
/* Show the memory stats only once. */
if (!early)
goto out;
return;
}
new_descs_count = new_log_buf_len >> PRB_AVGBITS;
if (new_descs_count == 0) {
pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len);
goto out;
}
new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN);
if (unlikely(!new_log_buf)) {
pr_err("log_buf_len: %lu text bytes not available\n",
new_log_buf_len);
goto out;
}
new_descs_size = new_descs_count * sizeof(struct prb_desc);
new_descs = memblock_alloc(new_descs_size, LOG_ALIGN);
if (unlikely(!new_descs)) {
pr_err("log_buf_len: %zu desc bytes not available\n",
new_descs_size);
goto err_free_log_buf;
}
new_infos_size = new_descs_count * sizeof(struct printk_info);
new_infos = memblock_alloc(new_infos_size, LOG_ALIGN);
if (unlikely(!new_infos)) {
pr_err("log_buf_len: %zu info bytes not available\n",
new_infos_size);
goto err_free_descs;
}
prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf));
prb_init(&printk_rb_dynamic,
new_log_buf, ilog2(new_log_buf_len),
new_descs, ilog2(new_descs_count),
new_infos);
local_irq_save(flags);
log_buf_len = new_log_buf_len;
log_buf = new_log_buf;
new_log_buf_len = 0;
free = __LOG_BUF_LEN;
prb_for_each_record(0, &printk_rb_static, seq, &r) {
text_size = add_to_rb(&printk_rb_dynamic, &r);
if (text_size > free)
free = 0;
else
free -= text_size;
}
prb = &printk_rb_dynamic;
local_irq_restore(flags);
/*
* Copy any remaining messages that might have appeared from
* NMI context after copying but before switching to the
* dynamic buffer.
*/
prb_for_each_record(seq, &printk_rb_static, seq, &r) {
text_size = add_to_rb(&printk_rb_dynamic, &r);
if (text_size > free)
free = 0;
else
free -= text_size;
}
if (seq != prb_next_seq(&printk_rb_static)) {
pr_err("dropped %llu messages\n",
prb_next_seq(&printk_rb_static) - seq);
}
print_log_buf_usage_stats();
pr_info("early log buf free: %u(%u%%)\n",
free, (free * 100) / __LOG_BUF_LEN);
return;
err_free_descs:
memblock_free(new_descs, new_descs_size);
err_free_log_buf:
memblock_free(new_log_buf, new_log_buf_len);
out:
print_log_buf_usage_stats();
}
static bool __read_mostly ignore_loglevel;
static int __init ignore_loglevel_setup(char *str)
{
ignore_loglevel = true;
pr_info("debug: ignoring loglevel setting.\n");
return 0;
}
early_param("ignore_loglevel", ignore_loglevel_setup);
module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ignore_loglevel,
"ignore loglevel setting (prints all kernel messages to the console)");
static bool suppress_message_printing(int level)
{
return (level >= console_loglevel && !ignore_loglevel);
}
#ifdef CONFIG_BOOT_PRINTK_DELAY
static int boot_delay; /* msecs delay after each printk during bootup */
static unsigned long long loops_per_msec; /* based on boot_delay */
static int __init boot_delay_setup(char *str)
{
unsigned long lpj;
lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */
loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
get_option(&str, &boot_delay);
if (boot_delay > 10 * 1000)
boot_delay = 0;
pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
"HZ: %d, loops_per_msec: %llu\n",
boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
return 0;
}
early_param("boot_delay", boot_delay_setup);
static void boot_delay_msec(int level)
{
unsigned long long k;
unsigned long timeout;
bool suppress = !is_printk_force_console() &&
suppress_message_printing(level);
if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress)
return;
k = (unsigned long long)loops_per_msec * boot_delay;
timeout = jiffies + msecs_to_jiffies(boot_delay);
while (k) {
k--;
cpu_relax();
/*
* use (volatile) jiffies to prevent
* compiler reduction; loop termination via jiffies
* is secondary and may or may not happen.
*/
if (time_after(jiffies, timeout))
break;
touch_nmi_watchdog();
}
}
#else
static inline void boot_delay_msec(int level)
{
}
#endif
static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME);
module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
static size_t print_syslog(unsigned int level, char *buf)
{
return sprintf(buf, "<%u>", level);
}
static size_t print_time(u64 ts, char *buf)
{
unsigned long rem_nsec = do_div(ts, 1000000000);
return sprintf(buf, "[%5lu.%06lu]",
(unsigned long)ts, rem_nsec / 1000);
}
#ifdef CONFIG_PRINTK_CALLER
static size_t print_caller(u32 id, char *buf)
{
char caller[12];
snprintf(caller, sizeof(caller), "%c%u",
id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
return sprintf(buf, "[%6s]", caller);
}
#else
#define print_caller(id, buf) 0
#endif
static size_t info_print_prefix(const struct printk_info *info, bool syslog,
bool time, char *buf)
{
size_t len = 0;
if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len);
len += print_caller(info->caller_id, buf + len);
if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) {
buf[len++] = ' ';
buf[len] = '\0';
}
return len;
}
/*
* Prepare the record for printing. The text is shifted within the given
* buffer to avoid a need for another one. The following operations are
* done:
*
* - Add prefix for each line.
* - Drop truncated lines that no longer fit into the buffer.
* - Add the trailing newline that has been removed in vprintk_store().
* - Add a string terminator.
*
* Since the produced string is always terminated, the maximum possible
* return value is @r->text_buf_size - 1;
*
* Return: The length of the updated/prepared text, including the added
* prefixes and the newline. The terminator is not counted. The dropped
* line(s) are not counted.
*/
static size_t record_print_text(struct printk_record *r, bool syslog,
bool time)
{
size_t text_len = r->info->text_len;
size_t buf_size = r->text_buf_size;
char *text = r->text_buf;
char prefix[PRINTK_PREFIX_MAX];
bool truncated = false;
size_t prefix_len;
size_t line_len;
size_t len = 0;
char *next;
/*
* If the message was truncated because the buffer was not large
* enough, treat the available text as if it were the full text.
*/
if (text_len > buf_size)
text_len = buf_size;
prefix_len = info_print_prefix(r->info, syslog, time, prefix);
/*
* @text_len: bytes of unprocessed text
* @line_len: bytes of current line _without_ newline
* @text: pointer to beginning of current line
* @len: number of bytes prepared in r->text_buf
*/
for (;;) {
next = memchr(text, '\n', text_len);
if (next) {
line_len = next - text;
} else {
/* Drop truncated line(s). */
if (truncated)
break;
line_len = text_len;
}
/*
* Truncate the text if there is not enough space to add the
* prefix and a trailing newline and a terminator.
*/
if (len + prefix_len + text_len + 1 + 1 > buf_size) {
/* Drop even the current line if no space. */
if (len + prefix_len + line_len + 1 + 1 > buf_size)
break;
text_len = buf_size - len - prefix_len - 1 - 1;
truncated = true;
}
memmove(text + prefix_len, text, text_len);
memcpy(text, prefix, prefix_len);
/*
* Increment the prepared length to include the text and
* prefix that were just moved+copied. Also increment for the
* newline at the end of this line. If this is the last line,
* there is no newline, but it will be added immediately below.
*/
len += prefix_len + line_len + 1;
if (text_len == line_len) {
/*
* This is the last line. Add the trailing newline
* removed in vprintk_store().
*/
text[prefix_len + line_len] = '\n';
break;
}
/*
* Advance beyond the added prefix and the related line with
* its newline.
*/
text += prefix_len + line_len + 1;
/*
* The remaining text has only decreased by the line with its
* newline.
*
* Note that @text_len can become zero. It happens when @text
* ended with a newline (either due to truncation or the
* original string ending with "\n\n"). The loop is correctly
* repeated and (if not truncated) an empty line with a prefix
* will be prepared.
*/
text_len -= line_len + 1;
}
/*
* If a buffer was provided, it will be terminated. Space for the
* string terminator is guaranteed to be available. The terminator is
* not counted in the return value.
*/
if (buf_size > 0) r->text_buf[len] = 0;
return len;
}
static size_t get_record_print_text_size(struct printk_info *info,
unsigned int line_count,
bool syslog, bool time)
{
char prefix[PRINTK_PREFIX_MAX];
size_t prefix_len;
prefix_len = info_print_prefix(info, syslog, time, prefix);
/*
* Each line will be preceded with a prefix. The intermediate
* newlines are already within the text, but a final trailing
* newline will be added.
*/
return ((prefix_len * line_count) + info->text_len + 1);
}
/*
* Beginning with @start_seq, find the first record where it and all following
* records up to (but not including) @max_seq fit into @size.
*
* @max_seq is simply an upper bound and does not need to exist. If the caller
* does not require an upper bound, -1 can be used for @max_seq.
*/
static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size,
bool syslog, bool time)
{
struct printk_info info;
unsigned int line_count;
size_t len = 0;
u64 seq;
/* Determine the size of the records up to @max_seq. */
prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
if (info.seq >= max_seq)
break;
len += get_record_print_text_size(&info, line_count, syslog, time);
}
/*
* Adjust the upper bound for the next loop to avoid subtracting
* lengths that were never added.
*/
if (seq < max_seq)
max_seq = seq;
/*
* Move first record forward until length fits into the buffer. Ignore
* newest messages that were not counted in the above cycle. Messages
* might appear and get lost in the meantime. This is a best effort
* that prevents an infinite loop that could occur with a retry.
*/
prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
if (len <= size || info.seq >= max_seq)
break;
len -= get_record_print_text_size(&info, line_count, syslog, time);
}
return seq;
}
/* The caller is responsible for making sure @size is greater than 0. */
static int syslog_print(char __user *buf, int size)
{
struct printk_info info;
struct printk_record r;
char *text;
int len = 0;
u64 seq;
text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX);
mutex_lock(&syslog_lock);
/*
* Wait for the @syslog_seq record to be available. @syslog_seq may
* change while waiting.
*/
do {
seq = syslog_seq;
mutex_unlock(&syslog_lock);
/*
* Guarantee this task is visible on the waitqueue before
* checking the wake condition.
*
* The full memory barrier within set_current_state() of
* prepare_to_wait_event() pairs with the full memory barrier
* within wq_has_sleeper().
*
* This pairs with __wake_up_klogd:A.
*/
len = wait_event_interruptible(log_wait,
prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */
mutex_lock(&syslog_lock);
if (len)
goto out;
} while (syslog_seq != seq);
/*
* Copy records that fit into the buffer. The above cycle makes sure
* that the first record is always available.
*/
do {
size_t n;
size_t skip;
int err;
if (!prb_read_valid(prb, syslog_seq, &r))
break;
if (r.info->seq != syslog_seq) {
/* message is gone, move to next valid one */
syslog_seq = r.info->seq;
syslog_partial = 0;
}
/*
* To keep reading/counting partial line consistent,
* use printk_time value as of the beginning of a line.
*/
if (!syslog_partial)
syslog_time = printk_time;
skip = syslog_partial;
n = record_print_text(&r, true, syslog_time);
if (n - syslog_partial <= size) {
/* message fits into buffer, move forward */
syslog_seq = r.info->seq + 1;
n -= syslog_partial;
syslog_partial = 0;
} else if (!len){
/* partial read(), remember position */
n = size;
syslog_partial += n;
} else
n = 0;
if (!n)
break;
mutex_unlock(&syslog_lock);
err = copy_to_user(buf, text + skip, n);
mutex_lock(&syslog_lock);
if (err) {
if (!len)
len = -EFAULT;
break;
}
len += n;
size -= n;
buf += n;
} while (size);
out:
mutex_unlock(&syslog_lock);
kfree(text);
return len;
}
static int syslog_print_all(char __user *buf, int size, bool clear)
{
struct printk_info info;
struct printk_record r;
char *text;
int len = 0;
u64 seq;
bool time;
text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
time = printk_time;
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump.
*/
seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1,
size, true, time);
prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX);
prb_for_each_record(seq, prb, seq, &r) {
int textlen;
textlen = record_print_text(&r, true, time);
if (len + textlen > size) {
seq--;
break;
}
if (copy_to_user(buf + len, text, textlen))
len = -EFAULT;
else
len += textlen;
if (len < 0)
break;
}
if (clear) {
mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, seq);
mutex_unlock(&syslog_lock);
}
kfree(text);
return len;
}
static void syslog_clear(void)
{
mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, prb_next_seq(prb));
mutex_unlock(&syslog_lock);
}
int do_syslog(int type, char __user *buf, int len, int source)
{
struct printk_info info;
bool clear = false;
static int saved_console_loglevel = LOGLEVEL_DEFAULT;
int error;
error = check_syslog_permissions(type, source);
if (error)
return error;
switch (type) {
case SYSLOG_ACTION_CLOSE: /* Close log */
break;
case SYSLOG_ACTION_OPEN: /* Open log */
break;
case SYSLOG_ACTION_READ: /* Read from log */
if (!buf || len < 0)
return -EINVAL;
if (!len)
return 0;
if (!access_ok(buf, len))
return -EFAULT;
error = syslog_print(buf, len);
break;
/* Read/clear last kernel messages */
case SYSLOG_ACTION_READ_CLEAR:
clear = true;
fallthrough;
/* Read last kernel messages */
case SYSLOG_ACTION_READ_ALL:
if (!buf || len < 0)
return -EINVAL;
if (!len)
return 0;
if (!access_ok(buf, len))
return -EFAULT;
error = syslog_print_all(buf, len, clear);
break;
/* Clear ring buffer */
case SYSLOG_ACTION_CLEAR:
syslog_clear();
break;
/* Disable logging to console */
case SYSLOG_ACTION_CONSOLE_OFF:
if (saved_console_loglevel == LOGLEVEL_DEFAULT)
saved_console_loglevel = console_loglevel;
console_loglevel = minimum_console_loglevel;
break;
/* Enable logging to console */
case SYSLOG_ACTION_CONSOLE_ON:
if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
console_loglevel = saved_console_loglevel;
saved_console_loglevel = LOGLEVEL_DEFAULT;
}
break;
/* Set level of messages printed to console */
case SYSLOG_ACTION_CONSOLE_LEVEL:
if (len < 1 || len > 8)
return -EINVAL;
if (len < minimum_console_loglevel)
len = minimum_console_loglevel;
console_loglevel = len;
/* Implicitly re-enable logging to console */
saved_console_loglevel = LOGLEVEL_DEFAULT;
break;
/* Number of chars in the log buffer */
case SYSLOG_ACTION_SIZE_UNREAD:
mutex_lock(&syslog_lock);
if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
/* No unread messages. */
mutex_unlock(&syslog_lock);
return 0;
}
if (info.seq != syslog_seq) {
/* messages are gone, move to first one */
syslog_seq = info.seq;
syslog_partial = 0;
}
if (source == SYSLOG_FROM_PROC) {
/*
* Short-cut for poll(/"proc/kmsg") which simply checks
* for pending data, not the size; return the count of
* records, not the length.
*/
error = prb_next_seq(prb) - syslog_seq;
} else {
bool time = syslog_partial ? syslog_time : printk_time;
unsigned int line_count;
u64 seq;
prb_for_each_info(syslog_seq, prb, seq, &info,
&line_count) {
error += get_record_print_text_size(&info, line_count,
true, time);
time = printk_time;
}
error -= syslog_partial;
}
mutex_unlock(&syslog_lock);
break;
/* Size of the log buffer */
case SYSLOG_ACTION_SIZE_BUFFER:
error = log_buf_len;
break;
default:
error = -EINVAL;
break;
}
return error;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
{
return do_syslog(type, buf, len, SYSLOG_FROM_READER);
}
/*
* Special console_lock variants that help to reduce the risk of soft-lockups.
* They allow to pass console_lock to another printk() call using a busy wait.
*/
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_owner_dep_map = {
.name = "console_owner"
};
#endif
static DEFINE_RAW_SPINLOCK(console_owner_lock);
static struct task_struct *console_owner;
static bool console_waiter;
/**
* console_lock_spinning_enable - mark beginning of code where another
* thread might safely busy wait
*
* This basically converts console_lock into a spinlock. This marks
* the section where the console_lock owner can not sleep, because
* there may be a waiter spinning (like a spinlock). Also it must be
* ready to hand over the lock at the end of the section.
*/
void console_lock_spinning_enable(void)
{
/*
* Do not use spinning in panic(). The panic CPU wants to keep the lock.
* Non-panic CPUs abandon the flush anyway.
*
* Just keep the lockdep annotation. The panic-CPU should avoid
* taking console_owner_lock because it might cause a deadlock.
* This looks like the easiest way how to prevent false lockdep
* reports without handling races a lockless way.
*/
if (panic_in_progress())
goto lockdep;
raw_spin_lock(&console_owner_lock);
console_owner = current;
raw_spin_unlock(&console_owner_lock);
lockdep:
/* The waiter may spin on us after setting console_owner */
spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
}
/**
* console_lock_spinning_disable_and_check - mark end of code where another
* thread was able to busy wait and check if there is a waiter
* @cookie: cookie returned from console_srcu_read_lock()
*
* This is called at the end of the section where spinning is allowed.
* It has two functions. First, it is a signal that it is no longer
* safe to start busy waiting for the lock. Second, it checks if
* there is a busy waiter and passes the lock rights to her.
*
* Important: Callers lose both the console_lock and the SRCU read lock if
* there was a busy waiter. They must not touch items synchronized by
* console_lock or SRCU read lock in this case.
*
* Return: 1 if the lock rights were passed, 0 otherwise.
*/
int console_lock_spinning_disable_and_check(int cookie)
{
int waiter;
/*
* Ignore spinning waiters during panic() because they might get stopped
* or blocked at any time,
*
* It is safe because nobody is allowed to start spinning during panic
* in the first place. If there has been a waiter then non panic CPUs
* might stay spinning. They would get stopped anyway. The panic context
* will never start spinning and an interrupted spin on panic CPU will
* never continue.
*/
if (panic_in_progress()) {
/* Keep lockdep happy. */
spin_release(&console_owner_dep_map, _THIS_IP_);
return 0;
}
raw_spin_lock(&console_owner_lock);
waiter = READ_ONCE(console_waiter);
console_owner = NULL;
raw_spin_unlock(&console_owner_lock);
if (!waiter) {
spin_release(&console_owner_dep_map, _THIS_IP_);
return 0;
}
/* The waiter is now free to continue */
WRITE_ONCE(console_waiter, false);
spin_release(&console_owner_dep_map, _THIS_IP_);
/*
* Preserve lockdep lock ordering. Release the SRCU read lock before
* releasing the console_lock.
*/
console_srcu_read_unlock(cookie);
/*
* Hand off console_lock to waiter. The waiter will perform
* the up(). After this, the waiter is the console_lock owner.
*/
mutex_release(&console_lock_dep_map, _THIS_IP_);
return 1;
}
/**
* console_trylock_spinning - try to get console_lock by busy waiting
*
* This allows to busy wait for the console_lock when the current
* owner is running in specially marked sections. It means that
* the current owner is running and cannot reschedule until it
* is ready to lose the lock.
*
* Return: 1 if we got the lock, 0 othrewise
*/
static int console_trylock_spinning(void)
{
struct task_struct *owner = NULL;
bool waiter;
bool spin = false;
unsigned long flags;
if (console_trylock())
return 1;
/*
* It's unsafe to spin once a panic has begun. If we are the
* panic CPU, we may have already halted the owner of the
* console_sem. If we are not the panic CPU, then we should
* avoid taking console_sem, so the panic CPU has a better
* chance of cleanly acquiring it later.
*/
if (panic_in_progress())
return 0;
printk_safe_enter_irqsave(flags);
raw_spin_lock(&console_owner_lock);
owner = READ_ONCE(console_owner);
waiter = READ_ONCE(console_waiter);
if (!waiter && owner && owner != current) {
WRITE_ONCE(console_waiter, true);
spin = true;
}
raw_spin_unlock(&console_owner_lock);
/*
* If there is an active printk() writing to the
* consoles, instead of having it write our data too,
* see if we can offload that load from the active
* printer, and do some printing ourselves.
* Go into a spin only if there isn't already a waiter
* spinning, and there is an active printer, and
* that active printer isn't us (recursive printk?).
*/
if (!spin) {
printk_safe_exit_irqrestore(flags);
return 0;
}
/* We spin waiting for the owner to release us */
spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
/* Owner will clear console_waiter on hand off */
while (READ_ONCE(console_waiter))
cpu_relax();
spin_release(&console_owner_dep_map, _THIS_IP_);
printk_safe_exit_irqrestore(flags);
/*
* The owner passed the console lock to us.
* Since we did not spin on console lock, annotate
* this as a trylock. Otherwise lockdep will
* complain.
*/
mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);
/*
* Update @console_may_schedule for trylock because the previous
* owner may have been schedulable.
*/
console_may_schedule = 0;
return 1;
}
/*
* Recursion is tracked separately on each CPU. If NMIs are supported, an
* additional NMI context per CPU is also separately tracked. Until per-CPU
* is available, a separate "early tracking" is performed.
*/
static DEFINE_PER_CPU(u8, printk_count);
static u8 printk_count_early;
#ifdef CONFIG_HAVE_NMI
static DEFINE_PER_CPU(u8, printk_count_nmi);
static u8 printk_count_nmi_early;
#endif
/*
* Recursion is limited to keep the output sane. printk() should not require
* more than 1 level of recursion (allowing, for example, printk() to trigger
* a WARN), but a higher value is used in case some printk-internal errors
* exist, such as the ringbuffer validation checks failing.
*/
#define PRINTK_MAX_RECURSION 3
/*
* Return a pointer to the dedicated counter for the CPU+context of the
* caller.
*/
static u8 *__printk_recursion_counter(void)
{
#ifdef CONFIG_HAVE_NMI
if (in_nmi()) {
if (printk_percpu_data_ready())
return this_cpu_ptr(&printk_count_nmi);
return &printk_count_nmi_early;
}
#endif
if (printk_percpu_data_ready())
return this_cpu_ptr(&printk_count);
return &printk_count_early;
}
/*
* Enter recursion tracking. Interrupts are disabled to simplify tracking.
* The caller must check the boolean return value to see if the recursion is
* allowed. On failure, interrupts are not disabled.
*
* @recursion_ptr must be a variable of type (u8 *) and is the same variable
* that is passed to printk_exit_irqrestore().
*/
#define printk_enter_irqsave(recursion_ptr, flags) \
({ \
bool success = true; \
\
typecheck(u8 *, recursion_ptr); \
local_irq_save(flags); \
(recursion_ptr) = __printk_recursion_counter(); \
if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \
local_irq_restore(flags); \
success = false; \
} else { \
(*(recursion_ptr))++; \
} \
success; \
})
/* Exit recursion tracking, restoring interrupts. */
#define printk_exit_irqrestore(recursion_ptr, flags) \
do { \
typecheck(u8 *, recursion_ptr); \
(*(recursion_ptr))--; \
local_irq_restore(flags); \
} while (0)
int printk_delay_msec __read_mostly;
static inline void printk_delay(int level)
{
boot_delay_msec(level);
if (unlikely(printk_delay_msec)) {
int m = printk_delay_msec;
while (m--) {
mdelay(1);
touch_nmi_watchdog();
}
}
}
static inline u32 printk_caller_id(void)
{
return in_task() ? task_pid_nr(current) : 0x80000000 + smp_processor_id();
}
/**
* printk_parse_prefix - Parse level and control flags.
*
* @text: The terminated text message.
* @level: A pointer to the current level value, will be updated.
* @flags: A pointer to the current printk_info flags, will be updated.
*
* @level may be NULL if the caller is not interested in the parsed value.
* Otherwise the variable pointed to by @level must be set to
* LOGLEVEL_DEFAULT in order to be updated with the parsed value.
*
* @flags may be NULL if the caller is not interested in the parsed value.
* Otherwise the variable pointed to by @flags will be OR'd with the parsed
* value.
*
* Return: The length of the parsed level and control flags.
*/
u16 printk_parse_prefix(const char *text, int *level,
enum printk_info_flags *flags)
{
u16 prefix_len = 0;
int kern_level;
while (*text) { kern_level = printk_get_level(text);
if (!kern_level)
break;
switch (kern_level) {
case '0' ... '7':
if (level && *level == LOGLEVEL_DEFAULT)
*level = kern_level - '0';
break;
case 'c': /* KERN_CONT */
if (flags)
*flags |= LOG_CONT;
}
prefix_len += 2;
text += 2;
}
return prefix_len;
}
__printf(5, 0)
static u16 printk_sprint(char *text, u16 size, int facility,
enum printk_info_flags *flags, const char *fmt,
va_list args)
{
u16 text_len;
text_len = vscnprintf(text, size, fmt, args);
/* Mark and strip a trailing newline. */
if (text_len && text[text_len - 1] == '\n') { text_len--;
*flags |= LOG_NEWLINE;
}
/* Strip log level and control flags. */
if (facility == 0) {
u16 prefix_len;
prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len;
memmove(text, text + prefix_len, text_len);
}
}
trace_console(text, text_len);
return text_len;
}
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args)
{
struct prb_reserved_entry e;
enum printk_info_flags flags = 0;
struct printk_record r;
unsigned long irqflags;
u16 trunc_msg_len = 0;
char prefix_buf[8];
u8 *recursion_ptr;
u16 reserve_size;
va_list args2;
u32 caller_id;
u16 text_len;
int ret = 0;
u64 ts_nsec;
if (!printk_enter_irqsave(recursion_ptr, irqflags))
return 0;
/*
* Since the duration of printk() can vary depending on the message
* and state of the ringbuffer, grab the timestamp now so that it is
* close to the call of printk(). This provides a more deterministic
* timestamp with respect to the caller.
*/
ts_nsec = local_clock();
caller_id = printk_caller_id();
/*
* The sprintf needs to come first since the syslog prefix might be
* passed in as a parameter. An extra byte must be reserved so that
* later the vscnprintf() into the reserved buffer has room for the
* terminating '\0', which is not counted by vsnprintf().
*/
va_copy(args2, args);
reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1;
va_end(args2);
if (reserve_size > PRINTKRB_RECORD_MAX)
reserve_size = PRINTKRB_RECORD_MAX;
/* Extract log level or control flags. */
if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (is_printk_force_console()) flags |= LOG_FORCE_CON; if (flags & LOG_CONT) {
prb_rec_init_wr(&r, reserve_size);
if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) {
text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size,
facility, &flags, fmt, args);
r.info->text_len += text_len;
if (flags & LOG_FORCE_CON) r.info->flags |= LOG_FORCE_CON;
if (flags & LOG_NEWLINE) {
r.info->flags |= LOG_NEWLINE;
prb_final_commit(&e);
} else {
prb_commit(&e);
}
ret = text_len;
goto out;
}
}
/*
* Explicitly initialize the record before every prb_reserve() call.
* prb_reserve_in_last() and prb_reserve() purposely invalidate the
* structure when they fail.
*/
prb_rec_init_wr(&r, reserve_size);
if (!prb_reserve(&e, prb, &r)) {
/* truncate the message if it is too long for empty buffer */
truncate_msg(&reserve_size, &trunc_msg_len);
prb_rec_init_wr(&r, reserve_size + trunc_msg_len);
if (!prb_reserve(&e, prb, &r))
goto out;
}
/* fill message */
text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args);
if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
r.info->text_len = text_len + trunc_msg_len;
r.info->facility = facility;
r.info->level = level & 7;
r.info->flags = flags & 0x1f;
r.info->ts_nsec = ts_nsec;
r.info->caller_id = caller_id;
if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
/* A message without a trailing newline can be continued. */
if (!(flags & LOG_NEWLINE))
prb_commit(&e);
else
prb_final_commit(&e);
ret = text_len + trunc_msg_len;
out:
printk_exit_irqrestore(recursion_ptr, irqflags);
return ret;
}
/*
* This acts as a one-way switch to allow legacy consoles to print from
* the printk() caller context on a panic CPU. It also attempts to flush
* the legacy consoles in this context.
*/
void printk_legacy_allow_panic_sync(void)
{
struct console_flush_type ft;
legacy_allow_panic_sync = true;
printk_get_console_flush_type(&ft);
if (ft.legacy_direct) {
if (console_trylock())
console_unlock();
}
}
bool __read_mostly debug_non_panic_cpus;
#ifdef CONFIG_PRINTK_CALLER
static int __init debug_non_panic_cpus_setup(char *str)
{
debug_non_panic_cpus = true;
pr_info("allow messages from non-panic CPUs in panic()\n");
return 0;
}
early_param("debug_non_panic_cpus", debug_non_panic_cpus_setup);
module_param(debug_non_panic_cpus, bool, 0644);
MODULE_PARM_DESC(debug_non_panic_cpus,
"allow messages from non-panic CPUs in panic()");
#endif
asmlinkage int vprintk_emit(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args)
{
struct console_flush_type ft;
int printed_len;
/* Suppress unimportant messages after panic happens */
if (unlikely(suppress_printk))
return 0;
/*
* The messages on the panic CPU are the most important. If
* non-panic CPUs are generating any messages, they will be
* silently dropped.
*/
if (other_cpu_in_panic() && !debug_non_panic_cpus &&
!panic_triggering_all_cpu_backtrace)
return 0;
printk_get_console_flush_type(&ft);
/* If called from the scheduler, we can not call up(). */
if (level == LOGLEVEL_SCHED) {
level = LOGLEVEL_DEFAULT;
ft.legacy_offload |= ft.legacy_direct;
ft.legacy_direct = false;
}
printk_delay(level);
printed_len = vprintk_store(facility, level, dev_info, fmt, args);
if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) {
/*
* The caller may be holding system-critical or
* timing-sensitive locks. Disable preemption during
* printing of all remaining records to all consoles so that
* this context can return as soon as possible. Hopefully
* another printk() caller will take over the printing.
*/
preempt_disable();
/*
* Try to acquire and then immediately release the console
* semaphore. The release will print out buffers. With the
* spinning variant, this context tries to take over the
* printing from another printing context.
*/
if (console_trylock_spinning()) console_unlock(); preempt_enable();
}
if (ft.legacy_offload)
defer_console_output();
else
wake_up_klogd();
return printed_len;
}
EXPORT_SYMBOL(vprintk_emit);
int vprintk_default(const char *fmt, va_list args)
{
return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
}
EXPORT_SYMBOL_GPL(vprintk_default);
asmlinkage __visible int _printk(const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = vprintk(fmt, args);
va_end(args);
return r;
}
EXPORT_SYMBOL(_printk);
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
#else /* CONFIG_PRINTK */
#define printk_time false
#define prb_read_valid(rb, seq, r) false
#define prb_first_valid_seq(rb) 0
#define prb_next_seq(rb) 0
static u64 syslog_seq;
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
#endif /* CONFIG_PRINTK */
#ifdef CONFIG_EARLY_PRINTK
struct console *early_console;
asmlinkage __visible void early_printk(const char *fmt, ...)
{
va_list ap;
char buf[512];
int n;
if (!early_console)
return;
va_start(ap, fmt);
n = vscnprintf(buf, sizeof(buf), fmt, ap);
va_end(ap);
early_console->write(early_console, buf, n);
}
#endif
static void set_user_specified(struct console_cmdline *c, bool user_specified)
{
if (!user_specified)
return;
/*
* @c console was defined by the user on the command line.
* Do not clear when added twice also by SPCR or the device tree.
*/
c->user_specified = true;
/* At least one console defined by the user on the command line. */
console_set_on_cmdline = 1;
}
static int __add_preferred_console(const char *name, const short idx,
const char *devname, char *options,
char *brl_options, bool user_specified)
{
struct console_cmdline *c;
int i;
if (!name && !devname)
return -EINVAL;
/*
* We use a signed short index for struct console for device drivers to
* indicate a not yet assigned index or port. However, a negative index
* value is not valid when the console name and index are defined on
* the command line.
*/
if (name && idx < 0)
return -EINVAL;
/*
* See if this tty is not yet registered, and
* if we have a slot free.
*/
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]);
i++, c++) {
if ((name && strcmp(c->name, name) == 0 && c->index == idx) ||
(devname && strcmp(c->devname, devname) == 0)) {
if (!brl_options)
preferred_console = i;
set_user_specified(c, user_specified);
return 0;
}
}
if (i == MAX_CMDLINECONSOLES)
return -E2BIG;
if (!brl_options)
preferred_console = i;
if (name)
strscpy(c->name, name);
if (devname)
strscpy(c->devname, devname);
c->options = options;
set_user_specified(c, user_specified);
braille_set_options(c, brl_options);
c->index = idx;
return 0;
}
static int __init console_msg_format_setup(char *str)
{
if (!strcmp(str, "syslog"))
console_msg_format = MSG_FORMAT_SYSLOG;
if (!strcmp(str, "default"))
console_msg_format = MSG_FORMAT_DEFAULT;
return 1;
}
__setup("console_msg_format=", console_msg_format_setup);
/*
* Set up a console. Called via do_early_param() in init/main.c
* for each "console=" parameter in the boot command line.
*/
static int __init console_setup(char *str)
{
static_assert(sizeof(console_cmdline[0].devname) >= sizeof(console_cmdline[0].name) + 4);
char buf[sizeof(console_cmdline[0].devname)];
char *brl_options = NULL;
char *ttyname = NULL;
char *devname = NULL;
char *options;
char *s;
int idx;
/*
* console="" or console=null have been suggested as a way to
* disable console output. Use ttynull that has been created
* for exactly this purpose.
*/
if (str[0] == 0 || strcmp(str, "null") == 0) {
__add_preferred_console("ttynull", 0, NULL, NULL, NULL, true);
return 1;
}
if (_braille_console_setup(&str, &brl_options))
return 1;
/* For a DEVNAME:0.0 style console the character device is unknown early */
if (strchr(str, ':'))
devname = buf;
else
ttyname = buf;
/*
* Decode str into name, index, options.
*/
if (ttyname && isdigit(str[0]))
scnprintf(buf, sizeof(buf), "ttyS%s", str);
else
strscpy(buf, str);
options = strchr(str, ',');
if (options)
*(options++) = 0;
#ifdef __sparc__
if (!strcmp(str, "ttya"))
strscpy(buf, "ttyS0");
if (!strcmp(str, "ttyb"))
strscpy(buf, "ttyS1");
#endif
for (s = buf; *s; s++)
if ((ttyname && isdigit(*s)) || *s == ',')
break;
/* @idx will get defined when devname matches. */
if (devname)
idx = -1;
else
idx = simple_strtoul(s, NULL, 10);
*s = 0;
__add_preferred_console(ttyname, idx, devname, options, brl_options, true);
return 1;
}
__setup("console=", console_setup);
/**
* add_preferred_console - add a device to the list of preferred consoles.
* @name: device name
* @idx: device index
* @options: options for this console
*
* The last preferred console added will be used for kernel messages
* and stdin/out/err for init. Normally this is used by console_setup
* above to handle user-supplied console arguments; however it can also
* be used by arch-specific code either to override the user or more
* commonly to provide a default console (ie from PROM variables) when
* the user has not supplied one.
*/
int add_preferred_console(const char *name, const short idx, char *options)
{
return __add_preferred_console(name, idx, NULL, options, NULL, false);
}
/**
* match_devname_and_update_preferred_console - Update a preferred console
* when matching devname is found.
* @devname: DEVNAME:0.0 style device name
* @name: Name of the corresponding console driver, e.g. "ttyS"
* @idx: Console index, e.g. port number.
*
* The function checks whether a device with the given @devname is
* preferred via the console=DEVNAME:0.0 command line option.
* It fills the missing console driver name and console index
* so that a later register_console() call could find (match)
* and enable this device.
*
* It might be used when a driver subsystem initializes particular
* devices with already known DEVNAME:0.0 style names. And it
* could predict which console driver name and index this device
* would later get associated with.
*
* Return: 0 on success, negative error code on failure.
*/
int match_devname_and_update_preferred_console(const char *devname,
const char *name,
const short idx)
{
struct console_cmdline *c = console_cmdline;
int i;
if (!devname || !strlen(devname) || !name || !strlen(name) || idx < 0)
return -EINVAL;
for (i = 0; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]);
i++, c++) {
if (!strcmp(devname, c->devname)) {
pr_info("associate the preferred console \"%s\" with \"%s%d\"\n",
devname, name, idx);
strscpy(c->name, name);
c->index = idx;
return 0;
}
}
return -ENOENT;
}
EXPORT_SYMBOL_GPL(match_devname_and_update_preferred_console);
bool console_suspend_enabled = true;
EXPORT_SYMBOL(console_suspend_enabled);
static int __init console_suspend_disable(char *str)
{
console_suspend_enabled = false;
return 1;
}
__setup("no_console_suspend", console_suspend_disable);
module_param_named(console_suspend, console_suspend_enabled,
bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(console_suspend, "suspend console during suspend"
" and hibernate operations");
static bool printk_console_no_auto_verbose;
void console_verbose(void)
{
if (console_loglevel && !printk_console_no_auto_verbose)
console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
}
EXPORT_SYMBOL_GPL(console_verbose);
module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644);
MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc");
/**
* console_suspend_all - suspend the console subsystem
*
* This disables printk() while we go into suspend states
*/
void console_suspend_all(void)
{
struct console *con;
if (!console_suspend_enabled)
return;
pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
pr_flush(1000, true);
console_list_lock();
for_each_console(con)
console_srcu_write_flags(con, con->flags | CON_SUSPENDED);
console_list_unlock();
/*
* Ensure that all SRCU list walks have completed. All printing
* contexts must be able to see that they are suspended so that it
* is guaranteed that all printing has stopped when this function
* completes.
*/
synchronize_srcu(&console_srcu);
}
void console_resume_all(void)
{
struct console_flush_type ft;
struct console *con;
if (!console_suspend_enabled)
return;
console_list_lock();
for_each_console(con)
console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
console_list_unlock();
/*
* Ensure that all SRCU list walks have completed. All printing
* contexts must be able to see they are no longer suspended so
* that they are guaranteed to wake up and resume printing.
*/
synchronize_srcu(&console_srcu);
printk_get_console_flush_type(&ft);
if (ft.nbcon_offload)
nbcon_kthreads_wake();
if (ft.legacy_offload)
defer_console_output();
pr_flush(1000, true);
}
/**
* console_cpu_notify - print deferred console messages after CPU hotplug
* @cpu: unused
*
* If printk() is called from a CPU that is not online yet, the messages
* will be printed on the console only if there are CON_ANYTIME consoles.
* This function is called when a new CPU comes online (or fails to come
* up) or goes offline.
*/
static int console_cpu_notify(unsigned int cpu)
{
struct console_flush_type ft;
if (!cpuhp_tasks_frozen) {
printk_get_console_flush_type(&ft);
if (ft.nbcon_atomic)
nbcon_atomic_flush_pending();
if (ft.legacy_direct) {
if (console_trylock())
console_unlock();
}
}
return 0;
}
/**
* console_lock - block the console subsystem from printing
*
* Acquires a lock which guarantees that no consoles will
* be in or enter their write() callback.
*
* Can sleep, returns nothing.
*/
void console_lock(void)
{
might_sleep();
/* On panic, the console_lock must be left to the panic cpu. */
while (other_cpu_in_panic())
msleep(1000);
down_console_sem();
console_locked = 1;
console_may_schedule = 1;
}
EXPORT_SYMBOL(console_lock);
/**
* console_trylock - try to block the console subsystem from printing
*
* Try to acquire a lock which guarantees that no consoles will
* be in or enter their write() callback.
*
* returns 1 on success, and 0 on failure to acquire the lock.
*/
int console_trylock(void)
{
/* On panic, the console_lock must be left to the panic cpu. */
if (other_cpu_in_panic())
return 0;
if (down_trylock_console_sem())
return 0;
console_locked = 1;
console_may_schedule = 0;
return 1;
}
EXPORT_SYMBOL(console_trylock);
int is_console_locked(void)
{
return console_locked;
}
EXPORT_SYMBOL(is_console_locked);
static void __console_unlock(void)
{
console_locked = 0;
up_console_sem();
}
#ifdef CONFIG_PRINTK
/*
* Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting
* the existing message over and inserting the scratchbuf message.
*
* @pmsg is the original printk message.
* @fmt is the printf format of the message which will prepend the existing one.
*
* If there is not enough space in @pmsg->pbufs->outbuf, the existing
* message text will be sufficiently truncated.
*
* If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated.
*/
__printf(2, 3)
static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...)
{
struct printk_buffers *pbufs = pmsg->pbufs;
const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf);
const size_t outbuf_sz = sizeof(pbufs->outbuf);
char *scratchbuf = &pbufs->scratchbuf[0];
char *outbuf = &pbufs->outbuf[0];
va_list args;
size_t len;
va_start(args, fmt);
len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args);
va_end(args);
/*
* Make sure outbuf is sufficiently large before prepending.
* Keep at least the prefix when the message must be truncated.
* It is a rather theoretical problem when someone tries to
* use a minimalist buffer.
*/
if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz))
return;
if (pmsg->outbuf_len + len >= outbuf_sz) {
/* Truncate the message, but keep it terminated. */
pmsg->outbuf_len = outbuf_sz - (len + 1);
outbuf[pmsg->outbuf_len] = 0;
}
memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1);
memcpy(outbuf, scratchbuf, len);
pmsg->outbuf_len += len;
}
/*
* Prepend the message in @pmsg->pbufs->outbuf with a "dropped message".
* @pmsg->outbuf_len is updated appropriately.
*
* @pmsg is the printk message to prepend.
*
* @dropped is the dropped count to report in the dropped message.
*/
void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
{
console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped);
}
/*
* Prepend the message in @pmsg->pbufs->outbuf with a "replay message".
* @pmsg->outbuf_len is updated appropriately.
*
* @pmsg is the printk message to prepend.
*/
void console_prepend_replay(struct printk_message *pmsg)
{
console_prepend_message(pmsg, "** replaying previous printk message **\n");
}
/*
* Read and format the specified record (or a later record if the specified
* record is not available).
*
* @pmsg will contain the formatted result. @pmsg->pbufs must point to a
* struct printk_buffers.
*
* @seq is the record to read and format. If it is not available, the next
* valid record is read.
*
* @is_extended specifies if the message should be formatted for extended
* console output.
*
* @may_supress specifies if records may be skipped based on loglevel.
*
* Returns false if no record is available. Otherwise true and all fields
* of @pmsg are valid. (See the documentation of struct printk_message
* for information about the @pmsg fields.)
*/
bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
bool is_extended, bool may_suppress)
{
struct printk_buffers *pbufs = pmsg->pbufs;
const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf);
const size_t outbuf_sz = sizeof(pbufs->outbuf);
char *scratchbuf = &pbufs->scratchbuf[0];
char *outbuf = &pbufs->outbuf[0];
struct printk_info info;
struct printk_record r;
size_t len = 0;
bool force_con;
/*
* Formatting extended messages requires a separate buffer, so use the
* scratch buffer to read in the ringbuffer text.
*
* Formatting normal messages is done in-place, so read the ringbuffer
* text directly into the output buffer.
*/
if (is_extended)
prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz);
else
prb_rec_init_rd(&r, &info, outbuf, outbuf_sz);
if (!prb_read_valid(prb, seq, &r))
return false;
pmsg->seq = r.info->seq;
pmsg->dropped = r.info->seq - seq;
force_con = r.info->flags & LOG_FORCE_CON;
/*
* Skip records that are not forced to be printed on consoles and that
* has level above the console loglevel.
*/
if (!force_con && may_suppress && suppress_message_printing(r.info->level))
goto out;
if (is_extended) {
len = info_print_ext_header(outbuf, outbuf_sz, r.info);
len += msg_print_ext_body(outbuf + len, outbuf_sz - len,
&r.text_buf[0], r.info->text_len, &r.info->dev_info);
} else {
len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time);
}
out:
pmsg->outbuf_len = len;
return true;
}
/*
* Legacy console printing from printk() caller context does not respect
* raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a
* false positive. For PREEMPT_RT the false positive condition does not
* occur.
*
* This map is used to temporarily establish LD_WAIT_SLEEP context for the
* console write() callback when legacy printing to avoid false positive
* lockdep complaints, thus allowing lockdep to continue to function for
* real issues.
*/
#ifdef CONFIG_PREEMPT_RT
static inline void printk_legacy_allow_spinlock_enter(void) { }
static inline void printk_legacy_allow_spinlock_exit(void) { }
#else
static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP);
static inline void printk_legacy_allow_spinlock_enter(void)
{ lock_map_acquire_try(&printk_legacy_map);
}
static inline void printk_legacy_allow_spinlock_exit(void)
{ lock_map_release(&printk_legacy_map);
}
#endif /* CONFIG_PREEMPT_RT */
/*
* Used as the printk buffers for non-panic, serialized console printing.
* This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles.
* Its usage requires the console_lock held.
*/
struct printk_buffers printk_shared_pbufs;
/*
* Print one record for the given console. The record printed is whatever
* record is the next available record for the given console.
*
* @handover will be set to true if a printk waiter has taken over the
* console_lock, in which case the caller is no longer holding both the
* console_lock and the SRCU read lock. Otherwise it is set to false.
*
* @cookie is the cookie from the SRCU read lock.
*
* Returns false if the given console has no next record to print, otherwise
* true.
*
* Requires the console_lock and the SRCU read lock.
*/
static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
{
bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
char *outbuf = &printk_shared_pbufs.outbuf[0];
struct printk_message pmsg = {
.pbufs = &printk_shared_pbufs,
};
unsigned long flags;
*handover = false;
if (!printk_get_next_message(&pmsg, con->seq, is_extended, true))
return false;
con->dropped += pmsg.dropped;
/* Skip messages of formatted length 0. */
if (pmsg.outbuf_len == 0) {
con->seq = pmsg.seq + 1;
goto skip;
}
if (con->dropped && !is_extended) { console_prepend_dropped(&pmsg, con->dropped);
con->dropped = 0;
}
/* Write everything out to the hardware. */
if (force_legacy_kthread() && !panic_in_progress()) {
/*
* With forced threading this function is in a task context
* (either legacy kthread or get_init_console_seq()). There
* is no need for concern about printk reentrance, handovers,
* or lockdep complaints.
*/
con->write(con, outbuf, pmsg.outbuf_len);
con->seq = pmsg.seq + 1;
} else {
/*
* While actively printing out messages, if another printk()
* were to occur on another CPU, it may wait for this one to
* finish. This task can not be preempted if there is a
* waiter waiting to take over.
*
* Interrupts are disabled because the hand over to a waiter
* must not be interrupted until the hand over is completed
* (@console_waiter is cleared).
*/
printk_safe_enter_irqsave(flags);
console_lock_spinning_enable();
/* Do not trace print latency. */
stop_critical_timings();
printk_legacy_allow_spinlock_enter();
con->write(con, outbuf, pmsg.outbuf_len);
printk_legacy_allow_spinlock_exit();
start_critical_timings();
con->seq = pmsg.seq + 1;
*handover = console_lock_spinning_disable_and_check(cookie);
printk_safe_exit_irqrestore(flags);
}
skip:
return true;
}
#else
static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
{
*handover = false;
return false;
}
static inline void printk_kthreads_check_locked(void) { }
#endif /* CONFIG_PRINTK */
/*
* Print out all remaining records to all consoles.
*
* @do_cond_resched is set by the caller. It can be true only in schedulable
* context.
*
* @next_seq is set to the sequence number after the last available record.
* The value is valid only when this function returns true. It means that all
* usable consoles are completely flushed.
*
* @handover will be set to true if a printk waiter has taken over the
* console_lock, in which case the caller is no longer holding the
* console_lock. Otherwise it is set to false.
*
* Returns true when there was at least one usable console and all messages
* were flushed to all usable consoles. A returned false informs the caller
* that everything was not flushed (either there were no usable consoles or
* another context has taken over printing or it is a panic situation and this
* is not the panic CPU). Regardless the reason, the caller should assume it
* is not useful to immediately try again.
*
* Requires the console_lock.
*/
static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
{
struct console_flush_type ft;
bool any_usable = false;
struct console *con;
bool any_progress;
int cookie;
*next_seq = 0;
*handover = false;
do {
any_progress = false;
printk_get_console_flush_type(&ft);
cookie = console_srcu_read_lock();
for_each_console_srcu(con) { short flags = console_srcu_read_flags(con);
u64 printk_seq;
bool progress;
/*
* console_flush_all() is only responsible for nbcon
* consoles when the nbcon consoles cannot print via
* their atomic or threaded flushing.
*/
if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload))
continue;
if (!console_is_usable(con, flags, !do_cond_resched))
continue;
any_usable = true;
if (flags & CON_NBCON) {
progress = nbcon_legacy_emit_next_record(con, handover, cookie,
!do_cond_resched);
printk_seq = nbcon_seq_read(con);
} else {
progress = console_emit_next_record(con, handover, cookie);
printk_seq = con->seq;
}
/*
* If a handover has occurred, the SRCU read lock
* is already released.
*/
if (*handover)
return false;
/* Track the next of the highest seq flushed. */
if (printk_seq > *next_seq) *next_seq = printk_seq; if (!progress)
continue;
any_progress = true;
/* Allow panic_cpu to take over the consoles safely. */
if (other_cpu_in_panic())
goto abandon;
if (do_cond_resched)
cond_resched();
}
console_srcu_read_unlock(cookie); } while (any_progress);
return any_usable;
abandon:
console_srcu_read_unlock(cookie);
return false;
}
static void __console_flush_and_unlock(void)
{
bool do_cond_resched;
bool handover;
bool flushed;
u64 next_seq;
/*
* Console drivers are called with interrupts disabled, so
* @console_may_schedule should be cleared before; however, we may
* end up dumping a lot of lines, for example, if called from
* console registration path, and should invoke cond_resched()
* between lines if allowable. Not doing so can cause a very long
* scheduling stall on a slow console leading to RCU stall and
* softlockup warnings which exacerbate the issue with more
* messages practically incapacitating the system. Therefore, create
* a local to use for the printing loop.
*/
do_cond_resched = console_may_schedule;
do {
console_may_schedule = 0;
flushed = console_flush_all(do_cond_resched, &next_seq, &handover);
if (!handover) __console_unlock();
/*
* Abort if there was a failure to flush all messages to all
* usable consoles. Either it is not possible to flush (in
* which case it would be an infinite loop of retrying) or
* another context has taken over printing.
*/
if (!flushed)
break;
/*
* Some context may have added new records after
* console_flush_all() but before unlocking the console.
* Re-check if there is a new record to flush. If the trylock
* fails, another context is already handling the printing.
*/
} while (prb_read_valid(prb, next_seq, NULL) && console_trylock());
}
/**
* console_unlock - unblock the legacy console subsystem from printing
*
* Releases the console_lock which the caller holds to block printing of
* the legacy console subsystem.
*
* While the console_lock was held, console output may have been buffered
* by printk(). If this is the case, console_unlock() emits the output on
* legacy consoles prior to releasing the lock.
*
* console_unlock(); may be called from any context.
*/
void console_unlock(void)
{
struct console_flush_type ft;
printk_get_console_flush_type(&ft);
if (ft.legacy_direct)
__console_flush_and_unlock();
else
__console_unlock();
}
EXPORT_SYMBOL(console_unlock);
/**
* console_conditional_schedule - yield the CPU if required
*
* If the console code is currently allowed to sleep, and
* if this CPU should yield the CPU to another task, do
* so here.
*
* Must be called within console_lock();.
*/
void __sched console_conditional_schedule(void)
{
if (console_may_schedule)
cond_resched();
}
EXPORT_SYMBOL(console_conditional_schedule);
void console_unblank(void)
{
bool found_unblank = false;
struct console *c;
int cookie;
/*
* First check if there are any consoles implementing the unblank()
* callback. If not, there is no reason to continue and take the
* console lock, which in particular can be dangerous if
* @oops_in_progress is set.
*/
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
short flags = console_srcu_read_flags(c);
if (flags & CON_SUSPENDED)
continue;
if ((flags & CON_ENABLED) && c->unblank) {
found_unblank = true;
break;
}
}
console_srcu_read_unlock(cookie);
if (!found_unblank)
return;
/*
* Stop console printing because the unblank() callback may
* assume the console is not within its write() callback.
*
* If @oops_in_progress is set, this may be an atomic context.
* In that case, attempt a trylock as best-effort.
*/
if (oops_in_progress) {
/* Semaphores are not NMI-safe. */
if (in_nmi())
return;
/*
* Attempting to trylock the console lock can deadlock
* if another CPU was stopped while modifying the
* semaphore. "Hope and pray" that this is not the
* current situation.
*/
if (down_trylock_console_sem() != 0)
return;
} else
console_lock();
console_locked = 1;
console_may_schedule = 0;
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
short flags = console_srcu_read_flags(c);
if (flags & CON_SUSPENDED)
continue;
if ((flags & CON_ENABLED) && c->unblank)
c->unblank();
}
console_srcu_read_unlock(cookie);
console_unlock();
if (!oops_in_progress)
pr_flush(1000, true);
}
/*
* Rewind all consoles to the oldest available record.
*
* IMPORTANT: The function is safe only when called under
* console_lock(). It is not enforced because
* it is used as a best effort in panic().
*/
static void __console_rewind_all(void)
{
struct console *c;
short flags;
int cookie;
u64 seq;
seq = prb_first_valid_seq(prb);
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
flags = console_srcu_read_flags(c);
if (flags & CON_NBCON) {
nbcon_seq_force(c, seq);
} else {
/*
* This assignment is safe only when called under
* console_lock(). On panic, legacy consoles are
* only best effort.
*/
c->seq = seq;
}
}
console_srcu_read_unlock(cookie);
}
/**
* console_flush_on_panic - flush console content on panic
* @mode: flush all messages in buffer or just the pending ones
*
* Immediately output all pending messages no matter what.
*/
void console_flush_on_panic(enum con_flush_mode mode)
{
struct console_flush_type ft;
bool handover;
u64 next_seq;
/*
* Ignore the console lock and flush out the messages. Attempting a
* trylock would not be useful because:
*
* - if it is contended, it must be ignored anyway
* - console_lock() and console_trylock() block and fail
* respectively in panic for non-panic CPUs
* - semaphores are not NMI-safe
*/
/*
* If another context is holding the console lock,
* @console_may_schedule might be set. Clear it so that
* this context does not call cond_resched() while flushing.
*/
console_may_schedule = 0;
if (mode == CONSOLE_REPLAY_ALL)
__console_rewind_all();
printk_get_console_flush_type(&ft);
if (ft.nbcon_atomic)
nbcon_atomic_flush_pending();
/* Flush legacy consoles once allowed, even when dangerous. */
if (legacy_allow_panic_sync)
console_flush_all(false, &next_seq, &handover);
}
/*
* Return the console tty driver structure and its associated index
*/
struct tty_driver *console_device(int *index)
{
struct console *c;
struct tty_driver *driver = NULL;
int cookie;
/*
* Take console_lock to serialize device() callback with
* other console operations. For example, fg_console is
* modified under console_lock when switching vt.
*/
console_lock();
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
if (!c->device)
continue;
driver = c->device(c, index);
if (driver)
break;
}
console_srcu_read_unlock(cookie);
console_unlock();
return driver;
}
/*
* Prevent further output on the passed console device so that (for example)
* serial drivers can suspend console output before suspending a port, and can
* re-enable output afterwards.
*/
void console_suspend(struct console *console)
{
__pr_flush(console, 1000, true);
console_list_lock();
console_srcu_write_flags(console, console->flags & ~CON_ENABLED);
console_list_unlock();
/*
* Ensure that all SRCU list walks have completed. All contexts must
* be able to see that this console is disabled so that (for example)
* the caller can suspend the port without risk of another context
* using the port.
*/
synchronize_srcu(&console_srcu);
}
EXPORT_SYMBOL(console_suspend);
void console_resume(struct console *console)
{
struct console_flush_type ft;
bool is_nbcon;
console_list_lock();
console_srcu_write_flags(console, console->flags | CON_ENABLED);
is_nbcon = console->flags & CON_NBCON;
console_list_unlock();
/*
* Ensure that all SRCU list walks have completed. The related
* printing context must be able to see it is enabled so that
* it is guaranteed to wake up and resume printing.
*/
synchronize_srcu(&console_srcu);
printk_get_console_flush_type(&ft);
if (is_nbcon && ft.nbcon_offload)
nbcon_kthread_wake(console);
else if (ft.legacy_offload)
defer_console_output();
__pr_flush(console, 1000, true);
}
EXPORT_SYMBOL(console_resume);
#ifdef CONFIG_PRINTK
static int unregister_console_locked(struct console *console);
/* True when system boot is far enough to create printer threads. */
static bool printk_kthreads_ready __ro_after_init;
static struct task_struct *printk_legacy_kthread;
static bool legacy_kthread_should_wakeup(void)
{
struct console_flush_type ft;
struct console *con;
bool ret = false;
int cookie;
if (kthread_should_stop())
return true;
printk_get_console_flush_type(&ft);
cookie = console_srcu_read_lock();
for_each_console_srcu(con) {
short flags = console_srcu_read_flags(con);
u64 printk_seq;
/*
* The legacy printer thread is only responsible for nbcon
* consoles when the nbcon consoles cannot print via their
* atomic or threaded flushing.
*/
if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload))
continue;
if (!console_is_usable(con, flags, false))
continue;
if (flags & CON_NBCON) {
printk_seq = nbcon_seq_read(con);
} else {
/*
* It is safe to read @seq because only this
* thread context updates @seq.
*/
printk_seq = con->seq;
}
if (prb_read_valid(prb, printk_seq, NULL)) {
ret = true;
break;
}
}
console_srcu_read_unlock(cookie);
return ret;
}
static int legacy_kthread_func(void *unused)
{
for (;;) {
wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup());
if (kthread_should_stop())
break;
console_lock();
__console_flush_and_unlock();
}
return 0;
}
static bool legacy_kthread_create(void)
{
struct task_struct *kt;
lockdep_assert_console_list_lock_held();
kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy");
if (WARN_ON(IS_ERR(kt))) {
pr_err("failed to start legacy printing thread\n");
return false;
}
printk_legacy_kthread = kt;
/*
* It is important that console printing threads are scheduled
* shortly after a printk call and with generous runtime budgets.
*/
sched_set_normal(printk_legacy_kthread, -20);
return true;
}
/**
* printk_kthreads_shutdown - shutdown all threaded printers
*
* On system shutdown all threaded printers are stopped. This allows printk
* to transition back to atomic printing, thus providing a robust mechanism
* for the final shutdown/reboot messages to be output.
*/
static void printk_kthreads_shutdown(void)
{
struct console *con;
console_list_lock();
if (printk_kthreads_running) {
printk_kthreads_running = false;
for_each_console(con) {
if (con->flags & CON_NBCON)
nbcon_kthread_stop(con);
}
/*
* The threads may have been stopped while printing a
* backlog. Flush any records left over.
*/
nbcon_atomic_flush_pending();
}
console_list_unlock();
}
static struct syscore_ops printk_syscore_ops = {
.shutdown = printk_kthreads_shutdown,
};
/*
* If appropriate, start nbcon kthreads and set @printk_kthreads_running.
* If any kthreads fail to start, those consoles are unregistered.
*
* Must be called under console_list_lock().
*/
static void printk_kthreads_check_locked(void)
{
struct hlist_node *tmp;
struct console *con;
lockdep_assert_console_list_lock_held();
if (!printk_kthreads_ready)
return;
if (have_legacy_console || have_boot_console) {
if (!printk_legacy_kthread &&
force_legacy_kthread() &&
!legacy_kthread_create()) {
/*
* All legacy consoles must be unregistered. If there
* are any nbcon consoles, they will set up their own
* kthread.
*/
hlist_for_each_entry_safe(con, tmp, &console_list, node) {
if (con->flags & CON_NBCON)
continue;
unregister_console_locked(con);
}
}
} else if (printk_legacy_kthread) {
kthread_stop(printk_legacy_kthread);
printk_legacy_kthread = NULL;
}
/*
* Printer threads cannot be started as long as any boot console is
* registered because there is no way to synchronize the hardware
* registers between boot console code and regular console code.
* It can only be known that there will be no new boot consoles when
* an nbcon console is registered.
*/
if (have_boot_console || !have_nbcon_console) {
/* Clear flag in case all nbcon consoles unregistered. */
printk_kthreads_running = false;
return;
}
if (printk_kthreads_running)
return;
hlist_for_each_entry_safe(con, tmp, &console_list, node) {
if (!(con->flags & CON_NBCON))
continue;
if (!nbcon_kthread_create(con))
unregister_console_locked(con);
}
printk_kthreads_running = true;
}
static int __init printk_set_kthreads_ready(void)
{
register_syscore_ops(&printk_syscore_ops);
console_list_lock();
printk_kthreads_ready = true;
printk_kthreads_check_locked();
console_list_unlock();
return 0;
}
early_initcall(printk_set_kthreads_ready);
#endif /* CONFIG_PRINTK */
static int __read_mostly keep_bootcon;
static int __init keep_bootcon_setup(char *str)
{
keep_bootcon = 1;
pr_info("debug: skip boot console de-registration.\n");
return 0;
}
early_param("keep_bootcon", keep_bootcon_setup);
static int console_call_setup(struct console *newcon, char *options)
{
int err;
if (!newcon->setup)
return 0;
/* Synchronize with possible boot console. */
console_lock();
err = newcon->setup(newcon, options);
console_unlock();
return err;
}
/*
* This is called by register_console() to try to match
* the newly registered console with any of the ones selected
* by either the command line or add_preferred_console() and
* setup/enable it.
*
* Care need to be taken with consoles that are statically
* enabled such as netconsole
*/
static int try_enable_preferred_console(struct console *newcon,
bool user_specified)
{
struct console_cmdline *c;
int i, err;
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]);
i++, c++) {
/* Console not yet initialized? */
if (!c->name[0])
continue;
if (c->user_specified != user_specified)
continue;
if (!newcon->match ||
newcon->match(newcon, c->name, c->index, c->options) != 0) {
/* default matching */
BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
if (strcmp(c->name, newcon->name) != 0)
continue;
if (newcon->index >= 0 &&
newcon->index != c->index)
continue;
if (newcon->index < 0)
newcon->index = c->index;
if (_braille_register_console(newcon, c))
return 0;
err = console_call_setup(newcon, c->options);
if (err)
return err;
}
newcon->flags |= CON_ENABLED;
if (i == preferred_console)
newcon->flags |= CON_CONSDEV;
return 0;
}
/*
* Some consoles, such as pstore and netconsole, can be enabled even
* without matching. Accept the pre-enabled consoles only when match()
* and setup() had a chance to be called.
*/
if (newcon->flags & CON_ENABLED && c->user_specified == user_specified)
return 0;
return -ENOENT;
}
/* Try to enable the console unconditionally */
static void try_enable_default_console(struct console *newcon)
{
if (newcon->index < 0)
newcon->index = 0;
if (console_call_setup(newcon, NULL) != 0)
return;
newcon->flags |= CON_ENABLED;
if (newcon->device)
newcon->flags |= CON_CONSDEV;
}
/* Return the starting sequence number for a newly registered console. */
static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered)
{
struct console *con;
bool handover;
u64 init_seq;
if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) {
/* Get a consistent copy of @syslog_seq. */
mutex_lock(&syslog_lock);
init_seq = syslog_seq;
mutex_unlock(&syslog_lock);
} else {
/* Begin with next message added to ringbuffer. */
init_seq = prb_next_seq(prb);
/*
* If any enabled boot consoles are due to be unregistered
* shortly, some may not be caught up and may be the same
* device as @newcon. Since it is not known which boot console
* is the same device, flush all consoles and, if necessary,
* start with the message of the enabled boot console that is
* the furthest behind.
*/
if (bootcon_registered && !keep_bootcon) {
/*
* Hold the console_lock to stop console printing and
* guarantee safe access to console->seq.
*/
console_lock();
/*
* Flush all consoles and set the console to start at
* the next unprinted sequence number.
*/
if (!console_flush_all(true, &init_seq, &handover)) {
/*
* Flushing failed. Just choose the lowest
* sequence of the enabled boot consoles.
*/
/*
* If there was a handover, this context no
* longer holds the console_lock.
*/
if (handover)
console_lock();
init_seq = prb_next_seq(prb);
for_each_console(con) {
u64 seq;
if (!(con->flags & CON_BOOT) ||
!(con->flags & CON_ENABLED)) {
continue;
}
if (con->flags & CON_NBCON)
seq = nbcon_seq_read(con);
else
seq = con->seq;
if (seq < init_seq)
init_seq = seq;
}
}
console_unlock();
}
}
return init_seq;
}
#define console_first() \
hlist_entry(console_list.first, struct console, node)
static int unregister_console_locked(struct console *console);
/*
* The console driver calls this routine during kernel initialization
* to register the console printing procedure with printk() and to
* print any messages that were printed by the kernel before the
* console driver was initialized.
*
* This can happen pretty early during the boot process (because of
* early_printk) - sometimes before setup_arch() completes - be careful
* of what kernel features are used - they may not be initialised yet.
*
* There are two types of consoles - bootconsoles (early_printk) and
* "real" consoles (everything which is not a bootconsole) which are
* handled differently.
* - Any number of bootconsoles can be registered at any time.
* - As soon as a "real" console is registered, all bootconsoles
* will be unregistered automatically.
* - Once a "real" console is registered, any attempt to register a
* bootconsoles will be rejected
*/
void register_console(struct console *newcon)
{
bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic;
bool bootcon_registered = false;
bool realcon_registered = false;
struct console *con;
unsigned long flags;
u64 init_seq;
int err;
console_list_lock();
for_each_console(con) {
if (WARN(con == newcon, "console '%s%d' already registered\n",
con->name, con->index)) {
goto unlock;
}
if (con->flags & CON_BOOT)
bootcon_registered = true;
else
realcon_registered = true;
}
/* Do not register boot consoles when there already is a real one. */
if ((newcon->flags & CON_BOOT) && realcon_registered) {
pr_info("Too late to register bootconsole %s%d\n",
newcon->name, newcon->index);
goto unlock;
}
if (newcon->flags & CON_NBCON) {
/*
* Ensure the nbcon console buffers can be allocated
* before modifying any global data.
*/
if (!nbcon_alloc(newcon))
goto unlock;
}
/*
* See if we want to enable this console driver by default.
*
* Nope when a console is preferred by the command line, device
* tree, or SPCR.
*
* The first real console with tty binding (driver) wins. More
* consoles might get enabled before the right one is found.
*
* Note that a console with tty binding will have CON_CONSDEV
* flag set and will be first in the list.
*/
if (preferred_console < 0) {
if (hlist_empty(&console_list) || !console_first()->device ||
console_first()->flags & CON_BOOT) {
try_enable_default_console(newcon);
}
}
/* See if this console matches one we selected on the command line */
err = try_enable_preferred_console(newcon, true);
/* If not, try to match against the platform default(s) */
if (err == -ENOENT)
err = try_enable_preferred_console(newcon, false);
/* printk() messages are not printed to the Braille console. */
if (err || newcon->flags & CON_BRL) {
if (newcon->flags & CON_NBCON)
nbcon_free(newcon);
goto unlock;
}
/*
* If we have a bootconsole, and are switching to a real console,
* don't print everything out again, since when the boot console, and
* the real console are the same physical device, it's annoying to
* see the beginning boot messages twice
*/
if (bootcon_registered &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) {
newcon->flags &= ~CON_PRINTBUFFER;
}
newcon->dropped = 0;
init_seq = get_init_console_seq(newcon, bootcon_registered);
if (newcon->flags & CON_NBCON) {
have_nbcon_console = true;
nbcon_seq_force(newcon, init_seq);
} else {
have_legacy_console = true;
newcon->seq = init_seq;
}
if (newcon->flags & CON_BOOT)
have_boot_console = true;
/*
* If another context is actively using the hardware of this new
* console, it will not be aware of the nbcon synchronization. This
* is a risk that two contexts could access the hardware
* simultaneously if this new console is used for atomic printing
* and the other context is still using the hardware.
*
* Use the driver synchronization to ensure that the hardware is not
* in use while this new console transitions to being registered.
*/
if (use_device_lock)
newcon->device_lock(newcon, &flags);
/*
* Put this console in the list - keep the
* preferred driver at the head of the list.
*/
if (hlist_empty(&console_list)) {
/* Ensure CON_CONSDEV is always set for the head. */
newcon->flags |= CON_CONSDEV;
hlist_add_head_rcu(&newcon->node, &console_list);
} else if (newcon->flags & CON_CONSDEV) {
/* Only the new head can have CON_CONSDEV set. */
console_srcu_write_flags(console_first(), console_first()->flags & ~CON_CONSDEV);
hlist_add_head_rcu(&newcon->node, &console_list);
} else {
hlist_add_behind_rcu(&newcon->node, console_list.first);
}
/*
* No need to synchronize SRCU here! The caller does not rely
* on all contexts being able to see the new console before
* register_console() completes.
*/
/* This new console is now registered. */
if (use_device_lock)
newcon->device_unlock(newcon, flags);
console_sysfs_notify();
/*
* By unregistering the bootconsoles after we enable the real console
* we get the "console xxx enabled" message on all the consoles -
* boot consoles, real consoles, etc - this is to ensure that end
* users know there might be something in the kernel's log buffer that
* went to the bootconsole (that they do not see on the real console)
*/
con_printk(KERN_INFO, newcon, "enabled\n");
if (bootcon_registered &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
!keep_bootcon) {
struct hlist_node *tmp;
hlist_for_each_entry_safe(con, tmp, &console_list, node) {
if (con->flags & CON_BOOT)
unregister_console_locked(con);
}
}
/* Changed console list, may require printer threads to start/stop. */
printk_kthreads_check_locked();
unlock:
console_list_unlock();
}
EXPORT_SYMBOL(register_console);
/* Must be called under console_list_lock(). */
static int unregister_console_locked(struct console *console)
{
bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic;
bool found_legacy_con = false;
bool found_nbcon_con = false;
bool found_boot_con = false;
unsigned long flags;
struct console *c;
int res;
lockdep_assert_console_list_lock_held();
con_printk(KERN_INFO, console, "disabled\n");
res = _braille_unregister_console(console);
if (res < 0)
return res;
if (res > 0)
return 0;
if (!console_is_registered_locked(console))
res = -ENODEV;
else if (console_is_usable(console, console->flags, true))
__pr_flush(console, 1000, true);
/* Disable it unconditionally */
console_srcu_write_flags(console, console->flags & ~CON_ENABLED);
if (res < 0)
return res;
/*
* Use the driver synchronization to ensure that the hardware is not
* in use while this console transitions to being unregistered.
*/
if (use_device_lock)
console->device_lock(console, &flags);
hlist_del_init_rcu(&console->node);
if (use_device_lock)
console->device_unlock(console, flags);
/*
* <HISTORICAL>
* If this isn't the last console and it has CON_CONSDEV set, we
* need to set it on the next preferred console.
* </HISTORICAL>
*
* The above makes no sense as there is no guarantee that the next
* console has any device attached. Oh well....
*/
if (!hlist_empty(&console_list) && console->flags & CON_CONSDEV)
console_srcu_write_flags(console_first(), console_first()->flags | CON_CONSDEV);
/*
* Ensure that all SRCU list walks have completed. All contexts
* must not be able to see this console in the list so that any
* exit/cleanup routines can be performed safely.
*/
synchronize_srcu(&console_srcu);
if (console->flags & CON_NBCON)
nbcon_free(console);
console_sysfs_notify();
if (console->exit)
res = console->exit(console);
/*
* With this console gone, the global flags tracking registered
* console types may have changed. Update them.
*/
for_each_console(c) {
if (c->flags & CON_BOOT)
found_boot_con = true;
if (c->flags & CON_NBCON)
found_nbcon_con = true;
else
found_legacy_con = true;
}
if (!found_boot_con)
have_boot_console = found_boot_con;
if (!found_legacy_con)
have_legacy_console = found_legacy_con;
if (!found_nbcon_con)
have_nbcon_console = found_nbcon_con;
/* Changed console list, may require printer threads to start/stop. */
printk_kthreads_check_locked();
return res;
}
int unregister_console(struct console *console)
{
int res;
console_list_lock();
res = unregister_console_locked(console);
console_list_unlock();
return res;
}
EXPORT_SYMBOL(unregister_console);
/**
* console_force_preferred_locked - force a registered console preferred
* @con: The registered console to force preferred.
*
* Must be called under console_list_lock().
*/
void console_force_preferred_locked(struct console *con)
{
struct console *cur_pref_con;
if (!console_is_registered_locked(con))
return;
cur_pref_con = console_first();
/* Already preferred? */
if (cur_pref_con == con)
return;
/*
* Delete, but do not re-initialize the entry. This allows the console
* to continue to appear registered (via any hlist_unhashed_lockless()
* checks), even though it was briefly removed from the console list.
*/
hlist_del_rcu(&con->node);
/*
* Ensure that all SRCU list walks have completed so that the console
* can be added to the beginning of the console list and its forward
* list pointer can be re-initialized.
*/
synchronize_srcu(&console_srcu);
con->flags |= CON_CONSDEV;
WARN_ON(!con->device);
/* Only the new head can have CON_CONSDEV set. */
console_srcu_write_flags(cur_pref_con, cur_pref_con->flags & ~CON_CONSDEV);
hlist_add_head_rcu(&con->node, &console_list);
}
EXPORT_SYMBOL(console_force_preferred_locked);
/*
* Initialize the console device. This is called *early*, so
* we can't necessarily depend on lots of kernel help here.
* Just do some early initializations, and do the complex setup
* later.
*/
void __init console_init(void)
{
int ret;
initcall_t call;
initcall_entry_t *ce;
#ifdef CONFIG_NULL_TTY_DEFAULT_CONSOLE
if (!console_set_on_cmdline)
add_preferred_console("ttynull", 0, NULL);
#endif
/* Setup the default TTY line discipline. */
n_tty_init();
/*
* set up the console device so that later boot sequences can
* inform about problems etc..
*/
ce = __con_initcall_start;
trace_initcall_level("console");
while (ce < __con_initcall_end) {
call = initcall_from_entry(ce);
trace_initcall_start(call);
ret = call();
trace_initcall_finish(call, ret);
ce++;
}
}
/*
* Some boot consoles access data that is in the init section and which will
* be discarded after the initcalls have been run. To make sure that no code
* will access this data, unregister the boot consoles in a late initcall.
*
* If for some reason, such as deferred probe or the driver being a loadable
* module, the real console hasn't registered yet at this point, there will
* be a brief interval in which no messages are logged to the console, which
* makes it difficult to diagnose problems that occur during this time.
*
* To mitigate this problem somewhat, only unregister consoles whose memory
* intersects with the init section. Note that all other boot consoles will
* get unregistered when the real preferred console is registered.
*/
static int __init printk_late_init(void)
{
struct hlist_node *tmp;
struct console *con;
int ret;
console_list_lock();
hlist_for_each_entry_safe(con, tmp, &console_list, node) {
if (!(con->flags & CON_BOOT))
continue;
/* Check addresses that might be used for enabled consoles. */
if (init_section_intersects(con, sizeof(*con)) ||
init_section_contains(con->write, 0) ||
init_section_contains(con->read, 0) ||
init_section_contains(con->device, 0) ||
init_section_contains(con->unblank, 0) ||
init_section_contains(con->data, 0)) {
/*
* Please, consider moving the reported consoles out
* of the init section.
*/
pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n",
con->name, con->index);
unregister_console_locked(con);
}
}
console_list_unlock();
ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL,
console_cpu_notify);
WARN_ON(ret < 0);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online",
console_cpu_notify, NULL);
WARN_ON(ret < 0);
printk_sysctl_init();
return 0;
}
late_initcall(printk_late_init);
#if defined CONFIG_PRINTK
/* If @con is specified, only wait for that console. Otherwise wait for all. */
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
{
unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms);
unsigned long remaining_jiffies = timeout_jiffies;
struct console_flush_type ft;
struct console *c;
u64 last_diff = 0;
u64 printk_seq;
short flags;
int cookie;
u64 diff;
u64 seq;
/* Sorry, pr_flush() will not work this early. */
if (system_state < SYSTEM_SCHEDULING)
return false;
might_sleep();
seq = prb_next_reserve_seq(prb);
/* Flush the consoles so that records up to @seq are printed. */
printk_get_console_flush_type(&ft);
if (ft.nbcon_atomic)
nbcon_atomic_flush_pending();
if (ft.legacy_direct) {
console_lock();
console_unlock();
}
for (;;) {
unsigned long begin_jiffies;
unsigned long slept_jiffies;
diff = 0;
/*
* Hold the console_lock to guarantee safe access to
* console->seq. Releasing console_lock flushes more
* records in case @seq is still not printed on all
* usable consoles.
*
* Holding the console_lock is not necessary if there
* are no legacy or boot consoles. However, such a
* console could register at any time. Always hold the
* console_lock as a precaution rather than
* synchronizing against register_console().
*/
console_lock();
cookie = console_srcu_read_lock();
for_each_console_srcu(c) {
if (con && con != c)
continue;
flags = console_srcu_read_flags(c);
/*
* If consoles are not usable, it cannot be expected
* that they make forward progress, so only increment
* @diff for usable consoles.
*/
if (!console_is_usable(c, flags, true) &&
!console_is_usable(c, flags, false)) {
continue;
}
if (flags & CON_NBCON) {
printk_seq = nbcon_seq_read(c);
} else {
printk_seq = c->seq;
}
if (printk_seq < seq)
diff += seq - printk_seq;
}
console_srcu_read_unlock(cookie);
if (diff != last_diff && reset_on_progress)
remaining_jiffies = timeout_jiffies;
console_unlock();
/* Note: @diff is 0 if there are no usable consoles. */
if (diff == 0 || remaining_jiffies == 0)
break;
/* msleep(1) might sleep much longer. Check time by jiffies. */
begin_jiffies = jiffies;
msleep(1);
slept_jiffies = jiffies - begin_jiffies;
remaining_jiffies -= min(slept_jiffies, remaining_jiffies);
last_diff = diff;
}
return (diff == 0);
}
/**
* pr_flush() - Wait for printing threads to catch up.
*
* @timeout_ms: The maximum time (in ms) to wait.
* @reset_on_progress: Reset the timeout if forward progress is seen.
*
* A value of 0 for @timeout_ms means no waiting will occur. A value of -1
* represents infinite waiting.
*
* If @reset_on_progress is true, the timeout will be reset whenever any
* printer has been seen to make some forward progress.
*
* Context: Process context. May sleep while acquiring console lock.
* Return: true if all usable printers are caught up.
*/
bool pr_flush(int timeout_ms, bool reset_on_progress)
{
return __pr_flush(NULL, timeout_ms, reset_on_progress);
}
/*
* Delayed printk version, for scheduler-internal messages:
*/
#define PRINTK_PENDING_WAKEUP 0x01
#define PRINTK_PENDING_OUTPUT 0x02
static DEFINE_PER_CPU(int, printk_pending);
static void wake_up_klogd_work_func(struct irq_work *irq_work)
{
int pending = this_cpu_xchg(printk_pending, 0);
if (pending & PRINTK_PENDING_OUTPUT) {
if (force_legacy_kthread()) {
if (printk_legacy_kthread)
wake_up_interruptible(&legacy_wait);
} else {
if (console_trylock())
console_unlock();
}
}
if (pending & PRINTK_PENDING_WAKEUP)
wake_up_interruptible(&log_wait);
}
static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) =
IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func);
static void __wake_up_klogd(int val)
{ if (!printk_percpu_data_ready())
return;
preempt_disable();
/*
* Guarantee any new records can be seen by tasks preparing to wait
* before this context checks if the wait queue is empty.
*
* The full memory barrier within wq_has_sleeper() pairs with the full
* memory barrier within set_current_state() of
* prepare_to_wait_event(), which is called after ___wait_event() adds
* the waiter but before it has checked the wait condition.
*
* This pairs with devkmsg_read:A and syslog_print:A.
*/
if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */
(val & PRINTK_PENDING_OUTPUT)) {
this_cpu_or(printk_pending, val);
irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
}
preempt_enable();
}
/**
* wake_up_klogd - Wake kernel logging daemon
*
* Use this function when new records have been added to the ringbuffer
* and the console printing of those records has already occurred or is
* known to be handled by some other context. This function will only
* wake the logging daemon.
*
* Context: Any context.
*/
void wake_up_klogd(void)
{
__wake_up_klogd(PRINTK_PENDING_WAKEUP);
}
/**
* defer_console_output - Wake kernel logging daemon and trigger
* console printing in a deferred context
*
* Use this function when new records have been added to the ringbuffer,
* this context is responsible for console printing those records, but
* the current context is not allowed to perform the console printing.
* Trigger an irq_work context to perform the console printing. This
* function also wakes the logging daemon.
*
* Context: Any context.
*/
void defer_console_output(void)
{
/*
* New messages may have been added directly to the ringbuffer
* using vprintk_store(), so wake any waiters as well.
*/
__wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT);
}
void printk_trigger_flush(void)
{
defer_console_output();
}
int vprintk_deferred(const char *fmt, va_list args)
{
return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
}
int _printk_deferred(const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = vprintk_deferred(fmt, args);
va_end(args);
return r;
}
/*
* printk rate limiting, lifted from the networking subsystem.
*
* This enforces a rate limit: not more than 10 kernel messages
* every 5s to make a denial-of-service attack impossible.
*/
DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
int __printk_ratelimit(const char *func)
{
return ___ratelimit(&printk_ratelimit_state, func);
}
EXPORT_SYMBOL(__printk_ratelimit);
/**
* printk_timed_ratelimit - caller-controlled printk ratelimiting
* @caller_jiffies: pointer to caller's state
* @interval_msecs: minimum interval between prints
*
* printk_timed_ratelimit() returns true if more than @interval_msecs
* milliseconds have elapsed since the last time printk_timed_ratelimit()
* returned true.
*/
bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msecs)
{
unsigned long elapsed = jiffies - *caller_jiffies;
if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs))
return false;
*caller_jiffies = jiffies;
return true;
}
EXPORT_SYMBOL(printk_timed_ratelimit);
static DEFINE_SPINLOCK(dump_list_lock);
static LIST_HEAD(dump_list);
/**
* kmsg_dump_register - register a kernel log dumper.
* @dumper: pointer to the kmsg_dumper structure
*
* Adds a kernel log dumper to the system. The dump callback in the
* structure will be called when the kernel oopses or panics and must be
* set. Returns zero on success and %-EINVAL or %-EBUSY otherwise.
*/
int kmsg_dump_register(struct kmsg_dumper *dumper)
{
unsigned long flags;
int err = -EBUSY;
/* The dump callback needs to be set */
if (!dumper->dump)
return -EINVAL;
spin_lock_irqsave(&dump_list_lock, flags);
/* Don't allow registering multiple times */
if (!dumper->registered) {
dumper->registered = 1;
list_add_tail_rcu(&dumper->list, &dump_list);
err = 0;
}
spin_unlock_irqrestore(&dump_list_lock, flags);
return err;
}
EXPORT_SYMBOL_GPL(kmsg_dump_register);
/**
* kmsg_dump_unregister - unregister a kmsg dumper.
* @dumper: pointer to the kmsg_dumper structure
*
* Removes a dump device from the system. Returns zero on success and
* %-EINVAL otherwise.
*/
int kmsg_dump_unregister(struct kmsg_dumper *dumper)
{
unsigned long flags;
int err = -EINVAL;
spin_lock_irqsave(&dump_list_lock, flags);
if (dumper->registered) {
dumper->registered = 0;
list_del_rcu(&dumper->list);
err = 0;
}
spin_unlock_irqrestore(&dump_list_lock, flags);
synchronize_rcu();
return err;
}
EXPORT_SYMBOL_GPL(kmsg_dump_unregister);
static bool always_kmsg_dump;
module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
{
switch (reason) {
case KMSG_DUMP_PANIC:
return "Panic";
case KMSG_DUMP_OOPS:
return "Oops";
case KMSG_DUMP_EMERG:
return "Emergency";
case KMSG_DUMP_SHUTDOWN:
return "Shutdown";
default:
return "Unknown";
}
}
EXPORT_SYMBOL_GPL(kmsg_dump_reason_str);
/**
* kmsg_dump_desc - dump kernel log to kernel message dumpers.
* @reason: the reason (oops, panic etc) for dumping
* @desc: a short string to describe what caused the panic or oops. Can be NULL
* if no additional description is available.
*
* Call each of the registered dumper's dump() callback, which can
* retrieve the kmsg records with kmsg_dump_get_line() or
* kmsg_dump_get_buffer().
*/
void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc)
{
struct kmsg_dumper *dumper;
struct kmsg_dump_detail detail = {
.reason = reason,
.description = desc};
rcu_read_lock();
list_for_each_entry_rcu(dumper, &dump_list, list) {
enum kmsg_dump_reason max_reason = dumper->max_reason;
/*
* If client has not provided a specific max_reason, default
* to KMSG_DUMP_OOPS, unless always_kmsg_dump was set.
*/
if (max_reason == KMSG_DUMP_UNDEF) {
max_reason = always_kmsg_dump ? KMSG_DUMP_MAX :
KMSG_DUMP_OOPS;
}
if (reason > max_reason)
continue;
/* invoke dumper which will iterate over records */
dumper->dump(dumper, &detail);
}
rcu_read_unlock();
}
/**
* kmsg_dump_get_line - retrieve one kmsg log line
* @iter: kmsg dump iterator
* @syslog: include the "<4>" prefixes
* @line: buffer to copy the line to
* @size: maximum size of the buffer
* @len: length of line placed into buffer
*
* Start at the beginning of the kmsg buffer, with the oldest kmsg
* record, and copy one record into the provided buffer.
*
* Consecutive calls will return the next available record moving
* towards the end of the buffer with the youngest messages.
*
* A return value of FALSE indicates that there are no more records to
* read.
*/
bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
char *line, size_t size, size_t *len)
{
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
unsigned int line_count;
struct printk_record r;
size_t l = 0;
bool ret = false;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
prb_rec_init_rd(&r, &info, line, size);
/* Read text or count text lines? */
if (line) {
if (!prb_read_valid(prb, iter->cur_seq, &r))
goto out;
l = record_print_text(&r, syslog, printk_time);
} else {
if (!prb_read_valid_info(prb, iter->cur_seq,
&info, &line_count)) {
goto out;
}
l = get_record_print_text_size(&info, line_count, syslog,
printk_time);
}
iter->cur_seq = r.info->seq + 1;
ret = true;
out:
if (len)
*len = l;
return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_line);
/**
* kmsg_dump_get_buffer - copy kmsg log lines
* @iter: kmsg dump iterator
* @syslog: include the "<4>" prefixes
* @buf: buffer to copy the line to
* @size: maximum size of the buffer
* @len_out: length of line placed into buffer
*
* Start at the end of the kmsg buffer and fill the provided buffer
* with as many of the *youngest* kmsg records that fit into it.
* If the buffer is large enough, all available kmsg records will be
* copied with a single call.
*
* Consecutive calls will fill the buffer with the next block of
* available older records, not including the earlier retrieved ones.
*
* A return value of FALSE indicates that there are no more records to
* read.
*/
bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
char *buf, size_t size, size_t *len_out)
{
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
struct printk_record r;
u64 seq;
u64 next_seq;
size_t len = 0;
bool ret = false;
bool time = printk_time;
if (!buf || !size)
goto out;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
if (info.seq != iter->cur_seq) {
/* messages are gone, move to first available one */
iter->cur_seq = info.seq;
}
}
/* last entry */
if (iter->cur_seq >= iter->next_seq)
goto out;
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump. Pass in size-1
* because this function (by way of record_print_text()) will
* not write more than size-1 bytes of text into @buf.
*/
seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq,
size - 1, syslog, time);
/*
* Next kmsg_dump_get_buffer() invocation will dump block of
* older records stored right before this one.
*/
next_seq = seq;
prb_rec_init_rd(&r, &info, buf, size);
prb_for_each_record(seq, prb, seq, &r) {
if (r.info->seq >= iter->next_seq)
break;
len += record_print_text(&r, syslog, time);
/* Adjust record to store to remaining buffer space. */
prb_rec_init_rd(&r, &info, buf + len, size - len);
}
iter->next_seq = next_seq;
ret = true;
out:
if (len_out)
*len_out = len;
return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
/**
* kmsg_dump_rewind - reset the iterator
* @iter: kmsg dump iterator
*
* Reset the dumper's iterator so that kmsg_dump_get_line() and
* kmsg_dump_get_buffer() can be called again and used multiple
* times within the same dumper.dump() callback.
*/
void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
{
iter->cur_seq = latched_seq_read_nolock(&clear_seq);
iter->next_seq = prb_next_seq(prb);
}
EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
/**
* console_try_replay_all - try to replay kernel log on consoles
*
* Try to obtain lock on console subsystem and replay all
* available records in printk buffer on the consoles.
* Does nothing if lock is not obtained.
*
* Context: Any, except for NMI.
*/
void console_try_replay_all(void)
{
struct console_flush_type ft;
printk_get_console_flush_type(&ft);
if (console_trylock()) {
__console_rewind_all();
if (ft.nbcon_atomic)
nbcon_atomic_flush_pending();
if (ft.nbcon_offload)
nbcon_kthreads_wake();
if (ft.legacy_offload)
defer_console_output();
/* Consoles are flushed as part of console_unlock(). */
console_unlock();
}
}
#endif
#ifdef CONFIG_SMP
static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1);
static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0);
bool is_printk_cpu_sync_owner(void)
{
return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id());
}
/**
* __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant
* spinning lock is not owned by any CPU.
*
* Context: Any context.
*/
void __printk_cpu_sync_wait(void)
{
do {
cpu_relax();
} while (atomic_read(&printk_cpu_sync_owner) != -1);
}
EXPORT_SYMBOL(__printk_cpu_sync_wait);
/**
* __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant
* spinning lock.
*
* If no processor has the lock, the calling processor takes the lock and
* becomes the owner. If the calling processor is already the owner of the
* lock, this function succeeds immediately.
*
* Context: Any context. Expects interrupts to be disabled.
* Return: 1 on success, otherwise 0.
*/
int __printk_cpu_sync_try_get(void)
{
int cpu;
int old;
cpu = smp_processor_id();
/*
* Guarantee loads and stores from this CPU when it is the lock owner
* are _not_ visible to the previous lock owner. This pairs with
* __printk_cpu_sync_put:B.
*
* Memory barrier involvement:
*
* If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
* then __printk_cpu_sync_put:A can never read from
* __printk_cpu_sync_try_get:B.
*
* Relies on:
*
* RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
* of the previous CPU
* matching
* ACQUIRE from __printk_cpu_sync_try_get:A to
* __printk_cpu_sync_try_get:B of this CPU
*/
old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1,
cpu); /* LMM(__printk_cpu_sync_try_get:A) */
if (old == -1) {
/*
* This CPU is now the owner and begins loading/storing
* data: LMM(__printk_cpu_sync_try_get:B)
*/
return 1;
} else if (old == cpu) {
/* This CPU is already the owner. */
atomic_inc(&printk_cpu_sync_nested);
return 1;
}
return 0;
}
EXPORT_SYMBOL(__printk_cpu_sync_try_get);
/**
* __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock.
*
* The calling processor must be the owner of the lock.
*
* Context: Any context. Expects interrupts to be disabled.
*/
void __printk_cpu_sync_put(void)
{
if (atomic_read(&printk_cpu_sync_nested)) {
atomic_dec(&printk_cpu_sync_nested);
return;
}
/*
* This CPU is finished loading/storing data:
* LMM(__printk_cpu_sync_put:A)
*/
/*
* Guarantee loads and stores from this CPU when it was the
* lock owner are visible to the next lock owner. This pairs
* with __printk_cpu_sync_try_get:A.
*
* Memory barrier involvement:
*
* If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
* then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A.
*
* Relies on:
*
* RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
* of this CPU
* matching
* ACQUIRE from __printk_cpu_sync_try_get:A to
* __printk_cpu_sync_try_get:B of the next CPU
*/
atomic_set_release(&printk_cpu_sync_owner,
-1); /* LMM(__printk_cpu_sync_put:B) */
}
EXPORT_SYMBOL(__printk_cpu_sync_put);
#endif /* CONFIG_SMP */
/**
* css_get - obtain a reference on the specified css
* @css: target css
*
* The caller must already have a reference.
*/
CGROUP_REF_FN_ATTRS
void css_get(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_get(&css->refcnt);
}
CGROUP_REF_EXPORT(css_get)
/**
* css_get_many - obtain references on the specified css
* @css: target css
* @n: number of references to get
*
* The caller must already have a reference.
*/
CGROUP_REF_FN_ATTRS
void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_get_many(&css->refcnt, n);
}
CGROUP_REF_EXPORT(css_get_many)
/**
* css_tryget - try to obtain a reference on the specified css
* @css: target css
*
* Obtain a reference on @css unless it already has reached zero and is
* being released. This function doesn't care whether @css is on or
* offline. The caller naturally needs to ensure that @css is accessible
* but doesn't have to be holding a reference on it - IOW, RCU protected
* access is good enough for this function. Returns %true if a reference
* count was successfully obtained; %false otherwise.
*/
CGROUP_REF_FN_ATTRS
bool css_tryget(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget(&css->refcnt);
return true;
}
CGROUP_REF_EXPORT(css_tryget)
/**
* css_tryget_online - try to obtain a reference on the specified css if online
* @css: target css
*
* Obtain a reference on @css if it's online. The caller naturally needs
* to ensure that @css is accessible but doesn't have to be holding a
* reference on it - IOW, RCU protected access is good enough for this
* function. Returns %true if a reference count was successfully obtained;
* %false otherwise.
*/
CGROUP_REF_FN_ATTRS
bool css_tryget_online(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
return percpu_ref_tryget_live(&css->refcnt);
return true;
}
CGROUP_REF_EXPORT(css_tryget_online)
/**
* css_put - put a css reference
* @css: target css
*
* Put a reference obtained via css_get() and css_tryget_online().
*/
CGROUP_REF_FN_ATTRS
void css_put(struct cgroup_subsys_state *css)
{ if (!(css->flags & CSS_NO_REF)) percpu_ref_put(&css->refcnt);
}
CGROUP_REF_EXPORT(css_put)
/**
* css_put_many - put css references
* @css: target css
* @n: number of references to put
*
* Put references obtained via css_get() and css_tryget_online().
*/
CGROUP_REF_FN_ATTRS
void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_put_many(&css->refcnt, n);
}
CGROUP_REF_EXPORT(css_put_many)
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/sched/xacct.h>
#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/dax.h>
#include <linux/overflow.h>
#include "internal.h"
#include <linux/uaccess.h>
#include <asm/unistd.h>
/*
* Performs necessary checks before doing a clone.
*
* Can adjust amount of bytes to clone via @req_count argument.
* Returns appropriate error code that caller should return or
* zero in case the clone should be allowed.
*/
static int generic_remap_checks(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *req_count, unsigned int remap_flags)
{
struct inode *inode_in = file_in->f_mapping->host;
struct inode *inode_out = file_out->f_mapping->host;
uint64_t count = *req_count;
uint64_t bcount;
loff_t size_in, size_out;
loff_t bs = inode_out->i_sb->s_blocksize;
int ret;
/* The start of both ranges must be aligned to an fs block. */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
return -EINVAL;
/* Ensure offsets don't wrap. */
if (pos_in + count < pos_in || pos_out + count < pos_out)
return -EINVAL;
size_in = i_size_read(inode_in);
size_out = i_size_read(inode_out);
/* Dedupe requires both ranges to be within EOF. */
if ((remap_flags & REMAP_FILE_DEDUP) &&
(pos_in >= size_in || pos_in + count > size_in ||
pos_out >= size_out || pos_out + count > size_out))
return -EINVAL;
/* Ensure the infile range is within the infile. */
if (pos_in >= size_in)
return -EINVAL;
count = min(count, size_in - (uint64_t)pos_in);
ret = generic_write_check_limits(file_out, pos_out, &count);
if (ret)
return ret;
/*
* If the user wanted us to link to the infile's EOF, round up to the
* next block boundary for this check.
*
* Otherwise, make sure the count is also block-aligned, having
* already confirmed the starting offsets' block alignment.
*/
if (pos_in + count == size_in &&
(!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) {
bcount = ALIGN(size_in, bs) - pos_in;
} else {
if (!IS_ALIGNED(count, bs))
count = ALIGN_DOWN(count, bs);
bcount = count;
}
/* Don't allow overlapped cloning within the same file. */
if (inode_in == inode_out &&
pos_out + bcount > pos_in &&
pos_out < pos_in + bcount)
return -EINVAL;
/*
* We shortened the request but the caller can't deal with that, so
* bounce the request back to userspace.
*/
if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
return -EINVAL;
*req_count = count;
return 0;
}
int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write)
{
int mask = write ? MAY_WRITE : MAY_READ;
loff_t tmp;
int ret;
if (unlikely(pos < 0 || len < 0))
return -EINVAL;
if (unlikely(check_add_overflow(pos, len, &tmp)))
return -EINVAL;
ret = security_file_permission(file, mask);
if (ret)
return ret;
return fsnotify_file_area_perm(file, mask, &pos, len);}
EXPORT_SYMBOL_GPL(remap_verify_area);
/*
* Ensure that we don't remap a partial EOF block in the middle of something
* else. Assume that the offsets have already been checked for block
* alignment.
*
* For clone we only link a partial EOF block above or at the destination file's
* EOF. For deduplication we accept a partial EOF block only if it ends at the
* destination file's EOF (can not link it into the middle of a file).
*
* Shorten the request if possible.
*/
static int generic_remap_check_len(struct inode *inode_in,
struct inode *inode_out,
loff_t pos_out,
loff_t *len,
unsigned int remap_flags)
{
u64 blkmask = i_blocksize(inode_in) - 1;
loff_t new_len = *len;
if ((*len & blkmask) == 0)
return 0;
if (pos_out + *len < i_size_read(inode_out))
new_len &= ~blkmask;
if (new_len == *len)
return 0;
if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
*len = new_len;
return 0;
}
return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
}
/* Read a page's worth of file data into the page cache. */
static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos)
{
return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file);
}
/*
* Lock two folios, ensuring that we lock in offset order if the folios
* are from the same file.
*/
static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2)
{
/* Always lock in order of increasing index. */
if (folio1->index > folio2->index)
swap(folio1, folio2);
folio_lock(folio1);
if (folio1 != folio2)
folio_lock(folio2);
}
/* Unlock two folios, being careful not to unlock the same folio twice. */
static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2)
{
folio_unlock(folio1);
if (folio1 != folio2)
folio_unlock(folio2);
}
/*
* Compare extents of two files to see if they are the same.
* Caller must have locked both inodes to prevent write races.
*/
static int vfs_dedupe_file_range_compare(struct file *src, loff_t srcoff,
struct file *dest, loff_t dstoff,
loff_t len, bool *is_same)
{
bool same = true;
int error = -EINVAL;
while (len) {
struct folio *src_folio, *dst_folio;
void *src_addr, *dst_addr;
loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff),
PAGE_SIZE - offset_in_page(dstoff));
cmp_len = min(cmp_len, len);
if (cmp_len <= 0)
goto out_error;
src_folio = vfs_dedupe_get_folio(src, srcoff);
if (IS_ERR(src_folio)) {
error = PTR_ERR(src_folio);
goto out_error;
}
dst_folio = vfs_dedupe_get_folio(dest, dstoff);
if (IS_ERR(dst_folio)) {
error = PTR_ERR(dst_folio);
folio_put(src_folio);
goto out_error;
}
vfs_lock_two_folios(src_folio, dst_folio);
/*
* Now that we've locked both folios, make sure they're still
* mapped to the file data we're interested in. If not,
* someone is invalidating pages on us and we lose.
*/
if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) ||
src_folio->mapping != src->f_mapping ||
dst_folio->mapping != dest->f_mapping) {
same = false;
goto unlock;
}
src_addr = kmap_local_folio(src_folio,
offset_in_folio(src_folio, srcoff));
dst_addr = kmap_local_folio(dst_folio,
offset_in_folio(dst_folio, dstoff));
flush_dcache_folio(src_folio);
flush_dcache_folio(dst_folio);
if (memcmp(src_addr, dst_addr, cmp_len))
same = false;
kunmap_local(dst_addr);
kunmap_local(src_addr);
unlock:
vfs_unlock_two_folios(src_folio, dst_folio);
folio_put(dst_folio);
folio_put(src_folio);
if (!same)
break;
srcoff += cmp_len;
dstoff += cmp_len;
len -= cmp_len;
}
*is_same = same;
return 0;
out_error:
return error;
}
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* If there's an error, then the usual negative error code is returned.
* Otherwise returns 0 with *len set to the request length.
*/
int
__generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
const struct iomap_ops *dax_read_ops)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
loff_t isize = i_size_read(inode_in);
if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
if (*len == 0)
return 0;
}
/* Check that we don't violate system file offset limits. */
ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
remap_flags);
if (ret || *len == 0)
return ret;
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (remap_flags & REMAP_FILE_DEDUP) {
bool is_same = false;
if (!IS_DAX(inode_in))
ret = vfs_dedupe_file_range_compare(file_in, pos_in,
file_out, pos_out, *len, &is_same);
else if (dax_read_ops)
ret = dax_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same,
dax_read_ops);
else
return -EINVAL;
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
remap_flags);
if (ret || *len == 0)
return ret;
/* If can't alter the file contents, we're done. */
if (!(remap_flags & REMAP_FILE_DEDUP))
ret = file_modified(file_out);
return ret;
}
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags)
{
return __generic_remap_file_range_prep(file_in, pos_in, file_out,
pos_out, len, remap_flags, NULL);
}
EXPORT_SYMBOL(generic_remap_file_range_prep);
loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags)
{
loff_t ret;
WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
return -EXDEV;
ret = generic_file_rw_checks(file_in, file_out);
if (ret < 0)
return ret;
if (!file_in->f_op->remap_file_range)
return -EOPNOTSUPP;
ret = remap_verify_area(file_in, pos_in, len, false);
if (ret)
return ret;
ret = remap_verify_area(file_out, pos_out, len, true); if (ret)
return ret;
file_start_write(file_out);
ret = file_in->f_op->remap_file_range(file_in, pos_in,
file_out, pos_out, len, remap_flags);
file_end_write(file_out); if (ret < 0)
return ret;
fsnotify_access(file_in);
fsnotify_modify(file_out);
return ret;
}
EXPORT_SYMBOL(vfs_clone_file_range);
/* Check whether we are allowed to dedupe the destination file */
static bool may_dedupe_file(struct file *file)
{
struct mnt_idmap *idmap = file_mnt_idmap(file);
struct inode *inode = file_inode(file);
if (capable(CAP_SYS_ADMIN))
return true;
if (file->f_mode & FMODE_WRITE)
return true;
if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid()))
return true;
if (!inode_permission(idmap, inode, MAY_WRITE))
return true;
return false;
}
loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
struct file *dst_file, loff_t dst_pos,
loff_t len, unsigned int remap_flags)
{
loff_t ret;
WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
REMAP_FILE_CAN_SHORTEN));
/*
* This is redundant if called from vfs_dedupe_file_range(), but other
* callers need it and it's not performance sesitive...
*/
ret = remap_verify_area(src_file, src_pos, len, false);
if (ret)
return ret;
ret = remap_verify_area(dst_file, dst_pos, len, true);
if (ret)
return ret;
/*
* This needs to be called after remap_verify_area() because of
* sb_start_write() and before may_dedupe_file() because the mount's
* MAY_WRITE need to be checked with mnt_get_write_access_file() held.
*/
ret = mnt_want_write_file(dst_file);
if (ret)
return ret;
ret = -EPERM;
if (!may_dedupe_file(dst_file))
goto out_drop_write;
ret = -EXDEV;
if (file_inode(src_file)->i_sb != file_inode(dst_file)->i_sb)
goto out_drop_write;
ret = -EISDIR;
if (S_ISDIR(file_inode(dst_file)->i_mode))
goto out_drop_write;
ret = -EINVAL;
if (!dst_file->f_op->remap_file_range)
goto out_drop_write;
if (len == 0) {
ret = 0;
goto out_drop_write;
}
ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
out_drop_write:
mnt_drop_write_file(dst_file);
return ret;
}
EXPORT_SYMBOL(vfs_dedupe_file_range_one);
int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
{
struct file_dedupe_range_info *info;
struct inode *src = file_inode(file);
u64 off;
u64 len;
int i;
int ret;
u16 count = same->dest_count;
loff_t deduped;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
if (same->reserved1 || same->reserved2)
return -EINVAL;
off = same->src_offset;
len = same->src_length;
if (S_ISDIR(src->i_mode))
return -EISDIR;
if (!S_ISREG(src->i_mode))
return -EINVAL;
if (!file->f_op->remap_file_range)
return -EOPNOTSUPP;
ret = remap_verify_area(file, off, len, false);
if (ret < 0)
return ret;
ret = 0;
if (off + len > i_size_read(src))
return -EINVAL;
/* Arbitrary 1G limit on a single dedupe request, can be raised. */
len = min_t(u64, len, 1 << 30);
/* pre-format output fields to sane values */
for (i = 0; i < count; i++) {
same->info[i].bytes_deduped = 0ULL;
same->info[i].status = FILE_DEDUPE_RANGE_SAME;
}
for (i = 0, info = same->info; i < count; i++, info++) {
CLASS(fd, dst_fd)(info->dest_fd);
if (fd_empty(dst_fd)) {
info->status = -EBADF;
goto next_loop;
}
if (info->reserved) {
info->status = -EINVAL;
goto next_loop;
}
deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd),
info->dest_offset, len,
REMAP_FILE_CAN_SHORTEN);
if (deduped == -EBADE)
info->status = FILE_DEDUPE_RANGE_DIFFERS;
else if (deduped < 0)
info->status = deduped;
else
info->bytes_deduped = len;
next_loop:
if (fatal_signal_pending(current))
break;
}
return ret;
}
EXPORT_SYMBOL(vfs_dedupe_file_range);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
*
* Provides a framework for enqueueing and running callbacks from hardirq
* context. The enqueueing is NMI-safe.
*/
#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/irq_work.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/tick.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <asm/processor.h>
#include <linux/kasan.h>
#include <trace/events/ipi.h>
static DEFINE_PER_CPU(struct llist_head, raised_list);
static DEFINE_PER_CPU(struct llist_head, lazy_list);
static DEFINE_PER_CPU(struct task_struct *, irq_workd);
static void wake_irq_workd(void)
{
struct task_struct *tsk = __this_cpu_read(irq_workd);
if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk)
wake_up_process(tsk);
}
#ifdef CONFIG_SMP
static void irq_work_wake(struct irq_work *entry)
{
wake_irq_workd();
}
static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) =
IRQ_WORK_INIT_HARD(irq_work_wake);
#endif
static int irq_workd_should_run(unsigned int cpu)
{
return !llist_empty(this_cpu_ptr(&lazy_list));
}
/*
* Claim the entry so that no one else will poke at it.
*/
static bool irq_work_claim(struct irq_work *work)
{
int oflags;
oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags);
/*
* If the work is already pending, no need to raise the IPI.
* The pairing smp_mb() in irq_work_single() makes sure
* everything we did before is visible.
*/
if (oflags & IRQ_WORK_PENDING)
return false;
return true;
}
void __weak arch_irq_work_raise(void)
{
/*
* Lame architectures will get the timer tick callback
*/
}
static __always_inline void irq_work_raise(struct irq_work *work)
{
if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func);
arch_irq_work_raise();
}
/* Enqueue on current CPU, work must already be claimed and preempt disabled */
static void __irq_work_queue_local(struct irq_work *work)
{
struct llist_head *list;
bool rt_lazy_work = false;
bool lazy_work = false;
int work_flags;
work_flags = atomic_read(&work->node.a_flags);
if (work_flags & IRQ_WORK_LAZY)
lazy_work = true;
else if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
!(work_flags & IRQ_WORK_HARD_IRQ))
rt_lazy_work = true;
if (lazy_work || rt_lazy_work)
list = this_cpu_ptr(&lazy_list);
else
list = this_cpu_ptr(&raised_list);
if (!llist_add(&work->node.llist, list))
return;
/* If the work is "lazy", handle it from next tick if any */
if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work);
}
/* Enqueue the irq work @work on the current CPU */
bool irq_work_queue(struct irq_work *work)
{
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
/* Queue the entry and raise the IPI if needed. */
preempt_disable();
__irq_work_queue_local(work);
preempt_enable();
return true;
}
EXPORT_SYMBOL_GPL(irq_work_queue);
/*
* Enqueue the irq_work @work on @cpu unless it's already pending
* somewhere.
*
* Can be re-enqueued while the callback is still in progress.
*/
bool irq_work_queue_on(struct irq_work *work, int cpu)
{
#ifndef CONFIG_SMP
return irq_work_queue(work);
#else /* CONFIG_SMP: */
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(cpu));
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
kasan_record_aux_stack(work);
preempt_disable();
if (cpu != smp_processor_id()) {
/* Arch remote IPI send/receive backend aren't NMI safe */
WARN_ON_ONCE(in_nmi());
/*
* On PREEMPT_RT the items which are not marked as
* IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work
* item is used on the remote CPU to wake the thread.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
!(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) {
if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu)))
goto out;
work = &per_cpu(irq_work_wakeup, cpu);
if (!irq_work_claim(work))
goto out;
}
__smp_call_single_queue(cpu, &work->node.llist);
} else {
__irq_work_queue_local(work);
}
out:
preempt_enable();
return true;
#endif /* CONFIG_SMP */
}
bool irq_work_needs_cpu(void)
{
struct llist_head *raised, *lazy;
raised = this_cpu_ptr(&raised_list);
lazy = this_cpu_ptr(&lazy_list);
if (llist_empty(raised) || arch_irq_work_has_interrupt())
if (llist_empty(lazy))
return false;
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
return true;
}
void irq_work_single(void *arg)
{
struct irq_work *work = arg;
int flags;
/*
* Clear the PENDING bit, after this point the @work can be re-used.
* The PENDING bit acts as a lock, and we own it, so we can clear it
* without atomic ops.
*/
flags = atomic_read(&work->node.a_flags);
flags &= ~IRQ_WORK_PENDING;
atomic_set(&work->node.a_flags, flags);
/*
* See irq_work_claim().
*/
smp_mb();
lockdep_irq_work_enter(flags);
work->func(work);
lockdep_irq_work_exit(flags);
/*
* Clear the BUSY bit, if set, and return to the free state if no-one
* else claimed it meanwhile.
*/
(void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY);
if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
!arch_irq_work_has_interrupt())
rcuwait_wake_up(&work->irqwait);
}
static void irq_work_run_list(struct llist_head *list)
{
struct irq_work *work, *tmp;
struct llist_node *llnode;
/*
* On PREEMPT_RT IRQ-work which is not marked as HARD will be processed
* in a per-CPU thread in preemptible context. Only the items which are
* marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context.
*/
BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT));
if (llist_empty(list))
return;
llnode = llist_del_all(list);
llist_for_each_entry_safe(work, tmp, llnode, node.llist)
irq_work_single(work);
}
/*
* hotplug calls this through:
* hotplug_cfd() -> flush_smp_call_function_queue()
*/
void irq_work_run(void)
{
irq_work_run_list(this_cpu_ptr(&raised_list));
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
irq_work_run_list(this_cpu_ptr(&lazy_list));
else
wake_irq_workd();
}
EXPORT_SYMBOL_GPL(irq_work_run);
void irq_work_tick(void)
{
struct llist_head *raised = this_cpu_ptr(&raised_list);
if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
irq_work_run_list(raised);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
irq_work_run_list(this_cpu_ptr(&lazy_list));
else
wake_irq_workd();
}
/*
* Synchronize against the irq_work @entry, ensures the entry is not
* currently in use.
*/
void irq_work_sync(struct irq_work *work)
{ lockdep_assert_irqs_enabled();
might_sleep();
if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
!arch_irq_work_has_interrupt()) {
rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work),
TASK_UNINTERRUPTIBLE);
return;
}
while (irq_work_is_busy(work))
cpu_relax();
}
EXPORT_SYMBOL_GPL(irq_work_sync);
static void run_irq_workd(unsigned int cpu)
{
irq_work_run_list(this_cpu_ptr(&lazy_list));
}
static void irq_workd_setup(unsigned int cpu)
{
sched_set_fifo_low(current);
}
static struct smp_hotplug_thread irqwork_threads = {
.store = &irq_workd,
.setup = irq_workd_setup,
.thread_should_run = irq_workd_should_run,
.thread_fn = run_irq_workd,
.thread_comm = "irq_work/%u",
};
static __init int irq_work_init_threads(void)
{
if (IS_ENABLED(CONFIG_PREEMPT_RT))
BUG_ON(smpboot_register_percpu_thread(&irqwork_threads));
return 0;
}
early_initcall(irq_work_init_threads);
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/namei.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* Some corrections by tytso.
*/
/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
* lookup logic.
*/
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
*/
#include <linux/init.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/wordpart.h>
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <linux/posix_acl.h>
#include <linux/hash.h>
#include <linux/bitops.h>
#include <linux/init_task.h>
#include <linux/uaccess.h>
#include "internal.h"
#include "mount.h"
/* [Feb-1997 T. Schoebel-Theuer]
* Fundamental changes in the pathname lookup mechanisms (namei)
* were necessary because of omirr. The reason is that omirr needs
* to know the _real_ pathname, not the user-supplied one, in case
* of symlinks (and also when transname replacements occur).
*
* The new code replaces the old recursive symlink resolution with
* an iterative one (in case of non-nested symlink chains). It does
* this with calls to <fs>_follow_link().
* As a side effect, dir_namei(), _namei() and follow_link() are now
* replaced with a single function lookup_dentry() that can handle all
* the special cases of the former code.
*
* With the new dcache, the pathname is stored at each inode, at least as
* long as the refcount of the inode is positive. As a side effect, the
* size of the dcache depends on the inode cache and thus is dynamic.
*
* [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
* resolution to correspond with current state of the code.
*
* Note that the symlink resolution is not *completely* iterative.
* There is still a significant amount of tail- and mid- recursion in
* the algorithm. Also, note that <fs>_readlink() is not used in
* lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
* may return different results than <fs>_follow_link(). Many virtual
* filesystems (including /proc) exhibit this behavior.
*/
/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
* New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
* and the name already exists in form of a symlink, try to create the new
* name indicated by the symlink. The old code always complained that the
* name already exists, due to not following the symlink even if its target
* is nonexistent. The new semantics affects also mknod() and link() when
* the name is a symlink pointing to a non-existent name.
*
* I don't know which semantics is the right one, since I have no access
* to standards. But I found by trial that HP-UX 9.0 has the full "new"
* semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
* "old" one. Personally, I think the new semantics is much more logical.
* Note that "ln old new" where "new" is a symlink pointing to a non-existing
* file does succeed in both HP-UX and SunOs, but not in Solaris
* and in the old Linux semantics.
*/
/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
* semantics. See the comments in "open_namei" and "do_link" below.
*
* [10-Sep-98 Alan Modra] Another symlink change.
*/
/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
* inside the path - always follow.
* in the last component in creation/removal/renaming - never follow.
* if LOOKUP_FOLLOW passed - follow.
* if the pathname has trailing slashes - follow.
* otherwise - don't follow.
* (applied in that order).
*
* [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
* restored for 2.4. This is the last surviving part of old 4.2BSD bug.
* During the 2.4 we need to fix the userland stuff depending on it -
* hopefully we will be able to get rid of that wart in 2.5. So far only
* XEmacs seems to be relying on it...
*/
/*
* [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
* implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives
* any extra contention...
*/
/* In order to reduce some races, while at the same time doing additional
* checking and hopefully speeding things up, we copy filenames to the
* kernel data space before using them..
*
* POSIX.1 2.4: an empty pathname is invalid (ENOENT).
* PATH_MAX includes the nul terminator --RR.
*/
#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname))
static inline void initname(struct filename *name, const char __user *uptr)
{
name->uptr = uptr;
name->aname = NULL;
atomic_set(&name->refcnt, 1);
}
struct filename *
getname_flags(const char __user *filename, int flags)
{
struct filename *result;
char *kname;
int len;
result = audit_reusename(filename); if (result)
return result;
result = __getname();
if (unlikely(!result))
return ERR_PTR(-ENOMEM);
/*
* First, try to embed the struct filename inside the names_cache
* allocation
*/
kname = (char *)result->iname;
result->name = kname;
len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
/*
* Handle both empty path and copy failure in one go.
*/
if (unlikely(len <= 0)) {
if (unlikely(len < 0)) {
__putname(result);
return ERR_PTR(len);
}
/* The empty path is special. */
if (!(flags & LOOKUP_EMPTY)) { __putname(result);
return ERR_PTR(-ENOENT);
}
}
/*
* Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
* separate struct filename so we can dedicate the entire
* names_cache allocation for the pathname, and re-do the copy from
* userland.
*/
if (unlikely(len == EMBEDDED_NAME_MAX)) {
const size_t size = offsetof(struct filename, iname[1]);
kname = (char *)result;
/*
* size is chosen that way we to guarantee that
* result->iname[0] is within the same object and that
* kname can't be equal to result->iname, no matter what.
*/
result = kzalloc(size, GFP_KERNEL);
if (unlikely(!result)) {
__putname(kname);
return ERR_PTR(-ENOMEM);
}
result->name = kname;
len = strncpy_from_user(kname, filename, PATH_MAX);
if (unlikely(len < 0)) {
__putname(kname);
kfree(result);
return ERR_PTR(len);
}
/* The empty path is special. */
if (unlikely(!len) && !(flags & LOOKUP_EMPTY)) { __putname(kname);
kfree(result);
return ERR_PTR(-ENOENT);
}
if (unlikely(len == PATH_MAX)) {
__putname(kname);
kfree(result);
return ERR_PTR(-ENAMETOOLONG);
}
}
initname(result, filename);
audit_getname(result);
return result;
}
struct filename *getname_uflags(const char __user *filename, int uflags)
{
int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
return getname_flags(filename, flags);
}
struct filename *__getname_maybe_null(const char __user *pathname)
{
struct filename *name;
char c;
/* try to save on allocations; loss on um, though */
if (get_user(c, pathname))
return ERR_PTR(-EFAULT);
if (!c)
return NULL;
name = getname_flags(pathname, LOOKUP_EMPTY);
if (!IS_ERR(name) && !(name->name[0])) {
putname(name);
name = NULL;
}
return name;
}
struct filename *getname_kernel(const char * filename)
{
struct filename *result;
int len = strlen(filename) + 1;
result = __getname();
if (unlikely(!result))
return ERR_PTR(-ENOMEM);
if (len <= EMBEDDED_NAME_MAX) {
result->name = (char *)result->iname;
} else if (len <= PATH_MAX) {
const size_t size = offsetof(struct filename, iname[1]);
struct filename *tmp;
tmp = kmalloc(size, GFP_KERNEL);
if (unlikely(!tmp)) {
__putname(result);
return ERR_PTR(-ENOMEM);
}
tmp->name = (char *)result;
result = tmp;
} else {
__putname(result);
return ERR_PTR(-ENAMETOOLONG);
}
memcpy((char *)result->name, filename, len);
initname(result, NULL);
audit_getname(result);
return result;
}
EXPORT_SYMBOL(getname_kernel);
void putname(struct filename *name)
{
int refcnt;
if (IS_ERR_OR_NULL(name))
return;
refcnt = atomic_read(&name->refcnt);
if (refcnt != 1) { if (WARN_ON_ONCE(!refcnt))
return;
if (!atomic_dec_and_test(&name->refcnt))
return;
}
if (name->name != name->iname) {
__putname(name->name);
kfree(name);
} else
__putname(name);
}
EXPORT_SYMBOL(putname);
/**
* check_acl - perform ACL permission checking
* @idmap: idmap of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* This function performs the ACL permission checking. Since this function
* retrieve POSIX acls it needs to know whether it is called from a blocking or
* non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
static int check_acl(struct mnt_idmap *idmap,
struct inode *inode, int mask)
{
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *acl;
if (mask & MAY_NOT_BLOCK) {
acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
if (!acl)
return -EAGAIN;
/* no ->get_inode_acl() calls in RCU mode... */
if (is_uncached_acl(acl))
return -ECHILD;
return posix_acl_permission(idmap, inode, acl, mask);
}
acl = get_inode_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl) {
int error = posix_acl_permission(idmap, inode, acl, mask);
posix_acl_release(acl);
return error;
}
#endif
return -EAGAIN;
}
/*
* Very quick optimistic "we know we have no ACL's" check.
*
* Note that this is purely for ACL_TYPE_ACCESS, and purely
* for the "we have cached that there are no ACLs" case.
*
* If this returns true, we know there are no ACLs. But if
* it returns false, we might still not have ACLs (it could
* be the is_uncached_acl() case).
*/
static inline bool no_acl_inode(struct inode *inode)
{
#ifdef CONFIG_FS_POSIX_ACL
return likely(!READ_ONCE(inode->i_acl));
#else
return true;
#endif
}
/**
* acl_permission_check - perform basic UNIX permission checking
* @idmap: idmap of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* This function performs the basic UNIX permission checking. Since this
* function may retrieve POSIX acls it needs to know whether it is called from a
* blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
static int acl_permission_check(struct mnt_idmap *idmap,
struct inode *inode, int mask)
{
unsigned int mode = inode->i_mode;
vfsuid_t vfsuid;
/*
* Common cheap case: everybody has the requested
* rights, and there are no ACLs to check. No need
* to do any owner/group checks in that case.
*
* - 'mask&7' is the requested permission bit set
* - multiplying by 0111 spreads them out to all of ugo
* - '& ~mode' looks for missing inode permission bits
* - the '!' is for "no missing permissions"
*
* After that, we just need to check that there are no
* ACL's on the inode - do the 'IS_POSIXACL()' check last
* because it will dereference the ->i_sb pointer and we
* want to avoid that if at all possible.
*/
if (!((mask & 7) * 0111 & ~mode)) { if (no_acl_inode(inode))
return 0;
if (!IS_POSIXACL(inode))
return 0;
}
/* Are we the owner? If so, ACL's don't matter */
vfsuid = i_uid_into_vfsuid(idmap, inode);
if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) {
mask &= 7;
mode >>= 6;
return (mask & ~mode) ? -EACCES : 0;
}
/* Do we have ACL's? */
if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
int error = check_acl(idmap, inode, mask);
if (error != -EAGAIN)
return error;
}
/* Only RWX matters for group/other mode bits */
mask &= 7;
/*
* Are the group permissions different from
* the other permissions in the bits we care
* about? Need to check group ownership if so.
*/
if (mask & (mode ^ (mode >> 3))) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
if (vfsgid_in_group_p(vfsgid))
mode >>= 3;
}
/* Bits in 'mode' clear that we require? */
return (mask & ~mode) ? -EACCES : 0;
}
/**
* generic_permission - check for access rights on a Posix-like filesystem
* @idmap: idmap of the mount the inode was found from
* @inode: inode to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC,
* %MAY_NOT_BLOCK ...)
*
* Used to check for read/write/execute permissions on a file.
* We use "fsuid" for this, letting us set arbitrary permissions
* for filesystem access without changing the "normal" uids which
* are used for other things.
*
* generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
* request cannot be satisfied (eg. requires blocking or too much complexity).
* It would then be called again in ref-walk mode.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int generic_permission(struct mnt_idmap *idmap, struct inode *inode,
int mask)
{
int ret;
/*
* Do the basic permission checks.
*/
ret = acl_permission_check(idmap, inode, mask);
if (ret != -EACCES)
return ret;
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(idmap, inode,
CAP_DAC_READ_SEARCH))
return 0;
if (capable_wrt_inode_uidgid(idmap, inode,
CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
/*
* Searching includes executable on directories, else just read.
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ) if (capable_wrt_inode_uidgid(idmap, inode,
CAP_DAC_READ_SEARCH))
return 0;
/*
* Read/write DACs are always overridable.
* Executable DACs are overridable when there is
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(idmap, inode,
CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
EXPORT_SYMBOL(generic_permission);
/**
* do_inode_permission - UNIX permission checking
* @idmap: idmap of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* We _really_ want to just do "generic_permission()" without
* even looking at the inode->i_op values. So we keep a cache
* flag in inode->i_opflags, that says "this has not special
* permission function, use the fast case".
*/
static inline int do_inode_permission(struct mnt_idmap *idmap,
struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
if (likely(inode->i_op->permission))
return inode->i_op->permission(idmap, inode, mask);
/* This gets set once for the inode lifetime */
spin_lock(&inode->i_lock);
inode->i_opflags |= IOP_FASTPERM;
spin_unlock(&inode->i_lock);
}
return generic_permission(idmap, inode, mask);
}
/**
* sb_permission - Check superblock-level permissions
* @sb: Superblock of inode to check permission on
* @inode: Inode to check permission on
* @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Separate out file-system wide checks from inode-specific permission checks.
*/
static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
{
if (unlikely(mask & MAY_WRITE)) {
umode_t mode = inode->i_mode;
/* Nobody gets write access to a read-only fs. */
if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
return -EROFS;
}
return 0;
}
/**
* inode_permission - Check for access rights to a given inode
* @idmap: idmap of the mount the inode was found from
* @inode: Inode to check permission on
* @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Check for read/write/execute permissions on an inode. We use fs[ug]id for
* this, letting us set arbitrary permissions for filesystem access without
* changing the "normal" UIDs which are used for other things.
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*/
int inode_permission(struct mnt_idmap *idmap,
struct inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
if (unlikely(mask & MAY_WRITE)) {
/*
* Nobody gets write access to an immutable file.
*/
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* Updating mtime will likely cause i_uid and i_gid to be
* written back improperly if their true value is unknown
* to the vfs.
*/
if (HAS_UNMAPPED_ID(idmap, inode))
return -EACCES;
}
retval = do_inode_permission(idmap, inode, mask); if (retval)
return retval;
retval = devcgroup_inode_permission(inode, mask); if (retval)
return retval;
return security_inode_permission(inode, mask);
}
EXPORT_SYMBOL(inode_permission);
/**
* path_get - get a reference to a path
* @path: path to get the reference to
*
* Given a path increment the reference count to the dentry and the vfsmount.
*/
void path_get(const struct path *path)
{
mntget(path->mnt);
dget(path->dentry);
}
EXPORT_SYMBOL(path_get);
/**
* path_put - put a reference to a path
* @path: path to put the reference to
*
* Given a path decrement the reference count to the dentry and the vfsmount.
*/
void path_put(const struct path *path)
{ dput(path->dentry);
mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);
#define EMBEDDED_LEVELS 2
struct nameidata {
struct path path;
struct qstr last;
struct path root;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags, state;
unsigned seq, next_seq, m_seq, r_seq;
int last_type;
unsigned depth;
int total_link_count;
struct saved {
struct path link;
struct delayed_call done;
const char *name;
unsigned seq;
} *stack, internal[EMBEDDED_LEVELS];
struct filename *name;
const char *pathname;
struct nameidata *saved;
unsigned root_seq;
int dfd;
vfsuid_t dir_vfsuid;
umode_t dir_mode;
} __randomize_layout;
#define ND_ROOT_PRESET 1
#define ND_ROOT_GRABBED 2
#define ND_JUMPED 4
static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name)
{
struct nameidata *old = current->nameidata;
p->stack = p->internal;
p->depth = 0;
p->dfd = dfd;
p->name = name;
p->pathname = likely(name) ? name->name : "";
p->path.mnt = NULL;
p->path.dentry = NULL;
p->total_link_count = old ? old->total_link_count : 0;
p->saved = old;
current->nameidata = p;
}
static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name,
const struct path *root)
{
__set_nameidata(p, dfd, name);
p->state = 0;
if (unlikely(root)) {
p->state = ND_ROOT_PRESET;
p->root = *root;
}
}
static void restore_nameidata(void)
{
struct nameidata *now = current->nameidata, *old = now->saved;
current->nameidata = old;
if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack);
}
static bool nd_alloc_stack(struct nameidata *nd)
{
struct saved *p;
p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved),
nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL);
if (unlikely(!p))
return false;
memcpy(p, nd->internal, sizeof(nd->internal));
nd->stack = p;
return true;
}
/**
* path_connected - Verify that a dentry is below mnt.mnt_root
* @mnt: The mountpoint to check.
* @dentry: The dentry to check.
*
* Rename can sometimes move a file or directory outside of a bind
* mount, path_connected allows those cases to be detected.
*/
static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
{
struct super_block *sb = mnt->mnt_sb;
/* Bind mounts can have disconnected paths */
if (mnt->mnt_root == sb->s_root)
return true;
return is_subdir(dentry, mnt->mnt_root);
}
static void drop_links(struct nameidata *nd)
{
int i = nd->depth;
while (i--) {
struct saved *last = nd->stack + i;
do_delayed_call(&last->done);
clear_delayed_call(&last->done);
}
}
static void leave_rcu(struct nameidata *nd)
{
nd->flags &= ~LOOKUP_RCU;
nd->seq = nd->next_seq = 0;
rcu_read_unlock();
}
static void terminate_walk(struct nameidata *nd)
{ drop_links(nd);
if (!(nd->flags & LOOKUP_RCU)) {
int i;
path_put(&nd->path);
for (i = 0; i < nd->depth; i++)
path_put(&nd->stack[i].link);
if (nd->state & ND_ROOT_GRABBED) { path_put(&nd->root);
nd->state &= ~ND_ROOT_GRABBED;
}
} else {
leave_rcu(nd);
}
nd->depth = 0;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
/* path_put is needed afterwards regardless of success or failure */
static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq)
{
int res = __legitimize_mnt(path->mnt, mseq);
if (unlikely(res)) {
if (res > 0) path->mnt = NULL;
path->dentry = NULL;
return false;
}
if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) {
path->dentry = NULL;
return false;
}
return !read_seqcount_retry(&path->dentry->d_seq, seq);
}
static inline bool legitimize_path(struct nameidata *nd,
struct path *path, unsigned seq)
{
return __legitimize_path(path, seq, nd->m_seq);
}
static bool legitimize_links(struct nameidata *nd)
{
int i;
if (unlikely(nd->flags & LOOKUP_CACHED)) {
drop_links(nd);
nd->depth = 0;
return false;
}
for (i = 0; i < nd->depth; i++) {
struct saved *last = nd->stack + i;
if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd);
nd->depth = i + 1;
return false;
}
}
return true;
}
static bool legitimize_root(struct nameidata *nd)
{
/* Nothing to do if nd->root is zero or is managed by the VFS user. */
if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET))
return true;
nd->state |= ND_ROOT_GRABBED;
return legitimize_path(nd, &nd->root, nd->root_seq);
}
/*
* Path walking has 2 modes, rcu-walk and ref-walk (see
* Documentation/filesystems/path-lookup.txt). In situations when we can't
* continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
* normal reference counts on dentries and vfsmounts to transition to ref-walk
* mode. Refcounts are grabbed at the last known good point before rcu-walk
* got stuck, so ref-walk may continue from there. If this is not successful
* (eg. a seqcount has changed), then failure is returned and it's up to caller
* to restart the path walk from the beginning in ref-walk mode.
*/
/**
* try_to_unlazy - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* Returns: true on success, false on failure
*
* try_to_unlazy attempts to legitimize the current nd->path and nd->root
* for ref-walk mode.
* Must be called from rcu-walk context.
* Nothing should touch nameidata between try_to_unlazy() failure and
* terminate_walk().
*/
static bool try_to_unlazy(struct nameidata *nd)
{
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (unlikely(!legitimize_links(nd)))
goto out1;
if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
goto out;
if (unlikely(!legitimize_root(nd)))
goto out;
leave_rcu(nd);
BUG_ON(nd->inode != parent->d_inode);
return true;
out1:
nd->path.mnt = NULL;
nd->path.dentry = NULL;
out:
leave_rcu(nd);
return false;
}
/**
* try_to_unlazy_next - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* @dentry: next dentry to step into
* Returns: true on success, false on failure
*
* Similar to try_to_unlazy(), but here we have the next dentry already
* picked by rcu-walk and want to legitimize that in addition to the current
* nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context.
* Nothing should touch nameidata between try_to_unlazy_next() failure and
* terminate_walk().
*/
static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry)
{
int res;
BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(!legitimize_links(nd)))
goto out2;
res = __legitimize_mnt(nd->path.mnt, nd->m_seq);
if (unlikely(res)) {
if (res > 0)
goto out2;
goto out1;
}
if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
goto out1;
/*
* We need to move both the parent and the dentry from the RCU domain
* to be properly refcounted. And the sequence number in the dentry
* validates *both* dentry counters, since we checked the sequence
* number of the parent after we got the child sequence number. So we
* know the parent must still be valid if the child sequence number is
*/
if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
goto out;
if (read_seqcount_retry(&dentry->d_seq, nd->next_seq))
goto out_dput;
/*
* Sequence counts matched. Now make sure that the root is
* still valid and get it if required.
*/
if (unlikely(!legitimize_root(nd)))
goto out_dput;
leave_rcu(nd);
return true;
out2:
nd->path.mnt = NULL;
out1:
nd->path.dentry = NULL;
out:
leave_rcu(nd);
return false;
out_dput:
leave_rcu(nd);
dput(dentry);
return false;
}
static inline int d_revalidate(struct inode *dir, const struct qstr *name,
struct dentry *dentry, unsigned int flags)
{
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
return dentry->d_op->d_revalidate(dir, name, dentry, flags);
else
return 1;
}
/**
* complete_walk - successful completion of path walk
* @nd: pointer nameidata
*
* If we had been in RCU mode, drop out of it and legitimize nd->path.
* Revalidate the final result, unless we'd already done that during
* the path walk or the filesystem doesn't ask for it. Return 0 on
* success, -error on failure. In case of failure caller does not
* need to drop nd->path.
*/
static int complete_walk(struct nameidata *nd)
{
struct dentry *dentry = nd->path.dentry;
int status;
if (nd->flags & LOOKUP_RCU) {
/*
* We don't want to zero nd->root for scoped-lookups or
* externally-managed nd->root.
*/
if (!(nd->state & ND_ROOT_PRESET))
if (!(nd->flags & LOOKUP_IS_SCOPED))
nd->root.mnt = NULL;
nd->flags &= ~LOOKUP_CACHED;
if (!try_to_unlazy(nd))
return -ECHILD;
}
if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
/*
* While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't
* ever step outside the root during lookup" and should already
* be guaranteed by the rest of namei, we want to avoid a namei
* BUG resulting in userspace being given a path that was not
* scoped within the root at some point during the lookup.
*
* So, do a final sanity-check to make sure that in the
* worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED)
* we won't silently return an fd completely outside of the
* requested root to userspace.
*
* Userspace could move the path outside the root after this
* check, but as discussed elsewhere this is not a concern (the
* resolved file was inside the root at some point).
*/
if (!path_is_under(&nd->path, &nd->root))
return -EXDEV;
}
if (likely(!(nd->state & ND_JUMPED)))
return 0;
if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
return 0;
status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
if (!status)
status = -ESTALE;
return status;
}
static int set_root(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
/*
* Jumping to the real root in a scoped-lookup is a BUG in namei, but we
* still have to ensure it doesn't happen because it will cause a breakout
* from the dirfd.
*/
if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED))
return -ENOTRECOVERABLE;
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq));
} else {
get_fs_root(fs, &nd->root);
nd->state |= ND_ROOT_GRABBED;
}
return 0;
}
static int nd_jump_root(struct nameidata *nd)
{ if (unlikely(nd->flags & LOOKUP_BENEATH))
return -EXDEV;
if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
/* Absolute path arguments to path_init() are allowed. */
if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
return -EXDEV;
}
if (!nd->root.mnt) {
int error = set_root(nd);
if (error)
return error;
}
if (nd->flags & LOOKUP_RCU) {
struct dentry *d;
nd->path = nd->root;
d = nd->path.dentry;
nd->inode = d->d_inode;
nd->seq = nd->root_seq;
if (read_seqcount_retry(&d->d_seq, nd->seq))
return -ECHILD;
} else {
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
nd->state |= ND_JUMPED;
return 0;
}
/*
* Helper to directly jump to a known parsed path from ->get_link,
* caller must have taken a reference to path beforehand.
*/
int nd_jump_link(const struct path *path)
{
int error = -ELOOP;
struct nameidata *nd = current->nameidata;
if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
goto err;
error = -EXDEV;
if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
if (nd->path.mnt != path->mnt)
goto err;
}
/* Not currently safe for scoped-lookups. */
if (unlikely(nd->flags & LOOKUP_IS_SCOPED))
goto err;
path_put(&nd->path);
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->state |= ND_JUMPED;
return 0;
err:
path_put(path);
return error;
}
static inline void put_link(struct nameidata *nd)
{
struct saved *last = nd->stack + --nd->depth;
do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link);
}
static int sysctl_protected_symlinks __read_mostly;
static int sysctl_protected_hardlinks __read_mostly;
static int sysctl_protected_fifos __read_mostly;
static int sysctl_protected_regular __read_mostly;
#ifdef CONFIG_SYSCTL
static const struct ctl_table namei_sysctls[] = {
{
.procname = "protected_symlinks",
.data = &sysctl_protected_symlinks,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "protected_hardlinks",
.data = &sysctl_protected_hardlinks,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "protected_fifos",
.data = &sysctl_protected_fifos,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "protected_regular",
.data = &sysctl_protected_regular,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
};
static int __init init_fs_namei_sysctls(void)
{
register_sysctl_init("fs", namei_sysctls);
return 0;
}
fs_initcall(init_fs_namei_sysctls);
#endif /* CONFIG_SYSCTL */
/**
* may_follow_link - Check symlink following for unsafe situations
* @nd: nameidata pathwalk data
* @inode: Used for idmapping.
*
* In the case of the sysctl_protected_symlinks sysctl being enabled,
* CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
* in a sticky world-writable directory. This is to protect privileged
* processes from failing races against path names that may change out
* from under them by way of other users creating malicious symlinks.
* It will permit symlinks to be followed only when outside a sticky
* world-writable directory, or when the uid of the symlink and follower
* match, or when the directory owner matches the symlink's owner.
*
* Returns 0 if following the symlink is allowed, -ve on error.
*/
static inline int may_follow_link(struct nameidata *nd, const struct inode *inode)
{
struct mnt_idmap *idmap;
vfsuid_t vfsuid;
if (!sysctl_protected_symlinks)
return 0;
idmap = mnt_idmap(nd->path.mnt);
vfsuid = i_uid_into_vfsuid(idmap, inode);
/* Allowed if owner and follower match. */
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
return 0;
/* Allowed if parent directory not sticky and world-writable. */
if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
return 0;
/* Allowed if parent directory and link owner match. */
if (vfsuid_valid(nd->dir_vfsuid) && vfsuid_eq(nd->dir_vfsuid, vfsuid))
return 0;
if (nd->flags & LOOKUP_RCU)
return -ECHILD;
audit_inode(nd->name, nd->stack[0].link.dentry, 0);
audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link");
return -EACCES;
}
/**
* safe_hardlink_source - Check for safe hardlink conditions
* @idmap: idmap of the mount the inode was found from
* @inode: the source inode to hardlink from
*
* Return false if at least one of the following conditions:
* - inode is not a regular file
* - inode is setuid
* - inode is setgid and group-exec
* - access failure for read and write
*
* Otherwise returns true.
*/
static bool safe_hardlink_source(struct mnt_idmap *idmap,
struct inode *inode)
{
umode_t mode = inode->i_mode;
/* Special files should not get pinned to the filesystem. */
if (!S_ISREG(mode))
return false;
/* Setuid files should not get pinned to the filesystem. */
if (mode & S_ISUID)
return false;
/* Executable setgid files should not get pinned to the filesystem. */
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
return false;
/* Hardlinking to unreadable or unwritable sources is dangerous. */
if (inode_permission(idmap, inode, MAY_READ | MAY_WRITE))
return false;
return true;
}
/**
* may_linkat - Check permissions for creating a hardlink
* @idmap: idmap of the mount the inode was found from
* @link: the source to hardlink from
*
* Block hardlink when all of:
* - sysctl_protected_hardlinks enabled
* - fsuid does not match inode
* - hardlink source is unsafe (see safe_hardlink_source() above)
* - not CAP_FOWNER in a namespace with the inode owner uid mapped
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*
* Returns 0 if successful, -ve on error.
*/
int may_linkat(struct mnt_idmap *idmap, const struct path *link)
{
struct inode *inode = link->dentry->d_inode;
/* Inode writeback is not safe when the uid or gid are invalid. */
if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) ||
!vfsgid_valid(i_gid_into_vfsgid(idmap, inode)))
return -EOVERFLOW;
if (!sysctl_protected_hardlinks)
return 0;
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
if (safe_hardlink_source(idmap, inode) ||
inode_owner_or_capable(idmap, inode))
return 0;
audit_log_path_denied(AUDIT_ANOM_LINK, "linkat");
return -EPERM;
}
/**
* may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
* should be allowed, or not, on files that already
* exist.
* @idmap: idmap of the mount the inode was found from
* @nd: nameidata pathwalk data
* @inode: the inode of the file to open
*
* Block an O_CREAT open of a FIFO (or a regular file) when:
* - sysctl_protected_fifos (or sysctl_protected_regular) is enabled
* - the file already exists
* - we are in a sticky directory
* - we don't own the file
* - the owner of the directory doesn't own the file
* - the directory is world writable
* If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2
* the directory doesn't have to be world writable: being group writable will
* be enough.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*
* Returns 0 if the open is allowed, -ve on error.
*/
static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd,
struct inode *const inode)
{
umode_t dir_mode = nd->dir_mode;
vfsuid_t dir_vfsuid = nd->dir_vfsuid, i_vfsuid;
if (likely(!(dir_mode & S_ISVTX)))
return 0;
if (S_ISREG(inode->i_mode) && !sysctl_protected_regular)
return 0;
if (S_ISFIFO(inode->i_mode) && !sysctl_protected_fifos)
return 0;
i_vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq(i_vfsuid, dir_vfsuid))
return 0;
if (vfsuid_eq_kuid(i_vfsuid, current_fsuid()))
return 0;
if (likely(dir_mode & 0002)) {
audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create");
return -EACCES;
}
if (dir_mode & 0020) { if (sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) {
audit_log_path_denied(AUDIT_ANOM_CREAT,
"sticky_create_fifo");
return -EACCES;
}
if (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode)) {
audit_log_path_denied(AUDIT_ANOM_CREAT,
"sticky_create_regular");
return -EACCES;
}
}
return 0;
}
/*
* follow_up - Find the mountpoint of path's vfsmount
*
* Given a path, find the mountpoint of its source file system.
* Replace @path with the path of the mountpoint in the parent mount.
* Up is towards /.
*
* Return 1 if we went up a level and 0 if we were already at the
* root.
*/
int follow_up(struct path *path)
{
struct mount *mnt = real_mount(path->mnt);
struct mount *parent;
struct dentry *mountpoint;
read_seqlock_excl(&mount_lock);
parent = mnt->mnt_parent;
if (parent == mnt) {
read_sequnlock_excl(&mount_lock);
return 0;
}
mntget(&parent->mnt);
mountpoint = dget(mnt->mnt_mountpoint);
read_sequnlock_excl(&mount_lock);
dput(path->dentry);
path->dentry = mountpoint;
mntput(path->mnt);
path->mnt = &parent->mnt;
return 1;
}
EXPORT_SYMBOL(follow_up);
static bool choose_mountpoint_rcu(struct mount *m, const struct path *root,
struct path *path, unsigned *seqp)
{
while (mnt_has_parent(m)) {
struct dentry *mountpoint = m->mnt_mountpoint;
m = m->mnt_parent;
if (unlikely(root->dentry == mountpoint &&
root->mnt == &m->mnt))
break;
if (mountpoint != m->mnt.mnt_root) {
path->mnt = &m->mnt;
path->dentry = mountpoint;
*seqp = read_seqcount_begin(&mountpoint->d_seq);
return true;
}
}
return false;
}
static bool choose_mountpoint(struct mount *m, const struct path *root,
struct path *path)
{
bool found;
rcu_read_lock();
while (1) {
unsigned seq, mseq = read_seqbegin(&mount_lock);
found = choose_mountpoint_rcu(m, root, path, &seq);
if (unlikely(!found)) {
if (!read_seqretry(&mount_lock, mseq))
break;
} else {
if (likely(__legitimize_path(path, seq, mseq)))
break;
rcu_read_unlock();
path_put(path);
rcu_read_lock();
}
}
rcu_read_unlock();
return found;
}
/*
* Perform an automount
* - return -EISDIR to tell follow_managed() to stop and return the path we
* were called with.
*/
static int follow_automount(struct path *path, int *count, unsigned lookup_flags)
{
struct dentry *dentry = path->dentry;
/* We don't want to mount if someone's just doing a stat -
* unless they're stat'ing a directory and appended a '/' to
* the name.
*
* We do, however, want to mount if someone wants to open or
* create a file of any type under the mountpoint, wants to
* traverse through the mountpoint or wants to open the
* mounted directory. Also, autofs may mark negative dentries
* as being automount points. These will need the attentions
* of the daemon to instantiate them before they can be used.
*/
if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
dentry->d_inode)
return -EISDIR;
if (count && (*count)++ >= MAXSYMLINKS)
return -ELOOP;
return finish_automount(dentry->d_op->d_automount(path), path);
}
/*
* mount traversal - out-of-line part. One note on ->d_flags accesses -
* dentries are pinned but not locked here, so negative dentry can go
* positive right under us. Use of smp_load_acquire() provides a barrier
* sufficient for ->d_inode and ->d_flags consistency.
*/
static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped,
int *count, unsigned lookup_flags)
{
struct vfsmount *mnt = path->mnt;
bool need_mntput = false;
int ret = 0;
while (flags & DCACHE_MANAGED_DENTRY) {
/* Allow the filesystem to manage the transit without i_mutex
* being held. */
if (flags & DCACHE_MANAGE_TRANSIT) {
ret = path->dentry->d_op->d_manage(path, false);
flags = smp_load_acquire(&path->dentry->d_flags);
if (ret < 0)
break;
}
if (flags & DCACHE_MOUNTED) { // something's mounted on it..
struct vfsmount *mounted = lookup_mnt(path);
if (mounted) { // ... in our namespace
dput(path->dentry);
if (need_mntput) mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
// here we know it's positive
flags = path->dentry->d_flags;
need_mntput = true;
continue;
}
}
if (!(flags & DCACHE_NEED_AUTOMOUNT))
break;
// uncovered automount point
ret = follow_automount(path, count, lookup_flags);
flags = smp_load_acquire(&path->dentry->d_flags);
if (ret < 0)
break;
}
if (ret == -EISDIR)
ret = 0;
// possible if you race with several mount --move
if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT;
*jumped = need_mntput;
return ret;
}
static inline int traverse_mounts(struct path *path, bool *jumped,
int *count, unsigned lookup_flags)
{
unsigned flags = smp_load_acquire(&path->dentry->d_flags);
/* fastpath */
if (likely(!(flags & DCACHE_MANAGED_DENTRY))) {
*jumped = false;
if (unlikely(d_flags_negative(flags)))
return -ENOENT;
return 0;
}
return __traverse_mounts(path, flags, jumped, count, lookup_flags);
}
int follow_down_one(struct path *path)
{
struct vfsmount *mounted;
mounted = lookup_mnt(path);
if (mounted) {
dput(path->dentry);
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
return 1;
}
return 0;
}
EXPORT_SYMBOL(follow_down_one);
/*
* Follow down to the covering mount currently visible to userspace. At each
* point, the filesystem owning that dentry may be queried as to whether the
* caller is permitted to proceed or not.
*/
int follow_down(struct path *path, unsigned int flags)
{
struct vfsmount *mnt = path->mnt;
bool jumped;
int ret = traverse_mounts(path, &jumped, NULL, flags);
if (path->mnt != mnt)
mntput(mnt);
return ret;
}
EXPORT_SYMBOL(follow_down);
/*
* Try to skip to top of mountpoint pile in rcuwalk mode. Fail if
* we meet a managed dentry that would need blocking.
*/
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path)
{
struct dentry *dentry = path->dentry;
unsigned int flags = dentry->d_flags;
if (likely(!(flags & DCACHE_MANAGED_DENTRY)))
return true;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return false;
for (;;) {
/*
* Don't forget we might have a non-mountpoint managed dentry
* that wants to block transit.
*/
if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) {
int res = dentry->d_op->d_manage(path, true);
if (res)
return res == -EISDIR;
flags = dentry->d_flags;
}
if (flags & DCACHE_MOUNTED) {
struct mount *mounted = __lookup_mnt(path->mnt, dentry);
if (mounted) {
path->mnt = &mounted->mnt;
dentry = path->dentry = mounted->mnt.mnt_root;
nd->state |= ND_JUMPED;
nd->next_seq = read_seqcount_begin(&dentry->d_seq);
flags = dentry->d_flags;
// makes sure that non-RCU pathwalk could reach
// this state.
if (read_seqretry(&mount_lock, nd->m_seq))
return false;
continue;
}
if (read_seqretry(&mount_lock, nd->m_seq))
return false;
}
return !(flags & DCACHE_NEED_AUTOMOUNT);
}
}
static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
struct path *path)
{
bool jumped;
int ret;
path->mnt = nd->path.mnt;
path->dentry = dentry;
if (nd->flags & LOOKUP_RCU) {
unsigned int seq = nd->next_seq;
if (likely(__follow_mount_rcu(nd, path)))
return 0;
// *path and nd->next_seq might've been clobbered
path->mnt = nd->path.mnt;
path->dentry = dentry;
nd->next_seq = seq;
if (!try_to_unlazy_next(nd, dentry))
return -ECHILD;
}
ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV))
ret = -EXDEV;
else
nd->state |= ND_JUMPED;
}
if (unlikely(ret)) {
dput(path->dentry);
if (path->mnt != nd->path.mnt) mntput(path->mnt);
}
return ret;
}
/*
* This looks up the name in dcache and possibly revalidates the found dentry.
* NULL is returned if the dentry does not exist in the cache.
*/
static struct dentry *lookup_dcache(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct dentry *dentry = d_lookup(dir, name);
if (dentry) { int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) {
if (!error)
d_invalidate(dentry); dput(dentry);
return ERR_PTR(error);
}
}
return dentry;
}
static struct dentry *lookup_one_qstr_excl_raw(const struct qstr *name,
struct dentry *base,
unsigned int flags)
{
struct dentry *dentry;
struct dentry *old;
struct inode *dir;
dentry = lookup_dcache(name, base, flags);
if (dentry)
return dentry;
/* Don't create child dentry for a dead directory. */
dir = base->d_inode;
if (unlikely(IS_DEADDIR(dir)))
return ERR_PTR(-ENOENT);
dentry = d_alloc(base, name);
if (unlikely(!dentry))
return ERR_PTR(-ENOMEM);
old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
dput(dentry);
dentry = old;
}
return dentry;
}
/*
* Parent directory has inode locked exclusive. This is one
* and only case when ->lookup() gets called on non in-lookup
* dentries - as the matter of fact, this only gets called
* when directory is guaranteed to have no in-lookup children
* at all.
* Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
* Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
*/
struct dentry *lookup_one_qstr_excl(const struct qstr *name,
struct dentry *base, unsigned int flags)
{
struct dentry *dentry;
dentry = lookup_one_qstr_excl_raw(name, base, flags);
if (IS_ERR(dentry))
return dentry;
if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) {
dput(dentry);
return ERR_PTR(-ENOENT);
}
if (d_is_positive(dentry) && (flags & LOOKUP_EXCL)) {
dput(dentry);
return ERR_PTR(-EEXIST);
}
return dentry;
}
EXPORT_SYMBOL(lookup_one_qstr_excl);
/**
* lookup_fast - do fast lockless (but racy) lookup of a dentry
* @nd: current nameidata
*
* Do a fast, but racy lookup in the dcache for the given dentry, and
* revalidate it. Returns a valid dentry pointer or NULL if one wasn't
* found. On error, an ERR_PTR will be returned.
*
* If this function returns a valid dentry and the walk is no longer
* lazy, the dentry will carry a reference that must later be put. If
* RCU mode is still in force, then this is not the case and the dentry
* must be legitimized before use. If this returns NULL, then the walk
* will no longer be in RCU mode.
*/
static struct dentry *lookup_fast(struct nameidata *nd)
{
struct dentry *dentry, *parent = nd->path.dentry;
int status = 1;
/*
* Rename seqlock is not required here because in the off chance
* of a false negative due to a concurrent rename, the caller is
* going to fall back to non-racy lookup.
*/
if (nd->flags & LOOKUP_RCU) {
dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq);
if (unlikely(!dentry)) {
if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
return NULL;
}
/*
* This sequence count validates that the parent had no
* changes while we did the lookup of the dentry above.
*/
if (read_seqcount_retry(&parent->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0))
return dentry;
if (!try_to_unlazy_next(nd, dentry))
return ERR_PTR(-ECHILD);
if (status == -ECHILD)
/* we'd been told to redo it in non-rcu mode */
status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags);
} else {
dentry = __d_lookup(parent, &nd->last);
if (unlikely(!dentry))
return NULL;
status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags);
}
if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry);
dput(dentry);
return ERR_PTR(status);
}
return dentry;
}
/* Fast lookup failed, do it the slow way */
static struct dentry *__lookup_slow(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct dentry *dentry, *old;
struct inode *inode = dir->d_inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
/* Don't go there if it's already dead */
if (unlikely(IS_DEADDIR(inode)))
return ERR_PTR(-ENOENT);
again:
dentry = d_alloc_parallel(dir, name, &wq);
if (IS_ERR(dentry))
return dentry;
if (unlikely(!d_in_lookup(dentry))) {
int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) {
if (!error) {
d_invalidate(dentry);
dput(dentry);
goto again;
}
dput(dentry);
dentry = ERR_PTR(error);
}
} else {
old = inode->i_op->lookup(inode, dentry, flags);
d_lookup_done(dentry); if (unlikely(old)) { dput(dentry);
dentry = old;
}
}
return dentry;
}
static struct dentry *lookup_slow(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct inode *inode = dir->d_inode;
struct dentry *res;
inode_lock_shared(inode);
res = __lookup_slow(name, dir, flags);
inode_unlock_shared(inode);
return res;
}
static inline int may_lookup(struct mnt_idmap *idmap,
struct nameidata *restrict nd)
{
int err, mask;
mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0;
err = inode_permission(idmap, nd->inode, mask | MAY_EXEC);
if (likely(!err))
return 0;
// If we failed, and we weren't in LOOKUP_RCU, it's final
if (!(nd->flags & LOOKUP_RCU))
return err;
// Drop out of RCU mode to make sure it wasn't transient
if (!try_to_unlazy(nd))
return -ECHILD; // redo it all non-lazy
if (err != -ECHILD) // hard error
return err;
return inode_permission(idmap, nd->inode, MAY_EXEC);
}
static int reserve_stack(struct nameidata *nd, struct path *link)
{
if (unlikely(nd->total_link_count++ >= MAXSYMLINKS))
return -ELOOP;
if (likely(nd->depth != EMBEDDED_LEVELS))
return 0;
if (likely(nd->stack != nd->internal))
return 0;
if (likely(nd_alloc_stack(nd)))
return 0;
if (nd->flags & LOOKUP_RCU) {
// we need to grab link before we do unlazy. And we can't skip
// unlazy even if we fail to grab the link - cleanup needs it
bool grabbed_link = legitimize_path(nd, link, nd->next_seq);
if (!try_to_unlazy(nd) || !grabbed_link)
return -ECHILD;
if (nd_alloc_stack(nd))
return 0;
}
return -ENOMEM;
}
enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
static const char *pick_link(struct nameidata *nd, struct path *link,
struct inode *inode, int flags)
{
struct saved *last;
const char *res;
int error = reserve_stack(nd, link);
if (unlikely(error)) {
if (!(nd->flags & LOOKUP_RCU))
path_put(link);
return ERR_PTR(error);
}
last = nd->stack + nd->depth++;
last->link = *link;
clear_delayed_call(&last->done);
last->seq = nd->next_seq;
if (flags & WALK_TRAILING) {
error = may_follow_link(nd, inode);
if (unlikely(error))
return ERR_PTR(error);
}
if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) ||
unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW))
return ERR_PTR(-ELOOP);
if (!(nd->flags & LOOKUP_RCU)) {
touch_atime(&last->link);
cond_resched();
} else if (atime_needs_update(&last->link, inode)) {
if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
touch_atime(&last->link);
}
error = security_inode_follow_link(link->dentry, inode,
nd->flags & LOOKUP_RCU);
if (unlikely(error))
return ERR_PTR(error);
res = READ_ONCE(inode->i_link);
if (!res) {
const char * (*get)(struct dentry *, struct inode *,
struct delayed_call *);
get = inode->i_op->get_link;
if (nd->flags & LOOKUP_RCU) {
res = get(NULL, inode, &last->done);
if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd))
res = get(link->dentry, inode, &last->done);
} else {
res = get(link->dentry, inode, &last->done);
}
if (!res)
goto all_done;
if (IS_ERR(res))
return res;
}
if (*res == '/') {
error = nd_jump_root(nd);
if (unlikely(error))
return ERR_PTR(error);
while (unlikely(*++res == '/'))
;
}
if (*res)
return res;
all_done: // pure jump
put_link(nd);
return NULL;
}
/*
* Do we need to follow links? We _really_ want to be able
* to do this check without having to look at inode->i_op,
* so we keep a cache of "no, this doesn't need follow_link"
* for the common case.
*
* NOTE: dentry must be what nd->next_seq had been sampled from.
*/
static const char *step_into(struct nameidata *nd, int flags,
struct dentry *dentry)
{
struct path path;
struct inode *inode;
int err = handle_mounts(nd, dentry, &path); if (err < 0)
return ERR_PTR(err);
inode = path.dentry->d_inode;
if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) ||
(flags & WALK_NOFOLLOW)) {
/* not a symlink or should not follow */
if (nd->flags & LOOKUP_RCU) {
if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
return ERR_PTR(-ECHILD);
if (unlikely(!inode))
return ERR_PTR(-ENOENT);
} else {
dput(nd->path.dentry);
if (nd->path.mnt != path.mnt) mntput(nd->path.mnt);
}
nd->path = path;
nd->inode = inode;
nd->seq = nd->next_seq;
return NULL;
}
if (nd->flags & LOOKUP_RCU) {
/* make sure that d_is_symlink above matches inode */
if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
return ERR_PTR(-ECHILD);
} else {
if (path.mnt == nd->path.mnt) mntget(path.mnt);
}
return pick_link(nd, &path, inode, flags);
}
static struct dentry *follow_dotdot_rcu(struct nameidata *nd)
{
struct dentry *parent, *old;
if (path_equal(&nd->path, &nd->root))
goto in_root;
if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) {
struct path path;
unsigned seq;
if (!choose_mountpoint_rcu(real_mount(nd->path.mnt),
&nd->root, &path, &seq))
goto in_root;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return ERR_PTR(-ECHILD);
nd->path = path;
nd->inode = path.dentry->d_inode;
nd->seq = seq;
// makes sure that non-RCU pathwalk could reach this state
if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
/* we know that mountpoint was pinned */
}
old = nd->path.dentry;
parent = old->d_parent;
nd->next_seq = read_seqcount_begin(&parent->d_seq);
// makes sure that non-RCU pathwalk could reach this state
if (read_seqcount_retry(&old->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
if (unlikely(!path_connected(nd->path.mnt, parent)))
return ERR_PTR(-ECHILD);
return parent;
in_root:
if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-ECHILD);
nd->next_seq = nd->seq;
return nd->path.dentry;
}
static struct dentry *follow_dotdot(struct nameidata *nd)
{
struct dentry *parent;
if (path_equal(&nd->path, &nd->root))
goto in_root;
if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) {
struct path path;
if (!choose_mountpoint(real_mount(nd->path.mnt),
&nd->root, &path))
goto in_root;
path_put(&nd->path);
nd->path = path;
nd->inode = path.dentry->d_inode;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return ERR_PTR(-EXDEV);
}
/* rare case of legitimate dget_parent()... */
parent = dget_parent(nd->path.dentry);
if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent);
return ERR_PTR(-ENOENT);
}
return parent;
in_root:
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-EXDEV);
return dget(nd->path.dentry);
}
static const char *handle_dots(struct nameidata *nd, int type)
{ if (type == LAST_DOTDOT) {
const char *error = NULL;
struct dentry *parent;
if (!nd->root.mnt) {
error = ERR_PTR(set_root(nd));
if (error)
return error;
}
if (nd->flags & LOOKUP_RCU)
parent = follow_dotdot_rcu(nd);
else
parent = follow_dotdot(nd); if (IS_ERR(parent))
return ERR_CAST(parent);
error = step_into(nd, WALK_NOFOLLOW, parent);
if (unlikely(error))
return error;
if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
/*
* If there was a racing rename or mount along our
* path, then we can't be sure that ".." hasn't jumped
* above nd->root (and so userspace should retry or use
* some fallback).
*/
smp_rmb();
if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))
return ERR_PTR(-EAGAIN);
if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))
return ERR_PTR(-EAGAIN);
}
}
return NULL;
}
static const char *walk_component(struct nameidata *nd, int flags)
{
struct dentry *dentry;
/*
* "." and ".." are special - ".." especially so because it has
* to be able to know about the current root directory and
* parent relationships.
*/
if (unlikely(nd->last_type != LAST_NORM)) {
if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type);
}
dentry = lookup_fast(nd);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (unlikely(!dentry)) {
dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
}
if (!(flags & WALK_MORE) && nd->depth) put_link(nd);
return step_into(nd, flags, dentry);
}
/*
* We can do the critical dentry name comparison and hashing
* operations one word at a time, but we are limited to:
*
* - Architectures with fast unaligned word accesses. We could
* do a "get_unaligned()" if this helps and is sufficiently
* fast.
*
* - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
* do not trap on the (extremely unlikely) case of a page
* crossing operation.
*
* - Furthermore, we need an efficient 64-bit compile for the
* 64-bit case in order to generate the "number of bytes in
* the final mask". Again, that could be replaced with a
* efficient population count instruction or similar.
*/
#ifdef CONFIG_DCACHE_WORD_ACCESS
#include <asm/word-at-a-time.h>
#ifdef HASH_MIX
/* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */
#elif defined(CONFIG_64BIT)
/*
* Register pressure in the mixing function is an issue, particularly
* on 32-bit x86, but almost any function requires one state value and
* one temporary. Instead, use a function designed for two state values
* and no temporaries.
*
* This function cannot create a collision in only two iterations, so
* we have two iterations to achieve avalanche. In those two iterations,
* we have six layers of mixing, which is enough to spread one bit's
* influence out to 2^6 = 64 state bits.
*
* Rotate constants are scored by considering either 64 one-bit input
* deltas or 64*63/2 = 2016 two-bit input deltas, and finding the
* probability of that delta causing a change to each of the 128 output
* bits, using a sample of random initial states.
*
* The Shannon entropy of the computed probabilities is then summed
* to produce a score. Ideally, any input change has a 50% chance of
* toggling any given output bit.
*
* Mixing scores (in bits) for (12,45):
* Input delta: 1-bit 2-bit
* 1 round: 713.3 42542.6
* 2 rounds: 2753.7 140389.8
* 3 rounds: 5954.1 233458.2
* 4 rounds: 7862.6 256672.2
* Perfect: 8192 258048
* (64*128) (64*63/2 * 128)
*/
#define HASH_MIX(x, y, a) \
( x ^= (a), \
y ^= x, x = rol64(x,12),\
x += y, y = rol64(y,45),\
y *= 9 )
/*
* Fold two longs into one 32-bit hash value. This must be fast, but
* latency isn't quite as critical, as there is a fair bit of additional
* work done before the hash value is used.
*/
static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
y ^= x * GOLDEN_RATIO_64;
y *= GOLDEN_RATIO_64;
return y >> 32;
}
#else /* 32-bit case */
/*
* Mixing scores (in bits) for (7,20):
* Input delta: 1-bit 2-bit
* 1 round: 330.3 9201.6
* 2 rounds: 1246.4 25475.4
* 3 rounds: 1907.1 31295.1
* 4 rounds: 2042.3 31718.6
* Perfect: 2048 31744
* (32*64) (32*31/2 * 64)
*/
#define HASH_MIX(x, y, a) \
( x ^= (a), \
y ^= x, x = rol32(x, 7),\
x += y, y = rol32(y,20),\
y *= 9 )
static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
/* Use arch-optimized multiply if one exists */
return __hash_32(y ^ __hash_32(x));
}
#endif
/*
* Return the hash of a string of known length. This is carfully
* designed to match hash_name(), which is the more critical function.
* In particular, we must end by hashing a final word containing 0..7
* payload bytes, to match the way that hash_name() iterates until it
* finds the delimiter after the name.
*/
unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
{
unsigned long a, x = 0, y = (unsigned long)salt;
for (;;) {
if (!len)
goto done;
a = load_unaligned_zeropad(name);
if (len < sizeof(unsigned long))
break;
HASH_MIX(x, y, a);
name += sizeof(unsigned long);
len -= sizeof(unsigned long);
}
x ^= a & bytemask_from_count(len);
done:
return fold_hash(x, y);
}
EXPORT_SYMBOL(full_name_hash);
/* Return the "hash_len" (hash and length) of a null-terminated string */
u64 hashlen_string(const void *salt, const char *name)
{
unsigned long a = 0, x = 0, y = (unsigned long)salt;
unsigned long adata, mask, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
len = 0;
goto inside;
do {
HASH_MIX(x, y, a);
len += sizeof(unsigned long);
inside:
a = load_unaligned_zeropad(name+len);
} while (!has_zero(a, &adata, &constants));
adata = prep_zero_mask(a, adata, &constants);
mask = create_zero_mask(adata);
x ^= a & zero_bytemask(mask);
return hashlen_create(fold_hash(x, y), len + find_zero(mask));
}
EXPORT_SYMBOL(hashlen_string);
/*
* Calculate the length and hash of the path component, and
* return the length as the result.
*/
static inline const char *hash_name(struct nameidata *nd,
const char *name,
unsigned long *lastword)
{
unsigned long a, b, x, y = (unsigned long)nd->path.dentry;
unsigned long adata, bdata, mask, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
/*
* The first iteration is special, because it can result in
* '.' and '..' and has no mixing other than the final fold.
*/
a = load_unaligned_zeropad(name);
b = a ^ REPEAT_BYTE('/');
if (has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)) {
adata = prep_zero_mask(a, adata, &constants);
bdata = prep_zero_mask(b, bdata, &constants);
mask = create_zero_mask(adata | bdata);
a &= zero_bytemask(mask);
*lastword = a;
len = find_zero(mask);
nd->last.hash = fold_hash(a, y);
nd->last.len = len;
return name + len;
}
len = 0;
x = 0;
do {
HASH_MIX(x, y, a);
len += sizeof(unsigned long);
a = load_unaligned_zeropad(name+len);
b = a ^ REPEAT_BYTE('/');
} while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));
adata = prep_zero_mask(a, adata, &constants);
bdata = prep_zero_mask(b, bdata, &constants);
mask = create_zero_mask(adata | bdata);
a &= zero_bytemask(mask);
x ^= a;
len += find_zero(mask);
*lastword = 0; // Multi-word components cannot be DOT or DOTDOT
nd->last.hash = fold_hash(x, y);
nd->last.len = len;
return name + len;
}
/*
* Note that the 'last' word is always zero-masked, but
* was loaded as a possibly big-endian word.
*/
#ifdef __BIG_ENDIAN
#define LAST_WORD_IS_DOT (0x2eul << (BITS_PER_LONG-8))
#define LAST_WORD_IS_DOTDOT (0x2e2eul << (BITS_PER_LONG-16))
#endif
#else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */
/* Return the hash of a string of known length */
unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
{
unsigned long hash = init_name_hash(salt);
while (len--)
hash = partial_name_hash((unsigned char)*name++, hash);
return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);
/* Return the "hash_len" (hash and length) of a null-terminated string */
u64 hashlen_string(const void *salt, const char *name)
{
unsigned long hash = init_name_hash(salt);
unsigned long len = 0, c;
c = (unsigned char)*name;
while (c) {
len++;
hash = partial_name_hash(c, hash);
c = (unsigned char)name[len];
}
return hashlen_create(end_name_hash(hash), len);
}
EXPORT_SYMBOL(hashlen_string);
/*
* We know there's a real path component here of at least
* one character.
*/
static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword)
{
unsigned long hash = init_name_hash(nd->path.dentry);
unsigned long len = 0, c, last = 0;
c = (unsigned char)*name;
do {
last = (last << 8) + c;
len++;
hash = partial_name_hash(c, hash);
c = (unsigned char)name[len];
} while (c && c != '/');
// This is reliable for DOT or DOTDOT, since the component
// cannot contain NUL characters - top bits being zero means
// we cannot have had any other pathnames.
*lastword = last;
nd->last.hash = end_name_hash(hash);
nd->last.len = len;
return name + len;
}
#endif
#ifndef LAST_WORD_IS_DOT
#define LAST_WORD_IS_DOT 0x2e
#define LAST_WORD_IS_DOTDOT 0x2e2e
#endif
/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
*
* Returns 0 and nd will have valid dentry and mnt on success.
* Returns error and drops reference to input namei data on failure.
*/
static int link_path_walk(const char *name, struct nameidata *nd)
{
int depth = 0; // depth <= nd->depth
int err;
nd->last_type = LAST_ROOT;
nd->flags |= LOOKUP_PARENT;
if (IS_ERR(name))
return PTR_ERR(name);
while (*name=='/')
name++;
if (!*name) {
nd->dir_mode = 0; // short-circuit the 'hardening' idiocy
return 0;
}
/* At this point we know we have a real path component. */
for(;;) {
struct mnt_idmap *idmap;
const char *link;
unsigned long lastword;
idmap = mnt_idmap(nd->path.mnt);
err = may_lookup(idmap, nd); if (err)
return err;
nd->last.name = name;
name = hash_name(nd, name, &lastword); switch(lastword) {
case LAST_WORD_IS_DOTDOT:
nd->last_type = LAST_DOTDOT;
nd->state |= ND_JUMPED;
break;
case LAST_WORD_IS_DOT:
nd->last_type = LAST_DOT;
break;
default:
nd->last_type = LAST_NORM;
nd->state &= ~ND_JUMPED;
struct dentry *parent = nd->path.dentry;
if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
err = parent->d_op->d_hash(parent, &nd->last);
if (err < 0)
return err;
}
}
if (!*name)
goto OK;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
*/
do {
name++;
} while (unlikely(*name == '/'));
if (unlikely(!*name)) {
OK:
/* pathname or trailing symlink, done */
if (!depth) {
nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode);
nd->dir_mode = nd->inode->i_mode;
nd->flags &= ~LOOKUP_PARENT;
return 0;
}
/* last component of nested symlink */
name = nd->stack[--depth].name;
link = walk_component(nd, 0);
} else {
/* not the last component */
link = walk_component(nd, WALK_MORE);
}
if (unlikely(link)) {
if (IS_ERR(link))
return PTR_ERR(link);
/* a symlink to follow */
nd->stack[depth++].name = name;
name = link;
continue;
}
if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd))
return -ECHILD;
}
return -ENOTDIR;
}
}
}
/* must be paired with terminate_walk() */
static const char *path_init(struct nameidata *nd, unsigned flags)
{
int error;
const char *s = nd->pathname;
/* LOOKUP_CACHED requires RCU, ask caller to retry */
if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)
return ERR_PTR(-EAGAIN);
if (!*s)
flags &= ~LOOKUP_RCU;
if (flags & LOOKUP_RCU)
rcu_read_lock();
else
nd->seq = nd->next_seq = 0;
nd->flags = flags;
nd->state |= ND_JUMPED;
nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
smp_rmb();
if (nd->state & ND_ROOT_PRESET) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
if (*s && unlikely(!d_can_lookup(root)))
return ERR_PTR(-ENOTDIR);
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
} else {
path_get(&nd->path);
}
return s;
}
nd->root.mnt = NULL;
/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
error = nd_jump_root(nd);
if (unlikely(error)) return ERR_PTR(error);
return s;
}
/* Relative pathname -- get the starting-point it is relative to. */
if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->path = fs->pwd;
nd->inode = nd->path.dentry->d_inode;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq));
} else {
get_fs_pwd(current->fs, &nd->path);
nd->inode = nd->path.dentry->d_inode;
}
} else {
/* Caller must check execute permissions on the starting path component */
CLASS(fd_raw, f)(nd->dfd);
struct dentry *dentry;
if (fd_empty(f))
return ERR_PTR(-EBADF);
if (flags & LOOKUP_LINKAT_EMPTY) { if (fd_file(f)->f_cred != current_cred() &&
!ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH))
return ERR_PTR(-ENOENT);
}
dentry = fd_file(f)->f_path.dentry;
if (*s && unlikely(!d_can_lookup(dentry)))
return ERR_PTR(-ENOTDIR);
nd->path = fd_file(f)->f_path;
if (flags & LOOKUP_RCU) {
nd->inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
}
/* For scoped-lookups we need to set the root to the dirfd as well. */
if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq;
} else {
path_get(&nd->root);
nd->state |= ND_ROOT_GRABBED;
}
}
return s;
}
static inline const char *lookup_last(struct nameidata *nd)
{
if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
return walk_component(nd, WALK_TRAILING);
}
static int handle_lookup_down(struct nameidata *nd)
{
if (!(nd->flags & LOOKUP_RCU))
dget(nd->path.dentry);
nd->next_seq = nd->seq;
return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
}
/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
const char *s = path_init(nd, flags);
int err;
if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
err = handle_lookup_down(nd);
if (unlikely(err < 0)) s = ERR_PTR(err);
}
while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL)
;
if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
err = handle_lookup_down(nd);
nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please...
}
if (!err)
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
terminate_walk(nd);
return err;
}
int filename_lookup(int dfd, struct filename *name, unsigned flags,
struct path *path, struct path *root)
{
int retval;
struct nameidata nd;
if (IS_ERR(name))
return PTR_ERR(name);
set_nameidata(&nd, dfd, name, root);
retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
if (unlikely(retval == -ECHILD))
retval = path_lookupat(&nd, flags, path);
if (unlikely(retval == -ESTALE))
retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);
if (likely(!retval))
audit_inode(name, path->dentry,
flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0);
restore_nameidata();
return retval;
}
/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_parentat(struct nameidata *nd, unsigned flags,
struct path *parent)
{
const char *s = path_init(nd, flags);
int err = link_path_walk(s, nd);
if (!err)
err = complete_walk(nd);
if (!err) {
*parent = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
terminate_walk(nd);
return err;
}
/* Note: this does not consume "name" */
static int __filename_parentat(int dfd, struct filename *name,
unsigned int flags, struct path *parent,
struct qstr *last, int *type,
const struct path *root)
{
int retval;
struct nameidata nd;
if (IS_ERR(name))
return PTR_ERR(name);
set_nameidata(&nd, dfd, name, root);
retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
if (unlikely(retval == -ECHILD))
retval = path_parentat(&nd, flags, parent);
if (unlikely(retval == -ESTALE))
retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent);
if (likely(!retval)) {
*last = nd.last;
*type = nd.last_type;
audit_inode(name, parent->dentry, AUDIT_INODE_PARENT);
}
restore_nameidata();
return retval;
}
static int filename_parentat(int dfd, struct filename *name,
unsigned int flags, struct path *parent,
struct qstr *last, int *type)
{
return __filename_parentat(dfd, name, flags, parent, last, type, NULL);
}
/* does lookup, returns the object with parent locked */
static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path)
{
struct path parent_path __free(path_put) = {};
struct dentry *d;
struct qstr last;
int type, error;
error = filename_parentat(dfd, name, 0, &parent_path, &last, &type);
if (error)
return ERR_PTR(error);
if (unlikely(type != LAST_NORM))
return ERR_PTR(-EINVAL);
inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
d = lookup_one_qstr_excl(&last, parent_path.dentry, 0);
if (IS_ERR(d)) {
inode_unlock(parent_path.dentry->d_inode);
return d;
}
path->dentry = no_free_ptr(parent_path.dentry);
path->mnt = no_free_ptr(parent_path.mnt);
return d;
}
struct dentry *kern_path_locked_negative(const char *name, struct path *path)
{
struct path parent_path __free(path_put) = {};
struct filename *filename __free(putname) = getname_kernel(name);
struct dentry *d;
struct qstr last;
int type, error;
error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type);
if (error)
return ERR_PTR(error);
if (unlikely(type != LAST_NORM))
return ERR_PTR(-EINVAL);
inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
d = lookup_one_qstr_excl_raw(&last, parent_path.dentry, 0);
if (IS_ERR(d)) {
inode_unlock(parent_path.dentry->d_inode);
return d;
}
path->dentry = no_free_ptr(parent_path.dentry);
path->mnt = no_free_ptr(parent_path.mnt);
return d;
}
struct dentry *kern_path_locked(const char *name, struct path *path)
{
struct filename *filename = getname_kernel(name);
struct dentry *res = __kern_path_locked(AT_FDCWD, filename, path);
putname(filename);
return res;
}
struct dentry *user_path_locked_at(int dfd, const char __user *name, struct path *path)
{
struct filename *filename = getname(name);
struct dentry *res = __kern_path_locked(dfd, filename, path);
putname(filename);
return res;
}
EXPORT_SYMBOL(user_path_locked_at);
int kern_path(const char *name, unsigned int flags, struct path *path)
{
struct filename *filename = getname_kernel(name);
int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL);
putname(filename);
return ret;
}
EXPORT_SYMBOL(kern_path);
/**
* vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair
* @filename: filename structure
* @flags: lookup flags
* @parent: pointer to struct path to fill
* @last: last component
* @type: type of the last component
* @root: pointer to struct path of the base directory
*/
int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
struct path *parent, struct qstr *last, int *type,
const struct path *root)
{
return __filename_parentat(AT_FDCWD, filename, flags, parent, last,
type, root);
}
EXPORT_SYMBOL(vfs_path_parent_lookup);
/**
* vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
* @dentry: pointer to dentry of the base directory
* @mnt: pointer to vfs mount of the base directory
* @name: pointer to file name
* @flags: lookup flags
* @path: pointer to struct path to fill
*/
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
const char *name, unsigned int flags,
struct path *path)
{
struct filename *filename;
struct path root = {.mnt = mnt, .dentry = dentry};
int ret;
filename = getname_kernel(name);
/* the first argument of filename_lookup() is ignored with root */
ret = filename_lookup(AT_FDCWD, filename, flags, path, &root);
putname(filename);
return ret;
}
EXPORT_SYMBOL(vfs_path_lookup);
static int lookup_one_common(struct mnt_idmap *idmap,
const char *name, struct dentry *base, int len,
struct qstr *this)
{
this->name = name;
this->len = len;
this->hash = full_name_hash(base, name, len);
if (!len)
return -EACCES;
if (is_dot_dotdot(name, len))
return -EACCES;
while (len--) {
unsigned int c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return -EACCES;
}
/*
* See if the low-level filesystem might want
* to use its own hash..
*/
if (base->d_flags & DCACHE_OP_HASH) {
int err = base->d_op->d_hash(base, this);
if (err < 0)
return err;
}
return inode_permission(idmap, base->d_inode, MAY_EXEC);
}
/**
* try_lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Look up a dentry by name in the dcache, returning NULL if it does not
* currently exist. The function does not try to create a dentry.
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* No locks need be held - only a counted reference to @base is needed.
*
*/
struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len)
{
struct qstr this;
int err;
err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this);
if (err)
return ERR_PTR(err);
return lookup_dcache(&this, base, 0);
}
EXPORT_SYMBOL(try_lookup_one_len);
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* The caller must hold base->i_mutex.
*/
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
struct dentry *dentry;
struct qstr this;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this);
if (err)
return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0);
return dentry ? dentry : __lookup_slow(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len);
/**
* lookup_one - filesystem helper to lookup single pathname component
* @idmap: idmap of the mount the lookup is performed from
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* The caller must hold base->i_mutex.
*/
struct dentry *lookup_one(struct mnt_idmap *idmap, const char *name,
struct dentry *base, int len)
{
struct dentry *dentry;
struct qstr this;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
err = lookup_one_common(idmap, name, base, len, &this);
if (err)
return ERR_PTR(err);
dentry = lookup_dcache(&this, base, 0);
return dentry ? dentry : __lookup_slow(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one);
/**
* lookup_one_unlocked - filesystem helper to lookup single pathname component
* @idmap: idmap of the mount the lookup is performed from
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* Unlike lookup_one_len, it should be called without the parent
* i_mutex held, and will take the i_mutex itself if necessary.
*/
struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap,
const char *name, struct dentry *base,
int len)
{
struct qstr this;
int err;
struct dentry *ret;
err = lookup_one_common(idmap, name, base, len, &this);
if (err)
return ERR_PTR(err); ret = lookup_dcache(&this, base, 0);
if (!ret)
ret = lookup_slow(&this, base, 0);
return ret;
}
EXPORT_SYMBOL(lookup_one_unlocked);
/**
* lookup_one_positive_unlocked - filesystem helper to lookup single
* pathname component
* @idmap: idmap of the mount the lookup is performed from
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns
* known positive or ERR_PTR(). This is what most of the users want.
*
* Note that pinned negative with unlocked parent _can_ become positive at any
* time, so callers of lookup_one_unlocked() need to be very careful; pinned
* positives have >d_inode stable, so this one avoids such problems.
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* The helper should be called without i_mutex held.
*/
struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap,
const char *name,
struct dentry *base, int len)
{
struct dentry *ret = lookup_one_unlocked(idmap, name, base, len);
if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret);
ret = ERR_PTR(-ENOENT);
}
return ret;
}
EXPORT_SYMBOL(lookup_one_positive_unlocked);
/**
* lookup_one_len_unlocked - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* Unlike lookup_one_len, it should be called without the parent
* i_mutex held, and will take the i_mutex itself if necessary.
*/
struct dentry *lookup_one_len_unlocked(const char *name,
struct dentry *base, int len)
{
return lookup_one_unlocked(&nop_mnt_idmap, name, base, len);
}
EXPORT_SYMBOL(lookup_one_len_unlocked);
/*
* Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT)
* on negatives. Returns known positive or ERR_PTR(); that's what
* most of the users want. Note that pinned negative with unlocked parent
* _can_ become positive at any time, so callers of lookup_one_len_unlocked()
* need to be very careful; pinned positives have ->d_inode stable, so
* this one avoids such problems.
*/
struct dentry *lookup_positive_unlocked(const char *name,
struct dentry *base, int len)
{ return lookup_one_positive_unlocked(&nop_mnt_idmap, name, base, len);
}
EXPORT_SYMBOL(lookup_positive_unlocked);
#ifdef CONFIG_UNIX98_PTYS
int path_pts(struct path *path)
{
/* Find something mounted on "pts" in the same directory as
* the input path.
*/
struct dentry *parent = dget_parent(path->dentry);
struct dentry *child;
struct qstr this = QSTR_INIT("pts", 3);
if (unlikely(!path_connected(path->mnt, parent))) {
dput(parent);
return -ENOENT;
}
dput(path->dentry);
path->dentry = parent;
child = d_hash_and_lookup(parent, &this);
if (IS_ERR_OR_NULL(child))
return -ENOENT;
path->dentry = child;
dput(parent);
follow_down(path, 0);
return 0;
}
#endif
int user_path_at(int dfd, const char __user *name, unsigned flags,
struct path *path)
{
struct filename *filename = getname_flags(name, flags);
int ret = filename_lookup(dfd, filename, flags, path, NULL);
putname(filename);
return ret;
}
EXPORT_SYMBOL(user_path_at);
int __check_sticky(struct mnt_idmap *idmap, struct inode *dir,
struct inode *inode)
{
kuid_t fsuid = current_fsuid();
if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), fsuid))
return 0;
if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, dir), fsuid))
return 0;
return !capable_wrt_inode_uidgid(idmap, inode, CAP_FOWNER);
}
EXPORT_SYMBOL(__check_sticky);
/*
* Check whether we can remove a link victim from directory dir, check
* whether the type of victim is right.
* 1. We can't do it if dir is read-only (done in permission())
* 2. We should have write and exec permissions on dir
* 3. We can't remove anything from append-only dir
* 4. We can't do anything with immutable dir (done in permission())
* 5. If the sticky bit on dir is set we should either
* a. be owner of dir, or
* b. be owner of victim, or
* c. have CAP_FOWNER capability
* 6. If the victim is append-only or immutable we can't do antyhing with
* links pointing to it.
* 7. If the victim has an unknown uid or gid we can't change the inode.
* 8. If we were asked to remove a directory and victim isn't one - ENOTDIR.
* 9. If we were asked to remove a non-directory and victim isn't one - EISDIR.
* 10. We can't remove a root or mountpoint.
* 11. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
static int may_delete(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *victim, bool isdir)
{
struct inode *inode = d_backing_inode(victim);
int error;
if (d_is_negative(victim))
return -ENOENT;
BUG_ON(!inode);
BUG_ON(victim->d_parent->d_inode != dir);
/* Inode writeback is not safe when the uid or gid are invalid. */
if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) ||
!vfsgid_valid(i_gid_into_vfsgid(idmap, inode)))
return -EOVERFLOW;
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
if (check_sticky(idmap, dir, inode) || IS_APPEND(inode) ||
IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) ||
HAS_UNMAPPED_ID(idmap, inode))
return -EPERM;
if (isdir) {
if (!d_is_dir(victim))
return -ENOTDIR;
if (IS_ROOT(victim))
return -EBUSY;
} else if (d_is_dir(victim))
return -EISDIR;
if (IS_DEADDIR(dir))
return -ENOENT;
if (victim->d_flags & DCACHE_NFSFS_RENAMED)
return -EBUSY;
return 0;
}
/* Check whether we can create an object with dentry child in directory
* dir.
* 1. We can't do it if child already exists (open has special treatment for
* this case, but since we are inlined it's OK)
* 2. We can't do it if dir is read-only (done in permission())
* 3. We can't do it if the fs can't represent the fsuid or fsgid.
* 4. We should have write and exec permissions on dir
* 5. We can't do it if dir is immutable (done in permission())
*/
static inline int may_create(struct mnt_idmap *idmap,
struct inode *dir, struct dentry *child)
{
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
if (!fsuidgid_has_mapping(dir->i_sb, idmap))
return -EOVERFLOW;
return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
}
// p1 != p2, both are on the same filesystem, ->s_vfs_rename_mutex is held
static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2)
{
struct dentry *p = p1, *q = p2, *r;
while ((r = p->d_parent) != p2 && r != p)
p = r;
if (r == p2) {
// p is a child of p2 and an ancestor of p1 or p1 itself
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2);
return p;
}
// p is the root of connected component that contains p1
// p2 does not occur on the path from p to p1
while ((r = q->d_parent) != p1 && r != p && r != q)
q = r;
if (r == p1) {
// q is a child of p1 and an ancestor of p2 or p2 itself
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
return q;
} else if (likely(r == p)) {
// both p2 and p1 are descendents of p
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
return NULL;
} else { // no common ancestor at the time we'd been called
mutex_unlock(&p1->d_sb->s_vfs_rename_mutex);
return ERR_PTR(-EXDEV);
}
}
/*
* p1 and p2 should be directories on the same fs.
*/
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
if (p1 == p2) {
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
return NULL;
}
mutex_lock(&p1->d_sb->s_vfs_rename_mutex);
return lock_two_directories(p1, p2);
}
EXPORT_SYMBOL(lock_rename);
/*
* c1 and p2 should be on the same fs.
*/
struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2)
{
if (READ_ONCE(c1->d_parent) == p2) {
/*
* hopefully won't need to touch ->s_vfs_rename_mutex at all.
*/
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
/*
* now that p2 is locked, nobody can move in or out of it,
* so the test below is safe.
*/
if (likely(c1->d_parent == p2))
return NULL;
/*
* c1 got moved out of p2 while we'd been taking locks;
* unlock and fall back to slow case.
*/
inode_unlock(p2->d_inode);
}
mutex_lock(&c1->d_sb->s_vfs_rename_mutex);
/*
* nobody can move out of any directories on this fs.
*/
if (likely(c1->d_parent != p2))
return lock_two_directories(c1->d_parent, p2);
/*
* c1 got moved into p2 while we were taking locks;
* we need p2 locked and ->s_vfs_rename_mutex unlocked,
* for consistency with lock_rename().
*/
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
mutex_unlock(&c1->d_sb->s_vfs_rename_mutex);
return NULL;
}
EXPORT_SYMBOL(lock_rename_child);
void unlock_rename(struct dentry *p1, struct dentry *p2)
{
inode_unlock(p1->d_inode);
if (p1 != p2) {
inode_unlock(p2->d_inode);
mutex_unlock(&p1->d_sb->s_vfs_rename_mutex);
}
}
EXPORT_SYMBOL(unlock_rename);
/**
* vfs_prepare_mode - prepare the mode to be used for a new inode
* @idmap: idmap of the mount the inode was found from
* @dir: parent directory of the new inode
* @mode: mode of the new inode
* @mask_perms: allowed permission by the vfs
* @type: type of file to be created
*
* This helper consolidates and enforces vfs restrictions on the @mode of a new
* object to be created.
*
* Umask stripping depends on whether the filesystem supports POSIX ACLs (see
* the kernel documentation for mode_strip_umask()). Moving umask stripping
* after setgid stripping allows the same ordering for both non-POSIX ACL and
* POSIX ACL supporting filesystems.
*
* Note that it's currently valid for @type to be 0 if a directory is created.
* Filesystems raise that flag individually and we need to check whether each
* filesystem can deal with receiving S_IFDIR from the vfs before we enforce a
* non-zero type.
*
* Returns: mode to be passed to the filesystem
*/
static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
const struct inode *dir, umode_t mode,
umode_t mask_perms, umode_t type)
{
mode = mode_strip_sgid(idmap, dir, mode);
mode = mode_strip_umask(dir, mode);
/*
* Apply the vfs mandated allowed permission mask and set the type of
* file to be created before we call into the filesystem.
*/
mode &= (mask_perms & ~S_IFMT);
mode |= (type & S_IFMT);
return mode;
}
/**
* vfs_create - create new file
* @idmap: idmap of the mount the inode was found from
* @dir: inode of the parent directory
* @dentry: dentry of the child file
* @mode: mode of the child file
* @want_excl: whether the file must not yet exist
*
* Create a new file.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool want_excl)
{
int error;
error = may_create(idmap, dir, dentry);
if (error)
return error;
if (!dir->i_op->create)
return -EACCES; /* shouldn't it be ENOSYS? */
mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG);
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
error = dir->i_op->create(idmap, dir, dentry, mode, want_excl);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_create);
int vfs_mkobj(struct dentry *dentry, umode_t mode,
int (*f)(struct dentry *, umode_t, void *),
void *arg)
{
struct inode *dir = dentry->d_parent->d_inode;
int error = may_create(&nop_mnt_idmap, dir, dentry);
if (error)
return error;
mode &= S_IALLUGO;
mode |= S_IFREG;
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
error = f(dentry, mode, arg);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_mkobj);
bool may_open_dev(const struct path *path)
{
return !(path->mnt->mnt_flags & MNT_NODEV) &&
!(path->mnt->mnt_sb->s_iflags & SB_I_NODEV);
}
static int may_open(struct mnt_idmap *idmap, const struct path *path,
int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
struct inode *inode = dentry->d_inode;
int error;
if (!inode)
return -ENOENT;
switch (inode->i_mode & S_IFMT) {
case S_IFLNK:
return -ELOOP;
case S_IFDIR:
if (acc_mode & MAY_WRITE)
return -EISDIR;
if (acc_mode & MAY_EXEC)
return -EACCES;
break;
case S_IFBLK:
case S_IFCHR:
if (!may_open_dev(path))
return -EACCES;
fallthrough;
case S_IFIFO:
case S_IFSOCK:
if (acc_mode & MAY_EXEC)
return -EACCES;
flag &= ~O_TRUNC;
break;
case S_IFREG:
if ((acc_mode & MAY_EXEC) && path_noexec(path))
return -EACCES;
break;
default:
VFS_BUG_ON_INODE(1, inode);
}
error = inode_permission(idmap, inode, MAY_OPEN | acc_mode);
if (error)
return error;
/*
* An append-only file must be opened in append mode for writing.
*/
if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
return -EPERM;
if (flag & O_TRUNC)
return -EPERM;
}
/* O_NOATIME can only be set by the owner or superuser */
if (flag & O_NOATIME && !inode_owner_or_capable(idmap, inode))
return -EPERM;
return 0;
}
static int handle_truncate(struct mnt_idmap *idmap, struct file *filp)
{
const struct path *path = &filp->f_path;
struct inode *inode = path->dentry->d_inode;
int error = get_write_access(inode);
if (error)
return error;
error = security_file_truncate(filp);
if (!error) { error = do_truncate(idmap, path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
filp);
}
put_write_access(inode);
return error;
}
static inline int open_to_namei_flags(int flag)
{
if ((flag & O_ACCMODE) == 3)
flag--;
return flag;
}
static int may_o_create(struct mnt_idmap *idmap,
const struct path *dir, struct dentry *dentry,
umode_t mode)
{
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
return error;
if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap))
return -EOVERFLOW;
error = inode_permission(idmap, dir->dentry->d_inode,
MAY_WRITE | MAY_EXEC);
if (error)
return error;
return security_inode_create(dir->dentry->d_inode, dentry, mode);
}
/*
* Attempt to atomically look up, create and open a file from a negative
* dentry.
*
* Returns 0 if successful. The file will have been created and attached to
* @file by the filesystem calling finish_open().
*
* If the file was looked up only or didn't need creating, FMODE_OPENED won't
* be set. The caller will need to perform the open themselves. @path will
* have been updated to point to the new dentry. This may be negative.
*
* Returns an error code otherwise.
*/
static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry,
struct file *file,
int open_flag, umode_t mode)
{
struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
struct inode *dir = nd->path.dentry->d_inode;
int error;
if (nd->flags & LOOKUP_DIRECTORY)
open_flag |= O_DIRECTORY;
file->f_path.dentry = DENTRY_NOT_SET;
file->f_path.mnt = nd->path.mnt;
error = dir->i_op->atomic_open(dir, dentry, file,
open_to_namei_flags(open_flag), mode);
d_lookup_done(dentry); if (!error) {
if (file->f_mode & FMODE_OPENED) {
if (unlikely(dentry != file->f_path.dentry)) {
dput(dentry);
dentry = dget(file->f_path.dentry);
}
} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
error = -EIO;
} else {
if (file->f_path.dentry) {
dput(dentry);
dentry = file->f_path.dentry;
}
if (unlikely(d_is_negative(dentry)))
error = -ENOENT;
}
}
if (error) {
dput(dentry);
dentry = ERR_PTR(error);
}
return dentry;
}
/*
* Look up and maybe create and open the last component.
*
* Must be called with parent locked (exclusive in O_CREAT case).
*
* Returns 0 on success, that is, if
* the file was successfully atomically created (if necessary) and opened, or
* the file was not completely opened at this time, though lookups and
* creations were performed.
* These case are distinguished by presence of FMODE_OPENED on file->f_mode.
* In the latter case dentry returned in @path might be negative if O_CREAT
* hadn't been specified.
*
* An error code is returned on failure.
*/
static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
const struct open_flags *op,
bool got_write)
{
struct mnt_idmap *idmap;
struct dentry *dir = nd->path.dentry;
struct inode *dir_inode = dir->d_inode;
int open_flag = op->open_flag;
struct dentry *dentry;
int error, create_error = 0;
umode_t mode = op->mode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
if (unlikely(IS_DEADDIR(dir_inode)))
return ERR_PTR(-ENOENT);
file->f_mode &= ~FMODE_CREATED;
dentry = d_lookup(dir, &nd->last);
for (;;) {
if (!dentry) {
dentry = d_alloc_parallel(dir, &nd->last, &wq);
if (IS_ERR(dentry))
return dentry;
}
if (d_in_lookup(dentry))
break;
error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags);
if (likely(error > 0))
break;
if (error)
goto out_dput;
d_invalidate(dentry);
dput(dentry);
dentry = NULL;
}
if (dentry->d_inode) {
/* Cached positive dentry: will open in f_op->open */
return dentry;
}
if (open_flag & O_CREAT) audit_inode(nd->name, dir, AUDIT_INODE_PARENT);
/*
* Checking write permission is tricky, bacuse we don't know if we are
* going to actually need it: O_CREAT opens should work as long as the
* file exists. But checking existence breaks atomicity. The trick is
* to check access and if not granted clear O_CREAT from the flags.
*
* Another problem is returing the "right" error value (e.g. for an
* O_EXCL open we want to return EEXIST not EROFS).
*/
if (unlikely(!got_write)) open_flag &= ~O_TRUNC;
idmap = mnt_idmap(nd->path.mnt);
if (open_flag & O_CREAT) {
if (open_flag & O_EXCL)
open_flag &= ~O_TRUNC;
mode = vfs_prepare_mode(idmap, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(idmap, &nd->path,
dentry, mode);
else
create_error = -EROFS;
}
if (create_error)
open_flag &= ~O_CREAT;
if (dir_inode->i_op->atomic_open) {
dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error);
return dentry;
}
if (d_in_lookup(dentry)) {
struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry,
nd->flags);
d_lookup_done(dentry); if (unlikely(res)) {
if (IS_ERR(res)) {
error = PTR_ERR(res);
goto out_dput;
}
dput(dentry);
dentry = res;
}
}
/* Negative dentry, just create the file */
if (!dentry->d_inode && (open_flag & O_CREAT)) {
file->f_mode |= FMODE_CREATED;
audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) {
error = -EACCES;
goto out_dput;
}
error = dir_inode->i_op->create(idmap, dir_inode, dentry,
mode, open_flag & O_EXCL);
if (error)
goto out_dput;
}
if (unlikely(create_error) && !dentry->d_inode) {
error = create_error;
goto out_dput;
}
return dentry;
out_dput:
dput(dentry);
return ERR_PTR(error);
}
static inline bool trailing_slashes(struct nameidata *nd)
{
return (bool)nd->last.name[nd->last.len];
}
static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
{
struct dentry *dentry;
if (open_flag & O_CREAT) { if (trailing_slashes(nd))
return ERR_PTR(-EISDIR);
/* Don't bother on an O_EXCL create */
if (open_flag & O_EXCL)
return NULL;
}
if (trailing_slashes(nd)) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
dentry = lookup_fast(nd);
if (IS_ERR_OR_NULL(dentry))
return dentry;
if (open_flag & O_CREAT) {
/* Discard negative dentries. Need inode_lock to do the create */
if (!dentry->d_inode) { if (!(nd->flags & LOOKUP_RCU)) dput(dentry);
dentry = NULL;
}
}
return dentry;
}
static const char *open_last_lookups(struct nameidata *nd,
struct file *file, const struct open_flags *op)
{
struct dentry *dir = nd->path.dentry;
int open_flag = op->open_flag;
bool got_write = false;
struct dentry *dentry;
const char *res;
nd->flags |= op->intent;
if (nd->last_type != LAST_NORM) {
if (nd->depth) put_link(nd);
return handle_dots(nd, nd->last_type);
}
/* We _can_ be in RCU mode here */
dentry = lookup_fast_for_open(nd, open_flag); if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (likely(dentry))
goto finish_lookup;
if (!(open_flag & O_CREAT)) { if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU))
return ERR_PTR(-ECHILD);
} else {
if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
}
}
if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt);
/*
* do _not_ fail yet - we might not need that or fail with
* a different error; let lookup_open() decide; we'll be
* dropping this one anyway.
*/
}
if (open_flag & O_CREAT)
inode_lock(dir->d_inode);
else
inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry)) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file);
}
if (open_flag & O_CREAT)
inode_unlock(dir->d_inode);
else
inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry);
nd->path.dentry = dentry;
return NULL;
}
finish_lookup:
if (nd->depth) put_link(nd);
res = step_into(nd, WALK_TRAILING, dentry);
if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
return res;
}
/*
* Handle the last step of open()
*/
static int do_open(struct nameidata *nd,
struct file *file, const struct open_flags *op)
{
struct mnt_idmap *idmap;
int open_flag = op->open_flag;
bool do_truncate;
int acc_mode;
int error;
if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) {
error = complete_walk(nd);
if (error)
return error;
}
if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0);
idmap = mnt_idmap(nd->path.mnt);
if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED))
return -EEXIST;
if (d_is_dir(nd->path.dentry))
return -EISDIR;
error = may_create_in_sticky(idmap, nd,
d_backing_inode(nd->path.dentry));
if (unlikely(error))
return error;
}
if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
return -ENOTDIR;
do_truncate = false;
acc_mode = op->acc_mode;
if (file->f_mode & FMODE_CREATED) {
/* Don't check for write permission, don't truncate */
open_flag &= ~O_TRUNC;
acc_mode = 0;
} else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) {
error = mnt_want_write(nd->path.mnt);
if (error)
return error;
do_truncate = true;
}
error = may_open(idmap, &nd->path, acc_mode, open_flag);
if (!error && !(file->f_mode & FMODE_OPENED))
error = vfs_open(&nd->path, file);
if (!error)
error = security_file_post_open(file, op->acc_mode);
if (!error && do_truncate) error = handle_truncate(idmap, file); if (unlikely(error > 0)) { WARN_ON(1);
error = -EINVAL;
}
if (do_truncate) mnt_drop_write(nd->path.mnt);
return error;
}
/**
* vfs_tmpfile - create tmpfile
* @idmap: idmap of the mount the inode was found from
* @parentpath: pointer to the path of the base directory
* @file: file descriptor of the new tmpfile
* @mode: mode of the new tmpfile
*
* Create a temporary file.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_tmpfile(struct mnt_idmap *idmap,
const struct path *parentpath,
struct file *file, umode_t mode)
{
struct dentry *child;
struct inode *dir = d_inode(parentpath->dentry);
struct inode *inode;
int error;
int open_flag = file->f_flags;
/* we want directory to be writable */
error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (!dir->i_op->tmpfile)
return -EOPNOTSUPP;
child = d_alloc(parentpath->dentry, &slash_name);
if (unlikely(!child))
return -ENOMEM;
file->f_path.mnt = parentpath->mnt;
file->f_path.dentry = child;
mode = vfs_prepare_mode(idmap, dir, mode, mode, mode);
error = dir->i_op->tmpfile(idmap, dir, file, mode);
dput(child);
if (file->f_mode & FMODE_OPENED) fsnotify_open(file); if (error)
return error;
/* Don't check for other permissions, the inode was just created */
error = may_open(idmap, &file->f_path, 0, file->f_flags);
if (error)
return error;
inode = file_inode(file);
if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock);
inode->i_state |= I_LINKABLE;
spin_unlock(&inode->i_lock);
}
security_inode_post_create_tmpfile(idmap, inode);
return 0;
}
/**
* kernel_tmpfile_open - open a tmpfile for kernel internal use
* @idmap: idmap of the mount the inode was found from
* @parentpath: path of the base directory
* @mode: mode of the new tmpfile
* @open_flag: flags
* @cred: credentials for open
*
* Create and open a temporary file. The file is not accounted in nr_files,
* hence this is only for kernel internal use, and must not be installed into
* file tables or such.
*/
struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,
const struct path *parentpath,
umode_t mode, int open_flag,
const struct cred *cred)
{
struct file *file;
int error;
file = alloc_empty_file_noaccount(open_flag, cred);
if (IS_ERR(file))
return file;
error = vfs_tmpfile(idmap, parentpath, file, mode);
if (error) {
fput(file);
file = ERR_PTR(error);
}
return file;
}
EXPORT_SYMBOL(kernel_tmpfile_open);
static int do_tmpfile(struct nameidata *nd, unsigned flags,
const struct open_flags *op,
struct file *file)
{
struct path path;
int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
if (unlikely(error))
return error;
error = mnt_want_write(path.mnt);
if (unlikely(error))
goto out;
error = vfs_tmpfile(mnt_idmap(path.mnt), &path, file, op->mode);
if (error)
goto out2;
audit_inode(nd->name, file->f_path.dentry, 0);
out2:
mnt_drop_write(path.mnt);
out:
path_put(&path);
return error;
}
static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
{
struct path path;
int error = path_lookupat(nd, flags, &path);
if (!error) { audit_inode(nd->name, path.dentry, 0);
error = vfs_open(&path, file);
path_put(&path);
}
return error;
}
static struct file *path_openat(struct nameidata *nd,
const struct open_flags *op, unsigned flags)
{
struct file *file;
int error;
file = alloc_empty_file(op->open_flag, current_cred());
if (IS_ERR(file))
return file;
if (unlikely(file->f_flags & __O_TMPFILE)) {
error = do_tmpfile(nd, flags, op, file);
} else if (unlikely(file->f_flags & O_PATH)) {
error = do_o_path(nd, flags, file);
} else {
const char *s = path_init(nd, flags);
while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL)
;
if (!error)
error = do_open(nd, file, op);
terminate_walk(nd);
}
if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED))
return file;
WARN_ON(1);
error = -EINVAL;
}
fput_close(file);
if (error == -EOPENSTALE) {
if (flags & LOOKUP_RCU)
error = -ECHILD;
else
error = -ESTALE;
}
return ERR_PTR(error);
}
struct file *do_filp_open(int dfd, struct filename *pathname,
const struct open_flags *op)
{
struct nameidata nd;
int flags = op->lookup_flags;
struct file *filp;
set_nameidata(&nd, dfd, pathname, NULL);
filp = path_openat(&nd, op, flags | LOOKUP_RCU);
if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata();
return filp;
}
struct file *do_file_open_root(const struct path *root,
const char *name, const struct open_flags *op)
{
struct nameidata nd;
struct file *file;
struct filename *filename;
int flags = op->lookup_flags;
if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN)
return ERR_PTR(-ELOOP);
filename = getname_kernel(name);
if (IS_ERR(filename))
return ERR_CAST(filename);
set_nameidata(&nd, -1, filename, root);
file = path_openat(&nd, op, flags | LOOKUP_RCU);
if (unlikely(file == ERR_PTR(-ECHILD)))
file = path_openat(&nd, op, flags);
if (unlikely(file == ERR_PTR(-ESTALE)))
file = path_openat(&nd, op, flags | LOOKUP_REVAL);
restore_nameidata();
putname(filename);
return file;
}
static struct dentry *filename_create(int dfd, struct filename *name,
struct path *path, unsigned int lookup_flags)
{
struct dentry *dentry = ERR_PTR(-EEXIST);
struct qstr last;
bool want_dir = lookup_flags & LOOKUP_DIRECTORY;
unsigned int reval_flag = lookup_flags & LOOKUP_REVAL;
unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL;
int type;
int err2;
int error;
error = filename_parentat(dfd, name, reval_flag, path, &last, &type);
if (error)
return ERR_PTR(error);
/*
* Yucky last component or no last component at all?
* (foo/., foo/.., /////)
*/
if (unlikely(type != LAST_NORM))
goto out;
/* don't fail immediately if it's r/o, at least try to report other errors */
err2 = mnt_want_write(path->mnt);
/*
* Do the final lookup. Suppress 'create' if there is a trailing
* '/', and a directory wasn't requested.
*/
if (last.name[last.len] && !want_dir)
create_flags &= ~LOOKUP_CREATE;
inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
dentry = lookup_one_qstr_excl(&last, path->dentry,
reval_flag | create_flags);
if (IS_ERR(dentry))
goto unlock;
if (unlikely(err2)) {
error = err2;
goto fail;
}
return dentry;
fail:
dput(dentry);
dentry = ERR_PTR(error);
unlock:
inode_unlock(path->dentry->d_inode);
if (!err2)
mnt_drop_write(path->mnt);
out:
path_put(path);
return dentry;
}
struct dentry *kern_path_create(int dfd, const char *pathname,
struct path *path, unsigned int lookup_flags)
{
struct filename *filename = getname_kernel(pathname);
struct dentry *res = filename_create(dfd, filename, path, lookup_flags);
putname(filename);
return res;
}
EXPORT_SYMBOL(kern_path_create);
void done_path_create(struct path *path, struct dentry *dentry)
{
if (!IS_ERR(dentry))
dput(dentry);
inode_unlock(path->dentry->d_inode);
mnt_drop_write(path->mnt);
path_put(path);
}
EXPORT_SYMBOL(done_path_create);
inline struct dentry *user_path_create(int dfd, const char __user *pathname,
struct path *path, unsigned int lookup_flags)
{
struct filename *filename = getname(pathname);
struct dentry *res = filename_create(dfd, filename, path, lookup_flags);
putname(filename);
return res;
}
EXPORT_SYMBOL(user_path_create);
/**
* vfs_mknod - create device node or file
* @idmap: idmap of the mount the inode was found from
* @dir: inode of the parent directory
* @dentry: dentry of the child device node
* @mode: mode of the child device node
* @dev: device number of device to create
*
* Create a device node or file.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV;
int error = may_create(idmap, dir, dentry);
if (error)
return error;
if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout &&
!capable(CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)
return -EPERM;
mode = vfs_prepare_mode(idmap, dir, mode, mode, mode);
error = devcgroup_inode_mknod(mode, dev);
if (error)
return error;
error = security_inode_mknod(dir, dentry, mode, dev);
if (error)
return error;
error = dir->i_op->mknod(idmap, dir, dentry, mode, dev);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_mknod);
static int may_mknod(umode_t mode)
{
switch (mode & S_IFMT) {
case S_IFREG:
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
case 0: /* zero mode translates to S_IFREG */
return 0;
case S_IFDIR:
return -EPERM;
default:
return -EINVAL;
}
}
static int do_mknodat(int dfd, struct filename *name, umode_t mode,
unsigned int dev)
{
struct mnt_idmap *idmap;
struct dentry *dentry;
struct path path;
int error;
unsigned int lookup_flags = 0;
error = may_mknod(mode);
if (error)
goto out1;
retry:
dentry = filename_create(dfd, name, &path, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out1;
error = security_path_mknod(&path, dentry,
mode_strip_umask(path.dentry->d_inode, mode), dev);
if (error)
goto out2;
idmap = mnt_idmap(path.mnt);
switch (mode & S_IFMT) {
case 0: case S_IFREG:
error = vfs_create(idmap, path.dentry->d_inode,
dentry, mode, true);
if (!error)
security_path_post_mknod(idmap, dentry);
break;
case S_IFCHR: case S_IFBLK:
error = vfs_mknod(idmap, path.dentry->d_inode,
dentry, mode, new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
error = vfs_mknod(idmap, path.dentry->d_inode,
dentry, mode, 0);
break;
}
out2:
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out1:
putname(name);
return error;
}
SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
unsigned int, dev)
{
return do_mknodat(dfd, getname(filename), mode, dev);
}
SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev)
{
return do_mknodat(AT_FDCWD, getname(filename), mode, dev);
}
/**
* vfs_mkdir - create directory returning correct dentry if possible
* @idmap: idmap of the mount the inode was found from
* @dir: inode of the parent directory
* @dentry: dentry of the child directory
* @mode: mode of the child directory
*
* Create a directory.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*
* In the event that the filesystem does not use the *@dentry but leaves it
* negative or unhashes it and possibly splices a different one returning it,
* the original dentry is dput() and the alternate is returned.
*
* In case of an error the dentry is dput() and an ERR_PTR() is returned.
*/
struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
int error;
unsigned max_links = dir->i_sb->s_max_links;
struct dentry *de;
error = may_create(idmap, dir, dentry);
if (error)
goto err;
error = -EPERM;
if (!dir->i_op->mkdir)
goto err;
mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0);
error = security_inode_mkdir(dir, dentry, mode);
if (error)
goto err;
error = -EMLINK;
if (max_links && dir->i_nlink >= max_links)
goto err;
de = dir->i_op->mkdir(idmap, dir, dentry, mode);
error = PTR_ERR(de);
if (IS_ERR(de))
goto err;
if (de) {
dput(dentry);
dentry = de;
}
fsnotify_mkdir(dir, dentry);
return dentry;
err:
dput(dentry);
return ERR_PTR(error);
}
EXPORT_SYMBOL(vfs_mkdir);
int do_mkdirat(int dfd, struct filename *name, umode_t mode)
{
struct dentry *dentry;
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_DIRECTORY;
retry:
dentry = filename_create(dfd, name, &path, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_putname;
error = security_path_mkdir(&path, dentry,
mode_strip_umask(path.dentry->d_inode, mode));
if (!error) {
dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
dentry, mode);
if (IS_ERR(dentry))
error = PTR_ERR(dentry);
}
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out_putname:
putname(name);
return error;
}
SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
{
return do_mkdirat(dfd, getname(pathname), mode);
}
SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
{
return do_mkdirat(AT_FDCWD, getname(pathname), mode);
}
/**
* vfs_rmdir - remove directory
* @idmap: idmap of the mount the inode was found from
* @dir: inode of the parent directory
* @dentry: dentry of the child directory
*
* Remove a directory.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry)
{
int error = may_delete(idmap, dir, dentry, 1);
if (error)
return error;
if (!dir->i_op->rmdir)
return -EPERM;
dget(dentry);
inode_lock(dentry->d_inode);
error = -EBUSY;
if (is_local_mountpoint(dentry) ||
(dentry->d_inode->i_flags & S_KERNEL_FILE))
goto out;
error = security_inode_rmdir(dir, dentry);
if (error)
goto out;
error = dir->i_op->rmdir(dir, dentry);
if (error)
goto out;
shrink_dcache_parent(dentry);
dentry->d_inode->i_flags |= S_DEAD;
dont_mount(dentry);
detach_mounts(dentry);
out:
inode_unlock(dentry->d_inode);
dput(dentry);
if (!error)
d_delete_notify(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_rmdir);
int do_rmdir(int dfd, struct filename *name)
{
int error;
struct dentry *dentry;
struct path path;
struct qstr last;
int type;
unsigned int lookup_flags = 0;
retry:
error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
if (error)
goto exit1;
switch (type) {
case LAST_DOTDOT:
error = -ENOTEMPTY;
goto exit2;
case LAST_DOT:
error = -EINVAL;
goto exit2;
case LAST_ROOT:
error = -EBUSY;
goto exit2;
}
error = mnt_want_write(path.mnt);
if (error)
goto exit2;
inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto exit3;
error = security_path_rmdir(&path, dentry);
if (error)
goto exit4;
error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry);
exit4:
dput(dentry);
exit3:
inode_unlock(path.dentry->d_inode);
mnt_drop_write(path.mnt);
exit2:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
exit1:
putname(name);
return error;
}
SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
{
return do_rmdir(AT_FDCWD, getname(pathname));
}
/**
* vfs_unlink - unlink a filesystem object
* @idmap: idmap of the mount the inode was found from
* @dir: parent directory
* @dentry: victim
* @delegated_inode: returns victim inode, if the inode is delegated.
*
* The caller must hold dir->i_mutex.
*
* If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
* return a reference to the inode in delegated_inode. The caller
* should then break the delegation on that inode and retry. Because
* breaking a delegation may take a long time, the caller should drop
* dir->i_mutex before doing so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, struct inode **delegated_inode)
{
struct inode *target = dentry->d_inode;
int error = may_delete(idmap, dir, dentry, 0);
if (error)
return error;
if (!dir->i_op->unlink)
return -EPERM;
inode_lock(target);
if (IS_SWAPFILE(target))
error = -EPERM;
else if (is_local_mountpoint(dentry))
error = -EBUSY;
else {
error = security_inode_unlink(dir, dentry);
if (!error) {
error = try_break_deleg(target, delegated_inode);
if (error)
goto out;
error = dir->i_op->unlink(dir, dentry);
if (!error) {
dont_mount(dentry);
detach_mounts(dentry);
}
}
}
out:
inode_unlock(target);
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) {
fsnotify_unlink(dir, dentry);
} else if (!error) {
fsnotify_link_count(target);
d_delete_notify(dir, dentry);
}
return error;
}
EXPORT_SYMBOL(vfs_unlink);
/*
* Make sure that the actual truncation of the file will occur outside its
* directory's i_mutex. Truncate can take a long time if there is a lot of
* writeout happening, and we don't want to prevent access to the directory
* while waiting on the I/O.
*/
int do_unlinkat(int dfd, struct filename *name)
{
int error;
struct dentry *dentry;
struct path path;
struct qstr last;
int type;
struct inode *inode = NULL;
struct inode *delegated_inode = NULL;
unsigned int lookup_flags = 0;
retry:
error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
if (error)
goto exit1;
error = -EISDIR;
if (type != LAST_NORM)
goto exit2;
error = mnt_want_write(path.mnt);
if (error)
goto exit2;
retry_deleg:
inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
/* Why not before? Because we want correct error value */
if (last.name[last.len])
goto slashes;
inode = dentry->d_inode;
ihold(inode);
error = security_path_unlink(&path, dentry);
if (error)
goto exit3;
error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode,
dentry, &delegated_inode);
exit3:
dput(dentry);
}
inode_unlock(path.dentry->d_inode);
if (inode)
iput(inode); /* truncate the inode here */
inode = NULL;
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
mnt_drop_write(path.mnt);
exit2:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
inode = NULL;
goto retry;
}
exit1:
putname(name);
return error;
slashes:
if (d_is_dir(dentry))
error = -EISDIR;
else
error = -ENOTDIR;
goto exit3;
}
SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
{
if ((flag & ~AT_REMOVEDIR) != 0)
return -EINVAL;
if (flag & AT_REMOVEDIR)
return do_rmdir(dfd, getname(pathname));
return do_unlinkat(dfd, getname(pathname));
}
SYSCALL_DEFINE1(unlink, const char __user *, pathname)
{
return do_unlinkat(AT_FDCWD, getname(pathname));
}
/**
* vfs_symlink - create symlink
* @idmap: idmap of the mount the inode was found from
* @dir: inode of the parent directory
* @dentry: dentry of the child symlink file
* @oldname: name of the file to link to
*
* Create a symlink.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *oldname)
{
int error;
error = may_create(idmap, dir, dentry);
if (error)
return error;
if (!dir->i_op->symlink)
return -EPERM;
error = security_inode_symlink(dir, dentry, oldname);
if (error)
return error;
error = dir->i_op->symlink(idmap, dir, dentry, oldname);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_symlink);
int do_symlinkat(struct filename *from, int newdfd, struct filename *to)
{
int error;
struct dentry *dentry;
struct path path;
unsigned int lookup_flags = 0;
if (IS_ERR(from)) {
error = PTR_ERR(from);
goto out_putnames;
}
retry:
dentry = filename_create(newdfd, to, &path, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_putnames;
error = security_path_symlink(&path, dentry, from->name);
if (!error)
error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode,
dentry, from->name);
done_path_create(&path, dentry);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out_putnames:
putname(to);
putname(from);
return error;
}
SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
int, newdfd, const char __user *, newname)
{
return do_symlinkat(getname(oldname), newdfd, getname(newname));
}
SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname)
{
return do_symlinkat(getname(oldname), AT_FDCWD, getname(newname));
}
/**
* vfs_link - create a new link
* @old_dentry: object to be linked
* @idmap: idmap of the mount
* @dir: new parent
* @new_dentry: where to create the new link
* @delegated_inode: returns inode needing a delegation break
*
* The caller must hold dir->i_mutex
*
* If vfs_link discovers a delegation on the to-be-linked file in need
* of breaking, it will return -EWOULDBLOCK and return a reference to the
* inode in delegated_inode. The caller should then break the delegation
* and retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*
* If the inode has been found through an idmapped mount the idmap of
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply pass @nop_mnt_idmap.
*/
int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
struct inode *dir, struct dentry *new_dentry,
struct inode **delegated_inode)
{
struct inode *inode = old_dentry->d_inode;
unsigned max_links = dir->i_sb->s_max_links;
int error;
if (!inode)
return -ENOENT;
error = may_create(idmap, dir, new_dentry);
if (error)
return error;
if (dir->i_sb != inode->i_sb)
return -EXDEV;
/*
* A link to an append-only or immutable file cannot be created.
*/
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return -EPERM;
/*
* Updating the link count will likely cause i_uid and i_gid to
* be writen back improperly if their true value is unknown to
* the vfs.
*/
if (HAS_UNMAPPED_ID(idmap, inode))
return -EPERM;
if (!dir->i_op->link)
return -EPERM;
if (S_ISDIR(inode->i_mode))
return -EPERM;
error = security_inode_link(old_dentry, dir, new_dentry);
if (error)
return error;
inode_lock(inode);
/* Make sure we don't allow creating hardlink to an unlinked file */
if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
error = -ENOENT;
else if (max_links && inode->i_nlink >= max_links)
error = -EMLINK;
else {
error = try_break_deleg(inode, delegated_inode);
if (!error)
error = dir->i_op->link(old_dentry, dir, new_dentry);
}
if (!error && (inode->i_state & I_LINKABLE)) {
spin_lock(&inode->i_lock);
inode->i_state &= ~I_LINKABLE;
spin_unlock(&inode->i_lock);
}
inode_unlock(inode);
if (!error)
fsnotify_link(dir, inode, new_dentry);
return error;
}
EXPORT_SYMBOL(vfs_link);
/*
* Hardlinks are often used in delicate situations. We avoid
* security-related surprises by not following symlinks on the
* newname. --KAB
*
* We don't follow them on the oldname either to be compatible
* with linux 2.0, and to avoid hard-linking to directories
* and other special files. --ADM
*/
int do_linkat(int olddfd, struct filename *old, int newdfd,
struct filename *new, int flags)
{
struct mnt_idmap *idmap;
struct dentry *new_dentry;
struct path old_path, new_path;
struct inode *delegated_inode = NULL;
int how = 0;
int error;
if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) {
error = -EINVAL;
goto out_putnames;
}
/*
* To use null names we require CAP_DAC_READ_SEARCH or
* that the open-time creds of the dfd matches current.
* This ensures that not everyone will be able to create
* a hardlink using the passed file descriptor.
*/
if (flags & AT_EMPTY_PATH)
how |= LOOKUP_LINKAT_EMPTY;
if (flags & AT_SYMLINK_FOLLOW)
how |= LOOKUP_FOLLOW;
retry:
error = filename_lookup(olddfd, old, how, &old_path, NULL);
if (error)
goto out_putnames;
new_dentry = filename_create(newdfd, new, &new_path,
(how & LOOKUP_REVAL));
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
goto out_putpath;
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
goto out_dput;
idmap = mnt_idmap(new_path.mnt);
error = may_linkat(idmap, &old_path);
if (unlikely(error))
goto out_dput;
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode,
new_dentry, &delegated_inode);
out_dput:
done_path_create(&new_path, new_dentry);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error) {
path_put(&old_path);
goto retry;
}
}
if (retry_estale(error, how)) {
path_put(&old_path);
how |= LOOKUP_REVAL;
goto retry;
}
out_putpath:
path_put(&old_path);
out_putnames:
putname(old);
putname(new);
return error;
}
SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
int, newdfd, const char __user *, newname, int, flags)
{
return do_linkat(olddfd, getname_uflags(oldname, flags),
newdfd, getname(newname), flags);
}
SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname)
{
return do_linkat(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0);
}
/**
* vfs_rename - rename a filesystem object
* @rd: pointer to &struct renamedata info
*
* The caller must hold multiple mutexes--see lock_rename()).
*
* If vfs_rename discovers a delegation in need of breaking at either
* the source or destination, it will return -EWOULDBLOCK and return a
* reference to the inode in delegated_inode. The caller should then
* break the delegation and retry. Because breaking a delegation may
* take a long time, the caller should drop all locks before doing
* so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported.
*
* The worst of all namespace operations - renaming directory. "Perverted"
* doesn't even start to describe it. Somebody in UCB had a heck of a trip...
* Problems:
*
* a) we can get into loop creation.
* b) race potential - two innocent renames can create a loop together.
* That's where 4.4BSD screws up. Current fix: serialization on
* sb->s_vfs_rename_mutex. We might be more accurate, but that's another
* story.
* c) we may have to lock up to _four_ objects - parents and victim (if it exists),
* and source (if it's a non-directory or a subdirectory that moves to
* different parent).
* And that - after we got ->i_mutex on parents (until then we don't know
* whether the target exists). Solution: try to be smart with locking
* order for inodes. We rely on the fact that tree topology may change
* only under ->s_vfs_rename_mutex _and_ that parent of the object we
* move will be locked. Thus we can rank directories by the tree
* (ancestors first) and rank all non-directories after them.
* That works since everybody except rename does "lock parent, lookup,
* lock child" and rename is under ->s_vfs_rename_mutex.
* HOWEVER, it relies on the assumption that any object with ->lookup()
* has no more than 1 dentry. If "hybrid" objects will ever appear,
* we'd better make sure that there's no link(2) for them.
* d) conversion from fhandle to dentry may come in the wrong moment - when
* we are removing the target. Solution: we will have to grab ->i_mutex
* in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
* ->i_mutex on parents, which works but leads to some truly excessive
* locking].
*/
int vfs_rename(struct renamedata *rd)
{
int error;
struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir;
struct dentry *old_dentry = rd->old_dentry;
struct dentry *new_dentry = rd->new_dentry;
struct inode **delegated_inode = rd->delegated_inode;
unsigned int flags = rd->flags;
bool is_dir = d_is_dir(old_dentry);
struct inode *source = old_dentry->d_inode;
struct inode *target = new_dentry->d_inode;
bool new_is_dir = false;
unsigned max_links = new_dir->i_sb->s_max_links;
struct name_snapshot old_name;
bool lock_old_subdir, lock_new_subdir;
if (source == target)
return 0;
error = may_delete(rd->old_mnt_idmap, old_dir, old_dentry, is_dir);
if (error)
return error;
if (!target) {
error = may_create(rd->new_mnt_idmap, new_dir, new_dentry);
} else {
new_is_dir = d_is_dir(new_dentry);
if (!(flags & RENAME_EXCHANGE))
error = may_delete(rd->new_mnt_idmap, new_dir,
new_dentry, is_dir);
else
error = may_delete(rd->new_mnt_idmap, new_dir,
new_dentry, new_is_dir);
}
if (error)
return error;
if (!old_dir->i_op->rename)
return -EPERM;
/*
* If we are going to change the parent - check write permissions,
* we'll need to flip '..'.
*/
if (new_dir != old_dir) {
if (is_dir) {
error = inode_permission(rd->old_mnt_idmap, source,
MAY_WRITE);
if (error)
return error;
}
if ((flags & RENAME_EXCHANGE) && new_is_dir) {
error = inode_permission(rd->new_mnt_idmap, target,
MAY_WRITE);
if (error)
return error;
}
}
error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
flags);
if (error)
return error;
take_dentry_name_snapshot(&old_name, old_dentry);
dget(new_dentry);
/*
* Lock children.
* The source subdirectory needs to be locked on cross-directory
* rename or cross-directory exchange since its parent changes.
* The target subdirectory needs to be locked on cross-directory
* exchange due to parent change and on any rename due to becoming
* a victim.
* Non-directories need locking in all cases (for NFS reasons);
* they get locked after any subdirectories (in inode address order).
*
* NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE.
* NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex.
*/
lock_old_subdir = new_dir != old_dir;
lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE);
if (is_dir) {
if (lock_old_subdir)
inode_lock_nested(source, I_MUTEX_CHILD);
if (target && (!new_is_dir || lock_new_subdir))
inode_lock(target);
} else if (new_is_dir) {
if (lock_new_subdir)
inode_lock_nested(target, I_MUTEX_CHILD);
inode_lock(source);
} else {
lock_two_nondirectories(source, target);
}
error = -EPERM;
if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target)))
goto out;
error = -EBUSY;
if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
goto out;
if (max_links && new_dir != old_dir) {
error = -EMLINK;
if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
goto out;
if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
old_dir->i_nlink >= max_links)
goto out;
}
if (!is_dir) {
error = try_break_deleg(source, delegated_inode);
if (error)
goto out;
}
if (target && !new_is_dir) {
error = try_break_deleg(target, delegated_inode);
if (error)
goto out;
}
error = old_dir->i_op->rename(rd->new_mnt_idmap, old_dir, old_dentry,
new_dir, new_dentry, flags);
if (error)
goto out;
if (!(flags & RENAME_EXCHANGE) && target) {
if (is_dir) {
shrink_dcache_parent(new_dentry);
target->i_flags |= S_DEAD;
}
dont_mount(new_dentry);
detach_mounts(new_dentry);
}
if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
if (!(flags & RENAME_EXCHANGE))
d_move(old_dentry, new_dentry);
else
d_exchange(old_dentry, new_dentry);
}
out:
if (!is_dir || lock_old_subdir)
inode_unlock(source);
if (target && (!new_is_dir || lock_new_subdir))
inode_unlock(target);
dput(new_dentry);
if (!error) {
fsnotify_move(old_dir, new_dir, &old_name.name, is_dir,
!(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
if (flags & RENAME_EXCHANGE) {
fsnotify_move(new_dir, old_dir, &old_dentry->d_name,
new_is_dir, NULL, new_dentry);
}
}
release_dentry_name_snapshot(&old_name);
return error;
}
EXPORT_SYMBOL(vfs_rename);
int do_renameat2(int olddfd, struct filename *from, int newdfd,
struct filename *to, unsigned int flags)
{
struct renamedata rd;
struct dentry *old_dentry, *new_dentry;
struct dentry *trap;
struct path old_path, new_path;
struct qstr old_last, new_last;
int old_type, new_type;
struct inode *delegated_inode = NULL;
unsigned int lookup_flags = 0, target_flags =
LOOKUP_RENAME_TARGET | LOOKUP_CREATE;
bool should_retry = false;
int error = -EINVAL;
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
goto put_names;
if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
(flags & RENAME_EXCHANGE))
goto put_names;
if (flags & RENAME_EXCHANGE)
target_flags = 0;
if (flags & RENAME_NOREPLACE)
target_flags |= LOOKUP_EXCL;
retry:
error = filename_parentat(olddfd, from, lookup_flags, &old_path,
&old_last, &old_type);
if (error)
goto put_names;
error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
&new_type);
if (error)
goto exit1;
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
goto exit2;
error = -EBUSY;
if (old_type != LAST_NORM)
goto exit2;
if (flags & RENAME_NOREPLACE)
error = -EEXIST;
if (new_type != LAST_NORM)
goto exit2;
error = mnt_want_write(old_path.mnt);
if (error)
goto exit2;
retry_deleg:
trap = lock_rename(new_path.dentry, old_path.dentry);
if (IS_ERR(trap)) {
error = PTR_ERR(trap);
goto exit_lock_rename;
}
old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry,
lookup_flags);
error = PTR_ERR(old_dentry);
if (IS_ERR(old_dentry))
goto exit3;
new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry,
lookup_flags | target_flags);
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
goto exit4;
if (flags & RENAME_EXCHANGE) {
if (!d_is_dir(new_dentry)) {
error = -ENOTDIR;
if (new_last.name[new_last.len])
goto exit5;
}
}
/* unless the source is a directory trailing slashes give -ENOTDIR */
if (!d_is_dir(old_dentry)) {
error = -ENOTDIR;
if (old_last.name[old_last.len])
goto exit5;
if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
goto exit5;
}
/* source should not be ancestor of target */
error = -EINVAL;
if (old_dentry == trap)
goto exit5;
/* target should not be an ancestor of source */
if (!(flags & RENAME_EXCHANGE))
error = -ENOTEMPTY;
if (new_dentry == trap)
goto exit5;
error = security_path_rename(&old_path, old_dentry,
&new_path, new_dentry, flags);
if (error)
goto exit5;
rd.old_dir = old_path.dentry->d_inode;
rd.old_dentry = old_dentry;
rd.old_mnt_idmap = mnt_idmap(old_path.mnt);
rd.new_dir = new_path.dentry->d_inode;
rd.new_dentry = new_dentry;
rd.new_mnt_idmap = mnt_idmap(new_path.mnt);
rd.delegated_inode = &delegated_inode;
rd.flags = flags;
error = vfs_rename(&rd);
exit5:
dput(new_dentry);
exit4:
dput(old_dentry);
exit3:
unlock_rename(new_path.dentry, old_path.dentry);
exit_lock_rename:
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
mnt_drop_write(old_path.mnt);
exit2:
if (retry_estale(error, lookup_flags))
should_retry = true;
path_put(&new_path);
exit1:
path_put(&old_path);
if (should_retry) {
should_retry = false;
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
put_names:
putname(from);
putname(to);
return error;
}
SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
int, newdfd, const char __user *, newname, unsigned int, flags)
{
return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname),
flags);
}
SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
int, newdfd, const char __user *, newname)
{
return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname),
0);
}
SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
{
return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD,
getname(newname), 0);
}
int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen)
{
int copylen;
copylen = linklen;
if (unlikely(copylen > (unsigned) buflen))
copylen = buflen;
if (copy_to_user(buffer, link, copylen))
copylen = -EFAULT;
return copylen;
}
/**
* vfs_readlink - copy symlink body into userspace buffer
* @dentry: dentry on which to get symbolic link
* @buffer: user memory pointer
* @buflen: size of buffer
*
* Does not touch atime. That's up to the caller if necessary
*
* Does not call security hook.
*/
int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
struct inode *inode = d_inode(dentry);
DEFINE_DELAYED_CALL(done);
const char *link;
int res;
if (inode->i_opflags & IOP_CACHED_LINK)
return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen);
if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
if (unlikely(inode->i_op->readlink))
return inode->i_op->readlink(dentry, buffer, buflen);
if (!d_is_symlink(dentry))
return -EINVAL;
spin_lock(&inode->i_lock);
inode->i_opflags |= IOP_DEFAULT_READLINK;
spin_unlock(&inode->i_lock);
}
link = READ_ONCE(inode->i_link);
if (!link) {
link = inode->i_op->get_link(dentry, inode, &done);
if (IS_ERR(link))
return PTR_ERR(link);
}
res = readlink_copy(buffer, buflen, link, strlen(link));
do_delayed_call(&done);
return res;
}
EXPORT_SYMBOL(vfs_readlink);
/**
* vfs_get_link - get symlink body
* @dentry: dentry on which to get symbolic link
* @done: caller needs to free returned data with this
*
* Calls security hook and i_op->get_link() on the supplied inode.
*
* It does not touch atime. That's up to the caller if necessary.
*
* Does not work on "special" symlinks like /proc/$$/fd/N
*/
const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done)
{
const char *res = ERR_PTR(-EINVAL);
struct inode *inode = d_inode(dentry);
if (d_is_symlink(dentry)) {
res = ERR_PTR(security_inode_readlink(dentry));
if (!res)
res = inode->i_op->get_link(dentry, inode, done);
}
return res;
}
EXPORT_SYMBOL(vfs_get_link);
/* get the link contents into pagecache */
static char *__page_get_link(struct dentry *dentry, struct inode *inode,
struct delayed_call *callback)
{
struct page *page;
struct address_space *mapping = inode->i_mapping;
if (!dentry) {
page = find_get_page(mapping, 0);
if (!page)
return ERR_PTR(-ECHILD);
if (!PageUptodate(page)) {
put_page(page);
return ERR_PTR(-ECHILD);
}
} else {
page = read_mapping_page(mapping, 0, NULL);
if (IS_ERR(page))
return (char*)page;
}
set_delayed_call(callback, page_put_link, page);
BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
return page_address(page);
}
const char *page_get_link_raw(struct dentry *dentry, struct inode *inode,
struct delayed_call *callback)
{
return __page_get_link(dentry, inode, callback);
}
EXPORT_SYMBOL_GPL(page_get_link_raw);
const char *page_get_link(struct dentry *dentry, struct inode *inode,
struct delayed_call *callback)
{
char *kaddr = __page_get_link(dentry, inode, callback);
if (!IS_ERR(kaddr))
nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
return kaddr;
}
EXPORT_SYMBOL(page_get_link);
void page_put_link(void *arg)
{
put_page(arg);
}
EXPORT_SYMBOL(page_put_link);
int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
const char *link;
int res;
DEFINE_DELAYED_CALL(done);
link = page_get_link(dentry, d_inode(dentry), &done);
res = PTR_ERR(link);
if (!IS_ERR(link))
res = readlink_copy(buffer, buflen, link, strlen(link));
do_delayed_call(&done);
return res;
}
EXPORT_SYMBOL(page_readlink);
int page_symlink(struct inode *inode, const char *symname, int len)
{
struct address_space *mapping = inode->i_mapping;
const struct address_space_operations *aops = mapping->a_ops;
bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS);
struct folio *folio;
void *fsdata = NULL;
int err;
unsigned int flags;
retry:
if (nofs)
flags = memalloc_nofs_save();
err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata);
if (nofs)
memalloc_nofs_restore(flags);
if (err)
goto fail;
memcpy(folio_address(folio), symname, len - 1);
err = aops->write_end(NULL, mapping, 0, len - 1, len - 1,
folio, fsdata);
if (err < 0)
goto fail;
if (err < len-1)
goto retry;
mark_inode_dirty(inode);
return 0;
fail:
return err;
}
EXPORT_SYMBOL(page_symlink);
const struct inode_operations page_symlink_inode_operations = {
.get_link = page_get_link,
};
EXPORT_SYMBOL(page_symlink_inode_operations);
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/mman.h>
#include <linux/kvm_host.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/sched/signal.h>
#include <trace/events/kvm.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_pgtable.h>
#include <asm/kvm_pkvm.h>
#include <asm/kvm_ras.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/virt.h>
#include "trace.h"
static struct kvm_pgtable *hyp_pgtable;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
static unsigned long __ro_after_init hyp_idmap_start;
static unsigned long __ro_after_init hyp_idmap_end;
static phys_addr_t __ro_after_init hyp_idmap_vector;
u32 __ro_after_init __hyp_va_bits;
static unsigned long __ro_after_init io_map_base;
#define KVM_PGT_FN(fn) (!is_protected_kvm_enabled() ? fn : p ## fn)
static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
phys_addr_t size)
{
phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
return (boundary - 1 < end - 1) ? boundary : end;
}
static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
{
phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
return __stage2_range_addr_end(addr, end, size);
}
/*
* Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
* we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
* CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too
* long will also starve other vCPUs. We have to also make sure that the page
* tables are not freed while we released the lock.
*/
static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
phys_addr_t end,
int (*fn)(struct kvm_pgtable *, u64, u64),
bool resched)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
int ret;
u64 next;
do {
struct kvm_pgtable *pgt = mmu->pgt;
if (!pgt)
return -EINVAL;
next = stage2_range_addr_end(addr, end);
ret = fn(pgt, addr, next - addr);
if (ret)
break;
if (resched && next != end) cond_resched_rwlock_write(&kvm->mmu_lock); } while (addr = next, addr != end);
return ret;
}
#define stage2_apply_range_resched(mmu, addr, end, fn) \
stage2_apply_range(mmu, addr, end, fn, true)
/*
* Get the maximum number of page-tables pages needed to split a range
* of blocks into PAGE_SIZE PTEs. It assumes the range is already
* mapped at level 2, or at level 1 if allowed.
*/
static int kvm_mmu_split_nr_page_tables(u64 range)
{
int n = 0;
if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
n += DIV_ROUND_UP(range, PUD_SIZE);
n += DIV_ROUND_UP(range, PMD_SIZE);
return n;
}
static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
{
struct kvm_mmu_memory_cache *cache;
u64 chunk_size, min;
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
return true;
chunk_size = kvm->arch.mmu.split_page_chunk_size;
min = kvm_mmu_split_nr_page_tables(chunk_size);
cache = &kvm->arch.mmu.split_page_cache;
return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
}
static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
phys_addr_t end)
{
struct kvm_mmu_memory_cache *cache;
struct kvm_pgtable *pgt;
int ret, cache_capacity;
u64 next, chunk_size;
lockdep_assert_held_write(&kvm->mmu_lock);
chunk_size = kvm->arch.mmu.split_page_chunk_size;
cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);
if (chunk_size == 0)
return 0;
cache = &kvm->arch.mmu.split_page_cache;
do {
if (need_split_memcache_topup_or_resched(kvm)) {
write_unlock(&kvm->mmu_lock);
cond_resched();
/* Eager page splitting is best-effort. */
ret = __kvm_mmu_topup_memory_cache(cache,
cache_capacity,
cache_capacity);
write_lock(&kvm->mmu_lock);
if (ret)
break;
}
pgt = kvm->arch.mmu.pgt;
if (!pgt)
return -EINVAL;
next = __stage2_range_addr_end(addr, end, chunk_size);
ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache); if (ret)
break;
} while (addr = next, addr != end);
return ret;
}
static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
}
/**
* kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8
* @kvm: pointer to kvm structure.
*
* Interface to HYP function to flush all VM TLB entries
*/
int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
if (is_protected_kvm_enabled())
kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
else
kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
return 0;
}
int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
gfn_t gfn, u64 nr_pages)
{
u64 size = nr_pages << PAGE_SHIFT;
u64 addr = gfn << PAGE_SHIFT; if (is_protected_kvm_enabled()) kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
else
kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size);
return 0;
}
static bool kvm_is_device_pfn(unsigned long pfn)
{
return !pfn_is_map_memory(pfn);
}
static void *stage2_memcache_zalloc_page(void *arg)
{
struct kvm_mmu_memory_cache *mc = arg;
void *virt;
/* Allocated with __GFP_ZERO, so no need to zero */
virt = kvm_mmu_memory_cache_alloc(mc);
if (virt) kvm_account_pgtable_pages(virt, 1);
return virt;
}
static void *kvm_host_zalloc_pages_exact(size_t size)
{
return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
}
static void *kvm_s2_zalloc_pages_exact(size_t size)
{
void *virt = kvm_host_zalloc_pages_exact(size);
if (virt) kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT));
return virt;
}
static void kvm_s2_free_pages_exact(void *virt, size_t size)
{ kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT));
free_pages_exact(virt, size);
}
static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;
static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
{
struct page *page = container_of(head, struct page, rcu_head);
void *pgtable = page_to_virt(page);
s8 level = page_private(page);
KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level);
}
static void stage2_free_unlinked_table(void *addr, s8 level)
{
struct page *page = virt_to_page(addr);
set_page_private(page, (unsigned long)level);
call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb);
}
static void kvm_host_get_page(void *addr)
{ get_page(virt_to_page(addr));
}
static void kvm_host_put_page(void *addr)
{
put_page(virt_to_page(addr));
}
static void kvm_s2_put_page(void *addr)
{
struct page *p = virt_to_page(addr);
/* Dropping last refcount, the page will be freed */
if (page_count(p) == 1) kvm_account_pgtable_pages(addr, -1); put_page(p);
}
static int kvm_host_page_count(void *addr)
{ return page_count(virt_to_page(addr));
}
static phys_addr_t kvm_host_pa(void *addr)
{
return __pa(addr);
}
static void *kvm_host_va(phys_addr_t phys)
{ return __va(phys);
}
static void clean_dcache_guest_page(void *va, size_t size)
{ __clean_dcache_guest_page(va, size);
}
static void invalidate_icache_guest_page(void *va, size_t size)
{ __invalidate_icache_guest_page(va, size);
}
/*
* Unmapping vs dcache management:
*
* If a guest maps certain memory pages as uncached, all writes will
* bypass the data cache and go directly to RAM. However, the CPUs
* can still speculate reads (not writes) and fill cache lines with
* data.
*
* Those cache lines will be *clean* cache lines though, so a
* clean+invalidate operation is equivalent to an invalidate
* operation, because no cache lines are marked dirty.
*
* Those clean cache lines could be filled prior to an uncached write
* by the guest, and the cache coherent IO subsystem would therefore
* end up writing old data to disk.
*
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we flush to make sure the IO subsystem will
* never hit in the cache.
*
* This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
* we then fully enforce cacheability of RAM, no matter what the guest
* does.
*/
/**
* __unmap_stage2_range -- Clear stage2 page table entries to unmap a range
* @mmu: The KVM stage-2 MMU pointer
* @start: The intermediate physical base address of the range to unmap
* @size: The size of the area to unmap
* @may_block: Whether or not we are permitted to block
*
* Clear a range of stage-2 mappings, lowering the various ref-counts. Must
* be called while holding mmu_lock (unless for freeing the stage2 pgd before
* destroying the VM), otherwise another faulting VCPU may come in and mess
* with things behind our backs.
*/
static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size,
bool may_block)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
phys_addr_t end = start + size;
lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap),
may_block));
}
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
u64 size, bool may_block)
{
__unmap_stage2_range(mmu, start, size, may_block);
}
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush));
}
static void stage2_flush_memslot(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
kvm_stage2_flush_range(&kvm->arch.mmu, addr, end);
}
/**
* stage2_flush_vm - Invalidate cache for pages mapped in stage 2
* @kvm: The struct kvm pointer
*
* Go through the stage 2 page tables and invalidate any cache lines
* backing memory already mapped to the VM.
*/
static void stage2_flush_vm(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int idx, bkt;
idx = srcu_read_lock(&kvm->srcu);
write_lock(&kvm->mmu_lock);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, bkt, slots)
stage2_flush_memslot(kvm, memslot);
kvm_nested_s2_flush(kvm);
write_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
}
/**
* free_hyp_pgds - free Hyp-mode page tables
*/
void __init free_hyp_pgds(void)
{
mutex_lock(&kvm_hyp_pgd_mutex);
if (hyp_pgtable) {
kvm_pgtable_hyp_destroy(hyp_pgtable);
kfree(hyp_pgtable);
hyp_pgtable = NULL;
}
mutex_unlock(&kvm_hyp_pgd_mutex);
}
static bool kvm_host_owns_hyp_mappings(void)
{
if (is_kernel_in_hyp_mode())
return false;
if (static_branch_likely(&kvm_protected_mode_initialized))
return false;
/*
* This can happen at boot time when __create_hyp_mappings() is called
* after the hyp protection has been enabled, but the static key has
* not been flipped yet.
*/
if (!hyp_pgtable && is_protected_kvm_enabled())
return false;
WARN_ON(!hyp_pgtable);
return true;
}
int __create_hyp_mappings(unsigned long start, unsigned long size,
unsigned long phys, enum kvm_pgtable_prot prot)
{
int err;
if (WARN_ON(!kvm_host_owns_hyp_mappings()))
return -EINVAL;
mutex_lock(&kvm_hyp_pgd_mutex);
err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
mutex_unlock(&kvm_hyp_pgd_mutex);
return err;
}
static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
{
if (!is_vmalloc_addr(kaddr)) {
BUG_ON(!virt_addr_valid(kaddr));
return __pa(kaddr);
} else {
return page_to_phys(vmalloc_to_page(kaddr)) +
offset_in_page(kaddr);
}
}
struct hyp_shared_pfn {
u64 pfn;
int count;
struct rb_node node;
};
static DEFINE_MUTEX(hyp_shared_pfns_lock);
static struct rb_root hyp_shared_pfns = RB_ROOT;
static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node,
struct rb_node **parent)
{
struct hyp_shared_pfn *this;
*node = &hyp_shared_pfns.rb_node;
*parent = NULL;
while (**node) {
this = container_of(**node, struct hyp_shared_pfn, node);
*parent = **node;
if (this->pfn < pfn)
*node = &((**node)->rb_left);
else if (this->pfn > pfn)
*node = &((**node)->rb_right);
else
return this;
}
return NULL;
}
static int share_pfn_hyp(u64 pfn)
{
struct rb_node **node, *parent;
struct hyp_shared_pfn *this;
int ret = 0;
mutex_lock(&hyp_shared_pfns_lock);
this = find_shared_pfn(pfn, &node, &parent); if (this) { this->count++;
goto unlock;
}
this = kzalloc(sizeof(*this), GFP_KERNEL);
if (!this) {
ret = -ENOMEM;
goto unlock;
}
this->pfn = pfn;
this->count = 1;
rb_link_node(&this->node, parent, node);
rb_insert_color(&this->node, &hyp_shared_pfns);
ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1);
unlock:
mutex_unlock(&hyp_shared_pfns_lock);
return ret;
}
static int unshare_pfn_hyp(u64 pfn)
{
struct rb_node **node, *parent;
struct hyp_shared_pfn *this;
int ret = 0;
mutex_lock(&hyp_shared_pfns_lock);
this = find_shared_pfn(pfn, &node, &parent); if (WARN_ON(!this)) {
ret = -ENOENT;
goto unlock;
}
this->count--;
if (this->count)
goto unlock;
rb_erase(&this->node, &hyp_shared_pfns);
kfree(this);
ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1);
unlock:
mutex_unlock(&hyp_shared_pfns_lock);
return ret;
}
int kvm_share_hyp(void *from, void *to)
{
phys_addr_t start, end, cur;
u64 pfn;
int ret;
if (is_kernel_in_hyp_mode())
return 0;
/*
* The share hcall maps things in the 'fixed-offset' region of the hyp
* VA space, so we can only share physically contiguous data-structures
* for now.
*/
if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to))
return -EINVAL;
if (kvm_host_owns_hyp_mappings())
return create_hyp_mappings(from, to, PAGE_HYP);
start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
end = PAGE_ALIGN(__pa(to));
for (cur = start; cur < end; cur += PAGE_SIZE) {
pfn = __phys_to_pfn(cur);
ret = share_pfn_hyp(pfn); if (ret)
return ret;
}
return 0;
}
void kvm_unshare_hyp(void *from, void *to)
{
phys_addr_t start, end, cur;
u64 pfn;
if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from)
return;
start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
end = PAGE_ALIGN(__pa(to));
for (cur = start; cur < end; cur += PAGE_SIZE) {
pfn = __phys_to_pfn(cur);
WARN_ON(unshare_pfn_hyp(pfn));
}
}
/**
* create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
* @from: The virtual kernel start address of the range
* @to: The virtual kernel end address of the range (exclusive)
* @prot: The protection to be applied to this range
*
* The same virtual address as the kernel virtual address is also used
* in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
* physical pages.
*/
int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
{
phys_addr_t phys_addr;
unsigned long virt_addr;
unsigned long start = kern_hyp_va((unsigned long)from);
unsigned long end = kern_hyp_va((unsigned long)to);
if (is_kernel_in_hyp_mode())
return 0;
if (!kvm_host_owns_hyp_mappings())
return -EPERM;
start = start & PAGE_MASK;
end = PAGE_ALIGN(end);
for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
int err;
phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr,
prot);
if (err)
return err;
}
return 0;
}
static int __hyp_alloc_private_va_range(unsigned long base)
{
lockdep_assert_held(&kvm_hyp_pgd_mutex);
if (!PAGE_ALIGNED(base))
return -EINVAL;
/*
* Verify that BIT(VA_BITS - 1) hasn't been flipped by
* allocating the new area, as it would indicate we've
* overflowed the idmap/IO address range.
*/
if ((base ^ io_map_base) & BIT(VA_BITS - 1))
return -ENOMEM;
io_map_base = base;
return 0;
}
/**
* hyp_alloc_private_va_range - Allocates a private VA range.
* @size: The size of the VA range to reserve.
* @haddr: The hypervisor virtual start address of the allocation.
*
* The private virtual address (VA) range is allocated below io_map_base
* and aligned based on the order of @size.
*
* Return: 0 on success or negative error code on failure.
*/
int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
{
unsigned long base;
int ret = 0;
mutex_lock(&kvm_hyp_pgd_mutex);
/*
* This assumes that we have enough space below the idmap
* page to allocate our VAs. If not, the check in
* __hyp_alloc_private_va_range() will kick. A potential
* alternative would be to detect that overflow and switch
* to an allocation above the idmap.
*
* The allocated size is always a multiple of PAGE_SIZE.
*/
size = PAGE_ALIGN(size);
base = io_map_base - size;
ret = __hyp_alloc_private_va_range(base);
mutex_unlock(&kvm_hyp_pgd_mutex);
if (!ret)
*haddr = base;
return ret;
}
static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
unsigned long *haddr,
enum kvm_pgtable_prot prot)
{
unsigned long addr;
int ret = 0;
if (!kvm_host_owns_hyp_mappings()) {
addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
phys_addr, size, prot);
if (IS_ERR_VALUE(addr))
return addr;
*haddr = addr;
return 0;
}
size = PAGE_ALIGN(size + offset_in_page(phys_addr));
ret = hyp_alloc_private_va_range(size, &addr);
if (ret)
return ret;
ret = __create_hyp_mappings(addr, size, phys_addr, prot);
if (ret)
return ret;
*haddr = addr + offset_in_page(phys_addr);
return ret;
}
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
{
unsigned long base;
size_t size;
int ret;
mutex_lock(&kvm_hyp_pgd_mutex);
/*
* Efficient stack verification using the NVHE_STACK_SHIFT bit implies
* an alignment of our allocation on the order of the size.
*/
size = NVHE_STACK_SIZE * 2;
base = ALIGN_DOWN(io_map_base - size, size);
ret = __hyp_alloc_private_va_range(base);
mutex_unlock(&kvm_hyp_pgd_mutex);
if (ret) {
kvm_err("Cannot allocate hyp stack guard page\n");
return ret;
}
/*
* Since the stack grows downwards, map the stack to the page
* at the higher address and leave the lower guard page
* unbacked.
*
* Any valid stack address now has the NVHE_STACK_SHIFT bit as 1
* and addresses corresponding to the guard page have the
* NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection.
*/
ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE,
phys_addr, PAGE_HYP);
if (ret)
kvm_err("Cannot map hyp stack\n");
*haddr = base + size;
return ret;
}
/**
* create_hyp_io_mappings - Map IO into both kernel and HYP
* @phys_addr: The physical start address which gets mapped
* @size: Size of the region being mapped
* @kaddr: Kernel VA for this mapping
* @haddr: HYP VA for this mapping
*/
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
void __iomem **kaddr,
void __iomem **haddr)
{
unsigned long addr;
int ret;
if (is_protected_kvm_enabled())
return -EPERM;
*kaddr = ioremap(phys_addr, size);
if (!*kaddr)
return -ENOMEM;
if (is_kernel_in_hyp_mode()) {
*haddr = *kaddr;
return 0;
}
ret = __create_hyp_private_mapping(phys_addr, size,
&addr, PAGE_HYP_DEVICE);
if (ret) {
iounmap(*kaddr);
*kaddr = NULL;
*haddr = NULL;
return ret;
}
*haddr = (void __iomem *)addr;
return 0;
}
/**
* create_hyp_exec_mappings - Map an executable range into HYP
* @phys_addr: The physical start address which gets mapped
* @size: Size of the region being mapped
* @haddr: HYP VA for this mapping
*/
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr)
{
unsigned long addr;
int ret;
BUG_ON(is_kernel_in_hyp_mode());
ret = __create_hyp_private_mapping(phys_addr, size,
&addr, PAGE_HYP_EXEC);
if (ret) {
*haddr = NULL;
return ret;
}
*haddr = (void *)addr;
return 0;
}
static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
/* We shouldn't need any other callback to walk the PT */
.phys_to_virt = kvm_host_va,
};
static int get_user_mapping_size(struct kvm *kvm, u64 addr)
{
struct kvm_pgtable pgt = {
.pgd = (kvm_pteref_t)kvm->mm->pgd,
.ia_bits = vabits_actual,
.start_level = (KVM_PGTABLE_LAST_LEVEL -
ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1),
.mm_ops = &kvm_user_mm_ops,
};
unsigned long flags;
kvm_pte_t pte = 0; /* Keep GCC quiet... */
s8 level = S8_MAX;
int ret;
/*
* Disable IRQs so that we hazard against a concurrent
* teardown of the userspace page tables (which relies on
* IPI-ing threads).
*/
local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); local_irq_restore(flags); if (ret)
return ret;
/*
* Not seeing an error, but not updating level? Something went
* deeply wrong...
*/
if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
return -EFAULT;
if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
return -EFAULT;
/* Oops, the userspace PTs are gone... Replay the fault */
if (!kvm_pte_valid(pte))
return -EAGAIN;
return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
}
static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.zalloc_page = stage2_memcache_zalloc_page,
.zalloc_pages_exact = kvm_s2_zalloc_pages_exact,
.free_pages_exact = kvm_s2_free_pages_exact,
.free_unlinked_table = stage2_free_unlinked_table,
.get_page = kvm_host_get_page,
.put_page = kvm_s2_put_page,
.page_count = kvm_host_page_count,
.phys_to_virt = kvm_host_va,
.virt_to_phys = kvm_host_pa,
.dcache_clean_inval_poc = clean_dcache_guest_page,
.icache_inval_pou = invalidate_icache_guest_page,
};
static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
{
u32 kvm_ipa_limit = get_kvm_ipa_limit();
u64 mmfr0, mmfr1;
u32 phys_shift;
if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
return -EINVAL;
phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
if (is_protected_kvm_enabled()) {
phys_shift = kvm_ipa_limit;
} else if (phys_shift) {
if (phys_shift > kvm_ipa_limit ||
phys_shift < ARM64_MIN_PARANGE_BITS)
return -EINVAL;
} else {
phys_shift = KVM_PHYS_SHIFT;
if (phys_shift > kvm_ipa_limit) { pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
current->comm);
return -EINVAL;
}
}
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
return 0;
}
/**
* kvm_init_stage2_mmu - Initialise a S2 MMU structure
* @kvm: The pointer to the KVM structure
* @mmu: The pointer to the s2 MMU structure
* @type: The machine type of the virtual machine
*
* Allocates only the stage-2 HW PGD level table(s).
* Note we don't need locking here as this is only called in two cases:
*
* - when the VM is created, which can't race against anything
*
* - when secondary kvm_s2_mmu structures are initialised for NV
* guests, and the caller must hold kvm->lock as this is called on a
* per-vcpu basis.
*/
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
{
int cpu, err;
struct kvm_pgtable *pgt;
/*
* If we already have our page tables in place, and that the
* MMU context is the canonical one, we have a bug somewhere,
* as this is only supposed to ever happen once per VM.
*
* Otherwise, we're building nested page tables, and that's
* probably because userspace called KVM_ARM_VCPU_INIT more
* than once on the same vcpu. Since that's actually legal,
* don't kick a fuss and leave gracefully.
*/
if (mmu->pgt != NULL) {
if (kvm_is_nested_s2_mmu(kvm, mmu))
return 0;
kvm_err("kvm_arch already initialized?\n");
return -EINVAL;
}
err = kvm_init_ipa_range(mmu, type);
if (err)
return err;
pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
if (!pgt)
return -ENOMEM;
mmu->arch = &kvm->arch;
err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops); if (err)
goto out_free_pgtable;
mmu->pgt = pgt;
if (is_protected_kvm_enabled())
return 0;
mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
if (!mmu->last_vcpu_ran) {
err = -ENOMEM;
goto out_destroy_pgtable;
}
for_each_possible_cpu(cpu)
*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
/* The eager page splitting is disabled by default */
mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
mmu->split_page_cache.gfp_zero = __GFP_ZERO;
mmu->pgd_phys = __pa(pgt->pgd);
if (kvm_is_nested_s2_mmu(kvm, mmu)) kvm_init_nested_s2_mmu(mmu);
return 0;
out_destroy_pgtable:
KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
out_free_pgtable:
kfree(pgt);
return err;
}
void kvm_uninit_stage2_mmu(struct kvm *kvm)
{ kvm_free_stage2_pgd(&kvm->arch.mmu);
kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
}
static void stage2_unmap_memslot(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
hva_t hva = memslot->userspace_addr;
phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t size = PAGE_SIZE * memslot->npages;
hva_t reg_end = hva + size;
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them to find out if we should
* unmap any of them.
*
* +--------------------------------------------+
* +---------------+----------------+ +----------------+
* | : VMA 1 | VMA 2 | | VMA 3 : |
* +---------------+----------------+ +----------------+
* | memory region |
* +--------------------------------------------+
*/
do {
struct vm_area_struct *vma;
hva_t vm_start, vm_end;
vma = find_vma_intersection(current->mm, hva, reg_end);
if (!vma)
break;
/*
* Take the intersection of this VMA with the memory region
*/
vm_start = max(hva, vma->vm_start);
vm_end = min(reg_end, vma->vm_end);
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
}
hva = vm_end;
} while (hva < reg_end);
}
/**
* stage2_unmap_vm - Unmap Stage-2 RAM mappings
* @kvm: The struct kvm pointer
*
* Go through the memregions and unmap any regular RAM
* backing memory already mapped to the VM.
*/
void stage2_unmap_vm(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int idx, bkt;
idx = srcu_read_lock(&kvm->srcu);
mmap_read_lock(current->mm);
write_lock(&kvm->mmu_lock);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, bkt, slots)
stage2_unmap_memslot(kvm, memslot);
kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
mmap_read_unlock(current->mm);
srcu_read_unlock(&kvm->srcu, idx);
}
void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
struct kvm_pgtable *pgt = NULL;
write_lock(&kvm->mmu_lock);
pgt = mmu->pgt;
if (pgt) {
mmu->pgd_phys = 0;
mmu->pgt = NULL;
free_percpu(mmu->last_vcpu_ran);
}
write_unlock(&kvm->mmu_lock);
if (pgt) {
KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
kfree(pgt);
}
}
static void hyp_mc_free_fn(void *addr, void *mc)
{
struct kvm_hyp_memcache *memcache = mc;
if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
kvm_account_pgtable_pages(addr, -1);
free_page((unsigned long)addr);
}
static void *hyp_mc_alloc_fn(void *mc)
{
struct kvm_hyp_memcache *memcache = mc;
void *addr;
addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
kvm_account_pgtable_pages(addr, 1);
return addr;
}
void free_hyp_memcache(struct kvm_hyp_memcache *mc)
{
if (!is_protected_kvm_enabled())
return;
kfree(mc->mapping);
__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc);
}
int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
{
if (!is_protected_kvm_enabled())
return 0;
if (!mc->mapping) {
mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT);
if (!mc->mapping)
return -ENOMEM;
}
return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
kvm_host_pa, mc);
}
/**
* kvm_phys_addr_ioremap - map a device range to guest IPA
*
* @kvm: The KVM pointer
* @guest_ipa: The IPA at which to insert the mapping
* @pa: The physical address of the device
* @size: The size of the mapping
* @writable: Whether or not to create a writable mapping
*/
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
phys_addr_t pa, unsigned long size, bool writable)
{
phys_addr_t addr;
int ret = 0;
struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO };
struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
struct kvm_pgtable *pgt = mmu->pgt;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
KVM_PGTABLE_PROT_R |
(writable ? KVM_PGTABLE_PROT_W : 0);
if (is_protected_kvm_enabled())
return -EPERM;
size += offset_in_page(guest_ipa);
guest_ipa &= PAGE_MASK;
for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) {
ret = kvm_mmu_topup_memory_cache(&cache,
kvm_mmu_cache_min_pages(mmu));
if (ret)
break;
write_lock(&kvm->mmu_lock);
ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE,
pa, prot, &cache, 0);
write_unlock(&kvm->mmu_lock);
if (ret)
break;
pa += PAGE_SIZE;
}
kvm_mmu_free_memory_cache(&cache);
return ret;
}
/**
* kvm_stage2_wp_range() - write protect stage2 memory region range
* @mmu: The KVM stage-2 MMU pointer
* @addr: Start address of range
* @end: End address of range
*/
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect));
}
/**
* kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
* @kvm: The KVM pointer
* @slot: The memory slot to write protect
*
* Called to start logging dirty pages after memory region
* KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
* all present PUD, PMD and PTEs are write protected in the memory region.
* Afterwards read of dirty page log can be called.
*
* Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
* serializing operations for VM memory regions.
*/
static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
phys_addr_t start, end;
if (WARN_ON_ONCE(!memslot))
return;
start = memslot->base_gfn << PAGE_SHIFT;
end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
kvm_nested_s2_wp(kvm);
write_unlock(&kvm->mmu_lock);
kvm_flush_remote_tlbs_memslot(kvm, memslot);
}
/**
* kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
* pages for memory slot
* @kvm: The KVM pointer
* @slot: The memory slot to split
*
* Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
* serializing operations for VM memory regions.
*/
static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
phys_addr_t start, end;
lockdep_assert_held(&kvm->slots_lock);
slots = kvm_memslots(kvm);
memslot = id_to_memslot(slots, slot);
start = memslot->base_gfn << PAGE_SHIFT;
end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
kvm_mmu_split_huge_pages(kvm, start, end);
write_unlock(&kvm->mmu_lock);
}
/*
* kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages.
* @kvm: The KVM pointer
* @slot: The memory slot associated with mask
* @gfn_offset: The gfn offset in memory slot
* @mask: The mask of pages at offset 'gfn_offset' in this memory
* slot to enable dirty logging on
*
* Writes protect selected pages to enable dirty logging, and then
* splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock.
*/
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn_offset, unsigned long mask)
{
phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT;
phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
lockdep_assert_held_write(&kvm->mmu_lock);
kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
/*
* Eager-splitting is done when manual-protect is set. We
* also check for initially-all-set because we can avoid
* eager-splitting if initially-all-set is false.
* Initially-all-set equal false implies that huge-pages were
* already split when enabling dirty logging: no need to do it
* again.
*/
if (kvm_dirty_log_manual_protect_and_init_set(kvm))
kvm_mmu_split_huge_pages(kvm, start, end);
kvm_nested_s2_wp(kvm);
}
static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
{
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
}
static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
unsigned long hva,
unsigned long map_size)
{
gpa_t gpa_start;
hva_t uaddr_start, uaddr_end;
size_t size;
/* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */
if (map_size == PAGE_SIZE)
return true;
/* pKVM only supports PMD_SIZE huge-mappings */
if (is_protected_kvm_enabled() && map_size != PMD_SIZE)
return false;
size = memslot->npages * PAGE_SIZE;
gpa_start = memslot->base_gfn << PAGE_SHIFT;
uaddr_start = memslot->userspace_addr;
uaddr_end = uaddr_start + size;
/*
* Pages belonging to memslots that don't have the same alignment
* within a PMD/PUD for userspace and IPA cannot be mapped with stage-2
* PMD/PUD entries, because we'll end up mapping the wrong pages.
*
* Consider a layout like the following:
*
* memslot->userspace_addr:
* +-----+--------------------+--------------------+---+
* |abcde|fgh Stage-1 block | Stage-1 block tv|xyz|
* +-----+--------------------+--------------------+---+
*
* memslot->base_gfn << PAGE_SHIFT:
* +---+--------------------+--------------------+-----+
* |abc|def Stage-2 block | Stage-2 block |tvxyz|
* +---+--------------------+--------------------+-----+
*
* If we create those stage-2 blocks, we'll end up with this incorrect
* mapping:
* d -> f
* e -> g
* f -> h
*/
if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
return false;
/*
* Next, let's make sure we're not trying to map anything not covered
* by the memslot. This means we have to prohibit block size mappings
* for the beginning and end of a non-block aligned and non-block sized
* memory slot (illustrated by the head and tail parts of the
* userspace view above containing pages 'abcde' and 'xyz',
* respectively).
*
* Note that it doesn't matter if we do the check using the
* userspace_addr or the base_gfn, as both are equally aligned (per
* the check above) and equally sized.
*/
return (hva & ~(map_size - 1)) >= uaddr_start &&
(hva & ~(map_size - 1)) + map_size <= uaddr_end;
}
/*
* Check if the given hva is backed by a transparent huge page (THP) and
* whether it can be mapped using block mapping in stage2. If so, adjust
* the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently
* supported. This will need to be updated to support other THP sizes.
*
* Returns the size of the mapping.
*/
static long
transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long hva, kvm_pfn_t *pfnp,
phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
/*
* Make sure the adjustment is done only for THP pages. Also make
* sure that the HVA and IPA are sufficiently aligned and that the
* block map is contained within the memslot.
*/
if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { int sz = get_user_mapping_size(kvm, hva); if (sz < 0)
return sz;
if (sz < PMD_SIZE)
return PAGE_SIZE;
*ipap &= PMD_MASK;
pfn &= ~(PTRS_PER_PMD - 1);
*pfnp = pfn;
return PMD_SIZE;
}
/* Use page mapping if we cannot use block mapping. */
return PAGE_SIZE;
}
static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva)
{
unsigned long pa;
if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP))
return huge_page_shift(hstate_vma(vma));
if (!(vma->vm_flags & VM_PFNMAP))
return PAGE_SHIFT;
VM_BUG_ON(is_vm_hugetlb_page(vma));
pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start);
#ifndef __PAGETABLE_PMD_FOLDED
if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) && ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start &&
ALIGN(hva, PUD_SIZE) <= vma->vm_end)
return PUD_SHIFT;
#endif
if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) && ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start &&
ALIGN(hva, PMD_SIZE) <= vma->vm_end)
return PMD_SHIFT;
return PAGE_SHIFT;
}
/*
* The page will be mapped in stage 2 as Normal Cacheable, so the VM will be
* able to see the page's tags and therefore they must be initialised first. If
* PG_mte_tagged is set, tags have already been initialised.
*
* The race in the test/set of the PG_mte_tagged flag is handled by:
* - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs
* racing to santise the same page
* - mmap_lock protects between a VM faulting a page in and the VMM performing
* an mprotect() to add VM_MTE
*/
static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
unsigned long size)
{
unsigned long i, nr_pages = size >> PAGE_SHIFT;
struct page *page = pfn_to_page(pfn);
struct folio *folio = page_folio(page);
if (!kvm_has_mte(kvm))
return;
if (folio_test_hugetlb(folio)) {
/* Hugetlb has MTE flags set on head page only */
if (folio_try_hugetlb_mte_tagging(folio)) {
for (i = 0; i < nr_pages; i++, page++)
mte_clear_page_tags(page_address(page));
folio_set_hugetlb_mte_tagged(folio);
}
return;
}
for (i = 0; i < nr_pages; i++, page++) {
if (try_page_mte_tagging(page)) {
mte_clear_page_tags(page_address(page));
set_page_mte_tagged(page);
}
}
}
static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
{
return vma->vm_flags & VM_MTE_ALLOWED;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_s2_trans *nested,
struct kvm_memory_slot *memslot, unsigned long hva,
bool fault_is_perm)
{
int ret = 0;
bool write_fault, writable, force_pte = false;
bool exec_fault, mte_allowed;
bool device = false, vfio_allow_any_uc = false;
unsigned long mmu_seq;
phys_addr_t ipa = fault_ipa;
struct kvm *kvm = vcpu->kvm;
struct vm_area_struct *vma;
short vma_shift;
void *memcache;
gfn_t gfn;
kvm_pfn_t pfn;
bool logging_active = memslot_is_logging(memslot);
long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
struct kvm_pgtable *pgt;
struct page *page;
enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); write_fault = kvm_is_write_fault(vcpu);
exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault); if (fault_is_perm && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
/*
* Permission faults just need to update the existing leaf entry,
* and so normally don't require allocations from the memcache. The
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
if (!fault_is_perm || (logging_active && write_fault)) {
int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
if (!is_protected_kvm_enabled()) { memcache = &vcpu->arch.mmu_page_cache;
ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
} else {
memcache = &vcpu->arch.pkvm_memcache;
ret = topup_hyp_memcache(memcache, min_pages);
}
if (ret)
return ret;
}
/*
* Let's check if we will get back a huge page backed by hugetlbfs, or
* get block mapping for device MMIO region.
*/
mmap_read_lock(current->mm);
vma = vma_lookup(current->mm, hva);
if (unlikely(!vma)) {
kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
mmap_read_unlock(current->mm);
return -EFAULT;
}
/*
* logging_active is guaranteed to never be true for VM_PFNMAP
* memslots.
*/
if (logging_active) {
force_pte = true;
vma_shift = PAGE_SHIFT;
} else {
vma_shift = get_vma_page_shift(vma, hva);
}
switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
case PUD_SHIFT:
if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
break;
fallthrough;
#endif
case CONT_PMD_SHIFT:
vma_shift = PMD_SHIFT;
fallthrough;
case PMD_SHIFT:
if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE))
break;
fallthrough;
case CONT_PTE_SHIFT:
vma_shift = PAGE_SHIFT;
force_pte = true;
fallthrough;
case PAGE_SHIFT:
break;
default:
WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
}
vma_pagesize = 1UL << vma_shift;
if (nested) {
unsigned long max_map_size;
max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE;
ipa = kvm_s2_trans_output(nested);
/*
* If we're about to create a shadow stage 2 entry, then we
* can only create a block mapping if the guest stage 2 page
* table uses at least as big a mapping.
*/
max_map_size = min(kvm_s2_trans_size(nested), max_map_size);
/*
* Be careful that if the mapping size falls between
* two host sizes, take the smallest of the two.
*/
if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE)
max_map_size = PMD_SIZE;
else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE)
max_map_size = PAGE_SIZE;
force_pte = (max_map_size == PAGE_SIZE);
vma_pagesize = min(vma_pagesize, (long)max_map_size);
}
/*
* Both the canonical IPA and fault IPA must be hugepage-aligned to
* ensure we find the right PFN and lay down the mapping in the right
* place.
*/
if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
fault_ipa &= ~(vma_pagesize - 1);
ipa &= ~(vma_pagesize - 1);
}
gfn = ipa >> PAGE_SHIFT;
mte_allowed = kvm_vma_mte_allowed(vma);
vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
/* Don't use the VMA after the unlock -- it may have vanished */
vma = NULL;
/*
* Read mmu_invalidate_seq so that KVM can detect if the results of
* vma_lookup() or __kvm_faultin_pfn() become stale prior to
* acquiring kvm->mmu_lock.
*
* Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
* with the smp_wmb() in kvm_mmu_invalidate_end().
*/
mmu_seq = vcpu->kvm->mmu_invalidate_seq;
mmap_read_unlock(current->mm);
pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
&writable, &page);
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
return 0;
}
if (is_error_noslot_pfn(pfn))
return -EFAULT;
if (kvm_is_device_pfn(pfn)) {
/*
* If the page was identified as device early by looking at
* the VMA flags, vma_pagesize is already representing the
* largest quantity we can map. If instead it was mapped
* via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE
* and must not be upgraded.
*
* In both cases, we don't let transparent_hugepage_adjust()
* change things at the last minute.
*/
device = true;
} else if (logging_active && !write_fault) {
/*
* Only actually map the page as writable if this was a write
* fault.
*/
writable = false;
}
if (exec_fault && device)
return -ENOEXEC;
/*
* Potentially reduce shadow S2 permissions to match the guest's own
* S2. For exec faults, we'd only reach this point if the guest
* actually allowed it (see kvm_s2_handle_perm_fault).
*
* Also encode the level of the original translation in the SW bits
* of the leaf entry as a proxy for the span of that translation.
* This will be retrieved on TLB invalidation from the guest and
* used to limit the invalidation scope if a TTL hint or a range
* isn't provided.
*/
if (nested) { writable &= kvm_s2_trans_writable(nested);
if (!kvm_s2_trans_readable(nested))
prot &= ~KVM_PGTABLE_PROT_R;
prot |= kvm_encode_nested_level(nested);
}
kvm_fault_lock(kvm);
pgt = vcpu->arch.hw_mmu->pgt;
if (mmu_invalidate_retry(kvm, mmu_seq)) {
ret = -EAGAIN;
goto out_unlock;
}
/*
* If we are not forced to use page mapping, check if we are
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { if (fault_is_perm && fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
hva, &pfn,
&fault_ipa);
if (vma_pagesize < 0) { ret = vma_pagesize;
goto out_unlock;
}
}
if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (mte_allowed) { sanitise_mte_tags(kvm, pfn, vma_pagesize);
} else {
ret = -EFAULT;
goto out_unlock;
}
}
if (writable)
prot |= KVM_PGTABLE_PROT_W;
if (exec_fault)
prot |= KVM_PGTABLE_PROT_X;
if (device) {
if (vfio_allow_any_uc)
prot |= KVM_PGTABLE_PROT_NORMAL_NC;
else
prot |= KVM_PGTABLE_PROT_DEVICE; } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) && (!nested || kvm_s2_trans_executable(nested))) {
prot |= KVM_PGTABLE_PROT_X;
}
/*
* Under the premise of getting a FSC_PERM fault, we just need to relax
* permissions only if vma_pagesize equals fault_granule. Otherwise,
* kvm_pgtable_stage2_map() should be called to change block size.
*/
if (fault_is_perm && vma_pagesize == fault_granule) {
/*
* Drop the SW bits in favour of those stored in the
* PTE, which will be preserved.
*/
prot &= ~KVM_NV_GUEST_MAP_SZ;
ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags);
} else {
ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize,
__pfn_to_phys(pfn), prot,
memcache, flags);
}
out_unlock:
kvm_release_faultin_page(kvm, page, !!ret, writable); kvm_fault_unlock(kvm);
/* Mark the page dirty only if the fault is handled successfully */
if (writable && !ret)
mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0;}
/* Resolve the access fault by making the page young again. */
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
struct kvm_s2_mmu *mmu;
trace_kvm_access_fault(fault_ipa);
read_lock(&vcpu->kvm->mmu_lock);
mmu = vcpu->arch.hw_mmu;
KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags);
read_unlock(&vcpu->kvm->mmu_lock);
}
/**
* kvm_handle_guest_abort - handles all 2nd stage aborts
* @vcpu: the VCPU pointer
*
* Any abort that gets to the host is almost guaranteed to be caused by a
* missing second stage translation table entry, which can mean that either the
* guest simply needs more memory and we must allocate an appropriate page or it
* can mean that the guest tried to access I/O memory, which is emulated by user
* space. The distinction is based on the IPA causing the fault and whether this
* memory region has been registered as standard RAM by user space.
*/
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
{
struct kvm_s2_trans nested_trans, *nested = NULL;
unsigned long esr;
phys_addr_t fault_ipa; /* The address we faulted on */
phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
struct kvm_memory_slot *memslot;
unsigned long hva;
bool is_iabt, write_fault, writable;
gfn_t gfn;
int ret, idx;
/* Synchronous External Abort? */
if (kvm_vcpu_abt_issea(vcpu)) {
/*
* For RAS the host kernel may handle this abort.
* There is no need to pass the error into the guest.
*/
if (kvm_handle_guest_sea()) kvm_inject_vabt(vcpu);
return 1;
}
esr = kvm_vcpu_get_esr(vcpu);
/*
* The fault IPA should be reliable at this point as we're not dealing
* with an SEA.
*/
ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
return -EFAULT;
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
if (esr_fsc_is_translation_fault(esr)) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
return 1;
}
/* Falls between the IPA range and the PARange? */
if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
if (is_iabt)
kvm_inject_pabt(vcpu, fault_ipa);
else
kvm_inject_dabt(vcpu, fault_ipa);
return 1;
}
}
trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr) &&
!esr_fsc_is_access_flag_fault(esr)) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
(unsigned long)kvm_vcpu_get_esr(vcpu));
return -EFAULT;
}
idx = srcu_read_lock(&vcpu->kvm->srcu);
/*
* We may have faulted on a shadow stage 2 page table if we are
* running a nested guest. In this case, we have to resolve the L2
* IPA to the L1 IPA first, before knowing what kind of memory should
* back the L1 IPA.
*
* If the shadow stage 2 page table walk faults, then we simply inject
* this to the guest and carry on.
*
* If there are no shadow S2 PTs because S2 is disabled, there is
* nothing to walk and we treat it as a 1:1 before going through the
* canonical translation.
*/
if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) &&
vcpu->arch.hw_mmu->nested_stage2_enabled) {
u32 esr;
ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
if (ret) {
esr = kvm_s2_trans_esr(&nested_trans);
kvm_inject_s2_fault(vcpu, esr);
goto out_unlock;
}
ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
if (ret) {
esr = kvm_s2_trans_esr(&nested_trans);
kvm_inject_s2_fault(vcpu, esr);
goto out_unlock;
}
ipa = kvm_s2_trans_output(&nested_trans);
nested = &nested_trans;
}
gfn = ipa >> PAGE_SHIFT;
memslot = gfn_to_memslot(vcpu->kvm, gfn);
hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
write_fault = kvm_is_write_fault(vcpu); if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
/*
* The guest has put either its instructions or its page-tables
* somewhere it shouldn't have. Userspace won't be able to do
* anything about this (there's no syndrome for a start), so
* re-inject the abort back into the guest.
*/
if (is_iabt) {
ret = -ENOEXEC;
goto out;
}
if (kvm_vcpu_abt_iss1tw(vcpu)) {
kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
ret = 1;
goto out_unlock;
}
/*
* Check for a cache maintenance operation. Since we
* ended-up here, we know it is outside of any memory
* slot. But we can't find out if that is for a device,
* or if the guest is just being stupid. The only thing
* we know for sure is that this range cannot be cached.
*
* So let's assume that the guest is just being
* cautious, and skip the instruction.
*/
if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { kvm_incr_pc(vcpu);
ret = 1;
goto out_unlock;
}
/*
* The IPA is reported as [MAX:12], so we need to
* complement it with the bottom 12 bits from the
* faulting VA. This is always 12 bits, irrespective
* of the page size.
*/
ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
ret = io_mem_abort(vcpu, ipa);
goto out_unlock;
}
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
if (esr_fsc_is_access_flag_fault(esr)) {
handle_access_fault(vcpu, fault_ipa);
ret = 1;
goto out_unlock;
}
ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
esr_fsc_is_permission_fault(esr));
if (ret == 0)
ret = 1;
out:
if (ret == -ENOEXEC) {
kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
ret = 1;
}
out_unlock:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{ if (!kvm->arch.mmu.pgt)
return false;
__unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT,
(range->end - range->start) << PAGE_SHIFT,
range->may_block);
kvm_nested_s2_unmap(kvm, range->may_block);
return false;
}
bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
u64 size = (range->end - range->start) << PAGE_SHIFT;
if (!kvm->arch.mmu.pgt)
return false;
return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,
range->start << PAGE_SHIFT,
size, true);
/*
* TODO: Handle nested_mmu structures here using the reverse mapping in
* a later version of patch series.
*/
}
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
u64 size = (range->end - range->start) << PAGE_SHIFT;
if (!kvm->arch.mmu.pgt)
return false;
return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,
range->start << PAGE_SHIFT,
size, false);
}
phys_addr_t kvm_mmu_get_httbr(void)
{
return __pa(hyp_pgtable->pgd);
}
phys_addr_t kvm_get_idmap_vector(void)
{
return hyp_idmap_vector;
}
static int kvm_map_idmap_text(void)
{
unsigned long size = hyp_idmap_end - hyp_idmap_start;
int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start,
PAGE_HYP_EXEC);
if (err)
kvm_err("Failed to idmap %lx-%lx\n",
hyp_idmap_start, hyp_idmap_end);
return err;
}
static void *kvm_hyp_zalloc_page(void *arg)
{
return (void *)get_zeroed_page(GFP_KERNEL);
}
static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
.zalloc_page = kvm_hyp_zalloc_page,
.get_page = kvm_host_get_page,
.put_page = kvm_host_put_page,
.phys_to_virt = kvm_host_va,
.virt_to_phys = kvm_host_pa,
};
int __init kvm_mmu_init(u32 *hyp_va_bits)
{
int err;
u32 idmap_bits;
u32 kernel_bits;
hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end);
hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE);
hyp_idmap_vector = __pa_symbol(__kvm_hyp_init);
/*
* We rely on the linker script to ensure at build time that the HYP
* init code does not cross a page boundary.
*/
BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
/*
* The ID map is always configured for 48 bits of translation, which
* may be fewer than the number of VA bits used by the regular kernel
* stage 1, when VA_BITS=52.
*
* At EL2, there is only one TTBR register, and we can't switch between
* translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom
* line: we need to use the extended range with *both* our translation
* tables.
*
* So use the maximum of the idmap VA bits and the regular kernel stage
* 1 VA bits to assure that the hypervisor can both ID map its code page
* and map any kernel memory.
*/
idmap_bits = IDMAP_VA_BITS;
kernel_bits = vabits_actual;
*hyp_va_bits = max(idmap_bits, kernel_bits);
kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits);
kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
kvm_debug("HYP VA range: %lx:%lx\n",
kern_hyp_va(PAGE_OFFSET),
kern_hyp_va((unsigned long)high_memory - 1));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
hyp_idmap_start < kern_hyp_va((unsigned long)high_memory - 1) &&
hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
*/
kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
err = -EINVAL;
goto out;
}
hyp_pgtable = kzalloc(sizeof(*hyp_pgtable), GFP_KERNEL);
if (!hyp_pgtable) {
kvm_err("Hyp mode page-table not allocated\n");
err = -ENOMEM;
goto out;
}
err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops);
if (err)
goto out_free_pgtable;
err = kvm_map_idmap_text();
if (err)
goto out_destroy_pgtable;
io_map_base = hyp_idmap_start;
__hyp_va_bits = *hyp_va_bits;
return 0;
out_destroy_pgtable:
kvm_pgtable_hyp_destroy(hyp_pgtable);
out_free_pgtable:
kfree(hyp_pgtable);
hyp_pgtable = NULL;
out:
return err;
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{ bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES;
/*
* At this point memslot has been committed and there is an
* allocated dirty_bitmap[], dirty pages will be tracked while the
* memory slot is write protected.
*/
if (log_dirty_pages) { if (change == KVM_MR_DELETE)
return;
/*
* Huge and normal pages are write-protected and split
* on either of these two cases:
*
* 1. with initial-all-set: gradually with CLEAR ioctls,
*/
if (kvm_dirty_log_manual_protect_and_init_set(kvm))
return;
/*
* or
* 2. without initial-all-set: all in one shot when
* enabling dirty logging.
*/
kvm_mmu_wp_memory_region(kvm, new->id); kvm_mmu_split_memory_region(kvm, new->id);
} else {
/*
* Free any leftovers from the eager page splitting cache. Do
* this when deleting, moving, disabling dirty logging, or
* creating the memslot (a nop). Doing it for deletes makes
* sure we don't leak memory, and there's no need to keep the
* cache around for any of the other cases.
*/
kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
}
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
hva_t hva, reg_end;
int ret = 0;
if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
change != KVM_MR_FLAGS_ONLY)
return 0;
/*
* Prevent userspace from creating a memory region outside of the IPA
* space addressable by the KVM guest IPA space.
*/
if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT))
return -EFAULT;
hva = new->userspace_addr;
reg_end = hva + (new->npages << PAGE_SHIFT);
mmap_read_lock(current->mm);
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them.
*
* +--------------------------------------------+
* +---------------+----------------+ +----------------+
* | : VMA 1 | VMA 2 | | VMA 3 : |
* +---------------+----------------+ +----------------+
* | memory region |
* +--------------------------------------------+
*/
do {
struct vm_area_struct *vma;
vma = find_vma_intersection(current->mm, hva, reg_end);
if (!vma)
break;
if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) {
ret = -EINVAL;
break;
}
if (vma->vm_flags & VM_PFNMAP) {
/* IO region dirty page logging not allowed */
if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
ret = -EINVAL;
break;
}
}
hva = min(reg_end, vma->vm_end);
} while (hva < reg_end);
mmap_read_unlock(current->mm);
return ret;
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
}
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
phys_addr_t size = slot->npages << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
}
/*
* See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*
* Main problems:
* - S/W ops are local to a CPU (not broadcast)
* - We have line migration behind our back (speculation)
* - System caches don't support S/W at all (damn!)
*
* In the face of the above, the best we can do is to try and convert
* S/W ops to VA ops. Because the guest is not allowed to infer the
* S/W to PA mapping, it can only use S/W to nuke the whole cache,
* which is a rather good thing for us.
*
* Also, it is only used when turning caches on/off ("The expected
* usage of the cache maintenance instructions that operate by set/way
* is associated with the cache maintenance instructions associated
* with the powerdown and powerup of caches, if this is required by
* the implementation.").
*
* We use the following policy:
*
* - If we trap a S/W operation, we enable VM trapping to detect
* caches being turned on/off, and do a full clean.
*
* - We flush the caches on both caches being turned on and off.
*
* - Once the caches are enabled, we stop trapping VM ops.
*/
void kvm_set_way_flush(struct kvm_vcpu *vcpu)
{
unsigned long hcr = *vcpu_hcr(vcpu);
/*
* If this is the first time we do a S/W operation
* (i.e. HCR_TVM not set) flush the whole memory, and set the
* VM trapping.
*
* Otherwise, rely on the VM trapping to wait for the MMU +
* Caches to be turned off. At that point, we'll be able to
* clean the caches again.
*/
if (!(hcr & HCR_TVM)) {
trace_kvm_set_way_flush(*vcpu_pc(vcpu),
vcpu_has_cache_enabled(vcpu));
stage2_flush_vm(vcpu->kvm);
*vcpu_hcr(vcpu) = hcr | HCR_TVM;
}
}
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
{
bool now_enabled = vcpu_has_cache_enabled(vcpu);
/*
* If switching the MMU+caches on, need to invalidate the caches.
* If switching it off, need to clean the caches.
* Clean + invalidate does the trick always.
*/
if (now_enabled != was_enabled)
stage2_flush_vm(vcpu->kvm);
/* Caches are now on, stop trapping VM ops (until a S/W op) */
if (now_enabled)
*vcpu_hcr(vcpu) &= ~HCR_TVM;
trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
}
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/export.h>
#include <linux/bvec.h>
#include <linux/fault-inject-usercopy.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/splice.h>
#include <linux/compat.h>
#include <linux/scatterlist.h>
#include <linux/instrumented.h>
#include <linux/iov_iter.h>
static __always_inline
size_t copy_to_user_iter(void __user *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
if (should_fail_usercopy())
return len;
if (access_ok(iter_to, len)) {
from += progress;
instrument_copy_to_user(iter_to, from, len);
len = raw_copy_to_user(iter_to, from, len);
}
return len;
}
static __always_inline
size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
ssize_t res;
if (should_fail_usercopy())
return len;
from += progress;
res = copy_to_user_nofault(iter_to, from, len);
return res < 0 ? len : res;
}
static __always_inline
size_t copy_from_user_iter(void __user *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
size_t res = len;
if (should_fail_usercopy())
return len;
if (access_ok(iter_from, len)) { to += progress; instrument_copy_from_user_before(to, iter_from, len);
res = raw_copy_from_user(to, iter_from, len);
instrument_copy_from_user_after(to, iter_from, len, res);
}
return res;
}
static __always_inline
size_t memcpy_to_iter(void *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
memcpy(iter_to, from + progress, len);
return 0;
}
static __always_inline
size_t memcpy_from_iter(void *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
memcpy(to + progress, iter_from, len);
return 0;
}
/*
* fault_in_iov_iter_readable - fault in iov iterator for reading
* @i: iterator
* @size: maximum length
*
* Fault in one or more iovecs of the given iov_iter, to a maximum length of
* @size. For each iovec, fault in each page that constitutes the iovec.
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*
* Always returns 0 for non-userspace iterators.
*/
size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size)
{ if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i));
n -= fault_in_readable(i->ubuf + i->iov_offset, n);
return size - n;
} else if (iter_is_iovec(i)) {
size_t count = min(size, iov_iter_count(i));
const struct iovec *p;
size_t skip;
size -= count;
for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) {
size_t len = min(count, p->iov_len - skip);
size_t ret;
if (unlikely(!len))
continue;
ret = fault_in_readable(p->iov_base + skip, len);
count -= len - ret;
if (ret)
break;
}
return count + size;
}
return 0;
}
EXPORT_SYMBOL(fault_in_iov_iter_readable);
/*
* fault_in_iov_iter_writeable - fault in iov iterator for writing
* @i: iterator
* @size: maximum length
*
* Faults in the iterator using get_user_pages(), i.e., without triggering
* hardware page faults. This is primarily useful when we already know that
* some or all of the pages in @i aren't in memory.
*
* Returns the number of bytes not faulted in, like copy_to_user() and
* copy_from_user().
*
* Always returns 0 for non-user-space iterators.
*/
size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
{
if (iter_is_ubuf(i)) {
size_t n = min(size, iov_iter_count(i));
n -= fault_in_safe_writeable(i->ubuf + i->iov_offset, n);
return size - n;
} else if (iter_is_iovec(i)) {
size_t count = min(size, iov_iter_count(i));
const struct iovec *p;
size_t skip;
size -= count;
for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) {
size_t len = min(count, p->iov_len - skip);
size_t ret;
if (unlikely(!len))
continue;
ret = fault_in_safe_writeable(p->iov_base + skip, len);
count -= len - ret;
if (ret)
break;
}
return count + size;
}
return 0;
}
EXPORT_SYMBOL(fault_in_iov_iter_writeable);
void iov_iter_init(struct iov_iter *i, unsigned int direction,
const struct iovec *iov, unsigned long nr_segs,
size_t count)
{
WARN_ON(direction & ~(READ | WRITE));
*i = (struct iov_iter) {
.iter_type = ITER_IOVEC,
.nofault = false,
.data_source = direction,
.__iov = iov,
.nr_segs = nr_segs,
.iov_offset = 0,
.count = count
};
}
EXPORT_SYMBOL(iov_iter_init);
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
if (WARN_ON_ONCE(i->data_source))
return 0;
if (user_backed_iter(i))
might_fault();
return iterate_and_advance(i, bytes, (void *)addr,
copy_to_user_iter, memcpy_to_iter);
}
EXPORT_SYMBOL(_copy_to_iter);
#ifdef CONFIG_ARCH_HAS_COPY_MC
static __always_inline
size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
if (access_ok(iter_to, len)) {
from += progress;
instrument_copy_to_user(iter_to, from, len);
len = copy_mc_to_user(iter_to, from, len);
}
return len;
}
static __always_inline
size_t memcpy_to_iter_mc(void *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
return copy_mc_to_kernel(iter_to, from + progress, len);
}
/**
* _copy_mc_to_iter - copy to iter with source memory error exception handling
* @addr: source kernel address
* @bytes: total transfer length
* @i: destination iterator
*
* The pmem driver deploys this for the dax operation
* (dax_copy_to_iter()) for dax reads (bypass page-cache and the
* block-layer). Upon #MC read(2) aborts and returns EIO or the bytes
* successfully copied.
*
* The main differences between this and typical _copy_to_iter().
*
* * Typical tail/residue handling after a fault retries the copy
* byte-by-byte until the fault happens again. Re-triggering machine
* checks is potentially fatal so the implementation uses source
* alignment and poison alignment assumptions to avoid re-triggering
* hardware exceptions.
*
* * ITER_KVEC and ITER_BVEC can return short copies. Compare to
* copy_to_iter() where only ITER_IOVEC attempts might return a short copy.
*
* Return: number of bytes copied (may be %0)
*/
size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
if (WARN_ON_ONCE(i->data_source))
return 0;
if (user_backed_iter(i))
might_fault();
return iterate_and_advance(i, bytes, (void *)addr,
copy_to_user_iter_mc, memcpy_to_iter_mc);
}
EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
#endif /* CONFIG_ARCH_HAS_COPY_MC */
static __always_inline
size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
return iterate_and_advance(i, bytes, addr,
copy_from_user_iter, memcpy_from_iter);
}
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{ if (WARN_ON_ONCE(!i->data_source))
return 0;
if (user_backed_iter(i)) might_fault(); return __copy_from_iter(addr, bytes, i);
}
EXPORT_SYMBOL(_copy_from_iter);
static __always_inline
size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
return __copy_from_user_inatomic_nocache(to + progress, iter_from, len);
}
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
if (WARN_ON_ONCE(!i->data_source))
return 0;
return iterate_and_advance(i, bytes, addr,
copy_from_user_iter_nocache,
memcpy_from_iter);
}
EXPORT_SYMBOL(_copy_from_iter_nocache);
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
static __always_inline
size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
return __copy_from_user_flushcache(to + progress, iter_from, len);
}
static __always_inline
size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
memcpy_flushcache(to + progress, iter_from, len);
return 0;
}
/**
* _copy_from_iter_flushcache - write destination through cpu cache
* @addr: destination kernel address
* @bytes: total transfer length
* @i: source iterator
*
* The pmem driver arranges for filesystem-dax to use this facility via
* dax_copy_from_iter() for ensuring that writes to persistent memory
* are flushed through the CPU cache. It is differentiated from
* _copy_from_iter_nocache() in that guarantees all data is flushed for
* all iterator types. The _copy_from_iter_nocache() only attempts to
* bypass the cache for the ITER_IOVEC case, and on some archs may use
* instructions that strand dirty-data in the cache.
*
* Return: number of bytes copied (may be %0)
*/
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
if (WARN_ON_ONCE(!i->data_source))
return 0;
return iterate_and_advance(i, bytes, addr,
copy_from_user_iter_flushcache,
memcpy_from_iter_flushcache);
}
EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache);
#endif
static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
{
struct page *head;
size_t v = n + offset;
/*
* The general case needs to access the page order in order
* to compute the page size.
* However, we mostly deal with order-0 pages and thus can
* avoid a possible cache line miss for requests that fit all
* page orders.
*/
if (n <= v && v <= PAGE_SIZE)
return true;
head = compound_head(page);
v += (page - head) << PAGE_SHIFT;
if (WARN_ON(n > v || v > page_size(head)))
return false;
return true;
}
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
size_t res = 0;
if (!page_copy_sane(page, offset, bytes))
return 0;
if (WARN_ON_ONCE(i->data_source))
return 0;
page += offset / PAGE_SIZE; // first subpage
offset %= PAGE_SIZE;
while (1) {
void *kaddr = kmap_local_page(page);
size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
n = _copy_to_iter(kaddr + offset, n, i);
kunmap_local(kaddr);
res += n;
bytes -= n;
if (!bytes || !n)
break;
offset += n;
if (offset == PAGE_SIZE) {
page++;
offset = 0;
}
}
return res;
}
EXPORT_SYMBOL(copy_page_to_iter);
size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes,
struct iov_iter *i)
{
size_t res = 0;
if (!page_copy_sane(page, offset, bytes))
return 0;
if (WARN_ON_ONCE(i->data_source))
return 0;
page += offset / PAGE_SIZE; // first subpage
offset %= PAGE_SIZE;
while (1) {
void *kaddr = kmap_local_page(page);
size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
n = iterate_and_advance(i, n, kaddr + offset,
copy_to_user_iter_nofault,
memcpy_to_iter);
kunmap_local(kaddr);
res += n;
bytes -= n;
if (!bytes || !n)
break;
offset += n;
if (offset == PAGE_SIZE) {
page++;
offset = 0;
}
}
return res;
}
EXPORT_SYMBOL(copy_page_to_iter_nofault);
size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
size_t res = 0;
if (!page_copy_sane(page, offset, bytes))
return 0;
page += offset / PAGE_SIZE; // first subpage
offset %= PAGE_SIZE;
while (1) {
void *kaddr = kmap_local_page(page);
size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
n = _copy_from_iter(kaddr + offset, n, i);
kunmap_local(kaddr);
res += n;
bytes -= n;
if (!bytes || !n)
break;
offset += n;
if (offset == PAGE_SIZE) {
page++;
offset = 0;
}
}
return res;
}
EXPORT_SYMBOL(copy_page_from_iter);
static __always_inline
size_t zero_to_user_iter(void __user *iter_to, size_t progress,
size_t len, void *priv, void *priv2)
{
return clear_user(iter_to, len);
}
static __always_inline
size_t zero_to_iter(void *iter_to, size_t progress,
size_t len, void *priv, void *priv2)
{
memset(iter_to, 0, len);
return 0;
}
size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
{
return iterate_and_advance(i, bytes, NULL,
zero_to_user_iter, zero_to_iter);
}
EXPORT_SYMBOL(iov_iter_zero);
size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
size_t bytes, struct iov_iter *i)
{
size_t n, copied = 0;
bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) ||
PageHighMem(page);
if (!page_copy_sane(page, offset, bytes))
return 0;
if (WARN_ON_ONCE(!i->data_source))
return 0;
do {
char *p;
n = bytes - copied;
if (uses_kmap) {
page += offset / PAGE_SIZE;
offset %= PAGE_SIZE;
n = min_t(size_t, n, PAGE_SIZE - offset);
}
p = kmap_atomic(page) + offset; n = __copy_from_iter(p, n, i); kunmap_atomic(p);
copied += n;
offset += n;
} while (uses_kmap && copied != bytes && n > 0);
return copied;
}
EXPORT_SYMBOL(copy_page_from_iter_atomic);
static void iov_iter_bvec_advance(struct iov_iter *i, size_t size)
{
const struct bio_vec *bvec, *end;
if (!i->count)
return;
i->count -= size;
size += i->iov_offset;
for (bvec = i->bvec, end = bvec + i->nr_segs; bvec < end; bvec++) {
if (likely(size < bvec->bv_len))
break;
size -= bvec->bv_len;
}
i->iov_offset = size;
i->nr_segs -= bvec - i->bvec;
i->bvec = bvec;
}
static void iov_iter_iovec_advance(struct iov_iter *i, size_t size)
{
const struct iovec *iov, *end;
if (!i->count)
return;
i->count -= size;
size += i->iov_offset; // from beginning of current segment
for (iov = iter_iov(i), end = iov + i->nr_segs; iov < end; iov++) {
if (likely(size < iov->iov_len))
break;
size -= iov->iov_len;
}
i->iov_offset = size;
i->nr_segs -= iov - iter_iov(i);
i->__iov = iov;
}
static void iov_iter_folioq_advance(struct iov_iter *i, size_t size)
{
const struct folio_queue *folioq = i->folioq;
unsigned int slot = i->folioq_slot;
if (!i->count)
return;
i->count -= size;
if (slot >= folioq_nr_slots(folioq)) {
folioq = folioq->next;
slot = 0;
}
size += i->iov_offset; /* From beginning of current segment. */
do {
size_t fsize = folioq_folio_size(folioq, slot);
if (likely(size < fsize))
break;
size -= fsize;
slot++;
if (slot >= folioq_nr_slots(folioq) && folioq->next) {
folioq = folioq->next;
slot = 0;
}
} while (size);
i->iov_offset = size;
i->folioq_slot = slot;
i->folioq = folioq;
}
void iov_iter_advance(struct iov_iter *i, size_t size)
{
if (unlikely(i->count < size))
size = i->count;
if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) {
i->iov_offset += size;
i->count -= size;
} else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) {
/* iovec and kvec have identical layouts */
iov_iter_iovec_advance(i, size);
} else if (iov_iter_is_bvec(i)) {
iov_iter_bvec_advance(i, size);
} else if (iov_iter_is_folioq(i)) {
iov_iter_folioq_advance(i, size);
} else if (iov_iter_is_discard(i)) {
i->count -= size;
}
}
EXPORT_SYMBOL(iov_iter_advance);
static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll)
{
const struct folio_queue *folioq = i->folioq;
unsigned int slot = i->folioq_slot;
for (;;) {
size_t fsize;
if (slot == 0) {
folioq = folioq->prev;
slot = folioq_nr_slots(folioq);
}
slot--;
fsize = folioq_folio_size(folioq, slot);
if (unroll <= fsize) {
i->iov_offset = fsize - unroll;
break;
}
unroll -= fsize;
}
i->folioq_slot = slot;
i->folioq = folioq;
}
void iov_iter_revert(struct iov_iter *i, size_t unroll)
{
if (!unroll)
return;
if (WARN_ON(unroll > MAX_RW_COUNT))
return;
i->count += unroll;
if (unlikely(iov_iter_is_discard(i)))
return;
if (unroll <= i->iov_offset) {
i->iov_offset -= unroll;
return;
}
unroll -= i->iov_offset;
if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) {
BUG(); /* We should never go beyond the start of the specified
* range since we might then be straying into pages that
* aren't pinned.
*/
} else if (iov_iter_is_bvec(i)) {
const struct bio_vec *bvec = i->bvec;
while (1) {
size_t n = (--bvec)->bv_len;
i->nr_segs++;
if (unroll <= n) {
i->bvec = bvec;
i->iov_offset = n - unroll;
return;
}
unroll -= n;
}
} else if (iov_iter_is_folioq(i)) {
i->iov_offset = 0;
iov_iter_folioq_revert(i, unroll);
} else { /* same logics for iovec and kvec */
const struct iovec *iov = iter_iov(i);
while (1) {
size_t n = (--iov)->iov_len;
i->nr_segs++;
if (unroll <= n) {
i->__iov = iov;
i->iov_offset = n - unroll;
return;
}
unroll -= n;
}
}
}
EXPORT_SYMBOL(iov_iter_revert);
/*
* Return the count of just the current iov_iter segment.
*/
size_t iov_iter_single_seg_count(const struct iov_iter *i)
{
if (i->nr_segs > 1) {
if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
return min(i->count, iter_iov(i)->iov_len - i->iov_offset);
if (iov_iter_is_bvec(i))
return min(i->count, i->bvec->bv_len - i->iov_offset);
}
if (unlikely(iov_iter_is_folioq(i)))
return !i->count ? 0 :
umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count);
return i->count;
}
EXPORT_SYMBOL(iov_iter_single_seg_count);
void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
const struct kvec *kvec, unsigned long nr_segs,
size_t count)
{
WARN_ON(direction & ~(READ | WRITE));
*i = (struct iov_iter){
.iter_type = ITER_KVEC,
.data_source = direction,
.kvec = kvec,
.nr_segs = nr_segs,
.iov_offset = 0,
.count = count
};
}
EXPORT_SYMBOL(iov_iter_kvec);
void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
const struct bio_vec *bvec, unsigned long nr_segs,
size_t count)
{
WARN_ON(direction & ~(READ | WRITE));
*i = (struct iov_iter){
.iter_type = ITER_BVEC,
.data_source = direction,
.bvec = bvec,
.nr_segs = nr_segs,
.iov_offset = 0,
.count = count
};
}
EXPORT_SYMBOL(iov_iter_bvec);
/**
* iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue
* @i: The iterator to initialise.
* @direction: The direction of the transfer.
* @folioq: The starting point in the folio queue.
* @first_slot: The first slot in the folio queue to use
* @offset: The offset into the folio in the first slot to start at
* @count: The size of the I/O buffer in bytes.
*
* Set up an I/O iterator to either draw data out of the pages attached to an
* inode or to inject data into those pages. The pages *must* be prevented
* from evaporation, either by taking a ref on them or locking them by the
* caller.
*/
void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction,
const struct folio_queue *folioq, unsigned int first_slot,
unsigned int offset, size_t count)
{
BUG_ON(direction & ~1);
*i = (struct iov_iter) {
.iter_type = ITER_FOLIOQ,
.data_source = direction,
.folioq = folioq,
.folioq_slot = first_slot,
.count = count,
.iov_offset = offset,
};
}
EXPORT_SYMBOL(iov_iter_folio_queue);
/**
* iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray
* @i: The iterator to initialise.
* @direction: The direction of the transfer.
* @xarray: The xarray to access.
* @start: The start file position.
* @count: The size of the I/O buffer in bytes.
*
* Set up an I/O iterator to either draw data out of the pages attached to an
* inode or to inject data into those pages. The pages *must* be prevented
* from evaporation, either by taking a ref on them or locking them by the
* caller.
*/
void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
struct xarray *xarray, loff_t start, size_t count)
{
BUG_ON(direction & ~1);
*i = (struct iov_iter) {
.iter_type = ITER_XARRAY,
.data_source = direction,
.xarray = xarray,
.xarray_start = start,
.count = count,
.iov_offset = 0
};
}
EXPORT_SYMBOL(iov_iter_xarray);
/**
* iov_iter_discard - Initialise an I/O iterator that discards data
* @i: The iterator to initialise.
* @direction: The direction of the transfer.
* @count: The size of the I/O buffer in bytes.
*
* Set up an I/O iterator that just discards everything that's written to it.
* It's only available as a READ iterator.
*/
void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
{
BUG_ON(direction != READ);
*i = (struct iov_iter){
.iter_type = ITER_DISCARD,
.data_source = false,
.count = count,
.iov_offset = 0
};
}
EXPORT_SYMBOL(iov_iter_discard);
static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
unsigned len_mask)
{
const struct iovec *iov = iter_iov(i);
size_t size = i->count;
size_t skip = i->iov_offset;
do {
size_t len = iov->iov_len - skip;
if (len > size)
len = size;
if (len & len_mask)
return false;
if ((unsigned long)(iov->iov_base + skip) & addr_mask)
return false;
iov++;
size -= len;
skip = 0;
} while (size);
return true;
}
static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
unsigned len_mask)
{
const struct bio_vec *bvec = i->bvec;
unsigned skip = i->iov_offset;
size_t size = i->count;
do {
size_t len = bvec->bv_len;
if (len > size)
len = size;
if (len & len_mask)
return false;
if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
return false;
bvec++;
size -= len;
skip = 0;
} while (size);
return true;
}
/**
* iov_iter_is_aligned() - Check if the addresses and lengths of each segments
* are aligned to the parameters.
*
* @i: &struct iov_iter to restore
* @addr_mask: bit mask to check against the iov element's addresses
* @len_mask: bit mask to check against the iov element's lengths
*
* Return: false if any addresses or lengths intersect with the provided masks
*/
bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
unsigned len_mask)
{
if (likely(iter_is_ubuf(i))) {
if (i->count & len_mask)
return false;
if ((unsigned long)(i->ubuf + i->iov_offset) & addr_mask)
return false;
return true;
}
if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
return iov_iter_aligned_iovec(i, addr_mask, len_mask);
if (iov_iter_is_bvec(i))
return iov_iter_aligned_bvec(i, addr_mask, len_mask);
/* With both xarray and folioq types, we're dealing with whole folios. */
if (iov_iter_is_xarray(i)) {
if (i->count & len_mask)
return false;
if ((i->xarray_start + i->iov_offset) & addr_mask)
return false;
}
if (iov_iter_is_folioq(i)) {
if (i->count & len_mask)
return false;
if (i->iov_offset & addr_mask)
return false;
}
return true;
}
EXPORT_SYMBOL_GPL(iov_iter_is_aligned);
static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
{
const struct iovec *iov = iter_iov(i);
unsigned long res = 0;
size_t size = i->count;
size_t skip = i->iov_offset;
do {
size_t len = iov->iov_len - skip;
if (len) {
res |= (unsigned long)iov->iov_base + skip;
if (len > size)
len = size;
res |= len;
size -= len;
}
iov++;
skip = 0;
} while (size);
return res;
}
static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
{
const struct bio_vec *bvec = i->bvec;
unsigned res = 0;
size_t size = i->count;
unsigned skip = i->iov_offset;
do {
size_t len = bvec->bv_len - skip;
res |= (unsigned long)bvec->bv_offset + skip;
if (len > size)
len = size;
res |= len;
bvec++;
size -= len;
skip = 0;
} while (size);
return res;
}
unsigned long iov_iter_alignment(const struct iov_iter *i)
{
if (likely(iter_is_ubuf(i))) {
size_t size = i->count;
if (size)
return ((unsigned long)i->ubuf + i->iov_offset) | size;
return 0;
}
/* iovec and kvec have identical layouts */
if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
return iov_iter_alignment_iovec(i);
if (iov_iter_is_bvec(i))
return iov_iter_alignment_bvec(i);
/* With both xarray and folioq types, we're dealing with whole folios. */
if (iov_iter_is_folioq(i))
return i->iov_offset | i->count;
if (iov_iter_is_xarray(i))
return (i->xarray_start + i->iov_offset) | i->count;
return 0;
}
EXPORT_SYMBOL(iov_iter_alignment);
unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
{
unsigned long res = 0;
unsigned long v = 0;
size_t size = i->count;
unsigned k;
if (iter_is_ubuf(i))
return 0;
if (WARN_ON(!iter_is_iovec(i)))
return ~0U;
for (k = 0; k < i->nr_segs; k++) {
const struct iovec *iov = iter_iov(i) + k;
if (iov->iov_len) {
unsigned long base = (unsigned long)iov->iov_base;
if (v) // if not the first one
res |= base | v; // this start | previous end
v = base + iov->iov_len;
if (size <= iov->iov_len)
break;
size -= iov->iov_len;
}
}
return res;
}
EXPORT_SYMBOL(iov_iter_gap_alignment);
static int want_pages_array(struct page ***res, size_t size,
size_t start, unsigned int maxpages)
{
unsigned int count = DIV_ROUND_UP(size + start, PAGE_SIZE);
if (count > maxpages)
count = maxpages;
WARN_ON(!count); // caller should've prevented that
if (!*res) {
*res = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL);
if (!*res)
return 0;
}
return count;
}
static ssize_t iter_folioq_get_pages(struct iov_iter *iter,
struct page ***ppages, size_t maxsize,
unsigned maxpages, size_t *_start_offset)
{
const struct folio_queue *folioq = iter->folioq;
struct page **pages;
unsigned int slot = iter->folioq_slot;
size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset;
if (slot >= folioq_nr_slots(folioq)) {
folioq = folioq->next;
slot = 0;
if (WARN_ON(iov_offset != 0))
return -EIO;
}
maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages);
if (!maxpages)
return -ENOMEM;
*_start_offset = iov_offset & ~PAGE_MASK;
pages = *ppages;
for (;;) {
struct folio *folio = folioq_folio(folioq, slot);
size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot);
size_t part = PAGE_SIZE - offset % PAGE_SIZE;
if (offset < fsize) {
part = umin(part, umin(maxsize - extracted, fsize - offset));
count -= part;
iov_offset += part;
extracted += part;
*pages = folio_page(folio, offset / PAGE_SIZE);
get_page(*pages);
pages++;
maxpages--;
}
if (maxpages == 0 || extracted >= maxsize)
break;
if (iov_offset >= fsize) {
iov_offset = 0;
slot++;
if (slot == folioq_nr_slots(folioq) && folioq->next) {
folioq = folioq->next;
slot = 0;
}
}
}
iter->count = count;
iter->iov_offset = iov_offset;
iter->folioq = folioq;
iter->folioq_slot = slot;
return extracted;
}
static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
pgoff_t index, unsigned int nr_pages)
{
XA_STATE(xas, xa, index);
struct page *page;
unsigned int ret = 0;
rcu_read_lock();
for (page = xas_load(&xas); page; page = xas_next(&xas)) {
if (xas_retry(&xas, page))
continue;
/* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas))) {
xas_reset(&xas);
continue;
}
pages[ret] = find_subpage(page, xas.xa_index);
get_page(pages[ret]);
if (++ret == nr_pages)
break;
}
rcu_read_unlock();
return ret;
}
static ssize_t iter_xarray_get_pages(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned maxpages, size_t *_start_offset)
{
unsigned nr, offset, count;
pgoff_t index;
loff_t pos;
pos = i->xarray_start + i->iov_offset;
index = pos >> PAGE_SHIFT;
offset = pos & ~PAGE_MASK;
*_start_offset = offset;
count = want_pages_array(pages, maxsize, offset, maxpages);
if (!count)
return -ENOMEM;
nr = iter_xarray_populate_pages(*pages, i->xarray, index, count);
if (nr == 0)
return 0;
maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
i->iov_offset += maxsize;
i->count -= maxsize;
return maxsize;
}
/* must be done on non-empty ITER_UBUF or ITER_IOVEC one */
static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size)
{
size_t skip;
long k;
if (iter_is_ubuf(i))
return (unsigned long)i->ubuf + i->iov_offset;
for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) {
const struct iovec *iov = iter_iov(i) + k;
size_t len = iov->iov_len - skip;
if (unlikely(!len))
continue;
if (*size > len)
*size = len;
return (unsigned long)iov->iov_base + skip;
}
BUG(); // if it had been empty, we wouldn't get called
}
/* must be done on non-empty ITER_BVEC one */
static struct page *first_bvec_segment(const struct iov_iter *i,
size_t *size, size_t *start)
{
struct page *page;
size_t skip = i->iov_offset, len;
len = i->bvec->bv_len - skip;
if (*size > len)
*size = len;
skip += i->bvec->bv_offset;
page = i->bvec->bv_page + skip / PAGE_SIZE;
*start = skip % PAGE_SIZE;
return page;
}
static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages, size_t *start)
{
unsigned int n, gup_flags = 0;
if (maxsize > i->count)
maxsize = i->count;
if (!maxsize)
return 0;
if (maxsize > MAX_RW_COUNT)
maxsize = MAX_RW_COUNT;
if (likely(user_backed_iter(i))) {
unsigned long addr;
int res;
if (iov_iter_rw(i) != WRITE)
gup_flags |= FOLL_WRITE;
if (i->nofault)
gup_flags |= FOLL_NOFAULT;
addr = first_iovec_segment(i, &maxsize);
*start = addr % PAGE_SIZE;
addr &= PAGE_MASK;
n = want_pages_array(pages, maxsize, *start, maxpages);
if (!n)
return -ENOMEM;
res = get_user_pages_fast(addr, n, gup_flags, *pages);
if (unlikely(res <= 0))
return res;
maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start);
iov_iter_advance(i, maxsize);
return maxsize;
}
if (iov_iter_is_bvec(i)) {
struct page **p;
struct page *page;
page = first_bvec_segment(i, &maxsize, start);
n = want_pages_array(pages, maxsize, *start, maxpages);
if (!n)
return -ENOMEM;
p = *pages;
for (int k = 0; k < n; k++) {
struct folio *folio = page_folio(page + k);
p[k] = page + k;
if (!folio_test_slab(folio))
folio_get(folio);
}
maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start);
i->count -= maxsize;
i->iov_offset += maxsize;
if (i->iov_offset == i->bvec->bv_len) {
i->iov_offset = 0;
i->bvec++;
i->nr_segs--;
}
return maxsize;
}
if (iov_iter_is_folioq(i))
return iter_folioq_get_pages(i, pages, maxsize, maxpages, start);
if (iov_iter_is_xarray(i))
return iter_xarray_get_pages(i, pages, maxsize, maxpages, start);
return -EFAULT;
}
ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start)
{
if (!maxpages)
return 0;
BUG_ON(!pages);
return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start);
}
EXPORT_SYMBOL(iov_iter_get_pages2);
ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i,
struct page ***pages, size_t maxsize, size_t *start)
{
ssize_t len;
*pages = NULL;
len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start);
if (len <= 0) {
kvfree(*pages);
*pages = NULL;
}
return len;
}
EXPORT_SYMBOL(iov_iter_get_pages_alloc2);
static int iov_npages(const struct iov_iter *i, int maxpages)
{
size_t skip = i->iov_offset, size = i->count;
const struct iovec *p;
int npages = 0;
for (p = iter_iov(i); size; skip = 0, p++) {
unsigned offs = offset_in_page(p->iov_base + skip);
size_t len = min(p->iov_len - skip, size);
if (len) {
size -= len;
npages += DIV_ROUND_UP(offs + len, PAGE_SIZE);
if (unlikely(npages > maxpages))
return maxpages;
}
}
return npages;
}
static int bvec_npages(const struct iov_iter *i, int maxpages)
{
size_t skip = i->iov_offset, size = i->count;
const struct bio_vec *p;
int npages = 0;
for (p = i->bvec; size; skip = 0, p++) {
unsigned offs = (p->bv_offset + skip) % PAGE_SIZE;
size_t len = min(p->bv_len - skip, size);
size -= len;
npages += DIV_ROUND_UP(offs + len, PAGE_SIZE);
if (unlikely(npages > maxpages))
return maxpages;
}
return npages;
}
int iov_iter_npages(const struct iov_iter *i, int maxpages)
{
if (unlikely(!i->count))
return 0;
if (likely(iter_is_ubuf(i))) {
unsigned offs = offset_in_page(i->ubuf + i->iov_offset);
int npages = DIV_ROUND_UP(offs + i->count, PAGE_SIZE);
return min(npages, maxpages);
}
/* iovec and kvec have identical layouts */
if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
return iov_npages(i, maxpages);
if (iov_iter_is_bvec(i))
return bvec_npages(i, maxpages);
if (iov_iter_is_folioq(i)) {
unsigned offset = i->iov_offset % PAGE_SIZE;
int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE);
return min(npages, maxpages);
}
if (iov_iter_is_xarray(i)) {
unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE;
int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE);
return min(npages, maxpages);
}
return 0;
}
EXPORT_SYMBOL(iov_iter_npages);
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
{
*new = *old;
if (iov_iter_is_bvec(new))
return new->bvec = kmemdup(new->bvec,
new->nr_segs * sizeof(struct bio_vec),
flags);
else if (iov_iter_is_kvec(new) || iter_is_iovec(new))
/* iovec and kvec have identical layout */
return new->__iov = kmemdup(new->__iov,
new->nr_segs * sizeof(struct iovec),
flags);
return NULL;
}
EXPORT_SYMBOL(dup_iter);
static __noclone int copy_compat_iovec_from_user(struct iovec *iov,
const struct iovec __user *uvec, u32 nr_segs)
{
const struct compat_iovec __user *uiov =
(const struct compat_iovec __user *)uvec;
int ret = -EFAULT;
u32 i;
if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
for (i = 0; i < nr_segs; i++) {
compat_uptr_t buf;
compat_ssize_t len;
unsafe_get_user(len, &uiov[i].iov_len, uaccess_end);
unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end);
/* check for compat_size_t not fitting in compat_ssize_t .. */
if (len < 0) {
ret = -EINVAL;
goto uaccess_end;
}
iov[i].iov_base = compat_ptr(buf);
iov[i].iov_len = len;
}
ret = 0;
uaccess_end:
user_access_end();
return ret;
}
static __noclone int copy_iovec_from_user(struct iovec *iov,
const struct iovec __user *uiov, unsigned long nr_segs)
{
int ret = -EFAULT;
if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
do {
void __user *buf;
ssize_t len;
unsafe_get_user(len, &uiov->iov_len, uaccess_end);
unsafe_get_user(buf, &uiov->iov_base, uaccess_end);
/* check for size_t not fitting in ssize_t .. */
if (unlikely(len < 0)) {
ret = -EINVAL;
goto uaccess_end;
}
iov->iov_base = buf;
iov->iov_len = len;
uiov++; iov++;
} while (--nr_segs);
ret = 0;
uaccess_end:
user_access_end();
return ret;
}
struct iovec *iovec_from_user(const struct iovec __user *uvec,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_iov, bool compat)
{
struct iovec *iov = fast_iov;
int ret;
/*
* SuS says "The readv() function *may* fail if the iovcnt argument was
* less than or equal to 0, or greater than {IOV_MAX}. Linux has
* traditionally returned zero for zero segments, so...
*/
if (nr_segs == 0)
return iov;
if (nr_segs > UIO_MAXIOV)
return ERR_PTR(-EINVAL);
if (nr_segs > fast_segs) {
iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
if (!iov)
return ERR_PTR(-ENOMEM);
}
if (unlikely(compat))
ret = copy_compat_iovec_from_user(iov, uvec, nr_segs);
else
ret = copy_iovec_from_user(iov, uvec, nr_segs);
if (ret) {
if (iov != fast_iov)
kfree(iov);
return ERR_PTR(ret);
}
return iov;
}
/*
* Single segment iovec supplied by the user, import it as ITER_UBUF.
*/
static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec,
struct iovec **iovp, struct iov_iter *i,
bool compat)
{
struct iovec *iov = *iovp;
ssize_t ret;
*iovp = NULL;
if (compat)
ret = copy_compat_iovec_from_user(iov, uvec, 1);
else
ret = copy_iovec_from_user(iov, uvec, 1);
if (unlikely(ret))
return ret;
ret = import_ubuf(type, iov->iov_base, iov->iov_len, i);
if (unlikely(ret))
return ret;
return i->count;
}
ssize_t __import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
struct iov_iter *i, bool compat)
{
ssize_t total_len = 0;
unsigned long seg;
struct iovec *iov;
if (nr_segs == 1)
return __import_iovec_ubuf(type, uvec, iovp, i, compat);
iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat);
if (IS_ERR(iov)) {
*iovp = NULL;
return PTR_ERR(iov);
}
/*
* According to the Single Unix Specification we should return EINVAL if
* an element length is < 0 when cast to ssize_t or if the total length
* would overflow the ssize_t return value of the system call.
*
* Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
* overflow case.
*/
for (seg = 0; seg < nr_segs; seg++) {
ssize_t len = (ssize_t)iov[seg].iov_len;
if (!access_ok(iov[seg].iov_base, len)) {
if (iov != *iovp)
kfree(iov);
*iovp = NULL;
return -EFAULT;
}
if (len > MAX_RW_COUNT - total_len) {
len = MAX_RW_COUNT - total_len;
iov[seg].iov_len = len;
}
total_len += len;
}
iov_iter_init(i, type, iov, nr_segs, total_len);
if (iov == *iovp)
*iovp = NULL;
else
*iovp = iov;
return total_len;
}
/**
* import_iovec() - Copy an array of &struct iovec from userspace
* into the kernel, check that it is valid, and initialize a new
* &struct iov_iter iterator to access it.
*
* @type: One of %READ or %WRITE.
* @uvec: Pointer to the userspace array.
* @nr_segs: Number of elements in userspace array.
* @fast_segs: Number of elements in @iov.
* @iovp: (input and output parameter) Pointer to pointer to (usually small
* on-stack) kernel array.
* @i: Pointer to iterator that will be initialized on success.
*
* If the array pointed to by *@iov is large enough to hold all @nr_segs,
* then this function places %NULL in *@iov on return. Otherwise, a new
* array will be allocated and the result placed in *@iov. This means that
* the caller may call kfree() on *@iov regardless of whether the small
* on-stack array was used or not (and regardless of whether this function
* returns an error or not).
*
* Return: Negative error code on error, bytes imported on success
*/
ssize_t import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iovp, struct iov_iter *i)
{
return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i,
in_compat_syscall());
}
EXPORT_SYMBOL(import_iovec);
int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i)
{
if (len > MAX_RW_COUNT)
len = MAX_RW_COUNT;
if (unlikely(!access_ok(buf, len)))
return -EFAULT;
iov_iter_ubuf(i, rw, buf, len);
return 0;
}
EXPORT_SYMBOL_GPL(import_ubuf);
/**
* iov_iter_restore() - Restore a &struct iov_iter to the same state as when
* iov_iter_save_state() was called.
*
* @i: &struct iov_iter to restore
* @state: state to restore from
*
* Used after iov_iter_save_state() to bring restore @i, if operations may
* have advanced it.
*
* Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC
*/
void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
{
if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) &&
!iter_is_ubuf(i)) && !iov_iter_is_kvec(i))
return;
i->iov_offset = state->iov_offset;
i->count = state->count;
if (iter_is_ubuf(i))
return;
/*
* For the *vec iters, nr_segs + iov is constant - if we increment
* the vec, then we also decrement the nr_segs count. Hence we don't
* need to track both of these, just one is enough and we can deduct
* the other from that. ITER_KVEC and ITER_IOVEC are the same struct
* size, so we can just increment the iov pointer as they are unionzed.
* ITER_BVEC _may_ be the same size on some archs, but on others it is
* not. Be safe and handle it separately.
*/
BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec));
if (iov_iter_is_bvec(i))
i->bvec -= state->nr_segs - i->nr_segs;
else
i->__iov -= state->nr_segs - i->nr_segs;
i->nr_segs = state->nr_segs;
}
/*
* Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does
* not get references on the pages, nor does it get a pin on them.
*/
static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
const struct folio_queue *folioq = i->folioq;
struct page **p;
unsigned int nr = 0;
size_t extracted = 0, offset, slot = i->folioq_slot;
if (slot >= folioq_nr_slots(folioq)) {
folioq = folioq->next;
slot = 0;
if (WARN_ON(i->iov_offset != 0))
return -EIO;
}
offset = i->iov_offset & ~PAGE_MASK;
*offset0 = offset;
maxpages = want_pages_array(pages, maxsize, offset, maxpages);
if (!maxpages)
return -ENOMEM;
p = *pages;
for (;;) {
struct folio *folio = folioq_folio(folioq, slot);
size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot);
size_t part = PAGE_SIZE - offset % PAGE_SIZE;
if (offset < fsize) {
part = umin(part, umin(maxsize - extracted, fsize - offset));
i->count -= part;
i->iov_offset += part;
extracted += part;
p[nr++] = folio_page(folio, offset / PAGE_SIZE);
}
if (nr >= maxpages || extracted >= maxsize)
break;
if (i->iov_offset >= fsize) {
i->iov_offset = 0;
slot++;
if (slot == folioq_nr_slots(folioq) && folioq->next) {
folioq = folioq->next;
slot = 0;
}
}
}
i->folioq = folioq;
i->folioq_slot = slot;
return extracted;
}
/*
* Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not
* get references on the pages, nor does it get a pin on them.
*/
static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
struct page *page, **p;
unsigned int nr = 0, offset;
loff_t pos = i->xarray_start + i->iov_offset;
pgoff_t index = pos >> PAGE_SHIFT;
XA_STATE(xas, i->xarray, index);
offset = pos & ~PAGE_MASK;
*offset0 = offset;
maxpages = want_pages_array(pages, maxsize, offset, maxpages);
if (!maxpages)
return -ENOMEM;
p = *pages;
rcu_read_lock();
for (page = xas_load(&xas); page; page = xas_next(&xas)) {
if (xas_retry(&xas, page))
continue;
/* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas))) {
xas_reset(&xas);
continue;
}
p[nr++] = find_subpage(page, xas.xa_index);
if (nr == maxpages)
break;
}
rcu_read_unlock();
maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
iov_iter_advance(i, maxsize);
return maxsize;
}
/*
* Extract a list of virtually contiguous pages from an ITER_BVEC iterator.
* This does not get references on the pages, nor does it get a pin on them.
*/
static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
size_t skip = i->iov_offset, size = 0;
struct bvec_iter bi;
int k = 0;
if (i->nr_segs == 0)
return 0;
if (i->iov_offset == i->bvec->bv_len) {
i->iov_offset = 0;
i->nr_segs--;
i->bvec++;
skip = 0;
}
bi.bi_idx = 0;
bi.bi_size = maxsize;
bi.bi_bvec_done = skip;
maxpages = want_pages_array(pages, maxsize, skip, maxpages);
while (bi.bi_size && bi.bi_idx < i->nr_segs) {
struct bio_vec bv = bvec_iter_bvec(i->bvec, bi);
/*
* The iov_iter_extract_pages interface only allows an offset
* into the first page. Break out of the loop if we see an
* offset into subsequent pages, the caller will have to call
* iov_iter_extract_pages again for the reminder.
*/
if (k) {
if (bv.bv_offset)
break;
} else {
*offset0 = bv.bv_offset;
}
(*pages)[k++] = bv.bv_page;
size += bv.bv_len;
if (k >= maxpages)
break;
/*
* We are done when the end of the bvec doesn't align to a page
* boundary as that would create a hole in the returned space.
* The caller will handle this with another call to
* iov_iter_extract_pages.
*/
if (bv.bv_offset + bv.bv_len != PAGE_SIZE)
break;
bvec_iter_advance_single(i->bvec, &bi, bv.bv_len);
}
iov_iter_advance(i, size);
return size;
}
/*
* Extract a list of virtually contiguous pages from an ITER_KVEC iterator.
* This does not get references on the pages, nor does it get a pin on them.
*/
static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i,
struct page ***pages, size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
struct page **p, *page;
const void *kaddr;
size_t skip = i->iov_offset, offset, len, size;
int k;
for (;;) {
if (i->nr_segs == 0)
return 0;
size = min(maxsize, i->kvec->iov_len - skip);
if (size)
break;
i->iov_offset = 0;
i->nr_segs--;
i->kvec++;
skip = 0;
}
kaddr = i->kvec->iov_base + skip;
offset = (unsigned long)kaddr & ~PAGE_MASK;
*offset0 = offset;
maxpages = want_pages_array(pages, size, offset, maxpages);
if (!maxpages)
return -ENOMEM;
p = *pages;
kaddr -= offset;
len = offset + size;
for (k = 0; k < maxpages; k++) {
size_t seg = min_t(size_t, len, PAGE_SIZE);
if (is_vmalloc_or_module_addr(kaddr))
page = vmalloc_to_page(kaddr);
else
page = virt_to_page(kaddr);
p[k] = page;
len -= seg;
kaddr += PAGE_SIZE;
}
size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
iov_iter_advance(i, size);
return size;
}
/*
* Extract a list of contiguous pages from a user iterator and get a pin on
* each of them. This should only be used if the iterator is user-backed
* (IOBUF/UBUF).
*
* It does not get refs on the pages, but the pages must be unpinned by the
* caller once the transfer is complete.
*
* This is safe to be used where background IO/DMA *is* going to be modifying
* the buffer; using a pin rather than a ref makes forces fork() to give the
* child a copy of the page.
*/
static ssize_t iov_iter_extract_user_pages(struct iov_iter *i,
struct page ***pages,
size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
unsigned long addr;
unsigned int gup_flags = 0;
size_t offset;
int res;
if (i->data_source == ITER_DEST)
gup_flags |= FOLL_WRITE;
if (extraction_flags & ITER_ALLOW_P2PDMA)
gup_flags |= FOLL_PCI_P2PDMA;
if (i->nofault)
gup_flags |= FOLL_NOFAULT;
addr = first_iovec_segment(i, &maxsize);
*offset0 = offset = addr % PAGE_SIZE;
addr &= PAGE_MASK;
maxpages = want_pages_array(pages, maxsize, offset, maxpages);
if (!maxpages)
return -ENOMEM;
res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages);
if (unlikely(res <= 0))
return res;
maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset);
iov_iter_advance(i, maxsize);
return maxsize;
}
/**
* iov_iter_extract_pages - Extract a list of contiguous pages from an iterator
* @i: The iterator to extract from
* @pages: Where to return the list of pages
* @maxsize: The maximum amount of iterator to extract
* @maxpages: The maximum size of the list of pages
* @extraction_flags: Flags to qualify request
* @offset0: Where to return the starting offset into (*@pages)[0]
*
* Extract a list of contiguous pages from the current point of the iterator,
* advancing the iterator. The maximum number of pages and the maximum amount
* of page contents can be set.
*
* If *@pages is NULL, a page list will be allocated to the required size and
* *@pages will be set to its base. If *@pages is not NULL, it will be assumed
* that the caller allocated a page list at least @maxpages in size and this
* will be filled in.
*
* @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA
* be allowed on the pages extracted.
*
* The iov_iter_extract_will_pin() function can be used to query how cleanup
* should be performed.
*
* Extra refs or pins on the pages may be obtained as follows:
*
* (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be
* added to the pages, but refs will not be taken.
* iov_iter_extract_will_pin() will return true.
*
* (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the
* pages are merely listed; no extra refs or pins are obtained.
* iov_iter_extract_will_pin() will return 0.
*
* Note also:
*
* (*) Use with ITER_DISCARD is not supported as that has no content.
*
* On success, the function sets *@pages to the new pagelist, if allocated, and
* sets *offset0 to the offset into the first page.
*
* It may also return -ENOMEM and -EFAULT.
*/
ssize_t iov_iter_extract_pages(struct iov_iter *i,
struct page ***pages,
size_t maxsize,
unsigned int maxpages,
iov_iter_extraction_t extraction_flags,
size_t *offset0)
{
maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT);
if (!maxsize)
return 0;
if (likely(user_backed_iter(i)))
return iov_iter_extract_user_pages(i, pages, maxsize,
maxpages, extraction_flags,
offset0);
if (iov_iter_is_kvec(i))
return iov_iter_extract_kvec_pages(i, pages, maxsize,
maxpages, extraction_flags,
offset0);
if (iov_iter_is_bvec(i))
return iov_iter_extract_bvec_pages(i, pages, maxsize,
maxpages, extraction_flags,
offset0);
if (iov_iter_is_folioq(i))
return iov_iter_extract_folioq_pages(i, pages, maxsize,
maxpages, extraction_flags,
offset0);
if (iov_iter_is_xarray(i))
return iov_iter_extract_xarray_pages(i, pages, maxsize,
maxpages, extraction_flags,
offset0);
return -EFAULT;
}
EXPORT_SYMBOL_GPL(iov_iter_extract_pages);
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* VMA-specific functions.
*/
#include "vma_internal.h"
#include "vma.h"
struct mmap_state {
struct mm_struct *mm;
struct vma_iterator *vmi;
unsigned long addr;
unsigned long end;
pgoff_t pgoff;
unsigned long pglen;
unsigned long flags;
struct file *file;
unsigned long charged;
bool retry_merge;
struct vm_area_struct *prev;
struct vm_area_struct *next;
/* Unmapping state. */
struct vma_munmap_struct vms;
struct ma_state mas_detach;
struct maple_tree mt_detach;
};
#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \
struct mmap_state name = { \
.mm = mm_, \
.vmi = vmi_, \
.addr = addr_, \
.end = (addr_) + (len_), \
.pgoff = pgoff_, \
.pglen = PHYS_PFN(len_), \
.flags = flags_, \
.file = file_, \
}
#define VMG_MMAP_STATE(name, map_, vma_) \
struct vma_merge_struct name = { \
.mm = (map_)->mm, \
.vmi = (map_)->vmi, \
.start = (map_)->addr, \
.end = (map_)->end, \
.flags = (map_)->flags, \
.pgoff = (map_)->pgoff, \
.file = (map_)->file, \
.prev = (map_)->prev, \
.middle = vma_, \
.next = (vma_) ? NULL : (map_)->next, \
.state = VMA_MERGE_START, \
}
static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next)
{
struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev;
if (!mpol_equal(vmg->policy, vma_policy(vma)))
return false;
/*
* VM_SOFTDIRTY should not prevent from VMA merging, if we
* match the flags but dirty bit -- the caller should mark
* merged VMA as dirty. If dirty bit won't be excluded from
* comparison, we increase pressure on the memory system forcing
* the kernel to generate new VMAs when old one could be
* extended instead.
*/
if ((vma->vm_flags ^ vmg->flags) & ~VM_SOFTDIRTY)
return false;
if (vma->vm_file != vmg->file)
return false;
if (!is_mergeable_vm_userfaultfd_ctx(vma, vmg->uffd_ctx))
return false;
if (!anon_vma_name_eq(anon_vma_name(vma), vmg->anon_name))
return false;
return true;
}
static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1,
struct anon_vma *anon_vma2, struct vm_area_struct *vma)
{
/*
* The list_is_singular() test is to avoid merging VMA cloned from
* parents. This can improve scalability caused by anon_vma lock.
*/
if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain)))
return true;
return anon_vma1 == anon_vma2;
}
/* Are the anon_vma's belonging to each VMA compatible with one another? */
static inline bool are_anon_vmas_compatible(struct vm_area_struct *vma1,
struct vm_area_struct *vma2)
{
return is_mergeable_anon_vma(vma1->anon_vma, vma2->anon_vma, NULL);
}
/*
* init_multi_vma_prep() - Initializer for struct vma_prepare
* @vp: The vma_prepare struct
* @vma: The vma that will be altered once locked
* @vmg: The merge state that will be used to determine adjustment and VMA
* removal.
*/
static void init_multi_vma_prep(struct vma_prepare *vp,
struct vm_area_struct *vma,
struct vma_merge_struct *vmg)
{
struct vm_area_struct *adjust;
struct vm_area_struct **remove = &vp->remove;
memset(vp, 0, sizeof(struct vma_prepare));
vp->vma = vma;
vp->anon_vma = vma->anon_vma;
if (vmg && vmg->__remove_middle) { *remove = vmg->middle;
remove = &vp->remove2;
}
if (vmg && vmg->__remove_next) *remove = vmg->next; if (vmg && vmg->__adjust_middle_start)
adjust = vmg->middle;
else if (vmg && vmg->__adjust_next_start)
adjust = vmg->next;
else
adjust = NULL;
vp->adj_next = adjust;
if (!vp->anon_vma && adjust) vp->anon_vma = adjust->anon_vma; VM_WARN_ON(vp->anon_vma && adjust && adjust->anon_vma &&
vp->anon_vma != adjust->anon_vma);
vp->file = vma->vm_file;
if (vp->file) vp->mapping = vma->vm_file->f_mapping;
}
/*
* Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
* in front of (at a lower virtual address and file offset than) the vma.
*
* We cannot merge two vmas if they have differently assigned (non-NULL)
* anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
*
* We don't check here for the merged mmap wrapping around the end of pagecache
* indices (16TB on ia32) because do_mmap() does not permit mmap's which
* wrap, nor mmaps which cover the final page at index -1UL.
*
* We assume the vma may be removed as part of the merge.
*/
static bool can_vma_merge_before(struct vma_merge_struct *vmg)
{
pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start);
if (is_mergeable_vma(vmg, /* merge_next = */ true) && is_mergeable_anon_vma(vmg->anon_vma, vmg->next->anon_vma, vmg->next)) { if (vmg->next->vm_pgoff == vmg->pgoff + pglen)
return true;
}
return false;
}
/*
* Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
* beyond (at a higher virtual address and file offset than) the vma.
*
* We cannot merge two vmas if they have differently assigned (non-NULL)
* anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
*
* We assume that vma is not removed as part of the merge.
*/
static bool can_vma_merge_after(struct vma_merge_struct *vmg)
{
if (is_mergeable_vma(vmg, /* merge_next = */ false) && is_mergeable_anon_vma(vmg->anon_vma, vmg->prev->anon_vma, vmg->prev)) { if (vmg->prev->vm_pgoff + vma_pages(vmg->prev) == vmg->pgoff)
return true;
}
return false;
}
static void __vma_link_file(struct vm_area_struct *vma,
struct address_space *mapping)
{
if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping);
flush_dcache_mmap_lock(mapping);
vma_interval_tree_insert(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
}
/*
* Requires inode->i_mapping->i_mmap_rwsem
*/
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
struct address_space *mapping)
{
if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping);
flush_dcache_mmap_lock(mapping);
vma_interval_tree_remove(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
}
/*
* vma has some anon_vma assigned, and is already inserted on that
* anon_vma's interval trees.
*
* Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
* vma must be removed from the anon_vma's interval trees using
* anon_vma_interval_tree_pre_update_vma().
*
* After the update, the vma will be reinserted using
* anon_vma_interval_tree_post_update_vma().
*
* The entire update must be protected by exclusive mmap_lock and by
* the root anon_vma's mutex.
*/
static void
anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
{
struct anon_vma_chain *avc;
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
}
static void
anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
{
struct anon_vma_chain *avc;
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
}
/*
* vma_prepare() - Helper function for handling locking VMAs prior to altering
* @vp: The initialized vma_prepare struct
*/
static void vma_prepare(struct vma_prepare *vp)
{ if (vp->file) {
uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end);
if (vp->adj_next)
uprobe_munmap(vp->adj_next, vp->adj_next->vm_start,
vp->adj_next->vm_end);
i_mmap_lock_write(vp->mapping);
if (vp->insert && vp->insert->vm_file) {
/*
* Put into interval tree now, so instantiated pages
* are visible to arm/parisc __flush_dcache_page
* throughout; but we cannot insert into address
* space until vma start or end is updated.
*/
__vma_link_file(vp->insert,
vp->insert->vm_file->f_mapping);
}
}
if (vp->anon_vma) {
anon_vma_lock_write(vp->anon_vma);
anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next);
}
if (vp->file) {
flush_dcache_mmap_lock(vp->mapping);
vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap);
if (vp->adj_next)
vma_interval_tree_remove(vp->adj_next,
&vp->mapping->i_mmap);
}
}
/*
* vma_complete- Helper function for handling the unlocking after altering VMAs,
* or for inserting a VMA.
*
* @vp: The vma_prepare struct
* @vmi: The vma iterator
* @mm: The mm_struct
*/
static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi,
struct mm_struct *mm)
{ if (vp->file) { if (vp->adj_next)
vma_interval_tree_insert(vp->adj_next,
&vp->mapping->i_mmap);
vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap);
flush_dcache_mmap_unlock(vp->mapping);
}
if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) {
/*
* split_vma has split insert from vma, and needs
* us to insert it before dropping the locks
* (it may either follow vma or precede it).
*/
vma_iter_store_new(vmi, vp->insert);
mm->map_count++;
}
if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next);
anon_vma_unlock_write(vp->anon_vma);
}
if (vp->file) { i_mmap_unlock_write(vp->mapping);
uprobe_mmap(vp->vma);
if (vp->adj_next)
uprobe_mmap(vp->adj_next);
}
if (vp->remove) {
again:
vma_mark_detached(vp->remove);
if (vp->file) {
uprobe_munmap(vp->remove, vp->remove->vm_start,
vp->remove->vm_end);
fput(vp->file);
}
if (vp->remove->anon_vma) anon_vma_merge(vp->vma, vp->remove);
mm->map_count--;
mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end);
vm_area_free(vp->remove);
/*
* In mprotect's case 6 (see comments on vma_merge),
* we are removing both mid and next vmas
*/
if (vp->remove2) { vp->remove = vp->remove2;
vp->remove2 = NULL;
goto again;
}
}
if (vp->insert && vp->file)
uprobe_mmap(vp->insert);
}
/*
* init_vma_prep() - Initializer wrapper for vma_prepare struct
* @vp: The vma_prepare struct
* @vma: The vma that will be altered once locked
*/
static void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma)
{
init_multi_vma_prep(vp, vma, NULL);
}
/*
* Can the proposed VMA be merged with the left (previous) VMA taking into
* account the start position of the proposed range.
*/
static bool can_vma_merge_left(struct vma_merge_struct *vmg)
{ return vmg->prev && vmg->prev->vm_end == vmg->start && can_vma_merge_after(vmg);
}
/*
* Can the proposed VMA be merged with the right (next) VMA taking into
* account the end position of the proposed range.
*
* In addition, if we can merge with the left VMA, ensure that left and right
* anon_vma's are also compatible.
*/
static bool can_vma_merge_right(struct vma_merge_struct *vmg,
bool can_merge_left)
{ if (!vmg->next || vmg->end != vmg->next->vm_start || !can_vma_merge_before(vmg))
return false;
if (!can_merge_left)
return true;
/*
* If we can merge with prev (left) and next (right), indicating that
* each VMA's anon_vma is compatible with the proposed anon_vma, this
* does not mean prev and next are compatible with EACH OTHER.
*
* We therefore check this in addition to mergeability to either side.
*/
return are_anon_vmas_compatible(vmg->prev, vmg->next);
}
/*
* Close a vm structure and free it.
*/
void remove_vma(struct vm_area_struct *vma)
{
might_sleep();
vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma));
vm_area_free(vma);
}
/*
* Get rid of page table information in the indicated region.
*
* Called with the mm semaphore held.
*/
void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct vm_area_struct *next)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
tlb_gather_mmu(&tlb, mm);
update_hiwater_rss(mm);
unmap_vmas(&tlb, mas, vma, vma->vm_start, vma->vm_end, vma->vm_end,
/* mm_wr_locked = */ true);
mas_set(mas, vma->vm_end);
free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING,
/* mm_wr_locked = */ true);
tlb_finish_mmu(&tlb);
}
/*
* __split_vma() bypasses sysctl_max_map_count checking. We use this where it
* has already been checked or doesn't make sense to fail.
* VMA Iterator will point to the original VMA.
*/
static __must_check int
__split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long addr, int new_below)
{
struct vma_prepare vp;
struct vm_area_struct *new;
int err;
WARN_ON(vma->vm_start >= addr); WARN_ON(vma->vm_end <= addr); if (vma->vm_ops && vma->vm_ops->may_split) {
err = vma->vm_ops->may_split(vma, addr);
if (err)
return err;
}
new = vm_area_dup(vma);
if (!new)
return -ENOMEM;
if (new_below) {
new->vm_end = addr;
} else {
new->vm_start = addr;
new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
}
err = -ENOMEM;
vma_iter_config(vmi, new->vm_start, new->vm_end);
if (vma_iter_prealloc(vmi, new))
goto out_free_vma;
err = vma_dup_policy(vma, new);
if (err)
goto out_free_vmi;
err = anon_vma_clone(new, vma);
if (err)
goto out_free_mpol;
if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); init_vma_prep(&vp, vma);
vp.insert = new;
vma_prepare(&vp);
vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL);
if (new_below) {
vma->vm_start = addr;
vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT;
} else {
vma->vm_end = addr;
}
/* vma_complete stores the new vma */
vma_complete(&vp, vmi, vma->vm_mm);
validate_mm(vma->vm_mm);
/* Success. */
if (new_below)
vma_next(vmi);
else
vma_prev(vmi);
return 0;
out_free_mpol:
mpol_put(vma_policy(new));
out_free_vmi:
vma_iter_free(vmi);
out_free_vma:
vm_area_free(new);
return err;
}
/*
* Split a vma into two pieces at address 'addr', a new vma is allocated
* either for the first part or the tail.
*/
static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long addr, int new_below)
{
if (vma->vm_mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
return __split_vma(vmi, vma, addr, new_below);
}
/*
* dup_anon_vma() - Helper function to duplicate anon_vma
* @dst: The destination VMA
* @src: The source VMA
* @dup: Pointer to the destination VMA when successful.
*
* Returns: 0 on success.
*/
static int dup_anon_vma(struct vm_area_struct *dst,
struct vm_area_struct *src, struct vm_area_struct **dup)
{
/*
* Easily overlooked: when mprotect shifts the boundary, make sure the
* expanding vma has anon_vma set if the shrinking vma had, to cover any
* anon pages imported.
*/
if (src->anon_vma && !dst->anon_vma) {
int ret;
vma_assert_write_locked(dst);
dst->anon_vma = src->anon_vma;
ret = anon_vma_clone(dst, src);
if (ret)
return ret;
*dup = dst;
}
return 0;
}
#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
void validate_mm(struct mm_struct *mm)
{
int bug = 0;
int i = 0;
struct vm_area_struct *vma;
VMA_ITERATOR(vmi, mm, 0);
mt_validate(&mm->mm_mt);
for_each_vma(vmi, vma) {
#ifdef CONFIG_DEBUG_VM_RB
struct anon_vma *anon_vma = vma->anon_vma;
struct anon_vma_chain *avc;
#endif
unsigned long vmi_start, vmi_end;
bool warn = 0;
vmi_start = vma_iter_addr(&vmi);
vmi_end = vma_iter_end(&vmi);
if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm))
warn = 1;
if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm))
warn = 1;
if (warn) {
pr_emerg("issue in %s\n", current->comm);
dump_stack();
dump_vma(vma);
pr_emerg("tree range: %px start %lx end %lx\n", vma,
vmi_start, vmi_end - 1);
vma_iter_dump_tree(&vmi);
}
#ifdef CONFIG_DEBUG_VM_RB
if (anon_vma) {
anon_vma_lock_read(anon_vma);
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
anon_vma_interval_tree_verify(avc);
anon_vma_unlock_read(anon_vma);
}
#endif
/* Check for a infinite loop */
if (++i > mm->map_count + 10) {
i = -1;
break;
}
}
if (i != mm->map_count) {
pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i);
bug = 1;
}
VM_BUG_ON_MM(bug, mm);
}
#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */
/*
* Based on the vmg flag indicating whether we need to adjust the vm_start field
* for the middle or next VMA, we calculate what the range of the newly adjusted
* VMA ought to be, and set the VMA's range accordingly.
*/
static void vmg_adjust_set_range(struct vma_merge_struct *vmg)
{
struct vm_area_struct *adjust;
pgoff_t pgoff;
if (vmg->__adjust_middle_start) {
adjust = vmg->middle;
pgoff = adjust->vm_pgoff + PHYS_PFN(vmg->end - adjust->vm_start);
} else if (vmg->__adjust_next_start) { adjust = vmg->next;
pgoff = adjust->vm_pgoff - PHYS_PFN(adjust->vm_start - vmg->end);
} else {
return;
}
vma_set_range(adjust, vmg->end, adjust->vm_end, pgoff);
}
/*
* Actually perform the VMA merge operation.
*
* IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not
* modify any VMAs or cause inconsistent state should an OOM condition arise.
*
* Returns 0 on success, or an error value on failure.
*/
static int commit_merge(struct vma_merge_struct *vmg)
{
struct vm_area_struct *vma;
struct vma_prepare vp;
if (vmg->__adjust_next_start) {
/* We manipulate middle and adjust next, which is the target. */
vma = vmg->middle;
vma_iter_config(vmg->vmi, vmg->end, vmg->next->vm_end);
} else {
vma = vmg->target;
/* Note: vma iterator must be pointing to 'start'. */
vma_iter_config(vmg->vmi, vmg->start, vmg->end);
}
init_multi_vma_prep(&vp, vma, vmg);
/*
* If vmg->give_up_on_oom is set, we're safe, because we don't actually
* manipulate any VMAs until we succeed at preallocation.
*
* Past this point, we will not return an error.
*/
if (vma_iter_prealloc(vmg->vmi, vma))
return -ENOMEM;
vma_prepare(&vp);
/*
* THP pages may need to do additional splits if we increase
* middle->vm_start.
*/
vma_adjust_trans_huge(vma, vmg->start, vmg->end,
vmg->__adjust_middle_start ? vmg->middle : NULL);
vma_set_range(vma, vmg->start, vmg->end, vmg->pgoff);
vmg_adjust_set_range(vmg);
vma_iter_store_overwrite(vmg->vmi, vmg->target);
vma_complete(&vp, vmg->vmi, vma->vm_mm);
return 0;
}
/* We can only remove VMAs when merging if they do not have a close hook. */
static bool can_merge_remove_vma(struct vm_area_struct *vma)
{
return !vma->vm_ops || !vma->vm_ops->close;
}
/*
* vma_merge_existing_range - Attempt to merge VMAs based on a VMA having its
* attributes modified.
*
* @vmg: Describes the modifications being made to a VMA and associated
* metadata.
*
* When the attributes of a range within a VMA change, then it might be possible
* for immediately adjacent VMAs to be merged into that VMA due to having
* identical properties.
*
* This function checks for the existence of any such mergeable VMAs and updates
* the maple tree describing the @vmg->middle->vm_mm address space to account
* for this, as well as any VMAs shrunk/expanded/deleted as a result of this
* merge.
*
* As part of this operation, if a merge occurs, the @vmg object will have its
* vma, start, end, and pgoff fields modified to execute the merge. Subsequent
* calls to this function should reset these fields.
*
* Returns: The merged VMA if merge succeeds, or NULL otherwise.
*
* ASSUMPTIONS:
* - The caller must assign the VMA to be modifed to @vmg->middle.
* - The caller must have set @vmg->prev to the previous VMA, if there is one.
* - The caller must not set @vmg->next, as we determine this.
* - The caller must hold a WRITE lock on the mm_struct->mmap_lock.
* - vmi must be positioned within [@vmg->middle->vm_start, @vmg->middle->vm_end).
*/
static __must_check struct vm_area_struct *vma_merge_existing_range(
struct vma_merge_struct *vmg)
{
struct vm_area_struct *middle = vmg->middle;
struct vm_area_struct *prev = vmg->prev;
struct vm_area_struct *next;
struct vm_area_struct *anon_dup = NULL;
unsigned long start = vmg->start;
unsigned long end = vmg->end;
bool left_side = middle && start == middle->vm_start;
bool right_side = middle && end == middle->vm_end;
int err = 0;
bool merge_left, merge_right, merge_both;
mmap_assert_write_locked(vmg->mm);
VM_WARN_ON_VMG(!middle, vmg); /* We are modifying a VMA, so caller must specify. */
VM_WARN_ON_VMG(vmg->next, vmg); /* We set this. */
VM_WARN_ON_VMG(prev && start <= prev->vm_start, vmg);
VM_WARN_ON_VMG(start >= end, vmg);
/*
* If middle == prev, then we are offset into a VMA. Otherwise, if we are
* not, we must span a portion of the VMA.
*/
VM_WARN_ON_VMG(middle &&
((middle != prev && vmg->start != middle->vm_start) ||
vmg->end > middle->vm_end), vmg);
/* The vmi must be positioned within vmg->middle. */
VM_WARN_ON_VMG(middle &&
!(vma_iter_addr(vmg->vmi) >= middle->vm_start &&
vma_iter_addr(vmg->vmi) < middle->vm_end), vmg);
vmg->state = VMA_MERGE_NOMERGE;
/*
* If a special mapping or if the range being modified is neither at the
* furthermost left or right side of the VMA, then we have no chance of
* merging and should abort.
*/
if (vmg->flags & VM_SPECIAL || (!left_side && !right_side))
return NULL;
if (left_side)
merge_left = can_vma_merge_left(vmg);
else
merge_left = false;
if (right_side) {
next = vmg->next = vma_iter_next_range(vmg->vmi);
vma_iter_prev_range(vmg->vmi);
merge_right = can_vma_merge_right(vmg, merge_left);
} else {
merge_right = false;
next = NULL;
}
if (merge_left) /* If merging prev, position iterator there. */
vma_prev(vmg->vmi);
else if (!merge_right) /* If we have nothing to merge, abort. */
return NULL;
merge_both = merge_left && merge_right;
/* If we span the entire VMA, a merge implies it will be deleted. */
vmg->__remove_middle = left_side && right_side;
/*
* If we need to remove middle in its entirety but are unable to do so,
* we have no sensible recourse but to abort the merge.
*/
if (vmg->__remove_middle && !can_merge_remove_vma(middle))
return NULL;
/*
* If we merge both VMAs, then next is also deleted. This implies
* merge_will_delete_vma also.
*/
vmg->__remove_next = merge_both;
/*
* If we cannot delete next, then we can reduce the operation to merging
* prev and middle (thereby deleting middle).
*/
if (vmg->__remove_next && !can_merge_remove_vma(next)) {
vmg->__remove_next = false;
merge_right = false;
merge_both = false;
}
/* No matter what happens, we will be adjusting middle. */
vma_start_write(middle);
if (merge_right) {
vma_start_write(next);
vmg->target = next;
}
if (merge_left) {
vma_start_write(prev);
vmg->target = prev;
}
if (merge_both) {
/*
* |<-------------------->|
* |-------********-------|
* prev middle next
* extend delete delete
*/
vmg->start = prev->vm_start;
vmg->end = next->vm_end;
vmg->pgoff = prev->vm_pgoff;
/*
* We already ensured anon_vma compatibility above, so now it's
* simply a case of, if prev has no anon_vma object, which of
* next or middle contains the anon_vma we must duplicate.
*/
err = dup_anon_vma(prev, next->anon_vma ? next : middle,
&anon_dup);
} else if (merge_left) {
/*
* |<------------>| OR
* |<----------------->|
* |-------*************
* prev middle
* extend shrink/delete
*/
vmg->start = prev->vm_start;
vmg->pgoff = prev->vm_pgoff;
if (!vmg->__remove_middle)
vmg->__adjust_middle_start = true;
err = dup_anon_vma(prev, middle, &anon_dup);
} else { /* merge_right */
/*
* |<------------->| OR
* |<----------------->|
* *************-------|
* middle next
* shrink/delete extend
*/
pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start);
VM_WARN_ON_VMG(!merge_right, vmg);
/* If we are offset into a VMA, then prev must be middle. */
VM_WARN_ON_VMG(vmg->start > middle->vm_start && prev && middle != prev, vmg);
if (vmg->__remove_middle) {
vmg->end = next->vm_end;
vmg->pgoff = next->vm_pgoff - pglen;
} else {
/* We shrink middle and expand next. */
vmg->__adjust_next_start = true;
vmg->start = middle->vm_start;
vmg->end = start;
vmg->pgoff = middle->vm_pgoff;
}
err = dup_anon_vma(next, middle, &anon_dup);
}
if (err)
goto abort;
err = commit_merge(vmg);
if (err) {
VM_WARN_ON(err != -ENOMEM);
if (anon_dup)
unlink_anon_vmas(anon_dup);
/*
* We've cleaned up any cloned anon_vma's, no VMAs have been
* modified, no harm no foul if the user requests that we not
* report this and just give up, leaving the VMAs unmerged.
*/
if (!vmg->give_up_on_oom)
vmg->state = VMA_MERGE_ERROR_NOMEM;
return NULL;
}
khugepaged_enter_vma(vmg->target, vmg->flags);
vmg->state = VMA_MERGE_SUCCESS;
return vmg->target;
abort:
vma_iter_set(vmg->vmi, start);
vma_iter_load(vmg->vmi);
/*
* This means we have failed to clone anon_vma's correctly, but no
* actual changes to VMAs have occurred, so no harm no foul - if the
* user doesn't want this reported and instead just wants to give up on
* the merge, allow it.
*/
if (!vmg->give_up_on_oom)
vmg->state = VMA_MERGE_ERROR_NOMEM;
return NULL;
}
/*
* vma_merge_new_range - Attempt to merge a new VMA into address space
*
* @vmg: Describes the VMA we are adding, in the range @vmg->start to @vmg->end
* (exclusive), which we try to merge with any adjacent VMAs if possible.
*
* We are about to add a VMA to the address space starting at @vmg->start and
* ending at @vmg->end. There are three different possible scenarios:
*
* 1. There is a VMA with identical properties immediately adjacent to the
* proposed new VMA [@vmg->start, @vmg->end) either before or after it -
* EXPAND that VMA:
*
* Proposed: |-----| or |-----|
* Existing: |----| |----|
*
* 2. There are VMAs with identical properties immediately adjacent to the
* proposed new VMA [@vmg->start, @vmg->end) both before AND after it -
* EXPAND the former and REMOVE the latter:
*
* Proposed: |-----|
* Existing: |----| |----|
*
* 3. There are no VMAs immediately adjacent to the proposed new VMA or those
* VMAs do not have identical attributes - NO MERGE POSSIBLE.
*
* In instances where we can merge, this function returns the expanded VMA which
* will have its range adjusted accordingly and the underlying maple tree also
* adjusted.
*
* Returns: In instances where no merge was possible, NULL. Otherwise, a pointer
* to the VMA we expanded.
*
* This function adjusts @vmg to provide @vmg->next if not already specified,
* and adjusts [@vmg->start, @vmg->end) to span the expanded range.
*
* ASSUMPTIONS:
* - The caller must hold a WRITE lock on the mm_struct->mmap_lock.
* - The caller must have determined that [@vmg->start, @vmg->end) is empty,
other than VMAs that will be unmapped should the operation succeed.
* - The caller must have specified the previous vma in @vmg->prev.
* - The caller must have specified the next vma in @vmg->next.
* - The caller must have positioned the vmi at or before the gap.
*/
struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
{
struct vm_area_struct *prev = vmg->prev;
struct vm_area_struct *next = vmg->next;
unsigned long end = vmg->end;
bool can_merge_left, can_merge_right;
mmap_assert_write_locked(vmg->mm); VM_WARN_ON_VMG(vmg->middle, vmg);
/* vmi must point at or before the gap. */
VM_WARN_ON_VMG(vma_iter_addr(vmg->vmi) > end, vmg);
vmg->state = VMA_MERGE_NOMERGE;
/* Special VMAs are unmergeable, also if no prev/next. */
if ((vmg->flags & VM_SPECIAL) || (!prev && !next))
return NULL;
can_merge_left = can_vma_merge_left(vmg);
can_merge_right = !vmg->just_expand && can_vma_merge_right(vmg, can_merge_left);
/* If we can merge with the next VMA, adjust vmg accordingly. */
if (can_merge_right) {
vmg->end = next->vm_end;
vmg->middle = next;
}
/* If we can merge with the previous VMA, adjust vmg accordingly. */
if (can_merge_left) { vmg->start = prev->vm_start;
vmg->middle = prev;
vmg->pgoff = prev->vm_pgoff;
/*
* If this merge would result in removal of the next VMA but we
* are not permitted to do so, reduce the operation to merging
* prev and vma.
*/
if (can_merge_right && !can_merge_remove_vma(next)) vmg->end = end;
/* In expand-only case we are already positioned at prev. */
if (!vmg->just_expand) {
/* Equivalent to going to the previous range. */
vma_prev(vmg->vmi);
}
}
/*
* Now try to expand adjacent VMA(s). This takes care of removing the
* following VMA if we have VMAs on both sides.
*/
if (vmg->middle && !vma_expand(vmg)) { khugepaged_enter_vma(vmg->middle, vmg->flags);
vmg->state = VMA_MERGE_SUCCESS;
return vmg->middle;
}
return NULL;
}
/*
* vma_expand - Expand an existing VMA
*
* @vmg: Describes a VMA expansion operation.
*
* Expand @vma to vmg->start and vmg->end. Can expand off the start and end.
* Will expand over vmg->next if it's different from vmg->middle and vmg->end ==
* vmg->next->vm_end. Checking if the vmg->middle can expand and merge with
* vmg->next needs to be handled by the caller.
*
* Returns: 0 on success.
*
* ASSUMPTIONS:
* - The caller must hold a WRITE lock on vmg->middle->mm->mmap_lock.
* - The caller must have set @vmg->middle and @vmg->next.
*/
int vma_expand(struct vma_merge_struct *vmg)
{
struct vm_area_struct *anon_dup = NULL;
bool remove_next = false;
struct vm_area_struct *middle = vmg->middle;
struct vm_area_struct *next = vmg->next;
mmap_assert_write_locked(vmg->mm); vma_start_write(middle); if (next && (middle != next) && (vmg->end == next->vm_end)) {
int ret;
remove_next = true;
/* This should already have been checked by this point. */
VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); vma_start_write(next);
/*
* In this case we don't report OOM, so vmg->give_up_on_mm is
* safe.
*/
ret = dup_anon_vma(middle, next, &anon_dup);
if (ret)
return ret;
}
/* Not merging but overwriting any part of next is not handled. */
VM_WARN_ON_VMG(next && !remove_next &&
next != middle && vmg->end > next->vm_start, vmg);
/* Only handles expanding */
VM_WARN_ON_VMG(middle->vm_start < vmg->start ||
middle->vm_end > vmg->end, vmg);
vmg->target = middle;
if (remove_next) vmg->__remove_next = true; if (commit_merge(vmg))
goto nomem;
return 0;
nomem:
if (anon_dup) unlink_anon_vmas(anon_dup);
/*
* If the user requests that we just give upon OOM, we are safe to do so
* here, as commit merge provides this contract to us. Nothing has been
* changed - no harm no foul, just don't report it.
*/
if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM;
return -ENOMEM;
}
/*
* vma_shrink() - Reduce an existing VMAs memory area
* @vmi: The vma iterator
* @vma: The VMA to modify
* @start: The new start
* @end: The new end
*
* Returns: 0 on success, -ENOMEM otherwise
*/
int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long start, unsigned long end, pgoff_t pgoff)
{
struct vma_prepare vp;
WARN_ON((vma->vm_start != start) && (vma->vm_end != end));
if (vma->vm_start < start)
vma_iter_config(vmi, vma->vm_start, start);
else
vma_iter_config(vmi, end, vma->vm_end);
if (vma_iter_prealloc(vmi, NULL))
return -ENOMEM;
vma_start_write(vma);
init_vma_prep(&vp, vma);
vma_prepare(&vp);
vma_adjust_trans_huge(vma, start, end, NULL);
vma_iter_clear(vmi);
vma_set_range(vma, start, end, pgoff);
vma_complete(&vp, vmi, vma->vm_mm);
validate_mm(vma->vm_mm);
return 0;
}
static inline void vms_clear_ptes(struct vma_munmap_struct *vms,
struct ma_state *mas_detach, bool mm_wr_locked)
{
struct mmu_gather tlb;
if (!vms->clear_ptes) /* Nothing to do */
return;
/*
* We can free page tables without write-locking mmap_lock because VMAs
* were isolated before we downgraded mmap_lock.
*/
mas_set(mas_detach, 1);
tlb_gather_mmu(&tlb, vms->vma->vm_mm);
update_hiwater_rss(vms->vma->vm_mm);
unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end,
vms->vma_count, mm_wr_locked);
mas_set(mas_detach, 1);
/* start and end may be different if there is no prev or next vma. */
free_pgtables(&tlb, mas_detach, vms->vma, vms->unmap_start,
vms->unmap_end, mm_wr_locked);
tlb_finish_mmu(&tlb);
vms->clear_ptes = false;
}
static void vms_clean_up_area(struct vma_munmap_struct *vms,
struct ma_state *mas_detach)
{
struct vm_area_struct *vma;
if (!vms->nr_pages)
return;
vms_clear_ptes(vms, mas_detach, true);
mas_set(mas_detach, 0);
mas_for_each(mas_detach, vma, ULONG_MAX) vma_close(vma);
}
/*
* vms_complete_munmap_vmas() - Finish the munmap() operation
* @vms: The vma munmap struct
* @mas_detach: The maple state of the detached vmas
*
* This updates the mm_struct, unmaps the region, frees the resources
* used for the munmap() and may downgrade the lock - if requested. Everything
* needed to be done once the vma maple tree is updated.
*/
static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
struct ma_state *mas_detach)
{
struct vm_area_struct *vma;
struct mm_struct *mm;
mm = current->mm;
mm->map_count -= vms->vma_count;
mm->locked_vm -= vms->locked_vm;
if (vms->unlock) mmap_write_downgrade(mm); if (!vms->nr_pages)
return;
vms_clear_ptes(vms, mas_detach, !vms->unlock);
/* Update high watermark before we lower total_vm */
update_hiwater_vm(mm);
/* Stat accounting */
WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages);
/* Paranoid bookkeeping */
VM_WARN_ON(vms->exec_vm > mm->exec_vm); VM_WARN_ON(vms->stack_vm > mm->stack_vm); VM_WARN_ON(vms->data_vm > mm->data_vm);
mm->exec_vm -= vms->exec_vm;
mm->stack_vm -= vms->stack_vm;
mm->data_vm -= vms->data_vm;
/* Remove and clean up vmas */
mas_set(mas_detach, 0);
mas_for_each(mas_detach, vma, ULONG_MAX) remove_vma(vma);
vm_unacct_memory(vms->nr_accounted);
validate_mm(mm);
if (vms->unlock) mmap_read_unlock(mm);
__mt_destroy(mas_detach->tree);
}
/*
* reattach_vmas() - Undo any munmap work and free resources
* @mas_detach: The maple state with the detached maple tree
*
* Reattach any detached vmas and free up the maple tree used to track the vmas.
*/
static void reattach_vmas(struct ma_state *mas_detach)
{
struct vm_area_struct *vma;
mas_set(mas_detach, 0);
mas_for_each(mas_detach, vma, ULONG_MAX) vma_mark_attached(vma);
__mt_destroy(mas_detach->tree);
}
/*
* vms_gather_munmap_vmas() - Put all VMAs within a range into a maple tree
* for removal at a later date. Handles splitting first and last if necessary
* and marking the vmas as isolated.
*
* @vms: The vma munmap struct
* @mas_detach: The maple state tracking the detached tree
*
* Return: 0 on success, error otherwise
*/
static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
struct ma_state *mas_detach)
{
struct vm_area_struct *next = NULL;
int error;
/*
* If we need to split any vma, do it now to save pain later.
* Does it split the first one?
*/
if (vms->start > vms->vma->vm_start) {
/*
* Make sure that map_count on return from munmap() will
* not exceed its limit; but let map_count go just above
* its limit temporarily, to help free resources as expected.
*/
if (vms->end < vms->vma->vm_end &&
vms->vma->vm_mm->map_count >= sysctl_max_map_count) {
error = -ENOMEM;
goto map_count_exceeded;
}
/* Don't bother splitting the VMA if we can't unmap it anyway */
if (!can_modify_vma(vms->vma)) {
error = -EPERM;
goto start_split_failed;
}
error = __split_vma(vms->vmi, vms->vma, vms->start, 1);
if (error)
goto start_split_failed;
}
vms->prev = vma_prev(vms->vmi);
if (vms->prev) vms->unmap_start = vms->prev->vm_end;
/*
* Detach a range of VMAs from the mm. Using next as a temp variable as
* it is always overwritten.
*/
for_each_vma_range(*(vms->vmi), next, vms->end) {
long nrpages;
if (!can_modify_vma(next)) {
error = -EPERM;
goto modify_vma_failed;
}
/* Does it split the end? */
if (next->vm_end > vms->end) {
error = __split_vma(vms->vmi, next, vms->end, 0);
if (error)
goto end_split_failed;
}
vma_start_write(next);
mas_set(mas_detach, vms->vma_count++);
error = mas_store_gfp(mas_detach, next, GFP_KERNEL);
if (error)
goto munmap_gather_failed;
vma_mark_detached(next);
nrpages = vma_pages(next);
vms->nr_pages += nrpages;
if (next->vm_flags & VM_LOCKED) vms->locked_vm += nrpages; if (next->vm_flags & VM_ACCOUNT) vms->nr_accounted += nrpages;
if (is_exec_mapping(next->vm_flags))
vms->exec_vm += nrpages;
else if (is_stack_mapping(next->vm_flags))
vms->stack_vm += nrpages; else if (is_data_mapping(next->vm_flags)) vms->data_vm += nrpages; if (vms->uf) {
/*
* If userfaultfd_unmap_prep returns an error the vmas
* will remain split, but userland will get a
* highly unexpected error anyway. This is no
* different than the case where the first of the two
* __split_vma fails, but we don't undo the first
* split, despite we could. This is unlikely enough
* failure that it's not worth optimizing it for.
*/
error = userfaultfd_unmap_prep(next, vms->start,
vms->end, vms->uf);
if (error)
goto userfaultfd_error;
}
#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
BUG_ON(next->vm_start < vms->start); BUG_ON(next->vm_start > vms->end);
#endif
}
vms->next = vma_next(vms->vmi);
if (vms->next) vms->unmap_end = vms->next->vm_start;
#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
/* Make sure no VMAs are about to be lost. */
{
MA_STATE(test, mas_detach->tree, 0, 0);
struct vm_area_struct *vma_mas, *vma_test;
int test_count = 0;
vma_iter_set(vms->vmi, vms->start);
rcu_read_lock();
vma_test = mas_find(&test, vms->vma_count - 1);
for_each_vma_range(*(vms->vmi), vma_mas, vms->end) { BUG_ON(vma_mas != vma_test);
test_count++;
vma_test = mas_next(&test, vms->vma_count - 1);
}
rcu_read_unlock(); BUG_ON(vms->vma_count != test_count);
}
#endif
while (vma_iter_addr(vms->vmi) > vms->start)
vma_iter_prev_range(vms->vmi);
vms->clear_ptes = true;
return 0;
userfaultfd_error:
munmap_gather_failed:
end_split_failed:
modify_vma_failed:
reattach_vmas(mas_detach);
start_split_failed:
map_count_exceeded:
return error;
}
/*
* init_vma_munmap() - Initializer wrapper for vma_munmap_struct
* @vms: The vma munmap struct
* @vmi: The vma iterator
* @vma: The first vm_area_struct to munmap
* @start: The aligned start address to munmap
* @end: The aligned end address to munmap
* @uf: The userfaultfd list_head
* @unlock: Unlock after the operation. Only unlocked on success
*/
static void init_vma_munmap(struct vma_munmap_struct *vms,
struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long start, unsigned long end, struct list_head *uf,
bool unlock)
{
vms->vmi = vmi;
vms->vma = vma;
if (vma) {
vms->start = start;
vms->end = end;
} else {
vms->start = vms->end = 0;
}
vms->unlock = unlock;
vms->uf = uf;
vms->vma_count = 0;
vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0;
vms->exec_vm = vms->stack_vm = vms->data_vm = 0;
vms->unmap_start = FIRST_USER_ADDRESS;
vms->unmap_end = USER_PGTABLES_CEILING;
vms->clear_ptes = false;
}
/*
* do_vmi_align_munmap() - munmap the aligned region from @start to @end.
* @vmi: The vma iterator
* @vma: The starting vm_area_struct
* @mm: The mm_struct
* @start: The aligned start address to munmap.
* @end: The aligned end address to munmap.
* @uf: The userfaultfd list_head
* @unlock: Set to true to drop the mmap_lock. unlocking only happens on
* success.
*
* Return: 0 on success and drops the lock if so directed, error and leaves the
* lock held otherwise.
*/
int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct mm_struct *mm, unsigned long start, unsigned long end,
struct list_head *uf, bool unlock)
{
struct maple_tree mt_detach;
MA_STATE(mas_detach, &mt_detach, 0, 0);
mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK);
mt_on_stack(mt_detach);
struct vma_munmap_struct vms;
int error;
init_vma_munmap(&vms, vmi, vma, start, end, uf, unlock);
error = vms_gather_munmap_vmas(&vms, &mas_detach);
if (error)
goto gather_failed;
error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL);
if (error)
goto clear_tree_failed;
/* Point of no return */
vms_complete_munmap_vmas(&vms, &mas_detach);
return 0;
clear_tree_failed:
reattach_vmas(&mas_detach);
gather_failed:
validate_mm(mm);
return error;
}
/*
* do_vmi_munmap() - munmap a given range.
* @vmi: The vma iterator
* @mm: The mm_struct
* @start: The start address to munmap
* @len: The length of the range to munmap
* @uf: The userfaultfd list_head
* @unlock: set to true if the user wants to drop the mmap_lock on success
*
* This function takes a @mas that is either pointing to the previous VMA or set
* to MA_START and sets it up to remove the mapping(s). The @len will be
* aligned.
*
* Return: 0 on success and drops the lock if so directed, error and leaves the
* lock held otherwise.
*/
int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
unsigned long start, size_t len, struct list_head *uf,
bool unlock)
{
unsigned long end;
struct vm_area_struct *vma;
if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start)
return -EINVAL;
end = start + PAGE_ALIGN(len);
if (end == start)
return -EINVAL;
/* Find the first overlapping VMA */
vma = vma_find(vmi, end);
if (!vma) {
if (unlock) mmap_write_unlock(mm);
return 0;
}
return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock);
}
/*
* We are about to modify one or multiple of a VMA's flags, policy, userfaultfd
* context and anonymous VMA name within the range [start, end).
*
* As a result, we might be able to merge the newly modified VMA range with an
* adjacent VMA with identical properties.
*
* If no merge is possible and the range does not span the entirety of the VMA,
* we then need to split the VMA to accommodate the change.
*
* The function returns either the merged VMA, the original VMA if a split was
* required instead, or an error if the split failed.
*/
static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
{
struct vm_area_struct *vma = vmg->middle;
unsigned long start = vmg->start;
unsigned long end = vmg->end;
struct vm_area_struct *merged;
/* First, try to merge. */
merged = vma_merge_existing_range(vmg);
if (merged)
return merged;
if (vmg_nomem(vmg))
return ERR_PTR(-ENOMEM);
/*
* Split can fail for reasons other than OOM, so if the user requests
* this it's probably a mistake.
*/
VM_WARN_ON(vmg->give_up_on_oom &&
(vma->vm_start != start || vma->vm_end != end));
/* Split any preceding portion of the VMA. */
if (vma->vm_start < start) {
int err = split_vma(vmg->vmi, vma, start, 1);
if (err)
return ERR_PTR(err);
}
/* Split any trailing portion of the VMA. */
if (vma->vm_end > end) {
int err = split_vma(vmg->vmi, vma, end, 0);
if (err)
return ERR_PTR(err);
}
return vma;
}
struct vm_area_struct *vma_modify_flags(
struct vma_iterator *vmi, struct vm_area_struct *prev,
struct vm_area_struct *vma, unsigned long start, unsigned long end,
unsigned long new_flags)
{
VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
vmg.flags = new_flags;
return vma_modify(&vmg);
}
struct vm_area_struct
*vma_modify_flags_name(struct vma_iterator *vmi,
struct vm_area_struct *prev,
struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
unsigned long new_flags,
struct anon_vma_name *new_name)
{
VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
vmg.flags = new_flags;
vmg.anon_name = new_name;
return vma_modify(&vmg);
}
struct vm_area_struct
*vma_modify_policy(struct vma_iterator *vmi,
struct vm_area_struct *prev,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct mempolicy *new_pol)
{
VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
vmg.policy = new_pol;
return vma_modify(&vmg);
}
struct vm_area_struct
*vma_modify_flags_uffd(struct vma_iterator *vmi,
struct vm_area_struct *prev,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long new_flags,
struct vm_userfaultfd_ctx new_ctx,
bool give_up_on_oom)
{
VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
vmg.flags = new_flags;
vmg.uffd_ctx = new_ctx;
if (give_up_on_oom)
vmg.give_up_on_oom = true;
return vma_modify(&vmg);
}
/*
* Expand vma by delta bytes, potentially merging with an immediately adjacent
* VMA with identical properties.
*/
struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
struct vm_area_struct *vma,
unsigned long delta)
{
VMG_VMA_STATE(vmg, vmi, vma, vma, vma->vm_end, vma->vm_end + delta);
vmg.next = vma_iter_next_rewind(vmi, NULL);
vmg.middle = NULL; /* We use the VMA to populate VMG fields only. */
return vma_merge_new_range(&vmg);
}
void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb)
{
vb->count = 0;
}
static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb)
{
struct address_space *mapping;
int i;
mapping = vb->vmas[0]->vm_file->f_mapping;
i_mmap_lock_write(mapping);
for (i = 0; i < vb->count; i++) { VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); __remove_shared_vm_struct(vb->vmas[i], mapping);
}
i_mmap_unlock_write(mapping);
unlink_file_vma_batch_init(vb);
}
void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb,
struct vm_area_struct *vma)
{ if (vma->vm_file == NULL)
return;
if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) ||
vb->count == ARRAY_SIZE(vb->vmas))
unlink_file_vma_batch_process(vb);
vb->vmas[vb->count] = vma;
vb->count++;
}
void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb)
{ if (vb->count > 0) unlink_file_vma_batch_process(vb);
}
/*
* Unlink a file-based vm structure from its interval tree, to hide
* vma from rmap and vmtruncate before freeing its page tables.
*/
void unlink_file_vma(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
if (file) {
struct address_space *mapping = file->f_mapping;
i_mmap_lock_write(mapping);
__remove_shared_vm_struct(vma, mapping);
i_mmap_unlock_write(mapping);
}
}
void vma_link_file(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct address_space *mapping;
if (file) {
mapping = file->f_mapping;
i_mmap_lock_write(mapping);
__vma_link_file(vma, mapping);
i_mmap_unlock_write(mapping);
}
}
int vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
{
VMA_ITERATOR(vmi, mm, 0);
vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
if (vma_iter_prealloc(&vmi, vma))
return -ENOMEM;
vma_start_write(vma);
vma_iter_store_new(&vmi, vma);
vma_link_file(vma);
mm->map_count++;
validate_mm(mm);
return 0;
}
/*
* Copy the vma structure to a new location in the same mm,
* prior to moving page table entries, to effect an mremap move.
*/
struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
unsigned long addr, unsigned long len, pgoff_t pgoff,
bool *need_rmap_locks)
{
struct vm_area_struct *vma = *vmap;
unsigned long vma_start = vma->vm_start;
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma;
bool faulted_in_anon_vma = true;
VMA_ITERATOR(vmi, mm, addr);
VMG_VMA_STATE(vmg, &vmi, NULL, vma, addr, addr + len);
/*
* If anonymous vma has not yet been faulted, update new pgoff
* to match new location, to increase its chance of merging.
*/
if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) {
pgoff = addr >> PAGE_SHIFT;
faulted_in_anon_vma = false;
}
new_vma = find_vma_prev(mm, addr, &vmg.prev);
if (new_vma && new_vma->vm_start < addr + len)
return NULL; /* should never get here */
vmg.middle = NULL; /* New VMA range. */
vmg.pgoff = pgoff;
vmg.next = vma_iter_next_rewind(&vmi, NULL);
new_vma = vma_merge_new_range(&vmg);
if (new_vma) {
/*
* Source vma may have been merged into new_vma
*/
if (unlikely(vma_start >= new_vma->vm_start &&
vma_start < new_vma->vm_end)) {
/*
* The only way we can get a vma_merge with
* self during an mremap is if the vma hasn't
* been faulted in yet and we were allowed to
* reset the dst vma->vm_pgoff to the
* destination address of the mremap to allow
* the merge to happen. mremap must change the
* vm_pgoff linearity between src and dst vmas
* (in turn preventing a vma_merge) to be
* safe. It is only safe to keep the vm_pgoff
* linear if there are no pages mapped yet.
*/
VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
*vmap = vma = new_vma;
}
*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
} else {
new_vma = vm_area_dup(vma);
if (!new_vma)
goto out;
vma_set_range(new_vma, addr, addr + len, pgoff);
if (vma_dup_policy(vma, new_vma))
goto out_free_vma;
if (anon_vma_clone(new_vma, vma))
goto out_free_mempol;
if (new_vma->vm_file)
get_file(new_vma->vm_file);
if (new_vma->vm_ops && new_vma->vm_ops->open)
new_vma->vm_ops->open(new_vma);
if (vma_link(mm, new_vma))
goto out_vma_link;
*need_rmap_locks = false;
}
return new_vma;
out_vma_link:
vma_close(new_vma);
if (new_vma->vm_file)
fput(new_vma->vm_file);
unlink_anon_vmas(new_vma);
out_free_mempol:
mpol_put(vma_policy(new_vma));
out_free_vma:
vm_area_free(new_vma);
out:
return NULL;
}
/*
* Rough compatibility check to quickly see if it's even worth looking
* at sharing an anon_vma.
*
* They need to have the same vm_file, and the flags can only differ
* in things that mprotect may change.
*
* NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
* we can merge the two vma's. For example, we refuse to merge a vma if
* there is a vm_ops->close() function, because that indicates that the
* driver is doing some kind of reference counting. But that doesn't
* really matter for the anon_vma sharing case.
*/
static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
{
return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) &&
b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
}
/*
* Do some basic sanity checking to see if we can re-use the anon_vma
* from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
* the same as 'old', the other will be the new one that is trying
* to share the anon_vma.
*
* NOTE! This runs with mmap_lock held for reading, so it is possible that
* the anon_vma of 'old' is concurrently in the process of being set up
* by another page fault trying to merge _that_. But that's ok: if it
* is being set up, that automatically means that it will be a singleton
* acceptable for merging, so we can do all of this optimistically. But
* we do that READ_ONCE() to make sure that we never re-load the pointer.
*
* IOW: that the "list_is_singular()" test on the anon_vma_chain only
* matters for the 'stable anon_vma' case (ie the thing we want to avoid
* is to return an anon_vma that is "complex" due to having gone through
* a fork).
*
* We also make sure that the two vma's are compatible (adjacent,
* and with the same memory policies). That's all stable, even with just
* a read lock on the mmap_lock.
*/
static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old,
struct vm_area_struct *a,
struct vm_area_struct *b)
{
if (anon_vma_compatible(a, b)) {
struct anon_vma *anon_vma = READ_ONCE(old->anon_vma);
if (anon_vma && list_is_singular(&old->anon_vma_chain))
return anon_vma;
}
return NULL;
}
/*
* find_mergeable_anon_vma is used by anon_vma_prepare, to check
* neighbouring vmas for a suitable anon_vma, before it goes off
* to allocate a new anon_vma. It checks because a repetitive
* sequence of mprotects and faults may otherwise lead to distinct
* anon_vmas being allocated, preventing vma merge in subsequent
* mprotect.
*/
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = NULL;
struct vm_area_struct *prev, *next;
VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end);
/* Try next first. */
next = vma_iter_load(&vmi);
if (next) { anon_vma = reusable_anon_vma(next, vma, next);
if (anon_vma)
return anon_vma;
}
prev = vma_prev(&vmi);
VM_BUG_ON_VMA(prev != vma, vma);
prev = vma_prev(&vmi);
/* Try prev next. */
if (prev) anon_vma = reusable_anon_vma(prev, prev, vma);
/*
* We might reach here with anon_vma == NULL if we can't find
* any reusable anon_vma.
* There's no absolute need to look only at touching neighbours:
* we could search further afield for "compatible" anon_vmas.
* But it would probably just be a waste of time searching,
* or lead to too many vmas hanging off the same anon_vma.
* We're trying to allow mprotect remerging later on,
* not trying to minimize memory used for anon_vmas.
*/
return anon_vma;
}
static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops)
{
return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite);
}
static bool vma_is_shared_writable(struct vm_area_struct *vma)
{
return (vma->vm_flags & (VM_WRITE | VM_SHARED)) ==
(VM_WRITE | VM_SHARED);
}
static bool vma_fs_can_writeback(struct vm_area_struct *vma)
{
/* No managed pages to writeback. */
if (vma->vm_flags & VM_PFNMAP)
return false;
return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping);
}
/*
* Does this VMA require the underlying folios to have their dirty state
* tracked?
*/
bool vma_needs_dirty_tracking(struct vm_area_struct *vma)
{
/* Only shared, writable VMAs require dirty tracking. */
if (!vma_is_shared_writable(vma))
return false;
/* Does the filesystem need to be notified? */
if (vm_ops_needs_writenotify(vma->vm_ops))
return true;
/*
* Even if the filesystem doesn't indicate a need for writenotify, if it
* can writeback, dirty tracking is still required.
*/
return vma_fs_can_writeback(vma);
}
/*
* Some shared mappings will want the pages marked read-only
* to track write events. If so, we'll downgrade vm_page_prot
* to the private version (using protection_map[] without the
* VM_SHARED bit).
*/
bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
{
/* If it was private or non-writable, the write bit is already clear */
if (!vma_is_shared_writable(vma))
return false;
/* The backer wishes to know when pages are first written to? */
if (vm_ops_needs_writenotify(vma->vm_ops))
return true;
/* The open routine did something to the protections that pgprot_modify
* won't preserve? */
if (pgprot_val(vm_page_prot) !=
pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags)))
return false;
/*
* Do we need to track softdirty? hugetlb does not support softdirty
* tracking yet.
*/
if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
return true;
/* Do we need write faults for uffd-wp tracking? */
if (userfaultfd_wp(vma))
return true;
/* Can the mapping track the dirty pages? */
return vma_fs_can_writeback(vma);
}
static DEFINE_MUTEX(mm_all_locks_mutex);
static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
{
if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) {
/*
* The LSB of head.next can't change from under us
* because we hold the mm_all_locks_mutex.
*/
down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock);
/*
* We can safely modify head.next after taking the
* anon_vma->root->rwsem. If some other vma in this mm shares
* the same anon_vma we won't take it again.
*
* No need of atomic instructions here, head.next
* can't change from under us thanks to the
* anon_vma->root->rwsem.
*/
if (__test_and_set_bit(0, (unsigned long *)
&anon_vma->root->rb_root.rb_root.rb_node))
BUG();
}
}
static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
{
if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
/*
* AS_MM_ALL_LOCKS can't change from under us because
* we hold the mm_all_locks_mutex.
*
* Operations on ->flags have to be atomic because
* even if AS_MM_ALL_LOCKS is stable thanks to the
* mm_all_locks_mutex, there may be other cpus
* changing other bitflags in parallel to us.
*/
if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock);
}
}
/*
* This operation locks against the VM for all pte/vma/mm related
* operations that could ever happen on a certain mm. This includes
* vmtruncate, try_to_unmap, and all page faults.
*
* The caller must take the mmap_lock in write mode before calling
* mm_take_all_locks(). The caller isn't allowed to release the
* mmap_lock until mm_drop_all_locks() returns.
*
* mmap_lock in write mode is required in order to block all operations
* that could modify pagetables and free pages without need of
* altering the vma layout. It's also needed in write mode to avoid new
* anon_vmas to be associated with existing vmas.
*
* A single task can't take more than one mm_take_all_locks() in a row
* or it would deadlock.
*
* The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in
* mapping->flags avoid to take the same lock twice, if more than one
* vma in this mm is backed by the same anon_vma or address_space.
*
* We take locks in following order, accordingly to comment at beginning
* of mm/rmap.c:
* - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for
* hugetlb mapping);
* - all vmas marked locked
* - all i_mmap_rwsem locks;
* - all anon_vma->rwseml
*
* We can take all locks within these types randomly because the VM code
* doesn't nest them and we protected from parallel mm_take_all_locks() by
* mm_all_locks_mutex.
*
* mm_take_all_locks() and mm_drop_all_locks are expensive operations
* that may have to take thousand of locks.
*
* mm_take_all_locks() can fail if it's interrupted by signals.
*/
int mm_take_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct anon_vma_chain *avc;
VMA_ITERATOR(vmi, mm, 0);
mmap_assert_write_locked(mm);
mutex_lock(&mm_all_locks_mutex);
/*
* vma_start_write() does not have a complement in mm_drop_all_locks()
* because vma_start_write() is always asymmetrical; it marks a VMA as
* being written to until mmap_write_unlock() or mmap_write_downgrade()
* is reached.
*/
for_each_vma(vmi, vma) { if (signal_pending(current))
goto out_unlock;
vma_start_write(vma);
}
vma_iter_init(&vmi, mm, 0);
for_each_vma(vmi, vma) { if (signal_pending(current))
goto out_unlock;
if (vma->vm_file && vma->vm_file->f_mapping &&
is_vm_hugetlb_page(vma))
vm_lock_mapping(mm, vma->vm_file->f_mapping);
}
vma_iter_init(&vmi, mm, 0);
for_each_vma(vmi, vma) { if (signal_pending(current))
goto out_unlock;
if (vma->vm_file && vma->vm_file->f_mapping &&
!is_vm_hugetlb_page(vma))
vm_lock_mapping(mm, vma->vm_file->f_mapping);
}
vma_iter_init(&vmi, mm, 0);
for_each_vma(vmi, vma) { if (signal_pending(current))
goto out_unlock;
if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma);
}
return 0;
out_unlock:
mm_drop_all_locks(mm);
return -EINTR;
}
static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
{
if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) {
/*
* The LSB of head.next can't change to 0 from under
* us because we hold the mm_all_locks_mutex.
*
* We must however clear the bitflag before unlocking
* the vma so the users using the anon_vma->rb_root will
* never see our bitflag.
*
* No need of atomic instructions here, head.next
* can't change from under us until we release the
* anon_vma->root->rwsem.
*/
if (!__test_and_clear_bit(0, (unsigned long *)
&anon_vma->root->rb_root.rb_root.rb_node))
BUG(); anon_vma_unlock_write(anon_vma);
}
}
static void vm_unlock_mapping(struct address_space *mapping)
{
if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
/*
* AS_MM_ALL_LOCKS can't change to 0 from under us
* because we hold the mm_all_locks_mutex.
*/
i_mmap_unlock_write(mapping);
if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
&mapping->flags))
BUG();
}
}
/*
* The mmap_lock cannot be released by the caller until
* mm_drop_all_locks() returns.
*/
void mm_drop_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
struct anon_vma_chain *avc;
VMA_ITERATOR(vmi, mm, 0);
mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping);
}
mutex_unlock(&mm_all_locks_mutex);
}
/*
* We account for memory if it's a private writeable mapping,
* not hugepages and VM_NORESERVE wasn't set.
*/
static bool accountable_mapping(struct file *file, vm_flags_t vm_flags)
{
/*
* hugetlb has its own accounting separate from the core VM
* VM_HUGETLB may not be set yet so we cannot check for that flag.
*/
if (file && is_file_hugepages(file))
return false;
return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}
/*
* vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap()
* operation.
* @vms: The vma unmap structure
* @mas_detach: The maple state with the detached maple tree
*
* Reattach any detached vmas, free up the maple tree used to track the vmas.
* If that's not possible because the ptes are cleared (and vm_ops->closed() may
* have been called), then a NULL is written over the vmas and the vmas are
* removed (munmap() completed).
*/
static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms,
struct ma_state *mas_detach)
{
struct ma_state *mas = &vms->vmi->mas;
if (!vms->nr_pages)
return;
if (vms->clear_ptes)
return reattach_vmas(mas_detach);
/*
* Aborting cannot just call the vm_ops open() because they are often
* not symmetrical and state data has been lost. Resort to the old
* failure method of leaving a gap where the MAP_FIXED mapping failed.
*/
mas_set_range(mas, vms->start, vms->end - 1);
mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL);
/* Clean up the insertion of the unfortunate gap */
vms_complete_munmap_vmas(vms, mas_detach);
}
/*
* __mmap_prepare() - Prepare to gather any overlapping VMAs that need to be
* unmapped once the map operation is completed, check limits, account mapping
* and clean up any pre-existing VMAs.
*
* @map: Mapping state.
* @uf: Userfaultfd context list.
*
* Returns: 0 on success, error code otherwise.
*/
static int __mmap_prepare(struct mmap_state *map, struct list_head *uf)
{
int error;
struct vma_iterator *vmi = map->vmi;
struct vma_munmap_struct *vms = &map->vms;
/* Find the first overlapping VMA and initialise unmap state. */
vms->vma = vma_find(vmi, map->end);
init_vma_munmap(vms, vmi, vms->vma, map->addr, map->end, uf,
/* unlock = */ false);
/* OK, we have overlapping VMAs - prepare to unmap them. */
if (vms->vma) {
mt_init_flags(&map->mt_detach,
vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK);
mt_on_stack(map->mt_detach);
mas_init(&map->mas_detach, &map->mt_detach, /* addr = */ 0);
/* Prepare to unmap any existing mapping in the area */
error = vms_gather_munmap_vmas(vms, &map->mas_detach);
if (error) {
/* On error VMAs will already have been reattached. */
vms->nr_pages = 0;
return error;
}
map->next = vms->next;
map->prev = vms->prev;
} else {
map->next = vma_iter_next_rewind(vmi, &map->prev);
}
/* Check against address space limit. */
if (!may_expand_vm(map->mm, map->flags, map->pglen - vms->nr_pages))
return -ENOMEM;
/* Private writable mapping: check memory availability. */
if (accountable_mapping(map->file, map->flags)) {
map->charged = map->pglen;
map->charged -= vms->nr_accounted;
if (map->charged) {
error = security_vm_enough_memory_mm(map->mm, map->charged);
if (error)
return error;
}
vms->nr_accounted = 0;
map->flags |= VM_ACCOUNT;
}
/*
* Clear PTEs while the vma is still in the tree so that rmap
* cannot race with the freeing later in the truncate scenario.
* This is also needed for mmap_file(), which is why vm_ops
* close function is called.
*/
vms_clean_up_area(vms, &map->mas_detach);
return 0;
}
static int __mmap_new_file_vma(struct mmap_state *map,
struct vm_area_struct *vma)
{
struct vma_iterator *vmi = map->vmi;
int error;
vma->vm_file = get_file(map->file); error = mmap_file(vma->vm_file, vma);
if (error) {
fput(vma->vm_file);
vma->vm_file = NULL;
vma_iter_set(vmi, vma->vm_end);
/* Undo any partial mapping done by a device driver. */
unmap_region(&vmi->mas, vma, map->prev, map->next);
return error;
}
/* Drivers cannot alter the address of the VMA. */
WARN_ON_ONCE(map->addr != vma->vm_start);
/*
* Drivers should not permit writability when previously it was
* disallowed.
*/
VM_WARN_ON_ONCE(map->flags != vma->vm_flags &&
!(map->flags & VM_MAYWRITE) &&
(vma->vm_flags & VM_MAYWRITE));
/* If the flags change (and are mergeable), let's retry later. */
map->retry_merge = vma->vm_flags != map->flags && !(vma->vm_flags & VM_SPECIAL);
map->flags = vma->vm_flags;
return 0;
}
/*
* __mmap_new_vma() - Allocate a new VMA for the region, as merging was not
* possible.
*
* @map: Mapping state.
* @vmap: Output pointer for the new VMA.
*
* Returns: Zero on success, or an error.
*/
static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
{
struct vma_iterator *vmi = map->vmi;
int error = 0;
struct vm_area_struct *vma;
/*
* Determine the object being mapped and call the appropriate
* specific mapper. the address has already been validated, but
* not unmapped, but the maps are removed from the list.
*/
vma = vm_area_alloc(map->mm);
if (!vma)
return -ENOMEM;
vma_iter_config(vmi, map->addr, map->end);
vma_set_range(vma, map->addr, map->end, map->pgoff);
vm_flags_init(vma, map->flags);
vma->vm_page_prot = vm_get_page_prot(map->flags);
if (vma_iter_prealloc(vmi, vma)) {
error = -ENOMEM;
goto free_vma;
}
if (map->file)
error = __mmap_new_file_vma(map, vma);
else if (map->flags & VM_SHARED)
error = shmem_zero_setup(vma);
else
vma_set_anonymous(vma); if (error)
goto free_iter_vma;
#ifdef CONFIG_SPARC64
/* TODO: Fix SPARC ADI! */
WARN_ON_ONCE(!arch_validate_flags(map->flags));
#endif
/* Lock the VMA since it is modified after insertion into VMA tree */
vma_start_write(vma); vma_iter_store_new(vmi, vma);
map->mm->map_count++;
vma_link_file(vma);
/*
* vma_merge_new_range() calls khugepaged_enter_vma() too, the below
* call covers the non-merge case.
*/
if (!vma_is_anonymous(vma)) khugepaged_enter_vma(vma, map->flags);
ksm_add_vma(vma);
*vmap = vma;
return 0;
free_iter_vma:
vma_iter_free(vmi);
free_vma:
vm_area_free(vma);
return error;
}
/*
* __mmap_complete() - Unmap any VMAs we overlap, account memory mapping
* statistics, handle locking and finalise the VMA.
*
* @map: Mapping state.
* @vma: Merged or newly allocated VMA for the mmap()'d region.
*/
static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
{
struct mm_struct *mm = map->mm;
unsigned long vm_flags = vma->vm_flags;
perf_event_mmap(vma);
/* Unmap any existing mapping in the area. */
vms_complete_munmap_vmas(&map->vms, &map->mas_detach);
vm_stat_account(mm, vma->vm_flags, map->pglen);
if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(mm))
vm_flags_clear(vma, VM_LOCKED_MASK);
else
mm->locked_vm += map->pglen;
}
if (vma->vm_file)
uprobe_mmap(vma);
/*
* New (or expanded) vma always get soft dirty status.
* Otherwise user-space soft-dirty page tracker won't
* be able to distinguish situation when vma area unmapped,
* then new mapped in-place (which must be aimed as
* a completely new data area).
*/
vm_flags_set(vma, VM_SOFTDIRTY);
vma_set_page_prot(vma);
}
static unsigned long __mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
struct list_head *uf)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = NULL;
int error;
VMA_ITERATOR(vmi, mm, addr);
MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file);
error = __mmap_prepare(&map, uf);
if (error)
goto abort_munmap;
/* Attempt to merge with adjacent VMAs... */
if (map.prev || map.next) {
VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL);
vma = vma_merge_new_range(&vmg);
}
/* ...but if we can't, allocate a new VMA. */
if (!vma) { error = __mmap_new_vma(&map, &vma);
if (error)
goto unacct_error;
}
/* If flags changed, we might be able to merge, so try again. */
if (map.retry_merge) {
struct vm_area_struct *merged;
VMG_MMAP_STATE(vmg, &map, vma);
vma_iter_config(map.vmi, map.addr, map.end);
merged = vma_merge_existing_range(&vmg);
if (merged)
vma = merged;
}
__mmap_complete(&map, vma);
return addr;
/* Accounting was done by __mmap_prepare(). */
unacct_error:
if (map.charged) vm_unacct_memory(map.charged);
abort_munmap:
vms_abort_munmap_vmas(&map.vms, &map.mas_detach);
return error;
}
/**
* mmap_region() - Actually perform the userland mapping of a VMA into
* current->mm with known, aligned and overflow-checked @addr and @len, and
* correctly determined VMA flags @vm_flags and page offset @pgoff.
*
* This is an internal memory management function, and should not be used
* directly.
*
* The caller must write-lock current->mm->mmap_lock.
*
* @file: If a file-backed mapping, a pointer to the struct file describing the
* file to be mapped, otherwise NULL.
* @addr: The page-aligned address at which to perform the mapping.
* @len: The page-aligned, non-zero, length of the mapping.
* @vm_flags: The VMA flags which should be applied to the mapping.
* @pgoff: If @file is specified, the page offset into the file, if not then
* the virtual page offset in memory of the anonymous mapping.
* @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap
* events.
*
* Returns: Either an error, or the address at which the requested mapping has
* been performed.
*/
unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
struct list_head *uf)
{
unsigned long ret;
bool writable_file_mapping = false;
mmap_assert_write_locked(current->mm);
/* Check to see if MDWE is applicable. */
if (map_deny_write_exec(vm_flags, vm_flags))
return -EACCES;
/* Allow architectures to sanity-check the vm_flags. */
if (!arch_validate_flags(vm_flags))
return -EINVAL;
/* Map writable and ensure this isn't a sealed memfd. */
if (file && is_shared_maywrite(vm_flags)) { int error = mapping_map_writable(file->f_mapping);
if (error)
return error;
writable_file_mapping = true;
}
ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf);
/* Clear our write mapping regardless of error. */
if (writable_file_mapping) mapping_unmap_writable(file->f_mapping);
validate_mm(current->mm);
return ret;
}
/*
* do_brk_flags() - Increase the brk vma if the flags match.
* @vmi: The vma iterator
* @addr: The start address
* @len: The length of the increase
* @vma: The vma,
* @flags: The VMA Flags
*
* Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags
* do not match then create a new anonymous VMA. Eventually we may be able to
* do some brk-specific accounting here.
*/
int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long addr, unsigned long len, unsigned long flags)
{
struct mm_struct *mm = current->mm;
/*
* Check against address space limits by the changed size
* Note: This happens *after* clearing old mappings in some code paths.
*/
flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
return -ENOMEM;
if (mm->map_count > sysctl_max_map_count)
return -ENOMEM;
if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
/*
* Expand the existing vma if possible; Note that singular lists do not
* occur after forking, so the expand will only happen on new VMAs.
*/
if (vma && vma->vm_end == addr) {
VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
vmg.prev = vma;
/* vmi is positioned at prev, which this mode expects. */
vmg.just_expand = true;
if (vma_merge_new_range(&vmg))
goto out;
else if (vmg_nomem(&vmg))
goto unacct_fail;
}
if (vma)
vma_iter_next_range(vmi);
/* create a vma struct for an anonymous mapping */
vma = vm_area_alloc(mm);
if (!vma)
goto unacct_fail;
vma_set_anonymous(vma);
vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT);
vm_flags_init(vma, flags);
vma->vm_page_prot = vm_get_page_prot(flags);
vma_start_write(vma);
if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL))
goto mas_store_fail;
mm->map_count++;
validate_mm(mm);
ksm_add_vma(vma);
out:
perf_event_mmap(vma);
mm->total_vm += len >> PAGE_SHIFT;
mm->data_vm += len >> PAGE_SHIFT;
if (flags & VM_LOCKED)
mm->locked_vm += (len >> PAGE_SHIFT);
vm_flags_set(vma, VM_SOFTDIRTY);
return 0;
mas_store_fail:
vm_area_free(vma);
unacct_fail:
vm_unacct_memory(len >> PAGE_SHIFT);
return -ENOMEM;
}
/**
* unmapped_area() - Find an area between the low_limit and the high_limit with
* the correct alignment and offset, all from @info. Note: current->mm is used
* for the search.
*
* @info: The unmapped area information including the range [low_limit -
* high_limit), the alignment offset and mask.
*
* Return: A memory address or -ENOMEM.
*/
unsigned long unmapped_area(struct vm_unmapped_area_info *info)
{
unsigned long length, gap;
unsigned long low_limit, high_limit;
struct vm_area_struct *tmp;
VMA_ITERATOR(vmi, current->mm, 0);
/* Adjust search length to account for worst case alignment overhead */
length = info->length + info->align_mask + info->start_gap;
if (length < info->length)
return -ENOMEM;
low_limit = info->low_limit;
if (low_limit < mmap_min_addr)
low_limit = mmap_min_addr;
high_limit = info->high_limit;
retry:
if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length))
return -ENOMEM;
/*
* Adjust for the gap first so it doesn't interfere with the
* later alignment. The first step is the minimum needed to
* fulill the start gap, the next steps is the minimum to align
* that. It is the minimum needed to fulill both.
*/
gap = vma_iter_addr(&vmi) + info->start_gap;
gap += (info->align_offset - gap) & info->align_mask;
tmp = vma_next(&vmi);
if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
if (vm_start_gap(tmp) < gap + length - 1) {
low_limit = tmp->vm_end;
vma_iter_reset(&vmi);
goto retry;
}
} else {
tmp = vma_prev(&vmi);
if (tmp && vm_end_gap(tmp) > gap) {
low_limit = vm_end_gap(tmp);
vma_iter_reset(&vmi);
goto retry;
}
}
return gap;
}
/**
* unmapped_area_topdown() - Find an area between the low_limit and the
* high_limit with the correct alignment and offset at the highest available
* address, all from @info. Note: current->mm is used for the search.
*
* @info: The unmapped area information including the range [low_limit -
* high_limit), the alignment offset and mask.
*
* Return: A memory address or -ENOMEM.
*/
unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
{
unsigned long length, gap, gap_end;
unsigned long low_limit, high_limit;
struct vm_area_struct *tmp;
VMA_ITERATOR(vmi, current->mm, 0);
/* Adjust search length to account for worst case alignment overhead */
length = info->length + info->align_mask + info->start_gap;
if (length < info->length)
return -ENOMEM;
low_limit = info->low_limit;
if (low_limit < mmap_min_addr)
low_limit = mmap_min_addr;
high_limit = info->high_limit;
retry:
if (vma_iter_area_highest(&vmi, low_limit, high_limit, length))
return -ENOMEM;
gap = vma_iter_end(&vmi) - info->length;
gap -= (gap - info->align_offset) & info->align_mask;
gap_end = vma_iter_end(&vmi);
tmp = vma_next(&vmi);
if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
if (vm_start_gap(tmp) < gap_end) {
high_limit = vm_start_gap(tmp);
vma_iter_reset(&vmi);
goto retry;
}
} else {
tmp = vma_prev(&vmi);
if (tmp && vm_end_gap(tmp) > gap) {
high_limit = tmp->vm_start;
vma_iter_reset(&vmi);
goto retry;
}
}
return gap;
}
/*
* Verify that the stack growth is acceptable and
* update accounting. This is shared with both the
* grow-up and grow-down cases.
*/
static int acct_stack_growth(struct vm_area_struct *vma,
unsigned long size, unsigned long grow)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long new_start;
/* address space limit tests */
if (!may_expand_vm(mm, vma->vm_flags, grow))
return -ENOMEM;
/* Stack limit test */
if (size > rlimit(RLIMIT_STACK))
return -ENOMEM;
/* mlock limit tests */
if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT))
return -ENOMEM;
/* Check to ensure the stack will not grow into a hugetlb-only region */
new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
vma->vm_end - size;
if (is_hugepage_only_range(vma->vm_mm, new_start, size))
return -EFAULT;
/*
* Overcommit.. This must be the final test, as it will
* update security statistics.
*/
if (security_vm_enough_memory_mm(mm, grow))
return -ENOMEM;
return 0;
}
#if defined(CONFIG_STACK_GROWSUP)
/*
* PA-RISC uses this for its stack.
* vma is the last one with address > vma->vm_end. Have to extend vma.
*/
int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *next;
unsigned long gap_addr;
int error = 0;
VMA_ITERATOR(vmi, mm, vma->vm_start);
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
mmap_assert_write_locked(mm);
/* Guard against exceeding limits of the address space. */
address &= PAGE_MASK;
if (address >= (TASK_SIZE & PAGE_MASK))
return -ENOMEM;
address += PAGE_SIZE;
/* Enforce stack_guard_gap */
gap_addr = address + stack_guard_gap;
/* Guard against overflow */
if (gap_addr < address || gap_addr > TASK_SIZE)
gap_addr = TASK_SIZE;
next = find_vma_intersection(mm, vma->vm_end, gap_addr);
if (next && vma_is_accessible(next)) {
if (!(next->vm_flags & VM_GROWSUP))
return -ENOMEM;
/* Check that both stack segments have the same anon_vma? */
}
if (next)
vma_iter_prev_range_limit(&vmi, address);
vma_iter_config(&vmi, vma->vm_start, address);
if (vma_iter_prealloc(&vmi, vma))
return -ENOMEM;
/* We must make sure the anon_vma is allocated. */
if (unlikely(anon_vma_prepare(vma))) {
vma_iter_free(&vmi);
return -ENOMEM;
}
/* Lock the VMA before expanding to prevent concurrent page faults */
vma_start_write(vma);
/* We update the anon VMA tree. */
anon_vma_lock_write(vma->anon_vma);
/* Somebody else might have raced and expanded it already */
if (address > vma->vm_end) {
unsigned long size, grow;
size = address - vma->vm_start;
grow = (address - vma->vm_end) >> PAGE_SHIFT;
error = -ENOMEM;
if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
error = acct_stack_growth(vma, size, grow);
if (!error) {
if (vma->vm_flags & VM_LOCKED)
mm->locked_vm += grow;
vm_stat_account(mm, vma->vm_flags, grow);
anon_vma_interval_tree_pre_update_vma(vma);
vma->vm_end = address;
/* Overwrite old entry in mtree. */
vma_iter_store_overwrite(&vmi, vma);
anon_vma_interval_tree_post_update_vma(vma);
perf_event_mmap(vma);
}
}
}
anon_vma_unlock_write(vma->anon_vma);
vma_iter_free(&vmi);
validate_mm(mm);
return error;
}
#endif /* CONFIG_STACK_GROWSUP */
/*
* vma is the first one with address < vma->vm_start. Have to extend vma.
* mmap_lock held for writing.
*/
int expand_downwards(struct vm_area_struct *vma, unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *prev;
int error = 0;
VMA_ITERATOR(vmi, mm, vma->vm_start);
if (!(vma->vm_flags & VM_GROWSDOWN))
return -EFAULT;
mmap_assert_write_locked(mm);
address &= PAGE_MASK;
if (address < mmap_min_addr || address < FIRST_USER_ADDRESS)
return -EPERM;
/* Enforce stack_guard_gap */
prev = vma_prev(&vmi);
/* Check that both stack segments have the same anon_vma? */
if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev) &&
(address - prev->vm_end < stack_guard_gap))
return -ENOMEM;
}
if (prev)
vma_iter_next_range_limit(&vmi, vma->vm_start);
vma_iter_config(&vmi, address, vma->vm_end);
if (vma_iter_prealloc(&vmi, vma))
return -ENOMEM;
/* We must make sure the anon_vma is allocated. */
if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi);
return -ENOMEM;
}
/* Lock the VMA before expanding to prevent concurrent page faults */
vma_start_write(vma);
/* We update the anon VMA tree. */
anon_vma_lock_write(vma->anon_vma);
/* Somebody else might have raced and expanded it already */
if (address < vma->vm_start) {
unsigned long size, grow;
size = vma->vm_end - address;
grow = (vma->vm_start - address) >> PAGE_SHIFT;
error = -ENOMEM;
if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow);
if (!error) {
if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow;
vm_stat_account(mm, vma->vm_flags, grow);
anon_vma_interval_tree_pre_update_vma(vma);
vma->vm_start = address;
vma->vm_pgoff -= grow;
/* Overwrite old entry in mtree. */
vma_iter_store_overwrite(&vmi, vma);
anon_vma_interval_tree_post_update_vma(vma);
perf_event_mmap(vma);
}
}
}
anon_vma_unlock_write(vma->anon_vma);
vma_iter_free(&vmi);
validate_mm(mm);
return error;
}
int __vm_munmap(unsigned long start, size_t len, bool unlock)
{
int ret;
struct mm_struct *mm = current->mm;
LIST_HEAD(uf);
VMA_ITERATOR(vmi, mm, start);
if (mmap_write_lock_killable(mm))
return -EINTR;
ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock);
if (ret || !unlock) mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
return ret;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/swap.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* This file contains the default values for the operation of the
* Linux VM subsystem. Fine-tuning documentation can be found in
* Documentation/admin-guide/sysctl/vm.rst.
* Started 18.12.91
* Swap aging added 23.2.95, Stephen Tweedie.
* Buffermem limits added 12.3.98, Rik van Riel.
*/
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/mm_inline.h>
#include <linux/percpu_counter.h>
#include <linux/memremap.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>
#include <linux/hugetlb.h>
#include <linux/page_idle.h>
#include <linux/local_lock.h>
#include <linux/buffer_head.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/pagemap.h>
/* How many pages do we try to swap or page in/out together? As a power of 2 */
int page_cluster;
static const int page_cluster_max = 31;
struct cpu_fbatches {
/*
* The following folio batches are grouped together because they are protected
* by disabling preemption (and interrupts remain enabled).
*/
local_lock_t lock;
struct folio_batch lru_add;
struct folio_batch lru_deactivate_file;
struct folio_batch lru_deactivate;
struct folio_batch lru_lazyfree;
#ifdef CONFIG_SMP
struct folio_batch lru_activate;
#endif
/* Protecting the following batches which require disabling interrupts */
local_lock_t lock_irq;
struct folio_batch lru_move_tail;
};
static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = {
.lock = INIT_LOCAL_LOCK(lock),
.lock_irq = INIT_LOCAL_LOCK(lock_irq),
};
static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
unsigned long *flagsp)
{ if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio);
}
}
/*
* This path almost never happens for VM activity - pages are normally freed
* in batches. But it gets used by networking - and for compound pages.
*/
static void page_cache_release(struct folio *folio)
{
struct lruvec *lruvec = NULL;
unsigned long flags;
__page_cache_release(folio, &lruvec, &flags);
if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags);
}
void __folio_put(struct folio *folio)
{
if (unlikely(folio_is_zone_device(folio))) {
free_zone_device_folio(folio);
return;
}
if (folio_test_hugetlb(folio)) {
free_huge_folio(folio);
return;
}
page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio));
}
EXPORT_SYMBOL(__folio_put);
typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio);
static void lru_add(struct lruvec *lruvec, struct folio *folio)
{ int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/*
* Is an smp_mb__after_atomic() still required here, before
* folio_evictable() tests the mlocked flag, to rule out the possibility
* of stranding an evictable folio on an unevictable LRU? I think
* not, because __munlock_folio() only clears the mlocked flag
* while the LRU lock is held.
*
* (That is not true of __page_cache_release(), and not necessarily
* true of folios_put(): but those only clear the mlocked flag after
* folio_put_testzero() has excluded any other users of the folio.)
*/
if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
} else {
folio_clear_active(folio); folio_set_unevictable(folio);
/*
* folio->mlock_count = !!folio_test_mlocked(folio)?
* But that leaves __mlock_folio() in doubt whether another
* actor has already counted the mlock or not. Err on the
* safe side, underestimate, let page reclaim fix it, rather
* than leaving a page on the unevictable LRU indefinitely.
*/
folio->mlock_count = 0;
if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
}
lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio);
}
static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
{
int i;
struct lruvec *lruvec = NULL;
unsigned long flags = 0;
for (i = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
folio_lruvec_relock_irqsave(folio, &lruvec, &flags);
move_fn(lruvec, folio);
folio_set_lru(folio);
}
if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags);
folios_put(fbatch);
}
static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
struct folio *folio, move_fn_t move_fn,
bool on_lru, bool disable_irq)
{
unsigned long flags;
if (on_lru && !folio_test_clear_lru(folio))
return;
folio_get(folio);
if (disable_irq)
local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
else
local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) ||
lru_cache_disabled())
folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
if (disable_irq)
local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
else
local_unlock(&cpu_fbatches.lock);
}
#define folio_batch_add_and_move(folio, op, on_lru) \
__folio_batch_add_and_move( \
&cpu_fbatches.op, \
folio, \
op, \
on_lru, \
offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \
)
static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
{
if (folio_test_unevictable(folio))
return;
lruvec_del_folio(lruvec, folio);
folio_clear_active(folio);
lruvec_add_folio_tail(lruvec, folio);
__count_vm_events(PGROTATED, folio_nr_pages(folio));
}
/*
* Writeback is about to end against a folio which has been marked for
* immediate reclaim. If it still appears to be reclaimable, move it
* to the tail of the inactive list.
*
* folio_rotate_reclaimable() must disable IRQs, to prevent nasty races.
*/
void folio_rotate_reclaimable(struct folio *folio)
{
if (folio_test_locked(folio) || folio_test_dirty(folio) ||
folio_test_unevictable(folio))
return;
folio_batch_add_and_move(folio, lru_move_tail, true);
}
void lru_note_cost(struct lruvec *lruvec, bool file,
unsigned int nr_io, unsigned int nr_rotated)
{
unsigned long cost;
/*
* Reflect the relative cost of incurring IO and spending CPU
* time on rotations. This doesn't attempt to make a precise
* comparison, it just says: if reloads are about comparable
* between the LRU lists, or rotations are overwhelmingly
* different between them, adjust scan balance for CPU work.
*/
cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated;
do {
unsigned long lrusize;
/*
* Hold lruvec->lru_lock is safe here, since
* 1) The pinned lruvec in reclaim, or
* 2) From a pre-LRU page during refault (which also holds the
* rcu lock, so would be safe even if the page was on the LRU
* and could move simultaneously to a new lruvec).
*/
spin_lock_irq(&lruvec->lru_lock);
/* Record cost event */
if (file)
lruvec->file_cost += cost;
else
lruvec->anon_cost += cost;
/*
* Decay previous events
*
* Because workloads change over time (and to avoid
* overflow) we keep these statistics as a floating
* average, which ends up weighing recent refaults
* more than old ones.
*/
lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) +
lruvec_page_state(lruvec, NR_ACTIVE_ANON) +
lruvec_page_state(lruvec, NR_INACTIVE_FILE) +
lruvec_page_state(lruvec, NR_ACTIVE_FILE);
if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) {
lruvec->file_cost /= 2;
lruvec->anon_cost /= 2;
}
spin_unlock_irq(&lruvec->lru_lock);
} while ((lruvec = parent_lruvec(lruvec)));
}
void lru_note_cost_refault(struct folio *folio)
{
lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
folio_nr_pages(folio), 0);
}
static void lru_activate(struct lruvec *lruvec, struct folio *folio)
{
long nr_pages = folio_nr_pages(folio);
if (folio_test_active(folio) || folio_test_unevictable(folio))
return;
lruvec_del_folio(lruvec, folio);
folio_set_active(folio);
lruvec_add_folio(lruvec, folio);
trace_mm_lru_activate(folio);
__count_vm_events(PGACTIVATE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages);
}
#ifdef CONFIG_SMP
static void folio_activate_drain(int cpu)
{
struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu);
if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate);
}
void folio_activate(struct folio *folio)
{
if (folio_test_active(folio) || folio_test_unevictable(folio))
return;
folio_batch_add_and_move(folio, lru_activate, true);
}
#else
static inline void folio_activate_drain(int cpu)
{
}
void folio_activate(struct folio *folio)
{
struct lruvec *lruvec;
if (!folio_test_clear_lru(folio))
return;
lruvec = folio_lruvec_lock_irq(folio);
lru_activate(lruvec, folio);
unlock_page_lruvec_irq(lruvec);
folio_set_lru(folio);
}
#endif
static void __lru_cache_activate_folio(struct folio *folio)
{
struct folio_batch *fbatch;
int i;
local_lock(&cpu_fbatches.lock);
fbatch = this_cpu_ptr(&cpu_fbatches.lru_add);
/*
* Search backwards on the optimistic assumption that the folio being
* activated has just been added to this batch. Note that only
* the local batch is examined as a !LRU folio could be in the
* process of being released, reclaimed, migrated or on a remote
* batch that is currently being drained. Furthermore, marking
* a remote batch's folio active potentially hits a race where
* a folio is marked active just after it is added to the inactive
* list causing accounting errors and BUG_ON checks to trigger.
*/
for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) {
struct folio *batch_folio = fbatch->folios[i];
if (batch_folio == folio) {
folio_set_active(folio);
break;
}
}
local_unlock(&cpu_fbatches.lock);
}
#ifdef CONFIG_LRU_GEN
static void lru_gen_inc_refs(struct folio *folio)
{
unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
if (folio_test_unevictable(folio))
return;
/* see the comment on LRU_REFS_FLAGS */
if (!folio_test_referenced(folio)) {
set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
return;
}
do {
if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio);
return;
}
new_flags = old_flags + BIT(LRU_REFS_PGOFF);
} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
}
static bool lru_gen_clear_refs(struct folio *folio)
{
struct lru_gen_folio *lrugen;
int gen = folio_lru_gen(folio);
int type = folio_is_file_lru(folio);
if (gen < 0)
return true;
set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0);
lrugen = &folio_lruvec(folio)->lrugen;
/* whether can do without shuffling under the LRU lock */
return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type]));
}
#else /* !CONFIG_LRU_GEN */
static void lru_gen_inc_refs(struct folio *folio)
{
}
static bool lru_gen_clear_refs(struct folio *folio)
{
return false;
}
#endif /* CONFIG_LRU_GEN */
/**
* folio_mark_accessed - Mark a folio as having seen activity.
* @folio: The folio to mark.
*
* This function will perform one of the following transitions:
*
* * inactive,unreferenced -> inactive,referenced
* * inactive,referenced -> active,unreferenced
* * active,unreferenced -> active,referenced
*
* When a newly allocated folio is not yet visible, so safe for non-atomic ops,
* __folio_set_referenced() may be substituted for folio_mark_accessed().
*/
void folio_mark_accessed(struct folio *folio)
{ if (folio_test_dropbehind(folio))
return;
if (lru_gen_enabled()) {
lru_gen_inc_refs(folio);
return;
}
if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) {
/*
* Unevictable pages are on the "LRU_UNEVICTABLE" list. But,
* this list is never rotated or maintained, so marking an
* unevictable page accessed has no effect.
*/
} else if (!folio_test_active(folio)) {
/*
* If the folio is on the LRU, queue it for activation via
* cpu_fbatches.lru_activate. Otherwise, assume the folio is in a
* folio_batch, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
if (folio_test_lru(folio))
folio_activate(folio);
else
__lru_cache_activate_folio(folio); folio_clear_referenced(folio);
workingset_activation(folio);
}
if (folio_test_idle(folio)) folio_clear_idle(folio);
}
EXPORT_SYMBOL(folio_mark_accessed);
/**
* folio_add_lru - Add a folio to an LRU list.
* @folio: The folio to be added to the LRU.
*
* Queue the folio for addition to the LRU. The decision on whether
* to add the page to the [in]active [file|anon] list is deferred until the
* folio_batch is drained. This gives a chance for the caller of folio_add_lru()
* have the folio added to the active list using folio_mark_accessed().
*/
void folio_add_lru(struct folio *folio)
{ VM_BUG_ON_FOLIO(folio_test_active(folio) &&
folio_test_unevictable(folio), folio);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/* see the comment in lru_gen_folio_seq() */
if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio);
folio_batch_add_and_move(folio, lru_add, false);
}
EXPORT_SYMBOL(folio_add_lru);
/**
* folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA.
* @folio: The folio to be added to the LRU.
* @vma: VMA in which the folio is mapped.
*
* If the VMA is mlocked, @folio is added to the unevictable list.
* Otherwise, it is treated the same way as folio_add_lru().
*/
void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma)
{ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED))
mlock_new_folio(folio);
else
folio_add_lru(folio);
}
/*
* If the folio cannot be invalidated, it is moved to the
* inactive list to speed up its reclaim. It is moved to the
* head of the list, rather than the tail, to give the flusher
* threads some time to write it out, as this is much more
* effective than the single-page writeout from reclaim.
*
* If the folio isn't mapped and dirty/writeback, the folio
* could be reclaimed asap using the reclaim flag.
*
* 1. active, mapped folio -> none
* 2. active, dirty/writeback folio -> inactive, head, reclaim
* 3. inactive, mapped folio -> none
* 4. inactive, dirty/writeback folio -> inactive, head, reclaim
* 5. inactive, clean -> inactive, tail
* 6. Others -> none
*
* In 4, it moves to the head of the inactive list so the folio is
* written out by flusher threads as this is much more efficient
* than the single-page writeout from reclaim.
*/
static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio)
{
bool active = folio_test_active(folio) || lru_gen_enabled();
long nr_pages = folio_nr_pages(folio);
if (folio_test_unevictable(folio))
return;
/* Some processes are using the folio */
if (folio_mapped(folio))
return;
lruvec_del_folio(lruvec, folio);
folio_clear_active(folio);
folio_clear_referenced(folio);
if (folio_test_writeback(folio) || folio_test_dirty(folio)) {
/*
* Setting the reclaim flag could race with
* folio_end_writeback() and confuse readahead. But the
* race window is _really_ small and it's not a critical
* problem.
*/
lruvec_add_folio(lruvec, folio);
folio_set_reclaim(folio);
} else {
/*
* The folio's writeback ended while it was in the batch.
* We move that folio to the tail of the inactive list.
*/
lruvec_add_folio_tail(lruvec, folio);
__count_vm_events(PGROTATED, nr_pages);
}
if (active) {
__count_vm_events(PGDEACTIVATE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
nr_pages);
}
}
static void lru_deactivate(struct lruvec *lruvec, struct folio *folio)
{
long nr_pages = folio_nr_pages(folio);
if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled()))
return;
lruvec_del_folio(lruvec, folio);
folio_clear_active(folio);
folio_clear_referenced(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(PGDEACTIVATE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages);
}
static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
{
long nr_pages = folio_nr_pages(folio);
if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
folio_test_swapcache(folio) || folio_test_unevictable(folio))
return;
lruvec_del_folio(lruvec, folio);
folio_clear_active(folio);
if (lru_gen_enabled())
lru_gen_clear_refs(folio);
else
folio_clear_referenced(folio);
/*
* Lazyfree folios are clean anonymous folios. They have
* the swapbacked flag cleared, to distinguish them from normal
* anonymous folios
*/
folio_clear_swapbacked(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(PGLAZYFREE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
}
/*
* Drain pages out of the cpu's folio_batch.
* Either "cpu" is the current CPU, and preemption has already been
* disabled; or "cpu" is being hot-unplugged, and is already dead.
*/
void lru_add_drain_cpu(int cpu)
{
struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
struct folio_batch *fbatch = &fbatches->lru_add;
if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add);
fbatch = &fbatches->lru_move_tail;
/* Disabling interrupts below acts as a compiler barrier. */
if (data_race(folio_batch_count(fbatch))) {
unsigned long flags;
/* No harm done if a racing interrupt already did this */
local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
folio_batch_move_lru(fbatch, lru_move_tail);
local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
}
fbatch = &fbatches->lru_deactivate_file;
if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file);
fbatch = &fbatches->lru_deactivate;
if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate);
fbatch = &fbatches->lru_lazyfree;
if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu);
}
/**
* deactivate_file_folio() - Deactivate a file folio.
* @folio: Folio to deactivate.
*
* This function hints to the VM that @folio is a good reclaim candidate,
* for example if its invalidation fails due to the folio being dirty
* or under writeback.
*
* Context: Caller holds a reference on the folio.
*/
void deactivate_file_folio(struct folio *folio)
{
/* Deactivating an unevictable folio will not accelerate reclaim */
if (folio_test_unevictable(folio))
return;
if (lru_gen_enabled() && lru_gen_clear_refs(folio))
return;
folio_batch_add_and_move(folio, lru_deactivate_file, true);
}
/*
* folio_deactivate - deactivate a folio
* @folio: folio to deactivate
*
* folio_deactivate() moves @folio to the inactive list if @folio was on the
* active list and was not unevictable. This is done to accelerate the
* reclaim of @folio.
*/
void folio_deactivate(struct folio *folio)
{
if (folio_test_unevictable(folio))
return;
if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
return;
folio_batch_add_and_move(folio, lru_deactivate, true);
}
/**
* folio_mark_lazyfree - make an anon folio lazyfree
* @folio: folio to deactivate
*
* folio_mark_lazyfree() moves @folio to the inactive file list.
* This is done to accelerate the reclaim of @folio.
*/
void folio_mark_lazyfree(struct folio *folio)
{
if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
folio_test_swapcache(folio) || folio_test_unevictable(folio))
return;
folio_batch_add_and_move(folio, lru_lazyfree, true);
}
void lru_add_drain(void)
{
local_lock(&cpu_fbatches.lock);
lru_add_drain_cpu(smp_processor_id());
local_unlock(&cpu_fbatches.lock);
mlock_drain_local();
}
/*
* It's called from per-cpu workqueue context in SMP case so
* lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on
* the same cpu. It shouldn't be a problem in !SMP case since
* the core is only one and the locks will disable preemption.
*/
static void lru_add_and_bh_lrus_drain(void)
{
local_lock(&cpu_fbatches.lock);
lru_add_drain_cpu(smp_processor_id());
local_unlock(&cpu_fbatches.lock);
invalidate_bh_lrus_cpu();
mlock_drain_local();
}
void lru_add_drain_cpu_zone(struct zone *zone)
{
local_lock(&cpu_fbatches.lock);
lru_add_drain_cpu(smp_processor_id());
drain_local_pages(zone);
local_unlock(&cpu_fbatches.lock);
mlock_drain_local();
}
#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
lru_add_and_bh_lrus_drain();
}
static bool cpu_needs_drain(unsigned int cpu)
{
struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
/* Check these in order of likelihood that they're not zero */
return folio_batch_count(&fbatches->lru_add) ||
folio_batch_count(&fbatches->lru_move_tail) ||
folio_batch_count(&fbatches->lru_deactivate_file) ||
folio_batch_count(&fbatches->lru_deactivate) ||
folio_batch_count(&fbatches->lru_lazyfree) ||
folio_batch_count(&fbatches->lru_activate) ||
need_mlock_drain(cpu) ||
has_bh_in_lru(cpu, NULL);
}
/*
* Doesn't need any cpu hotplug locking because we do rely on per-cpu
* kworkers being shut down before our page_alloc_cpu_dead callback is
* executed on the offlined cpu.
* Calling this function with cpu hotplug locks held can actually lead
* to obscure indirect dependencies via WQ context.
*/
static inline void __lru_add_drain_all(bool force_all_cpus)
{
/*
* lru_drain_gen - Global pages generation number
*
* (A) Definition: global lru_drain_gen = x implies that all generations
* 0 < n <= x are already *scheduled* for draining.
*
* This is an optimization for the highly-contended use case where a
* user space workload keeps constantly generating a flow of pages for
* each CPU.
*/
static unsigned int lru_drain_gen;
static struct cpumask has_work;
static DEFINE_MUTEX(lock);
unsigned cpu, this_gen;
/*
* Make sure nobody triggers this path before mm_percpu_wq is fully
* initialized.
*/
if (WARN_ON(!mm_percpu_wq))
return;
/*
* Guarantee folio_batch counter stores visible by this CPU
* are visible to other CPUs before loading the current drain
* generation.
*/
smp_mb();
/*
* (B) Locally cache global LRU draining generation number
*
* The read barrier ensures that the counter is loaded before the mutex
* is taken. It pairs with smp_mb() inside the mutex critical section
* at (D).
*/
this_gen = smp_load_acquire(&lru_drain_gen);
mutex_lock(&lock);
/*
* (C) Exit the draining operation if a newer generation, from another
* lru_add_drain_all(), was already scheduled for draining. Check (A).
*/
if (unlikely(this_gen != lru_drain_gen && !force_all_cpus))
goto done;
/*
* (D) Increment global generation number
*
* Pairs with smp_load_acquire() at (B), outside of the critical
* section. Use a full memory barrier to guarantee that the
* new global drain generation number is stored before loading
* folio_batch counters.
*
* This pairing must be done here, before the for_each_online_cpu loop
* below which drains the page vectors.
*
* Let x, y, and z represent some system CPU numbers, where x < y < z.
* Assume CPU #z is in the middle of the for_each_online_cpu loop
* below and has already reached CPU #y's per-cpu data. CPU #x comes
* along, adds some pages to its per-cpu vectors, then calls
* lru_add_drain_all().
*
* If the paired barrier is done at any later step, e.g. after the
* loop, CPU #x will just exit at (C) and miss flushing out all of its
* added pages.
*/
WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1);
smp_mb();
cpumask_clear(&has_work);
for_each_online_cpu(cpu) {
struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
if (cpu_needs_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
queue_work_on(cpu, mm_percpu_wq, work);
__cpumask_set_cpu(cpu, &has_work);
}
}
for_each_cpu(cpu, &has_work)
flush_work(&per_cpu(lru_add_drain_work, cpu));
done:
mutex_unlock(&lock);
}
void lru_add_drain_all(void)
{
__lru_add_drain_all(false);
}
#else
void lru_add_drain_all(void)
{
lru_add_drain();
}
#endif /* CONFIG_SMP */
atomic_t lru_disable_count = ATOMIC_INIT(0);
/*
* lru_cache_disable() needs to be called before we start compiling
* a list of folios to be migrated using folio_isolate_lru().
* It drains folios on LRU cache and then disable on all cpus until
* lru_cache_enable is called.
*
* Must be paired with a call to lru_cache_enable().
*/
void lru_cache_disable(void)
{
atomic_inc(&lru_disable_count);
/*
* Readers of lru_disable_count are protected by either disabling
* preemption or rcu_read_lock:
*
* preempt_disable, local_irq_disable [bh_lru_lock()]
* rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT]
* preempt_disable [local_lock !CONFIG_PREEMPT_RT]
*
* Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on
* preempt_disable() regions of code. So any CPU which sees
* lru_disable_count = 0 will have exited the critical
* section when synchronize_rcu() returns.
*/
synchronize_rcu_expedited();
#ifdef CONFIG_SMP
__lru_add_drain_all(true);
#else
lru_add_and_bh_lrus_drain();
#endif
}
/**
* folios_put_refs - Reduce the reference count on a batch of folios.
* @folios: The folios.
* @refs: The number of refs to subtract from each folio.
*
* Like folio_put(), but for a batch of folios. This is more efficient
* than writing the loop yourself as it will optimise the locks which need
* to be taken if the folios are freed. The folios batch is returned
* empty and ready to be reused for another batch; there is no need
* to reinitialise it. If @refs is NULL, we subtract one from each
* folio refcount.
*
* Context: May be called in process or interrupt context, but not in NMI
* context. May be called while holding a spinlock.
*/
void folios_put_refs(struct folio_batch *folios, unsigned int *refs)
{
int i, j;
struct lruvec *lruvec = NULL;
unsigned long flags = 0;
for (i = 0, j = 0; i < folios->nr; i++) {
struct folio *folio = folios->folios[i];
unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio))
continue;
if (folio_is_zone_device(folio)) {
if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags);
lruvec = NULL;
}
if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio);
continue;
}
if (!folio_ref_sub_and_test(folio, nr_refs))
continue;
/* hugetlb has its own memcg */
if (folio_test_hugetlb(folio)) {
if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags);
lruvec = NULL;
}
free_huge_folio(folio);
continue;
}
folio_unqueue_deferred_split(folio);
__page_cache_release(folio, &lruvec, &flags);
if (j != i) folios->folios[j] = folio;
j++;
}
if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) {
folio_batch_reinit(folios);
return;
}
folios->nr = j;
mem_cgroup_uncharge_folios(folios);
free_unref_folios(folios);
}
EXPORT_SYMBOL(folios_put_refs);
/**
* release_pages - batched put_page()
* @arg: array of pages to release
* @nr: number of pages
*
* Decrement the reference count on all the pages in @arg. If it
* fell to zero, remove the page from the LRU and free it.
*
* Note that the argument can be an array of pages, encoded pages,
* or folio pointers. We ignore any encoded bits, and turn any of
* them into just a folio that gets free'd.
*/
void release_pages(release_pages_arg arg, int nr)
{
struct folio_batch fbatch;
int refs[PAGEVEC_SIZE];
struct encoded_page **encoded = arg.encoded_pages;
int i;
folio_batch_init(&fbatch);
for (i = 0; i < nr; i++) {
/* Turn any of the argument types into a folio */
struct folio *folio = page_folio(encoded_page_ptr(encoded[i]));
/* Is our next entry actually "nr_pages" -> "nr_refs" ? */
refs[fbatch.nr] = 1;
if (unlikely(encoded_page_flags(encoded[i]) &
ENCODED_PAGE_BIT_NR_PAGES_NEXT))
refs[fbatch.nr] = encoded_nr_pages(encoded[++i]);
if (folio_batch_add(&fbatch, folio) > 0)
continue;
folios_put_refs(&fbatch, refs);
}
if (fbatch.nr)
folios_put_refs(&fbatch, refs);
}
EXPORT_SYMBOL(release_pages);
/*
* The folios which we're about to release may be in the deferred lru-addition
* queues. That would prevent them from really being freed right now. That's
* OK from a correctness point of view but is inefficient - those folios may be
* cache-warm and we want to give them back to the page allocator ASAP.
*
* So __folio_batch_release() will drain those queues here.
* folio_batch_move_lru() calls folios_put() directly to avoid
* mutual recursion.
*/
void __folio_batch_release(struct folio_batch *fbatch)
{ if (!fbatch->percpu_pvec_drained) { lru_add_drain();
fbatch->percpu_pvec_drained = true;
}
folios_put(fbatch);
}
EXPORT_SYMBOL(__folio_batch_release);
/**
* folio_batch_remove_exceptionals() - Prune non-folios from a batch.
* @fbatch: The batch to prune
*
* find_get_entries() fills a batch with both folios and shadow/swap/DAX
* entries. This function prunes all the non-folio entries from @fbatch
* without leaving holes, so that it can be passed on to folio-only batch
* operations.
*/
void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
{
unsigned int i, j;
for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
if (!xa_is_value(folio)) fbatch->folios[j++] = folio;
}
fbatch->nr = j;
}
static const struct ctl_table swap_sysctl_table[] = {
{
.procname = "page-cluster",
.data = &page_cluster,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = (void *)&page_cluster_max,
}
};
/*
* Perform any setup for the swap system
*/
void __init swap_setup(void)
{
unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT);
/* Use a smaller cluster for small-memory machines */
if (megs < 16)
page_cluster = 2;
else
page_cluster = 3;
/*
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
register_sysctl_init("vm", swap_sysctl_table);
}
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2015 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#ifndef __ARM64_KVM_HYP_SWITCH_H__
#define __ARM64_KVM_HYP_SWITCH_H__
#include <hyp/adjust_pc.h>
#include <hyp/fault.h>
#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <uapi/linux/psci.h>
#include <kvm/arm_psci.h>
#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/extable.h>
#include <asm/kprobes.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
#include <asm/traps.h>
struct kvm_exception_table_entry {
int insn, fixup;
};
extern struct kvm_exception_table_entry __start___kvm_ex_table;
extern struct kvm_exception_table_entry __stop___kvm_ex_table;
/* Save the 32-bit only FPSIMD system register state */
static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
{
if (!vcpu_el1_is_32bit(vcpu))
return;
__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
}
static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
{
/*
* We are about to set CPTR_EL2.TFP to trap all floating point
* register accesses to EL2, however, the ARM ARM clearly states that
* traps are only taken to EL2 if the operation would not otherwise
* trap to EL1. Therefore, always make sure that for 32-bit guests,
* we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
* If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
* it will cause an exception.
*/
if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) { write_sysreg(1 << 30, fpexc32_el2);
isb();
}
}
#define reg_to_fgt_masks(reg) \
({ \
struct fgt_masks *m; \
switch(reg) { \
case HFGRTR_EL2: \
m = &hfgrtr_masks; \
break; \
case HFGWTR_EL2: \
m = &hfgwtr_masks; \
break; \
case HFGITR_EL2: \
m = &hfgitr_masks; \
break; \
case HDFGRTR_EL2: \
m = &hdfgrtr_masks; \
break; \
case HDFGWTR_EL2: \
m = &hdfgwtr_masks; \
break; \
case HAFGRTR_EL2: \
m = &hafgrtr_masks; \
break; \
case HFGRTR2_EL2: \
m = &hfgrtr2_masks; \
break; \
case HFGWTR2_EL2: \
m = &hfgwtr2_masks; \
break; \
case HFGITR2_EL2: \
m = &hfgitr2_masks; \
break; \
case HDFGRTR2_EL2: \
m = &hdfgrtr2_masks; \
break; \
case HDFGWTR2_EL2: \
m = &hdfgwtr2_masks; \
break; \
default: \
BUILD_BUG_ON(1); \
} \
\
m; \
})
#define compute_clr_set(vcpu, reg, clr, set) \
do { \
u64 hfg = __vcpu_sys_reg(vcpu, reg); \
struct fgt_masks *m = reg_to_fgt_masks(reg); \
set |= hfg & m->mask; \
clr |= ~hfg & m->nmask; \
} while(0)
#define reg_to_fgt_group_id(reg) \
({ \
enum fgt_group_id id; \
switch(reg) { \
case HFGRTR_EL2: \
case HFGWTR_EL2: \
id = HFGRTR_GROUP; \
break; \
case HFGITR_EL2: \
id = HFGITR_GROUP; \
break; \
case HDFGRTR_EL2: \
case HDFGWTR_EL2: \
id = HDFGRTR_GROUP; \
break; \
case HAFGRTR_EL2: \
id = HAFGRTR_GROUP; \
break; \
case HFGRTR2_EL2: \
case HFGWTR2_EL2: \
id = HFGRTR2_GROUP; \
break; \
case HFGITR2_EL2: \
id = HFGITR2_GROUP; \
break; \
case HDFGRTR2_EL2: \
case HDFGWTR2_EL2: \
id = HDFGRTR2_GROUP; \
break; \
default: \
BUILD_BUG_ON(1); \
} \
\
id; \
})
#define compute_undef_clr_set(vcpu, kvm, reg, clr, set) \
do { \
u64 hfg = kvm->arch.fgu[reg_to_fgt_group_id(reg)]; \
struct fgt_masks *m = reg_to_fgt_masks(reg); \
set |= hfg & m->mask; \
clr |= hfg & m->nmask; \
} while(0)
#define update_fgt_traps_cs(hctxt, vcpu, kvm, reg, clr, set) \
do { \
struct fgt_masks *m = reg_to_fgt_masks(reg); \
u64 c = clr, s = set; \
u64 val; \
\
ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg); \
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) \
compute_clr_set(vcpu, reg, c, s); \
\
compute_undef_clr_set(vcpu, kvm, reg, c, s); \
\
val = m->nmask; \
val |= s; \
val &= ~c; \
write_sysreg_s(val, SYS_ ## reg); \
} while(0)
#define update_fgt_traps(hctxt, vcpu, kvm, reg) \
update_fgt_traps_cs(hctxt, vcpu, kvm, reg, 0, 0)
static inline bool cpu_has_amu(void)
{
u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
return cpuid_feature_extract_unsigned_field(pfr0,
ID_AA64PFR0_EL1_AMU_SHIFT);
}
static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
struct kvm *kvm = kern_hyp_va(vcpu->kvm);
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
update_fgt_traps(hctxt, vcpu, kvm, HFGRTR_EL2); update_fgt_traps_cs(hctxt, vcpu, kvm, HFGWTR_EL2, 0,
cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) ?
HFGWTR_EL2_TCR_EL1_MASK : 0);
update_fgt_traps(hctxt, vcpu, kvm, HFGITR_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR_EL2); if (cpu_has_amu()) update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2); if (!cpus_have_final_cap(ARM64_HAS_FGT2))
return;
update_fgt_traps(hctxt, vcpu, kvm, HFGRTR2_EL2); update_fgt_traps(hctxt, vcpu, kvm, HFGWTR2_EL2); update_fgt_traps(hctxt, vcpu, kvm, HFGITR2_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR2_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR2_EL2);
}
#define __deactivate_fgt(htcxt, vcpu, reg) \
do { \
write_sysreg_s(ctxt_sys_reg(hctxt, reg), \
SYS_ ## reg); \
} while(0)
static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
__deactivate_fgt(hctxt, vcpu, HFGRTR_EL2); __deactivate_fgt(hctxt, vcpu, HFGWTR_EL2); __deactivate_fgt(hctxt, vcpu, HFGITR_EL2); __deactivate_fgt(hctxt, vcpu, HDFGRTR_EL2); __deactivate_fgt(hctxt, vcpu, HDFGWTR_EL2); if (cpu_has_amu()) __deactivate_fgt(hctxt, vcpu, HAFGRTR_EL2); if (!cpus_have_final_cap(ARM64_HAS_FGT2))
return;
__deactivate_fgt(hctxt, vcpu, HFGRTR2_EL2); __deactivate_fgt(hctxt, vcpu, HFGWTR2_EL2); __deactivate_fgt(hctxt, vcpu, HFGITR2_EL2); __deactivate_fgt(hctxt, vcpu, HDFGRTR2_EL2); __deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2);
}
static inline void __activate_traps_mpam(struct kvm_vcpu *vcpu)
{
u64 r = MPAM2_EL2_TRAPMPAM0EL1 | MPAM2_EL2_TRAPMPAM1EL1;
if (!system_supports_mpam())
return;
/* trap guest access to MPAMIDR_EL1 */
if (system_supports_mpam_hcr()) { write_sysreg_s(MPAMHCR_EL2_TRAP_MPAMIDR_EL1, SYS_MPAMHCR_EL2);
} else {
/* From v1.1 TIDR can trap MPAMIDR, set it unconditionally */
r |= MPAM2_EL2_TIDR;
}
write_sysreg_s(r, SYS_MPAM2_EL2);
}
static inline void __deactivate_traps_mpam(void)
{
if (!system_supports_mpam())
return;
write_sysreg_s(0, SYS_MPAM2_EL2);
if (system_supports_mpam_hcr()) write_sysreg_s(MPAMHCR_HOST_FLAGS, SYS_MPAMHCR_EL2);
}
static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
{
/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
write_sysreg(1 << 15, hstr_el2);
/*
* Make sure we trap PMU access from EL0 to EL2. Also sanitize
* PMSELR_EL0 to make sure it never contains the cycle
* counter, which could make a PMXEVCNTR_EL0 access UNDEF at
* EL1 instead of being trapped to EL2.
*/
if (system_supports_pmuv3()) {
struct kvm_cpu_context *hctxt;
write_sysreg(0, pmselr_el0);
hctxt = host_data_ptr(host_ctxt);
ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
}
*host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2);
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
if (cpus_have_final_cap(ARM64_HAS_HCX)) {
u64 hcrx = vcpu->arch.hcrx_el2;
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2);
hcrx |= val & __HCRX_EL2_MASK;
hcrx &= ~(~val & __HCRX_EL2_nMASK);
}
write_sysreg_s(hcrx, SYS_HCRX_EL2);
}
__activate_traps_hfgxtr(vcpu); __activate_traps_mpam(vcpu);
}
static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
{
write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
write_sysreg(0, hstr_el2);
if (system_supports_pmuv3()) {
struct kvm_cpu_context *hctxt;
hctxt = host_data_ptr(host_ctxt);
write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
}
if (cpus_have_final_cap(ARM64_HAS_HCX)) write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2); __deactivate_traps_hfgxtr(vcpu); __deactivate_traps_mpam();
}
static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
{
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
hcr |= HCR_TVM;
write_sysreg_hcr(hcr); if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
}
static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
{
/*
* If we pended a virtual abort, preserve it until it gets
* cleared. See D1.14.3 (Virtual Interrupts) for details, but
* the crucial bit is "On taking a vSError interrupt,
* HCR_EL2.VSE is cleared to 0."
*/
if (vcpu->arch.hcr_el2 & HCR_VSE) { vcpu->arch.hcr_el2 &= ~HCR_VSE;
vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
}
}
static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
{
return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
}
static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
{
*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2);
write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
/*
* Finish potential single step before executing the prologue
* instruction.
*/
*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
return true;
}
static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
{
/*
* The vCPU's saved SVE state layout always matches the max VL of the
* vCPU. Start off with the max VL so we can load the SVE state.
*/
sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
__sve_restore_state(vcpu_sve_pffr(vcpu),
&vcpu->arch.ctxt.fp_regs.fpsr,
true);
/*
* The effective VL for a VM could differ from the max VL when running a
* nested guest, as the guest hypervisor could select a smaller VL. Slap
* that into hardware before wrapping up.
*/
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);
write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR);
}
static inline void __hyp_sve_save_host(void)
{
struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2);
__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
&sve_state->fpsr,
true);
}
static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
{
u64 zcr_el1, zcr_el2;
if (!guest_owns_fp_regs())
return;
if (vcpu_has_sve(vcpu)) {
/* A guest hypervisor may restrict the effective max VL. */
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2);
else
zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu));
write_sysreg_el1(zcr_el1, SYS_ZCR);
}
}
static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
{
u64 zcr_el1, zcr_el2;
if (!guest_owns_fp_regs())
return;
/*
* When the guest owns the FP regs, we know that guest+hyp traps for
* any FPSIMD/SVE/SME features exposed to the guest have been disabled
* by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
* prior to __guest_entry(). As __guest_entry() guarantees a context
* synchronization event, we don't need an ISB here to avoid taking
* traps for anything that was exposed to the guest.
*/
if (vcpu_has_sve(vcpu)) {
zcr_el1 = read_sysreg_el1(SYS_ZCR);
__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
/*
* The guest's state is always saved using the guest's max VL.
* Ensure that the host has the guest's max VL active such that
* the host can save the guest's state lazily, but don't
* artificially restrict the host to the guest's max VL.
*/
if (has_vhe()) {
zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
} else {
zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
zcr_el1 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el1(zcr_el1, SYS_ZCR);
}
}
}
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
{
/*
* Non-protected kvm relies on the host restoring its sve state.
* Protected kvm restores the host's sve state as not to reveal that
* fpsimd was used by a guest nor leak upper sve bits.
*/
if (system_supports_sve()) {
__hyp_sve_save_host();
/* Re-enable SVE traps if not supported for the guest vcpu. */
if (!vcpu_has_sve(vcpu))
cpacr_clear_set(CPACR_EL1_ZEN, 0);
} else {
__fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs));
}
if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm)))
*host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR);
}
/*
* We trap the first access to the FP/SIMD to save the host context and
* restore the guest context lazily.
* If FP/SIMD is not implemented, handle the trap and inject an undefined
* instruction exception to the guest. Similarly for trapped SVE accesses.
*/
static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
{
bool sve_guest;
u8 esr_ec;
if (!system_supports_fpsimd())
return false;
sve_guest = vcpu_has_sve(vcpu);
esr_ec = kvm_vcpu_trap_get_class(vcpu);
/* Only handle traps the vCPU can support here: */
switch (esr_ec) {
case ESR_ELx_EC_FP_ASIMD:
/* Forward traps to the guest hypervisor as required */
if (guest_hyp_fpsimd_traps_enabled(vcpu))
return false;
break;
case ESR_ELx_EC_SYS64:
if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu)))
return false;
fallthrough;
case ESR_ELx_EC_SVE:
if (!sve_guest)
return false;
if (guest_hyp_sve_traps_enabled(vcpu))
return false;
break;
default:
return false;
}
/* Valid trap. Switch the context: */
/* First disable enough traps to allow us to update the registers */
if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN);
else
cpacr_clear_set(0, CPACR_EL1_FPEN);
isb();
/* Write out the host state if it's in the registers */
if (is_protected_kvm_enabled() && host_owns_fp_regs())
kvm_hyp_save_fpsimd_host(vcpu);
/* Restore the guest state */
if (sve_guest)
__hyp_sve_restore_guest(vcpu);
else
__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm)))
write_sysreg_s(__vcpu_sys_reg(vcpu, FPMR), SYS_FPMR);
/* Skip restoring fpexc32 for AArch64 guests */
if (!(read_sysreg(hcr_el2) & HCR_RW))
write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
*host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED;
return true;
}
static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
{
u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
int rt = kvm_vcpu_sys_get_rt(vcpu);
u64 val = vcpu_get_reg(vcpu, rt);
/*
* The normal sysreg handling code expects to see the traps,
* let's not do anything here.
*/
if (vcpu->arch.hcr_el2 & HCR_TVM)
return false;
switch (sysreg) {
case SYS_SCTLR_EL1:
write_sysreg_el1(val, SYS_SCTLR);
break;
case SYS_TTBR0_EL1:
write_sysreg_el1(val, SYS_TTBR0);
break;
case SYS_TTBR1_EL1:
write_sysreg_el1(val, SYS_TTBR1);
break;
case SYS_TCR_EL1:
write_sysreg_el1(val, SYS_TCR);
break;
case SYS_ESR_EL1:
write_sysreg_el1(val, SYS_ESR);
break;
case SYS_FAR_EL1:
write_sysreg_el1(val, SYS_FAR);
break;
case SYS_AFSR0_EL1:
write_sysreg_el1(val, SYS_AFSR0);
break;
case SYS_AFSR1_EL1:
write_sysreg_el1(val, SYS_AFSR1);
break;
case SYS_MAIR_EL1:
write_sysreg_el1(val, SYS_MAIR);
break;
case SYS_AMAIR_EL1:
write_sysreg_el1(val, SYS_AMAIR);
break;
case SYS_CONTEXTIDR_EL1:
write_sysreg_el1(val, SYS_CONTEXTIDR);
break;
default:
return false;
}
__kvm_skip_instr(vcpu);
return true;
}
/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */
static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt)
{
u64 offset = 0;
if (ctxt->offset.vm_offset) offset += *kern_hyp_va(ctxt->offset.vm_offset); if (ctxt->offset.vcpu_offset) offset += *kern_hyp_va(ctxt->offset.vcpu_offset);
return offset;
}
static inline u64 compute_counter_value(struct arch_timer_context *ctxt)
{
return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt);
}
static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *ctxt;
u32 sysreg;
u64 val;
/*
* We only get here for 64bit guests, 32bit guests will hit
* the long and winding road all the way to the standard
* handling. Yes, it sucks to be irrelevant.
*
* Also, we only deal with non-hypervisor context here (either
* an EL1 guest, or a non-HYP context of an EL2 guest).
*/
if (is_hyp_ctxt(vcpu))
return false;
sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
switch (sysreg) {
case SYS_CNTPCT_EL0:
case SYS_CNTPCTSS_EL0:
if (vcpu_has_nv(vcpu)) {
/* Check for guest hypervisor trapping */
val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); if (!vcpu_el2_e2h_is_set(vcpu))
val = (val & CNTHCTL_EL1PCTEN) << 10;
if (!(val & (CNTHCTL_EL1PCTEN << 10)))
return false;
}
ctxt = vcpu_ptimer(vcpu);
break;
case SYS_CNTVCT_EL0:
case SYS_CNTVCTSS_EL0:
if (vcpu_has_nv(vcpu)) {
/* Check for guest hypervisor trapping */
val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); if (val & CNTHCTL_EL1TVCT)
return false;
}
ctxt = vcpu_vtimer(vcpu);
break;
default:
return false;
}
val = compute_counter_value(ctxt); vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); __kvm_skip_instr(vcpu);
return true;
}
static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu)
{
u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
int rt = kvm_vcpu_sys_get_rt(vcpu);
u64 val = vcpu_get_reg(vcpu, rt); if (sysreg != SYS_TCR_EL1)
return false;
/*
* Affected parts do not advertise support for hardware Access Flag /
* Dirty state management in ID_AA64MMFR1_EL1.HAFDBS, but the underlying
* control bits are still functional. The architecture requires these be
* RES0 on systems that do not implement FEAT_HAFDBS.
*
* Uphold the requirements of the architecture by masking guest writes
* to TCR_EL1.{HA,HD} here.
*/
val &= ~(TCR_HD | TCR_HA);
write_sysreg_el1(val, SYS_TCR);
__kvm_skip_instr(vcpu);
return true;
}
static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
{
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && handle_tx2_tvm(vcpu))
return true;
if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) && handle_ampere1_tcr(vcpu))
return true;
if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
__vgic_v3_perform_cpuif_access(vcpu) == 1)
return true;
if (kvm_handle_cntxct(vcpu))
return true;
return false;
}
static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
{ if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
__vgic_v3_perform_cpuif_access(vcpu) == 1)
return true;
return false;
}
static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu,
u64 *exit_code)
{ if (!__populate_fault_info(vcpu))
return true;
return false;
}
#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault
#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault
static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
{ if (kvm_hyp_handle_memory_fault(vcpu, exit_code))
return true;
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
valid = kvm_vcpu_trap_is_translation_fault(vcpu) && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
if (valid) {
int ret = __vgic_v2_perform_cpuif_access(vcpu);
if (ret == 1)
return true;
/* Promote an illegal access to an SError.*/
if (ret == -1)
*exit_code = ARM_EXCEPTION_EL1_SERROR;
}
}
return false;
}
typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
/*
* Allow the hypervisor to handle the exit with an exit handler if it has one.
*
* Returns true if the hypervisor handled the exit, and control should go back
* to the guest, or false if it hasn't.
*/
static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
const exit_handler_fn *handlers)
{
exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
if (fn)
return fn(vcpu, exit_code);
return false;
}
static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code)
{
/*
* Check for the conditions of Cortex-A510's #2077057. When these occur
* SPSR_EL2 can't be trusted, but isn't needed either as it is
* unchanged from the value in vcpu_gp_regs(vcpu)->pstate.
* Are we single-stepping the guest, and took a PAC exception from the
* active-not-pending state?
*/
if (cpus_have_final_cap(ARM64_WORKAROUND_2077057) && vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && *vcpu_cpsr(vcpu) & DBG_SPSR_SS &&
ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC)
write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
}
/*
* Return true when we were able to fixup the guest exit and should return to
* the guest, false when we should restore the host state and return to the
* main run loop.
*/
static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
const exit_handler_fn *handlers)
{
if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); if (ARM_SERROR_PENDING(*exit_code) &&
ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) {
u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
/*
* HVC already have an adjusted PC, which we need to
* correct in order to return to after having injected
* the SError.
*
* SMC, on the other hand, is *trapped*, meaning its
* preferred return address is the SMC itself.
*/
if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64)
write_sysreg_el2(read_sysreg_el2(SYS_ELR) - 4, SYS_ELR);
}
/*
* We're using the raw exception code in order to only process
* the trap if no SError is pending. We will come back to the
* same PC once the SError has been injected, and replay the
* trapping instruction.
*/
if (*exit_code != ARM_EXCEPTION_TRAP)
goto exit;
/* Check if there's an exit handler and allow it to handle the exit. */
if (kvm_hyp_handle_exit(vcpu, exit_code, handlers))
goto guest;
exit:
/* Return to the host kernel and handle the exit */
return false;
guest:
/* Re-enter the guest */
asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412));
return true;
}
static inline void __kvm_unexpected_el2_exception(void)
{
extern char __guest_exit_restore_elr_and_panic[];
unsigned long addr, fixup;
struct kvm_exception_table_entry *entry, *end;
unsigned long elr_el2 = read_sysreg(elr_el2);
entry = &__start___kvm_ex_table;
end = &__stop___kvm_ex_table;
while (entry < end) {
addr = (unsigned long)&entry->insn + entry->insn;
fixup = (unsigned long)&entry->fixup + entry->fixup;
if (addr != elr_el2) {
entry++;
continue;
}
write_sysreg(fixup, elr_el2);
return;
}
/* Trigger a panic after restoring the hyp context. */
this_cpu_ptr(&kvm_hyp_ctxt)->sys_regs[ELR_EL2] = elr_el2;
write_sysreg(__guest_exit_restore_elr_and_panic, elr_el2);
}
#endif /* __ARM64_KVM_HYP_SWITCH_H__ */